{ "best_metric": null, "best_model_checkpoint": null, "epoch": 0.17158176943699732, "eval_steps": 2, "global_step": 4, "is_hyper_param_search": false, "is_local_process_zero": true, "is_world_process_zero": true, "log_history": [ { "epoch": 0.04289544235924933, "grad_norm": 11.182668685913086, "learning_rate": 1e-05, "loss": 7.4229, "step": 1 }, { "epoch": 0.04289544235924933, "eval_loss": 6.950987339019775, "eval_runtime": 83.8323, "eval_samples_per_second": 0.477, "eval_steps_per_second": 0.239, "step": 1 }, { "epoch": 0.08579088471849866, "grad_norm": 10.96768569946289, "learning_rate": 2e-05, "loss": 7.0632, "step": 2 }, { "epoch": 0.08579088471849866, "eval_loss": 6.830499172210693, "eval_runtime": 2.5253, "eval_samples_per_second": 15.84, "eval_steps_per_second": 7.92, "step": 2 }, { "epoch": 0.128686327077748, "grad_norm": 10.156170845031738, "learning_rate": 3e-05, "loss": 6.9799, "step": 3 }, { "epoch": 0.17158176943699732, "grad_norm": 8.47403335571289, "learning_rate": 4e-05, "loss": 6.4964, "step": 4 }, { "epoch": 0.17158176943699732, "eval_loss": 6.270529747009277, "eval_runtime": 2.4834, "eval_samples_per_second": 16.107, "eval_steps_per_second": 8.053, "step": 4 } ], "logging_steps": 1, "max_steps": 5, "num_input_tokens_seen": 0, "num_train_epochs": 1, "save_steps": 2, "stateful_callbacks": { "TrainerControl": { "args": { "should_epoch_stop": false, "should_evaluate": false, "should_log": false, "should_save": true, "should_training_stop": false }, "attributes": {} } }, "total_flos": 3283829787721728.0, "train_batch_size": 2, "trial_name": null, "trial_params": null }