{
  "best_metric": 0.5952649379932357,
  "best_model_checkpoint": "swinv2-large-patch4-window12to16-192to256-22kto1k-ft-head-finetuned-galaxy10-decals/checkpoint-1750",
  "epoch": 29.76,
  "eval_steps": 500,
  "global_step": 1860,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.16,
      "learning_rate": 5.376344086021506e-06,
      "loss": 2.4183,
      "step": 10
    },
    {
      "epoch": 0.32,
      "learning_rate": 1.0752688172043012e-05,
      "loss": 2.3949,
      "step": 20
    },
    {
      "epoch": 0.48,
      "learning_rate": 1.6129032258064517e-05,
      "loss": 2.3777,
      "step": 30
    },
    {
      "epoch": 0.64,
      "learning_rate": 2.1505376344086024e-05,
      "loss": 2.335,
      "step": 40
    },
    {
      "epoch": 0.8,
      "learning_rate": 2.6881720430107527e-05,
      "loss": 2.2929,
      "step": 50
    },
    {
      "epoch": 0.96,
      "learning_rate": 3.2258064516129034e-05,
      "loss": 2.2152,
      "step": 60
    },
    {
      "epoch": 0.99,
      "eval_accuracy": 0.20349492671927846,
      "eval_f1": 0.15105203129445105,
      "eval_loss": 2.188288927078247,
      "eval_precision": 0.14895878509992708,
      "eval_recall": 0.20349492671927846,
      "eval_runtime": 22.1815,
      "eval_samples_per_second": 79.976,
      "eval_steps_per_second": 1.262,
      "step": 62
    },
    {
      "epoch": 1.12,
      "learning_rate": 3.763440860215054e-05,
      "loss": 2.1913,
      "step": 70
    },
    {
      "epoch": 1.28,
      "learning_rate": 4.301075268817205e-05,
      "loss": 2.1422,
      "step": 80
    },
    {
      "epoch": 1.44,
      "learning_rate": 4.8387096774193554e-05,
      "loss": 2.0878,
      "step": 90
    },
    {
      "epoch": 1.6,
      "learning_rate": 5.3763440860215054e-05,
      "loss": 2.0411,
      "step": 100
    },
    {
      "epoch": 1.76,
      "learning_rate": 5.913978494623657e-05,
      "loss": 1.9976,
      "step": 110
    },
    {
      "epoch": 1.92,
      "learning_rate": 6.451612903225807e-05,
      "loss": 1.9434,
      "step": 120
    },
    {
      "epoch": 2.0,
      "eval_accuracy": 0.3506200676437429,
      "eval_f1": 0.272465935568218,
      "eval_loss": 1.9051553010940552,
      "eval_precision": 0.39556561793778316,
      "eval_recall": 0.3506200676437429,
      "eval_runtime": 22.0737,
      "eval_samples_per_second": 80.367,
      "eval_steps_per_second": 1.268,
      "step": 125
    },
    {
      "epoch": 2.08,
      "learning_rate": 6.989247311827958e-05,
      "loss": 1.8905,
      "step": 130
    },
    {
      "epoch": 2.24,
      "learning_rate": 7.526881720430108e-05,
      "loss": 1.8585,
      "step": 140
    },
    {
      "epoch": 2.4,
      "learning_rate": 8.064516129032258e-05,
      "loss": 1.814,
      "step": 150
    },
    {
      "epoch": 2.56,
      "learning_rate": 8.60215053763441e-05,
      "loss": 1.8007,
      "step": 160
    },
    {
      "epoch": 2.72,
      "learning_rate": 9.13978494623656e-05,
      "loss": 1.7578,
      "step": 170
    },
    {
      "epoch": 2.88,
      "learning_rate": 9.677419354838711e-05,
      "loss": 1.7295,
      "step": 180
    },
    {
      "epoch": 2.99,
      "eval_accuracy": 0.4368658399098083,
      "eval_f1": 0.3915006667744191,
      "eval_loss": 1.6789493560791016,
      "eval_precision": 0.46298297663493393,
      "eval_recall": 0.4368658399098083,
      "eval_runtime": 22.0192,
      "eval_samples_per_second": 80.566,
      "eval_steps_per_second": 1.272,
      "step": 187
    },
    {
      "epoch": 3.04,
      "learning_rate": 9.97610513739546e-05,
      "loss": 1.7217,
      "step": 190
    },
    {
      "epoch": 3.2,
      "learning_rate": 9.916367980884111e-05,
      "loss": 1.6519,
      "step": 200
    },
    {
      "epoch": 3.36,
      "learning_rate": 9.85663082437276e-05,
      "loss": 1.6417,
      "step": 210
    },
    {
      "epoch": 3.52,
      "learning_rate": 9.79689366786141e-05,
      "loss": 1.6192,
      "step": 220
    },
    {
      "epoch": 3.68,
      "learning_rate": 9.73715651135006e-05,
      "loss": 1.6046,
      "step": 230
    },
    {
      "epoch": 3.84,
      "learning_rate": 9.677419354838711e-05,
      "loss": 1.5931,
      "step": 240
    },
    {
      "epoch": 4.0,
      "learning_rate": 9.61768219832736e-05,
      "loss": 1.5541,
      "step": 250
    },
    {
      "epoch": 4.0,
      "eval_accuracy": 0.47576099210823,
      "eval_f1": 0.4335867277644615,
      "eval_loss": 1.5338377952575684,
      "eval_precision": 0.509541084219624,
      "eval_recall": 0.47576099210823,
      "eval_runtime": 22.1469,
      "eval_samples_per_second": 80.102,
      "eval_steps_per_second": 1.264,
      "step": 250
    },
    {
      "epoch": 4.16,
      "learning_rate": 9.55794504181601e-05,
      "loss": 1.5557,
      "step": 260
    },
    {
      "epoch": 4.32,
      "learning_rate": 9.49820788530466e-05,
      "loss": 1.5259,
      "step": 270
    },
    {
      "epoch": 4.48,
      "learning_rate": 9.438470728793309e-05,
      "loss": 1.5044,
      "step": 280
    },
    {
      "epoch": 4.64,
      "learning_rate": 9.378733572281961e-05,
      "loss": 1.5017,
      "step": 290
    },
    {
      "epoch": 4.8,
      "learning_rate": 9.31899641577061e-05,
      "loss": 1.4979,
      "step": 300
    },
    {
      "epoch": 4.96,
      "learning_rate": 9.25925925925926e-05,
      "loss": 1.4558,
      "step": 310
    },
    {
      "epoch": 4.99,
      "eval_accuracy": 0.520293122886133,
      "eval_f1": 0.48596376905849764,
      "eval_loss": 1.4501919746398926,
      "eval_precision": 0.5414266437447433,
      "eval_recall": 0.520293122886133,
      "eval_runtime": 22.0839,
      "eval_samples_per_second": 80.33,
      "eval_steps_per_second": 1.268,
      "step": 312
    },
    {
      "epoch": 5.12,
      "learning_rate": 9.199522102747909e-05,
      "loss": 1.4861,
      "step": 320
    },
    {
      "epoch": 5.28,
      "learning_rate": 9.13978494623656e-05,
      "loss": 1.4779,
      "step": 330
    },
    {
      "epoch": 5.44,
      "learning_rate": 9.080047789725208e-05,
      "loss": 1.4526,
      "step": 340
    },
    {
      "epoch": 5.6,
      "learning_rate": 9.02031063321386e-05,
      "loss": 1.4667,
      "step": 350
    },
    {
      "epoch": 5.76,
      "learning_rate": 8.960573476702509e-05,
      "loss": 1.4395,
      "step": 360
    },
    {
      "epoch": 5.92,
      "learning_rate": 8.900836320191159e-05,
      "loss": 1.42,
      "step": 370
    },
    {
      "epoch": 6.0,
      "eval_accuracy": 0.520293122886133,
      "eval_f1": 0.4892009598786175,
      "eval_loss": 1.399051308631897,
      "eval_precision": 0.5529206104546609,
      "eval_recall": 0.520293122886133,
      "eval_runtime": 22.0309,
      "eval_samples_per_second": 80.523,
      "eval_steps_per_second": 1.271,
      "step": 375
    },
    {
      "epoch": 6.08,
      "learning_rate": 8.84109916367981e-05,
      "loss": 1.4285,
      "step": 380
    },
    {
      "epoch": 6.24,
      "learning_rate": 8.781362007168459e-05,
      "loss": 1.4283,
      "step": 390
    },
    {
      "epoch": 6.4,
      "learning_rate": 8.72162485065711e-05,
      "loss": 1.3969,
      "step": 400
    },
    {
      "epoch": 6.56,
      "learning_rate": 8.661887694145759e-05,
      "loss": 1.4135,
      "step": 410
    },
    {
      "epoch": 6.72,
      "learning_rate": 8.60215053763441e-05,
      "loss": 1.3878,
      "step": 420
    },
    {
      "epoch": 6.88,
      "learning_rate": 8.542413381123058e-05,
      "loss": 1.3806,
      "step": 430
    },
    {
      "epoch": 6.99,
      "eval_accuracy": 0.5501691093573844,
      "eval_f1": 0.5227011346941011,
      "eval_loss": 1.3529337644577026,
      "eval_precision": 0.5732264535553914,
      "eval_recall": 0.5501691093573844,
      "eval_runtime": 22.1773,
      "eval_samples_per_second": 79.992,
      "eval_steps_per_second": 1.263,
      "step": 437
    },
    {
      "epoch": 7.04,
      "learning_rate": 8.482676224611709e-05,
      "loss": 1.4184,
      "step": 440
    },
    {
      "epoch": 7.2,
      "learning_rate": 8.422939068100359e-05,
      "loss": 1.4169,
      "step": 450
    },
    {
      "epoch": 7.36,
      "learning_rate": 8.363201911589009e-05,
      "loss": 1.3882,
      "step": 460
    },
    {
      "epoch": 7.52,
      "learning_rate": 8.30346475507766e-05,
      "loss": 1.3869,
      "step": 470
    },
    {
      "epoch": 7.68,
      "learning_rate": 8.243727598566309e-05,
      "loss": 1.3499,
      "step": 480
    },
    {
      "epoch": 7.84,
      "learning_rate": 8.183990442054959e-05,
      "loss": 1.3531,
      "step": 490
    },
    {
      "epoch": 8.0,
      "learning_rate": 8.124253285543608e-05,
      "loss": 1.3541,
      "step": 500
    },
    {
      "epoch": 8.0,
      "eval_accuracy": 0.560315670800451,
      "eval_f1": 0.532522788067071,
      "eval_loss": 1.3217679262161255,
      "eval_precision": 0.5934036230328783,
      "eval_recall": 0.560315670800451,
      "eval_runtime": 22.0874,
      "eval_samples_per_second": 80.317,
      "eval_steps_per_second": 1.268,
      "step": 500
    },
    {
      "epoch": 8.16,
      "learning_rate": 8.064516129032258e-05,
      "loss": 1.3568,
      "step": 510
    },
    {
      "epoch": 8.32,
      "learning_rate": 8.004778972520908e-05,
      "loss": 1.3505,
      "step": 520
    },
    {
      "epoch": 8.48,
      "learning_rate": 7.945041816009559e-05,
      "loss": 1.397,
      "step": 530
    },
    {
      "epoch": 8.64,
      "learning_rate": 7.885304659498209e-05,
      "loss": 1.3614,
      "step": 540
    },
    {
      "epoch": 8.8,
      "learning_rate": 7.825567502986858e-05,
      "loss": 1.3543,
      "step": 550
    },
    {
      "epoch": 8.96,
      "learning_rate": 7.765830346475508e-05,
      "loss": 1.337,
      "step": 560
    },
    {
      "epoch": 8.99,
      "eval_accuracy": 0.5597519729425028,
      "eval_f1": 0.5304260590298405,
      "eval_loss": 1.3014049530029297,
      "eval_precision": 0.6007885455628412,
      "eval_recall": 0.5597519729425028,
      "eval_runtime": 22.0361,
      "eval_samples_per_second": 80.504,
      "eval_steps_per_second": 1.271,
      "step": 562
    },
    {
      "epoch": 9.12,
      "learning_rate": 7.706093189964157e-05,
      "loss": 1.359,
      "step": 570
    },
    {
      "epoch": 9.28,
      "learning_rate": 7.646356033452809e-05,
      "loss": 1.3222,
      "step": 580
    },
    {
      "epoch": 9.44,
      "learning_rate": 7.586618876941458e-05,
      "loss": 1.3325,
      "step": 590
    },
    {
      "epoch": 9.6,
      "learning_rate": 7.526881720430108e-05,
      "loss": 1.3524,
      "step": 600
    },
    {
      "epoch": 9.76,
      "learning_rate": 7.467144563918757e-05,
      "loss": 1.3077,
      "step": 610
    },
    {
      "epoch": 9.92,
      "learning_rate": 7.407407407407407e-05,
      "loss": 1.3164,
      "step": 620
    },
    {
      "epoch": 10.0,
      "eval_accuracy": 0.5552423900789177,
      "eval_f1": 0.5269514020319623,
      "eval_loss": 1.285463571548462,
      "eval_precision": 0.5617951310681798,
      "eval_recall": 0.5552423900789177,
      "eval_runtime": 22.0709,
      "eval_samples_per_second": 80.377,
      "eval_steps_per_second": 1.269,
      "step": 625
    },
    {
      "epoch": 10.08,
      "learning_rate": 7.347670250896058e-05,
      "loss": 1.336,
      "step": 630
    },
    {
      "epoch": 10.24,
      "learning_rate": 7.287933094384708e-05,
      "loss": 1.3231,
      "step": 640
    },
    {
      "epoch": 10.4,
      "learning_rate": 7.228195937873358e-05,
      "loss": 1.3111,
      "step": 650
    },
    {
      "epoch": 10.56,
      "learning_rate": 7.168458781362007e-05,
      "loss": 1.3081,
      "step": 660
    },
    {
      "epoch": 10.72,
      "learning_rate": 7.108721624850657e-05,
      "loss": 1.2971,
      "step": 670
    },
    {
      "epoch": 10.88,
      "learning_rate": 7.048984468339306e-05,
      "loss": 1.2904,
      "step": 680
    },
    {
      "epoch": 10.99,
      "eval_accuracy": 0.5715896279594137,
      "eval_f1": 0.544321340926892,
      "eval_loss": 1.2624871730804443,
      "eval_precision": 0.6199672961362004,
      "eval_recall": 0.5715896279594137,
      "eval_runtime": 22.0129,
      "eval_samples_per_second": 80.589,
      "eval_steps_per_second": 1.272,
      "step": 687
    },
    {
      "epoch": 11.04,
      "learning_rate": 6.989247311827958e-05,
      "loss": 1.3266,
      "step": 690
    },
    {
      "epoch": 11.2,
      "learning_rate": 6.929510155316607e-05,
      "loss": 1.3018,
      "step": 700
    },
    {
      "epoch": 11.36,
      "learning_rate": 6.869772998805257e-05,
      "loss": 1.2864,
      "step": 710
    },
    {
      "epoch": 11.52,
      "learning_rate": 6.810035842293908e-05,
      "loss": 1.3119,
      "step": 720
    },
    {
      "epoch": 11.68,
      "learning_rate": 6.750298685782557e-05,
      "loss": 1.2891,
      "step": 730
    },
    {
      "epoch": 11.84,
      "learning_rate": 6.690561529271207e-05,
      "loss": 1.2815,
      "step": 740
    },
    {
      "epoch": 12.0,
      "learning_rate": 6.630824372759857e-05,
      "loss": 1.2873,
      "step": 750
    },
    {
      "epoch": 12.0,
      "eval_accuracy": 0.5698985343855694,
      "eval_f1": 0.5446306363255216,
      "eval_loss": 1.248738169670105,
      "eval_precision": 0.5943470885639225,
      "eval_recall": 0.5698985343855694,
      "eval_runtime": 21.9956,
      "eval_samples_per_second": 80.653,
      "eval_steps_per_second": 1.273,
      "step": 750
    },
    {
      "epoch": 12.16,
      "learning_rate": 6.571087216248507e-05,
      "loss": 1.2642,
      "step": 760
    },
    {
      "epoch": 12.32,
      "learning_rate": 6.511350059737156e-05,
      "loss": 1.2815,
      "step": 770
    },
    {
      "epoch": 12.48,
      "learning_rate": 6.451612903225807e-05,
      "loss": 1.2987,
      "step": 780
    },
    {
      "epoch": 12.64,
      "learning_rate": 6.391875746714456e-05,
      "loss": 1.2964,
      "step": 790
    },
    {
      "epoch": 12.8,
      "learning_rate": 6.332138590203107e-05,
      "loss": 1.2946,
      "step": 800
    },
    {
      "epoch": 12.96,
      "learning_rate": 6.272401433691756e-05,
      "loss": 1.2911,
      "step": 810
    },
    {
      "epoch": 12.99,
      "eval_accuracy": 0.5772266065388951,
      "eval_f1": 0.5531271982911073,
      "eval_loss": 1.2366129159927368,
      "eval_precision": 0.6023489690717835,
      "eval_recall": 0.5772266065388951,
      "eval_runtime": 22.1699,
      "eval_samples_per_second": 80.019,
      "eval_steps_per_second": 1.263,
      "step": 812
    },
    {
      "epoch": 13.12,
      "learning_rate": 6.212664277180407e-05,
      "loss": 1.2581,
      "step": 820
    },
    {
      "epoch": 13.28,
      "learning_rate": 6.152927120669057e-05,
      "loss": 1.2737,
      "step": 830
    },
    {
      "epoch": 13.44,
      "learning_rate": 6.093189964157706e-05,
      "loss": 1.2834,
      "step": 840
    },
    {
      "epoch": 13.6,
      "learning_rate": 6.033452807646356e-05,
      "loss": 1.2522,
      "step": 850
    },
    {
      "epoch": 13.76,
      "learning_rate": 5.9737156511350064e-05,
      "loss": 1.2698,
      "step": 860
    },
    {
      "epoch": 13.92,
      "learning_rate": 5.913978494623657e-05,
      "loss": 1.2723,
      "step": 870
    },
    {
      "epoch": 14.0,
      "eval_accuracy": 0.5817361894024803,
      "eval_f1": 0.55938608951765,
      "eval_loss": 1.2241930961608887,
      "eval_precision": 0.5945742291844911,
      "eval_recall": 0.5817361894024803,
      "eval_runtime": 21.9188,
      "eval_samples_per_second": 80.935,
      "eval_steps_per_second": 1.277,
      "step": 875
    },
    {
      "epoch": 14.08,
      "learning_rate": 5.8542413381123063e-05,
      "loss": 1.2748,
      "step": 880
    },
    {
      "epoch": 14.24,
      "learning_rate": 5.794504181600956e-05,
      "loss": 1.2495,
      "step": 890
    },
    {
      "epoch": 14.4,
      "learning_rate": 5.7347670250896056e-05,
      "loss": 1.2677,
      "step": 900
    },
    {
      "epoch": 14.56,
      "learning_rate": 5.675029868578255e-05,
      "loss": 1.265,
      "step": 910
    },
    {
      "epoch": 14.72,
      "learning_rate": 5.615292712066906e-05,
      "loss": 1.2726,
      "step": 920
    },
    {
      "epoch": 14.88,
      "learning_rate": 5.555555555555556e-05,
      "loss": 1.2527,
      "step": 930
    },
    {
      "epoch": 14.99,
      "eval_accuracy": 0.5822998872604284,
      "eval_f1": 0.5601846765224702,
      "eval_loss": 1.2167905569076538,
      "eval_precision": 0.5957646682172907,
      "eval_recall": 0.5822998872604284,
      "eval_runtime": 22.0356,
      "eval_samples_per_second": 80.506,
      "eval_steps_per_second": 1.271,
      "step": 937
    },
    {
      "epoch": 15.04,
      "learning_rate": 5.495818399044206e-05,
      "loss": 1.2631,
      "step": 940
    },
    {
      "epoch": 15.2,
      "learning_rate": 5.436081242532856e-05,
      "loss": 1.2596,
      "step": 950
    },
    {
      "epoch": 15.36,
      "learning_rate": 5.3763440860215054e-05,
      "loss": 1.257,
      "step": 960
    },
    {
      "epoch": 15.52,
      "learning_rate": 5.316606929510155e-05,
      "loss": 1.2618,
      "step": 970
    },
    {
      "epoch": 15.68,
      "learning_rate": 5.256869772998806e-05,
      "loss": 1.2497,
      "step": 980
    },
    {
      "epoch": 15.84,
      "learning_rate": 5.1971326164874556e-05,
      "loss": 1.2499,
      "step": 990
    },
    {
      "epoch": 16.0,
      "learning_rate": 5.137395459976105e-05,
      "loss": 1.2692,
      "step": 1000
    },
    {
      "epoch": 16.0,
      "eval_accuracy": 0.5856820744081173,
      "eval_f1": 0.5625146496179491,
      "eval_loss": 1.2087658643722534,
      "eval_precision": 0.6014714549054646,
      "eval_recall": 0.5856820744081173,
      "eval_runtime": 22.0433,
      "eval_samples_per_second": 80.478,
      "eval_steps_per_second": 1.27,
      "step": 1000
    },
    {
      "epoch": 16.16,
      "learning_rate": 5.077658303464755e-05,
      "loss": 1.2429,
      "step": 1010
    },
    {
      "epoch": 16.32,
      "learning_rate": 5.017921146953405e-05,
      "loss": 1.2498,
      "step": 1020
    },
    {
      "epoch": 16.48,
      "learning_rate": 4.9581839904420555e-05,
      "loss": 1.2689,
      "step": 1030
    },
    {
      "epoch": 16.64,
      "learning_rate": 4.898446833930705e-05,
      "loss": 1.2683,
      "step": 1040
    },
    {
      "epoch": 16.8,
      "learning_rate": 4.8387096774193554e-05,
      "loss": 1.2617,
      "step": 1050
    },
    {
      "epoch": 16.96,
      "learning_rate": 4.778972520908005e-05,
      "loss": 1.2279,
      "step": 1060
    },
    {
      "epoch": 16.99,
      "eval_accuracy": 0.5851183765501691,
      "eval_f1": 0.5622039743774847,
      "eval_loss": 1.203583836555481,
      "eval_precision": 0.60014103604046,
      "eval_recall": 0.5851183765501691,
      "eval_runtime": 22.1622,
      "eval_samples_per_second": 80.046,
      "eval_steps_per_second": 1.263,
      "step": 1062
    },
    {
      "epoch": 17.12,
      "learning_rate": 4.7192353643966546e-05,
      "loss": 1.217,
      "step": 1070
    },
    {
      "epoch": 17.28,
      "learning_rate": 4.659498207885305e-05,
      "loss": 1.2531,
      "step": 1080
    },
    {
      "epoch": 17.44,
      "learning_rate": 4.5997610513739546e-05,
      "loss": 1.2634,
      "step": 1090
    },
    {
      "epoch": 17.6,
      "learning_rate": 4.540023894862604e-05,
      "loss": 1.2465,
      "step": 1100
    },
    {
      "epoch": 17.76,
      "learning_rate": 4.4802867383512545e-05,
      "loss": 1.2665,
      "step": 1110
    },
    {
      "epoch": 17.92,
      "learning_rate": 4.420549581839905e-05,
      "loss": 1.2539,
      "step": 1120
    },
    {
      "epoch": 18.0,
      "eval_accuracy": 0.5822998872604284,
      "eval_f1": 0.5591138810402552,
      "eval_loss": 1.1966551542282104,
      "eval_precision": 0.6010933850255593,
      "eval_recall": 0.5822998872604284,
      "eval_runtime": 22.0507,
      "eval_samples_per_second": 80.451,
      "eval_steps_per_second": 1.27,
      "step": 1125
    },
    {
      "epoch": 18.08,
      "learning_rate": 4.360812425328555e-05,
      "loss": 1.2355,
      "step": 1130
    },
    {
      "epoch": 18.24,
      "learning_rate": 4.301075268817205e-05,
      "loss": 1.2481,
      "step": 1140
    },
    {
      "epoch": 18.4,
      "learning_rate": 4.241338112305854e-05,
      "loss": 1.2128,
      "step": 1150
    },
    {
      "epoch": 18.56,
      "learning_rate": 4.1816009557945046e-05,
      "loss": 1.2455,
      "step": 1160
    },
    {
      "epoch": 18.72,
      "learning_rate": 4.121863799283154e-05,
      "loss": 1.2491,
      "step": 1170
    },
    {
      "epoch": 18.88,
      "learning_rate": 4.062126642771804e-05,
      "loss": 1.2341,
      "step": 1180
    },
    {
      "epoch": 18.99,
      "eval_accuracy": 0.5907553551296505,
      "eval_f1": 0.5665315520801317,
      "eval_loss": 1.187435269355774,
      "eval_precision": 0.6124355427768795,
      "eval_recall": 0.5907553551296505,
      "eval_runtime": 22.0769,
      "eval_samples_per_second": 80.356,
      "eval_steps_per_second": 1.268,
      "step": 1187
    },
    {
      "epoch": 19.04,
      "learning_rate": 4.002389486260454e-05,
      "loss": 1.2278,
      "step": 1190
    },
    {
      "epoch": 19.2,
      "learning_rate": 3.9426523297491045e-05,
      "loss": 1.2442,
      "step": 1200
    },
    {
      "epoch": 19.36,
      "learning_rate": 3.882915173237754e-05,
      "loss": 1.2192,
      "step": 1210
    },
    {
      "epoch": 19.52,
      "learning_rate": 3.8231780167264044e-05,
      "loss": 1.2532,
      "step": 1220
    },
    {
      "epoch": 19.68,
      "learning_rate": 3.763440860215054e-05,
      "loss": 1.2309,
      "step": 1230
    },
    {
      "epoch": 19.84,
      "learning_rate": 3.7037037037037037e-05,
      "loss": 1.2555,
      "step": 1240
    },
    {
      "epoch": 20.0,
      "learning_rate": 3.643966547192354e-05,
      "loss": 1.2475,
      "step": 1250
    },
    {
      "epoch": 20.0,
      "eval_accuracy": 0.584554678692221,
      "eval_f1": 0.5598437529375522,
      "eval_loss": 1.1870439052581787,
      "eval_precision": 0.6019233382358613,
      "eval_recall": 0.584554678692221,
      "eval_runtime": 21.6957,
      "eval_samples_per_second": 81.767,
      "eval_steps_per_second": 1.291,
      "step": 1250
    },
    {
      "epoch": 20.16,
      "learning_rate": 3.5842293906810036e-05,
      "loss": 1.2521,
      "step": 1260
    },
    {
      "epoch": 20.32,
      "learning_rate": 3.524492234169653e-05,
      "loss": 1.2373,
      "step": 1270
    },
    {
      "epoch": 20.48,
      "learning_rate": 3.4647550776583035e-05,
      "loss": 1.2188,
      "step": 1280
    },
    {
      "epoch": 20.64,
      "learning_rate": 3.405017921146954e-05,
      "loss": 1.2398,
      "step": 1290
    },
    {
      "epoch": 20.8,
      "learning_rate": 3.3452807646356034e-05,
      "loss": 1.2405,
      "step": 1300
    },
    {
      "epoch": 20.96,
      "learning_rate": 3.285543608124254e-05,
      "loss": 1.2009,
      "step": 1310
    },
    {
      "epoch": 20.99,
      "eval_accuracy": 0.593010146561443,
      "eval_f1": 0.5691157408882564,
      "eval_loss": 1.1792354583740234,
      "eval_precision": 0.6069905496006659,
      "eval_recall": 0.593010146561443,
      "eval_runtime": 21.918,
      "eval_samples_per_second": 80.938,
      "eval_steps_per_second": 1.277,
      "step": 1312
    },
    {
      "epoch": 21.12,
      "learning_rate": 3.2258064516129034e-05,
      "loss": 1.2068,
      "step": 1320
    },
    {
      "epoch": 21.28,
      "learning_rate": 3.1660692951015537e-05,
      "loss": 1.2272,
      "step": 1330
    },
    {
      "epoch": 21.44,
      "learning_rate": 3.106332138590203e-05,
      "loss": 1.2156,
      "step": 1340
    },
    {
      "epoch": 21.6,
      "learning_rate": 3.046594982078853e-05,
      "loss": 1.2154,
      "step": 1350
    },
    {
      "epoch": 21.76,
      "learning_rate": 2.9868578255675032e-05,
      "loss": 1.214,
      "step": 1360
    },
    {
      "epoch": 21.92,
      "learning_rate": 2.9271206690561532e-05,
      "loss": 1.2515,
      "step": 1370
    },
    {
      "epoch": 22.0,
      "eval_accuracy": 0.5918827508455468,
      "eval_f1": 0.5678475976802037,
      "eval_loss": 1.1771893501281738,
      "eval_precision": 0.606224629917707,
      "eval_recall": 0.5918827508455468,
      "eval_runtime": 21.8417,
      "eval_samples_per_second": 81.221,
      "eval_steps_per_second": 1.282,
      "step": 1375
    },
    {
      "epoch": 22.08,
      "learning_rate": 2.8673835125448028e-05,
      "loss": 1.2501,
      "step": 1380
    },
    {
      "epoch": 22.24,
      "learning_rate": 2.807646356033453e-05,
      "loss": 1.2147,
      "step": 1390
    },
    {
      "epoch": 22.4,
      "learning_rate": 2.747909199522103e-05,
      "loss": 1.184,
      "step": 1400
    },
    {
      "epoch": 22.56,
      "learning_rate": 2.6881720430107527e-05,
      "loss": 1.2386,
      "step": 1410
    },
    {
      "epoch": 22.72,
      "learning_rate": 2.628434886499403e-05,
      "loss": 1.2336,
      "step": 1420
    },
    {
      "epoch": 22.88,
      "learning_rate": 2.5686977299880526e-05,
      "loss": 1.2361,
      "step": 1430
    },
    {
      "epoch": 22.99,
      "eval_accuracy": 0.5918827508455468,
      "eval_f1": 0.5680339449025893,
      "eval_loss": 1.1749292612075806,
      "eval_precision": 0.6079590653989706,
      "eval_recall": 0.5918827508455468,
      "eval_runtime": 21.9917,
      "eval_samples_per_second": 80.667,
      "eval_steps_per_second": 1.273,
      "step": 1437
    },
    {
      "epoch": 23.04,
      "learning_rate": 2.5089605734767026e-05,
      "loss": 1.2493,
      "step": 1440
    },
    {
      "epoch": 23.2,
      "learning_rate": 2.4492234169653525e-05,
      "loss": 1.2109,
      "step": 1450
    },
    {
      "epoch": 23.36,
      "learning_rate": 2.3894862604540025e-05,
      "loss": 1.2227,
      "step": 1460
    },
    {
      "epoch": 23.52,
      "learning_rate": 2.3297491039426525e-05,
      "loss": 1.2163,
      "step": 1470
    },
    {
      "epoch": 23.68,
      "learning_rate": 2.270011947431302e-05,
      "loss": 1.2372,
      "step": 1480
    },
    {
      "epoch": 23.84,
      "learning_rate": 2.2102747909199524e-05,
      "loss": 1.1965,
      "step": 1490
    },
    {
      "epoch": 24.0,
      "learning_rate": 2.1505376344086024e-05,
      "loss": 1.2366,
      "step": 1500
    },
    {
      "epoch": 24.0,
      "eval_accuracy": 0.5924464487034949,
      "eval_f1": 0.5690711817132577,
      "eval_loss": 1.1708468198776245,
      "eval_precision": 0.6047825042790245,
      "eval_recall": 0.5924464487034949,
      "eval_runtime": 21.8673,
      "eval_samples_per_second": 81.126,
      "eval_steps_per_second": 1.28,
      "step": 1500
    },
    {
      "epoch": 24.16,
      "learning_rate": 2.0908004778972523e-05,
      "loss": 1.2444,
      "step": 1510
    },
    {
      "epoch": 24.32,
      "learning_rate": 2.031063321385902e-05,
      "loss": 1.2116,
      "step": 1520
    },
    {
      "epoch": 24.48,
      "learning_rate": 1.9713261648745522e-05,
      "loss": 1.2061,
      "step": 1530
    },
    {
      "epoch": 24.64,
      "learning_rate": 1.9115890083632022e-05,
      "loss": 1.2072,
      "step": 1540
    },
    {
      "epoch": 24.8,
      "learning_rate": 1.8518518518518518e-05,
      "loss": 1.2144,
      "step": 1550
    },
    {
      "epoch": 24.96,
      "learning_rate": 1.7921146953405018e-05,
      "loss": 1.2442,
      "step": 1560
    },
    {
      "epoch": 24.99,
      "eval_accuracy": 0.5913190529875987,
      "eval_f1": 0.5672449138626566,
      "eval_loss": 1.1695806980133057,
      "eval_precision": 0.6061531146445093,
      "eval_recall": 0.5913190529875987,
      "eval_runtime": 21.8809,
      "eval_samples_per_second": 81.075,
      "eval_steps_per_second": 1.28,
      "step": 1562
    },
    {
      "epoch": 25.12,
      "learning_rate": 1.7323775388291518e-05,
      "loss": 1.2032,
      "step": 1570
    },
    {
      "epoch": 25.28,
      "learning_rate": 1.6726403823178017e-05,
      "loss": 1.22,
      "step": 1580
    },
    {
      "epoch": 25.44,
      "learning_rate": 1.6129032258064517e-05,
      "loss": 1.2206,
      "step": 1590
    },
    {
      "epoch": 25.6,
      "learning_rate": 1.5531660692951016e-05,
      "loss": 1.2222,
      "step": 1600
    },
    {
      "epoch": 25.76,
      "learning_rate": 1.4934289127837516e-05,
      "loss": 1.2218,
      "step": 1610
    },
    {
      "epoch": 25.92,
      "learning_rate": 1.4336917562724014e-05,
      "loss": 1.1913,
      "step": 1620
    },
    {
      "epoch": 26.0,
      "eval_accuracy": 0.5918827508455468,
      "eval_f1": 0.5677595343942556,
      "eval_loss": 1.166059970855713,
      "eval_precision": 0.6011740510143309,
      "eval_recall": 0.5918827508455468,
      "eval_runtime": 24.7186,
      "eval_samples_per_second": 71.768,
      "eval_steps_per_second": 1.133,
      "step": 1625
    },
    {
      "epoch": 26.08,
      "learning_rate": 1.3739545997610515e-05,
      "loss": 1.2119,
      "step": 1630
    },
    {
      "epoch": 26.24,
      "learning_rate": 1.3142174432497015e-05,
      "loss": 1.2229,
      "step": 1640
    },
    {
      "epoch": 26.4,
      "learning_rate": 1.2544802867383513e-05,
      "loss": 1.2139,
      "step": 1650
    },
    {
      "epoch": 26.56,
      "learning_rate": 1.1947431302270013e-05,
      "loss": 1.228,
      "step": 1660
    },
    {
      "epoch": 26.72,
      "learning_rate": 1.135005973715651e-05,
      "loss": 1.2139,
      "step": 1670
    },
    {
      "epoch": 26.88,
      "learning_rate": 1.0752688172043012e-05,
      "loss": 1.2111,
      "step": 1680
    },
    {
      "epoch": 26.99,
      "eval_accuracy": 0.5941375422773394,
      "eval_f1": 0.5702300711030653,
      "eval_loss": 1.1638890504837036,
      "eval_precision": 0.6024395376181177,
      "eval_recall": 0.5941375422773394,
      "eval_runtime": 21.6884,
      "eval_samples_per_second": 81.795,
      "eval_steps_per_second": 1.291,
      "step": 1687
    },
    {
      "epoch": 27.04,
      "learning_rate": 1.015531660692951e-05,
      "loss": 1.2022,
      "step": 1690
    },
    {
      "epoch": 27.2,
      "learning_rate": 9.557945041816011e-06,
      "loss": 1.2367,
      "step": 1700
    },
    {
      "epoch": 27.36,
      "learning_rate": 8.960573476702509e-06,
      "loss": 1.2098,
      "step": 1710
    },
    {
      "epoch": 27.52,
      "learning_rate": 8.363201911589009e-06,
      "loss": 1.2068,
      "step": 1720
    },
    {
      "epoch": 27.68,
      "learning_rate": 7.765830346475508e-06,
      "loss": 1.2094,
      "step": 1730
    },
    {
      "epoch": 27.84,
      "learning_rate": 7.168458781362007e-06,
      "loss": 1.2081,
      "step": 1740
    },
    {
      "epoch": 28.0,
      "learning_rate": 6.5710872162485075e-06,
      "loss": 1.2168,
      "step": 1750
    },
    {
      "epoch": 28.0,
      "eval_accuracy": 0.5952649379932357,
      "eval_f1": 0.5714376467349129,
      "eval_loss": 1.1634987592697144,
      "eval_precision": 0.6038590156410394,
      "eval_recall": 0.5952649379932357,
      "eval_runtime": 21.7656,
      "eval_samples_per_second": 81.505,
      "eval_steps_per_second": 1.286,
      "step": 1750
    },
    {
      "epoch": 28.16,
      "learning_rate": 5.973715651135006e-06,
      "loss": 1.2345,
      "step": 1760
    },
    {
      "epoch": 28.32,
      "learning_rate": 5.376344086021506e-06,
      "loss": 1.2111,
      "step": 1770
    },
    {
      "epoch": 28.48,
      "learning_rate": 4.7789725209080055e-06,
      "loss": 1.2238,
      "step": 1780
    },
    {
      "epoch": 28.64,
      "learning_rate": 4.181600955794504e-06,
      "loss": 1.1954,
      "step": 1790
    },
    {
      "epoch": 28.8,
      "learning_rate": 3.5842293906810035e-06,
      "loss": 1.2056,
      "step": 1800
    },
    {
      "epoch": 28.96,
      "learning_rate": 2.986857825567503e-06,
      "loss": 1.2114,
      "step": 1810
    },
    {
      "epoch": 28.99,
      "eval_accuracy": 0.5947012401352875,
      "eval_f1": 0.5708424800157854,
      "eval_loss": 1.1630581617355347,
      "eval_precision": 0.6033834911301407,
      "eval_recall": 0.5947012401352875,
      "eval_runtime": 21.8632,
      "eval_samples_per_second": 81.141,
      "eval_steps_per_second": 1.281,
      "step": 1812
    },
    {
      "epoch": 29.12,
      "learning_rate": 2.3894862604540028e-06,
      "loss": 1.2062,
      "step": 1820
    },
    {
      "epoch": 29.28,
      "learning_rate": 1.7921146953405017e-06,
      "loss": 1.2096,
      "step": 1830
    },
    {
      "epoch": 29.44,
      "learning_rate": 1.1947431302270014e-06,
      "loss": 1.195,
      "step": 1840
    },
    {
      "epoch": 29.6,
      "learning_rate": 5.973715651135007e-07,
      "loss": 1.2149,
      "step": 1850
    },
    {
      "epoch": 29.76,
      "learning_rate": 0.0,
      "loss": 1.242,
      "step": 1860
    },
    {
      "epoch": 29.76,
      "eval_accuracy": 0.5941375422773394,
      "eval_f1": 0.5702626157511408,
      "eval_loss": 1.16298246383667,
      "eval_precision": 0.6025735728226277,
      "eval_recall": 0.5941375422773394,
      "eval_runtime": 21.8833,
      "eval_samples_per_second": 81.066,
      "eval_steps_per_second": 1.28,
      "step": 1860
    },
    {
      "epoch": 29.76,
      "step": 1860,
      "total_flos": 1.0940057452591763e+20,
      "train_loss": 1.3704575569398942,
      "train_runtime": 8385.7458,
      "train_samples_per_second": 57.104,
      "train_steps_per_second": 0.222
    }
  ],
  "logging_steps": 10,
  "max_steps": 1860,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 30,
  "save_steps": 500,
  "total_flos": 1.0940057452591763e+20,
  "train_batch_size": 64,
  "trial_name": null,
  "trial_params": null
}