| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 2.996011396011396, | |
| "eval_steps": 500, | |
| "global_step": 1314, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.022792022792022793, | |
| "grad_norm": 1.0739810245051853, | |
| "learning_rate": 5e-06, | |
| "loss": 0.7537, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.045584045584045586, | |
| "grad_norm": 0.7994628101956647, | |
| "learning_rate": 5e-06, | |
| "loss": 0.6991, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.06837606837606838, | |
| "grad_norm": 0.9145323254714245, | |
| "learning_rate": 5e-06, | |
| "loss": 0.6789, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.09116809116809117, | |
| "grad_norm": 0.8605909593743031, | |
| "learning_rate": 5e-06, | |
| "loss": 0.679, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.11396011396011396, | |
| "grad_norm": 0.8021870035086972, | |
| "learning_rate": 5e-06, | |
| "loss": 0.6752, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.13675213675213677, | |
| "grad_norm": 0.6758926016729375, | |
| "learning_rate": 5e-06, | |
| "loss": 0.655, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.15954415954415954, | |
| "grad_norm": 0.44534893164174444, | |
| "learning_rate": 5e-06, | |
| "loss": 0.6519, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.18233618233618235, | |
| "grad_norm": 0.37696622527442364, | |
| "learning_rate": 5e-06, | |
| "loss": 0.6549, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 0.20512820512820512, | |
| "grad_norm": 0.3175419708991312, | |
| "learning_rate": 5e-06, | |
| "loss": 0.6398, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 0.22792022792022792, | |
| "grad_norm": 0.3001218213930502, | |
| "learning_rate": 5e-06, | |
| "loss": 0.641, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.25071225071225073, | |
| "grad_norm": 0.34223463985482955, | |
| "learning_rate": 5e-06, | |
| "loss": 0.6324, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 0.27350427350427353, | |
| "grad_norm": 0.3077308175103466, | |
| "learning_rate": 5e-06, | |
| "loss": 0.6406, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 0.2962962962962963, | |
| "grad_norm": 0.29617511795201973, | |
| "learning_rate": 5e-06, | |
| "loss": 0.6416, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 0.3190883190883191, | |
| "grad_norm": 0.3026818192606662, | |
| "learning_rate": 5e-06, | |
| "loss": 0.6437, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 0.3418803418803419, | |
| "grad_norm": 0.311148025960206, | |
| "learning_rate": 5e-06, | |
| "loss": 0.6362, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 0.3646723646723647, | |
| "grad_norm": 0.31361619274470914, | |
| "learning_rate": 5e-06, | |
| "loss": 0.6414, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 0.38746438746438744, | |
| "grad_norm": 0.3521303409556207, | |
| "learning_rate": 5e-06, | |
| "loss": 0.6332, | |
| "step": 170 | |
| }, | |
| { | |
| "epoch": 0.41025641025641024, | |
| "grad_norm": 0.30576342429819114, | |
| "learning_rate": 5e-06, | |
| "loss": 0.6388, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 0.43304843304843305, | |
| "grad_norm": 0.30702497736375933, | |
| "learning_rate": 5e-06, | |
| "loss": 0.6314, | |
| "step": 190 | |
| }, | |
| { | |
| "epoch": 0.45584045584045585, | |
| "grad_norm": 0.307653504666299, | |
| "learning_rate": 5e-06, | |
| "loss": 0.6394, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.47863247863247865, | |
| "grad_norm": 0.31105273484324014, | |
| "learning_rate": 5e-06, | |
| "loss": 0.6357, | |
| "step": 210 | |
| }, | |
| { | |
| "epoch": 0.5014245014245015, | |
| "grad_norm": 0.30250447453896917, | |
| "learning_rate": 5e-06, | |
| "loss": 0.6395, | |
| "step": 220 | |
| }, | |
| { | |
| "epoch": 0.5242165242165242, | |
| "grad_norm": 0.3285222887381629, | |
| "learning_rate": 5e-06, | |
| "loss": 0.6351, | |
| "step": 230 | |
| }, | |
| { | |
| "epoch": 0.5470085470085471, | |
| "grad_norm": 0.3003044142913783, | |
| "learning_rate": 5e-06, | |
| "loss": 0.6309, | |
| "step": 240 | |
| }, | |
| { | |
| "epoch": 0.5698005698005698, | |
| "grad_norm": 0.34194673362428835, | |
| "learning_rate": 5e-06, | |
| "loss": 0.6359, | |
| "step": 250 | |
| }, | |
| { | |
| "epoch": 0.5925925925925926, | |
| "grad_norm": 0.3001674574869448, | |
| "learning_rate": 5e-06, | |
| "loss": 0.6341, | |
| "step": 260 | |
| }, | |
| { | |
| "epoch": 0.6153846153846154, | |
| "grad_norm": 0.30835975993743914, | |
| "learning_rate": 5e-06, | |
| "loss": 0.6312, | |
| "step": 270 | |
| }, | |
| { | |
| "epoch": 0.6381766381766382, | |
| "grad_norm": 0.32126177521374477, | |
| "learning_rate": 5e-06, | |
| "loss": 0.642, | |
| "step": 280 | |
| }, | |
| { | |
| "epoch": 0.6609686609686609, | |
| "grad_norm": 0.3253562411712521, | |
| "learning_rate": 5e-06, | |
| "loss": 0.6307, | |
| "step": 290 | |
| }, | |
| { | |
| "epoch": 0.6837606837606838, | |
| "grad_norm": 0.2870970459590682, | |
| "learning_rate": 5e-06, | |
| "loss": 0.6287, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 0.7065527065527065, | |
| "grad_norm": 0.296336527986831, | |
| "learning_rate": 5e-06, | |
| "loss": 0.6286, | |
| "step": 310 | |
| }, | |
| { | |
| "epoch": 0.7293447293447294, | |
| "grad_norm": 0.3438955274688111, | |
| "learning_rate": 5e-06, | |
| "loss": 0.6292, | |
| "step": 320 | |
| }, | |
| { | |
| "epoch": 0.7521367521367521, | |
| "grad_norm": 0.30319693533541087, | |
| "learning_rate": 5e-06, | |
| "loss": 0.6258, | |
| "step": 330 | |
| }, | |
| { | |
| "epoch": 0.7749287749287749, | |
| "grad_norm": 0.3301388859131474, | |
| "learning_rate": 5e-06, | |
| "loss": 0.6316, | |
| "step": 340 | |
| }, | |
| { | |
| "epoch": 0.7977207977207977, | |
| "grad_norm": 0.3332319279933739, | |
| "learning_rate": 5e-06, | |
| "loss": 0.6387, | |
| "step": 350 | |
| }, | |
| { | |
| "epoch": 0.8205128205128205, | |
| "grad_norm": 0.3184518153582213, | |
| "learning_rate": 5e-06, | |
| "loss": 0.6304, | |
| "step": 360 | |
| }, | |
| { | |
| "epoch": 0.8433048433048433, | |
| "grad_norm": 0.3306671049781329, | |
| "learning_rate": 5e-06, | |
| "loss": 0.6242, | |
| "step": 370 | |
| }, | |
| { | |
| "epoch": 0.8660968660968661, | |
| "grad_norm": 0.31692381604068587, | |
| "learning_rate": 5e-06, | |
| "loss": 0.6365, | |
| "step": 380 | |
| }, | |
| { | |
| "epoch": 0.8888888888888888, | |
| "grad_norm": 0.3349551362656854, | |
| "learning_rate": 5e-06, | |
| "loss": 0.6351, | |
| "step": 390 | |
| }, | |
| { | |
| "epoch": 0.9116809116809117, | |
| "grad_norm": 0.29774461380303896, | |
| "learning_rate": 5e-06, | |
| "loss": 0.6383, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 0.9344729344729344, | |
| "grad_norm": 0.2898640827900439, | |
| "learning_rate": 5e-06, | |
| "loss": 0.6345, | |
| "step": 410 | |
| }, | |
| { | |
| "epoch": 0.9572649572649573, | |
| "grad_norm": 0.3030450796705357, | |
| "learning_rate": 5e-06, | |
| "loss": 0.6214, | |
| "step": 420 | |
| }, | |
| { | |
| "epoch": 0.98005698005698, | |
| "grad_norm": 0.34293518568964354, | |
| "learning_rate": 5e-06, | |
| "loss": 0.6344, | |
| "step": 430 | |
| }, | |
| { | |
| "epoch": 0.9982905982905983, | |
| "eval_loss": 0.6250933408737183, | |
| "eval_runtime": 445.0313, | |
| "eval_samples_per_second": 26.567, | |
| "eval_steps_per_second": 0.416, | |
| "step": 438 | |
| }, | |
| { | |
| "epoch": 1.0034188034188034, | |
| "grad_norm": 0.3496591762247317, | |
| "learning_rate": 5e-06, | |
| "loss": 0.6472, | |
| "step": 440 | |
| }, | |
| { | |
| "epoch": 1.0262108262108263, | |
| "grad_norm": 0.3295177102407471, | |
| "learning_rate": 5e-06, | |
| "loss": 0.6016, | |
| "step": 450 | |
| }, | |
| { | |
| "epoch": 1.049002849002849, | |
| "grad_norm": 0.3161845171846921, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5954, | |
| "step": 460 | |
| }, | |
| { | |
| "epoch": 1.0717948717948718, | |
| "grad_norm": 0.2906063821439931, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5962, | |
| "step": 470 | |
| }, | |
| { | |
| "epoch": 1.0945868945868946, | |
| "grad_norm": 0.30805772899801226, | |
| "learning_rate": 5e-06, | |
| "loss": 0.6037, | |
| "step": 480 | |
| }, | |
| { | |
| "epoch": 1.1173789173789175, | |
| "grad_norm": 0.33477082326190616, | |
| "learning_rate": 5e-06, | |
| "loss": 0.6087, | |
| "step": 490 | |
| }, | |
| { | |
| "epoch": 1.1401709401709401, | |
| "grad_norm": 0.2887728257669836, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5986, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 1.162962962962963, | |
| "grad_norm": 0.3136735170329583, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5965, | |
| "step": 510 | |
| }, | |
| { | |
| "epoch": 1.1857549857549858, | |
| "grad_norm": 0.2927051539651346, | |
| "learning_rate": 5e-06, | |
| "loss": 0.6022, | |
| "step": 520 | |
| }, | |
| { | |
| "epoch": 1.2085470085470085, | |
| "grad_norm": 0.3239015995738983, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5952, | |
| "step": 530 | |
| }, | |
| { | |
| "epoch": 1.2313390313390313, | |
| "grad_norm": 0.2892848575930784, | |
| "learning_rate": 5e-06, | |
| "loss": 0.6055, | |
| "step": 540 | |
| }, | |
| { | |
| "epoch": 1.2541310541310542, | |
| "grad_norm": 0.33646769648023045, | |
| "learning_rate": 5e-06, | |
| "loss": 0.6021, | |
| "step": 550 | |
| }, | |
| { | |
| "epoch": 1.2769230769230768, | |
| "grad_norm": 0.2901600109400917, | |
| "learning_rate": 5e-06, | |
| "loss": 0.6036, | |
| "step": 560 | |
| }, | |
| { | |
| "epoch": 1.2997150997150997, | |
| "grad_norm": 0.31184131986048613, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5976, | |
| "step": 570 | |
| }, | |
| { | |
| "epoch": 1.3225071225071225, | |
| "grad_norm": 0.2695279664416552, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5961, | |
| "step": 580 | |
| }, | |
| { | |
| "epoch": 1.3452991452991454, | |
| "grad_norm": 0.29848016159193924, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5958, | |
| "step": 590 | |
| }, | |
| { | |
| "epoch": 1.368091168091168, | |
| "grad_norm": 0.3446971297569853, | |
| "learning_rate": 5e-06, | |
| "loss": 0.6014, | |
| "step": 600 | |
| }, | |
| { | |
| "epoch": 1.390883190883191, | |
| "grad_norm": 0.32024940335717283, | |
| "learning_rate": 5e-06, | |
| "loss": 0.6015, | |
| "step": 610 | |
| }, | |
| { | |
| "epoch": 1.4136752136752135, | |
| "grad_norm": 0.29585163109130136, | |
| "learning_rate": 5e-06, | |
| "loss": 0.6041, | |
| "step": 620 | |
| }, | |
| { | |
| "epoch": 1.4364672364672364, | |
| "grad_norm": 0.3167856171248506, | |
| "learning_rate": 5e-06, | |
| "loss": 0.6021, | |
| "step": 630 | |
| }, | |
| { | |
| "epoch": 1.4592592592592593, | |
| "grad_norm": 0.3049553700386225, | |
| "learning_rate": 5e-06, | |
| "loss": 0.597, | |
| "step": 640 | |
| }, | |
| { | |
| "epoch": 1.4820512820512821, | |
| "grad_norm": 0.29757036012290194, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5948, | |
| "step": 650 | |
| }, | |
| { | |
| "epoch": 1.504843304843305, | |
| "grad_norm": 0.291759060419908, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5945, | |
| "step": 660 | |
| }, | |
| { | |
| "epoch": 1.5276353276353276, | |
| "grad_norm": 0.3157827288327476, | |
| "learning_rate": 5e-06, | |
| "loss": 0.6022, | |
| "step": 670 | |
| }, | |
| { | |
| "epoch": 1.5504273504273505, | |
| "grad_norm": 0.2743215676996486, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5907, | |
| "step": 680 | |
| }, | |
| { | |
| "epoch": 1.573219373219373, | |
| "grad_norm": 0.32263652594832726, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5947, | |
| "step": 690 | |
| }, | |
| { | |
| "epoch": 1.596011396011396, | |
| "grad_norm": 0.28730967715918515, | |
| "learning_rate": 5e-06, | |
| "loss": 0.6102, | |
| "step": 700 | |
| }, | |
| { | |
| "epoch": 1.6188034188034188, | |
| "grad_norm": 0.3116433235624304, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5973, | |
| "step": 710 | |
| }, | |
| { | |
| "epoch": 1.6415954415954417, | |
| "grad_norm": 0.2896344272677128, | |
| "learning_rate": 5e-06, | |
| "loss": 0.6019, | |
| "step": 720 | |
| }, | |
| { | |
| "epoch": 1.6643874643874645, | |
| "grad_norm": 0.3282185407954139, | |
| "learning_rate": 5e-06, | |
| "loss": 0.595, | |
| "step": 730 | |
| }, | |
| { | |
| "epoch": 1.6871794871794872, | |
| "grad_norm": 0.322032527152575, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5961, | |
| "step": 740 | |
| }, | |
| { | |
| "epoch": 1.7099715099715098, | |
| "grad_norm": 0.30092223070733987, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5934, | |
| "step": 750 | |
| }, | |
| { | |
| "epoch": 1.7327635327635327, | |
| "grad_norm": 0.3142840082379115, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5974, | |
| "step": 760 | |
| }, | |
| { | |
| "epoch": 1.7555555555555555, | |
| "grad_norm": 0.29643234166018323, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5938, | |
| "step": 770 | |
| }, | |
| { | |
| "epoch": 1.7783475783475784, | |
| "grad_norm": 0.312901789138374, | |
| "learning_rate": 5e-06, | |
| "loss": 0.6009, | |
| "step": 780 | |
| }, | |
| { | |
| "epoch": 1.8011396011396013, | |
| "grad_norm": 0.2962685405787694, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5985, | |
| "step": 790 | |
| }, | |
| { | |
| "epoch": 1.823931623931624, | |
| "grad_norm": 0.31145106882464246, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5853, | |
| "step": 800 | |
| }, | |
| { | |
| "epoch": 1.8467236467236468, | |
| "grad_norm": 0.309467297432667, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5931, | |
| "step": 810 | |
| }, | |
| { | |
| "epoch": 1.8695156695156694, | |
| "grad_norm": 0.30355100124521783, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5909, | |
| "step": 820 | |
| }, | |
| { | |
| "epoch": 1.8923076923076922, | |
| "grad_norm": 0.32200762720000836, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5947, | |
| "step": 830 | |
| }, | |
| { | |
| "epoch": 1.915099715099715, | |
| "grad_norm": 0.3098948123749196, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5992, | |
| "step": 840 | |
| }, | |
| { | |
| "epoch": 1.937891737891738, | |
| "grad_norm": 0.30700981775160896, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5973, | |
| "step": 850 | |
| }, | |
| { | |
| "epoch": 1.9606837606837608, | |
| "grad_norm": 0.31319185289096263, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5986, | |
| "step": 860 | |
| }, | |
| { | |
| "epoch": 1.9834757834757835, | |
| "grad_norm": 0.35562707624163475, | |
| "learning_rate": 5e-06, | |
| "loss": 0.596, | |
| "step": 870 | |
| }, | |
| { | |
| "epoch": 1.9994301994301993, | |
| "eval_loss": 0.6187179088592529, | |
| "eval_runtime": 446.3898, | |
| "eval_samples_per_second": 26.486, | |
| "eval_steps_per_second": 0.414, | |
| "step": 877 | |
| }, | |
| { | |
| "epoch": 2.006837606837607, | |
| "grad_norm": 0.3417944185447755, | |
| "learning_rate": 5e-06, | |
| "loss": 0.6154, | |
| "step": 880 | |
| }, | |
| { | |
| "epoch": 2.0296296296296297, | |
| "grad_norm": 0.34616268875927075, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5546, | |
| "step": 890 | |
| }, | |
| { | |
| "epoch": 2.0524216524216525, | |
| "grad_norm": 0.29781053688788633, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5697, | |
| "step": 900 | |
| }, | |
| { | |
| "epoch": 2.0752136752136754, | |
| "grad_norm": 0.36039980373609887, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5678, | |
| "step": 910 | |
| }, | |
| { | |
| "epoch": 2.098005698005698, | |
| "grad_norm": 0.33211812332269275, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5709, | |
| "step": 920 | |
| }, | |
| { | |
| "epoch": 2.1207977207977207, | |
| "grad_norm": 0.2876489886321258, | |
| "learning_rate": 5e-06, | |
| "loss": 0.569, | |
| "step": 930 | |
| }, | |
| { | |
| "epoch": 2.1435897435897435, | |
| "grad_norm": 0.29881752400796563, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5636, | |
| "step": 940 | |
| }, | |
| { | |
| "epoch": 2.1663817663817664, | |
| "grad_norm": 0.31139094821795826, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5646, | |
| "step": 950 | |
| }, | |
| { | |
| "epoch": 2.1891737891737892, | |
| "grad_norm": 0.30636474244675393, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5696, | |
| "step": 960 | |
| }, | |
| { | |
| "epoch": 2.211965811965812, | |
| "grad_norm": 0.2894343716767469, | |
| "learning_rate": 5e-06, | |
| "loss": 0.569, | |
| "step": 970 | |
| }, | |
| { | |
| "epoch": 2.234757834757835, | |
| "grad_norm": 0.29002940785867926, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5587, | |
| "step": 980 | |
| }, | |
| { | |
| "epoch": 2.2575498575498574, | |
| "grad_norm": 0.32057223638674887, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5678, | |
| "step": 990 | |
| }, | |
| { | |
| "epoch": 2.2803418803418802, | |
| "grad_norm": 0.3048231629931698, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5681, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 2.303133903133903, | |
| "grad_norm": 0.3299934300807477, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5656, | |
| "step": 1010 | |
| }, | |
| { | |
| "epoch": 2.325925925925926, | |
| "grad_norm": 0.31087293705472, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5686, | |
| "step": 1020 | |
| }, | |
| { | |
| "epoch": 2.348717948717949, | |
| "grad_norm": 0.3494886385374996, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5699, | |
| "step": 1030 | |
| }, | |
| { | |
| "epoch": 2.3715099715099717, | |
| "grad_norm": 0.29899133294429575, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5679, | |
| "step": 1040 | |
| }, | |
| { | |
| "epoch": 2.394301994301994, | |
| "grad_norm": 0.30463402705936343, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5672, | |
| "step": 1050 | |
| }, | |
| { | |
| "epoch": 2.417094017094017, | |
| "grad_norm": 0.2945318595822716, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5756, | |
| "step": 1060 | |
| }, | |
| { | |
| "epoch": 2.43988603988604, | |
| "grad_norm": 0.29997491151695244, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5784, | |
| "step": 1070 | |
| }, | |
| { | |
| "epoch": 2.4626780626780627, | |
| "grad_norm": 0.3033305094849928, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5737, | |
| "step": 1080 | |
| }, | |
| { | |
| "epoch": 2.4854700854700855, | |
| "grad_norm": 0.3037964828678562, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5713, | |
| "step": 1090 | |
| }, | |
| { | |
| "epoch": 2.5082621082621084, | |
| "grad_norm": 0.30418855184587706, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5777, | |
| "step": 1100 | |
| }, | |
| { | |
| "epoch": 2.5310541310541312, | |
| "grad_norm": 0.3138371680814042, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5713, | |
| "step": 1110 | |
| }, | |
| { | |
| "epoch": 2.5538461538461537, | |
| "grad_norm": 0.3023135922454145, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5694, | |
| "step": 1120 | |
| }, | |
| { | |
| "epoch": 2.5766381766381765, | |
| "grad_norm": 0.30512938056640104, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5688, | |
| "step": 1130 | |
| }, | |
| { | |
| "epoch": 2.5994301994301994, | |
| "grad_norm": 0.31577166574147847, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5685, | |
| "step": 1140 | |
| }, | |
| { | |
| "epoch": 2.6222222222222222, | |
| "grad_norm": 0.30073490656170254, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5688, | |
| "step": 1150 | |
| }, | |
| { | |
| "epoch": 2.645014245014245, | |
| "grad_norm": 0.3126455724688638, | |
| "learning_rate": 5e-06, | |
| "loss": 0.57, | |
| "step": 1160 | |
| }, | |
| { | |
| "epoch": 2.667806267806268, | |
| "grad_norm": 0.2945936914416737, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5727, | |
| "step": 1170 | |
| }, | |
| { | |
| "epoch": 2.690598290598291, | |
| "grad_norm": 0.29259281033159984, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5679, | |
| "step": 1180 | |
| }, | |
| { | |
| "epoch": 2.7133903133903132, | |
| "grad_norm": 0.28737249917886826, | |
| "learning_rate": 5e-06, | |
| "loss": 0.569, | |
| "step": 1190 | |
| }, | |
| { | |
| "epoch": 2.736182336182336, | |
| "grad_norm": 0.29182583942629997, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5721, | |
| "step": 1200 | |
| }, | |
| { | |
| "epoch": 2.758974358974359, | |
| "grad_norm": 0.2895940448539701, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5755, | |
| "step": 1210 | |
| }, | |
| { | |
| "epoch": 2.781766381766382, | |
| "grad_norm": 0.2861124245272868, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5653, | |
| "step": 1220 | |
| }, | |
| { | |
| "epoch": 2.8045584045584047, | |
| "grad_norm": 0.29447466830382235, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5638, | |
| "step": 1230 | |
| }, | |
| { | |
| "epoch": 2.827350427350427, | |
| "grad_norm": 0.3091225464759551, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5787, | |
| "step": 1240 | |
| }, | |
| { | |
| "epoch": 2.8501424501424504, | |
| "grad_norm": 0.3053227321357754, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5753, | |
| "step": 1250 | |
| }, | |
| { | |
| "epoch": 2.872934472934473, | |
| "grad_norm": 0.29823852834350206, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5725, | |
| "step": 1260 | |
| }, | |
| { | |
| "epoch": 2.8957264957264957, | |
| "grad_norm": 0.3053854770280737, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5734, | |
| "step": 1270 | |
| }, | |
| { | |
| "epoch": 2.9185185185185185, | |
| "grad_norm": 0.28676487068028, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5636, | |
| "step": 1280 | |
| }, | |
| { | |
| "epoch": 2.9413105413105414, | |
| "grad_norm": 0.29912989395622075, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5638, | |
| "step": 1290 | |
| }, | |
| { | |
| "epoch": 2.9641025641025642, | |
| "grad_norm": 0.34162191616022247, | |
| "learning_rate": 5e-06, | |
| "loss": 0.565, | |
| "step": 1300 | |
| }, | |
| { | |
| "epoch": 2.9868945868945866, | |
| "grad_norm": 0.3075122515819171, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5748, | |
| "step": 1310 | |
| }, | |
| { | |
| "epoch": 2.996011396011396, | |
| "eval_loss": 0.618652880191803, | |
| "eval_runtime": 444.9412, | |
| "eval_samples_per_second": 26.572, | |
| "eval_steps_per_second": 0.416, | |
| "step": 1314 | |
| }, | |
| { | |
| "epoch": 2.996011396011396, | |
| "step": 1314, | |
| "total_flos": 2755219238682624.0, | |
| "train_loss": 0.6038940636897558, | |
| "train_runtime": 70682.398, | |
| "train_samples_per_second": 9.534, | |
| "train_steps_per_second": 0.019 | |
| } | |
| ], | |
| "logging_steps": 10, | |
| "max_steps": 1314, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 3, | |
| "save_steps": 500, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 2755219238682624.0, | |
| "train_batch_size": 8, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |