| { | |
| "best_metric": 0.4304260866765428, | |
| "best_model_checkpoint": "hw-01-finetuned-cola/run-2/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": 0.23, | |
| "learning_rate": 4.717583231684137e-06, | |
| "loss": 0.5783, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 0.47, | |
| "learning_rate": 4.318734463364544e-06, | |
| "loss": 0.5628, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 0.7, | |
| "learning_rate": 3.919885695044952e-06, | |
| "loss": 0.5371, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 0.94, | |
| "learning_rate": 3.52103692672536e-06, | |
| "loss": 0.5214, | |
| "step": 2000 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "eval_loss": 0.5808761715888977, | |
| "eval_matthews_correlation": 0.4304260866765428, | |
| "eval_runtime": 0.7545, | |
| "eval_samples_per_second": 1382.293, | |
| "eval_steps_per_second": 87.47, | |
| "step": 2138 | |
| } | |
| ], | |
| "logging_steps": 500, | |
| "max_steps": 6414, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 3, | |
| "save_steps": 500, | |
| "total_flos": 32649074162496.0, | |
| "train_batch_size": 4, | |
| "trial_name": null, | |
| "trial_params": { | |
| "learning_rate": 5.1164320000037285e-06, | |
| "num_train_epochs": 3, | |
| "per_device_train_batch_size": 4, | |
| "seed": 26 | |
| } | |
| } | |