| { | |
| "best_metric": 0.07205358892679214, | |
| "best_model_checkpoint": "saves/psy-course-doc/Ministral-8B-Instruct-2410/train/fold1/checkpoint-100", | |
| "epoch": 4.938271604938271, | |
| "eval_steps": 10, | |
| "global_step": 125, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.03950617283950617, | |
| "grad_norm": 0.24810998141765594, | |
| "learning_rate": 7.692307692307694e-06, | |
| "loss": 0.2092, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.07901234567901234, | |
| "grad_norm": 0.26039576530456543, | |
| "learning_rate": 1.5384615384615387e-05, | |
| "loss": 0.221, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.11851851851851852, | |
| "grad_norm": 0.29912298917770386, | |
| "learning_rate": 2.307692307692308e-05, | |
| "loss": 0.211, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.1580246913580247, | |
| "grad_norm": 0.25341591238975525, | |
| "learning_rate": 3.0769230769230774e-05, | |
| "loss": 0.2472, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.19753086419753085, | |
| "grad_norm": 0.25397586822509766, | |
| "learning_rate": 3.846153846153846e-05, | |
| "loss": 0.2688, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.23703703703703705, | |
| "grad_norm": 0.2542887330055237, | |
| "learning_rate": 4.615384615384616e-05, | |
| "loss": 0.1779, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.2765432098765432, | |
| "grad_norm": 0.23962284624576569, | |
| "learning_rate": 5.384615384615385e-05, | |
| "loss": 0.2425, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.3160493827160494, | |
| "grad_norm": 0.23435115814208984, | |
| "learning_rate": 6.153846153846155e-05, | |
| "loss": 0.201, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.35555555555555557, | |
| "grad_norm": 0.22143518924713135, | |
| "learning_rate": 6.923076923076924e-05, | |
| "loss": 0.1341, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.3950617283950617, | |
| "grad_norm": 0.22170604765415192, | |
| "learning_rate": 7.692307692307693e-05, | |
| "loss": 0.1495, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.3950617283950617, | |
| "eval_loss": 0.13552844524383545, | |
| "eval_runtime": 26.8803, | |
| "eval_samples_per_second": 1.674, | |
| "eval_steps_per_second": 1.674, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.4345679012345679, | |
| "grad_norm": 0.21747687458992004, | |
| "learning_rate": 8.461538461538461e-05, | |
| "loss": 0.1, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.4740740740740741, | |
| "grad_norm": 0.1885504573583603, | |
| "learning_rate": 9.230769230769232e-05, | |
| "loss": 0.1806, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.5135802469135803, | |
| "grad_norm": 0.17021319270133972, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0953, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.5530864197530864, | |
| "grad_norm": 0.19080102443695068, | |
| "learning_rate": 9.998033131915266e-05, | |
| "loss": 0.0955, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.5925925925925926, | |
| "grad_norm": 0.2320452183485031, | |
| "learning_rate": 9.992134075089084e-05, | |
| "loss": 0.0593, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.6320987654320988, | |
| "grad_norm": 0.17980320751667023, | |
| "learning_rate": 9.982307470588098e-05, | |
| "loss": 0.1111, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.671604938271605, | |
| "grad_norm": 0.14436128735542297, | |
| "learning_rate": 9.968561049466214e-05, | |
| "loss": 0.1019, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.7111111111111111, | |
| "grad_norm": 0.1278296858072281, | |
| "learning_rate": 9.950905626682228e-05, | |
| "loss": 0.0538, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.7506172839506173, | |
| "grad_norm": 0.14731793105602264, | |
| "learning_rate": 9.92935509259118e-05, | |
| "loss": 0.1104, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.7901234567901234, | |
| "grad_norm": 0.13458046317100525, | |
| "learning_rate": 9.903926402016153e-05, | |
| "loss": 0.0292, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.7901234567901234, | |
| "eval_loss": 0.09099149703979492, | |
| "eval_runtime": 27.3965, | |
| "eval_samples_per_second": 1.643, | |
| "eval_steps_per_second": 1.643, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.8296296296296296, | |
| "grad_norm": 0.13160204887390137, | |
| "learning_rate": 9.874639560909117e-05, | |
| "loss": 0.1058, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.8691358024691358, | |
| "grad_norm": 0.14559167623519897, | |
| "learning_rate": 9.841517610611309e-05, | |
| "loss": 0.073, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.908641975308642, | |
| "grad_norm": 0.14230301976203918, | |
| "learning_rate": 9.804586609725499e-05, | |
| "loss": 0.0987, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.9481481481481482, | |
| "grad_norm": 0.10383627563714981, | |
| "learning_rate": 9.763875613614482e-05, | |
| "loss": 0.0759, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.9876543209876543, | |
| "grad_norm": 0.11663982272148132, | |
| "learning_rate": 9.719416651541839e-05, | |
| "loss": 0.0906, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 1.0271604938271606, | |
| "grad_norm": 0.1367630809545517, | |
| "learning_rate": 9.671244701472999e-05, | |
| "loss": 0.0834, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 1.0666666666666667, | |
| "grad_norm": 0.09665873646736145, | |
| "learning_rate": 9.619397662556435e-05, | |
| "loss": 0.0708, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 1.106172839506173, | |
| "grad_norm": 0.11328412592411041, | |
| "learning_rate": 9.563916325306594e-05, | |
| "loss": 0.0484, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 1.145679012345679, | |
| "grad_norm": 0.13764064013957977, | |
| "learning_rate": 9.504844339512095e-05, | |
| "loss": 0.1173, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 1.1851851851851851, | |
| "grad_norm": 0.09059632569551468, | |
| "learning_rate": 9.442228179894362e-05, | |
| "loss": 0.0626, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 1.1851851851851851, | |
| "eval_loss": 0.0796937569975853, | |
| "eval_runtime": 27.4471, | |
| "eval_samples_per_second": 1.64, | |
| "eval_steps_per_second": 1.64, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 1.2246913580246914, | |
| "grad_norm": 0.09541764855384827, | |
| "learning_rate": 9.376117109543769e-05, | |
| "loss": 0.0648, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 1.2641975308641975, | |
| "grad_norm": 0.11591030657291412, | |
| "learning_rate": 9.306563141162046e-05, | |
| "loss": 0.1198, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 1.3037037037037038, | |
| "grad_norm": 0.08755677193403244, | |
| "learning_rate": 9.233620996141421e-05, | |
| "loss": 0.0634, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 1.34320987654321, | |
| "grad_norm": 0.08026272803544998, | |
| "learning_rate": 9.157348061512727e-05, | |
| "loss": 0.0646, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 1.382716049382716, | |
| "grad_norm": 0.08412012457847595, | |
| "learning_rate": 9.077804344796302e-05, | |
| "loss": 0.0508, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 1.4222222222222223, | |
| "grad_norm": 0.10387691110372543, | |
| "learning_rate": 8.995052426791247e-05, | |
| "loss": 0.0632, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 1.4617283950617284, | |
| "grad_norm": 0.07731848210096359, | |
| "learning_rate": 8.90915741234015e-05, | |
| "loss": 0.0322, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 1.5012345679012347, | |
| "grad_norm": 0.10354169458150864, | |
| "learning_rate": 8.820186879108038e-05, | |
| "loss": 0.102, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 1.5407407407407407, | |
| "grad_norm": 0.11002744734287262, | |
| "learning_rate": 8.728210824415827e-05, | |
| "loss": 0.0599, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 1.5802469135802468, | |
| "grad_norm": 0.11782169342041016, | |
| "learning_rate": 8.633301610170135e-05, | |
| "loss": 0.0771, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 1.5802469135802468, | |
| "eval_loss": 0.07648379355669022, | |
| "eval_runtime": 27.5025, | |
| "eval_samples_per_second": 1.636, | |
| "eval_steps_per_second": 1.636, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 1.6197530864197531, | |
| "grad_norm": 0.0960182249546051, | |
| "learning_rate": 8.535533905932738e-05, | |
| "loss": 0.0774, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 1.6592592592592592, | |
| "grad_norm": 0.10701272636651993, | |
| "learning_rate": 8.434984630174509e-05, | |
| "loss": 0.1063, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 1.6987654320987655, | |
| "grad_norm": 0.13072806596755981, | |
| "learning_rate": 8.33173288976002e-05, | |
| "loss": 0.0696, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 1.7382716049382716, | |
| "grad_norm": 0.12691301107406616, | |
| "learning_rate": 8.225859917710439e-05, | |
| "loss": 0.0831, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 1.7777777777777777, | |
| "grad_norm": 0.1352904886007309, | |
| "learning_rate": 8.117449009293668e-05, | |
| "loss": 0.0672, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 1.817283950617284, | |
| "grad_norm": 0.11082760989665985, | |
| "learning_rate": 8.006585456492029e-05, | |
| "loss": 0.0554, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 1.8567901234567903, | |
| "grad_norm": 0.11100582033395767, | |
| "learning_rate": 7.89335648089903e-05, | |
| "loss": 0.0709, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 1.8962962962962964, | |
| "grad_norm": 0.08830490708351135, | |
| "learning_rate": 7.777851165098012e-05, | |
| "loss": 0.0288, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 1.9358024691358025, | |
| "grad_norm": 0.11078186333179474, | |
| "learning_rate": 7.660160382576683e-05, | |
| "loss": 0.0914, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 1.9753086419753085, | |
| "grad_norm": 0.1210477203130722, | |
| "learning_rate": 7.540376726232648e-05, | |
| "loss": 0.1056, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 1.9753086419753085, | |
| "eval_loss": 0.07425841689109802, | |
| "eval_runtime": 27.6317, | |
| "eval_samples_per_second": 1.629, | |
| "eval_steps_per_second": 1.629, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 2.0148148148148146, | |
| "grad_norm": 0.1279354840517044, | |
| "learning_rate": 7.4185944355262e-05, | |
| "loss": 0.0605, | |
| "step": 51 | |
| }, | |
| { | |
| "epoch": 2.054320987654321, | |
| "grad_norm": 0.10435281693935394, | |
| "learning_rate": 7.294909322337689e-05, | |
| "loss": 0.1024, | |
| "step": 52 | |
| }, | |
| { | |
| "epoch": 2.093827160493827, | |
| "grad_norm": 0.09126003831624985, | |
| "learning_rate": 7.169418695587791e-05, | |
| "loss": 0.0575, | |
| "step": 53 | |
| }, | |
| { | |
| "epoch": 2.1333333333333333, | |
| "grad_norm": 0.09775116294622421, | |
| "learning_rate": 7.042221284679982e-05, | |
| "loss": 0.0522, | |
| "step": 54 | |
| }, | |
| { | |
| "epoch": 2.1728395061728394, | |
| "grad_norm": 0.07916697859764099, | |
| "learning_rate": 6.91341716182545e-05, | |
| "loss": 0.0401, | |
| "step": 55 | |
| }, | |
| { | |
| "epoch": 2.212345679012346, | |
| "grad_norm": 0.10299328714609146, | |
| "learning_rate": 6.783107663311565e-05, | |
| "loss": 0.0464, | |
| "step": 56 | |
| }, | |
| { | |
| "epoch": 2.251851851851852, | |
| "grad_norm": 0.1284073144197464, | |
| "learning_rate": 6.651395309775837e-05, | |
| "loss": 0.0846, | |
| "step": 57 | |
| }, | |
| { | |
| "epoch": 2.291358024691358, | |
| "grad_norm": 0.09349021315574646, | |
| "learning_rate": 6.518383725548074e-05, | |
| "loss": 0.0517, | |
| "step": 58 | |
| }, | |
| { | |
| "epoch": 2.330864197530864, | |
| "grad_norm": 0.09708677977323532, | |
| "learning_rate": 6.384177557124247e-05, | |
| "loss": 0.0636, | |
| "step": 59 | |
| }, | |
| { | |
| "epoch": 2.3703703703703702, | |
| "grad_norm": 0.12745961546897888, | |
| "learning_rate": 6.248882390836135e-05, | |
| "loss": 0.0558, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 2.3703703703703702, | |
| "eval_loss": 0.07404763251543045, | |
| "eval_runtime": 27.4832, | |
| "eval_samples_per_second": 1.637, | |
| "eval_steps_per_second": 1.637, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 2.4098765432098768, | |
| "grad_norm": 0.09800593554973602, | |
| "learning_rate": 6.112604669781572e-05, | |
| "loss": 0.0448, | |
| "step": 61 | |
| }, | |
| { | |
| "epoch": 2.449382716049383, | |
| "grad_norm": 0.11458192765712738, | |
| "learning_rate": 5.9754516100806423e-05, | |
| "loss": 0.09, | |
| "step": 62 | |
| }, | |
| { | |
| "epoch": 2.488888888888889, | |
| "grad_norm": 0.1109517440199852, | |
| "learning_rate": 5.837531116523682e-05, | |
| "loss": 0.0662, | |
| "step": 63 | |
| }, | |
| { | |
| "epoch": 2.528395061728395, | |
| "grad_norm": 0.10171234607696533, | |
| "learning_rate": 5.698951697677498e-05, | |
| "loss": 0.0232, | |
| "step": 64 | |
| }, | |
| { | |
| "epoch": 2.567901234567901, | |
| "grad_norm": 0.12857115268707275, | |
| "learning_rate": 5.559822380516539e-05, | |
| "loss": 0.0993, | |
| "step": 65 | |
| }, | |
| { | |
| "epoch": 2.6074074074074076, | |
| "grad_norm": 0.08992833644151688, | |
| "learning_rate": 5.420252624646238e-05, | |
| "loss": 0.0291, | |
| "step": 66 | |
| }, | |
| { | |
| "epoch": 2.6469135802469137, | |
| "grad_norm": 0.10966512560844421, | |
| "learning_rate": 5.2803522361859594e-05, | |
| "loss": 0.0668, | |
| "step": 67 | |
| }, | |
| { | |
| "epoch": 2.68641975308642, | |
| "grad_norm": 0.09445935487747192, | |
| "learning_rate": 5.140231281379345e-05, | |
| "loss": 0.0499, | |
| "step": 68 | |
| }, | |
| { | |
| "epoch": 2.725925925925926, | |
| "grad_norm": 0.09255904704332352, | |
| "learning_rate": 5e-05, | |
| "loss": 0.0246, | |
| "step": 69 | |
| }, | |
| { | |
| "epoch": 2.765432098765432, | |
| "grad_norm": 0.12672650814056396, | |
| "learning_rate": 4.859768718620656e-05, | |
| "loss": 0.0488, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 2.765432098765432, | |
| "eval_loss": 0.07281763106584549, | |
| "eval_runtime": 27.474, | |
| "eval_samples_per_second": 1.638, | |
| "eval_steps_per_second": 1.638, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 2.8049382716049385, | |
| "grad_norm": 0.09950120747089386, | |
| "learning_rate": 4.7196477638140404e-05, | |
| "loss": 0.0297, | |
| "step": 71 | |
| }, | |
| { | |
| "epoch": 2.8444444444444446, | |
| "grad_norm": 0.13572734594345093, | |
| "learning_rate": 4.579747375353763e-05, | |
| "loss": 0.1215, | |
| "step": 72 | |
| }, | |
| { | |
| "epoch": 2.8839506172839506, | |
| "grad_norm": 0.10585619509220123, | |
| "learning_rate": 4.4401776194834613e-05, | |
| "loss": 0.0685, | |
| "step": 73 | |
| }, | |
| { | |
| "epoch": 2.9234567901234567, | |
| "grad_norm": 0.12362095713615417, | |
| "learning_rate": 4.3010483023225045e-05, | |
| "loss": 0.0445, | |
| "step": 74 | |
| }, | |
| { | |
| "epoch": 2.962962962962963, | |
| "grad_norm": 0.1415012925863266, | |
| "learning_rate": 4.162468883476319e-05, | |
| "loss": 0.0871, | |
| "step": 75 | |
| }, | |
| { | |
| "epoch": 3.0024691358024693, | |
| "grad_norm": 0.1490877866744995, | |
| "learning_rate": 4.0245483899193595e-05, | |
| "loss": 0.1052, | |
| "step": 76 | |
| }, | |
| { | |
| "epoch": 3.0419753086419754, | |
| "grad_norm": 0.09459207952022552, | |
| "learning_rate": 3.887395330218429e-05, | |
| "loss": 0.0561, | |
| "step": 77 | |
| }, | |
| { | |
| "epoch": 3.0814814814814815, | |
| "grad_norm": 0.11990195512771606, | |
| "learning_rate": 3.7511176091638653e-05, | |
| "loss": 0.0765, | |
| "step": 78 | |
| }, | |
| { | |
| "epoch": 3.1209876543209876, | |
| "grad_norm": 0.10552315413951874, | |
| "learning_rate": 3.6158224428757535e-05, | |
| "loss": 0.0297, | |
| "step": 79 | |
| }, | |
| { | |
| "epoch": 3.1604938271604937, | |
| "grad_norm": 0.12247174978256226, | |
| "learning_rate": 3.4816162744519263e-05, | |
| "loss": 0.0649, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 3.1604938271604937, | |
| "eval_loss": 0.07212765514850616, | |
| "eval_runtime": 27.3851, | |
| "eval_samples_per_second": 1.643, | |
| "eval_steps_per_second": 1.643, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 3.2, | |
| "grad_norm": 0.11932343244552612, | |
| "learning_rate": 3.3486046902241664e-05, | |
| "loss": 0.0629, | |
| "step": 81 | |
| }, | |
| { | |
| "epoch": 3.2395061728395063, | |
| "grad_norm": 0.12215903401374817, | |
| "learning_rate": 3.216892336688435e-05, | |
| "loss": 0.0604, | |
| "step": 82 | |
| }, | |
| { | |
| "epoch": 3.2790123456790123, | |
| "grad_norm": 0.09939143806695938, | |
| "learning_rate": 3.086582838174551e-05, | |
| "loss": 0.0625, | |
| "step": 83 | |
| }, | |
| { | |
| "epoch": 3.3185185185185184, | |
| "grad_norm": 0.09993693977594376, | |
| "learning_rate": 2.9577787153200197e-05, | |
| "loss": 0.0459, | |
| "step": 84 | |
| }, | |
| { | |
| "epoch": 3.3580246913580245, | |
| "grad_norm": 0.11673483997583389, | |
| "learning_rate": 2.8305813044122097e-05, | |
| "loss": 0.0455, | |
| "step": 85 | |
| }, | |
| { | |
| "epoch": 3.397530864197531, | |
| "grad_norm": 0.11794883757829666, | |
| "learning_rate": 2.705090677662311e-05, | |
| "loss": 0.0586, | |
| "step": 86 | |
| }, | |
| { | |
| "epoch": 3.437037037037037, | |
| "grad_norm": 0.10317753255367279, | |
| "learning_rate": 2.581405564473801e-05, | |
| "loss": 0.0397, | |
| "step": 87 | |
| }, | |
| { | |
| "epoch": 3.476543209876543, | |
| "grad_norm": 0.12719328701496124, | |
| "learning_rate": 2.459623273767354e-05, | |
| "loss": 0.0692, | |
| "step": 88 | |
| }, | |
| { | |
| "epoch": 3.5160493827160493, | |
| "grad_norm": 0.11057513952255249, | |
| "learning_rate": 2.3398396174233178e-05, | |
| "loss": 0.0569, | |
| "step": 89 | |
| }, | |
| { | |
| "epoch": 3.5555555555555554, | |
| "grad_norm": 0.0870712623000145, | |
| "learning_rate": 2.2221488349019903e-05, | |
| "loss": 0.0235, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 3.5555555555555554, | |
| "eval_loss": 0.07221826165914536, | |
| "eval_runtime": 27.4054, | |
| "eval_samples_per_second": 1.642, | |
| "eval_steps_per_second": 1.642, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 3.595061728395062, | |
| "grad_norm": 0.145512193441391, | |
| "learning_rate": 2.1066435191009715e-05, | |
| "loss": 0.0741, | |
| "step": 91 | |
| }, | |
| { | |
| "epoch": 3.634567901234568, | |
| "grad_norm": 0.11553002148866653, | |
| "learning_rate": 1.9934145435079702e-05, | |
| "loss": 0.0564, | |
| "step": 92 | |
| }, | |
| { | |
| "epoch": 3.674074074074074, | |
| "grad_norm": 0.10770400613546371, | |
| "learning_rate": 1.8825509907063327e-05, | |
| "loss": 0.0475, | |
| "step": 93 | |
| }, | |
| { | |
| "epoch": 3.71358024691358, | |
| "grad_norm": 0.1617460399866104, | |
| "learning_rate": 1.774140082289563e-05, | |
| "loss": 0.0784, | |
| "step": 94 | |
| }, | |
| { | |
| "epoch": 3.753086419753086, | |
| "grad_norm": 0.14573591947555542, | |
| "learning_rate": 1.6682671102399805e-05, | |
| "loss": 0.0717, | |
| "step": 95 | |
| }, | |
| { | |
| "epoch": 3.7925925925925927, | |
| "grad_norm": 0.1260758489370346, | |
| "learning_rate": 1.5650153698254916e-05, | |
| "loss": 0.069, | |
| "step": 96 | |
| }, | |
| { | |
| "epoch": 3.832098765432099, | |
| "grad_norm": 0.10826553404331207, | |
| "learning_rate": 1.4644660940672627e-05, | |
| "loss": 0.0418, | |
| "step": 97 | |
| }, | |
| { | |
| "epoch": 3.871604938271605, | |
| "grad_norm": 0.08969935774803162, | |
| "learning_rate": 1.3666983898298657e-05, | |
| "loss": 0.0234, | |
| "step": 98 | |
| }, | |
| { | |
| "epoch": 3.911111111111111, | |
| "grad_norm": 0.11357671022415161, | |
| "learning_rate": 1.2717891755841722e-05, | |
| "loss": 0.0318, | |
| "step": 99 | |
| }, | |
| { | |
| "epoch": 3.950617283950617, | |
| "grad_norm": 0.11297564208507538, | |
| "learning_rate": 1.1798131208919627e-05, | |
| "loss": 0.0508, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 3.950617283950617, | |
| "eval_loss": 0.07205358892679214, | |
| "eval_runtime": 27.4453, | |
| "eval_samples_per_second": 1.64, | |
| "eval_steps_per_second": 1.64, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 3.9901234567901236, | |
| "grad_norm": 0.13930268585681915, | |
| "learning_rate": 1.090842587659851e-05, | |
| "loss": 0.0662, | |
| "step": 101 | |
| }, | |
| { | |
| "epoch": 4.029629629629629, | |
| "grad_norm": 0.12079107016324997, | |
| "learning_rate": 1.004947573208756e-05, | |
| "loss": 0.0723, | |
| "step": 102 | |
| }, | |
| { | |
| "epoch": 4.069135802469136, | |
| "grad_norm": 0.10999605059623718, | |
| "learning_rate": 9.221956552036992e-06, | |
| "loss": 0.0347, | |
| "step": 103 | |
| }, | |
| { | |
| "epoch": 4.108641975308642, | |
| "grad_norm": 0.10675299167633057, | |
| "learning_rate": 8.426519384872733e-06, | |
| "loss": 0.052, | |
| "step": 104 | |
| }, | |
| { | |
| "epoch": 4.148148148148148, | |
| "grad_norm": 0.12469816952943802, | |
| "learning_rate": 7.663790038585793e-06, | |
| "loss": 0.0788, | |
| "step": 105 | |
| }, | |
| { | |
| "epoch": 4.187654320987654, | |
| "grad_norm": 0.11500705778598785, | |
| "learning_rate": 6.934368588379553e-06, | |
| "loss": 0.0573, | |
| "step": 106 | |
| }, | |
| { | |
| "epoch": 4.22716049382716, | |
| "grad_norm": 0.11821264028549194, | |
| "learning_rate": 6.238828904562316e-06, | |
| "loss": 0.0591, | |
| "step": 107 | |
| }, | |
| { | |
| "epoch": 4.266666666666667, | |
| "grad_norm": 0.15900757908821106, | |
| "learning_rate": 5.577718201056392e-06, | |
| "loss": 0.0401, | |
| "step": 108 | |
| }, | |
| { | |
| "epoch": 4.306172839506173, | |
| "grad_norm": 0.1350027322769165, | |
| "learning_rate": 4.951556604879048e-06, | |
| "loss": 0.0729, | |
| "step": 109 | |
| }, | |
| { | |
| "epoch": 4.345679012345679, | |
| "grad_norm": 0.09698620438575745, | |
| "learning_rate": 4.360836746934055e-06, | |
| "loss": 0.0334, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 4.345679012345679, | |
| "eval_loss": 0.07236602902412415, | |
| "eval_runtime": 27.3346, | |
| "eval_samples_per_second": 1.646, | |
| "eval_steps_per_second": 1.646, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 4.385185185185185, | |
| "grad_norm": 0.0984768345952034, | |
| "learning_rate": 3.8060233744356633e-06, | |
| "loss": 0.0384, | |
| "step": 111 | |
| }, | |
| { | |
| "epoch": 4.424691358024692, | |
| "grad_norm": 0.12040996551513672, | |
| "learning_rate": 3.2875529852700147e-06, | |
| "loss": 0.0651, | |
| "step": 112 | |
| }, | |
| { | |
| "epoch": 4.4641975308641975, | |
| "grad_norm": 0.12405715137720108, | |
| "learning_rate": 2.8058334845816213e-06, | |
| "loss": 0.0191, | |
| "step": 113 | |
| }, | |
| { | |
| "epoch": 4.503703703703704, | |
| "grad_norm": 0.09675806015729904, | |
| "learning_rate": 2.361243863855184e-06, | |
| "loss": 0.0309, | |
| "step": 114 | |
| }, | |
| { | |
| "epoch": 4.54320987654321, | |
| "grad_norm": 0.13328631222248077, | |
| "learning_rate": 1.9541339027450256e-06, | |
| "loss": 0.0692, | |
| "step": 115 | |
| }, | |
| { | |
| "epoch": 4.582716049382716, | |
| "grad_norm": 0.12597902119159698, | |
| "learning_rate": 1.584823893886933e-06, | |
| "loss": 0.0566, | |
| "step": 116 | |
| }, | |
| { | |
| "epoch": 4.622222222222222, | |
| "grad_norm": 0.1236833855509758, | |
| "learning_rate": 1.2536043909088191e-06, | |
| "loss": 0.0455, | |
| "step": 117 | |
| }, | |
| { | |
| "epoch": 4.661728395061728, | |
| "grad_norm": 0.09165410697460175, | |
| "learning_rate": 9.607359798384785e-07, | |
| "loss": 0.0226, | |
| "step": 118 | |
| }, | |
| { | |
| "epoch": 4.701234567901235, | |
| "grad_norm": 0.1302453577518463, | |
| "learning_rate": 7.064490740882057e-07, | |
| "loss": 0.0561, | |
| "step": 119 | |
| }, | |
| { | |
| "epoch": 4.7407407407407405, | |
| "grad_norm": 0.12447182089090347, | |
| "learning_rate": 4.909437331777179e-07, | |
| "loss": 0.0604, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 4.7407407407407405, | |
| "eval_loss": 0.07253248989582062, | |
| "eval_runtime": 27.1811, | |
| "eval_samples_per_second": 1.656, | |
| "eval_steps_per_second": 1.656, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 4.780246913580247, | |
| "grad_norm": 0.10179347544908524, | |
| "learning_rate": 3.143895053378698e-07, | |
| "loss": 0.0269, | |
| "step": 121 | |
| }, | |
| { | |
| "epoch": 4.8197530864197535, | |
| "grad_norm": 0.13091501593589783, | |
| "learning_rate": 1.7692529411904578e-07, | |
| "loss": 0.058, | |
| "step": 122 | |
| }, | |
| { | |
| "epoch": 4.859259259259259, | |
| "grad_norm": 0.10802372545003891, | |
| "learning_rate": 7.865924910916977e-08, | |
| "loss": 0.0415, | |
| "step": 123 | |
| }, | |
| { | |
| "epoch": 4.898765432098766, | |
| "grad_norm": 0.12209034711122513, | |
| "learning_rate": 1.9668680847356735e-08, | |
| "loss": 0.0583, | |
| "step": 124 | |
| }, | |
| { | |
| "epoch": 4.938271604938271, | |
| "grad_norm": 0.09619519859552383, | |
| "learning_rate": 0.0, | |
| "loss": 0.0166, | |
| "step": 125 | |
| }, | |
| { | |
| "epoch": 4.938271604938271, | |
| "step": 125, | |
| "total_flos": 1.5289467254459597e+17, | |
| "train_loss": 0.07538180674612523, | |
| "train_runtime": 4379.9763, | |
| "train_samples_per_second": 0.462, | |
| "train_steps_per_second": 0.029 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 125, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 5, | |
| "save_steps": 10, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 1.5289467254459597e+17, | |
| "train_batch_size": 1, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |