| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 3.0, | |
| "global_step": 1725, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.87, | |
| "learning_rate": 3.5507246376811596e-05, | |
| "loss": 4.1204, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 1.74, | |
| "learning_rate": 2.101449275362319e-05, | |
| "loss": 3.1808, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 2.61, | |
| "learning_rate": 6.521739130434783e-06, | |
| "loss": 2.6402, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "step": 1725, | |
| "total_flos": 402670891253760.0, | |
| "train_loss": 3.2056930409307065, | |
| "train_runtime": 264.9723, | |
| "train_samples_per_second": 26.029, | |
| "train_steps_per_second": 6.51 | |
| } | |
| ], | |
| "max_steps": 1725, | |
| "num_train_epochs": 3, | |
| "total_flos": 402670891253760.0, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |