{ "best_metric": null, "best_model_checkpoint": null, "epoch": 1.0, "eval_steps": 500, "global_step": 48, "is_hyper_param_search": false, "is_local_process_zero": true, "is_world_process_zero": true, "log_history": [ { "epoch": 0.10416666666666667, "grad_norm": 10.75, "learning_rate": 4.978103154668534e-05, "loss": 0.9914, "step": 5 }, { "epoch": 0.20833333333333334, "grad_norm": 4.28125, "learning_rate": 4.7366320839325864e-05, "loss": 0.55, "step": 10 }, { "epoch": 0.3125, "grad_norm": 1.984375, "learning_rate": 4.255543864307431e-05, "loss": 0.4382, "step": 15 }, { "epoch": 0.4166666666666667, "grad_norm": 1.2578125, "learning_rate": 3.5928648351858027e-05, "loss": 0.3833, "step": 20 }, { "epoch": 0.5208333333333334, "grad_norm": 1.3515625, "learning_rate": 2.828523867580628e-05, "loss": 0.3536, "step": 25 }, { "epoch": 0.625, "grad_norm": 1.2734375, "learning_rate": 2.054711762656369e-05, "loss": 0.3548, "step": 30 }, { "epoch": 0.7291666666666666, "grad_norm": 1.1171875, "learning_rate": 1.364761680517269e-05, "loss": 0.3445, "step": 35 }, { "epoch": 0.8333333333333334, "grad_norm": 1.0078125, "learning_rate": 8.418917836480417e-06, "loss": 0.3189, "step": 40 }, { "epoch": 0.9375, "grad_norm": 0.8203125, "learning_rate": 5.491678983489372e-06, "loss": 0.3172, "step": 45 }, { "epoch": 1.0, "step": 48, "total_flos": 1.355802795311104e+16, "train_loss": 0.44515162458022434, "train_runtime": 298.6439, "train_samples_per_second": 0.161, "train_steps_per_second": 0.161 } ], "logging_steps": 5, "max_steps": 48, "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": true }, "attributes": {} } }, "total_flos": 1.355802795311104e+16, "train_batch_size": 1, "trial_name": null, "trial_params": null }