{ "best_metric": null, "best_model_checkpoint": null, "epoch": 0.030303030303030304, "eval_steps": 20, "global_step": 10, "is_hyper_param_search": false, "is_local_process_zero": true, "is_world_process_zero": true, "log_history": [ { "epoch": 0.0030303030303030303, "grad_norm": 119805.9375, "learning_rate": 4.0000000000000007e-10, "loss": 28.5896, "step": 1 }, { "epoch": 0.006060606060606061, "grad_norm": 120685.921875, "learning_rate": 8.000000000000001e-10, "loss": 27.3248, "step": 2 }, { "epoch": 0.00909090909090909, "grad_norm": 124471.25, "learning_rate": 1.2e-09, "loss": 27.2317, "step": 3 }, { "epoch": 0.012121212121212121, "grad_norm": 111007.1953125, "learning_rate": 1.6000000000000003e-09, "loss": 29.5275, "step": 4 }, { "epoch": 0.015151515151515152, "grad_norm": 118682.8984375, "learning_rate": 2e-09, "loss": 27.1987, "step": 5 }, { "epoch": 0.01818181818181818, "grad_norm": 123659.140625, "learning_rate": 1.978147600733806e-09, "loss": 26.3259, "step": 6 }, { "epoch": 0.021212121212121213, "grad_norm": 116267.609375, "learning_rate": 1.913545457642601e-09, "loss": 27.8884, "step": 7 }, { "epoch": 0.024242424242424242, "grad_norm": 126480.1875, "learning_rate": 1.8090169943749476e-09, "loss": 25.6212, "step": 8 }, { "epoch": 0.02727272727272727, "grad_norm": 123124.6328125, "learning_rate": 1.6691306063588583e-09, "loss": 26.5633, "step": 9 }, { "epoch": 0.030303030303030304, "grad_norm": 129796.8515625, "learning_rate": 1.5000000000000002e-09, "loss": 24.9898, "step": 10 } ], "logging_steps": 1, "max_steps": 20, "num_input_tokens_seen": 0, "num_train_epochs": 1, "save_steps": 10, "stateful_callbacks": { "TrainerControl": { "args": { "should_epoch_stop": false, "should_evaluate": false, "should_log": false, "should_save": true, "should_training_stop": false }, "attributes": {} } }, "total_flos": 1.627468166725632e+16, "train_batch_size": 3, "trial_name": null, "trial_params": null }