| { | |
| "best_metric": 0.3296754174940789, | |
| "best_model_checkpoint": "distilbert-base-uncased-finetuned-cola/run-3/checkpoint-2138", | |
| "epoch": 1.0, | |
| "eval_steps": 500, | |
| "global_step": 2138, | |
| "is_hyper_param_search": true, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.23386342376052385, | |
| "grad_norm": 3.277184009552002, | |
| "learning_rate": 4.2343189505455224e-05, | |
| "loss": 0.6317, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 0.4677268475210477, | |
| "grad_norm": 3.041562795639038, | |
| "learning_rate": 2.9417917983643493e-05, | |
| "loss": 0.6069, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 0.7015902712815716, | |
| "grad_norm": 5.285711765289307, | |
| "learning_rate": 1.6492646461831766e-05, | |
| "loss": 0.5833, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 0.9354536950420954, | |
| "grad_norm": 13.721405982971191, | |
| "learning_rate": 3.5673749400200375e-06, | |
| "loss": 0.5335, | |
| "step": 2000 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "eval_loss": 0.611344575881958, | |
| "eval_matthews_correlation": 0.3296754174940789, | |
| "eval_runtime": 29.4461, | |
| "eval_samples_per_second": 35.421, | |
| "eval_steps_per_second": 2.241, | |
| "step": 2138 | |
| } | |
| ], | |
| "logging_steps": 500, | |
| "max_steps": 2138, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 500, | |
| "total_flos": 32604573395760.0, | |
| "train_batch_size": 4, | |
| "trial_name": null, | |
| "trial_params": { | |
| "learning_rate": 5.5268461027266954e-05, | |
| "num_train_epochs": 1, | |
| "per_device_train_batch_size": 4, | |
| "seed": 6 | |
| } | |
| } | |