{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 1.0,
  "eval_steps": 500,
  "global_step": 2179,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0,
      "learning_rate": 9.174311926605506e-07,
      "loss": 1.136,
      "step": 1
    },
    {
      "epoch": 0.0,
      "learning_rate": 4.587155963302753e-06,
      "loss": 1.1485,
      "step": 5
    },
    {
      "epoch": 0.0,
      "learning_rate": 9.174311926605506e-06,
      "loss": 1.1204,
      "step": 10
    },
    {
      "epoch": 0.01,
      "learning_rate": 1.3761467889908258e-05,
      "loss": 1.1304,
      "step": 15
    },
    {
      "epoch": 0.01,
      "learning_rate": 1.834862385321101e-05,
      "loss": 1.0939,
      "step": 20
    },
    {
      "epoch": 0.01,
      "learning_rate": 2.2935779816513765e-05,
      "loss": 1.0726,
      "step": 25
    },
    {
      "epoch": 0.01,
      "learning_rate": 2.7522935779816515e-05,
      "loss": 1.0481,
      "step": 30
    },
    {
      "epoch": 0.02,
      "learning_rate": 3.211009174311927e-05,
      "loss": 1.0549,
      "step": 35
    },
    {
      "epoch": 0.02,
      "learning_rate": 3.669724770642202e-05,
      "loss": 1.0569,
      "step": 40
    },
    {
      "epoch": 0.02,
      "learning_rate": 4.1284403669724776e-05,
      "loss": 1.0303,
      "step": 45
    },
    {
      "epoch": 0.02,
      "learning_rate": 4.587155963302753e-05,
      "loss": 1.0319,
      "step": 50
    },
    {
      "epoch": 0.03,
      "learning_rate": 5.0458715596330276e-05,
      "loss": 1.0037,
      "step": 55
    },
    {
      "epoch": 0.03,
      "learning_rate": 5.504587155963303e-05,
      "loss": 1.007,
      "step": 60
    },
    {
      "epoch": 0.03,
      "learning_rate": 5.9633027522935784e-05,
      "loss": 1.0205,
      "step": 65
    },
    {
      "epoch": 0.03,
      "learning_rate": 6.422018348623854e-05,
      "loss": 0.9893,
      "step": 70
    },
    {
      "epoch": 0.03,
      "learning_rate": 6.880733944954129e-05,
      "loss": 1.0094,
      "step": 75
    },
    {
      "epoch": 0.04,
      "learning_rate": 7.339449541284404e-05,
      "loss": 1.0048,
      "step": 80
    },
    {
      "epoch": 0.04,
      "learning_rate": 7.79816513761468e-05,
      "loss": 1.0111,
      "step": 85
    },
    {
      "epoch": 0.04,
      "learning_rate": 8.256880733944955e-05,
      "loss": 1.0033,
      "step": 90
    },
    {
      "epoch": 0.04,
      "learning_rate": 8.715596330275229e-05,
      "loss": 1.0049,
      "step": 95
    },
    {
      "epoch": 0.05,
      "learning_rate": 9.174311926605506e-05,
      "loss": 0.9886,
      "step": 100
    },
    {
      "epoch": 0.05,
      "learning_rate": 9.63302752293578e-05,
      "loss": 0.9863,
      "step": 105
    },
    {
      "epoch": 0.05,
      "learning_rate": 0.00010091743119266055,
      "loss": 0.9712,
      "step": 110
    },
    {
      "epoch": 0.05,
      "learning_rate": 0.00010550458715596329,
      "loss": 1.0071,
      "step": 115
    },
    {
      "epoch": 0.06,
      "learning_rate": 0.00011009174311926606,
      "loss": 1.0044,
      "step": 120
    },
    {
      "epoch": 0.06,
      "learning_rate": 0.00011467889908256881,
      "loss": 0.9665,
      "step": 125
    },
    {
      "epoch": 0.06,
      "learning_rate": 0.00011926605504587157,
      "loss": 0.9981,
      "step": 130
    },
    {
      "epoch": 0.06,
      "learning_rate": 0.00012385321100917432,
      "loss": 0.9578,
      "step": 135
    },
    {
      "epoch": 0.06,
      "learning_rate": 0.00012844036697247707,
      "loss": 0.986,
      "step": 140
    },
    {
      "epoch": 0.07,
      "learning_rate": 0.00013302752293577983,
      "loss": 0.9935,
      "step": 145
    },
    {
      "epoch": 0.07,
      "learning_rate": 0.00013761467889908258,
      "loss": 0.953,
      "step": 150
    },
    {
      "epoch": 0.07,
      "learning_rate": 0.0001422018348623853,
      "loss": 0.9565,
      "step": 155
    },
    {
      "epoch": 0.07,
      "learning_rate": 0.0001467889908256881,
      "loss": 0.9737,
      "step": 160
    },
    {
      "epoch": 0.08,
      "learning_rate": 0.00015137614678899084,
      "loss": 0.9819,
      "step": 165
    },
    {
      "epoch": 0.08,
      "learning_rate": 0.0001559633027522936,
      "loss": 0.9927,
      "step": 170
    },
    {
      "epoch": 0.08,
      "learning_rate": 0.00016055045871559632,
      "loss": 0.9803,
      "step": 175
    },
    {
      "epoch": 0.08,
      "learning_rate": 0.0001651376146788991,
      "loss": 0.9545,
      "step": 180
    },
    {
      "epoch": 0.08,
      "learning_rate": 0.00016972477064220186,
      "loss": 0.9927,
      "step": 185
    },
    {
      "epoch": 0.09,
      "learning_rate": 0.00017431192660550458,
      "loss": 0.9737,
      "step": 190
    },
    {
      "epoch": 0.09,
      "learning_rate": 0.00017889908256880734,
      "loss": 0.9959,
      "step": 195
    },
    {
      "epoch": 0.09,
      "learning_rate": 0.00018348623853211012,
      "loss": 0.9655,
      "step": 200
    },
    {
      "epoch": 0.09,
      "learning_rate": 0.00018807339449541284,
      "loss": 0.951,
      "step": 205
    },
    {
      "epoch": 0.1,
      "learning_rate": 0.0001926605504587156,
      "loss": 0.9531,
      "step": 210
    },
    {
      "epoch": 0.1,
      "learning_rate": 0.00019724770642201835,
      "loss": 0.9682,
      "step": 215
    },
    {
      "epoch": 0.1,
      "learning_rate": 0.00019999948669655127,
      "loss": 0.9663,
      "step": 220
    },
    {
      "epoch": 0.1,
      "learning_rate": 0.00019999371209327089,
      "loss": 0.9875,
      "step": 225
    },
    {
      "epoch": 0.11,
      "learning_rate": 0.00019998152162914806,
      "loss": 0.9624,
      "step": 230
    },
    {
      "epoch": 0.11,
      "learning_rate": 0.00019996291608635525,
      "loss": 0.9615,
      "step": 235
    },
    {
      "epoch": 0.11,
      "learning_rate": 0.00019993789665867314,
      "loss": 0.9677,
      "step": 240
    },
    {
      "epoch": 0.11,
      "learning_rate": 0.00019990646495141444,
      "loss": 0.961,
      "step": 245
    },
    {
      "epoch": 0.11,
      "learning_rate": 0.0001998686229813205,
      "loss": 0.9984,
      "step": 250
    },
    {
      "epoch": 0.12,
      "learning_rate": 0.00019982437317643217,
      "loss": 1.0021,
      "step": 255
    },
    {
      "epoch": 0.12,
      "learning_rate": 0.0001997737183759338,
      "loss": 0.9611,
      "step": 260
    },
    {
      "epoch": 0.12,
      "learning_rate": 0.00019971666182997137,
      "loss": 0.9813,
      "step": 265
    },
    {
      "epoch": 0.12,
      "learning_rate": 0.00019965320719944366,
      "loss": 0.9875,
      "step": 270
    },
    {
      "epoch": 0.13,
      "learning_rate": 0.00019958335855576738,
      "loss": 0.992,
      "step": 275
    },
    {
      "epoch": 0.13,
      "learning_rate": 0.00019950712038061617,
      "loss": 0.9735,
      "step": 280
    },
    {
      "epoch": 0.13,
      "learning_rate": 0.00019942449756563279,
      "loss": 0.9527,
      "step": 285
    },
    {
      "epoch": 0.13,
      "learning_rate": 0.00019933549541211552,
      "loss": 0.9663,
      "step": 290
    },
    {
      "epoch": 0.14,
      "learning_rate": 0.00019924011963067765,
      "loss": 0.9567,
      "step": 295
    },
    {
      "epoch": 0.14,
      "learning_rate": 0.00019913837634088144,
      "loss": 0.9592,
      "step": 300
    },
    {
      "epoch": 0.14,
      "learning_rate": 0.00019903027207084523,
      "loss": 0.9665,
      "step": 305
    },
    {
      "epoch": 0.14,
      "learning_rate": 0.00019891581375682473,
      "loss": 0.9899,
      "step": 310
    },
    {
      "epoch": 0.14,
      "learning_rate": 0.00019879500874276786,
      "loss": 0.9579,
      "step": 315
    },
    {
      "epoch": 0.15,
      "learning_rate": 0.00019866786477984357,
      "loss": 0.9722,
      "step": 320
    },
    {
      "epoch": 0.15,
      "learning_rate": 0.0001985343900259446,
      "loss": 0.9859,
      "step": 325
    },
    {
      "epoch": 0.15,
      "learning_rate": 0.0001983945930451639,
      "loss": 0.9507,
      "step": 330
    },
    {
      "epoch": 0.15,
      "learning_rate": 0.0001982484828072452,
      "loss": 0.954,
      "step": 335
    },
    {
      "epoch": 0.16,
      "learning_rate": 0.00019809606868700756,
      "loss": 0.9514,
      "step": 340
    },
    {
      "epoch": 0.16,
      "learning_rate": 0.00019793736046374373,
      "loss": 0.9837,
      "step": 345
    },
    {
      "epoch": 0.16,
      "learning_rate": 0.0001977723683205928,
      "loss": 0.9614,
      "step": 350
    },
    {
      "epoch": 0.16,
      "learning_rate": 0.00019760110284388667,
      "loss": 0.9599,
      "step": 355
    },
    {
      "epoch": 0.17,
      "learning_rate": 0.00019742357502247103,
      "loss": 0.9687,
      "step": 360
    },
    {
      "epoch": 0.17,
      "learning_rate": 0.00019723979624700004,
      "loss": 0.9341,
      "step": 365
    },
    {
      "epoch": 0.17,
      "learning_rate": 0.0001970497783092057,
      "loss": 0.9717,
      "step": 370
    },
    {
      "epoch": 0.17,
      "learning_rate": 0.00019685353340114103,
      "loss": 0.9618,
      "step": 375
    },
    {
      "epoch": 0.17,
      "learning_rate": 0.00019665107411439805,
      "loss": 0.9694,
      "step": 380
    },
    {
      "epoch": 0.18,
      "learning_rate": 0.00019644241343929966,
      "loss": 0.9594,
      "step": 385
    },
    {
      "epoch": 0.18,
      "learning_rate": 0.00019622756476406626,
      "loss": 0.9628,
      "step": 390
    },
    {
      "epoch": 0.18,
      "learning_rate": 0.00019600654187395663,
      "loss": 0.9898,
      "step": 395
    },
    {
      "epoch": 0.18,
      "learning_rate": 0.00019577935895038361,
      "loss": 0.9763,
      "step": 400
    },
    {
      "epoch": 0.19,
      "learning_rate": 0.00019554603057000397,
      "loss": 0.9506,
      "step": 405
    },
    {
      "epoch": 0.19,
      "learning_rate": 0.0001953065717037832,
      "loss": 0.9376,
      "step": 410
    },
    {
      "epoch": 0.19,
      "learning_rate": 0.00019506099771603513,
      "loss": 0.9545,
      "step": 415
    },
    {
      "epoch": 0.19,
      "learning_rate": 0.00019480932436343582,
      "loss": 0.9778,
      "step": 420
    },
    {
      "epoch": 0.2,
      "learning_rate": 0.00019455156779401265,
      "loss": 0.9516,
      "step": 425
    },
    {
      "epoch": 0.2,
      "learning_rate": 0.00019428774454610843,
      "loss": 0.9429,
      "step": 430
    },
    {
      "epoch": 0.2,
      "learning_rate": 0.00019401787154731993,
      "loss": 0.9667,
      "step": 435
    },
    {
      "epoch": 0.2,
      "learning_rate": 0.0001937419661134121,
      "loss": 0.9919,
      "step": 440
    },
    {
      "epoch": 0.2,
      "learning_rate": 0.00019346004594720669,
      "loss": 0.9647,
      "step": 445
    },
    {
      "epoch": 0.21,
      "learning_rate": 0.0001931721291374467,
      "loss": 0.9802,
      "step": 450
    },
    {
      "epoch": 0.21,
      "learning_rate": 0.00019287823415763553,
      "loss": 0.9597,
      "step": 455
    },
    {
      "epoch": 0.21,
      "learning_rate": 0.00019257837986485187,
      "loss": 0.9517,
      "step": 460
    },
    {
      "epoch": 0.21,
      "learning_rate": 0.0001922725854985396,
      "loss": 0.9479,
      "step": 465
    },
    {
      "epoch": 0.22,
      "learning_rate": 0.0001919608706792735,
      "loss": 0.9598,
      "step": 470
    },
    {
      "epoch": 0.22,
      "learning_rate": 0.00019164325540750016,
      "loss": 0.9674,
      "step": 475
    },
    {
      "epoch": 0.22,
      "learning_rate": 0.00019131976006225488,
      "loss": 0.9816,
      "step": 480
    },
    {
      "epoch": 0.22,
      "learning_rate": 0.00019099040539985394,
      "loss": 0.9858,
      "step": 485
    },
    {
      "epoch": 0.22,
      "learning_rate": 0.00019065521255256298,
      "loss": 0.9755,
      "step": 490
    },
    {
      "epoch": 0.23,
      "learning_rate": 0.00019031420302724096,
      "loss": 0.9582,
      "step": 495
    },
    {
      "epoch": 0.23,
      "learning_rate": 0.00018996739870396026,
      "loss": 0.9595,
      "step": 500
    },
    {
      "epoch": 0.23,
      "learning_rate": 0.00018961482183460282,
      "loss": 0.9523,
      "step": 505
    },
    {
      "epoch": 0.23,
      "learning_rate": 0.00018925649504143244,
      "loss": 0.9531,
      "step": 510
    },
    {
      "epoch": 0.24,
      "learning_rate": 0.0001888924413156432,
      "loss": 0.9659,
      "step": 515
    },
    {
      "epoch": 0.24,
      "learning_rate": 0.0001885226840158843,
      "loss": 0.9642,
      "step": 520
    },
    {
      "epoch": 0.24,
      "learning_rate": 0.00018814724686676133,
      "loss": 0.9894,
      "step": 525
    },
    {
      "epoch": 0.24,
      "learning_rate": 0.00018776615395731398,
      "loss": 0.9611,
      "step": 530
    },
    {
      "epoch": 0.25,
      "learning_rate": 0.0001873794297394706,
      "loss": 0.934,
      "step": 535
    },
    {
      "epoch": 0.25,
      "learning_rate": 0.00018698709902647902,
      "loss": 0.9633,
      "step": 540
    },
    {
      "epoch": 0.25,
      "learning_rate": 0.00018658918699131468,
      "loss": 0.9509,
      "step": 545
    },
    {
      "epoch": 0.25,
      "learning_rate": 0.00018618571916506545,
      "loss": 0.9642,
      "step": 550
    },
    {
      "epoch": 0.25,
      "learning_rate": 0.00018577672143529336,
      "loss": 0.9582,
      "step": 555
    },
    {
      "epoch": 0.26,
      "learning_rate": 0.00018536222004437368,
      "loss": 0.9632,
      "step": 560
    },
    {
      "epoch": 0.26,
      "learning_rate": 0.0001849422415878112,
      "loss": 0.9604,
      "step": 565
    },
    {
      "epoch": 0.26,
      "learning_rate": 0.00018451681301253362,
      "loss": 0.9754,
      "step": 570
    },
    {
      "epoch": 0.26,
      "learning_rate": 0.00018408596161516267,
      "loss": 0.9724,
      "step": 575
    },
    {
      "epoch": 0.27,
      "learning_rate": 0.00018364971504026273,
      "loss": 0.9722,
      "step": 580
    },
    {
      "epoch": 0.27,
      "learning_rate": 0.00018320810127856705,
      "loss": 0.9498,
      "step": 585
    },
    {
      "epoch": 0.27,
      "learning_rate": 0.00018276114866518168,
      "loss": 0.9548,
      "step": 590
    },
    {
      "epoch": 0.27,
      "learning_rate": 0.00018230888587776755,
      "loss": 0.9414,
      "step": 595
    },
    {
      "epoch": 0.28,
      "learning_rate": 0.00018185134193470043,
      "loss": 0.9492,
      "step": 600
    },
    {
      "epoch": 0.28,
      "learning_rate": 0.00018138854619320893,
      "loss": 0.9346,
      "step": 605
    },
    {
      "epoch": 0.28,
      "learning_rate": 0.00018092052834749094,
      "loss": 0.9561,
      "step": 610
    },
    {
      "epoch": 0.28,
      "learning_rate": 0.0001804473184268084,
      "loss": 0.9477,
      "step": 615
    },
    {
      "epoch": 0.28,
      "learning_rate": 0.0001799689467935604,
      "loss": 0.9432,
      "step": 620
    },
    {
      "epoch": 0.29,
      "learning_rate": 0.00017948544414133534,
      "loss": 0.93,
      "step": 625
    },
    {
      "epoch": 0.29,
      "learning_rate": 0.00017899684149294117,
      "loss": 0.9643,
      "step": 630
    },
    {
      "epoch": 0.29,
      "learning_rate": 0.00017850317019841514,
      "loss": 0.9441,
      "step": 635
    },
    {
      "epoch": 0.29,
      "learning_rate": 0.00017800446193301227,
      "loss": 0.9684,
      "step": 640
    },
    {
      "epoch": 0.3,
      "learning_rate": 0.00017750074869517284,
      "loss": 0.9372,
      "step": 645
    },
    {
      "epoch": 0.3,
      "learning_rate": 0.00017699206280446953,
      "loss": 0.9582,
      "step": 650
    },
    {
      "epoch": 0.3,
      "learning_rate": 0.00017647843689953352,
      "loss": 0.9602,
      "step": 655
    },
    {
      "epoch": 0.3,
      "learning_rate": 0.00017595990393596026,
      "loss": 0.9721,
      "step": 660
    },
    {
      "epoch": 0.31,
      "learning_rate": 0.0001754364971841952,
      "loss": 0.9657,
      "step": 665
    },
    {
      "epoch": 0.31,
      "learning_rate": 0.0001749082502273988,
      "loss": 0.9369,
      "step": 670
    },
    {
      "epoch": 0.31,
      "learning_rate": 0.00017437519695929194,
      "loss": 0.9591,
      "step": 675
    },
    {
      "epoch": 0.31,
      "learning_rate": 0.0001738373715819811,
      "loss": 0.9628,
      "step": 680
    },
    {
      "epoch": 0.31,
      "learning_rate": 0.00017329480860376391,
      "loss": 0.9611,
      "step": 685
    },
    {
      "epoch": 0.32,
      "learning_rate": 0.00017274754283691504,
      "loss": 0.9724,
      "step": 690
    },
    {
      "epoch": 0.32,
      "learning_rate": 0.00017219560939545246,
      "loss": 0.9514,
      "step": 695
    },
    {
      "epoch": 0.32,
      "learning_rate": 0.00017163904369288445,
      "loss": 0.9536,
      "step": 700
    },
    {
      "epoch": 0.32,
      "learning_rate": 0.00017107788143993743,
      "loss": 0.942,
      "step": 705
    },
    {
      "epoch": 0.33,
      "learning_rate": 0.00017051215864226469,
      "loss": 0.9705,
      "step": 710
    },
    {
      "epoch": 0.33,
      "learning_rate": 0.0001699419115981361,
      "loss": 0.9683,
      "step": 715
    },
    {
      "epoch": 0.33,
      "learning_rate": 0.00016936717689610903,
      "loss": 0.9672,
      "step": 720
    },
    {
      "epoch": 0.33,
      "learning_rate": 0.00016878799141268106,
      "loss": 0.9224,
      "step": 725
    },
    {
      "epoch": 0.34,
      "learning_rate": 0.00016820439230992343,
      "loss": 0.9482,
      "step": 730
    },
    {
      "epoch": 0.34,
      "learning_rate": 0.00016761641703309704,
      "loss": 0.9733,
      "step": 735
    },
    {
      "epoch": 0.34,
      "learning_rate": 0.00016702410330824962,
      "loss": 0.9445,
      "step": 740
    },
    {
      "epoch": 0.34,
      "learning_rate": 0.00016642748913979513,
      "loss": 0.9564,
      "step": 745
    },
    {
      "epoch": 0.34,
      "learning_rate": 0.00016582661280807552,
      "loss": 0.9623,
      "step": 750
    },
    {
      "epoch": 0.35,
      "learning_rate": 0.0001652215128669042,
      "loss": 0.9501,
      "step": 755
    },
    {
      "epoch": 0.35,
      "learning_rate": 0.00016461222814109268,
      "loss": 0.9746,
      "step": 760
    },
    {
      "epoch": 0.35,
      "learning_rate": 0.00016399879772395915,
      "loss": 0.9298,
      "step": 765
    },
    {
      "epoch": 0.35,
      "learning_rate": 0.00016338126097482057,
      "loss": 0.9564,
      "step": 770
    },
    {
      "epoch": 0.36,
      "learning_rate": 0.0001627596575164668,
      "loss": 0.9743,
      "step": 775
    },
    {
      "epoch": 0.36,
      "learning_rate": 0.0001621340272326185,
      "loss": 0.9626,
      "step": 780
    },
    {
      "epoch": 0.36,
      "learning_rate": 0.00016150441026536823,
      "loss": 0.9584,
      "step": 785
    },
    {
      "epoch": 0.36,
      "learning_rate": 0.00016087084701260466,
      "loss": 0.9679,
      "step": 790
    },
    {
      "epoch": 0.36,
      "learning_rate": 0.00016023337812542048,
      "loss": 0.9611,
      "step": 795
    },
    {
      "epoch": 0.37,
      "learning_rate": 0.00015959204450550428,
      "loss": 0.9511,
      "step": 800
    },
    {
      "epoch": 0.37,
      "learning_rate": 0.00015894688730251614,
      "loss": 0.9421,
      "step": 805
    },
    {
      "epoch": 0.37,
      "learning_rate": 0.0001582979479114472,
      "loss": 0.9358,
      "step": 810
    },
    {
      "epoch": 0.37,
      "learning_rate": 0.000157645267969964,
      "loss": 0.9657,
      "step": 815
    },
    {
      "epoch": 0.38,
      "learning_rate": 0.0001569888893557365,
      "loss": 0.9834,
      "step": 820
    },
    {
      "epoch": 0.38,
      "learning_rate": 0.00015632885418375136,
      "loss": 0.9345,
      "step": 825
    },
    {
      "epoch": 0.38,
      "learning_rate": 0.00015566520480360957,
      "loss": 0.938,
      "step": 830
    },
    {
      "epoch": 0.38,
      "learning_rate": 0.0001549979837968094,
      "loss": 0.9689,
      "step": 835
    },
    {
      "epoch": 0.39,
      "learning_rate": 0.00015432723397401405,
      "loss": 0.949,
      "step": 840
    },
    {
      "epoch": 0.39,
      "learning_rate": 0.00015365299837230483,
      "loss": 0.9793,
      "step": 845
    },
    {
      "epoch": 0.39,
      "learning_rate": 0.00015297532025241992,
      "loss": 0.9817,
      "step": 850
    },
    {
      "epoch": 0.39,
      "learning_rate": 0.00015229424309597852,
      "loss": 0.9594,
      "step": 855
    },
    {
      "epoch": 0.39,
      "learning_rate": 0.00015160981060269107,
      "loss": 0.9492,
      "step": 860
    },
    {
      "epoch": 0.4,
      "learning_rate": 0.00015092206668755517,
      "loss": 0.9577,
      "step": 865
    },
    {
      "epoch": 0.4,
      "learning_rate": 0.00015023105547803806,
      "loss": 0.9571,
      "step": 870
    },
    {
      "epoch": 0.4,
      "learning_rate": 0.00014953682131124528,
      "loss": 0.9305,
      "step": 875
    },
    {
      "epoch": 0.4,
      "learning_rate": 0.0001488394087310757,
      "loss": 0.9605,
      "step": 880
    },
    {
      "epoch": 0.41,
      "learning_rate": 0.00014813886248536375,
      "loss": 0.9463,
      "step": 885
    },
    {
      "epoch": 0.41,
      "learning_rate": 0.00014743522752300793,
      "loss": 0.9414,
      "step": 890
    },
    {
      "epoch": 0.41,
      "learning_rate": 0.00014672854899108718,
      "loss": 0.9486,
      "step": 895
    },
    {
      "epoch": 0.41,
      "learning_rate": 0.00014601887223196372,
      "loss": 0.9595,
      "step": 900
    },
    {
      "epoch": 0.42,
      "learning_rate": 0.00014530624278037406,
      "loss": 0.9755,
      "step": 905
    },
    {
      "epoch": 0.42,
      "learning_rate": 0.0001445907063605072,
      "loss": 0.9635,
      "step": 910
    },
    {
      "epoch": 0.42,
      "learning_rate": 0.00014387230888307097,
      "loss": 0.9518,
      "step": 915
    },
    {
      "epoch": 0.42,
      "learning_rate": 0.0001431510964423462,
      "loss": 0.9446,
      "step": 920
    },
    {
      "epoch": 0.42,
      "learning_rate": 0.0001424271153132291,
      "loss": 0.9636,
      "step": 925
    },
    {
      "epoch": 0.43,
      "learning_rate": 0.00014170041194826248,
      "loss": 0.941,
      "step": 930
    },
    {
      "epoch": 0.43,
      "learning_rate": 0.0001409710329746547,
      "loss": 0.9571,
      "step": 935
    },
    {
      "epoch": 0.43,
      "learning_rate": 0.0001402390251912885,
      "loss": 0.9402,
      "step": 940
    },
    {
      "epoch": 0.43,
      "learning_rate": 0.00013950443556571778,
      "loss": 0.9489,
      "step": 945
    },
    {
      "epoch": 0.44,
      "learning_rate": 0.0001387673112311545,
      "loss": 0.9711,
      "step": 950
    },
    {
      "epoch": 0.44,
      "learning_rate": 0.00013802769948344405,
      "loss": 0.9624,
      "step": 955
    },
    {
      "epoch": 0.44,
      "learning_rate": 0.00013728564777803088,
      "loss": 0.9483,
      "step": 960
    },
    {
      "epoch": 0.44,
      "learning_rate": 0.0001365412037269136,
      "loss": 0.966,
      "step": 965
    },
    {
      "epoch": 0.45,
      "learning_rate": 0.00013579441509559004,
      "loss": 0.9386,
      "step": 970
    },
    {
      "epoch": 0.45,
      "learning_rate": 0.0001350453297999925,
      "loss": 0.9489,
      "step": 975
    },
    {
      "epoch": 0.45,
      "learning_rate": 0.00013429399590341324,
      "loss": 0.9417,
      "step": 980
    },
    {
      "epoch": 0.45,
      "learning_rate": 0.00013354046161342085,
      "loss": 0.9699,
      "step": 985
    },
    {
      "epoch": 0.45,
      "learning_rate": 0.0001327847752787669,
      "loss": 0.9395,
      "step": 990
    },
    {
      "epoch": 0.46,
      "learning_rate": 0.00013202698538628376,
      "loss": 0.9344,
      "step": 995
    },
    {
      "epoch": 0.46,
      "learning_rate": 0.00013126714055777377,
      "loss": 0.9291,
      "step": 1000
    },
    {
      "epoch": 0.46,
      "learning_rate": 0.0001305052895468893,
      "loss": 0.9535,
      "step": 1005
    },
    {
      "epoch": 0.46,
      "learning_rate": 0.00012974148123600477,
      "loss": 0.9784,
      "step": 1010
    },
    {
      "epoch": 0.47,
      "learning_rate": 0.00012897576463307997,
      "loss": 0.9547,
      "step": 1015
    },
    {
      "epoch": 0.47,
      "learning_rate": 0.00012820818886851598,
      "loss": 0.9349,
      "step": 1020
    },
    {
      "epoch": 0.47,
      "learning_rate": 0.00012743880319200242,
      "loss": 0.9619,
      "step": 1025
    },
    {
      "epoch": 0.47,
      "learning_rate": 0.00012666765696935773,
      "loss": 0.9487,
      "step": 1030
    },
    {
      "epoch": 0.47,
      "learning_rate": 0.0001258947996793616,
      "loss": 0.9415,
      "step": 1035
    },
    {
      "epoch": 0.48,
      "learning_rate": 0.00012512028091058044,
      "loss": 0.9346,
      "step": 1040
    },
    {
      "epoch": 0.48,
      "learning_rate": 0.00012434415035818535,
      "loss": 0.9423,
      "step": 1045
    },
    {
      "epoch": 0.48,
      "learning_rate": 0.00012356645782076383,
      "loss": 0.9546,
      "step": 1050
    },
    {
      "epoch": 0.48,
      "learning_rate": 0.00012278725319712447,
      "loss": 0.9534,
      "step": 1055
    },
    {
      "epoch": 0.49,
      "learning_rate": 0.00012200658648309531,
      "loss": 0.9592,
      "step": 1060
    },
    {
      "epoch": 0.49,
      "learning_rate": 0.00012122450776831594,
      "loss": 0.9446,
      "step": 1065
    },
    {
      "epoch": 0.49,
      "learning_rate": 0.00012044106723302364,
      "loss": 0.9418,
      "step": 1070
    },
    {
      "epoch": 0.49,
      "learning_rate": 0.00011965631514483375,
      "loss": 0.9591,
      "step": 1075
    },
    {
      "epoch": 0.5,
      "learning_rate": 0.00011887030185551426,
      "loss": 0.9674,
      "step": 1080
    },
    {
      "epoch": 0.5,
      "learning_rate": 0.00011808307779775518,
      "loss": 0.9651,
      "step": 1085
    },
    {
      "epoch": 0.5,
      "learning_rate": 0.00011729469348193262,
      "loss": 0.9482,
      "step": 1090
    },
    {
      "epoch": 0.5,
      "learning_rate": 0.00011650519949286795,
      "loss": 0.9484,
      "step": 1095
    },
    {
      "epoch": 0.5,
      "learning_rate": 0.00011571464648658201,
      "loss": 0.9306,
      "step": 1100
    },
    {
      "epoch": 0.51,
      "learning_rate": 0.00011492308518704506,
      "loss": 0.9342,
      "step": 1105
    },
    {
      "epoch": 0.51,
      "learning_rate": 0.00011413056638292215,
      "loss": 0.9506,
      "step": 1110
    },
    {
      "epoch": 0.51,
      "learning_rate": 0.00011333714092431423,
      "loss": 0.9625,
      "step": 1115
    },
    {
      "epoch": 0.51,
      "learning_rate": 0.00011254285971949574,
      "loss": 0.9709,
      "step": 1120
    },
    {
      "epoch": 0.52,
      "learning_rate": 0.00011174777373164798,
      "loss": 0.9229,
      "step": 1125
    },
    {
      "epoch": 0.52,
      "learning_rate": 0.0001109519339755893,
      "loss": 0.9306,
      "step": 1130
    },
    {
      "epoch": 0.52,
      "learning_rate": 0.00011015539151450172,
      "loss": 0.9394,
      "step": 1135
    },
    {
      "epoch": 0.52,
      "learning_rate": 0.00010935819745665477,
      "loss": 0.9445,
      "step": 1140
    },
    {
      "epoch": 0.53,
      "learning_rate": 0.00010856040295212612,
      "loss": 0.9618,
      "step": 1145
    },
    {
      "epoch": 0.53,
      "learning_rate": 0.00010776205918951969,
      "loss": 0.9556,
      "step": 1150
    },
    {
      "epoch": 0.53,
      "learning_rate": 0.00010696321739268121,
      "loss": 0.9095,
      "step": 1155
    },
    {
      "epoch": 0.53,
      "learning_rate": 0.00010616392881741166,
      "loss": 0.94,
      "step": 1160
    },
    {
      "epoch": 0.53,
      "learning_rate": 0.00010536424474817847,
      "loss": 0.952,
      "step": 1165
    },
    {
      "epoch": 0.54,
      "learning_rate": 0.00010456421649482502,
      "loss": 0.9408,
      "step": 1170
    },
    {
      "epoch": 0.54,
      "learning_rate": 0.0001037638953892784,
      "loss": 0.9453,
      "step": 1175
    },
    {
      "epoch": 0.54,
      "learning_rate": 0.00010296333278225599,
      "loss": 0.941,
      "step": 1180
    },
    {
      "epoch": 0.54,
      "learning_rate": 0.00010216258003997043,
      "loss": 0.9709,
      "step": 1185
    },
    {
      "epoch": 0.55,
      "learning_rate": 0.00010136168854083402,
      "loss": 0.9381,
      "step": 1190
    },
    {
      "epoch": 0.55,
      "learning_rate": 0.00010056070967216198,
      "loss": 0.9496,
      "step": 1195
    },
    {
      "epoch": 0.55,
      "learning_rate": 9.975969482687547e-05,
      "loss": 0.9514,
      "step": 1200
    },
    {
      "epoch": 0.55,
      "learning_rate": 9.8958695400204e-05,
      "loss": 0.9418,
      "step": 1205
    },
    {
      "epoch": 0.56,
      "learning_rate": 9.815776278638771e-05,
      "loss": 0.9563,
      "step": 1210
    },
    {
      "epoch": 0.56,
      "learning_rate": 9.735694837537993e-05,
      "loss": 0.9527,
      "step": 1215
    },
    {
      "epoch": 0.56,
      "learning_rate": 9.655630354954974e-05,
      "loss": 0.9241,
      "step": 1220
    },
    {
      "epoch": 0.56,
      "learning_rate": 9.57558796803852e-05,
      "loss": 0.9505,
      "step": 1225
    },
    {
      "epoch": 0.56,
      "learning_rate": 9.495572812519718e-05,
      "loss": 0.9556,
      "step": 1230
    },
    {
      "epoch": 0.57,
      "learning_rate": 9.415590022382419e-05,
      "loss": 0.9352,
      "step": 1235
    },
    {
      "epoch": 0.57,
      "learning_rate": 9.33564472953383e-05,
      "loss": 0.9459,
      "step": 1240
    },
    {
      "epoch": 0.57,
      "learning_rate": 9.255742063475228e-05,
      "loss": 0.9555,
      "step": 1245
    },
    {
      "epoch": 0.57,
      "learning_rate": 9.175887150972841e-05,
      "loss": 0.9463,
      "step": 1250
    },
    {
      "epoch": 0.58,
      "learning_rate": 9.096085115728902e-05,
      "loss": 0.925,
      "step": 1255
    },
    {
      "epoch": 0.58,
      "learning_rate": 9.016341078052908e-05,
      "loss": 0.9285,
      "step": 1260
    },
    {
      "epoch": 0.58,
      "learning_rate": 8.936660154533069e-05,
      "loss": 0.9344,
      "step": 1265
    },
    {
      "epoch": 0.58,
      "learning_rate": 8.857047457708023e-05,
      "loss": 0.9487,
      "step": 1270
    },
    {
      "epoch": 0.59,
      "learning_rate": 8.777508095738818e-05,
      "loss": 0.9461,
      "step": 1275
    },
    {
      "epoch": 0.59,
      "learning_rate": 8.698047172081128e-05,
      "loss": 0.9615,
      "step": 1280
    },
    {
      "epoch": 0.59,
      "learning_rate": 8.618669785157825e-05,
      "loss": 0.9358,
      "step": 1285
    },
    {
      "epoch": 0.59,
      "learning_rate": 8.539381028031837e-05,
      "loss": 0.942,
      "step": 1290
    },
    {
      "epoch": 0.59,
      "learning_rate": 8.460185988079379e-05,
      "loss": 0.9714,
      "step": 1295
    },
    {
      "epoch": 0.6,
      "learning_rate": 8.381089746663517e-05,
      "loss": 0.9644,
      "step": 1300
    },
    {
      "epoch": 0.6,
      "learning_rate": 8.302097378808146e-05,
      "loss": 0.9613,
      "step": 1305
    },
    {
      "epoch": 0.6,
      "learning_rate": 8.223213952872353e-05,
      "loss": 0.9394,
      "step": 1310
    },
    {
      "epoch": 0.6,
      "learning_rate": 8.144444530225236e-05,
      "loss": 0.9344,
      "step": 1315
    },
    {
      "epoch": 0.61,
      "learning_rate": 8.065794164921128e-05,
      "loss": 0.9706,
      "step": 1320
    },
    {
      "epoch": 0.61,
      "learning_rate": 7.987267903375332e-05,
      "loss": 0.953,
      "step": 1325
    },
    {
      "epoch": 0.61,
      "learning_rate": 7.90887078404033e-05,
      "loss": 0.9638,
      "step": 1330
    },
    {
      "epoch": 0.61,
      "learning_rate": 7.830607837082493e-05,
      "loss": 0.9567,
      "step": 1335
    },
    {
      "epoch": 0.61,
      "learning_rate": 7.75248408405934e-05,
      "loss": 0.9538,
      "step": 1340
    },
    {
      "epoch": 0.62,
      "learning_rate": 7.674504537597336e-05,
      "loss": 0.9365,
      "step": 1345
    },
    {
      "epoch": 0.62,
      "learning_rate": 7.596674201070282e-05,
      "loss": 0.9478,
      "step": 1350
    },
    {
      "epoch": 0.62,
      "learning_rate": 7.518998068278266e-05,
      "loss": 0.943,
      "step": 1355
    },
    {
      "epoch": 0.62,
      "learning_rate": 7.441481123127257e-05,
      "loss": 0.9414,
      "step": 1360
    },
    {
      "epoch": 0.63,
      "learning_rate": 7.364128339309326e-05,
      "loss": 0.9448,
      "step": 1365
    },
    {
      "epoch": 0.63,
      "learning_rate": 7.28694467998352e-05,
      "loss": 0.9299,
      "step": 1370
    },
    {
      "epoch": 0.63,
      "learning_rate": 7.209935097457413e-05,
      "loss": 0.9544,
      "step": 1375
    },
    {
      "epoch": 0.63,
      "learning_rate": 7.133104532869342e-05,
      "loss": 0.9757,
      "step": 1380
    },
    {
      "epoch": 0.64,
      "learning_rate": 7.056457915871399e-05,
      "loss": 0.9587,
      "step": 1385
    },
    {
      "epoch": 0.64,
      "learning_rate": 6.980000164313093e-05,
      "loss": 0.9593,
      "step": 1390
    },
    {
      "epoch": 0.64,
      "learning_rate": 6.903736183925835e-05,
      "loss": 0.9497,
      "step": 1395
    },
    {
      "epoch": 0.64,
      "learning_rate": 6.827670868008171e-05,
      "loss": 0.9351,
      "step": 1400
    },
    {
      "epoch": 0.64,
      "learning_rate": 6.751809097111798e-05,
      "loss": 0.9359,
      "step": 1405
    },
    {
      "epoch": 0.65,
      "learning_rate": 6.676155738728438e-05,
      "loss": 0.9662,
      "step": 1410
    },
    {
      "epoch": 0.65,
      "learning_rate": 6.600715646977502e-05,
      "loss": 0.9493,
      "step": 1415
    },
    {
      "epoch": 0.65,
      "learning_rate": 6.525493662294668e-05,
      "loss": 0.9547,
      "step": 1420
    },
    {
      "epoch": 0.65,
      "learning_rate": 6.450494611121273e-05,
      "loss": 0.944,
      "step": 1425
    },
    {
      "epoch": 0.66,
      "learning_rate": 6.375723305594658e-05,
      "loss": 0.9464,
      "step": 1430
    },
    {
      "epoch": 0.66,
      "learning_rate": 6.301184543239398e-05,
      "loss": 0.9497,
      "step": 1435
    },
    {
      "epoch": 0.66,
      "learning_rate": 6.226883106659485e-05,
      "loss": 0.926,
      "step": 1440
    },
    {
      "epoch": 0.66,
      "learning_rate": 6.152823763231463e-05,
      "loss": 0.9502,
      "step": 1445
    },
    {
      "epoch": 0.67,
      "learning_rate": 6.079011264798534e-05,
      "loss": 0.9521,
      "step": 1450
    },
    {
      "epoch": 0.67,
      "learning_rate": 6.005450347365687e-05,
      "loss": 0.9541,
      "step": 1455
    },
    {
      "epoch": 0.67,
      "learning_rate": 5.932145730795793e-05,
      "loss": 0.945,
      "step": 1460
    },
    {
      "epoch": 0.67,
      "learning_rate": 5.8591021185067876e-05,
      "loss": 0.9449,
      "step": 1465
    },
    {
      "epoch": 0.67,
      "learning_rate": 5.786324197169887e-05,
      "loss": 0.931,
      "step": 1470
    },
    {
      "epoch": 0.68,
      "learning_rate": 5.7138166364088705e-05,
      "loss": 0.9525,
      "step": 1475
    },
    {
      "epoch": 0.68,
      "learning_rate": 5.641584088500461e-05,
      "loss": 0.9394,
      "step": 1480
    },
    {
      "epoch": 0.68,
      "learning_rate": 5.569631188075841e-05,
      "loss": 0.9594,
      "step": 1485
    },
    {
      "epoch": 0.68,
      "learning_rate": 5.497962551823266e-05,
      "loss": 0.9467,
      "step": 1490
    },
    {
      "epoch": 0.69,
      "learning_rate": 5.4265827781918576e-05,
      "loss": 0.9452,
      "step": 1495
    },
    {
      "epoch": 0.69,
      "learning_rate": 5.355496447096533e-05,
      "loss": 0.9601,
      "step": 1500
    },
    {
      "epoch": 0.69,
      "learning_rate": 5.284708119624173e-05,
      "loss": 0.9639,
      "step": 1505
    },
    {
      "epoch": 0.69,
      "learning_rate": 5.214222337740962e-05,
      "loss": 0.9442,
      "step": 1510
    },
    {
      "epoch": 0.7,
      "learning_rate": 5.144043624000944e-05,
      "loss": 0.9456,
      "step": 1515
    },
    {
      "epoch": 0.7,
      "learning_rate": 5.0741764812558724e-05,
      "loss": 0.9434,
      "step": 1520
    },
    {
      "epoch": 0.7,
      "learning_rate": 5.00462539236628e-05,
      "loss": 0.9567,
      "step": 1525
    },
    {
      "epoch": 0.7,
      "learning_rate": 4.935394819913849e-05,
      "loss": 0.9528,
      "step": 1530
    },
    {
      "epoch": 0.7,
      "learning_rate": 4.8664892059150723e-05,
      "loss": 0.9367,
      "step": 1535
    },
    {
      "epoch": 0.71,
      "learning_rate": 4.7979129715362626e-05,
      "loss": 0.9558,
      "step": 1540
    },
    {
      "epoch": 0.71,
      "learning_rate": 4.72967051680985e-05,
      "loss": 0.9616,
      "step": 1545
    },
    {
      "epoch": 0.71,
      "learning_rate": 4.661766220352097e-05,
      "loss": 0.9527,
      "step": 1550
    },
    {
      "epoch": 0.71,
      "learning_rate": 4.5942044390821214e-05,
      "loss": 0.942,
      "step": 1555
    },
    {
      "epoch": 0.72,
      "learning_rate": 4.526989507942374e-05,
      "loss": 0.9435,
      "step": 1560
    },
    {
      "epoch": 0.72,
      "learning_rate": 4.460125739620479e-05,
      "loss": 0.9244,
      "step": 1565
    },
    {
      "epoch": 0.72,
      "learning_rate": 4.393617424272527e-05,
      "loss": 0.9669,
      "step": 1570
    },
    {
      "epoch": 0.72,
      "learning_rate": 4.3274688292478106e-05,
      "loss": 0.9575,
      "step": 1575
    },
    {
      "epoch": 0.73,
      "learning_rate": 4.261684198815003e-05,
      "loss": 0.958,
      "step": 1580
    },
    {
      "epoch": 0.73,
      "learning_rate": 4.1962677538898645e-05,
      "loss": 0.9391,
      "step": 1585
    },
    {
      "epoch": 0.73,
      "learning_rate": 4.131223691764383e-05,
      "loss": 0.932,
      "step": 1590
    },
    {
      "epoch": 0.73,
      "learning_rate": 4.0665561858374934e-05,
      "loss": 0.9601,
      "step": 1595
    },
    {
      "epoch": 0.73,
      "learning_rate": 4.0022693853472884e-05,
      "loss": 0.943,
      "step": 1600
    },
    {
      "epoch": 0.74,
      "learning_rate": 3.938367415104793e-05,
      "loss": 0.9406,
      "step": 1605
    },
    {
      "epoch": 0.74,
      "learning_rate": 3.8748543752293e-05,
      "loss": 0.9457,
      "step": 1610
    },
    {
      "epoch": 0.74,
      "learning_rate": 3.8117343408853127e-05,
      "loss": 0.9424,
      "step": 1615
    },
    {
      "epoch": 0.74,
      "learning_rate": 3.7490113620210485e-05,
      "loss": 0.9406,
      "step": 1620
    },
    {
      "epoch": 0.75,
      "learning_rate": 3.686689463108608e-05,
      "loss": 0.9414,
      "step": 1625
    },
    {
      "epoch": 0.75,
      "learning_rate": 3.624772642885734e-05,
      "loss": 0.9527,
      "step": 1630
    },
    {
      "epoch": 0.75,
      "learning_rate": 3.563264874099258e-05,
      "loss": 0.9572,
      "step": 1635
    },
    {
      "epoch": 0.75,
      "learning_rate": 3.502170103250177e-05,
      "loss": 0.9638,
      "step": 1640
    },
    {
      "epoch": 0.75,
      "learning_rate": 3.441492250340461e-05,
      "loss": 0.9635,
      "step": 1645
    },
    {
      "epoch": 0.76,
      "learning_rate": 3.381235208621522e-05,
      "loss": 0.9521,
      "step": 1650
    },
    {
      "epoch": 0.76,
      "learning_rate": 3.3214028443444036e-05,
      "loss": 0.9173,
      "step": 1655
    },
    {
      "epoch": 0.76,
      "learning_rate": 3.2619989965117356e-05,
      "loss": 0.9846,
      "step": 1660
    },
    {
      "epoch": 0.76,
      "learning_rate": 3.2030274766313865e-05,
      "loss": 0.9653,
      "step": 1665
    },
    {
      "epoch": 0.77,
      "learning_rate": 3.1444920684719394e-05,
      "loss": 0.9467,
      "step": 1670
    },
    {
      "epoch": 0.77,
      "learning_rate": 3.086396527819876e-05,
      "loss": 0.9321,
      "step": 1675
    },
    {
      "epoch": 0.77,
      "learning_rate": 3.028744582238633e-05,
      "loss": 0.9343,
      "step": 1680
    },
    {
      "epoch": 0.77,
      "learning_rate": 2.9715399308294e-05,
      "loss": 0.9647,
      "step": 1685
    },
    {
      "epoch": 0.78,
      "learning_rate": 2.914786243993808e-05,
      "loss": 0.9579,
      "step": 1690
    },
    {
      "epoch": 0.78,
      "learning_rate": 2.8584871631983888e-05,
      "loss": 0.9516,
      "step": 1695
    },
    {
      "epoch": 0.78,
      "learning_rate": 2.8026463007409664e-05,
      "loss": 0.9452,
      "step": 1700
    },
    {
      "epoch": 0.78,
      "learning_rate": 2.747267239518857e-05,
      "loss": 0.9831,
      "step": 1705
    },
    {
      "epoch": 0.78,
      "learning_rate": 2.6923535327989924e-05,
      "loss": 0.944,
      "step": 1710
    },
    {
      "epoch": 0.79,
      "learning_rate": 2.637908703989924e-05,
      "loss": 0.9344,
      "step": 1715
    },
    {
      "epoch": 0.79,
      "learning_rate": 2.5839362464157634e-05,
      "loss": 0.9247,
      "step": 1720
    },
    {
      "epoch": 0.79,
      "learning_rate": 2.5304396230920345e-05,
      "loss": 0.9407,
      "step": 1725
    },
    {
      "epoch": 0.79,
      "learning_rate": 2.477422266503473e-05,
      "loss": 0.9461,
      "step": 1730
    },
    {
      "epoch": 0.8,
      "learning_rate": 2.4248875783837987e-05,
      "loss": 0.9282,
      "step": 1735
    },
    {
      "epoch": 0.8,
      "learning_rate": 2.3728389294974475e-05,
      "loss": 0.9633,
      "step": 1740
    },
    {
      "epoch": 0.8,
      "learning_rate": 2.3212796594232943e-05,
      "loss": 0.9531,
      "step": 1745
    },
    {
      "epoch": 0.8,
      "learning_rate": 2.2702130763403673e-05,
      "loss": 0.9612,
      "step": 1750
    },
    {
      "epoch": 0.81,
      "learning_rate": 2.2196424568156073e-05,
      "loss": 0.9463,
      "step": 1755
    },
    {
      "epoch": 0.81,
      "learning_rate": 2.1695710455936115e-05,
      "loss": 0.9482,
      "step": 1760
    },
    {
      "epoch": 0.81,
      "learning_rate": 2.1200020553884604e-05,
      "loss": 0.9758,
      "step": 1765
    },
    {
      "epoch": 0.81,
      "learning_rate": 2.070938666677573e-05,
      "loss": 0.9313,
      "step": 1770
    },
    {
      "epoch": 0.81,
      "learning_rate": 2.0223840274976413e-05,
      "loss": 0.9348,
      "step": 1775
    },
    {
      "epoch": 0.82,
      "learning_rate": 1.974341253242635e-05,
      "loss": 0.9452,
      "step": 1780
    },
    {
      "epoch": 0.82,
      "learning_rate": 1.9268134264639272e-05,
      "loss": 0.9299,
      "step": 1785
    },
    {
      "epoch": 0.82,
      "learning_rate": 1.879803596672497e-05,
      "loss": 0.9704,
      "step": 1790
    },
    {
      "epoch": 0.82,
      "learning_rate": 1.8333147801432614e-05,
      "loss": 0.9808,
      "step": 1795
    },
    {
      "epoch": 0.83,
      "learning_rate": 1.7873499597215604e-05,
      "loss": 0.9529,
      "step": 1800
    },
    {
      "epoch": 0.83,
      "learning_rate": 1.741912084631746e-05,
      "loss": 0.9503,
      "step": 1805
    },
    {
      "epoch": 0.83,
      "learning_rate": 1.697004070287982e-05,
      "loss": 0.9607,
      "step": 1810
    },
    {
      "epoch": 0.83,
      "learning_rate": 1.6526287981071475e-05,
      "loss": 0.9486,
      "step": 1815
    },
    {
      "epoch": 0.84,
      "learning_rate": 1.608789115323993e-05,
      "loss": 0.9368,
      "step": 1820
    },
    {
      "epoch": 0.84,
      "learning_rate": 1.5654878348084244e-05,
      "loss": 0.9321,
      "step": 1825
    },
    {
      "epoch": 0.84,
      "learning_rate": 1.5227277348850466e-05,
      "loss": 0.9385,
      "step": 1830
    },
    {
      "epoch": 0.84,
      "learning_rate": 1.4805115591548746e-05,
      "loss": 0.9492,
      "step": 1835
    },
    {
      "epoch": 0.84,
      "learning_rate": 1.4388420163193217e-05,
      "loss": 0.9474,
      "step": 1840
    },
    {
      "epoch": 0.85,
      "learning_rate": 1.3977217800063846e-05,
      "loss": 0.9453,
      "step": 1845
    },
    {
      "epoch": 0.85,
      "learning_rate": 1.3571534885991044e-05,
      "loss": 0.9455,
      "step": 1850
    },
    {
      "epoch": 0.85,
      "learning_rate": 1.3171397450662715e-05,
      "loss": 0.9357,
      "step": 1855
    },
    {
      "epoch": 0.85,
      "learning_rate": 1.277683116795425e-05,
      "loss": 0.9337,
      "step": 1860
    },
    {
      "epoch": 0.86,
      "learning_rate": 1.2387861354281194e-05,
      "loss": 0.9389,
      "step": 1865
    },
    {
      "epoch": 0.86,
      "learning_rate": 1.2004512966974745e-05,
      "loss": 0.956,
      "step": 1870
    },
    {
      "epoch": 0.86,
      "learning_rate": 1.162681060268065e-05,
      "loss": 0.9514,
      "step": 1875
    },
    {
      "epoch": 0.86,
      "learning_rate": 1.1254778495780748e-05,
      "loss": 0.9247,
      "step": 1880
    },
    {
      "epoch": 0.87,
      "learning_rate": 1.0888440516838373e-05,
      "loss": 0.9509,
      "step": 1885
    },
    {
      "epoch": 0.87,
      "learning_rate": 1.0527820171066372e-05,
      "loss": 0.9588,
      "step": 1890
    },
    {
      "epoch": 0.87,
      "learning_rate": 1.0172940596819259e-05,
      "loss": 0.9608,
      "step": 1895
    },
    {
      "epoch": 0.87,
      "learning_rate": 9.823824564108408e-06,
      "loss": 0.9467,
      "step": 1900
    },
    {
      "epoch": 0.87,
      "learning_rate": 9.480494473141188e-06,
      "loss": 0.9543,
      "step": 1905
    },
    {
      "epoch": 0.88,
      "learning_rate": 9.142972352883594e-06,
      "loss": 0.9566,
      "step": 1910
    },
    {
      "epoch": 0.88,
      "learning_rate": 8.811279859646915e-06,
      "loss": 0.9541,
      "step": 1915
    },
    {
      "epoch": 0.88,
      "learning_rate": 8.485438275698154e-06,
      "loss": 0.9445,
      "step": 1920
    },
    {
      "epoch": 0.88,
      "learning_rate": 8.165468507894514e-06,
      "loss": 0.9209,
      "step": 1925
    },
    {
      "epoch": 0.89,
      "learning_rate": 7.851391086341952e-06,
      "loss": 0.9509,
      "step": 1930
    },
    {
      "epoch": 0.89,
      "learning_rate": 7.543226163077899e-06,
      "loss": 0.9576,
      "step": 1935
    },
    {
      "epoch": 0.89,
      "learning_rate": 7.240993510778305e-06,
      "loss": 0.9176,
      "step": 1940
    },
    {
      "epoch": 0.89,
      "learning_rate": 6.9447125214888835e-06,
      "loss": 0.9517,
      "step": 1945
    },
    {
      "epoch": 0.89,
      "learning_rate": 6.65440220538096e-06,
      "loss": 0.9372,
      "step": 1950
    },
    {
      "epoch": 0.9,
      "learning_rate": 6.370081189531707e-06,
      "loss": 0.9527,
      "step": 1955
    },
    {
      "epoch": 0.9,
      "learning_rate": 6.091767716728924e-06,
      "loss": 0.9653,
      "step": 1960
    },
    {
      "epoch": 0.9,
      "learning_rate": 5.819479644300563e-06,
      "loss": 0.9257,
      "step": 1965
    },
    {
      "epoch": 0.9,
      "learning_rate": 5.553234442969013e-06,
      "loss": 0.9785,
      "step": 1970
    },
    {
      "epoch": 0.91,
      "learning_rate": 5.293049195730038e-06,
      "loss": 0.9568,
      "step": 1975
    },
    {
      "epoch": 0.91,
      "learning_rate": 5.038940596756747e-06,
      "loss": 0.9402,
      "step": 1980
    },
    {
      "epoch": 0.91,
      "learning_rate": 4.790924950328435e-06,
      "loss": 0.9443,
      "step": 1985
    },
    {
      "epoch": 0.91,
      "learning_rate": 4.5490181697844916e-06,
      "loss": 0.9535,
      "step": 1990
    },
    {
      "epoch": 0.92,
      "learning_rate": 4.313235776503244e-06,
      "loss": 0.9405,
      "step": 1995
    },
    {
      "epoch": 0.92,
      "learning_rate": 4.08359289890623e-06,
      "loss": 0.9505,
      "step": 2000
    },
    {
      "epoch": 0.92,
      "learning_rate": 3.860104271487397e-06,
      "loss": 0.9569,
      "step": 2005
    },
    {
      "epoch": 0.92,
      "learning_rate": 3.6427842338677352e-06,
      "loss": 0.9419,
      "step": 2010
    },
    {
      "epoch": 0.92,
      "learning_rate": 3.4316467298752263e-06,
      "loss": 0.9239,
      "step": 2015
    },
    {
      "epoch": 0.93,
      "learning_rate": 3.226705306650113e-06,
      "loss": 0.946,
      "step": 2020
    },
    {
      "epoch": 0.93,
      "learning_rate": 3.0279731137757948e-06,
      "loss": 0.94,
      "step": 2025
    },
    {
      "epoch": 0.93,
      "learning_rate": 2.835462902434971e-06,
      "loss": 0.9607,
      "step": 2030
    },
    {
      "epoch": 0.93,
      "learning_rate": 2.649187024591604e-06,
      "loss": 0.9559,
      "step": 2035
    },
    {
      "epoch": 0.94,
      "learning_rate": 2.4691574321983215e-06,
      "loss": 0.959,
      "step": 2040
    },
    {
      "epoch": 0.94,
      "learning_rate": 2.2953856764295624e-06,
      "loss": 0.9536,
      "step": 2045
    },
    {
      "epoch": 0.94,
      "learning_rate": 2.1278829069404484e-06,
      "loss": 0.9233,
      "step": 2050
    },
    {
      "epoch": 0.94,
      "learning_rate": 1.966659871151366e-06,
      "loss": 0.9339,
      "step": 2055
    },
    {
      "epoch": 0.95,
      "learning_rate": 1.811726913558387e-06,
      "loss": 0.9364,
      "step": 2060
    },
    {
      "epoch": 0.95,
      "learning_rate": 1.6630939750695519e-06,
      "loss": 0.9281,
      "step": 2065
    },
    {
      "epoch": 0.95,
      "learning_rate": 1.5207705923670157e-06,
      "loss": 0.9581,
      "step": 2070
    },
    {
      "epoch": 0.95,
      "learning_rate": 1.3847658972951483e-06,
      "loss": 0.9191,
      "step": 2075
    },
    {
      "epoch": 0.95,
      "learning_rate": 1.2550886162746467e-06,
      "loss": 0.95,
      "step": 2080
    },
    {
      "epoch": 0.96,
      "learning_rate": 1.1317470697425837e-06,
      "loss": 0.9686,
      "step": 2085
    },
    {
      "epoch": 0.96,
      "learning_rate": 1.0147491716185676e-06,
      "loss": 0.958,
      "step": 2090
    },
    {
      "epoch": 0.96,
      "learning_rate": 9.04102428796949e-07,
      "loss": 0.9578,
      "step": 2095
    },
    {
      "epoch": 0.96,
      "learning_rate": 7.99813940665195e-07,
      "loss": 0.9487,
      "step": 2100
    },
    {
      "epoch": 0.97,
      "learning_rate": 7.018903986483083e-07,
      "loss": 0.9474,
      "step": 2105
    },
    {
      "epoch": 0.97,
      "learning_rate": 6.103380857795604e-07,
      "loss": 0.9377,
      "step": 2110
    },
    {
      "epoch": 0.97,
      "learning_rate": 5.251628762972916e-07,
      "loss": 0.9453,
      "step": 2115
    },
    {
      "epoch": 0.97,
      "learning_rate": 4.463702352680787e-07,
      "loss": 0.9353,
      "step": 2120
    },
    {
      "epoch": 0.98,
      "learning_rate": 3.7396521823600537e-07,
      "loss": 0.9256,
      "step": 2125
    },
    {
      "epoch": 0.98,
      "learning_rate": 3.079524708983095e-07,
      "loss": 0.9437,
      "step": 2130
    },
    {
      "epoch": 0.98,
      "learning_rate": 2.483362288073443e-07,
      "loss": 0.9629,
      "step": 2135
    },
    {
      "epoch": 0.98,
      "learning_rate": 1.9512031709874035e-07,
      "loss": 0.9361,
      "step": 2140
    },
    {
      "epoch": 0.98,
      "learning_rate": 1.4830815024606815e-07,
      "loss": 0.9511,
      "step": 2145
    },
    {
      "epoch": 0.99,
      "learning_rate": 1.0790273184164701e-07,
      "loss": 0.9489,
      "step": 2150
    },
    {
      "epoch": 0.99,
      "learning_rate": 7.390665440393241e-08,
      "loss": 0.9875,
      "step": 2155
    },
    {
      "epoch": 0.99,
      "learning_rate": 4.632209921107134e-08,
      "loss": 0.9478,
      "step": 2160
    },
    {
      "epoch": 0.99,
      "learning_rate": 2.5150836161058622e-08,
      "loss": 0.9372,
      "step": 2165
    },
    {
      "epoch": 1.0,
      "learning_rate": 1.03942236580723e-08,
      "loss": 0.939,
      "step": 2170
    },
    {
      "epoch": 1.0,
      "learning_rate": 2.053208525365502e-09,
      "loss": 0.9427,
      "step": 2175
    },
    {
      "epoch": 1.0,
      "eval_loss": 0.9502024054527283,
      "eval_runtime": 365.637,
      "eval_samples_per_second": 42.203,
      "eval_steps_per_second": 0.662,
      "step": 2179
    },
    {
      "epoch": 1.0,
      "step": 2179,
      "total_flos": 1.225695388701714e+19,
      "train_loss": 0.9579998909633823,
      "train_runtime": 11823.5935,
      "train_samples_per_second": 11.792,
      "train_steps_per_second": 0.184
    }
  ],
  "logging_steps": 5,
  "max_steps": 2179,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 100,
  "total_flos": 1.225695388701714e+19,
  "train_batch_size": 4,
  "trial_name": null,
  "trial_params": null
}