| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.26490066225165565, | |
| "eval_steps": 100, | |
| "global_step": 100, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.03, | |
| "learning_rate": 4.991324875275794e-05, | |
| "loss": 0.5919, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.05, | |
| "learning_rate": 4.9653597073343594e-05, | |
| "loss": 0.416, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.08, | |
| "learning_rate": 4.922284697031999e-05, | |
| "loss": 0.3812, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.11, | |
| "learning_rate": 4.8623987892382066e-05, | |
| "loss": 0.3123, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.13, | |
| "learning_rate": 4.78611759812845e-05, | |
| "loss": 0.3611, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.16, | |
| "learning_rate": 4.69397052278032e-05, | |
| "loss": 0.2925, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.19, | |
| "learning_rate": 4.586597073091109e-05, | |
| "loss": 0.3014, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.21, | |
| "learning_rate": 4.464742431515315e-05, | |
| "loss": 0.3692, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 0.24, | |
| "learning_rate": 4.329252281424052e-05, | |
| "loss": 0.2641, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 0.26, | |
| "learning_rate": 4.181066937978075e-05, | |
| "loss": 0.2579, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.26, | |
| "eval_accuracy": 0.0, | |
| "eval_loss": 0.2431439310312271, | |
| "eval_runtime": 18.0196, | |
| "eval_samples_per_second": 139.681, | |
| "eval_steps_per_second": 23.308, | |
| "step": 100 | |
| } | |
| ], | |
| "logging_steps": 10, | |
| "max_steps": 377, | |
| "num_train_epochs": 1, | |
| "save_steps": 100, | |
| "total_flos": 0.0, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |