{ "best_metric": null, "best_model_checkpoint": null, "epoch": 1.0, "eval_steps": 500, "global_step": 586, "is_hyper_param_search": false, "is_local_process_zero": true, "is_world_process_zero": true, "log_history": [ { "epoch": 0.08532423208191127, "grad_norm": 1.4077415466308594, "learning_rate": 2.0000000000000003e-06, "loss": 3.7038, "step": 50 }, { "epoch": 0.17064846416382254, "grad_norm": 1.4979158639907837, "learning_rate": 4.000000000000001e-06, "loss": 3.4791, "step": 100 }, { "epoch": 0.25597269624573377, "grad_norm": 1.5558234453201294, "learning_rate": 6e-06, "loss": 3.1832, "step": 150 }, { "epoch": 0.3412969283276451, "grad_norm": 6.143394470214844, "learning_rate": 8.000000000000001e-06, "loss": 2.0431, "step": 200 }, { "epoch": 0.42662116040955633, "grad_norm": 2.0573947429656982, "learning_rate": 1e-05, "loss": 1.2995, "step": 250 }, { "epoch": 0.5119453924914675, "grad_norm": 0.24337443709373474, "learning_rate": 1.2e-05, "loss": 1.6017, "step": 300 }, { "epoch": 0.5972696245733788, "grad_norm": 0.3346450626850128, "learning_rate": 1.4e-05, "loss": 1.5664, "step": 350 }, { "epoch": 0.6825938566552902, "grad_norm": 0.5089182257652283, "learning_rate": 1.6000000000000003e-05, "loss": 1.5137, "step": 400 }, { "epoch": 0.7679180887372014, "grad_norm": 0.6959832906723022, "learning_rate": 1.8e-05, "loss": 1.4477, "step": 450 }, { "epoch": 0.8532423208191127, "grad_norm": 1.5926487445831299, "learning_rate": 2e-05, "loss": 1.1669, "step": 500 }, { "epoch": 0.9385665529010239, "grad_norm": 1.663642168045044, "learning_rate": 8.372093023255815e-06, "loss": 0.7714, "step": 550 } ], "logging_steps": 50, "max_steps": 586, "num_input_tokens_seen": 0, "num_train_epochs": 1, "save_steps": 1000, "stateful_callbacks": { "TrainerControl": { "args": { "should_epoch_stop": false, "should_evaluate": false, "should_log": false, "should_save": true, "should_training_stop": true }, "attributes": {} } }, "total_flos": 0.0, "train_batch_size": 8, "trial_name": null, "trial_params": null }