| { | |
| "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": 0.7271, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.02, | |
| "learning_rate": 4.900952380952381e-05, | |
| "loss": 0.2895, | |
| "step": 52 | |
| }, | |
| { | |
| "epoch": 0.02, | |
| "eval_accuracy": 0.9933333333333333, | |
| "eval_f1": 0.9933451641526175, | |
| "eval_loss": 0.02848968468606472, | |
| "eval_precision": 0.991585473870682, | |
| "eval_recall": 0.9951111111111111, | |
| "eval_runtime": 53.465, | |
| "eval_samples_per_second": 84.167, | |
| "eval_steps_per_second": 10.53, | |
| "step": 52 | |
| }, | |
| { | |
| "epoch": 0.04, | |
| "learning_rate": 4.8019047619047617e-05, | |
| "loss": 0.0128, | |
| "step": 104 | |
| }, | |
| { | |
| "epoch": 0.04, | |
| "eval_accuracy": 0.9951111111111111, | |
| "eval_f1": 0.9950914770191879, | |
| "eval_loss": 0.03895995765924454, | |
| "eval_precision": 0.9991039426523297, | |
| "eval_recall": 0.9911111111111112, | |
| "eval_runtime": 52.7075, | |
| "eval_samples_per_second": 85.377, | |
| "eval_steps_per_second": 10.682, | |
| "step": 104 | |
| }, | |
| { | |
| "epoch": 0.06, | |
| "learning_rate": 4.702857142857143e-05, | |
| "loss": 0.0362, | |
| "step": 156 | |
| }, | |
| { | |
| "epoch": 0.06, | |
| "eval_accuracy": 0.9928888888888889, | |
| "eval_f1": 0.9929203539823008, | |
| "eval_loss": 0.046059854328632355, | |
| "eval_precision": 0.9885462555066079, | |
| "eval_recall": 0.9973333333333333, | |
| "eval_runtime": 52.6732, | |
| "eval_samples_per_second": 85.432, | |
| "eval_steps_per_second": 10.689, | |
| "step": 156 | |
| }, | |
| { | |
| "epoch": 0.08, | |
| "learning_rate": 4.6038095238095244e-05, | |
| "loss": 0.0746, | |
| "step": 208 | |
| }, | |
| { | |
| "epoch": 0.08, | |
| "eval_accuracy": 0.994, | |
| "eval_f1": 0.9939718687206966, | |
| "eval_loss": 0.037436459213495255, | |
| "eval_precision": 0.9986541049798116, | |
| "eval_recall": 0.9893333333333333, | |
| "eval_runtime": 54.0208, | |
| "eval_samples_per_second": 83.301, | |
| "eval_steps_per_second": 10.422, | |
| "step": 208 | |
| }, | |
| { | |
| "epoch": 0.1, | |
| "learning_rate": 4.504761904761905e-05, | |
| "loss": 0.065, | |
| "step": 260 | |
| }, | |
| { | |
| "epoch": 0.1, | |
| "eval_accuracy": 0.9964444444444445, | |
| "eval_f1": 0.9964349376114082, | |
| "eval_loss": 0.015599595382809639, | |
| "eval_precision": 0.9991063449508489, | |
| "eval_recall": 0.9937777777777778, | |
| "eval_runtime": 52.5898, | |
| "eval_samples_per_second": 85.568, | |
| "eval_steps_per_second": 10.706, | |
| "step": 260 | |
| }, | |
| { | |
| "epoch": 0.12, | |
| "learning_rate": 4.405714285714286e-05, | |
| "loss": 0.018, | |
| "step": 312 | |
| }, | |
| { | |
| "epoch": 0.12, | |
| "eval_accuracy": 0.9977777777777778, | |
| "eval_f1": 0.9977787649933363, | |
| "eval_loss": 0.013370415195822716, | |
| "eval_precision": 0.9973357015985791, | |
| "eval_recall": 0.9982222222222222, | |
| "eval_runtime": 52.6939, | |
| "eval_samples_per_second": 85.399, | |
| "eval_steps_per_second": 10.684, | |
| "step": 312 | |
| }, | |
| { | |
| "epoch": 0.14, | |
| "learning_rate": 4.3066666666666665e-05, | |
| "loss": 0.0021, | |
| "step": 364 | |
| }, | |
| { | |
| "epoch": 0.14, | |
| "eval_accuracy": 0.9968888888888889, | |
| "eval_f1": 0.9968819599109132, | |
| "eval_loss": 0.026465779170393944, | |
| "eval_precision": 0.9991071428571429, | |
| "eval_recall": 0.9946666666666667, | |
| "eval_runtime": 52.8294, | |
| "eval_samples_per_second": 85.18, | |
| "eval_steps_per_second": 10.657, | |
| "step": 364 | |
| }, | |
| { | |
| "epoch": 0.16, | |
| "learning_rate": 4.207619047619048e-05, | |
| "loss": 0.0385, | |
| "step": 416 | |
| }, | |
| { | |
| "epoch": 0.16, | |
| "eval_accuracy": 0.9968888888888889, | |
| "eval_f1": 0.9968791796700847, | |
| "eval_loss": 0.019380465149879456, | |
| "eval_precision": 1.0, | |
| "eval_recall": 0.9937777777777778, | |
| "eval_runtime": 53.1835, | |
| "eval_samples_per_second": 84.613, | |
| "eval_steps_per_second": 10.586, | |
| "step": 416 | |
| }, | |
| { | |
| "epoch": 0.18, | |
| "learning_rate": 4.1085714285714286e-05, | |
| "loss": 0.0158, | |
| "step": 468 | |
| }, | |
| { | |
| "epoch": 0.18, | |
| "eval_accuracy": 0.9926666666666667, | |
| "eval_f1": 0.9926124916051041, | |
| "eval_loss": 0.05080940201878548, | |
| "eval_precision": 1.0, | |
| "eval_recall": 0.9853333333333333, | |
| "eval_runtime": 53.8229, | |
| "eval_samples_per_second": 83.608, | |
| "eval_steps_per_second": 10.46, | |
| "step": 468 | |
| }, | |
| { | |
| "epoch": 0.2, | |
| "learning_rate": 4.00952380952381e-05, | |
| "loss": 0.0483, | |
| "step": 520 | |
| }, | |
| { | |
| "epoch": 0.2, | |
| "eval_accuracy": 0.9926666666666667, | |
| "eval_f1": 0.9926974994467802, | |
| "eval_loss": 0.03643398359417915, | |
| "eval_precision": 0.988541207580432, | |
| "eval_recall": 0.9968888888888889, | |
| "eval_runtime": 53.9013, | |
| "eval_samples_per_second": 83.486, | |
| "eval_steps_per_second": 10.445, | |
| "step": 520 | |
| }, | |
| { | |
| "epoch": 0.22, | |
| "learning_rate": 3.910476190476191e-05, | |
| "loss": 0.0008, | |
| "step": 572 | |
| }, | |
| { | |
| "epoch": 0.22, | |
| "eval_accuracy": 0.9968888888888889, | |
| "eval_f1": 0.9968791796700847, | |
| "eval_loss": 0.02641967684030533, | |
| "eval_precision": 1.0, | |
| "eval_recall": 0.9937777777777778, | |
| "eval_runtime": 52.853, | |
| "eval_samples_per_second": 85.142, | |
| "eval_steps_per_second": 10.652, | |
| "step": 572 | |
| }, | |
| { | |
| "epoch": 0.24, | |
| "learning_rate": 3.8114285714285714e-05, | |
| "loss": 0.0445, | |
| "step": 624 | |
| }, | |
| { | |
| "epoch": 0.24, | |
| "eval_accuracy": 0.9937777777777778, | |
| "eval_f1": 0.9937998228520815, | |
| "eval_loss": 0.04403863102197647, | |
| "eval_precision": 0.9902912621359223, | |
| "eval_recall": 0.9973333333333333, | |
| "eval_runtime": 52.6526, | |
| "eval_samples_per_second": 85.466, | |
| "eval_steps_per_second": 10.693, | |
| "step": 624 | |
| }, | |
| { | |
| "epoch": 0.26, | |
| "learning_rate": 3.712380952380953e-05, | |
| "loss": 0.0659, | |
| "step": 676 | |
| }, | |
| { | |
| "epoch": 0.26, | |
| "eval_accuracy": 0.9977777777777778, | |
| "eval_f1": 0.9977738201246661, | |
| "eval_loss": 0.0159127339720726, | |
| "eval_precision": 0.9995539696699376, | |
| "eval_recall": 0.996, | |
| "eval_runtime": 52.8265, | |
| "eval_samples_per_second": 85.184, | |
| "eval_steps_per_second": 10.658, | |
| "step": 676 | |
| }, | |
| { | |
| "epoch": 0.28, | |
| "learning_rate": 3.6133333333333335e-05, | |
| "loss": 0.0002, | |
| "step": 728 | |
| }, | |
| { | |
| "epoch": 0.28, | |
| "eval_accuracy": 0.9977777777777778, | |
| "eval_f1": 0.9977738201246661, | |
| "eval_loss": 0.019492752850055695, | |
| "eval_precision": 0.9995539696699376, | |
| "eval_recall": 0.996, | |
| "eval_runtime": 52.6759, | |
| "eval_samples_per_second": 85.428, | |
| "eval_steps_per_second": 10.688, | |
| "step": 728 | |
| }, | |
| { | |
| "epoch": 0.3, | |
| "learning_rate": 3.514285714285714e-05, | |
| "loss": 0.0001, | |
| "step": 780 | |
| }, | |
| { | |
| "epoch": 0.3, | |
| "eval_accuracy": 0.9977777777777778, | |
| "eval_f1": 0.9977738201246661, | |
| "eval_loss": 0.020457539707422256, | |
| "eval_precision": 0.9995539696699376, | |
| "eval_recall": 0.996, | |
| "eval_runtime": 53.9153, | |
| "eval_samples_per_second": 83.464, | |
| "eval_steps_per_second": 10.442, | |
| "step": 780 | |
| }, | |
| { | |
| "epoch": 0.32, | |
| "learning_rate": 3.415238095238095e-05, | |
| "loss": 0.0376, | |
| "step": 832 | |
| }, | |
| { | |
| "epoch": 0.32, | |
| "eval_accuracy": 0.9975555555555555, | |
| "eval_f1": 0.9975506568692942, | |
| "eval_loss": 0.017426395788788795, | |
| "eval_precision": 0.999553770638108, | |
| "eval_recall": 0.9955555555555555, | |
| "eval_runtime": 52.8865, | |
| "eval_samples_per_second": 85.088, | |
| "eval_steps_per_second": 10.645, | |
| "step": 832 | |
| }, | |
| { | |
| "epoch": 0.34, | |
| "learning_rate": 3.316190476190476e-05, | |
| "loss": 0.0003, | |
| "step": 884 | |
| }, | |
| { | |
| "epoch": 0.34, | |
| "eval_accuracy": 0.9915555555555555, | |
| "eval_f1": 0.9916114790286976, | |
| "eval_loss": 0.07331586629152298, | |
| "eval_precision": 0.9850877192982456, | |
| "eval_recall": 0.9982222222222222, | |
| "eval_runtime": 52.7607, | |
| "eval_samples_per_second": 85.291, | |
| "eval_steps_per_second": 10.671, | |
| "step": 884 | |
| }, | |
| { | |
| "epoch": 0.36, | |
| "learning_rate": 3.217142857142858e-05, | |
| "loss": 0.0386, | |
| "step": 936 | |
| }, | |
| { | |
| "epoch": 0.36, | |
| "eval_accuracy": 0.9977777777777778, | |
| "eval_f1": 0.997774810858923, | |
| "eval_loss": 0.01634088158607483, | |
| "eval_precision": 0.9991087344028521, | |
| "eval_recall": 0.9964444444444445, | |
| "eval_runtime": 52.7493, | |
| "eval_samples_per_second": 85.309, | |
| "eval_steps_per_second": 10.673, | |
| "step": 936 | |
| }, | |
| { | |
| "epoch": 0.38, | |
| "learning_rate": 3.1180952380952384e-05, | |
| "loss": 0.0189, | |
| "step": 988 | |
| }, | |
| { | |
| "epoch": 0.38, | |
| "eval_accuracy": 0.996, | |
| "eval_f1": 0.9960035523978685, | |
| "eval_loss": 0.017804233357310295, | |
| "eval_precision": 0.9951197870452528, | |
| "eval_recall": 0.9968888888888889, | |
| "eval_runtime": 53.7392, | |
| "eval_samples_per_second": 83.738, | |
| "eval_steps_per_second": 10.477, | |
| "step": 988 | |
| }, | |
| { | |
| "epoch": 0.4, | |
| "learning_rate": 3.019047619047619e-05, | |
| "loss": 0.0087, | |
| "step": 1040 | |
| }, | |
| { | |
| "epoch": 0.4, | |
| "eval_accuracy": 0.9962222222222222, | |
| "eval_f1": 0.9962230615418795, | |
| "eval_loss": 0.027117114514112473, | |
| "eval_precision": 0.9960017769880053, | |
| "eval_recall": 0.9964444444444445, | |
| "eval_runtime": 52.7187, | |
| "eval_samples_per_second": 85.359, | |
| "eval_steps_per_second": 10.679, | |
| "step": 1040 | |
| }, | |
| { | |
| "epoch": 0.42, | |
| "learning_rate": 2.9199999999999998e-05, | |
| "loss": 0.0003, | |
| "step": 1092 | |
| }, | |
| { | |
| "epoch": 0.42, | |
| "eval_accuracy": 0.9942222222222222, | |
| "eval_f1": 0.994188645507376, | |
| "eval_loss": 0.04296413064002991, | |
| "eval_precision": 1.0, | |
| "eval_recall": 0.9884444444444445, | |
| "eval_runtime": 53.6263, | |
| "eval_samples_per_second": 83.914, | |
| "eval_steps_per_second": 10.499, | |
| "step": 1092 | |
| }, | |
| { | |
| "epoch": 0.44, | |
| "learning_rate": 2.8209523809523812e-05, | |
| "loss": 0.0783, | |
| "step": 1144 | |
| }, | |
| { | |
| "epoch": 0.44, | |
| "eval_accuracy": 0.9737777777777777, | |
| "eval_f1": 0.9744367417677643, | |
| "eval_loss": 0.18719656765460968, | |
| "eval_precision": 0.9505494505494505, | |
| "eval_recall": 0.9995555555555555, | |
| "eval_runtime": 54.0229, | |
| "eval_samples_per_second": 83.298, | |
| "eval_steps_per_second": 10.422, | |
| "step": 1144 | |
| }, | |
| { | |
| "epoch": 0.46, | |
| "learning_rate": 2.7219047619047623e-05, | |
| "loss": 0.0383, | |
| "step": 1196 | |
| }, | |
| { | |
| "epoch": 0.46, | |
| "eval_accuracy": 0.9971111111111111, | |
| "eval_f1": 0.9971104689931096, | |
| "eval_loss": 0.020702555775642395, | |
| "eval_precision": 0.997332147621165, | |
| "eval_recall": 0.9968888888888889, | |
| "eval_runtime": 52.7011, | |
| "eval_samples_per_second": 85.387, | |
| "eval_steps_per_second": 10.683, | |
| "step": 1196 | |
| }, | |
| { | |
| "epoch": 0.48, | |
| "learning_rate": 2.622857142857143e-05, | |
| "loss": 0.0674, | |
| "step": 1248 | |
| }, | |
| { | |
| "epoch": 0.48, | |
| "eval_accuracy": 0.9973333333333333, | |
| "eval_f1": 0.9973262032085561, | |
| "eval_loss": 0.01964743435382843, | |
| "eval_precision": 1.0, | |
| "eval_recall": 0.9946666666666667, | |
| "eval_runtime": 52.7411, | |
| "eval_samples_per_second": 85.322, | |
| "eval_steps_per_second": 10.675, | |
| "step": 1248 | |
| }, | |
| { | |
| "epoch": 0.5, | |
| "learning_rate": 2.523809523809524e-05, | |
| "loss": 0.0619, | |
| "step": 1300 | |
| }, | |
| { | |
| "epoch": 0.5, | |
| "eval_accuracy": 0.9973333333333333, | |
| "eval_f1": 0.9973273942093541, | |
| "eval_loss": 0.021862877532839775, | |
| "eval_precision": 0.9995535714285714, | |
| "eval_recall": 0.9951111111111111, | |
| "eval_runtime": 52.7015, | |
| "eval_samples_per_second": 85.387, | |
| "eval_steps_per_second": 10.683, | |
| "step": 1300 | |
| }, | |
| { | |
| "epoch": 0.52, | |
| "learning_rate": 2.424761904761905e-05, | |
| "loss": 0.0208, | |
| "step": 1352 | |
| }, | |
| { | |
| "epoch": 0.52, | |
| "eval_accuracy": 0.9973333333333333, | |
| "eval_f1": 0.9973297730307076, | |
| "eval_loss": 0.01971598155796528, | |
| "eval_precision": 0.9986631016042781, | |
| "eval_recall": 0.996, | |
| "eval_runtime": 53.8268, | |
| "eval_samples_per_second": 83.602, | |
| "eval_steps_per_second": 10.459, | |
| "step": 1352 | |
| }, | |
| { | |
| "epoch": 0.53, | |
| "learning_rate": 2.3257142857142858e-05, | |
| "loss": 0.0407, | |
| "step": 1404 | |
| }, | |
| { | |
| "epoch": 0.53, | |
| "eval_accuracy": 0.9973333333333333, | |
| "eval_f1": 0.9973309608540925, | |
| "eval_loss": 0.01426586601883173, | |
| "eval_precision": 0.9982190560997328, | |
| "eval_recall": 0.9964444444444445, | |
| "eval_runtime": 53.9464, | |
| "eval_samples_per_second": 83.416, | |
| "eval_steps_per_second": 10.436, | |
| "step": 1404 | |
| }, | |
| { | |
| "epoch": 0.55, | |
| "learning_rate": 2.2266666666666668e-05, | |
| "loss": 0.0003, | |
| "step": 1456 | |
| }, | |
| { | |
| "epoch": 0.55, | |
| "eval_accuracy": 0.9973333333333333, | |
| "eval_f1": 0.9973309608540925, | |
| "eval_loss": 0.01685367338359356, | |
| "eval_precision": 0.9982190560997328, | |
| "eval_recall": 0.9964444444444445, | |
| "eval_runtime": 54.279, | |
| "eval_samples_per_second": 82.905, | |
| "eval_steps_per_second": 10.372, | |
| "step": 1456 | |
| }, | |
| { | |
| "epoch": 0.57, | |
| "learning_rate": 2.127619047619048e-05, | |
| "loss": 0.0185, | |
| "step": 1508 | |
| }, | |
| { | |
| "epoch": 0.57, | |
| "eval_accuracy": 0.9973333333333333, | |
| "eval_f1": 0.9973273942093541, | |
| "eval_loss": 0.018773263320326805, | |
| "eval_precision": 0.9995535714285714, | |
| "eval_recall": 0.9951111111111111, | |
| "eval_runtime": 54.1737, | |
| "eval_samples_per_second": 83.066, | |
| "eval_steps_per_second": 10.393, | |
| "step": 1508 | |
| }, | |
| { | |
| "epoch": 0.59, | |
| "learning_rate": 2.0285714285714286e-05, | |
| "loss": 0.0334, | |
| "step": 1560 | |
| }, | |
| { | |
| "epoch": 0.59, | |
| "eval_accuracy": 0.9977777777777778, | |
| "eval_f1": 0.9977738201246661, | |
| "eval_loss": 0.015659423545002937, | |
| "eval_precision": 0.9995539696699376, | |
| "eval_recall": 0.996, | |
| "eval_runtime": 54.2691, | |
| "eval_samples_per_second": 82.92, | |
| "eval_steps_per_second": 10.374, | |
| "step": 1560 | |
| }, | |
| { | |
| "epoch": 0.61, | |
| "learning_rate": 1.9295238095238096e-05, | |
| "loss": 0.0374, | |
| "step": 1612 | |
| }, | |
| { | |
| "epoch": 0.61, | |
| "eval_accuracy": 0.9913333333333333, | |
| "eval_f1": 0.9913774043776254, | |
| "eval_loss": 0.06105850636959076, | |
| "eval_precision": 0.9863616366036075, | |
| "eval_recall": 0.9964444444444445, | |
| "eval_runtime": 53.9747, | |
| "eval_samples_per_second": 83.372, | |
| "eval_steps_per_second": 10.431, | |
| "step": 1612 | |
| }, | |
| { | |
| "epoch": 0.63, | |
| "learning_rate": 1.8304761904761906e-05, | |
| "loss": 0.0332, | |
| "step": 1664 | |
| }, | |
| { | |
| "epoch": 0.63, | |
| "eval_accuracy": 0.9977777777777778, | |
| "eval_f1": 0.9977728285077951, | |
| "eval_loss": 0.017448944970965385, | |
| "eval_precision": 1.0, | |
| "eval_recall": 0.9955555555555555, | |
| "eval_runtime": 52.8918, | |
| "eval_samples_per_second": 85.079, | |
| "eval_steps_per_second": 10.644, | |
| "step": 1664 | |
| }, | |
| { | |
| "epoch": 0.65, | |
| "learning_rate": 1.7314285714285717e-05, | |
| "loss": 0.0003, | |
| "step": 1716 | |
| }, | |
| { | |
| "epoch": 0.65, | |
| "eval_accuracy": 0.9977777777777778, | |
| "eval_f1": 0.9977728285077951, | |
| "eval_loss": 0.018406476825475693, | |
| "eval_precision": 1.0, | |
| "eval_recall": 0.9955555555555555, | |
| "eval_runtime": 53.9635, | |
| "eval_samples_per_second": 83.39, | |
| "eval_steps_per_second": 10.433, | |
| "step": 1716 | |
| }, | |
| { | |
| "epoch": 0.67, | |
| "learning_rate": 1.6323809523809524e-05, | |
| "loss": 0.0542, | |
| "step": 1768 | |
| }, | |
| { | |
| "epoch": 0.67, | |
| "eval_accuracy": 0.9975555555555555, | |
| "eval_f1": 0.9975517471622524, | |
| "eval_loss": 0.013020477257668972, | |
| "eval_precision": 0.9991083370485956, | |
| "eval_recall": 0.996, | |
| "eval_runtime": 53.3551, | |
| "eval_samples_per_second": 84.341, | |
| "eval_steps_per_second": 10.552, | |
| "step": 1768 | |
| }, | |
| { | |
| "epoch": 0.69, | |
| "learning_rate": 1.5333333333333334e-05, | |
| "loss": 0.0354, | |
| "step": 1820 | |
| }, | |
| { | |
| "epoch": 0.69, | |
| "eval_accuracy": 0.9973333333333333, | |
| "eval_f1": 0.997332147621165, | |
| "eval_loss": 0.013979670591652393, | |
| "eval_precision": 0.9977758007117438, | |
| "eval_recall": 0.9968888888888889, | |
| "eval_runtime": 53.9647, | |
| "eval_samples_per_second": 83.388, | |
| "eval_steps_per_second": 10.433, | |
| "step": 1820 | |
| }, | |
| { | |
| "epoch": 0.71, | |
| "learning_rate": 1.4342857142857143e-05, | |
| "loss": 0.0003, | |
| "step": 1872 | |
| }, | |
| { | |
| "epoch": 0.71, | |
| "eval_accuracy": 0.9975555555555555, | |
| "eval_f1": 0.9975517471622524, | |
| "eval_loss": 0.016862161457538605, | |
| "eval_precision": 0.9991083370485956, | |
| "eval_recall": 0.996, | |
| "eval_runtime": 52.8464, | |
| "eval_samples_per_second": 85.152, | |
| "eval_steps_per_second": 10.654, | |
| "step": 1872 | |
| }, | |
| { | |
| "epoch": 0.73, | |
| "learning_rate": 1.3352380952380952e-05, | |
| "loss": 0.0052, | |
| "step": 1924 | |
| }, | |
| { | |
| "epoch": 0.73, | |
| "eval_accuracy": 0.9977777777777778, | |
| "eval_f1": 0.9977738201246661, | |
| "eval_loss": 0.01669122278690338, | |
| "eval_precision": 0.9995539696699376, | |
| "eval_recall": 0.996, | |
| "eval_runtime": 52.8849, | |
| "eval_samples_per_second": 85.09, | |
| "eval_steps_per_second": 10.646, | |
| "step": 1924 | |
| }, | |
| { | |
| "epoch": 0.75, | |
| "learning_rate": 1.2361904761904762e-05, | |
| "loss": 0.0001, | |
| "step": 1976 | |
| }, | |
| { | |
| "epoch": 0.75, | |
| "eval_accuracy": 0.9977777777777778, | |
| "eval_f1": 0.9977738201246661, | |
| "eval_loss": 0.016820691525936127, | |
| "eval_precision": 0.9995539696699376, | |
| "eval_recall": 0.996, | |
| "eval_runtime": 53.752, | |
| "eval_samples_per_second": 83.718, | |
| "eval_steps_per_second": 10.474, | |
| "step": 1976 | |
| }, | |
| { | |
| "epoch": 0.77, | |
| "learning_rate": 1.1371428571428571e-05, | |
| "loss": 0.0001, | |
| "step": 2028 | |
| }, | |
| { | |
| "epoch": 0.77, | |
| "eval_accuracy": 0.9977777777777778, | |
| "eval_f1": 0.9977738201246661, | |
| "eval_loss": 0.017111966386437416, | |
| "eval_precision": 0.9995539696699376, | |
| "eval_recall": 0.996, | |
| "eval_runtime": 53.4254, | |
| "eval_samples_per_second": 84.23, | |
| "eval_steps_per_second": 10.538, | |
| "step": 2028 | |
| }, | |
| { | |
| "epoch": 0.79, | |
| "learning_rate": 1.0380952380952382e-05, | |
| "loss": 0.0001, | |
| "step": 2080 | |
| }, | |
| { | |
| "epoch": 0.79, | |
| "eval_accuracy": 0.9977777777777778, | |
| "eval_f1": 0.9977738201246661, | |
| "eval_loss": 0.017430588603019714, | |
| "eval_precision": 0.9995539696699376, | |
| "eval_recall": 0.996, | |
| "eval_runtime": 54.0709, | |
| "eval_samples_per_second": 83.224, | |
| "eval_steps_per_second": 10.412, | |
| "step": 2080 | |
| }, | |
| { | |
| "epoch": 0.81, | |
| "learning_rate": 9.39047619047619e-06, | |
| "loss": 0.0545, | |
| "step": 2132 | |
| }, | |
| { | |
| "epoch": 0.81, | |
| "eval_accuracy": 0.9973333333333333, | |
| "eval_f1": 0.997335701598579, | |
| "eval_loss": 0.016096895560622215, | |
| "eval_precision": 0.9964507542147294, | |
| "eval_recall": 0.9982222222222222, | |
| "eval_runtime": 52.7688, | |
| "eval_samples_per_second": 85.278, | |
| "eval_steps_per_second": 10.669, | |
| "step": 2132 | |
| }, | |
| { | |
| "epoch": 0.83, | |
| "learning_rate": 8.400000000000001e-06, | |
| "loss": 0.0006, | |
| "step": 2184 | |
| }, | |
| { | |
| "epoch": 0.83, | |
| "eval_accuracy": 0.9977777777777778, | |
| "eval_f1": 0.997774810858923, | |
| "eval_loss": 0.013929061591625214, | |
| "eval_precision": 0.9991087344028521, | |
| "eval_recall": 0.9964444444444445, | |
| "eval_runtime": 54.6395, | |
| "eval_samples_per_second": 82.358, | |
| "eval_steps_per_second": 10.304, | |
| "step": 2184 | |
| }, | |
| { | |
| "epoch": 0.85, | |
| "learning_rate": 7.40952380952381e-06, | |
| "loss": 0.0208, | |
| "step": 2236 | |
| }, | |
| { | |
| "epoch": 0.85, | |
| "eval_accuracy": 0.998, | |
| "eval_f1": 0.9979959919839679, | |
| "eval_loss": 0.015503444708883762, | |
| "eval_precision": 1.0, | |
| "eval_recall": 0.996, | |
| "eval_runtime": 52.9508, | |
| "eval_samples_per_second": 84.984, | |
| "eval_steps_per_second": 10.633, | |
| "step": 2236 | |
| }, | |
| { | |
| "epoch": 0.87, | |
| "learning_rate": 6.419047619047619e-06, | |
| "loss": 0.0204, | |
| "step": 2288 | |
| }, | |
| { | |
| "epoch": 0.87, | |
| "eval_accuracy": 0.998, | |
| "eval_f1": 0.9979959919839679, | |
| "eval_loss": 0.014153528958559036, | |
| "eval_precision": 1.0, | |
| "eval_recall": 0.996, | |
| "eval_runtime": 52.7536, | |
| "eval_samples_per_second": 85.302, | |
| "eval_steps_per_second": 10.672, | |
| "step": 2288 | |
| }, | |
| { | |
| "epoch": 0.89, | |
| "learning_rate": 5.428571428571429e-06, | |
| "loss": 0.0129, | |
| "step": 2340 | |
| }, | |
| { | |
| "epoch": 0.89, | |
| "eval_accuracy": 0.998, | |
| "eval_f1": 0.997996884041843, | |
| "eval_loss": 0.012016250751912594, | |
| "eval_precision": 0.9995541685242978, | |
| "eval_recall": 0.9964444444444445, | |
| "eval_runtime": 52.656, | |
| "eval_samples_per_second": 85.46, | |
| "eval_steps_per_second": 10.692, | |
| "step": 2340 | |
| }, | |
| { | |
| "epoch": 0.91, | |
| "learning_rate": 4.4380952380952385e-06, | |
| "loss": 0.0157, | |
| "step": 2392 | |
| }, | |
| { | |
| "epoch": 0.91, | |
| "eval_accuracy": 0.9975555555555555, | |
| "eval_f1": 0.9975528364849834, | |
| "eval_loss": 0.012594416737556458, | |
| "eval_precision": 0.9986636971046771, | |
| "eval_recall": 0.9964444444444445, | |
| "eval_runtime": 53.7606, | |
| "eval_samples_per_second": 83.704, | |
| "eval_steps_per_second": 10.472, | |
| "step": 2392 | |
| }, | |
| { | |
| "epoch": 0.93, | |
| "learning_rate": 3.4476190476190472e-06, | |
| "loss": 0.0147, | |
| "step": 2444 | |
| }, | |
| { | |
| "epoch": 0.93, | |
| "eval_accuracy": 0.9973333333333333, | |
| "eval_f1": 0.9973309608540925, | |
| "eval_loss": 0.011972985230386257, | |
| "eval_precision": 0.9982190560997328, | |
| "eval_recall": 0.9964444444444445, | |
| "eval_runtime": 52.7147, | |
| "eval_samples_per_second": 85.365, | |
| "eval_steps_per_second": 10.68, | |
| "step": 2444 | |
| }, | |
| { | |
| "epoch": 0.95, | |
| "learning_rate": 2.4571428571428573e-06, | |
| "loss": 0.0115, | |
| "step": 2496 | |
| }, | |
| { | |
| "epoch": 0.95, | |
| "eval_accuracy": 0.9973333333333333, | |
| "eval_f1": 0.9973309608540925, | |
| "eval_loss": 0.01194427628070116, | |
| "eval_precision": 0.9982190560997328, | |
| "eval_recall": 0.9964444444444445, | |
| "eval_runtime": 55.506, | |
| "eval_samples_per_second": 81.072, | |
| "eval_steps_per_second": 10.143, | |
| "step": 2496 | |
| }, | |
| { | |
| "epoch": 0.97, | |
| "learning_rate": 1.4666666666666667e-06, | |
| "loss": 0.0002, | |
| "step": 2548 | |
| }, | |
| { | |
| "epoch": 0.97, | |
| "eval_accuracy": 0.9973333333333333, | |
| "eval_f1": 0.9973309608540925, | |
| "eval_loss": 0.011756585910916328, | |
| "eval_precision": 0.9982190560997328, | |
| "eval_recall": 0.9964444444444445, | |
| "eval_runtime": 54.1036, | |
| "eval_samples_per_second": 83.174, | |
| "eval_steps_per_second": 10.406, | |
| "step": 2548 | |
| }, | |
| { | |
| "epoch": 0.99, | |
| "learning_rate": 4.761904761904763e-07, | |
| "loss": 0.0125, | |
| "step": 2600 | |
| }, | |
| { | |
| "epoch": 0.99, | |
| "eval_accuracy": 0.9973333333333333, | |
| "eval_f1": 0.9973309608540925, | |
| "eval_loss": 0.011715704575181007, | |
| "eval_precision": 0.9982190560997328, | |
| "eval_recall": 0.9964444444444445, | |
| "eval_runtime": 54.017, | |
| "eval_samples_per_second": 83.307, | |
| "eval_steps_per_second": 10.423, | |
| "step": 2600 | |
| } | |
| ], | |
| "max_steps": 2625, | |
| "num_train_epochs": 1, | |
| "total_flos": 5525332162560000.0, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |