| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 1.0, | |
| "eval_steps": 500, | |
| "global_step": 2211, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.2261420171867933, | |
| "grad_norm": 0.06914567202329636, | |
| "learning_rate": 3.869289914066034e-05, | |
| "loss": 0.5695, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 0.4522840343735866, | |
| "grad_norm": 0.08596434444189072, | |
| "learning_rate": 2.7385798281320668e-05, | |
| "loss": 0.4016, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 0.6784260515603799, | |
| "grad_norm": 0.0946701392531395, | |
| "learning_rate": 1.6078697421981004e-05, | |
| "loss": 0.3921, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 0.9045680687471732, | |
| "grad_norm": 0.09613804519176483, | |
| "learning_rate": 4.771596562641339e-06, | |
| "loss": 0.39, | |
| "step": 2000 | |
| } | |
| ], | |
| "logging_steps": 500, | |
| "max_steps": 2211, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 5000, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 5.1529691352589664e+19, | |
| "train_batch_size": 128, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |