{
  "best_metric": 0.73,
  "best_model_checkpoint": "distilhubert-finetuned-gtzan/checkpoint-282",
  "epoch": 6.0,
  "eval_steps": 500,
  "global_step": 339,
  "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
    },
    {
      "epoch": 2.04,
      "learning_rate": 0.00044146825396825396,
      "loss": 1.1765,
      "step": 115
    },
    {
      "epoch": 2.12,
      "learning_rate": 0.0004365079365079365,
      "loss": 1.0945,
      "step": 120
    },
    {
      "epoch": 2.21,
      "learning_rate": 0.00043154761904761905,
      "loss": 0.9198,
      "step": 125
    },
    {
      "epoch": 2.3,
      "learning_rate": 0.0004265873015873016,
      "loss": 1.1504,
      "step": 130
    },
    {
      "epoch": 2.39,
      "learning_rate": 0.00042162698412698415,
      "loss": 1.03,
      "step": 135
    },
    {
      "epoch": 2.48,
      "learning_rate": 0.0004166666666666667,
      "loss": 1.294,
      "step": 140
    },
    {
      "epoch": 2.57,
      "learning_rate": 0.0004117063492063492,
      "loss": 0.918,
      "step": 145
    },
    {
      "epoch": 2.65,
      "learning_rate": 0.00040674603174603173,
      "loss": 0.9529,
      "step": 150
    },
    {
      "epoch": 2.74,
      "learning_rate": 0.00040178571428571433,
      "loss": 0.9366,
      "step": 155
    },
    {
      "epoch": 2.83,
      "learning_rate": 0.0003968253968253968,
      "loss": 0.9388,
      "step": 160
    },
    {
      "epoch": 2.92,
      "learning_rate": 0.00039186507936507937,
      "loss": 1.2432,
      "step": 165
    },
    {
      "epoch": 2.99,
      "eval_accuracy": 0.58,
      "eval_loss": 1.3774330615997314,
      "eval_runtime": 72.0805,
      "eval_samples_per_second": 1.387,
      "eval_steps_per_second": 0.18,
      "step": 169
    },
    {
      "epoch": 3.01,
      "learning_rate": 0.0003869047619047619,
      "loss": 0.8342,
      "step": 170
    },
    {
      "epoch": 3.1,
      "learning_rate": 0.0003819444444444444,
      "loss": 1.2782,
      "step": 175
    },
    {
      "epoch": 3.19,
      "learning_rate": 0.000376984126984127,
      "loss": 0.9997,
      "step": 180
    },
    {
      "epoch": 3.27,
      "learning_rate": 0.00037202380952380956,
      "loss": 0.6668,
      "step": 185
    },
    {
      "epoch": 3.36,
      "learning_rate": 0.00036706349206349205,
      "loss": 0.7267,
      "step": 190
    },
    {
      "epoch": 3.45,
      "learning_rate": 0.0003621031746031746,
      "loss": 0.892,
      "step": 195
    },
    {
      "epoch": 3.54,
      "learning_rate": 0.00035714285714285714,
      "loss": 1.0096,
      "step": 200
    },
    {
      "epoch": 3.63,
      "learning_rate": 0.0003521825396825397,
      "loss": 0.8909,
      "step": 205
    },
    {
      "epoch": 3.72,
      "learning_rate": 0.00034722222222222224,
      "loss": 1.0591,
      "step": 210
    },
    {
      "epoch": 3.81,
      "learning_rate": 0.0003422619047619048,
      "loss": 0.6526,
      "step": 215
    },
    {
      "epoch": 3.89,
      "learning_rate": 0.00033730158730158733,
      "loss": 0.847,
      "step": 220
    },
    {
      "epoch": 3.98,
      "learning_rate": 0.0003323412698412698,
      "loss": 0.7301,
      "step": 225
    },
    {
      "epoch": 4.0,
      "eval_accuracy": 0.66,
      "eval_loss": 0.9738250970840454,
      "eval_runtime": 70.9865,
      "eval_samples_per_second": 1.409,
      "eval_steps_per_second": 0.183,
      "step": 226
    },
    {
      "epoch": 4.07,
      "learning_rate": 0.00032738095238095237,
      "loss": 0.8506,
      "step": 230
    },
    {
      "epoch": 4.16,
      "learning_rate": 0.00032242063492063497,
      "loss": 0.642,
      "step": 235
    },
    {
      "epoch": 4.25,
      "learning_rate": 0.00031746031746031746,
      "loss": 0.6132,
      "step": 240
    },
    {
      "epoch": 4.34,
      "learning_rate": 0.0003125,
      "loss": 0.6279,
      "step": 245
    },
    {
      "epoch": 4.42,
      "learning_rate": 0.00030753968253968255,
      "loss": 0.7194,
      "step": 250
    },
    {
      "epoch": 4.51,
      "learning_rate": 0.00030257936507936505,
      "loss": 0.7127,
      "step": 255
    },
    {
      "epoch": 4.6,
      "learning_rate": 0.00029761904761904765,
      "loss": 0.5318,
      "step": 260
    },
    {
      "epoch": 4.69,
      "learning_rate": 0.0002926587301587302,
      "loss": 0.7127,
      "step": 265
    },
    {
      "epoch": 4.78,
      "learning_rate": 0.0002876984126984127,
      "loss": 0.5685,
      "step": 270
    },
    {
      "epoch": 4.87,
      "learning_rate": 0.00028273809523809523,
      "loss": 0.6034,
      "step": 275
    },
    {
      "epoch": 4.96,
      "learning_rate": 0.0002777777777777778,
      "loss": 0.5192,
      "step": 280
    },
    {
      "epoch": 4.99,
      "eval_accuracy": 0.73,
      "eval_loss": 0.9078372120857239,
      "eval_runtime": 71.0414,
      "eval_samples_per_second": 1.408,
      "eval_steps_per_second": 0.183,
      "step": 282
    },
    {
      "epoch": 5.04,
      "learning_rate": 0.0002728174603174603,
      "loss": 0.4625,
      "step": 285
    },
    {
      "epoch": 5.13,
      "learning_rate": 0.00026785714285714287,
      "loss": 0.5618,
      "step": 290
    },
    {
      "epoch": 5.22,
      "learning_rate": 0.0002628968253968254,
      "loss": 0.4268,
      "step": 295
    },
    {
      "epoch": 5.31,
      "learning_rate": 0.00025793650793650796,
      "loss": 0.545,
      "step": 300
    },
    {
      "epoch": 5.4,
      "learning_rate": 0.00025297619047619046,
      "loss": 0.4513,
      "step": 305
    },
    {
      "epoch": 5.49,
      "learning_rate": 0.000248015873015873,
      "loss": 0.4566,
      "step": 310
    },
    {
      "epoch": 5.58,
      "learning_rate": 0.00024305555555555555,
      "loss": 0.4533,
      "step": 315
    },
    {
      "epoch": 5.66,
      "learning_rate": 0.0002380952380952381,
      "loss": 0.4453,
      "step": 320
    },
    {
      "epoch": 5.75,
      "learning_rate": 0.00023313492063492064,
      "loss": 0.4401,
      "step": 325
    },
    {
      "epoch": 5.84,
      "learning_rate": 0.00022817460317460316,
      "loss": 0.3283,
      "step": 330
    },
    {
      "epoch": 5.93,
      "learning_rate": 0.00022321428571428573,
      "loss": 0.4163,
      "step": 335
    },
    {
      "epoch": 6.0,
      "eval_accuracy": 0.71,
      "eval_loss": 0.9995945692062378,
      "eval_runtime": 71.0596,
      "eval_samples_per_second": 1.407,
      "eval_steps_per_second": 0.183,
      "step": 339
    }
  ],
  "logging_steps": 5,
  "max_steps": 560,
  "num_train_epochs": 10,
  "save_steps": 500,
  "total_flos": 3.6803929647744e+17,
  "trial_name": null,
  "trial_params": null
}