| { | |
| "best_metric": 0.9211038961038961, | |
| "best_model_checkpoint": "mpnet-metric/checkpoint-600", | |
| "epoch": 13.636363636363637, | |
| "global_step": 600, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 2.27, | |
| "eval_accuracy": 0.8418831168831169, | |
| "eval_f1": 0.8027962745185904, | |
| "eval_loss": 1.4791860580444336, | |
| "eval_matthews_correlation": 0.8403536839300481, | |
| "eval_runtime": 2.0893, | |
| "eval_samples_per_second": 1474.144, | |
| "eval_steps_per_second": 9.572, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 4.55, | |
| "eval_accuracy": 0.9042207792207793, | |
| "eval_f1": 0.9047628877989691, | |
| "eval_loss": 1.487802267074585, | |
| "eval_matthews_correlation": 0.9030870359405524, | |
| "eval_runtime": 2.1548, | |
| "eval_samples_per_second": 1429.39, | |
| "eval_steps_per_second": 9.282, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 6.82, | |
| "eval_accuracy": 0.9172077922077922, | |
| "eval_f1": 0.9169016425995938, | |
| "eval_loss": 1.6755403280258179, | |
| "eval_matthews_correlation": 0.9161647270846853, | |
| "eval_runtime": 2.1745, | |
| "eval_samples_per_second": 1416.389, | |
| "eval_steps_per_second": 9.197, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 9.09, | |
| "eval_accuracy": 0.9123376623376623, | |
| "eval_f1": 0.9128534869153119, | |
| "eval_loss": 1.6229037046432495, | |
| "eval_matthews_correlation": 0.9111753584333115, | |
| "eval_runtime": 2.0543, | |
| "eval_samples_per_second": 1499.327, | |
| "eval_steps_per_second": 9.736, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 11.36, | |
| "learning_rate": 5.2705340156346366e-05, | |
| "loss": 1.1094, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 11.36, | |
| "eval_accuracy": 0.9172077922077922, | |
| "eval_f1": 0.9150003521466267, | |
| "eval_loss": 1.6902168989181519, | |
| "eval_matthews_correlation": 0.916107308697779, | |
| "eval_runtime": 2.1005, | |
| "eval_samples_per_second": 1466.292, | |
| "eval_steps_per_second": 9.521, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 13.64, | |
| "eval_accuracy": 0.9211038961038961, | |
| "eval_f1": 0.9217190641997036, | |
| "eval_loss": 1.809704065322876, | |
| "eval_matthews_correlation": 0.9200266092875187, | |
| "eval_runtime": 2.1893, | |
| "eval_samples_per_second": 1406.863, | |
| "eval_steps_per_second": 9.135, | |
| "step": 600 | |
| } | |
| ], | |
| "max_steps": 1760, | |
| "num_train_epochs": 40, | |
| "total_flos": 3134913031624572.0, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |