| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 3.0, | |
| "global_step": 9, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.33, | |
| "learning_rate": 2e-05, | |
| "loss": 2.0078, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.67, | |
| "learning_rate": 1.9238795325112867e-05, | |
| "loss": 1.8555, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "learning_rate": 1.7071067811865477e-05, | |
| "loss": 1.9688, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 1.33, | |
| "learning_rate": 1.3826834323650899e-05, | |
| "loss": 1.9648, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 1.67, | |
| "learning_rate": 1e-05, | |
| "loss": 1.9531, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "learning_rate": 6.173165676349103e-06, | |
| "loss": 1.8594, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 2.33, | |
| "learning_rate": 2.9289321881345257e-06, | |
| "loss": 1.8164, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 2.67, | |
| "learning_rate": 7.612046748871327e-07, | |
| "loss": 2.0547, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "learning_rate": 0.0, | |
| "loss": 1.8125, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "step": 9, | |
| "total_flos": 3615157490024448.0, | |
| "train_loss": 1.9214409722222223, | |
| "train_runtime": 539.9369, | |
| "train_samples_per_second": 0.533, | |
| "train_steps_per_second": 0.017 | |
| } | |
| ], | |
| "max_steps": 9, | |
| "num_train_epochs": 3, | |
| "total_flos": 3615157490024448.0, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |