{ "best_global_step": null, "best_metric": null, "best_model_checkpoint": null, "epoch": 0.5, "eval_steps": 21, "global_step": 21, "is_hyper_param_search": false, "is_local_process_zero": true, "is_world_process_zero": true, "log_history": [ { "epoch": 0.023809523809523808, "grad_norm": 0.09562449157238007, "learning_rate": 0.0, "loss": 0.9296531081199646, "step": 1 }, { "epoch": 0.047619047619047616, "grad_norm": 0.08915263414382935, "learning_rate": 4e-05, "loss": 0.8963991403579712, "step": 2 }, { "epoch": 0.07142857142857142, "grad_norm": 0.09575905650854111, "learning_rate": 8e-05, "loss": 0.9559247493743896, "step": 3 }, { "epoch": 0.09523809523809523, "grad_norm": 0.09761863201856613, "learning_rate": 0.00012, "loss": 0.9154826402664185, "step": 4 }, { "epoch": 0.11904761904761904, "grad_norm": 0.11157004535198212, "learning_rate": 0.00016, "loss": 0.904577374458313, "step": 5 }, { "epoch": 0.14285714285714285, "grad_norm": 0.13675838708877563, "learning_rate": 0.0002, "loss": 0.8809080123901367, "step": 6 }, { "epoch": 0.16666666666666666, "grad_norm": 0.1358879655599594, "learning_rate": 0.00019834710743801655, "loss": 0.8010007739067078, "step": 7 }, { "epoch": 0.19047619047619047, "grad_norm": 0.1459621638059616, "learning_rate": 0.0001966942148760331, "loss": 0.7688196897506714, "step": 8 }, { "epoch": 0.21428571428571427, "grad_norm": 0.15010619163513184, "learning_rate": 0.0001950413223140496, "loss": 0.682942271232605, "step": 9 }, { "epoch": 0.23809523809523808, "grad_norm": 0.15406596660614014, "learning_rate": 0.0001933884297520661, "loss": 0.6647316217422485, "step": 10 }, { "epoch": 0.2619047619047619, "grad_norm": 0.165545254945755, "learning_rate": 0.00019173553719008265, "loss": 0.5688892006874084, "step": 11 }, { "epoch": 0.2857142857142857, "grad_norm": 0.17254289984703064, "learning_rate": 0.0001900826446280992, "loss": 0.5390745401382446, "step": 12 }, { "epoch": 0.30952380952380953, "grad_norm": 0.1956062614917755, "learning_rate": 0.0001884297520661157, "loss": 0.46194905042648315, "step": 13 }, { "epoch": 0.3333333333333333, "grad_norm": 0.19603870809078217, "learning_rate": 0.00018677685950413224, "loss": 0.41473817825317383, "step": 14 }, { "epoch": 0.35714285714285715, "grad_norm": 0.20052343606948853, "learning_rate": 0.00018512396694214878, "loss": 0.3571416139602661, "step": 15 }, { "epoch": 0.38095238095238093, "grad_norm": 0.24088889360427856, "learning_rate": 0.00018347107438016532, "loss": 0.37838655710220337, "step": 16 }, { "epoch": 0.40476190476190477, "grad_norm": 0.23278626799583435, "learning_rate": 0.00018181818181818183, "loss": 0.31288638710975647, "step": 17 }, { "epoch": 0.42857142857142855, "grad_norm": 0.18987713754177094, "learning_rate": 0.00018016528925619835, "loss": 0.25435182452201843, "step": 18 }, { "epoch": 0.4523809523809524, "grad_norm": 0.17959612607955933, "learning_rate": 0.00017851239669421489, "loss": 0.25271108746528625, "step": 19 }, { "epoch": 0.47619047619047616, "grad_norm": 0.16697828471660614, "learning_rate": 0.00017685950413223143, "loss": 0.23363591730594635, "step": 20 }, { "epoch": 0.5, "grad_norm": 0.14224942028522491, "learning_rate": 0.00017520661157024794, "loss": 0.20100688934326172, "step": 21 }, { "epoch": 0.5, "eval_loss": 0.23801279067993164, "eval_runtime": 11.6604, "eval_samples_per_second": 4.116, "eval_steps_per_second": 2.058, "step": 21 } ], "logging_steps": 1, "max_steps": 126, "num_input_tokens_seen": 0, "num_train_epochs": 3, "save_steps": 21, "stateful_callbacks": { "TrainerControl": { "args": { "should_epoch_stop": false, "should_evaluate": false, "should_log": false, "should_save": true, "should_training_stop": false }, "attributes": {} } }, "total_flos": 7339906279931904.0, "train_batch_size": 2, "trial_name": null, "trial_params": null }