{"current_steps": 100, "total_steps": 761865, "loss": 1.9557, "lr": 9.999999655665828e-07, "epoch": 0.001968852749502865, "percentage": 0.01, "elapsed_time": "0:00:11", "remaining_time": "1 day, 1:15:02", "throughput": 8581.1, "total_tokens": 102400} {"current_steps": 200, "total_steps": 761865, "loss": 2.0835, "lr": 9.999998465374926e-07, "epoch": 0.00393770549900573, "percentage": 0.03, "elapsed_time": "0:00:23", "remaining_time": "1 day, 0:48:29", "throughput": 8631.38, "total_tokens": 202416} {"current_steps": 300, "total_steps": 761865, "loss": 1.9022, "lr": 9.999996424876457e-07, "epoch": 0.005906558248508594, "percentage": 0.04, "elapsed_time": "0:00:35", "remaining_time": "1 day, 0:46:34", "throughput": 8675.32, "total_tokens": 304816} {"current_steps": 400, "total_steps": 761865, "loss": 1.9903, "lr": 9.99999353417077e-07, "epoch": 0.00787541099801146, "percentage": 0.05, "elapsed_time": "0:00:46", "remaining_time": "1 day, 0:47:40", "throughput": 8684.74, "total_tokens": 407216} {"current_steps": 500, "total_steps": 761865, "loss": 1.9607, "lr": 9.999989793258351e-07, "epoch": 0.009844263747514324, "percentage": 0.07, "elapsed_time": "0:00:58", "remaining_time": "1 day, 0:51:45", "throughput": 8665.7, "total_tokens": 509368} {"current_steps": 600, "total_steps": 761865, "loss": 1.9747, "lr": 9.999985202139843e-07, "epoch": 0.011813116497017188, "percentage": 0.08, "elapsed_time": "0:01:10", "remaining_time": "1 day, 0:53:07", "throughput": 8655.36, "total_tokens": 611152} {"current_steps": 700, "total_steps": 761865, "loss": 1.9834, "lr": 9.99997976081602e-07, "epoch": 0.013781969246520052, "percentage": 0.09, "elapsed_time": "0:01:22", "remaining_time": "1 day, 0:50:19", "throughput": 8661.93, "total_tokens": 712304} {"current_steps": 800, "total_steps": 761865, "loss": 1.9282, "lr": 9.999973469287812e-07, "epoch": 0.01575082199602292, "percentage": 0.11, "elapsed_time": "0:01:33", "remaining_time": "1 day, 0:48:35", "throughput": 8670.61, "total_tokens": 814040} {"current_steps": 900, "total_steps": 761865, "loss": 1.9803, "lr": 9.999966327556286e-07, "epoch": 0.01771967474552578, "percentage": 0.12, "elapsed_time": "0:01:45", "remaining_time": "1 day, 0:46:54", "throughput": 8675.3, "total_tokens": 915376} {"current_steps": 1000, "total_steps": 761865, "loss": 2.0006, "lr": 9.99995833562266e-07, "epoch": 0.019688527495028647, "percentage": 0.13, "elapsed_time": "0:01:57", "remaining_time": "1 day, 0:46:29", "throughput": 8682.51, "total_tokens": 1017776} {"current_steps": 1100, "total_steps": 761865, "loss": 2.0001, "lr": 9.999949493488289e-07, "epoch": 0.02165738024453151, "percentage": 0.14, "elapsed_time": "0:02:08", "remaining_time": "1 day, 0:46:17", "throughput": 8687.4, "total_tokens": 1120176} {"current_steps": 1200, "total_steps": 761865, "loss": 2.0123, "lr": 9.999939801154677e-07, "epoch": 0.023626232994034376, "percentage": 0.16, "elapsed_time": "0:02:20", "remaining_time": "1 day, 0:46:25", "throughput": 8685.26, "total_tokens": 1221976} {"current_steps": 1300, "total_steps": 761865, "loss": 1.9841, "lr": 9.999929258623475e-07, "epoch": 0.025595085743537242, "percentage": 0.17, "elapsed_time": "0:02:32", "remaining_time": "1 day, 0:50:34", "throughput": 8663.65, "total_tokens": 1324376} {"current_steps": 1400, "total_steps": 761865, "loss": 1.9815, "lr": 9.999917865896474e-07, "epoch": 0.027563938493040105, "percentage": 0.18, "elapsed_time": "0:02:44", "remaining_time": "1 day, 0:53:09", "throughput": 8642.86, "total_tokens": 1425480} {"current_steps": 1500, "total_steps": 761865, "loss": 2.0264, "lr": 9.99990562297561e-07, "epoch": 0.02953279124254297, "percentage": 0.2, "elapsed_time": "0:02:56", "remaining_time": "1 day, 0:54:58", "throughput": 8621.07, "total_tokens": 1525512} {"current_steps": 1600, "total_steps": 761865, "loss": 2.0026, "lr": 9.999892529862967e-07, "epoch": 0.03150164399204584, "percentage": 0.21, "elapsed_time": "0:03:09", "remaining_time": "1 day, 0:57:49", "throughput": 8607.26, "total_tokens": 1627912} {"current_steps": 1700, "total_steps": 761865, "loss": 2.0291, "lr": 9.999878586560772e-07, "epoch": 0.0334704967415487, "percentage": 0.22, "elapsed_time": "0:03:21", "remaining_time": "1 day, 0:59:32", "throughput": 8591.97, "total_tokens": 1728800} {"current_steps": 1800, "total_steps": 761865, "loss": 2.0356, "lr": 9.999863793071392e-07, "epoch": 0.03543934949105156, "percentage": 0.24, "elapsed_time": "0:03:33", "remaining_time": "1 day, 1:00:54", "throughput": 8575.16, "total_tokens": 1828824} {"current_steps": 1900, "total_steps": 761865, "loss": 1.9708, "lr": 9.999848149397345e-07, "epoch": 0.03740820224055443, "percentage": 0.25, "elapsed_time": "0:03:45", "remaining_time": "1 day, 1:02:21", "throughput": 8563.67, "total_tokens": 1929944} {"current_steps": 2000, "total_steps": 761865, "loss": 1.969, "lr": 9.999831655541291e-07, "epoch": 0.039377054990057295, "percentage": 0.26, "elapsed_time": "0:03:57", "remaining_time": "1 day, 1:04:19", "throughput": 8554.42, "total_tokens": 2032256} {"current_steps": 2100, "total_steps": 761865, "loss": 1.9973, "lr": 9.999814311506033e-07, "epoch": 0.04134590773956016, "percentage": 0.28, "elapsed_time": "0:04:09", "remaining_time": "1 day, 1:05:59", "throughput": 8547.0, "total_tokens": 2134656} {"current_steps": 2200, "total_steps": 761865, "loss": 1.9728, "lr": 9.999796117294525e-07, "epoch": 0.04331476048906302, "percentage": 0.29, "elapsed_time": "0:04:21", "remaining_time": "1 day, 1:07:30", "throughput": 8540.1, "total_tokens": 2237056} {"current_steps": 2300, "total_steps": 761865, "loss": 1.9541, "lr": 9.999777072909855e-07, "epoch": 0.04528361323856589, "percentage": 0.3, "elapsed_time": "0:04:34", "remaining_time": "1 day, 1:08:38", "throughput": 8532.46, "total_tokens": 2338688} {"current_steps": 2400, "total_steps": 761865, "loss": 1.9632, "lr": 9.999757178355265e-07, "epoch": 0.04725246598806875, "percentage": 0.32, "elapsed_time": "0:04:46", "remaining_time": "1 day, 1:09:50", "throughput": 8527.07, "total_tokens": 2441088} {"current_steps": 2500, "total_steps": 761865, "loss": 2.0193, "lr": 9.999736433634135e-07, "epoch": 0.049221318737571615, "percentage": 0.33, "elapsed_time": "0:04:58", "remaining_time": "1 day, 1:10:57", "throughput": 8521.94, "total_tokens": 2543488} {"current_steps": 2600, "total_steps": 761865, "loss": 1.9967, "lr": 9.999714838749996e-07, "epoch": 0.051190171487074485, "percentage": 0.34, "elapsed_time": "0:05:10", "remaining_time": "1 day, 1:11:53", "throughput": 8516.9, "total_tokens": 2645664} {"current_steps": 2700, "total_steps": 761865, "loss": 1.9902, "lr": 9.999692393706517e-07, "epoch": 0.05315902423657735, "percentage": 0.35, "elapsed_time": "0:05:22", "remaining_time": "1 day, 1:12:48", "throughput": 8512.64, "total_tokens": 2748064} {"current_steps": 2800, "total_steps": 761865, "loss": 1.9793, "lr": 9.999669098507517e-07, "epoch": 0.05512787698608021, "percentage": 0.37, "elapsed_time": "0:05:35", "remaining_time": "1 day, 1:13:39", "throughput": 8508.55, "total_tokens": 2850464} {"current_steps": 2900, "total_steps": 761865, "loss": 2.0275, "lr": 9.999644953156955e-07, "epoch": 0.05709672973558307, "percentage": 0.38, "elapsed_time": "0:05:47", "remaining_time": "1 day, 1:14:10", "throughput": 8503.88, "total_tokens": 2952040} {"current_steps": 3000, "total_steps": 761865, "loss": 1.9634, "lr": 9.999619957658938e-07, "epoch": 0.05906558248508594, "percentage": 0.39, "elapsed_time": "0:05:59", "remaining_time": "1 day, 1:14:51", "throughput": 8500.65, "total_tokens": 3054440} {"current_steps": 3100, "total_steps": 761865, "loss": 2.0436, "lr": 9.999594112017717e-07, "epoch": 0.061034435234588805, "percentage": 0.41, "elapsed_time": "0:06:11", "remaining_time": "1 day, 1:15:16", "throughput": 8496.43, "total_tokens": 3155968} {"current_steps": 3200, "total_steps": 761865, "loss": 2.0317, "lr": 9.999567416237685e-07, "epoch": 0.06300328798409167, "percentage": 0.42, "elapsed_time": "0:06:23", "remaining_time": "1 day, 1:15:29", "throughput": 8491.68, "total_tokens": 3256848} {"current_steps": 3300, "total_steps": 761865, "loss": 1.9925, "lr": 9.99953987032338e-07, "epoch": 0.06497214073359453, "percentage": 0.43, "elapsed_time": "0:06:35", "remaining_time": "1 day, 1:16:04", "throughput": 8488.39, "total_tokens": 3359048} {"current_steps": 3400, "total_steps": 761865, "loss": 2.0083, "lr": 9.99951147427949e-07, "epoch": 0.0669409934830974, "percentage": 0.45, "elapsed_time": "0:06:47", "remaining_time": "1 day, 1:16:06", "throughput": 8484.65, "total_tokens": 3459880} {"current_steps": 3500, "total_steps": 761865, "loss": 1.9774, "lr": 9.999482228110844e-07, "epoch": 0.06890984623260027, "percentage": 0.46, "elapsed_time": "0:06:59", "remaining_time": "1 day, 1:16:25", "throughput": 8481.28, "total_tokens": 3561432} {"current_steps": 3600, "total_steps": 761865, "loss": 2.0003, "lr": 9.99945213182241e-07, "epoch": 0.07087869898210312, "percentage": 0.47, "elapsed_time": "0:07:12", "remaining_time": "1 day, 1:16:57", "throughput": 8478.74, "total_tokens": 3663832} {"current_steps": 3700, "total_steps": 761865, "loss": 2.0152, "lr": 9.999421185419309e-07, "epoch": 0.072847551731606, "percentage": 0.49, "elapsed_time": "0:07:24", "remaining_time": "1 day, 1:17:16", "throughput": 8475.55, "total_tokens": 3765496} {"current_steps": 3800, "total_steps": 761865, "loss": 1.9871, "lr": 9.9993893889068e-07, "epoch": 0.07481640448110886, "percentage": 0.5, "elapsed_time": "0:07:36", "remaining_time": "1 day, 1:17:28", "throughput": 8472.65, "total_tokens": 3866968} {"current_steps": 3900, "total_steps": 761865, "loss": 1.9997, "lr": 9.999356742290296e-07, "epoch": 0.07678525723061172, "percentage": 0.51, "elapsed_time": "0:07:48", "remaining_time": "1 day, 1:17:39", "throughput": 8470.53, "total_tokens": 3968728} {"current_steps": 4000, "total_steps": 761865, "loss": 1.9609, "lr": 9.999323245575343e-07, "epoch": 0.07875410998011459, "percentage": 0.53, "elapsed_time": "0:08:00", "remaining_time": "1 day, 1:18:02", "throughput": 8468.6, "total_tokens": 4071128} {"current_steps": 4100, "total_steps": 761865, "loss": 2.0073, "lr": 9.999288898767638e-07, "epoch": 0.08072296272961745, "percentage": 0.54, "elapsed_time": "0:08:12", "remaining_time": "1 day, 1:18:10", "throughput": 8466.85, "total_tokens": 4172968} {"current_steps": 4200, "total_steps": 761865, "loss": 1.9616, "lr": 9.999253701873024e-07, "epoch": 0.08269181547912031, "percentage": 0.55, "elapsed_time": "0:08:25", "remaining_time": "1 day, 1:18:29", "throughput": 8465.17, "total_tokens": 4275368} {"current_steps": 4300, "total_steps": 761865, "loss": 1.976, "lr": 9.999217654897481e-07, "epoch": 0.08466066822862318, "percentage": 0.56, "elapsed_time": "0:08:37", "remaining_time": "1 day, 1:18:44", "throughput": 8463.87, "total_tokens": 4377768} {"current_steps": 4400, "total_steps": 761865, "loss": 1.9941, "lr": 9.999180757847142e-07, "epoch": 0.08662952097812604, "percentage": 0.58, "elapsed_time": "0:08:49", "remaining_time": "1 day, 1:18:44", "throughput": 8461.13, "total_tokens": 4478712} {"current_steps": 4500, "total_steps": 761865, "loss": 1.981, "lr": 9.999143010728277e-07, "epoch": 0.08859837372762891, "percentage": 0.59, "elapsed_time": "0:09:01", "remaining_time": "1 day, 1:18:58", "throughput": 8459.87, "total_tokens": 4581112} {"current_steps": 4600, "total_steps": 761865, "loss": 1.9281, "lr": 9.999104413547313e-07, "epoch": 0.09056722647713178, "percentage": 0.6, "elapsed_time": "0:09:13", "remaining_time": "1 day, 1:19:11", "throughput": 8458.62, "total_tokens": 4683512} {"current_steps": 4700, "total_steps": 761865, "loss": 2.0088, "lr": 9.999064966310804e-07, "epoch": 0.09253607922663463, "percentage": 0.62, "elapsed_time": "0:09:25", "remaining_time": "1 day, 1:19:13", "throughput": 8456.84, "total_tokens": 4785088} {"current_steps": 4800, "total_steps": 761865, "loss": 2.0149, "lr": 9.999024669025464e-07, "epoch": 0.0945049319761375, "percentage": 0.63, "elapsed_time": "0:09:37", "remaining_time": "1 day, 1:19:15", "throughput": 8455.48, "total_tokens": 4886864} {"current_steps": 4900, "total_steps": 761865, "loss": 2.034, "lr": 9.998983521698141e-07, "epoch": 0.09647378472564037, "percentage": 0.64, "elapsed_time": "0:09:50", "remaining_time": "1 day, 1:19:26", "throughput": 8454.39, "total_tokens": 4989264} {"current_steps": 5000, "total_steps": 761865, "loss": 1.9854, "lr": 9.998941524335834e-07, "epoch": 0.09844263747514323, "percentage": 0.66, "elapsed_time": "0:10:02", "remaining_time": "1 day, 1:19:37", "throughput": 8453.19, "total_tokens": 5091664} {"current_steps": 5100, "total_steps": 761865, "loss": 1.9672, "lr": 9.998898676945684e-07, "epoch": 0.1004114902246461, "percentage": 0.67, "elapsed_time": "0:10:14", "remaining_time": "1 day, 1:20:41", "throughput": 8444.09, "total_tokens": 5192240} {"current_steps": 5200, "total_steps": 761865, "loss": 1.9863, "lr": 9.998854979534977e-07, "epoch": 0.10238034297414897, "percentage": 0.68, "elapsed_time": "0:10:27", "remaining_time": "1 day, 1:20:38", "throughput": 8443.05, "total_tokens": 5293912} {"current_steps": 5300, "total_steps": 761865, "loss": 1.9907, "lr": 9.998810432111144e-07, "epoch": 0.10434919572365182, "percentage": 0.7, "elapsed_time": "0:10:39", "remaining_time": "1 day, 1:20:39", "throughput": 8441.59, "total_tokens": 5395552} {"current_steps": 5400, "total_steps": 761865, "loss": 2.031, "lr": 9.998765034681758e-07, "epoch": 0.1063180484731547, "percentage": 0.71, "elapsed_time": "0:10:51", "remaining_time": "1 day, 1:20:34", "throughput": 8440.13, "total_tokens": 5496816} {"current_steps": 5500, "total_steps": 761865, "loss": 1.9305, "lr": 9.998718787254539e-07, "epoch": 0.10828690122265756, "percentage": 0.72, "elapsed_time": "0:11:03", "remaining_time": "1 day, 1:20:33", "throughput": 8439.32, "total_tokens": 5598768} {"current_steps": 5600, "total_steps": 761865, "loss": 1.9867, "lr": 9.99867168983735e-07, "epoch": 0.11025575397216042, "percentage": 0.74, "elapsed_time": "0:11:15", "remaining_time": "1 day, 1:20:38", "throughput": 8438.61, "total_tokens": 5701168} {"current_steps": 5700, "total_steps": 761865, "loss": 1.9319, "lr": 9.998623742438202e-07, "epoch": 0.11222460672166329, "percentage": 0.75, "elapsed_time": "0:11:27", "remaining_time": "1 day, 1:20:43", "throughput": 8437.88, "total_tokens": 5803568} {"current_steps": 5800, "total_steps": 761865, "loss": 1.9946, "lr": 9.998574945065248e-07, "epoch": 0.11419345947116614, "percentage": 0.76, "elapsed_time": "0:11:40", "remaining_time": "1 day, 1:20:49", "throughput": 8437.06, "total_tokens": 5905968} {"current_steps": 5900, "total_steps": 761865, "loss": 1.938, "lr": 9.998525297726783e-07, "epoch": 0.11616231222066901, "percentage": 0.77, "elapsed_time": "0:11:52", "remaining_time": "1 day, 1:20:55", "throughput": 8436.21, "total_tokens": 6008368} {"current_steps": 6000, "total_steps": 761865, "loss": 2.0306, "lr": 9.998474800431252e-07, "epoch": 0.11813116497017188, "percentage": 0.79, "elapsed_time": "0:12:04", "remaining_time": "1 day, 1:20:45", "throughput": 8434.59, "total_tokens": 6109176} {"current_steps": 6100, "total_steps": 761865, "loss": 1.9941, "lr": 9.99842345318724e-07, "epoch": 0.12010001771967474, "percentage": 0.8, "elapsed_time": "0:12:16", "remaining_time": "1 day, 1:20:44", "throughput": 8433.25, "total_tokens": 6210776} {"current_steps": 6200, "total_steps": 761865, "loss": 1.9467, "lr": 9.998371256003478e-07, "epoch": 0.12206887046917761, "percentage": 0.81, "elapsed_time": "0:12:28", "remaining_time": "1 day, 1:20:40", "throughput": 8432.31, "total_tokens": 6312432} {"current_steps": 6300, "total_steps": 761865, "loss": 2.0164, "lr": 9.998318208888844e-07, "epoch": 0.12403772321868048, "percentage": 0.83, "elapsed_time": "0:12:40", "remaining_time": "1 day, 1:20:30", "throughput": 8431.02, "total_tokens": 6413424} {"current_steps": 6400, "total_steps": 761865, "loss": 1.9963, "lr": 9.998264311852353e-07, "epoch": 0.12600657596818335, "percentage": 0.84, "elapsed_time": "0:12:52", "remaining_time": "1 day, 1:20:29", "throughput": 8430.03, "total_tokens": 6515200} {"current_steps": 6500, "total_steps": 761865, "loss": 1.9512, "lr": 9.998209564903175e-07, "epoch": 0.1279754287176862, "percentage": 0.85, "elapsed_time": "0:13:05", "remaining_time": "1 day, 1:20:25", "throughput": 8429.05, "total_tokens": 6616832} {"current_steps": 6600, "total_steps": 761865, "loss": 2.0194, "lr": 9.998153968050617e-07, "epoch": 0.12994428146718906, "percentage": 0.87, "elapsed_time": "0:13:17", "remaining_time": "1 day, 1:20:26", "throughput": 8428.55, "total_tokens": 6719232} {"current_steps": 6700, "total_steps": 761865, "loss": 1.9661, "lr": 9.998097521304132e-07, "epoch": 0.13191313421669193, "percentage": 0.88, "elapsed_time": "0:13:29", "remaining_time": "1 day, 1:20:27", "throughput": 8428.12, "total_tokens": 6821632} {"current_steps": 6800, "total_steps": 761865, "loss": 2.0127, "lr": 9.998040224673321e-07, "epoch": 0.1338819869661948, "percentage": 0.89, "elapsed_time": "0:13:41", "remaining_time": "1 day, 1:20:30", "throughput": 8427.41, "total_tokens": 6924032} {"current_steps": 6900, "total_steps": 761865, "loss": 1.9279, "lr": 9.997982078167925e-07, "epoch": 0.13585083971569767, "percentage": 0.91, "elapsed_time": "0:13:53", "remaining_time": "1 day, 1:20:25", "throughput": 8426.8, "total_tokens": 7025856} {"current_steps": 7000, "total_steps": 761865, "loss": 2.0707, "lr": 9.997923081797832e-07, "epoch": 0.13781969246520054, "percentage": 0.92, "elapsed_time": "0:14:05", "remaining_time": "1 day, 1:20:20", "throughput": 8426.09, "total_tokens": 7127656} {"current_steps": 7100, "total_steps": 761865, "loss": 1.9551, "lr": 9.997863235573072e-07, "epoch": 0.13978854521470338, "percentage": 0.93, "elapsed_time": "0:14:18", "remaining_time": "1 day, 1:20:20", "throughput": 8425.67, "total_tokens": 7230056} {"current_steps": 7200, "total_steps": 761865, "loss": 1.9781, "lr": 9.997802539503824e-07, "epoch": 0.14175739796420625, "percentage": 0.95, "elapsed_time": "0:14:30", "remaining_time": "1 day, 1:20:05", "throughput": 8425.72, "total_tokens": 7331696} {"current_steps": 7300, "total_steps": 761865, "loss": 2.0103, "lr": 9.997740993600406e-07, "epoch": 0.14372625071370912, "percentage": 0.96, "elapsed_time": "0:14:41", "remaining_time": "1 day, 1:19:10", "throughput": 8429.6, "total_tokens": 7433472} {"current_steps": 7400, "total_steps": 761865, "loss": 2.0444, "lr": 9.997678597873285e-07, "epoch": 0.145695103463212, "percentage": 0.97, "elapsed_time": "0:14:53", "remaining_time": "1 day, 1:18:13", "throughput": 8433.09, "total_tokens": 7534736} {"current_steps": 7500, "total_steps": 761865, "loss": 1.9925, "lr": 9.997615352333072e-07, "epoch": 0.14766395621271486, "percentage": 0.98, "elapsed_time": "0:15:05", "remaining_time": "1 day, 1:17:34", "throughput": 8436.28, "total_tokens": 7637136} {"current_steps": 7600, "total_steps": 761865, "loss": 1.9466, "lr": 9.99755125699052e-07, "epoch": 0.14963280896221773, "percentage": 1.0, "elapsed_time": "0:15:17", "remaining_time": "1 day, 1:17:16", "throughput": 8437.4, "total_tokens": 7739536} {"current_steps": 7700, "total_steps": 761865, "loss": 1.9693, "lr": 9.99748631185653e-07, "epoch": 0.15160166171172057, "percentage": 1.01, "elapsed_time": "0:15:29", "remaining_time": "1 day, 1:17:11", "throughput": 8437.07, "total_tokens": 7841640} {"current_steps": 7800, "total_steps": 761865, "loss": 2.0451, "lr": 9.99742051694214e-07, "epoch": 0.15357051446122344, "percentage": 1.02, "elapsed_time": "0:15:41", "remaining_time": "1 day, 1:17:22", "throughput": 8434.4, "total_tokens": 7943032} {"current_steps": 7900, "total_steps": 761865, "loss": 1.9811, "lr": 9.997353872258542e-07, "epoch": 0.1555393672107263, "percentage": 1.04, "elapsed_time": "0:15:53", "remaining_time": "1 day, 1:17:03", "throughput": 8434.38, "total_tokens": 8044224} {"current_steps": 8000, "total_steps": 761865, "loss": 2.0199, "lr": 9.997286377817067e-07, "epoch": 0.15750821996022918, "percentage": 1.05, "elapsed_time": "0:16:05", "remaining_time": "1 day, 1:16:56", "throughput": 8433.85, "total_tokens": 8145968} {"current_steps": 8100, "total_steps": 761865, "loss": 2.0, "lr": 9.997218033629195e-07, "epoch": 0.15947707270973205, "percentage": 1.06, "elapsed_time": "0:16:17", "remaining_time": "1 day, 1:16:37", "throughput": 8434.46, "total_tokens": 8247792} {"current_steps": 8200, "total_steps": 761865, "loss": 1.9879, "lr": 9.997148839706545e-07, "epoch": 0.1614459254592349, "percentage": 1.08, "elapsed_time": "0:16:29", "remaining_time": "1 day, 1:16:18", "throughput": 8434.74, "total_tokens": 8349264} {"current_steps": 8300, "total_steps": 761865, "loss": 1.9729, "lr": 9.99707879606088e-07, "epoch": 0.16341477820873776, "percentage": 1.09, "elapsed_time": "0:16:41", "remaining_time": "1 day, 1:15:40", "throughput": 8437.29, "total_tokens": 8451152} {"current_steps": 8400, "total_steps": 761865, "loss": 2.0167, "lr": 9.997007902704115e-07, "epoch": 0.16538363095824063, "percentage": 1.1, "elapsed_time": "0:16:53", "remaining_time": "1 day, 1:14:54", "throughput": 8440.47, "total_tokens": 8553040} {"current_steps": 8500, "total_steps": 761865, "loss": 2.0309, "lr": 9.996936159648302e-07, "epoch": 0.1673524837077435, "percentage": 1.12, "elapsed_time": "0:17:05", "remaining_time": "1 day, 1:14:13", "throughput": 8443.71, "total_tokens": 8655440} {"current_steps": 8600, "total_steps": 761865, "loss": 1.9358, "lr": 9.99686356690564e-07, "epoch": 0.16932133645724637, "percentage": 1.13, "elapsed_time": "0:17:16", "remaining_time": "1 day, 1:13:22", "throughput": 8447.86, "total_tokens": 8757840} {"current_steps": 8700, "total_steps": 761865, "loss": 1.9934, "lr": 9.996790124488477e-07, "epoch": 0.17129018920674924, "percentage": 1.14, "elapsed_time": "0:17:28", "remaining_time": "1 day, 1:12:22", "throughput": 8451.44, "total_tokens": 8858664} {"current_steps": 8800, "total_steps": 761865, "loss": 1.9581, "lr": 9.996715832409295e-07, "epoch": 0.17325904195625208, "percentage": 1.16, "elapsed_time": "0:17:39", "remaining_time": "1 day, 1:11:46", "throughput": 8454.14, "total_tokens": 8961064} {"current_steps": 8900, "total_steps": 761865, "loss": 1.9722, "lr": 9.996640690680732e-07, "epoch": 0.17522789470575495, "percentage": 1.17, "elapsed_time": "0:17:51", "remaining_time": "1 day, 1:10:55", "throughput": 8457.72, "total_tokens": 9062776} {"current_steps": 9000, "total_steps": 761865, "loss": 1.9504, "lr": 9.996564699315561e-07, "epoch": 0.17719674745525782, "percentage": 1.18, "elapsed_time": "0:18:03", "remaining_time": "1 day, 1:10:27", "throughput": 8459.67, "total_tokens": 9165176} {"current_steps": 9100, "total_steps": 761865, "loss": 1.9981, "lr": 9.996487858326708e-07, "epoch": 0.1791656002047607, "percentage": 1.19, "elapsed_time": "0:18:14", "remaining_time": "1 day, 1:09:39", "throughput": 8462.4, "total_tokens": 9266312} {"current_steps": 9200, "total_steps": 761865, "loss": 1.9342, "lr": 9.996410167727236e-07, "epoch": 0.18113445295426356, "percentage": 1.21, "elapsed_time": "0:18:26", "remaining_time": "1 day, 1:09:02", "throughput": 8464.56, "total_tokens": 9367936} {"current_steps": 9300, "total_steps": 761865, "loss": 1.9561, "lr": 9.99633162753036e-07, "epoch": 0.18310330570376643, "percentage": 1.22, "elapsed_time": "0:18:38", "remaining_time": "1 day, 1:08:33", "throughput": 8466.71, "total_tokens": 9470336} {"current_steps": 9400, "total_steps": 761865, "loss": 1.9991, "lr": 9.996252237749427e-07, "epoch": 0.18507215845326927, "percentage": 1.23, "elapsed_time": "0:18:50", "remaining_time": "1 day, 1:08:00", "throughput": 8469.19, "total_tokens": 9572736} {"current_steps": 9500, "total_steps": 761865, "loss": 1.9686, "lr": 9.996171998397944e-07, "epoch": 0.18704101120277214, "percentage": 1.25, "elapsed_time": "0:19:01", "remaining_time": "1 day, 1:07:17", "throughput": 8472.55, "total_tokens": 9675136} {"current_steps": 9600, "total_steps": 761865, "loss": 1.97, "lr": 9.996090909489552e-07, "epoch": 0.189009863952275, "percentage": 1.26, "elapsed_time": "0:19:13", "remaining_time": "1 day, 1:06:34", "throughput": 8475.89, "total_tokens": 9777536} {"current_steps": 9700, "total_steps": 761865, "loss": 1.9829, "lr": 9.99600897103804e-07, "epoch": 0.19097871670177788, "percentage": 1.27, "elapsed_time": "0:19:25", "remaining_time": "1 day, 1:05:50", "throughput": 8478.91, "total_tokens": 9879392} {"current_steps": 9800, "total_steps": 761865, "loss": 1.9965, "lr": 9.995926183057338e-07, "epoch": 0.19294756945128075, "percentage": 1.29, "elapsed_time": "0:19:36", "remaining_time": "1 day, 1:05:09", "throughput": 8481.15, "total_tokens": 9980648} {"current_steps": 9900, "total_steps": 761865, "loss": 1.981, "lr": 9.995842545561527e-07, "epoch": 0.1949164222007836, "percentage": 1.3, "elapsed_time": "0:19:48", "remaining_time": "1 day, 1:04:35", "throughput": 8483.72, "total_tokens": 10083048} {"current_steps": 10000, "total_steps": 761865, "loss": 1.9643, "lr": 9.995758058564832e-07, "epoch": 0.19688527495028646, "percentage": 1.31, "elapsed_time": "0:20:00", "remaining_time": "1 day, 1:03:59", "throughput": 8485.95, "total_tokens": 10184864} {"current_steps": 10100, "total_steps": 761865, "loss": 1.9848, "lr": 9.99567272208161e-07, "epoch": 0.19885412769978933, "percentage": 1.33, "elapsed_time": "0:20:12", "remaining_time": "1 day, 1:04:01", "throughput": 8485.07, "total_tokens": 10287264} {"current_steps": 10200, "total_steps": 761865, "loss": 1.9503, "lr": 9.995586536126381e-07, "epoch": 0.2008229804492922, "percentage": 1.34, "elapsed_time": "0:20:24", "remaining_time": "1 day, 1:03:28", "throughput": 8487.46, "total_tokens": 10389664} {"current_steps": 10300, "total_steps": 761865, "loss": 1.9629, "lr": 9.995499500713795e-07, "epoch": 0.20279183319879507, "percentage": 1.35, "elapsed_time": "0:20:35", "remaining_time": "1 day, 1:02:53", "throughput": 8489.54, "total_tokens": 10491440} {"current_steps": 10400, "total_steps": 761865, "loss": 1.9909, "lr": 9.995411615858654e-07, "epoch": 0.20476068594829794, "percentage": 1.37, "elapsed_time": "0:20:47", "remaining_time": "1 day, 1:02:23", "throughput": 8491.72, "total_tokens": 10593840} {"current_steps": 10500, "total_steps": 761865, "loss": 2.0632, "lr": 9.995322881575898e-07, "epoch": 0.20672953869780078, "percentage": 1.38, "elapsed_time": "0:20:59", "remaining_time": "1 day, 1:01:46", "throughput": 8493.41, "total_tokens": 10694928} {"current_steps": 10600, "total_steps": 761865, "loss": 2.0156, "lr": 9.99523329788062e-07, "epoch": 0.20869839144730365, "percentage": 1.39, "elapsed_time": "0:21:10", "remaining_time": "1 day, 1:01:11", "throughput": 8495.41, "total_tokens": 10796552} {"current_steps": 10700, "total_steps": 761865, "loss": 1.9922, "lr": 9.995142864788051e-07, "epoch": 0.21066724419680652, "percentage": 1.4, "elapsed_time": "0:21:22", "remaining_time": "1 day, 1:00:37", "throughput": 8497.26, "total_tokens": 10898160} {"current_steps": 10800, "total_steps": 761865, "loss": 1.9887, "lr": 9.99505158231357e-07, "epoch": 0.2126360969463094, "percentage": 1.42, "elapsed_time": "0:21:34", "remaining_time": "1 day, 1:00:08", "throughput": 8499.36, "total_tokens": 11000560} {"current_steps": 10900, "total_steps": 761865, "loss": 1.9892, "lr": 9.994959450472697e-07, "epoch": 0.21460494969581226, "percentage": 1.43, "elapsed_time": "0:21:45", "remaining_time": "1 day, 0:59:34", "throughput": 8500.94, "total_tokens": 11101736} {"current_steps": 11000, "total_steps": 761865, "loss": 1.999, "lr": 9.9948664692811e-07, "epoch": 0.21657380244531513, "percentage": 1.44, "elapsed_time": "0:21:57", "remaining_time": "1 day, 0:59:00", "throughput": 8502.68, "total_tokens": 11203232} {"current_steps": 11100, "total_steps": 761865, "loss": 2.0029, "lr": 9.994772638754587e-07, "epoch": 0.21854265519481797, "percentage": 1.46, "elapsed_time": "0:22:09", "remaining_time": "1 day, 0:58:32", "throughput": 8504.66, "total_tokens": 11305632} {"current_steps": 11200, "total_steps": 761865, "loss": 1.9623, "lr": 9.994677958909117e-07, "epoch": 0.22051150794432084, "percentage": 1.47, "elapsed_time": "0:22:21", "remaining_time": "1 day, 0:58:04", "throughput": 8506.6, "total_tokens": 11408032} {"current_steps": 11300, "total_steps": 761865, "loss": 1.9939, "lr": 9.994582429760785e-07, "epoch": 0.2224803606938237, "percentage": 1.48, "elapsed_time": "0:22:32", "remaining_time": "1 day, 0:57:33", "throughput": 8508.46, "total_tokens": 11510016} {"current_steps": 11400, "total_steps": 761865, "loss": 1.9569, "lr": 9.994486051325837e-07, "epoch": 0.22444921344332658, "percentage": 1.5, "elapsed_time": "0:22:44", "remaining_time": "1 day, 0:57:01", "throughput": 8510.09, "total_tokens": 11611544} {"current_steps": 11500, "total_steps": 761865, "loss": 2.0075, "lr": 9.99438882362066e-07, "epoch": 0.22641806619282945, "percentage": 1.51, "elapsed_time": "0:22:56", "remaining_time": "1 day, 0:56:32", "throughput": 8511.8, "total_tokens": 11713528} {"current_steps": 11600, "total_steps": 761865, "loss": 1.9548, "lr": 9.99429074666179e-07, "epoch": 0.2283869189423323, "percentage": 1.52, "elapsed_time": "0:23:07", "remaining_time": "1 day, 0:55:59", "throughput": 8513.01, "total_tokens": 11814312} {"current_steps": 11700, "total_steps": 761865, "loss": 2.0178, "lr": 9.994191820465902e-07, "epoch": 0.23035577169183516, "percentage": 1.54, "elapsed_time": "0:23:19", "remaining_time": "1 day, 0:55:33", "throughput": 8514.76, "total_tokens": 11916712} {"current_steps": 11800, "total_steps": 761865, "loss": 1.9757, "lr": 9.99409204504982e-07, "epoch": 0.23232462444133803, "percentage": 1.55, "elapsed_time": "0:23:31", "remaining_time": "1 day, 0:55:07", "throughput": 8516.51, "total_tokens": 12019112} {"current_steps": 11900, "total_steps": 761865, "loss": 1.9657, "lr": 9.993991420430506e-07, "epoch": 0.2342934771908409, "percentage": 1.56, "elapsed_time": "0:23:42", "remaining_time": "1 day, 0:54:38", "throughput": 8517.9, "total_tokens": 12120656} {"current_steps": 12000, "total_steps": 761865, "loss": 1.9828, "lr": 9.993889946625073e-07, "epoch": 0.23626232994034377, "percentage": 1.58, "elapsed_time": "0:23:54", "remaining_time": "1 day, 0:54:13", "throughput": 8519.49, "total_tokens": 12223056} {"current_steps": 12100, "total_steps": 761865, "loss": 1.9723, "lr": 9.993787623650773e-07, "epoch": 0.23823118268984664, "percentage": 1.59, "elapsed_time": "0:24:06", "remaining_time": "1 day, 0:53:45", "throughput": 8520.96, "total_tokens": 12324856} {"current_steps": 12200, "total_steps": 761865, "loss": 2.0026, "lr": 9.993684451525008e-07, "epoch": 0.24020003543934948, "percentage": 1.6, "elapsed_time": "0:24:18", "remaining_time": "1 day, 0:53:20", "throughput": 8522.59, "total_tokens": 12427256} {"current_steps": 12300, "total_steps": 761865, "loss": 1.9573, "lr": 9.993580430265321e-07, "epoch": 0.24216888818885235, "percentage": 1.61, "elapsed_time": "0:24:29", "remaining_time": "1 day, 0:52:55", "throughput": 8524.21, "total_tokens": 12529656} {"current_steps": 12400, "total_steps": 761865, "loss": 1.9974, "lr": 9.993475559889401e-07, "epoch": 0.24413774093835522, "percentage": 1.63, "elapsed_time": "0:24:41", "remaining_time": "1 day, 0:52:27", "throughput": 8525.49, "total_tokens": 12631136} {"current_steps": 12500, "total_steps": 761865, "loss": 1.9587, "lr": 9.993369840415076e-07, "epoch": 0.2461065936878581, "percentage": 1.64, "elapsed_time": "0:24:53", "remaining_time": "1 day, 0:51:56", "throughput": 8526.73, "total_tokens": 12732168} {"current_steps": 12600, "total_steps": 761865, "loss": 1.9721, "lr": 9.993263271860328e-07, "epoch": 0.24807544643736096, "percentage": 1.65, "elapsed_time": "0:25:04", "remaining_time": "1 day, 0:51:29", "throughput": 8528.12, "total_tokens": 12833992} {"current_steps": 12700, "total_steps": 761865, "loss": 2.0185, "lr": 9.993155854243275e-07, "epoch": 0.2500442991868638, "percentage": 1.67, "elapsed_time": "0:25:16", "remaining_time": "1 day, 0:51:00", "throughput": 8529.16, "total_tokens": 12934888} {"current_steps": 12800, "total_steps": 761865, "loss": 1.9909, "lr": 9.993047587582184e-07, "epoch": 0.2520131519363667, "percentage": 1.68, "elapsed_time": "0:25:28", "remaining_time": "1 day, 0:50:31", "throughput": 8530.28, "total_tokens": 13035984} {"current_steps": 12900, "total_steps": 761865, "loss": 2.1097, "lr": 9.992938471895462e-07, "epoch": 0.25398200468586957, "percentage": 1.69, "elapsed_time": "0:25:39", "remaining_time": "1 day, 0:50:05", "throughput": 8531.41, "total_tokens": 13137528} {"current_steps": 13000, "total_steps": 761865, "loss": 1.9904, "lr": 9.992828507201666e-07, "epoch": 0.2559508574353724, "percentage": 1.71, "elapsed_time": "0:25:51", "remaining_time": "1 day, 0:49:42", "throughput": 8532.81, "total_tokens": 13239928} {"current_steps": 13100, "total_steps": 761865, "loss": 1.9373, "lr": 9.992717693519497e-07, "epoch": 0.25791971018487525, "percentage": 1.72, "elapsed_time": "0:26:03", "remaining_time": "1 day, 0:49:19", "throughput": 8534.26, "total_tokens": 13342328} {"current_steps": 13200, "total_steps": 761865, "loss": 1.974, "lr": 9.992606030867792e-07, "epoch": 0.2598885629343781, "percentage": 1.73, "elapsed_time": "0:26:15", "remaining_time": "1 day, 0:48:53", "throughput": 8535.45, "total_tokens": 13443976} {"current_steps": 13300, "total_steps": 761865, "loss": 1.9461, "lr": 9.99249351926554e-07, "epoch": 0.261857415683881, "percentage": 1.75, "elapsed_time": "0:26:26", "remaining_time": "1 day, 0:48:30", "throughput": 8536.86, "total_tokens": 13546376} {"current_steps": 13400, "total_steps": 761865, "loss": 1.9667, "lr": 9.992380158731875e-07, "epoch": 0.26382626843338386, "percentage": 1.76, "elapsed_time": "0:26:38", "remaining_time": "1 day, 0:48:07", "throughput": 8538.25, "total_tokens": 13648776} {"current_steps": 13500, "total_steps": 761865, "loss": 1.9328, "lr": 9.99226594928607e-07, "epoch": 0.26579512118288673, "percentage": 1.77, "elapsed_time": "0:26:50", "remaining_time": "1 day, 0:47:45", "throughput": 8539.61, "total_tokens": 13751176} {"current_steps": 13600, "total_steps": 761865, "loss": 1.9817, "lr": 9.992150890947551e-07, "epoch": 0.2677639739323896, "percentage": 1.79, "elapsed_time": "0:27:02", "remaining_time": "1 day, 0:47:22", "throughput": 8540.96, "total_tokens": 13853576} {"current_steps": 13700, "total_steps": 761865, "loss": 1.9639, "lr": 9.992034983735876e-07, "epoch": 0.26973282668189247, "percentage": 1.8, "elapsed_time": "0:27:13", "remaining_time": "1 day, 0:46:57", "throughput": 8542.22, "total_tokens": 13955480} {"current_steps": 13800, "total_steps": 761865, "loss": 1.9584, "lr": 9.991918227670757e-07, "epoch": 0.27170167943139534, "percentage": 1.81, "elapsed_time": "0:27:25", "remaining_time": "1 day, 0:46:35", "throughput": 8543.56, "total_tokens": 14057880} {"current_steps": 13900, "total_steps": 761865, "loss": 1.9333, "lr": 9.991800622772047e-07, "epoch": 0.2736705321808982, "percentage": 1.82, "elapsed_time": "0:27:37", "remaining_time": "1 day, 0:46:12", "throughput": 8544.89, "total_tokens": 14160280} {"current_steps": 14000, "total_steps": 761865, "loss": 1.9996, "lr": 9.991682169059744e-07, "epoch": 0.2756393849304011, "percentage": 1.84, "elapsed_time": "0:27:48", "remaining_time": "1 day, 0:45:50", "throughput": 8546.17, "total_tokens": 14262680} {"current_steps": 14100, "total_steps": 761865, "loss": 1.9756, "lr": 9.99156286655399e-07, "epoch": 0.27760823767990395, "percentage": 1.85, "elapsed_time": "0:28:00", "remaining_time": "1 day, 0:45:27", "throughput": 8547.36, "total_tokens": 14364768} {"current_steps": 14200, "total_steps": 761865, "loss": 1.9927, "lr": 9.991442715275072e-07, "epoch": 0.27957709042940676, "percentage": 1.86, "elapsed_time": "0:28:12", "remaining_time": "1 day, 0:45:14", "throughput": 8547.82, "total_tokens": 14467168} {"current_steps": 14300, "total_steps": 761865, "loss": 2.0169, "lr": 9.99132171524342e-07, "epoch": 0.28154594317890963, "percentage": 1.88, "elapsed_time": "0:28:24", "remaining_time": "1 day, 0:44:58", "throughput": 8548.46, "total_tokens": 14569568} {"current_steps": 14400, "total_steps": 761865, "loss": 1.9812, "lr": 9.991199866479607e-07, "epoch": 0.2835147959284125, "percentage": 1.89, "elapsed_time": "0:28:36", "remaining_time": "1 day, 0:44:43", "throughput": 8549.04, "total_tokens": 14671968} {"current_steps": 14500, "total_steps": 761865, "loss": 1.9598, "lr": 9.991077169004355e-07, "epoch": 0.28548364867791537, "percentage": 1.9, "elapsed_time": "0:28:47", "remaining_time": "1 day, 0:44:22", "throughput": 8549.87, "total_tokens": 14773656} {"current_steps": 14600, "total_steps": 761865, "loss": 1.9954, "lr": 9.99095362283853e-07, "epoch": 0.28745250142741824, "percentage": 1.92, "elapsed_time": "0:28:59", "remaining_time": "1 day, 0:44:07", "throughput": 8550.23, "total_tokens": 14875680} {"current_steps": 14700, "total_steps": 761865, "loss": 1.9532, "lr": 9.990829228003136e-07, "epoch": 0.2894213541769211, "percentage": 1.93, "elapsed_time": "0:29:11", "remaining_time": "1 day, 0:43:54", "throughput": 8550.6, "total_tokens": 14978080} {"current_steps": 14800, "total_steps": 761865, "loss": 2.0163, "lr": 9.990703984519324e-07, "epoch": 0.291390206926424, "percentage": 1.94, "elapsed_time": "0:29:23", "remaining_time": "1 day, 0:43:41", "throughput": 8550.95, "total_tokens": 15080480} {"current_steps": 14900, "total_steps": 761865, "loss": 1.9416, "lr": 9.990577892408396e-07, "epoch": 0.29335905967592685, "percentage": 1.96, "elapsed_time": "0:29:35", "remaining_time": "1 day, 0:43:27", "throughput": 8551.17, "total_tokens": 15182336} {"current_steps": 15000, "total_steps": 761865, "loss": 2.0071, "lr": 9.990450951691786e-07, "epoch": 0.2953279124254297, "percentage": 1.97, "elapsed_time": "0:29:47", "remaining_time": "1 day, 0:43:13", "throughput": 8551.07, "total_tokens": 15283712} {"current_steps": 15100, "total_steps": 761865, "loss": 1.9592, "lr": 9.990323162391087e-07, "epoch": 0.2972967651749326, "percentage": 1.98, "elapsed_time": "0:30:01", "remaining_time": "1 day, 0:44:49", "throughput": 8540.68, "total_tokens": 15385432} {"current_steps": 15200, "total_steps": 761865, "loss": 1.8992, "lr": 9.990194524528024e-07, "epoch": 0.29926561792443546, "percentage": 2.0, "elapsed_time": "0:30:13", "remaining_time": "1 day, 0:44:38", "throughput": 8540.85, "total_tokens": 15487832} {"current_steps": 15300, "total_steps": 761865, "loss": 1.9654, "lr": 9.99006503812447e-07, "epoch": 0.30123447067393827, "percentage": 2.01, "elapsed_time": "0:30:25", "remaining_time": "1 day, 0:44:22", "throughput": 8541.25, "total_tokens": 15589736} {"current_steps": 15400, "total_steps": 761865, "loss": 1.9673, "lr": 9.989934703202444e-07, "epoch": 0.30320332342344114, "percentage": 2.02, "elapsed_time": "0:30:37", "remaining_time": "1 day, 0:44:06", "throughput": 8541.88, "total_tokens": 15692136} {"current_steps": 15500, "total_steps": 761865, "loss": 2.0, "lr": 9.98980351978411e-07, "epoch": 0.305172176172944, "percentage": 2.03, "elapsed_time": "0:30:48", "remaining_time": "1 day, 0:43:42", "throughput": 8542.66, "total_tokens": 15793344} {"current_steps": 15600, "total_steps": 761865, "loss": 2.0583, "lr": 9.989671487891773e-07, "epoch": 0.3071410289224469, "percentage": 2.05, "elapsed_time": "0:31:00", "remaining_time": "1 day, 0:43:25", "throughput": 8542.54, "total_tokens": 15894016} {"current_steps": 15700, "total_steps": 761865, "loss": 1.9946, "lr": 9.989538607547883e-07, "epoch": 0.30910988167194975, "percentage": 2.06, "elapsed_time": "0:31:12", "remaining_time": "1 day, 0:42:57", "throughput": 8543.3, "total_tokens": 15994488} {"current_steps": 15800, "total_steps": 761865, "loss": 1.9935, "lr": 9.989404878775038e-07, "epoch": 0.3110787344214526, "percentage": 2.07, "elapsed_time": "0:31:23", "remaining_time": "1 day, 0:42:36", "throughput": 8544.44, "total_tokens": 16096888} {"current_steps": 15900, "total_steps": 761865, "loss": 1.981, "lr": 9.989270301595976e-07, "epoch": 0.3130475871709555, "percentage": 2.09, "elapsed_time": "0:31:35", "remaining_time": "1 day, 0:42:13", "throughput": 8545.47, "total_tokens": 16198688} {"current_steps": 16000, "total_steps": 761865, "loss": 1.9702, "lr": 9.98913487603358e-07, "epoch": 0.31501643992045836, "percentage": 2.1, "elapsed_time": "0:31:47", "remaining_time": "1 day, 0:41:52", "throughput": 8546.57, "total_tokens": 16301088} {"current_steps": 16100, "total_steps": 761865, "loss": 1.9911, "lr": 9.98899860211088e-07, "epoch": 0.3169852926699612, "percentage": 2.11, "elapsed_time": "0:31:58", "remaining_time": "1 day, 0:41:28", "throughput": 8547.36, "total_tokens": 16402144} {"current_steps": 16200, "total_steps": 761865, "loss": 1.9966, "lr": 9.988861479851045e-07, "epoch": 0.3189541454194641, "percentage": 2.13, "elapsed_time": "0:32:10", "remaining_time": "1 day, 0:41:05", "throughput": 8548.22, "total_tokens": 16503728} {"current_steps": 16300, "total_steps": 761865, "loss": 1.9795, "lr": 9.988723509277395e-07, "epoch": 0.32092299816896697, "percentage": 2.14, "elapsed_time": "0:32:22", "remaining_time": "1 day, 0:40:46", "throughput": 8549.18, "total_tokens": 16606128} {"current_steps": 16400, "total_steps": 761865, "loss": 1.9247, "lr": 9.98858469041339e-07, "epoch": 0.3228918509184698, "percentage": 2.15, "elapsed_time": "0:32:34", "remaining_time": "1 day, 0:40:45", "throughput": 8548.41, "total_tokens": 16708528} {"current_steps": 16500, "total_steps": 761865, "loss": 2.0131, "lr": 9.988445023282631e-07, "epoch": 0.32486070366797265, "percentage": 2.17, "elapsed_time": "0:32:46", "remaining_time": "1 day, 0:40:47", "throughput": 8547.34, "total_tokens": 16810928} {"current_steps": 16600, "total_steps": 761865, "loss": 1.9906, "lr": 9.988304507908872e-07, "epoch": 0.3268295564174755, "percentage": 2.18, "elapsed_time": "0:32:58", "remaining_time": "1 day, 0:40:39", "throughput": 8546.81, "total_tokens": 16912496} {"current_steps": 16700, "total_steps": 761865, "loss": 1.972, "lr": 9.988163144316005e-07, "epoch": 0.3287984091669784, "percentage": 2.19, "elapsed_time": "0:33:10", "remaining_time": "1 day, 0:40:39", "throughput": 8545.63, "total_tokens": 17014288} {"current_steps": 16800, "total_steps": 761865, "loss": 1.9729, "lr": 9.988020932528065e-07, "epoch": 0.33076726191648126, "percentage": 2.21, "elapsed_time": "0:33:23", "remaining_time": "1 day, 0:40:36", "throughput": 8544.42, "total_tokens": 17115536} {"current_steps": 16900, "total_steps": 761865, "loss": 2.0161, "lr": 9.987877872569239e-07, "epoch": 0.33273611466598413, "percentage": 2.22, "elapsed_time": "0:33:35", "remaining_time": "1 day, 0:40:33", "throughput": 8542.94, "total_tokens": 17216168} {"current_steps": 17000, "total_steps": 761865, "loss": 1.9248, "lr": 9.98773396446385e-07, "epoch": 0.334704967415487, "percentage": 2.23, "elapsed_time": "0:33:47", "remaining_time": "1 day, 0:40:33", "throughput": 8541.84, "total_tokens": 17318072} {"current_steps": 17100, "total_steps": 761865, "loss": 2.002, "lr": 9.987589208236368e-07, "epoch": 0.33667382016498987, "percentage": 2.24, "elapsed_time": "0:33:59", "remaining_time": "1 day, 0:40:34", "throughput": 8540.87, "total_tokens": 17420472} {"current_steps": 17200, "total_steps": 761865, "loss": 1.997, "lr": 9.987443603911408e-07, "epoch": 0.33864267291449274, "percentage": 2.26, "elapsed_time": "0:34:11", "remaining_time": "1 day, 0:40:30", "throughput": 8539.6, "total_tokens": 17521296} {"current_steps": 17300, "total_steps": 761865, "loss": 1.9538, "lr": 9.98729715151373e-07, "epoch": 0.3406115256639956, "percentage": 2.27, "elapsed_time": "0:34:24", "remaining_time": "1 day, 0:40:31", "throughput": 8538.58, "total_tokens": 17623696} {"current_steps": 17400, "total_steps": 761865, "loss": 2.0244, "lr": 9.987149851068237e-07, "epoch": 0.3425803784134985, "percentage": 2.28, "elapsed_time": "0:34:36", "remaining_time": "1 day, 0:40:31", "throughput": 8537.53, "total_tokens": 17725640} {"current_steps": 17500, "total_steps": 761865, "loss": 2.046, "lr": 9.987001702599974e-07, "epoch": 0.34454923116300135, "percentage": 2.3, "elapsed_time": "0:34:48", "remaining_time": "1 day, 0:40:31", "throughput": 8536.61, "total_tokens": 17828040} {"current_steps": 17600, "total_steps": 761865, "loss": 1.9298, "lr": 9.986852706134134e-07, "epoch": 0.34651808391250416, "percentage": 2.31, "elapsed_time": "0:35:00", "remaining_time": "1 day, 0:40:31", "throughput": 8535.69, "total_tokens": 17930440} {"current_steps": 17700, "total_steps": 761865, "loss": 2.0293, "lr": 9.986702861696053e-07, "epoch": 0.34848693666200703, "percentage": 2.32, "elapsed_time": "0:35:12", "remaining_time": "1 day, 0:40:27", "throughput": 8534.46, "total_tokens": 18031296} {"current_steps": 17800, "total_steps": 761865, "loss": 1.9718, "lr": 9.986552169311211e-07, "epoch": 0.3504557894115099, "percentage": 2.34, "elapsed_time": "0:35:24", "remaining_time": "1 day, 0:40:22", "throughput": 8533.36, "total_tokens": 18132232} {"current_steps": 17900, "total_steps": 761865, "loss": 2.0083, "lr": 9.98640062900523e-07, "epoch": 0.35242464216101277, "percentage": 2.35, "elapsed_time": "0:35:37", "remaining_time": "1 day, 0:40:20", "throughput": 8532.23, "total_tokens": 18233696} {"current_steps": 18000, "total_steps": 761865, "loss": 1.9991, "lr": 9.986248240803878e-07, "epoch": 0.35439349491051564, "percentage": 2.36, "elapsed_time": "0:35:49", "remaining_time": "1 day, 0:40:16", "throughput": 8531.26, "total_tokens": 18335176} {"current_steps": 18100, "total_steps": 761865, "loss": 1.9941, "lr": 9.98609500473307e-07, "epoch": 0.3563623476600185, "percentage": 2.38, "elapsed_time": "0:36:01", "remaining_time": "1 day, 0:40:16", "throughput": 8530.37, "total_tokens": 18437576} {"current_steps": 18200, "total_steps": 761865, "loss": 1.9779, "lr": 9.985940920818863e-07, "epoch": 0.3583312004095214, "percentage": 2.39, "elapsed_time": "0:36:13", "remaining_time": "1 day, 0:40:16", "throughput": 8529.5, "total_tokens": 18539976} {"current_steps": 18300, "total_steps": 761865, "loss": 1.9569, "lr": 9.985785989087454e-07, "epoch": 0.36030005315902425, "percentage": 2.4, "elapsed_time": "0:36:25", "remaining_time": "1 day, 0:40:13", "throughput": 8528.51, "total_tokens": 18641568} {"current_steps": 18400, "total_steps": 761865, "loss": 2.0087, "lr": 9.985630209565187e-07, "epoch": 0.3622689059085271, "percentage": 2.42, "elapsed_time": "0:36:37", "remaining_time": "1 day, 0:40:09", "throughput": 8527.47, "total_tokens": 18742960} {"current_steps": 18500, "total_steps": 761865, "loss": 2.0024, "lr": 9.985473582278558e-07, "epoch": 0.36423775865803, "percentage": 2.43, "elapsed_time": "0:36:50", "remaining_time": "1 day, 0:40:05", "throughput": 8526.24, "total_tokens": 18843736} {"current_steps": 18600, "total_steps": 761865, "loss": 2.0421, "lr": 9.985316107254193e-07, "epoch": 0.36620661140753286, "percentage": 2.44, "elapsed_time": "0:37:02", "remaining_time": "1 day, 0:40:04", "throughput": 8525.28, "total_tokens": 18945800} {"current_steps": 18700, "total_steps": 761865, "loss": 2.0023, "lr": 9.985157784518873e-07, "epoch": 0.36817546415703567, "percentage": 2.45, "elapsed_time": "0:37:14", "remaining_time": "1 day, 0:40:01", "throughput": 8524.41, "total_tokens": 19047632} {"current_steps": 18800, "total_steps": 761865, "loss": 1.9879, "lr": 9.98499861409952e-07, "epoch": 0.37014431690653854, "percentage": 2.47, "elapsed_time": "0:37:26", "remaining_time": "1 day, 0:39:56", "throughput": 8523.16, "total_tokens": 19148216} {"current_steps": 18900, "total_steps": 761865, "loss": 1.9447, "lr": 9.984838596023195e-07, "epoch": 0.3721131696560414, "percentage": 2.48, "elapsed_time": "0:37:38", "remaining_time": "1 day, 0:39:55", "throughput": 8522.38, "total_tokens": 19250616} {"current_steps": 19000, "total_steps": 761865, "loss": 1.9803, "lr": 9.984677730317112e-07, "epoch": 0.3740820224055443, "percentage": 2.49, "elapsed_time": "0:37:51", "remaining_time": "1 day, 0:39:55", "throughput": 8521.5, "total_tokens": 19353016} {"current_steps": 19100, "total_steps": 761865, "loss": 1.9828, "lr": 9.984516017008623e-07, "epoch": 0.37605087515504715, "percentage": 2.51, "elapsed_time": "0:38:03", "remaining_time": "1 day, 0:39:53", "throughput": 8520.73, "total_tokens": 19455416} {"current_steps": 19200, "total_steps": 761865, "loss": 1.9757, "lr": 9.98435345612523e-07, "epoch": 0.37801972790455, "percentage": 2.52, "elapsed_time": "0:38:15", "remaining_time": "1 day, 0:39:49", "throughput": 8519.88, "total_tokens": 19557144} {"current_steps": 19300, "total_steps": 761865, "loss": 1.9925, "lr": 9.98419004769457e-07, "epoch": 0.3799885806540529, "percentage": 2.53, "elapsed_time": "0:38:27", "remaining_time": "1 day, 0:39:48", "throughput": 8519.13, "total_tokens": 19659544} {"current_steps": 19400, "total_steps": 761865, "loss": 1.9984, "lr": 9.98402579174443e-07, "epoch": 0.38195743340355576, "percentage": 2.55, "elapsed_time": "0:38:39", "remaining_time": "1 day, 0:39:42", "throughput": 8518.22, "total_tokens": 19760632} {"current_steps": 19500, "total_steps": 761865, "loss": 1.9942, "lr": 9.98386068830274e-07, "epoch": 0.3839262861530586, "percentage": 2.56, "elapsed_time": "0:38:51", "remaining_time": "1 day, 0:39:35", "throughput": 8517.3, "total_tokens": 19861480} {"current_steps": 19600, "total_steps": 761865, "loss": 1.9479, "lr": 9.983694737397579e-07, "epoch": 0.3858951389025615, "percentage": 2.57, "elapsed_time": "0:39:04", "remaining_time": "1 day, 0:39:31", "throughput": 8516.56, "total_tokens": 19963304} {"current_steps": 19700, "total_steps": 761865, "loss": 2.0048, "lr": 9.98352793905716e-07, "epoch": 0.38786399165206437, "percentage": 2.59, "elapsed_time": "0:39:16", "remaining_time": "1 day, 0:39:28", "throughput": 8515.88, "total_tokens": 20065704} {"current_steps": 19800, "total_steps": 761865, "loss": 1.9596, "lr": 9.983360293309849e-07, "epoch": 0.3898328444015672, "percentage": 2.6, "elapsed_time": "0:39:28", "remaining_time": "1 day, 0:39:22", "throughput": 8514.81, "total_tokens": 20166448} {"current_steps": 19900, "total_steps": 761865, "loss": 1.9505, "lr": 9.983191800184153e-07, "epoch": 0.39180169715107005, "percentage": 2.61, "elapsed_time": "0:39:40", "remaining_time": "1 day, 0:39:21", "throughput": 8514.0, "total_tokens": 20268848} {"current_steps": 20000, "total_steps": 761865, "loss": 1.9489, "lr": 9.98302245970872e-07, "epoch": 0.3937705499005729, "percentage": 2.63, "elapsed_time": "0:39:52", "remaining_time": "1 day, 0:39:17", "throughput": 8513.06, "total_tokens": 20370352} {"current_steps": 20100, "total_steps": 761865, "loss": 1.9811, "lr": 9.982852271912345e-07, "epoch": 0.3957394026500758, "percentage": 2.64, "elapsed_time": "0:40:05", "remaining_time": "1 day, 0:39:36", "throughput": 8510.39, "total_tokens": 20472752} {"current_steps": 20200, "total_steps": 761865, "loss": 1.9737, "lr": 9.982681236823972e-07, "epoch": 0.39770825539957866, "percentage": 2.65, "elapsed_time": "0:40:17", "remaining_time": "1 day, 0:39:34", "throughput": 8509.64, "total_tokens": 20575152} {"current_steps": 20300, "total_steps": 761865, "loss": 1.9698, "lr": 9.982509354472677e-07, "epoch": 0.39967710814908153, "percentage": 2.66, "elapsed_time": "0:40:30", "remaining_time": "1 day, 0:39:32", "throughput": 8508.93, "total_tokens": 20677552} {"current_steps": 20400, "total_steps": 761865, "loss": 1.9336, "lr": 9.982336624887693e-07, "epoch": 0.4016459608985844, "percentage": 2.68, "elapsed_time": "0:40:42", "remaining_time": "1 day, 0:39:30", "throughput": 8508.15, "total_tokens": 20779952} {"current_steps": 20500, "total_steps": 761865, "loss": 2.0186, "lr": 9.982163048098388e-07, "epoch": 0.40361481364808727, "percentage": 2.69, "elapsed_time": "0:40:54", "remaining_time": "1 day, 0:39:26", "throughput": 8507.37, "total_tokens": 20881720} {"current_steps": 20600, "total_steps": 761865, "loss": 2.0098, "lr": 9.981988624134278e-07, "epoch": 0.40558366639759014, "percentage": 2.7, "elapsed_time": "0:41:06", "remaining_time": "1 day, 0:39:24", "throughput": 8506.62, "total_tokens": 20983992} {"current_steps": 20700, "total_steps": 761865, "loss": 1.9684, "lr": 9.981813353025023e-07, "epoch": 0.407552519147093, "percentage": 2.72, "elapsed_time": "0:41:18", "remaining_time": "1 day, 0:39:17", "throughput": 8505.72, "total_tokens": 21084976} {"current_steps": 20800, "total_steps": 761865, "loss": 2.0056, "lr": 9.981637234800426e-07, "epoch": 0.4095213718965959, "percentage": 2.73, "elapsed_time": "0:41:31", "remaining_time": "1 day, 0:39:13", "throughput": 8504.94, "total_tokens": 21186616} {"current_steps": 20900, "total_steps": 761865, "loss": 1.9566, "lr": 9.981460269490434e-07, "epoch": 0.41149022464609875, "percentage": 2.74, "elapsed_time": "0:41:43", "remaining_time": "1 day, 0:39:11", "throughput": 8504.18, "total_tokens": 21289016} {"current_steps": 21000, "total_steps": 761865, "loss": 1.9389, "lr": 9.981282457125138e-07, "epoch": 0.41345907739560156, "percentage": 2.76, "elapsed_time": "0:41:55", "remaining_time": "1 day, 0:39:06", "throughput": 8503.34, "total_tokens": 21390608} {"current_steps": 21100, "total_steps": 761865, "loss": 1.964, "lr": 9.981103797734775e-07, "epoch": 0.41542793014510443, "percentage": 2.77, "elapsed_time": "0:42:07", "remaining_time": "1 day, 0:38:58", "throughput": 8502.29, "total_tokens": 21490552} {"current_steps": 21200, "total_steps": 761865, "loss": 1.9817, "lr": 9.980924291349724e-07, "epoch": 0.4173967828946073, "percentage": 2.78, "elapsed_time": "0:42:19", "remaining_time": "1 day, 0:38:55", "throughput": 8501.61, "total_tokens": 21592952} {"current_steps": 21300, "total_steps": 761865, "loss": 1.9842, "lr": 9.980743938000508e-07, "epoch": 0.41936563564411017, "percentage": 2.8, "elapsed_time": "0:42:32", "remaining_time": "1 day, 0:38:52", "throughput": 8500.81, "total_tokens": 21695056} {"current_steps": 21400, "total_steps": 761865, "loss": 2.0426, "lr": 9.980562737717797e-07, "epoch": 0.42133448839361304, "percentage": 2.81, "elapsed_time": "0:42:44", "remaining_time": "1 day, 0:38:46", "throughput": 8499.96, "total_tokens": 21796200} {"current_steps": 21500, "total_steps": 761865, "loss": 1.9813, "lr": 9.980380690532398e-07, "epoch": 0.4233033411431159, "percentage": 2.82, "elapsed_time": "0:42:56", "remaining_time": "1 day, 0:38:44", "throughput": 8499.24, "total_tokens": 21898600} {"current_steps": 21600, "total_steps": 761865, "loss": 1.9945, "lr": 9.98019779647527e-07, "epoch": 0.4252721938926188, "percentage": 2.84, "elapsed_time": "0:43:08", "remaining_time": "1 day, 0:38:40", "throughput": 8498.42, "total_tokens": 22000320} {"current_steps": 21700, "total_steps": 761865, "loss": 1.9862, "lr": 9.98001405557751e-07, "epoch": 0.42724104664212165, "percentage": 2.85, "elapsed_time": "0:43:20", "remaining_time": "1 day, 0:38:35", "throughput": 8497.57, "total_tokens": 22101792} {"current_steps": 21800, "total_steps": 761865, "loss": 1.9401, "lr": 9.979829467870365e-07, "epoch": 0.4292098993916245, "percentage": 2.86, "elapsed_time": "0:43:33", "remaining_time": "1 day, 0:38:33", "throughput": 8496.85, "total_tokens": 22204192} {"current_steps": 21900, "total_steps": 761865, "loss": 1.9513, "lr": 9.97964403338522e-07, "epoch": 0.4311787521411274, "percentage": 2.87, "elapsed_time": "0:43:45", "remaining_time": "1 day, 0:38:28", "throughput": 8496.15, "total_tokens": 22306048} {"current_steps": 22000, "total_steps": 761865, "loss": 2.0143, "lr": 9.979457752153606e-07, "epoch": 0.43314760489063026, "percentage": 2.89, "elapsed_time": "0:43:57", "remaining_time": "1 day, 0:38:25", "throughput": 8495.34, "total_tokens": 22407904} {"current_steps": 22100, "total_steps": 761865, "loss": 1.9838, "lr": 9.979270624207201e-07, "epoch": 0.43511645764013307, "percentage": 2.9, "elapsed_time": "0:44:09", "remaining_time": "1 day, 0:38:22", "throughput": 8494.64, "total_tokens": 22510208} {"current_steps": 22200, "total_steps": 761865, "loss": 1.9756, "lr": 9.979082649577826e-07, "epoch": 0.43708531038963594, "percentage": 2.91, "elapsed_time": "0:44:22", "remaining_time": "1 day, 0:38:17", "throughput": 8493.9, "total_tokens": 22611880} {"current_steps": 22300, "total_steps": 761865, "loss": 1.9765, "lr": 9.97889382829744e-07, "epoch": 0.4390541631391388, "percentage": 2.93, "elapsed_time": "0:44:34", "remaining_time": "1 day, 0:38:14", "throughput": 8493.26, "total_tokens": 22714280} {"current_steps": 22400, "total_steps": 761865, "loss": 1.9983, "lr": 9.97870416039815e-07, "epoch": 0.4410230158886417, "percentage": 2.94, "elapsed_time": "0:44:46", "remaining_time": "1 day, 0:38:07", "throughput": 8492.42, "total_tokens": 22815312} {"current_steps": 22500, "total_steps": 761865, "loss": 1.9532, "lr": 9.978513645912214e-07, "epoch": 0.44299186863814455, "percentage": 2.95, "elapsed_time": "0:44:58", "remaining_time": "1 day, 0:38:04", "throughput": 8491.83, "total_tokens": 22917712} {"current_steps": 22600, "total_steps": 761865, "loss": 1.9757, "lr": 9.978322284872021e-07, "epoch": 0.4449607213876474, "percentage": 2.97, "elapsed_time": "0:45:11", "remaining_time": "1 day, 0:37:59", "throughput": 8491.12, "total_tokens": 23019560} {"current_steps": 22700, "total_steps": 761865, "loss": 1.973, "lr": 9.978130077310113e-07, "epoch": 0.4469295741371503, "percentage": 2.98, "elapsed_time": "0:45:23", "remaining_time": "1 day, 0:37:56", "throughput": 8490.43, "total_tokens": 23121960} {"current_steps": 22800, "total_steps": 761865, "loss": 1.9391, "lr": 9.977937023259173e-07, "epoch": 0.44889842688665316, "percentage": 2.99, "elapsed_time": "0:45:35", "remaining_time": "1 day, 0:37:53", "throughput": 8489.78, "total_tokens": 23224360} {"current_steps": 22900, "total_steps": 761865, "loss": 1.9796, "lr": 9.97774312275203e-07, "epoch": 0.450867279636156, "percentage": 3.01, "elapsed_time": "0:45:47", "remaining_time": "1 day, 0:37:49", "throughput": 8489.06, "total_tokens": 23326288} {"current_steps": 23000, "total_steps": 761865, "loss": 1.9697, "lr": 9.977548375821649e-07, "epoch": 0.4528361323856589, "percentage": 3.02, "elapsed_time": "0:46:00", "remaining_time": "1 day, 0:37:45", "throughput": 8488.47, "total_tokens": 23428688} {"current_steps": 23100, "total_steps": 761865, "loss": 1.9518, "lr": 9.977352782501151e-07, "epoch": 0.45480498513516177, "percentage": 3.03, "elapsed_time": "0:46:12", "remaining_time": "1 day, 0:37:42", "throughput": 8487.84, "total_tokens": 23531088} {"current_steps": 23200, "total_steps": 761865, "loss": 1.9559, "lr": 9.977156342823794e-07, "epoch": 0.4567738378846646, "percentage": 3.05, "elapsed_time": "0:46:24", "remaining_time": "1 day, 0:37:38", "throughput": 8487.29, "total_tokens": 23633488} {"current_steps": 23300, "total_steps": 761865, "loss": 2.0245, "lr": 9.97695905682298e-07, "epoch": 0.45874269063416745, "percentage": 3.06, "elapsed_time": "0:46:36", "remaining_time": "1 day, 0:37:34", "throughput": 8486.66, "total_tokens": 23735888} {"current_steps": 23400, "total_steps": 761865, "loss": 1.9733, "lr": 9.976760924532254e-07, "epoch": 0.4607115433836703, "percentage": 3.07, "elapsed_time": "0:46:49", "remaining_time": "1 day, 0:37:27", "throughput": 8485.95, "total_tokens": 23837088} {"current_steps": 23500, "total_steps": 761865, "loss": 1.9581, "lr": 9.976561945985312e-07, "epoch": 0.4626803961331732, "percentage": 3.08, "elapsed_time": "0:47:01", "remaining_time": "1 day, 0:37:23", "throughput": 8485.34, "total_tokens": 23939488} {"current_steps": 23600, "total_steps": 761865, "loss": 2.0525, "lr": 9.976362121215984e-07, "epoch": 0.46464924888267606, "percentage": 3.1, "elapsed_time": "0:47:13", "remaining_time": "1 day, 0:37:14", "throughput": 8484.52, "total_tokens": 24039880} {"current_steps": 23700, "total_steps": 761865, "loss": 1.9868, "lr": 9.97616145025825e-07, "epoch": 0.4666181016321789, "percentage": 3.11, "elapsed_time": "0:47:25", "remaining_time": "1 day, 0:37:10", "throughput": 8483.84, "total_tokens": 24141800} {"current_steps": 23800, "total_steps": 761865, "loss": 2.006, "lr": 9.975959933146231e-07, "epoch": 0.4685869543816818, "percentage": 3.12, "elapsed_time": "0:47:37", "remaining_time": "1 day, 0:37:01", "throughput": 8483.1, "total_tokens": 24242464} {"current_steps": 23900, "total_steps": 761865, "loss": 1.9781, "lr": 9.975757569914196e-07, "epoch": 0.47055580713118467, "percentage": 3.14, "elapsed_time": "0:47:49", "remaining_time": "1 day, 0:36:57", "throughput": 8482.55, "total_tokens": 24344864} {"current_steps": 24000, "total_steps": 761865, "loss": 2.0087, "lr": 9.975554360596554e-07, "epoch": 0.47252465988068754, "percentage": 3.15, "elapsed_time": "0:48:02", "remaining_time": "1 day, 0:36:52", "throughput": 8482.02, "total_tokens": 24447264} {"current_steps": 24100, "total_steps": 761865, "loss": 1.9695, "lr": 9.975350305227858e-07, "epoch": 0.4744935126301904, "percentage": 3.16, "elapsed_time": "0:48:14", "remaining_time": "1 day, 0:36:49", "throughput": 8481.37, "total_tokens": 24549664} {"current_steps": 24200, "total_steps": 761865, "loss": 2.0153, "lr": 9.975145403842806e-07, "epoch": 0.4764623653796933, "percentage": 3.18, "elapsed_time": "0:48:26", "remaining_time": "1 day, 0:36:42", "throughput": 8480.79, "total_tokens": 24651336} {"current_steps": 24300, "total_steps": 761865, "loss": 1.9615, "lr": 9.97493965647624e-07, "epoch": 0.4784312181291961, "percentage": 3.19, "elapsed_time": "0:48:38", "remaining_time": "1 day, 0:36:37", "throughput": 8480.19, "total_tokens": 24753216} {"current_steps": 24400, "total_steps": 761865, "loss": 1.9781, "lr": 9.974733063163148e-07, "epoch": 0.48040007087869896, "percentage": 3.2, "elapsed_time": "0:48:51", "remaining_time": "1 day, 0:36:31", "throughput": 8479.55, "total_tokens": 24854888} {"current_steps": 24500, "total_steps": 761865, "loss": 2.0, "lr": 9.974525623938657e-07, "epoch": 0.48236892362820183, "percentage": 3.22, "elapsed_time": "0:49:03", "remaining_time": "1 day, 0:36:26", "throughput": 8479.02, "total_tokens": 24957288} {"current_steps": 24600, "total_steps": 761865, "loss": 1.985, "lr": 9.97431733883804e-07, "epoch": 0.4843377763777047, "percentage": 3.23, "elapsed_time": "0:49:15", "remaining_time": "1 day, 0:36:21", "throughput": 8478.43, "total_tokens": 25059480} {"current_steps": 24700, "total_steps": 761865, "loss": 1.962, "lr": 9.974108207896715e-07, "epoch": 0.48630662912720757, "percentage": 3.24, "elapsed_time": "0:49:27", "remaining_time": "1 day, 0:36:15", "throughput": 8477.84, "total_tokens": 25161104} {"current_steps": 24800, "total_steps": 761865, "loss": 1.9843, "lr": 9.973898231150243e-07, "epoch": 0.48827548187671044, "percentage": 3.26, "elapsed_time": "0:49:40", "remaining_time": "1 day, 0:36:09", "throughput": 8477.26, "total_tokens": 25262976} {"current_steps": 24900, "total_steps": 761865, "loss": 1.9635, "lr": 9.973687408634329e-07, "epoch": 0.4902443346262133, "percentage": 3.27, "elapsed_time": "0:49:52", "remaining_time": "1 day, 0:36:04", "throughput": 8476.76, "total_tokens": 25365376} {"current_steps": 25000, "total_steps": 761865, "loss": 1.9557, "lr": 9.97347574038482e-07, "epoch": 0.4922131873757162, "percentage": 3.28, "elapsed_time": "0:50:04", "remaining_time": "1 day, 0:35:56", "throughput": 8476.13, "total_tokens": 25466552} {"current_steps": 25100, "total_steps": 761865, "loss": 1.9476, "lr": 9.97326322643771e-07, "epoch": 0.49418204012521905, "percentage": 3.29, "elapsed_time": "0:50:17", "remaining_time": "1 day, 0:36:03", "throughput": 8473.99, "total_tokens": 25567552} {"current_steps": 25200, "total_steps": 761865, "loss": 2.011, "lr": 9.973049866829136e-07, "epoch": 0.4961508928747219, "percentage": 3.31, "elapsed_time": "0:50:29", "remaining_time": "1 day, 0:35:57", "throughput": 8473.44, "total_tokens": 25669424} {"current_steps": 25300, "total_steps": 761865, "loss": 1.9997, "lr": 9.972835661595377e-07, "epoch": 0.4981197456242248, "percentage": 3.32, "elapsed_time": "0:50:41", "remaining_time": "1 day, 0:35:52", "throughput": 8472.9, "total_tokens": 25771736} {"current_steps": 25400, "total_steps": 761865, "loss": 2.0229, "lr": 9.972620610772853e-07, "epoch": 0.5000885983737277, "percentage": 3.33, "elapsed_time": "0:50:53", "remaining_time": "1 day, 0:35:43", "throughput": 8472.18, "total_tokens": 25872328} {"current_steps": 25500, "total_steps": 761865, "loss": 2.0027, "lr": 9.972404714398137e-07, "epoch": 0.5020574511232305, "percentage": 3.35, "elapsed_time": "0:51:05", "remaining_time": "1 day, 0:35:35", "throughput": 8471.42, "total_tokens": 25972904} {"current_steps": 25600, "total_steps": 761865, "loss": 1.9755, "lr": 9.97218797250794e-07, "epoch": 0.5040263038727334, "percentage": 3.36, "elapsed_time": "0:51:18", "remaining_time": "1 day, 0:35:30", "throughput": 8470.93, "total_tokens": 26075304} {"current_steps": 25700, "total_steps": 761865, "loss": 1.9947, "lr": 9.971970385139114e-07, "epoch": 0.5059951566222363, "percentage": 3.37, "elapsed_time": "0:51:30", "remaining_time": "1 day, 0:35:22", "throughput": 8470.26, "total_tokens": 26176432} {"current_steps": 25800, "total_steps": 761865, "loss": 2.0154, "lr": 9.971751952328662e-07, "epoch": 0.5079640093717391, "percentage": 3.39, "elapsed_time": "0:51:42", "remaining_time": "1 day, 0:35:14", "throughput": 8469.52, "total_tokens": 26277160} {"current_steps": 25900, "total_steps": 761865, "loss": 2.0067, "lr": 9.97153267411372e-07, "epoch": 0.509932862121242, "percentage": 3.4, "elapsed_time": "0:51:54", "remaining_time": "1 day, 0:35:08", "throughput": 8468.98, "total_tokens": 26378984} {"current_steps": 26000, "total_steps": 761865, "loss": 2.0285, "lr": 9.971312550531582e-07, "epoch": 0.5119017148707448, "percentage": 3.41, "elapsed_time": "0:52:06", "remaining_time": "1 day, 0:35:00", "throughput": 8468.46, "total_tokens": 26480568} {"current_steps": 26100, "total_steps": 761865, "loss": 1.9685, "lr": 9.971091581619674e-07, "epoch": 0.5138705676202476, "percentage": 3.43, "elapsed_time": "0:52:19", "remaining_time": "1 day, 0:34:55", "throughput": 8467.99, "total_tokens": 26582968} {"current_steps": 26200, "total_steps": 761865, "loss": 1.9568, "lr": 9.970869767415572e-07, "epoch": 0.5158394203697505, "percentage": 3.44, "elapsed_time": "0:52:31", "remaining_time": "1 day, 0:34:50", "throughput": 8467.52, "total_tokens": 26685368} {"current_steps": 26300, "total_steps": 761865, "loss": 2.0229, "lr": 9.97064710795699e-07, "epoch": 0.5178082731192534, "percentage": 3.45, "elapsed_time": "0:52:43", "remaining_time": "1 day, 0:34:43", "throughput": 8467.02, "total_tokens": 26787328} {"current_steps": 26400, "total_steps": 761865, "loss": 1.9997, "lr": 9.970423603281792e-07, "epoch": 0.5197771258687562, "percentage": 3.47, "elapsed_time": "0:52:55", "remaining_time": "1 day, 0:34:35", "throughput": 8466.38, "total_tokens": 26888392} {"current_steps": 26500, "total_steps": 761865, "loss": 2.0388, "lr": 9.970199253427984e-07, "epoch": 0.5217459786182591, "percentage": 3.48, "elapsed_time": "0:53:08", "remaining_time": "1 day, 0:34:29", "throughput": 8465.86, "total_tokens": 26990144} {"current_steps": 26600, "total_steps": 761865, "loss": 2.0231, "lr": 9.969974058433712e-07, "epoch": 0.523714831367762, "percentage": 3.49, "elapsed_time": "0:53:20", "remaining_time": "1 day, 0:34:21", "throughput": 8465.3, "total_tokens": 27091712} {"current_steps": 26700, "total_steps": 761865, "loss": 1.9902, "lr": 9.96974801833727e-07, "epoch": 0.5256836841172648, "percentage": 3.5, "elapsed_time": "0:53:32", "remaining_time": "1 day, 0:34:16", "throughput": 8464.86, "total_tokens": 27194112} {"current_steps": 26800, "total_steps": 761865, "loss": 2.0088, "lr": 9.969521133177095e-07, "epoch": 0.5276525368667677, "percentage": 3.52, "elapsed_time": "0:53:44", "remaining_time": "1 day, 0:34:10", "throughput": 8464.41, "total_tokens": 27296512} {"current_steps": 26900, "total_steps": 761865, "loss": 1.9835, "lr": 9.969293402991768e-07, "epoch": 0.5296213896162706, "percentage": 3.53, "elapsed_time": "0:53:57", "remaining_time": "1 day, 0:34:04", "throughput": 8463.81, "total_tokens": 27398144} {"current_steps": 27000, "total_steps": 761865, "loss": 1.9739, "lr": 9.969064827820009e-07, "epoch": 0.5315902423657735, "percentage": 3.54, "elapsed_time": "0:54:09", "remaining_time": "1 day, 0:33:58", "throughput": 8463.41, "total_tokens": 27500544} {"current_steps": 27100, "total_steps": 761865, "loss": 1.9942, "lr": 9.968835407700687e-07, "epoch": 0.5335590951152763, "percentage": 3.56, "elapsed_time": "0:54:21", "remaining_time": "1 day, 0:33:51", "throughput": 8463.05, "total_tokens": 27602944} {"current_steps": 27200, "total_steps": 761865, "loss": 1.9802, "lr": 9.968605142672813e-07, "epoch": 0.5355279478647792, "percentage": 3.57, "elapsed_time": "0:54:33", "remaining_time": "1 day, 0:33:44", "throughput": 8462.55, "total_tokens": 27704704} {"current_steps": 27300, "total_steps": 761865, "loss": 2.0222, "lr": 9.968374032775542e-07, "epoch": 0.5374968006142821, "percentage": 3.58, "elapsed_time": "0:54:45", "remaining_time": "1 day, 0:33:36", "throughput": 8461.94, "total_tokens": 27805696} {"current_steps": 27400, "total_steps": 761865, "loss": 1.986, "lr": 9.968142078048171e-07, "epoch": 0.5394656533637849, "percentage": 3.6, "elapsed_time": "0:54:58", "remaining_time": "1 day, 0:33:28", "throughput": 8461.41, "total_tokens": 27907048} {"current_steps": 27500, "total_steps": 761865, "loss": 1.9341, "lr": 9.967909278530144e-07, "epoch": 0.5414345061132878, "percentage": 3.61, "elapsed_time": "0:55:10", "remaining_time": "1 day, 0:33:22", "throughput": 8460.98, "total_tokens": 28009448} {"current_steps": 27600, "total_steps": 761865, "loss": 1.9452, "lr": 9.967675634261043e-07, "epoch": 0.5434033588627907, "percentage": 3.62, "elapsed_time": "0:55:22", "remaining_time": "1 day, 0:33:16", "throughput": 8460.57, "total_tokens": 28111848} {"current_steps": 27700, "total_steps": 761865, "loss": 1.9426, "lr": 9.967441145280603e-07, "epoch": 0.5453722116122935, "percentage": 3.64, "elapsed_time": "0:55:35", "remaining_time": "1 day, 0:33:12", "throughput": 8459.81, "total_tokens": 28213720} {"current_steps": 27800, "total_steps": 761865, "loss": 1.9545, "lr": 9.967205811628691e-07, "epoch": 0.5473410643617964, "percentage": 3.65, "elapsed_time": "0:55:47", "remaining_time": "1 day, 0:33:08", "throughput": 8459.14, "total_tokens": 28316120} {"current_steps": 27900, "total_steps": 761865, "loss": 1.9895, "lr": 9.966969633345327e-07, "epoch": 0.5493099171112993, "percentage": 3.66, "elapsed_time": "0:55:59", "remaining_time": "1 day, 0:33:04", "throughput": 8458.39, "total_tokens": 28417872} {"current_steps": 28000, "total_steps": 761865, "loss": 1.9813, "lr": 9.96673261047067e-07, "epoch": 0.5512787698608022, "percentage": 3.68, "elapsed_time": "0:56:12", "remaining_time": "1 day, 0:33:00", "throughput": 8457.55, "total_tokens": 28519480} {"current_steps": 28100, "total_steps": 761865, "loss": 1.9445, "lr": 9.966494743045026e-07, "epoch": 0.553247622610305, "percentage": 3.69, "elapsed_time": "0:56:24", "remaining_time": "1 day, 0:32:55", "throughput": 8456.81, "total_tokens": 28621056} {"current_steps": 28200, "total_steps": 761865, "loss": 2.0336, "lr": 9.96625603110884e-07, "epoch": 0.5552164753598079, "percentage": 3.7, "elapsed_time": "0:56:36", "remaining_time": "1 day, 0:32:48", "throughput": 8455.86, "total_tokens": 28721304} {"current_steps": 28300, "total_steps": 761865, "loss": 1.9648, "lr": 9.9660164747027e-07, "epoch": 0.5571853281093107, "percentage": 3.71, "elapsed_time": "0:56:48", "remaining_time": "1 day, 0:32:44", "throughput": 8455.24, "total_tokens": 28823704} {"current_steps": 28400, "total_steps": 761865, "loss": 1.9886, "lr": 9.965776073867346e-07, "epoch": 0.5591541808588135, "percentage": 3.73, "elapsed_time": "0:57:01", "remaining_time": "1 day, 0:32:41", "throughput": 8454.55, "total_tokens": 28926104} {"current_steps": 28500, "total_steps": 761865, "loss": 2.0234, "lr": 9.965534828643655e-07, "epoch": 0.5611230336083164, "percentage": 3.74, "elapsed_time": "0:57:13", "remaining_time": "1 day, 0:32:34", "throughput": 8453.72, "total_tokens": 29027024} {"current_steps": 28600, "total_steps": 761865, "loss": 1.9691, "lr": 9.965292739072645e-07, "epoch": 0.5630918863578193, "percentage": 3.75, "elapsed_time": "0:57:25", "remaining_time": "1 day, 0:32:29", "throughput": 8453.06, "total_tokens": 29128792} {"current_steps": 28700, "total_steps": 761865, "loss": 2.0016, "lr": 9.965049805195486e-07, "epoch": 0.5650607391073221, "percentage": 3.77, "elapsed_time": "0:57:38", "remaining_time": "1 day, 0:32:25", "throughput": 8452.3, "total_tokens": 29230640} {"current_steps": 28800, "total_steps": 761865, "loss": 1.9457, "lr": 9.964806027053485e-07, "epoch": 0.567029591856825, "percentage": 3.78, "elapsed_time": "0:57:50", "remaining_time": "1 day, 0:32:20", "throughput": 8451.57, "total_tokens": 29332304} {"current_steps": 28900, "total_steps": 761865, "loss": 2.1029, "lr": 9.964561404688095e-07, "epoch": 0.5689984446063279, "percentage": 3.79, "elapsed_time": "0:58:02", "remaining_time": "1 day, 0:32:13", "throughput": 8450.73, "total_tokens": 29432944} {"current_steps": 29000, "total_steps": 761865, "loss": 1.9671, "lr": 9.964315938140908e-07, "epoch": 0.5709672973558307, "percentage": 3.81, "elapsed_time": "0:58:15", "remaining_time": "1 day, 0:32:07", "throughput": 8449.86, "total_tokens": 29533832} {"current_steps": 29100, "total_steps": 761865, "loss": 1.9647, "lr": 9.96406962745367e-07, "epoch": 0.5729361501053336, "percentage": 3.82, "elapsed_time": "0:58:27", "remaining_time": "1 day, 0:32:03", "throughput": 8449.25, "total_tokens": 29636232} {"current_steps": 29200, "total_steps": 761865, "loss": 1.973, "lr": 9.963822472668257e-07, "epoch": 0.5749050028548365, "percentage": 3.83, "elapsed_time": "0:58:39", "remaining_time": "1 day, 0:31:59", "throughput": 8448.64, "total_tokens": 29738632} {"current_steps": 29300, "total_steps": 761865, "loss": 1.9592, "lr": 9.963574473826702e-07, "epoch": 0.5768738556043393, "percentage": 3.85, "elapsed_time": "0:58:52", "remaining_time": "1 day, 0:31:54", "throughput": 8447.88, "total_tokens": 29840240} {"current_steps": 29400, "total_steps": 761865, "loss": 1.9705, "lr": 9.963325630971172e-07, "epoch": 0.5788427083538422, "percentage": 3.86, "elapsed_time": "0:59:04", "remaining_time": "1 day, 0:31:50", "throughput": 8447.28, "total_tokens": 29942640} {"current_steps": 29500, "total_steps": 761865, "loss": 2.0044, "lr": 9.96307594414398e-07, "epoch": 0.5808115611033451, "percentage": 3.87, "elapsed_time": "0:59:16", "remaining_time": "1 day, 0:31:39", "throughput": 8446.75, "total_tokens": 30043048} {"current_steps": 29600, "total_steps": 761865, "loss": 1.9797, "lr": 9.962825413387585e-07, "epoch": 0.582780413852848, "percentage": 3.89, "elapsed_time": "0:59:29", "remaining_time": "1 day, 0:31:32", "throughput": 8446.43, "total_tokens": 30145448} {"current_steps": 29700, "total_steps": 761865, "loss": 1.9933, "lr": 9.962574038744587e-07, "epoch": 0.5847492666023508, "percentage": 3.9, "elapsed_time": "0:59:41", "remaining_time": "1 day, 0:31:24", "throughput": 8446.06, "total_tokens": 30247384} {"current_steps": 29800, "total_steps": 761865, "loss": 1.9392, "lr": 9.96232182025773e-07, "epoch": 0.5867181193518537, "percentage": 3.91, "elapsed_time": "0:59:53", "remaining_time": "1 day, 0:31:17", "throughput": 8445.72, "total_tokens": 30349784} {"current_steps": 29900, "total_steps": 761865, "loss": 2.0357, "lr": 9.962068757969902e-07, "epoch": 0.5886869721013566, "percentage": 3.92, "elapsed_time": "1:00:05", "remaining_time": "1 day, 0:31:10", "throughput": 8445.41, "total_tokens": 30452184} {"current_steps": 30000, "total_steps": 761865, "loss": 1.9804, "lr": 9.961814851924132e-07, "epoch": 0.5906558248508594, "percentage": 3.94, "elapsed_time": "1:00:17", "remaining_time": "1 day, 0:31:02", "throughput": 8445.0, "total_tokens": 30553720} {"current_steps": 30100, "total_steps": 761865, "loss": 1.9781, "lr": 9.9615601021636e-07, "epoch": 0.5926246776003623, "percentage": 3.95, "elapsed_time": "1:00:30", "remaining_time": "1 day, 0:31:07", "throughput": 8443.46, "total_tokens": 30656120} {"current_steps": 30200, "total_steps": 761865, "loss": 2.001, "lr": 9.961304508731616e-07, "epoch": 0.5945935303498652, "percentage": 3.96, "elapsed_time": "1:00:42", "remaining_time": "1 day, 0:30:59", "throughput": 8443.01, "total_tokens": 30757728} {"current_steps": 30300, "total_steps": 761865, "loss": 2.0252, "lr": 9.961048071671648e-07, "epoch": 0.596562383099368, "percentage": 3.98, "elapsed_time": "1:00:55", "remaining_time": "1 day, 0:30:52", "throughput": 8442.7, "total_tokens": 30860128} {"current_steps": 30400, "total_steps": 761865, "loss": 1.9911, "lr": 9.960790791027297e-07, "epoch": 0.5985312358488709, "percentage": 3.99, "elapsed_time": "1:01:07", "remaining_time": "1 day, 0:30:42", "throughput": 8442.23, "total_tokens": 30960928} {"current_steps": 30500, "total_steps": 761865, "loss": 1.953, "lr": 9.960532666842317e-07, "epoch": 0.6005000885983738, "percentage": 4.0, "elapsed_time": "1:01:19", "remaining_time": "1 day, 0:30:33", "throughput": 8441.82, "total_tokens": 31062480} {"current_steps": 30600, "total_steps": 761865, "loss": 1.9692, "lr": 9.960273699160593e-07, "epoch": 0.6024689413478765, "percentage": 4.02, "elapsed_time": "1:01:31", "remaining_time": "1 day, 0:30:24", "throughput": 8441.34, "total_tokens": 31163536} {"current_steps": 30700, "total_steps": 761865, "loss": 2.0457, "lr": 9.960013888026165e-07, "epoch": 0.6044377940973794, "percentage": 4.03, "elapsed_time": "1:01:43", "remaining_time": "1 day, 0:30:14", "throughput": 8440.82, "total_tokens": 31264296} {"current_steps": 30800, "total_steps": 761865, "loss": 1.9794, "lr": 9.95975323348321e-07, "epoch": 0.6064066468468823, "percentage": 4.04, "elapsed_time": "1:01:56", "remaining_time": "1 day, 0:30:06", "throughput": 8440.5, "total_tokens": 31366200} {"current_steps": 30900, "total_steps": 761865, "loss": 1.9788, "lr": 9.959491735576048e-07, "epoch": 0.6083754995963851, "percentage": 4.06, "elapsed_time": "1:02:08", "remaining_time": "1 day, 0:29:57", "throughput": 8440.14, "total_tokens": 31468056} {"current_steps": 31000, "total_steps": 761865, "loss": 2.0007, "lr": 9.95922939434915e-07, "epoch": 0.610344352345888, "percentage": 4.07, "elapsed_time": "1:02:20", "remaining_time": "1 day, 0:29:49", "throughput": 8439.78, "total_tokens": 31570024} {"current_steps": 31100, "total_steps": 761865, "loss": 2.0011, "lr": 9.958966209847119e-07, "epoch": 0.6123132050953909, "percentage": 4.08, "elapsed_time": "1:02:32", "remaining_time": "1 day, 0:29:38", "throughput": 8439.34, "total_tokens": 31670456} {"current_steps": 31200, "total_steps": 761865, "loss": 2.0265, "lr": 9.95870218211471e-07, "epoch": 0.6142820578448938, "percentage": 4.1, "elapsed_time": "1:02:44", "remaining_time": "1 day, 0:29:30", "throughput": 8438.98, "total_tokens": 31772304} {"current_steps": 31300, "total_steps": 761865, "loss": 2.0047, "lr": 9.95843731119682e-07, "epoch": 0.6162509105943966, "percentage": 4.11, "elapsed_time": "1:02:57", "remaining_time": "1 day, 0:29:21", "throughput": 8438.67, "total_tokens": 31874224} {"current_steps": 31400, "total_steps": 761865, "loss": 1.9865, "lr": 9.958171597138484e-07, "epoch": 0.6182197633438995, "percentage": 4.12, "elapsed_time": "1:03:09", "remaining_time": "1 day, 0:29:12", "throughput": 8438.3, "total_tokens": 31975768} {"current_steps": 31500, "total_steps": 761865, "loss": 1.9703, "lr": 9.957905039984888e-07, "epoch": 0.6201886160934024, "percentage": 4.13, "elapsed_time": "1:03:21", "remaining_time": "1 day, 0:29:03", "throughput": 8437.93, "total_tokens": 32077064} {"current_steps": 31600, "total_steps": 761865, "loss": 1.9939, "lr": 9.957637639781359e-07, "epoch": 0.6221574688429052, "percentage": 4.15, "elapsed_time": "1:03:33", "remaining_time": "1 day, 0:28:54", "throughput": 8437.59, "total_tokens": 32178832} {"current_steps": 31700, "total_steps": 761865, "loss": 1.9873, "lr": 9.957369396573362e-07, "epoch": 0.6241263215924081, "percentage": 4.16, "elapsed_time": "1:03:46", "remaining_time": "1 day, 0:28:46", "throughput": 8437.32, "total_tokens": 32281232} {"current_steps": 31800, "total_steps": 761865, "loss": 2.0094, "lr": 9.957100310406511e-07, "epoch": 0.626095174341911, "percentage": 4.17, "elapsed_time": "1:03:58", "remaining_time": "1 day, 0:28:39", "throughput": 8437.04, "total_tokens": 32383632} {"current_steps": 31900, "total_steps": 761865, "loss": 1.9753, "lr": 9.956830381326565e-07, "epoch": 0.6280640270914138, "percentage": 4.19, "elapsed_time": "1:04:10", "remaining_time": "1 day, 0:28:32", "throughput": 8436.7, "total_tokens": 32486032} {"current_steps": 32000, "total_steps": 761865, "loss": 2.0039, "lr": 9.956559609379418e-07, "epoch": 0.6300328798409167, "percentage": 4.2, "elapsed_time": "1:04:22", "remaining_time": "1 day, 0:28:24", "throughput": 8436.42, "total_tokens": 32588432} {"current_steps": 32100, "total_steps": 761865, "loss": 2.0084, "lr": 9.956287994611116e-07, "epoch": 0.6320017325904196, "percentage": 4.21, "elapsed_time": "1:04:34", "remaining_time": "1 day, 0:28:13", "throughput": 8436.0, "total_tokens": 32688968} {"current_steps": 32200, "total_steps": 761865, "loss": 2.0633, "lr": 9.956015537067843e-07, "epoch": 0.6339705853399225, "percentage": 4.23, "elapsed_time": "1:04:47", "remaining_time": "1 day, 0:28:04", "throughput": 8435.68, "total_tokens": 32790728} {"current_steps": 32300, "total_steps": 761865, "loss": 2.0204, "lr": 9.95574223679593e-07, "epoch": 0.6359394380894253, "percentage": 4.24, "elapsed_time": "1:04:59", "remaining_time": "1 day, 0:27:56", "throughput": 8435.24, "total_tokens": 32892320} {"current_steps": 32400, "total_steps": 761865, "loss": 1.9224, "lr": 9.955468093841848e-07, "epoch": 0.6379082908389282, "percentage": 4.25, "elapsed_time": "1:05:11", "remaining_time": "1 day, 0:27:48", "throughput": 8434.96, "total_tokens": 32994720} {"current_steps": 32500, "total_steps": 761865, "loss": 2.0055, "lr": 9.955193108252214e-07, "epoch": 0.6398771435884311, "percentage": 4.27, "elapsed_time": "1:05:23", "remaining_time": "1 day, 0:27:38", "throughput": 8434.52, "total_tokens": 33095600} {"current_steps": 32600, "total_steps": 761865, "loss": 1.993, "lr": 9.954917280073784e-07, "epoch": 0.6418459963379339, "percentage": 4.28, "elapsed_time": "1:05:36", "remaining_time": "1 day, 0:27:29", "throughput": 8434.14, "total_tokens": 33197152} {"current_steps": 32700, "total_steps": 761865, "loss": 1.9665, "lr": 9.954640609353462e-07, "epoch": 0.6438148490874368, "percentage": 4.29, "elapsed_time": "1:05:48", "remaining_time": "1 day, 0:27:19", "throughput": 8433.8, "total_tokens": 33298512} {"current_steps": 32800, "total_steps": 761865, "loss": 2.0437, "lr": 9.954363096138297e-07, "epoch": 0.6457837018369396, "percentage": 4.31, "elapsed_time": "1:06:00", "remaining_time": "1 day, 0:27:05", "throughput": 8433.29, "total_tokens": 33397424} {"current_steps": 32900, "total_steps": 761865, "loss": 1.9945, "lr": 9.95408474047547e-07, "epoch": 0.6477525545864424, "percentage": 4.32, "elapsed_time": "1:06:12", "remaining_time": "1 day, 0:26:57", "throughput": 8432.97, "total_tokens": 33499384} {"current_steps": 33000, "total_steps": 761865, "loss": 1.966, "lr": 9.95380554241232e-07, "epoch": 0.6497214073359453, "percentage": 4.33, "elapsed_time": "1:06:24", "remaining_time": "1 day, 0:26:49", "throughput": 8432.61, "total_tokens": 33601552} {"current_steps": 33100, "total_steps": 761865, "loss": 1.9928, "lr": 9.95352550199632e-07, "epoch": 0.6516902600854482, "percentage": 4.34, "elapsed_time": "1:06:36", "remaining_time": "1 day, 0:26:42", "throughput": 8432.32, "total_tokens": 33703952} {"current_steps": 33200, "total_steps": 761865, "loss": 2.0221, "lr": 9.953244619275088e-07, "epoch": 0.653659112834951, "percentage": 4.36, "elapsed_time": "1:06:49", "remaining_time": "1 day, 0:26:34", "throughput": 8432.06, "total_tokens": 33806352} {"current_steps": 33300, "total_steps": 761865, "loss": 1.9933, "lr": 9.952962894296386e-07, "epoch": 0.6556279655844539, "percentage": 4.37, "elapsed_time": "1:07:01", "remaining_time": "1 day, 0:26:26", "throughput": 8431.77, "total_tokens": 33908752} {"current_steps": 33400, "total_steps": 761865, "loss": 1.9703, "lr": 9.952680327108122e-07, "epoch": 0.6575968183339568, "percentage": 4.38, "elapsed_time": "1:07:13", "remaining_time": "1 day, 0:26:18", "throughput": 8431.54, "total_tokens": 34011152} {"current_steps": 33500, "total_steps": 761865, "loss": 1.9908, "lr": 9.952396917758336e-07, "epoch": 0.6595656710834596, "percentage": 4.4, "elapsed_time": "1:07:26", "remaining_time": "1 day, 0:26:09", "throughput": 8431.25, "total_tokens": 34113048} {"current_steps": 33600, "total_steps": 761865, "loss": 2.0082, "lr": 9.952112666295227e-07, "epoch": 0.6615345238329625, "percentage": 4.41, "elapsed_time": "1:07:38", "remaining_time": "1 day, 0:26:01", "throughput": 8430.99, "total_tokens": 34215152} {"current_steps": 33700, "total_steps": 761865, "loss": 1.975, "lr": 9.951827572767128e-07, "epoch": 0.6635033765824654, "percentage": 4.42, "elapsed_time": "1:07:50", "remaining_time": "1 day, 0:25:51", "throughput": 8430.59, "total_tokens": 34316464} {"current_steps": 33800, "total_steps": 761865, "loss": 2.0031, "lr": 9.951541637222513e-07, "epoch": 0.6654722293319683, "percentage": 4.44, "elapsed_time": "1:08:02", "remaining_time": "1 day, 0:25:43", "throughput": 8430.26, "total_tokens": 34418312} {"current_steps": 33900, "total_steps": 761865, "loss": 1.9705, "lr": 9.95125485971001e-07, "epoch": 0.6674410820814711, "percentage": 4.45, "elapsed_time": "1:08:14", "remaining_time": "1 day, 0:25:33", "throughput": 8429.9, "total_tokens": 34519792} {"current_steps": 34000, "total_steps": 761865, "loss": 1.9463, "lr": 9.950967240278377e-07, "epoch": 0.669409934830974, "percentage": 4.46, "elapsed_time": "1:08:27", "remaining_time": "1 day, 0:25:25", "throughput": 8429.67, "total_tokens": 34622192} {"current_steps": 34100, "total_steps": 761865, "loss": 1.9799, "lr": 9.950678778976523e-07, "epoch": 0.6713787875804769, "percentage": 4.48, "elapsed_time": "1:08:39", "remaining_time": "1 day, 0:25:17", "throughput": 8429.42, "total_tokens": 34724592} {"current_steps": 34200, "total_steps": 761865, "loss": 1.9848, "lr": 9.950389475853499e-07, "epoch": 0.6733476403299797, "percentage": 4.49, "elapsed_time": "1:08:51", "remaining_time": "1 day, 0:25:09", "throughput": 8429.17, "total_tokens": 34826992} {"current_steps": 34300, "total_steps": 761865, "loss": 1.9814, "lr": 9.950099330958495e-07, "epoch": 0.6753164930794826, "percentage": 4.5, "elapsed_time": "1:09:03", "remaining_time": "1 day, 0:25:01", "throughput": 8428.94, "total_tokens": 34929392} {"current_steps": 34400, "total_steps": 761865, "loss": 2.0129, "lr": 9.949808344340855e-07, "epoch": 0.6772853458289855, "percentage": 4.52, "elapsed_time": "1:09:16", "remaining_time": "1 day, 0:24:52", "throughput": 8428.67, "total_tokens": 35031448} {"current_steps": 34500, "total_steps": 761865, "loss": 1.9997, "lr": 9.949516516050052e-07, "epoch": 0.6792541985784883, "percentage": 4.53, "elapsed_time": "1:09:28", "remaining_time": "1 day, 0:24:43", "throughput": 8428.39, "total_tokens": 35133128} {"current_steps": 34600, "total_steps": 761865, "loss": 1.9308, "lr": 9.949223846135713e-07, "epoch": 0.6812230513279912, "percentage": 4.54, "elapsed_time": "1:09:40", "remaining_time": "1 day, 0:24:34", "throughput": 8428.06, "total_tokens": 35234960} {"current_steps": 34700, "total_steps": 761865, "loss": 2.0636, "lr": 9.948930334647602e-07, "epoch": 0.6831919040774941, "percentage": 4.55, "elapsed_time": "1:09:52", "remaining_time": "1 day, 0:24:21", "throughput": 8427.6, "total_tokens": 35334576} {"current_steps": 34800, "total_steps": 761865, "loss": 1.9685, "lr": 9.94863598163563e-07, "epoch": 0.685160756826997, "percentage": 4.57, "elapsed_time": "1:10:04", "remaining_time": "1 day, 0:24:12", "throughput": 8427.31, "total_tokens": 35436176} {"current_steps": 34900, "total_steps": 761865, "loss": 1.9843, "lr": 9.948340787149847e-07, "epoch": 0.6871296095764998, "percentage": 4.58, "elapsed_time": "1:10:17", "remaining_time": "1 day, 0:24:03", "throughput": 8427.07, "total_tokens": 35538576} {"current_steps": 35000, "total_steps": 761865, "loss": 1.9959, "lr": 9.94804475124045e-07, "epoch": 0.6890984623260027, "percentage": 4.59, "elapsed_time": "1:10:29", "remaining_time": "1 day, 0:23:54", "throughput": 8426.78, "total_tokens": 35640288} {"current_steps": 35100, "total_steps": 761865, "loss": 1.988, "lr": 9.947747873957775e-07, "epoch": 0.6910673150755055, "percentage": 4.61, "elapsed_time": "1:10:42", "remaining_time": "1 day, 0:23:55", "throughput": 8425.49, "total_tokens": 35741992} {"current_steps": 35200, "total_steps": 761865, "loss": 1.9787, "lr": 9.94745015535231e-07, "epoch": 0.6930361678250083, "percentage": 4.62, "elapsed_time": "1:10:54", "remaining_time": "1 day, 0:23:46", "throughput": 8425.29, "total_tokens": 35844392} {"current_steps": 35300, "total_steps": 761865, "loss": 2.0372, "lr": 9.947151595474668e-07, "epoch": 0.6950050205745112, "percentage": 4.63, "elapsed_time": "1:11:06", "remaining_time": "1 day, 0:23:37", "throughput": 8425.02, "total_tokens": 35946208} {"current_steps": 35400, "total_steps": 761865, "loss": 1.9878, "lr": 9.946852194375629e-07, "epoch": 0.6969738733240141, "percentage": 4.65, "elapsed_time": "1:11:18", "remaining_time": "1 day, 0:23:28", "throughput": 8424.78, "total_tokens": 36048040} {"current_steps": 35500, "total_steps": 761865, "loss": 2.0269, "lr": 9.946551952106094e-07, "epoch": 0.6989427260735169, "percentage": 4.66, "elapsed_time": "1:11:31", "remaining_time": "1 day, 0:23:19", "throughput": 8424.57, "total_tokens": 36150440} {"current_steps": 35600, "total_steps": 761865, "loss": 2.0078, "lr": 9.946250868717122e-07, "epoch": 0.7009115788230198, "percentage": 4.67, "elapsed_time": "1:11:43", "remaining_time": "1 day, 0:23:09", "throughput": 8424.27, "total_tokens": 36251920} {"current_steps": 35700, "total_steps": 761865, "loss": 1.9861, "lr": 9.94594894425991e-07, "epoch": 0.7028804315725227, "percentage": 4.69, "elapsed_time": "1:11:55", "remaining_time": "1 day, 0:23:01", "throughput": 8424.05, "total_tokens": 36354320} {"current_steps": 35800, "total_steps": 761865, "loss": 1.9537, "lr": 9.945646178785797e-07, "epoch": 0.7048492843220255, "percentage": 4.7, "elapsed_time": "1:12:07", "remaining_time": "1 day, 0:22:52", "throughput": 8423.84, "total_tokens": 36456720} {"current_steps": 35900, "total_steps": 761865, "loss": 2.0293, "lr": 9.94534257234626e-07, "epoch": 0.7068181370715284, "percentage": 4.71, "elapsed_time": "1:12:19", "remaining_time": "1 day, 0:22:41", "throughput": 8423.5, "total_tokens": 36557424} {"current_steps": 36000, "total_steps": 761865, "loss": 1.9949, "lr": 9.945038124992933e-07, "epoch": 0.7087869898210313, "percentage": 4.73, "elapsed_time": "1:12:32", "remaining_time": "1 day, 0:22:31", "throughput": 8423.15, "total_tokens": 36658560} {"current_steps": 36100, "total_steps": 761865, "loss": 1.9858, "lr": 9.94473283677758e-07, "epoch": 0.7107558425705341, "percentage": 4.74, "elapsed_time": "1:12:44", "remaining_time": "1 day, 0:22:22", "throughput": 8422.94, "total_tokens": 36760960} {"current_steps": 36200, "total_steps": 761865, "loss": 2.0326, "lr": 9.944426707752117e-07, "epoch": 0.712724695320037, "percentage": 4.75, "elapsed_time": "1:12:56", "remaining_time": "1 day, 0:22:10", "throughput": 8422.6, "total_tokens": 36861200} {"current_steps": 36300, "total_steps": 761865, "loss": 1.9999, "lr": 9.944119737968592e-07, "epoch": 0.7146935480695399, "percentage": 4.76, "elapsed_time": "1:13:08", "remaining_time": "1 day, 0:22:01", "throughput": 8422.39, "total_tokens": 36963600} {"current_steps": 36400, "total_steps": 761865, "loss": 1.9843, "lr": 9.943811927479207e-07, "epoch": 0.7166624008190428, "percentage": 4.78, "elapsed_time": "1:13:20", "remaining_time": "1 day, 0:21:53", "throughput": 8422.19, "total_tokens": 37066000} {"current_steps": 36500, "total_steps": 761865, "loss": 1.9995, "lr": 9.9435032763363e-07, "epoch": 0.7186312535685456, "percentage": 4.79, "elapsed_time": "1:13:33", "remaining_time": "1 day, 0:21:44", "throughput": 8421.97, "total_tokens": 37168400} {"current_steps": 36600, "total_steps": 761865, "loss": 1.9962, "lr": 9.94319378459236e-07, "epoch": 0.7206001063180485, "percentage": 4.8, "elapsed_time": "1:13:45", "remaining_time": "1 day, 0:21:35", "throughput": 8421.65, "total_tokens": 37269864} {"current_steps": 36700, "total_steps": 761865, "loss": 1.9829, "lr": 9.94288345230001e-07, "epoch": 0.7225689590675514, "percentage": 4.82, "elapsed_time": "1:13:57", "remaining_time": "1 day, 0:21:25", "throughput": 8421.35, "total_tokens": 37371496} {"current_steps": 36800, "total_steps": 761865, "loss": 2.007, "lr": 9.942572279512014e-07, "epoch": 0.7245378118170542, "percentage": 4.83, "elapsed_time": "1:14:09", "remaining_time": "1 day, 0:21:15", "throughput": 8421.09, "total_tokens": 37473080} {"current_steps": 36900, "total_steps": 761865, "loss": 2.008, "lr": 9.942260266281295e-07, "epoch": 0.7265066645665571, "percentage": 4.84, "elapsed_time": "1:14:22", "remaining_time": "1 day, 0:21:06", "throughput": 8420.83, "total_tokens": 37574736} {"current_steps": 37000, "total_steps": 761865, "loss": 1.9557, "lr": 9.9419474126609e-07, "epoch": 0.72847551731606, "percentage": 4.86, "elapsed_time": "1:14:34", "remaining_time": "1 day, 0:20:55", "throughput": 8420.56, "total_tokens": 37676088} {"current_steps": 37100, "total_steps": 761865, "loss": 2.0327, "lr": 9.94163371870403e-07, "epoch": 0.7304443700655628, "percentage": 4.87, "elapsed_time": "1:14:46", "remaining_time": "1 day, 0:20:43", "throughput": 8420.04, "total_tokens": 37775664} {"current_steps": 37200, "total_steps": 761865, "loss": 1.9494, "lr": 9.941319184464026e-07, "epoch": 0.7324132228150657, "percentage": 4.88, "elapsed_time": "1:14:58", "remaining_time": "1 day, 0:20:34", "throughput": 8419.86, "total_tokens": 37878064} {"current_steps": 37300, "total_steps": 761865, "loss": 1.9297, "lr": 9.94100380999437e-07, "epoch": 0.7343820755645685, "percentage": 4.9, "elapsed_time": "1:15:10", "remaining_time": "1 day, 0:20:26", "throughput": 8419.67, "total_tokens": 37980464} {"current_steps": 37400, "total_steps": 761865, "loss": 2.0081, "lr": 9.940687595348693e-07, "epoch": 0.7363509283140713, "percentage": 4.91, "elapsed_time": "1:15:23", "remaining_time": "1 day, 0:20:16", "throughput": 8419.38, "total_tokens": 38082072} {"current_steps": 37500, "total_steps": 761865, "loss": 1.9588, "lr": 9.94037054058076e-07, "epoch": 0.7383197810635742, "percentage": 4.92, "elapsed_time": "1:15:35", "remaining_time": "1 day, 0:20:07", "throughput": 8419.2, "total_tokens": 38184472} {"current_steps": 37600, "total_steps": 761865, "loss": 1.9768, "lr": 9.940052645744488e-07, "epoch": 0.7402886338130771, "percentage": 4.94, "elapsed_time": "1:15:47", "remaining_time": "1 day, 0:19:58", "throughput": 8418.99, "total_tokens": 38286736} {"current_steps": 37700, "total_steps": 761865, "loss": 2.005, "lr": 9.939733910893928e-07, "epoch": 0.74225748656258, "percentage": 4.95, "elapsed_time": "1:15:59", "remaining_time": "1 day, 0:19:49", "throughput": 8418.74, "total_tokens": 38388616} {"current_steps": 37800, "total_steps": 761865, "loss": 1.9749, "lr": 9.93941433608328e-07, "epoch": 0.7442263393120828, "percentage": 4.96, "elapsed_time": "1:16:12", "remaining_time": "1 day, 0:19:39", "throughput": 8418.51, "total_tokens": 38490312} {"current_steps": 37900, "total_steps": 761865, "loss": 1.9948, "lr": 9.939093921366888e-07, "epoch": 0.7461951920615857, "percentage": 4.97, "elapsed_time": "1:16:24", "remaining_time": "1 day, 0:19:29", "throughput": 8418.22, "total_tokens": 38591968} {"current_steps": 38000, "total_steps": 761865, "loss": 1.9451, "lr": 9.93877266679923e-07, "epoch": 0.7481640448110886, "percentage": 4.99, "elapsed_time": "1:16:36", "remaining_time": "1 day, 0:19:20", "throughput": 8417.93, "total_tokens": 38693520} {"current_steps": 38100, "total_steps": 761865, "loss": 2.0305, "lr": 9.938450572434936e-07, "epoch": 0.7501328975605914, "percentage": 5.0, "elapsed_time": "1:16:48", "remaining_time": "1 day, 0:19:05", "throughput": 8417.5, "total_tokens": 38792232} {"current_steps": 38200, "total_steps": 761865, "loss": 1.9864, "lr": 9.938127638328775e-07, "epoch": 0.7521017503100943, "percentage": 5.01, "elapsed_time": "1:17:00", "remaining_time": "1 day, 0:18:54", "throughput": 8417.23, "total_tokens": 38893096} {"current_steps": 38300, "total_steps": 761865, "loss": 1.9588, "lr": 9.93780386453566e-07, "epoch": 0.7540706030595972, "percentage": 5.03, "elapsed_time": "1:17:12", "remaining_time": "1 day, 0:18:45", "throughput": 8417.01, "total_tokens": 38995496} {"current_steps": 38400, "total_steps": 761865, "loss": 1.9728, "lr": 9.937479251110642e-07, "epoch": 0.7560394558091, "percentage": 5.04, "elapsed_time": "1:17:25", "remaining_time": "1 day, 0:18:36", "throughput": 8416.85, "total_tokens": 39097896} {"current_steps": 38500, "total_steps": 761865, "loss": 1.9651, "lr": 9.937153798108927e-07, "epoch": 0.7580083085586029, "percentage": 5.05, "elapsed_time": "1:17:37", "remaining_time": "1 day, 0:18:27", "throughput": 8416.67, "total_tokens": 39200296} {"current_steps": 38600, "total_steps": 761865, "loss": 2.0322, "lr": 9.936827505585848e-07, "epoch": 0.7599771613081058, "percentage": 5.07, "elapsed_time": "1:17:49", "remaining_time": "1 day, 0:18:18", "throughput": 8416.51, "total_tokens": 39302696} {"current_steps": 38700, "total_steps": 761865, "loss": 1.9569, "lr": 9.93650037359689e-07, "epoch": 0.7619460140576086, "percentage": 5.08, "elapsed_time": "1:18:01", "remaining_time": "1 day, 0:18:09", "throughput": 8416.31, "total_tokens": 39405096} {"current_steps": 38800, "total_steps": 761865, "loss": 1.9536, "lr": 9.936172402197682e-07, "epoch": 0.7639148668071115, "percentage": 5.09, "elapsed_time": "1:18:14", "remaining_time": "1 day, 0:18:00", "throughput": 8416.14, "total_tokens": 39507496} {"current_steps": 38900, "total_steps": 761865, "loss": 1.9576, "lr": 9.935843591443988e-07, "epoch": 0.7658837195566144, "percentage": 5.11, "elapsed_time": "1:18:26", "remaining_time": "1 day, 0:17:50", "throughput": 8415.89, "total_tokens": 39608984} {"current_steps": 39000, "total_steps": 761865, "loss": 1.983, "lr": 9.935513941391724e-07, "epoch": 0.7678525723061173, "percentage": 5.12, "elapsed_time": "1:18:38", "remaining_time": "1 day, 0:17:41", "throughput": 8415.73, "total_tokens": 39711384} {"current_steps": 39100, "total_steps": 761865, "loss": 1.9447, "lr": 9.935183452096943e-07, "epoch": 0.7698214250556201, "percentage": 5.13, "elapsed_time": "1:18:50", "remaining_time": "1 day, 0:17:31", "throughput": 8415.53, "total_tokens": 39813312} {"current_steps": 39200, "total_steps": 761865, "loss": 1.9493, "lr": 9.934852123615838e-07, "epoch": 0.771790277805123, "percentage": 5.15, "elapsed_time": "1:19:03", "remaining_time": "1 day, 0:17:22", "throughput": 8415.33, "total_tokens": 39915712} {"current_steps": 39300, "total_steps": 761865, "loss": 2.0189, "lr": 9.934519956004753e-07, "epoch": 0.7737591305546259, "percentage": 5.16, "elapsed_time": "1:19:15", "remaining_time": "1 day, 0:17:13", "throughput": 8414.97, "total_tokens": 40017192} {"current_steps": 39400, "total_steps": 761865, "loss": 1.9848, "lr": 9.934186949320172e-07, "epoch": 0.7757279833041287, "percentage": 5.17, "elapsed_time": "1:19:27", "remaining_time": "1 day, 0:17:03", "throughput": 8414.7, "total_tokens": 40118776} {"current_steps": 39500, "total_steps": 761865, "loss": 2.0028, "lr": 9.933853103618715e-07, "epoch": 0.7776968360536316, "percentage": 5.18, "elapsed_time": "1:19:39", "remaining_time": "1 day, 0:16:53", "throughput": 8414.43, "total_tokens": 40220000} {"current_steps": 39600, "total_steps": 761865, "loss": 1.9879, "lr": 9.93351841895715e-07, "epoch": 0.7796656888031344, "percentage": 5.2, "elapsed_time": "1:19:52", "remaining_time": "1 day, 0:16:44", "throughput": 8414.25, "total_tokens": 40322400} {"current_steps": 39700, "total_steps": 761865, "loss": 1.9514, "lr": 9.933182895392392e-07, "epoch": 0.7816345415526372, "percentage": 5.21, "elapsed_time": "1:20:04", "remaining_time": "1 day, 0:16:34", "throughput": 8413.97, "total_tokens": 40424096} {"current_steps": 39800, "total_steps": 761865, "loss": 2.0307, "lr": 9.93284653298149e-07, "epoch": 0.7836033943021401, "percentage": 5.22, "elapsed_time": "1:20:16", "remaining_time": "1 day, 0:16:25", "throughput": 8413.77, "total_tokens": 40526264} {"current_steps": 39900, "total_steps": 761865, "loss": 1.9797, "lr": 9.932509331781641e-07, "epoch": 0.785572247051643, "percentage": 5.24, "elapsed_time": "1:20:28", "remaining_time": "1 day, 0:16:16", "throughput": 8413.58, "total_tokens": 40628664} {"current_steps": 40000, "total_steps": 761865, "loss": 2.0123, "lr": 9.93217129185018e-07, "epoch": 0.7875410998011458, "percentage": 5.25, "elapsed_time": "1:20:41", "remaining_time": "1 day, 0:16:07", "throughput": 8413.43, "total_tokens": 40731064} {"current_steps": 40100, "total_steps": 761865, "loss": 1.9777, "lr": 9.931832413244595e-07, "epoch": 0.7895099525506487, "percentage": 5.26, "elapsed_time": "1:20:53", "remaining_time": "1 day, 0:16:04", "throughput": 8412.21, "total_tokens": 40831424} {"current_steps": 40200, "total_steps": 761865, "loss": 1.9964, "lr": 9.931492696022503e-07, "epoch": 0.7914788053001516, "percentage": 5.28, "elapsed_time": "1:21:06", "remaining_time": "1 day, 0:15:55", "throughput": 8412.07, "total_tokens": 40933824} {"current_steps": 40300, "total_steps": 761865, "loss": 1.9658, "lr": 9.931152140241673e-07, "epoch": 0.7934476580496544, "percentage": 5.29, "elapsed_time": "1:21:18", "remaining_time": "1 day, 0:15:45", "throughput": 8411.85, "total_tokens": 41035632} {"current_steps": 40400, "total_steps": 761865, "loss": 1.9834, "lr": 9.930810745960012e-07, "epoch": 0.7954165107991573, "percentage": 5.3, "elapsed_time": "1:21:30", "remaining_time": "1 day, 0:15:36", "throughput": 8411.7, "total_tokens": 41138032} {"current_steps": 40500, "total_steps": 761865, "loss": 2.0175, "lr": 9.930468513235573e-07, "epoch": 0.7973853635486602, "percentage": 5.32, "elapsed_time": "1:21:42", "remaining_time": "1 day, 0:15:26", "throughput": 8411.46, "total_tokens": 41239848} {"current_steps": 40600, "total_steps": 761865, "loss": 1.9772, "lr": 9.930125442126546e-07, "epoch": 0.7993542162981631, "percentage": 5.33, "elapsed_time": "1:21:55", "remaining_time": "1 day, 0:15:16", "throughput": 8411.29, "total_tokens": 41341712} {"current_steps": 40700, "total_steps": 761865, "loss": 1.9549, "lr": 9.929781532691275e-07, "epoch": 0.8013230690476659, "percentage": 5.34, "elapsed_time": "1:22:07", "remaining_time": "1 day, 0:15:04", "throughput": 8411.09, "total_tokens": 41442864} {"current_steps": 40800, "total_steps": 761865, "loss": 2.0071, "lr": 9.929436784988229e-07, "epoch": 0.8032919217971688, "percentage": 5.36, "elapsed_time": "1:22:19", "remaining_time": "1 day, 0:14:54", "throughput": 8410.87, "total_tokens": 41544624} {"current_steps": 40900, "total_steps": 761865, "loss": 2.0175, "lr": 9.929091199076038e-07, "epoch": 0.8052607745466717, "percentage": 5.37, "elapsed_time": "1:22:31", "remaining_time": "1 day, 0:14:43", "throughput": 8410.56, "total_tokens": 41645312} {"current_steps": 41000, "total_steps": 761865, "loss": 1.9737, "lr": 9.928744775013462e-07, "epoch": 0.8072296272961745, "percentage": 5.38, "elapsed_time": "1:22:43", "remaining_time": "1 day, 0:14:31", "throughput": 8410.28, "total_tokens": 41745664} {"current_steps": 41100, "total_steps": 761865, "loss": 1.9739, "lr": 9.928397512859405e-07, "epoch": 0.8091984800456774, "percentage": 5.39, "elapsed_time": "1:22:55", "remaining_time": "1 day, 0:14:20", "throughput": 8410.08, "total_tokens": 41847232} {"current_steps": 41200, "total_steps": 761865, "loss": 1.969, "lr": 9.928049412672923e-07, "epoch": 0.8111673327951803, "percentage": 5.41, "elapsed_time": "1:23:08", "remaining_time": "1 day, 0:14:11", "throughput": 8409.93, "total_tokens": 41949632} {"current_steps": 41300, "total_steps": 761865, "loss": 1.9624, "lr": 9.9277004745132e-07, "epoch": 0.8131361855446831, "percentage": 5.42, "elapsed_time": "1:23:20", "remaining_time": "1 day, 0:14:01", "throughput": 8409.79, "total_tokens": 42052032} {"current_steps": 41400, "total_steps": 761865, "loss": 1.9597, "lr": 9.927350698439577e-07, "epoch": 0.815105038294186, "percentage": 5.43, "elapsed_time": "1:23:32", "remaining_time": "1 day, 0:13:52", "throughput": 8409.64, "total_tokens": 42154432} {"current_steps": 41500, "total_steps": 761865, "loss": 2.0168, "lr": 9.927000084511525e-07, "epoch": 0.8170738910436889, "percentage": 5.45, "elapsed_time": "1:23:44", "remaining_time": "1 day, 0:13:41", "throughput": 8409.44, "total_tokens": 42255664} {"current_steps": 41600, "total_steps": 761865, "loss": 1.9418, "lr": 9.926648632788663e-07, "epoch": 0.8190427437931918, "percentage": 5.46, "elapsed_time": "1:23:56", "remaining_time": "1 day, 0:13:30", "throughput": 8409.23, "total_tokens": 42357248} {"current_steps": 41700, "total_steps": 761865, "loss": 1.9218, "lr": 9.926296343330758e-07, "epoch": 0.8210115965426946, "percentage": 5.47, "elapsed_time": "1:24:09", "remaining_time": "1 day, 0:13:21", "throughput": 8409.08, "total_tokens": 42459648} {"current_steps": 41800, "total_steps": 761865, "loss": 2.0096, "lr": 9.925943216197707e-07, "epoch": 0.8229804492921975, "percentage": 5.49, "elapsed_time": "1:24:21", "remaining_time": "1 day, 0:13:10", "throughput": 8408.9, "total_tokens": 42561272} {"current_steps": 41900, "total_steps": 761865, "loss": 2.0198, "lr": 9.925589251449561e-07, "epoch": 0.8249493020417002, "percentage": 5.5, "elapsed_time": "1:24:33", "remaining_time": "1 day, 0:13:01", "throughput": 8408.76, "total_tokens": 42663672} {"current_steps": 42000, "total_steps": 761865, "loss": 1.9451, "lr": 9.925234449146507e-07, "epoch": 0.8269181547912031, "percentage": 5.51, "elapsed_time": "1:24:45", "remaining_time": "1 day, 0:12:50", "throughput": 8408.55, "total_tokens": 42764968} {"current_steps": 42100, "total_steps": 761865, "loss": 2.0011, "lr": 9.924878809348875e-07, "epoch": 0.828887007540706, "percentage": 5.53, "elapsed_time": "1:24:58", "remaining_time": "1 day, 0:12:39", "throughput": 8408.35, "total_tokens": 42866600} {"current_steps": 42200, "total_steps": 761865, "loss": 1.9953, "lr": 9.924522332117143e-07, "epoch": 0.8308558602902089, "percentage": 5.54, "elapsed_time": "1:25:10", "remaining_time": "1 day, 0:12:29", "throughput": 8408.15, "total_tokens": 42968352} {"current_steps": 42300, "total_steps": 761865, "loss": 1.964, "lr": 9.92416501751192e-07, "epoch": 0.8328247130397117, "percentage": 5.55, "elapsed_time": "1:25:22", "remaining_time": "1 day, 0:12:20", "throughput": 8408.01, "total_tokens": 43070752} {"current_steps": 42400, "total_steps": 761865, "loss": 1.9883, "lr": 9.92380686559397e-07, "epoch": 0.8347935657892146, "percentage": 5.57, "elapsed_time": "1:25:34", "remaining_time": "1 day, 0:12:10", "throughput": 8407.92, "total_tokens": 43173152} {"current_steps": 42500, "total_steps": 761865, "loss": 1.928, "lr": 9.923447876424192e-07, "epoch": 0.8367624185387175, "percentage": 5.58, "elapsed_time": "1:25:46", "remaining_time": "1 day, 0:11:58", "throughput": 8407.73, "total_tokens": 43274384} {"current_steps": 42600, "total_steps": 761865, "loss": 1.9831, "lr": 9.923088050063628e-07, "epoch": 0.8387312712882203, "percentage": 5.59, "elapsed_time": "1:25:59", "remaining_time": "1 day, 0:11:49", "throughput": 8407.56, "total_tokens": 43376784} {"current_steps": 42700, "total_steps": 761865, "loss": 1.9724, "lr": 9.922727386573465e-07, "epoch": 0.8407001240377232, "percentage": 5.6, "elapsed_time": "1:26:11", "remaining_time": "1 day, 0:11:40", "throughput": 8407.42, "total_tokens": 43479184} {"current_steps": 42800, "total_steps": 761865, "loss": 1.9748, "lr": 9.92236588601503e-07, "epoch": 0.8426689767872261, "percentage": 5.62, "elapsed_time": "1:26:23", "remaining_time": "1 day, 0:11:29", "throughput": 8407.19, "total_tokens": 43580352} {"current_steps": 42900, "total_steps": 761865, "loss": 2.0376, "lr": 9.922003548449793e-07, "epoch": 0.844637829536729, "percentage": 5.63, "elapsed_time": "1:26:35", "remaining_time": "1 day, 0:11:17", "throughput": 8406.87, "total_tokens": 43680896} {"current_steps": 43000, "total_steps": 761865, "loss": 1.9521, "lr": 9.921640373939367e-07, "epoch": 0.8466066822862318, "percentage": 5.64, "elapsed_time": "1:26:48", "remaining_time": "1 day, 0:11:08", "throughput": 8406.71, "total_tokens": 43783296} {"current_steps": 43100, "total_steps": 761865, "loss": 1.9842, "lr": 9.921276362545506e-07, "epoch": 0.8485755350357347, "percentage": 5.66, "elapsed_time": "1:27:00", "remaining_time": "1 day, 0:10:57", "throughput": 8406.47, "total_tokens": 43884520} {"current_steps": 43200, "total_steps": 761865, "loss": 1.9927, "lr": 9.920911514330108e-07, "epoch": 0.8505443877852376, "percentage": 5.67, "elapsed_time": "1:27:12", "remaining_time": "1 day, 0:10:48", "throughput": 8406.3, "total_tokens": 43986920} {"current_steps": 43300, "total_steps": 761865, "loss": 1.9525, "lr": 9.920545829355212e-07, "epoch": 0.8525132405347404, "percentage": 5.68, "elapsed_time": "1:27:24", "remaining_time": "1 day, 0:10:39", "throughput": 8406.15, "total_tokens": 44089320} {"current_steps": 43400, "total_steps": 761865, "loss": 2.0064, "lr": 9.920179307682998e-07, "epoch": 0.8544820932842433, "percentage": 5.7, "elapsed_time": "1:27:37", "remaining_time": "1 day, 0:10:28", "throughput": 8406.0, "total_tokens": 44190960} {"current_steps": 43500, "total_steps": 761865, "loss": 2.0172, "lr": 9.919811949375795e-07, "epoch": 0.8564509460337462, "percentage": 5.71, "elapsed_time": "1:27:49", "remaining_time": "1 day, 0:10:18", "throughput": 8405.87, "total_tokens": 44293360} {"current_steps": 43600, "total_steps": 761865, "loss": 2.0037, "lr": 9.919443754496063e-07, "epoch": 0.858419798783249, "percentage": 5.72, "elapsed_time": "1:28:01", "remaining_time": "1 day, 0:10:08", "throughput": 8405.72, "total_tokens": 44395216} {"current_steps": 43700, "total_steps": 761865, "loss": 1.9806, "lr": 9.91907472310641e-07, "epoch": 0.8603886515327519, "percentage": 5.74, "elapsed_time": "1:28:13", "remaining_time": "1 day, 0:09:57", "throughput": 8405.53, "total_tokens": 44496800} {"current_steps": 43800, "total_steps": 761865, "loss": 2.0107, "lr": 9.918704855269595e-07, "epoch": 0.8623575042822548, "percentage": 5.75, "elapsed_time": "1:28:25", "remaining_time": "1 day, 0:09:46", "throughput": 8405.37, "total_tokens": 44598504} {"current_steps": 43900, "total_steps": 761865, "loss": 1.9491, "lr": 9.918334151048504e-07, "epoch": 0.8643263570317576, "percentage": 5.76, "elapsed_time": "1:28:38", "remaining_time": "1 day, 0:09:36", "throughput": 8405.18, "total_tokens": 44700320} {"current_steps": 44000, "total_steps": 761865, "loss": 1.9544, "lr": 9.917962610506173e-07, "epoch": 0.8662952097812605, "percentage": 5.78, "elapsed_time": "1:28:50", "remaining_time": "1 day, 0:09:27", "throughput": 8405.04, "total_tokens": 44802720} {"current_steps": 44100, "total_steps": 761865, "loss": 2.0316, "lr": 9.917590233705779e-07, "epoch": 0.8682640625307633, "percentage": 5.79, "elapsed_time": "1:29:02", "remaining_time": "1 day, 0:09:16", "throughput": 8404.89, "total_tokens": 44904528} {"current_steps": 44200, "total_steps": 761865, "loss": 1.9944, "lr": 9.917217020710645e-07, "epoch": 0.8702329152802661, "percentage": 5.8, "elapsed_time": "1:29:14", "remaining_time": "1 day, 0:09:05", "throughput": 8404.68, "total_tokens": 45005728} {"current_steps": 44300, "total_steps": 761865, "loss": 2.0238, "lr": 9.91684297158423e-07, "epoch": 0.872201768029769, "percentage": 5.81, "elapsed_time": "1:29:27", "remaining_time": "1 day, 0:08:55", "throughput": 8404.56, "total_tokens": 45108128} {"current_steps": 44400, "total_steps": 761865, "loss": 2.0045, "lr": 9.916468086390137e-07, "epoch": 0.8741706207792719, "percentage": 5.83, "elapsed_time": "1:29:39", "remaining_time": "1 day, 0:08:44", "throughput": 8404.35, "total_tokens": 45209224} {"current_steps": 44500, "total_steps": 761865, "loss": 1.9804, "lr": 9.916092365192115e-07, "epoch": 0.8761394735287747, "percentage": 5.84, "elapsed_time": "1:29:51", "remaining_time": "1 day, 0:08:33", "throughput": 8404.21, "total_tokens": 45311072} {"current_steps": 44600, "total_steps": 761865, "loss": 2.0682, "lr": 9.915715808054049e-07, "epoch": 0.8781083262782776, "percentage": 5.85, "elapsed_time": "1:30:03", "remaining_time": "1 day, 0:08:20", "throughput": 8403.91, "total_tokens": 45410968} {"current_steps": 44700, "total_steps": 761865, "loss": 1.9653, "lr": 9.91533841503997e-07, "epoch": 0.8800771790277805, "percentage": 5.87, "elapsed_time": "1:30:15", "remaining_time": "1 day, 0:08:10", "throughput": 8403.8, "total_tokens": 45513368} {"current_steps": 44800, "total_steps": 761865, "loss": 1.9645, "lr": 9.914960186214055e-07, "epoch": 0.8820460317772834, "percentage": 5.88, "elapsed_time": "1:30:28", "remaining_time": "1 day, 0:08:01", "throughput": 8403.68, "total_tokens": 45615768} {"current_steps": 44900, "total_steps": 761865, "loss": 1.9974, "lr": 9.914581121640612e-07, "epoch": 0.8840148845267862, "percentage": 5.89, "elapsed_time": "1:30:40", "remaining_time": "1 day, 0:07:50", "throughput": 8403.53, "total_tokens": 45717544} {"current_steps": 45000, "total_steps": 761865, "loss": 1.9571, "lr": 9.914201221384101e-07, "epoch": 0.8859837372762891, "percentage": 5.91, "elapsed_time": "1:30:52", "remaining_time": "1 day, 0:07:39", "throughput": 8403.34, "total_tokens": 45819128} {"current_steps": 45100, "total_steps": 761865, "loss": 1.9756, "lr": 9.913820485509122e-07, "epoch": 0.887952590025792, "percentage": 5.92, "elapsed_time": "1:31:05", "remaining_time": "1 day, 0:07:37", "throughput": 8402.39, "total_tokens": 45920952} {"current_steps": 45200, "total_steps": 761865, "loss": 1.9643, "lr": 9.913438914080414e-07, "epoch": 0.8899214427752948, "percentage": 5.93, "elapsed_time": "1:31:17", "remaining_time": "1 day, 0:07:27", "throughput": 8402.28, "total_tokens": 46023352} {"current_steps": 45300, "total_steps": 761865, "loss": 2.0042, "lr": 9.91305650716286e-07, "epoch": 0.8918902955247977, "percentage": 5.95, "elapsed_time": "1:31:29", "remaining_time": "1 day, 0:07:17", "throughput": 8402.07, "total_tokens": 46124944} {"current_steps": 45400, "total_steps": 761865, "loss": 2.0368, "lr": 9.912673264821485e-07, "epoch": 0.8938591482743006, "percentage": 5.96, "elapsed_time": "1:31:41", "remaining_time": "1 day, 0:07:07", "throughput": 8401.89, "total_tokens": 46226720} {"current_steps": 45500, "total_steps": 761865, "loss": 1.9908, "lr": 9.91228918712146e-07, "epoch": 0.8958280010238034, "percentage": 5.97, "elapsed_time": "1:31:54", "remaining_time": "1 day, 0:06:57", "throughput": 8401.78, "total_tokens": 46329120} {"current_steps": 45600, "total_steps": 761865, "loss": 2.0278, "lr": 9.911904274128087e-07, "epoch": 0.8977968537733063, "percentage": 5.99, "elapsed_time": "1:32:06", "remaining_time": "1 day, 0:06:45", "throughput": 8401.6, "total_tokens": 46430336} {"current_steps": 45700, "total_steps": 761865, "loss": 1.9771, "lr": 9.911518525906822e-07, "epoch": 0.8997657065228092, "percentage": 6.0, "elapsed_time": "1:32:18", "remaining_time": "1 day, 0:06:35", "throughput": 8401.43, "total_tokens": 46532080} {"current_steps": 45800, "total_steps": 761865, "loss": 1.976, "lr": 9.911131942523257e-07, "epoch": 0.901734559272312, "percentage": 6.01, "elapsed_time": "1:32:30", "remaining_time": "1 day, 0:06:23", "throughput": 8401.15, "total_tokens": 46632704} {"current_steps": 45900, "total_steps": 761865, "loss": 2.0071, "lr": 9.91074452404313e-07, "epoch": 0.9037034120218149, "percentage": 6.02, "elapsed_time": "1:32:42", "remaining_time": "1 day, 0:06:13", "throughput": 8400.98, "total_tokens": 46734312} {"current_steps": 46000, "total_steps": 761865, "loss": 1.9931, "lr": 9.910356270532314e-07, "epoch": 0.9056722647713178, "percentage": 6.04, "elapsed_time": "1:32:55", "remaining_time": "1 day, 0:06:01", "throughput": 8400.76, "total_tokens": 46835240} {"current_steps": 46100, "total_steps": 761865, "loss": 1.9681, "lr": 9.90996718205683e-07, "epoch": 0.9076411175208207, "percentage": 6.05, "elapsed_time": "1:33:07", "remaining_time": "1 day, 0:05:51", "throughput": 8400.62, "total_tokens": 46937640} {"current_steps": 46200, "total_steps": 761865, "loss": 1.9566, "lr": 9.90957725868284e-07, "epoch": 0.9096099702703235, "percentage": 6.06, "elapsed_time": "1:33:19", "remaining_time": "1 day, 0:05:42", "throughput": 8400.5, "total_tokens": 47040040} {"current_steps": 46300, "total_steps": 761865, "loss": 1.9897, "lr": 9.909186500476645e-07, "epoch": 0.9115788230198264, "percentage": 6.08, "elapsed_time": "1:33:31", "remaining_time": "1 day, 0:05:30", "throughput": 8400.28, "total_tokens": 47141048} {"current_steps": 46400, "total_steps": 761865, "loss": 1.9685, "lr": 9.908794907504693e-07, "epoch": 0.9135476757693292, "percentage": 6.09, "elapsed_time": "1:33:44", "remaining_time": "1 day, 0:05:21", "throughput": 8400.16, "total_tokens": 47243448} {"current_steps": 46500, "total_steps": 761865, "loss": 1.9752, "lr": 9.908402479833569e-07, "epoch": 0.915516528518832, "percentage": 6.1, "elapsed_time": "1:33:56", "remaining_time": "1 day, 0:05:11", "throughput": 8400.05, "total_tokens": 47345848} {"current_steps": 46600, "total_steps": 761865, "loss": 1.9997, "lr": 9.908009217530004e-07, "epoch": 0.9174853812683349, "percentage": 6.12, "elapsed_time": "1:34:08", "remaining_time": "1 day, 0:05:00", "throughput": 8399.91, "total_tokens": 47447496} {"current_steps": 46700, "total_steps": 761865, "loss": 1.9873, "lr": 9.907615120660866e-07, "epoch": 0.9194542340178378, "percentage": 6.13, "elapsed_time": "1:34:20", "remaining_time": "1 day, 0:04:49", "throughput": 8399.76, "total_tokens": 47549320} {"current_steps": 46800, "total_steps": 761865, "loss": 2.0095, "lr": 9.90722018929317e-07, "epoch": 0.9214230867673406, "percentage": 6.14, "elapsed_time": "1:34:32", "remaining_time": "1 day, 0:04:37", "throughput": 8399.53, "total_tokens": 47649912} {"current_steps": 46900, "total_steps": 761865, "loss": 1.9489, "lr": 9.90682442349407e-07, "epoch": 0.9233919395168435, "percentage": 6.16, "elapsed_time": "1:34:45", "remaining_time": "1 day, 0:04:27", "throughput": 8399.42, "total_tokens": 47752312} {"current_steps": 47000, "total_steps": 761865, "loss": 2.0041, "lr": 9.906427823330862e-07, "epoch": 0.9253607922663464, "percentage": 6.17, "elapsed_time": "1:34:57", "remaining_time": "1 day, 0:04:17", "throughput": 8399.3, "total_tokens": 47854272} {"current_steps": 47100, "total_steps": 761865, "loss": 1.9714, "lr": 9.906030388870988e-07, "epoch": 0.9273296450158492, "percentage": 6.18, "elapsed_time": "1:35:09", "remaining_time": "1 day, 0:04:06", "throughput": 8399.11, "total_tokens": 47955944} {"current_steps": 47200, "total_steps": 761865, "loss": 1.9818, "lr": 9.905632120182024e-07, "epoch": 0.9292984977653521, "percentage": 6.2, "elapsed_time": "1:35:21", "remaining_time": "1 day, 0:03:55", "throughput": 8398.99, "total_tokens": 48057888} {"current_steps": 47300, "total_steps": 761865, "loss": 1.9912, "lr": 9.905233017331695e-07, "epoch": 0.931267350514855, "percentage": 6.21, "elapsed_time": "1:35:34", "remaining_time": "1 day, 0:03:44", "throughput": 8398.77, "total_tokens": 48158632} {"current_steps": 47400, "total_steps": 761865, "loss": 2.0233, "lr": 9.904833080387862e-07, "epoch": 0.9332362032643579, "percentage": 6.22, "elapsed_time": "1:35:46", "remaining_time": "1 day, 0:03:34", "throughput": 8398.68, "total_tokens": 48261032} {"current_steps": 47500, "total_steps": 761865, "loss": 1.99, "lr": 9.904432309418534e-07, "epoch": 0.9352050560138607, "percentage": 6.23, "elapsed_time": "1:35:58", "remaining_time": "1 day, 0:03:24", "throughput": 8398.56, "total_tokens": 48363432} {"current_steps": 47600, "total_steps": 761865, "loss": 1.9754, "lr": 9.90403070449186e-07, "epoch": 0.9371739087633636, "percentage": 6.25, "elapsed_time": "1:36:10", "remaining_time": "1 day, 0:03:14", "throughput": 8398.46, "total_tokens": 48465832} {"current_steps": 47700, "total_steps": 761865, "loss": 1.9668, "lr": 9.903628265676124e-07, "epoch": 0.9391427615128665, "percentage": 6.26, "elapsed_time": "1:36:22", "remaining_time": "1 day, 0:03:02", "throughput": 8398.26, "total_tokens": 48566944} {"current_steps": 47800, "total_steps": 761865, "loss": 1.9741, "lr": 9.90322499303976e-07, "epoch": 0.9411116142623693, "percentage": 6.27, "elapsed_time": "1:36:35", "remaining_time": "1 day, 0:02:52", "throughput": 8398.1, "total_tokens": 48668720} {"current_steps": 47900, "total_steps": 761865, "loss": 1.9926, "lr": 9.902820886651344e-07, "epoch": 0.9430804670118722, "percentage": 6.29, "elapsed_time": "1:36:47", "remaining_time": "1 day, 0:02:41", "throughput": 8397.93, "total_tokens": 48770432} {"current_steps": 48000, "total_steps": 761865, "loss": 1.9601, "lr": 9.902415946579589e-07, "epoch": 0.9450493197613751, "percentage": 6.3, "elapsed_time": "1:36:59", "remaining_time": "1 day, 0:02:32", "throughput": 8397.78, "total_tokens": 48872832} {"current_steps": 48100, "total_steps": 761865, "loss": 1.9797, "lr": 9.902010172893349e-07, "epoch": 0.9470181725108779, "percentage": 6.31, "elapsed_time": "1:37:12", "remaining_time": "1 day, 0:02:22", "throughput": 8397.66, "total_tokens": 48975232} {"current_steps": 48200, "total_steps": 761865, "loss": 2.003, "lr": 9.901603565661626e-07, "epoch": 0.9489870252603808, "percentage": 6.33, "elapsed_time": "1:37:24", "remaining_time": "1 day, 0:02:12", "throughput": 8397.52, "total_tokens": 49077320} {"current_steps": 48300, "total_steps": 761865, "loss": 1.9997, "lr": 9.901196124953557e-07, "epoch": 0.9509558780098837, "percentage": 6.34, "elapsed_time": "1:37:36", "remaining_time": "1 day, 0:02:01", "throughput": 8397.35, "total_tokens": 49178888} {"current_steps": 48400, "total_steps": 761865, "loss": 1.9996, "lr": 9.900787850838428e-07, "epoch": 0.9529247307593866, "percentage": 6.35, "elapsed_time": "1:37:48", "remaining_time": "1 day, 0:01:51", "throughput": 8397.24, "total_tokens": 49281288} {"current_steps": 48500, "total_steps": 761865, "loss": 2.0065, "lr": 9.900378743385659e-07, "epoch": 0.9548935835088894, "percentage": 6.37, "elapsed_time": "1:38:00", "remaining_time": "1 day, 0:01:40", "throughput": 8397.14, "total_tokens": 49383168} {"current_steps": 48600, "total_steps": 761865, "loss": 1.9805, "lr": 9.899968802664816e-07, "epoch": 0.9568624362583922, "percentage": 6.38, "elapsed_time": "1:38:13", "remaining_time": "1 day, 0:01:28", "throughput": 8396.93, "total_tokens": 49484008} {"current_steps": 48700, "total_steps": 761865, "loss": 1.9843, "lr": 9.899558028745607e-07, "epoch": 0.958831289007895, "percentage": 6.39, "elapsed_time": "1:38:25", "remaining_time": "1 day, 0:01:18", "throughput": 8396.72, "total_tokens": 49585552} {"current_steps": 48800, "total_steps": 761865, "loss": 2.0373, "lr": 9.89914642169788e-07, "epoch": 0.9608001417573979, "percentage": 6.41, "elapsed_time": "1:38:37", "remaining_time": "1 day, 0:01:08", "throughput": 8396.62, "total_tokens": 49687952} {"current_steps": 48900, "total_steps": 761865, "loss": 1.9435, "lr": 9.898733981591625e-07, "epoch": 0.9627689945069008, "percentage": 6.42, "elapsed_time": "1:38:49", "remaining_time": "1 day, 0:00:58", "throughput": 8396.52, "total_tokens": 49790352} {"current_steps": 49000, "total_steps": 761865, "loss": 1.9343, "lr": 9.898320708496974e-07, "epoch": 0.9647378472564037, "percentage": 6.43, "elapsed_time": "1:39:02", "remaining_time": "1 day, 0:00:47", "throughput": 8396.36, "total_tokens": 49891936} {"current_steps": 49100, "total_steps": 761865, "loss": 2.025, "lr": 9.8979066024842e-07, "epoch": 0.9667067000059065, "percentage": 6.44, "elapsed_time": "1:39:14", "remaining_time": "1 day, 0:00:36", "throughput": 8396.27, "total_tokens": 49994336} {"current_steps": 49200, "total_steps": 761865, "loss": 1.9972, "lr": 9.89749166362372e-07, "epoch": 0.9686755527554094, "percentage": 6.46, "elapsed_time": "1:39:26", "remaining_time": "1 day, 0:00:25", "throughput": 8396.18, "total_tokens": 50096256} {"current_steps": 49300, "total_steps": 761865, "loss": 1.9958, "lr": 9.89707589198609e-07, "epoch": 0.9706444055049123, "percentage": 6.47, "elapsed_time": "1:39:38", "remaining_time": "1 day, 0:00:15", "throughput": 8396.09, "total_tokens": 50198656} {"current_steps": 49400, "total_steps": 761865, "loss": 1.9598, "lr": 9.896659287642008e-07, "epoch": 0.9726132582544151, "percentage": 6.48, "elapsed_time": "1:39:51", "remaining_time": "1 day, 0:00:05", "throughput": 8396.0, "total_tokens": 50301056} {"current_steps": 49500, "total_steps": 761865, "loss": 1.9685, "lr": 9.896241850662316e-07, "epoch": 0.974582111003918, "percentage": 6.5, "elapsed_time": "1:40:03", "remaining_time": "23:59:54", "throughput": 8395.88, "total_tokens": 50402888} {"current_steps": 49600, "total_steps": 761865, "loss": 1.9915, "lr": 9.895823581117992e-07, "epoch": 0.9765509637534209, "percentage": 6.51, "elapsed_time": "1:40:15", "remaining_time": "23:59:44", "throughput": 8395.77, "total_tokens": 50505288} {"current_steps": 49700, "total_steps": 761865, "loss": 2.0079, "lr": 9.895404479080162e-07, "epoch": 0.9785198165029237, "percentage": 6.52, "elapsed_time": "1:40:27", "remaining_time": "23:59:34", "throughput": 8395.67, "total_tokens": 50607688} {"current_steps": 49800, "total_steps": 761865, "loss": 2.0239, "lr": 9.894984544620092e-07, "epoch": 0.9804886692524266, "percentage": 6.54, "elapsed_time": "1:40:40", "remaining_time": "23:59:23", "throughput": 8395.51, "total_tokens": 50709168} {"current_steps": 49900, "total_steps": 761865, "loss": 2.003, "lr": 9.894563777809185e-07, "epoch": 0.9824575220019295, "percentage": 6.55, "elapsed_time": "1:40:52", "remaining_time": "23:59:11", "throughput": 8395.3, "total_tokens": 50809968} {"current_steps": 50000, "total_steps": 761865, "loss": 1.9824, "lr": 9.894142178718989e-07, "epoch": 0.9844263747514324, "percentage": 6.56, "elapsed_time": "1:41:04", "remaining_time": "23:59:00", "throughput": 8395.15, "total_tokens": 50911664} {"current_steps": 50100, "total_steps": 761865, "loss": 1.9648, "lr": 9.893719747421196e-07, "epoch": 0.9863952275009352, "percentage": 6.58, "elapsed_time": "1:41:17", "remaining_time": "23:58:58", "throughput": 8394.18, "total_tokens": 51013200} {"current_steps": 50200, "total_steps": 761865, "loss": 1.9823, "lr": 9.893296483987636e-07, "epoch": 0.9883640802504381, "percentage": 6.59, "elapsed_time": "1:41:29", "remaining_time": "23:58:48", "throughput": 8393.94, "total_tokens": 51115104} {"current_steps": 50300, "total_steps": 761865, "loss": 1.9897, "lr": 9.89287238849028e-07, "epoch": 0.990332932999941, "percentage": 6.6, "elapsed_time": "1:41:41", "remaining_time": "23:58:40", "throughput": 8393.7, "total_tokens": 51217504} {"current_steps": 50400, "total_steps": 761865, "loss": 2.0414, "lr": 9.892447461001243e-07, "epoch": 0.9923017857494438, "percentage": 6.62, "elapsed_time": "1:41:54", "remaining_time": "23:58:30", "throughput": 8393.32, "total_tokens": 51318288} {"current_steps": 50500, "total_steps": 761865, "loss": 1.9811, "lr": 9.892021701592778e-07, "epoch": 0.9942706384989467, "percentage": 6.63, "elapsed_time": "1:42:06", "remaining_time": "23:58:21", "throughput": 8393.02, "total_tokens": 51420136} {"current_steps": 50600, "total_steps": 761865, "loss": 1.9351, "lr": 9.891595110337288e-07, "epoch": 0.9962394912484496, "percentage": 6.64, "elapsed_time": "1:42:18", "remaining_time": "23:58:12", "throughput": 8392.78, "total_tokens": 51522536} {"current_steps": 50700, "total_steps": 761865, "loss": 2.0245, "lr": 9.891167687307303e-07, "epoch": 0.9982083439979524, "percentage": 6.65, "elapsed_time": "1:42:31", "remaining_time": "23:58:02", "throughput": 8392.37, "total_tokens": 51622928} {"current_steps": 50800, "total_steps": 761865, "loss": 1.9652, "lr": 9.89073943257551e-07, "epoch": 1.0001771967474553, "percentage": 6.67, "elapsed_time": "1:42:43", "remaining_time": "23:57:53", "throughput": 8392.1, "total_tokens": 51725328} {"current_steps": 50900, "total_steps": 761865, "loss": 1.9659, "lr": 9.890310346214726e-07, "epoch": 1.002146049496958, "percentage": 6.68, "elapsed_time": "1:42:55", "remaining_time": "23:57:44", "throughput": 8391.86, "total_tokens": 51827728} {"current_steps": 51000, "total_steps": 761865, "loss": 1.9379, "lr": 9.889880428297912e-07, "epoch": 1.004114902246461, "percentage": 6.69, "elapsed_time": "1:43:08", "remaining_time": "23:57:36", "throughput": 8391.63, "total_tokens": 51930128} {"current_steps": 51100, "total_steps": 761865, "loss": 1.9795, "lr": 9.889449678898176e-07, "epoch": 1.0060837549959638, "percentage": 6.71, "elapsed_time": "1:43:20", "remaining_time": "23:57:27", "throughput": 8391.4, "total_tokens": 52032528} {"current_steps": 51200, "total_steps": 761865, "loss": 1.9782, "lr": 9.889018098088763e-07, "epoch": 1.0080526077454668, "percentage": 6.72, "elapsed_time": "1:43:32", "remaining_time": "23:57:16", "throughput": 8391.06, "total_tokens": 52133120} {"current_steps": 51300, "total_steps": 761865, "loss": 1.9832, "lr": 9.888585685943057e-07, "epoch": 1.0100214604949695, "percentage": 6.73, "elapsed_time": "1:43:45", "remaining_time": "23:57:07", "throughput": 8390.78, "total_tokens": 52235000} {"current_steps": 51400, "total_steps": 761865, "loss": 1.9645, "lr": 9.888152442534587e-07, "epoch": 1.0119903132444725, "percentage": 6.75, "elapsed_time": "1:43:57", "remaining_time": "23:56:58", "throughput": 8390.53, "total_tokens": 52337400} {"current_steps": 51500, "total_steps": 761865, "loss": 2.0113, "lr": 9.887718367937023e-07, "epoch": 1.0139591659939753, "percentage": 6.76, "elapsed_time": "1:44:10", "remaining_time": "23:56:49", "throughput": 8390.23, "total_tokens": 52438976} {"current_steps": 51600, "total_steps": 761865, "loss": 1.9937, "lr": 9.887283462224176e-07, "epoch": 1.0159280187434783, "percentage": 6.77, "elapsed_time": "1:44:22", "remaining_time": "23:56:40", "throughput": 8390.03, "total_tokens": 52541376} {"current_steps": 51700, "total_steps": 761865, "loss": 1.9855, "lr": 9.886847725469999e-07, "epoch": 1.017896871492981, "percentage": 6.79, "elapsed_time": "1:44:34", "remaining_time": "23:56:31", "throughput": 8389.82, "total_tokens": 52643776} {"current_steps": 51800, "total_steps": 761865, "loss": 1.974, "lr": 9.88641115774858e-07, "epoch": 1.019865724242484, "percentage": 6.8, "elapsed_time": "1:44:47", "remaining_time": "23:56:21", "throughput": 8389.65, "total_tokens": 52746176} {"current_steps": 51900, "total_steps": 761865, "loss": 1.9614, "lr": 9.88597375913416e-07, "epoch": 1.0218345769919868, "percentage": 6.81, "elapsed_time": "1:44:59", "remaining_time": "23:56:10", "throughput": 8389.54, "total_tokens": 52847936} {"current_steps": 52000, "total_steps": 761865, "loss": 1.996, "lr": 9.885535529701113e-07, "epoch": 1.0238034297414895, "percentage": 6.83, "elapsed_time": "1:45:11", "remaining_time": "23:56:00", "throughput": 8389.43, "total_tokens": 52950248} {"current_steps": 52100, "total_steps": 761865, "loss": 1.9267, "lr": 9.885096469523954e-07, "epoch": 1.0257722824909925, "percentage": 6.84, "elapsed_time": "1:45:23", "remaining_time": "23:55:49", "throughput": 8389.37, "total_tokens": 53052648} {"current_steps": 52200, "total_steps": 761865, "loss": 1.958, "lr": 9.884656578677344e-07, "epoch": 1.0277411352404953, "percentage": 6.85, "elapsed_time": "1:45:36", "remaining_time": "23:55:39", "throughput": 8389.3, "total_tokens": 53155048} {"current_steps": 52300, "total_steps": 761865, "loss": 1.9878, "lr": 9.884215857236082e-07, "epoch": 1.0297099879899982, "percentage": 6.86, "elapsed_time": "1:45:48", "remaining_time": "23:55:28", "throughput": 8389.18, "total_tokens": 53256672} {"current_steps": 52400, "total_steps": 761865, "loss": 2.0078, "lr": 9.883774305275107e-07, "epoch": 1.031678840739501, "percentage": 6.88, "elapsed_time": "1:46:00", "remaining_time": "23:55:17", "throughput": 8389.03, "total_tokens": 53358264} {"current_steps": 52500, "total_steps": 761865, "loss": 1.9489, "lr": 9.883331922869505e-07, "epoch": 1.033647693489004, "percentage": 6.89, "elapsed_time": "1:46:12", "remaining_time": "23:55:06", "throughput": 8388.97, "total_tokens": 53460664} {"current_steps": 52600, "total_steps": 761865, "loss": 2.0028, "lr": 9.882888710094498e-07, "epoch": 1.0356165462385067, "percentage": 6.9, "elapsed_time": "1:46:24", "remaining_time": "23:54:55", "throughput": 8388.83, "total_tokens": 53562144} {"current_steps": 52700, "total_steps": 761865, "loss": 2.0363, "lr": 9.882444667025449e-07, "epoch": 1.0375853989880097, "percentage": 6.92, "elapsed_time": "1:46:37", "remaining_time": "23:54:44", "throughput": 8388.74, "total_tokens": 53664544} {"current_steps": 52800, "total_steps": 761865, "loss": 1.9919, "lr": 9.881999793737865e-07, "epoch": 1.0395542517375125, "percentage": 6.93, "elapsed_time": "1:46:49", "remaining_time": "23:54:33", "throughput": 8388.64, "total_tokens": 53766376} {"current_steps": 52900, "total_steps": 761865, "loss": 1.9611, "lr": 9.881554090307393e-07, "epoch": 1.0415231044870155, "percentage": 6.94, "elapsed_time": "1:47:01", "remaining_time": "23:54:23", "throughput": 8388.52, "total_tokens": 53868776} {"current_steps": 53000, "total_steps": 761865, "loss": 1.9805, "lr": 9.88110755680982e-07, "epoch": 1.0434919572365182, "percentage": 6.96, "elapsed_time": "1:47:14", "remaining_time": "23:54:13", "throughput": 8388.43, "total_tokens": 53971176} {"current_steps": 53100, "total_steps": 761865, "loss": 1.9512, "lr": 9.880660193321078e-07, "epoch": 1.0454608099860212, "percentage": 6.97, "elapsed_time": "1:47:26", "remaining_time": "23:54:03", "throughput": 8388.33, "total_tokens": 54073424} {"current_steps": 53200, "total_steps": 761865, "loss": 1.9927, "lr": 9.880211999917234e-07, "epoch": 1.047429662735524, "percentage": 6.98, "elapsed_time": "1:47:38", "remaining_time": "23:53:51", "throughput": 8388.23, "total_tokens": 54175104} {"current_steps": 53300, "total_steps": 761865, "loss": 1.9625, "lr": 9.8797629766745e-07, "epoch": 1.049398515485027, "percentage": 7.0, "elapsed_time": "1:47:50", "remaining_time": "23:53:40", "throughput": 8388.13, "total_tokens": 54276800} {"current_steps": 53400, "total_steps": 761865, "loss": 1.9786, "lr": 9.87931312366923e-07, "epoch": 1.0513673682345297, "percentage": 7.01, "elapsed_time": "1:48:02", "remaining_time": "23:53:29", "throughput": 8388.0, "total_tokens": 54378432} {"current_steps": 53500, "total_steps": 761865, "loss": 1.9977, "lr": 9.87886244097792e-07, "epoch": 1.0533362209840327, "percentage": 7.02, "elapsed_time": "1:48:15", "remaining_time": "23:53:18", "throughput": 8387.83, "total_tokens": 54480152} {"current_steps": 53600, "total_steps": 761865, "loss": 1.9702, "lr": 9.8784109286772e-07, "epoch": 1.0553050737335354, "percentage": 7.04, "elapsed_time": "1:48:27", "remaining_time": "23:53:07", "throughput": 8387.74, "total_tokens": 54582256} {"current_steps": 53700, "total_steps": 761865, "loss": 1.9578, "lr": 9.87795858684385e-07, "epoch": 1.0572739264830384, "percentage": 7.05, "elapsed_time": "1:48:39", "remaining_time": "23:52:56", "throughput": 8387.61, "total_tokens": 54683912} {"current_steps": 53800, "total_steps": 761865, "loss": 1.9477, "lr": 9.87750541555478e-07, "epoch": 1.0592427792325412, "percentage": 7.06, "elapsed_time": "1:48:51", "remaining_time": "23:52:46", "throughput": 8387.55, "total_tokens": 54786312} {"current_steps": 53900, "total_steps": 761865, "loss": 2.022, "lr": 9.877051414887058e-07, "epoch": 1.0612116319820442, "percentage": 7.07, "elapsed_time": "1:49:04", "remaining_time": "23:52:35", "throughput": 8387.47, "total_tokens": 54888712} {"current_steps": 54000, "total_steps": 761865, "loss": 1.9789, "lr": 9.876596584917876e-07, "epoch": 1.063180484731547, "percentage": 7.09, "elapsed_time": "1:49:16", "remaining_time": "23:52:25", "throughput": 8387.38, "total_tokens": 54991112} {"current_steps": 54100, "total_steps": 761865, "loss": 2.003, "lr": 9.876140925724574e-07, "epoch": 1.06514933748105, "percentage": 7.1, "elapsed_time": "1:49:28", "remaining_time": "23:52:14", "throughput": 8387.23, "total_tokens": 55092752} {"current_steps": 54200, "total_steps": 761865, "loss": 1.966, "lr": 9.875684437384637e-07, "epoch": 1.0671181902305527, "percentage": 7.11, "elapsed_time": "1:49:40", "remaining_time": "23:52:03", "throughput": 8387.12, "total_tokens": 55194512} {"current_steps": 54300, "total_steps": 761865, "loss": 2.0077, "lr": 9.875227119975685e-07, "epoch": 1.0690870429800556, "percentage": 7.13, "elapsed_time": "1:49:53", "remaining_time": "23:51:53", "throughput": 8387.03, "total_tokens": 55296912} {"current_steps": 54400, "total_steps": 761865, "loss": 1.9686, "lr": 9.87476897357548e-07, "epoch": 1.0710558957295584, "percentage": 7.14, "elapsed_time": "1:50:05", "remaining_time": "23:51:42", "throughput": 8386.89, "total_tokens": 55398832} {"current_steps": 54500, "total_steps": 761865, "loss": 2.0322, "lr": 9.874309998261927e-07, "epoch": 1.0730247484790612, "percentage": 7.15, "elapsed_time": "1:50:17", "remaining_time": "23:51:31", "throughput": 8386.81, "total_tokens": 55501232} {"current_steps": 54600, "total_steps": 761865, "loss": 2.0826, "lr": 9.873850194113072e-07, "epoch": 1.0749936012285641, "percentage": 7.17, "elapsed_time": "1:50:29", "remaining_time": "23:51:20", "throughput": 8386.68, "total_tokens": 55602496} {"current_steps": 54700, "total_steps": 761865, "loss": 1.9722, "lr": 9.873389561207097e-07, "epoch": 1.076962453978067, "percentage": 7.18, "elapsed_time": "1:50:41", "remaining_time": "23:51:07", "throughput": 8386.52, "total_tokens": 55703048} {"current_steps": 54800, "total_steps": 761865, "loss": 1.9814, "lr": 9.872928099622334e-07, "epoch": 1.0789313067275699, "percentage": 7.19, "elapsed_time": "1:50:54", "remaining_time": "23:50:56", "throughput": 8386.4, "total_tokens": 55804592} {"current_steps": 54900, "total_steps": 761865, "loss": 1.9392, "lr": 9.872465809437245e-07, "epoch": 1.0809001594770726, "percentage": 7.21, "elapsed_time": "1:51:06", "remaining_time": "23:50:45", "throughput": 8386.29, "total_tokens": 55906248} {"current_steps": 55000, "total_steps": 761865, "loss": 2.0209, "lr": 9.872002690730444e-07, "epoch": 1.0828690122265756, "percentage": 7.22, "elapsed_time": "1:51:18", "remaining_time": "23:50:33", "throughput": 8386.16, "total_tokens": 56007496} {"current_steps": 55100, "total_steps": 761865, "loss": 1.986, "lr": 9.871538743580675e-07, "epoch": 1.0848378649760784, "percentage": 7.23, "elapsed_time": "1:51:31", "remaining_time": "23:50:29", "throughput": 8385.46, "total_tokens": 56109896} {"current_steps": 55200, "total_steps": 761865, "loss": 1.9862, "lr": 9.871073968066832e-07, "epoch": 1.0868067177255814, "percentage": 7.25, "elapsed_time": "1:51:43", "remaining_time": "23:50:18", "throughput": 8385.4, "total_tokens": 56212296} {"current_steps": 55300, "total_steps": 761865, "loss": 1.9599, "lr": 9.870608364267946e-07, "epoch": 1.088775570475084, "percentage": 7.26, "elapsed_time": "1:51:55", "remaining_time": "23:50:08", "throughput": 8385.34, "total_tokens": 56314696} {"current_steps": 55400, "total_steps": 761865, "loss": 2.0252, "lr": 9.87014193226319e-07, "epoch": 1.090744423224587, "percentage": 7.27, "elapsed_time": "1:52:08", "remaining_time": "23:49:57", "throughput": 8385.27, "total_tokens": 56417096} {"current_steps": 55500, "total_steps": 761865, "loss": 1.9421, "lr": 9.86967467213187e-07, "epoch": 1.0927132759740898, "percentage": 7.28, "elapsed_time": "1:52:20", "remaining_time": "23:49:46", "throughput": 8385.21, "total_tokens": 56519496} {"current_steps": 55600, "total_steps": 761865, "loss": 1.9723, "lr": 9.869206583953448e-07, "epoch": 1.0946821287235928, "percentage": 7.3, "elapsed_time": "1:52:32", "remaining_time": "23:49:36", "throughput": 8385.13, "total_tokens": 56621896} {"current_steps": 55700, "total_steps": 761865, "loss": 2.0142, "lr": 9.868737667807517e-07, "epoch": 1.0966509814730956, "percentage": 7.31, "elapsed_time": "1:52:44", "remaining_time": "23:49:25", "throughput": 8385.07, "total_tokens": 56724296} {"current_steps": 55800, "total_steps": 761865, "loss": 1.9717, "lr": 9.868267923773807e-07, "epoch": 1.0986198342225986, "percentage": 7.32, "elapsed_time": "1:52:57", "remaining_time": "23:49:14", "throughput": 8384.98, "total_tokens": 56826384} {"current_steps": 55900, "total_steps": 761865, "loss": 1.9431, "lr": 9.8677973519322e-07, "epoch": 1.1005886869721013, "percentage": 7.34, "elapsed_time": "1:53:09", "remaining_time": "23:49:04", "throughput": 8384.92, "total_tokens": 56928784} {"current_steps": 56000, "total_steps": 761865, "loss": 2.0366, "lr": 9.86732595236271e-07, "epoch": 1.1025575397216043, "percentage": 7.35, "elapsed_time": "1:53:21", "remaining_time": "23:48:53", "throughput": 8384.84, "total_tokens": 57031184} {"current_steps": 56100, "total_steps": 761865, "loss": 2.0002, "lr": 9.866853725145491e-07, "epoch": 1.104526392471107, "percentage": 7.36, "elapsed_time": "1:53:33", "remaining_time": "23:48:42", "throughput": 8384.74, "total_tokens": 57133096} {"current_steps": 56200, "total_steps": 761865, "loss": 1.9963, "lr": 9.866380670360848e-07, "epoch": 1.10649524522061, "percentage": 7.38, "elapsed_time": "1:53:46", "remaining_time": "23:48:30", "throughput": 8384.58, "total_tokens": 57233904} {"current_steps": 56300, "total_steps": 761865, "loss": 2.0254, "lr": 9.865906788089218e-07, "epoch": 1.1084640979701128, "percentage": 7.39, "elapsed_time": "1:53:58", "remaining_time": "23:48:19", "throughput": 8384.52, "total_tokens": 57336304} {"current_steps": 56400, "total_steps": 761865, "loss": 1.9778, "lr": 9.865432078411178e-07, "epoch": 1.1104329507196158, "percentage": 7.4, "elapsed_time": "1:54:10", "remaining_time": "23:48:08", "throughput": 8384.42, "total_tokens": 57438096} {"current_steps": 56500, "total_steps": 761865, "loss": 2.0114, "lr": 9.86495654140745e-07, "epoch": 1.1124018034691185, "percentage": 7.42, "elapsed_time": "1:54:22", "remaining_time": "23:47:57", "throughput": 8384.33, "total_tokens": 57539928} {"current_steps": 56600, "total_steps": 761865, "loss": 1.9805, "lr": 9.864480177158896e-07, "epoch": 1.1143706562186213, "percentage": 7.43, "elapsed_time": "1:54:34", "remaining_time": "23:47:45", "throughput": 8384.23, "total_tokens": 57641136} {"current_steps": 56700, "total_steps": 761865, "loss": 1.9595, "lr": 9.864002985746515e-07, "epoch": 1.1163395089681243, "percentage": 7.44, "elapsed_time": "1:54:47", "remaining_time": "23:47:34", "throughput": 8384.14, "total_tokens": 57743536} {"current_steps": 56800, "total_steps": 761865, "loss": 2.0062, "lr": 9.863524967251454e-07, "epoch": 1.118308361717627, "percentage": 7.46, "elapsed_time": "1:54:59", "remaining_time": "23:47:23", "throughput": 8384.03, "total_tokens": 57845104} {"current_steps": 56900, "total_steps": 761865, "loss": 1.9794, "lr": 9.86304612175499e-07, "epoch": 1.12027721446713, "percentage": 7.47, "elapsed_time": "1:55:11", "remaining_time": "23:47:12", "throughput": 8383.93, "total_tokens": 57946904} {"current_steps": 57000, "total_steps": 761865, "loss": 2.0205, "lr": 9.862566449338551e-07, "epoch": 1.1222460672166328, "percentage": 7.48, "elapsed_time": "1:55:23", "remaining_time": "23:47:00", "throughput": 8383.84, "total_tokens": 58048648} {"current_steps": 57100, "total_steps": 761865, "loss": 2.025, "lr": 9.8620859500837e-07, "epoch": 1.1242149199661358, "percentage": 7.49, "elapsed_time": "1:55:36", "remaining_time": "23:46:50", "throughput": 8383.78, "total_tokens": 58151048} {"current_steps": 57200, "total_steps": 761865, "loss": 2.0139, "lr": 9.861604624072144e-07, "epoch": 1.1261837727156385, "percentage": 7.51, "elapsed_time": "1:55:48", "remaining_time": "23:46:38", "throughput": 8383.63, "total_tokens": 58252152} {"current_steps": 57300, "total_steps": 761865, "loss": 1.9569, "lr": 9.861122471385725e-07, "epoch": 1.1281526254651415, "percentage": 7.52, "elapsed_time": "1:56:00", "remaining_time": "23:46:27", "throughput": 8383.57, "total_tokens": 58354552} {"current_steps": 57400, "total_steps": 761865, "loss": 1.986, "lr": 9.86063949210643e-07, "epoch": 1.1301214782146443, "percentage": 7.53, "elapsed_time": "1:56:12", "remaining_time": "23:46:16", "throughput": 8383.53, "total_tokens": 58456952} {"current_steps": 57500, "total_steps": 761865, "loss": 2.0413, "lr": 9.860155686316385e-07, "epoch": 1.1320903309641472, "percentage": 7.55, "elapsed_time": "1:56:25", "remaining_time": "23:46:06", "throughput": 8383.47, "total_tokens": 58559352} {"current_steps": 57600, "total_steps": 761865, "loss": 2.0551, "lr": 9.85967105409786e-07, "epoch": 1.13405918371365, "percentage": 7.56, "elapsed_time": "1:56:37", "remaining_time": "23:45:54", "throughput": 8383.34, "total_tokens": 58660832} {"current_steps": 57700, "total_steps": 761865, "loss": 2.0195, "lr": 9.85918559553326e-07, "epoch": 1.136028036463153, "percentage": 7.57, "elapsed_time": "1:56:49", "remaining_time": "23:45:44", "throughput": 8383.28, "total_tokens": 58763232} {"current_steps": 57800, "total_steps": 761865, "loss": 2.0333, "lr": 9.858699310705132e-07, "epoch": 1.1379968892126557, "percentage": 7.59, "elapsed_time": "1:57:01", "remaining_time": "23:45:32", "throughput": 8383.12, "total_tokens": 58863984} {"current_steps": 57900, "total_steps": 761865, "loss": 1.9875, "lr": 9.858212199696168e-07, "epoch": 1.1399657419621587, "percentage": 7.6, "elapsed_time": "1:57:13", "remaining_time": "23:45:20", "throughput": 8383.03, "total_tokens": 58965472} {"current_steps": 58000, "total_steps": 761865, "loss": 1.9172, "lr": 9.857724262589196e-07, "epoch": 1.1419345947116615, "percentage": 7.61, "elapsed_time": "1:57:26", "remaining_time": "23:45:09", "throughput": 8382.97, "total_tokens": 59067872} {"current_steps": 58100, "total_steps": 761865, "loss": 1.9401, "lr": 9.857235499467183e-07, "epoch": 1.1439034474611645, "percentage": 7.63, "elapsed_time": "1:57:38", "remaining_time": "23:44:58", "throughput": 8382.91, "total_tokens": 59170272} {"current_steps": 58200, "total_steps": 761865, "loss": 1.9258, "lr": 9.856745910413244e-07, "epoch": 1.1458723002106672, "percentage": 7.64, "elapsed_time": "1:57:50", "remaining_time": "23:44:48", "throughput": 8382.86, "total_tokens": 59272672} {"current_steps": 58300, "total_steps": 761865, "loss": 2.0125, "lr": 9.856255495510624e-07, "epoch": 1.1478411529601702, "percentage": 7.65, "elapsed_time": "1:58:02", "remaining_time": "23:44:37", "throughput": 8382.8, "total_tokens": 59375072} {"current_steps": 58400, "total_steps": 761865, "loss": 1.9584, "lr": 9.855764254842717e-07, "epoch": 1.149810005709673, "percentage": 7.67, "elapsed_time": "1:58:15", "remaining_time": "23:44:26", "throughput": 8382.74, "total_tokens": 59477472} {"current_steps": 58500, "total_steps": 761865, "loss": 1.9672, "lr": 9.855272188493055e-07, "epoch": 1.151778858459176, "percentage": 7.68, "elapsed_time": "1:58:27", "remaining_time": "23:44:15", "throughput": 8382.62, "total_tokens": 59579064} {"current_steps": 58600, "total_steps": 761865, "loss": 1.9999, "lr": 9.854779296545307e-07, "epoch": 1.1537477112086787, "percentage": 7.69, "elapsed_time": "1:58:39", "remaining_time": "23:44:03", "throughput": 8382.51, "total_tokens": 59680728} {"current_steps": 58700, "total_steps": 761865, "loss": 2.0145, "lr": 9.854285579083288e-07, "epoch": 1.1557165639581815, "percentage": 7.7, "elapsed_time": "1:58:51", "remaining_time": "23:43:53", "throughput": 8382.44, "total_tokens": 59783128} {"current_steps": 58800, "total_steps": 761865, "loss": 1.9645, "lr": 9.853791036190951e-07, "epoch": 1.1576854167076844, "percentage": 7.72, "elapsed_time": "1:59:04", "remaining_time": "23:43:41", "throughput": 8382.31, "total_tokens": 59884232} {"current_steps": 58900, "total_steps": 761865, "loss": 1.9537, "lr": 9.853295667952384e-07, "epoch": 1.1596542694571874, "percentage": 7.73, "elapsed_time": "1:59:16", "remaining_time": "23:43:30", "throughput": 8382.27, "total_tokens": 59986632} {"current_steps": 59000, "total_steps": 761865, "loss": 2.0467, "lr": 9.852799474451824e-07, "epoch": 1.1616231222066902, "percentage": 7.74, "elapsed_time": "1:59:28", "remaining_time": "23:43:16", "throughput": 8381.99, "total_tokens": 60085184} {"current_steps": 59100, "total_steps": 761865, "loss": 1.9878, "lr": 9.852302455773644e-07, "epoch": 1.163591974956193, "percentage": 7.76, "elapsed_time": "1:59:40", "remaining_time": "23:43:05", "throughput": 8381.93, "total_tokens": 60187240} {"current_steps": 59200, "total_steps": 761865, "loss": 2.027, "lr": 9.851804612002357e-07, "epoch": 1.165560827705696, "percentage": 7.77, "elapsed_time": "1:59:52", "remaining_time": "23:42:54", "throughput": 8381.84, "total_tokens": 60289048} {"current_steps": 59300, "total_steps": 761865, "loss": 1.9659, "lr": 9.851305943222619e-07, "epoch": 1.1675296804551987, "percentage": 7.78, "elapsed_time": "2:00:05", "remaining_time": "23:42:43", "throughput": 8381.77, "total_tokens": 60391448} {"current_steps": 59400, "total_steps": 761865, "loss": 1.9666, "lr": 9.850806449519223e-07, "epoch": 1.1694985332047017, "percentage": 7.8, "elapsed_time": "2:00:17", "remaining_time": "23:42:32", "throughput": 8381.72, "total_tokens": 60493848} {"current_steps": 59500, "total_steps": 761865, "loss": 1.9786, "lr": 9.850306130977102e-07, "epoch": 1.1714673859542044, "percentage": 7.81, "elapsed_time": "2:00:29", "remaining_time": "23:42:20", "throughput": 8381.57, "total_tokens": 60594760} {"current_steps": 59600, "total_steps": 761865, "loss": 1.9985, "lr": 9.849804987681334e-07, "epoch": 1.1734362387037074, "percentage": 7.82, "elapsed_time": "2:00:41", "remaining_time": "23:42:09", "throughput": 8381.47, "total_tokens": 60696576} {"current_steps": 59700, "total_steps": 761865, "loss": 2.0163, "lr": 9.849303019717134e-07, "epoch": 1.1754050914532101, "percentage": 7.84, "elapsed_time": "2:00:53", "remaining_time": "23:41:57", "throughput": 8381.36, "total_tokens": 60798120} {"current_steps": 59800, "total_steps": 761865, "loss": 1.9601, "lr": 9.848800227169855e-07, "epoch": 1.1773739442027131, "percentage": 7.85, "elapsed_time": "2:01:06", "remaining_time": "23:41:47", "throughput": 8381.3, "total_tokens": 60900520} {"current_steps": 59900, "total_steps": 761865, "loss": 1.9743, "lr": 9.848296610124995e-07, "epoch": 1.1793427969522159, "percentage": 7.86, "elapsed_time": "2:01:18", "remaining_time": "23:41:36", "throughput": 8381.24, "total_tokens": 61002920} {"current_steps": 60000, "total_steps": 761865, "loss": 2.024, "lr": 9.847792168668189e-07, "epoch": 1.1813116497017189, "percentage": 7.88, "elapsed_time": "2:01:30", "remaining_time": "23:41:23", "throughput": 8381.06, "total_tokens": 61103056} {"current_steps": 60100, "total_steps": 761865, "loss": 1.9976, "lr": 9.847286902885212e-07, "epoch": 1.1832805024512216, "percentage": 7.89, "elapsed_time": "2:01:43", "remaining_time": "23:41:18", "throughput": 8380.44, "total_tokens": 61205456} {"current_steps": 60200, "total_steps": 761865, "loss": 1.9978, "lr": 9.846780812861981e-07, "epoch": 1.1852493552007246, "percentage": 7.9, "elapsed_time": "2:01:55", "remaining_time": "23:41:07", "throughput": 8380.39, "total_tokens": 61307856} {"current_steps": 60300, "total_steps": 761865, "loss": 2.0157, "lr": 9.846273898684555e-07, "epoch": 1.1872182079502274, "percentage": 7.91, "elapsed_time": "2:02:07", "remaining_time": "23:40:56", "throughput": 8380.29, "total_tokens": 61409440} {"current_steps": 60400, "total_steps": 761865, "loss": 2.0098, "lr": 9.845766160439125e-07, "epoch": 1.1891870606997303, "percentage": 7.93, "elapsed_time": "2:02:19", "remaining_time": "23:40:43", "throughput": 8380.14, "total_tokens": 61509456} {"current_steps": 60500, "total_steps": 761865, "loss": 2.0143, "lr": 9.845257598212031e-07, "epoch": 1.191155913449233, "percentage": 7.94, "elapsed_time": "2:02:32", "remaining_time": "23:40:31", "throughput": 8380.04, "total_tokens": 61610824} {"current_steps": 60600, "total_steps": 761865, "loss": 1.9789, "lr": 9.844748212089748e-07, "epoch": 1.193124766198736, "percentage": 7.95, "elapsed_time": "2:02:44", "remaining_time": "23:40:19", "throughput": 8379.95, "total_tokens": 61712376} {"current_steps": 60700, "total_steps": 761865, "loss": 2.0057, "lr": 9.844238002158896e-07, "epoch": 1.1950936189482388, "percentage": 7.97, "elapsed_time": "2:02:56", "remaining_time": "23:40:07", "throughput": 8379.86, "total_tokens": 61813528} {"current_steps": 60800, "total_steps": 761865, "loss": 2.0387, "lr": 9.84372696850623e-07, "epoch": 1.1970624716977416, "percentage": 7.98, "elapsed_time": "2:03:08", "remaining_time": "23:39:56", "throughput": 8379.78, "total_tokens": 61915296} {"current_steps": 60900, "total_steps": 761865, "loss": 1.9788, "lr": 9.843215111218646e-07, "epoch": 1.1990313244472446, "percentage": 7.99, "elapsed_time": "2:03:20", "remaining_time": "23:39:45", "throughput": 8379.7, "total_tokens": 62017384} {"current_steps": 61000, "total_steps": 761865, "loss": 1.9791, "lr": 9.842702430383183e-07, "epoch": 1.2010001771967476, "percentage": 8.01, "elapsed_time": "2:03:33", "remaining_time": "23:39:33", "throughput": 8379.6, "total_tokens": 62119056} {"current_steps": 61100, "total_steps": 761865, "loss": 1.965, "lr": 9.842188926087016e-07, "epoch": 1.2029690299462503, "percentage": 8.02, "elapsed_time": "2:03:45", "remaining_time": "23:39:22", "throughput": 8379.52, "total_tokens": 62220832} {"current_steps": 61200, "total_steps": 761865, "loss": 1.9089, "lr": 9.841674598417462e-07, "epoch": 1.204937882695753, "percentage": 8.03, "elapsed_time": "2:03:57", "remaining_time": "23:39:10", "throughput": 8379.44, "total_tokens": 62322504} {"current_steps": 61300, "total_steps": 761865, "loss": 1.9467, "lr": 9.841159447461982e-07, "epoch": 1.206906735445256, "percentage": 8.05, "elapsed_time": "2:04:09", "remaining_time": "23:38:59", "throughput": 8379.33, "total_tokens": 62423800} {"current_steps": 61400, "total_steps": 761865, "loss": 1.9633, "lr": 9.840643473308167e-07, "epoch": 1.2088755881947588, "percentage": 8.06, "elapsed_time": "2:04:21", "remaining_time": "23:38:48", "throughput": 8379.29, "total_tokens": 62526200} {"current_steps": 61500, "total_steps": 761865, "loss": 1.9583, "lr": 9.84012667604376e-07, "epoch": 1.2108444409442618, "percentage": 8.07, "elapsed_time": "2:04:34", "remaining_time": "23:38:35", "throughput": 8379.17, "total_tokens": 62626904} {"current_steps": 61600, "total_steps": 761865, "loss": 1.9895, "lr": 9.839609055756633e-07, "epoch": 1.2128132936937646, "percentage": 8.09, "elapsed_time": "2:04:46", "remaining_time": "23:38:23", "throughput": 8379.03, "total_tokens": 62727760} {"current_steps": 61700, "total_steps": 761865, "loss": 2.0228, "lr": 9.839090612534807e-07, "epoch": 1.2147821464432675, "percentage": 8.1, "elapsed_time": "2:04:58", "remaining_time": "23:38:12", "throughput": 8378.98, "total_tokens": 62830160} {"current_steps": 61800, "total_steps": 761865, "loss": 2.0125, "lr": 9.838571346466435e-07, "epoch": 1.2167509991927703, "percentage": 8.11, "elapsed_time": "2:05:10", "remaining_time": "23:38:01", "throughput": 8378.87, "total_tokens": 62931632} {"current_steps": 61900, "total_steps": 761865, "loss": 1.9714, "lr": 9.838051257639816e-07, "epoch": 1.2187198519422733, "percentage": 8.12, "elapsed_time": "2:05:22", "remaining_time": "23:37:49", "throughput": 8378.76, "total_tokens": 63033176} {"current_steps": 62000, "total_steps": 761865, "loss": 2.0194, "lr": 9.83753034614339e-07, "epoch": 1.220688704691776, "percentage": 8.14, "elapsed_time": "2:05:35", "remaining_time": "23:37:38", "throughput": 8378.71, "total_tokens": 63135576} {"current_steps": 62100, "total_steps": 761865, "loss": 1.9567, "lr": 9.837008612065728e-07, "epoch": 1.222657557441279, "percentage": 8.15, "elapsed_time": "2:05:47", "remaining_time": "23:37:27", "throughput": 8378.64, "total_tokens": 63237376} {"current_steps": 62200, "total_steps": 761865, "loss": 1.9964, "lr": 9.836486055495548e-07, "epoch": 1.2246264101907818, "percentage": 8.16, "elapsed_time": "2:05:59", "remaining_time": "23:37:16", "throughput": 8378.6, "total_tokens": 63339776} {"current_steps": 62300, "total_steps": 761865, "loss": 1.9864, "lr": 9.835962676521708e-07, "epoch": 1.2265952629402848, "percentage": 8.18, "elapsed_time": "2:06:11", "remaining_time": "23:37:03", "throughput": 8378.43, "total_tokens": 63439912} {"current_steps": 62400, "total_steps": 761865, "loss": 2.0018, "lr": 9.835438475233204e-07, "epoch": 1.2285641156897875, "percentage": 8.19, "elapsed_time": "2:06:24", "remaining_time": "23:36:52", "throughput": 8378.37, "total_tokens": 63541744} {"current_steps": 62500, "total_steps": 761865, "loss": 2.0296, "lr": 9.834913451719168e-07, "epoch": 1.2305329684392905, "percentage": 8.2, "elapsed_time": "2:06:36", "remaining_time": "23:36:40", "throughput": 8378.3, "total_tokens": 63643704} {"current_steps": 62600, "total_steps": 761865, "loss": 1.9982, "lr": 9.834387606068883e-07, "epoch": 1.2325018211887933, "percentage": 8.22, "elapsed_time": "2:06:48", "remaining_time": "23:36:29", "throughput": 8378.25, "total_tokens": 63745576} {"current_steps": 62700, "total_steps": 761865, "loss": 1.9754, "lr": 9.833860938371758e-07, "epoch": 1.2344706739382962, "percentage": 8.23, "elapsed_time": "2:07:00", "remaining_time": "23:36:18", "throughput": 8378.2, "total_tokens": 63847888} {"current_steps": 62800, "total_steps": 761865, "loss": 2.0246, "lr": 9.833333448717354e-07, "epoch": 1.236439526687799, "percentage": 8.24, "elapsed_time": "2:07:12", "remaining_time": "23:36:06", "throughput": 8378.13, "total_tokens": 63949704} {"current_steps": 62900, "total_steps": 761865, "loss": 1.9625, "lr": 9.832805137195362e-07, "epoch": 1.238408379437302, "percentage": 8.26, "elapsed_time": "2:07:25", "remaining_time": "23:35:55", "throughput": 8378.07, "total_tokens": 64051544} {"current_steps": 63000, "total_steps": 761865, "loss": 1.9919, "lr": 9.832276003895616e-07, "epoch": 1.2403772321868047, "percentage": 8.27, "elapsed_time": "2:07:37", "remaining_time": "23:35:44", "throughput": 8378.02, "total_tokens": 64153944} {"current_steps": 63100, "total_steps": 761865, "loss": 1.9627, "lr": 9.831746048908095e-07, "epoch": 1.2423460849363077, "percentage": 8.28, "elapsed_time": "2:07:49", "remaining_time": "23:35:32", "throughput": 8377.95, "total_tokens": 64255584} {"current_steps": 63200, "total_steps": 761865, "loss": 1.9801, "lr": 9.83121527232291e-07, "epoch": 1.2443149376858105, "percentage": 8.3, "elapsed_time": "2:08:01", "remaining_time": "23:35:21", "throughput": 8377.84, "total_tokens": 64356992} {"current_steps": 63300, "total_steps": 761865, "loss": 2.0256, "lr": 9.830683674230318e-07, "epoch": 1.2462837904353132, "percentage": 8.31, "elapsed_time": "2:08:13", "remaining_time": "23:35:08", "throughput": 8377.66, "total_tokens": 64456856} {"current_steps": 63400, "total_steps": 761865, "loss": 1.9839, "lr": 9.83015125472071e-07, "epoch": 1.2482526431848162, "percentage": 8.32, "elapsed_time": "2:08:26", "remaining_time": "23:34:57", "throughput": 8377.63, "total_tokens": 64559256} {"current_steps": 63500, "total_steps": 761865, "loss": 2.0219, "lr": 9.82961801388462e-07, "epoch": 1.2502214959343192, "percentage": 8.33, "elapsed_time": "2:08:38", "remaining_time": "23:34:46", "throughput": 8377.57, "total_tokens": 64661656} {"current_steps": 63600, "total_steps": 761865, "loss": 2.0168, "lr": 9.829083951812723e-07, "epoch": 1.252190348683822, "percentage": 8.35, "elapsed_time": "2:08:50", "remaining_time": "23:34:35", "throughput": 8377.51, "total_tokens": 64763960} {"current_steps": 63700, "total_steps": 761865, "loss": 1.9511, "lr": 9.828549068595829e-07, "epoch": 1.2541592014333247, "percentage": 8.36, "elapsed_time": "2:09:02", "remaining_time": "23:34:23", "throughput": 8377.42, "total_tokens": 64865648} {"current_steps": 63800, "total_steps": 761865, "loss": 1.9926, "lr": 9.828013364324892e-07, "epoch": 1.2561280541828277, "percentage": 8.37, "elapsed_time": "2:09:15", "remaining_time": "23:34:12", "throughput": 8377.33, "total_tokens": 64967240} {"current_steps": 63900, "total_steps": 761865, "loss": 1.9805, "lr": 9.827476839091006e-07, "epoch": 1.2580969069323304, "percentage": 8.39, "elapsed_time": "2:09:27", "remaining_time": "23:34:00", "throughput": 8377.25, "total_tokens": 65068880} {"current_steps": 64000, "total_steps": 761865, "loss": 1.9444, "lr": 9.826939492985398e-07, "epoch": 1.2600657596818334, "percentage": 8.4, "elapsed_time": "2:09:39", "remaining_time": "23:33:49", "throughput": 8377.19, "total_tokens": 65171280} {"current_steps": 64100, "total_steps": 761865, "loss": 1.9323, "lr": 9.826401326099442e-07, "epoch": 1.2620346124313362, "percentage": 8.41, "elapsed_time": "2:09:51", "remaining_time": "23:33:38", "throughput": 8377.17, "total_tokens": 65273680} {"current_steps": 64200, "total_steps": 761865, "loss": 2.0457, "lr": 9.825862338524648e-07, "epoch": 1.2640034651808392, "percentage": 8.43, "elapsed_time": "2:10:04", "remaining_time": "23:33:27", "throughput": 8377.07, "total_tokens": 65375520} {"current_steps": 64300, "total_steps": 761865, "loss": 1.9929, "lr": 9.825322530352666e-07, "epoch": 1.265972317930342, "percentage": 8.44, "elapsed_time": "2:10:16", "remaining_time": "23:33:16", "throughput": 8376.98, "total_tokens": 65477072} {"current_steps": 64400, "total_steps": 761865, "loss": 1.9284, "lr": 9.824781901675287e-07, "epoch": 1.267941170679845, "percentage": 8.45, "elapsed_time": "2:10:28", "remaining_time": "23:33:04", "throughput": 8376.91, "total_tokens": 65578792} {"current_steps": 64500, "total_steps": 761865, "loss": 1.9872, "lr": 9.82424045258444e-07, "epoch": 1.2699100234293477, "percentage": 8.47, "elapsed_time": "2:10:40", "remaining_time": "23:32:53", "throughput": 8376.87, "total_tokens": 65681192} {"current_steps": 64600, "total_steps": 761865, "loss": 2.009, "lr": 9.823698183172192e-07, "epoch": 1.2718788761788506, "percentage": 8.48, "elapsed_time": "2:10:52", "remaining_time": "23:32:41", "throughput": 8376.8, "total_tokens": 65782744} {"current_steps": 64700, "total_steps": 761865, "loss": 1.9632, "lr": 9.823155093530755e-07, "epoch": 1.2738477289283534, "percentage": 8.49, "elapsed_time": "2:11:05", "remaining_time": "23:32:30", "throughput": 8376.76, "total_tokens": 65885144} {"current_steps": 64800, "total_steps": 761865, "loss": 1.9498, "lr": 9.822611183752473e-07, "epoch": 1.2758165816778564, "percentage": 8.51, "elapsed_time": "2:11:17", "remaining_time": "23:32:19", "throughput": 8376.71, "total_tokens": 65987544} {"current_steps": 64900, "total_steps": 761865, "loss": 2.0062, "lr": 9.822066453929839e-07, "epoch": 1.2777854344273591, "percentage": 8.52, "elapsed_time": "2:11:29", "remaining_time": "23:32:08", "throughput": 8376.66, "total_tokens": 66089416} {"current_steps": 65000, "total_steps": 761865, "loss": 1.9604, "lr": 9.821520904155471e-07, "epoch": 1.279754287176862, "percentage": 8.53, "elapsed_time": "2:11:41", "remaining_time": "23:31:56", "throughput": 8376.56, "total_tokens": 66191056} {"current_steps": 65100, "total_steps": 761865, "loss": 1.9932, "lr": 9.820974534522142e-07, "epoch": 1.2817231399263649, "percentage": 8.54, "elapsed_time": "2:11:54", "remaining_time": "23:31:51", "throughput": 8375.98, "total_tokens": 66293456} {"current_steps": 65200, "total_steps": 761865, "loss": 1.9576, "lr": 9.820427345122755e-07, "epoch": 1.2836919926758679, "percentage": 8.56, "elapsed_time": "2:12:06", "remaining_time": "23:31:38", "throughput": 8375.87, "total_tokens": 66394368} {"current_steps": 65300, "total_steps": 761865, "loss": 1.9723, "lr": 9.819879336050355e-07, "epoch": 1.2856608454253706, "percentage": 8.57, "elapsed_time": "2:12:19", "remaining_time": "23:31:27", "throughput": 8375.83, "total_tokens": 66496664} {"current_steps": 65400, "total_steps": 761865, "loss": 1.9823, "lr": 9.819330507398127e-07, "epoch": 1.2876296981748734, "percentage": 8.58, "elapsed_time": "2:12:31", "remaining_time": "23:31:16", "throughput": 8375.76, "total_tokens": 66598288} {"current_steps": 65500, "total_steps": 761865, "loss": 1.9796, "lr": 9.818780859259395e-07, "epoch": 1.2895985509243764, "percentage": 8.6, "elapsed_time": "2:12:43", "remaining_time": "23:31:05", "throughput": 8375.71, "total_tokens": 66700688} {"current_steps": 65600, "total_steps": 761865, "loss": 2.0197, "lr": 9.81823039172762e-07, "epoch": 1.2915674036738793, "percentage": 8.61, "elapsed_time": "2:12:55", "remaining_time": "23:30:53", "throughput": 8375.64, "total_tokens": 66802256} {"current_steps": 65700, "total_steps": 761865, "loss": 1.9878, "lr": 9.817679104896407e-07, "epoch": 1.293536256423382, "percentage": 8.62, "elapsed_time": "2:13:08", "remaining_time": "23:30:42", "throughput": 8375.6, "total_tokens": 66904656} {"current_steps": 65800, "total_steps": 761865, "loss": 1.9737, "lr": 9.817126998859493e-07, "epoch": 1.2955051091728849, "percentage": 8.64, "elapsed_time": "2:13:20", "remaining_time": "23:30:29", "throughput": 8375.51, "total_tokens": 67005536} {"current_steps": 65900, "total_steps": 761865, "loss": 1.9983, "lr": 9.816574073710767e-07, "epoch": 1.2974739619223878, "percentage": 8.65, "elapsed_time": "2:13:32", "remaining_time": "23:30:16", "throughput": 8375.38, "total_tokens": 67105736} {"current_steps": 66000, "total_steps": 761865, "loss": 1.9838, "lr": 9.81602032954424e-07, "epoch": 1.2994428146718908, "percentage": 8.66, "elapsed_time": "2:13:44", "remaining_time": "23:30:05", "throughput": 8375.34, "total_tokens": 67208136} {"current_steps": 66100, "total_steps": 761865, "loss": 1.9792, "lr": 9.81546576645408e-07, "epoch": 1.3014116674213936, "percentage": 8.68, "elapsed_time": "2:13:56", "remaining_time": "23:29:54", "throughput": 8375.31, "total_tokens": 67310536} {"current_steps": 66200, "total_steps": 761865, "loss": 1.9768, "lr": 9.81491038453458e-07, "epoch": 1.3033805201708963, "percentage": 8.69, "elapsed_time": "2:14:08", "remaining_time": "23:29:43", "throughput": 8375.24, "total_tokens": 67412160} {"current_steps": 66300, "total_steps": 761865, "loss": 1.9902, "lr": 9.814354183880182e-07, "epoch": 1.3053493729203993, "percentage": 8.7, "elapsed_time": "2:14:21", "remaining_time": "23:29:31", "throughput": 8375.15, "total_tokens": 67513384} {"current_steps": 66400, "total_steps": 761865, "loss": 1.979, "lr": 9.81379716458546e-07, "epoch": 1.307318225669902, "percentage": 8.72, "elapsed_time": "2:14:33", "remaining_time": "23:29:18", "throughput": 8375.04, "total_tokens": 67614232} {"current_steps": 66500, "total_steps": 761865, "loss": 2.0128, "lr": 9.813239326745131e-07, "epoch": 1.309287078419405, "percentage": 8.73, "elapsed_time": "2:14:45", "remaining_time": "23:29:07", "throughput": 8374.99, "total_tokens": 67716632} {"current_steps": 66600, "total_steps": 761865, "loss": 2.0334, "lr": 9.812680670454051e-07, "epoch": 1.3112559311689078, "percentage": 8.74, "elapsed_time": "2:14:57", "remaining_time": "23:28:56", "throughput": 8374.93, "total_tokens": 67818328} {"current_steps": 66700, "total_steps": 761865, "loss": 1.9849, "lr": 9.812121195807216e-07, "epoch": 1.3132247839184108, "percentage": 8.75, "elapsed_time": "2:15:09", "remaining_time": "23:28:44", "throughput": 8374.83, "total_tokens": 67919528} {"current_steps": 66800, "total_steps": 761865, "loss": 2.0113, "lr": 9.811560902899758e-07, "epoch": 1.3151936366679136, "percentage": 8.77, "elapsed_time": "2:15:22", "remaining_time": "23:28:32", "throughput": 8374.8, "total_tokens": 68021928} {"current_steps": 66900, "total_steps": 761865, "loss": 1.9536, "lr": 9.810999791826953e-07, "epoch": 1.3171624894174165, "percentage": 8.78, "elapsed_time": "2:15:34", "remaining_time": "23:28:21", "throughput": 8374.76, "total_tokens": 68124328} {"current_steps": 67000, "total_steps": 761865, "loss": 1.9535, "lr": 9.81043786268421e-07, "epoch": 1.3191313421669193, "percentage": 8.79, "elapsed_time": "2:15:46", "remaining_time": "23:28:09", "throughput": 8374.67, "total_tokens": 68225256} {"current_steps": 67100, "total_steps": 761865, "loss": 1.9658, "lr": 9.80987511556708e-07, "epoch": 1.3211001949164223, "percentage": 8.81, "elapsed_time": "2:15:58", "remaining_time": "23:27:57", "throughput": 8374.59, "total_tokens": 68326312} {"current_steps": 67200, "total_steps": 761865, "loss": 1.9966, "lr": 9.809311550571259e-07, "epoch": 1.323069047665925, "percentage": 8.82, "elapsed_time": "2:16:11", "remaining_time": "23:27:46", "throughput": 8374.55, "total_tokens": 68428712} {"current_steps": 67300, "total_steps": 761865, "loss": 1.983, "lr": 9.808747167792567e-07, "epoch": 1.325037900415428, "percentage": 8.83, "elapsed_time": "2:16:23", "remaining_time": "23:27:33", "throughput": 8374.44, "total_tokens": 68529312} {"current_steps": 67400, "total_steps": 761865, "loss": 1.9474, "lr": 9.808181967326983e-07, "epoch": 1.3270067531649308, "percentage": 8.85, "elapsed_time": "2:16:35", "remaining_time": "23:27:22", "throughput": 8374.38, "total_tokens": 68631264} {"current_steps": 67500, "total_steps": 761865, "loss": 1.9404, "lr": 9.807615949270606e-07, "epoch": 1.3289756059144335, "percentage": 8.86, "elapsed_time": "2:16:47", "remaining_time": "23:27:11", "throughput": 8374.36, "total_tokens": 68733664} {"current_steps": 67600, "total_steps": 761865, "loss": 1.9482, "lr": 9.807049113719687e-07, "epoch": 1.3309444586639365, "percentage": 8.87, "elapsed_time": "2:16:59", "remaining_time": "23:26:59", "throughput": 8374.3, "total_tokens": 68835272} {"current_steps": 67700, "total_steps": 761865, "loss": 1.9334, "lr": 9.806481460770613e-07, "epoch": 1.3329133114134395, "percentage": 8.89, "elapsed_time": "2:17:12", "remaining_time": "23:26:47", "throughput": 8374.27, "total_tokens": 68937672} {"current_steps": 67800, "total_steps": 761865, "loss": 1.95, "lr": 9.805912990519903e-07, "epoch": 1.3348821641629423, "percentage": 8.9, "elapsed_time": "2:17:24", "remaining_time": "23:26:36", "throughput": 8374.22, "total_tokens": 69039592} {"current_steps": 67900, "total_steps": 761865, "loss": 1.97, "lr": 9.805343703064226e-07, "epoch": 1.336851016912445, "percentage": 8.91, "elapsed_time": "2:17:36", "remaining_time": "23:26:24", "throughput": 8374.16, "total_tokens": 69141136} {"current_steps": 68000, "total_steps": 761865, "loss": 1.9966, "lr": 9.804773598500381e-07, "epoch": 1.338819869661948, "percentage": 8.93, "elapsed_time": "2:17:48", "remaining_time": "23:26:13", "throughput": 8374.13, "total_tokens": 69243536} {"current_steps": 68100, "total_steps": 761865, "loss": 1.981, "lr": 9.804202676925313e-07, "epoch": 1.340788722411451, "percentage": 8.94, "elapsed_time": "2:18:01", "remaining_time": "23:26:02", "throughput": 8374.08, "total_tokens": 69345808} {"current_steps": 68200, "total_steps": 761865, "loss": 1.9632, "lr": 9.8036309384361e-07, "epoch": 1.3427575751609537, "percentage": 8.95, "elapsed_time": "2:18:13", "remaining_time": "23:25:50", "throughput": 8374.03, "total_tokens": 69447728} {"current_steps": 68300, "total_steps": 761865, "loss": 1.9684, "lr": 9.803058383129958e-07, "epoch": 1.3447264279104565, "percentage": 8.96, "elapsed_time": "2:18:25", "remaining_time": "23:25:38", "throughput": 8373.92, "total_tokens": 69548456} {"current_steps": 68400, "total_steps": 761865, "loss": 1.9948, "lr": 9.802485011104254e-07, "epoch": 1.3466952806599595, "percentage": 8.98, "elapsed_time": "2:18:37", "remaining_time": "23:25:26", "throughput": 8373.83, "total_tokens": 69649928} {"current_steps": 68500, "total_steps": 761865, "loss": 1.9943, "lr": 9.801910822456476e-07, "epoch": 1.3486641334094622, "percentage": 8.99, "elapsed_time": "2:18:49", "remaining_time": "23:25:14", "throughput": 8373.75, "total_tokens": 69750912} {"current_steps": 68600, "total_steps": 761865, "loss": 1.9669, "lr": 9.801335817284266e-07, "epoch": 1.3506329861589652, "percentage": 9.0, "elapsed_time": "2:19:01", "remaining_time": "23:25:02", "throughput": 8373.7, "total_tokens": 69852200} {"current_steps": 68700, "total_steps": 761865, "loss": 1.9891, "lr": 9.800759995685395e-07, "epoch": 1.352601838908468, "percentage": 9.02, "elapsed_time": "2:19:13", "remaining_time": "23:24:49", "throughput": 8373.61, "total_tokens": 69952848} {"current_steps": 68800, "total_steps": 761865, "loss": 2.0238, "lr": 9.800183357757778e-07, "epoch": 1.354570691657971, "percentage": 9.03, "elapsed_time": "2:19:26", "remaining_time": "23:24:37", "throughput": 8373.5, "total_tokens": 70054280} {"current_steps": 68900, "total_steps": 761865, "loss": 1.9838, "lr": 9.79960590359947e-07, "epoch": 1.3565395444074737, "percentage": 9.04, "elapsed_time": "2:19:38", "remaining_time": "23:24:26", "throughput": 8373.44, "total_tokens": 70155976} {"current_steps": 69000, "total_steps": 761865, "loss": 1.9918, "lr": 9.799027633308658e-07, "epoch": 1.3585083971569767, "percentage": 9.06, "elapsed_time": "2:19:50", "remaining_time": "23:24:14", "throughput": 8373.41, "total_tokens": 70258376} {"current_steps": 69100, "total_steps": 761865, "loss": 1.9936, "lr": 9.798448546983674e-07, "epoch": 1.3604772499064794, "percentage": 9.07, "elapsed_time": "2:20:02", "remaining_time": "23:24:02", "throughput": 8373.29, "total_tokens": 70358560} {"current_steps": 69200, "total_steps": 761865, "loss": 1.9968, "lr": 9.797868644722987e-07, "epoch": 1.3624461026559824, "percentage": 9.08, "elapsed_time": "2:20:15", "remaining_time": "23:23:51", "throughput": 8373.23, "total_tokens": 70460960} {"current_steps": 69300, "total_steps": 761865, "loss": 1.9406, "lr": 9.797287926625203e-07, "epoch": 1.3644149554054852, "percentage": 9.1, "elapsed_time": "2:20:27", "remaining_time": "23:23:39", "throughput": 8373.19, "total_tokens": 70562768} {"current_steps": 69400, "total_steps": 761865, "loss": 1.9732, "lr": 9.796706392789072e-07, "epoch": 1.3663838081549882, "percentage": 9.11, "elapsed_time": "2:20:39", "remaining_time": "23:23:27", "throughput": 8373.12, "total_tokens": 70663960} {"current_steps": 69500, "total_steps": 761865, "loss": 1.9615, "lr": 9.796124043313474e-07, "epoch": 1.368352660904491, "percentage": 9.12, "elapsed_time": "2:20:51", "remaining_time": "23:23:15", "throughput": 8373.04, "total_tokens": 70765448} {"current_steps": 69600, "total_steps": 761865, "loss": 1.9313, "lr": 9.795540878297434e-07, "epoch": 1.3703215136539937, "percentage": 9.14, "elapsed_time": "2:21:03", "remaining_time": "23:23:03", "throughput": 8372.95, "total_tokens": 70867144} {"current_steps": 69700, "total_steps": 761865, "loss": 1.9658, "lr": 9.794956897840118e-07, "epoch": 1.3722903664034967, "percentage": 9.15, "elapsed_time": "2:21:16", "remaining_time": "23:22:52", "throughput": 8372.89, "total_tokens": 70968928} {"current_steps": 69800, "total_steps": 761865, "loss": 1.9558, "lr": 9.794372102040822e-07, "epoch": 1.3742592191529996, "percentage": 9.16, "elapsed_time": "2:21:28", "remaining_time": "23:22:41", "throughput": 8372.86, "total_tokens": 71071328} {"current_steps": 69900, "total_steps": 761865, "loss": 1.9873, "lr": 9.793786490998987e-07, "epoch": 1.3762280719025024, "percentage": 9.17, "elapsed_time": "2:21:40", "remaining_time": "23:22:28", "throughput": 8372.72, "total_tokens": 71171512} {"current_steps": 70000, "total_steps": 761865, "loss": 1.9997, "lr": 9.793200064814193e-07, "epoch": 1.3781969246520052, "percentage": 9.19, "elapsed_time": "2:21:52", "remaining_time": "23:22:16", "throughput": 8372.66, "total_tokens": 71273208} {"current_steps": 70100, "total_steps": 761865, "loss": 1.9791, "lr": 9.792612823586158e-07, "epoch": 1.3801657774015081, "percentage": 9.2, "elapsed_time": "2:22:05", "remaining_time": "23:22:10", "throughput": 8372.12, "total_tokens": 71375608} {"current_steps": 70200, "total_steps": 761865, "loss": 1.9928, "lr": 9.792024767414731e-07, "epoch": 1.3821346301510111, "percentage": 9.21, "elapsed_time": "2:22:17", "remaining_time": "23:21:59", "throughput": 8372.04, "total_tokens": 71477360} {"current_steps": 70300, "total_steps": 761865, "loss": 1.9577, "lr": 9.791435896399913e-07, "epoch": 1.3841034829005139, "percentage": 9.23, "elapsed_time": "2:22:29", "remaining_time": "23:21:48", "throughput": 8372.03, "total_tokens": 71579760} {"current_steps": 70400, "total_steps": 761865, "loss": 1.9734, "lr": 9.790846210641832e-07, "epoch": 1.3860723356500166, "percentage": 9.24, "elapsed_time": "2:22:42", "remaining_time": "23:21:36", "throughput": 8371.98, "total_tokens": 71682160} {"current_steps": 70500, "total_steps": 761865, "loss": 2.0064, "lr": 9.79025571024076e-07, "epoch": 1.3880411883995196, "percentage": 9.25, "elapsed_time": "2:22:54", "remaining_time": "23:21:25", "throughput": 8371.93, "total_tokens": 71783792} {"current_steps": 70600, "total_steps": 761865, "loss": 2.0239, "lr": 9.789664395297109e-07, "epoch": 1.3900100411490226, "percentage": 9.27, "elapsed_time": "2:23:06", "remaining_time": "23:21:13", "throughput": 8371.85, "total_tokens": 71885384} {"current_steps": 70700, "total_steps": 761865, "loss": 1.9708, "lr": 9.789072265911426e-07, "epoch": 1.3919788938985254, "percentage": 9.28, "elapsed_time": "2:23:18", "remaining_time": "23:21:01", "throughput": 8371.78, "total_tokens": 71987128} {"current_steps": 70800, "total_steps": 761865, "loss": 1.9854, "lr": 9.788479322184395e-07, "epoch": 1.3939477466480281, "percentage": 9.29, "elapsed_time": "2:23:30", "remaining_time": "23:20:49", "throughput": 8371.67, "total_tokens": 72088096} {"current_steps": 70900, "total_steps": 761865, "loss": 2.0041, "lr": 9.787885564216844e-07, "epoch": 1.395916599397531, "percentage": 9.31, "elapsed_time": "2:23:43", "remaining_time": "23:20:38", "throughput": 8371.62, "total_tokens": 72189944} {"current_steps": 71000, "total_steps": 761865, "loss": 1.9884, "lr": 9.787290992109737e-07, "epoch": 1.3978854521470339, "percentage": 9.32, "elapsed_time": "2:23:55", "remaining_time": "23:20:26", "throughput": 8371.49, "total_tokens": 72290592} {"current_steps": 71100, "total_steps": 761865, "loss": 1.9893, "lr": 9.786695605964175e-07, "epoch": 1.3998543048965368, "percentage": 9.33, "elapsed_time": "2:24:07", "remaining_time": "23:20:14", "throughput": 8371.37, "total_tokens": 72391536} {"current_steps": 71200, "total_steps": 761865, "loss": 1.9986, "lr": 9.786099405881395e-07, "epoch": 1.4018231576460396, "percentage": 9.35, "elapsed_time": "2:24:19", "remaining_time": "23:20:01", "throughput": 8371.3, "total_tokens": 72492576} {"current_steps": 71300, "total_steps": 761865, "loss": 1.9589, "lr": 9.785502391962781e-07, "epoch": 1.4037920103955426, "percentage": 9.36, "elapsed_time": "2:24:31", "remaining_time": "23:19:49", "throughput": 8371.18, "total_tokens": 72593528} {"current_steps": 71400, "total_steps": 761865, "loss": 1.9909, "lr": 9.78490456430985e-07, "epoch": 1.4057608631450453, "percentage": 9.37, "elapsed_time": "2:24:44", "remaining_time": "23:19:38", "throughput": 8371.15, "total_tokens": 72695928} {"current_steps": 71500, "total_steps": 761865, "loss": 2.0325, "lr": 9.78430592302425e-07, "epoch": 1.4077297158945483, "percentage": 9.38, "elapsed_time": "2:24:56", "remaining_time": "23:19:27", "throughput": 8371.04, "total_tokens": 72797424} {"current_steps": 71600, "total_steps": 761865, "loss": 1.9457, "lr": 9.783706468207784e-07, "epoch": 1.409698568644051, "percentage": 9.4, "elapsed_time": "2:25:08", "remaining_time": "23:19:15", "throughput": 8371.01, "total_tokens": 72899824} {"current_steps": 71700, "total_steps": 761865, "loss": 2.0035, "lr": 9.783106199962381e-07, "epoch": 1.411667421393554, "percentage": 9.41, "elapsed_time": "2:25:20", "remaining_time": "23:19:03", "throughput": 8370.9, "total_tokens": 73000784} {"current_steps": 71800, "total_steps": 761865, "loss": 1.9815, "lr": 9.782505118390109e-07, "epoch": 1.4136362741430568, "percentage": 9.42, "elapsed_time": "2:25:33", "remaining_time": "23:18:52", "throughput": 8370.84, "total_tokens": 73102680} {"current_steps": 71900, "total_steps": 761865, "loss": 1.9955, "lr": 9.781903223593182e-07, "epoch": 1.4156051268925598, "percentage": 9.44, "elapsed_time": "2:25:45", "remaining_time": "23:18:41", "throughput": 8370.81, "total_tokens": 73205080} {"current_steps": 72000, "total_steps": 761865, "loss": 2.0017, "lr": 9.781300515673942e-07, "epoch": 1.4175739796420626, "percentage": 9.45, "elapsed_time": "2:25:57", "remaining_time": "23:18:29", "throughput": 8370.74, "total_tokens": 73306728} {"current_steps": 72100, "total_steps": 761865, "loss": 1.9744, "lr": 9.78069699473488e-07, "epoch": 1.4195428323915653, "percentage": 9.46, "elapsed_time": "2:26:09", "remaining_time": "23:18:18", "throughput": 8370.7, "total_tokens": 73409128} {"current_steps": 72200, "total_steps": 761865, "loss": 1.9744, "lr": 9.780092660878614e-07, "epoch": 1.4215116851410683, "percentage": 9.48, "elapsed_time": "2:26:22", "remaining_time": "23:18:06", "throughput": 8370.65, "total_tokens": 73511032} {"current_steps": 72300, "total_steps": 761865, "loss": 2.0243, "lr": 9.779487514207906e-07, "epoch": 1.4234805378905713, "percentage": 9.49, "elapsed_time": "2:26:34", "remaining_time": "23:17:55", "throughput": 8370.57, "total_tokens": 73612768} {"current_steps": 72400, "total_steps": 761865, "loss": 1.9732, "lr": 9.778881554825662e-07, "epoch": 1.425449390640074, "percentage": 9.5, "elapsed_time": "2:26:46", "remaining_time": "23:17:43", "throughput": 8370.48, "total_tokens": 73714232} {"current_steps": 72500, "total_steps": 761865, "loss": 1.9609, "lr": 9.778274782834915e-07, "epoch": 1.4274182433895768, "percentage": 9.52, "elapsed_time": "2:26:58", "remaining_time": "23:17:32", "throughput": 8370.43, "total_tokens": 73816232} {"current_steps": 72600, "total_steps": 761865, "loss": 1.9909, "lr": 9.777667198338843e-07, "epoch": 1.4293870961390798, "percentage": 9.53, "elapsed_time": "2:27:10", "remaining_time": "23:17:21", "throughput": 8370.39, "total_tokens": 73918632} {"current_steps": 72700, "total_steps": 761865, "loss": 2.0129, "lr": 9.77705880144076e-07, "epoch": 1.4313559488885828, "percentage": 9.54, "elapsed_time": "2:27:23", "remaining_time": "23:17:09", "throughput": 8370.31, "total_tokens": 74020240} {"current_steps": 72800, "total_steps": 761865, "loss": 1.9846, "lr": 9.77644959224412e-07, "epoch": 1.4333248016380855, "percentage": 9.56, "elapsed_time": "2:27:35", "remaining_time": "23:16:55", "throughput": 8370.15, "total_tokens": 74119088} {"current_steps": 72900, "total_steps": 761865, "loss": 2.0401, "lr": 9.775839570852512e-07, "epoch": 1.4352936543875883, "percentage": 9.57, "elapsed_time": "2:27:47", "remaining_time": "23:16:44", "throughput": 8370.11, "total_tokens": 74221488} {"current_steps": 73000, "total_steps": 761865, "loss": 2.0336, "lr": 9.77522873736967e-07, "epoch": 1.4372625071370912, "percentage": 9.58, "elapsed_time": "2:27:59", "remaining_time": "23:16:32", "throughput": 8370.03, "total_tokens": 74322552} {"current_steps": 73100, "total_steps": 761865, "loss": 1.9896, "lr": 9.774617091899455e-07, "epoch": 1.439231359886594, "percentage": 9.59, "elapsed_time": "2:28:11", "remaining_time": "23:16:20", "throughput": 8369.95, "total_tokens": 74424288} {"current_steps": 73200, "total_steps": 761865, "loss": 2.0052, "lr": 9.774004634545874e-07, "epoch": 1.441200212636097, "percentage": 9.61, "elapsed_time": "2:28:24", "remaining_time": "23:16:09", "throughput": 8369.92, "total_tokens": 74526688} {"current_steps": 73300, "total_steps": 761865, "loss": 2.0013, "lr": 9.77339136541307e-07, "epoch": 1.4431690653855997, "percentage": 9.62, "elapsed_time": "2:28:36", "remaining_time": "23:15:58", "throughput": 8369.84, "total_tokens": 74628320} {"current_steps": 73400, "total_steps": 761865, "loss": 1.9748, "lr": 9.772777284605327e-07, "epoch": 1.4451379181351027, "percentage": 9.63, "elapsed_time": "2:28:48", "remaining_time": "23:15:46", "throughput": 8369.77, "total_tokens": 74729792} {"current_steps": 73500, "total_steps": 761865, "loss": 2.0092, "lr": 9.772162392227062e-07, "epoch": 1.4471067708846055, "percentage": 9.65, "elapsed_time": "2:29:00", "remaining_time": "23:15:34", "throughput": 8369.7, "total_tokens": 74831344} {"current_steps": 73600, "total_steps": 761865, "loss": 2.0175, "lr": 9.771546688382831e-07, "epoch": 1.4490756236341085, "percentage": 9.66, "elapsed_time": "2:29:12", "remaining_time": "23:15:22", "throughput": 8369.57, "total_tokens": 74931784} {"current_steps": 73700, "total_steps": 761865, "loss": 1.9752, "lr": 9.770930173177332e-07, "epoch": 1.4510444763836112, "percentage": 9.67, "elapsed_time": "2:29:25", "remaining_time": "23:15:11", "throughput": 8369.54, "total_tokens": 75034184} {"current_steps": 73800, "total_steps": 761865, "loss": 1.9799, "lr": 9.770312846715397e-07, "epoch": 1.4530133291331142, "percentage": 9.69, "elapsed_time": "2:29:37", "remaining_time": "23:14:59", "throughput": 8369.5, "total_tokens": 75135936} {"current_steps": 73900, "total_steps": 761865, "loss": 1.9754, "lr": 9.769694709101997e-07, "epoch": 1.454982181882617, "percentage": 9.7, "elapsed_time": "2:29:49", "remaining_time": "23:14:47", "throughput": 8369.44, "total_tokens": 75237440} {"current_steps": 74000, "total_steps": 761865, "loss": 1.9905, "lr": 9.76907576044224e-07, "epoch": 1.45695103463212, "percentage": 9.71, "elapsed_time": "2:30:01", "remaining_time": "23:14:34", "throughput": 8369.38, "total_tokens": 75338424} {"current_steps": 74100, "total_steps": 761865, "loss": 1.9839, "lr": 9.768456000841374e-07, "epoch": 1.4589198873816227, "percentage": 9.73, "elapsed_time": "2:30:13", "remaining_time": "23:14:23", "throughput": 8369.33, "total_tokens": 75440200} {"current_steps": 74200, "total_steps": 761865, "loss": 1.9775, "lr": 9.767835430404785e-07, "epoch": 1.4608887401311255, "percentage": 9.74, "elapsed_time": "2:30:26", "remaining_time": "23:14:11", "throughput": 8369.3, "total_tokens": 75542600} {"current_steps": 74300, "total_steps": 761865, "loss": 1.9546, "lr": 9.767214049237996e-07, "epoch": 1.4628575928806284, "percentage": 9.75, "elapsed_time": "2:30:38", "remaining_time": "23:14:00", "throughput": 8369.25, "total_tokens": 75644952} {"current_steps": 74400, "total_steps": 761865, "loss": 1.9341, "lr": 9.766591857446664e-07, "epoch": 1.4648264456301314, "percentage": 9.77, "elapsed_time": "2:30:50", "remaining_time": "23:13:49", "throughput": 8369.2, "total_tokens": 75747352} {"current_steps": 74500, "total_steps": 761865, "loss": 1.9894, "lr": 9.765968855136593e-07, "epoch": 1.4667952983796342, "percentage": 9.78, "elapsed_time": "2:31:02", "remaining_time": "23:13:38", "throughput": 8369.18, "total_tokens": 75849752} {"current_steps": 74600, "total_steps": 761865, "loss": 1.9596, "lr": 9.765345042413713e-07, "epoch": 1.468764151129137, "percentage": 9.79, "elapsed_time": "2:31:15", "remaining_time": "23:13:26", "throughput": 8369.12, "total_tokens": 75951408} {"current_steps": 74700, "total_steps": 761865, "loss": 2.0778, "lr": 9.764720419384102e-07, "epoch": 1.47073300387864, "percentage": 9.8, "elapsed_time": "2:31:27", "remaining_time": "23:13:14", "throughput": 8369.07, "total_tokens": 76052984} {"current_steps": 74800, "total_steps": 761865, "loss": 2.046, "lr": 9.764094986153972e-07, "epoch": 1.472701856628143, "percentage": 9.82, "elapsed_time": "2:31:39", "remaining_time": "23:13:03", "throughput": 8369.03, "total_tokens": 76155208} {"current_steps": 74900, "total_steps": 761865, "loss": 1.9592, "lr": 9.763468742829673e-07, "epoch": 1.4746707093776457, "percentage": 9.83, "elapsed_time": "2:31:51", "remaining_time": "23:12:52", "throughput": 8369.01, "total_tokens": 76257608} {"current_steps": 75000, "total_steps": 761865, "loss": 1.9825, "lr": 9.76284168951769e-07, "epoch": 1.4766395621271484, "percentage": 9.84, "elapsed_time": "2:32:04", "remaining_time": "23:12:40", "throughput": 8368.99, "total_tokens": 76360008} {"current_steps": 75100, "total_steps": 761865, "loss": 1.9805, "lr": 9.76221382632465e-07, "epoch": 1.4786084148766514, "percentage": 9.86, "elapsed_time": "2:32:16", "remaining_time": "23:12:33", "throughput": 8368.48, "total_tokens": 76461784} {"current_steps": 75200, "total_steps": 761865, "loss": 1.9806, "lr": 9.761585153357315e-07, "epoch": 1.4805772676261542, "percentage": 9.87, "elapsed_time": "2:32:29", "remaining_time": "23:12:22", "throughput": 8368.43, "total_tokens": 76563816} {"current_steps": 75300, "total_steps": 761865, "loss": 1.9819, "lr": 9.760955670722584e-07, "epoch": 1.4825461203756571, "percentage": 9.88, "elapsed_time": "2:32:41", "remaining_time": "23:12:10", "throughput": 8368.41, "total_tokens": 76666216} {"current_steps": 75400, "total_steps": 761865, "loss": 1.944, "lr": 9.760325378527498e-07, "epoch": 1.48451497312516, "percentage": 9.9, "elapsed_time": "2:32:53", "remaining_time": "23:11:59", "throughput": 8368.39, "total_tokens": 76768616} {"current_steps": 75500, "total_steps": 761865, "loss": 1.974, "lr": 9.759694276879233e-07, "epoch": 1.4864838258746629, "percentage": 9.91, "elapsed_time": "2:33:05", "remaining_time": "23:11:48", "throughput": 8368.36, "total_tokens": 76871016} {"current_steps": 75600, "total_steps": 761865, "loss": 2.0285, "lr": 9.7590623658851e-07, "epoch": 1.4884526786241656, "percentage": 9.92, "elapsed_time": "2:33:18", "remaining_time": "23:11:37", "throughput": 8368.33, "total_tokens": 76973416} {"current_steps": 75700, "total_steps": 761865, "loss": 1.9852, "lr": 9.758429645652552e-07, "epoch": 1.4904215313736686, "percentage": 9.94, "elapsed_time": "2:33:30", "remaining_time": "23:11:25", "throughput": 8368.23, "total_tokens": 77074376} {"current_steps": 75800, "total_steps": 761865, "loss": 1.9513, "lr": 9.757796116289176e-07, "epoch": 1.4923903841231714, "percentage": 9.95, "elapsed_time": "2:33:42", "remaining_time": "23:11:13", "throughput": 8368.17, "total_tokens": 77175984} {"current_steps": 75900, "total_steps": 761865, "loss": 1.9967, "lr": 9.757161777902703e-07, "epoch": 1.4943592368726744, "percentage": 9.96, "elapsed_time": "2:33:54", "remaining_time": "23:11:01", "throughput": 8368.12, "total_tokens": 77277296} {"current_steps": 76000, "total_steps": 761865, "loss": 2.0007, "lr": 9.75652663060099e-07, "epoch": 1.4963280896221771, "percentage": 9.98, "elapsed_time": "2:34:06", "remaining_time": "23:10:49", "throughput": 8368.08, "total_tokens": 77379448} {"current_steps": 76100, "total_steps": 761865, "loss": 2.004, "lr": 9.755890674492043e-07, "epoch": 1.49829694237168, "percentage": 9.99, "elapsed_time": "2:34:19", "remaining_time": "23:10:38", "throughput": 8368.01, "total_tokens": 77480992} {"current_steps": 76200, "total_steps": 761865, "loss": 2.0009, "lr": 9.755253909683999e-07, "epoch": 1.5002657951211829, "percentage": 10.0, "elapsed_time": "2:34:31", "remaining_time": "23:10:26", "throughput": 8367.98, "total_tokens": 77583392} {"current_steps": 76300, "total_steps": 761865, "loss": 1.973, "lr": 9.754616336285136e-07, "epoch": 1.5022346478706856, "percentage": 10.01, "elapsed_time": "2:34:43", "remaining_time": "23:10:14", "throughput": 8367.91, "total_tokens": 77684488} {"current_steps": 76400, "total_steps": 761865, "loss": 1.9916, "lr": 9.753977954403868e-07, "epoch": 1.5042035006201886, "percentage": 10.03, "elapsed_time": "2:34:55", "remaining_time": "23:10:01", "throughput": 8367.8, "total_tokens": 77785016} {"current_steps": 76500, "total_steps": 761865, "loss": 1.9824, "lr": 9.753338764148745e-07, "epoch": 1.5061723533696916, "percentage": 10.04, "elapsed_time": "2:35:08", "remaining_time": "23:09:50", "throughput": 8367.77, "total_tokens": 77887416} {"current_steps": 76600, "total_steps": 761865, "loss": 1.9843, "lr": 9.752698765628456e-07, "epoch": 1.5081412061191943, "percentage": 10.05, "elapsed_time": "2:35:20", "remaining_time": "23:09:39", "throughput": 8367.71, "total_tokens": 77989264} {"current_steps": 76700, "total_steps": 761865, "loss": 1.9854, "lr": 9.75205795895183e-07, "epoch": 1.510110058868697, "percentage": 10.07, "elapsed_time": "2:35:32", "remaining_time": "23:09:26", "throughput": 8367.66, "total_tokens": 78090520} {"current_steps": 76800, "total_steps": 761865, "loss": 1.9851, "lr": 9.751416344227828e-07, "epoch": 1.5120789116182, "percentage": 10.08, "elapsed_time": "2:35:44", "remaining_time": "23:09:15", "throughput": 8367.61, "total_tokens": 78192232} {"current_steps": 76900, "total_steps": 761865, "loss": 2.0401, "lr": 9.750773921565551e-07, "epoch": 1.514047764367703, "percentage": 10.09, "elapsed_time": "2:35:56", "remaining_time": "23:09:03", "throughput": 8367.6, "total_tokens": 78294632} {"current_steps": 77000, "total_steps": 761865, "loss": 1.9996, "lr": 9.75013069107424e-07, "epoch": 1.5160166171172058, "percentage": 10.11, "elapsed_time": "2:36:09", "remaining_time": "23:08:51", "throughput": 8367.55, "total_tokens": 78396368} {"current_steps": 77100, "total_steps": 761865, "loss": 1.9095, "lr": 9.749486652863268e-07, "epoch": 1.5179854698667086, "percentage": 10.12, "elapsed_time": "2:36:21", "remaining_time": "23:08:40", "throughput": 8367.5, "total_tokens": 78498216} {"current_steps": 77200, "total_steps": 761865, "loss": 2.0188, "lr": 9.74884180704215e-07, "epoch": 1.5199543226162116, "percentage": 10.13, "elapsed_time": "2:36:33", "remaining_time": "23:08:28", "throughput": 8367.43, "total_tokens": 78599792} {"current_steps": 77300, "total_steps": 761865, "loss": 2.0122, "lr": 9.748196153720536e-07, "epoch": 1.5219231753657145, "percentage": 10.15, "elapsed_time": "2:36:45", "remaining_time": "23:08:17", "throughput": 8367.41, "total_tokens": 78702192} {"current_steps": 77400, "total_steps": 761865, "loss": 1.9853, "lr": 9.747549693008214e-07, "epoch": 1.5238920281152173, "percentage": 10.16, "elapsed_time": "2:36:58", "remaining_time": "23:08:05", "throughput": 8367.39, "total_tokens": 78804592} {"current_steps": 77500, "total_steps": 761865, "loss": 2.0327, "lr": 9.746902425015112e-07, "epoch": 1.52586088086472, "percentage": 10.17, "elapsed_time": "2:37:10", "remaining_time": "23:07:53", "throughput": 8367.34, "total_tokens": 78906064} {"current_steps": 77600, "total_steps": 761865, "loss": 2.0012, "lr": 9.746254349851286e-07, "epoch": 1.527829733614223, "percentage": 10.19, "elapsed_time": "2:37:22", "remaining_time": "23:07:42", "throughput": 8367.31, "total_tokens": 79008024} {"current_steps": 77700, "total_steps": 761865, "loss": 2.0063, "lr": 9.745605467626943e-07, "epoch": 1.529798586363726, "percentage": 10.2, "elapsed_time": "2:37:34", "remaining_time": "23:07:30", "throughput": 8367.27, "total_tokens": 79110120} {"current_steps": 77800, "total_steps": 761865, "loss": 1.947, "lr": 9.744955778452414e-07, "epoch": 1.5317674391132288, "percentage": 10.21, "elapsed_time": "2:37:46", "remaining_time": "23:07:18", "throughput": 8367.24, "total_tokens": 79211944} {"current_steps": 77900, "total_steps": 761865, "loss": 1.9934, "lr": 9.744305282438177e-07, "epoch": 1.5337362918627315, "percentage": 10.22, "elapsed_time": "2:37:59", "remaining_time": "23:07:06", "throughput": 8367.14, "total_tokens": 79312744} {"current_steps": 78000, "total_steps": 761865, "loss": 1.9765, "lr": 9.743653979694841e-07, "epoch": 1.5357051446122343, "percentage": 10.24, "elapsed_time": "2:38:11", "remaining_time": "23:06:55", "throughput": 8367.11, "total_tokens": 79415144} {"current_steps": 78100, "total_steps": 761865, "loss": 2.0687, "lr": 9.743001870333156e-07, "epoch": 1.5376739973617373, "percentage": 10.25, "elapsed_time": "2:38:23", "remaining_time": "23:06:43", "throughput": 8367.07, "total_tokens": 79517256} {"current_steps": 78200, "total_steps": 761865, "loss": 1.9899, "lr": 9.742348954464007e-07, "epoch": 1.5396428501112402, "percentage": 10.26, "elapsed_time": "2:38:35", "remaining_time": "23:06:32", "throughput": 8367.03, "total_tokens": 79619112} {"current_steps": 78300, "total_steps": 761865, "loss": 1.9849, "lr": 9.74169523219842e-07, "epoch": 1.541611702860743, "percentage": 10.28, "elapsed_time": "2:38:48", "remaining_time": "23:06:20", "throughput": 8366.99, "total_tokens": 79720952} {"current_steps": 78400, "total_steps": 761865, "loss": 1.9927, "lr": 9.74104070364755e-07, "epoch": 1.5435805556102458, "percentage": 10.29, "elapsed_time": "2:39:00", "remaining_time": "23:06:08", "throughput": 8366.88, "total_tokens": 79821640} {"current_steps": 78500, "total_steps": 761865, "loss": 1.9666, "lr": 9.740385368922695e-07, "epoch": 1.5455494083597487, "percentage": 10.3, "elapsed_time": "2:39:12", "remaining_time": "23:05:56", "throughput": 8366.87, "total_tokens": 79924040} {"current_steps": 78600, "total_steps": 761865, "loss": 1.9533, "lr": 9.739729228135291e-07, "epoch": 1.5475182611092517, "percentage": 10.32, "elapsed_time": "2:39:24", "remaining_time": "23:05:45", "throughput": 8366.85, "total_tokens": 80026440} {"current_steps": 78700, "total_steps": 761865, "loss": 1.9791, "lr": 9.739072281396908e-07, "epoch": 1.5494871138587545, "percentage": 10.33, "elapsed_time": "2:39:36", "remaining_time": "23:05:33", "throughput": 8366.83, "total_tokens": 80128840} {"current_steps": 78800, "total_steps": 761865, "loss": 2.0118, "lr": 9.738414528819257e-07, "epoch": 1.5514559666082572, "percentage": 10.34, "elapsed_time": "2:39:49", "remaining_time": "23:05:21", "throughput": 8366.75, "total_tokens": 80229680} {"current_steps": 78900, "total_steps": 761865, "loss": 1.9749, "lr": 9.737755970514179e-07, "epoch": 1.5534248193577602, "percentage": 10.36, "elapsed_time": "2:40:01", "remaining_time": "23:05:09", "throughput": 8366.7, "total_tokens": 80331384} {"current_steps": 79000, "total_steps": 761865, "loss": 1.9282, "lr": 9.737096606593658e-07, "epoch": 1.5553936721072632, "percentage": 10.37, "elapsed_time": "2:40:13", "remaining_time": "23:04:58", "throughput": 8366.68, "total_tokens": 80433784} {"current_steps": 79100, "total_steps": 761865, "loss": 2.0078, "lr": 9.736436437169813e-07, "epoch": 1.557362524856766, "percentage": 10.38, "elapsed_time": "2:40:25", "remaining_time": "23:04:46", "throughput": 8366.63, "total_tokens": 80535416} {"current_steps": 79200, "total_steps": 761865, "loss": 2.0361, "lr": 9.735775462354904e-07, "epoch": 1.5593313776062687, "percentage": 10.4, "elapsed_time": "2:40:38", "remaining_time": "23:04:35", "throughput": 8366.59, "total_tokens": 80637360} {"current_steps": 79300, "total_steps": 761865, "loss": 1.9458, "lr": 9.735113682261318e-07, "epoch": 1.5613002303557717, "percentage": 10.41, "elapsed_time": "2:40:50", "remaining_time": "23:04:23", "throughput": 8366.56, "total_tokens": 80739160} {"current_steps": 79400, "total_steps": 761865, "loss": 2.0063, "lr": 9.734451097001588e-07, "epoch": 1.5632690831052747, "percentage": 10.42, "elapsed_time": "2:41:02", "remaining_time": "23:04:10", "throughput": 8366.52, "total_tokens": 80840392} {"current_steps": 79500, "total_steps": 761865, "loss": 1.9894, "lr": 9.733787706688383e-07, "epoch": 1.5652379358547774, "percentage": 10.43, "elapsed_time": "2:41:14", "remaining_time": "23:03:59", "throughput": 8366.5, "total_tokens": 80942792} {"current_steps": 79600, "total_steps": 761865, "loss": 2.0121, "lr": 9.733123511434504e-07, "epoch": 1.5672067886042802, "percentage": 10.45, "elapsed_time": "2:41:26", "remaining_time": "23:03:47", "throughput": 8366.47, "total_tokens": 81044760} {"current_steps": 79700, "total_steps": 761865, "loss": 2.0458, "lr": 9.732458511352894e-07, "epoch": 1.5691756413537832, "percentage": 10.46, "elapsed_time": "2:41:39", "remaining_time": "23:03:35", "throughput": 8366.41, "total_tokens": 81146360} {"current_steps": 79800, "total_steps": 761865, "loss": 1.9348, "lr": 9.73179270655663e-07, "epoch": 1.5711444941032862, "percentage": 10.47, "elapsed_time": "2:41:51", "remaining_time": "23:03:24", "throughput": 8366.39, "total_tokens": 81248760} {"current_steps": 79900, "total_steps": 761865, "loss": 1.9619, "lr": 9.731126097158923e-07, "epoch": 1.573113346852789, "percentage": 10.49, "elapsed_time": "2:42:03", "remaining_time": "23:03:13", "throughput": 8366.36, "total_tokens": 81351160} {"current_steps": 80000, "total_steps": 761865, "loss": 2.0226, "lr": 9.73045868327313e-07, "epoch": 1.5750821996022917, "percentage": 10.5, "elapsed_time": "2:42:15", "remaining_time": "23:03:01", "throughput": 8366.31, "total_tokens": 81452800} {"current_steps": 80100, "total_steps": 761865, "loss": 1.9838, "lr": 9.729790465012735e-07, "epoch": 1.5770510523517947, "percentage": 10.51, "elapsed_time": "2:42:28", "remaining_time": "23:02:54", "throughput": 8365.77, "total_tokens": 81554072} {"current_steps": 80200, "total_steps": 761865, "loss": 1.9746, "lr": 9.729121442491366e-07, "epoch": 1.5790199051012976, "percentage": 10.53, "elapsed_time": "2:42:40", "remaining_time": "23:02:42", "throughput": 8365.73, "total_tokens": 81656472} {"current_steps": 80300, "total_steps": 761865, "loss": 1.9403, "lr": 9.728451615822782e-07, "epoch": 1.5809887578508004, "percentage": 10.54, "elapsed_time": "2:42:53", "remaining_time": "23:02:31", "throughput": 8365.69, "total_tokens": 81758424} {"current_steps": 80400, "total_steps": 761865, "loss": 1.9945, "lr": 9.727780985120882e-07, "epoch": 1.5829576106003032, "percentage": 10.55, "elapsed_time": "2:43:05", "remaining_time": "23:02:19", "throughput": 8365.67, "total_tokens": 81860824} {"current_steps": 80500, "total_steps": 761865, "loss": 2.0118, "lr": 9.727109550499701e-07, "epoch": 1.584926463349806, "percentage": 10.57, "elapsed_time": "2:43:17", "remaining_time": "23:02:08", "throughput": 8365.64, "total_tokens": 81962864} {"current_steps": 80600, "total_steps": 761865, "loss": 2.0029, "lr": 9.726437312073413e-07, "epoch": 1.586895316099309, "percentage": 10.58, "elapsed_time": "2:43:29", "remaining_time": "23:01:56", "throughput": 8365.62, "total_tokens": 82065264} {"current_steps": 80700, "total_steps": 761865, "loss": 2.0214, "lr": 9.725764269956322e-07, "epoch": 1.5888641688488119, "percentage": 10.59, "elapsed_time": "2:43:42", "remaining_time": "23:01:44", "throughput": 8365.57, "total_tokens": 82166888} {"current_steps": 80800, "total_steps": 761865, "loss": 2.0482, "lr": 9.725090424262877e-07, "epoch": 1.5908330215983146, "percentage": 10.61, "elapsed_time": "2:43:54", "remaining_time": "23:01:32", "throughput": 8365.5, "total_tokens": 82268104} {"current_steps": 80900, "total_steps": 761865, "loss": 1.9227, "lr": 9.72441577510766e-07, "epoch": 1.5928018743478174, "percentage": 10.62, "elapsed_time": "2:44:06", "remaining_time": "23:01:21", "throughput": 8365.48, "total_tokens": 82370504} {"current_steps": 81000, "total_steps": 761865, "loss": 1.9769, "lr": 9.723740322605387e-07, "epoch": 1.5947707270973204, "percentage": 10.63, "elapsed_time": "2:44:18", "remaining_time": "23:01:10", "throughput": 8365.46, "total_tokens": 82472904} {"current_steps": 81100, "total_steps": 761865, "loss": 1.9725, "lr": 9.723064066870915e-07, "epoch": 1.5967395798468234, "percentage": 10.64, "elapsed_time": "2:44:31", "remaining_time": "23:00:58", "throughput": 8365.44, "total_tokens": 82575304} {"current_steps": 81200, "total_steps": 761865, "loss": 1.9381, "lr": 9.722387008019233e-07, "epoch": 1.5987084325963261, "percentage": 10.66, "elapsed_time": "2:44:43", "remaining_time": "23:00:46", "throughput": 8365.4, "total_tokens": 82677088} {"current_steps": 81300, "total_steps": 761865, "loss": 2.0336, "lr": 9.721709146165472e-07, "epoch": 1.6006772853458289, "percentage": 10.67, "elapsed_time": "2:44:55", "remaining_time": "23:00:34", "throughput": 8365.37, "total_tokens": 82778960} {"current_steps": 81400, "total_steps": 761865, "loss": 1.9552, "lr": 9.721030481424894e-07, "epoch": 1.6026461380953319, "percentage": 10.68, "elapsed_time": "2:45:07", "remaining_time": "23:00:23", "throughput": 8365.34, "total_tokens": 82881360} {"current_steps": 81500, "total_steps": 761865, "loss": 1.9766, "lr": 9.720351013912904e-07, "epoch": 1.6046149908448348, "percentage": 10.7, "elapsed_time": "2:45:19", "remaining_time": "23:00:11", "throughput": 8365.31, "total_tokens": 82983016} {"current_steps": 81600, "total_steps": 761865, "loss": 2.0009, "lr": 9.719670743745035e-07, "epoch": 1.6065838435943376, "percentage": 10.71, "elapsed_time": "2:45:32", "remaining_time": "22:59:59", "throughput": 8365.25, "total_tokens": 83084648} {"current_steps": 81700, "total_steps": 761865, "loss": 2.0358, "lr": 9.718989671036964e-07, "epoch": 1.6085526963438403, "percentage": 10.72, "elapsed_time": "2:45:44", "remaining_time": "22:59:47", "throughput": 8365.12, "total_tokens": 83184536} {"current_steps": 81800, "total_steps": 761865, "loss": 1.9746, "lr": 9.7183077959045e-07, "epoch": 1.6105215490933433, "percentage": 10.74, "elapsed_time": "2:45:56", "remaining_time": "22:59:34", "throughput": 8365.07, "total_tokens": 83285576} {"current_steps": 81900, "total_steps": 761865, "loss": 2.0006, "lr": 9.717625118463596e-07, "epoch": 1.6124904018428463, "percentage": 10.75, "elapsed_time": "2:46:08", "remaining_time": "22:59:23", "throughput": 8365.03, "total_tokens": 83387664} {"current_steps": 82000, "total_steps": 761865, "loss": 1.9574, "lr": 9.716941638830327e-07, "epoch": 1.614459254592349, "percentage": 10.76, "elapsed_time": "2:46:20", "remaining_time": "22:59:11", "throughput": 8364.99, "total_tokens": 83489336} {"current_steps": 82100, "total_steps": 761865, "loss": 1.985, "lr": 9.716257357120917e-07, "epoch": 1.6164281073418518, "percentage": 10.78, "elapsed_time": "2:46:32", "remaining_time": "22:58:58", "throughput": 8364.89, "total_tokens": 83589680} {"current_steps": 82200, "total_steps": 761865, "loss": 1.9733, "lr": 9.715572273451724e-07, "epoch": 1.6183969600913548, "percentage": 10.79, "elapsed_time": "2:46:45", "remaining_time": "22:58:47", "throughput": 8364.87, "total_tokens": 83692080} {"current_steps": 82300, "total_steps": 761865, "loss": 1.9695, "lr": 9.714886387939236e-07, "epoch": 1.6203658128408578, "percentage": 10.8, "elapsed_time": "2:46:57", "remaining_time": "22:58:34", "throughput": 8364.81, "total_tokens": 83793120} {"current_steps": 82400, "total_steps": 761865, "loss": 1.9293, "lr": 9.714199700700087e-07, "epoch": 1.6223346655903605, "percentage": 10.82, "elapsed_time": "2:47:09", "remaining_time": "22:58:23", "throughput": 8364.77, "total_tokens": 83894968} {"current_steps": 82500, "total_steps": 761865, "loss": 1.9694, "lr": 9.713512211851041e-07, "epoch": 1.6243035183398633, "percentage": 10.83, "elapsed_time": "2:47:21", "remaining_time": "22:58:11", "throughput": 8364.71, "total_tokens": 83996896} {"current_steps": 82600, "total_steps": 761865, "loss": 2.0562, "lr": 9.712823921508998e-07, "epoch": 1.626272371089366, "percentage": 10.84, "elapsed_time": "2:47:33", "remaining_time": "22:57:58", "throughput": 8364.58, "total_tokens": 84096456} {"current_steps": 82700, "total_steps": 761865, "loss": 1.9984, "lr": 9.712134829790997e-07, "epoch": 1.628241223838869, "percentage": 10.85, "elapsed_time": "2:47:46", "remaining_time": "22:57:47", "throughput": 8364.55, "total_tokens": 84198856} {"current_steps": 82800, "total_steps": 761865, "loss": 1.9305, "lr": 9.711444936814211e-07, "epoch": 1.630210076588372, "percentage": 10.87, "elapsed_time": "2:47:58", "remaining_time": "22:57:35", "throughput": 8364.5, "total_tokens": 84300632} {"current_steps": 82900, "total_steps": 761865, "loss": 1.9551, "lr": 9.710754242695952e-07, "epoch": 1.6321789293378748, "percentage": 10.88, "elapsed_time": "2:48:10", "remaining_time": "22:57:23", "throughput": 8364.46, "total_tokens": 84402584} {"current_steps": 83000, "total_steps": 761865, "loss": 1.9489, "lr": 9.710062747553668e-07, "epoch": 1.6341477820873775, "percentage": 10.89, "elapsed_time": "2:48:22", "remaining_time": "22:57:12", "throughput": 8364.44, "total_tokens": 84504984} {"current_steps": 83100, "total_steps": 761865, "loss": 1.9794, "lr": 9.70937045150494e-07, "epoch": 1.6361166348368805, "percentage": 10.91, "elapsed_time": "2:48:35", "remaining_time": "22:57:00", "throughput": 8364.4, "total_tokens": 84606920} {"current_steps": 83200, "total_steps": 761865, "loss": 2.0041, "lr": 9.708677354667487e-07, "epoch": 1.6380854875863835, "percentage": 10.92, "elapsed_time": "2:48:47", "remaining_time": "22:56:48", "throughput": 8364.36, "total_tokens": 84708232} {"current_steps": 83300, "total_steps": 761865, "loss": 2.0034, "lr": 9.707983457159164e-07, "epoch": 1.6400543403358863, "percentage": 10.93, "elapsed_time": "2:48:59", "remaining_time": "22:56:36", "throughput": 8364.3, "total_tokens": 84809944} {"current_steps": 83400, "total_steps": 761865, "loss": 2.0143, "lr": 9.707288759097963e-07, "epoch": 1.642023193085389, "percentage": 10.95, "elapsed_time": "2:49:11", "remaining_time": "22:56:24", "throughput": 8364.24, "total_tokens": 84911480} {"current_steps": 83500, "total_steps": 761865, "loss": 1.9945, "lr": 9.70659326060201e-07, "epoch": 1.643992045834892, "percentage": 10.96, "elapsed_time": "2:49:23", "remaining_time": "22:56:13", "throughput": 8364.19, "total_tokens": 85013152} {"current_steps": 83600, "total_steps": 761865, "loss": 1.9712, "lr": 9.705896961789575e-07, "epoch": 1.645960898584395, "percentage": 10.97, "elapsed_time": "2:49:36", "remaining_time": "22:56:01", "throughput": 8364.17, "total_tokens": 85115552} {"current_steps": 83700, "total_steps": 761865, "loss": 2.0293, "lr": 9.70519986277905e-07, "epoch": 1.6479297513338977, "percentage": 10.99, "elapsed_time": "2:49:48", "remaining_time": "22:55:49", "throughput": 8364.13, "total_tokens": 85217256} {"current_steps": 83800, "total_steps": 761865, "loss": 1.978, "lr": 9.704501963688973e-07, "epoch": 1.6498986040834005, "percentage": 11.0, "elapsed_time": "2:50:00", "remaining_time": "22:55:38", "throughput": 8364.1, "total_tokens": 85319104} {"current_steps": 83900, "total_steps": 761865, "loss": 2.0701, "lr": 9.703803264638018e-07, "epoch": 1.6518674568329035, "percentage": 11.01, "elapsed_time": "2:50:12", "remaining_time": "22:55:26", "throughput": 8364.07, "total_tokens": 85421296} {"current_steps": 84000, "total_steps": 761865, "loss": 1.9357, "lr": 9.703103765744992e-07, "epoch": 1.6538363095824065, "percentage": 11.03, "elapsed_time": "2:50:25", "remaining_time": "22:55:14", "throughput": 8364.04, "total_tokens": 85523144} {"current_steps": 84100, "total_steps": 761865, "loss": 2.0163, "lr": 9.702403467128838e-07, "epoch": 1.6558051623319092, "percentage": 11.04, "elapsed_time": "2:50:37", "remaining_time": "22:55:02", "throughput": 8363.95, "total_tokens": 85623960} {"current_steps": 84200, "total_steps": 761865, "loss": 2.0152, "lr": 9.701702368908636e-07, "epoch": 1.657774015081412, "percentage": 11.05, "elapsed_time": "2:50:49", "remaining_time": "22:54:50", "throughput": 8363.92, "total_tokens": 85725696} {"current_steps": 84300, "total_steps": 761865, "loss": 1.9914, "lr": 9.7010004712036e-07, "epoch": 1.659742867830915, "percentage": 11.06, "elapsed_time": "2:51:01", "remaining_time": "22:54:39", "throughput": 8363.9, "total_tokens": 85828096} {"current_steps": 84400, "total_steps": 761865, "loss": 2.0373, "lr": 9.700297774133088e-07, "epoch": 1.661711720580418, "percentage": 11.08, "elapsed_time": "2:51:13", "remaining_time": "22:54:26", "throughput": 8363.82, "total_tokens": 85928912} {"current_steps": 84500, "total_steps": 761865, "loss": 2.0367, "lr": 9.699594277816582e-07, "epoch": 1.6636805733299207, "percentage": 11.09, "elapsed_time": "2:51:26", "remaining_time": "22:54:15", "throughput": 8363.8, "total_tokens": 86031312} {"current_steps": 84600, "total_steps": 761865, "loss": 1.9781, "lr": 9.698889982373707e-07, "epoch": 1.6656494260794235, "percentage": 11.1, "elapsed_time": "2:51:38", "remaining_time": "22:54:03", "throughput": 8363.78, "total_tokens": 86133192} {"current_steps": 84700, "total_steps": 761865, "loss": 2.015, "lr": 9.698184887924224e-07, "epoch": 1.6676182788289264, "percentage": 11.12, "elapsed_time": "2:51:50", "remaining_time": "22:53:50", "throughput": 8363.66, "total_tokens": 86233248} {"current_steps": 84800, "total_steps": 761865, "loss": 2.0173, "lr": 9.697478994588026e-07, "epoch": 1.6695871315784292, "percentage": 11.13, "elapsed_time": "2:52:02", "remaining_time": "22:53:39", "throughput": 8363.63, "total_tokens": 86335648} {"current_steps": 84900, "total_steps": 761865, "loss": 1.9713, "lr": 9.696772302485146e-07, "epoch": 1.6715559843279322, "percentage": 11.14, "elapsed_time": "2:52:15", "remaining_time": "22:53:28", "throughput": 8363.61, "total_tokens": 86438048} {"current_steps": 85000, "total_steps": 761865, "loss": 1.9183, "lr": 9.69606481173575e-07, "epoch": 1.673524837077435, "percentage": 11.16, "elapsed_time": "2:52:27", "remaining_time": "22:53:16", "throughput": 8363.58, "total_tokens": 86539944} {"current_steps": 85100, "total_steps": 761865, "loss": 1.9736, "lr": 9.69535652246014e-07, "epoch": 1.6754936898269377, "percentage": 11.17, "elapsed_time": "2:52:40", "remaining_time": "22:53:09", "throughput": 8363.13, "total_tokens": 86642344} {"current_steps": 85200, "total_steps": 761865, "loss": 1.9544, "lr": 9.694647434778758e-07, "epoch": 1.6774625425764407, "percentage": 11.18, "elapsed_time": "2:52:52", "remaining_time": "22:52:57", "throughput": 8363.07, "total_tokens": 86744064} {"current_steps": 85300, "total_steps": 761865, "loss": 1.9852, "lr": 9.693937548812175e-07, "epoch": 1.6794313953259437, "percentage": 11.2, "elapsed_time": "2:53:04", "remaining_time": "22:52:45", "throughput": 8363.05, "total_tokens": 86846464} {"current_steps": 85400, "total_steps": 761865, "loss": 1.9742, "lr": 9.693226864681101e-07, "epoch": 1.6814002480754464, "percentage": 11.21, "elapsed_time": "2:53:16", "remaining_time": "22:52:34", "throughput": 8363.03, "total_tokens": 86948360} {"current_steps": 85500, "total_steps": 761865, "loss": 1.9824, "lr": 9.692515382506385e-07, "epoch": 1.6833691008249492, "percentage": 11.22, "elapsed_time": "2:53:28", "remaining_time": "22:52:22", "throughput": 8362.99, "total_tokens": 87050168} {"current_steps": 85600, "total_steps": 761865, "loss": 1.9663, "lr": 9.691803102409007e-07, "epoch": 1.6853379535744522, "percentage": 11.24, "elapsed_time": "2:53:41", "remaining_time": "22:52:10", "throughput": 8362.97, "total_tokens": 87152568} {"current_steps": 85700, "total_steps": 761865, "loss": 2.0377, "lr": 9.691090024510082e-07, "epoch": 1.6873068063239551, "percentage": 11.25, "elapsed_time": "2:53:53", "remaining_time": "22:51:58", "throughput": 8362.91, "total_tokens": 87253352} {"current_steps": 85800, "total_steps": 761865, "loss": 1.9643, "lr": 9.690376148930866e-07, "epoch": 1.689275659073458, "percentage": 11.26, "elapsed_time": "2:54:05", "remaining_time": "22:51:46", "throughput": 8362.85, "total_tokens": 87354512} {"current_steps": 85900, "total_steps": 761865, "loss": 1.9621, "lr": 9.689661475792747e-07, "epoch": 1.6912445118229606, "percentage": 11.27, "elapsed_time": "2:54:17", "remaining_time": "22:51:34", "throughput": 8362.78, "total_tokens": 87455960} {"current_steps": 86000, "total_steps": 761865, "loss": 2.0407, "lr": 9.688946005217247e-07, "epoch": 1.6932133645724636, "percentage": 11.29, "elapsed_time": "2:54:29", "remaining_time": "22:51:21", "throughput": 8362.69, "total_tokens": 87556448} {"current_steps": 86100, "total_steps": 761865, "loss": 2.0029, "lr": 9.688229737326028e-07, "epoch": 1.6951822173219666, "percentage": 11.3, "elapsed_time": "2:54:42", "remaining_time": "22:51:09", "throughput": 8362.65, "total_tokens": 87658168} {"current_steps": 86200, "total_steps": 761865, "loss": 2.0032, "lr": 9.687512672240886e-07, "epoch": 1.6971510700714694, "percentage": 11.31, "elapsed_time": "2:54:54", "remaining_time": "22:50:57", "throughput": 8362.56, "total_tokens": 87759112} {"current_steps": 86300, "total_steps": 761865, "loss": 1.9832, "lr": 9.686794810083748e-07, "epoch": 1.6991199228209721, "percentage": 11.33, "elapsed_time": "2:55:06", "remaining_time": "22:50:46", "throughput": 8362.55, "total_tokens": 87861512} {"current_steps": 86400, "total_steps": 761865, "loss": 1.9768, "lr": 9.686076150976683e-07, "epoch": 1.701088775570475, "percentage": 11.34, "elapsed_time": "2:55:18", "remaining_time": "22:50:33", "throughput": 8362.43, "total_tokens": 87961408} {"current_steps": 86500, "total_steps": 761865, "loss": 1.9896, "lr": 9.685356695041894e-07, "epoch": 1.703057628319978, "percentage": 11.35, "elapsed_time": "2:55:30", "remaining_time": "22:50:21", "throughput": 8362.34, "total_tokens": 88062232} {"current_steps": 86600, "total_steps": 761865, "loss": 2.0618, "lr": 9.684636442401717e-07, "epoch": 1.7050264810694808, "percentage": 11.37, "elapsed_time": "2:55:42", "remaining_time": "22:50:08", "throughput": 8362.25, "total_tokens": 88162504} {"current_steps": 86700, "total_steps": 761865, "loss": 2.0026, "lr": 9.683915393178623e-07, "epoch": 1.7069953338189836, "percentage": 11.38, "elapsed_time": "2:55:55", "remaining_time": "22:49:56", "throughput": 8362.25, "total_tokens": 88264904} {"current_steps": 86800, "total_steps": 761865, "loss": 1.9409, "lr": 9.683193547495225e-07, "epoch": 1.7089641865684866, "percentage": 11.39, "elapsed_time": "2:56:07", "remaining_time": "22:49:45", "throughput": 8362.23, "total_tokens": 88367304} {"current_steps": 86900, "total_steps": 761865, "loss": 1.9363, "lr": 9.682470905474262e-07, "epoch": 1.7109330393179896, "percentage": 11.41, "elapsed_time": "2:56:19", "remaining_time": "22:49:34", "throughput": 8362.22, "total_tokens": 88469704} {"current_steps": 87000, "total_steps": 761865, "loss": 2.0092, "lr": 9.681747467238616e-07, "epoch": 1.7129018920674923, "percentage": 11.42, "elapsed_time": "2:56:31", "remaining_time": "22:49:21", "throughput": 8362.16, "total_tokens": 88570816} {"current_steps": 87100, "total_steps": 761865, "loss": 2.0043, "lr": 9.681023232911303e-07, "epoch": 1.714870744816995, "percentage": 11.43, "elapsed_time": "2:56:44", "remaining_time": "22:49:10", "throughput": 8362.14, "total_tokens": 88673216} {"current_steps": 87200, "total_steps": 761865, "loss": 1.9723, "lr": 9.680298202615469e-07, "epoch": 1.7168395975664978, "percentage": 11.45, "elapsed_time": "2:56:56", "remaining_time": "22:48:58", "throughput": 8362.13, "total_tokens": 88775616} {"current_steps": 87300, "total_steps": 761865, "loss": 2.0005, "lr": 9.6795723764744e-07, "epoch": 1.7188084503160008, "percentage": 11.46, "elapsed_time": "2:57:08", "remaining_time": "22:48:47", "throughput": 8362.09, "total_tokens": 88878016} {"current_steps": 87400, "total_steps": 761865, "loss": 1.9812, "lr": 9.67884575461152e-07, "epoch": 1.7207773030655038, "percentage": 11.47, "elapsed_time": "2:57:20", "remaining_time": "22:48:35", "throughput": 8362.06, "total_tokens": 88979880} {"current_steps": 87500, "total_steps": 761865, "loss": 1.9936, "lr": 9.67811833715038e-07, "epoch": 1.7227461558150066, "percentage": 11.48, "elapsed_time": "2:57:33", "remaining_time": "22:48:23", "throughput": 8361.94, "total_tokens": 89080840} {"current_steps": 87600, "total_steps": 761865, "loss": 1.9728, "lr": 9.677390124214676e-07, "epoch": 1.7247150085645093, "percentage": 11.5, "elapsed_time": "2:57:45", "remaining_time": "22:48:11", "throughput": 8361.87, "total_tokens": 89181928} {"current_steps": 87700, "total_steps": 761865, "loss": 2.0041, "lr": 9.676661115928232e-07, "epoch": 1.7266838613140123, "percentage": 11.51, "elapsed_time": "2:57:57", "remaining_time": "22:48:00", "throughput": 8361.85, "total_tokens": 89284328} {"current_steps": 87800, "total_steps": 761865, "loss": 2.0008, "lr": 9.67593131241501e-07, "epoch": 1.7286527140635153, "percentage": 11.52, "elapsed_time": "2:58:09", "remaining_time": "22:47:48", "throughput": 8361.82, "total_tokens": 89386432} {"current_steps": 87900, "total_steps": 761865, "loss": 1.9439, "lr": 9.675200713799105e-07, "epoch": 1.730621566813018, "percentage": 11.54, "elapsed_time": "2:58:22", "remaining_time": "22:47:37", "throughput": 8361.81, "total_tokens": 89488832} {"current_steps": 88000, "total_steps": 761865, "loss": 1.9409, "lr": 9.674469320204754e-07, "epoch": 1.7325904195625208, "percentage": 11.55, "elapsed_time": "2:58:34", "remaining_time": "22:47:25", "throughput": 8361.76, "total_tokens": 89590416} {"current_steps": 88100, "total_steps": 761865, "loss": 1.9803, "lr": 9.67373713175632e-07, "epoch": 1.7345592723120238, "percentage": 11.56, "elapsed_time": "2:58:46", "remaining_time": "22:47:13", "throughput": 8361.67, "total_tokens": 89691896} {"current_steps": 88200, "total_steps": 761865, "loss": 1.9907, "lr": 9.673004148578308e-07, "epoch": 1.7365281250615268, "percentage": 11.58, "elapsed_time": "2:58:58", "remaining_time": "22:47:01", "throughput": 8361.59, "total_tokens": 89792872} {"current_steps": 88300, "total_steps": 761865, "loss": 1.9816, "lr": 9.672270370795353e-07, "epoch": 1.7384969778110295, "percentage": 11.59, "elapsed_time": "2:59:10", "remaining_time": "22:46:49", "throughput": 8361.56, "total_tokens": 89894496} {"current_steps": 88400, "total_steps": 761865, "loss": 2.0191, "lr": 9.67153579853223e-07, "epoch": 1.7404658305605323, "percentage": 11.6, "elapsed_time": "2:59:23", "remaining_time": "22:46:38", "throughput": 8361.55, "total_tokens": 89996896} {"current_steps": 88500, "total_steps": 761865, "loss": 1.9791, "lr": 9.670800431913843e-07, "epoch": 1.7424346833100353, "percentage": 11.62, "elapsed_time": "2:59:35", "remaining_time": "22:46:25", "throughput": 8361.49, "total_tokens": 90097968} {"current_steps": 88600, "total_steps": 761865, "loss": 1.9712, "lr": 9.67006427106524e-07, "epoch": 1.7444035360595382, "percentage": 11.63, "elapsed_time": "2:59:47", "remaining_time": "22:46:13", "throughput": 8361.44, "total_tokens": 90199632} {"current_steps": 88700, "total_steps": 761865, "loss": 2.022, "lr": 9.6693273161116e-07, "epoch": 1.746372388809041, "percentage": 11.64, "elapsed_time": "2:59:59", "remaining_time": "22:46:02", "throughput": 8361.43, "total_tokens": 90302032} {"current_steps": 88800, "total_steps": 761865, "loss": 1.9656, "lr": 9.66858956717823e-07, "epoch": 1.7483412415585438, "percentage": 11.66, "elapsed_time": "3:00:12", "remaining_time": "22:45:50", "throughput": 8361.42, "total_tokens": 90404432} {"current_steps": 88900, "total_steps": 761865, "loss": 1.9988, "lr": 9.66785102439058e-07, "epoch": 1.7503100943080467, "percentage": 11.67, "elapsed_time": "3:00:24", "remaining_time": "22:45:39", "throughput": 8361.4, "total_tokens": 90506832} {"current_steps": 89000, "total_steps": 761865, "loss": 2.0029, "lr": 9.667111687874235e-07, "epoch": 1.7522789470575497, "percentage": 11.68, "elapsed_time": "3:00:36", "remaining_time": "22:45:27", "throughput": 8361.34, "total_tokens": 90608080} {"current_steps": 89100, "total_steps": 761865, "loss": 1.9678, "lr": 9.66637155775491e-07, "epoch": 1.7542477998070525, "percentage": 11.69, "elapsed_time": "3:00:48", "remaining_time": "22:45:15", "throughput": 8361.32, "total_tokens": 90710480} {"current_steps": 89200, "total_steps": 761865, "loss": 1.9458, "lr": 9.665630634158463e-07, "epoch": 1.7562166525565552, "percentage": 11.71, "elapsed_time": "3:01:01", "remaining_time": "22:45:04", "throughput": 8361.3, "total_tokens": 90812880} {"current_steps": 89300, "total_steps": 761865, "loss": 2.0069, "lr": 9.664888917210876e-07, "epoch": 1.758185505306058, "percentage": 11.72, "elapsed_time": "3:01:13", "remaining_time": "22:44:52", "throughput": 8361.26, "total_tokens": 90914512} {"current_steps": 89400, "total_steps": 761865, "loss": 2.0099, "lr": 9.664146407038276e-07, "epoch": 1.760154358055561, "percentage": 11.73, "elapsed_time": "3:01:25", "remaining_time": "22:44:40", "throughput": 8361.25, "total_tokens": 91016912} {"current_steps": 89500, "total_steps": 761865, "loss": 1.9936, "lr": 9.663403103766915e-07, "epoch": 1.762123210805064, "percentage": 11.75, "elapsed_time": "3:01:37", "remaining_time": "22:44:29", "throughput": 8361.19, "total_tokens": 91118384} {"current_steps": 89600, "total_steps": 761865, "loss": 1.9865, "lr": 9.662659007523194e-07, "epoch": 1.7640920635545667, "percentage": 11.76, "elapsed_time": "3:01:49", "remaining_time": "22:44:17", "throughput": 8361.13, "total_tokens": 91219864} {"current_steps": 89700, "total_steps": 761865, "loss": 1.9887, "lr": 9.661914118433632e-07, "epoch": 1.7660609163040695, "percentage": 11.77, "elapsed_time": "3:02:02", "remaining_time": "22:44:05", "throughput": 8361.12, "total_tokens": 91322264} {"current_steps": 89800, "total_steps": 761865, "loss": 1.9671, "lr": 9.661168436624896e-07, "epoch": 1.7680297690535725, "percentage": 11.79, "elapsed_time": "3:02:14", "remaining_time": "22:43:53", "throughput": 8361.06, "total_tokens": 91423704} {"current_steps": 89900, "total_steps": 761865, "loss": 1.9824, "lr": 9.66042196222378e-07, "epoch": 1.7699986218030754, "percentage": 11.8, "elapsed_time": "3:02:26", "remaining_time": "22:43:41", "throughput": 8361.02, "total_tokens": 91525368} {"current_steps": 90000, "total_steps": 761865, "loss": 1.9883, "lr": 9.659674695357219e-07, "epoch": 1.7719674745525782, "percentage": 11.81, "elapsed_time": "3:02:38", "remaining_time": "22:43:29", "throughput": 8360.97, "total_tokens": 91626848} {"current_steps": 90100, "total_steps": 761865, "loss": 1.984, "lr": 9.658926636152277e-07, "epoch": 1.773936327302081, "percentage": 11.83, "elapsed_time": "3:02:51", "remaining_time": "22:43:22", "throughput": 8360.56, "total_tokens": 91729248} {"current_steps": 90200, "total_steps": 761865, "loss": 1.9806, "lr": 9.658177784736155e-07, "epoch": 1.775905180051584, "percentage": 11.84, "elapsed_time": "3:03:03", "remaining_time": "22:43:10", "throughput": 8360.52, "total_tokens": 91830856} {"current_steps": 90300, "total_steps": 761865, "loss": 1.9766, "lr": 9.65742814123619e-07, "epoch": 1.777874032801087, "percentage": 11.85, "elapsed_time": "3:03:16", "remaining_time": "22:42:58", "throughput": 8360.5, "total_tokens": 91932720} {"current_steps": 90400, "total_steps": 761865, "loss": 1.9995, "lr": 9.656677705779851e-07, "epoch": 1.7798428855505897, "percentage": 11.87, "elapsed_time": "3:03:28", "remaining_time": "22:42:46", "throughput": 8360.5, "total_tokens": 92035120} {"current_steps": 90500, "total_steps": 761865, "loss": 1.9849, "lr": 9.655926478494745e-07, "epoch": 1.7818117383000924, "percentage": 11.88, "elapsed_time": "3:03:40", "remaining_time": "22:42:34", "throughput": 8360.46, "total_tokens": 92136656} {"current_steps": 90600, "total_steps": 761865, "loss": 1.97, "lr": 9.655174459508612e-07, "epoch": 1.7837805910495954, "percentage": 11.89, "elapsed_time": "3:03:52", "remaining_time": "22:42:23", "throughput": 8360.46, "total_tokens": 92239056} {"current_steps": 90700, "total_steps": 761865, "loss": 2.0135, "lr": 9.654421648949326e-07, "epoch": 1.7857494437990984, "percentage": 11.9, "elapsed_time": "3:04:04", "remaining_time": "22:42:10", "throughput": 8360.4, "total_tokens": 92340088} {"current_steps": 90800, "total_steps": 761865, "loss": 1.9846, "lr": 9.653668046944895e-07, "epoch": 1.7877182965486011, "percentage": 11.92, "elapsed_time": "3:04:17", "remaining_time": "22:41:59", "throughput": 8360.39, "total_tokens": 92442488} {"current_steps": 90900, "total_steps": 761865, "loss": 2.0015, "lr": 9.652913653623463e-07, "epoch": 1.789687149298104, "percentage": 11.93, "elapsed_time": "3:04:29", "remaining_time": "22:41:47", "throughput": 8360.34, "total_tokens": 92544456} {"current_steps": 91000, "total_steps": 761865, "loss": 1.9725, "lr": 9.65215846911331e-07, "epoch": 1.7916560020476069, "percentage": 11.94, "elapsed_time": "3:04:41", "remaining_time": "22:41:35", "throughput": 8360.3, "total_tokens": 92645928} {"current_steps": 91100, "total_steps": 761865, "loss": 1.9466, "lr": 9.651402493542845e-07, "epoch": 1.7936248547971099, "percentage": 11.96, "elapsed_time": "3:04:53", "remaining_time": "22:41:23", "throughput": 8360.3, "total_tokens": 92748328} {"current_steps": 91200, "total_steps": 761865, "loss": 1.9408, "lr": 9.650645727040622e-07, "epoch": 1.7955937075466126, "percentage": 11.97, "elapsed_time": "3:05:06", "remaining_time": "22:41:11", "throughput": 8360.27, "total_tokens": 92849856} {"current_steps": 91300, "total_steps": 761865, "loss": 2.0098, "lr": 9.649888169735316e-07, "epoch": 1.7975625602961154, "percentage": 11.98, "elapsed_time": "3:05:18", "remaining_time": "22:40:59", "throughput": 8360.24, "total_tokens": 92951760} {"current_steps": 91400, "total_steps": 761865, "loss": 1.9681, "lr": 9.649129821755744e-07, "epoch": 1.7995314130456184, "percentage": 12.0, "elapsed_time": "3:05:30", "remaining_time": "22:40:47", "throughput": 8360.2, "total_tokens": 93053248} {"current_steps": 91500, "total_steps": 761865, "loss": 2.0062, "lr": 9.648370683230862e-07, "epoch": 1.8015002657951213, "percentage": 12.01, "elapsed_time": "3:05:42", "remaining_time": "22:40:36", "throughput": 8360.18, "total_tokens": 93155264} {"current_steps": 91600, "total_steps": 761865, "loss": 1.9573, "lr": 9.64761075428975e-07, "epoch": 1.803469118544624, "percentage": 12.02, "elapsed_time": "3:05:55", "remaining_time": "22:40:24", "throughput": 8360.15, "total_tokens": 93257664} {"current_steps": 91700, "total_steps": 761865, "loss": 1.9518, "lr": 9.646850035061627e-07, "epoch": 1.8054379712941269, "percentage": 12.04, "elapsed_time": "3:06:07", "remaining_time": "22:40:12", "throughput": 8360.12, "total_tokens": 93359472} {"current_steps": 91800, "total_steps": 761865, "loss": 1.953, "lr": 9.64608852567585e-07, "epoch": 1.8074068240436296, "percentage": 12.05, "elapsed_time": "3:06:19", "remaining_time": "22:40:01", "throughput": 8360.11, "total_tokens": 93461872} {"current_steps": 91900, "total_steps": 761865, "loss": 2.0197, "lr": 9.645326226261907e-07, "epoch": 1.8093756767931326, "percentage": 12.06, "elapsed_time": "3:06:31", "remaining_time": "22:39:49", "throughput": 8360.11, "total_tokens": 93564272} {"current_steps": 92000, "total_steps": 761865, "loss": 1.9998, "lr": 9.64456313694942e-07, "epoch": 1.8113445295426356, "percentage": 12.08, "elapsed_time": "3:06:43", "remaining_time": "22:39:37", "throughput": 8360.09, "total_tokens": 93666152} {"current_steps": 92100, "total_steps": 761865, "loss": 1.9895, "lr": 9.643799257868144e-07, "epoch": 1.8133133822921383, "percentage": 12.09, "elapsed_time": "3:06:56", "remaining_time": "22:39:26", "throughput": 8360.07, "total_tokens": 93768552} {"current_steps": 92200, "total_steps": 761865, "loss": 1.9744, "lr": 9.643034589147974e-07, "epoch": 1.815282235041641, "percentage": 12.1, "elapsed_time": "3:07:08", "remaining_time": "22:39:14", "throughput": 8360.04, "total_tokens": 93870192} {"current_steps": 92300, "total_steps": 761865, "loss": 1.9813, "lr": 9.642269130918933e-07, "epoch": 1.817251087791144, "percentage": 12.12, "elapsed_time": "3:07:20", "remaining_time": "22:39:02", "throughput": 8359.99, "total_tokens": 93971720} {"current_steps": 92400, "total_steps": 761865, "loss": 1.9521, "lr": 9.64150288331118e-07, "epoch": 1.819219940540647, "percentage": 12.13, "elapsed_time": "3:07:32", "remaining_time": "22:38:50", "throughput": 8359.97, "total_tokens": 94073592} {"current_steps": 92500, "total_steps": 761865, "loss": 1.9639, "lr": 9.640735846455008e-07, "epoch": 1.8211887932901498, "percentage": 12.14, "elapsed_time": "3:07:45", "remaining_time": "22:38:37", "throughput": 8359.95, "total_tokens": 94174896} {"current_steps": 92600, "total_steps": 761865, "loss": 2.0172, "lr": 9.639968020480848e-07, "epoch": 1.8231576460396526, "percentage": 12.15, "elapsed_time": "3:07:57", "remaining_time": "22:38:25", "throughput": 8359.92, "total_tokens": 94276528} {"current_steps": 92700, "total_steps": 761865, "loss": 1.9633, "lr": 9.639199405519264e-07, "epoch": 1.8251264987891556, "percentage": 12.17, "elapsed_time": "3:08:09", "remaining_time": "22:38:14", "throughput": 8359.92, "total_tokens": 94378928} {"current_steps": 92800, "total_steps": 761865, "loss": 1.9817, "lr": 9.638430001700947e-07, "epoch": 1.8270953515386585, "percentage": 12.18, "elapsed_time": "3:08:21", "remaining_time": "22:38:02", "throughput": 8359.88, "total_tokens": 94480736} {"current_steps": 92900, "total_steps": 761865, "loss": 1.9597, "lr": 9.637659809156734e-07, "epoch": 1.8290642042881613, "percentage": 12.19, "elapsed_time": "3:08:33", "remaining_time": "22:37:50", "throughput": 8359.87, "total_tokens": 94583136} {"current_steps": 93000, "total_steps": 761865, "loss": 1.977, "lr": 9.636888828017583e-07, "epoch": 1.831033057037664, "percentage": 12.21, "elapsed_time": "3:08:46", "remaining_time": "22:37:38", "throughput": 8359.84, "total_tokens": 94684968} {"current_steps": 93100, "total_steps": 761865, "loss": 2.0445, "lr": 9.636117058414597e-07, "epoch": 1.833001909787167, "percentage": 12.22, "elapsed_time": "3:08:58", "remaining_time": "22:37:27", "throughput": 8359.84, "total_tokens": 94787368} {"current_steps": 93200, "total_steps": 761865, "loss": 2.0241, "lr": 9.635344500479008e-07, "epoch": 1.83497076253667, "percentage": 12.23, "elapsed_time": "3:09:10", "remaining_time": "22:37:15", "throughput": 8359.84, "total_tokens": 94889768} {"current_steps": 93300, "total_steps": 761865, "loss": 1.9712, "lr": 9.634571154342185e-07, "epoch": 1.8369396152861728, "percentage": 12.25, "elapsed_time": "3:09:22", "remaining_time": "22:37:03", "throughput": 8359.81, "total_tokens": 94991496} {"current_steps": 93400, "total_steps": 761865, "loss": 1.9808, "lr": 9.633797020135623e-07, "epoch": 1.8389084680356755, "percentage": 12.26, "elapsed_time": "3:09:35", "remaining_time": "22:36:52", "throughput": 8359.8, "total_tokens": 95093896} {"current_steps": 93500, "total_steps": 761865, "loss": 2.0874, "lr": 9.633022097990964e-07, "epoch": 1.8408773207851785, "percentage": 12.27, "elapsed_time": "3:09:47", "remaining_time": "22:36:40", "throughput": 8359.78, "total_tokens": 95196296} {"current_steps": 93600, "total_steps": 761865, "loss": 1.9437, "lr": 9.632246388039973e-07, "epoch": 1.8428461735346815, "percentage": 12.29, "elapsed_time": "3:09:59", "remaining_time": "22:36:28", "throughput": 8359.76, "total_tokens": 95298072} {"current_steps": 93700, "total_steps": 761865, "loss": 1.9883, "lr": 9.631469890414555e-07, "epoch": 1.8448150262841843, "percentage": 12.3, "elapsed_time": "3:10:11", "remaining_time": "22:36:16", "throughput": 8359.71, "total_tokens": 95399152} {"current_steps": 93800, "total_steps": 761865, "loss": 2.0166, "lr": 9.630692605246745e-07, "epoch": 1.846783879033687, "percentage": 12.31, "elapsed_time": "3:10:24", "remaining_time": "22:36:04", "throughput": 8359.69, "total_tokens": 95501552} {"current_steps": 93900, "total_steps": 761865, "loss": 2.0062, "lr": 9.629914532668714e-07, "epoch": 1.8487527317831898, "percentage": 12.33, "elapsed_time": "3:10:36", "remaining_time": "22:35:52", "throughput": 8359.64, "total_tokens": 95602872} {"current_steps": 94000, "total_steps": 761865, "loss": 1.9453, "lr": 9.629135672812767e-07, "epoch": 1.8507215845326928, "percentage": 12.34, "elapsed_time": "3:10:48", "remaining_time": "22:35:40", "throughput": 8359.6, "total_tokens": 95704456} {"current_steps": 94100, "total_steps": 761865, "loss": 1.9747, "lr": 9.628356025811344e-07, "epoch": 1.8526904372821957, "percentage": 12.35, "elapsed_time": "3:11:00", "remaining_time": "22:35:29", "throughput": 8359.59, "total_tokens": 95806856} {"current_steps": 94200, "total_steps": 761865, "loss": 1.9613, "lr": 9.627575591797014e-07, "epoch": 1.8546592900316985, "percentage": 12.36, "elapsed_time": "3:11:12", "remaining_time": "22:35:17", "throughput": 8359.57, "total_tokens": 95909256} {"current_steps": 94300, "total_steps": 761865, "loss": 1.9573, "lr": 9.626794370902488e-07, "epoch": 1.8566281427812013, "percentage": 12.38, "elapsed_time": "3:11:25", "remaining_time": "22:35:05", "throughput": 8359.55, "total_tokens": 96011280} {"current_steps": 94400, "total_steps": 761865, "loss": 2.0107, "lr": 9.626012363260602e-07, "epoch": 1.8585969955307042, "percentage": 12.39, "elapsed_time": "3:11:37", "remaining_time": "22:34:53", "throughput": 8359.52, "total_tokens": 96112632} {"current_steps": 94500, "total_steps": 761865, "loss": 2.0194, "lr": 9.625229569004332e-07, "epoch": 1.8605658482802072, "percentage": 12.4, "elapsed_time": "3:11:49", "remaining_time": "22:34:41", "throughput": 8359.51, "total_tokens": 96215032} {"current_steps": 94600, "total_steps": 761865, "loss": 1.9917, "lr": 9.624445988266784e-07, "epoch": 1.86253470102971, "percentage": 12.42, "elapsed_time": "3:12:01", "remaining_time": "22:34:30", "throughput": 8359.5, "total_tokens": 96317432} {"current_steps": 94700, "total_steps": 761865, "loss": 1.962, "lr": 9.6236616211812e-07, "epoch": 1.8645035537792127, "percentage": 12.43, "elapsed_time": "3:12:14", "remaining_time": "22:34:17", "throughput": 8359.45, "total_tokens": 96417968} {"current_steps": 94800, "total_steps": 761865, "loss": 1.9406, "lr": 9.622876467880955e-07, "epoch": 1.8664724065287157, "percentage": 12.44, "elapsed_time": "3:12:26", "remaining_time": "22:34:05", "throughput": 8359.41, "total_tokens": 96519552} {"current_steps": 94900, "total_steps": 761865, "loss": 1.9959, "lr": 9.62209052849956e-07, "epoch": 1.8684412592782187, "percentage": 12.46, "elapsed_time": "3:12:38", "remaining_time": "22:33:53", "throughput": 8359.39, "total_tokens": 96621520} {"current_steps": 95000, "total_steps": 761865, "loss": 1.9945, "lr": 9.621303803170653e-07, "epoch": 1.8704101120277214, "percentage": 12.47, "elapsed_time": "3:12:50", "remaining_time": "22:33:41", "throughput": 8359.34, "total_tokens": 96722568} {"current_steps": 95100, "total_steps": 761865, "loss": 2.0119, "lr": 9.620516292028013e-07, "epoch": 1.8723789647772242, "percentage": 12.48, "elapsed_time": "3:13:03", "remaining_time": "22:33:33", "throughput": 8358.9, "total_tokens": 96824128} {"current_steps": 95200, "total_steps": 761865, "loss": 1.9748, "lr": 9.619727995205549e-07, "epoch": 1.8743478175267272, "percentage": 12.5, "elapsed_time": "3:13:15", "remaining_time": "22:33:20", "throughput": 8358.84, "total_tokens": 96925128} {"current_steps": 95300, "total_steps": 761865, "loss": 1.9338, "lr": 9.618938912837302e-07, "epoch": 1.8763166702762302, "percentage": 12.51, "elapsed_time": "3:13:27", "remaining_time": "22:33:09", "throughput": 8358.83, "total_tokens": 97027528} {"current_steps": 95400, "total_steps": 761865, "loss": 1.9623, "lr": 9.618149045057453e-07, "epoch": 1.878285523025733, "percentage": 12.52, "elapsed_time": "3:13:40", "remaining_time": "22:32:57", "throughput": 8358.82, "total_tokens": 97129928} {"current_steps": 95500, "total_steps": 761865, "loss": 1.9466, "lr": 9.617358392000308e-07, "epoch": 1.8802543757752357, "percentage": 12.54, "elapsed_time": "3:13:52", "remaining_time": "22:32:46", "throughput": 8358.79, "total_tokens": 97232328} {"current_steps": 95600, "total_steps": 761865, "loss": 1.9678, "lr": 9.616566953800315e-07, "epoch": 1.8822232285247387, "percentage": 12.55, "elapsed_time": "3:14:04", "remaining_time": "22:32:34", "throughput": 8358.78, "total_tokens": 97334128} {"current_steps": 95700, "total_steps": 761865, "loss": 1.9838, "lr": 9.615774730592048e-07, "epoch": 1.8841920812742416, "percentage": 12.56, "elapsed_time": "3:14:16", "remaining_time": "22:32:22", "throughput": 8358.76, "total_tokens": 97436528} {"current_steps": 95800, "total_steps": 761865, "loss": 1.9909, "lr": 9.61498172251022e-07, "epoch": 1.8861609340237444, "percentage": 12.57, "elapsed_time": "3:14:29", "remaining_time": "22:32:10", "throughput": 8358.69, "total_tokens": 97537648} {"current_steps": 95900, "total_steps": 761865, "loss": 1.9675, "lr": 9.614187929689676e-07, "epoch": 1.8881297867732472, "percentage": 12.59, "elapsed_time": "3:14:41", "remaining_time": "22:31:59", "throughput": 8358.64, "total_tokens": 97640048} {"current_steps": 96000, "total_steps": 761865, "loss": 1.9872, "lr": 9.61339335226539e-07, "epoch": 1.8900986395227501, "percentage": 12.6, "elapsed_time": "3:14:53", "remaining_time": "22:31:48", "throughput": 8358.55, "total_tokens": 97742448} {"current_steps": 96100, "total_steps": 761865, "loss": 1.9564, "lr": 9.612597990372478e-07, "epoch": 1.892067492272253, "percentage": 12.61, "elapsed_time": "3:15:06", "remaining_time": "22:31:37", "throughput": 8358.44, "total_tokens": 97844272} {"current_steps": 96200, "total_steps": 761865, "loss": 1.9709, "lr": 9.61180184414618e-07, "epoch": 1.8940363450217559, "percentage": 12.63, "elapsed_time": "3:15:18", "remaining_time": "22:31:26", "throughput": 8358.34, "total_tokens": 97946672} {"current_steps": 96300, "total_steps": 761865, "loss": 2.0124, "lr": 9.611004913721875e-07, "epoch": 1.8960051977712586, "percentage": 12.64, "elapsed_time": "3:15:30", "remaining_time": "22:31:15", "throughput": 8358.25, "total_tokens": 98048792} {"current_steps": 96400, "total_steps": 761865, "loss": 1.9263, "lr": 9.61020719923508e-07, "epoch": 1.8979740505207614, "percentage": 12.65, "elapsed_time": "3:15:43", "remaining_time": "22:31:05", "throughput": 8358.13, "total_tokens": 98151192} {"current_steps": 96500, "total_steps": 761865, "loss": 1.9979, "lr": 9.609408700821431e-07, "epoch": 1.8999429032702644, "percentage": 12.67, "elapsed_time": "3:15:55", "remaining_time": "22:30:54", "throughput": 8357.98, "total_tokens": 98253592} {"current_steps": 96600, "total_steps": 761865, "loss": 2.0247, "lr": 9.608609418616712e-07, "epoch": 1.9019117560197674, "percentage": 12.68, "elapsed_time": "3:16:08", "remaining_time": "22:30:44", "throughput": 8357.89, "total_tokens": 98355992} {"current_steps": 96700, "total_steps": 761865, "loss": 1.9279, "lr": 9.607809352756833e-07, "epoch": 1.9038806087692701, "percentage": 12.69, "elapsed_time": "3:16:20", "remaining_time": "22:30:33", "throughput": 8357.75, "total_tokens": 98457472} {"current_steps": 96800, "total_steps": 761865, "loss": 2.002, "lr": 9.607008503377835e-07, "epoch": 1.9058494615187729, "percentage": 12.71, "elapsed_time": "3:16:32", "remaining_time": "22:30:22", "throughput": 8357.59, "total_tokens": 98559072} {"current_steps": 96900, "total_steps": 761865, "loss": 1.9937, "lr": 9.6062068706159e-07, "epoch": 1.9078183142682759, "percentage": 12.72, "elapsed_time": "3:16:45", "remaining_time": "22:30:11", "throughput": 8357.48, "total_tokens": 98661472} {"current_steps": 97000, "total_steps": 761865, "loss": 1.9797, "lr": 9.605404454607336e-07, "epoch": 1.9097871670177788, "percentage": 12.73, "elapsed_time": "3:16:57", "remaining_time": "22:30:00", "throughput": 8357.44, "total_tokens": 98763872} {"current_steps": 97100, "total_steps": 761865, "loss": 1.9668, "lr": 9.60460125548859e-07, "epoch": 1.9117560197672816, "percentage": 12.75, "elapsed_time": "3:17:09", "remaining_time": "22:29:48", "throughput": 8357.43, "total_tokens": 98866272} {"current_steps": 97200, "total_steps": 761865, "loss": 1.9813, "lr": 9.603797273396238e-07, "epoch": 1.9137248725167844, "percentage": 12.76, "elapsed_time": "3:17:21", "remaining_time": "22:29:36", "throughput": 8357.41, "total_tokens": 98967592} {"current_steps": 97300, "total_steps": 761865, "loss": 2.0022, "lr": 9.602992508466988e-07, "epoch": 1.9156937252662873, "percentage": 12.77, "elapsed_time": "3:17:34", "remaining_time": "22:29:24", "throughput": 8357.4, "total_tokens": 99069328} {"current_steps": 97400, "total_steps": 761865, "loss": 1.9448, "lr": 9.602186960837686e-07, "epoch": 1.9176625780157903, "percentage": 12.78, "elapsed_time": "3:17:46", "remaining_time": "22:29:12", "throughput": 8357.39, "total_tokens": 99171296} {"current_steps": 97500, "total_steps": 761865, "loss": 1.9926, "lr": 9.601380630645306e-07, "epoch": 1.919631430765293, "percentage": 12.8, "elapsed_time": "3:17:58", "remaining_time": "22:28:59", "throughput": 8357.33, "total_tokens": 99272304} {"current_steps": 97600, "total_steps": 761865, "loss": 1.9754, "lr": 9.600573518026962e-07, "epoch": 1.9216002835147958, "percentage": 12.81, "elapsed_time": "3:18:10", "remaining_time": "22:28:48", "throughput": 8357.33, "total_tokens": 99374704} {"current_steps": 97700, "total_steps": 761865, "loss": 1.9787, "lr": 9.599765623119894e-07, "epoch": 1.9235691362642988, "percentage": 12.82, "elapsed_time": "3:18:22", "remaining_time": "22:28:36", "throughput": 8357.29, "total_tokens": 99476232} {"current_steps": 97800, "total_steps": 761865, "loss": 1.997, "lr": 9.598956946061477e-07, "epoch": 1.9255379890138018, "percentage": 12.84, "elapsed_time": "3:18:35", "remaining_time": "22:28:24", "throughput": 8357.28, "total_tokens": 99578632} {"current_steps": 97900, "total_steps": 761865, "loss": 2.0419, "lr": 9.59814748698922e-07, "epoch": 1.9275068417633046, "percentage": 12.85, "elapsed_time": "3:18:47", "remaining_time": "22:28:12", "throughput": 8357.24, "total_tokens": 99680224} {"current_steps": 98000, "total_steps": 761865, "loss": 1.9977, "lr": 9.597337246040768e-07, "epoch": 1.9294756945128073, "percentage": 12.86, "elapsed_time": "3:18:59", "remaining_time": "22:28:00", "throughput": 8357.19, "total_tokens": 99781520} {"current_steps": 98100, "total_steps": 761865, "loss": 1.9952, "lr": 9.59652622335389e-07, "epoch": 1.9314445472623103, "percentage": 12.88, "elapsed_time": "3:19:11", "remaining_time": "22:27:48", "throughput": 8357.17, "total_tokens": 99883256} {"current_steps": 98200, "total_steps": 761865, "loss": 1.9985, "lr": 9.5957144190665e-07, "epoch": 1.9334134000118133, "percentage": 12.89, "elapsed_time": "3:19:24", "remaining_time": "22:27:36", "throughput": 8357.15, "total_tokens": 99985656} {"current_steps": 98300, "total_steps": 761865, "loss": 1.9399, "lr": 9.594901833316633e-07, "epoch": 1.935382252761316, "percentage": 12.9, "elapsed_time": "3:19:36", "remaining_time": "22:27:24", "throughput": 8357.14, "total_tokens": 100087608} {"current_steps": 98400, "total_steps": 761865, "loss": 1.9726, "lr": 9.594088466242465e-07, "epoch": 1.9373511055108188, "percentage": 12.92, "elapsed_time": "3:19:48", "remaining_time": "22:27:13", "throughput": 8357.12, "total_tokens": 100190008} {"current_steps": 98500, "total_steps": 761865, "loss": 2.0431, "lr": 9.593274317982302e-07, "epoch": 1.9393199582603216, "percentage": 12.93, "elapsed_time": "3:20:00", "remaining_time": "22:27:01", "throughput": 8357.09, "total_tokens": 100291576} {"current_steps": 98600, "total_steps": 761865, "loss": 2.0123, "lr": 9.592459388674584e-07, "epoch": 1.9412888110098245, "percentage": 12.94, "elapsed_time": "3:20:13", "remaining_time": "22:26:49", "throughput": 8357.08, "total_tokens": 100393976} {"current_steps": 98700, "total_steps": 761865, "loss": 1.9633, "lr": 9.59164367845788e-07, "epoch": 1.9432576637593275, "percentage": 12.96, "elapsed_time": "3:20:25", "remaining_time": "22:26:38", "throughput": 8357.07, "total_tokens": 100496376} {"current_steps": 98800, "total_steps": 761865, "loss": 2.0061, "lr": 9.590827187470895e-07, "epoch": 1.9452265165088303, "percentage": 12.97, "elapsed_time": "3:20:37", "remaining_time": "22:26:26", "throughput": 8357.04, "total_tokens": 100598016} {"current_steps": 98900, "total_steps": 761865, "loss": 1.9904, "lr": 9.590009915852468e-07, "epoch": 1.947195369258333, "percentage": 12.98, "elapsed_time": "3:20:49", "remaining_time": "22:26:14", "throughput": 8357.03, "total_tokens": 100700416} {"current_steps": 99000, "total_steps": 761865, "loss": 1.9649, "lr": 9.589191863741569e-07, "epoch": 1.949164222007836, "percentage": 12.99, "elapsed_time": "3:21:02", "remaining_time": "22:26:02", "throughput": 8357.02, "total_tokens": 100802816} {"current_steps": 99100, "total_steps": 761865, "loss": 2.0067, "lr": 9.588373031277302e-07, "epoch": 1.951133074757339, "percentage": 13.01, "elapsed_time": "3:21:14", "remaining_time": "22:25:50", "throughput": 8357.0, "total_tokens": 100904712} {"current_steps": 99200, "total_steps": 761865, "loss": 2.052, "lr": 9.5875534185989e-07, "epoch": 1.9531019275068418, "percentage": 13.02, "elapsed_time": "3:21:26", "remaining_time": "22:25:38", "throughput": 8356.98, "total_tokens": 101006576} {"current_steps": 99300, "total_steps": 761865, "loss": 1.9737, "lr": 9.586733025845732e-07, "epoch": 1.9550707802563445, "percentage": 13.03, "elapsed_time": "3:21:38", "remaining_time": "22:25:27", "throughput": 8356.95, "total_tokens": 101108408} {"current_steps": 99400, "total_steps": 761865, "loss": 1.984, "lr": 9.5859118531573e-07, "epoch": 1.9570396330058475, "percentage": 13.05, "elapsed_time": "3:21:50", "remaining_time": "22:25:15", "throughput": 8356.91, "total_tokens": 101210200} {"current_steps": 99500, "total_steps": 761865, "loss": 2.0265, "lr": 9.585089900673235e-07, "epoch": 1.9590084857553505, "percentage": 13.06, "elapsed_time": "3:22:03", "remaining_time": "22:25:02", "throughput": 8356.86, "total_tokens": 101311160} {"current_steps": 99600, "total_steps": 761865, "loss": 1.9765, "lr": 9.584267168533306e-07, "epoch": 1.9609773385048532, "percentage": 13.07, "elapsed_time": "3:22:15", "remaining_time": "22:24:50", "throughput": 8356.83, "total_tokens": 101412824} {"current_steps": 99700, "total_steps": 761865, "loss": 1.9512, "lr": 9.583443656877413e-07, "epoch": 1.962946191254356, "percentage": 13.09, "elapsed_time": "3:22:27", "remaining_time": "22:24:39", "throughput": 8356.81, "total_tokens": 101515224} {"current_steps": 99800, "total_steps": 761865, "loss": 2.0074, "lr": 9.582619365845582e-07, "epoch": 1.964915044003859, "percentage": 13.1, "elapsed_time": "3:22:39", "remaining_time": "22:24:27", "throughput": 8356.81, "total_tokens": 101617624} {"current_steps": 99900, "total_steps": 761865, "loss": 1.9828, "lr": 9.581794295577979e-07, "epoch": 1.966883896753362, "percentage": 13.11, "elapsed_time": "3:22:52", "remaining_time": "22:24:16", "throughput": 8356.79, "total_tokens": 101720024} {"current_steps": 100000, "total_steps": 761865, "loss": 1.9944, "lr": 9.580968446214903e-07, "epoch": 1.9688527495028647, "percentage": 13.13, "elapsed_time": "3:23:04", "remaining_time": "22:24:04", "throughput": 8356.74, "total_tokens": 101821616} {"current_steps": 100100, "total_steps": 761865, "loss": 1.9757, "lr": 9.580141817896779e-07, "epoch": 1.9708216022523675, "percentage": 13.14, "elapsed_time": "3:23:17", "remaining_time": "22:23:55", "throughput": 8356.37, "total_tokens": 101923464} {"current_steps": 100200, "total_steps": 761865, "loss": 2.0337, "lr": 9.579314410764168e-07, "epoch": 1.9727904550018704, "percentage": 13.15, "elapsed_time": "3:23:29", "remaining_time": "22:23:43", "throughput": 8356.33, "total_tokens": 102025192} {"current_steps": 100300, "total_steps": 761865, "loss": 2.0133, "lr": 9.578486224957768e-07, "epoch": 1.9747593077513734, "percentage": 13.17, "elapsed_time": "3:23:41", "remaining_time": "22:23:31", "throughput": 8356.32, "total_tokens": 102127592} {"current_steps": 100400, "total_steps": 761865, "loss": 1.9646, "lr": 9.577657260618401e-07, "epoch": 1.9767281605008762, "percentage": 13.18, "elapsed_time": "3:23:53", "remaining_time": "22:23:20", "throughput": 8356.32, "total_tokens": 102229992} {"current_steps": 100500, "total_steps": 761865, "loss": 2.0036, "lr": 9.576827517887024e-07, "epoch": 1.978697013250379, "percentage": 13.19, "elapsed_time": "3:24:06", "remaining_time": "22:23:08", "throughput": 8356.31, "total_tokens": 102331856} {"current_steps": 100600, "total_steps": 761865, "loss": 1.996, "lr": 9.575996996904733e-07, "epoch": 1.9806658659998817, "percentage": 13.2, "elapsed_time": "3:24:18", "remaining_time": "22:22:56", "throughput": 8356.29, "total_tokens": 102434256} {"current_steps": 100700, "total_steps": 761865, "loss": 1.9995, "lr": 9.57516569781275e-07, "epoch": 1.9826347187493847, "percentage": 13.22, "elapsed_time": "3:24:30", "remaining_time": "22:22:44", "throughput": 8356.28, "total_tokens": 102536296} {"current_steps": 100800, "total_steps": 761865, "loss": 2.0036, "lr": 9.574333620752426e-07, "epoch": 1.9846035714988877, "percentage": 13.23, "elapsed_time": "3:24:42", "remaining_time": "22:22:32", "throughput": 8356.25, "total_tokens": 102638080} {"current_steps": 100900, "total_steps": 761865, "loss": 1.939, "lr": 9.573500765865253e-07, "epoch": 1.9865724242483904, "percentage": 13.24, "elapsed_time": "3:24:55", "remaining_time": "22:22:21", "throughput": 8356.25, "total_tokens": 102740480} {"current_steps": 101000, "total_steps": 761865, "loss": 1.9403, "lr": 9.572667133292849e-07, "epoch": 1.9885412769978932, "percentage": 13.26, "elapsed_time": "3:25:07", "remaining_time": "22:22:09", "throughput": 8356.23, "total_tokens": 102842336} {"current_steps": 101100, "total_steps": 761865, "loss": 2.0347, "lr": 9.571832723176967e-07, "epoch": 1.9905101297473962, "percentage": 13.27, "elapsed_time": "3:25:19", "remaining_time": "22:21:56", "throughput": 8356.17, "total_tokens": 102942616} {"current_steps": 101200, "total_steps": 761865, "loss": 1.9701, "lr": 9.57099753565949e-07, "epoch": 1.9924789824968991, "percentage": 13.28, "elapsed_time": "3:25:31", "remaining_time": "22:21:44", "throughput": 8356.15, "total_tokens": 103044392} {"current_steps": 101300, "total_steps": 761865, "loss": 1.9833, "lr": 9.570161570882436e-07, "epoch": 1.994447835246402, "percentage": 13.3, "elapsed_time": "3:25:43", "remaining_time": "22:21:32", "throughput": 8356.15, "total_tokens": 103146792} {"current_steps": 101400, "total_steps": 761865, "loss": 1.9858, "lr": 9.569324828987955e-07, "epoch": 1.9964166879959047, "percentage": 13.31, "elapsed_time": "3:25:55", "remaining_time": "22:21:20", "throughput": 8356.11, "total_tokens": 103247832} {"current_steps": 101500, "total_steps": 761865, "loss": 1.9665, "lr": 9.568487310118324e-07, "epoch": 1.9983855407454076, "percentage": 13.32, "elapsed_time": "3:26:08", "remaining_time": "22:21:07", "throughput": 8356.05, "total_tokens": 103348552} {"current_steps": 101600, "total_steps": 761865, "loss": 1.9641, "lr": 9.56764901441596e-07, "epoch": 2.0003543934949106, "percentage": 13.34, "elapsed_time": "3:26:20", "remaining_time": "22:20:55", "throughput": 8356.04, "total_tokens": 103450656} {"current_steps": 101700, "total_steps": 761865, "loss": 1.9251, "lr": 9.566809942023405e-07, "epoch": 2.0023232462444134, "percentage": 13.35, "elapsed_time": "3:26:32", "remaining_time": "22:20:44", "throughput": 8356.04, "total_tokens": 103553056} {"current_steps": 101800, "total_steps": 761865, "loss": 2.0007, "lr": 9.56597009308334e-07, "epoch": 2.004292098993916, "percentage": 13.36, "elapsed_time": "3:26:44", "remaining_time": "22:20:32", "throughput": 8356.01, "total_tokens": 103654728} {"current_steps": 101900, "total_steps": 761865, "loss": 1.9986, "lr": 9.56512946773857e-07, "epoch": 2.006260951743419, "percentage": 13.38, "elapsed_time": "3:26:57", "remaining_time": "22:20:19", "throughput": 8356.0, "total_tokens": 103756528} {"current_steps": 102000, "total_steps": 761865, "loss": 1.9309, "lr": 9.564288066132037e-07, "epoch": 2.008229804492922, "percentage": 13.39, "elapsed_time": "3:27:09", "remaining_time": "22:20:08", "throughput": 8355.98, "total_tokens": 103858584} {"current_steps": 102100, "total_steps": 761865, "loss": 1.9526, "lr": 9.563445888406815e-07, "epoch": 2.010198657242425, "percentage": 13.4, "elapsed_time": "3:27:21", "remaining_time": "22:19:56", "throughput": 8355.98, "total_tokens": 103960984} {"current_steps": 102200, "total_steps": 761865, "loss": 2.0099, "lr": 9.562602934706112e-07, "epoch": 2.0121675099919276, "percentage": 13.41, "elapsed_time": "3:27:33", "remaining_time": "22:19:44", "throughput": 8355.95, "total_tokens": 104062488} {"current_steps": 102300, "total_steps": 761865, "loss": 2.0142, "lr": 9.561759205173264e-07, "epoch": 2.0141363627414304, "percentage": 13.43, "elapsed_time": "3:27:45", "remaining_time": "22:19:31", "throughput": 8355.92, "total_tokens": 104163696} {"current_steps": 102400, "total_steps": 761865, "loss": 1.9843, "lr": 9.560914699951736e-07, "epoch": 2.0161052154909336, "percentage": 13.44, "elapsed_time": "3:27:58", "remaining_time": "22:19:20", "throughput": 8355.91, "total_tokens": 104266096} {"current_steps": 102500, "total_steps": 761865, "loss": 1.9188, "lr": 9.560069419185131e-07, "epoch": 2.0180740682404363, "percentage": 13.45, "elapsed_time": "3:28:10", "remaining_time": "22:19:08", "throughput": 8355.9, "total_tokens": 104368496} {"current_steps": 102600, "total_steps": 761865, "loss": 1.9917, "lr": 9.559223363017184e-07, "epoch": 2.020042920989939, "percentage": 13.47, "elapsed_time": "3:28:22", "remaining_time": "22:18:55", "throughput": 8355.79, "total_tokens": 104467432} {"current_steps": 102700, "total_steps": 761865, "loss": 2.0283, "lr": 9.558376531591758e-07, "epoch": 2.022011773739442, "percentage": 13.48, "elapsed_time": "3:28:34", "remaining_time": "22:18:43", "throughput": 8355.78, "total_tokens": 104569368} {"current_steps": 102800, "total_steps": 761865, "loss": 2.0213, "lr": 9.55752892505285e-07, "epoch": 2.023980626488945, "percentage": 13.49, "elapsed_time": "3:28:46", "remaining_time": "22:18:30", "throughput": 8355.72, "total_tokens": 104669888} {"current_steps": 102900, "total_steps": 761865, "loss": 2.0665, "lr": 9.556680543544591e-07, "epoch": 2.025949479238448, "percentage": 13.51, "elapsed_time": "3:28:58", "remaining_time": "22:18:18", "throughput": 8355.68, "total_tokens": 104771376} {"current_steps": 103000, "total_steps": 761865, "loss": 1.9477, "lr": 9.555831387211234e-07, "epoch": 2.0279183319879506, "percentage": 13.52, "elapsed_time": "3:29:11", "remaining_time": "22:18:06", "throughput": 8355.68, "total_tokens": 104873776} {"current_steps": 103100, "total_steps": 761865, "loss": 2.0178, "lr": 9.55498145619718e-07, "epoch": 2.0298871847374533, "percentage": 13.53, "elapsed_time": "3:29:23", "remaining_time": "22:17:55", "throughput": 8355.68, "total_tokens": 104976176} {"current_steps": 103200, "total_steps": 761865, "loss": 1.9767, "lr": 9.554130750646946e-07, "epoch": 2.0318560374869565, "percentage": 13.55, "elapsed_time": "3:29:35", "remaining_time": "22:17:43", "throughput": 8355.66, "total_tokens": 105078032} {"current_steps": 103300, "total_steps": 761865, "loss": 1.9914, "lr": 9.553279270705186e-07, "epoch": 2.0338248902364593, "percentage": 13.56, "elapsed_time": "3:29:47", "remaining_time": "22:17:31", "throughput": 8355.65, "total_tokens": 105180432} {"current_steps": 103400, "total_steps": 761865, "loss": 1.9623, "lr": 9.552427016516692e-07, "epoch": 2.035793742985962, "percentage": 13.57, "elapsed_time": "3:30:00", "remaining_time": "22:17:19", "throughput": 8355.65, "total_tokens": 105282832} {"current_steps": 103500, "total_steps": 761865, "loss": 1.9699, "lr": 9.551573988226382e-07, "epoch": 2.037762595735465, "percentage": 13.59, "elapsed_time": "3:30:12", "remaining_time": "22:17:08", "throughput": 8355.64, "total_tokens": 105385232} {"current_steps": 103600, "total_steps": 761865, "loss": 2.0081, "lr": 9.550720185979306e-07, "epoch": 2.039731448484968, "percentage": 13.6, "elapsed_time": "3:30:24", "remaining_time": "22:16:56", "throughput": 8355.63, "total_tokens": 105487632} {"current_steps": 103700, "total_steps": 761865, "loss": 2.0589, "lr": 9.549865609920642e-07, "epoch": 2.0417003012344708, "percentage": 13.61, "elapsed_time": "3:30:36", "remaining_time": "22:16:43", "throughput": 8355.57, "total_tokens": 105588200} {"current_steps": 103800, "total_steps": 761865, "loss": 1.9854, "lr": 9.54901026019571e-07, "epoch": 2.0436691539839735, "percentage": 13.62, "elapsed_time": "3:30:49", "remaining_time": "22:16:31", "throughput": 8355.53, "total_tokens": 105689824} {"current_steps": 103900, "total_steps": 761865, "loss": 1.9903, "lr": 9.548154136949948e-07, "epoch": 2.0456380067334763, "percentage": 13.64, "elapsed_time": "3:31:01", "remaining_time": "22:16:19", "throughput": 8355.51, "total_tokens": 105791384} {"current_steps": 104000, "total_steps": 761865, "loss": 2.0259, "lr": 9.547297240328937e-07, "epoch": 2.047606859482979, "percentage": 13.65, "elapsed_time": "3:31:13", "remaining_time": "22:16:08", "throughput": 8355.5, "total_tokens": 105893784} {"current_steps": 104100, "total_steps": 761865, "loss": 1.9472, "lr": 9.546439570478383e-07, "epoch": 2.0495757122324822, "percentage": 13.66, "elapsed_time": "3:31:25", "remaining_time": "22:15:56", "throughput": 8355.5, "total_tokens": 105996184} {"current_steps": 104200, "total_steps": 761865, "loss": 2.0228, "lr": 9.545581127544129e-07, "epoch": 2.051544564981985, "percentage": 13.68, "elapsed_time": "3:31:37", "remaining_time": "22:15:44", "throughput": 8355.46, "total_tokens": 106097432} {"current_steps": 104300, "total_steps": 761865, "loss": 1.9946, "lr": 9.54472191167214e-07, "epoch": 2.0535134177314878, "percentage": 13.69, "elapsed_time": "3:31:50", "remaining_time": "22:15:31", "throughput": 8355.38, "total_tokens": 106197552} {"current_steps": 104400, "total_steps": 761865, "loss": 1.9822, "lr": 9.543861923008526e-07, "epoch": 2.0554822704809905, "percentage": 13.7, "elapsed_time": "3:32:02", "remaining_time": "22:15:19", "throughput": 8355.39, "total_tokens": 106299952} {"current_steps": 104500, "total_steps": 761865, "loss": 1.9786, "lr": 9.543001161699514e-07, "epoch": 2.0574511232304937, "percentage": 13.72, "elapsed_time": "3:32:14", "remaining_time": "22:15:07", "throughput": 8355.37, "total_tokens": 106401848} {"current_steps": 104600, "total_steps": 761865, "loss": 2.0032, "lr": 9.54213962789147e-07, "epoch": 2.0594199759799965, "percentage": 13.73, "elapsed_time": "3:32:26", "remaining_time": "22:14:55", "throughput": 8355.33, "total_tokens": 106502624} {"current_steps": 104700, "total_steps": 761865, "loss": 2.0316, "lr": 9.541277321730896e-07, "epoch": 2.0613888287294992, "percentage": 13.74, "elapsed_time": "3:32:38", "remaining_time": "22:14:42", "throughput": 8355.3, "total_tokens": 106604280} {"current_steps": 104800, "total_steps": 761865, "loss": 1.9838, "lr": 9.540414243364415e-07, "epoch": 2.063357681479002, "percentage": 13.76, "elapsed_time": "3:32:51", "remaining_time": "22:14:30", "throughput": 8355.28, "total_tokens": 106705936} {"current_steps": 104900, "total_steps": 761865, "loss": 1.9563, "lr": 9.539550392938787e-07, "epoch": 2.065326534228505, "percentage": 13.77, "elapsed_time": "3:33:03", "remaining_time": "22:14:19", "throughput": 8355.28, "total_tokens": 106808336} {"current_steps": 105000, "total_steps": 761865, "loss": 2.0396, "lr": 9.538685770600906e-07, "epoch": 2.067295386978008, "percentage": 13.78, "elapsed_time": "3:33:15", "remaining_time": "22:14:07", "throughput": 8355.26, "total_tokens": 106910296} {"current_steps": 105100, "total_steps": 761865, "loss": 1.9999, "lr": 9.537820376497787e-07, "epoch": 2.0692642397275107, "percentage": 13.8, "elapsed_time": "3:33:28", "remaining_time": "22:13:58", "throughput": 8354.93, "total_tokens": 107012696} {"current_steps": 105200, "total_steps": 761865, "loss": 1.9577, "lr": 9.536954210776588e-07, "epoch": 2.0712330924770135, "percentage": 13.81, "elapsed_time": "3:33:40", "remaining_time": "22:13:46", "throughput": 8354.92, "total_tokens": 107115096} {"current_steps": 105300, "total_steps": 761865, "loss": 2.0351, "lr": 9.536087273584592e-07, "epoch": 2.0732019452265167, "percentage": 13.82, "elapsed_time": "3:33:52", "remaining_time": "22:13:34", "throughput": 8354.88, "total_tokens": 107215840} {"current_steps": 105400, "total_steps": 761865, "loss": 1.9819, "lr": 9.535219565069215e-07, "epoch": 2.0751707979760194, "percentage": 13.83, "elapsed_time": "3:34:04", "remaining_time": "22:13:22", "throughput": 8354.85, "total_tokens": 107317464} {"current_steps": 105500, "total_steps": 761865, "loss": 2.0, "lr": 9.534351085378001e-07, "epoch": 2.077139650725522, "percentage": 13.85, "elapsed_time": "3:34:17", "remaining_time": "22:13:10", "throughput": 8354.8, "total_tokens": 107419056} {"current_steps": 105600, "total_steps": 761865, "loss": 1.953, "lr": 9.533481834658631e-07, "epoch": 2.079108503475025, "percentage": 13.86, "elapsed_time": "3:34:29", "remaining_time": "22:12:58", "throughput": 8354.8, "total_tokens": 107521456} {"current_steps": 105700, "total_steps": 761865, "loss": 1.9844, "lr": 9.532611813058912e-07, "epoch": 2.081077356224528, "percentage": 13.87, "elapsed_time": "3:34:41", "remaining_time": "22:12:47", "throughput": 8354.79, "total_tokens": 107623856} {"current_steps": 105800, "total_steps": 761865, "loss": 2.0101, "lr": 9.531741020726783e-07, "epoch": 2.083046208974031, "percentage": 13.89, "elapsed_time": "3:34:53", "remaining_time": "22:12:35", "throughput": 8354.8, "total_tokens": 107726256} {"current_steps": 105900, "total_steps": 761865, "loss": 2.0208, "lr": 9.530869457810316e-07, "epoch": 2.0850150617235337, "percentage": 13.9, "elapsed_time": "3:35:06", "remaining_time": "22:12:22", "throughput": 8354.77, "total_tokens": 107827480} {"current_steps": 106000, "total_steps": 761865, "loss": 1.9645, "lr": 9.529997124457713e-07, "epoch": 2.0869839144730364, "percentage": 13.91, "elapsed_time": "3:35:18", "remaining_time": "22:12:11", "throughput": 8354.77, "total_tokens": 107929880} {"current_steps": 106100, "total_steps": 761865, "loss": 1.9071, "lr": 9.529124020817308e-07, "epoch": 2.0889527672225396, "percentage": 13.93, "elapsed_time": "3:35:30", "remaining_time": "22:11:59", "throughput": 8354.78, "total_tokens": 108032280} {"current_steps": 106200, "total_steps": 761865, "loss": 2.0584, "lr": 9.528250147037563e-07, "epoch": 2.0909216199720424, "percentage": 13.94, "elapsed_time": "3:35:42", "remaining_time": "22:11:47", "throughput": 8354.77, "total_tokens": 108134680} {"current_steps": 106300, "total_steps": 761865, "loss": 1.9705, "lr": 9.527375503267073e-07, "epoch": 2.092890472721545, "percentage": 13.95, "elapsed_time": "3:35:55", "remaining_time": "22:11:35", "throughput": 8354.75, "total_tokens": 108236464} {"current_steps": 106400, "total_steps": 761865, "loss": 1.9693, "lr": 9.526500089654565e-07, "epoch": 2.094859325471048, "percentage": 13.97, "elapsed_time": "3:36:07", "remaining_time": "22:11:23", "throughput": 8354.75, "total_tokens": 108338864} {"current_steps": 106500, "total_steps": 761865, "loss": 1.9823, "lr": 9.525623906348895e-07, "epoch": 2.0968281782205507, "percentage": 13.98, "elapsed_time": "3:36:19", "remaining_time": "22:11:11", "throughput": 8354.73, "total_tokens": 108440848} {"current_steps": 106600, "total_steps": 761865, "loss": 2.0181, "lr": 9.52474695349905e-07, "epoch": 2.098797030970054, "percentage": 13.99, "elapsed_time": "3:36:31", "remaining_time": "22:10:59", "throughput": 8354.71, "total_tokens": 108542304} {"current_steps": 106700, "total_steps": 761865, "loss": 2.0001, "lr": 9.52386923125415e-07, "epoch": 2.1007658837195566, "percentage": 14.01, "elapsed_time": "3:36:44", "remaining_time": "22:10:47", "throughput": 8354.71, "total_tokens": 108644704} {"current_steps": 106800, "total_steps": 761865, "loss": 1.9933, "lr": 9.522990739763442e-07, "epoch": 2.1027347364690594, "percentage": 14.02, "elapsed_time": "3:36:56", "remaining_time": "22:10:35", "throughput": 8354.72, "total_tokens": 108747104} {"current_steps": 106900, "total_steps": 761865, "loss": 2.0328, "lr": 9.522111479176307e-07, "epoch": 2.104703589218562, "percentage": 14.03, "elapsed_time": "3:37:08", "remaining_time": "22:10:24", "throughput": 8354.74, "total_tokens": 108849504} {"current_steps": 107000, "total_steps": 761865, "loss": 1.9932, "lr": 9.521231449642257e-07, "epoch": 2.1066724419680654, "percentage": 14.04, "elapsed_time": "3:37:20", "remaining_time": "22:10:11", "throughput": 8354.7, "total_tokens": 108950008} {"current_steps": 107100, "total_steps": 761865, "loss": 1.9547, "lr": 9.520350651310934e-07, "epoch": 2.108641294717568, "percentage": 14.06, "elapsed_time": "3:37:32", "remaining_time": "22:09:59", "throughput": 8354.7, "total_tokens": 109052408} {"current_steps": 107200, "total_steps": 761865, "loss": 1.9893, "lr": 9.519469084332108e-07, "epoch": 2.110610147467071, "percentage": 14.07, "elapsed_time": "3:37:45", "remaining_time": "22:09:47", "throughput": 8354.68, "total_tokens": 109154376} {"current_steps": 107300, "total_steps": 761865, "loss": 1.9651, "lr": 9.518586748855683e-07, "epoch": 2.1125790002165736, "percentage": 14.08, "elapsed_time": "3:37:57", "remaining_time": "22:09:35", "throughput": 8354.66, "total_tokens": 109256208} {"current_steps": 107400, "total_steps": 761865, "loss": 1.965, "lr": 9.517703645031693e-07, "epoch": 2.114547852966077, "percentage": 14.1, "elapsed_time": "3:38:09", "remaining_time": "22:09:23", "throughput": 8354.65, "total_tokens": 109358608} {"current_steps": 107500, "total_steps": 761865, "loss": 2.0604, "lr": 9.516819773010303e-07, "epoch": 2.1165167057155796, "percentage": 14.11, "elapsed_time": "3:38:21", "remaining_time": "22:09:11", "throughput": 8354.62, "total_tokens": 109459968} {"current_steps": 107600, "total_steps": 761865, "loss": 1.9922, "lr": 9.515935132941806e-07, "epoch": 2.1184855584650824, "percentage": 14.12, "elapsed_time": "3:38:33", "remaining_time": "22:08:59", "throughput": 8354.6, "total_tokens": 109561296} {"current_steps": 107700, "total_steps": 761865, "loss": 1.9399, "lr": 9.515049724976629e-07, "epoch": 2.120454411214585, "percentage": 14.14, "elapsed_time": "3:38:46", "remaining_time": "22:08:47", "throughput": 8354.59, "total_tokens": 109663696} {"current_steps": 107800, "total_steps": 761865, "loss": 1.971, "lr": 9.514163549265329e-07, "epoch": 2.1224232639640883, "percentage": 14.15, "elapsed_time": "3:38:58", "remaining_time": "22:08:36", "throughput": 8354.56, "total_tokens": 109765912} {"current_steps": 107900, "total_steps": 761865, "loss": 1.9789, "lr": 9.513276605958592e-07, "epoch": 2.124392116713591, "percentage": 14.16, "elapsed_time": "3:39:10", "remaining_time": "22:08:24", "throughput": 8354.55, "total_tokens": 109868312} {"current_steps": 108000, "total_steps": 761865, "loss": 1.9907, "lr": 9.512388895207233e-07, "epoch": 2.126360969463094, "percentage": 14.18, "elapsed_time": "3:39:22", "remaining_time": "22:08:12", "throughput": 8354.54, "total_tokens": 109970712} {"current_steps": 108100, "total_steps": 761865, "loss": 1.9896, "lr": 9.511500417162203e-07, "epoch": 2.1283298222125966, "percentage": 14.19, "elapsed_time": "3:39:35", "remaining_time": "22:08:00", "throughput": 8354.5, "total_tokens": 110071440} {"current_steps": 108200, "total_steps": 761865, "loss": 2.0375, "lr": 9.510611171974579e-07, "epoch": 2.1302986749621, "percentage": 14.2, "elapsed_time": "3:39:47", "remaining_time": "22:07:47", "throughput": 8354.43, "total_tokens": 110171600} {"current_steps": 108300, "total_steps": 761865, "loss": 1.9479, "lr": 9.509721159795567e-07, "epoch": 2.1322675277116026, "percentage": 14.22, "elapsed_time": "3:39:59", "remaining_time": "22:07:35", "throughput": 8354.41, "total_tokens": 110272832} {"current_steps": 108400, "total_steps": 761865, "loss": 2.0175, "lr": 9.508830380776512e-07, "epoch": 2.1342363804611053, "percentage": 14.23, "elapsed_time": "3:40:11", "remaining_time": "22:07:23", "throughput": 8354.41, "total_tokens": 110375232} {"current_steps": 108500, "total_steps": 761865, "loss": 1.9634, "lr": 9.507938835068877e-07, "epoch": 2.136205233210608, "percentage": 14.24, "elapsed_time": "3:40:23", "remaining_time": "22:07:11", "throughput": 8354.38, "total_tokens": 110477632} {"current_steps": 108600, "total_steps": 761865, "loss": 2.0112, "lr": 9.507046522824267e-07, "epoch": 2.1381740859601113, "percentage": 14.25, "elapsed_time": "3:40:36", "remaining_time": "22:07:00", "throughput": 8354.36, "total_tokens": 110579904} {"current_steps": 108700, "total_steps": 761865, "loss": 1.9663, "lr": 9.506153444194409e-07, "epoch": 2.140142938709614, "percentage": 14.27, "elapsed_time": "3:40:48", "remaining_time": "22:06:48", "throughput": 8354.35, "total_tokens": 110682304} {"current_steps": 108800, "total_steps": 761865, "loss": 1.9984, "lr": 9.505259599331164e-07, "epoch": 2.142111791459117, "percentage": 14.28, "elapsed_time": "3:41:00", "remaining_time": "22:06:36", "throughput": 8354.34, "total_tokens": 110784704} {"current_steps": 108900, "total_steps": 761865, "loss": 2.0161, "lr": 9.504364988386524e-07, "epoch": 2.1440806442086195, "percentage": 14.29, "elapsed_time": "3:41:12", "remaining_time": "22:06:24", "throughput": 8354.27, "total_tokens": 110885160} {"current_steps": 109000, "total_steps": 761865, "loss": 2.0052, "lr": 9.503469611512609e-07, "epoch": 2.1460494969581223, "percentage": 14.31, "elapsed_time": "3:41:25", "remaining_time": "22:06:12", "throughput": 8354.25, "total_tokens": 110986720} {"current_steps": 109100, "total_steps": 761865, "loss": 2.0, "lr": 9.50257346886167e-07, "epoch": 2.1480183497076255, "percentage": 14.32, "elapsed_time": "3:41:37", "remaining_time": "22:05:59", "throughput": 8354.21, "total_tokens": 111087864} {"current_steps": 109200, "total_steps": 761865, "loss": 1.9725, "lr": 9.501676560586091e-07, "epoch": 2.1499872024571283, "percentage": 14.33, "elapsed_time": "3:41:49", "remaining_time": "22:05:47", "throughput": 8354.17, "total_tokens": 111188912} {"current_steps": 109300, "total_steps": 761865, "loss": 1.9766, "lr": 9.50077888683838e-07, "epoch": 2.151956055206631, "percentage": 14.35, "elapsed_time": "3:42:01", "remaining_time": "22:05:35", "throughput": 8354.14, "total_tokens": 111290312} {"current_steps": 109400, "total_steps": 761865, "loss": 1.9844, "lr": 9.49988044777118e-07, "epoch": 2.153924907956134, "percentage": 14.36, "elapsed_time": "3:42:13", "remaining_time": "22:05:23", "throughput": 8354.14, "total_tokens": 111392712} {"current_steps": 109500, "total_steps": 761865, "loss": 2.008, "lr": 9.498981243537265e-07, "epoch": 2.155893760705637, "percentage": 14.37, "elapsed_time": "3:42:25", "remaining_time": "22:05:10", "throughput": 8354.06, "total_tokens": 111492632} {"current_steps": 109600, "total_steps": 761865, "loss": 1.9994, "lr": 9.498081274289535e-07, "epoch": 2.1578626134551397, "percentage": 14.39, "elapsed_time": "3:42:38", "remaining_time": "22:04:58", "throughput": 8354.01, "total_tokens": 111594104} {"current_steps": 109700, "total_steps": 761865, "loss": 1.9804, "lr": 9.497180540181024e-07, "epoch": 2.1598314662046425, "percentage": 14.4, "elapsed_time": "3:42:50", "remaining_time": "22:04:46", "throughput": 8353.97, "total_tokens": 111695128} {"current_steps": 109800, "total_steps": 761865, "loss": 1.954, "lr": 9.496279041364893e-07, "epoch": 2.1618003189541453, "percentage": 14.41, "elapsed_time": "3:43:02", "remaining_time": "22:04:34", "throughput": 8353.95, "total_tokens": 111796760} {"current_steps": 109900, "total_steps": 761865, "loss": 1.9674, "lr": 9.495376777994434e-07, "epoch": 2.1637691717036485, "percentage": 14.43, "elapsed_time": "3:43:14", "remaining_time": "22:04:22", "throughput": 8353.95, "total_tokens": 111899160} {"current_steps": 110000, "total_steps": 761865, "loss": 2.0086, "lr": 9.494473750223069e-07, "epoch": 2.1657380244531512, "percentage": 14.44, "elapsed_time": "3:43:26", "remaining_time": "22:04:10", "throughput": 8353.94, "total_tokens": 112000976} {"current_steps": 110100, "total_steps": 761865, "loss": 1.9913, "lr": 9.493569958204352e-07, "epoch": 2.167706877202654, "percentage": 14.45, "elapsed_time": "3:43:39", "remaining_time": "22:04:01", "throughput": 8353.62, "total_tokens": 112103376} {"current_steps": 110200, "total_steps": 761865, "loss": 1.9962, "lr": 9.492665402091964e-07, "epoch": 2.1696757299521567, "percentage": 14.46, "elapsed_time": "3:43:52", "remaining_time": "22:03:49", "throughput": 8353.61, "total_tokens": 112205776} {"current_steps": 110300, "total_steps": 761865, "loss": 1.9823, "lr": 9.491760082039716e-07, "epoch": 2.17164458270166, "percentage": 14.48, "elapsed_time": "3:44:04", "remaining_time": "22:03:37", "throughput": 8353.58, "total_tokens": 112307224} {"current_steps": 110400, "total_steps": 761865, "loss": 1.9862, "lr": 9.490853998201551e-07, "epoch": 2.1736134354511627, "percentage": 14.49, "elapsed_time": "3:44:16", "remaining_time": "22:03:26", "throughput": 8353.57, "total_tokens": 112409624} {"current_steps": 110500, "total_steps": 761865, "loss": 1.9418, "lr": 9.489947150731544e-07, "epoch": 2.1755822882006655, "percentage": 14.5, "elapsed_time": "3:44:28", "remaining_time": "22:03:14", "throughput": 8353.57, "total_tokens": 112512024} {"current_steps": 110600, "total_steps": 761865, "loss": 1.9478, "lr": 9.489039539783892e-07, "epoch": 2.177551140950168, "percentage": 14.52, "elapsed_time": "3:44:40", "remaining_time": "22:03:01", "throughput": 8353.56, "total_tokens": 112613608} {"current_steps": 110700, "total_steps": 761865, "loss": 1.9644, "lr": 9.488131165512928e-07, "epoch": 2.179519993699671, "percentage": 14.53, "elapsed_time": "3:44:53", "remaining_time": "22:02:49", "throughput": 8353.52, "total_tokens": 112715192} {"current_steps": 110800, "total_steps": 761865, "loss": 1.9624, "lr": 9.487222028073114e-07, "epoch": 2.181488846449174, "percentage": 14.54, "elapsed_time": "3:45:05", "remaining_time": "22:02:38", "throughput": 8353.53, "total_tokens": 112817592} {"current_steps": 110900, "total_steps": 761865, "loss": 1.9457, "lr": 9.486312127619043e-07, "epoch": 2.183457699198677, "percentage": 14.56, "elapsed_time": "3:45:17", "remaining_time": "22:02:26", "throughput": 8353.52, "total_tokens": 112919992} {"current_steps": 111000, "total_steps": 761865, "loss": 1.9655, "lr": 9.485401464305433e-07, "epoch": 2.1854265519481797, "percentage": 14.57, "elapsed_time": "3:45:29", "remaining_time": "22:02:14", "throughput": 8353.51, "total_tokens": 113022392} {"current_steps": 111100, "total_steps": 761865, "loss": 1.9608, "lr": 9.484490038287135e-07, "epoch": 2.1873954046976825, "percentage": 14.58, "elapsed_time": "3:45:42", "remaining_time": "22:02:02", "throughput": 8353.51, "total_tokens": 113124792} {"current_steps": 111200, "total_steps": 761865, "loss": 1.9875, "lr": 9.483577849719131e-07, "epoch": 2.1893642574471857, "percentage": 14.6, "elapsed_time": "3:45:54", "remaining_time": "22:01:50", "throughput": 8353.47, "total_tokens": 113226256} {"current_steps": 111300, "total_steps": 761865, "loss": 2.0006, "lr": 9.482664898756529e-07, "epoch": 2.1913331101966884, "percentage": 14.61, "elapsed_time": "3:46:06", "remaining_time": "22:01:38", "throughput": 8353.46, "total_tokens": 113327992} {"current_steps": 111400, "total_steps": 761865, "loss": 1.9812, "lr": 9.481751185554569e-07, "epoch": 2.193301962946191, "percentage": 14.62, "elapsed_time": "3:46:18", "remaining_time": "22:01:26", "throughput": 8353.43, "total_tokens": 113429528} {"current_steps": 111500, "total_steps": 761865, "loss": 2.0086, "lr": 9.480836710268623e-07, "epoch": 2.195270815695694, "percentage": 14.64, "elapsed_time": "3:46:30", "remaining_time": "22:01:14", "throughput": 8353.41, "total_tokens": 113531232} {"current_steps": 111600, "total_steps": 761865, "loss": 2.004, "lr": 9.479921473054185e-07, "epoch": 2.197239668445197, "percentage": 14.65, "elapsed_time": "3:46:43", "remaining_time": "22:01:02", "throughput": 8353.41, "total_tokens": 113633632} {"current_steps": 111700, "total_steps": 761865, "loss": 1.9878, "lr": 9.479005474066888e-07, "epoch": 2.1992085211947, "percentage": 14.66, "elapsed_time": "3:46:55", "remaining_time": "22:00:51", "throughput": 8353.41, "total_tokens": 113736032} {"current_steps": 111800, "total_steps": 761865, "loss": 1.9464, "lr": 9.478088713462487e-07, "epoch": 2.2011773739442027, "percentage": 14.67, "elapsed_time": "3:47:07", "remaining_time": "22:00:39", "throughput": 8353.41, "total_tokens": 113838432} {"current_steps": 111900, "total_steps": 761865, "loss": 1.941, "lr": 9.477171191396868e-07, "epoch": 2.2031462266937054, "percentage": 14.69, "elapsed_time": "3:47:20", "remaining_time": "22:00:27", "throughput": 8353.39, "total_tokens": 113940256} {"current_steps": 112000, "total_steps": 761865, "loss": 2.0294, "lr": 9.476252908026054e-07, "epoch": 2.2051150794432086, "percentage": 14.7, "elapsed_time": "3:47:32", "remaining_time": "22:00:15", "throughput": 8353.37, "total_tokens": 114042344} {"current_steps": 112100, "total_steps": 761865, "loss": 1.9986, "lr": 9.475333863506185e-07, "epoch": 2.2070839321927114, "percentage": 14.71, "elapsed_time": "3:47:44", "remaining_time": "22:00:03", "throughput": 8353.37, "total_tokens": 114144304} {"current_steps": 112200, "total_steps": 761865, "loss": 1.9797, "lr": 9.474414057993541e-07, "epoch": 2.209052784942214, "percentage": 14.73, "elapsed_time": "3:47:56", "remaining_time": "21:59:51", "throughput": 8353.36, "total_tokens": 114246184} {"current_steps": 112300, "total_steps": 761865, "loss": 1.9783, "lr": 9.473493491644523e-07, "epoch": 2.211021637691717, "percentage": 14.74, "elapsed_time": "3:48:08", "remaining_time": "21:59:39", "throughput": 8353.31, "total_tokens": 114347368} {"current_steps": 112400, "total_steps": 761865, "loss": 1.9963, "lr": 9.472572164615668e-07, "epoch": 2.21299049044122, "percentage": 14.75, "elapsed_time": "3:48:21", "remaining_time": "21:59:27", "throughput": 8353.28, "total_tokens": 114449064} {"current_steps": 112500, "total_steps": 761865, "loss": 2.0007, "lr": 9.471650077063642e-07, "epoch": 2.214959343190723, "percentage": 14.77, "elapsed_time": "3:48:33", "remaining_time": "21:59:15", "throughput": 8353.26, "total_tokens": 114550840} {"current_steps": 112600, "total_steps": 761865, "loss": 2.0029, "lr": 9.470727229145235e-07, "epoch": 2.2169281959402256, "percentage": 14.78, "elapsed_time": "3:48:45", "remaining_time": "21:59:03", "throughput": 8353.26, "total_tokens": 114653240} {"current_steps": 112700, "total_steps": 761865, "loss": 1.9654, "lr": 9.469803621017371e-07, "epoch": 2.2188970486897284, "percentage": 14.79, "elapsed_time": "3:48:57", "remaining_time": "21:58:51", "throughput": 8353.22, "total_tokens": 114755120} {"current_steps": 112800, "total_steps": 761865, "loss": 1.9523, "lr": 9.468879252837101e-07, "epoch": 2.2208659014392316, "percentage": 14.81, "elapsed_time": "3:49:10", "remaining_time": "21:58:39", "throughput": 8353.2, "total_tokens": 114856672} {"current_steps": 112900, "total_steps": 761865, "loss": 2.0349, "lr": 9.467954124761606e-07, "epoch": 2.2228347541887343, "percentage": 14.82, "elapsed_time": "3:49:22", "remaining_time": "21:58:27", "throughput": 8353.16, "total_tokens": 114958008} {"current_steps": 113000, "total_steps": 761865, "loss": 1.9762, "lr": 9.467028236948197e-07, "epoch": 2.224803606938237, "percentage": 14.83, "elapsed_time": "3:49:34", "remaining_time": "21:58:15", "throughput": 8353.15, "total_tokens": 115060408} {"current_steps": 113100, "total_steps": 761865, "loss": 1.9801, "lr": 9.466101589554312e-07, "epoch": 2.22677245968774, "percentage": 14.85, "elapsed_time": "3:49:46", "remaining_time": "21:58:03", "throughput": 8353.11, "total_tokens": 115161952} {"current_steps": 113200, "total_steps": 761865, "loss": 1.9496, "lr": 9.465174182737521e-07, "epoch": 2.2287413124372426, "percentage": 14.86, "elapsed_time": "3:49:58", "remaining_time": "21:57:51", "throughput": 8353.11, "total_tokens": 115264352} {"current_steps": 113300, "total_steps": 761865, "loss": 1.9687, "lr": 9.464246016655522e-07, "epoch": 2.230710165186746, "percentage": 14.87, "elapsed_time": "3:50:11", "remaining_time": "21:57:39", "throughput": 8353.1, "total_tokens": 115366752} {"current_steps": 113400, "total_steps": 761865, "loss": 2.0141, "lr": 9.463317091466141e-07, "epoch": 2.2326790179362486, "percentage": 14.88, "elapsed_time": "3:50:23", "remaining_time": "21:57:28", "throughput": 8353.09, "total_tokens": 115469152} {"current_steps": 113500, "total_steps": 761865, "loss": 1.9562, "lr": 9.462387407327332e-07, "epoch": 2.2346478706857513, "percentage": 14.9, "elapsed_time": "3:50:35", "remaining_time": "21:57:16", "throughput": 8353.08, "total_tokens": 115571552} {"current_steps": 113600, "total_steps": 761865, "loss": 1.9446, "lr": 9.461456964397184e-07, "epoch": 2.236616723435254, "percentage": 14.91, "elapsed_time": "3:50:48", "remaining_time": "21:57:04", "throughput": 8353.07, "total_tokens": 115673952} {"current_steps": 113700, "total_steps": 761865, "loss": 2.0464, "lr": 9.460525762833908e-07, "epoch": 2.2385855761847573, "percentage": 14.92, "elapsed_time": "3:51:00", "remaining_time": "21:56:52", "throughput": 8353.03, "total_tokens": 115775504} {"current_steps": 113800, "total_steps": 761865, "loss": 1.9711, "lr": 9.459593802795849e-07, "epoch": 2.24055442893426, "percentage": 14.94, "elapsed_time": "3:51:12", "remaining_time": "21:56:40", "throughput": 8353.02, "total_tokens": 115877296} {"current_steps": 113900, "total_steps": 761865, "loss": 1.9621, "lr": 9.458661084441478e-07, "epoch": 2.242523281683763, "percentage": 14.95, "elapsed_time": "3:51:24", "remaining_time": "21:56:28", "throughput": 8352.99, "total_tokens": 115979200} {"current_steps": 114000, "total_steps": 761865, "loss": 2.015, "lr": 9.457727607929393e-07, "epoch": 2.2444921344332656, "percentage": 14.96, "elapsed_time": "3:51:36", "remaining_time": "21:56:16", "throughput": 8352.97, "total_tokens": 116081096} {"current_steps": 114100, "total_steps": 761865, "loss": 1.9905, "lr": 9.456793373418328e-07, "epoch": 2.2464609871827688, "percentage": 14.98, "elapsed_time": "3:51:49", "remaining_time": "21:56:04", "throughput": 8352.93, "total_tokens": 116182640} {"current_steps": 114200, "total_steps": 761865, "loss": 1.9803, "lr": 9.455858381067141e-07, "epoch": 2.2484298399322715, "percentage": 14.99, "elapsed_time": "3:52:01", "remaining_time": "21:55:53", "throughput": 8352.92, "total_tokens": 116285040} {"current_steps": 114300, "total_steps": 761865, "loss": 2.0164, "lr": 9.454922631034818e-07, "epoch": 2.2503986926817743, "percentage": 15.0, "elapsed_time": "3:52:13", "remaining_time": "21:55:41", "throughput": 8352.91, "total_tokens": 116387440} {"current_steps": 114400, "total_steps": 761865, "loss": 2.0168, "lr": 9.453986123480476e-07, "epoch": 2.252367545431277, "percentage": 15.02, "elapsed_time": "3:52:26", "remaining_time": "21:55:29", "throughput": 8352.86, "total_tokens": 116489184} {"current_steps": 114500, "total_steps": 761865, "loss": 2.0379, "lr": 9.453048858563359e-07, "epoch": 2.2543363981807802, "percentage": 15.03, "elapsed_time": "3:52:38", "remaining_time": "21:55:17", "throughput": 8352.86, "total_tokens": 116591584} {"current_steps": 114600, "total_steps": 761865, "loss": 1.9564, "lr": 9.452110836442844e-07, "epoch": 2.256305250930283, "percentage": 15.04, "elapsed_time": "3:52:50", "remaining_time": "21:55:06", "throughput": 8352.85, "total_tokens": 116693984} {"current_steps": 114700, "total_steps": 761865, "loss": 1.9786, "lr": 9.451172057278432e-07, "epoch": 2.2582741036797858, "percentage": 15.06, "elapsed_time": "3:53:02", "remaining_time": "21:54:54", "throughput": 8352.82, "total_tokens": 116795520} {"current_steps": 114800, "total_steps": 761865, "loss": 1.9775, "lr": 9.450232521229755e-07, "epoch": 2.2602429564292885, "percentage": 15.07, "elapsed_time": "3:53:15", "remaining_time": "21:54:42", "throughput": 8352.82, "total_tokens": 116897920} {"current_steps": 114900, "total_steps": 761865, "loss": 1.957, "lr": 9.449292228456572e-07, "epoch": 2.2622118091787913, "percentage": 15.08, "elapsed_time": "3:53:27", "remaining_time": "21:54:29", "throughput": 8352.8, "total_tokens": 116999192} {"current_steps": 115000, "total_steps": 761865, "loss": 1.9599, "lr": 9.448351179118773e-07, "epoch": 2.2641806619282945, "percentage": 15.09, "elapsed_time": "3:53:39", "remaining_time": "21:54:17", "throughput": 8352.77, "total_tokens": 117100776} {"current_steps": 115100, "total_steps": 761865, "loss": 2.0059, "lr": 9.447409373376375e-07, "epoch": 2.2661495146777972, "percentage": 15.11, "elapsed_time": "3:53:52", "remaining_time": "21:54:08", "throughput": 8352.43, "total_tokens": 117202496} {"current_steps": 115200, "total_steps": 761865, "loss": 1.9853, "lr": 9.446466811389524e-07, "epoch": 2.2681183674273, "percentage": 15.12, "elapsed_time": "3:54:04", "remaining_time": "21:53:56", "throughput": 8352.41, "total_tokens": 117304136} {"current_steps": 115300, "total_steps": 761865, "loss": 1.9855, "lr": 9.445523493318496e-07, "epoch": 2.270087220176803, "percentage": 15.13, "elapsed_time": "3:54:16", "remaining_time": "21:53:44", "throughput": 8352.4, "total_tokens": 117406088} {"current_steps": 115400, "total_steps": 761865, "loss": 1.9693, "lr": 9.444579419323692e-07, "epoch": 2.272056072926306, "percentage": 15.15, "elapsed_time": "3:54:28", "remaining_time": "21:53:32", "throughput": 8352.4, "total_tokens": 117508488} {"current_steps": 115500, "total_steps": 761865, "loss": 2.0152, "lr": 9.443634589565646e-07, "epoch": 2.2740249256758087, "percentage": 15.16, "elapsed_time": "3:54:41", "remaining_time": "21:53:20", "throughput": 8352.37, "total_tokens": 117610112} {"current_steps": 115600, "total_steps": 761865, "loss": 1.9559, "lr": 9.442689004205015e-07, "epoch": 2.2759937784253115, "percentage": 15.17, "elapsed_time": "3:54:53", "remaining_time": "21:53:09", "throughput": 8352.36, "total_tokens": 117712512} {"current_steps": 115700, "total_steps": 761865, "loss": 1.9861, "lr": 9.441742663402593e-07, "epoch": 2.2779626311748142, "percentage": 15.19, "elapsed_time": "3:55:05", "remaining_time": "21:52:56", "throughput": 8352.32, "total_tokens": 117813136} {"current_steps": 115800, "total_steps": 761865, "loss": 1.966, "lr": 9.440795567319294e-07, "epoch": 2.2799314839243174, "percentage": 15.2, "elapsed_time": "3:55:17", "remaining_time": "21:52:44", "throughput": 8352.27, "total_tokens": 117913968} {"current_steps": 115900, "total_steps": 761865, "loss": 1.9665, "lr": 9.439847716116162e-07, "epoch": 2.28190033667382, "percentage": 15.21, "elapsed_time": "3:55:29", "remaining_time": "21:52:31", "throughput": 8352.19, "total_tokens": 118013648} {"current_steps": 116000, "total_steps": 761865, "loss": 1.99, "lr": 9.438899109954377e-07, "epoch": 2.283869189423323, "percentage": 15.23, "elapsed_time": "3:55:41", "remaining_time": "21:52:19", "throughput": 8352.17, "total_tokens": 118115552} {"current_steps": 116100, "total_steps": 761865, "loss": 1.9954, "lr": 9.437949748995235e-07, "epoch": 2.2858380421728257, "percentage": 15.24, "elapsed_time": "3:55:54", "remaining_time": "21:52:06", "throughput": 8352.09, "total_tokens": 118215696} {"current_steps": 116200, "total_steps": 761865, "loss": 2.0151, "lr": 9.436999633400171e-07, "epoch": 2.287806894922329, "percentage": 15.25, "elapsed_time": "3:56:06", "remaining_time": "21:51:54", "throughput": 8352.06, "total_tokens": 118316944} {"current_steps": 116300, "total_steps": 761865, "loss": 1.9737, "lr": 9.436048763330742e-07, "epoch": 2.2897757476718317, "percentage": 15.27, "elapsed_time": "3:56:18", "remaining_time": "21:51:42", "throughput": 8352.04, "total_tokens": 118418792} {"current_steps": 116400, "total_steps": 761865, "loss": 2.0081, "lr": 9.435097138948635e-07, "epoch": 2.2917446004213344, "percentage": 15.28, "elapsed_time": "3:56:30", "remaining_time": "21:51:30", "throughput": 8352.02, "total_tokens": 118520376} {"current_steps": 116500, "total_steps": 761865, "loss": 1.9929, "lr": 9.434144760415669e-07, "epoch": 2.293713453170837, "percentage": 15.29, "elapsed_time": "3:56:42", "remaining_time": "21:51:18", "throughput": 8352.0, "total_tokens": 118622776} {"current_steps": 116600, "total_steps": 761865, "loss": 1.9575, "lr": 9.433191627893784e-07, "epoch": 2.2956823059203404, "percentage": 15.3, "elapsed_time": "3:56:55", "remaining_time": "21:51:06", "throughput": 8351.98, "total_tokens": 118723912} {"current_steps": 116700, "total_steps": 761865, "loss": 2.0431, "lr": 9.432237741545055e-07, "epoch": 2.297651158669843, "percentage": 15.32, "elapsed_time": "3:57:07", "remaining_time": "21:50:54", "throughput": 8351.95, "total_tokens": 118825456} {"current_steps": 116800, "total_steps": 761865, "loss": 1.9622, "lr": 9.431283101531681e-07, "epoch": 2.299620011419346, "percentage": 15.33, "elapsed_time": "3:57:19", "remaining_time": "21:50:42", "throughput": 8351.94, "total_tokens": 118927856} {"current_steps": 116900, "total_steps": 761865, "loss": 1.9598, "lr": 9.43032770801599e-07, "epoch": 2.3015888641688487, "percentage": 15.34, "elapsed_time": "3:57:31", "remaining_time": "21:50:30", "throughput": 8351.94, "total_tokens": 119030256} {"current_steps": 117000, "total_steps": 761865, "loss": 2.0286, "lr": 9.429371561160442e-07, "epoch": 2.303557716918352, "percentage": 15.36, "elapsed_time": "3:57:43", "remaining_time": "21:50:18", "throughput": 8351.91, "total_tokens": 119131464} {"current_steps": 117100, "total_steps": 761865, "loss": 1.9796, "lr": 9.428414661127618e-07, "epoch": 2.3055265696678546, "percentage": 15.37, "elapsed_time": "3:57:56", "remaining_time": "21:50:06", "throughput": 8351.88, "total_tokens": 119232936} {"current_steps": 117200, "total_steps": 761865, "loss": 1.9914, "lr": 9.427457008080229e-07, "epoch": 2.3074954224173574, "percentage": 15.38, "elapsed_time": "3:58:08", "remaining_time": "21:49:54", "throughput": 8351.85, "total_tokens": 119335040} {"current_steps": 117300, "total_steps": 761865, "loss": 2.0175, "lr": 9.42649860218112e-07, "epoch": 2.30946427516686, "percentage": 15.4, "elapsed_time": "3:58:20", "remaining_time": "21:49:42", "throughput": 8351.83, "total_tokens": 119436864} {"current_steps": 117400, "total_steps": 761865, "loss": 1.985, "lr": 9.425539443593261e-07, "epoch": 2.311433127916363, "percentage": 15.41, "elapsed_time": "3:58:32", "remaining_time": "21:49:30", "throughput": 8351.83, "total_tokens": 119539264} {"current_steps": 117500, "total_steps": 761865, "loss": 2.0146, "lr": 9.424579532479744e-07, "epoch": 2.313401980665866, "percentage": 15.42, "elapsed_time": "3:58:45", "remaining_time": "21:49:18", "throughput": 8351.82, "total_tokens": 119641024} {"current_steps": 117600, "total_steps": 761865, "loss": 2.0019, "lr": 9.423618869003798e-07, "epoch": 2.315370833415369, "percentage": 15.44, "elapsed_time": "3:58:57", "remaining_time": "21:49:06", "throughput": 8351.79, "total_tokens": 119742472} {"current_steps": 117700, "total_steps": 761865, "loss": 1.9974, "lr": 9.422657453328772e-07, "epoch": 2.3173396861648716, "percentage": 15.45, "elapsed_time": "3:59:09", "remaining_time": "21:48:54", "throughput": 8351.79, "total_tokens": 119844872} {"current_steps": 117800, "total_steps": 761865, "loss": 2.017, "lr": 9.42169528561815e-07, "epoch": 2.319308538914375, "percentage": 15.46, "elapsed_time": "3:59:21", "remaining_time": "21:48:42", "throughput": 8351.76, "total_tokens": 119946560} {"current_steps": 117900, "total_steps": 761865, "loss": 1.9745, "lr": 9.420732366035538e-07, "epoch": 2.3212773916638776, "percentage": 15.48, "elapsed_time": "3:59:34", "remaining_time": "21:48:30", "throughput": 8351.74, "total_tokens": 120048392} {"current_steps": 118000, "total_steps": 761865, "loss": 1.9955, "lr": 9.419768694744672e-07, "epoch": 2.3232462444133803, "percentage": 15.49, "elapsed_time": "3:59:46", "remaining_time": "21:48:18", "throughput": 8351.7, "total_tokens": 120149472} {"current_steps": 118100, "total_steps": 761865, "loss": 1.9925, "lr": 9.41880427190942e-07, "epoch": 2.325215097162883, "percentage": 15.5, "elapsed_time": "3:59:58", "remaining_time": "21:48:06", "throughput": 8351.71, "total_tokens": 120251872} {"current_steps": 118200, "total_steps": 761865, "loss": 2.022, "lr": 9.41783909769377e-07, "epoch": 2.327183949912386, "percentage": 15.51, "elapsed_time": "4:00:10", "remaining_time": "21:47:54", "throughput": 8351.71, "total_tokens": 120354272} {"current_steps": 118300, "total_steps": 761865, "loss": 2.015, "lr": 9.416873172261843e-07, "epoch": 2.329152802661889, "percentage": 15.53, "elapsed_time": "4:00:22", "remaining_time": "21:47:42", "throughput": 8351.71, "total_tokens": 120456672} {"current_steps": 118400, "total_steps": 761865, "loss": 1.9741, "lr": 9.415906495777888e-07, "epoch": 2.331121655411392, "percentage": 15.54, "elapsed_time": "4:00:35", "remaining_time": "21:47:30", "throughput": 8351.67, "total_tokens": 120558152} {"current_steps": 118500, "total_steps": 761865, "loss": 1.9844, "lr": 9.414939068406278e-07, "epoch": 2.3330905081608946, "percentage": 15.55, "elapsed_time": "4:00:47", "remaining_time": "21:47:18", "throughput": 8351.64, "total_tokens": 120659776} {"current_steps": 118600, "total_steps": 761865, "loss": 1.9849, "lr": 9.413970890311517e-07, "epoch": 2.3350593609103973, "percentage": 15.57, "elapsed_time": "4:00:59", "remaining_time": "21:47:06", "throughput": 8351.61, "total_tokens": 120761304} {"current_steps": 118700, "total_steps": 761865, "loss": 2.046, "lr": 9.413001961658235e-07, "epoch": 2.3370282136599005, "percentage": 15.58, "elapsed_time": "4:01:11", "remaining_time": "21:46:54", "throughput": 8351.61, "total_tokens": 120863704} {"current_steps": 118800, "total_steps": 761865, "loss": 1.9968, "lr": 9.412032282611191e-07, "epoch": 2.3389970664094033, "percentage": 15.59, "elapsed_time": "4:01:24", "remaining_time": "21:46:42", "throughput": 8351.59, "total_tokens": 120965288} {"current_steps": 118900, "total_steps": 761865, "loss": 2.0215, "lr": 9.411061853335269e-07, "epoch": 2.340965919158906, "percentage": 15.61, "elapsed_time": "4:01:36", "remaining_time": "21:46:30", "throughput": 8351.58, "total_tokens": 121067240} {"current_steps": 119000, "total_steps": 761865, "loss": 1.9718, "lr": 9.410090673995483e-07, "epoch": 2.342934771908409, "percentage": 15.62, "elapsed_time": "4:01:48", "remaining_time": "21:46:18", "throughput": 8351.51, "total_tokens": 121167992} {"current_steps": 119100, "total_steps": 761865, "loss": 1.9698, "lr": 9.409118744756977e-07, "epoch": 2.344903624657912, "percentage": 15.63, "elapsed_time": "4:02:00", "remaining_time": "21:46:05", "throughput": 8351.47, "total_tokens": 121268824} {"current_steps": 119200, "total_steps": 761865, "loss": 2.0111, "lr": 9.408146065785014e-07, "epoch": 2.346872477407415, "percentage": 15.65, "elapsed_time": "4:02:12", "remaining_time": "21:45:53", "throughput": 8351.46, "total_tokens": 121370912} {"current_steps": 119300, "total_steps": 761865, "loss": 1.9716, "lr": 9.407172637244994e-07, "epoch": 2.3488413301569175, "percentage": 15.66, "elapsed_time": "4:02:25", "remaining_time": "21:45:41", "throughput": 8351.43, "total_tokens": 121472288} {"current_steps": 119400, "total_steps": 761865, "loss": 1.9807, "lr": 9.406198459302439e-07, "epoch": 2.3508101829064203, "percentage": 15.67, "elapsed_time": "4:02:37", "remaining_time": "21:45:29", "throughput": 8351.42, "total_tokens": 121574304} {"current_steps": 119500, "total_steps": 761865, "loss": 1.9585, "lr": 9.405223532122999e-07, "epoch": 2.3527790356559235, "percentage": 15.69, "elapsed_time": "4:02:49", "remaining_time": "21:45:17", "throughput": 8351.41, "total_tokens": 121676240} {"current_steps": 119600, "total_steps": 761865, "loss": 1.9701, "lr": 9.404247855872452e-07, "epoch": 2.3547478884054263, "percentage": 15.7, "elapsed_time": "4:03:01", "remaining_time": "21:45:05", "throughput": 8351.39, "total_tokens": 121778016} {"current_steps": 119700, "total_steps": 761865, "loss": 1.9727, "lr": 9.403271430716706e-07, "epoch": 2.356716741154929, "percentage": 15.71, "elapsed_time": "4:03:14", "remaining_time": "21:44:53", "throughput": 8351.38, "total_tokens": 121880416} {"current_steps": 119800, "total_steps": 761865, "loss": 1.9843, "lr": 9.40229425682179e-07, "epoch": 2.3586855939044318, "percentage": 15.72, "elapsed_time": "4:03:26", "remaining_time": "21:44:42", "throughput": 8351.38, "total_tokens": 121982816} {"current_steps": 119900, "total_steps": 761865, "loss": 1.9667, "lr": 9.401316334353868e-07, "epoch": 2.3606544466539345, "percentage": 15.74, "elapsed_time": "4:03:38", "remaining_time": "21:44:30", "throughput": 8351.35, "total_tokens": 122084400} {"current_steps": 120000, "total_steps": 761865, "loss": 1.9978, "lr": 9.400337663479226e-07, "epoch": 2.3626232994034377, "percentage": 15.75, "elapsed_time": "4:03:50", "remaining_time": "21:44:18", "throughput": 8351.34, "total_tokens": 122186800} {"current_steps": 120100, "total_steps": 761865, "loss": 2.0276, "lr": 9.399358244364277e-07, "epoch": 2.3645921521529405, "percentage": 15.76, "elapsed_time": "4:04:03", "remaining_time": "21:44:08", "throughput": 8350.99, "total_tokens": 122287616} {"current_steps": 120200, "total_steps": 761865, "loss": 1.9761, "lr": 9.398378077175566e-07, "epoch": 2.3665610049024433, "percentage": 15.78, "elapsed_time": "4:04:15", "remaining_time": "21:43:56", "throughput": 8350.97, "total_tokens": 122388864} {"current_steps": 120300, "total_steps": 761865, "loss": 2.0153, "lr": 9.397397162079759e-07, "epoch": 2.3685298576519465, "percentage": 15.79, "elapsed_time": "4:04:27", "remaining_time": "21:43:44", "throughput": 8350.97, "total_tokens": 122491264} {"current_steps": 120400, "total_steps": 761865, "loss": 1.9858, "lr": 9.396415499243655e-07, "epoch": 2.370498710401449, "percentage": 15.8, "elapsed_time": "4:04:40", "remaining_time": "21:43:32", "throughput": 8350.93, "total_tokens": 122592256} {"current_steps": 120500, "total_steps": 761865, "loss": 1.9605, "lr": 9.395433088834176e-07, "epoch": 2.372467563150952, "percentage": 15.82, "elapsed_time": "4:04:52", "remaining_time": "21:43:19", "throughput": 8350.89, "total_tokens": 122693184} {"current_steps": 120600, "total_steps": 761865, "loss": 1.9666, "lr": 9.394449931018373e-07, "epoch": 2.3744364159004547, "percentage": 15.83, "elapsed_time": "4:05:04", "remaining_time": "21:43:08", "throughput": 8350.89, "total_tokens": 122795584} {"current_steps": 120700, "total_steps": 761865, "loss": 1.9711, "lr": 9.393466025963423e-07, "epoch": 2.3764052686499575, "percentage": 15.84, "elapsed_time": "4:05:16", "remaining_time": "21:42:55", "throughput": 8350.87, "total_tokens": 122897248} {"current_steps": 120800, "total_steps": 761865, "loss": 1.959, "lr": 9.392481373836633e-07, "epoch": 2.3783741213994607, "percentage": 15.86, "elapsed_time": "4:05:28", "remaining_time": "21:42:44", "throughput": 8350.87, "total_tokens": 122999648} {"current_steps": 120900, "total_steps": 761865, "loss": 1.9725, "lr": 9.391495974805432e-07, "epoch": 2.3803429741489635, "percentage": 15.87, "elapsed_time": "4:05:41", "remaining_time": "21:42:31", "throughput": 8350.87, "total_tokens": 123101528} {"current_steps": 121000, "total_steps": 761865, "loss": 1.9841, "lr": 9.390509829037381e-07, "epoch": 2.382311826898466, "percentage": 15.88, "elapsed_time": "4:05:53", "remaining_time": "21:42:19", "throughput": 8350.83, "total_tokens": 123203056} {"current_steps": 121100, "total_steps": 761865, "loss": 1.9885, "lr": 9.389522936700165e-07, "epoch": 2.384280679647969, "percentage": 15.9, "elapsed_time": "4:06:05", "remaining_time": "21:42:07", "throughput": 8350.82, "total_tokens": 123304688} {"current_steps": 121200, "total_steps": 761865, "loss": 1.9858, "lr": 9.388535297961597e-07, "epoch": 2.386249532397472, "percentage": 15.91, "elapsed_time": "4:06:17", "remaining_time": "21:41:55", "throughput": 8350.81, "total_tokens": 123407088} {"current_steps": 121300, "total_steps": 761865, "loss": 2.0128, "lr": 9.387546912989614e-07, "epoch": 2.388218385146975, "percentage": 15.92, "elapsed_time": "4:06:30", "remaining_time": "21:41:44", "throughput": 8350.82, "total_tokens": 123509488} {"current_steps": 121400, "total_steps": 761865, "loss": 1.9363, "lr": 9.386557781952287e-07, "epoch": 2.3901872378964777, "percentage": 15.93, "elapsed_time": "4:06:42", "remaining_time": "21:41:32", "throughput": 8350.82, "total_tokens": 123611888} {"current_steps": 121500, "total_steps": 761865, "loss": 1.9847, "lr": 9.385567905017806e-07, "epoch": 2.3921560906459804, "percentage": 15.95, "elapsed_time": "4:06:54", "remaining_time": "21:41:20", "throughput": 8350.81, "total_tokens": 123713712} {"current_steps": 121600, "total_steps": 761865, "loss": 2.011, "lr": 9.384577282354493e-07, "epoch": 2.394124943395483, "percentage": 15.96, "elapsed_time": "4:07:06", "remaining_time": "21:41:07", "throughput": 8350.77, "total_tokens": 123814688} {"current_steps": 121700, "total_steps": 761865, "loss": 1.946, "lr": 9.383585914130794e-07, "epoch": 2.3960937961449864, "percentage": 15.97, "elapsed_time": "4:07:18", "remaining_time": "21:40:55", "throughput": 8350.74, "total_tokens": 123916328} {"current_steps": 121800, "total_steps": 761865, "loss": 1.9333, "lr": 9.382593800515283e-07, "epoch": 2.398062648894489, "percentage": 15.99, "elapsed_time": "4:07:31", "remaining_time": "21:40:43", "throughput": 8350.71, "total_tokens": 124017312} {"current_steps": 121900, "total_steps": 761865, "loss": 2.0135, "lr": 9.381600941676661e-07, "epoch": 2.400031501643992, "percentage": 16.0, "elapsed_time": "4:07:43", "remaining_time": "21:40:31", "throughput": 8350.66, "total_tokens": 124118480} {"current_steps": 122000, "total_steps": 761865, "loss": 1.9691, "lr": 9.380607337783754e-07, "epoch": 2.402000354393495, "percentage": 16.01, "elapsed_time": "4:07:55", "remaining_time": "21:40:19", "throughput": 8350.64, "total_tokens": 124220128} {"current_steps": 122100, "total_steps": 761865, "loss": 2.0552, "lr": 9.379612989005517e-07, "epoch": 2.403969207142998, "percentage": 16.03, "elapsed_time": "4:08:07", "remaining_time": "21:40:07", "throughput": 8350.64, "total_tokens": 124322528} {"current_steps": 122200, "total_steps": 761865, "loss": 1.983, "lr": 9.378617895511032e-07, "epoch": 2.4059380598925006, "percentage": 16.04, "elapsed_time": "4:08:20", "remaining_time": "21:39:55", "throughput": 8350.64, "total_tokens": 124424560} {"current_steps": 122300, "total_steps": 761865, "loss": 2.0576, "lr": 9.377622057469505e-07, "epoch": 2.4079069126420034, "percentage": 16.05, "elapsed_time": "4:08:32", "remaining_time": "21:39:42", "throughput": 8350.61, "total_tokens": 124525328} {"current_steps": 122400, "total_steps": 761865, "loss": 1.9936, "lr": 9.376625475050268e-07, "epoch": 2.409875765391506, "percentage": 16.07, "elapsed_time": "4:08:44", "remaining_time": "21:39:30", "throughput": 8350.59, "total_tokens": 124627080} {"current_steps": 122500, "total_steps": 761865, "loss": 1.9775, "lr": 9.375628148422785e-07, "epoch": 2.4118446181410094, "percentage": 16.08, "elapsed_time": "4:08:56", "remaining_time": "21:39:18", "throughput": 8350.59, "total_tokens": 124729480} {"current_steps": 122600, "total_steps": 761865, "loss": 1.9818, "lr": 9.37463007775664e-07, "epoch": 2.413813470890512, "percentage": 16.09, "elapsed_time": "4:09:08", "remaining_time": "21:39:06", "throughput": 8350.59, "total_tokens": 124831880} {"current_steps": 122700, "total_steps": 761865, "loss": 1.9536, "lr": 9.373631263221547e-07, "epoch": 2.415782323640015, "percentage": 16.11, "elapsed_time": "4:09:21", "remaining_time": "21:38:54", "throughput": 8350.56, "total_tokens": 124933616} {"current_steps": 122800, "total_steps": 761865, "loss": 2.0507, "lr": 9.372631704987347e-07, "epoch": 2.4177511763895176, "percentage": 16.12, "elapsed_time": "4:09:33", "remaining_time": "21:38:43", "throughput": 8350.55, "total_tokens": 125036016} {"current_steps": 122900, "total_steps": 761865, "loss": 1.9965, "lr": 9.371631403224008e-07, "epoch": 2.419720029139021, "percentage": 16.13, "elapsed_time": "4:09:45", "remaining_time": "21:38:31", "throughput": 8350.54, "total_tokens": 125137824} {"current_steps": 123000, "total_steps": 761865, "loss": 1.9897, "lr": 9.370630358101618e-07, "epoch": 2.4216888818885236, "percentage": 16.14, "elapsed_time": "4:09:57", "remaining_time": "21:38:18", "throughput": 8350.51, "total_tokens": 125238720} {"current_steps": 123100, "total_steps": 761865, "loss": 1.9864, "lr": 9.3696285697904e-07, "epoch": 2.4236577346380264, "percentage": 16.16, "elapsed_time": "4:10:09", "remaining_time": "21:38:06", "throughput": 8350.5, "total_tokens": 125340568} {"current_steps": 123200, "total_steps": 761865, "loss": 1.9357, "lr": 9.368626038460699e-07, "epoch": 2.425626587387529, "percentage": 16.17, "elapsed_time": "4:10:22", "remaining_time": "21:37:54", "throughput": 8350.5, "total_tokens": 125442968} {"current_steps": 123300, "total_steps": 761865, "loss": 1.9892, "lr": 9.367622764282987e-07, "epoch": 2.4275954401370323, "percentage": 16.18, "elapsed_time": "4:10:34", "remaining_time": "21:37:42", "throughput": 8350.48, "total_tokens": 125544640} {"current_steps": 123400, "total_steps": 761865, "loss": 1.9773, "lr": 9.366618747427863e-07, "epoch": 2.429564292886535, "percentage": 16.2, "elapsed_time": "4:10:46", "remaining_time": "21:37:30", "throughput": 8350.48, "total_tokens": 125647040} {"current_steps": 123500, "total_steps": 761865, "loss": 2.033, "lr": 9.36561398806605e-07, "epoch": 2.431533145636038, "percentage": 16.21, "elapsed_time": "4:10:58", "remaining_time": "21:37:18", "throughput": 8350.49, "total_tokens": 125748944} {"current_steps": 123600, "total_steps": 761865, "loss": 1.9951, "lr": 9.364608486368399e-07, "epoch": 2.4335019983855406, "percentage": 16.22, "elapsed_time": "4:11:11", "remaining_time": "21:37:06", "throughput": 8350.48, "total_tokens": 125851256} {"current_steps": 123700, "total_steps": 761865, "loss": 1.9914, "lr": 9.363602242505891e-07, "epoch": 2.435470851135044, "percentage": 16.24, "elapsed_time": "4:11:23", "remaining_time": "21:36:54", "throughput": 8350.47, "total_tokens": 125953072} {"current_steps": 123800, "total_steps": 761865, "loss": 1.9774, "lr": 9.362595256649621e-07, "epoch": 2.4374397038845466, "percentage": 16.25, "elapsed_time": "4:11:35", "remaining_time": "21:36:42", "throughput": 8350.45, "total_tokens": 126054664} {"current_steps": 123900, "total_steps": 761865, "loss": 2.0321, "lr": 9.361587528970827e-07, "epoch": 2.4394085566340493, "percentage": 16.26, "elapsed_time": "4:11:47", "remaining_time": "21:36:30", "throughput": 8350.42, "total_tokens": 126155992} {"current_steps": 124000, "total_steps": 761865, "loss": 1.9582, "lr": 9.360579059640859e-07, "epoch": 2.441377409383552, "percentage": 16.28, "elapsed_time": "4:11:59", "remaining_time": "21:36:18", "throughput": 8350.39, "total_tokens": 126257528} {"current_steps": 124100, "total_steps": 761865, "loss": 1.9825, "lr": 9.359569848831203e-07, "epoch": 2.443346262133055, "percentage": 16.29, "elapsed_time": "4:12:12", "remaining_time": "21:36:06", "throughput": 8350.37, "total_tokens": 126359416} {"current_steps": 124200, "total_steps": 761865, "loss": 1.9601, "lr": 9.358559896713463e-07, "epoch": 2.445315114882558, "percentage": 16.3, "elapsed_time": "4:12:24", "remaining_time": "21:35:54", "throughput": 8350.37, "total_tokens": 126461816} {"current_steps": 124300, "total_steps": 761865, "loss": 1.966, "lr": 9.357549203459374e-07, "epoch": 2.447283967632061, "percentage": 16.32, "elapsed_time": "4:12:36", "remaining_time": "21:35:42", "throughput": 8350.33, "total_tokens": 126562848} {"current_steps": 124400, "total_steps": 761865, "loss": 1.9607, "lr": 9.356537769240797e-07, "epoch": 2.4492528203815636, "percentage": 16.33, "elapsed_time": "4:12:48", "remaining_time": "21:35:29", "throughput": 8350.33, "total_tokens": 126664672} {"current_steps": 124500, "total_steps": 761865, "loss": 2.0049, "lr": 9.355525594229717e-07, "epoch": 2.4512216731310668, "percentage": 16.34, "elapsed_time": "4:13:00", "remaining_time": "21:35:17", "throughput": 8350.31, "total_tokens": 126765992} {"current_steps": 124600, "total_steps": 761865, "loss": 2.0275, "lr": 9.354512678598245e-07, "epoch": 2.4531905258805695, "percentage": 16.35, "elapsed_time": "4:13:13", "remaining_time": "21:35:05", "throughput": 8350.3, "total_tokens": 126868392} {"current_steps": 124700, "total_steps": 761865, "loss": 1.9962, "lr": 9.353499022518621e-07, "epoch": 2.4551593786300723, "percentage": 16.37, "elapsed_time": "4:13:25", "remaining_time": "21:34:53", "throughput": 8350.28, "total_tokens": 126969944} {"current_steps": 124800, "total_steps": 761865, "loss": 1.9911, "lr": 9.352484626163206e-07, "epoch": 2.457128231379575, "percentage": 16.38, "elapsed_time": "4:13:37", "remaining_time": "21:34:41", "throughput": 8350.27, "total_tokens": 127071792} {"current_steps": 124900, "total_steps": 761865, "loss": 1.9825, "lr": 9.351469489704491e-07, "epoch": 2.459097084129078, "percentage": 16.39, "elapsed_time": "4:13:49", "remaining_time": "21:34:29", "throughput": 8350.27, "total_tokens": 127174192} {"current_steps": 125000, "total_steps": 761865, "loss": 1.9921, "lr": 9.350453613315093e-07, "epoch": 2.461065936878581, "percentage": 16.41, "elapsed_time": "4:14:01", "remaining_time": "21:34:16", "throughput": 8350.21, "total_tokens": 127273704} {"current_steps": 125100, "total_steps": 761865, "loss": 2.0182, "lr": 9.34943699716775e-07, "epoch": 2.4630347896280838, "percentage": 16.42, "elapsed_time": "4:14:14", "remaining_time": "21:34:07", "throughput": 8349.89, "total_tokens": 127375568} {"current_steps": 125200, "total_steps": 761865, "loss": 2.0025, "lr": 9.34841964143533e-07, "epoch": 2.4650036423775865, "percentage": 16.43, "elapsed_time": "4:14:27", "remaining_time": "21:33:55", "throughput": 8349.9, "total_tokens": 127477968} {"current_steps": 125300, "total_steps": 761865, "loss": 1.9551, "lr": 9.347401546290827e-07, "epoch": 2.4669724951270893, "percentage": 16.45, "elapsed_time": "4:14:39", "remaining_time": "21:33:43", "throughput": 8349.9, "total_tokens": 127580368} {"current_steps": 125400, "total_steps": 761865, "loss": 1.9726, "lr": 9.346382711907359e-07, "epoch": 2.4689413478765925, "percentage": 16.46, "elapsed_time": "4:14:51", "remaining_time": "21:33:31", "throughput": 8349.9, "total_tokens": 127682768} {"current_steps": 125500, "total_steps": 761865, "loss": 1.9582, "lr": 9.34536313845817e-07, "epoch": 2.4709102006260952, "percentage": 16.47, "elapsed_time": "4:15:03", "remaining_time": "21:33:19", "throughput": 8349.9, "total_tokens": 127785168} {"current_steps": 125600, "total_steps": 761865, "loss": 1.9848, "lr": 9.344342826116629e-07, "epoch": 2.472879053375598, "percentage": 16.49, "elapsed_time": "4:15:16", "remaining_time": "21:33:08", "throughput": 8349.9, "total_tokens": 127887568} {"current_steps": 125700, "total_steps": 761865, "loss": 1.9615, "lr": 9.343321775056233e-07, "epoch": 2.4748479061251007, "percentage": 16.5, "elapsed_time": "4:15:28", "remaining_time": "21:32:56", "throughput": 8349.89, "total_tokens": 127989768} {"current_steps": 125800, "total_steps": 761865, "loss": 2.0324, "lr": 9.342299985450603e-07, "epoch": 2.476816758874604, "percentage": 16.51, "elapsed_time": "4:15:40", "remaining_time": "21:32:43", "throughput": 8349.86, "total_tokens": 128090480} {"current_steps": 125900, "total_steps": 761865, "loss": 1.9777, "lr": 9.341277457473484e-07, "epoch": 2.4787856116241067, "percentage": 16.53, "elapsed_time": "4:15:52", "remaining_time": "21:32:31", "throughput": 8349.84, "total_tokens": 128192112} {"current_steps": 126000, "total_steps": 761865, "loss": 1.9614, "lr": 9.340254191298749e-07, "epoch": 2.4807544643736095, "percentage": 16.54, "elapsed_time": "4:16:04", "remaining_time": "21:32:19", "throughput": 8349.85, "total_tokens": 128294512} {"current_steps": 126100, "total_steps": 761865, "loss": 1.9353, "lr": 9.339230187100398e-07, "epoch": 2.4827233171231122, "percentage": 16.55, "elapsed_time": "4:16:17", "remaining_time": "21:32:07", "throughput": 8349.85, "total_tokens": 128396912} {"current_steps": 126200, "total_steps": 761865, "loss": 1.963, "lr": 9.338205445052551e-07, "epoch": 2.4846921698726154, "percentage": 16.56, "elapsed_time": "4:16:29", "remaining_time": "21:31:55", "throughput": 8349.82, "total_tokens": 128498392} {"current_steps": 126300, "total_steps": 761865, "loss": 2.0064, "lr": 9.337179965329458e-07, "epoch": 2.486661022622118, "percentage": 16.58, "elapsed_time": "4:16:41", "remaining_time": "21:31:43", "throughput": 8349.82, "total_tokens": 128600792} {"current_steps": 126400, "total_steps": 761865, "loss": 1.9702, "lr": 9.336153748105494e-07, "epoch": 2.488629875371621, "percentage": 16.59, "elapsed_time": "4:16:53", "remaining_time": "21:31:31", "throughput": 8349.82, "total_tokens": 128703192} {"current_steps": 126500, "total_steps": 761865, "loss": 1.9968, "lr": 9.335126793555157e-07, "epoch": 2.4905987281211237, "percentage": 16.6, "elapsed_time": "4:17:06", "remaining_time": "21:31:20", "throughput": 8349.82, "total_tokens": 128805592} {"current_steps": 126600, "total_steps": 761865, "loss": 2.0016, "lr": 9.334099101853075e-07, "epoch": 2.4925675808706265, "percentage": 16.62, "elapsed_time": "4:17:18", "remaining_time": "21:31:08", "throughput": 8349.79, "total_tokens": 128907112} {"current_steps": 126700, "total_steps": 761865, "loss": 1.9742, "lr": 9.333070673173994e-07, "epoch": 2.4945364336201297, "percentage": 16.63, "elapsed_time": "4:17:30", "remaining_time": "21:30:55", "throughput": 8349.78, "total_tokens": 129008776} {"current_steps": 126800, "total_steps": 761865, "loss": 1.9775, "lr": 9.332041507692793e-07, "epoch": 2.4965052863696324, "percentage": 16.64, "elapsed_time": "4:17:42", "remaining_time": "21:30:43", "throughput": 8349.77, "total_tokens": 129110656} {"current_steps": 126900, "total_steps": 761865, "loss": 2.0023, "lr": 9.331011605584471e-07, "epoch": 2.498474139119135, "percentage": 16.66, "elapsed_time": "4:17:54", "remaining_time": "21:30:31", "throughput": 8349.75, "total_tokens": 129212296} {"current_steps": 127000, "total_steps": 761865, "loss": 1.9738, "lr": 9.329980967024156e-07, "epoch": 2.5004429918686384, "percentage": 16.67, "elapsed_time": "4:18:07", "remaining_time": "21:30:19", "throughput": 8349.73, "total_tokens": 129313952} {"current_steps": 127100, "total_steps": 761865, "loss": 2.013, "lr": 9.328949592187097e-07, "epoch": 2.502411844618141, "percentage": 16.68, "elapsed_time": "4:18:19", "remaining_time": "21:30:07", "throughput": 8349.73, "total_tokens": 129416352} {"current_steps": 127200, "total_steps": 761865, "loss": 2.0074, "lr": 9.327917481248673e-07, "epoch": 2.504380697367644, "percentage": 16.7, "elapsed_time": "4:18:31", "remaining_time": "21:29:55", "throughput": 8349.7, "total_tokens": 129517416} {"current_steps": 127300, "total_steps": 761865, "loss": 1.935, "lr": 9.326884634384384e-07, "epoch": 2.5063495501171467, "percentage": 16.71, "elapsed_time": "4:18:43", "remaining_time": "21:29:43", "throughput": 8349.7, "total_tokens": 129619816} {"current_steps": 127400, "total_steps": 761865, "loss": 1.9947, "lr": 9.325851051769858e-07, "epoch": 2.5083184028666494, "percentage": 16.72, "elapsed_time": "4:18:56", "remaining_time": "21:29:31", "throughput": 8349.67, "total_tokens": 129721680} {"current_steps": 127500, "total_steps": 761865, "loss": 1.9705, "lr": 9.324816733580846e-07, "epoch": 2.5102872556161526, "percentage": 16.74, "elapsed_time": "4:19:08", "remaining_time": "21:29:19", "throughput": 8349.64, "total_tokens": 129823256} {"current_steps": 127600, "total_steps": 761865, "loss": 1.9716, "lr": 9.323781679993225e-07, "epoch": 2.5122561083656554, "percentage": 16.75, "elapsed_time": "4:19:20", "remaining_time": "21:29:07", "throughput": 8349.62, "total_tokens": 129924656} {"current_steps": 127700, "total_steps": 761865, "loss": 2.0005, "lr": 9.322745891182999e-07, "epoch": 2.514224961115158, "percentage": 16.76, "elapsed_time": "4:19:32", "remaining_time": "21:28:55", "throughput": 8349.62, "total_tokens": 130027056} {"current_steps": 127800, "total_steps": 761865, "loss": 1.9997, "lr": 9.321709367326294e-07, "epoch": 2.516193813864661, "percentage": 16.77, "elapsed_time": "4:19:45", "remaining_time": "21:28:43", "throughput": 8349.62, "total_tokens": 130129456} {"current_steps": 127900, "total_steps": 761865, "loss": 2.0264, "lr": 9.320672108599361e-07, "epoch": 2.518162666614164, "percentage": 16.79, "elapsed_time": "4:19:57", "remaining_time": "21:28:31", "throughput": 8349.59, "total_tokens": 130231016} {"current_steps": 128000, "total_steps": 761865, "loss": 1.9705, "lr": 9.31963411517858e-07, "epoch": 2.520131519363667, "percentage": 16.8, "elapsed_time": "4:20:09", "remaining_time": "21:28:19", "throughput": 8349.6, "total_tokens": 130333416} {"current_steps": 128100, "total_steps": 761865, "loss": 2.0478, "lr": 9.31859538724045e-07, "epoch": 2.5221003721131696, "percentage": 16.81, "elapsed_time": "4:20:21", "remaining_time": "21:28:07", "throughput": 8349.55, "total_tokens": 130434344} {"current_steps": 128200, "total_steps": 761865, "loss": 1.9972, "lr": 9.317555924961599e-07, "epoch": 2.5240692248626724, "percentage": 16.83, "elapsed_time": "4:20:33", "remaining_time": "21:27:55", "throughput": 8349.55, "total_tokens": 130536744} {"current_steps": 128300, "total_steps": 761865, "loss": 2.027, "lr": 9.316515728518779e-07, "epoch": 2.526038077612175, "percentage": 16.84, "elapsed_time": "4:20:46", "remaining_time": "21:27:43", "throughput": 8349.54, "total_tokens": 130639144} {"current_steps": 128400, "total_steps": 761865, "loss": 1.9905, "lr": 9.315474798088867e-07, "epoch": 2.5280069303616783, "percentage": 16.85, "elapsed_time": "4:20:58", "remaining_time": "21:27:31", "throughput": 8349.53, "total_tokens": 130740896} {"current_steps": 128500, "total_steps": 761865, "loss": 1.9569, "lr": 9.314433133848864e-07, "epoch": 2.529975783111181, "percentage": 16.87, "elapsed_time": "4:21:10", "remaining_time": "21:27:19", "throughput": 8349.51, "total_tokens": 130842528} {"current_steps": 128600, "total_steps": 761865, "loss": 2.0254, "lr": 9.313390735975894e-07, "epoch": 2.531944635860684, "percentage": 16.88, "elapsed_time": "4:21:22", "remaining_time": "21:27:07", "throughput": 8349.52, "total_tokens": 130944928} {"current_steps": 128700, "total_steps": 761865, "loss": 1.989, "lr": 9.312347604647213e-07, "epoch": 2.533913488610187, "percentage": 16.89, "elapsed_time": "4:21:35", "remaining_time": "21:26:55", "throughput": 8349.52, "total_tokens": 131046696} {"current_steps": 128800, "total_steps": 761865, "loss": 1.9994, "lr": 9.311303740040193e-07, "epoch": 2.53588234135969, "percentage": 16.91, "elapsed_time": "4:21:47", "remaining_time": "21:26:43", "throughput": 8349.52, "total_tokens": 131149096} {"current_steps": 128900, "total_steps": 761865, "loss": 2.004, "lr": 9.310259142332335e-07, "epoch": 2.5378511941091926, "percentage": 16.92, "elapsed_time": "4:21:59", "remaining_time": "21:26:31", "throughput": 8349.5, "total_tokens": 131250664} {"current_steps": 129000, "total_steps": 761865, "loss": 1.9928, "lr": 9.309213811701265e-07, "epoch": 2.5398200468586953, "percentage": 16.93, "elapsed_time": "4:22:11", "remaining_time": "21:26:19", "throughput": 8349.5, "total_tokens": 131353064} {"current_steps": 129100, "total_steps": 761865, "loss": 1.967, "lr": 9.308167748324731e-07, "epoch": 2.541788899608198, "percentage": 16.95, "elapsed_time": "4:22:24", "remaining_time": "21:26:07", "throughput": 8349.49, "total_tokens": 131454872} {"current_steps": 129200, "total_steps": 761865, "loss": 1.9518, "lr": 9.307120952380607e-07, "epoch": 2.5437577523577013, "percentage": 16.96, "elapsed_time": "4:22:36", "remaining_time": "21:25:55", "throughput": 8349.49, "total_tokens": 131557272} {"current_steps": 129300, "total_steps": 761865, "loss": 2.0163, "lr": 9.306073424046896e-07, "epoch": 2.545726605107204, "percentage": 16.97, "elapsed_time": "4:22:48", "remaining_time": "21:25:43", "throughput": 8349.49, "total_tokens": 131659128} {"current_steps": 129400, "total_steps": 761865, "loss": 2.0305, "lr": 9.305025163501716e-07, "epoch": 2.547695457856707, "percentage": 16.98, "elapsed_time": "4:23:00", "remaining_time": "21:25:31", "throughput": 8349.46, "total_tokens": 131760680} {"current_steps": 129500, "total_steps": 761865, "loss": 2.0263, "lr": 9.303976170923317e-07, "epoch": 2.54966431060621, "percentage": 17.0, "elapsed_time": "4:23:13", "remaining_time": "21:25:19", "throughput": 8349.46, "total_tokens": 131863080} {"current_steps": 129600, "total_steps": 761865, "loss": 1.9723, "lr": 9.302926446490073e-07, "epoch": 2.5516331633557128, "percentage": 17.01, "elapsed_time": "4:23:25", "remaining_time": "21:25:06", "throughput": 8349.4, "total_tokens": 131963232} {"current_steps": 129700, "total_steps": 761865, "loss": 2.0053, "lr": 9.301875990380479e-07, "epoch": 2.5536020161052155, "percentage": 17.02, "elapsed_time": "4:23:37", "remaining_time": "21:24:54", "throughput": 8349.38, "total_tokens": 132065096} {"current_steps": 129800, "total_steps": 761865, "loss": 2.0095, "lr": 9.300824802773156e-07, "epoch": 2.5555708688547183, "percentage": 17.04, "elapsed_time": "4:23:49", "remaining_time": "21:24:42", "throughput": 8349.37, "total_tokens": 132167496} {"current_steps": 129900, "total_steps": 761865, "loss": 2.0523, "lr": 9.299772883846851e-07, "epoch": 2.557539721604221, "percentage": 17.05, "elapsed_time": "4:24:01", "remaining_time": "21:24:30", "throughput": 8349.33, "total_tokens": 132267848} {"current_steps": 130000, "total_steps": 761865, "loss": 1.9812, "lr": 9.298720233780432e-07, "epoch": 2.559508574353724, "percentage": 17.06, "elapsed_time": "4:24:13", "remaining_time": "21:24:18", "throughput": 8349.3, "total_tokens": 132369320} {"current_steps": 130100, "total_steps": 761865, "loss": 1.9506, "lr": 9.297666852752895e-07, "epoch": 2.561477427103227, "percentage": 17.08, "elapsed_time": "4:24:26", "remaining_time": "21:24:08", "throughput": 8349.01, "total_tokens": 132471720} {"current_steps": 130200, "total_steps": 761865, "loss": 1.9678, "lr": 9.296612740943357e-07, "epoch": 2.5634462798527298, "percentage": 17.09, "elapsed_time": "4:24:38", "remaining_time": "21:23:56", "throughput": 8349.0, "total_tokens": 132573360} {"current_steps": 130300, "total_steps": 761865, "loss": 1.9588, "lr": 9.295557898531064e-07, "epoch": 2.5654151326022325, "percentage": 17.1, "elapsed_time": "4:24:51", "remaining_time": "21:23:44", "throughput": 8348.98, "total_tokens": 132674944} {"current_steps": 130400, "total_steps": 761865, "loss": 1.9925, "lr": 9.294502325695378e-07, "epoch": 2.5673839853517357, "percentage": 17.12, "elapsed_time": "4:25:03", "remaining_time": "21:23:32", "throughput": 8348.97, "total_tokens": 132776768} {"current_steps": 130500, "total_steps": 761865, "loss": 1.9585, "lr": 9.293446022615794e-07, "epoch": 2.5693528381012385, "percentage": 17.13, "elapsed_time": "4:25:15", "remaining_time": "21:23:20", "throughput": 8348.97, "total_tokens": 132878672} {"current_steps": 130600, "total_steps": 761865, "loss": 1.9453, "lr": 9.292388989471927e-07, "epoch": 2.5713216908507412, "percentage": 17.14, "elapsed_time": "4:25:27", "remaining_time": "21:23:08", "throughput": 8348.96, "total_tokens": 132980480} {"current_steps": 130700, "total_steps": 761865, "loss": 1.9479, "lr": 9.291331226443516e-07, "epoch": 2.573290543600244, "percentage": 17.16, "elapsed_time": "4:25:39", "remaining_time": "21:22:55", "throughput": 8348.94, "total_tokens": 133081544} {"current_steps": 130800, "total_steps": 761865, "loss": 1.9936, "lr": 9.290272733710425e-07, "epoch": 2.5752593963497468, "percentage": 17.17, "elapsed_time": "4:25:52", "remaining_time": "21:22:43", "throughput": 8348.91, "total_tokens": 133182768} {"current_steps": 130900, "total_steps": 761865, "loss": 2.0311, "lr": 9.28921351145264e-07, "epoch": 2.57722824909925, "percentage": 17.18, "elapsed_time": "4:26:04", "remaining_time": "21:22:31", "throughput": 8348.91, "total_tokens": 133284528} {"current_steps": 131000, "total_steps": 761865, "loss": 2.0212, "lr": 9.288153559850274e-07, "epoch": 2.5791971018487527, "percentage": 17.19, "elapsed_time": "4:26:16", "remaining_time": "21:22:19", "throughput": 8348.88, "total_tokens": 133386016} {"current_steps": 131100, "total_steps": 761865, "loss": 2.0261, "lr": 9.287092879083565e-07, "epoch": 2.5811659545982555, "percentage": 17.21, "elapsed_time": "4:26:28", "remaining_time": "21:22:06", "throughput": 8348.85, "total_tokens": 133487032} {"current_steps": 131200, "total_steps": 761865, "loss": 1.9701, "lr": 9.286031469332871e-07, "epoch": 2.5831348073477587, "percentage": 17.22, "elapsed_time": "4:26:40", "remaining_time": "21:21:54", "throughput": 8348.83, "total_tokens": 133588608} {"current_steps": 131300, "total_steps": 761865, "loss": 1.9814, "lr": 9.284969330778674e-07, "epoch": 2.5851036600972614, "percentage": 17.23, "elapsed_time": "4:26:53", "remaining_time": "21:21:42", "throughput": 8348.84, "total_tokens": 133691008} {"current_steps": 131400, "total_steps": 761865, "loss": 2.004, "lr": 9.283906463601585e-07, "epoch": 2.587072512846764, "percentage": 17.25, "elapsed_time": "4:27:05", "remaining_time": "21:21:30", "throughput": 8348.82, "total_tokens": 133792328} {"current_steps": 131500, "total_steps": 761865, "loss": 1.9606, "lr": 9.282842867982332e-07, "epoch": 2.589041365596267, "percentage": 17.26, "elapsed_time": "4:27:17", "remaining_time": "21:21:18", "throughput": 8348.82, "total_tokens": 133894208} {"current_steps": 131600, "total_steps": 761865, "loss": 1.9693, "lr": 9.281778544101775e-07, "epoch": 2.5910102183457697, "percentage": 17.27, "elapsed_time": "4:27:29", "remaining_time": "21:21:06", "throughput": 8348.82, "total_tokens": 133996608} {"current_steps": 131700, "total_steps": 761865, "loss": 1.9697, "lr": 9.28071349214089e-07, "epoch": 2.592979071095273, "percentage": 17.29, "elapsed_time": "4:27:42", "remaining_time": "21:20:54", "throughput": 8348.82, "total_tokens": 134099008} {"current_steps": 131800, "total_steps": 761865, "loss": 1.9429, "lr": 9.27964771228078e-07, "epoch": 2.5949479238447757, "percentage": 17.3, "elapsed_time": "4:27:54", "remaining_time": "21:20:42", "throughput": 8348.82, "total_tokens": 134201408} {"current_steps": 131900, "total_steps": 761865, "loss": 1.9445, "lr": 9.278581204702672e-07, "epoch": 2.5969167765942784, "percentage": 17.31, "elapsed_time": "4:28:06", "remaining_time": "21:20:30", "throughput": 8348.82, "total_tokens": 134303808} {"current_steps": 132000, "total_steps": 761865, "loss": 1.9789, "lr": 9.277513969587919e-07, "epoch": 2.5988856293437816, "percentage": 17.33, "elapsed_time": "4:28:18", "remaining_time": "21:20:18", "throughput": 8348.8, "total_tokens": 134405456} {"current_steps": 132100, "total_steps": 761865, "loss": 1.985, "lr": 9.276446007117993e-07, "epoch": 2.6008544820932844, "percentage": 17.34, "elapsed_time": "4:28:31", "remaining_time": "21:20:06", "throughput": 8348.79, "total_tokens": 134507416} {"current_steps": 132200, "total_steps": 761865, "loss": 1.9638, "lr": 9.275377317474493e-07, "epoch": 2.602823334842787, "percentage": 17.35, "elapsed_time": "4:28:43", "remaining_time": "21:19:54", "throughput": 8348.8, "total_tokens": 134609816} {"current_steps": 132300, "total_steps": 761865, "loss": 1.9709, "lr": 9.27430790083914e-07, "epoch": 2.60479218759229, "percentage": 17.37, "elapsed_time": "4:28:55", "remaining_time": "21:19:42", "throughput": 8348.79, "total_tokens": 134711168} {"current_steps": 132400, "total_steps": 761865, "loss": 2.0193, "lr": 9.27323775739378e-07, "epoch": 2.6067610403417927, "percentage": 17.38, "elapsed_time": "4:29:07", "remaining_time": "21:19:30", "throughput": 8348.79, "total_tokens": 134813568} {"current_steps": 132500, "total_steps": 761865, "loss": 1.975, "lr": 9.27216688732038e-07, "epoch": 2.6087298930912954, "percentage": 17.39, "elapsed_time": "4:29:19", "remaining_time": "21:19:18", "throughput": 8348.75, "total_tokens": 134915104} {"current_steps": 132600, "total_steps": 761865, "loss": 1.9641, "lr": 9.271095290801036e-07, "epoch": 2.6106987458407986, "percentage": 17.4, "elapsed_time": "4:29:32", "remaining_time": "21:19:06", "throughput": 8348.75, "total_tokens": 135017504} {"current_steps": 132700, "total_steps": 761865, "loss": 1.9719, "lr": 9.270022968017961e-07, "epoch": 2.6126675985903014, "percentage": 17.42, "elapsed_time": "4:29:44", "remaining_time": "21:18:53", "throughput": 8348.7, "total_tokens": 135117920} {"current_steps": 132800, "total_steps": 761865, "loss": 1.9957, "lr": 9.268949919153496e-07, "epoch": 2.614636451339804, "percentage": 17.43, "elapsed_time": "4:29:56", "remaining_time": "21:18:41", "throughput": 8348.69, "total_tokens": 135219680} {"current_steps": 132900, "total_steps": 761865, "loss": 1.9878, "lr": 9.267876144390102e-07, "epoch": 2.6166053040893074, "percentage": 17.44, "elapsed_time": "4:30:08", "remaining_time": "21:18:29", "throughput": 8348.67, "total_tokens": 135321280} {"current_steps": 133000, "total_steps": 761865, "loss": 1.9808, "lr": 9.266801643910368e-07, "epoch": 2.61857415683881, "percentage": 17.46, "elapsed_time": "4:30:20", "remaining_time": "21:18:17", "throughput": 8348.64, "total_tokens": 135422760} {"current_steps": 133100, "total_steps": 761865, "loss": 2.0061, "lr": 9.265726417897002e-07, "epoch": 2.620543009588313, "percentage": 17.47, "elapsed_time": "4:30:33", "remaining_time": "21:18:05", "throughput": 8348.62, "total_tokens": 135523760} {"current_steps": 133200, "total_steps": 761865, "loss": 1.9839, "lr": 9.264650466532836e-07, "epoch": 2.6225118623378156, "percentage": 17.48, "elapsed_time": "4:30:45", "remaining_time": "21:17:53", "throughput": 8348.63, "total_tokens": 135626160} {"current_steps": 133300, "total_steps": 761865, "loss": 1.974, "lr": 9.263573790000829e-07, "epoch": 2.6244807150873184, "percentage": 17.5, "elapsed_time": "4:30:57", "remaining_time": "21:17:41", "throughput": 8348.63, "total_tokens": 135728560} {"current_steps": 133400, "total_steps": 761865, "loss": 2.0111, "lr": 9.26249638848406e-07, "epoch": 2.6264495678368216, "percentage": 17.51, "elapsed_time": "4:31:09", "remaining_time": "21:17:29", "throughput": 8348.64, "total_tokens": 135830960} {"current_steps": 133500, "total_steps": 761865, "loss": 2.0108, "lr": 9.261418262165731e-07, "epoch": 2.6284184205863244, "percentage": 17.52, "elapsed_time": "4:31:22", "remaining_time": "21:17:17", "throughput": 8348.64, "total_tokens": 135933360} {"current_steps": 133600, "total_steps": 761865, "loss": 2.0208, "lr": 9.26033941122917e-07, "epoch": 2.630387273335827, "percentage": 17.54, "elapsed_time": "4:31:34", "remaining_time": "21:17:05", "throughput": 8348.63, "total_tokens": 136035672} {"current_steps": 133700, "total_steps": 761865, "loss": 2.0209, "lr": 9.259259835857825e-07, "epoch": 2.6323561260853303, "percentage": 17.55, "elapsed_time": "4:31:46", "remaining_time": "21:16:53", "throughput": 8348.61, "total_tokens": 136137256} {"current_steps": 133800, "total_steps": 761865, "loss": 1.9751, "lr": 9.258179536235268e-07, "epoch": 2.634324978834833, "percentage": 17.56, "elapsed_time": "4:31:58", "remaining_time": "21:16:41", "throughput": 8348.61, "total_tokens": 136239656} {"current_steps": 133900, "total_steps": 761865, "loss": 1.9894, "lr": 9.257098512545196e-07, "epoch": 2.636293831584336, "percentage": 17.58, "elapsed_time": "4:32:11", "remaining_time": "21:16:29", "throughput": 8348.61, "total_tokens": 136342056} {"current_steps": 134000, "total_steps": 761865, "loss": 1.9832, "lr": 9.256016764971429e-07, "epoch": 2.6382626843338386, "percentage": 17.59, "elapsed_time": "4:32:23", "remaining_time": "21:16:17", "throughput": 8348.57, "total_tokens": 136442880} {"current_steps": 134100, "total_steps": 761865, "loss": 1.9743, "lr": 9.254934293697909e-07, "epoch": 2.6402315370833414, "percentage": 17.6, "elapsed_time": "4:32:35", "remaining_time": "21:16:05", "throughput": 8348.56, "total_tokens": 136544760} {"current_steps": 134200, "total_steps": 761865, "loss": 2.0062, "lr": 9.253851098908698e-07, "epoch": 2.6422003898328446, "percentage": 17.61, "elapsed_time": "4:32:47", "remaining_time": "21:15:53", "throughput": 8348.57, "total_tokens": 136647160} {"current_steps": 134300, "total_steps": 761865, "loss": 2.0146, "lr": 9.252767180787988e-07, "epoch": 2.6441692425823473, "percentage": 17.63, "elapsed_time": "4:33:00", "remaining_time": "21:15:41", "throughput": 8348.57, "total_tokens": 136749560} {"current_steps": 134400, "total_steps": 761865, "loss": 1.997, "lr": 9.251682539520087e-07, "epoch": 2.64613809533185, "percentage": 17.64, "elapsed_time": "4:33:12", "remaining_time": "21:15:29", "throughput": 8348.55, "total_tokens": 136850640} {"current_steps": 134500, "total_steps": 761865, "loss": 1.9582, "lr": 9.250597175289432e-07, "epoch": 2.648106948081353, "percentage": 17.65, "elapsed_time": "4:33:24", "remaining_time": "21:15:17", "throughput": 8348.55, "total_tokens": 136953040} {"current_steps": 134600, "total_steps": 761865, "loss": 2.0079, "lr": 9.249511088280577e-07, "epoch": 2.650075800830856, "percentage": 17.67, "elapsed_time": "4:33:36", "remaining_time": "21:15:04", "throughput": 8348.55, "total_tokens": 137054728} {"current_steps": 134700, "total_steps": 761865, "loss": 2.0114, "lr": 9.248424278678204e-07, "epoch": 2.652044653580359, "percentage": 17.68, "elapsed_time": "4:33:48", "remaining_time": "21:14:53", "throughput": 8348.55, "total_tokens": 137157128} {"current_steps": 134800, "total_steps": 761865, "loss": 1.9643, "lr": 9.247336746667116e-07, "epoch": 2.6540135063298615, "percentage": 17.69, "elapsed_time": "4:34:01", "remaining_time": "21:14:40", "throughput": 8348.52, "total_tokens": 137258224} {"current_steps": 134900, "total_steps": 761865, "loss": 1.9493, "lr": 9.246248492432239e-07, "epoch": 2.6559823590793643, "percentage": 17.71, "elapsed_time": "4:34:13", "remaining_time": "21:14:28", "throughput": 8348.49, "total_tokens": 137359768} {"current_steps": 135000, "total_steps": 761865, "loss": 1.9964, "lr": 9.245159516158617e-07, "epoch": 2.657951211828867, "percentage": 17.72, "elapsed_time": "4:34:25", "remaining_time": "21:14:16", "throughput": 8348.48, "total_tokens": 137461728} {"current_steps": 135100, "total_steps": 761865, "loss": 1.9381, "lr": 9.244069818031426e-07, "epoch": 2.6599200645783703, "percentage": 17.73, "elapsed_time": "4:34:38", "remaining_time": "21:14:07", "throughput": 8348.14, "total_tokens": 137564128} {"current_steps": 135200, "total_steps": 761865, "loss": 1.9997, "lr": 9.242979398235959e-07, "epoch": 2.661888917327873, "percentage": 17.75, "elapsed_time": "4:34:50", "remaining_time": "21:13:55", "throughput": 8348.15, "total_tokens": 137665824} {"current_steps": 135300, "total_steps": 761865, "loss": 2.0132, "lr": 9.241888256957633e-07, "epoch": 2.663857770077376, "percentage": 17.76, "elapsed_time": "4:35:02", "remaining_time": "21:13:43", "throughput": 8348.15, "total_tokens": 137768224} {"current_steps": 135400, "total_steps": 761865, "loss": 1.9664, "lr": 9.240796394381985e-07, "epoch": 2.665826622826879, "percentage": 17.77, "elapsed_time": "4:35:15", "remaining_time": "21:13:31", "throughput": 8348.13, "total_tokens": 137869808} {"current_steps": 135500, "total_steps": 761865, "loss": 1.9713, "lr": 9.23970381069468e-07, "epoch": 2.6677954755763817, "percentage": 17.79, "elapsed_time": "4:35:27", "remaining_time": "21:13:19", "throughput": 8348.14, "total_tokens": 137972208} {"current_steps": 135600, "total_steps": 761865, "loss": 1.9664, "lr": 9.238610506081501e-07, "epoch": 2.6697643283258845, "percentage": 17.8, "elapsed_time": "4:35:39", "remaining_time": "21:13:07", "throughput": 8348.13, "total_tokens": 138073880} {"current_steps": 135700, "total_steps": 761865, "loss": 2.032, "lr": 9.237516480728356e-07, "epoch": 2.6717331810753873, "percentage": 17.81, "elapsed_time": "4:35:51", "remaining_time": "21:12:55", "throughput": 8348.13, "total_tokens": 138176280} {"current_steps": 135800, "total_steps": 761865, "loss": 2.0422, "lr": 9.236421734821273e-07, "epoch": 2.67370203382489, "percentage": 17.82, "elapsed_time": "4:36:03", "remaining_time": "21:12:42", "throughput": 8348.09, "total_tokens": 138276816} {"current_steps": 135900, "total_steps": 761865, "loss": 1.9659, "lr": 9.235326268546406e-07, "epoch": 2.6756708865743932, "percentage": 17.84, "elapsed_time": "4:36:16", "remaining_time": "21:12:30", "throughput": 8348.09, "total_tokens": 138378616} {"current_steps": 136000, "total_steps": 761865, "loss": 1.963, "lr": 9.23423008209003e-07, "epoch": 2.677639739323896, "percentage": 17.85, "elapsed_time": "4:36:28", "remaining_time": "21:12:18", "throughput": 8348.09, "total_tokens": 138481016} {"current_steps": 136100, "total_steps": 761865, "loss": 2.0181, "lr": 9.233133175638541e-07, "epoch": 2.6796085920733987, "percentage": 17.86, "elapsed_time": "4:36:40", "remaining_time": "21:12:06", "throughput": 8348.07, "total_tokens": 138582584} {"current_steps": 136200, "total_steps": 761865, "loss": 1.9488, "lr": 9.23203554937846e-07, "epoch": 2.681577444822902, "percentage": 17.88, "elapsed_time": "4:36:52", "remaining_time": "21:11:54", "throughput": 8348.06, "total_tokens": 138684168} {"current_steps": 136300, "total_steps": 761865, "loss": 1.9828, "lr": 9.230937203496428e-07, "epoch": 2.6835462975724047, "percentage": 17.89, "elapsed_time": "4:37:04", "remaining_time": "21:11:42", "throughput": 8348.07, "total_tokens": 138786568} {"current_steps": 136400, "total_steps": 761865, "loss": 1.9879, "lr": 9.22983813817921e-07, "epoch": 2.6855151503219075, "percentage": 17.9, "elapsed_time": "4:37:17", "remaining_time": "21:11:30", "throughput": 8348.07, "total_tokens": 138888968} {"current_steps": 136500, "total_steps": 761865, "loss": 1.9555, "lr": 9.228738353613693e-07, "epoch": 2.68748400307141, "percentage": 17.92, "elapsed_time": "4:37:29", "remaining_time": "21:11:18", "throughput": 8348.04, "total_tokens": 138990600} {"current_steps": 136600, "total_steps": 761865, "loss": 1.9704, "lr": 9.227637849986886e-07, "epoch": 2.689452855820913, "percentage": 17.93, "elapsed_time": "4:37:41", "remaining_time": "21:11:06", "throughput": 8348.04, "total_tokens": 139093000} {"current_steps": 136700, "total_steps": 761865, "loss": 1.9854, "lr": 9.22653662748592e-07, "epoch": 2.691421708570416, "percentage": 17.94, "elapsed_time": "4:37:53", "remaining_time": "21:10:54", "throughput": 8348.02, "total_tokens": 139193960} {"current_steps": 136800, "total_steps": 761865, "loss": 2.0031, "lr": 9.225434686298048e-07, "epoch": 2.693390561319919, "percentage": 17.96, "elapsed_time": "4:38:05", "remaining_time": "21:10:41", "throughput": 8347.95, "total_tokens": 139293784} {"current_steps": 136900, "total_steps": 761865, "loss": 1.9305, "lr": 9.224332026610647e-07, "epoch": 2.6953594140694217, "percentage": 17.97, "elapsed_time": "4:38:18", "remaining_time": "21:10:29", "throughput": 8347.96, "total_tokens": 139396184} {"current_steps": 137000, "total_steps": 761865, "loss": 1.9994, "lr": 9.223228648611214e-07, "epoch": 2.6973282668189245, "percentage": 17.98, "elapsed_time": "4:38:30", "remaining_time": "21:10:17", "throughput": 8347.95, "total_tokens": 139498104} {"current_steps": 137100, "total_steps": 761865, "loss": 1.9572, "lr": 9.222124552487372e-07, "epoch": 2.6992971195684277, "percentage": 18.0, "elapsed_time": "4:38:42", "remaining_time": "21:10:05", "throughput": 8347.95, "total_tokens": 139600504} {"current_steps": 137200, "total_steps": 761865, "loss": 1.9585, "lr": 9.221019738426859e-07, "epoch": 2.7012659723179304, "percentage": 18.01, "elapsed_time": "4:38:54", "remaining_time": "21:09:53", "throughput": 8347.95, "total_tokens": 139702904} {"current_steps": 137300, "total_steps": 761865, "loss": 1.9695, "lr": 9.21991420661754e-07, "epoch": 2.703234825067433, "percentage": 18.02, "elapsed_time": "4:39:07", "remaining_time": "21:09:41", "throughput": 8347.91, "total_tokens": 139803896} {"current_steps": 137400, "total_steps": 761865, "loss": 1.9644, "lr": 9.218807957247406e-07, "epoch": 2.705203677816936, "percentage": 18.03, "elapsed_time": "4:39:19", "remaining_time": "21:09:28", "throughput": 8347.87, "total_tokens": 139904408} {"current_steps": 137500, "total_steps": 761865, "loss": 2.0034, "lr": 9.217700990504559e-07, "epoch": 2.7071725305664387, "percentage": 18.05, "elapsed_time": "4:39:31", "remaining_time": "21:09:16", "throughput": 8347.86, "total_tokens": 140006168} {"current_steps": 137600, "total_steps": 761865, "loss": 1.9777, "lr": 9.216593306577234e-07, "epoch": 2.709141383315942, "percentage": 18.06, "elapsed_time": "4:39:43", "remaining_time": "21:09:04", "throughput": 8347.87, "total_tokens": 140108568} {"current_steps": 137700, "total_steps": 761865, "loss": 2.0064, "lr": 9.21548490565378e-07, "epoch": 2.7111102360654447, "percentage": 18.07, "elapsed_time": "4:39:55", "remaining_time": "21:08:52", "throughput": 8347.87, "total_tokens": 140210664} {"current_steps": 137800, "total_steps": 761865, "loss": 1.9855, "lr": 9.214375787922673e-07, "epoch": 2.7130790888149474, "percentage": 18.09, "elapsed_time": "4:40:08", "remaining_time": "21:08:40", "throughput": 8347.86, "total_tokens": 140312432} {"current_steps": 137900, "total_steps": 761865, "loss": 1.9697, "lr": 9.21326595357251e-07, "epoch": 2.7150479415644506, "percentage": 18.1, "elapsed_time": "4:40:20", "remaining_time": "21:08:28", "throughput": 8347.81, "total_tokens": 140413056} {"current_steps": 138000, "total_steps": 761865, "loss": 2.0105, "lr": 9.212155402792008e-07, "epoch": 2.7170167943139534, "percentage": 18.11, "elapsed_time": "4:40:32", "remaining_time": "21:08:15", "throughput": 8347.77, "total_tokens": 140513744} {"current_steps": 138100, "total_steps": 761865, "loss": 2.0049, "lr": 9.211044135770005e-07, "epoch": 2.718985647063456, "percentage": 18.13, "elapsed_time": "4:40:44", "remaining_time": "21:08:03", "throughput": 8347.76, "total_tokens": 140616040} {"current_steps": 138200, "total_steps": 761865, "loss": 2.0164, "lr": 9.209932152695466e-07, "epoch": 2.720954499812959, "percentage": 18.14, "elapsed_time": "4:40:56", "remaining_time": "21:07:51", "throughput": 8347.76, "total_tokens": 140717936} {"current_steps": 138300, "total_steps": 761865, "loss": 2.0132, "lr": 9.208819453757473e-07, "epoch": 2.7229233525624617, "percentage": 18.15, "elapsed_time": "4:41:09", "remaining_time": "21:07:39", "throughput": 8347.75, "total_tokens": 140820144} {"current_steps": 138400, "total_steps": 761865, "loss": 1.9429, "lr": 9.207706039145229e-07, "epoch": 2.724892205311965, "percentage": 18.17, "elapsed_time": "4:41:21", "remaining_time": "21:07:27", "throughput": 8347.73, "total_tokens": 140921808} {"current_steps": 138500, "total_steps": 761865, "loss": 2.027, "lr": 9.206591909048063e-07, "epoch": 2.7268610580614676, "percentage": 18.18, "elapsed_time": "4:41:33", "remaining_time": "21:07:15", "throughput": 8347.72, "total_tokens": 141023760} {"current_steps": 138600, "total_steps": 761865, "loss": 2.0271, "lr": 9.205477063655424e-07, "epoch": 2.7288299108109704, "percentage": 18.19, "elapsed_time": "4:41:45", "remaining_time": "21:07:02", "throughput": 8347.67, "total_tokens": 141123640} {"current_steps": 138700, "total_steps": 761865, "loss": 2.0414, "lr": 9.204361503156881e-07, "epoch": 2.7307987635604736, "percentage": 18.21, "elapsed_time": "4:41:58", "remaining_time": "21:06:50", "throughput": 8347.66, "total_tokens": 141225992} {"current_steps": 138800, "total_steps": 761865, "loss": 1.9799, "lr": 9.203245227742125e-07, "epoch": 2.7327676163099763, "percentage": 18.22, "elapsed_time": "4:42:10", "remaining_time": "21:06:39", "throughput": 8347.67, "total_tokens": 141328392} {"current_steps": 138900, "total_steps": 761865, "loss": 1.9957, "lr": 9.202128237600969e-07, "epoch": 2.734736469059479, "percentage": 18.23, "elapsed_time": "4:42:22", "remaining_time": "21:06:26", "throughput": 8347.63, "total_tokens": 141429096} {"current_steps": 139000, "total_steps": 761865, "loss": 2.0387, "lr": 9.201010532923349e-07, "epoch": 2.736705321808982, "percentage": 18.24, "elapsed_time": "4:42:34", "remaining_time": "21:06:14", "throughput": 8347.63, "total_tokens": 141530920} {"current_steps": 139100, "total_steps": 761865, "loss": 1.9955, "lr": 9.199892113899322e-07, "epoch": 2.7386741745584846, "percentage": 18.26, "elapsed_time": "4:42:46", "remaining_time": "21:06:02", "throughput": 8347.59, "total_tokens": 141631704} {"current_steps": 139200, "total_steps": 761865, "loss": 1.9765, "lr": 9.198772980719063e-07, "epoch": 2.7406430273079874, "percentage": 18.27, "elapsed_time": "4:42:59", "remaining_time": "21:05:50", "throughput": 8347.59, "total_tokens": 141733880} {"current_steps": 139300, "total_steps": 761865, "loss": 1.9777, "lr": 9.197653133572873e-07, "epoch": 2.7426118800574906, "percentage": 18.28, "elapsed_time": "4:43:11", "remaining_time": "21:05:37", "throughput": 8347.55, "total_tokens": 141834960} {"current_steps": 139400, "total_steps": 761865, "loss": 2.0166, "lr": 9.196532572651172e-07, "epoch": 2.7445807328069933, "percentage": 18.3, "elapsed_time": "4:43:23", "remaining_time": "21:05:25", "throughput": 8347.52, "total_tokens": 141936176} {"current_steps": 139500, "total_steps": 761865, "loss": 1.9442, "lr": 9.195411298144504e-07, "epoch": 2.746549585556496, "percentage": 18.31, "elapsed_time": "4:43:35", "remaining_time": "21:05:13", "throughput": 8347.52, "total_tokens": 142038576} {"current_steps": 139600, "total_steps": 761865, "loss": 1.9608, "lr": 9.194289310243528e-07, "epoch": 2.7485184383059993, "percentage": 18.32, "elapsed_time": "4:43:47", "remaining_time": "21:05:01", "throughput": 8347.48, "total_tokens": 142139456} {"current_steps": 139700, "total_steps": 761865, "loss": 1.9783, "lr": 9.193166609139033e-07, "epoch": 2.750487291055502, "percentage": 18.34, "elapsed_time": "4:44:00", "remaining_time": "21:04:49", "throughput": 8347.48, "total_tokens": 142241856} {"current_steps": 139800, "total_steps": 761865, "loss": 2.0202, "lr": 9.192043195021922e-07, "epoch": 2.752456143805005, "percentage": 18.35, "elapsed_time": "4:44:12", "remaining_time": "21:04:37", "throughput": 8347.49, "total_tokens": 142344256} {"current_steps": 139900, "total_steps": 761865, "loss": 2.0064, "lr": 9.190919068083224e-07, "epoch": 2.7544249965545076, "percentage": 18.36, "elapsed_time": "4:44:24", "remaining_time": "21:04:25", "throughput": 8347.48, "total_tokens": 142446032} {"current_steps": 140000, "total_steps": 761865, "loss": 2.0104, "lr": 9.189794228514085e-07, "epoch": 2.7563938493040103, "percentage": 18.38, "elapsed_time": "4:44:36", "remaining_time": "21:04:13", "throughput": 8347.48, "total_tokens": 142548432} {"current_steps": 140100, "total_steps": 761865, "loss": 1.969, "lr": 9.188668676505777e-07, "epoch": 2.7583627020535135, "percentage": 18.39, "elapsed_time": "4:44:49", "remaining_time": "21:04:03", "throughput": 8347.2, "total_tokens": 142650280} {"current_steps": 140200, "total_steps": 761865, "loss": 1.9908, "lr": 9.187542412249689e-07, "epoch": 2.7603315548030163, "percentage": 18.4, "elapsed_time": "4:45:01", "remaining_time": "21:03:51", "throughput": 8347.19, "total_tokens": 142751704} {"current_steps": 140300, "total_steps": 761865, "loss": 1.9929, "lr": 9.186415435937333e-07, "epoch": 2.762300407552519, "percentage": 18.42, "elapsed_time": "4:45:14", "remaining_time": "21:03:39", "throughput": 8347.2, "total_tokens": 142854104} {"current_steps": 140400, "total_steps": 761865, "loss": 1.9594, "lr": 9.185287747760342e-07, "epoch": 2.7642692603020222, "percentage": 18.43, "elapsed_time": "4:45:26", "remaining_time": "21:03:27", "throughput": 8347.19, "total_tokens": 142955344} {"current_steps": 140500, "total_steps": 761865, "loss": 2.0056, "lr": 9.18415934791047e-07, "epoch": 2.766238113051525, "percentage": 18.44, "elapsed_time": "4:45:38", "remaining_time": "21:03:15", "throughput": 8347.2, "total_tokens": 143057744} {"current_steps": 140600, "total_steps": 761865, "loss": 1.9826, "lr": 9.183030236579591e-07, "epoch": 2.7682069658010278, "percentage": 18.45, "elapsed_time": "4:45:50", "remaining_time": "21:03:03", "throughput": 8347.2, "total_tokens": 143160144} {"current_steps": 140700, "total_steps": 761865, "loss": 2.0148, "lr": 9.181900413959703e-07, "epoch": 2.7701758185505305, "percentage": 18.47, "elapsed_time": "4:46:02", "remaining_time": "21:02:50", "throughput": 8347.17, "total_tokens": 143260632} {"current_steps": 140800, "total_steps": 761865, "loss": 1.9509, "lr": 9.18076988024292e-07, "epoch": 2.7721446713000333, "percentage": 18.48, "elapsed_time": "4:46:15", "remaining_time": "21:02:38", "throughput": 8347.14, "total_tokens": 143362720} {"current_steps": 140900, "total_steps": 761865, "loss": 1.971, "lr": 9.179638635621481e-07, "epoch": 2.7741135240495365, "percentage": 18.49, "elapsed_time": "4:46:27", "remaining_time": "21:02:26", "throughput": 8347.1, "total_tokens": 143463128} {"current_steps": 141000, "total_steps": 761865, "loss": 1.9975, "lr": 9.178506680287746e-07, "epoch": 2.7760823767990392, "percentage": 18.51, "elapsed_time": "4:46:39", "remaining_time": "21:02:14", "throughput": 8347.08, "total_tokens": 143564736} {"current_steps": 141100, "total_steps": 761865, "loss": 1.9718, "lr": 9.177374014434192e-07, "epoch": 2.778051229548542, "percentage": 18.52, "elapsed_time": "4:46:51", "remaining_time": "21:02:01", "throughput": 8347.04, "total_tokens": 143664912} {"current_steps": 141200, "total_steps": 761865, "loss": 1.9747, "lr": 9.176240638253421e-07, "epoch": 2.780020082298045, "percentage": 18.53, "elapsed_time": "4:47:03", "remaining_time": "21:01:49", "throughput": 8347.04, "total_tokens": 143767312} {"current_steps": 141300, "total_steps": 761865, "loss": 1.9852, "lr": 9.175106551938153e-07, "epoch": 2.781988935047548, "percentage": 18.55, "elapsed_time": "4:47:15", "remaining_time": "21:01:37", "throughput": 8347.03, "total_tokens": 143868904} {"current_steps": 141400, "total_steps": 761865, "loss": 1.9941, "lr": 9.173971755681231e-07, "epoch": 2.7839577877970507, "percentage": 18.56, "elapsed_time": "4:47:28", "remaining_time": "21:01:25", "throughput": 8347.03, "total_tokens": 143971304} {"current_steps": 141500, "total_steps": 761865, "loss": 1.9563, "lr": 9.172836249675617e-07, "epoch": 2.7859266405465535, "percentage": 18.57, "elapsed_time": "4:47:40", "remaining_time": "21:01:13", "throughput": 8347.03, "total_tokens": 144073704} {"current_steps": 141600, "total_steps": 761865, "loss": 2.0128, "lr": 9.171700034114394e-07, "epoch": 2.7878954932960562, "percentage": 18.59, "elapsed_time": "4:47:52", "remaining_time": "21:01:01", "throughput": 8347.01, "total_tokens": 144175584} {"current_steps": 141700, "total_steps": 761865, "loss": 2.004, "lr": 9.170563109190766e-07, "epoch": 2.789864346045559, "percentage": 18.6, "elapsed_time": "4:48:04", "remaining_time": "21:00:49", "throughput": 8347.02, "total_tokens": 144277984} {"current_steps": 141800, "total_steps": 761865, "loss": 1.9728, "lr": 9.169425475098056e-07, "epoch": 2.791833198795062, "percentage": 18.61, "elapsed_time": "4:48:17", "remaining_time": "21:00:37", "throughput": 8347.0, "total_tokens": 144379536} {"current_steps": 141900, "total_steps": 761865, "loss": 1.9135, "lr": 9.16828713202971e-07, "epoch": 2.793802051544565, "percentage": 18.63, "elapsed_time": "4:48:29", "remaining_time": "21:00:25", "throughput": 8347.0, "total_tokens": 144481936} {"current_steps": 142000, "total_steps": 761865, "loss": 1.9656, "lr": 9.167148080179297e-07, "epoch": 2.7957709042940677, "percentage": 18.64, "elapsed_time": "4:48:41", "remaining_time": "21:00:13", "throughput": 8347.0, "total_tokens": 144584336} {"current_steps": 142100, "total_steps": 761865, "loss": 1.993, "lr": 9.166008319740499e-07, "epoch": 2.797739757043571, "percentage": 18.65, "elapsed_time": "4:48:53", "remaining_time": "21:00:01", "throughput": 8346.98, "total_tokens": 144685840} {"current_steps": 142200, "total_steps": 761865, "loss": 1.9507, "lr": 9.164867850907124e-07, "epoch": 2.7997086097930737, "percentage": 18.66, "elapsed_time": "4:49:06", "remaining_time": "20:59:49", "throughput": 8346.99, "total_tokens": 144788240} {"current_steps": 142300, "total_steps": 761865, "loss": 1.9942, "lr": 9.1637266738731e-07, "epoch": 2.8016774625425764, "percentage": 18.68, "elapsed_time": "4:49:18", "remaining_time": "20:59:37", "throughput": 8346.98, "total_tokens": 144889976} {"current_steps": 142400, "total_steps": 761865, "loss": 2.0297, "lr": 9.162584788832473e-07, "epoch": 2.803646315292079, "percentage": 18.69, "elapsed_time": "4:49:30", "remaining_time": "20:59:25", "throughput": 8346.99, "total_tokens": 144992376} {"current_steps": 142500, "total_steps": 761865, "loss": 2.0164, "lr": 9.16144219597941e-07, "epoch": 2.805615168041582, "percentage": 18.7, "elapsed_time": "4:49:42", "remaining_time": "20:59:13", "throughput": 8346.99, "total_tokens": 145094776} {"current_steps": 142600, "total_steps": 761865, "loss": 1.948, "lr": 9.160298895508202e-07, "epoch": 2.807584020791085, "percentage": 18.72, "elapsed_time": "4:49:55", "remaining_time": "20:59:00", "throughput": 8346.95, "total_tokens": 145195616} {"current_steps": 142700, "total_steps": 761865, "loss": 1.9702, "lr": 9.159154887613257e-07, "epoch": 2.809552873540588, "percentage": 18.73, "elapsed_time": "4:50:07", "remaining_time": "20:58:49", "throughput": 8346.95, "total_tokens": 145298016} {"current_steps": 142800, "total_steps": 761865, "loss": 1.9656, "lr": 9.158010172489102e-07, "epoch": 2.8115217262900907, "percentage": 18.74, "elapsed_time": "4:50:19", "remaining_time": "20:58:37", "throughput": 8346.95, "total_tokens": 145400416} {"current_steps": 142900, "total_steps": 761865, "loss": 1.9631, "lr": 9.156864750330389e-07, "epoch": 2.813490579039594, "percentage": 18.76, "elapsed_time": "4:50:31", "remaining_time": "20:58:25", "throughput": 8346.96, "total_tokens": 145502816} {"current_steps": 143000, "total_steps": 761865, "loss": 1.9819, "lr": 9.155718621331885e-07, "epoch": 2.8154594317890966, "percentage": 18.77, "elapsed_time": "4:50:44", "remaining_time": "20:58:13", "throughput": 8346.97, "total_tokens": 145605216} {"current_steps": 143100, "total_steps": 761865, "loss": 2.0453, "lr": 9.15457178568848e-07, "epoch": 2.8174282845385994, "percentage": 18.78, "elapsed_time": "4:50:56", "remaining_time": "20:58:01", "throughput": 8346.97, "total_tokens": 145707616} {"current_steps": 143200, "total_steps": 761865, "loss": 1.9449, "lr": 9.153424243595185e-07, "epoch": 2.819397137288102, "percentage": 18.8, "elapsed_time": "4:51:08", "remaining_time": "20:57:49", "throughput": 8346.98, "total_tokens": 145810016} {"current_steps": 143300, "total_steps": 761865, "loss": 1.9548, "lr": 9.152275995247128e-07, "epoch": 2.821365990037605, "percentage": 18.81, "elapsed_time": "4:51:20", "remaining_time": "20:57:37", "throughput": 8346.98, "total_tokens": 145912416} {"current_steps": 143400, "total_steps": 761865, "loss": 1.9784, "lr": 9.15112704083956e-07, "epoch": 2.823334842787108, "percentage": 18.82, "elapsed_time": "4:51:33", "remaining_time": "20:57:25", "throughput": 8346.97, "total_tokens": 146013976} {"current_steps": 143500, "total_steps": 761865, "loss": 2.0034, "lr": 9.149977380567852e-07, "epoch": 2.825303695536611, "percentage": 18.84, "elapsed_time": "4:51:45", "remaining_time": "20:57:13", "throughput": 8346.97, "total_tokens": 146115888} {"current_steps": 143600, "total_steps": 761865, "loss": 1.9587, "lr": 9.148827014627492e-07, "epoch": 2.8272725482861136, "percentage": 18.85, "elapsed_time": "4:51:57", "remaining_time": "20:57:01", "throughput": 8346.97, "total_tokens": 146218288} {"current_steps": 143700, "total_steps": 761865, "loss": 1.9649, "lr": 9.147675943214091e-07, "epoch": 2.8292414010356164, "percentage": 18.86, "elapsed_time": "4:52:09", "remaining_time": "20:56:49", "throughput": 8346.98, "total_tokens": 146320688} {"current_steps": 143800, "total_steps": 761865, "loss": 2.0627, "lr": 9.14652416652338e-07, "epoch": 2.8312102537851196, "percentage": 18.87, "elapsed_time": "4:52:21", "remaining_time": "20:56:36", "throughput": 8346.97, "total_tokens": 146422056} {"current_steps": 143900, "total_steps": 761865, "loss": 1.9678, "lr": 9.145371684751206e-07, "epoch": 2.8331791065346223, "percentage": 18.89, "elapsed_time": "4:52:34", "remaining_time": "20:56:24", "throughput": 8346.97, "total_tokens": 146523976} {"current_steps": 144000, "total_steps": 761865, "loss": 1.9528, "lr": 9.144218498093541e-07, "epoch": 2.835147959284125, "percentage": 18.9, "elapsed_time": "4:52:46", "remaining_time": "20:56:12", "throughput": 8346.97, "total_tokens": 146626376} {"current_steps": 144100, "total_steps": 761865, "loss": 1.9807, "lr": 9.143064606746476e-07, "epoch": 2.837116812033628, "percentage": 18.91, "elapsed_time": "4:52:58", "remaining_time": "20:56:00", "throughput": 8346.98, "total_tokens": 146728776} {"current_steps": 144200, "total_steps": 761865, "loss": 2.0446, "lr": 9.141910010906218e-07, "epoch": 2.8390856647831306, "percentage": 18.93, "elapsed_time": "4:53:10", "remaining_time": "20:55:48", "throughput": 8346.96, "total_tokens": 146830576} {"current_steps": 144300, "total_steps": 761865, "loss": 1.9862, "lr": 9.140754710769097e-07, "epoch": 2.841054517532634, "percentage": 18.94, "elapsed_time": "4:53:23", "remaining_time": "20:55:36", "throughput": 8346.97, "total_tokens": 146932976} {"current_steps": 144400, "total_steps": 761865, "loss": 1.9735, "lr": 9.139598706531562e-07, "epoch": 2.8430233702821366, "percentage": 18.95, "elapsed_time": "4:53:35", "remaining_time": "20:55:24", "throughput": 8346.96, "total_tokens": 147034608} {"current_steps": 144500, "total_steps": 761865, "loss": 2.0029, "lr": 9.138441998390183e-07, "epoch": 2.8449922230316393, "percentage": 18.97, "elapsed_time": "4:53:47", "remaining_time": "20:55:12", "throughput": 8346.94, "total_tokens": 147135624} {"current_steps": 144600, "total_steps": 761865, "loss": 1.9741, "lr": 9.137284586541646e-07, "epoch": 2.8469610757811425, "percentage": 18.98, "elapsed_time": "4:53:59", "remaining_time": "20:55:00", "throughput": 8346.95, "total_tokens": 147238024} {"current_steps": 144700, "total_steps": 761865, "loss": 1.9228, "lr": 9.136126471182761e-07, "epoch": 2.8489299285306453, "percentage": 18.99, "elapsed_time": "4:54:11", "remaining_time": "20:54:47", "throughput": 8346.91, "total_tokens": 147338480} {"current_steps": 144800, "total_steps": 761865, "loss": 1.9574, "lr": 9.134967652510456e-07, "epoch": 2.850898781280148, "percentage": 19.01, "elapsed_time": "4:54:24", "remaining_time": "20:54:35", "throughput": 8346.87, "total_tokens": 147440360} {"current_steps": 144900, "total_steps": 761865, "loss": 2.0137, "lr": 9.133808130721777e-07, "epoch": 2.852867634029651, "percentage": 19.02, "elapsed_time": "4:54:36", "remaining_time": "20:54:23", "throughput": 8346.86, "total_tokens": 147542072} {"current_steps": 145000, "total_steps": 761865, "loss": 1.952, "lr": 9.13264790601389e-07, "epoch": 2.8548364867791536, "percentage": 19.03, "elapsed_time": "4:54:48", "remaining_time": "20:54:11", "throughput": 8346.86, "total_tokens": 147644472} {"current_steps": 145100, "total_steps": 761865, "loss": 2.0197, "lr": 9.131486978584085e-07, "epoch": 2.856805339528657, "percentage": 19.05, "elapsed_time": "4:55:01", "remaining_time": "20:54:02", "throughput": 8346.6, "total_tokens": 147746872} {"current_steps": 145200, "total_steps": 761865, "loss": 1.9374, "lr": 9.130325348629766e-07, "epoch": 2.8587741922781595, "percentage": 19.06, "elapsed_time": "4:55:13", "remaining_time": "20:53:50", "throughput": 8346.61, "total_tokens": 147849272} {"current_steps": 145300, "total_steps": 761865, "loss": 1.9459, "lr": 9.129163016348458e-07, "epoch": 2.8607430450276623, "percentage": 19.07, "elapsed_time": "4:55:25", "remaining_time": "20:53:38", "throughput": 8346.61, "total_tokens": 147951672} {"current_steps": 145400, "total_steps": 761865, "loss": 1.9606, "lr": 9.127999981937806e-07, "epoch": 2.8627118977771655, "percentage": 19.08, "elapsed_time": "4:55:38", "remaining_time": "20:53:26", "throughput": 8346.62, "total_tokens": 148054072} {"current_steps": 145500, "total_steps": 761865, "loss": 2.0163, "lr": 9.126836245595572e-07, "epoch": 2.8646807505266683, "percentage": 19.1, "elapsed_time": "4:55:50", "remaining_time": "20:53:14", "throughput": 8346.62, "total_tokens": 148156472} {"current_steps": 145600, "total_steps": 761865, "loss": 1.9884, "lr": 9.125671807519644e-07, "epoch": 2.866649603276171, "percentage": 19.11, "elapsed_time": "4:56:02", "remaining_time": "20:53:01", "throughput": 8346.6, "total_tokens": 148257416} {"current_steps": 145700, "total_steps": 761865, "loss": 2.0125, "lr": 9.124506667908023e-07, "epoch": 2.868618456025674, "percentage": 19.12, "elapsed_time": "4:56:14", "remaining_time": "20:52:49", "throughput": 8346.61, "total_tokens": 148359816} {"current_steps": 145800, "total_steps": 761865, "loss": 1.9562, "lr": 9.12334082695883e-07, "epoch": 2.8705873087751765, "percentage": 19.14, "elapsed_time": "4:56:27", "remaining_time": "20:52:37", "throughput": 8346.62, "total_tokens": 148462216} {"current_steps": 145900, "total_steps": 761865, "loss": 1.9803, "lr": 9.122174284870307e-07, "epoch": 2.8725561615246793, "percentage": 19.15, "elapsed_time": "4:56:39", "remaining_time": "20:52:25", "throughput": 8346.61, "total_tokens": 148563888} {"current_steps": 146000, "total_steps": 761865, "loss": 1.9816, "lr": 9.121007041840816e-07, "epoch": 2.8745250142741825, "percentage": 19.16, "elapsed_time": "4:56:51", "remaining_time": "20:52:13", "throughput": 8346.61, "total_tokens": 148665624} {"current_steps": 146100, "total_steps": 761865, "loss": 2.0486, "lr": 9.119839098068835e-07, "epoch": 2.8764938670236853, "percentage": 19.18, "elapsed_time": "4:57:03", "remaining_time": "20:52:00", "throughput": 8346.6, "total_tokens": 148766752} {"current_steps": 146200, "total_steps": 761865, "loss": 1.9396, "lr": 9.118670453752964e-07, "epoch": 2.878462719773188, "percentage": 19.19, "elapsed_time": "4:57:15", "remaining_time": "20:51:48", "throughput": 8346.59, "total_tokens": 148868736} {"current_steps": 146300, "total_steps": 761865, "loss": 1.9396, "lr": 9.11750110909192e-07, "epoch": 2.880431572522691, "percentage": 19.2, "elapsed_time": "4:57:28", "remaining_time": "20:51:36", "throughput": 8346.6, "total_tokens": 148971136} {"current_steps": 146400, "total_steps": 761865, "loss": 2.0412, "lr": 9.116331064284542e-07, "epoch": 2.882400425272194, "percentage": 19.22, "elapsed_time": "4:57:40", "remaining_time": "20:51:24", "throughput": 8346.56, "total_tokens": 149071728} {"current_steps": 146500, "total_steps": 761865, "loss": 2.0356, "lr": 9.115160319529783e-07, "epoch": 2.8843692780216967, "percentage": 19.23, "elapsed_time": "4:57:52", "remaining_time": "20:51:12", "throughput": 8346.55, "total_tokens": 149173560} {"current_steps": 146600, "total_steps": 761865, "loss": 2.0333, "lr": 9.113988875026724e-07, "epoch": 2.8863381307711995, "percentage": 19.24, "elapsed_time": "4:58:04", "remaining_time": "20:51:00", "throughput": 8346.54, "total_tokens": 149275328} {"current_steps": 146700, "total_steps": 761865, "loss": 1.964, "lr": 9.112816730974552e-07, "epoch": 2.8883069835207023, "percentage": 19.26, "elapsed_time": "4:58:16", "remaining_time": "20:50:47", "throughput": 8346.52, "total_tokens": 149376408} {"current_steps": 146800, "total_steps": 761865, "loss": 1.9503, "lr": 9.111643887572586e-07, "epoch": 2.8902758362702055, "percentage": 19.27, "elapsed_time": "4:58:29", "remaining_time": "20:50:35", "throughput": 8346.51, "total_tokens": 149478104} {"current_steps": 146900, "total_steps": 761865, "loss": 1.9369, "lr": 9.110470345020257e-07, "epoch": 2.892244689019708, "percentage": 19.28, "elapsed_time": "4:58:41", "remaining_time": "20:50:23", "throughput": 8346.5, "total_tokens": 149579984} {"current_steps": 147000, "total_steps": 761865, "loss": 2.013, "lr": 9.109296103517115e-07, "epoch": 2.894213541769211, "percentage": 19.29, "elapsed_time": "4:58:53", "remaining_time": "20:50:11", "throughput": 8346.51, "total_tokens": 149682384} {"current_steps": 147100, "total_steps": 761865, "loss": 1.9916, "lr": 9.10812116326283e-07, "epoch": 2.896182394518714, "percentage": 19.31, "elapsed_time": "4:59:05", "remaining_time": "20:49:59", "throughput": 8346.51, "total_tokens": 149784784} {"current_steps": 147200, "total_steps": 761865, "loss": 1.9398, "lr": 9.10694552445719e-07, "epoch": 2.898151247268217, "percentage": 19.32, "elapsed_time": "4:59:18", "remaining_time": "20:49:47", "throughput": 8346.52, "total_tokens": 149887184} {"current_steps": 147300, "total_steps": 761865, "loss": 2.0205, "lr": 9.105769187300102e-07, "epoch": 2.9001201000177197, "percentage": 19.33, "elapsed_time": "4:59:30", "remaining_time": "20:49:35", "throughput": 8346.52, "total_tokens": 149989584} {"current_steps": 147400, "total_steps": 761865, "loss": 2.0266, "lr": 9.104592151991594e-07, "epoch": 2.9020889527672225, "percentage": 19.35, "elapsed_time": "4:59:42", "remaining_time": "20:49:23", "throughput": 8346.48, "total_tokens": 150090624} {"current_steps": 147500, "total_steps": 761865, "loss": 1.9608, "lr": 9.103414418731811e-07, "epoch": 2.904057805516725, "percentage": 19.36, "elapsed_time": "4:59:54", "remaining_time": "20:49:11", "throughput": 8346.49, "total_tokens": 150193024} {"current_steps": 147600, "total_steps": 761865, "loss": 1.9864, "lr": 9.102235987721016e-07, "epoch": 2.9060266582662284, "percentage": 19.37, "elapsed_time": "5:00:06", "remaining_time": "20:48:59", "throughput": 8346.48, "total_tokens": 150294872} {"current_steps": 147700, "total_steps": 761865, "loss": 1.9823, "lr": 9.10105685915959e-07, "epoch": 2.907995511015731, "percentage": 19.39, "elapsed_time": "5:00:19", "remaining_time": "20:48:47", "throughput": 8346.47, "total_tokens": 150396128} {"current_steps": 147800, "total_steps": 761865, "loss": 1.9702, "lr": 9.099877033248036e-07, "epoch": 2.909964363765234, "percentage": 19.4, "elapsed_time": "5:00:31", "remaining_time": "20:48:34", "throughput": 8346.46, "total_tokens": 150497856} {"current_steps": 147900, "total_steps": 761865, "loss": 1.9961, "lr": 9.098696510186973e-07, "epoch": 2.911933216514737, "percentage": 19.41, "elapsed_time": "5:00:43", "remaining_time": "20:48:22", "throughput": 8346.46, "total_tokens": 150599704} {"current_steps": 148000, "total_steps": 761865, "loss": 1.9562, "lr": 9.097515290177138e-07, "epoch": 2.91390206926424, "percentage": 19.43, "elapsed_time": "5:00:55", "remaining_time": "20:48:10", "throughput": 8346.45, "total_tokens": 150701416} {"current_steps": 148100, "total_steps": 761865, "loss": 1.9961, "lr": 9.096333373419387e-07, "epoch": 2.9158709220137426, "percentage": 19.44, "elapsed_time": "5:01:07", "remaining_time": "20:47:58", "throughput": 8346.46, "total_tokens": 150803816} {"current_steps": 148200, "total_steps": 761865, "loss": 2.0, "lr": 9.095150760114696e-07, "epoch": 2.9178397747632454, "percentage": 19.45, "elapsed_time": "5:01:20", "remaining_time": "20:47:46", "throughput": 8346.47, "total_tokens": 150906216} {"current_steps": 148300, "total_steps": 761865, "loss": 1.9633, "lr": 9.093967450464159e-07, "epoch": 2.919808627512748, "percentage": 19.47, "elapsed_time": "5:01:32", "remaining_time": "20:47:34", "throughput": 8346.47, "total_tokens": 151007952} {"current_steps": 148400, "total_steps": 761865, "loss": 1.9963, "lr": 9.092783444668988e-07, "epoch": 2.921777480262251, "percentage": 19.48, "elapsed_time": "5:01:44", "remaining_time": "20:47:22", "throughput": 8346.47, "total_tokens": 151110080} {"current_steps": 148500, "total_steps": 761865, "loss": 1.9978, "lr": 9.091598742930511e-07, "epoch": 2.923746333011754, "percentage": 19.49, "elapsed_time": "5:01:56", "remaining_time": "20:47:10", "throughput": 8346.47, "total_tokens": 151212480} {"current_steps": 148600, "total_steps": 761865, "loss": 1.9963, "lr": 9.090413345450179e-07, "epoch": 2.925715185761257, "percentage": 19.5, "elapsed_time": "5:02:09", "remaining_time": "20:46:58", "throughput": 8346.46, "total_tokens": 151314568} {"current_steps": 148700, "total_steps": 761865, "loss": 2.0069, "lr": 9.089227252429557e-07, "epoch": 2.9276840385107596, "percentage": 19.52, "elapsed_time": "5:02:21", "remaining_time": "20:46:46", "throughput": 8346.45, "total_tokens": 151416344} {"current_steps": 148800, "total_steps": 761865, "loss": 2.0032, "lr": 9.08804046407033e-07, "epoch": 2.929652891260263, "percentage": 19.53, "elapsed_time": "5:02:33", "remaining_time": "20:46:33", "throughput": 8346.45, "total_tokens": 151518016} {"current_steps": 148900, "total_steps": 761865, "loss": 1.9748, "lr": 9.086852980574303e-07, "epoch": 2.9316217440097656, "percentage": 19.54, "elapsed_time": "5:02:45", "remaining_time": "20:46:21", "throughput": 8346.44, "total_tokens": 151619704} {"current_steps": 149000, "total_steps": 761865, "loss": 1.9605, "lr": 9.085664802143397e-07, "epoch": 2.9335905967592684, "percentage": 19.56, "elapsed_time": "5:02:58", "remaining_time": "20:46:09", "throughput": 8346.45, "total_tokens": 151722104} {"current_steps": 149100, "total_steps": 761865, "loss": 1.9814, "lr": 9.084475928979652e-07, "epoch": 2.935559449508771, "percentage": 19.57, "elapsed_time": "5:03:10", "remaining_time": "20:45:57", "throughput": 8346.44, "total_tokens": 151823880} {"current_steps": 149200, "total_steps": 761865, "loss": 1.9943, "lr": 9.083286361285225e-07, "epoch": 2.937528302258274, "percentage": 19.58, "elapsed_time": "5:03:22", "remaining_time": "20:45:45", "throughput": 8346.42, "total_tokens": 151925528} {"current_steps": 149300, "total_steps": 761865, "loss": 1.952, "lr": 9.082096099262391e-07, "epoch": 2.939497155007777, "percentage": 19.6, "elapsed_time": "5:03:34", "remaining_time": "20:45:33", "throughput": 8346.42, "total_tokens": 152027928} {"current_steps": 149400, "total_steps": 761865, "loss": 1.9856, "lr": 9.080905143113546e-07, "epoch": 2.94146600775728, "percentage": 19.61, "elapsed_time": "5:03:46", "remaining_time": "20:45:21", "throughput": 8346.39, "total_tokens": 152128712} {"current_steps": 149500, "total_steps": 761865, "loss": 1.9416, "lr": 9.079713493041203e-07, "epoch": 2.9434348605067826, "percentage": 19.62, "elapsed_time": "5:03:59", "remaining_time": "20:45:09", "throughput": 8346.4, "total_tokens": 152231112} {"current_steps": 149600, "total_steps": 761865, "loss": 1.925, "lr": 9.078521149247989e-07, "epoch": 2.945403713256286, "percentage": 19.64, "elapsed_time": "5:04:11", "remaining_time": "20:44:56", "throughput": 8346.37, "total_tokens": 152332144} {"current_steps": 149700, "total_steps": 761865, "loss": 1.9684, "lr": 9.077328111936653e-07, "epoch": 2.9473725660057886, "percentage": 19.65, "elapsed_time": "5:04:23", "remaining_time": "20:44:44", "throughput": 8346.36, "total_tokens": 152433712} {"current_steps": 149800, "total_steps": 761865, "loss": 1.9728, "lr": 9.076134381310061e-07, "epoch": 2.9493414187552913, "percentage": 19.66, "elapsed_time": "5:04:35", "remaining_time": "20:44:32", "throughput": 8346.36, "total_tokens": 152536112} {"current_steps": 149900, "total_steps": 761865, "loss": 1.963, "lr": 9.074939957571199e-07, "epoch": 2.951310271504794, "percentage": 19.68, "elapsed_time": "5:04:47", "remaining_time": "20:44:20", "throughput": 8346.35, "total_tokens": 152637648} {"current_steps": 150000, "total_steps": 761865, "loss": 1.9787, "lr": 9.073744840923165e-07, "epoch": 2.953279124254297, "percentage": 19.69, "elapsed_time": "5:05:00", "remaining_time": "20:44:08", "throughput": 8346.35, "total_tokens": 152740048} {"current_steps": 150100, "total_steps": 761865, "loss": 1.9894, "lr": 9.072549031569181e-07, "epoch": 2.9552479770038, "percentage": 19.7, "elapsed_time": "5:05:12", "remaining_time": "20:43:58", "throughput": 8346.1, "total_tokens": 152841808} {"current_steps": 150200, "total_steps": 761865, "loss": 1.9597, "lr": 9.071352529712584e-07, "epoch": 2.957216829753303, "percentage": 19.71, "elapsed_time": "5:05:25", "remaining_time": "20:43:46", "throughput": 8346.11, "total_tokens": 152944208} {"current_steps": 150300, "total_steps": 761865, "loss": 1.9777, "lr": 9.070155335556828e-07, "epoch": 2.9591856825028056, "percentage": 19.73, "elapsed_time": "5:05:37", "remaining_time": "20:43:34", "throughput": 8346.09, "total_tokens": 153045376} {"current_steps": 150400, "total_steps": 761865, "loss": 1.9811, "lr": 9.068957449305488e-07, "epoch": 2.9611545352523083, "percentage": 19.74, "elapsed_time": "5:05:49", "remaining_time": "20:43:22", "throughput": 8346.09, "total_tokens": 153147776} {"current_steps": 150500, "total_steps": 761865, "loss": 2.0175, "lr": 9.067758871162252e-07, "epoch": 2.9631233880018115, "percentage": 19.75, "elapsed_time": "5:06:01", "remaining_time": "20:43:09", "throughput": 8346.07, "total_tokens": 153248736} {"current_steps": 150600, "total_steps": 761865, "loss": 1.9907, "lr": 9.066559601330929e-07, "epoch": 2.9650922407513143, "percentage": 19.77, "elapsed_time": "5:06:14", "remaining_time": "20:42:57", "throughput": 8346.07, "total_tokens": 153351136} {"current_steps": 150700, "total_steps": 761865, "loss": 2.0143, "lr": 9.065359640015444e-07, "epoch": 2.967061093500817, "percentage": 19.78, "elapsed_time": "5:06:26", "remaining_time": "20:42:45", "throughput": 8346.06, "total_tokens": 153453464} {"current_steps": 150800, "total_steps": 761865, "loss": 1.9579, "lr": 9.064158987419842e-07, "epoch": 2.96902994625032, "percentage": 19.79, "elapsed_time": "5:06:38", "remaining_time": "20:42:33", "throughput": 8346.06, "total_tokens": 153555360} {"current_steps": 150900, "total_steps": 761865, "loss": 2.006, "lr": 9.062957643748284e-07, "epoch": 2.9709987989998226, "percentage": 19.81, "elapsed_time": "5:06:50", "remaining_time": "20:42:21", "throughput": 8346.06, "total_tokens": 153657760} {"current_steps": 151000, "total_steps": 761865, "loss": 1.999, "lr": 9.061755609205044e-07, "epoch": 2.9729676517493258, "percentage": 19.82, "elapsed_time": "5:07:02", "remaining_time": "20:42:09", "throughput": 8346.01, "total_tokens": 153757472} {"current_steps": 151100, "total_steps": 761865, "loss": 1.9399, "lr": 9.060552883994524e-07, "epoch": 2.9749365044988285, "percentage": 19.83, "elapsed_time": "5:07:15", "remaining_time": "20:41:56", "throughput": 8345.98, "total_tokens": 153858400} {"current_steps": 151200, "total_steps": 761865, "loss": 1.9781, "lr": 9.059349468321234e-07, "epoch": 2.9769053572483313, "percentage": 19.85, "elapsed_time": "5:07:27", "remaining_time": "20:41:44", "throughput": 8345.97, "total_tokens": 153960240} {"current_steps": 151300, "total_steps": 761865, "loss": 1.9746, "lr": 9.058145362389804e-07, "epoch": 2.9788742099978345, "percentage": 19.86, "elapsed_time": "5:07:39", "remaining_time": "20:41:32", "throughput": 8345.94, "total_tokens": 154061192} {"current_steps": 151400, "total_steps": 761865, "loss": 1.9691, "lr": 9.056940566404983e-07, "epoch": 2.9808430627473372, "percentage": 19.87, "elapsed_time": "5:07:51", "remaining_time": "20:41:20", "throughput": 8345.93, "total_tokens": 154162960} {"current_steps": 151500, "total_steps": 761865, "loss": 2.0362, "lr": 9.055735080571636e-07, "epoch": 2.98281191549684, "percentage": 19.89, "elapsed_time": "5:08:03", "remaining_time": "20:41:07", "throughput": 8345.89, "total_tokens": 154263232} {"current_steps": 151600, "total_steps": 761865, "loss": 1.9895, "lr": 9.054528905094747e-07, "epoch": 2.9847807682463428, "percentage": 19.9, "elapsed_time": "5:08:15", "remaining_time": "20:40:54", "throughput": 8345.84, "total_tokens": 154363224} {"current_steps": 151700, "total_steps": 761865, "loss": 1.9955, "lr": 9.053322040179416e-07, "epoch": 2.9867496209958455, "percentage": 19.91, "elapsed_time": "5:08:28", "remaining_time": "20:40:42", "throughput": 8345.82, "total_tokens": 154464776} {"current_steps": 151800, "total_steps": 761865, "loss": 1.966, "lr": 9.052114486030859e-07, "epoch": 2.9887184737453487, "percentage": 19.92, "elapsed_time": "5:08:40", "remaining_time": "20:40:30", "throughput": 8345.81, "total_tokens": 154566408} {"current_steps": 151900, "total_steps": 761865, "loss": 1.9901, "lr": 9.05090624285441e-07, "epoch": 2.9906873264948515, "percentage": 19.94, "elapsed_time": "5:08:52", "remaining_time": "20:40:18", "throughput": 8345.8, "total_tokens": 154667800} {"current_steps": 152000, "total_steps": 761865, "loss": 1.9483, "lr": 9.049697310855521e-07, "epoch": 2.9926561792443542, "percentage": 19.95, "elapsed_time": "5:09:04", "remaining_time": "20:40:06", "throughput": 8345.8, "total_tokens": 154770200} {"current_steps": 152100, "total_steps": 761865, "loss": 1.9753, "lr": 9.048487690239763e-07, "epoch": 2.9946250319938574, "percentage": 19.96, "elapsed_time": "5:09:16", "remaining_time": "20:39:54", "throughput": 8345.8, "total_tokens": 154872600} {"current_steps": 152200, "total_steps": 761865, "loss": 2.0067, "lr": 9.047277381212819e-07, "epoch": 2.99659388474336, "percentage": 19.98, "elapsed_time": "5:09:29", "remaining_time": "20:39:42", "throughput": 8345.78, "total_tokens": 154974128} {"current_steps": 152300, "total_steps": 761865, "loss": 1.9883, "lr": 9.046066383980491e-07, "epoch": 2.998562737492863, "percentage": 19.99, "elapsed_time": "5:09:41", "remaining_time": "20:39:29", "throughput": 8345.75, "total_tokens": 155074968} {"current_steps": 152400, "total_steps": 761865, "loss": 1.9731, "lr": 9.044854698748703e-07, "epoch": 3.0005315902423657, "percentage": 20.0, "elapsed_time": "5:09:53", "remaining_time": "20:39:17", "throughput": 8345.72, "total_tokens": 155175984} {"current_steps": 152500, "total_steps": 761865, "loss": 1.9718, "lr": 9.043642325723488e-07, "epoch": 3.0025004429918685, "percentage": 20.02, "elapsed_time": "5:10:05", "remaining_time": "20:39:05", "throughput": 8345.71, "total_tokens": 155277776} {"current_steps": 152600, "total_steps": 761865, "loss": 1.9881, "lr": 9.042429265111e-07, "epoch": 3.0044692957413717, "percentage": 20.03, "elapsed_time": "5:10:17", "remaining_time": "20:38:53", "throughput": 8345.71, "total_tokens": 155380176} {"current_steps": 152700, "total_steps": 761865, "loss": 1.9728, "lr": 9.041215517117513e-07, "epoch": 3.0064381484908744, "percentage": 20.04, "elapsed_time": "5:10:30", "remaining_time": "20:38:41", "throughput": 8345.72, "total_tokens": 155482576} {"current_steps": 152800, "total_steps": 761865, "loss": 1.9748, "lr": 9.040001081949412e-07, "epoch": 3.008407001240377, "percentage": 20.06, "elapsed_time": "5:10:42", "remaining_time": "20:38:29", "throughput": 8345.72, "total_tokens": 155584976} {"current_steps": 152900, "total_steps": 761865, "loss": 1.9952, "lr": 9.038785959813201e-07, "epoch": 3.01037585398988, "percentage": 20.07, "elapsed_time": "5:10:54", "remaining_time": "20:38:17", "throughput": 8345.73, "total_tokens": 155687376} {"current_steps": 153000, "total_steps": 761865, "loss": 1.9616, "lr": 9.037570150915502e-07, "epoch": 3.012344706739383, "percentage": 20.08, "elapsed_time": "5:11:06", "remaining_time": "20:38:05", "throughput": 8345.73, "total_tokens": 155789776} {"current_steps": 153100, "total_steps": 761865, "loss": 2.0036, "lr": 9.036353655463054e-07, "epoch": 3.014313559488886, "percentage": 20.1, "elapsed_time": "5:11:19", "remaining_time": "20:37:53", "throughput": 8345.74, "total_tokens": 155892176} {"current_steps": 153200, "total_steps": 761865, "loss": 1.9263, "lr": 9.035136473662712e-07, "epoch": 3.0162824122383887, "percentage": 20.11, "elapsed_time": "5:11:31", "remaining_time": "20:37:41", "throughput": 8345.74, "total_tokens": 155994096} {"current_steps": 153300, "total_steps": 761865, "loss": 1.9592, "lr": 9.033918605721445e-07, "epoch": 3.0182512649878914, "percentage": 20.12, "elapsed_time": "5:11:43", "remaining_time": "20:37:29", "throughput": 8345.75, "total_tokens": 156096496} {"current_steps": 153400, "total_steps": 761865, "loss": 1.9663, "lr": 9.032700051846345e-07, "epoch": 3.0202201177373946, "percentage": 20.13, "elapsed_time": "5:11:55", "remaining_time": "20:37:17", "throughput": 8345.74, "total_tokens": 156198120} {"current_steps": 153500, "total_steps": 761865, "loss": 2.0058, "lr": 9.031480812244612e-07, "epoch": 3.0221889704868974, "percentage": 20.15, "elapsed_time": "5:12:08", "remaining_time": "20:37:04", "throughput": 8345.7, "total_tokens": 156298320} {"current_steps": 153600, "total_steps": 761865, "loss": 1.943, "lr": 9.030260887123571e-07, "epoch": 3.0241578232364, "percentage": 20.16, "elapsed_time": "5:12:20", "remaining_time": "20:36:52", "throughput": 8345.69, "total_tokens": 156399448} {"current_steps": 153700, "total_steps": 761865, "loss": 2.0275, "lr": 9.029040276690658e-07, "epoch": 3.026126675985903, "percentage": 20.17, "elapsed_time": "5:12:32", "remaining_time": "20:36:39", "throughput": 8345.69, "total_tokens": 156500760} {"current_steps": 153800, "total_steps": 761865, "loss": 1.95, "lr": 9.02781898115343e-07, "epoch": 3.0280955287354057, "percentage": 20.19, "elapsed_time": "5:12:44", "remaining_time": "20:36:27", "throughput": 8345.69, "total_tokens": 156603160} {"current_steps": 153900, "total_steps": 761865, "loss": 1.9866, "lr": 9.026597000719555e-07, "epoch": 3.030064381484909, "percentage": 20.2, "elapsed_time": "5:12:56", "remaining_time": "20:36:15", "throughput": 8345.7, "total_tokens": 156705560} {"current_steps": 154000, "total_steps": 761865, "loss": 1.9878, "lr": 9.025374335596824e-07, "epoch": 3.0320332342344116, "percentage": 20.21, "elapsed_time": "5:13:09", "remaining_time": "20:36:03", "throughput": 8345.71, "total_tokens": 156807512} {"current_steps": 154100, "total_steps": 761865, "loss": 2.004, "lr": 9.024150985993138e-07, "epoch": 3.0340020869839144, "percentage": 20.23, "elapsed_time": "5:13:21", "remaining_time": "20:35:50", "throughput": 8345.68, "total_tokens": 156907672} {"current_steps": 154200, "total_steps": 761865, "loss": 1.9728, "lr": 9.022926952116516e-07, "epoch": 3.035970939733417, "percentage": 20.24, "elapsed_time": "5:13:33", "remaining_time": "20:35:38", "throughput": 8345.69, "total_tokens": 157010072} {"current_steps": 154300, "total_steps": 761865, "loss": 1.9871, "lr": 9.0217022341751e-07, "epoch": 3.0379397924829203, "percentage": 20.25, "elapsed_time": "5:13:45", "remaining_time": "20:35:26", "throughput": 8345.69, "total_tokens": 157112472} {"current_steps": 154400, "total_steps": 761865, "loss": 1.9695, "lr": 9.020476832377137e-07, "epoch": 3.039908645232423, "percentage": 20.27, "elapsed_time": "5:13:57", "remaining_time": "20:35:14", "throughput": 8345.69, "total_tokens": 157214872} {"current_steps": 154500, "total_steps": 761865, "loss": 1.9509, "lr": 9.019250746931e-07, "epoch": 3.041877497981926, "percentage": 20.28, "elapsed_time": "5:14:10", "remaining_time": "20:35:02", "throughput": 8345.67, "total_tokens": 157316408} {"current_steps": 154600, "total_steps": 761865, "loss": 1.9725, "lr": 9.018023978045173e-07, "epoch": 3.0438463507314286, "percentage": 20.29, "elapsed_time": "5:14:22", "remaining_time": "20:34:50", "throughput": 8345.66, "total_tokens": 157418208} {"current_steps": 154700, "total_steps": 761865, "loss": 1.989, "lr": 9.016796525928258e-07, "epoch": 3.045815203480932, "percentage": 20.31, "elapsed_time": "5:14:34", "remaining_time": "20:34:38", "throughput": 8345.64, "total_tokens": 157519448} {"current_steps": 154800, "total_steps": 761865, "loss": 2.0155, "lr": 9.015568390788974e-07, "epoch": 3.0477840562304346, "percentage": 20.32, "elapsed_time": "5:14:46", "remaining_time": "20:34:26", "throughput": 8345.62, "total_tokens": 157620976} {"current_steps": 154900, "total_steps": 761865, "loss": 2.0194, "lr": 9.014339572836153e-07, "epoch": 3.0497529089799373, "percentage": 20.33, "elapsed_time": "5:14:58", "remaining_time": "20:34:13", "throughput": 8345.63, "total_tokens": 157722760} {"current_steps": 155000, "total_steps": 761865, "loss": 1.9585, "lr": 9.013110072278747e-07, "epoch": 3.05172176172944, "percentage": 20.34, "elapsed_time": "5:15:11", "remaining_time": "20:34:01", "throughput": 8345.62, "total_tokens": 157824016} {"current_steps": 155100, "total_steps": 761865, "loss": 1.9959, "lr": 9.011879889325821e-07, "epoch": 3.0536906144789433, "percentage": 20.36, "elapsed_time": "5:15:23", "remaining_time": "20:33:51", "throughput": 8345.37, "total_tokens": 157925568} {"current_steps": 155200, "total_steps": 761865, "loss": 2.0125, "lr": 9.010649024186558e-07, "epoch": 3.055659467228446, "percentage": 20.37, "elapsed_time": "5:15:35", "remaining_time": "20:33:39", "throughput": 8345.38, "total_tokens": 158027968} {"current_steps": 155300, "total_steps": 761865, "loss": 1.9846, "lr": 9.009417477070254e-07, "epoch": 3.057628319977949, "percentage": 20.38, "elapsed_time": "5:15:48", "remaining_time": "20:33:26", "throughput": 8345.37, "total_tokens": 158129152} {"current_steps": 155400, "total_steps": 761865, "loss": 1.9872, "lr": 9.008185248186328e-07, "epoch": 3.0595971727274516, "percentage": 20.4, "elapsed_time": "5:16:00", "remaining_time": "20:33:15", "throughput": 8345.37, "total_tokens": 158231552} {"current_steps": 155500, "total_steps": 761865, "loss": 1.9969, "lr": 9.006952337744304e-07, "epoch": 3.0615660254769548, "percentage": 20.41, "elapsed_time": "5:16:12", "remaining_time": "20:33:02", "throughput": 8345.36, "total_tokens": 158333304} {"current_steps": 155600, "total_steps": 761865, "loss": 1.9884, "lr": 9.005718745953833e-07, "epoch": 3.0635348782264575, "percentage": 20.42, "elapsed_time": "5:16:24", "remaining_time": "20:32:50", "throughput": 8345.33, "total_tokens": 158434848} {"current_steps": 155700, "total_steps": 761865, "loss": 1.9332, "lr": 9.004484473024675e-07, "epoch": 3.0655037309759603, "percentage": 20.44, "elapsed_time": "5:16:37", "remaining_time": "20:32:38", "throughput": 8345.34, "total_tokens": 158537248} {"current_steps": 155800, "total_steps": 761865, "loss": 1.9378, "lr": 9.003249519166707e-07, "epoch": 3.067472583725463, "percentage": 20.45, "elapsed_time": "5:16:49", "remaining_time": "20:32:26", "throughput": 8345.34, "total_tokens": 158639648} {"current_steps": 155900, "total_steps": 761865, "loss": 2.0053, "lr": 9.002013884589924e-07, "epoch": 3.069441436474966, "percentage": 20.46, "elapsed_time": "5:17:01", "remaining_time": "20:32:14", "throughput": 8345.33, "total_tokens": 158741496} {"current_steps": 156000, "total_steps": 761865, "loss": 1.9448, "lr": 9.000777569504435e-07, "epoch": 3.071410289224469, "percentage": 20.48, "elapsed_time": "5:17:13", "remaining_time": "20:32:02", "throughput": 8345.33, "total_tokens": 158843424} {"current_steps": 156100, "total_steps": 761865, "loss": 2.0004, "lr": 8.999540574120462e-07, "epoch": 3.0733791419739718, "percentage": 20.49, "elapsed_time": "5:17:25", "remaining_time": "20:31:50", "throughput": 8345.33, "total_tokens": 158945048} {"current_steps": 156200, "total_steps": 761865, "loss": 2.0059, "lr": 8.99830289864835e-07, "epoch": 3.0753479947234745, "percentage": 20.5, "elapsed_time": "5:17:38", "remaining_time": "20:31:38", "throughput": 8345.3, "total_tokens": 159046584} {"current_steps": 156300, "total_steps": 761865, "loss": 1.9767, "lr": 8.997064543298553e-07, "epoch": 3.0773168474729773, "percentage": 20.52, "elapsed_time": "5:17:50", "remaining_time": "20:31:26", "throughput": 8345.3, "total_tokens": 159148504} {"current_steps": 156400, "total_steps": 761865, "loss": 1.9557, "lr": 8.995825508281643e-07, "epoch": 3.0792857002224805, "percentage": 20.53, "elapsed_time": "5:18:02", "remaining_time": "20:31:13", "throughput": 8345.28, "total_tokens": 159249696} {"current_steps": 156500, "total_steps": 761865, "loss": 1.9945, "lr": 8.994585793808308e-07, "epoch": 3.0812545529719833, "percentage": 20.54, "elapsed_time": "5:18:14", "remaining_time": "20:31:01", "throughput": 8345.3, "total_tokens": 159352096} {"current_steps": 156600, "total_steps": 761865, "loss": 1.9673, "lr": 8.993345400089351e-07, "epoch": 3.083223405721486, "percentage": 20.55, "elapsed_time": "5:18:27", "remaining_time": "20:30:49", "throughput": 8345.3, "total_tokens": 159454496} {"current_steps": 156700, "total_steps": 761865, "loss": 1.9692, "lr": 8.992104327335689e-07, "epoch": 3.0851922584709888, "percentage": 20.57, "elapsed_time": "5:18:39", "remaining_time": "20:30:37", "throughput": 8345.31, "total_tokens": 159556896} {"current_steps": 156800, "total_steps": 761865, "loss": 2.0218, "lr": 8.990862575758358e-07, "epoch": 3.087161111220492, "percentage": 20.58, "elapsed_time": "5:18:51", "remaining_time": "20:30:25", "throughput": 8345.32, "total_tokens": 159659296} {"current_steps": 156900, "total_steps": 761865, "loss": 1.9707, "lr": 8.989620145568506e-07, "epoch": 3.0891299639699947, "percentage": 20.59, "elapsed_time": "5:19:03", "remaining_time": "20:30:13", "throughput": 8345.33, "total_tokens": 159761696} {"current_steps": 157000, "total_steps": 761865, "loss": 2.0424, "lr": 8.988377036977398e-07, "epoch": 3.0910988167194975, "percentage": 20.61, "elapsed_time": "5:19:16", "remaining_time": "20:30:01", "throughput": 8345.33, "total_tokens": 159864096} {"current_steps": 157100, "total_steps": 761865, "loss": 1.9635, "lr": 8.987133250196414e-07, "epoch": 3.0930676694690002, "percentage": 20.62, "elapsed_time": "5:19:28", "remaining_time": "20:29:49", "throughput": 8345.34, "total_tokens": 159966496} {"current_steps": 157200, "total_steps": 761865, "loss": 1.9844, "lr": 8.985888785437052e-07, "epoch": 3.0950365222185034, "percentage": 20.63, "elapsed_time": "5:19:40", "remaining_time": "20:29:37", "throughput": 8345.32, "total_tokens": 160067936} {"current_steps": 157300, "total_steps": 761865, "loss": 1.9908, "lr": 8.984643642910918e-07, "epoch": 3.097005374968006, "percentage": 20.65, "elapsed_time": "5:19:52", "remaining_time": "20:29:25", "throughput": 8345.32, "total_tokens": 160170336} {"current_steps": 157400, "total_steps": 761865, "loss": 1.9762, "lr": 8.983397822829744e-07, "epoch": 3.098974227717509, "percentage": 20.66, "elapsed_time": "5:20:05", "remaining_time": "20:29:13", "throughput": 8345.32, "total_tokens": 160272736} {"current_steps": 157500, "total_steps": 761865, "loss": 1.984, "lr": 8.982151325405365e-07, "epoch": 3.1009430804670117, "percentage": 20.67, "elapsed_time": "5:20:17", "remaining_time": "20:29:01", "throughput": 8345.31, "total_tokens": 160375136} {"current_steps": 157600, "total_steps": 761865, "loss": 1.937, "lr": 8.98090415084974e-07, "epoch": 3.102911933216515, "percentage": 20.69, "elapsed_time": "5:20:29", "remaining_time": "20:28:49", "throughput": 8345.29, "total_tokens": 160476704} {"current_steps": 157700, "total_steps": 761865, "loss": 2.0462, "lr": 8.979656299374941e-07, "epoch": 3.1048807859660177, "percentage": 20.7, "elapsed_time": "5:20:41", "remaining_time": "20:28:37", "throughput": 8345.29, "total_tokens": 160579104} {"current_steps": 157800, "total_steps": 761865, "loss": 1.9849, "lr": 8.978407771193155e-07, "epoch": 3.1068496387155204, "percentage": 20.71, "elapsed_time": "5:20:54", "remaining_time": "20:28:25", "throughput": 8345.27, "total_tokens": 160680800} {"current_steps": 157900, "total_steps": 761865, "loss": 2.0085, "lr": 8.977158566516683e-07, "epoch": 3.108818491465023, "percentage": 20.73, "elapsed_time": "5:21:06", "remaining_time": "20:28:13", "throughput": 8345.27, "total_tokens": 160782568} {"current_steps": 158000, "total_steps": 761865, "loss": 2.0127, "lr": 8.97590868555794e-07, "epoch": 3.1107873442145264, "percentage": 20.74, "elapsed_time": "5:21:18", "remaining_time": "20:28:01", "throughput": 8345.27, "total_tokens": 160884968} {"current_steps": 158100, "total_steps": 761865, "loss": 1.9945, "lr": 8.974658128529461e-07, "epoch": 3.112756196964029, "percentage": 20.75, "elapsed_time": "5:21:30", "remaining_time": "20:27:49", "throughput": 8345.24, "total_tokens": 160987368} {"current_steps": 158200, "total_steps": 761865, "loss": 1.9623, "lr": 8.973406895643891e-07, "epoch": 3.114725049713532, "percentage": 20.76, "elapsed_time": "5:21:43", "remaining_time": "20:27:37", "throughput": 8345.25, "total_tokens": 161089768} {"current_steps": 158300, "total_steps": 761865, "loss": 1.9532, "lr": 8.972154987113991e-07, "epoch": 3.1166939024630347, "percentage": 20.78, "elapsed_time": "5:21:55", "remaining_time": "20:27:25", "throughput": 8345.23, "total_tokens": 161191304} {"current_steps": 158400, "total_steps": 761865, "loss": 1.9718, "lr": 8.970902403152638e-07, "epoch": 3.1186627552125374, "percentage": 20.79, "elapsed_time": "5:22:07", "remaining_time": "20:27:13", "throughput": 8345.21, "total_tokens": 161292304} {"current_steps": 158500, "total_steps": 761865, "loss": 2.0167, "lr": 8.969649143972824e-07, "epoch": 3.1206316079620406, "percentage": 20.8, "elapsed_time": "5:22:19", "remaining_time": "20:27:00", "throughput": 8345.21, "total_tokens": 161394160} {"current_steps": 158600, "total_steps": 761865, "loss": 2.0541, "lr": 8.968395209787656e-07, "epoch": 3.1226004607115434, "percentage": 20.82, "elapsed_time": "5:22:31", "remaining_time": "20:26:48", "throughput": 8345.22, "total_tokens": 161496560} {"current_steps": 158700, "total_steps": 761865, "loss": 2.0817, "lr": 8.967140600810351e-07, "epoch": 3.124569313461046, "percentage": 20.83, "elapsed_time": "5:22:44", "remaining_time": "20:26:36", "throughput": 8345.19, "total_tokens": 161598008} {"current_steps": 158800, "total_steps": 761865, "loss": 2.0078, "lr": 8.965885317254249e-07, "epoch": 3.126538166210549, "percentage": 20.84, "elapsed_time": "5:22:56", "remaining_time": "20:26:24", "throughput": 8345.19, "total_tokens": 161699800} {"current_steps": 158900, "total_steps": 761865, "loss": 1.9669, "lr": 8.964629359332797e-07, "epoch": 3.128507018960052, "percentage": 20.86, "elapsed_time": "5:23:08", "remaining_time": "20:26:12", "throughput": 8345.19, "total_tokens": 161801704} {"current_steps": 159000, "total_steps": 761865, "loss": 1.9613, "lr": 8.963372727259564e-07, "epoch": 3.130475871709555, "percentage": 20.87, "elapsed_time": "5:23:20", "remaining_time": "20:26:00", "throughput": 8345.18, "total_tokens": 161903336} {"current_steps": 159100, "total_steps": 761865, "loss": 1.9656, "lr": 8.962115421248225e-07, "epoch": 3.1324447244590576, "percentage": 20.88, "elapsed_time": "5:23:33", "remaining_time": "20:25:48", "throughput": 8345.18, "total_tokens": 162005736} {"current_steps": 159200, "total_steps": 761865, "loss": 1.9927, "lr": 8.960857441512578e-07, "epoch": 3.1344135772085604, "percentage": 20.9, "elapsed_time": "5:23:45", "remaining_time": "20:25:35", "throughput": 8345.17, "total_tokens": 162106912} {"current_steps": 159300, "total_steps": 761865, "loss": 2.0015, "lr": 8.95959878826653e-07, "epoch": 3.1363824299580636, "percentage": 20.91, "elapsed_time": "5:23:57", "remaining_time": "20:25:23", "throughput": 8345.16, "total_tokens": 162208520} {"current_steps": 159400, "total_steps": 761865, "loss": 1.9662, "lr": 8.958339461724104e-07, "epoch": 3.1383512827075664, "percentage": 20.92, "elapsed_time": "5:24:09", "remaining_time": "20:25:11", "throughput": 8345.16, "total_tokens": 162310920} {"current_steps": 159500, "total_steps": 761865, "loss": 1.9294, "lr": 8.957079462099442e-07, "epoch": 3.140320135457069, "percentage": 20.94, "elapsed_time": "5:24:21", "remaining_time": "20:24:59", "throughput": 8345.13, "total_tokens": 162412504} {"current_steps": 159600, "total_steps": 761865, "loss": 1.9676, "lr": 8.95581878960679e-07, "epoch": 3.142288988206572, "percentage": 20.95, "elapsed_time": "5:24:34", "remaining_time": "20:24:47", "throughput": 8345.12, "total_tokens": 162514304} {"current_steps": 159700, "total_steps": 761865, "loss": 2.025, "lr": 8.954557444460518e-07, "epoch": 3.144257840956075, "percentage": 20.96, "elapsed_time": "5:24:46", "remaining_time": "20:24:35", "throughput": 8345.1, "total_tokens": 162615960} {"current_steps": 159800, "total_steps": 761865, "loss": 1.9757, "lr": 8.953295426875107e-07, "epoch": 3.146226693705578, "percentage": 20.97, "elapsed_time": "5:24:58", "remaining_time": "20:24:23", "throughput": 8345.09, "total_tokens": 162717824} {"current_steps": 159900, "total_steps": 761865, "loss": 1.9565, "lr": 8.952032737065153e-07, "epoch": 3.1481955464550806, "percentage": 20.99, "elapsed_time": "5:25:10", "remaining_time": "20:24:11", "throughput": 8345.08, "total_tokens": 162819704} {"current_steps": 160000, "total_steps": 761865, "loss": 1.9858, "lr": 8.950769375245364e-07, "epoch": 3.1501643992045834, "percentage": 21.0, "elapsed_time": "5:25:23", "remaining_time": "20:23:59", "throughput": 8345.08, "total_tokens": 162922104} {"current_steps": 160100, "total_steps": 761865, "loss": 2.0013, "lr": 8.949505341630566e-07, "epoch": 3.1521332519540866, "percentage": 21.01, "elapsed_time": "5:25:35", "remaining_time": "20:23:48", "throughput": 8344.83, "total_tokens": 163022320} {"current_steps": 160200, "total_steps": 761865, "loss": 1.9869, "lr": 8.948240636435695e-07, "epoch": 3.1541021047035893, "percentage": 21.03, "elapsed_time": "5:25:47", "remaining_time": "20:23:36", "throughput": 8344.83, "total_tokens": 163123584} {"current_steps": 160300, "total_steps": 761865, "loss": 1.9716, "lr": 8.946975259875806e-07, "epoch": 3.156070957453092, "percentage": 21.04, "elapsed_time": "5:26:00", "remaining_time": "20:23:23", "throughput": 8344.83, "total_tokens": 163225344} {"current_steps": 160400, "total_steps": 761865, "loss": 1.9689, "lr": 8.945709212166066e-07, "epoch": 3.158039810202595, "percentage": 21.05, "elapsed_time": "5:26:12", "remaining_time": "20:23:11", "throughput": 8344.82, "total_tokens": 163327008} {"current_steps": 160500, "total_steps": 761865, "loss": 1.9864, "lr": 8.944442493521751e-07, "epoch": 3.160008662952098, "percentage": 21.07, "elapsed_time": "5:26:24", "remaining_time": "20:22:59", "throughput": 8344.83, "total_tokens": 163429408} {"current_steps": 160600, "total_steps": 761865, "loss": 2.0079, "lr": 8.94317510415826e-07, "epoch": 3.161977515701601, "percentage": 21.08, "elapsed_time": "5:26:36", "remaining_time": "20:22:47", "throughput": 8344.83, "total_tokens": 163531808} {"current_steps": 160700, "total_steps": 761865, "loss": 2.0031, "lr": 8.941907044291102e-07, "epoch": 3.1639463684511036, "percentage": 21.09, "elapsed_time": "5:26:49", "remaining_time": "20:22:35", "throughput": 8344.84, "total_tokens": 163634208} {"current_steps": 160800, "total_steps": 761865, "loss": 2.0465, "lr": 8.940638314135898e-07, "epoch": 3.1659152212006063, "percentage": 21.11, "elapsed_time": "5:27:01", "remaining_time": "20:22:23", "throughput": 8344.83, "total_tokens": 163735848} {"current_steps": 160900, "total_steps": 761865, "loss": 2.007, "lr": 8.939368913908385e-07, "epoch": 3.167884073950109, "percentage": 21.12, "elapsed_time": "5:27:13", "remaining_time": "20:22:11", "throughput": 8344.83, "total_tokens": 163837680} {"current_steps": 161000, "total_steps": 761865, "loss": 1.9985, "lr": 8.938098843824415e-07, "epoch": 3.1698529266996123, "percentage": 21.13, "elapsed_time": "5:27:25", "remaining_time": "20:21:59", "throughput": 8344.81, "total_tokens": 163939272} {"current_steps": 161100, "total_steps": 761865, "loss": 1.9931, "lr": 8.936828104099952e-07, "epoch": 3.171821779449115, "percentage": 21.15, "elapsed_time": "5:27:37", "remaining_time": "20:21:46", "throughput": 8344.8, "total_tokens": 164040760} {"current_steps": 161200, "total_steps": 761865, "loss": 2.0344, "lr": 8.935556694951074e-07, "epoch": 3.173790632198618, "percentage": 21.16, "elapsed_time": "5:27:50", "remaining_time": "20:21:34", "throughput": 8344.79, "total_tokens": 164142384} {"current_steps": 161300, "total_steps": 761865, "loss": 1.9667, "lr": 8.934284616593975e-07, "epoch": 3.1757594849481205, "percentage": 21.17, "elapsed_time": "5:28:02", "remaining_time": "20:21:22", "throughput": 8344.8, "total_tokens": 164244784} {"current_steps": 161400, "total_steps": 761865, "loss": 1.9644, "lr": 8.933011869244959e-07, "epoch": 3.1777283376976238, "percentage": 21.18, "elapsed_time": "5:28:14", "remaining_time": "20:21:10", "throughput": 8344.79, "total_tokens": 164346480} {"current_steps": 161500, "total_steps": 761865, "loss": 1.9888, "lr": 8.931738453120448e-07, "epoch": 3.1796971904471265, "percentage": 21.2, "elapsed_time": "5:28:26", "remaining_time": "20:20:58", "throughput": 8344.79, "total_tokens": 164448264} {"current_steps": 161600, "total_steps": 761865, "loss": 2.0127, "lr": 8.930464368436974e-07, "epoch": 3.1816660431966293, "percentage": 21.21, "elapsed_time": "5:28:38", "remaining_time": "20:20:46", "throughput": 8344.79, "total_tokens": 164550664} {"current_steps": 161700, "total_steps": 761865, "loss": 1.9547, "lr": 8.929189615411185e-07, "epoch": 3.183634895946132, "percentage": 21.22, "elapsed_time": "5:28:51", "remaining_time": "20:20:34", "throughput": 8344.79, "total_tokens": 164652440} {"current_steps": 161800, "total_steps": 761865, "loss": 1.9994, "lr": 8.927914194259845e-07, "epoch": 3.1856037486956352, "percentage": 21.24, "elapsed_time": "5:29:03", "remaining_time": "20:20:21", "throughput": 8344.78, "total_tokens": 164754008} {"current_steps": 161900, "total_steps": 761865, "loss": 1.9736, "lr": 8.926638105199824e-07, "epoch": 3.187572601445138, "percentage": 21.25, "elapsed_time": "5:29:15", "remaining_time": "20:20:09", "throughput": 8344.75, "total_tokens": 164854520} {"current_steps": 162000, "total_steps": 761865, "loss": 1.9764, "lr": 8.925361348448112e-07, "epoch": 3.1895414541946407, "percentage": 21.26, "elapsed_time": "5:29:27", "remaining_time": "20:19:57", "throughput": 8344.75, "total_tokens": 164956552} {"current_steps": 162100, "total_steps": 761865, "loss": 1.9695, "lr": 8.92408392422181e-07, "epoch": 3.1915103069441435, "percentage": 21.28, "elapsed_time": "5:29:39", "remaining_time": "20:19:45", "throughput": 8344.74, "total_tokens": 165058504} {"current_steps": 162200, "total_steps": 761865, "loss": 1.9296, "lr": 8.922805832738133e-07, "epoch": 3.1934791596936467, "percentage": 21.29, "elapsed_time": "5:29:52", "remaining_time": "20:19:33", "throughput": 8344.74, "total_tokens": 165160904} {"current_steps": 162300, "total_steps": 761865, "loss": 1.9708, "lr": 8.921527074214414e-07, "epoch": 3.1954480124431495, "percentage": 21.3, "elapsed_time": "5:30:04", "remaining_time": "20:19:21", "throughput": 8344.74, "total_tokens": 165262840} {"current_steps": 162400, "total_steps": 761865, "loss": 1.9825, "lr": 8.92024764886809e-07, "epoch": 3.1974168651926522, "percentage": 21.32, "elapsed_time": "5:30:16", "remaining_time": "20:19:08", "throughput": 8344.72, "total_tokens": 165364128} {"current_steps": 162500, "total_steps": 761865, "loss": 1.9494, "lr": 8.918967556916719e-07, "epoch": 3.199385717942155, "percentage": 21.33, "elapsed_time": "5:30:28", "remaining_time": "20:18:56", "throughput": 8344.71, "total_tokens": 165465896} {"current_steps": 162600, "total_steps": 761865, "loss": 1.9949, "lr": 8.917686798577968e-07, "epoch": 3.2013545706916577, "percentage": 21.34, "elapsed_time": "5:30:41", "remaining_time": "20:18:44", "throughput": 8344.71, "total_tokens": 165568296} {"current_steps": 162700, "total_steps": 761865, "loss": 1.9576, "lr": 8.91640537406962e-07, "epoch": 3.203323423441161, "percentage": 21.36, "elapsed_time": "5:30:53", "remaining_time": "20:18:32", "throughput": 8344.7, "total_tokens": 165669936} {"current_steps": 162800, "total_steps": 761865, "loss": 2.018, "lr": 8.915123283609572e-07, "epoch": 3.2052922761906637, "percentage": 21.37, "elapsed_time": "5:31:05", "remaining_time": "20:18:20", "throughput": 8344.68, "total_tokens": 165771440} {"current_steps": 162900, "total_steps": 761865, "loss": 1.9705, "lr": 8.91384052741583e-07, "epoch": 3.2072611289401665, "percentage": 21.38, "elapsed_time": "5:31:17", "remaining_time": "20:18:08", "throughput": 8344.69, "total_tokens": 165873840} {"current_steps": 163000, "total_steps": 761865, "loss": 1.9828, "lr": 8.912557105706517e-07, "epoch": 3.2092299816896697, "percentage": 21.39, "elapsed_time": "5:31:29", "remaining_time": "20:17:56", "throughput": 8344.69, "total_tokens": 165975416} {"current_steps": 163100, "total_steps": 761865, "loss": 1.999, "lr": 8.911273018699869e-07, "epoch": 3.2111988344391724, "percentage": 21.41, "elapsed_time": "5:31:42", "remaining_time": "20:17:43", "throughput": 8344.65, "total_tokens": 166075720} {"current_steps": 163200, "total_steps": 761865, "loss": 1.9918, "lr": 8.909988266614233e-07, "epoch": 3.213167687188675, "percentage": 21.42, "elapsed_time": "5:31:54", "remaining_time": "20:17:31", "throughput": 8344.63, "total_tokens": 166176728} {"current_steps": 163300, "total_steps": 761865, "loss": 2.0197, "lr": 8.90870284966807e-07, "epoch": 3.215136539938178, "percentage": 21.43, "elapsed_time": "5:32:06", "remaining_time": "20:17:19", "throughput": 8344.64, "total_tokens": 166279128} {"current_steps": 163400, "total_steps": 761865, "loss": 1.9746, "lr": 8.907416768079956e-07, "epoch": 3.2171053926876807, "percentage": 21.45, "elapsed_time": "5:32:18", "remaining_time": "20:17:06", "throughput": 8344.6, "total_tokens": 166379728} {"current_steps": 163500, "total_steps": 761865, "loss": 2.0108, "lr": 8.906130022068577e-07, "epoch": 3.219074245437184, "percentage": 21.46, "elapsed_time": "5:32:30", "remaining_time": "20:16:54", "throughput": 8344.6, "total_tokens": 166482128} {"current_steps": 163600, "total_steps": 761865, "loss": 2.0074, "lr": 8.904842611852734e-07, "epoch": 3.2210430981866867, "percentage": 21.47, "elapsed_time": "5:32:43", "remaining_time": "20:16:42", "throughput": 8344.58, "total_tokens": 166583688} {"current_steps": 163700, "total_steps": 761865, "loss": 1.9904, "lr": 8.903554537651339e-07, "epoch": 3.2230119509361894, "percentage": 21.49, "elapsed_time": "5:32:55", "remaining_time": "20:16:30", "throughput": 8344.59, "total_tokens": 166686088} {"current_steps": 163800, "total_steps": 761865, "loss": 1.951, "lr": 8.90226579968342e-07, "epoch": 3.224980803685692, "percentage": 21.5, "elapsed_time": "5:33:07", "remaining_time": "20:16:18", "throughput": 8344.6, "total_tokens": 166788488} {"current_steps": 163900, "total_steps": 761865, "loss": 1.9685, "lr": 8.900976398168113e-07, "epoch": 3.2269496564351954, "percentage": 21.51, "elapsed_time": "5:33:19", "remaining_time": "20:16:06", "throughput": 8344.59, "total_tokens": 166889480} {"current_steps": 164000, "total_steps": 761865, "loss": 2.015, "lr": 8.899686333324674e-07, "epoch": 3.228918509184698, "percentage": 21.53, "elapsed_time": "5:33:31", "remaining_time": "20:15:53", "throughput": 8344.58, "total_tokens": 166991232} {"current_steps": 164100, "total_steps": 761865, "loss": 2.0182, "lr": 8.898395605372464e-07, "epoch": 3.230887361934201, "percentage": 21.54, "elapsed_time": "5:33:44", "remaining_time": "20:15:41", "throughput": 8344.59, "total_tokens": 167092816} {"current_steps": 164200, "total_steps": 761865, "loss": 1.9717, "lr": 8.897104214530962e-07, "epoch": 3.2328562146837037, "percentage": 21.55, "elapsed_time": "5:33:56", "remaining_time": "20:15:29", "throughput": 8344.56, "total_tokens": 167193408} {"current_steps": 164300, "total_steps": 761865, "loss": 2.0157, "lr": 8.895812161019759e-07, "epoch": 3.234825067433207, "percentage": 21.57, "elapsed_time": "5:34:08", "remaining_time": "20:15:16", "throughput": 8344.55, "total_tokens": 167295312} {"current_steps": 164400, "total_steps": 761865, "loss": 1.922, "lr": 8.894519445058556e-07, "epoch": 3.2367939201827096, "percentage": 21.58, "elapsed_time": "5:34:20", "remaining_time": "20:15:04", "throughput": 8344.55, "total_tokens": 167397088} {"current_steps": 164500, "total_steps": 761865, "loss": 1.9658, "lr": 8.89322606686717e-07, "epoch": 3.2387627729322124, "percentage": 21.59, "elapsed_time": "5:34:32", "remaining_time": "20:14:52", "throughput": 8344.54, "total_tokens": 167498976} {"current_steps": 164600, "total_steps": 761865, "loss": 1.9703, "lr": 8.891932026665528e-07, "epoch": 3.240731625681715, "percentage": 21.6, "elapsed_time": "5:34:45", "remaining_time": "20:14:40", "throughput": 8344.55, "total_tokens": 167601376} {"current_steps": 164700, "total_steps": 761865, "loss": 1.9732, "lr": 8.890637324673671e-07, "epoch": 3.2427004784312183, "percentage": 21.62, "elapsed_time": "5:34:57", "remaining_time": "20:14:28", "throughput": 8344.55, "total_tokens": 167703768} {"current_steps": 164800, "total_steps": 761865, "loss": 2.0166, "lr": 8.889341961111751e-07, "epoch": 3.244669331180721, "percentage": 21.63, "elapsed_time": "5:35:09", "remaining_time": "20:14:16", "throughput": 8344.55, "total_tokens": 167806168} {"current_steps": 164900, "total_steps": 761865, "loss": 1.9954, "lr": 8.888045936200036e-07, "epoch": 3.246638183930224, "percentage": 21.64, "elapsed_time": "5:35:21", "remaining_time": "20:14:04", "throughput": 8344.56, "total_tokens": 167908568} {"current_steps": 165000, "total_steps": 761865, "loss": 2.0289, "lr": 8.886749250158903e-07, "epoch": 3.2486070366797266, "percentage": 21.66, "elapsed_time": "5:35:34", "remaining_time": "20:13:52", "throughput": 8344.56, "total_tokens": 168010376} {"current_steps": 165100, "total_steps": 761865, "loss": 1.9615, "lr": 8.885451903208841e-07, "epoch": 3.2505758894292294, "percentage": 21.67, "elapsed_time": "5:35:46", "remaining_time": "20:13:42", "throughput": 8344.32, "total_tokens": 168111576} {"current_steps": 165200, "total_steps": 761865, "loss": 1.9826, "lr": 8.884153895570456e-07, "epoch": 3.2525447421787326, "percentage": 21.68, "elapsed_time": "5:35:59", "remaining_time": "20:13:29", "throughput": 8344.31, "total_tokens": 168213104} {"current_steps": 165300, "total_steps": 761865, "loss": 1.9622, "lr": 8.882855227464461e-07, "epoch": 3.2545135949282353, "percentage": 21.7, "elapsed_time": "5:36:11", "remaining_time": "20:13:17", "throughput": 8344.31, "total_tokens": 168314768} {"current_steps": 165400, "total_steps": 761865, "loss": 1.9824, "lr": 8.881555899111683e-07, "epoch": 3.256482447677738, "percentage": 21.71, "elapsed_time": "5:36:23", "remaining_time": "20:13:05", "throughput": 8344.29, "total_tokens": 168415584} {"current_steps": 165500, "total_steps": 761865, "loss": 1.9423, "lr": 8.880255910733063e-07, "epoch": 3.2584513004272413, "percentage": 21.72, "elapsed_time": "5:36:35", "remaining_time": "20:12:52", "throughput": 8344.27, "total_tokens": 168517064} {"current_steps": 165600, "total_steps": 761865, "loss": 1.9966, "lr": 8.878955262549655e-07, "epoch": 3.260420153176744, "percentage": 21.74, "elapsed_time": "5:36:47", "remaining_time": "20:12:40", "throughput": 8344.25, "total_tokens": 168618720} {"current_steps": 165700, "total_steps": 761865, "loss": 1.9929, "lr": 8.877653954782619e-07, "epoch": 3.262389005926247, "percentage": 21.75, "elapsed_time": "5:37:00", "remaining_time": "20:12:28", "throughput": 8344.27, "total_tokens": 168721120} {"current_steps": 165800, "total_steps": 761865, "loss": 1.9942, "lr": 8.876351987653235e-07, "epoch": 3.2643578586757496, "percentage": 21.76, "elapsed_time": "5:37:12", "remaining_time": "20:12:16", "throughput": 8344.26, "total_tokens": 168822248} {"current_steps": 165900, "total_steps": 761865, "loss": 1.9777, "lr": 8.875049361382889e-07, "epoch": 3.2663267114252523, "percentage": 21.78, "elapsed_time": "5:37:24", "remaining_time": "20:12:04", "throughput": 8344.24, "total_tokens": 168923696} {"current_steps": 166000, "total_steps": 761865, "loss": 1.9761, "lr": 8.873746076193084e-07, "epoch": 3.2682955641747555, "percentage": 21.79, "elapsed_time": "5:37:36", "remaining_time": "20:11:51", "throughput": 8344.23, "total_tokens": 169024496} {"current_steps": 166100, "total_steps": 761865, "loss": 2.0066, "lr": 8.872442132305431e-07, "epoch": 3.2702644169242583, "percentage": 21.8, "elapsed_time": "5:37:48", "remaining_time": "20:11:39", "throughput": 8344.23, "total_tokens": 169126304} {"current_steps": 166200, "total_steps": 761865, "loss": 1.967, "lr": 8.871137529941655e-07, "epoch": 3.272233269673761, "percentage": 21.81, "elapsed_time": "5:38:00", "remaining_time": "20:11:26", "throughput": 8344.2, "total_tokens": 169226296} {"current_steps": 166300, "total_steps": 761865, "loss": 1.9969, "lr": 8.869832269323592e-07, "epoch": 3.274202122423264, "percentage": 21.83, "elapsed_time": "5:38:12", "remaining_time": "20:11:14", "throughput": 8344.19, "total_tokens": 169327776} {"current_steps": 166400, "total_steps": 761865, "loss": 1.9694, "lr": 8.868526350673191e-07, "epoch": 3.276170975172767, "percentage": 21.84, "elapsed_time": "5:38:25", "remaining_time": "20:11:02", "throughput": 8344.2, "total_tokens": 169430176} {"current_steps": 166500, "total_steps": 761865, "loss": 1.959, "lr": 8.867219774212514e-07, "epoch": 3.2781398279222698, "percentage": 21.85, "elapsed_time": "5:38:37", "remaining_time": "20:10:50", "throughput": 8344.2, "total_tokens": 169532488} {"current_steps": 166600, "total_steps": 761865, "loss": 2.009, "lr": 8.865912540163731e-07, "epoch": 3.2801086806717725, "percentage": 21.87, "elapsed_time": "5:38:49", "remaining_time": "20:10:38", "throughput": 8344.2, "total_tokens": 169634888} {"current_steps": 166700, "total_steps": 761865, "loss": 1.9963, "lr": 8.864604648749129e-07, "epoch": 3.2820775334212753, "percentage": 21.88, "elapsed_time": "5:39:01", "remaining_time": "20:10:26", "throughput": 8344.21, "total_tokens": 169737288} {"current_steps": 166800, "total_steps": 761865, "loss": 1.9577, "lr": 8.863296100191102e-07, "epoch": 3.284046386170778, "percentage": 21.89, "elapsed_time": "5:39:14", "remaining_time": "20:10:14", "throughput": 8344.22, "total_tokens": 169839688} {"current_steps": 166900, "total_steps": 761865, "loss": 2.025, "lr": 8.861986894712155e-07, "epoch": 3.2860152389202812, "percentage": 21.91, "elapsed_time": "5:39:26", "remaining_time": "20:10:02", "throughput": 8344.22, "total_tokens": 169942088} {"current_steps": 167000, "total_steps": 761865, "loss": 1.9597, "lr": 8.860677032534913e-07, "epoch": 3.287984091669784, "percentage": 21.92, "elapsed_time": "5:39:38", "remaining_time": "20:09:50", "throughput": 8344.23, "total_tokens": 170044488} {"current_steps": 167100, "total_steps": 761865, "loss": 1.9842, "lr": 8.859366513882103e-07, "epoch": 3.2899529444192868, "percentage": 21.93, "elapsed_time": "5:39:50", "remaining_time": "20:09:38", "throughput": 8344.23, "total_tokens": 170146368} {"current_steps": 167200, "total_steps": 761865, "loss": 1.9543, "lr": 8.858055338976566e-07, "epoch": 3.29192179716879, "percentage": 21.95, "elapsed_time": "5:40:03", "remaining_time": "20:09:25", "throughput": 8344.21, "total_tokens": 170247912} {"current_steps": 167300, "total_steps": 761865, "loss": 2.0287, "lr": 8.856743508041262e-07, "epoch": 3.2938906499182927, "percentage": 21.96, "elapsed_time": "5:40:15", "remaining_time": "20:09:13", "throughput": 8344.2, "total_tokens": 170349456} {"current_steps": 167400, "total_steps": 761865, "loss": 1.9911, "lr": 8.855431021299253e-07, "epoch": 3.2958595026677955, "percentage": 21.97, "elapsed_time": "5:40:27", "remaining_time": "20:09:01", "throughput": 8344.2, "total_tokens": 170451856} {"current_steps": 167500, "total_steps": 761865, "loss": 2.0775, "lr": 8.854117878973718e-07, "epoch": 3.2978283554172982, "percentage": 21.99, "elapsed_time": "5:40:39", "remaining_time": "20:08:49", "throughput": 8344.19, "total_tokens": 170553328} {"current_steps": 167600, "total_steps": 761865, "loss": 2.0236, "lr": 8.852804081287943e-07, "epoch": 3.299797208166801, "percentage": 22.0, "elapsed_time": "5:40:52", "remaining_time": "20:08:37", "throughput": 8344.18, "total_tokens": 170655680} {"current_steps": 167700, "total_steps": 761865, "loss": 2.0025, "lr": 8.851489628465331e-07, "epoch": 3.301766060916304, "percentage": 22.01, "elapsed_time": "5:41:04", "remaining_time": "20:08:25", "throughput": 8344.17, "total_tokens": 170757408} {"current_steps": 167800, "total_steps": 761865, "loss": 2.0344, "lr": 8.850174520729395e-07, "epoch": 3.303734913665807, "percentage": 22.02, "elapsed_time": "5:41:16", "remaining_time": "20:08:12", "throughput": 8344.16, "total_tokens": 170858144} {"current_steps": 167900, "total_steps": 761865, "loss": 1.9832, "lr": 8.848858758303752e-07, "epoch": 3.3057037664153097, "percentage": 22.04, "elapsed_time": "5:41:28", "remaining_time": "20:08:00", "throughput": 8344.16, "total_tokens": 170960232} {"current_steps": 168000, "total_steps": 761865, "loss": 1.9534, "lr": 8.84754234141214e-07, "epoch": 3.3076726191648125, "percentage": 22.05, "elapsed_time": "5:41:40", "remaining_time": "20:07:48", "throughput": 8344.16, "total_tokens": 171062632} {"current_steps": 168100, "total_steps": 761865, "loss": 1.9614, "lr": 8.846225270278406e-07, "epoch": 3.3096414719143157, "percentage": 22.06, "elapsed_time": "5:41:53", "remaining_time": "20:07:36", "throughput": 8344.17, "total_tokens": 171165032} {"current_steps": 168200, "total_steps": 761865, "loss": 1.9851, "lr": 8.844907545126506e-07, "epoch": 3.3116103246638184, "percentage": 22.08, "elapsed_time": "5:42:05", "remaining_time": "20:07:24", "throughput": 8344.17, "total_tokens": 171267144} {"current_steps": 168300, "total_steps": 761865, "loss": 1.9712, "lr": 8.843589166180506e-07, "epoch": 3.313579177413321, "percentage": 22.09, "elapsed_time": "5:42:17", "remaining_time": "20:07:12", "throughput": 8344.18, "total_tokens": 171369544} {"current_steps": 168400, "total_steps": 761865, "loss": 1.9966, "lr": 8.842270133664586e-07, "epoch": 3.315548030162824, "percentage": 22.1, "elapsed_time": "5:42:29", "remaining_time": "20:07:00", "throughput": 8344.16, "total_tokens": 171470576} {"current_steps": 168500, "total_steps": 761865, "loss": 1.9937, "lr": 8.84095044780304e-07, "epoch": 3.317516882912327, "percentage": 22.12, "elapsed_time": "5:42:42", "remaining_time": "20:06:48", "throughput": 8344.17, "total_tokens": 171572976} {"current_steps": 168600, "total_steps": 761865, "loss": 2.0208, "lr": 8.839630108820264e-07, "epoch": 3.31948573566183, "percentage": 22.13, "elapsed_time": "5:42:54", "remaining_time": "20:06:35", "throughput": 8344.15, "total_tokens": 171673944} {"current_steps": 168700, "total_steps": 761865, "loss": 1.9673, "lr": 8.838309116940773e-07, "epoch": 3.3214545884113327, "percentage": 22.14, "elapsed_time": "5:43:06", "remaining_time": "20:06:23", "throughput": 8344.16, "total_tokens": 171776344} {"current_steps": 168800, "total_steps": 761865, "loss": 1.9714, "lr": 8.83698747238919e-07, "epoch": 3.3234234411608354, "percentage": 22.16, "elapsed_time": "5:43:18", "remaining_time": "20:06:11", "throughput": 8344.17, "total_tokens": 171878744} {"current_steps": 168900, "total_steps": 761865, "loss": 2.0109, "lr": 8.835665175390252e-07, "epoch": 3.3253922939103386, "percentage": 22.17, "elapsed_time": "5:43:30", "remaining_time": "20:05:59", "throughput": 8344.17, "total_tokens": 171980688} {"current_steps": 169000, "total_steps": 761865, "loss": 1.9729, "lr": 8.8343422261688e-07, "epoch": 3.3273611466598414, "percentage": 22.18, "elapsed_time": "5:43:43", "remaining_time": "20:05:47", "throughput": 8344.18, "total_tokens": 172083088} {"current_steps": 169100, "total_steps": 761865, "loss": 2.0067, "lr": 8.833018624949795e-07, "epoch": 3.329329999409344, "percentage": 22.2, "elapsed_time": "5:43:55", "remaining_time": "20:05:35", "throughput": 8344.19, "total_tokens": 172185488} {"current_steps": 169200, "total_steps": 761865, "loss": 2.0186, "lr": 8.831694371958302e-07, "epoch": 3.331298852158847, "percentage": 22.21, "elapsed_time": "5:44:07", "remaining_time": "20:05:22", "throughput": 8344.15, "total_tokens": 172285832} {"current_steps": 169300, "total_steps": 761865, "loss": 1.9824, "lr": 8.830369467419497e-07, "epoch": 3.3332677049083497, "percentage": 22.22, "elapsed_time": "5:44:19", "remaining_time": "20:05:10", "throughput": 8344.16, "total_tokens": 172388232} {"current_steps": 169400, "total_steps": 761865, "loss": 2.0135, "lr": 8.829043911558671e-07, "epoch": 3.335236557657853, "percentage": 22.23, "elapsed_time": "5:44:31", "remaining_time": "20:04:58", "throughput": 8344.15, "total_tokens": 172489536} {"current_steps": 169500, "total_steps": 761865, "loss": 1.9755, "lr": 8.827717704601225e-07, "epoch": 3.3372054104073556, "percentage": 22.25, "elapsed_time": "5:44:44", "remaining_time": "20:04:46", "throughput": 8344.14, "total_tokens": 172590632} {"current_steps": 169600, "total_steps": 761865, "loss": 1.938, "lr": 8.826390846772668e-07, "epoch": 3.3391742631568584, "percentage": 22.26, "elapsed_time": "5:44:56", "remaining_time": "20:04:33", "throughput": 8344.12, "total_tokens": 172691736} {"current_steps": 169700, "total_steps": 761865, "loss": 1.9784, "lr": 8.825063338298619e-07, "epoch": 3.3411431159063616, "percentage": 22.27, "elapsed_time": "5:45:08", "remaining_time": "20:04:21", "throughput": 8344.11, "total_tokens": 172793368} {"current_steps": 169800, "total_steps": 761865, "loss": 1.9772, "lr": 8.823735179404812e-07, "epoch": 3.3431119686558644, "percentage": 22.29, "elapsed_time": "5:45:20", "remaining_time": "20:04:09", "throughput": 8344.08, "total_tokens": 172894400} {"current_steps": 169900, "total_steps": 761865, "loss": 1.9745, "lr": 8.82240637031709e-07, "epoch": 3.345080821405367, "percentage": 22.3, "elapsed_time": "5:45:32", "remaining_time": "20:03:57", "throughput": 8344.09, "total_tokens": 172996800} {"current_steps": 170000, "total_steps": 761865, "loss": 1.9564, "lr": 8.821076911261403e-07, "epoch": 3.34704967415487, "percentage": 22.31, "elapsed_time": "5:45:45", "remaining_time": "20:03:45", "throughput": 8344.09, "total_tokens": 173099200} {"current_steps": 170100, "total_steps": 761865, "loss": 1.9886, "lr": 8.819746802463817e-07, "epoch": 3.3490185269043726, "percentage": 22.33, "elapsed_time": "5:45:57", "remaining_time": "20:03:35", "throughput": 8343.88, "total_tokens": 173200976} {"current_steps": 170200, "total_steps": 761865, "loss": 1.9684, "lr": 8.818416044150503e-07, "epoch": 3.350987379653876, "percentage": 22.34, "elapsed_time": "5:46:10", "remaining_time": "20:03:22", "throughput": 8343.88, "total_tokens": 173303376} {"current_steps": 170300, "total_steps": 761865, "loss": 1.9877, "lr": 8.817084636547747e-07, "epoch": 3.3529562324033786, "percentage": 22.35, "elapsed_time": "5:46:22", "remaining_time": "20:03:10", "throughput": 8343.88, "total_tokens": 173404800} {"current_steps": 170400, "total_steps": 761865, "loss": 1.9827, "lr": 8.815752579881944e-07, "epoch": 3.3549250851528813, "percentage": 22.37, "elapsed_time": "5:46:34", "remaining_time": "20:02:58", "throughput": 8343.89, "total_tokens": 173507200} {"current_steps": 170500, "total_steps": 761865, "loss": 1.9758, "lr": 8.814419874379598e-07, "epoch": 3.356893937902384, "percentage": 22.38, "elapsed_time": "5:46:46", "remaining_time": "20:02:46", "throughput": 8343.87, "total_tokens": 173608488} {"current_steps": 170600, "total_steps": 761865, "loss": 1.9703, "lr": 8.813086520267324e-07, "epoch": 3.3588627906518873, "percentage": 22.39, "elapsed_time": "5:46:58", "remaining_time": "20:02:33", "throughput": 8343.84, "total_tokens": 173708024} {"current_steps": 170700, "total_steps": 761865, "loss": 1.9842, "lr": 8.811752517771848e-07, "epoch": 3.36083164340139, "percentage": 22.41, "elapsed_time": "5:47:10", "remaining_time": "20:02:21", "throughput": 8343.84, "total_tokens": 173810064} {"current_steps": 170800, "total_steps": 761865, "loss": 1.9513, "lr": 8.810417867120008e-07, "epoch": 3.362800496150893, "percentage": 22.42, "elapsed_time": "5:47:23", "remaining_time": "20:02:09", "throughput": 8343.84, "total_tokens": 173912464} {"current_steps": 170900, "total_steps": 761865, "loss": 2.0031, "lr": 8.809082568538748e-07, "epoch": 3.3647693489003956, "percentage": 22.43, "elapsed_time": "5:47:35", "remaining_time": "20:01:57", "throughput": 8343.84, "total_tokens": 174014216} {"current_steps": 171000, "total_steps": 761865, "loss": 1.9944, "lr": 8.807746622255123e-07, "epoch": 3.366738201649899, "percentage": 22.44, "elapsed_time": "5:47:47", "remaining_time": "20:01:45", "throughput": 8343.84, "total_tokens": 174116616} {"current_steps": 171100, "total_steps": 761865, "loss": 1.9605, "lr": 8.806410028496302e-07, "epoch": 3.3687070543994015, "percentage": 22.46, "elapsed_time": "5:47:59", "remaining_time": "20:01:33", "throughput": 8343.85, "total_tokens": 174219008} {"current_steps": 171200, "total_steps": 761865, "loss": 2.0292, "lr": 8.805072787489561e-07, "epoch": 3.3706759071489043, "percentage": 22.47, "elapsed_time": "5:48:12", "remaining_time": "20:01:20", "throughput": 8343.83, "total_tokens": 174320560} {"current_steps": 171300, "total_steps": 761865, "loss": 2.0272, "lr": 8.803734899462285e-07, "epoch": 3.372644759898407, "percentage": 22.48, "elapsed_time": "5:48:24", "remaining_time": "20:01:08", "throughput": 8343.8, "total_tokens": 174421456} {"current_steps": 171400, "total_steps": 761865, "loss": 2.0202, "lr": 8.802396364641971e-07, "epoch": 3.3746136126479103, "percentage": 22.5, "elapsed_time": "5:48:36", "remaining_time": "20:00:56", "throughput": 8343.81, "total_tokens": 174523856} {"current_steps": 171500, "total_steps": 761865, "loss": 1.9989, "lr": 8.801057183256226e-07, "epoch": 3.376582465397413, "percentage": 22.51, "elapsed_time": "5:48:48", "remaining_time": "20:00:44", "throughput": 8343.82, "total_tokens": 174626256} {"current_steps": 171600, "total_steps": 761865, "loss": 1.9893, "lr": 8.799717355532767e-07, "epoch": 3.378551318146916, "percentage": 22.52, "elapsed_time": "5:49:01", "remaining_time": "20:00:32", "throughput": 8343.75, "total_tokens": 174726680} {"current_steps": 171700, "total_steps": 761865, "loss": 1.9935, "lr": 8.798376881699421e-07, "epoch": 3.3805201708964185, "percentage": 22.54, "elapsed_time": "5:49:13", "remaining_time": "20:00:20", "throughput": 8343.73, "total_tokens": 174827712} {"current_steps": 171800, "total_steps": 761865, "loss": 1.9866, "lr": 8.797035761984123e-07, "epoch": 3.3824890236459213, "percentage": 22.55, "elapsed_time": "5:49:25", "remaining_time": "20:00:07", "throughput": 8343.74, "total_tokens": 174930112} {"current_steps": 171900, "total_steps": 761865, "loss": 1.9844, "lr": 8.795693996614919e-07, "epoch": 3.3844578763954245, "percentage": 22.56, "elapsed_time": "5:49:37", "remaining_time": "19:59:55", "throughput": 8343.72, "total_tokens": 175031400} {"current_steps": 172000, "total_steps": 761865, "loss": 2.0195, "lr": 8.794351585819965e-07, "epoch": 3.3864267291449273, "percentage": 22.58, "elapsed_time": "5:49:49", "remaining_time": "19:59:43", "throughput": 8343.73, "total_tokens": 175133800} {"current_steps": 172100, "total_steps": 761865, "loss": 1.9906, "lr": 8.793008529827527e-07, "epoch": 3.38839558189443, "percentage": 22.59, "elapsed_time": "5:50:02", "remaining_time": "19:59:31", "throughput": 8343.71, "total_tokens": 175234848} {"current_steps": 172200, "total_steps": 761865, "loss": 1.9701, "lr": 8.79166482886598e-07, "epoch": 3.3903644346439332, "percentage": 22.6, "elapsed_time": "5:50:14", "remaining_time": "19:59:19", "throughput": 8343.72, "total_tokens": 175337248} {"current_steps": 172300, "total_steps": 761865, "loss": 1.987, "lr": 8.790320483163809e-07, "epoch": 3.392333287393436, "percentage": 22.62, "elapsed_time": "5:50:26", "remaining_time": "19:59:06", "throughput": 8343.69, "total_tokens": 175438224} {"current_steps": 172400, "total_steps": 761865, "loss": 2.0261, "lr": 8.78897549294961e-07, "epoch": 3.3943021401429387, "percentage": 22.63, "elapsed_time": "5:50:38", "remaining_time": "19:58:54", "throughput": 8343.67, "total_tokens": 175539688} {"current_steps": 172500, "total_steps": 761865, "loss": 2.0154, "lr": 8.787629858452085e-07, "epoch": 3.3962709928924415, "percentage": 22.64, "elapsed_time": "5:50:50", "remaining_time": "19:58:42", "throughput": 8343.64, "total_tokens": 175640208} {"current_steps": 172600, "total_steps": 761865, "loss": 1.982, "lr": 8.786283579900049e-07, "epoch": 3.3982398456419443, "percentage": 22.65, "elapsed_time": "5:51:03", "remaining_time": "19:58:30", "throughput": 8343.64, "total_tokens": 175742608} {"current_steps": 172700, "total_steps": 761865, "loss": 1.9456, "lr": 8.784936657522426e-07, "epoch": 3.4002086983914475, "percentage": 22.67, "elapsed_time": "5:51:15", "remaining_time": "19:58:18", "throughput": 8343.64, "total_tokens": 175844480} {"current_steps": 172800, "total_steps": 761865, "loss": 1.9911, "lr": 8.783589091548247e-07, "epoch": 3.40217755114095, "percentage": 22.68, "elapsed_time": "5:51:27", "remaining_time": "19:58:05", "throughput": 8343.63, "total_tokens": 175946008} {"current_steps": 172900, "total_steps": 761865, "loss": 1.9776, "lr": 8.782240882206655e-07, "epoch": 3.404146403890453, "percentage": 22.69, "elapsed_time": "5:51:39", "remaining_time": "19:57:53", "throughput": 8343.64, "total_tokens": 176048408} {"current_steps": 173000, "total_steps": 761865, "loss": 2.0142, "lr": 8.780892029726904e-07, "epoch": 3.4061152566399557, "percentage": 22.71, "elapsed_time": "5:51:51", "remaining_time": "19:57:41", "throughput": 8343.63, "total_tokens": 176149992} {"current_steps": 173100, "total_steps": 761865, "loss": 1.959, "lr": 8.779542534338351e-07, "epoch": 3.408084109389459, "percentage": 22.72, "elapsed_time": "5:52:04", "remaining_time": "19:57:29", "throughput": 8343.62, "total_tokens": 176251648} {"current_steps": 173200, "total_steps": 761865, "loss": 2.0098, "lr": 8.77819239627047e-07, "epoch": 3.4100529621389617, "percentage": 22.73, "elapsed_time": "5:52:16", "remaining_time": "19:57:16", "throughput": 8343.59, "total_tokens": 176351816} {"current_steps": 173300, "total_steps": 761865, "loss": 1.9588, "lr": 8.776841615752837e-07, "epoch": 3.4120218148884645, "percentage": 22.75, "elapsed_time": "5:52:28", "remaining_time": "19:57:04", "throughput": 8343.59, "total_tokens": 176453520} {"current_steps": 173400, "total_steps": 761865, "loss": 2.0074, "lr": 8.775490193015143e-07, "epoch": 3.413990667637967, "percentage": 22.76, "elapsed_time": "5:52:40", "remaining_time": "19:56:52", "throughput": 8343.59, "total_tokens": 176555920} {"current_steps": 173500, "total_steps": 761865, "loss": 1.9695, "lr": 8.774138128287185e-07, "epoch": 3.41595952038747, "percentage": 22.77, "elapsed_time": "5:52:52", "remaining_time": "19:56:40", "throughput": 8343.6, "total_tokens": 176658320} {"current_steps": 173600, "total_steps": 761865, "loss": 1.926, "lr": 8.772785421798872e-07, "epoch": 3.417928373136973, "percentage": 22.79, "elapsed_time": "5:53:05", "remaining_time": "19:56:28", "throughput": 8343.62, "total_tokens": 176760720} {"current_steps": 173700, "total_steps": 761865, "loss": 1.9823, "lr": 8.771432073780219e-07, "epoch": 3.419897225886476, "percentage": 22.8, "elapsed_time": "5:53:17", "remaining_time": "19:56:16", "throughput": 8343.61, "total_tokens": 176862416} {"current_steps": 173800, "total_steps": 761865, "loss": 1.9637, "lr": 8.770078084461351e-07, "epoch": 3.4218660786359787, "percentage": 22.81, "elapsed_time": "5:53:29", "remaining_time": "19:56:04", "throughput": 8343.6, "total_tokens": 176964816} {"current_steps": 173900, "total_steps": 761865, "loss": 1.9809, "lr": 8.768723454072502e-07, "epoch": 3.423834931385482, "percentage": 22.83, "elapsed_time": "5:53:41", "remaining_time": "19:55:52", "throughput": 8343.59, "total_tokens": 177066648} {"current_steps": 174000, "total_steps": 761865, "loss": 2.001, "lr": 8.767368182844018e-07, "epoch": 3.4258037841349847, "percentage": 22.84, "elapsed_time": "5:53:54", "remaining_time": "19:55:40", "throughput": 8343.6, "total_tokens": 177169048} {"current_steps": 174100, "total_steps": 761865, "loss": 1.9709, "lr": 8.766012271006351e-07, "epoch": 3.4277726368844874, "percentage": 22.85, "elapsed_time": "5:54:06", "remaining_time": "19:55:28", "throughput": 8343.6, "total_tokens": 177270760} {"current_steps": 174200, "total_steps": 761865, "loss": 2.039, "lr": 8.764655718790059e-07, "epoch": 3.42974148963399, "percentage": 22.86, "elapsed_time": "5:54:18", "remaining_time": "19:55:16", "throughput": 8343.6, "total_tokens": 177373160} {"current_steps": 174300, "total_steps": 761865, "loss": 2.0096, "lr": 8.763298526425816e-07, "epoch": 3.431710342383493, "percentage": 22.88, "elapsed_time": "5:54:30", "remaining_time": "19:55:03", "throughput": 8343.59, "total_tokens": 177475128} {"current_steps": 174400, "total_steps": 761865, "loss": 1.9807, "lr": 8.761940694144399e-07, "epoch": 3.433679195132996, "percentage": 22.89, "elapsed_time": "5:54:43", "remaining_time": "19:54:51", "throughput": 8343.6, "total_tokens": 177577528} {"current_steps": 174500, "total_steps": 761865, "loss": 1.9268, "lr": 8.760582222176698e-07, "epoch": 3.435648047882499, "percentage": 22.9, "elapsed_time": "5:54:55", "remaining_time": "19:54:39", "throughput": 8343.61, "total_tokens": 177679928} {"current_steps": 174600, "total_steps": 761865, "loss": 1.9931, "lr": 8.759223110753708e-07, "epoch": 3.4376169006320016, "percentage": 22.92, "elapsed_time": "5:55:07", "remaining_time": "19:54:27", "throughput": 8343.62, "total_tokens": 177782328} {"current_steps": 174700, "total_steps": 761865, "loss": 2.0324, "lr": 8.757863360106534e-07, "epoch": 3.4395857533815044, "percentage": 22.93, "elapsed_time": "5:55:19", "remaining_time": "19:54:15", "throughput": 8343.62, "total_tokens": 177884728} {"current_steps": 174800, "total_steps": 761865, "loss": 2.0009, "lr": 8.756502970466391e-07, "epoch": 3.4415546061310076, "percentage": 22.94, "elapsed_time": "5:55:32", "remaining_time": "19:54:03", "throughput": 8343.63, "total_tokens": 177987128} {"current_steps": 174900, "total_steps": 761865, "loss": 1.937, "lr": 8.755141942064601e-07, "epoch": 3.4435234588805104, "percentage": 22.96, "elapsed_time": "5:55:44", "remaining_time": "19:53:51", "throughput": 8343.63, "total_tokens": 178088752} {"current_steps": 175000, "total_steps": 761865, "loss": 1.9945, "lr": 8.753780275132598e-07, "epoch": 3.445492311630013, "percentage": 22.97, "elapsed_time": "5:55:56", "remaining_time": "19:53:39", "throughput": 8343.63, "total_tokens": 178191152} {"current_steps": 175100, "total_steps": 761865, "loss": 2.0213, "lr": 8.752417969901918e-07, "epoch": 3.447461164379516, "percentage": 22.98, "elapsed_time": "5:56:09", "remaining_time": "19:53:29", "throughput": 8343.42, "total_tokens": 178292944} {"current_steps": 175200, "total_steps": 761865, "loss": 2.0624, "lr": 8.751055026604213e-07, "epoch": 3.449430017129019, "percentage": 23.0, "elapsed_time": "5:56:21", "remaining_time": "19:53:16", "throughput": 8343.42, "total_tokens": 178394768} {"current_steps": 175300, "total_steps": 761865, "loss": 2.0736, "lr": 8.749691445471236e-07, "epoch": 3.451398869878522, "percentage": 23.01, "elapsed_time": "5:56:33", "remaining_time": "19:53:04", "throughput": 8343.42, "total_tokens": 178496768} {"current_steps": 175400, "total_steps": 761865, "loss": 1.9192, "lr": 8.748327226734858e-07, "epoch": 3.4533677226280246, "percentage": 23.02, "elapsed_time": "5:56:45", "remaining_time": "19:52:52", "throughput": 8343.41, "total_tokens": 178598128} {"current_steps": 175500, "total_steps": 761865, "loss": 1.9605, "lr": 8.746962370627049e-07, "epoch": 3.4553365753775274, "percentage": 23.04, "elapsed_time": "5:56:58", "remaining_time": "19:52:40", "throughput": 8343.4, "total_tokens": 178699840} {"current_steps": 175600, "total_steps": 761865, "loss": 2.0159, "lr": 8.745596877379893e-07, "epoch": 3.4573054281270306, "percentage": 23.05, "elapsed_time": "5:57:10", "remaining_time": "19:52:27", "throughput": 8343.38, "total_tokens": 178800144} {"current_steps": 175700, "total_steps": 761865, "loss": 1.9723, "lr": 8.744230747225579e-07, "epoch": 3.4592742808765333, "percentage": 23.06, "elapsed_time": "5:57:22", "remaining_time": "19:52:15", "throughput": 8343.38, "total_tokens": 178902544} {"current_steps": 175800, "total_steps": 761865, "loss": 1.9882, "lr": 8.742863980396407e-07, "epoch": 3.461243133626036, "percentage": 23.07, "elapsed_time": "5:57:34", "remaining_time": "19:52:03", "throughput": 8343.38, "total_tokens": 179004304} {"current_steps": 175900, "total_steps": 761865, "loss": 2.0504, "lr": 8.741496577124783e-07, "epoch": 3.463211986375539, "percentage": 23.09, "elapsed_time": "5:57:46", "remaining_time": "19:51:51", "throughput": 8343.39, "total_tokens": 179106704} {"current_steps": 176000, "total_steps": 761865, "loss": 2.0043, "lr": 8.740128537643225e-07, "epoch": 3.4651808391250416, "percentage": 23.1, "elapsed_time": "5:57:59", "remaining_time": "19:51:39", "throughput": 8343.39, "total_tokens": 179209104} {"current_steps": 176100, "total_steps": 761865, "loss": 1.9861, "lr": 8.738759862184353e-07, "epoch": 3.467149691874545, "percentage": 23.11, "elapsed_time": "5:58:11", "remaining_time": "19:51:26", "throughput": 8343.38, "total_tokens": 179310104} {"current_steps": 176200, "total_steps": 761865, "loss": 1.9759, "lr": 8.737390550980901e-07, "epoch": 3.4691185446240476, "percentage": 23.13, "elapsed_time": "5:58:23", "remaining_time": "19:51:14", "throughput": 8343.36, "total_tokens": 179411736} {"current_steps": 176300, "total_steps": 761865, "loss": 1.9581, "lr": 8.73602060426571e-07, "epoch": 3.4710873973735503, "percentage": 23.14, "elapsed_time": "5:58:35", "remaining_time": "19:51:02", "throughput": 8343.37, "total_tokens": 179514136} {"current_steps": 176400, "total_steps": 761865, "loss": 1.945, "lr": 8.734650022271725e-07, "epoch": 3.4730562501230535, "percentage": 23.15, "elapsed_time": "5:58:48", "remaining_time": "19:50:50", "throughput": 8343.38, "total_tokens": 179616536} {"current_steps": 176500, "total_steps": 761865, "loss": 1.9158, "lr": 8.733278805232003e-07, "epoch": 3.4750251028725563, "percentage": 23.17, "elapsed_time": "5:59:00", "remaining_time": "19:50:38", "throughput": 8343.38, "total_tokens": 179718936} {"current_steps": 176600, "total_steps": 761865, "loss": 1.9646, "lr": 8.731906953379709e-07, "epoch": 3.476993955622059, "percentage": 23.18, "elapsed_time": "5:59:12", "remaining_time": "19:50:26", "throughput": 8343.39, "total_tokens": 179821336} {"current_steps": 176700, "total_steps": 761865, "loss": 1.9504, "lr": 8.730534466948113e-07, "epoch": 3.478962808371562, "percentage": 23.19, "elapsed_time": "5:59:24", "remaining_time": "19:50:14", "throughput": 8343.36, "total_tokens": 179922088} {"current_steps": 176800, "total_steps": 761865, "loss": 1.9762, "lr": 8.729161346170596e-07, "epoch": 3.4809316611210646, "percentage": 23.21, "elapsed_time": "5:59:36", "remaining_time": "19:50:02", "throughput": 8343.37, "total_tokens": 180024488} {"current_steps": 176900, "total_steps": 761865, "loss": 2.0408, "lr": 8.727787591280646e-07, "epoch": 3.4829005138705678, "percentage": 23.22, "elapsed_time": "5:59:49", "remaining_time": "19:49:50", "throughput": 8343.37, "total_tokens": 180126888} {"current_steps": 177000, "total_steps": 761865, "loss": 1.9324, "lr": 8.726413202511856e-07, "epoch": 3.4848693666200705, "percentage": 23.23, "elapsed_time": "6:00:01", "remaining_time": "19:49:38", "throughput": 8343.37, "total_tokens": 180228744} {"current_steps": 177100, "total_steps": 761865, "loss": 1.9831, "lr": 8.725038180097932e-07, "epoch": 3.4868382193695733, "percentage": 23.25, "elapsed_time": "6:00:13", "remaining_time": "19:49:25", "throughput": 8343.36, "total_tokens": 180330384} {"current_steps": 177200, "total_steps": 761865, "loss": 1.9566, "lr": 8.723662524272684e-07, "epoch": 3.488807072119076, "percentage": 23.26, "elapsed_time": "6:00:25", "remaining_time": "19:49:13", "throughput": 8343.36, "total_tokens": 180432784} {"current_steps": 177300, "total_steps": 761865, "loss": 2.0537, "lr": 8.722286235270031e-07, "epoch": 3.4907759248685792, "percentage": 23.27, "elapsed_time": "6:00:38", "remaining_time": "19:49:01", "throughput": 8343.35, "total_tokens": 180534240} {"current_steps": 177400, "total_steps": 761865, "loss": 2.0004, "lr": 8.720909313323999e-07, "epoch": 3.492744777618082, "percentage": 23.28, "elapsed_time": "6:00:50", "remaining_time": "19:48:49", "throughput": 8343.35, "total_tokens": 180636640} {"current_steps": 177500, "total_steps": 761865, "loss": 1.9714, "lr": 8.71953175866872e-07, "epoch": 3.4947136303675848, "percentage": 23.3, "elapsed_time": "6:01:02", "remaining_time": "19:48:37", "throughput": 8343.33, "total_tokens": 180737616} {"current_steps": 177600, "total_steps": 761865, "loss": 2.0145, "lr": 8.718153571538439e-07, "epoch": 3.4966824831170875, "percentage": 23.31, "elapsed_time": "6:01:14", "remaining_time": "19:48:24", "throughput": 8343.32, "total_tokens": 180838904} {"current_steps": 177700, "total_steps": 761865, "loss": 1.9813, "lr": 8.716774752167504e-07, "epoch": 3.4986513358665907, "percentage": 23.32, "elapsed_time": "6:01:26", "remaining_time": "19:48:12", "throughput": 8343.33, "total_tokens": 180941304} {"current_steps": 177800, "total_steps": 761865, "loss": 2.0262, "lr": 8.715395300790369e-07, "epoch": 3.5006201886160935, "percentage": 23.34, "elapsed_time": "6:01:39", "remaining_time": "19:48:00", "throughput": 8343.32, "total_tokens": 181042648} {"current_steps": 177900, "total_steps": 761865, "loss": 1.9373, "lr": 8.714015217641601e-07, "epoch": 3.5025890413655962, "percentage": 23.35, "elapsed_time": "6:01:51", "remaining_time": "19:47:48", "throughput": 8343.32, "total_tokens": 181145048} {"current_steps": 178000, "total_steps": 761865, "loss": 2.0458, "lr": 8.712634502955872e-07, "epoch": 3.504557894115099, "percentage": 23.36, "elapsed_time": "6:02:03", "remaining_time": "19:47:36", "throughput": 8343.32, "total_tokens": 181247448} {"current_steps": 178100, "total_steps": 761865, "loss": 2.0102, "lr": 8.711253156967959e-07, "epoch": 3.506526746864602, "percentage": 23.38, "elapsed_time": "6:02:15", "remaining_time": "19:47:24", "throughput": 8343.32, "total_tokens": 181349704} {"current_steps": 178200, "total_steps": 761865, "loss": 2.0012, "lr": 8.709871179912749e-07, "epoch": 3.508495599614105, "percentage": 23.39, "elapsed_time": "6:02:28", "remaining_time": "19:47:12", "throughput": 8343.31, "total_tokens": 181450736} {"current_steps": 178300, "total_steps": 761865, "loss": 1.9897, "lr": 8.708488572025234e-07, "epoch": 3.5104644523636077, "percentage": 23.4, "elapsed_time": "6:02:40", "remaining_time": "19:46:59", "throughput": 8343.27, "total_tokens": 181550728} {"current_steps": 178400, "total_steps": 761865, "loss": 2.0217, "lr": 8.707105333540518e-07, "epoch": 3.5124333051131105, "percentage": 23.42, "elapsed_time": "6:02:52", "remaining_time": "19:46:47", "throughput": 8343.28, "total_tokens": 181653128} {"current_steps": 178500, "total_steps": 761865, "loss": 2.0151, "lr": 8.705721464693805e-07, "epoch": 3.5144021578626132, "percentage": 23.43, "elapsed_time": "6:03:04", "remaining_time": "19:46:35", "throughput": 8343.28, "total_tokens": 181755528} {"current_steps": 178600, "total_steps": 761865, "loss": 1.9748, "lr": 8.704336965720414e-07, "epoch": 3.5163710106121164, "percentage": 23.44, "elapsed_time": "6:03:16", "remaining_time": "19:46:23", "throughput": 8343.27, "total_tokens": 181857176} {"current_steps": 178700, "total_steps": 761865, "loss": 1.9825, "lr": 8.702951836855766e-07, "epoch": 3.518339863361619, "percentage": 23.46, "elapsed_time": "6:03:29", "remaining_time": "19:46:11", "throughput": 8343.28, "total_tokens": 181959576} {"current_steps": 178800, "total_steps": 761865, "loss": 1.959, "lr": 8.70156607833539e-07, "epoch": 3.520308716111122, "percentage": 23.47, "elapsed_time": "6:03:41", "remaining_time": "19:45:59", "throughput": 8343.27, "total_tokens": 182061536} {"current_steps": 178900, "total_steps": 761865, "loss": 1.9947, "lr": 8.700179690394922e-07, "epoch": 3.522277568860625, "percentage": 23.48, "elapsed_time": "6:03:53", "remaining_time": "19:45:47", "throughput": 8343.27, "total_tokens": 182163464} {"current_steps": 179000, "total_steps": 761865, "loss": 1.9709, "lr": 8.698792673270108e-07, "epoch": 3.524246421610128, "percentage": 23.49, "elapsed_time": "6:04:05", "remaining_time": "19:45:34", "throughput": 8343.27, "total_tokens": 182265160} {"current_steps": 179100, "total_steps": 761865, "loss": 2.0081, "lr": 8.697405027196796e-07, "epoch": 3.5262152743596307, "percentage": 23.51, "elapsed_time": "6:04:17", "remaining_time": "19:45:22", "throughput": 8343.24, "total_tokens": 182366032} {"current_steps": 179200, "total_steps": 761865, "loss": 1.9512, "lr": 8.696016752410944e-07, "epoch": 3.5281841271091334, "percentage": 23.52, "elapsed_time": "6:04:30", "remaining_time": "19:45:10", "throughput": 8343.24, "total_tokens": 182468432} {"current_steps": 179300, "total_steps": 761865, "loss": 2.0498, "lr": 8.694627849148616e-07, "epoch": 3.530152979858636, "percentage": 23.53, "elapsed_time": "6:04:42", "remaining_time": "19:44:58", "throughput": 8343.24, "total_tokens": 182570832} {"current_steps": 179400, "total_steps": 761865, "loss": 1.9975, "lr": 8.693238317645988e-07, "epoch": 3.5321218326081394, "percentage": 23.55, "elapsed_time": "6:04:54", "remaining_time": "19:44:46", "throughput": 8343.25, "total_tokens": 182673232} {"current_steps": 179500, "total_steps": 761865, "loss": 1.9612, "lr": 8.691848158139331e-07, "epoch": 3.534090685357642, "percentage": 23.56, "elapsed_time": "6:05:06", "remaining_time": "19:44:34", "throughput": 8343.27, "total_tokens": 182775632} {"current_steps": 179600, "total_steps": 761865, "loss": 1.9844, "lr": 8.690457370865034e-07, "epoch": 3.536059538107145, "percentage": 23.57, "elapsed_time": "6:05:19", "remaining_time": "19:44:22", "throughput": 8343.27, "total_tokens": 182878032} {"current_steps": 179700, "total_steps": 761865, "loss": 1.9488, "lr": 8.689065956059588e-07, "epoch": 3.538028390856648, "percentage": 23.59, "elapsed_time": "6:05:31", "remaining_time": "19:44:10", "throughput": 8343.26, "total_tokens": 182979704} {"current_steps": 179800, "total_steps": 761865, "loss": 1.9948, "lr": 8.687673913959591e-07, "epoch": 3.539997243606151, "percentage": 23.6, "elapsed_time": "6:05:43", "remaining_time": "19:43:58", "throughput": 8343.25, "total_tokens": 183081480} {"current_steps": 179900, "total_steps": 761865, "loss": 1.9588, "lr": 8.686281244801748e-07, "epoch": 3.5419660963556536, "percentage": 23.61, "elapsed_time": "6:05:55", "remaining_time": "19:43:46", "throughput": 8343.25, "total_tokens": 183183880} {"current_steps": 180000, "total_steps": 761865, "loss": 1.9905, "lr": 8.684887948822872e-07, "epoch": 3.5439349491051564, "percentage": 23.63, "elapsed_time": "6:06:08", "remaining_time": "19:43:34", "throughput": 8343.26, "total_tokens": 183286280} {"current_steps": 180100, "total_steps": 761865, "loss": 2.01, "lr": 8.683494026259879e-07, "epoch": 3.545903801854659, "percentage": 23.64, "elapsed_time": "6:06:20", "remaining_time": "19:43:23", "throughput": 8343.06, "total_tokens": 183388680} {"current_steps": 180200, "total_steps": 761865, "loss": 1.9872, "lr": 8.682099477349795e-07, "epoch": 3.547872654604162, "percentage": 23.65, "elapsed_time": "6:06:33", "remaining_time": "19:43:11", "throughput": 8343.04, "total_tokens": 183489744} {"current_steps": 180300, "total_steps": 761865, "loss": 2.0279, "lr": 8.680704302329751e-07, "epoch": 3.549841507353665, "percentage": 23.67, "elapsed_time": "6:06:45", "remaining_time": "19:42:59", "throughput": 8343.04, "total_tokens": 183591624} {"current_steps": 180400, "total_steps": 761865, "loss": 2.0346, "lr": 8.679308501436985e-07, "epoch": 3.551810360103168, "percentage": 23.68, "elapsed_time": "6:06:57", "remaining_time": "19:42:47", "throughput": 8343.05, "total_tokens": 183694024} {"current_steps": 180500, "total_steps": 761865, "loss": 2.0251, "lr": 8.677912074908842e-07, "epoch": 3.5537792128526706, "percentage": 23.69, "elapsed_time": "6:07:09", "remaining_time": "19:42:34", "throughput": 8343.03, "total_tokens": 183795032} {"current_steps": 180600, "total_steps": 761865, "loss": 1.9951, "lr": 8.67651502298277e-07, "epoch": 3.555748065602174, "percentage": 23.7, "elapsed_time": "6:07:21", "remaining_time": "19:42:22", "throughput": 8343.0, "total_tokens": 183895856} {"current_steps": 180700, "total_steps": 761865, "loss": 1.9797, "lr": 8.675117345896328e-07, "epoch": 3.5577169183516766, "percentage": 23.72, "elapsed_time": "6:07:34", "remaining_time": "19:42:10", "throughput": 8343.0, "total_tokens": 183998160} {"current_steps": 180800, "total_steps": 761865, "loss": 2.0258, "lr": 8.67371904388718e-07, "epoch": 3.5596857711011793, "percentage": 23.73, "elapsed_time": "6:07:46", "remaining_time": "19:41:58", "throughput": 8342.99, "total_tokens": 184100080} {"current_steps": 180900, "total_steps": 761865, "loss": 1.9952, "lr": 8.672320117193093e-07, "epoch": 3.561654623850682, "percentage": 23.74, "elapsed_time": "6:07:58", "remaining_time": "19:41:45", "throughput": 8342.95, "total_tokens": 184200392} {"current_steps": 181000, "total_steps": 761865, "loss": 1.9979, "lr": 8.670920566051943e-07, "epoch": 3.563623476600185, "percentage": 23.76, "elapsed_time": "6:08:10", "remaining_time": "19:41:33", "throughput": 8342.94, "total_tokens": 184302000} {"current_steps": 181100, "total_steps": 761865, "loss": 1.9619, "lr": 8.669520390701715e-07, "epoch": 3.565592329349688, "percentage": 23.77, "elapsed_time": "6:08:23", "remaining_time": "19:41:21", "throughput": 8342.95, "total_tokens": 184404400} {"current_steps": 181200, "total_steps": 761865, "loss": 1.9436, "lr": 8.668119591380492e-07, "epoch": 3.567561182099191, "percentage": 23.78, "elapsed_time": "6:08:35", "remaining_time": "19:41:09", "throughput": 8342.96, "total_tokens": 184506800} {"current_steps": 181300, "total_steps": 761865, "loss": 1.991, "lr": 8.666718168326472e-07, "epoch": 3.5695300348486936, "percentage": 23.8, "elapsed_time": "6:08:47", "remaining_time": "19:40:57", "throughput": 8342.94, "total_tokens": 184608424} {"current_steps": 181400, "total_steps": 761865, "loss": 1.9495, "lr": 8.665316121777955e-07, "epoch": 3.571498887598197, "percentage": 23.81, "elapsed_time": "6:08:59", "remaining_time": "19:40:45", "throughput": 8342.94, "total_tokens": 184710528} {"current_steps": 181500, "total_steps": 761865, "loss": 2.0341, "lr": 8.663913451973346e-07, "epoch": 3.5734677403476995, "percentage": 23.82, "elapsed_time": "6:09:11", "remaining_time": "19:40:32", "throughput": 8342.91, "total_tokens": 184810776} {"current_steps": 181600, "total_steps": 761865, "loss": 1.9911, "lr": 8.662510159151156e-07, "epoch": 3.5754365930972023, "percentage": 23.84, "elapsed_time": "6:09:24", "remaining_time": "19:40:20", "throughput": 8342.92, "total_tokens": 184913176} {"current_steps": 181700, "total_steps": 761865, "loss": 2.0103, "lr": 8.661106243550005e-07, "epoch": 3.577405445846705, "percentage": 23.85, "elapsed_time": "6:09:36", "remaining_time": "19:40:08", "throughput": 8342.89, "total_tokens": 185013848} {"current_steps": 181800, "total_steps": 761865, "loss": 2.0237, "lr": 8.659701705408617e-07, "epoch": 3.579374298596208, "percentage": 23.86, "elapsed_time": "6:09:48", "remaining_time": "19:39:56", "throughput": 8342.88, "total_tokens": 185115936} {"current_steps": 181900, "total_steps": 761865, "loss": 1.962, "lr": 8.658296544965822e-07, "epoch": 3.581343151345711, "percentage": 23.88, "elapsed_time": "6:10:00", "remaining_time": "19:39:44", "throughput": 8342.88, "total_tokens": 185217720} {"current_steps": 182000, "total_steps": 761865, "loss": 1.9993, "lr": 8.656890762460553e-07, "epoch": 3.5833120040952138, "percentage": 23.89, "elapsed_time": "6:10:12", "remaining_time": "19:39:31", "throughput": 8342.86, "total_tokens": 185318928} {"current_steps": 182100, "total_steps": 761865, "loss": 1.9998, "lr": 8.655484358131855e-07, "epoch": 3.5852808568447165, "percentage": 23.9, "elapsed_time": "6:10:24", "remaining_time": "19:39:19", "throughput": 8342.84, "total_tokens": 185419008} {"current_steps": 182200, "total_steps": 761865, "loss": 1.9903, "lr": 8.654077332218873e-07, "epoch": 3.5872497095942193, "percentage": 23.91, "elapsed_time": "6:10:37", "remaining_time": "19:39:07", "throughput": 8342.82, "total_tokens": 185520616} {"current_steps": 182300, "total_steps": 761865, "loss": 1.9607, "lr": 8.65266968496086e-07, "epoch": 3.5892185623437225, "percentage": 23.93, "elapsed_time": "6:10:49", "remaining_time": "19:38:54", "throughput": 8342.79, "total_tokens": 185621336} {"current_steps": 182400, "total_steps": 761865, "loss": 2.0364, "lr": 8.651261416597178e-07, "epoch": 3.5911874150932253, "percentage": 23.94, "elapsed_time": "6:11:01", "remaining_time": "19:38:42", "throughput": 8342.78, "total_tokens": 185722904} {"current_steps": 182500, "total_steps": 761865, "loss": 1.9962, "lr": 8.649852527367286e-07, "epoch": 3.593156267842728, "percentage": 23.95, "elapsed_time": "6:11:13", "remaining_time": "19:38:30", "throughput": 8342.78, "total_tokens": 185825304} {"current_steps": 182600, "total_steps": 761865, "loss": 1.9647, "lr": 8.648443017510756e-07, "epoch": 3.5951251205922308, "percentage": 23.97, "elapsed_time": "6:11:25", "remaining_time": "19:38:18", "throughput": 8342.76, "total_tokens": 185926208} {"current_steps": 182700, "total_steps": 761865, "loss": 1.9971, "lr": 8.647032887267262e-07, "epoch": 3.5970939733417335, "percentage": 23.98, "elapsed_time": "6:11:38", "remaining_time": "19:38:05", "throughput": 8342.76, "total_tokens": 186027944} {"current_steps": 182800, "total_steps": 761865, "loss": 1.9784, "lr": 8.645622136876589e-07, "epoch": 3.5990628260912367, "percentage": 23.99, "elapsed_time": "6:11:50", "remaining_time": "19:37:53", "throughput": 8342.75, "total_tokens": 186129224} {"current_steps": 182900, "total_steps": 761865, "loss": 1.9903, "lr": 8.64421076657862e-07, "epoch": 3.6010316788407395, "percentage": 24.01, "elapsed_time": "6:12:02", "remaining_time": "19:37:41", "throughput": 8342.73, "total_tokens": 186230952} {"current_steps": 183000, "total_steps": 761865, "loss": 1.9691, "lr": 8.642798776613344e-07, "epoch": 3.6030005315902423, "percentage": 24.02, "elapsed_time": "6:12:14", "remaining_time": "19:37:29", "throughput": 8342.73, "total_tokens": 186333352} {"current_steps": 183100, "total_steps": 761865, "loss": 2.0193, "lr": 8.641386167220863e-07, "epoch": 3.6049693843397455, "percentage": 24.03, "elapsed_time": "6:12:27", "remaining_time": "19:37:17", "throughput": 8342.74, "total_tokens": 186435752} {"current_steps": 183200, "total_steps": 761865, "loss": 1.96, "lr": 8.639972938641375e-07, "epoch": 3.606938237089248, "percentage": 24.05, "elapsed_time": "6:12:39", "remaining_time": "19:37:05", "throughput": 8342.71, "total_tokens": 186536600} {"current_steps": 183300, "total_steps": 761865, "loss": 1.9586, "lr": 8.638559091115191e-07, "epoch": 3.608907089838751, "percentage": 24.06, "elapsed_time": "6:12:51", "remaining_time": "19:36:52", "throughput": 8342.72, "total_tokens": 186639000} {"current_steps": 183400, "total_steps": 761865, "loss": 2.0078, "lr": 8.637144624882724e-07, "epoch": 3.6108759425882537, "percentage": 24.07, "elapsed_time": "6:13:03", "remaining_time": "19:36:40", "throughput": 8342.72, "total_tokens": 186741400} {"current_steps": 183500, "total_steps": 761865, "loss": 1.9799, "lr": 8.63572954018449e-07, "epoch": 3.6128447953377565, "percentage": 24.09, "elapsed_time": "6:13:15", "remaining_time": "19:36:28", "throughput": 8342.72, "total_tokens": 186843048} {"current_steps": 183600, "total_steps": 761865, "loss": 1.9358, "lr": 8.634313837261111e-07, "epoch": 3.6148136480872597, "percentage": 24.1, "elapsed_time": "6:13:28", "remaining_time": "19:36:16", "throughput": 8342.72, "total_tokens": 186945448} {"current_steps": 183700, "total_steps": 761865, "loss": 1.9519, "lr": 8.632897516353319e-07, "epoch": 3.6167825008367624, "percentage": 24.11, "elapsed_time": "6:13:40", "remaining_time": "19:36:04", "throughput": 8342.73, "total_tokens": 187047848} {"current_steps": 183800, "total_steps": 761865, "loss": 1.9903, "lr": 8.631480577701947e-07, "epoch": 3.618751353586265, "percentage": 24.13, "elapsed_time": "6:13:52", "remaining_time": "19:35:52", "throughput": 8342.71, "total_tokens": 187148944} {"current_steps": 183900, "total_steps": 761865, "loss": 1.9741, "lr": 8.630063021547929e-07, "epoch": 3.6207202063357684, "percentage": 24.14, "elapsed_time": "6:14:04", "remaining_time": "19:35:40", "throughput": 8342.7, "total_tokens": 187250504} {"current_steps": 184000, "total_steps": 761865, "loss": 2.0098, "lr": 8.628644848132314e-07, "epoch": 3.622689059085271, "percentage": 24.15, "elapsed_time": "6:14:17", "remaining_time": "19:35:28", "throughput": 8342.71, "total_tokens": 187352904} {"current_steps": 184100, "total_steps": 761865, "loss": 2.0108, "lr": 8.627226057696245e-07, "epoch": 3.624657911834774, "percentage": 24.16, "elapsed_time": "6:14:29", "remaining_time": "19:35:15", "throughput": 8342.69, "total_tokens": 187454432} {"current_steps": 184200, "total_steps": 761865, "loss": 1.9512, "lr": 8.62580665048098e-07, "epoch": 3.6266267645842767, "percentage": 24.18, "elapsed_time": "6:14:41", "remaining_time": "19:35:03", "throughput": 8342.69, "total_tokens": 187556832} {"current_steps": 184300, "total_steps": 761865, "loss": 1.9921, "lr": 8.624386626727875e-07, "epoch": 3.6285956173337794, "percentage": 24.19, "elapsed_time": "6:14:53", "remaining_time": "19:34:51", "throughput": 8342.69, "total_tokens": 187658920} {"current_steps": 184400, "total_steps": 761865, "loss": 1.9784, "lr": 8.622965986678396e-07, "epoch": 3.630564470083282, "percentage": 24.2, "elapsed_time": "6:15:06", "remaining_time": "19:34:39", "throughput": 8342.68, "total_tokens": 187760560} {"current_steps": 184500, "total_steps": 761865, "loss": 1.9742, "lr": 8.621544730574106e-07, "epoch": 3.6325333228327854, "percentage": 24.22, "elapsed_time": "6:15:18", "remaining_time": "19:34:27", "throughput": 8342.68, "total_tokens": 187862960} {"current_steps": 184600, "total_steps": 761865, "loss": 1.9929, "lr": 8.62012285865668e-07, "epoch": 3.634502175582288, "percentage": 24.23, "elapsed_time": "6:15:30", "remaining_time": "19:34:15", "throughput": 8342.67, "total_tokens": 187963976} {"current_steps": 184700, "total_steps": 761865, "loss": 2.0315, "lr": 8.618700371167898e-07, "epoch": 3.636471028331791, "percentage": 24.24, "elapsed_time": "6:15:42", "remaining_time": "19:34:02", "throughput": 8342.66, "total_tokens": 188065560} {"current_steps": 184800, "total_steps": 761865, "loss": 1.9878, "lr": 8.617277268349636e-07, "epoch": 3.638439881081294, "percentage": 24.26, "elapsed_time": "6:15:54", "remaining_time": "19:33:50", "throughput": 8342.66, "total_tokens": 188167736} {"current_steps": 184900, "total_steps": 761865, "loss": 1.9637, "lr": 8.615853550443887e-07, "epoch": 3.640408733830797, "percentage": 24.27, "elapsed_time": "6:16:07", "remaining_time": "19:33:38", "throughput": 8342.65, "total_tokens": 188269344} {"current_steps": 185000, "total_steps": 761865, "loss": 2.0003, "lr": 8.614429217692738e-07, "epoch": 3.6423775865802996, "percentage": 24.28, "elapsed_time": "6:16:19", "remaining_time": "19:33:26", "throughput": 8342.64, "total_tokens": 188371744} {"current_steps": 185100, "total_steps": 761865, "loss": 2.0161, "lr": 8.613004270338384e-07, "epoch": 3.6443464393298024, "percentage": 24.3, "elapsed_time": "6:16:32", "remaining_time": "19:33:16", "throughput": 8342.42, "total_tokens": 188472352} {"current_steps": 185200, "total_steps": 761865, "loss": 1.9891, "lr": 8.611578708623131e-07, "epoch": 3.646315292079305, "percentage": 24.31, "elapsed_time": "6:16:44", "remaining_time": "19:33:03", "throughput": 8342.43, "total_tokens": 188574752} {"current_steps": 185300, "total_steps": 761865, "loss": 1.9667, "lr": 8.610152532789377e-07, "epoch": 3.6482841448288084, "percentage": 24.32, "elapsed_time": "6:16:56", "remaining_time": "19:32:51", "throughput": 8342.42, "total_tokens": 188676600} {"current_steps": 185400, "total_steps": 761865, "loss": 1.9937, "lr": 8.608725743079636e-07, "epoch": 3.650252997578311, "percentage": 24.34, "elapsed_time": "6:17:08", "remaining_time": "19:32:39", "throughput": 8342.43, "total_tokens": 188779000} {"current_steps": 185500, "total_steps": 761865, "loss": 1.9928, "lr": 8.60729833973652e-07, "epoch": 3.652221850327814, "percentage": 24.35, "elapsed_time": "6:17:21", "remaining_time": "19:32:27", "throughput": 8342.43, "total_tokens": 188881400} {"current_steps": 185600, "total_steps": 761865, "loss": 1.9409, "lr": 8.605870323002745e-07, "epoch": 3.654190703077317, "percentage": 24.36, "elapsed_time": "6:17:33", "remaining_time": "19:32:15", "throughput": 8342.44, "total_tokens": 188983800} {"current_steps": 185700, "total_steps": 761865, "loss": 1.9801, "lr": 8.604441693121136e-07, "epoch": 3.65615955582682, "percentage": 24.37, "elapsed_time": "6:17:45", "remaining_time": "19:32:03", "throughput": 8342.43, "total_tokens": 189085472} {"current_steps": 185800, "total_steps": 761865, "loss": 1.9457, "lr": 8.603012450334619e-07, "epoch": 3.6581284085763226, "percentage": 24.39, "elapsed_time": "6:17:57", "remaining_time": "19:31:51", "throughput": 8342.42, "total_tokens": 189187872} {"current_steps": 185900, "total_steps": 761865, "loss": 1.9638, "lr": 8.601582594886223e-07, "epoch": 3.6600972613258254, "percentage": 24.4, "elapsed_time": "6:18:10", "remaining_time": "19:31:39", "throughput": 8342.42, "total_tokens": 189289560} {"current_steps": 186000, "total_steps": 761865, "loss": 1.9725, "lr": 8.600152127019085e-07, "epoch": 3.662066114075328, "percentage": 24.41, "elapsed_time": "6:18:22", "remaining_time": "19:31:27", "throughput": 8342.42, "total_tokens": 189391960} {"current_steps": 186100, "total_steps": 761865, "loss": 1.9753, "lr": 8.598721046976441e-07, "epoch": 3.6640349668248313, "percentage": 24.43, "elapsed_time": "6:18:34", "remaining_time": "19:31:15", "throughput": 8342.42, "total_tokens": 189494360} {"current_steps": 186200, "total_steps": 761865, "loss": 1.9869, "lr": 8.597289355001638e-07, "epoch": 3.666003819574334, "percentage": 24.44, "elapsed_time": "6:18:46", "remaining_time": "19:31:03", "throughput": 8342.43, "total_tokens": 189596760} {"current_steps": 186300, "total_steps": 761865, "loss": 1.9507, "lr": 8.595857051338121e-07, "epoch": 3.667972672323837, "percentage": 24.45, "elapsed_time": "6:18:59", "remaining_time": "19:30:51", "throughput": 8342.43, "total_tokens": 189698688} {"current_steps": 186400, "total_steps": 761865, "loss": 1.9651, "lr": 8.594424136229439e-07, "epoch": 3.66994152507334, "percentage": 24.47, "elapsed_time": "6:19:11", "remaining_time": "19:30:38", "throughput": 8342.42, "total_tokens": 189800464} {"current_steps": 186500, "total_steps": 761865, "loss": 1.9953, "lr": 8.592990609919251e-07, "epoch": 3.671910377822843, "percentage": 24.48, "elapsed_time": "6:19:23", "remaining_time": "19:30:26", "throughput": 8342.41, "total_tokens": 189901968} {"current_steps": 186600, "total_steps": 761865, "loss": 1.9789, "lr": 8.591556472651315e-07, "epoch": 3.6738792305723456, "percentage": 24.49, "elapsed_time": "6:19:35", "remaining_time": "19:30:14", "throughput": 8342.41, "total_tokens": 190004368} {"current_steps": 186700, "total_steps": 761865, "loss": 1.9799, "lr": 8.590121724669492e-07, "epoch": 3.6758480833218483, "percentage": 24.51, "elapsed_time": "6:19:47", "remaining_time": "19:30:02", "throughput": 8342.39, "total_tokens": 190104880} {"current_steps": 186800, "total_steps": 761865, "loss": 1.9964, "lr": 8.58868636621775e-07, "epoch": 3.677816936071351, "percentage": 24.52, "elapsed_time": "6:19:59", "remaining_time": "19:29:49", "throughput": 8342.35, "total_tokens": 190205592} {"current_steps": 186900, "total_steps": 761865, "loss": 2.011, "lr": 8.587250397540163e-07, "epoch": 3.679785788820854, "percentage": 24.53, "elapsed_time": "6:20:12", "remaining_time": "19:29:37", "throughput": 8342.35, "total_tokens": 190307888} {"current_steps": 187000, "total_steps": 761865, "loss": 1.9983, "lr": 8.585813818880898e-07, "epoch": 3.681754641570357, "percentage": 24.55, "elapsed_time": "6:20:24", "remaining_time": "19:29:25", "throughput": 8342.35, "total_tokens": 190409176} {"current_steps": 187100, "total_steps": 761865, "loss": 1.9523, "lr": 8.58437663048424e-07, "epoch": 3.68372349431986, "percentage": 24.56, "elapsed_time": "6:20:36", "remaining_time": "19:29:13", "throughput": 8342.35, "total_tokens": 190511576} {"current_steps": 187200, "total_steps": 761865, "loss": 1.9646, "lr": 8.582938832594566e-07, "epoch": 3.6856923470693626, "percentage": 24.57, "elapsed_time": "6:20:48", "remaining_time": "19:29:01", "throughput": 8342.35, "total_tokens": 190612832} {"current_steps": 187300, "total_steps": 761865, "loss": 1.9459, "lr": 8.581500425456365e-07, "epoch": 3.6876611998188658, "percentage": 24.58, "elapsed_time": "6:21:01", "remaining_time": "19:28:49", "throughput": 8342.35, "total_tokens": 190715232} {"current_steps": 187400, "total_steps": 761865, "loss": 2.0061, "lr": 8.580061409314225e-07, "epoch": 3.6896300525683685, "percentage": 24.6, "elapsed_time": "6:21:13", "remaining_time": "19:28:36", "throughput": 8342.33, "total_tokens": 190816392} {"current_steps": 187500, "total_steps": 761865, "loss": 1.9828, "lr": 8.578621784412836e-07, "epoch": 3.6915989053178713, "percentage": 24.61, "elapsed_time": "6:21:25", "remaining_time": "19:28:24", "throughput": 8342.34, "total_tokens": 190918792} {"current_steps": 187600, "total_steps": 761865, "loss": 1.9355, "lr": 8.577181550996998e-07, "epoch": 3.693567758067374, "percentage": 24.62, "elapsed_time": "6:21:37", "remaining_time": "19:28:12", "throughput": 8342.34, "total_tokens": 191021192} {"current_steps": 187700, "total_steps": 761865, "loss": 1.9764, "lr": 8.575740709311607e-07, "epoch": 3.695536610816877, "percentage": 24.64, "elapsed_time": "6:21:50", "remaining_time": "19:28:00", "throughput": 8342.34, "total_tokens": 191123592} {"current_steps": 187800, "total_steps": 761865, "loss": 1.9945, "lr": 8.57429925960167e-07, "epoch": 3.69750546356638, "percentage": 24.65, "elapsed_time": "6:22:02", "remaining_time": "19:27:49", "throughput": 8342.25, "total_tokens": 191224936} {"current_steps": 187900, "total_steps": 761865, "loss": 1.9826, "lr": 8.572857202112288e-07, "epoch": 3.6994743163158827, "percentage": 24.66, "elapsed_time": "6:22:14", "remaining_time": "19:27:37", "throughput": 8342.18, "total_tokens": 191327336} {"current_steps": 188000, "total_steps": 761865, "loss": 1.9534, "lr": 8.571414537088675e-07, "epoch": 3.7014431690653855, "percentage": 24.68, "elapsed_time": "6:22:27", "remaining_time": "19:27:25", "throughput": 8342.15, "total_tokens": 191429736} {"current_steps": 188100, "total_steps": 761865, "loss": 1.9745, "lr": 8.569971264776141e-07, "epoch": 3.7034120218148887, "percentage": 24.69, "elapsed_time": "6:22:39", "remaining_time": "19:27:14", "throughput": 8342.07, "total_tokens": 191531208} {"current_steps": 188200, "total_steps": 761865, "loss": 1.9534, "lr": 8.568527385420105e-07, "epoch": 3.7053808745643915, "percentage": 24.7, "elapsed_time": "6:22:52", "remaining_time": "19:27:02", "throughput": 8342.03, "total_tokens": 191633608} {"current_steps": 188300, "total_steps": 761865, "loss": 1.9698, "lr": 8.567082899266087e-07, "epoch": 3.7073497273138942, "percentage": 24.72, "elapsed_time": "6:23:04", "remaining_time": "19:26:51", "throughput": 8341.96, "total_tokens": 191735480} {"current_steps": 188400, "total_steps": 761865, "loss": 1.9902, "lr": 8.565637806559707e-07, "epoch": 3.709318580063397, "percentage": 24.73, "elapsed_time": "6:23:16", "remaining_time": "19:26:39", "throughput": 8341.91, "total_tokens": 191837880} {"current_steps": 188500, "total_steps": 761865, "loss": 1.977, "lr": 8.564192107546693e-07, "epoch": 3.7112874328128997, "percentage": 24.74, "elapsed_time": "6:23:29", "remaining_time": "19:26:28", "throughput": 8341.85, "total_tokens": 191940280} {"current_steps": 188600, "total_steps": 761865, "loss": 1.9903, "lr": 8.562745802472871e-07, "epoch": 3.713256285562403, "percentage": 24.76, "elapsed_time": "6:23:41", "remaining_time": "19:26:16", "throughput": 8341.79, "total_tokens": 192042680} {"current_steps": 188700, "total_steps": 761865, "loss": 1.9602, "lr": 8.561298891584177e-07, "epoch": 3.7152251383119057, "percentage": 24.77, "elapsed_time": "6:23:54", "remaining_time": "19:26:04", "throughput": 8341.72, "total_tokens": 192144536} {"current_steps": 188800, "total_steps": 761865, "loss": 1.9796, "lr": 8.559851375126641e-07, "epoch": 3.7171939910614085, "percentage": 24.78, "elapsed_time": "6:24:06", "remaining_time": "19:25:52", "throughput": 8341.71, "total_tokens": 192246656} {"current_steps": 188900, "total_steps": 761865, "loss": 2.01, "lr": 8.558403253346407e-07, "epoch": 3.7191628438109112, "percentage": 24.79, "elapsed_time": "6:24:18", "remaining_time": "19:25:40", "throughput": 8341.72, "total_tokens": 192348552} {"current_steps": 189000, "total_steps": 761865, "loss": 1.9889, "lr": 8.556954526489711e-07, "epoch": 3.7211316965604144, "percentage": 24.81, "elapsed_time": "6:24:30", "remaining_time": "19:25:28", "throughput": 8341.7, "total_tokens": 192449680} {"current_steps": 189100, "total_steps": 761865, "loss": 2.0566, "lr": 8.555505194802899e-07, "epoch": 3.723100549309917, "percentage": 24.82, "elapsed_time": "6:24:43", "remaining_time": "19:25:16", "throughput": 8341.69, "total_tokens": 192551208} {"current_steps": 189200, "total_steps": 761865, "loss": 1.9601, "lr": 8.554055258532415e-07, "epoch": 3.72506940205942, "percentage": 24.83, "elapsed_time": "6:24:55", "remaining_time": "19:25:03", "throughput": 8341.66, "total_tokens": 192651576} {"current_steps": 189300, "total_steps": 761865, "loss": 1.9817, "lr": 8.552604717924813e-07, "epoch": 3.7270382548089227, "percentage": 24.85, "elapsed_time": "6:25:07", "remaining_time": "19:24:51", "throughput": 8341.66, "total_tokens": 192753976} {"current_steps": 189400, "total_steps": 761865, "loss": 1.9943, "lr": 8.551153573226742e-07, "epoch": 3.7290071075584255, "percentage": 24.86, "elapsed_time": "6:25:19", "remaining_time": "19:24:39", "throughput": 8341.65, "total_tokens": 192855344} {"current_steps": 189500, "total_steps": 761865, "loss": 1.9913, "lr": 8.549701824684958e-07, "epoch": 3.7309759603079287, "percentage": 24.87, "elapsed_time": "6:25:31", "remaining_time": "19:24:27", "throughput": 8341.65, "total_tokens": 192957104} {"current_steps": 189600, "total_steps": 761865, "loss": 1.9509, "lr": 8.548249472546318e-07, "epoch": 3.7329448130574314, "percentage": 24.89, "elapsed_time": "6:25:43", "remaining_time": "19:24:14", "throughput": 8341.64, "total_tokens": 193058936} {"current_steps": 189700, "total_steps": 761865, "loss": 2.0122, "lr": 8.546796517057783e-07, "epoch": 3.734913665806934, "percentage": 24.9, "elapsed_time": "6:25:56", "remaining_time": "19:24:02", "throughput": 8341.62, "total_tokens": 193159800} {"current_steps": 189800, "total_steps": 761865, "loss": 2.0278, "lr": 8.545342958466415e-07, "epoch": 3.7368825185564374, "percentage": 24.91, "elapsed_time": "6:26:08", "remaining_time": "19:23:50", "throughput": 8341.59, "total_tokens": 193260264} {"current_steps": 189900, "total_steps": 761865, "loss": 1.99, "lr": 8.543888797019379e-07, "epoch": 3.73885137130594, "percentage": 24.93, "elapsed_time": "6:26:20", "remaining_time": "19:23:37", "throughput": 8341.56, "total_tokens": 193361032} {"current_steps": 190000, "total_steps": 761865, "loss": 2.0445, "lr": 8.542434032963945e-07, "epoch": 3.740820224055443, "percentage": 24.94, "elapsed_time": "6:26:32", "remaining_time": "19:23:25", "throughput": 8341.56, "total_tokens": 193462888} {"current_steps": 190100, "total_steps": 761865, "loss": 2.0123, "lr": 8.540978666547481e-07, "epoch": 3.7427890768049457, "percentage": 24.95, "elapsed_time": "6:26:45", "remaining_time": "19:23:15", "throughput": 8341.35, "total_tokens": 193564496} {"current_steps": 190200, "total_steps": 761865, "loss": 1.9979, "lr": 8.539522698017461e-07, "epoch": 3.7447579295544484, "percentage": 24.97, "elapsed_time": "6:26:57", "remaining_time": "19:23:02", "throughput": 8341.35, "total_tokens": 193666456} {"current_steps": 190300, "total_steps": 761865, "loss": 2.0014, "lr": 8.53806612762146e-07, "epoch": 3.7467267823039516, "percentage": 24.98, "elapsed_time": "6:27:09", "remaining_time": "19:22:50", "throughput": 8341.36, "total_tokens": 193768856} {"current_steps": 190400, "total_steps": 761865, "loss": 2.0196, "lr": 8.536608955607156e-07, "epoch": 3.7486956350534544, "percentage": 24.99, "elapsed_time": "6:27:22", "remaining_time": "19:22:38", "throughput": 8341.35, "total_tokens": 193870632} {"current_steps": 190500, "total_steps": 761865, "loss": 1.9436, "lr": 8.535151182222327e-07, "epoch": 3.750664487802957, "percentage": 25.0, "elapsed_time": "6:27:34", "remaining_time": "19:22:26", "throughput": 8341.36, "total_tokens": 193973032} {"current_steps": 190600, "total_steps": 761865, "loss": 1.997, "lr": 8.533692807714858e-07, "epoch": 3.7526333405524603, "percentage": 25.02, "elapsed_time": "6:27:46", "remaining_time": "19:22:14", "throughput": 8341.36, "total_tokens": 194075016} {"current_steps": 190700, "total_steps": 761865, "loss": 1.9966, "lr": 8.532233832332729e-07, "epoch": 3.754602193301963, "percentage": 25.03, "elapsed_time": "6:27:58", "remaining_time": "19:22:02", "throughput": 8341.36, "total_tokens": 194176776} {"current_steps": 190800, "total_steps": 761865, "loss": 1.9886, "lr": 8.530774256324032e-07, "epoch": 3.756571046051466, "percentage": 25.04, "elapsed_time": "6:28:11", "remaining_time": "19:21:50", "throughput": 8341.36, "total_tokens": 194278600} {"current_steps": 190900, "total_steps": 761865, "loss": 2.0213, "lr": 8.529314079936951e-07, "epoch": 3.7585398988009686, "percentage": 25.06, "elapsed_time": "6:28:23", "remaining_time": "19:21:37", "throughput": 8341.34, "total_tokens": 194380088} {"current_steps": 191000, "total_steps": 761865, "loss": 1.9507, "lr": 8.527853303419779e-07, "epoch": 3.7605087515504714, "percentage": 25.07, "elapsed_time": "6:28:35", "remaining_time": "19:21:25", "throughput": 8341.32, "total_tokens": 194481016} {"current_steps": 191100, "total_steps": 761865, "loss": 2.0071, "lr": 8.526391927020907e-07, "epoch": 3.762477604299974, "percentage": 25.08, "elapsed_time": "6:28:47", "remaining_time": "19:21:12", "throughput": 8341.28, "total_tokens": 194580744} {"current_steps": 191200, "total_steps": 761865, "loss": 1.9863, "lr": 8.52492995098883e-07, "epoch": 3.7644464570494773, "percentage": 25.1, "elapsed_time": "6:28:59", "remaining_time": "19:21:00", "throughput": 8341.28, "total_tokens": 194682592} {"current_steps": 191300, "total_steps": 761865, "loss": 1.9554, "lr": 8.523467375572148e-07, "epoch": 3.76641530979898, "percentage": 25.11, "elapsed_time": "6:29:11", "remaining_time": "19:20:48", "throughput": 8341.27, "total_tokens": 194784152} {"current_steps": 191400, "total_steps": 761865, "loss": 1.9964, "lr": 8.522004201019556e-07, "epoch": 3.768384162548483, "percentage": 25.12, "elapsed_time": "6:29:23", "remaining_time": "19:20:35", "throughput": 8341.25, "total_tokens": 194884664} {"current_steps": 191500, "total_steps": 761865, "loss": 1.9821, "lr": 8.520540427579854e-07, "epoch": 3.770353015297986, "percentage": 25.14, "elapsed_time": "6:29:36", "remaining_time": "19:20:23", "throughput": 8341.25, "total_tokens": 194987064} {"current_steps": 191600, "total_steps": 761865, "loss": 1.9732, "lr": 8.519076055501948e-07, "epoch": 3.772321868047489, "percentage": 25.15, "elapsed_time": "6:29:48", "remaining_time": "19:20:11", "throughput": 8341.25, "total_tokens": 195088424} {"current_steps": 191700, "total_steps": 761865, "loss": 1.973, "lr": 8.517611085034839e-07, "epoch": 3.7742907207969916, "percentage": 25.16, "elapsed_time": "6:30:00", "remaining_time": "19:19:59", "throughput": 8341.25, "total_tokens": 195190344} {"current_steps": 191800, "total_steps": 761865, "loss": 1.9973, "lr": 8.516145516427635e-07, "epoch": 3.7762595735464943, "percentage": 25.18, "elapsed_time": "6:30:12", "remaining_time": "19:19:46", "throughput": 8341.23, "total_tokens": 195290768} {"current_steps": 191900, "total_steps": 761865, "loss": 1.9831, "lr": 8.514679349929541e-07, "epoch": 3.778228426295997, "percentage": 25.19, "elapsed_time": "6:30:24", "remaining_time": "19:19:34", "throughput": 8341.23, "total_tokens": 195393168} {"current_steps": 192000, "total_steps": 761865, "loss": 1.9653, "lr": 8.513212585789869e-07, "epoch": 3.7801972790455003, "percentage": 25.2, "elapsed_time": "6:30:37", "remaining_time": "19:19:22", "throughput": 8341.23, "total_tokens": 195495224} {"current_steps": 192100, "total_steps": 761865, "loss": 1.9975, "lr": 8.511745224258028e-07, "epoch": 3.782166131795003, "percentage": 25.21, "elapsed_time": "6:30:49", "remaining_time": "19:19:10", "throughput": 8341.23, "total_tokens": 195597624} {"current_steps": 192200, "total_steps": 761865, "loss": 1.9709, "lr": 8.510277265583532e-07, "epoch": 3.784134984544506, "percentage": 25.23, "elapsed_time": "6:31:01", "remaining_time": "19:18:58", "throughput": 8341.24, "total_tokens": 195700024} {"current_steps": 192300, "total_steps": 761865, "loss": 1.9736, "lr": 8.508808710015992e-07, "epoch": 3.786103837294009, "percentage": 25.24, "elapsed_time": "6:31:13", "remaining_time": "19:18:46", "throughput": 8341.25, "total_tokens": 195801880} {"current_steps": 192400, "total_steps": 761865, "loss": 1.9991, "lr": 8.507339557805127e-07, "epoch": 3.7880726900435118, "percentage": 25.25, "elapsed_time": "6:31:26", "remaining_time": "19:18:34", "throughput": 8341.24, "total_tokens": 195903720} {"current_steps": 192500, "total_steps": 761865, "loss": 2.0377, "lr": 8.505869809200752e-07, "epoch": 3.7900415427930145, "percentage": 25.27, "elapsed_time": "6:31:38", "remaining_time": "19:18:22", "throughput": 8341.24, "total_tokens": 196006120} {"current_steps": 192600, "total_steps": 761865, "loss": 1.9689, "lr": 8.504399464452785e-07, "epoch": 3.7920103955425173, "percentage": 25.28, "elapsed_time": "6:31:50", "remaining_time": "19:18:10", "throughput": 8341.25, "total_tokens": 196108520} {"current_steps": 192700, "total_steps": 761865, "loss": 1.9871, "lr": 8.502928523811249e-07, "epoch": 3.79397924829202, "percentage": 25.29, "elapsed_time": "6:32:02", "remaining_time": "19:17:58", "throughput": 8341.24, "total_tokens": 196210176} {"current_steps": 192800, "total_steps": 761865, "loss": 1.98, "lr": 8.50145698752626e-07, "epoch": 3.7959481010415232, "percentage": 25.31, "elapsed_time": "6:32:15", "remaining_time": "19:17:45", "throughput": 8341.25, "total_tokens": 196312576} {"current_steps": 192900, "total_steps": 761865, "loss": 2.0401, "lr": 8.499984855848044e-07, "epoch": 3.797916953791026, "percentage": 25.32, "elapsed_time": "6:32:27", "remaining_time": "19:17:33", "throughput": 8341.24, "total_tokens": 196414976} {"current_steps": 193000, "total_steps": 761865, "loss": 2.027, "lr": 8.498512129026924e-07, "epoch": 3.7998858065405288, "percentage": 25.33, "elapsed_time": "6:32:39", "remaining_time": "19:17:21", "throughput": 8341.24, "total_tokens": 196516168} {"current_steps": 193100, "total_steps": 761865, "loss": 2.0009, "lr": 8.497038807313324e-07, "epoch": 3.801854659290032, "percentage": 25.35, "elapsed_time": "6:32:51", "remaining_time": "19:17:09", "throughput": 8341.25, "total_tokens": 196618568} {"current_steps": 193200, "total_steps": 761865, "loss": 2.003, "lr": 8.495564890957769e-07, "epoch": 3.8038235120395347, "percentage": 25.36, "elapsed_time": "6:33:04", "remaining_time": "19:16:57", "throughput": 8341.23, "total_tokens": 196719792} {"current_steps": 193300, "total_steps": 761865, "loss": 1.9892, "lr": 8.494090380210888e-07, "epoch": 3.8057923647890375, "percentage": 25.37, "elapsed_time": "6:33:16", "remaining_time": "19:16:44", "throughput": 8341.22, "total_tokens": 196821376} {"current_steps": 193400, "total_steps": 761865, "loss": 1.9502, "lr": 8.492615275323409e-07, "epoch": 3.8077612175385402, "percentage": 25.39, "elapsed_time": "6:33:28", "remaining_time": "19:16:32", "throughput": 8341.23, "total_tokens": 196923776} {"current_steps": 193500, "total_steps": 761865, "loss": 1.9644, "lr": 8.49113957654616e-07, "epoch": 3.809730070288043, "percentage": 25.4, "elapsed_time": "6:33:40", "remaining_time": "19:16:20", "throughput": 8341.18, "total_tokens": 197023584} {"current_steps": 193600, "total_steps": 761865, "loss": 1.9929, "lr": 8.489663284130071e-07, "epoch": 3.8116989230375458, "percentage": 25.41, "elapsed_time": "6:33:52", "remaining_time": "19:16:08", "throughput": 8341.19, "total_tokens": 197125984} {"current_steps": 193700, "total_steps": 761865, "loss": 1.9873, "lr": 8.488186398326175e-07, "epoch": 3.813667775787049, "percentage": 25.42, "elapsed_time": "6:34:05", "remaining_time": "19:15:56", "throughput": 8341.19, "total_tokens": 197227784} {"current_steps": 193800, "total_steps": 761865, "loss": 1.9699, "lr": 8.486708919385601e-07, "epoch": 3.8156366285365517, "percentage": 25.44, "elapsed_time": "6:34:17", "remaining_time": "19:15:44", "throughput": 8341.2, "total_tokens": 197330184} {"current_steps": 193900, "total_steps": 761865, "loss": 1.9702, "lr": 8.485230847559586e-07, "epoch": 3.8176054812860545, "percentage": 25.45, "elapsed_time": "6:34:29", "remaining_time": "19:15:32", "throughput": 8341.2, "total_tokens": 197432584} {"current_steps": 194000, "total_steps": 761865, "loss": 1.9834, "lr": 8.48375218309946e-07, "epoch": 3.8195743340355577, "percentage": 25.46, "elapsed_time": "6:34:41", "remaining_time": "19:15:19", "throughput": 8341.22, "total_tokens": 197534984} {"current_steps": 194100, "total_steps": 761865, "loss": 2.0257, "lr": 8.482272926256657e-07, "epoch": 3.8215431867850604, "percentage": 25.48, "elapsed_time": "6:34:54", "remaining_time": "19:15:07", "throughput": 8341.21, "total_tokens": 197636808} {"current_steps": 194200, "total_steps": 761865, "loss": 1.9356, "lr": 8.480793077282715e-07, "epoch": 3.823512039534563, "percentage": 25.49, "elapsed_time": "6:35:06", "remaining_time": "19:14:55", "throughput": 8341.22, "total_tokens": 197739208} {"current_steps": 194300, "total_steps": 761865, "loss": 1.9702, "lr": 8.47931263642927e-07, "epoch": 3.825480892284066, "percentage": 25.5, "elapsed_time": "6:35:18", "remaining_time": "19:14:43", "throughput": 8341.2, "total_tokens": 197840224} {"current_steps": 194400, "total_steps": 761865, "loss": 1.9928, "lr": 8.477831603948056e-07, "epoch": 3.8274497450335687, "percentage": 25.52, "elapsed_time": "6:35:30", "remaining_time": "19:14:31", "throughput": 8341.2, "total_tokens": 197941960} {"current_steps": 194500, "total_steps": 761865, "loss": 1.9904, "lr": 8.47634998009091e-07, "epoch": 3.829418597783072, "percentage": 25.53, "elapsed_time": "6:35:42", "remaining_time": "19:14:18", "throughput": 8341.2, "total_tokens": 198043864} {"current_steps": 194600, "total_steps": 761865, "loss": 2.0096, "lr": 8.474867765109772e-07, "epoch": 3.8313874505325747, "percentage": 25.54, "elapsed_time": "6:35:55", "remaining_time": "19:14:06", "throughput": 8341.2, "total_tokens": 198145640} {"current_steps": 194700, "total_steps": 761865, "loss": 1.979, "lr": 8.473384959256678e-07, "epoch": 3.8333563032820774, "percentage": 25.56, "elapsed_time": "6:36:07", "remaining_time": "19:13:54", "throughput": 8341.2, "total_tokens": 198248040} {"current_steps": 194800, "total_steps": 761865, "loss": 2.0032, "lr": 8.471901562783767e-07, "epoch": 3.8353251560315806, "percentage": 25.57, "elapsed_time": "6:36:19", "remaining_time": "19:13:42", "throughput": 8341.18, "total_tokens": 198348840} {"current_steps": 194900, "total_steps": 761865, "loss": 1.9444, "lr": 8.47041757594328e-07, "epoch": 3.8372940087810834, "percentage": 25.58, "elapsed_time": "6:36:31", "remaining_time": "19:13:30", "throughput": 8341.18, "total_tokens": 198451240} {"current_steps": 195000, "total_steps": 761865, "loss": 1.9965, "lr": 8.468932998987556e-07, "epoch": 3.839262861530586, "percentage": 25.6, "elapsed_time": "6:36:43", "remaining_time": "19:13:18", "throughput": 8341.16, "total_tokens": 198552328} {"current_steps": 195100, "total_steps": 761865, "loss": 2.0584, "lr": 8.467447832169032e-07, "epoch": 3.841231714280089, "percentage": 25.61, "elapsed_time": "6:36:56", "remaining_time": "19:13:07", "throughput": 8340.95, "total_tokens": 198653104} {"current_steps": 195200, "total_steps": 761865, "loss": 1.9778, "lr": 8.465962075740252e-07, "epoch": 3.8432005670295917, "percentage": 25.62, "elapsed_time": "6:37:08", "remaining_time": "19:12:54", "throughput": 8340.95, "total_tokens": 198754936} {"current_steps": 195300, "total_steps": 761865, "loss": 1.969, "lr": 8.464475729953853e-07, "epoch": 3.845169419779095, "percentage": 25.63, "elapsed_time": "6:37:21", "remaining_time": "19:12:42", "throughput": 8340.96, "total_tokens": 198857336} {"current_steps": 195400, "total_steps": 761865, "loss": 1.9855, "lr": 8.462988795062575e-07, "epoch": 3.8471382725285976, "percentage": 25.65, "elapsed_time": "6:37:33", "remaining_time": "19:12:30", "throughput": 8340.97, "total_tokens": 198959736} {"current_steps": 195500, "total_steps": 761865, "loss": 1.9842, "lr": 8.461501271319262e-07, "epoch": 3.8491071252781004, "percentage": 25.66, "elapsed_time": "6:37:45", "remaining_time": "19:12:18", "throughput": 8340.98, "total_tokens": 199062136} {"current_steps": 195600, "total_steps": 761865, "loss": 2.0087, "lr": 8.460013158976856e-07, "epoch": 3.851075978027603, "percentage": 25.67, "elapsed_time": "6:37:57", "remaining_time": "19:12:06", "throughput": 8340.99, "total_tokens": 199164536} {"current_steps": 195700, "total_steps": 761865, "loss": 2.0274, "lr": 8.458524458288392e-07, "epoch": 3.8530448307771064, "percentage": 25.69, "elapsed_time": "6:38:10", "remaining_time": "19:11:54", "throughput": 8340.99, "total_tokens": 199266432} {"current_steps": 195800, "total_steps": 761865, "loss": 1.9717, "lr": 8.457035169507017e-07, "epoch": 3.855013683526609, "percentage": 25.7, "elapsed_time": "6:38:22", "remaining_time": "19:11:42", "throughput": 8341.0, "total_tokens": 199368832} {"current_steps": 195900, "total_steps": 761865, "loss": 2.0065, "lr": 8.455545292885966e-07, "epoch": 3.856982536276112, "percentage": 25.71, "elapsed_time": "6:38:34", "remaining_time": "19:11:30", "throughput": 8340.99, "total_tokens": 199470312} {"current_steps": 196000, "total_steps": 761865, "loss": 1.9557, "lr": 8.454054828678586e-07, "epoch": 3.8589513890256146, "percentage": 25.73, "elapsed_time": "6:38:46", "remaining_time": "19:11:17", "throughput": 8341.0, "total_tokens": 199572712} {"current_steps": 196100, "total_steps": 761865, "loss": 2.0068, "lr": 8.452563777138315e-07, "epoch": 3.8609202417751174, "percentage": 25.74, "elapsed_time": "6:38:58", "remaining_time": "19:11:05", "throughput": 8341.0, "total_tokens": 199674312} {"current_steps": 196200, "total_steps": 761865, "loss": 1.9492, "lr": 8.451072138518694e-07, "epoch": 3.8628890945246206, "percentage": 25.75, "elapsed_time": "6:39:11", "remaining_time": "19:10:53", "throughput": 8341.01, "total_tokens": 199776712} {"current_steps": 196300, "total_steps": 761865, "loss": 1.9589, "lr": 8.449579913073362e-07, "epoch": 3.8648579472741234, "percentage": 25.77, "elapsed_time": "6:39:23", "remaining_time": "19:10:41", "throughput": 8340.98, "total_tokens": 199876728} {"current_steps": 196400, "total_steps": 761865, "loss": 1.996, "lr": 8.448087101056063e-07, "epoch": 3.866826800023626, "percentage": 25.78, "elapsed_time": "6:39:35", "remaining_time": "19:10:28", "throughput": 8340.98, "total_tokens": 199978424} {"current_steps": 196500, "total_steps": 761865, "loss": 1.987, "lr": 8.446593702720633e-07, "epoch": 3.8687956527731293, "percentage": 25.79, "elapsed_time": "6:39:47", "remaining_time": "19:10:16", "throughput": 8340.96, "total_tokens": 200079264} {"current_steps": 196600, "total_steps": 761865, "loss": 1.9845, "lr": 8.445099718321014e-07, "epoch": 3.870764505522632, "percentage": 25.81, "elapsed_time": "6:39:59", "remaining_time": "19:10:04", "throughput": 8340.95, "total_tokens": 200180888} {"current_steps": 196700, "total_steps": 761865, "loss": 1.9131, "lr": 8.443605148111247e-07, "epoch": 3.872733358272135, "percentage": 25.82, "elapsed_time": "6:40:12", "remaining_time": "19:09:52", "throughput": 8340.95, "total_tokens": 200283288} {"current_steps": 196800, "total_steps": 761865, "loss": 1.9981, "lr": 8.442109992345468e-07, "epoch": 3.8747022110216376, "percentage": 25.83, "elapsed_time": "6:40:24", "remaining_time": "19:09:39", "throughput": 8340.93, "total_tokens": 200384456} {"current_steps": 196900, "total_steps": 761865, "loss": 1.9838, "lr": 8.440614251277918e-07, "epoch": 3.8766710637711403, "percentage": 25.84, "elapsed_time": "6:40:36", "remaining_time": "19:09:27", "throughput": 8340.93, "total_tokens": 200485656} {"current_steps": 197000, "total_steps": 761865, "loss": 2.0387, "lr": 8.439117925162933e-07, "epoch": 3.8786399165206435, "percentage": 25.86, "elapsed_time": "6:40:48", "remaining_time": "19:09:15", "throughput": 8340.92, "total_tokens": 200587456} {"current_steps": 197100, "total_steps": 761865, "loss": 2.0066, "lr": 8.437621014254952e-07, "epoch": 3.8806087692701463, "percentage": 25.87, "elapsed_time": "6:41:00", "remaining_time": "19:09:03", "throughput": 8340.93, "total_tokens": 200689856} {"current_steps": 197200, "total_steps": 761865, "loss": 1.9351, "lr": 8.436123518808511e-07, "epoch": 3.882577622019649, "percentage": 25.88, "elapsed_time": "6:41:13", "remaining_time": "19:08:51", "throughput": 8340.94, "total_tokens": 200792256} {"current_steps": 197300, "total_steps": 761865, "loss": 2.0019, "lr": 8.434625439078247e-07, "epoch": 3.8845464747691523, "percentage": 25.9, "elapsed_time": "6:41:25", "remaining_time": "19:08:38", "throughput": 8340.93, "total_tokens": 200893392} {"current_steps": 197400, "total_steps": 761865, "loss": 1.9791, "lr": 8.433126775318899e-07, "epoch": 3.886515327518655, "percentage": 25.91, "elapsed_time": "6:41:37", "remaining_time": "19:08:26", "throughput": 8340.93, "total_tokens": 200995272} {"current_steps": 197500, "total_steps": 761865, "loss": 2.0071, "lr": 8.431627527785297e-07, "epoch": 3.888484180268158, "percentage": 25.92, "elapsed_time": "6:41:49", "remaining_time": "19:08:14", "throughput": 8340.93, "total_tokens": 201097672} {"current_steps": 197600, "total_steps": 761865, "loss": 1.9774, "lr": 8.430127696732376e-07, "epoch": 3.8904530330176605, "percentage": 25.94, "elapsed_time": "6:42:02", "remaining_time": "19:08:02", "throughput": 8340.93, "total_tokens": 201200072} {"current_steps": 197700, "total_steps": 761865, "loss": 1.973, "lr": 8.428627282415173e-07, "epoch": 3.8924218857671633, "percentage": 25.95, "elapsed_time": "6:42:14", "remaining_time": "19:07:50", "throughput": 8340.92, "total_tokens": 201301280} {"current_steps": 197800, "total_steps": 761865, "loss": 1.9979, "lr": 8.427126285088819e-07, "epoch": 3.894390738516666, "percentage": 25.96, "elapsed_time": "6:42:26", "remaining_time": "19:07:38", "throughput": 8340.93, "total_tokens": 201403680} {"current_steps": 197900, "total_steps": 761865, "loss": 1.9887, "lr": 8.425624705008546e-07, "epoch": 3.8963595912661693, "percentage": 25.98, "elapsed_time": "6:42:38", "remaining_time": "19:07:26", "throughput": 8340.91, "total_tokens": 201505152} {"current_steps": 198000, "total_steps": 761865, "loss": 1.9901, "lr": 8.424122542429685e-07, "epoch": 3.898328444015672, "percentage": 25.99, "elapsed_time": "6:42:50", "remaining_time": "19:07:14", "throughput": 8340.91, "total_tokens": 201607552} {"current_steps": 198100, "total_steps": 761865, "loss": 1.9962, "lr": 8.422619797607667e-07, "epoch": 3.900297296765175, "percentage": 26.0, "elapsed_time": "6:43:03", "remaining_time": "19:07:01", "throughput": 8340.91, "total_tokens": 201709952} {"current_steps": 198200, "total_steps": 761865, "loss": 1.9556, "lr": 8.421116470798018e-07, "epoch": 3.902266149514678, "percentage": 26.02, "elapsed_time": "6:43:15", "remaining_time": "19:06:49", "throughput": 8340.89, "total_tokens": 201810960} {"current_steps": 198300, "total_steps": 761865, "loss": 2.028, "lr": 8.419612562256369e-07, "epoch": 3.9042350022641807, "percentage": 26.03, "elapsed_time": "6:43:27", "remaining_time": "19:06:37", "throughput": 8340.9, "total_tokens": 201913360} {"current_steps": 198400, "total_steps": 761865, "loss": 1.9523, "lr": 8.418108072238446e-07, "epoch": 3.9062038550136835, "percentage": 26.04, "elapsed_time": "6:43:39", "remaining_time": "19:06:25", "throughput": 8340.86, "total_tokens": 202015176} {"current_steps": 198500, "total_steps": 761865, "loss": 2.0028, "lr": 8.416603001000075e-07, "epoch": 3.9081727077631863, "percentage": 26.05, "elapsed_time": "6:43:52", "remaining_time": "19:06:13", "throughput": 8340.8, "total_tokens": 202116712} {"current_steps": 198600, "total_steps": 761865, "loss": 1.9562, "lr": 8.415097348797181e-07, "epoch": 3.910141560512689, "percentage": 26.07, "elapsed_time": "6:44:04", "remaining_time": "19:06:02", "throughput": 8340.77, "total_tokens": 202219112} {"current_steps": 198700, "total_steps": 761865, "loss": 1.9894, "lr": 8.413591115885788e-07, "epoch": 3.912110413262192, "percentage": 26.08, "elapsed_time": "6:44:17", "remaining_time": "19:05:50", "throughput": 8340.74, "total_tokens": 202321512} {"current_steps": 198800, "total_steps": 761865, "loss": 1.996, "lr": 8.412084302522016e-07, "epoch": 3.914079266011695, "percentage": 26.09, "elapsed_time": "6:44:29", "remaining_time": "19:05:38", "throughput": 8340.7, "total_tokens": 202423496} {"current_steps": 198900, "total_steps": 761865, "loss": 1.9765, "lr": 8.410576908962087e-07, "epoch": 3.9160481187611977, "percentage": 26.11, "elapsed_time": "6:44:41", "remaining_time": "19:05:26", "throughput": 8340.68, "total_tokens": 202525256} {"current_steps": 199000, "total_steps": 761865, "loss": 1.9696, "lr": 8.409068935462322e-07, "epoch": 3.918016971510701, "percentage": 26.12, "elapsed_time": "6:44:53", "remaining_time": "19:05:14", "throughput": 8340.69, "total_tokens": 202627656} {"current_steps": 199100, "total_steps": 761865, "loss": 1.9455, "lr": 8.407560382279136e-07, "epoch": 3.9199858242602037, "percentage": 26.13, "elapsed_time": "6:45:06", "remaining_time": "19:05:02", "throughput": 8340.7, "total_tokens": 202730056} {"current_steps": 199200, "total_steps": 761865, "loss": 1.9787, "lr": 8.406051249669049e-07, "epoch": 3.9219546770097065, "percentage": 26.15, "elapsed_time": "6:45:18", "remaining_time": "19:04:50", "throughput": 8340.7, "total_tokens": 202831760} {"current_steps": 199300, "total_steps": 761865, "loss": 1.9847, "lr": 8.404541537888674e-07, "epoch": 3.923923529759209, "percentage": 26.16, "elapsed_time": "6:45:30", "remaining_time": "19:04:38", "throughput": 8340.7, "total_tokens": 202934160} {"current_steps": 199400, "total_steps": 761865, "loss": 1.9484, "lr": 8.403031247194728e-07, "epoch": 3.925892382508712, "percentage": 26.17, "elapsed_time": "6:45:42", "remaining_time": "19:04:25", "throughput": 8340.71, "total_tokens": 203036560} {"current_steps": 199500, "total_steps": 761865, "loss": 1.959, "lr": 8.401520377844018e-07, "epoch": 3.927861235258215, "percentage": 26.19, "elapsed_time": "6:45:55", "remaining_time": "19:04:13", "throughput": 8340.7, "total_tokens": 203138032} {"current_steps": 199600, "total_steps": 761865, "loss": 1.9658, "lr": 8.400008930093459e-07, "epoch": 3.929830088007718, "percentage": 26.2, "elapsed_time": "6:46:07", "remaining_time": "19:04:01", "throughput": 8340.71, "total_tokens": 203240432} {"current_steps": 199700, "total_steps": 761865, "loss": 1.9998, "lr": 8.398496904200059e-07, "epoch": 3.9317989407572207, "percentage": 26.21, "elapsed_time": "6:46:19", "remaining_time": "19:03:49", "throughput": 8340.69, "total_tokens": 203340840} {"current_steps": 199800, "total_steps": 761865, "loss": 2.0053, "lr": 8.396984300420924e-07, "epoch": 3.933767793506724, "percentage": 26.23, "elapsed_time": "6:46:31", "remaining_time": "19:03:36", "throughput": 8340.66, "total_tokens": 203440832} {"current_steps": 199900, "total_steps": 761865, "loss": 2.041, "lr": 8.39547111901326e-07, "epoch": 3.9357366462562267, "percentage": 26.24, "elapsed_time": "6:46:43", "remaining_time": "19:03:24", "throughput": 8340.65, "total_tokens": 203542464} {"current_steps": 200000, "total_steps": 761865, "loss": 1.9668, "lr": 8.393957360234371e-07, "epoch": 3.9377054990057294, "percentage": 26.25, "elapsed_time": "6:46:55", "remaining_time": "19:03:12", "throughput": 8340.64, "total_tokens": 203644096} {"current_steps": 200100, "total_steps": 761865, "loss": 2.036, "lr": 8.39244302434166e-07, "epoch": 3.939674351755232, "percentage": 26.26, "elapsed_time": "6:47:08", "remaining_time": "19:03:01", "throughput": 8340.47, "total_tokens": 203746496} {"current_steps": 200200, "total_steps": 761865, "loss": 1.998, "lr": 8.390928111592624e-07, "epoch": 3.941643204504735, "percentage": 26.28, "elapsed_time": "6:47:20", "remaining_time": "19:02:49", "throughput": 8340.47, "total_tokens": 203848288} {"current_steps": 200300, "total_steps": 761865, "loss": 1.9637, "lr": 8.389412622244865e-07, "epoch": 3.9436120572542377, "percentage": 26.29, "elapsed_time": "6:47:33", "remaining_time": "19:02:37", "throughput": 8340.47, "total_tokens": 203950688} {"current_steps": 200400, "total_steps": 761865, "loss": 2.0262, "lr": 8.387896556556076e-07, "epoch": 3.945580910003741, "percentage": 26.3, "elapsed_time": "6:47:45", "remaining_time": "19:02:25", "throughput": 8340.48, "total_tokens": 204053088} {"current_steps": 200500, "total_steps": 761865, "loss": 1.9907, "lr": 8.386379914784052e-07, "epoch": 3.9475497627532437, "percentage": 26.32, "elapsed_time": "6:47:57", "remaining_time": "19:02:13", "throughput": 8340.49, "total_tokens": 204155488} {"current_steps": 200600, "total_steps": 761865, "loss": 1.9869, "lr": 8.384862697186685e-07, "epoch": 3.9495186155027464, "percentage": 26.33, "elapsed_time": "6:48:09", "remaining_time": "19:02:00", "throughput": 8340.48, "total_tokens": 204256816} {"current_steps": 200700, "total_steps": 761865, "loss": 1.9518, "lr": 8.383344904021967e-07, "epoch": 3.9514874682522496, "percentage": 26.34, "elapsed_time": "6:48:22", "remaining_time": "19:01:48", "throughput": 8340.47, "total_tokens": 204358720} {"current_steps": 200800, "total_steps": 761865, "loss": 2.001, "lr": 8.381826535547985e-07, "epoch": 3.9534563210017524, "percentage": 26.36, "elapsed_time": "6:48:34", "remaining_time": "19:01:36", "throughput": 8340.48, "total_tokens": 204461120} {"current_steps": 200900, "total_steps": 761865, "loss": 1.9508, "lr": 8.380307592022924e-07, "epoch": 3.955425173751255, "percentage": 26.37, "elapsed_time": "6:48:46", "remaining_time": "19:01:24", "throughput": 8340.49, "total_tokens": 204563520} {"current_steps": 201000, "total_steps": 761865, "loss": 1.9856, "lr": 8.378788073705068e-07, "epoch": 3.957394026500758, "percentage": 26.38, "elapsed_time": "6:48:58", "remaining_time": "19:01:12", "throughput": 8340.48, "total_tokens": 204664960} {"current_steps": 201100, "total_steps": 761865, "loss": 2.0254, "lr": 8.377267980852795e-07, "epoch": 3.9593628792502606, "percentage": 26.4, "elapsed_time": "6:49:10", "remaining_time": "19:00:59", "throughput": 8340.48, "total_tokens": 204766272} {"current_steps": 201200, "total_steps": 761865, "loss": 1.9597, "lr": 8.375747313724591e-07, "epoch": 3.961331731999764, "percentage": 26.41, "elapsed_time": "6:49:23", "remaining_time": "19:00:47", "throughput": 8340.48, "total_tokens": 204868136} {"current_steps": 201300, "total_steps": 761865, "loss": 2.0266, "lr": 8.374226072579027e-07, "epoch": 3.9633005847492666, "percentage": 26.42, "elapsed_time": "6:49:35", "remaining_time": "19:00:35", "throughput": 8340.49, "total_tokens": 204970536} {"current_steps": 201400, "total_steps": 761865, "loss": 1.9837, "lr": 8.372704257674779e-07, "epoch": 3.9652694374987694, "percentage": 26.44, "elapsed_time": "6:49:47", "remaining_time": "19:00:23", "throughput": 8340.48, "total_tokens": 205072080} {"current_steps": 201500, "total_steps": 761865, "loss": 2.0002, "lr": 8.371181869270618e-07, "epoch": 3.9672382902482726, "percentage": 26.45, "elapsed_time": "6:49:59", "remaining_time": "19:00:11", "throughput": 8340.47, "total_tokens": 205173616} {"current_steps": 201600, "total_steps": 761865, "loss": 1.9925, "lr": 8.369658907625415e-07, "epoch": 3.9692071429977753, "percentage": 26.46, "elapsed_time": "6:50:11", "remaining_time": "18:59:58", "throughput": 8340.46, "total_tokens": 205275200} {"current_steps": 201700, "total_steps": 761865, "loss": 2.0251, "lr": 8.368135372998135e-07, "epoch": 3.971175995747278, "percentage": 26.47, "elapsed_time": "6:50:24", "remaining_time": "18:59:46", "throughput": 8340.44, "total_tokens": 205375624} {"current_steps": 201800, "total_steps": 761865, "loss": 1.9952, "lr": 8.366611265647844e-07, "epoch": 3.973144848496781, "percentage": 26.49, "elapsed_time": "6:50:36", "remaining_time": "18:59:34", "throughput": 8340.45, "total_tokens": 205478024} {"current_steps": 201900, "total_steps": 761865, "loss": 2.0151, "lr": 8.365086585833701e-07, "epoch": 3.9751137012462836, "percentage": 26.5, "elapsed_time": "6:50:48", "remaining_time": "18:59:22", "throughput": 8340.44, "total_tokens": 205579664} {"current_steps": 202000, "total_steps": 761865, "loss": 1.9899, "lr": 8.363561333814968e-07, "epoch": 3.977082553995787, "percentage": 26.51, "elapsed_time": "6:51:00", "remaining_time": "18:59:09", "throughput": 8340.44, "total_tokens": 205681512} {"current_steps": 202100, "total_steps": 761865, "loss": 2.0283, "lr": 8.362035509851e-07, "epoch": 3.9790514067452896, "percentage": 26.53, "elapsed_time": "6:51:12", "remaining_time": "18:58:57", "throughput": 8340.43, "total_tokens": 205782336} {"current_steps": 202200, "total_steps": 761865, "loss": 1.9538, "lr": 8.36050911420125e-07, "epoch": 3.9810202594947923, "percentage": 26.54, "elapsed_time": "6:51:25", "remaining_time": "18:58:45", "throughput": 8340.41, "total_tokens": 205883464} {"current_steps": 202300, "total_steps": 761865, "loss": 1.9767, "lr": 8.358982147125269e-07, "epoch": 3.9829891122442955, "percentage": 26.55, "elapsed_time": "6:51:37", "remaining_time": "18:58:33", "throughput": 8340.43, "total_tokens": 205985864} {"current_steps": 202400, "total_steps": 761865, "loss": 1.9626, "lr": 8.357454608882704e-07, "epoch": 3.9849579649937983, "percentage": 26.57, "elapsed_time": "6:51:49", "remaining_time": "18:58:20", "throughput": 8340.42, "total_tokens": 206087512} {"current_steps": 202500, "total_steps": 761865, "loss": 1.9848, "lr": 8.355926499733301e-07, "epoch": 3.986926817743301, "percentage": 26.58, "elapsed_time": "6:52:01", "remaining_time": "18:58:08", "throughput": 8340.41, "total_tokens": 206188584} {"current_steps": 202600, "total_steps": 761865, "loss": 1.9682, "lr": 8.354397819936902e-07, "epoch": 3.988895670492804, "percentage": 26.59, "elapsed_time": "6:52:13", "remaining_time": "18:57:56", "throughput": 8340.39, "total_tokens": 206289464} {"current_steps": 202700, "total_steps": 761865, "loss": 1.9459, "lr": 8.352868569753446e-07, "epoch": 3.9908645232423066, "percentage": 26.61, "elapsed_time": "6:52:25", "remaining_time": "18:57:43", "throughput": 8340.38, "total_tokens": 206390680} {"current_steps": 202800, "total_steps": 761865, "loss": 1.9382, "lr": 8.351338749442969e-07, "epoch": 3.9928333759918093, "percentage": 26.62, "elapsed_time": "6:52:38", "remaining_time": "18:57:31", "throughput": 8340.39, "total_tokens": 206493080} {"current_steps": 202900, "total_steps": 761865, "loss": 2.0174, "lr": 8.349808359265604e-07, "epoch": 3.9948022287413125, "percentage": 26.63, "elapsed_time": "6:52:50", "remaining_time": "18:57:19", "throughput": 8340.38, "total_tokens": 206594872} {"current_steps": 203000, "total_steps": 761865, "loss": 2.0029, "lr": 8.348277399481583e-07, "epoch": 3.9967710814908153, "percentage": 26.65, "elapsed_time": "6:53:02", "remaining_time": "18:57:07", "throughput": 8340.38, "total_tokens": 206696512} {"current_steps": 203100, "total_steps": 761865, "loss": 1.9667, "lr": 8.346745870351228e-07, "epoch": 3.998739934240318, "percentage": 26.66, "elapsed_time": "6:53:14", "remaining_time": "18:56:55", "throughput": 8340.39, "total_tokens": 206798912} {"current_steps": 203200, "total_steps": 761865, "loss": 1.9123, "lr": 8.345213772134968e-07, "epoch": 4.000708786989821, "percentage": 26.67, "elapsed_time": "6:53:27", "remaining_time": "18:56:43", "throughput": 8340.4, "total_tokens": 206901312} {"current_steps": 203300, "total_steps": 761865, "loss": 1.982, "lr": 8.34368110509332e-07, "epoch": 4.002677639739324, "percentage": 26.68, "elapsed_time": "6:53:39", "remaining_time": "18:56:30", "throughput": 8340.4, "total_tokens": 207003112} {"current_steps": 203400, "total_steps": 761865, "loss": 1.9427, "lr": 8.342147869486902e-07, "epoch": 4.004646492488827, "percentage": 26.7, "elapsed_time": "6:53:51", "remaining_time": "18:56:18", "throughput": 8340.41, "total_tokens": 207105512} {"current_steps": 203500, "total_steps": 761865, "loss": 1.9943, "lr": 8.340614065576427e-07, "epoch": 4.0066153452383295, "percentage": 26.71, "elapsed_time": "6:54:03", "remaining_time": "18:56:06", "throughput": 8340.4, "total_tokens": 207206536} {"current_steps": 203600, "total_steps": 761865, "loss": 1.9707, "lr": 8.339079693622706e-07, "epoch": 4.008584197987832, "percentage": 26.72, "elapsed_time": "6:54:15", "remaining_time": "18:55:54", "throughput": 8340.4, "total_tokens": 207308400} {"current_steps": 203700, "total_steps": 761865, "loss": 1.9741, "lr": 8.337544753886648e-07, "epoch": 4.010553050737335, "percentage": 26.74, "elapsed_time": "6:54:28", "remaining_time": "18:55:42", "throughput": 8340.41, "total_tokens": 207410800} {"current_steps": 203800, "total_steps": 761865, "loss": 1.9616, "lr": 8.336009246629253e-07, "epoch": 4.012521903486838, "percentage": 26.75, "elapsed_time": "6:54:40", "remaining_time": "18:55:29", "throughput": 8340.41, "total_tokens": 207512616} {"current_steps": 203900, "total_steps": 761865, "loss": 1.9774, "lr": 8.334473172111624e-07, "epoch": 4.014490756236341, "percentage": 26.76, "elapsed_time": "6:54:52", "remaining_time": "18:55:17", "throughput": 8340.4, "total_tokens": 207614440} {"current_steps": 204000, "total_steps": 761865, "loss": 1.9815, "lr": 8.332936530594956e-07, "epoch": 4.016459608985844, "percentage": 26.78, "elapsed_time": "6:55:04", "remaining_time": "18:55:05", "throughput": 8340.39, "total_tokens": 207715888} {"current_steps": 204100, "total_steps": 761865, "loss": 1.9691, "lr": 8.331399322340542e-07, "epoch": 4.018428461735347, "percentage": 26.79, "elapsed_time": "6:55:17", "remaining_time": "18:54:53", "throughput": 8340.4, "total_tokens": 207818288} {"current_steps": 204200, "total_steps": 761865, "loss": 1.9727, "lr": 8.329861547609771e-07, "epoch": 4.02039731448485, "percentage": 26.8, "elapsed_time": "6:55:29", "remaining_time": "18:54:41", "throughput": 8340.4, "total_tokens": 207920688} {"current_steps": 204300, "total_steps": 761865, "loss": 1.9449, "lr": 8.328323206664129e-07, "epoch": 4.0223661672343525, "percentage": 26.82, "elapsed_time": "6:55:41", "remaining_time": "18:54:29", "throughput": 8340.4, "total_tokens": 208022560} {"current_steps": 204400, "total_steps": 761865, "loss": 2.0058, "lr": 8.3267842997652e-07, "epoch": 4.024335019983855, "percentage": 26.83, "elapsed_time": "6:55:53", "remaining_time": "18:54:16", "throughput": 8340.36, "total_tokens": 208122328} {"current_steps": 204500, "total_steps": 761865, "loss": 1.9511, "lr": 8.32524482717466e-07, "epoch": 4.026303872733358, "percentage": 26.84, "elapsed_time": "6:56:05", "remaining_time": "18:54:04", "throughput": 8340.37, "total_tokens": 208224728} {"current_steps": 204600, "total_steps": 761865, "loss": 1.962, "lr": 8.323704789154282e-07, "epoch": 4.028272725482861, "percentage": 26.86, "elapsed_time": "6:56:18", "remaining_time": "18:53:52", "throughput": 8340.38, "total_tokens": 208327128} {"current_steps": 204700, "total_steps": 761865, "loss": 2.0148, "lr": 8.322164185965939e-07, "epoch": 4.030241578232364, "percentage": 26.87, "elapsed_time": "6:56:30", "remaining_time": "18:53:40", "throughput": 8340.39, "total_tokens": 208429528} {"current_steps": 204800, "total_steps": 761865, "loss": 1.956, "lr": 8.320623017871596e-07, "epoch": 4.032210430981867, "percentage": 26.88, "elapsed_time": "6:56:42", "remaining_time": "18:53:28", "throughput": 8340.39, "total_tokens": 208531264} {"current_steps": 204900, "total_steps": 761865, "loss": 1.96, "lr": 8.319081285133316e-07, "epoch": 4.03417928373137, "percentage": 26.89, "elapsed_time": "6:56:54", "remaining_time": "18:53:15", "throughput": 8340.39, "total_tokens": 208632984} {"current_steps": 205000, "total_steps": 761865, "loss": 1.9643, "lr": 8.317538988013259e-07, "epoch": 4.036148136480873, "percentage": 26.91, "elapsed_time": "6:57:07", "remaining_time": "18:53:03", "throughput": 8340.39, "total_tokens": 208735384} {"current_steps": 205100, "total_steps": 761865, "loss": 1.9073, "lr": 8.315996126773678e-07, "epoch": 4.038116989230375, "percentage": 26.92, "elapsed_time": "6:57:19", "remaining_time": "18:52:53", "throughput": 8340.22, "total_tokens": 208837336} {"current_steps": 205200, "total_steps": 761865, "loss": 1.9671, "lr": 8.314452701676924e-07, "epoch": 4.040085841979878, "percentage": 26.93, "elapsed_time": "6:57:32", "remaining_time": "18:52:40", "throughput": 8340.22, "total_tokens": 208939544} {"current_steps": 205300, "total_steps": 761865, "loss": 1.9526, "lr": 8.312908712985443e-07, "epoch": 4.042054694729381, "percentage": 26.95, "elapsed_time": "6:57:44", "remaining_time": "18:52:28", "throughput": 8340.23, "total_tokens": 209041944} {"current_steps": 205400, "total_steps": 761865, "loss": 2.0005, "lr": 8.311364160961778e-07, "epoch": 4.044023547478884, "percentage": 26.96, "elapsed_time": "6:57:56", "remaining_time": "18:52:16", "throughput": 8340.23, "total_tokens": 209143344} {"current_steps": 205500, "total_steps": 761865, "loss": 1.9922, "lr": 8.309819045868567e-07, "epoch": 4.045992400228387, "percentage": 26.97, "elapsed_time": "6:58:08", "remaining_time": "18:52:04", "throughput": 8340.23, "total_tokens": 209244968} {"current_steps": 205600, "total_steps": 761865, "loss": 2.0, "lr": 8.308273367968543e-07, "epoch": 4.04796125297789, "percentage": 26.99, "elapsed_time": "6:58:20", "remaining_time": "18:51:52", "throughput": 8340.23, "total_tokens": 209347368} {"current_steps": 205700, "total_steps": 761865, "loss": 1.9963, "lr": 8.306727127524536e-07, "epoch": 4.049930105727393, "percentage": 27.0, "elapsed_time": "6:58:33", "remaining_time": "18:51:40", "throughput": 8340.25, "total_tokens": 209449768} {"current_steps": 205800, "total_steps": 761865, "loss": 1.9861, "lr": 8.305180324799472e-07, "epoch": 4.051898958476896, "percentage": 27.01, "elapsed_time": "6:58:45", "remaining_time": "18:51:27", "throughput": 8340.25, "total_tokens": 209551592} {"current_steps": 205900, "total_steps": 761865, "loss": 1.9687, "lr": 8.303632960056372e-07, "epoch": 4.053867811226398, "percentage": 27.03, "elapsed_time": "6:58:57", "remaining_time": "18:51:15", "throughput": 8340.25, "total_tokens": 209652912} {"current_steps": 206000, "total_steps": 761865, "loss": 1.9902, "lr": 8.302085033558349e-07, "epoch": 4.055836663975901, "percentage": 27.04, "elapsed_time": "6:59:09", "remaining_time": "18:51:03", "throughput": 8340.25, "total_tokens": 209754880} {"current_steps": 206100, "total_steps": 761865, "loss": 1.9743, "lr": 8.300536545568618e-07, "epoch": 4.057805516725404, "percentage": 27.05, "elapsed_time": "6:59:21", "remaining_time": "18:50:51", "throughput": 8340.26, "total_tokens": 209857280} {"current_steps": 206200, "total_steps": 761865, "loss": 2.0353, "lr": 8.298987496350486e-07, "epoch": 4.059774369474907, "percentage": 27.07, "elapsed_time": "6:59:34", "remaining_time": "18:50:38", "throughput": 8340.25, "total_tokens": 209958416} {"current_steps": 206300, "total_steps": 761865, "loss": 1.9995, "lr": 8.297437886167356e-07, "epoch": 4.061743222224409, "percentage": 27.08, "elapsed_time": "6:59:46", "remaining_time": "18:50:26", "throughput": 8340.26, "total_tokens": 210060256} {"current_steps": 206400, "total_steps": 761865, "loss": 2.0072, "lr": 8.295887715282723e-07, "epoch": 4.063712074973913, "percentage": 27.09, "elapsed_time": "6:59:58", "remaining_time": "18:50:14", "throughput": 8340.27, "total_tokens": 210162656} {"current_steps": 206500, "total_steps": 761865, "loss": 2.0172, "lr": 8.294336983960184e-07, "epoch": 4.065680927723416, "percentage": 27.1, "elapsed_time": "7:00:10", "remaining_time": "18:50:02", "throughput": 8340.28, "total_tokens": 210265056} {"current_steps": 206600, "total_steps": 761865, "loss": 1.9583, "lr": 8.292785692463426e-07, "epoch": 4.067649780472919, "percentage": 27.12, "elapsed_time": "7:00:23", "remaining_time": "18:49:50", "throughput": 8340.27, "total_tokens": 210367456} {"current_steps": 206700, "total_steps": 761865, "loss": 1.9861, "lr": 8.291233841056235e-07, "epoch": 4.069618633222421, "percentage": 27.13, "elapsed_time": "7:00:35", "remaining_time": "18:49:38", "throughput": 8340.29, "total_tokens": 210469856} {"current_steps": 206800, "total_steps": 761865, "loss": 1.9968, "lr": 8.289681430002487e-07, "epoch": 4.071587485971924, "percentage": 27.14, "elapsed_time": "7:00:47", "remaining_time": "18:49:26", "throughput": 8340.27, "total_tokens": 210572256} {"current_steps": 206900, "total_steps": 761865, "loss": 1.9992, "lr": 8.28812845956616e-07, "epoch": 4.073556338721427, "percentage": 27.16, "elapsed_time": "7:00:59", "remaining_time": "18:49:14", "throughput": 8340.26, "total_tokens": 210674120} {"current_steps": 207000, "total_steps": 761865, "loss": 1.9544, "lr": 8.28657493001132e-07, "epoch": 4.07552519147093, "percentage": 27.17, "elapsed_time": "7:01:12", "remaining_time": "18:49:02", "throughput": 8340.26, "total_tokens": 210776520} {"current_steps": 207100, "total_steps": 761865, "loss": 2.0996, "lr": 8.285020841602135e-07, "epoch": 4.077494044220432, "percentage": 27.18, "elapsed_time": "7:01:24", "remaining_time": "18:48:49", "throughput": 8340.25, "total_tokens": 210877536} {"current_steps": 207200, "total_steps": 761865, "loss": 1.9664, "lr": 8.283466194602862e-07, "epoch": 4.079462896969936, "percentage": 27.2, "elapsed_time": "7:01:36", "remaining_time": "18:48:37", "throughput": 8340.25, "total_tokens": 210979416} {"current_steps": 207300, "total_steps": 761865, "loss": 2.0187, "lr": 8.281910989277858e-07, "epoch": 4.081431749719439, "percentage": 27.21, "elapsed_time": "7:01:48", "remaining_time": "18:48:25", "throughput": 8340.26, "total_tokens": 211081816} {"current_steps": 207400, "total_steps": 761865, "loss": 1.9931, "lr": 8.28035522589157e-07, "epoch": 4.0834006024689415, "percentage": 27.22, "elapsed_time": "7:02:00", "remaining_time": "18:48:13", "throughput": 8340.26, "total_tokens": 211182888} {"current_steps": 207500, "total_steps": 761865, "loss": 1.9812, "lr": 8.278798904708543e-07, "epoch": 4.085369455218444, "percentage": 27.24, "elapsed_time": "7:02:13", "remaining_time": "18:48:01", "throughput": 8340.27, "total_tokens": 211285288} {"current_steps": 207600, "total_steps": 761865, "loss": 1.9635, "lr": 8.277242025993418e-07, "epoch": 4.087338307967947, "percentage": 27.25, "elapsed_time": "7:02:25", "remaining_time": "18:47:48", "throughput": 8340.27, "total_tokens": 211387040} {"current_steps": 207700, "total_steps": 761865, "loss": 1.9566, "lr": 8.275684590010928e-07, "epoch": 4.08930716071745, "percentage": 27.26, "elapsed_time": "7:02:37", "remaining_time": "18:47:36", "throughput": 8340.26, "total_tokens": 211488600} {"current_steps": 207800, "total_steps": 761865, "loss": 1.9676, "lr": 8.274126597025901e-07, "epoch": 4.091276013466953, "percentage": 27.28, "elapsed_time": "7:02:49", "remaining_time": "18:47:24", "throughput": 8340.26, "total_tokens": 211591000} {"current_steps": 207900, "total_steps": 761865, "loss": 1.9952, "lr": 8.272568047303263e-07, "epoch": 4.093244866216455, "percentage": 27.29, "elapsed_time": "7:03:02", "remaining_time": "18:47:12", "throughput": 8340.27, "total_tokens": 211693224} {"current_steps": 208000, "total_steps": 761865, "loss": 1.9882, "lr": 8.27100894110803e-07, "epoch": 4.095213718965958, "percentage": 27.3, "elapsed_time": "7:03:14", "remaining_time": "18:46:59", "throughput": 8340.25, "total_tokens": 211793832} {"current_steps": 208100, "total_steps": 761865, "loss": 1.9612, "lr": 8.269449278705315e-07, "epoch": 4.097182571715462, "percentage": 27.31, "elapsed_time": "7:03:26", "remaining_time": "18:46:47", "throughput": 8340.26, "total_tokens": 211896232} {"current_steps": 208200, "total_steps": 761865, "loss": 2.0129, "lr": 8.267889060360327e-07, "epoch": 4.0991514244649645, "percentage": 27.33, "elapsed_time": "7:03:38", "remaining_time": "18:46:35", "throughput": 8340.23, "total_tokens": 211996336} {"current_steps": 208300, "total_steps": 761865, "loss": 1.9711, "lr": 8.266328286338367e-07, "epoch": 4.101120277214467, "percentage": 27.34, "elapsed_time": "7:03:50", "remaining_time": "18:46:22", "throughput": 8340.2, "total_tokens": 212096544} {"current_steps": 208400, "total_steps": 761865, "loss": 2.0407, "lr": 8.264766956904829e-07, "epoch": 4.10308912996397, "percentage": 27.35, "elapsed_time": "7:04:02", "remaining_time": "18:46:10", "throughput": 8340.19, "total_tokens": 212197544} {"current_steps": 208500, "total_steps": 761865, "loss": 2.0048, "lr": 8.263205072325208e-07, "epoch": 4.105057982713473, "percentage": 27.37, "elapsed_time": "7:04:14", "remaining_time": "18:45:58", "throughput": 8340.17, "total_tokens": 212298336} {"current_steps": 208600, "total_steps": 761865, "loss": 1.9792, "lr": 8.261642632865088e-07, "epoch": 4.1070268354629755, "percentage": 27.38, "elapsed_time": "7:04:27", "remaining_time": "18:45:45", "throughput": 8340.18, "total_tokens": 212400512} {"current_steps": 208700, "total_steps": 761865, "loss": 1.982, "lr": 8.260079638790147e-07, "epoch": 4.108995688212478, "percentage": 27.39, "elapsed_time": "7:04:39", "remaining_time": "18:45:33", "throughput": 8340.19, "total_tokens": 212502912} {"current_steps": 208800, "total_steps": 761865, "loss": 2.0355, "lr": 8.258516090366161e-07, "epoch": 4.110964540961981, "percentage": 27.41, "elapsed_time": "7:04:51", "remaining_time": "18:45:21", "throughput": 8340.18, "total_tokens": 212605312} {"current_steps": 208900, "total_steps": 761865, "loss": 2.001, "lr": 8.256951987858998e-07, "epoch": 4.112933393711485, "percentage": 27.42, "elapsed_time": "7:05:03", "remaining_time": "18:45:09", "throughput": 8340.17, "total_tokens": 212706944} {"current_steps": 209000, "total_steps": 761865, "loss": 1.9415, "lr": 8.255387331534619e-07, "epoch": 4.1149022464609875, "percentage": 27.43, "elapsed_time": "7:05:16", "remaining_time": "18:44:57", "throughput": 8340.17, "total_tokens": 212809344} {"current_steps": 209100, "total_steps": 761865, "loss": 2.0208, "lr": 8.253822121659082e-07, "epoch": 4.11687109921049, "percentage": 27.45, "elapsed_time": "7:05:28", "remaining_time": "18:44:45", "throughput": 8340.16, "total_tokens": 212910824} {"current_steps": 209200, "total_steps": 761865, "loss": 1.942, "lr": 8.252256358498538e-07, "epoch": 4.118839951959993, "percentage": 27.46, "elapsed_time": "7:05:40", "remaining_time": "18:44:33", "throughput": 8340.16, "total_tokens": 213013224} {"current_steps": 209300, "total_steps": 761865, "loss": 1.9911, "lr": 8.250690042319229e-07, "epoch": 4.120808804709496, "percentage": 27.47, "elapsed_time": "7:05:52", "remaining_time": "18:44:21", "throughput": 8340.17, "total_tokens": 213115624} {"current_steps": 209400, "total_steps": 761865, "loss": 2.0294, "lr": 8.249123173387497e-07, "epoch": 4.1227776574589985, "percentage": 27.49, "elapsed_time": "7:06:04", "remaining_time": "18:44:08", "throughput": 8340.15, "total_tokens": 213215712} {"current_steps": 209500, "total_steps": 761865, "loss": 2.0028, "lr": 8.247555751969773e-07, "epoch": 4.124746510208501, "percentage": 27.5, "elapsed_time": "7:06:17", "remaining_time": "18:43:56", "throughput": 8340.13, "total_tokens": 213317184} {"current_steps": 209600, "total_steps": 761865, "loss": 1.9659, "lr": 8.245987778332586e-07, "epoch": 4.126715362958004, "percentage": 27.51, "elapsed_time": "7:06:29", "remaining_time": "18:43:44", "throughput": 8340.13, "total_tokens": 213418608} {"current_steps": 209700, "total_steps": 761865, "loss": 1.9893, "lr": 8.244419252742553e-07, "epoch": 4.128684215707508, "percentage": 27.52, "elapsed_time": "7:06:41", "remaining_time": "18:43:32", "throughput": 8340.14, "total_tokens": 213521008} {"current_steps": 209800, "total_steps": 761865, "loss": 2.003, "lr": 8.242850175466392e-07, "epoch": 4.13065306845701, "percentage": 27.54, "elapsed_time": "7:06:53", "remaining_time": "18:43:19", "throughput": 8340.13, "total_tokens": 213622856} {"current_steps": 209900, "total_steps": 761865, "loss": 1.9662, "lr": 8.24128054677091e-07, "epoch": 4.132621921206513, "percentage": 27.55, "elapsed_time": "7:07:06", "remaining_time": "18:43:07", "throughput": 8340.12, "total_tokens": 213724440} {"current_steps": 210000, "total_steps": 761865, "loss": 1.9721, "lr": 8.23971036692301e-07, "epoch": 4.134590773956016, "percentage": 27.56, "elapsed_time": "7:07:18", "remaining_time": "18:42:55", "throughput": 8340.12, "total_tokens": 213826840} {"current_steps": 210100, "total_steps": 761865, "loss": 1.9552, "lr": 8.238139636189687e-07, "epoch": 4.136559626705519, "percentage": 27.58, "elapsed_time": "7:07:31", "remaining_time": "18:42:45", "throughput": 8339.95, "total_tokens": 213929240} {"current_steps": 210200, "total_steps": 761865, "loss": 1.9565, "lr": 8.23656835483803e-07, "epoch": 4.1385284794550214, "percentage": 27.59, "elapsed_time": "7:07:43", "remaining_time": "18:42:32", "throughput": 8339.96, "total_tokens": 214031640} {"current_steps": 210300, "total_steps": 761865, "loss": 1.9584, "lr": 8.234996523135224e-07, "epoch": 4.140497332204524, "percentage": 27.6, "elapsed_time": "7:07:55", "remaining_time": "18:42:20", "throughput": 8339.97, "total_tokens": 214134040} {"current_steps": 210400, "total_steps": 761865, "loss": 1.949, "lr": 8.233424141348542e-07, "epoch": 4.142466184954027, "percentage": 27.62, "elapsed_time": "7:08:07", "remaining_time": "18:42:08", "throughput": 8339.98, "total_tokens": 214236440} {"current_steps": 210500, "total_steps": 761865, "loss": 1.9878, "lr": 8.23185120974536e-07, "epoch": 4.14443503770353, "percentage": 27.63, "elapsed_time": "7:08:20", "remaining_time": "18:41:56", "throughput": 8339.98, "total_tokens": 214337696} {"current_steps": 210600, "total_steps": 761865, "loss": 2.0009, "lr": 8.230277728593136e-07, "epoch": 4.146403890453033, "percentage": 27.64, "elapsed_time": "7:08:32", "remaining_time": "18:41:44", "throughput": 8339.98, "total_tokens": 214439176} {"current_steps": 210700, "total_steps": 761865, "loss": 1.9421, "lr": 8.228703698159429e-07, "epoch": 4.148372743202536, "percentage": 27.66, "elapsed_time": "7:08:44", "remaining_time": "18:41:31", "throughput": 8339.97, "total_tokens": 214540328} {"current_steps": 210800, "total_steps": 761865, "loss": 1.9908, "lr": 8.227129118711892e-07, "epoch": 4.150341595952039, "percentage": 27.67, "elapsed_time": "7:08:56", "remaining_time": "18:41:19", "throughput": 8339.96, "total_tokens": 214641656} {"current_steps": 210900, "total_steps": 761865, "loss": 1.9454, "lr": 8.225553990518267e-07, "epoch": 4.152310448701542, "percentage": 27.68, "elapsed_time": "7:09:08", "remaining_time": "18:41:07", "throughput": 8339.97, "total_tokens": 214744056} {"current_steps": 211000, "total_steps": 761865, "loss": 2.0, "lr": 8.223978313846392e-07, "epoch": 4.154279301451044, "percentage": 27.7, "elapsed_time": "7:09:20", "remaining_time": "18:40:55", "throughput": 8339.97, "total_tokens": 214845760} {"current_steps": 211100, "total_steps": 761865, "loss": 2.0573, "lr": 8.222402088964195e-07, "epoch": 4.156248154200547, "percentage": 27.71, "elapsed_time": "7:09:33", "remaining_time": "18:40:42", "throughput": 8339.96, "total_tokens": 214947368} {"current_steps": 211200, "total_steps": 761865, "loss": 1.929, "lr": 8.220825316139703e-07, "epoch": 4.15821700695005, "percentage": 27.72, "elapsed_time": "7:09:45", "remaining_time": "18:40:30", "throughput": 8339.97, "total_tokens": 215049768} {"current_steps": 211300, "total_steps": 761865, "loss": 1.9528, "lr": 8.219247995641032e-07, "epoch": 4.160185859699553, "percentage": 27.73, "elapsed_time": "7:09:57", "remaining_time": "18:40:18", "throughput": 8339.96, "total_tokens": 215151352} {"current_steps": 211400, "total_steps": 761865, "loss": 1.9722, "lr": 8.217670127736391e-07, "epoch": 4.162154712449056, "percentage": 27.75, "elapsed_time": "7:10:09", "remaining_time": "18:40:06", "throughput": 8339.95, "total_tokens": 215252352} {"current_steps": 211500, "total_steps": 761865, "loss": 2.0707, "lr": 8.216091712694086e-07, "epoch": 4.164123565198559, "percentage": 27.76, "elapsed_time": "7:10:22", "remaining_time": "18:39:53", "throughput": 8339.94, "total_tokens": 215353984} {"current_steps": 211600, "total_steps": 761865, "loss": 1.9643, "lr": 8.214512750782509e-07, "epoch": 4.166092417948062, "percentage": 27.77, "elapsed_time": "7:10:34", "remaining_time": "18:39:41", "throughput": 8339.94, "total_tokens": 215455768} {"current_steps": 211700, "total_steps": 761865, "loss": 1.9846, "lr": 8.212933242270151e-07, "epoch": 4.168061270697565, "percentage": 27.79, "elapsed_time": "7:10:46", "remaining_time": "18:39:29", "throughput": 8339.94, "total_tokens": 215557464} {"current_steps": 211800, "total_steps": 761865, "loss": 1.9754, "lr": 8.211353187425593e-07, "epoch": 4.170030123447067, "percentage": 27.8, "elapsed_time": "7:10:58", "remaining_time": "18:39:17", "throughput": 8339.93, "total_tokens": 215658584} {"current_steps": 211900, "total_steps": 761865, "loss": 1.9906, "lr": 8.209772586517513e-07, "epoch": 4.17199897619657, "percentage": 27.81, "elapsed_time": "7:11:10", "remaining_time": "18:39:05", "throughput": 8339.93, "total_tokens": 215760984} {"current_steps": 212000, "total_steps": 761865, "loss": 2.0133, "lr": 8.208191439814679e-07, "epoch": 4.173967828946073, "percentage": 27.83, "elapsed_time": "7:11:23", "remaining_time": "18:38:52", "throughput": 8339.92, "total_tokens": 215862536} {"current_steps": 212100, "total_steps": 761865, "loss": 2.0069, "lr": 8.206609747585949e-07, "epoch": 4.175936681695576, "percentage": 27.84, "elapsed_time": "7:11:35", "remaining_time": "18:38:40", "throughput": 8339.91, "total_tokens": 215963792} {"current_steps": 212200, "total_steps": 761865, "loss": 1.9822, "lr": 8.205027510100275e-07, "epoch": 4.177905534445079, "percentage": 27.85, "elapsed_time": "7:11:47", "remaining_time": "18:38:28", "throughput": 8339.92, "total_tokens": 216066192} {"current_steps": 212300, "total_steps": 761865, "loss": 1.9829, "lr": 8.203444727626708e-07, "epoch": 4.179874387194582, "percentage": 27.87, "elapsed_time": "7:11:59", "remaining_time": "18:38:16", "throughput": 8339.92, "total_tokens": 216168000} {"current_steps": 212400, "total_steps": 761865, "loss": 2.0066, "lr": 8.201861400434382e-07, "epoch": 4.181843239944085, "percentage": 27.88, "elapsed_time": "7:12:11", "remaining_time": "18:38:04", "throughput": 8339.89, "total_tokens": 216268720} {"current_steps": 212500, "total_steps": 761865, "loss": 1.9843, "lr": 8.200277528792531e-07, "epoch": 4.183812092693588, "percentage": 27.89, "elapsed_time": "7:12:24", "remaining_time": "18:37:51", "throughput": 8339.9, "total_tokens": 216371120} {"current_steps": 212600, "total_steps": 761865, "loss": 1.9634, "lr": 8.198693112970478e-07, "epoch": 4.18578094544309, "percentage": 27.91, "elapsed_time": "7:12:36", "remaining_time": "18:37:39", "throughput": 8339.9, "total_tokens": 216473520} {"current_steps": 212700, "total_steps": 761865, "loss": 1.9755, "lr": 8.197108153237642e-07, "epoch": 4.187749798192593, "percentage": 27.92, "elapsed_time": "7:12:48", "remaining_time": "18:37:27", "throughput": 8339.91, "total_tokens": 216575920} {"current_steps": 212800, "total_steps": 761865, "loss": 1.9761, "lr": 8.19552264986353e-07, "epoch": 4.189718650942096, "percentage": 27.93, "elapsed_time": "7:13:00", "remaining_time": "18:37:15", "throughput": 8339.91, "total_tokens": 216678320} {"current_steps": 212900, "total_steps": 761865, "loss": 1.9775, "lr": 8.193936603117741e-07, "epoch": 4.191687503691599, "percentage": 27.94, "elapsed_time": "7:13:13", "remaining_time": "18:37:03", "throughput": 8339.91, "total_tokens": 216780072} {"current_steps": 213000, "total_steps": 761865, "loss": 2.0049, "lr": 8.192350013269975e-07, "epoch": 4.193656356441101, "percentage": 27.96, "elapsed_time": "7:13:25", "remaining_time": "18:36:51", "throughput": 8339.92, "total_tokens": 216882472} {"current_steps": 213100, "total_steps": 761865, "loss": 2.0121, "lr": 8.190762880590013e-07, "epoch": 4.195625209190605, "percentage": 27.97, "elapsed_time": "7:13:37", "remaining_time": "18:36:39", "throughput": 8339.91, "total_tokens": 216984072} {"current_steps": 213200, "total_steps": 761865, "loss": 2.0088, "lr": 8.189175205347735e-07, "epoch": 4.197594061940108, "percentage": 27.98, "elapsed_time": "7:13:49", "remaining_time": "18:36:26", "throughput": 8339.9, "total_tokens": 217085240} {"current_steps": 213300, "total_steps": 761865, "loss": 1.9197, "lr": 8.187586987813113e-07, "epoch": 4.1995629146896105, "percentage": 28.0, "elapsed_time": "7:14:01", "remaining_time": "18:36:14", "throughput": 8339.89, "total_tokens": 217186816} {"current_steps": 213400, "total_steps": 761865, "loss": 1.9741, "lr": 8.185998228256209e-07, "epoch": 4.201531767439113, "percentage": 28.01, "elapsed_time": "7:14:14", "remaining_time": "18:36:02", "throughput": 8339.89, "total_tokens": 217288736} {"current_steps": 213500, "total_steps": 761865, "loss": 1.9746, "lr": 8.184408926947179e-07, "epoch": 4.203500620188616, "percentage": 28.02, "elapsed_time": "7:14:26", "remaining_time": "18:35:50", "throughput": 8339.89, "total_tokens": 217391136} {"current_steps": 213600, "total_steps": 761865, "loss": 1.955, "lr": 8.182819084156268e-07, "epoch": 4.205469472938119, "percentage": 28.04, "elapsed_time": "7:14:38", "remaining_time": "18:35:38", "throughput": 8339.9, "total_tokens": 217493536} {"current_steps": 213700, "total_steps": 761865, "loss": 1.9938, "lr": 8.181228700153817e-07, "epoch": 4.2074383256876215, "percentage": 28.05, "elapsed_time": "7:14:50", "remaining_time": "18:35:26", "throughput": 8339.89, "total_tokens": 217595096} {"current_steps": 213800, "total_steps": 761865, "loss": 1.9411, "lr": 8.179637775210258e-07, "epoch": 4.209407178437124, "percentage": 28.06, "elapsed_time": "7:15:03", "remaining_time": "18:35:14", "throughput": 8339.9, "total_tokens": 217697496} {"current_steps": 213900, "total_steps": 761865, "loss": 2.0071, "lr": 8.178046309596111e-07, "epoch": 4.211376031186628, "percentage": 28.08, "elapsed_time": "7:15:15", "remaining_time": "18:35:01", "throughput": 8339.91, "total_tokens": 217799896} {"current_steps": 214000, "total_steps": 761865, "loss": 2.0019, "lr": 8.176454303581998e-07, "epoch": 4.213344883936131, "percentage": 28.09, "elapsed_time": "7:15:27", "remaining_time": "18:34:49", "throughput": 8339.91, "total_tokens": 217902296} {"current_steps": 214100, "total_steps": 761865, "loss": 1.9549, "lr": 8.17486175743862e-07, "epoch": 4.2153137366856335, "percentage": 28.1, "elapsed_time": "7:15:39", "remaining_time": "18:34:37", "throughput": 8339.92, "total_tokens": 218004696} {"current_steps": 214200, "total_steps": 761865, "loss": 1.9808, "lr": 8.173268671436779e-07, "epoch": 4.217282589435136, "percentage": 28.12, "elapsed_time": "7:15:52", "remaining_time": "18:34:25", "throughput": 8339.9, "total_tokens": 218105096} {"current_steps": 214300, "total_steps": 761865, "loss": 2.0014, "lr": 8.171675045847363e-07, "epoch": 4.219251442184639, "percentage": 28.13, "elapsed_time": "7:16:04", "remaining_time": "18:34:13", "throughput": 8339.91, "total_tokens": 218207496} {"current_steps": 214400, "total_steps": 761865, "loss": 1.9452, "lr": 8.170080880941359e-07, "epoch": 4.221220294934142, "percentage": 28.14, "elapsed_time": "7:16:16", "remaining_time": "18:34:01", "throughput": 8339.92, "total_tokens": 218309896} {"current_steps": 214500, "total_steps": 761865, "loss": 2.0071, "lr": 8.168486176989838e-07, "epoch": 4.2231891476836445, "percentage": 28.15, "elapsed_time": "7:16:28", "remaining_time": "18:33:48", "throughput": 8339.92, "total_tokens": 218411864} {"current_steps": 214600, "total_steps": 761865, "loss": 1.9598, "lr": 8.166890934263968e-07, "epoch": 4.225158000433147, "percentage": 28.17, "elapsed_time": "7:16:40", "remaining_time": "18:33:36", "throughput": 8339.92, "total_tokens": 218513744} {"current_steps": 214700, "total_steps": 761865, "loss": 1.922, "lr": 8.165295153035003e-07, "epoch": 4.22712685318265, "percentage": 28.18, "elapsed_time": "7:16:53", "remaining_time": "18:33:24", "throughput": 8339.93, "total_tokens": 218616144} {"current_steps": 214800, "total_steps": 761865, "loss": 2.0144, "lr": 8.163698833574297e-07, "epoch": 4.229095705932154, "percentage": 28.19, "elapsed_time": "7:17:05", "remaining_time": "18:33:12", "throughput": 8339.94, "total_tokens": 218718544} {"current_steps": 214900, "total_steps": 761865, "loss": 1.997, "lr": 8.162101976153286e-07, "epoch": 4.231064558681656, "percentage": 28.21, "elapsed_time": "7:17:17", "remaining_time": "18:33:00", "throughput": 8339.94, "total_tokens": 218820944} {"current_steps": 215000, "total_steps": 761865, "loss": 1.987, "lr": 8.160504581043506e-07, "epoch": 4.233033411431159, "percentage": 28.22, "elapsed_time": "7:17:29", "remaining_time": "18:32:48", "throughput": 8339.94, "total_tokens": 218923128} {"current_steps": 215100, "total_steps": 761865, "loss": 1.928, "lr": 8.158906648516578e-07, "epoch": 4.235002264180662, "percentage": 28.23, "elapsed_time": "7:17:42", "remaining_time": "18:32:37", "throughput": 8339.77, "total_tokens": 219024752} {"current_steps": 215200, "total_steps": 761865, "loss": 2.0293, "lr": 8.157308178844218e-07, "epoch": 4.236971116930165, "percentage": 28.25, "elapsed_time": "7:17:54", "remaining_time": "18:32:25", "throughput": 8339.77, "total_tokens": 219126840} {"current_steps": 215300, "total_steps": 761865, "loss": 2.0154, "lr": 8.155709172298233e-07, "epoch": 4.2389399696796675, "percentage": 28.26, "elapsed_time": "7:18:07", "remaining_time": "18:32:13", "throughput": 8339.77, "total_tokens": 219229240} {"current_steps": 215400, "total_steps": 761865, "loss": 1.9819, "lr": 8.154109629150518e-07, "epoch": 4.24090882242917, "percentage": 28.27, "elapsed_time": "7:18:19", "remaining_time": "18:32:01", "throughput": 8339.78, "total_tokens": 219331224} {"current_steps": 215500, "total_steps": 761865, "loss": 1.9872, "lr": 8.152509549673066e-07, "epoch": 4.242877675178673, "percentage": 28.29, "elapsed_time": "7:18:31", "remaining_time": "18:31:48", "throughput": 8339.77, "total_tokens": 219432704} {"current_steps": 215600, "total_steps": 761865, "loss": 1.9877, "lr": 8.150908934137952e-07, "epoch": 4.244846527928177, "percentage": 28.3, "elapsed_time": "7:18:43", "remaining_time": "18:31:36", "throughput": 8339.77, "total_tokens": 219535104} {"current_steps": 215700, "total_steps": 761865, "loss": 1.9592, "lr": 8.149307782817352e-07, "epoch": 4.246815380677679, "percentage": 28.31, "elapsed_time": "7:18:56", "remaining_time": "18:31:24", "throughput": 8339.76, "total_tokens": 219636744} {"current_steps": 215800, "total_steps": 761865, "loss": 1.9351, "lr": 8.147706095983525e-07, "epoch": 4.248784233427182, "percentage": 28.33, "elapsed_time": "7:19:08", "remaining_time": "18:31:12", "throughput": 8339.77, "total_tokens": 219739144} {"current_steps": 215900, "total_steps": 761865, "loss": 1.9986, "lr": 8.146103873908825e-07, "epoch": 4.250753086176685, "percentage": 28.34, "elapsed_time": "7:19:20", "remaining_time": "18:31:00", "throughput": 8339.77, "total_tokens": 219841544} {"current_steps": 216000, "total_steps": 761865, "loss": 1.9911, "lr": 8.144501116865696e-07, "epoch": 4.252721938926188, "percentage": 28.35, "elapsed_time": "7:19:32", "remaining_time": "18:30:48", "throughput": 8339.78, "total_tokens": 219943944} {"current_steps": 216100, "total_steps": 761865, "loss": 2.0185, "lr": 8.142897825126675e-07, "epoch": 4.25469079167569, "percentage": 28.36, "elapsed_time": "7:19:45", "remaining_time": "18:30:36", "throughput": 8339.78, "total_tokens": 220046248} {"current_steps": 216200, "total_steps": 761865, "loss": 1.9602, "lr": 8.141293998964388e-07, "epoch": 4.256659644425193, "percentage": 28.38, "elapsed_time": "7:19:57", "remaining_time": "18:30:24", "throughput": 8339.79, "total_tokens": 220148648} {"current_steps": 216300, "total_steps": 761865, "loss": 1.9947, "lr": 8.13968963865155e-07, "epoch": 4.258628497174696, "percentage": 28.39, "elapsed_time": "7:20:09", "remaining_time": "18:30:11", "throughput": 8339.79, "total_tokens": 220250280} {"current_steps": 216400, "total_steps": 761865, "loss": 2.0138, "lr": 8.138084744460971e-07, "epoch": 4.2605973499242, "percentage": 28.4, "elapsed_time": "7:20:21", "remaining_time": "18:29:59", "throughput": 8339.77, "total_tokens": 220351728} {"current_steps": 216500, "total_steps": 761865, "loss": 1.9595, "lr": 8.136479316665549e-07, "epoch": 4.262566202673702, "percentage": 28.42, "elapsed_time": "7:20:33", "remaining_time": "18:29:47", "throughput": 8339.77, "total_tokens": 220453528} {"current_steps": 216600, "total_steps": 761865, "loss": 1.9962, "lr": 8.134873355538274e-07, "epoch": 4.264535055423205, "percentage": 28.43, "elapsed_time": "7:20:46", "remaining_time": "18:29:35", "throughput": 8339.76, "total_tokens": 220554864} {"current_steps": 216700, "total_steps": 761865, "loss": 2.0066, "lr": 8.133266861352226e-07, "epoch": 4.266503908172708, "percentage": 28.44, "elapsed_time": "7:20:58", "remaining_time": "18:29:22", "throughput": 8339.76, "total_tokens": 220656696} {"current_steps": 216800, "total_steps": 761865, "loss": 1.9398, "lr": 8.131659834380574e-07, "epoch": 4.268472760922211, "percentage": 28.46, "elapsed_time": "7:21:10", "remaining_time": "18:29:10", "throughput": 8339.76, "total_tokens": 220759096} {"current_steps": 216900, "total_steps": 761865, "loss": 1.9424, "lr": 8.130052274896581e-07, "epoch": 4.270441613671713, "percentage": 28.47, "elapsed_time": "7:21:22", "remaining_time": "18:28:58", "throughput": 8339.76, "total_tokens": 220860648} {"current_steps": 217000, "total_steps": 761865, "loss": 2.0372, "lr": 8.128444183173599e-07, "epoch": 4.272410466421216, "percentage": 28.48, "elapsed_time": "7:21:35", "remaining_time": "18:28:46", "throughput": 8339.76, "total_tokens": 220963048} {"current_steps": 217100, "total_steps": 761865, "loss": 1.9601, "lr": 8.12683555948507e-07, "epoch": 4.274379319170719, "percentage": 28.5, "elapsed_time": "7:21:47", "remaining_time": "18:28:34", "throughput": 8339.77, "total_tokens": 221065448} {"current_steps": 217200, "total_steps": 761865, "loss": 1.9583, "lr": 8.125226404104528e-07, "epoch": 4.2763481719202225, "percentage": 28.51, "elapsed_time": "7:21:59", "remaining_time": "18:28:22", "throughput": 8339.77, "total_tokens": 221167848} {"current_steps": 217300, "total_steps": 761865, "loss": 1.996, "lr": 8.123616717305595e-07, "epoch": 4.278317024669725, "percentage": 28.52, "elapsed_time": "7:22:11", "remaining_time": "18:28:10", "throughput": 8339.78, "total_tokens": 221269760} {"current_steps": 217400, "total_steps": 761865, "loss": 1.9959, "lr": 8.122006499361984e-07, "epoch": 4.280285877419228, "percentage": 28.54, "elapsed_time": "7:22:24", "remaining_time": "18:27:57", "throughput": 8339.77, "total_tokens": 221371328} {"current_steps": 217500, "total_steps": 761865, "loss": 1.9787, "lr": 8.120395750547501e-07, "epoch": 4.282254730168731, "percentage": 28.55, "elapsed_time": "7:22:36", "remaining_time": "18:27:45", "throughput": 8339.77, "total_tokens": 221473728} {"current_steps": 217600, "total_steps": 761865, "loss": 1.9408, "lr": 8.11878447113604e-07, "epoch": 4.284223582918234, "percentage": 28.56, "elapsed_time": "7:22:48", "remaining_time": "18:27:33", "throughput": 8339.77, "total_tokens": 221575632} {"current_steps": 217700, "total_steps": 761865, "loss": 1.9984, "lr": 8.117172661401584e-07, "epoch": 4.286192435667736, "percentage": 28.57, "elapsed_time": "7:23:00", "remaining_time": "18:27:21", "throughput": 8339.77, "total_tokens": 221677184} {"current_steps": 217800, "total_steps": 761865, "loss": 1.9746, "lr": 8.115560321618206e-07, "epoch": 4.288161288417239, "percentage": 28.59, "elapsed_time": "7:23:12", "remaining_time": "18:27:09", "throughput": 8339.78, "total_tokens": 221779584} {"current_steps": 217900, "total_steps": 761865, "loss": 2.002, "lr": 8.113947452060076e-07, "epoch": 4.290130141166742, "percentage": 28.6, "elapsed_time": "7:23:25", "remaining_time": "18:26:57", "throughput": 8339.79, "total_tokens": 221881984} {"current_steps": 218000, "total_steps": 761865, "loss": 1.985, "lr": 8.112334053001444e-07, "epoch": 4.292098993916245, "percentage": 28.61, "elapsed_time": "7:23:37", "remaining_time": "18:26:45", "throughput": 8339.79, "total_tokens": 221983856} {"current_steps": 218100, "total_steps": 761865, "loss": 1.985, "lr": 8.110720124716659e-07, "epoch": 4.294067846665748, "percentage": 28.63, "elapsed_time": "7:23:49", "remaining_time": "18:26:32", "throughput": 8339.79, "total_tokens": 222085744} {"current_steps": 218200, "total_steps": 761865, "loss": 1.9594, "lr": 8.109105667480153e-07, "epoch": 4.296036699415251, "percentage": 28.64, "elapsed_time": "7:24:01", "remaining_time": "18:26:20", "throughput": 8339.79, "total_tokens": 222187536} {"current_steps": 218300, "total_steps": 761865, "loss": 1.982, "lr": 8.107490681566451e-07, "epoch": 4.298005552164754, "percentage": 28.65, "elapsed_time": "7:24:14", "remaining_time": "18:26:08", "throughput": 8339.79, "total_tokens": 222289352} {"current_steps": 218400, "total_steps": 761865, "loss": 1.9871, "lr": 8.10587516725017e-07, "epoch": 4.2999744049142565, "percentage": 28.67, "elapsed_time": "7:24:26", "remaining_time": "18:25:56", "throughput": 8339.8, "total_tokens": 222391752} {"current_steps": 218500, "total_steps": 761865, "loss": 1.9659, "lr": 8.104259124806012e-07, "epoch": 4.301943257663759, "percentage": 28.68, "elapsed_time": "7:24:38", "remaining_time": "18:25:44", "throughput": 8339.8, "total_tokens": 222494152} {"current_steps": 218600, "total_steps": 761865, "loss": 1.9512, "lr": 8.102642554508772e-07, "epoch": 4.303912110413262, "percentage": 28.69, "elapsed_time": "7:24:50", "remaining_time": "18:25:31", "throughput": 8339.79, "total_tokens": 222595672} {"current_steps": 218700, "total_steps": 761865, "loss": 1.9729, "lr": 8.101025456633334e-07, "epoch": 4.305880963162765, "percentage": 28.71, "elapsed_time": "7:25:03", "remaining_time": "18:25:19", "throughput": 8339.8, "total_tokens": 222698072} {"current_steps": 218800, "total_steps": 761865, "loss": 2.0122, "lr": 8.099407831454674e-07, "epoch": 4.307849815912268, "percentage": 28.72, "elapsed_time": "7:25:15", "remaining_time": "18:25:07", "throughput": 8339.78, "total_tokens": 222798968} {"current_steps": 218900, "total_steps": 761865, "loss": 1.959, "lr": 8.097789679247853e-07, "epoch": 4.309818668661771, "percentage": 28.73, "elapsed_time": "7:25:27", "remaining_time": "18:24:55", "throughput": 8339.78, "total_tokens": 222901368} {"current_steps": 219000, "total_steps": 761865, "loss": 2.0052, "lr": 8.096171000288025e-07, "epoch": 4.311787521411274, "percentage": 28.75, "elapsed_time": "7:25:39", "remaining_time": "18:24:43", "throughput": 8339.78, "total_tokens": 223003768} {"current_steps": 219100, "total_steps": 761865, "loss": 2.0242, "lr": 8.094551794850432e-07, "epoch": 4.313756374160777, "percentage": 28.76, "elapsed_time": "7:25:51", "remaining_time": "18:24:31", "throughput": 8339.78, "total_tokens": 223105800} {"current_steps": 219200, "total_steps": 761865, "loss": 1.9974, "lr": 8.092932063210409e-07, "epoch": 4.3157252269102795, "percentage": 28.77, "elapsed_time": "7:26:04", "remaining_time": "18:24:19", "throughput": 8339.79, "total_tokens": 223208200} {"current_steps": 219300, "total_steps": 761865, "loss": 2.0031, "lr": 8.091311805643375e-07, "epoch": 4.317694079659782, "percentage": 28.78, "elapsed_time": "7:26:16", "remaining_time": "18:24:07", "throughput": 8339.8, "total_tokens": 223310600} {"current_steps": 219400, "total_steps": 761865, "loss": 1.9802, "lr": 8.089691022424841e-07, "epoch": 4.319662932409285, "percentage": 28.8, "elapsed_time": "7:26:28", "remaining_time": "18:23:55", "throughput": 8339.8, "total_tokens": 223413000} {"current_steps": 219500, "total_steps": 761865, "loss": 1.9982, "lr": 8.088069713830408e-07, "epoch": 4.321631785158788, "percentage": 28.81, "elapsed_time": "7:26:40", "remaining_time": "18:23:42", "throughput": 8339.8, "total_tokens": 223514864} {"current_steps": 219600, "total_steps": 761865, "loss": 1.9846, "lr": 8.086447880135767e-07, "epoch": 4.3236006379082905, "percentage": 28.82, "elapsed_time": "7:26:53", "remaining_time": "18:23:30", "throughput": 8339.81, "total_tokens": 223616984} {"current_steps": 219700, "total_steps": 761865, "loss": 1.9966, "lr": 8.084825521616696e-07, "epoch": 4.325569490657793, "percentage": 28.84, "elapsed_time": "7:27:05", "remaining_time": "18:23:18", "throughput": 8339.79, "total_tokens": 223717896} {"current_steps": 219800, "total_steps": 761865, "loss": 2.0122, "lr": 8.083202638549063e-07, "epoch": 4.327538343407297, "percentage": 28.85, "elapsed_time": "7:27:17", "remaining_time": "18:23:06", "throughput": 8339.78, "total_tokens": 223819536} {"current_steps": 219900, "total_steps": 761865, "loss": 1.9533, "lr": 8.081579231208827e-07, "epoch": 4.3295071961568, "percentage": 28.86, "elapsed_time": "7:27:29", "remaining_time": "18:22:54", "throughput": 8339.79, "total_tokens": 223921936} {"current_steps": 220000, "total_steps": 761865, "loss": 1.956, "lr": 8.079955299872034e-07, "epoch": 4.3314760489063024, "percentage": 28.88, "elapsed_time": "7:27:42", "remaining_time": "18:22:41", "throughput": 8339.78, "total_tokens": 224023568} {"current_steps": 220100, "total_steps": 761865, "loss": 1.9851, "lr": 8.078330844814819e-07, "epoch": 4.333444901655805, "percentage": 28.89, "elapsed_time": "7:27:54", "remaining_time": "18:22:30", "throughput": 8339.62, "total_tokens": 224125272} {"current_steps": 220200, "total_steps": 761865, "loss": 2.0065, "lr": 8.076705866313408e-07, "epoch": 4.335413754405308, "percentage": 28.9, "elapsed_time": "7:28:07", "remaining_time": "18:22:18", "throughput": 8339.62, "total_tokens": 224227672} {"current_steps": 220300, "total_steps": 761865, "loss": 2.0414, "lr": 8.075080364644116e-07, "epoch": 4.337382607154811, "percentage": 28.92, "elapsed_time": "7:28:19", "remaining_time": "18:22:06", "throughput": 8339.63, "total_tokens": 224329800} {"current_steps": 220400, "total_steps": 761865, "loss": 2.0027, "lr": 8.073454340083342e-07, "epoch": 4.3393514599043135, "percentage": 28.93, "elapsed_time": "7:28:31", "remaining_time": "18:21:54", "throughput": 8339.62, "total_tokens": 224431352} {"current_steps": 220500, "total_steps": 761865, "loss": 1.9898, "lr": 8.071827792907582e-07, "epoch": 4.341320312653816, "percentage": 28.94, "elapsed_time": "7:28:43", "remaining_time": "18:21:42", "throughput": 8339.61, "total_tokens": 224532992} {"current_steps": 220600, "total_steps": 761865, "loss": 2.0278, "lr": 8.070200723393414e-07, "epoch": 4.34328916540332, "percentage": 28.96, "elapsed_time": "7:28:55", "remaining_time": "18:21:29", "throughput": 8339.61, "total_tokens": 224634448} {"current_steps": 220700, "total_steps": 761865, "loss": 2.0014, "lr": 8.068573131817508e-07, "epoch": 4.345258018152823, "percentage": 28.97, "elapsed_time": "7:29:08", "remaining_time": "18:21:17", "throughput": 8339.59, "total_tokens": 224735272} {"current_steps": 220800, "total_steps": 761865, "loss": 1.9861, "lr": 8.066945018456623e-07, "epoch": 4.347226870902325, "percentage": 28.98, "elapsed_time": "7:29:20", "remaining_time": "18:21:05", "throughput": 8339.58, "total_tokens": 224836856} {"current_steps": 220900, "total_steps": 761865, "loss": 1.991, "lr": 8.065316383587606e-07, "epoch": 4.349195723651828, "percentage": 28.99, "elapsed_time": "7:29:32", "remaining_time": "18:20:53", "throughput": 8339.58, "total_tokens": 224938760} {"current_steps": 221000, "total_steps": 761865, "loss": 1.9606, "lr": 8.06368722748739e-07, "epoch": 4.351164576401331, "percentage": 29.01, "elapsed_time": "7:29:44", "remaining_time": "18:20:40", "throughput": 8339.59, "total_tokens": 225040864} {"current_steps": 221100, "total_steps": 761865, "loss": 1.9728, "lr": 8.062057550433003e-07, "epoch": 4.353133429150834, "percentage": 29.02, "elapsed_time": "7:29:56", "remaining_time": "18:20:28", "throughput": 8339.59, "total_tokens": 225143264} {"current_steps": 221200, "total_steps": 761865, "loss": 2.0219, "lr": 8.060427352701557e-07, "epoch": 4.355102281900336, "percentage": 29.03, "elapsed_time": "7:30:09", "remaining_time": "18:20:16", "throughput": 8339.58, "total_tokens": 225245080} {"current_steps": 221300, "total_steps": 761865, "loss": 1.9436, "lr": 8.058796634570251e-07, "epoch": 4.357071134649839, "percentage": 29.05, "elapsed_time": "7:30:21", "remaining_time": "18:20:04", "throughput": 8339.58, "total_tokens": 225346856} {"current_steps": 221400, "total_steps": 761865, "loss": 2.0174, "lr": 8.057165396316377e-07, "epoch": 4.359039987399342, "percentage": 29.06, "elapsed_time": "7:30:33", "remaining_time": "18:19:52", "throughput": 8339.58, "total_tokens": 225448656} {"current_steps": 221500, "total_steps": 761865, "loss": 1.9718, "lr": 8.055533638217312e-07, "epoch": 4.361008840148846, "percentage": 29.07, "elapsed_time": "7:30:45", "remaining_time": "18:19:40", "throughput": 8339.58, "total_tokens": 225551056} {"current_steps": 221600, "total_steps": 761865, "loss": 1.9771, "lr": 8.053901360550523e-07, "epoch": 4.362977692898348, "percentage": 29.09, "elapsed_time": "7:30:58", "remaining_time": "18:19:28", "throughput": 8339.57, "total_tokens": 225652584} {"current_steps": 221700, "total_steps": 761865, "loss": 2.0222, "lr": 8.052268563593567e-07, "epoch": 4.364946545647851, "percentage": 29.1, "elapsed_time": "7:31:10", "remaining_time": "18:19:15", "throughput": 8339.58, "total_tokens": 225754984} {"current_steps": 221800, "total_steps": 761865, "loss": 1.9827, "lr": 8.050635247624086e-07, "epoch": 4.366915398397354, "percentage": 29.11, "elapsed_time": "7:31:22", "remaining_time": "18:19:03", "throughput": 8339.57, "total_tokens": 225856552} {"current_steps": 221900, "total_steps": 761865, "loss": 1.9879, "lr": 8.04900141291981e-07, "epoch": 4.368884251146857, "percentage": 29.13, "elapsed_time": "7:31:34", "remaining_time": "18:18:51", "throughput": 8339.57, "total_tokens": 225958496} {"current_steps": 222000, "total_steps": 761865, "loss": 2.0074, "lr": 8.047367059758559e-07, "epoch": 4.370853103896359, "percentage": 29.14, "elapsed_time": "7:31:47", "remaining_time": "18:18:39", "throughput": 8339.57, "total_tokens": 226060896} {"current_steps": 222100, "total_steps": 761865, "loss": 1.9692, "lr": 8.045732188418244e-07, "epoch": 4.372821956645862, "percentage": 29.15, "elapsed_time": "7:31:59", "remaining_time": "18:18:27", "throughput": 8339.55, "total_tokens": 226161880} {"current_steps": 222200, "total_steps": 761865, "loss": 1.9683, "lr": 8.04409679917686e-07, "epoch": 4.374790809395365, "percentage": 29.17, "elapsed_time": "7:32:11", "remaining_time": "18:18:14", "throughput": 8339.55, "total_tokens": 226263008} {"current_steps": 222300, "total_steps": 761865, "loss": 1.9961, "lr": 8.04246089231249e-07, "epoch": 4.376759662144869, "percentage": 29.18, "elapsed_time": "7:32:23", "remaining_time": "18:18:02", "throughput": 8339.53, "total_tokens": 226364176} {"current_steps": 222400, "total_steps": 761865, "loss": 1.982, "lr": 8.040824468103306e-07, "epoch": 4.378728514894371, "percentage": 29.19, "elapsed_time": "7:32:35", "remaining_time": "18:17:50", "throughput": 8339.53, "total_tokens": 226466576} {"current_steps": 222500, "total_steps": 761865, "loss": 1.996, "lr": 8.039187526827568e-07, "epoch": 4.380697367643874, "percentage": 29.2, "elapsed_time": "7:32:48", "remaining_time": "18:17:38", "throughput": 8339.53, "total_tokens": 226568976} {"current_steps": 222600, "total_steps": 761865, "loss": 1.9948, "lr": 8.037550068763625e-07, "epoch": 4.382666220393377, "percentage": 29.22, "elapsed_time": "7:33:00", "remaining_time": "18:17:26", "throughput": 8339.54, "total_tokens": 226671376} {"current_steps": 222700, "total_steps": 761865, "loss": 1.9881, "lr": 8.035912094189914e-07, "epoch": 4.38463507314288, "percentage": 29.23, "elapsed_time": "7:33:12", "remaining_time": "18:17:14", "throughput": 8339.54, "total_tokens": 226773776} {"current_steps": 222800, "total_steps": 761865, "loss": 1.9644, "lr": 8.034273603384956e-07, "epoch": 4.386603925892382, "percentage": 29.24, "elapsed_time": "7:33:24", "remaining_time": "18:17:02", "throughput": 8339.54, "total_tokens": 226876176} {"current_steps": 222900, "total_steps": 761865, "loss": 1.934, "lr": 8.032634596627366e-07, "epoch": 4.388572778641885, "percentage": 29.26, "elapsed_time": "7:33:37", "remaining_time": "18:16:49", "throughput": 8339.52, "total_tokens": 226976896} {"current_steps": 223000, "total_steps": 761865, "loss": 2.0059, "lr": 8.030995074195839e-07, "epoch": 4.390541631391388, "percentage": 29.27, "elapsed_time": "7:33:49", "remaining_time": "18:16:37", "throughput": 8339.51, "total_tokens": 227078272} {"current_steps": 223100, "total_steps": 761865, "loss": 1.9639, "lr": 8.029355036369164e-07, "epoch": 4.3925104841408915, "percentage": 29.28, "elapsed_time": "7:34:01", "remaining_time": "18:16:25", "throughput": 8339.51, "total_tokens": 227180088} {"current_steps": 223200, "total_steps": 761865, "loss": 2.0324, "lr": 8.027714483426218e-07, "epoch": 4.394479336890394, "percentage": 29.3, "elapsed_time": "7:34:13", "remaining_time": "18:16:13", "throughput": 8339.48, "total_tokens": 227281896} {"current_steps": 223300, "total_steps": 761865, "loss": 2.0029, "lr": 8.02607341564596e-07, "epoch": 4.396448189639897, "percentage": 29.31, "elapsed_time": "7:34:26", "remaining_time": "18:16:01", "throughput": 8339.42, "total_tokens": 227383400} {"current_steps": 223400, "total_steps": 761865, "loss": 1.9632, "lr": 8.02443183330744e-07, "epoch": 4.3984170423894, "percentage": 29.32, "elapsed_time": "7:34:38", "remaining_time": "18:15:49", "throughput": 8339.39, "total_tokens": 227485800} {"current_steps": 223500, "total_steps": 761865, "loss": 1.97, "lr": 8.022789736689796e-07, "epoch": 4.4003858951389025, "percentage": 29.34, "elapsed_time": "7:34:50", "remaining_time": "18:15:37", "throughput": 8339.34, "total_tokens": 227587272} {"current_steps": 223600, "total_steps": 761865, "loss": 2.0101, "lr": 8.021147126072254e-07, "epoch": 4.402354747888405, "percentage": 29.35, "elapsed_time": "7:35:03", "remaining_time": "18:15:26", "throughput": 8339.28, "total_tokens": 227688816} {"current_steps": 223700, "total_steps": 761865, "loss": 2.0184, "lr": 8.019504001734124e-07, "epoch": 4.404323600637908, "percentage": 29.36, "elapsed_time": "7:35:15", "remaining_time": "18:15:13", "throughput": 8339.22, "total_tokens": 227789008} {"current_steps": 223800, "total_steps": 761865, "loss": 1.9591, "lr": 8.017860363954807e-07, "epoch": 4.406292453387411, "percentage": 29.38, "elapsed_time": "7:35:27", "remaining_time": "18:15:01", "throughput": 8339.17, "total_tokens": 227890552} {"current_steps": 223900, "total_steps": 761865, "loss": 1.9961, "lr": 8.016216213013788e-07, "epoch": 4.4082613061369145, "percentage": 29.39, "elapsed_time": "7:35:40", "remaining_time": "18:14:50", "throughput": 8339.12, "total_tokens": 227992664} {"current_steps": 224000, "total_steps": 761865, "loss": 2.0172, "lr": 8.014571549190642e-07, "epoch": 4.410230158886417, "percentage": 29.4, "elapsed_time": "7:35:52", "remaining_time": "18:14:38", "throughput": 8339.09, "total_tokens": 228094568} {"current_steps": 224100, "total_steps": 761865, "loss": 2.0225, "lr": 8.012926372765029e-07, "epoch": 4.41219901163592, "percentage": 29.41, "elapsed_time": "7:36:04", "remaining_time": "18:14:26", "throughput": 8339.03, "total_tokens": 228196104} {"current_steps": 224200, "total_steps": 761865, "loss": 1.9956, "lr": 8.011280684016699e-07, "epoch": 4.414167864385423, "percentage": 29.43, "elapsed_time": "7:36:17", "remaining_time": "18:14:14", "throughput": 8339.01, "total_tokens": 228298504} {"current_steps": 224300, "total_steps": 761865, "loss": 1.9948, "lr": 8.009634483225489e-07, "epoch": 4.4161367171349255, "percentage": 29.44, "elapsed_time": "7:36:29", "remaining_time": "18:14:02", "throughput": 8338.95, "total_tokens": 228399888} {"current_steps": 224400, "total_steps": 761865, "loss": 2.0094, "lr": 8.007987770671318e-07, "epoch": 4.418105569884428, "percentage": 29.45, "elapsed_time": "7:36:41", "remaining_time": "18:13:50", "throughput": 8338.91, "total_tokens": 228500976} {"current_steps": 224500, "total_steps": 761865, "loss": 1.9365, "lr": 8.006340546634197e-07, "epoch": 4.420074422633931, "percentage": 29.47, "elapsed_time": "7:36:54", "remaining_time": "18:13:38", "throughput": 8338.88, "total_tokens": 228603376} {"current_steps": 224600, "total_steps": 761865, "loss": 2.0129, "lr": 8.004692811394223e-07, "epoch": 4.422043275383434, "percentage": 29.48, "elapsed_time": "7:37:06", "remaining_time": "18:13:27", "throughput": 8338.84, "total_tokens": 228705776} {"current_steps": 224700, "total_steps": 761865, "loss": 1.9556, "lr": 8.00304456523158e-07, "epoch": 4.4240121281329365, "percentage": 29.49, "elapsed_time": "7:37:18", "remaining_time": "18:13:15", "throughput": 8338.82, "total_tokens": 228808176} {"current_steps": 224800, "total_steps": 761865, "loss": 1.9627, "lr": 8.001395808426537e-07, "epoch": 4.42598098088244, "percentage": 29.51, "elapsed_time": "7:37:31", "remaining_time": "18:13:03", "throughput": 8338.77, "total_tokens": 228909720} {"current_steps": 224900, "total_steps": 761865, "loss": 2.0559, "lr": 7.999746541259451e-07, "epoch": 4.427949833631943, "percentage": 29.52, "elapsed_time": "7:37:43", "remaining_time": "18:12:51", "throughput": 8338.74, "total_tokens": 229012120} {"current_steps": 225000, "total_steps": 761865, "loss": 1.9864, "lr": 7.998096764010767e-07, "epoch": 4.429918686381446, "percentage": 29.53, "elapsed_time": "7:37:55", "remaining_time": "18:12:39", "throughput": 8338.7, "total_tokens": 229113904} {"current_steps": 225100, "total_steps": 761865, "loss": 1.9841, "lr": 7.996446476961015e-07, "epoch": 4.4318875391309485, "percentage": 29.55, "elapsed_time": "7:38:08", "remaining_time": "18:12:29", "throughput": 8338.5, "total_tokens": 229216120} {"current_steps": 225200, "total_steps": 761865, "loss": 1.9934, "lr": 7.994795680390814e-07, "epoch": 4.433856391880451, "percentage": 29.56, "elapsed_time": "7:38:21", "remaining_time": "18:12:17", "throughput": 8338.44, "total_tokens": 229317288} {"current_steps": 225300, "total_steps": 761865, "loss": 1.9653, "lr": 7.993144374580866e-07, "epoch": 4.435825244629954, "percentage": 29.57, "elapsed_time": "7:38:33", "remaining_time": "18:12:04", "throughput": 8338.39, "total_tokens": 229418184} {"current_steps": 225400, "total_steps": 761865, "loss": 1.9907, "lr": 7.991492559811964e-07, "epoch": 4.437794097379457, "percentage": 29.59, "elapsed_time": "7:38:45", "remaining_time": "18:11:53", "throughput": 8338.35, "total_tokens": 229520584} {"current_steps": 225500, "total_steps": 761865, "loss": 1.9663, "lr": 7.989840236364981e-07, "epoch": 4.4397629501289595, "percentage": 29.6, "elapsed_time": "7:38:58", "remaining_time": "18:11:41", "throughput": 8338.33, "total_tokens": 229622984} {"current_steps": 225600, "total_steps": 761865, "loss": 2.0149, "lr": 7.988187404520884e-07, "epoch": 4.441731802878463, "percentage": 29.61, "elapsed_time": "7:39:10", "remaining_time": "18:11:29", "throughput": 8338.27, "total_tokens": 229724216} {"current_steps": 225700, "total_steps": 761865, "loss": 2.0108, "lr": 7.986534064560723e-07, "epoch": 4.443700655627966, "percentage": 29.62, "elapsed_time": "7:39:22", "remaining_time": "18:11:17", "throughput": 8338.23, "total_tokens": 229825784} {"current_steps": 225800, "total_steps": 761865, "loss": 2.0118, "lr": 7.984880216765635e-07, "epoch": 4.445669508377469, "percentage": 29.64, "elapsed_time": "7:39:35", "remaining_time": "18:11:05", "throughput": 8338.16, "total_tokens": 229926592} {"current_steps": 225900, "total_steps": 761865, "loss": 1.9749, "lr": 7.98322586141684e-07, "epoch": 4.447638361126971, "percentage": 29.65, "elapsed_time": "7:39:47", "remaining_time": "18:10:53", "throughput": 8338.12, "total_tokens": 230027664} {"current_steps": 226000, "total_steps": 761865, "loss": 2.0502, "lr": 7.98157099879565e-07, "epoch": 4.449607213876474, "percentage": 29.66, "elapsed_time": "7:39:59", "remaining_time": "18:10:41", "throughput": 8338.08, "total_tokens": 230129584} {"current_steps": 226100, "total_steps": 761865, "loss": 1.9923, "lr": 7.979915629183458e-07, "epoch": 4.451576066625977, "percentage": 29.68, "elapsed_time": "7:40:11", "remaining_time": "18:10:29", "throughput": 8338.07, "total_tokens": 230230648} {"current_steps": 226200, "total_steps": 761865, "loss": 1.9725, "lr": 7.978259752861747e-07, "epoch": 4.45354491937548, "percentage": 29.69, "elapsed_time": "7:40:24", "remaining_time": "18:10:16", "throughput": 8338.06, "total_tokens": 230332176} {"current_steps": 226300, "total_steps": 761865, "loss": 2.0041, "lr": 7.976603370112087e-07, "epoch": 4.4555137721249825, "percentage": 29.7, "elapsed_time": "7:40:36", "remaining_time": "18:10:04", "throughput": 8338.05, "total_tokens": 230433304} {"current_steps": 226400, "total_steps": 761865, "loss": 2.0362, "lr": 7.974946481216128e-07, "epoch": 4.457482624874485, "percentage": 29.72, "elapsed_time": "7:40:48", "remaining_time": "18:09:52", "throughput": 8338.01, "total_tokens": 230532976} {"current_steps": 226500, "total_steps": 761865, "loss": 1.987, "lr": 7.973289086455612e-07, "epoch": 4.459451477623989, "percentage": 29.73, "elapsed_time": "7:41:00", "remaining_time": "18:09:39", "throughput": 8338.01, "total_tokens": 230634808} {"current_steps": 226600, "total_steps": 761865, "loss": 1.9851, "lr": 7.971631186112367e-07, "epoch": 4.461420330373492, "percentage": 29.74, "elapsed_time": "7:41:12", "remaining_time": "18:09:27", "throughput": 8338.0, "total_tokens": 230736392} {"current_steps": 226700, "total_steps": 761865, "loss": 1.9943, "lr": 7.969972780468299e-07, "epoch": 4.463389183122994, "percentage": 29.76, "elapsed_time": "7:41:25", "remaining_time": "18:09:15", "throughput": 8338.01, "total_tokens": 230838792} {"current_steps": 226800, "total_steps": 761865, "loss": 1.9732, "lr": 7.968313869805412e-07, "epoch": 4.465358035872497, "percentage": 29.77, "elapsed_time": "7:41:37", "remaining_time": "18:09:03", "throughput": 8338.01, "total_tokens": 230941192} {"current_steps": 226900, "total_steps": 761865, "loss": 2.0134, "lr": 7.966654454405785e-07, "epoch": 4.467326888622, "percentage": 29.78, "elapsed_time": "7:41:49", "remaining_time": "18:08:51", "throughput": 8338.0, "total_tokens": 231042680} {"current_steps": 227000, "total_steps": 761865, "loss": 1.9556, "lr": 7.964994534551592e-07, "epoch": 4.469295741371503, "percentage": 29.8, "elapsed_time": "7:42:01", "remaining_time": "18:08:39", "throughput": 8338.01, "total_tokens": 231145080} {"current_steps": 227100, "total_steps": 761865, "loss": 1.9598, "lr": 7.963334110525086e-07, "epoch": 4.471264594121005, "percentage": 29.81, "elapsed_time": "7:42:14", "remaining_time": "18:08:27", "throughput": 8338.02, "total_tokens": 231247480} {"current_steps": 227200, "total_steps": 761865, "loss": 2.0634, "lr": 7.961673182608609e-07, "epoch": 4.473233446870508, "percentage": 29.82, "elapsed_time": "7:42:26", "remaining_time": "18:08:14", "throughput": 8338.0, "total_tokens": 231348544} {"current_steps": 227300, "total_steps": 761865, "loss": 2.003, "lr": 7.960011751084587e-07, "epoch": 4.475202299620012, "percentage": 29.83, "elapsed_time": "7:42:38", "remaining_time": "18:08:02", "throughput": 8338.0, "total_tokens": 231450944} {"current_steps": 227400, "total_steps": 761865, "loss": 1.9968, "lr": 7.958349816235533e-07, "epoch": 4.477171152369515, "percentage": 29.85, "elapsed_time": "7:42:50", "remaining_time": "18:07:50", "throughput": 8337.99, "total_tokens": 231551472} {"current_steps": 227500, "total_steps": 761865, "loss": 1.9972, "lr": 7.956687378344043e-07, "epoch": 4.479140005119017, "percentage": 29.86, "elapsed_time": "7:43:02", "remaining_time": "18:07:37", "throughput": 8337.99, "total_tokens": 231652656} {"current_steps": 227600, "total_steps": 761865, "loss": 1.9865, "lr": 7.955024437692803e-07, "epoch": 4.48110885786852, "percentage": 29.87, "elapsed_time": "7:43:15", "remaining_time": "18:07:25", "throughput": 8337.99, "total_tokens": 231754496} {"current_steps": 227700, "total_steps": 761865, "loss": 1.9826, "lr": 7.953360994564581e-07, "epoch": 4.483077710618023, "percentage": 29.89, "elapsed_time": "7:43:27", "remaining_time": "18:07:13", "throughput": 8338.0, "total_tokens": 231856896} {"current_steps": 227800, "total_steps": 761865, "loss": 1.9761, "lr": 7.951697049242232e-07, "epoch": 4.485046563367526, "percentage": 29.9, "elapsed_time": "7:43:39", "remaining_time": "18:07:01", "throughput": 8338.0, "total_tokens": 231958848} {"current_steps": 227900, "total_steps": 761865, "loss": 1.9852, "lr": 7.950032602008695e-07, "epoch": 4.487015416117028, "percentage": 29.91, "elapsed_time": "7:43:51", "remaining_time": "18:06:49", "throughput": 8337.98, "total_tokens": 232061248} {"current_steps": 228000, "total_steps": 761865, "loss": 1.9611, "lr": 7.948367653146997e-07, "epoch": 4.488984268866531, "percentage": 29.93, "elapsed_time": "7:44:04", "remaining_time": "18:06:37", "throughput": 8337.98, "total_tokens": 232163648} {"current_steps": 228100, "total_steps": 761865, "loss": 1.9767, "lr": 7.946702202940246e-07, "epoch": 4.490953121616034, "percentage": 29.94, "elapsed_time": "7:44:16", "remaining_time": "18:06:25", "throughput": 8337.96, "total_tokens": 232265032} {"current_steps": 228200, "total_steps": 761865, "loss": 1.9756, "lr": 7.945036251671639e-07, "epoch": 4.4929219743655375, "percentage": 29.95, "elapsed_time": "7:44:28", "remaining_time": "18:06:13", "throughput": 8337.95, "total_tokens": 232367432} {"current_steps": 228300, "total_steps": 761865, "loss": 1.9786, "lr": 7.943369799624458e-07, "epoch": 4.49489082711504, "percentage": 29.97, "elapsed_time": "7:44:40", "remaining_time": "18:06:01", "throughput": 8337.95, "total_tokens": 232469728} {"current_steps": 228400, "total_steps": 761865, "loss": 1.9877, "lr": 7.941702847082066e-07, "epoch": 4.496859679864543, "percentage": 29.98, "elapsed_time": "7:44:53", "remaining_time": "18:05:48", "throughput": 8337.9, "total_tokens": 232569256} {"current_steps": 228500, "total_steps": 761865, "loss": 1.9814, "lr": 7.940035394327918e-07, "epoch": 4.498828532614046, "percentage": 29.99, "elapsed_time": "7:45:05", "remaining_time": "18:05:36", "throughput": 8337.89, "total_tokens": 232670504} {"current_steps": 228600, "total_steps": 761865, "loss": 1.9505, "lr": 7.938367441645548e-07, "epoch": 4.500797385363549, "percentage": 30.01, "elapsed_time": "7:45:17", "remaining_time": "18:05:24", "throughput": 8337.9, "total_tokens": 232772904} {"current_steps": 228700, "total_steps": 761865, "loss": 1.9631, "lr": 7.936698989318579e-07, "epoch": 4.502766238113051, "percentage": 30.02, "elapsed_time": "7:45:29", "remaining_time": "18:05:12", "throughput": 8337.9, "total_tokens": 232875304} {"current_steps": 228800, "total_steps": 761865, "loss": 2.028, "lr": 7.935030037630715e-07, "epoch": 4.504735090862554, "percentage": 30.03, "elapsed_time": "7:45:41", "remaining_time": "18:05:00", "throughput": 8337.91, "total_tokens": 232977704} {"current_steps": 228900, "total_steps": 761865, "loss": 2.0266, "lr": 7.93336058686575e-07, "epoch": 4.506703943612058, "percentage": 30.04, "elapsed_time": "7:45:54", "remaining_time": "18:04:47", "throughput": 8337.9, "total_tokens": 233079184} {"current_steps": 229000, "total_steps": 761865, "loss": 2.0386, "lr": 7.931690637307556e-07, "epoch": 4.5086727963615605, "percentage": 30.06, "elapsed_time": "7:46:06", "remaining_time": "18:04:35", "throughput": 8337.89, "total_tokens": 233181168} {"current_steps": 229100, "total_steps": 761865, "loss": 2.0128, "lr": 7.930020189240098e-07, "epoch": 4.510641649111063, "percentage": 30.07, "elapsed_time": "7:46:18", "remaining_time": "18:04:23", "throughput": 8337.89, "total_tokens": 233283568} {"current_steps": 229200, "total_steps": 761865, "loss": 1.9569, "lr": 7.928349242947417e-07, "epoch": 4.512610501860566, "percentage": 30.08, "elapsed_time": "7:46:30", "remaining_time": "18:04:11", "throughput": 8337.88, "total_tokens": 233385224} {"current_steps": 229300, "total_steps": 761865, "loss": 1.9724, "lr": 7.926677798713648e-07, "epoch": 4.514579354610069, "percentage": 30.1, "elapsed_time": "7:46:43", "remaining_time": "18:03:59", "throughput": 8337.88, "total_tokens": 233487624} {"current_steps": 229400, "total_steps": 761865, "loss": 1.9751, "lr": 7.925005856823005e-07, "epoch": 4.5165482073595715, "percentage": 30.11, "elapsed_time": "7:46:55", "remaining_time": "18:03:47", "throughput": 8337.88, "total_tokens": 233590024} {"current_steps": 229500, "total_steps": 761865, "loss": 1.9788, "lr": 7.923333417559785e-07, "epoch": 4.518517060109074, "percentage": 30.12, "elapsed_time": "7:47:07", "remaining_time": "18:03:35", "throughput": 8337.86, "total_tokens": 233690840} {"current_steps": 229600, "total_steps": 761865, "loss": 2.0116, "lr": 7.921660481208375e-07, "epoch": 4.520485912858577, "percentage": 30.14, "elapsed_time": "7:47:19", "remaining_time": "18:03:22", "throughput": 8337.87, "total_tokens": 233793240} {"current_steps": 229700, "total_steps": 761865, "loss": 2.0102, "lr": 7.919987048053243e-07, "epoch": 4.52245476560808, "percentage": 30.15, "elapsed_time": "7:47:32", "remaining_time": "18:03:10", "throughput": 8337.86, "total_tokens": 233894824} {"current_steps": 229800, "total_steps": 761865, "loss": 2.0355, "lr": 7.91831311837894e-07, "epoch": 4.5244236183575826, "percentage": 30.16, "elapsed_time": "7:47:44", "remaining_time": "18:02:58", "throughput": 8337.85, "total_tokens": 233996416} {"current_steps": 229900, "total_steps": 761865, "loss": 2.0399, "lr": 7.916638692470107e-07, "epoch": 4.526392471107086, "percentage": 30.18, "elapsed_time": "7:47:56", "remaining_time": "18:02:46", "throughput": 8337.85, "total_tokens": 234098728} {"current_steps": 230000, "total_steps": 761865, "loss": 1.9528, "lr": 7.914963770611464e-07, "epoch": 4.528361323856589, "percentage": 30.19, "elapsed_time": "7:48:08", "remaining_time": "18:02:34", "throughput": 8337.84, "total_tokens": 234200336} {"current_steps": 230100, "total_steps": 761865, "loss": 2.0033, "lr": 7.913288353087817e-07, "epoch": 4.530330176606092, "percentage": 30.2, "elapsed_time": "7:48:21", "remaining_time": "18:02:23", "throughput": 8337.68, "total_tokens": 234302736} {"current_steps": 230200, "total_steps": 761865, "loss": 1.9786, "lr": 7.911612440184057e-07, "epoch": 4.5322990293555945, "percentage": 30.22, "elapsed_time": "7:48:33", "remaining_time": "18:02:10", "throughput": 8337.67, "total_tokens": 234403176} {"current_steps": 230300, "total_steps": 761865, "loss": 2.056, "lr": 7.909936032185161e-07, "epoch": 4.534267882105097, "percentage": 30.23, "elapsed_time": "7:48:45", "remaining_time": "18:01:58", "throughput": 8337.67, "total_tokens": 234505000} {"current_steps": 230400, "total_steps": 761865, "loss": 1.985, "lr": 7.908259129376185e-07, "epoch": 4.5362367348546, "percentage": 30.24, "elapsed_time": "7:48:58", "remaining_time": "18:01:46", "throughput": 8337.65, "total_tokens": 234605928} {"current_steps": 230500, "total_steps": 761865, "loss": 1.9942, "lr": 7.906581732042275e-07, "epoch": 4.538205587604103, "percentage": 30.25, "elapsed_time": "7:49:10", "remaining_time": "18:01:34", "throughput": 8337.65, "total_tokens": 234707848} {"current_steps": 230600, "total_steps": 761865, "loss": 1.9839, "lr": 7.904903840468655e-07, "epoch": 4.540174440353606, "percentage": 30.27, "elapsed_time": "7:49:22", "remaining_time": "18:01:22", "throughput": 8337.65, "total_tokens": 234809720} {"current_steps": 230700, "total_steps": 761865, "loss": 1.955, "lr": 7.903225454940639e-07, "epoch": 4.542143293103109, "percentage": 30.28, "elapsed_time": "7:49:34", "remaining_time": "18:01:09", "throughput": 8337.65, "total_tokens": 234911384} {"current_steps": 230800, "total_steps": 761865, "loss": 2.0247, "lr": 7.901546575743621e-07, "epoch": 4.544112145852612, "percentage": 30.29, "elapsed_time": "7:49:47", "remaining_time": "18:00:57", "throughput": 8337.64, "total_tokens": 235013416} {"current_steps": 230900, "total_steps": 761865, "loss": 1.9646, "lr": 7.89986720316308e-07, "epoch": 4.546080998602115, "percentage": 30.31, "elapsed_time": "7:49:59", "remaining_time": "18:00:45", "throughput": 8337.64, "total_tokens": 235115008} {"current_steps": 231000, "total_steps": 761865, "loss": 1.961, "lr": 7.89818733748458e-07, "epoch": 4.548049851351617, "percentage": 30.32, "elapsed_time": "7:50:11", "remaining_time": "18:00:33", "throughput": 8337.65, "total_tokens": 235217408} {"current_steps": 231100, "total_steps": 761865, "loss": 2.0015, "lr": 7.896506978993767e-07, "epoch": 4.55001870410112, "percentage": 30.33, "elapsed_time": "7:50:23", "remaining_time": "18:00:21", "throughput": 8337.65, "total_tokens": 235319256} {"current_steps": 231200, "total_steps": 761865, "loss": 2.015, "lr": 7.894826127976374e-07, "epoch": 4.551987556850623, "percentage": 30.35, "elapsed_time": "7:50:35", "remaining_time": "18:00:08", "throughput": 8337.64, "total_tokens": 235420928} {"current_steps": 231300, "total_steps": 761865, "loss": 1.997, "lr": 7.893144784718213e-07, "epoch": 4.553956409600126, "percentage": 30.36, "elapsed_time": "7:50:48", "remaining_time": "17:59:56", "throughput": 8337.64, "total_tokens": 235522856} {"current_steps": 231400, "total_steps": 761865, "loss": 1.9465, "lr": 7.891462949505185e-07, "epoch": 4.5559252623496285, "percentage": 30.37, "elapsed_time": "7:51:00", "remaining_time": "17:59:44", "throughput": 8337.65, "total_tokens": 235625256} {"current_steps": 231500, "total_steps": 761865, "loss": 2.0049, "lr": 7.889780622623268e-07, "epoch": 4.557894115099132, "percentage": 30.39, "elapsed_time": "7:51:12", "remaining_time": "17:59:32", "throughput": 8337.64, "total_tokens": 235725664} {"current_steps": 231600, "total_steps": 761865, "loss": 2.0241, "lr": 7.888097804358531e-07, "epoch": 4.559862967848635, "percentage": 30.4, "elapsed_time": "7:51:24", "remaining_time": "17:59:19", "throughput": 8337.63, "total_tokens": 235826840} {"current_steps": 231700, "total_steps": 761865, "loss": 1.9947, "lr": 7.88641449499712e-07, "epoch": 4.561831820598138, "percentage": 30.41, "elapsed_time": "7:51:36", "remaining_time": "17:59:07", "throughput": 8337.62, "total_tokens": 235927976} {"current_steps": 231800, "total_steps": 761865, "loss": 2.003, "lr": 7.884730694825271e-07, "epoch": 4.56380067334764, "percentage": 30.43, "elapsed_time": "7:51:49", "remaining_time": "17:58:55", "throughput": 8337.62, "total_tokens": 236029696} {"current_steps": 231900, "total_steps": 761865, "loss": 1.9189, "lr": 7.883046404129299e-07, "epoch": 4.565769526097143, "percentage": 30.44, "elapsed_time": "7:52:01", "remaining_time": "17:58:43", "throughput": 8337.62, "total_tokens": 236132096} {"current_steps": 232000, "total_steps": 761865, "loss": 1.9752, "lr": 7.8813616231956e-07, "epoch": 4.567738378846646, "percentage": 30.45, "elapsed_time": "7:52:13", "remaining_time": "17:58:31", "throughput": 8337.63, "total_tokens": 236234496} {"current_steps": 232100, "total_steps": 761865, "loss": 1.9923, "lr": 7.879676352310662e-07, "epoch": 4.569707231596149, "percentage": 30.46, "elapsed_time": "7:52:25", "remaining_time": "17:58:18", "throughput": 8337.63, "total_tokens": 236336752} {"current_steps": 232200, "total_steps": 761865, "loss": 1.9548, "lr": 7.877990591761046e-07, "epoch": 4.571676084345651, "percentage": 30.48, "elapsed_time": "7:52:38", "remaining_time": "17:58:06", "throughput": 8337.63, "total_tokens": 236439152} {"current_steps": 232300, "total_steps": 761865, "loss": 1.9822, "lr": 7.876304341833407e-07, "epoch": 4.573644937095155, "percentage": 30.49, "elapsed_time": "7:52:50", "remaining_time": "17:57:54", "throughput": 8337.63, "total_tokens": 236540784} {"current_steps": 232400, "total_steps": 761865, "loss": 1.9805, "lr": 7.874617602814472e-07, "epoch": 4.575613789844658, "percentage": 30.5, "elapsed_time": "7:53:02", "remaining_time": "17:57:42", "throughput": 8337.63, "total_tokens": 236642752} {"current_steps": 232500, "total_steps": 761865, "loss": 2.002, "lr": 7.87293037499106e-07, "epoch": 4.577582642594161, "percentage": 30.52, "elapsed_time": "7:53:14", "remaining_time": "17:57:30", "throughput": 8337.63, "total_tokens": 236745152} {"current_steps": 232600, "total_steps": 761865, "loss": 1.9208, "lr": 7.87124265865007e-07, "epoch": 4.579551495343663, "percentage": 30.53, "elapsed_time": "7:53:26", "remaining_time": "17:57:18", "throughput": 8337.63, "total_tokens": 236846792} {"current_steps": 232700, "total_steps": 761865, "loss": 1.9783, "lr": 7.869554454078482e-07, "epoch": 4.581520348093166, "percentage": 30.54, "elapsed_time": "7:53:39", "remaining_time": "17:57:05", "throughput": 8337.64, "total_tokens": 236949192} {"current_steps": 232800, "total_steps": 761865, "loss": 1.9966, "lr": 7.867865761563364e-07, "epoch": 4.583489200842669, "percentage": 30.56, "elapsed_time": "7:53:51", "remaining_time": "17:56:53", "throughput": 8337.64, "total_tokens": 237051000} {"current_steps": 232900, "total_steps": 761865, "loss": 1.9756, "lr": 7.866176581391861e-07, "epoch": 4.585458053592172, "percentage": 30.57, "elapsed_time": "7:54:03", "remaining_time": "17:56:41", "throughput": 8337.63, "total_tokens": 237152552} {"current_steps": 233000, "total_steps": 761865, "loss": 2.0251, "lr": 7.864486913851203e-07, "epoch": 4.587426906341674, "percentage": 30.58, "elapsed_time": "7:54:15", "remaining_time": "17:56:29", "throughput": 8337.62, "total_tokens": 237253944} {"current_steps": 233100, "total_steps": 761865, "loss": 1.9849, "lr": 7.862796759228707e-07, "epoch": 4.589395759091177, "percentage": 30.6, "elapsed_time": "7:54:28", "remaining_time": "17:56:16", "throughput": 8337.61, "total_tokens": 237355384} {"current_steps": 233200, "total_steps": 761865, "loss": 1.9724, "lr": 7.861106117811767e-07, "epoch": 4.591364611840681, "percentage": 30.61, "elapsed_time": "7:54:40", "remaining_time": "17:56:04", "throughput": 8337.61, "total_tokens": 237456600} {"current_steps": 233300, "total_steps": 761865, "loss": 1.9423, "lr": 7.859414989887865e-07, "epoch": 4.5933334645901835, "percentage": 30.62, "elapsed_time": "7:54:52", "remaining_time": "17:55:52", "throughput": 8337.6, "total_tokens": 237558360} {"current_steps": 233400, "total_steps": 761865, "loss": 2.0129, "lr": 7.85772337574456e-07, "epoch": 4.595302317339686, "percentage": 30.64, "elapsed_time": "7:55:04", "remaining_time": "17:55:40", "throughput": 8337.61, "total_tokens": 237660760} {"current_steps": 233500, "total_steps": 761865, "loss": 1.9746, "lr": 7.856031275669499e-07, "epoch": 4.597271170089189, "percentage": 30.65, "elapsed_time": "7:55:16", "remaining_time": "17:55:27", "throughput": 8337.6, "total_tokens": 237761864} {"current_steps": 233600, "total_steps": 761865, "loss": 1.9703, "lr": 7.854338689950408e-07, "epoch": 4.599240022838692, "percentage": 30.66, "elapsed_time": "7:55:28", "remaining_time": "17:55:15", "throughput": 8337.6, "total_tokens": 237862968} {"current_steps": 233700, "total_steps": 761865, "loss": 1.9833, "lr": 7.852645618875098e-07, "epoch": 4.601208875588195, "percentage": 30.67, "elapsed_time": "7:55:41", "remaining_time": "17:55:03", "throughput": 8337.59, "total_tokens": 237964040} {"current_steps": 233800, "total_steps": 761865, "loss": 2.0093, "lr": 7.85095206273146e-07, "epoch": 4.603177728337697, "percentage": 30.69, "elapsed_time": "7:55:53", "remaining_time": "17:54:50", "throughput": 8337.56, "total_tokens": 238064352} {"current_steps": 233900, "total_steps": 761865, "loss": 1.9902, "lr": 7.84925802180747e-07, "epoch": 4.605146581087201, "percentage": 30.7, "elapsed_time": "7:56:05", "remaining_time": "17:54:38", "throughput": 8337.56, "total_tokens": 238165888} {"current_steps": 234000, "total_steps": 761865, "loss": 1.9852, "lr": 7.847563496391185e-07, "epoch": 4.607115433836704, "percentage": 30.71, "elapsed_time": "7:56:17", "remaining_time": "17:54:26", "throughput": 8337.57, "total_tokens": 238268288} {"current_steps": 234100, "total_steps": 761865, "loss": 2.0179, "lr": 7.845868486770746e-07, "epoch": 4.6090842865862065, "percentage": 30.73, "elapsed_time": "7:56:29", "remaining_time": "17:54:14", "throughput": 8337.58, "total_tokens": 238370688} {"current_steps": 234200, "total_steps": 761865, "loss": 1.9391, "lr": 7.844172993234372e-07, "epoch": 4.611053139335709, "percentage": 30.74, "elapsed_time": "7:56:42", "remaining_time": "17:54:02", "throughput": 8337.57, "total_tokens": 238472456} {"current_steps": 234300, "total_steps": 761865, "loss": 1.9625, "lr": 7.84247701607037e-07, "epoch": 4.613021992085212, "percentage": 30.75, "elapsed_time": "7:56:54", "remaining_time": "17:53:50", "throughput": 8337.57, "total_tokens": 238574856} {"current_steps": 234400, "total_steps": 761865, "loss": 1.9387, "lr": 7.840780555567128e-07, "epoch": 4.614990844834715, "percentage": 30.77, "elapsed_time": "7:57:06", "remaining_time": "17:53:37", "throughput": 8337.58, "total_tokens": 238676608} {"current_steps": 234500, "total_steps": 761865, "loss": 1.9293, "lr": 7.839083612013111e-07, "epoch": 4.6169596975842175, "percentage": 30.78, "elapsed_time": "7:57:18", "remaining_time": "17:53:25", "throughput": 8337.57, "total_tokens": 238779008} {"current_steps": 234600, "total_steps": 761865, "loss": 1.9873, "lr": 7.837386185696872e-07, "epoch": 4.61892855033372, "percentage": 30.79, "elapsed_time": "7:57:31", "remaining_time": "17:53:13", "throughput": 8337.57, "total_tokens": 238880936} {"current_steps": 234700, "total_steps": 761865, "loss": 1.9705, "lr": 7.835688276907044e-07, "epoch": 4.620897403083223, "percentage": 30.81, "elapsed_time": "7:57:43", "remaining_time": "17:53:01", "throughput": 8337.57, "total_tokens": 238983336} {"current_steps": 234800, "total_steps": 761865, "loss": 2.0523, "lr": 7.833989885932342e-07, "epoch": 4.622866255832726, "percentage": 30.82, "elapsed_time": "7:57:55", "remaining_time": "17:52:49", "throughput": 8337.57, "total_tokens": 239084888} {"current_steps": 234900, "total_steps": 761865, "loss": 1.9507, "lr": 7.832291013061561e-07, "epoch": 4.6248351085822295, "percentage": 30.83, "elapsed_time": "7:58:07", "remaining_time": "17:52:37", "throughput": 8337.56, "total_tokens": 239186672} {"current_steps": 235000, "total_steps": 761865, "loss": 1.9871, "lr": 7.830591658583584e-07, "epoch": 4.626803961331732, "percentage": 30.85, "elapsed_time": "7:58:20", "remaining_time": "17:52:24", "throughput": 8337.56, "total_tokens": 239288384} {"current_steps": 235100, "total_steps": 761865, "loss": 2.0223, "lr": 7.828891822787369e-07, "epoch": 4.628772814081235, "percentage": 30.86, "elapsed_time": "7:58:32", "remaining_time": "17:52:13", "throughput": 8337.39, "total_tokens": 239389464} {"current_steps": 235200, "total_steps": 761865, "loss": 1.9643, "lr": 7.827191505961959e-07, "epoch": 4.630741666830738, "percentage": 30.87, "elapsed_time": "7:58:45", "remaining_time": "17:52:01", "throughput": 8337.4, "total_tokens": 239491864} {"current_steps": 235300, "total_steps": 761865, "loss": 2.0114, "lr": 7.82549070839648e-07, "epoch": 4.6327105195802405, "percentage": 30.88, "elapsed_time": "7:58:57", "remaining_time": "17:51:49", "throughput": 8337.4, "total_tokens": 239594264} {"current_steps": 235400, "total_steps": 761865, "loss": 1.9559, "lr": 7.823789430380136e-07, "epoch": 4.634679372329743, "percentage": 30.9, "elapsed_time": "7:59:09", "remaining_time": "17:51:37", "throughput": 8337.41, "total_tokens": 239696664} {"current_steps": 235500, "total_steps": 761865, "loss": 1.9618, "lr": 7.822087672202217e-07, "epoch": 4.636648225079246, "percentage": 30.91, "elapsed_time": "7:59:21", "remaining_time": "17:51:25", "throughput": 8337.4, "total_tokens": 239798208} {"current_steps": 235600, "total_steps": 761865, "loss": 1.9937, "lr": 7.820385434152093e-07, "epoch": 4.63861707782875, "percentage": 30.92, "elapsed_time": "7:59:33", "remaining_time": "17:51:13", "throughput": 8337.39, "total_tokens": 239899792} {"current_steps": 235700, "total_steps": 761865, "loss": 2.0103, "lr": 7.818682716519214e-07, "epoch": 4.640585930578252, "percentage": 30.94, "elapsed_time": "7:59:46", "remaining_time": "17:51:00", "throughput": 8337.38, "total_tokens": 240000832} {"current_steps": 235800, "total_steps": 761865, "loss": 1.9981, "lr": 7.816979519593112e-07, "epoch": 4.642554783327755, "percentage": 30.95, "elapsed_time": "7:59:58", "remaining_time": "17:50:48", "throughput": 8337.39, "total_tokens": 240103232} {"current_steps": 235900, "total_steps": 761865, "loss": 2.0369, "lr": 7.815275843663402e-07, "epoch": 4.644523636077258, "percentage": 30.96, "elapsed_time": "8:00:10", "remaining_time": "17:50:36", "throughput": 8337.38, "total_tokens": 240204352} {"current_steps": 236000, "total_steps": 761865, "loss": 2.0238, "lr": 7.813571689019781e-07, "epoch": 4.646492488826761, "percentage": 30.98, "elapsed_time": "8:00:22", "remaining_time": "17:50:24", "throughput": 8337.38, "total_tokens": 240306112} {"current_steps": 236100, "total_steps": 761865, "loss": 2.0585, "lr": 7.811867055952024e-07, "epoch": 4.6484613415762635, "percentage": 30.99, "elapsed_time": "8:00:34", "remaining_time": "17:50:11", "throughput": 8337.37, "total_tokens": 240407656} {"current_steps": 236200, "total_steps": 761865, "loss": 1.9717, "lr": 7.810161944749991e-07, "epoch": 4.650430194325766, "percentage": 31.0, "elapsed_time": "8:00:47", "remaining_time": "17:49:59", "throughput": 8337.37, "total_tokens": 240510056} {"current_steps": 236300, "total_steps": 761865, "loss": 2.0203, "lr": 7.808456355703621e-07, "epoch": 4.652399047075269, "percentage": 31.02, "elapsed_time": "8:00:59", "remaining_time": "17:49:47", "throughput": 8337.36, "total_tokens": 240610992} {"current_steps": 236400, "total_steps": 761865, "loss": 1.9609, "lr": 7.806750289102935e-07, "epoch": 4.654367899824772, "percentage": 31.03, "elapsed_time": "8:01:11", "remaining_time": "17:49:35", "throughput": 8337.35, "total_tokens": 240712640} {"current_steps": 236500, "total_steps": 761865, "loss": 1.9732, "lr": 7.805043745238037e-07, "epoch": 4.6563367525742745, "percentage": 31.04, "elapsed_time": "8:01:23", "remaining_time": "17:49:23", "throughput": 8337.36, "total_tokens": 240815040} {"current_steps": 236600, "total_steps": 761865, "loss": 2.0, "lr": 7.803336724399107e-07, "epoch": 4.658305605323778, "percentage": 31.06, "elapsed_time": "8:01:36", "remaining_time": "17:49:10", "throughput": 8337.37, "total_tokens": 240916976} {"current_steps": 236700, "total_steps": 761865, "loss": 1.9896, "lr": 7.801629226876414e-07, "epoch": 4.660274458073281, "percentage": 31.07, "elapsed_time": "8:01:48", "remaining_time": "17:48:58", "throughput": 8337.36, "total_tokens": 241018552} {"current_steps": 236800, "total_steps": 761865, "loss": 1.9879, "lr": 7.799921252960299e-07, "epoch": 4.662243310822784, "percentage": 31.08, "elapsed_time": "8:02:00", "remaining_time": "17:48:46", "throughput": 8337.37, "total_tokens": 241120952} {"current_steps": 236900, "total_steps": 761865, "loss": 2.0108, "lr": 7.798212802941191e-07, "epoch": 4.664212163572286, "percentage": 31.09, "elapsed_time": "8:02:12", "remaining_time": "17:48:34", "throughput": 8337.37, "total_tokens": 241223280} {"current_steps": 237000, "total_steps": 761865, "loss": 1.9737, "lr": 7.796503877109597e-07, "epoch": 4.666181016321789, "percentage": 31.11, "elapsed_time": "8:02:25", "remaining_time": "17:48:22", "throughput": 8337.38, "total_tokens": 241325680} {"current_steps": 237100, "total_steps": 761865, "loss": 1.9647, "lr": 7.794794475756106e-07, "epoch": 4.668149869071292, "percentage": 31.12, "elapsed_time": "8:02:37", "remaining_time": "17:48:10", "throughput": 8337.38, "total_tokens": 241427512} {"current_steps": 237200, "total_steps": 761865, "loss": 1.9795, "lr": 7.793084599171387e-07, "epoch": 4.670118721820795, "percentage": 31.13, "elapsed_time": "8:02:49", "remaining_time": "17:47:57", "throughput": 8337.38, "total_tokens": 241529912} {"current_steps": 237300, "total_steps": 761865, "loss": 1.933, "lr": 7.791374247646188e-07, "epoch": 4.672087574570298, "percentage": 31.15, "elapsed_time": "8:03:01", "remaining_time": "17:47:45", "throughput": 8337.37, "total_tokens": 241631400} {"current_steps": 237400, "total_steps": 761865, "loss": 1.9493, "lr": 7.789663421471343e-07, "epoch": 4.674056427319801, "percentage": 31.16, "elapsed_time": "8:03:13", "remaining_time": "17:47:33", "throughput": 8337.38, "total_tokens": 241733800} {"current_steps": 237500, "total_steps": 761865, "loss": 1.9725, "lr": 7.787952120937761e-07, "epoch": 4.676025280069304, "percentage": 31.17, "elapsed_time": "8:03:26", "remaining_time": "17:47:21", "throughput": 8337.38, "total_tokens": 241835624} {"current_steps": 237600, "total_steps": 761865, "loss": 2.0052, "lr": 7.78624034633644e-07, "epoch": 4.677994132818807, "percentage": 31.19, "elapsed_time": "8:03:38", "remaining_time": "17:47:09", "throughput": 8337.39, "total_tokens": 241937448} {"current_steps": 237700, "total_steps": 761865, "loss": 1.9878, "lr": 7.784528097958444e-07, "epoch": 4.679962985568309, "percentage": 31.2, "elapsed_time": "8:03:50", "remaining_time": "17:46:56", "throughput": 8337.38, "total_tokens": 242038424} {"current_steps": 237800, "total_steps": 761865, "loss": 1.9773, "lr": 7.782815376094931e-07, "epoch": 4.681931838317812, "percentage": 31.21, "elapsed_time": "8:04:02", "remaining_time": "17:46:44", "throughput": 8337.38, "total_tokens": 242139376} {"current_steps": 237900, "total_steps": 761865, "loss": 2.0059, "lr": 7.781102181037136e-07, "epoch": 4.683900691067315, "percentage": 31.23, "elapsed_time": "8:04:14", "remaining_time": "17:46:32", "throughput": 8337.38, "total_tokens": 242241136} {"current_steps": 238000, "total_steps": 761865, "loss": 1.9885, "lr": 7.779388513076373e-07, "epoch": 4.685869543816818, "percentage": 31.24, "elapsed_time": "8:04:27", "remaining_time": "17:46:19", "throughput": 8337.38, "total_tokens": 242342904} {"current_steps": 238100, "total_steps": 761865, "loss": 1.9919, "lr": 7.777674372504033e-07, "epoch": 4.68783839656632, "percentage": 31.25, "elapsed_time": "8:04:39", "remaining_time": "17:46:07", "throughput": 8337.36, "total_tokens": 242443632} {"current_steps": 238200, "total_steps": 761865, "loss": 1.9468, "lr": 7.775959759611595e-07, "epoch": 4.689807249315824, "percentage": 31.27, "elapsed_time": "8:04:51", "remaining_time": "17:45:55", "throughput": 8337.35, "total_tokens": 242544712} {"current_steps": 238300, "total_steps": 761865, "loss": 1.9898, "lr": 7.774244674690613e-07, "epoch": 4.691776102065327, "percentage": 31.28, "elapsed_time": "8:05:03", "remaining_time": "17:45:42", "throughput": 8337.34, "total_tokens": 242646256} {"current_steps": 238400, "total_steps": 761865, "loss": 1.9578, "lr": 7.772529118032725e-07, "epoch": 4.69374495481483, "percentage": 31.29, "elapsed_time": "8:05:15", "remaining_time": "17:45:30", "throughput": 8337.34, "total_tokens": 242748128} {"current_steps": 238500, "total_steps": 761865, "loss": 1.9804, "lr": 7.770813089929643e-07, "epoch": 4.695713807564332, "percentage": 31.3, "elapsed_time": "8:05:28", "remaining_time": "17:45:18", "throughput": 8337.35, "total_tokens": 242850528} {"current_steps": 238600, "total_steps": 761865, "loss": 1.9641, "lr": 7.769096590673167e-07, "epoch": 4.697682660313835, "percentage": 31.32, "elapsed_time": "8:05:40", "remaining_time": "17:45:06", "throughput": 8337.33, "total_tokens": 242951256} {"current_steps": 238700, "total_steps": 761865, "loss": 1.9761, "lr": 7.76737962055517e-07, "epoch": 4.699651513063338, "percentage": 31.33, "elapsed_time": "8:05:52", "remaining_time": "17:44:54", "throughput": 8337.34, "total_tokens": 243053656} {"current_steps": 238800, "total_steps": 761865, "loss": 1.9956, "lr": 7.76566217986761e-07, "epoch": 4.701620365812841, "percentage": 31.34, "elapsed_time": "8:06:04", "remaining_time": "17:44:41", "throughput": 8337.35, "total_tokens": 243156056} {"current_steps": 238900, "total_steps": 761865, "loss": 1.955, "lr": 7.763944268902524e-07, "epoch": 4.703589218562343, "percentage": 31.36, "elapsed_time": "8:06:16", "remaining_time": "17:44:29", "throughput": 8337.35, "total_tokens": 243258456} {"current_steps": 239000, "total_steps": 761865, "loss": 2.0129, "lr": 7.762225887952025e-07, "epoch": 4.705558071311847, "percentage": 31.37, "elapsed_time": "8:06:29", "remaining_time": "17:44:17", "throughput": 8337.36, "total_tokens": 243360856} {"current_steps": 239100, "total_steps": 761865, "loss": 2.0004, "lr": 7.760507037308313e-07, "epoch": 4.70752692406135, "percentage": 31.38, "elapsed_time": "8:06:41", "remaining_time": "17:44:05", "throughput": 8337.37, "total_tokens": 243463256} {"current_steps": 239200, "total_steps": 761865, "loss": 2.0329, "lr": 7.758787717263662e-07, "epoch": 4.7094957768108525, "percentage": 31.4, "elapsed_time": "8:06:53", "remaining_time": "17:43:53", "throughput": 8337.35, "total_tokens": 243564056} {"current_steps": 239300, "total_steps": 761865, "loss": 1.9915, "lr": 7.757067928110431e-07, "epoch": 4.711464629560355, "percentage": 31.41, "elapsed_time": "8:07:05", "remaining_time": "17:43:41", "throughput": 8337.34, "total_tokens": 243665560} {"current_steps": 239400, "total_steps": 761865, "loss": 1.9581, "lr": 7.755347670141049e-07, "epoch": 4.713433482309858, "percentage": 31.42, "elapsed_time": "8:07:18", "remaining_time": "17:43:28", "throughput": 8337.35, "total_tokens": 243767960} {"current_steps": 239500, "total_steps": 761865, "loss": 1.9533, "lr": 7.753626943648038e-07, "epoch": 4.715402335059361, "percentage": 31.44, "elapsed_time": "8:07:30", "remaining_time": "17:43:16", "throughput": 8337.35, "total_tokens": 243869880} {"current_steps": 239600, "total_steps": 761865, "loss": 2.0057, "lr": 7.751905748923989e-07, "epoch": 4.7173711878088636, "percentage": 31.45, "elapsed_time": "8:07:42", "remaining_time": "17:43:04", "throughput": 8337.36, "total_tokens": 243971688} {"current_steps": 239700, "total_steps": 761865, "loss": 1.99, "lr": 7.750184086261578e-07, "epoch": 4.719340040558366, "percentage": 31.46, "elapsed_time": "8:07:54", "remaining_time": "17:42:52", "throughput": 8337.36, "total_tokens": 244074088} {"current_steps": 239800, "total_steps": 761865, "loss": 1.979, "lr": 7.74846195595356e-07, "epoch": 4.721308893307869, "percentage": 31.48, "elapsed_time": "8:08:07", "remaining_time": "17:42:40", "throughput": 8337.36, "total_tokens": 244176488} {"current_steps": 239900, "total_steps": 761865, "loss": 1.9828, "lr": 7.746739358292769e-07, "epoch": 4.723277746057373, "percentage": 31.49, "elapsed_time": "8:08:19", "remaining_time": "17:42:27", "throughput": 8337.35, "total_tokens": 244277368} {"current_steps": 240000, "total_steps": 761865, "loss": 1.965, "lr": 7.745016293572115e-07, "epoch": 4.7252465988068755, "percentage": 31.5, "elapsed_time": "8:08:31", "remaining_time": "17:42:15", "throughput": 8337.35, "total_tokens": 244379768} {"current_steps": 240100, "total_steps": 761865, "loss": 1.9679, "lr": 7.743292762084594e-07, "epoch": 4.727215451556378, "percentage": 31.51, "elapsed_time": "8:08:44", "remaining_time": "17:42:04", "throughput": 8337.2, "total_tokens": 244482168} {"current_steps": 240200, "total_steps": 761865, "loss": 2.0063, "lr": 7.741568764123276e-07, "epoch": 4.729184304305881, "percentage": 31.53, "elapsed_time": "8:08:56", "remaining_time": "17:41:52", "throughput": 8337.2, "total_tokens": 244583776} {"current_steps": 240300, "total_steps": 761865, "loss": 1.9971, "lr": 7.739844299981315e-07, "epoch": 4.731153157055384, "percentage": 31.54, "elapsed_time": "8:09:08", "remaining_time": "17:41:40", "throughput": 8337.18, "total_tokens": 244684488} {"current_steps": 240400, "total_steps": 761865, "loss": 1.9554, "lr": 7.738119369951936e-07, "epoch": 4.7331220098048865, "percentage": 31.55, "elapsed_time": "8:09:20", "remaining_time": "17:41:27", "throughput": 8337.16, "total_tokens": 244784608} {"current_steps": 240500, "total_steps": 761865, "loss": 1.9819, "lr": 7.736393974328456e-07, "epoch": 4.735090862554389, "percentage": 31.57, "elapsed_time": "8:09:32", "remaining_time": "17:41:15", "throughput": 8337.16, "total_tokens": 244887008} {"current_steps": 240600, "total_steps": 761865, "loss": 2.0177, "lr": 7.734668113404259e-07, "epoch": 4.737059715303893, "percentage": 31.58, "elapsed_time": "8:09:45", "remaining_time": "17:41:03", "throughput": 8337.16, "total_tokens": 244988952} {"current_steps": 240700, "total_steps": 761865, "loss": 1.983, "lr": 7.732941787472815e-07, "epoch": 4.739028568053396, "percentage": 31.59, "elapsed_time": "8:09:57", "remaining_time": "17:40:51", "throughput": 8337.15, "total_tokens": 245090336} {"current_steps": 240800, "total_steps": 761865, "loss": 1.993, "lr": 7.731214996827671e-07, "epoch": 4.740997420802898, "percentage": 31.61, "elapsed_time": "8:10:09", "remaining_time": "17:40:39", "throughput": 8337.13, "total_tokens": 245191096} {"current_steps": 240900, "total_steps": 761865, "loss": 2.0268, "lr": 7.729487741762453e-07, "epoch": 4.742966273552401, "percentage": 31.62, "elapsed_time": "8:10:21", "remaining_time": "17:40:26", "throughput": 8337.13, "total_tokens": 245293496} {"current_steps": 241000, "total_steps": 761865, "loss": 1.9771, "lr": 7.727760022570866e-07, "epoch": 4.744935126301904, "percentage": 31.63, "elapsed_time": "8:10:33", "remaining_time": "17:40:14", "throughput": 8337.12, "total_tokens": 245394472} {"current_steps": 241100, "total_steps": 761865, "loss": 1.9415, "lr": 7.726031839546694e-07, "epoch": 4.746903979051407, "percentage": 31.65, "elapsed_time": "8:10:46", "remaining_time": "17:40:02", "throughput": 8337.12, "total_tokens": 245496872} {"current_steps": 241200, "total_steps": 761865, "loss": 1.9613, "lr": 7.724303192983798e-07, "epoch": 4.7488728318009095, "percentage": 31.66, "elapsed_time": "8:10:58", "remaining_time": "17:39:50", "throughput": 8337.12, "total_tokens": 245598696} {"current_steps": 241300, "total_steps": 761865, "loss": 1.9493, "lr": 7.722574083176126e-07, "epoch": 4.750841684550412, "percentage": 31.67, "elapsed_time": "8:11:10", "remaining_time": "17:39:38", "throughput": 8337.12, "total_tokens": 245700520} {"current_steps": 241400, "total_steps": 761865, "loss": 1.9343, "lr": 7.72084451041769e-07, "epoch": 4.752810537299915, "percentage": 31.69, "elapsed_time": "8:11:22", "remaining_time": "17:39:25", "throughput": 8337.12, "total_tokens": 245802376} {"current_steps": 241500, "total_steps": 761865, "loss": 1.9815, "lr": 7.719114475002598e-07, "epoch": 4.754779390049418, "percentage": 31.7, "elapsed_time": "8:11:35", "remaining_time": "17:39:13", "throughput": 8337.11, "total_tokens": 245903904} {"current_steps": 241600, "total_steps": 761865, "loss": 1.959, "lr": 7.717383977225021e-07, "epoch": 4.756748242798921, "percentage": 31.71, "elapsed_time": "8:11:47", "remaining_time": "17:39:01", "throughput": 8337.12, "total_tokens": 246006304} {"current_steps": 241700, "total_steps": 761865, "loss": 1.9583, "lr": 7.715653017379217e-07, "epoch": 4.758717095548424, "percentage": 31.72, "elapsed_time": "8:11:59", "remaining_time": "17:38:49", "throughput": 8337.12, "total_tokens": 246108040} {"current_steps": 241800, "total_steps": 761865, "loss": 2.0054, "lr": 7.713921595759525e-07, "epoch": 4.760685948297927, "percentage": 31.74, "elapsed_time": "8:12:11", "remaining_time": "17:38:37", "throughput": 8337.12, "total_tokens": 246209776} {"current_steps": 241900, "total_steps": 761865, "loss": 2.0034, "lr": 7.712189712660355e-07, "epoch": 4.76265480104743, "percentage": 31.75, "elapsed_time": "8:12:23", "remaining_time": "17:38:24", "throughput": 8337.12, "total_tokens": 246311672} {"current_steps": 242000, "total_steps": 761865, "loss": 1.9775, "lr": 7.7104573683762e-07, "epoch": 4.764623653796932, "percentage": 31.76, "elapsed_time": "8:12:36", "remaining_time": "17:38:12", "throughput": 8337.12, "total_tokens": 246413528} {"current_steps": 242100, "total_steps": 761865, "loss": 2.0206, "lr": 7.708724563201629e-07, "epoch": 4.766592506546435, "percentage": 31.78, "elapsed_time": "8:12:48", "remaining_time": "17:38:00", "throughput": 8337.12, "total_tokens": 246515928} {"current_steps": 242200, "total_steps": 761865, "loss": 2.0112, "lr": 7.706991297431294e-07, "epoch": 4.768561359295938, "percentage": 31.79, "elapsed_time": "8:13:00", "remaining_time": "17:37:48", "throughput": 8337.1, "total_tokens": 246616336} {"current_steps": 242300, "total_steps": 761865, "loss": 1.9552, "lr": 7.705257571359921e-07, "epoch": 4.770530212045442, "percentage": 31.8, "elapsed_time": "8:13:12", "remaining_time": "17:37:36", "throughput": 8337.1, "total_tokens": 246718736} {"current_steps": 242400, "total_steps": 761865, "loss": 1.9995, "lr": 7.703523385282314e-07, "epoch": 4.772499064794944, "percentage": 31.82, "elapsed_time": "8:13:25", "remaining_time": "17:37:23", "throughput": 8337.09, "total_tokens": 246820328} {"current_steps": 242500, "total_steps": 761865, "loss": 1.9152, "lr": 7.70178873949336e-07, "epoch": 4.774467917544447, "percentage": 31.83, "elapsed_time": "8:13:37", "remaining_time": "17:37:11", "throughput": 8337.07, "total_tokens": 246921128} {"current_steps": 242600, "total_steps": 761865, "loss": 2.0022, "lr": 7.700053634288018e-07, "epoch": 4.77643677029395, "percentage": 31.84, "elapsed_time": "8:13:49", "remaining_time": "17:36:59", "throughput": 8337.07, "total_tokens": 247022976} {"current_steps": 242700, "total_steps": 761865, "loss": 1.9786, "lr": 7.698318069961327e-07, "epoch": 4.778405623043453, "percentage": 31.86, "elapsed_time": "8:14:01", "remaining_time": "17:36:47", "throughput": 8337.08, "total_tokens": 247125376} {"current_steps": 242800, "total_steps": 761865, "loss": 2.0114, "lr": 7.696582046808409e-07, "epoch": 4.780374475792955, "percentage": 31.87, "elapsed_time": "8:14:13", "remaining_time": "17:36:35", "throughput": 8337.08, "total_tokens": 247227224} {"current_steps": 242900, "total_steps": 761865, "loss": 1.9674, "lr": 7.694845565124456e-07, "epoch": 4.782343328542458, "percentage": 31.88, "elapsed_time": "8:14:26", "remaining_time": "17:36:22", "throughput": 8337.08, "total_tokens": 247328480} {"current_steps": 243000, "total_steps": 761865, "loss": 1.9807, "lr": 7.693108625204745e-07, "epoch": 4.784312181291961, "percentage": 31.9, "elapsed_time": "8:14:38", "remaining_time": "17:36:10", "throughput": 8337.06, "total_tokens": 247430120} {"current_steps": 243100, "total_steps": 761865, "loss": 2.0155, "lr": 7.691371227344628e-07, "epoch": 4.786281034041464, "percentage": 31.91, "elapsed_time": "8:14:50", "remaining_time": "17:35:58", "throughput": 8337.04, "total_tokens": 247530976} {"current_steps": 243200, "total_steps": 761865, "loss": 1.9671, "lr": 7.689633371839533e-07, "epoch": 4.788249886790966, "percentage": 31.92, "elapsed_time": "8:15:02", "remaining_time": "17:35:45", "throughput": 8337.03, "total_tokens": 247631784} {"current_steps": 243300, "total_steps": 761865, "loss": 1.9918, "lr": 7.687895058984968e-07, "epoch": 4.79021873954047, "percentage": 31.93, "elapsed_time": "8:15:14", "remaining_time": "17:35:33", "throughput": 8337.01, "total_tokens": 247732560} {"current_steps": 243400, "total_steps": 761865, "loss": 2.0244, "lr": 7.686156289076519e-07, "epoch": 4.792187592289973, "percentage": 31.95, "elapsed_time": "8:15:27", "remaining_time": "17:35:21", "throughput": 8337.02, "total_tokens": 247834960} {"current_steps": 243500, "total_steps": 761865, "loss": 1.9407, "lr": 7.684417062409849e-07, "epoch": 4.794156445039476, "percentage": 31.96, "elapsed_time": "8:15:39", "remaining_time": "17:35:09", "throughput": 8337.01, "total_tokens": 247936560} {"current_steps": 243600, "total_steps": 761865, "loss": 1.9684, "lr": 7.682677379280699e-07, "epoch": 4.796125297788978, "percentage": 31.97, "elapsed_time": "8:15:51", "remaining_time": "17:34:57", "throughput": 8337.02, "total_tokens": 248038960} {"current_steps": 243700, "total_steps": 761865, "loss": 1.9862, "lr": 7.680937239984888e-07, "epoch": 4.798094150538481, "percentage": 31.99, "elapsed_time": "8:16:03", "remaining_time": "17:34:44", "throughput": 8337.01, "total_tokens": 248139920} {"current_steps": 243800, "total_steps": 761865, "loss": 2.0188, "lr": 7.679196644818313e-07, "epoch": 4.800063003287984, "percentage": 32.0, "elapsed_time": "8:16:15", "remaining_time": "17:34:32", "throughput": 8337.01, "total_tokens": 248242320} {"current_steps": 243900, "total_steps": 761865, "loss": 1.9799, "lr": 7.677455594076943e-07, "epoch": 4.802031856037487, "percentage": 32.01, "elapsed_time": "8:16:28", "remaining_time": "17:34:20", "throughput": 8337.02, "total_tokens": 248344720} {"current_steps": 244000, "total_steps": 761865, "loss": 1.9191, "lr": 7.675714088056833e-07, "epoch": 4.80400070878699, "percentage": 32.03, "elapsed_time": "8:16:40", "remaining_time": "17:34:08", "throughput": 8337.02, "total_tokens": 248446640} {"current_steps": 244100, "total_steps": 761865, "loss": 1.976, "lr": 7.673972127054112e-07, "epoch": 4.805969561536493, "percentage": 32.04, "elapsed_time": "8:16:52", "remaining_time": "17:33:55", "throughput": 8337.0, "total_tokens": 248546576} {"current_steps": 244200, "total_steps": 761865, "loss": 2.0169, "lr": 7.672229711364981e-07, "epoch": 4.807938414285996, "percentage": 32.05, "elapsed_time": "8:17:04", "remaining_time": "17:33:43", "throughput": 8337.01, "total_tokens": 248648840} {"current_steps": 244300, "total_steps": 761865, "loss": 2.0082, "lr": 7.670486841285728e-07, "epoch": 4.8099072670354985, "percentage": 32.07, "elapsed_time": "8:17:16", "remaining_time": "17:33:31", "throughput": 8337.01, "total_tokens": 248751240} {"current_steps": 244400, "total_steps": 761865, "loss": 2.003, "lr": 7.668743517112713e-07, "epoch": 4.811876119785001, "percentage": 32.08, "elapsed_time": "8:17:29", "remaining_time": "17:33:19", "throughput": 8336.99, "total_tokens": 248852264} {"current_steps": 244500, "total_steps": 761865, "loss": 1.9917, "lr": 7.66699973914237e-07, "epoch": 4.813844972534504, "percentage": 32.09, "elapsed_time": "8:17:41", "remaining_time": "17:33:07", "throughput": 8336.99, "total_tokens": 248954360} {"current_steps": 244600, "total_steps": 761865, "loss": 1.9517, "lr": 7.665255507671216e-07, "epoch": 4.815813825284007, "percentage": 32.11, "elapsed_time": "8:17:53", "remaining_time": "17:32:54", "throughput": 8337.0, "total_tokens": 249056760} {"current_steps": 244700, "total_steps": 761865, "loss": 1.9795, "lr": 7.663510822995842e-07, "epoch": 4.81778267803351, "percentage": 32.12, "elapsed_time": "8:18:05", "remaining_time": "17:32:42", "throughput": 8337.0, "total_tokens": 249159160} {"current_steps": 244800, "total_steps": 761865, "loss": 2.0136, "lr": 7.661765685412919e-07, "epoch": 4.819751530783012, "percentage": 32.13, "elapsed_time": "8:18:18", "remaining_time": "17:32:30", "throughput": 8337.0, "total_tokens": 249260792} {"current_steps": 244900, "total_steps": 761865, "loss": 1.9627, "lr": 7.660020095219192e-07, "epoch": 4.821720383532516, "percentage": 32.14, "elapsed_time": "8:18:30", "remaining_time": "17:32:18", "throughput": 8337.0, "total_tokens": 249362848} {"current_steps": 245000, "total_steps": 761865, "loss": 1.9917, "lr": 7.658274052711483e-07, "epoch": 4.823689236282019, "percentage": 32.16, "elapsed_time": "8:18:42", "remaining_time": "17:32:06", "throughput": 8337.0, "total_tokens": 249464624} {"current_steps": 245100, "total_steps": 761865, "loss": 2.0013, "lr": 7.656527558186692e-07, "epoch": 4.8256580890315215, "percentage": 32.17, "elapsed_time": "8:18:55", "remaining_time": "17:31:55", "throughput": 8336.85, "total_tokens": 249566456} {"current_steps": 245200, "total_steps": 761865, "loss": 2.0469, "lr": 7.654780611941796e-07, "epoch": 4.827626941781024, "percentage": 32.18, "elapsed_time": "8:19:07", "remaining_time": "17:31:42", "throughput": 8336.84, "total_tokens": 249667304} {"current_steps": 245300, "total_steps": 761865, "loss": 1.9682, "lr": 7.653033214273849e-07, "epoch": 4.829595794530527, "percentage": 32.2, "elapsed_time": "8:19:19", "remaining_time": "17:31:30", "throughput": 8336.85, "total_tokens": 249769704} {"current_steps": 245400, "total_steps": 761865, "loss": 1.945, "lr": 7.651285365479979e-07, "epoch": 4.83156464728003, "percentage": 32.21, "elapsed_time": "8:19:31", "remaining_time": "17:31:18", "throughput": 8336.86, "total_tokens": 249872104} {"current_steps": 245500, "total_steps": 761865, "loss": 1.9813, "lr": 7.649537065857397e-07, "epoch": 4.8335335000295325, "percentage": 32.22, "elapsed_time": "8:19:44", "remaining_time": "17:31:06", "throughput": 8336.86, "total_tokens": 249974504} {"current_steps": 245600, "total_steps": 761865, "loss": 1.9672, "lr": 7.647788315703381e-07, "epoch": 4.835502352779035, "percentage": 32.24, "elapsed_time": "8:19:56", "remaining_time": "17:30:54", "throughput": 8336.85, "total_tokens": 250076056} {"current_steps": 245700, "total_steps": 761865, "loss": 2.0243, "lr": 7.646039115315297e-07, "epoch": 4.837471205528539, "percentage": 32.25, "elapsed_time": "8:20:08", "remaining_time": "17:30:42", "throughput": 8336.85, "total_tokens": 250178000} {"current_steps": 245800, "total_steps": 761865, "loss": 1.9632, "lr": 7.644289464990578e-07, "epoch": 4.839440058278042, "percentage": 32.26, "elapsed_time": "8:20:20", "remaining_time": "17:30:29", "throughput": 8336.85, "total_tokens": 250279832} {"current_steps": 245900, "total_steps": 761865, "loss": 1.9973, "lr": 7.642539365026739e-07, "epoch": 4.8414089110275444, "percentage": 32.28, "elapsed_time": "8:20:33", "remaining_time": "17:30:17", "throughput": 8336.86, "total_tokens": 250382232} {"current_steps": 246000, "total_steps": 761865, "loss": 1.9749, "lr": 7.640788815721368e-07, "epoch": 4.843377763777047, "percentage": 32.29, "elapsed_time": "8:20:45", "remaining_time": "17:30:05", "throughput": 8336.87, "total_tokens": 250484632} {"current_steps": 246100, "total_steps": 761865, "loss": 2.0112, "lr": 7.639037817372135e-07, "epoch": 4.84534661652655, "percentage": 32.3, "elapsed_time": "8:20:57", "remaining_time": "17:29:53", "throughput": 8336.87, "total_tokens": 250586272} {"current_steps": 246200, "total_steps": 761865, "loss": 1.9555, "lr": 7.637286370276778e-07, "epoch": 4.847315469276053, "percentage": 32.32, "elapsed_time": "8:21:09", "remaining_time": "17:29:41", "throughput": 8336.87, "total_tokens": 250688672} {"current_steps": 246300, "total_steps": 761865, "loss": 2.0138, "lr": 7.635534474733118e-07, "epoch": 4.8492843220255555, "percentage": 32.33, "elapsed_time": "8:21:22", "remaining_time": "17:29:29", "throughput": 8336.87, "total_tokens": 250790488} {"current_steps": 246400, "total_steps": 761865, "loss": 1.9635, "lr": 7.633782131039048e-07, "epoch": 4.851253174775058, "percentage": 32.34, "elapsed_time": "8:21:34", "remaining_time": "17:29:16", "throughput": 8336.88, "total_tokens": 250892368} {"current_steps": 246500, "total_steps": 761865, "loss": 1.9928, "lr": 7.632029339492543e-07, "epoch": 4.853222027524561, "percentage": 32.35, "elapsed_time": "8:21:46", "remaining_time": "17:29:04", "throughput": 8336.87, "total_tokens": 250993536} {"current_steps": 246600, "total_steps": 761865, "loss": 2.0663, "lr": 7.630276100391647e-07, "epoch": 4.855190880274065, "percentage": 32.37, "elapsed_time": "8:21:58", "remaining_time": "17:28:51", "throughput": 8336.85, "total_tokens": 251093456} {"current_steps": 246700, "total_steps": 761865, "loss": 1.9865, "lr": 7.628522414034486e-07, "epoch": 4.857159733023567, "percentage": 32.38, "elapsed_time": "8:22:10", "remaining_time": "17:28:39", "throughput": 8336.84, "total_tokens": 251195032} {"current_steps": 246800, "total_steps": 761865, "loss": 1.9895, "lr": 7.626768280719258e-07, "epoch": 4.85912858577307, "percentage": 32.39, "elapsed_time": "8:22:22", "remaining_time": "17:28:27", "throughput": 8336.84, "total_tokens": 251297432} {"current_steps": 246900, "total_steps": 761865, "loss": 2.0129, "lr": 7.62501370074424e-07, "epoch": 4.861097438522573, "percentage": 32.41, "elapsed_time": "8:22:35", "remaining_time": "17:28:15", "throughput": 8336.84, "total_tokens": 251398832} {"current_steps": 247000, "total_steps": 761865, "loss": 1.9659, "lr": 7.623258674407782e-07, "epoch": 4.863066291272076, "percentage": 32.42, "elapsed_time": "8:22:47", "remaining_time": "17:28:03", "throughput": 8336.83, "total_tokens": 251501032} {"current_steps": 247100, "total_steps": 761865, "loss": 2.0045, "lr": 7.621503202008312e-07, "epoch": 4.865035144021578, "percentage": 32.43, "elapsed_time": "8:22:59", "remaining_time": "17:27:51", "throughput": 8336.83, "total_tokens": 251602816} {"current_steps": 247200, "total_steps": 761865, "loss": 1.9664, "lr": 7.619747283844332e-07, "epoch": 4.867003996771081, "percentage": 32.45, "elapsed_time": "8:23:11", "remaining_time": "17:27:38", "throughput": 8336.83, "total_tokens": 251705216} {"current_steps": 247300, "total_steps": 761865, "loss": 1.9633, "lr": 7.617990920214425e-07, "epoch": 4.868972849520585, "percentage": 32.46, "elapsed_time": "8:23:24", "remaining_time": "17:27:26", "throughput": 8336.84, "total_tokens": 251807616} {"current_steps": 247400, "total_steps": 761865, "loss": 1.9673, "lr": 7.61623411141724e-07, "epoch": 4.870941702270088, "percentage": 32.47, "elapsed_time": "8:23:36", "remaining_time": "17:27:14", "throughput": 8336.85, "total_tokens": 251910016} {"current_steps": 247500, "total_steps": 761865, "loss": 1.9885, "lr": 7.614476857751513e-07, "epoch": 4.87291055501959, "percentage": 32.49, "elapsed_time": "8:23:48", "remaining_time": "17:27:02", "throughput": 8336.85, "total_tokens": 252012416} {"current_steps": 247600, "total_steps": 761865, "loss": 1.9819, "lr": 7.612719159516046e-07, "epoch": 4.874879407769093, "percentage": 32.5, "elapsed_time": "8:24:00", "remaining_time": "17:26:50", "throughput": 8336.86, "total_tokens": 252114816} {"current_steps": 247700, "total_steps": 761865, "loss": 2.0085, "lr": 7.610961017009725e-07, "epoch": 4.876848260518596, "percentage": 32.51, "elapsed_time": "8:24:13", "remaining_time": "17:26:38", "throughput": 8336.85, "total_tokens": 252216488} {"current_steps": 247800, "total_steps": 761865, "loss": 1.997, "lr": 7.609202430531503e-07, "epoch": 4.878817113268099, "percentage": 32.53, "elapsed_time": "8:24:25", "remaining_time": "17:26:26", "throughput": 8336.85, "total_tokens": 252318344} {"current_steps": 247900, "total_steps": 761865, "loss": 2.068, "lr": 7.607443400380415e-07, "epoch": 4.880785966017601, "percentage": 32.54, "elapsed_time": "8:24:37", "remaining_time": "17:26:13", "throughput": 8336.85, "total_tokens": 252420184} {"current_steps": 248000, "total_steps": 761865, "loss": 2.034, "lr": 7.60568392685557e-07, "epoch": 4.882754818767104, "percentage": 32.55, "elapsed_time": "8:24:49", "remaining_time": "17:26:01", "throughput": 8336.84, "total_tokens": 252521064} {"current_steps": 248100, "total_steps": 761865, "loss": 1.9944, "lr": 7.603924010256149e-07, "epoch": 4.884723671516607, "percentage": 32.56, "elapsed_time": "8:25:02", "remaining_time": "17:25:49", "throughput": 8336.83, "total_tokens": 252622640} {"current_steps": 248200, "total_steps": 761865, "loss": 1.9715, "lr": 7.602163650881415e-07, "epoch": 4.88669252426611, "percentage": 32.58, "elapsed_time": "8:25:14", "remaining_time": "17:25:36", "throughput": 8336.81, "total_tokens": 252723392} {"current_steps": 248300, "total_steps": 761865, "loss": 2.0128, "lr": 7.600402849030698e-07, "epoch": 4.888661377015613, "percentage": 32.59, "elapsed_time": "8:25:26", "remaining_time": "17:25:24", "throughput": 8336.81, "total_tokens": 252825080} {"current_steps": 248400, "total_steps": 761865, "loss": 1.994, "lr": 7.598641605003408e-07, "epoch": 4.890630229765116, "percentage": 32.6, "elapsed_time": "8:25:38", "remaining_time": "17:25:12", "throughput": 8336.8, "total_tokens": 252926560} {"current_steps": 248500, "total_steps": 761865, "loss": 1.9687, "lr": 7.596879919099033e-07, "epoch": 4.892599082514619, "percentage": 32.62, "elapsed_time": "8:25:50", "remaining_time": "17:25:00", "throughput": 8336.8, "total_tokens": 253028960} {"current_steps": 248600, "total_steps": 761865, "loss": 2.0137, "lr": 7.595117791617131e-07, "epoch": 4.894567935264122, "percentage": 32.63, "elapsed_time": "8:26:03", "remaining_time": "17:24:48", "throughput": 8336.8, "total_tokens": 253130320} {"current_steps": 248700, "total_steps": 761865, "loss": 1.9851, "lr": 7.593355222857336e-07, "epoch": 4.896536788013624, "percentage": 32.64, "elapsed_time": "8:26:15", "remaining_time": "17:24:36", "throughput": 8336.8, "total_tokens": 253232720} {"current_steps": 248800, "total_steps": 761865, "loss": 1.9977, "lr": 7.591592213119359e-07, "epoch": 4.898505640763127, "percentage": 32.66, "elapsed_time": "8:26:27", "remaining_time": "17:24:23", "throughput": 8336.8, "total_tokens": 253334480} {"current_steps": 248900, "total_steps": 761865, "loss": 1.9797, "lr": 7.589828762702986e-07, "epoch": 4.90047449351263, "percentage": 32.67, "elapsed_time": "8:26:39", "remaining_time": "17:24:11", "throughput": 8336.8, "total_tokens": 253436360} {"current_steps": 249000, "total_steps": 761865, "loss": 2.0528, "lr": 7.588064871908073e-07, "epoch": 4.9024433462621335, "percentage": 32.68, "elapsed_time": "8:26:51", "remaining_time": "17:23:59", "throughput": 8336.77, "total_tokens": 253535936} {"current_steps": 249100, "total_steps": 761865, "loss": 1.9703, "lr": 7.586300541034559e-07, "epoch": 4.904412199011636, "percentage": 32.7, "elapsed_time": "8:27:03", "remaining_time": "17:23:46", "throughput": 8336.77, "total_tokens": 253637656} {"current_steps": 249200, "total_steps": 761865, "loss": 1.9691, "lr": 7.584535770382451e-07, "epoch": 4.906381051761139, "percentage": 32.71, "elapsed_time": "8:27:16", "remaining_time": "17:23:34", "throughput": 8336.77, "total_tokens": 253740056} {"current_steps": 249300, "total_steps": 761865, "loss": 1.9676, "lr": 7.582770560251835e-07, "epoch": 4.908349904510642, "percentage": 32.72, "elapsed_time": "8:27:28", "remaining_time": "17:23:22", "throughput": 8336.78, "total_tokens": 253842456} {"current_steps": 249400, "total_steps": 761865, "loss": 1.9926, "lr": 7.581004910942869e-07, "epoch": 4.9103187572601446, "percentage": 32.74, "elapsed_time": "8:27:40", "remaining_time": "17:23:10", "throughput": 8336.78, "total_tokens": 253944440} {"current_steps": 249500, "total_steps": 761865, "loss": 1.9619, "lr": 7.579238822755787e-07, "epoch": 4.912287610009647, "percentage": 32.75, "elapsed_time": "8:27:53", "remaining_time": "17:22:58", "throughput": 8336.78, "total_tokens": 254046840} {"current_steps": 249600, "total_steps": 761865, "loss": 1.9519, "lr": 7.577472295990896e-07, "epoch": 4.91425646275915, "percentage": 32.76, "elapsed_time": "8:28:05", "remaining_time": "17:22:46", "throughput": 8336.79, "total_tokens": 254148752} {"current_steps": 249700, "total_steps": 761865, "loss": 2.0006, "lr": 7.575705330948583e-07, "epoch": 4.916225315508653, "percentage": 32.77, "elapsed_time": "8:28:17", "remaining_time": "17:22:33", "throughput": 8336.79, "total_tokens": 254250520} {"current_steps": 249800, "total_steps": 761865, "loss": 1.9962, "lr": 7.573937927929302e-07, "epoch": 4.918194168258156, "percentage": 32.79, "elapsed_time": "8:28:29", "remaining_time": "17:22:21", "throughput": 8336.79, "total_tokens": 254352920} {"current_steps": 249900, "total_steps": 761865, "loss": 2.0098, "lr": 7.572170087233586e-07, "epoch": 4.920163021007658, "percentage": 32.8, "elapsed_time": "8:28:41", "remaining_time": "17:22:09", "throughput": 8336.79, "total_tokens": 254454720} {"current_steps": 250000, "total_steps": 761865, "loss": 1.9462, "lr": 7.570401809162042e-07, "epoch": 4.922131873757162, "percentage": 32.81, "elapsed_time": "8:28:54", "remaining_time": "17:21:57", "throughput": 8336.8, "total_tokens": 254557120} {"current_steps": 250100, "total_steps": 761865, "loss": 2.0181, "lr": 7.568633094015349e-07, "epoch": 4.924100726506665, "percentage": 32.83, "elapsed_time": "8:29:06", "remaining_time": "17:21:46", "throughput": 8336.64, "total_tokens": 254658400} {"current_steps": 250200, "total_steps": 761865, "loss": 1.9828, "lr": 7.566863942094263e-07, "epoch": 4.9260695792561675, "percentage": 32.84, "elapsed_time": "8:29:19", "remaining_time": "17:21:34", "throughput": 8336.65, "total_tokens": 254760800} {"current_steps": 250300, "total_steps": 761865, "loss": 1.9979, "lr": 7.565094353699614e-07, "epoch": 4.92803843200567, "percentage": 32.85, "elapsed_time": "8:29:31", "remaining_time": "17:21:21", "throughput": 8336.65, "total_tokens": 254862552} {"current_steps": 250400, "total_steps": 761865, "loss": 1.9988, "lr": 7.563324329132306e-07, "epoch": 4.930007284755173, "percentage": 32.87, "elapsed_time": "8:29:43", "remaining_time": "17:21:09", "throughput": 8336.63, "total_tokens": 254964096} {"current_steps": 250500, "total_steps": 761865, "loss": 1.984, "lr": 7.561553868693313e-07, "epoch": 4.931976137504676, "percentage": 32.88, "elapsed_time": "8:29:55", "remaining_time": "17:20:57", "throughput": 8336.64, "total_tokens": 255066496} {"current_steps": 250600, "total_steps": 761865, "loss": 1.9893, "lr": 7.559782972683694e-07, "epoch": 4.9339449902541785, "percentage": 32.89, "elapsed_time": "8:30:08", "remaining_time": "17:20:45", "throughput": 8336.65, "total_tokens": 255168896} {"current_steps": 250700, "total_steps": 761865, "loss": 2.0202, "lr": 7.558011641404568e-07, "epoch": 4.935913843003682, "percentage": 32.91, "elapsed_time": "8:30:20", "remaining_time": "17:20:33", "throughput": 8336.65, "total_tokens": 255271000} {"current_steps": 250800, "total_steps": 761865, "loss": 2.0018, "lr": 7.556239875157139e-07, "epoch": 4.937882695753185, "percentage": 32.92, "elapsed_time": "8:30:32", "remaining_time": "17:20:21", "throughput": 8336.63, "total_tokens": 255371784} {"current_steps": 250900, "total_steps": 761865, "loss": 1.9993, "lr": 7.554467674242678e-07, "epoch": 4.939851548502688, "percentage": 32.93, "elapsed_time": "8:30:44", "remaining_time": "17:20:08", "throughput": 8336.64, "total_tokens": 255474184} {"current_steps": 251000, "total_steps": 761865, "loss": 1.9614, "lr": 7.552695038962535e-07, "epoch": 4.9418204012521905, "percentage": 32.95, "elapsed_time": "8:30:57", "remaining_time": "17:19:56", "throughput": 8336.64, "total_tokens": 255576584} {"current_steps": 251100, "total_steps": 761865, "loss": 2.0229, "lr": 7.550921969618132e-07, "epoch": 4.943789254001693, "percentage": 32.96, "elapsed_time": "8:31:09", "remaining_time": "17:19:44", "throughput": 8336.64, "total_tokens": 255678280} {"current_steps": 251200, "total_steps": 761865, "loss": 1.9928, "lr": 7.549148466510964e-07, "epoch": 4.945758106751196, "percentage": 32.97, "elapsed_time": "8:31:21", "remaining_time": "17:19:32", "throughput": 8336.65, "total_tokens": 255780680} {"current_steps": 251300, "total_steps": 761865, "loss": 1.9626, "lr": 7.547374529942597e-07, "epoch": 4.947726959500699, "percentage": 32.98, "elapsed_time": "8:31:33", "remaining_time": "17:19:20", "throughput": 8336.65, "total_tokens": 255883080} {"current_steps": 251400, "total_steps": 761865, "loss": 1.9804, "lr": 7.545600160214679e-07, "epoch": 4.9496958122502015, "percentage": 33.0, "elapsed_time": "8:31:45", "remaining_time": "17:19:08", "throughput": 8336.64, "total_tokens": 255984064} {"current_steps": 251500, "total_steps": 761865, "loss": 1.9367, "lr": 7.543825357628924e-07, "epoch": 4.951664664999704, "percentage": 33.01, "elapsed_time": "8:31:58", "remaining_time": "17:18:55", "throughput": 8336.64, "total_tokens": 256086464} {"current_steps": 251600, "total_steps": 761865, "loss": 1.9902, "lr": 7.542050122487122e-07, "epoch": 4.953633517749208, "percentage": 33.02, "elapsed_time": "8:32:10", "remaining_time": "17:18:43", "throughput": 8336.63, "total_tokens": 256188104} {"current_steps": 251700, "total_steps": 761865, "loss": 1.9746, "lr": 7.540274455091136e-07, "epoch": 4.955602370498711, "percentage": 33.04, "elapsed_time": "8:32:22", "remaining_time": "17:18:31", "throughput": 8336.63, "total_tokens": 256289736} {"current_steps": 251800, "total_steps": 761865, "loss": 1.9361, "lr": 7.538498355742907e-07, "epoch": 4.957571223248213, "percentage": 33.05, "elapsed_time": "8:32:34", "remaining_time": "17:18:19", "throughput": 8336.63, "total_tokens": 256392136} {"current_steps": 251900, "total_steps": 761865, "loss": 2.0139, "lr": 7.536721824744443e-07, "epoch": 4.959540075997716, "percentage": 33.06, "elapsed_time": "8:32:47", "remaining_time": "17:18:07", "throughput": 8336.63, "total_tokens": 256494176} {"current_steps": 252000, "total_steps": 761865, "loss": 2.0195, "lr": 7.534944862397827e-07, "epoch": 4.961508928747219, "percentage": 33.08, "elapsed_time": "8:32:59", "remaining_time": "17:17:55", "throughput": 8336.63, "total_tokens": 256596032} {"current_steps": 252100, "total_steps": 761865, "loss": 2.0266, "lr": 7.533167469005219e-07, "epoch": 4.963477781496722, "percentage": 33.09, "elapsed_time": "8:33:11", "remaining_time": "17:17:42", "throughput": 8336.59, "total_tokens": 256694728} {"current_steps": 252200, "total_steps": 761865, "loss": 1.9878, "lr": 7.531389644868848e-07, "epoch": 4.9654466342462245, "percentage": 33.1, "elapsed_time": "8:33:23", "remaining_time": "17:17:30", "throughput": 8336.59, "total_tokens": 256796448} {"current_steps": 252300, "total_steps": 761865, "loss": 1.9393, "lr": 7.529611390291019e-07, "epoch": 4.967415486995727, "percentage": 33.12, "elapsed_time": "8:33:35", "remaining_time": "17:17:17", "throughput": 8336.57, "total_tokens": 256896400} {"current_steps": 252400, "total_steps": 761865, "loss": 1.979, "lr": 7.52783270557411e-07, "epoch": 4.969384339745231, "percentage": 33.13, "elapsed_time": "8:33:47", "remaining_time": "17:17:05", "throughput": 8336.58, "total_tokens": 256998800} {"current_steps": 252500, "total_steps": 761865, "loss": 2.0132, "lr": 7.526053591020568e-07, "epoch": 4.971353192494734, "percentage": 33.14, "elapsed_time": "8:34:00", "remaining_time": "17:16:53", "throughput": 8336.57, "total_tokens": 257100432} {"current_steps": 252600, "total_steps": 761865, "loss": 1.9673, "lr": 7.524274046932919e-07, "epoch": 4.973322045244236, "percentage": 33.16, "elapsed_time": "8:34:12", "remaining_time": "17:16:41", "throughput": 8336.57, "total_tokens": 257202832} {"current_steps": 252700, "total_steps": 761865, "loss": 2.0336, "lr": 7.52249407361376e-07, "epoch": 4.975290897993739, "percentage": 33.17, "elapsed_time": "8:34:24", "remaining_time": "17:16:28", "throughput": 8336.57, "total_tokens": 257304424} {"current_steps": 252800, "total_steps": 761865, "loss": 2.0102, "lr": 7.520713671365759e-07, "epoch": 4.977259750743242, "percentage": 33.18, "elapsed_time": "8:34:36", "remaining_time": "17:16:16", "throughput": 8336.55, "total_tokens": 257405552} {"current_steps": 252900, "total_steps": 761865, "loss": 1.9739, "lr": 7.518932840491659e-07, "epoch": 4.979228603492745, "percentage": 33.19, "elapsed_time": "8:34:48", "remaining_time": "17:16:04", "throughput": 8336.55, "total_tokens": 257507224} {"current_steps": 253000, "total_steps": 761865, "loss": 1.9371, "lr": 7.517151581294275e-07, "epoch": 4.981197456242247, "percentage": 33.21, "elapsed_time": "8:35:01", "remaining_time": "17:15:52", "throughput": 8336.55, "total_tokens": 257609624} {"current_steps": 253100, "total_steps": 761865, "loss": 1.9715, "lr": 7.515369894076494e-07, "epoch": 4.98316630899175, "percentage": 33.22, "elapsed_time": "8:35:13", "remaining_time": "17:15:39", "throughput": 8336.53, "total_tokens": 257709776} {"current_steps": 253200, "total_steps": 761865, "loss": 1.9851, "lr": 7.513587779141279e-07, "epoch": 4.985135161741253, "percentage": 33.23, "elapsed_time": "8:35:25", "remaining_time": "17:15:27", "throughput": 8336.53, "total_tokens": 257811656} {"current_steps": 253300, "total_steps": 761865, "loss": 1.9891, "lr": 7.511805236791664e-07, "epoch": 4.987104014490757, "percentage": 33.25, "elapsed_time": "8:35:37", "remaining_time": "17:15:15", "throughput": 8336.52, "total_tokens": 257912328} {"current_steps": 253400, "total_steps": 761865, "loss": 1.9633, "lr": 7.510022267330754e-07, "epoch": 4.989072867240259, "percentage": 33.26, "elapsed_time": "8:35:49", "remaining_time": "17:15:03", "throughput": 8336.52, "total_tokens": 258014728} {"current_steps": 253500, "total_steps": 761865, "loss": 1.9748, "lr": 7.508238871061725e-07, "epoch": 4.991041719989762, "percentage": 33.27, "elapsed_time": "8:36:02", "remaining_time": "17:14:50", "throughput": 8336.51, "total_tokens": 258115848} {"current_steps": 253600, "total_steps": 761865, "loss": 2.0179, "lr": 7.506455048287834e-07, "epoch": 4.993010572739265, "percentage": 33.29, "elapsed_time": "8:36:14", "remaining_time": "17:14:38", "throughput": 8336.52, "total_tokens": 258217816} {"current_steps": 253700, "total_steps": 761865, "loss": 1.9841, "lr": 7.504670799312403e-07, "epoch": 4.994979425488768, "percentage": 33.3, "elapsed_time": "8:36:26", "remaining_time": "17:14:26", "throughput": 8336.52, "total_tokens": 258319440} {"current_steps": 253800, "total_steps": 761865, "loss": 2.0438, "lr": 7.502886124438826e-07, "epoch": 4.99694827823827, "percentage": 33.31, "elapsed_time": "8:36:38", "remaining_time": "17:14:14", "throughput": 8336.52, "total_tokens": 258421840} {"current_steps": 253900, "total_steps": 761865, "loss": 1.9882, "lr": 7.501101023970575e-07, "epoch": 4.998917130987773, "percentage": 33.33, "elapsed_time": "8:36:51", "remaining_time": "17:14:02", "throughput": 8336.53, "total_tokens": 258524240} {"current_steps": 254000, "total_steps": 761865, "loss": 1.9443, "lr": 7.499315498211189e-07, "epoch": 5.000885983737276, "percentage": 33.34, "elapsed_time": "8:37:03", "remaining_time": "17:13:50", "throughput": 8336.54, "total_tokens": 258626640} {"current_steps": 254100, "total_steps": 761865, "loss": 1.9898, "lr": 7.497529547464284e-07, "epoch": 5.0028548364867795, "percentage": 33.35, "elapsed_time": "8:37:15", "remaining_time": "17:13:37", "throughput": 8336.54, "total_tokens": 258728416} {"current_steps": 254200, "total_steps": 761865, "loss": 2.0092, "lr": 7.495743172033544e-07, "epoch": 5.004823689236282, "percentage": 33.37, "elapsed_time": "8:37:27", "remaining_time": "17:13:25", "throughput": 8336.54, "total_tokens": 258830384} {"current_steps": 254300, "total_steps": 761865, "loss": 2.0209, "lr": 7.493956372222728e-07, "epoch": 5.006792541985785, "percentage": 33.38, "elapsed_time": "8:37:39", "remaining_time": "17:13:13", "throughput": 8336.53, "total_tokens": 258931456} {"current_steps": 254400, "total_steps": 761865, "loss": 1.9968, "lr": 7.492169148335665e-07, "epoch": 5.008761394735288, "percentage": 33.39, "elapsed_time": "8:37:52", "remaining_time": "17:13:01", "throughput": 8336.51, "total_tokens": 259032920} {"current_steps": 254500, "total_steps": 761865, "loss": 2.0187, "lr": 7.49038150067626e-07, "epoch": 5.010730247484791, "percentage": 33.4, "elapsed_time": "8:38:04", "remaining_time": "17:12:48", "throughput": 8336.49, "total_tokens": 259133080} {"current_steps": 254600, "total_steps": 761865, "loss": 1.9514, "lr": 7.488593429548484e-07, "epoch": 5.012699100234293, "percentage": 33.42, "elapsed_time": "8:38:16", "remaining_time": "17:12:36", "throughput": 8336.5, "total_tokens": 259235480} {"current_steps": 254700, "total_steps": 761865, "loss": 1.9713, "lr": 7.486804935256386e-07, "epoch": 5.014667952983796, "percentage": 33.43, "elapsed_time": "8:38:28", "remaining_time": "17:12:24", "throughput": 8336.51, "total_tokens": 259337880} {"current_steps": 254800, "total_steps": 761865, "loss": 2.0099, "lr": 7.485016018104082e-07, "epoch": 5.016636805733299, "percentage": 33.44, "elapsed_time": "8:38:40", "remaining_time": "17:12:12", "throughput": 8336.51, "total_tokens": 259440280} {"current_steps": 254900, "total_steps": 761865, "loss": 1.986, "lr": 7.483226678395767e-07, "epoch": 5.0186056584828025, "percentage": 33.46, "elapsed_time": "8:38:53", "remaining_time": "17:12:00", "throughput": 8336.51, "total_tokens": 259542000} {"current_steps": 255000, "total_steps": 761865, "loss": 1.9969, "lr": 7.481436916435696e-07, "epoch": 5.020574511232305, "percentage": 33.47, "elapsed_time": "8:39:05", "remaining_time": "17:11:47", "throughput": 8336.5, "total_tokens": 259642976} {"current_steps": 255100, "total_steps": 761865, "loss": 1.9783, "lr": 7.47964673252821e-07, "epoch": 5.022543363981808, "percentage": 33.48, "elapsed_time": "8:39:18", "remaining_time": "17:11:37", "throughput": 8336.24, "total_tokens": 259743568} {"current_steps": 255200, "total_steps": 761865, "loss": 1.9714, "lr": 7.477856126977709e-07, "epoch": 5.024512216731311, "percentage": 33.5, "elapsed_time": "8:39:30", "remaining_time": "17:11:25", "throughput": 8336.25, "total_tokens": 259845968} {"current_steps": 255300, "total_steps": 761865, "loss": 1.9458, "lr": 7.476065100088674e-07, "epoch": 5.0264810694808135, "percentage": 33.51, "elapsed_time": "8:39:42", "remaining_time": "17:11:12", "throughput": 8336.24, "total_tokens": 259947256} {"current_steps": 255400, "total_steps": 761865, "loss": 1.9767, "lr": 7.474273652165652e-07, "epoch": 5.028449922230316, "percentage": 33.52, "elapsed_time": "8:39:55", "remaining_time": "17:11:00", "throughput": 8336.25, "total_tokens": 260049344} {"current_steps": 255500, "total_steps": 761865, "loss": 1.9445, "lr": 7.472481783513266e-07, "epoch": 5.030418774979819, "percentage": 33.54, "elapsed_time": "8:40:07", "remaining_time": "17:10:48", "throughput": 8336.22, "total_tokens": 260151744} {"current_steps": 255600, "total_steps": 761865, "loss": 1.9259, "lr": 7.470689494436204e-07, "epoch": 5.032387627729322, "percentage": 33.55, "elapsed_time": "8:40:19", "remaining_time": "17:10:36", "throughput": 8336.18, "total_tokens": 260252792} {"current_steps": 255700, "total_steps": 761865, "loss": 2.0109, "lr": 7.468896785239234e-07, "epoch": 5.034356480478825, "percentage": 33.56, "elapsed_time": "8:40:31", "remaining_time": "17:10:24", "throughput": 8336.16, "total_tokens": 260354624} {"current_steps": 255800, "total_steps": 761865, "loss": 1.9802, "lr": 7.467103656227189e-07, "epoch": 5.036325333228328, "percentage": 33.58, "elapsed_time": "8:40:44", "remaining_time": "17:10:12", "throughput": 8336.1, "total_tokens": 260455456} {"current_steps": 255900, "total_steps": 761865, "loss": 1.9659, "lr": 7.465310107704976e-07, "epoch": 5.038294185977831, "percentage": 33.59, "elapsed_time": "8:40:56", "remaining_time": "17:10:00", "throughput": 8336.08, "total_tokens": 260557856} {"current_steps": 256000, "total_steps": 761865, "loss": 1.9694, "lr": 7.463516139977573e-07, "epoch": 5.040263038727334, "percentage": 33.6, "elapsed_time": "8:41:08", "remaining_time": "17:09:48", "throughput": 8336.07, "total_tokens": 260660256} {"current_steps": 256100, "total_steps": 761865, "loss": 2.0493, "lr": 7.461721753350027e-07, "epoch": 5.0422318914768365, "percentage": 33.61, "elapsed_time": "8:41:21", "remaining_time": "17:09:36", "throughput": 8336.04, "total_tokens": 260762656} {"current_steps": 256200, "total_steps": 761865, "loss": 1.9538, "lr": 7.459926948127462e-07, "epoch": 5.044200744226339, "percentage": 33.63, "elapsed_time": "8:41:33", "remaining_time": "17:09:24", "throughput": 8336.01, "total_tokens": 260864416} {"current_steps": 256300, "total_steps": 761865, "loss": 1.9323, "lr": 7.458131724615067e-07, "epoch": 5.046169596975842, "percentage": 33.64, "elapsed_time": "8:41:46", "remaining_time": "17:09:12", "throughput": 8335.98, "total_tokens": 260966816} {"current_steps": 256400, "total_steps": 761865, "loss": 1.9893, "lr": 7.456336083118105e-07, "epoch": 5.048138449725345, "percentage": 33.65, "elapsed_time": "8:41:58", "remaining_time": "17:09:00", "throughput": 8335.94, "total_tokens": 261067816} {"current_steps": 256500, "total_steps": 761865, "loss": 1.9601, "lr": 7.454540023941908e-07, "epoch": 5.0501073024748475, "percentage": 33.67, "elapsed_time": "8:42:10", "remaining_time": "17:08:48", "throughput": 8335.91, "total_tokens": 261170216} {"current_steps": 256600, "total_steps": 761865, "loss": 2.0006, "lr": 7.452743547391884e-07, "epoch": 5.052076155224351, "percentage": 33.68, "elapsed_time": "8:42:23", "remaining_time": "17:08:36", "throughput": 8335.86, "total_tokens": 261271224} {"current_steps": 256700, "total_steps": 761865, "loss": 2.0365, "lr": 7.450946653773506e-07, "epoch": 5.054045007973854, "percentage": 33.69, "elapsed_time": "8:42:35", "remaining_time": "17:08:24", "throughput": 8335.82, "total_tokens": 261372472} {"current_steps": 256800, "total_steps": 761865, "loss": 1.9775, "lr": 7.449149343392325e-07, "epoch": 5.056013860723357, "percentage": 33.71, "elapsed_time": "8:42:47", "remaining_time": "17:08:12", "throughput": 8335.76, "total_tokens": 261472112} {"current_steps": 256900, "total_steps": 761865, "loss": 1.9589, "lr": 7.447351616553951e-07, "epoch": 5.057982713472859, "percentage": 33.72, "elapsed_time": "8:42:59", "remaining_time": "17:08:00", "throughput": 8335.73, "total_tokens": 261574512} {"current_steps": 257000, "total_steps": 761865, "loss": 1.954, "lr": 7.445553473564079e-07, "epoch": 5.059951566222362, "percentage": 33.73, "elapsed_time": "8:43:12", "remaining_time": "17:07:48", "throughput": 8335.7, "total_tokens": 261676912} {"current_steps": 257100, "total_steps": 761865, "loss": 2.0053, "lr": 7.443754914728465e-07, "epoch": 5.061920418971865, "percentage": 33.75, "elapsed_time": "8:43:24", "remaining_time": "17:07:36", "throughput": 8335.65, "total_tokens": 261778688} {"current_steps": 257200, "total_steps": 761865, "loss": 1.9565, "lr": 7.44195594035294e-07, "epoch": 5.063889271721368, "percentage": 33.76, "elapsed_time": "8:43:37", "remaining_time": "17:07:25", "throughput": 8335.63, "total_tokens": 261881088} {"current_steps": 257300, "total_steps": 761865, "loss": 1.97, "lr": 7.440156550743403e-07, "epoch": 5.0658581244708705, "percentage": 33.77, "elapsed_time": "8:43:49", "remaining_time": "17:07:13", "throughput": 8335.61, "total_tokens": 261983488} {"current_steps": 257400, "total_steps": 761865, "loss": 1.9726, "lr": 7.438356746205825e-07, "epoch": 5.067826977220374, "percentage": 33.79, "elapsed_time": "8:44:01", "remaining_time": "17:07:01", "throughput": 8335.57, "total_tokens": 262085384} {"current_steps": 257500, "total_steps": 761865, "loss": 2.0127, "lr": 7.43655652704625e-07, "epoch": 5.069795829969877, "percentage": 33.8, "elapsed_time": "8:44:14", "remaining_time": "17:06:49", "throughput": 8335.53, "total_tokens": 262187104} {"current_steps": 257600, "total_steps": 761865, "loss": 1.9911, "lr": 7.434755893570787e-07, "epoch": 5.07176468271938, "percentage": 33.81, "elapsed_time": "8:44:26", "remaining_time": "17:06:37", "throughput": 8335.51, "total_tokens": 262289400} {"current_steps": 257700, "total_steps": 761865, "loss": 1.9775, "lr": 7.43295484608562e-07, "epoch": 5.073733535468882, "percentage": 33.82, "elapsed_time": "8:44:38", "remaining_time": "17:06:25", "throughput": 8335.48, "total_tokens": 262391800} {"current_steps": 257800, "total_steps": 761865, "loss": 1.9711, "lr": 7.431153384897004e-07, "epoch": 5.075702388218385, "percentage": 33.84, "elapsed_time": "8:44:51", "remaining_time": "17:06:13", "throughput": 8335.45, "total_tokens": 262493344} {"current_steps": 257900, "total_steps": 761865, "loss": 1.9974, "lr": 7.42935151031126e-07, "epoch": 5.077671240967888, "percentage": 33.85, "elapsed_time": "8:45:03", "remaining_time": "17:06:01", "throughput": 8335.41, "total_tokens": 262594912} {"current_steps": 258000, "total_steps": 761865, "loss": 1.9706, "lr": 7.427549222634779e-07, "epoch": 5.079640093717391, "percentage": 33.86, "elapsed_time": "8:45:15", "remaining_time": "17:05:49", "throughput": 8335.37, "total_tokens": 262697048} {"current_steps": 258100, "total_steps": 761865, "loss": 1.9856, "lr": 7.42574652217403e-07, "epoch": 5.081608946466893, "percentage": 33.88, "elapsed_time": "8:45:28", "remaining_time": "17:05:37", "throughput": 8335.35, "total_tokens": 262799448} {"current_steps": 258200, "total_steps": 761865, "loss": 2.0093, "lr": 7.423943409235543e-07, "epoch": 5.083577799216396, "percentage": 33.89, "elapsed_time": "8:45:40", "remaining_time": "17:05:25", "throughput": 8335.32, "total_tokens": 262901072} {"current_steps": 258300, "total_steps": 761865, "loss": 2.0036, "lr": 7.422139884125924e-07, "epoch": 5.0855466519659, "percentage": 33.9, "elapsed_time": "8:45:52", "remaining_time": "17:05:13", "throughput": 8335.29, "total_tokens": 263003472} {"current_steps": 258400, "total_steps": 761865, "loss": 2.0192, "lr": 7.420335947151849e-07, "epoch": 5.087515504715403, "percentage": 33.92, "elapsed_time": "8:46:05", "remaining_time": "17:05:01", "throughput": 8335.26, "total_tokens": 263105160} {"current_steps": 258500, "total_steps": 761865, "loss": 1.9804, "lr": 7.418531598620058e-07, "epoch": 5.089484357464905, "percentage": 33.93, "elapsed_time": "8:46:17", "remaining_time": "17:04:49", "throughput": 8335.2, "total_tokens": 263205152} {"current_steps": 258600, "total_steps": 761865, "loss": 1.9799, "lr": 7.416726838837368e-07, "epoch": 5.091453210214408, "percentage": 33.94, "elapsed_time": "8:46:29", "remaining_time": "17:04:37", "throughput": 8335.16, "total_tokens": 263306312} {"current_steps": 258700, "total_steps": 761865, "loss": 1.9747, "lr": 7.414921668110663e-07, "epoch": 5.093422062963911, "percentage": 33.96, "elapsed_time": "8:46:42", "remaining_time": "17:04:25", "throughput": 8335.14, "total_tokens": 263408096} {"current_steps": 258800, "total_steps": 761865, "loss": 2.0072, "lr": 7.413116086746897e-07, "epoch": 5.095390915713414, "percentage": 33.97, "elapsed_time": "8:46:54", "remaining_time": "17:04:13", "throughput": 8335.11, "total_tokens": 263509784} {"current_steps": 258900, "total_steps": 761865, "loss": 1.9938, "lr": 7.411310095053093e-07, "epoch": 5.097359768462916, "percentage": 33.98, "elapsed_time": "8:47:06", "remaining_time": "17:04:01", "throughput": 8335.07, "total_tokens": 263611888} {"current_steps": 259000, "total_steps": 761865, "loss": 1.9905, "lr": 7.409503693336346e-07, "epoch": 5.099328621212419, "percentage": 34.0, "elapsed_time": "8:47:19", "remaining_time": "17:03:49", "throughput": 8335.03, "total_tokens": 263713360} {"current_steps": 259100, "total_steps": 761865, "loss": 2.0082, "lr": 7.407696881903818e-07, "epoch": 5.101297473961923, "percentage": 34.01, "elapsed_time": "8:47:31", "remaining_time": "17:03:37", "throughput": 8334.98, "total_tokens": 263814176} {"current_steps": 259200, "total_steps": 761865, "loss": 1.999, "lr": 7.405889661062743e-07, "epoch": 5.1032663267114255, "percentage": 34.02, "elapsed_time": "8:47:43", "remaining_time": "17:03:25", "throughput": 8334.94, "total_tokens": 263915088} {"current_steps": 259300, "total_steps": 761865, "loss": 1.9333, "lr": 7.404082031120422e-07, "epoch": 5.105235179460928, "percentage": 34.03, "elapsed_time": "8:47:55", "remaining_time": "17:03:12", "throughput": 8334.94, "total_tokens": 264016672} {"current_steps": 259400, "total_steps": 761865, "loss": 1.994, "lr": 7.40227399238423e-07, "epoch": 5.107204032210431, "percentage": 34.05, "elapsed_time": "8:48:08", "remaining_time": "17:03:00", "throughput": 8334.94, "total_tokens": 264118272} {"current_steps": 259500, "total_steps": 761865, "loss": 1.9545, "lr": 7.400465545161607e-07, "epoch": 5.109172884959934, "percentage": 34.06, "elapsed_time": "8:48:20", "remaining_time": "17:02:48", "throughput": 8334.95, "total_tokens": 264220672} {"current_steps": 259600, "total_steps": 761865, "loss": 1.964, "lr": 7.398656689760065e-07, "epoch": 5.111141737709437, "percentage": 34.07, "elapsed_time": "8:48:32", "remaining_time": "17:02:36", "throughput": 8334.95, "total_tokens": 264323072} {"current_steps": 259700, "total_steps": 761865, "loss": 1.9751, "lr": 7.396847426487183e-07, "epoch": 5.113110590458939, "percentage": 34.09, "elapsed_time": "8:48:44", "remaining_time": "17:02:24", "throughput": 8334.94, "total_tokens": 264424128} {"current_steps": 259800, "total_steps": 761865, "loss": 2.0092, "lr": 7.395037755650613e-07, "epoch": 5.115079443208442, "percentage": 34.1, "elapsed_time": "8:48:57", "remaining_time": "17:02:11", "throughput": 8334.93, "total_tokens": 264525896} {"current_steps": 259900, "total_steps": 761865, "loss": 1.9909, "lr": 7.393227677558072e-07, "epoch": 5.117048295957945, "percentage": 34.11, "elapsed_time": "8:49:09", "remaining_time": "17:01:59", "throughput": 8334.94, "total_tokens": 264628296} {"current_steps": 260000, "total_steps": 761865, "loss": 1.9974, "lr": 7.391417192517352e-07, "epoch": 5.1190171487074485, "percentage": 34.13, "elapsed_time": "8:49:21", "remaining_time": "17:01:47", "throughput": 8334.91, "total_tokens": 264728216} {"current_steps": 260100, "total_steps": 761865, "loss": 1.9967, "lr": 7.389606300836306e-07, "epoch": 5.120986001456951, "percentage": 34.14, "elapsed_time": "8:49:34", "remaining_time": "17:01:36", "throughput": 8334.77, "total_tokens": 264830616} {"current_steps": 260200, "total_steps": 761865, "loss": 1.9633, "lr": 7.387795002822866e-07, "epoch": 5.122954854206454, "percentage": 34.15, "elapsed_time": "8:49:46", "remaining_time": "17:01:24", "throughput": 8334.77, "total_tokens": 264932528} {"current_steps": 260300, "total_steps": 761865, "loss": 1.9677, "lr": 7.385983298785023e-07, "epoch": 5.124923706955957, "percentage": 34.17, "elapsed_time": "8:49:58", "remaining_time": "17:01:11", "throughput": 8334.77, "total_tokens": 265034360} {"current_steps": 260400, "total_steps": 761865, "loss": 1.9643, "lr": 7.384171189030848e-07, "epoch": 5.1268925597054595, "percentage": 34.18, "elapsed_time": "8:50:10", "remaining_time": "17:00:59", "throughput": 8334.77, "total_tokens": 265136048} {"current_steps": 260500, "total_steps": 761865, "loss": 1.9801, "lr": 7.382358673868467e-07, "epoch": 5.128861412454962, "percentage": 34.19, "elapsed_time": "8:50:23", "remaining_time": "17:00:47", "throughput": 8334.77, "total_tokens": 265237584} {"current_steps": 260600, "total_steps": 761865, "loss": 2.0165, "lr": 7.380545753606091e-07, "epoch": 5.130830265204465, "percentage": 34.21, "elapsed_time": "8:50:35", "remaining_time": "17:00:35", "throughput": 8334.77, "total_tokens": 265339432} {"current_steps": 260700, "total_steps": 761865, "loss": 1.9829, "lr": 7.378732428551985e-07, "epoch": 5.132799117953968, "percentage": 34.22, "elapsed_time": "8:50:47", "remaining_time": "17:00:22", "throughput": 8334.76, "total_tokens": 265440536} {"current_steps": 260800, "total_steps": 761865, "loss": 1.9595, "lr": 7.376918699014494e-07, "epoch": 5.1347679707034715, "percentage": 34.23, "elapsed_time": "8:50:59", "remaining_time": "17:00:10", "throughput": 8334.76, "total_tokens": 265542360} {"current_steps": 260900, "total_steps": 761865, "loss": 1.9618, "lr": 7.375104565302027e-07, "epoch": 5.136736823452974, "percentage": 34.24, "elapsed_time": "8:51:11", "remaining_time": "16:59:58", "throughput": 8334.76, "total_tokens": 265644760} {"current_steps": 261000, "total_steps": 761865, "loss": 2.0161, "lr": 7.373290027723059e-07, "epoch": 5.138705676202477, "percentage": 34.26, "elapsed_time": "8:51:24", "remaining_time": "16:59:46", "throughput": 8334.77, "total_tokens": 265747160} {"current_steps": 261100, "total_steps": 761865, "loss": 2.0163, "lr": 7.37147508658614e-07, "epoch": 5.14067452895198, "percentage": 34.27, "elapsed_time": "8:51:36", "remaining_time": "16:59:33", "throughput": 8334.74, "total_tokens": 265846320} {"current_steps": 261200, "total_steps": 761865, "loss": 1.9463, "lr": 7.369659742199886e-07, "epoch": 5.1426433817014825, "percentage": 34.28, "elapsed_time": "8:51:48", "remaining_time": "16:59:21", "throughput": 8334.75, "total_tokens": 265948720} {"current_steps": 261300, "total_steps": 761865, "loss": 2.0115, "lr": 7.367843994872978e-07, "epoch": 5.144612234450985, "percentage": 34.3, "elapsed_time": "8:52:00", "remaining_time": "16:59:09", "throughput": 8334.74, "total_tokens": 266049864} {"current_steps": 261400, "total_steps": 761865, "loss": 1.9823, "lr": 7.36602784491417e-07, "epoch": 5.146581087200488, "percentage": 34.31, "elapsed_time": "8:52:12", "remaining_time": "16:58:57", "throughput": 8334.75, "total_tokens": 266152264} {"current_steps": 261500, "total_steps": 761865, "loss": 1.9628, "lr": 7.364211292632283e-07, "epoch": 5.148549939949991, "percentage": 34.32, "elapsed_time": "8:52:25", "remaining_time": "16:58:45", "throughput": 8334.76, "total_tokens": 266254664} {"current_steps": 261600, "total_steps": 761865, "loss": 1.9456, "lr": 7.362394338336206e-07, "epoch": 5.150518792699494, "percentage": 34.34, "elapsed_time": "8:52:37", "remaining_time": "16:58:32", "throughput": 8334.74, "total_tokens": 266355376} {"current_steps": 261700, "total_steps": 761865, "loss": 1.9937, "lr": 7.360576982334898e-07, "epoch": 5.152487645448997, "percentage": 34.35, "elapsed_time": "8:52:49", "remaining_time": "16:58:20", "throughput": 8334.74, "total_tokens": 266457776} {"current_steps": 261800, "total_steps": 761865, "loss": 1.9522, "lr": 7.358759224937383e-07, "epoch": 5.1544564981985, "percentage": 34.36, "elapsed_time": "8:53:01", "remaining_time": "16:58:08", "throughput": 8334.75, "total_tokens": 266560176} {"current_steps": 261900, "total_steps": 761865, "loss": 1.9974, "lr": 7.356941066452757e-07, "epoch": 5.156425350948003, "percentage": 34.38, "elapsed_time": "8:53:14", "remaining_time": "16:57:56", "throughput": 8334.74, "total_tokens": 266661616} {"current_steps": 262000, "total_steps": 761865, "loss": 2.0107, "lr": 7.355122507190184e-07, "epoch": 5.1583942036975055, "percentage": 34.39, "elapsed_time": "8:53:26", "remaining_time": "16:57:43", "throughput": 8334.72, "total_tokens": 266762344} {"current_steps": 262100, "total_steps": 761865, "loss": 1.9975, "lr": 7.353303547458891e-07, "epoch": 5.160363056447008, "percentage": 34.4, "elapsed_time": "8:53:38", "remaining_time": "16:57:31", "throughput": 8334.73, "total_tokens": 266864744} {"current_steps": 262200, "total_steps": 761865, "loss": 1.9982, "lr": 7.351484187568177e-07, "epoch": 5.162331909196511, "percentage": 34.42, "elapsed_time": "8:53:50", "remaining_time": "16:57:19", "throughput": 8334.73, "total_tokens": 266966320} {"current_steps": 262300, "total_steps": 761865, "loss": 1.9637, "lr": 7.349664427827413e-07, "epoch": 5.164300761946014, "percentage": 34.43, "elapsed_time": "8:54:02", "remaining_time": "16:57:07", "throughput": 8334.73, "total_tokens": 267068720} {"current_steps": 262400, "total_steps": 761865, "loss": 2.0391, "lr": 7.347844268546029e-07, "epoch": 5.166269614695517, "percentage": 34.44, "elapsed_time": "8:54:15", "remaining_time": "16:56:55", "throughput": 8334.74, "total_tokens": 267170592} {"current_steps": 262500, "total_steps": 761865, "loss": 2.0162, "lr": 7.346023710033531e-07, "epoch": 5.16823846744502, "percentage": 34.45, "elapsed_time": "8:54:27", "remaining_time": "16:56:43", "throughput": 8334.73, "total_tokens": 267272944} {"current_steps": 262600, "total_steps": 761865, "loss": 2.0217, "lr": 7.344202752599488e-07, "epoch": 5.170207320194523, "percentage": 34.47, "elapsed_time": "8:54:39", "remaining_time": "16:56:30", "throughput": 8334.83, "total_tokens": 267375344} {"current_steps": 262700, "total_steps": 761865, "loss": 1.9593, "lr": 7.342381396553539e-07, "epoch": 5.172176172944026, "percentage": 34.48, "elapsed_time": "8:54:51", "remaining_time": "16:56:17", "throughput": 8334.97, "total_tokens": 267477744} {"current_steps": 262800, "total_steps": 761865, "loss": 2.0127, "lr": 7.340559642205388e-07, "epoch": 5.174145025693528, "percentage": 34.49, "elapsed_time": "8:55:02", "remaining_time": "16:56:03", "throughput": 8335.09, "total_tokens": 267578648} {"current_steps": 262900, "total_steps": 761865, "loss": 1.9917, "lr": 7.338737489864814e-07, "epoch": 5.176113878443031, "percentage": 34.51, "elapsed_time": "8:55:14", "remaining_time": "16:55:50", "throughput": 8335.23, "total_tokens": 267681048} {"current_steps": 263000, "total_steps": 761865, "loss": 1.9616, "lr": 7.336914939841654e-07, "epoch": 5.178082731192534, "percentage": 34.52, "elapsed_time": "8:55:26", "remaining_time": "16:55:37", "throughput": 8335.37, "total_tokens": 267783448} {"current_steps": 263100, "total_steps": 761865, "loss": 1.9658, "lr": 7.335091992445819e-07, "epoch": 5.180051583942037, "percentage": 34.53, "elapsed_time": "8:55:37", "remaining_time": "16:55:24", "throughput": 8335.51, "total_tokens": 267885848} {"current_steps": 263200, "total_steps": 761865, "loss": 1.995, "lr": 7.333268647987286e-07, "epoch": 5.1820204366915394, "percentage": 34.55, "elapsed_time": "8:55:49", "remaining_time": "16:55:11", "throughput": 8335.64, "total_tokens": 267987696} {"current_steps": 263300, "total_steps": 761865, "loss": 1.961, "lr": 7.3314449067761e-07, "epoch": 5.183989289441043, "percentage": 34.56, "elapsed_time": "8:56:01", "remaining_time": "16:54:58", "throughput": 8335.78, "total_tokens": 268090096} {"current_steps": 263400, "total_steps": 761865, "loss": 2.0312, "lr": 7.329620769122371e-07, "epoch": 5.185958142190546, "percentage": 34.57, "elapsed_time": "8:56:13", "remaining_time": "16:54:45", "throughput": 8335.92, "total_tokens": 268192496} {"current_steps": 263500, "total_steps": 761865, "loss": 1.9876, "lr": 7.32779623533628e-07, "epoch": 5.187926994940049, "percentage": 34.59, "elapsed_time": "8:56:24", "remaining_time": "16:54:32", "throughput": 8336.06, "total_tokens": 268294600} {"current_steps": 263600, "total_steps": 761865, "loss": 2.0159, "lr": 7.325971305728071e-07, "epoch": 5.189895847689551, "percentage": 34.6, "elapsed_time": "8:56:36", "remaining_time": "16:54:18", "throughput": 8336.18, "total_tokens": 268395568} {"current_steps": 263700, "total_steps": 761865, "loss": 1.9888, "lr": 7.324145980608061e-07, "epoch": 5.191864700439054, "percentage": 34.61, "elapsed_time": "8:56:48", "remaining_time": "16:54:05", "throughput": 8336.31, "total_tokens": 268497280} {"current_steps": 263800, "total_steps": 761865, "loss": 1.9865, "lr": 7.322320260286628e-07, "epoch": 5.193833553188557, "percentage": 34.63, "elapsed_time": "8:56:59", "remaining_time": "16:53:52", "throughput": 8336.44, "total_tokens": 268598872} {"current_steps": 263900, "total_steps": 761865, "loss": 2.0033, "lr": 7.320494145074225e-07, "epoch": 5.19580240593806, "percentage": 34.64, "elapsed_time": "8:57:11", "remaining_time": "16:53:39", "throughput": 8336.58, "total_tokens": 268701272} {"current_steps": 264000, "total_steps": 761865, "loss": 2.0082, "lr": 7.318667635281362e-07, "epoch": 5.197771258687562, "percentage": 34.65, "elapsed_time": "8:57:23", "remaining_time": "16:53:25", "throughput": 8336.7, "total_tokens": 268802096} {"current_steps": 264100, "total_steps": 761865, "loss": 1.9643, "lr": 7.316840731218626e-07, "epoch": 5.199740111437066, "percentage": 34.66, "elapsed_time": "8:57:34", "remaining_time": "16:53:12", "throughput": 8336.84, "total_tokens": 268904496} {"current_steps": 264200, "total_steps": 761865, "loss": 1.9745, "lr": 7.315013433196664e-07, "epoch": 5.201708964186569, "percentage": 34.68, "elapsed_time": "8:57:46", "remaining_time": "16:52:59", "throughput": 8336.96, "total_tokens": 269005560} {"current_steps": 264300, "total_steps": 761865, "loss": 1.9806, "lr": 7.313185741526194e-07, "epoch": 5.203677816936072, "percentage": 34.69, "elapsed_time": "8:57:58", "remaining_time": "16:52:46", "throughput": 8337.1, "total_tokens": 269107960} {"current_steps": 264400, "total_steps": 761865, "loss": 1.9971, "lr": 7.311357656517998e-07, "epoch": 5.205646669685574, "percentage": 34.7, "elapsed_time": "8:58:10", "remaining_time": "16:52:33", "throughput": 8337.24, "total_tokens": 269210360} {"current_steps": 264500, "total_steps": 761865, "loss": 2.0123, "lr": 7.309529178482929e-07, "epoch": 5.207615522435077, "percentage": 34.72, "elapsed_time": "8:58:21", "remaining_time": "16:52:20", "throughput": 8337.38, "total_tokens": 269312760} {"current_steps": 264600, "total_steps": 761865, "loss": 1.975, "lr": 7.3077003077319e-07, "epoch": 5.20958437518458, "percentage": 34.73, "elapsed_time": "8:58:33", "remaining_time": "16:52:07", "throughput": 8337.49, "total_tokens": 269413704} {"current_steps": 264700, "total_steps": 761865, "loss": 1.9636, "lr": 7.3058710445759e-07, "epoch": 5.211553227934083, "percentage": 34.74, "elapsed_time": "8:58:45", "remaining_time": "16:51:53", "throughput": 8337.61, "total_tokens": 269514696} {"current_steps": 264800, "total_steps": 761865, "loss": 1.9479, "lr": 7.304041389325977e-07, "epoch": 5.213522080683585, "percentage": 34.76, "elapsed_time": "8:58:56", "remaining_time": "16:51:40", "throughput": 8337.73, "total_tokens": 269616544} {"current_steps": 264900, "total_steps": 761865, "loss": 1.9733, "lr": 7.302211342293248e-07, "epoch": 5.215490933433088, "percentage": 34.77, "elapsed_time": "8:59:08", "remaining_time": "16:51:27", "throughput": 8337.87, "total_tokens": 269718400} {"current_steps": 265000, "total_steps": 761865, "loss": 1.9468, "lr": 7.300380903788899e-07, "epoch": 5.217459786182592, "percentage": 34.78, "elapsed_time": "8:59:20", "remaining_time": "16:51:15", "throughput": 8337.92, "total_tokens": 269820800} {"current_steps": 265100, "total_steps": 761865, "loss": 1.9844, "lr": 7.298550074124177e-07, "epoch": 5.2194286389320945, "percentage": 34.8, "elapsed_time": "8:59:33", "remaining_time": "16:51:03", "throughput": 8337.75, "total_tokens": 269920656} {"current_steps": 265200, "total_steps": 761865, "loss": 1.9744, "lr": 7.296718853610407e-07, "epoch": 5.221397491681597, "percentage": 34.81, "elapsed_time": "8:59:45", "remaining_time": "16:50:50", "throughput": 8337.82, "total_tokens": 270022280} {"current_steps": 265300, "total_steps": 761865, "loss": 2.0031, "lr": 7.294887242558962e-07, "epoch": 5.2233663444311, "percentage": 34.82, "elapsed_time": "8:59:56", "remaining_time": "16:50:37", "throughput": 8337.93, "total_tokens": 270123712} {"current_steps": 265400, "total_steps": 761865, "loss": 2.0585, "lr": 7.293055241281301e-07, "epoch": 5.225335197180603, "percentage": 34.84, "elapsed_time": "9:00:08", "remaining_time": "16:50:24", "throughput": 8338.08, "total_tokens": 270226112} {"current_steps": 265500, "total_steps": 761865, "loss": 1.9708, "lr": 7.291222850088935e-07, "epoch": 5.227304049930106, "percentage": 34.85, "elapsed_time": "9:00:20", "remaining_time": "16:50:11", "throughput": 8338.24, "total_tokens": 270328512} {"current_steps": 265600, "total_steps": 761865, "loss": 2.0117, "lr": 7.289390069293448e-07, "epoch": 5.229272902679608, "percentage": 34.86, "elapsed_time": "9:00:32", "remaining_time": "16:49:58", "throughput": 8338.39, "total_tokens": 270430912} {"current_steps": 265700, "total_steps": 761865, "loss": 2.0293, "lr": 7.287556899206491e-07, "epoch": 5.231241755429111, "percentage": 34.87, "elapsed_time": "9:00:43", "remaining_time": "16:49:45", "throughput": 8338.54, "total_tokens": 270533312} {"current_steps": 265800, "total_steps": 761865, "loss": 1.991, "lr": 7.285723340139776e-07, "epoch": 5.233210608178615, "percentage": 34.89, "elapsed_time": "9:00:55", "remaining_time": "16:49:31", "throughput": 8338.7, "total_tokens": 270635536} {"current_steps": 265900, "total_steps": 761865, "loss": 1.9637, "lr": 7.283889392405086e-07, "epoch": 5.2351794609281175, "percentage": 34.9, "elapsed_time": "9:01:07", "remaining_time": "16:49:18", "throughput": 8338.85, "total_tokens": 270737936} {"current_steps": 266000, "total_steps": 761865, "loss": 2.0053, "lr": 7.282055056314269e-07, "epoch": 5.23714831367762, "percentage": 34.91, "elapsed_time": "9:01:18", "remaining_time": "16:49:05", "throughput": 8338.99, "total_tokens": 270839576} {"current_steps": 266100, "total_steps": 761865, "loss": 1.9983, "lr": 7.280220332179236e-07, "epoch": 5.239117166427123, "percentage": 34.93, "elapsed_time": "9:01:30", "remaining_time": "16:48:52", "throughput": 8339.13, "total_tokens": 270941144} {"current_steps": 266200, "total_steps": 761865, "loss": 2.0006, "lr": 7.278385220311969e-07, "epoch": 5.241086019176626, "percentage": 34.94, "elapsed_time": "9:01:41", "remaining_time": "16:48:38", "throughput": 8339.25, "total_tokens": 271041760} {"current_steps": 266300, "total_steps": 761865, "loss": 1.9903, "lr": 7.276549721024511e-07, "epoch": 5.2430548719261285, "percentage": 34.95, "elapsed_time": "9:01:53", "remaining_time": "16:48:25", "throughput": 8339.4, "total_tokens": 271143440} {"current_steps": 266400, "total_steps": 761865, "loss": 1.9921, "lr": 7.274713834628976e-07, "epoch": 5.245023724675631, "percentage": 34.97, "elapsed_time": "9:02:05", "remaining_time": "16:48:12", "throughput": 8339.54, "total_tokens": 271245072} {"current_steps": 266500, "total_steps": 761865, "loss": 1.9831, "lr": 7.272877561437538e-07, "epoch": 5.246992577425134, "percentage": 34.98, "elapsed_time": "9:02:16", "remaining_time": "16:47:58", "throughput": 8339.68, "total_tokens": 271346584} {"current_steps": 266600, "total_steps": 761865, "loss": 1.9835, "lr": 7.271040901762442e-07, "epoch": 5.248961430174637, "percentage": 34.99, "elapsed_time": "9:02:28", "remaining_time": "16:47:45", "throughput": 8339.81, "total_tokens": 271447520} {"current_steps": 266700, "total_steps": 761865, "loss": 1.9918, "lr": 7.269203855915994e-07, "epoch": 5.25093028292414, "percentage": 35.01, "elapsed_time": "9:02:40", "remaining_time": "16:47:32", "throughput": 8339.95, "total_tokens": 271549344} {"current_steps": 266800, "total_steps": 761865, "loss": 1.9705, "lr": 7.267366424210569e-07, "epoch": 5.252899135673643, "percentage": 35.02, "elapsed_time": "9:02:51", "remaining_time": "16:47:19", "throughput": 8340.11, "total_tokens": 271651744} {"current_steps": 266900, "total_steps": 761865, "loss": 1.9565, "lr": 7.265528606958608e-07, "epoch": 5.254867988423146, "percentage": 35.03, "elapsed_time": "9:03:03", "remaining_time": "16:47:05", "throughput": 8340.25, "total_tokens": 271753728} {"current_steps": 267000, "total_steps": 761865, "loss": 1.9715, "lr": 7.263690404472617e-07, "epoch": 5.256836841172649, "percentage": 35.05, "elapsed_time": "9:03:15", "remaining_time": "16:46:52", "throughput": 8340.41, "total_tokens": 271856128} {"current_steps": 267100, "total_steps": 761865, "loss": 1.9564, "lr": 7.261851817065166e-07, "epoch": 5.2588056939221515, "percentage": 35.06, "elapsed_time": "9:03:26", "remaining_time": "16:46:39", "throughput": 8340.55, "total_tokens": 271957712} {"current_steps": 267200, "total_steps": 761865, "loss": 1.9743, "lr": 7.260012845048889e-07, "epoch": 5.260774546671654, "percentage": 35.07, "elapsed_time": "9:03:38", "remaining_time": "16:46:26", "throughput": 8340.71, "total_tokens": 272060112} {"current_steps": 267300, "total_steps": 761865, "loss": 1.9784, "lr": 7.258173488736491e-07, "epoch": 5.262743399421157, "percentage": 35.08, "elapsed_time": "9:03:49", "remaining_time": "16:46:12", "throughput": 8340.85, "total_tokens": 272161680} {"current_steps": 267400, "total_steps": 761865, "loss": 1.989, "lr": 7.256333748440738e-07, "epoch": 5.26471225217066, "percentage": 35.1, "elapsed_time": "9:04:01", "remaining_time": "16:45:59", "throughput": 8340.97, "total_tokens": 272261816} {"current_steps": 267500, "total_steps": 761865, "loss": 1.9825, "lr": 7.254493624474459e-07, "epoch": 5.266681104920163, "percentage": 35.11, "elapsed_time": "9:04:13", "remaining_time": "16:45:46", "throughput": 8341.11, "total_tokens": 272363528} {"current_steps": 267600, "total_steps": 761865, "loss": 1.9691, "lr": 7.252653117150558e-07, "epoch": 5.268649957669666, "percentage": 35.12, "elapsed_time": "9:04:24", "remaining_time": "16:45:32", "throughput": 8341.26, "total_tokens": 272465928} {"current_steps": 267700, "total_steps": 761865, "loss": 1.9479, "lr": 7.250812226781992e-07, "epoch": 5.270618810419169, "percentage": 35.14, "elapsed_time": "9:04:36", "remaining_time": "16:45:19", "throughput": 8341.41, "total_tokens": 272568328} {"current_steps": 267800, "total_steps": 761865, "loss": 1.9611, "lr": 7.248970953681791e-07, "epoch": 5.272587663168672, "percentage": 35.15, "elapsed_time": "9:04:48", "remaining_time": "16:45:06", "throughput": 8341.56, "total_tokens": 272669912} {"current_steps": 267900, "total_steps": 761865, "loss": 1.9795, "lr": 7.247129298163047e-07, "epoch": 5.274556515918174, "percentage": 35.16, "elapsed_time": "9:04:59", "remaining_time": "16:44:53", "throughput": 8341.71, "total_tokens": 272772312} {"current_steps": 268000, "total_steps": 761865, "loss": 1.9582, "lr": 7.245287260538922e-07, "epoch": 5.276525368667677, "percentage": 35.18, "elapsed_time": "9:05:11", "remaining_time": "16:44:40", "throughput": 8341.86, "total_tokens": 272874712} {"current_steps": 268100, "total_steps": 761865, "loss": 2.0094, "lr": 7.243444841122633e-07, "epoch": 5.27849422141718, "percentage": 35.19, "elapsed_time": "9:05:23", "remaining_time": "16:44:26", "throughput": 8342.0, "total_tokens": 272976384} {"current_steps": 268200, "total_steps": 761865, "loss": 1.96, "lr": 7.241602040227473e-07, "epoch": 5.280463074166683, "percentage": 35.2, "elapsed_time": "9:05:34", "remaining_time": "16:44:13", "throughput": 8342.15, "total_tokens": 273078784} {"current_steps": 268300, "total_steps": 761865, "loss": 1.9581, "lr": 7.239758858166792e-07, "epoch": 5.282431926916186, "percentage": 35.22, "elapsed_time": "9:05:46", "remaining_time": "16:44:00", "throughput": 8342.3, "total_tokens": 273181184} {"current_steps": 268400, "total_steps": 761865, "loss": 2.0088, "lr": 7.237915295254009e-07, "epoch": 5.284400779665689, "percentage": 35.23, "elapsed_time": "9:05:58", "remaining_time": "16:43:47", "throughput": 8342.45, "total_tokens": 273283008} {"current_steps": 268500, "total_steps": 761865, "loss": 1.9636, "lr": 7.236071351802604e-07, "epoch": 5.286369632415192, "percentage": 35.24, "elapsed_time": "9:06:09", "remaining_time": "16:43:33", "throughput": 8342.59, "total_tokens": 273384560} {"current_steps": 268600, "total_steps": 761865, "loss": 1.9836, "lr": 7.234227028126126e-07, "epoch": 5.288338485164695, "percentage": 35.26, "elapsed_time": "9:06:21", "remaining_time": "16:43:20", "throughput": 8342.73, "total_tokens": 273486440} {"current_steps": 268700, "total_steps": 761865, "loss": 1.9769, "lr": 7.232382324538187e-07, "epoch": 5.290307337914197, "percentage": 35.27, "elapsed_time": "9:06:33", "remaining_time": "16:43:07", "throughput": 8342.87, "total_tokens": 273588264} {"current_steps": 268800, "total_steps": 761865, "loss": 1.9866, "lr": 7.230537241352461e-07, "epoch": 5.2922761906637, "percentage": 35.28, "elapsed_time": "9:06:44", "remaining_time": "16:42:54", "throughput": 8343.02, "total_tokens": 273690064} {"current_steps": 268900, "total_steps": 761865, "loss": 1.9612, "lr": 7.228691778882692e-07, "epoch": 5.294245043413203, "percentage": 35.29, "elapsed_time": "9:06:56", "remaining_time": "16:42:41", "throughput": 8343.17, "total_tokens": 273792464} {"current_steps": 269000, "total_steps": 761865, "loss": 1.9569, "lr": 7.226845937442682e-07, "epoch": 5.296213896162706, "percentage": 35.31, "elapsed_time": "9:07:07", "remaining_time": "16:42:27", "throughput": 8343.31, "total_tokens": 273894000} {"current_steps": 269100, "total_steps": 761865, "loss": 2.022, "lr": 7.224999717346303e-07, "epoch": 5.298182748912209, "percentage": 35.32, "elapsed_time": "9:07:19", "remaining_time": "16:42:14", "throughput": 8343.43, "total_tokens": 273994816} {"current_steps": 269200, "total_steps": 761865, "loss": 2.0185, "lr": 7.223153118907489e-07, "epoch": 5.300151601661712, "percentage": 35.33, "elapsed_time": "9:07:31", "remaining_time": "16:42:01", "throughput": 8343.59, "total_tokens": 274097216} {"current_steps": 269300, "total_steps": 761865, "loss": 1.9796, "lr": 7.221306142440238e-07, "epoch": 5.302120454411215, "percentage": 35.35, "elapsed_time": "9:07:42", "remaining_time": "16:41:48", "throughput": 8343.73, "total_tokens": 274199616} {"current_steps": 269400, "total_steps": 761865, "loss": 2.0091, "lr": 7.219458788258613e-07, "epoch": 5.304089307160718, "percentage": 35.36, "elapsed_time": "9:07:54", "remaining_time": "16:41:34", "throughput": 8343.88, "total_tokens": 274301400} {"current_steps": 269500, "total_steps": 761865, "loss": 1.988, "lr": 7.21761105667674e-07, "epoch": 5.30605815991022, "percentage": 35.37, "elapsed_time": "9:08:06", "remaining_time": "16:41:21", "throughput": 8344.02, "total_tokens": 274403176} {"current_steps": 269600, "total_steps": 761865, "loss": 1.9659, "lr": 7.215762948008812e-07, "epoch": 5.308027012659723, "percentage": 35.39, "elapsed_time": "9:08:17", "remaining_time": "16:41:08", "throughput": 8344.15, "total_tokens": 274504024} {"current_steps": 269700, "total_steps": 761865, "loss": 1.9774, "lr": 7.213914462569081e-07, "epoch": 5.309995865409226, "percentage": 35.4, "elapsed_time": "9:08:29", "remaining_time": "16:40:55", "throughput": 8344.3, "total_tokens": 274606136} {"current_steps": 269800, "total_steps": 761865, "loss": 2.0061, "lr": 7.212065600671872e-07, "epoch": 5.311964718158729, "percentage": 35.41, "elapsed_time": "9:08:41", "remaining_time": "16:40:41", "throughput": 8344.42, "total_tokens": 274706624} {"current_steps": 269900, "total_steps": 761865, "loss": 1.9677, "lr": 7.210216362631564e-07, "epoch": 5.313933570908231, "percentage": 35.43, "elapsed_time": "9:08:52", "remaining_time": "16:40:28", "throughput": 8344.56, "total_tokens": 274808480} {"current_steps": 270000, "total_steps": 761865, "loss": 1.9482, "lr": 7.208366748762604e-07, "epoch": 5.315902423657735, "percentage": 35.44, "elapsed_time": "9:09:04", "remaining_time": "16:40:15", "throughput": 8344.71, "total_tokens": 274910880} {"current_steps": 270100, "total_steps": 761865, "loss": 2.0014, "lr": 7.206516759379506e-07, "epoch": 5.317871276407238, "percentage": 35.45, "elapsed_time": "9:09:16", "remaining_time": "16:40:03", "throughput": 8344.71, "total_tokens": 275012448} {"current_steps": 270200, "total_steps": 761865, "loss": 1.96, "lr": 7.204666394796843e-07, "epoch": 5.3198401291567405, "percentage": 35.47, "elapsed_time": "9:09:28", "remaining_time": "16:39:49", "throughput": 8344.84, "total_tokens": 275113992} {"current_steps": 270300, "total_steps": 761865, "loss": 2.0011, "lr": 7.202815655329255e-07, "epoch": 5.321808981906243, "percentage": 35.48, "elapsed_time": "9:09:39", "remaining_time": "16:39:36", "throughput": 8344.98, "total_tokens": 275216392} {"current_steps": 270400, "total_steps": 761865, "loss": 1.9628, "lr": 7.200964541291443e-07, "epoch": 5.323777834655746, "percentage": 35.49, "elapsed_time": "9:09:51", "remaining_time": "16:39:23", "throughput": 8345.13, "total_tokens": 275318792} {"current_steps": 270500, "total_steps": 761865, "loss": 1.9621, "lr": 7.199113052998177e-07, "epoch": 5.325746687405249, "percentage": 35.5, "elapsed_time": "9:10:03", "remaining_time": "16:39:10", "throughput": 8345.27, "total_tokens": 275420112} {"current_steps": 270600, "total_steps": 761865, "loss": 2.0163, "lr": 7.197261190764283e-07, "epoch": 5.327715540154752, "percentage": 35.52, "elapsed_time": "9:10:14", "remaining_time": "16:38:57", "throughput": 8345.42, "total_tokens": 275522512} {"current_steps": 270700, "total_steps": 761865, "loss": 2.009, "lr": 7.195408954904656e-07, "epoch": 5.329684392904254, "percentage": 35.53, "elapsed_time": "9:10:26", "remaining_time": "16:38:44", "throughput": 8345.57, "total_tokens": 275624912} {"current_steps": 270800, "total_steps": 761865, "loss": 1.9733, "lr": 7.193556345734253e-07, "epoch": 5.331653245653758, "percentage": 35.54, "elapsed_time": "9:10:38", "remaining_time": "16:38:31", "throughput": 8345.71, "total_tokens": 275727312} {"current_steps": 270900, "total_steps": 761865, "loss": 1.99, "lr": 7.191703363568095e-07, "epoch": 5.333622098403261, "percentage": 35.56, "elapsed_time": "9:10:49", "remaining_time": "16:38:17", "throughput": 8345.85, "total_tokens": 275828920} {"current_steps": 271000, "total_steps": 761865, "loss": 1.9107, "lr": 7.189850008721264e-07, "epoch": 5.3355909511527635, "percentage": 35.57, "elapsed_time": "9:11:01", "remaining_time": "16:38:04", "throughput": 8346.0, "total_tokens": 275931320} {"current_steps": 271100, "total_steps": 761865, "loss": 1.9711, "lr": 7.187996281508912e-07, "epoch": 5.337559803902266, "percentage": 35.58, "elapsed_time": "9:11:13", "remaining_time": "16:37:51", "throughput": 8346.14, "total_tokens": 276033720} {"current_steps": 271200, "total_steps": 761865, "loss": 2.0245, "lr": 7.186142182246245e-07, "epoch": 5.339528656651769, "percentage": 35.6, "elapsed_time": "9:11:24", "remaining_time": "16:37:38", "throughput": 8346.29, "total_tokens": 276136120} {"current_steps": 271300, "total_steps": 761865, "loss": 1.9876, "lr": 7.18428771124854e-07, "epoch": 5.341497509401272, "percentage": 35.61, "elapsed_time": "9:11:36", "remaining_time": "16:37:25", "throughput": 8346.43, "total_tokens": 276237960} {"current_steps": 271400, "total_steps": 761865, "loss": 1.9671, "lr": 7.182432868831131e-07, "epoch": 5.3434663621507745, "percentage": 35.62, "elapsed_time": "9:11:48", "remaining_time": "16:37:12", "throughput": 8346.59, "total_tokens": 276340360} {"current_steps": 271500, "total_steps": 761865, "loss": 1.9718, "lr": 7.180577655309422e-07, "epoch": 5.345435214900277, "percentage": 35.64, "elapsed_time": "9:11:59", "remaining_time": "16:36:58", "throughput": 8346.74, "total_tokens": 276442760} {"current_steps": 271600, "total_steps": 761865, "loss": 2.0358, "lr": 7.178722070998872e-07, "epoch": 5.34740406764978, "percentage": 35.65, "elapsed_time": "9:12:11", "remaining_time": "16:36:45", "throughput": 8346.89, "total_tokens": 276545112} {"current_steps": 271700, "total_steps": 761865, "loss": 1.9698, "lr": 7.176866116215014e-07, "epoch": 5.349372920399284, "percentage": 35.66, "elapsed_time": "9:12:23", "remaining_time": "16:36:32", "throughput": 8347.03, "total_tokens": 276647512} {"current_steps": 271800, "total_steps": 761865, "loss": 2.0253, "lr": 7.17500979127343e-07, "epoch": 5.3513417731487865, "percentage": 35.68, "elapsed_time": "9:12:34", "remaining_time": "16:36:19", "throughput": 8347.18, "total_tokens": 276749544} {"current_steps": 271900, "total_steps": 761865, "loss": 1.9873, "lr": 7.173153096489776e-07, "epoch": 5.353310625898289, "percentage": 35.69, "elapsed_time": "9:12:46", "remaining_time": "16:36:06", "throughput": 8347.33, "total_tokens": 276851944} {"current_steps": 272000, "total_steps": 761865, "loss": 1.9718, "lr": 7.171296032179768e-07, "epoch": 5.355279478647792, "percentage": 35.7, "elapsed_time": "9:12:58", "remaining_time": "16:35:53", "throughput": 8347.48, "total_tokens": 276954344} {"current_steps": 272100, "total_steps": 761865, "loss": 2.0223, "lr": 7.169438598659185e-07, "epoch": 5.357248331397295, "percentage": 35.71, "elapsed_time": "9:13:09", "remaining_time": "16:35:39", "throughput": 8347.62, "total_tokens": 277056200} {"current_steps": 272200, "total_steps": 761865, "loss": 1.9871, "lr": 7.167580796243864e-07, "epoch": 5.3592171841467975, "percentage": 35.73, "elapsed_time": "9:13:21", "remaining_time": "16:35:26", "throughput": 8347.77, "total_tokens": 277158600} {"current_steps": 272300, "total_steps": 761865, "loss": 2.0257, "lr": 7.165722625249712e-07, "epoch": 5.3611860368963, "percentage": 35.74, "elapsed_time": "9:13:33", "remaining_time": "16:35:13", "throughput": 8347.91, "total_tokens": 277260912} {"current_steps": 272400, "total_steps": 761865, "loss": 2.0039, "lr": 7.163864085992693e-07, "epoch": 5.363154889645803, "percentage": 35.75, "elapsed_time": "9:13:44", "remaining_time": "16:35:00", "throughput": 8348.04, "total_tokens": 277361752} {"current_steps": 272500, "total_steps": 761865, "loss": 1.9659, "lr": 7.162005178788839e-07, "epoch": 5.365123742395307, "percentage": 35.77, "elapsed_time": "9:13:56", "remaining_time": "16:34:47", "throughput": 8348.18, "total_tokens": 277464152} {"current_steps": 272600, "total_steps": 761865, "loss": 1.9592, "lr": 7.160145903954238e-07, "epoch": 5.367092595144809, "percentage": 35.78, "elapsed_time": "9:14:08", "remaining_time": "16:34:34", "throughput": 8348.33, "total_tokens": 277566552} {"current_steps": 272700, "total_steps": 761865, "loss": 1.9748, "lr": 7.158286261805046e-07, "epoch": 5.369061447894312, "percentage": 35.79, "elapsed_time": "9:14:19", "remaining_time": "16:34:20", "throughput": 8348.46, "total_tokens": 277667784} {"current_steps": 272800, "total_steps": 761865, "loss": 1.9688, "lr": 7.156426252657478e-07, "epoch": 5.371030300643815, "percentage": 35.81, "elapsed_time": "9:14:31", "remaining_time": "16:34:07", "throughput": 8348.61, "total_tokens": 277770184} {"current_steps": 272900, "total_steps": 761865, "loss": 1.9271, "lr": 7.154565876827814e-07, "epoch": 5.372999153393318, "percentage": 35.82, "elapsed_time": "9:14:43", "remaining_time": "16:33:54", "throughput": 8348.75, "total_tokens": 277872584} {"current_steps": 273000, "total_steps": 761865, "loss": 1.9833, "lr": 7.152705134632396e-07, "epoch": 5.37496800614282, "percentage": 35.83, "elapsed_time": "9:14:54", "remaining_time": "16:33:41", "throughput": 8348.89, "total_tokens": 277974440} {"current_steps": 273100, "total_steps": 761865, "loss": 2.0069, "lr": 7.150844026387627e-07, "epoch": 5.376936858892323, "percentage": 35.85, "elapsed_time": "9:15:06", "remaining_time": "16:33:28", "throughput": 8349.02, "total_tokens": 278075432} {"current_steps": 273200, "total_steps": 761865, "loss": 1.9866, "lr": 7.148982552409972e-07, "epoch": 5.378905711641826, "percentage": 35.86, "elapsed_time": "9:15:18", "remaining_time": "16:33:15", "throughput": 8349.17, "total_tokens": 278177832} {"current_steps": 273300, "total_steps": 761865, "loss": 1.9769, "lr": 7.147120713015958e-07, "epoch": 5.380874564391329, "percentage": 35.87, "elapsed_time": "9:15:29", "remaining_time": "16:33:01", "throughput": 8349.31, "total_tokens": 278280232} {"current_steps": 273400, "total_steps": 761865, "loss": 1.9737, "lr": 7.145258508522178e-07, "epoch": 5.382843417140832, "percentage": 35.89, "elapsed_time": "9:15:41", "remaining_time": "16:32:48", "throughput": 8349.46, "total_tokens": 278382632} {"current_steps": 273500, "total_steps": 761865, "loss": 1.9702, "lr": 7.143395939245282e-07, "epoch": 5.384812269890335, "percentage": 35.9, "elapsed_time": "9:15:53", "remaining_time": "16:32:35", "throughput": 8349.61, "total_tokens": 278485032} {"current_steps": 273600, "total_steps": 761865, "loss": 2.0035, "lr": 7.141533005501985e-07, "epoch": 5.386781122639838, "percentage": 35.91, "elapsed_time": "9:16:04", "remaining_time": "16:32:22", "throughput": 8349.75, "total_tokens": 278587432} {"current_steps": 273700, "total_steps": 761865, "loss": 1.9657, "lr": 7.139669707609063e-07, "epoch": 5.388749975389341, "percentage": 35.92, "elapsed_time": "9:16:16", "remaining_time": "16:32:09", "throughput": 8349.88, "total_tokens": 278688496} {"current_steps": 273800, "total_steps": 761865, "loss": 2.0223, "lr": 7.137806045883353e-07, "epoch": 5.390718828138843, "percentage": 35.94, "elapsed_time": "9:16:27", "remaining_time": "16:31:56", "throughput": 8350.03, "total_tokens": 278790512} {"current_steps": 273900, "total_steps": 761865, "loss": 1.9799, "lr": 7.135942020641757e-07, "epoch": 5.392687680888346, "percentage": 35.95, "elapsed_time": "9:16:39", "remaining_time": "16:31:42", "throughput": 8350.16, "total_tokens": 278892256} {"current_steps": 274000, "total_steps": 761865, "loss": 2.0154, "lr": 7.134077632201236e-07, "epoch": 5.394656533637849, "percentage": 35.96, "elapsed_time": "9:16:51", "remaining_time": "16:31:29", "throughput": 8350.29, "total_tokens": 278992488} {"current_steps": 274100, "total_steps": 761865, "loss": 2.0385, "lr": 7.132212880878812e-07, "epoch": 5.396625386387352, "percentage": 35.98, "elapsed_time": "9:17:02", "remaining_time": "16:31:16", "throughput": 8350.43, "total_tokens": 279094224} {"current_steps": 274200, "total_steps": 761865, "loss": 1.9438, "lr": 7.130347766991572e-07, "epoch": 5.398594239136855, "percentage": 35.99, "elapsed_time": "9:17:14", "remaining_time": "16:31:03", "throughput": 8350.56, "total_tokens": 279195992} {"current_steps": 274300, "total_steps": 761865, "loss": 1.9707, "lr": 7.128482290856663e-07, "epoch": 5.400563091886358, "percentage": 36.0, "elapsed_time": "9:17:25", "remaining_time": "16:30:49", "throughput": 8350.69, "total_tokens": 279297160} {"current_steps": 274400, "total_steps": 761865, "loss": 1.9841, "lr": 7.126616452791293e-07, "epoch": 5.402531944635861, "percentage": 36.02, "elapsed_time": "9:17:37", "remaining_time": "16:30:36", "throughput": 8350.83, "total_tokens": 279399072} {"current_steps": 274500, "total_steps": 761865, "loss": 1.9721, "lr": 7.124750253112732e-07, "epoch": 5.404500797385364, "percentage": 36.03, "elapsed_time": "9:17:49", "remaining_time": "16:30:23", "throughput": 8350.98, "total_tokens": 279501472} {"current_steps": 274600, "total_steps": 761865, "loss": 1.99, "lr": 7.12288369213831e-07, "epoch": 5.406469650134866, "percentage": 36.04, "elapsed_time": "9:18:00", "remaining_time": "16:30:10", "throughput": 8351.12, "total_tokens": 279603168} {"current_steps": 274700, "total_steps": 761865, "loss": 1.9967, "lr": 7.121016770185423e-07, "epoch": 5.408438502884369, "percentage": 36.06, "elapsed_time": "9:18:12", "remaining_time": "16:29:57", "throughput": 8351.26, "total_tokens": 279705568} {"current_steps": 274800, "total_steps": 761865, "loss": 1.9451, "lr": 7.119149487571523e-07, "epoch": 5.410407355633872, "percentage": 36.07, "elapsed_time": "9:18:24", "remaining_time": "16:29:44", "throughput": 8351.4, "total_tokens": 279807000} {"current_steps": 274900, "total_steps": 761865, "loss": 1.9594, "lr": 7.117281844614126e-07, "epoch": 5.412376208383375, "percentage": 36.08, "elapsed_time": "9:18:35", "remaining_time": "16:29:30", "throughput": 8351.54, "total_tokens": 279909400} {"current_steps": 275000, "total_steps": 761865, "loss": 2.0033, "lr": 7.115413841630809e-07, "epoch": 5.414345061132878, "percentage": 36.1, "elapsed_time": "9:18:47", "remaining_time": "16:29:17", "throughput": 8351.68, "total_tokens": 280011800} {"current_steps": 275100, "total_steps": 761865, "loss": 2.0198, "lr": 7.113545478939211e-07, "epoch": 5.416313913882381, "percentage": 36.11, "elapsed_time": "9:18:59", "remaining_time": "16:29:05", "throughput": 8351.67, "total_tokens": 280113360} {"current_steps": 275200, "total_steps": 761865, "loss": 1.9338, "lr": 7.111676756857033e-07, "epoch": 5.418282766631884, "percentage": 36.12, "elapsed_time": "9:19:11", "remaining_time": "16:28:52", "throughput": 8351.81, "total_tokens": 280215760} {"current_steps": 275300, "total_steps": 761865, "loss": 2.0059, "lr": 7.109807675702029e-07, "epoch": 5.4202516193813866, "percentage": 36.14, "elapsed_time": "9:19:23", "remaining_time": "16:28:39", "throughput": 8351.95, "total_tokens": 280317640} {"current_steps": 275400, "total_steps": 761865, "loss": 1.9434, "lr": 7.107938235792028e-07, "epoch": 5.422220472130889, "percentage": 36.15, "elapsed_time": "9:19:34", "remaining_time": "16:28:26", "throughput": 8352.09, "total_tokens": 280419664} {"current_steps": 275500, "total_steps": 761865, "loss": 1.9485, "lr": 7.106068437444908e-07, "epoch": 5.424189324880392, "percentage": 36.16, "elapsed_time": "9:19:46", "remaining_time": "16:28:13", "throughput": 8352.22, "total_tokens": 280521488} {"current_steps": 275600, "total_steps": 761865, "loss": 2.0248, "lr": 7.104198280978614e-07, "epoch": 5.426158177629895, "percentage": 36.17, "elapsed_time": "9:19:58", "remaining_time": "16:28:00", "throughput": 8352.37, "total_tokens": 280623888} {"current_steps": 275700, "total_steps": 761865, "loss": 1.9829, "lr": 7.102327766711149e-07, "epoch": 5.428127030379398, "percentage": 36.19, "elapsed_time": "9:20:09", "remaining_time": "16:27:46", "throughput": 8352.5, "total_tokens": 280725144} {"current_steps": 275800, "total_steps": 761865, "loss": 1.9831, "lr": 7.100456894960581e-07, "epoch": 5.430095883128901, "percentage": 36.2, "elapsed_time": "9:20:21", "remaining_time": "16:27:33", "throughput": 8352.63, "total_tokens": 280826584} {"current_steps": 275900, "total_steps": 761865, "loss": 1.972, "lr": 7.098585666045032e-07, "epoch": 5.432064735878404, "percentage": 36.21, "elapsed_time": "9:20:32", "remaining_time": "16:27:20", "throughput": 8352.77, "total_tokens": 280928320} {"current_steps": 276000, "total_steps": 761865, "loss": 1.9603, "lr": 7.096714080282691e-07, "epoch": 5.434033588627907, "percentage": 36.23, "elapsed_time": "9:20:44", "remaining_time": "16:27:07", "throughput": 8352.91, "total_tokens": 281030720} {"current_steps": 276100, "total_steps": 761865, "loss": 1.9911, "lr": 7.094842137991804e-07, "epoch": 5.4360024413774095, "percentage": 36.24, "elapsed_time": "9:20:56", "remaining_time": "16:26:54", "throughput": 8353.06, "total_tokens": 281133120} {"current_steps": 276200, "total_steps": 761865, "loss": 2.0134, "lr": 7.092969839490683e-07, "epoch": 5.437971294126912, "percentage": 36.25, "elapsed_time": "9:21:07", "remaining_time": "16:26:41", "throughput": 8353.2, "total_tokens": 281234952} {"current_steps": 276300, "total_steps": 761865, "loss": 1.9603, "lr": 7.091097185097692e-07, "epoch": 5.439940146876415, "percentage": 36.27, "elapsed_time": "9:21:19", "remaining_time": "16:26:27", "throughput": 8353.34, "total_tokens": 281336728} {"current_steps": 276400, "total_steps": 761865, "loss": 2.0159, "lr": 7.089224175131263e-07, "epoch": 5.441908999625918, "percentage": 36.28, "elapsed_time": "9:21:31", "remaining_time": "16:26:14", "throughput": 8353.48, "total_tokens": 281438664} {"current_steps": 276500, "total_steps": 761865, "loss": 1.9942, "lr": 7.087350809909883e-07, "epoch": 5.4438778523754205, "percentage": 36.29, "elapsed_time": "9:21:42", "remaining_time": "16:26:01", "throughput": 8353.6, "total_tokens": 281539616} {"current_steps": 276600, "total_steps": 761865, "loss": 1.9664, "lr": 7.085477089752106e-07, "epoch": 5.445846705124923, "percentage": 36.31, "elapsed_time": "9:21:54", "remaining_time": "16:25:48", "throughput": 8353.74, "total_tokens": 281641496} {"current_steps": 276700, "total_steps": 761865, "loss": 2.0323, "lr": 7.083603014976536e-07, "epoch": 5.447815557874427, "percentage": 36.32, "elapsed_time": "9:22:06", "remaining_time": "16:25:35", "throughput": 8353.87, "total_tokens": 281742592} {"current_steps": 276800, "total_steps": 761865, "loss": 2.0215, "lr": 7.08172858590185e-07, "epoch": 5.44978441062393, "percentage": 36.33, "elapsed_time": "9:22:17", "remaining_time": "16:25:21", "throughput": 8354.0, "total_tokens": 281844384} {"current_steps": 276900, "total_steps": 761865, "loss": 1.9482, "lr": 7.079853802846773e-07, "epoch": 5.4517532633734325, "percentage": 36.35, "elapsed_time": "9:22:29", "remaining_time": "16:25:08", "throughput": 8354.14, "total_tokens": 281946136} {"current_steps": 277000, "total_steps": 761865, "loss": 1.9417, "lr": 7.077978666130103e-07, "epoch": 5.453722116122935, "percentage": 36.36, "elapsed_time": "9:22:40", "remaining_time": "16:24:55", "throughput": 8354.28, "total_tokens": 282048536} {"current_steps": 277100, "total_steps": 761865, "loss": 1.9708, "lr": 7.076103176070685e-07, "epoch": 5.455690968872438, "percentage": 36.37, "elapsed_time": "9:22:52", "remaining_time": "16:24:42", "throughput": 8354.43, "total_tokens": 282150936} {"current_steps": 277200, "total_steps": 761865, "loss": 1.9656, "lr": 7.074227332987432e-07, "epoch": 5.457659821621941, "percentage": 36.38, "elapsed_time": "9:23:04", "remaining_time": "16:24:29", "throughput": 8354.56, "total_tokens": 282252712} {"current_steps": 277300, "total_steps": 761865, "loss": 2.004, "lr": 7.072351137199317e-07, "epoch": 5.4596286743714435, "percentage": 36.4, "elapsed_time": "9:23:15", "remaining_time": "16:24:16", "throughput": 8354.71, "total_tokens": 282355112} {"current_steps": 277400, "total_steps": 761865, "loss": 1.9707, "lr": 7.070474589025371e-07, "epoch": 5.461597527120946, "percentage": 36.41, "elapsed_time": "9:23:27", "remaining_time": "16:24:03", "throughput": 8354.84, "total_tokens": 282456920} {"current_steps": 277500, "total_steps": 761865, "loss": 1.995, "lr": 7.068597688784683e-07, "epoch": 5.46356637987045, "percentage": 36.42, "elapsed_time": "9:23:39", "remaining_time": "16:23:50", "throughput": 8354.95, "total_tokens": 282557656} {"current_steps": 277600, "total_steps": 761865, "loss": 1.9817, "lr": 7.066720436796405e-07, "epoch": 5.465535232619953, "percentage": 36.44, "elapsed_time": "9:23:50", "remaining_time": "16:23:36", "throughput": 8355.1, "total_tokens": 282660056} {"current_steps": 277700, "total_steps": 761865, "loss": 1.9861, "lr": 7.064842833379749e-07, "epoch": 5.467504085369455, "percentage": 36.45, "elapsed_time": "9:24:02", "remaining_time": "16:23:23", "throughput": 8355.22, "total_tokens": 282760936} {"current_steps": 277800, "total_steps": 761865, "loss": 1.994, "lr": 7.062964878853985e-07, "epoch": 5.469472938118958, "percentage": 36.46, "elapsed_time": "9:24:14", "remaining_time": "16:23:10", "throughput": 8355.37, "total_tokens": 282863336} {"current_steps": 277900, "total_steps": 761865, "loss": 1.9454, "lr": 7.061086573538444e-07, "epoch": 5.471441790868461, "percentage": 36.48, "elapsed_time": "9:24:25", "remaining_time": "16:22:57", "throughput": 8355.5, "total_tokens": 282964928} {"current_steps": 278000, "total_steps": 761865, "loss": 1.9857, "lr": 7.059207917752512e-07, "epoch": 5.473410643617964, "percentage": 36.49, "elapsed_time": "9:24:37", "remaining_time": "16:22:44", "throughput": 8355.63, "total_tokens": 283066736} {"current_steps": 278100, "total_steps": 761865, "loss": 1.9627, "lr": 7.057328911815644e-07, "epoch": 5.4753794963674665, "percentage": 36.5, "elapsed_time": "9:24:48", "remaining_time": "16:22:31", "throughput": 8355.76, "total_tokens": 283167920} {"current_steps": 278200, "total_steps": 761865, "loss": 2.0062, "lr": 7.055449556047347e-07, "epoch": 5.477348349116969, "percentage": 36.52, "elapsed_time": "9:25:00", "remaining_time": "16:22:17", "throughput": 8355.89, "total_tokens": 283269752} {"current_steps": 278300, "total_steps": 761865, "loss": 1.9848, "lr": 7.053569850767189e-07, "epoch": 5.479317201866472, "percentage": 36.53, "elapsed_time": "9:25:12", "remaining_time": "16:22:04", "throughput": 8356.0, "total_tokens": 283370360} {"current_steps": 278400, "total_steps": 761865, "loss": 2.0248, "lr": 7.051689796294799e-07, "epoch": 5.481286054615976, "percentage": 36.54, "elapsed_time": "9:25:23", "remaining_time": "16:21:51", "throughput": 8356.14, "total_tokens": 283471992} {"current_steps": 278500, "total_steps": 761865, "loss": 1.9933, "lr": 7.049809392949863e-07, "epoch": 5.483254907365478, "percentage": 36.56, "elapsed_time": "9:25:35", "remaining_time": "16:21:38", "throughput": 8356.28, "total_tokens": 283574392} {"current_steps": 278600, "total_steps": 761865, "loss": 2.0123, "lr": 7.04792864105213e-07, "epoch": 5.485223760114981, "percentage": 36.57, "elapsed_time": "9:25:47", "remaining_time": "16:21:25", "throughput": 8356.41, "total_tokens": 283676200} {"current_steps": 278700, "total_steps": 761865, "loss": 1.9983, "lr": 7.046047540921403e-07, "epoch": 5.487192612864484, "percentage": 36.58, "elapsed_time": "9:25:58", "remaining_time": "16:21:12", "throughput": 8356.55, "total_tokens": 283777928} {"current_steps": 278800, "total_steps": 761865, "loss": 1.9652, "lr": 7.044166092877551e-07, "epoch": 5.489161465613987, "percentage": 36.59, "elapsed_time": "9:26:10", "remaining_time": "16:20:59", "throughput": 8356.69, "total_tokens": 283880328} {"current_steps": 278900, "total_steps": 761865, "loss": 2.0007, "lr": 7.042284297240496e-07, "epoch": 5.491130318363489, "percentage": 36.61, "elapsed_time": "9:26:21", "remaining_time": "16:20:45", "throughput": 8356.81, "total_tokens": 283980984} {"current_steps": 279000, "total_steps": 761865, "loss": 2.0202, "lr": 7.040402154330218e-07, "epoch": 5.493099171112992, "percentage": 36.62, "elapsed_time": "9:26:33", "remaining_time": "16:20:32", "throughput": 8356.95, "total_tokens": 284083384} {"current_steps": 279100, "total_steps": 761865, "loss": 2.0162, "lr": 7.038519664466767e-07, "epoch": 5.495068023862495, "percentage": 36.63, "elapsed_time": "9:26:45", "remaining_time": "16:20:19", "throughput": 8357.09, "total_tokens": 284185312} {"current_steps": 279200, "total_steps": 761865, "loss": 1.9652, "lr": 7.036636827970238e-07, "epoch": 5.497036876611999, "percentage": 36.65, "elapsed_time": "9:26:56", "remaining_time": "16:20:06", "throughput": 8357.22, "total_tokens": 284287072} {"current_steps": 279300, "total_steps": 761865, "loss": 2.0085, "lr": 7.034753645160796e-07, "epoch": 5.499005729361501, "percentage": 36.66, "elapsed_time": "9:27:08", "remaining_time": "16:19:53", "throughput": 8357.36, "total_tokens": 284389472} {"current_steps": 279400, "total_steps": 761865, "loss": 2.0226, "lr": 7.032870116358658e-07, "epoch": 5.500974582111004, "percentage": 36.67, "elapsed_time": "9:27:20", "remaining_time": "16:19:40", "throughput": 8357.49, "total_tokens": 284491160} {"current_steps": 279500, "total_steps": 761865, "loss": 1.996, "lr": 7.030986241884104e-07, "epoch": 5.502943434860507, "percentage": 36.69, "elapsed_time": "9:27:31", "remaining_time": "16:19:27", "throughput": 8357.64, "total_tokens": 284593560} {"current_steps": 279600, "total_steps": 761865, "loss": 1.9927, "lr": 7.029102022057467e-07, "epoch": 5.50491228761001, "percentage": 36.7, "elapsed_time": "9:27:43", "remaining_time": "16:19:14", "throughput": 8357.78, "total_tokens": 284695960} {"current_steps": 279700, "total_steps": 761865, "loss": 2.0303, "lr": 7.027217457199149e-07, "epoch": 5.506881140359512, "percentage": 36.71, "elapsed_time": "9:27:55", "remaining_time": "16:19:01", "throughput": 8357.9, "total_tokens": 284797496} {"current_steps": 279800, "total_steps": 761865, "loss": 2.0225, "lr": 7.025332547629598e-07, "epoch": 5.508849993109015, "percentage": 36.73, "elapsed_time": "9:28:06", "remaining_time": "16:18:47", "throughput": 8358.03, "total_tokens": 284898824} {"current_steps": 279900, "total_steps": 761865, "loss": 1.9667, "lr": 7.023447293669332e-07, "epoch": 5.510818845858518, "percentage": 36.74, "elapsed_time": "9:28:18", "remaining_time": "16:18:34", "throughput": 8358.16, "total_tokens": 285000416} {"current_steps": 280000, "total_steps": 761865, "loss": 1.9313, "lr": 7.021561695638917e-07, "epoch": 5.512787698608021, "percentage": 36.75, "elapsed_time": "9:28:30", "remaining_time": "16:18:21", "throughput": 8358.3, "total_tokens": 285102816} {"current_steps": 280100, "total_steps": 761865, "loss": 2.0217, "lr": 7.019675753858987e-07, "epoch": 5.514756551357524, "percentage": 36.77, "elapsed_time": "9:28:42", "remaining_time": "16:18:09", "throughput": 8358.29, "total_tokens": 285204384} {"current_steps": 280200, "total_steps": 761865, "loss": 1.9988, "lr": 7.01778946865023e-07, "epoch": 5.516725404107027, "percentage": 36.78, "elapsed_time": "9:28:53", "remaining_time": "16:17:56", "throughput": 8358.42, "total_tokens": 285306048} {"current_steps": 280300, "total_steps": 761865, "loss": 2.0129, "lr": 7.015902840333394e-07, "epoch": 5.51869425685653, "percentage": 36.79, "elapsed_time": "9:29:05", "remaining_time": "16:17:43", "throughput": 8358.56, "total_tokens": 285408448} {"current_steps": 280400, "total_steps": 761865, "loss": 1.9638, "lr": 7.014015869229283e-07, "epoch": 5.520663109606033, "percentage": 36.8, "elapsed_time": "9:29:17", "remaining_time": "16:17:30", "throughput": 8358.69, "total_tokens": 285510352} {"current_steps": 280500, "total_steps": 761865, "loss": 2.0367, "lr": 7.01212855565876e-07, "epoch": 5.522631962355535, "percentage": 36.82, "elapsed_time": "9:29:28", "remaining_time": "16:17:17", "throughput": 8358.82, "total_tokens": 285611592} {"current_steps": 280600, "total_steps": 761865, "loss": 1.97, "lr": 7.010240899942747e-07, "epoch": 5.524600815105038, "percentage": 36.83, "elapsed_time": "9:29:40", "remaining_time": "16:17:04", "throughput": 8358.95, "total_tokens": 285713376} {"current_steps": 280700, "total_steps": 761865, "loss": 2.0261, "lr": 7.008352902402224e-07, "epoch": 5.526569667854541, "percentage": 36.84, "elapsed_time": "9:29:52", "remaining_time": "16:16:50", "throughput": 8359.08, "total_tokens": 285815128} {"current_steps": 280800, "total_steps": 761865, "loss": 1.9813, "lr": 7.00646456335823e-07, "epoch": 5.5285385206040445, "percentage": 36.86, "elapsed_time": "9:30:03", "remaining_time": "16:16:37", "throughput": 8359.21, "total_tokens": 285916920} {"current_steps": 280900, "total_steps": 761865, "loss": 1.9776, "lr": 7.004575883131859e-07, "epoch": 5.530507373353547, "percentage": 36.87, "elapsed_time": "9:30:15", "remaining_time": "16:16:24", "throughput": 8359.34, "total_tokens": 286019320} {"current_steps": 281000, "total_steps": 761865, "loss": 1.9733, "lr": 7.002686862044266e-07, "epoch": 5.53247622610305, "percentage": 36.88, "elapsed_time": "9:30:27", "remaining_time": "16:16:11", "throughput": 8359.48, "total_tokens": 286121720} {"current_steps": 281100, "total_steps": 761865, "loss": 1.9733, "lr": 7.000797500416665e-07, "epoch": 5.534445078852553, "percentage": 36.9, "elapsed_time": "9:30:38", "remaining_time": "16:15:58", "throughput": 8359.62, "total_tokens": 286224120} {"current_steps": 281200, "total_steps": 761865, "loss": 1.998, "lr": 6.998907798570325e-07, "epoch": 5.5364139316020555, "percentage": 36.91, "elapsed_time": "9:30:50", "remaining_time": "16:15:45", "throughput": 8359.75, "total_tokens": 286325336} {"current_steps": 281300, "total_steps": 761865, "loss": 1.9691, "lr": 6.997017756826572e-07, "epoch": 5.538382784351558, "percentage": 36.92, "elapsed_time": "9:31:02", "remaining_time": "16:15:32", "throughput": 8359.88, "total_tokens": 286427256} {"current_steps": 281400, "total_steps": 761865, "loss": 1.9654, "lr": 6.995127375506794e-07, "epoch": 5.540351637101061, "percentage": 36.94, "elapsed_time": "9:31:13", "remaining_time": "16:15:19", "throughput": 8360.02, "total_tokens": 286529656} {"current_steps": 281500, "total_steps": 761865, "loss": 1.9904, "lr": 6.993236654932433e-07, "epoch": 5.542320489850564, "percentage": 36.95, "elapsed_time": "9:31:25", "remaining_time": "16:15:06", "throughput": 8360.15, "total_tokens": 286631064} {"current_steps": 281600, "total_steps": 761865, "loss": 1.9814, "lr": 6.991345595424991e-07, "epoch": 5.544289342600067, "percentage": 36.96, "elapsed_time": "9:31:37", "remaining_time": "16:14:53", "throughput": 8360.28, "total_tokens": 286733464} {"current_steps": 281700, "total_steps": 761865, "loss": 2.0289, "lr": 6.989454197306027e-07, "epoch": 5.546258195349569, "percentage": 36.98, "elapsed_time": "9:31:48", "remaining_time": "16:14:40", "throughput": 8360.41, "total_tokens": 286835120} {"current_steps": 281800, "total_steps": 761865, "loss": 1.979, "lr": 6.987562460897155e-07, "epoch": 5.548227048099073, "percentage": 36.99, "elapsed_time": "9:32:00", "remaining_time": "16:14:27", "throughput": 8360.55, "total_tokens": 286937520} {"current_steps": 281900, "total_steps": 761865, "loss": 1.9442, "lr": 6.98567038652005e-07, "epoch": 5.550195900848576, "percentage": 37.0, "elapsed_time": "9:32:12", "remaining_time": "16:14:14", "throughput": 8360.69, "total_tokens": 287039920} {"current_steps": 282000, "total_steps": 761865, "loss": 1.9655, "lr": 6.983777974496446e-07, "epoch": 5.5521647535980785, "percentage": 37.01, "elapsed_time": "9:32:23", "remaining_time": "16:14:01", "throughput": 8360.83, "total_tokens": 287142320} {"current_steps": 282100, "total_steps": 761865, "loss": 1.9509, "lr": 6.981885225148127e-07, "epoch": 5.554133606347581, "percentage": 37.03, "elapsed_time": "9:32:35", "remaining_time": "16:13:47", "throughput": 8360.97, "total_tokens": 287244720} {"current_steps": 282200, "total_steps": 761865, "loss": 2.0188, "lr": 6.979992138796941e-07, "epoch": 5.556102459097084, "percentage": 37.04, "elapsed_time": "9:32:47", "remaining_time": "16:13:34", "throughput": 8361.1, "total_tokens": 287346560} {"current_steps": 282300, "total_steps": 761865, "loss": 2.0305, "lr": 6.978098715764794e-07, "epoch": 5.558071311846587, "percentage": 37.05, "elapsed_time": "9:32:58", "remaining_time": "16:13:21", "throughput": 8361.22, "total_tokens": 287447432} {"current_steps": 282400, "total_steps": 761865, "loss": 1.9655, "lr": 6.976204956373645e-07, "epoch": 5.5600401645960895, "percentage": 37.07, "elapsed_time": "9:33:10", "remaining_time": "16:13:08", "throughput": 8361.36, "total_tokens": 287549832} {"current_steps": 282500, "total_steps": 761865, "loss": 1.9744, "lr": 6.974310860945509e-07, "epoch": 5.562009017345593, "percentage": 37.08, "elapsed_time": "9:33:21", "remaining_time": "16:12:55", "throughput": 8361.49, "total_tokens": 287651728} {"current_steps": 282600, "total_steps": 761865, "loss": 1.9985, "lr": 6.972416429802465e-07, "epoch": 5.563977870095096, "percentage": 37.09, "elapsed_time": "9:33:33", "remaining_time": "16:12:42", "throughput": 8361.63, "total_tokens": 287754128} {"current_steps": 282700, "total_steps": 761865, "loss": 1.9789, "lr": 6.970521663266642e-07, "epoch": 5.565946722844599, "percentage": 37.11, "elapsed_time": "9:33:45", "remaining_time": "16:12:29", "throughput": 8361.76, "total_tokens": 287855848} {"current_steps": 282800, "total_steps": 761865, "loss": 1.9898, "lr": 6.968626561660231e-07, "epoch": 5.567915575594101, "percentage": 37.12, "elapsed_time": "9:33:56", "remaining_time": "16:12:16", "throughput": 8361.9, "total_tokens": 287958248} {"current_steps": 282900, "total_steps": 761865, "loss": 1.9427, "lr": 6.966731125305476e-07, "epoch": 5.569884428343604, "percentage": 37.13, "elapsed_time": "9:34:08", "remaining_time": "16:12:03", "throughput": 8362.03, "total_tokens": 288060648} {"current_steps": 283000, "total_steps": 761865, "loss": 2.001, "lr": 6.964835354524684e-07, "epoch": 5.571853281093107, "percentage": 37.15, "elapsed_time": "9:34:20", "remaining_time": "16:11:50", "throughput": 8362.15, "total_tokens": 288161920} {"current_steps": 283100, "total_steps": 761865, "loss": 1.9891, "lr": 6.962939249640209e-07, "epoch": 5.57382213384261, "percentage": 37.16, "elapsed_time": "9:34:31", "remaining_time": "16:11:37", "throughput": 8362.29, "total_tokens": 288264320} {"current_steps": 283200, "total_steps": 761865, "loss": 1.9779, "lr": 6.961042810974474e-07, "epoch": 5.5757909865921125, "percentage": 37.17, "elapsed_time": "9:34:43", "remaining_time": "16:11:24", "throughput": 8362.41, "total_tokens": 288365376} {"current_steps": 283300, "total_steps": 761865, "loss": 1.9889, "lr": 6.959146038849945e-07, "epoch": 5.577759839341615, "percentage": 37.19, "elapsed_time": "9:34:55", "remaining_time": "16:11:11", "throughput": 8362.55, "total_tokens": 288467776} {"current_steps": 283400, "total_steps": 761865, "loss": 2.011, "lr": 6.957248933589161e-07, "epoch": 5.579728692091119, "percentage": 37.2, "elapsed_time": "9:35:06", "remaining_time": "16:10:57", "throughput": 8362.68, "total_tokens": 288569528} {"current_steps": 283500, "total_steps": 761865, "loss": 1.9834, "lr": 6.955351495514701e-07, "epoch": 5.581697544840622, "percentage": 37.21, "elapsed_time": "9:35:18", "remaining_time": "16:10:44", "throughput": 8362.81, "total_tokens": 288671928} {"current_steps": 283600, "total_steps": 761865, "loss": 2.0101, "lr": 6.953453724949212e-07, "epoch": 5.583666397590124, "percentage": 37.22, "elapsed_time": "9:35:30", "remaining_time": "16:10:31", "throughput": 8362.95, "total_tokens": 288774328} {"current_steps": 283700, "total_steps": 761865, "loss": 2.0175, "lr": 6.951555622215393e-07, "epoch": 5.585635250339627, "percentage": 37.24, "elapsed_time": "9:35:41", "remaining_time": "16:10:18", "throughput": 8363.06, "total_tokens": 288875096} {"current_steps": 283800, "total_steps": 761865, "loss": 2.0156, "lr": 6.949657187636003e-07, "epoch": 5.58760410308913, "percentage": 37.25, "elapsed_time": "9:35:53", "remaining_time": "16:10:05", "throughput": 8363.19, "total_tokens": 288977016} {"current_steps": 283900, "total_steps": 761865, "loss": 1.9681, "lr": 6.947758421533849e-07, "epoch": 5.589572955838633, "percentage": 37.26, "elapsed_time": "9:36:05", "remaining_time": "16:09:52", "throughput": 8363.31, "total_tokens": 289078216} {"current_steps": 284000, "total_steps": 761865, "loss": 1.9827, "lr": 6.945859324231806e-07, "epoch": 5.591541808588135, "percentage": 37.28, "elapsed_time": "9:36:16", "remaining_time": "16:09:39", "throughput": 8363.44, "total_tokens": 289180616} {"current_steps": 284100, "total_steps": 761865, "loss": 2.0707, "lr": 6.943959896052796e-07, "epoch": 5.593510661337638, "percentage": 37.29, "elapsed_time": "9:36:28", "remaining_time": "16:09:26", "throughput": 8363.55, "total_tokens": 289280832} {"current_steps": 284200, "total_steps": 761865, "loss": 2.032, "lr": 6.942060137319802e-07, "epoch": 5.595479514087142, "percentage": 37.3, "elapsed_time": "9:36:39", "remaining_time": "16:09:13", "throughput": 8363.69, "total_tokens": 289383232} {"current_steps": 284300, "total_steps": 761865, "loss": 1.9833, "lr": 6.940160048355861e-07, "epoch": 5.597448366836645, "percentage": 37.32, "elapsed_time": "9:36:51", "remaining_time": "16:09:00", "throughput": 8363.83, "total_tokens": 289485632} {"current_steps": 284400, "total_steps": 761865, "loss": 2.0212, "lr": 6.938259629484069e-07, "epoch": 5.599417219586147, "percentage": 37.33, "elapsed_time": "9:37:03", "remaining_time": "16:08:47", "throughput": 8363.96, "total_tokens": 289587584} {"current_steps": 284500, "total_steps": 761865, "loss": 1.9549, "lr": 6.936358881027575e-07, "epoch": 5.60138607233565, "percentage": 37.34, "elapsed_time": "9:37:14", "remaining_time": "16:08:34", "throughput": 8364.07, "total_tokens": 289688536} {"current_steps": 284600, "total_steps": 761865, "loss": 1.9611, "lr": 6.934457803309585e-07, "epoch": 5.603354925085153, "percentage": 37.36, "elapsed_time": "9:37:26", "remaining_time": "16:08:21", "throughput": 8364.21, "total_tokens": 289790936} {"current_steps": 284700, "total_steps": 761865, "loss": 1.9793, "lr": 6.93255639665336e-07, "epoch": 5.605323777834656, "percentage": 37.37, "elapsed_time": "9:37:38", "remaining_time": "16:08:08", "throughput": 8364.35, "total_tokens": 289893336} {"current_steps": 284800, "total_steps": 761865, "loss": 2.0022, "lr": 6.930654661382223e-07, "epoch": 5.607292630584158, "percentage": 37.38, "elapsed_time": "9:37:49", "remaining_time": "16:07:55", "throughput": 8364.47, "total_tokens": 289994992} {"current_steps": 284900, "total_steps": 761865, "loss": 2.0112, "lr": 6.928752597819541e-07, "epoch": 5.609261483333661, "percentage": 37.4, "elapsed_time": "9:38:01", "remaining_time": "16:07:41", "throughput": 8364.61, "total_tokens": 290096792} {"current_steps": 285000, "total_steps": 761865, "loss": 1.9136, "lr": 6.92685020628875e-07, "epoch": 5.611230336083164, "percentage": 37.41, "elapsed_time": "9:38:13", "remaining_time": "16:07:28", "throughput": 8364.74, "total_tokens": 290199192} {"current_steps": 285100, "total_steps": 761865, "loss": 1.9666, "lr": 6.924947487113333e-07, "epoch": 5.6131991888326676, "percentage": 37.42, "elapsed_time": "9:38:25", "remaining_time": "16:07:16", "throughput": 8364.74, "total_tokens": 290300824} {"current_steps": 285200, "total_steps": 761865, "loss": 1.974, "lr": 6.923044440616831e-07, "epoch": 5.61516804158217, "percentage": 37.43, "elapsed_time": "9:38:36", "remaining_time": "16:07:03", "throughput": 8364.87, "total_tokens": 290402608} {"current_steps": 285300, "total_steps": 761865, "loss": 2.0539, "lr": 6.921141067122842e-07, "epoch": 5.617136894331673, "percentage": 37.45, "elapsed_time": "9:38:48", "remaining_time": "16:06:50", "throughput": 8365.0, "total_tokens": 290504248} {"current_steps": 285400, "total_steps": 761865, "loss": 2.0213, "lr": 6.919237366955017e-07, "epoch": 5.619105747081176, "percentage": 37.46, "elapsed_time": "9:39:00", "remaining_time": "16:06:37", "throughput": 8365.13, "total_tokens": 290606024} {"current_steps": 285500, "total_steps": 761865, "loss": 1.9549, "lr": 6.917333340437067e-07, "epoch": 5.621074599830679, "percentage": 37.47, "elapsed_time": "9:39:11", "remaining_time": "16:06:24", "throughput": 8365.25, "total_tokens": 290707120} {"current_steps": 285600, "total_steps": 761865, "loss": 2.0025, "lr": 6.915428987892753e-07, "epoch": 5.623043452580181, "percentage": 37.49, "elapsed_time": "9:39:23", "remaining_time": "16:06:11", "throughput": 8365.38, "total_tokens": 290809520} {"current_steps": 285700, "total_steps": 761865, "loss": 1.996, "lr": 6.913524309645897e-07, "epoch": 5.625012305329684, "percentage": 37.5, "elapsed_time": "9:39:35", "remaining_time": "16:05:58", "throughput": 8365.5, "total_tokens": 290910528} {"current_steps": 285800, "total_steps": 761865, "loss": 1.9955, "lr": 6.911619306020368e-07, "epoch": 5.626981158079188, "percentage": 37.51, "elapsed_time": "9:39:46", "remaining_time": "16:05:45", "throughput": 8365.62, "total_tokens": 291012456} {"current_steps": 285900, "total_steps": 761865, "loss": 1.9883, "lr": 6.909713977340102e-07, "epoch": 5.6289500108286905, "percentage": 37.53, "elapsed_time": "9:39:58", "remaining_time": "16:05:32", "throughput": 8365.74, "total_tokens": 291113584} {"current_steps": 286000, "total_steps": 761865, "loss": 2.0086, "lr": 6.90780832392908e-07, "epoch": 5.630918863578193, "percentage": 37.54, "elapsed_time": "9:40:09", "remaining_time": "16:05:18", "throughput": 8365.87, "total_tokens": 291215224} {"current_steps": 286100, "total_steps": 761865, "loss": 2.0076, "lr": 6.905902346111346e-07, "epoch": 5.632887716327696, "percentage": 37.55, "elapsed_time": "9:40:21", "remaining_time": "16:05:05", "throughput": 8365.98, "total_tokens": 291315200} {"current_steps": 286200, "total_steps": 761865, "loss": 1.9033, "lr": 6.90399604421099e-07, "epoch": 5.634856569077199, "percentage": 37.57, "elapsed_time": "9:40:33", "remaining_time": "16:04:52", "throughput": 8366.11, "total_tokens": 291417600} {"current_steps": 286300, "total_steps": 761865, "loss": 1.9776, "lr": 6.902089418552169e-07, "epoch": 5.6368254218267015, "percentage": 37.58, "elapsed_time": "9:40:44", "remaining_time": "16:04:39", "throughput": 8366.23, "total_tokens": 291519184} {"current_steps": 286400, "total_steps": 761865, "loss": 1.9789, "lr": 6.900182469459082e-07, "epoch": 5.638794274576204, "percentage": 37.59, "elapsed_time": "9:40:56", "remaining_time": "16:04:26", "throughput": 8366.37, "total_tokens": 291621584} {"current_steps": 286500, "total_steps": 761865, "loss": 1.9895, "lr": 6.898275197255996e-07, "epoch": 5.640763127325707, "percentage": 37.61, "elapsed_time": "9:41:08", "remaining_time": "16:04:13", "throughput": 8366.5, "total_tokens": 291723360} {"current_steps": 286600, "total_steps": 761865, "loss": 2.0115, "lr": 6.896367602267221e-07, "epoch": 5.64273198007521, "percentage": 37.62, "elapsed_time": "9:41:19", "remaining_time": "16:04:00", "throughput": 8366.63, "total_tokens": 291825400} {"current_steps": 286700, "total_steps": 761865, "loss": 1.9229, "lr": 6.894459684817133e-07, "epoch": 5.644700832824713, "percentage": 37.63, "elapsed_time": "9:41:31", "remaining_time": "16:03:47", "throughput": 8366.77, "total_tokens": 291927800} {"current_steps": 286800, "total_steps": 761865, "loss": 1.9744, "lr": 6.89255144523015e-07, "epoch": 5.646669685574216, "percentage": 37.64, "elapsed_time": "9:41:43", "remaining_time": "16:03:34", "throughput": 8366.9, "total_tokens": 292030200} {"current_steps": 286900, "total_steps": 761865, "loss": 1.9755, "lr": 6.89064288383076e-07, "epoch": 5.648638538323719, "percentage": 37.66, "elapsed_time": "9:41:54", "remaining_time": "16:03:21", "throughput": 8367.01, "total_tokens": 292131136} {"current_steps": 287000, "total_steps": 761865, "loss": 2.0074, "lr": 6.888734000943493e-07, "epoch": 5.650607391073222, "percentage": 37.67, "elapsed_time": "9:42:06", "remaining_time": "16:03:08", "throughput": 8367.13, "total_tokens": 292232536} {"current_steps": 287100, "total_steps": 761865, "loss": 1.9892, "lr": 6.886824796892939e-07, "epoch": 5.6525762438227245, "percentage": 37.68, "elapsed_time": "9:42:17", "remaining_time": "16:02:55", "throughput": 8367.26, "total_tokens": 292334296} {"current_steps": 287200, "total_steps": 761865, "loss": 1.967, "lr": 6.88491527200374e-07, "epoch": 5.654545096572227, "percentage": 37.7, "elapsed_time": "9:42:29", "remaining_time": "16:02:42", "throughput": 8367.39, "total_tokens": 292436696} {"current_steps": 287300, "total_steps": 761865, "loss": 1.9608, "lr": 6.883005426600601e-07, "epoch": 5.65651394932173, "percentage": 37.71, "elapsed_time": "9:42:41", "remaining_time": "16:02:29", "throughput": 8367.52, "total_tokens": 292538504} {"current_steps": 287400, "total_steps": 761865, "loss": 1.9634, "lr": 6.88109526100827e-07, "epoch": 5.658482802071233, "percentage": 37.72, "elapsed_time": "9:42:52", "remaining_time": "16:02:16", "throughput": 8367.65, "total_tokens": 292640904} {"current_steps": 287500, "total_steps": 761865, "loss": 1.9478, "lr": 6.879184775551556e-07, "epoch": 5.660451654820736, "percentage": 37.74, "elapsed_time": "9:43:04", "remaining_time": "16:02:03", "throughput": 8367.79, "total_tokens": 292743304} {"current_steps": 287600, "total_steps": 761865, "loss": 1.988, "lr": 6.87727397055532e-07, "epoch": 5.662420507570239, "percentage": 37.75, "elapsed_time": "9:43:16", "remaining_time": "16:01:50", "throughput": 8367.9, "total_tokens": 292844304} {"current_steps": 287700, "total_steps": 761865, "loss": 1.986, "lr": 6.875362846344479e-07, "epoch": 5.664389360319742, "percentage": 37.76, "elapsed_time": "9:43:27", "remaining_time": "16:01:37", "throughput": 8368.02, "total_tokens": 292945192} {"current_steps": 287800, "total_steps": 761865, "loss": 1.9173, "lr": 6.873451403244004e-07, "epoch": 5.666358213069245, "percentage": 37.78, "elapsed_time": "9:43:39", "remaining_time": "16:01:24", "throughput": 8368.14, "total_tokens": 293047176} {"current_steps": 287900, "total_steps": 761865, "loss": 2.0048, "lr": 6.871539641578919e-07, "epoch": 5.6683270658187475, "percentage": 37.79, "elapsed_time": "9:43:51", "remaining_time": "16:01:10", "throughput": 8368.26, "total_tokens": 293148896} {"current_steps": 288000, "total_steps": 761865, "loss": 1.9975, "lr": 6.869627561674303e-07, "epoch": 5.67029591856825, "percentage": 37.8, "elapsed_time": "9:44:02", "remaining_time": "16:00:58", "throughput": 8368.4, "total_tokens": 293251296} {"current_steps": 288100, "total_steps": 761865, "loss": 1.9658, "lr": 6.86771516385529e-07, "epoch": 5.672264771317753, "percentage": 37.82, "elapsed_time": "9:44:14", "remaining_time": "16:00:45", "throughput": 8368.53, "total_tokens": 293353696} {"current_steps": 288200, "total_steps": 761865, "loss": 1.9763, "lr": 6.865802448447064e-07, "epoch": 5.674233624067256, "percentage": 37.83, "elapsed_time": "9:44:25", "remaining_time": "16:00:31", "throughput": 8368.64, "total_tokens": 293454416} {"current_steps": 288300, "total_steps": 761865, "loss": 2.0191, "lr": 6.863889415774872e-07, "epoch": 5.6762024768167585, "percentage": 37.84, "elapsed_time": "9:44:37", "remaining_time": "16:00:18", "throughput": 8368.75, "total_tokens": 293555320} {"current_steps": 288400, "total_steps": 761865, "loss": 1.9844, "lr": 6.861976066164004e-07, "epoch": 5.678171329566261, "percentage": 37.85, "elapsed_time": "9:44:49", "remaining_time": "16:00:05", "throughput": 8368.87, "total_tokens": 293657720} {"current_steps": 288500, "total_steps": 761865, "loss": 2.0506, "lr": 6.86006239993981e-07, "epoch": 5.680140182315765, "percentage": 37.87, "elapsed_time": "9:45:00", "remaining_time": "15:59:53", "throughput": 8369.0, "total_tokens": 293760120} {"current_steps": 288600, "total_steps": 761865, "loss": 1.961, "lr": 6.858148417427693e-07, "epoch": 5.682109035065268, "percentage": 37.88, "elapsed_time": "9:45:12", "remaining_time": "15:59:40", "throughput": 8369.13, "total_tokens": 293862520} {"current_steps": 288700, "total_steps": 761865, "loss": 1.9825, "lr": 6.856234118953112e-07, "epoch": 5.68407788781477, "percentage": 37.89, "elapsed_time": "9:45:24", "remaining_time": "15:59:27", "throughput": 8369.25, "total_tokens": 293964288} {"current_steps": 288800, "total_steps": 761865, "loss": 1.9683, "lr": 6.854319504841575e-07, "epoch": 5.686046740564273, "percentage": 37.91, "elapsed_time": "9:45:36", "remaining_time": "15:59:14", "throughput": 8369.38, "total_tokens": 294066688} {"current_steps": 288900, "total_steps": 761865, "loss": 2.0323, "lr": 6.852404575418647e-07, "epoch": 5.688015593313776, "percentage": 37.92, "elapsed_time": "9:45:47", "remaining_time": "15:59:01", "throughput": 8369.5, "total_tokens": 294168744} {"current_steps": 289000, "total_steps": 761865, "loss": 2.0024, "lr": 6.850489331009942e-07, "epoch": 5.689984446063279, "percentage": 37.93, "elapsed_time": "9:45:59", "remaining_time": "15:58:47", "throughput": 8369.61, "total_tokens": 294269424} {"current_steps": 289100, "total_steps": 761865, "loss": 1.9956, "lr": 6.848573771941137e-07, "epoch": 5.6919532988127814, "percentage": 37.95, "elapsed_time": "9:46:10", "remaining_time": "15:58:34", "throughput": 8369.74, "total_tokens": 294371160} {"current_steps": 289200, "total_steps": 761865, "loss": 2.0071, "lr": 6.846657898537951e-07, "epoch": 5.693922151562285, "percentage": 37.96, "elapsed_time": "9:46:22", "remaining_time": "15:58:22", "throughput": 8369.86, "total_tokens": 294473560} {"current_steps": 289300, "total_steps": 761865, "loss": 1.9922, "lr": 6.844741711126165e-07, "epoch": 5.695891004311788, "percentage": 37.97, "elapsed_time": "9:46:34", "remaining_time": "15:58:09", "throughput": 8369.99, "total_tokens": 294575816} {"current_steps": 289400, "total_steps": 761865, "loss": 1.9967, "lr": 6.842825210031612e-07, "epoch": 5.697859857061291, "percentage": 37.99, "elapsed_time": "9:46:45", "remaining_time": "15:57:56", "throughput": 8370.12, "total_tokens": 294678216} {"current_steps": 289500, "total_steps": 761865, "loss": 1.9757, "lr": 6.840908395580174e-07, "epoch": 5.699828709810793, "percentage": 38.0, "elapsed_time": "9:46:57", "remaining_time": "15:57:43", "throughput": 8370.25, "total_tokens": 294780616} {"current_steps": 289600, "total_steps": 761865, "loss": 1.9713, "lr": 6.838991268097791e-07, "epoch": 5.701797562560296, "percentage": 38.01, "elapsed_time": "9:47:09", "remaining_time": "15:57:30", "throughput": 8370.38, "total_tokens": 294883016} {"current_steps": 289700, "total_steps": 761865, "loss": 1.9793, "lr": 6.837073827910453e-07, "epoch": 5.703766415309799, "percentage": 38.03, "elapsed_time": "9:47:20", "remaining_time": "15:57:17", "throughput": 8370.5, "total_tokens": 294984552} {"current_steps": 289800, "total_steps": 761865, "loss": 1.9934, "lr": 6.835156075344206e-07, "epoch": 5.705735268059302, "percentage": 38.04, "elapsed_time": "9:47:32", "remaining_time": "15:57:04", "throughput": 8370.61, "total_tokens": 295085672} {"current_steps": 289900, "total_steps": 761865, "loss": 1.9639, "lr": 6.833238010725146e-07, "epoch": 5.707704120808804, "percentage": 38.05, "elapsed_time": "9:47:44", "remaining_time": "15:56:51", "throughput": 8370.74, "total_tokens": 295188072} {"current_steps": 290000, "total_steps": 761865, "loss": 1.9379, "lr": 6.831319634379426e-07, "epoch": 5.709672973558307, "percentage": 38.06, "elapsed_time": "9:47:55", "remaining_time": "15:56:38", "throughput": 8370.87, "total_tokens": 295290472} {"current_steps": 290100, "total_steps": 761865, "loss": 1.9655, "lr": 6.829400946633245e-07, "epoch": 5.711641826307811, "percentage": 38.08, "elapsed_time": "9:48:08", "remaining_time": "15:56:26", "throughput": 8370.87, "total_tokens": 295392408} {"current_steps": 290200, "total_steps": 761865, "loss": 1.9791, "lr": 6.827481947812865e-07, "epoch": 5.713610679057314, "percentage": 38.09, "elapsed_time": "9:48:19", "remaining_time": "15:56:12", "throughput": 8370.98, "total_tokens": 295493256} {"current_steps": 290300, "total_steps": 761865, "loss": 1.9498, "lr": 6.825562638244593e-07, "epoch": 5.715579531806816, "percentage": 38.1, "elapsed_time": "9:48:31", "remaining_time": "15:55:59", "throughput": 8371.1, "total_tokens": 295594432} {"current_steps": 290400, "total_steps": 761865, "loss": 1.9931, "lr": 6.823643018254794e-07, "epoch": 5.717548384556319, "percentage": 38.12, "elapsed_time": "9:48:42", "remaining_time": "15:55:46", "throughput": 8371.23, "total_tokens": 295696832} {"current_steps": 290500, "total_steps": 761865, "loss": 1.9763, "lr": 6.821723088169879e-07, "epoch": 5.719517237305822, "percentage": 38.13, "elapsed_time": "9:48:54", "remaining_time": "15:55:33", "throughput": 8371.35, "total_tokens": 295798408} {"current_steps": 290600, "total_steps": 761865, "loss": 1.9509, "lr": 6.819802848316318e-07, "epoch": 5.721486090055325, "percentage": 38.14, "elapsed_time": "9:49:06", "remaining_time": "15:55:20", "throughput": 8371.48, "total_tokens": 295900808} {"current_steps": 290700, "total_steps": 761865, "loss": 1.9939, "lr": 6.817882299020631e-07, "epoch": 5.723454942804827, "percentage": 38.16, "elapsed_time": "9:49:17", "remaining_time": "15:55:07", "throughput": 8371.61, "total_tokens": 296002648} {"current_steps": 290800, "total_steps": 761865, "loss": 2.0672, "lr": 6.815961440609393e-07, "epoch": 5.72542379555433, "percentage": 38.17, "elapsed_time": "9:49:29", "remaining_time": "15:54:54", "throughput": 8371.72, "total_tokens": 296103424} {"current_steps": 290900, "total_steps": 761865, "loss": 1.978, "lr": 6.814040273409229e-07, "epoch": 5.727392648303834, "percentage": 38.18, "elapsed_time": "9:49:41", "remaining_time": "15:54:41", "throughput": 8371.83, "total_tokens": 296204248} {"current_steps": 291000, "total_steps": 761865, "loss": 2.104, "lr": 6.812118797746817e-07, "epoch": 5.7293615010533365, "percentage": 38.2, "elapsed_time": "9:49:52", "remaining_time": "15:54:28", "throughput": 8371.95, "total_tokens": 296305504} {"current_steps": 291100, "total_steps": 761865, "loss": 1.9739, "lr": 6.810197013948885e-07, "epoch": 5.731330353802839, "percentage": 38.21, "elapsed_time": "9:50:04", "remaining_time": "15:54:15", "throughput": 8372.08, "total_tokens": 296407904} {"current_steps": 291200, "total_steps": 761865, "loss": 1.9535, "lr": 6.808274922342221e-07, "epoch": 5.733299206552342, "percentage": 38.22, "elapsed_time": "9:50:15", "remaining_time": "15:54:02", "throughput": 8372.18, "total_tokens": 296507648} {"current_steps": 291300, "total_steps": 761865, "loss": 1.9836, "lr": 6.806352523253655e-07, "epoch": 5.735268059301845, "percentage": 38.24, "elapsed_time": "9:50:27", "remaining_time": "15:53:49", "throughput": 8372.3, "total_tokens": 296609736} {"current_steps": 291400, "total_steps": 761865, "loss": 2.0004, "lr": 6.804429817010082e-07, "epoch": 5.737236912051348, "percentage": 38.25, "elapsed_time": "9:50:39", "remaining_time": "15:53:36", "throughput": 8372.42, "total_tokens": 296710632} {"current_steps": 291500, "total_steps": 761865, "loss": 2.0035, "lr": 6.802506803938436e-07, "epoch": 5.73920576480085, "percentage": 38.26, "elapsed_time": "9:50:50", "remaining_time": "15:53:23", "throughput": 8372.53, "total_tokens": 296811680} {"current_steps": 291600, "total_steps": 761865, "loss": 1.9697, "lr": 6.800583484365712e-07, "epoch": 5.741174617550353, "percentage": 38.27, "elapsed_time": "9:51:02", "remaining_time": "15:53:10", "throughput": 8372.64, "total_tokens": 296912344} {"current_steps": 291700, "total_steps": 761865, "loss": 1.9509, "lr": 6.798659858618951e-07, "epoch": 5.743143470299856, "percentage": 38.29, "elapsed_time": "9:51:13", "remaining_time": "15:52:57", "throughput": 8372.76, "total_tokens": 297013824} {"current_steps": 291800, "total_steps": 761865, "loss": 2.0054, "lr": 6.796735927025255e-07, "epoch": 5.7451123230493595, "percentage": 38.3, "elapsed_time": "9:51:25", "remaining_time": "15:52:44", "throughput": 8372.89, "total_tokens": 297116224} {"current_steps": 291900, "total_steps": 761865, "loss": 2.0063, "lr": 6.794811689911766e-07, "epoch": 5.747081175798862, "percentage": 38.31, "elapsed_time": "9:51:37", "remaining_time": "15:52:31", "throughput": 8373.0, "total_tokens": 297217696} {"current_steps": 292000, "total_steps": 761865, "loss": 1.9432, "lr": 6.792887147605689e-07, "epoch": 5.749050028548365, "percentage": 38.33, "elapsed_time": "9:51:48", "remaining_time": "15:52:18", "throughput": 8373.13, "total_tokens": 297319328} {"current_steps": 292100, "total_steps": 761865, "loss": 1.983, "lr": 6.790962300434273e-07, "epoch": 5.751018881297868, "percentage": 38.34, "elapsed_time": "9:52:00", "remaining_time": "15:52:05", "throughput": 8373.25, "total_tokens": 297421288} {"current_steps": 292200, "total_steps": 761865, "loss": 1.9708, "lr": 6.789037148724826e-07, "epoch": 5.7529877340473705, "percentage": 38.35, "elapsed_time": "9:52:12", "remaining_time": "15:51:52", "throughput": 8373.38, "total_tokens": 297523688} {"current_steps": 292300, "total_steps": 761865, "loss": 1.9471, "lr": 6.787111692804698e-07, "epoch": 5.754956586796873, "percentage": 38.37, "elapsed_time": "9:52:23", "remaining_time": "15:51:39", "throughput": 8373.51, "total_tokens": 297624984} {"current_steps": 292400, "total_steps": 761865, "loss": 2.043, "lr": 6.785185933001302e-07, "epoch": 5.756925439546376, "percentage": 38.38, "elapsed_time": "9:52:35", "remaining_time": "15:51:26", "throughput": 8373.64, "total_tokens": 297727384} {"current_steps": 292500, "total_steps": 761865, "loss": 1.924, "lr": 6.783259869642094e-07, "epoch": 5.75889429229588, "percentage": 38.39, "elapsed_time": "9:52:46", "remaining_time": "15:51:13", "throughput": 8373.76, "total_tokens": 297829080} {"current_steps": 292600, "total_steps": 761865, "loss": 1.9722, "lr": 6.781333503054587e-07, "epoch": 5.760863145045382, "percentage": 38.41, "elapsed_time": "9:52:58", "remaining_time": "15:51:00", "throughput": 8373.89, "total_tokens": 297931480} {"current_steps": 292700, "total_steps": 761865, "loss": 2.0215, "lr": 6.779406833566341e-07, "epoch": 5.762831997794885, "percentage": 38.42, "elapsed_time": "9:53:10", "remaining_time": "15:50:47", "throughput": 8374.01, "total_tokens": 298033880} {"current_steps": 292800, "total_steps": 761865, "loss": 1.9846, "lr": 6.777479861504973e-07, "epoch": 5.764800850544388, "percentage": 38.43, "elapsed_time": "9:53:21", "remaining_time": "15:50:34", "throughput": 8374.13, "total_tokens": 298135456} {"current_steps": 292900, "total_steps": 761865, "loss": 1.981, "lr": 6.775552587198144e-07, "epoch": 5.766769703293891, "percentage": 38.45, "elapsed_time": "9:53:33", "remaining_time": "15:50:21", "throughput": 8374.26, "total_tokens": 298237856} {"current_steps": 293000, "total_steps": 761865, "loss": 2.046, "lr": 6.773625010973576e-07, "epoch": 5.7687385560433935, "percentage": 38.46, "elapsed_time": "9:53:45", "remaining_time": "15:50:08", "throughput": 8374.36, "total_tokens": 298338064} {"current_steps": 293100, "total_steps": 761865, "loss": 2.0324, "lr": 6.771697133159033e-07, "epoch": 5.770707408792896, "percentage": 38.47, "elapsed_time": "9:53:56", "remaining_time": "15:49:55", "throughput": 8374.47, "total_tokens": 298438440} {"current_steps": 293200, "total_steps": 761865, "loss": 1.9919, "lr": 6.769768954082335e-07, "epoch": 5.772676261542399, "percentage": 38.48, "elapsed_time": "9:54:08", "remaining_time": "15:49:42", "throughput": 8374.6, "total_tokens": 298540840} {"current_steps": 293300, "total_steps": 761865, "loss": 2.0144, "lr": 6.767840474071354e-07, "epoch": 5.774645114291902, "percentage": 38.5, "elapsed_time": "9:54:20", "remaining_time": "15:49:29", "throughput": 8374.72, "total_tokens": 298643168} {"current_steps": 293400, "total_steps": 761865, "loss": 1.9693, "lr": 6.76591169345401e-07, "epoch": 5.7766139670414045, "percentage": 38.51, "elapsed_time": "9:54:31", "remaining_time": "15:49:16", "throughput": 8374.85, "total_tokens": 298745568} {"current_steps": 293500, "total_steps": 761865, "loss": 1.9826, "lr": 6.763982612558279e-07, "epoch": 5.778582819790908, "percentage": 38.52, "elapsed_time": "9:54:43", "remaining_time": "15:49:03", "throughput": 8374.98, "total_tokens": 298847968} {"current_steps": 293600, "total_steps": 761865, "loss": 2.0128, "lr": 6.762053231712181e-07, "epoch": 5.780551672540411, "percentage": 38.54, "elapsed_time": "9:54:55", "remaining_time": "15:48:50", "throughput": 8375.08, "total_tokens": 298948504} {"current_steps": 293700, "total_steps": 761865, "loss": 2.0273, "lr": 6.760123551243795e-07, "epoch": 5.782520525289914, "percentage": 38.55, "elapsed_time": "9:55:06", "remaining_time": "15:48:37", "throughput": 8375.19, "total_tokens": 299049216} {"current_steps": 293800, "total_steps": 761865, "loss": 1.9591, "lr": 6.758193571481242e-07, "epoch": 5.784489378039416, "percentage": 38.56, "elapsed_time": "9:55:18", "remaining_time": "15:48:24", "throughput": 8375.31, "total_tokens": 299151016} {"current_steps": 293900, "total_steps": 761865, "loss": 2.005, "lr": 6.756263292752703e-07, "epoch": 5.786458230788919, "percentage": 38.58, "elapsed_time": "9:55:29", "remaining_time": "15:48:11", "throughput": 8375.43, "total_tokens": 299252600} {"current_steps": 294000, "total_steps": 761865, "loss": 1.9876, "lr": 6.754332715386403e-07, "epoch": 5.788427083538422, "percentage": 38.59, "elapsed_time": "9:55:41", "remaining_time": "15:47:58", "throughput": 8375.56, "total_tokens": 299354504} {"current_steps": 294100, "total_steps": 761865, "loss": 1.9929, "lr": 6.752401839710623e-07, "epoch": 5.790395936287925, "percentage": 38.6, "elapsed_time": "9:55:53", "remaining_time": "15:47:45", "throughput": 8375.69, "total_tokens": 299456624} {"current_steps": 294200, "total_steps": 761865, "loss": 1.9901, "lr": 6.750470666053689e-07, "epoch": 5.792364789037428, "percentage": 38.62, "elapsed_time": "9:56:04", "remaining_time": "15:47:32", "throughput": 8375.81, "total_tokens": 299559024} {"current_steps": 294300, "total_steps": 761865, "loss": 1.9729, "lr": 6.748539194743983e-07, "epoch": 5.794333641786931, "percentage": 38.63, "elapsed_time": "9:56:16", "remaining_time": "15:47:19", "throughput": 8375.93, "total_tokens": 299660120} {"current_steps": 294400, "total_steps": 761865, "loss": 2.0085, "lr": 6.746607426109935e-07, "epoch": 5.796302494536434, "percentage": 38.64, "elapsed_time": "9:56:27", "remaining_time": "15:47:06", "throughput": 8376.04, "total_tokens": 299761664} {"current_steps": 294500, "total_steps": 761865, "loss": 1.9446, "lr": 6.744675360480026e-07, "epoch": 5.798271347285937, "percentage": 38.66, "elapsed_time": "9:56:39", "remaining_time": "15:46:53", "throughput": 8376.17, "total_tokens": 299864064} {"current_steps": 294600, "total_steps": 761865, "loss": 1.9954, "lr": 6.742742998182786e-07, "epoch": 5.800240200035439, "percentage": 38.67, "elapsed_time": "9:56:51", "remaining_time": "15:46:40", "throughput": 8376.3, "total_tokens": 299966464} {"current_steps": 294700, "total_steps": 761865, "loss": 1.9703, "lr": 6.740810339546801e-07, "epoch": 5.802209052784942, "percentage": 38.68, "elapsed_time": "9:57:03", "remaining_time": "15:46:27", "throughput": 8376.43, "total_tokens": 300068864} {"current_steps": 294800, "total_steps": 761865, "loss": 1.9419, "lr": 6.738877384900698e-07, "epoch": 5.804177905534445, "percentage": 38.69, "elapsed_time": "9:57:14", "remaining_time": "15:46:14", "throughput": 8376.56, "total_tokens": 300171264} {"current_steps": 294900, "total_steps": 761865, "loss": 1.9759, "lr": 6.736944134573162e-07, "epoch": 5.806146758283948, "percentage": 38.71, "elapsed_time": "9:57:26", "remaining_time": "15:46:01", "throughput": 8376.68, "total_tokens": 300273664} {"current_steps": 295000, "total_steps": 761865, "loss": 2.006, "lr": 6.735010588892926e-07, "epoch": 5.80811561103345, "percentage": 38.72, "elapsed_time": "9:57:37", "remaining_time": "15:45:48", "throughput": 8376.8, "total_tokens": 300375192} {"current_steps": 295100, "total_steps": 761865, "loss": 1.9794, "lr": 6.733076748188775e-07, "epoch": 5.810084463782953, "percentage": 38.73, "elapsed_time": "9:57:50", "remaining_time": "15:45:36", "throughput": 8376.77, "total_tokens": 300475400} {"current_steps": 295200, "total_steps": 761865, "loss": 1.9873, "lr": 6.731142612789539e-07, "epoch": 5.812053316532457, "percentage": 38.75, "elapsed_time": "9:58:01", "remaining_time": "15:45:23", "throughput": 8376.9, "total_tokens": 300577360} {"current_steps": 295300, "total_steps": 761865, "loss": 2.0005, "lr": 6.729208183024102e-07, "epoch": 5.81402216928196, "percentage": 38.76, "elapsed_time": "9:58:13", "remaining_time": "15:45:10", "throughput": 8377.03, "total_tokens": 300679760} {"current_steps": 295400, "total_steps": 761865, "loss": 1.9458, "lr": 6.727273459221399e-07, "epoch": 5.815991022031462, "percentage": 38.77, "elapsed_time": "9:58:25", "remaining_time": "15:44:57", "throughput": 8377.15, "total_tokens": 300782160} {"current_steps": 295500, "total_steps": 761865, "loss": 1.9488, "lr": 6.725338441710413e-07, "epoch": 5.817959874780965, "percentage": 38.79, "elapsed_time": "9:58:36", "remaining_time": "15:44:44", "throughput": 8377.28, "total_tokens": 300884560} {"current_steps": 295600, "total_steps": 761865, "loss": 1.9835, "lr": 6.723403130820177e-07, "epoch": 5.819928727530468, "percentage": 38.8, "elapsed_time": "9:58:48", "remaining_time": "15:44:31", "throughput": 8377.4, "total_tokens": 300986424} {"current_steps": 295700, "total_steps": 761865, "loss": 1.9954, "lr": 6.721467526879775e-07, "epoch": 5.821897580279971, "percentage": 38.81, "elapsed_time": "9:59:00", "remaining_time": "15:44:18", "throughput": 8377.53, "total_tokens": 301088824} {"current_steps": 295800, "total_steps": 761865, "loss": 1.9929, "lr": 6.719531630218339e-07, "epoch": 5.823866433029473, "percentage": 38.83, "elapsed_time": "9:59:11", "remaining_time": "15:44:05", "throughput": 8377.65, "total_tokens": 301191224} {"current_steps": 295900, "total_steps": 761865, "loss": 1.9756, "lr": 6.717595441165053e-07, "epoch": 5.825835285778977, "percentage": 38.84, "elapsed_time": "9:59:23", "remaining_time": "15:43:52", "throughput": 8377.78, "total_tokens": 301293624} {"current_steps": 296000, "total_steps": 761865, "loss": 1.9704, "lr": 6.715658960049148e-07, "epoch": 5.82780413852848, "percentage": 38.85, "elapsed_time": "9:59:35", "remaining_time": "15:43:40", "throughput": 8377.9, "total_tokens": 301395480} {"current_steps": 296100, "total_steps": 761865, "loss": 1.9791, "lr": 6.71372218719991e-07, "epoch": 5.8297729912779825, "percentage": 38.87, "elapsed_time": "9:59:46", "remaining_time": "15:43:27", "throughput": 8378.01, "total_tokens": 301497128} {"current_steps": 296200, "total_steps": 761865, "loss": 2.0157, "lr": 6.711785122946665e-07, "epoch": 5.831741844027485, "percentage": 38.88, "elapsed_time": "9:59:58", "remaining_time": "15:43:14", "throughput": 8378.13, "total_tokens": 301598712} {"current_steps": 296300, "total_steps": 761865, "loss": 2.0557, "lr": 6.709847767618799e-07, "epoch": 5.833710696776988, "percentage": 38.89, "elapsed_time": "10:00:10", "remaining_time": "15:43:01", "throughput": 8378.25, "total_tokens": 301701112} {"current_steps": 296400, "total_steps": 761865, "loss": 1.9887, "lr": 6.707910121545741e-07, "epoch": 5.835679549526491, "percentage": 38.9, "elapsed_time": "10:00:21", "remaining_time": "15:42:48", "throughput": 8378.35, "total_tokens": 301801120} {"current_steps": 296500, "total_steps": 761865, "loss": 1.973, "lr": 6.705972185056974e-07, "epoch": 5.837648402275994, "percentage": 38.92, "elapsed_time": "10:00:33", "remaining_time": "15:42:35", "throughput": 8378.47, "total_tokens": 301902472} {"current_steps": 296600, "total_steps": 761865, "loss": 2.0214, "lr": 6.704033958482023e-07, "epoch": 5.839617255025496, "percentage": 38.93, "elapsed_time": "10:00:44", "remaining_time": "15:42:21", "throughput": 8378.56, "total_tokens": 302002760} {"current_steps": 296700, "total_steps": 761865, "loss": 2.0106, "lr": 6.702095442150473e-07, "epoch": 5.841586107774999, "percentage": 38.94, "elapsed_time": "10:00:56", "remaining_time": "15:42:09", "throughput": 8378.69, "total_tokens": 302105160} {"current_steps": 296800, "total_steps": 761865, "loss": 2.0012, "lr": 6.700156636391946e-07, "epoch": 5.843554960524503, "percentage": 38.96, "elapsed_time": "10:01:07", "remaining_time": "15:41:55", "throughput": 8378.8, "total_tokens": 302206168} {"current_steps": 296900, "total_steps": 761865, "loss": 1.9686, "lr": 6.698217541536126e-07, "epoch": 5.8455238132740055, "percentage": 38.97, "elapsed_time": "10:01:19", "remaining_time": "15:41:42", "throughput": 8378.92, "total_tokens": 302307472} {"current_steps": 297000, "total_steps": 761865, "loss": 1.9898, "lr": 6.696278157912734e-07, "epoch": 5.847492666023508, "percentage": 38.98, "elapsed_time": "10:01:31", "remaining_time": "15:41:30", "throughput": 8379.04, "total_tokens": 302409872} {"current_steps": 297100, "total_steps": 761865, "loss": 1.9624, "lr": 6.69433848585155e-07, "epoch": 5.849461518773011, "percentage": 39.0, "elapsed_time": "10:01:42", "remaining_time": "15:41:17", "throughput": 8379.16, "total_tokens": 302512272} {"current_steps": 297200, "total_steps": 761865, "loss": 1.9856, "lr": 6.692398525682396e-07, "epoch": 5.851430371522514, "percentage": 39.01, "elapsed_time": "10:01:54", "remaining_time": "15:41:04", "throughput": 8379.27, "total_tokens": 302613304} {"current_steps": 297300, "total_steps": 761865, "loss": 1.9771, "lr": 6.690458277735147e-07, "epoch": 5.8533992242720165, "percentage": 39.02, "elapsed_time": "10:02:06", "remaining_time": "15:40:51", "throughput": 8379.4, "total_tokens": 302715704} {"current_steps": 297400, "total_steps": 761865, "loss": 1.9781, "lr": 6.688517742339726e-07, "epoch": 5.855368077021519, "percentage": 39.04, "elapsed_time": "10:02:17", "remaining_time": "15:40:38", "throughput": 8379.52, "total_tokens": 302817512} {"current_steps": 297500, "total_steps": 761865, "loss": 1.9988, "lr": 6.686576919826104e-07, "epoch": 5.857336929771022, "percentage": 39.05, "elapsed_time": "10:02:29", "remaining_time": "15:40:25", "throughput": 8379.62, "total_tokens": 302918136} {"current_steps": 297600, "total_steps": 761865, "loss": 1.9895, "lr": 6.684635810524303e-07, "epoch": 5.859305782520526, "percentage": 39.06, "elapsed_time": "10:02:40", "remaining_time": "15:40:12", "throughput": 8379.73, "total_tokens": 303019304} {"current_steps": 297700, "total_steps": 761865, "loss": 1.986, "lr": 6.682694414764391e-07, "epoch": 5.8612746352700285, "percentage": 39.08, "elapsed_time": "10:02:52", "remaining_time": "15:39:59", "throughput": 8379.86, "total_tokens": 303121704} {"current_steps": 297800, "total_steps": 761865, "loss": 1.9639, "lr": 6.680752732876487e-07, "epoch": 5.863243488019531, "percentage": 39.09, "elapsed_time": "10:03:04", "remaining_time": "15:39:46", "throughput": 8379.95, "total_tokens": 303221752} {"current_steps": 297900, "total_steps": 761865, "loss": 2.0142, "lr": 6.678810765190756e-07, "epoch": 5.865212340769034, "percentage": 39.1, "elapsed_time": "10:03:15", "remaining_time": "15:39:33", "throughput": 8380.07, "total_tokens": 303323392} {"current_steps": 298000, "total_steps": 761865, "loss": 1.9939, "lr": 6.676868512037414e-07, "epoch": 5.867181193518537, "percentage": 39.11, "elapsed_time": "10:03:27", "remaining_time": "15:39:20", "throughput": 8380.19, "total_tokens": 303425792} {"current_steps": 298100, "total_steps": 761865, "loss": 1.966, "lr": 6.674925973746725e-07, "epoch": 5.8691500462680395, "percentage": 39.13, "elapsed_time": "10:03:39", "remaining_time": "15:39:07", "throughput": 8380.31, "total_tokens": 303527608} {"current_steps": 298200, "total_steps": 761865, "loss": 2.004, "lr": 6.672983150649003e-07, "epoch": 5.871118899017542, "percentage": 39.14, "elapsed_time": "10:03:50", "remaining_time": "15:38:54", "throughput": 8380.42, "total_tokens": 303629160} {"current_steps": 298300, "total_steps": 761865, "loss": 1.9543, "lr": 6.671040043074605e-07, "epoch": 5.873087751767045, "percentage": 39.15, "elapsed_time": "10:04:02", "remaining_time": "15:38:41", "throughput": 8380.54, "total_tokens": 303731464} {"current_steps": 298400, "total_steps": 761865, "loss": 1.9276, "lr": 6.669096651353941e-07, "epoch": 5.875056604516548, "percentage": 39.17, "elapsed_time": "10:04:14", "remaining_time": "15:38:28", "throughput": 8380.66, "total_tokens": 303833104} {"current_steps": 298500, "total_steps": 761865, "loss": 1.9594, "lr": 6.66715297581747e-07, "epoch": 5.877025457266051, "percentage": 39.18, "elapsed_time": "10:04:25", "remaining_time": "15:38:15", "throughput": 8380.79, "total_tokens": 303935504} {"current_steps": 298600, "total_steps": 761865, "loss": 1.9259, "lr": 6.665209016795698e-07, "epoch": 5.878994310015554, "percentage": 39.19, "elapsed_time": "10:04:37", "remaining_time": "15:38:02", "throughput": 8380.9, "total_tokens": 304037304} {"current_steps": 298700, "total_steps": 761865, "loss": 2.0013, "lr": 6.663264774619177e-07, "epoch": 5.880963162765057, "percentage": 39.21, "elapsed_time": "10:04:49", "remaining_time": "15:37:49", "throughput": 8381.02, "total_tokens": 304138928} {"current_steps": 298800, "total_steps": 761865, "loss": 1.9836, "lr": 6.66132024961851e-07, "epoch": 5.88293201551456, "percentage": 39.22, "elapsed_time": "10:05:00", "remaining_time": "15:37:36", "throughput": 8381.14, "total_tokens": 304241328} {"current_steps": 298900, "total_steps": 761865, "loss": 1.9933, "lr": 6.659375442124346e-07, "epoch": 5.8849008682640624, "percentage": 39.23, "elapsed_time": "10:05:12", "remaining_time": "15:37:24", "throughput": 8381.27, "total_tokens": 304343728} {"current_steps": 299000, "total_steps": 761865, "loss": 2.0005, "lr": 6.657430352467384e-07, "epoch": 5.886869721013565, "percentage": 39.25, "elapsed_time": "10:05:24", "remaining_time": "15:37:11", "throughput": 8381.39, "total_tokens": 304446128} {"current_steps": 299100, "total_steps": 761865, "loss": 2.0001, "lr": 6.655484980978369e-07, "epoch": 5.888838573763068, "percentage": 39.26, "elapsed_time": "10:05:35", "remaining_time": "15:36:58", "throughput": 8381.5, "total_tokens": 304547992} {"current_steps": 299200, "total_steps": 761865, "loss": 2.0099, "lr": 6.653539327988099e-07, "epoch": 5.890807426512572, "percentage": 39.27, "elapsed_time": "10:05:47", "remaining_time": "15:36:45", "throughput": 8381.63, "total_tokens": 304649976} {"current_steps": 299300, "total_steps": 761865, "loss": 1.9703, "lr": 6.65159339382741e-07, "epoch": 5.892776279262074, "percentage": 39.29, "elapsed_time": "10:05:58", "remaining_time": "15:36:32", "throughput": 8381.75, "total_tokens": 304751824} {"current_steps": 299400, "total_steps": 761865, "loss": 2.0043, "lr": 6.649647178827196e-07, "epoch": 5.894745132011577, "percentage": 39.3, "elapsed_time": "10:06:10", "remaining_time": "15:36:19", "throughput": 8381.87, "total_tokens": 304854224} {"current_steps": 299500, "total_steps": 761865, "loss": 1.9998, "lr": 6.647700683318393e-07, "epoch": 5.89671398476108, "percentage": 39.31, "elapsed_time": "10:06:22", "remaining_time": "15:36:06", "throughput": 8382.0, "total_tokens": 304956624} {"current_steps": 299600, "total_steps": 761865, "loss": 1.9958, "lr": 6.645753907631985e-07, "epoch": 5.898682837510583, "percentage": 39.32, "elapsed_time": "10:06:34", "remaining_time": "15:35:53", "throughput": 8382.12, "total_tokens": 305059024} {"current_steps": 299700, "total_steps": 761865, "loss": 1.9783, "lr": 6.643806852099008e-07, "epoch": 5.900651690260085, "percentage": 39.34, "elapsed_time": "10:06:45", "remaining_time": "15:35:40", "throughput": 8382.22, "total_tokens": 305159496} {"current_steps": 299800, "total_steps": 761865, "loss": 1.9963, "lr": 6.641859517050539e-07, "epoch": 5.902620543009588, "percentage": 39.35, "elapsed_time": "10:06:57", "remaining_time": "15:35:27", "throughput": 8382.34, "total_tokens": 305261896} {"current_steps": 299900, "total_steps": 761865, "loss": 2.0045, "lr": 6.639911902817706e-07, "epoch": 5.904589395759091, "percentage": 39.36, "elapsed_time": "10:07:08", "remaining_time": "15:35:15", "throughput": 8382.47, "total_tokens": 305364296} {"current_steps": 300000, "total_steps": 761865, "loss": 1.9278, "lr": 6.637964009731688e-07, "epoch": 5.906558248508594, "percentage": 39.38, "elapsed_time": "10:07:20", "remaining_time": "15:35:02", "throughput": 8382.58, "total_tokens": 305466144} {"current_steps": 300100, "total_steps": 761865, "loss": 1.9974, "lr": 6.636015838123705e-07, "epoch": 5.908527101258096, "percentage": 39.39, "elapsed_time": "10:07:32", "remaining_time": "15:34:50", "throughput": 8382.58, "total_tokens": 305568544} {"current_steps": 300200, "total_steps": 761865, "loss": 1.9641, "lr": 6.634067388325027e-07, "epoch": 5.9104959540076, "percentage": 39.4, "elapsed_time": "10:07:44", "remaining_time": "15:34:37", "throughput": 8382.7, "total_tokens": 305670424} {"current_steps": 300300, "total_steps": 761865, "loss": 1.9954, "lr": 6.632118660666971e-07, "epoch": 5.912464806757103, "percentage": 39.42, "elapsed_time": "10:07:56", "remaining_time": "15:34:24", "throughput": 8382.82, "total_tokens": 305772208} {"current_steps": 300400, "total_steps": 761865, "loss": 2.0143, "lr": 6.630169655480903e-07, "epoch": 5.914433659506606, "percentage": 39.43, "elapsed_time": "10:08:07", "remaining_time": "15:34:11", "throughput": 8382.93, "total_tokens": 305874256} {"current_steps": 300500, "total_steps": 761865, "loss": 1.9657, "lr": 6.628220373098234e-07, "epoch": 5.916402512256108, "percentage": 39.44, "elapsed_time": "10:08:19", "remaining_time": "15:33:58", "throughput": 8383.04, "total_tokens": 305975320} {"current_steps": 300600, "total_steps": 761865, "loss": 1.9915, "lr": 6.626270813850425e-07, "epoch": 5.918371365005611, "percentage": 39.46, "elapsed_time": "10:08:30", "remaining_time": "15:33:45", "throughput": 8383.15, "total_tokens": 306077192} {"current_steps": 300700, "total_steps": 761865, "loss": 1.9738, "lr": 6.624320978068981e-07, "epoch": 5.920340217755114, "percentage": 39.47, "elapsed_time": "10:08:42", "remaining_time": "15:33:32", "throughput": 8383.26, "total_tokens": 306178816} {"current_steps": 300800, "total_steps": 761865, "loss": 1.9791, "lr": 6.622370866085454e-07, "epoch": 5.922309070504617, "percentage": 39.48, "elapsed_time": "10:08:54", "remaining_time": "15:33:19", "throughput": 8383.39, "total_tokens": 306281216} {"current_steps": 300900, "total_steps": 761865, "loss": 1.9553, "lr": 6.620420478231445e-07, "epoch": 5.92427792325412, "percentage": 39.5, "elapsed_time": "10:09:05", "remaining_time": "15:33:06", "throughput": 8383.5, "total_tokens": 306382984} {"current_steps": 301000, "total_steps": 761865, "loss": 2.0037, "lr": 6.618469814838601e-07, "epoch": 5.926246776003623, "percentage": 39.51, "elapsed_time": "10:09:17", "remaining_time": "15:32:53", "throughput": 8383.6, "total_tokens": 306483880} {"current_steps": 301100, "total_steps": 761865, "loss": 1.9711, "lr": 6.616518876238616e-07, "epoch": 5.928215628753126, "percentage": 39.52, "elapsed_time": "10:09:29", "remaining_time": "15:32:40", "throughput": 8383.72, "total_tokens": 306585752} {"current_steps": 301200, "total_steps": 761865, "loss": 1.9962, "lr": 6.614567662763231e-07, "epoch": 5.930184481502629, "percentage": 39.53, "elapsed_time": "10:09:40", "remaining_time": "15:32:27", "throughput": 8383.84, "total_tokens": 306688152} {"current_steps": 301300, "total_steps": 761865, "loss": 1.9595, "lr": 6.612616174744231e-07, "epoch": 5.932153334252131, "percentage": 39.55, "elapsed_time": "10:09:52", "remaining_time": "15:32:15", "throughput": 8383.96, "total_tokens": 306790552} {"current_steps": 301400, "total_steps": 761865, "loss": 1.9946, "lr": 6.610664412513452e-07, "epoch": 5.934122187001634, "percentage": 39.56, "elapsed_time": "10:10:04", "remaining_time": "15:32:02", "throughput": 8384.07, "total_tokens": 306891424} {"current_steps": 301500, "total_steps": 761865, "loss": 1.9761, "lr": 6.608712376402777e-07, "epoch": 5.936091039751137, "percentage": 39.57, "elapsed_time": "10:10:15", "remaining_time": "15:31:49", "throughput": 8384.18, "total_tokens": 306993384} {"current_steps": 301600, "total_steps": 761865, "loss": 2.0071, "lr": 6.606760066744129e-07, "epoch": 5.93805989250064, "percentage": 39.59, "elapsed_time": "10:10:27", "remaining_time": "15:31:36", "throughput": 8384.28, "total_tokens": 307094568} {"current_steps": 301700, "total_steps": 761865, "loss": 2.0056, "lr": 6.604807483869485e-07, "epoch": 5.940028745250142, "percentage": 39.6, "elapsed_time": "10:10:39", "remaining_time": "15:31:23", "throughput": 8384.4, "total_tokens": 307196744} {"current_steps": 301800, "total_steps": 761865, "loss": 2.002, "lr": 6.602854628110863e-07, "epoch": 5.941997597999645, "percentage": 39.61, "elapsed_time": "10:10:50", "remaining_time": "15:31:10", "throughput": 8384.52, "total_tokens": 307298552} {"current_steps": 301900, "total_steps": 761865, "loss": 2.0117, "lr": 6.600901499800331e-07, "epoch": 5.943966450749149, "percentage": 39.63, "elapsed_time": "10:11:02", "remaining_time": "15:30:57", "throughput": 8384.64, "total_tokens": 307400952} {"current_steps": 302000, "total_steps": 761865, "loss": 1.9945, "lr": 6.598948099270001e-07, "epoch": 5.9459353034986515, "percentage": 39.64, "elapsed_time": "10:11:13", "remaining_time": "15:30:44", "throughput": 8384.74, "total_tokens": 307501816} {"current_steps": 302100, "total_steps": 761865, "loss": 2.0174, "lr": 6.596994426852034e-07, "epoch": 5.947904156248154, "percentage": 39.65, "elapsed_time": "10:11:25", "remaining_time": "15:30:31", "throughput": 8384.86, "total_tokens": 307604216} {"current_steps": 302200, "total_steps": 761865, "loss": 1.9804, "lr": 6.595040482878634e-07, "epoch": 5.949873008997657, "percentage": 39.67, "elapsed_time": "10:11:37", "remaining_time": "15:30:18", "throughput": 8384.97, "total_tokens": 307706408} {"current_steps": 302300, "total_steps": 761865, "loss": 1.9871, "lr": 6.593086267682052e-07, "epoch": 5.95184186174716, "percentage": 39.68, "elapsed_time": "10:11:49", "remaining_time": "15:30:06", "throughput": 8385.09, "total_tokens": 307808168} {"current_steps": 302400, "total_steps": 761865, "loss": 2.0571, "lr": 6.591131781594587e-07, "epoch": 5.9538107144966625, "percentage": 39.69, "elapsed_time": "10:12:00", "remaining_time": "15:29:52", "throughput": 8385.17, "total_tokens": 307907840} {"current_steps": 302500, "total_steps": 761865, "loss": 1.982, "lr": 6.589177024948584e-07, "epoch": 5.955779567246165, "percentage": 39.71, "elapsed_time": "10:12:12", "remaining_time": "15:29:40", "throughput": 8385.29, "total_tokens": 308010240} {"current_steps": 302600, "total_steps": 761865, "loss": 1.97, "lr": 6.587221998076429e-07, "epoch": 5.957748419995669, "percentage": 39.72, "elapsed_time": "10:12:23", "remaining_time": "15:29:27", "throughput": 8385.42, "total_tokens": 308112640} {"current_steps": 302700, "total_steps": 761865, "loss": 1.9622, "lr": 6.585266701310563e-07, "epoch": 5.959717272745172, "percentage": 39.73, "elapsed_time": "10:12:35", "remaining_time": "15:29:14", "throughput": 8385.53, "total_tokens": 308213864} {"current_steps": 302800, "total_steps": 761865, "loss": 1.9822, "lr": 6.583311134983464e-07, "epoch": 5.9616861254946745, "percentage": 39.74, "elapsed_time": "10:12:47", "remaining_time": "15:29:01", "throughput": 8385.64, "total_tokens": 308315672} {"current_steps": 302900, "total_steps": 761865, "loss": 1.9894, "lr": 6.581355299427662e-07, "epoch": 5.963654978244177, "percentage": 39.76, "elapsed_time": "10:12:58", "remaining_time": "15:28:48", "throughput": 8385.76, "total_tokens": 308418072} {"current_steps": 303000, "total_steps": 761865, "loss": 1.9726, "lr": 6.579399194975729e-07, "epoch": 5.96562383099368, "percentage": 39.77, "elapsed_time": "10:13:10", "remaining_time": "15:28:35", "throughput": 8385.88, "total_tokens": 308520472} {"current_steps": 303100, "total_steps": 761865, "loss": 2.0136, "lr": 6.577442821960284e-07, "epoch": 5.967592683743183, "percentage": 39.78, "elapsed_time": "10:13:22", "remaining_time": "15:28:22", "throughput": 8385.99, "total_tokens": 308622208} {"current_steps": 303200, "total_steps": 761865, "loss": 2.0166, "lr": 6.575486180713992e-07, "epoch": 5.9695615364926855, "percentage": 39.8, "elapsed_time": "10:13:33", "remaining_time": "15:28:09", "throughput": 8386.1, "total_tokens": 308723224} {"current_steps": 303300, "total_steps": 761865, "loss": 2.0004, "lr": 6.573529271569562e-07, "epoch": 5.971530389242188, "percentage": 39.81, "elapsed_time": "10:13:45", "remaining_time": "15:27:56", "throughput": 8386.21, "total_tokens": 308824872} {"current_steps": 303400, "total_steps": 761865, "loss": 1.9879, "lr": 6.571572094859752e-07, "epoch": 5.973499241991691, "percentage": 39.82, "elapsed_time": "10:13:56", "remaining_time": "15:27:44", "throughput": 8386.31, "total_tokens": 308926504} {"current_steps": 303500, "total_steps": 761865, "loss": 1.9813, "lr": 6.569614650917362e-07, "epoch": 5.975468094741195, "percentage": 39.84, "elapsed_time": "10:14:08", "remaining_time": "15:27:31", "throughput": 8386.42, "total_tokens": 309027640} {"current_steps": 303600, "total_steps": 761865, "loss": 2.0483, "lr": 6.56765694007524e-07, "epoch": 5.977436947490697, "percentage": 39.85, "elapsed_time": "10:14:20", "remaining_time": "15:27:18", "throughput": 8386.54, "total_tokens": 309129488} {"current_steps": 303700, "total_steps": 761865, "loss": 1.9652, "lr": 6.565698962666277e-07, "epoch": 5.9794058002402, "percentage": 39.86, "elapsed_time": "10:14:31", "remaining_time": "15:27:05", "throughput": 8386.65, "total_tokens": 309231336} {"current_steps": 303800, "total_steps": 761865, "loss": 2.0091, "lr": 6.563740719023412e-07, "epoch": 5.981374652989703, "percentage": 39.88, "elapsed_time": "10:14:43", "remaining_time": "15:26:52", "throughput": 8386.77, "total_tokens": 309333736} {"current_steps": 303900, "total_steps": 761865, "loss": 1.9728, "lr": 6.561782209479626e-07, "epoch": 5.983343505739206, "percentage": 39.89, "elapsed_time": "10:14:55", "remaining_time": "15:26:39", "throughput": 8386.89, "total_tokens": 309436136} {"current_steps": 304000, "total_steps": 761865, "loss": 2.0493, "lr": 6.559823434367948e-07, "epoch": 5.9853123584887085, "percentage": 39.9, "elapsed_time": "10:15:06", "remaining_time": "15:26:26", "throughput": 8387.01, "total_tokens": 309538312} {"current_steps": 304100, "total_steps": 761865, "loss": 1.9785, "lr": 6.557864394021453e-07, "epoch": 5.987281211238211, "percentage": 39.92, "elapsed_time": "10:15:18", "remaining_time": "15:26:13", "throughput": 8387.12, "total_tokens": 309640232} {"current_steps": 304200, "total_steps": 761865, "loss": 1.9847, "lr": 6.555905088773255e-07, "epoch": 5.989250063987714, "percentage": 39.93, "elapsed_time": "10:15:30", "remaining_time": "15:26:00", "throughput": 8387.23, "total_tokens": 309741984} {"current_steps": 304300, "total_steps": 761865, "loss": 1.9464, "lr": 6.55394551895652e-07, "epoch": 5.991218916737218, "percentage": 39.94, "elapsed_time": "10:15:41", "remaining_time": "15:25:47", "throughput": 8387.34, "total_tokens": 309843072} {"current_steps": 304400, "total_steps": 761865, "loss": 1.9916, "lr": 6.551985684904457e-07, "epoch": 5.99318776948672, "percentage": 39.95, "elapsed_time": "10:15:53", "remaining_time": "15:25:34", "throughput": 8387.44, "total_tokens": 309943736} {"current_steps": 304500, "total_steps": 761865, "loss": 2.0215, "lr": 6.550025586950319e-07, "epoch": 5.995156622236223, "percentage": 39.97, "elapsed_time": "10:16:04", "remaining_time": "15:25:22", "throughput": 8387.56, "total_tokens": 310046136} {"current_steps": 304600, "total_steps": 761865, "loss": 1.9955, "lr": 6.548065225427402e-07, "epoch": 5.997125474985726, "percentage": 39.98, "elapsed_time": "10:16:16", "remaining_time": "15:25:09", "throughput": 8387.68, "total_tokens": 310148536} {"current_steps": 304700, "total_steps": 761865, "loss": 2.0323, "lr": 6.546104600669051e-07, "epoch": 5.999094327735229, "percentage": 39.99, "elapsed_time": "10:16:28", "remaining_time": "15:24:56", "throughput": 8387.78, "total_tokens": 310249568} {"current_steps": 304800, "total_steps": 761865, "loss": 1.9671, "lr": 6.544143713008652e-07, "epoch": 6.001063180484731, "percentage": 40.01, "elapsed_time": "10:16:39", "remaining_time": "15:24:43", "throughput": 8387.89, "total_tokens": 310351192} {"current_steps": 304900, "total_steps": 761865, "loss": 1.9604, "lr": 6.542182562779641e-07, "epoch": 6.003032033234234, "percentage": 40.02, "elapsed_time": "10:16:51", "remaining_time": "15:24:30", "throughput": 8387.99, "total_tokens": 310452128} {"current_steps": 305000, "total_steps": 761865, "loss": 2.0128, "lr": 6.54022115031549e-07, "epoch": 6.005000885983737, "percentage": 40.03, "elapsed_time": "10:17:03", "remaining_time": "15:24:17", "throughput": 8388.09, "total_tokens": 310552416} {"current_steps": 305100, "total_steps": 761865, "loss": 1.9888, "lr": 6.538259475949726e-07, "epoch": 6.006969738733241, "percentage": 40.05, "elapsed_time": "10:17:15", "remaining_time": "15:24:05", "throughput": 8388.08, "total_tokens": 310654816} {"current_steps": 305200, "total_steps": 761865, "loss": 1.9771, "lr": 6.53629754001591e-07, "epoch": 6.008938591482743, "percentage": 40.06, "elapsed_time": "10:17:26", "remaining_time": "15:23:52", "throughput": 8388.2, "total_tokens": 310757216} {"current_steps": 305300, "total_steps": 761865, "loss": 2.0169, "lr": 6.534335342847657e-07, "epoch": 6.010907444232246, "percentage": 40.07, "elapsed_time": "10:17:38", "remaining_time": "15:23:39", "throughput": 8388.29, "total_tokens": 310856768} {"current_steps": 305400, "total_steps": 761865, "loss": 1.9687, "lr": 6.532372884778618e-07, "epoch": 6.012876296981749, "percentage": 40.09, "elapsed_time": "10:17:50", "remaining_time": "15:23:26", "throughput": 8388.41, "total_tokens": 310959168} {"current_steps": 305500, "total_steps": 761865, "loss": 1.9883, "lr": 6.530410166142495e-07, "epoch": 6.014845149731252, "percentage": 40.1, "elapsed_time": "10:18:01", "remaining_time": "15:23:13", "throughput": 8388.52, "total_tokens": 311060792} {"current_steps": 305600, "total_steps": 761865, "loss": 1.9433, "lr": 6.528447187273032e-07, "epoch": 6.016814002480754, "percentage": 40.11, "elapsed_time": "10:18:13", "remaining_time": "15:23:00", "throughput": 8388.64, "total_tokens": 311163192} {"current_steps": 305700, "total_steps": 761865, "loss": 1.964, "lr": 6.526483948504016e-07, "epoch": 6.018782855230257, "percentage": 40.13, "elapsed_time": "10:18:24", "remaining_time": "15:22:48", "throughput": 8388.73, "total_tokens": 311263936} {"current_steps": 305800, "total_steps": 761865, "loss": 2.0609, "lr": 6.52452045016928e-07, "epoch": 6.02075170797976, "percentage": 40.14, "elapsed_time": "10:18:36", "remaining_time": "15:22:35", "throughput": 8388.83, "total_tokens": 311364776} {"current_steps": 305900, "total_steps": 761865, "loss": 2.0215, "lr": 6.522556692602698e-07, "epoch": 6.022720560729263, "percentage": 40.15, "elapsed_time": "10:18:48", "remaining_time": "15:22:22", "throughput": 8388.93, "total_tokens": 311465584} {"current_steps": 306000, "total_steps": 761865, "loss": 1.9621, "lr": 6.520592676138196e-07, "epoch": 6.024689413478766, "percentage": 40.16, "elapsed_time": "10:18:59", "remaining_time": "15:22:09", "throughput": 8389.05, "total_tokens": 311567984} {"current_steps": 306100, "total_steps": 761865, "loss": 1.998, "lr": 6.518628401109731e-07, "epoch": 6.026658266228269, "percentage": 40.18, "elapsed_time": "10:19:11", "remaining_time": "15:21:56", "throughput": 8389.17, "total_tokens": 311669728} {"current_steps": 306200, "total_steps": 761865, "loss": 1.9819, "lr": 6.516663867851318e-07, "epoch": 6.028627118977772, "percentage": 40.19, "elapsed_time": "10:19:23", "remaining_time": "15:21:43", "throughput": 8389.26, "total_tokens": 311770080} {"current_steps": 306300, "total_steps": 761865, "loss": 1.9614, "lr": 6.514699076697005e-07, "epoch": 6.030595971727275, "percentage": 40.2, "elapsed_time": "10:19:34", "remaining_time": "15:21:30", "throughput": 8389.38, "total_tokens": 311872480} {"current_steps": 306400, "total_steps": 761865, "loss": 2.0079, "lr": 6.512734027980889e-07, "epoch": 6.032564824476777, "percentage": 40.22, "elapsed_time": "10:19:46", "remaining_time": "15:21:17", "throughput": 8389.49, "total_tokens": 311974880} {"current_steps": 306500, "total_steps": 761865, "loss": 2.0224, "lr": 6.51076872203711e-07, "epoch": 6.03453367722628, "percentage": 40.23, "elapsed_time": "10:19:58", "remaining_time": "15:21:04", "throughput": 8389.61, "total_tokens": 312076840} {"current_steps": 306600, "total_steps": 761865, "loss": 1.962, "lr": 6.508803159199854e-07, "epoch": 6.036502529975783, "percentage": 40.24, "elapsed_time": "10:20:09", "remaining_time": "15:20:52", "throughput": 8389.72, "total_tokens": 312179240} {"current_steps": 306700, "total_steps": 761865, "loss": 1.9511, "lr": 6.506837339803346e-07, "epoch": 6.038471382725286, "percentage": 40.26, "elapsed_time": "10:20:21", "remaining_time": "15:20:39", "throughput": 8389.84, "total_tokens": 312281640} {"current_steps": 306800, "total_steps": 761865, "loss": 2.016, "lr": 6.504871264181857e-07, "epoch": 6.040440235474789, "percentage": 40.27, "elapsed_time": "10:20:33", "remaining_time": "15:20:26", "throughput": 8389.96, "total_tokens": 312384040} {"current_steps": 306900, "total_steps": 761865, "loss": 2.0034, "lr": 6.502904932669702e-07, "epoch": 6.042409088224292, "percentage": 40.28, "elapsed_time": "10:20:44", "remaining_time": "15:20:13", "throughput": 8390.06, "total_tokens": 312484688} {"current_steps": 307000, "total_steps": 761865, "loss": 2.0577, "lr": 6.500938345601242e-07, "epoch": 6.044377940973795, "percentage": 40.3, "elapsed_time": "10:20:56", "remaining_time": "15:20:00", "throughput": 8390.17, "total_tokens": 312586792} {"current_steps": 307100, "total_steps": 761865, "loss": 1.9655, "lr": 6.498971503310872e-07, "epoch": 6.0463467937232975, "percentage": 40.31, "elapsed_time": "10:21:07", "remaining_time": "15:19:47", "throughput": 8390.29, "total_tokens": 312688880} {"current_steps": 307200, "total_steps": 761865, "loss": 2.0385, "lr": 6.497004406133044e-07, "epoch": 6.0483156464728, "percentage": 40.32, "elapsed_time": "10:21:19", "remaining_time": "15:19:34", "throughput": 8390.39, "total_tokens": 312790280} {"current_steps": 307300, "total_steps": 761865, "loss": 1.9808, "lr": 6.495037054402242e-07, "epoch": 6.050284499222303, "percentage": 40.34, "elapsed_time": "10:21:31", "remaining_time": "15:19:22", "throughput": 8390.51, "total_tokens": 312892680} {"current_steps": 307400, "total_steps": 761865, "loss": 1.9673, "lr": 6.493069448452998e-07, "epoch": 6.052253351971806, "percentage": 40.35, "elapsed_time": "10:21:42", "remaining_time": "15:19:09", "throughput": 8390.62, "total_tokens": 312994440} {"current_steps": 307500, "total_steps": 761865, "loss": 1.9874, "lr": 6.491101588619888e-07, "epoch": 6.054222204721309, "percentage": 40.36, "elapsed_time": "10:21:54", "remaining_time": "15:18:56", "throughput": 8390.74, "total_tokens": 313096840} {"current_steps": 307600, "total_steps": 761865, "loss": 1.9606, "lr": 6.489133475237528e-07, "epoch": 6.056191057470811, "percentage": 40.37, "elapsed_time": "10:22:06", "remaining_time": "15:18:43", "throughput": 8390.85, "total_tokens": 313198624} {"current_steps": 307700, "total_steps": 761865, "loss": 2.0203, "lr": 6.487165108640581e-07, "epoch": 6.058159910220315, "percentage": 40.39, "elapsed_time": "10:22:17", "remaining_time": "15:18:30", "throughput": 8390.96, "total_tokens": 313300320} {"current_steps": 307800, "total_steps": 761865, "loss": 2.0202, "lr": 6.485196489163752e-07, "epoch": 6.060128762969818, "percentage": 40.4, "elapsed_time": "10:22:29", "remaining_time": "15:18:17", "throughput": 8391.06, "total_tokens": 313401664} {"current_steps": 307900, "total_steps": 761865, "loss": 1.9897, "lr": 6.483227617141786e-07, "epoch": 6.0620976157193205, "percentage": 40.41, "elapsed_time": "10:22:41", "remaining_time": "15:18:04", "throughput": 8391.18, "total_tokens": 313504064} {"current_steps": 308000, "total_steps": 761865, "loss": 2.024, "lr": 6.481258492909474e-07, "epoch": 6.064066468468823, "percentage": 40.43, "elapsed_time": "10:22:52", "remaining_time": "15:17:51", "throughput": 8391.27, "total_tokens": 313604280} {"current_steps": 308100, "total_steps": 761865, "loss": 2.0033, "lr": 6.479289116801648e-07, "epoch": 6.066035321218326, "percentage": 40.44, "elapsed_time": "10:23:04", "remaining_time": "15:17:39", "throughput": 8391.37, "total_tokens": 313705928} {"current_steps": 308200, "total_steps": 761865, "loss": 1.9879, "lr": 6.477319489153185e-07, "epoch": 6.068004173967829, "percentage": 40.45, "elapsed_time": "10:23:16", "remaining_time": "15:17:26", "throughput": 8391.49, "total_tokens": 313808328} {"current_steps": 308300, "total_steps": 761865, "loss": 1.9798, "lr": 6.475349610299004e-07, "epoch": 6.0699730267173315, "percentage": 40.47, "elapsed_time": "10:23:27", "remaining_time": "15:17:13", "throughput": 8391.6, "total_tokens": 313909912} {"current_steps": 308400, "total_steps": 761865, "loss": 2.0272, "lr": 6.473379480574065e-07, "epoch": 6.071941879466834, "percentage": 40.48, "elapsed_time": "10:23:39", "remaining_time": "15:17:00", "throughput": 8391.71, "total_tokens": 314011856} {"current_steps": 308500, "total_steps": 761865, "loss": 2.0186, "lr": 6.471409100313372e-07, "epoch": 6.073910732216338, "percentage": 40.49, "elapsed_time": "10:23:50", "remaining_time": "15:16:47", "throughput": 8391.83, "total_tokens": 314114256} {"current_steps": 308600, "total_steps": 761865, "loss": 2.01, "lr": 6.469438469851971e-07, "epoch": 6.075879584965841, "percentage": 40.51, "elapsed_time": "10:24:02", "remaining_time": "15:16:34", "throughput": 8391.93, "total_tokens": 314215208} {"current_steps": 308700, "total_steps": 761865, "loss": 1.9789, "lr": 6.467467589524954e-07, "epoch": 6.077848437715343, "percentage": 40.52, "elapsed_time": "10:24:14", "remaining_time": "15:16:22", "throughput": 8392.04, "total_tokens": 314317608} {"current_steps": 308800, "total_steps": 761865, "loss": 2.0178, "lr": 6.465496459667449e-07, "epoch": 6.079817290464846, "percentage": 40.53, "elapsed_time": "10:24:25", "remaining_time": "15:16:09", "throughput": 8392.13, "total_tokens": 314418184} {"current_steps": 308900, "total_steps": 761865, "loss": 2.0023, "lr": 6.463525080614631e-07, "epoch": 6.081786143214349, "percentage": 40.55, "elapsed_time": "10:24:37", "remaining_time": "15:15:56", "throughput": 8392.25, "total_tokens": 314520584} {"current_steps": 309000, "total_steps": 761865, "loss": 1.9614, "lr": 6.46155345270172e-07, "epoch": 6.083754995963852, "percentage": 40.56, "elapsed_time": "10:24:49", "remaining_time": "15:15:43", "throughput": 8392.36, "total_tokens": 314622984} {"current_steps": 309100, "total_steps": 761865, "loss": 2.0152, "lr": 6.459581576263969e-07, "epoch": 6.0857238487133545, "percentage": 40.57, "elapsed_time": "10:25:00", "remaining_time": "15:15:30", "throughput": 8392.48, "total_tokens": 314724968} {"current_steps": 309200, "total_steps": 761865, "loss": 2.0155, "lr": 6.457609451636683e-07, "epoch": 6.087692701462857, "percentage": 40.58, "elapsed_time": "10:25:12", "remaining_time": "15:15:17", "throughput": 8392.6, "total_tokens": 314827368} {"current_steps": 309300, "total_steps": 761865, "loss": 1.9914, "lr": 6.455637079155203e-07, "epoch": 6.089661554212361, "percentage": 40.6, "elapsed_time": "10:25:24", "remaining_time": "15:15:04", "throughput": 8392.71, "total_tokens": 314929080} {"current_steps": 309400, "total_steps": 761865, "loss": 1.9567, "lr": 6.453664459154916e-07, "epoch": 6.091630406961864, "percentage": 40.61, "elapsed_time": "10:25:35", "remaining_time": "15:14:52", "throughput": 8392.82, "total_tokens": 315031480} {"current_steps": 309500, "total_steps": 761865, "loss": 1.9582, "lr": 6.451691591971248e-07, "epoch": 6.093599259711366, "percentage": 40.62, "elapsed_time": "10:25:47", "remaining_time": "15:14:39", "throughput": 8392.93, "total_tokens": 315133880} {"current_steps": 309600, "total_steps": 761865, "loss": 1.9556, "lr": 6.449718477939669e-07, "epoch": 6.095568112460869, "percentage": 40.64, "elapsed_time": "10:25:59", "remaining_time": "15:14:26", "throughput": 8393.05, "total_tokens": 315236280} {"current_steps": 309700, "total_steps": 761865, "loss": 1.9876, "lr": 6.44774511739569e-07, "epoch": 6.097536965210372, "percentage": 40.65, "elapsed_time": "10:26:10", "remaining_time": "15:14:13", "throughput": 8393.14, "total_tokens": 315336760} {"current_steps": 309800, "total_steps": 761865, "loss": 1.988, "lr": 6.445771510674865e-07, "epoch": 6.099505817959875, "percentage": 40.66, "elapsed_time": "10:26:22", "remaining_time": "15:14:00", "throughput": 8393.25, "total_tokens": 315439160} {"current_steps": 309900, "total_steps": 761865, "loss": 1.9711, "lr": 6.443797658112788e-07, "epoch": 6.101474670709377, "percentage": 40.68, "elapsed_time": "10:26:34", "remaining_time": "15:13:48", "throughput": 8393.36, "total_tokens": 315541112} {"current_steps": 310000, "total_steps": 761865, "loss": 1.9465, "lr": 6.441823560045098e-07, "epoch": 6.10344352345888, "percentage": 40.69, "elapsed_time": "10:26:45", "remaining_time": "15:13:35", "throughput": 8393.47, "total_tokens": 315642496} {"current_steps": 310100, "total_steps": 761865, "loss": 1.9585, "lr": 6.439849216807472e-07, "epoch": 6.105412376208383, "percentage": 40.7, "elapsed_time": "10:26:57", "remaining_time": "15:13:23", "throughput": 8393.46, "total_tokens": 315744896} {"current_steps": 310200, "total_steps": 761865, "loss": 2.0367, "lr": 6.437874628735631e-07, "epoch": 6.107381228957887, "percentage": 40.72, "elapsed_time": "10:27:09", "remaining_time": "15:13:10", "throughput": 8393.57, "total_tokens": 315846560} {"current_steps": 310300, "total_steps": 761865, "loss": 1.9712, "lr": 6.435899796165337e-07, "epoch": 6.109350081707389, "percentage": 40.73, "elapsed_time": "10:27:21", "remaining_time": "15:12:57", "throughput": 8393.68, "total_tokens": 315948960} {"current_steps": 310400, "total_steps": 761865, "loss": 1.9535, "lr": 6.433924719432393e-07, "epoch": 6.111318934456892, "percentage": 40.74, "elapsed_time": "10:27:32", "remaining_time": "15:12:44", "throughput": 8393.79, "total_tokens": 316050872} {"current_steps": 310500, "total_steps": 761865, "loss": 1.9809, "lr": 6.431949398872646e-07, "epoch": 6.113287787206395, "percentage": 40.76, "elapsed_time": "10:27:44", "remaining_time": "15:12:31", "throughput": 8393.89, "total_tokens": 316151576} {"current_steps": 310600, "total_steps": 761865, "loss": 2.0128, "lr": 6.429973834821979e-07, "epoch": 6.115256639955898, "percentage": 40.77, "elapsed_time": "10:27:56", "remaining_time": "15:12:18", "throughput": 8394.0, "total_tokens": 316253384} {"current_steps": 310700, "total_steps": 761865, "loss": 1.9806, "lr": 6.427998027616324e-07, "epoch": 6.1172254927054, "percentage": 40.78, "elapsed_time": "10:28:07", "remaining_time": "15:12:06", "throughput": 8394.12, "total_tokens": 316355784} {"current_steps": 310800, "total_steps": 761865, "loss": 1.9777, "lr": 6.426021977591648e-07, "epoch": 6.119194345454903, "percentage": 40.79, "elapsed_time": "10:28:19", "remaining_time": "15:11:53", "throughput": 8394.21, "total_tokens": 316456696} {"current_steps": 310900, "total_steps": 761865, "loss": 1.9684, "lr": 6.424045685083963e-07, "epoch": 6.121163198204406, "percentage": 40.81, "elapsed_time": "10:28:31", "remaining_time": "15:11:40", "throughput": 8394.31, "total_tokens": 316558008} {"current_steps": 311000, "total_steps": 761865, "loss": 2.0026, "lr": 6.42206915042932e-07, "epoch": 6.1231320509539096, "percentage": 40.82, "elapsed_time": "10:28:42", "remaining_time": "15:11:27", "throughput": 8394.42, "total_tokens": 316659848} {"current_steps": 311100, "total_steps": 761865, "loss": 1.9969, "lr": 6.420092373963814e-07, "epoch": 6.125100903703412, "percentage": 40.83, "elapsed_time": "10:28:54", "remaining_time": "15:11:14", "throughput": 8394.54, "total_tokens": 316761712} {"current_steps": 311200, "total_steps": 761865, "loss": 1.9864, "lr": 6.418115356023575e-07, "epoch": 6.127069756452915, "percentage": 40.85, "elapsed_time": "10:29:05", "remaining_time": "15:11:01", "throughput": 8394.65, "total_tokens": 316864112} {"current_steps": 311300, "total_steps": 761865, "loss": 2.0291, "lr": 6.416138096944782e-07, "epoch": 6.129038609202418, "percentage": 40.86, "elapsed_time": "10:29:17", "remaining_time": "15:10:48", "throughput": 8394.75, "total_tokens": 316965184} {"current_steps": 311400, "total_steps": 761865, "loss": 2.0362, "lr": 6.414160597063648e-07, "epoch": 6.131007461951921, "percentage": 40.87, "elapsed_time": "10:29:29", "remaining_time": "15:10:36", "throughput": 8394.87, "total_tokens": 317067584} {"current_steps": 311500, "total_steps": 761865, "loss": 2.0357, "lr": 6.412182856716435e-07, "epoch": 6.132976314701423, "percentage": 40.89, "elapsed_time": "10:29:40", "remaining_time": "15:10:23", "throughput": 8394.98, "total_tokens": 317169984} {"current_steps": 311600, "total_steps": 761865, "loss": 1.9955, "lr": 6.410204876239435e-07, "epoch": 6.134945167450926, "percentage": 40.9, "elapsed_time": "10:29:52", "remaining_time": "15:10:10", "throughput": 8395.1, "total_tokens": 317272384} {"current_steps": 311700, "total_steps": 761865, "loss": 1.9822, "lr": 6.408226655968992e-07, "epoch": 6.136914020200429, "percentage": 40.91, "elapsed_time": "10:30:04", "remaining_time": "15:09:57", "throughput": 8395.21, "total_tokens": 317373952} {"current_steps": 311800, "total_steps": 761865, "loss": 1.9544, "lr": 6.406248196241482e-07, "epoch": 6.138882872949932, "percentage": 40.93, "elapsed_time": "10:30:15", "remaining_time": "15:09:44", "throughput": 8395.32, "total_tokens": 317476352} {"current_steps": 311900, "total_steps": 761865, "loss": 1.9694, "lr": 6.404269497393329e-07, "epoch": 6.140851725699435, "percentage": 40.94, "elapsed_time": "10:30:27", "remaining_time": "15:09:32", "throughput": 8395.44, "total_tokens": 317578752} {"current_steps": 312000, "total_steps": 761865, "loss": 1.9487, "lr": 6.402290559760991e-07, "epoch": 6.142820578448938, "percentage": 40.95, "elapsed_time": "10:30:39", "remaining_time": "15:09:19", "throughput": 8395.55, "total_tokens": 317681152} {"current_steps": 312100, "total_steps": 761865, "loss": 2.0625, "lr": 6.400311383680972e-07, "epoch": 6.144789431198441, "percentage": 40.97, "elapsed_time": "10:30:50", "remaining_time": "15:09:06", "throughput": 8395.66, "total_tokens": 317782736} {"current_steps": 312200, "total_steps": 761865, "loss": 2.0034, "lr": 6.398331969489812e-07, "epoch": 6.1467582839479435, "percentage": 40.98, "elapsed_time": "10:31:02", "remaining_time": "15:08:53", "throughput": 8395.73, "total_tokens": 317882104} {"current_steps": 312300, "total_steps": 761865, "loss": 2.0182, "lr": 6.396352317524094e-07, "epoch": 6.148727136697446, "percentage": 40.99, "elapsed_time": "10:31:13", "remaining_time": "15:08:40", "throughput": 8395.84, "total_tokens": 317983328} {"current_steps": 312400, "total_steps": 761865, "loss": 2.0063, "lr": 6.394372428120442e-07, "epoch": 6.150695989446949, "percentage": 41.0, "elapsed_time": "10:31:25", "remaining_time": "15:08:27", "throughput": 8395.95, "total_tokens": 318085728} {"current_steps": 312500, "total_steps": 761865, "loss": 1.9624, "lr": 6.392392301615521e-07, "epoch": 6.152664842196452, "percentage": 41.02, "elapsed_time": "10:31:37", "remaining_time": "15:08:15", "throughput": 8396.06, "total_tokens": 318187600} {"current_steps": 312600, "total_steps": 761865, "loss": 1.9519, "lr": 6.390411938346032e-07, "epoch": 6.154633694945955, "percentage": 41.03, "elapsed_time": "10:31:48", "remaining_time": "15:08:02", "throughput": 8396.16, "total_tokens": 318289240} {"current_steps": 312700, "total_steps": 761865, "loss": 1.9764, "lr": 6.388431338648719e-07, "epoch": 6.156602547695458, "percentage": 41.04, "elapsed_time": "10:32:00", "remaining_time": "15:07:49", "throughput": 8396.26, "total_tokens": 318390368} {"current_steps": 312800, "total_steps": 761865, "loss": 2.0118, "lr": 6.386450502860369e-07, "epoch": 6.158571400444961, "percentage": 41.06, "elapsed_time": "10:32:12", "remaining_time": "15:07:36", "throughput": 8396.35, "total_tokens": 318491344} {"current_steps": 312900, "total_steps": 761865, "loss": 2.008, "lr": 6.384469431317805e-07, "epoch": 6.160540253194464, "percentage": 41.07, "elapsed_time": "10:32:23", "remaining_time": "15:07:23", "throughput": 8396.47, "total_tokens": 318593744} {"current_steps": 313000, "total_steps": 761865, "loss": 1.9992, "lr": 6.382488124357889e-07, "epoch": 6.1625091059439665, "percentage": 41.08, "elapsed_time": "10:32:35", "remaining_time": "15:07:10", "throughput": 8396.58, "total_tokens": 318696144} {"current_steps": 313100, "total_steps": 761865, "loss": 1.9387, "lr": 6.380506582317531e-07, "epoch": 6.164477958693469, "percentage": 41.1, "elapsed_time": "10:32:47", "remaining_time": "15:06:58", "throughput": 8396.7, "total_tokens": 318798544} {"current_steps": 313200, "total_steps": 761865, "loss": 1.9605, "lr": 6.37852480553367e-07, "epoch": 6.166446811442972, "percentage": 41.11, "elapsed_time": "10:32:58", "remaining_time": "15:06:45", "throughput": 8396.81, "total_tokens": 318900944} {"current_steps": 313300, "total_steps": 761865, "loss": 1.9499, "lr": 6.376542794343295e-07, "epoch": 6.168415664192475, "percentage": 41.12, "elapsed_time": "10:33:10", "remaining_time": "15:06:32", "throughput": 8396.91, "total_tokens": 319001936} {"current_steps": 313400, "total_steps": 761865, "loss": 1.9951, "lr": 6.374560549083426e-07, "epoch": 6.1703845169419775, "percentage": 41.14, "elapsed_time": "10:33:22", "remaining_time": "15:06:19", "throughput": 8397.01, "total_tokens": 319103568} {"current_steps": 313500, "total_steps": 761865, "loss": 1.9354, "lr": 6.372578070091131e-07, "epoch": 6.172353369691481, "percentage": 41.15, "elapsed_time": "10:33:33", "remaining_time": "15:06:06", "throughput": 8397.12, "total_tokens": 319205968} {"current_steps": 313600, "total_steps": 761865, "loss": 2.0053, "lr": 6.370595357703511e-07, "epoch": 6.174322222440984, "percentage": 41.16, "elapsed_time": "10:33:45", "remaining_time": "15:05:54", "throughput": 8397.24, "total_tokens": 319308368} {"current_steps": 313700, "total_steps": 761865, "loss": 1.9863, "lr": 6.36861241225771e-07, "epoch": 6.176291075190487, "percentage": 41.18, "elapsed_time": "10:33:57", "remaining_time": "15:05:41", "throughput": 8397.35, "total_tokens": 319410128} {"current_steps": 313800, "total_steps": 761865, "loss": 1.9867, "lr": 6.366629234090913e-07, "epoch": 6.1782599279399895, "percentage": 41.19, "elapsed_time": "10:34:08", "remaining_time": "15:05:28", "throughput": 8397.46, "total_tokens": 319512528} {"current_steps": 313900, "total_steps": 761865, "loss": 1.9278, "lr": 6.364645823540341e-07, "epoch": 6.180228780689492, "percentage": 41.2, "elapsed_time": "10:34:20", "remaining_time": "15:05:15", "throughput": 8397.57, "total_tokens": 319614928} {"current_steps": 314000, "total_steps": 761865, "loss": 2.0377, "lr": 6.362662180943257e-07, "epoch": 6.182197633438995, "percentage": 41.21, "elapsed_time": "10:34:32", "remaining_time": "15:05:02", "throughput": 8397.68, "total_tokens": 319716376} {"current_steps": 314100, "total_steps": 761865, "loss": 1.9887, "lr": 6.360678306636962e-07, "epoch": 6.184166486188498, "percentage": 41.23, "elapsed_time": "10:34:43", "remaining_time": "15:04:50", "throughput": 8397.78, "total_tokens": 319817640} {"current_steps": 314200, "total_steps": 761865, "loss": 2.0208, "lr": 6.358694200958797e-07, "epoch": 6.1861353389380005, "percentage": 41.24, "elapsed_time": "10:34:55", "remaining_time": "15:04:37", "throughput": 8397.89, "total_tokens": 319919264} {"current_steps": 314300, "total_steps": 761865, "loss": 1.9916, "lr": 6.356709864246143e-07, "epoch": 6.188104191687504, "percentage": 41.25, "elapsed_time": "10:35:06", "remaining_time": "15:04:24", "throughput": 8398.0, "total_tokens": 320021568} {"current_steps": 314400, "total_steps": 761865, "loss": 2.0141, "lr": 6.354725296836421e-07, "epoch": 6.190073044437007, "percentage": 41.27, "elapsed_time": "10:35:18", "remaining_time": "15:04:11", "throughput": 8398.11, "total_tokens": 320123920} {"current_steps": 314500, "total_steps": 761865, "loss": 2.0139, "lr": 6.352740499067086e-07, "epoch": 6.19204189718651, "percentage": 41.28, "elapsed_time": "10:35:30", "remaining_time": "15:03:58", "throughput": 8398.22, "total_tokens": 320226024} {"current_steps": 314600, "total_steps": 761865, "loss": 1.9685, "lr": 6.350755471275642e-07, "epoch": 6.194010749936012, "percentage": 41.29, "elapsed_time": "10:35:41", "remaining_time": "15:03:46", "throughput": 8398.33, "total_tokens": 320328424} {"current_steps": 314700, "total_steps": 761865, "loss": 1.966, "lr": 6.34877021379962e-07, "epoch": 6.195979602685515, "percentage": 41.31, "elapsed_time": "10:35:53", "remaining_time": "15:03:33", "throughput": 8398.44, "total_tokens": 320430824} {"current_steps": 314800, "total_steps": 761865, "loss": 1.9815, "lr": 6.346784726976599e-07, "epoch": 6.197948455435018, "percentage": 41.32, "elapsed_time": "10:36:05", "remaining_time": "15:03:20", "throughput": 8398.56, "total_tokens": 320533224} {"current_steps": 314900, "total_steps": 761865, "loss": 2.0185, "lr": 6.344799011144196e-07, "epoch": 6.199917308184521, "percentage": 41.33, "elapsed_time": "10:36:16", "remaining_time": "15:03:07", "throughput": 8398.66, "total_tokens": 320634864} {"current_steps": 315000, "total_steps": 761865, "loss": 2.0046, "lr": 6.342813066640063e-07, "epoch": 6.2018861609340235, "percentage": 41.35, "elapsed_time": "10:36:28", "remaining_time": "15:02:55", "throughput": 8398.77, "total_tokens": 320736832} {"current_steps": 315100, "total_steps": 761865, "loss": 1.9641, "lr": 6.340826893801895e-07, "epoch": 6.203855013683526, "percentage": 41.36, "elapsed_time": "10:36:40", "remaining_time": "15:02:43", "throughput": 8398.76, "total_tokens": 320839232} {"current_steps": 315200, "total_steps": 761865, "loss": 1.9799, "lr": 6.338840492967422e-07, "epoch": 6.20582386643303, "percentage": 41.37, "elapsed_time": "10:36:52", "remaining_time": "15:02:30", "throughput": 8398.86, "total_tokens": 320940808} {"current_steps": 315300, "total_steps": 761865, "loss": 1.9989, "lr": 6.336853864474416e-07, "epoch": 6.207792719182533, "percentage": 41.39, "elapsed_time": "10:37:04", "remaining_time": "15:02:17", "throughput": 8398.98, "total_tokens": 321043208} {"current_steps": 315400, "total_steps": 761865, "loss": 1.9933, "lr": 6.334867008660685e-07, "epoch": 6.209761571932035, "percentage": 41.4, "elapsed_time": "10:37:15", "remaining_time": "15:02:04", "throughput": 8399.09, "total_tokens": 321145608} {"current_steps": 315500, "total_steps": 761865, "loss": 1.9407, "lr": 6.332879925864079e-07, "epoch": 6.211730424681538, "percentage": 41.41, "elapsed_time": "10:37:27", "remaining_time": "15:01:51", "throughput": 8399.2, "total_tokens": 321248008} {"current_steps": 315600, "total_steps": 761865, "loss": 2.0361, "lr": 6.330892616422483e-07, "epoch": 6.213699277431041, "percentage": 41.42, "elapsed_time": "10:37:39", "remaining_time": "15:01:39", "throughput": 8399.31, "total_tokens": 321350408} {"current_steps": 315700, "total_steps": 761865, "loss": 2.0177, "lr": 6.328905080673821e-07, "epoch": 6.215668130180544, "percentage": 41.44, "elapsed_time": "10:37:50", "remaining_time": "15:01:26", "throughput": 8399.42, "total_tokens": 321451936} {"current_steps": 315800, "total_steps": 761865, "loss": 2.0181, "lr": 6.326917318956061e-07, "epoch": 6.217636982930046, "percentage": 41.45, "elapsed_time": "10:38:02", "remaining_time": "15:01:13", "throughput": 8399.53, "total_tokens": 321554336} {"current_steps": 315900, "total_steps": 761865, "loss": 1.9909, "lr": 6.324929331607201e-07, "epoch": 6.219605835679549, "percentage": 41.46, "elapsed_time": "10:38:13", "remaining_time": "15:01:00", "throughput": 8399.62, "total_tokens": 321655032} {"current_steps": 316000, "total_steps": 761865, "loss": 1.9734, "lr": 6.322941118965285e-07, "epoch": 6.221574688429053, "percentage": 41.48, "elapsed_time": "10:38:25", "remaining_time": "15:00:47", "throughput": 8399.73, "total_tokens": 321757432} {"current_steps": 316100, "total_steps": 761865, "loss": 1.9818, "lr": 6.320952681368389e-07, "epoch": 6.223543541178556, "percentage": 41.49, "elapsed_time": "10:38:37", "remaining_time": "15:00:35", "throughput": 8399.84, "total_tokens": 321859072} {"current_steps": 316200, "total_steps": 761865, "loss": 1.9601, "lr": 6.318964019154632e-07, "epoch": 6.225512393928058, "percentage": 41.5, "elapsed_time": "10:38:48", "remaining_time": "15:00:22", "throughput": 8399.94, "total_tokens": 321960168} {"current_steps": 316300, "total_steps": 761865, "loss": 2.0435, "lr": 6.316975132662165e-07, "epoch": 6.227481246677561, "percentage": 41.52, "elapsed_time": "10:39:00", "remaining_time": "15:00:09", "throughput": 8400.02, "total_tokens": 322060616} {"current_steps": 316400, "total_steps": 761865, "loss": 1.9044, "lr": 6.314986022229189e-07, "epoch": 6.229450099427064, "percentage": 41.53, "elapsed_time": "10:39:12", "remaining_time": "14:59:56", "throughput": 8400.12, "total_tokens": 322162184} {"current_steps": 316500, "total_steps": 761865, "loss": 1.993, "lr": 6.312996688193927e-07, "epoch": 6.231418952176567, "percentage": 41.54, "elapsed_time": "10:39:23", "remaining_time": "14:59:43", "throughput": 8400.22, "total_tokens": 322263808} {"current_steps": 316600, "total_steps": 761865, "loss": 1.9723, "lr": 6.311007130894656e-07, "epoch": 6.233387804926069, "percentage": 41.56, "elapsed_time": "10:39:35", "remaining_time": "14:59:31", "throughput": 8400.34, "total_tokens": 322366208} {"current_steps": 316700, "total_steps": 761865, "loss": 1.9883, "lr": 6.309017350669677e-07, "epoch": 6.235356657675572, "percentage": 41.57, "elapsed_time": "10:39:46", "remaining_time": "14:59:18", "throughput": 8400.44, "total_tokens": 322467584} {"current_steps": 316800, "total_steps": 761865, "loss": 1.9783, "lr": 6.307027347857338e-07, "epoch": 6.237325510425075, "percentage": 41.58, "elapsed_time": "10:39:58", "remaining_time": "14:59:05", "throughput": 8400.55, "total_tokens": 322569432} {"current_steps": 316900, "total_steps": 761865, "loss": 1.9398, "lr": 6.305037122796027e-07, "epoch": 6.2392943631745785, "percentage": 41.6, "elapsed_time": "10:40:10", "remaining_time": "14:58:52", "throughput": 8400.66, "total_tokens": 322671832} {"current_steps": 317000, "total_steps": 761865, "loss": 2.0154, "lr": 6.303046675824156e-07, "epoch": 6.241263215924081, "percentage": 41.61, "elapsed_time": "10:40:21", "remaining_time": "14:58:39", "throughput": 8400.78, "total_tokens": 322774232} {"current_steps": 317100, "total_steps": 761865, "loss": 1.956, "lr": 6.301056007280189e-07, "epoch": 6.243232068673584, "percentage": 41.62, "elapsed_time": "10:40:33", "remaining_time": "14:58:27", "throughput": 8400.89, "total_tokens": 322876632} {"current_steps": 317200, "total_steps": 761865, "loss": 1.9618, "lr": 6.299065117502623e-07, "epoch": 6.245200921423087, "percentage": 41.63, "elapsed_time": "10:40:45", "remaining_time": "14:58:14", "throughput": 8401.0, "total_tokens": 322979032} {"current_steps": 317300, "total_steps": 761865, "loss": 2.0166, "lr": 6.29707400682999e-07, "epoch": 6.24716977417259, "percentage": 41.65, "elapsed_time": "10:40:56", "remaining_time": "14:58:01", "throughput": 8401.08, "total_tokens": 323079712} {"current_steps": 317400, "total_steps": 761865, "loss": 1.9586, "lr": 6.295082675600862e-07, "epoch": 6.249138626922092, "percentage": 41.66, "elapsed_time": "10:41:08", "remaining_time": "14:57:48", "throughput": 8401.2, "total_tokens": 323182112} {"current_steps": 317500, "total_steps": 761865, "loss": 1.9939, "lr": 6.293091124153847e-07, "epoch": 6.251107479671595, "percentage": 41.67, "elapsed_time": "10:41:20", "remaining_time": "14:57:35", "throughput": 8401.29, "total_tokens": 323283144} {"current_steps": 317600, "total_steps": 761865, "loss": 2.0027, "lr": 6.291099352827596e-07, "epoch": 6.253076332421098, "percentage": 41.69, "elapsed_time": "10:41:31", "remaining_time": "14:57:23", "throughput": 8401.4, "total_tokens": 323385544} {"current_steps": 317700, "total_steps": 761865, "loss": 1.9662, "lr": 6.289107361960786e-07, "epoch": 6.2550451851706015, "percentage": 41.7, "elapsed_time": "10:41:43", "remaining_time": "14:57:10", "throughput": 8401.5, "total_tokens": 323487352} {"current_steps": 317800, "total_steps": 761865, "loss": 2.022, "lr": 6.287115151892144e-07, "epoch": 6.257014037920104, "percentage": 41.71, "elapsed_time": "10:41:55", "remaining_time": "14:56:57", "throughput": 8401.6, "total_tokens": 323588072} {"current_steps": 317900, "total_steps": 761865, "loss": 1.9903, "lr": 6.285122722960426e-07, "epoch": 6.258982890669607, "percentage": 41.73, "elapsed_time": "10:42:06", "remaining_time": "14:56:44", "throughput": 8401.69, "total_tokens": 323689392} {"current_steps": 318000, "total_steps": 761865, "loss": 2.026, "lr": 6.283130075504428e-07, "epoch": 6.26095174341911, "percentage": 41.74, "elapsed_time": "10:42:18", "remaining_time": "14:56:31", "throughput": 8401.8, "total_tokens": 323791560} {"current_steps": 318100, "total_steps": 761865, "loss": 1.984, "lr": 6.281137209862984e-07, "epoch": 6.2629205961686125, "percentage": 41.75, "elapsed_time": "10:42:30", "remaining_time": "14:56:19", "throughput": 8401.9, "total_tokens": 323893424} {"current_steps": 318200, "total_steps": 761865, "loss": 1.9701, "lr": 6.279144126374962e-07, "epoch": 6.264889448918115, "percentage": 41.77, "elapsed_time": "10:42:41", "remaining_time": "14:56:06", "throughput": 8402.01, "total_tokens": 323995824} {"current_steps": 318300, "total_steps": 761865, "loss": 1.9989, "lr": 6.27715082537927e-07, "epoch": 6.266858301667618, "percentage": 41.78, "elapsed_time": "10:42:53", "remaining_time": "14:55:53", "throughput": 8402.1, "total_tokens": 324096224} {"current_steps": 318400, "total_steps": 761865, "loss": 1.9546, "lr": 6.275157307214853e-07, "epoch": 6.268827154417121, "percentage": 41.79, "elapsed_time": "10:43:04", "remaining_time": "14:55:40", "throughput": 8402.19, "total_tokens": 324196616} {"current_steps": 318500, "total_steps": 761865, "loss": 1.9438, "lr": 6.273163572220691e-07, "epoch": 6.2707960071666236, "percentage": 41.81, "elapsed_time": "10:43:16", "remaining_time": "14:55:27", "throughput": 8402.3, "total_tokens": 324299016} {"current_steps": 318600, "total_steps": 761865, "loss": 1.9761, "lr": 6.271169620735801e-07, "epoch": 6.272764859916127, "percentage": 41.82, "elapsed_time": "10:43:28", "remaining_time": "14:55:15", "throughput": 8402.41, "total_tokens": 324401416} {"current_steps": 318700, "total_steps": 761865, "loss": 2.0024, "lr": 6.269175453099241e-07, "epoch": 6.27473371266563, "percentage": 41.83, "elapsed_time": "10:43:39", "remaining_time": "14:55:02", "throughput": 8402.51, "total_tokens": 324503136} {"current_steps": 318800, "total_steps": 761865, "loss": 1.9696, "lr": 6.267181069650096e-07, "epoch": 6.276702565415133, "percentage": 41.84, "elapsed_time": "10:43:51", "remaining_time": "14:54:49", "throughput": 8402.62, "total_tokens": 324605536} {"current_steps": 318900, "total_steps": 761865, "loss": 1.9885, "lr": 6.2651864707275e-07, "epoch": 6.2786714181646355, "percentage": 41.86, "elapsed_time": "10:44:03", "remaining_time": "14:54:36", "throughput": 8402.73, "total_tokens": 324707936} {"current_steps": 319000, "total_steps": 761865, "loss": 1.9958, "lr": 6.263191656670615e-07, "epoch": 6.280640270914138, "percentage": 41.87, "elapsed_time": "10:44:14", "remaining_time": "14:54:24", "throughput": 8402.84, "total_tokens": 324810336} {"current_steps": 319100, "total_steps": 761865, "loss": 1.9889, "lr": 6.261196627818646e-07, "epoch": 6.282609123663641, "percentage": 41.88, "elapsed_time": "10:44:26", "remaining_time": "14:54:11", "throughput": 8402.94, "total_tokens": 324912024} {"current_steps": 319200, "total_steps": 761865, "loss": 1.9664, "lr": 6.259201384510824e-07, "epoch": 6.284577976413144, "percentage": 41.9, "elapsed_time": "10:44:38", "remaining_time": "14:53:58", "throughput": 8403.04, "total_tokens": 325013592} {"current_steps": 319300, "total_steps": 761865, "loss": 1.9934, "lr": 6.25720592708643e-07, "epoch": 6.2865468291626465, "percentage": 41.91, "elapsed_time": "10:44:49", "remaining_time": "14:53:45", "throughput": 8403.14, "total_tokens": 325115456} {"current_steps": 319400, "total_steps": 761865, "loss": 2.1073, "lr": 6.25521025588477e-07, "epoch": 6.28851568191215, "percentage": 41.92, "elapsed_time": "10:45:01", "remaining_time": "14:53:32", "throughput": 8403.23, "total_tokens": 325216088} {"current_steps": 319500, "total_steps": 761865, "loss": 2.0009, "lr": 6.253214371245195e-07, "epoch": 6.290484534661653, "percentage": 41.94, "elapsed_time": "10:45:13", "remaining_time": "14:53:20", "throughput": 8403.33, "total_tokens": 325318488} {"current_steps": 319600, "total_steps": 761865, "loss": 2.0127, "lr": 6.251218273507084e-07, "epoch": 6.292453387411156, "percentage": 41.95, "elapsed_time": "10:45:24", "remaining_time": "14:53:07", "throughput": 8403.44, "total_tokens": 325420888} {"current_steps": 319700, "total_steps": 761865, "loss": 2.0115, "lr": 6.249221963009859e-07, "epoch": 6.294422240160658, "percentage": 41.96, "elapsed_time": "10:45:36", "remaining_time": "14:52:54", "throughput": 8403.54, "total_tokens": 325522520} {"current_steps": 319800, "total_steps": 761865, "loss": 1.9458, "lr": 6.247225440092976e-07, "epoch": 6.296391092910161, "percentage": 41.98, "elapsed_time": "10:45:48", "remaining_time": "14:52:42", "throughput": 8403.65, "total_tokens": 325624920} {"current_steps": 319900, "total_steps": 761865, "loss": 1.9764, "lr": 6.245228705095928e-07, "epoch": 6.298359945659664, "percentage": 41.99, "elapsed_time": "10:45:59", "remaining_time": "14:52:29", "throughput": 8403.74, "total_tokens": 325725856} {"current_steps": 320000, "total_steps": 761865, "loss": 1.9396, "lr": 6.243231758358239e-07, "epoch": 6.300328798409167, "percentage": 42.0, "elapsed_time": "10:46:11", "remaining_time": "14:52:16", "throughput": 8403.85, "total_tokens": 325828256} {"current_steps": 320100, "total_steps": 761865, "loss": 1.983, "lr": 6.241234600219477e-07, "epoch": 6.3022976511586695, "percentage": 42.02, "elapsed_time": "10:46:23", "remaining_time": "14:52:04", "throughput": 8403.85, "total_tokens": 325930656} {"current_steps": 320200, "total_steps": 761865, "loss": 1.9626, "lr": 6.23923723101924e-07, "epoch": 6.304266503908173, "percentage": 42.03, "elapsed_time": "10:46:35", "remaining_time": "14:51:51", "throughput": 8403.95, "total_tokens": 326033056} {"current_steps": 320300, "total_steps": 761865, "loss": 1.9853, "lr": 6.237239651097165e-07, "epoch": 6.306235356657676, "percentage": 42.04, "elapsed_time": "10:46:46", "remaining_time": "14:51:39", "throughput": 8404.06, "total_tokens": 326135456} {"current_steps": 320400, "total_steps": 761865, "loss": 1.9929, "lr": 6.235241860792921e-07, "epoch": 6.308204209407179, "percentage": 42.05, "elapsed_time": "10:46:58", "remaining_time": "14:51:26", "throughput": 8404.16, "total_tokens": 326237272} {"current_steps": 320500, "total_steps": 761865, "loss": 1.951, "lr": 6.233243860446218e-07, "epoch": 6.310173062156681, "percentage": 42.07, "elapsed_time": "10:47:10", "remaining_time": "14:51:13", "throughput": 8404.27, "total_tokens": 326339672} {"current_steps": 320600, "total_steps": 761865, "loss": 2.0165, "lr": 6.231245650396798e-07, "epoch": 6.312141914906184, "percentage": 42.08, "elapsed_time": "10:47:21", "remaining_time": "14:51:00", "throughput": 8404.37, "total_tokens": 326441152} {"current_steps": 320700, "total_steps": 761865, "loss": 1.9924, "lr": 6.22924723098444e-07, "epoch": 6.314110767655687, "percentage": 42.09, "elapsed_time": "10:47:33", "remaining_time": "14:50:48", "throughput": 8404.48, "total_tokens": 326543376} {"current_steps": 320800, "total_steps": 761865, "loss": 2.0027, "lr": 6.227248602548958e-07, "epoch": 6.31607962040519, "percentage": 42.11, "elapsed_time": "10:47:45", "remaining_time": "14:50:35", "throughput": 8404.59, "total_tokens": 326645776} {"current_steps": 320900, "total_steps": 761865, "loss": 1.981, "lr": 6.225249765430203e-07, "epoch": 6.318048473154692, "percentage": 42.12, "elapsed_time": "10:47:56", "remaining_time": "14:50:22", "throughput": 8404.69, "total_tokens": 326748176} {"current_steps": 321000, "total_steps": 761865, "loss": 1.9753, "lr": 6.22325071996806e-07, "epoch": 6.320017325904196, "percentage": 42.13, "elapsed_time": "10:48:08", "remaining_time": "14:50:09", "throughput": 8404.8, "total_tokens": 326850576} {"current_steps": 321100, "total_steps": 761865, "loss": 1.9666, "lr": 6.221251466502447e-07, "epoch": 6.321986178653699, "percentage": 42.15, "elapsed_time": "10:48:20", "remaining_time": "14:49:57", "throughput": 8404.91, "total_tokens": 326952464} {"current_steps": 321200, "total_steps": 761865, "loss": 1.9883, "lr": 6.219252005373326e-07, "epoch": 6.323955031403202, "percentage": 42.16, "elapsed_time": "10:48:31", "remaining_time": "14:49:44", "throughput": 8405.01, "total_tokens": 327054088} {"current_steps": 321300, "total_steps": 761865, "loss": 1.9541, "lr": 6.217252336920682e-07, "epoch": 6.325923884152704, "percentage": 42.17, "elapsed_time": "10:48:43", "remaining_time": "14:49:31", "throughput": 8405.11, "total_tokens": 327155672} {"current_steps": 321400, "total_steps": 761865, "loss": 2.0029, "lr": 6.215252461484546e-07, "epoch": 6.327892736902207, "percentage": 42.19, "elapsed_time": "10:48:54", "remaining_time": "14:49:18", "throughput": 8405.19, "total_tokens": 327255728} {"current_steps": 321500, "total_steps": 761865, "loss": 2.0022, "lr": 6.21325237940498e-07, "epoch": 6.32986158965171, "percentage": 42.2, "elapsed_time": "10:49:06", "remaining_time": "14:49:05", "throughput": 8405.29, "total_tokens": 327357848} {"current_steps": 321600, "total_steps": 761865, "loss": 1.9813, "lr": 6.211252091022078e-07, "epoch": 6.331830442401213, "percentage": 42.21, "elapsed_time": "10:49:18", "remaining_time": "14:48:53", "throughput": 8405.4, "total_tokens": 327460040} {"current_steps": 321700, "total_steps": 761865, "loss": 1.9681, "lr": 6.209251596675975e-07, "epoch": 6.333799295150715, "percentage": 42.23, "elapsed_time": "10:49:29", "remaining_time": "14:48:40", "throughput": 8405.49, "total_tokens": 327561032} {"current_steps": 321800, "total_steps": 761865, "loss": 1.9965, "lr": 6.207250896706838e-07, "epoch": 6.335768147900218, "percentage": 42.24, "elapsed_time": "10:49:41", "remaining_time": "14:48:27", "throughput": 8405.58, "total_tokens": 327662536} {"current_steps": 321900, "total_steps": 761865, "loss": 2.0221, "lr": 6.205249991454868e-07, "epoch": 6.337737000649722, "percentage": 42.25, "elapsed_time": "10:49:53", "remaining_time": "14:48:14", "throughput": 8405.69, "total_tokens": 327764936} {"current_steps": 322000, "total_steps": 761865, "loss": 1.9776, "lr": 6.203248881260301e-07, "epoch": 6.3397058533992245, "percentage": 42.26, "elapsed_time": "10:50:04", "remaining_time": "14:48:02", "throughput": 8405.78, "total_tokens": 327865688} {"current_steps": 322100, "total_steps": 761865, "loss": 1.9853, "lr": 6.201247566463412e-07, "epoch": 6.341674706148727, "percentage": 42.28, "elapsed_time": "10:50:16", "remaining_time": "14:47:49", "throughput": 8405.87, "total_tokens": 327966528} {"current_steps": 322200, "total_steps": 761865, "loss": 1.9795, "lr": 6.199246047404506e-07, "epoch": 6.34364355889823, "percentage": 42.29, "elapsed_time": "10:50:28", "remaining_time": "14:47:36", "throughput": 8405.97, "total_tokens": 328068064} {"current_steps": 322300, "total_steps": 761865, "loss": 1.9746, "lr": 6.197244324423925e-07, "epoch": 6.345612411647733, "percentage": 42.3, "elapsed_time": "10:50:39", "remaining_time": "14:47:23", "throughput": 8406.07, "total_tokens": 328170464} {"current_steps": 322400, "total_steps": 761865, "loss": 1.9834, "lr": 6.195242397862043e-07, "epoch": 6.347581264397236, "percentage": 42.32, "elapsed_time": "10:50:51", "remaining_time": "14:47:11", "throughput": 8406.17, "total_tokens": 328272120} {"current_steps": 322500, "total_steps": 761865, "loss": 1.9511, "lr": 6.193240268059275e-07, "epoch": 6.349550117146738, "percentage": 42.33, "elapsed_time": "10:51:02", "remaining_time": "14:46:58", "throughput": 8406.27, "total_tokens": 328373880} {"current_steps": 322600, "total_steps": 761865, "loss": 1.9747, "lr": 6.191237935356062e-07, "epoch": 6.351518969896241, "percentage": 42.34, "elapsed_time": "10:51:14", "remaining_time": "14:46:45", "throughput": 8406.37, "total_tokens": 328475704} {"current_steps": 322700, "total_steps": 761865, "loss": 1.9615, "lr": 6.189235400092885e-07, "epoch": 6.353487822645745, "percentage": 42.36, "elapsed_time": "10:51:26", "remaining_time": "14:46:32", "throughput": 8406.48, "total_tokens": 328578104} {"current_steps": 322800, "total_steps": 761865, "loss": 1.9806, "lr": 6.187232662610259e-07, "epoch": 6.3554566753952475, "percentage": 42.37, "elapsed_time": "10:51:37", "remaining_time": "14:46:20", "throughput": 8406.58, "total_tokens": 328679928} {"current_steps": 322900, "total_steps": 761865, "loss": 1.9712, "lr": 6.185229723248731e-07, "epoch": 6.35742552814475, "percentage": 42.38, "elapsed_time": "10:51:49", "remaining_time": "14:46:07", "throughput": 8406.69, "total_tokens": 328781864} {"current_steps": 323000, "total_steps": 761865, "loss": 1.9722, "lr": 6.183226582348888e-07, "epoch": 6.359394380894253, "percentage": 42.4, "elapsed_time": "10:52:01", "remaining_time": "14:45:54", "throughput": 8406.79, "total_tokens": 328883384} {"current_steps": 323100, "total_steps": 761865, "loss": 1.9865, "lr": 6.181223240251343e-07, "epoch": 6.361363233643756, "percentage": 42.41, "elapsed_time": "10:52:12", "remaining_time": "14:45:41", "throughput": 8406.89, "total_tokens": 328985784} {"current_steps": 323200, "total_steps": 761865, "loss": 1.9655, "lr": 6.17921969729675e-07, "epoch": 6.3633320863932585, "percentage": 42.42, "elapsed_time": "10:52:24", "remaining_time": "14:45:29", "throughput": 8407.0, "total_tokens": 329087640} {"current_steps": 323300, "total_steps": 761865, "loss": 1.9763, "lr": 6.177215953825792e-07, "epoch": 6.365300939142761, "percentage": 42.44, "elapsed_time": "10:52:36", "remaining_time": "14:45:16", "throughput": 8407.1, "total_tokens": 329190040} {"current_steps": 323400, "total_steps": 761865, "loss": 1.9809, "lr": 6.175212010179191e-07, "epoch": 6.367269791892264, "percentage": 42.45, "elapsed_time": "10:52:47", "remaining_time": "14:45:03", "throughput": 8407.21, "total_tokens": 329291960} {"current_steps": 323500, "total_steps": 761865, "loss": 2.0051, "lr": 6.173207866697699e-07, "epoch": 6.369238644641767, "percentage": 42.46, "elapsed_time": "10:52:59", "remaining_time": "14:44:50", "throughput": 8407.29, "total_tokens": 329392688} {"current_steps": 323600, "total_steps": 761865, "loss": 2.0257, "lr": 6.171203523722106e-07, "epoch": 6.3712074973912705, "percentage": 42.47, "elapsed_time": "10:53:11", "remaining_time": "14:44:38", "throughput": 8407.39, "total_tokens": 329494464} {"current_steps": 323700, "total_steps": 761865, "loss": 1.958, "lr": 6.169198981593231e-07, "epoch": 6.373176350140773, "percentage": 42.49, "elapsed_time": "10:53:22", "remaining_time": "14:44:25", "throughput": 8407.49, "total_tokens": 329596000} {"current_steps": 323800, "total_steps": 761865, "loss": 2.0022, "lr": 6.167194240651931e-07, "epoch": 6.375145202890276, "percentage": 42.5, "elapsed_time": "10:53:34", "remaining_time": "14:44:12", "throughput": 8407.6, "total_tokens": 329698400} {"current_steps": 323900, "total_steps": 761865, "loss": 1.9617, "lr": 6.165189301239094e-07, "epoch": 6.377114055639779, "percentage": 42.51, "elapsed_time": "10:53:45", "remaining_time": "14:43:59", "throughput": 8407.7, "total_tokens": 329800088} {"current_steps": 324000, "total_steps": 761865, "loss": 1.9507, "lr": 6.163184163695646e-07, "epoch": 6.3790829083892815, "percentage": 42.53, "elapsed_time": "10:53:57", "remaining_time": "14:43:47", "throughput": 8407.79, "total_tokens": 329901672} {"current_steps": 324100, "total_steps": 761865, "loss": 2.0282, "lr": 6.16117882836254e-07, "epoch": 6.381051761138784, "percentage": 42.54, "elapsed_time": "10:54:09", "remaining_time": "14:43:34", "throughput": 8407.89, "total_tokens": 330003256} {"current_steps": 324200, "total_steps": 761865, "loss": 1.9634, "lr": 6.159173295580769e-07, "epoch": 6.383020613888287, "percentage": 42.55, "elapsed_time": "10:54:20", "remaining_time": "14:43:21", "throughput": 8407.99, "total_tokens": 330105136} {"current_steps": 324300, "total_steps": 761865, "loss": 1.9662, "lr": 6.157167565691356e-07, "epoch": 6.38498946663779, "percentage": 42.57, "elapsed_time": "10:54:32", "remaining_time": "14:43:08", "throughput": 8408.09, "total_tokens": 330207536} {"current_steps": 324400, "total_steps": 761865, "loss": 2.033, "lr": 6.155161639035359e-07, "epoch": 6.386958319387293, "percentage": 42.58, "elapsed_time": "10:54:44", "remaining_time": "14:42:56", "throughput": 8408.18, "total_tokens": 330308104} {"current_steps": 324500, "total_steps": 761865, "loss": 1.9661, "lr": 6.153155515953867e-07, "epoch": 6.388927172136796, "percentage": 42.59, "elapsed_time": "10:54:55", "remaining_time": "14:42:43", "throughput": 8408.28, "total_tokens": 330410504} {"current_steps": 324600, "total_steps": 761865, "loss": 1.9667, "lr": 6.151149196788007e-07, "epoch": 6.390896024886299, "percentage": 42.61, "elapsed_time": "10:55:07", "remaining_time": "14:42:30", "throughput": 8408.37, "total_tokens": 330511512} {"current_steps": 324700, "total_steps": 761865, "loss": 2.0224, "lr": 6.149142681878934e-07, "epoch": 6.392864877635802, "percentage": 42.62, "elapsed_time": "10:55:19", "remaining_time": "14:42:17", "throughput": 8408.46, "total_tokens": 330613056} {"current_steps": 324800, "total_steps": 761865, "loss": 1.9618, "lr": 6.147135971567841e-07, "epoch": 6.3948337303853044, "percentage": 42.63, "elapsed_time": "10:55:30", "remaining_time": "14:42:05", "throughput": 8408.57, "total_tokens": 330715456} {"current_steps": 324900, "total_steps": 761865, "loss": 1.9512, "lr": 6.145129066195951e-07, "epoch": 6.396802583134807, "percentage": 42.65, "elapsed_time": "10:55:42", "remaining_time": "14:41:52", "throughput": 8408.68, "total_tokens": 330817856} {"current_steps": 325000, "total_steps": 761865, "loss": 1.9715, "lr": 6.143121966104522e-07, "epoch": 6.39877143588431, "percentage": 42.66, "elapsed_time": "10:55:54", "remaining_time": "14:41:39", "throughput": 8408.78, "total_tokens": 330919608} {"current_steps": 325100, "total_steps": 761865, "loss": 1.9778, "lr": 6.141114671634844e-07, "epoch": 6.400740288633813, "percentage": 42.67, "elapsed_time": "10:56:06", "remaining_time": "14:41:27", "throughput": 8408.77, "total_tokens": 331022008} {"current_steps": 325200, "total_steps": 761865, "loss": 1.9972, "lr": 6.139107183128241e-07, "epoch": 6.4027091413833155, "percentage": 42.68, "elapsed_time": "10:56:17", "remaining_time": "14:41:14", "throughput": 8408.86, "total_tokens": 331122512} {"current_steps": 325300, "total_steps": 761865, "loss": 1.9836, "lr": 6.13709950092607e-07, "epoch": 6.404677994132819, "percentage": 42.7, "elapsed_time": "10:56:29", "remaining_time": "14:41:02", "throughput": 8408.95, "total_tokens": 331224008} {"current_steps": 325400, "total_steps": 761865, "loss": 1.989, "lr": 6.135091625369718e-07, "epoch": 6.406646846882322, "percentage": 42.71, "elapsed_time": "10:56:41", "remaining_time": "14:40:49", "throughput": 8409.05, "total_tokens": 331325904} {"current_steps": 325500, "total_steps": 761865, "loss": 1.9713, "lr": 6.133083556800609e-07, "epoch": 6.408615699631825, "percentage": 42.72, "elapsed_time": "10:56:52", "remaining_time": "14:40:36", "throughput": 8409.15, "total_tokens": 331427776} {"current_steps": 325600, "total_steps": 761865, "loss": 2.0217, "lr": 6.1310752955602e-07, "epoch": 6.410584552381327, "percentage": 42.74, "elapsed_time": "10:57:04", "remaining_time": "14:40:23", "throughput": 8409.26, "total_tokens": 331530176} {"current_steps": 325700, "total_steps": 761865, "loss": 1.9553, "lr": 6.129066841989974e-07, "epoch": 6.41255340513083, "percentage": 42.75, "elapsed_time": "10:57:16", "remaining_time": "14:40:11", "throughput": 8409.36, "total_tokens": 331631640} {"current_steps": 325800, "total_steps": 761865, "loss": 1.9457, "lr": 6.127058196431457e-07, "epoch": 6.414522257880333, "percentage": 42.76, "elapsed_time": "10:57:27", "remaining_time": "14:39:58", "throughput": 8409.46, "total_tokens": 331734040} {"current_steps": 325900, "total_steps": 761865, "loss": 1.9858, "lr": 6.125049359226199e-07, "epoch": 6.416491110629836, "percentage": 42.78, "elapsed_time": "10:57:39", "remaining_time": "14:39:45", "throughput": 8409.56, "total_tokens": 331835920} {"current_steps": 326000, "total_steps": 761865, "loss": 1.9908, "lr": 6.123040330715785e-07, "epoch": 6.418459963379339, "percentage": 42.79, "elapsed_time": "10:57:51", "remaining_time": "14:39:33", "throughput": 8409.67, "total_tokens": 331938320} {"current_steps": 326100, "total_steps": 761865, "loss": 1.9863, "lr": 6.121031111241837e-07, "epoch": 6.420428816128842, "percentage": 42.8, "elapsed_time": "10:58:02", "remaining_time": "14:39:20", "throughput": 8409.77, "total_tokens": 332040720} {"current_steps": 326200, "total_steps": 761865, "loss": 1.9864, "lr": 6.119021701146003e-07, "epoch": 6.422397668878345, "percentage": 42.82, "elapsed_time": "10:58:14", "remaining_time": "14:39:07", "throughput": 8409.88, "total_tokens": 332142592} {"current_steps": 326300, "total_steps": 761865, "loss": 1.9638, "lr": 6.117012100769967e-07, "epoch": 6.424366521627848, "percentage": 42.83, "elapsed_time": "10:58:26", "remaining_time": "14:38:55", "throughput": 8409.98, "total_tokens": 332244992} {"current_steps": 326400, "total_steps": 761865, "loss": 1.9432, "lr": 6.115002310455445e-07, "epoch": 6.42633537437735, "percentage": 42.84, "elapsed_time": "10:58:37", "remaining_time": "14:38:42", "throughput": 8410.08, "total_tokens": 332346752} {"current_steps": 326500, "total_steps": 761865, "loss": 1.9676, "lr": 6.112992330544184e-07, "epoch": 6.428304227126853, "percentage": 42.86, "elapsed_time": "10:58:49", "remaining_time": "14:38:29", "throughput": 8410.18, "total_tokens": 332448616} {"current_steps": 326600, "total_steps": 761865, "loss": 2.0212, "lr": 6.110982161377964e-07, "epoch": 6.430273079876356, "percentage": 42.87, "elapsed_time": "10:59:01", "remaining_time": "14:38:16", "throughput": 8410.28, "total_tokens": 332551016} {"current_steps": 326700, "total_steps": 761865, "loss": 1.996, "lr": 6.1089718032986e-07, "epoch": 6.432241932625859, "percentage": 42.88, "elapsed_time": "10:59:12", "remaining_time": "14:38:04", "throughput": 8410.38, "total_tokens": 332653416} {"current_steps": 326800, "total_steps": 761865, "loss": 1.9219, "lr": 6.106961256647932e-07, "epoch": 6.434210785375361, "percentage": 42.89, "elapsed_time": "10:59:24", "remaining_time": "14:37:51", "throughput": 8410.48, "total_tokens": 332755064} {"current_steps": 326900, "total_steps": 761865, "loss": 2.0384, "lr": 6.10495052176784e-07, "epoch": 6.436179638124865, "percentage": 42.91, "elapsed_time": "10:59:35", "remaining_time": "14:37:38", "throughput": 8410.57, "total_tokens": 332855528} {"current_steps": 327000, "total_steps": 761865, "loss": 1.9601, "lr": 6.102939599000231e-07, "epoch": 6.438148490874368, "percentage": 42.92, "elapsed_time": "10:59:47", "remaining_time": "14:37:25", "throughput": 8410.66, "total_tokens": 332957248} {"current_steps": 327100, "total_steps": 761865, "loss": 1.9764, "lr": 6.100928488687046e-07, "epoch": 6.440117343623871, "percentage": 42.93, "elapsed_time": "10:59:59", "remaining_time": "14:37:13", "throughput": 8410.76, "total_tokens": 333059648} {"current_steps": 327200, "total_steps": 761865, "loss": 2.0064, "lr": 6.098917191170257e-07, "epoch": 6.442086196373373, "percentage": 42.95, "elapsed_time": "11:00:10", "remaining_time": "14:37:00", "throughput": 8410.86, "total_tokens": 333161352} {"current_steps": 327300, "total_steps": 761865, "loss": 1.9555, "lr": 6.096905706791869e-07, "epoch": 6.444055049122876, "percentage": 42.96, "elapsed_time": "11:00:22", "remaining_time": "14:36:47", "throughput": 8410.96, "total_tokens": 333263152} {"current_steps": 327400, "total_steps": 761865, "loss": 1.946, "lr": 6.094894035893916e-07, "epoch": 6.446023901872379, "percentage": 42.97, "elapsed_time": "11:00:34", "remaining_time": "14:36:35", "throughput": 8411.06, "total_tokens": 333365552} {"current_steps": 327500, "total_steps": 761865, "loss": 1.9646, "lr": 6.092882178818468e-07, "epoch": 6.447992754621882, "percentage": 42.99, "elapsed_time": "11:00:45", "remaining_time": "14:36:22", "throughput": 8411.16, "total_tokens": 333467288} {"current_steps": 327600, "total_steps": 761865, "loss": 2.0014, "lr": 6.090870135907623e-07, "epoch": 6.449961607371384, "percentage": 43.0, "elapsed_time": "11:00:57", "remaining_time": "14:36:09", "throughput": 8411.26, "total_tokens": 333569056} {"current_steps": 327700, "total_steps": 761865, "loss": 1.9777, "lr": 6.088857907503513e-07, "epoch": 6.451930460120888, "percentage": 43.01, "elapsed_time": "11:01:09", "remaining_time": "14:35:56", "throughput": 8411.36, "total_tokens": 333670616} {"current_steps": 327800, "total_steps": 761865, "loss": 1.9434, "lr": 6.086845493948299e-07, "epoch": 6.453899312870391, "percentage": 43.03, "elapsed_time": "11:01:20", "remaining_time": "14:35:44", "throughput": 8411.46, "total_tokens": 333773016} {"current_steps": 327900, "total_steps": 761865, "loss": 1.9661, "lr": 6.084832895584174e-07, "epoch": 6.4558681656198935, "percentage": 43.04, "elapsed_time": "11:01:32", "remaining_time": "14:35:31", "throughput": 8411.57, "total_tokens": 333875416} {"current_steps": 328000, "total_steps": 761865, "loss": 2.0031, "lr": 6.082820112753367e-07, "epoch": 6.457837018369396, "percentage": 43.05, "elapsed_time": "11:01:44", "remaining_time": "14:35:18", "throughput": 8411.66, "total_tokens": 333976984} {"current_steps": 328100, "total_steps": 761865, "loss": 2.0056, "lr": 6.080807145798133e-07, "epoch": 6.459805871118899, "percentage": 43.07, "elapsed_time": "11:01:55", "remaining_time": "14:35:06", "throughput": 8411.76, "total_tokens": 334078616} {"current_steps": 328200, "total_steps": 761865, "loss": 2.0113, "lr": 6.078793995060758e-07, "epoch": 6.461774723868402, "percentage": 43.08, "elapsed_time": "11:02:07", "remaining_time": "14:34:53", "throughput": 8411.83, "total_tokens": 334178672} {"current_steps": 328300, "total_steps": 761865, "loss": 1.9309, "lr": 6.076780660883565e-07, "epoch": 6.4637435766179046, "percentage": 43.09, "elapsed_time": "11:02:18", "remaining_time": "14:34:40", "throughput": 8411.93, "total_tokens": 334280160} {"current_steps": 328400, "total_steps": 761865, "loss": 1.9724, "lr": 6.074767143608901e-07, "epoch": 6.465712429367407, "percentage": 43.1, "elapsed_time": "11:02:30", "remaining_time": "14:34:27", "throughput": 8412.03, "total_tokens": 334382128} {"current_steps": 328500, "total_steps": 761865, "loss": 2.0113, "lr": 6.072753443579151e-07, "epoch": 6.46768128211691, "percentage": 43.12, "elapsed_time": "11:02:42", "remaining_time": "14:34:15", "throughput": 8412.13, "total_tokens": 334483960} {"current_steps": 328600, "total_steps": 761865, "loss": 2.0152, "lr": 6.070739561136724e-07, "epoch": 6.469650134866414, "percentage": 43.13, "elapsed_time": "11:02:53", "remaining_time": "14:34:02", "throughput": 8412.21, "total_tokens": 334585072} {"current_steps": 328700, "total_steps": 761865, "loss": 1.9484, "lr": 6.068725496624068e-07, "epoch": 6.4716189876159165, "percentage": 43.14, "elapsed_time": "11:03:05", "remaining_time": "14:33:49", "throughput": 8412.32, "total_tokens": 334687472} {"current_steps": 328800, "total_steps": 761865, "loss": 1.9737, "lr": 6.066711250383653e-07, "epoch": 6.473587840365419, "percentage": 43.16, "elapsed_time": "11:03:17", "remaining_time": "14:33:37", "throughput": 8412.41, "total_tokens": 334789160} {"current_steps": 328900, "total_steps": 761865, "loss": 1.9503, "lr": 6.064696822757988e-07, "epoch": 6.475556693114922, "percentage": 43.17, "elapsed_time": "11:03:28", "remaining_time": "14:33:24", "throughput": 8412.52, "total_tokens": 334891560} {"current_steps": 329000, "total_steps": 761865, "loss": 1.97, "lr": 6.062682214089608e-07, "epoch": 6.477525545864425, "percentage": 43.18, "elapsed_time": "11:03:40", "remaining_time": "14:33:11", "throughput": 8412.62, "total_tokens": 334993960} {"current_steps": 329100, "total_steps": 761865, "loss": 2.0122, "lr": 6.060667424721081e-07, "epoch": 6.4794943986139275, "percentage": 43.2, "elapsed_time": "11:03:52", "remaining_time": "14:32:59", "throughput": 8412.72, "total_tokens": 335096360} {"current_steps": 329200, "total_steps": 761865, "loss": 1.9992, "lr": 6.058652454995004e-07, "epoch": 6.48146325136343, "percentage": 43.21, "elapsed_time": "11:04:03", "remaining_time": "14:32:46", "throughput": 8412.82, "total_tokens": 335198072} {"current_steps": 329300, "total_steps": 761865, "loss": 1.9994, "lr": 6.056637305254007e-07, "epoch": 6.483432104112933, "percentage": 43.22, "elapsed_time": "11:04:15", "remaining_time": "14:32:33", "throughput": 8412.91, "total_tokens": 335299576} {"current_steps": 329400, "total_steps": 761865, "loss": 1.9752, "lr": 6.054621975840748e-07, "epoch": 6.485400956862437, "percentage": 43.24, "elapsed_time": "11:04:27", "remaining_time": "14:32:20", "throughput": 8413.01, "total_tokens": 335401360} {"current_steps": 329500, "total_steps": 761865, "loss": 2.0178, "lr": 6.052606467097917e-07, "epoch": 6.487369809611939, "percentage": 43.25, "elapsed_time": "11:04:38", "remaining_time": "14:32:08", "throughput": 8413.11, "total_tokens": 335503760} {"current_steps": 329600, "total_steps": 761865, "loss": 1.967, "lr": 6.050590779368234e-07, "epoch": 6.489338662361442, "percentage": 43.26, "elapsed_time": "11:04:50", "remaining_time": "14:31:55", "throughput": 8413.21, "total_tokens": 335605520} {"current_steps": 329700, "total_steps": 761865, "loss": 1.9705, "lr": 6.048574912994451e-07, "epoch": 6.491307515110945, "percentage": 43.28, "elapsed_time": "11:05:01", "remaining_time": "14:31:42", "throughput": 8413.31, "total_tokens": 335707920} {"current_steps": 329800, "total_steps": 761865, "loss": 1.9384, "lr": 6.046558868319347e-07, "epoch": 6.493276367860448, "percentage": 43.29, "elapsed_time": "11:05:13", "remaining_time": "14:31:30", "throughput": 8413.41, "total_tokens": 335810320} {"current_steps": 329900, "total_steps": 761865, "loss": 1.9509, "lr": 6.044542645685735e-07, "epoch": 6.4952452206099505, "percentage": 43.3, "elapsed_time": "11:05:25", "remaining_time": "14:31:17", "throughput": 8413.52, "total_tokens": 335912720} {"current_steps": 330000, "total_steps": 761865, "loss": 1.9802, "lr": 6.042526245436455e-07, "epoch": 6.497214073359453, "percentage": 43.31, "elapsed_time": "11:05:36", "remaining_time": "14:31:04", "throughput": 8413.61, "total_tokens": 336014264} {"current_steps": 330100, "total_steps": 761865, "loss": 2.009, "lr": 6.040509667914382e-07, "epoch": 6.499182926108956, "percentage": 43.33, "elapsed_time": "11:05:49", "remaining_time": "14:30:52", "throughput": 8413.6, "total_tokens": 336116576} {"current_steps": 330200, "total_steps": 761865, "loss": 1.9367, "lr": 6.038492913462417e-07, "epoch": 6.501151778858459, "percentage": 43.34, "elapsed_time": "11:06:00", "remaining_time": "14:30:40", "throughput": 8413.71, "total_tokens": 336218976} {"current_steps": 330300, "total_steps": 761865, "loss": 1.9565, "lr": 6.036475982423488e-07, "epoch": 6.503120631607962, "percentage": 43.35, "elapsed_time": "11:06:12", "remaining_time": "14:30:27", "throughput": 8413.79, "total_tokens": 336319424} {"current_steps": 330400, "total_steps": 761865, "loss": 1.9525, "lr": 6.034458875140563e-07, "epoch": 6.505089484357465, "percentage": 43.37, "elapsed_time": "11:06:24", "remaining_time": "14:30:14", "throughput": 8413.88, "total_tokens": 336420968} {"current_steps": 330500, "total_steps": 761865, "loss": 1.9453, "lr": 6.032441591956628e-07, "epoch": 6.507058337106968, "percentage": 43.38, "elapsed_time": "11:06:35", "remaining_time": "14:30:01", "throughput": 8413.98, "total_tokens": 336523368} {"current_steps": 330600, "total_steps": 761865, "loss": 1.9638, "lr": 6.030424133214711e-07, "epoch": 6.509027189856471, "percentage": 43.39, "elapsed_time": "11:06:47", "remaining_time": "14:29:49", "throughput": 8414.08, "total_tokens": 336624960} {"current_steps": 330700, "total_steps": 761865, "loss": 1.9829, "lr": 6.02840649925786e-07, "epoch": 6.510996042605973, "percentage": 43.41, "elapsed_time": "11:06:59", "remaining_time": "14:29:36", "throughput": 8414.18, "total_tokens": 336727360} {"current_steps": 330800, "total_steps": 761865, "loss": 2.0137, "lr": 6.026388690429158e-07, "epoch": 6.512964895355476, "percentage": 43.42, "elapsed_time": "11:07:10", "remaining_time": "14:29:23", "throughput": 8414.28, "total_tokens": 336828952} {"current_steps": 330900, "total_steps": 761865, "loss": 1.948, "lr": 6.024370707071717e-07, "epoch": 6.514933748104979, "percentage": 43.43, "elapsed_time": "11:07:22", "remaining_time": "14:29:11", "throughput": 8414.37, "total_tokens": 336930544} {"current_steps": 331000, "total_steps": 761865, "loss": 1.9875, "lr": 6.022352549528675e-07, "epoch": 6.516902600854483, "percentage": 43.45, "elapsed_time": "11:07:33", "remaining_time": "14:28:58", "throughput": 8414.47, "total_tokens": 337032312} {"current_steps": 331100, "total_steps": 761865, "loss": 2.0037, "lr": 6.020334218143206e-07, "epoch": 6.518871453603985, "percentage": 43.46, "elapsed_time": "11:07:45", "remaining_time": "14:28:45", "throughput": 8414.55, "total_tokens": 337133152} {"current_steps": 331200, "total_steps": 761865, "loss": 1.9783, "lr": 6.01831571325851e-07, "epoch": 6.520840306353488, "percentage": 43.47, "elapsed_time": "11:07:57", "remaining_time": "14:28:32", "throughput": 8414.64, "total_tokens": 337234616} {"current_steps": 331300, "total_steps": 761865, "loss": 1.9855, "lr": 6.016297035217816e-07, "epoch": 6.522809159102991, "percentage": 43.49, "elapsed_time": "11:08:08", "remaining_time": "14:28:20", "throughput": 8414.74, "total_tokens": 337337016} {"current_steps": 331400, "total_steps": 761865, "loss": 2.0007, "lr": 6.014278184364382e-07, "epoch": 6.524778011852494, "percentage": 43.5, "elapsed_time": "11:08:20", "remaining_time": "14:28:07", "throughput": 8414.84, "total_tokens": 337439128} {"current_steps": 331500, "total_steps": 761865, "loss": 1.9533, "lr": 6.012259161041497e-07, "epoch": 6.526746864601996, "percentage": 43.51, "elapsed_time": "11:08:32", "remaining_time": "14:27:54", "throughput": 8414.93, "total_tokens": 337540664} {"current_steps": 331600, "total_steps": 761865, "loss": 2.0135, "lr": 6.010239965592482e-07, "epoch": 6.528715717351499, "percentage": 43.52, "elapsed_time": "11:08:43", "remaining_time": "14:27:42", "throughput": 8415.02, "total_tokens": 337641112} {"current_steps": 331700, "total_steps": 761865, "loss": 1.9419, "lr": 6.008220598360679e-07, "epoch": 6.530684570101002, "percentage": 43.54, "elapsed_time": "11:08:55", "remaining_time": "14:27:29", "throughput": 8415.12, "total_tokens": 337742960} {"current_steps": 331800, "total_steps": 761865, "loss": 1.982, "lr": 6.006201059689468e-07, "epoch": 6.532653422850505, "percentage": 43.55, "elapsed_time": "11:09:06", "remaining_time": "14:27:16", "throughput": 8415.22, "total_tokens": 337845360} {"current_steps": 331900, "total_steps": 761865, "loss": 2.0188, "lr": 6.004181349922253e-07, "epoch": 6.534622275600007, "percentage": 43.56, "elapsed_time": "11:09:18", "remaining_time": "14:27:04", "throughput": 8415.31, "total_tokens": 337947008} {"current_steps": 332000, "total_steps": 761865, "loss": 1.9757, "lr": 6.002161469402469e-07, "epoch": 6.536591128349511, "percentage": 43.58, "elapsed_time": "11:09:30", "remaining_time": "14:26:51", "throughput": 8415.41, "total_tokens": 338049408} {"current_steps": 332100, "total_steps": 761865, "loss": 1.9633, "lr": 6.000141418473581e-07, "epoch": 6.538559981099014, "percentage": 43.59, "elapsed_time": "11:09:41", "remaining_time": "14:26:38", "throughput": 8415.5, "total_tokens": 338150376} {"current_steps": 332200, "total_steps": 761865, "loss": 2.0123, "lr": 5.99812119747908e-07, "epoch": 6.540528833848517, "percentage": 43.6, "elapsed_time": "11:09:53", "remaining_time": "14:26:25", "throughput": 8415.58, "total_tokens": 338251064} {"current_steps": 332300, "total_steps": 761865, "loss": 2.0188, "lr": 5.996100806762487e-07, "epoch": 6.542497686598019, "percentage": 43.62, "elapsed_time": "11:10:05", "remaining_time": "14:26:13", "throughput": 8415.68, "total_tokens": 338353016} {"current_steps": 332400, "total_steps": 761865, "loss": 1.9853, "lr": 5.994080246667354e-07, "epoch": 6.544466539347522, "percentage": 43.63, "elapsed_time": "11:10:16", "remaining_time": "14:26:00", "throughput": 8415.78, "total_tokens": 338455416} {"current_steps": 332500, "total_steps": 761865, "loss": 1.969, "lr": 5.992059517537259e-07, "epoch": 6.546435392097025, "percentage": 43.64, "elapsed_time": "11:10:28", "remaining_time": "14:25:47", "throughput": 8415.88, "total_tokens": 338557264} {"current_steps": 332600, "total_steps": 761865, "loss": 2.0201, "lr": 5.990038619715811e-07, "epoch": 6.548404244846528, "percentage": 43.66, "elapsed_time": "11:10:39", "remaining_time": "14:25:35", "throughput": 8415.97, "total_tokens": 338658312} {"current_steps": 332700, "total_steps": 761865, "loss": 2.0123, "lr": 5.988017553546646e-07, "epoch": 6.550373097596031, "percentage": 43.67, "elapsed_time": "11:10:51", "remaining_time": "14:25:22", "throughput": 8416.06, "total_tokens": 338759352} {"current_steps": 332800, "total_steps": 761865, "loss": 2.0006, "lr": 5.98599631937343e-07, "epoch": 6.552341950345534, "percentage": 43.68, "elapsed_time": "11:11:03", "remaining_time": "14:25:09", "throughput": 8416.15, "total_tokens": 338861536} {"current_steps": 332900, "total_steps": 761865, "loss": 1.9879, "lr": 5.983974917539855e-07, "epoch": 6.554310803095037, "percentage": 43.7, "elapsed_time": "11:11:14", "remaining_time": "14:24:57", "throughput": 8416.25, "total_tokens": 338963936} {"current_steps": 333000, "total_steps": 761865, "loss": 2.0082, "lr": 5.981953348389645e-07, "epoch": 6.5562796558445395, "percentage": 43.71, "elapsed_time": "11:11:26", "remaining_time": "14:24:44", "throughput": 8416.35, "total_tokens": 339066336} {"current_steps": 333100, "total_steps": 761865, "loss": 1.9956, "lr": 5.97993161226655e-07, "epoch": 6.558248508594042, "percentage": 43.72, "elapsed_time": "11:11:38", "remaining_time": "14:24:31", "throughput": 8416.45, "total_tokens": 339168080} {"current_steps": 333200, "total_steps": 761865, "loss": 1.9451, "lr": 5.977909709514349e-07, "epoch": 6.560217361343545, "percentage": 43.73, "elapsed_time": "11:11:49", "remaining_time": "14:24:19", "throughput": 8416.55, "total_tokens": 339270480} {"current_steps": 333300, "total_steps": 761865, "loss": 2.0153, "lr": 5.975887640476852e-07, "epoch": 6.562186214093048, "percentage": 43.75, "elapsed_time": "11:12:01", "remaining_time": "14:24:06", "throughput": 8416.63, "total_tokens": 339370784} {"current_steps": 333400, "total_steps": 761865, "loss": 1.9787, "lr": 5.97386540549789e-07, "epoch": 6.564155066842551, "percentage": 43.76, "elapsed_time": "11:12:13", "remaining_time": "14:23:53", "throughput": 8416.72, "total_tokens": 339472264} {"current_steps": 333500, "total_steps": 761865, "loss": 1.9873, "lr": 5.971843004921332e-07, "epoch": 6.566123919592053, "percentage": 43.77, "elapsed_time": "11:12:24", "remaining_time": "14:23:40", "throughput": 8416.81, "total_tokens": 339573752} {"current_steps": 333600, "total_steps": 761865, "loss": 2.0252, "lr": 5.969820439091066e-07, "epoch": 6.568092772341556, "percentage": 43.79, "elapsed_time": "11:12:36", "remaining_time": "14:23:28", "throughput": 8416.91, "total_tokens": 339676152} {"current_steps": 333700, "total_steps": 761865, "loss": 1.9662, "lr": 5.967797708351016e-07, "epoch": 6.57006162509106, "percentage": 43.8, "elapsed_time": "11:12:48", "remaining_time": "14:23:15", "throughput": 8417.0, "total_tokens": 339778552} {"current_steps": 333800, "total_steps": 761865, "loss": 1.9947, "lr": 5.965774813045128e-07, "epoch": 6.5720304778405625, "percentage": 43.81, "elapsed_time": "11:12:59", "remaining_time": "14:23:03", "throughput": 8417.1, "total_tokens": 339880824} {"current_steps": 333900, "total_steps": 761865, "loss": 1.9986, "lr": 5.963751753517378e-07, "epoch": 6.573999330590065, "percentage": 43.83, "elapsed_time": "11:13:11", "remaining_time": "14:22:50", "throughput": 8417.2, "total_tokens": 339983224} {"current_steps": 334000, "total_steps": 761865, "loss": 1.9697, "lr": 5.961728530111771e-07, "epoch": 6.575968183339568, "percentage": 43.84, "elapsed_time": "11:13:23", "remaining_time": "14:22:37", "throughput": 8417.3, "total_tokens": 340084880} {"current_steps": 334100, "total_steps": 761865, "loss": 2.0124, "lr": 5.95970514317234e-07, "epoch": 6.577937036089071, "percentage": 43.85, "elapsed_time": "11:13:34", "remaining_time": "14:22:25", "throughput": 8417.4, "total_tokens": 340187280} {"current_steps": 334200, "total_steps": 761865, "loss": 1.9799, "lr": 5.957681593043144e-07, "epoch": 6.5799058888385735, "percentage": 43.87, "elapsed_time": "11:13:46", "remaining_time": "14:22:12", "throughput": 8417.49, "total_tokens": 340288896} {"current_steps": 334300, "total_steps": 761865, "loss": 1.9683, "lr": 5.95565788006827e-07, "epoch": 6.581874741588076, "percentage": 43.88, "elapsed_time": "11:13:58", "remaining_time": "14:21:59", "throughput": 8417.59, "total_tokens": 340391296} {"current_steps": 334400, "total_steps": 761865, "loss": 1.9453, "lr": 5.953634004591833e-07, "epoch": 6.58384359433758, "percentage": 43.89, "elapsed_time": "11:14:09", "remaining_time": "14:21:46", "throughput": 8417.67, "total_tokens": 340491568} {"current_steps": 334500, "total_steps": 761865, "loss": 1.9641, "lr": 5.951609966957978e-07, "epoch": 6.585812447087083, "percentage": 43.91, "elapsed_time": "11:14:21", "remaining_time": "14:21:34", "throughput": 8417.75, "total_tokens": 340592192} {"current_steps": 334600, "total_steps": 761865, "loss": 1.9991, "lr": 5.949585767510874e-07, "epoch": 6.5877812998365854, "percentage": 43.92, "elapsed_time": "11:14:32", "remaining_time": "14:21:21", "throughput": 8417.85, "total_tokens": 340694592} {"current_steps": 334700, "total_steps": 761865, "loss": 1.9617, "lr": 5.94756140659472e-07, "epoch": 6.589750152586088, "percentage": 43.93, "elapsed_time": "11:14:44", "remaining_time": "14:21:08", "throughput": 8417.95, "total_tokens": 340796992} {"current_steps": 334800, "total_steps": 761865, "loss": 2.0403, "lr": 5.94553688455374e-07, "epoch": 6.591719005335591, "percentage": 43.94, "elapsed_time": "11:14:56", "remaining_time": "14:20:56", "throughput": 8418.05, "total_tokens": 340899008} {"current_steps": 334900, "total_steps": 761865, "loss": 2.0017, "lr": 5.943512201732189e-07, "epoch": 6.593687858085094, "percentage": 43.96, "elapsed_time": "11:15:07", "remaining_time": "14:20:43", "throughput": 8418.15, "total_tokens": 341001408} {"current_steps": 335000, "total_steps": 761865, "loss": 1.9468, "lr": 5.941487358474344e-07, "epoch": 6.5956567108345965, "percentage": 43.97, "elapsed_time": "11:15:19", "remaining_time": "14:20:30", "throughput": 8418.24, "total_tokens": 341102960} {"current_steps": 335100, "total_steps": 761865, "loss": 2.0083, "lr": 5.939462355124516e-07, "epoch": 6.597625563584099, "percentage": 43.98, "elapsed_time": "11:15:31", "remaining_time": "14:20:18", "throughput": 8418.22, "total_tokens": 341204744} {"current_steps": 335200, "total_steps": 761865, "loss": 2.0086, "lr": 5.937437192027037e-07, "epoch": 6.599594416333602, "percentage": 44.0, "elapsed_time": "11:15:43", "remaining_time": "14:20:06", "throughput": 8418.3, "total_tokens": 341305304} {"current_steps": 335300, "total_steps": 761865, "loss": 1.9781, "lr": 5.935411869526273e-07, "epoch": 6.601563269083106, "percentage": 44.01, "elapsed_time": "11:15:54", "remaining_time": "14:19:53", "throughput": 8418.4, "total_tokens": 341407704} {"current_steps": 335400, "total_steps": 761865, "loss": 1.9822, "lr": 5.933386387966608e-07, "epoch": 6.603532121832608, "percentage": 44.02, "elapsed_time": "11:16:06", "remaining_time": "14:19:40", "throughput": 8418.5, "total_tokens": 341510104} {"current_steps": 335500, "total_steps": 761865, "loss": 2.0323, "lr": 5.931360747692461e-07, "epoch": 6.605500974582111, "percentage": 44.04, "elapsed_time": "11:16:18", "remaining_time": "14:19:28", "throughput": 8418.6, "total_tokens": 341612504} {"current_steps": 335600, "total_steps": 761865, "loss": 1.9899, "lr": 5.929334949048274e-07, "epoch": 6.607469827331614, "percentage": 44.05, "elapsed_time": "11:16:29", "remaining_time": "14:19:15", "throughput": 8418.69, "total_tokens": 341714080} {"current_steps": 335700, "total_steps": 761865, "loss": 2.0027, "lr": 5.927308992378518e-07, "epoch": 6.609438680081117, "percentage": 44.06, "elapsed_time": "11:16:41", "remaining_time": "14:19:02", "throughput": 8418.79, "total_tokens": 341816480} {"current_steps": 335800, "total_steps": 761865, "loss": 2.004, "lr": 5.925282878027688e-07, "epoch": 6.611407532830619, "percentage": 44.08, "elapsed_time": "11:16:53", "remaining_time": "14:18:50", "throughput": 8418.88, "total_tokens": 341918184} {"current_steps": 335900, "total_steps": 761865, "loss": 2.0263, "lr": 5.92325660634031e-07, "epoch": 6.613376385580122, "percentage": 44.09, "elapsed_time": "11:17:04", "remaining_time": "14:18:37", "throughput": 8418.98, "total_tokens": 342019904} {"current_steps": 336000, "total_steps": 761865, "loss": 2.0009, "lr": 5.921230177660932e-07, "epoch": 6.615345238329625, "percentage": 44.1, "elapsed_time": "11:17:16", "remaining_time": "14:18:25", "throughput": 8419.08, "total_tokens": 342122304} {"current_steps": 336100, "total_steps": 761865, "loss": 2.002, "lr": 5.919203592334132e-07, "epoch": 6.617314091079129, "percentage": 44.12, "elapsed_time": "11:17:28", "remaining_time": "14:18:12", "throughput": 8419.18, "total_tokens": 342224272} {"current_steps": 336200, "total_steps": 761865, "loss": 1.9729, "lr": 5.917176850704515e-07, "epoch": 6.619282943828631, "percentage": 44.13, "elapsed_time": "11:17:39", "remaining_time": "14:17:59", "throughput": 8419.28, "total_tokens": 342326672} {"current_steps": 336300, "total_steps": 761865, "loss": 2.0465, "lr": 5.91514995311671e-07, "epoch": 6.621251796578134, "percentage": 44.14, "elapsed_time": "11:17:51", "remaining_time": "14:17:46", "throughput": 8419.34, "total_tokens": 342426264} {"current_steps": 336400, "total_steps": 761865, "loss": 1.9889, "lr": 5.913122899915375e-07, "epoch": 6.623220649327637, "percentage": 44.15, "elapsed_time": "11:18:03", "remaining_time": "14:17:34", "throughput": 8419.44, "total_tokens": 342528032} {"current_steps": 336500, "total_steps": 761865, "loss": 1.9909, "lr": 5.911095691445192e-07, "epoch": 6.62518950207714, "percentage": 44.17, "elapsed_time": "11:18:14", "remaining_time": "14:17:21", "throughput": 8419.53, "total_tokens": 342629840} {"current_steps": 336600, "total_steps": 761865, "loss": 1.9538, "lr": 5.909068328050871e-07, "epoch": 6.627158354826642, "percentage": 44.18, "elapsed_time": "11:18:26", "remaining_time": "14:17:08", "throughput": 8419.63, "total_tokens": 342732240} {"current_steps": 336700, "total_steps": 761865, "loss": 1.9459, "lr": 5.907040810077149e-07, "epoch": 6.629127207576145, "percentage": 44.19, "elapsed_time": "11:18:38", "remaining_time": "14:16:56", "throughput": 8419.73, "total_tokens": 342834640} {"current_steps": 336800, "total_steps": 761865, "loss": 1.948, "lr": 5.905013137868786e-07, "epoch": 6.631096060325648, "percentage": 44.21, "elapsed_time": "11:18:49", "remaining_time": "14:16:43", "throughput": 8419.83, "total_tokens": 342937040} {"current_steps": 336900, "total_steps": 761865, "loss": 1.994, "lr": 5.902985311770574e-07, "epoch": 6.633064913075151, "percentage": 44.22, "elapsed_time": "11:19:01", "remaining_time": "14:16:31", "throughput": 8419.91, "total_tokens": 343038568} {"current_steps": 337000, "total_steps": 761865, "loss": 1.9739, "lr": 5.900957332127324e-07, "epoch": 6.635033765824654, "percentage": 44.23, "elapsed_time": "11:19:13", "remaining_time": "14:16:18", "throughput": 8420.01, "total_tokens": 343140968} {"current_steps": 337100, "total_steps": 761865, "loss": 2.0175, "lr": 5.898929199283879e-07, "epoch": 6.637002618574157, "percentage": 44.25, "elapsed_time": "11:19:24", "remaining_time": "14:16:05", "throughput": 8420.1, "total_tokens": 343241880} {"current_steps": 337200, "total_steps": 761865, "loss": 1.9806, "lr": 5.896900913585108e-07, "epoch": 6.63897147132366, "percentage": 44.26, "elapsed_time": "11:19:36", "remaining_time": "14:15:53", "throughput": 8420.19, "total_tokens": 343344232} {"current_steps": 337300, "total_steps": 761865, "loss": 1.9897, "lr": 5.894872475375898e-07, "epoch": 6.640940324073163, "percentage": 44.27, "elapsed_time": "11:19:47", "remaining_time": "14:15:40", "throughput": 8420.28, "total_tokens": 343445784} {"current_steps": 337400, "total_steps": 761865, "loss": 1.9749, "lr": 5.892843885001174e-07, "epoch": 6.642909176822665, "percentage": 44.29, "elapsed_time": "11:19:59", "remaining_time": "14:15:27", "throughput": 8420.38, "total_tokens": 343548184} {"current_steps": 337500, "total_steps": 761865, "loss": 2.027, "lr": 5.890815142805877e-07, "epoch": 6.644878029572168, "percentage": 44.3, "elapsed_time": "11:20:11", "remaining_time": "14:15:15", "throughput": 8420.48, "total_tokens": 343650584} {"current_steps": 337600, "total_steps": 761865, "loss": 1.9785, "lr": 5.88878624913498e-07, "epoch": 6.646846882321671, "percentage": 44.31, "elapsed_time": "11:20:22", "remaining_time": "14:15:02", "throughput": 8420.58, "total_tokens": 343752984} {"current_steps": 337700, "total_steps": 761865, "loss": 1.9714, "lr": 5.886757204333474e-07, "epoch": 6.6488157350711745, "percentage": 44.33, "elapsed_time": "11:20:34", "remaining_time": "14:14:49", "throughput": 8420.66, "total_tokens": 343853312} {"current_steps": 337800, "total_steps": 761865, "loss": 1.9606, "lr": 5.884728008746388e-07, "epoch": 6.650784587820677, "percentage": 44.34, "elapsed_time": "11:20:46", "remaining_time": "14:14:37", "throughput": 8420.75, "total_tokens": 343955088} {"current_steps": 337900, "total_steps": 761865, "loss": 1.9502, "lr": 5.882698662718765e-07, "epoch": 6.65275344057018, "percentage": 44.35, "elapsed_time": "11:20:57", "remaining_time": "14:14:24", "throughput": 8420.85, "total_tokens": 344057488} {"current_steps": 338000, "total_steps": 761865, "loss": 1.9567, "lr": 5.880669166595679e-07, "epoch": 6.654722293319683, "percentage": 44.36, "elapsed_time": "11:21:09", "remaining_time": "14:14:11", "throughput": 8420.95, "total_tokens": 344159272} {"current_steps": 338100, "total_steps": 761865, "loss": 1.9406, "lr": 5.878639520722228e-07, "epoch": 6.6566911460691855, "percentage": 44.38, "elapsed_time": "11:21:21", "remaining_time": "14:13:59", "throughput": 8421.04, "total_tokens": 344261216} {"current_steps": 338200, "total_steps": 761865, "loss": 1.9812, "lr": 5.87660972544354e-07, "epoch": 6.658659998818688, "percentage": 44.39, "elapsed_time": "11:21:32", "remaining_time": "14:13:46", "throughput": 8421.14, "total_tokens": 344363616} {"current_steps": 338300, "total_steps": 761865, "loss": 1.9939, "lr": 5.874579781104761e-07, "epoch": 6.660628851568191, "percentage": 44.4, "elapsed_time": "11:21:44", "remaining_time": "14:13:33", "throughput": 8421.24, "total_tokens": 344466016} {"current_steps": 338400, "total_steps": 761865, "loss": 1.9588, "lr": 5.872549688051066e-07, "epoch": 6.662597704317694, "percentage": 44.42, "elapsed_time": "11:21:56", "remaining_time": "14:13:21", "throughput": 8421.33, "total_tokens": 344567736} {"current_steps": 338500, "total_steps": 761865, "loss": 2.0107, "lr": 5.870519446627656e-07, "epoch": 6.664566557067197, "percentage": 44.43, "elapsed_time": "11:22:07", "remaining_time": "14:13:08", "throughput": 8421.39, "total_tokens": 344666912} {"current_steps": 338600, "total_steps": 761865, "loss": 1.9665, "lr": 5.868489057179757e-07, "epoch": 6.666535409816699, "percentage": 44.44, "elapsed_time": "11:22:19", "remaining_time": "14:12:55", "throughput": 8421.48, "total_tokens": 344768880} {"current_steps": 338700, "total_steps": 761865, "loss": 1.9924, "lr": 5.86645852005262e-07, "epoch": 6.668504262566203, "percentage": 44.46, "elapsed_time": "11:22:30", "remaining_time": "14:12:43", "throughput": 8421.57, "total_tokens": 344870384} {"current_steps": 338800, "total_steps": 761865, "loss": 1.9494, "lr": 5.864427835591518e-07, "epoch": 6.670473115315706, "percentage": 44.47, "elapsed_time": "11:22:42", "remaining_time": "14:12:30", "throughput": 8421.65, "total_tokens": 344971976} {"current_steps": 338900, "total_steps": 761865, "loss": 2.0234, "lr": 5.862397004141754e-07, "epoch": 6.6724419680652085, "percentage": 44.48, "elapsed_time": "11:22:54", "remaining_time": "14:12:17", "throughput": 8421.73, "total_tokens": 345072800} {"current_steps": 339000, "total_steps": 761865, "loss": 2.0197, "lr": 5.860366026048654e-07, "epoch": 6.674410820814711, "percentage": 44.5, "elapsed_time": "11:23:05", "remaining_time": "14:12:05", "throughput": 8421.81, "total_tokens": 345173656} {"current_steps": 339100, "total_steps": 761865, "loss": 1.9947, "lr": 5.858334901657565e-07, "epoch": 6.676379673564214, "percentage": 44.51, "elapsed_time": "11:23:17", "remaining_time": "14:11:52", "throughput": 8421.9, "total_tokens": 345275320} {"current_steps": 339200, "total_steps": 761865, "loss": 2.0067, "lr": 5.85630363131387e-07, "epoch": 6.678348526313717, "percentage": 44.52, "elapsed_time": "11:23:28", "remaining_time": "14:11:39", "throughput": 8421.99, "total_tokens": 345376992} {"current_steps": 339300, "total_steps": 761865, "loss": 2.0146, "lr": 5.85427221536296e-07, "epoch": 6.6803173790632195, "percentage": 44.54, "elapsed_time": "11:23:40", "remaining_time": "14:11:27", "throughput": 8422.08, "total_tokens": 345479392} {"current_steps": 339400, "total_steps": 761865, "loss": 2.0072, "lr": 5.852240654150268e-07, "epoch": 6.682286231812723, "percentage": 44.55, "elapsed_time": "11:23:52", "remaining_time": "14:11:14", "throughput": 8422.18, "total_tokens": 345581216} {"current_steps": 339500, "total_steps": 761865, "loss": 2.0149, "lr": 5.850208948021241e-07, "epoch": 6.684255084562226, "percentage": 44.56, "elapsed_time": "11:24:03", "remaining_time": "14:11:01", "throughput": 8422.27, "total_tokens": 345683072} {"current_steps": 339600, "total_steps": 761865, "loss": 1.9422, "lr": 5.848177097321354e-07, "epoch": 6.686223937311729, "percentage": 44.57, "elapsed_time": "11:24:15", "remaining_time": "14:10:49", "throughput": 8422.37, "total_tokens": 345785472} {"current_steps": 339700, "total_steps": 761865, "loss": 1.916, "lr": 5.846145102396104e-07, "epoch": 6.6881927900612315, "percentage": 44.59, "elapsed_time": "11:24:27", "remaining_time": "14:10:36", "throughput": 8422.47, "total_tokens": 345887872} {"current_steps": 339800, "total_steps": 761865, "loss": 1.9643, "lr": 5.844112963591017e-07, "epoch": 6.690161642810734, "percentage": 44.6, "elapsed_time": "11:24:38", "remaining_time": "14:10:24", "throughput": 8422.56, "total_tokens": 345990272} {"current_steps": 339900, "total_steps": 761865, "loss": 2.0061, "lr": 5.842080681251638e-07, "epoch": 6.692130495560237, "percentage": 44.61, "elapsed_time": "11:24:50", "remaining_time": "14:10:11", "throughput": 8422.65, "total_tokens": 346091328} {"current_steps": 340000, "total_steps": 761865, "loss": 2.013, "lr": 5.840048255723544e-07, "epoch": 6.69409934830974, "percentage": 44.63, "elapsed_time": "11:25:02", "remaining_time": "14:09:58", "throughput": 8422.73, "total_tokens": 346192800} {"current_steps": 340100, "total_steps": 761865, "loss": 1.9896, "lr": 5.838015687352327e-07, "epoch": 6.6960682010592425, "percentage": 44.64, "elapsed_time": "11:25:14", "remaining_time": "14:09:46", "throughput": 8422.71, "total_tokens": 346294408} {"current_steps": 340200, "total_steps": 761865, "loss": 1.9382, "lr": 5.835982976483613e-07, "epoch": 6.698037053808745, "percentage": 44.65, "elapsed_time": "11:25:26", "remaining_time": "14:09:34", "throughput": 8422.81, "total_tokens": 346396808} {"current_steps": 340300, "total_steps": 761865, "loss": 1.9993, "lr": 5.833950123463043e-07, "epoch": 6.700005906558248, "percentage": 44.67, "elapsed_time": "11:25:37", "remaining_time": "14:09:21", "throughput": 8422.89, "total_tokens": 346497864} {"current_steps": 340400, "total_steps": 761865, "loss": 1.961, "lr": 5.83191712863629e-07, "epoch": 6.701974759307752, "percentage": 44.68, "elapsed_time": "11:25:49", "remaining_time": "14:09:08", "throughput": 8422.99, "total_tokens": 346600264} {"current_steps": 340500, "total_steps": 761865, "loss": 1.985, "lr": 5.829883992349045e-07, "epoch": 6.703943612057254, "percentage": 44.69, "elapsed_time": "11:26:00", "remaining_time": "14:08:56", "throughput": 8423.08, "total_tokens": 346701840} {"current_steps": 340600, "total_steps": 761865, "loss": 1.9871, "lr": 5.827850714947028e-07, "epoch": 6.705912464806757, "percentage": 44.71, "elapsed_time": "11:26:12", "remaining_time": "14:08:43", "throughput": 8423.17, "total_tokens": 346803280} {"current_steps": 340700, "total_steps": 761865, "loss": 1.9796, "lr": 5.825817296775978e-07, "epoch": 6.70788131755626, "percentage": 44.72, "elapsed_time": "11:26:24", "remaining_time": "14:08:30", "throughput": 8423.26, "total_tokens": 346905576} {"current_steps": 340800, "total_steps": 761865, "loss": 1.9752, "lr": 5.823783738181662e-07, "epoch": 6.709850170305763, "percentage": 44.73, "elapsed_time": "11:26:35", "remaining_time": "14:08:18", "throughput": 8423.35, "total_tokens": 347007240} {"current_steps": 340900, "total_steps": 761865, "loss": 1.9913, "lr": 5.821750039509869e-07, "epoch": 6.7118190230552655, "percentage": 44.75, "elapsed_time": "11:26:47", "remaining_time": "14:08:05", "throughput": 8423.45, "total_tokens": 347109120} {"current_steps": 341000, "total_steps": 761865, "loss": 1.9771, "lr": 5.819716201106415e-07, "epoch": 6.713787875804768, "percentage": 44.76, "elapsed_time": "11:26:59", "remaining_time": "14:07:53", "throughput": 8423.54, "total_tokens": 347211152} {"current_steps": 341100, "total_steps": 761865, "loss": 1.9602, "lr": 5.817682223317133e-07, "epoch": 6.715756728554272, "percentage": 44.77, "elapsed_time": "11:27:10", "remaining_time": "14:07:40", "throughput": 8423.64, "total_tokens": 347313448} {"current_steps": 341200, "total_steps": 761865, "loss": 2.0098, "lr": 5.815648106487885e-07, "epoch": 6.717725581303775, "percentage": 44.78, "elapsed_time": "11:27:22", "remaining_time": "14:07:27", "throughput": 8423.72, "total_tokens": 347414544} {"current_steps": 341300, "total_steps": 761865, "loss": 2.0203, "lr": 5.813613850964557e-07, "epoch": 6.719694434053277, "percentage": 44.8, "elapsed_time": "11:27:34", "remaining_time": "14:07:15", "throughput": 8423.8, "total_tokens": 347515848} {"current_steps": 341400, "total_steps": 761865, "loss": 2.0277, "lr": 5.811579457093056e-07, "epoch": 6.72166328680278, "percentage": 44.81, "elapsed_time": "11:27:45", "remaining_time": "14:07:02", "throughput": 8423.9, "total_tokens": 347618248} {"current_steps": 341500, "total_steps": 761865, "loss": 1.9778, "lr": 5.809544925219313e-07, "epoch": 6.723632139552283, "percentage": 44.82, "elapsed_time": "11:27:57", "remaining_time": "14:06:49", "throughput": 8423.99, "total_tokens": 347720104} {"current_steps": 341600, "total_steps": 761865, "loss": 1.994, "lr": 5.807510255689283e-07, "epoch": 6.725600992301786, "percentage": 44.84, "elapsed_time": "11:28:09", "remaining_time": "14:06:37", "throughput": 8424.09, "total_tokens": 347822504} {"current_steps": 341700, "total_steps": 761865, "loss": 2.0046, "lr": 5.805475448848947e-07, "epoch": 6.727569845051288, "percentage": 44.85, "elapsed_time": "11:28:20", "remaining_time": "14:06:24", "throughput": 8424.19, "total_tokens": 347924560} {"current_steps": 341800, "total_steps": 761865, "loss": 1.9474, "lr": 5.803440505044302e-07, "epoch": 6.729538697800791, "percentage": 44.86, "elapsed_time": "11:28:32", "remaining_time": "14:06:11", "throughput": 8424.27, "total_tokens": 348025520} {"current_steps": 341900, "total_steps": 761865, "loss": 2.0128, "lr": 5.801405424621379e-07, "epoch": 6.731507550550294, "percentage": 44.88, "elapsed_time": "11:28:43", "remaining_time": "14:05:59", "throughput": 8424.35, "total_tokens": 348126256} {"current_steps": 342000, "total_steps": 761865, "loss": 1.9743, "lr": 5.79937020792622e-07, "epoch": 6.733476403299798, "percentage": 44.89, "elapsed_time": "11:28:55", "remaining_time": "14:05:46", "throughput": 8424.44, "total_tokens": 348228104} {"current_steps": 342100, "total_steps": 761865, "loss": 1.9498, "lr": 5.797334855304898e-07, "epoch": 6.7354452560493, "percentage": 44.9, "elapsed_time": "11:29:07", "remaining_time": "14:05:33", "throughput": 8424.54, "total_tokens": 348330504} {"current_steps": 342200, "total_steps": 761865, "loss": 1.9674, "lr": 5.795299367103511e-07, "epoch": 6.737414108798803, "percentage": 44.92, "elapsed_time": "11:29:18", "remaining_time": "14:05:21", "throughput": 8424.63, "total_tokens": 348432904} {"current_steps": 342300, "total_steps": 761865, "loss": 1.9997, "lr": 5.793263743668175e-07, "epoch": 6.739382961548306, "percentage": 44.93, "elapsed_time": "11:29:30", "remaining_time": "14:05:08", "throughput": 8424.73, "total_tokens": 348535304} {"current_steps": 342400, "total_steps": 761865, "loss": 1.9741, "lr": 5.79122798534503e-07, "epoch": 6.741351814297809, "percentage": 44.94, "elapsed_time": "11:29:42", "remaining_time": "14:04:56", "throughput": 8424.82, "total_tokens": 348636496} {"current_steps": 342500, "total_steps": 761865, "loss": 2.0057, "lr": 5.789192092480239e-07, "epoch": 6.743320667047311, "percentage": 44.96, "elapsed_time": "11:29:53", "remaining_time": "14:04:43", "throughput": 8424.89, "total_tokens": 348736832} {"current_steps": 342600, "total_steps": 761865, "loss": 1.9634, "lr": 5.787156065419989e-07, "epoch": 6.745289519796814, "percentage": 44.97, "elapsed_time": "11:30:05", "remaining_time": "14:04:30", "throughput": 8424.97, "total_tokens": 348837472} {"current_steps": 342700, "total_steps": 761865, "loss": 1.9541, "lr": 5.78511990451049e-07, "epoch": 6.747258372546317, "percentage": 44.98, "elapsed_time": "11:30:16", "remaining_time": "14:04:17", "throughput": 8425.06, "total_tokens": 348939224} {"current_steps": 342800, "total_steps": 761865, "loss": 2.0377, "lr": 5.783083610097973e-07, "epoch": 6.7492272252958205, "percentage": 44.99, "elapsed_time": "11:30:28", "remaining_time": "14:04:05", "throughput": 8425.15, "total_tokens": 349040752} {"current_steps": 342900, "total_steps": 761865, "loss": 1.9621, "lr": 5.781047182528693e-07, "epoch": 6.751196078045323, "percentage": 45.01, "elapsed_time": "11:30:40", "remaining_time": "14:03:52", "throughput": 8425.24, "total_tokens": 349142576} {"current_steps": 343000, "total_steps": 761865, "loss": 2.0212, "lr": 5.779010622148926e-07, "epoch": 6.753164930794826, "percentage": 45.02, "elapsed_time": "11:30:51", "remaining_time": "14:03:40", "throughput": 8425.34, "total_tokens": 349244976} {"current_steps": 343100, "total_steps": 761865, "loss": 1.9123, "lr": 5.776973929304976e-07, "epoch": 6.755133783544329, "percentage": 45.03, "elapsed_time": "11:31:03", "remaining_time": "14:03:27", "throughput": 8425.43, "total_tokens": 349346712} {"current_steps": 343200, "total_steps": 761865, "loss": 1.994, "lr": 5.774937104343159e-07, "epoch": 6.757102636293832, "percentage": 45.05, "elapsed_time": "11:31:14", "remaining_time": "14:03:14", "throughput": 8425.51, "total_tokens": 349447256} {"current_steps": 343300, "total_steps": 761865, "loss": 2.0143, "lr": 5.772900147609825e-07, "epoch": 6.759071489043334, "percentage": 45.06, "elapsed_time": "11:31:26", "remaining_time": "14:03:01", "throughput": 8425.6, "total_tokens": 349548592} {"current_steps": 343400, "total_steps": 761865, "loss": 1.9973, "lr": 5.77086305945134e-07, "epoch": 6.761040341792837, "percentage": 45.07, "elapsed_time": "11:31:38", "remaining_time": "14:02:49", "throughput": 8425.69, "total_tokens": 349650312} {"current_steps": 343500, "total_steps": 761865, "loss": 1.9502, "lr": 5.768825840214095e-07, "epoch": 6.76300919454234, "percentage": 45.09, "elapsed_time": "11:31:49", "remaining_time": "14:02:36", "throughput": 8425.78, "total_tokens": 349752712} {"current_steps": 343600, "total_steps": 761865, "loss": 2.0053, "lr": 5.766788490244498e-07, "epoch": 6.764978047291843, "percentage": 45.1, "elapsed_time": "11:32:01", "remaining_time": "14:02:24", "throughput": 8425.87, "total_tokens": 349853808} {"current_steps": 343700, "total_steps": 761865, "loss": 1.9851, "lr": 5.764751009888987e-07, "epoch": 6.766946900041346, "percentage": 45.11, "elapsed_time": "11:32:13", "remaining_time": "14:02:11", "throughput": 8425.96, "total_tokens": 349955768} {"current_steps": 343800, "total_steps": 761865, "loss": 1.9581, "lr": 5.762713399494015e-07, "epoch": 6.768915752790849, "percentage": 45.13, "elapsed_time": "11:32:24", "remaining_time": "14:01:58", "throughput": 8426.05, "total_tokens": 350057696} {"current_steps": 343900, "total_steps": 761865, "loss": 1.9688, "lr": 5.760675659406065e-07, "epoch": 6.770884605540352, "percentage": 45.14, "elapsed_time": "11:32:36", "remaining_time": "14:01:46", "throughput": 8426.15, "total_tokens": 350160096} {"current_steps": 344000, "total_steps": 761865, "loss": 2.0069, "lr": 5.758637789971635e-07, "epoch": 6.7728534582898545, "percentage": 45.15, "elapsed_time": "11:32:47", "remaining_time": "14:01:33", "throughput": 8426.23, "total_tokens": 350261160} {"current_steps": 344100, "total_steps": 761865, "loss": 2.0035, "lr": 5.756599791537247e-07, "epoch": 6.774822311039357, "percentage": 45.17, "elapsed_time": "11:32:59", "remaining_time": "14:01:20", "throughput": 8426.31, "total_tokens": 350361944} {"current_steps": 344200, "total_steps": 761865, "loss": 1.9541, "lr": 5.754561664449444e-07, "epoch": 6.77679116378886, "percentage": 45.18, "elapsed_time": "11:33:11", "remaining_time": "14:01:08", "throughput": 8426.4, "total_tokens": 350464344} {"current_steps": 344300, "total_steps": 761865, "loss": 2.0018, "lr": 5.752523409054796e-07, "epoch": 6.778760016538363, "percentage": 45.19, "elapsed_time": "11:33:22", "remaining_time": "14:00:55", "throughput": 8426.49, "total_tokens": 350566144} {"current_steps": 344400, "total_steps": 761865, "loss": 2.0351, "lr": 5.750485025699889e-07, "epoch": 6.7807288692878664, "percentage": 45.2, "elapsed_time": "11:33:34", "remaining_time": "14:00:43", "throughput": 8426.58, "total_tokens": 350667904} {"current_steps": 344500, "total_steps": 761865, "loss": 1.9764, "lr": 5.748446514731333e-07, "epoch": 6.782697722037369, "percentage": 45.22, "elapsed_time": "11:33:46", "remaining_time": "14:00:30", "throughput": 8426.66, "total_tokens": 350769064} {"current_steps": 344600, "total_steps": 761865, "loss": 1.9674, "lr": 5.74640787649576e-07, "epoch": 6.784666574786872, "percentage": 45.23, "elapsed_time": "11:33:57", "remaining_time": "14:00:17", "throughput": 8426.75, "total_tokens": 350871184} {"current_steps": 344700, "total_steps": 761865, "loss": 1.9963, "lr": 5.744369111339824e-07, "epoch": 6.786635427536375, "percentage": 45.24, "elapsed_time": "11:34:09", "remaining_time": "14:00:05", "throughput": 8426.85, "total_tokens": 350973584} {"current_steps": 344800, "total_steps": 761865, "loss": 2.0007, "lr": 5.742330219610197e-07, "epoch": 6.7886042802858775, "percentage": 45.26, "elapsed_time": "11:34:21", "remaining_time": "13:59:52", "throughput": 8426.95, "total_tokens": 351075984} {"current_steps": 344900, "total_steps": 761865, "loss": 1.9819, "lr": 5.740291201653579e-07, "epoch": 6.79057313303538, "percentage": 45.27, "elapsed_time": "11:34:32", "remaining_time": "13:59:40", "throughput": 8427.04, "total_tokens": 351178384} {"current_steps": 345000, "total_steps": 761865, "loss": 1.9915, "lr": 5.738252057816684e-07, "epoch": 6.792541985784883, "percentage": 45.28, "elapsed_time": "11:34:44", "remaining_time": "13:59:27", "throughput": 8427.12, "total_tokens": 351279120} {"current_steps": 345100, "total_steps": 761865, "loss": 1.9725, "lr": 5.736212788446257e-07, "epoch": 6.794510838534386, "percentage": 45.3, "elapsed_time": "11:34:56", "remaining_time": "13:59:15", "throughput": 8427.08, "total_tokens": 351380592} {"current_steps": 345200, "total_steps": 761865, "loss": 2.03, "lr": 5.734173393889051e-07, "epoch": 6.7964796912838885, "percentage": 45.31, "elapsed_time": "11:35:08", "remaining_time": "13:59:02", "throughput": 8427.17, "total_tokens": 351482440} {"current_steps": 345300, "total_steps": 761865, "loss": 2.0021, "lr": 5.732133874491853e-07, "epoch": 6.798448544033391, "percentage": 45.32, "elapsed_time": "11:35:19", "remaining_time": "13:58:50", "throughput": 8427.27, "total_tokens": 351584840} {"current_steps": 345400, "total_steps": 761865, "loss": 1.9792, "lr": 5.730094230601466e-07, "epoch": 6.800417396782895, "percentage": 45.34, "elapsed_time": "11:35:31", "remaining_time": "13:58:37", "throughput": 8427.36, "total_tokens": 351687240} {"current_steps": 345500, "total_steps": 761865, "loss": 1.9815, "lr": 5.728054462564711e-07, "epoch": 6.802386249532398, "percentage": 45.35, "elapsed_time": "11:35:43", "remaining_time": "13:58:25", "throughput": 8427.46, "total_tokens": 351789640} {"current_steps": 345600, "total_steps": 761865, "loss": 2.0082, "lr": 5.726014570728437e-07, "epoch": 6.8043551022819, "percentage": 45.36, "elapsed_time": "11:35:54", "remaining_time": "13:58:12", "throughput": 8427.55, "total_tokens": 351892040} {"current_steps": 345700, "total_steps": 761865, "loss": 1.9791, "lr": 5.723974555439508e-07, "epoch": 6.806323955031403, "percentage": 45.38, "elapsed_time": "11:36:06", "remaining_time": "13:57:59", "throughput": 8427.64, "total_tokens": 351993888} {"current_steps": 345800, "total_steps": 761865, "loss": 1.9926, "lr": 5.721934417044813e-07, "epoch": 6.808292807780906, "percentage": 45.39, "elapsed_time": "11:36:18", "remaining_time": "13:57:47", "throughput": 8427.74, "total_tokens": 352096288} {"current_steps": 345900, "total_steps": 761865, "loss": 2.0123, "lr": 5.719894155891258e-07, "epoch": 6.810261660530409, "percentage": 45.4, "elapsed_time": "11:36:29", "remaining_time": "13:57:34", "throughput": 8427.83, "total_tokens": 352198240} {"current_steps": 346000, "total_steps": 761865, "loss": 2.0488, "lr": 5.717853772325774e-07, "epoch": 6.8122305132799115, "percentage": 45.41, "elapsed_time": "11:36:41", "remaining_time": "13:57:22", "throughput": 8427.92, "total_tokens": 352300088} {"current_steps": 346100, "total_steps": 761865, "loss": 2.0212, "lr": 5.71581326669531e-07, "epoch": 6.814199366029415, "percentage": 45.43, "elapsed_time": "11:36:53", "remaining_time": "13:57:09", "throughput": 8428.02, "total_tokens": 352402488} {"current_steps": 346200, "total_steps": 761865, "loss": 2.006, "lr": 5.713772639346839e-07, "epoch": 6.816168218778918, "percentage": 45.44, "elapsed_time": "11:37:04", "remaining_time": "13:56:56", "throughput": 8428.1, "total_tokens": 352503584} {"current_steps": 346300, "total_steps": 761865, "loss": 2.0214, "lr": 5.71173189062735e-07, "epoch": 6.818137071528421, "percentage": 45.45, "elapsed_time": "11:37:16", "remaining_time": "13:56:44", "throughput": 8428.19, "total_tokens": 352605112} {"current_steps": 346400, "total_steps": 761865, "loss": 1.9857, "lr": 5.709691020883856e-07, "epoch": 6.820105924277923, "percentage": 45.47, "elapsed_time": "11:37:28", "remaining_time": "13:56:31", "throughput": 8428.29, "total_tokens": 352707512} {"current_steps": 346500, "total_steps": 761865, "loss": 1.9477, "lr": 5.707650030463392e-07, "epoch": 6.822074777027426, "percentage": 45.48, "elapsed_time": "11:37:39", "remaining_time": "13:56:19", "throughput": 8428.38, "total_tokens": 352809688} {"current_steps": 346600, "total_steps": 761865, "loss": 1.9765, "lr": 5.705608919713006e-07, "epoch": 6.824043629776929, "percentage": 45.49, "elapsed_time": "11:37:51", "remaining_time": "13:56:06", "throughput": 8428.47, "total_tokens": 352912088} {"current_steps": 346700, "total_steps": 761865, "loss": 1.9902, "lr": 5.703567688979776e-07, "epoch": 6.826012482526432, "percentage": 45.51, "elapsed_time": "11:38:03", "remaining_time": "13:55:53", "throughput": 8428.56, "total_tokens": 353013616} {"current_steps": 346800, "total_steps": 761865, "loss": 1.9447, "lr": 5.701526338610794e-07, "epoch": 6.827981335275934, "percentage": 45.52, "elapsed_time": "11:38:14", "remaining_time": "13:55:41", "throughput": 8428.65, "total_tokens": 353116016} {"current_steps": 346900, "total_steps": 761865, "loss": 1.9477, "lr": 5.699484868953175e-07, "epoch": 6.829950188025437, "percentage": 45.53, "elapsed_time": "11:38:26", "remaining_time": "13:55:28", "throughput": 8428.75, "total_tokens": 353218416} {"current_steps": 347000, "total_steps": 761865, "loss": 1.9551, "lr": 5.697443280354055e-07, "epoch": 6.83191904077494, "percentage": 45.55, "elapsed_time": "11:38:38", "remaining_time": "13:55:16", "throughput": 8428.84, "total_tokens": 353320312} {"current_steps": 347100, "total_steps": 761865, "loss": 1.9697, "lr": 5.695401573160586e-07, "epoch": 6.833887893524444, "percentage": 45.56, "elapsed_time": "11:38:49", "remaining_time": "13:55:03", "throughput": 8428.93, "total_tokens": 353422712} {"current_steps": 347200, "total_steps": 761865, "loss": 1.9567, "lr": 5.693359747719946e-07, "epoch": 6.835856746273946, "percentage": 45.57, "elapsed_time": "11:39:01", "remaining_time": "13:54:51", "throughput": 8429.03, "total_tokens": 353525112} {"current_steps": 347300, "total_steps": 761865, "loss": 1.9624, "lr": 5.691317804379326e-07, "epoch": 6.837825599023449, "percentage": 45.59, "elapsed_time": "11:39:13", "remaining_time": "13:54:38", "throughput": 8429.12, "total_tokens": 353627248} {"current_steps": 347400, "total_steps": 761865, "loss": 2.0254, "lr": 5.689275743485949e-07, "epoch": 6.839794451772952, "percentage": 45.6, "elapsed_time": "11:39:24", "remaining_time": "13:54:25", "throughput": 8429.21, "total_tokens": 353729648} {"current_steps": 347500, "total_steps": 761865, "loss": 1.9797, "lr": 5.687233565387041e-07, "epoch": 6.841763304522455, "percentage": 45.61, "elapsed_time": "11:39:36", "remaining_time": "13:54:13", "throughput": 8429.3, "total_tokens": 353831512} {"current_steps": 347600, "total_steps": 761865, "loss": 2.0576, "lr": 5.685191270429866e-07, "epoch": 6.843732157271957, "percentage": 45.62, "elapsed_time": "11:39:47", "remaining_time": "13:54:00", "throughput": 8429.38, "total_tokens": 353932304} {"current_steps": 347700, "total_steps": 761865, "loss": 2.0094, "lr": 5.68314885896169e-07, "epoch": 6.84570101002146, "percentage": 45.64, "elapsed_time": "11:39:59", "remaining_time": "13:53:48", "throughput": 8429.46, "total_tokens": 354033616} {"current_steps": 347800, "total_steps": 761865, "loss": 2.01, "lr": 5.681106331329817e-07, "epoch": 6.847669862770964, "percentage": 45.65, "elapsed_time": "11:40:11", "remaining_time": "13:53:35", "throughput": 8429.56, "total_tokens": 354136008} {"current_steps": 347900, "total_steps": 761865, "loss": 1.9384, "lr": 5.679063687881554e-07, "epoch": 6.8496387155204665, "percentage": 45.66, "elapsed_time": "11:40:22", "remaining_time": "13:53:22", "throughput": 8429.64, "total_tokens": 354237600} {"current_steps": 348000, "total_steps": 761865, "loss": 1.9875, "lr": 5.67702092896424e-07, "epoch": 6.851607568269969, "percentage": 45.68, "elapsed_time": "11:40:34", "remaining_time": "13:53:10", "throughput": 8429.72, "total_tokens": 354338600} {"current_steps": 348100, "total_steps": 761865, "loss": 2.0607, "lr": 5.674978054925226e-07, "epoch": 6.853576421019472, "percentage": 45.69, "elapsed_time": "11:40:45", "remaining_time": "13:52:57", "throughput": 8429.8, "total_tokens": 354439248} {"current_steps": 348200, "total_steps": 761865, "loss": 1.9402, "lr": 5.672935066111888e-07, "epoch": 6.855545273768975, "percentage": 45.7, "elapsed_time": "11:40:57", "remaining_time": "13:52:44", "throughput": 8429.88, "total_tokens": 354540184} {"current_steps": 348300, "total_steps": 761865, "loss": 1.9366, "lr": 5.670891962871616e-07, "epoch": 6.857514126518478, "percentage": 45.72, "elapsed_time": "11:41:09", "remaining_time": "13:52:32", "throughput": 8429.97, "total_tokens": 354642584} {"current_steps": 348400, "total_steps": 761865, "loss": 1.9895, "lr": 5.668848745551826e-07, "epoch": 6.85948297926798, "percentage": 45.73, "elapsed_time": "11:41:20", "remaining_time": "13:52:19", "throughput": 8430.06, "total_tokens": 354744464} {"current_steps": 348500, "total_steps": 761865, "loss": 2.0603, "lr": 5.666805414499947e-07, "epoch": 6.861451832017483, "percentage": 45.74, "elapsed_time": "11:41:32", "remaining_time": "13:52:07", "throughput": 8430.16, "total_tokens": 354846864} {"current_steps": 348600, "total_steps": 761865, "loss": 1.9852, "lr": 5.664761970063432e-07, "epoch": 6.863420684766986, "percentage": 45.76, "elapsed_time": "11:41:44", "remaining_time": "13:51:54", "throughput": 8430.25, "total_tokens": 354948904} {"current_steps": 348700, "total_steps": 761865, "loss": 1.9727, "lr": 5.662718412589749e-07, "epoch": 6.8653895375164895, "percentage": 45.77, "elapsed_time": "11:41:55", "remaining_time": "13:51:41", "throughput": 8430.34, "total_tokens": 355051304} {"current_steps": 348800, "total_steps": 761865, "loss": 1.9834, "lr": 5.660674742426393e-07, "epoch": 6.867358390265992, "percentage": 45.78, "elapsed_time": "11:42:07", "remaining_time": "13:51:29", "throughput": 8430.42, "total_tokens": 355152888} {"current_steps": 348900, "total_steps": 761865, "loss": 1.9556, "lr": 5.658630959920867e-07, "epoch": 6.869327243015495, "percentage": 45.8, "elapsed_time": "11:42:19", "remaining_time": "13:51:16", "throughput": 8430.51, "total_tokens": 355255288} {"current_steps": 349000, "total_steps": 761865, "loss": 1.988, "lr": 5.656587065420703e-07, "epoch": 6.871296095764998, "percentage": 45.81, "elapsed_time": "11:42:30", "remaining_time": "13:51:04", "throughput": 8430.6, "total_tokens": 355357136} {"current_steps": 349100, "total_steps": 761865, "loss": 1.9965, "lr": 5.654543059273446e-07, "epoch": 6.8732649485145005, "percentage": 45.82, "elapsed_time": "11:42:42", "remaining_time": "13:50:51", "throughput": 8430.68, "total_tokens": 355457976} {"current_steps": 349200, "total_steps": 761865, "loss": 1.9976, "lr": 5.652498941826662e-07, "epoch": 6.875233801264003, "percentage": 45.83, "elapsed_time": "11:42:54", "remaining_time": "13:50:39", "throughput": 8430.77, "total_tokens": 355560376} {"current_steps": 349300, "total_steps": 761865, "loss": 2.0092, "lr": 5.650454713427936e-07, "epoch": 6.877202654013506, "percentage": 45.85, "elapsed_time": "11:43:05", "remaining_time": "13:50:26", "throughput": 8430.86, "total_tokens": 355662776} {"current_steps": 349400, "total_steps": 761865, "loss": 2.0167, "lr": 5.648410374424872e-07, "epoch": 6.879171506763009, "percentage": 45.86, "elapsed_time": "11:43:17", "remaining_time": "13:50:13", "throughput": 8430.95, "total_tokens": 355764680} {"current_steps": 349500, "total_steps": 761865, "loss": 1.9845, "lr": 5.646365925165094e-07, "epoch": 6.8811403595125125, "percentage": 45.87, "elapsed_time": "11:43:29", "remaining_time": "13:50:01", "throughput": 8431.03, "total_tokens": 355866312} {"current_steps": 349600, "total_steps": 761865, "loss": 1.9968, "lr": 5.644321365996241e-07, "epoch": 6.883109212262015, "percentage": 45.89, "elapsed_time": "11:43:40", "remaining_time": "13:49:48", "throughput": 8431.1, "total_tokens": 355966392} {"current_steps": 349700, "total_steps": 761865, "loss": 1.9822, "lr": 5.642276697265975e-07, "epoch": 6.885078065011518, "percentage": 45.9, "elapsed_time": "11:43:52", "remaining_time": "13:49:36", "throughput": 8431.18, "total_tokens": 356067968} {"current_steps": 349800, "total_steps": 761865, "loss": 1.9615, "lr": 5.640231919321974e-07, "epoch": 6.887046917761021, "percentage": 45.91, "elapsed_time": "11:44:03", "remaining_time": "13:49:23", "throughput": 8431.27, "total_tokens": 356170368} {"current_steps": 349900, "total_steps": 761865, "loss": 1.9239, "lr": 5.638187032511935e-07, "epoch": 6.8890157705105235, "percentage": 45.93, "elapsed_time": "11:44:15", "remaining_time": "13:49:10", "throughput": 8431.36, "total_tokens": 356272768} {"current_steps": 350000, "total_steps": 761865, "loss": 1.9914, "lr": 5.636142037183574e-07, "epoch": 6.890984623260026, "percentage": 45.94, "elapsed_time": "11:44:27", "remaining_time": "13:48:58", "throughput": 8431.45, "total_tokens": 356375168} {"current_steps": 350100, "total_steps": 761865, "loss": 1.9485, "lr": 5.634096933684625e-07, "epoch": 6.892953476009529, "percentage": 45.95, "elapsed_time": "11:44:39", "remaining_time": "13:48:46", "throughput": 8431.43, "total_tokens": 356477568} {"current_steps": 350200, "total_steps": 761865, "loss": 1.9729, "lr": 5.632051722362838e-07, "epoch": 6.894922328759032, "percentage": 45.97, "elapsed_time": "11:44:51", "remaining_time": "13:48:33", "throughput": 8431.52, "total_tokens": 356579120} {"current_steps": 350300, "total_steps": 761865, "loss": 1.9926, "lr": 5.630006403565989e-07, "epoch": 6.8968911815085345, "percentage": 45.98, "elapsed_time": "11:45:02", "remaining_time": "13:48:21", "throughput": 8431.6, "total_tokens": 356680896} {"current_steps": 350400, "total_steps": 761865, "loss": 1.9603, "lr": 5.627960977641863e-07, "epoch": 6.898860034258038, "percentage": 45.99, "elapsed_time": "11:45:14", "remaining_time": "13:48:08", "throughput": 8431.69, "total_tokens": 356783296} {"current_steps": 350500, "total_steps": 761865, "loss": 2.0383, "lr": 5.625915444938271e-07, "epoch": 6.900828887007541, "percentage": 46.01, "elapsed_time": "11:45:26", "remaining_time": "13:47:56", "throughput": 8431.78, "total_tokens": 356885128} {"current_steps": 350600, "total_steps": 761865, "loss": 2.0111, "lr": 5.623869805803038e-07, "epoch": 6.902797739757044, "percentage": 46.02, "elapsed_time": "11:45:37", "remaining_time": "13:47:43", "throughput": 8431.87, "total_tokens": 356987392} {"current_steps": 350700, "total_steps": 761865, "loss": 2.0086, "lr": 5.621824060584005e-07, "epoch": 6.9047665925065465, "percentage": 46.03, "elapsed_time": "11:45:49", "remaining_time": "13:47:31", "throughput": 8431.97, "total_tokens": 357089792} {"current_steps": 350800, "total_steps": 761865, "loss": 1.9734, "lr": 5.619778209629034e-07, "epoch": 6.906735445256049, "percentage": 46.04, "elapsed_time": "11:46:01", "remaining_time": "13:47:18", "throughput": 8432.05, "total_tokens": 357190952} {"current_steps": 350900, "total_steps": 761865, "loss": 1.9931, "lr": 5.617732253286009e-07, "epoch": 6.908704298005552, "percentage": 46.06, "elapsed_time": "11:46:12", "remaining_time": "13:47:05", "throughput": 8432.14, "total_tokens": 357293352} {"current_steps": 351000, "total_steps": 761865, "loss": 1.954, "lr": 5.615686191902822e-07, "epoch": 6.910673150755055, "percentage": 46.07, "elapsed_time": "11:46:24", "remaining_time": "13:46:53", "throughput": 8432.23, "total_tokens": 357395216} {"current_steps": 351100, "total_steps": 761865, "loss": 2.0366, "lr": 5.613640025827392e-07, "epoch": 6.912642003504558, "percentage": 46.08, "elapsed_time": "11:46:36", "remaining_time": "13:46:40", "throughput": 8432.31, "total_tokens": 357496904} {"current_steps": 351200, "total_steps": 761865, "loss": 1.9804, "lr": 5.61159375540765e-07, "epoch": 6.914610856254061, "percentage": 46.1, "elapsed_time": "11:46:47", "remaining_time": "13:46:28", "throughput": 8432.39, "total_tokens": 357598344} {"current_steps": 351300, "total_steps": 761865, "loss": 2.0139, "lr": 5.60954738099155e-07, "epoch": 6.916579709003564, "percentage": 46.11, "elapsed_time": "11:46:59", "remaining_time": "13:46:15", "throughput": 8432.48, "total_tokens": 357700200} {"current_steps": 351400, "total_steps": 761865, "loss": 2.0063, "lr": 5.607500902927057e-07, "epoch": 6.918548561753067, "percentage": 46.12, "elapsed_time": "11:47:11", "remaining_time": "13:46:03", "throughput": 8432.57, "total_tokens": 357802600} {"current_steps": 351500, "total_steps": 761865, "loss": 2.0143, "lr": 5.605454321562161e-07, "epoch": 6.920517414502569, "percentage": 46.14, "elapsed_time": "11:47:22", "remaining_time": "13:45:50", "throughput": 8432.66, "total_tokens": 357905000} {"current_steps": 351600, "total_steps": 761865, "loss": 1.9555, "lr": 5.603407637244864e-07, "epoch": 6.922486267252072, "percentage": 46.15, "elapsed_time": "11:47:34", "remaining_time": "13:45:37", "throughput": 8432.75, "total_tokens": 358007400} {"current_steps": 351700, "total_steps": 761865, "loss": 1.9822, "lr": 5.601360850323188e-07, "epoch": 6.924455120001575, "percentage": 46.16, "elapsed_time": "11:47:46", "remaining_time": "13:45:25", "throughput": 8432.84, "total_tokens": 358109800} {"current_steps": 351800, "total_steps": 761865, "loss": 1.9898, "lr": 5.59931396114517e-07, "epoch": 6.926423972751078, "percentage": 46.18, "elapsed_time": "11:47:57", "remaining_time": "13:45:12", "throughput": 8432.93, "total_tokens": 358212200} {"current_steps": 351900, "total_steps": 761865, "loss": 1.983, "lr": 5.59726697005887e-07, "epoch": 6.92839282550058, "percentage": 46.19, "elapsed_time": "11:48:09", "remaining_time": "13:45:00", "throughput": 8433.03, "total_tokens": 358314600} {"current_steps": 352000, "total_steps": 761865, "loss": 2.0139, "lr": 5.595219877412357e-07, "epoch": 6.930361678250083, "percentage": 46.2, "elapsed_time": "11:48:21", "remaining_time": "13:44:47", "throughput": 8433.1, "total_tokens": 358415216} {"current_steps": 352100, "total_steps": 761865, "loss": 2.0202, "lr": 5.593172683553726e-07, "epoch": 6.932330530999587, "percentage": 46.22, "elapsed_time": "11:48:32", "remaining_time": "13:44:35", "throughput": 8433.18, "total_tokens": 358517144} {"current_steps": 352200, "total_steps": 761865, "loss": 1.9623, "lr": 5.591125388831083e-07, "epoch": 6.93429938374909, "percentage": 46.23, "elapsed_time": "11:48:44", "remaining_time": "13:44:22", "throughput": 8433.27, "total_tokens": 358618752} {"current_steps": 352300, "total_steps": 761865, "loss": 1.9568, "lr": 5.589077993592552e-07, "epoch": 6.936268236498592, "percentage": 46.24, "elapsed_time": "11:48:55", "remaining_time": "13:44:09", "throughput": 8433.35, "total_tokens": 358720296} {"current_steps": 352400, "total_steps": 761865, "loss": 2.0339, "lr": 5.587030498186277e-07, "epoch": 6.938237089248095, "percentage": 46.25, "elapsed_time": "11:49:07", "remaining_time": "13:43:57", "throughput": 8433.43, "total_tokens": 358822200} {"current_steps": 352500, "total_steps": 761865, "loss": 1.9545, "lr": 5.584982902960418e-07, "epoch": 6.940205941997598, "percentage": 46.27, "elapsed_time": "11:49:19", "remaining_time": "13:43:44", "throughput": 8433.52, "total_tokens": 358924104} {"current_steps": 352600, "total_steps": 761865, "loss": 2.0338, "lr": 5.58293520826315e-07, "epoch": 6.942174794747101, "percentage": 46.28, "elapsed_time": "11:49:30", "remaining_time": "13:43:32", "throughput": 8433.6, "total_tokens": 359026024} {"current_steps": 352700, "total_steps": 761865, "loss": 1.974, "lr": 5.580887414442667e-07, "epoch": 6.944143647496603, "percentage": 46.29, "elapsed_time": "11:49:42", "remaining_time": "13:43:19", "throughput": 8433.69, "total_tokens": 359128112} {"current_steps": 352800, "total_steps": 761865, "loss": 1.9398, "lr": 5.578839521847178e-07, "epoch": 6.946112500246107, "percentage": 46.31, "elapsed_time": "11:49:54", "remaining_time": "13:43:07", "throughput": 8433.78, "total_tokens": 359230512} {"current_steps": 352900, "total_steps": 761865, "loss": 1.9806, "lr": 5.576791530824911e-07, "epoch": 6.94808135299561, "percentage": 46.32, "elapsed_time": "11:50:05", "remaining_time": "13:42:54", "throughput": 8433.87, "total_tokens": 359332912} {"current_steps": 353000, "total_steps": 761865, "loss": 1.9822, "lr": 5.574743441724108e-07, "epoch": 6.950050205745113, "percentage": 46.33, "elapsed_time": "11:50:17", "remaining_time": "13:42:42", "throughput": 8433.95, "total_tokens": 359434016} {"current_steps": 353100, "total_steps": 761865, "loss": 2.0024, "lr": 5.572695254893031e-07, "epoch": 6.952019058494615, "percentage": 46.35, "elapsed_time": "11:50:29", "remaining_time": "13:42:29", "throughput": 8434.04, "total_tokens": 359536416} {"current_steps": 353200, "total_steps": 761865, "loss": 1.9881, "lr": 5.570646970679957e-07, "epoch": 6.953987911244118, "percentage": 46.36, "elapsed_time": "11:50:40", "remaining_time": "13:42:17", "throughput": 8434.13, "total_tokens": 359638816} {"current_steps": 353300, "total_steps": 761865, "loss": 1.9824, "lr": 5.568598589433178e-07, "epoch": 6.955956763993621, "percentage": 46.37, "elapsed_time": "11:50:52", "remaining_time": "13:42:04", "throughput": 8434.21, "total_tokens": 359740496} {"current_steps": 353400, "total_steps": 761865, "loss": 1.9757, "lr": 5.566550111501003e-07, "epoch": 6.957925616743124, "percentage": 46.39, "elapsed_time": "11:51:04", "remaining_time": "13:41:51", "throughput": 8434.3, "total_tokens": 359842272} {"current_steps": 353500, "total_steps": 761865, "loss": 1.9465, "lr": 5.564501537231763e-07, "epoch": 6.959894469492626, "percentage": 46.4, "elapsed_time": "11:51:15", "remaining_time": "13:41:39", "throughput": 8434.39, "total_tokens": 359944672} {"current_steps": 353600, "total_steps": 761865, "loss": 1.9346, "lr": 5.562452866973797e-07, "epoch": 6.961863322242129, "percentage": 46.41, "elapsed_time": "11:51:27", "remaining_time": "13:41:26", "throughput": 8434.46, "total_tokens": 360045192} {"current_steps": 353700, "total_steps": 761865, "loss": 2.0468, "lr": 5.560404101075463e-07, "epoch": 6.963832174991633, "percentage": 46.43, "elapsed_time": "11:51:39", "remaining_time": "13:41:14", "throughput": 8434.55, "total_tokens": 360147592} {"current_steps": 353800, "total_steps": 761865, "loss": 1.9634, "lr": 5.558355239885141e-07, "epoch": 6.9658010277411355, "percentage": 46.44, "elapsed_time": "11:51:50", "remaining_time": "13:41:01", "throughput": 8434.64, "total_tokens": 360249384} {"current_steps": 353900, "total_steps": 761865, "loss": 1.9686, "lr": 5.556306283751217e-07, "epoch": 6.967769880490638, "percentage": 46.45, "elapsed_time": "11:52:02", "remaining_time": "13:40:48", "throughput": 8434.71, "total_tokens": 360350376} {"current_steps": 354000, "total_steps": 761865, "loss": 1.9833, "lr": 5.554257233022104e-07, "epoch": 6.969738733240141, "percentage": 46.46, "elapsed_time": "11:52:14", "remaining_time": "13:40:36", "throughput": 8434.8, "total_tokens": 360452776} {"current_steps": 354100, "total_steps": 761865, "loss": 2.0229, "lr": 5.552208088046222e-07, "epoch": 6.971707585989644, "percentage": 46.48, "elapsed_time": "11:52:25", "remaining_time": "13:40:23", "throughput": 8434.87, "total_tokens": 360553616} {"current_steps": 354200, "total_steps": 761865, "loss": 2.0487, "lr": 5.550158849172013e-07, "epoch": 6.9736764387391466, "percentage": 46.49, "elapsed_time": "11:52:37", "remaining_time": "13:40:11", "throughput": 8434.95, "total_tokens": 360655200} {"current_steps": 354300, "total_steps": 761865, "loss": 1.9601, "lr": 5.548109516747932e-07, "epoch": 6.975645291488649, "percentage": 46.5, "elapsed_time": "11:52:48", "remaining_time": "13:39:58", "throughput": 8435.04, "total_tokens": 360756976} {"current_steps": 354400, "total_steps": 761865, "loss": 1.9854, "lr": 5.546060091122448e-07, "epoch": 6.977614144238152, "percentage": 46.52, "elapsed_time": "11:53:00", "remaining_time": "13:39:46", "throughput": 8435.12, "total_tokens": 360858088} {"current_steps": 354500, "total_steps": 761865, "loss": 1.9871, "lr": 5.544010572644053e-07, "epoch": 6.979582996987656, "percentage": 46.53, "elapsed_time": "11:53:12", "remaining_time": "13:39:33", "throughput": 8435.2, "total_tokens": 360959016} {"current_steps": 354600, "total_steps": 761865, "loss": 2.0087, "lr": 5.54196096166125e-07, "epoch": 6.9815518497371585, "percentage": 46.54, "elapsed_time": "11:53:23", "remaining_time": "13:39:20", "throughput": 8435.29, "total_tokens": 361061416} {"current_steps": 354700, "total_steps": 761865, "loss": 1.952, "lr": 5.539911258522555e-07, "epoch": 6.983520702486661, "percentage": 46.56, "elapsed_time": "11:53:35", "remaining_time": "13:39:08", "throughput": 8435.37, "total_tokens": 361162432} {"current_steps": 354800, "total_steps": 761865, "loss": 1.9504, "lr": 5.537861463576505e-07, "epoch": 6.985489555236164, "percentage": 46.57, "elapsed_time": "11:53:46", "remaining_time": "13:38:55", "throughput": 8435.45, "total_tokens": 361264208} {"current_steps": 354900, "total_steps": 761865, "loss": 1.9919, "lr": 5.535811577171649e-07, "epoch": 6.987458407985667, "percentage": 46.58, "elapsed_time": "11:53:58", "remaining_time": "13:38:43", "throughput": 8435.54, "total_tokens": 361366416} {"current_steps": 355000, "total_steps": 761865, "loss": 1.9851, "lr": 5.533761599656556e-07, "epoch": 6.9894272607351695, "percentage": 46.6, "elapsed_time": "11:54:10", "remaining_time": "13:38:30", "throughput": 8435.61, "total_tokens": 361466832} {"current_steps": 355100, "total_steps": 761865, "loss": 1.9815, "lr": 5.531711531379801e-07, "epoch": 6.991396113484672, "percentage": 46.61, "elapsed_time": "11:54:22", "remaining_time": "13:38:18", "throughput": 8435.58, "total_tokens": 361568632} {"current_steps": 355200, "total_steps": 761865, "loss": 1.9938, "lr": 5.529661372689987e-07, "epoch": 6.993364966234175, "percentage": 46.62, "elapsed_time": "11:54:33", "remaining_time": "13:38:05", "throughput": 8435.67, "total_tokens": 361670496} {"current_steps": 355300, "total_steps": 761865, "loss": 2.0307, "lr": 5.527611123935724e-07, "epoch": 6.995333818983678, "percentage": 46.64, "elapsed_time": "11:54:45", "remaining_time": "13:37:53", "throughput": 8435.74, "total_tokens": 361771968} {"current_steps": 355400, "total_steps": 761865, "loss": 1.9936, "lr": 5.525560785465638e-07, "epoch": 6.997302671733181, "percentage": 46.65, "elapsed_time": "11:54:57", "remaining_time": "13:37:40", "throughput": 8435.81, "total_tokens": 361872496} {"current_steps": 355500, "total_steps": 761865, "loss": 1.989, "lr": 5.523510357628375e-07, "epoch": 6.999271524482684, "percentage": 46.66, "elapsed_time": "11:55:08", "remaining_time": "13:37:28", "throughput": 8435.91, "total_tokens": 361974896} {"current_steps": 355600, "total_steps": 761865, "loss": 2.018, "lr": 5.521459840772591e-07, "epoch": 7.001240377232187, "percentage": 46.67, "elapsed_time": "11:55:20", "remaining_time": "13:37:15", "throughput": 8436.0, "total_tokens": 362077296} {"current_steps": 355700, "total_steps": 761865, "loss": 2.0031, "lr": 5.519409235246958e-07, "epoch": 7.00320922998169, "percentage": 46.69, "elapsed_time": "11:55:32", "remaining_time": "13:37:03", "throughput": 8436.09, "total_tokens": 362179696} {"current_steps": 355800, "total_steps": 761865, "loss": 1.9816, "lr": 5.517358541400166e-07, "epoch": 7.0051780827311925, "percentage": 46.7, "elapsed_time": "11:55:43", "remaining_time": "13:36:50", "throughput": 8436.17, "total_tokens": 362282096} {"current_steps": 355900, "total_steps": 761865, "loss": 1.9919, "lr": 5.515307759580917e-07, "epoch": 7.007146935480695, "percentage": 46.71, "elapsed_time": "11:55:55", "remaining_time": "13:36:38", "throughput": 8436.25, "total_tokens": 362383640} {"current_steps": 356000, "total_steps": 761865, "loss": 2.0344, "lr": 5.513256890137932e-07, "epoch": 7.009115788230198, "percentage": 46.73, "elapsed_time": "11:56:07", "remaining_time": "13:36:25", "throughput": 8436.34, "total_tokens": 362485072} {"current_steps": 356100, "total_steps": 761865, "loss": 1.9684, "lr": 5.511205933419941e-07, "epoch": 7.011084640979701, "percentage": 46.74, "elapsed_time": "11:56:18", "remaining_time": "13:36:13", "throughput": 8436.42, "total_tokens": 362587472} {"current_steps": 356200, "total_steps": 761865, "loss": 1.9543, "lr": 5.509154889775691e-07, "epoch": 7.013053493729204, "percentage": 46.75, "elapsed_time": "11:56:30", "remaining_time": "13:36:00", "throughput": 8436.51, "total_tokens": 362689872} {"current_steps": 356300, "total_steps": 761865, "loss": 2.0076, "lr": 5.507103759553947e-07, "epoch": 7.015022346478707, "percentage": 46.77, "elapsed_time": "11:56:42", "remaining_time": "13:35:48", "throughput": 8436.6, "total_tokens": 362792272} {"current_steps": 356400, "total_steps": 761865, "loss": 2.0034, "lr": 5.505052543103487e-07, "epoch": 7.01699119922821, "percentage": 46.78, "elapsed_time": "11:56:53", "remaining_time": "13:35:35", "throughput": 8436.68, "total_tokens": 362893760} {"current_steps": 356500, "total_steps": 761865, "loss": 1.9681, "lr": 5.503001240773099e-07, "epoch": 7.018960051977713, "percentage": 46.79, "elapsed_time": "11:57:05", "remaining_time": "13:35:22", "throughput": 8436.77, "total_tokens": 362995512} {"current_steps": 356600, "total_steps": 761865, "loss": 2.0361, "lr": 5.500949852911596e-07, "epoch": 7.020928904727215, "percentage": 46.81, "elapsed_time": "11:57:17", "remaining_time": "13:35:10", "throughput": 8436.85, "total_tokens": 363097352} {"current_steps": 356700, "total_steps": 761865, "loss": 2.0205, "lr": 5.498898379867794e-07, "epoch": 7.022897757476718, "percentage": 46.82, "elapsed_time": "11:57:28", "remaining_time": "13:34:57", "throughput": 8436.94, "total_tokens": 363199752} {"current_steps": 356800, "total_steps": 761865, "loss": 1.98, "lr": 5.496846821990532e-07, "epoch": 7.024866610226221, "percentage": 46.83, "elapsed_time": "11:57:40", "remaining_time": "13:34:45", "throughput": 8437.03, "total_tokens": 363302152} {"current_steps": 356900, "total_steps": 761865, "loss": 1.9822, "lr": 5.494795179628658e-07, "epoch": 7.026835462975724, "percentage": 46.85, "elapsed_time": "11:57:51", "remaining_time": "13:34:32", "throughput": 8437.11, "total_tokens": 363403064} {"current_steps": 357000, "total_steps": 761865, "loss": 2.0479, "lr": 5.492743453131036e-07, "epoch": 7.028804315725227, "percentage": 46.86, "elapsed_time": "11:58:03", "remaining_time": "13:34:20", "throughput": 8437.19, "total_tokens": 363504872} {"current_steps": 357100, "total_steps": 761865, "loss": 1.9885, "lr": 5.490691642846545e-07, "epoch": 7.03077316847473, "percentage": 46.87, "elapsed_time": "11:58:15", "remaining_time": "13:34:07", "throughput": 8437.28, "total_tokens": 363606808} {"current_steps": 357200, "total_steps": 761865, "loss": 1.9712, "lr": 5.488639749124081e-07, "epoch": 7.032742021224233, "percentage": 46.88, "elapsed_time": "11:58:26", "remaining_time": "13:33:54", "throughput": 8437.35, "total_tokens": 363707656} {"current_steps": 357300, "total_steps": 761865, "loss": 1.9733, "lr": 5.486587772312547e-07, "epoch": 7.034710873973736, "percentage": 46.9, "elapsed_time": "11:58:38", "remaining_time": "13:33:42", "throughput": 8437.43, "total_tokens": 363809576} {"current_steps": 357400, "total_steps": 761865, "loss": 2.0122, "lr": 5.484535712760867e-07, "epoch": 7.036679726723238, "percentage": 46.91, "elapsed_time": "11:58:50", "remaining_time": "13:33:29", "throughput": 8437.51, "total_tokens": 363911056} {"current_steps": 357500, "total_steps": 761865, "loss": 2.0123, "lr": 5.482483570817977e-07, "epoch": 7.038648579472741, "percentage": 46.92, "elapsed_time": "11:59:01", "remaining_time": "13:33:17", "throughput": 8437.58, "total_tokens": 364012088} {"current_steps": 357600, "total_steps": 761865, "loss": 1.9571, "lr": 5.480431346832825e-07, "epoch": 7.040617432222244, "percentage": 46.94, "elapsed_time": "11:59:13", "remaining_time": "13:33:04", "throughput": 8437.67, "total_tokens": 364114008} {"current_steps": 357700, "total_steps": 761865, "loss": 2.0002, "lr": 5.478379041154374e-07, "epoch": 7.042586284971747, "percentage": 46.95, "elapsed_time": "11:59:24", "remaining_time": "13:32:52", "throughput": 8437.75, "total_tokens": 364215568} {"current_steps": 357800, "total_steps": 761865, "loss": 1.998, "lr": 5.476326654131601e-07, "epoch": 7.044555137721249, "percentage": 46.96, "elapsed_time": "11:59:36", "remaining_time": "13:32:39", "throughput": 8437.84, "total_tokens": 364317968} {"current_steps": 357900, "total_steps": 761865, "loss": 1.9667, "lr": 5.4742741861135e-07, "epoch": 7.046523990470753, "percentage": 46.98, "elapsed_time": "11:59:48", "remaining_time": "13:32:27", "throughput": 8437.92, "total_tokens": 364419264} {"current_steps": 358000, "total_steps": 761865, "loss": 1.9726, "lr": 5.472221637449073e-07, "epoch": 7.048492843220256, "percentage": 46.99, "elapsed_time": "11:59:59", "remaining_time": "13:32:14", "throughput": 8438.0, "total_tokens": 364521664} {"current_steps": 358100, "total_steps": 761865, "loss": 2.0125, "lr": 5.470169008487339e-07, "epoch": 7.050461695969759, "percentage": 47.0, "elapsed_time": "12:00:11", "remaining_time": "13:32:01", "throughput": 8438.08, "total_tokens": 364622504} {"current_steps": 358200, "total_steps": 761865, "loss": 1.9554, "lr": 5.468116299577331e-07, "epoch": 7.052430548719261, "percentage": 47.02, "elapsed_time": "12:00:23", "remaining_time": "13:31:49", "throughput": 8438.17, "total_tokens": 364724224} {"current_steps": 358300, "total_steps": 761865, "loss": 1.9793, "lr": 5.466063511068095e-07, "epoch": 7.054399401468764, "percentage": 47.03, "elapsed_time": "12:00:34", "remaining_time": "13:31:36", "throughput": 8438.25, "total_tokens": 364825912} {"current_steps": 358400, "total_steps": 761865, "loss": 1.9385, "lr": 5.464010643308689e-07, "epoch": 7.056368254218267, "percentage": 47.04, "elapsed_time": "12:00:46", "remaining_time": "13:31:24", "throughput": 8438.33, "total_tokens": 364927736} {"current_steps": 358500, "total_steps": 761865, "loss": 1.9591, "lr": 5.461957696648186e-07, "epoch": 7.05833710696777, "percentage": 47.06, "elapsed_time": "12:00:58", "remaining_time": "13:31:11", "throughput": 8438.42, "total_tokens": 365030136} {"current_steps": 358600, "total_steps": 761865, "loss": 1.982, "lr": 5.459904671435673e-07, "epoch": 7.060305959717272, "percentage": 47.07, "elapsed_time": "12:01:09", "remaining_time": "13:30:59", "throughput": 8438.51, "total_tokens": 365132088} {"current_steps": 358700, "total_steps": 761865, "loss": 2.0108, "lr": 5.457851568020252e-07, "epoch": 7.062274812466776, "percentage": 47.08, "elapsed_time": "12:01:21", "remaining_time": "13:30:46", "throughput": 8438.58, "total_tokens": 365233056} {"current_steps": 358800, "total_steps": 761865, "loss": 1.9933, "lr": 5.455798386751033e-07, "epoch": 7.064243665216279, "percentage": 47.09, "elapsed_time": "12:01:32", "remaining_time": "13:30:34", "throughput": 8438.66, "total_tokens": 365334920} {"current_steps": 358900, "total_steps": 761865, "loss": 1.9743, "lr": 5.453745127977142e-07, "epoch": 7.0662125179657815, "percentage": 47.11, "elapsed_time": "12:01:44", "remaining_time": "13:30:21", "throughput": 8438.76, "total_tokens": 365437320} {"current_steps": 359000, "total_steps": 761865, "loss": 1.9767, "lr": 5.451691792047719e-07, "epoch": 7.068181370715284, "percentage": 47.12, "elapsed_time": "12:01:56", "remaining_time": "13:30:08", "throughput": 8438.84, "total_tokens": 365539152} {"current_steps": 359100, "total_steps": 761865, "loss": 2.0361, "lr": 5.449638379311917e-07, "epoch": 7.070150223464787, "percentage": 47.13, "elapsed_time": "12:02:07", "remaining_time": "13:29:56", "throughput": 8438.92, "total_tokens": 365640624} {"current_steps": 359200, "total_steps": 761865, "loss": 1.9738, "lr": 5.447584890118901e-07, "epoch": 7.07211907621429, "percentage": 47.15, "elapsed_time": "12:02:19", "remaining_time": "13:29:43", "throughput": 8439.01, "total_tokens": 365743024} {"current_steps": 359300, "total_steps": 761865, "loss": 1.9797, "lr": 5.445531324817849e-07, "epoch": 7.074087928963793, "percentage": 47.16, "elapsed_time": "12:02:31", "remaining_time": "13:29:31", "throughput": 8439.1, "total_tokens": 365845424} {"current_steps": 359400, "total_steps": 761865, "loss": 1.9798, "lr": 5.443477683757952e-07, "epoch": 7.076056781713295, "percentage": 47.17, "elapsed_time": "12:02:42", "remaining_time": "13:29:18", "throughput": 8439.17, "total_tokens": 365946416} {"current_steps": 359500, "total_steps": 761865, "loss": 1.9628, "lr": 5.441423967288416e-07, "epoch": 7.078025634462799, "percentage": 47.19, "elapsed_time": "12:02:54", "remaining_time": "13:29:06", "throughput": 8439.25, "total_tokens": 366047360} {"current_steps": 359600, "total_steps": 761865, "loss": 1.9381, "lr": 5.439370175758457e-07, "epoch": 7.079994487212302, "percentage": 47.2, "elapsed_time": "12:03:06", "remaining_time": "13:28:53", "throughput": 8439.33, "total_tokens": 366149760} {"current_steps": 359700, "total_steps": 761865, "loss": 1.9481, "lr": 5.437316309517308e-07, "epoch": 7.0819633399618045, "percentage": 47.21, "elapsed_time": "12:03:17", "remaining_time": "13:28:41", "throughput": 8439.43, "total_tokens": 366252160} {"current_steps": 359800, "total_steps": 761865, "loss": 1.9574, "lr": 5.435262368914207e-07, "epoch": 7.083932192711307, "percentage": 47.23, "elapsed_time": "12:03:29", "remaining_time": "13:28:28", "throughput": 8439.49, "total_tokens": 366352440} {"current_steps": 359900, "total_steps": 761865, "loss": 1.9789, "lr": 5.433208354298413e-07, "epoch": 7.08590104546081, "percentage": 47.24, "elapsed_time": "12:03:40", "remaining_time": "13:28:16", "throughput": 8439.58, "total_tokens": 366454840} {"current_steps": 360000, "total_steps": 761865, "loss": 2.0061, "lr": 5.43115426601919e-07, "epoch": 7.087869898210313, "percentage": 47.25, "elapsed_time": "12:03:52", "remaining_time": "13:28:03", "throughput": 8439.63, "total_tokens": 366553904} {"current_steps": 360100, "total_steps": 761865, "loss": 2.0108, "lr": 5.429100104425823e-07, "epoch": 7.0898387509598155, "percentage": 47.27, "elapsed_time": "12:04:04", "remaining_time": "13:27:51", "throughput": 8439.6, "total_tokens": 366655624} {"current_steps": 360200, "total_steps": 761865, "loss": 1.971, "lr": 5.427045869867601e-07, "epoch": 7.091807603709318, "percentage": 47.28, "elapsed_time": "12:04:16", "remaining_time": "13:27:38", "throughput": 8439.67, "total_tokens": 366757520} {"current_steps": 360300, "total_steps": 761865, "loss": 1.9798, "lr": 5.424991562693831e-07, "epoch": 7.093776456458821, "percentage": 47.29, "elapsed_time": "12:04:28", "remaining_time": "13:27:26", "throughput": 8439.75, "total_tokens": 366859920} {"current_steps": 360400, "total_steps": 761865, "loss": 2.05, "lr": 5.422937183253828e-07, "epoch": 7.095745309208325, "percentage": 47.3, "elapsed_time": "12:04:39", "remaining_time": "13:27:13", "throughput": 8439.83, "total_tokens": 366961816} {"current_steps": 360500, "total_steps": 761865, "loss": 2.0098, "lr": 5.420882731896926e-07, "epoch": 7.0977141619578275, "percentage": 47.32, "elapsed_time": "12:04:51", "remaining_time": "13:27:01", "throughput": 8439.91, "total_tokens": 367063400} {"current_steps": 360600, "total_steps": 761865, "loss": 1.9966, "lr": 5.418828208972465e-07, "epoch": 7.09968301470733, "percentage": 47.33, "elapsed_time": "12:05:03", "remaining_time": "13:26:48", "throughput": 8440.0, "total_tokens": 367165800} {"current_steps": 360700, "total_steps": 761865, "loss": 1.9548, "lr": 5.416773614829802e-07, "epoch": 7.101651867456833, "percentage": 47.34, "elapsed_time": "12:05:14", "remaining_time": "13:26:36", "throughput": 8440.09, "total_tokens": 367267584} {"current_steps": 360800, "total_steps": 761865, "loss": 1.9843, "lr": 5.414718949818299e-07, "epoch": 7.103620720206336, "percentage": 47.36, "elapsed_time": "12:05:26", "remaining_time": "13:26:23", "throughput": 8440.17, "total_tokens": 367369216} {"current_steps": 360900, "total_steps": 761865, "loss": 1.9398, "lr": 5.412664214287337e-07, "epoch": 7.1055895729558385, "percentage": 47.37, "elapsed_time": "12:05:37", "remaining_time": "13:26:11", "throughput": 8440.25, "total_tokens": 367471616} {"current_steps": 361000, "total_steps": 761865, "loss": 2.0362, "lr": 5.410609408586305e-07, "epoch": 7.107558425705341, "percentage": 47.38, "elapsed_time": "12:05:49", "remaining_time": "13:25:58", "throughput": 8440.31, "total_tokens": 367571432} {"current_steps": 361100, "total_steps": 761865, "loss": 1.948, "lr": 5.408554533064607e-07, "epoch": 7.109527278454844, "percentage": 47.4, "elapsed_time": "12:06:01", "remaining_time": "13:25:46", "throughput": 8440.39, "total_tokens": 367673160} {"current_steps": 361200, "total_steps": 761865, "loss": 1.9899, "lr": 5.406499588071657e-07, "epoch": 7.111496131204348, "percentage": 47.41, "elapsed_time": "12:06:12", "remaining_time": "13:25:33", "throughput": 8440.47, "total_tokens": 367774728} {"current_steps": 361300, "total_steps": 761865, "loss": 1.977, "lr": 5.404444573956881e-07, "epoch": 7.11346498395385, "percentage": 47.42, "elapsed_time": "12:06:24", "remaining_time": "13:25:21", "throughput": 8440.56, "total_tokens": 367876416} {"current_steps": 361400, "total_steps": 761865, "loss": 1.9838, "lr": 5.402389491069714e-07, "epoch": 7.115433836703353, "percentage": 47.44, "elapsed_time": "12:06:36", "remaining_time": "13:25:08", "throughput": 8440.64, "total_tokens": 367978816} {"current_steps": 361500, "total_steps": 761865, "loss": 2.0028, "lr": 5.400334339759611e-07, "epoch": 7.117402689452856, "percentage": 47.45, "elapsed_time": "12:06:47", "remaining_time": "13:24:55", "throughput": 8440.71, "total_tokens": 368079560} {"current_steps": 361600, "total_steps": 761865, "loss": 1.9971, "lr": 5.398279120376028e-07, "epoch": 7.119371542202359, "percentage": 47.46, "elapsed_time": "12:06:59", "remaining_time": "13:24:43", "throughput": 8440.79, "total_tokens": 368181960} {"current_steps": 361700, "total_steps": 761865, "loss": 1.9993, "lr": 5.39622383326844e-07, "epoch": 7.121340394951861, "percentage": 47.48, "elapsed_time": "12:07:11", "remaining_time": "13:24:30", "throughput": 8440.88, "total_tokens": 368284360} {"current_steps": 361800, "total_steps": 761865, "loss": 2.0051, "lr": 5.394168478786333e-07, "epoch": 7.123309247701364, "percentage": 47.49, "elapsed_time": "12:07:22", "remaining_time": "13:24:18", "throughput": 8440.97, "total_tokens": 368386240} {"current_steps": 361900, "total_steps": 761865, "loss": 2.0154, "lr": 5.392113057279199e-07, "epoch": 7.125278100450867, "percentage": 47.5, "elapsed_time": "12:07:34", "remaining_time": "13:24:05", "throughput": 8441.05, "total_tokens": 368488640} {"current_steps": 362000, "total_steps": 761865, "loss": 2.0187, "lr": 5.390057569096547e-07, "epoch": 7.12724695320037, "percentage": 47.51, "elapsed_time": "12:07:45", "remaining_time": "13:23:53", "throughput": 8441.14, "total_tokens": 368590752} {"current_steps": 362100, "total_steps": 761865, "loss": 1.9533, "lr": 5.388002014587895e-07, "epoch": 7.129215805949873, "percentage": 47.53, "elapsed_time": "12:07:57", "remaining_time": "13:23:40", "throughput": 8441.23, "total_tokens": 368693152} {"current_steps": 362200, "total_steps": 761865, "loss": 2.0007, "lr": 5.385946394102774e-07, "epoch": 7.131184658699376, "percentage": 47.54, "elapsed_time": "12:08:09", "remaining_time": "13:23:28", "throughput": 8441.31, "total_tokens": 368795552} {"current_steps": 362300, "total_steps": 761865, "loss": 1.9714, "lr": 5.383890707990722e-07, "epoch": 7.133153511448879, "percentage": 47.55, "elapsed_time": "12:08:20", "remaining_time": "13:23:15", "throughput": 8441.39, "total_tokens": 368897056} {"current_steps": 362400, "total_steps": 761865, "loss": 2.0043, "lr": 5.381834956601296e-07, "epoch": 7.135122364198382, "percentage": 47.57, "elapsed_time": "12:08:32", "remaining_time": "13:23:03", "throughput": 8441.47, "total_tokens": 368998624} {"current_steps": 362500, "total_steps": 761865, "loss": 2.024, "lr": 5.379779140284054e-07, "epoch": 7.137091216947884, "percentage": 47.58, "elapsed_time": "12:08:44", "remaining_time": "13:22:50", "throughput": 8441.55, "total_tokens": 369100440} {"current_steps": 362600, "total_steps": 761865, "loss": 1.9471, "lr": 5.377723259388572e-07, "epoch": 7.139060069697387, "percentage": 47.59, "elapsed_time": "12:08:55", "remaining_time": "13:22:38", "throughput": 8441.64, "total_tokens": 369202840} {"current_steps": 362700, "total_steps": 761865, "loss": 1.968, "lr": 5.375667314264436e-07, "epoch": 7.14102892244689, "percentage": 47.61, "elapsed_time": "12:09:07", "remaining_time": "13:22:25", "throughput": 8441.72, "total_tokens": 369304720} {"current_steps": 362800, "total_steps": 761865, "loss": 1.9488, "lr": 5.373611305261243e-07, "epoch": 7.142997775196393, "percentage": 47.62, "elapsed_time": "12:09:19", "remaining_time": "13:22:13", "throughput": 8441.79, "total_tokens": 369405672} {"current_steps": 362900, "total_steps": 761865, "loss": 2.0228, "lr": 5.371555232728597e-07, "epoch": 7.144966627945896, "percentage": 47.63, "elapsed_time": "12:09:30", "remaining_time": "13:22:00", "throughput": 8441.87, "total_tokens": 369507456} {"current_steps": 363000, "total_steps": 761865, "loss": 1.9745, "lr": 5.369499097016119e-07, "epoch": 7.146935480695399, "percentage": 47.65, "elapsed_time": "12:09:42", "remaining_time": "13:21:48", "throughput": 8441.95, "total_tokens": 369609304} {"current_steps": 363100, "total_steps": 761865, "loss": 1.975, "lr": 5.367442898473435e-07, "epoch": 7.148904333444902, "percentage": 47.66, "elapsed_time": "12:09:54", "remaining_time": "13:21:35", "throughput": 8442.03, "total_tokens": 369711064} {"current_steps": 363200, "total_steps": 761865, "loss": 2.0399, "lr": 5.365386637450187e-07, "epoch": 7.150873186194405, "percentage": 47.67, "elapsed_time": "12:10:05", "remaining_time": "13:21:23", "throughput": 8442.11, "total_tokens": 369812864} {"current_steps": 363300, "total_steps": 761865, "loss": 1.9809, "lr": 5.363330314296022e-07, "epoch": 7.152842038943907, "percentage": 47.69, "elapsed_time": "12:10:17", "remaining_time": "13:21:10", "throughput": 8442.19, "total_tokens": 369914504} {"current_steps": 363400, "total_steps": 761865, "loss": 2.0227, "lr": 5.361273929360601e-07, "epoch": 7.15481089169341, "percentage": 47.7, "elapsed_time": "12:10:29", "remaining_time": "13:20:58", "throughput": 8442.28, "total_tokens": 370016904} {"current_steps": 363500, "total_steps": 761865, "loss": 1.9704, "lr": 5.359217482993596e-07, "epoch": 7.156779744442913, "percentage": 47.71, "elapsed_time": "12:10:40", "remaining_time": "13:20:45", "throughput": 8442.36, "total_tokens": 370119304} {"current_steps": 363600, "total_steps": 761865, "loss": 1.9766, "lr": 5.357160975544687e-07, "epoch": 7.158748597192416, "percentage": 47.72, "elapsed_time": "12:10:52", "remaining_time": "13:20:33", "throughput": 8442.45, "total_tokens": 370221704} {"current_steps": 363700, "total_steps": 761865, "loss": 1.9631, "lr": 5.355104407363566e-07, "epoch": 7.160717449941918, "percentage": 47.74, "elapsed_time": "12:11:04", "remaining_time": "13:20:20", "throughput": 8442.53, "total_tokens": 370323464} {"current_steps": 363800, "total_steps": 761865, "loss": 1.9185, "lr": 5.353047778799938e-07, "epoch": 7.162686302691422, "percentage": 47.75, "elapsed_time": "12:11:15", "remaining_time": "13:20:08", "throughput": 8442.61, "total_tokens": 370425232} {"current_steps": 363900, "total_steps": 761865, "loss": 2.0283, "lr": 5.350991090203511e-07, "epoch": 7.164655155440925, "percentage": 47.76, "elapsed_time": "12:11:27", "remaining_time": "13:19:55", "throughput": 8442.69, "total_tokens": 370527632} {"current_steps": 364000, "total_steps": 761865, "loss": 1.9769, "lr": 5.348934341924011e-07, "epoch": 7.1666240081904276, "percentage": 47.78, "elapsed_time": "12:11:38", "remaining_time": "13:19:43", "throughput": 8442.77, "total_tokens": 370628736} {"current_steps": 364100, "total_steps": 761865, "loss": 2.0164, "lr": 5.346877534311169e-07, "epoch": 7.16859286093993, "percentage": 47.79, "elapsed_time": "12:11:50", "remaining_time": "13:19:30", "throughput": 8442.85, "total_tokens": 370730432} {"current_steps": 364200, "total_steps": 761865, "loss": 1.9886, "lr": 5.344820667714727e-07, "epoch": 7.170561713689433, "percentage": 47.8, "elapsed_time": "12:12:02", "remaining_time": "13:19:18", "throughput": 8442.93, "total_tokens": 370832832} {"current_steps": 364300, "total_steps": 761865, "loss": 2.0217, "lr": 5.342763742484439e-07, "epoch": 7.172530566438936, "percentage": 47.82, "elapsed_time": "12:12:13", "remaining_time": "13:19:05", "throughput": 8443.01, "total_tokens": 370934408} {"current_steps": 364400, "total_steps": 761865, "loss": 1.9404, "lr": 5.340706758970069e-07, "epoch": 7.174499419188439, "percentage": 47.83, "elapsed_time": "12:12:25", "remaining_time": "13:18:53", "throughput": 8443.09, "total_tokens": 371036352} {"current_steps": 364500, "total_steps": 761865, "loss": 1.9922, "lr": 5.338649717521387e-07, "epoch": 7.176468271937941, "percentage": 47.84, "elapsed_time": "12:12:37", "remaining_time": "13:18:40", "throughput": 8443.17, "total_tokens": 371137976} {"current_steps": 364600, "total_steps": 761865, "loss": 1.9469, "lr": 5.336592618488176e-07, "epoch": 7.178437124687445, "percentage": 47.86, "elapsed_time": "12:12:48", "remaining_time": "13:18:28", "throughput": 8443.25, "total_tokens": 371240376} {"current_steps": 364700, "total_steps": 761865, "loss": 1.9582, "lr": 5.33453546222023e-07, "epoch": 7.180405977436948, "percentage": 47.87, "elapsed_time": "12:13:00", "remaining_time": "13:18:15", "throughput": 8443.34, "total_tokens": 371342776} {"current_steps": 364800, "total_steps": 761865, "loss": 2.0503, "lr": 5.33247824906735e-07, "epoch": 7.1823748301864505, "percentage": 47.88, "elapsed_time": "12:13:12", "remaining_time": "13:18:03", "throughput": 8443.42, "total_tokens": 371445176} {"current_steps": 364900, "total_steps": 761865, "loss": 1.9721, "lr": 5.330420979379349e-07, "epoch": 7.184343682935953, "percentage": 47.9, "elapsed_time": "12:13:23", "remaining_time": "13:17:50", "throughput": 8443.5, "total_tokens": 371546968} {"current_steps": 365000, "total_steps": 761865, "loss": 1.9958, "lr": 5.328363653506047e-07, "epoch": 7.186312535685456, "percentage": 47.91, "elapsed_time": "12:13:35", "remaining_time": "13:17:38", "throughput": 8443.59, "total_tokens": 371649368} {"current_steps": 365100, "total_steps": 761865, "loss": 2.0003, "lr": 5.326306271797274e-07, "epoch": 7.188281388434959, "percentage": 47.92, "elapsed_time": "12:13:47", "remaining_time": "13:17:26", "throughput": 8443.57, "total_tokens": 371751400} {"current_steps": 365200, "total_steps": 761865, "loss": 2.0071, "lr": 5.324248834602874e-07, "epoch": 7.1902502411844615, "percentage": 47.94, "elapsed_time": "12:13:59", "remaining_time": "13:17:13", "throughput": 8443.65, "total_tokens": 371853800} {"current_steps": 365300, "total_steps": 761865, "loss": 1.9618, "lr": 5.322191342272692e-07, "epoch": 7.192219093933964, "percentage": 47.95, "elapsed_time": "12:14:11", "remaining_time": "13:17:01", "throughput": 8443.73, "total_tokens": 371955704} {"current_steps": 365400, "total_steps": 761865, "loss": 1.9965, "lr": 5.320133795156591e-07, "epoch": 7.194187946683468, "percentage": 47.96, "elapsed_time": "12:14:22", "remaining_time": "13:16:48", "throughput": 8443.81, "total_tokens": 372058104} {"current_steps": 365500, "total_steps": 761865, "loss": 1.9829, "lr": 5.318076193604439e-07, "epoch": 7.196156799432971, "percentage": 47.97, "elapsed_time": "12:14:34", "remaining_time": "13:16:36", "throughput": 8443.9, "total_tokens": 372160504} {"current_steps": 365600, "total_steps": 761865, "loss": 2.0115, "lr": 5.316018537966112e-07, "epoch": 7.1981256521824735, "percentage": 47.99, "elapsed_time": "12:14:46", "remaining_time": "13:16:23", "throughput": 8443.97, "total_tokens": 372262128} {"current_steps": 365700, "total_steps": 761865, "loss": 1.9878, "lr": 5.313960828591498e-07, "epoch": 7.200094504931976, "percentage": 48.0, "elapsed_time": "12:14:57", "remaining_time": "13:16:11", "throughput": 8444.06, "total_tokens": 372364528} {"current_steps": 365800, "total_steps": 761865, "loss": 1.9765, "lr": 5.311903065830494e-07, "epoch": 7.202063357681479, "percentage": 48.01, "elapsed_time": "12:15:09", "remaining_time": "13:15:58", "throughput": 8444.14, "total_tokens": 372466584} {"current_steps": 365900, "total_steps": 761865, "loss": 2.0381, "lr": 5.309845250033004e-07, "epoch": 7.204032210430982, "percentage": 48.03, "elapsed_time": "12:15:20", "remaining_time": "13:15:46", "throughput": 8444.19, "total_tokens": 372564808} {"current_steps": 366000, "total_steps": 761865, "loss": 1.9692, "lr": 5.307787381548943e-07, "epoch": 7.2060010631804845, "percentage": 48.04, "elapsed_time": "12:15:32", "remaining_time": "13:15:33", "throughput": 8444.25, "total_tokens": 372665648} {"current_steps": 366100, "total_steps": 761865, "loss": 2.0435, "lr": 5.305729460728233e-07, "epoch": 7.207969915929987, "percentage": 48.05, "elapsed_time": "12:15:44", "remaining_time": "13:15:21", "throughput": 8444.33, "total_tokens": 372767024} {"current_steps": 366200, "total_steps": 761865, "loss": 1.9828, "lr": 5.303671487920807e-07, "epoch": 7.209938768679491, "percentage": 48.07, "elapsed_time": "12:15:55", "remaining_time": "13:15:08", "throughput": 8444.41, "total_tokens": 372868616} {"current_steps": 366300, "total_steps": 761865, "loss": 2.0166, "lr": 5.301613463476606e-07, "epoch": 7.211907621428994, "percentage": 48.08, "elapsed_time": "12:16:07", "remaining_time": "13:14:55", "throughput": 8444.47, "total_tokens": 372969136} {"current_steps": 366400, "total_steps": 761865, "loss": 1.9703, "lr": 5.299555387745579e-07, "epoch": 7.213876474178496, "percentage": 48.09, "elapsed_time": "12:16:18", "remaining_time": "13:14:43", "throughput": 8444.55, "total_tokens": 373070784} {"current_steps": 366500, "total_steps": 761865, "loss": 1.9703, "lr": 5.297497261077686e-07, "epoch": 7.215845326927999, "percentage": 48.11, "elapsed_time": "12:16:30", "remaining_time": "13:14:30", "throughput": 8444.63, "total_tokens": 373173184} {"current_steps": 366600, "total_steps": 761865, "loss": 2.0189, "lr": 5.295439083822891e-07, "epoch": 7.217814179677502, "percentage": 48.12, "elapsed_time": "12:16:42", "remaining_time": "13:14:18", "throughput": 8444.71, "total_tokens": 373274960} {"current_steps": 366700, "total_steps": 761865, "loss": 1.9366, "lr": 5.293380856331173e-07, "epoch": 7.219783032427005, "percentage": 48.13, "elapsed_time": "12:16:53", "remaining_time": "13:14:06", "throughput": 8444.79, "total_tokens": 373377360} {"current_steps": 366800, "total_steps": 761865, "loss": 2.0299, "lr": 5.291322578952514e-07, "epoch": 7.2217518851765075, "percentage": 48.15, "elapsed_time": "12:17:05", "remaining_time": "13:13:53", "throughput": 8444.88, "total_tokens": 373479760} {"current_steps": 366900, "total_steps": 761865, "loss": 2.0199, "lr": 5.28926425203691e-07, "epoch": 7.22372073792601, "percentage": 48.16, "elapsed_time": "12:17:17", "remaining_time": "13:13:41", "throughput": 8444.96, "total_tokens": 373582160} {"current_steps": 367000, "total_steps": 761865, "loss": 2.0034, "lr": 5.287205875934357e-07, "epoch": 7.225689590675513, "percentage": 48.17, "elapsed_time": "12:17:28", "remaining_time": "13:13:28", "throughput": 8445.04, "total_tokens": 373683944} {"current_steps": 367100, "total_steps": 761865, "loss": 1.9944, "lr": 5.285147450994868e-07, "epoch": 7.227658443425017, "percentage": 48.18, "elapsed_time": "12:17:40", "remaining_time": "13:13:16", "throughput": 8445.13, "total_tokens": 373786344} {"current_steps": 367200, "total_steps": 761865, "loss": 1.9888, "lr": 5.283088977568459e-07, "epoch": 7.229627296174519, "percentage": 48.2, "elapsed_time": "12:17:52", "remaining_time": "13:13:03", "throughput": 8445.21, "total_tokens": 373887952} {"current_steps": 367300, "total_steps": 761865, "loss": 1.9572, "lr": 5.281030456005159e-07, "epoch": 7.231596148924022, "percentage": 48.21, "elapsed_time": "12:18:03", "remaining_time": "13:12:51", "throughput": 8445.29, "total_tokens": 373990352} {"current_steps": 367400, "total_steps": 761865, "loss": 1.9775, "lr": 5.278971886654999e-07, "epoch": 7.233565001673525, "percentage": 48.22, "elapsed_time": "12:18:15", "remaining_time": "13:12:38", "throughput": 8445.37, "total_tokens": 374091760} {"current_steps": 367500, "total_steps": 761865, "loss": 1.982, "lr": 5.276913269868024e-07, "epoch": 7.235533854423028, "percentage": 48.24, "elapsed_time": "12:18:27", "remaining_time": "13:12:26", "throughput": 8445.45, "total_tokens": 374193528} {"current_steps": 367600, "total_steps": 761865, "loss": 1.9915, "lr": 5.274854605994281e-07, "epoch": 7.23750270717253, "percentage": 48.25, "elapsed_time": "12:18:38", "remaining_time": "13:12:13", "throughput": 8445.53, "total_tokens": 374294808} {"current_steps": 367700, "total_steps": 761865, "loss": 1.9947, "lr": 5.272795895383831e-07, "epoch": 7.239471559922033, "percentage": 48.26, "elapsed_time": "12:18:50", "remaining_time": "13:12:00", "throughput": 8445.6, "total_tokens": 374396448} {"current_steps": 367800, "total_steps": 761865, "loss": 1.9894, "lr": 5.27073713838674e-07, "epoch": 7.241440412671536, "percentage": 48.28, "elapsed_time": "12:19:01", "remaining_time": "13:11:48", "throughput": 8445.68, "total_tokens": 374498288} {"current_steps": 367900, "total_steps": 761865, "loss": 1.9905, "lr": 5.268678335353084e-07, "epoch": 7.24340926542104, "percentage": 48.29, "elapsed_time": "12:19:13", "remaining_time": "13:11:35", "throughput": 8445.76, "total_tokens": 374599984} {"current_steps": 368000, "total_steps": 761865, "loss": 1.9732, "lr": 5.266619486632941e-07, "epoch": 7.245378118170542, "percentage": 48.3, "elapsed_time": "12:19:25", "remaining_time": "13:11:23", "throughput": 8445.84, "total_tokens": 374702384} {"current_steps": 368100, "total_steps": 761865, "loss": 1.9993, "lr": 5.264560592576404e-07, "epoch": 7.247346970920045, "percentage": 48.32, "elapsed_time": "12:19:36", "remaining_time": "13:11:11", "throughput": 8445.93, "total_tokens": 374804784} {"current_steps": 368200, "total_steps": 761865, "loss": 2.0149, "lr": 5.26250165353357e-07, "epoch": 7.249315823669548, "percentage": 48.33, "elapsed_time": "12:19:48", "remaining_time": "13:10:58", "throughput": 8446.01, "total_tokens": 374906256} {"current_steps": 368300, "total_steps": 761865, "loss": 1.958, "lr": 5.260442669854544e-07, "epoch": 7.251284676419051, "percentage": 48.34, "elapsed_time": "12:20:00", "remaining_time": "13:10:46", "throughput": 8446.09, "total_tokens": 375008656} {"current_steps": 368400, "total_steps": 761865, "loss": 1.9831, "lr": 5.258383641889438e-07, "epoch": 7.253253529168553, "percentage": 48.36, "elapsed_time": "12:20:11", "remaining_time": "13:10:33", "throughput": 8446.16, "total_tokens": 375109680} {"current_steps": 368500, "total_steps": 761865, "loss": 1.988, "lr": 5.256324569988373e-07, "epoch": 7.255222381918056, "percentage": 48.37, "elapsed_time": "12:20:23", "remaining_time": "13:10:21", "throughput": 8446.25, "total_tokens": 375212080} {"current_steps": 368600, "total_steps": 761865, "loss": 1.9472, "lr": 5.254265454501476e-07, "epoch": 7.257191234667559, "percentage": 48.38, "elapsed_time": "12:20:35", "remaining_time": "13:10:08", "throughput": 8446.33, "total_tokens": 375314000} {"current_steps": 368700, "total_steps": 761865, "loss": 1.983, "lr": 5.252206295778884e-07, "epoch": 7.259160087417062, "percentage": 48.39, "elapsed_time": "12:20:46", "remaining_time": "13:09:56", "throughput": 8446.41, "total_tokens": 375415704} {"current_steps": 368800, "total_steps": 761865, "loss": 2.0033, "lr": 5.250147094170738e-07, "epoch": 7.261128940166565, "percentage": 48.41, "elapsed_time": "12:20:58", "remaining_time": "13:09:43", "throughput": 8446.49, "total_tokens": 375518104} {"current_steps": 368900, "total_steps": 761865, "loss": 1.9646, "lr": 5.24808785002719e-07, "epoch": 7.263097792916068, "percentage": 48.42, "elapsed_time": "12:21:10", "remaining_time": "13:09:31", "throughput": 8446.58, "total_tokens": 375620504} {"current_steps": 369000, "total_steps": 761865, "loss": 1.9885, "lr": 5.246028563698394e-07, "epoch": 7.265066645665571, "percentage": 48.43, "elapsed_time": "12:21:21", "remaining_time": "13:09:18", "throughput": 8446.66, "total_tokens": 375722712} {"current_steps": 369100, "total_steps": 761865, "loss": 1.9718, "lr": 5.243969235534517e-07, "epoch": 7.267035498415074, "percentage": 48.45, "elapsed_time": "12:21:33", "remaining_time": "13:09:06", "throughput": 8446.74, "total_tokens": 375824536} {"current_steps": 369200, "total_steps": 761865, "loss": 1.9586, "lr": 5.241909865885728e-07, "epoch": 7.269004351164576, "percentage": 48.46, "elapsed_time": "12:21:45", "remaining_time": "13:08:53", "throughput": 8446.82, "total_tokens": 375926936} {"current_steps": 369300, "total_steps": 761865, "loss": 1.9874, "lr": 5.239850455102208e-07, "epoch": 7.270973203914079, "percentage": 48.47, "elapsed_time": "12:21:56", "remaining_time": "13:08:41", "throughput": 8446.89, "total_tokens": 376028128} {"current_steps": 369400, "total_steps": 761865, "loss": 1.9952, "lr": 5.23779100353414e-07, "epoch": 7.272942056663582, "percentage": 48.49, "elapsed_time": "12:22:08", "remaining_time": "13:08:28", "throughput": 8446.96, "total_tokens": 376129192} {"current_steps": 369500, "total_steps": 761865, "loss": 1.9623, "lr": 5.235731511531718e-07, "epoch": 7.274910909413085, "percentage": 48.5, "elapsed_time": "12:22:20", "remaining_time": "13:08:16", "throughput": 8447.04, "total_tokens": 376231592} {"current_steps": 369600, "total_steps": 761865, "loss": 2.0113, "lr": 5.23367197944514e-07, "epoch": 7.276879762162588, "percentage": 48.51, "elapsed_time": "12:22:31", "remaining_time": "13:08:03", "throughput": 8447.12, "total_tokens": 376333552} {"current_steps": 369700, "total_steps": 761865, "loss": 1.9529, "lr": 5.231612407624614e-07, "epoch": 7.278848614912091, "percentage": 48.53, "elapsed_time": "12:22:43", "remaining_time": "13:07:51", "throughput": 8447.21, "total_tokens": 376435672} {"current_steps": 369800, "total_steps": 761865, "loss": 2.0072, "lr": 5.229552796420351e-07, "epoch": 7.280817467661594, "percentage": 48.54, "elapsed_time": "12:22:54", "remaining_time": "13:07:38", "throughput": 8447.28, "total_tokens": 376536784} {"current_steps": 369900, "total_steps": 761865, "loss": 2.0258, "lr": 5.227493146182571e-07, "epoch": 7.2827863204110965, "percentage": 48.55, "elapsed_time": "12:23:06", "remaining_time": "13:07:26", "throughput": 8447.35, "total_tokens": 376637344} {"current_steps": 370000, "total_steps": 761865, "loss": 1.9895, "lr": 5.225433457261501e-07, "epoch": 7.284755173160599, "percentage": 48.57, "elapsed_time": "12:23:18", "remaining_time": "13:07:13", "throughput": 8447.42, "total_tokens": 376738952} {"current_steps": 370100, "total_steps": 761865, "loss": 1.9619, "lr": 5.223373730007371e-07, "epoch": 7.286724025910102, "percentage": 48.58, "elapsed_time": "12:23:30", "remaining_time": "13:07:01", "throughput": 8447.39, "total_tokens": 376840224} {"current_steps": 370200, "total_steps": 761865, "loss": 1.9698, "lr": 5.221313964770424e-07, "epoch": 7.288692878659605, "percentage": 48.59, "elapsed_time": "12:23:41", "remaining_time": "13:06:49", "throughput": 8447.46, "total_tokens": 376941584} {"current_steps": 370300, "total_steps": 761865, "loss": 1.9748, "lr": 5.219254161900903e-07, "epoch": 7.290661731409108, "percentage": 48.6, "elapsed_time": "12:23:53", "remaining_time": "13:06:36", "throughput": 8447.54, "total_tokens": 377043984} {"current_steps": 370400, "total_steps": 761865, "loss": 1.9599, "lr": 5.217194321749064e-07, "epoch": 7.29263058415861, "percentage": 48.62, "elapsed_time": "12:24:05", "remaining_time": "13:06:24", "throughput": 8447.62, "total_tokens": 377146384} {"current_steps": 370500, "total_steps": 761865, "loss": 2.0045, "lr": 5.215134444665157e-07, "epoch": 7.294599436908114, "percentage": 48.63, "elapsed_time": "12:24:16", "remaining_time": "13:06:11", "throughput": 8447.7, "total_tokens": 377248784} {"current_steps": 370600, "total_steps": 761865, "loss": 1.9863, "lr": 5.213074530999457e-07, "epoch": 7.296568289657617, "percentage": 48.64, "elapsed_time": "12:24:28", "remaining_time": "13:05:59", "throughput": 8447.77, "total_tokens": 377349416} {"current_steps": 370700, "total_steps": 761865, "loss": 1.9816, "lr": 5.211014581102227e-07, "epoch": 7.2985371424071195, "percentage": 48.66, "elapsed_time": "12:24:40", "remaining_time": "13:05:46", "throughput": 8447.84, "total_tokens": 377450296} {"current_steps": 370800, "total_steps": 761865, "loss": 2.0244, "lr": 5.208954595323749e-07, "epoch": 7.300505995156622, "percentage": 48.67, "elapsed_time": "12:24:51", "remaining_time": "13:05:34", "throughput": 8447.9, "total_tokens": 377550640} {"current_steps": 370900, "total_steps": 761865, "loss": 1.9991, "lr": 5.206894574014303e-07, "epoch": 7.302474847906125, "percentage": 48.68, "elapsed_time": "12:25:03", "remaining_time": "13:05:21", "throughput": 8447.98, "total_tokens": 377652896} {"current_steps": 371000, "total_steps": 761865, "loss": 1.9665, "lr": 5.204834517524182e-07, "epoch": 7.304443700655628, "percentage": 48.7, "elapsed_time": "12:25:14", "remaining_time": "13:05:09", "throughput": 8448.05, "total_tokens": 377753784} {"current_steps": 371100, "total_steps": 761865, "loss": 1.9223, "lr": 5.202774426203678e-07, "epoch": 7.3064125534051305, "percentage": 48.71, "elapsed_time": "12:25:26", "remaining_time": "13:04:56", "throughput": 8448.13, "total_tokens": 377856184} {"current_steps": 371200, "total_steps": 761865, "loss": 1.9927, "lr": 5.200714300403093e-07, "epoch": 7.308381406154634, "percentage": 48.72, "elapsed_time": "12:25:38", "remaining_time": "13:04:44", "throughput": 8448.2, "total_tokens": 377957056} {"current_steps": 371300, "total_steps": 761865, "loss": 1.9718, "lr": 5.198654140472733e-07, "epoch": 7.310350258904137, "percentage": 48.74, "elapsed_time": "12:25:49", "remaining_time": "13:04:31", "throughput": 8448.28, "total_tokens": 378059456} {"current_steps": 371400, "total_steps": 761865, "loss": 1.9936, "lr": 5.196593946762914e-07, "epoch": 7.31231911165364, "percentage": 48.75, "elapsed_time": "12:26:01", "remaining_time": "13:04:19", "throughput": 8448.36, "total_tokens": 378161320} {"current_steps": 371500, "total_steps": 761865, "loss": 2.0122, "lr": 5.194533719623951e-07, "epoch": 7.314287964403142, "percentage": 48.76, "elapsed_time": "12:26:13", "remaining_time": "13:04:06", "throughput": 8448.43, "total_tokens": 378262448} {"current_steps": 371600, "total_steps": 761865, "loss": 1.9676, "lr": 5.192473459406171e-07, "epoch": 7.316256817152645, "percentage": 48.78, "elapsed_time": "12:26:24", "remaining_time": "13:03:54", "throughput": 8448.52, "total_tokens": 378364848} {"current_steps": 371700, "total_steps": 761865, "loss": 1.9577, "lr": 5.190413166459901e-07, "epoch": 7.318225669902148, "percentage": 48.79, "elapsed_time": "12:26:36", "remaining_time": "13:03:41", "throughput": 8448.59, "total_tokens": 378466480} {"current_steps": 371800, "total_steps": 761865, "loss": 1.9613, "lr": 5.188352841135478e-07, "epoch": 7.320194522651651, "percentage": 48.8, "elapsed_time": "12:26:48", "remaining_time": "13:03:29", "throughput": 8448.67, "total_tokens": 378568256} {"current_steps": 371900, "total_steps": 761865, "loss": 1.9721, "lr": 5.186292483783244e-07, "epoch": 7.3221633754011535, "percentage": 48.81, "elapsed_time": "12:26:59", "remaining_time": "13:03:16", "throughput": 8448.74, "total_tokens": 378669696} {"current_steps": 372000, "total_steps": 761865, "loss": 2.0076, "lr": 5.184232094753545e-07, "epoch": 7.324132228150656, "percentage": 48.83, "elapsed_time": "12:27:11", "remaining_time": "13:03:04", "throughput": 8448.82, "total_tokens": 378772096} {"current_steps": 372100, "total_steps": 761865, "loss": 1.9804, "lr": 5.182171674396732e-07, "epoch": 7.32610108090016, "percentage": 48.84, "elapsed_time": "12:27:22", "remaining_time": "13:02:51", "throughput": 8448.9, "total_tokens": 378873680} {"current_steps": 372200, "total_steps": 761865, "loss": 1.9435, "lr": 5.180111223063162e-07, "epoch": 7.328069933649663, "percentage": 48.85, "elapsed_time": "12:27:34", "remaining_time": "13:02:39", "throughput": 8448.98, "total_tokens": 378976080} {"current_steps": 372300, "total_steps": 761865, "loss": 1.9769, "lr": 5.178050741103196e-07, "epoch": 7.330038786399165, "percentage": 48.87, "elapsed_time": "12:27:46", "remaining_time": "13:02:26", "throughput": 8449.05, "total_tokens": 379077664} {"current_steps": 372400, "total_steps": 761865, "loss": 1.9737, "lr": 5.175990228867205e-07, "epoch": 7.332007639148668, "percentage": 48.88, "elapsed_time": "12:27:57", "remaining_time": "13:02:14", "throughput": 8449.12, "total_tokens": 379179144} {"current_steps": 372500, "total_steps": 761865, "loss": 1.9448, "lr": 5.173929686705559e-07, "epoch": 7.333976491898171, "percentage": 48.89, "elapsed_time": "12:28:09", "remaining_time": "13:02:02", "throughput": 8449.2, "total_tokens": 379281544} {"current_steps": 372600, "total_steps": 761865, "loss": 2.0001, "lr": 5.171869114968639e-07, "epoch": 7.335945344647674, "percentage": 48.91, "elapsed_time": "12:28:21", "remaining_time": "13:01:49", "throughput": 8449.27, "total_tokens": 379382264} {"current_steps": 372700, "total_steps": 761865, "loss": 1.983, "lr": 5.169808514006822e-07, "epoch": 7.337914197397176, "percentage": 48.92, "elapsed_time": "12:28:32", "remaining_time": "13:01:36", "throughput": 8449.35, "total_tokens": 379484168} {"current_steps": 372800, "total_steps": 761865, "loss": 1.9849, "lr": 5.167747884170502e-07, "epoch": 7.339883050146679, "percentage": 48.93, "elapsed_time": "12:28:44", "remaining_time": "13:01:24", "throughput": 8449.43, "total_tokens": 379586568} {"current_steps": 372900, "total_steps": 761865, "loss": 2.0222, "lr": 5.165687225810068e-07, "epoch": 7.341851902896183, "percentage": 48.95, "elapsed_time": "12:28:56", "remaining_time": "13:01:12", "throughput": 8449.5, "total_tokens": 379688032} {"current_steps": 373000, "total_steps": 761865, "loss": 2.0037, "lr": 5.163626539275919e-07, "epoch": 7.343820755645686, "percentage": 48.96, "elapsed_time": "12:29:07", "remaining_time": "13:00:59", "throughput": 8449.58, "total_tokens": 379789992} {"current_steps": 373100, "total_steps": 761865, "loss": 2.0557, "lr": 5.161565824918457e-07, "epoch": 7.345789608395188, "percentage": 48.97, "elapsed_time": "12:29:19", "remaining_time": "13:00:47", "throughput": 8449.66, "total_tokens": 379891664} {"current_steps": 373200, "total_steps": 761865, "loss": 2.013, "lr": 5.15950508308809e-07, "epoch": 7.347758461144691, "percentage": 48.99, "elapsed_time": "12:29:31", "remaining_time": "13:00:34", "throughput": 8449.73, "total_tokens": 379992776} {"current_steps": 373300, "total_steps": 761865, "loss": 1.9999, "lr": 5.157444314135229e-07, "epoch": 7.349727313894194, "percentage": 49.0, "elapsed_time": "12:29:42", "remaining_time": "13:00:22", "throughput": 8449.8, "total_tokens": 380093768} {"current_steps": 373400, "total_steps": 761865, "loss": 1.9896, "lr": 5.15538351841029e-07, "epoch": 7.351696166643697, "percentage": 49.01, "elapsed_time": "12:29:54", "remaining_time": "13:00:09", "throughput": 8449.87, "total_tokens": 380195320} {"current_steps": 373500, "total_steps": 761865, "loss": 2.0226, "lr": 5.153322696263693e-07, "epoch": 7.353665019393199, "percentage": 49.02, "elapsed_time": "12:30:05", "remaining_time": "12:59:57", "throughput": 8449.95, "total_tokens": 380296872} {"current_steps": 373600, "total_steps": 761865, "loss": 1.9622, "lr": 5.151261848045867e-07, "epoch": 7.355633872142702, "percentage": 49.04, "elapsed_time": "12:30:17", "remaining_time": "12:59:44", "throughput": 8450.03, "total_tokens": 380399272} {"current_steps": 373700, "total_steps": 761865, "loss": 1.9745, "lr": 5.149200974107237e-07, "epoch": 7.357602724892205, "percentage": 49.05, "elapsed_time": "12:30:29", "remaining_time": "12:59:32", "throughput": 8450.08, "total_tokens": 380499280} {"current_steps": 373800, "total_steps": 761865, "loss": 1.9719, "lr": 5.147140074798242e-07, "epoch": 7.3595715776417086, "percentage": 49.06, "elapsed_time": "12:30:40", "remaining_time": "12:59:19", "throughput": 8450.16, "total_tokens": 380601680} {"current_steps": 373900, "total_steps": 761865, "loss": 1.9557, "lr": 5.145079150469317e-07, "epoch": 7.361540430391211, "percentage": 49.08, "elapsed_time": "12:30:52", "remaining_time": "12:59:07", "throughput": 8450.24, "total_tokens": 380704080} {"current_steps": 374000, "total_steps": 761865, "loss": 2.0062, "lr": 5.143018201470907e-07, "epoch": 7.363509283140714, "percentage": 49.09, "elapsed_time": "12:31:04", "remaining_time": "12:58:54", "throughput": 8450.32, "total_tokens": 380806480} {"current_steps": 374100, "total_steps": 761865, "loss": 1.9592, "lr": 5.140957228153458e-07, "epoch": 7.365478135890217, "percentage": 49.1, "elapsed_time": "12:31:15", "remaining_time": "12:58:42", "throughput": 8450.41, "total_tokens": 380908880} {"current_steps": 374200, "total_steps": 761865, "loss": 2.0127, "lr": 5.13889623086742e-07, "epoch": 7.36744698863972, "percentage": 49.12, "elapsed_time": "12:31:27", "remaining_time": "12:58:29", "throughput": 8450.48, "total_tokens": 381010488} {"current_steps": 374300, "total_steps": 761865, "loss": 1.9735, "lr": 5.13683520996325e-07, "epoch": 7.369415841389222, "percentage": 49.13, "elapsed_time": "12:31:39", "remaining_time": "12:58:17", "throughput": 8450.56, "total_tokens": 381112880} {"current_steps": 374400, "total_steps": 761865, "loss": 1.9619, "lr": 5.134774165791406e-07, "epoch": 7.371384694138725, "percentage": 49.14, "elapsed_time": "12:31:50", "remaining_time": "12:58:04", "throughput": 8450.64, "total_tokens": 381214616} {"current_steps": 374500, "total_steps": 761865, "loss": 1.9567, "lr": 5.132713098702354e-07, "epoch": 7.373353546888228, "percentage": 49.16, "elapsed_time": "12:32:02", "remaining_time": "12:57:52", "throughput": 8450.71, "total_tokens": 381316440} {"current_steps": 374600, "total_steps": 761865, "loss": 1.9488, "lr": 5.130652009046557e-07, "epoch": 7.3753223996377315, "percentage": 49.17, "elapsed_time": "12:32:14", "remaining_time": "12:57:40", "throughput": 8450.79, "total_tokens": 381418840} {"current_steps": 374700, "total_steps": 761865, "loss": 1.9884, "lr": 5.12859089717449e-07, "epoch": 7.377291252387234, "percentage": 49.18, "elapsed_time": "12:32:25", "remaining_time": "12:57:27", "throughput": 8450.87, "total_tokens": 381520672} {"current_steps": 374800, "total_steps": 761865, "loss": 1.9947, "lr": 5.126529763436622e-07, "epoch": 7.379260105136737, "percentage": 49.2, "elapsed_time": "12:32:37", "remaining_time": "12:57:15", "throughput": 8450.95, "total_tokens": 381623072} {"current_steps": 374900, "total_steps": 761865, "loss": 1.9858, "lr": 5.124468608183437e-07, "epoch": 7.38122895788624, "percentage": 49.21, "elapsed_time": "12:32:49", "remaining_time": "12:57:02", "throughput": 8451.04, "total_tokens": 381725472} {"current_steps": 375000, "total_steps": 761865, "loss": 1.9967, "lr": 5.122407431765415e-07, "epoch": 7.3831978106357425, "percentage": 49.22, "elapsed_time": "12:33:00", "remaining_time": "12:56:50", "throughput": 8451.11, "total_tokens": 381826600} {"current_steps": 375100, "total_steps": 761865, "loss": 1.9229, "lr": 5.120346234533042e-07, "epoch": 7.385166663385245, "percentage": 49.23, "elapsed_time": "12:33:12", "remaining_time": "12:56:38", "throughput": 8451.09, "total_tokens": 381929000} {"current_steps": 375200, "total_steps": 761865, "loss": 1.983, "lr": 5.118285016836806e-07, "epoch": 7.387135516134748, "percentage": 49.25, "elapsed_time": "12:33:24", "remaining_time": "12:56:25", "throughput": 8451.17, "total_tokens": 382031400} {"current_steps": 375300, "total_steps": 761865, "loss": 1.9336, "lr": 5.116223779027202e-07, "epoch": 7.389104368884251, "percentage": 49.26, "elapsed_time": "12:33:36", "remaining_time": "12:56:13", "throughput": 8451.25, "total_tokens": 382133800} {"current_steps": 375400, "total_steps": 761865, "loss": 1.9777, "lr": 5.114162521454724e-07, "epoch": 7.391073221633754, "percentage": 49.27, "elapsed_time": "12:33:47", "remaining_time": "12:56:01", "throughput": 8451.33, "total_tokens": 382236200} {"current_steps": 375500, "total_steps": 761865, "loss": 1.9951, "lr": 5.112101244469872e-07, "epoch": 7.393042074383257, "percentage": 49.29, "elapsed_time": "12:33:59", "remaining_time": "12:55:48", "throughput": 8451.42, "total_tokens": 382338600} {"current_steps": 375600, "total_steps": 761865, "loss": 1.9833, "lr": 5.110039948423148e-07, "epoch": 7.39501092713276, "percentage": 49.3, "elapsed_time": "12:34:11", "remaining_time": "12:55:36", "throughput": 8451.49, "total_tokens": 382439760} {"current_steps": 375700, "total_steps": 761865, "loss": 2.0236, "lr": 5.107978633665061e-07, "epoch": 7.396979779882263, "percentage": 49.31, "elapsed_time": "12:34:22", "remaining_time": "12:55:23", "throughput": 8451.56, "total_tokens": 382541456} {"current_steps": 375800, "total_steps": 761865, "loss": 1.9868, "lr": 5.105917300546114e-07, "epoch": 7.3989486326317655, "percentage": 49.33, "elapsed_time": "12:34:34", "remaining_time": "12:55:11", "throughput": 8451.64, "total_tokens": 382643720} {"current_steps": 375900, "total_steps": 761865, "loss": 2.014, "lr": 5.103855949416828e-07, "epoch": 7.400917485381268, "percentage": 49.34, "elapsed_time": "12:34:46", "remaining_time": "12:54:58", "throughput": 8451.71, "total_tokens": 382745352} {"current_steps": 376000, "total_steps": 761865, "loss": 1.9616, "lr": 5.101794580627711e-07, "epoch": 7.402886338130771, "percentage": 49.35, "elapsed_time": "12:34:57", "remaining_time": "12:54:46", "throughput": 8451.8, "total_tokens": 382847752} {"current_steps": 376100, "total_steps": 761865, "loss": 1.988, "lr": 5.099733194529285e-07, "epoch": 7.404855190880274, "percentage": 49.37, "elapsed_time": "12:35:09", "remaining_time": "12:54:33", "throughput": 8451.87, "total_tokens": 382949488} {"current_steps": 376200, "total_steps": 761865, "loss": 1.9586, "lr": 5.09767179147207e-07, "epoch": 7.4068240436297765, "percentage": 49.38, "elapsed_time": "12:35:21", "remaining_time": "12:54:21", "throughput": 8451.95, "total_tokens": 383051888} {"current_steps": 376300, "total_steps": 761865, "loss": 2.0053, "lr": 5.095610371806593e-07, "epoch": 7.40879289637928, "percentage": 49.39, "elapsed_time": "12:35:32", "remaining_time": "12:54:08", "throughput": 8452.02, "total_tokens": 383152944} {"current_steps": 376400, "total_steps": 761865, "loss": 2.0005, "lr": 5.093548935883374e-07, "epoch": 7.410761749128783, "percentage": 49.41, "elapsed_time": "12:35:44", "remaining_time": "12:53:56", "throughput": 8452.1, "total_tokens": 383255344} {"current_steps": 376500, "total_steps": 761865, "loss": 2.0023, "lr": 5.091487484052952e-07, "epoch": 7.412730601878286, "percentage": 49.42, "elapsed_time": "12:35:56", "remaining_time": "12:53:44", "throughput": 8452.18, "total_tokens": 383357744} {"current_steps": 376600, "total_steps": 761865, "loss": 1.9713, "lr": 5.089426016665854e-07, "epoch": 7.4146994546277885, "percentage": 49.43, "elapsed_time": "12:36:07", "remaining_time": "12:53:31", "throughput": 8452.25, "total_tokens": 383458144} {"current_steps": 376700, "total_steps": 761865, "loss": 1.9759, "lr": 5.087364534072615e-07, "epoch": 7.416668307377291, "percentage": 49.44, "elapsed_time": "12:36:19", "remaining_time": "12:53:19", "throughput": 8452.33, "total_tokens": 383560544} {"current_steps": 376800, "total_steps": 761865, "loss": 2.0017, "lr": 5.085303036623773e-07, "epoch": 7.418637160126794, "percentage": 49.46, "elapsed_time": "12:36:30", "remaining_time": "12:53:06", "throughput": 8452.41, "total_tokens": 383662720} {"current_steps": 376900, "total_steps": 761865, "loss": 2.0033, "lr": 5.08324152466987e-07, "epoch": 7.420606012876297, "percentage": 49.47, "elapsed_time": "12:36:42", "remaining_time": "12:52:54", "throughput": 8452.49, "total_tokens": 383764568} {"current_steps": 377000, "total_steps": 761865, "loss": 1.9831, "lr": 5.081179998561448e-07, "epoch": 7.4225748656257995, "percentage": 49.48, "elapsed_time": "12:36:54", "remaining_time": "12:52:41", "throughput": 8452.57, "total_tokens": 383866968} {"current_steps": 377100, "total_steps": 761865, "loss": 2.0068, "lr": 5.079118458649053e-07, "epoch": 7.424543718375302, "percentage": 49.5, "elapsed_time": "12:37:05", "remaining_time": "12:52:29", "throughput": 8452.64, "total_tokens": 383968736} {"current_steps": 377200, "total_steps": 761865, "loss": 1.991, "lr": 5.077056905283231e-07, "epoch": 7.426512571124806, "percentage": 49.51, "elapsed_time": "12:37:17", "remaining_time": "12:52:16", "throughput": 8452.72, "total_tokens": 384071136} {"current_steps": 377300, "total_steps": 761865, "loss": 1.9528, "lr": 5.074995338814531e-07, "epoch": 7.428481423874309, "percentage": 49.52, "elapsed_time": "12:37:29", "remaining_time": "12:52:04", "throughput": 8452.8, "total_tokens": 384173536} {"current_steps": 377400, "total_steps": 761865, "loss": 1.9709, "lr": 5.072933759593506e-07, "epoch": 7.430450276623811, "percentage": 49.54, "elapsed_time": "12:37:40", "remaining_time": "12:51:51", "throughput": 8452.87, "total_tokens": 384274624} {"current_steps": 377500, "total_steps": 761865, "loss": 1.9723, "lr": 5.070872167970712e-07, "epoch": 7.432419129373314, "percentage": 49.55, "elapsed_time": "12:37:52", "remaining_time": "12:51:39", "throughput": 8452.95, "total_tokens": 384377024} {"current_steps": 377600, "total_steps": 761865, "loss": 1.9585, "lr": 5.068810564296702e-07, "epoch": 7.434387982122817, "percentage": 49.56, "elapsed_time": "12:38:04", "remaining_time": "12:51:27", "throughput": 8453.03, "total_tokens": 384479424} {"current_steps": 377700, "total_steps": 761865, "loss": 1.9816, "lr": 5.066748948922039e-07, "epoch": 7.43635683487232, "percentage": 49.58, "elapsed_time": "12:38:15", "remaining_time": "12:51:14", "throughput": 8453.11, "total_tokens": 384581824} {"current_steps": 377800, "total_steps": 761865, "loss": 1.9873, "lr": 5.064687322197277e-07, "epoch": 7.4383256876218224, "percentage": 49.59, "elapsed_time": "12:38:27", "remaining_time": "12:51:02", "throughput": 8453.19, "total_tokens": 384683360} {"current_steps": 377900, "total_steps": 761865, "loss": 2.0197, "lr": 5.062625684472981e-07, "epoch": 7.440294540371326, "percentage": 49.6, "elapsed_time": "12:38:39", "remaining_time": "12:50:49", "throughput": 8453.26, "total_tokens": 384784528} {"current_steps": 378000, "total_steps": 761865, "loss": 1.9432, "lr": 5.060564036099718e-07, "epoch": 7.442263393120829, "percentage": 49.62, "elapsed_time": "12:38:50", "remaining_time": "12:50:37", "throughput": 8453.34, "total_tokens": 384886928} {"current_steps": 378100, "total_steps": 761865, "loss": 1.9394, "lr": 5.05850237742805e-07, "epoch": 7.444232245870332, "percentage": 49.63, "elapsed_time": "12:39:02", "remaining_time": "12:50:24", "throughput": 8453.41, "total_tokens": 384989328} {"current_steps": 378200, "total_steps": 761865, "loss": 1.9962, "lr": 5.056440708808547e-07, "epoch": 7.446201098619834, "percentage": 49.64, "elapsed_time": "12:39:14", "remaining_time": "12:50:12", "throughput": 8453.5, "total_tokens": 385091728} {"current_steps": 378300, "total_steps": 761865, "loss": 1.9904, "lr": 5.054379030591777e-07, "epoch": 7.448169951369337, "percentage": 49.65, "elapsed_time": "12:39:25", "remaining_time": "12:49:59", "throughput": 8453.57, "total_tokens": 385193256} {"current_steps": 378400, "total_steps": 761865, "loss": 2.005, "lr": 5.052317343128312e-07, "epoch": 7.45013880411884, "percentage": 49.67, "elapsed_time": "12:39:37", "remaining_time": "12:49:47", "throughput": 8453.63, "total_tokens": 385294232} {"current_steps": 378500, "total_steps": 761865, "loss": 1.9861, "lr": 5.050255646768723e-07, "epoch": 7.452107656868343, "percentage": 49.68, "elapsed_time": "12:39:49", "remaining_time": "12:49:35", "throughput": 8453.71, "total_tokens": 385396632} {"current_steps": 378600, "total_steps": 761865, "loss": 1.9449, "lr": 5.048193941863586e-07, "epoch": 7.454076509617845, "percentage": 49.69, "elapsed_time": "12:40:00", "remaining_time": "12:49:22", "throughput": 8453.79, "total_tokens": 385499032} {"current_steps": 378700, "total_steps": 761865, "loss": 2.0466, "lr": 5.046132228763476e-07, "epoch": 7.456045362367348, "percentage": 49.71, "elapsed_time": "12:40:12", "remaining_time": "12:49:10", "throughput": 8453.87, "total_tokens": 385601432} {"current_steps": 378800, "total_steps": 761865, "loss": 1.9658, "lr": 5.044070507818968e-07, "epoch": 7.458014215116852, "percentage": 49.72, "elapsed_time": "12:40:24", "remaining_time": "12:48:57", "throughput": 8453.94, "total_tokens": 385702968} {"current_steps": 378900, "total_steps": 761865, "loss": 1.98, "lr": 5.042008779380642e-07, "epoch": 7.459983067866355, "percentage": 49.73, "elapsed_time": "12:40:35", "remaining_time": "12:48:45", "throughput": 8454.03, "total_tokens": 385805368} {"current_steps": 379000, "total_steps": 761865, "loss": 1.9442, "lr": 5.039947043799078e-07, "epoch": 7.461951920615857, "percentage": 49.75, "elapsed_time": "12:40:47", "remaining_time": "12:48:32", "throughput": 8454.09, "total_tokens": 385906328} {"current_steps": 379100, "total_steps": 761865, "loss": 1.9677, "lr": 5.037885301424857e-07, "epoch": 7.46392077336536, "percentage": 49.76, "elapsed_time": "12:40:58", "remaining_time": "12:48:20", "throughput": 8454.17, "total_tokens": 386007952} {"current_steps": 379200, "total_steps": 761865, "loss": 2.0439, "lr": 5.035823552608561e-07, "epoch": 7.465889626114863, "percentage": 49.77, "elapsed_time": "12:41:10", "remaining_time": "12:48:07", "throughput": 8454.24, "total_tokens": 386109376} {"current_steps": 379300, "total_steps": 761865, "loss": 2.0019, "lr": 5.033761797700769e-07, "epoch": 7.467858478864366, "percentage": 49.79, "elapsed_time": "12:41:22", "remaining_time": "12:47:55", "throughput": 8454.31, "total_tokens": 386211112} {"current_steps": 379400, "total_steps": 761865, "loss": 1.9618, "lr": 5.031700037052071e-07, "epoch": 7.469827331613868, "percentage": 49.8, "elapsed_time": "12:41:33", "remaining_time": "12:47:42", "throughput": 8454.39, "total_tokens": 386313512} {"current_steps": 379500, "total_steps": 761865, "loss": 1.9814, "lr": 5.029638271013047e-07, "epoch": 7.471796184363371, "percentage": 49.81, "elapsed_time": "12:41:45", "remaining_time": "12:47:30", "throughput": 8454.47, "total_tokens": 386415912} {"current_steps": 379600, "total_steps": 761865, "loss": 1.9812, "lr": 5.027576499934286e-07, "epoch": 7.473765037112875, "percentage": 49.83, "elapsed_time": "12:41:57", "remaining_time": "12:47:18", "throughput": 8454.55, "total_tokens": 386518312} {"current_steps": 379700, "total_steps": 761865, "loss": 2.0277, "lr": 5.025514724166373e-07, "epoch": 7.4757338898623775, "percentage": 49.84, "elapsed_time": "12:42:08", "remaining_time": "12:47:05", "throughput": 8454.63, "total_tokens": 386620112} {"current_steps": 379800, "total_steps": 761865, "loss": 1.9941, "lr": 5.023452944059896e-07, "epoch": 7.47770274261188, "percentage": 49.85, "elapsed_time": "12:42:20", "remaining_time": "12:46:53", "throughput": 8454.69, "total_tokens": 386721640} {"current_steps": 379900, "total_steps": 761865, "loss": 2.0435, "lr": 5.021391159965444e-07, "epoch": 7.479671595361383, "percentage": 49.86, "elapsed_time": "12:42:32", "remaining_time": "12:46:40", "throughput": 8454.77, "total_tokens": 386824040} {"current_steps": 380000, "total_steps": 761865, "loss": 1.9917, "lr": 5.019329372233607e-07, "epoch": 7.481640448110886, "percentage": 49.88, "elapsed_time": "12:42:43", "remaining_time": "12:46:28", "throughput": 8454.85, "total_tokens": 386925888} {"current_steps": 380100, "total_steps": 761865, "loss": 1.9669, "lr": 5.017267581214971e-07, "epoch": 7.483609300860389, "percentage": 49.89, "elapsed_time": "12:42:56", "remaining_time": "12:46:16", "throughput": 8454.82, "total_tokens": 387028288} {"current_steps": 380200, "total_steps": 761865, "loss": 2.0032, "lr": 5.015205787260131e-07, "epoch": 7.485578153609891, "percentage": 49.9, "elapsed_time": "12:43:07", "remaining_time": "12:46:04", "throughput": 8454.89, "total_tokens": 387129536} {"current_steps": 380300, "total_steps": 761865, "loss": 1.98, "lr": 5.013143990719674e-07, "epoch": 7.487547006359394, "percentage": 49.92, "elapsed_time": "12:43:19", "remaining_time": "12:45:51", "throughput": 8454.96, "total_tokens": 387231232} {"current_steps": 380400, "total_steps": 761865, "loss": 1.9772, "lr": 5.011082191944193e-07, "epoch": 7.489515859108897, "percentage": 49.93, "elapsed_time": "12:43:30", "remaining_time": "12:45:39", "throughput": 8455.04, "total_tokens": 387333184} {"current_steps": 380500, "total_steps": 761865, "loss": 1.9928, "lr": 5.009020391284277e-07, "epoch": 7.4914847118584005, "percentage": 49.94, "elapsed_time": "12:43:42", "remaining_time": "12:45:26", "throughput": 8455.11, "total_tokens": 387434408} {"current_steps": 380600, "total_steps": 761865, "loss": 1.9968, "lr": 5.006958589090521e-07, "epoch": 7.493453564607903, "percentage": 49.96, "elapsed_time": "12:43:54", "remaining_time": "12:45:14", "throughput": 8455.19, "total_tokens": 387536808} {"current_steps": 380700, "total_steps": 761865, "loss": 1.9626, "lr": 5.004896785713515e-07, "epoch": 7.495422417357406, "percentage": 49.97, "elapsed_time": "12:44:05", "remaining_time": "12:45:01", "throughput": 8455.26, "total_tokens": 387639208} {"current_steps": 380800, "total_steps": 761865, "loss": 2.0093, "lr": 5.002834981503852e-07, "epoch": 7.497391270106909, "percentage": 49.98, "elapsed_time": "12:44:17", "remaining_time": "12:44:49", "throughput": 8455.34, "total_tokens": 387741112} {"current_steps": 380900, "total_steps": 761865, "loss": 2.0292, "lr": 5.000773176812125e-07, "epoch": 7.4993601228564115, "percentage": 50.0, "elapsed_time": "12:44:29", "remaining_time": "12:44:37", "throughput": 8455.41, "total_tokens": 387842600} {"current_steps": 381000, "total_steps": 761865, "loss": 1.9622, "lr": 4.998711371988923e-07, "epoch": 7.501328975605914, "percentage": 50.01, "elapsed_time": "12:44:40", "remaining_time": "12:44:24", "throughput": 8455.47, "total_tokens": 387943632} {"current_steps": 381100, "total_steps": 761865, "loss": 2.0529, "lr": 4.996649567384845e-07, "epoch": 7.503297828355417, "percentage": 50.02, "elapsed_time": "12:44:52", "remaining_time": "12:44:12", "throughput": 8455.54, "total_tokens": 388044400} {"current_steps": 381200, "total_steps": 761865, "loss": 1.9565, "lr": 4.994587763350477e-07, "epoch": 7.50526668110492, "percentage": 50.04, "elapsed_time": "12:45:03", "remaining_time": "12:43:59", "throughput": 8455.61, "total_tokens": 388145936} {"current_steps": 381300, "total_steps": 761865, "loss": 1.9969, "lr": 4.992525960236417e-07, "epoch": 7.507235533854423, "percentage": 50.05, "elapsed_time": "12:45:15", "remaining_time": "12:43:47", "throughput": 8455.68, "total_tokens": 388248336} {"current_steps": 381400, "total_steps": 761865, "loss": 1.956, "lr": 4.990464158393252e-07, "epoch": 7.509204386603926, "percentage": 50.06, "elapsed_time": "12:45:27", "remaining_time": "12:43:34", "throughput": 8455.76, "total_tokens": 388350736} {"current_steps": 381500, "total_steps": 761865, "loss": 1.9539, "lr": 4.988402358171577e-07, "epoch": 7.511173239353429, "percentage": 50.07, "elapsed_time": "12:45:38", "remaining_time": "12:43:22", "throughput": 8455.84, "total_tokens": 388452512} {"current_steps": 381600, "total_steps": 761865, "loss": 2.0061, "lr": 4.986340559921984e-07, "epoch": 7.513142092102932, "percentage": 50.09, "elapsed_time": "12:45:50", "remaining_time": "12:43:09", "throughput": 8455.91, "total_tokens": 388554248} {"current_steps": 381700, "total_steps": 761865, "loss": 1.9892, "lr": 4.984278763995062e-07, "epoch": 7.5151109448524345, "percentage": 50.1, "elapsed_time": "12:46:02", "remaining_time": "12:42:57", "throughput": 8455.99, "total_tokens": 388656648} {"current_steps": 381800, "total_steps": 761865, "loss": 1.98, "lr": 4.982216970741406e-07, "epoch": 7.517079797601937, "percentage": 50.11, "elapsed_time": "12:46:13", "remaining_time": "12:42:44", "throughput": 8456.06, "total_tokens": 388757640} {"current_steps": 381900, "total_steps": 761865, "loss": 2.0105, "lr": 4.980155180511602e-07, "epoch": 7.51904865035144, "percentage": 50.13, "elapsed_time": "12:46:25", "remaining_time": "12:42:32", "throughput": 8456.13, "total_tokens": 388860040} {"current_steps": 382000, "total_steps": 761865, "loss": 2.0139, "lr": 4.978093393656243e-07, "epoch": 7.521017503100943, "percentage": 50.14, "elapsed_time": "12:46:37", "remaining_time": "12:42:20", "throughput": 8456.19, "total_tokens": 388960760} {"current_steps": 382100, "total_steps": 761865, "loss": 1.9737, "lr": 4.976031610525918e-07, "epoch": 7.5229863558504455, "percentage": 50.15, "elapsed_time": "12:46:48", "remaining_time": "12:42:07", "throughput": 8456.27, "total_tokens": 389062648} {"current_steps": 382200, "total_steps": 761865, "loss": 2.0052, "lr": 4.973969831471215e-07, "epoch": 7.524955208599949, "percentage": 50.17, "elapsed_time": "12:47:00", "remaining_time": "12:41:55", "throughput": 8456.34, "total_tokens": 389164152} {"current_steps": 382300, "total_steps": 761865, "loss": 1.9984, "lr": 4.971908056842723e-07, "epoch": 7.526924061349452, "percentage": 50.18, "elapsed_time": "12:47:12", "remaining_time": "12:41:42", "throughput": 8456.42, "total_tokens": 389266552} {"current_steps": 382400, "total_steps": 761865, "loss": 1.9902, "lr": 4.969846286991027e-07, "epoch": 7.528892914098955, "percentage": 50.19, "elapsed_time": "12:47:23", "remaining_time": "12:41:30", "throughput": 8456.49, "total_tokens": 389368064} {"current_steps": 382500, "total_steps": 761865, "loss": 1.966, "lr": 4.967784522266718e-07, "epoch": 7.530861766848457, "percentage": 50.21, "elapsed_time": "12:47:35", "remaining_time": "12:41:17", "throughput": 8456.56, "total_tokens": 389469832} {"current_steps": 382600, "total_steps": 761865, "loss": 2.0059, "lr": 4.965722763020377e-07, "epoch": 7.53283061959796, "percentage": 50.22, "elapsed_time": "12:47:46", "remaining_time": "12:41:05", "throughput": 8456.62, "total_tokens": 389570504} {"current_steps": 382700, "total_steps": 761865, "loss": 1.9822, "lr": 4.963661009602594e-07, "epoch": 7.534799472347463, "percentage": 50.23, "elapsed_time": "12:47:58", "remaining_time": "12:40:52", "throughput": 8456.7, "total_tokens": 389672904} {"current_steps": 382800, "total_steps": 761865, "loss": 2.0026, "lr": 4.961599262363947e-07, "epoch": 7.536768325096966, "percentage": 50.25, "elapsed_time": "12:48:10", "remaining_time": "12:40:40", "throughput": 8456.76, "total_tokens": 389773800} {"current_steps": 382900, "total_steps": 761865, "loss": 2.0021, "lr": 4.959537521655025e-07, "epoch": 7.538737177846469, "percentage": 50.26, "elapsed_time": "12:48:21", "remaining_time": "12:40:28", "throughput": 8456.84, "total_tokens": 389875648} {"current_steps": 383000, "total_steps": 761865, "loss": 1.9656, "lr": 4.957475787826402e-07, "epoch": 7.540706030595972, "percentage": 50.27, "elapsed_time": "12:48:33", "remaining_time": "12:40:15", "throughput": 8456.91, "total_tokens": 389977280} {"current_steps": 383100, "total_steps": 761865, "loss": 1.9959, "lr": 4.955414061228667e-07, "epoch": 7.542674883345475, "percentage": 50.28, "elapsed_time": "12:48:45", "remaining_time": "12:40:03", "throughput": 8456.97, "total_tokens": 390078728} {"current_steps": 383200, "total_steps": 761865, "loss": 2.0271, "lr": 4.95335234221239e-07, "epoch": 7.544643736094978, "percentage": 50.3, "elapsed_time": "12:48:56", "remaining_time": "12:39:50", "throughput": 8457.05, "total_tokens": 390181128} {"current_steps": 383300, "total_steps": 761865, "loss": 1.9793, "lr": 4.951290631128159e-07, "epoch": 7.54661258884448, "percentage": 50.31, "elapsed_time": "12:49:08", "remaining_time": "12:39:38", "throughput": 8457.12, "total_tokens": 390283296} {"current_steps": 383400, "total_steps": 761865, "loss": 1.9816, "lr": 4.949228928326541e-07, "epoch": 7.548581441593983, "percentage": 50.32, "elapsed_time": "12:49:20", "remaining_time": "12:39:25", "throughput": 8457.2, "total_tokens": 390385424} {"current_steps": 383500, "total_steps": 761865, "loss": 1.9783, "lr": 4.947167234158116e-07, "epoch": 7.550550294343486, "percentage": 50.34, "elapsed_time": "12:49:31", "remaining_time": "12:39:13", "throughput": 8457.28, "total_tokens": 390487824} {"current_steps": 383600, "total_steps": 761865, "loss": 1.9687, "lr": 4.945105548973459e-07, "epoch": 7.552519147092989, "percentage": 50.35, "elapsed_time": "12:49:43", "remaining_time": "12:39:01", "throughput": 8457.35, "total_tokens": 390589808} {"current_steps": 383700, "total_steps": 761865, "loss": 2.0251, "lr": 4.94304387312314e-07, "epoch": 7.554487999842491, "percentage": 50.36, "elapsed_time": "12:49:55", "remaining_time": "12:38:48", "throughput": 8457.42, "total_tokens": 390690984} {"current_steps": 383800, "total_steps": 761865, "loss": 1.9761, "lr": 4.94098220695773e-07, "epoch": 7.556456852591994, "percentage": 50.38, "elapsed_time": "12:50:06", "remaining_time": "12:38:36", "throughput": 8457.5, "total_tokens": 390792944} {"current_steps": 383900, "total_steps": 761865, "loss": 2.0295, "lr": 4.938920550827797e-07, "epoch": 7.558425705341498, "percentage": 50.39, "elapsed_time": "12:50:18", "remaining_time": "12:38:23", "throughput": 8457.55, "total_tokens": 390892968} {"current_steps": 384000, "total_steps": 761865, "loss": 1.9938, "lr": 4.936858905083911e-07, "epoch": 7.560394558091001, "percentage": 50.4, "elapsed_time": "12:50:29", "remaining_time": "12:38:11", "throughput": 8457.63, "total_tokens": 390995368} {"current_steps": 384100, "total_steps": 761865, "loss": 1.9942, "lr": 4.934797270076633e-07, "epoch": 7.562363410840503, "percentage": 50.42, "elapsed_time": "12:50:41", "remaining_time": "12:37:58", "throughput": 8457.71, "total_tokens": 391097768} {"current_steps": 384200, "total_steps": 761865, "loss": 1.974, "lr": 4.932735646156531e-07, "epoch": 7.564332263590006, "percentage": 50.43, "elapsed_time": "12:50:53", "remaining_time": "12:37:46", "throughput": 8457.78, "total_tokens": 391199616} {"current_steps": 384300, "total_steps": 761865, "loss": 1.9561, "lr": 4.930674033674164e-07, "epoch": 7.566301116339509, "percentage": 50.44, "elapsed_time": "12:51:04", "remaining_time": "12:37:34", "throughput": 8457.86, "total_tokens": 391301424} {"current_steps": 384400, "total_steps": 761865, "loss": 1.9855, "lr": 4.928612432980095e-07, "epoch": 7.568269969089012, "percentage": 50.46, "elapsed_time": "12:51:16", "remaining_time": "12:37:21", "throughput": 8457.92, "total_tokens": 391402448} {"current_steps": 384500, "total_steps": 761865, "loss": 1.9937, "lr": 4.926550844424879e-07, "epoch": 7.570238821838514, "percentage": 50.47, "elapsed_time": "12:51:28", "remaining_time": "12:37:09", "throughput": 8458.0, "total_tokens": 391504024} {"current_steps": 384600, "total_steps": 761865, "loss": 1.9792, "lr": 4.92448926835907e-07, "epoch": 7.572207674588018, "percentage": 50.48, "elapsed_time": "12:51:39", "remaining_time": "12:36:56", "throughput": 8458.06, "total_tokens": 391605728} {"current_steps": 384700, "total_steps": 761865, "loss": 1.9588, "lr": 4.922427705133227e-07, "epoch": 7.574176527337521, "percentage": 50.49, "elapsed_time": "12:51:51", "remaining_time": "12:36:44", "throughput": 8458.13, "total_tokens": 391707208} {"current_steps": 384800, "total_steps": 761865, "loss": 1.9357, "lr": 4.920366155097896e-07, "epoch": 7.5761453800870235, "percentage": 50.51, "elapsed_time": "12:52:03", "remaining_time": "12:36:31", "throughput": 8458.21, "total_tokens": 391809608} {"current_steps": 384900, "total_steps": 761865, "loss": 1.9654, "lr": 4.918304618603631e-07, "epoch": 7.578114232836526, "percentage": 50.52, "elapsed_time": "12:52:14", "remaining_time": "12:36:19", "throughput": 8458.28, "total_tokens": 391912008} {"current_steps": 385000, "total_steps": 761865, "loss": 1.9744, "lr": 4.916243096000975e-07, "epoch": 7.580083085586029, "percentage": 50.53, "elapsed_time": "12:52:26", "remaining_time": "12:36:07", "throughput": 8458.36, "total_tokens": 392014408} {"current_steps": 385100, "total_steps": 761865, "loss": 2.0231, "lr": 4.914181587640474e-07, "epoch": 7.582051938335532, "percentage": 50.55, "elapsed_time": "12:52:40", "remaining_time": "12:35:56", "throughput": 8458.04, "total_tokens": 392116808} {"current_steps": 385200, "total_steps": 761865, "loss": 2.009, "lr": 4.912120093872671e-07, "epoch": 7.584020791085035, "percentage": 50.56, "elapsed_time": "12:52:51", "remaining_time": "12:35:44", "throughput": 8458.12, "total_tokens": 392219208} {"current_steps": 385300, "total_steps": 761865, "loss": 2.024, "lr": 4.910058615048106e-07, "epoch": 7.585989643834537, "percentage": 50.57, "elapsed_time": "12:53:03", "remaining_time": "12:35:32", "throughput": 8458.19, "total_tokens": 392321608} {"current_steps": 385400, "total_steps": 761865, "loss": 1.9752, "lr": 4.907997151517312e-07, "epoch": 7.58795849658404, "percentage": 50.59, "elapsed_time": "12:53:15", "remaining_time": "12:35:19", "throughput": 8458.27, "total_tokens": 392424008} {"current_steps": 385500, "total_steps": 761865, "loss": 2.0203, "lr": 4.905935703630827e-07, "epoch": 7.589927349333543, "percentage": 50.6, "elapsed_time": "12:53:26", "remaining_time": "12:35:07", "throughput": 8458.35, "total_tokens": 392525792} {"current_steps": 385600, "total_steps": 761865, "loss": 2.0493, "lr": 4.903874271739183e-07, "epoch": 7.5918962020830465, "percentage": 50.61, "elapsed_time": "12:53:38", "remaining_time": "12:34:54", "throughput": 8458.42, "total_tokens": 392627240} {"current_steps": 385700, "total_steps": 761865, "loss": 1.9721, "lr": 4.901812856192907e-07, "epoch": 7.593865054832549, "percentage": 50.63, "elapsed_time": "12:53:50", "remaining_time": "12:34:42", "throughput": 8458.48, "total_tokens": 392728072} {"current_steps": 385800, "total_steps": 761865, "loss": 1.958, "lr": 4.89975145734253e-07, "epoch": 7.595833907582052, "percentage": 50.64, "elapsed_time": "12:54:01", "remaining_time": "12:34:29", "throughput": 8458.55, "total_tokens": 392829648} {"current_steps": 385900, "total_steps": 761865, "loss": 1.9792, "lr": 4.897690075538569e-07, "epoch": 7.597802760331555, "percentage": 50.65, "elapsed_time": "12:54:13", "remaining_time": "12:34:17", "throughput": 8458.63, "total_tokens": 392932048} {"current_steps": 386000, "total_steps": 761865, "loss": 1.9674, "lr": 4.89562871113155e-07, "epoch": 7.5997716130810575, "percentage": 50.67, "elapsed_time": "12:54:24", "remaining_time": "12:34:04", "throughput": 8458.69, "total_tokens": 393033064} {"current_steps": 386100, "total_steps": 761865, "loss": 1.9564, "lr": 4.893567364471987e-07, "epoch": 7.60174046583056, "percentage": 50.68, "elapsed_time": "12:54:36", "remaining_time": "12:33:52", "throughput": 8458.77, "total_tokens": 393134944} {"current_steps": 386200, "total_steps": 761865, "loss": 1.9998, "lr": 4.891506035910397e-07, "epoch": 7.603709318580063, "percentage": 50.69, "elapsed_time": "12:54:48", "remaining_time": "12:33:40", "throughput": 8458.82, "total_tokens": 393235272} {"current_steps": 386300, "total_steps": 761865, "loss": 1.9973, "lr": 4.889444725797289e-07, "epoch": 7.605678171329567, "percentage": 50.7, "elapsed_time": "12:54:59", "remaining_time": "12:33:27", "throughput": 8458.9, "total_tokens": 393337672} {"current_steps": 386400, "total_steps": 761865, "loss": 1.9796, "lr": 4.887383434483174e-07, "epoch": 7.6076470240790695, "percentage": 50.72, "elapsed_time": "12:55:11", "remaining_time": "12:33:15", "throughput": 8458.97, "total_tokens": 393438960} {"current_steps": 386500, "total_steps": 761865, "loss": 1.9711, "lr": 4.885322162318555e-07, "epoch": 7.609615876828572, "percentage": 50.73, "elapsed_time": "12:55:23", "remaining_time": "12:33:02", "throughput": 8459.05, "total_tokens": 393541000} {"current_steps": 386600, "total_steps": 761865, "loss": 1.9856, "lr": 4.883260909653936e-07, "epoch": 7.611584729578075, "percentage": 50.74, "elapsed_time": "12:55:34", "remaining_time": "12:32:50", "throughput": 8459.12, "total_tokens": 393643400} {"current_steps": 386700, "total_steps": 761865, "loss": 2.0015, "lr": 4.881199676839815e-07, "epoch": 7.613553582327578, "percentage": 50.76, "elapsed_time": "12:55:46", "remaining_time": "12:32:37", "throughput": 8459.2, "total_tokens": 393745800} {"current_steps": 386800, "total_steps": 761865, "loss": 1.9924, "lr": 4.879138464226685e-07, "epoch": 7.6155224350770805, "percentage": 50.77, "elapsed_time": "12:55:58", "remaining_time": "12:32:25", "throughput": 8459.27, "total_tokens": 393847664} {"current_steps": 386900, "total_steps": 761865, "loss": 1.9937, "lr": 4.877077272165042e-07, "epoch": 7.617491287826583, "percentage": 50.78, "elapsed_time": "12:56:09", "remaining_time": "12:32:13", "throughput": 8459.35, "total_tokens": 393949472} {"current_steps": 387000, "total_steps": 761865, "loss": 1.9419, "lr": 4.875016101005371e-07, "epoch": 7.619460140576086, "percentage": 50.8, "elapsed_time": "12:56:21", "remaining_time": "12:32:00", "throughput": 8459.43, "total_tokens": 394051872} {"current_steps": 387100, "total_steps": 761865, "loss": 2.0024, "lr": 4.87295495109816e-07, "epoch": 7.621428993325589, "percentage": 50.81, "elapsed_time": "12:56:33", "remaining_time": "12:31:48", "throughput": 8459.5, "total_tokens": 394154272} {"current_steps": 387200, "total_steps": 761865, "loss": 1.9831, "lr": 4.870893822793885e-07, "epoch": 7.623397846075092, "percentage": 50.82, "elapsed_time": "12:56:44", "remaining_time": "12:31:35", "throughput": 8459.58, "total_tokens": 394256672} {"current_steps": 387300, "total_steps": 761865, "loss": 1.953, "lr": 4.868832716443028e-07, "epoch": 7.625366698824595, "percentage": 50.84, "elapsed_time": "12:56:56", "remaining_time": "12:31:23", "throughput": 8459.66, "total_tokens": 394359072} {"current_steps": 387400, "total_steps": 761865, "loss": 2.0144, "lr": 4.866771632396061e-07, "epoch": 7.627335551574098, "percentage": 50.85, "elapsed_time": "12:57:08", "remaining_time": "12:31:11", "throughput": 8459.73, "total_tokens": 394460712} {"current_steps": 387500, "total_steps": 761865, "loss": 1.9703, "lr": 4.864710571003452e-07, "epoch": 7.629304404323601, "percentage": 50.86, "elapsed_time": "12:57:19", "remaining_time": "12:30:58", "throughput": 8459.8, "total_tokens": 394562384} {"current_steps": 387600, "total_steps": 761865, "loss": 1.9779, "lr": 4.862649532615674e-07, "epoch": 7.6312732570731034, "percentage": 50.88, "elapsed_time": "12:57:31", "remaining_time": "12:30:46", "throughput": 8459.88, "total_tokens": 394664784} {"current_steps": 387700, "total_steps": 761865, "loss": 1.9999, "lr": 4.86058851758318e-07, "epoch": 7.633242109822606, "percentage": 50.89, "elapsed_time": "12:57:42", "remaining_time": "12:30:33", "throughput": 8459.94, "total_tokens": 394765608} {"current_steps": 387800, "total_steps": 761865, "loss": 1.9336, "lr": 4.858527526256436e-07, "epoch": 7.635210962572109, "percentage": 50.9, "elapsed_time": "12:57:54", "remaining_time": "12:30:21", "throughput": 8460.01, "total_tokens": 394868008} {"current_steps": 387900, "total_steps": 761865, "loss": 1.979, "lr": 4.856466558985891e-07, "epoch": 7.637179815321612, "percentage": 50.91, "elapsed_time": "12:58:06", "remaining_time": "12:30:09", "throughput": 8460.08, "total_tokens": 394969544} {"current_steps": 388000, "total_steps": 761865, "loss": 1.9796, "lr": 4.854405616122e-07, "epoch": 7.639148668071115, "percentage": 50.93, "elapsed_time": "12:58:17", "remaining_time": "12:29:56", "throughput": 8460.16, "total_tokens": 395071944} {"current_steps": 388100, "total_steps": 761865, "loss": 1.9725, "lr": 4.852344698015201e-07, "epoch": 7.641117520820618, "percentage": 50.94, "elapsed_time": "12:58:29", "remaining_time": "12:29:44", "throughput": 8460.2, "total_tokens": 395171824} {"current_steps": 388200, "total_steps": 761865, "loss": 1.9663, "lr": 4.850283805015945e-07, "epoch": 7.643086373570121, "percentage": 50.95, "elapsed_time": "12:58:41", "remaining_time": "12:29:31", "throughput": 8460.27, "total_tokens": 395272880} {"current_steps": 388300, "total_steps": 761865, "loss": 1.9934, "lr": 4.848222937474662e-07, "epoch": 7.645055226319624, "percentage": 50.97, "elapsed_time": "12:58:52", "remaining_time": "12:29:19", "throughput": 8460.34, "total_tokens": 395375280} {"current_steps": 388400, "total_steps": 761865, "loss": 1.9712, "lr": 4.846162095741792e-07, "epoch": 7.647024079069126, "percentage": 50.98, "elapsed_time": "12:59:04", "remaining_time": "12:29:07", "throughput": 8460.42, "total_tokens": 395477680} {"current_steps": 388500, "total_steps": 761865, "loss": 1.9636, "lr": 4.844101280167757e-07, "epoch": 7.648992931818629, "percentage": 50.99, "elapsed_time": "12:59:16", "remaining_time": "12:28:54", "throughput": 8460.49, "total_tokens": 395579736} {"current_steps": 388600, "total_steps": 761865, "loss": 1.9908, "lr": 4.842040491102984e-07, "epoch": 7.650961784568132, "percentage": 51.01, "elapsed_time": "12:59:27", "remaining_time": "12:28:42", "throughput": 8460.56, "total_tokens": 395681648} {"current_steps": 388700, "total_steps": 761865, "loss": 2.0163, "lr": 4.839979728897896e-07, "epoch": 7.652930637317635, "percentage": 51.02, "elapsed_time": "12:59:39", "remaining_time": "12:28:29", "throughput": 8460.62, "total_tokens": 395782360} {"current_steps": 388800, "total_steps": 761865, "loss": 1.9773, "lr": 4.837918993902903e-07, "epoch": 7.654899490067137, "percentage": 51.03, "elapsed_time": "12:59:51", "remaining_time": "12:28:17", "throughput": 8460.7, "total_tokens": 395884760} {"current_steps": 388900, "total_steps": 761865, "loss": 2.0128, "lr": 4.83585828646842e-07, "epoch": 7.656868342816641, "percentage": 51.05, "elapsed_time": "13:00:02", "remaining_time": "12:28:04", "throughput": 8460.77, "total_tokens": 395986296} {"current_steps": 389000, "total_steps": 761865, "loss": 2.0028, "lr": 4.833797606944849e-07, "epoch": 7.658837195566144, "percentage": 51.06, "elapsed_time": "13:00:14", "remaining_time": "12:27:52", "throughput": 8460.84, "total_tokens": 396088696} {"current_steps": 389100, "total_steps": 761865, "loss": 2.0206, "lr": 4.831736955682594e-07, "epoch": 7.660806048315647, "percentage": 51.07, "elapsed_time": "13:00:25", "remaining_time": "12:27:39", "throughput": 8460.88, "total_tokens": 396186872} {"current_steps": 389200, "total_steps": 761865, "loss": 1.966, "lr": 4.829676333032052e-07, "epoch": 7.662774901065149, "percentage": 51.09, "elapsed_time": "13:00:37", "remaining_time": "12:27:27", "throughput": 8460.95, "total_tokens": 396288552} {"current_steps": 389300, "total_steps": 761865, "loss": 1.9273, "lr": 4.827615739343611e-07, "epoch": 7.664743753814652, "percentage": 51.1, "elapsed_time": "13:00:49", "remaining_time": "12:27:15", "throughput": 8461.02, "total_tokens": 396390520} {"current_steps": 389400, "total_steps": 761865, "loss": 1.9807, "lr": 4.82555517496766e-07, "epoch": 7.666712606564155, "percentage": 51.11, "elapsed_time": "13:01:00", "remaining_time": "12:27:02", "throughput": 8461.1, "total_tokens": 396492920} {"current_steps": 389500, "total_steps": 761865, "loss": 1.9808, "lr": 4.82349464025458e-07, "epoch": 7.668681459313658, "percentage": 51.12, "elapsed_time": "13:01:12", "remaining_time": "12:26:50", "throughput": 8461.17, "total_tokens": 396594784} {"current_steps": 389600, "total_steps": 761865, "loss": 1.9423, "lr": 4.821434135554749e-07, "epoch": 7.670650312063161, "percentage": 51.14, "elapsed_time": "13:01:23", "remaining_time": "12:26:37", "throughput": 8461.25, "total_tokens": 396696568} {"current_steps": 389700, "total_steps": 761865, "loss": 1.9883, "lr": 4.819373661218535e-07, "epoch": 7.672619164812664, "percentage": 51.15, "elapsed_time": "13:01:35", "remaining_time": "12:26:25", "throughput": 8461.3, "total_tokens": 396797000} {"current_steps": 389800, "total_steps": 761865, "loss": 1.9903, "lr": 4.817313217596309e-07, "epoch": 7.674588017562167, "percentage": 51.16, "elapsed_time": "13:01:47", "remaining_time": "12:26:13", "throughput": 8461.38, "total_tokens": 396899400} {"current_steps": 389900, "total_steps": 761865, "loss": 1.9834, "lr": 4.815252805038427e-07, "epoch": 7.67655687031167, "percentage": 51.18, "elapsed_time": "13:01:58", "remaining_time": "12:26:00", "throughput": 8461.45, "total_tokens": 397001352} {"current_steps": 390000, "total_steps": 761865, "loss": 1.9938, "lr": 4.813192423895249e-07, "epoch": 7.678525723061172, "percentage": 51.19, "elapsed_time": "13:02:10", "remaining_time": "12:25:48", "throughput": 8461.53, "total_tokens": 397103120} {"current_steps": 390100, "total_steps": 761865, "loss": 1.9765, "lr": 4.811132074517123e-07, "epoch": 7.680494575810675, "percentage": 51.2, "elapsed_time": "13:02:22", "remaining_time": "12:25:36", "throughput": 8461.48, "total_tokens": 397203488} {"current_steps": 390200, "total_steps": 761865, "loss": 1.988, "lr": 4.809071757254396e-07, "epoch": 7.682463428560178, "percentage": 51.22, "elapsed_time": "13:02:34", "remaining_time": "12:25:23", "throughput": 8461.56, "total_tokens": 397305888} {"current_steps": 390300, "total_steps": 761865, "loss": 1.9803, "lr": 4.807011472457404e-07, "epoch": 7.684432281309681, "percentage": 51.23, "elapsed_time": "13:02:45", "remaining_time": "12:25:11", "throughput": 8461.61, "total_tokens": 397406536} {"current_steps": 390400, "total_steps": 761865, "loss": 1.9725, "lr": 4.804951220476485e-07, "epoch": 7.686401134059183, "percentage": 51.24, "elapsed_time": "13:02:57", "remaining_time": "12:24:59", "throughput": 8461.68, "total_tokens": 397508936} {"current_steps": 390500, "total_steps": 761865, "loss": 1.9621, "lr": 4.802891001661966e-07, "epoch": 7.688369986808686, "percentage": 51.26, "elapsed_time": "13:03:09", "remaining_time": "12:24:46", "throughput": 8461.76, "total_tokens": 397611336} {"current_steps": 390600, "total_steps": 761865, "loss": 1.9509, "lr": 4.800830816364167e-07, "epoch": 7.69033883955819, "percentage": 51.27, "elapsed_time": "13:03:20", "remaining_time": "12:24:34", "throughput": 8461.83, "total_tokens": 397713048} {"current_steps": 390700, "total_steps": 761865, "loss": 1.9888, "lr": 4.798770664933412e-07, "epoch": 7.6923076923076925, "percentage": 51.28, "elapsed_time": "13:03:32", "remaining_time": "12:24:21", "throughput": 8461.91, "total_tokens": 397815448} {"current_steps": 390800, "total_steps": 761865, "loss": 1.9934, "lr": 4.796710547720004e-07, "epoch": 7.694276545057195, "percentage": 51.3, "elapsed_time": "13:03:44", "remaining_time": "12:24:09", "throughput": 8461.99, "total_tokens": 397917848} {"current_steps": 390900, "total_steps": 761865, "loss": 1.9506, "lr": 4.794650465074256e-07, "epoch": 7.696245397806698, "percentage": 51.31, "elapsed_time": "13:03:55", "remaining_time": "12:23:57", "throughput": 8462.06, "total_tokens": 398019352} {"current_steps": 391000, "total_steps": 761865, "loss": 2.0059, "lr": 4.792590417346462e-07, "epoch": 7.698214250556201, "percentage": 51.32, "elapsed_time": "13:04:07", "remaining_time": "12:23:44", "throughput": 8462.13, "total_tokens": 398121752} {"current_steps": 391100, "total_steps": 761865, "loss": 1.9725, "lr": 4.790530404886921e-07, "epoch": 7.7001831033057035, "percentage": 51.33, "elapsed_time": "13:04:19", "remaining_time": "12:23:32", "throughput": 8462.21, "total_tokens": 398224152} {"current_steps": 391200, "total_steps": 761865, "loss": 1.9833, "lr": 4.788470428045915e-07, "epoch": 7.702151956055206, "percentage": 51.35, "elapsed_time": "13:04:30", "remaining_time": "12:23:19", "throughput": 8462.28, "total_tokens": 398326000} {"current_steps": 391300, "total_steps": 761865, "loss": 2.0046, "lr": 4.786410487173732e-07, "epoch": 7.70412080880471, "percentage": 51.36, "elapsed_time": "13:04:42", "remaining_time": "12:23:07", "throughput": 8462.34, "total_tokens": 398427544} {"current_steps": 391400, "total_steps": 761865, "loss": 2.0173, "lr": 4.78435058262064e-07, "epoch": 7.706089661554213, "percentage": 51.37, "elapsed_time": "13:04:54", "remaining_time": "12:22:55", "throughput": 8462.42, "total_tokens": 398529944} {"current_steps": 391500, "total_steps": 761865, "loss": 1.9428, "lr": 4.782290714736917e-07, "epoch": 7.7080585143037155, "percentage": 51.39, "elapsed_time": "13:05:05", "remaining_time": "12:22:42", "throughput": 8462.49, "total_tokens": 398632344} {"current_steps": 391600, "total_steps": 761865, "loss": 1.9698, "lr": 4.780230883872817e-07, "epoch": 7.710027367053218, "percentage": 51.4, "elapsed_time": "13:05:17", "remaining_time": "12:22:30", "throughput": 8462.57, "total_tokens": 398734648} {"current_steps": 391700, "total_steps": 761865, "loss": 2.0544, "lr": 4.778171090378603e-07, "epoch": 7.711996219802721, "percentage": 51.41, "elapsed_time": "13:05:29", "remaining_time": "12:22:17", "throughput": 8462.64, "total_tokens": 398836128} {"current_steps": 391800, "total_steps": 761865, "loss": 2.0082, "lr": 4.776111334604525e-07, "epoch": 7.713965072552224, "percentage": 51.43, "elapsed_time": "13:05:40", "remaining_time": "12:22:05", "throughput": 8462.7, "total_tokens": 398937160} {"current_steps": 391900, "total_steps": 761865, "loss": 2.0238, "lr": 4.774051616900827e-07, "epoch": 7.7159339253017265, "percentage": 51.44, "elapsed_time": "13:05:52", "remaining_time": "12:21:53", "throughput": 8462.77, "total_tokens": 399039032} {"current_steps": 392000, "total_steps": 761865, "loss": 2.0645, "lr": 4.771991937617745e-07, "epoch": 7.717902778051229, "percentage": 51.45, "elapsed_time": "13:06:03", "remaining_time": "12:21:40", "throughput": 8462.85, "total_tokens": 399141432} {"current_steps": 392100, "total_steps": 761865, "loss": 1.9769, "lr": 4.769932297105511e-07, "epoch": 7.719871630800732, "percentage": 51.47, "elapsed_time": "13:06:15", "remaining_time": "12:21:28", "throughput": 8462.92, "total_tokens": 399243832} {"current_steps": 392200, "total_steps": 761865, "loss": 1.9954, "lr": 4.7678726957143496e-07, "epoch": 7.721840483550235, "percentage": 51.48, "elapsed_time": "13:06:27", "remaining_time": "12:21:16", "throughput": 8462.99, "total_tokens": 399345736} {"current_steps": 392300, "total_steps": 761865, "loss": 1.976, "lr": 4.7658131337944773e-07, "epoch": 7.723809336299738, "percentage": 51.49, "elapsed_time": "13:06:38", "remaining_time": "12:21:03", "throughput": 8463.06, "total_tokens": 399447264} {"current_steps": 392400, "total_steps": 761865, "loss": 1.9823, "lr": 4.763753611696108e-07, "epoch": 7.725778189049241, "percentage": 51.51, "elapsed_time": "13:06:50", "remaining_time": "12:20:51", "throughput": 8463.12, "total_tokens": 399548816} {"current_steps": 392500, "total_steps": 761865, "loss": 2.0116, "lr": 4.761694129769443e-07, "epoch": 7.727747041798744, "percentage": 51.52, "elapsed_time": "13:07:02", "remaining_time": "12:20:38", "throughput": 8463.17, "total_tokens": 399648552} {"current_steps": 392600, "total_steps": 761865, "loss": 1.9611, "lr": 4.7596346883646813e-07, "epoch": 7.729715894548247, "percentage": 51.53, "elapsed_time": "13:07:13", "remaining_time": "12:20:26", "throughput": 8463.23, "total_tokens": 399748816} {"current_steps": 392700, "total_steps": 761865, "loss": 1.9828, "lr": 4.7575752878320144e-07, "epoch": 7.7316847472977495, "percentage": 51.54, "elapsed_time": "13:07:25", "remaining_time": "12:20:13", "throughput": 8463.3, "total_tokens": 399851216} {"current_steps": 392800, "total_steps": 761865, "loss": 2.0269, "lr": 4.7555159285216247e-07, "epoch": 7.733653600047252, "percentage": 51.56, "elapsed_time": "13:07:36", "remaining_time": "12:20:01", "throughput": 8463.35, "total_tokens": 399950960} {"current_steps": 392900, "total_steps": 761865, "loss": 1.9684, "lr": 4.75345661078369e-07, "epoch": 7.735622452796755, "percentage": 51.57, "elapsed_time": "13:07:48", "remaining_time": "12:19:48", "throughput": 8463.43, "total_tokens": 400053360} {"current_steps": 393000, "total_steps": 761865, "loss": 1.9843, "lr": 4.751397334968378e-07, "epoch": 7.737591305546259, "percentage": 51.58, "elapsed_time": "13:08:00", "remaining_time": "12:19:36", "throughput": 8463.49, "total_tokens": 400154744} {"current_steps": 393100, "total_steps": 761865, "loss": 1.9915, "lr": 4.749338101425854e-07, "epoch": 7.739560158295761, "percentage": 51.6, "elapsed_time": "13:08:11", "remaining_time": "12:19:24", "throughput": 8463.56, "total_tokens": 400256528} {"current_steps": 393200, "total_steps": 761865, "loss": 1.9644, "lr": 4.74727891050627e-07, "epoch": 7.741529011045264, "percentage": 51.61, "elapsed_time": "13:08:23", "remaining_time": "12:19:11", "throughput": 8463.63, "total_tokens": 400358928} {"current_steps": 393300, "total_steps": 761865, "loss": 1.9546, "lr": 4.7452197625597766e-07, "epoch": 7.743497863794767, "percentage": 51.62, "elapsed_time": "13:08:35", "remaining_time": "12:18:59", "throughput": 8463.71, "total_tokens": 400461328} {"current_steps": 393400, "total_steps": 761865, "loss": 1.9918, "lr": 4.743160657936513e-07, "epoch": 7.74546671654427, "percentage": 51.64, "elapsed_time": "13:08:46", "remaining_time": "12:18:47", "throughput": 8463.78, "total_tokens": 400563576} {"current_steps": 393500, "total_steps": 761865, "loss": 1.9688, "lr": 4.741101596986614e-07, "epoch": 7.747435569293772, "percentage": 51.65, "elapsed_time": "13:08:58", "remaining_time": "12:18:34", "throughput": 8463.85, "total_tokens": 400665368} {"current_steps": 393600, "total_steps": 761865, "loss": 1.9926, "lr": 4.739042580060204e-07, "epoch": 7.749404422043275, "percentage": 51.66, "elapsed_time": "13:09:10", "remaining_time": "12:18:22", "throughput": 8463.92, "total_tokens": 400767768} {"current_steps": 393700, "total_steps": 761865, "loss": 1.9844, "lr": 4.736983607507401e-07, "epoch": 7.751373274792778, "percentage": 51.68, "elapsed_time": "13:09:21", "remaining_time": "12:18:09", "throughput": 8463.97, "total_tokens": 400867752} {"current_steps": 393800, "total_steps": 761865, "loss": 2.0072, "lr": 4.7349246796783196e-07, "epoch": 7.753342127542281, "percentage": 51.69, "elapsed_time": "13:09:33", "remaining_time": "12:17:57", "throughput": 8464.04, "total_tokens": 400970152} {"current_steps": 393900, "total_steps": 761865, "loss": 1.9447, "lr": 4.7328657969230597e-07, "epoch": 7.755310980291784, "percentage": 51.7, "elapsed_time": "13:09:45", "remaining_time": "12:17:45", "throughput": 8464.12, "total_tokens": 401072552} {"current_steps": 394000, "total_steps": 761865, "loss": 1.9471, "lr": 4.7308069595917183e-07, "epoch": 7.757279833041287, "percentage": 51.72, "elapsed_time": "13:09:56", "remaining_time": "12:17:32", "throughput": 8464.19, "total_tokens": 401174952} {"current_steps": 394100, "total_steps": 761865, "loss": 1.9743, "lr": 4.728748168034382e-07, "epoch": 7.75924868579079, "percentage": 51.73, "elapsed_time": "13:10:08", "remaining_time": "12:17:20", "throughput": 8464.26, "total_tokens": 401276432} {"current_steps": 394200, "total_steps": 761865, "loss": 1.977, "lr": 4.726689422601133e-07, "epoch": 7.761217538540293, "percentage": 51.74, "elapsed_time": "13:10:19", "remaining_time": "12:17:07", "throughput": 8464.32, "total_tokens": 401377968} {"current_steps": 394300, "total_steps": 761865, "loss": 1.9881, "lr": 4.724630723642042e-07, "epoch": 7.763186391289795, "percentage": 51.75, "elapsed_time": "13:10:31", "remaining_time": "12:16:55", "throughput": 8464.39, "total_tokens": 401479664} {"current_steps": 394400, "total_steps": 761865, "loss": 2.0008, "lr": 4.722572071507175e-07, "epoch": 7.765155244039298, "percentage": 51.77, "elapsed_time": "13:10:43", "remaining_time": "12:16:43", "throughput": 8464.45, "total_tokens": 401581496} {"current_steps": 394500, "total_steps": 761865, "loss": 1.9945, "lr": 4.720513466546586e-07, "epoch": 7.767124096788801, "percentage": 51.78, "elapsed_time": "13:10:54", "remaining_time": "12:16:30", "throughput": 8464.52, "total_tokens": 401682520} {"current_steps": 394600, "total_steps": 761865, "loss": 1.9644, "lr": 4.718454909110324e-07, "epoch": 7.769092949538304, "percentage": 51.79, "elapsed_time": "13:11:06", "remaining_time": "12:16:18", "throughput": 8464.58, "total_tokens": 401783360} {"current_steps": 394700, "total_steps": 761865, "loss": 1.9831, "lr": 4.7163963995484316e-07, "epoch": 7.771061802287807, "percentage": 51.81, "elapsed_time": "13:11:18", "remaining_time": "12:16:05", "throughput": 8464.64, "total_tokens": 401884904} {"current_steps": 394800, "total_steps": 761865, "loss": 2.0089, "lr": 4.7143379382109386e-07, "epoch": 7.77303065503731, "percentage": 51.82, "elapsed_time": "13:11:29", "remaining_time": "12:15:53", "throughput": 8464.72, "total_tokens": 401987304} {"current_steps": 394900, "total_steps": 761865, "loss": 1.9891, "lr": 4.712279525447871e-07, "epoch": 7.774999507786813, "percentage": 51.83, "elapsed_time": "13:11:41", "remaining_time": "12:15:41", "throughput": 8464.79, "total_tokens": 402089704} {"current_steps": 395000, "total_steps": 761865, "loss": 2.0138, "lr": 4.710221161609242e-07, "epoch": 7.776968360536316, "percentage": 51.85, "elapsed_time": "13:11:53", "remaining_time": "12:15:28", "throughput": 8464.87, "total_tokens": 402192104} {"current_steps": 395100, "total_steps": 761865, "loss": 1.9889, "lr": 4.7081628470450615e-07, "epoch": 7.778937213285818, "percentage": 51.86, "elapsed_time": "13:12:05", "remaining_time": "12:15:16", "throughput": 8464.83, "total_tokens": 402293080} {"current_steps": 395200, "total_steps": 761865, "loss": 1.9743, "lr": 4.706104582105326e-07, "epoch": 7.780906066035321, "percentage": 51.87, "elapsed_time": "13:12:16", "remaining_time": "12:15:04", "throughput": 8464.9, "total_tokens": 402394952} {"current_steps": 395300, "total_steps": 761865, "loss": 1.958, "lr": 4.704046367140029e-07, "epoch": 7.782874918784824, "percentage": 51.89, "elapsed_time": "13:12:28", "remaining_time": "12:14:52", "throughput": 8464.97, "total_tokens": 402497352} {"current_steps": 395400, "total_steps": 761865, "loss": 1.9683, "lr": 4.701988202499149e-07, "epoch": 7.784843771534327, "percentage": 51.9, "elapsed_time": "13:12:40", "remaining_time": "12:14:39", "throughput": 8465.04, "total_tokens": 402599664} {"current_steps": 395500, "total_steps": 761865, "loss": 1.9328, "lr": 4.6999300885326636e-07, "epoch": 7.786812624283829, "percentage": 51.91, "elapsed_time": "13:12:51", "remaining_time": "12:14:27", "throughput": 8465.11, "total_tokens": 402701568} {"current_steps": 395600, "total_steps": 761865, "loss": 1.9937, "lr": 4.697872025590535e-07, "epoch": 7.788781477033333, "percentage": 51.93, "elapsed_time": "13:13:03", "remaining_time": "12:14:15", "throughput": 8465.17, "total_tokens": 402802392} {"current_steps": 395700, "total_steps": 761865, "loss": 2.0285, "lr": 4.695814014022719e-07, "epoch": 7.790750329782836, "percentage": 51.94, "elapsed_time": "13:13:15", "remaining_time": "12:14:02", "throughput": 8465.24, "total_tokens": 402904168} {"current_steps": 395800, "total_steps": 761865, "loss": 1.9824, "lr": 4.6937560541791666e-07, "epoch": 7.7927191825323385, "percentage": 51.95, "elapsed_time": "13:13:26", "remaining_time": "12:13:50", "throughput": 8465.32, "total_tokens": 403006568} {"current_steps": 395900, "total_steps": 761865, "loss": 1.9791, "lr": 4.6916981464098114e-07, "epoch": 7.794688035281841, "percentage": 51.96, "elapsed_time": "13:13:38", "remaining_time": "12:13:37", "throughput": 8465.39, "total_tokens": 403108968} {"current_steps": 396000, "total_steps": 761865, "loss": 2.0055, "lr": 4.68964029106459e-07, "epoch": 7.796656888031344, "percentage": 51.98, "elapsed_time": "13:13:50", "remaining_time": "12:13:25", "throughput": 8465.46, "total_tokens": 403211368} {"current_steps": 396100, "total_steps": 761865, "loss": 1.9772, "lr": 4.687582488493415e-07, "epoch": 7.798625740780847, "percentage": 51.99, "elapsed_time": "13:14:01", "remaining_time": "12:13:13", "throughput": 8465.53, "total_tokens": 403312368} {"current_steps": 396200, "total_steps": 761865, "loss": 1.9769, "lr": 4.6855247390462073e-07, "epoch": 7.80059459353035, "percentage": 52.0, "elapsed_time": "13:14:13", "remaining_time": "12:13:00", "throughput": 8465.6, "total_tokens": 403414768} {"current_steps": 396300, "total_steps": 761865, "loss": 1.9937, "lr": 4.683467043072861e-07, "epoch": 7.802563446279853, "percentage": 52.02, "elapsed_time": "13:14:25", "remaining_time": "12:12:48", "throughput": 8465.67, "total_tokens": 403516520} {"current_steps": 396400, "total_steps": 761865, "loss": 2.0014, "lr": 4.681409400923278e-07, "epoch": 7.804532299029356, "percentage": 52.03, "elapsed_time": "13:14:36", "remaining_time": "12:12:35", "throughput": 8465.73, "total_tokens": 403617400} {"current_steps": 396500, "total_steps": 761865, "loss": 1.9794, "lr": 4.6793518129473357e-07, "epoch": 7.806501151778859, "percentage": 52.04, "elapsed_time": "13:14:48", "remaining_time": "12:12:23", "throughput": 8465.8, "total_tokens": 403719576} {"current_steps": 396600, "total_steps": 761865, "loss": 1.9729, "lr": 4.6772942794949144e-07, "epoch": 7.8084700045283615, "percentage": 52.06, "elapsed_time": "13:14:59", "remaining_time": "12:12:11", "throughput": 8465.86, "total_tokens": 403821376} {"current_steps": 396700, "total_steps": 761865, "loss": 1.9552, "lr": 4.6752368009158803e-07, "epoch": 7.810438857277864, "percentage": 52.07, "elapsed_time": "13:15:11", "remaining_time": "12:11:58", "throughput": 8465.93, "total_tokens": 403922984} {"current_steps": 396800, "total_steps": 761865, "loss": 1.9948, "lr": 4.673179377560088e-07, "epoch": 7.812407710027367, "percentage": 52.08, "elapsed_time": "13:15:23", "remaining_time": "12:11:46", "throughput": 8466.0, "total_tokens": 404024592} {"current_steps": 396900, "total_steps": 761865, "loss": 2.0161, "lr": 4.671122009777387e-07, "epoch": 7.81437656277687, "percentage": 52.1, "elapsed_time": "13:15:34", "remaining_time": "12:11:34", "throughput": 8466.06, "total_tokens": 404126120} {"current_steps": 397000, "total_steps": 761865, "loss": 1.9808, "lr": 4.669064697917613e-07, "epoch": 7.8163454155263725, "percentage": 52.11, "elapsed_time": "13:15:46", "remaining_time": "12:11:21", "throughput": 8466.14, "total_tokens": 404228520} {"current_steps": 397100, "total_steps": 761865, "loss": 1.9991, "lr": 4.667007442330597e-07, "epoch": 7.818314268275875, "percentage": 52.12, "elapsed_time": "13:15:58", "remaining_time": "12:11:09", "throughput": 8466.21, "total_tokens": 404330920} {"current_steps": 397200, "total_steps": 761865, "loss": 2.018, "lr": 4.6649502433661566e-07, "epoch": 7.820283121025378, "percentage": 52.14, "elapsed_time": "13:16:09", "remaining_time": "12:10:56", "throughput": 8466.27, "total_tokens": 404432512} {"current_steps": 397300, "total_steps": 761865, "loss": 1.9811, "lr": 4.6628931013741015e-07, "epoch": 7.822251973774882, "percentage": 52.15, "elapsed_time": "13:16:21", "remaining_time": "12:10:44", "throughput": 8466.35, "total_tokens": 404534912} {"current_steps": 397400, "total_steps": 761865, "loss": 1.9727, "lr": 4.66083601670423e-07, "epoch": 7.824220826524384, "percentage": 52.16, "elapsed_time": "13:16:33", "remaining_time": "12:10:32", "throughput": 8466.42, "total_tokens": 404636808} {"current_steps": 397500, "total_steps": 761865, "loss": 1.9598, "lr": 4.658778989706335e-07, "epoch": 7.826189679273887, "percentage": 52.17, "elapsed_time": "13:16:44", "remaining_time": "12:10:19", "throughput": 8466.49, "total_tokens": 404739208} {"current_steps": 397600, "total_steps": 761865, "loss": 1.9881, "lr": 4.6567220207301933e-07, "epoch": 7.82815853202339, "percentage": 52.19, "elapsed_time": "13:16:56", "remaining_time": "12:10:07", "throughput": 8466.56, "total_tokens": 404841608} {"current_steps": 397700, "total_steps": 761865, "loss": 1.9751, "lr": 4.654665110125577e-07, "epoch": 7.830127384772893, "percentage": 52.2, "elapsed_time": "13:17:08", "remaining_time": "12:09:55", "throughput": 8466.62, "total_tokens": 404942592} {"current_steps": 397800, "total_steps": 761865, "loss": 1.9832, "lr": 4.652608258242247e-07, "epoch": 7.8320962375223955, "percentage": 52.21, "elapsed_time": "13:17:19", "remaining_time": "12:09:42", "throughput": 8466.69, "total_tokens": 405044224} {"current_steps": 397900, "total_steps": 761865, "loss": 1.9799, "lr": 4.6505514654299516e-07, "epoch": 7.834065090271898, "percentage": 52.23, "elapsed_time": "13:17:31", "remaining_time": "12:09:30", "throughput": 8466.76, "total_tokens": 405146624} {"current_steps": 398000, "total_steps": 761865, "loss": 2.0608, "lr": 4.648494732038433e-07, "epoch": 7.836033943021402, "percentage": 52.24, "elapsed_time": "13:17:43", "remaining_time": "12:09:18", "throughput": 8466.82, "total_tokens": 405248096} {"current_steps": 398100, "total_steps": 761865, "loss": 2.0156, "lr": 4.646438058417419e-07, "epoch": 7.838002795770905, "percentage": 52.25, "elapsed_time": "13:17:54", "remaining_time": "12:09:05", "throughput": 8466.89, "total_tokens": 405350312} {"current_steps": 398200, "total_steps": 761865, "loss": 1.9995, "lr": 4.644381444916633e-07, "epoch": 7.839971648520407, "percentage": 52.27, "elapsed_time": "13:18:06", "remaining_time": "12:08:53", "throughput": 8466.96, "total_tokens": 405451952} {"current_steps": 398300, "total_steps": 761865, "loss": 1.9949, "lr": 4.642324891885781e-07, "epoch": 7.84194050126991, "percentage": 52.28, "elapsed_time": "13:18:18", "remaining_time": "12:08:40", "throughput": 8467.03, "total_tokens": 405553912} {"current_steps": 398400, "total_steps": 761865, "loss": 1.9698, "lr": 4.640268399674566e-07, "epoch": 7.843909354019413, "percentage": 52.29, "elapsed_time": "13:18:29", "remaining_time": "12:08:28", "throughput": 8467.1, "total_tokens": 405656312} {"current_steps": 398500, "total_steps": 761865, "loss": 1.9669, "lr": 4.638211968632674e-07, "epoch": 7.845878206768916, "percentage": 52.31, "elapsed_time": "13:18:41", "remaining_time": "12:08:16", "throughput": 8467.18, "total_tokens": 405758712} {"current_steps": 398600, "total_steps": 761865, "loss": 1.961, "lr": 4.6361555991097875e-07, "epoch": 7.847847059518418, "percentage": 52.32, "elapsed_time": "13:18:53", "remaining_time": "12:08:03", "throughput": 8467.25, "total_tokens": 405861112} {"current_steps": 398700, "total_steps": 761865, "loss": 1.9415, "lr": 4.6340992914555705e-07, "epoch": 7.849815912267921, "percentage": 52.33, "elapsed_time": "13:19:04", "remaining_time": "12:07:51", "throughput": 8467.33, "total_tokens": 405963512} {"current_steps": 398800, "total_steps": 761865, "loss": 1.9445, "lr": 4.632043046019681e-07, "epoch": 7.851784765017424, "percentage": 52.35, "elapsed_time": "13:19:16", "remaining_time": "12:07:39", "throughput": 8467.41, "total_tokens": 406065912} {"current_steps": 398900, "total_steps": 761865, "loss": 1.9951, "lr": 4.629986863151773e-07, "epoch": 7.853753617766928, "percentage": 52.36, "elapsed_time": "13:19:27", "remaining_time": "12:07:26", "throughput": 8467.47, "total_tokens": 406167552} {"current_steps": 399000, "total_steps": 761865, "loss": 2.0278, "lr": 4.6279307432014734e-07, "epoch": 7.85572247051643, "percentage": 52.37, "elapsed_time": "13:19:39", "remaining_time": "12:07:14", "throughput": 8467.54, "total_tokens": 406269176} {"current_steps": 399100, "total_steps": 761865, "loss": 1.9805, "lr": 4.625874686518417e-07, "epoch": 7.857691323265933, "percentage": 52.38, "elapsed_time": "13:19:51", "remaining_time": "12:07:02", "throughput": 8467.61, "total_tokens": 406371056} {"current_steps": 399200, "total_steps": 761865, "loss": 1.9664, "lr": 4.6238186934522113e-07, "epoch": 7.859660176015436, "percentage": 52.4, "elapsed_time": "13:20:02", "remaining_time": "12:06:49", "throughput": 8467.67, "total_tokens": 406472104} {"current_steps": 399300, "total_steps": 761865, "loss": 1.9796, "lr": 4.6217627643524663e-07, "epoch": 7.861629028764939, "percentage": 52.41, "elapsed_time": "13:20:14", "remaining_time": "12:06:37", "throughput": 8467.73, "total_tokens": 406573320} {"current_steps": 399400, "total_steps": 761865, "loss": 1.9649, "lr": 4.6197068995687704e-07, "epoch": 7.863597881514441, "percentage": 52.42, "elapsed_time": "13:20:26", "remaining_time": "12:06:24", "throughput": 8467.79, "total_tokens": 406674712} {"current_steps": 399500, "total_steps": 761865, "loss": 1.9471, "lr": 4.617651099450712e-07, "epoch": 7.865566734263944, "percentage": 52.44, "elapsed_time": "13:20:37", "remaining_time": "12:06:12", "throughput": 8467.86, "total_tokens": 406777112} {"current_steps": 399600, "total_steps": 761865, "loss": 2.0067, "lr": 4.6155953643478563e-07, "epoch": 7.867535587013447, "percentage": 52.45, "elapsed_time": "13:20:49", "remaining_time": "12:06:00", "throughput": 8467.93, "total_tokens": 406879512} {"current_steps": 399700, "total_steps": 761865, "loss": 1.9832, "lr": 4.613539694609767e-07, "epoch": 7.8695044397629506, "percentage": 52.46, "elapsed_time": "13:21:01", "remaining_time": "12:05:47", "throughput": 8468.0, "total_tokens": 406981272} {"current_steps": 399800, "total_steps": 761865, "loss": 1.9983, "lr": 4.611484090585994e-07, "epoch": 7.871473292512453, "percentage": 52.48, "elapsed_time": "13:21:12", "remaining_time": "12:05:35", "throughput": 8468.07, "total_tokens": 407082968} {"current_steps": 399900, "total_steps": 761865, "loss": 1.9626, "lr": 4.6094285526260745e-07, "epoch": 7.873442145261956, "percentage": 52.49, "elapsed_time": "13:21:24", "remaining_time": "12:05:22", "throughput": 8468.14, "total_tokens": 407184656} {"current_steps": 400000, "total_steps": 761865, "loss": 1.9699, "lr": 4.6073730810795357e-07, "epoch": 7.875410998011459, "percentage": 52.5, "elapsed_time": "13:21:36", "remaining_time": "12:05:10", "throughput": 8468.21, "total_tokens": 407286960} {"current_steps": 400100, "total_steps": 761865, "loss": 1.9637, "lr": 4.605317676295892e-07, "epoch": 7.877379850760962, "percentage": 52.52, "elapsed_time": "13:21:48", "remaining_time": "12:04:58", "throughput": 8468.18, "total_tokens": 407389360} {"current_steps": 400200, "total_steps": 761865, "loss": 2.0162, "lr": 4.60326233862465e-07, "epoch": 7.879348703510464, "percentage": 52.53, "elapsed_time": "13:21:59", "remaining_time": "12:04:46", "throughput": 8468.24, "total_tokens": 407490992} {"current_steps": 400300, "total_steps": 761865, "loss": 1.9887, "lr": 4.601207068415299e-07, "epoch": 7.881317556259967, "percentage": 52.54, "elapsed_time": "13:22:11", "remaining_time": "12:04:34", "throughput": 8468.3, "total_tokens": 407592552} {"current_steps": 400400, "total_steps": 761865, "loss": 1.9524, "lr": 4.5991518660173243e-07, "epoch": 7.88328640900947, "percentage": 52.56, "elapsed_time": "13:22:23", "remaining_time": "12:04:21", "throughput": 8468.37, "total_tokens": 407694568} {"current_steps": 400500, "total_steps": 761865, "loss": 1.9761, "lr": 4.597096731780193e-07, "epoch": 7.885255261758973, "percentage": 52.57, "elapsed_time": "13:22:34", "remaining_time": "12:04:09", "throughput": 8468.44, "total_tokens": 407796968} {"current_steps": 400600, "total_steps": 761865, "loss": 1.93, "lr": 4.5950416660533647e-07, "epoch": 7.887224114508476, "percentage": 52.58, "elapsed_time": "13:22:46", "remaining_time": "12:03:57", "throughput": 8468.52, "total_tokens": 407899368} {"current_steps": 400700, "total_steps": 761865, "loss": 2.0151, "lr": 4.5929866691862843e-07, "epoch": 7.889192967257979, "percentage": 52.59, "elapsed_time": "13:22:58", "remaining_time": "12:03:44", "throughput": 8468.58, "total_tokens": 408001720} {"current_steps": 400800, "total_steps": 761865, "loss": 2.0049, "lr": 4.590931741528389e-07, "epoch": 7.891161820007482, "percentage": 52.61, "elapsed_time": "13:23:09", "remaining_time": "12:03:32", "throughput": 8468.64, "total_tokens": 408102688} {"current_steps": 400900, "total_steps": 761865, "loss": 2.0066, "lr": 4.588876883429101e-07, "epoch": 7.8931306727569845, "percentage": 52.62, "elapsed_time": "13:23:21", "remaining_time": "12:03:19", "throughput": 8468.7, "total_tokens": 408203800} {"current_steps": 401000, "total_steps": 761865, "loss": 1.9598, "lr": 4.58682209523783e-07, "epoch": 7.895099525506487, "percentage": 52.63, "elapsed_time": "13:23:33", "remaining_time": "12:03:07", "throughput": 8468.77, "total_tokens": 408306200} {"current_steps": 401100, "total_steps": 761865, "loss": 1.976, "lr": 4.5847673773039787e-07, "epoch": 7.89706837825599, "percentage": 52.65, "elapsed_time": "13:23:44", "remaining_time": "12:02:55", "throughput": 8468.84, "total_tokens": 408407960} {"current_steps": 401200, "total_steps": 761865, "loss": 2.0141, "lr": 4.5827127299769316e-07, "epoch": 7.899037231005493, "percentage": 52.66, "elapsed_time": "13:23:56", "remaining_time": "12:02:42", "throughput": 8468.91, "total_tokens": 408510272} {"current_steps": 401300, "total_steps": 761865, "loss": 1.9648, "lr": 4.580658153606066e-07, "epoch": 7.901006083754996, "percentage": 52.67, "elapsed_time": "13:24:08", "remaining_time": "12:02:30", "throughput": 8468.98, "total_tokens": 408612672} {"current_steps": 401400, "total_steps": 761865, "loss": 1.918, "lr": 4.5786036485407433e-07, "epoch": 7.902974936504499, "percentage": 52.69, "elapsed_time": "13:24:19", "remaining_time": "12:02:18", "throughput": 8469.05, "total_tokens": 408715072} {"current_steps": 401500, "total_steps": 761865, "loss": 1.95, "lr": 4.5765492151303164e-07, "epoch": 7.904943789254002, "percentage": 52.7, "elapsed_time": "13:24:31", "remaining_time": "12:02:05", "throughput": 8469.12, "total_tokens": 408816776} {"current_steps": 401600, "total_steps": 761865, "loss": 2.0605, "lr": 4.574494853724123e-07, "epoch": 7.906912642003505, "percentage": 52.71, "elapsed_time": "13:24:43", "remaining_time": "12:01:53", "throughput": 8469.18, "total_tokens": 408917632} {"current_steps": 401700, "total_steps": 761865, "loss": 1.9802, "lr": 4.572440564671491e-07, "epoch": 7.9088814947530075, "percentage": 52.73, "elapsed_time": "13:24:54", "remaining_time": "12:01:41", "throughput": 8469.24, "total_tokens": 409019168} {"current_steps": 401800, "total_steps": 761865, "loss": 1.9523, "lr": 4.5703863483217376e-07, "epoch": 7.91085034750251, "percentage": 52.74, "elapsed_time": "13:25:06", "remaining_time": "12:01:28", "throughput": 8469.31, "total_tokens": 409121568} {"current_steps": 401900, "total_steps": 761865, "loss": 1.9634, "lr": 4.5683322050241577e-07, "epoch": 7.912819200252013, "percentage": 52.75, "elapsed_time": "13:25:17", "remaining_time": "12:01:16", "throughput": 8469.38, "total_tokens": 409223392} {"current_steps": 402000, "total_steps": 761865, "loss": 1.971, "lr": 4.566278135128049e-07, "epoch": 7.914788053001516, "percentage": 52.77, "elapsed_time": "13:25:29", "remaining_time": "12:01:04", "throughput": 8469.45, "total_tokens": 409325792} {"current_steps": 402100, "total_steps": 761865, "loss": 1.9921, "lr": 4.5642241389826835e-07, "epoch": 7.9167569057510185, "percentage": 52.78, "elapsed_time": "13:25:41", "remaining_time": "12:00:51", "throughput": 8469.51, "total_tokens": 409426512} {"current_steps": 402200, "total_steps": 761865, "loss": 1.9475, "lr": 4.562170216937329e-07, "epoch": 7.918725758500521, "percentage": 52.79, "elapsed_time": "13:25:52", "remaining_time": "12:00:39", "throughput": 8469.58, "total_tokens": 409528912} {"current_steps": 402300, "total_steps": 761865, "loss": 1.9598, "lr": 4.560116369341235e-07, "epoch": 7.920694611250025, "percentage": 52.8, "elapsed_time": "13:26:04", "remaining_time": "12:00:26", "throughput": 8469.64, "total_tokens": 409630464} {"current_steps": 402400, "total_steps": 761865, "loss": 2.0094, "lr": 4.558062596543644e-07, "epoch": 7.922663463999528, "percentage": 52.82, "elapsed_time": "13:26:16", "remaining_time": "12:00:14", "throughput": 8469.7, "total_tokens": 409731408} {"current_steps": 402500, "total_steps": 761865, "loss": 1.9937, "lr": 4.556008898893779e-07, "epoch": 7.9246323167490305, "percentage": 52.83, "elapsed_time": "13:26:27", "remaining_time": "12:00:02", "throughput": 8469.77, "total_tokens": 409833592} {"current_steps": 402600, "total_steps": 761865, "loss": 2.0166, "lr": 4.5539552767408575e-07, "epoch": 7.926601169498533, "percentage": 52.84, "elapsed_time": "13:26:39", "remaining_time": "11:59:49", "throughput": 8469.84, "total_tokens": 409935264} {"current_steps": 402700, "total_steps": 761865, "loss": 2.023, "lr": 4.5519017304340777e-07, "epoch": 7.928570022248036, "percentage": 52.86, "elapsed_time": "13:26:51", "remaining_time": "11:59:37", "throughput": 8469.89, "total_tokens": 410036296} {"current_steps": 402800, "total_steps": 761865, "loss": 1.9832, "lr": 4.5498482603226295e-07, "epoch": 7.930538874997539, "percentage": 52.87, "elapsed_time": "13:27:02", "remaining_time": "11:59:25", "throughput": 8469.96, "total_tokens": 410138696} {"current_steps": 402900, "total_steps": 761865, "loss": 2.0532, "lr": 4.5477948667556885e-07, "epoch": 7.9325077277470415, "percentage": 52.88, "elapsed_time": "13:27:14", "remaining_time": "11:59:12", "throughput": 8470.01, "total_tokens": 410238312} {"current_steps": 403000, "total_steps": 761865, "loss": 2.0072, "lr": 4.545741550082416e-07, "epoch": 7.934476580496545, "percentage": 52.9, "elapsed_time": "13:27:25", "remaining_time": "11:59:00", "throughput": 8470.08, "total_tokens": 410340712} {"current_steps": 403100, "total_steps": 761865, "loss": 1.9968, "lr": 4.543688310651962e-07, "epoch": 7.936445433246048, "percentage": 52.91, "elapsed_time": "13:27:37", "remaining_time": "11:58:47", "throughput": 8470.15, "total_tokens": 410443112} {"current_steps": 403200, "total_steps": 761865, "loss": 1.9661, "lr": 4.541635148813461e-07, "epoch": 7.938414285995551, "percentage": 52.92, "elapsed_time": "13:27:49", "remaining_time": "11:58:35", "throughput": 8470.18, "total_tokens": 410541816} {"current_steps": 403300, "total_steps": 761865, "loss": 1.9378, "lr": 4.539582064916038e-07, "epoch": 7.940383138745053, "percentage": 52.94, "elapsed_time": "13:28:00", "remaining_time": "11:58:23", "throughput": 8470.25, "total_tokens": 410643456} {"current_steps": 403400, "total_steps": 761865, "loss": 2.0237, "lr": 4.537529059308801e-07, "epoch": 7.942351991494556, "percentage": 52.95, "elapsed_time": "13:28:12", "remaining_time": "11:58:10", "throughput": 8470.3, "total_tokens": 410744504} {"current_steps": 403500, "total_steps": 761865, "loss": 1.9494, "lr": 4.5354761323408476e-07, "epoch": 7.944320844244059, "percentage": 52.96, "elapsed_time": "13:28:23", "remaining_time": "11:57:58", "throughput": 8470.37, "total_tokens": 410846904} {"current_steps": 403600, "total_steps": 761865, "loss": 1.9988, "lr": 4.5334232843612587e-07, "epoch": 7.946289696993562, "percentage": 52.98, "elapsed_time": "13:28:35", "remaining_time": "11:57:46", "throughput": 8470.45, "total_tokens": 410949304} {"current_steps": 403700, "total_steps": 761865, "loss": 2.0084, "lr": 4.531370515719106e-07, "epoch": 7.9482585497430644, "percentage": 52.99, "elapsed_time": "13:28:47", "remaining_time": "11:57:33", "throughput": 8470.51, "total_tokens": 411051272} {"current_steps": 403800, "total_steps": 761865, "loss": 1.9817, "lr": 4.5293178267634435e-07, "epoch": 7.950227402492567, "percentage": 53.0, "elapsed_time": "13:28:58", "remaining_time": "11:57:21", "throughput": 8470.58, "total_tokens": 411152936} {"current_steps": 403900, "total_steps": 761865, "loss": 2.0533, "lr": 4.5272652178433137e-07, "epoch": 7.95219625524207, "percentage": 53.01, "elapsed_time": "13:29:10", "remaining_time": "11:57:08", "throughput": 8470.62, "total_tokens": 411252824} {"current_steps": 404000, "total_steps": 761865, "loss": 1.9447, "lr": 4.5252126893077494e-07, "epoch": 7.954165107991574, "percentage": 53.03, "elapsed_time": "13:29:22", "remaining_time": "11:56:56", "throughput": 8470.68, "total_tokens": 411354408} {"current_steps": 404100, "total_steps": 761865, "loss": 1.9597, "lr": 4.52316024150576e-07, "epoch": 7.956133960741076, "percentage": 53.04, "elapsed_time": "13:29:33", "remaining_time": "11:56:44", "throughput": 8470.75, "total_tokens": 411456808} {"current_steps": 404200, "total_steps": 761865, "loss": 2.0305, "lr": 4.521107874786352e-07, "epoch": 7.958102813490579, "percentage": 53.05, "elapsed_time": "13:29:45", "remaining_time": "11:56:31", "throughput": 8470.81, "total_tokens": 411557928} {"current_steps": 404300, "total_steps": 761865, "loss": 2.0123, "lr": 4.5190555894985084e-07, "epoch": 7.960071666240082, "percentage": 53.07, "elapsed_time": "13:29:57", "remaining_time": "11:56:19", "throughput": 8470.88, "total_tokens": 411660328} {"current_steps": 404400, "total_steps": 761865, "loss": 1.9605, "lr": 4.517003385991208e-07, "epoch": 7.962040518989585, "percentage": 53.08, "elapsed_time": "13:30:08", "remaining_time": "11:56:07", "throughput": 8470.95, "total_tokens": 411762184} {"current_steps": 404500, "total_steps": 761865, "loss": 2.0205, "lr": 4.5149512646134045e-07, "epoch": 7.964009371739087, "percentage": 53.09, "elapsed_time": "13:30:20", "remaining_time": "11:55:54", "throughput": 8471.01, "total_tokens": 411863848} {"current_steps": 404600, "total_steps": 761865, "loss": 2.0331, "lr": 4.5128992257140514e-07, "epoch": 7.96597822448859, "percentage": 53.11, "elapsed_time": "13:30:32", "remaining_time": "11:55:42", "throughput": 8471.08, "total_tokens": 411965808} {"current_steps": 404700, "total_steps": 761865, "loss": 2.029, "lr": 4.510847269642073e-07, "epoch": 7.967947077238094, "percentage": 53.12, "elapsed_time": "13:30:43", "remaining_time": "11:55:30", "throughput": 8471.15, "total_tokens": 412068208} {"current_steps": 404800, "total_steps": 761865, "loss": 2.0108, "lr": 4.508795396746392e-07, "epoch": 7.969915929987597, "percentage": 53.13, "elapsed_time": "13:30:55", "remaining_time": "11:55:17", "throughput": 8471.22, "total_tokens": 412169984} {"current_steps": 404900, "total_steps": 761865, "loss": 1.9365, "lr": 4.5067436073759114e-07, "epoch": 7.971884782737099, "percentage": 53.15, "elapsed_time": "13:31:07", "remaining_time": "11:55:05", "throughput": 8471.29, "total_tokens": 412272384} {"current_steps": 405000, "total_steps": 761865, "loss": 1.999, "lr": 4.504691901879519e-07, "epoch": 7.973853635486602, "percentage": 53.16, "elapsed_time": "13:31:18", "remaining_time": "11:54:53", "throughput": 8471.36, "total_tokens": 412374352} {"current_steps": 405100, "total_steps": 761865, "loss": 1.9979, "lr": 4.5026402806060924e-07, "epoch": 7.975822488236105, "percentage": 53.17, "elapsed_time": "13:31:30", "remaining_time": "11:54:41", "throughput": 8471.32, "total_tokens": 412475384} {"current_steps": 405200, "total_steps": 761865, "loss": 2.0108, "lr": 4.5005887439044904e-07, "epoch": 7.977791340985608, "percentage": 53.19, "elapsed_time": "13:31:42", "remaining_time": "11:54:28", "throughput": 8471.4, "total_tokens": 412577784} {"current_steps": 405300, "total_steps": 761865, "loss": 1.9855, "lr": 4.498537292123561e-07, "epoch": 7.97976019373511, "percentage": 53.2, "elapsed_time": "13:31:54", "remaining_time": "11:54:16", "throughput": 8471.45, "total_tokens": 412678760} {"current_steps": 405400, "total_steps": 761865, "loss": 2.001, "lr": 4.4964859256121347e-07, "epoch": 7.981729046484613, "percentage": 53.21, "elapsed_time": "13:32:05", "remaining_time": "11:54:04", "throughput": 8471.52, "total_tokens": 412781160} {"current_steps": 405500, "total_steps": 761865, "loss": 1.9783, "lr": 4.4944346447190307e-07, "epoch": 7.983697899234116, "percentage": 53.22, "elapsed_time": "13:32:17", "remaining_time": "11:53:51", "throughput": 8471.6, "total_tokens": 412883560} {"current_steps": 405600, "total_steps": 761865, "loss": 1.979, "lr": 4.49238344979305e-07, "epoch": 7.9856667519836195, "percentage": 53.24, "elapsed_time": "13:32:29", "remaining_time": "11:53:39", "throughput": 8471.66, "total_tokens": 412985912} {"current_steps": 405700, "total_steps": 761865, "loss": 1.9656, "lr": 4.4903323411829834e-07, "epoch": 7.987635604733122, "percentage": 53.25, "elapsed_time": "13:32:40", "remaining_time": "11:53:27", "throughput": 8471.73, "total_tokens": 413088264} {"current_steps": 405800, "total_steps": 761865, "loss": 1.9573, "lr": 4.4882813192376024e-07, "epoch": 7.989604457482625, "percentage": 53.26, "elapsed_time": "13:32:52", "remaining_time": "11:53:14", "throughput": 8471.8, "total_tokens": 413190080} {"current_steps": 405900, "total_steps": 761865, "loss": 1.9908, "lr": 4.486230384305667e-07, "epoch": 7.991573310232128, "percentage": 53.28, "elapsed_time": "13:33:04", "remaining_time": "11:53:02", "throughput": 8471.86, "total_tokens": 413291752} {"current_steps": 406000, "total_steps": 761865, "loss": 1.976, "lr": 4.4841795367359223e-07, "epoch": 7.993542162981631, "percentage": 53.29, "elapsed_time": "13:33:15", "remaining_time": "11:52:50", "throughput": 8471.93, "total_tokens": 413393568} {"current_steps": 406100, "total_steps": 761865, "loss": 1.9935, "lr": 4.4821287768770967e-07, "epoch": 7.995511015731133, "percentage": 53.3, "elapsed_time": "13:33:27", "remaining_time": "11:52:37", "throughput": 8472.0, "total_tokens": 413495424} {"current_steps": 406200, "total_steps": 761865, "loss": 1.9843, "lr": 4.480078105077905e-07, "epoch": 7.997479868480636, "percentage": 53.32, "elapsed_time": "13:33:39", "remaining_time": "11:52:25", "throughput": 8472.07, "total_tokens": 413597824} {"current_steps": 406300, "total_steps": 761865, "loss": 2.0093, "lr": 4.478027521687045e-07, "epoch": 7.999448721230139, "percentage": 53.33, "elapsed_time": "13:33:50", "remaining_time": "11:52:13", "throughput": 8472.14, "total_tokens": 413700224} {"current_steps": 406400, "total_steps": 761865, "loss": 2.0736, "lr": 4.475977027053204e-07, "epoch": 8.001417573979642, "percentage": 53.34, "elapsed_time": "13:34:02", "remaining_time": "11:52:00", "throughput": 8472.21, "total_tokens": 413802624} {"current_steps": 406500, "total_steps": 761865, "loss": 1.9937, "lr": 4.473926621525048e-07, "epoch": 8.003386426729145, "percentage": 53.36, "elapsed_time": "13:34:13", "remaining_time": "11:51:48", "throughput": 8472.28, "total_tokens": 413904352} {"current_steps": 406600, "total_steps": 761865, "loss": 1.9593, "lr": 4.471876305451234e-07, "epoch": 8.005355279478648, "percentage": 53.37, "elapsed_time": "13:34:25", "remaining_time": "11:51:36", "throughput": 8472.34, "total_tokens": 414006752} {"current_steps": 406700, "total_steps": 761865, "loss": 1.9714, "lr": 4.4698260791804e-07, "epoch": 8.00732413222815, "percentage": 53.38, "elapsed_time": "13:34:37", "remaining_time": "11:51:23", "throughput": 8472.4, "total_tokens": 414108384} {"current_steps": 406800, "total_steps": 761865, "loss": 2.0084, "lr": 4.4677759430611674e-07, "epoch": 8.009292984977654, "percentage": 53.4, "elapsed_time": "13:34:48", "remaining_time": "11:51:11", "throughput": 8472.47, "total_tokens": 414210496} {"current_steps": 406900, "total_steps": 761865, "loss": 1.9955, "lr": 4.46572589744215e-07, "epoch": 8.011261837727156, "percentage": 53.41, "elapsed_time": "13:35:00", "remaining_time": "11:50:59", "throughput": 8472.54, "total_tokens": 414312808} {"current_steps": 407000, "total_steps": 761865, "loss": 1.954, "lr": 4.4636759426719347e-07, "epoch": 8.013230690476659, "percentage": 53.42, "elapsed_time": "13:35:12", "remaining_time": "11:50:46", "throughput": 8472.6, "total_tokens": 414414488} {"current_steps": 407100, "total_steps": 761865, "loss": 1.9182, "lr": 4.461626079099104e-07, "epoch": 8.015199543226162, "percentage": 53.43, "elapsed_time": "13:35:23", "remaining_time": "11:50:34", "throughput": 8472.67, "total_tokens": 414516888} {"current_steps": 407200, "total_steps": 761865, "loss": 1.9731, "lr": 4.459576307072215e-07, "epoch": 8.017168395975665, "percentage": 53.45, "elapsed_time": "13:35:35", "remaining_time": "11:50:22", "throughput": 8472.73, "total_tokens": 414617696} {"current_steps": 407300, "total_steps": 761865, "loss": 1.9797, "lr": 4.4575266269398203e-07, "epoch": 8.019137248725167, "percentage": 53.46, "elapsed_time": "13:35:47", "remaining_time": "11:50:09", "throughput": 8472.79, "total_tokens": 414719648} {"current_steps": 407400, "total_steps": 761865, "loss": 1.971, "lr": 4.4554770390504443e-07, "epoch": 8.02110610147467, "percentage": 53.47, "elapsed_time": "13:35:58", "remaining_time": "11:49:57", "throughput": 8472.86, "total_tokens": 414821432} {"current_steps": 407500, "total_steps": 761865, "loss": 2.0352, "lr": 4.453427543752608e-07, "epoch": 8.023074954224173, "percentage": 53.49, "elapsed_time": "13:36:10", "remaining_time": "11:49:45", "throughput": 8472.92, "total_tokens": 414922488} {"current_steps": 407600, "total_steps": 761865, "loss": 1.9791, "lr": 4.451378141394805e-07, "epoch": 8.025043806973676, "percentage": 53.5, "elapsed_time": "13:36:22", "remaining_time": "11:49:32", "throughput": 8472.99, "total_tokens": 415024888} {"current_steps": 407700, "total_steps": 761865, "loss": 1.9586, "lr": 4.449328832325524e-07, "epoch": 8.02701265972318, "percentage": 53.51, "elapsed_time": "13:36:33", "remaining_time": "11:49:20", "throughput": 8473.05, "total_tokens": 415126456} {"current_steps": 407800, "total_steps": 761865, "loss": 1.9698, "lr": 4.447279616893228e-07, "epoch": 8.028981512472683, "percentage": 53.53, "elapsed_time": "13:36:45", "remaining_time": "11:49:08", "throughput": 8473.12, "total_tokens": 415228856} {"current_steps": 407900, "total_steps": 761865, "loss": 2.0053, "lr": 4.445230495446372e-07, "epoch": 8.030950365222186, "percentage": 53.54, "elapsed_time": "13:36:57", "remaining_time": "11:48:55", "throughput": 8473.19, "total_tokens": 415331256} {"current_steps": 408000, "total_steps": 761865, "loss": 2.045, "lr": 4.443181468333392e-07, "epoch": 8.032919217971688, "percentage": 53.55, "elapsed_time": "13:37:08", "remaining_time": "11:48:43", "throughput": 8473.24, "total_tokens": 415431368} {"current_steps": 408100, "total_steps": 761865, "loss": 1.9582, "lr": 4.441132535902707e-07, "epoch": 8.034888070721191, "percentage": 53.57, "elapsed_time": "13:37:20", "remaining_time": "11:48:30", "throughput": 8473.31, "total_tokens": 415533312} {"current_steps": 408200, "total_steps": 761865, "loss": 1.9816, "lr": 4.439083698502721e-07, "epoch": 8.036856923470694, "percentage": 53.58, "elapsed_time": "13:37:31", "remaining_time": "11:48:18", "throughput": 8473.38, "total_tokens": 415635712} {"current_steps": 408300, "total_steps": 761865, "loss": 1.9609, "lr": 4.4370349564818197e-07, "epoch": 8.038825776220197, "percentage": 53.59, "elapsed_time": "13:37:43", "remaining_time": "11:48:06", "throughput": 8473.43, "total_tokens": 415736664} {"current_steps": 408400, "total_steps": 761865, "loss": 1.9643, "lr": 4.4349863101883767e-07, "epoch": 8.0407946289697, "percentage": 53.61, "elapsed_time": "13:37:55", "remaining_time": "11:47:53", "throughput": 8473.5, "total_tokens": 415839064} {"current_steps": 408500, "total_steps": 761865, "loss": 2.0263, "lr": 4.432937759970746e-07, "epoch": 8.042763481719202, "percentage": 53.62, "elapsed_time": "13:38:06", "remaining_time": "11:47:41", "throughput": 8473.56, "total_tokens": 415940552} {"current_steps": 408600, "total_steps": 761865, "loss": 1.9846, "lr": 4.430889306177267e-07, "epoch": 8.044732334468705, "percentage": 53.63, "elapsed_time": "13:38:18", "remaining_time": "11:47:29", "throughput": 8473.63, "total_tokens": 416042952} {"current_steps": 408700, "total_steps": 761865, "loss": 1.9659, "lr": 4.42884094915626e-07, "epoch": 8.046701187218208, "percentage": 53.64, "elapsed_time": "13:38:30", "remaining_time": "11:47:16", "throughput": 8473.69, "total_tokens": 416143776} {"current_steps": 408800, "total_steps": 761865, "loss": 2.0357, "lr": 4.4267926892560334e-07, "epoch": 8.04867003996771, "percentage": 53.66, "elapsed_time": "13:38:41", "remaining_time": "11:47:04", "throughput": 8473.75, "total_tokens": 416244952} {"current_steps": 408900, "total_steps": 761865, "loss": 1.9849, "lr": 4.424744526824874e-07, "epoch": 8.050638892717213, "percentage": 53.67, "elapsed_time": "13:38:53", "remaining_time": "11:46:52", "throughput": 8473.81, "total_tokens": 416347352} {"current_steps": 409000, "total_steps": 761865, "loss": 2.0101, "lr": 4.422696462211056e-07, "epoch": 8.052607745466716, "percentage": 53.68, "elapsed_time": "13:39:05", "remaining_time": "11:46:39", "throughput": 8473.88, "total_tokens": 416449752} {"current_steps": 409100, "total_steps": 761865, "loss": 1.9676, "lr": 4.4206484957628367e-07, "epoch": 8.054576598216219, "percentage": 53.7, "elapsed_time": "13:39:16", "remaining_time": "11:46:27", "throughput": 8473.95, "total_tokens": 416551520} {"current_steps": 409200, "total_steps": 761865, "loss": 2.0223, "lr": 4.4186006278284535e-07, "epoch": 8.056545450965721, "percentage": 53.71, "elapsed_time": "13:39:28", "remaining_time": "11:46:15", "throughput": 8474.01, "total_tokens": 416652472} {"current_steps": 409300, "total_steps": 761865, "loss": 1.9441, "lr": 4.41655285875613e-07, "epoch": 8.058514303715224, "percentage": 53.72, "elapsed_time": "13:39:39", "remaining_time": "11:46:02", "throughput": 8474.07, "total_tokens": 416754208} {"current_steps": 409400, "total_steps": 761865, "loss": 1.9885, "lr": 4.4145051888940715e-07, "epoch": 8.060483156464729, "percentage": 53.74, "elapsed_time": "13:39:51", "remaining_time": "11:45:50", "throughput": 8474.14, "total_tokens": 416856608} {"current_steps": 409500, "total_steps": 761865, "loss": 1.9663, "lr": 4.412457618590468e-07, "epoch": 8.062452009214232, "percentage": 53.75, "elapsed_time": "13:40:03", "remaining_time": "11:45:38", "throughput": 8474.21, "total_tokens": 416959008} {"current_steps": 409600, "total_steps": 761865, "loss": 2.0136, "lr": 4.4104101481934896e-07, "epoch": 8.064420861963734, "percentage": 53.76, "elapsed_time": "13:40:14", "remaining_time": "11:45:25", "throughput": 8474.27, "total_tokens": 417060840} {"current_steps": 409700, "total_steps": 761865, "loss": 1.9905, "lr": 4.4083627780512945e-07, "epoch": 8.066389714713237, "percentage": 53.78, "elapsed_time": "13:40:26", "remaining_time": "11:45:13", "throughput": 8474.33, "total_tokens": 417162384} {"current_steps": 409800, "total_steps": 761865, "loss": 1.9415, "lr": 4.4063155085120173e-07, "epoch": 8.06835856746274, "percentage": 53.79, "elapsed_time": "13:40:38", "remaining_time": "11:45:01", "throughput": 8474.4, "total_tokens": 417264280} {"current_steps": 409900, "total_steps": 761865, "loss": 2.0524, "lr": 4.4042683399237796e-07, "epoch": 8.070327420212243, "percentage": 53.8, "elapsed_time": "13:40:49", "remaining_time": "11:44:48", "throughput": 8474.44, "total_tokens": 417363904} {"current_steps": 410000, "total_steps": 761865, "loss": 1.9839, "lr": 4.402221272634689e-07, "epoch": 8.072296272961745, "percentage": 53.82, "elapsed_time": "13:41:01", "remaining_time": "11:44:36", "throughput": 8474.51, "total_tokens": 417466304} {"current_steps": 410100, "total_steps": 761865, "loss": 1.9513, "lr": 4.4001743069928265e-07, "epoch": 8.074265125711248, "percentage": 53.83, "elapsed_time": "13:41:13", "remaining_time": "11:44:24", "throughput": 8474.49, "total_tokens": 417567960} {"current_steps": 410200, "total_steps": 761865, "loss": 2.0032, "lr": 4.398127443346267e-07, "epoch": 8.07623397846075, "percentage": 53.84, "elapsed_time": "13:41:25", "remaining_time": "11:44:12", "throughput": 8474.55, "total_tokens": 417670360} {"current_steps": 410300, "total_steps": 761865, "loss": 1.9924, "lr": 4.3960806820430555e-07, "epoch": 8.078202831210254, "percentage": 53.85, "elapsed_time": "13:41:36", "remaining_time": "11:43:59", "throughput": 8474.62, "total_tokens": 417772224} {"current_steps": 410400, "total_steps": 761865, "loss": 2.0176, "lr": 4.394034023431233e-07, "epoch": 8.080171683959756, "percentage": 53.87, "elapsed_time": "13:41:48", "remaining_time": "11:43:47", "throughput": 8474.69, "total_tokens": 417874624} {"current_steps": 410500, "total_steps": 761865, "loss": 1.9908, "lr": 4.3919874678588126e-07, "epoch": 8.08214053670926, "percentage": 53.88, "elapsed_time": "13:42:00", "remaining_time": "11:43:35", "throughput": 8474.75, "total_tokens": 417976104} {"current_steps": 410600, "total_steps": 761865, "loss": 1.9808, "lr": 4.389941015673796e-07, "epoch": 8.084109389458762, "percentage": 53.89, "elapsed_time": "13:42:11", "remaining_time": "11:43:22", "throughput": 8474.81, "total_tokens": 418077208} {"current_steps": 410700, "total_steps": 761865, "loss": 2.0238, "lr": 4.3878946672241634e-07, "epoch": 8.086078242208265, "percentage": 53.91, "elapsed_time": "13:42:23", "remaining_time": "11:43:10", "throughput": 8474.88, "total_tokens": 418179608} {"current_steps": 410800, "total_steps": 761865, "loss": 1.9857, "lr": 4.385848422857881e-07, "epoch": 8.088047094957767, "percentage": 53.92, "elapsed_time": "13:42:35", "remaining_time": "11:42:58", "throughput": 8474.93, "total_tokens": 418281152} {"current_steps": 410900, "total_steps": 761865, "loss": 2.0139, "lr": 4.3838022829228933e-07, "epoch": 8.09001594770727, "percentage": 53.93, "elapsed_time": "13:42:46", "remaining_time": "11:42:46", "throughput": 8475.0, "total_tokens": 418383552} {"current_steps": 411000, "total_steps": 761865, "loss": 2.0021, "lr": 4.38175624776713e-07, "epoch": 8.091984800456775, "percentage": 53.95, "elapsed_time": "13:42:58", "remaining_time": "11:42:33", "throughput": 8475.06, "total_tokens": 418485144} {"current_steps": 411100, "total_steps": 761865, "loss": 1.9899, "lr": 4.379710317738503e-07, "epoch": 8.093953653206277, "percentage": 53.96, "elapsed_time": "13:43:10", "remaining_time": "11:42:21", "throughput": 8475.12, "total_tokens": 418586160} {"current_steps": 411200, "total_steps": 761865, "loss": 1.9949, "lr": 4.3776644931849044e-07, "epoch": 8.09592250595578, "percentage": 53.97, "elapsed_time": "13:43:21", "remaining_time": "11:42:08", "throughput": 8475.18, "total_tokens": 418687712} {"current_steps": 411300, "total_steps": 761865, "loss": 1.9742, "lr": 4.37561877445421e-07, "epoch": 8.097891358705283, "percentage": 53.99, "elapsed_time": "13:43:33", "remaining_time": "11:41:56", "throughput": 8475.25, "total_tokens": 418790112} {"current_steps": 411400, "total_steps": 761865, "loss": 1.9978, "lr": 4.3735731618942764e-07, "epoch": 8.099860211454786, "percentage": 54.0, "elapsed_time": "13:43:44", "remaining_time": "11:41:44", "throughput": 8475.31, "total_tokens": 418892064} {"current_steps": 411500, "total_steps": 761865, "loss": 1.9588, "lr": 4.3715276558529436e-07, "epoch": 8.101829064204288, "percentage": 54.01, "elapsed_time": "13:43:56", "remaining_time": "11:41:32", "throughput": 8475.37, "total_tokens": 418993728} {"current_steps": 411600, "total_steps": 761865, "loss": 1.9947, "lr": 4.369482256678031e-07, "epoch": 8.103797916953791, "percentage": 54.03, "elapsed_time": "13:44:08", "remaining_time": "11:41:19", "throughput": 8475.43, "total_tokens": 419094808} {"current_steps": 411700, "total_steps": 761865, "loss": 1.9949, "lr": 4.3674369647173435e-07, "epoch": 8.105766769703294, "percentage": 54.04, "elapsed_time": "13:44:19", "remaining_time": "11:41:07", "throughput": 8475.49, "total_tokens": 419196312} {"current_steps": 411800, "total_steps": 761865, "loss": 1.9819, "lr": 4.3653917803186644e-07, "epoch": 8.107735622452797, "percentage": 54.05, "elapsed_time": "13:44:31", "remaining_time": "11:40:54", "throughput": 8475.54, "total_tokens": 419297152} {"current_steps": 411900, "total_steps": 761865, "loss": 1.992, "lr": 4.3633467038297604e-07, "epoch": 8.1097044752023, "percentage": 54.06, "elapsed_time": "13:44:43", "remaining_time": "11:40:42", "throughput": 8475.61, "total_tokens": 419399040} {"current_steps": 412000, "total_steps": 761865, "loss": 1.9362, "lr": 4.3613017355983803e-07, "epoch": 8.111673327951802, "percentage": 54.08, "elapsed_time": "13:44:54", "remaining_time": "11:40:30", "throughput": 8475.67, "total_tokens": 419500592} {"current_steps": 412100, "total_steps": 761865, "loss": 2.0041, "lr": 4.3592568759722513e-07, "epoch": 8.113642180701305, "percentage": 54.09, "elapsed_time": "13:45:06", "remaining_time": "11:40:17", "throughput": 8475.73, "total_tokens": 419602416} {"current_steps": 412200, "total_steps": 761865, "loss": 1.9372, "lr": 4.35721212529909e-07, "epoch": 8.115611033450808, "percentage": 54.1, "elapsed_time": "13:45:18", "remaining_time": "11:40:05", "throughput": 8475.8, "total_tokens": 419704816} {"current_steps": 412300, "total_steps": 761865, "loss": 1.9939, "lr": 4.3551674839265814e-07, "epoch": 8.11757988620031, "percentage": 54.12, "elapsed_time": "13:45:29", "remaining_time": "11:39:53", "throughput": 8475.87, "total_tokens": 419807216} {"current_steps": 412400, "total_steps": 761865, "loss": 1.9665, "lr": 4.3531229522024065e-07, "epoch": 8.119548738949813, "percentage": 54.13, "elapsed_time": "13:45:41", "remaining_time": "11:39:40", "throughput": 8475.93, "total_tokens": 419908792} {"current_steps": 412500, "total_steps": 761865, "loss": 1.9767, "lr": 4.351078530474215e-07, "epoch": 8.121517591699316, "percentage": 54.14, "elapsed_time": "13:45:52", "remaining_time": "11:39:28", "throughput": 8475.99, "total_tokens": 420010400} {"current_steps": 412600, "total_steps": 761865, "loss": 1.955, "lr": 4.3490342190896485e-07, "epoch": 8.123486444448819, "percentage": 54.16, "elapsed_time": "13:46:04", "remaining_time": "11:39:16", "throughput": 8476.05, "total_tokens": 420112136} {"current_steps": 412700, "total_steps": 761865, "loss": 1.9891, "lr": 4.346990018396319e-07, "epoch": 8.125455297198323, "percentage": 54.17, "elapsed_time": "13:46:16", "remaining_time": "11:39:03", "throughput": 8476.11, "total_tokens": 420213672} {"current_steps": 412800, "total_steps": 761865, "loss": 1.9666, "lr": 4.344945928741834e-07, "epoch": 8.127424149947826, "percentage": 54.18, "elapsed_time": "13:46:27", "remaining_time": "11:38:51", "throughput": 8476.16, "total_tokens": 420314440} {"current_steps": 412900, "total_steps": 761865, "loss": 1.9398, "lr": 4.3429019504737643e-07, "epoch": 8.129393002697329, "percentage": 54.2, "elapsed_time": "13:46:39", "remaining_time": "11:38:39", "throughput": 8476.23, "total_tokens": 420416840} {"current_steps": 413000, "total_steps": 761865, "loss": 1.9923, "lr": 4.340858083939677e-07, "epoch": 8.131361855446832, "percentage": 54.21, "elapsed_time": "13:46:51", "remaining_time": "11:38:26", "throughput": 8476.3, "total_tokens": 420518608} {"current_steps": 413100, "total_steps": 761865, "loss": 1.9991, "lr": 4.3388143294871144e-07, "epoch": 8.133330708196334, "percentage": 54.22, "elapsed_time": "13:47:02", "remaining_time": "11:38:14", "throughput": 8476.36, "total_tokens": 420619736} {"current_steps": 413200, "total_steps": 761865, "loss": 1.9679, "lr": 4.3367706874635975e-07, "epoch": 8.135299560945837, "percentage": 54.24, "elapsed_time": "13:47:14", "remaining_time": "11:38:02", "throughput": 8476.43, "total_tokens": 420722136} {"current_steps": 413300, "total_steps": 761865, "loss": 1.9271, "lr": 4.334727158216632e-07, "epoch": 8.13726841369534, "percentage": 54.25, "elapsed_time": "13:47:25", "remaining_time": "11:37:49", "throughput": 8476.48, "total_tokens": 420823080} {"current_steps": 413400, "total_steps": 761865, "loss": 2.0056, "lr": 4.3326837420937007e-07, "epoch": 8.139237266444843, "percentage": 54.26, "elapsed_time": "13:47:37", "remaining_time": "11:37:37", "throughput": 8476.55, "total_tokens": 420925480} {"current_steps": 413500, "total_steps": 761865, "loss": 1.9977, "lr": 4.3306404394422716e-07, "epoch": 8.141206119194345, "percentage": 54.27, "elapsed_time": "13:47:49", "remaining_time": "11:37:25", "throughput": 8476.61, "total_tokens": 421026864} {"current_steps": 413600, "total_steps": 761865, "loss": 1.9456, "lr": 4.32859725060979e-07, "epoch": 8.143174971943848, "percentage": 54.29, "elapsed_time": "13:48:00", "remaining_time": "11:37:12", "throughput": 8476.66, "total_tokens": 421127064} {"current_steps": 413700, "total_steps": 761865, "loss": 1.9837, "lr": 4.326554175943684e-07, "epoch": 8.145143824693351, "percentage": 54.3, "elapsed_time": "13:48:12", "remaining_time": "11:37:00", "throughput": 8476.72, "total_tokens": 421228704} {"current_steps": 413800, "total_steps": 761865, "loss": 1.9887, "lr": 4.3245112157913583e-07, "epoch": 8.147112677442854, "percentage": 54.31, "elapsed_time": "13:48:24", "remaining_time": "11:36:48", "throughput": 8476.79, "total_tokens": 421331104} {"current_steps": 413900, "total_steps": 761865, "loss": 1.9525, "lr": 4.3224683705002046e-07, "epoch": 8.149081530192356, "percentage": 54.33, "elapsed_time": "13:48:35", "remaining_time": "11:36:35", "throughput": 8476.85, "total_tokens": 421433128} {"current_steps": 414000, "total_steps": 761865, "loss": 2.0093, "lr": 4.3204256404175886e-07, "epoch": 8.15105038294186, "percentage": 54.34, "elapsed_time": "13:48:47", "remaining_time": "11:36:23", "throughput": 8476.91, "total_tokens": 421534480} {"current_steps": 414100, "total_steps": 761865, "loss": 1.9754, "lr": 4.318383025890862e-07, "epoch": 8.153019235691362, "percentage": 54.35, "elapsed_time": "13:48:59", "remaining_time": "11:36:11", "throughput": 8476.98, "total_tokens": 421636880} {"current_steps": 414200, "total_steps": 761865, "loss": 1.9348, "lr": 4.316340527267352e-07, "epoch": 8.154988088440865, "percentage": 54.37, "elapsed_time": "13:49:10", "remaining_time": "11:35:59", "throughput": 8477.05, "total_tokens": 421739280} {"current_steps": 414300, "total_steps": 761865, "loss": 1.9707, "lr": 4.3142981448943687e-07, "epoch": 8.156956941190368, "percentage": 54.38, "elapsed_time": "13:49:22", "remaining_time": "11:35:46", "throughput": 8477.11, "total_tokens": 421841680} {"current_steps": 414400, "total_steps": 761865, "loss": 1.9807, "lr": 4.312255879119204e-07, "epoch": 8.158925793939872, "percentage": 54.39, "elapsed_time": "13:49:34", "remaining_time": "11:35:34", "throughput": 8477.18, "total_tokens": 421943600} {"current_steps": 414500, "total_steps": 761865, "loss": 2.0153, "lr": 4.310213730289125e-07, "epoch": 8.160894646689375, "percentage": 54.41, "elapsed_time": "13:49:45", "remaining_time": "11:35:22", "throughput": 8477.24, "total_tokens": 422045392} {"current_steps": 414600, "total_steps": 761865, "loss": 1.9624, "lr": 4.308171698751384e-07, "epoch": 8.162863499438878, "percentage": 54.42, "elapsed_time": "13:49:57", "remaining_time": "11:35:09", "throughput": 8477.3, "total_tokens": 422147040} {"current_steps": 414700, "total_steps": 761865, "loss": 1.9825, "lr": 4.3061297848532094e-07, "epoch": 8.16483235218838, "percentage": 54.43, "elapsed_time": "13:50:08", "remaining_time": "11:34:57", "throughput": 8477.36, "total_tokens": 422248016} {"current_steps": 414800, "total_steps": 761865, "loss": 1.9748, "lr": 4.3040879889418143e-07, "epoch": 8.166801204937883, "percentage": 54.45, "elapsed_time": "13:50:20", "remaining_time": "11:34:45", "throughput": 8477.43, "total_tokens": 422349664} {"current_steps": 414900, "total_steps": 761865, "loss": 2.0006, "lr": 4.302046311364385e-07, "epoch": 8.168770057687386, "percentage": 54.46, "elapsed_time": "13:50:32", "remaining_time": "11:34:32", "throughput": 8477.49, "total_tokens": 422452064} {"current_steps": 415000, "total_steps": 761865, "loss": 1.9735, "lr": 4.3000047524680935e-07, "epoch": 8.170738910436889, "percentage": 54.47, "elapsed_time": "13:50:43", "remaining_time": "11:34:20", "throughput": 8477.55, "total_tokens": 422552784} {"current_steps": 415100, "total_steps": 761865, "loss": 2.003, "lr": 4.2979633126000923e-07, "epoch": 8.172707763186391, "percentage": 54.48, "elapsed_time": "13:50:56", "remaining_time": "11:34:08", "throughput": 8477.52, "total_tokens": 422655184} {"current_steps": 415200, "total_steps": 761865, "loss": 2.0106, "lr": 4.295921992107506e-07, "epoch": 8.174676615935894, "percentage": 54.5, "elapsed_time": "13:51:07", "remaining_time": "11:33:56", "throughput": 8477.57, "total_tokens": 422756176} {"current_steps": 415300, "total_steps": 761865, "loss": 1.9747, "lr": 4.2938807913374494e-07, "epoch": 8.176645468685397, "percentage": 54.51, "elapsed_time": "13:51:19", "remaining_time": "11:33:43", "throughput": 8477.64, "total_tokens": 422858040} {"current_steps": 415400, "total_steps": 761865, "loss": 1.9635, "lr": 4.2918397106370047e-07, "epoch": 8.1786143214349, "percentage": 54.52, "elapsed_time": "13:51:30", "remaining_time": "11:33:31", "throughput": 8477.69, "total_tokens": 422959528} {"current_steps": 415500, "total_steps": 761865, "loss": 2.0448, "lr": 4.2897987503532486e-07, "epoch": 8.180583174184402, "percentage": 54.54, "elapsed_time": "13:51:42", "remaining_time": "11:33:19", "throughput": 8477.76, "total_tokens": 423061928} {"current_steps": 415600, "total_steps": 761865, "loss": 1.977, "lr": 4.287757910833221e-07, "epoch": 8.182552026933905, "percentage": 54.55, "elapsed_time": "13:51:54", "remaining_time": "11:33:07", "throughput": 8477.82, "total_tokens": 423164328} {"current_steps": 415700, "total_steps": 761865, "loss": 1.9657, "lr": 4.2857171924239565e-07, "epoch": 8.184520879683408, "percentage": 54.56, "elapsed_time": "13:52:05", "remaining_time": "11:32:54", "throughput": 8477.88, "total_tokens": 423265456} {"current_steps": 415800, "total_steps": 761865, "loss": 1.9946, "lr": 4.283676595472456e-07, "epoch": 8.18648973243291, "percentage": 54.58, "elapsed_time": "13:52:17", "remaining_time": "11:32:42", "throughput": 8477.95, "total_tokens": 423367856} {"current_steps": 415900, "total_steps": 761865, "loss": 2.0006, "lr": 4.281636120325712e-07, "epoch": 8.188458585182413, "percentage": 54.59, "elapsed_time": "13:52:29", "remaining_time": "11:32:30", "throughput": 8478.02, "total_tokens": 423470256} {"current_steps": 416000, "total_steps": 761865, "loss": 1.9659, "lr": 4.2795957673306824e-07, "epoch": 8.190427437931916, "percentage": 54.6, "elapsed_time": "13:52:40", "remaining_time": "11:32:17", "throughput": 8478.08, "total_tokens": 423571888} {"current_steps": 416100, "total_steps": 761865, "loss": 1.9503, "lr": 4.2775555368343184e-07, "epoch": 8.19239629068142, "percentage": 54.62, "elapsed_time": "13:52:52", "remaining_time": "11:32:05", "throughput": 8478.15, "total_tokens": 423673592} {"current_steps": 416200, "total_steps": 761865, "loss": 1.9951, "lr": 4.2755154291835436e-07, "epoch": 8.194365143430923, "percentage": 54.63, "elapsed_time": "13:53:04", "remaining_time": "11:31:53", "throughput": 8478.21, "total_tokens": 423775992} {"current_steps": 416300, "total_steps": 761865, "loss": 1.9828, "lr": 4.273475444725258e-07, "epoch": 8.196333996180426, "percentage": 54.64, "elapsed_time": "13:53:15", "remaining_time": "11:31:40", "throughput": 8478.27, "total_tokens": 423877600} {"current_steps": 416400, "total_steps": 761865, "loss": 2.0001, "lr": 4.2714355838063457e-07, "epoch": 8.198302848929929, "percentage": 54.66, "elapsed_time": "13:53:27", "remaining_time": "11:31:28", "throughput": 8478.33, "total_tokens": 423979040} {"current_steps": 416500, "total_steps": 761865, "loss": 1.9072, "lr": 4.269395846773667e-07, "epoch": 8.200271701679432, "percentage": 54.67, "elapsed_time": "13:53:39", "remaining_time": "11:31:16", "throughput": 8478.4, "total_tokens": 424081440} {"current_steps": 416600, "total_steps": 761865, "loss": 1.9907, "lr": 4.2673562339740634e-07, "epoch": 8.202240554428935, "percentage": 54.68, "elapsed_time": "13:53:50", "remaining_time": "11:31:03", "throughput": 8478.45, "total_tokens": 424182984} {"current_steps": 416700, "total_steps": 761865, "loss": 2.0106, "lr": 4.2653167457543515e-07, "epoch": 8.204209407178437, "percentage": 54.69, "elapsed_time": "13:54:02", "remaining_time": "11:30:51", "throughput": 8478.51, "total_tokens": 424284424} {"current_steps": 416800, "total_steps": 761865, "loss": 2.037, "lr": 4.2632773824613314e-07, "epoch": 8.20617825992794, "percentage": 54.71, "elapsed_time": "13:54:13", "remaining_time": "11:30:39", "throughput": 8478.57, "total_tokens": 424386312} {"current_steps": 416900, "total_steps": 761865, "loss": 1.9819, "lr": 4.261238144441778e-07, "epoch": 8.208147112677443, "percentage": 54.72, "elapsed_time": "13:54:25", "remaining_time": "11:30:26", "throughput": 8478.63, "total_tokens": 424487896} {"current_steps": 417000, "total_steps": 761865, "loss": 1.9742, "lr": 4.2591990320424464e-07, "epoch": 8.210115965426946, "percentage": 54.73, "elapsed_time": "13:54:37", "remaining_time": "11:30:14", "throughput": 8478.7, "total_tokens": 424590296} {"current_steps": 417100, "total_steps": 761865, "loss": 2.0141, "lr": 4.2571600456100727e-07, "epoch": 8.212084818176448, "percentage": 54.75, "elapsed_time": "13:54:48", "remaining_time": "11:30:02", "throughput": 8478.77, "total_tokens": 424692696} {"current_steps": 417200, "total_steps": 761865, "loss": 1.9624, "lr": 4.2551211854913666e-07, "epoch": 8.214053670925951, "percentage": 54.76, "elapsed_time": "13:55:00", "remaining_time": "11:29:50", "throughput": 8478.83, "total_tokens": 424795096} {"current_steps": 417300, "total_steps": 761865, "loss": 1.9824, "lr": 4.253082452033022e-07, "epoch": 8.216022523675454, "percentage": 54.77, "elapsed_time": "13:55:12", "remaining_time": "11:29:37", "throughput": 8478.9, "total_tokens": 424897496} {"current_steps": 417400, "total_steps": 761865, "loss": 2.01, "lr": 4.2510438455817045e-07, "epoch": 8.217991376424957, "percentage": 54.79, "elapsed_time": "13:55:23", "remaining_time": "11:29:25", "throughput": 8478.96, "total_tokens": 424998560} {"current_steps": 417500, "total_steps": 761865, "loss": 2.0074, "lr": 4.2490053664840657e-07, "epoch": 8.21996022917446, "percentage": 54.8, "elapsed_time": "13:55:35", "remaining_time": "11:29:13", "throughput": 8479.03, "total_tokens": 425100960} {"current_steps": 417600, "total_steps": 761865, "loss": 1.9644, "lr": 4.246967015086729e-07, "epoch": 8.221929081923962, "percentage": 54.81, "elapsed_time": "13:55:47", "remaining_time": "11:29:00", "throughput": 8479.08, "total_tokens": 425202240} {"current_steps": 417700, "total_steps": 761865, "loss": 2.0033, "lr": 4.2449287917363013e-07, "epoch": 8.223897934673467, "percentage": 54.83, "elapsed_time": "13:55:58", "remaining_time": "11:28:48", "throughput": 8479.15, "total_tokens": 425303872} {"current_steps": 417800, "total_steps": 761865, "loss": 1.9778, "lr": 4.2428906967793627e-07, "epoch": 8.22586678742297, "percentage": 54.84, "elapsed_time": "13:56:10", "remaining_time": "11:28:36", "throughput": 8479.21, "total_tokens": 425406272} {"current_steps": 417900, "total_steps": 761865, "loss": 1.9131, "lr": 4.2408527305624763e-07, "epoch": 8.227835640172472, "percentage": 54.85, "elapsed_time": "13:56:22", "remaining_time": "11:28:23", "throughput": 8479.28, "total_tokens": 425508672} {"current_steps": 418000, "total_steps": 761865, "loss": 1.9759, "lr": 4.2388148934321797e-07, "epoch": 8.229804492921975, "percentage": 54.87, "elapsed_time": "13:56:33", "remaining_time": "11:28:11", "throughput": 8479.35, "total_tokens": 425611072} {"current_steps": 418100, "total_steps": 761865, "loss": 1.9959, "lr": 4.236777185734989e-07, "epoch": 8.231773345671478, "percentage": 54.88, "elapsed_time": "13:56:45", "remaining_time": "11:27:59", "throughput": 8479.4, "total_tokens": 425711696} {"current_steps": 418200, "total_steps": 761865, "loss": 1.981, "lr": 4.2347396078174035e-07, "epoch": 8.23374219842098, "percentage": 54.89, "elapsed_time": "13:56:57", "remaining_time": "11:27:46", "throughput": 8479.46, "total_tokens": 425813368} {"current_steps": 418300, "total_steps": 761865, "loss": 1.9627, "lr": 4.23270216002589e-07, "epoch": 8.235711051170483, "percentage": 54.9, "elapsed_time": "13:57:08", "remaining_time": "11:27:34", "throughput": 8479.53, "total_tokens": 425915768} {"current_steps": 418400, "total_steps": 761865, "loss": 1.949, "lr": 4.230664842706906e-07, "epoch": 8.237679903919986, "percentage": 54.92, "elapsed_time": "13:57:20", "remaining_time": "11:27:22", "throughput": 8479.59, "total_tokens": 426018168} {"current_steps": 418500, "total_steps": 761865, "loss": 1.9839, "lr": 4.228627656206873e-07, "epoch": 8.239648756669489, "percentage": 54.93, "elapsed_time": "13:57:32", "remaining_time": "11:27:10", "throughput": 8479.66, "total_tokens": 426120472} {"current_steps": 418600, "total_steps": 761865, "loss": 1.9741, "lr": 4.226590600872204e-07, "epoch": 8.241617609418991, "percentage": 54.94, "elapsed_time": "13:57:43", "remaining_time": "11:26:57", "throughput": 8479.72, "total_tokens": 426222872} {"current_steps": 418700, "total_steps": 761865, "loss": 2.0482, "lr": 4.224553677049277e-07, "epoch": 8.243586462168494, "percentage": 54.96, "elapsed_time": "13:57:55", "remaining_time": "11:26:45", "throughput": 8479.78, "total_tokens": 426323976} {"current_steps": 418800, "total_steps": 761865, "loss": 2.0172, "lr": 4.222516885084459e-07, "epoch": 8.245555314917997, "percentage": 54.97, "elapsed_time": "13:58:07", "remaining_time": "11:26:33", "throughput": 8479.84, "total_tokens": 426425728} {"current_steps": 418900, "total_steps": 761865, "loss": 2.0268, "lr": 4.2204802253240867e-07, "epoch": 8.2475241676675, "percentage": 54.98, "elapsed_time": "13:58:18", "remaining_time": "11:26:20", "throughput": 8479.91, "total_tokens": 426528128} {"current_steps": 419000, "total_steps": 761865, "loss": 1.9851, "lr": 4.218443698114477e-07, "epoch": 8.249493020417002, "percentage": 55.0, "elapsed_time": "13:58:30", "remaining_time": "11:26:08", "throughput": 8479.97, "total_tokens": 426629912} {"current_steps": 419100, "total_steps": 761865, "loss": 1.9909, "lr": 4.2164073038019255e-07, "epoch": 8.251461873166505, "percentage": 55.01, "elapsed_time": "13:58:41", "remaining_time": "11:25:56", "throughput": 8480.03, "total_tokens": 426730600} {"current_steps": 419200, "total_steps": 761865, "loss": 1.9292, "lr": 4.2143710427327016e-07, "epoch": 8.253430725916008, "percentage": 55.02, "elapsed_time": "13:58:53", "remaining_time": "11:25:43", "throughput": 8480.09, "total_tokens": 426832208} {"current_steps": 419300, "total_steps": 761865, "loss": 2.0009, "lr": 4.2123349152530567e-07, "epoch": 8.25539957866551, "percentage": 55.04, "elapsed_time": "13:59:05", "remaining_time": "11:25:31", "throughput": 8480.15, "total_tokens": 426934008} {"current_steps": 419400, "total_steps": 761865, "loss": 1.9699, "lr": 4.2102989217092155e-07, "epoch": 8.257368431415015, "percentage": 55.05, "elapsed_time": "13:59:16", "remaining_time": "11:25:19", "throughput": 8480.21, "total_tokens": 427036408} {"current_steps": 419500, "total_steps": 761865, "loss": 1.9936, "lr": 4.2082630624473824e-07, "epoch": 8.259337284164518, "percentage": 55.06, "elapsed_time": "13:59:28", "remaining_time": "11:25:07", "throughput": 8480.28, "total_tokens": 427138808} {"current_steps": 419600, "total_steps": 761865, "loss": 1.9563, "lr": 4.206227337813737e-07, "epoch": 8.26130613691402, "percentage": 55.08, "elapsed_time": "13:59:40", "remaining_time": "11:24:54", "throughput": 8480.35, "total_tokens": 427241208} {"current_steps": 419700, "total_steps": 761865, "loss": 1.9736, "lr": 4.204191748154439e-07, "epoch": 8.263274989663524, "percentage": 55.09, "elapsed_time": "13:59:51", "remaining_time": "11:24:42", "throughput": 8480.4, "total_tokens": 427342240} {"current_steps": 419800, "total_steps": 761865, "loss": 1.9145, "lr": 4.2021562938156204e-07, "epoch": 8.265243842413026, "percentage": 55.1, "elapsed_time": "14:00:03", "remaining_time": "11:24:30", "throughput": 8480.47, "total_tokens": 427444640} {"current_steps": 419900, "total_steps": 761865, "loss": 2.0103, "lr": 4.200120975143396e-07, "epoch": 8.267212695162529, "percentage": 55.11, "elapsed_time": "14:00:15", "remaining_time": "11:24:17", "throughput": 8480.53, "total_tokens": 427546264} {"current_steps": 420000, "total_steps": 761865, "loss": 2.0053, "lr": 4.198085792483852e-07, "epoch": 8.269181547912032, "percentage": 55.13, "elapsed_time": "14:00:26", "remaining_time": "11:24:05", "throughput": 8480.56, "total_tokens": 427645224} {"current_steps": 420100, "total_steps": 761865, "loss": 1.9874, "lr": 4.196050746183056e-07, "epoch": 8.271150400661535, "percentage": 55.14, "elapsed_time": "14:00:38", "remaining_time": "11:23:53", "throughput": 8480.52, "total_tokens": 427747056} {"current_steps": 420200, "total_steps": 761865, "loss": 2.0144, "lr": 4.1940158365870505e-07, "epoch": 8.273119253411037, "percentage": 55.15, "elapsed_time": "14:00:50", "remaining_time": "11:23:41", "throughput": 8480.58, "total_tokens": 427847912} {"current_steps": 420300, "total_steps": 761865, "loss": 1.9802, "lr": 4.191981064041852e-07, "epoch": 8.27508810616054, "percentage": 55.17, "elapsed_time": "14:01:01", "remaining_time": "11:23:28", "throughput": 8480.63, "total_tokens": 427948560} {"current_steps": 420400, "total_steps": 761865, "loss": 1.9744, "lr": 4.189946428893461e-07, "epoch": 8.277056958910043, "percentage": 55.18, "elapsed_time": "14:01:13", "remaining_time": "11:23:16", "throughput": 8480.69, "total_tokens": 428050336} {"current_steps": 420500, "total_steps": 761865, "loss": 1.9827, "lr": 4.1879119314878445e-07, "epoch": 8.279025811659546, "percentage": 55.19, "elapsed_time": "14:01:25", "remaining_time": "11:23:04", "throughput": 8480.75, "total_tokens": 428151904} {"current_steps": 420600, "total_steps": 761865, "loss": 2.0161, "lr": 4.185877572170958e-07, "epoch": 8.280994664409048, "percentage": 55.21, "elapsed_time": "14:01:36", "remaining_time": "11:22:51", "throughput": 8480.81, "total_tokens": 428254304} {"current_steps": 420700, "total_steps": 761865, "loss": 2.0101, "lr": 4.1838433512887206e-07, "epoch": 8.282963517158551, "percentage": 55.22, "elapsed_time": "14:01:48", "remaining_time": "11:22:39", "throughput": 8480.86, "total_tokens": 428354696} {"current_steps": 420800, "total_steps": 761865, "loss": 1.9907, "lr": 4.181809269187041e-07, "epoch": 8.284932369908054, "percentage": 55.23, "elapsed_time": "14:02:00", "remaining_time": "11:22:27", "throughput": 8480.93, "total_tokens": 428457096} {"current_steps": 420900, "total_steps": 761865, "loss": 2.0325, "lr": 4.1797753262117906e-07, "epoch": 8.286901222657557, "percentage": 55.25, "elapsed_time": "14:02:11", "remaining_time": "11:22:15", "throughput": 8481.0, "total_tokens": 428559496} {"current_steps": 421000, "total_steps": 761865, "loss": 1.9524, "lr": 4.177741522708831e-07, "epoch": 8.28887007540706, "percentage": 55.26, "elapsed_time": "14:02:23", "remaining_time": "11:22:02", "throughput": 8481.06, "total_tokens": 428661456} {"current_steps": 421100, "total_steps": 761865, "loss": 1.9485, "lr": 4.1757078590239877e-07, "epoch": 8.290838928156564, "percentage": 55.27, "elapsed_time": "14:02:35", "remaining_time": "11:21:50", "throughput": 8481.12, "total_tokens": 428763120} {"current_steps": 421200, "total_steps": 761865, "loss": 1.9618, "lr": 4.173674335503071e-07, "epoch": 8.292807780906067, "percentage": 55.29, "elapsed_time": "14:02:46", "remaining_time": "11:21:38", "throughput": 8481.18, "total_tokens": 428865056} {"current_steps": 421300, "total_steps": 761865, "loss": 1.959, "lr": 4.171640952491865e-07, "epoch": 8.29477663365557, "percentage": 55.3, "elapsed_time": "14:02:58", "remaining_time": "11:21:25", "throughput": 8481.25, "total_tokens": 428967456} {"current_steps": 421400, "total_steps": 761865, "loss": 2.0106, "lr": 4.169607710336127e-07, "epoch": 8.296745486405072, "percentage": 55.31, "elapsed_time": "14:03:09", "remaining_time": "11:21:13", "throughput": 8481.31, "total_tokens": 429069320} {"current_steps": 421500, "total_steps": 761865, "loss": 2.0069, "lr": 4.167574609381596e-07, "epoch": 8.298714339154575, "percentage": 55.32, "elapsed_time": "14:03:21", "remaining_time": "11:21:01", "throughput": 8481.38, "total_tokens": 429171720} {"current_steps": 421600, "total_steps": 761865, "loss": 1.9547, "lr": 4.1655416499739805e-07, "epoch": 8.300683191904078, "percentage": 55.34, "elapsed_time": "14:03:33", "remaining_time": "11:20:48", "throughput": 8481.44, "total_tokens": 429273488} {"current_steps": 421700, "total_steps": 761865, "loss": 1.9648, "lr": 4.1635088324589697e-07, "epoch": 8.30265204465358, "percentage": 55.35, "elapsed_time": "14:03:44", "remaining_time": "11:20:36", "throughput": 8481.5, "total_tokens": 429375128} {"current_steps": 421800, "total_steps": 761865, "loss": 2.0021, "lr": 4.161476157182226e-07, "epoch": 8.304620897403083, "percentage": 55.36, "elapsed_time": "14:03:56", "remaining_time": "11:20:24", "throughput": 8481.57, "total_tokens": 429477528} {"current_steps": 421900, "total_steps": 761865, "loss": 1.9753, "lr": 4.15944362448939e-07, "epoch": 8.306589750152586, "percentage": 55.38, "elapsed_time": "14:04:08", "remaining_time": "11:20:12", "throughput": 8481.63, "total_tokens": 429579928} {"current_steps": 422000, "total_steps": 761865, "loss": 2.026, "lr": 4.157411234726075e-07, "epoch": 8.308558602902089, "percentage": 55.39, "elapsed_time": "14:04:19", "remaining_time": "11:19:59", "throughput": 8481.7, "total_tokens": 429682328} {"current_steps": 422100, "total_steps": 761865, "loss": 1.9869, "lr": 4.155378988237873e-07, "epoch": 8.310527455651592, "percentage": 55.4, "elapsed_time": "14:04:31", "remaining_time": "11:19:47", "throughput": 8481.75, "total_tokens": 429783424} {"current_steps": 422200, "total_steps": 761865, "loss": 1.9707, "lr": 4.153346885370352e-07, "epoch": 8.312496308401094, "percentage": 55.42, "elapsed_time": "14:04:43", "remaining_time": "11:19:35", "throughput": 8481.82, "total_tokens": 429885824} {"current_steps": 422300, "total_steps": 761865, "loss": 1.9664, "lr": 4.15131492646905e-07, "epoch": 8.314465161150597, "percentage": 55.43, "elapsed_time": "14:04:54", "remaining_time": "11:19:22", "throughput": 8481.88, "total_tokens": 429987752} {"current_steps": 422400, "total_steps": 761865, "loss": 1.9944, "lr": 4.149283111879488e-07, "epoch": 8.3164340139001, "percentage": 55.44, "elapsed_time": "14:05:06", "remaining_time": "11:19:10", "throughput": 8481.94, "total_tokens": 430089480} {"current_steps": 422500, "total_steps": 761865, "loss": 1.963, "lr": 4.147251441947157e-07, "epoch": 8.318402866649603, "percentage": 55.46, "elapsed_time": "14:05:18", "remaining_time": "11:18:58", "throughput": 8482.0, "total_tokens": 430191200} {"current_steps": 422600, "total_steps": 761865, "loss": 1.9883, "lr": 4.145219917017526e-07, "epoch": 8.320371719399105, "percentage": 55.47, "elapsed_time": "14:05:29", "remaining_time": "11:18:46", "throughput": 8482.07, "total_tokens": 430293600} {"current_steps": 422700, "total_steps": 761865, "loss": 1.9865, "lr": 4.1431885374360386e-07, "epoch": 8.322340572148608, "percentage": 55.48, "elapsed_time": "14:05:41", "remaining_time": "11:18:33", "throughput": 8482.11, "total_tokens": 430393568} {"current_steps": 422800, "total_steps": 761865, "loss": 1.9893, "lr": 4.141157303548114e-07, "epoch": 8.324309424898113, "percentage": 55.5, "elapsed_time": "14:05:53", "remaining_time": "11:18:21", "throughput": 8482.17, "total_tokens": 430495968} {"current_steps": 422900, "total_steps": 761865, "loss": 1.9625, "lr": 4.1391262156991454e-07, "epoch": 8.326278277647615, "percentage": 55.51, "elapsed_time": "14:06:04", "remaining_time": "11:18:09", "throughput": 8482.24, "total_tokens": 430598368} {"current_steps": 423000, "total_steps": 761865, "loss": 1.9965, "lr": 4.137095274234504e-07, "epoch": 8.328247130397118, "percentage": 55.52, "elapsed_time": "14:06:16", "remaining_time": "11:17:56", "throughput": 8482.3, "total_tokens": 430699680} {"current_steps": 423100, "total_steps": 761865, "loss": 2.0005, "lr": 4.1350644794995315e-07, "epoch": 8.330215983146621, "percentage": 55.53, "elapsed_time": "14:06:27", "remaining_time": "11:17:44", "throughput": 8482.36, "total_tokens": 430801344} {"current_steps": 423200, "total_steps": 761865, "loss": 2.0115, "lr": 4.133033831839549e-07, "epoch": 8.332184835896124, "percentage": 55.55, "elapsed_time": "14:06:39", "remaining_time": "11:17:32", "throughput": 8482.41, "total_tokens": 430902008} {"current_steps": 423300, "total_steps": 761865, "loss": 1.9885, "lr": 4.131003331599853e-07, "epoch": 8.334153688645626, "percentage": 55.56, "elapsed_time": "14:06:51", "remaining_time": "11:17:19", "throughput": 8482.48, "total_tokens": 431004408} {"current_steps": 423400, "total_steps": 761865, "loss": 1.9816, "lr": 4.128972979125709e-07, "epoch": 8.33612254139513, "percentage": 55.57, "elapsed_time": "14:07:02", "remaining_time": "11:17:07", "throughput": 8482.53, "total_tokens": 431105448} {"current_steps": 423500, "total_steps": 761865, "loss": 1.992, "lr": 4.126942774762365e-07, "epoch": 8.338091394144632, "percentage": 55.59, "elapsed_time": "14:07:14", "remaining_time": "11:16:55", "throughput": 8482.6, "total_tokens": 431207848} {"current_steps": 423600, "total_steps": 761865, "loss": 1.9986, "lr": 4.124912718855037e-07, "epoch": 8.340060246894135, "percentage": 55.6, "elapsed_time": "14:07:25", "remaining_time": "11:16:42", "throughput": 8482.66, "total_tokens": 431309032} {"current_steps": 423700, "total_steps": 761865, "loss": 1.9755, "lr": 4.1228828117489225e-07, "epoch": 8.342029099643637, "percentage": 55.61, "elapsed_time": "14:07:37", "remaining_time": "11:16:30", "throughput": 8482.72, "total_tokens": 431410840} {"current_steps": 423800, "total_steps": 761865, "loss": 1.9747, "lr": 4.120853053789185e-07, "epoch": 8.34399795239314, "percentage": 55.63, "elapsed_time": "14:07:49", "remaining_time": "11:16:18", "throughput": 8482.78, "total_tokens": 431512200} {"current_steps": 423900, "total_steps": 761865, "loss": 1.9553, "lr": 4.1188234453209735e-07, "epoch": 8.345966805142643, "percentage": 55.64, "elapsed_time": "14:08:00", "remaining_time": "11:16:06", "throughput": 8482.85, "total_tokens": 431614600} {"current_steps": 424000, "total_steps": 761865, "loss": 1.9603, "lr": 4.1167939866894e-07, "epoch": 8.347935657892146, "percentage": 55.65, "elapsed_time": "14:08:12", "remaining_time": "11:15:53", "throughput": 8482.91, "total_tokens": 431716448} {"current_steps": 424100, "total_steps": 761865, "loss": 1.9783, "lr": 4.1147646782395614e-07, "epoch": 8.349904510641649, "percentage": 55.67, "elapsed_time": "14:08:24", "remaining_time": "11:15:41", "throughput": 8482.96, "total_tokens": 431817920} {"current_steps": 424200, "total_steps": 761865, "loss": 1.9808, "lr": 4.112735520316523e-07, "epoch": 8.351873363391151, "percentage": 55.68, "elapsed_time": "14:08:35", "remaining_time": "11:15:29", "throughput": 8483.02, "total_tokens": 431919736} {"current_steps": 424300, "total_steps": 761865, "loss": 1.9357, "lr": 4.110706513265325e-07, "epoch": 8.353842216140654, "percentage": 55.69, "elapsed_time": "14:08:47", "remaining_time": "11:15:16", "throughput": 8483.08, "total_tokens": 432020928} {"current_steps": 424400, "total_steps": 761865, "loss": 1.9918, "lr": 4.108677657430986e-07, "epoch": 8.355811068890159, "percentage": 55.71, "elapsed_time": "14:08:58", "remaining_time": "11:15:04", "throughput": 8483.13, "total_tokens": 432121480} {"current_steps": 424500, "total_steps": 761865, "loss": 1.9791, "lr": 4.106648953158491e-07, "epoch": 8.357779921639661, "percentage": 55.72, "elapsed_time": "14:09:10", "remaining_time": "11:14:52", "throughput": 8483.18, "total_tokens": 432223008} {"current_steps": 424600, "total_steps": 761865, "loss": 1.9955, "lr": 4.1046204007928083e-07, "epoch": 8.359748774389164, "percentage": 55.73, "elapsed_time": "14:09:22", "remaining_time": "11:14:39", "throughput": 8483.24, "total_tokens": 432324496} {"current_steps": 424700, "total_steps": 761865, "loss": 1.9879, "lr": 4.102592000678873e-07, "epoch": 8.361717627138667, "percentage": 55.74, "elapsed_time": "14:09:33", "remaining_time": "11:14:27", "throughput": 8483.31, "total_tokens": 432426896} {"current_steps": 424800, "total_steps": 761865, "loss": 1.9809, "lr": 4.1005637531616006e-07, "epoch": 8.36368647988817, "percentage": 55.76, "elapsed_time": "14:09:45", "remaining_time": "11:14:15", "throughput": 8483.37, "total_tokens": 432529208} {"current_steps": 424900, "total_steps": 761865, "loss": 1.9566, "lr": 4.098535658585874e-07, "epoch": 8.365655332637672, "percentage": 55.77, "elapsed_time": "14:09:57", "remaining_time": "11:14:03", "throughput": 8483.43, "total_tokens": 432631608} {"current_steps": 425000, "total_steps": 761865, "loss": 2.0003, "lr": 4.096507717296557e-07, "epoch": 8.367624185387175, "percentage": 55.78, "elapsed_time": "14:10:08", "remaining_time": "11:13:50", "throughput": 8483.49, "total_tokens": 432733384} {"current_steps": 425100, "total_steps": 761865, "loss": 1.9813, "lr": 4.0944799296384813e-07, "epoch": 8.369593038136678, "percentage": 55.8, "elapsed_time": "14:10:21", "remaining_time": "11:13:39", "throughput": 8483.46, "total_tokens": 432835784} {"current_steps": 425200, "total_steps": 761865, "loss": 2.0267, "lr": 4.092452295956456e-07, "epoch": 8.37156189088618, "percentage": 55.81, "elapsed_time": "14:10:32", "remaining_time": "11:13:26", "throughput": 8483.51, "total_tokens": 432936896} {"current_steps": 425300, "total_steps": 761865, "loss": 1.9489, "lr": 4.090424816595264e-07, "epoch": 8.373530743635683, "percentage": 55.82, "elapsed_time": "14:10:44", "remaining_time": "11:13:14", "throughput": 8483.57, "total_tokens": 433038616} {"current_steps": 425400, "total_steps": 761865, "loss": 1.9718, "lr": 4.0883974918996587e-07, "epoch": 8.375499596385186, "percentage": 55.84, "elapsed_time": "14:10:56", "remaining_time": "11:13:02", "throughput": 8483.64, "total_tokens": 433141016} {"current_steps": 425500, "total_steps": 761865, "loss": 1.9749, "lr": 4.0863703222143725e-07, "epoch": 8.377468449134689, "percentage": 55.85, "elapsed_time": "14:11:07", "remaining_time": "11:12:49", "throughput": 8483.69, "total_tokens": 433242080} {"current_steps": 425600, "total_steps": 761865, "loss": 1.9709, "lr": 4.084343307884106e-07, "epoch": 8.379437301884192, "percentage": 55.86, "elapsed_time": "14:11:19", "remaining_time": "11:12:37", "throughput": 8483.75, "total_tokens": 433343856} {"current_steps": 425700, "total_steps": 761865, "loss": 2.0071, "lr": 4.0823164492535383e-07, "epoch": 8.381406154633694, "percentage": 55.88, "elapsed_time": "14:11:30", "remaining_time": "11:12:25", "throughput": 8483.82, "total_tokens": 433446256} {"current_steps": 425800, "total_steps": 761865, "loss": 1.9643, "lr": 4.080289746667317e-07, "epoch": 8.383375007383197, "percentage": 55.89, "elapsed_time": "14:11:42", "remaining_time": "11:12:13", "throughput": 8483.88, "total_tokens": 433548656} {"current_steps": 425900, "total_steps": 761865, "loss": 2.0125, "lr": 4.0782632004700685e-07, "epoch": 8.3853438601327, "percentage": 55.9, "elapsed_time": "14:11:54", "remaining_time": "11:12:00", "throughput": 8483.94, "total_tokens": 433649784} {"current_steps": 426000, "total_steps": 761865, "loss": 1.9535, "lr": 4.0762368110063874e-07, "epoch": 8.387312712882203, "percentage": 55.92, "elapsed_time": "14:12:05", "remaining_time": "11:11:48", "throughput": 8484.0, "total_tokens": 433751712} {"current_steps": 426100, "total_steps": 761865, "loss": 1.9249, "lr": 4.0742105786208456e-07, "epoch": 8.389281565631707, "percentage": 55.93, "elapsed_time": "14:12:17", "remaining_time": "11:11:36", "throughput": 8484.06, "total_tokens": 433854112} {"current_steps": 426200, "total_steps": 761865, "loss": 1.9851, "lr": 4.072184503657986e-07, "epoch": 8.39125041838121, "percentage": 55.94, "elapsed_time": "14:12:29", "remaining_time": "11:11:23", "throughput": 8484.12, "total_tokens": 433955736} {"current_steps": 426300, "total_steps": 761865, "loss": 2.0063, "lr": 4.070158586462325e-07, "epoch": 8.393219271130713, "percentage": 55.95, "elapsed_time": "14:12:40", "remaining_time": "11:11:11", "throughput": 8484.18, "total_tokens": 434057696} {"current_steps": 426400, "total_steps": 761865, "loss": 2.0578, "lr": 4.0681328273783565e-07, "epoch": 8.395188123880216, "percentage": 55.97, "elapsed_time": "14:12:52", "remaining_time": "11:10:59", "throughput": 8484.24, "total_tokens": 434159568} {"current_steps": 426500, "total_steps": 761865, "loss": 1.9879, "lr": 4.066107226750538e-07, "epoch": 8.397156976629718, "percentage": 55.98, "elapsed_time": "14:13:04", "remaining_time": "11:10:47", "throughput": 8484.3, "total_tokens": 434261768} {"current_steps": 426600, "total_steps": 761865, "loss": 2.0116, "lr": 4.0640817849233124e-07, "epoch": 8.399125829379221, "percentage": 55.99, "elapsed_time": "14:13:15", "remaining_time": "11:10:34", "throughput": 8484.36, "total_tokens": 434363464} {"current_steps": 426700, "total_steps": 761865, "loss": 2.0201, "lr": 4.062056502241081e-07, "epoch": 8.401094682128724, "percentage": 56.01, "elapsed_time": "14:13:27", "remaining_time": "11:10:22", "throughput": 8484.42, "total_tokens": 434465864} {"current_steps": 426800, "total_steps": 761865, "loss": 2.0158, "lr": 4.0600313790482347e-07, "epoch": 8.403063534878227, "percentage": 56.02, "elapsed_time": "14:13:39", "remaining_time": "11:10:10", "throughput": 8484.48, "total_tokens": 434567000} {"current_steps": 426900, "total_steps": 761865, "loss": 2.0208, "lr": 4.058006415689121e-07, "epoch": 8.40503238762773, "percentage": 56.03, "elapsed_time": "14:13:50", "remaining_time": "11:09:57", "throughput": 8484.53, "total_tokens": 434668168} {"current_steps": 427000, "total_steps": 761865, "loss": 2.0415, "lr": 4.0559816125080733e-07, "epoch": 8.407001240377232, "percentage": 56.05, "elapsed_time": "14:14:02", "remaining_time": "11:09:45", "throughput": 8484.58, "total_tokens": 434769040} {"current_steps": 427100, "total_steps": 761865, "loss": 1.9822, "lr": 4.053956969849389e-07, "epoch": 8.408970093126735, "percentage": 56.06, "elapsed_time": "14:14:13", "remaining_time": "11:09:33", "throughput": 8484.65, "total_tokens": 434870896} {"current_steps": 427200, "total_steps": 761865, "loss": 1.9624, "lr": 4.0519324880573423e-07, "epoch": 8.410938945876238, "percentage": 56.07, "elapsed_time": "14:14:25", "remaining_time": "11:09:20", "throughput": 8484.7, "total_tokens": 434972520} {"current_steps": 427300, "total_steps": 761865, "loss": 1.9915, "lr": 4.049908167476181e-07, "epoch": 8.41290779862574, "percentage": 56.09, "elapsed_time": "14:14:37", "remaining_time": "11:09:08", "throughput": 8484.77, "total_tokens": 435074920} {"current_steps": 427400, "total_steps": 761865, "loss": 1.9835, "lr": 4.0478840084501207e-07, "epoch": 8.414876651375243, "percentage": 56.1, "elapsed_time": "14:14:48", "remaining_time": "11:08:56", "throughput": 8484.83, "total_tokens": 435177320} {"current_steps": 427500, "total_steps": 761865, "loss": 1.9841, "lr": 4.0458600113233566e-07, "epoch": 8.416845504124746, "percentage": 56.11, "elapsed_time": "14:15:00", "remaining_time": "11:08:44", "throughput": 8484.89, "total_tokens": 435279088} {"current_steps": 427600, "total_steps": 761865, "loss": 1.9733, "lr": 4.043836176440048e-07, "epoch": 8.418814356874249, "percentage": 56.13, "elapsed_time": "14:15:12", "remaining_time": "11:08:31", "throughput": 8484.95, "total_tokens": 435381488} {"current_steps": 427700, "total_steps": 761865, "loss": 2.0083, "lr": 4.041812504144334e-07, "epoch": 8.420783209623753, "percentage": 56.14, "elapsed_time": "14:15:23", "remaining_time": "11:08:19", "throughput": 8485.01, "total_tokens": 435483144} {"current_steps": 427800, "total_steps": 761865, "loss": 1.9969, "lr": 4.039788994780321e-07, "epoch": 8.422752062373256, "percentage": 56.15, "elapsed_time": "14:15:35", "remaining_time": "11:08:07", "throughput": 8485.06, "total_tokens": 435584784} {"current_steps": 427900, "total_steps": 761865, "loss": 1.9947, "lr": 4.037765648692092e-07, "epoch": 8.424720915122759, "percentage": 56.16, "elapsed_time": "14:15:47", "remaining_time": "11:07:55", "throughput": 8485.11, "total_tokens": 435685320} {"current_steps": 428000, "total_steps": 761865, "loss": 2.0373, "lr": 4.0357424662236974e-07, "epoch": 8.426689767872261, "percentage": 56.18, "elapsed_time": "14:15:58", "remaining_time": "11:07:42", "throughput": 8485.16, "total_tokens": 435785712} {"current_steps": 428100, "total_steps": 761865, "loss": 2.0173, "lr": 4.0337194477191643e-07, "epoch": 8.428658620621764, "percentage": 56.19, "elapsed_time": "14:16:10", "remaining_time": "11:07:30", "throughput": 8485.2, "total_tokens": 435886168} {"current_steps": 428200, "total_steps": 761865, "loss": 1.9716, "lr": 4.031696593522488e-07, "epoch": 8.430627473371267, "percentage": 56.2, "elapsed_time": "14:16:21", "remaining_time": "11:07:18", "throughput": 8485.27, "total_tokens": 435988568} {"current_steps": 428300, "total_steps": 761865, "loss": 1.9326, "lr": 4.0296739039776394e-07, "epoch": 8.43259632612077, "percentage": 56.22, "elapsed_time": "14:16:33", "remaining_time": "11:07:05", "throughput": 8485.33, "total_tokens": 436090968} {"current_steps": 428400, "total_steps": 761865, "loss": 1.9479, "lr": 4.02765137942856e-07, "epoch": 8.434565178870272, "percentage": 56.23, "elapsed_time": "14:16:45", "remaining_time": "11:06:53", "throughput": 8485.38, "total_tokens": 436191576} {"current_steps": 428500, "total_steps": 761865, "loss": 2.0043, "lr": 4.0256290202191615e-07, "epoch": 8.436534031619775, "percentage": 56.24, "elapsed_time": "14:16:56", "remaining_time": "11:06:41", "throughput": 8485.44, "total_tokens": 436293976} {"current_steps": 428600, "total_steps": 761865, "loss": 1.9447, "lr": 4.023606826693331e-07, "epoch": 8.438502884369278, "percentage": 56.26, "elapsed_time": "14:17:08", "remaining_time": "11:06:29", "throughput": 8485.51, "total_tokens": 436396376} {"current_steps": 428700, "total_steps": 761865, "loss": 1.969, "lr": 4.0215847991949226e-07, "epoch": 8.44047173711878, "percentage": 56.27, "elapsed_time": "14:17:20", "remaining_time": "11:06:16", "throughput": 8485.57, "total_tokens": 436498776} {"current_steps": 428800, "total_steps": 761865, "loss": 1.9825, "lr": 4.0195629380677695e-07, "epoch": 8.442440589868283, "percentage": 56.28, "elapsed_time": "14:17:31", "remaining_time": "11:06:04", "throughput": 8485.62, "total_tokens": 436599592} {"current_steps": 428900, "total_steps": 761865, "loss": 2.0007, "lr": 4.017541243655666e-07, "epoch": 8.444409442617786, "percentage": 56.3, "elapsed_time": "14:17:43", "remaining_time": "11:05:52", "throughput": 8485.68, "total_tokens": 436701992} {"current_steps": 429000, "total_steps": 761865, "loss": 1.9881, "lr": 4.015519716302391e-07, "epoch": 8.446378295367289, "percentage": 56.31, "elapsed_time": "14:17:55", "remaining_time": "11:05:39", "throughput": 8485.75, "total_tokens": 436804392} {"current_steps": 429100, "total_steps": 761865, "loss": 1.9946, "lr": 4.013498356351681e-07, "epoch": 8.448347148116792, "percentage": 56.32, "elapsed_time": "14:18:06", "remaining_time": "11:05:27", "throughput": 8485.8, "total_tokens": 436905456} {"current_steps": 429200, "total_steps": 761865, "loss": 1.9784, "lr": 4.011477164147257e-07, "epoch": 8.450316000866295, "percentage": 56.34, "elapsed_time": "14:18:18", "remaining_time": "11:05:15", "throughput": 8485.85, "total_tokens": 437006192} {"current_steps": 429300, "total_steps": 761865, "loss": 1.9949, "lr": 4.009456140032804e-07, "epoch": 8.452284853615797, "percentage": 56.35, "elapsed_time": "14:18:29", "remaining_time": "11:05:03", "throughput": 8485.92, "total_tokens": 437108592} {"current_steps": 429400, "total_steps": 761865, "loss": 2.0295, "lr": 4.0074352843519787e-07, "epoch": 8.4542537063653, "percentage": 56.36, "elapsed_time": "14:18:41", "remaining_time": "11:04:50", "throughput": 8485.96, "total_tokens": 437208776} {"current_steps": 429500, "total_steps": 761865, "loss": 1.9856, "lr": 4.0054145974484134e-07, "epoch": 8.456222559114805, "percentage": 56.37, "elapsed_time": "14:18:53", "remaining_time": "11:04:38", "throughput": 8486.01, "total_tokens": 437309936} {"current_steps": 429600, "total_steps": 761865, "loss": 1.9485, "lr": 4.003394079665705e-07, "epoch": 8.458191411864307, "percentage": 56.39, "elapsed_time": "14:19:04", "remaining_time": "11:04:26", "throughput": 8486.07, "total_tokens": 437412104} {"current_steps": 429700, "total_steps": 761865, "loss": 2.0115, "lr": 4.0013737313474297e-07, "epoch": 8.46016026461381, "percentage": 56.4, "elapsed_time": "14:19:16", "remaining_time": "11:04:13", "throughput": 8486.13, "total_tokens": 437513832} {"current_steps": 429800, "total_steps": 761865, "loss": 1.9659, "lr": 3.999353552837127e-07, "epoch": 8.462129117363313, "percentage": 56.41, "elapsed_time": "14:19:27", "remaining_time": "11:04:01", "throughput": 8486.19, "total_tokens": 437615416} {"current_steps": 429900, "total_steps": 761865, "loss": 1.9783, "lr": 3.997333544478314e-07, "epoch": 8.464097970112816, "percentage": 56.43, "elapsed_time": "14:19:39", "remaining_time": "11:03:49", "throughput": 8486.25, "total_tokens": 437717816} {"current_steps": 430000, "total_steps": 761865, "loss": 1.9966, "lr": 3.9953137066144736e-07, "epoch": 8.466066822862318, "percentage": 56.44, "elapsed_time": "14:19:51", "remaining_time": "11:03:37", "throughput": 8486.32, "total_tokens": 437820216} {"current_steps": 430100, "total_steps": 761865, "loss": 1.9953, "lr": 3.993294039589065e-07, "epoch": 8.468035675611821, "percentage": 56.45, "elapsed_time": "14:20:03", "remaining_time": "11:03:25", "throughput": 8486.28, "total_tokens": 437921048} {"current_steps": 430200, "total_steps": 761865, "loss": 1.9526, "lr": 3.991274543745512e-07, "epoch": 8.470004528361324, "percentage": 56.47, "elapsed_time": "14:20:15", "remaining_time": "11:03:12", "throughput": 8486.34, "total_tokens": 438023448} {"current_steps": 430300, "total_steps": 761865, "loss": 1.9768, "lr": 3.9892552194272156e-07, "epoch": 8.471973381110827, "percentage": 56.48, "elapsed_time": "14:20:26", "remaining_time": "11:03:00", "throughput": 8486.4, "total_tokens": 438125848} {"current_steps": 430400, "total_steps": 761865, "loss": 2.0123, "lr": 3.987236066977545e-07, "epoch": 8.47394223386033, "percentage": 56.49, "elapsed_time": "14:20:38", "remaining_time": "11:02:48", "throughput": 8486.46, "total_tokens": 438227656} {"current_steps": 430500, "total_steps": 761865, "loss": 2.0069, "lr": 3.9852170867398385e-07, "epoch": 8.475911086609832, "percentage": 56.51, "elapsed_time": "14:20:50", "remaining_time": "11:02:36", "throughput": 8486.52, "total_tokens": 438329464} {"current_steps": 430600, "total_steps": 761865, "loss": 1.9812, "lr": 3.9831982790574074e-07, "epoch": 8.477879939359335, "percentage": 56.52, "elapsed_time": "14:21:01", "remaining_time": "11:02:23", "throughput": 8486.58, "total_tokens": 438430968} {"current_steps": 430700, "total_steps": 761865, "loss": 1.9583, "lr": 3.9811796442735326e-07, "epoch": 8.479848792108838, "percentage": 56.53, "elapsed_time": "14:21:13", "remaining_time": "11:02:11", "throughput": 8486.64, "total_tokens": 438533368} {"current_steps": 430800, "total_steps": 761865, "loss": 2.0006, "lr": 3.979161182731467e-07, "epoch": 8.48181764485834, "percentage": 56.55, "elapsed_time": "14:21:25", "remaining_time": "11:01:59", "throughput": 8486.7, "total_tokens": 438635328} {"current_steps": 430900, "total_steps": 761865, "loss": 2.0123, "lr": 3.977142894774431e-07, "epoch": 8.483786497607843, "percentage": 56.56, "elapsed_time": "14:21:36", "remaining_time": "11:01:47", "throughput": 8486.76, "total_tokens": 438737728} {"current_steps": 431000, "total_steps": 761865, "loss": 1.9989, "lr": 3.97512478074562e-07, "epoch": 8.485755350357346, "percentage": 56.57, "elapsed_time": "14:21:48", "remaining_time": "11:01:34", "throughput": 8486.82, "total_tokens": 438840128} {"current_steps": 431100, "total_steps": 761865, "loss": 1.9562, "lr": 3.973106840988194e-07, "epoch": 8.48772420310685, "percentage": 56.58, "elapsed_time": "14:22:00", "remaining_time": "11:01:22", "throughput": 8486.88, "total_tokens": 438942184} {"current_steps": 431200, "total_steps": 761865, "loss": 1.9784, "lr": 3.97108907584529e-07, "epoch": 8.489693055856353, "percentage": 56.6, "elapsed_time": "14:22:11", "remaining_time": "11:01:10", "throughput": 8486.95, "total_tokens": 439044584} {"current_steps": 431300, "total_steps": 761865, "loss": 1.9849, "lr": 3.969071485660009e-07, "epoch": 8.491661908605856, "percentage": 56.61, "elapsed_time": "14:22:23", "remaining_time": "11:00:58", "throughput": 8487.01, "total_tokens": 439146984} {"current_steps": 431400, "total_steps": 761865, "loss": 2.0059, "lr": 3.967054070775426e-07, "epoch": 8.493630761355359, "percentage": 56.62, "elapsed_time": "14:22:35", "remaining_time": "11:00:45", "throughput": 8487.08, "total_tokens": 439249384} {"current_steps": 431500, "total_steps": 761865, "loss": 1.9808, "lr": 3.965036831534589e-07, "epoch": 8.495599614104862, "percentage": 56.64, "elapsed_time": "14:22:46", "remaining_time": "11:00:33", "throughput": 8487.14, "total_tokens": 439351784} {"current_steps": 431600, "total_steps": 761865, "loss": 1.9865, "lr": 3.963019768280507e-07, "epoch": 8.497568466854364, "percentage": 56.65, "elapsed_time": "14:22:58", "remaining_time": "11:00:21", "throughput": 8487.2, "total_tokens": 439454184} {"current_steps": 431700, "total_steps": 761865, "loss": 1.9583, "lr": 3.9610028813561696e-07, "epoch": 8.499537319603867, "percentage": 56.66, "elapsed_time": "14:23:10", "remaining_time": "11:00:09", "throughput": 8487.26, "total_tokens": 439556088} {"current_steps": 431800, "total_steps": 761865, "loss": 1.9762, "lr": 3.9589861711045257e-07, "epoch": 8.50150617235337, "percentage": 56.68, "elapsed_time": "14:23:21", "remaining_time": "10:59:56", "throughput": 8487.32, "total_tokens": 439657728} {"current_steps": 431900, "total_steps": 761865, "loss": 1.9874, "lr": 3.956969637868507e-07, "epoch": 8.503475025102873, "percentage": 56.69, "elapsed_time": "14:23:33", "remaining_time": "10:59:44", "throughput": 8487.39, "total_tokens": 439760128} {"current_steps": 432000, "total_steps": 761865, "loss": 1.9648, "lr": 3.954953281991e-07, "epoch": 8.505443877852375, "percentage": 56.7, "elapsed_time": "14:23:45", "remaining_time": "10:59:32", "throughput": 8487.45, "total_tokens": 439862528} {"current_steps": 432100, "total_steps": 761865, "loss": 1.9935, "lr": 3.9529371038148765e-07, "epoch": 8.507412730601878, "percentage": 56.72, "elapsed_time": "14:23:56", "remaining_time": "10:59:20", "throughput": 8487.51, "total_tokens": 439964928} {"current_steps": 432200, "total_steps": 761865, "loss": 1.9885, "lr": 3.9509211036829644e-07, "epoch": 8.50938158335138, "percentage": 56.73, "elapsed_time": "14:24:08", "remaining_time": "10:59:07", "throughput": 8487.58, "total_tokens": 440067328} {"current_steps": 432300, "total_steps": 761865, "loss": 1.9709, "lr": 3.948905281938071e-07, "epoch": 8.511350436100884, "percentage": 56.74, "elapsed_time": "14:24:20", "remaining_time": "10:58:55", "throughput": 8487.63, "total_tokens": 440168432} {"current_steps": 432400, "total_steps": 761865, "loss": 2.0214, "lr": 3.94688963892297e-07, "epoch": 8.513319288850386, "percentage": 56.76, "elapsed_time": "14:24:31", "remaining_time": "10:58:43", "throughput": 8487.68, "total_tokens": 440270032} {"current_steps": 432500, "total_steps": 761865, "loss": 1.9927, "lr": 3.9448741749804027e-07, "epoch": 8.51528814159989, "percentage": 56.77, "elapsed_time": "14:24:43", "remaining_time": "10:58:31", "throughput": 8487.73, "total_tokens": 440371184} {"current_steps": 432600, "total_steps": 761865, "loss": 2.0034, "lr": 3.9428588904530836e-07, "epoch": 8.517256994349392, "percentage": 56.78, "elapsed_time": "14:24:54", "remaining_time": "10:58:18", "throughput": 8487.8, "total_tokens": 440473584} {"current_steps": 432700, "total_steps": 761865, "loss": 1.9497, "lr": 3.940843785683692e-07, "epoch": 8.519225847098895, "percentage": 56.79, "elapsed_time": "14:25:06", "remaining_time": "10:58:06", "throughput": 8487.85, "total_tokens": 440575384} {"current_steps": 432800, "total_steps": 761865, "loss": 1.9514, "lr": 3.9388288610148833e-07, "epoch": 8.5211946998484, "percentage": 56.81, "elapsed_time": "14:25:18", "remaining_time": "10:57:54", "throughput": 8487.91, "total_tokens": 440677712} {"current_steps": 432900, "total_steps": 761865, "loss": 1.9723, "lr": 3.9368141167892756e-07, "epoch": 8.523163552597902, "percentage": 56.82, "elapsed_time": "14:25:29", "remaining_time": "10:57:42", "throughput": 8487.97, "total_tokens": 440779680} {"current_steps": 433000, "total_steps": 761865, "loss": 1.9724, "lr": 3.9347995533494605e-07, "epoch": 8.525132405347405, "percentage": 56.83, "elapsed_time": "14:25:41", "remaining_time": "10:57:29", "throughput": 8488.03, "total_tokens": 440880920} {"current_steps": 433100, "total_steps": 761865, "loss": 1.9915, "lr": 3.932785171037996e-07, "epoch": 8.527101258096907, "percentage": 56.85, "elapsed_time": "14:25:53", "remaining_time": "10:57:17", "throughput": 8488.09, "total_tokens": 440983320} {"current_steps": 433200, "total_steps": 761865, "loss": 1.9952, "lr": 3.9307709701974135e-07, "epoch": 8.52907011084641, "percentage": 56.86, "elapsed_time": "14:26:04", "remaining_time": "10:57:05", "throughput": 8488.13, "total_tokens": 441082520} {"current_steps": 433300, "total_steps": 761865, "loss": 1.9617, "lr": 3.928756951170208e-07, "epoch": 8.531038963595913, "percentage": 56.87, "elapsed_time": "14:26:16", "remaining_time": "10:56:52", "throughput": 8488.19, "total_tokens": 441184920} {"current_steps": 433400, "total_steps": 761865, "loss": 1.9576, "lr": 3.9267431142988473e-07, "epoch": 8.533007816345416, "percentage": 56.89, "elapsed_time": "14:26:27", "remaining_time": "10:56:40", "throughput": 8488.25, "total_tokens": 441286760} {"current_steps": 433500, "total_steps": 761865, "loss": 1.996, "lr": 3.9247294599257683e-07, "epoch": 8.534976669094918, "percentage": 56.9, "elapsed_time": "14:26:39", "remaining_time": "10:56:28", "throughput": 8488.31, "total_tokens": 441389160} {"current_steps": 433600, "total_steps": 761865, "loss": 1.9503, "lr": 3.922715988393375e-07, "epoch": 8.536945521844421, "percentage": 56.91, "elapsed_time": "14:26:51", "remaining_time": "10:56:16", "throughput": 8488.38, "total_tokens": 441491560} {"current_steps": 433700, "total_steps": 761865, "loss": 1.9922, "lr": 3.9207027000440427e-07, "epoch": 8.538914374593924, "percentage": 56.93, "elapsed_time": "14:27:02", "remaining_time": "10:56:03", "throughput": 8488.44, "total_tokens": 441593128} {"current_steps": 433800, "total_steps": 761865, "loss": 1.9514, "lr": 3.918689595220112e-07, "epoch": 8.540883227343427, "percentage": 56.94, "elapsed_time": "14:27:14", "remaining_time": "10:55:51", "throughput": 8488.49, "total_tokens": 441694936} {"current_steps": 433900, "total_steps": 761865, "loss": 1.9915, "lr": 3.916676674263897e-07, "epoch": 8.54285208009293, "percentage": 56.95, "elapsed_time": "14:27:26", "remaining_time": "10:55:39", "throughput": 8488.56, "total_tokens": 441797336} {"current_steps": 434000, "total_steps": 761865, "loss": 2.0036, "lr": 3.914663937517674e-07, "epoch": 8.544820932842432, "percentage": 56.97, "elapsed_time": "14:27:37", "remaining_time": "10:55:27", "throughput": 8488.61, "total_tokens": 441899256} {"current_steps": 434100, "total_steps": 761865, "loss": 1.9632, "lr": 3.9126513853236966e-07, "epoch": 8.546789785591935, "percentage": 56.98, "elapsed_time": "14:27:49", "remaining_time": "10:55:14", "throughput": 8488.67, "total_tokens": 442001088} {"current_steps": 434200, "total_steps": 761865, "loss": 1.9731, "lr": 3.9106390180241784e-07, "epoch": 8.548758638341438, "percentage": 56.99, "elapsed_time": "14:28:01", "remaining_time": "10:55:02", "throughput": 8488.73, "total_tokens": 442102624} {"current_steps": 434300, "total_steps": 761865, "loss": 2.0017, "lr": 3.908626835961306e-07, "epoch": 8.55072749109094, "percentage": 57.0, "elapsed_time": "14:28:12", "remaining_time": "10:54:50", "throughput": 8488.78, "total_tokens": 442204096} {"current_steps": 434400, "total_steps": 761865, "loss": 1.9831, "lr": 3.906614839477238e-07, "epoch": 8.552696343840445, "percentage": 57.02, "elapsed_time": "14:28:24", "remaining_time": "10:54:37", "throughput": 8488.83, "total_tokens": 442304768} {"current_steps": 434500, "total_steps": 761865, "loss": 2.0015, "lr": 3.9046030289140916e-07, "epoch": 8.554665196589948, "percentage": 57.03, "elapsed_time": "14:28:35", "remaining_time": "10:54:25", "throughput": 8488.89, "total_tokens": 442407168} {"current_steps": 434600, "total_steps": 761865, "loss": 2.0227, "lr": 3.902591404613965e-07, "epoch": 8.55663404933945, "percentage": 57.04, "elapsed_time": "14:28:47", "remaining_time": "10:54:13", "throughput": 8488.94, "total_tokens": 442507768} {"current_steps": 434700, "total_steps": 761865, "loss": 2.0247, "lr": 3.90057996691891e-07, "epoch": 8.558602902088953, "percentage": 57.06, "elapsed_time": "14:28:59", "remaining_time": "10:54:01", "throughput": 8488.98, "total_tokens": 442608272} {"current_steps": 434800, "total_steps": 761865, "loss": 1.963, "lr": 3.898568716170962e-07, "epoch": 8.560571754838456, "percentage": 57.07, "elapsed_time": "14:29:10", "remaining_time": "10:53:48", "throughput": 8489.04, "total_tokens": 442710216} {"current_steps": 434900, "total_steps": 761865, "loss": 1.9748, "lr": 3.8965576527121106e-07, "epoch": 8.562540607587959, "percentage": 57.08, "elapsed_time": "14:29:22", "remaining_time": "10:53:36", "throughput": 8489.1, "total_tokens": 442811976} {"current_steps": 435000, "total_steps": 761865, "loss": 2.0141, "lr": 3.894546776884327e-07, "epoch": 8.564509460337462, "percentage": 57.1, "elapsed_time": "14:29:34", "remaining_time": "10:53:24", "throughput": 8489.15, "total_tokens": 442913288} {"current_steps": 435100, "total_steps": 761865, "loss": 1.9889, "lr": 3.892536089029537e-07, "epoch": 8.566478313086964, "percentage": 57.11, "elapsed_time": "14:29:46", "remaining_time": "10:53:12", "throughput": 8489.13, "total_tokens": 443015688} {"current_steps": 435200, "total_steps": 761865, "loss": 1.9583, "lr": 3.8905255894896475e-07, "epoch": 8.568447165836467, "percentage": 57.12, "elapsed_time": "14:29:57", "remaining_time": "10:53:00", "throughput": 8489.19, "total_tokens": 443118088} {"current_steps": 435300, "total_steps": 761865, "loss": 2.046, "lr": 3.8885152786065204e-07, "epoch": 8.57041601858597, "percentage": 57.14, "elapsed_time": "14:30:09", "remaining_time": "10:52:47", "throughput": 8489.24, "total_tokens": 443219720} {"current_steps": 435400, "total_steps": 761865, "loss": 1.9642, "lr": 3.886505156721996e-07, "epoch": 8.572384871335473, "percentage": 57.15, "elapsed_time": "14:30:21", "remaining_time": "10:52:35", "throughput": 8489.3, "total_tokens": 443322120} {"current_steps": 435500, "total_steps": 761865, "loss": 1.9432, "lr": 3.8844952241778807e-07, "epoch": 8.574353724084975, "percentage": 57.16, "elapsed_time": "14:30:32", "remaining_time": "10:52:23", "throughput": 8489.36, "total_tokens": 443424432} {"current_steps": 435600, "total_steps": 761865, "loss": 1.9411, "lr": 3.882485481315941e-07, "epoch": 8.576322576834478, "percentage": 57.18, "elapsed_time": "14:30:44", "remaining_time": "10:52:11", "throughput": 8489.42, "total_tokens": 443526096} {"current_steps": 435700, "total_steps": 761865, "loss": 1.964, "lr": 3.880475928477922e-07, "epoch": 8.578291429583981, "percentage": 57.19, "elapsed_time": "14:30:56", "remaining_time": "10:51:59", "throughput": 8489.48, "total_tokens": 443628200} {"current_steps": 435800, "total_steps": 761865, "loss": 1.9801, "lr": 3.878466566005528e-07, "epoch": 8.580260282333484, "percentage": 57.2, "elapsed_time": "14:31:07", "remaining_time": "10:51:46", "throughput": 8489.54, "total_tokens": 443730600} {"current_steps": 435900, "total_steps": 761865, "loss": 1.9669, "lr": 3.876457394240435e-07, "epoch": 8.582229135082986, "percentage": 57.21, "elapsed_time": "14:31:19", "remaining_time": "10:51:34", "throughput": 8489.59, "total_tokens": 443832128} {"current_steps": 436000, "total_steps": 761865, "loss": 1.978, "lr": 3.874448413524285e-07, "epoch": 8.58419798783249, "percentage": 57.23, "elapsed_time": "14:31:31", "remaining_time": "10:51:22", "throughput": 8489.64, "total_tokens": 443932944} {"current_steps": 436100, "total_steps": 761865, "loss": 2.0172, "lr": 3.87243962419869e-07, "epoch": 8.586166840581992, "percentage": 57.24, "elapsed_time": "14:31:42", "remaining_time": "10:51:09", "throughput": 8489.7, "total_tokens": 444035344} {"current_steps": 436200, "total_steps": 761865, "loss": 1.9877, "lr": 3.8704310266052257e-07, "epoch": 8.588135693331497, "percentage": 57.25, "elapsed_time": "14:31:54", "remaining_time": "10:50:57", "throughput": 8489.77, "total_tokens": 444137744} {"current_steps": 436300, "total_steps": 761865, "loss": 1.9757, "lr": 3.868422621085439e-07, "epoch": 8.590104546081, "percentage": 57.27, "elapsed_time": "14:32:06", "remaining_time": "10:50:45", "throughput": 8489.83, "total_tokens": 444240144} {"current_steps": 436400, "total_steps": 761865, "loss": 1.9651, "lr": 3.866414407980841e-07, "epoch": 8.592073398830502, "percentage": 57.28, "elapsed_time": "14:32:17", "remaining_time": "10:50:33", "throughput": 8489.89, "total_tokens": 444342008} {"current_steps": 436500, "total_steps": 761865, "loss": 1.9837, "lr": 3.8644063876329114e-07, "epoch": 8.594042251580005, "percentage": 57.29, "elapsed_time": "14:32:29", "remaining_time": "10:50:20", "throughput": 8489.93, "total_tokens": 444442616} {"current_steps": 436600, "total_steps": 761865, "loss": 1.9728, "lr": 3.862398560383098e-07, "epoch": 8.596011104329508, "percentage": 57.31, "elapsed_time": "14:32:40", "remaining_time": "10:50:08", "throughput": 8489.99, "total_tokens": 444543928} {"current_steps": 436700, "total_steps": 761865, "loss": 1.9836, "lr": 3.860390926572814e-07, "epoch": 8.59797995707901, "percentage": 57.32, "elapsed_time": "14:32:52", "remaining_time": "10:49:56", "throughput": 8490.05, "total_tokens": 444646328} {"current_steps": 436800, "total_steps": 761865, "loss": 1.9898, "lr": 3.858383486543442e-07, "epoch": 8.599948809828513, "percentage": 57.33, "elapsed_time": "14:33:04", "remaining_time": "10:49:44", "throughput": 8490.11, "total_tokens": 444748176} {"current_steps": 436900, "total_steps": 761865, "loss": 1.9241, "lr": 3.8563762406363284e-07, "epoch": 8.601917662578016, "percentage": 57.35, "elapsed_time": "14:33:15", "remaining_time": "10:49:31", "throughput": 8490.16, "total_tokens": 444849872} {"current_steps": 437000, "total_steps": 761865, "loss": 2.0357, "lr": 3.8543691891927896e-07, "epoch": 8.603886515327519, "percentage": 57.36, "elapsed_time": "14:33:27", "remaining_time": "10:49:19", "throughput": 8490.21, "total_tokens": 444950808} {"current_steps": 437100, "total_steps": 761865, "loss": 2.007, "lr": 3.852362332554107e-07, "epoch": 8.605855368077021, "percentage": 57.37, "elapsed_time": "14:33:39", "remaining_time": "10:49:07", "throughput": 8490.27, "total_tokens": 445053208} {"current_steps": 437200, "total_steps": 761865, "loss": 1.9548, "lr": 3.8503556710615316e-07, "epoch": 8.607824220826524, "percentage": 57.39, "elapsed_time": "14:33:50", "remaining_time": "10:48:55", "throughput": 8490.33, "total_tokens": 445155040} {"current_steps": 437300, "total_steps": 761865, "loss": 1.9922, "lr": 3.8483492050562747e-07, "epoch": 8.609793073576027, "percentage": 57.4, "elapsed_time": "14:34:02", "remaining_time": "10:48:42", "throughput": 8490.38, "total_tokens": 445256480} {"current_steps": 437400, "total_steps": 761865, "loss": 1.9615, "lr": 3.846342934879524e-07, "epoch": 8.61176192632553, "percentage": 57.41, "elapsed_time": "14:34:14", "remaining_time": "10:48:30", "throughput": 8490.45, "total_tokens": 445358880} {"current_steps": 437500, "total_steps": 761865, "loss": 2.022, "lr": 3.8443368608724274e-07, "epoch": 8.613730779075032, "percentage": 57.42, "elapsed_time": "14:34:25", "remaining_time": "10:48:18", "throughput": 8490.5, "total_tokens": 445460488} {"current_steps": 437600, "total_steps": 761865, "loss": 1.9643, "lr": 3.8423309833761e-07, "epoch": 8.615699631824535, "percentage": 57.44, "elapsed_time": "14:34:37", "remaining_time": "10:48:06", "throughput": 8490.56, "total_tokens": 445562888} {"current_steps": 437700, "total_steps": 761865, "loss": 1.9618, "lr": 3.8403253027316246e-07, "epoch": 8.617668484574038, "percentage": 57.45, "elapsed_time": "14:34:49", "remaining_time": "10:47:53", "throughput": 8490.61, "total_tokens": 445664008} {"current_steps": 437800, "total_steps": 761865, "loss": 2.0324, "lr": 3.8383198192800496e-07, "epoch": 8.619637337323542, "percentage": 57.46, "elapsed_time": "14:35:00", "remaining_time": "10:47:41", "throughput": 8490.68, "total_tokens": 445766408} {"current_steps": 437900, "total_steps": 761865, "loss": 1.9561, "lr": 3.8363145333623924e-07, "epoch": 8.621606190073045, "percentage": 57.48, "elapsed_time": "14:35:12", "remaining_time": "10:47:29", "throughput": 8490.73, "total_tokens": 445868808} {"current_steps": 438000, "total_steps": 761865, "loss": 1.9656, "lr": 3.834309445319633e-07, "epoch": 8.623575042822548, "percentage": 57.49, "elapsed_time": "14:35:24", "remaining_time": "10:47:17", "throughput": 8490.8, "total_tokens": 445971208} {"current_steps": 438100, "total_steps": 761865, "loss": 1.9902, "lr": 3.8323045554927215e-07, "epoch": 8.62554389557205, "percentage": 57.5, "elapsed_time": "14:35:35", "remaining_time": "10:47:04", "throughput": 8490.85, "total_tokens": 446072184} {"current_steps": 438200, "total_steps": 761865, "loss": 1.982, "lr": 3.8302998642225705e-07, "epoch": 8.627512748321553, "percentage": 57.52, "elapsed_time": "14:35:47", "remaining_time": "10:46:52", "throughput": 8490.91, "total_tokens": 446174584} {"current_steps": 438300, "total_steps": 761865, "loss": 1.9624, "lr": 3.828295371850062e-07, "epoch": 8.629481601071056, "percentage": 57.53, "elapsed_time": "14:35:59", "remaining_time": "10:46:40", "throughput": 8490.97, "total_tokens": 446276984} {"current_steps": 438400, "total_steps": 761865, "loss": 1.9954, "lr": 3.826291078716043e-07, "epoch": 8.631450453820559, "percentage": 57.54, "elapsed_time": "14:36:10", "remaining_time": "10:46:28", "throughput": 8491.02, "total_tokens": 446378328} {"current_steps": 438500, "total_steps": 761865, "loss": 1.9833, "lr": 3.8242869851613265e-07, "epoch": 8.633419306570062, "percentage": 57.56, "elapsed_time": "14:36:22", "remaining_time": "10:46:15", "throughput": 8491.08, "total_tokens": 446479984} {"current_steps": 438600, "total_steps": 761865, "loss": 1.9779, "lr": 3.8222830915266923e-07, "epoch": 8.635388159319564, "percentage": 57.57, "elapsed_time": "14:36:33", "remaining_time": "10:46:03", "throughput": 8491.14, "total_tokens": 446582384} {"current_steps": 438700, "total_steps": 761865, "loss": 2.0006, "lr": 3.820279398152884e-07, "epoch": 8.637357012069067, "percentage": 57.58, "elapsed_time": "14:36:45", "remaining_time": "10:45:51", "throughput": 8491.2, "total_tokens": 446684784} {"current_steps": 438800, "total_steps": 761865, "loss": 2.0278, "lr": 3.818275905380615e-07, "epoch": 8.63932586481857, "percentage": 57.6, "elapsed_time": "14:36:57", "remaining_time": "10:45:39", "throughput": 8491.26, "total_tokens": 446787184} {"current_steps": 438900, "total_steps": 761865, "loss": 1.9513, "lr": 3.8162726135505607e-07, "epoch": 8.641294717568073, "percentage": 57.61, "elapsed_time": "14:37:08", "remaining_time": "10:45:27", "throughput": 8491.32, "total_tokens": 446889584} {"current_steps": 439000, "total_steps": 761865, "loss": 1.938, "lr": 3.814269523003365e-07, "epoch": 8.643263570317576, "percentage": 57.62, "elapsed_time": "14:37:20", "remaining_time": "10:45:14", "throughput": 8491.38, "total_tokens": 446991984} {"current_steps": 439100, "total_steps": 761865, "loss": 1.9841, "lr": 3.812266634079635e-07, "epoch": 8.645232423067078, "percentage": 57.63, "elapsed_time": "14:37:32", "remaining_time": "10:45:02", "throughput": 8491.45, "total_tokens": 447094384} {"current_steps": 439200, "total_steps": 761865, "loss": 1.9702, "lr": 3.8102639471199473e-07, "epoch": 8.647201275816581, "percentage": 57.65, "elapsed_time": "14:37:43", "remaining_time": "10:44:50", "throughput": 8491.5, "total_tokens": 447196160} {"current_steps": 439300, "total_steps": 761865, "loss": 2.1175, "lr": 3.808261462464839e-07, "epoch": 8.649170128566084, "percentage": 57.66, "elapsed_time": "14:37:55", "remaining_time": "10:44:38", "throughput": 8491.55, "total_tokens": 447297608} {"current_steps": 439400, "total_steps": 761865, "loss": 1.9412, "lr": 3.8062591804548165e-07, "epoch": 8.651138981315587, "percentage": 57.67, "elapsed_time": "14:38:07", "remaining_time": "10:44:25", "throughput": 8491.61, "total_tokens": 447400008} {"current_steps": 439500, "total_steps": 761865, "loss": 2.0423, "lr": 3.804257101430355e-07, "epoch": 8.653107834065091, "percentage": 57.69, "elapsed_time": "14:38:18", "remaining_time": "10:44:13", "throughput": 8491.67, "total_tokens": 447502024} {"current_steps": 439600, "total_steps": 761865, "loss": 2.0018, "lr": 3.802255225731886e-07, "epoch": 8.655076686814594, "percentage": 57.7, "elapsed_time": "14:38:30", "remaining_time": "10:44:01", "throughput": 8491.73, "total_tokens": 447604424} {"current_steps": 439700, "total_steps": 761865, "loss": 1.998, "lr": 3.800253553699816e-07, "epoch": 8.657045539564097, "percentage": 57.71, "elapsed_time": "14:38:42", "remaining_time": "10:43:49", "throughput": 8491.79, "total_tokens": 447706824} {"current_steps": 439800, "total_steps": 761865, "loss": 2.011, "lr": 3.7982520856745063e-07, "epoch": 8.6590143923136, "percentage": 57.73, "elapsed_time": "14:38:53", "remaining_time": "10:43:36", "throughput": 8491.85, "total_tokens": 447808600} {"current_steps": 439900, "total_steps": 761865, "loss": 1.9868, "lr": 3.7962508219962975e-07, "epoch": 8.660983245063102, "percentage": 57.74, "elapsed_time": "14:39:05", "remaining_time": "10:43:24", "throughput": 8491.9, "total_tokens": 447910184} {"current_steps": 440000, "total_steps": 761865, "loss": 2.0129, "lr": 3.7942497630054803e-07, "epoch": 8.662952097812605, "percentage": 57.75, "elapsed_time": "14:39:17", "remaining_time": "10:43:12", "throughput": 8491.97, "total_tokens": 448012584} {"current_steps": 440100, "total_steps": 761865, "loss": 2.0276, "lr": 3.792248909042324e-07, "epoch": 8.664920950562108, "percentage": 57.77, "elapsed_time": "14:39:29", "remaining_time": "10:43:00", "throughput": 8491.94, "total_tokens": 448114984} {"current_steps": 440200, "total_steps": 761865, "loss": 2.033, "lr": 3.790248260447051e-07, "epoch": 8.66688980331161, "percentage": 57.78, "elapsed_time": "14:39:41", "remaining_time": "10:42:48", "throughput": 8491.99, "total_tokens": 448216312} {"current_steps": 440300, "total_steps": 761865, "loss": 1.9778, "lr": 3.788247817559861e-07, "epoch": 8.668858656061113, "percentage": 57.79, "elapsed_time": "14:39:52", "remaining_time": "10:42:36", "throughput": 8492.04, "total_tokens": 448317328} {"current_steps": 440400, "total_steps": 761865, "loss": 1.9561, "lr": 3.786247580720906e-07, "epoch": 8.670827508810616, "percentage": 57.81, "elapsed_time": "14:40:04", "remaining_time": "10:42:23", "throughput": 8492.09, "total_tokens": 448418960} {"current_steps": 440500, "total_steps": 761865, "loss": 1.9836, "lr": 3.784247550270313e-07, "epoch": 8.672796361560119, "percentage": 57.82, "elapsed_time": "14:40:15", "remaining_time": "10:42:11", "throughput": 8492.15, "total_tokens": 448521360} {"current_steps": 440600, "total_steps": 761865, "loss": 2.0119, "lr": 3.7822477265481725e-07, "epoch": 8.674765214309621, "percentage": 57.83, "elapsed_time": "14:40:27", "remaining_time": "10:41:59", "throughput": 8492.21, "total_tokens": 448623760} {"current_steps": 440700, "total_steps": 761865, "loss": 1.9884, "lr": 3.7802481098945325e-07, "epoch": 8.676734067059124, "percentage": 57.84, "elapsed_time": "14:40:39", "remaining_time": "10:41:47", "throughput": 8492.26, "total_tokens": 448724848} {"current_steps": 440800, "total_steps": 761865, "loss": 1.943, "lr": 3.7782487006494155e-07, "epoch": 8.678702919808627, "percentage": 57.86, "elapsed_time": "14:40:50", "remaining_time": "10:41:34", "throughput": 8492.32, "total_tokens": 448827248} {"current_steps": 440900, "total_steps": 761865, "loss": 2.0372, "lr": 3.776249499152801e-07, "epoch": 8.68067177255813, "percentage": 57.87, "elapsed_time": "14:41:02", "remaining_time": "10:41:22", "throughput": 8492.38, "total_tokens": 448928944} {"current_steps": 441000, "total_steps": 761865, "loss": 1.9563, "lr": 3.774250505744639e-07, "epoch": 8.682640625307632, "percentage": 57.88, "elapsed_time": "14:41:14", "remaining_time": "10:41:10", "throughput": 8492.43, "total_tokens": 449030248} {"current_steps": 441100, "total_steps": 761865, "loss": 2.0016, "lr": 3.7722517207648385e-07, "epoch": 8.684609478057137, "percentage": 57.9, "elapsed_time": "14:41:25", "remaining_time": "10:40:58", "throughput": 8492.48, "total_tokens": 449131240} {"current_steps": 441200, "total_steps": 761865, "loss": 2.0404, "lr": 3.770253144553279e-07, "epoch": 8.68657833080664, "percentage": 57.91, "elapsed_time": "14:41:37", "remaining_time": "10:40:45", "throughput": 8492.54, "total_tokens": 449233192} {"current_steps": 441300, "total_steps": 761865, "loss": 2.0045, "lr": 3.7682547774497985e-07, "epoch": 8.688547183556143, "percentage": 57.92, "elapsed_time": "14:41:49", "remaining_time": "10:40:33", "throughput": 8492.61, "total_tokens": 449335592} {"current_steps": 441400, "total_steps": 761865, "loss": 1.9987, "lr": 3.766256619794205e-07, "epoch": 8.690516036305645, "percentage": 57.94, "elapsed_time": "14:42:00", "remaining_time": "10:40:21", "throughput": 8492.67, "total_tokens": 449437992} {"current_steps": 441500, "total_steps": 761865, "loss": 2.012, "lr": 3.764258671926267e-07, "epoch": 8.692484889055148, "percentage": 57.95, "elapsed_time": "14:42:12", "remaining_time": "10:40:09", "throughput": 8492.72, "total_tokens": 449538968} {"current_steps": 441600, "total_steps": 761865, "loss": 1.9857, "lr": 3.762260934185719e-07, "epoch": 8.69445374180465, "percentage": 57.96, "elapsed_time": "14:42:23", "remaining_time": "10:39:56", "throughput": 8492.77, "total_tokens": 449640816} {"current_steps": 441700, "total_steps": 761865, "loss": 1.9827, "lr": 3.760263406912261e-07, "epoch": 8.696422594554154, "percentage": 57.98, "elapsed_time": "14:42:35", "remaining_time": "10:39:44", "throughput": 8492.82, "total_tokens": 449742352} {"current_steps": 441800, "total_steps": 761865, "loss": 1.9565, "lr": 3.758266090445553e-07, "epoch": 8.698391447303656, "percentage": 57.99, "elapsed_time": "14:42:47", "remaining_time": "10:39:32", "throughput": 8492.88, "total_tokens": 449844104} {"current_steps": 441900, "total_steps": 761865, "loss": 1.9257, "lr": 3.7562689851252233e-07, "epoch": 8.700360300053159, "percentage": 58.0, "elapsed_time": "14:42:58", "remaining_time": "10:39:20", "throughput": 8492.94, "total_tokens": 449946504} {"current_steps": 442000, "total_steps": 761865, "loss": 1.9943, "lr": 3.754272091290862e-07, "epoch": 8.702329152802662, "percentage": 58.02, "elapsed_time": "14:43:10", "remaining_time": "10:39:07", "throughput": 8492.99, "total_tokens": 450047648} {"current_steps": 442100, "total_steps": 761865, "loss": 1.9611, "lr": 3.7522754092820256e-07, "epoch": 8.704298005552165, "percentage": 58.03, "elapsed_time": "14:43:22", "remaining_time": "10:38:55", "throughput": 8493.05, "total_tokens": 450149208} {"current_steps": 442200, "total_steps": 761865, "loss": 1.9854, "lr": 3.7502789394382316e-07, "epoch": 8.706266858301667, "percentage": 58.04, "elapsed_time": "14:43:33", "remaining_time": "10:38:43", "throughput": 8493.11, "total_tokens": 450251608} {"current_steps": 442300, "total_steps": 761865, "loss": 1.9714, "lr": 3.748282682098964e-07, "epoch": 8.70823571105117, "percentage": 58.05, "elapsed_time": "14:43:45", "remaining_time": "10:38:31", "throughput": 8493.17, "total_tokens": 450354008} {"current_steps": 442400, "total_steps": 761865, "loss": 1.9278, "lr": 3.7462866376036674e-07, "epoch": 8.710204563800673, "percentage": 58.07, "elapsed_time": "14:43:57", "remaining_time": "10:38:19", "throughput": 8493.23, "total_tokens": 450456408} {"current_steps": 442500, "total_steps": 761865, "loss": 1.9564, "lr": 3.7442908062917533e-07, "epoch": 8.712173416550176, "percentage": 58.08, "elapsed_time": "14:44:08", "remaining_time": "10:38:06", "throughput": 8493.29, "total_tokens": 450558808} {"current_steps": 442600, "total_steps": 761865, "loss": 1.9451, "lr": 3.7422951885025986e-07, "epoch": 8.714142269299678, "percentage": 58.09, "elapsed_time": "14:44:20", "remaining_time": "10:37:54", "throughput": 8493.35, "total_tokens": 450661208} {"current_steps": 442700, "total_steps": 761865, "loss": 2.01, "lr": 3.740299784575537e-07, "epoch": 8.716111122049181, "percentage": 58.11, "elapsed_time": "14:44:32", "remaining_time": "10:37:42", "throughput": 8493.4, "total_tokens": 450763064} {"current_steps": 442800, "total_steps": 761865, "loss": 1.9864, "lr": 3.7383045948498754e-07, "epoch": 8.718079974798684, "percentage": 58.12, "elapsed_time": "14:44:43", "remaining_time": "10:37:30", "throughput": 8493.46, "total_tokens": 450865464} {"current_steps": 442900, "total_steps": 761865, "loss": 1.9767, "lr": 3.7363096196648723e-07, "epoch": 8.720048827548188, "percentage": 58.13, "elapsed_time": "14:44:55", "remaining_time": "10:37:17", "throughput": 8493.52, "total_tokens": 450967864} {"current_steps": 443000, "total_steps": 761865, "loss": 1.9688, "lr": 3.734314859359763e-07, "epoch": 8.722017680297691, "percentage": 58.15, "elapsed_time": "14:45:07", "remaining_time": "10:37:05", "throughput": 8493.58, "total_tokens": 451069624} {"current_steps": 443100, "total_steps": 761865, "loss": 1.9957, "lr": 3.7323203142737336e-07, "epoch": 8.723986533047194, "percentage": 58.16, "elapsed_time": "14:45:18", "remaining_time": "10:36:53", "throughput": 8493.63, "total_tokens": 451170392} {"current_steps": 443200, "total_steps": 761865, "loss": 1.9405, "lr": 3.7303259847459457e-07, "epoch": 8.725955385796697, "percentage": 58.17, "elapsed_time": "14:45:30", "remaining_time": "10:36:41", "throughput": 8493.69, "total_tokens": 451272792} {"current_steps": 443300, "total_steps": 761865, "loss": 2.0114, "lr": 3.728331871115512e-07, "epoch": 8.7279242385462, "percentage": 58.19, "elapsed_time": "14:45:42", "remaining_time": "10:36:29", "throughput": 8493.75, "total_tokens": 451375192} {"current_steps": 443400, "total_steps": 761865, "loss": 1.9643, "lr": 3.726337973721521e-07, "epoch": 8.729893091295702, "percentage": 58.2, "elapsed_time": "14:45:53", "remaining_time": "10:36:16", "throughput": 8493.81, "total_tokens": 451477040} {"current_steps": 443500, "total_steps": 761865, "loss": 1.957, "lr": 3.724344292903012e-07, "epoch": 8.731861944045205, "percentage": 58.21, "elapsed_time": "14:46:05", "remaining_time": "10:36:04", "throughput": 8493.86, "total_tokens": 451579440} {"current_steps": 443600, "total_steps": 761865, "loss": 1.9845, "lr": 3.722350828998998e-07, "epoch": 8.733830796794708, "percentage": 58.23, "elapsed_time": "14:46:17", "remaining_time": "10:35:52", "throughput": 8493.92, "total_tokens": 451681840} {"current_steps": 443700, "total_steps": 761865, "loss": 2.0014, "lr": 3.7203575823484497e-07, "epoch": 8.73579964954421, "percentage": 58.24, "elapsed_time": "14:46:28", "remaining_time": "10:35:40", "throughput": 8493.97, "total_tokens": 451782536} {"current_steps": 443800, "total_steps": 761865, "loss": 2.0083, "lr": 3.718364553290301e-07, "epoch": 8.737768502293713, "percentage": 58.25, "elapsed_time": "14:46:40", "remaining_time": "10:35:27", "throughput": 8494.01, "total_tokens": 451884344} {"current_steps": 443900, "total_steps": 761865, "loss": 1.9539, "lr": 3.716371742163451e-07, "epoch": 8.739737355043216, "percentage": 58.26, "elapsed_time": "14:46:52", "remaining_time": "10:35:15", "throughput": 8494.06, "total_tokens": 451986744} {"current_steps": 444000, "total_steps": 761865, "loss": 2.0239, "lr": 3.714379149306758e-07, "epoch": 8.741706207792719, "percentage": 58.28, "elapsed_time": "14:47:03", "remaining_time": "10:35:03", "throughput": 8494.09, "total_tokens": 452088856} {"current_steps": 444100, "total_steps": 761865, "loss": 1.9747, "lr": 3.7123867750590493e-07, "epoch": 8.743675060542222, "percentage": 58.29, "elapsed_time": "14:47:15", "remaining_time": "10:34:51", "throughput": 8494.12, "total_tokens": 452189624} {"current_steps": 444200, "total_steps": 761865, "loss": 1.9705, "lr": 3.7103946197591073e-07, "epoch": 8.745643913291724, "percentage": 58.3, "elapsed_time": "14:47:27", "remaining_time": "10:34:39", "throughput": 8494.16, "total_tokens": 452291248} {"current_steps": 444300, "total_steps": 761865, "loss": 2.0073, "lr": 3.708402683745685e-07, "epoch": 8.747612766041227, "percentage": 58.32, "elapsed_time": "14:47:39", "remaining_time": "10:34:27", "throughput": 8494.19, "total_tokens": 452393648} {"current_steps": 444400, "total_steps": 761865, "loss": 2.003, "lr": 3.7064109673574917e-07, "epoch": 8.74958161879073, "percentage": 58.33, "elapsed_time": "14:47:51", "remaining_time": "10:34:15", "throughput": 8494.19, "total_tokens": 452494688} {"current_steps": 444500, "total_steps": 761865, "loss": 1.9798, "lr": 3.704419470933202e-07, "epoch": 8.751550471540234, "percentage": 58.34, "elapsed_time": "14:48:02", "remaining_time": "10:34:03", "throughput": 8494.2, "total_tokens": 452596408} {"current_steps": 444600, "total_steps": 761865, "loss": 1.9931, "lr": 3.702428194811455e-07, "epoch": 8.753519324289737, "percentage": 58.36, "elapsed_time": "14:48:14", "remaining_time": "10:33:50", "throughput": 8494.27, "total_tokens": 452698808} {"current_steps": 444700, "total_steps": 761865, "loss": 2.0221, "lr": 3.7004371393308484e-07, "epoch": 8.75548817703924, "percentage": 58.37, "elapsed_time": "14:48:26", "remaining_time": "10:33:38", "throughput": 8494.31, "total_tokens": 452799992} {"current_steps": 444800, "total_steps": 761865, "loss": 2.0111, "lr": 3.6984463048299465e-07, "epoch": 8.757457029788743, "percentage": 58.38, "elapsed_time": "14:48:37", "remaining_time": "10:33:26", "throughput": 8494.35, "total_tokens": 452900960} {"current_steps": 444900, "total_steps": 761865, "loss": 1.9805, "lr": 3.696455691647271e-07, "epoch": 8.759425882538245, "percentage": 58.4, "elapsed_time": "14:48:49", "remaining_time": "10:33:14", "throughput": 8494.39, "total_tokens": 453002720} {"current_steps": 445000, "total_steps": 761865, "loss": 2.0197, "lr": 3.694465300121312e-07, "epoch": 8.761394735287748, "percentage": 58.41, "elapsed_time": "14:49:01", "remaining_time": "10:33:02", "throughput": 8494.43, "total_tokens": 453104312} {"current_steps": 445100, "total_steps": 761865, "loss": 1.9399, "lr": 3.6924751305905157e-07, "epoch": 8.763363588037251, "percentage": 58.42, "elapsed_time": "14:49:13", "remaining_time": "10:32:50", "throughput": 8494.38, "total_tokens": 453205288} {"current_steps": 445200, "total_steps": 761865, "loss": 1.9581, "lr": 3.690485183393297e-07, "epoch": 8.765332440786754, "percentage": 58.44, "elapsed_time": "14:49:25", "remaining_time": "10:32:38", "throughput": 8494.43, "total_tokens": 453307688} {"current_steps": 445300, "total_steps": 761865, "loss": 2.0297, "lr": 3.6884954588680254e-07, "epoch": 8.767301293536256, "percentage": 58.45, "elapsed_time": "14:49:36", "remaining_time": "10:32:25", "throughput": 8494.48, "total_tokens": 453409512} {"current_steps": 445400, "total_steps": 761865, "loss": 2.013, "lr": 3.6865059573530427e-07, "epoch": 8.76927014628576, "percentage": 58.46, "elapsed_time": "14:49:48", "remaining_time": "10:32:13", "throughput": 8494.53, "total_tokens": 453511152} {"current_steps": 445500, "total_steps": 761865, "loss": 1.993, "lr": 3.68451667918664e-07, "epoch": 8.771238999035262, "percentage": 58.47, "elapsed_time": "14:50:00", "remaining_time": "10:32:01", "throughput": 8494.58, "total_tokens": 453613552} {"current_steps": 445600, "total_steps": 761865, "loss": 1.9934, "lr": 3.682527624707082e-07, "epoch": 8.773207851784765, "percentage": 58.49, "elapsed_time": "14:50:12", "remaining_time": "10:31:49", "throughput": 8494.63, "total_tokens": 453715472} {"current_steps": 445700, "total_steps": 761865, "loss": 1.9601, "lr": 3.6805387942525904e-07, "epoch": 8.775176704534267, "percentage": 58.5, "elapsed_time": "14:50:24", "remaining_time": "10:31:37", "throughput": 8494.63, "total_tokens": 453817872} {"current_steps": 445800, "total_steps": 761865, "loss": 1.971, "lr": 3.6785501881613466e-07, "epoch": 8.77714555728377, "percentage": 58.51, "elapsed_time": "14:50:36", "remaining_time": "10:31:25", "throughput": 8494.61, "total_tokens": 453919544} {"current_steps": 445900, "total_steps": 761865, "loss": 2.0277, "lr": 3.6765618067714997e-07, "epoch": 8.779114410033273, "percentage": 58.53, "elapsed_time": "14:50:48", "remaining_time": "10:31:13", "throughput": 8494.65, "total_tokens": 454021944} {"current_steps": 446000, "total_steps": 761865, "loss": 1.959, "lr": 3.6745736504211533e-07, "epoch": 8.781083262782776, "percentage": 58.54, "elapsed_time": "14:50:59", "remaining_time": "10:31:01", "throughput": 8494.68, "total_tokens": 454123072} {"current_steps": 446100, "total_steps": 761865, "loss": 2.0495, "lr": 3.67258571944838e-07, "epoch": 8.783052115532278, "percentage": 58.55, "elapsed_time": "14:51:11", "remaining_time": "10:30:49", "throughput": 8494.67, "total_tokens": 454225472} {"current_steps": 446200, "total_steps": 761865, "loss": 2.0057, "lr": 3.670598014191207e-07, "epoch": 8.785020968281783, "percentage": 58.57, "elapsed_time": "14:51:23", "remaining_time": "10:30:37", "throughput": 8494.68, "total_tokens": 454327024} {"current_steps": 446300, "total_steps": 761865, "loss": 2.0012, "lr": 3.668610534987631e-07, "epoch": 8.786989821031286, "percentage": 58.58, "elapsed_time": "14:51:35", "remaining_time": "10:30:25", "throughput": 8494.69, "total_tokens": 454429424} {"current_steps": 446400, "total_steps": 761865, "loss": 1.9778, "lr": 3.666623282175603e-07, "epoch": 8.788958673780789, "percentage": 58.59, "elapsed_time": "14:51:48", "remaining_time": "10:30:13", "throughput": 8494.64, "total_tokens": 454531272} {"current_steps": 446500, "total_steps": 761865, "loss": 2.0007, "lr": 3.66463625609304e-07, "epoch": 8.790927526530291, "percentage": 58.61, "elapsed_time": "14:51:59", "remaining_time": "10:30:01", "throughput": 8494.65, "total_tokens": 454632824} {"current_steps": 446600, "total_steps": 761865, "loss": 1.9609, "lr": 3.662649457077819e-07, "epoch": 8.792896379279794, "percentage": 58.62, "elapsed_time": "14:52:11", "remaining_time": "10:29:49", "throughput": 8494.69, "total_tokens": 454735224} {"current_steps": 446700, "total_steps": 761865, "loss": 1.9816, "lr": 3.660662885467777e-07, "epoch": 8.794865232029297, "percentage": 58.63, "elapsed_time": "14:52:23", "remaining_time": "10:29:37", "throughput": 8494.71, "total_tokens": 454836544} {"current_steps": 446800, "total_steps": 761865, "loss": 1.9409, "lr": 3.658676541600716e-07, "epoch": 8.7968340847788, "percentage": 58.65, "elapsed_time": "14:52:35", "remaining_time": "10:29:24", "throughput": 8494.75, "total_tokens": 454938408} {"current_steps": 446900, "total_steps": 761865, "loss": 1.9658, "lr": 3.656690425814395e-07, "epoch": 8.798802937528302, "percentage": 58.66, "elapsed_time": "14:52:46", "remaining_time": "10:29:12", "throughput": 8494.77, "total_tokens": 455038888} {"current_steps": 447000, "total_steps": 761865, "loss": 2.0191, "lr": 3.654704538446538e-07, "epoch": 8.800771790277805, "percentage": 58.67, "elapsed_time": "14:52:58", "remaining_time": "10:29:00", "throughput": 8494.8, "total_tokens": 455141288} {"current_steps": 447100, "total_steps": 761865, "loss": 1.9853, "lr": 3.652718879834827e-07, "epoch": 8.802740643027308, "percentage": 58.68, "elapsed_time": "14:53:10", "remaining_time": "10:28:48", "throughput": 8494.84, "total_tokens": 455243688} {"current_steps": 447200, "total_steps": 761865, "loss": 1.9376, "lr": 3.650733450316907e-07, "epoch": 8.80470949577681, "percentage": 58.7, "elapsed_time": "14:53:22", "remaining_time": "10:28:36", "throughput": 8494.87, "total_tokens": 455345344} {"current_steps": 447300, "total_steps": 761865, "loss": 1.9435, "lr": 3.6487482502303833e-07, "epoch": 8.806678348526313, "percentage": 58.71, "elapsed_time": "14:53:34", "remaining_time": "10:28:24", "throughput": 8494.88, "total_tokens": 455447744} {"current_steps": 447400, "total_steps": 761865, "loss": 1.981, "lr": 3.6467632799128236e-07, "epoch": 8.808647201275816, "percentage": 58.72, "elapsed_time": "14:53:46", "remaining_time": "10:28:12", "throughput": 8494.88, "total_tokens": 455550144} {"current_steps": 447500, "total_steps": 761865, "loss": 1.9773, "lr": 3.644778539701753e-07, "epoch": 8.810616054025319, "percentage": 58.74, "elapsed_time": "14:53:58", "remaining_time": "10:28:00", "throughput": 8494.92, "total_tokens": 455651888} {"current_steps": 447600, "total_steps": 761865, "loss": 1.9986, "lr": 3.64279402993466e-07, "epoch": 8.812584906774822, "percentage": 58.75, "elapsed_time": "14:54:09", "remaining_time": "10:27:48", "throughput": 8494.95, "total_tokens": 455753608} {"current_steps": 447700, "total_steps": 761865, "loss": 1.9769, "lr": 3.640809750949e-07, "epoch": 8.814553759524324, "percentage": 58.76, "elapsed_time": "14:54:21", "remaining_time": "10:27:36", "throughput": 8494.97, "total_tokens": 455856008} {"current_steps": 447800, "total_steps": 761865, "loss": 2.0695, "lr": 3.638825703082173e-07, "epoch": 8.816522612273829, "percentage": 58.78, "elapsed_time": "14:54:33", "remaining_time": "10:27:24", "throughput": 8495.01, "total_tokens": 455958408} {"current_steps": 447900, "total_steps": 761865, "loss": 1.9935, "lr": 3.636841886671558e-07, "epoch": 8.818491465023332, "percentage": 58.79, "elapsed_time": "14:54:45", "remaining_time": "10:27:11", "throughput": 8495.06, "total_tokens": 456060496} {"current_steps": 448000, "total_steps": 761865, "loss": 1.9769, "lr": 3.63485830205448e-07, "epoch": 8.820460317772834, "percentage": 58.8, "elapsed_time": "14:54:57", "remaining_time": "10:26:59", "throughput": 8495.09, "total_tokens": 456161528} {"current_steps": 448100, "total_steps": 761865, "loss": 2.0191, "lr": 3.632874949568236e-07, "epoch": 8.822429170522337, "percentage": 58.82, "elapsed_time": "14:55:08", "remaining_time": "10:26:47", "throughput": 8495.13, "total_tokens": 456263512} {"current_steps": 448200, "total_steps": 761865, "loss": 1.9856, "lr": 3.6308918295500736e-07, "epoch": 8.82439802327184, "percentage": 58.83, "elapsed_time": "14:55:20", "remaining_time": "10:26:35", "throughput": 8495.16, "total_tokens": 456365032} {"current_steps": 448300, "total_steps": 761865, "loss": 2.014, "lr": 3.6289089423372106e-07, "epoch": 8.826366876021343, "percentage": 58.84, "elapsed_time": "14:55:32", "remaining_time": "10:26:23", "throughput": 8495.18, "total_tokens": 456463664} {"current_steps": 448400, "total_steps": 761865, "loss": 2.0203, "lr": 3.626926288266814e-07, "epoch": 8.828335728770845, "percentage": 58.86, "elapsed_time": "14:55:43", "remaining_time": "10:26:10", "throughput": 8495.22, "total_tokens": 456565664} {"current_steps": 448500, "total_steps": 761865, "loss": 1.9957, "lr": 3.624943867676026e-07, "epoch": 8.830304581520348, "percentage": 58.87, "elapsed_time": "14:55:55", "remaining_time": "10:25:58", "throughput": 8495.25, "total_tokens": 456667120} {"current_steps": 448600, "total_steps": 761865, "loss": 1.9833, "lr": 3.6229616809019305e-07, "epoch": 8.832273434269851, "percentage": 58.88, "elapsed_time": "14:56:07", "remaining_time": "10:25:46", "throughput": 8495.29, "total_tokens": 456769520} {"current_steps": 448700, "total_steps": 761865, "loss": 2.0258, "lr": 3.620979728281588e-07, "epoch": 8.834242287019354, "percentage": 58.89, "elapsed_time": "14:56:19", "remaining_time": "10:25:34", "throughput": 8495.29, "total_tokens": 456869608} {"current_steps": 448800, "total_steps": 761865, "loss": 2.0104, "lr": 3.6189980101520133e-07, "epoch": 8.836211139768857, "percentage": 58.91, "elapsed_time": "14:56:31", "remaining_time": "10:25:22", "throughput": 8495.29, "total_tokens": 456970768} {"current_steps": 448900, "total_steps": 761865, "loss": 1.9563, "lr": 3.6170165268501786e-07, "epoch": 8.83817999251836, "percentage": 58.92, "elapsed_time": "14:56:42", "remaining_time": "10:25:10", "throughput": 8495.34, "total_tokens": 457073168} {"current_steps": 449000, "total_steps": 761865, "loss": 2.0247, "lr": 3.615035278713019e-07, "epoch": 8.840148845267862, "percentage": 58.93, "elapsed_time": "14:56:54", "remaining_time": "10:24:58", "throughput": 8495.39, "total_tokens": 457174920} {"current_steps": 449100, "total_steps": 761865, "loss": 1.9894, "lr": 3.613054266077428e-07, "epoch": 8.842117698017365, "percentage": 58.95, "elapsed_time": "14:57:06", "remaining_time": "10:24:45", "throughput": 8495.42, "total_tokens": 457276104} {"current_steps": 449200, "total_steps": 761865, "loss": 2.0195, "lr": 3.611073489280262e-07, "epoch": 8.844086550766868, "percentage": 58.96, "elapsed_time": "14:57:18", "remaining_time": "10:24:33", "throughput": 8495.45, "total_tokens": 457378504} {"current_steps": 449300, "total_steps": 761865, "loss": 2.0333, "lr": 3.609092948658333e-07, "epoch": 8.84605540351637, "percentage": 58.97, "elapsed_time": "14:57:29", "remaining_time": "10:24:21", "throughput": 8495.48, "total_tokens": 457479344} {"current_steps": 449400, "total_steps": 761865, "loss": 1.9964, "lr": 3.607112644548418e-07, "epoch": 8.848024256265873, "percentage": 58.99, "elapsed_time": "14:57:41", "remaining_time": "10:24:09", "throughput": 8495.46, "total_tokens": 457580864} {"current_steps": 449500, "total_steps": 761865, "loss": 2.0488, "lr": 3.605132577287249e-07, "epoch": 8.849993109015376, "percentage": 59.0, "elapsed_time": "14:57:53", "remaining_time": "10:23:57", "throughput": 8495.5, "total_tokens": 457682344} {"current_steps": 449600, "total_steps": 761865, "loss": 1.9409, "lr": 3.60315274721152e-07, "epoch": 8.85196196176488, "percentage": 59.01, "elapsed_time": "14:58:05", "remaining_time": "10:23:45", "throughput": 8495.55, "total_tokens": 457784744} {"current_steps": 449700, "total_steps": 761865, "loss": 2.0058, "lr": 3.601173154657885e-07, "epoch": 8.853930814514383, "percentage": 59.03, "elapsed_time": "14:58:17", "remaining_time": "10:23:33", "throughput": 8495.58, "total_tokens": 457887040} {"current_steps": 449800, "total_steps": 761865, "loss": 1.976, "lr": 3.5991937999629575e-07, "epoch": 8.855899667263886, "percentage": 59.04, "elapsed_time": "14:58:29", "remaining_time": "10:23:21", "throughput": 8495.57, "total_tokens": 457988544} {"current_steps": 449900, "total_steps": 761865, "loss": 1.9861, "lr": 3.5972146834633094e-07, "epoch": 8.857868520013389, "percentage": 59.05, "elapsed_time": "14:58:41", "remaining_time": "10:23:09", "throughput": 8495.57, "total_tokens": 458090944} {"current_steps": 450000, "total_steps": 761865, "loss": 1.9914, "lr": 3.595235805495472e-07, "epoch": 8.859837372762891, "percentage": 59.07, "elapsed_time": "14:58:53", "remaining_time": "10:22:57", "throughput": 8495.57, "total_tokens": 458193344} {"current_steps": 450100, "total_steps": 761865, "loss": 2.0072, "lr": 3.593257166395938e-07, "epoch": 8.861806225512394, "percentage": 59.08, "elapsed_time": "14:59:05", "remaining_time": "10:22:45", "throughput": 8495.46, "total_tokens": 458294048} {"current_steps": 450200, "total_steps": 761865, "loss": 1.9979, "lr": 3.591278766501157e-07, "epoch": 8.863775078261897, "percentage": 59.09, "elapsed_time": "14:59:17", "remaining_time": "10:22:33", "throughput": 8495.51, "total_tokens": 458396272} {"current_steps": 450300, "total_steps": 761865, "loss": 2.0004, "lr": 3.589300606147542e-07, "epoch": 8.8657439310114, "percentage": 59.1, "elapsed_time": "14:59:29", "remaining_time": "10:22:21", "throughput": 8495.54, "total_tokens": 458497200} {"current_steps": 450400, "total_steps": 761865, "loss": 1.9616, "lr": 3.5873226856714584e-07, "epoch": 8.867712783760902, "percentage": 59.12, "elapsed_time": "14:59:40", "remaining_time": "10:22:09", "throughput": 8495.57, "total_tokens": 458598408} {"current_steps": 450500, "total_steps": 761865, "loss": 1.9723, "lr": 3.585345005409238e-07, "epoch": 8.869681636510405, "percentage": 59.13, "elapsed_time": "14:59:52", "remaining_time": "10:21:57", "throughput": 8495.63, "total_tokens": 458700808} {"current_steps": 450600, "total_steps": 761865, "loss": 1.9593, "lr": 3.5833675656971675e-07, "epoch": 8.871650489259908, "percentage": 59.14, "elapsed_time": "15:00:04", "remaining_time": "10:21:45", "throughput": 8495.68, "total_tokens": 458803208} {"current_steps": 450700, "total_steps": 761865, "loss": 2.0061, "lr": 3.581390366871493e-07, "epoch": 8.87361934200941, "percentage": 59.16, "elapsed_time": "15:00:16", "remaining_time": "10:21:32", "throughput": 8495.73, "total_tokens": 458905608} {"current_steps": 450800, "total_steps": 761865, "loss": 1.945, "lr": 3.579413409268424e-07, "epoch": 8.875588194758913, "percentage": 59.17, "elapsed_time": "15:00:27", "remaining_time": "10:21:20", "throughput": 8495.78, "total_tokens": 459007408} {"current_steps": 450900, "total_steps": 761865, "loss": 2.0026, "lr": 3.5774366932241197e-07, "epoch": 8.877557047508416, "percentage": 59.18, "elapsed_time": "15:00:39", "remaining_time": "10:21:08", "throughput": 8495.83, "total_tokens": 459109368} {"current_steps": 451000, "total_steps": 761865, "loss": 1.956, "lr": 3.5754602190747107e-07, "epoch": 8.879525900257919, "percentage": 59.2, "elapsed_time": "15:00:51", "remaining_time": "10:20:56", "throughput": 8495.89, "total_tokens": 459211768} {"current_steps": 451100, "total_steps": 761865, "loss": 1.9439, "lr": 3.573483987156274e-07, "epoch": 8.881494753007422, "percentage": 59.21, "elapsed_time": "15:01:02", "remaining_time": "10:20:44", "throughput": 8495.92, "total_tokens": 459312560} {"current_steps": 451200, "total_steps": 761865, "loss": 1.9483, "lr": 3.5715079978048557e-07, "epoch": 8.883463605756926, "percentage": 59.22, "elapsed_time": "15:01:14", "remaining_time": "10:20:31", "throughput": 8495.98, "total_tokens": 459414960} {"current_steps": 451300, "total_steps": 761865, "loss": 1.9446, "lr": 3.5695322513564505e-07, "epoch": 8.885432458506429, "percentage": 59.24, "elapsed_time": "15:01:26", "remaining_time": "10:20:19", "throughput": 8496.03, "total_tokens": 459517360} {"current_steps": 451400, "total_steps": 761865, "loss": 2.0121, "lr": 3.567556748147025e-07, "epoch": 8.887401311255932, "percentage": 59.25, "elapsed_time": "15:01:37", "remaining_time": "10:20:07", "throughput": 8496.07, "total_tokens": 459618216} {"current_steps": 451500, "total_steps": 761865, "loss": 1.9641, "lr": 3.565581488512489e-07, "epoch": 8.889370164005435, "percentage": 59.26, "elapsed_time": "15:01:49", "remaining_time": "10:19:55", "throughput": 8496.12, "total_tokens": 459719928} {"current_steps": 451600, "total_steps": 761865, "loss": 2.0073, "lr": 3.5636064727887227e-07, "epoch": 8.891339016754937, "percentage": 59.28, "elapsed_time": "15:02:01", "remaining_time": "10:19:43", "throughput": 8496.16, "total_tokens": 459821088} {"current_steps": 451700, "total_steps": 761865, "loss": 2.0011, "lr": 3.5616317013115627e-07, "epoch": 8.89330786950444, "percentage": 59.29, "elapsed_time": "15:02:12", "remaining_time": "10:19:30", "throughput": 8496.21, "total_tokens": 459923008} {"current_steps": 451800, "total_steps": 761865, "loss": 1.9735, "lr": 3.5596571744167994e-07, "epoch": 8.895276722253943, "percentage": 59.3, "elapsed_time": "15:02:24", "remaining_time": "10:19:18", "throughput": 8496.26, "total_tokens": 460024416} {"current_steps": 451900, "total_steps": 761865, "loss": 1.9947, "lr": 3.5576828924401855e-07, "epoch": 8.897245575003446, "percentage": 59.31, "elapsed_time": "15:02:36", "remaining_time": "10:19:06", "throughput": 8496.31, "total_tokens": 460126816} {"current_steps": 452000, "total_steps": 761865, "loss": 1.9902, "lr": 3.55570885571743e-07, "epoch": 8.899214427752948, "percentage": 59.33, "elapsed_time": "15:02:47", "remaining_time": "10:18:54", "throughput": 8496.36, "total_tokens": 460228528} {"current_steps": 452100, "total_steps": 761865, "loss": 1.978, "lr": 3.553735064584202e-07, "epoch": 8.901183280502451, "percentage": 59.34, "elapsed_time": "15:02:59", "remaining_time": "10:18:42", "throughput": 8496.41, "total_tokens": 460330512} {"current_steps": 452200, "total_steps": 761865, "loss": 1.9982, "lr": 3.5517615193761274e-07, "epoch": 8.903152133251954, "percentage": 59.35, "elapsed_time": "15:03:11", "remaining_time": "10:18:29", "throughput": 8496.46, "total_tokens": 460432912} {"current_steps": 452300, "total_steps": 761865, "loss": 1.9914, "lr": 3.5497882204287933e-07, "epoch": 8.905120986001457, "percentage": 59.37, "elapsed_time": "15:03:22", "remaining_time": "10:18:17", "throughput": 8496.5, "total_tokens": 460534880} {"current_steps": 452400, "total_steps": 761865, "loss": 1.9967, "lr": 3.5478151680777387e-07, "epoch": 8.90708983875096, "percentage": 59.38, "elapsed_time": "15:03:34", "remaining_time": "10:18:05", "throughput": 8496.56, "total_tokens": 460637280} {"current_steps": 452500, "total_steps": 761865, "loss": 2.0346, "lr": 3.5458423626584675e-07, "epoch": 8.909058691500462, "percentage": 59.39, "elapsed_time": "15:03:46", "remaining_time": "10:17:53", "throughput": 8496.6, "total_tokens": 460739680} {"current_steps": 452600, "total_steps": 761865, "loss": 2.0016, "lr": 3.543869804506437e-07, "epoch": 8.911027544249965, "percentage": 59.41, "elapsed_time": "15:03:58", "remaining_time": "10:17:41", "throughput": 8496.62, "total_tokens": 460840632} {"current_steps": 452700, "total_steps": 761865, "loss": 1.9751, "lr": 3.5418974939570644e-07, "epoch": 8.912996396999468, "percentage": 59.42, "elapsed_time": "15:04:09", "remaining_time": "10:17:29", "throughput": 8496.67, "total_tokens": 460943032} {"current_steps": 452800, "total_steps": 761865, "loss": 2.0151, "lr": 3.539925431345726e-07, "epoch": 8.91496524974897, "percentage": 59.43, "elapsed_time": "15:04:21", "remaining_time": "10:17:16", "throughput": 8496.7, "total_tokens": 461044488} {"current_steps": 452900, "total_steps": 761865, "loss": 1.9507, "lr": 3.537953617007752e-07, "epoch": 8.916934102498475, "percentage": 59.45, "elapsed_time": "15:04:33", "remaining_time": "10:17:04", "throughput": 8496.72, "total_tokens": 461146888} {"current_steps": 453000, "total_steps": 761865, "loss": 2.0159, "lr": 3.5359820512784347e-07, "epoch": 8.918902955247978, "percentage": 59.46, "elapsed_time": "15:04:45", "remaining_time": "10:16:52", "throughput": 8496.76, "total_tokens": 461249288} {"current_steps": 453100, "total_steps": 761865, "loss": 1.9918, "lr": 3.5340107344930206e-07, "epoch": 8.92087180799748, "percentage": 59.47, "elapsed_time": "15:04:57", "remaining_time": "10:16:40", "throughput": 8496.81, "total_tokens": 461351688} {"current_steps": 453200, "total_steps": 761865, "loss": 1.9929, "lr": 3.532039666986718e-07, "epoch": 8.922840660746983, "percentage": 59.49, "elapsed_time": "15:05:08", "remaining_time": "10:16:28", "throughput": 8496.85, "total_tokens": 461454088} {"current_steps": 453300, "total_steps": 761865, "loss": 1.9731, "lr": 3.5300688490946873e-07, "epoch": 8.924809513496486, "percentage": 59.5, "elapsed_time": "15:05:20", "remaining_time": "10:16:16", "throughput": 8496.9, "total_tokens": 461556488} {"current_steps": 453400, "total_steps": 761865, "loss": 1.9509, "lr": 3.5280982811520517e-07, "epoch": 8.926778366245989, "percentage": 59.51, "elapsed_time": "15:05:32", "remaining_time": "10:16:04", "throughput": 8496.93, "total_tokens": 461658888} {"current_steps": 453500, "total_steps": 761865, "loss": 1.9776, "lr": 3.5261279634938877e-07, "epoch": 8.928747218995492, "percentage": 59.52, "elapsed_time": "15:05:44", "remaining_time": "10:15:52", "throughput": 8496.98, "total_tokens": 461761288} {"current_steps": 453600, "total_steps": 761865, "loss": 1.9595, "lr": 3.5241578964552333e-07, "epoch": 8.930716071744994, "percentage": 59.54, "elapsed_time": "15:05:56", "remaining_time": "10:15:40", "throughput": 8497.0, "total_tokens": 461863096} {"current_steps": 453700, "total_steps": 761865, "loss": 1.9883, "lr": 3.522188080371079e-07, "epoch": 8.932684924494497, "percentage": 59.55, "elapsed_time": "15:06:07", "remaining_time": "10:15:28", "throughput": 8497.05, "total_tokens": 461965496} {"current_steps": 453800, "total_steps": 761865, "loss": 1.9884, "lr": 3.5202185155763783e-07, "epoch": 8.934653777244, "percentage": 59.56, "elapsed_time": "15:06:19", "remaining_time": "10:15:15", "throughput": 8497.11, "total_tokens": 462067896} {"current_steps": 453900, "total_steps": 761865, "loss": 2.0315, "lr": 3.5182492024060383e-07, "epoch": 8.936622629993503, "percentage": 59.58, "elapsed_time": "15:06:31", "remaining_time": "10:15:03", "throughput": 8497.11, "total_tokens": 462170296} {"current_steps": 454000, "total_steps": 761865, "loss": 1.9948, "lr": 3.5162801411949234e-07, "epoch": 8.938591482743005, "percentage": 59.59, "elapsed_time": "15:06:43", "remaining_time": "10:14:51", "throughput": 8497.14, "total_tokens": 462272696} {"current_steps": 454100, "total_steps": 761865, "loss": 2.0359, "lr": 3.5143113322778574e-07, "epoch": 8.940560335492508, "percentage": 59.6, "elapsed_time": "15:06:55", "remaining_time": "10:14:39", "throughput": 8497.19, "total_tokens": 462374432} {"current_steps": 454200, "total_steps": 761865, "loss": 1.9737, "lr": 3.5123427759896167e-07, "epoch": 8.94252918824201, "percentage": 59.62, "elapsed_time": "15:07:06", "remaining_time": "10:14:27", "throughput": 8497.19, "total_tokens": 462476064} {"current_steps": 454300, "total_steps": 761865, "loss": 1.9971, "lr": 3.510374472664941e-07, "epoch": 8.944498040991514, "percentage": 59.63, "elapsed_time": "15:07:19", "remaining_time": "10:14:15", "throughput": 8497.16, "total_tokens": 462578464} {"current_steps": 454400, "total_steps": 761865, "loss": 2.0277, "lr": 3.508406422638521e-07, "epoch": 8.946466893741016, "percentage": 59.64, "elapsed_time": "15:07:31", "remaining_time": "10:14:03", "throughput": 8497.12, "total_tokens": 462679216} {"current_steps": 454500, "total_steps": 761865, "loss": 2.0097, "lr": 3.50643862624501e-07, "epoch": 8.94843574649052, "percentage": 59.66, "elapsed_time": "15:07:43", "remaining_time": "10:13:52", "throughput": 8497.11, "total_tokens": 462781616} {"current_steps": 454600, "total_steps": 761865, "loss": 1.9723, "lr": 3.5044710838190107e-07, "epoch": 8.950404599240024, "percentage": 59.67, "elapsed_time": "15:07:55", "remaining_time": "10:13:40", "throughput": 8497.1, "total_tokens": 462883488} {"current_steps": 454700, "total_steps": 761865, "loss": 1.9541, "lr": 3.502503795695091e-07, "epoch": 8.952373451989526, "percentage": 59.68, "elapsed_time": "15:08:07", "remaining_time": "10:13:28", "throughput": 8497.11, "total_tokens": 462985888} {"current_steps": 454800, "total_steps": 761865, "loss": 2.0205, "lr": 3.500536762207771e-07, "epoch": 8.95434230473903, "percentage": 59.7, "elapsed_time": "15:08:19", "remaining_time": "10:13:16", "throughput": 8497.11, "total_tokens": 463088240} {"current_steps": 454900, "total_steps": 761865, "loss": 2.0027, "lr": 3.4985699836915263e-07, "epoch": 8.956311157488532, "percentage": 59.71, "elapsed_time": "15:08:31", "remaining_time": "10:13:04", "throughput": 8497.07, "total_tokens": 463188960} {"current_steps": 455000, "total_steps": 761865, "loss": 1.9786, "lr": 3.496603460480793e-07, "epoch": 8.958280010238035, "percentage": 59.72, "elapsed_time": "15:08:43", "remaining_time": "10:12:52", "throughput": 8497.08, "total_tokens": 463289064} {"current_steps": 455100, "total_steps": 761865, "loss": 1.9584, "lr": 3.4946371929099605e-07, "epoch": 8.960248862987537, "percentage": 59.73, "elapsed_time": "15:08:55", "remaining_time": "10:12:40", "throughput": 8497.04, "total_tokens": 463391464} {"current_steps": 455200, "total_steps": 761865, "loss": 1.9637, "lr": 3.4926711813133773e-07, "epoch": 8.96221771573704, "percentage": 59.75, "elapsed_time": "15:09:07", "remaining_time": "10:12:28", "throughput": 8497.07, "total_tokens": 463491528} {"current_steps": 455300, "total_steps": 761865, "loss": 2.0351, "lr": 3.4907054260253455e-07, "epoch": 8.964186568486543, "percentage": 59.76, "elapsed_time": "15:09:18", "remaining_time": "10:12:15", "throughput": 8497.11, "total_tokens": 463593008} {"current_steps": 455400, "total_steps": 761865, "loss": 1.9595, "lr": 3.488739927380127e-07, "epoch": 8.966155421236046, "percentage": 59.77, "elapsed_time": "15:09:30", "remaining_time": "10:12:03", "throughput": 8497.15, "total_tokens": 463694592} {"current_steps": 455500, "total_steps": 761865, "loss": 1.9792, "lr": 3.4867746857119365e-07, "epoch": 8.968124273985548, "percentage": 59.79, "elapsed_time": "15:09:42", "remaining_time": "10:11:51", "throughput": 8497.18, "total_tokens": 463796992} {"current_steps": 455600, "total_steps": 761865, "loss": 2.0071, "lr": 3.484809701354948e-07, "epoch": 8.970093126735051, "percentage": 59.8, "elapsed_time": "15:09:54", "remaining_time": "10:11:39", "throughput": 8497.15, "total_tokens": 463898024} {"current_steps": 455700, "total_steps": 761865, "loss": 1.9898, "lr": 3.4828449746432896e-07, "epoch": 8.972061979484554, "percentage": 59.81, "elapsed_time": "15:10:06", "remaining_time": "10:11:27", "throughput": 8497.11, "total_tokens": 463999600} {"current_steps": 455800, "total_steps": 761865, "loss": 1.998, "lr": 3.480880505911046e-07, "epoch": 8.974030832234057, "percentage": 59.83, "elapsed_time": "15:10:18", "remaining_time": "10:11:16", "throughput": 8497.1, "total_tokens": 464101824} {"current_steps": 455900, "total_steps": 761865, "loss": 2.0109, "lr": 3.478916295492262e-07, "epoch": 8.97599968498356, "percentage": 59.84, "elapsed_time": "15:10:31", "remaining_time": "10:11:04", "throughput": 8497.06, "total_tokens": 464203464} {"current_steps": 456000, "total_steps": 761865, "loss": 2.0182, "lr": 3.47695234372093e-07, "epoch": 8.977968537733062, "percentage": 59.85, "elapsed_time": "15:10:43", "remaining_time": "10:10:52", "throughput": 8497.05, "total_tokens": 464305472} {"current_steps": 456100, "total_steps": 761865, "loss": 1.9661, "lr": 3.474988650931009e-07, "epoch": 8.979937390482565, "percentage": 59.87, "elapsed_time": "15:10:55", "remaining_time": "10:10:40", "throughput": 8497.06, "total_tokens": 464407872} {"current_steps": 456200, "total_steps": 761865, "loss": 1.9571, "lr": 3.4730252174564017e-07, "epoch": 8.981906243232068, "percentage": 59.88, "elapsed_time": "15:11:07", "remaining_time": "10:10:28", "throughput": 8496.99, "total_tokens": 464510272} {"current_steps": 456300, "total_steps": 761865, "loss": 2.0023, "lr": 3.471062043630981e-07, "epoch": 8.983875095981572, "percentage": 59.89, "elapsed_time": "15:11:19", "remaining_time": "10:10:16", "throughput": 8497.0, "total_tokens": 464612672} {"current_steps": 456400, "total_steps": 761865, "loss": 1.9853, "lr": 3.46909912978856e-07, "epoch": 8.985843948731075, "percentage": 59.91, "elapsed_time": "15:11:31", "remaining_time": "10:10:04", "throughput": 8497.02, "total_tokens": 464715064} {"current_steps": 456500, "total_steps": 761865, "loss": 1.9396, "lr": 3.467136476262924e-07, "epoch": 8.987812801480578, "percentage": 59.92, "elapsed_time": "15:11:43", "remaining_time": "10:09:52", "throughput": 8497.03, "total_tokens": 464816272} {"current_steps": 456600, "total_steps": 761865, "loss": 2.019, "lr": 3.4651740833877975e-07, "epoch": 8.98978165423008, "percentage": 59.93, "elapsed_time": "15:11:55", "remaining_time": "10:09:40", "throughput": 8496.99, "total_tokens": 464917816} {"current_steps": 456700, "total_steps": 761865, "loss": 2.0066, "lr": 3.4632119514968744e-07, "epoch": 8.991750506979583, "percentage": 59.95, "elapsed_time": "15:12:08", "remaining_time": "10:09:29", "throughput": 8496.9, "total_tokens": 465018928} {"current_steps": 456800, "total_steps": 761865, "loss": 1.9996, "lr": 3.461250080923798e-07, "epoch": 8.993719359729086, "percentage": 59.96, "elapsed_time": "15:12:19", "remaining_time": "10:09:17", "throughput": 8496.9, "total_tokens": 465120168} {"current_steps": 456900, "total_steps": 761865, "loss": 1.9869, "lr": 3.4592884720021654e-07, "epoch": 8.995688212478589, "percentage": 59.97, "elapsed_time": "15:12:31", "remaining_time": "10:09:04", "throughput": 8496.92, "total_tokens": 465221984} {"current_steps": 457000, "total_steps": 761865, "loss": 1.9616, "lr": 3.4573271250655345e-07, "epoch": 8.997657065228092, "percentage": 59.98, "elapsed_time": "15:12:43", "remaining_time": "10:08:52", "throughput": 8496.94, "total_tokens": 465323832} {"current_steps": 457100, "total_steps": 761865, "loss": 1.9666, "lr": 3.4553660404474136e-07, "epoch": 8.999625917977594, "percentage": 60.0, "elapsed_time": "15:12:55", "remaining_time": "10:08:40", "throughput": 8496.97, "total_tokens": 465425696} {"current_steps": 457200, "total_steps": 761865, "loss": 2.0245, "lr": 3.453405218481271e-07, "epoch": 9.001594770727097, "percentage": 60.01, "elapsed_time": "15:13:07", "remaining_time": "10:08:28", "throughput": 8496.99, "total_tokens": 465527952} {"current_steps": 457300, "total_steps": 761865, "loss": 1.9865, "lr": 3.451444659500524e-07, "epoch": 9.0035636234766, "percentage": 60.02, "elapsed_time": "15:13:19", "remaining_time": "10:08:16", "throughput": 8497.01, "total_tokens": 465630352} {"current_steps": 457400, "total_steps": 761865, "loss": 1.9751, "lr": 3.449484363838554e-07, "epoch": 9.005532476226103, "percentage": 60.04, "elapsed_time": "15:13:31", "remaining_time": "10:08:04", "throughput": 8497.03, "total_tokens": 465732208} {"current_steps": 457500, "total_steps": 761865, "loss": 1.9877, "lr": 3.4475243318286885e-07, "epoch": 9.007501328975605, "percentage": 60.05, "elapsed_time": "15:13:43", "remaining_time": "10:07:52", "throughput": 8497.06, "total_tokens": 465834608} {"current_steps": 457600, "total_steps": 761865, "loss": 1.9947, "lr": 3.4455645638042173e-07, "epoch": 9.009470181725108, "percentage": 60.06, "elapsed_time": "15:13:54", "remaining_time": "10:07:40", "throughput": 8497.08, "total_tokens": 465935952} {"current_steps": 457700, "total_steps": 761865, "loss": 1.967, "lr": 3.44360506009838e-07, "epoch": 9.011439034474611, "percentage": 60.08, "elapsed_time": "15:14:06", "remaining_time": "10:07:28", "throughput": 8497.1, "total_tokens": 466037480} {"current_steps": 457800, "total_steps": 761865, "loss": 2.0061, "lr": 3.4416458210443755e-07, "epoch": 9.013407887224114, "percentage": 60.09, "elapsed_time": "15:14:18", "remaining_time": "10:07:16", "throughput": 8497.12, "total_tokens": 466138688} {"current_steps": 457900, "total_steps": 761865, "loss": 1.9726, "lr": 3.439686846975357e-07, "epoch": 9.015376739973618, "percentage": 60.1, "elapsed_time": "15:14:30", "remaining_time": "10:07:04", "throughput": 8497.13, "total_tokens": 466239656} {"current_steps": 458000, "total_steps": 761865, "loss": 1.9786, "lr": 3.437728138224428e-07, "epoch": 9.017345592723121, "percentage": 60.12, "elapsed_time": "15:14:41", "remaining_time": "10:06:52", "throughput": 8497.15, "total_tokens": 466340224} {"current_steps": 458100, "total_steps": 761865, "loss": 1.9627, "lr": 3.435769695124653e-07, "epoch": 9.019314445472624, "percentage": 60.13, "elapsed_time": "15:14:53", "remaining_time": "10:06:39", "throughput": 8497.17, "total_tokens": 466442104} {"current_steps": 458200, "total_steps": 761865, "loss": 1.9436, "lr": 3.433811518009048e-07, "epoch": 9.021283298222126, "percentage": 60.14, "elapsed_time": "15:15:05", "remaining_time": "10:06:27", "throughput": 8497.2, "total_tokens": 466544504} {"current_steps": 458300, "total_steps": 761865, "loss": 1.9877, "lr": 3.431853607210584e-07, "epoch": 9.02325215097163, "percentage": 60.16, "elapsed_time": "15:15:17", "remaining_time": "10:06:15", "throughput": 8497.22, "total_tokens": 466646264} {"current_steps": 458400, "total_steps": 761865, "loss": 1.9771, "lr": 3.429895963062188e-07, "epoch": 9.025221003721132, "percentage": 60.17, "elapsed_time": "15:15:29", "remaining_time": "10:06:03", "throughput": 8497.25, "total_tokens": 466748064} {"current_steps": 458500, "total_steps": 761865, "loss": 1.991, "lr": 3.4279385858967414e-07, "epoch": 9.027189856470635, "percentage": 60.18, "elapsed_time": "15:15:41", "remaining_time": "10:05:51", "throughput": 8497.22, "total_tokens": 466850464} {"current_steps": 458600, "total_steps": 761865, "loss": 2.0166, "lr": 3.4259814760470774e-07, "epoch": 9.029158709220138, "percentage": 60.19, "elapsed_time": "15:15:53", "remaining_time": "10:05:39", "throughput": 8497.23, "total_tokens": 466952864} {"current_steps": 458700, "total_steps": 761865, "loss": 1.9757, "lr": 3.424024633845989e-07, "epoch": 9.03112756196964, "percentage": 60.21, "elapsed_time": "15:16:05", "remaining_time": "10:05:27", "throughput": 8497.25, "total_tokens": 467054560} {"current_steps": 458800, "total_steps": 761865, "loss": 2.0129, "lr": 3.4220680596262186e-07, "epoch": 9.033096414719143, "percentage": 60.22, "elapsed_time": "15:16:17", "remaining_time": "10:05:15", "throughput": 8497.25, "total_tokens": 467156424} {"current_steps": 458900, "total_steps": 761865, "loss": 1.9643, "lr": 3.4201117537204636e-07, "epoch": 9.035065267468646, "percentage": 60.23, "elapsed_time": "15:16:29", "remaining_time": "10:05:03", "throughput": 8497.27, "total_tokens": 467258824} {"current_steps": 459000, "total_steps": 761865, "loss": 1.9674, "lr": 3.4181557164613833e-07, "epoch": 9.037034120218149, "percentage": 60.25, "elapsed_time": "15:16:41", "remaining_time": "10:04:51", "throughput": 8497.3, "total_tokens": 467360768} {"current_steps": 459100, "total_steps": 761865, "loss": 1.9679, "lr": 3.4161999481815785e-07, "epoch": 9.039002972967651, "percentage": 60.26, "elapsed_time": "15:16:52", "remaining_time": "10:04:39", "throughput": 8497.34, "total_tokens": 467462536} {"current_steps": 459200, "total_steps": 761865, "loss": 1.9877, "lr": 3.414244449213617e-07, "epoch": 9.040971825717154, "percentage": 60.27, "elapsed_time": "15:17:04", "remaining_time": "10:04:27", "throughput": 8497.38, "total_tokens": 467563664} {"current_steps": 459300, "total_steps": 761865, "loss": 2.0316, "lr": 3.412289219890009e-07, "epoch": 9.042940678466657, "percentage": 60.29, "elapsed_time": "15:17:16", "remaining_time": "10:04:15", "throughput": 8497.41, "total_tokens": 467663904} {"current_steps": 459400, "total_steps": 761865, "loss": 1.9859, "lr": 3.4103342605432305e-07, "epoch": 9.04490953121616, "percentage": 60.3, "elapsed_time": "15:17:28", "remaining_time": "10:04:03", "throughput": 8497.4, "total_tokens": 467765456} {"current_steps": 459500, "total_steps": 761865, "loss": 1.9911, "lr": 3.408379571505701e-07, "epoch": 9.046878383965662, "percentage": 60.31, "elapsed_time": "15:17:39", "remaining_time": "10:03:51", "throughput": 8497.43, "total_tokens": 467867856} {"current_steps": 459600, "total_steps": 761865, "loss": 1.9657, "lr": 3.4064251531098034e-07, "epoch": 9.048847236715167, "percentage": 60.33, "elapsed_time": "15:17:51", "remaining_time": "10:03:38", "throughput": 8497.45, "total_tokens": 467968848} {"current_steps": 459700, "total_steps": 761865, "loss": 1.9945, "lr": 3.4044710056878646e-07, "epoch": 9.05081608946467, "percentage": 60.34, "elapsed_time": "15:18:03", "remaining_time": "10:03:26", "throughput": 8497.47, "total_tokens": 468071248} {"current_steps": 459800, "total_steps": 761865, "loss": 2.0039, "lr": 3.402517129572175e-07, "epoch": 9.052784942214172, "percentage": 60.35, "elapsed_time": "15:18:15", "remaining_time": "10:03:14", "throughput": 8497.5, "total_tokens": 468173648} {"current_steps": 459900, "total_steps": 761865, "loss": 2.0248, "lr": 3.400563525094975e-07, "epoch": 9.054753794963675, "percentage": 60.37, "elapsed_time": "15:18:27", "remaining_time": "10:03:02", "throughput": 8497.52, "total_tokens": 468275312} {"current_steps": 460000, "total_steps": 761865, "loss": 1.9548, "lr": 3.3986101925884556e-07, "epoch": 9.056722647713178, "percentage": 60.38, "elapsed_time": "15:18:39", "remaining_time": "10:02:50", "throughput": 8497.54, "total_tokens": 468377216} {"current_steps": 460100, "total_steps": 761865, "loss": 2.0347, "lr": 3.396657132384768e-07, "epoch": 9.05869150046268, "percentage": 60.39, "elapsed_time": "15:18:51", "remaining_time": "10:02:39", "throughput": 8497.47, "total_tokens": 468479064} {"current_steps": 460200, "total_steps": 761865, "loss": 1.9563, "lr": 3.3947043448160106e-07, "epoch": 9.060660353212183, "percentage": 60.4, "elapsed_time": "15:19:03", "remaining_time": "10:02:26", "throughput": 8497.48, "total_tokens": 468580176} {"current_steps": 460300, "total_steps": 761865, "loss": 1.9627, "lr": 3.392751830214241e-07, "epoch": 9.062629205961686, "percentage": 60.42, "elapsed_time": "15:19:15", "remaining_time": "10:02:14", "throughput": 8497.5, "total_tokens": 468681344} {"current_steps": 460400, "total_steps": 761865, "loss": 1.9417, "lr": 3.3907995889114647e-07, "epoch": 9.064598058711189, "percentage": 60.43, "elapsed_time": "15:19:27", "remaining_time": "10:02:02", "throughput": 8497.53, "total_tokens": 468783744} {"current_steps": 460500, "total_steps": 761865, "loss": 1.9711, "lr": 3.388847621239648e-07, "epoch": 9.066566911460692, "percentage": 60.44, "elapsed_time": "15:19:38", "remaining_time": "10:01:50", "throughput": 8497.55, "total_tokens": 468886144} {"current_steps": 460600, "total_steps": 761865, "loss": 1.9846, "lr": 3.386895927530702e-07, "epoch": 9.068535764210194, "percentage": 60.46, "elapsed_time": "15:19:50", "remaining_time": "10:01:38", "throughput": 8497.58, "total_tokens": 468988544} {"current_steps": 460700, "total_steps": 761865, "loss": 1.9648, "lr": 3.384944508116499e-07, "epoch": 9.070504616959697, "percentage": 60.47, "elapsed_time": "15:20:02", "remaining_time": "10:01:26", "throughput": 8497.6, "total_tokens": 469090944} {"current_steps": 460800, "total_steps": 761865, "loss": 1.9657, "lr": 3.38299336332886e-07, "epoch": 9.0724734697092, "percentage": 60.48, "elapsed_time": "15:20:14", "remaining_time": "10:01:14", "throughput": 8497.62, "total_tokens": 469192808} {"current_steps": 460900, "total_steps": 761865, "loss": 1.9983, "lr": 3.3810424934995605e-07, "epoch": 9.074442322458703, "percentage": 60.5, "elapsed_time": "15:20:26", "remaining_time": "10:01:02", "throughput": 8497.64, "total_tokens": 469293984} {"current_steps": 461000, "total_steps": 761865, "loss": 1.9514, "lr": 3.379091898960331e-07, "epoch": 9.076411175208206, "percentage": 60.51, "elapsed_time": "15:20:38", "remaining_time": "10:00:50", "throughput": 8497.67, "total_tokens": 469396384} {"current_steps": 461100, "total_steps": 761865, "loss": 1.9298, "lr": 3.3771415800428527e-07, "epoch": 9.078380027957708, "percentage": 60.52, "elapsed_time": "15:20:50", "remaining_time": "10:00:38", "throughput": 8497.69, "total_tokens": 469498784} {"current_steps": 461200, "total_steps": 761865, "loss": 1.9784, "lr": 3.375191537078761e-07, "epoch": 9.080348880707213, "percentage": 60.54, "elapsed_time": "15:21:02", "remaining_time": "10:00:26", "throughput": 8497.71, "total_tokens": 469600832} {"current_steps": 461300, "total_steps": 761865, "loss": 2.0515, "lr": 3.3732417703996435e-07, "epoch": 9.082317733456716, "percentage": 60.55, "elapsed_time": "15:21:13", "remaining_time": "10:00:14", "throughput": 8497.74, "total_tokens": 469703232} {"current_steps": 461400, "total_steps": 761865, "loss": 2.0081, "lr": 3.3712922803370435e-07, "epoch": 9.084286586206218, "percentage": 60.56, "elapsed_time": "15:21:25", "remaining_time": "10:00:02", "throughput": 8497.75, "total_tokens": 469804048} {"current_steps": 461500, "total_steps": 761865, "loss": 2.025, "lr": 3.369343067222452e-07, "epoch": 9.086255438955721, "percentage": 60.58, "elapsed_time": "15:21:37", "remaining_time": "9:59:50", "throughput": 8497.78, "total_tokens": 469906448} {"current_steps": 461600, "total_steps": 761865, "loss": 1.9767, "lr": 3.3673941313873206e-07, "epoch": 9.088224291705224, "percentage": 60.59, "elapsed_time": "15:21:49", "remaining_time": "9:59:38", "throughput": 8497.8, "total_tokens": 470008256} {"current_steps": 461700, "total_steps": 761865, "loss": 1.9599, "lr": 3.3654454731630455e-07, "epoch": 9.090193144454727, "percentage": 60.6, "elapsed_time": "15:22:01", "remaining_time": "9:59:25", "throughput": 8497.82, "total_tokens": 470109848} {"current_steps": 461800, "total_steps": 761865, "loss": 1.9951, "lr": 3.36349709288098e-07, "epoch": 9.09216199720423, "percentage": 60.61, "elapsed_time": "15:22:13", "remaining_time": "9:59:13", "throughput": 8497.84, "total_tokens": 470212248} {"current_steps": 461900, "total_steps": 761865, "loss": 1.937, "lr": 3.361548990872435e-07, "epoch": 9.094130849953732, "percentage": 60.63, "elapsed_time": "15:22:24", "remaining_time": "9:59:01", "throughput": 8497.86, "total_tokens": 470313776} {"current_steps": 462000, "total_steps": 761865, "loss": 2.0437, "lr": 3.359601167468661e-07, "epoch": 9.096099702703235, "percentage": 60.64, "elapsed_time": "15:22:36", "remaining_time": "9:58:49", "throughput": 8497.89, "total_tokens": 470415696} {"current_steps": 462100, "total_steps": 761865, "loss": 2.0122, "lr": 3.3576536230008747e-07, "epoch": 9.098068555452738, "percentage": 60.65, "elapsed_time": "15:22:48", "remaining_time": "9:58:37", "throughput": 8497.9, "total_tokens": 470517224} {"current_steps": 462200, "total_steps": 761865, "loss": 1.9621, "lr": 3.3557063578002365e-07, "epoch": 9.10003740820224, "percentage": 60.67, "elapsed_time": "15:23:00", "remaining_time": "9:58:25", "throughput": 8497.93, "total_tokens": 470619624} {"current_steps": 462300, "total_steps": 761865, "loss": 1.9552, "lr": 3.353759372197865e-07, "epoch": 9.102006260951743, "percentage": 60.68, "elapsed_time": "15:23:12", "remaining_time": "9:58:13", "throughput": 8497.95, "total_tokens": 470722024} {"current_steps": 462400, "total_steps": 761865, "loss": 1.9675, "lr": 3.351812666524826e-07, "epoch": 9.103975113701246, "percentage": 60.69, "elapsed_time": "15:23:24", "remaining_time": "9:58:01", "throughput": 8497.97, "total_tokens": 470823176} {"current_steps": 462500, "total_steps": 761865, "loss": 2.0105, "lr": 3.349866241112142e-07, "epoch": 9.105943966450749, "percentage": 60.71, "elapsed_time": "15:23:36", "remaining_time": "9:57:49", "throughput": 8497.99, "total_tokens": 470924648} {"current_steps": 462600, "total_steps": 761865, "loss": 2.0098, "lr": 3.347920096290785e-07, "epoch": 9.107912819200251, "percentage": 60.72, "elapsed_time": "15:23:47", "remaining_time": "9:57:37", "throughput": 8498.02, "total_tokens": 471027048} {"current_steps": 462700, "total_steps": 761865, "loss": 1.9851, "lr": 3.345974232391683e-07, "epoch": 9.109881671949754, "percentage": 60.73, "elapsed_time": "15:23:59", "remaining_time": "9:57:25", "throughput": 8498.03, "total_tokens": 471128008} {"current_steps": 462800, "total_steps": 761865, "loss": 2.0088, "lr": 3.344028649745711e-07, "epoch": 9.111850524699257, "percentage": 60.75, "elapsed_time": "15:24:11", "remaining_time": "9:57:13", "throughput": 8498.05, "total_tokens": 471229656} {"current_steps": 462900, "total_steps": 761865, "loss": 2.0201, "lr": 3.3420833486837e-07, "epoch": 9.113819377448761, "percentage": 60.76, "elapsed_time": "15:24:23", "remaining_time": "9:57:01", "throughput": 8498.07, "total_tokens": 471332056} {"current_steps": 463000, "total_steps": 761865, "loss": 2.0, "lr": 3.3401383295364326e-07, "epoch": 9.115788230198264, "percentage": 60.77, "elapsed_time": "15:24:35", "remaining_time": "9:56:49", "throughput": 8498.1, "total_tokens": 471434456} {"current_steps": 463100, "total_steps": 761865, "loss": 1.9544, "lr": 3.3381935926346416e-07, "epoch": 9.117757082947767, "percentage": 60.79, "elapsed_time": "15:24:47", "remaining_time": "9:56:37", "throughput": 8498.12, "total_tokens": 471536216} {"current_steps": 463200, "total_steps": 761865, "loss": 1.9781, "lr": 3.3362491383090144e-07, "epoch": 9.11972593569727, "percentage": 60.8, "elapsed_time": "15:24:58", "remaining_time": "9:56:24", "throughput": 8498.15, "total_tokens": 471638144} {"current_steps": 463300, "total_steps": 761865, "loss": 1.9692, "lr": 3.334304966890188e-07, "epoch": 9.121694788446773, "percentage": 60.81, "elapsed_time": "15:25:10", "remaining_time": "9:56:12", "throughput": 8498.17, "total_tokens": 471740544} {"current_steps": 463400, "total_steps": 761865, "loss": 2.0102, "lr": 3.3323610787087544e-07, "epoch": 9.123663641196275, "percentage": 60.82, "elapsed_time": "15:25:22", "remaining_time": "9:56:00", "throughput": 8498.19, "total_tokens": 471842408} {"current_steps": 463500, "total_steps": 761865, "loss": 2.0388, "lr": 3.330417474095252e-07, "epoch": 9.125632493945778, "percentage": 60.84, "elapsed_time": "15:25:34", "remaining_time": "9:55:48", "throughput": 8498.21, "total_tokens": 471943608} {"current_steps": 463600, "total_steps": 761865, "loss": 2.0586, "lr": 3.328474153380177e-07, "epoch": 9.12760134669528, "percentage": 60.85, "elapsed_time": "15:25:46", "remaining_time": "9:55:36", "throughput": 8498.2, "total_tokens": 472044560} {"current_steps": 463700, "total_steps": 761865, "loss": 2.0018, "lr": 3.326531116893974e-07, "epoch": 9.129570199444784, "percentage": 60.86, "elapsed_time": "15:25:58", "remaining_time": "9:55:24", "throughput": 8498.22, "total_tokens": 472145456} {"current_steps": 463800, "total_steps": 761865, "loss": 2.0114, "lr": 3.324588364967038e-07, "epoch": 9.131539052194286, "percentage": 60.88, "elapsed_time": "15:26:10", "remaining_time": "9:55:12", "throughput": 8498.18, "total_tokens": 472246504} {"current_steps": 463900, "total_steps": 761865, "loss": 2.0308, "lr": 3.3226458979297224e-07, "epoch": 9.133507904943789, "percentage": 60.89, "elapsed_time": "15:26:22", "remaining_time": "9:55:00", "throughput": 8498.2, "total_tokens": 472348344} {"current_steps": 464000, "total_steps": 761865, "loss": 1.9563, "lr": 3.320703716112322e-07, "epoch": 9.135476757693292, "percentage": 60.9, "elapsed_time": "15:26:34", "remaining_time": "9:54:48", "throughput": 8498.23, "total_tokens": 472450744} {"current_steps": 464100, "total_steps": 761865, "loss": 1.9685, "lr": 3.3187618198450935e-07, "epoch": 9.137445610442795, "percentage": 60.92, "elapsed_time": "15:26:45", "remaining_time": "9:54:36", "throughput": 8498.25, "total_tokens": 472552648} {"current_steps": 464200, "total_steps": 761865, "loss": 2.0024, "lr": 3.3168202094582344e-07, "epoch": 9.139414463192297, "percentage": 60.93, "elapsed_time": "15:26:57", "remaining_time": "9:54:24", "throughput": 8498.28, "total_tokens": 472654536} {"current_steps": 464300, "total_steps": 761865, "loss": 1.9917, "lr": 3.3148788852819056e-07, "epoch": 9.1413833159418, "percentage": 60.94, "elapsed_time": "15:27:09", "remaining_time": "9:54:12", "throughput": 8498.3, "total_tokens": 472755744} {"current_steps": 464400, "total_steps": 761865, "loss": 1.9891, "lr": 3.3129378476462057e-07, "epoch": 9.143352168691303, "percentage": 60.96, "elapsed_time": "15:27:21", "remaining_time": "9:54:00", "throughput": 8498.34, "total_tokens": 472858144} {"current_steps": 464500, "total_steps": 761865, "loss": 1.9967, "lr": 3.310997096881198e-07, "epoch": 9.145321021440806, "percentage": 60.97, "elapsed_time": "15:27:32", "remaining_time": "9:53:48", "throughput": 8498.38, "total_tokens": 472959768} {"current_steps": 464600, "total_steps": 761865, "loss": 1.9958, "lr": 3.309056633316886e-07, "epoch": 9.14728987419031, "percentage": 60.98, "elapsed_time": "15:27:44", "remaining_time": "9:53:35", "throughput": 8498.41, "total_tokens": 473062168} {"current_steps": 464700, "total_steps": 761865, "loss": 2.0571, "lr": 3.3071164572832346e-07, "epoch": 9.149258726939813, "percentage": 61.0, "elapsed_time": "15:27:56", "remaining_time": "9:53:23", "throughput": 8498.45, "total_tokens": 473163344} {"current_steps": 464800, "total_steps": 761865, "loss": 1.9225, "lr": 3.3051765691101474e-07, "epoch": 9.151227579689316, "percentage": 61.01, "elapsed_time": "15:28:08", "remaining_time": "9:53:11", "throughput": 8498.5, "total_tokens": 473265112} {"current_steps": 464900, "total_steps": 761865, "loss": 1.9586, "lr": 3.303236969127492e-07, "epoch": 9.153196432438818, "percentage": 61.02, "elapsed_time": "15:28:19", "remaining_time": "9:52:59", "throughput": 8498.55, "total_tokens": 473367512} {"current_steps": 465000, "total_steps": 761865, "loss": 1.9973, "lr": 3.3012976576650785e-07, "epoch": 9.155165285188321, "percentage": 61.03, "elapsed_time": "15:28:31", "remaining_time": "9:52:47", "throughput": 8498.57, "total_tokens": 473469912} {"current_steps": 465100, "total_steps": 761865, "loss": 1.9918, "lr": 3.299358635052671e-07, "epoch": 9.157134137937824, "percentage": 61.05, "elapsed_time": "15:28:44", "remaining_time": "9:52:35", "throughput": 8498.48, "total_tokens": 473571536} {"current_steps": 465200, "total_steps": 761865, "loss": 1.9498, "lr": 3.2974199016199844e-07, "epoch": 9.159102990687327, "percentage": 61.06, "elapsed_time": "15:28:56", "remaining_time": "9:52:23", "throughput": 8498.51, "total_tokens": 473673936} {"current_steps": 465300, "total_steps": 761865, "loss": 1.9651, "lr": 3.2954814576966816e-07, "epoch": 9.16107184343683, "percentage": 61.07, "elapsed_time": "15:29:07", "remaining_time": "9:52:11", "throughput": 8498.53, "total_tokens": 473775760} {"current_steps": 465400, "total_steps": 761865, "loss": 1.9336, "lr": 3.293543303612382e-07, "epoch": 9.163040696186332, "percentage": 61.09, "elapsed_time": "15:29:19", "remaining_time": "9:51:59", "throughput": 8498.56, "total_tokens": 473878160} {"current_steps": 465500, "total_steps": 761865, "loss": 1.9652, "lr": 3.29160543969665e-07, "epoch": 9.165009548935835, "percentage": 61.1, "elapsed_time": "15:29:31", "remaining_time": "9:51:47", "throughput": 8498.58, "total_tokens": 473979912} {"current_steps": 465600, "total_steps": 761865, "loss": 1.9712, "lr": 3.289667866279004e-07, "epoch": 9.166978401685338, "percentage": 61.11, "elapsed_time": "15:29:43", "remaining_time": "9:51:35", "throughput": 8498.61, "total_tokens": 474082312} {"current_steps": 465700, "total_steps": 761865, "loss": 2.044, "lr": 3.2877305836889113e-07, "epoch": 9.16894725443484, "percentage": 61.13, "elapsed_time": "15:29:55", "remaining_time": "9:51:23", "throughput": 8498.62, "total_tokens": 474183328} {"current_steps": 465800, "total_steps": 761865, "loss": 1.9763, "lr": 3.285793592255791e-07, "epoch": 9.170916107184343, "percentage": 61.14, "elapsed_time": "15:30:07", "remaining_time": "9:51:11", "throughput": 8498.65, "total_tokens": 474285552} {"current_steps": 465900, "total_steps": 761865, "loss": 2.0322, "lr": 3.2838568923090115e-07, "epoch": 9.172884959933846, "percentage": 61.15, "elapsed_time": "15:30:19", "remaining_time": "9:50:59", "throughput": 8498.67, "total_tokens": 474387680} {"current_steps": 466000, "total_steps": 761865, "loss": 2.047, "lr": 3.2819204841778936e-07, "epoch": 9.174853812683349, "percentage": 61.17, "elapsed_time": "15:30:30", "remaining_time": "9:50:47", "throughput": 8498.69, "total_tokens": 474489416} {"current_steps": 466100, "total_steps": 761865, "loss": 1.9924, "lr": 3.2799843681917066e-07, "epoch": 9.176822665432852, "percentage": 61.18, "elapsed_time": "15:30:42", "remaining_time": "9:50:35", "throughput": 8498.72, "total_tokens": 474591816} {"current_steps": 466200, "total_steps": 761865, "loss": 1.9742, "lr": 3.27804854467967e-07, "epoch": 9.178791518182354, "percentage": 61.19, "elapsed_time": "15:30:54", "remaining_time": "9:50:23", "throughput": 8498.73, "total_tokens": 474692704} {"current_steps": 466300, "total_steps": 761865, "loss": 1.9653, "lr": 3.276113013970955e-07, "epoch": 9.180760370931859, "percentage": 61.21, "elapsed_time": "15:31:06", "remaining_time": "9:50:10", "throughput": 8498.75, "total_tokens": 474793976} {"current_steps": 466400, "total_steps": 761865, "loss": 1.9498, "lr": 3.274177776394682e-07, "epoch": 9.182729223681362, "percentage": 61.22, "elapsed_time": "15:31:18", "remaining_time": "9:49:58", "throughput": 8498.77, "total_tokens": 474895736} {"current_steps": 466500, "total_steps": 761865, "loss": 1.9733, "lr": 3.272242832279922e-07, "epoch": 9.184698076430864, "percentage": 61.23, "elapsed_time": "15:31:30", "remaining_time": "9:49:46", "throughput": 8498.8, "total_tokens": 474997872} {"current_steps": 466600, "total_steps": 761865, "loss": 1.988, "lr": 3.2703081819556957e-07, "epoch": 9.186666929180367, "percentage": 61.24, "elapsed_time": "15:31:41", "remaining_time": "9:49:34", "throughput": 8498.81, "total_tokens": 475099320} {"current_steps": 466700, "total_steps": 761865, "loss": 1.9975, "lr": 3.268373825750974e-07, "epoch": 9.18863578192987, "percentage": 61.26, "elapsed_time": "15:31:53", "remaining_time": "9:49:22", "throughput": 8498.84, "total_tokens": 475201616} {"current_steps": 466800, "total_steps": 761865, "loss": 1.984, "lr": 3.266439763994678e-07, "epoch": 9.190604634679373, "percentage": 61.27, "elapsed_time": "15:32:05", "remaining_time": "9:49:10", "throughput": 8498.86, "total_tokens": 475303720} {"current_steps": 466900, "total_steps": 761865, "loss": 2.0096, "lr": 3.2645059970156776e-07, "epoch": 9.192573487428875, "percentage": 61.28, "elapsed_time": "15:32:17", "remaining_time": "9:48:58", "throughput": 8498.88, "total_tokens": 475406120} {"current_steps": 467000, "total_steps": 761865, "loss": 1.9945, "lr": 3.262572525142797e-07, "epoch": 9.194542340178378, "percentage": 61.3, "elapsed_time": "15:32:29", "remaining_time": "9:48:46", "throughput": 8498.91, "total_tokens": 475507832} {"current_steps": 467100, "total_steps": 761865, "loss": 1.9935, "lr": 3.2606393487048017e-07, "epoch": 9.19651119292788, "percentage": 61.31, "elapsed_time": "15:32:40", "remaining_time": "9:48:34", "throughput": 8498.93, "total_tokens": 475608792} {"current_steps": 467200, "total_steps": 761865, "loss": 1.9534, "lr": 3.2587064680304177e-07, "epoch": 9.198480045677384, "percentage": 61.32, "elapsed_time": "15:32:52", "remaining_time": "9:48:22", "throughput": 8498.97, "total_tokens": 475710400} {"current_steps": 467300, "total_steps": 761865, "loss": 1.9876, "lr": 3.2567738834483086e-07, "epoch": 9.200448898426886, "percentage": 61.34, "elapsed_time": "15:33:04", "remaining_time": "9:48:10", "throughput": 8499.02, "total_tokens": 475812800} {"current_steps": 467400, "total_steps": 761865, "loss": 1.9952, "lr": 3.254841595287101e-07, "epoch": 9.20241775117639, "percentage": 61.35, "elapsed_time": "15:33:16", "remaining_time": "9:47:57", "throughput": 8499.06, "total_tokens": 475914248} {"current_steps": 467500, "total_steps": 761865, "loss": 2.0325, "lr": 3.252909603875358e-07, "epoch": 9.204386603925892, "percentage": 61.36, "elapsed_time": "15:33:27", "remaining_time": "9:47:45", "throughput": 8499.1, "total_tokens": 476015624} {"current_steps": 467600, "total_steps": 761865, "loss": 2.0211, "lr": 3.250977909541604e-07, "epoch": 9.206355456675395, "percentage": 61.38, "elapsed_time": "15:33:39", "remaining_time": "9:47:33", "throughput": 8499.14, "total_tokens": 476117536} {"current_steps": 467700, "total_steps": 761865, "loss": 1.9722, "lr": 3.249046512614302e-07, "epoch": 9.208324309424897, "percentage": 61.39, "elapsed_time": "15:33:51", "remaining_time": "9:47:21", "throughput": 8499.19, "total_tokens": 476219936} {"current_steps": 467800, "total_steps": 761865, "loss": 1.9958, "lr": 3.2471154134218747e-07, "epoch": 9.2102931621744, "percentage": 61.4, "elapsed_time": "15:34:02", "remaining_time": "9:47:09", "throughput": 8499.24, "total_tokens": 476321784} {"current_steps": 467900, "total_steps": 761865, "loss": 1.9936, "lr": 3.245184612292684e-07, "epoch": 9.212262014923905, "percentage": 61.42, "elapsed_time": "15:34:14", "remaining_time": "9:46:57", "throughput": 8499.28, "total_tokens": 476423248} {"current_steps": 468000, "total_steps": 761865, "loss": 1.9763, "lr": 3.2432541095550496e-07, "epoch": 9.214230867673407, "percentage": 61.43, "elapsed_time": "15:34:26", "remaining_time": "9:46:44", "throughput": 8499.31, "total_tokens": 476524256} {"current_steps": 468100, "total_steps": 761865, "loss": 1.9921, "lr": 3.241323905537239e-07, "epoch": 9.21619972042291, "percentage": 61.44, "elapsed_time": "15:34:37", "remaining_time": "9:46:32", "throughput": 8499.35, "total_tokens": 476625112} {"current_steps": 468200, "total_steps": 761865, "loss": 1.9985, "lr": 3.2393940005674625e-07, "epoch": 9.218168573172413, "percentage": 61.45, "elapsed_time": "15:34:49", "remaining_time": "9:46:20", "throughput": 8499.38, "total_tokens": 476725296} {"current_steps": 468300, "total_steps": 761865, "loss": 1.9309, "lr": 3.237464394973889e-07, "epoch": 9.220137425921916, "percentage": 61.47, "elapsed_time": "15:35:01", "remaining_time": "9:46:08", "throughput": 8499.42, "total_tokens": 476827104} {"current_steps": 468400, "total_steps": 761865, "loss": 1.9663, "lr": 3.2355350890846266e-07, "epoch": 9.222106278671419, "percentage": 61.48, "elapsed_time": "15:35:12", "remaining_time": "9:45:56", "throughput": 8499.47, "total_tokens": 476929072} {"current_steps": 468500, "total_steps": 761865, "loss": 1.9992, "lr": 3.2336060832277423e-07, "epoch": 9.224075131420921, "percentage": 61.49, "elapsed_time": "15:35:24", "remaining_time": "9:45:44", "throughput": 8499.51, "total_tokens": 477031472} {"current_steps": 468600, "total_steps": 761865, "loss": 1.9978, "lr": 3.2316773777312445e-07, "epoch": 9.226043984170424, "percentage": 61.51, "elapsed_time": "15:35:36", "remaining_time": "9:45:31", "throughput": 8499.55, "total_tokens": 477132880} {"current_steps": 468700, "total_steps": 761865, "loss": 1.9728, "lr": 3.2297489729230944e-07, "epoch": 9.228012836919927, "percentage": 61.52, "elapsed_time": "15:35:47", "remaining_time": "9:45:19", "throughput": 8499.6, "total_tokens": 477235280} {"current_steps": 468800, "total_steps": 761865, "loss": 2.003, "lr": 3.2278208691311987e-07, "epoch": 9.22998168966943, "percentage": 61.53, "elapsed_time": "15:35:59", "remaining_time": "9:45:07", "throughput": 8499.64, "total_tokens": 477337232} {"current_steps": 468900, "total_steps": 761865, "loss": 2.0079, "lr": 3.225893066683417e-07, "epoch": 9.231950542418932, "percentage": 61.55, "elapsed_time": "15:36:11", "remaining_time": "9:44:55", "throughput": 8499.68, "total_tokens": 477438184} {"current_steps": 469000, "total_steps": 761865, "loss": 1.9683, "lr": 3.223965565907558e-07, "epoch": 9.233919395168435, "percentage": 61.56, "elapsed_time": "15:36:23", "remaining_time": "9:44:43", "throughput": 8499.72, "total_tokens": 477540120} {"current_steps": 469100, "total_steps": 761865, "loss": 1.9713, "lr": 3.222038367131373e-07, "epoch": 9.235888247917938, "percentage": 61.57, "elapsed_time": "15:36:34", "remaining_time": "9:44:31", "throughput": 8499.76, "total_tokens": 477641864} {"current_steps": 469200, "total_steps": 761865, "loss": 2.0003, "lr": 3.2201114706825687e-07, "epoch": 9.23785710066744, "percentage": 61.59, "elapsed_time": "15:36:46", "remaining_time": "9:44:18", "throughput": 8499.79, "total_tokens": 477743704} {"current_steps": 469300, "total_steps": 761865, "loss": 1.9419, "lr": 3.2181848768887953e-07, "epoch": 9.239825953416943, "percentage": 61.6, "elapsed_time": "15:36:58", "remaining_time": "9:44:06", "throughput": 8499.81, "total_tokens": 477846104} {"current_steps": 469400, "total_steps": 761865, "loss": 2.0125, "lr": 3.216258586077657e-07, "epoch": 9.241794806166446, "percentage": 61.61, "elapsed_time": "15:37:10", "remaining_time": "9:43:54", "throughput": 8499.84, "total_tokens": 477947016} {"current_steps": 469500, "total_steps": 761865, "loss": 2.0128, "lr": 3.2143325985766994e-07, "epoch": 9.243763658915949, "percentage": 61.63, "elapsed_time": "15:37:21", "remaining_time": "9:43:42", "throughput": 8499.86, "total_tokens": 478048688} {"current_steps": 469600, "total_steps": 761865, "loss": 1.9549, "lr": 3.2124069147134234e-07, "epoch": 9.245732511665453, "percentage": 61.64, "elapsed_time": "15:37:33", "remaining_time": "9:43:30", "throughput": 8499.9, "total_tokens": 478150456} {"current_steps": 469700, "total_steps": 761865, "loss": 2.0572, "lr": 3.2104815348152743e-07, "epoch": 9.247701364414956, "percentage": 61.65, "elapsed_time": "15:37:45", "remaining_time": "9:43:18", "throughput": 8499.94, "total_tokens": 478251496} {"current_steps": 469800, "total_steps": 761865, "loss": 1.9898, "lr": 3.208556459209647e-07, "epoch": 9.249670217164459, "percentage": 61.66, "elapsed_time": "15:37:57", "remaining_time": "9:43:06", "throughput": 8499.99, "total_tokens": 478353896} {"current_steps": 469900, "total_steps": 761865, "loss": 1.9776, "lr": 3.2066316882238833e-07, "epoch": 9.251639069913962, "percentage": 61.68, "elapsed_time": "15:38:08", "remaining_time": "9:42:54", "throughput": 8500.03, "total_tokens": 478455536} {"current_steps": 470000, "total_steps": 761865, "loss": 1.9509, "lr": 3.2047072221852734e-07, "epoch": 9.253607922663464, "percentage": 61.69, "elapsed_time": "15:38:20", "remaining_time": "9:42:41", "throughput": 8500.07, "total_tokens": 478557312} {"current_steps": 470100, "total_steps": 761865, "loss": 1.9946, "lr": 3.2027830614210614e-07, "epoch": 9.255576775412967, "percentage": 61.7, "elapsed_time": "15:38:32", "remaining_time": "9:42:30", "throughput": 8500.01, "total_tokens": 478659128} {"current_steps": 470200, "total_steps": 761865, "loss": 2.0302, "lr": 3.2008592062584287e-07, "epoch": 9.25754562816247, "percentage": 61.72, "elapsed_time": "15:38:44", "remaining_time": "9:42:18", "throughput": 8500.06, "total_tokens": 478761528} {"current_steps": 470300, "total_steps": 761865, "loss": 2.0035, "lr": 3.198935657024515e-07, "epoch": 9.259514480911973, "percentage": 61.73, "elapsed_time": "15:38:56", "remaining_time": "9:42:05", "throughput": 8500.11, "total_tokens": 478863928} {"current_steps": 470400, "total_steps": 761865, "loss": 1.9601, "lr": 3.1970124140464017e-07, "epoch": 9.261483333661475, "percentage": 61.74, "elapsed_time": "15:39:07", "remaining_time": "9:41:53", "throughput": 8500.15, "total_tokens": 478966328} {"current_steps": 470500, "total_steps": 761865, "loss": 1.9842, "lr": 3.195089477651121e-07, "epoch": 9.263452186410978, "percentage": 61.76, "elapsed_time": "15:39:19", "remaining_time": "9:41:41", "throughput": 8500.2, "total_tokens": 479068728} {"current_steps": 470600, "total_steps": 761865, "loss": 1.9632, "lr": 3.19316684816565e-07, "epoch": 9.265421039160481, "percentage": 61.77, "elapsed_time": "15:39:31", "remaining_time": "9:41:29", "throughput": 8500.24, "total_tokens": 479171032} {"current_steps": 470700, "total_steps": 761865, "loss": 1.9479, "lr": 3.191244525916918e-07, "epoch": 9.267389891909984, "percentage": 61.78, "elapsed_time": "15:39:43", "remaining_time": "9:41:17", "throughput": 8500.29, "total_tokens": 479273432} {"current_steps": 470800, "total_steps": 761865, "loss": 1.9992, "lr": 3.1893225112317974e-07, "epoch": 9.269358744659487, "percentage": 61.8, "elapsed_time": "15:39:54", "remaining_time": "9:41:05", "throughput": 8500.33, "total_tokens": 479374640} {"current_steps": 470900, "total_steps": 761865, "loss": 1.9912, "lr": 3.187400804437113e-07, "epoch": 9.27132759740899, "percentage": 61.81, "elapsed_time": "15:40:06", "remaining_time": "9:40:53", "throughput": 8500.33, "total_tokens": 479475344} {"current_steps": 471000, "total_steps": 761865, "loss": 1.9643, "lr": 3.1854794058596325e-07, "epoch": 9.273296450158492, "percentage": 61.82, "elapsed_time": "15:40:18", "remaining_time": "9:40:41", "throughput": 8500.29, "total_tokens": 479577744} {"current_steps": 471100, "total_steps": 761865, "loss": 2.017, "lr": 3.183558315826075e-07, "epoch": 9.275265302907995, "percentage": 61.84, "elapsed_time": "15:40:30", "remaining_time": "9:40:29", "throughput": 8500.33, "total_tokens": 479678816} {"current_steps": 471200, "total_steps": 761865, "loss": 1.954, "lr": 3.1816375346631064e-07, "epoch": 9.277234155657498, "percentage": 61.85, "elapsed_time": "15:40:42", "remaining_time": "9:40:17", "throughput": 8500.38, "total_tokens": 479781216} {"current_steps": 471300, "total_steps": 761865, "loss": 1.9689, "lr": 3.179717062697337e-07, "epoch": 9.279203008407002, "percentage": 61.86, "elapsed_time": "15:40:53", "remaining_time": "9:40:04", "throughput": 8500.41, "total_tokens": 479881016} {"current_steps": 471400, "total_steps": 761865, "loss": 1.9697, "lr": 3.1777969002553287e-07, "epoch": 9.281171861156505, "percentage": 61.87, "elapsed_time": "15:41:05", "remaining_time": "9:39:52", "throughput": 8500.45, "total_tokens": 479983416} {"current_steps": 471500, "total_steps": 761865, "loss": 1.9627, "lr": 3.175877047663588e-07, "epoch": 9.283140713906008, "percentage": 61.89, "elapsed_time": "15:41:17", "remaining_time": "9:39:40", "throughput": 8500.49, "total_tokens": 480085136} {"current_steps": 471600, "total_steps": 761865, "loss": 1.9896, "lr": 3.1739575052485704e-07, "epoch": 9.28510956665551, "percentage": 61.9, "elapsed_time": "15:41:29", "remaining_time": "9:39:28", "throughput": 8500.54, "total_tokens": 480187536} {"current_steps": 471700, "total_steps": 761865, "loss": 1.999, "lr": 3.172038273336677e-07, "epoch": 9.287078419405013, "percentage": 61.91, "elapsed_time": "15:41:40", "remaining_time": "9:39:16", "throughput": 8500.58, "total_tokens": 480289248} {"current_steps": 471800, "total_steps": 761865, "loss": 2.0432, "lr": 3.1701193522542584e-07, "epoch": 9.289047272154516, "percentage": 61.93, "elapsed_time": "15:41:52", "remaining_time": "9:39:04", "throughput": 8500.62, "total_tokens": 480390720} {"current_steps": 471900, "total_steps": 761865, "loss": 2.0247, "lr": 3.168200742327609e-07, "epoch": 9.291016124904019, "percentage": 61.94, "elapsed_time": "15:42:03", "remaining_time": "9:38:51", "throughput": 8500.65, "total_tokens": 480489912} {"current_steps": 472000, "total_steps": 761865, "loss": 1.9814, "lr": 3.166282443882972e-07, "epoch": 9.292984977653521, "percentage": 61.95, "elapsed_time": "15:42:15", "remaining_time": "9:38:39", "throughput": 8500.69, "total_tokens": 480592312} {"current_steps": 472100, "total_steps": 761865, "loss": 1.9446, "lr": 3.164364457246542e-07, "epoch": 9.294953830403024, "percentage": 61.97, "elapsed_time": "15:42:27", "remaining_time": "9:38:27", "throughput": 8500.74, "total_tokens": 480694712} {"current_steps": 472200, "total_steps": 761865, "loss": 1.9776, "lr": 3.1624467827444514e-07, "epoch": 9.296922683152527, "percentage": 61.98, "elapsed_time": "15:42:39", "remaining_time": "9:38:15", "throughput": 8500.77, "total_tokens": 480795456} {"current_steps": 472300, "total_steps": 761865, "loss": 1.9725, "lr": 3.1605294207027896e-07, "epoch": 9.29889153590203, "percentage": 61.99, "elapsed_time": "15:42:50", "remaining_time": "9:38:03", "throughput": 8500.81, "total_tokens": 480897112} {"current_steps": 472400, "total_steps": 761865, "loss": 1.9986, "lr": 3.158612371447581e-07, "epoch": 9.300860388651532, "percentage": 62.01, "elapsed_time": "15:43:02", "remaining_time": "9:37:51", "throughput": 8500.86, "total_tokens": 480999512} {"current_steps": 472500, "total_steps": 761865, "loss": 1.9936, "lr": 3.1566956353048114e-07, "epoch": 9.302829241401035, "percentage": 62.02, "elapsed_time": "15:43:14", "remaining_time": "9:37:38", "throughput": 8500.89, "total_tokens": 481100288} {"current_steps": 472600, "total_steps": 761865, "loss": 2.0239, "lr": 3.154779212600399e-07, "epoch": 9.304798094150538, "percentage": 62.03, "elapsed_time": "15:43:25", "remaining_time": "9:37:26", "throughput": 8500.93, "total_tokens": 481202688} {"current_steps": 472700, "total_steps": 761865, "loss": 1.908, "lr": 3.152863103660221e-07, "epoch": 9.30676694690004, "percentage": 62.05, "elapsed_time": "15:43:37", "remaining_time": "9:37:14", "throughput": 8500.98, "total_tokens": 481305088} {"current_steps": 472800, "total_steps": 761865, "loss": 1.9849, "lr": 3.15094730881009e-07, "epoch": 9.308735799649543, "percentage": 62.06, "elapsed_time": "15:43:49", "remaining_time": "9:37:02", "throughput": 8501.01, "total_tokens": 481405152} {"current_steps": 472900, "total_steps": 761865, "loss": 1.9627, "lr": 3.1490318283757757e-07, "epoch": 9.310704652399046, "percentage": 62.07, "elapsed_time": "15:44:00", "remaining_time": "9:36:50", "throughput": 8501.06, "total_tokens": 481507552} {"current_steps": 473000, "total_steps": 761865, "loss": 2.0307, "lr": 3.147116662682985e-07, "epoch": 9.31267350514855, "percentage": 62.08, "elapsed_time": "15:44:12", "remaining_time": "9:36:38", "throughput": 8501.1, "total_tokens": 481609952} {"current_steps": 473100, "total_steps": 761865, "loss": 1.9673, "lr": 3.1452018120573785e-07, "epoch": 9.314642357898054, "percentage": 62.1, "elapsed_time": "15:44:24", "remaining_time": "9:36:26", "throughput": 8501.14, "total_tokens": 481711112} {"current_steps": 473200, "total_steps": 761865, "loss": 1.9647, "lr": 3.143287276824561e-07, "epoch": 9.316611210647556, "percentage": 62.11, "elapsed_time": "15:44:35", "remaining_time": "9:36:13", "throughput": 8501.19, "total_tokens": 481813512} {"current_steps": 473300, "total_steps": 761865, "loss": 2.039, "lr": 3.1413730573100807e-07, "epoch": 9.318580063397059, "percentage": 62.12, "elapsed_time": "15:44:47", "remaining_time": "9:36:01", "throughput": 8501.22, "total_tokens": 481914184} {"current_steps": 473400, "total_steps": 761865, "loss": 1.9752, "lr": 3.1394591538394366e-07, "epoch": 9.320548916146562, "percentage": 62.14, "elapsed_time": "15:44:59", "remaining_time": "9:35:49", "throughput": 8501.27, "total_tokens": 482016584} {"current_steps": 473500, "total_steps": 761865, "loss": 1.9844, "lr": 3.1375455667380695e-07, "epoch": 9.322517768896065, "percentage": 62.15, "elapsed_time": "15:45:11", "remaining_time": "9:35:37", "throughput": 8501.31, "total_tokens": 482118984} {"current_steps": 473600, "total_steps": 761865, "loss": 1.9718, "lr": 3.135632296331372e-07, "epoch": 9.324486621645567, "percentage": 62.16, "elapsed_time": "15:45:22", "remaining_time": "9:35:25", "throughput": 8501.36, "total_tokens": 482221384} {"current_steps": 473700, "total_steps": 761865, "loss": 2.0285, "lr": 3.133719342944676e-07, "epoch": 9.32645547439507, "percentage": 62.18, "elapsed_time": "15:45:34", "remaining_time": "9:35:13", "throughput": 8501.4, "total_tokens": 482323344} {"current_steps": 473800, "total_steps": 761865, "loss": 1.9986, "lr": 3.131806706903266e-07, "epoch": 9.328424327144573, "percentage": 62.19, "elapsed_time": "15:45:46", "remaining_time": "9:35:01", "throughput": 8501.43, "total_tokens": 482424064} {"current_steps": 473900, "total_steps": 761865, "loss": 1.9741, "lr": 3.129894388532367e-07, "epoch": 9.330393179894076, "percentage": 62.2, "elapsed_time": "15:45:57", "remaining_time": "9:34:48", "throughput": 8501.48, "total_tokens": 482525984} {"current_steps": 474000, "total_steps": 761865, "loss": 1.989, "lr": 3.1279823881571545e-07, "epoch": 9.332362032643578, "percentage": 62.22, "elapsed_time": "15:46:09", "remaining_time": "9:34:36", "throughput": 8501.52, "total_tokens": 482627552} {"current_steps": 474100, "total_steps": 761865, "loss": 1.9663, "lr": 3.1260707061027485e-07, "epoch": 9.334330885393081, "percentage": 62.23, "elapsed_time": "15:46:21", "remaining_time": "9:34:24", "throughput": 8501.56, "total_tokens": 482729952} {"current_steps": 474200, "total_steps": 761865, "loss": 1.9881, "lr": 3.1241593426942123e-07, "epoch": 9.336299738142584, "percentage": 62.24, "elapsed_time": "15:46:32", "remaining_time": "9:34:12", "throughput": 8501.6, "total_tokens": 482831120} {"current_steps": 474300, "total_steps": 761865, "loss": 2.0132, "lr": 3.12224829825656e-07, "epoch": 9.338268590892087, "percentage": 62.26, "elapsed_time": "15:46:44", "remaining_time": "9:34:00", "throughput": 8501.65, "total_tokens": 482933520} {"current_steps": 474400, "total_steps": 761865, "loss": 1.9447, "lr": 3.1203375731147455e-07, "epoch": 9.34023744364159, "percentage": 62.27, "elapsed_time": "15:46:56", "remaining_time": "9:33:48", "throughput": 8501.69, "total_tokens": 483035288} {"current_steps": 474500, "total_steps": 761865, "loss": 1.9601, "lr": 3.1184271675936734e-07, "epoch": 9.342206296391092, "percentage": 62.28, "elapsed_time": "15:47:07", "remaining_time": "9:33:35", "throughput": 8501.73, "total_tokens": 483136136} {"current_steps": 474600, "total_steps": 761865, "loss": 1.9267, "lr": 3.1165170820181906e-07, "epoch": 9.344175149140597, "percentage": 62.29, "elapsed_time": "15:47:19", "remaining_time": "9:33:23", "throughput": 8501.77, "total_tokens": 483238536} {"current_steps": 474700, "total_steps": 761865, "loss": 2.0041, "lr": 3.1146073167130936e-07, "epoch": 9.3461440018901, "percentage": 62.31, "elapsed_time": "15:47:31", "remaining_time": "9:33:11", "throughput": 8501.81, "total_tokens": 483340120} {"current_steps": 474800, "total_steps": 761865, "loss": 2.0101, "lr": 3.1126978720031194e-07, "epoch": 9.348112854639602, "percentage": 62.32, "elapsed_time": "15:47:43", "remaining_time": "9:32:59", "throughput": 8501.86, "total_tokens": 483442240} {"current_steps": 474900, "total_steps": 761865, "loss": 2.0322, "lr": 3.1107887482129537e-07, "epoch": 9.350081707389105, "percentage": 62.33, "elapsed_time": "15:47:54", "remaining_time": "9:32:47", "throughput": 8501.9, "total_tokens": 483544640} {"current_steps": 475000, "total_steps": 761865, "loss": 1.9665, "lr": 3.1088799456672267e-07, "epoch": 9.352050560138608, "percentage": 62.35, "elapsed_time": "15:48:06", "remaining_time": "9:32:35", "throughput": 8501.94, "total_tokens": 483645528} {"current_steps": 475100, "total_steps": 761865, "loss": 1.9719, "lr": 3.106971464690514e-07, "epoch": 9.35401941288811, "percentage": 62.36, "elapsed_time": "15:48:18", "remaining_time": "9:32:23", "throughput": 8501.89, "total_tokens": 483747928} {"current_steps": 475200, "total_steps": 761865, "loss": 1.9826, "lr": 3.105063305607339e-07, "epoch": 9.355988265637613, "percentage": 62.37, "elapsed_time": "15:48:30", "remaining_time": "9:32:11", "throughput": 8501.94, "total_tokens": 483850328} {"current_steps": 475300, "total_steps": 761865, "loss": 2.0131, "lr": 3.1031554687421644e-07, "epoch": 9.357957118387116, "percentage": 62.39, "elapsed_time": "15:48:42", "remaining_time": "9:31:59", "throughput": 8501.98, "total_tokens": 483951776} {"current_steps": 475400, "total_steps": 761865, "loss": 2.0197, "lr": 3.101247954419406e-07, "epoch": 9.359925971136619, "percentage": 62.4, "elapsed_time": "15:48:53", "remaining_time": "9:31:47", "throughput": 8502.02, "total_tokens": 484053648} {"current_steps": 475500, "total_steps": 761865, "loss": 1.9762, "lr": 3.099340762963415e-07, "epoch": 9.361894823886121, "percentage": 62.41, "elapsed_time": "15:49:05", "remaining_time": "9:31:34", "throughput": 8502.06, "total_tokens": 484154704} {"current_steps": 475600, "total_steps": 761865, "loss": 1.9717, "lr": 3.0974338946985e-07, "epoch": 9.363863676635624, "percentage": 62.43, "elapsed_time": "15:49:17", "remaining_time": "9:31:22", "throughput": 8502.1, "total_tokens": 484256280} {"current_steps": 475700, "total_steps": 761865, "loss": 1.9731, "lr": 3.095527349948901e-07, "epoch": 9.365832529385127, "percentage": 62.44, "elapsed_time": "15:49:28", "remaining_time": "9:31:10", "throughput": 8502.14, "total_tokens": 484358008} {"current_steps": 475800, "total_steps": 761865, "loss": 1.9819, "lr": 3.093621129038816e-07, "epoch": 9.36780138213463, "percentage": 62.45, "elapsed_time": "15:49:40", "remaining_time": "9:30:58", "throughput": 8502.18, "total_tokens": 484458936} {"current_steps": 475900, "total_steps": 761865, "loss": 1.9712, "lr": 3.091715232292376e-07, "epoch": 9.369770234884133, "percentage": 62.47, "elapsed_time": "15:49:52", "remaining_time": "9:30:46", "throughput": 8502.2, "total_tokens": 484557976} {"current_steps": 476000, "total_steps": 761865, "loss": 2.0142, "lr": 3.0898096600336676e-07, "epoch": 9.371739087633635, "percentage": 62.48, "elapsed_time": "15:50:03", "remaining_time": "9:30:34", "throughput": 8502.24, "total_tokens": 484660376} {"current_steps": 476100, "total_steps": 761865, "loss": 1.949, "lr": 3.0879044125867133e-07, "epoch": 9.373707940383138, "percentage": 62.49, "elapsed_time": "15:50:15", "remaining_time": "9:30:21", "throughput": 8502.29, "total_tokens": 484762776} {"current_steps": 476200, "total_steps": 761865, "loss": 1.9707, "lr": 3.085999490275487e-07, "epoch": 9.37567679313264, "percentage": 62.5, "elapsed_time": "15:50:27", "remaining_time": "9:30:09", "throughput": 8502.33, "total_tokens": 484865176} {"current_steps": 476300, "total_steps": 761865, "loss": 1.9919, "lr": 3.0840948934239046e-07, "epoch": 9.377645645882145, "percentage": 62.52, "elapsed_time": "15:50:39", "remaining_time": "9:29:57", "throughput": 8502.38, "total_tokens": 484967576} {"current_steps": 476400, "total_steps": 761865, "loss": 1.9463, "lr": 3.0821906223558255e-07, "epoch": 9.379614498631648, "percentage": 62.53, "elapsed_time": "15:50:50", "remaining_time": "9:29:45", "throughput": 8502.42, "total_tokens": 485069312} {"current_steps": 476500, "total_steps": 761865, "loss": 1.9481, "lr": 3.0802866773950563e-07, "epoch": 9.38158335138115, "percentage": 62.54, "elapsed_time": "15:51:02", "remaining_time": "9:29:33", "throughput": 8502.47, "total_tokens": 485171712} {"current_steps": 476600, "total_steps": 761865, "loss": 2.0063, "lr": 3.0783830588653446e-07, "epoch": 9.383552204130654, "percentage": 62.56, "elapsed_time": "15:51:14", "remaining_time": "9:29:21", "throughput": 8502.51, "total_tokens": 485274112} {"current_steps": 476700, "total_steps": 761865, "loss": 1.9552, "lr": 3.076479767090388e-07, "epoch": 9.385521056880156, "percentage": 62.57, "elapsed_time": "15:51:25", "remaining_time": "9:29:09", "throughput": 8502.56, "total_tokens": 485376512} {"current_steps": 476800, "total_steps": 761865, "loss": 1.964, "lr": 3.074576802393822e-07, "epoch": 9.38748990962966, "percentage": 62.58, "elapsed_time": "15:51:37", "remaining_time": "9:28:57", "throughput": 8502.6, "total_tokens": 485478288} {"current_steps": 476900, "total_steps": 761865, "loss": 1.9986, "lr": 3.0726741650992317e-07, "epoch": 9.389458762379162, "percentage": 62.6, "elapsed_time": "15:51:49", "remaining_time": "9:28:44", "throughput": 8502.64, "total_tokens": 485579840} {"current_steps": 477000, "total_steps": 761865, "loss": 1.9481, "lr": 3.0707718555301434e-07, "epoch": 9.391427615128665, "percentage": 62.61, "elapsed_time": "15:52:01", "remaining_time": "9:28:32", "throughput": 8502.69, "total_tokens": 485682240} {"current_steps": 477100, "total_steps": 761865, "loss": 1.967, "lr": 3.068869874010028e-07, "epoch": 9.393396467878167, "percentage": 62.62, "elapsed_time": "15:52:12", "remaining_time": "9:28:20", "throughput": 8502.73, "total_tokens": 485784424} {"current_steps": 477200, "total_steps": 761865, "loss": 1.9881, "lr": 3.0669682208623047e-07, "epoch": 9.39536532062767, "percentage": 62.64, "elapsed_time": "15:52:24", "remaining_time": "9:28:08", "throughput": 8502.76, "total_tokens": 485885896} {"current_steps": 477300, "total_steps": 761865, "loss": 1.9643, "lr": 3.06506689641033e-07, "epoch": 9.397334173377173, "percentage": 62.65, "elapsed_time": "15:52:36", "remaining_time": "9:27:56", "throughput": 8502.8, "total_tokens": 485987680} {"current_steps": 477400, "total_steps": 761865, "loss": 2.0009, "lr": 3.0631659009774106e-07, "epoch": 9.399303026126676, "percentage": 62.66, "elapsed_time": "15:52:47", "remaining_time": "9:27:44", "throughput": 8502.84, "total_tokens": 486089264} {"current_steps": 477500, "total_steps": 761865, "loss": 1.9808, "lr": 3.061265234886793e-07, "epoch": 9.401271878876178, "percentage": 62.68, "elapsed_time": "15:52:59", "remaining_time": "9:27:32", "throughput": 8502.89, "total_tokens": 486191664} {"current_steps": 477600, "total_steps": 761865, "loss": 1.9908, "lr": 3.059364898461671e-07, "epoch": 9.403240731625681, "percentage": 62.69, "elapsed_time": "15:53:11", "remaining_time": "9:27:19", "throughput": 8502.93, "total_tokens": 486293832} {"current_steps": 477700, "total_steps": 761865, "loss": 1.9616, "lr": 3.0574648920251787e-07, "epoch": 9.405209584375184, "percentage": 62.7, "elapsed_time": "15:53:23", "remaining_time": "9:27:07", "throughput": 8502.97, "total_tokens": 486395472} {"current_steps": 477800, "total_steps": 761865, "loss": 1.9431, "lr": 3.055565215900399e-07, "epoch": 9.407178437124687, "percentage": 62.71, "elapsed_time": "15:53:34", "remaining_time": "9:26:55", "throughput": 8503.01, "total_tokens": 486497872} {"current_steps": 477900, "total_steps": 761865, "loss": 2.0107, "lr": 3.053665870410353e-07, "epoch": 9.40914728987419, "percentage": 62.73, "elapsed_time": "15:53:46", "remaining_time": "9:26:43", "throughput": 8503.06, "total_tokens": 486600272} {"current_steps": 478000, "total_steps": 761865, "loss": 1.9571, "lr": 3.051766855878011e-07, "epoch": 9.411116142623694, "percentage": 62.74, "elapsed_time": "15:53:58", "remaining_time": "9:26:31", "throughput": 8503.1, "total_tokens": 486702672} {"current_steps": 478100, "total_steps": 761865, "loss": 1.9536, "lr": 3.049868172626281e-07, "epoch": 9.413084995373197, "percentage": 62.75, "elapsed_time": "15:54:09", "remaining_time": "9:26:19", "throughput": 8503.14, "total_tokens": 486804256} {"current_steps": 478200, "total_steps": 761865, "loss": 1.9842, "lr": 3.047969820978019e-07, "epoch": 9.4150538481227, "percentage": 62.77, "elapsed_time": "15:54:21", "remaining_time": "9:26:07", "throughput": 8503.18, "total_tokens": 486906656} {"current_steps": 478300, "total_steps": 761865, "loss": 2.025, "lr": 3.046071801256029e-07, "epoch": 9.417022700872202, "percentage": 62.78, "elapsed_time": "15:54:33", "remaining_time": "9:25:55", "throughput": 8503.22, "total_tokens": 487008176} {"current_steps": 478400, "total_steps": 761865, "loss": 1.9808, "lr": 3.044174113783045e-07, "epoch": 9.418991553621705, "percentage": 62.79, "elapsed_time": "15:54:45", "remaining_time": "9:25:42", "throughput": 8503.25, "total_tokens": 487109512} {"current_steps": 478500, "total_steps": 761865, "loss": 1.9879, "lr": 3.04227675888176e-07, "epoch": 9.420960406371208, "percentage": 62.81, "elapsed_time": "15:54:56", "remaining_time": "9:25:30", "throughput": 8503.3, "total_tokens": 487211912} {"current_steps": 478600, "total_steps": 761865, "loss": 1.9978, "lr": 3.0403797368747975e-07, "epoch": 9.42292925912071, "percentage": 62.82, "elapsed_time": "15:55:08", "remaining_time": "9:25:18", "throughput": 8503.34, "total_tokens": 487314312} {"current_steps": 478700, "total_steps": 761865, "loss": 1.9807, "lr": 3.038483048084734e-07, "epoch": 9.424898111870213, "percentage": 62.83, "elapsed_time": "15:55:20", "remaining_time": "9:25:06", "throughput": 8503.39, "total_tokens": 487416280} {"current_steps": 478800, "total_steps": 761865, "loss": 1.9728, "lr": 3.0365866928340833e-07, "epoch": 9.426866964619716, "percentage": 62.85, "elapsed_time": "15:55:31", "remaining_time": "9:24:54", "throughput": 8503.43, "total_tokens": 487517608} {"current_steps": 478900, "total_steps": 761865, "loss": 2.0177, "lr": 3.0346906714453056e-07, "epoch": 9.428835817369219, "percentage": 62.86, "elapsed_time": "15:55:43", "remaining_time": "9:24:42", "throughput": 8503.46, "total_tokens": 487619256} {"current_steps": 479000, "total_steps": 761865, "loss": 1.9777, "lr": 3.032794984240803e-07, "epoch": 9.430804670118722, "percentage": 62.87, "elapsed_time": "15:55:55", "remaining_time": "9:24:30", "throughput": 8503.51, "total_tokens": 487721656} {"current_steps": 479100, "total_steps": 761865, "loss": 1.9758, "lr": 3.0308996315429205e-07, "epoch": 9.432773522868224, "percentage": 62.89, "elapsed_time": "15:56:07", "remaining_time": "9:24:18", "throughput": 8503.55, "total_tokens": 487824056} {"current_steps": 479200, "total_steps": 761865, "loss": 1.9564, "lr": 3.029004613673949e-07, "epoch": 9.434742375617727, "percentage": 62.9, "elapsed_time": "15:56:18", "remaining_time": "9:24:05", "throughput": 8503.59, "total_tokens": 487925704} {"current_steps": 479300, "total_steps": 761865, "loss": 1.9816, "lr": 3.0271099309561164e-07, "epoch": 9.43671122836723, "percentage": 62.91, "elapsed_time": "15:56:30", "remaining_time": "9:23:53", "throughput": 8503.64, "total_tokens": 488028104} {"current_steps": 479400, "total_steps": 761865, "loss": 1.9441, "lr": 3.0252155837116023e-07, "epoch": 9.438680081116733, "percentage": 62.92, "elapsed_time": "15:56:42", "remaining_time": "9:23:41", "throughput": 8503.68, "total_tokens": 488129640} {"current_steps": 479500, "total_steps": 761865, "loss": 1.9221, "lr": 3.023321572262521e-07, "epoch": 9.440648933866235, "percentage": 62.94, "elapsed_time": "15:56:53", "remaining_time": "9:23:29", "throughput": 8503.72, "total_tokens": 488232040} {"current_steps": 479600, "total_steps": 761865, "loss": 1.9781, "lr": 3.021427896930935e-07, "epoch": 9.442617786615738, "percentage": 62.95, "elapsed_time": "15:57:05", "remaining_time": "9:23:17", "throughput": 8503.76, "total_tokens": 488334256} {"current_steps": 479700, "total_steps": 761865, "loss": 2.0058, "lr": 3.019534558038846e-07, "epoch": 9.444586639365243, "percentage": 62.96, "elapsed_time": "15:57:17", "remaining_time": "9:23:05", "throughput": 8503.81, "total_tokens": 488436656} {"current_steps": 479800, "total_steps": 761865, "loss": 1.9889, "lr": 3.0176415559082026e-07, "epoch": 9.446555492114745, "percentage": 62.98, "elapsed_time": "15:57:29", "remaining_time": "9:22:53", "throughput": 8503.85, "total_tokens": 488539056} {"current_steps": 479900, "total_steps": 761865, "loss": 2.0041, "lr": 3.0157488908608917e-07, "epoch": 9.448524344864248, "percentage": 62.99, "elapsed_time": "15:57:40", "remaining_time": "9:22:41", "throughput": 8503.89, "total_tokens": 488640640} {"current_steps": 480000, "total_steps": 761865, "loss": 2.0161, "lr": 3.0138565632187463e-07, "epoch": 9.450493197613751, "percentage": 63.0, "elapsed_time": "15:57:52", "remaining_time": "9:22:28", "throughput": 8503.92, "total_tokens": 488741480} {"current_steps": 480100, "total_steps": 761865, "loss": 1.959, "lr": 3.0119645733035406e-07, "epoch": 9.452462050363254, "percentage": 63.02, "elapsed_time": "15:58:04", "remaining_time": "9:22:17", "throughput": 8503.87, "total_tokens": 488843120} {"current_steps": 480200, "total_steps": 761865, "loss": 1.9811, "lr": 3.01007292143699e-07, "epoch": 9.454430903112756, "percentage": 63.03, "elapsed_time": "15:58:16", "remaining_time": "9:22:04", "throughput": 8503.91, "total_tokens": 488944896} {"current_steps": 480300, "total_steps": 761865, "loss": 1.9601, "lr": 3.008181607940757e-07, "epoch": 9.45639975586226, "percentage": 63.04, "elapsed_time": "15:58:28", "remaining_time": "9:21:52", "throughput": 8503.95, "total_tokens": 489047064} {"current_steps": 480400, "total_steps": 761865, "loss": 2.0049, "lr": 3.00629063313644e-07, "epoch": 9.458368608611762, "percentage": 63.06, "elapsed_time": "15:58:39", "remaining_time": "9:21:40", "throughput": 8504.0, "total_tokens": 489148944} {"current_steps": 480500, "total_steps": 761865, "loss": 1.975, "lr": 3.004399997345588e-07, "epoch": 9.460337461361265, "percentage": 63.07, "elapsed_time": "15:58:51", "remaining_time": "9:21:28", "throughput": 8504.04, "total_tokens": 489251344} {"current_steps": 480600, "total_steps": 761865, "loss": 1.9407, "lr": 3.0025097008896814e-07, "epoch": 9.462306314110768, "percentage": 63.08, "elapsed_time": "15:59:03", "remaining_time": "9:21:16", "throughput": 8504.09, "total_tokens": 489353744} {"current_steps": 480700, "total_steps": 761865, "loss": 2.0201, "lr": 3.000619744090156e-07, "epoch": 9.46427516686027, "percentage": 63.1, "elapsed_time": "15:59:14", "remaining_time": "9:21:04", "throughput": 8504.12, "total_tokens": 489453912} {"current_steps": 480800, "total_steps": 761865, "loss": 1.9823, "lr": 2.998730127268376e-07, "epoch": 9.466244019609773, "percentage": 63.11, "elapsed_time": "15:59:26", "remaining_time": "9:20:52", "throughput": 8504.15, "total_tokens": 489554936} {"current_steps": 480900, "total_steps": 761865, "loss": 1.9776, "lr": 2.996840850745662e-07, "epoch": 9.468212872359276, "percentage": 63.12, "elapsed_time": "15:59:38", "remaining_time": "9:20:39", "throughput": 8504.2, "total_tokens": 489656792} {"current_steps": 481000, "total_steps": 761865, "loss": 1.9719, "lr": 2.994951914843262e-07, "epoch": 9.470181725108779, "percentage": 63.13, "elapsed_time": "15:59:50", "remaining_time": "9:20:27", "throughput": 8504.24, "total_tokens": 489759192} {"current_steps": 481100, "total_steps": 761865, "loss": 2.0045, "lr": 2.993063319882382e-07, "epoch": 9.472150577858281, "percentage": 63.15, "elapsed_time": "16:00:01", "remaining_time": "9:20:15", "throughput": 8504.28, "total_tokens": 489860464} {"current_steps": 481200, "total_steps": 761865, "loss": 1.9754, "lr": 2.9911750661841526e-07, "epoch": 9.474119430607784, "percentage": 63.16, "elapsed_time": "16:00:13", "remaining_time": "9:20:03", "throughput": 8504.32, "total_tokens": 489962864} {"current_steps": 481300, "total_steps": 761865, "loss": 1.9865, "lr": 2.989287154069662e-07, "epoch": 9.476088283357289, "percentage": 63.17, "elapsed_time": "16:00:25", "remaining_time": "9:19:51", "throughput": 8504.36, "total_tokens": 490065056} {"current_steps": 481400, "total_steps": 761865, "loss": 1.9861, "lr": 2.987399583859932e-07, "epoch": 9.478057136106791, "percentage": 63.19, "elapsed_time": "16:00:36", "remaining_time": "9:19:39", "throughput": 8504.41, "total_tokens": 490167456} {"current_steps": 481500, "total_steps": 761865, "loss": 1.9892, "lr": 2.9855123558759275e-07, "epoch": 9.480025988856294, "percentage": 63.2, "elapsed_time": "16:00:48", "remaining_time": "9:19:27", "throughput": 8504.44, "total_tokens": 490269040} {"current_steps": 481600, "total_steps": 761865, "loss": 1.9572, "lr": 2.9836254704385567e-07, "epoch": 9.481994841605797, "percentage": 63.21, "elapsed_time": "16:01:00", "remaining_time": "9:19:15", "throughput": 8504.49, "total_tokens": 490371440} {"current_steps": 481700, "total_steps": 761865, "loss": 1.9963, "lr": 2.981738927868667e-07, "epoch": 9.4839636943553, "percentage": 63.23, "elapsed_time": "16:01:12", "remaining_time": "9:19:03", "throughput": 8504.53, "total_tokens": 490473840} {"current_steps": 481800, "total_steps": 761865, "loss": 2.0024, "lr": 2.9798527284870503e-07, "epoch": 9.485932547104802, "percentage": 63.24, "elapsed_time": "16:01:23", "remaining_time": "9:18:50", "throughput": 8504.56, "total_tokens": 490573944} {"current_steps": 481900, "total_steps": 761865, "loss": 2.039, "lr": 2.977966872614437e-07, "epoch": 9.487901399854305, "percentage": 63.25, "elapsed_time": "16:01:35", "remaining_time": "9:18:38", "throughput": 8504.59, "total_tokens": 490674256} {"current_steps": 482000, "total_steps": 761865, "loss": 1.9972, "lr": 2.976081360571504e-07, "epoch": 9.489870252603808, "percentage": 63.27, "elapsed_time": "16:01:46", "remaining_time": "9:18:26", "throughput": 8504.63, "total_tokens": 490776656} {"current_steps": 482100, "total_steps": 761865, "loss": 2.0485, "lr": 2.9741961926788637e-07, "epoch": 9.49183910535331, "percentage": 63.28, "elapsed_time": "16:01:58", "remaining_time": "9:18:14", "throughput": 8504.67, "total_tokens": 490878264} {"current_steps": 482200, "total_steps": 761865, "loss": 1.9917, "lr": 2.9723113692570755e-07, "epoch": 9.493807958102813, "percentage": 63.29, "elapsed_time": "16:02:10", "remaining_time": "9:18:02", "throughput": 8504.72, "total_tokens": 490980664} {"current_steps": 482300, "total_steps": 761865, "loss": 1.9525, "lr": 2.970426890626637e-07, "epoch": 9.495776810852316, "percentage": 63.31, "elapsed_time": "16:02:22", "remaining_time": "9:17:50", "throughput": 8504.76, "total_tokens": 491083064} {"current_steps": 482400, "total_steps": 761865, "loss": 2.036, "lr": 2.9685427571079856e-07, "epoch": 9.497745663601819, "percentage": 63.32, "elapsed_time": "16:02:33", "remaining_time": "9:17:38", "throughput": 8504.79, "total_tokens": 491183808} {"current_steps": 482500, "total_steps": 761865, "loss": 1.969, "lr": 2.9666589690215066e-07, "epoch": 9.499714516351322, "percentage": 63.33, "elapsed_time": "16:02:45", "remaining_time": "9:17:25", "throughput": 8504.84, "total_tokens": 491286208} {"current_steps": 482600, "total_steps": 761865, "loss": 2.0328, "lr": 2.9647755266875187e-07, "epoch": 9.501683369100824, "percentage": 63.34, "elapsed_time": "16:02:57", "remaining_time": "9:17:13", "throughput": 8504.87, "total_tokens": 491387224} {"current_steps": 482700, "total_steps": 761865, "loss": 2.0247, "lr": 2.962892430426287e-07, "epoch": 9.503652221850327, "percentage": 63.36, "elapsed_time": "16:03:08", "remaining_time": "9:17:01", "throughput": 8504.91, "total_tokens": 491488816} {"current_steps": 482800, "total_steps": 761865, "loss": 1.9656, "lr": 2.9610096805580155e-07, "epoch": 9.50562107459983, "percentage": 63.37, "elapsed_time": "16:03:20", "remaining_time": "9:16:49", "throughput": 8504.95, "total_tokens": 491590696} {"current_steps": 482900, "total_steps": 761865, "loss": 1.9105, "lr": 2.9591272774028504e-07, "epoch": 9.507589927349333, "percentage": 63.38, "elapsed_time": "16:03:32", "remaining_time": "9:16:37", "throughput": 8505.0, "total_tokens": 491693096} {"current_steps": 483000, "total_steps": 761865, "loss": 1.9887, "lr": 2.9572452212808774e-07, "epoch": 9.509558780098835, "percentage": 63.4, "elapsed_time": "16:03:43", "remaining_time": "9:16:25", "throughput": 8505.03, "total_tokens": 491794912} {"current_steps": 483100, "total_steps": 761865, "loss": 1.9926, "lr": 2.9553635125121267e-07, "epoch": 9.51152763284834, "percentage": 63.41, "elapsed_time": "16:03:55", "remaining_time": "9:16:13", "throughput": 8505.08, "total_tokens": 491897312} {"current_steps": 483200, "total_steps": 761865, "loss": 2.0144, "lr": 2.953482151416564e-07, "epoch": 9.513496485597843, "percentage": 63.42, "elapsed_time": "16:04:07", "remaining_time": "9:16:01", "throughput": 8505.12, "total_tokens": 491999712} {"current_steps": 483300, "total_steps": 761865, "loss": 1.9935, "lr": 2.9516011383140994e-07, "epoch": 9.515465338347346, "percentage": 63.44, "elapsed_time": "16:04:19", "remaining_time": "9:15:48", "throughput": 8505.17, "total_tokens": 492102112} {"current_steps": 483400, "total_steps": 761865, "loss": 1.9682, "lr": 2.9497204735245874e-07, "epoch": 9.517434191096848, "percentage": 63.45, "elapsed_time": "16:04:30", "remaining_time": "9:15:36", "throughput": 8505.21, "total_tokens": 492204512} {"current_steps": 483500, "total_steps": 761865, "loss": 1.9826, "lr": 2.9478401573678124e-07, "epoch": 9.519403043846351, "percentage": 63.46, "elapsed_time": "16:04:42", "remaining_time": "9:15:24", "throughput": 8505.25, "total_tokens": 492306088} {"current_steps": 483600, "total_steps": 761865, "loss": 1.9787, "lr": 2.9459601901635135e-07, "epoch": 9.521371896595854, "percentage": 63.48, "elapsed_time": "16:04:54", "remaining_time": "9:15:12", "throughput": 8505.29, "total_tokens": 492408488} {"current_steps": 483700, "total_steps": 761865, "loss": 2.0177, "lr": 2.944080572231357e-07, "epoch": 9.523340749345357, "percentage": 63.49, "elapsed_time": "16:05:06", "remaining_time": "9:15:00", "throughput": 8505.33, "total_tokens": 492510224} {"current_steps": 483800, "total_steps": 761865, "loss": 1.9909, "lr": 2.942201303890961e-07, "epoch": 9.52530960209486, "percentage": 63.5, "elapsed_time": "16:05:17", "remaining_time": "9:14:48", "throughput": 8505.38, "total_tokens": 492612624} {"current_steps": 483900, "total_steps": 761865, "loss": 1.9944, "lr": 2.940322385461874e-07, "epoch": 9.527278454844362, "percentage": 63.52, "elapsed_time": "16:05:29", "remaining_time": "9:14:36", "throughput": 8505.42, "total_tokens": 492714232} {"current_steps": 484000, "total_steps": 761865, "loss": 1.982, "lr": 2.938443817263597e-07, "epoch": 9.529247307593865, "percentage": 63.53, "elapsed_time": "16:05:41", "remaining_time": "9:14:24", "throughput": 8505.46, "total_tokens": 492816632} {"current_steps": 484100, "total_steps": 761865, "loss": 1.9994, "lr": 2.9365655996155573e-07, "epoch": 9.531216160343368, "percentage": 63.54, "elapsed_time": "16:05:52", "remaining_time": "9:14:12", "throughput": 8505.5, "total_tokens": 492919024} {"current_steps": 484200, "total_steps": 761865, "loss": 1.9182, "lr": 2.934687732837135e-07, "epoch": 9.53318501309287, "percentage": 63.55, "elapsed_time": "16:06:04", "remaining_time": "9:13:59", "throughput": 8505.54, "total_tokens": 493021424} {"current_steps": 484300, "total_steps": 761865, "loss": 1.9992, "lr": 2.9328102172476447e-07, "epoch": 9.535153865842373, "percentage": 63.57, "elapsed_time": "16:06:16", "remaining_time": "9:13:47", "throughput": 8505.58, "total_tokens": 493122904} {"current_steps": 484400, "total_steps": 761865, "loss": 2.0263, "lr": 2.930933053166341e-07, "epoch": 9.537122718591876, "percentage": 63.58, "elapsed_time": "16:06:28", "remaining_time": "9:13:35", "throughput": 8505.62, "total_tokens": 493224592} {"current_steps": 484500, "total_steps": 761865, "loss": 1.9926, "lr": 2.9290562409124207e-07, "epoch": 9.539091571341379, "percentage": 63.59, "elapsed_time": "16:06:39", "remaining_time": "9:13:23", "throughput": 8505.66, "total_tokens": 493326136} {"current_steps": 484600, "total_steps": 761865, "loss": 1.975, "lr": 2.927179780805019e-07, "epoch": 9.541060424090883, "percentage": 63.61, "elapsed_time": "16:06:51", "remaining_time": "9:13:11", "throughput": 8505.7, "total_tokens": 493428536} {"current_steps": 484700, "total_steps": 761865, "loss": 1.9885, "lr": 2.925303673163213e-07, "epoch": 9.543029276840386, "percentage": 63.62, "elapsed_time": "16:07:03", "remaining_time": "9:12:59", "throughput": 8505.74, "total_tokens": 493530936} {"current_steps": 484800, "total_steps": 761865, "loss": 1.9855, "lr": 2.923427918306018e-07, "epoch": 9.544998129589889, "percentage": 63.63, "elapsed_time": "16:07:14", "remaining_time": "9:12:47", "throughput": 8505.78, "total_tokens": 493632416} {"current_steps": 484900, "total_steps": 761865, "loss": 1.9792, "lr": 2.9215525165523914e-07, "epoch": 9.546966982339391, "percentage": 63.65, "elapsed_time": "16:07:26", "remaining_time": "9:12:35", "throughput": 8505.82, "total_tokens": 493734264} {"current_steps": 485000, "total_steps": 761865, "loss": 1.989, "lr": 2.919677468221229e-07, "epoch": 9.548935835088894, "percentage": 63.66, "elapsed_time": "16:07:38", "remaining_time": "9:12:22", "throughput": 8505.86, "total_tokens": 493836040} {"current_steps": 485100, "total_steps": 761865, "loss": 1.9415, "lr": 2.917802773631367e-07, "epoch": 9.550904687838397, "percentage": 63.67, "elapsed_time": "16:07:50", "remaining_time": "9:12:11", "throughput": 8505.81, "total_tokens": 493937768} {"current_steps": 485200, "total_steps": 761865, "loss": 2.0194, "lr": 2.9159284331015797e-07, "epoch": 9.5528735405879, "percentage": 63.69, "elapsed_time": "16:08:02", "remaining_time": "9:11:59", "throughput": 8505.85, "total_tokens": 494040168} {"current_steps": 485300, "total_steps": 761865, "loss": 1.9741, "lr": 2.914054446950586e-07, "epoch": 9.554842393337402, "percentage": 63.7, "elapsed_time": "16:08:14", "remaining_time": "9:11:46", "throughput": 8505.89, "total_tokens": 494141928} {"current_steps": 485400, "total_steps": 761865, "loss": 2.0084, "lr": 2.912180815497039e-07, "epoch": 9.556811246086905, "percentage": 63.71, "elapsed_time": "16:08:25", "remaining_time": "9:11:34", "throughput": 8505.93, "total_tokens": 494243072} {"current_steps": 485500, "total_steps": 761865, "loss": 2.0252, "lr": 2.9103075390595347e-07, "epoch": 9.558780098836408, "percentage": 63.73, "elapsed_time": "16:08:37", "remaining_time": "9:11:22", "throughput": 8505.96, "total_tokens": 494343600} {"current_steps": 485600, "total_steps": 761865, "loss": 1.9835, "lr": 2.9084346179566107e-07, "epoch": 9.56074895158591, "percentage": 63.74, "elapsed_time": "16:08:49", "remaining_time": "9:11:10", "throughput": 8506.0, "total_tokens": 494446000} {"current_steps": 485700, "total_steps": 761865, "loss": 2.0066, "lr": 2.906562052506736e-07, "epoch": 9.562717804335414, "percentage": 63.75, "elapsed_time": "16:09:00", "remaining_time": "9:10:58", "throughput": 8506.04, "total_tokens": 494548400} {"current_steps": 485800, "total_steps": 761865, "loss": 2.0113, "lr": 2.9046898430283286e-07, "epoch": 9.564686657084916, "percentage": 63.76, "elapsed_time": "16:09:12", "remaining_time": "9:10:46", "throughput": 8506.08, "total_tokens": 494650040} {"current_steps": 485900, "total_steps": 761865, "loss": 1.9713, "lr": 2.9028179898397397e-07, "epoch": 9.566655509834419, "percentage": 63.78, "elapsed_time": "16:09:24", "remaining_time": "9:10:34", "throughput": 8506.13, "total_tokens": 494752440} {"current_steps": 486000, "total_steps": 761865, "loss": 2.033, "lr": 2.9009464932592653e-07, "epoch": 9.568624362583922, "percentage": 63.79, "elapsed_time": "16:09:35", "remaining_time": "9:10:22", "throughput": 8506.17, "total_tokens": 494854840} {"current_steps": 486100, "total_steps": 761865, "loss": 2.0372, "lr": 2.8990753536051335e-07, "epoch": 9.570593215333425, "percentage": 63.8, "elapsed_time": "16:09:47", "remaining_time": "9:10:09", "throughput": 8506.2, "total_tokens": 494955728} {"current_steps": 486200, "total_steps": 761865, "loss": 1.9987, "lr": 2.8972045711955186e-07, "epoch": 9.572562068082927, "percentage": 63.82, "elapsed_time": "16:09:59", "remaining_time": "9:09:57", "throughput": 8506.25, "total_tokens": 495058128} {"current_steps": 486300, "total_steps": 761865, "loss": 1.9405, "lr": 2.89533414634853e-07, "epoch": 9.57453092083243, "percentage": 63.83, "elapsed_time": "16:10:11", "remaining_time": "9:09:45", "throughput": 8506.29, "total_tokens": 495160024} {"current_steps": 486400, "total_steps": 761865, "loss": 1.9612, "lr": 2.8934640793822184e-07, "epoch": 9.576499773581935, "percentage": 63.84, "elapsed_time": "16:10:22", "remaining_time": "9:09:33", "throughput": 8506.33, "total_tokens": 495262424} {"current_steps": 486500, "total_steps": 761865, "loss": 2.0034, "lr": 2.891594370614575e-07, "epoch": 9.578468626331437, "percentage": 63.86, "elapsed_time": "16:10:34", "remaining_time": "9:09:21", "throughput": 8506.37, "total_tokens": 495364824} {"current_steps": 486600, "total_steps": 761865, "loss": 2.0004, "lr": 2.8897250203635227e-07, "epoch": 9.58043747908094, "percentage": 63.87, "elapsed_time": "16:10:46", "remaining_time": "9:09:09", "throughput": 8506.41, "total_tokens": 495466600} {"current_steps": 486700, "total_steps": 761865, "loss": 1.9654, "lr": 2.8878560289469323e-07, "epoch": 9.582406331830443, "percentage": 63.88, "elapsed_time": "16:10:57", "remaining_time": "9:08:57", "throughput": 8506.46, "total_tokens": 495569000} {"current_steps": 486800, "total_steps": 761865, "loss": 1.9751, "lr": 2.88598739668261e-07, "epoch": 9.584375184579946, "percentage": 63.9, "elapsed_time": "16:11:09", "remaining_time": "9:08:45", "throughput": 8506.49, "total_tokens": 495670232} {"current_steps": 486900, "total_steps": 761865, "loss": 1.9639, "lr": 2.8841191238883024e-07, "epoch": 9.586344037329448, "percentage": 63.91, "elapsed_time": "16:11:21", "remaining_time": "9:08:32", "throughput": 8506.53, "total_tokens": 495771984} {"current_steps": 487000, "total_steps": 761865, "loss": 1.9311, "lr": 2.8822512108816895e-07, "epoch": 9.588312890078951, "percentage": 63.92, "elapsed_time": "16:11:33", "remaining_time": "9:08:20", "throughput": 8506.57, "total_tokens": 495874384} {"current_steps": 487100, "total_steps": 761865, "loss": 1.9724, "lr": 2.880383657980396e-07, "epoch": 9.590281742828454, "percentage": 63.94, "elapsed_time": "16:11:44", "remaining_time": "9:08:08", "throughput": 8506.62, "total_tokens": 495976248} {"current_steps": 487200, "total_steps": 761865, "loss": 1.9517, "lr": 2.8785164655019837e-07, "epoch": 9.592250595577957, "percentage": 63.95, "elapsed_time": "16:11:56", "remaining_time": "9:07:56", "throughput": 8506.66, "total_tokens": 496078368} {"current_steps": 487300, "total_steps": 761865, "loss": 1.9817, "lr": 2.876649633763953e-07, "epoch": 9.59421944832746, "percentage": 63.96, "elapsed_time": "16:12:08", "remaining_time": "9:07:44", "throughput": 8506.7, "total_tokens": 496180008} {"current_steps": 487400, "total_steps": 761865, "loss": 2.005, "lr": 2.874783163083746e-07, "epoch": 9.596188301076962, "percentage": 63.97, "elapsed_time": "16:12:19", "remaining_time": "9:07:32", "throughput": 8506.74, "total_tokens": 496281200} {"current_steps": 487500, "total_steps": 761865, "loss": 1.9451, "lr": 2.872917053778732e-07, "epoch": 9.598157153826465, "percentage": 63.99, "elapsed_time": "16:12:31", "remaining_time": "9:07:20", "throughput": 8506.78, "total_tokens": 496383600} {"current_steps": 487600, "total_steps": 761865, "loss": 2.006, "lr": 2.871051306166237e-07, "epoch": 9.600126006575968, "percentage": 64.0, "elapsed_time": "16:12:43", "remaining_time": "9:07:08", "throughput": 8506.82, "total_tokens": 496485952} {"current_steps": 487700, "total_steps": 761865, "loss": 2.0255, "lr": 2.869185920563509e-07, "epoch": 9.60209485932547, "percentage": 64.01, "elapsed_time": "16:12:55", "remaining_time": "9:06:56", "throughput": 8506.86, "total_tokens": 496588352} {"current_steps": 487800, "total_steps": 761865, "loss": 1.979, "lr": 2.867320897287745e-07, "epoch": 9.604063712074973, "percentage": 64.03, "elapsed_time": "16:13:06", "remaining_time": "9:06:43", "throughput": 8506.9, "total_tokens": 496689888} {"current_steps": 487900, "total_steps": 761865, "loss": 1.9682, "lr": 2.8654562366560695e-07, "epoch": 9.606032564824476, "percentage": 64.04, "elapsed_time": "16:13:18", "remaining_time": "9:06:31", "throughput": 8506.94, "total_tokens": 496792288} {"current_steps": 488000, "total_steps": 761865, "loss": 1.9592, "lr": 2.863591938985563e-07, "epoch": 9.60800141757398, "percentage": 64.05, "elapsed_time": "16:13:30", "remaining_time": "9:06:19", "throughput": 8506.98, "total_tokens": 496893816} {"current_steps": 488100, "total_steps": 761865, "loss": 1.9533, "lr": 2.8617280045932254e-07, "epoch": 9.609970270323483, "percentage": 64.07, "elapsed_time": "16:13:41", "remaining_time": "9:06:07", "throughput": 8507.02, "total_tokens": 496996216} {"current_steps": 488200, "total_steps": 761865, "loss": 1.9905, "lr": 2.859864433796008e-07, "epoch": 9.611939123072986, "percentage": 64.08, "elapsed_time": "16:13:53", "remaining_time": "9:05:55", "throughput": 8507.06, "total_tokens": 497098616} {"current_steps": 488300, "total_steps": 761865, "loss": 1.9753, "lr": 2.858001226910788e-07, "epoch": 9.613907975822489, "percentage": 64.09, "elapsed_time": "16:14:05", "remaining_time": "9:05:43", "throughput": 8507.1, "total_tokens": 497200288} {"current_steps": 488400, "total_steps": 761865, "loss": 1.9834, "lr": 2.8561383842543953e-07, "epoch": 9.615876828571992, "percentage": 64.11, "elapsed_time": "16:14:17", "remaining_time": "9:05:31", "throughput": 8507.14, "total_tokens": 497302144} {"current_steps": 488500, "total_steps": 761865, "loss": 2.0187, "lr": 2.85427590614359e-07, "epoch": 9.617845681321494, "percentage": 64.12, "elapsed_time": "16:14:28", "remaining_time": "9:05:19", "throughput": 8507.17, "total_tokens": 497403072} {"current_steps": 488600, "total_steps": 761865, "loss": 1.9858, "lr": 2.8524137928950676e-07, "epoch": 9.619814534070997, "percentage": 64.13, "elapsed_time": "16:14:40", "remaining_time": "9:05:07", "throughput": 8507.22, "total_tokens": 497505472} {"current_steps": 488700, "total_steps": 761865, "loss": 1.9786, "lr": 2.8505520448254647e-07, "epoch": 9.6217833868205, "percentage": 64.15, "elapsed_time": "16:14:52", "remaining_time": "9:04:54", "throughput": 8507.26, "total_tokens": 497607288} {"current_steps": 488800, "total_steps": 761865, "loss": 2.017, "lr": 2.848690662251359e-07, "epoch": 9.623752239570003, "percentage": 64.16, "elapsed_time": "16:15:03", "remaining_time": "9:04:42", "throughput": 8507.29, "total_tokens": 497708920} {"current_steps": 488900, "total_steps": 761865, "loss": 2.0175, "lr": 2.8468296454892625e-07, "epoch": 9.625721092319505, "percentage": 64.17, "elapsed_time": "16:15:15", "remaining_time": "9:04:30", "throughput": 8507.34, "total_tokens": 497811320} {"current_steps": 489000, "total_steps": 761865, "loss": 1.9561, "lr": 2.8449689948556223e-07, "epoch": 9.627689945069008, "percentage": 64.18, "elapsed_time": "16:15:27", "remaining_time": "9:04:18", "throughput": 8507.38, "total_tokens": 497913720} {"current_steps": 489100, "total_steps": 761865, "loss": 1.9508, "lr": 2.843108710666828e-07, "epoch": 9.62965879781851, "percentage": 64.2, "elapsed_time": "16:15:38", "remaining_time": "9:04:06", "throughput": 8507.42, "total_tokens": 498015576} {"current_steps": 489200, "total_steps": 761865, "loss": 2.0133, "lr": 2.841248793239205e-07, "epoch": 9.631627650568014, "percentage": 64.21, "elapsed_time": "16:15:50", "remaining_time": "9:03:54", "throughput": 8507.46, "total_tokens": 498117384} {"current_steps": 489300, "total_steps": 761865, "loss": 1.9905, "lr": 2.8393892428890176e-07, "epoch": 9.633596503317516, "percentage": 64.22, "elapsed_time": "16:16:02", "remaining_time": "9:03:42", "throughput": 8507.5, "total_tokens": 498219784} {"current_steps": 489400, "total_steps": 761865, "loss": 1.9921, "lr": 2.837530059932468e-07, "epoch": 9.63556535606702, "percentage": 64.24, "elapsed_time": "16:16:14", "remaining_time": "9:03:30", "throughput": 8507.54, "total_tokens": 498321480} {"current_steps": 489500, "total_steps": 761865, "loss": 1.9707, "lr": 2.8356712446856903e-07, "epoch": 9.637534208816522, "percentage": 64.25, "elapsed_time": "16:16:25", "remaining_time": "9:03:18", "throughput": 8507.58, "total_tokens": 498423232} {"current_steps": 489600, "total_steps": 761865, "loss": 1.9575, "lr": 2.8338127974647623e-07, "epoch": 9.639503061566025, "percentage": 64.26, "elapsed_time": "16:16:37", "remaining_time": "9:03:05", "throughput": 8507.62, "total_tokens": 498525632} {"current_steps": 489700, "total_steps": 761865, "loss": 1.9986, "lr": 2.8319547185856983e-07, "epoch": 9.641471914315527, "percentage": 64.28, "elapsed_time": "16:16:49", "remaining_time": "9:02:53", "throughput": 8507.66, "total_tokens": 498627744} {"current_steps": 489800, "total_steps": 761865, "loss": 1.9953, "lr": 2.8300970083644505e-07, "epoch": 9.643440767065032, "percentage": 64.29, "elapsed_time": "16:17:00", "remaining_time": "9:02:41", "throughput": 8507.7, "total_tokens": 498729304} {"current_steps": 489900, "total_steps": 761865, "loss": 1.9903, "lr": 2.828239667116902e-07, "epoch": 9.645409619814535, "percentage": 64.3, "elapsed_time": "16:17:12", "remaining_time": "9:02:29", "throughput": 8507.74, "total_tokens": 498831704} {"current_steps": 490000, "total_steps": 761865, "loss": 1.9601, "lr": 2.82638269515888e-07, "epoch": 9.647378472564037, "percentage": 64.32, "elapsed_time": "16:17:24", "remaining_time": "9:02:17", "throughput": 8507.78, "total_tokens": 498933656} {"current_steps": 490100, "total_steps": 761865, "loss": 1.9976, "lr": 2.8245260928061485e-07, "epoch": 9.64934732531354, "percentage": 64.33, "elapsed_time": "16:17:36", "remaining_time": "9:02:05", "throughput": 8507.73, "total_tokens": 499036056} {"current_steps": 490200, "total_steps": 761865, "loss": 1.9393, "lr": 2.8226698603744084e-07, "epoch": 9.651316178063043, "percentage": 64.34, "elapsed_time": "16:17:48", "remaining_time": "9:01:53", "throughput": 8507.77, "total_tokens": 499137696} {"current_steps": 490300, "total_steps": 761865, "loss": 2.0059, "lr": 2.820813998179291e-07, "epoch": 9.653285030812546, "percentage": 64.36, "elapsed_time": "16:18:00", "remaining_time": "9:01:41", "throughput": 8507.81, "total_tokens": 499240096} {"current_steps": 490400, "total_steps": 761865, "loss": 2.0026, "lr": 2.818958506536372e-07, "epoch": 9.655253883562049, "percentage": 64.37, "elapsed_time": "16:18:11", "remaining_time": "9:01:29", "throughput": 8507.86, "total_tokens": 499342496} {"current_steps": 490500, "total_steps": 761865, "loss": 2.002, "lr": 2.817103385761167e-07, "epoch": 9.657222736311551, "percentage": 64.38, "elapsed_time": "16:18:23", "remaining_time": "9:01:17", "throughput": 8507.89, "total_tokens": 499444128} {"current_steps": 490600, "total_steps": 761865, "loss": 1.9577, "lr": 2.815248636169118e-07, "epoch": 9.659191589061054, "percentage": 64.39, "elapsed_time": "16:18:35", "remaining_time": "9:01:05", "throughput": 8507.94, "total_tokens": 499546528} {"current_steps": 490700, "total_steps": 761865, "loss": 1.9521, "lr": 2.813394258075613e-07, "epoch": 9.661160441810557, "percentage": 64.41, "elapsed_time": "16:18:47", "remaining_time": "9:00:53", "throughput": 8507.98, "total_tokens": 499648928} {"current_steps": 490800, "total_steps": 761865, "loss": 1.9455, "lr": 2.811540251795968e-07, "epoch": 9.66312929456006, "percentage": 64.42, "elapsed_time": "16:18:58", "remaining_time": "9:00:40", "throughput": 8508.03, "total_tokens": 499751328} {"current_steps": 490900, "total_steps": 761865, "loss": 1.9988, "lr": 2.809686617645449e-07, "epoch": 9.665098147309562, "percentage": 64.43, "elapsed_time": "16:19:10", "remaining_time": "9:00:28", "throughput": 8508.07, "total_tokens": 499853024} {"current_steps": 491000, "total_steps": 761865, "loss": 2.0047, "lr": 2.8078333559392445e-07, "epoch": 9.667067000059065, "percentage": 64.45, "elapsed_time": "16:19:22", "remaining_time": "9:00:16", "throughput": 8508.11, "total_tokens": 499954528} {"current_steps": 491100, "total_steps": 761865, "loss": 1.9715, "lr": 2.805980466992488e-07, "epoch": 9.669035852808568, "percentage": 64.46, "elapsed_time": "16:19:33", "remaining_time": "9:00:04", "throughput": 8508.15, "total_tokens": 500056312} {"current_steps": 491200, "total_steps": 761865, "loss": 1.9975, "lr": 2.804127951120248e-07, "epoch": 9.67100470555807, "percentage": 64.47, "elapsed_time": "16:19:45", "remaining_time": "8:59:52", "throughput": 8508.19, "total_tokens": 500158144} {"current_steps": 491300, "total_steps": 761865, "loss": 1.9748, "lr": 2.802275808637529e-07, "epoch": 9.672973558307575, "percentage": 64.49, "elapsed_time": "16:19:57", "remaining_time": "8:59:40", "throughput": 8508.23, "total_tokens": 500260544} {"current_steps": 491400, "total_steps": 761865, "loss": 2.0078, "lr": 2.800424039859275e-07, "epoch": 9.674942411057078, "percentage": 64.5, "elapsed_time": "16:20:08", "remaining_time": "8:59:28", "throughput": 8508.27, "total_tokens": 500361696} {"current_steps": 491500, "total_steps": 761865, "loss": 2.0308, "lr": 2.7985726451003575e-07, "epoch": 9.67691126380658, "percentage": 64.51, "elapsed_time": "16:20:20", "remaining_time": "8:59:16", "throughput": 8508.3, "total_tokens": 500462624} {"current_steps": 491600, "total_steps": 761865, "loss": 1.976, "lr": 2.796721624675595e-07, "epoch": 9.678880116556083, "percentage": 64.53, "elapsed_time": "16:20:32", "remaining_time": "8:59:03", "throughput": 8508.34, "total_tokens": 500565024} {"current_steps": 491700, "total_steps": 761865, "loss": 1.9558, "lr": 2.7948709788997373e-07, "epoch": 9.680848969305586, "percentage": 64.54, "elapsed_time": "16:20:43", "remaining_time": "8:58:51", "throughput": 8508.38, "total_tokens": 500666680} {"current_steps": 491800, "total_steps": 761865, "loss": 2.0421, "lr": 2.7930207080874723e-07, "epoch": 9.682817822055089, "percentage": 64.55, "elapsed_time": "16:20:55", "remaining_time": "8:58:39", "throughput": 8508.42, "total_tokens": 500769080} {"current_steps": 491900, "total_steps": 761865, "loss": 1.9356, "lr": 2.791170812553419e-07, "epoch": 9.684786674804592, "percentage": 64.57, "elapsed_time": "16:21:07", "remaining_time": "8:58:27", "throughput": 8508.47, "total_tokens": 500871480} {"current_steps": 492000, "total_steps": 761865, "loss": 2.0088, "lr": 2.789321292612139e-07, "epoch": 9.686755527554094, "percentage": 64.58, "elapsed_time": "16:21:19", "remaining_time": "8:58:15", "throughput": 8508.5, "total_tokens": 500972744} {"current_steps": 492100, "total_steps": 761865, "loss": 1.9819, "lr": 2.7874721485781285e-07, "epoch": 9.688724380303597, "percentage": 64.59, "elapsed_time": "16:21:30", "remaining_time": "8:58:03", "throughput": 8508.54, "total_tokens": 501074712} {"current_steps": 492200, "total_steps": 761865, "loss": 1.9853, "lr": 2.785623380765818e-07, "epoch": 9.6906932330531, "percentage": 64.6, "elapsed_time": "16:21:42", "remaining_time": "8:57:51", "throughput": 8508.58, "total_tokens": 501176480} {"current_steps": 492300, "total_steps": 761865, "loss": 1.9698, "lr": 2.783774989489574e-07, "epoch": 9.692662085802603, "percentage": 64.62, "elapsed_time": "16:21:54", "remaining_time": "8:57:39", "throughput": 8508.63, "total_tokens": 501278880} {"current_steps": 492400, "total_steps": 761865, "loss": 2.0016, "lr": 2.7819269750637003e-07, "epoch": 9.694630938552105, "percentage": 64.63, "elapsed_time": "16:22:05", "remaining_time": "8:57:27", "throughput": 8508.67, "total_tokens": 501380888} {"current_steps": 492500, "total_steps": 761865, "loss": 1.9658, "lr": 2.780079337802436e-07, "epoch": 9.696599791301608, "percentage": 64.64, "elapsed_time": "16:22:17", "remaining_time": "8:57:14", "throughput": 8508.71, "total_tokens": 501483288} {"current_steps": 492600, "total_steps": 761865, "loss": 1.9907, "lr": 2.7782320780199575e-07, "epoch": 9.698568644051111, "percentage": 64.66, "elapsed_time": "16:22:29", "remaining_time": "8:57:02", "throughput": 8508.76, "total_tokens": 501585688} {"current_steps": 492700, "total_steps": 761865, "loss": 2.0221, "lr": 2.7763851960303766e-07, "epoch": 9.700537496800614, "percentage": 64.67, "elapsed_time": "16:22:41", "remaining_time": "8:56:50", "throughput": 8508.79, "total_tokens": 501687240} {"current_steps": 492800, "total_steps": 761865, "loss": 1.9818, "lr": 2.774538692147733e-07, "epoch": 9.702506349550116, "percentage": 64.68, "elapsed_time": "16:22:52", "remaining_time": "8:56:38", "throughput": 8508.83, "total_tokens": 501788744} {"current_steps": 492900, "total_steps": 761865, "loss": 1.9906, "lr": 2.7726925666860196e-07, "epoch": 9.70447520229962, "percentage": 64.7, "elapsed_time": "16:23:04", "remaining_time": "8:56:26", "throughput": 8508.87, "total_tokens": 501891144} {"current_steps": 493000, "total_steps": 761865, "loss": 1.996, "lr": 2.7708468199591474e-07, "epoch": 9.706444055049122, "percentage": 64.71, "elapsed_time": "16:23:16", "remaining_time": "8:56:14", "throughput": 8508.9, "total_tokens": 501991904} {"current_steps": 493100, "total_steps": 761865, "loss": 1.9955, "lr": 2.7690014522809734e-07, "epoch": 9.708412907798627, "percentage": 64.72, "elapsed_time": "16:23:27", "remaining_time": "8:56:02", "throughput": 8508.95, "total_tokens": 502094304} {"current_steps": 493200, "total_steps": 761865, "loss": 1.9854, "lr": 2.7671564639652814e-07, "epoch": 9.71038176054813, "percentage": 64.74, "elapsed_time": "16:23:39", "remaining_time": "8:55:50", "throughput": 8508.99, "total_tokens": 502196704} {"current_steps": 493300, "total_steps": 761865, "loss": 2.0202, "lr": 2.7653118553258034e-07, "epoch": 9.712350613297632, "percentage": 64.75, "elapsed_time": "16:23:51", "remaining_time": "8:55:38", "throughput": 8509.03, "total_tokens": 502299104} {"current_steps": 493400, "total_steps": 761865, "loss": 2.0088, "lr": 2.763467626676196e-07, "epoch": 9.714319466047135, "percentage": 64.76, "elapsed_time": "16:24:02", "remaining_time": "8:55:26", "throughput": 8509.07, "total_tokens": 502400896} {"current_steps": 493500, "total_steps": 761865, "loss": 1.9739, "lr": 2.7616237783300534e-07, "epoch": 9.716288318796638, "percentage": 64.78, "elapsed_time": "16:24:14", "remaining_time": "8:55:13", "throughput": 8509.11, "total_tokens": 502502600} {"current_steps": 493600, "total_steps": 761865, "loss": 1.934, "lr": 2.759780310600908e-07, "epoch": 9.71825717154614, "percentage": 64.79, "elapsed_time": "16:24:26", "remaining_time": "8:55:01", "throughput": 8509.15, "total_tokens": 502604488} {"current_steps": 493700, "total_steps": 761865, "loss": 1.9673, "lr": 2.757937223802226e-07, "epoch": 9.720226024295643, "percentage": 64.8, "elapsed_time": "16:24:38", "remaining_time": "8:54:49", "throughput": 8509.19, "total_tokens": 502705680} {"current_steps": 493800, "total_steps": 761865, "loss": 2.0069, "lr": 2.7560945182474114e-07, "epoch": 9.722194877045146, "percentage": 64.81, "elapsed_time": "16:24:49", "remaining_time": "8:54:37", "throughput": 8509.23, "total_tokens": 502808032} {"current_steps": 493900, "total_steps": 761865, "loss": 1.955, "lr": 2.7542521942497956e-07, "epoch": 9.724163729794649, "percentage": 64.83, "elapsed_time": "16:25:01", "remaining_time": "8:54:25", "throughput": 8509.26, "total_tokens": 502908816} {"current_steps": 494000, "total_steps": 761865, "loss": 1.9777, "lr": 2.752410252122652e-07, "epoch": 9.726132582544151, "percentage": 64.84, "elapsed_time": "16:25:13", "remaining_time": "8:54:13", "throughput": 8509.3, "total_tokens": 503011216} {"current_steps": 494100, "total_steps": 761865, "loss": 1.9646, "lr": 2.750568692179189e-07, "epoch": 9.728101435293654, "percentage": 64.85, "elapsed_time": "16:25:24", "remaining_time": "8:54:01", "throughput": 8509.34, "total_tokens": 503113120} {"current_steps": 494200, "total_steps": 761865, "loss": 2.0183, "lr": 2.748727514732549e-07, "epoch": 9.730070288043157, "percentage": 64.87, "elapsed_time": "16:25:36", "remaining_time": "8:53:49", "throughput": 8509.37, "total_tokens": 503213472} {"current_steps": 494300, "total_steps": 761865, "loss": 1.9554, "lr": 2.7468867200958045e-07, "epoch": 9.73203914079266, "percentage": 64.88, "elapsed_time": "16:25:48", "remaining_time": "8:53:36", "throughput": 8509.42, "total_tokens": 503315872} {"current_steps": 494400, "total_steps": 761865, "loss": 1.9637, "lr": 2.7450463085819704e-07, "epoch": 9.734007993542162, "percentage": 64.89, "elapsed_time": "16:25:59", "remaining_time": "8:53:24", "throughput": 8509.45, "total_tokens": 503416696} {"current_steps": 494500, "total_steps": 761865, "loss": 1.9732, "lr": 2.743206280503992e-07, "epoch": 9.735976846291665, "percentage": 64.91, "elapsed_time": "16:26:11", "remaining_time": "8:53:12", "throughput": 8509.49, "total_tokens": 503519096} {"current_steps": 494600, "total_steps": 761865, "loss": 1.9506, "lr": 2.7413666361747506e-07, "epoch": 9.737945699041168, "percentage": 64.92, "elapsed_time": "16:26:23", "remaining_time": "8:53:00", "throughput": 8509.53, "total_tokens": 503621496} {"current_steps": 494700, "total_steps": 761865, "loss": 1.9915, "lr": 2.7395273759070645e-07, "epoch": 9.739914551790672, "percentage": 64.93, "elapsed_time": "16:26:34", "remaining_time": "8:52:48", "throughput": 8509.57, "total_tokens": 503723896} {"current_steps": 494800, "total_steps": 761865, "loss": 2.0217, "lr": 2.7376885000136807e-07, "epoch": 9.741883404540175, "percentage": 64.95, "elapsed_time": "16:26:46", "remaining_time": "8:52:36", "throughput": 8509.61, "total_tokens": 503825136} {"current_steps": 494900, "total_steps": 761865, "loss": 1.9994, "lr": 2.735850008807287e-07, "epoch": 9.743852257289678, "percentage": 64.96, "elapsed_time": "16:26:58", "remaining_time": "8:52:24", "throughput": 8509.65, "total_tokens": 503927536} {"current_steps": 495000, "total_steps": 761865, "loss": 2.062, "lr": 2.7340119026005015e-07, "epoch": 9.74582111003918, "percentage": 64.97, "elapsed_time": "16:27:10", "remaining_time": "8:52:12", "throughput": 8509.68, "total_tokens": 504028856} {"current_steps": 495100, "total_steps": 761865, "loss": 1.9727, "lr": 2.732174181705882e-07, "epoch": 9.747789962788683, "percentage": 64.99, "elapsed_time": "16:27:22", "remaining_time": "8:52:00", "throughput": 8509.63, "total_tokens": 504131168} {"current_steps": 495200, "total_steps": 761865, "loss": 1.9456, "lr": 2.7303368464359133e-07, "epoch": 9.749758815538186, "percentage": 65.0, "elapsed_time": "16:27:34", "remaining_time": "8:51:48", "throughput": 8509.68, "total_tokens": 504233568} {"current_steps": 495300, "total_steps": 761865, "loss": 1.9769, "lr": 2.7284998971030205e-07, "epoch": 9.751727668287689, "percentage": 65.01, "elapsed_time": "16:27:45", "remaining_time": "8:51:36", "throughput": 8509.72, "total_tokens": 504335152} {"current_steps": 495400, "total_steps": 761865, "loss": 1.9694, "lr": 2.7266633340195615e-07, "epoch": 9.753696521037192, "percentage": 65.02, "elapsed_time": "16:27:57", "remaining_time": "8:51:24", "throughput": 8509.76, "total_tokens": 504436984} {"current_steps": 495500, "total_steps": 761865, "loss": 1.9582, "lr": 2.724827157497829e-07, "epoch": 9.755665373786695, "percentage": 65.04, "elapsed_time": "16:28:09", "remaining_time": "8:51:11", "throughput": 8509.79, "total_tokens": 504538504} {"current_steps": 495600, "total_steps": 761865, "loss": 2.0069, "lr": 2.7229913678500495e-07, "epoch": 9.757634226536197, "percentage": 65.05, "elapsed_time": "16:28:20", "remaining_time": "8:50:59", "throughput": 8509.83, "total_tokens": 504640904} {"current_steps": 495700, "total_steps": 761865, "loss": 1.9436, "lr": 2.72115596538838e-07, "epoch": 9.7596030792857, "percentage": 65.06, "elapsed_time": "16:28:32", "remaining_time": "8:50:47", "throughput": 8509.87, "total_tokens": 504743304} {"current_steps": 495800, "total_steps": 761865, "loss": 1.9954, "lr": 2.7193209504249205e-07, "epoch": 9.761571932035203, "percentage": 65.08, "elapsed_time": "16:28:44", "remaining_time": "8:50:35", "throughput": 8509.91, "total_tokens": 504845016} {"current_steps": 495900, "total_steps": 761865, "loss": 1.96, "lr": 2.717486323271696e-07, "epoch": 9.763540784784706, "percentage": 65.09, "elapsed_time": "16:28:56", "remaining_time": "8:50:23", "throughput": 8509.95, "total_tokens": 504946704} {"current_steps": 496000, "total_steps": 761865, "loss": 2.009, "lr": 2.715652084240673e-07, "epoch": 9.765509637534208, "percentage": 65.1, "elapsed_time": "16:29:07", "remaining_time": "8:50:11", "throughput": 8509.98, "total_tokens": 505047872} {"current_steps": 496100, "total_steps": 761865, "loss": 1.961, "lr": 2.7138182336437407e-07, "epoch": 9.767478490283711, "percentage": 65.12, "elapsed_time": "16:29:19", "remaining_time": "8:49:59", "throughput": 8510.01, "total_tokens": 505147912} {"current_steps": 496200, "total_steps": 761865, "loss": 1.9419, "lr": 2.711984771792741e-07, "epoch": 9.769447343033214, "percentage": 65.13, "elapsed_time": "16:29:31", "remaining_time": "8:49:47", "throughput": 8510.05, "total_tokens": 505250312} {"current_steps": 496300, "total_steps": 761865, "loss": 1.9676, "lr": 2.71015169899943e-07, "epoch": 9.771416195782717, "percentage": 65.14, "elapsed_time": "16:29:42", "remaining_time": "8:49:35", "throughput": 8510.09, "total_tokens": 505351496} {"current_steps": 496400, "total_steps": 761865, "loss": 2.0155, "lr": 2.7083190155755087e-07, "epoch": 9.77338504853222, "percentage": 65.16, "elapsed_time": "16:29:54", "remaining_time": "8:49:22", "throughput": 8510.13, "total_tokens": 505453896} {"current_steps": 496500, "total_steps": 761865, "loss": 1.9633, "lr": 2.7064867218326104e-07, "epoch": 9.775353901281724, "percentage": 65.17, "elapsed_time": "16:30:06", "remaining_time": "8:49:10", "throughput": 8510.18, "total_tokens": 505556296} {"current_steps": 496600, "total_steps": 761865, "loss": 1.9416, "lr": 2.7046548180823003e-07, "epoch": 9.777322754031227, "percentage": 65.18, "elapsed_time": "16:30:17", "remaining_time": "8:48:58", "throughput": 8510.22, "total_tokens": 505658696} {"current_steps": 496700, "total_steps": 761865, "loss": 2.0206, "lr": 2.702823304636081e-07, "epoch": 9.77929160678073, "percentage": 65.2, "elapsed_time": "16:30:29", "remaining_time": "8:48:46", "throughput": 8510.25, "total_tokens": 505760160} {"current_steps": 496800, "total_steps": 761865, "loss": 2.0011, "lr": 2.700992181805382e-07, "epoch": 9.781260459530232, "percentage": 65.21, "elapsed_time": "16:30:41", "remaining_time": "8:48:34", "throughput": 8510.29, "total_tokens": 505862048} {"current_steps": 496900, "total_steps": 761865, "loss": 1.9832, "lr": 2.69916144990157e-07, "epoch": 9.783229312279735, "percentage": 65.22, "elapsed_time": "16:30:52", "remaining_time": "8:48:22", "throughput": 8510.33, "total_tokens": 505964448} {"current_steps": 497000, "total_steps": 761865, "loss": 1.9563, "lr": 2.6973311092359485e-07, "epoch": 9.785198165029238, "percentage": 65.23, "elapsed_time": "16:31:04", "remaining_time": "8:48:10", "throughput": 8510.36, "total_tokens": 506066032} {"current_steps": 497100, "total_steps": 761865, "loss": 1.9488, "lr": 2.695501160119752e-07, "epoch": 9.78716701777874, "percentage": 65.25, "elapsed_time": "16:31:16", "remaining_time": "8:47:58", "throughput": 8510.4, "total_tokens": 506167392} {"current_steps": 497200, "total_steps": 761865, "loss": 2.0115, "lr": 2.6936716028641445e-07, "epoch": 9.789135870528243, "percentage": 65.26, "elapsed_time": "16:31:28", "remaining_time": "8:47:46", "throughput": 8510.44, "total_tokens": 506269792} {"current_steps": 497300, "total_steps": 761865, "loss": 1.9597, "lr": 2.691842437780228e-07, "epoch": 9.791104723277746, "percentage": 65.27, "elapsed_time": "16:31:39", "remaining_time": "8:47:34", "throughput": 8510.48, "total_tokens": 506371384} {"current_steps": 497400, "total_steps": 761865, "loss": 2.0004, "lr": 2.690013665179037e-07, "epoch": 9.793073576027249, "percentage": 65.29, "elapsed_time": "16:31:51", "remaining_time": "8:47:21", "throughput": 8510.52, "total_tokens": 506473040} {"current_steps": 497500, "total_steps": 761865, "loss": 1.9905, "lr": 2.6881852853715394e-07, "epoch": 9.795042428776751, "percentage": 65.3, "elapsed_time": "16:32:03", "remaining_time": "8:47:09", "throughput": 8510.54, "total_tokens": 506573416} {"current_steps": 497600, "total_steps": 761865, "loss": 2.0227, "lr": 2.6863572986686365e-07, "epoch": 9.797011281526254, "percentage": 65.31, "elapsed_time": "16:32:14", "remaining_time": "8:46:57", "throughput": 8510.58, "total_tokens": 506675376} {"current_steps": 497700, "total_steps": 761865, "loss": 1.9679, "lr": 2.68452970538116e-07, "epoch": 9.798980134275757, "percentage": 65.33, "elapsed_time": "16:32:26", "remaining_time": "8:46:45", "throughput": 8510.62, "total_tokens": 506776608} {"current_steps": 497800, "total_steps": 761865, "loss": 1.9893, "lr": 2.6827025058198767e-07, "epoch": 9.80094898702526, "percentage": 65.34, "elapsed_time": "16:32:38", "remaining_time": "8:46:33", "throughput": 8510.66, "total_tokens": 506877784} {"current_steps": 497900, "total_steps": 761865, "loss": 1.9751, "lr": 2.6808757002954873e-07, "epoch": 9.802917839774762, "percentage": 65.35, "elapsed_time": "16:32:49", "remaining_time": "8:46:21", "throughput": 8510.7, "total_tokens": 506980184} {"current_steps": 498000, "total_steps": 761865, "loss": 1.9837, "lr": 2.6790492891186267e-07, "epoch": 9.804886692524267, "percentage": 65.37, "elapsed_time": "16:33:01", "remaining_time": "8:46:09", "throughput": 8510.74, "total_tokens": 507081840} {"current_steps": 498100, "total_steps": 761865, "loss": 1.9597, "lr": 2.677223272599857e-07, "epoch": 9.80685554527377, "percentage": 65.38, "elapsed_time": "16:33:13", "remaining_time": "8:45:57", "throughput": 8510.77, "total_tokens": 507183472} {"current_steps": 498200, "total_steps": 761865, "loss": 1.9883, "lr": 2.675397651049678e-07, "epoch": 9.808824398023273, "percentage": 65.39, "elapsed_time": "16:33:24", "remaining_time": "8:45:44", "throughput": 8510.81, "total_tokens": 507285232} {"current_steps": 498300, "total_steps": 761865, "loss": 1.9834, "lr": 2.6735724247785224e-07, "epoch": 9.810793250772775, "percentage": 65.41, "elapsed_time": "16:33:36", "remaining_time": "8:45:32", "throughput": 8510.85, "total_tokens": 507387632} {"current_steps": 498400, "total_steps": 761865, "loss": 1.9949, "lr": 2.671747594096756e-07, "epoch": 9.812762103522278, "percentage": 65.42, "elapsed_time": "16:33:48", "remaining_time": "8:45:20", "throughput": 8510.89, "total_tokens": 507488704} {"current_steps": 498500, "total_steps": 761865, "loss": 1.9388, "lr": 2.6699231593146717e-07, "epoch": 9.81473095627178, "percentage": 65.43, "elapsed_time": "16:33:59", "remaining_time": "8:45:08", "throughput": 8510.93, "total_tokens": 507590536} {"current_steps": 498600, "total_steps": 761865, "loss": 1.9734, "lr": 2.668099120742499e-07, "epoch": 9.816699809021284, "percentage": 65.44, "elapsed_time": "16:34:11", "remaining_time": "8:44:56", "throughput": 8510.97, "total_tokens": 507692360} {"current_steps": 498700, "total_steps": 761865, "loss": 2.0219, "lr": 2.666275478690407e-07, "epoch": 9.818668661770786, "percentage": 65.46, "elapsed_time": "16:34:23", "remaining_time": "8:44:44", "throughput": 8511.01, "total_tokens": 507794112} {"current_steps": 498800, "total_steps": 761865, "loss": 2.0062, "lr": 2.6644522334684844e-07, "epoch": 9.820637514520289, "percentage": 65.47, "elapsed_time": "16:34:34", "remaining_time": "8:44:32", "throughput": 8511.04, "total_tokens": 507895664} {"current_steps": 498900, "total_steps": 761865, "loss": 1.963, "lr": 2.662629385386762e-07, "epoch": 9.822606367269792, "percentage": 65.48, "elapsed_time": "16:34:46", "remaining_time": "8:44:20", "throughput": 8511.07, "total_tokens": 507996664} {"current_steps": 499000, "total_steps": 761865, "loss": 1.9652, "lr": 2.660806934755195e-07, "epoch": 9.824575220019295, "percentage": 65.5, "elapsed_time": "16:34:58", "remaining_time": "8:44:08", "throughput": 8511.12, "total_tokens": 508099064} {"current_steps": 499100, "total_steps": 761865, "loss": 2.0077, "lr": 2.658984881883683e-07, "epoch": 9.826544072768797, "percentage": 65.51, "elapsed_time": "16:35:09", "remaining_time": "8:43:55", "throughput": 8511.15, "total_tokens": 508200608} {"current_steps": 499200, "total_steps": 761865, "loss": 1.9899, "lr": 2.6571632270820443e-07, "epoch": 9.8285129255183, "percentage": 65.52, "elapsed_time": "16:35:21", "remaining_time": "8:43:43", "throughput": 8511.18, "total_tokens": 508301488} {"current_steps": 499300, "total_steps": 761865, "loss": 1.9432, "lr": 2.655341970660041e-07, "epoch": 9.830481778267803, "percentage": 65.54, "elapsed_time": "16:35:33", "remaining_time": "8:43:31", "throughput": 8511.22, "total_tokens": 508403888} {"current_steps": 499400, "total_steps": 761865, "loss": 1.9801, "lr": 2.653521112927356e-07, "epoch": 9.832450631017306, "percentage": 65.55, "elapsed_time": "16:35:45", "remaining_time": "8:43:19", "throughput": 8511.26, "total_tokens": 508506288} {"current_steps": 499500, "total_steps": 761865, "loss": 1.9688, "lr": 2.651700654193616e-07, "epoch": 9.834419483766808, "percentage": 65.56, "elapsed_time": "16:35:56", "remaining_time": "8:43:07", "throughput": 8511.3, "total_tokens": 508608688} {"current_steps": 499600, "total_steps": 761865, "loss": 2.0125, "lr": 2.6498805947683756e-07, "epoch": 9.836388336516311, "percentage": 65.58, "elapsed_time": "16:36:08", "remaining_time": "8:42:55", "throughput": 8511.34, "total_tokens": 508711088} {"current_steps": 499700, "total_steps": 761865, "loss": 1.9359, "lr": 2.648060934961116e-07, "epoch": 9.838357189265814, "percentage": 65.59, "elapsed_time": "16:36:20", "remaining_time": "8:42:43", "throughput": 8511.38, "total_tokens": 508813288} {"current_steps": 499800, "total_steps": 761865, "loss": 2.0064, "lr": 2.6462416750812577e-07, "epoch": 9.840326042015318, "percentage": 65.6, "elapsed_time": "16:36:32", "remaining_time": "8:42:31", "throughput": 8511.42, "total_tokens": 508915152} {"current_steps": 499900, "total_steps": 761865, "loss": 1.9775, "lr": 2.6444228154381497e-07, "epoch": 9.842294894764821, "percentage": 65.62, "elapsed_time": "16:36:43", "remaining_time": "8:42:19", "throughput": 8511.46, "total_tokens": 509017552} {"current_steps": 500000, "total_steps": 761865, "loss": 1.9749, "lr": 2.642604356341076e-07, "epoch": 9.844263747514324, "percentage": 65.63, "elapsed_time": "16:36:55", "remaining_time": "8:42:07", "throughput": 8511.5, "total_tokens": 509118664} {"current_steps": 500100, "total_steps": 761865, "loss": 2.0087, "lr": 2.6407862980992467e-07, "epoch": 9.846232600263827, "percentage": 65.64, "elapsed_time": "16:37:07", "remaining_time": "8:41:55", "throughput": 8511.44, "total_tokens": 509219320} {"current_steps": 500200, "total_steps": 761865, "loss": 2.0134, "lr": 2.638968641021808e-07, "epoch": 9.84820145301333, "percentage": 65.65, "elapsed_time": "16:37:19", "remaining_time": "8:41:43", "throughput": 8511.48, "total_tokens": 509321720} {"current_steps": 500300, "total_steps": 761865, "loss": 1.9761, "lr": 2.637151385417839e-07, "epoch": 9.850170305762832, "percentage": 65.67, "elapsed_time": "16:37:31", "remaining_time": "8:41:31", "throughput": 8511.53, "total_tokens": 509424120} {"current_steps": 500400, "total_steps": 761865, "loss": 1.9859, "lr": 2.635334531596349e-07, "epoch": 9.852139158512335, "percentage": 65.68, "elapsed_time": "16:37:42", "remaining_time": "8:41:19", "throughput": 8511.56, "total_tokens": 509525688} {"current_steps": 500500, "total_steps": 761865, "loss": 1.9598, "lr": 2.633518079866276e-07, "epoch": 9.854108011261838, "percentage": 65.69, "elapsed_time": "16:37:54", "remaining_time": "8:41:06", "throughput": 8511.6, "total_tokens": 509628088} {"current_steps": 500600, "total_steps": 761865, "loss": 2.0112, "lr": 2.6317020305364936e-07, "epoch": 9.85607686401134, "percentage": 65.71, "elapsed_time": "16:38:06", "remaining_time": "8:40:54", "throughput": 8511.63, "total_tokens": 509728448} {"current_steps": 500700, "total_steps": 761865, "loss": 1.9739, "lr": 2.6298863839158056e-07, "epoch": 9.858045716760843, "percentage": 65.72, "elapsed_time": "16:38:17", "remaining_time": "8:40:42", "throughput": 8511.67, "total_tokens": 509830848} {"current_steps": 500800, "total_steps": 761865, "loss": 1.9801, "lr": 2.6280711403129477e-07, "epoch": 9.860014569510346, "percentage": 65.73, "elapsed_time": "16:38:29", "remaining_time": "8:40:30", "throughput": 8511.71, "total_tokens": 509933248} {"current_steps": 500900, "total_steps": 761865, "loss": 2.0005, "lr": 2.6262563000365886e-07, "epoch": 9.861983422259849, "percentage": 65.75, "elapsed_time": "16:38:41", "remaining_time": "8:40:18", "throughput": 8511.75, "total_tokens": 510034840} {"current_steps": 501000, "total_steps": 761865, "loss": 1.9879, "lr": 2.6244418633953226e-07, "epoch": 9.863952275009352, "percentage": 65.76, "elapsed_time": "16:38:52", "remaining_time": "8:40:06", "throughput": 8511.79, "total_tokens": 510136696} {"current_steps": 501100, "total_steps": 761865, "loss": 1.9808, "lr": 2.6226278306976815e-07, "epoch": 9.865921127758854, "percentage": 65.77, "elapsed_time": "16:39:04", "remaining_time": "8:39:54", "throughput": 8511.82, "total_tokens": 510238304} {"current_steps": 501200, "total_steps": 761865, "loss": 2.0128, "lr": 2.620814202252125e-07, "epoch": 9.867889980508357, "percentage": 65.79, "elapsed_time": "16:39:16", "remaining_time": "8:39:42", "throughput": 8511.86, "total_tokens": 510340704} {"current_steps": 501300, "total_steps": 761865, "loss": 2.0451, "lr": 2.61900097836705e-07, "epoch": 9.86985883325786, "percentage": 65.8, "elapsed_time": "16:39:28", "remaining_time": "8:39:30", "throughput": 8511.9, "total_tokens": 510441816} {"current_steps": 501400, "total_steps": 761865, "loss": 2.0257, "lr": 2.617188159350772e-07, "epoch": 9.871827686007364, "percentage": 65.81, "elapsed_time": "16:39:39", "remaining_time": "8:39:17", "throughput": 8511.93, "total_tokens": 510543376} {"current_steps": 501500, "total_steps": 761865, "loss": 1.9786, "lr": 2.615375745511551e-07, "epoch": 9.873796538756867, "percentage": 65.83, "elapsed_time": "16:39:51", "remaining_time": "8:39:05", "throughput": 8511.97, "total_tokens": 510645064} {"current_steps": 501600, "total_steps": 761865, "loss": 2.0041, "lr": 2.6135637371575743e-07, "epoch": 9.87576539150637, "percentage": 65.84, "elapsed_time": "16:40:03", "remaining_time": "8:38:53", "throughput": 8512.0, "total_tokens": 510746392} {"current_steps": 501700, "total_steps": 761865, "loss": 1.9877, "lr": 2.611752134596954e-07, "epoch": 9.877734244255873, "percentage": 65.85, "elapsed_time": "16:40:14", "remaining_time": "8:38:41", "throughput": 8512.04, "total_tokens": 510848192} {"current_steps": 501800, "total_steps": 761865, "loss": 1.9885, "lr": 2.609940938137739e-07, "epoch": 9.879703097005375, "percentage": 65.86, "elapsed_time": "16:40:26", "remaining_time": "8:38:29", "throughput": 8512.08, "total_tokens": 510950592} {"current_steps": 501900, "total_steps": 761865, "loss": 1.9937, "lr": 2.60813014808791e-07, "epoch": 9.881671949754878, "percentage": 65.88, "elapsed_time": "16:40:38", "remaining_time": "8:38:17", "throughput": 8512.12, "total_tokens": 511052992} {"current_steps": 502000, "total_steps": 761865, "loss": 2.0191, "lr": 2.6063197647553763e-07, "epoch": 9.883640802504381, "percentage": 65.89, "elapsed_time": "16:40:49", "remaining_time": "8:38:05", "throughput": 8512.15, "total_tokens": 511152664} {"current_steps": 502100, "total_steps": 761865, "loss": 1.9992, "lr": 2.604509788447976e-07, "epoch": 9.885609655253884, "percentage": 65.9, "elapsed_time": "16:41:01", "remaining_time": "8:37:53", "throughput": 8512.18, "total_tokens": 511253880} {"current_steps": 502200, "total_steps": 761865, "loss": 2.0121, "lr": 2.6027002194734813e-07, "epoch": 9.887578508003386, "percentage": 65.92, "elapsed_time": "16:41:13", "remaining_time": "8:37:41", "throughput": 8512.21, "total_tokens": 511354808} {"current_steps": 502300, "total_steps": 761865, "loss": 1.9703, "lr": 2.6008910581395946e-07, "epoch": 9.88954736075289, "percentage": 65.93, "elapsed_time": "16:41:24", "remaining_time": "8:37:28", "throughput": 8512.25, "total_tokens": 511456360} {"current_steps": 502400, "total_steps": 761865, "loss": 1.9316, "lr": 2.599082304753951e-07, "epoch": 9.891516213502392, "percentage": 65.94, "elapsed_time": "16:41:36", "remaining_time": "8:37:16", "throughput": 8512.28, "total_tokens": 511557536} {"current_steps": 502500, "total_steps": 761865, "loss": 2.0277, "lr": 2.597273959624109e-07, "epoch": 9.893485066251895, "percentage": 65.96, "elapsed_time": "16:41:48", "remaining_time": "8:37:04", "throughput": 8512.32, "total_tokens": 511658456} {"current_steps": 502600, "total_steps": 761865, "loss": 2.0189, "lr": 2.595466023057564e-07, "epoch": 9.895453919001397, "percentage": 65.97, "elapsed_time": "16:41:59", "remaining_time": "8:36:52", "throughput": 8512.36, "total_tokens": 511760856} {"current_steps": 502700, "total_steps": 761865, "loss": 1.9804, "lr": 2.593658495361742e-07, "epoch": 9.8974227717509, "percentage": 65.98, "elapsed_time": "16:42:11", "remaining_time": "8:36:40", "throughput": 8512.38, "total_tokens": 511861480} {"current_steps": 502800, "total_steps": 761865, "loss": 1.973, "lr": 2.591851376843996e-07, "epoch": 9.899391624500403, "percentage": 66.0, "elapsed_time": "16:42:23", "remaining_time": "8:36:28", "throughput": 8512.43, "total_tokens": 511963880} {"current_steps": 502900, "total_steps": 761865, "loss": 2.0083, "lr": 2.5900446678116145e-07, "epoch": 9.901360477249906, "percentage": 66.01, "elapsed_time": "16:42:34", "remaining_time": "8:36:16", "throughput": 8512.46, "total_tokens": 512065416} {"current_steps": 503000, "total_steps": 761865, "loss": 2.0159, "lr": 2.588238368571809e-07, "epoch": 9.903329329999409, "percentage": 66.02, "elapsed_time": "16:42:46", "remaining_time": "8:36:04", "throughput": 8512.49, "total_tokens": 512166376} {"current_steps": 503100, "total_steps": 761865, "loss": 1.9427, "lr": 2.5864324794317263e-07, "epoch": 9.905298182748911, "percentage": 66.04, "elapsed_time": "16:42:58", "remaining_time": "8:35:52", "throughput": 8512.53, "total_tokens": 512268224} {"current_steps": 503200, "total_steps": 761865, "loss": 2.0108, "lr": 2.584627000698444e-07, "epoch": 9.907267035498416, "percentage": 66.05, "elapsed_time": "16:43:09", "remaining_time": "8:35:40", "throughput": 8512.57, "total_tokens": 512370176} {"current_steps": 503300, "total_steps": 761865, "loss": 2.0182, "lr": 2.58282193267897e-07, "epoch": 9.909235888247919, "percentage": 66.06, "elapsed_time": "16:43:21", "remaining_time": "8:35:27", "throughput": 8512.59, "total_tokens": 512470304} {"current_steps": 503400, "total_steps": 761865, "loss": 2.0415, "lr": 2.581017275680237e-07, "epoch": 9.911204740997421, "percentage": 66.07, "elapsed_time": "16:43:33", "remaining_time": "8:35:15", "throughput": 8512.64, "total_tokens": 512572704} {"current_steps": 503500, "total_steps": 761865, "loss": 2.0169, "lr": 2.579213030009114e-07, "epoch": 9.913173593746924, "percentage": 66.09, "elapsed_time": "16:43:44", "remaining_time": "8:35:03", "throughput": 8512.68, "total_tokens": 512675104} {"current_steps": 503600, "total_steps": 761865, "loss": 1.995, "lr": 2.577409195972397e-07, "epoch": 9.915142446496427, "percentage": 66.1, "elapsed_time": "16:43:56", "remaining_time": "8:34:51", "throughput": 8512.71, "total_tokens": 512776680} {"current_steps": 503700, "total_steps": 761865, "loss": 2.0216, "lr": 2.5756057738768133e-07, "epoch": 9.91711129924593, "percentage": 66.11, "elapsed_time": "16:44:08", "remaining_time": "8:34:39", "throughput": 8512.75, "total_tokens": 512878600} {"current_steps": 503800, "total_steps": 761865, "loss": 2.0301, "lr": 2.573802764029021e-07, "epoch": 9.919080151995432, "percentage": 66.13, "elapsed_time": "16:44:19", "remaining_time": "8:34:27", "throughput": 8512.78, "total_tokens": 512979456} {"current_steps": 503900, "total_steps": 761865, "loss": 1.9495, "lr": 2.572000166735602e-07, "epoch": 9.921049004744935, "percentage": 66.14, "elapsed_time": "16:44:31", "remaining_time": "8:34:15", "throughput": 8512.82, "total_tokens": 513081248} {"current_steps": 504000, "total_steps": 761865, "loss": 1.9724, "lr": 2.5701979823030796e-07, "epoch": 9.923017857494438, "percentage": 66.15, "elapsed_time": "16:44:43", "remaining_time": "8:34:03", "throughput": 8512.86, "total_tokens": 513183648} {"current_steps": 504100, "total_steps": 761865, "loss": 1.9874, "lr": 2.5683962110378935e-07, "epoch": 9.92498671024394, "percentage": 66.17, "elapsed_time": "16:44:55", "remaining_time": "8:33:51", "throughput": 8512.9, "total_tokens": 513286048} {"current_steps": 504200, "total_steps": 761865, "loss": 1.9934, "lr": 2.5665948532464254e-07, "epoch": 9.926955562993443, "percentage": 66.18, "elapsed_time": "16:45:06", "remaining_time": "8:33:39", "throughput": 8512.94, "total_tokens": 513387744} {"current_steps": 504300, "total_steps": 761865, "loss": 1.9569, "lr": 2.5647939092349746e-07, "epoch": 9.928924415742946, "percentage": 66.19, "elapsed_time": "16:45:18", "remaining_time": "8:33:26", "throughput": 8512.98, "total_tokens": 513490144} {"current_steps": 504400, "total_steps": 761865, "loss": 1.9535, "lr": 2.562993379309784e-07, "epoch": 9.930893268492449, "percentage": 66.21, "elapsed_time": "16:45:30", "remaining_time": "8:33:14", "throughput": 8513.02, "total_tokens": 513592184} {"current_steps": 504500, "total_steps": 761865, "loss": 1.9927, "lr": 2.561193263777012e-07, "epoch": 9.932862121241952, "percentage": 66.22, "elapsed_time": "16:45:41", "remaining_time": "8:33:02", "throughput": 8513.05, "total_tokens": 513693624} {"current_steps": 504600, "total_steps": 761865, "loss": 2.032, "lr": 2.5593935629427555e-07, "epoch": 9.934830973991454, "percentage": 66.23, "elapsed_time": "16:45:53", "remaining_time": "8:32:50", "throughput": 8513.08, "total_tokens": 513794608} {"current_steps": 504700, "total_steps": 761865, "loss": 1.9867, "lr": 2.557594277113039e-07, "epoch": 9.936799826740959, "percentage": 66.25, "elapsed_time": "16:46:05", "remaining_time": "8:32:38", "throughput": 8513.12, "total_tokens": 513896696} {"current_steps": 504800, "total_steps": 761865, "loss": 1.9819, "lr": 2.555795406593816e-07, "epoch": 9.938768679490462, "percentage": 66.26, "elapsed_time": "16:46:16", "remaining_time": "8:32:26", "throughput": 8513.16, "total_tokens": 513998472} {"current_steps": 504900, "total_steps": 761865, "loss": 2.0163, "lr": 2.55399695169097e-07, "epoch": 9.940737532239964, "percentage": 66.27, "elapsed_time": "16:46:28", "remaining_time": "8:32:14", "throughput": 8513.2, "total_tokens": 514100400} {"current_steps": 505000, "total_steps": 761865, "loss": 1.9759, "lr": 2.55219891271031e-07, "epoch": 9.942706384989467, "percentage": 66.28, "elapsed_time": "16:46:40", "remaining_time": "8:32:02", "throughput": 8513.23, "total_tokens": 514202208} {"current_steps": 505100, "total_steps": 761865, "loss": 1.9478, "lr": 2.550401289957579e-07, "epoch": 9.94467523773897, "percentage": 66.3, "elapsed_time": "16:46:52", "remaining_time": "8:31:50", "throughput": 8513.19, "total_tokens": 514304608} {"current_steps": 505200, "total_steps": 761865, "loss": 1.9466, "lr": 2.548604083738448e-07, "epoch": 9.946644090488473, "percentage": 66.31, "elapsed_time": "16:47:04", "remaining_time": "8:31:38", "throughput": 8513.21, "total_tokens": 514404648} {"current_steps": 505300, "total_steps": 761865, "loss": 1.9911, "lr": 2.546807294358518e-07, "epoch": 9.948612943237976, "percentage": 66.32, "elapsed_time": "16:47:15", "remaining_time": "8:31:26", "throughput": 8513.25, "total_tokens": 514506368} {"current_steps": 505400, "total_steps": 761865, "loss": 1.9833, "lr": 2.5450109221233157e-07, "epoch": 9.950581795987478, "percentage": 66.34, "elapsed_time": "16:47:27", "remaining_time": "8:31:14", "throughput": 8513.29, "total_tokens": 514608768} {"current_steps": 505500, "total_steps": 761865, "loss": 2.0226, "lr": 2.543214967338299e-07, "epoch": 9.952550648736981, "percentage": 66.35, "elapsed_time": "16:47:39", "remaining_time": "8:31:02", "throughput": 8513.32, "total_tokens": 514710648} {"current_steps": 505600, "total_steps": 761865, "loss": 2.0253, "lr": 2.5414194303088555e-07, "epoch": 9.954519501486484, "percentage": 66.36, "elapsed_time": "16:47:51", "remaining_time": "8:30:49", "throughput": 8513.36, "total_tokens": 514811992} {"current_steps": 505700, "total_steps": 761865, "loss": 2.0207, "lr": 2.5396243113403016e-07, "epoch": 9.956488354235987, "percentage": 66.38, "elapsed_time": "16:48:02", "remaining_time": "8:30:37", "throughput": 8513.38, "total_tokens": 514912672} {"current_steps": 505800, "total_steps": 761865, "loss": 1.9898, "lr": 2.537829610737883e-07, "epoch": 9.95845720698549, "percentage": 66.39, "elapsed_time": "16:48:14", "remaining_time": "8:30:25", "throughput": 8513.41, "total_tokens": 515013056} {"current_steps": 505900, "total_steps": 761865, "loss": 1.9628, "lr": 2.5360353288067714e-07, "epoch": 9.960426059734992, "percentage": 66.4, "elapsed_time": "16:48:25", "remaining_time": "8:30:13", "throughput": 8513.44, "total_tokens": 515114144} {"current_steps": 506000, "total_steps": 761865, "loss": 2.02, "lr": 2.534241465852069e-07, "epoch": 9.962394912484495, "percentage": 66.42, "elapsed_time": "16:48:37", "remaining_time": "8:30:01", "throughput": 8513.48, "total_tokens": 515216456} {"current_steps": 506100, "total_steps": 761865, "loss": 2.0424, "lr": 2.532448022178809e-07, "epoch": 9.964363765233998, "percentage": 66.43, "elapsed_time": "16:48:49", "remaining_time": "8:29:49", "throughput": 8513.52, "total_tokens": 515318376} {"current_steps": 506200, "total_steps": 761865, "loss": 1.9999, "lr": 2.5306549980919525e-07, "epoch": 9.9663326179835, "percentage": 66.44, "elapsed_time": "16:49:01", "remaining_time": "8:29:37", "throughput": 8513.56, "total_tokens": 515420776} {"current_steps": 506300, "total_steps": 761865, "loss": 1.9778, "lr": 2.5288623938963833e-07, "epoch": 9.968301470733003, "percentage": 66.46, "elapsed_time": "16:49:12", "remaining_time": "8:29:25", "throughput": 8513.6, "total_tokens": 515523040} {"current_steps": 506400, "total_steps": 761865, "loss": 1.9611, "lr": 2.5270702098969223e-07, "epoch": 9.970270323482506, "percentage": 66.47, "elapsed_time": "16:49:24", "remaining_time": "8:29:13", "throughput": 8513.63, "total_tokens": 515624704} {"current_steps": 506500, "total_steps": 761865, "loss": 2.0287, "lr": 2.525278446398314e-07, "epoch": 9.97223917623201, "percentage": 66.48, "elapsed_time": "16:49:36", "remaining_time": "8:29:01", "throughput": 8513.67, "total_tokens": 515727104} {"current_steps": 506600, "total_steps": 761865, "loss": 1.9825, "lr": 2.523487103705233e-07, "epoch": 9.974208028981513, "percentage": 66.49, "elapsed_time": "16:49:47", "remaining_time": "8:28:48", "throughput": 8513.7, "total_tokens": 515827264} {"current_steps": 506700, "total_steps": 761865, "loss": 1.9909, "lr": 2.521696182122285e-07, "epoch": 9.976176881731016, "percentage": 66.51, "elapsed_time": "16:49:59", "remaining_time": "8:28:36", "throughput": 8513.74, "total_tokens": 515929664} {"current_steps": 506800, "total_steps": 761865, "loss": 1.9831, "lr": 2.5199056819539935e-07, "epoch": 9.978145734480519, "percentage": 66.52, "elapsed_time": "16:50:11", "remaining_time": "8:28:24", "throughput": 8513.78, "total_tokens": 516032064} {"current_steps": 506900, "total_steps": 761865, "loss": 1.9951, "lr": 2.5181156035048267e-07, "epoch": 9.980114587230021, "percentage": 66.53, "elapsed_time": "16:50:23", "remaining_time": "8:28:12", "throughput": 8513.81, "total_tokens": 516133664} {"current_steps": 507000, "total_steps": 761865, "loss": 2.0282, "lr": 2.5163259470791665e-07, "epoch": 9.982083439979524, "percentage": 66.55, "elapsed_time": "16:50:34", "remaining_time": "8:28:00", "throughput": 8513.84, "total_tokens": 516233848} {"current_steps": 507100, "total_steps": 761865, "loss": 1.9461, "lr": 2.514536712981332e-07, "epoch": 9.984052292729027, "percentage": 66.56, "elapsed_time": "16:50:46", "remaining_time": "8:27:48", "throughput": 8513.88, "total_tokens": 516336248} {"current_steps": 507200, "total_steps": 761865, "loss": 1.9632, "lr": 2.5127479015155633e-07, "epoch": 9.98602114547853, "percentage": 66.57, "elapsed_time": "16:50:58", "remaining_time": "8:27:36", "throughput": 8513.92, "total_tokens": 516438648} {"current_steps": 507300, "total_steps": 761865, "loss": 2.0052, "lr": 2.5109595129860394e-07, "epoch": 9.987989998228032, "percentage": 66.59, "elapsed_time": "16:51:09", "remaining_time": "8:27:24", "throughput": 8513.96, "total_tokens": 516540552} {"current_steps": 507400, "total_steps": 761865, "loss": 1.9831, "lr": 2.5091715476968547e-07, "epoch": 9.989958850977535, "percentage": 66.6, "elapsed_time": "16:51:21", "remaining_time": "8:27:12", "throughput": 8513.99, "total_tokens": 516641440} {"current_steps": 507500, "total_steps": 761865, "loss": 1.9368, "lr": 2.5073840059520407e-07, "epoch": 9.991927703727038, "percentage": 66.61, "elapsed_time": "16:51:33", "remaining_time": "8:27:00", "throughput": 8514.02, "total_tokens": 516743064} {"current_steps": 507600, "total_steps": 761865, "loss": 1.9597, "lr": 2.50559688805555e-07, "epoch": 9.99389655647654, "percentage": 66.63, "elapsed_time": "16:51:44", "remaining_time": "8:26:48", "throughput": 8514.06, "total_tokens": 516845464} {"current_steps": 507700, "total_steps": 761865, "loss": 1.9873, "lr": 2.503810194311271e-07, "epoch": 9.995865409226043, "percentage": 66.64, "elapsed_time": "16:51:56", "remaining_time": "8:26:35", "throughput": 8514.09, "total_tokens": 516946080} {"current_steps": 507800, "total_steps": 761865, "loss": 1.9768, "lr": 2.502023925023017e-07, "epoch": 9.997834261975546, "percentage": 66.65, "elapsed_time": "16:52:08", "remaining_time": "8:26:23", "throughput": 8514.13, "total_tokens": 517048480} {"current_steps": 507900, "total_steps": 761865, "loss": 1.9664, "lr": 2.5002380804945233e-07, "epoch": 9.999803114725049, "percentage": 66.67, "elapsed_time": "16:52:20", "remaining_time": "8:26:11", "throughput": 8514.17, "total_tokens": 517150880} {"current_steps": 508000, "total_steps": 761865, "loss": 2.0134, "lr": 2.4984526610294596e-07, "epoch": 10.001771967474552, "percentage": 66.68, "elapsed_time": "16:52:31", "remaining_time": "8:25:59", "throughput": 8514.2, "total_tokens": 517252488} {"current_steps": 508100, "total_steps": 761865, "loss": 1.9949, "lr": 2.496667666931423e-07, "epoch": 10.003740820224056, "percentage": 66.69, "elapsed_time": "16:52:43", "remaining_time": "8:25:47", "throughput": 8514.23, "total_tokens": 517352984} {"current_steps": 508200, "total_steps": 761865, "loss": 1.9413, "lr": 2.494883098503937e-07, "epoch": 10.005709672973559, "percentage": 66.7, "elapsed_time": "16:52:55", "remaining_time": "8:25:35", "throughput": 8514.26, "total_tokens": 517454640} {"current_steps": 508300, "total_steps": 761865, "loss": 1.9683, "lr": 2.493098956050449e-07, "epoch": 10.007678525723062, "percentage": 66.72, "elapsed_time": "16:53:06", "remaining_time": "8:25:23", "throughput": 8514.29, "total_tokens": 517555064} {"current_steps": 508400, "total_steps": 761865, "loss": 2.0346, "lr": 2.491315239874339e-07, "epoch": 10.009647378472565, "percentage": 66.73, "elapsed_time": "16:53:18", "remaining_time": "8:25:11", "throughput": 8514.33, "total_tokens": 517656984} {"current_steps": 508500, "total_steps": 761865, "loss": 2.0483, "lr": 2.4895319502789143e-07, "epoch": 10.011616231222067, "percentage": 66.74, "elapsed_time": "16:53:30", "remaining_time": "8:24:59", "throughput": 8514.37, "total_tokens": 517759384} {"current_steps": 508600, "total_steps": 761865, "loss": 1.9784, "lr": 2.487749087567406e-07, "epoch": 10.01358508397157, "percentage": 66.76, "elapsed_time": "16:53:41", "remaining_time": "8:24:47", "throughput": 8514.41, "total_tokens": 517861280} {"current_steps": 508700, "total_steps": 761865, "loss": 1.9719, "lr": 2.4859666520429785e-07, "epoch": 10.015553936721073, "percentage": 66.77, "elapsed_time": "16:53:53", "remaining_time": "8:24:35", "throughput": 8514.45, "total_tokens": 517963208} {"current_steps": 508800, "total_steps": 761865, "loss": 2.0126, "lr": 2.4841846440087156e-07, "epoch": 10.017522789470576, "percentage": 66.78, "elapsed_time": "16:54:05", "remaining_time": "8:24:22", "throughput": 8514.48, "total_tokens": 518064736} {"current_steps": 508900, "total_steps": 761865, "loss": 1.9861, "lr": 2.482403063767635e-07, "epoch": 10.019491642220078, "percentage": 66.8, "elapsed_time": "16:54:16", "remaining_time": "8:24:10", "throughput": 8514.52, "total_tokens": 518167136} {"current_steps": 509000, "total_steps": 761865, "loss": 1.9833, "lr": 2.4806219116226787e-07, "epoch": 10.021460494969581, "percentage": 66.81, "elapsed_time": "16:54:28", "remaining_time": "8:23:58", "throughput": 8514.56, "total_tokens": 518268768} {"current_steps": 509100, "total_steps": 761865, "loss": 1.9851, "lr": 2.4788411878767185e-07, "epoch": 10.023429347719084, "percentage": 66.82, "elapsed_time": "16:54:40", "remaining_time": "8:23:46", "throughput": 8514.59, "total_tokens": 518370488} {"current_steps": 509200, "total_steps": 761865, "loss": 2.0302, "lr": 2.477060892832548e-07, "epoch": 10.025398200468587, "percentage": 66.84, "elapsed_time": "16:54:51", "remaining_time": "8:23:34", "throughput": 8514.63, "total_tokens": 518472800} {"current_steps": 509300, "total_steps": 761865, "loss": 2.0248, "lr": 2.475281026792893e-07, "epoch": 10.02736705321809, "percentage": 66.85, "elapsed_time": "16:55:03", "remaining_time": "8:23:22", "throughput": 8514.67, "total_tokens": 518574760} {"current_steps": 509400, "total_steps": 761865, "loss": 1.9267, "lr": 2.4735015900604056e-07, "epoch": 10.029335905967592, "percentage": 66.86, "elapsed_time": "16:55:15", "remaining_time": "8:23:10", "throughput": 8514.7, "total_tokens": 518676296} {"current_steps": 509500, "total_steps": 761865, "loss": 1.9654, "lr": 2.471722582937665e-07, "epoch": 10.031304758717095, "percentage": 66.88, "elapsed_time": "16:55:27", "remaining_time": "8:22:58", "throughput": 8514.74, "total_tokens": 518778696} {"current_steps": 509600, "total_steps": 761865, "loss": 1.9638, "lr": 2.469944005727171e-07, "epoch": 10.033273611466598, "percentage": 66.89, "elapsed_time": "16:55:38", "remaining_time": "8:22:46", "throughput": 8514.78, "total_tokens": 518881096} {"current_steps": 509700, "total_steps": 761865, "loss": 2.0003, "lr": 2.468165858731361e-07, "epoch": 10.0352424642161, "percentage": 66.9, "elapsed_time": "16:55:50", "remaining_time": "8:22:34", "throughput": 8514.82, "total_tokens": 518982808} {"current_steps": 509800, "total_steps": 761865, "loss": 1.9397, "lr": 2.466388142252594e-07, "epoch": 10.037211316965605, "percentage": 66.91, "elapsed_time": "16:56:02", "remaining_time": "8:22:22", "throughput": 8514.86, "total_tokens": 519085208} {"current_steps": 509900, "total_steps": 761865, "loss": 1.9773, "lr": 2.464610856593152e-07, "epoch": 10.039180169715108, "percentage": 66.93, "elapsed_time": "16:56:14", "remaining_time": "8:22:10", "throughput": 8514.9, "total_tokens": 519187608} {"current_steps": 510000, "total_steps": 761865, "loss": 2.0049, "lr": 2.4628340020552503e-07, "epoch": 10.04114902246461, "percentage": 66.94, "elapsed_time": "16:56:25", "remaining_time": "8:21:57", "throughput": 8514.93, "total_tokens": 519288824} {"current_steps": 510100, "total_steps": 761865, "loss": 1.9865, "lr": 2.4610575789410266e-07, "epoch": 10.043117875214113, "percentage": 66.95, "elapsed_time": "16:56:38", "remaining_time": "8:21:46", "throughput": 8514.89, "total_tokens": 519391224} {"current_steps": 510200, "total_steps": 761865, "loss": 2.0033, "lr": 2.4592815875525483e-07, "epoch": 10.045086727963616, "percentage": 66.97, "elapsed_time": "16:56:49", "remaining_time": "8:21:34", "throughput": 8514.92, "total_tokens": 519493624} {"current_steps": 510300, "total_steps": 761865, "loss": 1.9956, "lr": 2.457506028191806e-07, "epoch": 10.047055580713119, "percentage": 66.98, "elapsed_time": "16:57:01", "remaining_time": "8:21:22", "throughput": 8514.95, "total_tokens": 519594240} {"current_steps": 510400, "total_steps": 761865, "loss": 1.9841, "lr": 2.455730901160718e-07, "epoch": 10.049024433462622, "percentage": 66.99, "elapsed_time": "16:57:13", "remaining_time": "8:21:09", "throughput": 8514.99, "total_tokens": 519695984} {"current_steps": 510500, "total_steps": 761865, "loss": 1.9647, "lr": 2.453956206761132e-07, "epoch": 10.050993286212124, "percentage": 67.01, "elapsed_time": "16:57:24", "remaining_time": "8:20:57", "throughput": 8515.03, "total_tokens": 519798384} {"current_steps": 510600, "total_steps": 761865, "loss": 2.0005, "lr": 2.45218194529482e-07, "epoch": 10.052962138961627, "percentage": 67.02, "elapsed_time": "16:57:36", "remaining_time": "8:20:45", "throughput": 8515.06, "total_tokens": 519900048} {"current_steps": 510700, "total_steps": 761865, "loss": 1.9848, "lr": 2.450408117063477e-07, "epoch": 10.05493099171113, "percentage": 67.03, "elapsed_time": "16:57:48", "remaining_time": "8:20:33", "throughput": 8515.1, "total_tokens": 520001808} {"current_steps": 510800, "total_steps": 761865, "loss": 1.9745, "lr": 2.44863472236873e-07, "epoch": 10.056899844460633, "percentage": 67.05, "elapsed_time": "16:57:59", "remaining_time": "8:20:21", "throughput": 8515.13, "total_tokens": 520102888} {"current_steps": 510900, "total_steps": 761865, "loss": 1.9473, "lr": 2.4468617615121285e-07, "epoch": 10.058868697210135, "percentage": 67.06, "elapsed_time": "16:58:11", "remaining_time": "8:20:09", "throughput": 8515.17, "total_tokens": 520205288} {"current_steps": 511000, "total_steps": 761865, "loss": 1.9238, "lr": 2.44508923479515e-07, "epoch": 10.060837549959638, "percentage": 67.07, "elapsed_time": "16:58:23", "remaining_time": "8:19:57", "throughput": 8515.21, "total_tokens": 520307688} {"current_steps": 511100, "total_steps": 761865, "loss": 2.0178, "lr": 2.4433171425192013e-07, "epoch": 10.06280640270914, "percentage": 67.09, "elapsed_time": "16:58:34", "remaining_time": "8:19:45", "throughput": 8515.24, "total_tokens": 520408568} {"current_steps": 511200, "total_steps": 761865, "loss": 2.0106, "lr": 2.4415454849856053e-07, "epoch": 10.064775255458644, "percentage": 67.1, "elapsed_time": "16:58:46", "remaining_time": "8:19:33", "throughput": 8515.28, "total_tokens": 520510488} {"current_steps": 511300, "total_steps": 761865, "loss": 2.0193, "lr": 2.4397742624956214e-07, "epoch": 10.066744108208146, "percentage": 67.11, "elapsed_time": "16:58:58", "remaining_time": "8:19:21", "throughput": 8515.31, "total_tokens": 520612128} {"current_steps": 511400, "total_steps": 761865, "loss": 1.9404, "lr": 2.4380034753504296e-07, "epoch": 10.06871296095765, "percentage": 67.12, "elapsed_time": "16:59:10", "remaining_time": "8:19:09", "throughput": 8515.34, "total_tokens": 520712912} {"current_steps": 511500, "total_steps": 761865, "loss": 1.9989, "lr": 2.43623312385114e-07, "epoch": 10.070681813707154, "percentage": 67.14, "elapsed_time": "16:59:21", "remaining_time": "8:18:56", "throughput": 8515.37, "total_tokens": 520813928} {"current_steps": 511600, "total_steps": 761865, "loss": 1.9649, "lr": 2.434463208298782e-07, "epoch": 10.072650666456656, "percentage": 67.15, "elapsed_time": "16:59:33", "remaining_time": "8:18:44", "throughput": 8515.39, "total_tokens": 520914072} {"current_steps": 511700, "total_steps": 761865, "loss": 1.9807, "lr": 2.432693728994315e-07, "epoch": 10.07461951920616, "percentage": 67.16, "elapsed_time": "16:59:44", "remaining_time": "8:18:32", "throughput": 8515.43, "total_tokens": 521015904} {"current_steps": 511800, "total_steps": 761865, "loss": 1.9625, "lr": 2.4309246862386295e-07, "epoch": 10.076588371955662, "percentage": 67.18, "elapsed_time": "16:59:56", "remaining_time": "8:18:20", "throughput": 8515.47, "total_tokens": 521118304} {"current_steps": 511900, "total_steps": 761865, "loss": 1.9813, "lr": 2.4291560803325304e-07, "epoch": 10.078557224705165, "percentage": 67.19, "elapsed_time": "17:00:08", "remaining_time": "8:18:08", "throughput": 8515.5, "total_tokens": 521218856} {"current_steps": 512000, "total_steps": 761865, "loss": 2.0091, "lr": 2.427387911576759e-07, "epoch": 10.080526077454667, "percentage": 67.2, "elapsed_time": "17:00:20", "remaining_time": "8:17:56", "throughput": 8515.54, "total_tokens": 521321256} {"current_steps": 512100, "total_steps": 761865, "loss": 2.0034, "lr": 2.42562018027197e-07, "epoch": 10.08249493020417, "percentage": 67.22, "elapsed_time": "17:00:31", "remaining_time": "8:17:44", "throughput": 8515.57, "total_tokens": 521422960} {"current_steps": 512200, "total_steps": 761865, "loss": 2.0196, "lr": 2.42385288671876e-07, "epoch": 10.084463782953673, "percentage": 67.23, "elapsed_time": "17:00:43", "remaining_time": "8:17:32", "throughput": 8515.61, "total_tokens": 521524184} {"current_steps": 512300, "total_steps": 761865, "loss": 1.965, "lr": 2.4220860312176364e-07, "epoch": 10.086432635703176, "percentage": 67.24, "elapsed_time": "17:00:55", "remaining_time": "8:17:20", "throughput": 8515.64, "total_tokens": 521625968} {"current_steps": 512400, "total_steps": 761865, "loss": 2.0187, "lr": 2.420319614069043e-07, "epoch": 10.088401488452678, "percentage": 67.26, "elapsed_time": "17:01:06", "remaining_time": "8:17:08", "throughput": 8515.67, "total_tokens": 521727608} {"current_steps": 512500, "total_steps": 761865, "loss": 1.9888, "lr": 2.4185536355733363e-07, "epoch": 10.090370341202181, "percentage": 67.27, "elapsed_time": "17:01:18", "remaining_time": "8:16:55", "throughput": 8515.71, "total_tokens": 521829152} {"current_steps": 512600, "total_steps": 761865, "loss": 1.9639, "lr": 2.4167880960308153e-07, "epoch": 10.092339193951684, "percentage": 67.28, "elapsed_time": "17:01:30", "remaining_time": "8:16:43", "throughput": 8515.75, "total_tokens": 521931552} {"current_steps": 512700, "total_steps": 761865, "loss": 1.9477, "lr": 2.4150229957416887e-07, "epoch": 10.094308046701187, "percentage": 67.3, "elapsed_time": "17:01:41", "remaining_time": "8:16:31", "throughput": 8515.78, "total_tokens": 522033448} {"current_steps": 512800, "total_steps": 761865, "loss": 1.9932, "lr": 2.4132583350060984e-07, "epoch": 10.09627689945069, "percentage": 67.31, "elapsed_time": "17:01:53", "remaining_time": "8:16:19", "throughput": 8515.81, "total_tokens": 522134376} {"current_steps": 512900, "total_steps": 761865, "loss": 1.9581, "lr": 2.411494114124112e-07, "epoch": 10.098245752200192, "percentage": 67.32, "elapsed_time": "17:02:05", "remaining_time": "8:16:07", "throughput": 8515.85, "total_tokens": 522236776} {"current_steps": 513000, "total_steps": 761865, "loss": 1.9736, "lr": 2.409730333395718e-07, "epoch": 10.100214604949695, "percentage": 67.33, "elapsed_time": "17:02:16", "remaining_time": "8:15:55", "throughput": 8515.89, "total_tokens": 522338552} {"current_steps": 513100, "total_steps": 761865, "loss": 1.9951, "lr": 2.407966993120835e-07, "epoch": 10.102183457699198, "percentage": 67.35, "elapsed_time": "17:02:28", "remaining_time": "8:15:43", "throughput": 8515.93, "total_tokens": 522440952} {"current_steps": 513200, "total_steps": 761865, "loss": 1.9675, "lr": 2.406204093599302e-07, "epoch": 10.104152310448702, "percentage": 67.36, "elapsed_time": "17:02:40", "remaining_time": "8:15:31", "throughput": 8515.96, "total_tokens": 522542616} {"current_steps": 513300, "total_steps": 761865, "loss": 1.9681, "lr": 2.404441635130885e-07, "epoch": 10.106121163198205, "percentage": 67.37, "elapsed_time": "17:02:52", "remaining_time": "8:15:19", "throughput": 8516.0, "total_tokens": 522645016} {"current_steps": 513400, "total_steps": 761865, "loss": 1.9743, "lr": 2.4026796180152757e-07, "epoch": 10.108090015947708, "percentage": 67.39, "elapsed_time": "17:03:03", "remaining_time": "8:15:07", "throughput": 8516.04, "total_tokens": 522746672} {"current_steps": 513500, "total_steps": 761865, "loss": 1.9734, "lr": 2.400918042552093e-07, "epoch": 10.11005886869721, "percentage": 67.4, "elapsed_time": "17:03:15", "remaining_time": "8:14:55", "throughput": 8516.08, "total_tokens": 522849072} {"current_steps": 513600, "total_steps": 761865, "loss": 2.0136, "lr": 2.3991569090408737e-07, "epoch": 10.112027721446713, "percentage": 67.41, "elapsed_time": "17:03:27", "remaining_time": "8:14:43", "throughput": 8516.1, "total_tokens": 522949760} {"current_steps": 513700, "total_steps": 761865, "loss": 1.9863, "lr": 2.3973962177810845e-07, "epoch": 10.113996574196216, "percentage": 67.43, "elapsed_time": "17:03:38", "remaining_time": "8:14:31", "throughput": 8516.14, "total_tokens": 523051608} {"current_steps": 513800, "total_steps": 761865, "loss": 1.9778, "lr": 2.3956359690721186e-07, "epoch": 10.115965426945719, "percentage": 67.44, "elapsed_time": "17:03:50", "remaining_time": "8:14:18", "throughput": 8516.18, "total_tokens": 523153568} {"current_steps": 513900, "total_steps": 761865, "loss": 1.9951, "lr": 2.393876163213289e-07, "epoch": 10.117934279695222, "percentage": 67.45, "elapsed_time": "17:04:02", "remaining_time": "8:14:06", "throughput": 8516.21, "total_tokens": 523255056} {"current_steps": 514000, "total_steps": 761865, "loss": 1.9755, "lr": 2.3921168005038384e-07, "epoch": 10.119903132444724, "percentage": 67.47, "elapsed_time": "17:04:13", "remaining_time": "8:13:54", "throughput": 8516.25, "total_tokens": 523357456} {"current_steps": 514100, "total_steps": 761865, "loss": 1.9992, "lr": 2.390357881242929e-07, "epoch": 10.121871985194227, "percentage": 67.48, "elapsed_time": "17:04:25", "remaining_time": "8:13:42", "throughput": 8516.29, "total_tokens": 523459856} {"current_steps": 514200, "total_steps": 761865, "loss": 1.9695, "lr": 2.3885994057296506e-07, "epoch": 10.12384083794373, "percentage": 67.49, "elapsed_time": "17:04:37", "remaining_time": "8:13:30", "throughput": 8516.33, "total_tokens": 523561464} {"current_steps": 514300, "total_steps": 761865, "loss": 1.9772, "lr": 2.386841374263017e-07, "epoch": 10.125809690693233, "percentage": 67.51, "elapsed_time": "17:04:49", "remaining_time": "8:13:18", "throughput": 8516.37, "total_tokens": 523663864} {"current_steps": 514400, "total_steps": 761865, "loss": 1.9902, "lr": 2.3850837871419703e-07, "epoch": 10.127778543442735, "percentage": 67.52, "elapsed_time": "17:05:00", "remaining_time": "8:13:06", "throughput": 8516.4, "total_tokens": 523765712} {"current_steps": 514500, "total_steps": 761865, "loss": 2.0134, "lr": 2.3833266446653682e-07, "epoch": 10.129747396192238, "percentage": 67.53, "elapsed_time": "17:05:12", "remaining_time": "8:12:54", "throughput": 8516.44, "total_tokens": 523867632} {"current_steps": 514600, "total_steps": 761865, "loss": 1.9597, "lr": 2.381569947132e-07, "epoch": 10.131716248941741, "percentage": 67.54, "elapsed_time": "17:05:24", "remaining_time": "8:12:42", "throughput": 8516.47, "total_tokens": 523969264} {"current_steps": 514700, "total_steps": 761865, "loss": 1.9922, "lr": 2.379813694840578e-07, "epoch": 10.133685101691244, "percentage": 67.56, "elapsed_time": "17:05:35", "remaining_time": "8:12:30", "throughput": 8516.49, "total_tokens": 524069256} {"current_steps": 514800, "total_steps": 761865, "loss": 1.9293, "lr": 2.3780578880897367e-07, "epoch": 10.135653954440748, "percentage": 67.57, "elapsed_time": "17:05:47", "remaining_time": "8:12:18", "throughput": 8516.52, "total_tokens": 524170704} {"current_steps": 514900, "total_steps": 761865, "loss": 1.9511, "lr": 2.3763025271780392e-07, "epoch": 10.137622807190251, "percentage": 67.58, "elapsed_time": "17:05:59", "remaining_time": "8:12:06", "throughput": 8516.56, "total_tokens": 524272904} {"current_steps": 515000, "total_steps": 761865, "loss": 1.959, "lr": 2.3745476124039638e-07, "epoch": 10.139591659939754, "percentage": 67.6, "elapsed_time": "17:06:10", "remaining_time": "8:11:54", "throughput": 8516.6, "total_tokens": 524375304} {"current_steps": 515100, "total_steps": 761865, "loss": 1.9715, "lr": 2.3727931440659267e-07, "epoch": 10.141560512689257, "percentage": 67.61, "elapsed_time": "17:06:23", "remaining_time": "8:11:42", "throughput": 8516.54, "total_tokens": 524477112} {"current_steps": 515200, "total_steps": 761865, "loss": 1.9913, "lr": 2.371039122462255e-07, "epoch": 10.14352936543876, "percentage": 67.62, "elapsed_time": "17:06:35", "remaining_time": "8:11:30", "throughput": 8516.58, "total_tokens": 524579296} {"current_steps": 515300, "total_steps": 761865, "loss": 1.9816, "lr": 2.3692855478912082e-07, "epoch": 10.145498218188262, "percentage": 67.64, "elapsed_time": "17:06:46", "remaining_time": "8:11:18", "throughput": 8516.62, "total_tokens": 524681208} {"current_steps": 515400, "total_steps": 761865, "loss": 1.9869, "lr": 2.3675324206509624e-07, "epoch": 10.147467070937765, "percentage": 67.65, "elapsed_time": "17:06:58", "remaining_time": "8:11:05", "throughput": 8516.64, "total_tokens": 524781424} {"current_steps": 515500, "total_steps": 761865, "loss": 2.0115, "lr": 2.3657797410396279e-07, "epoch": 10.149435923687268, "percentage": 67.66, "elapsed_time": "17:07:10", "remaining_time": "8:10:53", "throughput": 8516.67, "total_tokens": 524883008} {"current_steps": 515600, "total_steps": 761865, "loss": 1.9893, "lr": 2.3640275093552292e-07, "epoch": 10.15140477643677, "percentage": 67.68, "elapsed_time": "17:07:21", "remaining_time": "8:10:41", "throughput": 8516.71, "total_tokens": 524985040} {"current_steps": 515700, "total_steps": 761865, "loss": 1.9814, "lr": 2.3622757258957215e-07, "epoch": 10.153373629186273, "percentage": 67.69, "elapsed_time": "17:07:33", "remaining_time": "8:10:29", "throughput": 8516.74, "total_tokens": 525086168} {"current_steps": 515800, "total_steps": 761865, "loss": 2.0084, "lr": 2.3605243909589756e-07, "epoch": 10.155342481935776, "percentage": 67.7, "elapsed_time": "17:07:45", "remaining_time": "8:10:17", "throughput": 8516.78, "total_tokens": 525188568} {"current_steps": 515900, "total_steps": 761865, "loss": 2.0243, "lr": 2.3587735048427964e-07, "epoch": 10.157311334685279, "percentage": 67.72, "elapsed_time": "17:07:56", "remaining_time": "8:10:05", "throughput": 8516.81, "total_tokens": 525289304} {"current_steps": 516000, "total_steps": 761865, "loss": 2.0297, "lr": 2.357023067844907e-07, "epoch": 10.159280187434781, "percentage": 67.73, "elapsed_time": "17:08:08", "remaining_time": "8:09:53", "throughput": 8516.83, "total_tokens": 525389840} {"current_steps": 516100, "total_steps": 761865, "loss": 1.985, "lr": 2.3552730802629518e-07, "epoch": 10.161249040184284, "percentage": 67.74, "elapsed_time": "17:08:20", "remaining_time": "8:09:41", "throughput": 8516.87, "total_tokens": 525492240} {"current_steps": 516200, "total_steps": 761865, "loss": 2.0207, "lr": 2.3535235423945022e-07, "epoch": 10.163217892933787, "percentage": 67.75, "elapsed_time": "17:08:31", "remaining_time": "8:09:29", "throughput": 8516.91, "total_tokens": 525594056} {"current_steps": 516300, "total_steps": 761865, "loss": 1.9616, "lr": 2.3517744545370527e-07, "epoch": 10.16518674568329, "percentage": 67.77, "elapsed_time": "17:08:43", "remaining_time": "8:09:17", "throughput": 8516.95, "total_tokens": 525696456} {"current_steps": 516400, "total_steps": 761865, "loss": 1.9646, "lr": 2.3500258169880233e-07, "epoch": 10.167155598432792, "percentage": 67.78, "elapsed_time": "17:08:55", "remaining_time": "8:09:05", "throughput": 8516.96, "total_tokens": 525798416} {"current_steps": 516500, "total_steps": 761865, "loss": 1.9957, "lr": 2.348277630044751e-07, "epoch": 10.169124451182297, "percentage": 67.79, "elapsed_time": "17:09:07", "remaining_time": "8:08:53", "throughput": 8516.98, "total_tokens": 525900816} {"current_steps": 516600, "total_steps": 761865, "loss": 1.9885, "lr": 2.3465298940045014e-07, "epoch": 10.1710933039318, "percentage": 67.81, "elapsed_time": "17:09:19", "remaining_time": "8:08:41", "throughput": 8516.99, "total_tokens": 526002544} {"current_steps": 516700, "total_steps": 761865, "loss": 2.0208, "lr": 2.3447826091644635e-07, "epoch": 10.173062156681302, "percentage": 67.82, "elapsed_time": "17:09:30", "remaining_time": "8:08:29", "throughput": 8517.01, "total_tokens": 526103712} {"current_steps": 516800, "total_steps": 761865, "loss": 2.0158, "lr": 2.3430357758217478e-07, "epoch": 10.175031009430805, "percentage": 67.83, "elapsed_time": "17:09:42", "remaining_time": "8:08:17", "throughput": 8517.03, "total_tokens": 526206112} {"current_steps": 516900, "total_steps": 761865, "loss": 1.9853, "lr": 2.34128939427339e-07, "epoch": 10.176999862180308, "percentage": 67.85, "elapsed_time": "17:09:54", "remaining_time": "8:08:05", "throughput": 8517.03, "total_tokens": 526307128} {"current_steps": 517000, "total_steps": 761865, "loss": 1.994, "lr": 2.339543464816344e-07, "epoch": 10.17896871492981, "percentage": 67.86, "elapsed_time": "17:10:06", "remaining_time": "8:07:53", "throughput": 8517.03, "total_tokens": 526407776} {"current_steps": 517100, "total_steps": 761865, "loss": 1.9619, "lr": 2.3377979877474935e-07, "epoch": 10.180937567679313, "percentage": 67.87, "elapsed_time": "17:10:18", "remaining_time": "8:07:41", "throughput": 8517.03, "total_tokens": 526510176} {"current_steps": 517200, "total_steps": 761865, "loss": 1.9753, "lr": 2.3360529633636406e-07, "epoch": 10.182906420428816, "percentage": 67.89, "elapsed_time": "17:10:30", "remaining_time": "8:07:29", "throughput": 8517.03, "total_tokens": 526612576} {"current_steps": 517300, "total_steps": 761865, "loss": 2.0142, "lr": 2.334308391961514e-07, "epoch": 10.184875273178319, "percentage": 67.9, "elapsed_time": "17:10:42", "remaining_time": "8:07:17", "throughput": 8517.03, "total_tokens": 526714120} {"current_steps": 517400, "total_steps": 761865, "loss": 1.9928, "lr": 2.3325642738377604e-07, "epoch": 10.186844125927822, "percentage": 67.91, "elapsed_time": "17:10:54", "remaining_time": "8:07:05", "throughput": 8517.03, "total_tokens": 526815200} {"current_steps": 517500, "total_steps": 761865, "loss": 1.9741, "lr": 2.3308206092889537e-07, "epoch": 10.188812978677324, "percentage": 67.93, "elapsed_time": "17:11:06", "remaining_time": "8:06:53", "throughput": 8517.08, "total_tokens": 526917600} {"current_steps": 517600, "total_steps": 761865, "loss": 1.9922, "lr": 2.3290773986115896e-07, "epoch": 10.190781831426827, "percentage": 67.94, "elapsed_time": "17:11:17", "remaining_time": "8:06:41", "throughput": 8517.14, "total_tokens": 527019424} {"current_steps": 517700, "total_steps": 761865, "loss": 1.9675, "lr": 2.3273346421020884e-07, "epoch": 10.19275068417633, "percentage": 67.95, "elapsed_time": "17:11:29", "remaining_time": "8:06:28", "throughput": 8517.17, "total_tokens": 527119576} {"current_steps": 517800, "total_steps": 761865, "loss": 1.9674, "lr": 2.325592340056785e-07, "epoch": 10.194719536925833, "percentage": 67.96, "elapsed_time": "17:11:40", "remaining_time": "8:06:16", "throughput": 8517.19, "total_tokens": 527220704} {"current_steps": 517900, "total_steps": 761865, "loss": 1.964, "lr": 2.3238504927719489e-07, "epoch": 10.196688389675336, "percentage": 67.98, "elapsed_time": "17:11:52", "remaining_time": "8:06:04", "throughput": 8517.22, "total_tokens": 527323104} {"current_steps": 518000, "total_steps": 761865, "loss": 1.9945, "lr": 2.3221091005437671e-07, "epoch": 10.198657242424838, "percentage": 67.99, "elapsed_time": "17:12:04", "remaining_time": "8:05:52", "throughput": 8517.24, "total_tokens": 527425504} {"current_steps": 518100, "total_steps": 761865, "loss": 1.9797, "lr": 2.3203681636683443e-07, "epoch": 10.200626095174341, "percentage": 68.0, "elapsed_time": "17:12:16", "remaining_time": "8:05:40", "throughput": 8517.25, "total_tokens": 527527904} {"current_steps": 518200, "total_steps": 761865, "loss": 2.0198, "lr": 2.318627682441714e-07, "epoch": 10.202594947923846, "percentage": 68.02, "elapsed_time": "17:12:28", "remaining_time": "8:05:29", "throughput": 8517.24, "total_tokens": 527629408} {"current_steps": 518300, "total_steps": 761865, "loss": 1.9578, "lr": 2.3168876571598305e-07, "epoch": 10.204563800673348, "percentage": 68.03, "elapsed_time": "17:12:40", "remaining_time": "8:05:17", "throughput": 8517.24, "total_tokens": 527731808} {"current_steps": 518400, "total_steps": 761865, "loss": 1.9384, "lr": 2.3151480881185724e-07, "epoch": 10.206532653422851, "percentage": 68.04, "elapsed_time": "17:12:52", "remaining_time": "8:05:05", "throughput": 8517.28, "total_tokens": 527834208} {"current_steps": 518500, "total_steps": 761865, "loss": 1.9443, "lr": 2.3134089756137355e-07, "epoch": 10.208501506172354, "percentage": 68.06, "elapsed_time": "17:13:03", "remaining_time": "8:04:52", "throughput": 8517.31, "total_tokens": 527936608} {"current_steps": 518600, "total_steps": 761865, "loss": 1.9886, "lr": 2.311670319941042e-07, "epoch": 10.210470358921857, "percentage": 68.07, "elapsed_time": "17:13:15", "remaining_time": "8:04:41", "throughput": 8517.32, "total_tokens": 528038208} {"current_steps": 518700, "total_steps": 761865, "loss": 1.9796, "lr": 2.3099321213961365e-07, "epoch": 10.21243921167136, "percentage": 68.08, "elapsed_time": "17:13:27", "remaining_time": "8:04:28", "throughput": 8517.34, "total_tokens": 528138552} {"current_steps": 518800, "total_steps": 761865, "loss": 1.9795, "lr": 2.3081943802745845e-07, "epoch": 10.214408064420862, "percentage": 68.1, "elapsed_time": "17:13:39", "remaining_time": "8:04:16", "throughput": 8517.38, "total_tokens": 528240952} {"current_steps": 518900, "total_steps": 761865, "loss": 1.9542, "lr": 2.306457096871876e-07, "epoch": 10.216376917170365, "percentage": 68.11, "elapsed_time": "17:13:51", "remaining_time": "8:04:04", "throughput": 8517.38, "total_tokens": 528341680} {"current_steps": 519000, "total_steps": 761865, "loss": 1.9563, "lr": 2.3047202714834185e-07, "epoch": 10.218345769919868, "percentage": 68.12, "elapsed_time": "17:14:02", "remaining_time": "8:03:52", "throughput": 8517.41, "total_tokens": 528444080} {"current_steps": 519100, "total_steps": 761865, "loss": 1.9612, "lr": 2.302983904404545e-07, "epoch": 10.22031462266937, "percentage": 68.14, "elapsed_time": "17:14:14", "remaining_time": "8:03:40", "throughput": 8517.44, "total_tokens": 528545760} {"current_steps": 519200, "total_steps": 761865, "loss": 1.9761, "lr": 2.3012479959305114e-07, "epoch": 10.222283475418873, "percentage": 68.15, "elapsed_time": "17:14:26", "remaining_time": "8:03:28", "throughput": 8517.45, "total_tokens": 528648160} {"current_steps": 519300, "total_steps": 761865, "loss": 1.9773, "lr": 2.2995125463564956e-07, "epoch": 10.224252328168376, "percentage": 68.16, "elapsed_time": "17:14:38", "remaining_time": "8:03:16", "throughput": 8517.46, "total_tokens": 528750560} {"current_steps": 519400, "total_steps": 761865, "loss": 1.9713, "lr": 2.2977775559775924e-07, "epoch": 10.226221180917879, "percentage": 68.17, "elapsed_time": "17:14:50", "remaining_time": "8:03:04", "throughput": 8517.44, "total_tokens": 528852960} {"current_steps": 519500, "total_steps": 761865, "loss": 1.9711, "lr": 2.2960430250888247e-07, "epoch": 10.228190033667381, "percentage": 68.19, "elapsed_time": "17:15:02", "remaining_time": "8:02:53", "throughput": 8517.45, "total_tokens": 528955360} {"current_steps": 519600, "total_steps": 761865, "loss": 2.0199, "lr": 2.294308953985134e-07, "epoch": 10.230158886416884, "percentage": 68.2, "elapsed_time": "17:15:14", "remaining_time": "8:02:41", "throughput": 8517.41, "total_tokens": 529055856} {"current_steps": 519700, "total_steps": 761865, "loss": 1.9829, "lr": 2.2925753429613863e-07, "epoch": 10.232127739166387, "percentage": 68.21, "elapsed_time": "17:15:26", "remaining_time": "8:02:29", "throughput": 8517.42, "total_tokens": 529158256} {"current_steps": 519800, "total_steps": 761865, "loss": 2.0033, "lr": 2.2908421923123644e-07, "epoch": 10.23409659191589, "percentage": 68.23, "elapsed_time": "17:15:38", "remaining_time": "8:02:17", "throughput": 8517.44, "total_tokens": 529260656} {"current_steps": 519900, "total_steps": 761865, "loss": 1.9559, "lr": 2.2891095023327762e-07, "epoch": 10.236065444665394, "percentage": 68.24, "elapsed_time": "17:15:50", "remaining_time": "8:02:05", "throughput": 8517.48, "total_tokens": 529363056} {"current_steps": 520000, "total_steps": 761865, "loss": 1.9941, "lr": 2.2873772733172559e-07, "epoch": 10.238034297414897, "percentage": 68.25, "elapsed_time": "17:16:01", "remaining_time": "8:01:53", "throughput": 8517.52, "total_tokens": 529465456} {"current_steps": 520100, "total_steps": 761865, "loss": 2.0323, "lr": 2.2856455055603485e-07, "epoch": 10.2400031501644, "percentage": 68.27, "elapsed_time": "17:16:14", "remaining_time": "8:01:41", "throughput": 8517.47, "total_tokens": 529567856} {"current_steps": 520200, "total_steps": 761865, "loss": 1.9791, "lr": 2.2839141993565314e-07, "epoch": 10.241972002913903, "percentage": 68.28, "elapsed_time": "17:16:26", "remaining_time": "8:01:29", "throughput": 8517.5, "total_tokens": 529670256} {"current_steps": 520300, "total_steps": 761865, "loss": 1.9815, "lr": 2.2821833550001923e-07, "epoch": 10.243940855663405, "percentage": 68.29, "elapsed_time": "17:16:37", "remaining_time": "8:01:17", "throughput": 8517.54, "total_tokens": 529772656} {"current_steps": 520400, "total_steps": 761865, "loss": 1.9928, "lr": 2.2804529727856547e-07, "epoch": 10.245909708412908, "percentage": 68.31, "elapsed_time": "17:16:49", "remaining_time": "8:01:05", "throughput": 8517.58, "total_tokens": 529875056} {"current_steps": 520500, "total_steps": 761865, "loss": 2.0213, "lr": 2.278723053007149e-07, "epoch": 10.24787856116241, "percentage": 68.32, "elapsed_time": "17:17:01", "remaining_time": "8:00:53", "throughput": 8517.61, "total_tokens": 529975784} {"current_steps": 520600, "total_steps": 761865, "loss": 1.9674, "lr": 2.2769935959588377e-07, "epoch": 10.249847413911914, "percentage": 68.33, "elapsed_time": "17:17:12", "remaining_time": "8:00:40", "throughput": 8517.64, "total_tokens": 530077432} {"current_steps": 520700, "total_steps": 761865, "loss": 1.9796, "lr": 2.2752646019347947e-07, "epoch": 10.251816266661416, "percentage": 68.35, "elapsed_time": "17:17:24", "remaining_time": "8:00:28", "throughput": 8517.68, "total_tokens": 530179832} {"current_steps": 520800, "total_steps": 761865, "loss": 2.0127, "lr": 2.273536071229029e-07, "epoch": 10.253785119410919, "percentage": 68.36, "elapsed_time": "17:17:36", "remaining_time": "8:00:16", "throughput": 8517.67, "total_tokens": 530280344} {"current_steps": 520900, "total_steps": 761865, "loss": 1.9719, "lr": 2.271808004135456e-07, "epoch": 10.255753972160422, "percentage": 68.37, "elapsed_time": "17:17:48", "remaining_time": "8:00:05", "throughput": 8517.67, "total_tokens": 530382744} {"current_steps": 521000, "total_steps": 761865, "loss": 1.9448, "lr": 2.2700804009479212e-07, "epoch": 10.257722824909925, "percentage": 68.38, "elapsed_time": "17:18:00", "remaining_time": "7:59:53", "throughput": 8517.69, "total_tokens": 530485144} {"current_steps": 521100, "total_steps": 761865, "loss": 1.9488, "lr": 2.268353261960189e-07, "epoch": 10.259691677659427, "percentage": 68.4, "elapsed_time": "17:18:12", "remaining_time": "7:59:41", "throughput": 8517.71, "total_tokens": 530587544} {"current_steps": 521200, "total_steps": 761865, "loss": 2.0316, "lr": 2.266626587465945e-07, "epoch": 10.26166053040893, "percentage": 68.41, "elapsed_time": "17:18:24", "remaining_time": "7:59:29", "throughput": 8517.74, "total_tokens": 530689944} {"current_steps": 521300, "total_steps": 761865, "loss": 1.9591, "lr": 2.2649003777587978e-07, "epoch": 10.263629383158433, "percentage": 68.42, "elapsed_time": "17:18:35", "remaining_time": "7:59:16", "throughput": 8517.77, "total_tokens": 530792344} {"current_steps": 521400, "total_steps": 761865, "loss": 2.0049, "lr": 2.2631746331322697e-07, "epoch": 10.265598235907936, "percentage": 68.44, "elapsed_time": "17:18:47", "remaining_time": "7:59:04", "throughput": 8517.8, "total_tokens": 530893896} {"current_steps": 521500, "total_steps": 761865, "loss": 1.9504, "lr": 2.2614493538798124e-07, "epoch": 10.26756708865744, "percentage": 68.45, "elapsed_time": "17:18:59", "remaining_time": "7:58:52", "throughput": 8517.82, "total_tokens": 530996296} {"current_steps": 521600, "total_steps": 761865, "loss": 1.9635, "lr": 2.2597245402947946e-07, "epoch": 10.269535941406943, "percentage": 68.46, "elapsed_time": "17:19:11", "remaining_time": "7:58:40", "throughput": 8517.84, "total_tokens": 531098696} {"current_steps": 521700, "total_steps": 761865, "loss": 1.949, "lr": 2.2580001926705073e-07, "epoch": 10.271504794156446, "percentage": 68.48, "elapsed_time": "17:19:23", "remaining_time": "7:58:28", "throughput": 8517.86, "total_tokens": 531201096} {"current_steps": 521800, "total_steps": 761865, "loss": 2.0177, "lr": 2.2562763113001588e-07, "epoch": 10.273473646905948, "percentage": 68.49, "elapsed_time": "17:19:34", "remaining_time": "7:58:16", "throughput": 8517.89, "total_tokens": 531302584} {"current_steps": 521900, "total_steps": 761865, "loss": 2.0019, "lr": 2.2545528964768818e-07, "epoch": 10.275442499655451, "percentage": 68.5, "elapsed_time": "17:19:46", "remaining_time": "7:58:04", "throughput": 8517.92, "total_tokens": 531404984} {"current_steps": 522000, "total_steps": 761865, "loss": 2.0172, "lr": 2.2528299484937285e-07, "epoch": 10.277411352404954, "percentage": 68.52, "elapsed_time": "17:19:58", "remaining_time": "7:57:52", "throughput": 8517.96, "total_tokens": 531507384} {"current_steps": 522100, "total_steps": 761865, "loss": 2.0293, "lr": 2.251107467643672e-07, "epoch": 10.279380205154457, "percentage": 68.53, "elapsed_time": "17:20:10", "remaining_time": "7:57:40", "throughput": 8517.98, "total_tokens": 531608608} {"current_steps": 522200, "total_steps": 761865, "loss": 1.9613, "lr": 2.2493854542196073e-07, "epoch": 10.28134905790396, "percentage": 68.54, "elapsed_time": "17:20:21", "remaining_time": "7:57:28", "throughput": 8518.0, "total_tokens": 531710160} {"current_steps": 522300, "total_steps": 761865, "loss": 1.949, "lr": 2.247663908514344e-07, "epoch": 10.283317910653462, "percentage": 68.56, "elapsed_time": "17:20:33", "remaining_time": "7:57:16", "throughput": 8518.02, "total_tokens": 531811880} {"current_steps": 522400, "total_steps": 761865, "loss": 1.9901, "lr": 2.245942830820619e-07, "epoch": 10.285286763402965, "percentage": 68.57, "elapsed_time": "17:20:45", "remaining_time": "7:57:04", "throughput": 8518.04, "total_tokens": 531913512} {"current_steps": 522500, "total_steps": 761865, "loss": 2.029, "lr": 2.2442222214310869e-07, "epoch": 10.287255616152468, "percentage": 68.58, "elapsed_time": "17:20:57", "remaining_time": "7:56:52", "throughput": 8518.05, "total_tokens": 532014576} {"current_steps": 522600, "total_steps": 761865, "loss": 1.9949, "lr": 2.2425020806383248e-07, "epoch": 10.28922446890197, "percentage": 68.59, "elapsed_time": "17:21:09", "remaining_time": "7:56:40", "throughput": 8518.07, "total_tokens": 532116232} {"current_steps": 522700, "total_steps": 761865, "loss": 2.0079, "lr": 2.2407824087348237e-07, "epoch": 10.291193321651473, "percentage": 68.61, "elapsed_time": "17:21:20", "remaining_time": "7:56:28", "throughput": 8518.09, "total_tokens": 532218536} {"current_steps": 522800, "total_steps": 761865, "loss": 2.0133, "lr": 2.239063206013002e-07, "epoch": 10.293162174400976, "percentage": 68.62, "elapsed_time": "17:21:32", "remaining_time": "7:56:16", "throughput": 8518.09, "total_tokens": 532319624} {"current_steps": 522900, "total_steps": 761865, "loss": 1.9766, "lr": 2.237344472765196e-07, "epoch": 10.295131027150479, "percentage": 68.63, "elapsed_time": "17:21:44", "remaining_time": "7:56:04", "throughput": 8518.11, "total_tokens": 532421472} {"current_steps": 523000, "total_steps": 761865, "loss": 1.9889, "lr": 2.2356262092836598e-07, "epoch": 10.297099879899982, "percentage": 68.65, "elapsed_time": "17:21:56", "remaining_time": "7:55:52", "throughput": 8518.14, "total_tokens": 532523048} {"current_steps": 523100, "total_steps": 761865, "loss": 2.0042, "lr": 2.2339084158605736e-07, "epoch": 10.299068732649484, "percentage": 68.66, "elapsed_time": "17:22:08", "remaining_time": "7:55:40", "throughput": 8518.14, "total_tokens": 532623536} {"current_steps": 523200, "total_steps": 761865, "loss": 1.9936, "lr": 2.2321910927880273e-07, "epoch": 10.301037585398989, "percentage": 68.67, "elapsed_time": "17:22:19", "remaining_time": "7:55:28", "throughput": 8518.17, "total_tokens": 532725936} {"current_steps": 523300, "total_steps": 761865, "loss": 1.9373, "lr": 2.230474240358044e-07, "epoch": 10.303006438148492, "percentage": 68.69, "elapsed_time": "17:22:31", "remaining_time": "7:55:16", "throughput": 8518.18, "total_tokens": 532828336} {"current_steps": 523400, "total_steps": 761865, "loss": 1.9802, "lr": 2.2287578588625555e-07, "epoch": 10.304975290897994, "percentage": 68.7, "elapsed_time": "17:22:43", "remaining_time": "7:55:04", "throughput": 8518.2, "total_tokens": 532930736} {"current_steps": 523500, "total_steps": 761865, "loss": 2.0174, "lr": 2.227041948593421e-07, "epoch": 10.306944143647497, "percentage": 68.71, "elapsed_time": "17:22:55", "remaining_time": "7:54:52", "throughput": 8518.21, "total_tokens": 533033136} {"current_steps": 523600, "total_steps": 761865, "loss": 1.9514, "lr": 2.2253265098424111e-07, "epoch": 10.308912996397, "percentage": 68.73, "elapsed_time": "17:23:07", "remaining_time": "7:54:40", "throughput": 8518.23, "total_tokens": 533134480} {"current_steps": 523700, "total_steps": 761865, "loss": 1.9811, "lr": 2.2236115429012296e-07, "epoch": 10.310881849146503, "percentage": 68.74, "elapsed_time": "17:23:19", "remaining_time": "7:54:28", "throughput": 8518.25, "total_tokens": 533236880} {"current_steps": 523800, "total_steps": 761865, "loss": 1.9441, "lr": 2.2218970480614862e-07, "epoch": 10.312850701896005, "percentage": 68.75, "elapsed_time": "17:23:31", "remaining_time": "7:54:16", "throughput": 8518.27, "total_tokens": 533339280} {"current_steps": 523900, "total_steps": 761865, "loss": 2.0012, "lr": 2.220183025614718e-07, "epoch": 10.314819554645508, "percentage": 68.77, "elapsed_time": "17:23:42", "remaining_time": "7:54:04", "throughput": 8518.29, "total_tokens": 533440728} {"current_steps": 524000, "total_steps": 761865, "loss": 1.9657, "lr": 2.2184694758523802e-07, "epoch": 10.316788407395011, "percentage": 68.78, "elapsed_time": "17:23:54", "remaining_time": "7:53:52", "throughput": 8518.32, "total_tokens": 533542312} {"current_steps": 524100, "total_steps": 761865, "loss": 2.0017, "lr": 2.2167563990658478e-07, "epoch": 10.318757260144514, "percentage": 68.79, "elapsed_time": "17:24:06", "remaining_time": "7:53:40", "throughput": 8518.32, "total_tokens": 533644224} {"current_steps": 524200, "total_steps": 761865, "loss": 1.9784, "lr": 2.2150437955464164e-07, "epoch": 10.320726112894016, "percentage": 68.8, "elapsed_time": "17:24:18", "remaining_time": "7:53:28", "throughput": 8518.33, "total_tokens": 533746104} {"current_steps": 524300, "total_steps": 761865, "loss": 2.026, "lr": 2.2133316655852962e-07, "epoch": 10.32269496564352, "percentage": 68.82, "elapsed_time": "17:24:30", "remaining_time": "7:53:16", "throughput": 8518.35, "total_tokens": 533848504} {"current_steps": 524400, "total_steps": 761865, "loss": 1.9924, "lr": 2.2116200094736226e-07, "epoch": 10.324663818393022, "percentage": 68.83, "elapsed_time": "17:24:42", "remaining_time": "7:53:04", "throughput": 8518.35, "total_tokens": 533950312} {"current_steps": 524500, "total_steps": 761865, "loss": 2.0138, "lr": 2.209908827502448e-07, "epoch": 10.326632671142525, "percentage": 68.84, "elapsed_time": "17:24:54", "remaining_time": "7:52:52", "throughput": 8518.36, "total_tokens": 534052712} {"current_steps": 524600, "total_steps": 761865, "loss": 1.9975, "lr": 2.2081981199627464e-07, "epoch": 10.328601523892027, "percentage": 68.86, "elapsed_time": "17:25:06", "remaining_time": "7:52:40", "throughput": 8518.39, "total_tokens": 534154120} {"current_steps": 524700, "total_steps": 761865, "loss": 1.9657, "lr": 2.2064878871454056e-07, "epoch": 10.33057037664153, "percentage": 68.87, "elapsed_time": "17:25:17", "remaining_time": "7:52:28", "throughput": 8518.41, "total_tokens": 534256520} {"current_steps": 524800, "total_steps": 761865, "loss": 1.9913, "lr": 2.2047781293412382e-07, "epoch": 10.332539229391035, "percentage": 68.88, "elapsed_time": "17:25:30", "remaining_time": "7:52:16", "throughput": 8518.38, "total_tokens": 534358920} {"current_steps": 524900, "total_steps": 761865, "loss": 2.0529, "lr": 2.2030688468409736e-07, "epoch": 10.334508082140538, "percentage": 68.9, "elapsed_time": "17:25:41", "remaining_time": "7:52:04", "throughput": 8518.38, "total_tokens": 534458480} {"current_steps": 525000, "total_steps": 761865, "loss": 1.9256, "lr": 2.2013600399352617e-07, "epoch": 10.33647693489004, "percentage": 68.91, "elapsed_time": "17:25:53", "remaining_time": "7:51:52", "throughput": 8518.39, "total_tokens": 534560408} {"current_steps": 525100, "total_steps": 761865, "loss": 1.9474, "lr": 2.1996517089146716e-07, "epoch": 10.338445787639543, "percentage": 68.92, "elapsed_time": "17:26:06", "remaining_time": "7:51:40", "throughput": 8518.33, "total_tokens": 534662808} {"current_steps": 525200, "total_steps": 761865, "loss": 2.0159, "lr": 2.1979438540696872e-07, "epoch": 10.340414640389046, "percentage": 68.94, "elapsed_time": "17:26:17", "remaining_time": "7:51:28", "throughput": 8518.34, "total_tokens": 534764512} {"current_steps": 525300, "total_steps": 761865, "loss": 1.9986, "lr": 2.196236475690717e-07, "epoch": 10.342383493138549, "percentage": 68.95, "elapsed_time": "17:26:29", "remaining_time": "7:51:16", "throughput": 8518.36, "total_tokens": 534866272} {"current_steps": 525400, "total_steps": 761865, "loss": 1.9787, "lr": 2.194529574068086e-07, "epoch": 10.344352345888051, "percentage": 68.96, "elapsed_time": "17:26:41", "remaining_time": "7:51:04", "throughput": 8518.38, "total_tokens": 534968584} {"current_steps": 525500, "total_steps": 761865, "loss": 2.0047, "lr": 2.19282314949204e-07, "epoch": 10.346321198637554, "percentage": 68.98, "elapsed_time": "17:26:53", "remaining_time": "7:50:52", "throughput": 8518.39, "total_tokens": 535070224} {"current_steps": 525600, "total_steps": 761865, "loss": 2.0216, "lr": 2.1911172022527397e-07, "epoch": 10.348290051387057, "percentage": 68.99, "elapsed_time": "17:27:05", "remaining_time": "7:50:40", "throughput": 8518.39, "total_tokens": 535170960} {"current_steps": 525700, "total_steps": 761865, "loss": 1.9949, "lr": 2.1894117326402673e-07, "epoch": 10.35025890413656, "percentage": 69.0, "elapsed_time": "17:27:17", "remaining_time": "7:50:28", "throughput": 8518.41, "total_tokens": 535273360} {"current_steps": 525800, "total_steps": 761865, "loss": 1.964, "lr": 2.1877067409446241e-07, "epoch": 10.352227756886062, "percentage": 69.01, "elapsed_time": "17:27:29", "remaining_time": "7:50:16", "throughput": 8518.42, "total_tokens": 535374984} {"current_steps": 525900, "total_steps": 761865, "loss": 2.0191, "lr": 2.1860022274557317e-07, "epoch": 10.354196609635565, "percentage": 69.03, "elapsed_time": "17:27:40", "remaining_time": "7:50:04", "throughput": 8518.44, "total_tokens": 535477384} {"current_steps": 526000, "total_steps": 761865, "loss": 1.9617, "lr": 2.1842981924634242e-07, "epoch": 10.356165462385068, "percentage": 69.04, "elapsed_time": "17:27:52", "remaining_time": "7:49:52", "throughput": 8518.46, "total_tokens": 535579088} {"current_steps": 526100, "total_steps": 761865, "loss": 1.9685, "lr": 2.182594636257459e-07, "epoch": 10.35813431513457, "percentage": 69.05, "elapsed_time": "17:28:04", "remaining_time": "7:49:40", "throughput": 8518.48, "total_tokens": 535681488} {"current_steps": 526200, "total_steps": 761865, "loss": 2.0081, "lr": 2.1808915591275155e-07, "epoch": 10.360103167884073, "percentage": 69.07, "elapsed_time": "17:28:16", "remaining_time": "7:49:28", "throughput": 8518.5, "total_tokens": 535783448} {"current_steps": 526300, "total_steps": 761865, "loss": 1.9611, "lr": 2.1791889613631836e-07, "epoch": 10.362072020633576, "percentage": 69.08, "elapsed_time": "17:28:28", "remaining_time": "7:49:16", "throughput": 8518.51, "total_tokens": 535885848} {"current_steps": 526400, "total_steps": 761865, "loss": 1.9851, "lr": 2.1774868432539773e-07, "epoch": 10.364040873383079, "percentage": 69.09, "elapsed_time": "17:28:40", "remaining_time": "7:49:04", "throughput": 8518.53, "total_tokens": 535987608} {"current_steps": 526500, "total_steps": 761865, "loss": 2.0047, "lr": 2.1757852050893265e-07, "epoch": 10.366009726132582, "percentage": 69.11, "elapsed_time": "17:28:52", "remaining_time": "7:48:52", "throughput": 8518.54, "total_tokens": 536089304} {"current_steps": 526600, "total_steps": 761865, "loss": 1.9521, "lr": 2.1740840471585837e-07, "epoch": 10.367978578882086, "percentage": 69.12, "elapsed_time": "17:29:03", "remaining_time": "7:48:40", "throughput": 8518.56, "total_tokens": 536191704} {"current_steps": 526700, "total_steps": 761865, "loss": 1.9706, "lr": 2.1723833697510113e-07, "epoch": 10.369947431631589, "percentage": 69.13, "elapsed_time": "17:29:15", "remaining_time": "7:48:28", "throughput": 8518.58, "total_tokens": 536293504} {"current_steps": 526800, "total_steps": 761865, "loss": 1.9381, "lr": 2.170683173155798e-07, "epoch": 10.371916284381092, "percentage": 69.15, "elapsed_time": "17:29:27", "remaining_time": "7:48:16", "throughput": 8518.59, "total_tokens": 536395376} {"current_steps": 526900, "total_steps": 761865, "loss": 2.0253, "lr": 2.1689834576620474e-07, "epoch": 10.373885137130594, "percentage": 69.16, "elapsed_time": "17:29:39", "remaining_time": "7:48:04", "throughput": 8518.61, "total_tokens": 536497776} {"current_steps": 527000, "total_steps": 761865, "loss": 2.0039, "lr": 2.167284223558782e-07, "epoch": 10.375853989880097, "percentage": 69.17, "elapsed_time": "17:29:51", "remaining_time": "7:47:52", "throughput": 8518.62, "total_tokens": 536599184} {"current_steps": 527100, "total_steps": 761865, "loss": 1.9946, "lr": 2.1655854711349442e-07, "epoch": 10.3778228426296, "percentage": 69.19, "elapsed_time": "17:30:03", "remaining_time": "7:47:40", "throughput": 8518.64, "total_tokens": 536701584} {"current_steps": 527200, "total_steps": 761865, "loss": 1.9438, "lr": 2.163887200679388e-07, "epoch": 10.379791695379103, "percentage": 69.2, "elapsed_time": "17:30:15", "remaining_time": "7:47:28", "throughput": 8518.65, "total_tokens": 536803128} {"current_steps": 527300, "total_steps": 761865, "loss": 1.9879, "lr": 2.1621894124808932e-07, "epoch": 10.381760548128605, "percentage": 69.21, "elapsed_time": "17:30:26", "remaining_time": "7:47:16", "throughput": 8518.67, "total_tokens": 536905528} {"current_steps": 527400, "total_steps": 761865, "loss": 1.9822, "lr": 2.1604921068281528e-07, "epoch": 10.383729400878108, "percentage": 69.22, "elapsed_time": "17:30:38", "remaining_time": "7:47:05", "throughput": 8518.69, "total_tokens": 537007928} {"current_steps": 527500, "total_steps": 761865, "loss": 1.964, "lr": 2.1587952840097823e-07, "epoch": 10.385698253627611, "percentage": 69.24, "elapsed_time": "17:30:50", "remaining_time": "7:46:53", "throughput": 8518.7, "total_tokens": 537109896} {"current_steps": 527600, "total_steps": 761865, "loss": 2.0012, "lr": 2.1570989443143084e-07, "epoch": 10.387667106377114, "percentage": 69.25, "elapsed_time": "17:31:02", "remaining_time": "7:46:41", "throughput": 8518.71, "total_tokens": 537211504} {"current_steps": 527700, "total_steps": 761865, "loss": 2.0267, "lr": 2.1554030880301803e-07, "epoch": 10.389635959126617, "percentage": 69.26, "elapsed_time": "17:31:14", "remaining_time": "7:46:29", "throughput": 8518.72, "total_tokens": 537313448} {"current_steps": 527800, "total_steps": 761865, "loss": 2.0146, "lr": 2.1537077154457656e-07, "epoch": 10.39160481187612, "percentage": 69.28, "elapsed_time": "17:31:26", "remaining_time": "7:46:17", "throughput": 8518.74, "total_tokens": 537415304} {"current_steps": 527900, "total_steps": 761865, "loss": 1.9446, "lr": 2.152012826849348e-07, "epoch": 10.393573664625622, "percentage": 69.29, "elapsed_time": "17:31:38", "remaining_time": "7:46:05", "throughput": 8518.75, "total_tokens": 537516896} {"current_steps": 528000, "total_steps": 761865, "loss": 1.9952, "lr": 2.150318422529127e-07, "epoch": 10.395542517375125, "percentage": 69.3, "elapsed_time": "17:31:49", "remaining_time": "7:45:53", "throughput": 8518.76, "total_tokens": 537618984} {"current_steps": 528100, "total_steps": 761865, "loss": 1.9506, "lr": 2.1486245027732208e-07, "epoch": 10.397511370124628, "percentage": 69.32, "elapsed_time": "17:32:01", "remaining_time": "7:45:41", "throughput": 8518.78, "total_tokens": 537721384} {"current_steps": 528200, "total_steps": 761865, "loss": 1.9586, "lr": 2.1469310678696718e-07, "epoch": 10.399480222874132, "percentage": 69.33, "elapsed_time": "17:32:13", "remaining_time": "7:45:29", "throughput": 8518.8, "total_tokens": 537823104} {"current_steps": 528300, "total_steps": 761865, "loss": 2.0144, "lr": 2.1452381181064293e-07, "epoch": 10.401449075623635, "percentage": 69.34, "elapsed_time": "17:32:25", "remaining_time": "7:45:17", "throughput": 8518.82, "total_tokens": 537925504} {"current_steps": 528400, "total_steps": 761865, "loss": 1.9708, "lr": 2.1435456537713681e-07, "epoch": 10.403417928373138, "percentage": 69.36, "elapsed_time": "17:32:37", "remaining_time": "7:45:05", "throughput": 8518.83, "total_tokens": 538027088} {"current_steps": 528500, "total_steps": 761865, "loss": 1.9414, "lr": 2.1418536751522726e-07, "epoch": 10.40538678112264, "percentage": 69.37, "elapsed_time": "17:32:49", "remaining_time": "7:44:53", "throughput": 8518.85, "total_tokens": 538129488} {"current_steps": 528600, "total_steps": 761865, "loss": 1.9672, "lr": 2.1401621825368565e-07, "epoch": 10.407355633872143, "percentage": 69.38, "elapsed_time": "17:33:01", "remaining_time": "7:44:41", "throughput": 8518.86, "total_tokens": 538230440} {"current_steps": 528700, "total_steps": 761865, "loss": 1.9203, "lr": 2.138471176212739e-07, "epoch": 10.409324486621646, "percentage": 69.4, "elapsed_time": "17:33:12", "remaining_time": "7:44:29", "throughput": 8518.88, "total_tokens": 538332840} {"current_steps": 528800, "total_steps": 761865, "loss": 1.9704, "lr": 2.136780656467464e-07, "epoch": 10.411293339371149, "percentage": 69.41, "elapsed_time": "17:33:24", "remaining_time": "7:44:17", "throughput": 8518.89, "total_tokens": 538433896} {"current_steps": 528900, "total_steps": 761865, "loss": 1.9656, "lr": 2.1350906235884852e-07, "epoch": 10.413262192120651, "percentage": 69.42, "elapsed_time": "17:33:36", "remaining_time": "7:44:05", "throughput": 8518.89, "total_tokens": 538534640} {"current_steps": 529000, "total_steps": 761865, "loss": 1.985, "lr": 2.133401077863184e-07, "epoch": 10.415231044870154, "percentage": 69.43, "elapsed_time": "17:33:48", "remaining_time": "7:43:53", "throughput": 8518.9, "total_tokens": 538636176} {"current_steps": 529100, "total_steps": 761865, "loss": 2.019, "lr": 2.131712019578853e-07, "epoch": 10.417199897619657, "percentage": 69.45, "elapsed_time": "17:34:00", "remaining_time": "7:43:41", "throughput": 8518.92, "total_tokens": 538738576} {"current_steps": 529200, "total_steps": 761865, "loss": 2.0357, "lr": 2.1300234490226992e-07, "epoch": 10.41916875036916, "percentage": 69.46, "elapsed_time": "17:34:12", "remaining_time": "7:43:29", "throughput": 8518.93, "total_tokens": 538839320} {"current_steps": 529300, "total_steps": 761865, "loss": 2.0347, "lr": 2.1283353664818516e-07, "epoch": 10.421137603118662, "percentage": 69.47, "elapsed_time": "17:34:23", "remaining_time": "7:43:17", "throughput": 8518.95, "total_tokens": 538941720} {"current_steps": 529400, "total_steps": 761865, "loss": 2.0019, "lr": 2.126647772243354e-07, "epoch": 10.423106455868165, "percentage": 69.49, "elapsed_time": "17:34:35", "remaining_time": "7:43:05", "throughput": 8518.96, "total_tokens": 539044120} {"current_steps": 529500, "total_steps": 761865, "loss": 1.9818, "lr": 2.12496066659417e-07, "epoch": 10.425075308617668, "percentage": 69.5, "elapsed_time": "17:34:47", "remaining_time": "7:42:53", "throughput": 8518.98, "total_tokens": 539146520} {"current_steps": 529600, "total_steps": 761865, "loss": 2.0276, "lr": 2.1232740498211731e-07, "epoch": 10.42704416136717, "percentage": 69.51, "elapsed_time": "17:34:59", "remaining_time": "7:42:41", "throughput": 8518.99, "total_tokens": 539248232} {"current_steps": 529700, "total_steps": 761865, "loss": 2.0075, "lr": 2.121587922211161e-07, "epoch": 10.429013014116673, "percentage": 69.53, "elapsed_time": "17:35:11", "remaining_time": "7:42:29", "throughput": 8519.01, "total_tokens": 539350632} {"current_steps": 529800, "total_steps": 761865, "loss": 1.9499, "lr": 2.1199022840508452e-07, "epoch": 10.430981866866176, "percentage": 69.54, "elapsed_time": "17:35:23", "remaining_time": "7:42:17", "throughput": 8519.02, "total_tokens": 539451976} {"current_steps": 529900, "total_steps": 761865, "loss": 1.9291, "lr": 2.1182171356268552e-07, "epoch": 10.43295071961568, "percentage": 69.55, "elapsed_time": "17:35:35", "remaining_time": "7:42:05", "throughput": 8519.04, "total_tokens": 539553840} {"current_steps": 530000, "total_steps": 761865, "loss": 2.0332, "lr": 2.116532477225734e-07, "epoch": 10.434919572365184, "percentage": 69.57, "elapsed_time": "17:35:46", "remaining_time": "7:41:53", "throughput": 8519.05, "total_tokens": 539655664} {"current_steps": 530100, "total_steps": 761865, "loss": 2.0249, "lr": 2.1148483091339447e-07, "epoch": 10.436888425114686, "percentage": 69.58, "elapsed_time": "17:35:59", "remaining_time": "7:41:41", "throughput": 8518.98, "total_tokens": 539757336} {"current_steps": 530200, "total_steps": 761865, "loss": 1.9842, "lr": 2.1131646316378655e-07, "epoch": 10.438857277864189, "percentage": 69.59, "elapsed_time": "17:36:11", "remaining_time": "7:41:29", "throughput": 8518.99, "total_tokens": 539858816} {"current_steps": 530300, "total_steps": 761865, "loss": 1.9736, "lr": 2.111481445023793e-07, "epoch": 10.440826130613692, "percentage": 69.61, "elapsed_time": "17:36:22", "remaining_time": "7:41:17", "throughput": 8518.99, "total_tokens": 539958856} {"current_steps": 530400, "total_steps": 761865, "loss": 1.9289, "lr": 2.1097987495779385e-07, "epoch": 10.442794983363195, "percentage": 69.62, "elapsed_time": "17:36:34", "remaining_time": "7:41:05", "throughput": 8519.01, "total_tokens": 540060736} {"current_steps": 530500, "total_steps": 761865, "loss": 2.0148, "lr": 2.108116545586428e-07, "epoch": 10.444763836112697, "percentage": 69.63, "elapsed_time": "17:36:46", "remaining_time": "7:40:53", "throughput": 8519.03, "total_tokens": 540162928} {"current_steps": 530600, "total_steps": 761865, "loss": 1.9506, "lr": 2.1064348333353084e-07, "epoch": 10.4467326888622, "percentage": 69.64, "elapsed_time": "17:36:58", "remaining_time": "7:40:41", "throughput": 8519.05, "total_tokens": 540265328} {"current_steps": 530700, "total_steps": 761865, "loss": 1.9451, "lr": 2.1047536131105392e-07, "epoch": 10.448701541611703, "percentage": 69.66, "elapsed_time": "17:37:10", "remaining_time": "7:40:29", "throughput": 8519.07, "total_tokens": 540367728} {"current_steps": 530800, "total_steps": 761865, "loss": 2.0824, "lr": 2.1030728851980008e-07, "epoch": 10.450670394361206, "percentage": 69.67, "elapsed_time": "17:37:22", "remaining_time": "7:40:17", "throughput": 8519.08, "total_tokens": 540469616} {"current_steps": 530900, "total_steps": 761865, "loss": 1.9891, "lr": 2.1013926498834822e-07, "epoch": 10.452639247110708, "percentage": 69.68, "elapsed_time": "17:37:34", "remaining_time": "7:40:05", "throughput": 8519.09, "total_tokens": 540570664} {"current_steps": 531000, "total_steps": 761865, "loss": 1.9399, "lr": 2.0997129074526936e-07, "epoch": 10.454608099860211, "percentage": 69.7, "elapsed_time": "17:37:45", "remaining_time": "7:39:53", "throughput": 8519.1, "total_tokens": 540672496} {"current_steps": 531100, "total_steps": 761865, "loss": 1.9804, "lr": 2.0980336581912672e-07, "epoch": 10.456576952609714, "percentage": 69.71, "elapsed_time": "17:37:57", "remaining_time": "7:39:41", "throughput": 8519.12, "total_tokens": 540774072} {"current_steps": 531200, "total_steps": 761865, "loss": 1.9774, "lr": 2.0963549023847383e-07, "epoch": 10.458545805359217, "percentage": 69.72, "elapsed_time": "17:38:09", "remaining_time": "7:39:29", "throughput": 8519.13, "total_tokens": 540876472} {"current_steps": 531300, "total_steps": 761865, "loss": 2.0, "lr": 2.09467664031857e-07, "epoch": 10.46051465810872, "percentage": 69.74, "elapsed_time": "17:38:21", "remaining_time": "7:39:17", "throughput": 8519.15, "total_tokens": 540978000} {"current_steps": 531400, "total_steps": 761865, "loss": 1.968, "lr": 2.092998872278131e-07, "epoch": 10.462483510858222, "percentage": 69.75, "elapsed_time": "17:38:33", "remaining_time": "7:39:05", "throughput": 8519.17, "total_tokens": 541080400} {"current_steps": 531500, "total_steps": 761865, "loss": 1.9518, "lr": 2.091321598548718e-07, "epoch": 10.464452363607727, "percentage": 69.76, "elapsed_time": "17:38:45", "remaining_time": "7:38:53", "throughput": 8519.17, "total_tokens": 541181352} {"current_steps": 531600, "total_steps": 761865, "loss": 1.97, "lr": 2.0896448194155332e-07, "epoch": 10.46642121635723, "percentage": 69.78, "elapsed_time": "17:38:56", "remaining_time": "7:38:41", "throughput": 8519.19, "total_tokens": 541283752} {"current_steps": 531700, "total_steps": 761865, "loss": 1.9683, "lr": 2.0879685351637011e-07, "epoch": 10.468390069106732, "percentage": 69.79, "elapsed_time": "17:39:08", "remaining_time": "7:38:29", "throughput": 8519.2, "total_tokens": 541384760} {"current_steps": 531800, "total_steps": 761865, "loss": 1.9893, "lr": 2.0862927460782547e-07, "epoch": 10.470358921856235, "percentage": 69.8, "elapsed_time": "17:39:20", "remaining_time": "7:38:17", "throughput": 8519.22, "total_tokens": 541487160} {"current_steps": 531900, "total_steps": 761865, "loss": 1.9839, "lr": 2.0846174524441557e-07, "epoch": 10.472327774605738, "percentage": 69.82, "elapsed_time": "17:39:32", "remaining_time": "7:38:05", "throughput": 8519.23, "total_tokens": 541588088} {"current_steps": 532000, "total_steps": 761865, "loss": 1.9573, "lr": 2.082942654546267e-07, "epoch": 10.47429662735524, "percentage": 69.83, "elapsed_time": "17:39:44", "remaining_time": "7:37:53", "throughput": 8519.24, "total_tokens": 541690488} {"current_steps": 532100, "total_steps": 761865, "loss": 1.9708, "lr": 2.0812683526693765e-07, "epoch": 10.476265480104743, "percentage": 69.84, "elapsed_time": "17:39:56", "remaining_time": "7:37:41", "throughput": 8519.26, "total_tokens": 541792056} {"current_steps": 532200, "total_steps": 761865, "loss": 2.0323, "lr": 2.0795945470981853e-07, "epoch": 10.478234332854246, "percentage": 69.85, "elapsed_time": "17:40:08", "remaining_time": "7:37:29", "throughput": 8519.27, "total_tokens": 541893760} {"current_steps": 532300, "total_steps": 761865, "loss": 2.0381, "lr": 2.077921238117309e-07, "epoch": 10.480203185603749, "percentage": 69.87, "elapsed_time": "17:40:19", "remaining_time": "7:37:17", "throughput": 8519.28, "total_tokens": 541995800} {"current_steps": 532400, "total_steps": 761865, "loss": 1.9719, "lr": 2.0762484260112824e-07, "epoch": 10.482172038353252, "percentage": 69.88, "elapsed_time": "17:40:31", "remaining_time": "7:37:05", "throughput": 8519.3, "total_tokens": 542098200} {"current_steps": 532500, "total_steps": 761865, "loss": 2.0419, "lr": 2.0745761110645483e-07, "epoch": 10.484140891102754, "percentage": 69.89, "elapsed_time": "17:40:43", "remaining_time": "7:36:53", "throughput": 8519.32, "total_tokens": 542199584} {"current_steps": 532600, "total_steps": 761865, "loss": 2.027, "lr": 2.0729042935614733e-07, "epoch": 10.486109743852257, "percentage": 69.91, "elapsed_time": "17:40:55", "remaining_time": "7:36:41", "throughput": 8519.33, "total_tokens": 542301064} {"current_steps": 532700, "total_steps": 761865, "loss": 1.967, "lr": 2.0712329737863343e-07, "epoch": 10.48807859660176, "percentage": 69.92, "elapsed_time": "17:41:07", "remaining_time": "7:36:29", "throughput": 8519.35, "total_tokens": 542403464} {"current_steps": 532800, "total_steps": 761865, "loss": 1.9957, "lr": 2.0695621520233275e-07, "epoch": 10.490047449351263, "percentage": 69.93, "elapsed_time": "17:41:19", "remaining_time": "7:36:17", "throughput": 8519.36, "total_tokens": 542505864} {"current_steps": 532900, "total_steps": 761865, "loss": 2.0094, "lr": 2.0678918285565589e-07, "epoch": 10.492016302100765, "percentage": 69.95, "elapsed_time": "17:41:30", "remaining_time": "7:36:05", "throughput": 8519.37, "total_tokens": 542606008} {"current_steps": 533000, "total_steps": 761865, "loss": 1.998, "lr": 2.0662220036700545e-07, "epoch": 10.493985154850268, "percentage": 69.96, "elapsed_time": "17:41:42", "remaining_time": "7:35:53", "throughput": 8519.38, "total_tokens": 542707056} {"current_steps": 533100, "total_steps": 761865, "loss": 2.0218, "lr": 2.0645526776477535e-07, "epoch": 10.49595400759977, "percentage": 69.97, "elapsed_time": "17:41:54", "remaining_time": "7:35:41", "throughput": 8519.4, "total_tokens": 542808688} {"current_steps": 533200, "total_steps": 761865, "loss": 2.0525, "lr": 2.0628838507735107e-07, "epoch": 10.497922860349274, "percentage": 69.99, "elapsed_time": "17:42:06", "remaining_time": "7:35:29", "throughput": 8519.41, "total_tokens": 542910160} {"current_steps": 533300, "total_steps": 761865, "loss": 2.0243, "lr": 2.061215523331098e-07, "epoch": 10.499891713098778, "percentage": 70.0, "elapsed_time": "17:42:18", "remaining_time": "7:35:17", "throughput": 8519.41, "total_tokens": 543010928} {"current_steps": 533400, "total_steps": 761865, "loss": 2.0143, "lr": 2.0595476956041974e-07, "epoch": 10.50186056584828, "percentage": 70.01, "elapsed_time": "17:42:29", "remaining_time": "7:35:05", "throughput": 8519.43, "total_tokens": 543112216} {"current_steps": 533500, "total_steps": 761865, "loss": 1.985, "lr": 2.05788036787641e-07, "epoch": 10.503829418597784, "percentage": 70.03, "elapsed_time": "17:42:41", "remaining_time": "7:34:53", "throughput": 8519.44, "total_tokens": 543213808} {"current_steps": 533600, "total_steps": 761865, "loss": 1.9961, "lr": 2.056213540431251e-07, "epoch": 10.505798271347286, "percentage": 70.04, "elapsed_time": "17:42:53", "remaining_time": "7:34:41", "throughput": 8519.45, "total_tokens": 543315576} {"current_steps": 533700, "total_steps": 761865, "loss": 2.0058, "lr": 2.0545472135521523e-07, "epoch": 10.50776712409679, "percentage": 70.05, "elapsed_time": "17:43:05", "remaining_time": "7:34:29", "throughput": 8519.47, "total_tokens": 543417976} {"current_steps": 533800, "total_steps": 761865, "loss": 2.017, "lr": 2.052881387522455e-07, "epoch": 10.509735976846292, "percentage": 70.06, "elapsed_time": "17:43:17", "remaining_time": "7:34:17", "throughput": 8519.48, "total_tokens": 543519456} {"current_steps": 533900, "total_steps": 761865, "loss": 1.9796, "lr": 2.0512160626254205e-07, "epoch": 10.511704829595795, "percentage": 70.08, "elapsed_time": "17:43:29", "remaining_time": "7:34:05", "throughput": 8519.5, "total_tokens": 543621368} {"current_steps": 534000, "total_steps": 761865, "loss": 2.0095, "lr": 2.0495512391442238e-07, "epoch": 10.513673682345297, "percentage": 70.09, "elapsed_time": "17:43:40", "remaining_time": "7:33:53", "throughput": 8519.51, "total_tokens": 543723768} {"current_steps": 534100, "total_steps": 761865, "loss": 1.962, "lr": 2.0478869173619534e-07, "epoch": 10.5156425350948, "percentage": 70.1, "elapsed_time": "17:43:52", "remaining_time": "7:33:41", "throughput": 8519.53, "total_tokens": 543826168} {"current_steps": 534200, "total_steps": 761865, "loss": 1.9686, "lr": 2.046223097561615e-07, "epoch": 10.517611387844303, "percentage": 70.12, "elapsed_time": "17:44:04", "remaining_time": "7:33:29", "throughput": 8519.55, "total_tokens": 543928016} {"current_steps": 534300, "total_steps": 761865, "loss": 2.0071, "lr": 2.044559780026122e-07, "epoch": 10.519580240593806, "percentage": 70.13, "elapsed_time": "17:44:16", "remaining_time": "7:33:17", "throughput": 8519.56, "total_tokens": 544029240} {"current_steps": 534400, "total_steps": 761865, "loss": 1.9813, "lr": 2.042896965038315e-07, "epoch": 10.521549093343308, "percentage": 70.14, "elapsed_time": "17:44:28", "remaining_time": "7:33:05", "throughput": 8519.57, "total_tokens": 544130888} {"current_steps": 534500, "total_steps": 761865, "loss": 1.9375, "lr": 2.0412346528809353e-07, "epoch": 10.523517946092811, "percentage": 70.16, "elapsed_time": "17:44:40", "remaining_time": "7:32:53", "throughput": 8519.59, "total_tokens": 544233288} {"current_steps": 534600, "total_steps": 761865, "loss": 2.0245, "lr": 2.0395728438366482e-07, "epoch": 10.525486798842314, "percentage": 70.17, "elapsed_time": "17:44:51", "remaining_time": "7:32:41", "throughput": 8519.59, "total_tokens": 544332856} {"current_steps": 534700, "total_steps": 761865, "loss": 1.9959, "lr": 2.0379115381880295e-07, "epoch": 10.527455651591817, "percentage": 70.18, "elapsed_time": "17:45:03", "remaining_time": "7:32:29", "throughput": 8519.61, "total_tokens": 544434272} {"current_steps": 534800, "total_steps": 761865, "loss": 2.0373, "lr": 2.0362507362175718e-07, "epoch": 10.52942450434132, "percentage": 70.2, "elapsed_time": "17:45:15", "remaining_time": "7:32:17", "throughput": 8519.61, "total_tokens": 544533528} {"current_steps": 534900, "total_steps": 761865, "loss": 2.0041, "lr": 2.0345904382076772e-07, "epoch": 10.531393357090824, "percentage": 70.21, "elapsed_time": "17:45:27", "remaining_time": "7:32:05", "throughput": 8519.62, "total_tokens": 544635120} {"current_steps": 535000, "total_steps": 761865, "loss": 1.9818, "lr": 2.032930644440668e-07, "epoch": 10.533362209840327, "percentage": 70.22, "elapsed_time": "17:45:39", "remaining_time": "7:31:53", "throughput": 8519.64, "total_tokens": 544737520} {"current_steps": 535100, "total_steps": 761865, "loss": 1.9781, "lr": 2.0312713551987764e-07, "epoch": 10.53533106258983, "percentage": 70.24, "elapsed_time": "17:45:51", "remaining_time": "7:31:41", "throughput": 8519.57, "total_tokens": 544838688} {"current_steps": 535200, "total_steps": 761865, "loss": 2.001, "lr": 2.0296125707641515e-07, "epoch": 10.537299915339332, "percentage": 70.25, "elapsed_time": "17:46:03", "remaining_time": "7:31:29", "throughput": 8519.58, "total_tokens": 544941088} {"current_steps": 535300, "total_steps": 761865, "loss": 1.9559, "lr": 2.0279542914188575e-07, "epoch": 10.539268768088835, "percentage": 70.26, "elapsed_time": "17:46:15", "remaining_time": "7:31:17", "throughput": 8519.6, "total_tokens": 545042840} {"current_steps": 535400, "total_steps": 761865, "loss": 2.0156, "lr": 2.026296517444867e-07, "epoch": 10.541237620838338, "percentage": 70.27, "elapsed_time": "17:46:27", "remaining_time": "7:31:05", "throughput": 8519.62, "total_tokens": 545144968} {"current_steps": 535500, "total_steps": 761865, "loss": 1.9822, "lr": 2.0246392491240726e-07, "epoch": 10.54320647358784, "percentage": 70.29, "elapsed_time": "17:46:38", "remaining_time": "7:30:53", "throughput": 8519.63, "total_tokens": 545246592} {"current_steps": 535600, "total_steps": 761865, "loss": 2.0302, "lr": 2.0229824867382784e-07, "epoch": 10.545175326337343, "percentage": 70.3, "elapsed_time": "17:46:50", "remaining_time": "7:30:41", "throughput": 8519.65, "total_tokens": 545348992} {"current_steps": 535700, "total_steps": 761865, "loss": 1.9629, "lr": 2.0213262305692046e-07, "epoch": 10.547144179086846, "percentage": 70.31, "elapsed_time": "17:47:02", "remaining_time": "7:30:29", "throughput": 8519.66, "total_tokens": 545450464} {"current_steps": 535800, "total_steps": 761865, "loss": 1.9757, "lr": 2.0196704808984805e-07, "epoch": 10.549113031836349, "percentage": 70.33, "elapsed_time": "17:47:14", "remaining_time": "7:30:17", "throughput": 8519.68, "total_tokens": 545552864} {"current_steps": 535900, "total_steps": 761865, "loss": 2.0186, "lr": 2.0180152380076532e-07, "epoch": 10.551081884585852, "percentage": 70.34, "elapsed_time": "17:47:26", "remaining_time": "7:30:05", "throughput": 8519.69, "total_tokens": 545654192} {"current_steps": 536000, "total_steps": 761865, "loss": 2.0142, "lr": 2.0163605021781843e-07, "epoch": 10.553050737335354, "percentage": 70.35, "elapsed_time": "17:47:38", "remaining_time": "7:29:53", "throughput": 8519.7, "total_tokens": 545755120} {"current_steps": 536100, "total_steps": 761865, "loss": 1.9556, "lr": 2.0147062736914468e-07, "epoch": 10.555019590084857, "percentage": 70.37, "elapsed_time": "17:47:49", "remaining_time": "7:29:41", "throughput": 8519.72, "total_tokens": 545857024} {"current_steps": 536200, "total_steps": 761865, "loss": 2.0136, "lr": 2.0130525528287297e-07, "epoch": 10.55698844283436, "percentage": 70.38, "elapsed_time": "17:48:01", "remaining_time": "7:29:29", "throughput": 8519.74, "total_tokens": 545959424} {"current_steps": 536300, "total_steps": 761865, "loss": 1.9556, "lr": 2.0113993398712291e-07, "epoch": 10.558957295583863, "percentage": 70.39, "elapsed_time": "17:48:13", "remaining_time": "7:29:17", "throughput": 8519.76, "total_tokens": 546061824} {"current_steps": 536400, "total_steps": 761865, "loss": 1.9847, "lr": 2.0097466351000675e-07, "epoch": 10.560926148333365, "percentage": 70.41, "elapsed_time": "17:48:25", "remaining_time": "7:29:05", "throughput": 8519.77, "total_tokens": 546163608} {"current_steps": 536500, "total_steps": 761865, "loss": 2.0082, "lr": 2.0080944387962683e-07, "epoch": 10.562895001082868, "percentage": 70.42, "elapsed_time": "17:48:37", "remaining_time": "7:28:53", "throughput": 8519.78, "total_tokens": 546265304} {"current_steps": 536600, "total_steps": 761865, "loss": 1.9857, "lr": 2.0064427512407762e-07, "epoch": 10.564863853832373, "percentage": 70.43, "elapsed_time": "17:48:49", "remaining_time": "7:28:41", "throughput": 8519.79, "total_tokens": 546366488} {"current_steps": 536700, "total_steps": 761865, "loss": 1.9564, "lr": 2.0047915727144422e-07, "epoch": 10.566832706581875, "percentage": 70.45, "elapsed_time": "17:49:00", "remaining_time": "7:28:29", "throughput": 8519.8, "total_tokens": 546466864} {"current_steps": 536800, "total_steps": 761865, "loss": 2.0156, "lr": 2.0031409034980418e-07, "epoch": 10.568801559331378, "percentage": 70.46, "elapsed_time": "17:49:12", "remaining_time": "7:28:17", "throughput": 8519.82, "total_tokens": 546569264} {"current_steps": 536900, "total_steps": 761865, "loss": 2.0054, "lr": 2.0014907438722522e-07, "epoch": 10.570770412080881, "percentage": 70.47, "elapsed_time": "17:49:24", "remaining_time": "7:28:05", "throughput": 8519.84, "total_tokens": 546671072} {"current_steps": 537000, "total_steps": 761865, "loss": 2.0417, "lr": 1.999841094117673e-07, "epoch": 10.572739264830384, "percentage": 70.48, "elapsed_time": "17:49:36", "remaining_time": "7:27:53", "throughput": 8519.85, "total_tokens": 546773472} {"current_steps": 537100, "total_steps": 761865, "loss": 1.9848, "lr": 1.9981919545148078e-07, "epoch": 10.574708117579886, "percentage": 70.5, "elapsed_time": "17:49:48", "remaining_time": "7:27:41", "throughput": 8519.87, "total_tokens": 546875872} {"current_steps": 537200, "total_steps": 761865, "loss": 1.9481, "lr": 1.996543325344084e-07, "epoch": 10.57667697032939, "percentage": 70.51, "elapsed_time": "17:50:00", "remaining_time": "7:27:29", "throughput": 8519.89, "total_tokens": 546978272} {"current_steps": 537300, "total_steps": 761865, "loss": 2.0419, "lr": 1.994895206885837e-07, "epoch": 10.578645823078892, "percentage": 70.52, "elapsed_time": "17:50:11", "remaining_time": "7:27:17", "throughput": 8519.91, "total_tokens": 547080048} {"current_steps": 537400, "total_steps": 761865, "loss": 2.0005, "lr": 1.9932475994203123e-07, "epoch": 10.580614675828395, "percentage": 70.54, "elapsed_time": "17:50:23", "remaining_time": "7:27:05", "throughput": 8519.91, "total_tokens": 547180208} {"current_steps": 537500, "total_steps": 761865, "loss": 2.0015, "lr": 1.991600503227673e-07, "epoch": 10.582583528577898, "percentage": 70.55, "elapsed_time": "17:50:35", "remaining_time": "7:26:53", "throughput": 8519.92, "total_tokens": 547281936} {"current_steps": 537600, "total_steps": 761865, "loss": 2.0246, "lr": 1.9899539185879943e-07, "epoch": 10.5845523813274, "percentage": 70.56, "elapsed_time": "17:50:47", "remaining_time": "7:26:41", "throughput": 8519.94, "total_tokens": 547383752} {"current_steps": 537700, "total_steps": 761865, "loss": 2.0164, "lr": 1.988307845781265e-07, "epoch": 10.586521234076903, "percentage": 70.58, "elapsed_time": "17:50:59", "remaining_time": "7:26:29", "throughput": 8519.95, "total_tokens": 547484800} {"current_steps": 537800, "total_steps": 761865, "loss": 2.0221, "lr": 1.9866622850873838e-07, "epoch": 10.588490086826406, "percentage": 70.59, "elapsed_time": "17:51:10", "remaining_time": "7:26:17", "throughput": 8519.96, "total_tokens": 547585760} {"current_steps": 537900, "total_steps": 761865, "loss": 1.9704, "lr": 1.985017236786165e-07, "epoch": 10.590458939575909, "percentage": 70.6, "elapsed_time": "17:51:22", "remaining_time": "7:26:05", "throughput": 8519.98, "total_tokens": 547687624} {"current_steps": 538000, "total_steps": 761865, "loss": 2.0119, "lr": 1.983372701157336e-07, "epoch": 10.592427792325411, "percentage": 70.62, "elapsed_time": "17:51:34", "remaining_time": "7:25:53", "throughput": 8519.99, "total_tokens": 547788776} {"current_steps": 538100, "total_steps": 761865, "loss": 1.9796, "lr": 1.981728678480537e-07, "epoch": 10.594396645074914, "percentage": 70.63, "elapsed_time": "17:51:46", "remaining_time": "7:25:41", "throughput": 8520.0, "total_tokens": 547889920} {"current_steps": 538200, "total_steps": 761865, "loss": 1.9646, "lr": 1.9800851690353171e-07, "epoch": 10.596365497824419, "percentage": 70.64, "elapsed_time": "17:51:58", "remaining_time": "7:25:29", "throughput": 8520.02, "total_tokens": 547992320} {"current_steps": 538300, "total_steps": 761865, "loss": 2.0002, "lr": 1.9784421731011435e-07, "epoch": 10.598334350573921, "percentage": 70.66, "elapsed_time": "17:52:10", "remaining_time": "7:25:17", "throughput": 8520.03, "total_tokens": 548094264} {"current_steps": 538400, "total_steps": 761865, "loss": 1.9559, "lr": 1.9767996909573931e-07, "epoch": 10.600303203323424, "percentage": 70.67, "elapsed_time": "17:52:21", "remaining_time": "7:25:05", "throughput": 8520.05, "total_tokens": 548196064} {"current_steps": 538500, "total_steps": 761865, "loss": 2.0164, "lr": 1.9751577228833565e-07, "epoch": 10.602272056072927, "percentage": 70.68, "elapsed_time": "17:52:33", "remaining_time": "7:24:53", "throughput": 8520.06, "total_tokens": 548297648} {"current_steps": 538600, "total_steps": 761865, "loss": 2.036, "lr": 1.973516269158238e-07, "epoch": 10.60424090882243, "percentage": 70.69, "elapsed_time": "17:52:45", "remaining_time": "7:24:41", "throughput": 8520.07, "total_tokens": 548399568} {"current_steps": 538700, "total_steps": 761865, "loss": 1.9437, "lr": 1.9718753300611495e-07, "epoch": 10.606209761571932, "percentage": 70.71, "elapsed_time": "17:52:57", "remaining_time": "7:24:29", "throughput": 8520.09, "total_tokens": 548501968} {"current_steps": 538800, "total_steps": 761865, "loss": 1.9995, "lr": 1.9702349058711216e-07, "epoch": 10.608178614321435, "percentage": 70.72, "elapsed_time": "17:53:09", "remaining_time": "7:24:17", "throughput": 8520.11, "total_tokens": 548603816} {"current_steps": 538900, "total_steps": 761865, "loss": 1.9478, "lr": 1.968594996867093e-07, "epoch": 10.610147467070938, "percentage": 70.73, "elapsed_time": "17:53:21", "remaining_time": "7:24:05", "throughput": 8520.12, "total_tokens": 548705456} {"current_steps": 539000, "total_steps": 761865, "loss": 2.0025, "lr": 1.9669556033279188e-07, "epoch": 10.61211631982044, "percentage": 70.75, "elapsed_time": "17:53:33", "remaining_time": "7:23:53", "throughput": 8520.14, "total_tokens": 548807856} {"current_steps": 539100, "total_steps": 761865, "loss": 2.0287, "lr": 1.965316725532361e-07, "epoch": 10.614085172569943, "percentage": 70.76, "elapsed_time": "17:53:44", "remaining_time": "7:23:41", "throughput": 8520.16, "total_tokens": 548910256} {"current_steps": 539200, "total_steps": 761865, "loss": 1.9812, "lr": 1.9636783637590964e-07, "epoch": 10.616054025319446, "percentage": 70.77, "elapsed_time": "17:53:56", "remaining_time": "7:23:29", "throughput": 8520.17, "total_tokens": 549011888} {"current_steps": 539300, "total_steps": 761865, "loss": 1.9846, "lr": 1.96204051828672e-07, "epoch": 10.618022878068949, "percentage": 70.79, "elapsed_time": "17:54:08", "remaining_time": "7:23:17", "throughput": 8520.18, "total_tokens": 549113040} {"current_steps": 539400, "total_steps": 761865, "loss": 1.9836, "lr": 1.9604031893937284e-07, "epoch": 10.619991730818452, "percentage": 70.8, "elapsed_time": "17:54:20", "remaining_time": "7:23:05", "throughput": 8520.2, "total_tokens": 549215440} {"current_steps": 539500, "total_steps": 761865, "loss": 1.9707, "lr": 1.9587663773585395e-07, "epoch": 10.621960583567954, "percentage": 70.81, "elapsed_time": "17:54:32", "remaining_time": "7:22:53", "throughput": 8520.21, "total_tokens": 549315832} {"current_steps": 539600, "total_steps": 761865, "loss": 1.9586, "lr": 1.9571300824594727e-07, "epoch": 10.623929436317457, "percentage": 70.83, "elapsed_time": "17:54:43", "remaining_time": "7:22:41", "throughput": 8520.23, "total_tokens": 549418232} {"current_steps": 539700, "total_steps": 761865, "loss": 2.0373, "lr": 1.955494304974775e-07, "epoch": 10.62589828906696, "percentage": 70.84, "elapsed_time": "17:54:55", "remaining_time": "7:22:29", "throughput": 8520.24, "total_tokens": 549520480} {"current_steps": 539800, "total_steps": 761865, "loss": 2.0142, "lr": 1.9538590451825898e-07, "epoch": 10.627867141816463, "percentage": 70.85, "elapsed_time": "17:55:07", "remaining_time": "7:22:17", "throughput": 8520.25, "total_tokens": 549622152} {"current_steps": 539900, "total_steps": 761865, "loss": 1.9897, "lr": 1.952224303360984e-07, "epoch": 10.629835994565966, "percentage": 70.87, "elapsed_time": "17:55:19", "remaining_time": "7:22:05", "throughput": 8520.27, "total_tokens": 549724552} {"current_steps": 540000, "total_steps": 761865, "loss": 1.998, "lr": 1.9505900797879255e-07, "epoch": 10.63180484731547, "percentage": 70.88, "elapsed_time": "17:55:31", "remaining_time": "7:21:53", "throughput": 8520.28, "total_tokens": 549825912} {"current_steps": 540100, "total_steps": 761865, "loss": 1.9597, "lr": 1.9489563747413075e-07, "epoch": 10.633773700064973, "percentage": 70.89, "elapsed_time": "17:55:43", "remaining_time": "7:21:41", "throughput": 8520.22, "total_tokens": 549928312} {"current_steps": 540200, "total_steps": 761865, "loss": 2.0268, "lr": 1.9473231884989228e-07, "epoch": 10.635742552814476, "percentage": 70.9, "elapsed_time": "17:55:55", "remaining_time": "7:21:29", "throughput": 8520.24, "total_tokens": 550030712} {"current_steps": 540300, "total_steps": 761865, "loss": 1.9472, "lr": 1.9456905213384818e-07, "epoch": 10.637711405563978, "percentage": 70.92, "elapsed_time": "17:56:07", "remaining_time": "7:21:17", "throughput": 8520.26, "total_tokens": 550133112} {"current_steps": 540400, "total_steps": 761865, "loss": 1.9933, "lr": 1.944058373537607e-07, "epoch": 10.639680258313481, "percentage": 70.93, "elapsed_time": "17:56:19", "remaining_time": "7:21:05", "throughput": 8520.27, "total_tokens": 550233992} {"current_steps": 540500, "total_steps": 761865, "loss": 2.0051, "lr": 1.9424267453738307e-07, "epoch": 10.641649111062984, "percentage": 70.94, "elapsed_time": "17:56:31", "remaining_time": "7:20:53", "throughput": 8520.29, "total_tokens": 550336392} {"current_steps": 540600, "total_steps": 761865, "loss": 1.9517, "lr": 1.9407956371245993e-07, "epoch": 10.643617963812487, "percentage": 70.96, "elapsed_time": "17:56:43", "remaining_time": "7:20:41", "throughput": 8520.3, "total_tokens": 550438792} {"current_steps": 540700, "total_steps": 761865, "loss": 1.9642, "lr": 1.939165049067265e-07, "epoch": 10.64558681656199, "percentage": 70.97, "elapsed_time": "17:56:55", "remaining_time": "7:20:29", "throughput": 8520.32, "total_tokens": 550540632} {"current_steps": 540800, "total_steps": 761865, "loss": 1.9798, "lr": 1.9375349814790985e-07, "epoch": 10.647555669311492, "percentage": 70.98, "elapsed_time": "17:57:06", "remaining_time": "7:20:17", "throughput": 8520.34, "total_tokens": 550643032} {"current_steps": 540900, "total_steps": 761865, "loss": 2.0034, "lr": 1.9359054346372784e-07, "epoch": 10.649524522060995, "percentage": 71.0, "elapsed_time": "17:57:18", "remaining_time": "7:20:05", "throughput": 8520.35, "total_tokens": 550744768} {"current_steps": 541000, "total_steps": 761865, "loss": 1.9512, "lr": 1.9342764088188967e-07, "epoch": 10.651493374810498, "percentage": 71.01, "elapsed_time": "17:57:30", "remaining_time": "7:19:53", "throughput": 8520.37, "total_tokens": 550847168} {"current_steps": 541100, "total_steps": 761865, "loss": 1.9809, "lr": 1.9326479043009526e-07, "epoch": 10.65346222756, "percentage": 71.02, "elapsed_time": "17:57:42", "remaining_time": "7:19:41", "throughput": 8520.38, "total_tokens": 550949000} {"current_steps": 541200, "total_steps": 761865, "loss": 1.9153, "lr": 1.9310199213603611e-07, "epoch": 10.655431080309503, "percentage": 71.04, "elapsed_time": "17:57:54", "remaining_time": "7:19:29", "throughput": 8520.4, "total_tokens": 551051400} {"current_steps": 541300, "total_steps": 761865, "loss": 1.9686, "lr": 1.929392460273947e-07, "epoch": 10.657399933059006, "percentage": 71.05, "elapsed_time": "17:58:06", "remaining_time": "7:19:17", "throughput": 8520.41, "total_tokens": 551152200} {"current_steps": 541400, "total_steps": 761865, "loss": 1.9648, "lr": 1.9277655213184462e-07, "epoch": 10.659368785808509, "percentage": 71.06, "elapsed_time": "17:58:18", "remaining_time": "7:19:05", "throughput": 8520.43, "total_tokens": 551254600} {"current_steps": 541500, "total_steps": 761865, "loss": 1.9509, "lr": 1.9261391047705083e-07, "epoch": 10.661337638558011, "percentage": 71.08, "elapsed_time": "17:58:29", "remaining_time": "7:18:53", "throughput": 8520.44, "total_tokens": 551356448} {"current_steps": 541600, "total_steps": 761865, "loss": 1.9598, "lr": 1.9245132109066874e-07, "epoch": 10.663306491307516, "percentage": 71.09, "elapsed_time": "17:58:41", "remaining_time": "7:18:41", "throughput": 8520.46, "total_tokens": 551458264} {"current_steps": 541700, "total_steps": 761865, "loss": 1.9813, "lr": 1.9228878400034548e-07, "epoch": 10.665275344057019, "percentage": 71.1, "elapsed_time": "17:58:53", "remaining_time": "7:18:29", "throughput": 8520.47, "total_tokens": 551560664} {"current_steps": 541800, "total_steps": 761865, "loss": 1.9625, "lr": 1.921262992337192e-07, "epoch": 10.667244196806521, "percentage": 71.11, "elapsed_time": "17:59:05", "remaining_time": "7:18:17", "throughput": 8520.49, "total_tokens": 551662648} {"current_steps": 541900, "total_steps": 761865, "loss": 1.9948, "lr": 1.9196386681841914e-07, "epoch": 10.669213049556024, "percentage": 71.13, "elapsed_time": "17:59:17", "remaining_time": "7:18:05", "throughput": 8520.5, "total_tokens": 551763808} {"current_steps": 542000, "total_steps": 761865, "loss": 1.975, "lr": 1.918014867820653e-07, "epoch": 10.671181902305527, "percentage": 71.14, "elapsed_time": "17:59:29", "remaining_time": "7:17:53", "throughput": 8520.52, "total_tokens": 551866208} {"current_steps": 542100, "total_steps": 761865, "loss": 1.9942, "lr": 1.9163915915226914e-07, "epoch": 10.67315075505503, "percentage": 71.15, "elapsed_time": "17:59:40", "remaining_time": "7:17:41", "throughput": 8520.53, "total_tokens": 551968296} {"current_steps": 542200, "total_steps": 761865, "loss": 1.9886, "lr": 1.9147688395663315e-07, "epoch": 10.675119607804533, "percentage": 71.17, "elapsed_time": "17:59:52", "remaining_time": "7:17:29", "throughput": 8520.54, "total_tokens": 552069288} {"current_steps": 542300, "total_steps": 761865, "loss": 1.9473, "lr": 1.9131466122275085e-07, "epoch": 10.677088460554035, "percentage": 71.18, "elapsed_time": "18:00:04", "remaining_time": "7:17:17", "throughput": 8520.56, "total_tokens": 552171088} {"current_steps": 542400, "total_steps": 761865, "loss": 1.9987, "lr": 1.9115249097820695e-07, "epoch": 10.679057313303538, "percentage": 71.19, "elapsed_time": "18:00:16", "remaining_time": "7:17:05", "throughput": 8520.56, "total_tokens": 552272080} {"current_steps": 542500, "total_steps": 761865, "loss": 1.9792, "lr": 1.9099037325057672e-07, "epoch": 10.68102616605304, "percentage": 71.21, "elapsed_time": "18:00:28", "remaining_time": "7:16:53", "throughput": 8520.58, "total_tokens": 552373664} {"current_steps": 542600, "total_steps": 761865, "loss": 2.0089, "lr": 1.9082830806742755e-07, "epoch": 10.682995018802544, "percentage": 71.22, "elapsed_time": "18:00:40", "remaining_time": "7:16:41", "throughput": 8520.6, "total_tokens": 552476064} {"current_steps": 542700, "total_steps": 761865, "loss": 1.971, "lr": 1.9066629545631675e-07, "epoch": 10.684963871552046, "percentage": 71.23, "elapsed_time": "18:00:51", "remaining_time": "7:16:29", "throughput": 8520.61, "total_tokens": 552577944} {"current_steps": 542800, "total_steps": 761865, "loss": 1.9845, "lr": 1.9050433544479338e-07, "epoch": 10.686932724301549, "percentage": 71.25, "elapsed_time": "18:01:03", "remaining_time": "7:16:17", "throughput": 8520.63, "total_tokens": 552680344} {"current_steps": 542900, "total_steps": 761865, "loss": 1.9252, "lr": 1.903424280603973e-07, "epoch": 10.688901577051052, "percentage": 71.26, "elapsed_time": "18:01:15", "remaining_time": "7:16:05", "throughput": 8520.64, "total_tokens": 552782264} {"current_steps": 543000, "total_steps": 761865, "loss": 2.0062, "lr": 1.9018057333065979e-07, "epoch": 10.690870429800555, "percentage": 71.27, "elapsed_time": "18:01:27", "remaining_time": "7:15:53", "throughput": 8520.65, "total_tokens": 552883224} {"current_steps": 543100, "total_steps": 761865, "loss": 1.9744, "lr": 1.9001877128310246e-07, "epoch": 10.692839282550057, "percentage": 71.29, "elapsed_time": "18:01:39", "remaining_time": "7:15:41", "throughput": 8520.66, "total_tokens": 552984800} {"current_steps": 543200, "total_steps": 761865, "loss": 1.9985, "lr": 1.8985702194523856e-07, "epoch": 10.69480813529956, "percentage": 71.3, "elapsed_time": "18:01:51", "remaining_time": "7:15:29", "throughput": 8520.68, "total_tokens": 553087200} {"current_steps": 543300, "total_steps": 761865, "loss": 2.0328, "lr": 1.8969532534457223e-07, "epoch": 10.696776988049065, "percentage": 71.31, "elapsed_time": "18:02:02", "remaining_time": "7:15:17", "throughput": 8520.69, "total_tokens": 553188536} {"current_steps": 543400, "total_steps": 761865, "loss": 1.9933, "lr": 1.8953368150859854e-07, "epoch": 10.698745840798567, "percentage": 71.32, "elapsed_time": "18:02:14", "remaining_time": "7:15:05", "throughput": 8520.7, "total_tokens": 553289712} {"current_steps": 543500, "total_steps": 761865, "loss": 1.9887, "lr": 1.8937209046480395e-07, "epoch": 10.70071469354807, "percentage": 71.34, "elapsed_time": "18:02:26", "remaining_time": "7:14:53", "throughput": 8520.72, "total_tokens": 553391664} {"current_steps": 543600, "total_steps": 761865, "loss": 1.9374, "lr": 1.8921055224066522e-07, "epoch": 10.702683546297573, "percentage": 71.35, "elapsed_time": "18:02:38", "remaining_time": "7:14:41", "throughput": 8520.74, "total_tokens": 553494064} {"current_steps": 543700, "total_steps": 761865, "loss": 1.9607, "lr": 1.890490668636508e-07, "epoch": 10.704652399047076, "percentage": 71.36, "elapsed_time": "18:02:50", "remaining_time": "7:14:30", "throughput": 8520.75, "total_tokens": 553596464} {"current_steps": 543800, "total_steps": 761865, "loss": 1.9777, "lr": 1.8888763436121986e-07, "epoch": 10.706621251796578, "percentage": 71.38, "elapsed_time": "18:03:02", "remaining_time": "7:14:18", "throughput": 8520.76, "total_tokens": 553697952} {"current_steps": 543900, "total_steps": 761865, "loss": 1.9756, "lr": 1.8872625476082277e-07, "epoch": 10.708590104546081, "percentage": 71.39, "elapsed_time": "18:03:14", "remaining_time": "7:14:06", "throughput": 8520.78, "total_tokens": 553800352} {"current_steps": 544000, "total_steps": 761865, "loss": 1.9781, "lr": 1.8856492808990055e-07, "epoch": 10.710558957295584, "percentage": 71.4, "elapsed_time": "18:03:25", "remaining_time": "7:13:54", "throughput": 8520.79, "total_tokens": 553901904} {"current_steps": 544100, "total_steps": 761865, "loss": 2.0011, "lr": 1.8840365437588552e-07, "epoch": 10.712527810045087, "percentage": 71.42, "elapsed_time": "18:03:37", "remaining_time": "7:13:42", "throughput": 8520.81, "total_tokens": 554004304} {"current_steps": 544200, "total_steps": 761865, "loss": 1.9838, "lr": 1.8824243364620091e-07, "epoch": 10.71449666279459, "percentage": 71.43, "elapsed_time": "18:03:49", "remaining_time": "7:13:30", "throughput": 8520.83, "total_tokens": 554106208} {"current_steps": 544300, "total_steps": 761865, "loss": 1.985, "lr": 1.88081265928261e-07, "epoch": 10.716465515544092, "percentage": 71.44, "elapsed_time": "18:04:01", "remaining_time": "7:13:18", "throughput": 8520.85, "total_tokens": 554208608} {"current_steps": 544400, "total_steps": 761865, "loss": 1.9327, "lr": 1.8792015124947118e-07, "epoch": 10.718434368293595, "percentage": 71.46, "elapsed_time": "18:04:13", "remaining_time": "7:13:06", "throughput": 8520.86, "total_tokens": 554311008} {"current_steps": 544500, "total_steps": 761865, "loss": 1.9693, "lr": 1.8775908963722703e-07, "epoch": 10.720403221043098, "percentage": 71.47, "elapsed_time": "18:04:25", "remaining_time": "7:12:54", "throughput": 8520.88, "total_tokens": 554412944} {"current_steps": 544600, "total_steps": 761865, "loss": 1.9832, "lr": 1.875980811189165e-07, "epoch": 10.7223720737926, "percentage": 71.48, "elapsed_time": "18:04:37", "remaining_time": "7:12:42", "throughput": 8520.9, "total_tokens": 554515344} {"current_steps": 544700, "total_steps": 761865, "loss": 1.924, "lr": 1.8743712572191722e-07, "epoch": 10.724340926542103, "percentage": 71.5, "elapsed_time": "18:04:48", "remaining_time": "7:12:30", "throughput": 8520.91, "total_tokens": 554617744} {"current_steps": 544800, "total_steps": 761865, "loss": 1.9734, "lr": 1.8727622347359857e-07, "epoch": 10.726309779291606, "percentage": 71.51, "elapsed_time": "18:05:00", "remaining_time": "7:12:18", "throughput": 8520.92, "total_tokens": 554718976} {"current_steps": 544900, "total_steps": 761865, "loss": 1.9793, "lr": 1.8711537440132013e-07, "epoch": 10.72827863204111, "percentage": 71.52, "elapsed_time": "18:05:12", "remaining_time": "7:12:06", "throughput": 8520.94, "total_tokens": 554821376} {"current_steps": 545000, "total_steps": 761865, "loss": 1.9605, "lr": 1.8695457853243363e-07, "epoch": 10.730247484790613, "percentage": 71.53, "elapsed_time": "18:05:24", "remaining_time": "7:11:54", "throughput": 8520.96, "total_tokens": 554923200} {"current_steps": 545100, "total_steps": 761865, "loss": 1.9705, "lr": 1.8679383589428056e-07, "epoch": 10.732216337540116, "percentage": 71.55, "elapsed_time": "18:05:37", "remaining_time": "7:11:42", "throughput": 8520.9, "total_tokens": 555025600} {"current_steps": 545200, "total_steps": 761865, "loss": 2.0378, "lr": 1.8663314651419416e-07, "epoch": 10.734185190289619, "percentage": 71.56, "elapsed_time": "18:05:48", "remaining_time": "7:11:30", "throughput": 8520.91, "total_tokens": 555127408} {"current_steps": 545300, "total_steps": 761865, "loss": 1.996, "lr": 1.8647251041949775e-07, "epoch": 10.736154043039122, "percentage": 71.57, "elapsed_time": "18:06:00", "remaining_time": "7:11:18", "throughput": 8520.92, "total_tokens": 555228912} {"current_steps": 545400, "total_steps": 761865, "loss": 1.9941, "lr": 1.8631192763750676e-07, "epoch": 10.738122895788624, "percentage": 71.59, "elapsed_time": "18:06:12", "remaining_time": "7:11:06", "throughput": 8520.94, "total_tokens": 555331312} {"current_steps": 545500, "total_steps": 761865, "loss": 1.9384, "lr": 1.8615139819552683e-07, "epoch": 10.740091748538127, "percentage": 71.6, "elapsed_time": "18:06:24", "remaining_time": "7:10:54", "throughput": 8520.95, "total_tokens": 555432840} {"current_steps": 545600, "total_steps": 761865, "loss": 1.9991, "lr": 1.8599092212085437e-07, "epoch": 10.74206060128763, "percentage": 71.61, "elapsed_time": "18:06:36", "remaining_time": "7:10:42", "throughput": 8520.97, "total_tokens": 555535240} {"current_steps": 545700, "total_steps": 761865, "loss": 1.996, "lr": 1.858304994407771e-07, "epoch": 10.744029454037133, "percentage": 71.63, "elapsed_time": "18:06:48", "remaining_time": "7:10:30", "throughput": 8520.98, "total_tokens": 555636504} {"current_steps": 545800, "total_steps": 761865, "loss": 2.0408, "lr": 1.856701301825736e-07, "epoch": 10.745998306786635, "percentage": 71.64, "elapsed_time": "18:06:59", "remaining_time": "7:10:18", "throughput": 8520.99, "total_tokens": 555738904} {"current_steps": 545900, "total_steps": 761865, "loss": 1.9639, "lr": 1.8550981437351343e-07, "epoch": 10.747967159536138, "percentage": 71.65, "elapsed_time": "18:07:11", "remaining_time": "7:10:06", "throughput": 8521.01, "total_tokens": 555840704} {"current_steps": 546000, "total_steps": 761865, "loss": 1.9826, "lr": 1.8534955204085668e-07, "epoch": 10.74993601228564, "percentage": 71.67, "elapsed_time": "18:07:23", "remaining_time": "7:09:54", "throughput": 8521.02, "total_tokens": 555942048} {"current_steps": 546100, "total_steps": 761865, "loss": 1.9606, "lr": 1.8518934321185464e-07, "epoch": 10.751904865035144, "percentage": 71.68, "elapsed_time": "18:07:35", "remaining_time": "7:09:42", "throughput": 8521.03, "total_tokens": 556043680} {"current_steps": 546200, "total_steps": 761865, "loss": 1.9645, "lr": 1.850291879137496e-07, "epoch": 10.753873717784646, "percentage": 71.69, "elapsed_time": "18:07:47", "remaining_time": "7:09:30", "throughput": 8521.05, "total_tokens": 556146080} {"current_steps": 546300, "total_steps": 761865, "loss": 1.9802, "lr": 1.8486908617377456e-07, "epoch": 10.75584257053415, "percentage": 71.71, "elapsed_time": "18:07:59", "remaining_time": "7:09:18", "throughput": 8521.07, "total_tokens": 556247888} {"current_steps": 546400, "total_steps": 761865, "loss": 1.9566, "lr": 1.8470903801915366e-07, "epoch": 10.757811423283652, "percentage": 71.72, "elapsed_time": "18:08:10", "remaining_time": "7:09:06", "throughput": 8521.08, "total_tokens": 556349440} {"current_steps": 546500, "total_steps": 761865, "loss": 1.9755, "lr": 1.8454904347710138e-07, "epoch": 10.759780276033155, "percentage": 71.73, "elapsed_time": "18:08:22", "remaining_time": "7:08:54", "throughput": 8521.1, "total_tokens": 556451840} {"current_steps": 546600, "total_steps": 761865, "loss": 1.9436, "lr": 1.843891025748236e-07, "epoch": 10.761749128782657, "percentage": 71.74, "elapsed_time": "18:08:34", "remaining_time": "7:08:42", "throughput": 8521.12, "total_tokens": 556554240} {"current_steps": 546700, "total_steps": 761865, "loss": 2.0207, "lr": 1.8422921533951697e-07, "epoch": 10.763717981532162, "percentage": 71.76, "elapsed_time": "18:08:46", "remaining_time": "7:08:30", "throughput": 8521.12, "total_tokens": 556655296} {"current_steps": 546800, "total_steps": 761865, "loss": 1.992, "lr": 1.8406938179836912e-07, "epoch": 10.765686834281665, "percentage": 71.77, "elapsed_time": "18:08:58", "remaining_time": "7:08:18", "throughput": 8521.14, "total_tokens": 556757696} {"current_steps": 546900, "total_steps": 761865, "loss": 1.9803, "lr": 1.83909601978558e-07, "epoch": 10.767655687031167, "percentage": 71.78, "elapsed_time": "18:09:10", "remaining_time": "7:08:06", "throughput": 8521.15, "total_tokens": 556859232} {"current_steps": 547000, "total_steps": 761865, "loss": 1.9494, "lr": 1.8374987590725306e-07, "epoch": 10.76962453978067, "percentage": 71.8, "elapsed_time": "18:09:22", "remaining_time": "7:07:54", "throughput": 8521.17, "total_tokens": 556961136} {"current_steps": 547100, "total_steps": 761865, "loss": 1.9882, "lr": 1.8359020361161437e-07, "epoch": 10.771593392530173, "percentage": 71.81, "elapsed_time": "18:09:33", "remaining_time": "7:07:42", "throughput": 8521.19, "total_tokens": 557063536} {"current_steps": 547200, "total_steps": 761865, "loss": 2.014, "lr": 1.8343058511879296e-07, "epoch": 10.773562245279676, "percentage": 71.82, "elapsed_time": "18:09:45", "remaining_time": "7:07:30", "throughput": 8521.2, "total_tokens": 557164472} {"current_steps": 547300, "total_steps": 761865, "loss": 1.9844, "lr": 1.832710204559303e-07, "epoch": 10.775531098029179, "percentage": 71.84, "elapsed_time": "18:09:57", "remaining_time": "7:07:18", "throughput": 8521.21, "total_tokens": 557266872} {"current_steps": 547400, "total_steps": 761865, "loss": 1.9789, "lr": 1.831115096501591e-07, "epoch": 10.777499950778681, "percentage": 71.85, "elapsed_time": "18:10:09", "remaining_time": "7:07:06", "throughput": 8521.22, "total_tokens": 557367608} {"current_steps": 547500, "total_steps": 761865, "loss": 2.0199, "lr": 1.829520527286032e-07, "epoch": 10.779468803528184, "percentage": 71.86, "elapsed_time": "18:10:21", "remaining_time": "7:06:54", "throughput": 8521.24, "total_tokens": 557470008} {"current_steps": 547600, "total_steps": 761865, "loss": 2.0638, "lr": 1.8279264971837644e-07, "epoch": 10.781437656277687, "percentage": 71.88, "elapsed_time": "18:10:33", "remaining_time": "7:06:42", "throughput": 8521.24, "total_tokens": 557571088} {"current_steps": 547700, "total_steps": 761865, "loss": 1.9636, "lr": 1.8263330064658434e-07, "epoch": 10.78340650902719, "percentage": 71.89, "elapsed_time": "18:10:44", "remaining_time": "7:06:30", "throughput": 8521.26, "total_tokens": 557673488} {"current_steps": 547800, "total_steps": 761865, "loss": 1.9807, "lr": 1.8247400554032233e-07, "epoch": 10.785375361776692, "percentage": 71.9, "elapsed_time": "18:10:56", "remaining_time": "7:06:18", "throughput": 8521.28, "total_tokens": 557775312} {"current_steps": 547900, "total_steps": 761865, "loss": 1.9661, "lr": 1.8231476442667794e-07, "epoch": 10.787344214526195, "percentage": 71.92, "elapsed_time": "18:11:08", "remaining_time": "7:06:06", "throughput": 8521.29, "total_tokens": 557876896} {"current_steps": 548000, "total_steps": 761865, "loss": 1.996, "lr": 1.8215557733272813e-07, "epoch": 10.789313067275698, "percentage": 71.93, "elapsed_time": "18:11:20", "remaining_time": "7:05:54", "throughput": 8521.31, "total_tokens": 557979296} {"current_steps": 548100, "total_steps": 761865, "loss": 1.9259, "lr": 1.8199644428554177e-07, "epoch": 10.7912819200252, "percentage": 71.94, "elapsed_time": "18:11:32", "remaining_time": "7:05:42", "throughput": 8521.32, "total_tokens": 558081696} {"current_steps": 548200, "total_steps": 761865, "loss": 1.9632, "lr": 1.8183736531217753e-07, "epoch": 10.793250772774703, "percentage": 71.96, "elapsed_time": "18:11:44", "remaining_time": "7:05:30", "throughput": 8521.34, "total_tokens": 558184096} {"current_steps": 548300, "total_steps": 761865, "loss": 1.9789, "lr": 1.8167834043968616e-07, "epoch": 10.795219625524208, "percentage": 71.97, "elapsed_time": "18:11:56", "remaining_time": "7:05:18", "throughput": 8521.35, "total_tokens": 558285808} {"current_steps": 548400, "total_steps": 761865, "loss": 1.9752, "lr": 1.81519369695108e-07, "epoch": 10.79718847827371, "percentage": 71.98, "elapsed_time": "18:12:07", "remaining_time": "7:05:06", "throughput": 8521.37, "total_tokens": 558388136} {"current_steps": 548500, "total_steps": 761865, "loss": 1.9626, "lr": 1.8136045310547483e-07, "epoch": 10.799157331023213, "percentage": 71.99, "elapsed_time": "18:12:19", "remaining_time": "7:04:54", "throughput": 8521.38, "total_tokens": 558490088} {"current_steps": 548600, "total_steps": 761865, "loss": 2.0121, "lr": 1.812015906978091e-07, "epoch": 10.801126183772716, "percentage": 72.01, "elapsed_time": "18:12:31", "remaining_time": "7:04:42", "throughput": 8521.4, "total_tokens": 558592488} {"current_steps": 548700, "total_steps": 761865, "loss": 1.9753, "lr": 1.8104278249912398e-07, "epoch": 10.803095036522219, "percentage": 72.02, "elapsed_time": "18:12:43", "remaining_time": "7:04:30", "throughput": 8521.42, "total_tokens": 558694888} {"current_steps": 548800, "total_steps": 761865, "loss": 1.9593, "lr": 1.8088402853642365e-07, "epoch": 10.805063889271722, "percentage": 72.03, "elapsed_time": "18:12:55", "remaining_time": "7:04:18", "throughput": 8521.44, "total_tokens": 558796840} {"current_steps": 548900, "total_steps": 761865, "loss": 1.9732, "lr": 1.8072532883670256e-07, "epoch": 10.807032742021224, "percentage": 72.05, "elapsed_time": "18:13:07", "remaining_time": "7:04:06", "throughput": 8521.45, "total_tokens": 558898864} {"current_steps": 549000, "total_steps": 761865, "loss": 1.9944, "lr": 1.8056668342694637e-07, "epoch": 10.809001594770727, "percentage": 72.06, "elapsed_time": "18:13:19", "remaining_time": "7:03:54", "throughput": 8521.46, "total_tokens": 558999960} {"current_steps": 549100, "total_steps": 761865, "loss": 1.9797, "lr": 1.8040809233413147e-07, "epoch": 10.81097044752023, "percentage": 72.07, "elapsed_time": "18:13:30", "remaining_time": "7:03:42", "throughput": 8521.47, "total_tokens": 559100584} {"current_steps": 549200, "total_steps": 761865, "loss": 2.0122, "lr": 1.8024955558522509e-07, "epoch": 10.812939300269733, "percentage": 72.09, "elapsed_time": "18:13:42", "remaining_time": "7:03:30", "throughput": 8521.48, "total_tokens": 559202984} {"current_steps": 549300, "total_steps": 761865, "loss": 1.9312, "lr": 1.800910732071847e-07, "epoch": 10.814908153019235, "percentage": 72.1, "elapsed_time": "18:13:54", "remaining_time": "7:03:18", "throughput": 8521.5, "total_tokens": 559304560} {"current_steps": 549400, "total_steps": 761865, "loss": 1.986, "lr": 1.7993264522695905e-07, "epoch": 10.816877005768738, "percentage": 72.11, "elapsed_time": "18:14:06", "remaining_time": "7:03:06", "throughput": 8521.51, "total_tokens": 559405872} {"current_steps": 549500, "total_steps": 761865, "loss": 2.0036, "lr": 1.7977427167148758e-07, "epoch": 10.818845858518241, "percentage": 72.13, "elapsed_time": "18:14:18", "remaining_time": "7:02:54", "throughput": 8521.53, "total_tokens": 559508272} {"current_steps": 549600, "total_steps": 761865, "loss": 1.9619, "lr": 1.7961595256770024e-07, "epoch": 10.820814711267744, "percentage": 72.14, "elapsed_time": "18:14:30", "remaining_time": "7:02:42", "throughput": 8521.54, "total_tokens": 559610112} {"current_steps": 549700, "total_steps": 761865, "loss": 2.0236, "lr": 1.794576879425181e-07, "epoch": 10.822783564017247, "percentage": 72.15, "elapsed_time": "18:14:41", "remaining_time": "7:02:30", "throughput": 8521.56, "total_tokens": 559712512} {"current_steps": 549800, "total_steps": 761865, "loss": 1.9962, "lr": 1.7929947782285239e-07, "epoch": 10.82475241676675, "percentage": 72.17, "elapsed_time": "18:14:53", "remaining_time": "7:02:18", "throughput": 8521.58, "total_tokens": 559814912} {"current_steps": 549900, "total_steps": 761865, "loss": 2.0282, "lr": 1.7914132223560558e-07, "epoch": 10.826721269516252, "percentage": 72.18, "elapsed_time": "18:15:05", "remaining_time": "7:02:06", "throughput": 8521.59, "total_tokens": 559917168} {"current_steps": 550000, "total_steps": 761865, "loss": 2.0156, "lr": 1.7898322120767063e-07, "epoch": 10.828690122265757, "percentage": 72.19, "elapsed_time": "18:15:17", "remaining_time": "7:01:54", "throughput": 8521.6, "total_tokens": 560018000} {"current_steps": 550100, "total_steps": 761865, "loss": 2.0037, "lr": 1.788251747659315e-07, "epoch": 10.83065897501526, "percentage": 72.2, "elapsed_time": "18:15:29", "remaining_time": "7:01:43", "throughput": 8521.53, "total_tokens": 560119568} {"current_steps": 550200, "total_steps": 761865, "loss": 1.9807, "lr": 1.7866718293726236e-07, "epoch": 10.832627827764762, "percentage": 72.22, "elapsed_time": "18:15:41", "remaining_time": "7:01:31", "throughput": 8521.55, "total_tokens": 560221512} {"current_steps": 550300, "total_steps": 761865, "loss": 2.0092, "lr": 1.7850924574852854e-07, "epoch": 10.834596680514265, "percentage": 72.23, "elapsed_time": "18:15:53", "remaining_time": "7:01:19", "throughput": 8521.55, "total_tokens": 560320424} {"current_steps": 550400, "total_steps": 761865, "loss": 1.939, "lr": 1.7835136322658584e-07, "epoch": 10.836565533263768, "percentage": 72.24, "elapsed_time": "18:16:05", "remaining_time": "7:01:07", "throughput": 8521.56, "total_tokens": 560422480} {"current_steps": 550500, "total_steps": 761865, "loss": 1.9604, "lr": 1.7819353539828097e-07, "epoch": 10.83853438601327, "percentage": 72.26, "elapsed_time": "18:16:17", "remaining_time": "7:00:55", "throughput": 8521.58, "total_tokens": 560524240} {"current_steps": 550600, "total_steps": 761865, "loss": 1.9907, "lr": 1.7803576229045125e-07, "epoch": 10.840503238762773, "percentage": 72.27, "elapsed_time": "18:16:28", "remaining_time": "7:00:43", "throughput": 8521.59, "total_tokens": 560625744} {"current_steps": 550700, "total_steps": 761865, "loss": 2.0138, "lr": 1.7787804392992433e-07, "epoch": 10.842472091512276, "percentage": 72.28, "elapsed_time": "18:16:40", "remaining_time": "7:00:31", "throughput": 8521.6, "total_tokens": 560727272} {"current_steps": 550800, "total_steps": 761865, "loss": 1.9414, "lr": 1.7772038034351943e-07, "epoch": 10.844440944261779, "percentage": 72.3, "elapsed_time": "18:16:52", "remaining_time": "7:00:19", "throughput": 8521.61, "total_tokens": 560829672} {"current_steps": 550900, "total_steps": 761865, "loss": 1.9839, "lr": 1.7756277155804545e-07, "epoch": 10.846409797011281, "percentage": 72.31, "elapsed_time": "18:17:04", "remaining_time": "7:00:07", "throughput": 8521.63, "total_tokens": 560931520} {"current_steps": 551000, "total_steps": 761865, "loss": 1.9676, "lr": 1.7740521760030264e-07, "epoch": 10.848378649760784, "percentage": 72.32, "elapsed_time": "18:17:16", "remaining_time": "6:59:55", "throughput": 8521.64, "total_tokens": 561033416} {"current_steps": 551100, "total_steps": 761865, "loss": 1.9416, "lr": 1.7724771849708164e-07, "epoch": 10.850347502510287, "percentage": 72.34, "elapsed_time": "18:17:28", "remaining_time": "6:59:43", "throughput": 8521.66, "total_tokens": 561135816} {"current_steps": 551200, "total_steps": 761865, "loss": 1.9874, "lr": 1.770902742751641e-07, "epoch": 10.85231635525979, "percentage": 72.35, "elapsed_time": "18:17:40", "remaining_time": "6:59:31", "throughput": 8521.67, "total_tokens": 561237280} {"current_steps": 551300, "total_steps": 761865, "loss": 2.0408, "lr": 1.769328849613217e-07, "epoch": 10.854285208009292, "percentage": 72.36, "elapsed_time": "18:17:51", "remaining_time": "6:59:19", "throughput": 8521.68, "total_tokens": 561338968} {"current_steps": 551400, "total_steps": 761865, "loss": 1.9723, "lr": 1.7677555058231731e-07, "epoch": 10.856254060758795, "percentage": 72.38, "elapsed_time": "18:18:03", "remaining_time": "6:59:07", "throughput": 8521.7, "total_tokens": 561441368} {"current_steps": 551500, "total_steps": 761865, "loss": 1.9687, "lr": 1.7661827116490435e-07, "epoch": 10.858222913508298, "percentage": 72.39, "elapsed_time": "18:18:15", "remaining_time": "6:58:55", "throughput": 8521.71, "total_tokens": 561542992} {"current_steps": 551600, "total_steps": 761865, "loss": 1.9687, "lr": 1.7646104673582685e-07, "epoch": 10.860191766257802, "percentage": 72.4, "elapsed_time": "18:18:27", "remaining_time": "6:58:43", "throughput": 8521.73, "total_tokens": 561645392} {"current_steps": 551700, "total_steps": 761865, "loss": 1.9726, "lr": 1.7630387732181973e-07, "epoch": 10.862160619007305, "percentage": 72.41, "elapsed_time": "18:18:39", "remaining_time": "6:58:31", "throughput": 8521.75, "total_tokens": 561747792} {"current_steps": 551800, "total_steps": 761865, "loss": 1.9377, "lr": 1.7614676294960785e-07, "epoch": 10.864129471756808, "percentage": 72.43, "elapsed_time": "18:18:51", "remaining_time": "6:58:19", "throughput": 8521.76, "total_tokens": 561849584} {"current_steps": 551900, "total_steps": 761865, "loss": 2.0214, "lr": 1.7598970364590742e-07, "epoch": 10.86609832450631, "percentage": 72.44, "elapsed_time": "18:19:02", "remaining_time": "6:58:07", "throughput": 8521.77, "total_tokens": 561951112} {"current_steps": 552000, "total_steps": 761865, "loss": 2.0145, "lr": 1.7583269943742513e-07, "epoch": 10.868067177255814, "percentage": 72.45, "elapsed_time": "18:19:14", "remaining_time": "6:57:55", "throughput": 8521.78, "total_tokens": 562052280} {"current_steps": 552100, "total_steps": 761865, "loss": 2.0146, "lr": 1.7567575035085824e-07, "epoch": 10.870036030005316, "percentage": 72.47, "elapsed_time": "18:19:26", "remaining_time": "6:57:43", "throughput": 8521.8, "total_tokens": 562154680} {"current_steps": 552200, "total_steps": 761865, "loss": 1.9759, "lr": 1.7551885641289437e-07, "epoch": 10.872004882754819, "percentage": 72.48, "elapsed_time": "18:19:38", "remaining_time": "6:57:31", "throughput": 8521.82, "total_tokens": 562257080} {"current_steps": 552300, "total_steps": 761865, "loss": 2.0018, "lr": 1.753620176502122e-07, "epoch": 10.873973735504322, "percentage": 72.49, "elapsed_time": "18:19:50", "remaining_time": "6:57:19", "throughput": 8521.83, "total_tokens": 562359024} {"current_steps": 552400, "total_steps": 761865, "loss": 2.0174, "lr": 1.752052340894808e-07, "epoch": 10.875942588253825, "percentage": 72.51, "elapsed_time": "18:20:02", "remaining_time": "6:57:07", "throughput": 8521.85, "total_tokens": 562460808} {"current_steps": 552500, "total_steps": 761865, "loss": 1.9412, "lr": 1.7504850575735984e-07, "epoch": 10.877911441003327, "percentage": 72.52, "elapsed_time": "18:20:14", "remaining_time": "6:56:55", "throughput": 8521.86, "total_tokens": 562562624} {"current_steps": 552600, "total_steps": 761865, "loss": 2.0346, "lr": 1.7489183268049994e-07, "epoch": 10.87988029375283, "percentage": 72.53, "elapsed_time": "18:20:25", "remaining_time": "6:56:43", "throughput": 8521.88, "total_tokens": 562665024} {"current_steps": 552700, "total_steps": 761865, "loss": 1.9846, "lr": 1.747352148855415e-07, "epoch": 10.881849146502333, "percentage": 72.55, "elapsed_time": "18:20:37", "remaining_time": "6:56:31", "throughput": 8521.9, "total_tokens": 562767424} {"current_steps": 552800, "total_steps": 761865, "loss": 1.9838, "lr": 1.7457865239911663e-07, "epoch": 10.883817999251836, "percentage": 72.56, "elapsed_time": "18:20:49", "remaining_time": "6:56:19", "throughput": 8521.91, "total_tokens": 562869016} {"current_steps": 552900, "total_steps": 761865, "loss": 2.006, "lr": 1.7442214524784705e-07, "epoch": 10.885786852001338, "percentage": 72.57, "elapsed_time": "18:21:01", "remaining_time": "6:56:07", "throughput": 8521.93, "total_tokens": 562971416} {"current_steps": 553000, "total_steps": 761865, "loss": 1.9823, "lr": 1.7426569345834573e-07, "epoch": 10.887755704750841, "percentage": 72.59, "elapsed_time": "18:21:13", "remaining_time": "6:55:55", "throughput": 8521.95, "total_tokens": 563073816} {"current_steps": 553100, "total_steps": 761865, "loss": 2.0341, "lr": 1.741092970572156e-07, "epoch": 10.889724557500344, "percentage": 72.6, "elapsed_time": "18:21:25", "remaining_time": "6:55:43", "throughput": 8521.95, "total_tokens": 563175296} {"current_steps": 553200, "total_steps": 761865, "loss": 2.0162, "lr": 1.7395295607105116e-07, "epoch": 10.891693410249847, "percentage": 72.61, "elapsed_time": "18:21:37", "remaining_time": "6:55:31", "throughput": 8521.97, "total_tokens": 563277328} {"current_steps": 553300, "total_steps": 761865, "loss": 1.9976, "lr": 1.7379667052643632e-07, "epoch": 10.89366226299935, "percentage": 72.62, "elapsed_time": "18:21:48", "remaining_time": "6:55:19", "throughput": 8521.98, "total_tokens": 563378568} {"current_steps": 553400, "total_steps": 761865, "loss": 1.9893, "lr": 1.736404404499463e-07, "epoch": 10.895631115748854, "percentage": 72.64, "elapsed_time": "18:22:00", "remaining_time": "6:55:07", "throughput": 8522.0, "total_tokens": 563480968} {"current_steps": 553500, "total_steps": 761865, "loss": 2.036, "lr": 1.734842658681468e-07, "epoch": 10.897599968498357, "percentage": 72.65, "elapsed_time": "18:22:12", "remaining_time": "6:54:55", "throughput": 8522.0, "total_tokens": 563581760} {"current_steps": 553600, "total_steps": 761865, "loss": 1.9807, "lr": 1.7332814680759396e-07, "epoch": 10.89956882124786, "percentage": 72.66, "elapsed_time": "18:22:24", "remaining_time": "6:54:43", "throughput": 8522.01, "total_tokens": 563683200} {"current_steps": 553700, "total_steps": 761865, "loss": 1.95, "lr": 1.7317208329483456e-07, "epoch": 10.901537673997362, "percentage": 72.68, "elapsed_time": "18:22:36", "remaining_time": "6:54:31", "throughput": 8522.03, "total_tokens": 563784976} {"current_steps": 553800, "total_steps": 761865, "loss": 1.9791, "lr": 1.7301607535640566e-07, "epoch": 10.903506526746865, "percentage": 72.69, "elapsed_time": "18:22:48", "remaining_time": "6:54:19", "throughput": 8522.04, "total_tokens": 563886624} {"current_steps": 553900, "total_steps": 761865, "loss": 1.9887, "lr": 1.7286012301883523e-07, "epoch": 10.905475379496368, "percentage": 72.7, "elapsed_time": "18:22:59", "remaining_time": "6:54:07", "throughput": 8522.06, "total_tokens": 563989024} {"current_steps": 554000, "total_steps": 761865, "loss": 2.0081, "lr": 1.727042263086417e-07, "epoch": 10.90744423224587, "percentage": 72.72, "elapsed_time": "18:23:11", "remaining_time": "6:53:55", "throughput": 8522.06, "total_tokens": 564089872} {"current_steps": 554100, "total_steps": 761865, "loss": 1.9486, "lr": 1.7254838525233406e-07, "epoch": 10.909413084995373, "percentage": 72.73, "elapsed_time": "18:23:23", "remaining_time": "6:53:43", "throughput": 8522.08, "total_tokens": 564192272} {"current_steps": 554200, "total_steps": 761865, "loss": 2.0381, "lr": 1.7239259987641152e-07, "epoch": 10.911381937744876, "percentage": 72.74, "elapsed_time": "18:23:35", "remaining_time": "6:53:31", "throughput": 8522.09, "total_tokens": 564293720} {"current_steps": 554300, "total_steps": 761865, "loss": 1.9525, "lr": 1.7223687020736421e-07, "epoch": 10.913350790494379, "percentage": 72.76, "elapsed_time": "18:23:47", "remaining_time": "6:53:19", "throughput": 8522.11, "total_tokens": 564396120} {"current_steps": 554400, "total_steps": 761865, "loss": 1.9901, "lr": 1.7208119627167262e-07, "epoch": 10.915319643243881, "percentage": 72.77, "elapsed_time": "18:23:59", "remaining_time": "6:53:07", "throughput": 8522.12, "total_tokens": 564497872} {"current_steps": 554500, "total_steps": 761865, "loss": 1.9713, "lr": 1.7192557809580782e-07, "epoch": 10.917288495993384, "percentage": 72.78, "elapsed_time": "18:24:11", "remaining_time": "6:52:55", "throughput": 8522.14, "total_tokens": 564600272} {"current_steps": 554600, "total_steps": 761865, "loss": 1.9652, "lr": 1.7177001570623152e-07, "epoch": 10.919257348742887, "percentage": 72.8, "elapsed_time": "18:24:22", "remaining_time": "6:52:43", "throughput": 8522.15, "total_tokens": 564701904} {"current_steps": 554700, "total_steps": 761865, "loss": 1.9955, "lr": 1.7161450912939546e-07, "epoch": 10.92122620149239, "percentage": 72.81, "elapsed_time": "18:24:34", "remaining_time": "6:52:31", "throughput": 8522.16, "total_tokens": 564803376} {"current_steps": 554800, "total_steps": 761865, "loss": 1.9527, "lr": 1.7145905839174241e-07, "epoch": 10.923195054241893, "percentage": 72.82, "elapsed_time": "18:24:46", "remaining_time": "6:52:19", "throughput": 8522.18, "total_tokens": 564905776} {"current_steps": 554900, "total_steps": 761865, "loss": 1.9534, "lr": 1.7130366351970538e-07, "epoch": 10.925163906991397, "percentage": 72.83, "elapsed_time": "18:24:58", "remaining_time": "6:52:07", "throughput": 8522.2, "total_tokens": 565008176} {"current_steps": 555000, "total_steps": 761865, "loss": 1.9654, "lr": 1.7114832453970822e-07, "epoch": 10.9271327597409, "percentage": 72.85, "elapsed_time": "18:25:10", "remaining_time": "6:51:55", "throughput": 8522.22, "total_tokens": 565110576} {"current_steps": 555100, "total_steps": 761865, "loss": 1.9346, "lr": 1.7099304147816467e-07, "epoch": 10.929101612490403, "percentage": 72.86, "elapsed_time": "18:25:22", "remaining_time": "6:51:44", "throughput": 8522.15, "total_tokens": 565212792} {"current_steps": 555200, "total_steps": 761865, "loss": 1.969, "lr": 1.7083781436147943e-07, "epoch": 10.931070465239905, "percentage": 72.87, "elapsed_time": "18:25:34", "remaining_time": "6:51:32", "throughput": 8522.17, "total_tokens": 565315192} {"current_steps": 555300, "total_steps": 761865, "loss": 2.0155, "lr": 1.7068264321604753e-07, "epoch": 10.933039317989408, "percentage": 72.89, "elapsed_time": "18:25:46", "remaining_time": "6:51:20", "throughput": 8522.17, "total_tokens": 565415928} {"current_steps": 555400, "total_steps": 761865, "loss": 2.0495, "lr": 1.7052752806825477e-07, "epoch": 10.93500817073891, "percentage": 72.9, "elapsed_time": "18:25:58", "remaining_time": "6:51:08", "throughput": 8522.19, "total_tokens": 565517616} {"current_steps": 555500, "total_steps": 761865, "loss": 1.9904, "lr": 1.7037246894447677e-07, "epoch": 10.936977023488414, "percentage": 72.91, "elapsed_time": "18:26:10", "remaining_time": "6:50:56", "throughput": 8522.2, "total_tokens": 565619440} {"current_steps": 555600, "total_steps": 761865, "loss": 1.9493, "lr": 1.702174658710801e-07, "epoch": 10.938945876237916, "percentage": 72.93, "elapsed_time": "18:26:21", "remaining_time": "6:50:44", "throughput": 8522.21, "total_tokens": 565721296} {"current_steps": 555700, "total_steps": 761865, "loss": 1.9937, "lr": 1.7006251887442213e-07, "epoch": 10.94091472898742, "percentage": 72.94, "elapsed_time": "18:26:33", "remaining_time": "6:50:32", "throughput": 8522.23, "total_tokens": 565823608} {"current_steps": 555800, "total_steps": 761865, "loss": 2.0009, "lr": 1.6990762798084984e-07, "epoch": 10.942883581736922, "percentage": 72.95, "elapsed_time": "18:26:45", "remaining_time": "6:50:20", "throughput": 8522.25, "total_tokens": 565926008} {"current_steps": 555900, "total_steps": 761865, "loss": 1.9993, "lr": 1.6975279321670148e-07, "epoch": 10.944852434486425, "percentage": 72.97, "elapsed_time": "18:26:57", "remaining_time": "6:50:08", "throughput": 8522.26, "total_tokens": 566027696} {"current_steps": 556000, "total_steps": 761865, "loss": 2.0226, "lr": 1.6959801460830487e-07, "epoch": 10.946821287235927, "percentage": 72.98, "elapsed_time": "18:27:09", "remaining_time": "6:49:56", "throughput": 8522.27, "total_tokens": 566129400} {"current_steps": 556100, "total_steps": 761865, "loss": 1.9986, "lr": 1.6944329218197943e-07, "epoch": 10.94879013998543, "percentage": 72.99, "elapsed_time": "18:27:21", "remaining_time": "6:49:44", "throughput": 8522.28, "total_tokens": 566231272} {"current_steps": 556200, "total_steps": 761865, "loss": 2.003, "lr": 1.6928862596403397e-07, "epoch": 10.950758992734933, "percentage": 73.01, "elapsed_time": "18:27:33", "remaining_time": "6:49:32", "throughput": 8522.3, "total_tokens": 566333672} {"current_steps": 556300, "total_steps": 761865, "loss": 1.9752, "lr": 1.6913401598076848e-07, "epoch": 10.952727845484436, "percentage": 73.02, "elapsed_time": "18:27:45", "remaining_time": "6:49:20", "throughput": 8522.32, "total_tokens": 566436072} {"current_steps": 556400, "total_steps": 761865, "loss": 1.9981, "lr": 1.6897946225847258e-07, "epoch": 10.954696698233938, "percentage": 73.03, "elapsed_time": "18:27:56", "remaining_time": "6:49:08", "throughput": 8522.33, "total_tokens": 566537920} {"current_steps": 556500, "total_steps": 761865, "loss": 1.9692, "lr": 1.6882496482342734e-07, "epoch": 10.956665550983441, "percentage": 73.04, "elapsed_time": "18:28:08", "remaining_time": "6:48:56", "throughput": 8522.35, "total_tokens": 566640320} {"current_steps": 556600, "total_steps": 761865, "loss": 1.9715, "lr": 1.6867052370190376e-07, "epoch": 10.958634403732944, "percentage": 73.06, "elapsed_time": "18:28:20", "remaining_time": "6:48:44", "throughput": 8522.37, "total_tokens": 566742720} {"current_steps": 556700, "total_steps": 761865, "loss": 1.9685, "lr": 1.6851613892016286e-07, "epoch": 10.960603256482448, "percentage": 73.07, "elapsed_time": "18:28:32", "remaining_time": "6:48:32", "throughput": 8522.38, "total_tokens": 566844328} {"current_steps": 556800, "total_steps": 761865, "loss": 1.9762, "lr": 1.683618105044567e-07, "epoch": 10.962572109231951, "percentage": 73.08, "elapsed_time": "18:28:44", "remaining_time": "6:48:20", "throughput": 8522.39, "total_tokens": 566946600} {"current_steps": 556900, "total_steps": 761865, "loss": 1.9475, "lr": 1.6820753848102748e-07, "epoch": 10.964540961981454, "percentage": 73.1, "elapsed_time": "18:28:56", "remaining_time": "6:48:08", "throughput": 8522.41, "total_tokens": 567049000} {"current_steps": 557000, "total_steps": 761865, "loss": 2.0123, "lr": 1.6805332287610807e-07, "epoch": 10.966509814730957, "percentage": 73.11, "elapsed_time": "18:29:07", "remaining_time": "6:47:56", "throughput": 8522.41, "total_tokens": 567148664} {"current_steps": 557100, "total_steps": 761865, "loss": 2.0617, "lr": 1.678991637159211e-07, "epoch": 10.96847866748046, "percentage": 73.12, "elapsed_time": "18:29:19", "remaining_time": "6:47:44", "throughput": 8522.42, "total_tokens": 567250544} {"current_steps": 557200, "total_steps": 761865, "loss": 1.9657, "lr": 1.6774506102668035e-07, "epoch": 10.970447520229962, "percentage": 73.14, "elapsed_time": "18:29:31", "remaining_time": "6:47:32", "throughput": 8522.44, "total_tokens": 567352448} {"current_steps": 557300, "total_steps": 761865, "loss": 1.9856, "lr": 1.6759101483458954e-07, "epoch": 10.972416372979465, "percentage": 73.15, "elapsed_time": "18:29:43", "remaining_time": "6:47:20", "throughput": 8522.45, "total_tokens": 567453400} {"current_steps": 557400, "total_steps": 761865, "loss": 2.0378, "lr": 1.6743702516584323e-07, "epoch": 10.974385225728968, "percentage": 73.16, "elapsed_time": "18:29:55", "remaining_time": "6:47:08", "throughput": 8522.45, "total_tokens": 567553656} {"current_steps": 557500, "total_steps": 761865, "loss": 1.9628, "lr": 1.672830920466256e-07, "epoch": 10.97635407847847, "percentage": 73.18, "elapsed_time": "18:30:06", "remaining_time": "6:46:56", "throughput": 8522.47, "total_tokens": 567656056} {"current_steps": 557600, "total_steps": 761865, "loss": 1.9569, "lr": 1.6712921550311192e-07, "epoch": 10.978322931227973, "percentage": 73.19, "elapsed_time": "18:30:18", "remaining_time": "6:46:44", "throughput": 8522.49, "total_tokens": 567758456} {"current_steps": 557700, "total_steps": 761865, "loss": 1.9886, "lr": 1.6697539556146762e-07, "epoch": 10.980291783977476, "percentage": 73.2, "elapsed_time": "18:30:30", "remaining_time": "6:46:32", "throughput": 8522.5, "total_tokens": 567860680} {"current_steps": 557800, "total_steps": 761865, "loss": 2.0117, "lr": 1.668216322478484e-07, "epoch": 10.982260636726979, "percentage": 73.22, "elapsed_time": "18:30:42", "remaining_time": "6:46:20", "throughput": 8522.52, "total_tokens": 567962464} {"current_steps": 557900, "total_steps": 761865, "loss": 1.966, "lr": 1.6666792558840058e-07, "epoch": 10.984229489476482, "percentage": 73.23, "elapsed_time": "18:30:54", "remaining_time": "6:46:08", "throughput": 8522.53, "total_tokens": 568063992} {"current_steps": 558000, "total_steps": 761865, "loss": 1.9484, "lr": 1.6651427560926053e-07, "epoch": 10.986198342225984, "percentage": 73.24, "elapsed_time": "18:31:06", "remaining_time": "6:45:56", "throughput": 8522.53, "total_tokens": 568164104} {"current_steps": 558100, "total_steps": 761865, "loss": 1.9726, "lr": 1.6636068233655504e-07, "epoch": 10.988167194975487, "percentage": 73.25, "elapsed_time": "18:31:17", "remaining_time": "6:45:44", "throughput": 8522.54, "total_tokens": 568265776} {"current_steps": 558200, "total_steps": 761865, "loss": 1.9986, "lr": 1.6620714579640155e-07, "epoch": 10.99013604772499, "percentage": 73.27, "elapsed_time": "18:31:29", "remaining_time": "6:45:32", "throughput": 8522.56, "total_tokens": 568367792} {"current_steps": 558300, "total_steps": 761865, "loss": 1.9918, "lr": 1.6605366601490767e-07, "epoch": 10.992104900474494, "percentage": 73.28, "elapsed_time": "18:31:41", "remaining_time": "6:45:20", "throughput": 8522.57, "total_tokens": 568469384} {"current_steps": 558400, "total_steps": 761865, "loss": 2.0342, "lr": 1.659002430181712e-07, "epoch": 10.994073753223997, "percentage": 73.29, "elapsed_time": "18:31:53", "remaining_time": "6:45:08", "throughput": 8522.58, "total_tokens": 568571048} {"current_steps": 558500, "total_steps": 761865, "loss": 2.0571, "lr": 1.6574687683228016e-07, "epoch": 10.9960426059735, "percentage": 73.31, "elapsed_time": "18:32:05", "remaining_time": "6:44:56", "throughput": 8522.59, "total_tokens": 568671840} {"current_steps": 558600, "total_steps": 761865, "loss": 1.9717, "lr": 1.6559356748331394e-07, "epoch": 10.998011458723003, "percentage": 73.32, "elapsed_time": "18:32:17", "remaining_time": "6:44:44", "throughput": 8522.61, "total_tokens": 568774240} {"current_steps": 558700, "total_steps": 761865, "loss": 2.0256, "lr": 1.6544031499734085e-07, "epoch": 10.999980311472505, "percentage": 73.33, "elapsed_time": "18:32:28", "remaining_time": "6:44:32", "throughput": 8522.62, "total_tokens": 568876208} {"current_steps": 558800, "total_steps": 761865, "loss": 1.9573, "lr": 1.6528711940042056e-07, "epoch": 11.001949164222008, "percentage": 73.35, "elapsed_time": "18:32:40", "remaining_time": "6:44:20", "throughput": 8522.64, "total_tokens": 568978608} {"current_steps": 558900, "total_steps": 761865, "loss": 1.944, "lr": 1.651339807186022e-07, "epoch": 11.003918016971511, "percentage": 73.36, "elapsed_time": "18:32:52", "remaining_time": "6:44:08", "throughput": 8522.66, "total_tokens": 569081008} {"current_steps": 559000, "total_steps": 761865, "loss": 2.0115, "lr": 1.6498089897792634e-07, "epoch": 11.005886869721014, "percentage": 73.37, "elapsed_time": "18:33:04", "remaining_time": "6:43:56", "throughput": 8522.68, "total_tokens": 569183408} {"current_steps": 559100, "total_steps": 761865, "loss": 1.9466, "lr": 1.648278742044228e-07, "epoch": 11.007855722470516, "percentage": 73.39, "elapsed_time": "18:33:16", "remaining_time": "6:43:44", "throughput": 8522.68, "total_tokens": 569284776} {"current_steps": 559200, "total_steps": 761865, "loss": 1.9733, "lr": 1.646749064241124e-07, "epoch": 11.00982457522002, "percentage": 73.4, "elapsed_time": "18:33:28", "remaining_time": "6:43:32", "throughput": 8522.7, "total_tokens": 569387176} {"current_steps": 559300, "total_steps": 761865, "loss": 1.9397, "lr": 1.6452199566300557e-07, "epoch": 11.011793427969522, "percentage": 73.41, "elapsed_time": "18:33:40", "remaining_time": "6:43:20", "throughput": 8522.72, "total_tokens": 569489576} {"current_steps": 559400, "total_steps": 761865, "loss": 1.9486, "lr": 1.6436914194710416e-07, "epoch": 11.013762280719025, "percentage": 73.43, "elapsed_time": "18:33:52", "remaining_time": "6:43:08", "throughput": 8522.73, "total_tokens": 569591344} {"current_steps": 559500, "total_steps": 761865, "loss": 2.0292, "lr": 1.6421634530239913e-07, "epoch": 11.015731133468528, "percentage": 73.44, "elapsed_time": "18:34:03", "remaining_time": "6:42:56", "throughput": 8522.74, "total_tokens": 569693144} {"current_steps": 559600, "total_steps": 761865, "loss": 2.0163, "lr": 1.6406360575487254e-07, "epoch": 11.01769998621803, "percentage": 73.45, "elapsed_time": "18:34:15", "remaining_time": "6:42:44", "throughput": 8522.75, "total_tokens": 569793808} {"current_steps": 559700, "total_steps": 761865, "loss": 1.9609, "lr": 1.6391092333049627e-07, "epoch": 11.019668838967533, "percentage": 73.46, "elapsed_time": "18:34:27", "remaining_time": "6:42:32", "throughput": 8522.76, "total_tokens": 569894256} {"current_steps": 559800, "total_steps": 761865, "loss": 2.0057, "lr": 1.6375829805523285e-07, "epoch": 11.021637691717036, "percentage": 73.48, "elapsed_time": "18:34:39", "remaining_time": "6:42:20", "throughput": 8522.77, "total_tokens": 569996112} {"current_steps": 559900, "total_steps": 761865, "loss": 1.9741, "lr": 1.6360572995503503e-07, "epoch": 11.023606544466539, "percentage": 73.49, "elapsed_time": "18:34:51", "remaining_time": "6:42:08", "throughput": 8522.79, "total_tokens": 570098512} {"current_steps": 560000, "total_steps": 761865, "loss": 1.9892, "lr": 1.634532190558453e-07, "epoch": 11.025575397216043, "percentage": 73.5, "elapsed_time": "18:35:02", "remaining_time": "6:41:56", "throughput": 8522.81, "total_tokens": 570200912} {"current_steps": 560100, "total_steps": 761865, "loss": 2.0215, "lr": 1.6330076538359717e-07, "epoch": 11.027544249965546, "percentage": 73.52, "elapsed_time": "18:35:15", "remaining_time": "6:41:44", "throughput": 8522.73, "total_tokens": 570302456} {"current_steps": 560200, "total_steps": 761865, "loss": 1.938, "lr": 1.63148368964214e-07, "epoch": 11.029513102715049, "percentage": 73.53, "elapsed_time": "18:35:27", "remaining_time": "6:41:32", "throughput": 8522.75, "total_tokens": 570404128} {"current_steps": 560300, "total_steps": 761865, "loss": 1.9825, "lr": 1.6299602982360977e-07, "epoch": 11.031481955464551, "percentage": 73.54, "elapsed_time": "18:35:38", "remaining_time": "6:41:20", "throughput": 8522.75, "total_tokens": 570504216} {"current_steps": 560400, "total_steps": 761865, "loss": 2.0262, "lr": 1.6284374798768802e-07, "epoch": 11.033450808214054, "percentage": 73.56, "elapsed_time": "18:35:50", "remaining_time": "6:41:08", "throughput": 8522.76, "total_tokens": 570605856} {"current_steps": 560500, "total_steps": 761865, "loss": 1.9857, "lr": 1.6269152348234328e-07, "epoch": 11.035419660963557, "percentage": 73.57, "elapsed_time": "18:36:02", "remaining_time": "6:40:56", "throughput": 8522.77, "total_tokens": 570706544} {"current_steps": 560600, "total_steps": 761865, "loss": 1.9742, "lr": 1.6253935633345995e-07, "epoch": 11.03738851371306, "percentage": 73.58, "elapsed_time": "18:36:14", "remaining_time": "6:40:44", "throughput": 8522.78, "total_tokens": 570808264} {"current_steps": 560700, "total_steps": 761865, "loss": 1.9635, "lr": 1.6238724656691277e-07, "epoch": 11.039357366462562, "percentage": 73.6, "elapsed_time": "18:36:26", "remaining_time": "6:40:32", "throughput": 8522.8, "total_tokens": 570910664} {"current_steps": 560800, "total_steps": 761865, "loss": 1.9952, "lr": 1.6223519420856697e-07, "epoch": 11.041326219212065, "percentage": 73.61, "elapsed_time": "18:36:38", "remaining_time": "6:40:20", "throughput": 8522.81, "total_tokens": 571011392} {"current_steps": 560900, "total_steps": 761865, "loss": 1.9233, "lr": 1.6208319928427732e-07, "epoch": 11.043295071961568, "percentage": 73.62, "elapsed_time": "18:36:49", "remaining_time": "6:40:08", "throughput": 8522.82, "total_tokens": 571113056} {"current_steps": 561000, "total_steps": 761865, "loss": 2.0118, "lr": 1.6193126181988958e-07, "epoch": 11.04526392471107, "percentage": 73.64, "elapsed_time": "18:37:01", "remaining_time": "6:39:56", "throughput": 8522.83, "total_tokens": 571214160} {"current_steps": 561100, "total_steps": 761865, "loss": 1.9679, "lr": 1.6177938184123928e-07, "epoch": 11.047232777460573, "percentage": 73.65, "elapsed_time": "18:37:13", "remaining_time": "6:39:44", "throughput": 8522.84, "total_tokens": 571315792} {"current_steps": 561200, "total_steps": 761865, "loss": 1.9897, "lr": 1.6162755937415268e-07, "epoch": 11.049201630210076, "percentage": 73.66, "elapsed_time": "18:37:25", "remaining_time": "6:39:32", "throughput": 8522.85, "total_tokens": 571416736} {"current_steps": 561300, "total_steps": 761865, "loss": 1.978, "lr": 1.6147579444444526e-07, "epoch": 11.051170482959579, "percentage": 73.67, "elapsed_time": "18:37:37", "remaining_time": "6:39:20", "throughput": 8522.87, "total_tokens": 571518296} {"current_steps": 561400, "total_steps": 761865, "loss": 2.0047, "lr": 1.6132408707792411e-07, "epoch": 11.053139335709082, "percentage": 73.69, "elapsed_time": "18:37:48", "remaining_time": "6:39:08", "throughput": 8522.88, "total_tokens": 571619800} {"current_steps": 561500, "total_steps": 761865, "loss": 1.9374, "lr": 1.611724373003852e-07, "epoch": 11.055108188458584, "percentage": 73.7, "elapsed_time": "18:38:00", "remaining_time": "6:38:56", "throughput": 8522.89, "total_tokens": 571721408} {"current_steps": 561600, "total_steps": 761865, "loss": 1.9598, "lr": 1.610208451376156e-07, "epoch": 11.057077041208087, "percentage": 73.71, "elapsed_time": "18:38:12", "remaining_time": "6:38:44", "throughput": 8522.9, "total_tokens": 571822328} {"current_steps": 561700, "total_steps": 761865, "loss": 1.9683, "lr": 1.6086931061539217e-07, "epoch": 11.059045893957592, "percentage": 73.73, "elapsed_time": "18:38:24", "remaining_time": "6:38:32", "throughput": 8522.91, "total_tokens": 571923528} {"current_steps": 561800, "total_steps": 761865, "loss": 1.9853, "lr": 1.607178337594821e-07, "epoch": 11.061014746707095, "percentage": 73.74, "elapsed_time": "18:38:36", "remaining_time": "6:38:21", "throughput": 8522.93, "total_tokens": 572025928} {"current_steps": 561900, "total_steps": 761865, "loss": 1.9622, "lr": 1.6056641459564292e-07, "epoch": 11.062983599456597, "percentage": 73.75, "elapsed_time": "18:38:48", "remaining_time": "6:38:09", "throughput": 8522.94, "total_tokens": 572128328} {"current_steps": 562000, "total_steps": 761865, "loss": 1.9895, "lr": 1.604150531496219e-07, "epoch": 11.0649524522061, "percentage": 73.77, "elapsed_time": "18:38:59", "remaining_time": "6:37:57", "throughput": 8522.96, "total_tokens": 572230728} {"current_steps": 562100, "total_steps": 761865, "loss": 1.9744, "lr": 1.6026374944715682e-07, "epoch": 11.066921304955603, "percentage": 73.78, "elapsed_time": "18:39:11", "remaining_time": "6:37:45", "throughput": 8522.98, "total_tokens": 572333128} {"current_steps": 562200, "total_steps": 761865, "loss": 1.952, "lr": 1.6011250351397575e-07, "epoch": 11.068890157705106, "percentage": 73.79, "elapsed_time": "18:39:23", "remaining_time": "6:37:33", "throughput": 8522.99, "total_tokens": 572435528} {"current_steps": 562300, "total_steps": 761865, "loss": 1.9921, "lr": 1.5996131537579688e-07, "epoch": 11.070859010454608, "percentage": 73.81, "elapsed_time": "18:39:35", "remaining_time": "6:37:21", "throughput": 8523.0, "total_tokens": 572537136} {"current_steps": 562400, "total_steps": 761865, "loss": 1.965, "lr": 1.598101850583281e-07, "epoch": 11.072827863204111, "percentage": 73.82, "elapsed_time": "18:39:47", "remaining_time": "6:37:09", "throughput": 8523.02, "total_tokens": 572639536} {"current_steps": 562500, "total_steps": 761865, "loss": 2.0186, "lr": 1.596591125872681e-07, "epoch": 11.074796715953614, "percentage": 73.83, "elapsed_time": "18:39:59", "remaining_time": "6:36:57", "throughput": 8523.03, "total_tokens": 572741464} {"current_steps": 562600, "total_steps": 761865, "loss": 2.0402, "lr": 1.595080979883054e-07, "epoch": 11.076765568703117, "percentage": 73.85, "elapsed_time": "18:40:11", "remaining_time": "6:36:45", "throughput": 8523.05, "total_tokens": 572843864} {"current_steps": 562700, "total_steps": 761865, "loss": 1.9514, "lr": 1.5935714128711886e-07, "epoch": 11.07873442145262, "percentage": 73.86, "elapsed_time": "18:40:23", "remaining_time": "6:36:33", "throughput": 8523.06, "total_tokens": 572946264} {"current_steps": 562800, "total_steps": 761865, "loss": 1.9852, "lr": 1.5920624250937743e-07, "epoch": 11.080703274202122, "percentage": 73.87, "elapsed_time": "18:40:34", "remaining_time": "6:36:21", "throughput": 8523.08, "total_tokens": 573048664} {"current_steps": 562900, "total_steps": 761865, "loss": 1.95, "lr": 1.5905540168073993e-07, "epoch": 11.082672126951625, "percentage": 73.88, "elapsed_time": "18:40:46", "remaining_time": "6:36:09", "throughput": 8523.09, "total_tokens": 573151064} {"current_steps": 563000, "total_steps": 761865, "loss": 1.9567, "lr": 1.589046188268557e-07, "epoch": 11.084640979701128, "percentage": 73.9, "elapsed_time": "18:40:58", "remaining_time": "6:35:57", "throughput": 8523.11, "total_tokens": 573253464} {"current_steps": 563100, "total_steps": 761865, "loss": 1.9779, "lr": 1.5875389397336413e-07, "epoch": 11.08660983245063, "percentage": 73.91, "elapsed_time": "18:41:10", "remaining_time": "6:35:45", "throughput": 8523.12, "total_tokens": 573355048} {"current_steps": 563200, "total_steps": 761865, "loss": 1.9522, "lr": 1.5860322714589487e-07, "epoch": 11.088578685200133, "percentage": 73.92, "elapsed_time": "18:41:22", "remaining_time": "6:35:33", "throughput": 8523.13, "total_tokens": 573456920} {"current_steps": 563300, "total_steps": 761865, "loss": 1.9963, "lr": 1.5845261837006712e-07, "epoch": 11.090547537949636, "percentage": 73.94, "elapsed_time": "18:41:34", "remaining_time": "6:35:21", "throughput": 8523.14, "total_tokens": 573559216} {"current_steps": 563400, "total_steps": 761865, "loss": 1.994, "lr": 1.5830206767149097e-07, "epoch": 11.09251639069914, "percentage": 73.95, "elapsed_time": "18:41:46", "remaining_time": "6:35:09", "throughput": 8523.15, "total_tokens": 573661616} {"current_steps": 563500, "total_steps": 761865, "loss": 1.993, "lr": 1.581515750757661e-07, "epoch": 11.094485243448643, "percentage": 73.96, "elapsed_time": "18:41:57", "remaining_time": "6:34:57", "throughput": 8523.15, "total_tokens": 573761264} {"current_steps": 563600, "total_steps": 761865, "loss": 1.9719, "lr": 1.5800114060848268e-07, "epoch": 11.096454096198146, "percentage": 73.98, "elapsed_time": "18:42:09", "remaining_time": "6:34:45", "throughput": 8523.17, "total_tokens": 573863528} {"current_steps": 563700, "total_steps": 761865, "loss": 1.9866, "lr": 1.5785076429522089e-07, "epoch": 11.098422948947649, "percentage": 73.99, "elapsed_time": "18:42:21", "remaining_time": "6:34:33", "throughput": 8523.18, "total_tokens": 573964744} {"current_steps": 563800, "total_steps": 761865, "loss": 1.9711, "lr": 1.5770044616155048e-07, "epoch": 11.100391801697151, "percentage": 74.0, "elapsed_time": "18:42:33", "remaining_time": "6:34:21", "throughput": 8523.19, "total_tokens": 574067144} {"current_steps": 563900, "total_steps": 761865, "loss": 1.9967, "lr": 1.5755018623303247e-07, "epoch": 11.102360654446654, "percentage": 74.02, "elapsed_time": "18:42:45", "remaining_time": "6:34:09", "throughput": 8523.21, "total_tokens": 574169232} {"current_steps": 564000, "total_steps": 761865, "loss": 1.9236, "lr": 1.5739998453521668e-07, "epoch": 11.104329507196157, "percentage": 74.03, "elapsed_time": "18:42:57", "remaining_time": "6:33:57", "throughput": 8523.22, "total_tokens": 574271632} {"current_steps": 564100, "total_steps": 761865, "loss": 1.9722, "lr": 1.5724984109364414e-07, "epoch": 11.10629835994566, "percentage": 74.04, "elapsed_time": "18:43:09", "remaining_time": "6:33:45", "throughput": 8523.23, "total_tokens": 574373296} {"current_steps": 564200, "total_steps": 761865, "loss": 1.9822, "lr": 1.5709975593384489e-07, "epoch": 11.108267212695162, "percentage": 74.06, "elapsed_time": "18:43:21", "remaining_time": "6:33:33", "throughput": 8523.25, "total_tokens": 574475408} {"current_steps": 564300, "total_steps": 761865, "loss": 2.032, "lr": 1.5694972908134034e-07, "epoch": 11.110236065444665, "percentage": 74.07, "elapsed_time": "18:43:32", "remaining_time": "6:33:21", "throughput": 8523.25, "total_tokens": 574576424} {"current_steps": 564400, "total_steps": 761865, "loss": 2.0213, "lr": 1.5679976056164074e-07, "epoch": 11.112204918194168, "percentage": 74.08, "elapsed_time": "18:43:44", "remaining_time": "6:33:09", "throughput": 8523.26, "total_tokens": 574678512} {"current_steps": 564500, "total_steps": 761865, "loss": 1.9384, "lr": 1.5664985040024737e-07, "epoch": 11.11417377094367, "percentage": 74.09, "elapsed_time": "18:43:56", "remaining_time": "6:32:57", "throughput": 8523.28, "total_tokens": 574779736} {"current_steps": 564600, "total_steps": 761865, "loss": 2.0487, "lr": 1.564999986226506e-07, "epoch": 11.116142623693174, "percentage": 74.11, "elapsed_time": "18:44:08", "remaining_time": "6:32:45", "throughput": 8523.29, "total_tokens": 574881512} {"current_steps": 564700, "total_steps": 761865, "loss": 1.9697, "lr": 1.5635020525433207e-07, "epoch": 11.118111476442676, "percentage": 74.12, "elapsed_time": "18:44:20", "remaining_time": "6:32:33", "throughput": 8523.3, "total_tokens": 574983912} {"current_steps": 564800, "total_steps": 761865, "loss": 1.9658, "lr": 1.5620047032076282e-07, "epoch": 11.120080329192179, "percentage": 74.13, "elapsed_time": "18:44:32", "remaining_time": "6:32:21", "throughput": 8523.32, "total_tokens": 575086312} {"current_steps": 564900, "total_steps": 761865, "loss": 2.0302, "lr": 1.5605079384740373e-07, "epoch": 11.122049181941682, "percentage": 74.15, "elapsed_time": "18:44:44", "remaining_time": "6:32:09", "throughput": 8523.33, "total_tokens": 575188712} {"current_steps": 565000, "total_steps": 761865, "loss": 1.9845, "lr": 1.5590117585970608e-07, "epoch": 11.124018034691186, "percentage": 74.16, "elapsed_time": "18:44:55", "remaining_time": "6:31:57", "throughput": 8523.35, "total_tokens": 575291112} {"current_steps": 565100, "total_steps": 761865, "loss": 1.9315, "lr": 1.5575161638311124e-07, "epoch": 11.125986887440689, "percentage": 74.17, "elapsed_time": "18:45:08", "remaining_time": "6:31:46", "throughput": 8523.28, "total_tokens": 575393512} {"current_steps": 565200, "total_steps": 761865, "loss": 1.9842, "lr": 1.5560211544305063e-07, "epoch": 11.127955740190192, "percentage": 74.19, "elapsed_time": "18:45:20", "remaining_time": "6:31:34", "throughput": 8523.3, "total_tokens": 575495392} {"current_steps": 565300, "total_steps": 761865, "loss": 1.9941, "lr": 1.5545267306494537e-07, "epoch": 11.129924592939695, "percentage": 74.2, "elapsed_time": "18:45:32", "remaining_time": "6:31:22", "throughput": 8523.31, "total_tokens": 575597792} {"current_steps": 565400, "total_steps": 761865, "loss": 1.998, "lr": 1.5530328927420705e-07, "epoch": 11.131893445689197, "percentage": 74.21, "elapsed_time": "18:45:43", "remaining_time": "6:31:10", "throughput": 8523.32, "total_tokens": 575699280} {"current_steps": 565500, "total_steps": 761865, "loss": 1.9904, "lr": 1.5515396409623704e-07, "epoch": 11.1338622984387, "percentage": 74.23, "elapsed_time": "18:45:55", "remaining_time": "6:30:58", "throughput": 8523.33, "total_tokens": 575799888} {"current_steps": 565600, "total_steps": 761865, "loss": 1.9609, "lr": 1.5500469755642702e-07, "epoch": 11.135831151188203, "percentage": 74.24, "elapsed_time": "18:46:07", "remaining_time": "6:30:46", "throughput": 8523.34, "total_tokens": 575902288} {"current_steps": 565700, "total_steps": 761865, "loss": 1.9981, "lr": 1.548554896801582e-07, "epoch": 11.137800003937706, "percentage": 74.25, "elapsed_time": "18:46:19", "remaining_time": "6:30:34", "throughput": 8523.35, "total_tokens": 576002808} {"current_steps": 565800, "total_steps": 761865, "loss": 2.0262, "lr": 1.5470634049280228e-07, "epoch": 11.139768856687208, "percentage": 74.27, "elapsed_time": "18:46:31", "remaining_time": "6:30:22", "throughput": 8523.36, "total_tokens": 576104288} {"current_steps": 565900, "total_steps": 761865, "loss": 2.0091, "lr": 1.545572500197208e-07, "epoch": 11.141737709436711, "percentage": 74.28, "elapsed_time": "18:46:43", "remaining_time": "6:30:10", "throughput": 8523.37, "total_tokens": 576206136} {"current_steps": 566000, "total_steps": 761865, "loss": 1.9671, "lr": 1.5440821828626538e-07, "epoch": 11.143706562186214, "percentage": 74.29, "elapsed_time": "18:46:54", "remaining_time": "6:29:58", "throughput": 8523.39, "total_tokens": 576308536} {"current_steps": 566100, "total_steps": 761865, "loss": 1.98, "lr": 1.542592453177778e-07, "epoch": 11.145675414935717, "percentage": 74.3, "elapsed_time": "18:47:06", "remaining_time": "6:29:46", "throughput": 8523.4, "total_tokens": 576410368} {"current_steps": 566200, "total_steps": 761865, "loss": 1.9989, "lr": 1.541103311395892e-07, "epoch": 11.14764426768522, "percentage": 74.32, "elapsed_time": "18:47:18", "remaining_time": "6:29:34", "throughput": 8523.41, "total_tokens": 576511456} {"current_steps": 566300, "total_steps": 761865, "loss": 1.9486, "lr": 1.5396147577702145e-07, "epoch": 11.149613120434722, "percentage": 74.33, "elapsed_time": "18:47:30", "remaining_time": "6:29:22", "throughput": 8523.42, "total_tokens": 576612360} {"current_steps": 566400, "total_steps": 761865, "loss": 2.0102, "lr": 1.538126792553861e-07, "epoch": 11.151581973184225, "percentage": 74.34, "elapsed_time": "18:47:42", "remaining_time": "6:29:10", "throughput": 8523.43, "total_tokens": 576713904} {"current_steps": 566500, "total_steps": 761865, "loss": 1.9764, "lr": 1.5366394159998498e-07, "epoch": 11.153550825933728, "percentage": 74.36, "elapsed_time": "18:47:54", "remaining_time": "6:28:58", "throughput": 8523.44, "total_tokens": 576815784} {"current_steps": 566600, "total_steps": 761865, "loss": 1.9892, "lr": 1.5351526283610922e-07, "epoch": 11.15551967868323, "percentage": 74.37, "elapsed_time": "18:48:05", "remaining_time": "6:28:46", "throughput": 8523.45, "total_tokens": 576917360} {"current_steps": 566700, "total_steps": 761865, "loss": 1.9749, "lr": 1.533666429890405e-07, "epoch": 11.157488531432735, "percentage": 74.38, "elapsed_time": "18:48:17", "remaining_time": "6:28:34", "throughput": 8523.46, "total_tokens": 577019760} {"current_steps": 566800, "total_steps": 761865, "loss": 1.9923, "lr": 1.5321808208405084e-07, "epoch": 11.159457384182238, "percentage": 74.4, "elapsed_time": "18:48:29", "remaining_time": "6:28:22", "throughput": 8523.48, "total_tokens": 577121680} {"current_steps": 566900, "total_steps": 761865, "loss": 2.0039, "lr": 1.5306958014640125e-07, "epoch": 11.16142623693174, "percentage": 74.41, "elapsed_time": "18:48:41", "remaining_time": "6:28:10", "throughput": 8523.49, "total_tokens": 577224080} {"current_steps": 567000, "total_steps": 761865, "loss": 1.9718, "lr": 1.529211372013436e-07, "epoch": 11.163395089681243, "percentage": 74.42, "elapsed_time": "18:48:53", "remaining_time": "6:27:58", "throughput": 8523.51, "total_tokens": 577326480} {"current_steps": 567100, "total_steps": 761865, "loss": 1.976, "lr": 1.527727532741188e-07, "epoch": 11.165363942430746, "percentage": 74.44, "elapsed_time": "18:49:05", "remaining_time": "6:27:46", "throughput": 8523.52, "total_tokens": 577428200} {"current_steps": 567200, "total_steps": 761865, "loss": 1.9921, "lr": 1.5262442838995903e-07, "epoch": 11.167332795180249, "percentage": 74.45, "elapsed_time": "18:49:17", "remaining_time": "6:27:34", "throughput": 8523.53, "total_tokens": 577530600} {"current_steps": 567300, "total_steps": 761865, "loss": 1.9831, "lr": 1.5247616257408508e-07, "epoch": 11.169301647929752, "percentage": 74.46, "elapsed_time": "18:49:28", "remaining_time": "6:27:22", "throughput": 8523.54, "total_tokens": 577631408} {"current_steps": 567400, "total_steps": 761865, "loss": 1.9984, "lr": 1.5232795585170876e-07, "epoch": 11.171270500679254, "percentage": 74.48, "elapsed_time": "18:49:40", "remaining_time": "6:27:10", "throughput": 8523.54, "total_tokens": 577731176} {"current_steps": 567500, "total_steps": 761865, "loss": 1.9783, "lr": 1.5217980824803078e-07, "epoch": 11.173239353428757, "percentage": 74.49, "elapsed_time": "18:49:52", "remaining_time": "6:26:58", "throughput": 8523.55, "total_tokens": 577833576} {"current_steps": 567600, "total_steps": 761865, "loss": 2.0714, "lr": 1.5203171978824315e-07, "epoch": 11.17520820617826, "percentage": 74.5, "elapsed_time": "18:50:04", "remaining_time": "6:26:46", "throughput": 8523.57, "total_tokens": 577935976} {"current_steps": 567700, "total_steps": 761865, "loss": 1.951, "lr": 1.5188369049752643e-07, "epoch": 11.177177058927763, "percentage": 74.51, "elapsed_time": "18:50:16", "remaining_time": "6:26:34", "throughput": 8523.58, "total_tokens": 578038376} {"current_steps": 567800, "total_steps": 761865, "loss": 1.9677, "lr": 1.51735720401052e-07, "epoch": 11.179145911677265, "percentage": 74.53, "elapsed_time": "18:50:28", "remaining_time": "6:26:22", "throughput": 8523.6, "total_tokens": 578140776} {"current_steps": 567900, "total_steps": 761865, "loss": 2.0331, "lr": 1.5158780952398092e-07, "epoch": 11.181114764426768, "percentage": 74.54, "elapsed_time": "18:50:40", "remaining_time": "6:26:10", "throughput": 8523.61, "total_tokens": 578243176} {"current_steps": 568000, "total_steps": 761865, "loss": 2.016, "lr": 1.5143995789146423e-07, "epoch": 11.18308361717627, "percentage": 74.55, "elapsed_time": "18:50:51", "remaining_time": "6:25:58", "throughput": 8523.62, "total_tokens": 578344376} {"current_steps": 568100, "total_steps": 761865, "loss": 1.9612, "lr": 1.5129216552864294e-07, "epoch": 11.185052469925774, "percentage": 74.57, "elapsed_time": "18:51:03", "remaining_time": "6:25:46", "throughput": 8523.63, "total_tokens": 578446216} {"current_steps": 568200, "total_steps": 761865, "loss": 1.9729, "lr": 1.5114443246064762e-07, "epoch": 11.187021322675276, "percentage": 74.58, "elapsed_time": "18:51:15", "remaining_time": "6:25:34", "throughput": 8523.64, "total_tokens": 578548616} {"current_steps": 568300, "total_steps": 761865, "loss": 1.9807, "lr": 1.5099675871259914e-07, "epoch": 11.18899017542478, "percentage": 74.59, "elapsed_time": "18:51:27", "remaining_time": "6:25:22", "throughput": 8523.66, "total_tokens": 578650312} {"current_steps": 568400, "total_steps": 761865, "loss": 1.978, "lr": 1.5084914430960827e-07, "epoch": 11.190959028174284, "percentage": 74.61, "elapsed_time": "18:51:39", "remaining_time": "6:25:10", "throughput": 8523.67, "total_tokens": 578752168} {"current_steps": 568500, "total_steps": 761865, "loss": 1.9887, "lr": 1.5070158927677568e-07, "epoch": 11.192927880923786, "percentage": 74.62, "elapsed_time": "18:51:51", "remaining_time": "6:24:58", "throughput": 8523.68, "total_tokens": 578853584} {"current_steps": 568600, "total_steps": 761865, "loss": 1.9914, "lr": 1.5055409363919153e-07, "epoch": 11.19489673367329, "percentage": 74.63, "elapsed_time": "18:52:03", "remaining_time": "6:24:46", "throughput": 8523.69, "total_tokens": 578955536} {"current_steps": 568700, "total_steps": 761865, "loss": 2.0241, "lr": 1.5040665742193636e-07, "epoch": 11.196865586422792, "percentage": 74.65, "elapsed_time": "18:52:15", "remaining_time": "6:24:34", "throughput": 8523.7, "total_tokens": 579057936} {"current_steps": 568800, "total_steps": 761865, "loss": 1.989, "lr": 1.5025928065008053e-07, "epoch": 11.198834439172295, "percentage": 74.66, "elapsed_time": "18:52:26", "remaining_time": "6:24:22", "throughput": 8523.72, "total_tokens": 579160336} {"current_steps": 568900, "total_steps": 761865, "loss": 1.9584, "lr": 1.501119633486842e-07, "epoch": 11.200803291921797, "percentage": 74.67, "elapsed_time": "18:52:38", "remaining_time": "6:24:10", "throughput": 8523.73, "total_tokens": 579262048} {"current_steps": 569000, "total_steps": 761865, "loss": 1.9962, "lr": 1.4996470554279755e-07, "epoch": 11.2027721446713, "percentage": 74.69, "elapsed_time": "18:52:50", "remaining_time": "6:23:58", "throughput": 8523.75, "total_tokens": 579364360} {"current_steps": 569100, "total_steps": 761865, "loss": 2.0264, "lr": 1.4981750725746023e-07, "epoch": 11.204740997420803, "percentage": 74.7, "elapsed_time": "18:53:02", "remaining_time": "6:23:46", "throughput": 8523.76, "total_tokens": 579465560} {"current_steps": 569200, "total_steps": 761865, "loss": 1.9811, "lr": 1.496703685177022e-07, "epoch": 11.206709850170306, "percentage": 74.71, "elapsed_time": "18:53:14", "remaining_time": "6:23:34", "throughput": 8523.77, "total_tokens": 579567960} {"current_steps": 569300, "total_steps": 761865, "loss": 2.0287, "lr": 1.495232893485432e-07, "epoch": 11.208678702919809, "percentage": 74.72, "elapsed_time": "18:53:26", "remaining_time": "6:23:23", "throughput": 8523.79, "total_tokens": 579670360} {"current_steps": 569400, "total_steps": 761865, "loss": 1.982, "lr": 1.4937626977499295e-07, "epoch": 11.210647555669311, "percentage": 74.74, "elapsed_time": "18:53:38", "remaining_time": "6:23:11", "throughput": 8523.79, "total_tokens": 579771912} {"current_steps": 569500, "total_steps": 761865, "loss": 1.9384, "lr": 1.4922930982205045e-07, "epoch": 11.212616408418814, "percentage": 74.75, "elapsed_time": "18:53:49", "remaining_time": "6:22:59", "throughput": 8523.81, "total_tokens": 579874312} {"current_steps": 569600, "total_steps": 761865, "loss": 2.005, "lr": 1.490824095147055e-07, "epoch": 11.214585261168317, "percentage": 74.76, "elapsed_time": "18:54:01", "remaining_time": "6:22:47", "throughput": 8523.83, "total_tokens": 579976712} {"current_steps": 569700, "total_steps": 761865, "loss": 2.0216, "lr": 1.4893556887793702e-07, "epoch": 11.21655411391782, "percentage": 74.78, "elapsed_time": "18:54:13", "remaining_time": "6:22:35", "throughput": 8523.84, "total_tokens": 580077800} {"current_steps": 569800, "total_steps": 761865, "loss": 2.024, "lr": 1.487887879367139e-07, "epoch": 11.218522966667322, "percentage": 74.79, "elapsed_time": "18:54:25", "remaining_time": "6:22:23", "throughput": 8523.85, "total_tokens": 580180200} {"current_steps": 569900, "total_steps": 761865, "loss": 2.033, "lr": 1.4864206671599522e-07, "epoch": 11.220491819416825, "percentage": 74.8, "elapsed_time": "18:54:37", "remaining_time": "6:22:11", "throughput": 8523.87, "total_tokens": 580282600} {"current_steps": 570000, "total_steps": 761865, "loss": 2.0203, "lr": 1.4849540524072956e-07, "epoch": 11.222460672166328, "percentage": 74.82, "elapsed_time": "18:54:49", "remaining_time": "6:21:59", "throughput": 8523.88, "total_tokens": 580384776} {"current_steps": 570100, "total_steps": 761865, "loss": 1.9994, "lr": 1.4834880353585573e-07, "epoch": 11.224429524915832, "percentage": 74.83, "elapsed_time": "18:55:01", "remaining_time": "6:21:47", "throughput": 8523.81, "total_tokens": 580486544} {"current_steps": 570200, "total_steps": 761865, "loss": 1.9608, "lr": 1.4820226162630168e-07, "epoch": 11.226398377665335, "percentage": 74.84, "elapsed_time": "18:55:13", "remaining_time": "6:21:35", "throughput": 8523.82, "total_tokens": 580588184} {"current_steps": 570300, "total_steps": 761865, "loss": 1.9514, "lr": 1.4805577953698589e-07, "epoch": 11.228367230414838, "percentage": 74.86, "elapsed_time": "18:55:25", "remaining_time": "6:21:23", "throughput": 8523.84, "total_tokens": 580690584} {"current_steps": 570400, "total_steps": 761865, "loss": 1.9708, "lr": 1.4790935729281627e-07, "epoch": 11.23033608316434, "percentage": 74.87, "elapsed_time": "18:55:37", "remaining_time": "6:21:11", "throughput": 8523.86, "total_tokens": 580792984} {"current_steps": 570500, "total_steps": 761865, "loss": 2.0117, "lr": 1.4776299491869104e-07, "epoch": 11.232304935913843, "percentage": 74.88, "elapsed_time": "18:55:49", "remaining_time": "6:20:59", "throughput": 8523.86, "total_tokens": 580894040} {"current_steps": 570600, "total_steps": 761865, "loss": 1.9612, "lr": 1.4761669243949738e-07, "epoch": 11.234273788663346, "percentage": 74.9, "elapsed_time": "18:56:00", "remaining_time": "6:20:47", "throughput": 8523.87, "total_tokens": 580995568} {"current_steps": 570700, "total_steps": 761865, "loss": 1.9442, "lr": 1.474704498801131e-07, "epoch": 11.236242641412849, "percentage": 74.91, "elapsed_time": "18:56:12", "remaining_time": "6:20:35", "throughput": 8523.89, "total_tokens": 581097968} {"current_steps": 570800, "total_steps": 761865, "loss": 1.986, "lr": 1.4732426726540538e-07, "epoch": 11.238211494162352, "percentage": 74.92, "elapsed_time": "18:56:24", "remaining_time": "6:20:23", "throughput": 8523.9, "total_tokens": 581200368} {"current_steps": 570900, "total_steps": 761865, "loss": 1.9895, "lr": 1.4717814462023142e-07, "epoch": 11.240180346911854, "percentage": 74.93, "elapsed_time": "18:56:36", "remaining_time": "6:20:11", "throughput": 8523.92, "total_tokens": 581302768} {"current_steps": 571000, "total_steps": 761865, "loss": 1.9941, "lr": 1.4703208196943833e-07, "epoch": 11.242149199661357, "percentage": 74.95, "elapsed_time": "18:56:48", "remaining_time": "6:19:59", "throughput": 8523.93, "total_tokens": 581404080} {"current_steps": 571100, "total_steps": 761865, "loss": 1.9897, "lr": 1.4688607933786247e-07, "epoch": 11.24411805241086, "percentage": 74.96, "elapsed_time": "18:57:00", "remaining_time": "6:19:47", "throughput": 8523.93, "total_tokens": 581505192} {"current_steps": 571200, "total_steps": 761865, "loss": 2.0142, "lr": 1.4674013675033047e-07, "epoch": 11.246086905160363, "percentage": 74.97, "elapsed_time": "18:57:12", "remaining_time": "6:19:35", "throughput": 8523.95, "total_tokens": 581607592} {"current_steps": 571300, "total_steps": 761865, "loss": 1.9901, "lr": 1.465942542316587e-07, "epoch": 11.248055757909865, "percentage": 74.99, "elapsed_time": "18:57:23", "remaining_time": "6:19:23", "throughput": 8523.96, "total_tokens": 581708536} {"current_steps": 571400, "total_steps": 761865, "loss": 2.0462, "lr": 1.464484318066534e-07, "epoch": 11.250024610659368, "percentage": 75.0, "elapsed_time": "18:57:35", "remaining_time": "6:19:11", "throughput": 8523.97, "total_tokens": 581810296} {"current_steps": 571500, "total_steps": 761865, "loss": 1.995, "lr": 1.4630266950011012e-07, "epoch": 11.251993463408871, "percentage": 75.01, "elapsed_time": "18:57:47", "remaining_time": "6:18:59", "throughput": 8523.97, "total_tokens": 581910408} {"current_steps": 571600, "total_steps": 761865, "loss": 1.9868, "lr": 1.461569673368147e-07, "epoch": 11.253962316158374, "percentage": 75.03, "elapsed_time": "18:57:59", "remaining_time": "6:18:47", "throughput": 8523.98, "total_tokens": 582012000} {"current_steps": 571700, "total_steps": 761865, "loss": 1.9675, "lr": 1.460113253415425e-07, "epoch": 11.255931168907878, "percentage": 75.04, "elapsed_time": "18:58:11", "remaining_time": "6:18:35", "throughput": 8523.99, "total_tokens": 582113920} {"current_steps": 571800, "total_steps": 761865, "loss": 1.9635, "lr": 1.458657435390588e-07, "epoch": 11.257900021657381, "percentage": 75.05, "elapsed_time": "18:58:23", "remaining_time": "6:18:23", "throughput": 8524.01, "total_tokens": 582216320} {"current_steps": 571900, "total_steps": 761865, "loss": 1.9334, "lr": 1.457202219541186e-07, "epoch": 11.259868874406884, "percentage": 75.07, "elapsed_time": "18:58:34", "remaining_time": "6:18:11", "throughput": 8524.02, "total_tokens": 582317976} {"current_steps": 572000, "total_steps": 761865, "loss": 1.9132, "lr": 1.4557476061146624e-07, "epoch": 11.261837727156387, "percentage": 75.08, "elapsed_time": "18:58:46", "remaining_time": "6:17:59", "throughput": 8524.03, "total_tokens": 582419872} {"current_steps": 572100, "total_steps": 761865, "loss": 1.9686, "lr": 1.4542935953583673e-07, "epoch": 11.26380657990589, "percentage": 75.09, "elapsed_time": "18:58:58", "remaining_time": "6:17:47", "throughput": 8524.04, "total_tokens": 582521016} {"current_steps": 572200, "total_steps": 761865, "loss": 1.9833, "lr": 1.4528401875195395e-07, "epoch": 11.265775432655392, "percentage": 75.11, "elapsed_time": "18:59:10", "remaining_time": "6:17:35", "throughput": 8524.05, "total_tokens": 582623416} {"current_steps": 572300, "total_steps": 761865, "loss": 1.9421, "lr": 1.4513873828453215e-07, "epoch": 11.267744285404895, "percentage": 75.12, "elapsed_time": "18:59:22", "remaining_time": "6:17:23", "throughput": 8524.06, "total_tokens": 582725088} {"current_steps": 572400, "total_steps": 761865, "loss": 1.9725, "lr": 1.449935181582745e-07, "epoch": 11.269713138154398, "percentage": 75.13, "elapsed_time": "18:59:34", "remaining_time": "6:17:11", "throughput": 8524.08, "total_tokens": 582826864} {"current_steps": 572500, "total_steps": 761865, "loss": 2.0038, "lr": 1.4484835839787512e-07, "epoch": 11.2716819909039, "percentage": 75.14, "elapsed_time": "18:59:46", "remaining_time": "6:16:59", "throughput": 8524.09, "total_tokens": 582929264} {"current_steps": 572600, "total_steps": 761865, "loss": 1.9878, "lr": 1.4470325902801684e-07, "epoch": 11.273650843653403, "percentage": 75.16, "elapsed_time": "18:59:57", "remaining_time": "6:16:47", "throughput": 8524.1, "total_tokens": 583030960} {"current_steps": 572700, "total_steps": 761865, "loss": 2.0348, "lr": 1.4455822007337271e-07, "epoch": 11.275619696402906, "percentage": 75.17, "elapsed_time": "19:00:09", "remaining_time": "6:16:35", "throughput": 8524.11, "total_tokens": 583131856} {"current_steps": 572800, "total_steps": 761865, "loss": 1.9922, "lr": 1.4441324155860506e-07, "epoch": 11.277588549152409, "percentage": 75.18, "elapsed_time": "19:00:21", "remaining_time": "6:16:24", "throughput": 8524.12, "total_tokens": 583233440} {"current_steps": 572900, "total_steps": 761865, "loss": 2.0571, "lr": 1.4426832350836671e-07, "epoch": 11.279557401901911, "percentage": 75.2, "elapsed_time": "19:00:33", "remaining_time": "6:16:12", "throughput": 8524.13, "total_tokens": 583335224} {"current_steps": 573000, "total_steps": 761865, "loss": 1.9999, "lr": 1.4412346594729967e-07, "epoch": 11.281526254651414, "percentage": 75.21, "elapsed_time": "19:00:45", "remaining_time": "6:16:00", "throughput": 8524.15, "total_tokens": 583437624} {"current_steps": 573100, "total_steps": 761865, "loss": 1.9369, "lr": 1.439786689000355e-07, "epoch": 11.283495107400917, "percentage": 75.22, "elapsed_time": "19:00:57", "remaining_time": "6:15:48", "throughput": 8524.16, "total_tokens": 583540024} {"current_steps": 573200, "total_steps": 761865, "loss": 1.9874, "lr": 1.4383393239119585e-07, "epoch": 11.28546396015042, "percentage": 75.24, "elapsed_time": "19:01:09", "remaining_time": "6:15:36", "throughput": 8524.17, "total_tokens": 583641720} {"current_steps": 573300, "total_steps": 761865, "loss": 1.9549, "lr": 1.4368925644539199e-07, "epoch": 11.287432812899922, "percentage": 75.25, "elapsed_time": "19:01:20", "remaining_time": "6:15:24", "throughput": 8524.19, "total_tokens": 583744120} {"current_steps": 573400, "total_steps": 761865, "loss": 1.9397, "lr": 1.4354464108722497e-07, "epoch": 11.289401665649427, "percentage": 75.26, "elapsed_time": "19:01:32", "remaining_time": "6:15:12", "throughput": 8524.2, "total_tokens": 583846520} {"current_steps": 573500, "total_steps": 761865, "loss": 1.9893, "lr": 1.4340008634128503e-07, "epoch": 11.29137051839893, "percentage": 75.28, "elapsed_time": "19:01:44", "remaining_time": "6:15:00", "throughput": 8524.21, "total_tokens": 583948448} {"current_steps": 573600, "total_steps": 761865, "loss": 1.9454, "lr": 1.4325559223215278e-07, "epoch": 11.293339371148432, "percentage": 75.29, "elapsed_time": "19:01:56", "remaining_time": "6:14:48", "throughput": 8524.23, "total_tokens": 584050848} {"current_steps": 573700, "total_steps": 761865, "loss": 2.02, "lr": 1.4311115878439812e-07, "epoch": 11.295308223897935, "percentage": 75.3, "elapsed_time": "19:02:08", "remaining_time": "6:14:36", "throughput": 8524.24, "total_tokens": 584153248} {"current_steps": 573800, "total_steps": 761865, "loss": 1.997, "lr": 1.429667860225807e-07, "epoch": 11.297277076647438, "percentage": 75.32, "elapsed_time": "19:02:20", "remaining_time": "6:14:24", "throughput": 8524.26, "total_tokens": 584255008} {"current_steps": 573900, "total_steps": 761865, "loss": 1.9901, "lr": 1.428224739712502e-07, "epoch": 11.29924592939694, "percentage": 75.33, "elapsed_time": "19:02:32", "remaining_time": "6:14:12", "throughput": 8524.26, "total_tokens": 584356096} {"current_steps": 574000, "total_steps": 761865, "loss": 1.9713, "lr": 1.426782226549453e-07, "epoch": 11.301214782146443, "percentage": 75.34, "elapsed_time": "19:02:43", "remaining_time": "6:14:00", "throughput": 8524.27, "total_tokens": 584457408} {"current_steps": 574100, "total_steps": 761865, "loss": 1.9918, "lr": 1.4253403209819476e-07, "epoch": 11.303183634895946, "percentage": 75.35, "elapsed_time": "19:02:55", "remaining_time": "6:13:48", "throughput": 8524.29, "total_tokens": 584559808} {"current_steps": 574200, "total_steps": 761865, "loss": 1.9851, "lr": 1.4238990232551713e-07, "epoch": 11.305152487645449, "percentage": 75.37, "elapsed_time": "19:03:07", "remaining_time": "6:13:36", "throughput": 8524.29, "total_tokens": 584661440} {"current_steps": 574300, "total_steps": 761865, "loss": 1.994, "lr": 1.4224583336142043e-07, "epoch": 11.307121340394952, "percentage": 75.38, "elapsed_time": "19:03:19", "remaining_time": "6:13:24", "throughput": 8524.3, "total_tokens": 584762864} {"current_steps": 574400, "total_steps": 761865, "loss": 2.0, "lr": 1.4210182523040226e-07, "epoch": 11.309090193144455, "percentage": 75.39, "elapsed_time": "19:03:31", "remaining_time": "6:13:12", "throughput": 8524.32, "total_tokens": 584865264} {"current_steps": 574500, "total_steps": 761865, "loss": 1.9854, "lr": 1.4195787795695007e-07, "epoch": 11.311059045893957, "percentage": 75.41, "elapsed_time": "19:03:43", "remaining_time": "6:13:00", "throughput": 8524.32, "total_tokens": 584966056} {"current_steps": 574600, "total_steps": 761865, "loss": 1.9642, "lr": 1.4181399156554087e-07, "epoch": 11.31302789864346, "percentage": 75.42, "elapsed_time": "19:03:54", "remaining_time": "6:12:48", "throughput": 8524.32, "total_tokens": 585065648} {"current_steps": 574700, "total_steps": 761865, "loss": 2.0091, "lr": 1.4167016608064142e-07, "epoch": 11.314996751392963, "percentage": 75.43, "elapsed_time": "19:04:06", "remaining_time": "6:12:36", "throughput": 8524.32, "total_tokens": 585166184} {"current_steps": 574800, "total_steps": 761865, "loss": 2.0012, "lr": 1.4152640152670782e-07, "epoch": 11.316965604142466, "percentage": 75.45, "elapsed_time": "19:04:18", "remaining_time": "6:12:24", "throughput": 8524.34, "total_tokens": 585268584} {"current_steps": 574900, "total_steps": 761865, "loss": 1.9249, "lr": 1.4138269792818596e-07, "epoch": 11.318934456891968, "percentage": 75.46, "elapsed_time": "19:04:30", "remaining_time": "6:12:12", "throughput": 8524.35, "total_tokens": 585370144} {"current_steps": 575000, "total_steps": 761865, "loss": 2.0058, "lr": 1.412390553095119e-07, "epoch": 11.320903309641471, "percentage": 75.47, "elapsed_time": "19:04:42", "remaining_time": "6:12:00", "throughput": 8524.36, "total_tokens": 585471936} {"current_steps": 575100, "total_steps": 761865, "loss": 2.0141, "lr": 1.4109547369511044e-07, "epoch": 11.322872162390976, "percentage": 75.49, "elapsed_time": "19:04:54", "remaining_time": "6:11:48", "throughput": 8524.28, "total_tokens": 585574336} {"current_steps": 575200, "total_steps": 761865, "loss": 1.9526, "lr": 1.4095195310939668e-07, "epoch": 11.324841015140478, "percentage": 75.5, "elapsed_time": "19:05:06", "remaining_time": "6:11:36", "throughput": 8524.28, "total_tokens": 585676200} {"current_steps": 575300, "total_steps": 761865, "loss": 2.0132, "lr": 1.408084935767746e-07, "epoch": 11.326809867889981, "percentage": 75.51, "elapsed_time": "19:05:14", "remaining_time": "6:11:23", "throughput": 8524.78, "total_tokens": 585777960} {"current_steps": 575400, "total_steps": 761865, "loss": 1.9714, "lr": 1.4066509512163898e-07, "epoch": 11.328778720639484, "percentage": 75.53, "elapsed_time": "19:05:26", "remaining_time": "6:11:11", "throughput": 8524.79, "total_tokens": 585879760} {"current_steps": 575500, "total_steps": 761865, "loss": 1.9772, "lr": 1.40521757768373e-07, "epoch": 11.330747573388987, "percentage": 75.54, "elapsed_time": "19:05:38", "remaining_time": "6:10:59", "throughput": 8524.8, "total_tokens": 585981528} {"current_steps": 575600, "total_steps": 761865, "loss": 1.9412, "lr": 1.4037848154135028e-07, "epoch": 11.33271642613849, "percentage": 75.55, "elapsed_time": "19:05:50", "remaining_time": "6:10:47", "throughput": 8524.81, "total_tokens": 586083232} {"current_steps": 575700, "total_steps": 761865, "loss": 1.9495, "lr": 1.4023526646493328e-07, "epoch": 11.334685278887992, "percentage": 75.56, "elapsed_time": "19:06:02", "remaining_time": "6:10:35", "throughput": 8524.83, "total_tokens": 586185632} {"current_steps": 575800, "total_steps": 761865, "loss": 1.9981, "lr": 1.4009211256347492e-07, "epoch": 11.336654131637495, "percentage": 75.58, "elapsed_time": "19:06:14", "remaining_time": "6:10:23", "throughput": 8524.84, "total_tokens": 586287736} {"current_steps": 575900, "total_steps": 761865, "loss": 1.9876, "lr": 1.399490198613174e-07, "epoch": 11.338622984386998, "percentage": 75.59, "elapsed_time": "19:06:25", "remaining_time": "6:10:11", "throughput": 8524.85, "total_tokens": 586390136} {"current_steps": 576000, "total_steps": 761865, "loss": 1.9817, "lr": 1.3980598838279212e-07, "epoch": 11.3405918371365, "percentage": 75.6, "elapsed_time": "19:06:37", "remaining_time": "6:09:59", "throughput": 8524.87, "total_tokens": 586492536} {"current_steps": 576100, "total_steps": 761865, "loss": 1.9608, "lr": 1.3966301815222049e-07, "epoch": 11.342560689886003, "percentage": 75.62, "elapsed_time": "19:06:49", "remaining_time": "6:09:47", "throughput": 8524.88, "total_tokens": 586594272} {"current_steps": 576200, "total_steps": 761865, "loss": 2.005, "lr": 1.3952010919391344e-07, "epoch": 11.344529542635506, "percentage": 75.63, "elapsed_time": "19:07:01", "remaining_time": "6:09:35", "throughput": 8524.89, "total_tokens": 586696672} {"current_steps": 576300, "total_steps": 761865, "loss": 1.9469, "lr": 1.393772615321715e-07, "epoch": 11.346498395385009, "percentage": 75.64, "elapsed_time": "19:07:13", "remaining_time": "6:09:23", "throughput": 8524.9, "total_tokens": 586799072} {"current_steps": 576400, "total_steps": 761865, "loss": 2.0158, "lr": 1.3923447519128438e-07, "epoch": 11.348467248134511, "percentage": 75.66, "elapsed_time": "19:07:25", "remaining_time": "6:09:11", "throughput": 8524.91, "total_tokens": 586900176} {"current_steps": 576500, "total_steps": 761865, "loss": 1.9645, "lr": 1.3909175019553206e-07, "epoch": 11.350436100884014, "percentage": 75.67, "elapsed_time": "19:07:37", "remaining_time": "6:09:00", "throughput": 8524.92, "total_tokens": 587002576} {"current_steps": 576600, "total_steps": 761865, "loss": 1.9708, "lr": 1.3894908656918346e-07, "epoch": 11.352404953633517, "percentage": 75.68, "elapsed_time": "19:07:49", "remaining_time": "6:08:48", "throughput": 8524.93, "total_tokens": 587104016} {"current_steps": 576700, "total_steps": 761865, "loss": 1.9898, "lr": 1.3880648433649767e-07, "epoch": 11.35437380638302, "percentage": 75.7, "elapsed_time": "19:08:00", "remaining_time": "6:08:36", "throughput": 8524.94, "total_tokens": 587205496} {"current_steps": 576800, "total_steps": 761865, "loss": 1.9464, "lr": 1.3866394352172262e-07, "epoch": 11.356342659132524, "percentage": 75.71, "elapsed_time": "19:08:12", "remaining_time": "6:08:24", "throughput": 8524.96, "total_tokens": 587307896} {"current_steps": 576900, "total_steps": 761865, "loss": 1.9639, "lr": 1.3852146414909626e-07, "epoch": 11.358311511882027, "percentage": 75.72, "elapsed_time": "19:08:24", "remaining_time": "6:08:12", "throughput": 8524.97, "total_tokens": 587410296} {"current_steps": 577000, "total_steps": 761865, "loss": 1.9839, "lr": 1.3837904624284613e-07, "epoch": 11.36028036463153, "percentage": 75.74, "elapsed_time": "19:08:36", "remaining_time": "6:08:00", "throughput": 8524.98, "total_tokens": 587511824} {"current_steps": 577100, "total_steps": 761865, "loss": 1.923, "lr": 1.3823668982718912e-07, "epoch": 11.362249217381033, "percentage": 75.75, "elapsed_time": "19:08:48", "remaining_time": "6:07:48", "throughput": 8524.99, "total_tokens": 587614224} {"current_steps": 577200, "total_steps": 761865, "loss": 1.999, "lr": 1.380943949263319e-07, "epoch": 11.364218070130535, "percentage": 75.76, "elapsed_time": "19:09:00", "remaining_time": "6:07:36", "throughput": 8525.0, "total_tokens": 587716080} {"current_steps": 577300, "total_steps": 761865, "loss": 1.9936, "lr": 1.379521615644702e-07, "epoch": 11.366186922880038, "percentage": 75.77, "elapsed_time": "19:09:12", "remaining_time": "6:07:24", "throughput": 8525.02, "total_tokens": 587818480} {"current_steps": 577400, "total_steps": 761865, "loss": 1.9804, "lr": 1.3780998976578984e-07, "epoch": 11.36815577562954, "percentage": 75.79, "elapsed_time": "19:09:24", "remaining_time": "6:07:12", "throughput": 8525.03, "total_tokens": 587919928} {"current_steps": 577500, "total_steps": 761865, "loss": 1.981, "lr": 1.376678795544658e-07, "epoch": 11.370124628379044, "percentage": 75.8, "elapsed_time": "19:09:35", "remaining_time": "6:07:00", "throughput": 8525.04, "total_tokens": 588022328} {"current_steps": 577600, "total_steps": 761865, "loss": 2.0243, "lr": 1.3752583095466296e-07, "epoch": 11.372093481128546, "percentage": 75.81, "elapsed_time": "19:09:47", "remaining_time": "6:06:48", "throughput": 8525.05, "total_tokens": 588123872} {"current_steps": 577700, "total_steps": 761865, "loss": 1.987, "lr": 1.3738384399053504e-07, "epoch": 11.374062333878049, "percentage": 75.83, "elapsed_time": "19:09:59", "remaining_time": "6:06:36", "throughput": 8525.06, "total_tokens": 588226272} {"current_steps": 577800, "total_steps": 761865, "loss": 2.0012, "lr": 1.3724191868622626e-07, "epoch": 11.376031186627552, "percentage": 75.84, "elapsed_time": "19:10:11", "remaining_time": "6:06:24", "throughput": 8525.07, "total_tokens": 588327776} {"current_steps": 577900, "total_steps": 761865, "loss": 1.9756, "lr": 1.3710005506586948e-07, "epoch": 11.378000039377055, "percentage": 75.85, "elapsed_time": "19:10:23", "remaining_time": "6:06:12", "throughput": 8525.08, "total_tokens": 588429640} {"current_steps": 578000, "total_steps": 761865, "loss": 1.966, "lr": 1.3695825315358745e-07, "epoch": 11.379968892126557, "percentage": 75.87, "elapsed_time": "19:10:35", "remaining_time": "6:06:00", "throughput": 8525.1, "total_tokens": 588532040} {"current_steps": 578100, "total_steps": 761865, "loss": 1.9319, "lr": 1.368165129734924e-07, "epoch": 11.38193774487606, "percentage": 75.88, "elapsed_time": "19:10:47", "remaining_time": "6:05:48", "throughput": 8525.11, "total_tokens": 588634440} {"current_steps": 578200, "total_steps": 761865, "loss": 1.9359, "lr": 1.3667483454968614e-07, "epoch": 11.383906597625563, "percentage": 75.89, "elapsed_time": "19:10:59", "remaining_time": "6:05:36", "throughput": 8525.13, "total_tokens": 588736840} {"current_steps": 578300, "total_steps": 761865, "loss": 1.9927, "lr": 1.3653321790626e-07, "epoch": 11.385875450375066, "percentage": 75.91, "elapsed_time": "19:11:10", "remaining_time": "6:05:24", "throughput": 8525.13, "total_tokens": 588838304} {"current_steps": 578400, "total_steps": 761865, "loss": 1.9792, "lr": 1.3639166306729432e-07, "epoch": 11.38784430312457, "percentage": 75.92, "elapsed_time": "19:11:22", "remaining_time": "6:05:12", "throughput": 8525.14, "total_tokens": 588939856} {"current_steps": 578500, "total_steps": 761865, "loss": 2.031, "lr": 1.3625017005685958e-07, "epoch": 11.389813155874073, "percentage": 75.93, "elapsed_time": "19:11:34", "remaining_time": "6:05:00", "throughput": 8525.14, "total_tokens": 589040408} {"current_steps": 578600, "total_steps": 761865, "loss": 2.0541, "lr": 1.361087388990154e-07, "epoch": 11.391782008623576, "percentage": 75.95, "elapsed_time": "19:11:46", "remaining_time": "6:04:48", "throughput": 8525.15, "total_tokens": 589141480} {"current_steps": 578700, "total_steps": 761865, "loss": 1.9962, "lr": 1.3596736961781115e-07, "epoch": 11.393750861373078, "percentage": 75.96, "elapsed_time": "19:11:58", "remaining_time": "6:04:36", "throughput": 8525.16, "total_tokens": 589243880} {"current_steps": 578800, "total_steps": 761865, "loss": 1.9847, "lr": 1.358260622372851e-07, "epoch": 11.395719714122581, "percentage": 75.97, "elapsed_time": "19:12:10", "remaining_time": "6:04:24", "throughput": 8525.17, "total_tokens": 589345728} {"current_steps": 578900, "total_steps": 761865, "loss": 2.0179, "lr": 1.356848167814656e-07, "epoch": 11.397688566872084, "percentage": 75.98, "elapsed_time": "19:12:21", "remaining_time": "6:04:12", "throughput": 8525.18, "total_tokens": 589446256} {"current_steps": 579000, "total_steps": 761865, "loss": 1.9559, "lr": 1.3554363327437023e-07, "epoch": 11.399657419621587, "percentage": 76.0, "elapsed_time": "19:12:33", "remaining_time": "6:04:00", "throughput": 8525.19, "total_tokens": 589548656} {"current_steps": 579100, "total_steps": 761865, "loss": 1.9844, "lr": 1.3540251174000606e-07, "epoch": 11.40162627237109, "percentage": 76.01, "elapsed_time": "19:12:45", "remaining_time": "6:03:48", "throughput": 8525.2, "total_tokens": 589649688} {"current_steps": 579200, "total_steps": 761865, "loss": 2.0004, "lr": 1.3526145220236973e-07, "epoch": 11.403595125120592, "percentage": 76.02, "elapsed_time": "19:12:57", "remaining_time": "6:03:36", "throughput": 8525.2, "total_tokens": 589749616} {"current_steps": 579300, "total_steps": 761865, "loss": 2.0328, "lr": 1.3512045468544703e-07, "epoch": 11.405563977870095, "percentage": 76.04, "elapsed_time": "19:13:09", "remaining_time": "6:03:24", "throughput": 8525.21, "total_tokens": 589852016} {"current_steps": 579400, "total_steps": 761865, "loss": 2.0259, "lr": 1.3497951921321337e-07, "epoch": 11.407532830619598, "percentage": 76.05, "elapsed_time": "19:13:20", "remaining_time": "6:03:12", "throughput": 8525.22, "total_tokens": 589953456} {"current_steps": 579500, "total_steps": 761865, "loss": 2.0185, "lr": 1.3483864580963384e-07, "epoch": 11.4095016833691, "percentage": 76.06, "elapsed_time": "19:13:32", "remaining_time": "6:03:00", "throughput": 8525.23, "total_tokens": 590055088} {"current_steps": 579600, "total_steps": 761865, "loss": 2.0111, "lr": 1.346978344986628e-07, "epoch": 11.411470536118603, "percentage": 76.08, "elapsed_time": "19:13:44", "remaining_time": "6:02:48", "throughput": 8525.24, "total_tokens": 590157488} {"current_steps": 579700, "total_steps": 761865, "loss": 1.9501, "lr": 1.3455708530424375e-07, "epoch": 11.413439388868106, "percentage": 76.09, "elapsed_time": "19:13:56", "remaining_time": "6:02:36", "throughput": 8525.26, "total_tokens": 590259344} {"current_steps": 579800, "total_steps": 761865, "loss": 2.0623, "lr": 1.3441639825031003e-07, "epoch": 11.415408241617609, "percentage": 76.1, "elapsed_time": "19:14:08", "remaining_time": "6:02:24", "throughput": 8525.26, "total_tokens": 590360504} {"current_steps": 579900, "total_steps": 761865, "loss": 1.9529, "lr": 1.3427577336078431e-07, "epoch": 11.417377094367112, "percentage": 76.12, "elapsed_time": "19:14:20", "remaining_time": "6:02:12", "throughput": 8525.27, "total_tokens": 590462464} {"current_steps": 580000, "total_steps": 761865, "loss": 2.0399, "lr": 1.3413521065957873e-07, "epoch": 11.419345947116614, "percentage": 76.13, "elapsed_time": "19:14:32", "remaining_time": "6:02:00", "throughput": 8525.29, "total_tokens": 590564472} {"current_steps": 580100, "total_steps": 761865, "loss": 2.0402, "lr": 1.3399471017059483e-07, "epoch": 11.421314799866119, "percentage": 76.14, "elapsed_time": "19:14:44", "remaining_time": "6:01:49", "throughput": 8525.22, "total_tokens": 590665696} {"current_steps": 580200, "total_steps": 761865, "loss": 2.0511, "lr": 1.3385427191772315e-07, "epoch": 11.423283652615622, "percentage": 76.16, "elapsed_time": "19:14:56", "remaining_time": "6:01:37", "throughput": 8525.23, "total_tokens": 590768096} {"current_steps": 580300, "total_steps": 761865, "loss": 1.9878, "lr": 1.3371389592484461e-07, "epoch": 11.425252505365124, "percentage": 76.17, "elapsed_time": "19:15:08", "remaining_time": "6:01:25", "throughput": 8525.24, "total_tokens": 590869752} {"current_steps": 580400, "total_steps": 761865, "loss": 1.9829, "lr": 1.3357358221582854e-07, "epoch": 11.427221358114627, "percentage": 76.18, "elapsed_time": "19:15:20", "remaining_time": "6:01:13", "throughput": 8525.26, "total_tokens": 590972152} {"current_steps": 580500, "total_steps": 761865, "loss": 1.9853, "lr": 1.3343333081453434e-07, "epoch": 11.42919021086413, "percentage": 76.19, "elapsed_time": "19:15:32", "remaining_time": "6:01:01", "throughput": 8525.27, "total_tokens": 591074552} {"current_steps": 580600, "total_steps": 761865, "loss": 1.9869, "lr": 1.3329314174481022e-07, "epoch": 11.431159063613633, "percentage": 76.21, "elapsed_time": "19:15:43", "remaining_time": "6:00:49", "throughput": 8525.28, "total_tokens": 591176088} {"current_steps": 580700, "total_steps": 761865, "loss": 1.9784, "lr": 1.3315301503049464e-07, "epoch": 11.433127916363135, "percentage": 76.22, "elapsed_time": "19:15:55", "remaining_time": "6:00:37", "throughput": 8525.29, "total_tokens": 591278480} {"current_steps": 580800, "total_steps": 761865, "loss": 1.9742, "lr": 1.3301295069541464e-07, "epoch": 11.435096769112638, "percentage": 76.23, "elapsed_time": "19:16:07", "remaining_time": "6:00:25", "throughput": 8525.3, "total_tokens": 591380304} {"current_steps": 580900, "total_steps": 761865, "loss": 1.9576, "lr": 1.32872948763387e-07, "epoch": 11.437065621862141, "percentage": 76.25, "elapsed_time": "19:16:19", "remaining_time": "6:00:13", "throughput": 8525.31, "total_tokens": 591481872} {"current_steps": 581000, "total_steps": 761865, "loss": 1.982, "lr": 1.3273300925821795e-07, "epoch": 11.439034474611644, "percentage": 76.26, "elapsed_time": "19:16:31", "remaining_time": "6:00:01", "throughput": 8525.33, "total_tokens": 591583600} {"current_steps": 581100, "total_steps": 761865, "loss": 2.0285, "lr": 1.3259313220370298e-07, "epoch": 11.441003327361146, "percentage": 76.27, "elapsed_time": "19:16:43", "remaining_time": "5:59:49", "throughput": 8525.34, "total_tokens": 591686000} {"current_steps": 581200, "total_steps": 761865, "loss": 2.0074, "lr": 1.3245331762362723e-07, "epoch": 11.44297218011065, "percentage": 76.29, "elapsed_time": "19:16:55", "remaining_time": "5:59:37", "throughput": 8525.36, "total_tokens": 591788400} {"current_steps": 581300, "total_steps": 761865, "loss": 2.0276, "lr": 1.323135655417646e-07, "epoch": 11.444941032860152, "percentage": 76.3, "elapsed_time": "19:17:06", "remaining_time": "5:59:25", "throughput": 8525.37, "total_tokens": 591890496} {"current_steps": 581400, "total_steps": 761865, "loss": 2.017, "lr": 1.3217387598187895e-07, "epoch": 11.446909885609655, "percentage": 76.31, "elapsed_time": "19:17:18", "remaining_time": "5:59:13", "throughput": 8525.38, "total_tokens": 591991800} {"current_steps": 581500, "total_steps": 761865, "loss": 1.9957, "lr": 1.320342489677233e-07, "epoch": 11.448878738359157, "percentage": 76.33, "elapsed_time": "19:17:30", "remaining_time": "5:59:01", "throughput": 8525.39, "total_tokens": 592093008} {"current_steps": 581600, "total_steps": 761865, "loss": 1.9603, "lr": 1.318946845230402e-07, "epoch": 11.45084759110866, "percentage": 76.34, "elapsed_time": "19:17:42", "remaining_time": "5:58:49", "throughput": 8525.4, "total_tokens": 592194024} {"current_steps": 581700, "total_steps": 761865, "loss": 1.9894, "lr": 1.317551826715611e-07, "epoch": 11.452816443858163, "percentage": 76.35, "elapsed_time": "19:17:54", "remaining_time": "5:58:37", "throughput": 8525.41, "total_tokens": 592295600} {"current_steps": 581800, "total_steps": 761865, "loss": 1.9842, "lr": 1.3161574343700727e-07, "epoch": 11.454785296607668, "percentage": 76.37, "elapsed_time": "19:18:06", "remaining_time": "5:58:25", "throughput": 8525.41, "total_tokens": 592396872} {"current_steps": 581900, "total_steps": 761865, "loss": 2.0282, "lr": 1.3147636684308917e-07, "epoch": 11.45675414935717, "percentage": 76.38, "elapsed_time": "19:18:17", "remaining_time": "5:58:13", "throughput": 8525.42, "total_tokens": 592498104} {"current_steps": 582000, "total_steps": 761865, "loss": 1.9633, "lr": 1.313370529135066e-07, "epoch": 11.458723002106673, "percentage": 76.39, "elapsed_time": "19:18:29", "remaining_time": "5:58:01", "throughput": 8525.42, "total_tokens": 592597736} {"current_steps": 582100, "total_steps": 761865, "loss": 1.9863, "lr": 1.3119780167194893e-07, "epoch": 11.460691854856176, "percentage": 76.4, "elapsed_time": "19:18:41", "remaining_time": "5:57:49", "throughput": 8525.43, "total_tokens": 592700136} {"current_steps": 582200, "total_steps": 761865, "loss": 1.9724, "lr": 1.3105861314209426e-07, "epoch": 11.462660707605679, "percentage": 76.42, "elapsed_time": "19:18:53", "remaining_time": "5:57:37", "throughput": 8525.44, "total_tokens": 592801664} {"current_steps": 582300, "total_steps": 761865, "loss": 2.0213, "lr": 1.3091948734761065e-07, "epoch": 11.464629560355181, "percentage": 76.43, "elapsed_time": "19:19:05", "remaining_time": "5:57:25", "throughput": 8525.46, "total_tokens": 592903792} {"current_steps": 582400, "total_steps": 761865, "loss": 1.9787, "lr": 1.3078042431215524e-07, "epoch": 11.466598413104684, "percentage": 76.44, "elapsed_time": "19:19:16", "remaining_time": "5:57:13", "throughput": 8525.47, "total_tokens": 593005504} {"current_steps": 582500, "total_steps": 761865, "loss": 1.9885, "lr": 1.3064142405937472e-07, "epoch": 11.468567265854187, "percentage": 76.46, "elapsed_time": "19:19:28", "remaining_time": "5:57:01", "throughput": 8525.48, "total_tokens": 593106544} {"current_steps": 582600, "total_steps": 761865, "loss": 1.9836, "lr": 1.3050248661290452e-07, "epoch": 11.47053611860369, "percentage": 76.47, "elapsed_time": "19:19:40", "remaining_time": "5:56:49", "throughput": 8525.49, "total_tokens": 593208352} {"current_steps": 582700, "total_steps": 761865, "loss": 1.9239, "lr": 1.3036361199637002e-07, "epoch": 11.472504971353192, "percentage": 76.48, "elapsed_time": "19:19:52", "remaining_time": "5:56:37", "throughput": 8525.5, "total_tokens": 593310000} {"current_steps": 582800, "total_steps": 761865, "loss": 2.0132, "lr": 1.3022480023338567e-07, "epoch": 11.474473824102695, "percentage": 76.5, "elapsed_time": "19:20:04", "remaining_time": "5:56:25", "throughput": 8525.5, "total_tokens": 593411416} {"current_steps": 582900, "total_steps": 761865, "loss": 1.9853, "lr": 1.300860513475553e-07, "epoch": 11.476442676852198, "percentage": 76.51, "elapsed_time": "19:20:16", "remaining_time": "5:56:13", "throughput": 8525.52, "total_tokens": 593513064} {"current_steps": 583000, "total_steps": 761865, "loss": 1.975, "lr": 1.299473653624718e-07, "epoch": 11.4784115296017, "percentage": 76.52, "elapsed_time": "19:20:27", "remaining_time": "5:56:01", "throughput": 8525.53, "total_tokens": 593615464} {"current_steps": 583100, "total_steps": 761865, "loss": 1.9976, "lr": 1.2980874230171751e-07, "epoch": 11.480380382351203, "percentage": 76.54, "elapsed_time": "19:20:39", "remaining_time": "5:55:49", "throughput": 8525.53, "total_tokens": 593716144} {"current_steps": 583200, "total_steps": 761865, "loss": 1.9811, "lr": 1.296701821888645e-07, "epoch": 11.482349235100706, "percentage": 76.55, "elapsed_time": "19:20:51", "remaining_time": "5:55:37", "throughput": 8525.55, "total_tokens": 593818544} {"current_steps": 583300, "total_steps": 761865, "loss": 1.9803, "lr": 1.295316850474734e-07, "epoch": 11.484318087850209, "percentage": 76.56, "elapsed_time": "19:21:03", "remaining_time": "5:55:26", "throughput": 8525.56, "total_tokens": 593920944} {"current_steps": 583400, "total_steps": 761865, "loss": 1.9224, "lr": 1.293932509010947e-07, "epoch": 11.486286940599712, "percentage": 76.58, "elapsed_time": "19:21:15", "remaining_time": "5:55:14", "throughput": 8525.58, "total_tokens": 594023344} {"current_steps": 583500, "total_steps": 761865, "loss": 2.0006, "lr": 1.2925487977326753e-07, "epoch": 11.488255793349216, "percentage": 76.59, "elapsed_time": "19:21:27", "remaining_time": "5:55:02", "throughput": 8525.59, "total_tokens": 594124760} {"current_steps": 583600, "total_steps": 761865, "loss": 1.9692, "lr": 1.2911657168752138e-07, "epoch": 11.490224646098719, "percentage": 76.6, "elapsed_time": "19:21:39", "remaining_time": "5:54:50", "throughput": 8525.6, "total_tokens": 594226512} {"current_steps": 583700, "total_steps": 761865, "loss": 2.0289, "lr": 1.289783266673739e-07, "epoch": 11.492193498848222, "percentage": 76.61, "elapsed_time": "19:21:50", "remaining_time": "5:54:38", "throughput": 8525.61, "total_tokens": 594328912} {"current_steps": 583800, "total_steps": 761865, "loss": 1.9865, "lr": 1.2884014473633276e-07, "epoch": 11.494162351597724, "percentage": 76.63, "elapsed_time": "19:22:02", "remaining_time": "5:54:26", "throughput": 8525.63, "total_tokens": 594431312} {"current_steps": 583900, "total_steps": 761865, "loss": 1.9655, "lr": 1.287020259178942e-07, "epoch": 11.496131204347227, "percentage": 76.64, "elapsed_time": "19:22:14", "remaining_time": "5:54:14", "throughput": 8525.64, "total_tokens": 594533712} {"current_steps": 584000, "total_steps": 761865, "loss": 1.969, "lr": 1.285639702355446e-07, "epoch": 11.49810005709673, "percentage": 76.65, "elapsed_time": "19:22:26", "remaining_time": "5:54:02", "throughput": 8525.66, "total_tokens": 594636112} {"current_steps": 584100, "total_steps": 761865, "loss": 1.9958, "lr": 1.284259777127592e-07, "epoch": 11.500068909846233, "percentage": 76.67, "elapsed_time": "19:22:38", "remaining_time": "5:53:50", "throughput": 8525.66, "total_tokens": 594737096} {"current_steps": 584200, "total_steps": 761865, "loss": 1.9662, "lr": 1.282880483730021e-07, "epoch": 11.502037762595736, "percentage": 76.68, "elapsed_time": "19:22:50", "remaining_time": "5:53:38", "throughput": 8525.68, "total_tokens": 594839496} {"current_steps": 584300, "total_steps": 761865, "loss": 1.9606, "lr": 1.2815018223972728e-07, "epoch": 11.504006615345238, "percentage": 76.69, "elapsed_time": "19:23:02", "remaining_time": "5:53:26", "throughput": 8525.69, "total_tokens": 594941448} {"current_steps": 584400, "total_steps": 761865, "loss": 2.028, "lr": 1.280123793363776e-07, "epoch": 11.505975468094741, "percentage": 76.71, "elapsed_time": "19:23:14", "remaining_time": "5:53:14", "throughput": 8525.71, "total_tokens": 595043848} {"current_steps": 584500, "total_steps": 761865, "loss": 1.979, "lr": 1.2787463968638546e-07, "epoch": 11.507944320844244, "percentage": 76.72, "elapsed_time": "19:23:25", "remaining_time": "5:53:02", "throughput": 8525.72, "total_tokens": 595145456} {"current_steps": 584600, "total_steps": 761865, "loss": 2.0121, "lr": 1.277369633131721e-07, "epoch": 11.509913173593747, "percentage": 76.73, "elapsed_time": "19:23:37", "remaining_time": "5:52:50", "throughput": 8525.73, "total_tokens": 595246472} {"current_steps": 584700, "total_steps": 761865, "loss": 2.0076, "lr": 1.2759935024014822e-07, "epoch": 11.51188202634325, "percentage": 76.75, "elapsed_time": "19:23:49", "remaining_time": "5:52:38", "throughput": 8525.74, "total_tokens": 595348120} {"current_steps": 584800, "total_steps": 761865, "loss": 1.9597, "lr": 1.2746180049071392e-07, "epoch": 11.513850879092752, "percentage": 76.76, "elapsed_time": "19:24:01", "remaining_time": "5:52:26", "throughput": 8525.75, "total_tokens": 595450520} {"current_steps": 584900, "total_steps": 761865, "loss": 1.9856, "lr": 1.273243140882585e-07, "epoch": 11.515819731842255, "percentage": 76.77, "elapsed_time": "19:24:13", "remaining_time": "5:52:14", "throughput": 8525.76, "total_tokens": 595552144} {"current_steps": 585000, "total_steps": 761865, "loss": 1.9415, "lr": 1.2718689105616e-07, "epoch": 11.517788584591758, "percentage": 76.79, "elapsed_time": "19:24:25", "remaining_time": "5:52:02", "throughput": 8525.78, "total_tokens": 595654544} {"current_steps": 585100, "total_steps": 761865, "loss": 1.9806, "lr": 1.2704953141778617e-07, "epoch": 11.519757437341262, "percentage": 76.8, "elapsed_time": "19:24:37", "remaining_time": "5:51:50", "throughput": 8525.72, "total_tokens": 595756448} {"current_steps": 585200, "total_steps": 761865, "loss": 2.0164, "lr": 1.2691223519649396e-07, "epoch": 11.521726290090765, "percentage": 76.81, "elapsed_time": "19:24:49", "remaining_time": "5:51:38", "throughput": 8525.73, "total_tokens": 595858648} {"current_steps": 585300, "total_steps": 761865, "loss": 1.9695, "lr": 1.2677500241562938e-07, "epoch": 11.523695142840268, "percentage": 76.82, "elapsed_time": "19:25:01", "remaining_time": "5:51:26", "throughput": 8525.74, "total_tokens": 595960224} {"current_steps": 585400, "total_steps": 761865, "loss": 1.9693, "lr": 1.2663783309852788e-07, "epoch": 11.52566399558977, "percentage": 76.84, "elapsed_time": "19:25:12", "remaining_time": "5:51:14", "throughput": 8525.74, "total_tokens": 596059680} {"current_steps": 585500, "total_steps": 761865, "loss": 1.9633, "lr": 1.2650072726851362e-07, "epoch": 11.527632848339273, "percentage": 76.85, "elapsed_time": "19:25:24", "remaining_time": "5:51:02", "throughput": 8525.75, "total_tokens": 596160920} {"current_steps": 585600, "total_steps": 761865, "loss": 2.0251, "lr": 1.263636849489005e-07, "epoch": 11.529601701088776, "percentage": 76.86, "elapsed_time": "19:25:36", "remaining_time": "5:50:50", "throughput": 8525.75, "total_tokens": 596262168} {"current_steps": 585100, "total_steps": 609492, "loss": 1.9812, "lr": 3.94675918389431e-09, "epoch": 11.519757437341262, "percentage": 96.0, "elapsed_time": "0:00:11", "remaining_time": "0:00:00", "throughput": 50003805.2, "total_tokens": 595756448} {"current_steps": 585200, "total_steps": 609492, "loss": 2.0162, "lr": 3.914506629807912e-09, "epoch": 11.521726290090765, "percentage": 96.01, "elapsed_time": "0:00:23", "remaining_time": "0:00:00", "throughput": 25202148.23, "total_tokens": 595858648} {"current_steps": 585300, "total_steps": 609492, "loss": 1.9694, "lr": 3.882385881513572e-09, "epoch": 11.523695142840268, "percentage": 96.03, "elapsed_time": "0:00:35", "remaining_time": "0:00:01", "throughput": 16752405.16, "total_tokens": 595960224} {"current_steps": 585400, "total_steps": 609492, "loss": 1.9692, "lr": 3.8503969475454645e-09, "epoch": 11.52566399558977, "percentage": 96.05, "elapsed_time": "0:00:47", "remaining_time": "0:00:01", "throughput": 12548387.2, "total_tokens": 596059680} {"current_steps": 585500, "total_steps": 609492, "loss": 1.9634, "lr": 3.818539836402901e-09, "epoch": 11.527632848339273, "percentage": 96.06, "elapsed_time": "0:00:59", "remaining_time": "0:00:02", "throughput": 10008058.95, "total_tokens": 596160920} {"current_steps": 585600, "total_steps": 609492, "loss": 2.0249, "lr": 3.786814556549889e-09, "epoch": 11.529601701088776, "percentage": 96.08, "elapsed_time": "0:01:11", "remaining_time": "0:00:02", "throughput": 8363752.91, "total_tokens": 596262168} {"current_steps": 585700, "total_steps": 609492, "loss": 1.9759, "lr": 3.755221116415685e-09, "epoch": 11.531570553838279, "percentage": 96.1, "elapsed_time": "0:01:23", "remaining_time": "0:00:03", "throughput": 7170473.74, "total_tokens": 596364568} {"current_steps": 585800, "total_steps": 609492, "loss": 2.0019, "lr": 3.7237595243944097e-09, "epoch": 11.533539406587781, "percentage": 96.11, "elapsed_time": "0:01:34", "remaining_time": "0:00:03", "throughput": 6291290.77, "total_tokens": 596466344} {"current_steps": 585900, "total_steps": 609492, "loss": 1.98, "lr": 3.6924297888450974e-09, "epoch": 11.535508259337284, "percentage": 96.13, "elapsed_time": "0:01:46", "remaining_time": "0:00:04", "throughput": 5603383.58, "total_tokens": 596568744} {"current_steps": 586000, "total_steps": 609492, "loss": 1.9993, "lr": 3.661231918091756e-09, "epoch": 11.537477112086787, "percentage": 96.15, "elapsed_time": "0:01:57", "remaining_time": "0:00:04", "throughput": 5058860.9, "total_tokens": 596670520} {"current_steps": 586100, "total_steps": 609492, "loss": 1.9438, "lr": 3.6301659204235335e-09, "epoch": 11.53944596483629, "percentage": 96.16, "elapsed_time": "0:02:09", "remaining_time": "0:00:05", "throughput": 4612411.9, "total_tokens": 596771432} {"current_steps": 586200, "total_steps": 609492, "loss": 2.0, "lr": 3.5992318040942714e-09, "epoch": 11.541414817585792, "percentage": 96.18, "elapsed_time": "0:02:20", "remaining_time": "0:00:05", "throughput": 4237182.77, "total_tokens": 596873104} {"current_steps": 586300, "total_steps": 609492, "loss": 2.0493, "lr": 3.5684295773230066e-09, "epoch": 11.543383670335295, "percentage": 96.19, "elapsed_time": "0:02:32", "remaining_time": "0:00:06", "throughput": 3919609.73, "total_tokens": 596974128} {"current_steps": 586400, "total_steps": 609492, "loss": 1.9846, "lr": 3.5377592482935816e-09, "epoch": 11.545352523084798, "percentage": 96.21, "elapsed_time": "0:02:43", "remaining_time": "0:00:06", "throughput": 3644083.96, "total_tokens": 597076528} {"current_steps": 586500, "total_steps": 609492, "loss": 1.9597, "lr": 3.5072208251548665e-09, "epoch": 11.5473213758343, "percentage": 96.23, "elapsed_time": "0:02:55", "remaining_time": "0:00:06", "throughput": 3405057.81, "total_tokens": 597178928} {"current_steps": 586600, "total_steps": 609492, "loss": 2.0429, "lr": 3.4768143160206486e-09, "epoch": 11.549290228583803, "percentage": 96.24, "elapsed_time": "0:03:06", "remaining_time": "0:00:07", "throughput": 3196451.63, "total_tokens": 597280600} {"current_steps": 586700, "total_steps": 609492, "loss": 1.9481, "lr": 3.4465397289696884e-09, "epoch": 11.551259081333306, "percentage": 96.26, "elapsed_time": "0:03:18", "remaining_time": "0:00:07", "throughput": 3011092.35, "total_tokens": 597383000} {"current_steps": 586800, "total_steps": 609492, "loss": 1.9765, "lr": 3.416397072045718e-09, "epoch": 11.553227934082809, "percentage": 96.28, "elapsed_time": "0:03:30", "remaining_time": "0:00:08", "throughput": 2844004.86, "total_tokens": 597484064} {"current_steps": 586900, "total_steps": 609492, "loss": 2.05, "lr": 3.386386353257387e-09, "epoch": 11.555196786832314, "percentage": 96.29, "elapsed_time": "0:03:41", "remaining_time": "0:00:08", "throughput": 2695596.64, "total_tokens": 597586464} {"current_steps": 587000, "total_steps": 609492, "loss": 2.0157, "lr": 3.3565075805782605e-09, "epoch": 11.557165639581816, "percentage": 96.31, "elapsed_time": "0:03:53", "remaining_time": "0:00:08", "throughput": 2563562.8, "total_tokens": 597686616} {"current_steps": 587100, "total_steps": 609492, "loss": 2.0172, "lr": 3.326760761946934e-09, "epoch": 11.559134492331319, "percentage": 96.33, "elapsed_time": "0:04:04", "remaining_time": "0:00:09", "throughput": 2443655.33, "total_tokens": 597787712} {"current_steps": 587200, "total_steps": 609492, "loss": 1.9731, "lr": 3.2971459052668627e-09, "epoch": 11.561103345080822, "percentage": 96.34, "elapsed_time": "0:04:16", "remaining_time": "0:00:09", "throughput": 2330850.0, "total_tokens": 597890112} {"current_steps": 587300, "total_steps": 609492, "loss": 2.021, "lr": 3.2676630184064193e-09, "epoch": 11.563072197830325, "percentage": 96.36, "elapsed_time": "0:04:28", "remaining_time": "0:00:10", "throughput": 2228412.35, "total_tokens": 597991024} {"current_steps": 587400, "total_steps": 609492, "loss": 1.9729, "lr": 3.238312109199004e-09, "epoch": 11.565041050579827, "percentage": 96.38, "elapsed_time": "0:04:40", "remaining_time": "0:00:10", "throughput": 2135025.81, "total_tokens": 598093424} {"current_steps": 587500, "total_steps": 609492, "loss": 2.0153, "lr": 3.2090931854429347e-09, "epoch": 11.56700990332933, "percentage": 96.39, "elapsed_time": "0:04:51", "remaining_time": "0:00:10", "throughput": 2049017.68, "total_tokens": 598195824} {"current_steps": 587600, "total_steps": 609492, "loss": 1.9696, "lr": 3.1800062549013906e-09, "epoch": 11.568978756078833, "percentage": 96.41, "elapsed_time": "0:05:03", "remaining_time": "0:00:11", "throughput": 1968648.47, "total_tokens": 598296504} {"current_steps": 587700, "total_steps": 609492, "loss": 1.9419, "lr": 3.151051325302523e-09, "epoch": 11.570947608828336, "percentage": 96.42, "elapsed_time": "0:05:15", "remaining_time": "0:00:11", "throughput": 1895060.01, "total_tokens": 598398328} {"current_steps": 587800, "total_steps": 609492, "loss": 2.0142, "lr": 3.122228404339511e-09, "epoch": 11.572916461577838, "percentage": 96.44, "elapsed_time": "0:05:27", "remaining_time": "0:00:12", "throughput": 1827059.79, "total_tokens": 598500728} {"current_steps": 587900, "total_steps": 609492, "loss": 2.0028, "lr": 3.0935374996702292e-09, "epoch": 11.574885314327341, "percentage": 96.46, "elapsed_time": "0:05:39", "remaining_time": "0:00:12", "throughput": 1763616.14, "total_tokens": 598602488} {"current_steps": 588000, "total_steps": 609492, "loss": 1.98, "lr": 3.0649786189176908e-09, "epoch": 11.576854167076844, "percentage": 96.47, "elapsed_time": "0:05:51", "remaining_time": "0:00:12", "throughput": 1704997.68, "total_tokens": 598703832} {"current_steps": 588100, "total_steps": 609492, "loss": 2.0216, "lr": 3.0365517696697705e-09, "epoch": 11.578823019826347, "percentage": 96.49, "elapsed_time": "0:06:02", "remaining_time": "0:00:13", "throughput": 1650129.04, "total_tokens": 598805000} {"current_steps": 588200, "total_steps": 609492, "loss": 1.9755, "lr": 3.0082569594792052e-09, "epoch": 11.58079187257585, "percentage": 96.51, "elapsed_time": "0:06:14", "remaining_time": "0:00:13", "throughput": 1598132.07, "total_tokens": 598906680} {"current_steps": 588300, "total_steps": 609492, "loss": 2.0083, "lr": 2.9800941958637027e-09, "epoch": 11.582760725325352, "percentage": 96.52, "elapsed_time": "0:06:26", "remaining_time": "0:00:13", "throughput": 1550207.97, "total_tokens": 599006296} {"current_steps": 588400, "total_steps": 609492, "loss": 2.0161, "lr": 2.9520634863058336e-09, "epoch": 11.584729578074857, "percentage": 96.54, "elapsed_time": "0:06:38", "remaining_time": "0:00:14", "throughput": 1504244.14, "total_tokens": 599106608} {"current_steps": 588500, "total_steps": 609492, "loss": 2.0157, "lr": 2.924164838253196e-09, "epoch": 11.58669843082436, "percentage": 96.56, "elapsed_time": "0:06:49", "remaining_time": "0:00:14", "throughput": 1461629.99, "total_tokens": 599208192} {"current_steps": 588600, "total_steps": 609492, "loss": 1.9792, "lr": 2.8963982591182488e-09, "epoch": 11.588667283573862, "percentage": 96.57, "elapsed_time": "0:07:01", "remaining_time": "0:00:14", "throughput": 1421289.44, "total_tokens": 599309664} {"current_steps": 588700, "total_steps": 609492, "loss": 1.9482, "lr": 2.868763756278203e-09, "epoch": 11.590636136323365, "percentage": 96.59, "elapsed_time": "0:07:13", "remaining_time": "0:00:15", "throughput": 1382339.41, "total_tokens": 599411336} {"current_steps": 588800, "total_steps": 609492, "loss": 2.0295, "lr": 2.8412613370754624e-09, "epoch": 11.592604989072868, "percentage": 96.61, "elapsed_time": "0:07:25", "remaining_time": "0:00:15", "throughput": 1346070.98, "total_tokens": 599513736} {"current_steps": 588900, "total_steps": 609492, "loss": 1.9778, "lr": 2.8138910088170708e-09, "epoch": 11.59457384182237, "percentage": 96.62, "elapsed_time": "0:07:37", "remaining_time": "0:00:15", "throughput": 1311592.72, "total_tokens": 599616136} {"current_steps": 589000, "total_steps": 609492, "loss": 2.0103, "lr": 2.786652778775267e-09, "epoch": 11.596542694571873, "percentage": 96.64, "elapsed_time": "0:07:48", "remaining_time": "0:00:16", "throughput": 1279350.97, "total_tokens": 599718536} {"current_steps": 589100, "total_steps": 609492, "loss": 1.9449, "lr": 2.7595466541868175e-09, "epoch": 11.598511547321376, "percentage": 96.65, "elapsed_time": "0:08:00", "remaining_time": "0:00:16", "throughput": 1248312.09, "total_tokens": 599820168} {"current_steps": 589200, "total_steps": 609492, "loss": 2.011, "lr": 2.7325726422536833e-09, "epoch": 11.600480400070879, "percentage": 96.67, "elapsed_time": "0:08:12", "remaining_time": "0:00:16", "throughput": 1218768.16, "total_tokens": 599922480} {"current_steps": 589300, "total_steps": 609492, "loss": 1.9304, "lr": 2.705730750142743e-09, "epoch": 11.602449252820382, "percentage": 96.69, "elapsed_time": "0:08:24", "remaining_time": "0:00:17", "throughput": 1190297.15, "total_tokens": 600023624} {"current_steps": 589400, "total_steps": 609492, "loss": 1.9709, "lr": 2.6790209849854584e-09, "epoch": 11.604418105569884, "percentage": 96.7, "elapsed_time": "0:08:36", "remaining_time": "0:00:17", "throughput": 1162183.03, "total_tokens": 600125280} {"current_steps": 589500, "total_steps": 609492, "loss": 1.9486, "lr": 2.6524433538785418e-09, "epoch": 11.606386958319387, "percentage": 96.72, "elapsed_time": "0:08:48", "remaining_time": "0:00:17", "throughput": 1136347.3, "total_tokens": 600227680} {"current_steps": 589600, "total_steps": 609492, "loss": 1.9941, "lr": 2.6259978638834e-09, "epoch": 11.60835581106889, "percentage": 96.74, "elapsed_time": "0:08:59", "remaining_time": "0:00:18", "throughput": 1111856.81, "total_tokens": 600328576} {"current_steps": 589700, "total_steps": 609492, "loss": 1.9774, "lr": 2.599684522026413e-09, "epoch": 11.610324663818393, "percentage": 96.75, "elapsed_time": "0:09:11", "remaining_time": "0:00:18", "throughput": 1088182.32, "total_tokens": 600430928} {"current_steps": 589800, "total_steps": 609492, "loss": 1.9954, "lr": 2.5735033352987656e-09, "epoch": 11.612293516567895, "percentage": 96.77, "elapsed_time": "0:09:23", "remaining_time": "0:00:18", "throughput": 1065718.96, "total_tokens": 600532056} {"current_steps": 589900, "total_steps": 609492, "loss": 2.0438, "lr": 2.547454310656616e-09, "epoch": 11.614262369317398, "percentage": 96.79, "elapsed_time": "0:09:35", "remaining_time": "0:00:19", "throughput": 1044277.87, "total_tokens": 600632248} {"current_steps": 590000, "total_steps": 609492, "loss": 2.0343, "lr": 2.521537455020928e-09, "epoch": 11.6162312220669, "percentage": 96.8, "elapsed_time": "0:09:46", "remaining_time": "0:00:19", "throughput": 1023489.66, "total_tokens": 600733752} {"current_steps": 590100, "total_steps": 609492, "loss": 2.0148, "lr": 2.4957527752776376e-09, "epoch": 11.618200074816404, "percentage": 96.82, "elapsed_time": "0:09:59", "remaining_time": "0:00:19", "throughput": 1002469.52, "total_tokens": 600835576} {"current_steps": 590200, "total_steps": 609492, "loss": 1.9398, "lr": 2.470100278277487e-09, "epoch": 11.620168927565908, "percentage": 96.83, "elapsed_time": "0:10:11", "remaining_time": "0:00:19", "throughput": 983195.98, "total_tokens": 600937968} {"current_steps": 590300, "total_steps": 609492, "loss": 2.0115, "lr": 2.4445799708361914e-09, "epoch": 11.622137780315411, "percentage": 96.85, "elapsed_time": "0:10:22", "remaining_time": "0:00:20", "throughput": 964942.63, "total_tokens": 601038016} {"current_steps": 590400, "total_steps": 609492, "loss": 1.9977, "lr": 2.419191859734271e-09, "epoch": 11.624106633064914, "percentage": 96.87, "elapsed_time": "0:10:34", "remaining_time": "0:00:20", "throughput": 946799.71, "total_tokens": 601140416} {"current_steps": 590500, "total_steps": 609492, "loss": 1.979, "lr": 2.393935951717052e-09, "epoch": 11.626075485814416, "percentage": 96.88, "elapsed_time": "0:10:46", "remaining_time": "0:00:20", "throughput": 929612.66, "total_tokens": 601241464} {"current_steps": 590600, "total_steps": 609492, "loss": 2.0179, "lr": 2.368812253494945e-09, "epoch": 11.62804433856392, "percentage": 96.9, "elapsed_time": "0:10:58", "remaining_time": "0:00:21", "throughput": 912840.69, "total_tokens": 601343864} {"current_steps": 590700, "total_steps": 609492, "loss": 1.9422, "lr": 2.343820771742999e-09, "epoch": 11.630013191313422, "percentage": 96.92, "elapsed_time": "0:11:10", "remaining_time": "0:00:21", "throughput": 897250.33, "total_tokens": 601445440} {"current_steps": 590800, "total_steps": 609492, "loss": 1.971, "lr": 2.318961513101292e-09, "epoch": 11.631982044062925, "percentage": 96.93, "elapsed_time": "0:11:21", "remaining_time": "0:00:21", "throughput": 882243.27, "total_tokens": 601547200} {"current_steps": 590900, "total_steps": 609492, "loss": 1.99, "lr": 2.294234484174762e-09, "epoch": 11.633950896812427, "percentage": 96.95, "elapsed_time": "0:11:33", "remaining_time": "0:00:21", "throughput": 867690.03, "total_tokens": 601649600} {"current_steps": 591000, "total_steps": 609492, "loss": 2.0106, "lr": 2.269639691533043e-09, "epoch": 11.63591974956193, "percentage": 96.97, "elapsed_time": "0:11:44", "remaining_time": "0:00:22", "throughput": 853674.2, "total_tokens": 601751416} {"current_steps": 591100, "total_steps": 609492, "loss": 1.9897, "lr": 2.2451771417109077e-09, "epoch": 11.637888602311433, "percentage": 96.98, "elapsed_time": "0:11:56", "remaining_time": "0:00:22", "throughput": 840110.77, "total_tokens": 601853120} {"current_steps": 591200, "total_steps": 609492, "loss": 2.0037, "lr": 2.220846841207824e-09, "epoch": 11.639857455060936, "percentage": 97.0, "elapsed_time": "0:12:07", "remaining_time": "0:00:22", "throughput": 826914.64, "total_tokens": 601955520} {"current_steps": 591300, "total_steps": 609492, "loss": 1.9609, "lr": 2.1966487964880652e-09, "epoch": 11.641826307810438, "percentage": 97.02, "elapsed_time": "0:12:19", "remaining_time": "0:00:22", "throughput": 814139.5, "total_tokens": 602057920} {"current_steps": 591400, "total_steps": 609492, "loss": 2.0072, "lr": 2.172583013980933e-09, "epoch": 11.643795160559941, "percentage": 97.03, "elapsed_time": "0:12:30", "remaining_time": "0:00:22", "throughput": 801848.4, "total_tokens": 602159032} {"current_steps": 591500, "total_steps": 609492, "loss": 1.9598, "lr": 2.1486495000804796e-09, "epoch": 11.645764013309444, "percentage": 97.05, "elapsed_time": "0:12:42", "remaining_time": "0:00:23", "throughput": 789459.13, "total_tokens": 602261432} {"current_steps": 591600, "total_steps": 609492, "loss": 1.9845, "lr": 2.124848261145673e-09, "epoch": 11.647732866058947, "percentage": 97.06, "elapsed_time": "0:12:54", "remaining_time": "0:00:23", "throughput": 777598.46, "total_tokens": 602363384} {"current_steps": 591700, "total_steps": 609492, "loss": 1.9423, "lr": 2.101179303500289e-09, "epoch": 11.64970171880845, "percentage": 97.08, "elapsed_time": "0:13:06", "remaining_time": "0:00:23", "throughput": 766045.0, "total_tokens": 602465536} {"current_steps": 591800, "total_steps": 609492, "loss": 1.9774, "lr": 2.0776426334329077e-09, "epoch": 11.651670571557954, "percentage": 97.1, "elapsed_time": "0:13:18", "remaining_time": "0:00:23", "throughput": 754823.16, "total_tokens": 602567936} {"current_steps": 591900, "total_steps": 609492, "loss": 2.0093, "lr": 2.0542382571971384e-09, "epoch": 11.653639424307457, "percentage": 97.11, "elapsed_time": "0:13:30", "remaining_time": "0:00:24", "throughput": 743976.59, "total_tokens": 602669528} {"current_steps": 592000, "total_steps": 609492, "loss": 1.9717, "lr": 2.0309661810112287e-09, "epoch": 11.65560827705696, "percentage": 97.13, "elapsed_time": "0:13:41", "remaining_time": "0:00:24", "throughput": 733371.47, "total_tokens": 602771928} {"current_steps": 592100, "total_steps": 609492, "loss": 1.9794, "lr": 2.0078264110584e-09, "epoch": 11.657577129806462, "percentage": 97.15, "elapsed_time": "0:13:53", "remaining_time": "0:00:24", "throughput": 723085.26, "total_tokens": 602874328} {"current_steps": 592200, "total_steps": 609492, "loss": 1.9593, "lr": 1.9848189534867332e-09, "epoch": 11.659545982555965, "percentage": 97.16, "elapsed_time": "0:14:05", "remaining_time": "0:00:24", "throughput": 713131.55, "total_tokens": 602976112} {"current_steps": 592300, "total_steps": 609492, "loss": 1.9501, "lr": 1.9619438144091173e-09, "epoch": 11.661514835305468, "percentage": 97.18, "elapsed_time": "0:14:17", "remaining_time": "0:00:24", "throughput": 703409.15, "total_tokens": 603078512} {"current_steps": 592400, "total_steps": 609492, "loss": 1.9638, "lr": 1.9392009999032455e-09, "epoch": 11.66348368805497, "percentage": 97.2, "elapsed_time": "0:14:29", "remaining_time": "0:00:25", "throughput": 693950.69, "total_tokens": 603180912} {"current_steps": 592500, "total_steps": 609492, "loss": 1.9802, "lr": 1.916590516011729e-09, "epoch": 11.665452540804473, "percentage": 97.21, "elapsed_time": "0:14:40", "remaining_time": "0:00:25", "throughput": 684783.6, "total_tokens": 603282784} {"current_steps": 592600, "total_steps": 609492, "loss": 1.9731, "lr": 1.8941123687419292e-09, "epoch": 11.667421393553976, "percentage": 97.23, "elapsed_time": "0:14:53", "remaining_time": "0:00:25", "throughput": 675622.49, "total_tokens": 603385184} {"current_steps": 592700, "total_steps": 609492, "loss": 1.9767, "lr": 1.871766564066235e-09, "epoch": 11.669390246303479, "percentage": 97.24, "elapsed_time": "0:15:05", "remaining_time": "0:00:25", "throughput": 666580.81, "total_tokens": 603487584} {"current_steps": 592800, "total_steps": 609492, "loss": 1.9927, "lr": 1.8495531079216199e-09, "epoch": 11.671359099052982, "percentage": 97.26, "elapsed_time": "0:15:17", "remaining_time": "0:00:25", "throughput": 658156.99, "total_tokens": 603589520} {"current_steps": 592900, "total_steps": 609492, "loss": 1.9931, "lr": 1.827472006210029e-09, "epoch": 11.673327951802484, "percentage": 97.28, "elapsed_time": "0:15:28", "remaining_time": "0:00:25", "throughput": 649934.04, "total_tokens": 603690792} {"current_steps": 593000, "total_steps": 609492, "loss": 1.9789, "lr": 1.8055232647982698e-09, "epoch": 11.675296804551987, "percentage": 97.29, "elapsed_time": "0:15:40", "remaining_time": "0:00:26", "throughput": 641903.03, "total_tokens": 603793192} {"current_steps": 593100, "total_steps": 609492, "loss": 2.0209, "lr": 1.7837068895178997e-09, "epoch": 11.67726565730149, "percentage": 97.31, "elapsed_time": "0:15:52", "remaining_time": "0:00:26", "throughput": 634098.47, "total_tokens": 603894648} {"current_steps": 593200, "total_steps": 609492, "loss": 1.9245, "lr": 1.7620228861653374e-09, "epoch": 11.679234510050993, "percentage": 97.33, "elapsed_time": "0:16:04", "remaining_time": "0:00:26", "throughput": 626445.98, "total_tokens": 603997000} {"current_steps": 593300, "total_steps": 609492, "loss": 2.0252, "lr": 1.740471260501919e-09, "epoch": 11.681203362800495, "percentage": 97.34, "elapsed_time": "0:16:15", "remaining_time": "0:00:26", "throughput": 618981.54, "total_tokens": 604099400} {"current_steps": 593400, "total_steps": 609492, "loss": 2.0151, "lr": 1.719052018253675e-09, "epoch": 11.683172215549998, "percentage": 97.36, "elapsed_time": "0:16:27", "remaining_time": "0:00:26", "throughput": 611668.79, "total_tokens": 604201128} {"current_steps": 593500, "total_steps": 609492, "loss": 1.9501, "lr": 1.6977651651114976e-09, "epoch": 11.685141068299501, "percentage": 97.38, "elapsed_time": "0:16:39", "remaining_time": "0:00:26", "throughput": 604546.71, "total_tokens": 604302984} {"current_steps": 593600, "total_steps": 609492, "loss": 2.0443, "lr": 1.6766107067311964e-09, "epoch": 11.687109921049005, "percentage": 97.39, "elapsed_time": "0:16:51", "remaining_time": "0:00:27", "throughput": 597713.96, "total_tokens": 604404160} {"current_steps": 593700, "total_steps": 609492, "loss": 1.9772, "lr": 1.6555886487332749e-09, "epoch": 11.689078773798508, "percentage": 97.41, "elapsed_time": "0:17:02", "remaining_time": "0:00:27", "throughput": 591071.07, "total_tokens": 604505368} {"current_steps": 593800, "total_steps": 609492, "loss": 1.993, "lr": 1.6346989967031545e-09, "epoch": 11.691047626548011, "percentage": 97.43, "elapsed_time": "0:17:14", "remaining_time": "0:00:27", "throughput": 584451.24, "total_tokens": 604607768} {"current_steps": 593900, "total_steps": 609492, "loss": 2.0026, "lr": 1.6139417561910063e-09, "epoch": 11.693016479297514, "percentage": 97.44, "elapsed_time": "0:17:26", "remaining_time": "0:00:27", "throughput": 577957.44, "total_tokens": 604709664} {"current_steps": 594000, "total_steps": 609492, "loss": 2.0245, "lr": 1.5933169327119189e-09, "epoch": 11.694985332047017, "percentage": 97.46, "elapsed_time": "0:17:37", "remaining_time": "0:00:27", "throughput": 571700.05, "total_tokens": 604809960} {"current_steps": 594100, "total_steps": 609492, "loss": 2.0352, "lr": 1.5728245317456756e-09, "epoch": 11.69695418479652, "percentage": 97.47, "elapsed_time": "0:17:49", "remaining_time": "0:00:27", "throughput": 565427.48, "total_tokens": 604912360} {"current_steps": 594200, "total_steps": 609492, "loss": 1.9875, "lr": 1.5524645587369768e-09, "epoch": 11.698923037546022, "percentage": 97.49, "elapsed_time": "0:18:01", "remaining_time": "0:00:27", "throughput": 559389.83, "total_tokens": 605014080} {"current_steps": 594300, "total_steps": 609492, "loss": 1.9973, "lr": 1.5322370190952727e-09, "epoch": 11.700891890295525, "percentage": 97.51, "elapsed_time": "0:18:13", "remaining_time": "0:00:27", "throughput": 553408.92, "total_tokens": 605116480} {"current_steps": 594400, "total_steps": 609492, "loss": 2.0091, "lr": 1.5121419181948204e-09, "epoch": 11.702860743045028, "percentage": 97.52, "elapsed_time": "0:18:25", "remaining_time": "0:00:28", "throughput": 547663.7, "total_tokens": 605218016} {"current_steps": 594500, "total_steps": 609492, "loss": 2.0294, "lr": 1.492179261374793e-09, "epoch": 11.70482959579453, "percentage": 97.54, "elapsed_time": "0:18:36", "remaining_time": "0:00:28", "throughput": 542034.94, "total_tokens": 605319816} {"current_steps": 594600, "total_steps": 609492, "loss": 1.9653, "lr": 1.4723490539390592e-09, "epoch": 11.706798448544033, "percentage": 97.56, "elapsed_time": "0:18:48", "remaining_time": "0:00:28", "throughput": 536571.61, "total_tokens": 605421400} {"current_steps": 594700, "total_steps": 609492, "loss": 1.9635, "lr": 1.4526513011564046e-09, "epoch": 11.708767301293536, "percentage": 97.57, "elapsed_time": "0:18:59", "remaining_time": "0:00:28", "throughput": 531161.51, "total_tokens": 605523800} {"current_steps": 594800, "total_steps": 609492, "loss": 1.9859, "lr": 1.4330860082602535e-09, "epoch": 11.710736154043039, "percentage": 97.59, "elapsed_time": "0:19:11", "remaining_time": "0:00:28", "throughput": 525822.29, "total_tokens": 605626200} {"current_steps": 594900, "total_steps": 609492, "loss": 1.9933, "lr": 1.4136531804490036e-09, "epoch": 11.712705006792541, "percentage": 97.61, "elapsed_time": "0:19:23", "remaining_time": "0:00:28", "throughput": 520580.98, "total_tokens": 605728600} {"current_steps": 595000, "total_steps": 609492, "loss": 1.9638, "lr": 1.3943528228858026e-09, "epoch": 11.714673859542044, "percentage": 97.62, "elapsed_time": "0:19:35", "remaining_time": "0:00:28", "throughput": 515438.63, "total_tokens": 605831000} {"current_steps": 595100, "total_steps": 609492, "loss": 2.022, "lr": 1.3751849406985483e-09, "epoch": 11.716642712291549, "percentage": 97.64, "elapsed_time": "0:19:47", "remaining_time": "0:00:28", "throughput": 510131.56, "total_tokens": 605932824} {"current_steps": 595200, "total_steps": 609492, "loss": 1.9692, "lr": 1.3561495389800004e-09, "epoch": 11.718611565041051, "percentage": 97.66, "elapsed_time": "0:19:59", "remaining_time": "0:00:28", "throughput": 505271.09, "total_tokens": 606035224} {"current_steps": 595300, "total_steps": 609492, "loss": 1.9671, "lr": 1.3372466227877243e-09, "epoch": 11.720580417790554, "percentage": 97.67, "elapsed_time": "0:20:10", "remaining_time": "0:00:28", "throughput": 500534.56, "total_tokens": 606136760} {"current_steps": 595400, "total_steps": 609492, "loss": 1.984, "lr": 1.3184761971440917e-09, "epoch": 11.722549270540057, "percentage": 97.69, "elapsed_time": "0:20:22", "remaining_time": "0:00:28", "throughput": 495856.27, "total_tokens": 606239160} {"current_steps": 595500, "total_steps": 609492, "loss": 1.9937, "lr": 1.299838267036224e-09, "epoch": 11.72451812328956, "percentage": 97.7, "elapsed_time": "0:20:34", "remaining_time": "0:00:28", "throughput": 491327.18, "total_tokens": 606338368} {"current_steps": 595600, "total_steps": 609492, "loss": 1.9848, "lr": 1.2813328374161047e-09, "epoch": 11.726486976039062, "percentage": 97.72, "elapsed_time": "0:20:45", "remaining_time": "0:00:29", "throughput": 486779.6, "total_tokens": 606440768} {"current_steps": 595700, "total_steps": 609492, "loss": 1.9859, "lr": 1.2629599132003566e-09, "epoch": 11.728455828788565, "percentage": 97.74, "elapsed_time": "0:20:57", "remaining_time": "0:00:29", "throughput": 482340.06, "total_tokens": 606541504} {"current_steps": 595800, "total_steps": 609492, "loss": 2.0021, "lr": 1.24471949927063e-09, "epoch": 11.730424681538068, "percentage": 97.75, "elapsed_time": "0:21:09", "remaining_time": "0:00:29", "throughput": 478029.97, "total_tokens": 606642144} {"current_steps": 595900, "total_steps": 609492, "loss": 1.9589, "lr": 1.2266116004731598e-09, "epoch": 11.73239353428757, "percentage": 97.77, "elapsed_time": "0:21:20", "remaining_time": "0:00:29", "throughput": 473763.66, "total_tokens": 606744544} {"current_steps": 596000, "total_steps": 609492, "loss": 2.0034, "lr": 1.2086362216191525e-09, "epoch": 11.734362387037073, "percentage": 97.79, "elapsed_time": "0:21:32", "remaining_time": "0:00:29", "throughput": 469588.35, "total_tokens": 606846352} {"current_steps": 596100, "total_steps": 609492, "loss": 1.9454, "lr": 1.1907933674845106e-09, "epoch": 11.736331239786576, "percentage": 97.8, "elapsed_time": "0:21:43", "remaining_time": "0:00:29", "throughput": 465484.85, "total_tokens": 606947992} {"current_steps": 596200, "total_steps": 609492, "loss": 1.9692, "lr": 1.173083042809886e-09, "epoch": 11.738300092536079, "percentage": 97.82, "elapsed_time": "0:21:55", "remaining_time": "0:00:29", "throughput": 461443.54, "total_tokens": 607050392} {"current_steps": 596300, "total_steps": 609492, "loss": 1.9869, "lr": 1.155505252300737e-09, "epoch": 11.740268945285582, "percentage": 97.84, "elapsed_time": "0:22:07", "remaining_time": "0:00:29", "throughput": 457476.9, "total_tokens": 607152792} {"current_steps": 596400, "total_steps": 609492, "loss": 1.9897, "lr": 1.1380600006273833e-09, "epoch": 11.742237798035084, "percentage": 97.85, "elapsed_time": "0:22:18", "remaining_time": "0:00:29", "throughput": 453577.26, "total_tokens": 607254336} {"current_steps": 596500, "total_steps": 609492, "loss": 1.9508, "lr": 1.120747292424895e-09, "epoch": 11.744206650784587, "percentage": 97.87, "elapsed_time": "0:22:30", "remaining_time": "0:00:29", "throughput": 449756.4, "total_tokens": 607356072} {"current_steps": 596600, "total_steps": 609492, "loss": 2.0472, "lr": 1.103567132293093e-09, "epoch": 11.74617550353409, "percentage": 97.88, "elapsed_time": "0:22:42", "remaining_time": "0:00:29", "throughput": 445933.85, "total_tokens": 607458472} {"current_steps": 596700, "total_steps": 609492, "loss": 2.0183, "lr": 1.0865195247966585e-09, "epoch": 11.748144356283593, "percentage": 97.9, "elapsed_time": "0:22:53", "remaining_time": "0:00:29", "throughput": 442211.33, "total_tokens": 607560872} {"current_steps": 596800, "total_steps": 609492, "loss": 1.9619, "lr": 1.0696044744649135e-09, "epoch": 11.750113209033096, "percentage": 97.92, "elapsed_time": "0:23:05", "remaining_time": "0:00:29", "throughput": 438547.56, "total_tokens": 607663272} {"current_steps": 596900, "total_steps": 609492, "loss": 1.9705, "lr": 1.0528219857920407e-09, "epoch": 11.7520820617826, "percentage": 97.93, "elapsed_time": "0:23:17", "remaining_time": "0:00:29", "throughput": 434931.99, "total_tokens": 607765672} {"current_steps": 597000, "total_steps": 609492, "loss": 1.9639, "lr": 1.036172063237084e-09, "epoch": 11.754050914532103, "percentage": 97.95, "elapsed_time": "0:23:29", "remaining_time": "0:00:29", "throughput": 431369.53, "total_tokens": 607868072} {"current_steps": 597100, "total_steps": 609492, "loss": 2.018, "lr": 1.0196547112237275e-09, "epoch": 11.756019767281606, "percentage": 97.97, "elapsed_time": "0:23:40", "remaining_time": "0:00:29", "throughput": 427895.84, "total_tokens": 607970472} {"current_steps": 597200, "total_steps": 609492, "loss": 1.9725, "lr": 1.0032699341405716e-09, "epoch": 11.757988620031108, "percentage": 97.98, "elapsed_time": "0:23:52", "remaining_time": "0:00:29", "throughput": 424536.52, "total_tokens": 608071744} {"current_steps": 597300, "total_steps": 609492, "loss": 1.972, "lr": 9.870177363408005e-10, "epoch": 11.759957472780611, "percentage": 98.0, "elapsed_time": "0:24:04", "remaining_time": "0:00:29", "throughput": 421155.65, "total_tokens": 608174144} {"current_steps": 597400, "total_steps": 609492, "loss": 1.9493, "lr": 9.70898122142627e-10, "epoch": 11.761926325530114, "percentage": 98.02, "elapsed_time": "0:24:15", "remaining_time": "0:00:29", "throughput": 417872.57, "total_tokens": 608276544} {"current_steps": 597500, "total_steps": 609492, "loss": 1.9629, "lr": 9.549110958287365e-10, "epoch": 11.763895178279617, "percentage": 98.03, "elapsed_time": "0:24:27", "remaining_time": "0:00:29", "throughput": 414591.42, "total_tokens": 608378944} {"current_steps": 597600, "total_steps": 609492, "loss": 2.0116, "lr": 9.390566616468976e-10, "epoch": 11.76586403102912, "percentage": 98.05, "elapsed_time": "0:24:39", "remaining_time": "0:00:29", "throughput": 411412.15, "total_tokens": 608480472} {"current_steps": 597700, "total_steps": 609492, "loss": 1.9794, "lr": 9.23334823809463e-10, "epoch": 11.767832883778622, "percentage": 98.07, "elapsed_time": "0:24:50", "remaining_time": "0:00:29", "throughput": 408307.17, "total_tokens": 608582048} {"current_steps": 597800, "total_steps": 609492, "loss": 2.0005, "lr": 9.077455864934803e-10, "epoch": 11.769801736528125, "percentage": 98.08, "elapsed_time": "0:25:02", "remaining_time": "0:00:29", "throughput": 405234.4, "total_tokens": 608682832} {"current_steps": 597900, "total_steps": 609492, "loss": 2.0201, "lr": 8.92288953841025e-10, "epoch": 11.771770589277628, "percentage": 98.1, "elapsed_time": "0:25:13", "remaining_time": "0:00:29", "throughput": 402202.34, "total_tokens": 608785232} {"current_steps": 598000, "total_steps": 609492, "loss": 2.0112, "lr": 8.769649299587568e-10, "epoch": 11.77373944202713, "percentage": 98.11, "elapsed_time": "0:25:25", "remaining_time": "0:00:29", "throughput": 399205.39, "total_tokens": 608887632} {"current_steps": 598100, "total_steps": 609492, "loss": 1.983, "lr": 8.617735189181408e-10, "epoch": 11.775708294776633, "percentage": 98.13, "elapsed_time": "0:25:37", "remaining_time": "0:00:29", "throughput": 396210.92, "total_tokens": 608988488} {"current_steps": 598200, "total_steps": 609492, "loss": 1.9361, "lr": 8.467147247553375e-10, "epoch": 11.777677147526136, "percentage": 98.15, "elapsed_time": "0:25:48", "remaining_time": "0:00:29", "throughput": 393320.81, "total_tokens": 609090216} {"current_steps": 598300, "total_steps": 609492, "loss": 1.95, "lr": 8.317885514714241e-10, "epoch": 11.779646000275639, "percentage": 98.16, "elapsed_time": "0:26:00", "remaining_time": "0:00:29", "throughput": 390469.11, "total_tokens": 609192616} {"current_steps": 598400, "total_steps": 609492, "loss": 1.9692, "lr": 8.169950030321726e-10, "epoch": 11.781614853025141, "percentage": 98.18, "elapsed_time": "0:26:11", "remaining_time": "0:00:29", "throughput": 387669.28, "total_tokens": 609294416} {"current_steps": 598500, "total_steps": 609492, "loss": 1.9561, "lr": 8.023340833679948e-10, "epoch": 11.783583705774646, "percentage": 98.2, "elapsed_time": "0:26:23", "remaining_time": "0:00:29", "throughput": 384887.83, "total_tokens": 609396352} {"current_steps": 598600, "total_steps": 609492, "loss": 1.9669, "lr": 7.878057963743301e-10, "epoch": 11.785552558524149, "percentage": 98.21, "elapsed_time": "0:26:34", "remaining_time": "0:00:29", "throughput": 382152.22, "total_tokens": 609498752} {"current_steps": 598700, "total_steps": 609492, "loss": 2.0171, "lr": 7.734101459110909e-10, "epoch": 11.787521411273651, "percentage": 98.23, "elapsed_time": "0:26:46", "remaining_time": "0:00:28", "throughput": 379451.83, "total_tokens": 609601152} {"current_steps": 598800, "total_steps": 609492, "loss": 1.9596, "lr": 7.59147135803162e-10, "epoch": 11.789490264023154, "percentage": 98.25, "elapsed_time": "0:26:58", "remaining_time": "0:00:28", "throughput": 376779.36, "total_tokens": 609702952} {"current_steps": 598900, "total_steps": 609492, "loss": 1.9839, "lr": 7.450167698400678e-10, "epoch": 11.791459116772657, "percentage": 98.26, "elapsed_time": "0:27:09", "remaining_time": "0:00:28", "throughput": 374121.06, "total_tokens": 609804584} {"current_steps": 599000, "total_steps": 609492, "loss": 1.967, "lr": 7.310190517761383e-10, "epoch": 11.79342796952216, "percentage": 98.28, "elapsed_time": "0:27:21", "remaining_time": "0:00:28", "throughput": 371467.09, "total_tokens": 609905832} {"current_steps": 599100, "total_steps": 609492, "loss": 1.959, "lr": 7.171539853304542e-10, "epoch": 11.795396822271663, "percentage": 98.29, "elapsed_time": "0:27:33", "remaining_time": "0:00:28", "throughput": 368908.16, "total_tokens": 610007656} {"current_steps": 599200, "total_steps": 609492, "loss": 1.9685, "lr": 7.034215741868465e-10, "epoch": 11.797365675021165, "percentage": 98.31, "elapsed_time": "0:27:45", "remaining_time": "0:00:28", "throughput": 366412.85, "total_tokens": 610109456} {"current_steps": 599300, "total_steps": 609492, "loss": 1.9602, "lr": 6.898218219938967e-10, "epoch": 11.799334527770668, "percentage": 98.33, "elapsed_time": "0:27:56", "remaining_time": "0:00:28", "throughput": 363886.09, "total_tokens": 610211088} {"current_steps": 599400, "total_steps": 609492, "loss": 1.9667, "lr": 6.763547323649921e-10, "epoch": 11.80130338052017, "percentage": 98.34, "elapsed_time": "0:28:08", "remaining_time": "0:00:28", "throughput": 361409.68, "total_tokens": 610312904} {"current_steps": 599500, "total_steps": 609492, "loss": 1.9997, "lr": 6.630203088781594e-10, "epoch": 11.803272233269674, "percentage": 98.36, "elapsed_time": "0:28:20", "remaining_time": "0:00:28", "throughput": 359002.79, "total_tokens": 610414856} {"current_steps": 599600, "total_steps": 609492, "loss": 1.9776, "lr": 6.49818555076287e-10, "epoch": 11.805241086019176, "percentage": 98.38, "elapsed_time": "0:28:31", "remaining_time": "0:00:28", "throughput": 356673.52, "total_tokens": 610514968} {"current_steps": 599700, "total_steps": 609492, "loss": 1.937, "lr": 6.367494744669577e-10, "epoch": 11.807209938768679, "percentage": 98.39, "elapsed_time": "0:28:43", "remaining_time": "0:00:28", "throughput": 354316.74, "total_tokens": 610617368} {"current_steps": 599800, "total_steps": 609492, "loss": 1.9884, "lr": 6.238130705225053e-10, "epoch": 11.809178791518182, "percentage": 98.41, "elapsed_time": "0:28:55", "remaining_time": "0:00:28", "throughput": 351970.04, "total_tokens": 610719000} {"current_steps": 599900, "total_steps": 609492, "loss": 1.9506, "lr": 6.110093466800137e-10, "epoch": 11.811147644267685, "percentage": 98.43, "elapsed_time": "0:29:06", "remaining_time": "0:00:27", "throughput": 349703.67, "total_tokens": 610820752} {"current_steps": 600000, "total_steps": 609492, "loss": 1.9925, "lr": 5.983383063413728e-10, "epoch": 11.813116497017187, "percentage": 98.44, "elapsed_time": "0:29:18", "remaining_time": "0:00:27", "throughput": 347455.5, "total_tokens": 610923152} {"current_steps": 600100, "total_steps": 609492, "loss": 2.0176, "lr": 5.857999528731672e-10, "epoch": 11.81508534976669, "percentage": 98.46, "elapsed_time": "0:29:30", "remaining_time": "0:00:27", "throughput": 345137.06, "total_tokens": 611024096} {"current_steps": 600200, "total_steps": 609492, "loss": 1.977, "lr": 5.733942896066768e-10, "epoch": 11.817054202516193, "percentage": 98.48, "elapsed_time": "0:29:41", "remaining_time": "0:00:27", "throughput": 342956.52, "total_tokens": 611126496} {"current_steps": 600300, "total_steps": 609492, "loss": 2.0058, "lr": 5.611213198380427e-10, "epoch": 11.819023055265697, "percentage": 98.49, "elapsed_time": "0:29:53", "remaining_time": "0:00:27", "throughput": 340798.55, "total_tokens": 611228088} {"current_steps": 600400, "total_steps": 609492, "loss": 1.948, "lr": 5.489810468280454e-10, "epoch": 11.8209919080152, "percentage": 98.51, "elapsed_time": "0:30:05", "remaining_time": "0:00:27", "throughput": 338660.27, "total_tokens": 611329448} {"current_steps": 600500, "total_steps": 609492, "loss": 1.9882, "lr": 5.369734738023269e-10, "epoch": 11.822960760764703, "percentage": 98.52, "elapsed_time": "0:30:16", "remaining_time": "0:00:27", "throughput": 336520.05, "total_tokens": 611431072} {"current_steps": 600600, "total_steps": 609492, "loss": 1.9543, "lr": 5.250986039511129e-10, "epoch": 11.824929613514206, "percentage": 98.54, "elapsed_time": "0:30:29", "remaining_time": "0:00:27", "throughput": 334342.07, "total_tokens": 611533040} {"current_steps": 600700, "total_steps": 609492, "loss": 2.0162, "lr": 5.13356440429491e-10, "epoch": 11.826898466263708, "percentage": 98.56, "elapsed_time": "0:30:41", "remaining_time": "0:00:26", "throughput": 332223.27, "total_tokens": 611633952} {"current_steps": 600800, "total_steps": 609492, "loss": 1.97, "lr": 5.017469863572987e-10, "epoch": 11.828867319013211, "percentage": 98.57, "elapsed_time": "0:30:52", "remaining_time": "0:00:26", "throughput": 330148.95, "total_tokens": 611736264} {"current_steps": 600900, "total_steps": 609492, "loss": 1.9556, "lr": 4.902702448190133e-10, "epoch": 11.830836171762714, "percentage": 98.59, "elapsed_time": "0:31:04", "remaining_time": "0:00:26", "throughput": 328120.14, "total_tokens": 611838664} {"current_steps": 601000, "total_steps": 609492, "loss": 1.9164, "lr": 4.789262188639176e-10, "epoch": 11.832805024512217, "percentage": 98.61, "elapsed_time": "0:31:16", "remaining_time": "0:00:26", "throughput": 326103.62, "total_tokens": 611940568} {"current_steps": 601100, "total_steps": 609492, "loss": 2.0214, "lr": 4.677149115059897e-10, "epoch": 11.83477387726172, "percentage": 98.62, "elapsed_time": "0:31:28", "remaining_time": "0:00:26", "throughput": 324137.85, "total_tokens": 612042136} {"current_steps": 601200, "total_steps": 609492, "loss": 1.9946, "lr": 4.5663632572412456e-10, "epoch": 11.836742730011222, "percentage": 98.64, "elapsed_time": "0:31:40", "remaining_time": "0:00:26", "throughput": 322178.13, "total_tokens": 612144536} {"current_steps": 601300, "total_steps": 609492, "loss": 1.9869, "lr": 4.456904644616344e-10, "epoch": 11.838711582760725, "percentage": 98.66, "elapsed_time": "0:31:51", "remaining_time": "0:00:26", "throughput": 320240.19, "total_tokens": 612246720} {"current_steps": 601400, "total_steps": 609492, "loss": 1.9422, "lr": 4.348773306268594e-10, "epoch": 11.840680435510228, "percentage": 98.67, "elapsed_time": "0:32:03", "remaining_time": "0:00:25", "throughput": 318336.19, "total_tokens": 612347272} {"current_steps": 601500, "total_steps": 609492, "loss": 2.0274, "lr": 4.241969270927237e-10, "epoch": 11.84264928825973, "percentage": 98.69, "elapsed_time": "0:32:15", "remaining_time": "0:00:25", "throughput": 316426.29, "total_tokens": 612448768} {"current_steps": 601600, "total_steps": 609492, "loss": 1.9705, "lr": 4.1364925669695736e-10, "epoch": 11.844618141009233, "percentage": 98.71, "elapsed_time": "0:32:27", "remaining_time": "0:00:25", "throughput": 314563.35, "total_tokens": 612551168} {"current_steps": 601700, "total_steps": 609492, "loss": 2.0292, "lr": 4.0323432224187435e-10, "epoch": 11.846586993758736, "percentage": 98.72, "elapsed_time": "0:32:38", "remaining_time": "0:00:25", "throughput": 312747.74, "total_tokens": 612652048} {"current_steps": 601800, "total_steps": 609492, "loss": 1.9715, "lr": 3.9295212649476105e-10, "epoch": 11.84855584650824, "percentage": 98.74, "elapsed_time": "0:32:50", "remaining_time": "0:00:25", "throughput": 310944.31, "total_tokens": 612753936} {"current_steps": 601900, "total_steps": 609492, "loss": 1.9632, "lr": 3.8280267218748773e-10, "epoch": 11.850524699257743, "percentage": 98.75, "elapsed_time": "0:33:02", "remaining_time": "0:00:25", "throughput": 309151.82, "total_tokens": 612856336} {"current_steps": 602000, "total_steps": 609492, "loss": 1.9986, "lr": 3.727859620166196e-10, "epoch": 11.852493552007246, "percentage": 98.77, "elapsed_time": "0:33:14", "remaining_time": "0:00:24", "throughput": 307389.38, "total_tokens": 612957960} {"current_steps": 602100, "total_steps": 609492, "loss": 1.9875, "lr": 3.6290199864358326e-10, "epoch": 11.854462404756749, "percentage": 98.79, "elapsed_time": "0:33:25", "remaining_time": "0:00:24", "throughput": 305642.32, "total_tokens": 613059136} {"current_steps": 602200, "total_steps": 609492, "loss": 1.9834, "lr": 3.531507846943893e-10, "epoch": 11.856431257506252, "percentage": 98.8, "elapsed_time": "0:33:37", "remaining_time": "0:00:24", "throughput": 303915.22, "total_tokens": 613160608} {"current_steps": 602300, "total_steps": 609492, "loss": 1.9761, "lr": 3.435323227599096e-10, "epoch": 11.858400110255754, "percentage": 98.82, "elapsed_time": "0:33:49", "remaining_time": "0:00:24", "throughput": 302186.17, "total_tokens": 613262392} {"current_steps": 602400, "total_steps": 609492, "loss": 1.9958, "lr": 3.340466153957111e-10, "epoch": 11.860368963005257, "percentage": 98.84, "elapsed_time": "0:34:01", "remaining_time": "0:00:24", "throughput": 300490.49, "total_tokens": 613364792} {"current_steps": 602500, "total_steps": 609492, "loss": 1.9794, "lr": 3.24693665122e-10, "epoch": 11.86233781575476, "percentage": 98.85, "elapsed_time": "0:34:12", "remaining_time": "0:00:23", "throughput": 298820.94, "total_tokens": 613466696} {"current_steps": 602600, "total_steps": 609492, "loss": 1.9959, "lr": 3.1547347442384406e-10, "epoch": 11.864306668504263, "percentage": 98.87, "elapsed_time": "0:34:24", "remaining_time": "0:00:23", "throughput": 297188.72, "total_tokens": 613567792} {"current_steps": 602700, "total_steps": 609492, "loss": 2.0291, "lr": 3.063860457508949e-10, "epoch": 11.866275521253765, "percentage": 98.89, "elapsed_time": "0:34:36", "remaining_time": "0:00:23", "throughput": 295566.17, "total_tokens": 613669760} {"current_steps": 602800, "total_steps": 609492, "loss": 1.9732, "lr": 2.9743138151766546e-10, "epoch": 11.868244374003268, "percentage": 98.9, "elapsed_time": "0:34:47", "remaining_time": "0:00:23", "throughput": 293965.39, "total_tokens": 613771232} {"current_steps": 602900, "total_steps": 609492, "loss": 1.9883, "lr": 2.886094841033637e-10, "epoch": 11.870213226752771, "percentage": 98.92, "elapsed_time": "0:34:59", "remaining_time": "0:00:22", "throughput": 292397.39, "total_tokens": 613871376} {"current_steps": 603000, "total_steps": 609492, "loss": 2.0485, "lr": 2.799203558517815e-10, "epoch": 11.872182079502274, "percentage": 98.93, "elapsed_time": "0:35:11", "remaining_time": "0:00:22", "throughput": 290839.54, "total_tokens": 613972416} {"current_steps": 603100, "total_steps": 609492, "loss": 1.9821, "lr": 2.713639990716832e-10, "epoch": 11.874150932251776, "percentage": 98.95, "elapsed_time": "0:35:22", "remaining_time": "0:00:22", "throughput": 289296.97, "total_tokens": 614073528} {"current_steps": 603200, "total_steps": 609492, "loss": 1.926, "lr": 2.629404160363058e-10, "epoch": 11.87611978500128, "percentage": 98.97, "elapsed_time": "0:35:34", "remaining_time": "0:00:22", "throughput": 287758.88, "total_tokens": 614175928} {"current_steps": 603300, "total_steps": 609492, "loss": 1.9753, "lr": 2.546496089838035e-10, "epoch": 11.878088637750782, "percentage": 98.98, "elapsed_time": "0:35:46", "remaining_time": "0:00:22", "throughput": 286236.56, "total_tokens": 614278328} {"current_steps": 603400, "total_steps": 609492, "loss": 1.9688, "lr": 2.464915801169143e-10, "epoch": 11.880057490500285, "percentage": 99.0, "elapsed_time": "0:35:57", "remaining_time": "0:00:21", "throughput": 284738.27, "total_tokens": 614379912} {"current_steps": 603500, "total_steps": 609492, "loss": 2.0239, "lr": 2.384663316032376e-10, "epoch": 11.882026343249787, "percentage": 99.02, "elapsed_time": "0:36:09", "remaining_time": "0:00:21", "throughput": 283255.23, "total_tokens": 614481512} {"current_steps": 603600, "total_steps": 609492, "loss": 1.9905, "lr": 2.3057386557495674e-10, "epoch": 11.883995195999292, "percentage": 99.03, "elapsed_time": "0:36:21", "remaining_time": "0:00:21", "throughput": 281788.13, "total_tokens": 614583072} {"current_steps": 603700, "total_steps": 609492, "loss": 1.9786, "lr": 2.2281418412906095e-10, "epoch": 11.885964048748795, "percentage": 99.05, "elapsed_time": "0:36:32", "remaining_time": "0:00:21", "throughput": 280336.59, "total_tokens": 614684672} {"current_steps": 603800, "total_steps": 609492, "loss": 1.9951, "lr": 2.151872893271789e-10, "epoch": 11.887932901498298, "percentage": 99.07, "elapsed_time": "0:36:44", "remaining_time": "0:00:20", "throughput": 278902.58, "total_tokens": 614786264} {"current_steps": 603900, "total_steps": 609492, "loss": 1.9598, "lr": 2.0769318319580065e-10, "epoch": 11.8899017542478, "percentage": 99.08, "elapsed_time": "0:36:56", "remaining_time": "0:00:20", "throughput": 277472.95, "total_tokens": 614888128} {"current_steps": 604000, "total_steps": 609492, "loss": 2.0105, "lr": 2.0033186772594468e-10, "epoch": 11.891870606997303, "percentage": 99.1, "elapsed_time": "0:37:07", "remaining_time": "0:00:20", "throughput": 276052.37, "total_tokens": 614990072} {"current_steps": 604100, "total_steps": 609492, "loss": 1.982, "lr": 1.9310334487354641e-10, "epoch": 11.893839459746806, "percentage": 99.12, "elapsed_time": "0:37:19", "remaining_time": "0:00:19", "throughput": 274651.96, "total_tokens": 615091848} {"current_steps": 604200, "total_steps": 609492, "loss": 1.9581, "lr": 1.8600761655912512e-10, "epoch": 11.895808312496309, "percentage": 99.13, "elapsed_time": "0:37:31", "remaining_time": "0:00:19", "throughput": 273266.57, "total_tokens": 615194248} {"current_steps": 604300, "total_steps": 609492, "loss": 1.9834, "lr": 1.7904468466795054e-10, "epoch": 11.897777165245811, "percentage": 99.15, "elapsed_time": "0:37:42", "remaining_time": "0:00:19", "throughput": 271897.28, "total_tokens": 615295800} {"current_steps": 604400, "total_steps": 609492, "loss": 2.0045, "lr": 1.722145510499873e-10, "epoch": 11.899746017995314, "percentage": 99.16, "elapsed_time": "0:37:54", "remaining_time": "0:00:19", "throughput": 270528.26, "total_tokens": 615398200} {"current_steps": 604500, "total_steps": 609492, "loss": 1.9594, "lr": 1.655172175200059e-10, "epoch": 11.901714870744817, "percentage": 99.18, "elapsed_time": "0:38:06", "remaining_time": "0:00:18", "throughput": 269176.81, "total_tokens": 615500072} {"current_steps": 604600, "total_steps": 609492, "loss": 1.9738, "lr": 1.589526858574164e-10, "epoch": 11.90368372349432, "percentage": 99.2, "elapsed_time": "0:38:18", "remaining_time": "0:00:18", "throughput": 267831.2, "total_tokens": 615601776} {"current_steps": 604700, "total_steps": 609492, "loss": 2.0208, "lr": 1.5252095780637907e-10, "epoch": 11.905652576243822, "percentage": 99.21, "elapsed_time": "0:38:30", "remaining_time": "0:00:18", "throughput": 266498.59, "total_tokens": 615704176} {"current_steps": 604800, "total_steps": 609492, "loss": 1.9997, "lr": 1.4622203507569375e-10, "epoch": 11.907621428993325, "percentage": 99.23, "elapsed_time": "0:38:42", "remaining_time": "0:00:18", "throughput": 265185.54, "total_tokens": 615805168} {"current_steps": 604900, "total_steps": 609492, "loss": 2.0192, "lr": 1.400559193389106e-10, "epoch": 11.909590281742828, "percentage": 99.25, "elapsed_time": "0:38:54", "remaining_time": "0:00:17", "throughput": 263875.74, "total_tokens": 615907568} {"current_steps": 605000, "total_steps": 609492, "loss": 2.0046, "lr": 1.340226122344412e-10, "epoch": 11.91155913449233, "percentage": 99.26, "elapsed_time": "0:39:06", "remaining_time": "0:00:17", "throughput": 262555.68, "total_tokens": 616009968} {"current_steps": 605100, "total_steps": 609492, "loss": 1.9669, "lr": 1.2812211536517016e-10, "epoch": 11.913527987241833, "percentage": 99.28, "elapsed_time": "0:39:19", "remaining_time": "0:00:17", "throughput": 261169.48, "total_tokens": 616111552} {"current_steps": 605200, "total_steps": 609492, "loss": 1.9956, "lr": 1.223544302988433e-10, "epoch": 11.915496839991338, "percentage": 99.3, "elapsed_time": "0:39:30", "remaining_time": "0:00:16", "throughput": 259898.9, "total_tokens": 616213952} {"current_steps": 605300, "total_steps": 609492, "loss": 2.0026, "lr": 1.167195585679015e-10, "epoch": 11.91746569274084, "percentage": 99.31, "elapsed_time": "0:39:42", "remaining_time": "0:00:16", "throughput": 258652.69, "total_tokens": 616316352} {"current_steps": 605400, "total_steps": 609492, "loss": 1.9802, "lr": 1.1121750166948052e-10, "epoch": 11.919434545490343, "percentage": 99.33, "elapsed_time": "0:39:54", "remaining_time": "0:00:16", "throughput": 257444.84, "total_tokens": 616417960} {"current_steps": 605500, "total_steps": 609492, "loss": 1.9955, "lr": 1.05848261065411e-10, "epoch": 11.921403398239846, "percentage": 99.35, "elapsed_time": "0:40:05", "remaining_time": "0:00:15", "throughput": 256244.85, "total_tokens": 616520360} {"current_steps": 605600, "total_steps": 609492, "loss": 2.008, "lr": 1.0061183818227403e-10, "epoch": 11.923372250989349, "percentage": 99.36, "elapsed_time": "0:40:17", "remaining_time": "0:00:15", "throughput": 255055.64, "total_tokens": 616622760} {"current_steps": 605700, "total_steps": 609492, "loss": 2.0313, "lr": 9.550823441134559e-11, "epoch": 11.925341103738852, "percentage": 99.38, "elapsed_time": "0:40:29", "remaining_time": "0:00:15", "throughput": 253878.46, "total_tokens": 616723584} {"current_steps": 605800, "total_steps": 609492, "loss": 2.01, "lr": 9.053745110859656e-11, "epoch": 11.927309956488354, "percentage": 99.39, "elapsed_time": "0:40:40", "remaining_time": "0:00:14", "throughput": 252726.02, "total_tokens": 616824488} {"current_steps": 605900, "total_steps": 609492, "loss": 2.0303, "lr": 8.569948959474827e-11, "epoch": 11.929278809237857, "percentage": 99.41, "elapsed_time": "0:40:52", "remaining_time": "0:00:14", "throughput": 251573.33, "total_tokens": 616926888} {"current_steps": 606000, "total_steps": 609492, "loss": 1.968, "lr": 8.099435115521691e-11, "epoch": 11.93124766198736, "percentage": 99.43, "elapsed_time": "0:41:03", "remaining_time": "0:00:14", "throughput": 250425.41, "total_tokens": 617028512} {"current_steps": 606100, "total_steps": 609492, "loss": 2.0075, "lr": 7.642203704000261e-11, "epoch": 11.933216514736863, "percentage": 99.44, "elapsed_time": "0:41:15", "remaining_time": "0:00:13", "throughput": 249294.78, "total_tokens": 617130264} {"current_steps": 606200, "total_steps": 609492, "loss": 1.979, "lr": 7.198254846407792e-11, "epoch": 11.935185367486365, "percentage": 99.46, "elapsed_time": "0:41:27", "remaining_time": "0:00:13", "throughput": 248167.19, "total_tokens": 617232320} {"current_steps": 606300, "total_steps": 609492, "loss": 2.0086, "lr": 6.767588660694378e-11, "epoch": 11.937154220235868, "percentage": 99.48, "elapsed_time": "0:41:38", "remaining_time": "0:00:13", "throughput": 247047.41, "total_tokens": 617334088} {"current_steps": 606400, "total_steps": 609492, "loss": 1.9897, "lr": 6.350205261274055e-11, "epoch": 11.939123072985371, "percentage": 99.49, "elapsed_time": "0:41:50", "remaining_time": "0:00:12", "throughput": 245938.79, "total_tokens": 617436488} {"current_steps": 606500, "total_steps": 609492, "loss": 2.0329, "lr": 5.946104759058102e-11, "epoch": 11.941091925734874, "percentage": 99.51, "elapsed_time": "0:42:02", "remaining_time": "0:00:12", "throughput": 244853.8, "total_tokens": 617537816} {"current_steps": 606600, "total_steps": 609492, "loss": 1.9813, "lr": 5.555287261399533e-11, "epoch": 11.943060778484377, "percentage": 99.53, "elapsed_time": "0:42:13", "remaining_time": "0:00:12", "throughput": 243763.46, "total_tokens": 617640216} {"current_steps": 606700, "total_steps": 609492, "loss": 1.9675, "lr": 5.1777528721430595e-11, "epoch": 11.94502963123388, "percentage": 99.54, "elapsed_time": "0:42:25", "remaining_time": "0:00:11", "throughput": 242684.81, "total_tokens": 617742616} {"current_steps": 606800, "total_steps": 609492, "loss": 2.0206, "lr": 4.8135016915917815e-11, "epoch": 11.946998483983382, "percentage": 99.56, "elapsed_time": "0:42:37", "remaining_time": "0:00:11", "throughput": 241619.87, "total_tokens": 617844024} {"current_steps": 606900, "total_steps": 609492, "loss": 1.9695, "lr": 4.462533816523839e-11, "epoch": 11.948967336732887, "percentage": 99.57, "elapsed_time": "0:42:48", "remaining_time": "0:00:10", "throughput": 240551.71, "total_tokens": 617946424} {"current_steps": 607000, "total_steps": 609492, "loss": 1.9561, "lr": 4.1248493401924154e-11, "epoch": 11.95093618948239, "percentage": 99.59, "elapsed_time": "0:43:00", "remaining_time": "0:00:10", "throughput": 239500.87, "total_tokens": 618048824} {"current_steps": 607100, "total_steps": 609492, "loss": 1.9766, "lr": 3.8004483523201846e-11, "epoch": 11.952905042231892, "percentage": 99.61, "elapsed_time": "0:43:12", "remaining_time": "0:00:10", "throughput": 238446.21, "total_tokens": 618151224} {"current_steps": 607200, "total_steps": 609492, "loss": 2.033, "lr": 3.4893309390882084e-11, "epoch": 11.954873894981395, "percentage": 99.62, "elapsed_time": "0:43:24", "remaining_time": "0:00:09", "throughput": 237392.63, "total_tokens": 618253480} {"current_steps": 607300, "total_steps": 609492, "loss": 1.9738, "lr": 3.191497183169245e-11, "epoch": 11.956842747730898, "percentage": 99.64, "elapsed_time": "0:43:36", "remaining_time": "0:00:09", "throughput": 236352.43, "total_tokens": 618355880} {"current_steps": 607400, "total_steps": 609492, "loss": 2.0233, "lr": 2.9069471636833375e-11, "epoch": 11.9588116004804, "percentage": 99.66, "elapsed_time": "0:43:48", "remaining_time": "0:00:09", "throughput": 235318.62, "total_tokens": 618457680} {"current_steps": 607500, "total_steps": 609492, "loss": 1.9637, "lr": 2.6356809562422254e-11, "epoch": 11.960780453229903, "percentage": 99.67, "elapsed_time": "0:43:59", "remaining_time": "0:00:08", "throughput": 234313.34, "total_tokens": 618559264} {"current_steps": 607600, "total_steps": 609492, "loss": 1.9714, "lr": 2.3776986329104853e-11, "epoch": 11.962749305979406, "percentage": 99.69, "elapsed_time": "0:44:11", "remaining_time": "0:00:08", "throughput": 233322.02, "total_tokens": 618661664} {"current_steps": 607700, "total_steps": 609492, "loss": 1.9451, "lr": 2.133000262244389e-11, "epoch": 11.964718158728909, "percentage": 99.71, "elapsed_time": "0:44:23", "remaining_time": "0:00:07", "throughput": 232339.87, "total_tokens": 618763152} {"current_steps": 607800, "total_steps": 609492, "loss": 2.0128, "lr": 1.901585909247494e-11, "epoch": 11.966687011478411, "percentage": 99.72, "elapsed_time": "0:44:34", "remaining_time": "0:00:07", "throughput": 231362.97, "total_tokens": 618865552} {"current_steps": 607900, "total_steps": 609492, "loss": 1.9903, "lr": 1.683455635403952e-11, "epoch": 11.968655864227914, "percentage": 99.74, "elapsed_time": "0:44:46", "remaining_time": "0:00:07", "throughput": 230391.77, "total_tokens": 618967856} {"current_steps": 608000, "total_steps": 609492, "loss": 2.005, "lr": 1.478609498678507e-11, "epoch": 11.970624716977417, "percentage": 99.76, "elapsed_time": "0:44:58", "remaining_time": "0:00:06", "throughput": 229432.14, "total_tokens": 619069488} {"current_steps": 608100, "total_steps": 609492, "loss": 1.9584, "lr": 1.2870475534942915e-11, "epoch": 11.97259356972692, "percentage": 99.77, "elapsed_time": "0:45:10", "remaining_time": "0:00:06", "throughput": 228474.82, "total_tokens": 619171888} {"current_steps": 608200, "total_steps": 609492, "loss": 1.9683, "lr": 1.1087698507383781e-11, "epoch": 11.974562422476422, "percentage": 99.79, "elapsed_time": "0:45:21", "remaining_time": "0:00:05", "throughput": 227535.44, "total_tokens": 619273856} {"current_steps": 608300, "total_steps": 609492, "loss": 1.9758, "lr": 9.43776437789534e-12, "epoch": 11.976531275225925, "percentage": 99.8, "elapsed_time": "0:45:33", "remaining_time": "0:00:05", "throughput": 226600.82, "total_tokens": 619374808} {"current_steps": 608400, "total_steps": 609492, "loss": 2.0262, "lr": 7.920673584793646e-12, "epoch": 11.978500127975428, "percentage": 99.82, "elapsed_time": "0:45:44", "remaining_time": "0:00:04", "throughput": 225680.27, "total_tokens": 619476568} {"current_steps": 608500, "total_steps": 609492, "loss": 1.9921, "lr": 6.536426531145167e-12, "epoch": 11.980468980724932, "percentage": 99.84, "elapsed_time": "0:45:56", "remaining_time": "0:00:04", "throughput": 224757.71, "total_tokens": 619578008} {"current_steps": 608600, "total_steps": 609492, "loss": 1.991, "lr": 5.28502358476679e-12, "epoch": 11.982437833474435, "percentage": 99.85, "elapsed_time": "0:46:08", "remaining_time": "0:00:04", "throughput": 223841.89, "total_tokens": 619680408} {"current_steps": 608700, "total_steps": 609492, "loss": 1.9481, "lr": 4.1664650781148e-12, "epoch": 11.984406686223938, "percentage": 99.87, "elapsed_time": "0:46:20", "remaining_time": "0:00:03", "throughput": 222924.9, "total_tokens": 619782808} {"current_steps": 608800, "total_steps": 609492, "loss": 1.9444, "lr": 3.1807513084514127e-12, "epoch": 11.98637553897344, "percentage": 99.89, "elapsed_time": "0:46:31", "remaining_time": "0:00:03", "throughput": 222033.51, "total_tokens": 619885000} {"current_steps": 608900, "total_steps": 609492, "loss": 1.957, "lr": 2.3278825375672163e-12, "epoch": 11.988344391722944, "percentage": 99.9, "elapsed_time": "0:46:43", "remaining_time": "0:00:02", "throughput": 221145.11, "total_tokens": 619987400} {"current_steps": 609000, "total_steps": 609492, "loss": 2.0438, "lr": 1.6078589921142417e-12, "epoch": 11.990313244472446, "percentage": 99.92, "elapsed_time": "0:46:55", "remaining_time": "0:00:02", "throughput": 220258.6, "total_tokens": 620089800} {"current_steps": 609100, "total_steps": 609492, "loss": 1.9305, "lr": 1.0206808634394271e-12, "epoch": 11.992282097221949, "percentage": 99.94, "elapsed_time": "0:47:07", "remaining_time": "0:00:01", "throughput": 219369.78, "total_tokens": 620192200} {"current_steps": 609200, "total_steps": 609492, "loss": 1.9854, "lr": 5.663483074735965e-13, "epoch": 11.994250949971452, "percentage": 99.95, "elapsed_time": "0:47:19", "remaining_time": "0:00:01", "throughput": 218488.66, "total_tokens": 620294600} {"current_steps": 609300, "total_steps": 609492, "loss": 1.9765, "lr": 2.4486144495350357e-13, "epoch": 11.996219802720955, "percentage": 99.97, "elapsed_time": "0:47:30", "remaining_time": "0:00:00", "throughput": 217621.92, "total_tokens": 620397000} {"current_steps": 609400, "total_steps": 609492, "loss": 1.9388, "lr": 5.622036136632147e-14, "epoch": 11.998188655470457, "percentage": 99.98, "elapsed_time": "0:47:42", "remaining_time": "0:00:00", "throughput": 216764.99, "total_tokens": 620499400} {"current_steps": 609492, "total_steps": 609492, "epoch": 12.0, "percentage": 100.0, "elapsed_time": "0:47:54", "remaining_time": "0:00:00", "throughput": 215932.48, "total_tokens": 620593344}