| { | |
| "best_metric": 1.9221878051757812, | |
| "best_model_checkpoint": "output/sqwore/checkpoint-10", | |
| "epoch": 1.0, | |
| "global_step": 10, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.5, | |
| "learning_rate": 6.86e-05, | |
| "loss": 2.5984, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "learning_rate": 0.0, | |
| "loss": 2.2553, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "eval_loss": 1.9221878051757812, | |
| "eval_runtime": 0.8231, | |
| "eval_samples_per_second": 20.653, | |
| "eval_steps_per_second": 3.645, | |
| "step": 10 | |
| } | |
| ], | |
| "max_steps": 10, | |
| "num_train_epochs": 1, | |
| "total_flos": 10059743232000.0, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |