{ "best_metric": null, "best_model_checkpoint": null, "epoch": 4.5607476635514015, "eval_steps": 500, "global_step": 30, "is_hyper_param_search": false, "is_local_process_zero": true, "is_world_process_zero": true, "log_history": [ { "epoch": 0.14953271028037382, "grad_norm": 12.843625877113869, "learning_rate": 4.986304738420684e-06, "loss": 0.8827, "step": 1 }, { "epoch": 0.7476635514018691, "grad_norm": 17.112854785869143, "learning_rate": 4.665063509461098e-06, "loss": 0.5415, "step": 5 }, { "epoch": 1.514018691588785, "grad_norm": 1.2913937457330225, "learning_rate": 3.7500000000000005e-06, "loss": 0.2689, "step": 10 }, { "epoch": 2.2803738317757007, "grad_norm": 0.8391183302335447, "learning_rate": 2.5e-06, "loss": 0.2245, "step": 15 }, { "epoch": 3.046728971962617, "grad_norm": 1.1744266942018853, "learning_rate": 1.2500000000000007e-06, "loss": 0.2057, "step": 20 }, { "epoch": 3.794392523364486, "grad_norm": 0.6974419605317868, "learning_rate": 3.3493649053890325e-07, "loss": 0.1717, "step": 25 }, { "epoch": 4.5607476635514015, "grad_norm": 0.6095186289099851, "learning_rate": 0.0, "loss": 0.1753, "step": 30 }, { "epoch": 4.5607476635514015, "step": 30, "total_flos": 4378551058432.0, "train_loss": 0.2759698271751404, "train_runtime": 650.5481, "train_samples_per_second": 3.266, "train_steps_per_second": 0.046 } ], "logging_steps": 5, "max_steps": 30, "num_input_tokens_seen": 0, "num_train_epochs": 5, "save_steps": 500, "stateful_callbacks": { "TrainerControl": { "args": { "should_epoch_stop": false, "should_evaluate": false, "should_log": false, "should_save": false, "should_training_stop": false }, "attributes": {} } }, "total_flos": 4378551058432.0, "train_batch_size": 1, "trial_name": null, "trial_params": null }