{
  "best_metric": 0.9931339977851605,
  "best_model_checkpoint": "swinv2-large-patch4-window12to16-192to256-22kto1k-ft-finetuned-LungCancer-LC25000-AH-40-30-30-S/checkpoint-1309",
  "epoch": 6.990654205607477,
  "global_step": 1309,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.03,
      "learning_rate": 3.816793893129771e-06,
      "loss": 1.1779,
      "step": 5
    },
    {
      "epoch": 0.05,
      "learning_rate": 7.633587786259541e-06,
      "loss": 1.006,
      "step": 10
    },
    {
      "epoch": 0.08,
      "learning_rate": 1.1450381679389314e-05,
      "loss": 0.756,
      "step": 15
    },
    {
      "epoch": 0.11,
      "learning_rate": 1.5267175572519083e-05,
      "loss": 0.443,
      "step": 20
    },
    {
      "epoch": 0.13,
      "learning_rate": 1.9083969465648855e-05,
      "loss": 0.2475,
      "step": 25
    },
    {
      "epoch": 0.16,
      "learning_rate": 2.2900763358778628e-05,
      "loss": 0.2196,
      "step": 30
    },
    {
      "epoch": 0.19,
      "learning_rate": 2.6717557251908397e-05,
      "loss": 0.17,
      "step": 35
    },
    {
      "epoch": 0.21,
      "learning_rate": 3.0534351145038166e-05,
      "loss": 0.189,
      "step": 40
    },
    {
      "epoch": 0.24,
      "learning_rate": 3.435114503816794e-05,
      "loss": 0.3358,
      "step": 45
    },
    {
      "epoch": 0.27,
      "learning_rate": 3.816793893129771e-05,
      "loss": 0.2714,
      "step": 50
    },
    {
      "epoch": 0.29,
      "learning_rate": 4.198473282442748e-05,
      "loss": 0.1602,
      "step": 55
    },
    {
      "epoch": 0.32,
      "learning_rate": 4.5801526717557256e-05,
      "loss": 0.2671,
      "step": 60
    },
    {
      "epoch": 0.35,
      "learning_rate": 4.9618320610687025e-05,
      "loss": 0.2408,
      "step": 65
    },
    {
      "epoch": 0.37,
      "learning_rate": 5.3435114503816794e-05,
      "loss": 0.2186,
      "step": 70
    },
    {
      "epoch": 0.4,
      "learning_rate": 5.725190839694656e-05,
      "loss": 0.1904,
      "step": 75
    },
    {
      "epoch": 0.43,
      "learning_rate": 6.106870229007633e-05,
      "loss": 0.1271,
      "step": 80
    },
    {
      "epoch": 0.45,
      "learning_rate": 6.488549618320611e-05,
      "loss": 0.3301,
      "step": 85
    },
    {
      "epoch": 0.48,
      "learning_rate": 6.870229007633588e-05,
      "loss": 0.2404,
      "step": 90
    },
    {
      "epoch": 0.51,
      "learning_rate": 7.251908396946565e-05,
      "loss": 0.229,
      "step": 95
    },
    {
      "epoch": 0.53,
      "learning_rate": 7.633587786259542e-05,
      "loss": 0.1829,
      "step": 100
    },
    {
      "epoch": 0.56,
      "learning_rate": 8.015267175572518e-05,
      "loss": 0.1683,
      "step": 105
    },
    {
      "epoch": 0.59,
      "learning_rate": 8.396946564885496e-05,
      "loss": 0.2363,
      "step": 110
    },
    {
      "epoch": 0.61,
      "learning_rate": 8.778625954198472e-05,
      "loss": 0.2637,
      "step": 115
    },
    {
      "epoch": 0.64,
      "learning_rate": 9.160305343511451e-05,
      "loss": 0.3301,
      "step": 120
    },
    {
      "epoch": 0.67,
      "learning_rate": 9.541984732824429e-05,
      "loss": 0.2141,
      "step": 125
    },
    {
      "epoch": 0.69,
      "learning_rate": 9.923664122137405e-05,
      "loss": 0.1592,
      "step": 130
    },
    {
      "epoch": 0.72,
      "learning_rate": 0.00010305343511450383,
      "loss": 0.2908,
      "step": 135
    },
    {
      "epoch": 0.75,
      "learning_rate": 0.00010687022900763359,
      "loss": 0.1797,
      "step": 140
    },
    {
      "epoch": 0.77,
      "learning_rate": 0.00011068702290076336,
      "loss": 0.3134,
      "step": 145
    },
    {
      "epoch": 0.8,
      "learning_rate": 0.00011450381679389313,
      "loss": 0.2634,
      "step": 150
    },
    {
      "epoch": 0.83,
      "learning_rate": 0.0001183206106870229,
      "loss": 0.2527,
      "step": 155
    },
    {
      "epoch": 0.85,
      "learning_rate": 0.00012213740458015266,
      "loss": 0.3261,
      "step": 160
    },
    {
      "epoch": 0.88,
      "learning_rate": 0.00012595419847328244,
      "loss": 0.2047,
      "step": 165
    },
    {
      "epoch": 0.91,
      "learning_rate": 0.00012977099236641222,
      "loss": 0.1162,
      "step": 170
    },
    {
      "epoch": 0.93,
      "learning_rate": 0.000133587786259542,
      "loss": 0.2225,
      "step": 175
    },
    {
      "epoch": 0.96,
      "learning_rate": 0.00013740458015267177,
      "loss": 0.1982,
      "step": 180
    },
    {
      "epoch": 0.99,
      "learning_rate": 0.00014122137404580154,
      "loss": 0.176,
      "step": 185
    },
    {
      "epoch": 1.0,
      "eval_accuracy": 0.9663344407530454,
      "eval_loss": 0.08905145525932312,
      "eval_runtime": 2220.808,
      "eval_samples_per_second": 2.033,
      "eval_steps_per_second": 0.254,
      "step": 187
    },
    {
      "epoch": 1.01,
      "learning_rate": 0.0001450381679389313,
      "loss": 0.2658,
      "step": 190
    },
    {
      "epoch": 1.04,
      "learning_rate": 0.00014885496183206107,
      "loss": 0.2131,
      "step": 195
    },
    {
      "epoch": 1.07,
      "learning_rate": 0.00015267175572519084,
      "loss": 0.4798,
      "step": 200
    },
    {
      "epoch": 1.09,
      "learning_rate": 0.00015648854961832062,
      "loss": 0.4856,
      "step": 205
    },
    {
      "epoch": 1.12,
      "learning_rate": 0.00016030534351145037,
      "loss": 0.1263,
      "step": 210
    },
    {
      "epoch": 1.15,
      "learning_rate": 0.00016412213740458014,
      "loss": 0.1071,
      "step": 215
    },
    {
      "epoch": 1.17,
      "learning_rate": 0.00016793893129770992,
      "loss": 0.3246,
      "step": 220
    },
    {
      "epoch": 1.2,
      "learning_rate": 0.0001717557251908397,
      "loss": 0.3047,
      "step": 225
    },
    {
      "epoch": 1.23,
      "learning_rate": 0.00017557251908396944,
      "loss": 0.3411,
      "step": 230
    },
    {
      "epoch": 1.26,
      "learning_rate": 0.00017938931297709925,
      "loss": 0.1746,
      "step": 235
    },
    {
      "epoch": 1.28,
      "learning_rate": 0.00018320610687022902,
      "loss": 0.199,
      "step": 240
    },
    {
      "epoch": 1.31,
      "learning_rate": 0.0001870229007633588,
      "loss": 0.1853,
      "step": 245
    },
    {
      "epoch": 1.34,
      "learning_rate": 0.00019083969465648857,
      "loss": 0.2752,
      "step": 250
    },
    {
      "epoch": 1.36,
      "learning_rate": 0.00019465648854961832,
      "loss": 0.5029,
      "step": 255
    },
    {
      "epoch": 1.39,
      "learning_rate": 0.0001984732824427481,
      "loss": 0.4166,
      "step": 260
    },
    {
      "epoch": 1.42,
      "learning_rate": 0.00020229007633587788,
      "loss": 0.2551,
      "step": 265
    },
    {
      "epoch": 1.44,
      "learning_rate": 0.00020610687022900765,
      "loss": 0.1754,
      "step": 270
    },
    {
      "epoch": 1.47,
      "learning_rate": 0.0002099236641221374,
      "loss": 0.192,
      "step": 275
    },
    {
      "epoch": 1.5,
      "learning_rate": 0.00021374045801526718,
      "loss": 0.2465,
      "step": 280
    },
    {
      "epoch": 1.52,
      "learning_rate": 0.00021755725190839695,
      "loss": 0.3647,
      "step": 285
    },
    {
      "epoch": 1.55,
      "learning_rate": 0.00022137404580152673,
      "loss": 0.2527,
      "step": 290
    },
    {
      "epoch": 1.58,
      "learning_rate": 0.00022519083969465648,
      "loss": 0.1766,
      "step": 295
    },
    {
      "epoch": 1.6,
      "learning_rate": 0.00022900763358778625,
      "loss": 0.255,
      "step": 300
    },
    {
      "epoch": 1.63,
      "learning_rate": 0.00023282442748091603,
      "loss": 0.2679,
      "step": 305
    },
    {
      "epoch": 1.66,
      "learning_rate": 0.0002366412213740458,
      "loss": 0.3582,
      "step": 310
    },
    {
      "epoch": 1.68,
      "learning_rate": 0.00024045801526717558,
      "loss": 0.3507,
      "step": 315
    },
    {
      "epoch": 1.71,
      "learning_rate": 0.00024427480916030533,
      "loss": 0.236,
      "step": 320
    },
    {
      "epoch": 1.74,
      "learning_rate": 0.00024809160305343513,
      "loss": 0.2117,
      "step": 325
    },
    {
      "epoch": 1.76,
      "learning_rate": 0.0002519083969465649,
      "loss": 0.1137,
      "step": 330
    },
    {
      "epoch": 1.79,
      "learning_rate": 0.00025572519083969463,
      "loss": 0.1813,
      "step": 335
    },
    {
      "epoch": 1.82,
      "learning_rate": 0.00025954198473282443,
      "loss": 0.3319,
      "step": 340
    },
    {
      "epoch": 1.84,
      "learning_rate": 0.0002633587786259542,
      "loss": 0.3197,
      "step": 345
    },
    {
      "epoch": 1.87,
      "learning_rate": 0.000267175572519084,
      "loss": 0.2639,
      "step": 350
    },
    {
      "epoch": 1.9,
      "learning_rate": 0.00027099236641221373,
      "loss": 0.2399,
      "step": 355
    },
    {
      "epoch": 1.92,
      "learning_rate": 0.00027480916030534353,
      "loss": 0.3508,
      "step": 360
    },
    {
      "epoch": 1.95,
      "learning_rate": 0.0002786259541984733,
      "loss": 0.2495,
      "step": 365
    },
    {
      "epoch": 1.98,
      "learning_rate": 0.0002824427480916031,
      "loss": 0.2574,
      "step": 370
    },
    {
      "epoch": 2.0,
      "eval_accuracy": 0.9249169435215947,
      "eval_loss": 0.21274060010910034,
      "eval_runtime": 199.9611,
      "eval_samples_per_second": 22.579,
      "eval_steps_per_second": 2.826,
      "step": 374
    },
    {
      "epoch": 2.0,
      "learning_rate": 0.0002862595419847328,
      "loss": 0.3538,
      "step": 375
    },
    {
      "epoch": 2.03,
      "learning_rate": 0.0002900763358778626,
      "loss": 0.1445,
      "step": 380
    },
    {
      "epoch": 2.06,
      "learning_rate": 0.0002938931297709924,
      "loss": 0.2736,
      "step": 385
    },
    {
      "epoch": 2.08,
      "learning_rate": 0.00029770992366412214,
      "loss": 0.2254,
      "step": 390
    },
    {
      "epoch": 2.11,
      "learning_rate": 0.00030152671755725194,
      "loss": 0.1761,
      "step": 395
    },
    {
      "epoch": 2.14,
      "learning_rate": 0.0003053435114503817,
      "loss": 0.2928,
      "step": 400
    },
    {
      "epoch": 2.16,
      "learning_rate": 0.0003091603053435115,
      "loss": 0.1804,
      "step": 405
    },
    {
      "epoch": 2.19,
      "learning_rate": 0.00031297709923664124,
      "loss": 0.2572,
      "step": 410
    },
    {
      "epoch": 2.22,
      "learning_rate": 0.000316793893129771,
      "loss": 0.2419,
      "step": 415
    },
    {
      "epoch": 2.24,
      "learning_rate": 0.00032061068702290074,
      "loss": 0.1741,
      "step": 420
    },
    {
      "epoch": 2.27,
      "learning_rate": 0.00032442748091603054,
      "loss": 0.1857,
      "step": 425
    },
    {
      "epoch": 2.3,
      "learning_rate": 0.0003282442748091603,
      "loss": 0.2407,
      "step": 430
    },
    {
      "epoch": 2.32,
      "learning_rate": 0.0003320610687022901,
      "loss": 0.2855,
      "step": 435
    },
    {
      "epoch": 2.35,
      "learning_rate": 0.00033587786259541984,
      "loss": 0.2814,
      "step": 440
    },
    {
      "epoch": 2.38,
      "learning_rate": 0.00033969465648854964,
      "loss": 0.2093,
      "step": 445
    },
    {
      "epoch": 2.4,
      "learning_rate": 0.0003435114503816794,
      "loss": 0.5727,
      "step": 450
    },
    {
      "epoch": 2.43,
      "learning_rate": 0.0003473282442748092,
      "loss": 0.2078,
      "step": 455
    },
    {
      "epoch": 2.46,
      "learning_rate": 0.0003511450381679389,
      "loss": 0.2195,
      "step": 460
    },
    {
      "epoch": 2.48,
      "learning_rate": 0.0003549618320610687,
      "loss": 0.2145,
      "step": 465
    },
    {
      "epoch": 2.51,
      "learning_rate": 0.0003587786259541985,
      "loss": 0.3072,
      "step": 470
    },
    {
      "epoch": 2.54,
      "learning_rate": 0.00036259541984732824,
      "loss": 0.1972,
      "step": 475
    },
    {
      "epoch": 2.56,
      "learning_rate": 0.00036641221374045805,
      "loss": 0.1569,
      "step": 480
    },
    {
      "epoch": 2.59,
      "learning_rate": 0.0003702290076335878,
      "loss": 0.2367,
      "step": 485
    },
    {
      "epoch": 2.62,
      "learning_rate": 0.0003740458015267176,
      "loss": 0.1382,
      "step": 490
    },
    {
      "epoch": 2.64,
      "learning_rate": 0.00037786259541984735,
      "loss": 0.313,
      "step": 495
    },
    {
      "epoch": 2.67,
      "learning_rate": 0.00038167938931297715,
      "loss": 0.2987,
      "step": 500
    },
    {
      "epoch": 2.7,
      "learning_rate": 0.00038549618320610684,
      "loss": 0.4081,
      "step": 505
    },
    {
      "epoch": 2.72,
      "learning_rate": 0.00038931297709923665,
      "loss": 0.21,
      "step": 510
    },
    {
      "epoch": 2.75,
      "learning_rate": 0.0003931297709923664,
      "loss": 0.2028,
      "step": 515
    },
    {
      "epoch": 2.78,
      "learning_rate": 0.0003969465648854962,
      "loss": 0.2109,
      "step": 520
    },
    {
      "epoch": 2.8,
      "learning_rate": 0.00040076335877862595,
      "loss": 0.1649,
      "step": 525
    },
    {
      "epoch": 2.83,
      "learning_rate": 0.00040458015267175575,
      "loss": 0.1715,
      "step": 530
    },
    {
      "epoch": 2.86,
      "learning_rate": 0.0004083969465648855,
      "loss": 0.2841,
      "step": 535
    },
    {
      "epoch": 2.88,
      "learning_rate": 0.0004122137404580153,
      "loss": 0.5783,
      "step": 540
    },
    {
      "epoch": 2.91,
      "learning_rate": 0.00041603053435114505,
      "loss": 0.2577,
      "step": 545
    },
    {
      "epoch": 2.94,
      "learning_rate": 0.0004198473282442748,
      "loss": 0.3562,
      "step": 550
    },
    {
      "epoch": 2.96,
      "learning_rate": 0.00042366412213740455,
      "loss": 0.1978,
      "step": 555
    },
    {
      "epoch": 2.99,
      "learning_rate": 0.00042748091603053435,
      "loss": 0.2416,
      "step": 560
    },
    {
      "epoch": 3.0,
      "eval_accuracy": 0.9235880398671097,
      "eval_loss": 0.24068056046962738,
      "eval_runtime": 199.5391,
      "eval_samples_per_second": 22.627,
      "eval_steps_per_second": 2.832,
      "step": 561
    },
    {
      "epoch": 3.02,
      "learning_rate": 0.00043129770992366415,
      "loss": 0.4637,
      "step": 565
    },
    {
      "epoch": 3.04,
      "learning_rate": 0.0004351145038167939,
      "loss": 0.2742,
      "step": 570
    },
    {
      "epoch": 3.07,
      "learning_rate": 0.0004389312977099237,
      "loss": 0.1964,
      "step": 575
    },
    {
      "epoch": 3.1,
      "learning_rate": 0.00044274809160305345,
      "loss": 0.1171,
      "step": 580
    },
    {
      "epoch": 3.12,
      "learning_rate": 0.00044656488549618326,
      "loss": 0.2311,
      "step": 585
    },
    {
      "epoch": 3.15,
      "learning_rate": 0.00045038167938931295,
      "loss": 0.3213,
      "step": 590
    },
    {
      "epoch": 3.18,
      "learning_rate": 0.00045419847328244275,
      "loss": 0.4646,
      "step": 595
    },
    {
      "epoch": 3.2,
      "learning_rate": 0.0004580152671755725,
      "loss": 0.3705,
      "step": 600
    },
    {
      "epoch": 3.23,
      "learning_rate": 0.0004618320610687023,
      "loss": 0.3722,
      "step": 605
    },
    {
      "epoch": 3.26,
      "learning_rate": 0.00046564885496183206,
      "loss": 0.2067,
      "step": 610
    },
    {
      "epoch": 3.28,
      "learning_rate": 0.00046946564885496186,
      "loss": 0.3482,
      "step": 615
    },
    {
      "epoch": 3.31,
      "learning_rate": 0.0004732824427480916,
      "loss": 0.6133,
      "step": 620
    },
    {
      "epoch": 3.34,
      "learning_rate": 0.0004770992366412214,
      "loss": 0.1821,
      "step": 625
    },
    {
      "epoch": 3.36,
      "learning_rate": 0.00048091603053435116,
      "loss": 0.1156,
      "step": 630
    },
    {
      "epoch": 3.39,
      "learning_rate": 0.0004847328244274809,
      "loss": 0.3412,
      "step": 635
    },
    {
      "epoch": 3.42,
      "learning_rate": 0.0004885496183206107,
      "loss": 0.3401,
      "step": 640
    },
    {
      "epoch": 3.44,
      "learning_rate": 0.0004923664122137404,
      "loss": 0.3777,
      "step": 645
    },
    {
      "epoch": 3.47,
      "learning_rate": 0.0004961832061068703,
      "loss": 0.3208,
      "step": 650
    },
    {
      "epoch": 3.5,
      "learning_rate": 0.0005,
      "loss": 0.2342,
      "step": 655
    },
    {
      "epoch": 3.52,
      "learning_rate": 0.000496177370030581,
      "loss": 0.138,
      "step": 660
    },
    {
      "epoch": 3.55,
      "learning_rate": 0.0004923547400611621,
      "loss": 0.347,
      "step": 665
    },
    {
      "epoch": 3.58,
      "learning_rate": 0.0004885321100917432,
      "loss": 0.1618,
      "step": 670
    },
    {
      "epoch": 3.6,
      "learning_rate": 0.00048470948012232416,
      "loss": 0.4014,
      "step": 675
    },
    {
      "epoch": 3.63,
      "learning_rate": 0.00048088685015290524,
      "loss": 0.2076,
      "step": 680
    },
    {
      "epoch": 3.66,
      "learning_rate": 0.00047706422018348627,
      "loss": 0.3927,
      "step": 685
    },
    {
      "epoch": 3.68,
      "learning_rate": 0.00047324159021406724,
      "loss": 0.2456,
      "step": 690
    },
    {
      "epoch": 3.71,
      "learning_rate": 0.0004694189602446483,
      "loss": 0.2381,
      "step": 695
    },
    {
      "epoch": 3.74,
      "learning_rate": 0.00046559633027522934,
      "loss": 0.3495,
      "step": 700
    },
    {
      "epoch": 3.77,
      "learning_rate": 0.00046177370030581037,
      "loss": 0.2412,
      "step": 705
    },
    {
      "epoch": 3.79,
      "learning_rate": 0.00045795107033639145,
      "loss": 0.0919,
      "step": 710
    },
    {
      "epoch": 3.82,
      "learning_rate": 0.0004541284403669725,
      "loss": 0.1719,
      "step": 715
    },
    {
      "epoch": 3.85,
      "learning_rate": 0.00045030581039755355,
      "loss": 0.2253,
      "step": 720
    },
    {
      "epoch": 3.87,
      "learning_rate": 0.0004464831804281346,
      "loss": 0.266,
      "step": 725
    },
    {
      "epoch": 3.9,
      "learning_rate": 0.0004426605504587156,
      "loss": 0.393,
      "step": 730
    },
    {
      "epoch": 3.93,
      "learning_rate": 0.0004388379204892967,
      "loss": 0.1946,
      "step": 735
    },
    {
      "epoch": 3.95,
      "learning_rate": 0.0004350152905198777,
      "loss": 0.2403,
      "step": 740
    },
    {
      "epoch": 3.98,
      "learning_rate": 0.00043119266055045873,
      "loss": 0.2457,
      "step": 745
    },
    {
      "epoch": 4.0,
      "eval_accuracy": 0.9632336655592469,
      "eval_loss": 0.12449143081903458,
      "eval_runtime": 199.4812,
      "eval_samples_per_second": 22.634,
      "eval_steps_per_second": 2.832,
      "step": 749
    },
    {
      "epoch": 4.01,
      "learning_rate": 0.00042737003058103976,
      "loss": 0.1742,
      "step": 750
    },
    {
      "epoch": 4.03,
      "learning_rate": 0.0004235474006116208,
      "loss": 0.1818,
      "step": 755
    },
    {
      "epoch": 4.06,
      "learning_rate": 0.0004197247706422018,
      "loss": 0.1993,
      "step": 760
    },
    {
      "epoch": 4.09,
      "learning_rate": 0.0004159021406727829,
      "loss": 0.2366,
      "step": 765
    },
    {
      "epoch": 4.11,
      "learning_rate": 0.0004120795107033639,
      "loss": 0.3832,
      "step": 770
    },
    {
      "epoch": 4.14,
      "learning_rate": 0.00040825688073394494,
      "loss": 0.3366,
      "step": 775
    },
    {
      "epoch": 4.17,
      "learning_rate": 0.000404434250764526,
      "loss": 0.2643,
      "step": 780
    },
    {
      "epoch": 4.19,
      "learning_rate": 0.00040061162079510704,
      "loss": 0.1366,
      "step": 785
    },
    {
      "epoch": 4.22,
      "learning_rate": 0.00039678899082568807,
      "loss": 0.1477,
      "step": 790
    },
    {
      "epoch": 4.25,
      "learning_rate": 0.00039296636085626915,
      "loss": 0.1768,
      "step": 795
    },
    {
      "epoch": 4.27,
      "learning_rate": 0.00038914373088685017,
      "loss": 0.1896,
      "step": 800
    },
    {
      "epoch": 4.3,
      "learning_rate": 0.0003853211009174312,
      "loss": 0.1293,
      "step": 805
    },
    {
      "epoch": 4.33,
      "learning_rate": 0.0003814984709480123,
      "loss": 0.1712,
      "step": 810
    },
    {
      "epoch": 4.35,
      "learning_rate": 0.00037767584097859325,
      "loss": 0.2588,
      "step": 815
    },
    {
      "epoch": 4.38,
      "learning_rate": 0.00037385321100917427,
      "loss": 0.2662,
      "step": 820
    },
    {
      "epoch": 4.41,
      "learning_rate": 0.00037003058103975535,
      "loss": 0.1665,
      "step": 825
    },
    {
      "epoch": 4.43,
      "learning_rate": 0.0003662079510703364,
      "loss": 0.1282,
      "step": 830
    },
    {
      "epoch": 4.46,
      "learning_rate": 0.00036238532110091746,
      "loss": 0.3499,
      "step": 835
    },
    {
      "epoch": 4.49,
      "learning_rate": 0.0003585626911314985,
      "loss": 0.5141,
      "step": 840
    },
    {
      "epoch": 4.51,
      "learning_rate": 0.0003547400611620795,
      "loss": 0.2327,
      "step": 845
    },
    {
      "epoch": 4.54,
      "learning_rate": 0.0003509174311926606,
      "loss": 0.1088,
      "step": 850
    },
    {
      "epoch": 4.57,
      "learning_rate": 0.0003470948012232416,
      "loss": 0.0992,
      "step": 855
    },
    {
      "epoch": 4.59,
      "learning_rate": 0.00034327217125382264,
      "loss": 0.1203,
      "step": 860
    },
    {
      "epoch": 4.62,
      "learning_rate": 0.0003394495412844037,
      "loss": 0.2057,
      "step": 865
    },
    {
      "epoch": 4.65,
      "learning_rate": 0.00033562691131498474,
      "loss": 0.2275,
      "step": 870
    },
    {
      "epoch": 4.67,
      "learning_rate": 0.00033180428134556576,
      "loss": 0.09,
      "step": 875
    },
    {
      "epoch": 4.7,
      "learning_rate": 0.0003279816513761468,
      "loss": 0.1304,
      "step": 880
    },
    {
      "epoch": 4.73,
      "learning_rate": 0.0003241590214067278,
      "loss": 0.125,
      "step": 885
    },
    {
      "epoch": 4.75,
      "learning_rate": 0.00032033639143730884,
      "loss": 0.1223,
      "step": 890
    },
    {
      "epoch": 4.78,
      "learning_rate": 0.0003165137614678899,
      "loss": 0.1314,
      "step": 895
    },
    {
      "epoch": 4.81,
      "learning_rate": 0.00031269113149847094,
      "loss": 0.1529,
      "step": 900
    },
    {
      "epoch": 4.83,
      "learning_rate": 0.00030886850152905197,
      "loss": 0.1601,
      "step": 905
    },
    {
      "epoch": 4.86,
      "learning_rate": 0.00030504587155963305,
      "loss": 0.0514,
      "step": 910
    },
    {
      "epoch": 4.89,
      "learning_rate": 0.0003012232415902141,
      "loss": 0.1469,
      "step": 915
    },
    {
      "epoch": 4.91,
      "learning_rate": 0.0002974006116207951,
      "loss": 0.1872,
      "step": 920
    },
    {
      "epoch": 4.94,
      "learning_rate": 0.0002935779816513762,
      "loss": 0.4385,
      "step": 925
    },
    {
      "epoch": 4.97,
      "learning_rate": 0.0002897553516819572,
      "loss": 0.1051,
      "step": 930
    },
    {
      "epoch": 4.99,
      "learning_rate": 0.0002859327217125383,
      "loss": 0.3583,
      "step": 935
    },
    {
      "epoch": 5.0,
      "eval_accuracy": 0.940420819490587,
      "eval_loss": 0.17089825868606567,
      "eval_runtime": 199.5748,
      "eval_samples_per_second": 22.623,
      "eval_steps_per_second": 2.831,
      "step": 936
    },
    {
      "epoch": 5.02,
      "learning_rate": 0.00028211009174311925,
      "loss": 0.2089,
      "step": 940
    },
    {
      "epoch": 5.05,
      "learning_rate": 0.0002782874617737003,
      "loss": 0.0995,
      "step": 945
    },
    {
      "epoch": 5.07,
      "learning_rate": 0.00027446483180428136,
      "loss": 0.1323,
      "step": 950
    },
    {
      "epoch": 5.1,
      "learning_rate": 0.0002706422018348624,
      "loss": 0.1608,
      "step": 955
    },
    {
      "epoch": 5.13,
      "learning_rate": 0.0002668195718654434,
      "loss": 0.1366,
      "step": 960
    },
    {
      "epoch": 5.15,
      "learning_rate": 0.0002629969418960245,
      "loss": 0.1587,
      "step": 965
    },
    {
      "epoch": 5.18,
      "learning_rate": 0.0002591743119266055,
      "loss": 0.0915,
      "step": 970
    },
    {
      "epoch": 5.21,
      "learning_rate": 0.00025535168195718654,
      "loss": 0.1566,
      "step": 975
    },
    {
      "epoch": 5.23,
      "learning_rate": 0.0002515290519877676,
      "loss": 0.1494,
      "step": 980
    },
    {
      "epoch": 5.26,
      "learning_rate": 0.00024770642201834864,
      "loss": 0.1051,
      "step": 985
    },
    {
      "epoch": 5.29,
      "learning_rate": 0.00024388379204892967,
      "loss": 0.0536,
      "step": 990
    },
    {
      "epoch": 5.31,
      "learning_rate": 0.0002400611620795107,
      "loss": 0.1352,
      "step": 995
    },
    {
      "epoch": 5.34,
      "learning_rate": 0.00023623853211009174,
      "loss": 0.1114,
      "step": 1000
    },
    {
      "epoch": 5.37,
      "learning_rate": 0.0002324159021406728,
      "loss": 0.108,
      "step": 1005
    },
    {
      "epoch": 5.39,
      "learning_rate": 0.00022859327217125385,
      "loss": 0.1227,
      "step": 1010
    },
    {
      "epoch": 5.42,
      "learning_rate": 0.00022477064220183487,
      "loss": 0.1345,
      "step": 1015
    },
    {
      "epoch": 5.45,
      "learning_rate": 0.0002209480122324159,
      "loss": 0.1356,
      "step": 1020
    },
    {
      "epoch": 5.47,
      "learning_rate": 0.00021712538226299695,
      "loss": 0.0851,
      "step": 1025
    },
    {
      "epoch": 5.5,
      "learning_rate": 0.00021330275229357798,
      "loss": 0.1514,
      "step": 1030
    },
    {
      "epoch": 5.53,
      "learning_rate": 0.00020948012232415903,
      "loss": 0.1007,
      "step": 1035
    },
    {
      "epoch": 5.55,
      "learning_rate": 0.00020565749235474008,
      "loss": 0.0984,
      "step": 1040
    },
    {
      "epoch": 5.58,
      "learning_rate": 0.0002018348623853211,
      "loss": 0.1566,
      "step": 1045
    },
    {
      "epoch": 5.61,
      "learning_rate": 0.00019801223241590213,
      "loss": 0.2042,
      "step": 1050
    },
    {
      "epoch": 5.63,
      "learning_rate": 0.00019418960244648318,
      "loss": 0.1433,
      "step": 1055
    },
    {
      "epoch": 5.66,
      "learning_rate": 0.0001903669724770642,
      "loss": 0.0526,
      "step": 1060
    },
    {
      "epoch": 5.69,
      "learning_rate": 0.00018654434250764526,
      "loss": 0.1404,
      "step": 1065
    },
    {
      "epoch": 5.71,
      "learning_rate": 0.0001827217125382263,
      "loss": 0.1393,
      "step": 1070
    },
    {
      "epoch": 5.74,
      "learning_rate": 0.00017889908256880736,
      "loss": 0.198,
      "step": 1075
    },
    {
      "epoch": 5.77,
      "learning_rate": 0.00017507645259938836,
      "loss": 0.0803,
      "step": 1080
    },
    {
      "epoch": 5.79,
      "learning_rate": 0.00017125382262996941,
      "loss": 0.0685,
      "step": 1085
    },
    {
      "epoch": 5.82,
      "learning_rate": 0.00016743119266055047,
      "loss": 0.075,
      "step": 1090
    },
    {
      "epoch": 5.85,
      "learning_rate": 0.0001636085626911315,
      "loss": 0.113,
      "step": 1095
    },
    {
      "epoch": 5.87,
      "learning_rate": 0.00015978593272171254,
      "loss": 0.166,
      "step": 1100
    },
    {
      "epoch": 5.9,
      "learning_rate": 0.0001559633027522936,
      "loss": 0.1116,
      "step": 1105
    },
    {
      "epoch": 5.93,
      "learning_rate": 0.00015214067278287462,
      "loss": 0.0457,
      "step": 1110
    },
    {
      "epoch": 5.95,
      "learning_rate": 0.00014831804281345565,
      "loss": 0.1791,
      "step": 1115
    },
    {
      "epoch": 5.98,
      "learning_rate": 0.0001444954128440367,
      "loss": 0.149,
      "step": 1120
    },
    {
      "epoch": 6.0,
      "eval_accuracy": 0.9813953488372092,
      "eval_loss": 0.050164252519607544,
      "eval_runtime": 200.5287,
      "eval_samples_per_second": 22.515,
      "eval_steps_per_second": 2.818,
      "step": 1123
    },
    {
      "epoch": 6.01,
      "learning_rate": 0.00014067278287461775,
      "loss": 0.0968,
      "step": 1125
    },
    {
      "epoch": 6.03,
      "learning_rate": 0.00013685015290519878,
      "loss": 0.1238,
      "step": 1130
    },
    {
      "epoch": 6.06,
      "learning_rate": 0.00013302752293577983,
      "loss": 0.0348,
      "step": 1135
    },
    {
      "epoch": 6.09,
      "learning_rate": 0.00012920489296636088,
      "loss": 0.1474,
      "step": 1140
    },
    {
      "epoch": 6.11,
      "learning_rate": 0.00012538226299694188,
      "loss": 0.0695,
      "step": 1145
    },
    {
      "epoch": 6.14,
      "learning_rate": 0.00012155963302752294,
      "loss": 0.0442,
      "step": 1150
    },
    {
      "epoch": 6.17,
      "learning_rate": 0.00011773700305810397,
      "loss": 0.0618,
      "step": 1155
    },
    {
      "epoch": 6.19,
      "learning_rate": 0.00011391437308868502,
      "loss": 0.0461,
      "step": 1160
    },
    {
      "epoch": 6.22,
      "learning_rate": 0.00011009174311926606,
      "loss": 0.0709,
      "step": 1165
    },
    {
      "epoch": 6.25,
      "learning_rate": 0.0001062691131498471,
      "loss": 0.298,
      "step": 1170
    },
    {
      "epoch": 6.28,
      "learning_rate": 0.00010244648318042814,
      "loss": 0.1027,
      "step": 1175
    },
    {
      "epoch": 6.3,
      "learning_rate": 9.862385321100918e-05,
      "loss": 0.0527,
      "step": 1180
    },
    {
      "epoch": 6.33,
      "learning_rate": 9.480122324159021e-05,
      "loss": 0.1324,
      "step": 1185
    },
    {
      "epoch": 6.36,
      "learning_rate": 9.097859327217125e-05,
      "loss": 0.0493,
      "step": 1190
    },
    {
      "epoch": 6.38,
      "learning_rate": 8.71559633027523e-05,
      "loss": 0.1259,
      "step": 1195
    },
    {
      "epoch": 6.41,
      "learning_rate": 8.333333333333333e-05,
      "loss": 0.0601,
      "step": 1200
    },
    {
      "epoch": 6.44,
      "learning_rate": 7.951070336391437e-05,
      "loss": 0.0347,
      "step": 1205
    },
    {
      "epoch": 6.46,
      "learning_rate": 7.568807339449542e-05,
      "loss": 0.114,
      "step": 1210
    },
    {
      "epoch": 6.49,
      "learning_rate": 7.186544342507645e-05,
      "loss": 0.0324,
      "step": 1215
    },
    {
      "epoch": 6.52,
      "learning_rate": 6.80428134556575e-05,
      "loss": 0.0766,
      "step": 1220
    },
    {
      "epoch": 6.54,
      "learning_rate": 6.422018348623854e-05,
      "loss": 0.0466,
      "step": 1225
    },
    {
      "epoch": 6.57,
      "learning_rate": 6.0397553516819576e-05,
      "loss": 0.0974,
      "step": 1230
    },
    {
      "epoch": 6.6,
      "learning_rate": 5.6574923547400615e-05,
      "loss": 0.1163,
      "step": 1235
    },
    {
      "epoch": 6.62,
      "learning_rate": 5.275229357798165e-05,
      "loss": 0.1117,
      "step": 1240
    },
    {
      "epoch": 6.65,
      "learning_rate": 4.892966360856269e-05,
      "loss": 0.1026,
      "step": 1245
    },
    {
      "epoch": 6.68,
      "learning_rate": 4.510703363914373e-05,
      "loss": 0.0873,
      "step": 1250
    },
    {
      "epoch": 6.7,
      "learning_rate": 4.1284403669724776e-05,
      "loss": 0.069,
      "step": 1255
    },
    {
      "epoch": 6.73,
      "learning_rate": 3.746177370030581e-05,
      "loss": 0.0464,
      "step": 1260
    },
    {
      "epoch": 6.76,
      "learning_rate": 3.3639143730886846e-05,
      "loss": 0.0256,
      "step": 1265
    },
    {
      "epoch": 6.78,
      "learning_rate": 2.9816513761467892e-05,
      "loss": 0.1119,
      "step": 1270
    },
    {
      "epoch": 6.81,
      "learning_rate": 2.599388379204893e-05,
      "loss": 0.0179,
      "step": 1275
    },
    {
      "epoch": 6.84,
      "learning_rate": 2.217125382262997e-05,
      "loss": 0.0448,
      "step": 1280
    },
    {
      "epoch": 6.86,
      "learning_rate": 1.834862385321101e-05,
      "loss": 0.0438,
      "step": 1285
    },
    {
      "epoch": 6.89,
      "learning_rate": 1.452599388379205e-05,
      "loss": 0.0184,
      "step": 1290
    },
    {
      "epoch": 6.92,
      "learning_rate": 1.0703363914373088e-05,
      "loss": 0.0423,
      "step": 1295
    },
    {
      "epoch": 6.94,
      "learning_rate": 6.880733944954129e-06,
      "loss": 0.0928,
      "step": 1300
    },
    {
      "epoch": 6.97,
      "learning_rate": 3.0581039755351682e-06,
      "loss": 0.061,
      "step": 1305
    },
    {
      "epoch": 6.99,
      "eval_accuracy": 0.9931339977851605,
      "eval_loss": 0.021680034697055817,
      "eval_runtime": 200.3527,
      "eval_samples_per_second": 22.535,
      "eval_steps_per_second": 2.82,
      "step": 1309
    },
    {
      "epoch": 6.99,
      "step": 1309,
      "total_flos": 9.636137349860819e+18,
      "train_loss": 0.2149346098929894,
      "train_runtime": 11488.9653,
      "train_samples_per_second": 3.647,
      "train_steps_per_second": 0.114
    }
  ],
  "max_steps": 1309,
  "num_train_epochs": 7,
  "total_flos": 9.636137349860819e+18,
  "trial_name": null,
  "trial_params": null
}