{
  "best_metric": 0.9869324473975637,
  "best_model_checkpoint": "swinv2-large-patch4-window12to16-192to256-22kto1k-ft-finetuned-LungCancer-LC25000-AH-40-30-30/checkpoint-935",
  "epoch": 4.993324432576769,
  "global_step": 935,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.03,
      "learning_rate": 5.341880341880342e-06,
      "loss": 1.0848,
      "step": 5
    },
    {
      "epoch": 0.05,
      "learning_rate": 1.0683760683760684e-05,
      "loss": 0.8475,
      "step": 10
    },
    {
      "epoch": 0.08,
      "learning_rate": 1.6025641025641026e-05,
      "loss": 0.5854,
      "step": 15
    },
    {
      "epoch": 0.11,
      "learning_rate": 2.1367521367521368e-05,
      "loss": 0.4202,
      "step": 20
    },
    {
      "epoch": 0.13,
      "learning_rate": 2.670940170940171e-05,
      "loss": 0.2353,
      "step": 25
    },
    {
      "epoch": 0.16,
      "learning_rate": 3.205128205128205e-05,
      "loss": 0.3821,
      "step": 30
    },
    {
      "epoch": 0.19,
      "learning_rate": 3.739316239316239e-05,
      "loss": 0.2081,
      "step": 35
    },
    {
      "epoch": 0.21,
      "learning_rate": 4.2735042735042735e-05,
      "loss": 0.2178,
      "step": 40
    },
    {
      "epoch": 0.24,
      "learning_rate": 4.8076923076923084e-05,
      "loss": 0.2564,
      "step": 45
    },
    {
      "epoch": 0.27,
      "learning_rate": 5.341880341880342e-05,
      "loss": 0.3044,
      "step": 50
    },
    {
      "epoch": 0.29,
      "learning_rate": 5.876068376068376e-05,
      "loss": 0.3078,
      "step": 55
    },
    {
      "epoch": 0.32,
      "learning_rate": 6.41025641025641e-05,
      "loss": 0.2956,
      "step": 60
    },
    {
      "epoch": 0.35,
      "learning_rate": 6.944444444444444e-05,
      "loss": 0.3315,
      "step": 65
    },
    {
      "epoch": 0.37,
      "learning_rate": 7.478632478632479e-05,
      "loss": 0.2415,
      "step": 70
    },
    {
      "epoch": 0.4,
      "learning_rate": 8.012820512820514e-05,
      "loss": 0.2106,
      "step": 75
    },
    {
      "epoch": 0.43,
      "learning_rate": 8.547008547008547e-05,
      "loss": 0.3041,
      "step": 80
    },
    {
      "epoch": 0.45,
      "learning_rate": 9.081196581196581e-05,
      "loss": 0.2804,
      "step": 85
    },
    {
      "epoch": 0.48,
      "learning_rate": 9.615384615384617e-05,
      "loss": 0.2595,
      "step": 90
    },
    {
      "epoch": 0.51,
      "learning_rate": 0.0001014957264957265,
      "loss": 0.2368,
      "step": 95
    },
    {
      "epoch": 0.53,
      "learning_rate": 0.00010683760683760684,
      "loss": 0.2289,
      "step": 100
    },
    {
      "epoch": 0.56,
      "learning_rate": 0.00011217948717948718,
      "loss": 0.2365,
      "step": 105
    },
    {
      "epoch": 0.59,
      "learning_rate": 0.00011752136752136752,
      "loss": 0.1883,
      "step": 110
    },
    {
      "epoch": 0.61,
      "learning_rate": 0.00012286324786324785,
      "loss": 0.1392,
      "step": 115
    },
    {
      "epoch": 0.64,
      "learning_rate": 0.0001282051282051282,
      "loss": 0.1846,
      "step": 120
    },
    {
      "epoch": 0.67,
      "learning_rate": 0.00013354700854700856,
      "loss": 0.1617,
      "step": 125
    },
    {
      "epoch": 0.69,
      "learning_rate": 0.0001388888888888889,
      "loss": 0.175,
      "step": 130
    },
    {
      "epoch": 0.72,
      "learning_rate": 0.00014423076923076922,
      "loss": 0.1804,
      "step": 135
    },
    {
      "epoch": 0.75,
      "learning_rate": 0.00014957264957264957,
      "loss": 0.1856,
      "step": 140
    },
    {
      "epoch": 0.77,
      "learning_rate": 0.00015491452991452993,
      "loss": 0.3335,
      "step": 145
    },
    {
      "epoch": 0.8,
      "learning_rate": 0.00016025641025641028,
      "loss": 0.2025,
      "step": 150
    },
    {
      "epoch": 0.83,
      "learning_rate": 0.00016559829059829058,
      "loss": 0.2874,
      "step": 155
    },
    {
      "epoch": 0.85,
      "learning_rate": 0.00017094017094017094,
      "loss": 0.1968,
      "step": 160
    },
    {
      "epoch": 0.88,
      "learning_rate": 0.0001762820512820513,
      "loss": 0.2061,
      "step": 165
    },
    {
      "epoch": 0.91,
      "learning_rate": 0.00018162393162393162,
      "loss": 0.1617,
      "step": 170
    },
    {
      "epoch": 0.93,
      "learning_rate": 0.00018696581196581198,
      "loss": 0.3653,
      "step": 175
    },
    {
      "epoch": 0.96,
      "learning_rate": 0.00019230769230769233,
      "loss": 0.3449,
      "step": 180
    },
    {
      "epoch": 0.99,
      "learning_rate": 0.00019764957264957264,
      "loss": 0.3299,
      "step": 185
    },
    {
      "epoch": 1.0,
      "eval_accuracy": 0.9218161683277962,
      "eval_loss": 0.2117503136396408,
      "eval_runtime": 2740.4947,
      "eval_samples_per_second": 1.648,
      "eval_steps_per_second": 0.206,
      "step": 187
    },
    {
      "epoch": 1.01,
      "learning_rate": 0.000202991452991453,
      "loss": 0.2588,
      "step": 190
    },
    {
      "epoch": 1.04,
      "learning_rate": 0.00020833333333333335,
      "loss": 0.2101,
      "step": 195
    },
    {
      "epoch": 1.07,
      "learning_rate": 0.00021367521367521368,
      "loss": 0.5778,
      "step": 200
    },
    {
      "epoch": 1.09,
      "learning_rate": 0.00021901709401709403,
      "loss": 0.1887,
      "step": 205
    },
    {
      "epoch": 1.12,
      "learning_rate": 0.00022435897435897436,
      "loss": 0.2366,
      "step": 210
    },
    {
      "epoch": 1.15,
      "learning_rate": 0.0002297008547008547,
      "loss": 0.1779,
      "step": 215
    },
    {
      "epoch": 1.17,
      "learning_rate": 0.00023504273504273504,
      "loss": 0.1902,
      "step": 220
    },
    {
      "epoch": 1.2,
      "learning_rate": 0.0002403846153846154,
      "loss": 0.4555,
      "step": 225
    },
    {
      "epoch": 1.23,
      "learning_rate": 0.0002457264957264957,
      "loss": 0.2295,
      "step": 230
    },
    {
      "epoch": 1.26,
      "learning_rate": 0.00025106837606837605,
      "loss": 0.2224,
      "step": 235
    },
    {
      "epoch": 1.28,
      "learning_rate": 0.0002564102564102564,
      "loss": 0.257,
      "step": 240
    },
    {
      "epoch": 1.31,
      "learning_rate": 0.00026175213675213677,
      "loss": 0.395,
      "step": 245
    },
    {
      "epoch": 1.34,
      "learning_rate": 0.0002670940170940171,
      "loss": 0.3104,
      "step": 250
    },
    {
      "epoch": 1.36,
      "learning_rate": 0.0002724358974358974,
      "loss": 0.1329,
      "step": 255
    },
    {
      "epoch": 1.39,
      "learning_rate": 0.0002777777777777778,
      "loss": 0.6173,
      "step": 260
    },
    {
      "epoch": 1.42,
      "learning_rate": 0.00028311965811965813,
      "loss": 0.2237,
      "step": 265
    },
    {
      "epoch": 1.44,
      "learning_rate": 0.00028846153846153843,
      "loss": 0.1947,
      "step": 270
    },
    {
      "epoch": 1.47,
      "learning_rate": 0.00029380341880341884,
      "loss": 0.5807,
      "step": 275
    },
    {
      "epoch": 1.5,
      "learning_rate": 0.00029914529914529915,
      "loss": 0.193,
      "step": 280
    },
    {
      "epoch": 1.52,
      "learning_rate": 0.00030448717948717945,
      "loss": 0.2717,
      "step": 285
    },
    {
      "epoch": 1.55,
      "learning_rate": 0.00030982905982905986,
      "loss": 0.2197,
      "step": 290
    },
    {
      "epoch": 1.58,
      "learning_rate": 0.00031517094017094016,
      "loss": 0.3151,
      "step": 295
    },
    {
      "epoch": 1.6,
      "learning_rate": 0.00032051282051282057,
      "loss": 0.2323,
      "step": 300
    },
    {
      "epoch": 1.63,
      "learning_rate": 0.00032585470085470087,
      "loss": 0.1102,
      "step": 305
    },
    {
      "epoch": 1.66,
      "learning_rate": 0.00033119658119658117,
      "loss": 0.1711,
      "step": 310
    },
    {
      "epoch": 1.68,
      "learning_rate": 0.0003365384615384616,
      "loss": 0.411,
      "step": 315
    },
    {
      "epoch": 1.71,
      "learning_rate": 0.0003418803418803419,
      "loss": 0.2767,
      "step": 320
    },
    {
      "epoch": 1.74,
      "learning_rate": 0.00034722222222222224,
      "loss": 0.3315,
      "step": 325
    },
    {
      "epoch": 1.76,
      "learning_rate": 0.0003525641025641026,
      "loss": 0.368,
      "step": 330
    },
    {
      "epoch": 1.79,
      "learning_rate": 0.0003579059829059829,
      "loss": 0.0977,
      "step": 335
    },
    {
      "epoch": 1.82,
      "learning_rate": 0.00036324786324786325,
      "loss": 0.346,
      "step": 340
    },
    {
      "epoch": 1.84,
      "learning_rate": 0.0003685897435897436,
      "loss": 0.6349,
      "step": 345
    },
    {
      "epoch": 1.87,
      "learning_rate": 0.00037393162393162396,
      "loss": 0.7342,
      "step": 350
    },
    {
      "epoch": 1.9,
      "learning_rate": 0.00037927350427350426,
      "loss": 0.3546,
      "step": 355
    },
    {
      "epoch": 1.92,
      "learning_rate": 0.00038461538461538467,
      "loss": 0.1764,
      "step": 360
    },
    {
      "epoch": 1.95,
      "learning_rate": 0.00038995726495726497,
      "loss": 0.2848,
      "step": 365
    },
    {
      "epoch": 1.98,
      "learning_rate": 0.00039529914529914527,
      "loss": 0.5922,
      "step": 370
    },
    {
      "epoch": 2.0,
      "eval_accuracy": 0.8629014396456257,
      "eval_loss": 0.3205777704715729,
      "eval_runtime": 207.8751,
      "eval_samples_per_second": 21.72,
      "eval_steps_per_second": 2.718,
      "step": 374
    },
    {
      "epoch": 2.0,
      "learning_rate": 0.0004006410256410257,
      "loss": 0.4581,
      "step": 375
    },
    {
      "epoch": 2.03,
      "learning_rate": 0.000405982905982906,
      "loss": 0.3347,
      "step": 380
    },
    {
      "epoch": 2.06,
      "learning_rate": 0.00041132478632478634,
      "loss": 0.2635,
      "step": 385
    },
    {
      "epoch": 2.08,
      "learning_rate": 0.0004166666666666667,
      "loss": 0.2595,
      "step": 390
    },
    {
      "epoch": 2.11,
      "learning_rate": 0.000422008547008547,
      "loss": 0.3457,
      "step": 395
    },
    {
      "epoch": 2.14,
      "learning_rate": 0.00042735042735042735,
      "loss": 0.2144,
      "step": 400
    },
    {
      "epoch": 2.16,
      "learning_rate": 0.0004326923076923077,
      "loss": 0.3235,
      "step": 405
    },
    {
      "epoch": 2.19,
      "learning_rate": 0.00043803418803418806,
      "loss": 0.4917,
      "step": 410
    },
    {
      "epoch": 2.22,
      "learning_rate": 0.00044337606837606836,
      "loss": 0.4038,
      "step": 415
    },
    {
      "epoch": 2.24,
      "learning_rate": 0.0004487179487179487,
      "loss": 0.1941,
      "step": 420
    },
    {
      "epoch": 2.27,
      "learning_rate": 0.0004540598290598291,
      "loss": 0.2165,
      "step": 425
    },
    {
      "epoch": 2.3,
      "learning_rate": 0.0004594017094017094,
      "loss": 0.2612,
      "step": 430
    },
    {
      "epoch": 2.32,
      "learning_rate": 0.0004647435897435898,
      "loss": 0.3141,
      "step": 435
    },
    {
      "epoch": 2.35,
      "learning_rate": 0.0004700854700854701,
      "loss": 0.1971,
      "step": 440
    },
    {
      "epoch": 2.38,
      "learning_rate": 0.00047542735042735044,
      "loss": 0.3959,
      "step": 445
    },
    {
      "epoch": 2.4,
      "learning_rate": 0.0004807692307692308,
      "loss": 0.3421,
      "step": 450
    },
    {
      "epoch": 2.43,
      "learning_rate": 0.0004861111111111111,
      "loss": 0.697,
      "step": 455
    },
    {
      "epoch": 2.46,
      "learning_rate": 0.0004914529914529914,
      "loss": 0.4143,
      "step": 460
    },
    {
      "epoch": 2.48,
      "learning_rate": 0.0004967948717948718,
      "loss": 0.2158,
      "step": 465
    },
    {
      "epoch": 2.51,
      "learning_rate": 0.0004978586723768737,
      "loss": 0.307,
      "step": 470
    },
    {
      "epoch": 2.54,
      "learning_rate": 0.0004925053533190578,
      "loss": 0.3092,
      "step": 475
    },
    {
      "epoch": 2.56,
      "learning_rate": 0.000487152034261242,
      "loss": 0.2478,
      "step": 480
    },
    {
      "epoch": 2.59,
      "learning_rate": 0.00048179871520342613,
      "loss": 0.343,
      "step": 485
    },
    {
      "epoch": 2.62,
      "learning_rate": 0.0004764453961456103,
      "loss": 0.2089,
      "step": 490
    },
    {
      "epoch": 2.64,
      "learning_rate": 0.0004710920770877944,
      "loss": 0.3304,
      "step": 495
    },
    {
      "epoch": 2.67,
      "learning_rate": 0.0004657387580299786,
      "loss": 0.2251,
      "step": 500
    },
    {
      "epoch": 2.7,
      "learning_rate": 0.0004603854389721627,
      "loss": 0.6617,
      "step": 505
    },
    {
      "epoch": 2.72,
      "learning_rate": 0.0004550321199143469,
      "loss": 0.4365,
      "step": 510
    },
    {
      "epoch": 2.75,
      "learning_rate": 0.00044967880085653106,
      "loss": 0.3923,
      "step": 515
    },
    {
      "epoch": 2.78,
      "learning_rate": 0.00044432548179871526,
      "loss": 0.1877,
      "step": 520
    },
    {
      "epoch": 2.8,
      "learning_rate": 0.00043897216274089935,
      "loss": 0.2519,
      "step": 525
    },
    {
      "epoch": 2.83,
      "learning_rate": 0.0004336188436830835,
      "loss": 0.1869,
      "step": 530
    },
    {
      "epoch": 2.86,
      "learning_rate": 0.0004282655246252677,
      "loss": 0.2737,
      "step": 535
    },
    {
      "epoch": 2.88,
      "learning_rate": 0.0004229122055674518,
      "loss": 0.3389,
      "step": 540
    },
    {
      "epoch": 2.91,
      "learning_rate": 0.000417558886509636,
      "loss": 0.1682,
      "step": 545
    },
    {
      "epoch": 2.94,
      "learning_rate": 0.00041220556745182014,
      "loss": 0.1925,
      "step": 550
    },
    {
      "epoch": 2.96,
      "learning_rate": 0.0004068522483940043,
      "loss": 0.0948,
      "step": 555
    },
    {
      "epoch": 2.99,
      "learning_rate": 0.00040149892933618843,
      "loss": 0.1763,
      "step": 560
    },
    {
      "epoch": 3.0,
      "eval_accuracy": 0.9127353266888151,
      "eval_loss": 0.2446804940700531,
      "eval_runtime": 208.6202,
      "eval_samples_per_second": 21.642,
      "eval_steps_per_second": 2.708,
      "step": 561
    },
    {
      "epoch": 3.02,
      "learning_rate": 0.0003961456102783726,
      "loss": 0.2367,
      "step": 565
    },
    {
      "epoch": 3.04,
      "learning_rate": 0.0003907922912205568,
      "loss": 0.2498,
      "step": 570
    },
    {
      "epoch": 3.07,
      "learning_rate": 0.0003854389721627409,
      "loss": 0.2699,
      "step": 575
    },
    {
      "epoch": 3.1,
      "learning_rate": 0.000380085653104925,
      "loss": 0.1427,
      "step": 580
    },
    {
      "epoch": 3.12,
      "learning_rate": 0.0003747323340471092,
      "loss": 0.2793,
      "step": 585
    },
    {
      "epoch": 3.15,
      "learning_rate": 0.00036937901498929336,
      "loss": 0.1657,
      "step": 590
    },
    {
      "epoch": 3.18,
      "learning_rate": 0.0003640256959314775,
      "loss": 0.1275,
      "step": 595
    },
    {
      "epoch": 3.2,
      "learning_rate": 0.00035867237687366166,
      "loss": 0.3048,
      "step": 600
    },
    {
      "epoch": 3.23,
      "learning_rate": 0.00035331905781584586,
      "loss": 0.1886,
      "step": 605
    },
    {
      "epoch": 3.26,
      "learning_rate": 0.00034796573875803,
      "loss": 0.1595,
      "step": 610
    },
    {
      "epoch": 3.28,
      "learning_rate": 0.0003426124197002141,
      "loss": 0.2196,
      "step": 615
    },
    {
      "epoch": 3.31,
      "learning_rate": 0.0003372591006423983,
      "loss": 0.3155,
      "step": 620
    },
    {
      "epoch": 3.34,
      "learning_rate": 0.00033190578158458244,
      "loss": 0.2957,
      "step": 625
    },
    {
      "epoch": 3.36,
      "learning_rate": 0.00032655246252676664,
      "loss": 0.2555,
      "step": 630
    },
    {
      "epoch": 3.39,
      "learning_rate": 0.00032119914346895073,
      "loss": 0.2318,
      "step": 635
    },
    {
      "epoch": 3.42,
      "learning_rate": 0.0003158458244111349,
      "loss": 0.271,
      "step": 640
    },
    {
      "epoch": 3.44,
      "learning_rate": 0.0003104925053533191,
      "loss": 0.1326,
      "step": 645
    },
    {
      "epoch": 3.47,
      "learning_rate": 0.00030513918629550323,
      "loss": 0.184,
      "step": 650
    },
    {
      "epoch": 3.5,
      "learning_rate": 0.0002997858672376874,
      "loss": 0.1722,
      "step": 655
    },
    {
      "epoch": 3.52,
      "learning_rate": 0.0002944325481798715,
      "loss": 0.1703,
      "step": 660
    },
    {
      "epoch": 3.55,
      "learning_rate": 0.0002890792291220557,
      "loss": 0.1832,
      "step": 665
    },
    {
      "epoch": 3.58,
      "learning_rate": 0.0002837259100642398,
      "loss": 0.0724,
      "step": 670
    },
    {
      "epoch": 3.6,
      "learning_rate": 0.00027837259100642396,
      "loss": 0.2362,
      "step": 675
    },
    {
      "epoch": 3.63,
      "learning_rate": 0.00027301927194860816,
      "loss": 0.1697,
      "step": 680
    },
    {
      "epoch": 3.66,
      "learning_rate": 0.0002676659528907923,
      "loss": 0.2273,
      "step": 685
    },
    {
      "epoch": 3.68,
      "learning_rate": 0.00026231263383297645,
      "loss": 0.1521,
      "step": 690
    },
    {
      "epoch": 3.71,
      "learning_rate": 0.0002569593147751606,
      "loss": 0.1556,
      "step": 695
    },
    {
      "epoch": 3.74,
      "learning_rate": 0.00025160599571734475,
      "loss": 0.2266,
      "step": 700
    },
    {
      "epoch": 3.77,
      "learning_rate": 0.0002462526766595289,
      "loss": 0.1827,
      "step": 705
    },
    {
      "epoch": 3.79,
      "learning_rate": 0.00024089935760171306,
      "loss": 0.083,
      "step": 710
    },
    {
      "epoch": 3.82,
      "learning_rate": 0.0002355460385438972,
      "loss": 0.1368,
      "step": 715
    },
    {
      "epoch": 3.85,
      "learning_rate": 0.00023019271948608136,
      "loss": 0.1649,
      "step": 720
    },
    {
      "epoch": 3.87,
      "learning_rate": 0.00022483940042826553,
      "loss": 0.1999,
      "step": 725
    },
    {
      "epoch": 3.9,
      "learning_rate": 0.00021948608137044968,
      "loss": 0.147,
      "step": 730
    },
    {
      "epoch": 3.93,
      "learning_rate": 0.00021413276231263385,
      "loss": 0.1472,
      "step": 735
    },
    {
      "epoch": 3.95,
      "learning_rate": 0.000208779443254818,
      "loss": 0.1193,
      "step": 740
    },
    {
      "epoch": 3.98,
      "learning_rate": 0.00020342612419700214,
      "loss": 0.1351,
      "step": 745
    },
    {
      "epoch": 4.0,
      "eval_accuracy": 0.9563676633444075,
      "eval_loss": 0.10276087373495102,
      "eval_runtime": 207.7116,
      "eval_samples_per_second": 21.737,
      "eval_steps_per_second": 2.72,
      "step": 749
    },
    {
      "epoch": 4.01,
      "learning_rate": 0.0001980728051391863,
      "loss": 0.2576,
      "step": 750
    },
    {
      "epoch": 4.03,
      "learning_rate": 0.00019271948608137046,
      "loss": 0.1087,
      "step": 755
    },
    {
      "epoch": 4.06,
      "learning_rate": 0.0001873661670235546,
      "loss": 0.12,
      "step": 760
    },
    {
      "epoch": 4.09,
      "learning_rate": 0.00018201284796573876,
      "loss": 0.1427,
      "step": 765
    },
    {
      "epoch": 4.11,
      "learning_rate": 0.00017665952890792293,
      "loss": 0.1297,
      "step": 770
    },
    {
      "epoch": 4.14,
      "learning_rate": 0.00017130620985010705,
      "loss": 0.0887,
      "step": 775
    },
    {
      "epoch": 4.17,
      "learning_rate": 0.00016595289079229122,
      "loss": 0.0872,
      "step": 780
    },
    {
      "epoch": 4.19,
      "learning_rate": 0.00016059957173447537,
      "loss": 0.1259,
      "step": 785
    },
    {
      "epoch": 4.22,
      "learning_rate": 0.00015524625267665954,
      "loss": 0.1486,
      "step": 790
    },
    {
      "epoch": 4.25,
      "learning_rate": 0.0001498929336188437,
      "loss": 0.1123,
      "step": 795
    },
    {
      "epoch": 4.27,
      "learning_rate": 0.00014453961456102786,
      "loss": 0.1699,
      "step": 800
    },
    {
      "epoch": 4.3,
      "learning_rate": 0.00013918629550321198,
      "loss": 0.0964,
      "step": 805
    },
    {
      "epoch": 4.33,
      "learning_rate": 0.00013383297644539615,
      "loss": 0.1556,
      "step": 810
    },
    {
      "epoch": 4.35,
      "learning_rate": 0.0001284796573875803,
      "loss": 0.1347,
      "step": 815
    },
    {
      "epoch": 4.38,
      "learning_rate": 0.00012312633832976445,
      "loss": 0.1876,
      "step": 820
    },
    {
      "epoch": 4.41,
      "learning_rate": 0.0001177730192719486,
      "loss": 0.0863,
      "step": 825
    },
    {
      "epoch": 4.43,
      "learning_rate": 0.00011241970021413277,
      "loss": 0.1614,
      "step": 830
    },
    {
      "epoch": 4.46,
      "learning_rate": 0.00010706638115631693,
      "loss": 0.1407,
      "step": 835
    },
    {
      "epoch": 4.49,
      "learning_rate": 0.00010171306209850107,
      "loss": 0.0918,
      "step": 840
    },
    {
      "epoch": 4.51,
      "learning_rate": 9.635974304068523e-05,
      "loss": 0.0966,
      "step": 845
    },
    {
      "epoch": 4.54,
      "learning_rate": 9.100642398286938e-05,
      "loss": 0.0563,
      "step": 850
    },
    {
      "epoch": 4.57,
      "learning_rate": 8.565310492505352e-05,
      "loss": 0.0795,
      "step": 855
    },
    {
      "epoch": 4.59,
      "learning_rate": 8.029978586723768e-05,
      "loss": 0.0409,
      "step": 860
    },
    {
      "epoch": 4.62,
      "learning_rate": 7.494646680942184e-05,
      "loss": 0.0707,
      "step": 865
    },
    {
      "epoch": 4.65,
      "learning_rate": 6.959314775160599e-05,
      "loss": 0.1622,
      "step": 870
    },
    {
      "epoch": 4.67,
      "learning_rate": 6.423982869379015e-05,
      "loss": 0.0814,
      "step": 875
    },
    {
      "epoch": 4.7,
      "learning_rate": 5.88865096359743e-05,
      "loss": 0.1475,
      "step": 880
    },
    {
      "epoch": 4.73,
      "learning_rate": 5.353319057815846e-05,
      "loss": 0.129,
      "step": 885
    },
    {
      "epoch": 4.75,
      "learning_rate": 4.8179871520342616e-05,
      "loss": 0.1013,
      "step": 890
    },
    {
      "epoch": 4.78,
      "learning_rate": 4.282655246252676e-05,
      "loss": 0.0852,
      "step": 895
    },
    {
      "epoch": 4.81,
      "learning_rate": 3.747323340471092e-05,
      "loss": 0.0799,
      "step": 900
    },
    {
      "epoch": 4.83,
      "learning_rate": 3.2119914346895075e-05,
      "loss": 0.1067,
      "step": 905
    },
    {
      "epoch": 4.86,
      "learning_rate": 2.676659528907923e-05,
      "loss": 0.0713,
      "step": 910
    },
    {
      "epoch": 4.89,
      "learning_rate": 2.141327623126338e-05,
      "loss": 0.0497,
      "step": 915
    },
    {
      "epoch": 4.91,
      "learning_rate": 1.6059957173447537e-05,
      "loss": 0.0876,
      "step": 920
    },
    {
      "epoch": 4.94,
      "learning_rate": 1.070663811563169e-05,
      "loss": 0.0796,
      "step": 925
    },
    {
      "epoch": 4.97,
      "learning_rate": 5.353319057815845e-06,
      "loss": 0.0755,
      "step": 930
    },
    {
      "epoch": 4.99,
      "learning_rate": 0.0,
      "loss": 0.142,
      "step": 935
    },
    {
      "epoch": 4.99,
      "eval_accuracy": 0.9869324473975637,
      "eval_loss": 0.04178118333220482,
      "eval_runtime": 207.692,
      "eval_samples_per_second": 21.739,
      "eval_steps_per_second": 2.72,
      "step": 935
    },
    {
      "epoch": 4.99,
      "step": 935,
      "total_flos": 6.883415802275955e+18,
      "train_loss": 0.24478418331413984,
      "train_runtime": 10756.8608,
      "train_samples_per_second": 2.782,
      "train_steps_per_second": 0.087
    }
  ],
  "max_steps": 935,
  "num_train_epochs": 5,
  "total_flos": 6.883415802275955e+18,
  "trial_name": null,
  "trial_params": null
}