| { | |
| "best_metric": 0.07052170485258102, | |
| "best_model_checkpoint": "token_level_model/best_model/checkpoint-948", | |
| "epoch": 12.0, | |
| "global_step": 3792, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 1.0, | |
| "eval_balanced accuracy": 0.5633085631676005, | |
| "eval_f1": 0.5303163390780957, | |
| "eval_loss": 0.09163307398557663, | |
| "eval_precision": 0.6548165588282941, | |
| "eval_recall": 0.5633085631676005, | |
| "eval_runtime": 5.3367, | |
| "eval_samples_per_second": 236.852, | |
| "eval_steps_per_second": 14.803, | |
| "step": 316 | |
| }, | |
| { | |
| "epoch": 1.58, | |
| "learning_rate": 1.7362869198312237e-05, | |
| "loss": 0.1839, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "eval_balanced accuracy": 0.7195902052549533, | |
| "eval_f1": 0.7255288809894066, | |
| "eval_loss": 0.0722324550151825, | |
| "eval_precision": 0.7454575741625619, | |
| "eval_recall": 0.7195902052549533, | |
| "eval_runtime": 5.3534, | |
| "eval_samples_per_second": 236.111, | |
| "eval_steps_per_second": 14.757, | |
| "step": 632 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "eval_balanced accuracy": 0.7147400555506803, | |
| "eval_f1": 0.7192305114894215, | |
| "eval_loss": 0.07052170485258102, | |
| "eval_precision": 0.7756273409712318, | |
| "eval_recall": 0.7147400555506803, | |
| "eval_runtime": 5.4755, | |
| "eval_samples_per_second": 230.847, | |
| "eval_steps_per_second": 14.428, | |
| "step": 948 | |
| }, | |
| { | |
| "epoch": 3.16, | |
| "learning_rate": 1.4725738396624474e-05, | |
| "loss": 0.0587, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 4.0, | |
| "eval_balanced accuracy": 0.7295185936273012, | |
| "eval_f1": 0.7296703416168215, | |
| "eval_loss": 0.07182055711746216, | |
| "eval_precision": 0.7401045017667032, | |
| "eval_recall": 0.7295185936273012, | |
| "eval_runtime": 5.3937, | |
| "eval_samples_per_second": 234.345, | |
| "eval_steps_per_second": 14.647, | |
| "step": 1264 | |
| }, | |
| { | |
| "epoch": 4.75, | |
| "learning_rate": 1.208860759493671e-05, | |
| "loss": 0.0376, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 5.0, | |
| "eval_balanced accuracy": 0.735330002568732, | |
| "eval_f1": 0.743746101471838, | |
| "eval_loss": 0.07561135292053223, | |
| "eval_precision": 0.758929084908083, | |
| "eval_recall": 0.735330002568732, | |
| "eval_runtime": 5.5304, | |
| "eval_samples_per_second": 228.555, | |
| "eval_steps_per_second": 14.285, | |
| "step": 1580 | |
| }, | |
| { | |
| "epoch": 6.0, | |
| "eval_balanced accuracy": 0.7487913019838482, | |
| "eval_f1": 0.7539294881409199, | |
| "eval_loss": 0.08333344757556915, | |
| "eval_precision": 0.7640729935139194, | |
| "eval_recall": 0.7487913019838482, | |
| "eval_runtime": 5.304, | |
| "eval_samples_per_second": 238.312, | |
| "eval_steps_per_second": 14.894, | |
| "step": 1896 | |
| }, | |
| { | |
| "epoch": 6.33, | |
| "learning_rate": 9.451476793248946e-06, | |
| "loss": 0.0239, | |
| "step": 2000 | |
| }, | |
| { | |
| "epoch": 7.0, | |
| "eval_balanced accuracy": 0.7495077050154062, | |
| "eval_f1": 0.7547220689413356, | |
| "eval_loss": 0.09176070988178253, | |
| "eval_precision": 0.7680132999431392, | |
| "eval_recall": 0.7495077050154062, | |
| "eval_runtime": 5.4894, | |
| "eval_samples_per_second": 230.262, | |
| "eval_steps_per_second": 14.391, | |
| "step": 2212 | |
| }, | |
| { | |
| "epoch": 7.91, | |
| "learning_rate": 6.814345991561182e-06, | |
| "loss": 0.0161, | |
| "step": 2500 | |
| }, | |
| { | |
| "epoch": 8.0, | |
| "eval_balanced accuracy": 0.7519480763726148, | |
| "eval_f1": 0.7441340002103095, | |
| "eval_loss": 0.10090441256761551, | |
| "eval_precision": 0.7421918161304624, | |
| "eval_recall": 0.7519480763726148, | |
| "eval_runtime": 5.4772, | |
| "eval_samples_per_second": 230.774, | |
| "eval_steps_per_second": 14.423, | |
| "step": 2528 | |
| }, | |
| { | |
| "epoch": 9.0, | |
| "eval_balanced accuracy": 0.7372305744818235, | |
| "eval_f1": 0.7418663358868686, | |
| "eval_loss": 0.10627683997154236, | |
| "eval_precision": 0.747694948865169, | |
| "eval_recall": 0.7372305744818235, | |
| "eval_runtime": 5.673, | |
| "eval_samples_per_second": 222.809, | |
| "eval_steps_per_second": 13.926, | |
| "step": 2844 | |
| }, | |
| { | |
| "epoch": 9.49, | |
| "learning_rate": 4.177215189873418e-06, | |
| "loss": 0.0107, | |
| "step": 3000 | |
| }, | |
| { | |
| "epoch": 10.0, | |
| "eval_balanced accuracy": 0.7454153105654866, | |
| "eval_f1": 0.7532278014935634, | |
| "eval_loss": 0.11291743814945221, | |
| "eval_precision": 0.7635910633921945, | |
| "eval_recall": 0.7454153105654866, | |
| "eval_runtime": 5.7497, | |
| "eval_samples_per_second": 219.839, | |
| "eval_steps_per_second": 13.74, | |
| "step": 3160 | |
| }, | |
| { | |
| "epoch": 11.0, | |
| "eval_balanced accuracy": 0.7422514651185799, | |
| "eval_f1": 0.7462413455365297, | |
| "eval_loss": 0.11802595853805542, | |
| "eval_precision": 0.7518280300030182, | |
| "eval_recall": 0.7422514651185799, | |
| "eval_runtime": 5.6277, | |
| "eval_samples_per_second": 224.602, | |
| "eval_steps_per_second": 14.038, | |
| "step": 3476 | |
| }, | |
| { | |
| "epoch": 11.08, | |
| "learning_rate": 1.5400843881856542e-06, | |
| "loss": 0.007, | |
| "step": 3500 | |
| }, | |
| { | |
| "epoch": 12.0, | |
| "eval_balanced accuracy": 0.7397630177088332, | |
| "eval_f1": 0.7454360643197575, | |
| "eval_loss": 0.11985792219638824, | |
| "eval_precision": 0.7526407260582226, | |
| "eval_recall": 0.7397630177088332, | |
| "eval_runtime": 5.7001, | |
| "eval_samples_per_second": 221.752, | |
| "eval_steps_per_second": 13.859, | |
| "step": 3792 | |
| } | |
| ], | |
| "max_steps": 3792, | |
| "num_train_epochs": 12, | |
| "total_flos": 302819736843288.0, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |