{
  "best_metric": 0.9310862172434486,
  "best_model_checkpoint": "10-convnextv2-base-22k-384-finetuned-spiderTraining100-1000/checkpoint-7400",
  "epoch": 9.989875126560918,
  "eval_steps": 500,
  "global_step": 7400,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.01,
      "learning_rate": 6.7567567567567575e-06,
      "loss": 4.7191,
      "step": 10
    },
    {
      "epoch": 0.03,
      "learning_rate": 1.3513513513513515e-05,
      "loss": 4.6815,
      "step": 20
    },
    {
      "epoch": 0.04,
      "learning_rate": 2.0270270270270273e-05,
      "loss": 4.6441,
      "step": 30
    },
    {
      "epoch": 0.05,
      "learning_rate": 2.702702702702703e-05,
      "loss": 4.5566,
      "step": 40
    },
    {
      "epoch": 0.07,
      "learning_rate": 3.3783783783783784e-05,
      "loss": 4.5796,
      "step": 50
    },
    {
      "epoch": 0.08,
      "learning_rate": 4.0540540540540545e-05,
      "loss": 4.6235,
      "step": 60
    },
    {
      "epoch": 0.09,
      "learning_rate": 4.72972972972973e-05,
      "loss": 4.61,
      "step": 70
    },
    {
      "epoch": 0.11,
      "learning_rate": 5.405405405405406e-05,
      "loss": 4.6244,
      "step": 80
    },
    {
      "epoch": 0.12,
      "learning_rate": 6.0810810810810814e-05,
      "loss": 4.6277,
      "step": 90
    },
    {
      "epoch": 0.13,
      "learning_rate": 6.756756756756757e-05,
      "loss": 4.6237,
      "step": 100
    },
    {
      "epoch": 0.15,
      "learning_rate": 7.432432432432433e-05,
      "loss": 4.5135,
      "step": 110
    },
    {
      "epoch": 0.16,
      "learning_rate": 8.108108108108109e-05,
      "loss": 4.4143,
      "step": 120
    },
    {
      "epoch": 0.18,
      "learning_rate": 8.783783783783784e-05,
      "loss": 4.1232,
      "step": 130
    },
    {
      "epoch": 0.19,
      "learning_rate": 9.45945945945946e-05,
      "loss": 3.7123,
      "step": 140
    },
    {
      "epoch": 0.2,
      "learning_rate": 0.00010135135135135136,
      "loss": 3.1878,
      "step": 150
    },
    {
      "epoch": 0.22,
      "learning_rate": 0.00010810810810810812,
      "loss": 2.7711,
      "step": 160
    },
    {
      "epoch": 0.23,
      "learning_rate": 0.00011486486486486487,
      "loss": 2.3975,
      "step": 170
    },
    {
      "epoch": 0.24,
      "learning_rate": 0.00012162162162162163,
      "loss": 2.2354,
      "step": 180
    },
    {
      "epoch": 0.26,
      "learning_rate": 0.00012837837837837836,
      "loss": 2.0567,
      "step": 190
    },
    {
      "epoch": 0.27,
      "learning_rate": 0.00013513513513513514,
      "loss": 1.9001,
      "step": 200
    },
    {
      "epoch": 0.28,
      "learning_rate": 0.00014189189189189188,
      "loss": 1.7957,
      "step": 210
    },
    {
      "epoch": 0.3,
      "learning_rate": 0.00014864864864864866,
      "loss": 1.683,
      "step": 220
    },
    {
      "epoch": 0.31,
      "learning_rate": 0.0001554054054054054,
      "loss": 1.6268,
      "step": 230
    },
    {
      "epoch": 0.32,
      "learning_rate": 0.00016216216216216218,
      "loss": 1.6159,
      "step": 240
    },
    {
      "epoch": 0.34,
      "learning_rate": 0.00016891891891891893,
      "loss": 1.4989,
      "step": 250
    },
    {
      "epoch": 0.35,
      "learning_rate": 0.00017567567567567568,
      "loss": 1.4819,
      "step": 260
    },
    {
      "epoch": 0.36,
      "learning_rate": 0.00018243243243243242,
      "loss": 1.4353,
      "step": 270
    },
    {
      "epoch": 0.38,
      "learning_rate": 0.0001891891891891892,
      "loss": 1.4604,
      "step": 280
    },
    {
      "epoch": 0.39,
      "learning_rate": 0.00019594594594594594,
      "loss": 1.4115,
      "step": 290
    },
    {
      "epoch": 0.4,
      "learning_rate": 0.00020270270270270272,
      "loss": 1.3756,
      "step": 300
    },
    {
      "epoch": 0.42,
      "learning_rate": 0.00020945945945945947,
      "loss": 1.3704,
      "step": 310
    },
    {
      "epoch": 0.43,
      "learning_rate": 0.00021621621621621624,
      "loss": 1.3525,
      "step": 320
    },
    {
      "epoch": 0.45,
      "learning_rate": 0.000222972972972973,
      "loss": 1.3842,
      "step": 330
    },
    {
      "epoch": 0.46,
      "learning_rate": 0.00022972972972972974,
      "loss": 1.3297,
      "step": 340
    },
    {
      "epoch": 0.47,
      "learning_rate": 0.00023648648648648648,
      "loss": 1.304,
      "step": 350
    },
    {
      "epoch": 0.49,
      "learning_rate": 0.00024324324324324326,
      "loss": 1.4385,
      "step": 360
    },
    {
      "epoch": 0.5,
      "learning_rate": 0.00025,
      "loss": 1.3085,
      "step": 370
    },
    {
      "epoch": 0.51,
      "learning_rate": 0.0002567567567567567,
      "loss": 1.3235,
      "step": 380
    },
    {
      "epoch": 0.53,
      "learning_rate": 0.0002635135135135135,
      "loss": 1.3504,
      "step": 390
    },
    {
      "epoch": 0.54,
      "learning_rate": 0.0002702702702702703,
      "loss": 1.3193,
      "step": 400
    },
    {
      "epoch": 0.55,
      "learning_rate": 0.00027702702702702705,
      "loss": 1.2816,
      "step": 410
    },
    {
      "epoch": 0.57,
      "learning_rate": 0.00028378378378378377,
      "loss": 1.3683,
      "step": 420
    },
    {
      "epoch": 0.58,
      "learning_rate": 0.00029054054054054054,
      "loss": 1.1493,
      "step": 430
    },
    {
      "epoch": 0.59,
      "learning_rate": 0.0002972972972972973,
      "loss": 1.3138,
      "step": 440
    },
    {
      "epoch": 0.61,
      "learning_rate": 0.00030405405405405404,
      "loss": 1.3149,
      "step": 450
    },
    {
      "epoch": 0.62,
      "learning_rate": 0.0003108108108108108,
      "loss": 1.297,
      "step": 460
    },
    {
      "epoch": 0.63,
      "learning_rate": 0.00031756756756756753,
      "loss": 1.4255,
      "step": 470
    },
    {
      "epoch": 0.65,
      "learning_rate": 0.00032432432432432436,
      "loss": 1.3951,
      "step": 480
    },
    {
      "epoch": 0.66,
      "learning_rate": 0.0003310810810810811,
      "loss": 1.2615,
      "step": 490
    },
    {
      "epoch": 0.67,
      "learning_rate": 0.00033783783783783786,
      "loss": 1.2754,
      "step": 500
    },
    {
      "epoch": 0.69,
      "learning_rate": 0.0003445945945945946,
      "loss": 1.3006,
      "step": 510
    },
    {
      "epoch": 0.7,
      "learning_rate": 0.00035135135135135135,
      "loss": 1.444,
      "step": 520
    },
    {
      "epoch": 0.72,
      "learning_rate": 0.0003581081081081081,
      "loss": 1.2068,
      "step": 530
    },
    {
      "epoch": 0.73,
      "learning_rate": 0.00036486486486486485,
      "loss": 1.4908,
      "step": 540
    },
    {
      "epoch": 0.74,
      "learning_rate": 0.0003716216216216216,
      "loss": 1.3093,
      "step": 550
    },
    {
      "epoch": 0.76,
      "learning_rate": 0.0003783783783783784,
      "loss": 1.2905,
      "step": 560
    },
    {
      "epoch": 0.77,
      "learning_rate": 0.00038513513513513517,
      "loss": 1.4815,
      "step": 570
    },
    {
      "epoch": 0.78,
      "learning_rate": 0.0003918918918918919,
      "loss": 1.2824,
      "step": 580
    },
    {
      "epoch": 0.8,
      "learning_rate": 0.00039864864864864866,
      "loss": 1.3966,
      "step": 590
    },
    {
      "epoch": 0.81,
      "learning_rate": 0.00040540540540540544,
      "loss": 1.3284,
      "step": 600
    },
    {
      "epoch": 0.82,
      "learning_rate": 0.00041216216216216216,
      "loss": 1.249,
      "step": 610
    },
    {
      "epoch": 0.84,
      "learning_rate": 0.00041891891891891893,
      "loss": 1.2585,
      "step": 620
    },
    {
      "epoch": 0.85,
      "learning_rate": 0.00042567567567567565,
      "loss": 1.3343,
      "step": 630
    },
    {
      "epoch": 0.86,
      "learning_rate": 0.0004324324324324325,
      "loss": 1.2704,
      "step": 640
    },
    {
      "epoch": 0.88,
      "learning_rate": 0.0004391891891891892,
      "loss": 1.3528,
      "step": 650
    },
    {
      "epoch": 0.89,
      "learning_rate": 0.000445945945945946,
      "loss": 1.3853,
      "step": 660
    },
    {
      "epoch": 0.9,
      "learning_rate": 0.0004527027027027027,
      "loss": 1.3388,
      "step": 670
    },
    {
      "epoch": 0.92,
      "learning_rate": 0.00045945945945945947,
      "loss": 1.4151,
      "step": 680
    },
    {
      "epoch": 0.93,
      "learning_rate": 0.00046621621621621625,
      "loss": 1.4184,
      "step": 690
    },
    {
      "epoch": 0.94,
      "learning_rate": 0.00047297297297297297,
      "loss": 1.3309,
      "step": 700
    },
    {
      "epoch": 0.96,
      "learning_rate": 0.00047972972972972974,
      "loss": 1.4356,
      "step": 710
    },
    {
      "epoch": 0.97,
      "learning_rate": 0.0004864864864864865,
      "loss": 1.4564,
      "step": 720
    },
    {
      "epoch": 0.99,
      "learning_rate": 0.0004932432432432432,
      "loss": 1.3526,
      "step": 730
    },
    {
      "epoch": 1.0,
      "learning_rate": 0.0005,
      "loss": 1.2855,
      "step": 740
    },
    {
      "epoch": 1.0,
      "eval_accuracy": 0.7249449889977996,
      "eval_f1": 0.7228725416685348,
      "eval_loss": 0.9570144414901733,
      "eval_precision": 0.7636111347187294,
      "eval_recall": 0.7236760047474455,
      "eval_runtime": 196.5787,
      "eval_samples_per_second": 50.86,
      "eval_steps_per_second": 1.887,
      "step": 740
    },
    {
      "epoch": 1.01,
      "learning_rate": 0.0004992492492492493,
      "loss": 1.2199,
      "step": 750
    },
    {
      "epoch": 1.03,
      "learning_rate": 0.0004984984984984984,
      "loss": 1.3408,
      "step": 760
    },
    {
      "epoch": 1.04,
      "learning_rate": 0.0004977477477477478,
      "loss": 1.2037,
      "step": 770
    },
    {
      "epoch": 1.05,
      "learning_rate": 0.000496996996996997,
      "loss": 1.3243,
      "step": 780
    },
    {
      "epoch": 1.07,
      "learning_rate": 0.0004962462462462463,
      "loss": 1.3089,
      "step": 790
    },
    {
      "epoch": 1.08,
      "learning_rate": 0.0004954954954954955,
      "loss": 1.2901,
      "step": 800
    },
    {
      "epoch": 1.09,
      "learning_rate": 0.0004947447447447447,
      "loss": 1.2378,
      "step": 810
    },
    {
      "epoch": 1.11,
      "learning_rate": 0.0004939939939939941,
      "loss": 1.2818,
      "step": 820
    },
    {
      "epoch": 1.12,
      "learning_rate": 0.0004932432432432432,
      "loss": 1.2249,
      "step": 830
    },
    {
      "epoch": 1.13,
      "learning_rate": 0.0004924924924924925,
      "loss": 1.2199,
      "step": 840
    },
    {
      "epoch": 1.15,
      "learning_rate": 0.0004917417417417418,
      "loss": 1.2566,
      "step": 850
    },
    {
      "epoch": 1.16,
      "learning_rate": 0.0004909909909909909,
      "loss": 1.2868,
      "step": 860
    },
    {
      "epoch": 1.17,
      "learning_rate": 0.0004902402402402403,
      "loss": 1.4444,
      "step": 870
    },
    {
      "epoch": 1.19,
      "learning_rate": 0.0004894894894894895,
      "loss": 1.3055,
      "step": 880
    },
    {
      "epoch": 1.2,
      "learning_rate": 0.0004887387387387388,
      "loss": 1.2765,
      "step": 890
    },
    {
      "epoch": 1.21,
      "learning_rate": 0.000487987987987988,
      "loss": 1.2846,
      "step": 900
    },
    {
      "epoch": 1.23,
      "learning_rate": 0.00048723723723723724,
      "loss": 1.2887,
      "step": 910
    },
    {
      "epoch": 1.24,
      "learning_rate": 0.0004864864864864865,
      "loss": 1.2308,
      "step": 920
    },
    {
      "epoch": 1.26,
      "learning_rate": 0.0004857357357357358,
      "loss": 1.2236,
      "step": 930
    },
    {
      "epoch": 1.27,
      "learning_rate": 0.000484984984984985,
      "loss": 1.2052,
      "step": 940
    },
    {
      "epoch": 1.28,
      "learning_rate": 0.0004842342342342342,
      "loss": 1.1945,
      "step": 950
    },
    {
      "epoch": 1.3,
      "learning_rate": 0.0004834834834834835,
      "loss": 1.2301,
      "step": 960
    },
    {
      "epoch": 1.31,
      "learning_rate": 0.0004827327327327327,
      "loss": 1.2469,
      "step": 970
    },
    {
      "epoch": 1.32,
      "learning_rate": 0.00048198198198198204,
      "loss": 1.1334,
      "step": 980
    },
    {
      "epoch": 1.34,
      "learning_rate": 0.00048123123123123125,
      "loss": 1.2563,
      "step": 990
    },
    {
      "epoch": 1.35,
      "learning_rate": 0.00048048048048048047,
      "loss": 1.2526,
      "step": 1000
    },
    {
      "epoch": 1.36,
      "learning_rate": 0.00047972972972972974,
      "loss": 1.3089,
      "step": 1010
    },
    {
      "epoch": 1.38,
      "learning_rate": 0.00047897897897897896,
      "loss": 1.1471,
      "step": 1020
    },
    {
      "epoch": 1.39,
      "learning_rate": 0.0004782282282282283,
      "loss": 1.2159,
      "step": 1030
    },
    {
      "epoch": 1.4,
      "learning_rate": 0.0004774774774774775,
      "loss": 1.254,
      "step": 1040
    },
    {
      "epoch": 1.42,
      "learning_rate": 0.0004767267267267267,
      "loss": 1.1875,
      "step": 1050
    },
    {
      "epoch": 1.43,
      "learning_rate": 0.000475975975975976,
      "loss": 1.28,
      "step": 1060
    },
    {
      "epoch": 1.44,
      "learning_rate": 0.0004752252252252252,
      "loss": 1.2797,
      "step": 1070
    },
    {
      "epoch": 1.46,
      "learning_rate": 0.0004744744744744745,
      "loss": 1.2614,
      "step": 1080
    },
    {
      "epoch": 1.47,
      "learning_rate": 0.00047372372372372375,
      "loss": 1.2121,
      "step": 1090
    },
    {
      "epoch": 1.48,
      "learning_rate": 0.00047297297297297297,
      "loss": 1.2221,
      "step": 1100
    },
    {
      "epoch": 1.5,
      "learning_rate": 0.00047222222222222224,
      "loss": 1.1854,
      "step": 1110
    },
    {
      "epoch": 1.51,
      "learning_rate": 0.00047147147147147146,
      "loss": 1.147,
      "step": 1120
    },
    {
      "epoch": 1.53,
      "learning_rate": 0.0004707207207207207,
      "loss": 1.1233,
      "step": 1130
    },
    {
      "epoch": 1.54,
      "learning_rate": 0.00046996996996997,
      "loss": 1.1032,
      "step": 1140
    },
    {
      "epoch": 1.55,
      "learning_rate": 0.0004692192192192192,
      "loss": 1.1887,
      "step": 1150
    },
    {
      "epoch": 1.57,
      "learning_rate": 0.0004684684684684685,
      "loss": 1.1418,
      "step": 1160
    },
    {
      "epoch": 1.58,
      "learning_rate": 0.0004677177177177177,
      "loss": 1.283,
      "step": 1170
    },
    {
      "epoch": 1.59,
      "learning_rate": 0.000466966966966967,
      "loss": 1.1715,
      "step": 1180
    },
    {
      "epoch": 1.61,
      "learning_rate": 0.00046621621621621625,
      "loss": 1.1116,
      "step": 1190
    },
    {
      "epoch": 1.62,
      "learning_rate": 0.00046546546546546546,
      "loss": 1.1327,
      "step": 1200
    },
    {
      "epoch": 1.63,
      "learning_rate": 0.00046471471471471473,
      "loss": 1.1484,
      "step": 1210
    },
    {
      "epoch": 1.65,
      "learning_rate": 0.00046396396396396395,
      "loss": 1.0976,
      "step": 1220
    },
    {
      "epoch": 1.66,
      "learning_rate": 0.0004632132132132132,
      "loss": 1.2164,
      "step": 1230
    },
    {
      "epoch": 1.67,
      "learning_rate": 0.0004624624624624625,
      "loss": 1.108,
      "step": 1240
    },
    {
      "epoch": 1.69,
      "learning_rate": 0.0004617117117117117,
      "loss": 1.0269,
      "step": 1250
    },
    {
      "epoch": 1.7,
      "learning_rate": 0.000460960960960961,
      "loss": 1.1285,
      "step": 1260
    },
    {
      "epoch": 1.71,
      "learning_rate": 0.0004602102102102102,
      "loss": 1.0542,
      "step": 1270
    },
    {
      "epoch": 1.73,
      "learning_rate": 0.00045945945945945947,
      "loss": 1.1624,
      "step": 1280
    },
    {
      "epoch": 1.74,
      "learning_rate": 0.00045870870870870874,
      "loss": 1.1616,
      "step": 1290
    },
    {
      "epoch": 1.75,
      "learning_rate": 0.00045795795795795796,
      "loss": 1.1036,
      "step": 1300
    },
    {
      "epoch": 1.77,
      "learning_rate": 0.00045720720720720723,
      "loss": 1.0506,
      "step": 1310
    },
    {
      "epoch": 1.78,
      "learning_rate": 0.00045645645645645645,
      "loss": 1.1882,
      "step": 1320
    },
    {
      "epoch": 1.8,
      "learning_rate": 0.0004557057057057057,
      "loss": 1.1138,
      "step": 1330
    },
    {
      "epoch": 1.81,
      "learning_rate": 0.000454954954954955,
      "loss": 1.1566,
      "step": 1340
    },
    {
      "epoch": 1.82,
      "learning_rate": 0.0004542042042042042,
      "loss": 1.1016,
      "step": 1350
    },
    {
      "epoch": 1.84,
      "learning_rate": 0.0004534534534534535,
      "loss": 1.0219,
      "step": 1360
    },
    {
      "epoch": 1.85,
      "learning_rate": 0.0004527027027027027,
      "loss": 1.0964,
      "step": 1370
    },
    {
      "epoch": 1.86,
      "learning_rate": 0.0004519519519519519,
      "loss": 1.0864,
      "step": 1380
    },
    {
      "epoch": 1.88,
      "learning_rate": 0.00045120120120120124,
      "loss": 1.15,
      "step": 1390
    },
    {
      "epoch": 1.89,
      "learning_rate": 0.00045045045045045046,
      "loss": 1.074,
      "step": 1400
    },
    {
      "epoch": 1.9,
      "learning_rate": 0.00044969969969969973,
      "loss": 0.9878,
      "step": 1410
    },
    {
      "epoch": 1.92,
      "learning_rate": 0.00044894894894894895,
      "loss": 1.1312,
      "step": 1420
    },
    {
      "epoch": 1.93,
      "learning_rate": 0.00044819819819819816,
      "loss": 1.0452,
      "step": 1430
    },
    {
      "epoch": 1.94,
      "learning_rate": 0.0004474474474474475,
      "loss": 1.1523,
      "step": 1440
    },
    {
      "epoch": 1.96,
      "learning_rate": 0.0004466966966966967,
      "loss": 1.0347,
      "step": 1450
    },
    {
      "epoch": 1.97,
      "learning_rate": 0.000445945945945946,
      "loss": 1.1487,
      "step": 1460
    },
    {
      "epoch": 1.98,
      "learning_rate": 0.0004451951951951952,
      "loss": 1.1014,
      "step": 1470
    },
    {
      "epoch": 2.0,
      "learning_rate": 0.0004444444444444444,
      "loss": 1.1598,
      "step": 1480
    },
    {
      "epoch": 2.0,
      "eval_accuracy": 0.7715543108621724,
      "eval_f1": 0.7705672329120885,
      "eval_loss": 0.8161230087280273,
      "eval_precision": 0.7970684748506285,
      "eval_recall": 0.7687323574914616,
      "eval_runtime": 192.2102,
      "eval_samples_per_second": 52.016,
      "eval_steps_per_second": 1.93,
      "step": 1481
    },
    {
      "epoch": 2.01,
      "learning_rate": 0.00044369369369369374,
      "loss": 1.0385,
      "step": 1490
    },
    {
      "epoch": 2.02,
      "learning_rate": 0.00044294294294294295,
      "loss": 0.9801,
      "step": 1500
    },
    {
      "epoch": 2.04,
      "learning_rate": 0.0004421921921921922,
      "loss": 0.9433,
      "step": 1510
    },
    {
      "epoch": 2.05,
      "learning_rate": 0.00044144144144144144,
      "loss": 0.9969,
      "step": 1520
    },
    {
      "epoch": 2.07,
      "learning_rate": 0.00044069069069069066,
      "loss": 1.0062,
      "step": 1530
    },
    {
      "epoch": 2.08,
      "learning_rate": 0.00043993993993994,
      "loss": 0.9232,
      "step": 1540
    },
    {
      "epoch": 2.09,
      "learning_rate": 0.0004391891891891892,
      "loss": 1.0435,
      "step": 1550
    },
    {
      "epoch": 2.11,
      "learning_rate": 0.0004384384384384385,
      "loss": 0.9815,
      "step": 1560
    },
    {
      "epoch": 2.12,
      "learning_rate": 0.0004376876876876877,
      "loss": 0.98,
      "step": 1570
    },
    {
      "epoch": 2.13,
      "learning_rate": 0.0004369369369369369,
      "loss": 0.9993,
      "step": 1580
    },
    {
      "epoch": 2.15,
      "learning_rate": 0.00043618618618618623,
      "loss": 0.9791,
      "step": 1590
    },
    {
      "epoch": 2.16,
      "learning_rate": 0.00043543543543543545,
      "loss": 0.9976,
      "step": 1600
    },
    {
      "epoch": 2.17,
      "learning_rate": 0.00043468468468468467,
      "loss": 0.9826,
      "step": 1610
    },
    {
      "epoch": 2.19,
      "learning_rate": 0.00043393393393393394,
      "loss": 0.9983,
      "step": 1620
    },
    {
      "epoch": 2.2,
      "learning_rate": 0.00043318318318318316,
      "loss": 0.9786,
      "step": 1630
    },
    {
      "epoch": 2.21,
      "learning_rate": 0.0004324324324324325,
      "loss": 0.9759,
      "step": 1640
    },
    {
      "epoch": 2.23,
      "learning_rate": 0.0004316816816816817,
      "loss": 0.9812,
      "step": 1650
    },
    {
      "epoch": 2.24,
      "learning_rate": 0.0004309309309309309,
      "loss": 0.9019,
      "step": 1660
    },
    {
      "epoch": 2.25,
      "learning_rate": 0.0004301801801801802,
      "loss": 0.9509,
      "step": 1670
    },
    {
      "epoch": 2.27,
      "learning_rate": 0.0004294294294294294,
      "loss": 0.8406,
      "step": 1680
    },
    {
      "epoch": 2.28,
      "learning_rate": 0.00042867867867867873,
      "loss": 0.8635,
      "step": 1690
    },
    {
      "epoch": 2.29,
      "learning_rate": 0.00042792792792792795,
      "loss": 0.9476,
      "step": 1700
    },
    {
      "epoch": 2.31,
      "learning_rate": 0.00042717717717717717,
      "loss": 0.9808,
      "step": 1710
    },
    {
      "epoch": 2.32,
      "learning_rate": 0.00042642642642642644,
      "loss": 0.8811,
      "step": 1720
    },
    {
      "epoch": 2.34,
      "learning_rate": 0.00042567567567567565,
      "loss": 0.9824,
      "step": 1730
    },
    {
      "epoch": 2.35,
      "learning_rate": 0.000424924924924925,
      "loss": 0.8877,
      "step": 1740
    },
    {
      "epoch": 2.36,
      "learning_rate": 0.0004241741741741742,
      "loss": 0.9078,
      "step": 1750
    },
    {
      "epoch": 2.38,
      "learning_rate": 0.0004234234234234234,
      "loss": 0.9928,
      "step": 1760
    },
    {
      "epoch": 2.39,
      "learning_rate": 0.0004226726726726727,
      "loss": 0.9896,
      "step": 1770
    },
    {
      "epoch": 2.4,
      "learning_rate": 0.0004219219219219219,
      "loss": 0.9167,
      "step": 1780
    },
    {
      "epoch": 2.42,
      "learning_rate": 0.0004211711711711712,
      "loss": 0.9614,
      "step": 1790
    },
    {
      "epoch": 2.43,
      "learning_rate": 0.00042042042042042044,
      "loss": 0.9728,
      "step": 1800
    },
    {
      "epoch": 2.44,
      "learning_rate": 0.00041966966966966966,
      "loss": 0.8913,
      "step": 1810
    },
    {
      "epoch": 2.46,
      "learning_rate": 0.00041891891891891893,
      "loss": 0.9239,
      "step": 1820
    },
    {
      "epoch": 2.47,
      "learning_rate": 0.00041816816816816815,
      "loss": 0.8981,
      "step": 1830
    },
    {
      "epoch": 2.48,
      "learning_rate": 0.0004174174174174174,
      "loss": 0.9159,
      "step": 1840
    },
    {
      "epoch": 2.5,
      "learning_rate": 0.0004166666666666667,
      "loss": 0.9693,
      "step": 1850
    },
    {
      "epoch": 2.51,
      "learning_rate": 0.0004159159159159159,
      "loss": 0.9409,
      "step": 1860
    },
    {
      "epoch": 2.52,
      "learning_rate": 0.0004151651651651652,
      "loss": 0.9313,
      "step": 1870
    },
    {
      "epoch": 2.54,
      "learning_rate": 0.0004144144144144144,
      "loss": 0.8637,
      "step": 1880
    },
    {
      "epoch": 2.55,
      "learning_rate": 0.00041366366366366367,
      "loss": 0.9116,
      "step": 1890
    },
    {
      "epoch": 2.56,
      "learning_rate": 0.00041291291291291294,
      "loss": 0.9368,
      "step": 1900
    },
    {
      "epoch": 2.58,
      "learning_rate": 0.00041216216216216216,
      "loss": 0.9111,
      "step": 1910
    },
    {
      "epoch": 2.59,
      "learning_rate": 0.00041141141141141143,
      "loss": 0.9446,
      "step": 1920
    },
    {
      "epoch": 2.61,
      "learning_rate": 0.00041066066066066065,
      "loss": 0.9185,
      "step": 1930
    },
    {
      "epoch": 2.62,
      "learning_rate": 0.0004099099099099099,
      "loss": 0.8664,
      "step": 1940
    },
    {
      "epoch": 2.63,
      "learning_rate": 0.0004091591591591592,
      "loss": 0.7811,
      "step": 1950
    },
    {
      "epoch": 2.65,
      "learning_rate": 0.0004084084084084084,
      "loss": 0.9265,
      "step": 1960
    },
    {
      "epoch": 2.66,
      "learning_rate": 0.0004076576576576577,
      "loss": 0.83,
      "step": 1970
    },
    {
      "epoch": 2.67,
      "learning_rate": 0.0004069069069069069,
      "loss": 0.8942,
      "step": 1980
    },
    {
      "epoch": 2.69,
      "learning_rate": 0.00040615615615615617,
      "loss": 0.9473,
      "step": 1990
    },
    {
      "epoch": 2.7,
      "learning_rate": 0.00040540540540540544,
      "loss": 0.9547,
      "step": 2000
    },
    {
      "epoch": 2.71,
      "learning_rate": 0.00040465465465465466,
      "loss": 0.9377,
      "step": 2010
    },
    {
      "epoch": 2.73,
      "learning_rate": 0.00040390390390390393,
      "loss": 0.9604,
      "step": 2020
    },
    {
      "epoch": 2.74,
      "learning_rate": 0.00040315315315315314,
      "loss": 0.9484,
      "step": 2030
    },
    {
      "epoch": 2.75,
      "learning_rate": 0.0004024024024024024,
      "loss": 0.8361,
      "step": 2040
    },
    {
      "epoch": 2.77,
      "learning_rate": 0.0004016516516516517,
      "loss": 0.8545,
      "step": 2050
    },
    {
      "epoch": 2.78,
      "learning_rate": 0.0004009009009009009,
      "loss": 0.9045,
      "step": 2060
    },
    {
      "epoch": 2.79,
      "learning_rate": 0.0004001501501501502,
      "loss": 0.8322,
      "step": 2070
    },
    {
      "epoch": 2.81,
      "learning_rate": 0.0003993993993993994,
      "loss": 0.9181,
      "step": 2080
    },
    {
      "epoch": 2.82,
      "learning_rate": 0.00039864864864864866,
      "loss": 0.7966,
      "step": 2090
    },
    {
      "epoch": 2.83,
      "learning_rate": 0.00039789789789789794,
      "loss": 0.9089,
      "step": 2100
    },
    {
      "epoch": 2.85,
      "learning_rate": 0.00039714714714714715,
      "loss": 0.9082,
      "step": 2110
    },
    {
      "epoch": 2.86,
      "learning_rate": 0.0003963963963963964,
      "loss": 0.8908,
      "step": 2120
    },
    {
      "epoch": 2.88,
      "learning_rate": 0.00039564564564564564,
      "loss": 0.8805,
      "step": 2130
    },
    {
      "epoch": 2.89,
      "learning_rate": 0.00039489489489489486,
      "loss": 0.9338,
      "step": 2140
    },
    {
      "epoch": 2.9,
      "learning_rate": 0.0003941441441441442,
      "loss": 0.9174,
      "step": 2150
    },
    {
      "epoch": 2.92,
      "learning_rate": 0.0003933933933933934,
      "loss": 0.902,
      "step": 2160
    },
    {
      "epoch": 2.93,
      "learning_rate": 0.00039264264264264267,
      "loss": 0.8365,
      "step": 2170
    },
    {
      "epoch": 2.94,
      "learning_rate": 0.0003918918918918919,
      "loss": 0.7663,
      "step": 2180
    },
    {
      "epoch": 2.96,
      "learning_rate": 0.0003911411411411411,
      "loss": 0.9336,
      "step": 2190
    },
    {
      "epoch": 2.97,
      "learning_rate": 0.0003903903903903904,
      "loss": 0.8055,
      "step": 2200
    },
    {
      "epoch": 2.98,
      "learning_rate": 0.00038963963963963965,
      "loss": 0.8888,
      "step": 2210
    },
    {
      "epoch": 3.0,
      "learning_rate": 0.0003888888888888889,
      "loss": 0.9069,
      "step": 2220
    },
    {
      "epoch": 3.0,
      "eval_accuracy": 0.8292658531706342,
      "eval_f1": 0.8288337486077575,
      "eval_loss": 0.5952173471450806,
      "eval_precision": 0.842670072902701,
      "eval_recall": 0.8282744379906413,
      "eval_runtime": 192.1316,
      "eval_samples_per_second": 52.037,
      "eval_steps_per_second": 1.931,
      "step": 2222
    },
    {
      "epoch": 3.01,
      "learning_rate": 0.00038813813813813814,
      "loss": 0.7958,
      "step": 2230
    },
    {
      "epoch": 3.02,
      "learning_rate": 0.00038738738738738736,
      "loss": 0.7455,
      "step": 2240
    },
    {
      "epoch": 3.04,
      "learning_rate": 0.0003866366366366366,
      "loss": 0.7151,
      "step": 2250
    },
    {
      "epoch": 3.05,
      "learning_rate": 0.0003858858858858859,
      "loss": 0.7621,
      "step": 2260
    },
    {
      "epoch": 3.06,
      "learning_rate": 0.00038513513513513517,
      "loss": 0.8418,
      "step": 2270
    },
    {
      "epoch": 3.08,
      "learning_rate": 0.0003843843843843844,
      "loss": 0.8065,
      "step": 2280
    },
    {
      "epoch": 3.09,
      "learning_rate": 0.0003836336336336336,
      "loss": 0.7361,
      "step": 2290
    },
    {
      "epoch": 3.1,
      "learning_rate": 0.0003828828828828829,
      "loss": 0.7774,
      "step": 2300
    },
    {
      "epoch": 3.12,
      "learning_rate": 0.00038213213213213215,
      "loss": 0.7262,
      "step": 2310
    },
    {
      "epoch": 3.13,
      "learning_rate": 0.0003813813813813814,
      "loss": 0.7989,
      "step": 2320
    },
    {
      "epoch": 3.15,
      "learning_rate": 0.00038063063063063064,
      "loss": 0.8062,
      "step": 2330
    },
    {
      "epoch": 3.16,
      "learning_rate": 0.00037987987987987985,
      "loss": 0.7957,
      "step": 2340
    },
    {
      "epoch": 3.17,
      "learning_rate": 0.0003791291291291291,
      "loss": 0.7507,
      "step": 2350
    },
    {
      "epoch": 3.19,
      "learning_rate": 0.0003783783783783784,
      "loss": 0.7881,
      "step": 2360
    },
    {
      "epoch": 3.2,
      "learning_rate": 0.00037762762762762767,
      "loss": 0.7048,
      "step": 2370
    },
    {
      "epoch": 3.21,
      "learning_rate": 0.0003768768768768769,
      "loss": 0.8162,
      "step": 2380
    },
    {
      "epoch": 3.23,
      "learning_rate": 0.0003761261261261261,
      "loss": 0.7446,
      "step": 2390
    },
    {
      "epoch": 3.24,
      "learning_rate": 0.00037537537537537537,
      "loss": 0.7904,
      "step": 2400
    },
    {
      "epoch": 3.25,
      "learning_rate": 0.00037462462462462464,
      "loss": 0.7939,
      "step": 2410
    },
    {
      "epoch": 3.27,
      "learning_rate": 0.0003738738738738739,
      "loss": 0.6914,
      "step": 2420
    },
    {
      "epoch": 3.28,
      "learning_rate": 0.00037312312312312313,
      "loss": 0.8431,
      "step": 2430
    },
    {
      "epoch": 3.29,
      "learning_rate": 0.00037237237237237235,
      "loss": 0.775,
      "step": 2440
    },
    {
      "epoch": 3.31,
      "learning_rate": 0.0003716216216216216,
      "loss": 0.7682,
      "step": 2450
    },
    {
      "epoch": 3.32,
      "learning_rate": 0.0003708708708708709,
      "loss": 0.8463,
      "step": 2460
    },
    {
      "epoch": 3.33,
      "learning_rate": 0.00037012012012012016,
      "loss": 0.7268,
      "step": 2470
    },
    {
      "epoch": 3.35,
      "learning_rate": 0.0003693693693693694,
      "loss": 0.7556,
      "step": 2480
    },
    {
      "epoch": 3.36,
      "learning_rate": 0.0003686186186186186,
      "loss": 0.7808,
      "step": 2490
    },
    {
      "epoch": 3.37,
      "learning_rate": 0.00036786786786786787,
      "loss": 0.7615,
      "step": 2500
    },
    {
      "epoch": 3.39,
      "learning_rate": 0.00036711711711711714,
      "loss": 0.798,
      "step": 2510
    },
    {
      "epoch": 3.4,
      "learning_rate": 0.0003663663663663664,
      "loss": 0.7917,
      "step": 2520
    },
    {
      "epoch": 3.42,
      "learning_rate": 0.00036561561561561563,
      "loss": 0.75,
      "step": 2530
    },
    {
      "epoch": 3.43,
      "learning_rate": 0.00036486486486486485,
      "loss": 0.6937,
      "step": 2540
    },
    {
      "epoch": 3.44,
      "learning_rate": 0.0003641141141141141,
      "loss": 0.7988,
      "step": 2550
    },
    {
      "epoch": 3.46,
      "learning_rate": 0.0003633633633633634,
      "loss": 0.7315,
      "step": 2560
    },
    {
      "epoch": 3.47,
      "learning_rate": 0.00036261261261261266,
      "loss": 0.7546,
      "step": 2570
    },
    {
      "epoch": 3.48,
      "learning_rate": 0.0003618618618618619,
      "loss": 0.7216,
      "step": 2580
    },
    {
      "epoch": 3.5,
      "learning_rate": 0.0003611111111111111,
      "loss": 0.7669,
      "step": 2590
    },
    {
      "epoch": 3.51,
      "learning_rate": 0.00036036036036036037,
      "loss": 0.7127,
      "step": 2600
    },
    {
      "epoch": 3.52,
      "learning_rate": 0.00035960960960960964,
      "loss": 0.7755,
      "step": 2610
    },
    {
      "epoch": 3.54,
      "learning_rate": 0.0003588588588588589,
      "loss": 0.8252,
      "step": 2620
    },
    {
      "epoch": 3.55,
      "learning_rate": 0.0003581081081081081,
      "loss": 0.7839,
      "step": 2630
    },
    {
      "epoch": 3.56,
      "learning_rate": 0.00035735735735735734,
      "loss": 0.7111,
      "step": 2640
    },
    {
      "epoch": 3.58,
      "learning_rate": 0.0003566066066066066,
      "loss": 0.6958,
      "step": 2650
    },
    {
      "epoch": 3.59,
      "learning_rate": 0.00035585585585585583,
      "loss": 0.6712,
      "step": 2660
    },
    {
      "epoch": 3.6,
      "learning_rate": 0.00035510510510510516,
      "loss": 0.6692,
      "step": 2670
    },
    {
      "epoch": 3.62,
      "learning_rate": 0.0003543543543543544,
      "loss": 0.7866,
      "step": 2680
    },
    {
      "epoch": 3.63,
      "learning_rate": 0.0003536036036036036,
      "loss": 0.7061,
      "step": 2690
    },
    {
      "epoch": 3.64,
      "learning_rate": 0.00035285285285285286,
      "loss": 0.7742,
      "step": 2700
    },
    {
      "epoch": 3.66,
      "learning_rate": 0.0003521021021021021,
      "loss": 0.6905,
      "step": 2710
    },
    {
      "epoch": 3.67,
      "learning_rate": 0.00035135135135135135,
      "loss": 0.7464,
      "step": 2720
    },
    {
      "epoch": 3.69,
      "learning_rate": 0.0003506006006006006,
      "loss": 0.7855,
      "step": 2730
    },
    {
      "epoch": 3.7,
      "learning_rate": 0.00034984984984984984,
      "loss": 0.7871,
      "step": 2740
    },
    {
      "epoch": 3.71,
      "learning_rate": 0.0003490990990990991,
      "loss": 0.6782,
      "step": 2750
    },
    {
      "epoch": 3.73,
      "learning_rate": 0.00034834834834834833,
      "loss": 0.836,
      "step": 2760
    },
    {
      "epoch": 3.74,
      "learning_rate": 0.0003475975975975976,
      "loss": 0.6404,
      "step": 2770
    },
    {
      "epoch": 3.75,
      "learning_rate": 0.00034684684684684687,
      "loss": 0.8315,
      "step": 2780
    },
    {
      "epoch": 3.77,
      "learning_rate": 0.0003460960960960961,
      "loss": 0.6882,
      "step": 2790
    },
    {
      "epoch": 3.78,
      "learning_rate": 0.00034534534534534536,
      "loss": 0.7388,
      "step": 2800
    },
    {
      "epoch": 3.79,
      "learning_rate": 0.0003445945945945946,
      "loss": 0.8343,
      "step": 2810
    },
    {
      "epoch": 3.81,
      "learning_rate": 0.00034384384384384385,
      "loss": 0.7021,
      "step": 2820
    },
    {
      "epoch": 3.82,
      "learning_rate": 0.0003430930930930931,
      "loss": 0.7739,
      "step": 2830
    },
    {
      "epoch": 3.83,
      "learning_rate": 0.00034234234234234234,
      "loss": 0.7021,
      "step": 2840
    },
    {
      "epoch": 3.85,
      "learning_rate": 0.0003415915915915916,
      "loss": 0.8136,
      "step": 2850
    },
    {
      "epoch": 3.86,
      "learning_rate": 0.0003408408408408408,
      "loss": 0.7634,
      "step": 2860
    },
    {
      "epoch": 3.87,
      "learning_rate": 0.0003400900900900901,
      "loss": 0.7506,
      "step": 2870
    },
    {
      "epoch": 3.89,
      "learning_rate": 0.00033933933933933937,
      "loss": 0.7432,
      "step": 2880
    },
    {
      "epoch": 3.9,
      "learning_rate": 0.0003385885885885886,
      "loss": 0.7378,
      "step": 2890
    },
    {
      "epoch": 3.91,
      "learning_rate": 0.00033783783783783786,
      "loss": 0.6994,
      "step": 2900
    },
    {
      "epoch": 3.93,
      "learning_rate": 0.0003370870870870871,
      "loss": 0.7371,
      "step": 2910
    },
    {
      "epoch": 3.94,
      "learning_rate": 0.00033633633633633635,
      "loss": 0.7055,
      "step": 2920
    },
    {
      "epoch": 3.96,
      "learning_rate": 0.0003355855855855856,
      "loss": 0.703,
      "step": 2930
    },
    {
      "epoch": 3.97,
      "learning_rate": 0.00033483483483483483,
      "loss": 0.7472,
      "step": 2940
    },
    {
      "epoch": 3.98,
      "learning_rate": 0.0003340840840840841,
      "loss": 0.8109,
      "step": 2950
    },
    {
      "epoch": 4.0,
      "learning_rate": 0.0003333333333333333,
      "loss": 0.7519,
      "step": 2960
    },
    {
      "epoch": 4.0,
      "eval_accuracy": 0.8491698339667934,
      "eval_f1": 0.849423792771648,
      "eval_loss": 0.5195841789245605,
      "eval_precision": 0.8611084598890817,
      "eval_recall": 0.8482889408623805,
      "eval_runtime": 190.693,
      "eval_samples_per_second": 52.43,
      "eval_steps_per_second": 1.946,
      "step": 2963
    },
    {
      "epoch": 4.01,
      "learning_rate": 0.0003325825825825826,
      "loss": 0.7232,
      "step": 2970
    },
    {
      "epoch": 4.02,
      "learning_rate": 0.00033183183183183186,
      "loss": 0.5435,
      "step": 2980
    },
    {
      "epoch": 4.04,
      "learning_rate": 0.0003310810810810811,
      "loss": 0.6165,
      "step": 2990
    },
    {
      "epoch": 4.05,
      "learning_rate": 0.00033033033033033035,
      "loss": 0.6642,
      "step": 3000
    },
    {
      "epoch": 4.06,
      "learning_rate": 0.00032957957957957957,
      "loss": 0.6566,
      "step": 3010
    },
    {
      "epoch": 4.08,
      "learning_rate": 0.00032882882882882884,
      "loss": 0.6535,
      "step": 3020
    },
    {
      "epoch": 4.09,
      "learning_rate": 0.0003280780780780781,
      "loss": 0.6825,
      "step": 3030
    },
    {
      "epoch": 4.1,
      "learning_rate": 0.00032732732732732733,
      "loss": 0.5755,
      "step": 3040
    },
    {
      "epoch": 4.12,
      "learning_rate": 0.0003265765765765766,
      "loss": 0.6186,
      "step": 3050
    },
    {
      "epoch": 4.13,
      "learning_rate": 0.0003258258258258258,
      "loss": 0.6469,
      "step": 3060
    },
    {
      "epoch": 4.14,
      "learning_rate": 0.00032507507507507504,
      "loss": 0.6201,
      "step": 3070
    },
    {
      "epoch": 4.16,
      "learning_rate": 0.00032432432432432436,
      "loss": 0.6528,
      "step": 3080
    },
    {
      "epoch": 4.17,
      "learning_rate": 0.0003235735735735736,
      "loss": 0.7014,
      "step": 3090
    },
    {
      "epoch": 4.18,
      "learning_rate": 0.00032282282282282285,
      "loss": 0.6835,
      "step": 3100
    },
    {
      "epoch": 4.2,
      "learning_rate": 0.00032207207207207207,
      "loss": 0.6827,
      "step": 3110
    },
    {
      "epoch": 4.21,
      "learning_rate": 0.0003213213213213213,
      "loss": 0.7095,
      "step": 3120
    },
    {
      "epoch": 4.23,
      "learning_rate": 0.0003205705705705706,
      "loss": 0.6773,
      "step": 3130
    },
    {
      "epoch": 4.24,
      "learning_rate": 0.00031981981981981983,
      "loss": 0.6967,
      "step": 3140
    },
    {
      "epoch": 4.25,
      "learning_rate": 0.0003190690690690691,
      "loss": 0.6751,
      "step": 3150
    },
    {
      "epoch": 4.27,
      "learning_rate": 0.0003183183183183183,
      "loss": 0.6711,
      "step": 3160
    },
    {
      "epoch": 4.28,
      "learning_rate": 0.00031756756756756753,
      "loss": 0.5826,
      "step": 3170
    },
    {
      "epoch": 4.29,
      "learning_rate": 0.00031681681681681686,
      "loss": 0.6481,
      "step": 3180
    },
    {
      "epoch": 4.31,
      "learning_rate": 0.0003160660660660661,
      "loss": 0.6282,
      "step": 3190
    },
    {
      "epoch": 4.32,
      "learning_rate": 0.00031531531531531535,
      "loss": 0.6441,
      "step": 3200
    },
    {
      "epoch": 4.33,
      "learning_rate": 0.00031456456456456456,
      "loss": 0.643,
      "step": 3210
    },
    {
      "epoch": 4.35,
      "learning_rate": 0.0003138138138138138,
      "loss": 0.6681,
      "step": 3220
    },
    {
      "epoch": 4.36,
      "learning_rate": 0.0003130630630630631,
      "loss": 0.642,
      "step": 3230
    },
    {
      "epoch": 4.37,
      "learning_rate": 0.0003123123123123123,
      "loss": 0.6114,
      "step": 3240
    },
    {
      "epoch": 4.39,
      "learning_rate": 0.00031156156156156154,
      "loss": 0.6465,
      "step": 3250
    },
    {
      "epoch": 4.4,
      "learning_rate": 0.0003108108108108108,
      "loss": 0.7339,
      "step": 3260
    },
    {
      "epoch": 4.41,
      "learning_rate": 0.00031006006006006003,
      "loss": 0.6085,
      "step": 3270
    },
    {
      "epoch": 4.43,
      "learning_rate": 0.00030930930930930936,
      "loss": 0.6396,
      "step": 3280
    },
    {
      "epoch": 4.44,
      "learning_rate": 0.00030855855855855857,
      "loss": 0.6864,
      "step": 3290
    },
    {
      "epoch": 4.45,
      "learning_rate": 0.0003078078078078078,
      "loss": 0.6241,
      "step": 3300
    },
    {
      "epoch": 4.47,
      "learning_rate": 0.00030705705705705706,
      "loss": 0.634,
      "step": 3310
    },
    {
      "epoch": 4.48,
      "learning_rate": 0.0003063063063063063,
      "loss": 0.6854,
      "step": 3320
    },
    {
      "epoch": 4.5,
      "learning_rate": 0.0003055555555555556,
      "loss": 0.5872,
      "step": 3330
    },
    {
      "epoch": 4.51,
      "learning_rate": 0.0003048048048048048,
      "loss": 0.5485,
      "step": 3340
    },
    {
      "epoch": 4.52,
      "learning_rate": 0.00030405405405405404,
      "loss": 0.6161,
      "step": 3350
    },
    {
      "epoch": 4.54,
      "learning_rate": 0.0003033033033033033,
      "loss": 0.6059,
      "step": 3360
    },
    {
      "epoch": 4.55,
      "learning_rate": 0.0003025525525525525,
      "loss": 0.6244,
      "step": 3370
    },
    {
      "epoch": 4.56,
      "learning_rate": 0.00030180180180180185,
      "loss": 0.6937,
      "step": 3380
    },
    {
      "epoch": 4.58,
      "learning_rate": 0.00030105105105105107,
      "loss": 0.6506,
      "step": 3390
    },
    {
      "epoch": 4.59,
      "learning_rate": 0.0003003003003003003,
      "loss": 0.6477,
      "step": 3400
    },
    {
      "epoch": 4.6,
      "learning_rate": 0.00029954954954954956,
      "loss": 0.6439,
      "step": 3410
    },
    {
      "epoch": 4.62,
      "learning_rate": 0.0002987987987987988,
      "loss": 0.6016,
      "step": 3420
    },
    {
      "epoch": 4.63,
      "learning_rate": 0.0002980480480480481,
      "loss": 0.5656,
      "step": 3430
    },
    {
      "epoch": 4.64,
      "learning_rate": 0.0002972972972972973,
      "loss": 0.6457,
      "step": 3440
    },
    {
      "epoch": 4.66,
      "learning_rate": 0.00029654654654654654,
      "loss": 0.6378,
      "step": 3450
    },
    {
      "epoch": 4.67,
      "learning_rate": 0.0002957957957957958,
      "loss": 0.6456,
      "step": 3460
    },
    {
      "epoch": 4.68,
      "learning_rate": 0.000295045045045045,
      "loss": 0.6649,
      "step": 3470
    },
    {
      "epoch": 4.7,
      "learning_rate": 0.0002942942942942943,
      "loss": 0.6672,
      "step": 3480
    },
    {
      "epoch": 4.71,
      "learning_rate": 0.00029354354354354357,
      "loss": 0.6567,
      "step": 3490
    },
    {
      "epoch": 4.72,
      "learning_rate": 0.0002927927927927928,
      "loss": 0.6411,
      "step": 3500
    },
    {
      "epoch": 4.74,
      "learning_rate": 0.00029204204204204206,
      "loss": 0.6502,
      "step": 3510
    },
    {
      "epoch": 4.75,
      "learning_rate": 0.00029129129129129127,
      "loss": 0.6637,
      "step": 3520
    },
    {
      "epoch": 4.77,
      "learning_rate": 0.00029054054054054054,
      "loss": 0.6339,
      "step": 3530
    },
    {
      "epoch": 4.78,
      "learning_rate": 0.0002897897897897898,
      "loss": 0.5812,
      "step": 3540
    },
    {
      "epoch": 4.79,
      "learning_rate": 0.00028903903903903903,
      "loss": 0.6396,
      "step": 3550
    },
    {
      "epoch": 4.81,
      "learning_rate": 0.0002882882882882883,
      "loss": 0.6208,
      "step": 3560
    },
    {
      "epoch": 4.82,
      "learning_rate": 0.0002875375375375375,
      "loss": 0.6381,
      "step": 3570
    },
    {
      "epoch": 4.83,
      "learning_rate": 0.0002867867867867868,
      "loss": 0.691,
      "step": 3580
    },
    {
      "epoch": 4.85,
      "learning_rate": 0.00028603603603603606,
      "loss": 0.7211,
      "step": 3590
    },
    {
      "epoch": 4.86,
      "learning_rate": 0.0002852852852852853,
      "loss": 0.616,
      "step": 3600
    },
    {
      "epoch": 4.87,
      "learning_rate": 0.00028453453453453455,
      "loss": 0.5619,
      "step": 3610
    },
    {
      "epoch": 4.89,
      "learning_rate": 0.00028378378378378377,
      "loss": 0.5765,
      "step": 3620
    },
    {
      "epoch": 4.9,
      "learning_rate": 0.00028303303303303304,
      "loss": 0.6436,
      "step": 3630
    },
    {
      "epoch": 4.91,
      "learning_rate": 0.0002822822822822823,
      "loss": 0.6864,
      "step": 3640
    },
    {
      "epoch": 4.93,
      "learning_rate": 0.00028153153153153153,
      "loss": 0.6217,
      "step": 3650
    },
    {
      "epoch": 4.94,
      "learning_rate": 0.0002807807807807808,
      "loss": 0.5852,
      "step": 3660
    },
    {
      "epoch": 4.95,
      "learning_rate": 0.00028003003003003,
      "loss": 0.6185,
      "step": 3670
    },
    {
      "epoch": 4.97,
      "learning_rate": 0.0002792792792792793,
      "loss": 0.6803,
      "step": 3680
    },
    {
      "epoch": 4.98,
      "learning_rate": 0.00027852852852852856,
      "loss": 0.5834,
      "step": 3690
    },
    {
      "epoch": 4.99,
      "learning_rate": 0.0002777777777777778,
      "loss": 0.6357,
      "step": 3700
    },
    {
      "epoch": 5.0,
      "eval_accuracy": 0.8704740948189638,
      "eval_f1": 0.8689097751341385,
      "eval_loss": 0.44387924671173096,
      "eval_precision": 0.8761662335945799,
      "eval_recall": 0.8693479074500065,
      "eval_runtime": 191.3953,
      "eval_samples_per_second": 52.237,
      "eval_steps_per_second": 1.938,
      "step": 3703
    },
    {
      "epoch": 5.01,
      "learning_rate": 0.00027702702702702705,
      "loss": 0.5605,
      "step": 3710
    },
    {
      "epoch": 5.02,
      "learning_rate": 0.00027627627627627627,
      "loss": 0.5468,
      "step": 3720
    },
    {
      "epoch": 5.04,
      "learning_rate": 0.00027552552552552554,
      "loss": 0.5749,
      "step": 3730
    },
    {
      "epoch": 5.05,
      "learning_rate": 0.0002747747747747748,
      "loss": 0.53,
      "step": 3740
    },
    {
      "epoch": 5.06,
      "learning_rate": 0.000274024024024024,
      "loss": 0.5308,
      "step": 3750
    },
    {
      "epoch": 5.08,
      "learning_rate": 0.0002732732732732733,
      "loss": 0.5127,
      "step": 3760
    },
    {
      "epoch": 5.09,
      "learning_rate": 0.0002725225225225225,
      "loss": 0.5424,
      "step": 3770
    },
    {
      "epoch": 5.1,
      "learning_rate": 0.00027177177177177173,
      "loss": 0.5608,
      "step": 3780
    },
    {
      "epoch": 5.12,
      "learning_rate": 0.00027102102102102106,
      "loss": 0.621,
      "step": 3790
    },
    {
      "epoch": 5.13,
      "learning_rate": 0.0002702702702702703,
      "loss": 0.5018,
      "step": 3800
    },
    {
      "epoch": 5.14,
      "learning_rate": 0.00026951951951951955,
      "loss": 0.4879,
      "step": 3810
    },
    {
      "epoch": 5.16,
      "learning_rate": 0.00026876876876876876,
      "loss": 0.4991,
      "step": 3820
    },
    {
      "epoch": 5.17,
      "learning_rate": 0.000268018018018018,
      "loss": 0.5633,
      "step": 3830
    },
    {
      "epoch": 5.18,
      "learning_rate": 0.0002672672672672673,
      "loss": 0.6233,
      "step": 3840
    },
    {
      "epoch": 5.2,
      "learning_rate": 0.0002665165165165165,
      "loss": 0.511,
      "step": 3850
    },
    {
      "epoch": 5.21,
      "learning_rate": 0.0002657657657657658,
      "loss": 0.5036,
      "step": 3860
    },
    {
      "epoch": 5.22,
      "learning_rate": 0.000265015015015015,
      "loss": 0.5826,
      "step": 3870
    },
    {
      "epoch": 5.24,
      "learning_rate": 0.00026426426426426423,
      "loss": 0.5605,
      "step": 3880
    },
    {
      "epoch": 5.25,
      "learning_rate": 0.0002635135135135135,
      "loss": 0.6443,
      "step": 3890
    },
    {
      "epoch": 5.26,
      "learning_rate": 0.00026276276276276277,
      "loss": 0.582,
      "step": 3900
    },
    {
      "epoch": 5.28,
      "learning_rate": 0.00026201201201201204,
      "loss": 0.6232,
      "step": 3910
    },
    {
      "epoch": 5.29,
      "learning_rate": 0.00026126126126126126,
      "loss": 0.5763,
      "step": 3920
    },
    {
      "epoch": 5.31,
      "learning_rate": 0.0002605105105105105,
      "loss": 0.6183,
      "step": 3930
    },
    {
      "epoch": 5.32,
      "learning_rate": 0.00025975975975975975,
      "loss": 0.5533,
      "step": 3940
    },
    {
      "epoch": 5.33,
      "learning_rate": 0.000259009009009009,
      "loss": 0.5633,
      "step": 3950
    },
    {
      "epoch": 5.35,
      "learning_rate": 0.0002582582582582583,
      "loss": 0.544,
      "step": 3960
    },
    {
      "epoch": 5.36,
      "learning_rate": 0.0002575075075075075,
      "loss": 0.5882,
      "step": 3970
    },
    {
      "epoch": 5.37,
      "learning_rate": 0.0002567567567567567,
      "loss": 0.5974,
      "step": 3980
    },
    {
      "epoch": 5.39,
      "learning_rate": 0.000256006006006006,
      "loss": 0.557,
      "step": 3990
    },
    {
      "epoch": 5.4,
      "learning_rate": 0.00025525525525525527,
      "loss": 0.5013,
      "step": 4000
    },
    {
      "epoch": 5.41,
      "learning_rate": 0.00025450450450450454,
      "loss": 0.5785,
      "step": 4010
    },
    {
      "epoch": 5.43,
      "learning_rate": 0.00025375375375375376,
      "loss": 0.558,
      "step": 4020
    },
    {
      "epoch": 5.44,
      "learning_rate": 0.000253003003003003,
      "loss": 0.5429,
      "step": 4030
    },
    {
      "epoch": 5.45,
      "learning_rate": 0.00025225225225225225,
      "loss": 0.5667,
      "step": 4040
    },
    {
      "epoch": 5.47,
      "learning_rate": 0.0002515015015015015,
      "loss": 0.5386,
      "step": 4050
    },
    {
      "epoch": 5.48,
      "learning_rate": 0.0002507507507507508,
      "loss": 0.6074,
      "step": 4060
    },
    {
      "epoch": 5.49,
      "learning_rate": 0.00025,
      "loss": 0.5583,
      "step": 4070
    },
    {
      "epoch": 5.51,
      "learning_rate": 0.0002492492492492492,
      "loss": 0.4637,
      "step": 4080
    },
    {
      "epoch": 5.52,
      "learning_rate": 0.0002484984984984985,
      "loss": 0.5877,
      "step": 4090
    },
    {
      "epoch": 5.53,
      "learning_rate": 0.00024774774774774777,
      "loss": 0.4403,
      "step": 4100
    },
    {
      "epoch": 5.55,
      "learning_rate": 0.00024699699699699704,
      "loss": 0.5379,
      "step": 4110
    },
    {
      "epoch": 5.56,
      "learning_rate": 0.00024624624624624625,
      "loss": 0.5562,
      "step": 4120
    },
    {
      "epoch": 5.58,
      "learning_rate": 0.00024549549549549547,
      "loss": 0.5481,
      "step": 4130
    },
    {
      "epoch": 5.59,
      "learning_rate": 0.00024474474474474474,
      "loss": 0.5422,
      "step": 4140
    },
    {
      "epoch": 5.6,
      "learning_rate": 0.000243993993993994,
      "loss": 0.5545,
      "step": 4150
    },
    {
      "epoch": 5.62,
      "learning_rate": 0.00024324324324324326,
      "loss": 0.5128,
      "step": 4160
    },
    {
      "epoch": 5.63,
      "learning_rate": 0.0002424924924924925,
      "loss": 0.5653,
      "step": 4170
    },
    {
      "epoch": 5.64,
      "learning_rate": 0.00024174174174174175,
      "loss": 0.5782,
      "step": 4180
    },
    {
      "epoch": 5.66,
      "learning_rate": 0.00024099099099099102,
      "loss": 0.5709,
      "step": 4190
    },
    {
      "epoch": 5.67,
      "learning_rate": 0.00024024024024024023,
      "loss": 0.5307,
      "step": 4200
    },
    {
      "epoch": 5.68,
      "learning_rate": 0.00023948948948948948,
      "loss": 0.569,
      "step": 4210
    },
    {
      "epoch": 5.7,
      "learning_rate": 0.00023873873873873875,
      "loss": 0.5939,
      "step": 4220
    },
    {
      "epoch": 5.71,
      "learning_rate": 0.000237987987987988,
      "loss": 0.5127,
      "step": 4230
    },
    {
      "epoch": 5.72,
      "learning_rate": 0.00023723723723723724,
      "loss": 0.5174,
      "step": 4240
    },
    {
      "epoch": 5.74,
      "learning_rate": 0.00023648648648648648,
      "loss": 0.558,
      "step": 4250
    },
    {
      "epoch": 5.75,
      "learning_rate": 0.00023573573573573573,
      "loss": 0.5006,
      "step": 4260
    },
    {
      "epoch": 5.76,
      "learning_rate": 0.000234984984984985,
      "loss": 0.6208,
      "step": 4270
    },
    {
      "epoch": 5.78,
      "learning_rate": 0.00023423423423423424,
      "loss": 0.554,
      "step": 4280
    },
    {
      "epoch": 5.79,
      "learning_rate": 0.0002334834834834835,
      "loss": 0.5183,
      "step": 4290
    },
    {
      "epoch": 5.8,
      "learning_rate": 0.00023273273273273273,
      "loss": 0.5545,
      "step": 4300
    },
    {
      "epoch": 5.82,
      "learning_rate": 0.00023198198198198198,
      "loss": 0.5011,
      "step": 4310
    },
    {
      "epoch": 5.83,
      "learning_rate": 0.00023123123123123125,
      "loss": 0.5286,
      "step": 4320
    },
    {
      "epoch": 5.85,
      "learning_rate": 0.0002304804804804805,
      "loss": 0.4974,
      "step": 4330
    },
    {
      "epoch": 5.86,
      "learning_rate": 0.00022972972972972974,
      "loss": 0.576,
      "step": 4340
    },
    {
      "epoch": 5.87,
      "learning_rate": 0.00022897897897897898,
      "loss": 0.4924,
      "step": 4350
    },
    {
      "epoch": 5.89,
      "learning_rate": 0.00022822822822822822,
      "loss": 0.5501,
      "step": 4360
    },
    {
      "epoch": 5.9,
      "learning_rate": 0.0002274774774774775,
      "loss": 0.5307,
      "step": 4370
    },
    {
      "epoch": 5.91,
      "learning_rate": 0.00022672672672672674,
      "loss": 0.5161,
      "step": 4380
    },
    {
      "epoch": 5.93,
      "learning_rate": 0.00022597597597597596,
      "loss": 0.5153,
      "step": 4390
    },
    {
      "epoch": 5.94,
      "learning_rate": 0.00022522522522522523,
      "loss": 0.5222,
      "step": 4400
    },
    {
      "epoch": 5.95,
      "learning_rate": 0.00022447447447447447,
      "loss": 0.5144,
      "step": 4410
    },
    {
      "epoch": 5.97,
      "learning_rate": 0.00022372372372372374,
      "loss": 0.5002,
      "step": 4420
    },
    {
      "epoch": 5.98,
      "learning_rate": 0.000222972972972973,
      "loss": 0.4556,
      "step": 4430
    },
    {
      "epoch": 5.99,
      "learning_rate": 0.0002222222222222222,
      "loss": 0.5657,
      "step": 4440
    },
    {
      "epoch": 6.0,
      "eval_accuracy": 0.8890778155631126,
      "eval_f1": 0.8884475854159729,
      "eval_loss": 0.405392587184906,
      "eval_precision": 0.8929255500739524,
      "eval_recall": 0.8885232893443815,
      "eval_runtime": 191.4068,
      "eval_samples_per_second": 52.234,
      "eval_steps_per_second": 1.938,
      "step": 4444
    },
    {
      "epoch": 6.01,
      "learning_rate": 0.00022147147147147148,
      "loss": 0.5383,
      "step": 4450
    },
    {
      "epoch": 6.02,
      "learning_rate": 0.00022072072072072072,
      "loss": 0.444,
      "step": 4460
    },
    {
      "epoch": 6.03,
      "learning_rate": 0.00021996996996997,
      "loss": 0.4961,
      "step": 4470
    },
    {
      "epoch": 6.05,
      "learning_rate": 0.00021921921921921924,
      "loss": 0.5372,
      "step": 4480
    },
    {
      "epoch": 6.06,
      "learning_rate": 0.00021846846846846845,
      "loss": 0.4424,
      "step": 4490
    },
    {
      "epoch": 6.07,
      "learning_rate": 0.00021771771771771773,
      "loss": 0.3961,
      "step": 4500
    },
    {
      "epoch": 6.09,
      "learning_rate": 0.00021696696696696697,
      "loss": 0.4882,
      "step": 4510
    },
    {
      "epoch": 6.1,
      "learning_rate": 0.00021621621621621624,
      "loss": 0.4517,
      "step": 4520
    },
    {
      "epoch": 6.12,
      "learning_rate": 0.00021546546546546546,
      "loss": 0.4742,
      "step": 4530
    },
    {
      "epoch": 6.13,
      "learning_rate": 0.0002147147147147147,
      "loss": 0.5285,
      "step": 4540
    },
    {
      "epoch": 6.14,
      "learning_rate": 0.00021396396396396397,
      "loss": 0.4771,
      "step": 4550
    },
    {
      "epoch": 6.16,
      "learning_rate": 0.00021321321321321322,
      "loss": 0.4278,
      "step": 4560
    },
    {
      "epoch": 6.17,
      "learning_rate": 0.0002124624624624625,
      "loss": 0.5205,
      "step": 4570
    },
    {
      "epoch": 6.18,
      "learning_rate": 0.0002117117117117117,
      "loss": 0.5019,
      "step": 4580
    },
    {
      "epoch": 6.2,
      "learning_rate": 0.00021096096096096095,
      "loss": 0.4504,
      "step": 4590
    },
    {
      "epoch": 6.21,
      "learning_rate": 0.00021021021021021022,
      "loss": 0.411,
      "step": 4600
    },
    {
      "epoch": 6.22,
      "learning_rate": 0.00020945945945945947,
      "loss": 0.5114,
      "step": 4610
    },
    {
      "epoch": 6.24,
      "learning_rate": 0.0002087087087087087,
      "loss": 0.4836,
      "step": 4620
    },
    {
      "epoch": 6.25,
      "learning_rate": 0.00020795795795795796,
      "loss": 0.4559,
      "step": 4630
    },
    {
      "epoch": 6.26,
      "learning_rate": 0.0002072072072072072,
      "loss": 0.4264,
      "step": 4640
    },
    {
      "epoch": 6.28,
      "learning_rate": 0.00020645645645645647,
      "loss": 0.4078,
      "step": 4650
    },
    {
      "epoch": 6.29,
      "learning_rate": 0.00020570570570570572,
      "loss": 0.451,
      "step": 4660
    },
    {
      "epoch": 6.3,
      "learning_rate": 0.00020495495495495496,
      "loss": 0.407,
      "step": 4670
    },
    {
      "epoch": 6.32,
      "learning_rate": 0.0002042042042042042,
      "loss": 0.412,
      "step": 4680
    },
    {
      "epoch": 6.33,
      "learning_rate": 0.00020345345345345345,
      "loss": 0.502,
      "step": 4690
    },
    {
      "epoch": 6.34,
      "learning_rate": 0.00020270270270270272,
      "loss": 0.4881,
      "step": 4700
    },
    {
      "epoch": 6.36,
      "learning_rate": 0.00020195195195195196,
      "loss": 0.4685,
      "step": 4710
    },
    {
      "epoch": 6.37,
      "learning_rate": 0.0002012012012012012,
      "loss": 0.4531,
      "step": 4720
    },
    {
      "epoch": 6.39,
      "learning_rate": 0.00020045045045045045,
      "loss": 0.3962,
      "step": 4730
    },
    {
      "epoch": 6.4,
      "learning_rate": 0.0001996996996996997,
      "loss": 0.3741,
      "step": 4740
    },
    {
      "epoch": 6.41,
      "learning_rate": 0.00019894894894894897,
      "loss": 0.4502,
      "step": 4750
    },
    {
      "epoch": 6.43,
      "learning_rate": 0.0001981981981981982,
      "loss": 0.4775,
      "step": 4760
    },
    {
      "epoch": 6.44,
      "learning_rate": 0.00019744744744744743,
      "loss": 0.5319,
      "step": 4770
    },
    {
      "epoch": 6.45,
      "learning_rate": 0.0001966966966966967,
      "loss": 0.5363,
      "step": 4780
    },
    {
      "epoch": 6.47,
      "learning_rate": 0.00019594594594594594,
      "loss": 0.4511,
      "step": 4790
    },
    {
      "epoch": 6.48,
      "learning_rate": 0.0001951951951951952,
      "loss": 0.4314,
      "step": 4800
    },
    {
      "epoch": 6.49,
      "learning_rate": 0.00019444444444444446,
      "loss": 0.405,
      "step": 4810
    },
    {
      "epoch": 6.51,
      "learning_rate": 0.00019369369369369368,
      "loss": 0.4473,
      "step": 4820
    },
    {
      "epoch": 6.52,
      "learning_rate": 0.00019294294294294295,
      "loss": 0.436,
      "step": 4830
    },
    {
      "epoch": 6.53,
      "learning_rate": 0.0001921921921921922,
      "loss": 0.4574,
      "step": 4840
    },
    {
      "epoch": 6.55,
      "learning_rate": 0.00019144144144144144,
      "loss": 0.4293,
      "step": 4850
    },
    {
      "epoch": 6.56,
      "learning_rate": 0.0001906906906906907,
      "loss": 0.3983,
      "step": 4860
    },
    {
      "epoch": 6.57,
      "learning_rate": 0.00018993993993993993,
      "loss": 0.4439,
      "step": 4870
    },
    {
      "epoch": 6.59,
      "learning_rate": 0.0001891891891891892,
      "loss": 0.4613,
      "step": 4880
    },
    {
      "epoch": 6.6,
      "learning_rate": 0.00018843843843843844,
      "loss": 0.4209,
      "step": 4890
    },
    {
      "epoch": 6.61,
      "learning_rate": 0.00018768768768768769,
      "loss": 0.5008,
      "step": 4900
    },
    {
      "epoch": 6.63,
      "learning_rate": 0.00018693693693693696,
      "loss": 0.4341,
      "step": 4910
    },
    {
      "epoch": 6.64,
      "learning_rate": 0.00018618618618618617,
      "loss": 0.4438,
      "step": 4920
    },
    {
      "epoch": 6.66,
      "learning_rate": 0.00018543543543543545,
      "loss": 0.3922,
      "step": 4930
    },
    {
      "epoch": 6.67,
      "learning_rate": 0.0001846846846846847,
      "loss": 0.4661,
      "step": 4940
    },
    {
      "epoch": 6.68,
      "learning_rate": 0.00018393393393393393,
      "loss": 0.4535,
      "step": 4950
    },
    {
      "epoch": 6.7,
      "learning_rate": 0.0001831831831831832,
      "loss": 0.4534,
      "step": 4960
    },
    {
      "epoch": 6.71,
      "learning_rate": 0.00018243243243243242,
      "loss": 0.4782,
      "step": 4970
    },
    {
      "epoch": 6.72,
      "learning_rate": 0.0001816816816816817,
      "loss": 0.4182,
      "step": 4980
    },
    {
      "epoch": 6.74,
      "learning_rate": 0.00018093093093093094,
      "loss": 0.4373,
      "step": 4990
    },
    {
      "epoch": 6.75,
      "learning_rate": 0.00018018018018018018,
      "loss": 0.4867,
      "step": 5000
    },
    {
      "epoch": 6.76,
      "learning_rate": 0.00017942942942942945,
      "loss": 0.4659,
      "step": 5010
    },
    {
      "epoch": 6.78,
      "learning_rate": 0.00017867867867867867,
      "loss": 0.3941,
      "step": 5020
    },
    {
      "epoch": 6.79,
      "learning_rate": 0.00017792792792792792,
      "loss": 0.4212,
      "step": 5030
    },
    {
      "epoch": 6.8,
      "learning_rate": 0.0001771771771771772,
      "loss": 0.4637,
      "step": 5040
    },
    {
      "epoch": 6.82,
      "learning_rate": 0.00017642642642642643,
      "loss": 0.5005,
      "step": 5050
    },
    {
      "epoch": 6.83,
      "learning_rate": 0.00017567567567567568,
      "loss": 0.4785,
      "step": 5060
    },
    {
      "epoch": 6.84,
      "learning_rate": 0.00017492492492492492,
      "loss": 0.4328,
      "step": 5070
    },
    {
      "epoch": 6.86,
      "learning_rate": 0.00017417417417417416,
      "loss": 0.3952,
      "step": 5080
    },
    {
      "epoch": 6.87,
      "learning_rate": 0.00017342342342342344,
      "loss": 0.4419,
      "step": 5090
    },
    {
      "epoch": 6.88,
      "learning_rate": 0.00017267267267267268,
      "loss": 0.4173,
      "step": 5100
    },
    {
      "epoch": 6.9,
      "learning_rate": 0.00017192192192192192,
      "loss": 0.4701,
      "step": 5110
    },
    {
      "epoch": 6.91,
      "learning_rate": 0.00017117117117117117,
      "loss": 0.4804,
      "step": 5120
    },
    {
      "epoch": 6.93,
      "learning_rate": 0.0001704204204204204,
      "loss": 0.3814,
      "step": 5130
    },
    {
      "epoch": 6.94,
      "learning_rate": 0.00016966966966966968,
      "loss": 0.4407,
      "step": 5140
    },
    {
      "epoch": 6.95,
      "learning_rate": 0.00016891891891891893,
      "loss": 0.4275,
      "step": 5150
    },
    {
      "epoch": 6.97,
      "learning_rate": 0.00016816816816816817,
      "loss": 0.4784,
      "step": 5160
    },
    {
      "epoch": 6.98,
      "learning_rate": 0.00016741741741741742,
      "loss": 0.5154,
      "step": 5170
    },
    {
      "epoch": 6.99,
      "learning_rate": 0.00016666666666666666,
      "loss": 0.4628,
      "step": 5180
    },
    {
      "epoch": 7.0,
      "eval_accuracy": 0.9037807561512302,
      "eval_f1": 0.9033003135892885,
      "eval_loss": 0.3493529260158539,
      "eval_precision": 0.9058549926677517,
      "eval_recall": 0.9033230091030984,
      "eval_runtime": 191.6635,
      "eval_samples_per_second": 52.164,
      "eval_steps_per_second": 1.936,
      "step": 5185
    },
    {
      "epoch": 7.01,
      "learning_rate": 0.00016591591591591593,
      "loss": 0.3719,
      "step": 5190
    },
    {
      "epoch": 7.02,
      "learning_rate": 0.00016516516516516518,
      "loss": 0.3562,
      "step": 5200
    },
    {
      "epoch": 7.03,
      "learning_rate": 0.00016441441441441442,
      "loss": 0.4041,
      "step": 5210
    },
    {
      "epoch": 7.05,
      "learning_rate": 0.00016366366366366367,
      "loss": 0.3744,
      "step": 5220
    },
    {
      "epoch": 7.06,
      "learning_rate": 0.0001629129129129129,
      "loss": 0.4728,
      "step": 5230
    },
    {
      "epoch": 7.07,
      "learning_rate": 0.00016216216216216218,
      "loss": 0.4138,
      "step": 5240
    },
    {
      "epoch": 7.09,
      "learning_rate": 0.00016141141141141143,
      "loss": 0.3801,
      "step": 5250
    },
    {
      "epoch": 7.1,
      "learning_rate": 0.00016066066066066064,
      "loss": 0.4113,
      "step": 5260
    },
    {
      "epoch": 7.11,
      "learning_rate": 0.00015990990990990991,
      "loss": 0.388,
      "step": 5270
    },
    {
      "epoch": 7.13,
      "learning_rate": 0.00015915915915915916,
      "loss": 0.4006,
      "step": 5280
    },
    {
      "epoch": 7.14,
      "learning_rate": 0.00015840840840840843,
      "loss": 0.3767,
      "step": 5290
    },
    {
      "epoch": 7.15,
      "learning_rate": 0.00015765765765765767,
      "loss": 0.419,
      "step": 5300
    },
    {
      "epoch": 7.17,
      "learning_rate": 0.0001569069069069069,
      "loss": 0.3563,
      "step": 5310
    },
    {
      "epoch": 7.18,
      "learning_rate": 0.00015615615615615616,
      "loss": 0.4191,
      "step": 5320
    },
    {
      "epoch": 7.2,
      "learning_rate": 0.0001554054054054054,
      "loss": 0.4491,
      "step": 5330
    },
    {
      "epoch": 7.21,
      "learning_rate": 0.00015465465465465468,
      "loss": 0.3764,
      "step": 5340
    },
    {
      "epoch": 7.22,
      "learning_rate": 0.0001539039039039039,
      "loss": 0.3798,
      "step": 5350
    },
    {
      "epoch": 7.24,
      "learning_rate": 0.00015315315315315314,
      "loss": 0.4415,
      "step": 5360
    },
    {
      "epoch": 7.25,
      "learning_rate": 0.0001524024024024024,
      "loss": 0.3818,
      "step": 5370
    },
    {
      "epoch": 7.26,
      "learning_rate": 0.00015165165165165165,
      "loss": 0.3974,
      "step": 5380
    },
    {
      "epoch": 7.28,
      "learning_rate": 0.00015090090090090093,
      "loss": 0.4371,
      "step": 5390
    },
    {
      "epoch": 7.29,
      "learning_rate": 0.00015015015015015014,
      "loss": 0.4014,
      "step": 5400
    },
    {
      "epoch": 7.3,
      "learning_rate": 0.0001493993993993994,
      "loss": 0.3844,
      "step": 5410
    },
    {
      "epoch": 7.32,
      "learning_rate": 0.00014864864864864866,
      "loss": 0.384,
      "step": 5420
    },
    {
      "epoch": 7.33,
      "learning_rate": 0.0001478978978978979,
      "loss": 0.4619,
      "step": 5430
    },
    {
      "epoch": 7.34,
      "learning_rate": 0.00014714714714714715,
      "loss": 0.3962,
      "step": 5440
    },
    {
      "epoch": 7.36,
      "learning_rate": 0.0001463963963963964,
      "loss": 0.4337,
      "step": 5450
    },
    {
      "epoch": 7.37,
      "learning_rate": 0.00014564564564564564,
      "loss": 0.4088,
      "step": 5460
    },
    {
      "epoch": 7.38,
      "learning_rate": 0.0001448948948948949,
      "loss": 0.3786,
      "step": 5470
    },
    {
      "epoch": 7.4,
      "learning_rate": 0.00014414414414414415,
      "loss": 0.4226,
      "step": 5480
    },
    {
      "epoch": 7.41,
      "learning_rate": 0.0001433933933933934,
      "loss": 0.44,
      "step": 5490
    },
    {
      "epoch": 7.42,
      "learning_rate": 0.00014264264264264264,
      "loss": 0.4322,
      "step": 5500
    },
    {
      "epoch": 7.44,
      "learning_rate": 0.00014189189189189188,
      "loss": 0.3269,
      "step": 5510
    },
    {
      "epoch": 7.45,
      "learning_rate": 0.00014114114114114116,
      "loss": 0.347,
      "step": 5520
    },
    {
      "epoch": 7.47,
      "learning_rate": 0.0001403903903903904,
      "loss": 0.4496,
      "step": 5530
    },
    {
      "epoch": 7.48,
      "learning_rate": 0.00013963963963963964,
      "loss": 0.4092,
      "step": 5540
    },
    {
      "epoch": 7.49,
      "learning_rate": 0.0001388888888888889,
      "loss": 0.3484,
      "step": 5550
    },
    {
      "epoch": 7.51,
      "learning_rate": 0.00013813813813813813,
      "loss": 0.4184,
      "step": 5560
    },
    {
      "epoch": 7.52,
      "learning_rate": 0.0001373873873873874,
      "loss": 0.3967,
      "step": 5570
    },
    {
      "epoch": 7.53,
      "learning_rate": 0.00013663663663663665,
      "loss": 0.4125,
      "step": 5580
    },
    {
      "epoch": 7.55,
      "learning_rate": 0.00013588588588588587,
      "loss": 0.401,
      "step": 5590
    },
    {
      "epoch": 7.56,
      "learning_rate": 0.00013513513513513514,
      "loss": 0.4787,
      "step": 5600
    },
    {
      "epoch": 7.57,
      "learning_rate": 0.00013438438438438438,
      "loss": 0.3997,
      "step": 5610
    },
    {
      "epoch": 7.59,
      "learning_rate": 0.00013363363363363365,
      "loss": 0.3598,
      "step": 5620
    },
    {
      "epoch": 7.6,
      "learning_rate": 0.0001328828828828829,
      "loss": 0.3988,
      "step": 5630
    },
    {
      "epoch": 7.61,
      "learning_rate": 0.00013213213213213211,
      "loss": 0.3209,
      "step": 5640
    },
    {
      "epoch": 7.63,
      "learning_rate": 0.00013138138138138139,
      "loss": 0.3528,
      "step": 5650
    },
    {
      "epoch": 7.64,
      "learning_rate": 0.00013063063063063063,
      "loss": 0.4024,
      "step": 5660
    },
    {
      "epoch": 7.65,
      "learning_rate": 0.00012987987987987987,
      "loss": 0.3689,
      "step": 5670
    },
    {
      "epoch": 7.67,
      "learning_rate": 0.00012912912912912915,
      "loss": 0.3908,
      "step": 5680
    },
    {
      "epoch": 7.68,
      "learning_rate": 0.00012837837837837836,
      "loss": 0.4048,
      "step": 5690
    },
    {
      "epoch": 7.69,
      "learning_rate": 0.00012762762762762763,
      "loss": 0.3461,
      "step": 5700
    },
    {
      "epoch": 7.71,
      "learning_rate": 0.00012687687687687688,
      "loss": 0.4064,
      "step": 5710
    },
    {
      "epoch": 7.72,
      "learning_rate": 0.00012612612612612612,
      "loss": 0.3859,
      "step": 5720
    },
    {
      "epoch": 7.74,
      "learning_rate": 0.0001253753753753754,
      "loss": 0.3992,
      "step": 5730
    },
    {
      "epoch": 7.75,
      "learning_rate": 0.0001246246246246246,
      "loss": 0.3116,
      "step": 5740
    },
    {
      "epoch": 7.76,
      "learning_rate": 0.00012387387387387388,
      "loss": 0.3627,
      "step": 5750
    },
    {
      "epoch": 7.78,
      "learning_rate": 0.00012312312312312313,
      "loss": 0.3946,
      "step": 5760
    },
    {
      "epoch": 7.79,
      "learning_rate": 0.00012237237237237237,
      "loss": 0.3297,
      "step": 5770
    },
    {
      "epoch": 7.8,
      "learning_rate": 0.00012162162162162163,
      "loss": 0.4199,
      "step": 5780
    },
    {
      "epoch": 7.82,
      "learning_rate": 0.00012087087087087087,
      "loss": 0.4164,
      "step": 5790
    },
    {
      "epoch": 7.83,
      "learning_rate": 0.00012012012012012012,
      "loss": 0.3763,
      "step": 5800
    },
    {
      "epoch": 7.84,
      "learning_rate": 0.00011936936936936938,
      "loss": 0.3401,
      "step": 5810
    },
    {
      "epoch": 7.86,
      "learning_rate": 0.00011861861861861862,
      "loss": 0.3524,
      "step": 5820
    },
    {
      "epoch": 7.87,
      "learning_rate": 0.00011786786786786786,
      "loss": 0.4263,
      "step": 5830
    },
    {
      "epoch": 7.88,
      "learning_rate": 0.00011711711711711712,
      "loss": 0.3855,
      "step": 5840
    },
    {
      "epoch": 7.9,
      "learning_rate": 0.00011636636636636637,
      "loss": 0.3678,
      "step": 5850
    },
    {
      "epoch": 7.91,
      "learning_rate": 0.00011561561561561562,
      "loss": 0.3067,
      "step": 5860
    },
    {
      "epoch": 7.92,
      "learning_rate": 0.00011486486486486487,
      "loss": 0.3637,
      "step": 5870
    },
    {
      "epoch": 7.94,
      "learning_rate": 0.00011411411411411411,
      "loss": 0.4032,
      "step": 5880
    },
    {
      "epoch": 7.95,
      "learning_rate": 0.00011336336336336337,
      "loss": 0.3832,
      "step": 5890
    },
    {
      "epoch": 7.96,
      "learning_rate": 0.00011261261261261261,
      "loss": 0.4019,
      "step": 5900
    },
    {
      "epoch": 7.98,
      "learning_rate": 0.00011186186186186187,
      "loss": 0.4264,
      "step": 5910
    },
    {
      "epoch": 7.99,
      "learning_rate": 0.0001111111111111111,
      "loss": 0.3256,
      "step": 5920
    },
    {
      "epoch": 8.0,
      "eval_accuracy": 0.9149829965993198,
      "eval_f1": 0.9145293036070032,
      "eval_loss": 0.3138176500797272,
      "eval_precision": 0.9170611788545995,
      "eval_recall": 0.9140792071407026,
      "eval_runtime": 191.5713,
      "eval_samples_per_second": 52.189,
      "eval_steps_per_second": 1.937,
      "step": 5926
    },
    {
      "epoch": 8.01,
      "learning_rate": 0.00011036036036036036,
      "loss": 0.3767,
      "step": 5930
    },
    {
      "epoch": 8.02,
      "learning_rate": 0.00010960960960960962,
      "loss": 0.3465,
      "step": 5940
    },
    {
      "epoch": 8.03,
      "learning_rate": 0.00010885885885885886,
      "loss": 0.3514,
      "step": 5950
    },
    {
      "epoch": 8.05,
      "learning_rate": 0.00010810810810810812,
      "loss": 0.3637,
      "step": 5960
    },
    {
      "epoch": 8.06,
      "learning_rate": 0.00010735735735735735,
      "loss": 0.3834,
      "step": 5970
    },
    {
      "epoch": 8.07,
      "learning_rate": 0.00010660660660660661,
      "loss": 0.2656,
      "step": 5980
    },
    {
      "epoch": 8.09,
      "learning_rate": 0.00010585585585585585,
      "loss": 0.3559,
      "step": 5990
    },
    {
      "epoch": 8.1,
      "learning_rate": 0.00010510510510510511,
      "loss": 0.3491,
      "step": 6000
    },
    {
      "epoch": 8.11,
      "learning_rate": 0.00010435435435435436,
      "loss": 0.4012,
      "step": 6010
    },
    {
      "epoch": 8.13,
      "learning_rate": 0.0001036036036036036,
      "loss": 0.3757,
      "step": 6020
    },
    {
      "epoch": 8.14,
      "learning_rate": 0.00010285285285285286,
      "loss": 0.3678,
      "step": 6030
    },
    {
      "epoch": 8.15,
      "learning_rate": 0.0001021021021021021,
      "loss": 0.3667,
      "step": 6040
    },
    {
      "epoch": 8.17,
      "learning_rate": 0.00010135135135135136,
      "loss": 0.3421,
      "step": 6050
    },
    {
      "epoch": 8.18,
      "learning_rate": 0.0001006006006006006,
      "loss": 0.3924,
      "step": 6060
    },
    {
      "epoch": 8.19,
      "learning_rate": 9.984984984984985e-05,
      "loss": 0.2621,
      "step": 6070
    },
    {
      "epoch": 8.21,
      "learning_rate": 9.90990990990991e-05,
      "loss": 0.3959,
      "step": 6080
    },
    {
      "epoch": 8.22,
      "learning_rate": 9.834834834834835e-05,
      "loss": 0.3191,
      "step": 6090
    },
    {
      "epoch": 8.23,
      "learning_rate": 9.75975975975976e-05,
      "loss": 0.3449,
      "step": 6100
    },
    {
      "epoch": 8.25,
      "learning_rate": 9.684684684684684e-05,
      "loss": 0.3142,
      "step": 6110
    },
    {
      "epoch": 8.26,
      "learning_rate": 9.60960960960961e-05,
      "loss": 0.3093,
      "step": 6120
    },
    {
      "epoch": 8.28,
      "learning_rate": 9.534534534534535e-05,
      "loss": 0.3446,
      "step": 6130
    },
    {
      "epoch": 8.29,
      "learning_rate": 9.45945945945946e-05,
      "loss": 0.2899,
      "step": 6140
    },
    {
      "epoch": 8.3,
      "learning_rate": 9.384384384384384e-05,
      "loss": 0.3068,
      "step": 6150
    },
    {
      "epoch": 8.32,
      "learning_rate": 9.309309309309309e-05,
      "loss": 0.3611,
      "step": 6160
    },
    {
      "epoch": 8.33,
      "learning_rate": 9.234234234234235e-05,
      "loss": 0.2767,
      "step": 6170
    },
    {
      "epoch": 8.34,
      "learning_rate": 9.15915915915916e-05,
      "loss": 0.4126,
      "step": 6180
    },
    {
      "epoch": 8.36,
      "learning_rate": 9.084084084084085e-05,
      "loss": 0.3741,
      "step": 6190
    },
    {
      "epoch": 8.37,
      "learning_rate": 9.009009009009009e-05,
      "loss": 0.3326,
      "step": 6200
    },
    {
      "epoch": 8.38,
      "learning_rate": 8.933933933933934e-05,
      "loss": 0.3034,
      "step": 6210
    },
    {
      "epoch": 8.4,
      "learning_rate": 8.85885885885886e-05,
      "loss": 0.3002,
      "step": 6220
    },
    {
      "epoch": 8.41,
      "learning_rate": 8.783783783783784e-05,
      "loss": 0.3728,
      "step": 6230
    },
    {
      "epoch": 8.42,
      "learning_rate": 8.708708708708708e-05,
      "loss": 0.3149,
      "step": 6240
    },
    {
      "epoch": 8.44,
      "learning_rate": 8.633633633633634e-05,
      "loss": 0.3122,
      "step": 6250
    },
    {
      "epoch": 8.45,
      "learning_rate": 8.558558558558558e-05,
      "loss": 0.3404,
      "step": 6260
    },
    {
      "epoch": 8.46,
      "learning_rate": 8.483483483483484e-05,
      "loss": 0.3521,
      "step": 6270
    },
    {
      "epoch": 8.48,
      "learning_rate": 8.408408408408409e-05,
      "loss": 0.3154,
      "step": 6280
    },
    {
      "epoch": 8.49,
      "learning_rate": 8.333333333333333e-05,
      "loss": 0.3654,
      "step": 6290
    },
    {
      "epoch": 8.5,
      "learning_rate": 8.258258258258259e-05,
      "loss": 0.3591,
      "step": 6300
    },
    {
      "epoch": 8.52,
      "learning_rate": 8.183183183183183e-05,
      "loss": 0.3284,
      "step": 6310
    },
    {
      "epoch": 8.53,
      "learning_rate": 8.108108108108109e-05,
      "loss": 0.2774,
      "step": 6320
    },
    {
      "epoch": 8.55,
      "learning_rate": 8.033033033033032e-05,
      "loss": 0.2813,
      "step": 6330
    },
    {
      "epoch": 8.56,
      "learning_rate": 7.957957957957958e-05,
      "loss": 0.3347,
      "step": 6340
    },
    {
      "epoch": 8.57,
      "learning_rate": 7.882882882882884e-05,
      "loss": 0.2895,
      "step": 6350
    },
    {
      "epoch": 8.59,
      "learning_rate": 7.807807807807808e-05,
      "loss": 0.3634,
      "step": 6360
    },
    {
      "epoch": 8.6,
      "learning_rate": 7.732732732732734e-05,
      "loss": 0.3155,
      "step": 6370
    },
    {
      "epoch": 8.61,
      "learning_rate": 7.657657657657657e-05,
      "loss": 0.3407,
      "step": 6380
    },
    {
      "epoch": 8.63,
      "learning_rate": 7.582582582582583e-05,
      "loss": 0.318,
      "step": 6390
    },
    {
      "epoch": 8.64,
      "learning_rate": 7.507507507507507e-05,
      "loss": 0.2963,
      "step": 6400
    },
    {
      "epoch": 8.65,
      "learning_rate": 7.432432432432433e-05,
      "loss": 0.3049,
      "step": 6410
    },
    {
      "epoch": 8.67,
      "learning_rate": 7.357357357357357e-05,
      "loss": 0.3612,
      "step": 6420
    },
    {
      "epoch": 8.68,
      "learning_rate": 7.282282282282282e-05,
      "loss": 0.3931,
      "step": 6430
    },
    {
      "epoch": 8.69,
      "learning_rate": 7.207207207207208e-05,
      "loss": 0.3213,
      "step": 6440
    },
    {
      "epoch": 8.71,
      "learning_rate": 7.132132132132132e-05,
      "loss": 0.3216,
      "step": 6450
    },
    {
      "epoch": 8.72,
      "learning_rate": 7.057057057057058e-05,
      "loss": 0.341,
      "step": 6460
    },
    {
      "epoch": 8.73,
      "learning_rate": 6.981981981981982e-05,
      "loss": 0.2771,
      "step": 6470
    },
    {
      "epoch": 8.75,
      "learning_rate": 6.906906906906907e-05,
      "loss": 0.3066,
      "step": 6480
    },
    {
      "epoch": 8.76,
      "learning_rate": 6.831831831831832e-05,
      "loss": 0.2938,
      "step": 6490
    },
    {
      "epoch": 8.77,
      "learning_rate": 6.756756756756757e-05,
      "loss": 0.3225,
      "step": 6500
    },
    {
      "epoch": 8.79,
      "learning_rate": 6.681681681681683e-05,
      "loss": 0.2781,
      "step": 6510
    },
    {
      "epoch": 8.8,
      "learning_rate": 6.606606606606606e-05,
      "loss": 0.3331,
      "step": 6520
    },
    {
      "epoch": 8.82,
      "learning_rate": 6.531531531531531e-05,
      "loss": 0.3598,
      "step": 6530
    },
    {
      "epoch": 8.83,
      "learning_rate": 6.456456456456457e-05,
      "loss": 0.325,
      "step": 6540
    },
    {
      "epoch": 8.84,
      "learning_rate": 6.381381381381382e-05,
      "loss": 0.3053,
      "step": 6550
    },
    {
      "epoch": 8.86,
      "learning_rate": 6.306306306306306e-05,
      "loss": 0.2996,
      "step": 6560
    },
    {
      "epoch": 8.87,
      "learning_rate": 6.23123123123123e-05,
      "loss": 0.3505,
      "step": 6570
    },
    {
      "epoch": 8.88,
      "learning_rate": 6.156156156156156e-05,
      "loss": 0.2732,
      "step": 6580
    },
    {
      "epoch": 8.9,
      "learning_rate": 6.0810810810810814e-05,
      "loss": 0.3205,
      "step": 6590
    },
    {
      "epoch": 8.91,
      "learning_rate": 6.006006006006006e-05,
      "loss": 0.3117,
      "step": 6600
    },
    {
      "epoch": 8.92,
      "learning_rate": 5.930930930930931e-05,
      "loss": 0.3402,
      "step": 6610
    },
    {
      "epoch": 8.94,
      "learning_rate": 5.855855855855856e-05,
      "loss": 0.3251,
      "step": 6620
    },
    {
      "epoch": 8.95,
      "learning_rate": 5.780780780780781e-05,
      "loss": 0.3538,
      "step": 6630
    },
    {
      "epoch": 8.96,
      "learning_rate": 5.7057057057057056e-05,
      "loss": 0.3323,
      "step": 6640
    },
    {
      "epoch": 8.98,
      "learning_rate": 5.630630630630631e-05,
      "loss": 0.2546,
      "step": 6650
    },
    {
      "epoch": 8.99,
      "learning_rate": 5.555555555555555e-05,
      "loss": 0.3567,
      "step": 6660
    },
    {
      "epoch": 9.0,
      "eval_accuracy": 0.9256851370274055,
      "eval_f1": 0.9250707611820068,
      "eval_loss": 0.27885687351226807,
      "eval_precision": 0.9262127050820336,
      "eval_recall": 0.9250555525343819,
      "eval_runtime": 194.8139,
      "eval_samples_per_second": 51.321,
      "eval_steps_per_second": 1.904,
      "step": 6666
    },
    {
      "epoch": 9.0,
      "learning_rate": 5.480480480480481e-05,
      "loss": 0.2732,
      "step": 6670
    },
    {
      "epoch": 9.02,
      "learning_rate": 5.405405405405406e-05,
      "loss": 0.316,
      "step": 6680
    },
    {
      "epoch": 9.03,
      "learning_rate": 5.3303303303303305e-05,
      "loss": 0.2812,
      "step": 6690
    },
    {
      "epoch": 9.04,
      "learning_rate": 5.2552552552552556e-05,
      "loss": 0.3061,
      "step": 6700
    },
    {
      "epoch": 9.06,
      "learning_rate": 5.18018018018018e-05,
      "loss": 0.2993,
      "step": 6710
    },
    {
      "epoch": 9.07,
      "learning_rate": 5.105105105105105e-05,
      "loss": 0.323,
      "step": 6720
    },
    {
      "epoch": 9.09,
      "learning_rate": 5.03003003003003e-05,
      "loss": 0.2922,
      "step": 6730
    },
    {
      "epoch": 9.1,
      "learning_rate": 4.954954954954955e-05,
      "loss": 0.3282,
      "step": 6740
    },
    {
      "epoch": 9.11,
      "learning_rate": 4.87987987987988e-05,
      "loss": 0.2847,
      "step": 6750
    },
    {
      "epoch": 9.13,
      "learning_rate": 4.804804804804805e-05,
      "loss": 0.2945,
      "step": 6760
    },
    {
      "epoch": 9.14,
      "learning_rate": 4.72972972972973e-05,
      "loss": 0.2525,
      "step": 6770
    },
    {
      "epoch": 9.15,
      "learning_rate": 4.6546546546546544e-05,
      "loss": 0.2907,
      "step": 6780
    },
    {
      "epoch": 9.17,
      "learning_rate": 4.57957957957958e-05,
      "loss": 0.3036,
      "step": 6790
    },
    {
      "epoch": 9.18,
      "learning_rate": 4.5045045045045046e-05,
      "loss": 0.2495,
      "step": 6800
    },
    {
      "epoch": 9.19,
      "learning_rate": 4.42942942942943e-05,
      "loss": 0.2752,
      "step": 6810
    },
    {
      "epoch": 9.21,
      "learning_rate": 4.354354354354354e-05,
      "loss": 0.3388,
      "step": 6820
    },
    {
      "epoch": 9.22,
      "learning_rate": 4.279279279279279e-05,
      "loss": 0.3166,
      "step": 6830
    },
    {
      "epoch": 9.23,
      "learning_rate": 4.204204204204204e-05,
      "loss": 0.3494,
      "step": 6840
    },
    {
      "epoch": 9.25,
      "learning_rate": 4.1291291291291294e-05,
      "loss": 0.2602,
      "step": 6850
    },
    {
      "epoch": 9.26,
      "learning_rate": 4.0540540540540545e-05,
      "loss": 0.2571,
      "step": 6860
    },
    {
      "epoch": 9.27,
      "learning_rate": 3.978978978978979e-05,
      "loss": 0.3087,
      "step": 6870
    },
    {
      "epoch": 9.29,
      "learning_rate": 3.903903903903904e-05,
      "loss": 0.2927,
      "step": 6880
    },
    {
      "epoch": 9.3,
      "learning_rate": 3.8288288288288285e-05,
      "loss": 0.2868,
      "step": 6890
    },
    {
      "epoch": 9.31,
      "learning_rate": 3.7537537537537536e-05,
      "loss": 0.2722,
      "step": 6900
    },
    {
      "epoch": 9.33,
      "learning_rate": 3.678678678678679e-05,
      "loss": 0.249,
      "step": 6910
    },
    {
      "epoch": 9.34,
      "learning_rate": 3.603603603603604e-05,
      "loss": 0.2773,
      "step": 6920
    },
    {
      "epoch": 9.36,
      "learning_rate": 3.528528528528529e-05,
      "loss": 0.2947,
      "step": 6930
    },
    {
      "epoch": 9.37,
      "learning_rate": 3.453453453453453e-05,
      "loss": 0.3421,
      "step": 6940
    },
    {
      "epoch": 9.38,
      "learning_rate": 3.3783783783783784e-05,
      "loss": 0.2547,
      "step": 6950
    },
    {
      "epoch": 9.4,
      "learning_rate": 3.303303303303303e-05,
      "loss": 0.2803,
      "step": 6960
    },
    {
      "epoch": 9.41,
      "learning_rate": 3.2282282282282286e-05,
      "loss": 0.2675,
      "step": 6970
    },
    {
      "epoch": 9.42,
      "learning_rate": 3.153153153153153e-05,
      "loss": 0.2654,
      "step": 6980
    },
    {
      "epoch": 9.44,
      "learning_rate": 3.078078078078078e-05,
      "loss": 0.2709,
      "step": 6990
    },
    {
      "epoch": 9.45,
      "learning_rate": 3.003003003003003e-05,
      "loss": 0.2359,
      "step": 7000
    },
    {
      "epoch": 9.46,
      "learning_rate": 2.927927927927928e-05,
      "loss": 0.2535,
      "step": 7010
    },
    {
      "epoch": 9.48,
      "learning_rate": 2.8528528528528528e-05,
      "loss": 0.2867,
      "step": 7020
    },
    {
      "epoch": 9.49,
      "learning_rate": 2.7777777777777776e-05,
      "loss": 0.254,
      "step": 7030
    },
    {
      "epoch": 9.5,
      "learning_rate": 2.702702702702703e-05,
      "loss": 0.2382,
      "step": 7040
    },
    {
      "epoch": 9.52,
      "learning_rate": 2.6276276276276278e-05,
      "loss": 0.2711,
      "step": 7050
    },
    {
      "epoch": 9.53,
      "learning_rate": 2.5525525525525525e-05,
      "loss": 0.2785,
      "step": 7060
    },
    {
      "epoch": 9.54,
      "learning_rate": 2.4774774774774777e-05,
      "loss": 0.2695,
      "step": 7070
    },
    {
      "epoch": 9.56,
      "learning_rate": 2.4024024024024024e-05,
      "loss": 0.3143,
      "step": 7080
    },
    {
      "epoch": 9.57,
      "learning_rate": 2.3273273273273272e-05,
      "loss": 0.2781,
      "step": 7090
    },
    {
      "epoch": 9.58,
      "learning_rate": 2.2522522522522523e-05,
      "loss": 0.254,
      "step": 7100
    },
    {
      "epoch": 9.6,
      "learning_rate": 2.177177177177177e-05,
      "loss": 0.2371,
      "step": 7110
    },
    {
      "epoch": 9.61,
      "learning_rate": 2.102102102102102e-05,
      "loss": 0.2558,
      "step": 7120
    },
    {
      "epoch": 9.63,
      "learning_rate": 2.0270270270270273e-05,
      "loss": 0.2748,
      "step": 7130
    },
    {
      "epoch": 9.64,
      "learning_rate": 1.951951951951952e-05,
      "loss": 0.3006,
      "step": 7140
    },
    {
      "epoch": 9.65,
      "learning_rate": 1.8768768768768768e-05,
      "loss": 0.3219,
      "step": 7150
    },
    {
      "epoch": 9.67,
      "learning_rate": 1.801801801801802e-05,
      "loss": 0.3013,
      "step": 7160
    },
    {
      "epoch": 9.68,
      "learning_rate": 1.7267267267267267e-05,
      "loss": 0.2612,
      "step": 7170
    },
    {
      "epoch": 9.69,
      "learning_rate": 1.6516516516516514e-05,
      "loss": 0.2406,
      "step": 7180
    },
    {
      "epoch": 9.71,
      "learning_rate": 1.5765765765765765e-05,
      "loss": 0.2628,
      "step": 7190
    },
    {
      "epoch": 9.72,
      "learning_rate": 1.5015015015015015e-05,
      "loss": 0.2798,
      "step": 7200
    },
    {
      "epoch": 9.73,
      "learning_rate": 1.4264264264264264e-05,
      "loss": 0.2725,
      "step": 7210
    },
    {
      "epoch": 9.75,
      "learning_rate": 1.3513513513513515e-05,
      "loss": 0.3193,
      "step": 7220
    },
    {
      "epoch": 9.76,
      "learning_rate": 1.2762762762762763e-05,
      "loss": 0.277,
      "step": 7230
    },
    {
      "epoch": 9.77,
      "learning_rate": 1.2012012012012012e-05,
      "loss": 0.3349,
      "step": 7240
    },
    {
      "epoch": 9.79,
      "learning_rate": 1.1261261261261261e-05,
      "loss": 0.272,
      "step": 7250
    },
    {
      "epoch": 9.8,
      "learning_rate": 1.051051051051051e-05,
      "loss": 0.3017,
      "step": 7260
    },
    {
      "epoch": 9.81,
      "learning_rate": 9.75975975975976e-06,
      "loss": 0.3224,
      "step": 7270
    },
    {
      "epoch": 9.83,
      "learning_rate": 9.00900900900901e-06,
      "loss": 0.2935,
      "step": 7280
    },
    {
      "epoch": 9.84,
      "learning_rate": 8.258258258258257e-06,
      "loss": 0.3441,
      "step": 7290
    },
    {
      "epoch": 9.85,
      "learning_rate": 7.507507507507507e-06,
      "loss": 0.3263,
      "step": 7300
    },
    {
      "epoch": 9.87,
      "learning_rate": 6.7567567567567575e-06,
      "loss": 0.2503,
      "step": 7310
    },
    {
      "epoch": 9.88,
      "learning_rate": 6.006006006006006e-06,
      "loss": 0.316,
      "step": 7320
    },
    {
      "epoch": 9.9,
      "learning_rate": 5.255255255255255e-06,
      "loss": 0.309,
      "step": 7330
    },
    {
      "epoch": 9.91,
      "learning_rate": 4.504504504504505e-06,
      "loss": 0.2497,
      "step": 7340
    },
    {
      "epoch": 9.92,
      "learning_rate": 3.7537537537537537e-06,
      "loss": 0.206,
      "step": 7350
    },
    {
      "epoch": 9.94,
      "learning_rate": 3.003003003003003e-06,
      "loss": 0.2813,
      "step": 7360
    },
    {
      "epoch": 9.95,
      "learning_rate": 2.2522522522522524e-06,
      "loss": 0.3494,
      "step": 7370
    },
    {
      "epoch": 9.96,
      "learning_rate": 1.5015015015015015e-06,
      "loss": 0.3268,
      "step": 7380
    },
    {
      "epoch": 9.98,
      "learning_rate": 7.507507507507508e-07,
      "loss": 0.2431,
      "step": 7390
    },
    {
      "epoch": 9.99,
      "learning_rate": 0.0,
      "loss": 0.3313,
      "step": 7400
    },
    {
      "epoch": 9.99,
      "eval_accuracy": 0.9310862172434486,
      "eval_f1": 0.9305170890009876,
      "eval_loss": 0.26112696528434753,
      "eval_precision": 0.9311947598825216,
      "eval_recall": 0.9304846180354004,
      "eval_runtime": 191.2068,
      "eval_samples_per_second": 52.289,
      "eval_steps_per_second": 1.94,
      "step": 7400
    },
    {
      "epoch": 9.99,
      "step": 7400,
      "total_flos": 1.8619741375601993e+20,
      "train_loss": 0.7571127768142804,
      "train_runtime": 37998.3887,
      "train_samples_per_second": 21.049,
      "train_steps_per_second": 0.195
    }
  ],
  "logging_steps": 10,
  "max_steps": 7400,
  "num_train_epochs": 10,
  "save_steps": 500,
  "total_flos": 1.8619741375601993e+20,
  "trial_name": null,
  "trial_params": null
}