| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 9.967741935483872, | |
| "global_step": 150, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 6.65, | |
| "learning_rate": 1.4999999999999999e-05, | |
| "loss": 6.9618, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 9.97, | |
| "step": 150, | |
| "total_flos": 2.264182160412142e+18, | |
| "train_loss": 5.883141581217448, | |
| "train_runtime": 4312.7885, | |
| "train_samples_per_second": 2.295, | |
| "train_steps_per_second": 0.035 | |
| } | |
| ], | |
| "max_steps": 150, | |
| "num_train_epochs": 10, | |
| "total_flos": 2.264182160412142e+18, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |