| { | |
| "best_metric": 3.504110097885132, | |
| "best_model_checkpoint": "output/arctic-monkeys/checkpoint-23", | |
| "epoch": 1.0, | |
| "global_step": 23, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.22, | |
| "learning_rate": 0.0001218137945423232, | |
| "loss": 3.7306, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.43, | |
| "learning_rate": 8.255708249541069e-05, | |
| "loss": 3.638, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.65, | |
| "learning_rate": 3.703953841164296e-05, | |
| "loss": 3.4653, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.87, | |
| "learning_rate": 5.679304716725937e-06, | |
| "loss": 3.4323, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "eval_loss": 3.504110097885132, | |
| "eval_runtime": 1.5247, | |
| "eval_samples_per_second": 20.987, | |
| "eval_steps_per_second": 2.623, | |
| "step": 23 | |
| } | |
| ], | |
| "max_steps": 23, | |
| "num_train_epochs": 1, | |
| "total_flos": 23908220928000.0, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |