{ "best_metric": null, "best_model_checkpoint": null, "epoch": 0.0016941973739940702, "eval_steps": 3, "global_step": 3, "is_hyper_param_search": false, "is_local_process_zero": true, "is_world_process_zero": true, "log_history": [ { "epoch": 0.0005647324579980235, "grad_norm": 6.657321453094482, "learning_rate": 2e-05, "loss": 3.0027, "step": 1 }, { "epoch": 0.0005647324579980235, "eval_loss": 2.7413086891174316, "eval_runtime": 209.2902, "eval_samples_per_second": 3.564, "eval_steps_per_second": 1.782, "step": 1 }, { "epoch": 0.001129464915996047, "grad_norm": 4.548604965209961, "learning_rate": 4e-05, "loss": 2.5806, "step": 2 }, { "epoch": 0.0016941973739940702, "grad_norm": 4.600951194763184, "learning_rate": 6e-05, "loss": 3.2098, "step": 3 }, { "epoch": 0.0016941973739940702, "eval_loss": 2.6281063556671143, "eval_runtime": 212.6516, "eval_samples_per_second": 3.508, "eval_steps_per_second": 1.754, "step": 3 } ], "logging_steps": 1, "max_steps": 10, "num_input_tokens_seen": 0, "num_train_epochs": 1, "save_steps": 3, "stateful_callbacks": { "TrainerControl": { "args": { "should_epoch_stop": false, "should_evaluate": false, "should_log": false, "should_save": true, "should_training_stop": false }, "attributes": {} } }, "total_flos": 4601366169255936.0, "train_batch_size": 2, "trial_name": null, "trial_params": null }