| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 3.048780487804878, | |
| "global_step": 500, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 1.0, | |
| "eval_loss": 1.8646807670593262, | |
| "eval_runtime": 68.8052, | |
| "eval_samples_per_second": 4.709, | |
| "eval_steps_per_second": 0.596, | |
| "step": 164 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "eval_loss": 1.8987102508544922, | |
| "eval_runtime": 70.9224, | |
| "eval_samples_per_second": 4.568, | |
| "eval_steps_per_second": 0.578, | |
| "step": 328 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "eval_loss": 2.09053373336792, | |
| "eval_runtime": 65.7815, | |
| "eval_samples_per_second": 4.925, | |
| "eval_steps_per_second": 0.623, | |
| "step": 492 | |
| }, | |
| { | |
| "epoch": 3.05, | |
| "learning_rate": 1.3902439024390244e-05, | |
| "loss": 1.6067, | |
| "step": 500 | |
| } | |
| ], | |
| "max_steps": 1640, | |
| "num_train_epochs": 10, | |
| "total_flos": 925920865026048.0, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |