{
  "best_metric": 1.0,
  "best_model_checkpoint": "bit-50-Otitis-binary\\checkpoint-312",
  "epoch": 46.15384615384615,
  "global_step": 450,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.92,
      "eval_accuracy": 0.6142857142857143,
      "eval_loss": 0.828590989112854,
      "eval_runtime": 1.3305,
      "eval_samples_per_second": 52.613,
      "eval_steps_per_second": 3.758,
      "step": 9
    },
    {
      "epoch": 1.03,
      "learning_rate": 1.1111111111111112e-05,
      "loss": 0.9957,
      "step": 10
    },
    {
      "epoch": 1.95,
      "eval_accuracy": 0.6714285714285714,
      "eval_loss": 0.5884611010551453,
      "eval_runtime": 0.9182,
      "eval_samples_per_second": 76.24,
      "eval_steps_per_second": 5.446,
      "step": 19
    },
    {
      "epoch": 2.05,
      "learning_rate": 2.2222222222222223e-05,
      "loss": 0.6913,
      "step": 20
    },
    {
      "epoch": 2.97,
      "eval_accuracy": 0.8,
      "eval_loss": 0.4655839502811432,
      "eval_runtime": 0.9168,
      "eval_samples_per_second": 76.355,
      "eval_steps_per_second": 5.454,
      "step": 29
    },
    {
      "epoch": 3.08,
      "learning_rate": 3.3333333333333335e-05,
      "loss": 0.5636,
      "step": 30
    },
    {
      "epoch": 4.0,
      "eval_accuracy": 0.7142857142857143,
      "eval_loss": 0.5395815372467041,
      "eval_runtime": 0.9219,
      "eval_samples_per_second": 75.926,
      "eval_steps_per_second": 5.423,
      "step": 39
    },
    {
      "epoch": 4.1,
      "learning_rate": 4.4444444444444447e-05,
      "loss": 0.5036,
      "step": 40
    },
    {
      "epoch": 4.92,
      "eval_accuracy": 0.8714285714285714,
      "eval_loss": 0.31175073981285095,
      "eval_runtime": 0.9263,
      "eval_samples_per_second": 75.568,
      "eval_steps_per_second": 5.398,
      "step": 48
    },
    {
      "epoch": 5.13,
      "learning_rate": 4.938271604938271e-05,
      "loss": 0.4238,
      "step": 50
    },
    {
      "epoch": 5.95,
      "eval_accuracy": 0.7714285714285715,
      "eval_loss": 0.500621497631073,
      "eval_runtime": 0.962,
      "eval_samples_per_second": 72.767,
      "eval_steps_per_second": 5.198,
      "step": 58
    },
    {
      "epoch": 6.15,
      "learning_rate": 4.814814814814815e-05,
      "loss": 0.4115,
      "step": 60
    },
    {
      "epoch": 6.97,
      "eval_accuracy": 0.8571428571428571,
      "eval_loss": 0.30729931592941284,
      "eval_runtime": 0.9315,
      "eval_samples_per_second": 75.145,
      "eval_steps_per_second": 5.367,
      "step": 68
    },
    {
      "epoch": 7.18,
      "learning_rate": 4.691358024691358e-05,
      "loss": 0.3887,
      "step": 70
    },
    {
      "epoch": 8.0,
      "eval_accuracy": 0.8714285714285714,
      "eval_loss": 0.2601815164089203,
      "eval_runtime": 0.9413,
      "eval_samples_per_second": 74.368,
      "eval_steps_per_second": 5.312,
      "step": 78
    },
    {
      "epoch": 8.21,
      "learning_rate": 4.567901234567901e-05,
      "loss": 0.3072,
      "step": 80
    },
    {
      "epoch": 8.92,
      "eval_accuracy": 0.8285714285714286,
      "eval_loss": 0.2863541543483734,
      "eval_runtime": 0.9861,
      "eval_samples_per_second": 70.987,
      "eval_steps_per_second": 5.071,
      "step": 87
    },
    {
      "epoch": 9.23,
      "learning_rate": 4.4444444444444447e-05,
      "loss": 0.414,
      "step": 90
    },
    {
      "epoch": 9.95,
      "eval_accuracy": 0.8714285714285714,
      "eval_loss": 0.3076455593109131,
      "eval_runtime": 0.9303,
      "eval_samples_per_second": 75.243,
      "eval_steps_per_second": 5.374,
      "step": 97
    },
    {
      "epoch": 10.26,
      "learning_rate": 4.3209876543209875e-05,
      "loss": 0.2338,
      "step": 100
    },
    {
      "epoch": 10.97,
      "eval_accuracy": 0.9571428571428572,
      "eval_loss": 0.14239218831062317,
      "eval_runtime": 0.942,
      "eval_samples_per_second": 74.31,
      "eval_steps_per_second": 5.308,
      "step": 107
    },
    {
      "epoch": 11.28,
      "learning_rate": 4.197530864197531e-05,
      "loss": 0.2929,
      "step": 110
    },
    {
      "epoch": 12.0,
      "eval_accuracy": 0.9714285714285714,
      "eval_loss": 0.140659362077713,
      "eval_runtime": 0.9302,
      "eval_samples_per_second": 75.252,
      "eval_steps_per_second": 5.375,
      "step": 117
    },
    {
      "epoch": 12.31,
      "learning_rate": 4.074074074074074e-05,
      "loss": 0.2749,
      "step": 120
    },
    {
      "epoch": 12.92,
      "eval_accuracy": 0.9428571428571428,
      "eval_loss": 0.1332792341709137,
      "eval_runtime": 0.9308,
      "eval_samples_per_second": 75.204,
      "eval_steps_per_second": 5.372,
      "step": 126
    },
    {
      "epoch": 13.33,
      "learning_rate": 3.950617283950617e-05,
      "loss": 0.2115,
      "step": 130
    },
    {
      "epoch": 13.95,
      "eval_accuracy": 0.9285714285714286,
      "eval_loss": 0.11323489248752594,
      "eval_runtime": 0.926,
      "eval_samples_per_second": 75.595,
      "eval_steps_per_second": 5.4,
      "step": 136
    },
    {
      "epoch": 14.36,
      "learning_rate": 3.82716049382716e-05,
      "loss": 0.1988,
      "step": 140
    },
    {
      "epoch": 14.97,
      "eval_accuracy": 0.9571428571428572,
      "eval_loss": 0.10268964618444443,
      "eval_runtime": 0.9214,
      "eval_samples_per_second": 75.969,
      "eval_steps_per_second": 5.426,
      "step": 146
    },
    {
      "epoch": 15.38,
      "learning_rate": 3.7037037037037037e-05,
      "loss": 0.1931,
      "step": 150
    },
    {
      "epoch": 16.0,
      "eval_accuracy": 0.9857142857142858,
      "eval_loss": 0.04763292521238327,
      "eval_runtime": 0.9302,
      "eval_samples_per_second": 75.249,
      "eval_steps_per_second": 5.375,
      "step": 156
    },
    {
      "epoch": 16.41,
      "learning_rate": 3.580246913580247e-05,
      "loss": 0.1597,
      "step": 160
    },
    {
      "epoch": 16.92,
      "eval_accuracy": 0.9571428571428572,
      "eval_loss": 0.10970413684844971,
      "eval_runtime": 0.9199,
      "eval_samples_per_second": 76.095,
      "eval_steps_per_second": 5.435,
      "step": 165
    },
    {
      "epoch": 17.44,
      "learning_rate": 3.45679012345679e-05,
      "loss": 0.1786,
      "step": 170
    },
    {
      "epoch": 17.95,
      "eval_accuracy": 0.9428571428571428,
      "eval_loss": 0.17402605712413788,
      "eval_runtime": 0.9614,
      "eval_samples_per_second": 72.809,
      "eval_steps_per_second": 5.201,
      "step": 175
    },
    {
      "epoch": 18.46,
      "learning_rate": 3.3333333333333335e-05,
      "loss": 0.139,
      "step": 180
    },
    {
      "epoch": 18.97,
      "eval_accuracy": 0.9571428571428572,
      "eval_loss": 0.07017717510461807,
      "eval_runtime": 0.9316,
      "eval_samples_per_second": 75.143,
      "eval_steps_per_second": 5.367,
      "step": 185
    },
    {
      "epoch": 19.49,
      "learning_rate": 3.209876543209876e-05,
      "loss": 0.1553,
      "step": 190
    },
    {
      "epoch": 20.0,
      "eval_accuracy": 0.9571428571428572,
      "eval_loss": 0.15834562480449677,
      "eval_runtime": 0.9425,
      "eval_samples_per_second": 74.274,
      "eval_steps_per_second": 5.305,
      "step": 195
    },
    {
      "epoch": 20.51,
      "learning_rate": 3.08641975308642e-05,
      "loss": 0.1488,
      "step": 200
    },
    {
      "epoch": 20.92,
      "eval_accuracy": 0.9857142857142858,
      "eval_loss": 0.04526468738913536,
      "eval_runtime": 0.9153,
      "eval_samples_per_second": 76.476,
      "eval_steps_per_second": 5.463,
      "step": 204
    },
    {
      "epoch": 21.54,
      "learning_rate": 2.962962962962963e-05,
      "loss": 0.1425,
      "step": 210
    },
    {
      "epoch": 21.95,
      "eval_accuracy": 0.9285714285714286,
      "eval_loss": 0.21590319275856018,
      "eval_runtime": 0.916,
      "eval_samples_per_second": 76.423,
      "eval_steps_per_second": 5.459,
      "step": 214
    },
    {
      "epoch": 22.56,
      "learning_rate": 2.839506172839506e-05,
      "loss": 0.1716,
      "step": 220
    },
    {
      "epoch": 22.97,
      "eval_accuracy": 0.9857142857142858,
      "eval_loss": 0.03548683598637581,
      "eval_runtime": 0.9262,
      "eval_samples_per_second": 75.579,
      "eval_steps_per_second": 5.399,
      "step": 224
    },
    {
      "epoch": 23.59,
      "learning_rate": 2.7160493827160493e-05,
      "loss": 0.0913,
      "step": 230
    },
    {
      "epoch": 24.0,
      "eval_accuracy": 0.9857142857142858,
      "eval_loss": 0.026874909177422523,
      "eval_runtime": 0.9611,
      "eval_samples_per_second": 72.836,
      "eval_steps_per_second": 5.203,
      "step": 234
    },
    {
      "epoch": 24.62,
      "learning_rate": 2.5925925925925925e-05,
      "loss": 0.1076,
      "step": 240
    },
    {
      "epoch": 24.92,
      "eval_accuracy": 0.9857142857142858,
      "eval_loss": 0.0271690022200346,
      "eval_runtime": 0.9105,
      "eval_samples_per_second": 76.881,
      "eval_steps_per_second": 5.491,
      "step": 243
    },
    {
      "epoch": 25.64,
      "learning_rate": 2.4691358024691357e-05,
      "loss": 0.1083,
      "step": 250
    },
    {
      "epoch": 25.95,
      "eval_accuracy": 0.9857142857142858,
      "eval_loss": 0.0268684271723032,
      "eval_runtime": 0.9263,
      "eval_samples_per_second": 75.573,
      "eval_steps_per_second": 5.398,
      "step": 253
    },
    {
      "epoch": 26.67,
      "learning_rate": 2.345679012345679e-05,
      "loss": 0.1002,
      "step": 260
    },
    {
      "epoch": 26.97,
      "eval_accuracy": 0.9857142857142858,
      "eval_loss": 0.04236455634236336,
      "eval_runtime": 0.9254,
      "eval_samples_per_second": 75.641,
      "eval_steps_per_second": 5.403,
      "step": 263
    },
    {
      "epoch": 27.69,
      "learning_rate": 2.2222222222222223e-05,
      "loss": 0.1344,
      "step": 270
    },
    {
      "epoch": 28.0,
      "eval_accuracy": 0.9857142857142858,
      "eval_loss": 0.027010390534996986,
      "eval_runtime": 0.9149,
      "eval_samples_per_second": 76.508,
      "eval_steps_per_second": 5.465,
      "step": 273
    },
    {
      "epoch": 28.72,
      "learning_rate": 2.0987654320987655e-05,
      "loss": 0.1223,
      "step": 280
    },
    {
      "epoch": 28.92,
      "eval_accuracy": 0.9857142857142858,
      "eval_loss": 0.0340094119310379,
      "eval_runtime": 0.9259,
      "eval_samples_per_second": 75.599,
      "eval_steps_per_second": 5.4,
      "step": 282
    },
    {
      "epoch": 29.74,
      "learning_rate": 1.9753086419753087e-05,
      "loss": 0.1192,
      "step": 290
    },
    {
      "epoch": 29.95,
      "eval_accuracy": 0.9857142857142858,
      "eval_loss": 0.02797979861497879,
      "eval_runtime": 0.9576,
      "eval_samples_per_second": 73.098,
      "eval_steps_per_second": 5.221,
      "step": 292
    },
    {
      "epoch": 30.77,
      "learning_rate": 1.8518518518518518e-05,
      "loss": 0.0896,
      "step": 300
    },
    {
      "epoch": 30.97,
      "eval_accuracy": 0.9857142857142858,
      "eval_loss": 0.03946752846240997,
      "eval_runtime": 0.9155,
      "eval_samples_per_second": 76.463,
      "eval_steps_per_second": 5.462,
      "step": 302
    },
    {
      "epoch": 31.79,
      "learning_rate": 1.728395061728395e-05,
      "loss": 0.0778,
      "step": 310
    },
    {
      "epoch": 32.0,
      "eval_accuracy": 1.0,
      "eval_loss": 0.009111489169299603,
      "eval_runtime": 0.9421,
      "eval_samples_per_second": 74.306,
      "eval_steps_per_second": 5.308,
      "step": 312
    },
    {
      "epoch": 32.82,
      "learning_rate": 1.604938271604938e-05,
      "loss": 0.0709,
      "step": 320
    },
    {
      "epoch": 32.92,
      "eval_accuracy": 1.0,
      "eval_loss": 0.006697469856590033,
      "eval_runtime": 0.9422,
      "eval_samples_per_second": 74.295,
      "eval_steps_per_second": 5.307,
      "step": 321
    },
    {
      "epoch": 33.85,
      "learning_rate": 1.4814814814814815e-05,
      "loss": 0.0603,
      "step": 330
    },
    {
      "epoch": 33.95,
      "eval_accuracy": 1.0,
      "eval_loss": 0.012383648194372654,
      "eval_runtime": 0.9149,
      "eval_samples_per_second": 76.511,
      "eval_steps_per_second": 5.465,
      "step": 331
    },
    {
      "epoch": 34.87,
      "learning_rate": 1.3580246913580247e-05,
      "loss": 0.0777,
      "step": 340
    },
    {
      "epoch": 34.97,
      "eval_accuracy": 0.9857142857142858,
      "eval_loss": 0.035239022225141525,
      "eval_runtime": 0.9299,
      "eval_samples_per_second": 75.274,
      "eval_steps_per_second": 5.377,
      "step": 341
    },
    {
      "epoch": 35.9,
      "learning_rate": 1.2345679012345678e-05,
      "loss": 0.1045,
      "step": 350
    },
    {
      "epoch": 36.0,
      "eval_accuracy": 1.0,
      "eval_loss": 0.012970388866961002,
      "eval_runtime": 0.9568,
      "eval_samples_per_second": 73.163,
      "eval_steps_per_second": 5.226,
      "step": 351
    },
    {
      "epoch": 36.92,
      "learning_rate": 1.1111111111111112e-05,
      "loss": 0.0647,
      "step": 360
    },
    {
      "epoch": 36.92,
      "eval_accuracy": 1.0,
      "eval_loss": 0.0034227774012833834,
      "eval_runtime": 0.9154,
      "eval_samples_per_second": 76.471,
      "eval_steps_per_second": 5.462,
      "step": 360
    },
    {
      "epoch": 37.95,
      "learning_rate": 9.876543209876543e-06,
      "loss": 0.0733,
      "step": 370
    },
    {
      "epoch": 37.95,
      "eval_accuracy": 1.0,
      "eval_loss": 0.005396140739321709,
      "eval_runtime": 0.9146,
      "eval_samples_per_second": 76.538,
      "eval_steps_per_second": 5.467,
      "step": 370
    },
    {
      "epoch": 38.97,
      "learning_rate": 8.641975308641975e-06,
      "loss": 0.0576,
      "step": 380
    },
    {
      "epoch": 38.97,
      "eval_accuracy": 0.9714285714285714,
      "eval_loss": 0.024362746626138687,
      "eval_runtime": 0.926,
      "eval_samples_per_second": 75.596,
      "eval_steps_per_second": 5.4,
      "step": 380
    },
    {
      "epoch": 40.0,
      "learning_rate": 7.4074074074074075e-06,
      "loss": 0.0695,
      "step": 390
    },
    {
      "epoch": 40.0,
      "eval_accuracy": 1.0,
      "eval_loss": 0.002876411657780409,
      "eval_runtime": 0.9256,
      "eval_samples_per_second": 75.626,
      "eval_steps_per_second": 5.402,
      "step": 390
    },
    {
      "epoch": 40.92,
      "eval_accuracy": 1.0,
      "eval_loss": 0.006180027965456247,
      "eval_runtime": 0.916,
      "eval_samples_per_second": 76.421,
      "eval_steps_per_second": 5.459,
      "step": 399
    },
    {
      "epoch": 41.03,
      "learning_rate": 6.172839506172839e-06,
      "loss": 0.0592,
      "step": 400
    },
    {
      "epoch": 41.95,
      "eval_accuracy": 1.0,
      "eval_loss": 0.0032598855905234814,
      "eval_runtime": 0.9432,
      "eval_samples_per_second": 74.216,
      "eval_steps_per_second": 5.301,
      "step": 409
    },
    {
      "epoch": 42.05,
      "learning_rate": 4.938271604938272e-06,
      "loss": 0.0643,
      "step": 410
    },
    {
      "epoch": 42.97,
      "eval_accuracy": 1.0,
      "eval_loss": 0.002199623268097639,
      "eval_runtime": 0.9419,
      "eval_samples_per_second": 74.319,
      "eval_steps_per_second": 5.309,
      "step": 419
    },
    {
      "epoch": 43.08,
      "learning_rate": 3.7037037037037037e-06,
      "loss": 0.0474,
      "step": 420
    },
    {
      "epoch": 44.0,
      "eval_accuracy": 1.0,
      "eval_loss": 0.0029794778674840927,
      "eval_runtime": 0.9143,
      "eval_samples_per_second": 76.558,
      "eval_steps_per_second": 5.468,
      "step": 429
    },
    {
      "epoch": 44.1,
      "learning_rate": 2.469135802469136e-06,
      "loss": 0.085,
      "step": 430
    },
    {
      "epoch": 44.92,
      "eval_accuracy": 1.0,
      "eval_loss": 0.004402108024805784,
      "eval_runtime": 0.926,
      "eval_samples_per_second": 75.591,
      "eval_steps_per_second": 5.399,
      "step": 438
    },
    {
      "epoch": 45.13,
      "learning_rate": 1.234567901234568e-06,
      "loss": 0.0472,
      "step": 440
    },
    {
      "epoch": 45.95,
      "eval_accuracy": 1.0,
      "eval_loss": 0.0060264961794018745,
      "eval_runtime": 0.9252,
      "eval_samples_per_second": 75.656,
      "eval_steps_per_second": 5.404,
      "step": 448
    },
    {
      "epoch": 46.15,
      "learning_rate": 0.0,
      "loss": 0.0563,
      "step": 450
    },
    {
      "epoch": 46.15,
      "eval_accuracy": 1.0,
      "eval_loss": 0.006070576608181,
      "eval_runtime": 0.9303,
      "eval_samples_per_second": 75.246,
      "eval_steps_per_second": 5.375,
      "step": 450
    }
  ],
  "max_steps": 450,
  "num_train_epochs": 50,
  "total_flos": 2.437707333751603e+18,
  "trial_name": null,
  "trial_params": null
}