| { |
| "best_metric": null, |
| "best_model_checkpoint": null, |
| "epoch": 0.9646302250803859, |
| "eval_steps": 500, |
| "global_step": 1500, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "epoch": 0.32, |
| "grad_norm": 3.718449354171753, |
| "learning_rate": 0.00015351442961239234, |
| "loss": 0.8573, |
| "step": 500 |
| }, |
| { |
| "epoch": 0.64, |
| "grad_norm": 2.904940128326416, |
| "learning_rate": 5.691090437887502e-05, |
| "loss": 0.8197, |
| "step": 1000 |
| }, |
| { |
| "epoch": 0.96, |
| "grad_norm": 2.560385227203369, |
| "learning_rate": 6.857533850272103e-07, |
| "loss": 0.8041, |
| "step": 1500 |
| } |
| ], |
| "logging_steps": 500, |
| "max_steps": 1555, |
| "num_input_tokens_seen": 0, |
| "num_train_epochs": 1, |
| "save_steps": 500, |
| "total_flos": 3.561139923868877e+16, |
| "train_batch_size": 1, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
