{ "best_metric": null, "best_model_checkpoint": null, "epoch": 0.007827788649706457, "eval_steps": 3, "global_step": 3, "is_hyper_param_search": false, "is_local_process_zero": true, "is_world_process_zero": true, "log_history": [ { "epoch": 0.002609262883235486, "grad_norm": 0.6899170279502869, "learning_rate": 2e-05, "loss": 2.7018, "step": 1 }, { "epoch": 0.002609262883235486, "eval_loss": 2.74656343460083, "eval_runtime": 3.6737, "eval_samples_per_second": 44.097, "eval_steps_per_second": 22.049, "step": 1 }, { "epoch": 0.005218525766470972, "grad_norm": 0.7338986396789551, "learning_rate": 4e-05, "loss": 2.849, "step": 2 }, { "epoch": 0.007827788649706457, "grad_norm": 0.5598652958869934, "learning_rate": 6e-05, "loss": 2.9166, "step": 3 }, { "epoch": 0.007827788649706457, "eval_loss": 2.746614456176758, "eval_runtime": 2.964, "eval_samples_per_second": 54.655, "eval_steps_per_second": 27.328, "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": 18003641499648.0, "train_batch_size": 2, "trial_name": null, "trial_params": null }