| { | |
| "best_metric": 1.0, | |
| "best_model_checkpoint": "./saved-model-all-data/checkpoint-882", | |
| "epoch": 25.0, | |
| "global_step": 1575, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 1.0, | |
| "eval_accuracy": 0.8670662363608421, | |
| "eval_f1": 0.5017103762827823, | |
| "eval_loss": 0.42577993869781494, | |
| "eval_precision": 0.4592901878914405, | |
| "eval_recall": 0.5527638190954773, | |
| "eval_runtime": 0.6534, | |
| "eval_samples_per_second": 76.527, | |
| "eval_steps_per_second": 10.714, | |
| "step": 63 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "eval_accuracy": 0.9293069002612571, | |
| "eval_f1": 0.7072289156626506, | |
| "eval_loss": 0.22081975638866425, | |
| "eval_precision": 0.6793981481481481, | |
| "eval_recall": 0.7374371859296482, | |
| "eval_runtime": 0.5804, | |
| "eval_samples_per_second": 86.142, | |
| "eval_steps_per_second": 12.06, | |
| "step": 126 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "eval_accuracy": 0.9549715690794529, | |
| "eval_f1": 0.8209500609013398, | |
| "eval_loss": 0.13680364191532135, | |
| "eval_precision": 0.7966903073286052, | |
| "eval_recall": 0.8467336683417085, | |
| "eval_runtime": 0.5883, | |
| "eval_samples_per_second": 84.997, | |
| "eval_steps_per_second": 11.9, | |
| "step": 189 | |
| }, | |
| { | |
| "epoch": 4.0, | |
| "eval_accuracy": 0.9778699861687413, | |
| "eval_f1": 0.8866995073891626, | |
| "eval_loss": 0.07373423129320145, | |
| "eval_precision": 0.8695652173913043, | |
| "eval_recall": 0.9045226130653267, | |
| "eval_runtime": 0.6005, | |
| "eval_samples_per_second": 83.259, | |
| "eval_steps_per_second": 11.656, | |
| "step": 252 | |
| }, | |
| { | |
| "epoch": 5.0, | |
| "eval_accuracy": 0.9855540187490395, | |
| "eval_f1": 0.9316239316239316, | |
| "eval_loss": 0.04712964966893196, | |
| "eval_precision": 0.9061757719714965, | |
| "eval_recall": 0.9585427135678392, | |
| "eval_runtime": 0.6021, | |
| "eval_samples_per_second": 83.049, | |
| "eval_steps_per_second": 11.627, | |
| "step": 315 | |
| }, | |
| { | |
| "epoch": 6.0, | |
| "eval_accuracy": 0.9929306900261257, | |
| "eval_f1": 0.9652605459057072, | |
| "eval_loss": 0.02583940699696541, | |
| "eval_precision": 0.9534313725490197, | |
| "eval_recall": 0.9773869346733668, | |
| "eval_runtime": 0.5826, | |
| "eval_samples_per_second": 85.82, | |
| "eval_steps_per_second": 12.015, | |
| "step": 378 | |
| }, | |
| { | |
| "epoch": 7.0, | |
| "eval_accuracy": 0.9967727063162748, | |
| "eval_f1": 0.9849435382685068, | |
| "eval_loss": 0.015803957358002663, | |
| "eval_precision": 0.9837092731829574, | |
| "eval_recall": 0.9861809045226131, | |
| "eval_runtime": 0.5833, | |
| "eval_samples_per_second": 85.718, | |
| "eval_steps_per_second": 12.0, | |
| "step": 441 | |
| }, | |
| { | |
| "epoch": 7.94, | |
| "learning_rate": 3.644067796610169e-05, | |
| "loss": 0.268, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 8.0, | |
| "eval_accuracy": 0.9972337482710927, | |
| "eval_f1": 0.9880578252671276, | |
| "eval_loss": 0.012770027853548527, | |
| "eval_precision": 0.9886792452830189, | |
| "eval_recall": 0.9874371859296482, | |
| "eval_runtime": 0.5723, | |
| "eval_samples_per_second": 87.36, | |
| "eval_steps_per_second": 12.23, | |
| "step": 504 | |
| }, | |
| { | |
| "epoch": 9.0, | |
| "eval_accuracy": 0.9978484708775165, | |
| "eval_f1": 0.9861809045226131, | |
| "eval_loss": 0.008633743040263653, | |
| "eval_precision": 0.9861809045226131, | |
| "eval_recall": 0.9861809045226131, | |
| "eval_runtime": 0.5754, | |
| "eval_samples_per_second": 86.898, | |
| "eval_steps_per_second": 12.166, | |
| "step": 567 | |
| }, | |
| { | |
| "epoch": 10.0, | |
| "eval_accuracy": 0.9983095128323344, | |
| "eval_f1": 0.9899497487437185, | |
| "eval_loss": 0.006678320933133364, | |
| "eval_precision": 0.9899497487437185, | |
| "eval_recall": 0.9899497487437185, | |
| "eval_runtime": 0.5717, | |
| "eval_samples_per_second": 87.461, | |
| "eval_steps_per_second": 12.245, | |
| "step": 630 | |
| }, | |
| { | |
| "epoch": 11.0, | |
| "eval_accuracy": 0.9990779160903642, | |
| "eval_f1": 0.9962311557788944, | |
| "eval_loss": 0.004529367666691542, | |
| "eval_precision": 0.9962311557788944, | |
| "eval_recall": 0.9962311557788944, | |
| "eval_runtime": 0.5852, | |
| "eval_samples_per_second": 85.445, | |
| "eval_steps_per_second": 11.962, | |
| "step": 693 | |
| }, | |
| { | |
| "epoch": 12.0, | |
| "eval_accuracy": 0.999692638696788, | |
| "eval_f1": 0.9987437185929648, | |
| "eval_loss": 0.0013231054181233048, | |
| "eval_precision": 0.9987437185929648, | |
| "eval_recall": 0.9987437185929648, | |
| "eval_runtime": 0.5808, | |
| "eval_samples_per_second": 86.093, | |
| "eval_steps_per_second": 12.053, | |
| "step": 756 | |
| }, | |
| { | |
| "epoch": 13.0, | |
| "eval_accuracy": 0.9990779160903642, | |
| "eval_f1": 0.9956112852664577, | |
| "eval_loss": 0.0035528314765542746, | |
| "eval_precision": 0.9937421777221527, | |
| "eval_recall": 0.9974874371859297, | |
| "eval_runtime": 0.6108, | |
| "eval_samples_per_second": 81.86, | |
| "eval_steps_per_second": 11.46, | |
| "step": 819 | |
| }, | |
| { | |
| "epoch": 14.0, | |
| "eval_accuracy": 1.0, | |
| "eval_f1": 1.0, | |
| "eval_loss": 0.00045324634993448853, | |
| "eval_precision": 1.0, | |
| "eval_recall": 1.0, | |
| "eval_runtime": 0.5759, | |
| "eval_samples_per_second": 86.817, | |
| "eval_steps_per_second": 12.154, | |
| "step": 882 | |
| }, | |
| { | |
| "epoch": 15.0, | |
| "eval_accuracy": 1.0, | |
| "eval_f1": 1.0, | |
| "eval_loss": 0.00044708128552883863, | |
| "eval_precision": 1.0, | |
| "eval_recall": 1.0, | |
| "eval_runtime": 0.575, | |
| "eval_samples_per_second": 86.954, | |
| "eval_steps_per_second": 12.174, | |
| "step": 945 | |
| }, | |
| { | |
| "epoch": 15.87, | |
| "learning_rate": 1.9491525423728814e-05, | |
| "loss": 0.0097, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 16.0, | |
| "eval_accuracy": 1.0, | |
| "eval_f1": 1.0, | |
| "eval_loss": 0.00018117745639756322, | |
| "eval_precision": 1.0, | |
| "eval_recall": 1.0, | |
| "eval_runtime": 0.5823, | |
| "eval_samples_per_second": 85.872, | |
| "eval_steps_per_second": 12.022, | |
| "step": 1008 | |
| }, | |
| { | |
| "epoch": 17.0, | |
| "eval_accuracy": 1.0, | |
| "eval_f1": 1.0, | |
| "eval_loss": 0.00018171708506997675, | |
| "eval_precision": 1.0, | |
| "eval_recall": 1.0, | |
| "eval_runtime": 0.6909, | |
| "eval_samples_per_second": 72.373, | |
| "eval_steps_per_second": 10.132, | |
| "step": 1071 | |
| }, | |
| { | |
| "epoch": 18.0, | |
| "eval_accuracy": 1.0, | |
| "eval_f1": 1.0, | |
| "eval_loss": 0.0002043112035607919, | |
| "eval_precision": 1.0, | |
| "eval_recall": 1.0, | |
| "eval_runtime": 0.6068, | |
| "eval_samples_per_second": 82.399, | |
| "eval_steps_per_second": 11.536, | |
| "step": 1134 | |
| }, | |
| { | |
| "epoch": 19.0, | |
| "eval_accuracy": 1.0, | |
| "eval_f1": 1.0, | |
| "eval_loss": 0.00015518060536123812, | |
| "eval_precision": 1.0, | |
| "eval_recall": 1.0, | |
| "eval_runtime": 0.594, | |
| "eval_samples_per_second": 84.176, | |
| "eval_steps_per_second": 11.785, | |
| "step": 1197 | |
| }, | |
| { | |
| "epoch": 20.0, | |
| "eval_accuracy": 1.0, | |
| "eval_f1": 1.0, | |
| "eval_loss": 0.00014525999722536653, | |
| "eval_precision": 1.0, | |
| "eval_recall": 1.0, | |
| "eval_runtime": 0.5981, | |
| "eval_samples_per_second": 83.6, | |
| "eval_steps_per_second": 11.704, | |
| "step": 1260 | |
| }, | |
| { | |
| "epoch": 21.0, | |
| "eval_accuracy": 1.0, | |
| "eval_f1": 1.0, | |
| "eval_loss": 0.00013857503654435277, | |
| "eval_precision": 1.0, | |
| "eval_recall": 1.0, | |
| "eval_runtime": 0.5825, | |
| "eval_samples_per_second": 85.832, | |
| "eval_steps_per_second": 12.017, | |
| "step": 1323 | |
| }, | |
| { | |
| "epoch": 22.0, | |
| "eval_accuracy": 1.0, | |
| "eval_f1": 1.0, | |
| "eval_loss": 0.00013503569061867893, | |
| "eval_precision": 1.0, | |
| "eval_recall": 1.0, | |
| "eval_runtime": 0.573, | |
| "eval_samples_per_second": 87.267, | |
| "eval_steps_per_second": 12.217, | |
| "step": 1386 | |
| }, | |
| { | |
| "epoch": 23.0, | |
| "eval_accuracy": 1.0, | |
| "eval_f1": 1.0, | |
| "eval_loss": 0.00012487478670664132, | |
| "eval_precision": 1.0, | |
| "eval_recall": 1.0, | |
| "eval_runtime": 0.5904, | |
| "eval_samples_per_second": 84.687, | |
| "eval_steps_per_second": 11.856, | |
| "step": 1449 | |
| }, | |
| { | |
| "epoch": 23.81, | |
| "learning_rate": 2.5423728813559323e-06, | |
| "loss": 0.0019, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 24.0, | |
| "eval_accuracy": 1.0, | |
| "eval_f1": 1.0, | |
| "eval_loss": 0.00012091387179680169, | |
| "eval_precision": 1.0, | |
| "eval_recall": 1.0, | |
| "eval_runtime": 0.5792, | |
| "eval_samples_per_second": 86.322, | |
| "eval_steps_per_second": 12.085, | |
| "step": 1512 | |
| }, | |
| { | |
| "epoch": 25.0, | |
| "eval_accuracy": 1.0, | |
| "eval_f1": 1.0, | |
| "eval_loss": 0.00011829046707134694, | |
| "eval_precision": 1.0, | |
| "eval_recall": 1.0, | |
| "eval_runtime": 0.6205, | |
| "eval_samples_per_second": 80.581, | |
| "eval_steps_per_second": 11.281, | |
| "step": 1575 | |
| } | |
| ], | |
| "max_steps": 1575, | |
| "num_train_epochs": 25, | |
| "total_flos": 1550715696271320.0, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |