| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 6.880341880341881, | |
| "global_step": 3220, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 1.07, | |
| "learning_rate": 4.9289772727272735e-05, | |
| "loss": 0.2614, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 2.14, | |
| "learning_rate": 4.041193181818182e-05, | |
| "loss": 0.039, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 3.21, | |
| "learning_rate": 3.153409090909091e-05, | |
| "loss": 0.0193, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 4.27, | |
| "learning_rate": 2.2656250000000002e-05, | |
| "loss": 0.0112, | |
| "step": 2000 | |
| }, | |
| { | |
| "epoch": 5.34, | |
| "learning_rate": 1.3778409090909091e-05, | |
| "loss": 0.0071, | |
| "step": 2500 | |
| }, | |
| { | |
| "epoch": 6.41, | |
| "learning_rate": 4.900568181818182e-06, | |
| "loss": 0.0048, | |
| "step": 3000 | |
| } | |
| ], | |
| "max_steps": 3276, | |
| "num_train_epochs": 7, | |
| "total_flos": 3433722892293120.0, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |