{ "best_metric": null, "best_model_checkpoint": null, "epoch": 0.004302231782737295, "eval_steps": 2, "global_step": 2, "is_hyper_param_search": false, "is_local_process_zero": true, "is_world_process_zero": true, "log_history": [ { "epoch": 0.0021511158913686476, "grad_norm": 0.26105204224586487, "learning_rate": 1e-05, "loss": 6.9241, "step": 1 }, { "epoch": 0.0021511158913686476, "eval_loss": 6.925580024719238, "eval_runtime": 22.4294, "eval_samples_per_second": 34.91, "eval_steps_per_second": 17.477, "step": 1 }, { "epoch": 0.004302231782737295, "grad_norm": 0.23727715015411377, "learning_rate": 2e-05, "loss": 6.9281, "step": 2 }, { "epoch": 0.004302231782737295, "eval_loss": 6.925536155700684, "eval_runtime": 1.1629, "eval_samples_per_second": 673.301, "eval_steps_per_second": 337.08, "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": 10876225536.0, "train_batch_size": 2, "trial_name": null, "trial_params": null }