| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.15241579027587257, | |
| "eval_steps": 100, | |
| "global_step": 100, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.02, | |
| "learning_rate": 8.99484069051768e-06, | |
| "loss": 0.672, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.03, | |
| "learning_rate": 8.979374592503753e-06, | |
| "loss": 0.393, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.05, | |
| "learning_rate": 8.953637170129838e-06, | |
| "loss": 0.1594, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.06, | |
| "learning_rate": 8.917687439985847e-06, | |
| "loss": 0.122, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.08, | |
| "learning_rate": 8.87160783575339e-06, | |
| "loss": 0.0956, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.09, | |
| "learning_rate": 8.815504019183158e-06, | |
| "loss": 0.102, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.11, | |
| "learning_rate": 8.749504637809742e-06, | |
| "loss": 0.0888, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.12, | |
| "learning_rate": 8.673761029959426e-06, | |
| "loss": 0.097, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 0.14, | |
| "learning_rate": 8.588446877727417e-06, | |
| "loss": 0.0968, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 0.15, | |
| "learning_rate": 8.493757808720196e-06, | |
| "loss": 0.0808, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.15, | |
| "eval_accuracy": 0.0, | |
| "eval_loss": 3.0685205274494365e-05, | |
| "eval_runtime": 30.877, | |
| "eval_samples_per_second": 141.659, | |
| "eval_steps_per_second": 23.61, | |
| "step": 100 | |
| } | |
| ], | |
| "logging_steps": 10, | |
| "max_steps": 656, | |
| "num_train_epochs": 1, | |
| "save_steps": 100, | |
| "total_flos": 0.0, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |