{ "best_metric": null, "best_model_checkpoint": null, "epoch": 1.0, "eval_steps": 500, "global_step": 150, "is_hyper_param_search": false, "is_local_process_zero": true, "is_world_process_zero": true, "log_history": [ { "epoch": 0.13333333333333333, "grad_norm": 2.822765588760376, "learning_rate": 1.3333333333333333e-05, "loss": 2.4018, "step": 20 }, { "epoch": 0.26666666666666666, "grad_norm": 1.161797046661377, "learning_rate": 1.9659258262890683e-05, "loss": 1.9236, "step": 40 }, { "epoch": 0.4, "grad_norm": 0.9369487166404724, "learning_rate": 1.7071067811865477e-05, "loss": 1.7284, "step": 60 }, { "epoch": 0.5333333333333333, "grad_norm": 0.9531047344207764, "learning_rate": 1.2588190451025209e-05, "loss": 1.6271, "step": 80 }, { "epoch": 0.6666666666666666, "grad_norm": 1.023579478263855, "learning_rate": 7.411809548974792e-06, "loss": 1.5982, "step": 100 }, { "epoch": 0.8, "grad_norm": 0.9166858196258545, "learning_rate": 2.9289321881345257e-06, "loss": 1.5298, "step": 120 }, { "epoch": 0.9333333333333333, "grad_norm": 0.957330584526062, "learning_rate": 3.4074173710931804e-07, "loss": 1.5615, "step": 140 }, { "epoch": 1.0, "step": 150, "total_flos": 11777605632000.0, "train_loss": 1.7528484280904133, "train_runtime": 2910.6477, "train_samples_per_second": 0.819, "train_steps_per_second": 0.052 } ], "logging_steps": 20, "max_steps": 150, "num_input_tokens_seen": 0, "num_train_epochs": 1, "save_steps": 100, "stateful_callbacks": { "TrainerControl": { "args": { "should_epoch_stop": false, "should_evaluate": false, "should_log": false, "should_save": true, "should_training_stop": false }, "attributes": {} } }, "total_flos": 11777605632000.0, "train_batch_size": 4, "trial_name": null, "trial_params": null }