| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 2.69, | |
| "eval_steps": 500, | |
| "global_step": 1035, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.2, | |
| "learning_rate": 0.00013333333333333334, | |
| "loss": 0.6747, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.4, | |
| "learning_rate": 0.0001925925925925926, | |
| "loss": 0.4326, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.6, | |
| "learning_rate": 0.00017777777777777779, | |
| "loss": 0.32, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 1.11, | |
| "learning_rate": 0.00016296296296296295, | |
| "loss": 0.2383, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 1.31, | |
| "learning_rate": 0.00014814814814814815, | |
| "loss": 0.1934, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 1.51, | |
| "learning_rate": 0.00013333333333333334, | |
| "loss": 0.1729, | |
| "step": 600 | |
| }, | |
| { | |
| "epoch": 2.02, | |
| "learning_rate": 0.00011851851851851852, | |
| "loss": 0.1683, | |
| "step": 700 | |
| }, | |
| { | |
| "epoch": 2.22, | |
| "learning_rate": 0.0001037037037037037, | |
| "loss": 0.1237, | |
| "step": 800 | |
| }, | |
| { | |
| "epoch": 2.42, | |
| "learning_rate": 8.888888888888889e-05, | |
| "loss": 0.1201, | |
| "step": 900 | |
| }, | |
| { | |
| "epoch": 2.62, | |
| "learning_rate": 7.407407407407407e-05, | |
| "loss": 0.1295, | |
| "step": 1000 | |
| } | |
| ], | |
| "logging_steps": 100, | |
| "max_steps": 1500, | |
| "num_train_epochs": 3, | |
| "save_steps": 500, | |
| "total_flos": 8.401830279118848e+16, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |