{
  "best_metric": 0.9950738916256158,
  "best_model_checkpoint": "swinv2-large-patch4-window12to16-192to256-22kto1k-ft-finetuned-Lesion-Classification-HAM10000-3/checkpoint-1140",
  "epoch": 9.978118161925602,
  "eval_steps": 500,
  "global_step": 1140,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.04,
      "learning_rate": 4.385964912280702e-07,
      "loss": 2.0125,
      "step": 5
    },
    {
      "epoch": 0.09,
      "learning_rate": 8.771929824561404e-07,
      "loss": 2.0062,
      "step": 10
    },
    {
      "epoch": 0.13,
      "learning_rate": 1.3157894736842106e-06,
      "loss": 2.0213,
      "step": 15
    },
    {
      "epoch": 0.18,
      "learning_rate": 1.7543859649122807e-06,
      "loss": 2.0005,
      "step": 20
    },
    {
      "epoch": 0.22,
      "learning_rate": 2.1929824561403507e-06,
      "loss": 1.9605,
      "step": 25
    },
    {
      "epoch": 0.26,
      "learning_rate": 2.631578947368421e-06,
      "loss": 1.9693,
      "step": 30
    },
    {
      "epoch": 0.31,
      "learning_rate": 3.070175438596491e-06,
      "loss": 1.9539,
      "step": 35
    },
    {
      "epoch": 0.35,
      "learning_rate": 3.5087719298245615e-06,
      "loss": 1.8969,
      "step": 40
    },
    {
      "epoch": 0.39,
      "learning_rate": 3.9473684210526315e-06,
      "loss": 1.8464,
      "step": 45
    },
    {
      "epoch": 0.44,
      "learning_rate": 4.3859649122807014e-06,
      "loss": 1.8472,
      "step": 50
    },
    {
      "epoch": 0.48,
      "learning_rate": 4.824561403508772e-06,
      "loss": 1.8315,
      "step": 55
    },
    {
      "epoch": 0.53,
      "learning_rate": 5.263157894736842e-06,
      "loss": 1.7747,
      "step": 60
    },
    {
      "epoch": 0.57,
      "learning_rate": 5.701754385964912e-06,
      "loss": 1.6972,
      "step": 65
    },
    {
      "epoch": 0.61,
      "learning_rate": 6.140350877192982e-06,
      "loss": 1.5887,
      "step": 70
    },
    {
      "epoch": 0.66,
      "learning_rate": 6.578947368421053e-06,
      "loss": 1.5541,
      "step": 75
    },
    {
      "epoch": 0.7,
      "learning_rate": 7.017543859649123e-06,
      "loss": 1.4549,
      "step": 80
    },
    {
      "epoch": 0.74,
      "learning_rate": 7.456140350877193e-06,
      "loss": 1.4104,
      "step": 85
    },
    {
      "epoch": 0.79,
      "learning_rate": 7.894736842105263e-06,
      "loss": 1.3381,
      "step": 90
    },
    {
      "epoch": 0.83,
      "learning_rate": 8.333333333333334e-06,
      "loss": 1.2994,
      "step": 95
    },
    {
      "epoch": 0.88,
      "learning_rate": 8.771929824561403e-06,
      "loss": 1.1369,
      "step": 100
    },
    {
      "epoch": 0.92,
      "learning_rate": 9.210526315789474e-06,
      "loss": 1.181,
      "step": 105
    },
    {
      "epoch": 0.96,
      "learning_rate": 9.649122807017545e-06,
      "loss": 1.1885,
      "step": 110
    },
    {
      "epoch": 1.0,
      "eval_accuracy": 0.6592775041050903,
      "eval_loss": 0.871817946434021,
      "eval_runtime": 272.9497,
      "eval_samples_per_second": 4.462,
      "eval_steps_per_second": 0.561,
      "step": 114
    },
    {
      "epoch": 1.01,
      "learning_rate": 1.0087719298245614e-05,
      "loss": 1.0284,
      "step": 115
    },
    {
      "epoch": 1.05,
      "learning_rate": 1.0526315789473684e-05,
      "loss": 0.9502,
      "step": 120
    },
    {
      "epoch": 1.09,
      "learning_rate": 1.0964912280701754e-05,
      "loss": 1.0752,
      "step": 125
    },
    {
      "epoch": 1.14,
      "learning_rate": 1.1403508771929824e-05,
      "loss": 0.8783,
      "step": 130
    },
    {
      "epoch": 1.18,
      "learning_rate": 1.1842105263157895e-05,
      "loss": 0.7479,
      "step": 135
    },
    {
      "epoch": 1.23,
      "learning_rate": 1.2280701754385964e-05,
      "loss": 0.9468,
      "step": 140
    },
    {
      "epoch": 1.27,
      "learning_rate": 1.2719298245614037e-05,
      "loss": 0.8863,
      "step": 145
    },
    {
      "epoch": 1.31,
      "learning_rate": 1.3157894736842106e-05,
      "loss": 0.9492,
      "step": 150
    },
    {
      "epoch": 1.36,
      "learning_rate": 1.3596491228070177e-05,
      "loss": 0.8521,
      "step": 155
    },
    {
      "epoch": 1.4,
      "learning_rate": 1.4035087719298246e-05,
      "loss": 0.7445,
      "step": 160
    },
    {
      "epoch": 1.44,
      "learning_rate": 1.4473684210526317e-05,
      "loss": 0.9228,
      "step": 165
    },
    {
      "epoch": 1.49,
      "learning_rate": 1.4912280701754386e-05,
      "loss": 0.8637,
      "step": 170
    },
    {
      "epoch": 1.53,
      "learning_rate": 1.5350877192982457e-05,
      "loss": 0.7486,
      "step": 175
    },
    {
      "epoch": 1.58,
      "learning_rate": 1.5789473684210526e-05,
      "loss": 0.9474,
      "step": 180
    },
    {
      "epoch": 1.62,
      "learning_rate": 1.62280701754386e-05,
      "loss": 0.7842,
      "step": 185
    },
    {
      "epoch": 1.66,
      "learning_rate": 1.6666666666666667e-05,
      "loss": 0.8101,
      "step": 190
    },
    {
      "epoch": 1.71,
      "learning_rate": 1.7105263157894737e-05,
      "loss": 0.8701,
      "step": 195
    },
    {
      "epoch": 1.75,
      "learning_rate": 1.7543859649122806e-05,
      "loss": 0.8223,
      "step": 200
    },
    {
      "epoch": 1.79,
      "learning_rate": 1.7982456140350878e-05,
      "loss": 0.6153,
      "step": 205
    },
    {
      "epoch": 1.84,
      "learning_rate": 1.8421052631578947e-05,
      "loss": 0.7246,
      "step": 210
    },
    {
      "epoch": 1.88,
      "learning_rate": 1.885964912280702e-05,
      "loss": 0.5416,
      "step": 215
    },
    {
      "epoch": 1.93,
      "learning_rate": 1.929824561403509e-05,
      "loss": 0.5653,
      "step": 220
    },
    {
      "epoch": 1.97,
      "learning_rate": 1.9736842105263158e-05,
      "loss": 0.7037,
      "step": 225
    },
    {
      "epoch": 2.0,
      "eval_accuracy": 0.8637110016420362,
      "eval_loss": 0.4207600951194763,
      "eval_runtime": 19.4349,
      "eval_samples_per_second": 62.671,
      "eval_steps_per_second": 7.872,
      "step": 228
    },
    {
      "epoch": 2.01,
      "learning_rate": 2.0175438596491227e-05,
      "loss": 0.5668,
      "step": 230
    },
    {
      "epoch": 2.06,
      "learning_rate": 2.06140350877193e-05,
      "loss": 0.616,
      "step": 235
    },
    {
      "epoch": 2.1,
      "learning_rate": 2.105263157894737e-05,
      "loss": 0.6098,
      "step": 240
    },
    {
      "epoch": 2.14,
      "learning_rate": 2.149122807017544e-05,
      "loss": 0.5217,
      "step": 245
    },
    {
      "epoch": 2.19,
      "learning_rate": 2.1929824561403507e-05,
      "loss": 0.5275,
      "step": 250
    },
    {
      "epoch": 2.23,
      "learning_rate": 2.236842105263158e-05,
      "loss": 0.6111,
      "step": 255
    },
    {
      "epoch": 2.28,
      "learning_rate": 2.280701754385965e-05,
      "loss": 0.4977,
      "step": 260
    },
    {
      "epoch": 2.32,
      "learning_rate": 2.324561403508772e-05,
      "loss": 0.6095,
      "step": 265
    },
    {
      "epoch": 2.36,
      "learning_rate": 2.368421052631579e-05,
      "loss": 0.6547,
      "step": 270
    },
    {
      "epoch": 2.41,
      "learning_rate": 2.412280701754386e-05,
      "loss": 0.5991,
      "step": 275
    },
    {
      "epoch": 2.45,
      "learning_rate": 2.456140350877193e-05,
      "loss": 0.6997,
      "step": 280
    },
    {
      "epoch": 2.49,
      "learning_rate": 2.5e-05,
      "loss": 0.532,
      "step": 285
    },
    {
      "epoch": 2.54,
      "learning_rate": 2.5438596491228074e-05,
      "loss": 0.4929,
      "step": 290
    },
    {
      "epoch": 2.58,
      "learning_rate": 2.5877192982456143e-05,
      "loss": 0.5004,
      "step": 295
    },
    {
      "epoch": 2.63,
      "learning_rate": 2.6315789473684212e-05,
      "loss": 0.5739,
      "step": 300
    },
    {
      "epoch": 2.67,
      "learning_rate": 2.675438596491228e-05,
      "loss": 0.6012,
      "step": 305
    },
    {
      "epoch": 2.71,
      "learning_rate": 2.7192982456140354e-05,
      "loss": 0.5107,
      "step": 310
    },
    {
      "epoch": 2.76,
      "learning_rate": 2.7631578947368426e-05,
      "loss": 0.6075,
      "step": 315
    },
    {
      "epoch": 2.8,
      "learning_rate": 2.8070175438596492e-05,
      "loss": 0.5597,
      "step": 320
    },
    {
      "epoch": 2.84,
      "learning_rate": 2.850877192982456e-05,
      "loss": 0.4941,
      "step": 325
    },
    {
      "epoch": 2.89,
      "learning_rate": 2.8947368421052634e-05,
      "loss": 0.6285,
      "step": 330
    },
    {
      "epoch": 2.93,
      "learning_rate": 2.9385964912280706e-05,
      "loss": 0.4644,
      "step": 335
    },
    {
      "epoch": 2.98,
      "learning_rate": 2.9824561403508772e-05,
      "loss": 0.5085,
      "step": 340
    },
    {
      "epoch": 2.99,
      "eval_accuracy": 0.874384236453202,
      "eval_loss": 0.3445686399936676,
      "eval_runtime": 19.2674,
      "eval_samples_per_second": 63.216,
      "eval_steps_per_second": 7.941,
      "step": 342
    },
    {
      "epoch": 3.02,
      "learning_rate": 3.0263157894736844e-05,
      "loss": 0.542,
      "step": 345
    },
    {
      "epoch": 3.06,
      "learning_rate": 3.0701754385964913e-05,
      "loss": 0.4411,
      "step": 350
    },
    {
      "epoch": 3.11,
      "learning_rate": 3.1140350877192986e-05,
      "loss": 0.5084,
      "step": 355
    },
    {
      "epoch": 3.15,
      "learning_rate": 3.157894736842105e-05,
      "loss": 0.5346,
      "step": 360
    },
    {
      "epoch": 3.19,
      "learning_rate": 3.2017543859649124e-05,
      "loss": 0.4539,
      "step": 365
    },
    {
      "epoch": 3.24,
      "learning_rate": 3.24561403508772e-05,
      "loss": 0.308,
      "step": 370
    },
    {
      "epoch": 3.28,
      "learning_rate": 3.289473684210527e-05,
      "loss": 0.5257,
      "step": 375
    },
    {
      "epoch": 3.33,
      "learning_rate": 3.3333333333333335e-05,
      "loss": 0.3717,
      "step": 380
    },
    {
      "epoch": 3.37,
      "learning_rate": 3.377192982456141e-05,
      "loss": 0.3999,
      "step": 385
    },
    {
      "epoch": 3.41,
      "learning_rate": 3.421052631578947e-05,
      "loss": 0.5481,
      "step": 390
    },
    {
      "epoch": 3.46,
      "learning_rate": 3.4649122807017546e-05,
      "loss": 0.3296,
      "step": 395
    },
    {
      "epoch": 3.5,
      "learning_rate": 3.508771929824561e-05,
      "loss": 0.4459,
      "step": 400
    },
    {
      "epoch": 3.54,
      "learning_rate": 3.5526315789473684e-05,
      "loss": 0.355,
      "step": 405
    },
    {
      "epoch": 3.59,
      "learning_rate": 3.5964912280701756e-05,
      "loss": 0.2903,
      "step": 410
    },
    {
      "epoch": 3.63,
      "learning_rate": 3.640350877192983e-05,
      "loss": 0.4224,
      "step": 415
    },
    {
      "epoch": 3.68,
      "learning_rate": 3.6842105263157895e-05,
      "loss": 0.4467,
      "step": 420
    },
    {
      "epoch": 3.72,
      "learning_rate": 3.728070175438597e-05,
      "loss": 0.298,
      "step": 425
    },
    {
      "epoch": 3.76,
      "learning_rate": 3.771929824561404e-05,
      "loss": 0.4309,
      "step": 430
    },
    {
      "epoch": 3.81,
      "learning_rate": 3.815789473684211e-05,
      "loss": 0.4773,
      "step": 435
    },
    {
      "epoch": 3.85,
      "learning_rate": 3.859649122807018e-05,
      "loss": 0.5006,
      "step": 440
    },
    {
      "epoch": 3.89,
      "learning_rate": 3.9035087719298244e-05,
      "loss": 0.412,
      "step": 445
    },
    {
      "epoch": 3.94,
      "learning_rate": 3.9473684210526316e-05,
      "loss": 0.3844,
      "step": 450
    },
    {
      "epoch": 3.98,
      "learning_rate": 3.991228070175439e-05,
      "loss": 0.2874,
      "step": 455
    },
    {
      "epoch": 4.0,
      "eval_accuracy": 0.9326765188834154,
      "eval_loss": 0.20270153880119324,
      "eval_runtime": 19.2109,
      "eval_samples_per_second": 63.401,
      "eval_steps_per_second": 7.964,
      "step": 457
    },
    {
      "epoch": 4.03,
      "learning_rate": 4.0350877192982455e-05,
      "loss": 0.4108,
      "step": 460
    },
    {
      "epoch": 4.07,
      "learning_rate": 4.078947368421053e-05,
      "loss": 0.3113,
      "step": 465
    },
    {
      "epoch": 4.11,
      "learning_rate": 4.12280701754386e-05,
      "loss": 0.3695,
      "step": 470
    },
    {
      "epoch": 4.16,
      "learning_rate": 4.166666666666667e-05,
      "loss": 0.4312,
      "step": 475
    },
    {
      "epoch": 4.2,
      "learning_rate": 4.210526315789474e-05,
      "loss": 0.5009,
      "step": 480
    },
    {
      "epoch": 4.25,
      "learning_rate": 4.254385964912281e-05,
      "loss": 0.4491,
      "step": 485
    },
    {
      "epoch": 4.29,
      "learning_rate": 4.298245614035088e-05,
      "loss": 0.3298,
      "step": 490
    },
    {
      "epoch": 4.33,
      "learning_rate": 4.342105263157895e-05,
      "loss": 0.3188,
      "step": 495
    },
    {
      "epoch": 4.38,
      "learning_rate": 4.3859649122807014e-05,
      "loss": 0.3462,
      "step": 500
    },
    {
      "epoch": 4.42,
      "learning_rate": 4.429824561403509e-05,
      "loss": 0.3797,
      "step": 505
    },
    {
      "epoch": 4.46,
      "learning_rate": 4.473684210526316e-05,
      "loss": 0.412,
      "step": 510
    },
    {
      "epoch": 4.51,
      "learning_rate": 4.517543859649123e-05,
      "loss": 0.3163,
      "step": 515
    },
    {
      "epoch": 4.55,
      "learning_rate": 4.56140350877193e-05,
      "loss": 0.4202,
      "step": 520
    },
    {
      "epoch": 4.6,
      "learning_rate": 4.605263157894737e-05,
      "loss": 0.3902,
      "step": 525
    },
    {
      "epoch": 4.64,
      "learning_rate": 4.649122807017544e-05,
      "loss": 0.3598,
      "step": 530
    },
    {
      "epoch": 4.68,
      "learning_rate": 4.6929824561403515e-05,
      "loss": 0.2675,
      "step": 535
    },
    {
      "epoch": 4.73,
      "learning_rate": 4.736842105263158e-05,
      "loss": 0.3208,
      "step": 540
    },
    {
      "epoch": 4.77,
      "learning_rate": 4.780701754385965e-05,
      "loss": 0.3622,
      "step": 545
    },
    {
      "epoch": 4.81,
      "learning_rate": 4.824561403508772e-05,
      "loss": 0.3299,
      "step": 550
    },
    {
      "epoch": 4.86,
      "learning_rate": 4.868421052631579e-05,
      "loss": 0.2825,
      "step": 555
    },
    {
      "epoch": 4.9,
      "learning_rate": 4.912280701754386e-05,
      "loss": 0.4182,
      "step": 560
    },
    {
      "epoch": 4.95,
      "learning_rate": 4.956140350877193e-05,
      "loss": 0.282,
      "step": 565
    },
    {
      "epoch": 4.99,
      "learning_rate": 5e-05,
      "loss": 0.355,
      "step": 570
    },
    {
      "epoch": 5.0,
      "eval_accuracy": 0.9400656814449918,
      "eval_loss": 0.1666150987148285,
      "eval_runtime": 19.15,
      "eval_samples_per_second": 63.603,
      "eval_steps_per_second": 7.99,
      "step": 571
    },
    {
      "epoch": 5.03,
      "learning_rate": 4.956140350877193e-05,
      "loss": 0.3916,
      "step": 575
    },
    {
      "epoch": 5.08,
      "learning_rate": 4.912280701754386e-05,
      "loss": 0.3083,
      "step": 580
    },
    {
      "epoch": 5.12,
      "learning_rate": 4.868421052631579e-05,
      "loss": 0.2193,
      "step": 585
    },
    {
      "epoch": 5.16,
      "learning_rate": 4.824561403508772e-05,
      "loss": 0.2596,
      "step": 590
    },
    {
      "epoch": 5.21,
      "learning_rate": 4.780701754385965e-05,
      "loss": 0.2697,
      "step": 595
    },
    {
      "epoch": 5.25,
      "learning_rate": 4.736842105263158e-05,
      "loss": 0.2519,
      "step": 600
    },
    {
      "epoch": 5.3,
      "learning_rate": 4.6929824561403515e-05,
      "loss": 0.3345,
      "step": 605
    },
    {
      "epoch": 5.34,
      "learning_rate": 4.649122807017544e-05,
      "loss": 0.2694,
      "step": 610
    },
    {
      "epoch": 5.38,
      "learning_rate": 4.605263157894737e-05,
      "loss": 0.2815,
      "step": 615
    },
    {
      "epoch": 5.43,
      "learning_rate": 4.56140350877193e-05,
      "loss": 0.2315,
      "step": 620
    },
    {
      "epoch": 5.47,
      "learning_rate": 4.517543859649123e-05,
      "loss": 0.2701,
      "step": 625
    },
    {
      "epoch": 5.51,
      "learning_rate": 4.473684210526316e-05,
      "loss": 0.2506,
      "step": 630
    },
    {
      "epoch": 5.56,
      "learning_rate": 4.429824561403509e-05,
      "loss": 0.2141,
      "step": 635
    },
    {
      "epoch": 5.6,
      "learning_rate": 4.3859649122807014e-05,
      "loss": 0.2323,
      "step": 640
    },
    {
      "epoch": 5.65,
      "learning_rate": 4.342105263157895e-05,
      "loss": 0.2465,
      "step": 645
    },
    {
      "epoch": 5.69,
      "learning_rate": 4.298245614035088e-05,
      "loss": 0.3737,
      "step": 650
    },
    {
      "epoch": 5.73,
      "learning_rate": 4.254385964912281e-05,
      "loss": 0.3958,
      "step": 655
    },
    {
      "epoch": 5.78,
      "learning_rate": 4.210526315789474e-05,
      "loss": 0.4959,
      "step": 660
    },
    {
      "epoch": 5.82,
      "learning_rate": 4.166666666666667e-05,
      "loss": 0.3131,
      "step": 665
    },
    {
      "epoch": 5.86,
      "learning_rate": 4.12280701754386e-05,
      "loss": 0.2104,
      "step": 670
    },
    {
      "epoch": 5.91,
      "learning_rate": 4.078947368421053e-05,
      "loss": 0.2501,
      "step": 675
    },
    {
      "epoch": 5.95,
      "learning_rate": 4.0350877192982455e-05,
      "loss": 0.3094,
      "step": 680
    },
    {
      "epoch": 6.0,
      "learning_rate": 3.991228070175439e-05,
      "loss": 0.2493,
      "step": 685
    },
    {
      "epoch": 6.0,
      "eval_accuracy": 0.9655172413793104,
      "eval_loss": 0.09691629558801651,
      "eval_runtime": 19.1884,
      "eval_samples_per_second": 63.476,
      "eval_steps_per_second": 7.974,
      "step": 685
    },
    {
      "epoch": 6.04,
      "learning_rate": 3.9473684210526316e-05,
      "loss": 0.2233,
      "step": 690
    },
    {
      "epoch": 6.08,
      "learning_rate": 3.9035087719298244e-05,
      "loss": 0.1551,
      "step": 695
    },
    {
      "epoch": 6.13,
      "learning_rate": 3.859649122807018e-05,
      "loss": 0.2415,
      "step": 700
    },
    {
      "epoch": 6.17,
      "learning_rate": 3.815789473684211e-05,
      "loss": 0.1373,
      "step": 705
    },
    {
      "epoch": 6.21,
      "learning_rate": 3.771929824561404e-05,
      "loss": 0.2754,
      "step": 710
    },
    {
      "epoch": 6.26,
      "learning_rate": 3.728070175438597e-05,
      "loss": 0.2255,
      "step": 715
    },
    {
      "epoch": 6.3,
      "learning_rate": 3.6842105263157895e-05,
      "loss": 0.156,
      "step": 720
    },
    {
      "epoch": 6.35,
      "learning_rate": 3.640350877192983e-05,
      "loss": 0.2596,
      "step": 725
    },
    {
      "epoch": 6.39,
      "learning_rate": 3.5964912280701756e-05,
      "loss": 0.2366,
      "step": 730
    },
    {
      "epoch": 6.43,
      "learning_rate": 3.5526315789473684e-05,
      "loss": 0.2985,
      "step": 735
    },
    {
      "epoch": 6.48,
      "learning_rate": 3.508771929824561e-05,
      "loss": 0.1712,
      "step": 740
    },
    {
      "epoch": 6.52,
      "learning_rate": 3.4649122807017546e-05,
      "loss": 0.1222,
      "step": 745
    },
    {
      "epoch": 6.56,
      "learning_rate": 3.421052631578947e-05,
      "loss": 0.1547,
      "step": 750
    },
    {
      "epoch": 6.61,
      "learning_rate": 3.377192982456141e-05,
      "loss": 0.1938,
      "step": 755
    },
    {
      "epoch": 6.65,
      "learning_rate": 3.3333333333333335e-05,
      "loss": 0.1712,
      "step": 760
    },
    {
      "epoch": 6.7,
      "learning_rate": 3.289473684210527e-05,
      "loss": 0.1423,
      "step": 765
    },
    {
      "epoch": 6.74,
      "learning_rate": 3.24561403508772e-05,
      "loss": 0.2396,
      "step": 770
    },
    {
      "epoch": 6.78,
      "learning_rate": 3.2017543859649124e-05,
      "loss": 0.2153,
      "step": 775
    },
    {
      "epoch": 6.83,
      "learning_rate": 3.157894736842105e-05,
      "loss": 0.2239,
      "step": 780
    },
    {
      "epoch": 6.87,
      "learning_rate": 3.1140350877192986e-05,
      "loss": 0.0997,
      "step": 785
    },
    {
      "epoch": 6.91,
      "learning_rate": 3.0701754385964913e-05,
      "loss": 0.1459,
      "step": 790
    },
    {
      "epoch": 6.96,
      "learning_rate": 3.0263157894736844e-05,
      "loss": 0.1909,
      "step": 795
    },
    {
      "epoch": 6.99,
      "eval_accuracy": 0.9835796387520526,
      "eval_loss": 0.05583478882908821,
      "eval_runtime": 19.3251,
      "eval_samples_per_second": 63.027,
      "eval_steps_per_second": 7.917,
      "step": 799
    },
    {
      "epoch": 7.0,
      "learning_rate": 2.9824561403508772e-05,
      "loss": 0.1693,
      "step": 800
    },
    {
      "epoch": 7.05,
      "learning_rate": 2.9385964912280706e-05,
      "loss": 0.1497,
      "step": 805
    },
    {
      "epoch": 7.09,
      "learning_rate": 2.8947368421052634e-05,
      "loss": 0.2175,
      "step": 810
    },
    {
      "epoch": 7.13,
      "learning_rate": 2.850877192982456e-05,
      "loss": 0.1438,
      "step": 815
    },
    {
      "epoch": 7.18,
      "learning_rate": 2.8070175438596492e-05,
      "loss": 0.1668,
      "step": 820
    },
    {
      "epoch": 7.22,
      "learning_rate": 2.7631578947368426e-05,
      "loss": 0.1601,
      "step": 825
    },
    {
      "epoch": 7.26,
      "learning_rate": 2.7192982456140354e-05,
      "loss": 0.0939,
      "step": 830
    },
    {
      "epoch": 7.31,
      "learning_rate": 2.675438596491228e-05,
      "loss": 0.1289,
      "step": 835
    },
    {
      "epoch": 7.35,
      "learning_rate": 2.6315789473684212e-05,
      "loss": 0.1687,
      "step": 840
    },
    {
      "epoch": 7.4,
      "learning_rate": 2.5877192982456143e-05,
      "loss": 0.1336,
      "step": 845
    },
    {
      "epoch": 7.44,
      "learning_rate": 2.5438596491228074e-05,
      "loss": 0.1448,
      "step": 850
    },
    {
      "epoch": 7.48,
      "learning_rate": 2.5e-05,
      "loss": 0.2031,
      "step": 855
    },
    {
      "epoch": 7.53,
      "learning_rate": 2.456140350877193e-05,
      "loss": 0.1245,
      "step": 860
    },
    {
      "epoch": 7.57,
      "learning_rate": 2.412280701754386e-05,
      "loss": 0.1954,
      "step": 865
    },
    {
      "epoch": 7.61,
      "learning_rate": 2.368421052631579e-05,
      "loss": 0.2028,
      "step": 870
    },
    {
      "epoch": 7.66,
      "learning_rate": 2.324561403508772e-05,
      "loss": 0.1675,
      "step": 875
    },
    {
      "epoch": 7.7,
      "learning_rate": 2.280701754385965e-05,
      "loss": 0.1371,
      "step": 880
    },
    {
      "epoch": 7.75,
      "learning_rate": 2.236842105263158e-05,
      "loss": 0.1443,
      "step": 885
    },
    {
      "epoch": 7.79,
      "learning_rate": 2.1929824561403507e-05,
      "loss": 0.2014,
      "step": 890
    },
    {
      "epoch": 7.83,
      "learning_rate": 2.149122807017544e-05,
      "loss": 0.1106,
      "step": 895
    },
    {
      "epoch": 7.88,
      "learning_rate": 2.105263157894737e-05,
      "loss": 0.1049,
      "step": 900
    },
    {
      "epoch": 7.92,
      "learning_rate": 2.06140350877193e-05,
      "loss": 0.0893,
      "step": 905
    },
    {
      "epoch": 7.96,
      "learning_rate": 2.0175438596491227e-05,
      "loss": 0.1821,
      "step": 910
    },
    {
      "epoch": 8.0,
      "eval_accuracy": 0.9901477832512315,
      "eval_loss": 0.041182905435562134,
      "eval_runtime": 19.2291,
      "eval_samples_per_second": 63.341,
      "eval_steps_per_second": 7.957,
      "step": 914
    },
    {
      "epoch": 8.01,
      "learning_rate": 1.9736842105263158e-05,
      "loss": 0.137,
      "step": 915
    },
    {
      "epoch": 8.05,
      "learning_rate": 1.929824561403509e-05,
      "loss": 0.1225,
      "step": 920
    },
    {
      "epoch": 8.1,
      "learning_rate": 1.885964912280702e-05,
      "loss": 0.1465,
      "step": 925
    },
    {
      "epoch": 8.14,
      "learning_rate": 1.8421052631578947e-05,
      "loss": 0.1588,
      "step": 930
    },
    {
      "epoch": 8.18,
      "learning_rate": 1.7982456140350878e-05,
      "loss": 0.163,
      "step": 935
    },
    {
      "epoch": 8.23,
      "learning_rate": 1.7543859649122806e-05,
      "loss": 0.0645,
      "step": 940
    },
    {
      "epoch": 8.27,
      "learning_rate": 1.7105263157894737e-05,
      "loss": 0.0546,
      "step": 945
    },
    {
      "epoch": 8.32,
      "learning_rate": 1.6666666666666667e-05,
      "loss": 0.0346,
      "step": 950
    },
    {
      "epoch": 8.36,
      "learning_rate": 1.62280701754386e-05,
      "loss": 0.099,
      "step": 955
    },
    {
      "epoch": 8.4,
      "learning_rate": 1.5789473684210526e-05,
      "loss": 0.1723,
      "step": 960
    },
    {
      "epoch": 8.45,
      "learning_rate": 1.5350877192982457e-05,
      "loss": 0.1102,
      "step": 965
    },
    {
      "epoch": 8.49,
      "learning_rate": 1.4912280701754386e-05,
      "loss": 0.1221,
      "step": 970
    },
    {
      "epoch": 8.53,
      "learning_rate": 1.4473684210526317e-05,
      "loss": 0.1574,
      "step": 975
    },
    {
      "epoch": 8.58,
      "learning_rate": 1.4035087719298246e-05,
      "loss": 0.0542,
      "step": 980
    },
    {
      "epoch": 8.62,
      "learning_rate": 1.3596491228070177e-05,
      "loss": 0.121,
      "step": 985
    },
    {
      "epoch": 8.67,
      "learning_rate": 1.3157894736842106e-05,
      "loss": 0.0355,
      "step": 990
    },
    {
      "epoch": 8.71,
      "learning_rate": 1.2719298245614037e-05,
      "loss": 0.0715,
      "step": 995
    },
    {
      "epoch": 8.75,
      "learning_rate": 1.2280701754385964e-05,
      "loss": 0.0456,
      "step": 1000
    },
    {
      "epoch": 8.8,
      "learning_rate": 1.1842105263157895e-05,
      "loss": 0.0774,
      "step": 1005
    },
    {
      "epoch": 8.84,
      "learning_rate": 1.1403508771929824e-05,
      "loss": 0.0309,
      "step": 1010
    },
    {
      "epoch": 8.88,
      "learning_rate": 1.0964912280701754e-05,
      "loss": 0.1048,
      "step": 1015
    },
    {
      "epoch": 8.93,
      "learning_rate": 1.0526315789473684e-05,
      "loss": 0.1286,
      "step": 1020
    },
    {
      "epoch": 8.97,
      "learning_rate": 1.0087719298245614e-05,
      "loss": 0.1853,
      "step": 1025
    },
    {
      "epoch": 9.0,
      "eval_accuracy": 0.9942528735632183,
      "eval_loss": 0.02394494228065014,
      "eval_runtime": 19.1714,
      "eval_samples_per_second": 63.532,
      "eval_steps_per_second": 7.981,
      "step": 1028
    },
    {
      "epoch": 9.02,
      "learning_rate": 9.649122807017545e-06,
      "loss": 0.0881,
      "step": 1030
    },
    {
      "epoch": 9.06,
      "learning_rate": 9.210526315789474e-06,
      "loss": 0.0734,
      "step": 1035
    },
    {
      "epoch": 9.1,
      "learning_rate": 8.771929824561403e-06,
      "loss": 0.0274,
      "step": 1040
    },
    {
      "epoch": 9.15,
      "learning_rate": 8.333333333333334e-06,
      "loss": 0.1102,
      "step": 1045
    },
    {
      "epoch": 9.19,
      "learning_rate": 7.894736842105263e-06,
      "loss": 0.0844,
      "step": 1050
    },
    {
      "epoch": 9.23,
      "learning_rate": 7.456140350877193e-06,
      "loss": 0.0348,
      "step": 1055
    },
    {
      "epoch": 9.28,
      "learning_rate": 7.017543859649123e-06,
      "loss": 0.1314,
      "step": 1060
    },
    {
      "epoch": 9.32,
      "learning_rate": 6.578947368421053e-06,
      "loss": 0.1114,
      "step": 1065
    },
    {
      "epoch": 9.37,
      "learning_rate": 6.140350877192982e-06,
      "loss": 0.0509,
      "step": 1070
    },
    {
      "epoch": 9.41,
      "learning_rate": 5.701754385964912e-06,
      "loss": 0.0867,
      "step": 1075
    },
    {
      "epoch": 9.45,
      "learning_rate": 5.263157894736842e-06,
      "loss": 0.0165,
      "step": 1080
    },
    {
      "epoch": 9.5,
      "learning_rate": 4.824561403508772e-06,
      "loss": 0.1223,
      "step": 1085
    },
    {
      "epoch": 9.54,
      "learning_rate": 4.3859649122807014e-06,
      "loss": 0.0802,
      "step": 1090
    },
    {
      "epoch": 9.58,
      "learning_rate": 3.9473684210526315e-06,
      "loss": 0.1373,
      "step": 1095
    },
    {
      "epoch": 9.63,
      "learning_rate": 3.5087719298245615e-06,
      "loss": 0.0855,
      "step": 1100
    },
    {
      "epoch": 9.67,
      "learning_rate": 3.070175438596491e-06,
      "loss": 0.0934,
      "step": 1105
    },
    {
      "epoch": 9.72,
      "learning_rate": 2.631578947368421e-06,
      "loss": 0.0544,
      "step": 1110
    },
    {
      "epoch": 9.76,
      "learning_rate": 2.1929824561403507e-06,
      "loss": 0.0704,
      "step": 1115
    },
    {
      "epoch": 9.8,
      "learning_rate": 1.7543859649122807e-06,
      "loss": 0.0644,
      "step": 1120
    },
    {
      "epoch": 9.85,
      "learning_rate": 1.3157894736842106e-06,
      "loss": 0.064,
      "step": 1125
    },
    {
      "epoch": 9.89,
      "learning_rate": 8.771929824561404e-07,
      "loss": 0.0153,
      "step": 1130
    },
    {
      "epoch": 9.93,
      "learning_rate": 4.385964912280702e-07,
      "loss": 0.0909,
      "step": 1135
    },
    {
      "epoch": 9.98,
      "learning_rate": 0.0,
      "loss": 0.0666,
      "step": 1140
    },
    {
      "epoch": 9.98,
      "eval_accuracy": 0.9950738916256158,
      "eval_loss": 0.011206304654479027,
      "eval_runtime": 19.1932,
      "eval_samples_per_second": 63.46,
      "eval_steps_per_second": 7.972,
      "step": 1140
    },
    {
      "epoch": 9.98,
      "step": 1140,
      "total_flos": 8.390377142257582e+18,
      "train_loss": 0.46324286803341747,
      "train_runtime": 2845.9625,
      "train_samples_per_second": 12.829,
      "train_steps_per_second": 0.401
    }
  ],
  "logging_steps": 5,
  "max_steps": 1140,
  "num_train_epochs": 10,
  "save_steps": 500,
  "total_flos": 8.390377142257582e+18,
  "trial_name": null,
  "trial_params": null
}