{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 45.0,
  "global_step": 6300,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.07,
      "learning_rate": 0.00047619047619047614,
      "loss": 0.4551,
      "step": 10
    },
    {
      "epoch": 0.14,
      "learning_rate": 0.0009523809523809523,
      "loss": 0.4547,
      "step": 20
    },
    {
      "epoch": 0.21,
      "learning_rate": 0.0014285714285714284,
      "loss": 0.4544,
      "step": 30
    },
    {
      "epoch": 0.29,
      "learning_rate": 0.0019047619047619045,
      "loss": 0.4511,
      "step": 40
    },
    {
      "epoch": 0.36,
      "learning_rate": 0.0023809523809523807,
      "loss": 0.4473,
      "step": 50
    },
    {
      "epoch": 0.43,
      "learning_rate": 0.0028571428571428567,
      "loss": 0.4409,
      "step": 60
    },
    {
      "epoch": 0.5,
      "learning_rate": 0.003333333333333333,
      "loss": 0.4332,
      "step": 70
    },
    {
      "epoch": 0.57,
      "learning_rate": 0.003809523809523809,
      "loss": 0.4166,
      "step": 80
    },
    {
      "epoch": 0.64,
      "learning_rate": 0.004285714285714285,
      "loss": 0.391,
      "step": 90
    },
    {
      "epoch": 0.71,
      "learning_rate": 0.0047619047619047615,
      "loss": 0.3292,
      "step": 100
    },
    {
      "epoch": 0.79,
      "learning_rate": 0.005238095238095238,
      "loss": 0.2205,
      "step": 110
    },
    {
      "epoch": 0.86,
      "learning_rate": 0.005714285714285713,
      "loss": 0.1464,
      "step": 120
    },
    {
      "epoch": 0.93,
      "learning_rate": 0.00619047619047619,
      "loss": 0.1104,
      "step": 130
    },
    {
      "epoch": 1.0,
      "learning_rate": 0.006666666666666666,
      "loss": 0.0839,
      "step": 140
    },
    {
      "epoch": 1.07,
      "learning_rate": 0.007142857142857142,
      "loss": 0.0637,
      "step": 150
    },
    {
      "epoch": 1.14,
      "learning_rate": 0.007619047619047618,
      "loss": 0.0519,
      "step": 160
    },
    {
      "epoch": 1.21,
      "learning_rate": 0.008095238095238095,
      "loss": 0.0478,
      "step": 170
    },
    {
      "epoch": 1.29,
      "learning_rate": 0.00857142857142857,
      "loss": 0.045,
      "step": 180
    },
    {
      "epoch": 1.36,
      "learning_rate": 0.009047619047619047,
      "loss": 0.0432,
      "step": 190
    },
    {
      "epoch": 1.43,
      "learning_rate": 0.009523809523809523,
      "loss": 0.0399,
      "step": 200
    },
    {
      "epoch": 1.5,
      "learning_rate": 0.009999999999999998,
      "loss": 0.0373,
      "step": 210
    },
    {
      "epoch": 1.57,
      "learning_rate": 0.010476190476190476,
      "loss": 0.038,
      "step": 220
    },
    {
      "epoch": 1.64,
      "learning_rate": 0.010952380952380951,
      "loss": 0.0349,
      "step": 230
    },
    {
      "epoch": 1.71,
      "learning_rate": 0.011428571428571427,
      "loss": 0.0335,
      "step": 240
    },
    {
      "epoch": 1.79,
      "learning_rate": 0.011904761904761904,
      "loss": 0.0344,
      "step": 250
    },
    {
      "epoch": 1.86,
      "learning_rate": 0.01238095238095238,
      "loss": 0.0298,
      "step": 260
    },
    {
      "epoch": 1.93,
      "learning_rate": 0.012857142857142855,
      "loss": 0.0312,
      "step": 270
    },
    {
      "epoch": 2.0,
      "learning_rate": 0.013333333333333332,
      "loss": 0.0287,
      "step": 280
    },
    {
      "epoch": 2.07,
      "learning_rate": 0.013809523809523808,
      "loss": 0.0275,
      "step": 290
    },
    {
      "epoch": 2.14,
      "learning_rate": 0.014285714285714284,
      "loss": 0.0275,
      "step": 300
    },
    {
      "epoch": 2.21,
      "learning_rate": 0.01476190476190476,
      "loss": 0.0258,
      "step": 310
    },
    {
      "epoch": 2.29,
      "learning_rate": 0.015238095238095236,
      "loss": 0.0259,
      "step": 320
    },
    {
      "epoch": 2.36,
      "learning_rate": 0.015714285714285715,
      "loss": 0.0255,
      "step": 330
    },
    {
      "epoch": 2.43,
      "learning_rate": 0.01619047619047619,
      "loss": 0.0242,
      "step": 340
    },
    {
      "epoch": 2.5,
      "learning_rate": 0.016666666666666666,
      "loss": 0.0262,
      "step": 350
    },
    {
      "epoch": 2.57,
      "learning_rate": 0.01714285714285714,
      "loss": 0.0254,
      "step": 360
    },
    {
      "epoch": 2.64,
      "learning_rate": 0.017619047619047618,
      "loss": 0.0232,
      "step": 370
    },
    {
      "epoch": 2.71,
      "learning_rate": 0.018095238095238095,
      "loss": 0.0241,
      "step": 380
    },
    {
      "epoch": 2.79,
      "learning_rate": 0.018571428571428572,
      "loss": 0.0227,
      "step": 390
    },
    {
      "epoch": 2.86,
      "learning_rate": 0.019047619047619046,
      "loss": 0.0242,
      "step": 400
    },
    {
      "epoch": 2.93,
      "learning_rate": 0.019523809523809523,
      "loss": 0.0236,
      "step": 410
    },
    {
      "epoch": 3.0,
      "learning_rate": 0.019999999999999997,
      "loss": 0.023,
      "step": 420
    },
    {
      "epoch": 3.07,
      "learning_rate": 0.020476190476190478,
      "loss": 0.0213,
      "step": 430
    },
    {
      "epoch": 3.14,
      "learning_rate": 0.02095238095238095,
      "loss": 0.0214,
      "step": 440
    },
    {
      "epoch": 3.21,
      "learning_rate": 0.02142857142857143,
      "loss": 0.0219,
      "step": 450
    },
    {
      "epoch": 3.29,
      "learning_rate": 0.021904761904761903,
      "loss": 0.0206,
      "step": 460
    },
    {
      "epoch": 3.36,
      "learning_rate": 0.02238095238095238,
      "loss": 0.0214,
      "step": 470
    },
    {
      "epoch": 3.43,
      "learning_rate": 0.022857142857142854,
      "loss": 0.0213,
      "step": 480
    },
    {
      "epoch": 3.5,
      "learning_rate": 0.023333333333333334,
      "loss": 0.0212,
      "step": 490
    },
    {
      "epoch": 3.57,
      "learning_rate": 0.023809523809523808,
      "loss": 0.0209,
      "step": 500
    },
    {
      "epoch": 3.64,
      "learning_rate": 0.024285714285714285,
      "loss": 0.0198,
      "step": 510
    },
    {
      "epoch": 3.71,
      "learning_rate": 0.02476190476190476,
      "loss": 0.0206,
      "step": 520
    },
    {
      "epoch": 3.79,
      "learning_rate": 0.025238095238095237,
      "loss": 0.0195,
      "step": 530
    },
    {
      "epoch": 3.86,
      "learning_rate": 0.02571428571428571,
      "loss": 0.0223,
      "step": 540
    },
    {
      "epoch": 3.93,
      "learning_rate": 0.02619047619047619,
      "loss": 0.0207,
      "step": 550
    },
    {
      "epoch": 4.0,
      "learning_rate": 0.026666666666666665,
      "loss": 0.0197,
      "step": 560
    },
    {
      "epoch": 4.07,
      "learning_rate": 0.027142857142857142,
      "loss": 0.0209,
      "step": 570
    },
    {
      "epoch": 4.14,
      "learning_rate": 0.027619047619047616,
      "loss": 0.0188,
      "step": 580
    },
    {
      "epoch": 4.21,
      "learning_rate": 0.028095238095238093,
      "loss": 0.0181,
      "step": 590
    },
    {
      "epoch": 4.29,
      "learning_rate": 0.028571428571428567,
      "loss": 0.0184,
      "step": 600
    },
    {
      "epoch": 4.36,
      "learning_rate": 0.029047619047619048,
      "loss": 0.0178,
      "step": 610
    },
    {
      "epoch": 4.43,
      "learning_rate": 0.02952380952380952,
      "loss": 0.0177,
      "step": 620
    },
    {
      "epoch": 4.5,
      "learning_rate": 0.03,
      "loss": 0.0169,
      "step": 630
    },
    {
      "epoch": 4.57,
      "learning_rate": 0.029947089947089944,
      "loss": 0.0169,
      "step": 640
    },
    {
      "epoch": 4.64,
      "learning_rate": 0.029894179894179893,
      "loss": 0.017,
      "step": 650
    },
    {
      "epoch": 4.71,
      "learning_rate": 0.02984126984126984,
      "loss": 0.0162,
      "step": 660
    },
    {
      "epoch": 4.79,
      "learning_rate": 0.029788359788359788,
      "loss": 0.0159,
      "step": 670
    },
    {
      "epoch": 4.86,
      "learning_rate": 0.029735449735449733,
      "loss": 0.0143,
      "step": 680
    },
    {
      "epoch": 4.93,
      "learning_rate": 0.029682539682539682,
      "loss": 0.0127,
      "step": 690
    },
    {
      "epoch": 5.0,
      "learning_rate": 0.029629629629629627,
      "loss": 0.0135,
      "step": 700
    },
    {
      "epoch": 5.07,
      "learning_rate": 0.029576719576719576,
      "loss": 0.0137,
      "step": 710
    },
    {
      "epoch": 5.14,
      "learning_rate": 0.02952380952380952,
      "loss": 0.0124,
      "step": 720
    },
    {
      "epoch": 5.21,
      "learning_rate": 0.02947089947089947,
      "loss": 0.0125,
      "step": 730
    },
    {
      "epoch": 5.29,
      "learning_rate": 0.029417989417989416,
      "loss": 0.0127,
      "step": 740
    },
    {
      "epoch": 5.36,
      "learning_rate": 0.029365079365079365,
      "loss": 0.0118,
      "step": 750
    },
    {
      "epoch": 5.43,
      "learning_rate": 0.02931216931216931,
      "loss": 0.013,
      "step": 760
    },
    {
      "epoch": 5.5,
      "learning_rate": 0.02925925925925926,
      "loss": 0.0116,
      "step": 770
    },
    {
      "epoch": 5.57,
      "learning_rate": 0.029206349206349205,
      "loss": 0.0111,
      "step": 780
    },
    {
      "epoch": 5.64,
      "learning_rate": 0.029153439153439153,
      "loss": 0.0103,
      "step": 790
    },
    {
      "epoch": 5.71,
      "learning_rate": 0.0291005291005291,
      "loss": 0.011,
      "step": 800
    },
    {
      "epoch": 5.79,
      "learning_rate": 0.029047619047619048,
      "loss": 0.0102,
      "step": 810
    },
    {
      "epoch": 5.86,
      "learning_rate": 0.028994708994708993,
      "loss": 0.0097,
      "step": 820
    },
    {
      "epoch": 5.93,
      "learning_rate": 0.028941798941798942,
      "loss": 0.0094,
      "step": 830
    },
    {
      "epoch": 6.0,
      "learning_rate": 0.028888888888888888,
      "loss": 0.0102,
      "step": 840
    },
    {
      "epoch": 6.07,
      "learning_rate": 0.028835978835978836,
      "loss": 0.0091,
      "step": 850
    },
    {
      "epoch": 6.14,
      "learning_rate": 0.028783068783068782,
      "loss": 0.0086,
      "step": 860
    },
    {
      "epoch": 6.21,
      "learning_rate": 0.02873015873015873,
      "loss": 0.0096,
      "step": 870
    },
    {
      "epoch": 6.29,
      "learning_rate": 0.028677248677248676,
      "loss": 0.0091,
      "step": 880
    },
    {
      "epoch": 6.36,
      "learning_rate": 0.02862433862433862,
      "loss": 0.0076,
      "step": 890
    },
    {
      "epoch": 6.43,
      "learning_rate": 0.028571428571428567,
      "loss": 0.009,
      "step": 900
    },
    {
      "epoch": 6.5,
      "learning_rate": 0.028518518518518516,
      "loss": 0.0081,
      "step": 910
    },
    {
      "epoch": 6.57,
      "learning_rate": 0.02846560846560846,
      "loss": 0.0076,
      "step": 920
    },
    {
      "epoch": 6.64,
      "learning_rate": 0.02841269841269841,
      "loss": 0.0078,
      "step": 930
    },
    {
      "epoch": 6.71,
      "learning_rate": 0.028359788359788356,
      "loss": 0.0081,
      "step": 940
    },
    {
      "epoch": 6.79,
      "learning_rate": 0.028306878306878305,
      "loss": 0.0076,
      "step": 950
    },
    {
      "epoch": 6.86,
      "learning_rate": 0.02825396825396825,
      "loss": 0.0071,
      "step": 960
    },
    {
      "epoch": 6.93,
      "learning_rate": 0.0282010582010582,
      "loss": 0.0072,
      "step": 970
    },
    {
      "epoch": 7.0,
      "learning_rate": 0.028148148148148144,
      "loss": 0.0068,
      "step": 980
    },
    {
      "epoch": 7.07,
      "learning_rate": 0.028095238095238093,
      "loss": 0.0071,
      "step": 990
    },
    {
      "epoch": 7.14,
      "learning_rate": 0.02804232804232804,
      "loss": 0.0071,
      "step": 1000
    },
    {
      "epoch": 7.21,
      "learning_rate": 0.027989417989417988,
      "loss": 0.0066,
      "step": 1010
    },
    {
      "epoch": 7.29,
      "learning_rate": 0.027936507936507933,
      "loss": 0.0065,
      "step": 1020
    },
    {
      "epoch": 7.36,
      "learning_rate": 0.027883597883597882,
      "loss": 0.0067,
      "step": 1030
    },
    {
      "epoch": 7.43,
      "learning_rate": 0.027830687830687827,
      "loss": 0.0061,
      "step": 1040
    },
    {
      "epoch": 7.5,
      "learning_rate": 0.027777777777777776,
      "loss": 0.0063,
      "step": 1050
    },
    {
      "epoch": 7.57,
      "learning_rate": 0.02772486772486772,
      "loss": 0.0062,
      "step": 1060
    },
    {
      "epoch": 7.64,
      "learning_rate": 0.02767195767195767,
      "loss": 0.0061,
      "step": 1070
    },
    {
      "epoch": 7.71,
      "learning_rate": 0.027619047619047616,
      "loss": 0.0064,
      "step": 1080
    },
    {
      "epoch": 7.79,
      "learning_rate": 0.027566137566137565,
      "loss": 0.0069,
      "step": 1090
    },
    {
      "epoch": 7.86,
      "learning_rate": 0.02751322751322751,
      "loss": 0.0066,
      "step": 1100
    },
    {
      "epoch": 7.93,
      "learning_rate": 0.02746031746031746,
      "loss": 0.0064,
      "step": 1110
    },
    {
      "epoch": 8.0,
      "learning_rate": 0.027407407407407405,
      "loss": 0.0058,
      "step": 1120
    },
    {
      "epoch": 8.07,
      "learning_rate": 0.027354497354497354,
      "loss": 0.0057,
      "step": 1130
    },
    {
      "epoch": 8.14,
      "learning_rate": 0.0273015873015873,
      "loss": 0.006,
      "step": 1140
    },
    {
      "epoch": 8.21,
      "learning_rate": 0.027248677248677248,
      "loss": 0.0059,
      "step": 1150
    },
    {
      "epoch": 8.29,
      "learning_rate": 0.027195767195767193,
      "loss": 0.0056,
      "step": 1160
    },
    {
      "epoch": 8.36,
      "learning_rate": 0.027142857142857142,
      "loss": 0.0061,
      "step": 1170
    },
    {
      "epoch": 8.43,
      "learning_rate": 0.027089947089947088,
      "loss": 0.0062,
      "step": 1180
    },
    {
      "epoch": 8.5,
      "learning_rate": 0.027037037037037037,
      "loss": 0.0059,
      "step": 1190
    },
    {
      "epoch": 8.57,
      "learning_rate": 0.026984126984126982,
      "loss": 0.0053,
      "step": 1200
    },
    {
      "epoch": 8.64,
      "learning_rate": 0.02693121693121693,
      "loss": 0.0058,
      "step": 1210
    },
    {
      "epoch": 8.71,
      "learning_rate": 0.026878306878306876,
      "loss": 0.005,
      "step": 1220
    },
    {
      "epoch": 8.79,
      "learning_rate": 0.026825396825396825,
      "loss": 0.0049,
      "step": 1230
    },
    {
      "epoch": 8.86,
      "learning_rate": 0.02677248677248677,
      "loss": 0.0053,
      "step": 1240
    },
    {
      "epoch": 8.93,
      "learning_rate": 0.02671957671957672,
      "loss": 0.0045,
      "step": 1250
    },
    {
      "epoch": 9.0,
      "learning_rate": 0.026666666666666665,
      "loss": 0.0048,
      "step": 1260
    },
    {
      "epoch": 9.07,
      "learning_rate": 0.026613756613756614,
      "loss": 0.0046,
      "step": 1270
    },
    {
      "epoch": 9.14,
      "learning_rate": 0.02656084656084656,
      "loss": 0.0051,
      "step": 1280
    },
    {
      "epoch": 9.21,
      "learning_rate": 0.026507936507936508,
      "loss": 0.005,
      "step": 1290
    },
    {
      "epoch": 9.29,
      "learning_rate": 0.026455026455026454,
      "loss": 0.0046,
      "step": 1300
    },
    {
      "epoch": 9.36,
      "learning_rate": 0.026402116402116402,
      "loss": 0.0047,
      "step": 1310
    },
    {
      "epoch": 9.43,
      "learning_rate": 0.026349206349206348,
      "loss": 0.005,
      "step": 1320
    },
    {
      "epoch": 9.5,
      "learning_rate": 0.026296296296296297,
      "loss": 0.0045,
      "step": 1330
    },
    {
      "epoch": 9.57,
      "learning_rate": 0.026243386243386242,
      "loss": 0.0048,
      "step": 1340
    },
    {
      "epoch": 9.64,
      "learning_rate": 0.02619047619047619,
      "loss": 0.004,
      "step": 1350
    },
    {
      "epoch": 9.71,
      "learning_rate": 0.026137566137566137,
      "loss": 0.0039,
      "step": 1360
    },
    {
      "epoch": 9.79,
      "learning_rate": 0.026084656084656085,
      "loss": 0.0037,
      "step": 1370
    },
    {
      "epoch": 9.86,
      "learning_rate": 0.02603174603174603,
      "loss": 0.004,
      "step": 1380
    },
    {
      "epoch": 9.93,
      "learning_rate": 0.02597883597883598,
      "loss": 0.0036,
      "step": 1390
    },
    {
      "epoch": 10.0,
      "learning_rate": 0.025925925925925925,
      "loss": 0.0041,
      "step": 1400
    },
    {
      "epoch": 10.07,
      "learning_rate": 0.02587301587301587,
      "loss": 0.0034,
      "step": 1410
    },
    {
      "epoch": 10.14,
      "learning_rate": 0.025820105820105816,
      "loss": 0.0029,
      "step": 1420
    },
    {
      "epoch": 10.21,
      "learning_rate": 0.025767195767195765,
      "loss": 0.0037,
      "step": 1430
    },
    {
      "epoch": 10.29,
      "learning_rate": 0.02571428571428571,
      "loss": 0.0032,
      "step": 1440
    },
    {
      "epoch": 10.36,
      "learning_rate": 0.02566137566137566,
      "loss": 0.0028,
      "step": 1450
    },
    {
      "epoch": 10.43,
      "learning_rate": 0.025608465608465605,
      "loss": 0.0031,
      "step": 1460
    },
    {
      "epoch": 10.5,
      "learning_rate": 0.025555555555555554,
      "loss": 0.0031,
      "step": 1470
    },
    {
      "epoch": 10.57,
      "learning_rate": 0.0255026455026455,
      "loss": 0.0034,
      "step": 1480
    },
    {
      "epoch": 10.64,
      "learning_rate": 0.025449735449735448,
      "loss": 0.003,
      "step": 1490
    },
    {
      "epoch": 10.71,
      "learning_rate": 0.025396825396825393,
      "loss": 0.0033,
      "step": 1500
    },
    {
      "epoch": 10.79,
      "learning_rate": 0.025343915343915342,
      "loss": 0.003,
      "step": 1510
    },
    {
      "epoch": 10.86,
      "learning_rate": 0.025291005291005288,
      "loss": 0.0029,
      "step": 1520
    },
    {
      "epoch": 10.93,
      "learning_rate": 0.025238095238095237,
      "loss": 0.0031,
      "step": 1530
    },
    {
      "epoch": 11.0,
      "learning_rate": 0.025185185185185182,
      "loss": 0.0027,
      "step": 1540
    },
    {
      "epoch": 11.07,
      "learning_rate": 0.02513227513227513,
      "loss": 0.003,
      "step": 1550
    },
    {
      "epoch": 11.14,
      "learning_rate": 0.025079365079365076,
      "loss": 0.0027,
      "step": 1560
    },
    {
      "epoch": 11.21,
      "learning_rate": 0.025026455026455025,
      "loss": 0.0025,
      "step": 1570
    },
    {
      "epoch": 11.29,
      "learning_rate": 0.02497354497354497,
      "loss": 0.0027,
      "step": 1580
    },
    {
      "epoch": 11.36,
      "learning_rate": 0.02492063492063492,
      "loss": 0.0026,
      "step": 1590
    },
    {
      "epoch": 11.43,
      "learning_rate": 0.024867724867724865,
      "loss": 0.0024,
      "step": 1600
    },
    {
      "epoch": 11.5,
      "learning_rate": 0.024814814814814814,
      "loss": 0.0028,
      "step": 1610
    },
    {
      "epoch": 11.57,
      "learning_rate": 0.02476190476190476,
      "loss": 0.0027,
      "step": 1620
    },
    {
      "epoch": 11.64,
      "learning_rate": 0.024708994708994708,
      "loss": 0.0026,
      "step": 1630
    },
    {
      "epoch": 11.71,
      "learning_rate": 0.024656084656084654,
      "loss": 0.0024,
      "step": 1640
    },
    {
      "epoch": 11.79,
      "learning_rate": 0.024603174603174603,
      "loss": 0.0028,
      "step": 1650
    },
    {
      "epoch": 11.86,
      "learning_rate": 0.024550264550264548,
      "loss": 0.0023,
      "step": 1660
    },
    {
      "epoch": 11.93,
      "learning_rate": 0.024497354497354497,
      "loss": 0.002,
      "step": 1670
    },
    {
      "epoch": 12.0,
      "learning_rate": 0.024444444444444442,
      "loss": 0.0023,
      "step": 1680
    },
    {
      "epoch": 12.07,
      "learning_rate": 0.02439153439153439,
      "loss": 0.0023,
      "step": 1690
    },
    {
      "epoch": 12.14,
      "learning_rate": 0.024338624338624337,
      "loss": 0.0024,
      "step": 1700
    },
    {
      "epoch": 12.21,
      "learning_rate": 0.024285714285714285,
      "loss": 0.0022,
      "step": 1710
    },
    {
      "epoch": 12.29,
      "learning_rate": 0.02423280423280423,
      "loss": 0.002,
      "step": 1720
    },
    {
      "epoch": 12.36,
      "learning_rate": 0.02417989417989418,
      "loss": 0.0022,
      "step": 1730
    },
    {
      "epoch": 12.43,
      "learning_rate": 0.024126984126984125,
      "loss": 0.0022,
      "step": 1740
    },
    {
      "epoch": 12.5,
      "learning_rate": 0.024074074074074074,
      "loss": 0.0022,
      "step": 1750
    },
    {
      "epoch": 12.57,
      "learning_rate": 0.02402116402116402,
      "loss": 0.0025,
      "step": 1760
    },
    {
      "epoch": 12.64,
      "learning_rate": 0.02396825396825397,
      "loss": 0.0021,
      "step": 1770
    },
    {
      "epoch": 12.71,
      "learning_rate": 0.023915343915343914,
      "loss": 0.0022,
      "step": 1780
    },
    {
      "epoch": 12.79,
      "learning_rate": 0.023862433862433863,
      "loss": 0.0019,
      "step": 1790
    },
    {
      "epoch": 12.86,
      "learning_rate": 0.023809523809523808,
      "loss": 0.0023,
      "step": 1800
    },
    {
      "epoch": 12.93,
      "learning_rate": 0.023756613756613757,
      "loss": 0.002,
      "step": 1810
    },
    {
      "epoch": 13.0,
      "learning_rate": 0.023703703703703703,
      "loss": 0.0018,
      "step": 1820
    },
    {
      "epoch": 13.07,
      "learning_rate": 0.02365079365079365,
      "loss": 0.002,
      "step": 1830
    },
    {
      "epoch": 13.14,
      "learning_rate": 0.023597883597883597,
      "loss": 0.0021,
      "step": 1840
    },
    {
      "epoch": 13.21,
      "learning_rate": 0.023544973544973546,
      "loss": 0.002,
      "step": 1850
    },
    {
      "epoch": 13.29,
      "learning_rate": 0.02349206349206349,
      "loss": 0.0018,
      "step": 1860
    },
    {
      "epoch": 13.36,
      "learning_rate": 0.02343915343915344,
      "loss": 0.0018,
      "step": 1870
    },
    {
      "epoch": 13.43,
      "learning_rate": 0.023386243386243386,
      "loss": 0.002,
      "step": 1880
    },
    {
      "epoch": 13.5,
      "learning_rate": 0.023333333333333334,
      "loss": 0.0017,
      "step": 1890
    },
    {
      "epoch": 13.57,
      "learning_rate": 0.02328042328042328,
      "loss": 0.0018,
      "step": 1900
    },
    {
      "epoch": 13.64,
      "learning_rate": 0.02322751322751323,
      "loss": 0.002,
      "step": 1910
    },
    {
      "epoch": 13.71,
      "learning_rate": 0.023174603174603174,
      "loss": 0.0019,
      "step": 1920
    },
    {
      "epoch": 13.79,
      "learning_rate": 0.02312169312169312,
      "loss": 0.0019,
      "step": 1930
    },
    {
      "epoch": 13.86,
      "learning_rate": 0.023068783068783065,
      "loss": 0.002,
      "step": 1940
    },
    {
      "epoch": 13.93,
      "learning_rate": 0.023015873015873014,
      "loss": 0.0017,
      "step": 1950
    },
    {
      "epoch": 14.0,
      "learning_rate": 0.02296296296296296,
      "loss": 0.0015,
      "step": 1960
    },
    {
      "epoch": 14.07,
      "learning_rate": 0.022910052910052908,
      "loss": 0.0017,
      "step": 1970
    },
    {
      "epoch": 14.14,
      "learning_rate": 0.022857142857142854,
      "loss": 0.0018,
      "step": 1980
    },
    {
      "epoch": 14.21,
      "learning_rate": 0.022804232804232803,
      "loss": 0.0019,
      "step": 1990
    },
    {
      "epoch": 14.29,
      "learning_rate": 0.022751322751322748,
      "loss": 0.0019,
      "step": 2000
    },
    {
      "epoch": 14.36,
      "learning_rate": 0.022698412698412697,
      "loss": 0.0018,
      "step": 2010
    },
    {
      "epoch": 14.43,
      "learning_rate": 0.022645502645502642,
      "loss": 0.0018,
      "step": 2020
    },
    {
      "epoch": 14.5,
      "learning_rate": 0.02259259259259259,
      "loss": 0.0018,
      "step": 2030
    },
    {
      "epoch": 14.57,
      "learning_rate": 0.022539682539682537,
      "loss": 0.0017,
      "step": 2040
    },
    {
      "epoch": 14.64,
      "learning_rate": 0.022486772486772486,
      "loss": 0.0019,
      "step": 2050
    },
    {
      "epoch": 14.71,
      "learning_rate": 0.02243386243386243,
      "loss": 0.0018,
      "step": 2060
    },
    {
      "epoch": 14.79,
      "learning_rate": 0.02238095238095238,
      "loss": 0.0015,
      "step": 2070
    },
    {
      "epoch": 14.86,
      "learning_rate": 0.022328042328042325,
      "loss": 0.0018,
      "step": 2080
    },
    {
      "epoch": 14.93,
      "learning_rate": 0.022275132275132274,
      "loss": 0.0017,
      "step": 2090
    },
    {
      "epoch": 15.0,
      "learning_rate": 0.02222222222222222,
      "loss": 0.0015,
      "step": 2100
    },
    {
      "epoch": 15.07,
      "learning_rate": 0.02216931216931217,
      "loss": 0.0016,
      "step": 2110
    },
    {
      "epoch": 15.14,
      "learning_rate": 0.022116402116402114,
      "loss": 0.0016,
      "step": 2120
    },
    {
      "epoch": 15.21,
      "learning_rate": 0.022063492063492063,
      "loss": 0.0016,
      "step": 2130
    },
    {
      "epoch": 15.29,
      "learning_rate": 0.022010582010582008,
      "loss": 0.0016,
      "step": 2140
    },
    {
      "epoch": 15.36,
      "learning_rate": 0.021957671957671957,
      "loss": 0.0017,
      "step": 2150
    },
    {
      "epoch": 15.43,
      "learning_rate": 0.021904761904761903,
      "loss": 0.0021,
      "step": 2160
    },
    {
      "epoch": 15.5,
      "learning_rate": 0.02185185185185185,
      "loss": 0.0018,
      "step": 2170
    },
    {
      "epoch": 15.57,
      "learning_rate": 0.021798941798941797,
      "loss": 0.0017,
      "step": 2180
    },
    {
      "epoch": 15.64,
      "learning_rate": 0.021746031746031746,
      "loss": 0.0018,
      "step": 2190
    },
    {
      "epoch": 15.71,
      "learning_rate": 0.02169312169312169,
      "loss": 0.0017,
      "step": 2200
    },
    {
      "epoch": 15.79,
      "learning_rate": 0.02164021164021164,
      "loss": 0.0015,
      "step": 2210
    },
    {
      "epoch": 15.86,
      "learning_rate": 0.021587301587301586,
      "loss": 0.0016,
      "step": 2220
    },
    {
      "epoch": 15.93,
      "learning_rate": 0.021534391534391534,
      "loss": 0.0016,
      "step": 2230
    },
    {
      "epoch": 16.0,
      "learning_rate": 0.02148148148148148,
      "loss": 0.0015,
      "step": 2240
    },
    {
      "epoch": 16.07,
      "learning_rate": 0.02142857142857143,
      "loss": 0.0016,
      "step": 2250
    },
    {
      "epoch": 16.14,
      "learning_rate": 0.021375661375661374,
      "loss": 0.0016,
      "step": 2260
    },
    {
      "epoch": 16.21,
      "learning_rate": 0.021322751322751323,
      "loss": 0.0015,
      "step": 2270
    },
    {
      "epoch": 16.29,
      "learning_rate": 0.02126984126984127,
      "loss": 0.0017,
      "step": 2280
    },
    {
      "epoch": 16.36,
      "learning_rate": 0.021216931216931217,
      "loss": 0.0017,
      "step": 2290
    },
    {
      "epoch": 16.43,
      "learning_rate": 0.021164021164021163,
      "loss": 0.0015,
      "step": 2300
    },
    {
      "epoch": 16.5,
      "learning_rate": 0.021111111111111112,
      "loss": 0.0014,
      "step": 2310
    },
    {
      "epoch": 16.57,
      "learning_rate": 0.021058201058201057,
      "loss": 0.0016,
      "step": 2320
    },
    {
      "epoch": 16.64,
      "learning_rate": 0.021005291005291006,
      "loss": 0.0015,
      "step": 2330
    },
    {
      "epoch": 16.71,
      "learning_rate": 0.02095238095238095,
      "loss": 0.0015,
      "step": 2340
    },
    {
      "epoch": 16.79,
      "learning_rate": 0.0208994708994709,
      "loss": 0.0017,
      "step": 2350
    },
    {
      "epoch": 16.86,
      "learning_rate": 0.020846560846560846,
      "loss": 0.0015,
      "step": 2360
    },
    {
      "epoch": 16.93,
      "learning_rate": 0.020793650793650795,
      "loss": 0.0015,
      "step": 2370
    },
    {
      "epoch": 17.0,
      "learning_rate": 0.02074074074074074,
      "loss": 0.0016,
      "step": 2380
    },
    {
      "epoch": 17.07,
      "learning_rate": 0.02068783068783069,
      "loss": 0.0015,
      "step": 2390
    },
    {
      "epoch": 17.14,
      "learning_rate": 0.020634920634920634,
      "loss": 0.0015,
      "step": 2400
    },
    {
      "epoch": 17.21,
      "learning_rate": 0.020582010582010583,
      "loss": 0.0017,
      "step": 2410
    },
    {
      "epoch": 17.29,
      "learning_rate": 0.02052910052910053,
      "loss": 0.0017,
      "step": 2420
    },
    {
      "epoch": 17.36,
      "learning_rate": 0.020476190476190478,
      "loss": 0.0016,
      "step": 2430
    },
    {
      "epoch": 17.43,
      "learning_rate": 0.020423280423280423,
      "loss": 0.0016,
      "step": 2440
    },
    {
      "epoch": 17.5,
      "learning_rate": 0.02037037037037037,
      "loss": 0.0016,
      "step": 2450
    },
    {
      "epoch": 17.57,
      "learning_rate": 0.020317460317460314,
      "loss": 0.0014,
      "step": 2460
    },
    {
      "epoch": 17.64,
      "learning_rate": 0.020264550264550263,
      "loss": 0.0014,
      "step": 2470
    },
    {
      "epoch": 17.71,
      "learning_rate": 0.02021164021164021,
      "loss": 0.0015,
      "step": 2480
    },
    {
      "epoch": 17.79,
      "learning_rate": 0.020158730158730157,
      "loss": 0.0015,
      "step": 2490
    },
    {
      "epoch": 17.86,
      "learning_rate": 0.020105820105820103,
      "loss": 0.0015,
      "step": 2500
    },
    {
      "epoch": 17.93,
      "learning_rate": 0.02005291005291005,
      "loss": 0.0018,
      "step": 2510
    },
    {
      "epoch": 18.0,
      "learning_rate": 0.019999999999999997,
      "loss": 0.0014,
      "step": 2520
    },
    {
      "epoch": 18.07,
      "learning_rate": 0.019947089947089946,
      "loss": 0.0016,
      "step": 2530
    },
    {
      "epoch": 18.14,
      "learning_rate": 0.01989417989417989,
      "loss": 0.0015,
      "step": 2540
    },
    {
      "epoch": 18.21,
      "learning_rate": 0.01984126984126984,
      "loss": 0.0015,
      "step": 2550
    },
    {
      "epoch": 18.29,
      "learning_rate": 0.019788359788359786,
      "loss": 0.0015,
      "step": 2560
    },
    {
      "epoch": 18.36,
      "learning_rate": 0.019735449735449734,
      "loss": 0.0015,
      "step": 2570
    },
    {
      "epoch": 18.43,
      "learning_rate": 0.01968253968253968,
      "loss": 0.0014,
      "step": 2580
    },
    {
      "epoch": 18.5,
      "learning_rate": 0.01962962962962963,
      "loss": 0.0014,
      "step": 2590
    },
    {
      "epoch": 18.57,
      "learning_rate": 0.019576719576719574,
      "loss": 0.0015,
      "step": 2600
    },
    {
      "epoch": 18.64,
      "learning_rate": 0.019523809523809523,
      "loss": 0.0017,
      "step": 2610
    },
    {
      "epoch": 18.71,
      "learning_rate": 0.01947089947089947,
      "loss": 0.0015,
      "step": 2620
    },
    {
      "epoch": 18.79,
      "learning_rate": 0.019417989417989417,
      "loss": 0.0014,
      "step": 2630
    },
    {
      "epoch": 18.86,
      "learning_rate": 0.019365079365079363,
      "loss": 0.0015,
      "step": 2640
    },
    {
      "epoch": 18.93,
      "learning_rate": 0.019312169312169312,
      "loss": 0.0014,
      "step": 2650
    },
    {
      "epoch": 19.0,
      "learning_rate": 0.019259259259259257,
      "loss": 0.0014,
      "step": 2660
    },
    {
      "epoch": 19.07,
      "learning_rate": 0.019206349206349206,
      "loss": 0.0013,
      "step": 2670
    },
    {
      "epoch": 19.14,
      "learning_rate": 0.01915343915343915,
      "loss": 0.0014,
      "step": 2680
    },
    {
      "epoch": 19.21,
      "learning_rate": 0.0191005291005291,
      "loss": 0.0015,
      "step": 2690
    },
    {
      "epoch": 19.29,
      "learning_rate": 0.019047619047619046,
      "loss": 0.0014,
      "step": 2700
    },
    {
      "epoch": 19.36,
      "learning_rate": 0.018994708994708995,
      "loss": 0.0015,
      "step": 2710
    },
    {
      "epoch": 19.43,
      "learning_rate": 0.01894179894179894,
      "loss": 0.0016,
      "step": 2720
    },
    {
      "epoch": 19.5,
      "learning_rate": 0.01888888888888889,
      "loss": 0.0015,
      "step": 2730
    },
    {
      "epoch": 19.57,
      "learning_rate": 0.018835978835978835,
      "loss": 0.0014,
      "step": 2740
    },
    {
      "epoch": 19.64,
      "learning_rate": 0.018783068783068783,
      "loss": 0.0014,
      "step": 2750
    },
    {
      "epoch": 19.71,
      "learning_rate": 0.01873015873015873,
      "loss": 0.0015,
      "step": 2760
    },
    {
      "epoch": 19.79,
      "learning_rate": 0.018677248677248678,
      "loss": 0.0014,
      "step": 2770
    },
    {
      "epoch": 19.86,
      "learning_rate": 0.018624338624338623,
      "loss": 0.0016,
      "step": 2780
    },
    {
      "epoch": 19.93,
      "learning_rate": 0.018571428571428572,
      "loss": 0.0014,
      "step": 2790
    },
    {
      "epoch": 20.0,
      "learning_rate": 0.018518518518518517,
      "loss": 0.0014,
      "step": 2800
    },
    {
      "epoch": 20.07,
      "learning_rate": 0.018465608465608466,
      "loss": 0.0014,
      "step": 2810
    },
    {
      "epoch": 20.14,
      "learning_rate": 0.018412698412698412,
      "loss": 0.0013,
      "step": 2820
    },
    {
      "epoch": 20.21,
      "learning_rate": 0.01835978835978836,
      "loss": 0.0015,
      "step": 2830
    },
    {
      "epoch": 20.29,
      "learning_rate": 0.018306878306878306,
      "loss": 0.0014,
      "step": 2840
    },
    {
      "epoch": 20.36,
      "learning_rate": 0.018253968253968255,
      "loss": 0.0016,
      "step": 2850
    },
    {
      "epoch": 20.43,
      "learning_rate": 0.0182010582010582,
      "loss": 0.0014,
      "step": 2860
    },
    {
      "epoch": 20.5,
      "learning_rate": 0.01814814814814815,
      "loss": 0.0015,
      "step": 2870
    },
    {
      "epoch": 20.57,
      "learning_rate": 0.018095238095238095,
      "loss": 0.0015,
      "step": 2880
    },
    {
      "epoch": 20.64,
      "learning_rate": 0.018042328042328044,
      "loss": 0.0014,
      "step": 2890
    },
    {
      "epoch": 20.71,
      "learning_rate": 0.01798941798941799,
      "loss": 0.0014,
      "step": 2900
    },
    {
      "epoch": 20.79,
      "learning_rate": 0.017936507936507938,
      "loss": 0.0014,
      "step": 2910
    },
    {
      "epoch": 20.86,
      "learning_rate": 0.017883597883597883,
      "loss": 0.0014,
      "step": 2920
    },
    {
      "epoch": 20.93,
      "learning_rate": 0.017830687830687832,
      "loss": 0.0016,
      "step": 2930
    },
    {
      "epoch": 21.0,
      "learning_rate": 0.017777777777777778,
      "loss": 0.0014,
      "step": 2940
    },
    {
      "epoch": 21.07,
      "learning_rate": 0.017724867724867723,
      "loss": 0.0015,
      "step": 2950
    },
    {
      "epoch": 21.14,
      "learning_rate": 0.01767195767195767,
      "loss": 0.0014,
      "step": 2960
    },
    {
      "epoch": 21.21,
      "learning_rate": 0.017619047619047618,
      "loss": 0.0014,
      "step": 2970
    },
    {
      "epoch": 21.29,
      "learning_rate": 0.017566137566137563,
      "loss": 0.0012,
      "step": 2980
    },
    {
      "epoch": 21.36,
      "learning_rate": 0.017513227513227512,
      "loss": 0.0014,
      "step": 2990
    },
    {
      "epoch": 21.43,
      "learning_rate": 0.017460317460317457,
      "loss": 0.0014,
      "step": 3000
    },
    {
      "epoch": 21.5,
      "learning_rate": 0.017407407407407406,
      "loss": 0.0013,
      "step": 3010
    },
    {
      "epoch": 21.57,
      "learning_rate": 0.01735449735449735,
      "loss": 0.0014,
      "step": 3020
    },
    {
      "epoch": 21.64,
      "learning_rate": 0.0173015873015873,
      "loss": 0.0014,
      "step": 3030
    },
    {
      "epoch": 21.71,
      "learning_rate": 0.017248677248677246,
      "loss": 0.0013,
      "step": 3040
    },
    {
      "epoch": 21.79,
      "learning_rate": 0.017195767195767195,
      "loss": 0.0013,
      "step": 3050
    },
    {
      "epoch": 21.86,
      "learning_rate": 0.01714285714285714,
      "loss": 0.0013,
      "step": 3060
    },
    {
      "epoch": 21.93,
      "learning_rate": 0.01708994708994709,
      "loss": 0.0013,
      "step": 3070
    },
    {
      "epoch": 22.0,
      "learning_rate": 0.017037037037037035,
      "loss": 0.0014,
      "step": 3080
    },
    {
      "epoch": 22.07,
      "learning_rate": 0.016984126984126983,
      "loss": 0.0012,
      "step": 3090
    },
    {
      "epoch": 22.14,
      "learning_rate": 0.01693121693121693,
      "loss": 0.0013,
      "step": 3100
    },
    {
      "epoch": 22.21,
      "learning_rate": 0.016878306878306878,
      "loss": 0.0014,
      "step": 3110
    },
    {
      "epoch": 22.29,
      "learning_rate": 0.016825396825396823,
      "loss": 0.0013,
      "step": 3120
    },
    {
      "epoch": 22.36,
      "learning_rate": 0.016772486772486772,
      "loss": 0.0013,
      "step": 3130
    },
    {
      "epoch": 22.43,
      "learning_rate": 0.016719576719576718,
      "loss": 0.0013,
      "step": 3140
    },
    {
      "epoch": 22.5,
      "learning_rate": 0.016666666666666666,
      "loss": 0.0013,
      "step": 3150
    },
    {
      "epoch": 22.57,
      "learning_rate": 0.016613756613756612,
      "loss": 0.0014,
      "step": 3160
    },
    {
      "epoch": 22.64,
      "learning_rate": 0.01656084656084656,
      "loss": 0.0012,
      "step": 3170
    },
    {
      "epoch": 22.71,
      "learning_rate": 0.016507936507936506,
      "loss": 0.0014,
      "step": 3180
    },
    {
      "epoch": 22.79,
      "learning_rate": 0.016455026455026455,
      "loss": 0.0013,
      "step": 3190
    },
    {
      "epoch": 22.86,
      "learning_rate": 0.0164021164021164,
      "loss": 0.0014,
      "step": 3200
    },
    {
      "epoch": 22.93,
      "learning_rate": 0.01634920634920635,
      "loss": 0.0013,
      "step": 3210
    },
    {
      "epoch": 23.0,
      "learning_rate": 0.016296296296296295,
      "loss": 0.0013,
      "step": 3220
    },
    {
      "epoch": 23.07,
      "learning_rate": 0.016243386243386244,
      "loss": 0.0012,
      "step": 3230
    },
    {
      "epoch": 23.14,
      "learning_rate": 0.01619047619047619,
      "loss": 0.0014,
      "step": 3240
    },
    {
      "epoch": 23.21,
      "learning_rate": 0.016137566137566138,
      "loss": 0.0015,
      "step": 3250
    },
    {
      "epoch": 23.29,
      "learning_rate": 0.016084656084656083,
      "loss": 0.0012,
      "step": 3260
    },
    {
      "epoch": 23.36,
      "learning_rate": 0.016031746031746032,
      "loss": 0.0012,
      "step": 3270
    },
    {
      "epoch": 23.43,
      "learning_rate": 0.015978835978835978,
      "loss": 0.0013,
      "step": 3280
    },
    {
      "epoch": 23.5,
      "learning_rate": 0.015925925925925927,
      "loss": 0.0014,
      "step": 3290
    },
    {
      "epoch": 23.57,
      "learning_rate": 0.015873015873015872,
      "loss": 0.0013,
      "step": 3300
    },
    {
      "epoch": 23.64,
      "learning_rate": 0.01582010582010582,
      "loss": 0.0013,
      "step": 3310
    },
    {
      "epoch": 23.71,
      "learning_rate": 0.015767195767195766,
      "loss": 0.0013,
      "step": 3320
    },
    {
      "epoch": 23.79,
      "learning_rate": 0.015714285714285715,
      "loss": 0.0015,
      "step": 3330
    },
    {
      "epoch": 23.86,
      "learning_rate": 0.01566137566137566,
      "loss": 0.0013,
      "step": 3340
    },
    {
      "epoch": 23.93,
      "learning_rate": 0.015608465608465608,
      "loss": 0.0012,
      "step": 3350
    },
    {
      "epoch": 24.0,
      "learning_rate": 0.015555555555555553,
      "loss": 0.0014,
      "step": 3360
    },
    {
      "epoch": 24.07,
      "learning_rate": 0.015502645502645502,
      "loss": 0.0013,
      "step": 3370
    },
    {
      "epoch": 24.14,
      "learning_rate": 0.015449735449735448,
      "loss": 0.0013,
      "step": 3380
    },
    {
      "epoch": 24.21,
      "learning_rate": 0.015396825396825397,
      "loss": 0.0013,
      "step": 3390
    },
    {
      "epoch": 24.29,
      "learning_rate": 0.015343915343915342,
      "loss": 0.0013,
      "step": 3400
    },
    {
      "epoch": 24.36,
      "learning_rate": 0.015291005291005291,
      "loss": 0.0013,
      "step": 3410
    },
    {
      "epoch": 24.43,
      "learning_rate": 0.015238095238095236,
      "loss": 0.0013,
      "step": 3420
    },
    {
      "epoch": 24.5,
      "learning_rate": 0.015185185185185185,
      "loss": 0.0013,
      "step": 3430
    },
    {
      "epoch": 24.57,
      "learning_rate": 0.01513227513227513,
      "loss": 0.0013,
      "step": 3440
    },
    {
      "epoch": 24.64,
      "learning_rate": 0.01507936507936508,
      "loss": 0.0013,
      "step": 3450
    },
    {
      "epoch": 24.71,
      "learning_rate": 0.015026455026455025,
      "loss": 0.0014,
      "step": 3460
    },
    {
      "epoch": 24.79,
      "learning_rate": 0.014973544973544972,
      "loss": 0.0014,
      "step": 3470
    },
    {
      "epoch": 24.86,
      "learning_rate": 0.01492063492063492,
      "loss": 0.0013,
      "step": 3480
    },
    {
      "epoch": 24.93,
      "learning_rate": 0.014867724867724866,
      "loss": 0.0012,
      "step": 3490
    },
    {
      "epoch": 25.0,
      "learning_rate": 0.014814814814814814,
      "loss": 0.0012,
      "step": 3500
    },
    {
      "epoch": 25.07,
      "learning_rate": 0.01476190476190476,
      "loss": 0.0012,
      "step": 3510
    },
    {
      "epoch": 25.14,
      "learning_rate": 0.014708994708994708,
      "loss": 0.0014,
      "step": 3520
    },
    {
      "epoch": 25.21,
      "learning_rate": 0.014656084656084655,
      "loss": 0.0013,
      "step": 3530
    },
    {
      "epoch": 25.29,
      "learning_rate": 0.014603174603174602,
      "loss": 0.0014,
      "step": 3540
    },
    {
      "epoch": 25.36,
      "learning_rate": 0.01455026455026455,
      "loss": 0.0014,
      "step": 3550
    },
    {
      "epoch": 25.43,
      "learning_rate": 0.014497354497354497,
      "loss": 0.0013,
      "step": 3560
    },
    {
      "epoch": 25.5,
      "learning_rate": 0.014444444444444444,
      "loss": 0.0014,
      "step": 3570
    },
    {
      "epoch": 25.57,
      "learning_rate": 0.014391534391534391,
      "loss": 0.0013,
      "step": 3580
    },
    {
      "epoch": 25.64,
      "learning_rate": 0.014338624338624338,
      "loss": 0.0014,
      "step": 3590
    },
    {
      "epoch": 25.71,
      "learning_rate": 0.014285714285714284,
      "loss": 0.0013,
      "step": 3600
    },
    {
      "epoch": 25.79,
      "learning_rate": 0.01423280423280423,
      "loss": 0.0012,
      "step": 3610
    },
    {
      "epoch": 25.86,
      "learning_rate": 0.014179894179894178,
      "loss": 0.0013,
      "step": 3620
    },
    {
      "epoch": 25.93,
      "learning_rate": 0.014126984126984125,
      "loss": 0.0012,
      "step": 3630
    },
    {
      "epoch": 26.0,
      "learning_rate": 0.014074074074074072,
      "loss": 0.0013,
      "step": 3640
    },
    {
      "epoch": 26.07,
      "learning_rate": 0.01402116402116402,
      "loss": 0.0013,
      "step": 3650
    },
    {
      "epoch": 26.14,
      "learning_rate": 0.013968253968253967,
      "loss": 0.0012,
      "step": 3660
    },
    {
      "epoch": 26.21,
      "learning_rate": 0.013915343915343914,
      "loss": 0.0013,
      "step": 3670
    },
    {
      "epoch": 26.29,
      "learning_rate": 0.01386243386243386,
      "loss": 0.0012,
      "step": 3680
    },
    {
      "epoch": 26.36,
      "learning_rate": 0.013809523809523808,
      "loss": 0.0014,
      "step": 3690
    },
    {
      "epoch": 26.43,
      "learning_rate": 0.013756613756613755,
      "loss": 0.0013,
      "step": 3700
    },
    {
      "epoch": 26.5,
      "learning_rate": 0.013703703703703702,
      "loss": 0.0013,
      "step": 3710
    },
    {
      "epoch": 26.57,
      "learning_rate": 0.01365079365079365,
      "loss": 0.0012,
      "step": 3720
    },
    {
      "epoch": 26.64,
      "learning_rate": 0.013597883597883597,
      "loss": 0.0014,
      "step": 3730
    },
    {
      "epoch": 26.71,
      "learning_rate": 0.013544973544973544,
      "loss": 0.0013,
      "step": 3740
    },
    {
      "epoch": 26.79,
      "learning_rate": 0.013492063492063491,
      "loss": 0.0013,
      "step": 3750
    },
    {
      "epoch": 26.86,
      "learning_rate": 0.013439153439153438,
      "loss": 0.0013,
      "step": 3760
    },
    {
      "epoch": 26.93,
      "learning_rate": 0.013386243386243385,
      "loss": 0.0013,
      "step": 3770
    },
    {
      "epoch": 27.0,
      "learning_rate": 0.013333333333333332,
      "loss": 0.0013,
      "step": 3780
    },
    {
      "epoch": 27.07,
      "learning_rate": 0.01328042328042328,
      "loss": 0.0012,
      "step": 3790
    },
    {
      "epoch": 27.14,
      "learning_rate": 0.013227513227513227,
      "loss": 0.0012,
      "step": 3800
    },
    {
      "epoch": 27.21,
      "learning_rate": 0.013174603174603174,
      "loss": 0.0013,
      "step": 3810
    },
    {
      "epoch": 27.29,
      "learning_rate": 0.013121693121693121,
      "loss": 0.0013,
      "step": 3820
    },
    {
      "epoch": 27.36,
      "learning_rate": 0.013068783068783068,
      "loss": 0.0013,
      "step": 3830
    },
    {
      "epoch": 27.43,
      "learning_rate": 0.013015873015873015,
      "loss": 0.0012,
      "step": 3840
    },
    {
      "epoch": 27.5,
      "learning_rate": 0.012962962962962963,
      "loss": 0.0012,
      "step": 3850
    },
    {
      "epoch": 27.57,
      "learning_rate": 0.012910052910052908,
      "loss": 0.0012,
      "step": 3860
    },
    {
      "epoch": 27.64,
      "learning_rate": 0.012857142857142855,
      "loss": 0.0012,
      "step": 3870
    },
    {
      "epoch": 27.71,
      "learning_rate": 0.012804232804232802,
      "loss": 0.0013,
      "step": 3880
    },
    {
      "epoch": 27.79,
      "learning_rate": 0.01275132275132275,
      "loss": 0.0016,
      "step": 3890
    },
    {
      "epoch": 27.86,
      "learning_rate": 0.012698412698412697,
      "loss": 0.0012,
      "step": 3900
    },
    {
      "epoch": 27.93,
      "learning_rate": 0.012645502645502644,
      "loss": 0.0013,
      "step": 3910
    },
    {
      "epoch": 28.0,
      "learning_rate": 0.012592592592592591,
      "loss": 0.0013,
      "step": 3920
    },
    {
      "epoch": 28.07,
      "learning_rate": 0.012539682539682538,
      "loss": 0.0013,
      "step": 3930
    },
    {
      "epoch": 28.14,
      "learning_rate": 0.012486772486772485,
      "loss": 0.0012,
      "step": 3940
    },
    {
      "epoch": 28.21,
      "learning_rate": 0.012433862433862432,
      "loss": 0.0012,
      "step": 3950
    },
    {
      "epoch": 28.29,
      "learning_rate": 0.01238095238095238,
      "loss": 0.0012,
      "step": 3960
    },
    {
      "epoch": 28.36,
      "learning_rate": 0.012328042328042327,
      "loss": 0.0013,
      "step": 3970
    },
    {
      "epoch": 28.43,
      "learning_rate": 0.012275132275132274,
      "loss": 0.0012,
      "step": 3980
    },
    {
      "epoch": 28.5,
      "learning_rate": 0.012222222222222221,
      "loss": 0.0013,
      "step": 3990
    },
    {
      "epoch": 28.57,
      "learning_rate": 0.012169312169312168,
      "loss": 0.0012,
      "step": 4000
    },
    {
      "epoch": 28.64,
      "learning_rate": 0.012116402116402115,
      "loss": 0.0012,
      "step": 4010
    },
    {
      "epoch": 28.71,
      "learning_rate": 0.012063492063492063,
      "loss": 0.0013,
      "step": 4020
    },
    {
      "epoch": 28.79,
      "learning_rate": 0.01201058201058201,
      "loss": 0.0011,
      "step": 4030
    },
    {
      "epoch": 28.86,
      "learning_rate": 0.011957671957671957,
      "loss": 0.0013,
      "step": 4040
    },
    {
      "epoch": 28.93,
      "learning_rate": 0.011904761904761904,
      "loss": 0.0013,
      "step": 4050
    },
    {
      "epoch": 29.0,
      "learning_rate": 0.011851851851851851,
      "loss": 0.0012,
      "step": 4060
    },
    {
      "epoch": 29.07,
      "learning_rate": 0.011798941798941798,
      "loss": 0.0011,
      "step": 4070
    },
    {
      "epoch": 29.14,
      "learning_rate": 0.011746031746031746,
      "loss": 0.0013,
      "step": 4080
    },
    {
      "epoch": 29.21,
      "learning_rate": 0.011693121693121693,
      "loss": 0.0012,
      "step": 4090
    },
    {
      "epoch": 29.29,
      "learning_rate": 0.01164021164021164,
      "loss": 0.0014,
      "step": 4100
    },
    {
      "epoch": 29.36,
      "learning_rate": 0.011587301587301587,
      "loss": 0.0012,
      "step": 4110
    },
    {
      "epoch": 29.43,
      "learning_rate": 0.011534391534391533,
      "loss": 0.0013,
      "step": 4120
    },
    {
      "epoch": 29.5,
      "learning_rate": 0.01148148148148148,
      "loss": 0.0012,
      "step": 4130
    },
    {
      "epoch": 29.57,
      "learning_rate": 0.011428571428571427,
      "loss": 0.0012,
      "step": 4140
    },
    {
      "epoch": 29.64,
      "learning_rate": 0.011375661375661374,
      "loss": 0.0013,
      "step": 4150
    },
    {
      "epoch": 29.71,
      "learning_rate": 0.011322751322751321,
      "loss": 0.0012,
      "step": 4160
    },
    {
      "epoch": 29.79,
      "learning_rate": 0.011269841269841268,
      "loss": 0.0013,
      "step": 4170
    },
    {
      "epoch": 29.86,
      "learning_rate": 0.011216931216931215,
      "loss": 0.0013,
      "step": 4180
    },
    {
      "epoch": 29.93,
      "learning_rate": 0.011164021164021163,
      "loss": 0.0013,
      "step": 4190
    },
    {
      "epoch": 30.0,
      "learning_rate": 0.01111111111111111,
      "loss": 0.0012,
      "step": 4200
    },
    {
      "epoch": 30.07,
      "learning_rate": 0.011058201058201057,
      "loss": 0.0013,
      "step": 4210
    },
    {
      "epoch": 30.14,
      "learning_rate": 0.011005291005291004,
      "loss": 0.0012,
      "step": 4220
    },
    {
      "epoch": 30.21,
      "learning_rate": 0.010952380952380951,
      "loss": 0.0012,
      "step": 4230
    },
    {
      "epoch": 30.29,
      "learning_rate": 0.010899470899470898,
      "loss": 0.0012,
      "step": 4240
    },
    {
      "epoch": 30.36,
      "learning_rate": 0.010846560846560846,
      "loss": 0.0012,
      "step": 4250
    },
    {
      "epoch": 30.43,
      "learning_rate": 0.010793650793650793,
      "loss": 0.0012,
      "step": 4260
    },
    {
      "epoch": 30.5,
      "learning_rate": 0.01074074074074074,
      "loss": 0.0013,
      "step": 4270
    },
    {
      "epoch": 30.57,
      "learning_rate": 0.010687830687830687,
      "loss": 0.0012,
      "step": 4280
    },
    {
      "epoch": 30.64,
      "learning_rate": 0.010634920634920634,
      "loss": 0.0013,
      "step": 4290
    },
    {
      "epoch": 30.71,
      "learning_rate": 0.010582010582010581,
      "loss": 0.0012,
      "step": 4300
    },
    {
      "epoch": 30.79,
      "learning_rate": 0.010529100529100529,
      "loss": 0.0012,
      "step": 4310
    },
    {
      "epoch": 30.86,
      "learning_rate": 0.010476190476190476,
      "loss": 0.0012,
      "step": 4320
    },
    {
      "epoch": 30.93,
      "learning_rate": 0.010423280423280423,
      "loss": 0.0012,
      "step": 4330
    },
    {
      "epoch": 31.0,
      "learning_rate": 0.01037037037037037,
      "loss": 0.0013,
      "step": 4340
    },
    {
      "epoch": 31.07,
      "learning_rate": 0.010317460317460317,
      "loss": 0.0012,
      "step": 4350
    },
    {
      "epoch": 31.14,
      "learning_rate": 0.010264550264550264,
      "loss": 0.0011,
      "step": 4360
    },
    {
      "epoch": 31.21,
      "learning_rate": 0.010211640211640212,
      "loss": 0.0012,
      "step": 4370
    },
    {
      "epoch": 31.29,
      "learning_rate": 0.010158730158730157,
      "loss": 0.0013,
      "step": 4380
    },
    {
      "epoch": 31.36,
      "learning_rate": 0.010105820105820104,
      "loss": 0.0011,
      "step": 4390
    },
    {
      "epoch": 31.43,
      "learning_rate": 0.010052910052910051,
      "loss": 0.0012,
      "step": 4400
    },
    {
      "epoch": 31.5,
      "learning_rate": 0.009999999999999998,
      "loss": 0.0013,
      "step": 4410
    },
    {
      "epoch": 31.57,
      "learning_rate": 0.009947089947089946,
      "loss": 0.0012,
      "step": 4420
    },
    {
      "epoch": 31.64,
      "learning_rate": 0.009894179894179893,
      "loss": 0.0013,
      "step": 4430
    },
    {
      "epoch": 31.71,
      "learning_rate": 0.00984126984126984,
      "loss": 0.0012,
      "step": 4440
    },
    {
      "epoch": 31.79,
      "learning_rate": 0.009788359788359787,
      "loss": 0.0012,
      "step": 4450
    },
    {
      "epoch": 31.86,
      "learning_rate": 0.009735449735449734,
      "loss": 0.0012,
      "step": 4460
    },
    {
      "epoch": 31.93,
      "learning_rate": 0.009682539682539681,
      "loss": 0.0013,
      "step": 4470
    },
    {
      "epoch": 32.0,
      "learning_rate": 0.009629629629629629,
      "loss": 0.0011,
      "step": 4480
    },
    {
      "epoch": 32.07,
      "learning_rate": 0.009576719576719576,
      "loss": 0.0012,
      "step": 4490
    },
    {
      "epoch": 32.14,
      "learning_rate": 0.009523809523809523,
      "loss": 0.0013,
      "step": 4500
    },
    {
      "epoch": 32.21,
      "learning_rate": 0.00947089947089947,
      "loss": 0.0012,
      "step": 4510
    },
    {
      "epoch": 32.29,
      "learning_rate": 0.009417989417989417,
      "loss": 0.0012,
      "step": 4520
    },
    {
      "epoch": 32.36,
      "learning_rate": 0.009365079365079364,
      "loss": 0.0013,
      "step": 4530
    },
    {
      "epoch": 32.43,
      "learning_rate": 0.009312169312169312,
      "loss": 0.0013,
      "step": 4540
    },
    {
      "epoch": 32.5,
      "learning_rate": 0.009259259259259259,
      "loss": 0.0012,
      "step": 4550
    },
    {
      "epoch": 32.57,
      "learning_rate": 0.009206349206349206,
      "loss": 0.0011,
      "step": 4560
    },
    {
      "epoch": 32.64,
      "learning_rate": 0.009153439153439153,
      "loss": 0.0012,
      "step": 4570
    },
    {
      "epoch": 32.71,
      "learning_rate": 0.0091005291005291,
      "loss": 0.0012,
      "step": 4580
    },
    {
      "epoch": 32.79,
      "learning_rate": 0.009047619047619047,
      "loss": 0.0013,
      "step": 4590
    },
    {
      "epoch": 32.86,
      "learning_rate": 0.008994708994708995,
      "loss": 0.0012,
      "step": 4600
    },
    {
      "epoch": 32.93,
      "learning_rate": 0.008941798941798942,
      "loss": 0.0014,
      "step": 4610
    },
    {
      "epoch": 33.0,
      "learning_rate": 0.008888888888888889,
      "loss": 0.0012,
      "step": 4620
    },
    {
      "epoch": 33.07,
      "learning_rate": 0.008835978835978834,
      "loss": 0.0012,
      "step": 4630
    },
    {
      "epoch": 33.14,
      "learning_rate": 0.008783068783068781,
      "loss": 0.0013,
      "step": 4640
    },
    {
      "epoch": 33.21,
      "learning_rate": 0.008730158730158729,
      "loss": 0.0012,
      "step": 4650
    },
    {
      "epoch": 33.29,
      "learning_rate": 0.008677248677248676,
      "loss": 0.0012,
      "step": 4660
    },
    {
      "epoch": 33.36,
      "learning_rate": 0.008624338624338623,
      "loss": 0.0012,
      "step": 4670
    },
    {
      "epoch": 33.43,
      "learning_rate": 0.00857142857142857,
      "loss": 0.0012,
      "step": 4680
    },
    {
      "epoch": 33.5,
      "learning_rate": 0.008518518518518517,
      "loss": 0.0012,
      "step": 4690
    },
    {
      "epoch": 33.57,
      "learning_rate": 0.008465608465608464,
      "loss": 0.0012,
      "step": 4700
    },
    {
      "epoch": 33.64,
      "learning_rate": 0.008412698412698412,
      "loss": 0.0012,
      "step": 4710
    },
    {
      "epoch": 33.71,
      "learning_rate": 0.008359788359788359,
      "loss": 0.0012,
      "step": 4720
    },
    {
      "epoch": 33.79,
      "learning_rate": 0.008306878306878306,
      "loss": 0.0012,
      "step": 4730
    },
    {
      "epoch": 33.86,
      "learning_rate": 0.008253968253968253,
      "loss": 0.0012,
      "step": 4740
    },
    {
      "epoch": 33.93,
      "learning_rate": 0.0082010582010582,
      "loss": 0.0012,
      "step": 4750
    },
    {
      "epoch": 34.0,
      "learning_rate": 0.008148148148148147,
      "loss": 0.0012,
      "step": 4760
    },
    {
      "epoch": 34.07,
      "learning_rate": 0.008095238095238095,
      "loss": 0.0011,
      "step": 4770
    },
    {
      "epoch": 34.14,
      "learning_rate": 0.008042328042328042,
      "loss": 0.0013,
      "step": 4780
    },
    {
      "epoch": 34.21,
      "learning_rate": 0.007989417989417989,
      "loss": 0.0011,
      "step": 4790
    },
    {
      "epoch": 34.29,
      "learning_rate": 0.007936507936507936,
      "loss": 0.0011,
      "step": 4800
    },
    {
      "epoch": 34.36,
      "learning_rate": 0.007883597883597883,
      "loss": 0.0012,
      "step": 4810
    },
    {
      "epoch": 34.43,
      "learning_rate": 0.00783068783068783,
      "loss": 0.0012,
      "step": 4820
    },
    {
      "epoch": 34.5,
      "learning_rate": 0.007777777777777777,
      "loss": 0.0011,
      "step": 4830
    },
    {
      "epoch": 34.57,
      "learning_rate": 0.007724867724867724,
      "loss": 0.0011,
      "step": 4840
    },
    {
      "epoch": 34.64,
      "learning_rate": 0.007671957671957671,
      "loss": 0.0011,
      "step": 4850
    },
    {
      "epoch": 34.71,
      "learning_rate": 0.007619047619047618,
      "loss": 0.0012,
      "step": 4860
    },
    {
      "epoch": 34.79,
      "learning_rate": 0.007566137566137565,
      "loss": 0.0012,
      "step": 4870
    },
    {
      "epoch": 34.86,
      "learning_rate": 0.0075132275132275125,
      "loss": 0.0012,
      "step": 4880
    },
    {
      "epoch": 34.93,
      "learning_rate": 0.00746031746031746,
      "loss": 0.0011,
      "step": 4890
    },
    {
      "epoch": 35.0,
      "learning_rate": 0.007407407407407407,
      "loss": 0.0012,
      "step": 4900
    },
    {
      "epoch": 35.07,
      "learning_rate": 0.007354497354497354,
      "loss": 0.0012,
      "step": 4910
    },
    {
      "epoch": 35.14,
      "learning_rate": 0.007301587301587301,
      "loss": 0.0012,
      "step": 4920
    },
    {
      "epoch": 35.21,
      "learning_rate": 0.007248677248677248,
      "loss": 0.0012,
      "step": 4930
    },
    {
      "epoch": 35.29,
      "learning_rate": 0.0071957671957671955,
      "loss": 0.0011,
      "step": 4940
    },
    {
      "epoch": 35.36,
      "learning_rate": 0.007142857142857142,
      "loss": 0.0012,
      "step": 4950
    },
    {
      "epoch": 35.43,
      "learning_rate": 0.007089947089947089,
      "loss": 0.0012,
      "step": 4960
    },
    {
      "epoch": 35.5,
      "learning_rate": 0.007037037037037036,
      "loss": 0.0013,
      "step": 4970
    },
    {
      "epoch": 35.57,
      "learning_rate": 0.006984126984126983,
      "loss": 0.0012,
      "step": 4980
    },
    {
      "epoch": 35.64,
      "learning_rate": 0.00693121693121693,
      "loss": 0.0012,
      "step": 4990
    },
    {
      "epoch": 35.71,
      "learning_rate": 0.006878306878306878,
      "loss": 0.0011,
      "step": 5000
    },
    {
      "epoch": 35.79,
      "learning_rate": 0.006825396825396825,
      "loss": 0.0012,
      "step": 5010
    },
    {
      "epoch": 35.86,
      "learning_rate": 0.006772486772486772,
      "loss": 0.0012,
      "step": 5020
    },
    {
      "epoch": 35.93,
      "learning_rate": 0.006719576719576719,
      "loss": 0.0012,
      "step": 5030
    },
    {
      "epoch": 36.0,
      "learning_rate": 0.006666666666666666,
      "loss": 0.0011,
      "step": 5040
    },
    {
      "epoch": 36.07,
      "learning_rate": 0.006613756613756613,
      "loss": 0.0012,
      "step": 5050
    },
    {
      "epoch": 36.14,
      "learning_rate": 0.0065608465608465606,
      "loss": 0.0011,
      "step": 5060
    },
    {
      "epoch": 36.21,
      "learning_rate": 0.006507936507936508,
      "loss": 0.0012,
      "step": 5070
    },
    {
      "epoch": 36.29,
      "learning_rate": 0.006455026455026454,
      "loss": 0.0013,
      "step": 5080
    },
    {
      "epoch": 36.36,
      "learning_rate": 0.006402116402116401,
      "loss": 0.0011,
      "step": 5090
    },
    {
      "epoch": 36.43,
      "learning_rate": 0.006349206349206348,
      "loss": 0.0012,
      "step": 5100
    },
    {
      "epoch": 36.5,
      "learning_rate": 0.0062962962962962955,
      "loss": 0.0011,
      "step": 5110
    },
    {
      "epoch": 36.57,
      "learning_rate": 0.006243386243386243,
      "loss": 0.0012,
      "step": 5120
    },
    {
      "epoch": 36.64,
      "learning_rate": 0.00619047619047619,
      "loss": 0.0011,
      "step": 5130
    },
    {
      "epoch": 36.71,
      "learning_rate": 0.006137566137566137,
      "loss": 0.0011,
      "step": 5140
    },
    {
      "epoch": 36.79,
      "learning_rate": 0.006084656084656084,
      "loss": 0.0011,
      "step": 5150
    },
    {
      "epoch": 36.86,
      "learning_rate": 0.006031746031746031,
      "loss": 0.0011,
      "step": 5160
    },
    {
      "epoch": 36.93,
      "learning_rate": 0.0059788359788359785,
      "loss": 0.0012,
      "step": 5170
    },
    {
      "epoch": 37.0,
      "learning_rate": 0.005925925925925926,
      "loss": 0.0011,
      "step": 5180
    },
    {
      "epoch": 37.07,
      "learning_rate": 0.005873015873015873,
      "loss": 0.0012,
      "step": 5190
    },
    {
      "epoch": 37.14,
      "learning_rate": 0.00582010582010582,
      "loss": 0.0012,
      "step": 5200
    },
    {
      "epoch": 37.21,
      "learning_rate": 0.005767195767195766,
      "loss": 0.0011,
      "step": 5210
    },
    {
      "epoch": 37.29,
      "learning_rate": 0.005714285714285713,
      "loss": 0.0011,
      "step": 5220
    },
    {
      "epoch": 37.36,
      "learning_rate": 0.005661375661375661,
      "loss": 0.0012,
      "step": 5230
    },
    {
      "epoch": 37.43,
      "learning_rate": 0.005608465608465608,
      "loss": 0.0012,
      "step": 5240
    },
    {
      "epoch": 37.5,
      "learning_rate": 0.005555555555555555,
      "loss": 0.0012,
      "step": 5250
    },
    {
      "epoch": 37.57,
      "learning_rate": 0.005502645502645502,
      "loss": 0.0011,
      "step": 5260
    },
    {
      "epoch": 37.64,
      "learning_rate": 0.005449735449735449,
      "loss": 0.0012,
      "step": 5270
    },
    {
      "epoch": 37.71,
      "learning_rate": 0.005396825396825396,
      "loss": 0.0011,
      "step": 5280
    },
    {
      "epoch": 37.79,
      "learning_rate": 0.0053439153439153435,
      "loss": 0.0012,
      "step": 5290
    },
    {
      "epoch": 37.86,
      "learning_rate": 0.005291005291005291,
      "loss": 0.0011,
      "step": 5300
    },
    {
      "epoch": 37.93,
      "learning_rate": 0.005238095238095238,
      "loss": 0.0012,
      "step": 5310
    },
    {
      "epoch": 38.0,
      "learning_rate": 0.005185185185185185,
      "loss": 0.0012,
      "step": 5320
    },
    {
      "epoch": 38.07,
      "learning_rate": 0.005132275132275132,
      "loss": 0.0013,
      "step": 5330
    },
    {
      "epoch": 38.14,
      "learning_rate": 0.0050793650793650785,
      "loss": 0.0011,
      "step": 5340
    },
    {
      "epoch": 38.21,
      "learning_rate": 0.005026455026455026,
      "loss": 0.0012,
      "step": 5350
    },
    {
      "epoch": 38.29,
      "learning_rate": 0.004973544973544973,
      "loss": 0.0012,
      "step": 5360
    },
    {
      "epoch": 38.36,
      "learning_rate": 0.00492063492063492,
      "loss": 0.0011,
      "step": 5370
    },
    {
      "epoch": 38.43,
      "learning_rate": 0.004867724867724867,
      "loss": 0.0011,
      "step": 5380
    },
    {
      "epoch": 38.5,
      "learning_rate": 0.004814814814814814,
      "loss": 0.0011,
      "step": 5390
    },
    {
      "epoch": 38.57,
      "learning_rate": 0.0047619047619047615,
      "loss": 0.0012,
      "step": 5400
    },
    {
      "epoch": 38.64,
      "learning_rate": 0.004708994708994709,
      "loss": 0.0011,
      "step": 5410
    },
    {
      "epoch": 38.71,
      "learning_rate": 0.004656084656084656,
      "loss": 0.0011,
      "step": 5420
    },
    {
      "epoch": 38.79,
      "learning_rate": 0.004603174603174603,
      "loss": 0.0011,
      "step": 5430
    },
    {
      "epoch": 38.86,
      "learning_rate": 0.00455026455026455,
      "loss": 0.0011,
      "step": 5440
    },
    {
      "epoch": 38.93,
      "learning_rate": 0.004497354497354497,
      "loss": 0.0011,
      "step": 5450
    },
    {
      "epoch": 39.0,
      "learning_rate": 0.0044444444444444444,
      "loss": 0.0012,
      "step": 5460
    },
    {
      "epoch": 39.07,
      "learning_rate": 0.004391534391534391,
      "loss": 0.0011,
      "step": 5470
    },
    {
      "epoch": 39.14,
      "learning_rate": 0.004338624338624338,
      "loss": 0.0012,
      "step": 5480
    },
    {
      "epoch": 39.21,
      "learning_rate": 0.004285714285714285,
      "loss": 0.0011,
      "step": 5490
    },
    {
      "epoch": 39.29,
      "learning_rate": 0.004232804232804232,
      "loss": 0.0012,
      "step": 5500
    },
    {
      "epoch": 39.36,
      "learning_rate": 0.004179894179894179,
      "loss": 0.0011,
      "step": 5510
    },
    {
      "epoch": 39.43,
      "learning_rate": 0.0041269841269841265,
      "loss": 0.0011,
      "step": 5520
    },
    {
      "epoch": 39.5,
      "learning_rate": 0.004074074074074074,
      "loss": 0.0011,
      "step": 5530
    },
    {
      "epoch": 39.57,
      "learning_rate": 0.004021164021164021,
      "loss": 0.0012,
      "step": 5540
    },
    {
      "epoch": 39.64,
      "learning_rate": 0.003968253968253968,
      "loss": 0.0011,
      "step": 5550
    },
    {
      "epoch": 39.71,
      "learning_rate": 0.003915343915343915,
      "loss": 0.0012,
      "step": 5560
    },
    {
      "epoch": 39.79,
      "learning_rate": 0.003862433862433862,
      "loss": 0.0012,
      "step": 5570
    },
    {
      "epoch": 39.86,
      "learning_rate": 0.003809523809523809,
      "loss": 0.0012,
      "step": 5580
    },
    {
      "epoch": 39.93,
      "learning_rate": 0.0037566137566137562,
      "loss": 0.0012,
      "step": 5590
    },
    {
      "epoch": 40.0,
      "learning_rate": 0.0037037037037037034,
      "loss": 0.0013,
      "step": 5600
    },
    {
      "epoch": 40.07,
      "learning_rate": 0.0036507936507936506,
      "loss": 0.0012,
      "step": 5610
    },
    {
      "epoch": 40.14,
      "learning_rate": 0.0035978835978835977,
      "loss": 0.0011,
      "step": 5620
    },
    {
      "epoch": 40.21,
      "learning_rate": 0.0035449735449735445,
      "loss": 0.0012,
      "step": 5630
    },
    {
      "epoch": 40.29,
      "learning_rate": 0.0034920634920634916,
      "loss": 0.0013,
      "step": 5640
    },
    {
      "epoch": 40.36,
      "learning_rate": 0.003439153439153439,
      "loss": 0.0012,
      "step": 5650
    },
    {
      "epoch": 40.43,
      "learning_rate": 0.003386243386243386,
      "loss": 0.0012,
      "step": 5660
    },
    {
      "epoch": 40.5,
      "learning_rate": 0.003333333333333333,
      "loss": 0.0012,
      "step": 5670
    },
    {
      "epoch": 40.57,
      "learning_rate": 0.0032804232804232803,
      "loss": 0.0011,
      "step": 5680
    },
    {
      "epoch": 40.64,
      "learning_rate": 0.003227513227513227,
      "loss": 0.0012,
      "step": 5690
    },
    {
      "epoch": 40.71,
      "learning_rate": 0.003174603174603174,
      "loss": 0.0012,
      "step": 5700
    },
    {
      "epoch": 40.79,
      "learning_rate": 0.0031216931216931213,
      "loss": 0.0011,
      "step": 5710
    },
    {
      "epoch": 40.86,
      "learning_rate": 0.0030687830687830685,
      "loss": 0.0012,
      "step": 5720
    },
    {
      "epoch": 40.93,
      "learning_rate": 0.0030158730158730157,
      "loss": 0.0011,
      "step": 5730
    },
    {
      "epoch": 41.0,
      "learning_rate": 0.002962962962962963,
      "loss": 0.001,
      "step": 5740
    },
    {
      "epoch": 41.07,
      "learning_rate": 0.00291005291005291,
      "loss": 0.0012,
      "step": 5750
    },
    {
      "epoch": 41.14,
      "learning_rate": 0.0028571428571428567,
      "loss": 0.0011,
      "step": 5760
    },
    {
      "epoch": 41.21,
      "learning_rate": 0.002804232804232804,
      "loss": 0.0012,
      "step": 5770
    },
    {
      "epoch": 41.29,
      "learning_rate": 0.002751322751322751,
      "loss": 0.0011,
      "step": 5780
    },
    {
      "epoch": 41.36,
      "learning_rate": 0.002698412698412698,
      "loss": 0.001,
      "step": 5790
    },
    {
      "epoch": 41.43,
      "learning_rate": 0.0026455026455026454,
      "loss": 0.0012,
      "step": 5800
    },
    {
      "epoch": 41.5,
      "learning_rate": 0.0025925925925925925,
      "loss": 0.0011,
      "step": 5810
    },
    {
      "epoch": 41.57,
      "learning_rate": 0.0025396825396825392,
      "loss": 0.001,
      "step": 5820
    },
    {
      "epoch": 41.64,
      "learning_rate": 0.0024867724867724864,
      "loss": 0.0012,
      "step": 5830
    },
    {
      "epoch": 41.71,
      "learning_rate": 0.0024338624338624336,
      "loss": 0.0012,
      "step": 5840
    },
    {
      "epoch": 41.79,
      "learning_rate": 0.0023809523809523807,
      "loss": 0.0011,
      "step": 5850
    },
    {
      "epoch": 41.86,
      "learning_rate": 0.002328042328042328,
      "loss": 0.0012,
      "step": 5860
    },
    {
      "epoch": 41.93,
      "learning_rate": 0.002275132275132275,
      "loss": 0.0011,
      "step": 5870
    },
    {
      "epoch": 42.0,
      "learning_rate": 0.0022222222222222222,
      "loss": 0.0011,
      "step": 5880
    },
    {
      "epoch": 42.07,
      "learning_rate": 0.002169312169312169,
      "loss": 0.0012,
      "step": 5890
    },
    {
      "epoch": 42.14,
      "learning_rate": 0.002116402116402116,
      "loss": 0.001,
      "step": 5900
    },
    {
      "epoch": 42.21,
      "learning_rate": 0.0020634920634920633,
      "loss": 0.0011,
      "step": 5910
    },
    {
      "epoch": 42.29,
      "learning_rate": 0.0020105820105820104,
      "loss": 0.0012,
      "step": 5920
    },
    {
      "epoch": 42.36,
      "learning_rate": 0.0019576719576719576,
      "loss": 0.0012,
      "step": 5930
    },
    {
      "epoch": 42.43,
      "learning_rate": 0.0019047619047619045,
      "loss": 0.0011,
      "step": 5940
    },
    {
      "epoch": 42.5,
      "learning_rate": 0.0018518518518518517,
      "loss": 0.0011,
      "step": 5950
    },
    {
      "epoch": 42.57,
      "learning_rate": 0.0017989417989417989,
      "loss": 0.0012,
      "step": 5960
    },
    {
      "epoch": 42.64,
      "learning_rate": 0.0017460317460317458,
      "loss": 0.0012,
      "step": 5970
    },
    {
      "epoch": 42.71,
      "learning_rate": 0.001693121693121693,
      "loss": 0.0011,
      "step": 5980
    },
    {
      "epoch": 42.79,
      "learning_rate": 0.0016402116402116401,
      "loss": 0.0012,
      "step": 5990
    },
    {
      "epoch": 42.86,
      "learning_rate": 0.001587301587301587,
      "loss": 0.0011,
      "step": 6000
    },
    {
      "epoch": 42.93,
      "learning_rate": 0.0015343915343915342,
      "loss": 0.0011,
      "step": 6010
    },
    {
      "epoch": 43.0,
      "learning_rate": 0.0014814814814814814,
      "loss": 0.0011,
      "step": 6020
    },
    {
      "epoch": 43.07,
      "learning_rate": 0.0014285714285714284,
      "loss": 0.0011,
      "step": 6030
    },
    {
      "epoch": 43.14,
      "learning_rate": 0.0013756613756613755,
      "loss": 0.0012,
      "step": 6040
    },
    {
      "epoch": 43.21,
      "learning_rate": 0.0013227513227513227,
      "loss": 0.0012,
      "step": 6050
    },
    {
      "epoch": 43.29,
      "learning_rate": 0.0012698412698412696,
      "loss": 0.0013,
      "step": 6060
    },
    {
      "epoch": 43.36,
      "learning_rate": 0.0012169312169312168,
      "loss": 0.0012,
      "step": 6070
    },
    {
      "epoch": 43.43,
      "learning_rate": 0.001164021164021164,
      "loss": 0.0011,
      "step": 6080
    },
    {
      "epoch": 43.5,
      "learning_rate": 0.0011111111111111111,
      "loss": 0.0011,
      "step": 6090
    },
    {
      "epoch": 43.57,
      "learning_rate": 0.001058201058201058,
      "loss": 0.0011,
      "step": 6100
    },
    {
      "epoch": 43.64,
      "learning_rate": 0.0010052910052910052,
      "loss": 0.0012,
      "step": 6110
    },
    {
      "epoch": 43.71,
      "learning_rate": 0.0009523809523809523,
      "loss": 0.0011,
      "step": 6120
    },
    {
      "epoch": 43.79,
      "learning_rate": 0.0008994708994708994,
      "loss": 0.0011,
      "step": 6130
    },
    {
      "epoch": 43.86,
      "learning_rate": 0.0008465608465608465,
      "loss": 0.0011,
      "step": 6140
    },
    {
      "epoch": 43.93,
      "learning_rate": 0.0007936507936507935,
      "loss": 0.0011,
      "step": 6150
    },
    {
      "epoch": 44.0,
      "learning_rate": 0.0007407407407407407,
      "loss": 0.0011,
      "step": 6160
    },
    {
      "epoch": 44.07,
      "learning_rate": 0.0006878306878306878,
      "loss": 0.0011,
      "step": 6170
    },
    {
      "epoch": 44.14,
      "learning_rate": 0.0006349206349206348,
      "loss": 0.0011,
      "step": 6180
    },
    {
      "epoch": 44.21,
      "learning_rate": 0.000582010582010582,
      "loss": 0.0012,
      "step": 6190
    },
    {
      "epoch": 44.29,
      "learning_rate": 0.000529100529100529,
      "loss": 0.0011,
      "step": 6200
    },
    {
      "epoch": 44.36,
      "learning_rate": 0.00047619047619047614,
      "loss": 0.0011,
      "step": 6210
    },
    {
      "epoch": 44.43,
      "learning_rate": 0.00042328042328042324,
      "loss": 0.0012,
      "step": 6220
    },
    {
      "epoch": 44.5,
      "learning_rate": 0.00037037037037037035,
      "loss": 0.0011,
      "step": 6230
    },
    {
      "epoch": 44.57,
      "learning_rate": 0.0003174603174603174,
      "loss": 0.0012,
      "step": 6240
    },
    {
      "epoch": 44.64,
      "learning_rate": 0.0002645502645502645,
      "loss": 0.0011,
      "step": 6250
    },
    {
      "epoch": 44.71,
      "learning_rate": 0.00021164021164021162,
      "loss": 0.0012,
      "step": 6260
    },
    {
      "epoch": 44.79,
      "learning_rate": 0.0001587301587301587,
      "loss": 0.0012,
      "step": 6270
    },
    {
      "epoch": 44.86,
      "learning_rate": 0.00010582010582010581,
      "loss": 0.0011,
      "step": 6280
    },
    {
      "epoch": 44.93,
      "learning_rate": 5.2910052910052905e-05,
      "loss": 0.0011,
      "step": 6290
    },
    {
      "epoch": 45.0,
      "learning_rate": 0.0,
      "loss": 0.0012,
      "step": 6300
    }
  ],
  "max_steps": 6300,
  "num_train_epochs": 45,
  "total_flos": 1.8837542182050202e+18,
  "trial_name": null,
  "trial_params": null
}