| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 79.36167076167077, | |
| "global_step": 5000, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 7.93, | |
| "learning_rate": 4.603174603174603e-05, | |
| "loss": 2.3851, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 15.86, | |
| "learning_rate": 4.2063492063492065e-05, | |
| "loss": 2.3266, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 23.8, | |
| "learning_rate": 3.809523809523809e-05, | |
| "loss": 2.2793, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 31.74, | |
| "learning_rate": 3.412698412698413e-05, | |
| "loss": 2.2354, | |
| "step": 2000 | |
| }, | |
| { | |
| "epoch": 39.68, | |
| "learning_rate": 3.0158730158730158e-05, | |
| "loss": 2.1978, | |
| "step": 2500 | |
| }, | |
| { | |
| "epoch": 47.61, | |
| "learning_rate": 2.6190476190476192e-05, | |
| "loss": 2.1656, | |
| "step": 3000 | |
| }, | |
| { | |
| "epoch": 55.55, | |
| "learning_rate": 2.2222222222222223e-05, | |
| "loss": 2.1374, | |
| "step": 3500 | |
| }, | |
| { | |
| "epoch": 63.49, | |
| "learning_rate": 1.8253968253968254e-05, | |
| "loss": 2.1132, | |
| "step": 4000 | |
| }, | |
| { | |
| "epoch": 71.42, | |
| "learning_rate": 1.4285714285714285e-05, | |
| "loss": 2.0931, | |
| "step": 4500 | |
| }, | |
| { | |
| "epoch": 79.36, | |
| "learning_rate": 1.0317460317460318e-05, | |
| "loss": 2.0763, | |
| "step": 5000 | |
| } | |
| ], | |
| "max_steps": 6300, | |
| "num_train_epochs": 100, | |
| "total_flos": 2.720215956373635e+19, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |