| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 5.0, | |
| "global_step": 60, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 1.0, | |
| "learning_rate": 1.6000000000000003e-05, | |
| "loss": 0.4916, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "eval_accuracy": 0.9361702127659575, | |
| "eval_f1": 0.9362281082645824, | |
| "eval_loss": 0.2990593910217285, | |
| "eval_precision": 0.9371338267036695, | |
| "eval_recall": 0.9361702127659575, | |
| "eval_runtime": 20.3046, | |
| "eval_samples_per_second": 2.315, | |
| "eval_steps_per_second": 0.148, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "learning_rate": 1.2e-05, | |
| "loss": 0.2834, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "eval_accuracy": 0.9574468085106383, | |
| "eval_f1": 0.957485353068147, | |
| "eval_loss": 0.1967730075120926, | |
| "eval_precision": 0.9609929078014184, | |
| "eval_recall": 0.9574468085106383, | |
| "eval_runtime": 21.6345, | |
| "eval_samples_per_second": 2.172, | |
| "eval_steps_per_second": 0.139, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "learning_rate": 8.000000000000001e-06, | |
| "loss": 0.185, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "eval_accuracy": 0.9574468085106383, | |
| "eval_f1": 0.957485353068147, | |
| "eval_loss": 0.15521566569805145, | |
| "eval_precision": 0.9609929078014184, | |
| "eval_recall": 0.9574468085106383, | |
| "eval_runtime": 19.4305, | |
| "eval_samples_per_second": 2.419, | |
| "eval_steps_per_second": 0.154, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 4.0, | |
| "learning_rate": 4.000000000000001e-06, | |
| "loss": 0.1162, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 4.0, | |
| "eval_accuracy": 0.9787234042553191, | |
| "eval_f1": 0.9787427027548607, | |
| "eval_loss": 0.09382404386997223, | |
| "eval_precision": 0.9796484736355227, | |
| "eval_recall": 0.9787234042553191, | |
| "eval_runtime": 20.1514, | |
| "eval_samples_per_second": 2.332, | |
| "eval_steps_per_second": 0.149, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 5.0, | |
| "learning_rate": 0.0, | |
| "loss": 0.0842, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 5.0, | |
| "eval_accuracy": 0.9787234042553191, | |
| "eval_f1": 0.9787427027548607, | |
| "eval_loss": 0.09307459741830826, | |
| "eval_precision": 0.9796484736355227, | |
| "eval_recall": 0.9787234042553191, | |
| "eval_runtime": 22.1003, | |
| "eval_samples_per_second": 2.127, | |
| "eval_steps_per_second": 0.136, | |
| "step": 60 | |
| } | |
| ], | |
| "max_steps": 60, | |
| "num_train_epochs": 5, | |
| "total_flos": 60515542732800.0, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |