| { | |
| "best_metric": 2.2600128650665283, | |
| "best_model_checkpoint": "output/tanzy-minus/checkpoint-6", | |
| "epoch": 2.0, | |
| "global_step": 6, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 1.0, | |
| "eval_loss": 2.3025755882263184, | |
| "eval_runtime": 0.077, | |
| "eval_samples_per_second": 12.994, | |
| "eval_steps_per_second": 12.994, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 1.67, | |
| "learning_rate": 0.00010290000000000001, | |
| "loss": 2.2031, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "eval_loss": 2.2600128650665283, | |
| "eval_runtime": 0.0621, | |
| "eval_samples_per_second": 16.098, | |
| "eval_steps_per_second": 16.098, | |
| "step": 6 | |
| } | |
| ], | |
| "max_steps": 6, | |
| "num_train_epochs": 2, | |
| "total_flos": 4964548608000.0, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |