| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 1.0, | |
| "global_step": 1000, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.1, | |
| "learning_rate": 1e-05, | |
| "loss": 11.9971, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.2, | |
| "learning_rate": 2e-05, | |
| "loss": 10.4333, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.3, | |
| "learning_rate": 3e-05, | |
| "loss": 9.2986, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 0.4, | |
| "learning_rate": 4e-05, | |
| "loss": 5.9939, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 0.5, | |
| "learning_rate": 5e-05, | |
| "loss": 1.0993, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 0.6, | |
| "learning_rate": 4e-05, | |
| "loss": 0.387, | |
| "step": 600 | |
| }, | |
| { | |
| "epoch": 0.7, | |
| "learning_rate": 3e-05, | |
| "loss": 0.2896, | |
| "step": 700 | |
| }, | |
| { | |
| "epoch": 0.8, | |
| "learning_rate": 2e-05, | |
| "loss": 0.2603, | |
| "step": 800 | |
| }, | |
| { | |
| "epoch": 0.9, | |
| "learning_rate": 1e-05, | |
| "loss": 0.2621, | |
| "step": 900 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "learning_rate": 0.0, | |
| "loss": 0.2278, | |
| "step": 1000 | |
| } | |
| ], | |
| "max_steps": 1000, | |
| "num_train_epochs": 1, | |
| "total_flos": 2889464414208000.0, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |