| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 9.149130832570906, | |
| "global_step": 40000, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 2.29, | |
| "learning_rate": 9.42817932296432e-06, | |
| "loss": 2.4808, | |
| "step": 10000 | |
| }, | |
| { | |
| "epoch": 4.57, | |
| "learning_rate": 8.856358645928637e-06, | |
| "loss": 1.2166, | |
| "step": 20000 | |
| }, | |
| { | |
| "epoch": 6.86, | |
| "learning_rate": 8.284537968892956e-06, | |
| "loss": 0.9323, | |
| "step": 30000 | |
| }, | |
| { | |
| "epoch": 9.15, | |
| "learning_rate": 7.712717291857275e-06, | |
| "loss": 0.7901, | |
| "step": 40000 | |
| } | |
| ], | |
| "max_steps": 174880, | |
| "num_train_epochs": 40, | |
| "total_flos": 9.92204617219769e+19, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |