| { |
| "best_metric": 0.04644819721579552, |
| "best_model_checkpoint": "saves/psy-course-doc-info/Ministral-8B-Instruct-2410/train/fold3/checkpoint-120", |
| "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": 0.6357119083404541, |
| "learning_rate": 7.692307692307694e-06, |
| "loss": 0.3382, |
| "step": 1 |
| }, |
| { |
| "epoch": 0.07901234567901234, |
| "grad_norm": 0.7237588167190552, |
| "learning_rate": 1.5384615384615387e-05, |
| "loss": 0.3843, |
| "step": 2 |
| }, |
| { |
| "epoch": 0.11851851851851852, |
| "grad_norm": 0.7471053600311279, |
| "learning_rate": 2.307692307692308e-05, |
| "loss": 0.3595, |
| "step": 3 |
| }, |
| { |
| "epoch": 0.1580246913580247, |
| "grad_norm": 0.7023885846138, |
| "learning_rate": 3.0769230769230774e-05, |
| "loss": 0.3492, |
| "step": 4 |
| }, |
| { |
| "epoch": 0.19753086419753085, |
| "grad_norm": 0.5739474296569824, |
| "learning_rate": 3.846153846153846e-05, |
| "loss": 0.319, |
| "step": 5 |
| }, |
| { |
| "epoch": 0.23703703703703705, |
| "grad_norm": 0.6540513038635254, |
| "learning_rate": 4.615384615384616e-05, |
| "loss": 0.3313, |
| "step": 6 |
| }, |
| { |
| "epoch": 0.2765432098765432, |
| "grad_norm": 0.4819052219390869, |
| "learning_rate": 5.384615384615385e-05, |
| "loss": 0.2951, |
| "step": 7 |
| }, |
| { |
| "epoch": 0.3160493827160494, |
| "grad_norm": 0.4157477915287018, |
| "learning_rate": 6.153846153846155e-05, |
| "loss": 0.2749, |
| "step": 8 |
| }, |
| { |
| "epoch": 0.35555555555555557, |
| "grad_norm": 0.5308283567428589, |
| "learning_rate": 6.923076923076924e-05, |
| "loss": 0.2881, |
| "step": 9 |
| }, |
| { |
| "epoch": 0.3950617283950617, |
| "grad_norm": 0.5385208129882812, |
| "learning_rate": 7.692307692307693e-05, |
| "loss": 0.2249, |
| "step": 10 |
| }, |
| { |
| "epoch": 0.3950617283950617, |
| "eval_loss": 0.22487014532089233, |
| "eval_runtime": 27.9129, |
| "eval_samples_per_second": 1.612, |
| "eval_steps_per_second": 1.612, |
| "step": 10 |
| }, |
| { |
| "epoch": 0.4345679012345679, |
| "grad_norm": 0.5301581621170044, |
| "learning_rate": 8.461538461538461e-05, |
| "loss": 0.2133, |
| "step": 11 |
| }, |
| { |
| "epoch": 0.4740740740740741, |
| "grad_norm": 0.5417924523353577, |
| "learning_rate": 9.230769230769232e-05, |
| "loss": 0.2143, |
| "step": 12 |
| }, |
| { |
| "epoch": 0.5135802469135803, |
| "grad_norm": 0.48627904057502747, |
| "learning_rate": 0.0001, |
| "loss": 0.1901, |
| "step": 13 |
| }, |
| { |
| "epoch": 0.5530864197530864, |
| "grad_norm": 0.46598610281944275, |
| "learning_rate": 9.998033131915266e-05, |
| "loss": 0.1727, |
| "step": 14 |
| }, |
| { |
| "epoch": 0.5925925925925926, |
| "grad_norm": 0.4300041198730469, |
| "learning_rate": 9.992134075089084e-05, |
| "loss": 0.1474, |
| "step": 15 |
| }, |
| { |
| "epoch": 0.6320987654320988, |
| "grad_norm": 0.5483227968215942, |
| "learning_rate": 9.982307470588098e-05, |
| "loss": 0.1364, |
| "step": 16 |
| }, |
| { |
| "epoch": 0.671604938271605, |
| "grad_norm": 0.4638817310333252, |
| "learning_rate": 9.968561049466214e-05, |
| "loss": 0.1253, |
| "step": 17 |
| }, |
| { |
| "epoch": 0.7111111111111111, |
| "grad_norm": 0.46473464369773865, |
| "learning_rate": 9.950905626682228e-05, |
| "loss": 0.1186, |
| "step": 18 |
| }, |
| { |
| "epoch": 0.7506172839506173, |
| "grad_norm": 0.49891844391822815, |
| "learning_rate": 9.92935509259118e-05, |
| "loss": 0.1087, |
| "step": 19 |
| }, |
| { |
| "epoch": 0.7901234567901234, |
| "grad_norm": 0.7426947951316833, |
| "learning_rate": 9.903926402016153e-05, |
| "loss": 0.1035, |
| "step": 20 |
| }, |
| { |
| "epoch": 0.7901234567901234, |
| "eval_loss": 0.10323404520750046, |
| "eval_runtime": 27.7895, |
| "eval_samples_per_second": 1.619, |
| "eval_steps_per_second": 1.619, |
| "step": 20 |
| }, |
| { |
| "epoch": 0.8296296296296296, |
| "grad_norm": 0.5166817903518677, |
| "learning_rate": 9.874639560909117e-05, |
| "loss": 0.1002, |
| "step": 21 |
| }, |
| { |
| "epoch": 0.8691358024691358, |
| "grad_norm": 0.31225165724754333, |
| "learning_rate": 9.841517610611309e-05, |
| "loss": 0.1034, |
| "step": 22 |
| }, |
| { |
| "epoch": 0.908641975308642, |
| "grad_norm": 0.4357728362083435, |
| "learning_rate": 9.804586609725499e-05, |
| "loss": 0.0877, |
| "step": 23 |
| }, |
| { |
| "epoch": 0.9481481481481482, |
| "grad_norm": 0.37829163670539856, |
| "learning_rate": 9.763875613614482e-05, |
| "loss": 0.0953, |
| "step": 24 |
| }, |
| { |
| "epoch": 0.9876543209876543, |
| "grad_norm": 0.45089611411094666, |
| "learning_rate": 9.719416651541839e-05, |
| "loss": 0.0961, |
| "step": 25 |
| }, |
| { |
| "epoch": 1.0271604938271606, |
| "grad_norm": 0.3842175602912903, |
| "learning_rate": 9.671244701472999e-05, |
| "loss": 0.081, |
| "step": 26 |
| }, |
| { |
| "epoch": 1.0666666666666667, |
| "grad_norm": 0.2731744647026062, |
| "learning_rate": 9.619397662556435e-05, |
| "loss": 0.0864, |
| "step": 27 |
| }, |
| { |
| "epoch": 1.106172839506173, |
| "grad_norm": 0.23375199735164642, |
| "learning_rate": 9.563916325306594e-05, |
| "loss": 0.0853, |
| "step": 28 |
| }, |
| { |
| "epoch": 1.145679012345679, |
| "grad_norm": 0.2906055152416229, |
| "learning_rate": 9.504844339512095e-05, |
| "loss": 0.0901, |
| "step": 29 |
| }, |
| { |
| "epoch": 1.1851851851851851, |
| "grad_norm": 0.27497485280036926, |
| "learning_rate": 9.442228179894362e-05, |
| "loss": 0.0769, |
| "step": 30 |
| }, |
| { |
| "epoch": 1.1851851851851851, |
| "eval_loss": 0.07871007919311523, |
| "eval_runtime": 27.8029, |
| "eval_samples_per_second": 1.619, |
| "eval_steps_per_second": 1.619, |
| "step": 30 |
| }, |
| { |
| "epoch": 1.2246913580246914, |
| "grad_norm": 0.32507264614105225, |
| "learning_rate": 9.376117109543769e-05, |
| "loss": 0.0793, |
| "step": 31 |
| }, |
| { |
| "epoch": 1.2641975308641975, |
| "grad_norm": 0.2574046850204468, |
| "learning_rate": 9.306563141162046e-05, |
| "loss": 0.073, |
| "step": 32 |
| }, |
| { |
| "epoch": 1.3037037037037038, |
| "grad_norm": 0.2699359655380249, |
| "learning_rate": 9.233620996141421e-05, |
| "loss": 0.0657, |
| "step": 33 |
| }, |
| { |
| "epoch": 1.34320987654321, |
| "grad_norm": 0.2902401089668274, |
| "learning_rate": 9.157348061512727e-05, |
| "loss": 0.0753, |
| "step": 34 |
| }, |
| { |
| "epoch": 1.382716049382716, |
| "grad_norm": 0.29739823937416077, |
| "learning_rate": 9.077804344796302e-05, |
| "loss": 0.0735, |
| "step": 35 |
| }, |
| { |
| "epoch": 1.4222222222222223, |
| "grad_norm": 0.2852456271648407, |
| "learning_rate": 8.995052426791247e-05, |
| "loss": 0.065, |
| "step": 36 |
| }, |
| { |
| "epoch": 1.4617283950617284, |
| "grad_norm": 0.2901184856891632, |
| "learning_rate": 8.90915741234015e-05, |
| "loss": 0.0717, |
| "step": 37 |
| }, |
| { |
| "epoch": 1.5012345679012347, |
| "grad_norm": 0.26133614778518677, |
| "learning_rate": 8.820186879108038e-05, |
| "loss": 0.0661, |
| "step": 38 |
| }, |
| { |
| "epoch": 1.5407407407407407, |
| "grad_norm": 0.22330009937286377, |
| "learning_rate": 8.728210824415827e-05, |
| "loss": 0.0517, |
| "step": 39 |
| }, |
| { |
| "epoch": 1.5802469135802468, |
| "grad_norm": 0.2404627501964569, |
| "learning_rate": 8.633301610170135e-05, |
| "loss": 0.0686, |
| "step": 40 |
| }, |
| { |
| "epoch": 1.5802469135802468, |
| "eval_loss": 0.061676185578107834, |
| "eval_runtime": 27.7995, |
| "eval_samples_per_second": 1.619, |
| "eval_steps_per_second": 1.619, |
| "step": 40 |
| }, |
| { |
| "epoch": 1.6197530864197531, |
| "grad_norm": 0.2976852357387543, |
| "learning_rate": 8.535533905932738e-05, |
| "loss": 0.0518, |
| "step": 41 |
| }, |
| { |
| "epoch": 1.6592592592592592, |
| "grad_norm": 0.21440541744232178, |
| "learning_rate": 8.434984630174509e-05, |
| "loss": 0.0537, |
| "step": 42 |
| }, |
| { |
| "epoch": 1.6987654320987655, |
| "grad_norm": 0.2148607224225998, |
| "learning_rate": 8.33173288976002e-05, |
| "loss": 0.057, |
| "step": 43 |
| }, |
| { |
| "epoch": 1.7382716049382716, |
| "grad_norm": 0.2529148757457733, |
| "learning_rate": 8.225859917710439e-05, |
| "loss": 0.0594, |
| "step": 44 |
| }, |
| { |
| "epoch": 1.7777777777777777, |
| "grad_norm": 0.2526922821998596, |
| "learning_rate": 8.117449009293668e-05, |
| "loss": 0.0557, |
| "step": 45 |
| }, |
| { |
| "epoch": 1.817283950617284, |
| "grad_norm": 0.22504571080207825, |
| "learning_rate": 8.006585456492029e-05, |
| "loss": 0.0539, |
| "step": 46 |
| }, |
| { |
| "epoch": 1.8567901234567903, |
| "grad_norm": 0.28532981872558594, |
| "learning_rate": 7.89335648089903e-05, |
| "loss": 0.0501, |
| "step": 47 |
| }, |
| { |
| "epoch": 1.8962962962962964, |
| "grad_norm": 0.35784009099006653, |
| "learning_rate": 7.777851165098012e-05, |
| "loss": 0.0585, |
| "step": 48 |
| }, |
| { |
| "epoch": 1.9358024691358025, |
| "grad_norm": 0.2801336348056793, |
| "learning_rate": 7.660160382576683e-05, |
| "loss": 0.0549, |
| "step": 49 |
| }, |
| { |
| "epoch": 1.9753086419753085, |
| "grad_norm": 0.20945020020008087, |
| "learning_rate": 7.540376726232648e-05, |
| "loss": 0.0502, |
| "step": 50 |
| }, |
| { |
| "epoch": 1.9753086419753085, |
| "eval_loss": 0.05541590601205826, |
| "eval_runtime": 27.7885, |
| "eval_samples_per_second": 1.619, |
| "eval_steps_per_second": 1.619, |
| "step": 50 |
| }, |
| { |
| "epoch": 2.0148148148148146, |
| "grad_norm": 0.31398406624794006, |
| "learning_rate": 7.4185944355262e-05, |
| "loss": 0.0491, |
| "step": 51 |
| }, |
| { |
| "epoch": 2.054320987654321, |
| "grad_norm": 0.2059389352798462, |
| "learning_rate": 7.294909322337689e-05, |
| "loss": 0.0402, |
| "step": 52 |
| }, |
| { |
| "epoch": 2.093827160493827, |
| "grad_norm": 0.4046320617198944, |
| "learning_rate": 7.169418695587791e-05, |
| "loss": 0.0421, |
| "step": 53 |
| }, |
| { |
| "epoch": 2.1333333333333333, |
| "grad_norm": 0.2759629487991333, |
| "learning_rate": 7.042221284679982e-05, |
| "loss": 0.0479, |
| "step": 54 |
| }, |
| { |
| "epoch": 2.1728395061728394, |
| "grad_norm": 0.2715336084365845, |
| "learning_rate": 6.91341716182545e-05, |
| "loss": 0.044, |
| "step": 55 |
| }, |
| { |
| "epoch": 2.212345679012346, |
| "grad_norm": 0.2801962196826935, |
| "learning_rate": 6.783107663311565e-05, |
| "loss": 0.0482, |
| "step": 56 |
| }, |
| { |
| "epoch": 2.251851851851852, |
| "grad_norm": 0.2721697688102722, |
| "learning_rate": 6.651395309775837e-05, |
| "loss": 0.054, |
| "step": 57 |
| }, |
| { |
| "epoch": 2.291358024691358, |
| "grad_norm": 0.24091903865337372, |
| "learning_rate": 6.518383725548074e-05, |
| "loss": 0.051, |
| "step": 58 |
| }, |
| { |
| "epoch": 2.330864197530864, |
| "grad_norm": 0.22097615897655487, |
| "learning_rate": 6.384177557124247e-05, |
| "loss": 0.0497, |
| "step": 59 |
| }, |
| { |
| "epoch": 2.3703703703703702, |
| "grad_norm": 0.23931631445884705, |
| "learning_rate": 6.248882390836135e-05, |
| "loss": 0.0458, |
| "step": 60 |
| }, |
| { |
| "epoch": 2.3703703703703702, |
| "eval_loss": 0.051887184381484985, |
| "eval_runtime": 27.7833, |
| "eval_samples_per_second": 1.62, |
| "eval_steps_per_second": 1.62, |
| "step": 60 |
| }, |
| { |
| "epoch": 2.4098765432098768, |
| "grad_norm": 0.23549491167068481, |
| "learning_rate": 6.112604669781572e-05, |
| "loss": 0.0482, |
| "step": 61 |
| }, |
| { |
| "epoch": 2.449382716049383, |
| "grad_norm": 0.19091638922691345, |
| "learning_rate": 5.9754516100806423e-05, |
| "loss": 0.0404, |
| "step": 62 |
| }, |
| { |
| "epoch": 2.488888888888889, |
| "grad_norm": 0.2045690417289734, |
| "learning_rate": 5.837531116523682e-05, |
| "loss": 0.0466, |
| "step": 63 |
| }, |
| { |
| "epoch": 2.528395061728395, |
| "grad_norm": 0.2098655253648758, |
| "learning_rate": 5.698951697677498e-05, |
| "loss": 0.0334, |
| "step": 64 |
| }, |
| { |
| "epoch": 2.567901234567901, |
| "grad_norm": 0.1953309178352356, |
| "learning_rate": 5.559822380516539e-05, |
| "loss": 0.0395, |
| "step": 65 |
| }, |
| { |
| "epoch": 2.6074074074074076, |
| "grad_norm": 0.21388518810272217, |
| "learning_rate": 5.420252624646238e-05, |
| "loss": 0.0466, |
| "step": 66 |
| }, |
| { |
| "epoch": 2.6469135802469137, |
| "grad_norm": 0.2073850780725479, |
| "learning_rate": 5.2803522361859594e-05, |
| "loss": 0.0388, |
| "step": 67 |
| }, |
| { |
| "epoch": 2.68641975308642, |
| "grad_norm": 0.18799500167369843, |
| "learning_rate": 5.140231281379345e-05, |
| "loss": 0.04, |
| "step": 68 |
| }, |
| { |
| "epoch": 2.725925925925926, |
| "grad_norm": 0.2780764102935791, |
| "learning_rate": 5e-05, |
| "loss": 0.0438, |
| "step": 69 |
| }, |
| { |
| "epoch": 2.765432098765432, |
| "grad_norm": 0.2084600329399109, |
| "learning_rate": 4.859768718620656e-05, |
| "loss": 0.0403, |
| "step": 70 |
| }, |
| { |
| "epoch": 2.765432098765432, |
| "eval_loss": 0.04916129633784294, |
| "eval_runtime": 27.7661, |
| "eval_samples_per_second": 1.621, |
| "eval_steps_per_second": 1.621, |
| "step": 70 |
| }, |
| { |
| "epoch": 2.8049382716049385, |
| "grad_norm": 0.217365100979805, |
| "learning_rate": 4.7196477638140404e-05, |
| "loss": 0.0425, |
| "step": 71 |
| }, |
| { |
| "epoch": 2.8444444444444446, |
| "grad_norm": 0.22451704740524292, |
| "learning_rate": 4.579747375353763e-05, |
| "loss": 0.0382, |
| "step": 72 |
| }, |
| { |
| "epoch": 2.8839506172839506, |
| "grad_norm": 0.1980130970478058, |
| "learning_rate": 4.4401776194834613e-05, |
| "loss": 0.0323, |
| "step": 73 |
| }, |
| { |
| "epoch": 2.9234567901234567, |
| "grad_norm": 0.29505684971809387, |
| "learning_rate": 4.3010483023225045e-05, |
| "loss": 0.0574, |
| "step": 74 |
| }, |
| { |
| "epoch": 2.962962962962963, |
| "grad_norm": 0.26398712396621704, |
| "learning_rate": 4.162468883476319e-05, |
| "loss": 0.05, |
| "step": 75 |
| }, |
| { |
| "epoch": 3.0024691358024693, |
| "grad_norm": 0.194844588637352, |
| "learning_rate": 4.0245483899193595e-05, |
| "loss": 0.0425, |
| "step": 76 |
| }, |
| { |
| "epoch": 3.0419753086419754, |
| "grad_norm": 0.36465680599212646, |
| "learning_rate": 3.887395330218429e-05, |
| "loss": 0.0382, |
| "step": 77 |
| }, |
| { |
| "epoch": 3.0814814814814815, |
| "grad_norm": 0.1569417417049408, |
| "learning_rate": 3.7511176091638653e-05, |
| "loss": 0.0344, |
| "step": 78 |
| }, |
| { |
| "epoch": 3.1209876543209876, |
| "grad_norm": 0.16212761402130127, |
| "learning_rate": 3.6158224428757535e-05, |
| "loss": 0.0351, |
| "step": 79 |
| }, |
| { |
| "epoch": 3.1604938271604937, |
| "grad_norm": 0.16740812361240387, |
| "learning_rate": 3.4816162744519263e-05, |
| "loss": 0.0369, |
| "step": 80 |
| }, |
| { |
| "epoch": 3.1604938271604937, |
| "eval_loss": 0.04776258021593094, |
| "eval_runtime": 27.7849, |
| "eval_samples_per_second": 1.62, |
| "eval_steps_per_second": 1.62, |
| "step": 80 |
| }, |
| { |
| "epoch": 3.2, |
| "grad_norm": 0.19212019443511963, |
| "learning_rate": 3.3486046902241664e-05, |
| "loss": 0.0415, |
| "step": 81 |
| }, |
| { |
| "epoch": 3.2395061728395063, |
| "grad_norm": 0.1885809749364853, |
| "learning_rate": 3.216892336688435e-05, |
| "loss": 0.0359, |
| "step": 82 |
| }, |
| { |
| "epoch": 3.2790123456790123, |
| "grad_norm": 0.19402921199798584, |
| "learning_rate": 3.086582838174551e-05, |
| "loss": 0.0337, |
| "step": 83 |
| }, |
| { |
| "epoch": 3.3185185185185184, |
| "grad_norm": 0.2325384020805359, |
| "learning_rate": 2.9577787153200197e-05, |
| "loss": 0.0329, |
| "step": 84 |
| }, |
| { |
| "epoch": 3.3580246913580245, |
| "grad_norm": 0.17437316477298737, |
| "learning_rate": 2.8305813044122097e-05, |
| "loss": 0.0334, |
| "step": 85 |
| }, |
| { |
| "epoch": 3.397530864197531, |
| "grad_norm": 0.14131787419319153, |
| "learning_rate": 2.705090677662311e-05, |
| "loss": 0.0332, |
| "step": 86 |
| }, |
| { |
| "epoch": 3.437037037037037, |
| "grad_norm": 0.17351099848747253, |
| "learning_rate": 2.581405564473801e-05, |
| "loss": 0.0327, |
| "step": 87 |
| }, |
| { |
| "epoch": 3.476543209876543, |
| "grad_norm": 0.2270965278148651, |
| "learning_rate": 2.459623273767354e-05, |
| "loss": 0.0329, |
| "step": 88 |
| }, |
| { |
| "epoch": 3.5160493827160493, |
| "grad_norm": 0.17000773549079895, |
| "learning_rate": 2.3398396174233178e-05, |
| "loss": 0.027, |
| "step": 89 |
| }, |
| { |
| "epoch": 3.5555555555555554, |
| "grad_norm": 0.2202456146478653, |
| "learning_rate": 2.2221488349019903e-05, |
| "loss": 0.0378, |
| "step": 90 |
| }, |
| { |
| "epoch": 3.5555555555555554, |
| "eval_loss": 0.04705554246902466, |
| "eval_runtime": 27.8041, |
| "eval_samples_per_second": 1.618, |
| "eval_steps_per_second": 1.618, |
| "step": 90 |
| }, |
| { |
| "epoch": 3.595061728395062, |
| "grad_norm": 0.1907626837491989, |
| "learning_rate": 2.1066435191009715e-05, |
| "loss": 0.038, |
| "step": 91 |
| }, |
| { |
| "epoch": 3.634567901234568, |
| "grad_norm": 0.22113323211669922, |
| "learning_rate": 1.9934145435079702e-05, |
| "loss": 0.0336, |
| "step": 92 |
| }, |
| { |
| "epoch": 3.674074074074074, |
| "grad_norm": 0.2739070951938629, |
| "learning_rate": 1.8825509907063327e-05, |
| "loss": 0.0376, |
| "step": 93 |
| }, |
| { |
| "epoch": 3.71358024691358, |
| "grad_norm": 0.2200823873281479, |
| "learning_rate": 1.774140082289563e-05, |
| "loss": 0.0446, |
| "step": 94 |
| }, |
| { |
| "epoch": 3.753086419753086, |
| "grad_norm": 0.22136153280735016, |
| "learning_rate": 1.6682671102399805e-05, |
| "loss": 0.0395, |
| "step": 95 |
| }, |
| { |
| "epoch": 3.7925925925925927, |
| "grad_norm": 0.20699213445186615, |
| "learning_rate": 1.5650153698254916e-05, |
| "loss": 0.0318, |
| "step": 96 |
| }, |
| { |
| "epoch": 3.832098765432099, |
| "grad_norm": 0.212611123919487, |
| "learning_rate": 1.4644660940672627e-05, |
| "loss": 0.0359, |
| "step": 97 |
| }, |
| { |
| "epoch": 3.871604938271605, |
| "grad_norm": 0.23981963098049164, |
| "learning_rate": 1.3666983898298657e-05, |
| "loss": 0.0307, |
| "step": 98 |
| }, |
| { |
| "epoch": 3.911111111111111, |
| "grad_norm": 0.18824400007724762, |
| "learning_rate": 1.2717891755841722e-05, |
| "loss": 0.0278, |
| "step": 99 |
| }, |
| { |
| "epoch": 3.950617283950617, |
| "grad_norm": 0.17974048852920532, |
| "learning_rate": 1.1798131208919627e-05, |
| "loss": 0.0286, |
| "step": 100 |
| }, |
| { |
| "epoch": 3.950617283950617, |
| "eval_loss": 0.04705539718270302, |
| "eval_runtime": 27.8107, |
| "eval_samples_per_second": 1.618, |
| "eval_steps_per_second": 1.618, |
| "step": 100 |
| }, |
| { |
| "epoch": 3.9901234567901236, |
| "grad_norm": 0.17898544669151306, |
| "learning_rate": 1.090842587659851e-05, |
| "loss": 0.0339, |
| "step": 101 |
| }, |
| { |
| "epoch": 4.029629629629629, |
| "grad_norm": 0.1873004138469696, |
| "learning_rate": 1.004947573208756e-05, |
| "loss": 0.0396, |
| "step": 102 |
| }, |
| { |
| "epoch": 4.069135802469136, |
| "grad_norm": 0.1678961217403412, |
| "learning_rate": 9.221956552036992e-06, |
| "loss": 0.0298, |
| "step": 103 |
| }, |
| { |
| "epoch": 4.108641975308642, |
| "grad_norm": 0.19086045026779175, |
| "learning_rate": 8.426519384872733e-06, |
| "loss": 0.0293, |
| "step": 104 |
| }, |
| { |
| "epoch": 4.148148148148148, |
| "grad_norm": 0.17178262770175934, |
| "learning_rate": 7.663790038585793e-06, |
| "loss": 0.0363, |
| "step": 105 |
| }, |
| { |
| "epoch": 4.187654320987654, |
| "grad_norm": 0.17829401791095734, |
| "learning_rate": 6.934368588379553e-06, |
| "loss": 0.031, |
| "step": 106 |
| }, |
| { |
| "epoch": 4.22716049382716, |
| "grad_norm": 0.15265066921710968, |
| "learning_rate": 6.238828904562316e-06, |
| "loss": 0.0227, |
| "step": 107 |
| }, |
| { |
| "epoch": 4.266666666666667, |
| "grad_norm": 0.1667207032442093, |
| "learning_rate": 5.577718201056392e-06, |
| "loss": 0.0407, |
| "step": 108 |
| }, |
| { |
| "epoch": 4.306172839506173, |
| "grad_norm": 0.17126813530921936, |
| "learning_rate": 4.951556604879048e-06, |
| "loss": 0.0309, |
| "step": 109 |
| }, |
| { |
| "epoch": 4.345679012345679, |
| "grad_norm": 0.16789357364177704, |
| "learning_rate": 4.360836746934055e-06, |
| "loss": 0.0287, |
| "step": 110 |
| }, |
| { |
| "epoch": 4.345679012345679, |
| "eval_loss": 0.04661821946501732, |
| "eval_runtime": 27.7886, |
| "eval_samples_per_second": 1.619, |
| "eval_steps_per_second": 1.619, |
| "step": 110 |
| }, |
| { |
| "epoch": 4.385185185185185, |
| "grad_norm": 0.14951647818088531, |
| "learning_rate": 3.8060233744356633e-06, |
| "loss": 0.0228, |
| "step": 111 |
| }, |
| { |
| "epoch": 4.424691358024692, |
| "grad_norm": 0.18676163256168365, |
| "learning_rate": 3.2875529852700147e-06, |
| "loss": 0.0273, |
| "step": 112 |
| }, |
| { |
| "epoch": 4.4641975308641975, |
| "grad_norm": 0.176141619682312, |
| "learning_rate": 2.8058334845816213e-06, |
| "loss": 0.0272, |
| "step": 113 |
| }, |
| { |
| "epoch": 4.503703703703704, |
| "grad_norm": 0.17098359763622284, |
| "learning_rate": 2.361243863855184e-06, |
| "loss": 0.0332, |
| "step": 114 |
| }, |
| { |
| "epoch": 4.54320987654321, |
| "grad_norm": 0.1787126064300537, |
| "learning_rate": 1.9541339027450256e-06, |
| "loss": 0.0297, |
| "step": 115 |
| }, |
| { |
| "epoch": 4.582716049382716, |
| "grad_norm": 0.18490760028362274, |
| "learning_rate": 1.584823893886933e-06, |
| "loss": 0.0293, |
| "step": 116 |
| }, |
| { |
| "epoch": 4.622222222222222, |
| "grad_norm": 0.16674566268920898, |
| "learning_rate": 1.2536043909088191e-06, |
| "loss": 0.0333, |
| "step": 117 |
| }, |
| { |
| "epoch": 4.661728395061728, |
| "grad_norm": 0.18049101531505585, |
| "learning_rate": 9.607359798384785e-07, |
| "loss": 0.0288, |
| "step": 118 |
| }, |
| { |
| "epoch": 4.701234567901235, |
| "grad_norm": 0.16676746308803558, |
| "learning_rate": 7.064490740882057e-07, |
| "loss": 0.0332, |
| "step": 119 |
| }, |
| { |
| "epoch": 4.7407407407407405, |
| "grad_norm": 0.17619037628173828, |
| "learning_rate": 4.909437331777179e-07, |
| "loss": 0.0348, |
| "step": 120 |
| }, |
| { |
| "epoch": 4.7407407407407405, |
| "eval_loss": 0.04644819721579552, |
| "eval_runtime": 27.7996, |
| "eval_samples_per_second": 1.619, |
| "eval_steps_per_second": 1.619, |
| "step": 120 |
| }, |
| { |
| "epoch": 4.780246913580247, |
| "grad_norm": 0.18961088359355927, |
| "learning_rate": 3.143895053378698e-07, |
| "loss": 0.0282, |
| "step": 121 |
| }, |
| { |
| "epoch": 4.8197530864197535, |
| "grad_norm": 0.1797262579202652, |
| "learning_rate": 1.7692529411904578e-07, |
| "loss": 0.0308, |
| "step": 122 |
| }, |
| { |
| "epoch": 4.859259259259259, |
| "grad_norm": 0.17407402396202087, |
| "learning_rate": 7.865924910916977e-08, |
| "loss": 0.0271, |
| "step": 123 |
| }, |
| { |
| "epoch": 4.898765432098766, |
| "grad_norm": 0.15580911934375763, |
| "learning_rate": 1.9668680847356735e-08, |
| "loss": 0.0269, |
| "step": 124 |
| }, |
| { |
| "epoch": 4.938271604938271, |
| "grad_norm": 0.19355471432209015, |
| "learning_rate": 0.0, |
| "loss": 0.0353, |
| "step": 125 |
| }, |
| { |
| "epoch": 4.938271604938271, |
| "step": 125, |
| "total_flos": 1.7656024539031142e+17, |
| "train_loss": 0.07671511381864547, |
| "train_runtime": 5248.7199, |
| "train_samples_per_second": 0.386, |
| "train_steps_per_second": 0.024 |
| } |
| ], |
| "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": 1.7656024539031142e+17, |
| "train_batch_size": 1, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
