| { |
| "best_global_step": null, |
| "best_metric": null, |
| "best_model_checkpoint": null, |
| "epoch": 3.0, |
| "eval_steps": 500, |
| "global_step": 39, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "epoch": 0.7692307692307693, |
| "grad_norm": 1.4972448348999023, |
| "learning_rate": 0.00016923076923076923, |
| "loss": 3.7393, |
| "step": 10 |
| }, |
| { |
| "epoch": 1.5384615384615383, |
| "grad_norm": 0.39184582233428955, |
| "learning_rate": 0.00011794871794871796, |
| "loss": 0.1276, |
| "step": 20 |
| }, |
| { |
| "epoch": 2.3076923076923075, |
| "grad_norm": 0.367369681596756, |
| "learning_rate": 6.666666666666667e-05, |
| "loss": 0.0627, |
| "step": 30 |
| } |
| ], |
| "logging_steps": 10, |
| "max_steps": 39, |
| "num_input_tokens_seen": 0, |
| "num_train_epochs": 3, |
| "save_steps": 100, |
| "stateful_callbacks": { |
| "TrainerControl": { |
| "args": { |
| "should_epoch_stop": false, |
| "should_evaluate": false, |
| "should_log": false, |
| "should_save": true, |
| "should_training_stop": true |
| }, |
| "attributes": {} |
| } |
| }, |
| "total_flos": 3409465269288960.0, |
| "train_batch_size": 4, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
