| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 3.0, | |
| "eval_steps": 500, | |
| "global_step": 2742, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.5470459518599562, | |
| "grad_norm": 10.830166816711426, | |
| "learning_rate": 4.088256746900073e-05, | |
| "loss": 1.6341, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 1.0940919037199124, | |
| "grad_norm": 18.06269645690918, | |
| "learning_rate": 3.1765134938001465e-05, | |
| "loss": 1.4008, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 1.6411378555798688, | |
| "grad_norm": 365.6752624511719, | |
| "learning_rate": 2.264770240700219e-05, | |
| "loss": 1.4704, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 2.1881838074398248, | |
| "grad_norm": 3.707717723955284e-07, | |
| "learning_rate": 1.353026987600292e-05, | |
| "loss": 1.1974, | |
| "step": 2000 | |
| }, | |
| { | |
| "epoch": 2.735229759299781, | |
| "grad_norm": 2.492510642326806e-09, | |
| "learning_rate": 4.412837345003647e-06, | |
| "loss": 0.5534, | |
| "step": 2500 | |
| } | |
| ], | |
| "logging_steps": 500, | |
| "max_steps": 2742, | |
| "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": 0.0, | |
| "train_batch_size": 1, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |