| { |
| "best_metric": null, |
| "best_model_checkpoint": null, |
| "epoch": 2.0, |
| "eval_steps": 500, |
| "global_step": 3, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "epoch": 1.0, |
| "learning_rate": 8e-05, |
| "loss": 0.9135, |
| "step": 1 |
| }, |
| { |
| "epoch": 1.3333333333333333, |
| "grad_norm": 7.572297574311586, |
| "learning_rate": 4e-05, |
| "loss": 0.3015, |
| "step": 2 |
| }, |
| { |
| "epoch": 2.0, |
| "grad_norm": 7.572297574311586, |
| "learning_rate": 0.0, |
| "loss": 1.0228, |
| "step": 3 |
| }, |
| { |
| "epoch": 2.0, |
| "step": 3, |
| "total_flos": 3.945562687039078e+16, |
| "train_loss": 0.745947023232778, |
| "train_runtime": 454.119, |
| "train_samples_per_second": 2.51, |
| "train_steps_per_second": 0.007 |
| } |
| ], |
| "logging_steps": 1, |
| "max_steps": 3, |
| "num_input_tokens_seen": 0, |
| "num_train_epochs": 3, |
| "save_steps": 500, |
| "stateful_callbacks": { |
| "TrainerControl": { |
| "args": { |
| "should_epoch_stop": false, |
| "should_evaluate": false, |
| "should_log": false, |
| "should_save": true, |
| "should_training_stop": true |
| }, |
| "attributes": {} |
| } |
| }, |
| "total_flos": 3.945562687039078e+16, |
| "train_batch_size": 1, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
