| { | |
| "best_metric": 0.5425688103069501, | |
| "best_model_checkpoint": "distilbert-base-uncased-finetuned-cola/run-2/checkpoint-402", | |
| "epoch": 4.0, | |
| "eval_steps": 500, | |
| "global_step": 536, | |
| "is_hyper_param_search": true, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 1.0, | |
| "eval_loss": 0.47476544976234436, | |
| "eval_matthews_correlation": 0.45140096820158837, | |
| "eval_runtime": 0.7004, | |
| "eval_samples_per_second": 1489.214, | |
| "eval_steps_per_second": 94.236, | |
| "step": 134 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "eval_loss": 0.47363194823265076, | |
| "eval_matthews_correlation": 0.49626557567073315, | |
| "eval_runtime": 1.2181, | |
| "eval_samples_per_second": 856.246, | |
| "eval_steps_per_second": 54.182, | |
| "step": 268 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "eval_loss": 0.5049272775650024, | |
| "eval_matthews_correlation": 0.5425688103069501, | |
| "eval_runtime": 0.7884, | |
| "eval_samples_per_second": 1322.911, | |
| "eval_steps_per_second": 83.712, | |
| "step": 402 | |
| }, | |
| { | |
| "epoch": 3.73, | |
| "grad_norm": 6.596341133117676, | |
| "learning_rate": 1.9834803529148066e-06, | |
| "loss": 0.3452, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 4.0, | |
| "eval_loss": 0.5818902254104614, | |
| "eval_matthews_correlation": 0.49626557567073315, | |
| "eval_runtime": 0.8031, | |
| "eval_samples_per_second": 1298.797, | |
| "eval_steps_per_second": 82.187, | |
| "step": 536 | |
| } | |
| ], | |
| "logging_steps": 500, | |
| "max_steps": 536, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 4, | |
| "save_steps": 500, | |
| "total_flos": 209747119699272.0, | |
| "train_batch_size": 64, | |
| "trial_name": null, | |
| "trial_params": { | |
| "learning_rate": 2.9531818587842675e-05, | |
| "num_train_epochs": 4, | |
| "per_device_train_batch_size": 64, | |
| "seed": 38 | |
| } | |
| } | |