| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 1.0, | |
| "global_step": 2188, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0, | |
| "learning_rate": 4.997714808043876e-05, | |
| "loss": 0.701, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.02, | |
| "learning_rate": 4.9017367458866546e-05, | |
| "loss": 0.5623, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 0.02, | |
| "eval_accuracy": 0.9112, | |
| "eval_f1": 0.9178386380458919, | |
| "eval_loss": 0.3157382309436798, | |
| "eval_precision": 0.8539944903581267, | |
| "eval_recall": 0.992, | |
| "eval_runtime": 31.9687, | |
| "eval_samples_per_second": 117.302, | |
| "eval_steps_per_second": 14.671, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 0.04, | |
| "learning_rate": 4.8034734917733096e-05, | |
| "loss": 0.4041, | |
| "step": 86 | |
| }, | |
| { | |
| "epoch": 0.04, | |
| "eval_accuracy": 0.9682666666666667, | |
| "eval_f1": 0.9688563203349909, | |
| "eval_loss": 0.10907813906669617, | |
| "eval_precision": 0.9511819116135662, | |
| "eval_recall": 0.9872, | |
| "eval_runtime": 31.8725, | |
| "eval_samples_per_second": 117.656, | |
| "eval_steps_per_second": 14.715, | |
| "step": 86 | |
| }, | |
| { | |
| "epoch": 0.06, | |
| "learning_rate": 4.705210237659964e-05, | |
| "loss": 0.0811, | |
| "step": 129 | |
| }, | |
| { | |
| "epoch": 0.06, | |
| "eval_accuracy": 0.9829333333333333, | |
| "eval_f1": 0.9830777366472766, | |
| "eval_loss": 0.11184453219175339, | |
| "eval_precision": 0.9748295752490823, | |
| "eval_recall": 0.9914666666666667, | |
| "eval_runtime": 32.1826, | |
| "eval_samples_per_second": 116.523, | |
| "eval_steps_per_second": 14.573, | |
| "step": 129 | |
| }, | |
| { | |
| "epoch": 0.08, | |
| "learning_rate": 4.606946983546618e-05, | |
| "loss": 0.1455, | |
| "step": 172 | |
| }, | |
| { | |
| "epoch": 0.08, | |
| "eval_accuracy": 0.9826666666666667, | |
| "eval_f1": 0.9828360179561658, | |
| "eval_loss": 0.08915094286203384, | |
| "eval_precision": 0.9733263598326359, | |
| "eval_recall": 0.9925333333333334, | |
| "eval_runtime": 31.7933, | |
| "eval_samples_per_second": 117.949, | |
| "eval_steps_per_second": 14.752, | |
| "step": 172 | |
| }, | |
| { | |
| "epoch": 0.1, | |
| "learning_rate": 4.5086837294332726e-05, | |
| "loss": 0.1159, | |
| "step": 215 | |
| }, | |
| { | |
| "epoch": 0.1, | |
| "eval_accuracy": 0.9722666666666666, | |
| "eval_f1": 0.9729448491155047, | |
| "eval_loss": 0.15372106432914734, | |
| "eval_precision": 0.9497206703910615, | |
| "eval_recall": 0.9973333333333333, | |
| "eval_runtime": 31.823, | |
| "eval_samples_per_second": 117.839, | |
| "eval_steps_per_second": 14.738, | |
| "step": 215 | |
| }, | |
| { | |
| "epoch": 0.12, | |
| "learning_rate": 4.410420475319927e-05, | |
| "loss": 0.1902, | |
| "step": 258 | |
| }, | |
| { | |
| "epoch": 0.12, | |
| "eval_accuracy": 0.9765333333333334, | |
| "eval_f1": 0.9769874476987447, | |
| "eval_loss": 0.11824183911085129, | |
| "eval_precision": 0.9584402257567983, | |
| "eval_recall": 0.9962666666666666, | |
| "eval_runtime": 31.879, | |
| "eval_samples_per_second": 117.632, | |
| "eval_steps_per_second": 14.712, | |
| "step": 258 | |
| }, | |
| { | |
| "epoch": 0.14, | |
| "learning_rate": 4.312157221206581e-05, | |
| "loss": 0.0948, | |
| "step": 301 | |
| }, | |
| { | |
| "epoch": 0.14, | |
| "eval_accuracy": 0.9917333333333334, | |
| "eval_f1": 0.9917443408788282, | |
| "eval_loss": 0.04853309690952301, | |
| "eval_precision": 0.9904255319148936, | |
| "eval_recall": 0.9930666666666667, | |
| "eval_runtime": 32.1725, | |
| "eval_samples_per_second": 116.559, | |
| "eval_steps_per_second": 14.578, | |
| "step": 301 | |
| }, | |
| { | |
| "epoch": 0.16, | |
| "learning_rate": 4.213893967093236e-05, | |
| "loss": 0.0947, | |
| "step": 344 | |
| }, | |
| { | |
| "epoch": 0.16, | |
| "eval_accuracy": 0.9589333333333333, | |
| "eval_f1": 0.960431654676259, | |
| "eval_loss": 0.21628336608409882, | |
| "eval_precision": 0.9266236985622212, | |
| "eval_recall": 0.9968, | |
| "eval_runtime": 31.9931, | |
| "eval_samples_per_second": 117.213, | |
| "eval_steps_per_second": 14.659, | |
| "step": 344 | |
| }, | |
| { | |
| "epoch": 0.18, | |
| "learning_rate": 4.1156307129798905e-05, | |
| "loss": 0.1513, | |
| "step": 387 | |
| }, | |
| { | |
| "epoch": 0.18, | |
| "eval_accuracy": 0.9885333333333334, | |
| "eval_f1": 0.9884315308044122, | |
| "eval_loss": 0.056088127195835114, | |
| "eval_precision": 0.99728555917481, | |
| "eval_recall": 0.9797333333333333, | |
| "eval_runtime": 31.868, | |
| "eval_samples_per_second": 117.673, | |
| "eval_steps_per_second": 14.717, | |
| "step": 387 | |
| }, | |
| { | |
| "epoch": 0.2, | |
| "learning_rate": 4.017367458866545e-05, | |
| "loss": 0.2024, | |
| "step": 430 | |
| }, | |
| { | |
| "epoch": 0.2, | |
| "eval_accuracy": 0.9770666666666666, | |
| "eval_f1": 0.9774869109947643, | |
| "eval_loss": 0.11541605740785599, | |
| "eval_precision": 0.9598971722365038, | |
| "eval_recall": 0.9957333333333334, | |
| "eval_runtime": 31.7697, | |
| "eval_samples_per_second": 118.037, | |
| "eval_steps_per_second": 14.763, | |
| "step": 430 | |
| }, | |
| { | |
| "epoch": 0.22, | |
| "learning_rate": 3.919104204753199e-05, | |
| "loss": 0.0442, | |
| "step": 473 | |
| }, | |
| { | |
| "epoch": 0.22, | |
| "eval_accuracy": 0.9872, | |
| "eval_f1": 0.9871931696905016, | |
| "eval_loss": 0.06453149765729904, | |
| "eval_precision": 0.987720234917245, | |
| "eval_recall": 0.9866666666666667, | |
| "eval_runtime": 31.8692, | |
| "eval_samples_per_second": 117.668, | |
| "eval_steps_per_second": 14.716, | |
| "step": 473 | |
| }, | |
| { | |
| "epoch": 0.24, | |
| "learning_rate": 3.820840950639854e-05, | |
| "loss": 0.0859, | |
| "step": 516 | |
| }, | |
| { | |
| "epoch": 0.24, | |
| "eval_accuracy": 0.9792, | |
| "eval_f1": 0.9794736842105262, | |
| "eval_loss": 0.11312653124332428, | |
| "eval_precision": 0.9667532467532467, | |
| "eval_recall": 0.9925333333333334, | |
| "eval_runtime": 31.8306, | |
| "eval_samples_per_second": 117.811, | |
| "eval_steps_per_second": 14.734, | |
| "step": 516 | |
| }, | |
| { | |
| "epoch": 0.26, | |
| "learning_rate": 3.7225776965265085e-05, | |
| "loss": 0.0802, | |
| "step": 559 | |
| }, | |
| { | |
| "epoch": 0.26, | |
| "eval_accuracy": 0.9866666666666667, | |
| "eval_f1": 0.9867654843832716, | |
| "eval_loss": 0.07340351492166519, | |
| "eval_precision": 0.9795060430898581, | |
| "eval_recall": 0.9941333333333333, | |
| "eval_runtime": 31.9433, | |
| "eval_samples_per_second": 117.396, | |
| "eval_steps_per_second": 14.682, | |
| "step": 559 | |
| }, | |
| { | |
| "epoch": 0.28, | |
| "learning_rate": 3.624314442413163e-05, | |
| "loss": 0.0754, | |
| "step": 602 | |
| }, | |
| { | |
| "epoch": 0.28, | |
| "eval_accuracy": 0.9909333333333333, | |
| "eval_f1": 0.9909718534253851, | |
| "eval_loss": 0.05534309148788452, | |
| "eval_precision": 0.9867794817556849, | |
| "eval_recall": 0.9952, | |
| "eval_runtime": 31.9035, | |
| "eval_samples_per_second": 117.542, | |
| "eval_steps_per_second": 14.701, | |
| "step": 602 | |
| }, | |
| { | |
| "epoch": 0.29, | |
| "learning_rate": 3.526051188299818e-05, | |
| "loss": 0.0446, | |
| "step": 645 | |
| }, | |
| { | |
| "epoch": 0.29, | |
| "eval_accuracy": 0.9802666666666666, | |
| "eval_f1": 0.980546792849632, | |
| "eval_loss": 0.10309968888759613, | |
| "eval_precision": 0.966822187662001, | |
| "eval_recall": 0.9946666666666667, | |
| "eval_runtime": 31.8495, | |
| "eval_samples_per_second": 117.741, | |
| "eval_steps_per_second": 14.725, | |
| "step": 645 | |
| }, | |
| { | |
| "epoch": 0.31, | |
| "learning_rate": 3.4277879341864715e-05, | |
| "loss": 0.2247, | |
| "step": 688 | |
| }, | |
| { | |
| "epoch": 0.31, | |
| "eval_accuracy": 0.9837333333333333, | |
| "eval_f1": 0.9839262187088275, | |
| "eval_loss": 0.05565320700407028, | |
| "eval_precision": 0.9723958333333333, | |
| "eval_recall": 0.9957333333333334, | |
| "eval_runtime": 31.8106, | |
| "eval_samples_per_second": 117.885, | |
| "eval_steps_per_second": 14.744, | |
| "step": 688 | |
| }, | |
| { | |
| "epoch": 0.33, | |
| "learning_rate": 3.329524680073126e-05, | |
| "loss": 0.0198, | |
| "step": 731 | |
| }, | |
| { | |
| "epoch": 0.33, | |
| "eval_accuracy": 0.972, | |
| "eval_f1": 0.9726491273769211, | |
| "eval_loss": 0.19524268805980682, | |
| "eval_precision": 0.9506109979633401, | |
| "eval_recall": 0.9957333333333334, | |
| "eval_runtime": 31.8384, | |
| "eval_samples_per_second": 117.782, | |
| "eval_steps_per_second": 14.731, | |
| "step": 731 | |
| }, | |
| { | |
| "epoch": 0.35, | |
| "learning_rate": 3.231261425959781e-05, | |
| "loss": 0.144, | |
| "step": 774 | |
| }, | |
| { | |
| "epoch": 0.35, | |
| "eval_accuracy": 0.9845333333333334, | |
| "eval_f1": 0.984688489968321, | |
| "eval_loss": 0.07750081270933151, | |
| "eval_precision": 0.9749085206481966, | |
| "eval_recall": 0.9946666666666667, | |
| "eval_runtime": 31.9146, | |
| "eval_samples_per_second": 117.501, | |
| "eval_steps_per_second": 14.695, | |
| "step": 774 | |
| }, | |
| { | |
| "epoch": 0.37, | |
| "learning_rate": 3.132998171846435e-05, | |
| "loss": 0.1193, | |
| "step": 817 | |
| }, | |
| { | |
| "epoch": 0.37, | |
| "eval_accuracy": 0.988, | |
| "eval_f1": 0.9879194630872483, | |
| "eval_loss": 0.04342731088399887, | |
| "eval_precision": 0.9945945945945946, | |
| "eval_recall": 0.9813333333333333, | |
| "eval_runtime": 32.0746, | |
| "eval_samples_per_second": 116.915, | |
| "eval_steps_per_second": 14.622, | |
| "step": 817 | |
| }, | |
| { | |
| "epoch": 0.39, | |
| "learning_rate": 3.03473491773309e-05, | |
| "loss": 0.0813, | |
| "step": 860 | |
| }, | |
| { | |
| "epoch": 0.39, | |
| "eval_accuracy": 0.9773333333333334, | |
| "eval_f1": 0.9777661522364636, | |
| "eval_loss": 0.13094328343868256, | |
| "eval_precision": 0.9594455852156057, | |
| "eval_recall": 0.9968, | |
| "eval_runtime": 31.8439, | |
| "eval_samples_per_second": 117.762, | |
| "eval_steps_per_second": 14.728, | |
| "step": 860 | |
| }, | |
| { | |
| "epoch": 0.41, | |
| "learning_rate": 2.9364716636197442e-05, | |
| "loss": 0.1484, | |
| "step": 903 | |
| }, | |
| { | |
| "epoch": 0.41, | |
| "eval_accuracy": 0.9893333333333333, | |
| "eval_f1": 0.989406779661017, | |
| "eval_loss": 0.04147784784436226, | |
| "eval_precision": 0.9826407154129405, | |
| "eval_recall": 0.9962666666666666, | |
| "eval_runtime": 32.1496, | |
| "eval_samples_per_second": 116.642, | |
| "eval_steps_per_second": 14.588, | |
| "step": 903 | |
| }, | |
| { | |
| "epoch": 0.43, | |
| "learning_rate": 2.838208409506399e-05, | |
| "loss": 0.0575, | |
| "step": 946 | |
| }, | |
| { | |
| "epoch": 0.43, | |
| "eval_accuracy": 0.9936, | |
| "eval_f1": 0.9935897435897435, | |
| "eval_loss": 0.0342133492231369, | |
| "eval_precision": 0.9951845906902087, | |
| "eval_recall": 0.992, | |
| "eval_runtime": 31.8831, | |
| "eval_samples_per_second": 117.617, | |
| "eval_steps_per_second": 14.71, | |
| "step": 946 | |
| }, | |
| { | |
| "epoch": 0.45, | |
| "learning_rate": 2.739945155393053e-05, | |
| "loss": 0.0377, | |
| "step": 989 | |
| }, | |
| { | |
| "epoch": 0.45, | |
| "eval_accuracy": 0.984, | |
| "eval_f1": 0.9842022116903633, | |
| "eval_loss": 0.08944225311279297, | |
| "eval_precision": 0.9719188767550702, | |
| "eval_recall": 0.9968, | |
| "eval_runtime": 31.8105, | |
| "eval_samples_per_second": 117.886, | |
| "eval_steps_per_second": 14.744, | |
| "step": 989 | |
| }, | |
| { | |
| "epoch": 0.47, | |
| "learning_rate": 2.641681901279708e-05, | |
| "loss": 0.023, | |
| "step": 1032 | |
| }, | |
| { | |
| "epoch": 0.47, | |
| "eval_accuracy": 0.9666666666666667, | |
| "eval_f1": 0.9676752004137574, | |
| "eval_loss": 0.2229950875043869, | |
| "eval_precision": 0.9392570281124498, | |
| "eval_recall": 0.9978666666666667, | |
| "eval_runtime": 32.2928, | |
| "eval_samples_per_second": 116.125, | |
| "eval_steps_per_second": 14.523, | |
| "step": 1032 | |
| }, | |
| { | |
| "epoch": 0.49, | |
| "learning_rate": 2.5434186471663625e-05, | |
| "loss": 0.0147, | |
| "step": 1075 | |
| }, | |
| { | |
| "epoch": 0.49, | |
| "eval_accuracy": 0.9922666666666666, | |
| "eval_f1": 0.9922892847646902, | |
| "eval_loss": 0.054798923432826996, | |
| "eval_precision": 0.9893955461293743, | |
| "eval_recall": 0.9952, | |
| "eval_runtime": 31.9316, | |
| "eval_samples_per_second": 117.439, | |
| "eval_steps_per_second": 14.688, | |
| "step": 1075 | |
| }, | |
| { | |
| "epoch": 0.51, | |
| "learning_rate": 2.4451553930530165e-05, | |
| "loss": 0.0904, | |
| "step": 1118 | |
| }, | |
| { | |
| "epoch": 0.51, | |
| "eval_accuracy": 0.9946666666666667, | |
| "eval_f1": 0.9946638207043758, | |
| "eval_loss": 0.029427310451865196, | |
| "eval_precision": 0.9951948745328351, | |
| "eval_recall": 0.9941333333333333, | |
| "eval_runtime": 31.7699, | |
| "eval_samples_per_second": 118.036, | |
| "eval_steps_per_second": 14.762, | |
| "step": 1118 | |
| }, | |
| { | |
| "epoch": 0.53, | |
| "learning_rate": 2.346892138939671e-05, | |
| "loss": 0.0578, | |
| "step": 1161 | |
| }, | |
| { | |
| "epoch": 0.53, | |
| "eval_accuracy": 0.9922666666666666, | |
| "eval_f1": 0.992281075326058, | |
| "eval_loss": 0.03940477967262268, | |
| "eval_precision": 0.9904357066950054, | |
| "eval_recall": 0.9941333333333333, | |
| "eval_runtime": 31.7813, | |
| "eval_samples_per_second": 117.994, | |
| "eval_steps_per_second": 14.757, | |
| "step": 1161 | |
| }, | |
| { | |
| "epoch": 0.55, | |
| "learning_rate": 2.2486288848263255e-05, | |
| "loss": 0.0049, | |
| "step": 1204 | |
| }, | |
| { | |
| "epoch": 0.55, | |
| "eval_accuracy": 0.9837333333333333, | |
| "eval_f1": 0.9839515916863982, | |
| "eval_loss": 0.10390568524599075, | |
| "eval_precision": 0.9709241952232607, | |
| "eval_recall": 0.9973333333333333, | |
| "eval_runtime": 31.8349, | |
| "eval_samples_per_second": 117.795, | |
| "eval_steps_per_second": 14.732, | |
| "step": 1204 | |
| }, | |
| { | |
| "epoch": 0.57, | |
| "learning_rate": 2.1503656307129798e-05, | |
| "loss": 0.0008, | |
| "step": 1247 | |
| }, | |
| { | |
| "epoch": 0.57, | |
| "eval_accuracy": 0.9930666666666667, | |
| "eval_f1": 0.9930851063829788, | |
| "eval_loss": 0.04775088652968407, | |
| "eval_precision": 0.9904509283819629, | |
| "eval_recall": 0.9957333333333334, | |
| "eval_runtime": 31.8926, | |
| "eval_samples_per_second": 117.582, | |
| "eval_steps_per_second": 14.706, | |
| "step": 1247 | |
| }, | |
| { | |
| "epoch": 0.59, | |
| "learning_rate": 2.0521023765996345e-05, | |
| "loss": 0.0437, | |
| "step": 1290 | |
| }, | |
| { | |
| "epoch": 0.59, | |
| "eval_accuracy": 0.9848, | |
| "eval_f1": 0.9849802371541502, | |
| "eval_loss": 0.10180956870317459, | |
| "eval_precision": 0.9734375, | |
| "eval_recall": 0.9968, | |
| "eval_runtime": 31.9165, | |
| "eval_samples_per_second": 117.494, | |
| "eval_steps_per_second": 14.695, | |
| "step": 1290 | |
| }, | |
| { | |
| "epoch": 0.61, | |
| "learning_rate": 1.953839122486289e-05, | |
| "loss": 0.0482, | |
| "step": 1333 | |
| }, | |
| { | |
| "epoch": 0.61, | |
| "eval_accuracy": 0.9952, | |
| "eval_f1": 0.995187165775401, | |
| "eval_loss": 0.03259880468249321, | |
| "eval_precision": 0.9978552278820375, | |
| "eval_recall": 0.9925333333333334, | |
| "eval_runtime": 31.8461, | |
| "eval_samples_per_second": 117.754, | |
| "eval_steps_per_second": 14.727, | |
| "step": 1333 | |
| }, | |
| { | |
| "epoch": 0.63, | |
| "learning_rate": 1.8555758683729435e-05, | |
| "loss": 0.0513, | |
| "step": 1376 | |
| }, | |
| { | |
| "epoch": 0.63, | |
| "eval_accuracy": 0.9941333333333333, | |
| "eval_f1": 0.9941302027748132, | |
| "eval_loss": 0.03475691378116608, | |
| "eval_precision": 0.99466097170315, | |
| "eval_recall": 0.9936, | |
| "eval_runtime": 31.7619, | |
| "eval_samples_per_second": 118.066, | |
| "eval_steps_per_second": 14.766, | |
| "step": 1376 | |
| }, | |
| { | |
| "epoch": 0.65, | |
| "learning_rate": 1.7573126142595978e-05, | |
| "loss": 0.0184, | |
| "step": 1419 | |
| }, | |
| { | |
| "epoch": 0.65, | |
| "eval_accuracy": 0.9888, | |
| "eval_f1": 0.9888830068819482, | |
| "eval_loss": 0.07543797791004181, | |
| "eval_precision": 0.9816079873883342, | |
| "eval_recall": 0.9962666666666666, | |
| "eval_runtime": 31.8663, | |
| "eval_samples_per_second": 117.679, | |
| "eval_steps_per_second": 14.718, | |
| "step": 1419 | |
| }, | |
| { | |
| "epoch": 0.67, | |
| "learning_rate": 1.659049360146252e-05, | |
| "loss": 0.0327, | |
| "step": 1462 | |
| }, | |
| { | |
| "epoch": 0.67, | |
| "eval_accuracy": 0.9914666666666667, | |
| "eval_f1": 0.9914984059511159, | |
| "eval_loss": 0.05370575934648514, | |
| "eval_precision": 0.9878242456326098, | |
| "eval_recall": 0.9952, | |
| "eval_runtime": 31.7637, | |
| "eval_samples_per_second": 118.059, | |
| "eval_steps_per_second": 14.765, | |
| "step": 1462 | |
| }, | |
| { | |
| "epoch": 0.69, | |
| "learning_rate": 1.5607861060329068e-05, | |
| "loss": 0.0218, | |
| "step": 1505 | |
| }, | |
| { | |
| "epoch": 0.69, | |
| "eval_accuracy": 0.988, | |
| "eval_f1": 0.9880920878539297, | |
| "eval_loss": 0.07749391347169876, | |
| "eval_precision": 0.9805672268907563, | |
| "eval_recall": 0.9957333333333334, | |
| "eval_runtime": 32.0308, | |
| "eval_samples_per_second": 117.075, | |
| "eval_steps_per_second": 14.642, | |
| "step": 1505 | |
| }, | |
| { | |
| "epoch": 0.71, | |
| "learning_rate": 1.4625228519195613e-05, | |
| "loss": 0.0592, | |
| "step": 1548 | |
| }, | |
| { | |
| "epoch": 0.71, | |
| "eval_accuracy": 0.9906666666666667, | |
| "eval_f1": 0.9907137171663571, | |
| "eval_loss": 0.05098994821310043, | |
| "eval_precision": 0.9857444561774024, | |
| "eval_recall": 0.9957333333333334, | |
| "eval_runtime": 32.1011, | |
| "eval_samples_per_second": 116.818, | |
| "eval_steps_per_second": 14.61, | |
| "step": 1548 | |
| }, | |
| { | |
| "epoch": 0.73, | |
| "learning_rate": 1.3642595978062158e-05, | |
| "loss": 0.0506, | |
| "step": 1591 | |
| }, | |
| { | |
| "epoch": 0.73, | |
| "eval_accuracy": 0.9928, | |
| "eval_f1": 0.9928172386272945, | |
| "eval_loss": 0.040217798203229904, | |
| "eval_precision": 0.9904458598726115, | |
| "eval_recall": 0.9952, | |
| "eval_runtime": 32.4765, | |
| "eval_samples_per_second": 115.468, | |
| "eval_steps_per_second": 14.441, | |
| "step": 1591 | |
| }, | |
| { | |
| "epoch": 0.75, | |
| "learning_rate": 1.2659963436928701e-05, | |
| "loss": 0.0228, | |
| "step": 1634 | |
| }, | |
| { | |
| "epoch": 0.75, | |
| "eval_accuracy": 0.9946666666666667, | |
| "eval_f1": 0.9946695095948828, | |
| "eval_loss": 0.031395528465509415, | |
| "eval_precision": 0.9941395844432606, | |
| "eval_recall": 0.9952, | |
| "eval_runtime": 32.1532, | |
| "eval_samples_per_second": 116.629, | |
| "eval_steps_per_second": 14.586, | |
| "step": 1634 | |
| }, | |
| { | |
| "epoch": 0.77, | |
| "learning_rate": 1.1677330895795248e-05, | |
| "loss": 0.0297, | |
| "step": 1677 | |
| }, | |
| { | |
| "epoch": 0.77, | |
| "eval_accuracy": 0.9928, | |
| "eval_f1": 0.9928210582291943, | |
| "eval_loss": 0.044785238802433014, | |
| "eval_precision": 0.9899257688229056, | |
| "eval_recall": 0.9957333333333334, | |
| "eval_runtime": 32.1967, | |
| "eval_samples_per_second": 116.472, | |
| "eval_steps_per_second": 14.567, | |
| "step": 1677 | |
| }, | |
| { | |
| "epoch": 0.79, | |
| "learning_rate": 1.0694698354661791e-05, | |
| "loss": 0.0138, | |
| "step": 1720 | |
| }, | |
| { | |
| "epoch": 0.79, | |
| "eval_accuracy": 0.9853333333333333, | |
| "eval_f1": 0.9855072463768116, | |
| "eval_loss": 0.09062495082616806, | |
| "eval_precision": 0.9739583333333334, | |
| "eval_recall": 0.9973333333333333, | |
| "eval_runtime": 32.0852, | |
| "eval_samples_per_second": 116.876, | |
| "eval_steps_per_second": 14.617, | |
| "step": 1720 | |
| }, | |
| { | |
| "epoch": 0.81, | |
| "learning_rate": 9.712065813528338e-06, | |
| "loss": 0.0949, | |
| "step": 1763 | |
| }, | |
| { | |
| "epoch": 0.81, | |
| "eval_accuracy": 0.9941333333333333, | |
| "eval_f1": 0.994136460554371, | |
| "eval_loss": 0.028302613645792007, | |
| "eval_precision": 0.9936068193926478, | |
| "eval_recall": 0.9946666666666667, | |
| "eval_runtime": 32.2498, | |
| "eval_samples_per_second": 116.28, | |
| "eval_steps_per_second": 14.543, | |
| "step": 1763 | |
| }, | |
| { | |
| "epoch": 0.83, | |
| "learning_rate": 8.729433272394881e-06, | |
| "loss": 0.0614, | |
| "step": 1806 | |
| }, | |
| { | |
| "epoch": 0.83, | |
| "eval_accuracy": 0.9941333333333333, | |
| "eval_f1": 0.9941333333333333, | |
| "eval_loss": 0.029561299830675125, | |
| "eval_precision": 0.9941333333333333, | |
| "eval_recall": 0.9941333333333333, | |
| "eval_runtime": 32.2034, | |
| "eval_samples_per_second": 116.447, | |
| "eval_steps_per_second": 14.564, | |
| "step": 1806 | |
| }, | |
| { | |
| "epoch": 0.85, | |
| "learning_rate": 7.746800731261426e-06, | |
| "loss": 0.0012, | |
| "step": 1849 | |
| }, | |
| { | |
| "epoch": 0.85, | |
| "eval_accuracy": 0.9936, | |
| "eval_f1": 0.9936068193926478, | |
| "eval_loss": 0.03323618695139885, | |
| "eval_precision": 0.9925492283129325, | |
| "eval_recall": 0.9946666666666667, | |
| "eval_runtime": 32.2063, | |
| "eval_samples_per_second": 116.437, | |
| "eval_steps_per_second": 14.562, | |
| "step": 1849 | |
| }, | |
| { | |
| "epoch": 0.86, | |
| "learning_rate": 6.764168190127972e-06, | |
| "loss": 0.015, | |
| "step": 1892 | |
| }, | |
| { | |
| "epoch": 0.86, | |
| "eval_accuracy": 0.9944, | |
| "eval_f1": 0.9943955164131306, | |
| "eval_loss": 0.03202632814645767, | |
| "eval_precision": 0.9951923076923077, | |
| "eval_recall": 0.9936, | |
| "eval_runtime": 32.1602, | |
| "eval_samples_per_second": 116.604, | |
| "eval_steps_per_second": 14.583, | |
| "step": 1892 | |
| }, | |
| { | |
| "epoch": 0.88, | |
| "learning_rate": 5.781535648994515e-06, | |
| "loss": 0.0266, | |
| "step": 1935 | |
| }, | |
| { | |
| "epoch": 0.88, | |
| "eval_accuracy": 0.9922666666666666, | |
| "eval_f1": 0.9922933829391443, | |
| "eval_loss": 0.042477842420339584, | |
| "eval_precision": 0.9888771186440678, | |
| "eval_recall": 0.9957333333333334, | |
| "eval_runtime": 32.2356, | |
| "eval_samples_per_second": 116.331, | |
| "eval_steps_per_second": 14.549, | |
| "step": 1935 | |
| }, | |
| { | |
| "epoch": 0.9, | |
| "learning_rate": 4.798903107861061e-06, | |
| "loss": 0.0292, | |
| "step": 1978 | |
| }, | |
| { | |
| "epoch": 0.9, | |
| "eval_accuracy": 0.9901333333333333, | |
| "eval_f1": 0.9901934799893983, | |
| "eval_loss": 0.04828348755836487, | |
| "eval_precision": 0.9841938883034773, | |
| "eval_recall": 0.9962666666666666, | |
| "eval_runtime": 32.2496, | |
| "eval_samples_per_second": 116.281, | |
| "eval_steps_per_second": 14.543, | |
| "step": 1978 | |
| }, | |
| { | |
| "epoch": 0.92, | |
| "learning_rate": 3.816270566727605e-06, | |
| "loss": 0.0141, | |
| "step": 2021 | |
| }, | |
| { | |
| "epoch": 0.92, | |
| "eval_accuracy": 0.9890666666666666, | |
| "eval_f1": 0.9891505689335803, | |
| "eval_loss": 0.052797310054302216, | |
| "eval_precision": 0.9816176470588235, | |
| "eval_recall": 0.9968, | |
| "eval_runtime": 32.2638, | |
| "eval_samples_per_second": 116.229, | |
| "eval_steps_per_second": 14.536, | |
| "step": 2021 | |
| }, | |
| { | |
| "epoch": 0.94, | |
| "learning_rate": 2.83363802559415e-06, | |
| "loss": 0.0006, | |
| "step": 2064 | |
| }, | |
| { | |
| "epoch": 0.94, | |
| "eval_accuracy": 0.9909333333333333, | |
| "eval_f1": 0.9909862142099681, | |
| "eval_loss": 0.04819910600781441, | |
| "eval_precision": 0.985239852398524, | |
| "eval_recall": 0.9968, | |
| "eval_runtime": 32.596, | |
| "eval_samples_per_second": 115.045, | |
| "eval_steps_per_second": 14.388, | |
| "step": 2064 | |
| }, | |
| { | |
| "epoch": 0.96, | |
| "learning_rate": 1.851005484460695e-06, | |
| "loss": 0.0225, | |
| "step": 2107 | |
| }, | |
| { | |
| "epoch": 0.96, | |
| "eval_accuracy": 0.9922666666666666, | |
| "eval_f1": 0.9922933829391443, | |
| "eval_loss": 0.03804012015461922, | |
| "eval_precision": 0.9888771186440678, | |
| "eval_recall": 0.9957333333333334, | |
| "eval_runtime": 32.1606, | |
| "eval_samples_per_second": 116.602, | |
| "eval_steps_per_second": 14.583, | |
| "step": 2107 | |
| }, | |
| { | |
| "epoch": 0.98, | |
| "learning_rate": 8.683729433272396e-07, | |
| "loss": 0.0199, | |
| "step": 2150 | |
| }, | |
| { | |
| "epoch": 0.98, | |
| "eval_accuracy": 0.9925333333333334, | |
| "eval_f1": 0.9925492283129324, | |
| "eval_loss": 0.036869850009679794, | |
| "eval_precision": 0.9904407859798194, | |
| "eval_recall": 0.9946666666666667, | |
| "eval_runtime": 32.2379, | |
| "eval_samples_per_second": 116.323, | |
| "eval_steps_per_second": 14.548, | |
| "step": 2150 | |
| } | |
| ], | |
| "max_steps": 2188, | |
| "num_train_epochs": 1, | |
| "total_flos": 4604443468800000.0, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |