{
  "best_metric": 0.9857904085257548,
  "best_model_checkpoint": "10-finetuned-ausSpiders2000/checkpoint-2535",
  "epoch": 9.97338065661047,
  "eval_steps": 500,
  "global_step": 2810,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.04,
      "learning_rate": 1.7793594306049825e-05,
      "loss": 2.4863,
      "step": 10
    },
    {
      "epoch": 0.07,
      "learning_rate": 3.558718861209965e-05,
      "loss": 2.1753,
      "step": 20
    },
    {
      "epoch": 0.11,
      "learning_rate": 5.338078291814947e-05,
      "loss": 1.6356,
      "step": 30
    },
    {
      "epoch": 0.14,
      "learning_rate": 7.11743772241993e-05,
      "loss": 0.9598,
      "step": 40
    },
    {
      "epoch": 0.18,
      "learning_rate": 8.896797153024912e-05,
      "loss": 0.5263,
      "step": 50
    },
    {
      "epoch": 0.21,
      "learning_rate": 0.00010676156583629893,
      "loss": 0.2692,
      "step": 60
    },
    {
      "epoch": 0.25,
      "learning_rate": 0.00012455516014234875,
      "loss": 0.233,
      "step": 70
    },
    {
      "epoch": 0.28,
      "learning_rate": 0.0001423487544483986,
      "loss": 0.1485,
      "step": 80
    },
    {
      "epoch": 0.32,
      "learning_rate": 0.00016014234875444842,
      "loss": 0.148,
      "step": 90
    },
    {
      "epoch": 0.35,
      "learning_rate": 0.00017793594306049823,
      "loss": 0.1282,
      "step": 100
    },
    {
      "epoch": 0.39,
      "learning_rate": 0.00019572953736654805,
      "loss": 0.1211,
      "step": 110
    },
    {
      "epoch": 0.43,
      "learning_rate": 0.00021352313167259787,
      "loss": 0.1153,
      "step": 120
    },
    {
      "epoch": 0.46,
      "learning_rate": 0.0002313167259786477,
      "loss": 0.1512,
      "step": 130
    },
    {
      "epoch": 0.5,
      "learning_rate": 0.0002491103202846975,
      "loss": 0.1465,
      "step": 140
    },
    {
      "epoch": 0.53,
      "learning_rate": 0.0002669039145907473,
      "loss": 0.1391,
      "step": 150
    },
    {
      "epoch": 0.57,
      "learning_rate": 0.0002846975088967972,
      "loss": 0.099,
      "step": 160
    },
    {
      "epoch": 0.6,
      "learning_rate": 0.000302491103202847,
      "loss": 0.1788,
      "step": 170
    },
    {
      "epoch": 0.64,
      "learning_rate": 0.00032028469750889683,
      "loss": 0.1824,
      "step": 180
    },
    {
      "epoch": 0.67,
      "learning_rate": 0.0003380782918149466,
      "loss": 0.1867,
      "step": 190
    },
    {
      "epoch": 0.71,
      "learning_rate": 0.00035587188612099647,
      "loss": 0.1699,
      "step": 200
    },
    {
      "epoch": 0.75,
      "learning_rate": 0.0003736654804270463,
      "loss": 0.1658,
      "step": 210
    },
    {
      "epoch": 0.78,
      "learning_rate": 0.0003914590747330961,
      "loss": 0.1465,
      "step": 220
    },
    {
      "epoch": 0.82,
      "learning_rate": 0.00040925266903914595,
      "loss": 0.173,
      "step": 230
    },
    {
      "epoch": 0.85,
      "learning_rate": 0.00042704626334519574,
      "loss": 0.2829,
      "step": 240
    },
    {
      "epoch": 0.89,
      "learning_rate": 0.0004448398576512456,
      "loss": 0.1879,
      "step": 250
    },
    {
      "epoch": 0.92,
      "learning_rate": 0.0004626334519572954,
      "loss": 0.2341,
      "step": 260
    },
    {
      "epoch": 0.96,
      "learning_rate": 0.0004804270462633452,
      "loss": 0.2539,
      "step": 270
    },
    {
      "epoch": 0.99,
      "learning_rate": 0.000498220640569395,
      "loss": 0.1997,
      "step": 280
    },
    {
      "epoch": 1.0,
      "eval_accuracy": 0.9280639431616341,
      "eval_f1": 0.9044835301236254,
      "eval_loss": 0.2264249473810196,
      "eval_precision": 0.9395261094135103,
      "eval_recall": 0.8868521981209923,
      "eval_runtime": 40.9312,
      "eval_samples_per_second": 27.51,
      "eval_steps_per_second": 3.445,
      "step": 281
    },
    {
      "epoch": 1.03,
      "learning_rate": 0.000498220640569395,
      "loss": 0.1887,
      "step": 290
    },
    {
      "epoch": 1.06,
      "learning_rate": 0.0004962435745353895,
      "loss": 0.227,
      "step": 300
    },
    {
      "epoch": 1.1,
      "learning_rate": 0.0004942665085013839,
      "loss": 0.1633,
      "step": 310
    },
    {
      "epoch": 1.14,
      "learning_rate": 0.0004922894424673784,
      "loss": 0.2611,
      "step": 320
    },
    {
      "epoch": 1.17,
      "learning_rate": 0.0004903123764333729,
      "loss": 0.1793,
      "step": 330
    },
    {
      "epoch": 1.21,
      "learning_rate": 0.0004883353103993673,
      "loss": 0.1217,
      "step": 340
    },
    {
      "epoch": 1.24,
      "learning_rate": 0.0004863582443653618,
      "loss": 0.2545,
      "step": 350
    },
    {
      "epoch": 1.28,
      "learning_rate": 0.00048438117833135623,
      "loss": 0.3059,
      "step": 360
    },
    {
      "epoch": 1.31,
      "learning_rate": 0.00048240411229735075,
      "loss": 0.2185,
      "step": 370
    },
    {
      "epoch": 1.35,
      "learning_rate": 0.0004804270462633452,
      "loss": 0.1968,
      "step": 380
    },
    {
      "epoch": 1.38,
      "learning_rate": 0.0004784499802293397,
      "loss": 0.2301,
      "step": 390
    },
    {
      "epoch": 1.42,
      "learning_rate": 0.0004764729141953341,
      "loss": 0.3476,
      "step": 400
    },
    {
      "epoch": 1.46,
      "learning_rate": 0.0004744958481613286,
      "loss": 0.2723,
      "step": 410
    },
    {
      "epoch": 1.49,
      "learning_rate": 0.0004725187821273231,
      "loss": 0.2253,
      "step": 420
    },
    {
      "epoch": 1.53,
      "learning_rate": 0.0004705417160933175,
      "loss": 0.1927,
      "step": 430
    },
    {
      "epoch": 1.56,
      "learning_rate": 0.00046856465005931197,
      "loss": 0.2396,
      "step": 440
    },
    {
      "epoch": 1.6,
      "learning_rate": 0.00046658758402530644,
      "loss": 0.2278,
      "step": 450
    },
    {
      "epoch": 1.63,
      "learning_rate": 0.00046461051799130096,
      "loss": 0.275,
      "step": 460
    },
    {
      "epoch": 1.67,
      "learning_rate": 0.0004626334519572954,
      "loss": 0.1884,
      "step": 470
    },
    {
      "epoch": 1.7,
      "learning_rate": 0.00046065638592328984,
      "loss": 0.2211,
      "step": 480
    },
    {
      "epoch": 1.74,
      "learning_rate": 0.0004586793198892843,
      "loss": 0.2202,
      "step": 490
    },
    {
      "epoch": 1.77,
      "learning_rate": 0.0004567022538552787,
      "loss": 0.2851,
      "step": 500
    },
    {
      "epoch": 1.81,
      "learning_rate": 0.00045472518782127324,
      "loss": 0.2128,
      "step": 510
    },
    {
      "epoch": 1.85,
      "learning_rate": 0.0004527481217872677,
      "loss": 0.2074,
      "step": 520
    },
    {
      "epoch": 1.88,
      "learning_rate": 0.0004507710557532622,
      "loss": 0.2324,
      "step": 530
    },
    {
      "epoch": 1.92,
      "learning_rate": 0.0004487939897192566,
      "loss": 0.1803,
      "step": 540
    },
    {
      "epoch": 1.95,
      "learning_rate": 0.0004468169236852511,
      "loss": 0.209,
      "step": 550
    },
    {
      "epoch": 1.99,
      "learning_rate": 0.0004448398576512456,
      "loss": 0.17,
      "step": 560
    },
    {
      "epoch": 2.0,
      "eval_accuracy": 0.9564831261101243,
      "eval_f1": 0.8380915867647825,
      "eval_loss": 0.13818518817424774,
      "eval_precision": 0.8539785317750744,
      "eval_recall": 0.8265891631354911,
      "eval_runtime": 39.8834,
      "eval_samples_per_second": 28.232,
      "eval_steps_per_second": 3.535,
      "step": 563
    },
    {
      "epoch": 2.02,
      "learning_rate": 0.00044286279161724005,
      "loss": 0.2291,
      "step": 570
    },
    {
      "epoch": 2.06,
      "learning_rate": 0.00044088572558323446,
      "loss": 0.1695,
      "step": 580
    },
    {
      "epoch": 2.09,
      "learning_rate": 0.00043890865954922893,
      "loss": 0.2086,
      "step": 590
    },
    {
      "epoch": 2.13,
      "learning_rate": 0.00043693159351522345,
      "loss": 0.1849,
      "step": 600
    },
    {
      "epoch": 2.17,
      "learning_rate": 0.00043495452748121787,
      "loss": 0.2532,
      "step": 610
    },
    {
      "epoch": 2.2,
      "learning_rate": 0.00043297746144721233,
      "loss": 0.2137,
      "step": 620
    },
    {
      "epoch": 2.24,
      "learning_rate": 0.0004310003954132068,
      "loss": 0.1389,
      "step": 630
    },
    {
      "epoch": 2.27,
      "learning_rate": 0.0004290233293792013,
      "loss": 0.2308,
      "step": 640
    },
    {
      "epoch": 2.31,
      "learning_rate": 0.00042704626334519574,
      "loss": 0.1713,
      "step": 650
    },
    {
      "epoch": 2.34,
      "learning_rate": 0.0004250691973111902,
      "loss": 0.1593,
      "step": 660
    },
    {
      "epoch": 2.38,
      "learning_rate": 0.0004230921312771847,
      "loss": 0.199,
      "step": 670
    },
    {
      "epoch": 2.41,
      "learning_rate": 0.0004211150652431791,
      "loss": 0.2582,
      "step": 680
    },
    {
      "epoch": 2.45,
      "learning_rate": 0.0004191379992091736,
      "loss": 0.182,
      "step": 690
    },
    {
      "epoch": 2.48,
      "learning_rate": 0.0004171609331751681,
      "loss": 0.2524,
      "step": 700
    },
    {
      "epoch": 2.52,
      "learning_rate": 0.00041518386714116254,
      "loss": 0.1836,
      "step": 710
    },
    {
      "epoch": 2.56,
      "learning_rate": 0.00041320680110715696,
      "loss": 0.1668,
      "step": 720
    },
    {
      "epoch": 2.59,
      "learning_rate": 0.0004112297350731515,
      "loss": 0.2326,
      "step": 730
    },
    {
      "epoch": 2.63,
      "learning_rate": 0.00040925266903914595,
      "loss": 0.1824,
      "step": 740
    },
    {
      "epoch": 2.66,
      "learning_rate": 0.00040727560300514036,
      "loss": 0.1817,
      "step": 750
    },
    {
      "epoch": 2.7,
      "learning_rate": 0.00040529853697113483,
      "loss": 0.1547,
      "step": 760
    },
    {
      "epoch": 2.73,
      "learning_rate": 0.0004033214709371293,
      "loss": 0.1652,
      "step": 770
    },
    {
      "epoch": 2.77,
      "learning_rate": 0.0004013444049031238,
      "loss": 0.2278,
      "step": 780
    },
    {
      "epoch": 2.8,
      "learning_rate": 0.00039936733886911823,
      "loss": 0.2369,
      "step": 790
    },
    {
      "epoch": 2.84,
      "learning_rate": 0.0003973902728351127,
      "loss": 0.1947,
      "step": 800
    },
    {
      "epoch": 2.87,
      "learning_rate": 0.00039541320680110717,
      "loss": 0.1326,
      "step": 810
    },
    {
      "epoch": 2.91,
      "learning_rate": 0.0003934361407671016,
      "loss": 0.1644,
      "step": 820
    },
    {
      "epoch": 2.95,
      "learning_rate": 0.0003914590747330961,
      "loss": 0.1888,
      "step": 830
    },
    {
      "epoch": 2.98,
      "learning_rate": 0.00038948200869909057,
      "loss": 0.21,
      "step": 840
    },
    {
      "epoch": 3.0,
      "eval_accuracy": 0.9582593250444049,
      "eval_f1": 0.9348978364444572,
      "eval_loss": 0.14037781953811646,
      "eval_precision": 0.9746987945146139,
      "eval_recall": 0.9063700900026892,
      "eval_runtime": 39.7299,
      "eval_samples_per_second": 28.341,
      "eval_steps_per_second": 3.549,
      "step": 845
    },
    {
      "epoch": 3.02,
      "learning_rate": 0.00038750494266508504,
      "loss": 0.129,
      "step": 850
    },
    {
      "epoch": 3.05,
      "learning_rate": 0.00038552787663107945,
      "loss": 0.1675,
      "step": 860
    },
    {
      "epoch": 3.09,
      "learning_rate": 0.000383550810597074,
      "loss": 0.1136,
      "step": 870
    },
    {
      "epoch": 3.12,
      "learning_rate": 0.00038157374456306844,
      "loss": 0.1937,
      "step": 880
    },
    {
      "epoch": 3.16,
      "learning_rate": 0.00037959667852906285,
      "loss": 0.1219,
      "step": 890
    },
    {
      "epoch": 3.19,
      "learning_rate": 0.0003776196124950573,
      "loss": 0.1394,
      "step": 900
    },
    {
      "epoch": 3.23,
      "learning_rate": 0.0003756425464610518,
      "loss": 0.1505,
      "step": 910
    },
    {
      "epoch": 3.27,
      "learning_rate": 0.0003736654804270463,
      "loss": 0.1487,
      "step": 920
    },
    {
      "epoch": 3.3,
      "learning_rate": 0.0003716884143930407,
      "loss": 0.1228,
      "step": 930
    },
    {
      "epoch": 3.34,
      "learning_rate": 0.0003697113483590352,
      "loss": 0.185,
      "step": 940
    },
    {
      "epoch": 3.37,
      "learning_rate": 0.00036773428232502966,
      "loss": 0.1313,
      "step": 950
    },
    {
      "epoch": 3.41,
      "learning_rate": 0.00036575721629102413,
      "loss": 0.1977,
      "step": 960
    },
    {
      "epoch": 3.44,
      "learning_rate": 0.0003637801502570186,
      "loss": 0.2188,
      "step": 970
    },
    {
      "epoch": 3.48,
      "learning_rate": 0.00036180308422301306,
      "loss": 0.1717,
      "step": 980
    },
    {
      "epoch": 3.51,
      "learning_rate": 0.00035982601818900753,
      "loss": 0.1357,
      "step": 990
    },
    {
      "epoch": 3.55,
      "learning_rate": 0.00035784895215500194,
      "loss": 0.1386,
      "step": 1000
    },
    {
      "epoch": 3.58,
      "learning_rate": 0.00035587188612099647,
      "loss": 0.169,
      "step": 1010
    },
    {
      "epoch": 3.62,
      "learning_rate": 0.00035389482008699093,
      "loss": 0.164,
      "step": 1020
    },
    {
      "epoch": 3.66,
      "learning_rate": 0.00035191775405298535,
      "loss": 0.1334,
      "step": 1030
    },
    {
      "epoch": 3.69,
      "learning_rate": 0.0003499406880189798,
      "loss": 0.1634,
      "step": 1040
    },
    {
      "epoch": 3.73,
      "learning_rate": 0.00034796362198497434,
      "loss": 0.1614,
      "step": 1050
    },
    {
      "epoch": 3.76,
      "learning_rate": 0.0003459865559509688,
      "loss": 0.1819,
      "step": 1060
    },
    {
      "epoch": 3.8,
      "learning_rate": 0.0003440094899169632,
      "loss": 0.1796,
      "step": 1070
    },
    {
      "epoch": 3.83,
      "learning_rate": 0.0003420324238829577,
      "loss": 0.1341,
      "step": 1080
    },
    {
      "epoch": 3.87,
      "learning_rate": 0.00034005535784895215,
      "loss": 0.127,
      "step": 1090
    },
    {
      "epoch": 3.9,
      "learning_rate": 0.0003380782918149466,
      "loss": 0.1709,
      "step": 1100
    },
    {
      "epoch": 3.94,
      "learning_rate": 0.0003361012257809411,
      "loss": 0.2003,
      "step": 1110
    },
    {
      "epoch": 3.98,
      "learning_rate": 0.00033412415974693556,
      "loss": 0.1976,
      "step": 1120
    },
    {
      "epoch": 4.0,
      "eval_accuracy": 0.9689165186500888,
      "eval_f1": 0.912801315494264,
      "eval_loss": 0.09873761981725693,
      "eval_precision": 0.9716016779252258,
      "eval_recall": 0.8917025082468766,
      "eval_runtime": 39.8355,
      "eval_samples_per_second": 28.266,
      "eval_steps_per_second": 3.54,
      "step": 1127
    },
    {
      "epoch": 4.01,
      "learning_rate": 0.00033214709371293,
      "loss": 0.1981,
      "step": 1130
    },
    {
      "epoch": 4.05,
      "learning_rate": 0.00033017002767892444,
      "loss": 0.1504,
      "step": 1140
    },
    {
      "epoch": 4.08,
      "learning_rate": 0.00032819296164491896,
      "loss": 0.1655,
      "step": 1150
    },
    {
      "epoch": 4.12,
      "learning_rate": 0.00032621589561091343,
      "loss": 0.0908,
      "step": 1160
    },
    {
      "epoch": 4.15,
      "learning_rate": 0.00032423882957690784,
      "loss": 0.1043,
      "step": 1170
    },
    {
      "epoch": 4.19,
      "learning_rate": 0.0003222617635429023,
      "loss": 0.1908,
      "step": 1180
    },
    {
      "epoch": 4.22,
      "learning_rate": 0.00032028469750889683,
      "loss": 0.1202,
      "step": 1190
    },
    {
      "epoch": 4.26,
      "learning_rate": 0.0003183076314748913,
      "loss": 0.1597,
      "step": 1200
    },
    {
      "epoch": 4.29,
      "learning_rate": 0.0003163305654408857,
      "loss": 0.1318,
      "step": 1210
    },
    {
      "epoch": 4.33,
      "learning_rate": 0.0003143534994068802,
      "loss": 0.1674,
      "step": 1220
    },
    {
      "epoch": 4.37,
      "learning_rate": 0.00031237643337287465,
      "loss": 0.1218,
      "step": 1230
    },
    {
      "epoch": 4.4,
      "learning_rate": 0.00031039936733886917,
      "loss": 0.156,
      "step": 1240
    },
    {
      "epoch": 4.44,
      "learning_rate": 0.0003084223013048636,
      "loss": 0.1314,
      "step": 1250
    },
    {
      "epoch": 4.47,
      "learning_rate": 0.00030644523527085805,
      "loss": 0.1817,
      "step": 1260
    },
    {
      "epoch": 4.51,
      "learning_rate": 0.0003044681692368525,
      "loss": 0.187,
      "step": 1270
    },
    {
      "epoch": 4.54,
      "learning_rate": 0.000302491103202847,
      "loss": 0.1318,
      "step": 1280
    },
    {
      "epoch": 4.58,
      "learning_rate": 0.00030051403716884145,
      "loss": 0.1806,
      "step": 1290
    },
    {
      "epoch": 4.61,
      "learning_rate": 0.0002985369711348359,
      "loss": 0.1614,
      "step": 1300
    },
    {
      "epoch": 4.65,
      "learning_rate": 0.0002965599051008304,
      "loss": 0.1221,
      "step": 1310
    },
    {
      "epoch": 4.69,
      "learning_rate": 0.0002945828390668248,
      "loss": 0.1391,
      "step": 1320
    },
    {
      "epoch": 4.72,
      "learning_rate": 0.0002926057730328193,
      "loss": 0.1275,
      "step": 1330
    },
    {
      "epoch": 4.76,
      "learning_rate": 0.0002906287069988138,
      "loss": 0.1265,
      "step": 1340
    },
    {
      "epoch": 4.79,
      "learning_rate": 0.0002886516409648082,
      "loss": 0.1637,
      "step": 1350
    },
    {
      "epoch": 4.83,
      "learning_rate": 0.0002866745749308027,
      "loss": 0.1833,
      "step": 1360
    },
    {
      "epoch": 4.86,
      "learning_rate": 0.0002846975088967972,
      "loss": 0.1235,
      "step": 1370
    },
    {
      "epoch": 4.9,
      "learning_rate": 0.00028272044286279166,
      "loss": 0.0997,
      "step": 1380
    },
    {
      "epoch": 4.93,
      "learning_rate": 0.0002807433768287861,
      "loss": 0.0879,
      "step": 1390
    },
    {
      "epoch": 4.97,
      "learning_rate": 0.00027876631079478054,
      "loss": 0.178,
      "step": 1400
    },
    {
      "epoch": 5.0,
      "eval_accuracy": 0.9635879218472468,
      "eval_f1": 0.9471608472683106,
      "eval_loss": 0.12194248288869858,
      "eval_precision": 0.9393499332363083,
      "eval_recall": 0.9600466296790979,
      "eval_runtime": 39.8939,
      "eval_samples_per_second": 28.225,
      "eval_steps_per_second": 3.534,
      "step": 1408
    },
    {
      "epoch": 5.0,
      "learning_rate": 0.000276789244760775,
      "loss": 0.0922,
      "step": 1410
    },
    {
      "epoch": 5.04,
      "learning_rate": 0.0002748121787267695,
      "loss": 0.0684,
      "step": 1420
    },
    {
      "epoch": 5.08,
      "learning_rate": 0.00027283511269276395,
      "loss": 0.1164,
      "step": 1430
    },
    {
      "epoch": 5.11,
      "learning_rate": 0.0002708580466587584,
      "loss": 0.0982,
      "step": 1440
    },
    {
      "epoch": 5.15,
      "learning_rate": 0.0002688809806247529,
      "loss": 0.1041,
      "step": 1450
    },
    {
      "epoch": 5.18,
      "learning_rate": 0.0002669039145907473,
      "loss": 0.1143,
      "step": 1460
    },
    {
      "epoch": 5.22,
      "learning_rate": 0.0002649268485567418,
      "loss": 0.1927,
      "step": 1470
    },
    {
      "epoch": 5.25,
      "learning_rate": 0.0002629497825227363,
      "loss": 0.1207,
      "step": 1480
    },
    {
      "epoch": 5.29,
      "learning_rate": 0.0002609727164887307,
      "loss": 0.1076,
      "step": 1490
    },
    {
      "epoch": 5.32,
      "learning_rate": 0.00025899565045472517,
      "loss": 0.1068,
      "step": 1500
    },
    {
      "epoch": 5.36,
      "learning_rate": 0.0002570185844207197,
      "loss": 0.1254,
      "step": 1510
    },
    {
      "epoch": 5.39,
      "learning_rate": 0.00025504151838671416,
      "loss": 0.0679,
      "step": 1520
    },
    {
      "epoch": 5.43,
      "learning_rate": 0.00025306445235270857,
      "loss": 0.12,
      "step": 1530
    },
    {
      "epoch": 5.47,
      "learning_rate": 0.00025108738631870304,
      "loss": 0.1157,
      "step": 1540
    },
    {
      "epoch": 5.5,
      "learning_rate": 0.0002491103202846975,
      "loss": 0.1034,
      "step": 1550
    },
    {
      "epoch": 5.54,
      "learning_rate": 0.00024713325425069197,
      "loss": 0.1317,
      "step": 1560
    },
    {
      "epoch": 5.57,
      "learning_rate": 0.00024515618821668644,
      "loss": 0.0942,
      "step": 1570
    },
    {
      "epoch": 5.61,
      "learning_rate": 0.0002431791221826809,
      "loss": 0.1381,
      "step": 1580
    },
    {
      "epoch": 5.64,
      "learning_rate": 0.00024120205614867538,
      "loss": 0.1109,
      "step": 1590
    },
    {
      "epoch": 5.68,
      "learning_rate": 0.00023922499011466984,
      "loss": 0.1132,
      "step": 1600
    },
    {
      "epoch": 5.71,
      "learning_rate": 0.0002372479240806643,
      "loss": 0.0736,
      "step": 1610
    },
    {
      "epoch": 5.75,
      "learning_rate": 0.00023527085804665875,
      "loss": 0.1418,
      "step": 1620
    },
    {
      "epoch": 5.79,
      "learning_rate": 0.00023329379201265322,
      "loss": 0.1318,
      "step": 1630
    },
    {
      "epoch": 5.82,
      "learning_rate": 0.0002313167259786477,
      "loss": 0.1313,
      "step": 1640
    },
    {
      "epoch": 5.86,
      "learning_rate": 0.00022933965994464215,
      "loss": 0.1749,
      "step": 1650
    },
    {
      "epoch": 5.89,
      "learning_rate": 0.00022736259391063662,
      "loss": 0.1526,
      "step": 1660
    },
    {
      "epoch": 5.93,
      "learning_rate": 0.0002253855278766311,
      "loss": 0.0911,
      "step": 1670
    },
    {
      "epoch": 5.96,
      "learning_rate": 0.00022340846184262556,
      "loss": 0.1377,
      "step": 1680
    },
    {
      "epoch": 6.0,
      "learning_rate": 0.00022143139580862003,
      "loss": 0.0659,
      "step": 1690
    },
    {
      "epoch": 6.0,
      "eval_accuracy": 0.9813499111900533,
      "eval_f1": 0.9807178013915328,
      "eval_loss": 0.08037910610437393,
      "eval_precision": 0.9815439633215112,
      "eval_recall": 0.9801148444477591,
      "eval_runtime": 39.9217,
      "eval_samples_per_second": 28.205,
      "eval_steps_per_second": 3.532,
      "step": 1690
    },
    {
      "epoch": 6.03,
      "learning_rate": 0.00021945432977461447,
      "loss": 0.1303,
      "step": 1700
    },
    {
      "epoch": 6.07,
      "learning_rate": 0.00021747726374060893,
      "loss": 0.0513,
      "step": 1710
    },
    {
      "epoch": 6.1,
      "learning_rate": 0.0002155001977066034,
      "loss": 0.0856,
      "step": 1720
    },
    {
      "epoch": 6.14,
      "learning_rate": 0.00021352313167259787,
      "loss": 0.1485,
      "step": 1730
    },
    {
      "epoch": 6.18,
      "learning_rate": 0.00021154606563859234,
      "loss": 0.118,
      "step": 1740
    },
    {
      "epoch": 6.21,
      "learning_rate": 0.0002095689996045868,
      "loss": 0.0684,
      "step": 1750
    },
    {
      "epoch": 6.25,
      "learning_rate": 0.00020759193357058127,
      "loss": 0.1394,
      "step": 1760
    },
    {
      "epoch": 6.28,
      "learning_rate": 0.00020561486753657574,
      "loss": 0.1556,
      "step": 1770
    },
    {
      "epoch": 6.32,
      "learning_rate": 0.00020363780150257018,
      "loss": 0.1246,
      "step": 1780
    },
    {
      "epoch": 6.35,
      "learning_rate": 0.00020166073546856465,
      "loss": 0.1257,
      "step": 1790
    },
    {
      "epoch": 6.39,
      "learning_rate": 0.00019968366943455912,
      "loss": 0.17,
      "step": 1800
    },
    {
      "epoch": 6.42,
      "learning_rate": 0.00019770660340055358,
      "loss": 0.0932,
      "step": 1810
    },
    {
      "epoch": 6.46,
      "learning_rate": 0.00019572953736654805,
      "loss": 0.1288,
      "step": 1820
    },
    {
      "epoch": 6.5,
      "learning_rate": 0.00019375247133254252,
      "loss": 0.0677,
      "step": 1830
    },
    {
      "epoch": 6.53,
      "learning_rate": 0.000191775405298537,
      "loss": 0.1177,
      "step": 1840
    },
    {
      "epoch": 6.57,
      "learning_rate": 0.00018979833926453143,
      "loss": 0.1093,
      "step": 1850
    },
    {
      "epoch": 6.6,
      "learning_rate": 0.0001878212732305259,
      "loss": 0.1438,
      "step": 1860
    },
    {
      "epoch": 6.64,
      "learning_rate": 0.00018584420719652036,
      "loss": 0.0854,
      "step": 1870
    },
    {
      "epoch": 6.67,
      "learning_rate": 0.00018386714116251483,
      "loss": 0.0865,
      "step": 1880
    },
    {
      "epoch": 6.71,
      "learning_rate": 0.0001818900751285093,
      "loss": 0.1254,
      "step": 1890
    },
    {
      "epoch": 6.74,
      "learning_rate": 0.00017991300909450377,
      "loss": 0.0999,
      "step": 1900
    },
    {
      "epoch": 6.78,
      "learning_rate": 0.00017793594306049823,
      "loss": 0.1072,
      "step": 1910
    },
    {
      "epoch": 6.81,
      "learning_rate": 0.00017595887702649267,
      "loss": 0.1191,
      "step": 1920
    },
    {
      "epoch": 6.85,
      "learning_rate": 0.00017398181099248717,
      "loss": 0.1147,
      "step": 1930
    },
    {
      "epoch": 6.89,
      "learning_rate": 0.0001720047449584816,
      "loss": 0.1028,
      "step": 1940
    },
    {
      "epoch": 6.92,
      "learning_rate": 0.00017002767892447608,
      "loss": 0.0695,
      "step": 1950
    },
    {
      "epoch": 6.96,
      "learning_rate": 0.00016805061289047054,
      "loss": 0.0913,
      "step": 1960
    },
    {
      "epoch": 6.99,
      "learning_rate": 0.000166073546856465,
      "loss": 0.0917,
      "step": 1970
    },
    {
      "epoch": 7.0,
      "eval_accuracy": 0.9733570159857904,
      "eval_f1": 0.9715717407405214,
      "eval_loss": 0.10624586045742035,
      "eval_precision": 0.9764811708120374,
      "eval_recall": 0.9675866233506976,
      "eval_runtime": 39.8459,
      "eval_samples_per_second": 28.259,
      "eval_steps_per_second": 3.539,
      "step": 1972
    },
    {
      "epoch": 7.03,
      "learning_rate": 0.00016409648082245948,
      "loss": 0.1021,
      "step": 1980
    },
    {
      "epoch": 7.06,
      "learning_rate": 0.00016211941478845392,
      "loss": 0.0706,
      "step": 1990
    },
    {
      "epoch": 7.1,
      "learning_rate": 0.00016014234875444842,
      "loss": 0.0677,
      "step": 2000
    },
    {
      "epoch": 7.13,
      "learning_rate": 0.00015816528272044286,
      "loss": 0.0857,
      "step": 2010
    },
    {
      "epoch": 7.17,
      "learning_rate": 0.00015618821668643732,
      "loss": 0.0865,
      "step": 2020
    },
    {
      "epoch": 7.2,
      "learning_rate": 0.0001542111506524318,
      "loss": 0.0641,
      "step": 2030
    },
    {
      "epoch": 7.24,
      "learning_rate": 0.00015223408461842626,
      "loss": 0.0446,
      "step": 2040
    },
    {
      "epoch": 7.28,
      "learning_rate": 0.00015025701858442073,
      "loss": 0.053,
      "step": 2050
    },
    {
      "epoch": 7.31,
      "learning_rate": 0.0001482799525504152,
      "loss": 0.087,
      "step": 2060
    },
    {
      "epoch": 7.35,
      "learning_rate": 0.00014630288651640966,
      "loss": 0.0873,
      "step": 2070
    },
    {
      "epoch": 7.38,
      "learning_rate": 0.0001443258204824041,
      "loss": 0.099,
      "step": 2080
    },
    {
      "epoch": 7.42,
      "learning_rate": 0.0001423487544483986,
      "loss": 0.1161,
      "step": 2090
    },
    {
      "epoch": 7.45,
      "learning_rate": 0.00014037168841439304,
      "loss": 0.0951,
      "step": 2100
    },
    {
      "epoch": 7.49,
      "learning_rate": 0.0001383946223803875,
      "loss": 0.0605,
      "step": 2110
    },
    {
      "epoch": 7.52,
      "learning_rate": 0.00013641755634638197,
      "loss": 0.0857,
      "step": 2120
    },
    {
      "epoch": 7.56,
      "learning_rate": 0.00013444049031237644,
      "loss": 0.1027,
      "step": 2130
    },
    {
      "epoch": 7.6,
      "learning_rate": 0.0001324634242783709,
      "loss": 0.1222,
      "step": 2140
    },
    {
      "epoch": 7.63,
      "learning_rate": 0.00013048635824436535,
      "loss": 0.1055,
      "step": 2150
    },
    {
      "epoch": 7.67,
      "learning_rate": 0.00012850929221035984,
      "loss": 0.1326,
      "step": 2160
    },
    {
      "epoch": 7.7,
      "learning_rate": 0.00012653222617635428,
      "loss": 0.0953,
      "step": 2170
    },
    {
      "epoch": 7.74,
      "learning_rate": 0.00012455516014234875,
      "loss": 0.0672,
      "step": 2180
    },
    {
      "epoch": 7.77,
      "learning_rate": 0.00012257809410834322,
      "loss": 0.0827,
      "step": 2190
    },
    {
      "epoch": 7.81,
      "learning_rate": 0.00012060102807433769,
      "loss": 0.0651,
      "step": 2200
    },
    {
      "epoch": 7.84,
      "learning_rate": 0.00011862396204033216,
      "loss": 0.0662,
      "step": 2210
    },
    {
      "epoch": 7.88,
      "learning_rate": 0.00011664689600632661,
      "loss": 0.1431,
      "step": 2220
    },
    {
      "epoch": 7.91,
      "learning_rate": 0.00011466982997232108,
      "loss": 0.0315,
      "step": 2230
    },
    {
      "epoch": 7.95,
      "learning_rate": 0.00011269276393831554,
      "loss": 0.0996,
      "step": 2240
    },
    {
      "epoch": 7.99,
      "learning_rate": 0.00011071569790431001,
      "loss": 0.108,
      "step": 2250
    },
    {
      "epoch": 8.0,
      "eval_accuracy": 0.9849023090586145,
      "eval_f1": 0.9828334388632164,
      "eval_loss": 0.05676717311143875,
      "eval_precision": 0.9868491250375566,
      "eval_recall": 0.9794172540958566,
      "eval_runtime": 39.7132,
      "eval_samples_per_second": 28.353,
      "eval_steps_per_second": 3.55,
      "step": 2254
    },
    {
      "epoch": 8.02,
      "learning_rate": 0.00010873863187030447,
      "loss": 0.0307,
      "step": 2260
    },
    {
      "epoch": 8.06,
      "learning_rate": 0.00010676156583629893,
      "loss": 0.0847,
      "step": 2270
    },
    {
      "epoch": 8.09,
      "learning_rate": 0.0001047844998022934,
      "loss": 0.1177,
      "step": 2280
    },
    {
      "epoch": 8.13,
      "learning_rate": 0.00010280743376828787,
      "loss": 0.0689,
      "step": 2290
    },
    {
      "epoch": 8.16,
      "learning_rate": 0.00010083036773428232,
      "loss": 0.0873,
      "step": 2300
    },
    {
      "epoch": 8.2,
      "learning_rate": 9.885330170027679e-05,
      "loss": 0.1209,
      "step": 2310
    },
    {
      "epoch": 8.23,
      "learning_rate": 9.687623566627126e-05,
      "loss": 0.0488,
      "step": 2320
    },
    {
      "epoch": 8.27,
      "learning_rate": 9.489916963226571e-05,
      "loss": 0.0558,
      "step": 2330
    },
    {
      "epoch": 8.31,
      "learning_rate": 9.292210359826018e-05,
      "loss": 0.067,
      "step": 2340
    },
    {
      "epoch": 8.34,
      "learning_rate": 9.094503756425465e-05,
      "loss": 0.13,
      "step": 2350
    },
    {
      "epoch": 8.38,
      "learning_rate": 8.896797153024912e-05,
      "loss": 0.0743,
      "step": 2360
    },
    {
      "epoch": 8.41,
      "learning_rate": 8.699090549624358e-05,
      "loss": 0.0797,
      "step": 2370
    },
    {
      "epoch": 8.45,
      "learning_rate": 8.501383946223804e-05,
      "loss": 0.0913,
      "step": 2380
    },
    {
      "epoch": 8.48,
      "learning_rate": 8.30367734282325e-05,
      "loss": 0.0772,
      "step": 2390
    },
    {
      "epoch": 8.52,
      "learning_rate": 8.105970739422696e-05,
      "loss": 0.072,
      "step": 2400
    },
    {
      "epoch": 8.55,
      "learning_rate": 7.908264136022143e-05,
      "loss": 0.0566,
      "step": 2410
    },
    {
      "epoch": 8.59,
      "learning_rate": 7.71055753262159e-05,
      "loss": 0.1198,
      "step": 2420
    },
    {
      "epoch": 8.62,
      "learning_rate": 7.512850929221036e-05,
      "loss": 0.0647,
      "step": 2430
    },
    {
      "epoch": 8.66,
      "learning_rate": 7.315144325820483e-05,
      "loss": 0.1079,
      "step": 2440
    },
    {
      "epoch": 8.7,
      "learning_rate": 7.11743772241993e-05,
      "loss": 0.0792,
      "step": 2450
    },
    {
      "epoch": 8.73,
      "learning_rate": 6.919731119019375e-05,
      "loss": 0.0712,
      "step": 2460
    },
    {
      "epoch": 8.77,
      "learning_rate": 6.722024515618822e-05,
      "loss": 0.0707,
      "step": 2470
    },
    {
      "epoch": 8.8,
      "learning_rate": 6.524317912218267e-05,
      "loss": 0.0571,
      "step": 2480
    },
    {
      "epoch": 8.84,
      "learning_rate": 6.326611308817714e-05,
      "loss": 0.0802,
      "step": 2490
    },
    {
      "epoch": 8.87,
      "learning_rate": 6.128904705417161e-05,
      "loss": 0.0533,
      "step": 2500
    },
    {
      "epoch": 8.91,
      "learning_rate": 5.931198102016608e-05,
      "loss": 0.078,
      "step": 2510
    },
    {
      "epoch": 8.94,
      "learning_rate": 5.733491498616054e-05,
      "loss": 0.0795,
      "step": 2520
    },
    {
      "epoch": 8.98,
      "learning_rate": 5.5357848952155006e-05,
      "loss": 0.1151,
      "step": 2530
    },
    {
      "epoch": 9.0,
      "eval_accuracy": 0.9857904085257548,
      "eval_f1": 0.9868558448721283,
      "eval_loss": 0.050765056163072586,
      "eval_precision": 0.987576986984624,
      "eval_recall": 0.9863465915836483,
      "eval_runtime": 39.9806,
      "eval_samples_per_second": 28.164,
      "eval_steps_per_second": 3.527,
      "step": 2535
    },
    {
      "epoch": 9.02,
      "learning_rate": 5.338078291814947e-05,
      "loss": 0.0986,
      "step": 2540
    },
    {
      "epoch": 9.05,
      "learning_rate": 5.1403716884143935e-05,
      "loss": 0.0261,
      "step": 2550
    },
    {
      "epoch": 9.09,
      "learning_rate": 4.9426650850138396e-05,
      "loss": 0.0691,
      "step": 2560
    },
    {
      "epoch": 9.12,
      "learning_rate": 4.744958481613286e-05,
      "loss": 0.0361,
      "step": 2570
    },
    {
      "epoch": 9.16,
      "learning_rate": 4.5472518782127324e-05,
      "loss": 0.0829,
      "step": 2580
    },
    {
      "epoch": 9.19,
      "learning_rate": 4.349545274812179e-05,
      "loss": 0.0701,
      "step": 2590
    },
    {
      "epoch": 9.23,
      "learning_rate": 4.151838671411625e-05,
      "loss": 0.0608,
      "step": 2600
    },
    {
      "epoch": 9.26,
      "learning_rate": 3.9541320680110714e-05,
      "loss": 0.056,
      "step": 2610
    },
    {
      "epoch": 9.3,
      "learning_rate": 3.756425464610518e-05,
      "loss": 0.0595,
      "step": 2620
    },
    {
      "epoch": 9.33,
      "learning_rate": 3.558718861209965e-05,
      "loss": 0.0891,
      "step": 2630
    },
    {
      "epoch": 9.37,
      "learning_rate": 3.361012257809411e-05,
      "loss": 0.0716,
      "step": 2640
    },
    {
      "epoch": 9.41,
      "learning_rate": 3.163305654408857e-05,
      "loss": 0.0674,
      "step": 2650
    },
    {
      "epoch": 9.44,
      "learning_rate": 2.965599051008304e-05,
      "loss": 0.0568,
      "step": 2660
    },
    {
      "epoch": 9.48,
      "learning_rate": 2.7678924476077503e-05,
      "loss": 0.0531,
      "step": 2670
    },
    {
      "epoch": 9.51,
      "learning_rate": 2.5701858442071967e-05,
      "loss": 0.0749,
      "step": 2680
    },
    {
      "epoch": 9.55,
      "learning_rate": 2.372479240806643e-05,
      "loss": 0.09,
      "step": 2690
    },
    {
      "epoch": 9.58,
      "learning_rate": 2.1747726374060896e-05,
      "loss": 0.0794,
      "step": 2700
    },
    {
      "epoch": 9.62,
      "learning_rate": 1.9770660340055357e-05,
      "loss": 0.0452,
      "step": 2710
    },
    {
      "epoch": 9.65,
      "learning_rate": 1.7793594306049825e-05,
      "loss": 0.0822,
      "step": 2720
    },
    {
      "epoch": 9.69,
      "learning_rate": 1.5816528272044286e-05,
      "loss": 0.0461,
      "step": 2730
    },
    {
      "epoch": 9.72,
      "learning_rate": 1.3839462238038752e-05,
      "loss": 0.043,
      "step": 2740
    },
    {
      "epoch": 9.76,
      "learning_rate": 1.1862396204033214e-05,
      "loss": 0.1089,
      "step": 2750
    },
    {
      "epoch": 9.8,
      "learning_rate": 9.885330170027678e-06,
      "loss": 0.0963,
      "step": 2760
    },
    {
      "epoch": 9.83,
      "learning_rate": 7.908264136022143e-06,
      "loss": 0.0683,
      "step": 2770
    },
    {
      "epoch": 9.87,
      "learning_rate": 5.931198102016607e-06,
      "loss": 0.047,
      "step": 2780
    },
    {
      "epoch": 9.9,
      "learning_rate": 3.954132068011071e-06,
      "loss": 0.0792,
      "step": 2790
    },
    {
      "epoch": 9.94,
      "learning_rate": 1.9770660340055357e-06,
      "loss": 0.0441,
      "step": 2800
    },
    {
      "epoch": 9.97,
      "learning_rate": 0.0,
      "loss": 0.049,
      "step": 2810
    },
    {
      "epoch": 9.97,
      "eval_accuracy": 0.9857904085257548,
      "eval_f1": 0.9877505171364073,
      "eval_loss": 0.050837442278862,
      "eval_precision": 0.9891672844560683,
      "eval_recall": 0.9865008922572412,
      "eval_runtime": 39.8176,
      "eval_samples_per_second": 28.279,
      "eval_steps_per_second": 3.541,
      "step": 2810
    },
    {
      "epoch": 9.97,
      "step": 2810,
      "total_flos": 2.0918954997191803e+19,
      "train_loss": 0.16025869953462663,
      "train_runtime": 8523.7997,
      "train_samples_per_second": 10.57,
      "train_steps_per_second": 0.33
    }
  ],
  "logging_steps": 10,
  "max_steps": 2810,
  "num_train_epochs": 10,
  "save_steps": 500,
  "total_flos": 2.0918954997191803e+19,
  "trial_name": null,
  "trial_params": null
}