| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.09244356402954892, | |
| "eval_steps": 20, | |
| "global_step": 140, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0006603111716396351, | |
| "grad_norm": 300608.875, | |
| "learning_rate": 2.9999999999999997e-05, | |
| "loss": 118.0917, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0006603111716396351, | |
| "eval_loss": 15.74350357055664, | |
| "eval_runtime": 6.9487, | |
| "eval_samples_per_second": 71.236, | |
| "eval_steps_per_second": 71.236, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0013206223432792703, | |
| "grad_norm": 277566.0, | |
| "learning_rate": 5.9999999999999995e-05, | |
| "loss": 120.2507, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.0019809335149189055, | |
| "grad_norm": 418405.1875, | |
| "learning_rate": 8.999999999999999e-05, | |
| "loss": 143.5985, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.0026412446865585405, | |
| "grad_norm": 222641.09375, | |
| "learning_rate": 0.00011999999999999999, | |
| "loss": 113.3078, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.003301555858198176, | |
| "grad_norm": 80659.1640625, | |
| "learning_rate": 0.00015, | |
| "loss": 89.0113, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.003961867029837811, | |
| "grad_norm": 174515.8125, | |
| "learning_rate": 0.00017999999999999998, | |
| "loss": 92.8388, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.004622178201477446, | |
| "grad_norm": 68650.6640625, | |
| "learning_rate": 0.00020999999999999998, | |
| "loss": 88.8969, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.005282489373117081, | |
| "grad_norm": 52668.09765625, | |
| "learning_rate": 0.00023999999999999998, | |
| "loss": 83.2267, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.005942800544756717, | |
| "grad_norm": 61407.41796875, | |
| "learning_rate": 0.00027, | |
| "loss": 92.7579, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.006603111716396352, | |
| "grad_norm": 37122.61328125, | |
| "learning_rate": 0.0003, | |
| "loss": 84.5321, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.007263422888035987, | |
| "grad_norm": 58673.69921875, | |
| "learning_rate": 0.0002999911984174669, | |
| "loss": 93.7724, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.007923734059675622, | |
| "grad_norm": 121362.359375, | |
| "learning_rate": 0.0002999647947027726, | |
| "loss": 108.6176, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.008584045231315257, | |
| "grad_norm": 233485.53125, | |
| "learning_rate": 0.0002999207919545099, | |
| "loss": 105.0768, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.009244356402954892, | |
| "grad_norm": 318686.03125, | |
| "learning_rate": 0.0002998591953365965, | |
| "loss": 99.2428, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.009904667574594527, | |
| "grad_norm": 101194.0625, | |
| "learning_rate": 0.00029978001207766854, | |
| "loss": 95.0131, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.010564978746234162, | |
| "grad_norm": 83839.953125, | |
| "learning_rate": 0.00029968325147023263, | |
| "loss": 86.1607, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.011225289917873797, | |
| "grad_norm": 68342.7109375, | |
| "learning_rate": 0.000299568924869575, | |
| "loss": 85.744, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.011885601089513434, | |
| "grad_norm": 232218.078125, | |
| "learning_rate": 0.00029943704569242917, | |
| "loss": 89.0831, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.012545912261153069, | |
| "grad_norm": 142226.359375, | |
| "learning_rate": 0.0002992876294154013, | |
| "loss": 87.8575, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.013206223432792704, | |
| "grad_norm": 99313.8125, | |
| "learning_rate": 0.00029912069357315393, | |
| "loss": 91.0717, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.013206223432792704, | |
| "eval_loss": 15.472484588623047, | |
| "eval_runtime": 6.5506, | |
| "eval_samples_per_second": 75.565, | |
| "eval_steps_per_second": 75.565, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.013866534604432339, | |
| "grad_norm": 361644.25, | |
| "learning_rate": 0.00029893625775634835, | |
| "loss": 97.0436, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.014526845776071974, | |
| "grad_norm": 1564964.125, | |
| "learning_rate": 0.0002987343436093454, | |
| "loss": 279.3873, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.015187156947711609, | |
| "grad_norm": 1539204.875, | |
| "learning_rate": 0.00029851497482766547, | |
| "loss": 668.731, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.015847468119351244, | |
| "grad_norm": 2246419.0, | |
| "learning_rate": 0.00029827817715520773, | |
| "loss": 758.2188, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.01650777929099088, | |
| "grad_norm": 2776799.5, | |
| "learning_rate": 0.0002980239783812289, | |
| "loss": 546.4688, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.017168090462630514, | |
| "grad_norm": 1617533.25, | |
| "learning_rate": 0.0002977524083370822, | |
| "loss": 422.7344, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.01782840163427015, | |
| "grad_norm": 450934.75, | |
| "learning_rate": 0.00029746349889271645, | |
| "loss": 339.3945, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.018488712805909784, | |
| "grad_norm": 2286499.5, | |
| "learning_rate": 0.0002971572839529358, | |
| "loss": 236.2812, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.01914902397754942, | |
| "grad_norm": 3999992.25, | |
| "learning_rate": 0.00029683379945342125, | |
| "loss": 159.8123, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.019809335149189054, | |
| "grad_norm": 308621.125, | |
| "learning_rate": 0.000296493083356513, | |
| "loss": 124.3508, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.02046964632082869, | |
| "grad_norm": 497120.59375, | |
| "learning_rate": 0.00029613517564675565, | |
| "loss": 138.8941, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.021129957492468324, | |
| "grad_norm": 99928.7890625, | |
| "learning_rate": 0.0002957601183262058, | |
| "loss": 151.8223, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.02179026866410796, | |
| "grad_norm": 405539.0625, | |
| "learning_rate": 0.000295367955409503, | |
| "loss": 1203.2074, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.022450579835747594, | |
| "grad_norm": 463994.21875, | |
| "learning_rate": 0.00029495873291870436, | |
| "loss": 1256.5367, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.02311089100738723, | |
| "grad_norm": 953879.5625, | |
| "learning_rate": 0.0002945324988778834, | |
| "loss": 938.6675, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.023771202179026868, | |
| "grad_norm": 178221.28125, | |
| "learning_rate": 0.00029408930330749477, | |
| "loss": 356.9532, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.0244315133506665, | |
| "grad_norm": 146182.625, | |
| "learning_rate": 0.0002936291982185036, | |
| "loss": 238.3703, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.025091824522306138, | |
| "grad_norm": 116065.7421875, | |
| "learning_rate": 0.00029315223760628217, | |
| "loss": 212.9555, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.02575213569394577, | |
| "grad_norm": 129193.03125, | |
| "learning_rate": 0.00029265847744427303, | |
| "loss": 227.929, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.026412446865585408, | |
| "grad_norm": 152996.75, | |
| "learning_rate": 0.00029214797567742035, | |
| "loss": 220.4361, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.026412446865585408, | |
| "eval_loss": 16.9798526763916, | |
| "eval_runtime": 6.5479, | |
| "eval_samples_per_second": 75.597, | |
| "eval_steps_per_second": 75.597, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.02707275803722504, | |
| "grad_norm": 166313.5, | |
| "learning_rate": 0.00029162079221537, | |
| "loss": 178.7949, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 0.027733069208864678, | |
| "grad_norm": 135891.28125, | |
| "learning_rate": 0.0002910769889254386, | |
| "loss": 201.0785, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.02839338038050431, | |
| "grad_norm": 64060.7890625, | |
| "learning_rate": 0.0002905166296253533, | |
| "loss": 163.5094, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 0.029053691552143948, | |
| "grad_norm": 96362.4921875, | |
| "learning_rate": 0.0002899397800757626, | |
| "loss": 140.6384, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.02971400272378358, | |
| "grad_norm": 166254.203125, | |
| "learning_rate": 0.0002893465079725187, | |
| "loss": 139.1684, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.030374313895423218, | |
| "grad_norm": 161925.5625, | |
| "learning_rate": 0.0002887368829387333, | |
| "loss": 140.9152, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 0.031034625067062855, | |
| "grad_norm": 637966.3125, | |
| "learning_rate": 0.0002881109765166071, | |
| "loss": 131.3419, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 0.03169493623870249, | |
| "grad_norm": 367775.03125, | |
| "learning_rate": 0.00028746886215903387, | |
| "loss": 155.0525, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.032355247410342125, | |
| "grad_norm": 307120.84375, | |
| "learning_rate": 0.00028681061522098047, | |
| "loss": 148.0313, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 0.03301555858198176, | |
| "grad_norm": 164428.203125, | |
| "learning_rate": 0.0002861363129506435, | |
| "loss": 139.0605, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.03367586975362139, | |
| "grad_norm": 56655.140625, | |
| "learning_rate": 0.0002854460344803842, | |
| "loss": 105.2498, | |
| "step": 51 | |
| }, | |
| { | |
| "epoch": 0.03433618092526103, | |
| "grad_norm": 110095.71875, | |
| "learning_rate": 0.00028473986081744163, | |
| "loss": 107.1039, | |
| "step": 52 | |
| }, | |
| { | |
| "epoch": 0.034996492096900665, | |
| "grad_norm": 84727.8125, | |
| "learning_rate": 0.000284017874834426, | |
| "loss": 114.7597, | |
| "step": 53 | |
| }, | |
| { | |
| "epoch": 0.0356568032685403, | |
| "grad_norm": 108558.9140625, | |
| "learning_rate": 0.0002832801612595937, | |
| "loss": 131.0451, | |
| "step": 54 | |
| }, | |
| { | |
| "epoch": 0.03631711444017993, | |
| "grad_norm": 35595.47265625, | |
| "learning_rate": 0.0002825268066669034, | |
| "loss": 135.1516, | |
| "step": 55 | |
| }, | |
| { | |
| "epoch": 0.03697742561181957, | |
| "grad_norm": 54421.08203125, | |
| "learning_rate": 0.00028175789946585693, | |
| "loss": 116.2731, | |
| "step": 56 | |
| }, | |
| { | |
| "epoch": 0.037637736783459205, | |
| "grad_norm": 72844.515625, | |
| "learning_rate": 0.0002809735298911234, | |
| "loss": 101.419, | |
| "step": 57 | |
| }, | |
| { | |
| "epoch": 0.03829804795509884, | |
| "grad_norm": 58473.41015625, | |
| "learning_rate": 0.00028017378999195015, | |
| "loss": 101.8432, | |
| "step": 58 | |
| }, | |
| { | |
| "epoch": 0.03895835912673848, | |
| "grad_norm": 41094.68359375, | |
| "learning_rate": 0.0002793587736213603, | |
| "loss": 114.5148, | |
| "step": 59 | |
| }, | |
| { | |
| "epoch": 0.03961867029837811, | |
| "grad_norm": 75345.5234375, | |
| "learning_rate": 0.00027852857642513836, | |
| "loss": 119.3659, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.03961867029837811, | |
| "eval_loss": 16.175268173217773, | |
| "eval_runtime": 6.5722, | |
| "eval_samples_per_second": 75.317, | |
| "eval_steps_per_second": 75.317, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.040278981470017745, | |
| "grad_norm": 70272.1640625, | |
| "learning_rate": 0.00027768329583060635, | |
| "loss": 110.4526, | |
| "step": 61 | |
| }, | |
| { | |
| "epoch": 0.04093929264165738, | |
| "grad_norm": 34992.48828125, | |
| "learning_rate": 0.00027682303103518976, | |
| "loss": 116.5263, | |
| "step": 62 | |
| }, | |
| { | |
| "epoch": 0.04159960381329702, | |
| "grad_norm": 56546.65625, | |
| "learning_rate": 0.00027594788299477655, | |
| "loss": 107.9915, | |
| "step": 63 | |
| }, | |
| { | |
| "epoch": 0.04225991498493665, | |
| "grad_norm": 23483.95703125, | |
| "learning_rate": 0.0002750579544118695, | |
| "loss": 105.6012, | |
| "step": 64 | |
| }, | |
| { | |
| "epoch": 0.042920226156576285, | |
| "grad_norm": 56980.02734375, | |
| "learning_rate": 0.00027415334972353357, | |
| "loss": 115.8085, | |
| "step": 65 | |
| }, | |
| { | |
| "epoch": 0.04358053732821592, | |
| "grad_norm": 32112.759765625, | |
| "learning_rate": 0.0002732341750891397, | |
| "loss": 100.6383, | |
| "step": 66 | |
| }, | |
| { | |
| "epoch": 0.04424084849985556, | |
| "grad_norm": 26189.25, | |
| "learning_rate": 0.00027230053837790666, | |
| "loss": 95.9158, | |
| "step": 67 | |
| }, | |
| { | |
| "epoch": 0.04490115967149519, | |
| "grad_norm": 27246.33203125, | |
| "learning_rate": 0.0002713525491562421, | |
| "loss": 107.4022, | |
| "step": 68 | |
| }, | |
| { | |
| "epoch": 0.045561470843134826, | |
| "grad_norm": 55204.88671875, | |
| "learning_rate": 0.0002703903186748843, | |
| "loss": 104.1617, | |
| "step": 69 | |
| }, | |
| { | |
| "epoch": 0.04622178201477446, | |
| "grad_norm": 47799.21875, | |
| "learning_rate": 0.00026941395985584653, | |
| "loss": 107.3508, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.0468820931864141, | |
| "grad_norm": 24187.337890625, | |
| "learning_rate": 0.00026842358727916524, | |
| "loss": 98.8449, | |
| "step": 71 | |
| }, | |
| { | |
| "epoch": 0.047542404358053736, | |
| "grad_norm": 99253.2421875, | |
| "learning_rate": 0.0002674193171694533, | |
| "loss": 226.1011, | |
| "step": 72 | |
| }, | |
| { | |
| "epoch": 0.048202715529693366, | |
| "grad_norm": 293996.9375, | |
| "learning_rate": 0.0002664012673822609, | |
| "loss": 507.2474, | |
| "step": 73 | |
| }, | |
| { | |
| "epoch": 0.048863026701333, | |
| "grad_norm": 565162.4375, | |
| "learning_rate": 0.0002653695573902443, | |
| "loss": 619.3906, | |
| "step": 74 | |
| }, | |
| { | |
| "epoch": 0.04952333787297264, | |
| "grad_norm": 569260.125, | |
| "learning_rate": 0.0002643243082691454, | |
| "loss": 489.5234, | |
| "step": 75 | |
| }, | |
| { | |
| "epoch": 0.050183649044612276, | |
| "grad_norm": 564170.875, | |
| "learning_rate": 0.0002632656426835831, | |
| "loss": 570.9297, | |
| "step": 76 | |
| }, | |
| { | |
| "epoch": 0.050843960216251906, | |
| "grad_norm": 505015.0625, | |
| "learning_rate": 0.00026219368487265753, | |
| "loss": 504.5522, | |
| "step": 77 | |
| }, | |
| { | |
| "epoch": 0.05150427138789154, | |
| "grad_norm": 1804335.375, | |
| "learning_rate": 0.00026110856063537083, | |
| "loss": 404.3008, | |
| "step": 78 | |
| }, | |
| { | |
| "epoch": 0.05216458255953118, | |
| "grad_norm": 255148.265625, | |
| "learning_rate": 0.00026001039731586334, | |
| "loss": 266.7525, | |
| "step": 79 | |
| }, | |
| { | |
| "epoch": 0.052824893731170816, | |
| "grad_norm": 410041.71875, | |
| "learning_rate": 0.0002588993237884696, | |
| "loss": 194.2475, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 0.052824893731170816, | |
| "eval_loss": 21.787084579467773, | |
| "eval_runtime": 6.6223, | |
| "eval_samples_per_second": 74.747, | |
| "eval_steps_per_second": 74.747, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 0.05348520490281045, | |
| "grad_norm": 259394.6875, | |
| "learning_rate": 0.00025777547044259435, | |
| "loss": 200.2073, | |
| "step": 81 | |
| }, | |
| { | |
| "epoch": 0.05414551607445008, | |
| "grad_norm": 1378326.625, | |
| "learning_rate": 0.0002566389691674106, | |
| "loss": 100.5475, | |
| "step": 82 | |
| }, | |
| { | |
| "epoch": 0.05480582724608972, | |
| "grad_norm": 63462.6875, | |
| "learning_rate": 0.00025548995333638197, | |
| "loss": 189.407, | |
| "step": 83 | |
| }, | |
| { | |
| "epoch": 0.055466138417729356, | |
| "grad_norm": 149989.21875, | |
| "learning_rate": 0.00025432855779161076, | |
| "loss": 655.0445, | |
| "step": 84 | |
| }, | |
| { | |
| "epoch": 0.05612644958936899, | |
| "grad_norm": 161908.9375, | |
| "learning_rate": 0.00025315491882801347, | |
| "loss": 542.2335, | |
| "step": 85 | |
| }, | |
| { | |
| "epoch": 0.05678676076100862, | |
| "grad_norm": 140391.09375, | |
| "learning_rate": 0.00025196917417732615, | |
| "loss": 178.0071, | |
| "step": 86 | |
| }, | |
| { | |
| "epoch": 0.05744707193264826, | |
| "grad_norm": 45774.61328125, | |
| "learning_rate": 0.0002507714629919409, | |
| "loss": 145.9398, | |
| "step": 87 | |
| }, | |
| { | |
| "epoch": 0.058107383104287896, | |
| "grad_norm": 74355.359375, | |
| "learning_rate": 0.0002495619258285757, | |
| "loss": 162.5158, | |
| "step": 88 | |
| }, | |
| { | |
| "epoch": 0.05876769427592753, | |
| "grad_norm": 112329.7265625, | |
| "learning_rate": 0.0002483407046317794, | |
| "loss": 223.498, | |
| "step": 89 | |
| }, | |
| { | |
| "epoch": 0.05942800544756716, | |
| "grad_norm": 488449.875, | |
| "learning_rate": 0.00024710794271727413, | |
| "loss": 223.1561, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 0.0600883166192068, | |
| "grad_norm": 146916.296875, | |
| "learning_rate": 0.0002458637847551364, | |
| "loss": 252.3947, | |
| "step": 91 | |
| }, | |
| { | |
| "epoch": 0.060748627790846436, | |
| "grad_norm": 115853.0703125, | |
| "learning_rate": 0.00024460837675281926, | |
| "loss": 265.611, | |
| "step": 92 | |
| }, | |
| { | |
| "epoch": 0.06140893896248607, | |
| "grad_norm": 95760.921875, | |
| "learning_rate": 0.00024334186603801807, | |
| "loss": 195.9439, | |
| "step": 93 | |
| }, | |
| { | |
| "epoch": 0.06206925013412571, | |
| "grad_norm": 58220.4609375, | |
| "learning_rate": 0.00024206440124138062, | |
| "loss": 173.6973, | |
| "step": 94 | |
| }, | |
| { | |
| "epoch": 0.06272956130576535, | |
| "grad_norm": 44573.25390625, | |
| "learning_rate": 0.0002407761322790648, | |
| "loss": 130.0355, | |
| "step": 95 | |
| }, | |
| { | |
| "epoch": 0.06338987247740498, | |
| "grad_norm": 48302.27734375, | |
| "learning_rate": 0.00023947721033514512, | |
| "loss": 110.2012, | |
| "step": 96 | |
| }, | |
| { | |
| "epoch": 0.0640501836490446, | |
| "grad_norm": 18446.73046875, | |
| "learning_rate": 0.00023816778784387094, | |
| "loss": 118.2505, | |
| "step": 97 | |
| }, | |
| { | |
| "epoch": 0.06471049482068425, | |
| "grad_norm": 35311.09375, | |
| "learning_rate": 0.0002368480184717773, | |
| "loss": 133.5809, | |
| "step": 98 | |
| }, | |
| { | |
| "epoch": 0.06537080599232388, | |
| "grad_norm": 38145.79296875, | |
| "learning_rate": 0.00023551805709965147, | |
| "loss": 129.8271, | |
| "step": 99 | |
| }, | |
| { | |
| "epoch": 0.06603111716396352, | |
| "grad_norm": 32865.98046875, | |
| "learning_rate": 0.00023417805980435736, | |
| "loss": 116.0362, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.06603111716396352, | |
| "eval_loss": 9.961955070495605, | |
| "eval_runtime": 6.5733, | |
| "eval_samples_per_second": 75.305, | |
| "eval_steps_per_second": 75.305, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.06669142833560315, | |
| "grad_norm": 18817.16796875, | |
| "learning_rate": 0.00023282818384051866, | |
| "loss": 113.1262, | |
| "step": 101 | |
| }, | |
| { | |
| "epoch": 0.06735173950724278, | |
| "grad_norm": 24054.869140625, | |
| "learning_rate": 0.00023146858762206489, | |
| "loss": 108.1982, | |
| "step": 102 | |
| }, | |
| { | |
| "epoch": 0.06801205067888243, | |
| "grad_norm": 34655.8671875, | |
| "learning_rate": 0.00023009943070364044, | |
| "loss": 108.4203, | |
| "step": 103 | |
| }, | |
| { | |
| "epoch": 0.06867236185052206, | |
| "grad_norm": 29425.787109375, | |
| "learning_rate": 0.0002287208737618801, | |
| "loss": 107.4073, | |
| "step": 104 | |
| }, | |
| { | |
| "epoch": 0.0693326730221617, | |
| "grad_norm": 13952.1171875, | |
| "learning_rate": 0.00022733307857655325, | |
| "loss": 105.1398, | |
| "step": 105 | |
| }, | |
| { | |
| "epoch": 0.06999298419380133, | |
| "grad_norm": 20227.431640625, | |
| "learning_rate": 0.00022593620801157808, | |
| "loss": 115.2134, | |
| "step": 106 | |
| }, | |
| { | |
| "epoch": 0.07065329536544096, | |
| "grad_norm": 19999.79296875, | |
| "learning_rate": 0.00022453042599590882, | |
| "loss": 113.6159, | |
| "step": 107 | |
| }, | |
| { | |
| "epoch": 0.0713136065370806, | |
| "grad_norm": 18226.33203125, | |
| "learning_rate": 0.00022311589750429787, | |
| "loss": 110.2182, | |
| "step": 108 | |
| }, | |
| { | |
| "epoch": 0.07197391770872023, | |
| "grad_norm": 15471.123046875, | |
| "learning_rate": 0.00022169278853793545, | |
| "loss": 98.862, | |
| "step": 109 | |
| }, | |
| { | |
| "epoch": 0.07263422888035986, | |
| "grad_norm": 9518.90625, | |
| "learning_rate": 0.00022026126610496852, | |
| "loss": 100.519, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 0.07329454005199951, | |
| "grad_norm": 12838.0771484375, | |
| "learning_rate": 0.0002188214982009016, | |
| "loss": 99.1184, | |
| "step": 111 | |
| }, | |
| { | |
| "epoch": 0.07395485122363914, | |
| "grad_norm": 13236.9697265625, | |
| "learning_rate": 0.00021737365378888187, | |
| "loss": 108.3643, | |
| "step": 112 | |
| }, | |
| { | |
| "epoch": 0.07461516239527878, | |
| "grad_norm": 21540.712890625, | |
| "learning_rate": 0.00021591790277987043, | |
| "loss": 106.4385, | |
| "step": 113 | |
| }, | |
| { | |
| "epoch": 0.07527547356691841, | |
| "grad_norm": 13282.7333984375, | |
| "learning_rate": 0.00021445441601270276, | |
| "loss": 111.6325, | |
| "step": 114 | |
| }, | |
| { | |
| "epoch": 0.07593578473855804, | |
| "grad_norm": 32402.203125, | |
| "learning_rate": 0.00021298336523403968, | |
| "loss": 102.4856, | |
| "step": 115 | |
| }, | |
| { | |
| "epoch": 0.07659609591019768, | |
| "grad_norm": 23308.939453125, | |
| "learning_rate": 0.0002115049230782124, | |
| "loss": 99.6906, | |
| "step": 116 | |
| }, | |
| { | |
| "epoch": 0.07725640708183731, | |
| "grad_norm": 21524.953125, | |
| "learning_rate": 0.00021001926304696296, | |
| "loss": 90.451, | |
| "step": 117 | |
| }, | |
| { | |
| "epoch": 0.07791671825347696, | |
| "grad_norm": 13045.5537109375, | |
| "learning_rate": 0.00020852655948908316, | |
| "loss": 93.52, | |
| "step": 118 | |
| }, | |
| { | |
| "epoch": 0.07857702942511659, | |
| "grad_norm": 18377.09375, | |
| "learning_rate": 0.0002070269875799538, | |
| "loss": 85.6482, | |
| "step": 119 | |
| }, | |
| { | |
| "epoch": 0.07923734059675622, | |
| "grad_norm": 12025.564453125, | |
| "learning_rate": 0.00020552072330098716, | |
| "loss": 89.6598, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 0.07923734059675622, | |
| "eval_loss": 12.788580894470215, | |
| "eval_runtime": 6.5873, | |
| "eval_samples_per_second": 75.145, | |
| "eval_steps_per_second": 75.145, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 0.07989765176839586, | |
| "grad_norm": 10677.837890625, | |
| "learning_rate": 0.0002040079434189748, | |
| "loss": 90.3255, | |
| "step": 121 | |
| }, | |
| { | |
| "epoch": 0.08055796294003549, | |
| "grad_norm": 13001.4951171875, | |
| "learning_rate": 0.00020248882546534326, | |
| "loss": 94.9763, | |
| "step": 122 | |
| }, | |
| { | |
| "epoch": 0.08121827411167512, | |
| "grad_norm": 88364.6875, | |
| "learning_rate": 0.00020096354771531976, | |
| "loss": 210.5573, | |
| "step": 123 | |
| }, | |
| { | |
| "epoch": 0.08187858528331476, | |
| "grad_norm": 314990.40625, | |
| "learning_rate": 0.00019943228916701104, | |
| "loss": 602.6875, | |
| "step": 124 | |
| }, | |
| { | |
| "epoch": 0.0825388964549544, | |
| "grad_norm": 264931.5, | |
| "learning_rate": 0.00019789522952039695, | |
| "loss": 513.6562, | |
| "step": 125 | |
| }, | |
| { | |
| "epoch": 0.08319920762659404, | |
| "grad_norm": 157227.640625, | |
| "learning_rate": 0.0001963525491562421, | |
| "loss": 511.8125, | |
| "step": 126 | |
| }, | |
| { | |
| "epoch": 0.08385951879823367, | |
| "grad_norm": 537004.0625, | |
| "learning_rate": 0.00019480442911492702, | |
| "loss": 268.8125, | |
| "step": 127 | |
| }, | |
| { | |
| "epoch": 0.0845198299698733, | |
| "grad_norm": 1529112.375, | |
| "learning_rate": 0.00019325105107520263, | |
| "loss": 257.3359, | |
| "step": 128 | |
| }, | |
| { | |
| "epoch": 0.08518014114151294, | |
| "grad_norm": 231625.046875, | |
| "learning_rate": 0.00019169259733286913, | |
| "loss": 202.3438, | |
| "step": 129 | |
| }, | |
| { | |
| "epoch": 0.08584045231315257, | |
| "grad_norm": 306631.5625, | |
| "learning_rate": 0.00019012925077938314, | |
| "loss": 181.8047, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 0.08650076348479221, | |
| "grad_norm": 118856.3203125, | |
| "learning_rate": 0.0001885611948803941, | |
| "loss": 179.7969, | |
| "step": 131 | |
| }, | |
| { | |
| "epoch": 0.08716107465643184, | |
| "grad_norm": 98292.1796875, | |
| "learning_rate": 0.0001869886136542143, | |
| "loss": 392.7283, | |
| "step": 132 | |
| }, | |
| { | |
| "epoch": 0.08782138582807147, | |
| "grad_norm": 89386.7734375, | |
| "learning_rate": 0.00018541169165022298, | |
| "loss": 318.7403, | |
| "step": 133 | |
| }, | |
| { | |
| "epoch": 0.08848169699971112, | |
| "grad_norm": 137117.296875, | |
| "learning_rate": 0.00018383061392720913, | |
| "loss": 245.4405, | |
| "step": 134 | |
| }, | |
| { | |
| "epoch": 0.08914200817135075, | |
| "grad_norm": 150909.71875, | |
| "learning_rate": 0.0001822455660316536, | |
| "loss": 156.249, | |
| "step": 135 | |
| }, | |
| { | |
| "epoch": 0.08980231934299038, | |
| "grad_norm": 60323.1875, | |
| "learning_rate": 0.00018065673397595473, | |
| "loss": 113.9602, | |
| "step": 136 | |
| }, | |
| { | |
| "epoch": 0.09046263051463002, | |
| "grad_norm": 42032.9921875, | |
| "learning_rate": 0.00017906430421659876, | |
| "loss": 107.9544, | |
| "step": 137 | |
| }, | |
| { | |
| "epoch": 0.09112294168626965, | |
| "grad_norm": 33694.890625, | |
| "learning_rate": 0.00017746846363227842, | |
| "loss": 111.8, | |
| "step": 138 | |
| }, | |
| { | |
| "epoch": 0.0917832528579093, | |
| "grad_norm": 34851.86328125, | |
| "learning_rate": 0.00017586939950196186, | |
| "loss": 103.5465, | |
| "step": 139 | |
| }, | |
| { | |
| "epoch": 0.09244356402954892, | |
| "grad_norm": 24885.861328125, | |
| "learning_rate": 0.00017426729948291474, | |
| "loss": 101.8808, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 0.09244356402954892, | |
| "eval_loss": 10.751233100891113, | |
| "eval_runtime": 6.5882, | |
| "eval_samples_per_second": 75.135, | |
| "eval_steps_per_second": 75.135, | |
| "step": 140 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 300, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 20, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": false | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 93374726012928.0, | |
| "train_batch_size": 1, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |