| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 6.999466666666667, | |
| "global_step": 3281, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 1.0, | |
| "learning_rate": 0.00027499999999999996, | |
| "loss": 2.2976, | |
| "step": 468 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "eval_loss": 2.336582899093628, | |
| "eval_runtime": 78.6661, | |
| "eval_samples_per_second": 474.805, | |
| "eval_steps_per_second": 59.352, | |
| "step": 468 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "learning_rate": 0.0002499465811965812, | |
| "loss": 1.9877, | |
| "step": 937 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "eval_loss": 2.378277540206909, | |
| "eval_runtime": 78.6809, | |
| "eval_samples_per_second": 474.715, | |
| "eval_steps_per_second": 59.341, | |
| "step": 937 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "learning_rate": 0.00022489316239316236, | |
| "loss": 1.7492, | |
| "step": 1406 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "eval_loss": 2.487154960632324, | |
| "eval_runtime": 79.1756, | |
| "eval_samples_per_second": 471.749, | |
| "eval_steps_per_second": 58.97, | |
| "step": 1406 | |
| }, | |
| { | |
| "epoch": 4.0, | |
| "learning_rate": 0.00019983974358974357, | |
| "loss": 1.5071, | |
| "step": 1875 | |
| }, | |
| { | |
| "epoch": 4.0, | |
| "eval_loss": 2.652348041534424, | |
| "eval_runtime": 79.1787, | |
| "eval_samples_per_second": 471.73, | |
| "eval_steps_per_second": 58.968, | |
| "step": 1875 | |
| }, | |
| { | |
| "epoch": 5.0, | |
| "learning_rate": 0.00017483974358974358, | |
| "loss": 1.2629, | |
| "step": 2343 | |
| }, | |
| { | |
| "epoch": 5.0, | |
| "eval_loss": 2.86438250541687, | |
| "eval_runtime": 79.0436, | |
| "eval_samples_per_second": 472.537, | |
| "eval_steps_per_second": 59.069, | |
| "step": 2343 | |
| }, | |
| { | |
| "epoch": 6.0, | |
| "learning_rate": 0.00014978632478632477, | |
| "loss": 1.0163, | |
| "step": 2812 | |
| }, | |
| { | |
| "epoch": 6.0, | |
| "eval_loss": 3.113752603530884, | |
| "eval_runtime": 78.7145, | |
| "eval_samples_per_second": 474.512, | |
| "eval_steps_per_second": 59.316, | |
| "step": 2812 | |
| }, | |
| { | |
| "epoch": 7.0, | |
| "learning_rate": 0.00012473290598290598, | |
| "loss": 0.7859, | |
| "step": 3281 | |
| }, | |
| { | |
| "epoch": 7.0, | |
| "eval_loss": 3.4060871601104736, | |
| "eval_runtime": 78.8544, | |
| "eval_samples_per_second": 473.671, | |
| "eval_steps_per_second": 59.21, | |
| "step": 3281 | |
| } | |
| ], | |
| "max_steps": 5616, | |
| "num_train_epochs": 12, | |
| "total_flos": 1.2915021003952435e+17, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |