| { | |
| "best_metric": 1.1261494159698486, | |
| "best_model_checkpoint": "./outputs/checkpoint-32", | |
| "epoch": 1.0, | |
| "global_step": 32, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.31, | |
| "learning_rate": 1.375e-05, | |
| "loss": 1.3798, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.62, | |
| "learning_rate": 7.500000000000001e-06, | |
| "loss": 1.2247, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.94, | |
| "learning_rate": 1.25e-06, | |
| "loss": 1.1396, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "eval_loss": 1.1261494159698486, | |
| "eval_runtime": 365.6189, | |
| "eval_samples_per_second": 62.94, | |
| "eval_steps_per_second": 1.969, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "step": 32, | |
| "total_flos": 7.8026085236736e+16, | |
| "train_loss": 1.2410431504249573, | |
| "train_runtime": 414.7473, | |
| "train_samples_per_second": 2.411, | |
| "train_steps_per_second": 0.077 | |
| } | |
| ], | |
| "max_steps": 32, | |
| "num_train_epochs": 1, | |
| "total_flos": 7.8026085236736e+16, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |