{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 1.0,
  "eval_steps": 500,
  "global_step": 315,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0031746031746031746,
      "grad_norm": 5.5625,
      "learning_rate": 2e-05,
      "loss": 0.4882,
      "step": 1
    },
    {
      "epoch": 0.006349206349206349,
      "grad_norm": 4.84375,
      "learning_rate": 4e-05,
      "loss": 0.5092,
      "step": 2
    },
    {
      "epoch": 0.009523809523809525,
      "grad_norm": 10.5625,
      "learning_rate": 6e-05,
      "loss": 0.584,
      "step": 3
    },
    {
      "epoch": 0.012698412698412698,
      "grad_norm": 5.71875,
      "learning_rate": 8e-05,
      "loss": 0.4811,
      "step": 4
    },
    {
      "epoch": 0.015873015873015872,
      "grad_norm": 8.3125,
      "learning_rate": 0.0001,
      "loss": 0.6836,
      "step": 5
    },
    {
      "epoch": 0.01904761904761905,
      "grad_norm": 19.5,
      "learning_rate": 0.00012,
      "loss": 0.9705,
      "step": 6
    },
    {
      "epoch": 0.022222222222222223,
      "grad_norm": 35.5,
      "learning_rate": 0.00014,
      "loss": 1.1903,
      "step": 7
    },
    {
      "epoch": 0.025396825396825397,
      "grad_norm": 17.875,
      "learning_rate": 0.00016,
      "loss": 1.1362,
      "step": 8
    },
    {
      "epoch": 0.02857142857142857,
      "grad_norm": 19.875,
      "learning_rate": 0.00018,
      "loss": 1.4816,
      "step": 9
    },
    {
      "epoch": 0.031746031746031744,
      "grad_norm": 29.125,
      "learning_rate": 0.0002,
      "loss": 1.7281,
      "step": 10
    },
    {
      "epoch": 0.03492063492063492,
      "grad_norm": 102.0,
      "learning_rate": 0.00019999968417282543,
      "loss": 3.067,
      "step": 11
    },
    {
      "epoch": 0.0380952380952381,
      "grad_norm": 71.5,
      "learning_rate": 0.0001999987366932966,
      "loss": 2.223,
      "step": 12
    },
    {
      "epoch": 0.04126984126984127,
      "grad_norm": 11.875,
      "learning_rate": 0.00019999715756739833,
      "loss": 1.6384,
      "step": 13
    },
    {
      "epoch": 0.044444444444444446,
      "grad_norm": 19.875,
      "learning_rate": 0.00019999494680510518,
      "loss": 1.6407,
      "step": 14
    },
    {
      "epoch": 0.047619047619047616,
      "grad_norm": 15.25,
      "learning_rate": 0.00019999210442038162,
      "loss": 1.5053,
      "step": 15
    },
    {
      "epoch": 0.050793650793650794,
      "grad_norm": 77.0,
      "learning_rate": 0.00019998863043118163,
      "loss": 1.9586,
      "step": 16
    },
    {
      "epoch": 0.05396825396825397,
      "grad_norm": 33.0,
      "learning_rate": 0.00019998452485944887,
      "loss": 2.3313,
      "step": 17
    },
    {
      "epoch": 0.05714285714285714,
      "grad_norm": 14.6875,
      "learning_rate": 0.0001999797877311163,
      "loss": 1.5517,
      "step": 18
    },
    {
      "epoch": 0.06031746031746032,
      "grad_norm": 24.375,
      "learning_rate": 0.00019997441907610624,
      "loss": 1.7327,
      "step": 19
    },
    {
      "epoch": 0.06349206349206349,
      "grad_norm": 11.0625,
      "learning_rate": 0.00019996841892833,
      "loss": 1.4351,
      "step": 20
    },
    {
      "epoch": 0.06666666666666667,
      "grad_norm": 11.3125,
      "learning_rate": 0.00019996178732568782,
      "loss": 1.4974,
      "step": 21
    },
    {
      "epoch": 0.06984126984126984,
      "grad_norm": 10.0625,
      "learning_rate": 0.00019995452431006844,
      "loss": 1.3888,
      "step": 22
    },
    {
      "epoch": 0.07301587301587302,
      "grad_norm": 8.3125,
      "learning_rate": 0.0001999466299273491,
      "loss": 1.4097,
      "step": 23
    },
    {
      "epoch": 0.0761904761904762,
      "grad_norm": 8.0625,
      "learning_rate": 0.00019993810422739495,
      "loss": 1.4168,
      "step": 24
    },
    {
      "epoch": 0.07936507936507936,
      "grad_norm": 10.125,
      "learning_rate": 0.00019992894726405893,
      "loss": 1.6777,
      "step": 25
    },
    {
      "epoch": 0.08253968253968254,
      "grad_norm": 14.25,
      "learning_rate": 0.00019991915909518143,
      "loss": 1.6031,
      "step": 26
    },
    {
      "epoch": 0.08571428571428572,
      "grad_norm": 7.75,
      "learning_rate": 0.0001999087397825899,
      "loss": 1.4771,
      "step": 27
    },
    {
      "epoch": 0.08888888888888889,
      "grad_norm": 6.90625,
      "learning_rate": 0.00019989768939209824,
      "loss": 1.2748,
      "step": 28
    },
    {
      "epoch": 0.09206349206349207,
      "grad_norm": 9.625,
      "learning_rate": 0.00019988600799350685,
      "loss": 1.4211,
      "step": 29
    },
    {
      "epoch": 0.09523809523809523,
      "grad_norm": 9.4375,
      "learning_rate": 0.00019987369566060176,
      "loss": 1.6158,
      "step": 30
    },
    {
      "epoch": 0.09841269841269841,
      "grad_norm": 4.75,
      "learning_rate": 0.00019986075247115432,
      "loss": 0.9995,
      "step": 31
    },
    {
      "epoch": 0.10158730158730159,
      "grad_norm": 5.8125,
      "learning_rate": 0.0001998471785069208,
      "loss": 0.9024,
      "step": 32
    },
    {
      "epoch": 0.10476190476190476,
      "grad_norm": 7.96875,
      "learning_rate": 0.00019983297385364166,
      "loss": 1.6809,
      "step": 33
    },
    {
      "epoch": 0.10793650793650794,
      "grad_norm": 8.0625,
      "learning_rate": 0.00019981813860104128,
      "loss": 1.2161,
      "step": 34
    },
    {
      "epoch": 0.1111111111111111,
      "grad_norm": 6.125,
      "learning_rate": 0.00019980267284282717,
      "loss": 1.2645,
      "step": 35
    },
    {
      "epoch": 0.11428571428571428,
      "grad_norm": 7.59375,
      "learning_rate": 0.00019978657667668942,
      "loss": 1.7419,
      "step": 36
    },
    {
      "epoch": 0.11746031746031746,
      "grad_norm": 7.21875,
      "learning_rate": 0.00019976985020430022,
      "loss": 1.465,
      "step": 37
    },
    {
      "epoch": 0.12063492063492064,
      "grad_norm": 13.1875,
      "learning_rate": 0.00019975249353131305,
      "loss": 1.8324,
      "step": 38
    },
    {
      "epoch": 0.12380952380952381,
      "grad_norm": 11.0625,
      "learning_rate": 0.00019973450676736204,
      "loss": 1.6745,
      "step": 39
    },
    {
      "epoch": 0.12698412698412698,
      "grad_norm": 5.03125,
      "learning_rate": 0.0001997158900260614,
      "loss": 1.3337,
      "step": 40
    },
    {
      "epoch": 0.13015873015873017,
      "grad_norm": 4.75,
      "learning_rate": 0.0001996966434250046,
      "loss": 1.151,
      "step": 41
    },
    {
      "epoch": 0.13333333333333333,
      "grad_norm": 6.0,
      "learning_rate": 0.00019967676708576362,
      "loss": 1.1229,
      "step": 42
    },
    {
      "epoch": 0.1365079365079365,
      "grad_norm": 7.90625,
      "learning_rate": 0.00019965626113388824,
      "loss": 1.7332,
      "step": 43
    },
    {
      "epoch": 0.13968253968253969,
      "grad_norm": 5.1875,
      "learning_rate": 0.00019963512569890512,
      "loss": 1.5288,
      "step": 44
    },
    {
      "epoch": 0.14285714285714285,
      "grad_norm": 5.09375,
      "learning_rate": 0.00019961336091431727,
      "loss": 1.4823,
      "step": 45
    },
    {
      "epoch": 0.14603174603174604,
      "grad_norm": 5.75,
      "learning_rate": 0.00019959096691760282,
      "loss": 1.7105,
      "step": 46
    },
    {
      "epoch": 0.1492063492063492,
      "grad_norm": 5.8125,
      "learning_rate": 0.00019956794385021442,
      "loss": 1.4352,
      "step": 47
    },
    {
      "epoch": 0.1523809523809524,
      "grad_norm": 10.1875,
      "learning_rate": 0.00019954429185757832,
      "loss": 1.5014,
      "step": 48
    },
    {
      "epoch": 0.15555555555555556,
      "grad_norm": 8.625,
      "learning_rate": 0.00019952001108909336,
      "loss": 1.3925,
      "step": 49
    },
    {
      "epoch": 0.15873015873015872,
      "grad_norm": 4.21875,
      "learning_rate": 0.00019949510169813003,
      "loss": 1.1968,
      "step": 50
    },
    {
      "epoch": 0.1619047619047619,
      "grad_norm": 5.75,
      "learning_rate": 0.0001994695638420296,
      "loss": 1.6516,
      "step": 51
    },
    {
      "epoch": 0.16507936507936508,
      "grad_norm": 7.625,
      "learning_rate": 0.00019944339768210306,
      "loss": 1.5957,
      "step": 52
    },
    {
      "epoch": 0.16825396825396827,
      "grad_norm": 5.90625,
      "learning_rate": 0.0001994166033836301,
      "loss": 1.347,
      "step": 53
    },
    {
      "epoch": 0.17142857142857143,
      "grad_norm": 7.75,
      "learning_rate": 0.00019938918111585805,
      "loss": 1.4683,
      "step": 54
    },
    {
      "epoch": 0.1746031746031746,
      "grad_norm": 3.84375,
      "learning_rate": 0.00019936113105200085,
      "loss": 1.0574,
      "step": 55
    },
    {
      "epoch": 0.17777777777777778,
      "grad_norm": 4.5,
      "learning_rate": 0.000199332453369238,
      "loss": 1.4662,
      "step": 56
    },
    {
      "epoch": 0.18095238095238095,
      "grad_norm": 5.71875,
      "learning_rate": 0.00019930314824871326,
      "loss": 1.1714,
      "step": 57
    },
    {
      "epoch": 0.18412698412698414,
      "grad_norm": 4.875,
      "learning_rate": 0.00019927321587553376,
      "loss": 1.2882,
      "step": 58
    },
    {
      "epoch": 0.1873015873015873,
      "grad_norm": 9.0,
      "learning_rate": 0.0001992426564387686,
      "loss": 1.31,
      "step": 59
    },
    {
      "epoch": 0.19047619047619047,
      "grad_norm": 5.125,
      "learning_rate": 0.0001992114701314478,
      "loss": 1.4787,
      "step": 60
    },
    {
      "epoch": 0.19365079365079366,
      "grad_norm": 4.53125,
      "learning_rate": 0.00019917965715056103,
      "loss": 1.3568,
      "step": 61
    },
    {
      "epoch": 0.19682539682539682,
      "grad_norm": 5.03125,
      "learning_rate": 0.00019914721769705634,
      "loss": 1.2429,
      "step": 62
    },
    {
      "epoch": 0.2,
      "grad_norm": 4.71875,
      "learning_rate": 0.00019911415197583905,
      "loss": 1.1885,
      "step": 63
    },
    {
      "epoch": 0.20317460317460317,
      "grad_norm": 4.75,
      "learning_rate": 0.00019908046019577008,
      "loss": 1.465,
      "step": 64
    },
    {
      "epoch": 0.20634920634920634,
      "grad_norm": 5.59375,
      "learning_rate": 0.00019904614256966512,
      "loss": 1.6841,
      "step": 65
    },
    {
      "epoch": 0.20952380952380953,
      "grad_norm": 6.28125,
      "learning_rate": 0.00019901119931429296,
      "loss": 1.3299,
      "step": 66
    },
    {
      "epoch": 0.2126984126984127,
      "grad_norm": 5.03125,
      "learning_rate": 0.0001989756306503741,
      "loss": 1.3073,
      "step": 67
    },
    {
      "epoch": 0.21587301587301588,
      "grad_norm": 3.5625,
      "learning_rate": 0.00019893943680257962,
      "loss": 1.3444,
      "step": 68
    },
    {
      "epoch": 0.21904761904761905,
      "grad_norm": 9.1875,
      "learning_rate": 0.00019890261799952955,
      "loss": 1.5232,
      "step": 69
    },
    {
      "epoch": 0.2222222222222222,
      "grad_norm": 5.03125,
      "learning_rate": 0.0001988651744737914,
      "loss": 1.3022,
      "step": 70
    },
    {
      "epoch": 0.2253968253968254,
      "grad_norm": 6.8125,
      "learning_rate": 0.00019882710646187886,
      "loss": 1.5566,
      "step": 71
    },
    {
      "epoch": 0.22857142857142856,
      "grad_norm": 5.0,
      "learning_rate": 0.00019878841420425023,
      "loss": 1.1856,
      "step": 72
    },
    {
      "epoch": 0.23174603174603176,
      "grad_norm": 5.875,
      "learning_rate": 0.00019874909794530675,
      "loss": 1.4443,
      "step": 73
    },
    {
      "epoch": 0.23492063492063492,
      "grad_norm": 4.34375,
      "learning_rate": 0.00019870915793339137,
      "loss": 1.3829,
      "step": 74
    },
    {
      "epoch": 0.23809523809523808,
      "grad_norm": 3.921875,
      "learning_rate": 0.0001986685944207868,
      "loss": 1.2855,
      "step": 75
    },
    {
      "epoch": 0.24126984126984127,
      "grad_norm": 6.125,
      "learning_rate": 0.00019862740766371436,
      "loss": 1.429,
      "step": 76
    },
    {
      "epoch": 0.24444444444444444,
      "grad_norm": 4.5,
      "learning_rate": 0.00019858559792233188,
      "loss": 1.3491,
      "step": 77
    },
    {
      "epoch": 0.24761904761904763,
      "grad_norm": 5.84375,
      "learning_rate": 0.0001985431654607325,
      "loss": 1.2587,
      "step": 78
    },
    {
      "epoch": 0.2507936507936508,
      "grad_norm": 3.890625,
      "learning_rate": 0.0001985001105469426,
      "loss": 0.9128,
      "step": 79
    },
    {
      "epoch": 0.25396825396825395,
      "grad_norm": 5.3125,
      "learning_rate": 0.00019845643345292054,
      "loss": 1.2216,
      "step": 80
    },
    {
      "epoch": 0.2571428571428571,
      "grad_norm": 5.71875,
      "learning_rate": 0.0001984121344545545,
      "loss": 1.2427,
      "step": 81
    },
    {
      "epoch": 0.26031746031746034,
      "grad_norm": 7.625,
      "learning_rate": 0.0001983672138316611,
      "loss": 1.0946,
      "step": 82
    },
    {
      "epoch": 0.2634920634920635,
      "grad_norm": 6.75,
      "learning_rate": 0.00019832167186798331,
      "loss": 1.7476,
      "step": 83
    },
    {
      "epoch": 0.26666666666666666,
      "grad_norm": 4.875,
      "learning_rate": 0.00019827550885118903,
      "loss": 1.4327,
      "step": 84
    },
    {
      "epoch": 0.2698412698412698,
      "grad_norm": 7.5625,
      "learning_rate": 0.0001982287250728689,
      "loss": 1.5031,
      "step": 85
    },
    {
      "epoch": 0.273015873015873,
      "grad_norm": 6.6875,
      "learning_rate": 0.00019818132082853466,
      "loss": 1.7595,
      "step": 86
    },
    {
      "epoch": 0.2761904761904762,
      "grad_norm": 4.5625,
      "learning_rate": 0.0001981332964176174,
      "loss": 1.3127,
      "step": 87
    },
    {
      "epoch": 0.27936507936507937,
      "grad_norm": 4.8125,
      "learning_rate": 0.00019808465214346524,
      "loss": 1.0837,
      "step": 88
    },
    {
      "epoch": 0.28253968253968254,
      "grad_norm": 3.625,
      "learning_rate": 0.00019803538831334198,
      "loss": 1.236,
      "step": 89
    },
    {
      "epoch": 0.2857142857142857,
      "grad_norm": 8.5,
      "learning_rate": 0.0001979855052384247,
      "loss": 1.4098,
      "step": 90
    },
    {
      "epoch": 0.28888888888888886,
      "grad_norm": 6.59375,
      "learning_rate": 0.000197935003233802,
      "loss": 1.4328,
      "step": 91
    },
    {
      "epoch": 0.2920634920634921,
      "grad_norm": 5.90625,
      "learning_rate": 0.00019788388261847203,
      "loss": 1.2988,
      "step": 92
    },
    {
      "epoch": 0.29523809523809524,
      "grad_norm": 3.3125,
      "learning_rate": 0.00019783214371534035,
      "loss": 1.2953,
      "step": 93
    },
    {
      "epoch": 0.2984126984126984,
      "grad_norm": 4.84375,
      "learning_rate": 0.00019777978685121798,
      "loss": 1.5484,
      "step": 94
    },
    {
      "epoch": 0.30158730158730157,
      "grad_norm": 4.59375,
      "learning_rate": 0.00019772681235681936,
      "loss": 1.4477,
      "step": 95
    },
    {
      "epoch": 0.3047619047619048,
      "grad_norm": 5.0625,
      "learning_rate": 0.00019767322056676016,
      "loss": 1.5552,
      "step": 96
    },
    {
      "epoch": 0.30793650793650795,
      "grad_norm": 3.921875,
      "learning_rate": 0.0001976190118195553,
      "loss": 1.0938,
      "step": 97
    },
    {
      "epoch": 0.3111111111111111,
      "grad_norm": 4.3125,
      "learning_rate": 0.0001975641864576166,
      "loss": 1.3172,
      "step": 98
    },
    {
      "epoch": 0.3142857142857143,
      "grad_norm": 5.625,
      "learning_rate": 0.00019750874482725092,
      "loss": 1.4208,
      "step": 99
    },
    {
      "epoch": 0.31746031746031744,
      "grad_norm": 3.6875,
      "learning_rate": 0.00019745268727865774,
      "loss": 1.1331,
      "step": 100
    },
    {
      "epoch": 0.32063492063492066,
      "grad_norm": 4.65625,
      "learning_rate": 0.00019739601416592691,
      "loss": 1.4513,
      "step": 101
    },
    {
      "epoch": 0.3238095238095238,
      "grad_norm": 3.890625,
      "learning_rate": 0.00019733872584703672,
      "loss": 1.0613,
      "step": 102
    },
    {
      "epoch": 0.326984126984127,
      "grad_norm": 6.03125,
      "learning_rate": 0.00019728082268385125,
      "loss": 1.2647,
      "step": 103
    },
    {
      "epoch": 0.33015873015873015,
      "grad_norm": 4.90625,
      "learning_rate": 0.00019722230504211843,
      "loss": 1.2359,
      "step": 104
    },
    {
      "epoch": 0.3333333333333333,
      "grad_norm": 5.09375,
      "learning_rate": 0.0001971631732914674,
      "loss": 1.4131,
      "step": 105
    },
    {
      "epoch": 0.33650793650793653,
      "grad_norm": 5.8125,
      "learning_rate": 0.00019710342780540648,
      "loss": 1.4764,
      "step": 106
    },
    {
      "epoch": 0.3396825396825397,
      "grad_norm": 3.5625,
      "learning_rate": 0.00019704306896132064,
      "loss": 1.1251,
      "step": 107
    },
    {
      "epoch": 0.34285714285714286,
      "grad_norm": 3.609375,
      "learning_rate": 0.0001969820971404691,
      "loss": 1.2523,
      "step": 108
    },
    {
      "epoch": 0.346031746031746,
      "grad_norm": 4.25,
      "learning_rate": 0.00019692051272798304,
      "loss": 1.31,
      "step": 109
    },
    {
      "epoch": 0.3492063492063492,
      "grad_norm": 4.625,
      "learning_rate": 0.0001968583161128631,
      "loss": 1.4099,
      "step": 110
    },
    {
      "epoch": 0.3523809523809524,
      "grad_norm": 4.125,
      "learning_rate": 0.00019679550768797693,
      "loss": 1.1298,
      "step": 111
    },
    {
      "epoch": 0.35555555555555557,
      "grad_norm": 3.859375,
      "learning_rate": 0.0001967320878500566,
      "loss": 1.0828,
      "step": 112
    },
    {
      "epoch": 0.35873015873015873,
      "grad_norm": 5.5,
      "learning_rate": 0.0001966680569996963,
      "loss": 1.4486,
      "step": 113
    },
    {
      "epoch": 0.3619047619047619,
      "grad_norm": 5.46875,
      "learning_rate": 0.0001966034155413497,
      "loss": 1.3412,
      "step": 114
    },
    {
      "epoch": 0.36507936507936506,
      "grad_norm": 4.75,
      "learning_rate": 0.0001965381638833274,
      "loss": 1.2534,
      "step": 115
    },
    {
      "epoch": 0.3682539682539683,
      "grad_norm": 4.1875,
      "learning_rate": 0.00019647230243779432,
      "loss": 1.4807,
      "step": 116
    },
    {
      "epoch": 0.37142857142857144,
      "grad_norm": 5.78125,
      "learning_rate": 0.0001964058316207671,
      "loss": 1.6319,
      "step": 117
    },
    {
      "epoch": 0.3746031746031746,
      "grad_norm": 4.65625,
      "learning_rate": 0.00019633875185211158,
      "loss": 1.3659,
      "step": 118
    },
    {
      "epoch": 0.37777777777777777,
      "grad_norm": 6.0,
      "learning_rate": 0.00019627106355554007,
      "loss": 1.2221,
      "step": 119
    },
    {
      "epoch": 0.38095238095238093,
      "grad_norm": 5.125,
      "learning_rate": 0.0001962027671586086,
      "loss": 1.1326,
      "step": 120
    },
    {
      "epoch": 0.38412698412698415,
      "grad_norm": 4.59375,
      "learning_rate": 0.00019613386309271435,
      "loss": 1.2941,
      "step": 121
    },
    {
      "epoch": 0.3873015873015873,
      "grad_norm": 5.78125,
      "learning_rate": 0.0001960643517930928,
      "loss": 1.4116,
      "step": 122
    },
    {
      "epoch": 0.3904761904761905,
      "grad_norm": 4.4375,
      "learning_rate": 0.0001959942336988152,
      "loss": 1.4073,
      "step": 123
    },
    {
      "epoch": 0.39365079365079364,
      "grad_norm": 3.484375,
      "learning_rate": 0.00019592350925278545,
      "loss": 1.2554,
      "step": 124
    },
    {
      "epoch": 0.3968253968253968,
      "grad_norm": 3.90625,
      "learning_rate": 0.0001958521789017376,
      "loss": 1.5309,
      "step": 125
    },
    {
      "epoch": 0.4,
      "grad_norm": 4.90625,
      "learning_rate": 0.00019578024309623295,
      "loss": 1.2464,
      "step": 126
    },
    {
      "epoch": 0.4031746031746032,
      "grad_norm": 4.34375,
      "learning_rate": 0.00019570770229065715,
      "loss": 1.1707,
      "step": 127
    },
    {
      "epoch": 0.40634920634920635,
      "grad_norm": 6.125,
      "learning_rate": 0.0001956345569432173,
      "loss": 1.274,
      "step": 128
    },
    {
      "epoch": 0.4095238095238095,
      "grad_norm": 4.8125,
      "learning_rate": 0.00019556080751593918,
      "loss": 1.28,
      "step": 129
    },
    {
      "epoch": 0.4126984126984127,
      "grad_norm": 6.9375,
      "learning_rate": 0.00019548645447466431,
      "loss": 1.6019,
      "step": 130
    },
    {
      "epoch": 0.4158730158730159,
      "grad_norm": 4.1875,
      "learning_rate": 0.00019541149828904687,
      "loss": 1.286,
      "step": 131
    },
    {
      "epoch": 0.41904761904761906,
      "grad_norm": 5.53125,
      "learning_rate": 0.00019533593943255086,
      "loss": 1.2265,
      "step": 132
    },
    {
      "epoch": 0.4222222222222222,
      "grad_norm": 4.4375,
      "learning_rate": 0.0001952597783824471,
      "loss": 1.1624,
      "step": 133
    },
    {
      "epoch": 0.4253968253968254,
      "grad_norm": 4.125,
      "learning_rate": 0.00019518301561981014,
      "loss": 1.5051,
      "step": 134
    },
    {
      "epoch": 0.42857142857142855,
      "grad_norm": 2.671875,
      "learning_rate": 0.00019510565162951537,
      "loss": 0.7997,
      "step": 135
    },
    {
      "epoch": 0.43174603174603177,
      "grad_norm": 4.03125,
      "learning_rate": 0.00019502768690023574,
      "loss": 1.3338,
      "step": 136
    },
    {
      "epoch": 0.43492063492063493,
      "grad_norm": 7.0,
      "learning_rate": 0.0001949491219244389,
      "loss": 1.4556,
      "step": 137
    },
    {
      "epoch": 0.4380952380952381,
      "grad_norm": 3.796875,
      "learning_rate": 0.00019486995719838392,
      "loss": 1.2246,
      "step": 138
    },
    {
      "epoch": 0.44126984126984126,
      "grad_norm": 3.3125,
      "learning_rate": 0.00019479019322211823,
      "loss": 1.0053,
      "step": 139
    },
    {
      "epoch": 0.4444444444444444,
      "grad_norm": 6.25,
      "learning_rate": 0.00019470983049947444,
      "loss": 1.3433,
      "step": 140
    },
    {
      "epoch": 0.44761904761904764,
      "grad_norm": 8.625,
      "learning_rate": 0.0001946288695380672,
      "loss": 1.4911,
      "step": 141
    },
    {
      "epoch": 0.4507936507936508,
      "grad_norm": 4.1875,
      "learning_rate": 0.00019454731084928993,
      "loss": 1.2431,
      "step": 142
    },
    {
      "epoch": 0.45396825396825397,
      "grad_norm": 3.421875,
      "learning_rate": 0.00019446515494831167,
      "loss": 1.1637,
      "step": 143
    },
    {
      "epoch": 0.45714285714285713,
      "grad_norm": 4.21875,
      "learning_rate": 0.00019438240235407375,
      "loss": 1.1885,
      "step": 144
    },
    {
      "epoch": 0.4603174603174603,
      "grad_norm": 3.96875,
      "learning_rate": 0.00019429905358928646,
      "loss": 1.3931,
      "step": 145
    },
    {
      "epoch": 0.4634920634920635,
      "grad_norm": 4.65625,
      "learning_rate": 0.00019421510918042593,
      "loss": 1.1286,
      "step": 146
    },
    {
      "epoch": 0.4666666666666667,
      "grad_norm": 3.25,
      "learning_rate": 0.0001941305696577307,
      "loss": 1.0868,
      "step": 147
    },
    {
      "epoch": 0.46984126984126984,
      "grad_norm": 3.140625,
      "learning_rate": 0.00019404543555519833,
      "loss": 1.1095,
      "step": 148
    },
    {
      "epoch": 0.473015873015873,
      "grad_norm": 4.28125,
      "learning_rate": 0.00019395970741058202,
      "loss": 1.316,
      "step": 149
    },
    {
      "epoch": 0.47619047619047616,
      "grad_norm": 4.5,
      "learning_rate": 0.00019387338576538744,
      "loss": 0.8492,
      "step": 150
    },
    {
      "epoch": 0.4793650793650794,
      "grad_norm": 2.875,
      "learning_rate": 0.0001937864711648689,
      "loss": 0.906,
      "step": 151
    },
    {
      "epoch": 0.48253968253968255,
      "grad_norm": 4.59375,
      "learning_rate": 0.0001936989641580263,
      "loss": 1.3716,
      "step": 152
    },
    {
      "epoch": 0.4857142857142857,
      "grad_norm": 4.53125,
      "learning_rate": 0.0001936108652976015,
      "loss": 1.2317,
      "step": 153
    },
    {
      "epoch": 0.4888888888888889,
      "grad_norm": 5.53125,
      "learning_rate": 0.0001935221751400747,
      "loss": 1.3703,
      "step": 154
    },
    {
      "epoch": 0.49206349206349204,
      "grad_norm": 5.34375,
      "learning_rate": 0.00019343289424566122,
      "loss": 1.1271,
      "step": 155
    },
    {
      "epoch": 0.49523809523809526,
      "grad_norm": 3.875,
      "learning_rate": 0.00019334302317830764,
      "loss": 1.1003,
      "step": 156
    },
    {
      "epoch": 0.4984126984126984,
      "grad_norm": 4.46875,
      "learning_rate": 0.0001932525625056885,
      "loss": 1.4605,
      "step": 157
    },
    {
      "epoch": 0.5015873015873016,
      "grad_norm": 5.0,
      "learning_rate": 0.0001931615127992026,
      "loss": 1.4922,
      "step": 158
    },
    {
      "epoch": 0.5047619047619047,
      "grad_norm": 3.09375,
      "learning_rate": 0.00019306987463396934,
      "loss": 1.1037,
      "step": 159
    },
    {
      "epoch": 0.5079365079365079,
      "grad_norm": 3.546875,
      "learning_rate": 0.00019297764858882514,
      "loss": 1.1211,
      "step": 160
    },
    {
      "epoch": 0.5111111111111111,
      "grad_norm": 5.125,
      "learning_rate": 0.0001928848352463199,
      "loss": 1.2307,
      "step": 161
    },
    {
      "epoch": 0.5142857142857142,
      "grad_norm": 3.6875,
      "learning_rate": 0.00019279143519271307,
      "loss": 1.0421,
      "step": 162
    },
    {
      "epoch": 0.5174603174603175,
      "grad_norm": 3.25,
      "learning_rate": 0.0001926974490179702,
      "loss": 1.303,
      "step": 163
    },
    {
      "epoch": 0.5206349206349207,
      "grad_norm": 3.203125,
      "learning_rate": 0.00019260287731575902,
      "loss": 1.1132,
      "step": 164
    },
    {
      "epoch": 0.5238095238095238,
      "grad_norm": 3.578125,
      "learning_rate": 0.0001925077206834458,
      "loss": 1.144,
      "step": 165
    },
    {
      "epoch": 0.526984126984127,
      "grad_norm": 5.15625,
      "learning_rate": 0.00019241197972209157,
      "loss": 1.1203,
      "step": 166
    },
    {
      "epoch": 0.5301587301587302,
      "grad_norm": 4.3125,
      "learning_rate": 0.00019231565503644826,
      "loss": 1.2756,
      "step": 167
    },
    {
      "epoch": 0.5333333333333333,
      "grad_norm": 4.46875,
      "learning_rate": 0.00019221874723495495,
      "loss": 1.2898,
      "step": 168
    },
    {
      "epoch": 0.5365079365079365,
      "grad_norm": 4.09375,
      "learning_rate": 0.00019212125692973396,
      "loss": 1.3759,
      "step": 169
    },
    {
      "epoch": 0.5396825396825397,
      "grad_norm": 3.34375,
      "learning_rate": 0.00019202318473658705,
      "loss": 1.113,
      "step": 170
    },
    {
      "epoch": 0.5428571428571428,
      "grad_norm": 3.09375,
      "learning_rate": 0.0001919245312749915,
      "loss": 0.9661,
      "step": 171
    },
    {
      "epoch": 0.546031746031746,
      "grad_norm": 2.921875,
      "learning_rate": 0.0001918252971680962,
      "loss": 1.1019,
      "step": 172
    },
    {
      "epoch": 0.5492063492063493,
      "grad_norm": 2.265625,
      "learning_rate": 0.00019172548304271768,
      "loss": 0.773,
      "step": 173
    },
    {
      "epoch": 0.5523809523809524,
      "grad_norm": 3.359375,
      "learning_rate": 0.0001916250895293362,
      "loss": 1.2015,
      "step": 174
    },
    {
      "epoch": 0.5555555555555556,
      "grad_norm": 4.40625,
      "learning_rate": 0.00019152411726209176,
      "loss": 1.3768,
      "step": 175
    },
    {
      "epoch": 0.5587301587301587,
      "grad_norm": 3.484375,
      "learning_rate": 0.0001914225668787801,
      "loss": 0.9422,
      "step": 176
    },
    {
      "epoch": 0.5619047619047619,
      "grad_norm": 5.78125,
      "learning_rate": 0.00019132043902084865,
      "loss": 1.4228,
      "step": 177
    },
    {
      "epoch": 0.5650793650793651,
      "grad_norm": 3.703125,
      "learning_rate": 0.0001912177343333924,
      "loss": 1.2504,
      "step": 178
    },
    {
      "epoch": 0.5682539682539682,
      "grad_norm": 4.09375,
      "learning_rate": 0.00019111445346515002,
      "loss": 1.2305,
      "step": 179
    },
    {
      "epoch": 0.5714285714285714,
      "grad_norm": 3.234375,
      "learning_rate": 0.00019101059706849957,
      "loss": 1.1119,
      "step": 180
    },
    {
      "epoch": 0.5746031746031746,
      "grad_norm": 3.0625,
      "learning_rate": 0.00019090616579945456,
      "loss": 1.0028,
      "step": 181
    },
    {
      "epoch": 0.5777777777777777,
      "grad_norm": 3.890625,
      "learning_rate": 0.00019080116031765958,
      "loss": 1.1326,
      "step": 182
    },
    {
      "epoch": 0.580952380952381,
      "grad_norm": 6.25,
      "learning_rate": 0.00019069558128638635,
      "loss": 1.582,
      "step": 183
    },
    {
      "epoch": 0.5841269841269842,
      "grad_norm": 5.59375,
      "learning_rate": 0.00019058942937252943,
      "loss": 1.4948,
      "step": 184
    },
    {
      "epoch": 0.5873015873015873,
      "grad_norm": 3.109375,
      "learning_rate": 0.00019048270524660196,
      "loss": 0.9625,
      "step": 185
    },
    {
      "epoch": 0.5904761904761905,
      "grad_norm": 3.75,
      "learning_rate": 0.00019037540958273156,
      "loss": 1.4566,
      "step": 186
    },
    {
      "epoch": 0.5936507936507937,
      "grad_norm": 4.28125,
      "learning_rate": 0.00019026754305865592,
      "loss": 1.1914,
      "step": 187
    },
    {
      "epoch": 0.5968253968253968,
      "grad_norm": 4.15625,
      "learning_rate": 0.00019015910635571869,
      "loss": 1.3762,
      "step": 188
    },
    {
      "epoch": 0.6,
      "grad_norm": 3.875,
      "learning_rate": 0.00019005010015886496,
      "loss": 1.3227,
      "step": 189
    },
    {
      "epoch": 0.6031746031746031,
      "grad_norm": 2.984375,
      "learning_rate": 0.0001899405251566371,
      "loss": 1.0795,
      "step": 190
    },
    {
      "epoch": 0.6063492063492063,
      "grad_norm": 6.09375,
      "learning_rate": 0.00018983038204117044,
      "loss": 1.5507,
      "step": 191
    },
    {
      "epoch": 0.6095238095238096,
      "grad_norm": 4.3125,
      "learning_rate": 0.00018971967150818877,
      "loss": 1.2823,
      "step": 192
    },
    {
      "epoch": 0.6126984126984127,
      "grad_norm": 5.34375,
      "learning_rate": 0.0001896083942569999,
      "loss": 1.5036,
      "step": 193
    },
    {
      "epoch": 0.6158730158730159,
      "grad_norm": 3.484375,
      "learning_rate": 0.00018949655099049148,
      "loss": 1.08,
      "step": 194
    },
    {
      "epoch": 0.6190476190476191,
      "grad_norm": 3.34375,
      "learning_rate": 0.0001893841424151264,
      "loss": 1.2002,
      "step": 195
    },
    {
      "epoch": 0.6222222222222222,
      "grad_norm": 2.9375,
      "learning_rate": 0.00018927116924093824,
      "loss": 1.1845,
      "step": 196
    },
    {
      "epoch": 0.6253968253968254,
      "grad_norm": 2.65625,
      "learning_rate": 0.00018915763218152704,
      "loss": 0.9349,
      "step": 197
    },
    {
      "epoch": 0.6285714285714286,
      "grad_norm": 4.0625,
      "learning_rate": 0.0001890435319540545,
      "loss": 1.4206,
      "step": 198
    },
    {
      "epoch": 0.6317460317460317,
      "grad_norm": 2.25,
      "learning_rate": 0.00018892886927923973,
      "loss": 1.016,
      "step": 199
    },
    {
      "epoch": 0.6349206349206349,
      "grad_norm": 4.90625,
      "learning_rate": 0.00018881364488135448,
      "loss": 1.3077,
      "step": 200
    },
    {
      "epoch": 0.638095238095238,
      "grad_norm": 3.28125,
      "learning_rate": 0.00018869785948821865,
      "loss": 1.3698,
      "step": 201
    },
    {
      "epoch": 0.6412698412698413,
      "grad_norm": 5.5625,
      "learning_rate": 0.00018858151383119575,
      "loss": 1.5526,
      "step": 202
    },
    {
      "epoch": 0.6444444444444445,
      "grad_norm": 3.515625,
      "learning_rate": 0.00018846460864518818,
      "loss": 1.2174,
      "step": 203
    },
    {
      "epoch": 0.6476190476190476,
      "grad_norm": 3.234375,
      "learning_rate": 0.0001883471446686326,
      "loss": 1.3522,
      "step": 204
    },
    {
      "epoch": 0.6507936507936508,
      "grad_norm": 4.09375,
      "learning_rate": 0.00018822912264349534,
      "loss": 1.4896,
      "step": 205
    },
    {
      "epoch": 0.653968253968254,
      "grad_norm": 2.40625,
      "learning_rate": 0.00018811054331526768,
      "loss": 1.0023,
      "step": 206
    },
    {
      "epoch": 0.6571428571428571,
      "grad_norm": 8.375,
      "learning_rate": 0.00018799140743296105,
      "loss": 1.495,
      "step": 207
    },
    {
      "epoch": 0.6603174603174603,
      "grad_norm": 4.375,
      "learning_rate": 0.00018787171574910247,
      "loss": 1.1232,
      "step": 208
    },
    {
      "epoch": 0.6634920634920635,
      "grad_norm": 4.09375,
      "learning_rate": 0.00018775146901972968,
      "loss": 1.2766,
      "step": 209
    },
    {
      "epoch": 0.6666666666666666,
      "grad_norm": 2.5,
      "learning_rate": 0.00018763066800438636,
      "loss": 1.2216,
      "step": 210
    },
    {
      "epoch": 0.6698412698412698,
      "grad_norm": 3.96875,
      "learning_rate": 0.00018750931346611739,
      "loss": 1.2713,
      "step": 211
    },
    {
      "epoch": 0.6730158730158731,
      "grad_norm": 2.953125,
      "learning_rate": 0.00018738740617146396,
      "loss": 1.1207,
      "step": 212
    },
    {
      "epoch": 0.6761904761904762,
      "grad_norm": 4.34375,
      "learning_rate": 0.00018726494689045876,
      "loss": 1.609,
      "step": 213
    },
    {
      "epoch": 0.6793650793650794,
      "grad_norm": 2.53125,
      "learning_rate": 0.00018714193639662128,
      "loss": 0.8925,
      "step": 214
    },
    {
      "epoch": 0.6825396825396826,
      "grad_norm": 2.984375,
      "learning_rate": 0.0001870183754669526,
      "loss": 1.1183,
      "step": 215
    },
    {
      "epoch": 0.6857142857142857,
      "grad_norm": 4.46875,
      "learning_rate": 0.00018689426488193066,
      "loss": 1.3495,
      "step": 216
    },
    {
      "epoch": 0.6888888888888889,
      "grad_norm": 3.421875,
      "learning_rate": 0.0001867696054255054,
      "loss": 1.0495,
      "step": 217
    },
    {
      "epoch": 0.692063492063492,
      "grad_norm": 7.09375,
      "learning_rate": 0.0001866443978850937,
      "loss": 1.5438,
      "step": 218
    },
    {
      "epoch": 0.6952380952380952,
      "grad_norm": 4.3125,
      "learning_rate": 0.0001865186430515745,
      "loss": 1.3319,
      "step": 219
    },
    {
      "epoch": 0.6984126984126984,
      "grad_norm": 3.796875,
      "learning_rate": 0.00018639234171928353,
      "loss": 1.1643,
      "step": 220
    },
    {
      "epoch": 0.7015873015873015,
      "grad_norm": 2.828125,
      "learning_rate": 0.00018626549468600878,
      "loss": 0.9681,
      "step": 221
    },
    {
      "epoch": 0.7047619047619048,
      "grad_norm": 3.84375,
      "learning_rate": 0.000186138102752985,
      "loss": 1.1597,
      "step": 222
    },
    {
      "epoch": 0.707936507936508,
      "grad_norm": 3.234375,
      "learning_rate": 0.00018601016672488888,
      "loss": 1.1647,
      "step": 223
    },
    {
      "epoch": 0.7111111111111111,
      "grad_norm": 4.25,
      "learning_rate": 0.00018588168740983388,
      "loss": 1.15,
      "step": 224
    },
    {
      "epoch": 0.7142857142857143,
      "grad_norm": 4.5,
      "learning_rate": 0.00018575266561936523,
      "loss": 1.2461,
      "step": 225
    },
    {
      "epoch": 0.7174603174603175,
      "grad_norm": 3.59375,
      "learning_rate": 0.00018562310216845465,
      "loss": 1.108,
      "step": 226
    },
    {
      "epoch": 0.7206349206349206,
      "grad_norm": 4.40625,
      "learning_rate": 0.00018549299787549533,
      "loss": 1.2701,
      "step": 227
    },
    {
      "epoch": 0.7238095238095238,
      "grad_norm": 3.453125,
      "learning_rate": 0.0001853623535622967,
      "loss": 1.2034,
      "step": 228
    },
    {
      "epoch": 0.726984126984127,
      "grad_norm": 4.0625,
      "learning_rate": 0.0001852311700540792,
      "loss": 1.1526,
      "step": 229
    },
    {
      "epoch": 0.7301587301587301,
      "grad_norm": 3.296875,
      "learning_rate": 0.00018509944817946922,
      "loss": 1.3439,
      "step": 230
    },
    {
      "epoch": 0.7333333333333333,
      "grad_norm": 3.734375,
      "learning_rate": 0.00018496718877049367,
      "loss": 1.3328,
      "step": 231
    },
    {
      "epoch": 0.7365079365079366,
      "grad_norm": 3.515625,
      "learning_rate": 0.00018483439266257486,
      "loss": 1.2361,
      "step": 232
    },
    {
      "epoch": 0.7396825396825397,
      "grad_norm": 2.875,
      "learning_rate": 0.0001847010606945252,
      "loss": 0.9363,
      "step": 233
    },
    {
      "epoch": 0.7428571428571429,
      "grad_norm": 5.46875,
      "learning_rate": 0.0001845671937085419,
      "loss": 1.2527,
      "step": 234
    },
    {
      "epoch": 0.746031746031746,
      "grad_norm": 2.90625,
      "learning_rate": 0.00018443279255020152,
      "loss": 1.2294,
      "step": 235
    },
    {
      "epoch": 0.7492063492063492,
      "grad_norm": 2.828125,
      "learning_rate": 0.00018429785806845487,
      "loss": 1.0708,
      "step": 236
    },
    {
      "epoch": 0.7523809523809524,
      "grad_norm": 3.046875,
      "learning_rate": 0.00018416239111562147,
      "loss": 1.1407,
      "step": 237
    },
    {
      "epoch": 0.7555555555555555,
      "grad_norm": 2.609375,
      "learning_rate": 0.00018402639254738422,
      "loss": 0.7489,
      "step": 238
    },
    {
      "epoch": 0.7587301587301587,
      "grad_norm": 5.34375,
      "learning_rate": 0.00018388986322278398,
      "loss": 1.1833,
      "step": 239
    },
    {
      "epoch": 0.7619047619047619,
      "grad_norm": 3.875,
      "learning_rate": 0.0001837528040042142,
      "loss": 1.3504,
      "step": 240
    },
    {
      "epoch": 0.765079365079365,
      "grad_norm": 3.21875,
      "learning_rate": 0.0001836152157574153,
      "loss": 1.5183,
      "step": 241
    },
    {
      "epoch": 0.7682539682539683,
      "grad_norm": 2.9375,
      "learning_rate": 0.00018347709935146958,
      "loss": 1.0679,
      "step": 242
    },
    {
      "epoch": 0.7714285714285715,
      "grad_norm": 3.421875,
      "learning_rate": 0.00018333845565879516,
      "loss": 1.2424,
      "step": 243
    },
    {
      "epoch": 0.7746031746031746,
      "grad_norm": 5.875,
      "learning_rate": 0.00018319928555514108,
      "loss": 1.3007,
      "step": 244
    },
    {
      "epoch": 0.7777777777777778,
      "grad_norm": 2.6875,
      "learning_rate": 0.00018305958991958127,
      "loss": 1.0213,
      "step": 245
    },
    {
      "epoch": 0.780952380952381,
      "grad_norm": 3.375,
      "learning_rate": 0.00018291936963450934,
      "loss": 1.3583,
      "step": 246
    },
    {
      "epoch": 0.7841269841269841,
      "grad_norm": 3.59375,
      "learning_rate": 0.00018277862558563278,
      "loss": 1.1568,
      "step": 247
    },
    {
      "epoch": 0.7873015873015873,
      "grad_norm": 6.53125,
      "learning_rate": 0.00018263735866196756,
      "loss": 1.3523,
      "step": 248
    },
    {
      "epoch": 0.7904761904761904,
      "grad_norm": 3.21875,
      "learning_rate": 0.0001824955697558323,
      "loss": 1.1265,
      "step": 249
    },
    {
      "epoch": 0.7936507936507936,
      "grad_norm": 4.59375,
      "learning_rate": 0.00018235325976284275,
      "loss": 1.2869,
      "step": 250
    },
    {
      "epoch": 0.7968253968253968,
      "grad_norm": 3.0,
      "learning_rate": 0.00018221042958190627,
      "loss": 1.1097,
      "step": 251
    },
    {
      "epoch": 0.8,
      "grad_norm": 2.765625,
      "learning_rate": 0.00018206708011521582,
      "loss": 1.3495,
      "step": 252
    },
    {
      "epoch": 0.8031746031746032,
      "grad_norm": 2.8125,
      "learning_rate": 0.00018192321226824455,
      "loss": 1.0061,
      "step": 253
    },
    {
      "epoch": 0.8063492063492064,
      "grad_norm": 3.328125,
      "learning_rate": 0.00018177882694974006,
      "loss": 1.0327,
      "step": 254
    },
    {
      "epoch": 0.8095238095238095,
      "grad_norm": 3.015625,
      "learning_rate": 0.00018163392507171842,
      "loss": 0.9958,
      "step": 255
    },
    {
      "epoch": 0.8126984126984127,
      "grad_norm": 2.28125,
      "learning_rate": 0.00018148850754945862,
      "loss": 1.2192,
      "step": 256
    },
    {
      "epoch": 0.8158730158730159,
      "grad_norm": 4.90625,
      "learning_rate": 0.00018134257530149684,
      "loss": 1.1918,
      "step": 257
    },
    {
      "epoch": 0.819047619047619,
      "grad_norm": 2.78125,
      "learning_rate": 0.00018119612924962045,
      "loss": 1.0672,
      "step": 258
    },
    {
      "epoch": 0.8222222222222222,
      "grad_norm": 4.40625,
      "learning_rate": 0.00018104917031886222,
      "loss": 1.318,
      "step": 259
    },
    {
      "epoch": 0.8253968253968254,
      "grad_norm": 3.890625,
      "learning_rate": 0.00018090169943749476,
      "loss": 1.2472,
      "step": 260
    },
    {
      "epoch": 0.8285714285714286,
      "grad_norm": 2.71875,
      "learning_rate": 0.0001807537175370242,
      "loss": 0.7784,
      "step": 261
    },
    {
      "epoch": 0.8317460317460318,
      "grad_norm": 2.765625,
      "learning_rate": 0.0001806052255521847,
      "loss": 0.9956,
      "step": 262
    },
    {
      "epoch": 0.834920634920635,
      "grad_norm": 3.203125,
      "learning_rate": 0.00018045622442093237,
      "loss": 1.0368,
      "step": 263
    },
    {
      "epoch": 0.8380952380952381,
      "grad_norm": 3.921875,
      "learning_rate": 0.00018030671508443929,
      "loss": 1.4863,
      "step": 264
    },
    {
      "epoch": 0.8412698412698413,
      "grad_norm": 4.03125,
      "learning_rate": 0.00018015669848708767,
      "loss": 1.3369,
      "step": 265
    },
    {
      "epoch": 0.8444444444444444,
      "grad_norm": 2.328125,
      "learning_rate": 0.0001800061755764639,
      "loss": 1.0004,
      "step": 266
    },
    {
      "epoch": 0.8476190476190476,
      "grad_norm": 4.0625,
      "learning_rate": 0.00017985514730335252,
      "loss": 1.3371,
      "step": 267
    },
    {
      "epoch": 0.8507936507936508,
      "grad_norm": 2.84375,
      "learning_rate": 0.0001797036146217301,
      "loss": 1.1897,
      "step": 268
    },
    {
      "epoch": 0.8539682539682539,
      "grad_norm": 1.765625,
      "learning_rate": 0.0001795515784887595,
      "loss": 0.7096,
      "step": 269
    },
    {
      "epoch": 0.8571428571428571,
      "grad_norm": 3.34375,
      "learning_rate": 0.00017939903986478355,
      "loss": 1.0215,
      "step": 270
    },
    {
      "epoch": 0.8603174603174604,
      "grad_norm": 4.0625,
      "learning_rate": 0.00017924599971331907,
      "loss": 1.0234,
      "step": 271
    },
    {
      "epoch": 0.8634920634920635,
      "grad_norm": 2.765625,
      "learning_rate": 0.00017909245900105084,
      "loss": 1.1715,
      "step": 272
    },
    {
      "epoch": 0.8666666666666667,
      "grad_norm": 2.765625,
      "learning_rate": 0.00017893841869782547,
      "loss": 1.2362,
      "step": 273
    },
    {
      "epoch": 0.8698412698412699,
      "grad_norm": 2.546875,
      "learning_rate": 0.0001787838797766452,
      "loss": 1.0232,
      "step": 274
    },
    {
      "epoch": 0.873015873015873,
      "grad_norm": 3.40625,
      "learning_rate": 0.00017862884321366188,
      "loss": 1.2369,
      "step": 275
    },
    {
      "epoch": 0.8761904761904762,
      "grad_norm": 2.65625,
      "learning_rate": 0.00017847330998817072,
      "loss": 1.1853,
      "step": 276
    },
    {
      "epoch": 0.8793650793650793,
      "grad_norm": 4.25,
      "learning_rate": 0.00017831728108260407,
      "loss": 1.0452,
      "step": 277
    },
    {
      "epoch": 0.8825396825396825,
      "grad_norm": 2.40625,
      "learning_rate": 0.00017816075748252526,
      "loss": 0.9878,
      "step": 278
    },
    {
      "epoch": 0.8857142857142857,
      "grad_norm": 3.96875,
      "learning_rate": 0.0001780037401766225,
      "loss": 1.4861,
      "step": 279
    },
    {
      "epoch": 0.8888888888888888,
      "grad_norm": 4.28125,
      "learning_rate": 0.00017784623015670238,
      "loss": 1.4139,
      "step": 280
    },
    {
      "epoch": 0.8920634920634921,
      "grad_norm": 2.296875,
      "learning_rate": 0.00017768822841768379,
      "loss": 1.0084,
      "step": 281
    },
    {
      "epoch": 0.8952380952380953,
      "grad_norm": 3.203125,
      "learning_rate": 0.00017752973595759158,
      "loss": 1.2464,
      "step": 282
    },
    {
      "epoch": 0.8984126984126984,
      "grad_norm": 7.25,
      "learning_rate": 0.00017737075377755032,
      "loss": 1.4547,
      "step": 283
    },
    {
      "epoch": 0.9015873015873016,
      "grad_norm": 3.46875,
      "learning_rate": 0.00017721128288177782,
      "loss": 1.3467,
      "step": 284
    },
    {
      "epoch": 0.9047619047619048,
      "grad_norm": 2.375,
      "learning_rate": 0.00017705132427757895,
      "loss": 1.0596,
      "step": 285
    },
    {
      "epoch": 0.9079365079365079,
      "grad_norm": 3.140625,
      "learning_rate": 0.00017689087897533915,
      "loss": 1.3504,
      "step": 286
    },
    {
      "epoch": 0.9111111111111111,
      "grad_norm": 2.640625,
      "learning_rate": 0.0001767299479885182,
      "loss": 1.206,
      "step": 287
    },
    {
      "epoch": 0.9142857142857143,
      "grad_norm": 3.5625,
      "learning_rate": 0.00017656853233364369,
      "loss": 1.0524,
      "step": 288
    },
    {
      "epoch": 0.9174603174603174,
      "grad_norm": 3.75,
      "learning_rate": 0.00017640663303030452,
      "loss": 1.1057,
      "step": 289
    },
    {
      "epoch": 0.9206349206349206,
      "grad_norm": 4.96875,
      "learning_rate": 0.0001762442511011448,
      "loss": 1.2462,
      "step": 290
    },
    {
      "epoch": 0.9238095238095239,
      "grad_norm": 2.515625,
      "learning_rate": 0.00017608138757185698,
      "loss": 0.9525,
      "step": 291
    },
    {
      "epoch": 0.926984126984127,
      "grad_norm": 3.203125,
      "learning_rate": 0.00017591804347117567,
      "loss": 0.9553,
      "step": 292
    },
    {
      "epoch": 0.9301587301587302,
      "grad_norm": 4.1875,
      "learning_rate": 0.00017575421983087095,
      "loss": 1.2396,
      "step": 293
    },
    {
      "epoch": 0.9333333333333333,
      "grad_norm": 4.5625,
      "learning_rate": 0.000175589917685742,
      "loss": 1.0318,
      "step": 294
    },
    {
      "epoch": 0.9365079365079365,
      "grad_norm": 2.65625,
      "learning_rate": 0.00017542513807361037,
      "loss": 1.0792,
      "step": 295
    },
    {
      "epoch": 0.9396825396825397,
      "grad_norm": 1.5625,
      "learning_rate": 0.0001752598820353138,
      "loss": 0.6749,
      "step": 296
    },
    {
      "epoch": 0.9428571428571428,
      "grad_norm": 3.46875,
      "learning_rate": 0.00017509415061469917,
      "loss": 1.5,
      "step": 297
    },
    {
      "epoch": 0.946031746031746,
      "grad_norm": 2.46875,
      "learning_rate": 0.00017492794485861617,
      "loss": 1.0022,
      "step": 298
    },
    {
      "epoch": 0.9492063492063492,
      "grad_norm": 2.90625,
      "learning_rate": 0.0001747612658169107,
      "loss": 0.9312,
      "step": 299
    },
    {
      "epoch": 0.9523809523809523,
      "grad_norm": 4.84375,
      "learning_rate": 0.00017459411454241822,
      "loss": 1.1697,
      "step": 300
    },
    {
      "epoch": 0.9555555555555556,
      "grad_norm": 3.390625,
      "learning_rate": 0.000174426492090957,
      "loss": 1.1664,
      "step": 301
    },
    {
      "epoch": 0.9587301587301588,
      "grad_norm": 2.78125,
      "learning_rate": 0.00017425839952132157,
      "loss": 1.2322,
      "step": 302
    },
    {
      "epoch": 0.9619047619047619,
      "grad_norm": 2.6875,
      "learning_rate": 0.0001740898378952759,
      "loss": 1.1428,
      "step": 303
    },
    {
      "epoch": 0.9650793650793651,
      "grad_norm": 3.609375,
      "learning_rate": 0.00017392080827754688,
      "loss": 1.2497,
      "step": 304
    },
    {
      "epoch": 0.9682539682539683,
      "grad_norm": 2.390625,
      "learning_rate": 0.0001737513117358174,
      "loss": 0.9671,
      "step": 305
    },
    {
      "epoch": 0.9714285714285714,
      "grad_norm": 4.53125,
      "learning_rate": 0.00017358134934071978,
      "loss": 1.1203,
      "step": 306
    },
    {
      "epoch": 0.9746031746031746,
      "grad_norm": 2.53125,
      "learning_rate": 0.00017341092216582887,
      "loss": 1.0647,
      "step": 307
    },
    {
      "epoch": 0.9777777777777777,
      "grad_norm": 2.65625,
      "learning_rate": 0.00017324003128765534,
      "loss": 1.1387,
      "step": 308
    },
    {
      "epoch": 0.9809523809523809,
      "grad_norm": 2.640625,
      "learning_rate": 0.0001730686777856388,
      "loss": 1.1033,
      "step": 309
    },
    {
      "epoch": 0.9841269841269841,
      "grad_norm": 4.0625,
      "learning_rate": 0.00017289686274214118,
      "loss": 1.2105,
      "step": 310
    },
    {
      "epoch": 0.9873015873015873,
      "grad_norm": 3.015625,
      "learning_rate": 0.0001727245872424396,
      "loss": 0.9702,
      "step": 311
    },
    {
      "epoch": 0.9904761904761905,
      "grad_norm": 2.59375,
      "learning_rate": 0.00017255185237471978,
      "loss": 0.8773,
      "step": 312
    },
    {
      "epoch": 0.9936507936507937,
      "grad_norm": 2.90625,
      "learning_rate": 0.00017237865923006905,
      "loss": 0.954,
      "step": 313
    },
    {
      "epoch": 0.9968253968253968,
      "grad_norm": 3.375,
      "learning_rate": 0.00017220500890246943,
      "loss": 1.3194,
      "step": 314
    },
    {
      "epoch": 1.0,
      "grad_norm": 3.28125,
      "learning_rate": 0.0001720309024887907,
      "loss": 1.4559,
      "step": 315
    }
  ],
  "logging_steps": 1,
  "max_steps": 1260,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 4,
  "save_steps": 315,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 1.0192095972478157e+17,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}