| { |
| "best_metric": 0.11820545047521591, |
| "best_model_checkpoint": "saves/psy-course-info/Ministral-8B-Instruct-2410/train/fold9/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": 2.267932891845703, |
| "learning_rate": 7.692307692307694e-06, |
| "loss": 0.9081, |
| "step": 1 |
| }, |
| { |
| "epoch": 0.07901234567901234, |
| "grad_norm": 2.149989366531372, |
| "learning_rate": 1.5384615384615387e-05, |
| "loss": 0.8694, |
| "step": 2 |
| }, |
| { |
| "epoch": 0.11851851851851852, |
| "grad_norm": 2.1561567783355713, |
| "learning_rate": 2.307692307692308e-05, |
| "loss": 0.9707, |
| "step": 3 |
| }, |
| { |
| "epoch": 0.1580246913580247, |
| "grad_norm": 2.010114908218384, |
| "learning_rate": 3.0769230769230774e-05, |
| "loss": 0.8854, |
| "step": 4 |
| }, |
| { |
| "epoch": 0.19753086419753085, |
| "grad_norm": 1.9949238300323486, |
| "learning_rate": 3.846153846153846e-05, |
| "loss": 0.9068, |
| "step": 5 |
| }, |
| { |
| "epoch": 0.23703703703703705, |
| "grad_norm": 2.290142297744751, |
| "learning_rate": 4.615384615384616e-05, |
| "loss": 0.7982, |
| "step": 6 |
| }, |
| { |
| "epoch": 0.2765432098765432, |
| "grad_norm": 1.9806084632873535, |
| "learning_rate": 5.384615384615385e-05, |
| "loss": 0.7193, |
| "step": 7 |
| }, |
| { |
| "epoch": 0.3160493827160494, |
| "grad_norm": 1.5576744079589844, |
| "learning_rate": 6.153846153846155e-05, |
| "loss": 0.5019, |
| "step": 8 |
| }, |
| { |
| "epoch": 0.35555555555555557, |
| "grad_norm": 1.2144361734390259, |
| "learning_rate": 6.923076923076924e-05, |
| "loss": 0.493, |
| "step": 9 |
| }, |
| { |
| "epoch": 0.3950617283950617, |
| "grad_norm": 1.2067241668701172, |
| "learning_rate": 7.692307692307693e-05, |
| "loss": 0.421, |
| "step": 10 |
| }, |
| { |
| "epoch": 0.3950617283950617, |
| "eval_loss": 0.3943081796169281, |
| "eval_runtime": 21.1261, |
| "eval_samples_per_second": 2.13, |
| "eval_steps_per_second": 2.13, |
| "step": 10 |
| }, |
| { |
| "epoch": 0.4345679012345679, |
| "grad_norm": 1.4360164403915405, |
| "learning_rate": 8.461538461538461e-05, |
| "loss": 0.3594, |
| "step": 11 |
| }, |
| { |
| "epoch": 0.4740740740740741, |
| "grad_norm": 1.263163685798645, |
| "learning_rate": 9.230769230769232e-05, |
| "loss": 0.315, |
| "step": 12 |
| }, |
| { |
| "epoch": 0.5135802469135803, |
| "grad_norm": 1.0089137554168701, |
| "learning_rate": 0.0001, |
| "loss": 0.2873, |
| "step": 13 |
| }, |
| { |
| "epoch": 0.5530864197530864, |
| "grad_norm": 0.8546875715255737, |
| "learning_rate": 9.998033131915266e-05, |
| "loss": 0.2753, |
| "step": 14 |
| }, |
| { |
| "epoch": 0.5925925925925926, |
| "grad_norm": 1.0516281127929688, |
| "learning_rate": 9.992134075089084e-05, |
| "loss": 0.2268, |
| "step": 15 |
| }, |
| { |
| "epoch": 0.6320987654320988, |
| "grad_norm": 0.7883739471435547, |
| "learning_rate": 9.982307470588098e-05, |
| "loss": 0.2001, |
| "step": 16 |
| }, |
| { |
| "epoch": 0.671604938271605, |
| "grad_norm": 0.8319458365440369, |
| "learning_rate": 9.968561049466214e-05, |
| "loss": 0.284, |
| "step": 17 |
| }, |
| { |
| "epoch": 0.7111111111111111, |
| "grad_norm": 0.7572959661483765, |
| "learning_rate": 9.950905626682228e-05, |
| "loss": 0.1945, |
| "step": 18 |
| }, |
| { |
| "epoch": 0.7506172839506173, |
| "grad_norm": 0.7129479646682739, |
| "learning_rate": 9.92935509259118e-05, |
| "loss": 0.2275, |
| "step": 19 |
| }, |
| { |
| "epoch": 0.7901234567901234, |
| "grad_norm": 0.6761314272880554, |
| "learning_rate": 9.903926402016153e-05, |
| "loss": 0.1967, |
| "step": 20 |
| }, |
| { |
| "epoch": 0.7901234567901234, |
| "eval_loss": 0.19770129024982452, |
| "eval_runtime": 21.0247, |
| "eval_samples_per_second": 2.14, |
| "eval_steps_per_second": 2.14, |
| "step": 20 |
| }, |
| { |
| "epoch": 0.8296296296296296, |
| "grad_norm": 0.7422728538513184, |
| "learning_rate": 9.874639560909117e-05, |
| "loss": 0.2397, |
| "step": 21 |
| }, |
| { |
| "epoch": 0.8691358024691358, |
| "grad_norm": 0.6258648633956909, |
| "learning_rate": 9.841517610611309e-05, |
| "loss": 0.1865, |
| "step": 22 |
| }, |
| { |
| "epoch": 0.908641975308642, |
| "grad_norm": 0.6076794266700745, |
| "learning_rate": 9.804586609725499e-05, |
| "loss": 0.164, |
| "step": 23 |
| }, |
| { |
| "epoch": 0.9481481481481482, |
| "grad_norm": 0.7265359163284302, |
| "learning_rate": 9.763875613614482e-05, |
| "loss": 0.1935, |
| "step": 24 |
| }, |
| { |
| "epoch": 0.9876543209876543, |
| "grad_norm": 0.6017918586730957, |
| "learning_rate": 9.719416651541839e-05, |
| "loss": 0.1417, |
| "step": 25 |
| }, |
| { |
| "epoch": 1.0271604938271606, |
| "grad_norm": 0.6983426213264465, |
| "learning_rate": 9.671244701472999e-05, |
| "loss": 0.1564, |
| "step": 26 |
| }, |
| { |
| "epoch": 1.0666666666666667, |
| "grad_norm": 0.5039434432983398, |
| "learning_rate": 9.619397662556435e-05, |
| "loss": 0.1451, |
| "step": 27 |
| }, |
| { |
| "epoch": 1.106172839506173, |
| "grad_norm": 0.5276407599449158, |
| "learning_rate": 9.563916325306594e-05, |
| "loss": 0.1332, |
| "step": 28 |
| }, |
| { |
| "epoch": 1.145679012345679, |
| "grad_norm": 0.5025568604469299, |
| "learning_rate": 9.504844339512095e-05, |
| "loss": 0.1187, |
| "step": 29 |
| }, |
| { |
| "epoch": 1.1851851851851851, |
| "grad_norm": 0.7655392289161682, |
| "learning_rate": 9.442228179894362e-05, |
| "loss": 0.1802, |
| "step": 30 |
| }, |
| { |
| "epoch": 1.1851851851851851, |
| "eval_loss": 0.15895450115203857, |
| "eval_runtime": 21.0278, |
| "eval_samples_per_second": 2.14, |
| "eval_steps_per_second": 2.14, |
| "step": 30 |
| }, |
| { |
| "epoch": 1.2246913580246914, |
| "grad_norm": 0.7681614756584167, |
| "learning_rate": 9.376117109543769e-05, |
| "loss": 0.1496, |
| "step": 31 |
| }, |
| { |
| "epoch": 1.2641975308641975, |
| "grad_norm": 0.699471652507782, |
| "learning_rate": 9.306563141162046e-05, |
| "loss": 0.1534, |
| "step": 32 |
| }, |
| { |
| "epoch": 1.3037037037037038, |
| "grad_norm": 0.6465251445770264, |
| "learning_rate": 9.233620996141421e-05, |
| "loss": 0.1116, |
| "step": 33 |
| }, |
| { |
| "epoch": 1.34320987654321, |
| "grad_norm": 0.6052675247192383, |
| "learning_rate": 9.157348061512727e-05, |
| "loss": 0.1491, |
| "step": 34 |
| }, |
| { |
| "epoch": 1.382716049382716, |
| "grad_norm": 0.7901648879051208, |
| "learning_rate": 9.077804344796302e-05, |
| "loss": 0.1375, |
| "step": 35 |
| }, |
| { |
| "epoch": 1.4222222222222223, |
| "grad_norm": 0.888197124004364, |
| "learning_rate": 8.995052426791247e-05, |
| "loss": 0.1174, |
| "step": 36 |
| }, |
| { |
| "epoch": 1.4617283950617284, |
| "grad_norm": 0.6305508613586426, |
| "learning_rate": 8.90915741234015e-05, |
| "loss": 0.142, |
| "step": 37 |
| }, |
| { |
| "epoch": 1.5012345679012347, |
| "grad_norm": 0.6919771432876587, |
| "learning_rate": 8.820186879108038e-05, |
| "loss": 0.1258, |
| "step": 38 |
| }, |
| { |
| "epoch": 1.5407407407407407, |
| "grad_norm": 0.5369614362716675, |
| "learning_rate": 8.728210824415827e-05, |
| "loss": 0.1094, |
| "step": 39 |
| }, |
| { |
| "epoch": 1.5802469135802468, |
| "grad_norm": 0.8118646740913391, |
| "learning_rate": 8.633301610170135e-05, |
| "loss": 0.1218, |
| "step": 40 |
| }, |
| { |
| "epoch": 1.5802469135802468, |
| "eval_loss": 0.1370917111635208, |
| "eval_runtime": 21.0318, |
| "eval_samples_per_second": 2.14, |
| "eval_steps_per_second": 2.14, |
| "step": 40 |
| }, |
| { |
| "epoch": 1.6197530864197531, |
| "grad_norm": 0.6777732372283936, |
| "learning_rate": 8.535533905932738e-05, |
| "loss": 0.1134, |
| "step": 41 |
| }, |
| { |
| "epoch": 1.6592592592592592, |
| "grad_norm": 0.6571015119552612, |
| "learning_rate": 8.434984630174509e-05, |
| "loss": 0.1019, |
| "step": 42 |
| }, |
| { |
| "epoch": 1.6987654320987655, |
| "grad_norm": 0.7193453907966614, |
| "learning_rate": 8.33173288976002e-05, |
| "loss": 0.1635, |
| "step": 43 |
| }, |
| { |
| "epoch": 1.7382716049382716, |
| "grad_norm": 0.6420557498931885, |
| "learning_rate": 8.225859917710439e-05, |
| "loss": 0.1315, |
| "step": 44 |
| }, |
| { |
| "epoch": 1.7777777777777777, |
| "grad_norm": 0.8335546851158142, |
| "learning_rate": 8.117449009293668e-05, |
| "loss": 0.1017, |
| "step": 45 |
| }, |
| { |
| "epoch": 1.817283950617284, |
| "grad_norm": 0.7458674907684326, |
| "learning_rate": 8.006585456492029e-05, |
| "loss": 0.0889, |
| "step": 46 |
| }, |
| { |
| "epoch": 1.8567901234567903, |
| "grad_norm": 0.5509297251701355, |
| "learning_rate": 7.89335648089903e-05, |
| "loss": 0.109, |
| "step": 47 |
| }, |
| { |
| "epoch": 1.8962962962962964, |
| "grad_norm": 0.6223629117012024, |
| "learning_rate": 7.777851165098012e-05, |
| "loss": 0.1163, |
| "step": 48 |
| }, |
| { |
| "epoch": 1.9358024691358025, |
| "grad_norm": 0.6716957688331604, |
| "learning_rate": 7.660160382576683e-05, |
| "loss": 0.0974, |
| "step": 49 |
| }, |
| { |
| "epoch": 1.9753086419753085, |
| "grad_norm": 0.5991176962852478, |
| "learning_rate": 7.540376726232648e-05, |
| "loss": 0.13, |
| "step": 50 |
| }, |
| { |
| "epoch": 1.9753086419753085, |
| "eval_loss": 0.13754324615001678, |
| "eval_runtime": 21.0412, |
| "eval_samples_per_second": 2.139, |
| "eval_steps_per_second": 2.139, |
| "step": 50 |
| }, |
| { |
| "epoch": 2.0148148148148146, |
| "grad_norm": 0.5294541120529175, |
| "learning_rate": 7.4185944355262e-05, |
| "loss": 0.1017, |
| "step": 51 |
| }, |
| { |
| "epoch": 2.054320987654321, |
| "grad_norm": 0.4622446894645691, |
| "learning_rate": 7.294909322337689e-05, |
| "loss": 0.106, |
| "step": 52 |
| }, |
| { |
| "epoch": 2.093827160493827, |
| "grad_norm": 0.5528680086135864, |
| "learning_rate": 7.169418695587791e-05, |
| "loss": 0.1142, |
| "step": 53 |
| }, |
| { |
| "epoch": 2.1333333333333333, |
| "grad_norm": 0.464229941368103, |
| "learning_rate": 7.042221284679982e-05, |
| "loss": 0.0772, |
| "step": 54 |
| }, |
| { |
| "epoch": 2.1728395061728394, |
| "grad_norm": 0.5126218199729919, |
| "learning_rate": 6.91341716182545e-05, |
| "loss": 0.0791, |
| "step": 55 |
| }, |
| { |
| "epoch": 2.212345679012346, |
| "grad_norm": 0.4333389401435852, |
| "learning_rate": 6.783107663311565e-05, |
| "loss": 0.0846, |
| "step": 56 |
| }, |
| { |
| "epoch": 2.251851851851852, |
| "grad_norm": 0.4767718017101288, |
| "learning_rate": 6.651395309775837e-05, |
| "loss": 0.0798, |
| "step": 57 |
| }, |
| { |
| "epoch": 2.291358024691358, |
| "grad_norm": 0.5369983315467834, |
| "learning_rate": 6.518383725548074e-05, |
| "loss": 0.0834, |
| "step": 58 |
| }, |
| { |
| "epoch": 2.330864197530864, |
| "grad_norm": 0.5478147268295288, |
| "learning_rate": 6.384177557124247e-05, |
| "loss": 0.0848, |
| "step": 59 |
| }, |
| { |
| "epoch": 2.3703703703703702, |
| "grad_norm": 0.588340163230896, |
| "learning_rate": 6.248882390836135e-05, |
| "loss": 0.0895, |
| "step": 60 |
| }, |
| { |
| "epoch": 2.3703703703703702, |
| "eval_loss": 0.13253279030323029, |
| "eval_runtime": 21.0299, |
| "eval_samples_per_second": 2.14, |
| "eval_steps_per_second": 2.14, |
| "step": 60 |
| }, |
| { |
| "epoch": 2.4098765432098768, |
| "grad_norm": 0.47088488936424255, |
| "learning_rate": 6.112604669781572e-05, |
| "loss": 0.0676, |
| "step": 61 |
| }, |
| { |
| "epoch": 2.449382716049383, |
| "grad_norm": 0.6412016153335571, |
| "learning_rate": 5.9754516100806423e-05, |
| "loss": 0.083, |
| "step": 62 |
| }, |
| { |
| "epoch": 2.488888888888889, |
| "grad_norm": 0.5681815147399902, |
| "learning_rate": 5.837531116523682e-05, |
| "loss": 0.0822, |
| "step": 63 |
| }, |
| { |
| "epoch": 2.528395061728395, |
| "grad_norm": 0.8427196145057678, |
| "learning_rate": 5.698951697677498e-05, |
| "loss": 0.1547, |
| "step": 64 |
| }, |
| { |
| "epoch": 2.567901234567901, |
| "grad_norm": 0.6931471824645996, |
| "learning_rate": 5.559822380516539e-05, |
| "loss": 0.0919, |
| "step": 65 |
| }, |
| { |
| "epoch": 2.6074074074074076, |
| "grad_norm": 0.7217737436294556, |
| "learning_rate": 5.420252624646238e-05, |
| "loss": 0.0985, |
| "step": 66 |
| }, |
| { |
| "epoch": 2.6469135802469137, |
| "grad_norm": 0.5449070334434509, |
| "learning_rate": 5.2803522361859594e-05, |
| "loss": 0.0699, |
| "step": 67 |
| }, |
| { |
| "epoch": 2.68641975308642, |
| "grad_norm": 0.7367754578590393, |
| "learning_rate": 5.140231281379345e-05, |
| "loss": 0.0875, |
| "step": 68 |
| }, |
| { |
| "epoch": 2.725925925925926, |
| "grad_norm": 0.722212553024292, |
| "learning_rate": 5e-05, |
| "loss": 0.0802, |
| "step": 69 |
| }, |
| { |
| "epoch": 2.765432098765432, |
| "grad_norm": 0.6478943228721619, |
| "learning_rate": 4.859768718620656e-05, |
| "loss": 0.0734, |
| "step": 70 |
| }, |
| { |
| "epoch": 2.765432098765432, |
| "eval_loss": 0.12502159178256989, |
| "eval_runtime": 21.0432, |
| "eval_samples_per_second": 2.138, |
| "eval_steps_per_second": 2.138, |
| "step": 70 |
| }, |
| { |
| "epoch": 2.8049382716049385, |
| "grad_norm": 0.7225408554077148, |
| "learning_rate": 4.7196477638140404e-05, |
| "loss": 0.0774, |
| "step": 71 |
| }, |
| { |
| "epoch": 2.8444444444444446, |
| "grad_norm": 0.6027604937553406, |
| "learning_rate": 4.579747375353763e-05, |
| "loss": 0.084, |
| "step": 72 |
| }, |
| { |
| "epoch": 2.8839506172839506, |
| "grad_norm": 0.7571199536323547, |
| "learning_rate": 4.4401776194834613e-05, |
| "loss": 0.0912, |
| "step": 73 |
| }, |
| { |
| "epoch": 2.9234567901234567, |
| "grad_norm": 0.5917590856552124, |
| "learning_rate": 4.3010483023225045e-05, |
| "loss": 0.07, |
| "step": 74 |
| }, |
| { |
| "epoch": 2.962962962962963, |
| "grad_norm": 0.8222047090530396, |
| "learning_rate": 4.162468883476319e-05, |
| "loss": 0.0887, |
| "step": 75 |
| }, |
| { |
| "epoch": 3.0024691358024693, |
| "grad_norm": 0.5354052186012268, |
| "learning_rate": 4.0245483899193595e-05, |
| "loss": 0.0528, |
| "step": 76 |
| }, |
| { |
| "epoch": 3.0419753086419754, |
| "grad_norm": 0.36689287424087524, |
| "learning_rate": 3.887395330218429e-05, |
| "loss": 0.0376, |
| "step": 77 |
| }, |
| { |
| "epoch": 3.0814814814814815, |
| "grad_norm": 0.5953245162963867, |
| "learning_rate": 3.7511176091638653e-05, |
| "loss": 0.0586, |
| "step": 78 |
| }, |
| { |
| "epoch": 3.1209876543209876, |
| "grad_norm": 0.5751317739486694, |
| "learning_rate": 3.6158224428757535e-05, |
| "loss": 0.0595, |
| "step": 79 |
| }, |
| { |
| "epoch": 3.1604938271604937, |
| "grad_norm": 0.4844985008239746, |
| "learning_rate": 3.4816162744519263e-05, |
| "loss": 0.0631, |
| "step": 80 |
| }, |
| { |
| "epoch": 3.1604938271604937, |
| "eval_loss": 0.1273876577615738, |
| "eval_runtime": 21.0513, |
| "eval_samples_per_second": 2.138, |
| "eval_steps_per_second": 2.138, |
| "step": 80 |
| }, |
| { |
| "epoch": 3.2, |
| "grad_norm": 0.6709802150726318, |
| "learning_rate": 3.3486046902241664e-05, |
| "loss": 0.0909, |
| "step": 81 |
| }, |
| { |
| "epoch": 3.2395061728395063, |
| "grad_norm": 0.29190948605537415, |
| "learning_rate": 3.216892336688435e-05, |
| "loss": 0.031, |
| "step": 82 |
| }, |
| { |
| "epoch": 3.2790123456790123, |
| "grad_norm": 0.39608946442604065, |
| "learning_rate": 3.086582838174551e-05, |
| "loss": 0.0507, |
| "step": 83 |
| }, |
| { |
| "epoch": 3.3185185185185184, |
| "grad_norm": 0.6933883428573608, |
| "learning_rate": 2.9577787153200197e-05, |
| "loss": 0.0693, |
| "step": 84 |
| }, |
| { |
| "epoch": 3.3580246913580245, |
| "grad_norm": 0.3954196274280548, |
| "learning_rate": 2.8305813044122097e-05, |
| "loss": 0.0536, |
| "step": 85 |
| }, |
| { |
| "epoch": 3.397530864197531, |
| "grad_norm": 0.5974686741828918, |
| "learning_rate": 2.705090677662311e-05, |
| "loss": 0.0667, |
| "step": 86 |
| }, |
| { |
| "epoch": 3.437037037037037, |
| "grad_norm": 0.7052604556083679, |
| "learning_rate": 2.581405564473801e-05, |
| "loss": 0.0612, |
| "step": 87 |
| }, |
| { |
| "epoch": 3.476543209876543, |
| "grad_norm": 0.6860325932502747, |
| "learning_rate": 2.459623273767354e-05, |
| "loss": 0.0567, |
| "step": 88 |
| }, |
| { |
| "epoch": 3.5160493827160493, |
| "grad_norm": 0.4220046401023865, |
| "learning_rate": 2.3398396174233178e-05, |
| "loss": 0.0394, |
| "step": 89 |
| }, |
| { |
| "epoch": 3.5555555555555554, |
| "grad_norm": 0.39881110191345215, |
| "learning_rate": 2.2221488349019903e-05, |
| "loss": 0.0475, |
| "step": 90 |
| }, |
| { |
| "epoch": 3.5555555555555554, |
| "eval_loss": 0.12234313786029816, |
| "eval_runtime": 21.061, |
| "eval_samples_per_second": 2.137, |
| "eval_steps_per_second": 2.137, |
| "step": 90 |
| }, |
| { |
| "epoch": 3.595061728395062, |
| "grad_norm": 0.6795773506164551, |
| "learning_rate": 2.1066435191009715e-05, |
| "loss": 0.0897, |
| "step": 91 |
| }, |
| { |
| "epoch": 3.634567901234568, |
| "grad_norm": 0.8449930548667908, |
| "learning_rate": 1.9934145435079702e-05, |
| "loss": 0.0724, |
| "step": 92 |
| }, |
| { |
| "epoch": 3.674074074074074, |
| "grad_norm": 0.49083274602890015, |
| "learning_rate": 1.8825509907063327e-05, |
| "loss": 0.057, |
| "step": 93 |
| }, |
| { |
| "epoch": 3.71358024691358, |
| "grad_norm": 0.6024028658866882, |
| "learning_rate": 1.774140082289563e-05, |
| "loss": 0.069, |
| "step": 94 |
| }, |
| { |
| "epoch": 3.753086419753086, |
| "grad_norm": 0.6425252556800842, |
| "learning_rate": 1.6682671102399805e-05, |
| "loss": 0.0719, |
| "step": 95 |
| }, |
| { |
| "epoch": 3.7925925925925927, |
| "grad_norm": 0.31590351462364197, |
| "learning_rate": 1.5650153698254916e-05, |
| "loss": 0.0256, |
| "step": 96 |
| }, |
| { |
| "epoch": 3.832098765432099, |
| "grad_norm": 0.5202229619026184, |
| "learning_rate": 1.4644660940672627e-05, |
| "loss": 0.0569, |
| "step": 97 |
| }, |
| { |
| "epoch": 3.871604938271605, |
| "grad_norm": 0.5161954164505005, |
| "learning_rate": 1.3666983898298657e-05, |
| "loss": 0.0557, |
| "step": 98 |
| }, |
| { |
| "epoch": 3.911111111111111, |
| "grad_norm": 0.6807634234428406, |
| "learning_rate": 1.2717891755841722e-05, |
| "loss": 0.0682, |
| "step": 99 |
| }, |
| { |
| "epoch": 3.950617283950617, |
| "grad_norm": 0.6412593722343445, |
| "learning_rate": 1.1798131208919627e-05, |
| "loss": 0.0618, |
| "step": 100 |
| }, |
| { |
| "epoch": 3.950617283950617, |
| "eval_loss": 0.11820545047521591, |
| "eval_runtime": 21.0622, |
| "eval_samples_per_second": 2.137, |
| "eval_steps_per_second": 2.137, |
| "step": 100 |
| }, |
| { |
| "epoch": 3.9901234567901236, |
| "grad_norm": 0.6479275822639465, |
| "learning_rate": 1.090842587659851e-05, |
| "loss": 0.0593, |
| "step": 101 |
| }, |
| { |
| "epoch": 4.029629629629629, |
| "grad_norm": 0.5316906571388245, |
| "learning_rate": 1.004947573208756e-05, |
| "loss": 0.0464, |
| "step": 102 |
| }, |
| { |
| "epoch": 4.069135802469136, |
| "grad_norm": 0.6391744017601013, |
| "learning_rate": 9.221956552036992e-06, |
| "loss": 0.0398, |
| "step": 103 |
| }, |
| { |
| "epoch": 4.108641975308642, |
| "grad_norm": 0.4400300681591034, |
| "learning_rate": 8.426519384872733e-06, |
| "loss": 0.0374, |
| "step": 104 |
| }, |
| { |
| "epoch": 4.148148148148148, |
| "grad_norm": 0.5314998030662537, |
| "learning_rate": 7.663790038585793e-06, |
| "loss": 0.0459, |
| "step": 105 |
| }, |
| { |
| "epoch": 4.187654320987654, |
| "grad_norm": 0.38742637634277344, |
| "learning_rate": 6.934368588379553e-06, |
| "loss": 0.0302, |
| "step": 106 |
| }, |
| { |
| "epoch": 4.22716049382716, |
| "grad_norm": 0.48696058988571167, |
| "learning_rate": 6.238828904562316e-06, |
| "loss": 0.0508, |
| "step": 107 |
| }, |
| { |
| "epoch": 4.266666666666667, |
| "grad_norm": 0.5439883470535278, |
| "learning_rate": 5.577718201056392e-06, |
| "loss": 0.0507, |
| "step": 108 |
| }, |
| { |
| "epoch": 4.306172839506173, |
| "grad_norm": 0.6359132528305054, |
| "learning_rate": 4.951556604879048e-06, |
| "loss": 0.0597, |
| "step": 109 |
| }, |
| { |
| "epoch": 4.345679012345679, |
| "grad_norm": 0.46427908539772034, |
| "learning_rate": 4.360836746934055e-06, |
| "loss": 0.035, |
| "step": 110 |
| }, |
| { |
| "epoch": 4.345679012345679, |
| "eval_loss": 0.12267247587442398, |
| "eval_runtime": 21.0636, |
| "eval_samples_per_second": 2.136, |
| "eval_steps_per_second": 2.136, |
| "step": 110 |
| }, |
| { |
| "epoch": 4.385185185185185, |
| "grad_norm": 0.5930352210998535, |
| "learning_rate": 3.8060233744356633e-06, |
| "loss": 0.0517, |
| "step": 111 |
| }, |
| { |
| "epoch": 4.424691358024692, |
| "grad_norm": 0.5504700541496277, |
| "learning_rate": 3.2875529852700147e-06, |
| "loss": 0.0505, |
| "step": 112 |
| }, |
| { |
| "epoch": 4.4641975308641975, |
| "grad_norm": 0.41203999519348145, |
| "learning_rate": 2.8058334845816213e-06, |
| "loss": 0.0365, |
| "step": 113 |
| }, |
| { |
| "epoch": 4.503703703703704, |
| "grad_norm": 0.5552165508270264, |
| "learning_rate": 2.361243863855184e-06, |
| "loss": 0.0552, |
| "step": 114 |
| }, |
| { |
| "epoch": 4.54320987654321, |
| "grad_norm": 0.5268175601959229, |
| "learning_rate": 1.9541339027450256e-06, |
| "loss": 0.0446, |
| "step": 115 |
| }, |
| { |
| "epoch": 4.582716049382716, |
| "grad_norm": 0.5041577816009521, |
| "learning_rate": 1.584823893886933e-06, |
| "loss": 0.046, |
| "step": 116 |
| }, |
| { |
| "epoch": 4.622222222222222, |
| "grad_norm": 0.4874894320964813, |
| "learning_rate": 1.2536043909088191e-06, |
| "loss": 0.0351, |
| "step": 117 |
| }, |
| { |
| "epoch": 4.661728395061728, |
| "grad_norm": 0.4240318834781647, |
| "learning_rate": 9.607359798384785e-07, |
| "loss": 0.0502, |
| "step": 118 |
| }, |
| { |
| "epoch": 4.701234567901235, |
| "grad_norm": 0.584980309009552, |
| "learning_rate": 7.064490740882057e-07, |
| "loss": 0.0582, |
| "step": 119 |
| }, |
| { |
| "epoch": 4.7407407407407405, |
| "grad_norm": 0.43420925736427307, |
| "learning_rate": 4.909437331777179e-07, |
| "loss": 0.0355, |
| "step": 120 |
| }, |
| { |
| "epoch": 4.7407407407407405, |
| "eval_loss": 0.12219589203596115, |
| "eval_runtime": 21.0582, |
| "eval_samples_per_second": 2.137, |
| "eval_steps_per_second": 2.137, |
| "step": 120 |
| }, |
| { |
| "epoch": 4.780246913580247, |
| "grad_norm": 0.5829199552536011, |
| "learning_rate": 3.143895053378698e-07, |
| "loss": 0.0555, |
| "step": 121 |
| }, |
| { |
| "epoch": 4.8197530864197535, |
| "grad_norm": 0.5836547017097473, |
| "learning_rate": 1.7692529411904578e-07, |
| "loss": 0.047, |
| "step": 122 |
| }, |
| { |
| "epoch": 4.859259259259259, |
| "grad_norm": 0.4449784457683563, |
| "learning_rate": 7.865924910916977e-08, |
| "loss": 0.0323, |
| "step": 123 |
| }, |
| { |
| "epoch": 4.898765432098766, |
| "grad_norm": 0.5675125122070312, |
| "learning_rate": 1.9668680847356735e-08, |
| "loss": 0.0599, |
| "step": 124 |
| }, |
| { |
| "epoch": 4.938271604938271, |
| "grad_norm": 0.6015435457229614, |
| "learning_rate": 0.0, |
| "loss": 0.0511, |
| "step": 125 |
| }, |
| { |
| "epoch": 4.938271604938271, |
| "step": 125, |
| "total_flos": 1.3026835897889587e+17, |
| "train_loss": 0.15202062311768533, |
| "train_runtime": 3654.1094, |
| "train_samples_per_second": 0.554, |
| "train_steps_per_second": 0.034 |
| } |
| ], |
| "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": 1.3026835897889587e+17, |
| "train_batch_size": 1, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
