{ "best_metric": null, "best_model_checkpoint": null, "epoch": 0.0016601385178075796, "eval_steps": 2, "global_step": 4, "is_hyper_param_search": false, "is_local_process_zero": true, "is_world_process_zero": true, "log_history": [ { "epoch": 0.0004150346294518949, "grad_norm": 0.8002733588218689, "learning_rate": 1e-05, "loss": 2.2335, "step": 1 }, { "epoch": 0.0004150346294518949, "eval_loss": 2.4260973930358887, "eval_runtime": 214.0607, "eval_samples_per_second": 18.957, "eval_steps_per_second": 9.479, "step": 1 }, { "epoch": 0.0008300692589037898, "grad_norm": 0.7987782955169678, "learning_rate": 2e-05, "loss": 2.0365, "step": 2 }, { "epoch": 0.0008300692589037898, "eval_loss": 2.4085092544555664, "eval_runtime": 128.1003, "eval_samples_per_second": 31.678, "eval_steps_per_second": 15.839, "step": 2 }, { "epoch": 0.0012451038883556846, "grad_norm": 0.8058750033378601, "learning_rate": 3e-05, "loss": 2.1679, "step": 3 }, { "epoch": 0.0016601385178075796, "grad_norm": 0.88985675573349, "learning_rate": 4e-05, "loss": 2.3762, "step": 4 }, { "epoch": 0.0016601385178075796, "eval_loss": 2.386413812637329, "eval_runtime": 128.1821, "eval_samples_per_second": 31.658, "eval_steps_per_second": 15.829, "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": 4346475983142912.0, "train_batch_size": 2, "trial_name": null, "trial_params": null }