| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.12690355329949238, | |
| "eval_steps": 1000, | |
| "global_step": 200, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.01, | |
| "learning_rate": 0.0001, | |
| "loss": 0.9676, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.03, | |
| "learning_rate": 0.0001, | |
| "loss": 0.7339, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.04, | |
| "learning_rate": 0.0001, | |
| "loss": 0.6708, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.05, | |
| "learning_rate": 0.0001, | |
| "loss": 0.6334, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 0.06, | |
| "learning_rate": 0.0001, | |
| "loss": 0.6169, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.08, | |
| "learning_rate": 0.0001, | |
| "loss": 0.5886, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 0.09, | |
| "learning_rate": 0.0001, | |
| "loss": 0.5877, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 0.1, | |
| "learning_rate": 0.0001, | |
| "loss": 0.5867, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 0.11, | |
| "learning_rate": 0.0001, | |
| "loss": 0.5791, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 0.13, | |
| "learning_rate": 0.0001, | |
| "loss": 0.5764, | |
| "step": 200 | |
| } | |
| ], | |
| "logging_steps": 20, | |
| "max_steps": 45000, | |
| "num_train_epochs": 29, | |
| "save_steps": 200, | |
| "total_flos": 4.706262881912488e+18, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |