| { | |
| "best_metric": 2.213008165359497, | |
| "best_model_checkpoint": "output/mikhail-gorshenev/checkpoint-21", | |
| "epoch": 1.0, | |
| "global_step": 21, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.24, | |
| "learning_rate": 0.00011888735840752609, | |
| "loss": 2.5564, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.48, | |
| "learning_rate": 7.372648442002871e-05, | |
| "loss": 2.3124, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.71, | |
| "learning_rate": 2.5828599592490882e-05, | |
| "loss": 2.2458, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.95, | |
| "learning_rate": 7.662053209561833e-07, | |
| "loss": 2.1298, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "eval_loss": 2.213008165359497, | |
| "eval_runtime": 1.75, | |
| "eval_samples_per_second": 21.715, | |
| "eval_steps_per_second": 2.857, | |
| "step": 21 | |
| } | |
| ], | |
| "max_steps": 21, | |
| "num_train_epochs": 1, | |
| "total_flos": 21164654592000.0, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |