| { |
| "best_global_step": null, |
| "best_metric": null, |
| "best_model_checkpoint": null, |
| "epoch": 1.5625, |
| "eval_steps": 500, |
| "global_step": 50, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "epoch": 0.3125, |
| "grad_norm": 0.2920430898666382, |
| "learning_rate": 0.00045000000000000004, |
| "loss": 3.779199981689453, |
| "step": 10 |
| }, |
| { |
| "epoch": 0.625, |
| "grad_norm": 0.43692970275878906, |
| "learning_rate": 0.00095, |
| "loss": 3.7675334930419924, |
| "step": 20 |
| }, |
| { |
| "epoch": 0.9375, |
| "grad_norm": 0.3336999714374542, |
| "learning_rate": 0.0009699999999999999, |
| "loss": 3.719318389892578, |
| "step": 30 |
| }, |
| { |
| "epoch": 1.25, |
| "grad_norm": 0.294895738363266, |
| "learning_rate": 0.0009366666666666667, |
| "loss": 3.654178237915039, |
| "step": 40 |
| }, |
| { |
| "epoch": 1.5625, |
| "grad_norm": 0.2748182713985443, |
| "learning_rate": 0.0009033333333333334, |
| "loss": 3.5974361419677736, |
| "step": 50 |
| } |
| ], |
| "logging_steps": 10, |
| "max_steps": 320, |
| "num_input_tokens_seen": 0, |
| "num_train_epochs": 10, |
| "save_steps": 50, |
| "stateful_callbacks": { |
| "TrainerControl": { |
| "args": { |
| "should_epoch_stop": false, |
| "should_evaluate": false, |
| "should_log": false, |
| "should_save": true, |
| "should_training_stop": false |
| }, |
| "attributes": {} |
| } |
| }, |
| "total_flos": 179596032.0, |
| "train_batch_size": 32, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
