| { | |
| "best_global_step": null, | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 2.0, | |
| "eval_steps": 500, | |
| "global_step": 1308, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.3058103975535168, | |
| "grad_norm": 0.2780028283596039, | |
| "learning_rate": 1.8936627282491947e-05, | |
| "loss": 0.0195, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.6116207951070336, | |
| "grad_norm": 0.22156599164009094, | |
| "learning_rate": 1.678839957035446e-05, | |
| "loss": 0.0132, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 0.9174311926605505, | |
| "grad_norm": 0.09372077137231827, | |
| "learning_rate": 1.4640171858216972e-05, | |
| "loss": 0.0111, | |
| "step": 600 | |
| }, | |
| { | |
| "epoch": 1.2232415902140672, | |
| "grad_norm": 0.1351478546857834, | |
| "learning_rate": 1.2491944146079485e-05, | |
| "loss": 0.0099, | |
| "step": 800 | |
| }, | |
| { | |
| "epoch": 1.529051987767584, | |
| "grad_norm": 0.23781578242778778, | |
| "learning_rate": 1.0343716433942e-05, | |
| "loss": 0.0086, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 1.834862385321101, | |
| "grad_norm": 0.2146996110677719, | |
| "learning_rate": 8.195488721804512e-06, | |
| "loss": 0.0072, | |
| "step": 1200 | |
| } | |
| ], | |
| "logging_steps": 200, | |
| "max_steps": 1962, | |
| "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": false | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 0.0, | |
| "train_batch_size": 8, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |