{ "best_global_step": null, "best_metric": null, "best_model_checkpoint": null, "epoch": 1.0, "eval_steps": 500, "global_step": 10, "is_hyper_param_search": false, "is_local_process_zero": true, "is_world_process_zero": true, "log_history": [ { "epoch": 0.1, "grad_norm": 100.40143726200853, "learning_rate": 0.0, "loss": 0.5811, "step": 1 }, { "epoch": 0.2, "grad_norm": 129.71402585686204, "learning_rate": 1e-05, "loss": 0.467, "step": 2 }, { "epoch": 0.3, "grad_norm": 29.015093040604047, "learning_rate": 9.698463103929542e-06, "loss": 0.1934, "step": 3 }, { "epoch": 0.4, "grad_norm": 15.432068211700624, "learning_rate": 8.83022221559489e-06, "loss": 0.2041, "step": 4 }, { "epoch": 0.5, "grad_norm": 11.999880389822504, "learning_rate": 7.500000000000001e-06, "loss": 0.2021, "step": 5 }, { "epoch": 0.6, "grad_norm": 6.0339581455964515, "learning_rate": 5.8682408883346535e-06, "loss": 0.1701, "step": 6 }, { "epoch": 0.7, "grad_norm": 11.554575721981072, "learning_rate": 4.131759111665349e-06, "loss": 0.2163, "step": 7 }, { "epoch": 0.8, "grad_norm": 6.001520320866495, "learning_rate": 2.5000000000000015e-06, "loss": 0.1705, "step": 8 }, { "epoch": 0.9, "grad_norm": 7.633047084071537, "learning_rate": 1.1697777844051105e-06, "loss": 0.1862, "step": 9 }, { "epoch": 1.0, "grad_norm": 9.387443274917667, "learning_rate": 3.015368960704584e-07, "loss": 0.1394, "step": 10 }, { "epoch": 1.0, "step": 10, "total_flos": 796236840960.0, "train_loss": 0.25302437841892245, "train_runtime": 1467.3943, "train_samples_per_second": 0.027, "train_steps_per_second": 0.007 } ], "logging_steps": 1, "max_steps": 10, "num_input_tokens_seen": 0, "num_train_epochs": 1, "save_steps": 500, "stateful_callbacks": { "TrainerControl": { "args": { "should_epoch_stop": false, "should_evaluate": false, "should_log": false, "should_save": true, "should_training_stop": true }, "attributes": {} } }, "total_flos": 796236840960.0, "train_batch_size": 1, "trial_name": null, "trial_params": null }