| { |
| "best_metric": null, |
| "best_model_checkpoint": null, |
| "epoch": 2.0, |
| "eval_steps": 500, |
| "global_step": 2000, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "epoch": 0.5, |
| "grad_norm": 28.593961715698242, |
| "learning_rate": 1.8e-05, |
| "loss": 0.5987, |
| "step": 500 |
| }, |
| { |
| "epoch": 1.0, |
| "grad_norm": 28.91183090209961, |
| "learning_rate": 1.6000000000000003e-05, |
| "loss": 0.4193, |
| "step": 1000 |
| }, |
| { |
| "epoch": 1.5, |
| "grad_norm": 14.28818130493164, |
| "learning_rate": 1.4e-05, |
| "loss": 0.327, |
| "step": 1500 |
| }, |
| { |
| "epoch": 2.0, |
| "grad_norm": 0.3224489390850067, |
| "learning_rate": 1.2e-05, |
| "loss": 0.3122, |
| "step": 2000 |
| } |
| ], |
| "logging_steps": 500, |
| "max_steps": 5000, |
| "num_input_tokens_seen": 0, |
| "num_train_epochs": 5, |
| "save_steps": 500, |
| "total_flos": 3727725453312000.0, |
| "train_batch_size": 8, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
