| { |
| "best_global_step": null, |
| "best_metric": null, |
| "best_model_checkpoint": null, |
| "epoch": 5.0, |
| "eval_steps": 500, |
| "global_step": 315, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "epoch": 0.7936507936507936, |
| "grad_norm": 4.6148552894592285, |
| "learning_rate": 1.740740740740741e-05, |
| "loss": 1.5568, |
| "step": 50 |
| }, |
| { |
| "epoch": 1.5873015873015874, |
| "grad_norm": 1.964592695236206, |
| "learning_rate": 1.4761904761904763e-05, |
| "loss": 0.4282, |
| "step": 100 |
| }, |
| { |
| "epoch": 2.380952380952381, |
| "grad_norm": 0.401151180267334, |
| "learning_rate": 1.2116402116402117e-05, |
| "loss": 0.0969, |
| "step": 150 |
| }, |
| { |
| "epoch": 3.1746031746031744, |
| "grad_norm": 0.24489885568618774, |
| "learning_rate": 9.470899470899471e-06, |
| "loss": 0.0392, |
| "step": 200 |
| }, |
| { |
| "epoch": 3.9682539682539684, |
| "grad_norm": 0.17426319420337677, |
| "learning_rate": 6.825396825396826e-06, |
| "loss": 0.0267, |
| "step": 250 |
| }, |
| { |
| "epoch": 4.761904761904762, |
| "grad_norm": 0.17985087633132935, |
| "learning_rate": 4.17989417989418e-06, |
| "loss": 0.0216, |
| "step": 300 |
| } |
| ], |
| "logging_steps": 50, |
| "max_steps": 378, |
| "num_input_tokens_seen": 0, |
| "num_train_epochs": 6, |
| "save_steps": 500, |
| "stateful_callbacks": { |
| "TrainerControl": { |
| "args": { |
| "should_epoch_stop": false, |
| "should_evaluate": false, |
| "should_log": false, |
| "should_save": true, |
| "should_training_stop": false |
| }, |
| "attributes": {} |
| } |
| }, |
| "total_flos": 328909489920000.0, |
| "train_batch_size": 16, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
