| { | |
| "best_metric": 0.1395142674446106, | |
| "best_model_checkpoint": "/home/steam3/origin-ai/results/multilingual-train-test-table-results/ablation-arabic-mgte/arabic_chatgpt__3__bulgarian_true-and-fake-news_chatgpt;russian_chatgpt;bulgarian_true-and-fake-news_davinci/checkpoint-320", | |
| "epoch": 0.5015873015873016, | |
| "eval_steps": 10, | |
| "global_step": 790, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.006349206349206349, | |
| "grad_norm": 3.314401388168335, | |
| "learning_rate": 9.993646759847523e-05, | |
| "loss": 0.6929, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.006349206349206349, | |
| "eval_accuracy": 0.5251851851851852, | |
| "eval_f1": 0.6566684520621318, | |
| "eval_loss": 0.6887626647949219, | |
| "eval_precision": 0.514261744966443, | |
| "eval_recall": 0.9081481481481481, | |
| "eval_roc_auc": 0.5891390946502058, | |
| "eval_runtime": 5.5333, | |
| "eval_samples_per_second": 487.955, | |
| "eval_steps_per_second": 15.362, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.012698412698412698, | |
| "grad_norm": 2.6429762840270996, | |
| "learning_rate": 9.980940279542568e-05, | |
| "loss": 0.688, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.012698412698412698, | |
| "eval_accuracy": 0.5637037037037037, | |
| "eval_f1": 0.2929171668667467, | |
| "eval_loss": 0.674746036529541, | |
| "eval_precision": 0.7721518987341772, | |
| "eval_recall": 0.18074074074074073, | |
| "eval_roc_auc": 0.6710831275720164, | |
| "eval_runtime": 5.528, | |
| "eval_samples_per_second": 488.42, | |
| "eval_steps_per_second": 15.376, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.01904761904761905, | |
| "grad_norm": 3.3568179607391357, | |
| "learning_rate": 9.968233799237612e-05, | |
| "loss": 0.6482, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.01904761904761905, | |
| "eval_accuracy": 0.5981481481481481, | |
| "eval_f1": 0.3710144927536232, | |
| "eval_loss": 0.6537347435951233, | |
| "eval_precision": 0.8533333333333334, | |
| "eval_recall": 0.23703703703703705, | |
| "eval_roc_auc": 0.7466732510288066, | |
| "eval_runtime": 5.5119, | |
| "eval_samples_per_second": 489.853, | |
| "eval_steps_per_second": 15.421, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.025396825396825397, | |
| "grad_norm": 2.775456666946411, | |
| "learning_rate": 9.955527318932655e-05, | |
| "loss": 0.6524, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.025396825396825397, | |
| "eval_accuracy": 0.7307407407407407, | |
| "eval_f1": 0.7163480296527507, | |
| "eval_loss": 0.6117509603500366, | |
| "eval_precision": 0.7568013190436933, | |
| "eval_recall": 0.68, | |
| "eval_roc_auc": 0.8087465020576132, | |
| "eval_runtime": 5.5237, | |
| "eval_samples_per_second": 488.803, | |
| "eval_steps_per_second": 15.388, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.031746031746031744, | |
| "grad_norm": 2.0409586429595947, | |
| "learning_rate": 9.942820838627701e-05, | |
| "loss": 0.58, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.031746031746031744, | |
| "eval_accuracy": 0.7433333333333333, | |
| "eval_f1": 0.7790883009244501, | |
| "eval_loss": 0.5712039470672607, | |
| "eval_precision": 0.6838276440962507, | |
| "eval_recall": 0.9051851851851852, | |
| "eval_roc_auc": 0.8662809327846365, | |
| "eval_runtime": 5.5269, | |
| "eval_samples_per_second": 488.52, | |
| "eval_steps_per_second": 15.379, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.0380952380952381, | |
| "grad_norm": 5.313755035400391, | |
| "learning_rate": 9.930114358322745e-05, | |
| "loss": 0.5608, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.0380952380952381, | |
| "eval_accuracy": 0.8322222222222222, | |
| "eval_f1": 0.8195937873357229, | |
| "eval_loss": 0.48943084478378296, | |
| "eval_precision": 0.8863049095607235, | |
| "eval_recall": 0.7622222222222222, | |
| "eval_roc_auc": 0.9197953360768176, | |
| "eval_runtime": 5.541, | |
| "eval_samples_per_second": 487.279, | |
| "eval_steps_per_second": 15.34, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.044444444444444446, | |
| "grad_norm": 2.1755828857421875, | |
| "learning_rate": 9.91740787801779e-05, | |
| "loss": 0.4534, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.044444444444444446, | |
| "eval_accuracy": 0.8322222222222222, | |
| "eval_f1": 0.8533505988993202, | |
| "eval_loss": 0.4028916656970978, | |
| "eval_precision": 0.757906843013226, | |
| "eval_recall": 0.9762962962962963, | |
| "eval_roc_auc": 0.95520438957476, | |
| "eval_runtime": 5.5166, | |
| "eval_samples_per_second": 489.434, | |
| "eval_steps_per_second": 15.408, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.050793650793650794, | |
| "grad_norm": 2.359863758087158, | |
| "learning_rate": 9.904701397712835e-05, | |
| "loss": 0.2939, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 0.050793650793650794, | |
| "eval_accuracy": 0.87, | |
| "eval_f1": 0.882804674457429, | |
| "eval_loss": 0.30669787526130676, | |
| "eval_precision": 0.8036474164133739, | |
| "eval_recall": 0.9792592592592593, | |
| "eval_roc_auc": 0.967720987654321, | |
| "eval_runtime": 5.5661, | |
| "eval_samples_per_second": 485.082, | |
| "eval_steps_per_second": 15.271, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 0.05714285714285714, | |
| "grad_norm": 2.1184494495391846, | |
| "learning_rate": 9.893265565438374e-05, | |
| "loss": 0.2494, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 0.05714285714285714, | |
| "eval_accuracy": 0.9244444444444444, | |
| "eval_f1": 0.9246676514032496, | |
| "eval_loss": 0.19904199242591858, | |
| "eval_precision": 0.9219440353460973, | |
| "eval_recall": 0.9274074074074075, | |
| "eval_roc_auc": 0.9763517146776406, | |
| "eval_runtime": 5.5491, | |
| "eval_samples_per_second": 486.564, | |
| "eval_steps_per_second": 15.318, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 0.06349206349206349, | |
| "grad_norm": 2.1063764095306396, | |
| "learning_rate": 9.880559085133418e-05, | |
| "loss": 0.174, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.06349206349206349, | |
| "eval_accuracy": 0.8692592592592593, | |
| "eval_f1": 0.8829963539940338, | |
| "eval_loss": 0.4303587079048157, | |
| "eval_precision": 0.7990401919616077, | |
| "eval_recall": 0.9866666666666667, | |
| "eval_roc_auc": 0.9744661179698217, | |
| "eval_runtime": 5.5309, | |
| "eval_samples_per_second": 488.17, | |
| "eval_steps_per_second": 15.368, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.06984126984126984, | |
| "grad_norm": 11.44679069519043, | |
| "learning_rate": 9.869123252858958e-05, | |
| "loss": 0.269, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 0.06984126984126984, | |
| "eval_accuracy": 0.9277777777777778, | |
| "eval_f1": 0.9302824454772971, | |
| "eval_loss": 0.2445582151412964, | |
| "eval_precision": 0.899101589495508, | |
| "eval_recall": 0.9637037037037037, | |
| "eval_roc_auc": 0.9810120713305899, | |
| "eval_runtime": 5.5203, | |
| "eval_samples_per_second": 489.102, | |
| "eval_steps_per_second": 15.398, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 0.0761904761904762, | |
| "grad_norm": 0.09498822689056396, | |
| "learning_rate": 9.856416772554004e-05, | |
| "loss": 0.1981, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 0.0761904761904762, | |
| "eval_accuracy": 0.9303703703703704, | |
| "eval_f1": 0.9330960854092527, | |
| "eval_loss": 0.24259698390960693, | |
| "eval_precision": 0.897945205479452, | |
| "eval_recall": 0.9711111111111111, | |
| "eval_roc_auc": 0.9832271604938272, | |
| "eval_runtime": 5.5208, | |
| "eval_samples_per_second": 489.057, | |
| "eval_steps_per_second": 15.396, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 0.08253968253968254, | |
| "grad_norm": 0.047983940690755844, | |
| "learning_rate": 9.843710292249048e-05, | |
| "loss": 0.2035, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 0.08253968253968254, | |
| "eval_accuracy": 0.9288888888888889, | |
| "eval_f1": 0.9320594479830149, | |
| "eval_loss": 0.2548026740550995, | |
| "eval_precision": 0.8922764227642277, | |
| "eval_recall": 0.9755555555555555, | |
| "eval_roc_auc": 0.9850041152263376, | |
| "eval_runtime": 5.5252, | |
| "eval_samples_per_second": 488.669, | |
| "eval_steps_per_second": 15.384, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 0.08888888888888889, | |
| "grad_norm": 0.1345868706703186, | |
| "learning_rate": 9.831003811944091e-05, | |
| "loss": 0.2392, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 0.08888888888888889, | |
| "eval_accuracy": 0.9214814814814815, | |
| "eval_f1": 0.9260293091416608, | |
| "eval_loss": 0.28311270475387573, | |
| "eval_precision": 0.8753298153034301, | |
| "eval_recall": 0.9829629629629629, | |
| "eval_roc_auc": 0.9863648834019204, | |
| "eval_runtime": 5.5246, | |
| "eval_samples_per_second": 488.727, | |
| "eval_steps_per_second": 15.386, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 0.09523809523809523, | |
| "grad_norm": 0.3760770559310913, | |
| "learning_rate": 9.818297331639137e-05, | |
| "loss": 0.1965, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 0.09523809523809523, | |
| "eval_accuracy": 0.8429629629629629, | |
| "eval_f1": 0.8640153944836434, | |
| "eval_loss": 0.5912654995918274, | |
| "eval_precision": 0.7618778280542986, | |
| "eval_recall": 0.9977777777777778, | |
| "eval_roc_auc": 0.9832545953360768, | |
| "eval_runtime": 5.5302, | |
| "eval_samples_per_second": 488.232, | |
| "eval_steps_per_second": 15.37, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 0.10158730158730159, | |
| "grad_norm": 3.2790462970733643, | |
| "learning_rate": 9.805590851334181e-05, | |
| "loss": 0.3521, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 0.10158730158730159, | |
| "eval_accuracy": 0.9185185185185185, | |
| "eval_f1": 0.9238754325259516, | |
| "eval_loss": 0.25474533438682556, | |
| "eval_precision": 0.8668831168831169, | |
| "eval_recall": 0.9888888888888889, | |
| "eval_roc_auc": 0.9880035665294925, | |
| "eval_runtime": 5.5201, | |
| "eval_samples_per_second": 489.123, | |
| "eval_steps_per_second": 15.398, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 0.10793650793650794, | |
| "grad_norm": 3.765111207962036, | |
| "learning_rate": 9.792884371029225e-05, | |
| "loss": 0.4232, | |
| "step": 170 | |
| }, | |
| { | |
| "epoch": 0.10793650793650794, | |
| "eval_accuracy": 0.9474074074074074, | |
| "eval_f1": 0.9478324761204996, | |
| "eval_loss": 0.14082331955432892, | |
| "eval_precision": 0.9402332361516035, | |
| "eval_recall": 0.9555555555555556, | |
| "eval_roc_auc": 0.9880447187928669, | |
| "eval_runtime": 5.5338, | |
| "eval_samples_per_second": 487.911, | |
| "eval_steps_per_second": 15.36, | |
| "step": 170 | |
| }, | |
| { | |
| "epoch": 0.11428571428571428, | |
| "grad_norm": 1.110823154449463, | |
| "learning_rate": 9.780177890724271e-05, | |
| "loss": 0.1239, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 0.11428571428571428, | |
| "eval_accuracy": 0.9014814814814814, | |
| "eval_f1": 0.9098915989159891, | |
| "eval_loss": 0.26993757486343384, | |
| "eval_precision": 0.83832709113608, | |
| "eval_recall": 0.9948148148148148, | |
| "eval_roc_auc": 0.9881753086419753, | |
| "eval_runtime": 5.5165, | |
| "eval_samples_per_second": 489.445, | |
| "eval_steps_per_second": 15.408, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 0.12063492063492064, | |
| "grad_norm": 1.8782886266708374, | |
| "learning_rate": 9.767471410419315e-05, | |
| "loss": 0.1301, | |
| "step": 190 | |
| }, | |
| { | |
| "epoch": 0.12063492063492064, | |
| "eval_accuracy": 0.9366666666666666, | |
| "eval_f1": 0.9396825396825397, | |
| "eval_loss": 0.17670103907585144, | |
| "eval_precision": 0.896969696969697, | |
| "eval_recall": 0.9866666666666667, | |
| "eval_roc_auc": 0.989798353909465, | |
| "eval_runtime": 5.514, | |
| "eval_samples_per_second": 489.66, | |
| "eval_steps_per_second": 15.415, | |
| "step": 190 | |
| }, | |
| { | |
| "epoch": 0.12698412698412698, | |
| "grad_norm": 4.296081066131592, | |
| "learning_rate": 9.754764930114358e-05, | |
| "loss": 0.1532, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.12698412698412698, | |
| "eval_accuracy": 0.9225925925925926, | |
| "eval_f1": 0.9275563258232236, | |
| "eval_loss": 0.25379836559295654, | |
| "eval_precision": 0.8716612377850163, | |
| "eval_recall": 0.9911111111111112, | |
| "eval_roc_auc": 0.99000658436214, | |
| "eval_runtime": 5.5116, | |
| "eval_samples_per_second": 489.878, | |
| "eval_steps_per_second": 15.422, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.13333333333333333, | |
| "grad_norm": 1.7609732151031494, | |
| "learning_rate": 9.742058449809403e-05, | |
| "loss": 0.2815, | |
| "step": 210 | |
| }, | |
| { | |
| "epoch": 0.13333333333333333, | |
| "eval_accuracy": 0.9285185185185185, | |
| "eval_f1": 0.9328695652173913, | |
| "eval_loss": 0.24461880326271057, | |
| "eval_precision": 0.879344262295082, | |
| "eval_recall": 0.9933333333333333, | |
| "eval_roc_auc": 0.9911909465020576, | |
| "eval_runtime": 5.5105, | |
| "eval_samples_per_second": 489.978, | |
| "eval_steps_per_second": 15.425, | |
| "step": 210 | |
| }, | |
| { | |
| "epoch": 0.13968253968253969, | |
| "grad_norm": 0.20786483585834503, | |
| "learning_rate": 9.729351969504448e-05, | |
| "loss": 0.1336, | |
| "step": 220 | |
| }, | |
| { | |
| "epoch": 0.13968253968253969, | |
| "eval_accuracy": 0.9518518518518518, | |
| "eval_f1": 0.9534717251252685, | |
| "eval_loss": 0.1563795804977417, | |
| "eval_precision": 0.9224376731301939, | |
| "eval_recall": 0.9866666666666667, | |
| "eval_roc_auc": 0.992451303155007, | |
| "eval_runtime": 5.5138, | |
| "eval_samples_per_second": 489.68, | |
| "eval_steps_per_second": 15.416, | |
| "step": 220 | |
| }, | |
| { | |
| "epoch": 0.14603174603174604, | |
| "grad_norm": 0.6910555362701416, | |
| "learning_rate": 9.716645489199492e-05, | |
| "loss": 0.1237, | |
| "step": 230 | |
| }, | |
| { | |
| "epoch": 0.14603174603174604, | |
| "eval_accuracy": 0.937037037037037, | |
| "eval_f1": 0.9404344779257183, | |
| "eval_loss": 0.22764083743095398, | |
| "eval_precision": 0.8922872340425532, | |
| "eval_recall": 0.9940740740740741, | |
| "eval_roc_auc": 0.9923105624142661, | |
| "eval_runtime": 5.5171, | |
| "eval_samples_per_second": 489.388, | |
| "eval_steps_per_second": 15.407, | |
| "step": 230 | |
| }, | |
| { | |
| "epoch": 0.1523809523809524, | |
| "grad_norm": 2.4784867763519287, | |
| "learning_rate": 9.703939008894538e-05, | |
| "loss": 0.063, | |
| "step": 240 | |
| }, | |
| { | |
| "epoch": 0.1523809523809524, | |
| "eval_accuracy": 0.8637037037037038, | |
| "eval_f1": 0.8799739073711677, | |
| "eval_loss": 0.616968035697937, | |
| "eval_precision": 0.7861305361305362, | |
| "eval_recall": 0.9992592592592593, | |
| "eval_roc_auc": 0.9860919067215363, | |
| "eval_runtime": 5.5121, | |
| "eval_samples_per_second": 489.827, | |
| "eval_steps_per_second": 15.42, | |
| "step": 240 | |
| }, | |
| { | |
| "epoch": 0.15873015873015872, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.692503176620077e-05, | |
| "loss": 0.1347, | |
| "step": 250 | |
| }, | |
| { | |
| "epoch": 0.15873015873015872, | |
| "eval_accuracy": 0.9388888888888889, | |
| "eval_f1": 0.9420442571127503, | |
| "eval_loss": 0.24191488325595856, | |
| "eval_precision": 0.8957915831663327, | |
| "eval_recall": 0.9933333333333333, | |
| "eval_roc_auc": 0.9917956104252401, | |
| "eval_runtime": 5.5139, | |
| "eval_samples_per_second": 489.672, | |
| "eval_steps_per_second": 15.416, | |
| "step": 250 | |
| }, | |
| { | |
| "epoch": 0.16507936507936508, | |
| "grad_norm": 9.05746078491211, | |
| "learning_rate": 9.679796696315121e-05, | |
| "loss": 0.1642, | |
| "step": 260 | |
| }, | |
| { | |
| "epoch": 0.16507936507936508, | |
| "eval_accuracy": 0.9425925925925925, | |
| "eval_f1": 0.9452103216684341, | |
| "eval_loss": 0.2284214049577713, | |
| "eval_precision": 0.9039891818796484, | |
| "eval_recall": 0.9903703703703703, | |
| "eval_roc_auc": 0.9920307270233196, | |
| "eval_runtime": 5.5153, | |
| "eval_samples_per_second": 489.547, | |
| "eval_steps_per_second": 15.412, | |
| "step": 260 | |
| }, | |
| { | |
| "epoch": 0.17142857142857143, | |
| "grad_norm": 1.0563305616378784, | |
| "learning_rate": 9.667090216010166e-05, | |
| "loss": 0.1503, | |
| "step": 270 | |
| }, | |
| { | |
| "epoch": 0.17142857142857143, | |
| "eval_accuracy": 0.894074074074074, | |
| "eval_f1": 0.9040912139503688, | |
| "eval_loss": 0.4835222661495209, | |
| "eval_precision": 0.8259803921568627, | |
| "eval_recall": 0.9985185185185185, | |
| "eval_roc_auc": 0.9872872427983539, | |
| "eval_runtime": 5.5128, | |
| "eval_samples_per_second": 489.765, | |
| "eval_steps_per_second": 15.419, | |
| "step": 270 | |
| }, | |
| { | |
| "epoch": 0.17777777777777778, | |
| "grad_norm": 0.09033135324716568, | |
| "learning_rate": 9.65438373570521e-05, | |
| "loss": 0.0974, | |
| "step": 280 | |
| }, | |
| { | |
| "epoch": 0.17777777777777778, | |
| "eval_accuracy": 0.9507407407407408, | |
| "eval_f1": 0.9523809523809523, | |
| "eval_loss": 0.19544483721256256, | |
| "eval_precision": 0.9216909216909217, | |
| "eval_recall": 0.9851851851851852, | |
| "eval_roc_auc": 0.9924573388203017, | |
| "eval_runtime": 5.5105, | |
| "eval_samples_per_second": 489.975, | |
| "eval_steps_per_second": 15.425, | |
| "step": 280 | |
| }, | |
| { | |
| "epoch": 0.18412698412698414, | |
| "grad_norm": 0.0589861236512661, | |
| "learning_rate": 9.641677255400255e-05, | |
| "loss": 0.1201, | |
| "step": 290 | |
| }, | |
| { | |
| "epoch": 0.18412698412698414, | |
| "eval_accuracy": 0.9174074074074074, | |
| "eval_f1": 0.923394022672621, | |
| "eval_loss": 0.3497244715690613, | |
| "eval_precision": 0.8609865470852018, | |
| "eval_recall": 0.9955555555555555, | |
| "eval_roc_auc": 0.9902913580246913, | |
| "eval_runtime": 5.5119, | |
| "eval_samples_per_second": 489.85, | |
| "eval_steps_per_second": 15.421, | |
| "step": 290 | |
| }, | |
| { | |
| "epoch": 0.19047619047619047, | |
| "grad_norm": 1.337423324584961, | |
| "learning_rate": 9.628970775095299e-05, | |
| "loss": 0.1636, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 0.19047619047619047, | |
| "eval_accuracy": 0.8674074074074074, | |
| "eval_f1": 0.882699868938401, | |
| "eval_loss": 0.6298528909683228, | |
| "eval_precision": 0.7914218566392479, | |
| "eval_recall": 0.9977777777777778, | |
| "eval_roc_auc": 0.985441975308642, | |
| "eval_runtime": 5.5138, | |
| "eval_samples_per_second": 489.684, | |
| "eval_steps_per_second": 15.416, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 0.19682539682539682, | |
| "grad_norm": 5.734988212585449, | |
| "learning_rate": 9.616264294790343e-05, | |
| "loss": 0.2139, | |
| "step": 310 | |
| }, | |
| { | |
| "epoch": 0.19682539682539682, | |
| "eval_accuracy": 0.9418518518518518, | |
| "eval_f1": 0.944620811287478, | |
| "eval_loss": 0.20854391157627106, | |
| "eval_precision": 0.9016835016835016, | |
| "eval_recall": 0.9918518518518519, | |
| "eval_roc_auc": 0.9917333333333334, | |
| "eval_runtime": 5.5127, | |
| "eval_samples_per_second": 489.776, | |
| "eval_steps_per_second": 15.419, | |
| "step": 310 | |
| }, | |
| { | |
| "epoch": 0.20317460317460317, | |
| "grad_norm": 0.2367023378610611, | |
| "learning_rate": 9.603557814485387e-05, | |
| "loss": 0.1894, | |
| "step": 320 | |
| }, | |
| { | |
| "epoch": 0.20317460317460317, | |
| "eval_accuracy": 0.9562962962962963, | |
| "eval_f1": 0.9572463768115942, | |
| "eval_loss": 0.1395142674446106, | |
| "eval_precision": 0.9368794326241134, | |
| "eval_recall": 0.9785185185185186, | |
| "eval_roc_auc": 0.9925939643347051, | |
| "eval_runtime": 5.5134, | |
| "eval_samples_per_second": 489.717, | |
| "eval_steps_per_second": 15.417, | |
| "step": 320 | |
| }, | |
| { | |
| "epoch": 0.20952380952380953, | |
| "grad_norm": 14.949374198913574, | |
| "learning_rate": 9.590851334180433e-05, | |
| "loss": 0.057, | |
| "step": 330 | |
| }, | |
| { | |
| "epoch": 0.20952380952380953, | |
| "eval_accuracy": 0.9255555555555556, | |
| "eval_f1": 0.9305219495333564, | |
| "eval_loss": 0.29976287484169006, | |
| "eval_precision": 0.8723266364225535, | |
| "eval_recall": 0.997037037037037, | |
| "eval_roc_auc": 0.9900480109739369, | |
| "eval_runtime": 5.5137, | |
| "eval_samples_per_second": 489.687, | |
| "eval_steps_per_second": 15.416, | |
| "step": 330 | |
| }, | |
| { | |
| "epoch": 0.21587301587301588, | |
| "grad_norm": 3.3133888244628906, | |
| "learning_rate": 9.578144853875477e-05, | |
| "loss": 0.2029, | |
| "step": 340 | |
| }, | |
| { | |
| "epoch": 0.21587301587301588, | |
| "eval_accuracy": 0.9251851851851852, | |
| "eval_f1": 0.9302486187845304, | |
| "eval_loss": 0.3038364350795746, | |
| "eval_precision": 0.871280724450194, | |
| "eval_recall": 0.9977777777777778, | |
| "eval_roc_auc": 0.9897953360768176, | |
| "eval_runtime": 5.5193, | |
| "eval_samples_per_second": 489.19, | |
| "eval_steps_per_second": 15.4, | |
| "step": 340 | |
| }, | |
| { | |
| "epoch": 0.2222222222222222, | |
| "grad_norm": 1.5984865427017212, | |
| "learning_rate": 9.565438373570522e-05, | |
| "loss": 0.0849, | |
| "step": 350 | |
| }, | |
| { | |
| "epoch": 0.2222222222222222, | |
| "eval_accuracy": 0.9511111111111111, | |
| "eval_f1": 0.9525521207764198, | |
| "eval_loss": 0.15116137266159058, | |
| "eval_precision": 0.9252793296089385, | |
| "eval_recall": 0.9814814814814815, | |
| "eval_roc_auc": 0.9926340192043897, | |
| "eval_runtime": 5.5231, | |
| "eval_samples_per_second": 488.853, | |
| "eval_steps_per_second": 15.39, | |
| "step": 350 | |
| }, | |
| { | |
| "epoch": 0.22857142857142856, | |
| "grad_norm": 5.849670886993408, | |
| "learning_rate": 9.552731893265566e-05, | |
| "loss": 0.2559, | |
| "step": 360 | |
| }, | |
| { | |
| "epoch": 0.22857142857142856, | |
| "eval_accuracy": 0.9392592592592592, | |
| "eval_f1": 0.9424561403508772, | |
| "eval_loss": 0.22722864151000977, | |
| "eval_precision": 0.8953333333333333, | |
| "eval_recall": 0.9948148148148148, | |
| "eval_roc_auc": 0.9912104252400549, | |
| "eval_runtime": 5.5252, | |
| "eval_samples_per_second": 488.669, | |
| "eval_steps_per_second": 15.384, | |
| "step": 360 | |
| }, | |
| { | |
| "epoch": 0.23492063492063492, | |
| "grad_norm": 0.2203754186630249, | |
| "learning_rate": 9.54002541296061e-05, | |
| "loss": 0.0809, | |
| "step": 370 | |
| }, | |
| { | |
| "epoch": 0.23492063492063492, | |
| "eval_accuracy": 0.9225925925925926, | |
| "eval_f1": 0.9279061745429459, | |
| "eval_loss": 0.29464688897132874, | |
| "eval_precision": 0.868302130406714, | |
| "eval_recall": 0.9962962962962963, | |
| "eval_roc_auc": 0.9903662551440329, | |
| "eval_runtime": 5.5169, | |
| "eval_samples_per_second": 489.409, | |
| "eval_steps_per_second": 15.407, | |
| "step": 370 | |
| }, | |
| { | |
| "epoch": 0.24126984126984127, | |
| "grad_norm": 9.942216873168945, | |
| "learning_rate": 9.527318932655654e-05, | |
| "loss": 0.193, | |
| "step": 380 | |
| }, | |
| { | |
| "epoch": 0.24126984126984127, | |
| "eval_accuracy": 0.9407407407407408, | |
| "eval_f1": 0.9436222692036645, | |
| "eval_loss": 0.20582349598407745, | |
| "eval_precision": 0.8998655913978495, | |
| "eval_recall": 0.9918518518518519, | |
| "eval_roc_auc": 0.9918285322359396, | |
| "eval_runtime": 5.5161, | |
| "eval_samples_per_second": 489.479, | |
| "eval_steps_per_second": 15.41, | |
| "step": 380 | |
| }, | |
| { | |
| "epoch": 0.24761904761904763, | |
| "grad_norm": 11.672406196594238, | |
| "learning_rate": 9.5146124523507e-05, | |
| "loss": 0.208, | |
| "step": 390 | |
| }, | |
| { | |
| "epoch": 0.24761904761904763, | |
| "eval_accuracy": 0.9296296296296296, | |
| "eval_f1": 0.9339360222531293, | |
| "eval_loss": 0.24709771573543549, | |
| "eval_precision": 0.8800786369593709, | |
| "eval_recall": 0.9948148148148148, | |
| "eval_roc_auc": 0.9910834019204389, | |
| "eval_runtime": 5.5183, | |
| "eval_samples_per_second": 489.282, | |
| "eval_steps_per_second": 15.403, | |
| "step": 390 | |
| }, | |
| { | |
| "epoch": 0.25396825396825395, | |
| "grad_norm": 0.7513141632080078, | |
| "learning_rate": 9.501905972045744e-05, | |
| "loss": 0.141, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 0.25396825396825395, | |
| "eval_accuracy": 0.9248148148148149, | |
| "eval_f1": 0.9298306256481161, | |
| "eval_loss": 0.2548695504665375, | |
| "eval_precision": 0.8716785482825664, | |
| "eval_recall": 0.9962962962962963, | |
| "eval_roc_auc": 0.9910268861454047, | |
| "eval_runtime": 5.5134, | |
| "eval_samples_per_second": 489.718, | |
| "eval_steps_per_second": 15.417, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 0.26031746031746034, | |
| "grad_norm": 0.11584247648715973, | |
| "learning_rate": 9.489199491740788e-05, | |
| "loss": 0.067, | |
| "step": 410 | |
| }, | |
| { | |
| "epoch": 0.26031746031746034, | |
| "eval_accuracy": 0.9403703703703704, | |
| "eval_f1": 0.9435285864608909, | |
| "eval_loss": 0.20395933091640472, | |
| "eval_precision": 0.8960692871419054, | |
| "eval_recall": 0.9962962962962963, | |
| "eval_roc_auc": 0.9919632373113855, | |
| "eval_runtime": 5.5068, | |
| "eval_samples_per_second": 490.299, | |
| "eval_steps_per_second": 15.435, | |
| "step": 410 | |
| }, | |
| { | |
| "epoch": 0.26666666666666666, | |
| "grad_norm": 5.374762058258057, | |
| "learning_rate": 9.476493011435832e-05, | |
| "loss": 0.0581, | |
| "step": 420 | |
| }, | |
| { | |
| "epoch": 0.26666666666666666, | |
| "eval_accuracy": 0.9362962962962963, | |
| "eval_f1": 0.9399021663172606, | |
| "eval_loss": 0.21634648740291595, | |
| "eval_precision": 0.8895502645502645, | |
| "eval_recall": 0.9962962962962963, | |
| "eval_roc_auc": 0.9913909465020577, | |
| "eval_runtime": 5.5127, | |
| "eval_samples_per_second": 489.778, | |
| "eval_steps_per_second": 15.419, | |
| "step": 420 | |
| }, | |
| { | |
| "epoch": 0.273015873015873, | |
| "grad_norm": 0.1900794953107834, | |
| "learning_rate": 9.463786531130877e-05, | |
| "loss": 0.0425, | |
| "step": 430 | |
| }, | |
| { | |
| "epoch": 0.273015873015873, | |
| "eval_accuracy": 0.9018518518518519, | |
| "eval_f1": 0.9104427171341669, | |
| "eval_loss": 0.3560587167739868, | |
| "eval_precision": 0.8371659415786202, | |
| "eval_recall": 0.9977777777777778, | |
| "eval_roc_auc": 0.9883901234567901, | |
| "eval_runtime": 5.5144, | |
| "eval_samples_per_second": 489.628, | |
| "eval_steps_per_second": 15.414, | |
| "step": 430 | |
| }, | |
| { | |
| "epoch": 0.27936507936507937, | |
| "grad_norm": 0.9057045578956604, | |
| "learning_rate": 9.451080050825921e-05, | |
| "loss": 0.0736, | |
| "step": 440 | |
| }, | |
| { | |
| "epoch": 0.27936507936507937, | |
| "eval_accuracy": 0.8792592592592593, | |
| "eval_f1": 0.8921244209133025, | |
| "eval_loss": 0.4899263083934784, | |
| "eval_precision": 0.80622009569378, | |
| "eval_recall": 0.9985185185185185, | |
| "eval_roc_auc": 0.9859388203017831, | |
| "eval_runtime": 5.5176, | |
| "eval_samples_per_second": 489.34, | |
| "eval_steps_per_second": 15.405, | |
| "step": 440 | |
| }, | |
| { | |
| "epoch": 0.2857142857142857, | |
| "grad_norm": 12.068155288696289, | |
| "learning_rate": 9.438373570520967e-05, | |
| "loss": 0.0788, | |
| "step": 450 | |
| }, | |
| { | |
| "epoch": 0.2857142857142857, | |
| "eval_accuracy": 0.9311111111111111, | |
| "eval_f1": 0.935326842837274, | |
| "eval_loss": 0.27715030312538147, | |
| "eval_precision": 0.8813892529488859, | |
| "eval_recall": 0.9962962962962963, | |
| "eval_roc_auc": 0.990839231824417, | |
| "eval_runtime": 5.5146, | |
| "eval_samples_per_second": 489.612, | |
| "eval_steps_per_second": 15.414, | |
| "step": 450 | |
| }, | |
| { | |
| "epoch": 0.2920634920634921, | |
| "grad_norm": 0.20492731034755707, | |
| "learning_rate": 9.425667090216011e-05, | |
| "loss": 0.1801, | |
| "step": 460 | |
| }, | |
| { | |
| "epoch": 0.2920634920634921, | |
| "eval_accuracy": 0.924074074074074, | |
| "eval_f1": 0.9292371418709009, | |
| "eval_loss": 0.32135429978370667, | |
| "eval_precision": 0.870071105365223, | |
| "eval_recall": 0.997037037037037, | |
| "eval_roc_auc": 0.9897657064471879, | |
| "eval_runtime": 5.5135, | |
| "eval_samples_per_second": 489.707, | |
| "eval_steps_per_second": 15.417, | |
| "step": 460 | |
| }, | |
| { | |
| "epoch": 0.2984126984126984, | |
| "grad_norm": 0.016238894313573837, | |
| "learning_rate": 9.412960609911055e-05, | |
| "loss": 0.0886, | |
| "step": 470 | |
| }, | |
| { | |
| "epoch": 0.2984126984126984, | |
| "eval_accuracy": 0.9348148148148148, | |
| "eval_f1": 0.9385045422781272, | |
| "eval_loss": 0.26370832324028015, | |
| "eval_precision": 0.8882275132275133, | |
| "eval_recall": 0.9948148148148148, | |
| "eval_roc_auc": 0.9905368998628258, | |
| "eval_runtime": 5.5161, | |
| "eval_samples_per_second": 489.473, | |
| "eval_steps_per_second": 15.409, | |
| "step": 470 | |
| }, | |
| { | |
| "epoch": 0.3047619047619048, | |
| "grad_norm": 0.18422342836856842, | |
| "learning_rate": 9.400254129606099e-05, | |
| "loss": 0.0303, | |
| "step": 480 | |
| }, | |
| { | |
| "epoch": 0.3047619047619048, | |
| "eval_accuracy": 0.8840740740740741, | |
| "eval_f1": 0.8959095443964084, | |
| "eval_loss": 0.4938906133174896, | |
| "eval_precision": 0.8129149064574532, | |
| "eval_recall": 0.9977777777777778, | |
| "eval_roc_auc": 0.9840238683127571, | |
| "eval_runtime": 5.5213, | |
| "eval_samples_per_second": 489.015, | |
| "eval_steps_per_second": 15.395, | |
| "step": 480 | |
| }, | |
| { | |
| "epoch": 0.3111111111111111, | |
| "grad_norm": 0.018785802647471428, | |
| "learning_rate": 9.387547649301143e-05, | |
| "loss": 0.0849, | |
| "step": 490 | |
| }, | |
| { | |
| "epoch": 0.3111111111111111, | |
| "eval_accuracy": 0.914074074074074, | |
| "eval_f1": 0.920656634746922, | |
| "eval_loss": 0.3513197600841522, | |
| "eval_precision": 0.855146124523507, | |
| "eval_recall": 0.997037037037037, | |
| "eval_roc_auc": 0.9879089163237311, | |
| "eval_runtime": 5.5492, | |
| "eval_samples_per_second": 486.557, | |
| "eval_steps_per_second": 15.318, | |
| "step": 490 | |
| }, | |
| { | |
| "epoch": 0.31746031746031744, | |
| "grad_norm": 17.461837768554688, | |
| "learning_rate": 9.374841168996189e-05, | |
| "loss": 0.2025, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 0.31746031746031744, | |
| "eval_accuracy": 0.9414814814814815, | |
| "eval_f1": 0.9443661971830986, | |
| "eval_loss": 0.23329515755176544, | |
| "eval_precision": 0.9, | |
| "eval_recall": 0.9933333333333333, | |
| "eval_roc_auc": 0.990923182441701, | |
| "eval_runtime": 5.522, | |
| "eval_samples_per_second": 488.954, | |
| "eval_steps_per_second": 15.393, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 0.3238095238095238, | |
| "grad_norm": 0.4385194182395935, | |
| "learning_rate": 9.362134688691233e-05, | |
| "loss": 0.4251, | |
| "step": 510 | |
| }, | |
| { | |
| "epoch": 0.3238095238095238, | |
| "eval_accuracy": 0.952962962962963, | |
| "eval_f1": 0.9547559672247952, | |
| "eval_loss": 0.17835260927677155, | |
| "eval_precision": 0.9196980096087852, | |
| "eval_recall": 0.9925925925925926, | |
| "eval_roc_auc": 0.9925997256515775, | |
| "eval_runtime": 5.5197, | |
| "eval_samples_per_second": 489.161, | |
| "eval_steps_per_second": 15.4, | |
| "step": 510 | |
| }, | |
| { | |
| "epoch": 0.33015873015873015, | |
| "grad_norm": 2.7863709926605225, | |
| "learning_rate": 9.349428208386277e-05, | |
| "loss": 0.1384, | |
| "step": 520 | |
| }, | |
| { | |
| "epoch": 0.33015873015873015, | |
| "eval_accuracy": 0.9525925925925925, | |
| "eval_f1": 0.9543834640057021, | |
| "eval_loss": 0.17517130076885223, | |
| "eval_precision": 0.9196428571428571, | |
| "eval_recall": 0.9918518518518519, | |
| "eval_roc_auc": 0.9930340192043895, | |
| "eval_runtime": 5.5216, | |
| "eval_samples_per_second": 488.99, | |
| "eval_steps_per_second": 15.394, | |
| "step": 520 | |
| }, | |
| { | |
| "epoch": 0.33650793650793653, | |
| "grad_norm": 0.09477631747722626, | |
| "learning_rate": 9.336721728081323e-05, | |
| "loss": 0.0516, | |
| "step": 530 | |
| }, | |
| { | |
| "epoch": 0.33650793650793653, | |
| "eval_accuracy": 0.94, | |
| "eval_f1": 0.9430379746835443, | |
| "eval_loss": 0.2342747449874878, | |
| "eval_precision": 0.8975903614457831, | |
| "eval_recall": 0.9933333333333333, | |
| "eval_roc_auc": 0.9920493827160494, | |
| "eval_runtime": 5.5193, | |
| "eval_samples_per_second": 489.195, | |
| "eval_steps_per_second": 15.401, | |
| "step": 530 | |
| }, | |
| { | |
| "epoch": 0.34285714285714286, | |
| "grad_norm": 0.060261718928813934, | |
| "learning_rate": 9.324015247776366e-05, | |
| "loss": 0.0048, | |
| "step": 540 | |
| }, | |
| { | |
| "epoch": 0.34285714285714286, | |
| "eval_accuracy": 0.927037037037037, | |
| "eval_f1": 0.9316684009712105, | |
| "eval_loss": 0.2969974875450134, | |
| "eval_precision": 0.8760600130463144, | |
| "eval_recall": 0.9948148148148148, | |
| "eval_roc_auc": 0.991082853223594, | |
| "eval_runtime": 5.5259, | |
| "eval_samples_per_second": 488.608, | |
| "eval_steps_per_second": 15.382, | |
| "step": 540 | |
| }, | |
| { | |
| "epoch": 0.3492063492063492, | |
| "grad_norm": 0.1148306354880333, | |
| "learning_rate": 9.31130876747141e-05, | |
| "loss": 0.0832, | |
| "step": 550 | |
| }, | |
| { | |
| "epoch": 0.3492063492063492, | |
| "eval_accuracy": 0.96, | |
| "eval_f1": 0.9609544468546638, | |
| "eval_loss": 0.1580500602722168, | |
| "eval_precision": 0.9385593220338984, | |
| "eval_recall": 0.9844444444444445, | |
| "eval_roc_auc": 0.9940183813443072, | |
| "eval_runtime": 5.5217, | |
| "eval_samples_per_second": 488.978, | |
| "eval_steps_per_second": 15.394, | |
| "step": 550 | |
| }, | |
| { | |
| "epoch": 0.35555555555555557, | |
| "grad_norm": 0.034114107489585876, | |
| "learning_rate": 9.298602287166456e-05, | |
| "loss": 0.1202, | |
| "step": 560 | |
| }, | |
| { | |
| "epoch": 0.35555555555555557, | |
| "eval_accuracy": 0.9485185185185185, | |
| "eval_f1": 0.9507266926621766, | |
| "eval_loss": 0.23128464818000793, | |
| "eval_precision": 0.91162474507138, | |
| "eval_recall": 0.9933333333333333, | |
| "eval_roc_auc": 0.9926241426611797, | |
| "eval_runtime": 5.5201, | |
| "eval_samples_per_second": 489.125, | |
| "eval_steps_per_second": 15.398, | |
| "step": 560 | |
| }, | |
| { | |
| "epoch": 0.3619047619047619, | |
| "grad_norm": 0.02656545117497444, | |
| "learning_rate": 9.2858958068615e-05, | |
| "loss": 0.1321, | |
| "step": 570 | |
| }, | |
| { | |
| "epoch": 0.3619047619047619, | |
| "eval_accuracy": 0.9514814814814815, | |
| "eval_f1": 0.9534635879218473, | |
| "eval_loss": 0.22296707332134247, | |
| "eval_precision": 0.9160409556313993, | |
| "eval_recall": 0.9940740740740741, | |
| "eval_roc_auc": 0.9931102880658437, | |
| "eval_runtime": 5.5181, | |
| "eval_samples_per_second": 489.3, | |
| "eval_steps_per_second": 15.404, | |
| "step": 570 | |
| }, | |
| { | |
| "epoch": 0.3682539682539683, | |
| "grad_norm": 0.03909531608223915, | |
| "learning_rate": 9.273189326556544e-05, | |
| "loss": 0.0552, | |
| "step": 580 | |
| }, | |
| { | |
| "epoch": 0.3682539682539683, | |
| "eval_accuracy": 0.9092592592592592, | |
| "eval_f1": 0.916695001700102, | |
| "eval_loss": 0.4478496313095093, | |
| "eval_precision": 0.8472658705216844, | |
| "eval_recall": 0.9985185185185185, | |
| "eval_roc_auc": 0.9875185185185186, | |
| "eval_runtime": 5.5291, | |
| "eval_samples_per_second": 488.323, | |
| "eval_steps_per_second": 15.373, | |
| "step": 580 | |
| }, | |
| { | |
| "epoch": 0.3746031746031746, | |
| "grad_norm": 0.01843447797000408, | |
| "learning_rate": 9.26048284625159e-05, | |
| "loss": 0.1449, | |
| "step": 590 | |
| }, | |
| { | |
| "epoch": 0.3746031746031746, | |
| "eval_accuracy": 0.9014814814814814, | |
| "eval_f1": 0.9101958136394328, | |
| "eval_loss": 0.4929225444793701, | |
| "eval_precision": 0.8362282878411911, | |
| "eval_recall": 0.9985185185185185, | |
| "eval_roc_auc": 0.985960768175583, | |
| "eval_runtime": 5.5503, | |
| "eval_samples_per_second": 486.461, | |
| "eval_steps_per_second": 15.315, | |
| "step": 590 | |
| }, | |
| { | |
| "epoch": 0.38095238095238093, | |
| "grad_norm": 0.1456720530986786, | |
| "learning_rate": 9.249047013977129e-05, | |
| "loss": 0.068, | |
| "step": 600 | |
| }, | |
| { | |
| "epoch": 0.38095238095238093, | |
| "eval_accuracy": 0.9366666666666666, | |
| "eval_f1": 0.9401888772298006, | |
| "eval_loss": 0.29736340045928955, | |
| "eval_precision": 0.8906560636182903, | |
| "eval_recall": 0.9955555555555555, | |
| "eval_roc_auc": 0.9906285322359396, | |
| "eval_runtime": 5.5246, | |
| "eval_samples_per_second": 488.726, | |
| "eval_steps_per_second": 15.386, | |
| "step": 600 | |
| }, | |
| { | |
| "epoch": 0.3873015873015873, | |
| "grad_norm": 0.00903715193271637, | |
| "learning_rate": 9.236340533672173e-05, | |
| "loss": 0.0065, | |
| "step": 610 | |
| }, | |
| { | |
| "epoch": 0.3873015873015873, | |
| "eval_accuracy": 0.9588888888888889, | |
| "eval_f1": 0.9601436265709156, | |
| "eval_loss": 0.19618448615074158, | |
| "eval_precision": 0.9317073170731708, | |
| "eval_recall": 0.9903703703703703, | |
| "eval_roc_auc": 0.9935338820301782, | |
| "eval_runtime": 5.5182, | |
| "eval_samples_per_second": 489.287, | |
| "eval_steps_per_second": 15.403, | |
| "step": 610 | |
| }, | |
| { | |
| "epoch": 0.39365079365079364, | |
| "grad_norm": 0.04093470424413681, | |
| "learning_rate": 9.223634053367217e-05, | |
| "loss": 0.131, | |
| "step": 620 | |
| }, | |
| { | |
| "epoch": 0.39365079365079364, | |
| "eval_accuracy": 0.9251851851851852, | |
| "eval_f1": 0.9302486187845304, | |
| "eval_loss": 0.3867323100566864, | |
| "eval_precision": 0.871280724450194, | |
| "eval_recall": 0.9977777777777778, | |
| "eval_roc_auc": 0.9864683127572016, | |
| "eval_runtime": 5.5187, | |
| "eval_samples_per_second": 489.248, | |
| "eval_steps_per_second": 15.402, | |
| "step": 620 | |
| }, | |
| { | |
| "epoch": 0.4, | |
| "grad_norm": 13.493297576904297, | |
| "learning_rate": 9.210927573062263e-05, | |
| "loss": 0.2599, | |
| "step": 630 | |
| }, | |
| { | |
| "epoch": 0.4, | |
| "eval_accuracy": 0.8918518518518519, | |
| "eval_f1": 0.9022757697456493, | |
| "eval_loss": 0.5704190731048584, | |
| "eval_precision": 0.8229548229548229, | |
| "eval_recall": 0.9985185185185185, | |
| "eval_roc_auc": 0.981446364883402, | |
| "eval_runtime": 5.5214, | |
| "eval_samples_per_second": 489.005, | |
| "eval_steps_per_second": 15.395, | |
| "step": 630 | |
| }, | |
| { | |
| "epoch": 0.40634920634920635, | |
| "grad_norm": 0.01696428842842579, | |
| "learning_rate": 9.198221092757307e-05, | |
| "loss": 0.0087, | |
| "step": 640 | |
| }, | |
| { | |
| "epoch": 0.40634920634920635, | |
| "eval_accuracy": 0.9277777777777778, | |
| "eval_f1": 0.9324090121317158, | |
| "eval_loss": 0.3256017863750458, | |
| "eval_precision": 0.8762214983713354, | |
| "eval_recall": 0.9962962962962963, | |
| "eval_roc_auc": 0.9897610425240055, | |
| "eval_runtime": 5.5213, | |
| "eval_samples_per_second": 489.017, | |
| "eval_steps_per_second": 15.395, | |
| "step": 640 | |
| }, | |
| { | |
| "epoch": 0.4126984126984127, | |
| "grad_norm": 0.01224907673895359, | |
| "learning_rate": 9.185514612452351e-05, | |
| "loss": 0.0602, | |
| "step": 650 | |
| }, | |
| { | |
| "epoch": 0.4126984126984127, | |
| "eval_accuracy": 0.9207407407407407, | |
| "eval_f1": 0.9263592567102547, | |
| "eval_loss": 0.3757924735546112, | |
| "eval_precision": 0.8650385604113111, | |
| "eval_recall": 0.997037037037037, | |
| "eval_roc_auc": 0.9885146776406035, | |
| "eval_runtime": 5.522, | |
| "eval_samples_per_second": 488.951, | |
| "eval_steps_per_second": 15.393, | |
| "step": 650 | |
| }, | |
| { | |
| "epoch": 0.41904761904761906, | |
| "grad_norm": 0.01693762093782425, | |
| "learning_rate": 9.172808132147396e-05, | |
| "loss": 0.4184, | |
| "step": 660 | |
| }, | |
| { | |
| "epoch": 0.41904761904761906, | |
| "eval_accuracy": 0.9548148148148148, | |
| "eval_f1": 0.9564285714285714, | |
| "eval_loss": 0.1783735305070877, | |
| "eval_precision": 0.923448275862069, | |
| "eval_recall": 0.9918518518518519, | |
| "eval_roc_auc": 0.9926477366255145, | |
| "eval_runtime": 5.5199, | |
| "eval_samples_per_second": 489.135, | |
| "eval_steps_per_second": 15.399, | |
| "step": 660 | |
| }, | |
| { | |
| "epoch": 0.4253968253968254, | |
| "grad_norm": 0.3128555119037628, | |
| "learning_rate": 9.16010165184244e-05, | |
| "loss": 0.0977, | |
| "step": 670 | |
| }, | |
| { | |
| "epoch": 0.4253968253968254, | |
| "eval_accuracy": 0.9492592592592592, | |
| "eval_f1": 0.9513667021654242, | |
| "eval_loss": 0.18898966908454895, | |
| "eval_precision": 0.9134287661895024, | |
| "eval_recall": 0.9925925925925926, | |
| "eval_roc_auc": 0.9929882030178325, | |
| "eval_runtime": 5.513, | |
| "eval_samples_per_second": 489.751, | |
| "eval_steps_per_second": 15.418, | |
| "step": 670 | |
| }, | |
| { | |
| "epoch": 0.43174603174603177, | |
| "grad_norm": 7.7761383056640625, | |
| "learning_rate": 9.147395171537485e-05, | |
| "loss": 0.1996, | |
| "step": 680 | |
| }, | |
| { | |
| "epoch": 0.43174603174603177, | |
| "eval_accuracy": 0.9096296296296297, | |
| "eval_f1": 0.9168937329700273, | |
| "eval_loss": 0.3682536780834198, | |
| "eval_precision": 0.8486759142496847, | |
| "eval_recall": 0.997037037037037, | |
| "eval_roc_auc": 0.9902880658436214, | |
| "eval_runtime": 5.5189, | |
| "eval_samples_per_second": 489.232, | |
| "eval_steps_per_second": 15.402, | |
| "step": 680 | |
| }, | |
| { | |
| "epoch": 0.4380952380952381, | |
| "grad_norm": 0.04118531197309494, | |
| "learning_rate": 9.13468869123253e-05, | |
| "loss": 0.0329, | |
| "step": 690 | |
| }, | |
| { | |
| "epoch": 0.4380952380952381, | |
| "eval_accuracy": 0.9048148148148148, | |
| "eval_f1": 0.9128518141742964, | |
| "eval_loss": 0.38119447231292725, | |
| "eval_precision": 0.841776110068793, | |
| "eval_recall": 0.997037037037037, | |
| "eval_roc_auc": 0.9900367626886146, | |
| "eval_runtime": 5.5111, | |
| "eval_samples_per_second": 489.917, | |
| "eval_steps_per_second": 15.423, | |
| "step": 690 | |
| }, | |
| { | |
| "epoch": 0.4444444444444444, | |
| "grad_norm": 5.560464382171631, | |
| "learning_rate": 9.121982210927574e-05, | |
| "loss": 0.1425, | |
| "step": 700 | |
| }, | |
| { | |
| "epoch": 0.4444444444444444, | |
| "eval_accuracy": 0.9511111111111111, | |
| "eval_f1": 0.9529579472558802, | |
| "eval_loss": 0.177493155002594, | |
| "eval_precision": 0.9182692307692307, | |
| "eval_recall": 0.9903703703703703, | |
| "eval_roc_auc": 0.9938277091906722, | |
| "eval_runtime": 5.5066, | |
| "eval_samples_per_second": 490.322, | |
| "eval_steps_per_second": 15.436, | |
| "step": 700 | |
| }, | |
| { | |
| "epoch": 0.4507936507936508, | |
| "grad_norm": 0.03769376501441002, | |
| "learning_rate": 9.109275730622618e-05, | |
| "loss": 0.1651, | |
| "step": 710 | |
| }, | |
| { | |
| "epoch": 0.4507936507936508, | |
| "eval_accuracy": 0.9448148148148148, | |
| "eval_f1": 0.9474055771267208, | |
| "eval_loss": 0.20647479593753815, | |
| "eval_precision": 0.9049224544841538, | |
| "eval_recall": 0.9940740740740741, | |
| "eval_roc_auc": 0.9933665294924554, | |
| "eval_runtime": 5.5143, | |
| "eval_samples_per_second": 489.634, | |
| "eval_steps_per_second": 15.414, | |
| "step": 710 | |
| }, | |
| { | |
| "epoch": 0.45714285714285713, | |
| "grad_norm": 10.711636543273926, | |
| "learning_rate": 9.096569250317662e-05, | |
| "loss": 0.1278, | |
| "step": 720 | |
| }, | |
| { | |
| "epoch": 0.45714285714285713, | |
| "eval_accuracy": 0.9359259259259259, | |
| "eval_f1": 0.9395738735592036, | |
| "eval_loss": 0.25338342785835266, | |
| "eval_precision": 0.8889623265036352, | |
| "eval_recall": 0.9962962962962963, | |
| "eval_roc_auc": 0.9929604938271603, | |
| "eval_runtime": 5.5162, | |
| "eval_samples_per_second": 489.471, | |
| "eval_steps_per_second": 15.409, | |
| "step": 720 | |
| }, | |
| { | |
| "epoch": 0.4634920634920635, | |
| "grad_norm": 0.17392298579216003, | |
| "learning_rate": 9.083862770012706e-05, | |
| "loss": 0.0979, | |
| "step": 730 | |
| }, | |
| { | |
| "epoch": 0.4634920634920635, | |
| "eval_accuracy": 0.9440740740740741, | |
| "eval_f1": 0.9468497008095741, | |
| "eval_loss": 0.22556233406066895, | |
| "eval_precision": 0.9020791415157612, | |
| "eval_recall": 0.9962962962962963, | |
| "eval_roc_auc": 0.9937440329218106, | |
| "eval_runtime": 5.5189, | |
| "eval_samples_per_second": 489.224, | |
| "eval_steps_per_second": 15.401, | |
| "step": 730 | |
| }, | |
| { | |
| "epoch": 0.46984126984126984, | |
| "grad_norm": 3.3036723136901855, | |
| "learning_rate": 9.071156289707752e-05, | |
| "loss": 0.0228, | |
| "step": 740 | |
| }, | |
| { | |
| "epoch": 0.46984126984126984, | |
| "eval_accuracy": 0.9251851851851852, | |
| "eval_f1": 0.9302004146510021, | |
| "eval_loss": 0.317281037569046, | |
| "eval_precision": 0.8717616580310881, | |
| "eval_recall": 0.997037037037037, | |
| "eval_roc_auc": 0.9925075445816187, | |
| "eval_runtime": 5.5192, | |
| "eval_samples_per_second": 489.2, | |
| "eval_steps_per_second": 15.401, | |
| "step": 740 | |
| }, | |
| { | |
| "epoch": 0.47619047619047616, | |
| "grad_norm": 2.8324198722839355, | |
| "learning_rate": 9.058449809402796e-05, | |
| "loss": 0.1754, | |
| "step": 750 | |
| }, | |
| { | |
| "epoch": 0.47619047619047616, | |
| "eval_accuracy": 0.9581481481481482, | |
| "eval_f1": 0.9594254937163376, | |
| "eval_loss": 0.1706221103668213, | |
| "eval_precision": 0.9310104529616725, | |
| "eval_recall": 0.9896296296296296, | |
| "eval_roc_auc": 0.9952694101508917, | |
| "eval_runtime": 5.5194, | |
| "eval_samples_per_second": 489.187, | |
| "eval_steps_per_second": 15.4, | |
| "step": 750 | |
| }, | |
| { | |
| "epoch": 0.48253968253968255, | |
| "grad_norm": 0.046114906668663025, | |
| "learning_rate": 9.04574332909784e-05, | |
| "loss": 0.0727, | |
| "step": 760 | |
| }, | |
| { | |
| "epoch": 0.48253968253968255, | |
| "eval_accuracy": 0.9088888888888889, | |
| "eval_f1": 0.9163265306122449, | |
| "eval_loss": 0.42058730125427246, | |
| "eval_precision": 0.8471698113207548, | |
| "eval_recall": 0.9977777777777778, | |
| "eval_roc_auc": 0.9914013717421125, | |
| "eval_runtime": 5.5127, | |
| "eval_samples_per_second": 489.781, | |
| "eval_steps_per_second": 15.419, | |
| "step": 760 | |
| }, | |
| { | |
| "epoch": 0.4888888888888889, | |
| "grad_norm": 0.3374621272087097, | |
| "learning_rate": 9.033036848792885e-05, | |
| "loss": 0.1076, | |
| "step": 770 | |
| }, | |
| { | |
| "epoch": 0.4888888888888889, | |
| "eval_accuracy": 0.9407407407407408, | |
| "eval_f1": 0.9438596491228071, | |
| "eval_loss": 0.2562646269798279, | |
| "eval_precision": 0.8966666666666666, | |
| "eval_recall": 0.9962962962962963, | |
| "eval_roc_auc": 0.993437585733882, | |
| "eval_runtime": 5.5242, | |
| "eval_samples_per_second": 488.761, | |
| "eval_steps_per_second": 15.387, | |
| "step": 770 | |
| }, | |
| { | |
| "epoch": 0.49523809523809526, | |
| "grad_norm": 0.027243219316005707, | |
| "learning_rate": 9.020330368487929e-05, | |
| "loss": 0.0842, | |
| "step": 780 | |
| }, | |
| { | |
| "epoch": 0.49523809523809526, | |
| "eval_accuracy": 0.9633333333333334, | |
| "eval_f1": 0.9640130861504908, | |
| "eval_loss": 0.14165127277374268, | |
| "eval_precision": 0.9464668094218416, | |
| "eval_recall": 0.9822222222222222, | |
| "eval_roc_auc": 0.9951972565157751, | |
| "eval_runtime": 5.5142, | |
| "eval_samples_per_second": 489.648, | |
| "eval_steps_per_second": 15.415, | |
| "step": 780 | |
| }, | |
| { | |
| "epoch": 0.5015873015873016, | |
| "grad_norm": 1.7387934923171997, | |
| "learning_rate": 9.007623888182973e-05, | |
| "loss": 0.134, | |
| "step": 790 | |
| }, | |
| { | |
| "epoch": 0.5015873015873016, | |
| "eval_accuracy": 0.9577777777777777, | |
| "eval_f1": 0.958963282937365, | |
| "eval_loss": 0.1754920780658722, | |
| "eval_precision": 0.9327731092436975, | |
| "eval_recall": 0.9866666666666667, | |
| "eval_roc_auc": 0.994798353909465, | |
| "eval_runtime": 5.5138, | |
| "eval_samples_per_second": 489.682, | |
| "eval_steps_per_second": 15.416, | |
| "step": 790 | |
| } | |
| ], | |
| "logging_steps": 10, | |
| "max_steps": 7875, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 5, | |
| "save_steps": 10, | |
| "stateful_callbacks": { | |
| "EarlyStoppingCallback": { | |
| "args": { | |
| "early_stopping_patience": 50, | |
| "early_stopping_threshold": 0.0 | |
| }, | |
| "attributes": { | |
| "early_stopping_patience_counter": 47 | |
| } | |
| }, | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": false | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 0.0, | |
| "train_batch_size": 8, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |