{ "best_global_step": null, "best_metric": null, "best_model_checkpoint": null, "epoch": 1.0, "eval_steps": 500, "global_step": 50, "is_hyper_param_search": false, "is_local_process_zero": true, "is_world_process_zero": true, "log_history": [ { "epoch": 0.2, "grad_norm": 6.699235885703409, "learning_rate": 9.806308479691595e-06, "loss": 3.3526, "step": 10 }, { "epoch": 0.4, "grad_norm": 7.265192108764275, "learning_rate": 7.795964517353734e-06, "loss": 0.5978, "step": 20 }, { "epoch": 0.6, "grad_norm": 5.588145236673648, "learning_rate": 4.477357683661734e-06, "loss": 0.6108, "step": 30 }, { "epoch": 0.8, "grad_norm": 7.117965141671009, "learning_rate": 1.4033009983067454e-06, "loss": 0.6467, "step": 40 }, { "epoch": 1.0, "grad_norm": 7.806578743138265, "learning_rate": 1.2179748700879013e-08, "loss": 0.6008, "step": 50 }, { "epoch": 1.0, "step": 50, "total_flos": 350412570624.0, "train_loss": 1.1617375755310058, "train_runtime": 75.1787, "train_samples_per_second": 21.283, "train_steps_per_second": 0.665 } ], "logging_steps": 10, "max_steps": 50, "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": 350412570624.0, "train_batch_size": 4, "trial_name": null, "trial_params": null }