| { | |
| "best_metric": 0.12139405310153961, | |
| "best_model_checkpoint": "saves/psy-course-info/Ministral-8B-Instruct-2410/train/fold2/checkpoint-70", | |
| "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": 1.9392163753509521, | |
| "learning_rate": 7.692307692307694e-06, | |
| "loss": 0.8147, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.07901234567901234, | |
| "grad_norm": 2.0744500160217285, | |
| "learning_rate": 1.5384615384615387e-05, | |
| "loss": 0.9249, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.11851851851851852, | |
| "grad_norm": 2.1147079467773438, | |
| "learning_rate": 2.307692307692308e-05, | |
| "loss": 0.9351, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.1580246913580247, | |
| "grad_norm": 2.055079460144043, | |
| "learning_rate": 3.0769230769230774e-05, | |
| "loss": 0.9152, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.19753086419753085, | |
| "grad_norm": 1.8916347026824951, | |
| "learning_rate": 3.846153846153846e-05, | |
| "loss": 0.843, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.23703703703703705, | |
| "grad_norm": 2.1509392261505127, | |
| "learning_rate": 4.615384615384616e-05, | |
| "loss": 0.7458, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.2765432098765432, | |
| "grad_norm": 1.9193289279937744, | |
| "learning_rate": 5.384615384615385e-05, | |
| "loss": 0.7233, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.3160493827160494, | |
| "grad_norm": 1.467572808265686, | |
| "learning_rate": 6.153846153846155e-05, | |
| "loss": 0.552, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.35555555555555557, | |
| "grad_norm": 1.462829351425171, | |
| "learning_rate": 6.923076923076924e-05, | |
| "loss": 0.5136, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.3950617283950617, | |
| "grad_norm": 1.2101597785949707, | |
| "learning_rate": 7.692307692307693e-05, | |
| "loss": 0.4274, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.3950617283950617, | |
| "eval_loss": 0.36409687995910645, | |
| "eval_runtime": 21.4172, | |
| "eval_samples_per_second": 2.101, | |
| "eval_steps_per_second": 2.101, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.4345679012345679, | |
| "grad_norm": 1.5486946105957031, | |
| "learning_rate": 8.461538461538461e-05, | |
| "loss": 0.3841, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.4740740740740741, | |
| "grad_norm": 1.572493553161621, | |
| "learning_rate": 9.230769230769232e-05, | |
| "loss": 0.3212, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.5135802469135803, | |
| "grad_norm": 0.8203847408294678, | |
| "learning_rate": 0.0001, | |
| "loss": 0.2499, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.5530864197530864, | |
| "grad_norm": 0.7756222486495972, | |
| "learning_rate": 9.998033131915266e-05, | |
| "loss": 0.2554, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.5925925925925926, | |
| "grad_norm": 0.7892242074012756, | |
| "learning_rate": 9.992134075089084e-05, | |
| "loss": 0.2115, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.6320987654320988, | |
| "grad_norm": 0.8253913521766663, | |
| "learning_rate": 9.982307470588098e-05, | |
| "loss": 0.2206, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.671604938271605, | |
| "grad_norm": 0.7081310749053955, | |
| "learning_rate": 9.968561049466214e-05, | |
| "loss": 0.2433, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.7111111111111111, | |
| "grad_norm": 0.79506915807724, | |
| "learning_rate": 9.950905626682228e-05, | |
| "loss": 0.1785, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.7506172839506173, | |
| "grad_norm": 0.6451151371002197, | |
| "learning_rate": 9.92935509259118e-05, | |
| "loss": 0.1689, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.7901234567901234, | |
| "grad_norm": 0.7431484460830688, | |
| "learning_rate": 9.903926402016153e-05, | |
| "loss": 0.1848, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.7901234567901234, | |
| "eval_loss": 0.18945984542369843, | |
| "eval_runtime": 21.2889, | |
| "eval_samples_per_second": 2.114, | |
| "eval_steps_per_second": 2.114, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.8296296296296296, | |
| "grad_norm": 0.7917724847793579, | |
| "learning_rate": 9.874639560909117e-05, | |
| "loss": 0.2267, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.8691358024691358, | |
| "grad_norm": 0.6341084241867065, | |
| "learning_rate": 9.841517610611309e-05, | |
| "loss": 0.1831, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.908641975308642, | |
| "grad_norm": 0.728559136390686, | |
| "learning_rate": 9.804586609725499e-05, | |
| "loss": 0.1746, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.9481481481481482, | |
| "grad_norm": 0.7549369931221008, | |
| "learning_rate": 9.763875613614482e-05, | |
| "loss": 0.1538, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.9876543209876543, | |
| "grad_norm": 0.8737193942070007, | |
| "learning_rate": 9.719416651541839e-05, | |
| "loss": 0.1828, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 1.0271604938271606, | |
| "grad_norm": 0.6450258493423462, | |
| "learning_rate": 9.671244701472999e-05, | |
| "loss": 0.1621, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 1.0666666666666667, | |
| "grad_norm": 0.6465139389038086, | |
| "learning_rate": 9.619397662556435e-05, | |
| "loss": 0.1145, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 1.106172839506173, | |
| "grad_norm": 0.5950374007225037, | |
| "learning_rate": 9.563916325306594e-05, | |
| "loss": 0.1578, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 1.145679012345679, | |
| "grad_norm": 0.5813158750534058, | |
| "learning_rate": 9.504844339512095e-05, | |
| "loss": 0.1207, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 1.1851851851851851, | |
| "grad_norm": 0.6251365542411804, | |
| "learning_rate": 9.442228179894362e-05, | |
| "loss": 0.1516, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 1.1851851851851851, | |
| "eval_loss": 0.15647557377815247, | |
| "eval_runtime": 21.2827, | |
| "eval_samples_per_second": 2.114, | |
| "eval_steps_per_second": 2.114, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 1.2246913580246914, | |
| "grad_norm": 0.5688738822937012, | |
| "learning_rate": 9.376117109543769e-05, | |
| "loss": 0.1453, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 1.2641975308641975, | |
| "grad_norm": 0.638246476650238, | |
| "learning_rate": 9.306563141162046e-05, | |
| "loss": 0.1472, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 1.3037037037037038, | |
| "grad_norm": 0.6661675572395325, | |
| "learning_rate": 9.233620996141421e-05, | |
| "loss": 0.1117, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 1.34320987654321, | |
| "grad_norm": 0.6050694584846497, | |
| "learning_rate": 9.157348061512727e-05, | |
| "loss": 0.1054, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 1.382716049382716, | |
| "grad_norm": 0.7352551817893982, | |
| "learning_rate": 9.077804344796302e-05, | |
| "loss": 0.1301, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 1.4222222222222223, | |
| "grad_norm": 0.7025603652000427, | |
| "learning_rate": 8.995052426791247e-05, | |
| "loss": 0.1268, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 1.4617283950617284, | |
| "grad_norm": 0.6238076686859131, | |
| "learning_rate": 8.90915741234015e-05, | |
| "loss": 0.0965, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 1.5012345679012347, | |
| "grad_norm": 0.6396238207817078, | |
| "learning_rate": 8.820186879108038e-05, | |
| "loss": 0.131, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 1.5407407407407407, | |
| "grad_norm": 0.6953352689743042, | |
| "learning_rate": 8.728210824415827e-05, | |
| "loss": 0.1356, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 1.5802469135802468, | |
| "grad_norm": 0.8018702268600464, | |
| "learning_rate": 8.633301610170135e-05, | |
| "loss": 0.104, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 1.5802469135802468, | |
| "eval_loss": 0.1408115029335022, | |
| "eval_runtime": 21.2772, | |
| "eval_samples_per_second": 2.115, | |
| "eval_steps_per_second": 2.115, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 1.6197530864197531, | |
| "grad_norm": 0.6032540202140808, | |
| "learning_rate": 8.535533905932738e-05, | |
| "loss": 0.1553, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 1.6592592592592592, | |
| "grad_norm": 0.8814234137535095, | |
| "learning_rate": 8.434984630174509e-05, | |
| "loss": 0.1188, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 1.6987654320987655, | |
| "grad_norm": 0.5424626469612122, | |
| "learning_rate": 8.33173288976002e-05, | |
| "loss": 0.1117, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 1.7382716049382716, | |
| "grad_norm": 0.6306973695755005, | |
| "learning_rate": 8.225859917710439e-05, | |
| "loss": 0.1169, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 1.7777777777777777, | |
| "grad_norm": 0.509702742099762, | |
| "learning_rate": 8.117449009293668e-05, | |
| "loss": 0.086, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 1.817283950617284, | |
| "grad_norm": 0.5520027875900269, | |
| "learning_rate": 8.006585456492029e-05, | |
| "loss": 0.1313, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 1.8567901234567903, | |
| "grad_norm": 0.5237116813659668, | |
| "learning_rate": 7.89335648089903e-05, | |
| "loss": 0.1029, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 1.8962962962962964, | |
| "grad_norm": 0.6442205309867859, | |
| "learning_rate": 7.777851165098012e-05, | |
| "loss": 0.1043, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 1.9358024691358025, | |
| "grad_norm": 0.549638032913208, | |
| "learning_rate": 7.660160382576683e-05, | |
| "loss": 0.1036, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 1.9753086419753085, | |
| "grad_norm": 0.6014506816864014, | |
| "learning_rate": 7.540376726232648e-05, | |
| "loss": 0.1363, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 1.9753086419753085, | |
| "eval_loss": 0.13063183426856995, | |
| "eval_runtime": 21.2754, | |
| "eval_samples_per_second": 2.115, | |
| "eval_steps_per_second": 2.115, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 2.0148148148148146, | |
| "grad_norm": 0.5955559015274048, | |
| "learning_rate": 7.4185944355262e-05, | |
| "loss": 0.1293, | |
| "step": 51 | |
| }, | |
| { | |
| "epoch": 2.054320987654321, | |
| "grad_norm": 0.5651622414588928, | |
| "learning_rate": 7.294909322337689e-05, | |
| "loss": 0.0892, | |
| "step": 52 | |
| }, | |
| { | |
| "epoch": 2.093827160493827, | |
| "grad_norm": 0.5932772159576416, | |
| "learning_rate": 7.169418695587791e-05, | |
| "loss": 0.1127, | |
| "step": 53 | |
| }, | |
| { | |
| "epoch": 2.1333333333333333, | |
| "grad_norm": 0.7837232947349548, | |
| "learning_rate": 7.042221284679982e-05, | |
| "loss": 0.0928, | |
| "step": 54 | |
| }, | |
| { | |
| "epoch": 2.1728395061728394, | |
| "grad_norm": 0.5273874402046204, | |
| "learning_rate": 6.91341716182545e-05, | |
| "loss": 0.0715, | |
| "step": 55 | |
| }, | |
| { | |
| "epoch": 2.212345679012346, | |
| "grad_norm": 0.45036017894744873, | |
| "learning_rate": 6.783107663311565e-05, | |
| "loss": 0.0663, | |
| "step": 56 | |
| }, | |
| { | |
| "epoch": 2.251851851851852, | |
| "grad_norm": 0.581554114818573, | |
| "learning_rate": 6.651395309775837e-05, | |
| "loss": 0.0698, | |
| "step": 57 | |
| }, | |
| { | |
| "epoch": 2.291358024691358, | |
| "grad_norm": 0.42598626017570496, | |
| "learning_rate": 6.518383725548074e-05, | |
| "loss": 0.07, | |
| "step": 58 | |
| }, | |
| { | |
| "epoch": 2.330864197530864, | |
| "grad_norm": 0.7419708371162415, | |
| "learning_rate": 6.384177557124247e-05, | |
| "loss": 0.1106, | |
| "step": 59 | |
| }, | |
| { | |
| "epoch": 2.3703703703703702, | |
| "grad_norm": 0.5811840295791626, | |
| "learning_rate": 6.248882390836135e-05, | |
| "loss": 0.0662, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 2.3703703703703702, | |
| "eval_loss": 0.12864066660404205, | |
| "eval_runtime": 21.2801, | |
| "eval_samples_per_second": 2.115, | |
| "eval_steps_per_second": 2.115, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 2.4098765432098768, | |
| "grad_norm": 0.44270482659339905, | |
| "learning_rate": 6.112604669781572e-05, | |
| "loss": 0.0627, | |
| "step": 61 | |
| }, | |
| { | |
| "epoch": 2.449382716049383, | |
| "grad_norm": 0.6928550004959106, | |
| "learning_rate": 5.9754516100806423e-05, | |
| "loss": 0.0854, | |
| "step": 62 | |
| }, | |
| { | |
| "epoch": 2.488888888888889, | |
| "grad_norm": 0.6658982634544373, | |
| "learning_rate": 5.837531116523682e-05, | |
| "loss": 0.1113, | |
| "step": 63 | |
| }, | |
| { | |
| "epoch": 2.528395061728395, | |
| "grad_norm": 0.9538989663124084, | |
| "learning_rate": 5.698951697677498e-05, | |
| "loss": 0.103, | |
| "step": 64 | |
| }, | |
| { | |
| "epoch": 2.567901234567901, | |
| "grad_norm": 0.9965769052505493, | |
| "learning_rate": 5.559822380516539e-05, | |
| "loss": 0.0945, | |
| "step": 65 | |
| }, | |
| { | |
| "epoch": 2.6074074074074076, | |
| "grad_norm": 0.5255608558654785, | |
| "learning_rate": 5.420252624646238e-05, | |
| "loss": 0.0881, | |
| "step": 66 | |
| }, | |
| { | |
| "epoch": 2.6469135802469137, | |
| "grad_norm": 0.6020313501358032, | |
| "learning_rate": 5.2803522361859594e-05, | |
| "loss": 0.0556, | |
| "step": 67 | |
| }, | |
| { | |
| "epoch": 2.68641975308642, | |
| "grad_norm": 0.6699146628379822, | |
| "learning_rate": 5.140231281379345e-05, | |
| "loss": 0.0704, | |
| "step": 68 | |
| }, | |
| { | |
| "epoch": 2.725925925925926, | |
| "grad_norm": 0.5984654426574707, | |
| "learning_rate": 5e-05, | |
| "loss": 0.0803, | |
| "step": 69 | |
| }, | |
| { | |
| "epoch": 2.765432098765432, | |
| "grad_norm": 0.7844510078430176, | |
| "learning_rate": 4.859768718620656e-05, | |
| "loss": 0.0922, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 2.765432098765432, | |
| "eval_loss": 0.12139405310153961, | |
| "eval_runtime": 21.2667, | |
| "eval_samples_per_second": 2.116, | |
| "eval_steps_per_second": 2.116, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 2.8049382716049385, | |
| "grad_norm": 0.5050274133682251, | |
| "learning_rate": 4.7196477638140404e-05, | |
| "loss": 0.0589, | |
| "step": 71 | |
| }, | |
| { | |
| "epoch": 2.8444444444444446, | |
| "grad_norm": 0.5122713446617126, | |
| "learning_rate": 4.579747375353763e-05, | |
| "loss": 0.0712, | |
| "step": 72 | |
| }, | |
| { | |
| "epoch": 2.8839506172839506, | |
| "grad_norm": 0.5053260922431946, | |
| "learning_rate": 4.4401776194834613e-05, | |
| "loss": 0.0862, | |
| "step": 73 | |
| }, | |
| { | |
| "epoch": 2.9234567901234567, | |
| "grad_norm": 0.7144730091094971, | |
| "learning_rate": 4.3010483023225045e-05, | |
| "loss": 0.0872, | |
| "step": 74 | |
| }, | |
| { | |
| "epoch": 2.962962962962963, | |
| "grad_norm": 0.7245128750801086, | |
| "learning_rate": 4.162468883476319e-05, | |
| "loss": 0.104, | |
| "step": 75 | |
| }, | |
| { | |
| "epoch": 3.0024691358024693, | |
| "grad_norm": 0.5463870167732239, | |
| "learning_rate": 4.0245483899193595e-05, | |
| "loss": 0.0698, | |
| "step": 76 | |
| }, | |
| { | |
| "epoch": 3.0419753086419754, | |
| "grad_norm": 0.36004742980003357, | |
| "learning_rate": 3.887395330218429e-05, | |
| "loss": 0.0474, | |
| "step": 77 | |
| }, | |
| { | |
| "epoch": 3.0814814814814815, | |
| "grad_norm": 0.3733809292316437, | |
| "learning_rate": 3.7511176091638653e-05, | |
| "loss": 0.0552, | |
| "step": 78 | |
| }, | |
| { | |
| "epoch": 3.1209876543209876, | |
| "grad_norm": 0.508301317691803, | |
| "learning_rate": 3.6158224428757535e-05, | |
| "loss": 0.0773, | |
| "step": 79 | |
| }, | |
| { | |
| "epoch": 3.1604938271604937, | |
| "grad_norm": 0.45114657282829285, | |
| "learning_rate": 3.4816162744519263e-05, | |
| "loss": 0.0522, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 3.1604938271604937, | |
| "eval_loss": 0.12697041034698486, | |
| "eval_runtime": 21.2698, | |
| "eval_samples_per_second": 2.116, | |
| "eval_steps_per_second": 2.116, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 3.2, | |
| "grad_norm": 0.6771267056465149, | |
| "learning_rate": 3.3486046902241664e-05, | |
| "loss": 0.0661, | |
| "step": 81 | |
| }, | |
| { | |
| "epoch": 3.2395061728395063, | |
| "grad_norm": 0.3586583137512207, | |
| "learning_rate": 3.216892336688435e-05, | |
| "loss": 0.0455, | |
| "step": 82 | |
| }, | |
| { | |
| "epoch": 3.2790123456790123, | |
| "grad_norm": 0.46627748012542725, | |
| "learning_rate": 3.086582838174551e-05, | |
| "loss": 0.0704, | |
| "step": 83 | |
| }, | |
| { | |
| "epoch": 3.3185185185185184, | |
| "grad_norm": 0.5237717628479004, | |
| "learning_rate": 2.9577787153200197e-05, | |
| "loss": 0.0654, | |
| "step": 84 | |
| }, | |
| { | |
| "epoch": 3.3580246913580245, | |
| "grad_norm": 0.4477337598800659, | |
| "learning_rate": 2.8305813044122097e-05, | |
| "loss": 0.0372, | |
| "step": 85 | |
| }, | |
| { | |
| "epoch": 3.397530864197531, | |
| "grad_norm": 0.6172931790351868, | |
| "learning_rate": 2.705090677662311e-05, | |
| "loss": 0.0774, | |
| "step": 86 | |
| }, | |
| { | |
| "epoch": 3.437037037037037, | |
| "grad_norm": 0.5166515111923218, | |
| "learning_rate": 2.581405564473801e-05, | |
| "loss": 0.0434, | |
| "step": 87 | |
| }, | |
| { | |
| "epoch": 3.476543209876543, | |
| "grad_norm": 0.4992319643497467, | |
| "learning_rate": 2.459623273767354e-05, | |
| "loss": 0.0326, | |
| "step": 88 | |
| }, | |
| { | |
| "epoch": 3.5160493827160493, | |
| "grad_norm": 0.5272431373596191, | |
| "learning_rate": 2.3398396174233178e-05, | |
| "loss": 0.0452, | |
| "step": 89 | |
| }, | |
| { | |
| "epoch": 3.5555555555555554, | |
| "grad_norm": 0.4650990068912506, | |
| "learning_rate": 2.2221488349019903e-05, | |
| "loss": 0.0379, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 3.5555555555555554, | |
| "eval_loss": 0.12529005110263824, | |
| "eval_runtime": 21.3007, | |
| "eval_samples_per_second": 2.113, | |
| "eval_steps_per_second": 2.113, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 3.595061728395062, | |
| "grad_norm": 0.5520841479301453, | |
| "learning_rate": 2.1066435191009715e-05, | |
| "loss": 0.0793, | |
| "step": 91 | |
| }, | |
| { | |
| "epoch": 3.634567901234568, | |
| "grad_norm": 0.6085020899772644, | |
| "learning_rate": 1.9934145435079702e-05, | |
| "loss": 0.0617, | |
| "step": 92 | |
| }, | |
| { | |
| "epoch": 3.674074074074074, | |
| "grad_norm": 0.6123881936073303, | |
| "learning_rate": 1.8825509907063327e-05, | |
| "loss": 0.0511, | |
| "step": 93 | |
| }, | |
| { | |
| "epoch": 3.71358024691358, | |
| "grad_norm": 0.5792705416679382, | |
| "learning_rate": 1.774140082289563e-05, | |
| "loss": 0.0452, | |
| "step": 94 | |
| }, | |
| { | |
| "epoch": 3.753086419753086, | |
| "grad_norm": 0.5349885821342468, | |
| "learning_rate": 1.6682671102399805e-05, | |
| "loss": 0.0738, | |
| "step": 95 | |
| }, | |
| { | |
| "epoch": 3.7925925925925927, | |
| "grad_norm": 0.5215051770210266, | |
| "learning_rate": 1.5650153698254916e-05, | |
| "loss": 0.05, | |
| "step": 96 | |
| }, | |
| { | |
| "epoch": 3.832098765432099, | |
| "grad_norm": 0.5220066905021667, | |
| "learning_rate": 1.4644660940672627e-05, | |
| "loss": 0.0454, | |
| "step": 97 | |
| }, | |
| { | |
| "epoch": 3.871604938271605, | |
| "grad_norm": 0.5737330913543701, | |
| "learning_rate": 1.3666983898298657e-05, | |
| "loss": 0.0558, | |
| "step": 98 | |
| }, | |
| { | |
| "epoch": 3.911111111111111, | |
| "grad_norm": 0.6050511002540588, | |
| "learning_rate": 1.2717891755841722e-05, | |
| "loss": 0.0602, | |
| "step": 99 | |
| }, | |
| { | |
| "epoch": 3.950617283950617, | |
| "grad_norm": 0.6588086485862732, | |
| "learning_rate": 1.1798131208919627e-05, | |
| "loss": 0.0497, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 3.950617283950617, | |
| "eval_loss": 0.12695680558681488, | |
| "eval_runtime": 21.2658, | |
| "eval_samples_per_second": 2.116, | |
| "eval_steps_per_second": 2.116, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 3.9901234567901236, | |
| "grad_norm": 0.6601673364639282, | |
| "learning_rate": 1.090842587659851e-05, | |
| "loss": 0.0607, | |
| "step": 101 | |
| }, | |
| { | |
| "epoch": 4.029629629629629, | |
| "grad_norm": 0.5535750985145569, | |
| "learning_rate": 1.004947573208756e-05, | |
| "loss": 0.0558, | |
| "step": 102 | |
| }, | |
| { | |
| "epoch": 4.069135802469136, | |
| "grad_norm": 0.48454391956329346, | |
| "learning_rate": 9.221956552036992e-06, | |
| "loss": 0.0304, | |
| "step": 103 | |
| }, | |
| { | |
| "epoch": 4.108641975308642, | |
| "grad_norm": 0.508762776851654, | |
| "learning_rate": 8.426519384872733e-06, | |
| "loss": 0.051, | |
| "step": 104 | |
| }, | |
| { | |
| "epoch": 4.148148148148148, | |
| "grad_norm": 0.5949965715408325, | |
| "learning_rate": 7.663790038585793e-06, | |
| "loss": 0.0459, | |
| "step": 105 | |
| }, | |
| { | |
| "epoch": 4.187654320987654, | |
| "grad_norm": 0.5218549370765686, | |
| "learning_rate": 6.934368588379553e-06, | |
| "loss": 0.0388, | |
| "step": 106 | |
| }, | |
| { | |
| "epoch": 4.22716049382716, | |
| "grad_norm": 0.5128703713417053, | |
| "learning_rate": 6.238828904562316e-06, | |
| "loss": 0.0518, | |
| "step": 107 | |
| }, | |
| { | |
| "epoch": 4.266666666666667, | |
| "grad_norm": 0.5916151404380798, | |
| "learning_rate": 5.577718201056392e-06, | |
| "loss": 0.0521, | |
| "step": 108 | |
| }, | |
| { | |
| "epoch": 4.306172839506173, | |
| "grad_norm": 0.5764836072921753, | |
| "learning_rate": 4.951556604879048e-06, | |
| "loss": 0.0485, | |
| "step": 109 | |
| }, | |
| { | |
| "epoch": 4.345679012345679, | |
| "grad_norm": 0.41454049944877625, | |
| "learning_rate": 4.360836746934055e-06, | |
| "loss": 0.0362, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 4.345679012345679, | |
| "eval_loss": 0.12637026607990265, | |
| "eval_runtime": 21.2938, | |
| "eval_samples_per_second": 2.113, | |
| "eval_steps_per_second": 2.113, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 4.385185185185185, | |
| "grad_norm": 0.5815073847770691, | |
| "learning_rate": 3.8060233744356633e-06, | |
| "loss": 0.0426, | |
| "step": 111 | |
| }, | |
| { | |
| "epoch": 4.424691358024692, | |
| "grad_norm": 0.5312104821205139, | |
| "learning_rate": 3.2875529852700147e-06, | |
| "loss": 0.0349, | |
| "step": 112 | |
| }, | |
| { | |
| "epoch": 4.4641975308641975, | |
| "grad_norm": 0.616237223148346, | |
| "learning_rate": 2.8058334845816213e-06, | |
| "loss": 0.0377, | |
| "step": 113 | |
| }, | |
| { | |
| "epoch": 4.503703703703704, | |
| "grad_norm": 0.6417801976203918, | |
| "learning_rate": 2.361243863855184e-06, | |
| "loss": 0.0575, | |
| "step": 114 | |
| }, | |
| { | |
| "epoch": 4.54320987654321, | |
| "grad_norm": 0.3886057138442993, | |
| "learning_rate": 1.9541339027450256e-06, | |
| "loss": 0.0243, | |
| "step": 115 | |
| }, | |
| { | |
| "epoch": 4.582716049382716, | |
| "grad_norm": 0.38211461901664734, | |
| "learning_rate": 1.584823893886933e-06, | |
| "loss": 0.032, | |
| "step": 116 | |
| }, | |
| { | |
| "epoch": 4.622222222222222, | |
| "grad_norm": 0.3659462630748749, | |
| "learning_rate": 1.2536043909088191e-06, | |
| "loss": 0.0333, | |
| "step": 117 | |
| }, | |
| { | |
| "epoch": 4.661728395061728, | |
| "grad_norm": 0.615944504737854, | |
| "learning_rate": 9.607359798384785e-07, | |
| "loss": 0.0523, | |
| "step": 118 | |
| }, | |
| { | |
| "epoch": 4.701234567901235, | |
| "grad_norm": 0.6254489421844482, | |
| "learning_rate": 7.064490740882057e-07, | |
| "loss": 0.0591, | |
| "step": 119 | |
| }, | |
| { | |
| "epoch": 4.7407407407407405, | |
| "grad_norm": 0.49035632610321045, | |
| "learning_rate": 4.909437331777179e-07, | |
| "loss": 0.0447, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 4.7407407407407405, | |
| "eval_loss": 0.1263754665851593, | |
| "eval_runtime": 21.2846, | |
| "eval_samples_per_second": 2.114, | |
| "eval_steps_per_second": 2.114, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 4.780246913580247, | |
| "grad_norm": 0.4719583988189697, | |
| "learning_rate": 3.143895053378698e-07, | |
| "loss": 0.0488, | |
| "step": 121 | |
| }, | |
| { | |
| "epoch": 4.8197530864197535, | |
| "grad_norm": 0.37755486369132996, | |
| "learning_rate": 1.7692529411904578e-07, | |
| "loss": 0.0306, | |
| "step": 122 | |
| }, | |
| { | |
| "epoch": 4.859259259259259, | |
| "grad_norm": 0.5087811350822449, | |
| "learning_rate": 7.865924910916977e-08, | |
| "loss": 0.0448, | |
| "step": 123 | |
| }, | |
| { | |
| "epoch": 4.898765432098766, | |
| "grad_norm": 0.641684889793396, | |
| "learning_rate": 1.9668680847356735e-08, | |
| "loss": 0.0408, | |
| "step": 124 | |
| }, | |
| { | |
| "epoch": 4.938271604938271, | |
| "grad_norm": 0.5486564040184021, | |
| "learning_rate": 0.0, | |
| "loss": 0.0314, | |
| "step": 125 | |
| }, | |
| { | |
| "epoch": 4.938271604938271, | |
| "step": 125, | |
| "total_flos": 1.2889660877497958e+17, | |
| "train_loss": 0.1476166524887085, | |
| "train_runtime": 3601.8893, | |
| "train_samples_per_second": 0.562, | |
| "train_steps_per_second": 0.035 | |
| } | |
| ], | |
| "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": 1.2889660877497958e+17, | |
| "train_batch_size": 1, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |