| { |
| "best_global_step": null, |
| "best_metric": null, |
| "best_model_checkpoint": null, |
| "epoch": 0.0778549406745352, |
| "eval_steps": 500, |
| "global_step": 2500, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "epoch": 0.015570988134907041, |
| "grad_norm": 0.0, |
| "learning_rate": 4.961150384603407e-05, |
| "loss": 0.0421, |
| "step": 500 |
| }, |
| { |
| "epoch": 0.031141976269814083, |
| "grad_norm": 0.0, |
| "learning_rate": 4.92222291426614e-05, |
| "loss": 0.0622, |
| "step": 1000 |
| }, |
| { |
| "epoch": 0.04671296440472112, |
| "grad_norm": 0.0, |
| "learning_rate": 4.883295443928872e-05, |
| "loss": 0.0062, |
| "step": 1500 |
| }, |
| { |
| "epoch": 0.062283952539628165, |
| "grad_norm": 0.0, |
| "learning_rate": 4.844367973591604e-05, |
| "loss": 0.0024, |
| "step": 2000 |
| }, |
| { |
| "epoch": 0.0778549406745352, |
| "grad_norm": 0.0, |
| "learning_rate": 4.8054405032543364e-05, |
| "loss": 0.0002, |
| "step": 2500 |
| } |
| ], |
| "logging_steps": 500, |
| "max_steps": 64222, |
| "num_input_tokens_seen": 0, |
| "num_train_epochs": 2, |
| "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": 0.0, |
| "train_batch_size": 8, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
