{
  "best_metric": 0.61,
  "best_model_checkpoint": "distilhubert-finetuned-gtzan/checkpoint-113",
  "epoch": 2.0,
  "eval_steps": 500,
  "global_step": 113,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.09,
      "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
    },
    {
      "epoch": 1.06,
      "learning_rate": 0.000496031746031746,
      "loss": 1.3528,
      "step": 60
    },
    {
      "epoch": 1.15,
      "learning_rate": 0.0004910714285714286,
      "loss": 1.507,
      "step": 65
    },
    {
      "epoch": 1.24,
      "learning_rate": 0.0004861111111111111,
      "loss": 1.504,
      "step": 70
    },
    {
      "epoch": 1.33,
      "learning_rate": 0.0004811507936507937,
      "loss": 1.3719,
      "step": 75
    },
    {
      "epoch": 1.42,
      "learning_rate": 0.0004761904761904762,
      "loss": 1.2284,
      "step": 80
    },
    {
      "epoch": 1.5,
      "learning_rate": 0.00047123015873015874,
      "loss": 1.2997,
      "step": 85
    },
    {
      "epoch": 1.59,
      "learning_rate": 0.0004662698412698413,
      "loss": 1.2284,
      "step": 90
    },
    {
      "epoch": 1.68,
      "learning_rate": 0.00046130952380952383,
      "loss": 1.3332,
      "step": 95
    },
    {
      "epoch": 1.77,
      "learning_rate": 0.0004563492063492063,
      "loss": 1.1091,
      "step": 100
    },
    {
      "epoch": 1.86,
      "learning_rate": 0.0004513888888888889,
      "loss": 1.1335,
      "step": 105
    },
    {
      "epoch": 1.95,
      "learning_rate": 0.00044642857142857147,
      "loss": 1.1313,
      "step": 110
    },
    {
      "epoch": 2.0,
      "eval_accuracy": 0.61,
      "eval_loss": 1.175675868988037,
      "eval_runtime": 71.9077,
      "eval_samples_per_second": 1.391,
      "eval_steps_per_second": 0.181,
      "step": 113
    }
  ],
  "logging_steps": 5,
  "max_steps": 560,
  "num_train_epochs": 10,
  "save_steps": 500,
  "total_flos": 1.2267976549248e+17,
  "trial_name": null,
  "trial_params": null
}