{ "best_metric": null, "best_model_checkpoint": null, "epoch": 0.00886426592797784, "eval_steps": 2, "global_step": 2, "is_hyper_param_search": false, "is_local_process_zero": true, "is_world_process_zero": true, "log_history": [ { "epoch": 0.00443213296398892, "grad_norm": 2.3340044021606445, "learning_rate": 1e-05, "loss": 178.0625, "step": 1 }, { "epoch": 0.00443213296398892, "eval_loss": 11.120723724365234, "eval_runtime": 11.2678, "eval_samples_per_second": 33.724, "eval_steps_per_second": 16.862, "step": 1 }, { "epoch": 0.00886426592797784, "grad_norm": 2.0113182067871094, "learning_rate": 2e-05, "loss": 178.0, "step": 2 }, { "epoch": 0.00886426592797784, "eval_loss": 11.120723724365234, "eval_runtime": 0.6821, "eval_samples_per_second": 557.1, "eval_steps_per_second": 278.55, "step": 2 } ], "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": 137438429184.0, "train_batch_size": 2, "trial_name": null, "trial_params": null }