{ "best_global_step": null, "best_metric": null, "best_model_checkpoint": null, "epoch": 5.0, "eval_steps": 500, "global_step": 35, "is_hyper_param_search": false, "is_local_process_zero": true, "is_world_process_zero": true, "log_history": [ { "epoch": 0.8, "grad_norm": 3.259864531321342, "learning_rate": 4e-05, "loss": 1.4742, "step": 5 }, { "epoch": 1.48, "grad_norm": 0.8667296122043516, "learning_rate": 3.7486932322891646e-05, "loss": 1.1805, "step": 10 }, { "epoch": 2.16, "grad_norm": 1.1702501570497998, "learning_rate": 3.057928020653925e-05, "loss": 1.0103, "step": 15 }, { "epoch": 2.96, "grad_norm": 0.5594678761762011, "learning_rate": 2.1012983376774255e-05, "loss": 0.8829, "step": 20 }, { "epoch": 3.64, "grad_norm": 0.4663773011398953, "learning_rate": 1.1192116968847313e-05, "loss": 0.8153, "step": 25 }, { "epoch": 4.32, "grad_norm": 0.4013367647254134, "learning_rate": 3.584731175854479e-06, "loss": 0.7423, "step": 30 }, { "epoch": 5.0, "grad_norm": 0.4269932011983022, "learning_rate": 1.0261353216209691e-07, "loss": 0.707, "step": 35 }, { "epoch": 5.0, "step": 35, "total_flos": 60301855162368.0, "train_loss": 0.9732139451163155, "train_runtime": 2951.2184, "train_samples_per_second": 1.355, "train_steps_per_second": 0.012 } ], "logging_steps": 5, "max_steps": 35, "num_input_tokens_seen": 0, "num_train_epochs": 5, "save_steps": 100, "stateful_callbacks": { "TrainerControl": { "args": { "should_epoch_stop": false, "should_evaluate": false, "should_log": false, "should_save": false, "should_training_stop": false }, "attributes": {} } }, "total_flos": 60301855162368.0, "train_batch_size": 1, "trial_name": null, "trial_params": null }