{ "best_metric": 0.27, "best_model_checkpoint": "distilhubert-finetuned-gtzan/checkpoint-56", "epoch": 0.9911504424778761, "eval_steps": 500, "global_step": 56, "is_hyper_param_search": false, "is_local_process_zero": true, "is_world_process_zero": true, "log_history": [ { "epoch": 0.09, "learning_rate": 4.464285714285714e-05, "loss": 2.2976, "step": 5 }, { "epoch": 0.18, "learning_rate": 8.928571428571429e-05, "loss": 2.2855, "step": 10 }, { "epoch": 0.27, "learning_rate": 0.00013392857142857144, "loss": 2.2307, "step": 15 }, { "epoch": 0.35, "learning_rate": 0.00017857142857142857, "loss": 2.1327, "step": 20 }, { "epoch": 0.44, "learning_rate": 0.00022321428571428573, "loss": 2.0339, "step": 25 }, { "epoch": 0.53, "learning_rate": 0.00026785714285714287, "loss": 1.9633, "step": 30 }, { "epoch": 0.62, "learning_rate": 0.0003125, "loss": 1.8021, "step": 35 }, { "epoch": 0.71, "learning_rate": 0.00035714285714285714, "loss": 1.6938, "step": 40 }, { "epoch": 0.8, "learning_rate": 0.00040178571428571433, "loss": 1.5271, "step": 45 }, { "epoch": 0.88, "learning_rate": 0.00044642857142857147, "loss": 1.4038, "step": 50 }, { "epoch": 0.97, "learning_rate": 0.0004910714285714286, "loss": 1.496, "step": 55 }, { "epoch": 0.99, "eval_accuracy": 0.27, "eval_loss": 1.8467493057250977, "eval_runtime": 72.5718, "eval_samples_per_second": 1.378, "eval_steps_per_second": 0.179, "step": 56 } ], "logging_steps": 5, "max_steps": 560, "num_train_epochs": 10, "save_steps": 500, "total_flos": 6.133988274624e+16, "trial_name": null, "trial_params": null }