| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 1.0, | |
| "global_step": 2625, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0, | |
| "learning_rate": 4.998095238095239e-05, | |
| "loss": 0.0837, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.02, | |
| "learning_rate": 4.900952380952381e-05, | |
| "loss": 3.1832, | |
| "step": 52 | |
| }, | |
| { | |
| "epoch": 0.02, | |
| "eval_accuracy": 0.5, | |
| "eval_f1": 0.0, | |
| "eval_loss": 1.1445605754852295, | |
| "eval_precision": 0.0, | |
| "eval_recall": 0.0, | |
| "eval_runtime": 367.3994, | |
| "eval_samples_per_second": 12.248, | |
| "eval_steps_per_second": 1.532, | |
| "step": 52 | |
| }, | |
| { | |
| "epoch": 0.04, | |
| "learning_rate": 4.8019047619047617e-05, | |
| "loss": 0.5495, | |
| "step": 104 | |
| }, | |
| { | |
| "epoch": 0.04, | |
| "eval_accuracy": 0.9688888888888889, | |
| "eval_f1": 0.9681528662420383, | |
| "eval_loss": 0.3199825882911682, | |
| "eval_precision": 0.9916123019571296, | |
| "eval_recall": 0.9457777777777778, | |
| "eval_runtime": 366.8654, | |
| "eval_samples_per_second": 12.266, | |
| "eval_steps_per_second": 1.535, | |
| "step": 104 | |
| }, | |
| { | |
| "epoch": 0.06, | |
| "learning_rate": 4.702857142857143e-05, | |
| "loss": 0.5137, | |
| "step": 156 | |
| }, | |
| { | |
| "epoch": 0.06, | |
| "eval_accuracy": 0.9622222222222222, | |
| "eval_f1": 0.9608114338404794, | |
| "eval_loss": 0.14260223507881165, | |
| "eval_precision": 0.9980842911877394, | |
| "eval_recall": 0.9262222222222222, | |
| "eval_runtime": 366.5855, | |
| "eval_samples_per_second": 12.275, | |
| "eval_steps_per_second": 1.536, | |
| "step": 156 | |
| }, | |
| { | |
| "epoch": 0.08, | |
| "learning_rate": 4.6038095238095244e-05, | |
| "loss": 0.8596, | |
| "step": 208 | |
| }, | |
| { | |
| "epoch": 0.08, | |
| "eval_accuracy": 0.5, | |
| "eval_f1": 0.6666666666666666, | |
| "eval_loss": 1.3752027750015259, | |
| "eval_precision": 0.5, | |
| "eval_recall": 1.0, | |
| "eval_runtime": 366.5836, | |
| "eval_samples_per_second": 12.276, | |
| "eval_steps_per_second": 1.536, | |
| "step": 208 | |
| }, | |
| { | |
| "epoch": 0.1, | |
| "learning_rate": 4.504761904761905e-05, | |
| "loss": 0.5534, | |
| "step": 260 | |
| }, | |
| { | |
| "epoch": 0.1, | |
| "eval_accuracy": 0.9573333333333334, | |
| "eval_f1": 0.9563239308462239, | |
| "eval_loss": 0.4955243170261383, | |
| "eval_precision": 0.9794967381174278, | |
| "eval_recall": 0.9342222222222222, | |
| "eval_runtime": 366.7821, | |
| "eval_samples_per_second": 12.269, | |
| "eval_steps_per_second": 1.535, | |
| "step": 260 | |
| }, | |
| { | |
| "epoch": 0.12, | |
| "learning_rate": 4.405714285714286e-05, | |
| "loss": 0.2591, | |
| "step": 312 | |
| }, | |
| { | |
| "epoch": 0.12, | |
| "eval_accuracy": 0.9713333333333334, | |
| "eval_f1": 0.9705142857142858, | |
| "eval_loss": 0.19041332602500916, | |
| "eval_precision": 0.9990588235294118, | |
| "eval_recall": 0.9435555555555556, | |
| "eval_runtime": 366.5597, | |
| "eval_samples_per_second": 12.276, | |
| "eval_steps_per_second": 1.536, | |
| "step": 312 | |
| }, | |
| { | |
| "epoch": 0.14, | |
| "learning_rate": 4.3066666666666665e-05, | |
| "loss": 0.1978, | |
| "step": 364 | |
| }, | |
| { | |
| "epoch": 0.14, | |
| "eval_accuracy": 0.9668888888888889, | |
| "eval_f1": 0.9657864523536166, | |
| "eval_loss": 0.16762977838516235, | |
| "eval_precision": 0.9990498812351544, | |
| "eval_recall": 0.9346666666666666, | |
| "eval_runtime": 366.5739, | |
| "eval_samples_per_second": 12.276, | |
| "eval_steps_per_second": 1.536, | |
| "step": 364 | |
| }, | |
| { | |
| "epoch": 0.16, | |
| "learning_rate": 4.207619047619048e-05, | |
| "loss": 0.1662, | |
| "step": 416 | |
| }, | |
| { | |
| "epoch": 0.16, | |
| "eval_accuracy": 0.9686666666666667, | |
| "eval_f1": 0.9676531314521679, | |
| "eval_loss": 0.20070703327655792, | |
| "eval_precision": 1.0, | |
| "eval_recall": 0.9373333333333334, | |
| "eval_runtime": 366.9725, | |
| "eval_samples_per_second": 12.262, | |
| "eval_steps_per_second": 1.534, | |
| "step": 416 | |
| }, | |
| { | |
| "epoch": 0.18, | |
| "learning_rate": 4.1085714285714286e-05, | |
| "loss": 0.3206, | |
| "step": 468 | |
| }, | |
| { | |
| "epoch": 0.18, | |
| "eval_accuracy": 0.968, | |
| "eval_f1": 0.9669421487603307, | |
| "eval_loss": 0.18063302338123322, | |
| "eval_precision": 1.0, | |
| "eval_recall": 0.936, | |
| "eval_runtime": 371.3928, | |
| "eval_samples_per_second": 12.117, | |
| "eval_steps_per_second": 1.516, | |
| "step": 468 | |
| }, | |
| { | |
| "epoch": 0.2, | |
| "learning_rate": 4.00952380952381e-05, | |
| "loss": 0.2036, | |
| "step": 520 | |
| }, | |
| { | |
| "epoch": 0.2, | |
| "eval_accuracy": 0.9628888888888889, | |
| "eval_f1": 0.9625308503477674, | |
| "eval_loss": 0.5867714881896973, | |
| "eval_precision": 0.9719075668328047, | |
| "eval_recall": 0.9533333333333334, | |
| "eval_runtime": 366.8218, | |
| "eval_samples_per_second": 12.268, | |
| "eval_steps_per_second": 1.535, | |
| "step": 520 | |
| }, | |
| { | |
| "epoch": 0.22, | |
| "learning_rate": 3.910476190476191e-05, | |
| "loss": 0.4246, | |
| "step": 572 | |
| }, | |
| { | |
| "epoch": 0.22, | |
| "eval_accuracy": 0.9682222222222222, | |
| "eval_f1": 0.9675663415740532, | |
| "eval_loss": 0.14041858911514282, | |
| "eval_precision": 0.9879573876794813, | |
| "eval_recall": 0.948, | |
| "eval_runtime": 366.7155, | |
| "eval_samples_per_second": 12.271, | |
| "eval_steps_per_second": 1.535, | |
| "step": 572 | |
| }, | |
| { | |
| "epoch": 0.24, | |
| "learning_rate": 3.8114285714285714e-05, | |
| "loss": 0.1938, | |
| "step": 624 | |
| }, | |
| { | |
| "epoch": 0.24, | |
| "eval_accuracy": 0.9688888888888889, | |
| "eval_f1": 0.9679046309032554, | |
| "eval_loss": 0.12066192179918289, | |
| "eval_precision": 0.9995265151515151, | |
| "eval_recall": 0.9382222222222222, | |
| "eval_runtime": 367.3124, | |
| "eval_samples_per_second": 12.251, | |
| "eval_steps_per_second": 1.533, | |
| "step": 624 | |
| }, | |
| { | |
| "epoch": 0.26, | |
| "learning_rate": 3.712380952380953e-05, | |
| "loss": 0.1131, | |
| "step": 676 | |
| }, | |
| { | |
| "epoch": 0.26, | |
| "eval_accuracy": 0.9702222222222222, | |
| "eval_f1": 0.9693363844393592, | |
| "eval_loss": 0.15112678706645966, | |
| "eval_precision": 0.9990566037735849, | |
| "eval_recall": 0.9413333333333334, | |
| "eval_runtime": 366.4976, | |
| "eval_samples_per_second": 12.278, | |
| "eval_steps_per_second": 1.536, | |
| "step": 676 | |
| }, | |
| { | |
| "epoch": 0.28, | |
| "learning_rate": 3.6133333333333335e-05, | |
| "loss": 0.1786, | |
| "step": 728 | |
| }, | |
| { | |
| "epoch": 0.28, | |
| "eval_accuracy": 0.9717777777777777, | |
| "eval_f1": 0.9710376282782212, | |
| "eval_loss": 0.1380281001329422, | |
| "eval_precision": 0.9971896955503513, | |
| "eval_recall": 0.9462222222222222, | |
| "eval_runtime": 366.0457, | |
| "eval_samples_per_second": 12.294, | |
| "eval_steps_per_second": 1.538, | |
| "step": 728 | |
| }, | |
| { | |
| "epoch": 0.3, | |
| "learning_rate": 3.514285714285714e-05, | |
| "loss": 0.1303, | |
| "step": 780 | |
| }, | |
| { | |
| "epoch": 0.3, | |
| "eval_accuracy": 0.9717777777777777, | |
| "eval_f1": 0.9709846927119031, | |
| "eval_loss": 0.14563770592212677, | |
| "eval_precision": 0.999059708509638, | |
| "eval_recall": 0.9444444444444444, | |
| "eval_runtime": 366.3569, | |
| "eval_samples_per_second": 12.283, | |
| "eval_steps_per_second": 1.537, | |
| "step": 780 | |
| }, | |
| { | |
| "epoch": 0.32, | |
| "learning_rate": 3.415238095238095e-05, | |
| "loss": 0.1851, | |
| "step": 832 | |
| }, | |
| { | |
| "epoch": 0.32, | |
| "eval_accuracy": 0.9711111111111111, | |
| "eval_f1": 0.970360237118103, | |
| "eval_loss": 0.20535722374916077, | |
| "eval_precision": 0.9962546816479401, | |
| "eval_recall": 0.9457777777777778, | |
| "eval_runtime": 366.4431, | |
| "eval_samples_per_second": 12.28, | |
| "eval_steps_per_second": 1.536, | |
| "step": 832 | |
| }, | |
| { | |
| "epoch": 0.34, | |
| "learning_rate": 3.316190476190476e-05, | |
| "loss": 0.1857, | |
| "step": 884 | |
| }, | |
| { | |
| "epoch": 0.34, | |
| "eval_accuracy": 0.9722222222222222, | |
| "eval_f1": 0.9714807209673739, | |
| "eval_loss": 0.12345914542675018, | |
| "eval_precision": 0.9981247069854665, | |
| "eval_recall": 0.9462222222222222, | |
| "eval_runtime": 366.3331, | |
| "eval_samples_per_second": 12.284, | |
| "eval_steps_per_second": 1.537, | |
| "step": 884 | |
| }, | |
| { | |
| "epoch": 0.36, | |
| "learning_rate": 3.217142857142858e-05, | |
| "loss": 0.2037, | |
| "step": 936 | |
| }, | |
| { | |
| "epoch": 0.36, | |
| "eval_accuracy": 0.9548888888888889, | |
| "eval_f1": 0.9527797162130728, | |
| "eval_loss": 0.19388167560100555, | |
| "eval_precision": 0.9995119570522206, | |
| "eval_recall": 0.9102222222222223, | |
| "eval_runtime": 368.1148, | |
| "eval_samples_per_second": 12.224, | |
| "eval_steps_per_second": 1.529, | |
| "step": 936 | |
| }, | |
| { | |
| "epoch": 0.38, | |
| "learning_rate": 3.1180952380952384e-05, | |
| "loss": 0.133, | |
| "step": 988 | |
| }, | |
| { | |
| "epoch": 0.38, | |
| "eval_accuracy": 0.9591111111111111, | |
| "eval_f1": 0.9585772174696083, | |
| "eval_loss": 0.2834174335002899, | |
| "eval_precision": 0.9712591240875912, | |
| "eval_recall": 0.9462222222222222, | |
| "eval_runtime": 366.4123, | |
| "eval_samples_per_second": 12.281, | |
| "eval_steps_per_second": 1.537, | |
| "step": 988 | |
| }, | |
| { | |
| "epoch": 0.4, | |
| "learning_rate": 3.019047619047619e-05, | |
| "loss": 0.105, | |
| "step": 1040 | |
| }, | |
| { | |
| "epoch": 0.4, | |
| "eval_accuracy": 0.9693333333333334, | |
| "eval_f1": 0.9684065934065934, | |
| "eval_loss": 0.13286447525024414, | |
| "eval_precision": 0.9985835694050992, | |
| "eval_recall": 0.94, | |
| "eval_runtime": 372.0042, | |
| "eval_samples_per_second": 12.097, | |
| "eval_steps_per_second": 1.513, | |
| "step": 1040 | |
| }, | |
| { | |
| "epoch": 0.42, | |
| "learning_rate": 2.9199999999999998e-05, | |
| "loss": 0.2736, | |
| "step": 1092 | |
| }, | |
| { | |
| "epoch": 0.42, | |
| "eval_accuracy": 0.9504444444444444, | |
| "eval_f1": 0.9502343226958269, | |
| "eval_loss": 0.2549838125705719, | |
| "eval_precision": 0.9542805916629314, | |
| "eval_recall": 0.9462222222222222, | |
| "eval_runtime": 366.5595, | |
| "eval_samples_per_second": 12.276, | |
| "eval_steps_per_second": 1.536, | |
| "step": 1092 | |
| }, | |
| { | |
| "epoch": 0.44, | |
| "learning_rate": 2.8209523809523812e-05, | |
| "loss": 0.2565, | |
| "step": 1144 | |
| }, | |
| { | |
| "epoch": 0.44, | |
| "eval_accuracy": 0.9693333333333334, | |
| "eval_f1": 0.9683921209344939, | |
| "eval_loss": 0.16569776833057404, | |
| "eval_precision": 0.999054820415879, | |
| "eval_recall": 0.9395555555555556, | |
| "eval_runtime": 366.5097, | |
| "eval_samples_per_second": 12.278, | |
| "eval_steps_per_second": 1.536, | |
| "step": 1144 | |
| }, | |
| { | |
| "epoch": 0.46, | |
| "learning_rate": 2.7219047619047623e-05, | |
| "loss": 0.0888, | |
| "step": 1196 | |
| }, | |
| { | |
| "epoch": 0.46, | |
| "eval_accuracy": 0.9717777777777777, | |
| "eval_f1": 0.9709979447362412, | |
| "eval_loss": 0.14255712926387787, | |
| "eval_precision": 0.9985908877407234, | |
| "eval_recall": 0.9448888888888889, | |
| "eval_runtime": 366.3675, | |
| "eval_samples_per_second": 12.283, | |
| "eval_steps_per_second": 1.537, | |
| "step": 1196 | |
| }, | |
| { | |
| "epoch": 0.48, | |
| "learning_rate": 2.622857142857143e-05, | |
| "loss": 0.1704, | |
| "step": 1248 | |
| }, | |
| { | |
| "epoch": 0.48, | |
| "eval_accuracy": 0.9717777777777777, | |
| "eval_f1": 0.9709714285714286, | |
| "eval_loss": 0.13756924867630005, | |
| "eval_precision": 0.9995294117647059, | |
| "eval_recall": 0.944, | |
| "eval_runtime": 366.5849, | |
| "eval_samples_per_second": 12.275, | |
| "eval_steps_per_second": 1.536, | |
| "step": 1248 | |
| }, | |
| { | |
| "epoch": 0.5, | |
| "learning_rate": 2.523809523809524e-05, | |
| "loss": 0.0877, | |
| "step": 1300 | |
| }, | |
| { | |
| "epoch": 0.5, | |
| "eval_accuracy": 0.9715555555555555, | |
| "eval_f1": 0.9707895937927886, | |
| "eval_loss": 0.12067598104476929, | |
| "eval_precision": 0.9976547842401501, | |
| "eval_recall": 0.9453333333333334, | |
| "eval_runtime": 366.3594, | |
| "eval_samples_per_second": 12.283, | |
| "eval_steps_per_second": 1.537, | |
| "step": 1300 | |
| }, | |
| { | |
| "epoch": 0.52, | |
| "learning_rate": 2.424761904761905e-05, | |
| "loss": 0.1013, | |
| "step": 1352 | |
| }, | |
| { | |
| "epoch": 0.52, | |
| "eval_accuracy": 0.9711111111111111, | |
| "eval_f1": 0.9702653247941445, | |
| "eval_loss": 0.10261368751525879, | |
| "eval_precision": 0.9995287464655985, | |
| "eval_recall": 0.9426666666666667, | |
| "eval_runtime": 367.9823, | |
| "eval_samples_per_second": 12.229, | |
| "eval_steps_per_second": 1.53, | |
| "step": 1352 | |
| }, | |
| { | |
| "epoch": 0.53, | |
| "learning_rate": 2.3257142857142858e-05, | |
| "loss": 0.1281, | |
| "step": 1404 | |
| }, | |
| { | |
| "epoch": 0.53, | |
| "eval_accuracy": 0.9697777777777777, | |
| "eval_f1": 0.968878718535469, | |
| "eval_loss": 0.19041745364665985, | |
| "eval_precision": 0.9985849056603774, | |
| "eval_recall": 0.9408888888888889, | |
| "eval_runtime": 368.2198, | |
| "eval_samples_per_second": 12.221, | |
| "eval_steps_per_second": 1.529, | |
| "step": 1404 | |
| }, | |
| { | |
| "epoch": 0.55, | |
| "learning_rate": 2.2266666666666668e-05, | |
| "loss": 0.1385, | |
| "step": 1456 | |
| }, | |
| { | |
| "epoch": 0.55, | |
| "eval_accuracy": 0.9704444444444444, | |
| "eval_f1": 0.9695443095946874, | |
| "eval_loss": 0.1330152004957199, | |
| "eval_precision": 1.0, | |
| "eval_recall": 0.9408888888888889, | |
| "eval_runtime": 366.4259, | |
| "eval_samples_per_second": 12.281, | |
| "eval_steps_per_second": 1.536, | |
| "step": 1456 | |
| }, | |
| { | |
| "epoch": 0.57, | |
| "learning_rate": 2.127619047619048e-05, | |
| "loss": 0.0947, | |
| "step": 1508 | |
| }, | |
| { | |
| "epoch": 0.57, | |
| "eval_accuracy": 0.9722222222222222, | |
| "eval_f1": 0.9714285714285714, | |
| "eval_loss": 0.16506431996822357, | |
| "eval_precision": 1.0, | |
| "eval_recall": 0.9444444444444444, | |
| "eval_runtime": 366.4491, | |
| "eval_samples_per_second": 12.28, | |
| "eval_steps_per_second": 1.536, | |
| "step": 1508 | |
| }, | |
| { | |
| "epoch": 0.59, | |
| "learning_rate": 2.0285714285714286e-05, | |
| "loss": 0.1062, | |
| "step": 1560 | |
| }, | |
| { | |
| "epoch": 0.59, | |
| "eval_accuracy": 0.9728888888888889, | |
| "eval_f1": 0.9721333942439471, | |
| "eval_loss": 0.08876548707485199, | |
| "eval_precision": 1.0, | |
| "eval_recall": 0.9457777777777778, | |
| "eval_runtime": 366.4995, | |
| "eval_samples_per_second": 12.278, | |
| "eval_steps_per_second": 1.536, | |
| "step": 1560 | |
| }, | |
| { | |
| "epoch": 0.61, | |
| "learning_rate": 1.9295238095238096e-05, | |
| "loss": 0.0974, | |
| "step": 1612 | |
| }, | |
| { | |
| "epoch": 0.61, | |
| "eval_accuracy": 0.9726666666666667, | |
| "eval_f1": 0.9719113952957296, | |
| "eval_loss": 0.1103716641664505, | |
| "eval_precision": 0.9995302959135745, | |
| "eval_recall": 0.9457777777777778, | |
| "eval_runtime": 367.3196, | |
| "eval_samples_per_second": 12.251, | |
| "eval_steps_per_second": 1.533, | |
| "step": 1612 | |
| }, | |
| { | |
| "epoch": 0.63, | |
| "learning_rate": 1.8304761904761906e-05, | |
| "loss": 0.1549, | |
| "step": 1664 | |
| }, | |
| { | |
| "epoch": 0.63, | |
| "eval_accuracy": 0.9362222222222222, | |
| "eval_f1": 0.9375951293759512, | |
| "eval_loss": 1.4429972171783447, | |
| "eval_precision": 0.9178373776074925, | |
| "eval_recall": 0.9582222222222222, | |
| "eval_runtime": 366.4448, | |
| "eval_samples_per_second": 12.28, | |
| "eval_steps_per_second": 1.536, | |
| "step": 1664 | |
| }, | |
| { | |
| "epoch": 0.65, | |
| "learning_rate": 1.7314285714285717e-05, | |
| "loss": 0.1223, | |
| "step": 1716 | |
| }, | |
| { | |
| "epoch": 0.65, | |
| "eval_accuracy": 0.9717777777777777, | |
| "eval_f1": 0.9710244125028521, | |
| "eval_loss": 0.07695630192756653, | |
| "eval_precision": 0.9976558837318331, | |
| "eval_recall": 0.9457777777777778, | |
| "eval_runtime": 366.6321, | |
| "eval_samples_per_second": 12.274, | |
| "eval_steps_per_second": 1.536, | |
| "step": 1716 | |
| }, | |
| { | |
| "epoch": 0.67, | |
| "learning_rate": 1.6323809523809524e-05, | |
| "loss": 0.0686, | |
| "step": 1768 | |
| }, | |
| { | |
| "epoch": 0.67, | |
| "eval_accuracy": 0.9704444444444444, | |
| "eval_f1": 0.9697107720337054, | |
| "eval_loss": 0.15851092338562012, | |
| "eval_precision": 0.9943951424567959, | |
| "eval_recall": 0.9462222222222222, | |
| "eval_runtime": 366.4624, | |
| "eval_samples_per_second": 12.28, | |
| "eval_steps_per_second": 1.536, | |
| "step": 1768 | |
| }, | |
| { | |
| "epoch": 0.69, | |
| "learning_rate": 1.5333333333333334e-05, | |
| "loss": 0.156, | |
| "step": 1820 | |
| }, | |
| { | |
| "epoch": 0.69, | |
| "eval_accuracy": 0.9646666666666667, | |
| "eval_f1": 0.9633724948168625, | |
| "eval_loss": 0.2488366961479187, | |
| "eval_precision": 1.0, | |
| "eval_recall": 0.9293333333333333, | |
| "eval_runtime": 369.4407, | |
| "eval_samples_per_second": 12.181, | |
| "eval_steps_per_second": 1.524, | |
| "step": 1820 | |
| }, | |
| { | |
| "epoch": 0.71, | |
| "learning_rate": 1.4342857142857143e-05, | |
| "loss": 0.1607, | |
| "step": 1872 | |
| }, | |
| { | |
| "epoch": 0.71, | |
| "eval_accuracy": 0.9726666666666667, | |
| "eval_f1": 0.971898560657985, | |
| "eval_loss": 0.10330852121114731, | |
| "eval_precision": 1.0, | |
| "eval_recall": 0.9453333333333334, | |
| "eval_runtime": 367.7786, | |
| "eval_samples_per_second": 12.236, | |
| "eval_steps_per_second": 1.531, | |
| "step": 1872 | |
| }, | |
| { | |
| "epoch": 0.73, | |
| "learning_rate": 1.3352380952380952e-05, | |
| "loss": 0.0813, | |
| "step": 1924 | |
| }, | |
| { | |
| "epoch": 0.73, | |
| "eval_accuracy": 0.9726666666666667, | |
| "eval_f1": 0.971898560657985, | |
| "eval_loss": 0.11011069267988205, | |
| "eval_precision": 1.0, | |
| "eval_recall": 0.9453333333333334, | |
| "eval_runtime": 366.3291, | |
| "eval_samples_per_second": 12.284, | |
| "eval_steps_per_second": 1.537, | |
| "step": 1924 | |
| }, | |
| { | |
| "epoch": 0.75, | |
| "learning_rate": 1.2361904761904762e-05, | |
| "loss": 0.0902, | |
| "step": 1976 | |
| }, | |
| { | |
| "epoch": 0.75, | |
| "eval_accuracy": 0.9726666666666667, | |
| "eval_f1": 0.971898560657985, | |
| "eval_loss": 0.09210823476314545, | |
| "eval_precision": 1.0, | |
| "eval_recall": 0.9453333333333334, | |
| "eval_runtime": 366.51, | |
| "eval_samples_per_second": 12.278, | |
| "eval_steps_per_second": 1.536, | |
| "step": 1976 | |
| }, | |
| { | |
| "epoch": 0.77, | |
| "learning_rate": 1.1371428571428571e-05, | |
| "loss": 0.1138, | |
| "step": 2028 | |
| }, | |
| { | |
| "epoch": 0.77, | |
| "eval_accuracy": 0.9728888888888889, | |
| "eval_f1": 0.9721333942439471, | |
| "eval_loss": 0.12518948316574097, | |
| "eval_precision": 1.0, | |
| "eval_recall": 0.9457777777777778, | |
| "eval_runtime": 367.2547, | |
| "eval_samples_per_second": 12.253, | |
| "eval_steps_per_second": 1.533, | |
| "step": 2028 | |
| }, | |
| { | |
| "epoch": 0.79, | |
| "learning_rate": 1.0380952380952382e-05, | |
| "loss": 0.1131, | |
| "step": 2080 | |
| }, | |
| { | |
| "epoch": 0.79, | |
| "eval_accuracy": 0.9728888888888889, | |
| "eval_f1": 0.9721333942439471, | |
| "eval_loss": 0.07795156538486481, | |
| "eval_precision": 1.0, | |
| "eval_recall": 0.9457777777777778, | |
| "eval_runtime": 366.7002, | |
| "eval_samples_per_second": 12.272, | |
| "eval_steps_per_second": 1.535, | |
| "step": 2080 | |
| }, | |
| { | |
| "epoch": 0.81, | |
| "learning_rate": 9.39047619047619e-06, | |
| "loss": 0.1169, | |
| "step": 2132 | |
| }, | |
| { | |
| "epoch": 0.81, | |
| "eval_accuracy": 0.9728888888888889, | |
| "eval_f1": 0.9721333942439471, | |
| "eval_loss": 0.0857003927230835, | |
| "eval_precision": 1.0, | |
| "eval_recall": 0.9457777777777778, | |
| "eval_runtime": 366.5193, | |
| "eval_samples_per_second": 12.278, | |
| "eval_steps_per_second": 1.536, | |
| "step": 2132 | |
| }, | |
| { | |
| "epoch": 0.83, | |
| "learning_rate": 8.400000000000001e-06, | |
| "loss": 0.0624, | |
| "step": 2184 | |
| }, | |
| { | |
| "epoch": 0.83, | |
| "eval_accuracy": 0.9728888888888889, | |
| "eval_f1": 0.9721333942439471, | |
| "eval_loss": 0.11906697601079941, | |
| "eval_precision": 1.0, | |
| "eval_recall": 0.9457777777777778, | |
| "eval_runtime": 366.4052, | |
| "eval_samples_per_second": 12.281, | |
| "eval_steps_per_second": 1.537, | |
| "step": 2184 | |
| }, | |
| { | |
| "epoch": 0.85, | |
| "learning_rate": 7.40952380952381e-06, | |
| "loss": 0.0936, | |
| "step": 2236 | |
| }, | |
| { | |
| "epoch": 0.85, | |
| "eval_accuracy": 0.9728888888888889, | |
| "eval_f1": 0.9721333942439471, | |
| "eval_loss": 0.1168401688337326, | |
| "eval_precision": 1.0, | |
| "eval_recall": 0.9457777777777778, | |
| "eval_runtime": 368.3489, | |
| "eval_samples_per_second": 12.217, | |
| "eval_steps_per_second": 1.528, | |
| "step": 2236 | |
| }, | |
| { | |
| "epoch": 0.87, | |
| "learning_rate": 6.419047619047619e-06, | |
| "loss": 0.1124, | |
| "step": 2288 | |
| }, | |
| { | |
| "epoch": 0.87, | |
| "eval_accuracy": 0.9728888888888889, | |
| "eval_f1": 0.9721333942439471, | |
| "eval_loss": 0.08958863466978073, | |
| "eval_precision": 1.0, | |
| "eval_recall": 0.9457777777777778, | |
| "eval_runtime": 367.9579, | |
| "eval_samples_per_second": 12.23, | |
| "eval_steps_per_second": 1.53, | |
| "step": 2288 | |
| }, | |
| { | |
| "epoch": 0.89, | |
| "learning_rate": 5.428571428571429e-06, | |
| "loss": 0.0519, | |
| "step": 2340 | |
| }, | |
| { | |
| "epoch": 0.89, | |
| "eval_accuracy": 0.9728888888888889, | |
| "eval_f1": 0.9721333942439471, | |
| "eval_loss": 0.10539975017309189, | |
| "eval_precision": 1.0, | |
| "eval_recall": 0.9457777777777778, | |
| "eval_runtime": 367.9097, | |
| "eval_samples_per_second": 12.231, | |
| "eval_steps_per_second": 1.53, | |
| "step": 2340 | |
| }, | |
| { | |
| "epoch": 0.91, | |
| "learning_rate": 4.4380952380952385e-06, | |
| "loss": 0.1278, | |
| "step": 2392 | |
| }, | |
| { | |
| "epoch": 0.91, | |
| "eval_accuracy": 0.9728888888888889, | |
| "eval_f1": 0.9721333942439471, | |
| "eval_loss": 0.11540067195892334, | |
| "eval_precision": 1.0, | |
| "eval_recall": 0.9457777777777778, | |
| "eval_runtime": 367.0779, | |
| "eval_samples_per_second": 12.259, | |
| "eval_steps_per_second": 1.534, | |
| "step": 2392 | |
| }, | |
| { | |
| "epoch": 0.93, | |
| "learning_rate": 3.4476190476190472e-06, | |
| "loss": 0.1412, | |
| "step": 2444 | |
| }, | |
| { | |
| "epoch": 0.93, | |
| "eval_accuracy": 0.9728888888888889, | |
| "eval_f1": 0.9721333942439471, | |
| "eval_loss": 0.09740398824214935, | |
| "eval_precision": 1.0, | |
| "eval_recall": 0.9457777777777778, | |
| "eval_runtime": 366.6614, | |
| "eval_samples_per_second": 12.273, | |
| "eval_steps_per_second": 1.535, | |
| "step": 2444 | |
| }, | |
| { | |
| "epoch": 0.95, | |
| "learning_rate": 2.4571428571428573e-06, | |
| "loss": 0.0472, | |
| "step": 2496 | |
| }, | |
| { | |
| "epoch": 0.95, | |
| "eval_accuracy": 0.9728888888888889, | |
| "eval_f1": 0.9721333942439471, | |
| "eval_loss": 0.11149758845567703, | |
| "eval_precision": 1.0, | |
| "eval_recall": 0.9457777777777778, | |
| "eval_runtime": 366.4328, | |
| "eval_samples_per_second": 12.281, | |
| "eval_steps_per_second": 1.536, | |
| "step": 2496 | |
| }, | |
| { | |
| "epoch": 0.97, | |
| "learning_rate": 1.4666666666666667e-06, | |
| "loss": 0.128, | |
| "step": 2548 | |
| }, | |
| { | |
| "epoch": 0.97, | |
| "eval_accuracy": 0.9728888888888889, | |
| "eval_f1": 0.9721333942439471, | |
| "eval_loss": 0.09608805179595947, | |
| "eval_precision": 1.0, | |
| "eval_recall": 0.9457777777777778, | |
| "eval_runtime": 367.1973, | |
| "eval_samples_per_second": 12.255, | |
| "eval_steps_per_second": 1.533, | |
| "step": 2548 | |
| }, | |
| { | |
| "epoch": 0.99, | |
| "learning_rate": 4.761904761904763e-07, | |
| "loss": 0.0462, | |
| "step": 2600 | |
| }, | |
| { | |
| "epoch": 0.99, | |
| "eval_accuracy": 0.9728888888888889, | |
| "eval_f1": 0.9721333942439471, | |
| "eval_loss": 0.10537552833557129, | |
| "eval_precision": 1.0, | |
| "eval_recall": 0.9457777777777778, | |
| "eval_runtime": 366.8901, | |
| "eval_samples_per_second": 12.265, | |
| "eval_steps_per_second": 1.535, | |
| "step": 2600 | |
| } | |
| ], | |
| "max_steps": 2625, | |
| "num_train_epochs": 1, | |
| "total_flos": 7.7969900961792e+16, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |