{ "best_metric": 0.83, "best_model_checkpoint": "distilhubert-finetuned-gtzan/checkpoint-56", "epoch": 4.0, "eval_steps": 500, "global_step": 113, "is_hyper_param_search": false, "is_local_process_zero": true, "is_world_process_zero": true, "log_history": [ { "epoch": 0.18, "learning_rate": 3.5714285714285718e-06, "loss": 0.0338, "step": 5 }, { "epoch": 0.35, "learning_rate": 7.1428571428571436e-06, "loss": 0.0053, "step": 10 }, { "epoch": 0.53, "learning_rate": 9.920634920634922e-06, "loss": 0.0056, "step": 15 }, { "epoch": 0.71, "learning_rate": 9.523809523809525e-06, "loss": 0.0437, "step": 20 }, { "epoch": 0.88, "learning_rate": 9.126984126984127e-06, "loss": 0.0017, "step": 25 }, { "epoch": 0.99, "eval_accuracy": 0.82, "eval_loss": 1.0909959077835083, "eval_runtime": 72.1207, "eval_samples_per_second": 1.387, "eval_steps_per_second": 0.18, "step": 28 }, { "epoch": 1.06, "learning_rate": 8.730158730158731e-06, "loss": 0.0013, "step": 30 }, { "epoch": 1.24, "learning_rate": 8.333333333333334e-06, "loss": 0.0373, "step": 35 }, { "epoch": 1.42, "learning_rate": 7.936507936507936e-06, "loss": 0.0041, "step": 40 }, { "epoch": 1.59, "learning_rate": 7.53968253968254e-06, "loss": 0.0012, "step": 45 }, { "epoch": 1.77, "learning_rate": 7.1428571428571436e-06, "loss": 0.0338, "step": 50 }, { "epoch": 1.95, "learning_rate": 6.746031746031747e-06, "loss": 0.0143, "step": 55 }, { "epoch": 1.98, "eval_accuracy": 0.83, "eval_loss": 1.1379410028457642, "eval_runtime": 71.5138, "eval_samples_per_second": 1.398, "eval_steps_per_second": 0.182, "step": 56 }, { "epoch": 2.12, "learning_rate": 6.349206349206349e-06, "loss": 0.036, "step": 60 }, { "epoch": 2.3, "learning_rate": 5.9523809523809525e-06, "loss": 0.001, "step": 65 }, { "epoch": 2.48, "learning_rate": 5.555555555555557e-06, "loss": 0.0412, "step": 70 }, { "epoch": 2.65, "learning_rate": 5.15873015873016e-06, "loss": 0.001, "step": 75 }, { "epoch": 2.83, "learning_rate": 4.761904761904762e-06, "loss": 0.01, "step": 80 }, { "epoch": 2.97, "eval_accuracy": 0.82, "eval_loss": 1.1369585990905762, "eval_runtime": 71.7929, "eval_samples_per_second": 1.393, "eval_steps_per_second": 0.181, "step": 84 }, { "epoch": 3.01, "learning_rate": 4.365079365079366e-06, "loss": 0.001, "step": 85 }, { "epoch": 3.19, "learning_rate": 3.968253968253968e-06, "loss": 0.0476, "step": 90 }, { "epoch": 3.36, "learning_rate": 3.5714285714285718e-06, "loss": 0.0009, "step": 95 }, { "epoch": 3.54, "learning_rate": 3.1746031746031746e-06, "loss": 0.0009, "step": 100 }, { "epoch": 3.72, "learning_rate": 2.7777777777777783e-06, "loss": 0.001, "step": 105 }, { "epoch": 3.89, "learning_rate": 2.380952380952381e-06, "loss": 0.0377, "step": 110 }, { "epoch": 4.0, "eval_accuracy": 0.82, "eval_loss": 1.142837643623352, "eval_runtime": 71.2388, "eval_samples_per_second": 1.404, "eval_steps_per_second": 0.182, "step": 113 } ], "logging_steps": 5, "max_steps": 140, "num_train_epochs": 5, "save_steps": 500, "total_flos": 2.4535953098496e+17, "trial_name": null, "trial_params": null }