{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.9994397759103641,
  "eval_steps": 500,
  "global_step": 446,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.002240896358543417,
      "grad_norm": 0.22982779145240784,
      "learning_rate": 1.1235955056179775e-06,
      "loss": 1.1973,
      "step": 1
    },
    {
      "epoch": 0.004481792717086834,
      "grad_norm": 0.2098255604505539,
      "learning_rate": 2.247191011235955e-06,
      "loss": 1.2685,
      "step": 2
    },
    {
      "epoch": 0.0067226890756302525,
      "grad_norm": 0.2404344230890274,
      "learning_rate": 3.3707865168539327e-06,
      "loss": 1.2292,
      "step": 3
    },
    {
      "epoch": 0.008963585434173669,
      "grad_norm": 0.23824891448020935,
      "learning_rate": 4.49438202247191e-06,
      "loss": 1.1901,
      "step": 4
    },
    {
      "epoch": 0.011204481792717087,
      "grad_norm": 0.22885526716709137,
      "learning_rate": 5.617977528089888e-06,
      "loss": 1.2695,
      "step": 5
    },
    {
      "epoch": 0.013445378151260505,
      "grad_norm": 0.2576353847980499,
      "learning_rate": 6.741573033707865e-06,
      "loss": 1.2872,
      "step": 6
    },
    {
      "epoch": 0.01568627450980392,
      "grad_norm": 0.2190636247396469,
      "learning_rate": 7.865168539325843e-06,
      "loss": 1.1952,
      "step": 7
    },
    {
      "epoch": 0.017927170868347338,
      "grad_norm": 0.21357473731040955,
      "learning_rate": 8.98876404494382e-06,
      "loss": 1.2597,
      "step": 8
    },
    {
      "epoch": 0.020168067226890758,
      "grad_norm": 0.24502670764923096,
      "learning_rate": 1.0112359550561798e-05,
      "loss": 1.279,
      "step": 9
    },
    {
      "epoch": 0.022408963585434174,
      "grad_norm": 0.25532686710357666,
      "learning_rate": 1.1235955056179776e-05,
      "loss": 1.2163,
      "step": 10
    },
    {
      "epoch": 0.02464985994397759,
      "grad_norm": 0.250683456659317,
      "learning_rate": 1.2359550561797752e-05,
      "loss": 1.2735,
      "step": 11
    },
    {
      "epoch": 0.02689075630252101,
      "grad_norm": 0.2523595988750458,
      "learning_rate": 1.348314606741573e-05,
      "loss": 1.3471,
      "step": 12
    },
    {
      "epoch": 0.029131652661064426,
      "grad_norm": 0.23875640332698822,
      "learning_rate": 1.4606741573033709e-05,
      "loss": 1.2595,
      "step": 13
    },
    {
      "epoch": 0.03137254901960784,
      "grad_norm": 0.24998927116394043,
      "learning_rate": 1.5730337078651687e-05,
      "loss": 1.2142,
      "step": 14
    },
    {
      "epoch": 0.03361344537815126,
      "grad_norm": 0.2783028483390808,
      "learning_rate": 1.6853932584269665e-05,
      "loss": 1.185,
      "step": 15
    },
    {
      "epoch": 0.035854341736694675,
      "grad_norm": 0.2796604633331299,
      "learning_rate": 1.797752808988764e-05,
      "loss": 1.226,
      "step": 16
    },
    {
      "epoch": 0.0380952380952381,
      "grad_norm": 0.2899184823036194,
      "learning_rate": 1.9101123595505618e-05,
      "loss": 1.1672,
      "step": 17
    },
    {
      "epoch": 0.040336134453781515,
      "grad_norm": 0.2601150572299957,
      "learning_rate": 2.0224719101123596e-05,
      "loss": 1.1127,
      "step": 18
    },
    {
      "epoch": 0.04257703081232493,
      "grad_norm": 0.3052348792552948,
      "learning_rate": 2.1348314606741574e-05,
      "loss": 1.2865,
      "step": 19
    },
    {
      "epoch": 0.04481792717086835,
      "grad_norm": 0.24783451855182648,
      "learning_rate": 2.2471910112359552e-05,
      "loss": 1.0888,
      "step": 20
    },
    {
      "epoch": 0.047058823529411764,
      "grad_norm": 0.24703693389892578,
      "learning_rate": 2.359550561797753e-05,
      "loss": 1.059,
      "step": 21
    },
    {
      "epoch": 0.04929971988795518,
      "grad_norm": 0.2503679096698761,
      "learning_rate": 2.4719101123595505e-05,
      "loss": 1.1602,
      "step": 22
    },
    {
      "epoch": 0.0515406162464986,
      "grad_norm": 0.2639842927455902,
      "learning_rate": 2.5842696629213486e-05,
      "loss": 1.0911,
      "step": 23
    },
    {
      "epoch": 0.05378151260504202,
      "grad_norm": 0.2942507266998291,
      "learning_rate": 2.696629213483146e-05,
      "loss": 1.0777,
      "step": 24
    },
    {
      "epoch": 0.056022408963585436,
      "grad_norm": 0.28088828921318054,
      "learning_rate": 2.8089887640449443e-05,
      "loss": 1.1111,
      "step": 25
    },
    {
      "epoch": 0.05826330532212885,
      "grad_norm": 0.26791295409202576,
      "learning_rate": 2.9213483146067417e-05,
      "loss": 1.0016,
      "step": 26
    },
    {
      "epoch": 0.06050420168067227,
      "grad_norm": 0.2685791850090027,
      "learning_rate": 3.0337078651685396e-05,
      "loss": 1.1085,
      "step": 27
    },
    {
      "epoch": 0.06274509803921569,
      "grad_norm": 0.2627420127391815,
      "learning_rate": 3.1460674157303374e-05,
      "loss": 1.0704,
      "step": 28
    },
    {
      "epoch": 0.06498599439775911,
      "grad_norm": 0.3000424802303314,
      "learning_rate": 3.258426966292135e-05,
      "loss": 1.0786,
      "step": 29
    },
    {
      "epoch": 0.06722689075630252,
      "grad_norm": 0.3018706738948822,
      "learning_rate": 3.370786516853933e-05,
      "loss": 1.0423,
      "step": 30
    },
    {
      "epoch": 0.06946778711484594,
      "grad_norm": 0.27565667033195496,
      "learning_rate": 3.483146067415731e-05,
      "loss": 0.9834,
      "step": 31
    },
    {
      "epoch": 0.07170868347338935,
      "grad_norm": 0.30244842171669006,
      "learning_rate": 3.595505617977528e-05,
      "loss": 1.0927,
      "step": 32
    },
    {
      "epoch": 0.07394957983193277,
      "grad_norm": 0.3654678165912628,
      "learning_rate": 3.7078651685393264e-05,
      "loss": 0.9812,
      "step": 33
    },
    {
      "epoch": 0.0761904761904762,
      "grad_norm": 0.36483272910118103,
      "learning_rate": 3.8202247191011236e-05,
      "loss": 0.9693,
      "step": 34
    },
    {
      "epoch": 0.0784313725490196,
      "grad_norm": 0.2949022054672241,
      "learning_rate": 3.9325842696629214e-05,
      "loss": 0.9647,
      "step": 35
    },
    {
      "epoch": 0.08067226890756303,
      "grad_norm": 0.36239683628082275,
      "learning_rate": 4.044943820224719e-05,
      "loss": 0.9725,
      "step": 36
    },
    {
      "epoch": 0.08291316526610644,
      "grad_norm": 0.32511067390441895,
      "learning_rate": 4.157303370786517e-05,
      "loss": 1.0136,
      "step": 37
    },
    {
      "epoch": 0.08515406162464986,
      "grad_norm": 0.32111090421676636,
      "learning_rate": 4.269662921348315e-05,
      "loss": 0.9207,
      "step": 38
    },
    {
      "epoch": 0.08739495798319327,
      "grad_norm": 0.3080519735813141,
      "learning_rate": 4.3820224719101126e-05,
      "loss": 0.9729,
      "step": 39
    },
    {
      "epoch": 0.0896358543417367,
      "grad_norm": 0.2933235764503479,
      "learning_rate": 4.4943820224719104e-05,
      "loss": 0.9403,
      "step": 40
    },
    {
      "epoch": 0.09187675070028012,
      "grad_norm": 0.3132348358631134,
      "learning_rate": 4.606741573033708e-05,
      "loss": 0.9587,
      "step": 41
    },
    {
      "epoch": 0.09411764705882353,
      "grad_norm": 0.3013119101524353,
      "learning_rate": 4.719101123595506e-05,
      "loss": 0.9162,
      "step": 42
    },
    {
      "epoch": 0.09635854341736695,
      "grad_norm": 0.300485223531723,
      "learning_rate": 4.831460674157304e-05,
      "loss": 0.8984,
      "step": 43
    },
    {
      "epoch": 0.09859943977591036,
      "grad_norm": 0.2726304233074188,
      "learning_rate": 4.943820224719101e-05,
      "loss": 0.987,
      "step": 44
    },
    {
      "epoch": 0.10084033613445378,
      "grad_norm": 0.2733825445175171,
      "learning_rate": 5.0561797752808995e-05,
      "loss": 0.9438,
      "step": 45
    },
    {
      "epoch": 0.1030812324929972,
      "grad_norm": 0.28922319412231445,
      "learning_rate": 5.168539325842697e-05,
      "loss": 0.8674,
      "step": 46
    },
    {
      "epoch": 0.10532212885154062,
      "grad_norm": 0.2743085026741028,
      "learning_rate": 5.2808988764044944e-05,
      "loss": 0.9041,
      "step": 47
    },
    {
      "epoch": 0.10756302521008404,
      "grad_norm": 0.28649550676345825,
      "learning_rate": 5.393258426966292e-05,
      "loss": 0.9057,
      "step": 48
    },
    {
      "epoch": 0.10980392156862745,
      "grad_norm": 0.2877427339553833,
      "learning_rate": 5.50561797752809e-05,
      "loss": 0.9139,
      "step": 49
    },
    {
      "epoch": 0.11204481792717087,
      "grad_norm": 0.27738648653030396,
      "learning_rate": 5.6179775280898885e-05,
      "loss": 0.8518,
      "step": 50
    },
    {
      "epoch": 0.11428571428571428,
      "grad_norm": 0.2839404046535492,
      "learning_rate": 5.730337078651685e-05,
      "loss": 0.8634,
      "step": 51
    },
    {
      "epoch": 0.1165266106442577,
      "grad_norm": 0.2748688757419586,
      "learning_rate": 5.8426966292134835e-05,
      "loss": 0.9504,
      "step": 52
    },
    {
      "epoch": 0.11876750700280111,
      "grad_norm": 0.2953556776046753,
      "learning_rate": 5.955056179775281e-05,
      "loss": 0.861,
      "step": 53
    },
    {
      "epoch": 0.12100840336134454,
      "grad_norm": 0.2947392165660858,
      "learning_rate": 6.067415730337079e-05,
      "loss": 0.8578,
      "step": 54
    },
    {
      "epoch": 0.12324929971988796,
      "grad_norm": 0.3029733896255493,
      "learning_rate": 6.179775280898876e-05,
      "loss": 0.895,
      "step": 55
    },
    {
      "epoch": 0.12549019607843137,
      "grad_norm": 0.28483161330223083,
      "learning_rate": 6.292134831460675e-05,
      "loss": 0.9316,
      "step": 56
    },
    {
      "epoch": 0.12773109243697478,
      "grad_norm": 0.280499666929245,
      "learning_rate": 6.404494382022472e-05,
      "loss": 0.8763,
      "step": 57
    },
    {
      "epoch": 0.12997198879551822,
      "grad_norm": 0.2687634825706482,
      "learning_rate": 6.51685393258427e-05,
      "loss": 0.9216,
      "step": 58
    },
    {
      "epoch": 0.13221288515406163,
      "grad_norm": 0.2869422435760498,
      "learning_rate": 6.629213483146067e-05,
      "loss": 0.8783,
      "step": 59
    },
    {
      "epoch": 0.13445378151260504,
      "grad_norm": 0.29140859842300415,
      "learning_rate": 6.741573033707866e-05,
      "loss": 0.9613,
      "step": 60
    },
    {
      "epoch": 0.13669467787114845,
      "grad_norm": 0.29342207312583923,
      "learning_rate": 6.853932584269663e-05,
      "loss": 0.982,
      "step": 61
    },
    {
      "epoch": 0.13893557422969188,
      "grad_norm": 0.29143285751342773,
      "learning_rate": 6.966292134831462e-05,
      "loss": 0.8857,
      "step": 62
    },
    {
      "epoch": 0.1411764705882353,
      "grad_norm": 0.2944166660308838,
      "learning_rate": 7.078651685393259e-05,
      "loss": 0.8668,
      "step": 63
    },
    {
      "epoch": 0.1434173669467787,
      "grad_norm": 0.27430447936058044,
      "learning_rate": 7.191011235955056e-05,
      "loss": 0.9403,
      "step": 64
    },
    {
      "epoch": 0.14565826330532214,
      "grad_norm": 0.274800568819046,
      "learning_rate": 7.303370786516854e-05,
      "loss": 0.8689,
      "step": 65
    },
    {
      "epoch": 0.14789915966386555,
      "grad_norm": 0.3063383102416992,
      "learning_rate": 7.415730337078653e-05,
      "loss": 0.9217,
      "step": 66
    },
    {
      "epoch": 0.15014005602240896,
      "grad_norm": 0.26958584785461426,
      "learning_rate": 7.52808988764045e-05,
      "loss": 0.949,
      "step": 67
    },
    {
      "epoch": 0.1523809523809524,
      "grad_norm": 0.3030094504356384,
      "learning_rate": 7.640449438202247e-05,
      "loss": 0.8814,
      "step": 68
    },
    {
      "epoch": 0.1546218487394958,
      "grad_norm": 0.26790764927864075,
      "learning_rate": 7.752808988764046e-05,
      "loss": 0.9814,
      "step": 69
    },
    {
      "epoch": 0.1568627450980392,
      "grad_norm": 0.28143975138664246,
      "learning_rate": 7.865168539325843e-05,
      "loss": 0.8667,
      "step": 70
    },
    {
      "epoch": 0.15910364145658262,
      "grad_norm": 0.32539746165275574,
      "learning_rate": 7.97752808988764e-05,
      "loss": 1.0709,
      "step": 71
    },
    {
      "epoch": 0.16134453781512606,
      "grad_norm": 0.28114452958106995,
      "learning_rate": 8.089887640449438e-05,
      "loss": 0.9253,
      "step": 72
    },
    {
      "epoch": 0.16358543417366947,
      "grad_norm": 0.2680191993713379,
      "learning_rate": 8.202247191011237e-05,
      "loss": 0.9345,
      "step": 73
    },
    {
      "epoch": 0.16582633053221288,
      "grad_norm": 0.2928783893585205,
      "learning_rate": 8.314606741573034e-05,
      "loss": 0.906,
      "step": 74
    },
    {
      "epoch": 0.16806722689075632,
      "grad_norm": 0.2979438900947571,
      "learning_rate": 8.426966292134831e-05,
      "loss": 0.9581,
      "step": 75
    },
    {
      "epoch": 0.17030812324929973,
      "grad_norm": 0.27883946895599365,
      "learning_rate": 8.53932584269663e-05,
      "loss": 0.9203,
      "step": 76
    },
    {
      "epoch": 0.17254901960784313,
      "grad_norm": 0.3945503234863281,
      "learning_rate": 8.651685393258427e-05,
      "loss": 0.8136,
      "step": 77
    },
    {
      "epoch": 0.17478991596638654,
      "grad_norm": 0.27328184247016907,
      "learning_rate": 8.764044943820225e-05,
      "loss": 0.8966,
      "step": 78
    },
    {
      "epoch": 0.17703081232492998,
      "grad_norm": 0.3049486577510834,
      "learning_rate": 8.876404494382022e-05,
      "loss": 0.9658,
      "step": 79
    },
    {
      "epoch": 0.1792717086834734,
      "grad_norm": 0.3143669366836548,
      "learning_rate": 8.988764044943821e-05,
      "loss": 0.9867,
      "step": 80
    },
    {
      "epoch": 0.1815126050420168,
      "grad_norm": 0.30048221349716187,
      "learning_rate": 9.101123595505618e-05,
      "loss": 0.9249,
      "step": 81
    },
    {
      "epoch": 0.18375350140056024,
      "grad_norm": 0.28177568316459656,
      "learning_rate": 9.213483146067416e-05,
      "loss": 0.9899,
      "step": 82
    },
    {
      "epoch": 0.18599439775910365,
      "grad_norm": 0.296478807926178,
      "learning_rate": 9.325842696629214e-05,
      "loss": 0.8476,
      "step": 83
    },
    {
      "epoch": 0.18823529411764706,
      "grad_norm": 0.2855791449546814,
      "learning_rate": 9.438202247191012e-05,
      "loss": 0.8869,
      "step": 84
    },
    {
      "epoch": 0.19047619047619047,
      "grad_norm": 0.2829147279262543,
      "learning_rate": 9.550561797752809e-05,
      "loss": 0.9274,
      "step": 85
    },
    {
      "epoch": 0.1927170868347339,
      "grad_norm": 0.2549046277999878,
      "learning_rate": 9.662921348314608e-05,
      "loss": 0.8535,
      "step": 86
    },
    {
      "epoch": 0.1949579831932773,
      "grad_norm": 0.2655014991760254,
      "learning_rate": 9.775280898876405e-05,
      "loss": 0.8905,
      "step": 87
    },
    {
      "epoch": 0.19719887955182072,
      "grad_norm": 0.27607807517051697,
      "learning_rate": 9.887640449438202e-05,
      "loss": 0.8788,
      "step": 88
    },
    {
      "epoch": 0.19943977591036416,
      "grad_norm": 0.24970707297325134,
      "learning_rate": 0.0001,
      "loss": 0.7632,
      "step": 89
    },
    {
      "epoch": 0.20168067226890757,
      "grad_norm": 0.2821432650089264,
      "learning_rate": 0.00010112359550561799,
      "loss": 0.9314,
      "step": 90
    },
    {
      "epoch": 0.20392156862745098,
      "grad_norm": 0.28368303179740906,
      "learning_rate": 0.00010224719101123596,
      "loss": 0.8424,
      "step": 91
    },
    {
      "epoch": 0.2061624649859944,
      "grad_norm": 0.3087138235569,
      "learning_rate": 0.00010337078651685395,
      "loss": 0.9787,
      "step": 92
    },
    {
      "epoch": 0.20840336134453782,
      "grad_norm": 0.2952103614807129,
      "learning_rate": 0.00010449438202247193,
      "loss": 0.9679,
      "step": 93
    },
    {
      "epoch": 0.21064425770308123,
      "grad_norm": 0.2875281572341919,
      "learning_rate": 0.00010561797752808989,
      "loss": 0.9181,
      "step": 94
    },
    {
      "epoch": 0.21288515406162464,
      "grad_norm": 0.3084465265274048,
      "learning_rate": 0.00010674157303370786,
      "loss": 0.9615,
      "step": 95
    },
    {
      "epoch": 0.21512605042016808,
      "grad_norm": 0.28005871176719666,
      "learning_rate": 0.00010786516853932584,
      "loss": 0.8757,
      "step": 96
    },
    {
      "epoch": 0.2173669467787115,
      "grad_norm": 0.2795560657978058,
      "learning_rate": 0.00010898876404494383,
      "loss": 0.8266,
      "step": 97
    },
    {
      "epoch": 0.2196078431372549,
      "grad_norm": 0.2671497166156769,
      "learning_rate": 0.0001101123595505618,
      "loss": 0.8693,
      "step": 98
    },
    {
      "epoch": 0.2218487394957983,
      "grad_norm": 0.24397605657577515,
      "learning_rate": 0.00011123595505617979,
      "loss": 0.8334,
      "step": 99
    },
    {
      "epoch": 0.22408963585434175,
      "grad_norm": 0.26632094383239746,
      "learning_rate": 0.00011235955056179777,
      "loss": 0.966,
      "step": 100
    },
    {
      "epoch": 0.22633053221288515,
      "grad_norm": 0.2785671055316925,
      "learning_rate": 0.00011348314606741574,
      "loss": 0.8823,
      "step": 101
    },
    {
      "epoch": 0.22857142857142856,
      "grad_norm": 0.26920077204704285,
      "learning_rate": 0.0001146067415730337,
      "loss": 0.9726,
      "step": 102
    },
    {
      "epoch": 0.230812324929972,
      "grad_norm": 0.2633483409881592,
      "learning_rate": 0.00011573033707865168,
      "loss": 0.8849,
      "step": 103
    },
    {
      "epoch": 0.2330532212885154,
      "grad_norm": 0.26563239097595215,
      "learning_rate": 0.00011685393258426967,
      "loss": 0.7896,
      "step": 104
    },
    {
      "epoch": 0.23529411764705882,
      "grad_norm": 0.27475470304489136,
      "learning_rate": 0.00011797752808988764,
      "loss": 0.9659,
      "step": 105
    },
    {
      "epoch": 0.23753501400560223,
      "grad_norm": 0.2691081166267395,
      "learning_rate": 0.00011910112359550563,
      "loss": 0.9758,
      "step": 106
    },
    {
      "epoch": 0.23977591036414567,
      "grad_norm": 0.2714226543903351,
      "learning_rate": 0.00012022471910112361,
      "loss": 0.8736,
      "step": 107
    },
    {
      "epoch": 0.24201680672268908,
      "grad_norm": 0.2638857960700989,
      "learning_rate": 0.00012134831460674158,
      "loss": 0.8792,
      "step": 108
    },
    {
      "epoch": 0.24425770308123249,
      "grad_norm": 0.25696009397506714,
      "learning_rate": 0.00012247191011235955,
      "loss": 0.8813,
      "step": 109
    },
    {
      "epoch": 0.24649859943977592,
      "grad_norm": 0.27648770809173584,
      "learning_rate": 0.00012359550561797752,
      "loss": 0.9341,
      "step": 110
    },
    {
      "epoch": 0.24873949579831933,
      "grad_norm": 0.27543121576309204,
      "learning_rate": 0.0001247191011235955,
      "loss": 0.8102,
      "step": 111
    },
    {
      "epoch": 0.25098039215686274,
      "grad_norm": 0.2804222106933594,
      "learning_rate": 0.0001258426966292135,
      "loss": 0.9004,
      "step": 112
    },
    {
      "epoch": 0.25322128851540615,
      "grad_norm": 0.27446436882019043,
      "learning_rate": 0.00012696629213483147,
      "loss": 0.8432,
      "step": 113
    },
    {
      "epoch": 0.25546218487394956,
      "grad_norm": 0.27675163745880127,
      "learning_rate": 0.00012808988764044944,
      "loss": 0.8868,
      "step": 114
    },
    {
      "epoch": 0.25770308123249297,
      "grad_norm": 0.24772736430168152,
      "learning_rate": 0.00012921348314606744,
      "loss": 0.8711,
      "step": 115
    },
    {
      "epoch": 0.25994397759103643,
      "grad_norm": 0.2736036479473114,
      "learning_rate": 0.0001303370786516854,
      "loss": 0.922,
      "step": 116
    },
    {
      "epoch": 0.26218487394957984,
      "grad_norm": 0.23815171420574188,
      "learning_rate": 0.00013146067415730338,
      "loss": 0.8469,
      "step": 117
    },
    {
      "epoch": 0.26442577030812325,
      "grad_norm": 0.2564987540245056,
      "learning_rate": 0.00013258426966292135,
      "loss": 0.7626,
      "step": 118
    },
    {
      "epoch": 0.26666666666666666,
      "grad_norm": 0.26105883717536926,
      "learning_rate": 0.00013370786516853932,
      "loss": 0.7911,
      "step": 119
    },
    {
      "epoch": 0.2689075630252101,
      "grad_norm": 0.2915550768375397,
      "learning_rate": 0.00013483146067415732,
      "loss": 0.9643,
      "step": 120
    },
    {
      "epoch": 0.2711484593837535,
      "grad_norm": 0.28031301498413086,
      "learning_rate": 0.0001359550561797753,
      "loss": 0.8797,
      "step": 121
    },
    {
      "epoch": 0.2733893557422969,
      "grad_norm": 0.2468908429145813,
      "learning_rate": 0.00013707865168539326,
      "loss": 0.8497,
      "step": 122
    },
    {
      "epoch": 0.27563025210084036,
      "grad_norm": 0.2498752921819687,
      "learning_rate": 0.00013820224719101123,
      "loss": 0.842,
      "step": 123
    },
    {
      "epoch": 0.27787114845938377,
      "grad_norm": 0.2517074942588806,
      "learning_rate": 0.00013932584269662923,
      "loss": 0.8072,
      "step": 124
    },
    {
      "epoch": 0.2801120448179272,
      "grad_norm": 0.24205273389816284,
      "learning_rate": 0.0001404494382022472,
      "loss": 0.796,
      "step": 125
    },
    {
      "epoch": 0.2823529411764706,
      "grad_norm": 0.259343683719635,
      "learning_rate": 0.00014157303370786517,
      "loss": 0.8609,
      "step": 126
    },
    {
      "epoch": 0.284593837535014,
      "grad_norm": 0.2564795911312103,
      "learning_rate": 0.00014269662921348315,
      "loss": 0.8976,
      "step": 127
    },
    {
      "epoch": 0.2868347338935574,
      "grad_norm": 0.2650969922542572,
      "learning_rate": 0.00014382022471910112,
      "loss": 0.8239,
      "step": 128
    },
    {
      "epoch": 0.28907563025210087,
      "grad_norm": 0.26443368196487427,
      "learning_rate": 0.00014494382022471912,
      "loss": 0.8479,
      "step": 129
    },
    {
      "epoch": 0.2913165266106443,
      "grad_norm": 0.26897069811820984,
      "learning_rate": 0.0001460674157303371,
      "loss": 0.9104,
      "step": 130
    },
    {
      "epoch": 0.2935574229691877,
      "grad_norm": 0.2578631341457367,
      "learning_rate": 0.00014719101123595506,
      "loss": 0.8151,
      "step": 131
    },
    {
      "epoch": 0.2957983193277311,
      "grad_norm": 0.2454749345779419,
      "learning_rate": 0.00014831460674157306,
      "loss": 0.7915,
      "step": 132
    },
    {
      "epoch": 0.2980392156862745,
      "grad_norm": 0.25589731335639954,
      "learning_rate": 0.00014943820224719103,
      "loss": 0.8952,
      "step": 133
    },
    {
      "epoch": 0.3002801120448179,
      "grad_norm": 0.2591662108898163,
      "learning_rate": 0.000150561797752809,
      "loss": 0.8112,
      "step": 134
    },
    {
      "epoch": 0.3025210084033613,
      "grad_norm": 0.26816102862358093,
      "learning_rate": 0.00015168539325842697,
      "loss": 0.8893,
      "step": 135
    },
    {
      "epoch": 0.3047619047619048,
      "grad_norm": 0.24405767023563385,
      "learning_rate": 0.00015280898876404494,
      "loss": 0.877,
      "step": 136
    },
    {
      "epoch": 0.3070028011204482,
      "grad_norm": 0.2588540315628052,
      "learning_rate": 0.00015393258426966294,
      "loss": 0.7779,
      "step": 137
    },
    {
      "epoch": 0.3092436974789916,
      "grad_norm": 0.27598896622657776,
      "learning_rate": 0.0001550561797752809,
      "loss": 0.7752,
      "step": 138
    },
    {
      "epoch": 0.311484593837535,
      "grad_norm": 0.24622836709022522,
      "learning_rate": 0.00015617977528089888,
      "loss": 0.8849,
      "step": 139
    },
    {
      "epoch": 0.3137254901960784,
      "grad_norm": 0.2502545118331909,
      "learning_rate": 0.00015730337078651685,
      "loss": 0.8012,
      "step": 140
    },
    {
      "epoch": 0.31596638655462184,
      "grad_norm": 0.25384724140167236,
      "learning_rate": 0.00015842696629213485,
      "loss": 0.8395,
      "step": 141
    },
    {
      "epoch": 0.31820728291316525,
      "grad_norm": 0.2527698874473572,
      "learning_rate": 0.0001595505617977528,
      "loss": 0.831,
      "step": 142
    },
    {
      "epoch": 0.3204481792717087,
      "grad_norm": 0.24567513167858124,
      "learning_rate": 0.0001606741573033708,
      "loss": 0.7959,
      "step": 143
    },
    {
      "epoch": 0.3226890756302521,
      "grad_norm": 0.24283619225025177,
      "learning_rate": 0.00016179775280898877,
      "loss": 0.8146,
      "step": 144
    },
    {
      "epoch": 0.32492997198879553,
      "grad_norm": 0.2708129286766052,
      "learning_rate": 0.00016292134831460674,
      "loss": 0.905,
      "step": 145
    },
    {
      "epoch": 0.32717086834733894,
      "grad_norm": 0.27091729640960693,
      "learning_rate": 0.00016404494382022474,
      "loss": 0.8681,
      "step": 146
    },
    {
      "epoch": 0.32941176470588235,
      "grad_norm": 0.2502163350582123,
      "learning_rate": 0.0001651685393258427,
      "loss": 0.8859,
      "step": 147
    },
    {
      "epoch": 0.33165266106442576,
      "grad_norm": 0.23066553473472595,
      "learning_rate": 0.00016629213483146068,
      "loss": 0.9034,
      "step": 148
    },
    {
      "epoch": 0.33389355742296917,
      "grad_norm": 0.2503213882446289,
      "learning_rate": 0.00016741573033707868,
      "loss": 0.8348,
      "step": 149
    },
    {
      "epoch": 0.33613445378151263,
      "grad_norm": 0.25126519799232483,
      "learning_rate": 0.00016853932584269662,
      "loss": 0.8553,
      "step": 150
    },
    {
      "epoch": 0.33837535014005604,
      "grad_norm": 0.241397425532341,
      "learning_rate": 0.00016966292134831462,
      "loss": 0.9132,
      "step": 151
    },
    {
      "epoch": 0.34061624649859945,
      "grad_norm": 0.25682827830314636,
      "learning_rate": 0.0001707865168539326,
      "loss": 0.9481,
      "step": 152
    },
    {
      "epoch": 0.34285714285714286,
      "grad_norm": 0.24024637043476105,
      "learning_rate": 0.00017191011235955056,
      "loss": 0.943,
      "step": 153
    },
    {
      "epoch": 0.34509803921568627,
      "grad_norm": 0.2626055181026459,
      "learning_rate": 0.00017303370786516853,
      "loss": 0.7863,
      "step": 154
    },
    {
      "epoch": 0.3473389355742297,
      "grad_norm": 0.24571183323860168,
      "learning_rate": 0.00017415730337078653,
      "loss": 0.926,
      "step": 155
    },
    {
      "epoch": 0.3495798319327731,
      "grad_norm": 0.2499912977218628,
      "learning_rate": 0.0001752808988764045,
      "loss": 0.8232,
      "step": 156
    },
    {
      "epoch": 0.35182072829131655,
      "grad_norm": 0.25473934412002563,
      "learning_rate": 0.00017640449438202248,
      "loss": 0.9021,
      "step": 157
    },
    {
      "epoch": 0.35406162464985996,
      "grad_norm": 0.25837019085884094,
      "learning_rate": 0.00017752808988764045,
      "loss": 0.7753,
      "step": 158
    },
    {
      "epoch": 0.3563025210084034,
      "grad_norm": 0.255958616733551,
      "learning_rate": 0.00017865168539325842,
      "loss": 0.9155,
      "step": 159
    },
    {
      "epoch": 0.3585434173669468,
      "grad_norm": 0.24315786361694336,
      "learning_rate": 0.00017977528089887642,
      "loss": 0.8039,
      "step": 160
    },
    {
      "epoch": 0.3607843137254902,
      "grad_norm": 0.24614644050598145,
      "learning_rate": 0.0001808988764044944,
      "loss": 0.8857,
      "step": 161
    },
    {
      "epoch": 0.3630252100840336,
      "grad_norm": 0.24280671775341034,
      "learning_rate": 0.00018202247191011236,
      "loss": 0.8354,
      "step": 162
    },
    {
      "epoch": 0.365266106442577,
      "grad_norm": 0.2597411572933197,
      "learning_rate": 0.00018314606741573036,
      "loss": 0.8852,
      "step": 163
    },
    {
      "epoch": 0.3675070028011205,
      "grad_norm": 0.2597702145576477,
      "learning_rate": 0.00018426966292134833,
      "loss": 0.9029,
      "step": 164
    },
    {
      "epoch": 0.3697478991596639,
      "grad_norm": 0.23551709949970245,
      "learning_rate": 0.0001853932584269663,
      "loss": 0.9118,
      "step": 165
    },
    {
      "epoch": 0.3719887955182073,
      "grad_norm": 0.2516990303993225,
      "learning_rate": 0.00018651685393258427,
      "loss": 0.7997,
      "step": 166
    },
    {
      "epoch": 0.3742296918767507,
      "grad_norm": 0.2297232747077942,
      "learning_rate": 0.00018764044943820224,
      "loss": 0.7823,
      "step": 167
    },
    {
      "epoch": 0.3764705882352941,
      "grad_norm": 0.22287945449352264,
      "learning_rate": 0.00018876404494382024,
      "loss": 0.8609,
      "step": 168
    },
    {
      "epoch": 0.3787114845938375,
      "grad_norm": 0.2428523749113083,
      "learning_rate": 0.0001898876404494382,
      "loss": 0.8842,
      "step": 169
    },
    {
      "epoch": 0.38095238095238093,
      "grad_norm": 0.25949063897132874,
      "learning_rate": 0.00019101123595505618,
      "loss": 0.7737,
      "step": 170
    },
    {
      "epoch": 0.3831932773109244,
      "grad_norm": 0.2532324492931366,
      "learning_rate": 0.00019213483146067416,
      "loss": 0.7548,
      "step": 171
    },
    {
      "epoch": 0.3854341736694678,
      "grad_norm": 0.2657643258571625,
      "learning_rate": 0.00019325842696629215,
      "loss": 0.8375,
      "step": 172
    },
    {
      "epoch": 0.3876750700280112,
      "grad_norm": 0.2578238546848297,
      "learning_rate": 0.00019438202247191013,
      "loss": 0.8591,
      "step": 173
    },
    {
      "epoch": 0.3899159663865546,
      "grad_norm": 0.24303969740867615,
      "learning_rate": 0.0001955056179775281,
      "loss": 0.8131,
      "step": 174
    },
    {
      "epoch": 0.39215686274509803,
      "grad_norm": 0.271139919757843,
      "learning_rate": 0.00019662921348314607,
      "loss": 0.8234,
      "step": 175
    },
    {
      "epoch": 0.39439775910364144,
      "grad_norm": 0.2569217085838318,
      "learning_rate": 0.00019775280898876404,
      "loss": 0.8907,
      "step": 176
    },
    {
      "epoch": 0.39663865546218485,
      "grad_norm": 0.23687879741191864,
      "learning_rate": 0.00019887640449438204,
      "loss": 0.8082,
      "step": 177
    },
    {
      "epoch": 0.3988795518207283,
      "grad_norm": 0.24828100204467773,
      "learning_rate": 0.0002,
      "loss": 0.8575,
      "step": 178
    },
    {
      "epoch": 0.4011204481792717,
      "grad_norm": 0.24300478398799896,
      "learning_rate": 0.00019999980867200105,
      "loss": 0.7963,
      "step": 179
    },
    {
      "epoch": 0.40336134453781514,
      "grad_norm": 0.2662373483181,
      "learning_rate": 0.00019999923468873635,
      "loss": 0.8871,
      "step": 180
    },
    {
      "epoch": 0.40560224089635855,
      "grad_norm": 0.2600310146808624,
      "learning_rate": 0.00019999827805240226,
      "loss": 0.8477,
      "step": 181
    },
    {
      "epoch": 0.40784313725490196,
      "grad_norm": 0.26801761984825134,
      "learning_rate": 0.00019999693876665938,
      "loss": 0.8978,
      "step": 182
    },
    {
      "epoch": 0.41008403361344536,
      "grad_norm": 0.26510775089263916,
      "learning_rate": 0.00019999521683663262,
      "loss": 0.8387,
      "step": 183
    },
    {
      "epoch": 0.4123249299719888,
      "grad_norm": 0.25927454233169556,
      "learning_rate": 0.00019999311226891103,
      "loss": 0.884,
      "step": 184
    },
    {
      "epoch": 0.41456582633053224,
      "grad_norm": 0.2489653080701828,
      "learning_rate": 0.00019999062507154784,
      "loss": 0.9473,
      "step": 185
    },
    {
      "epoch": 0.41680672268907565,
      "grad_norm": 0.2461009919643402,
      "learning_rate": 0.0001999877552540605,
      "loss": 0.8609,
      "step": 186
    },
    {
      "epoch": 0.41904761904761906,
      "grad_norm": 0.24591152369976044,
      "learning_rate": 0.00019998450282743052,
      "loss": 0.9284,
      "step": 187
    },
    {
      "epoch": 0.42128851540616247,
      "grad_norm": 0.23085853457450867,
      "learning_rate": 0.00019998086780410353,
      "loss": 0.8898,
      "step": 188
    },
    {
      "epoch": 0.4235294117647059,
      "grad_norm": 0.2512655556201935,
      "learning_rate": 0.00019997685019798912,
      "loss": 0.8275,
      "step": 189
    },
    {
      "epoch": 0.4257703081232493,
      "grad_norm": 0.24720723927021027,
      "learning_rate": 0.0001999724500244609,
      "loss": 0.8809,
      "step": 190
    },
    {
      "epoch": 0.4280112044817927,
      "grad_norm": 0.25972652435302734,
      "learning_rate": 0.00019996766730035642,
      "loss": 0.891,
      "step": 191
    },
    {
      "epoch": 0.43025210084033616,
      "grad_norm": 0.26756009459495544,
      "learning_rate": 0.0001999625020439771,
      "loss": 0.923,
      "step": 192
    },
    {
      "epoch": 0.43249299719887957,
      "grad_norm": 0.24553890526294708,
      "learning_rate": 0.000199956954275088,
      "loss": 0.8222,
      "step": 193
    },
    {
      "epoch": 0.434733893557423,
      "grad_norm": 0.24937503039836884,
      "learning_rate": 0.0001999510240149181,
      "loss": 0.788,
      "step": 194
    },
    {
      "epoch": 0.4369747899159664,
      "grad_norm": 0.2749722898006439,
      "learning_rate": 0.00019994471128615985,
      "loss": 0.9383,
      "step": 195
    },
    {
      "epoch": 0.4392156862745098,
      "grad_norm": 0.25508439540863037,
      "learning_rate": 0.00019993801611296923,
      "loss": 0.8234,
      "step": 196
    },
    {
      "epoch": 0.4414565826330532,
      "grad_norm": 0.26953256130218506,
      "learning_rate": 0.00019993093852096582,
      "loss": 0.9895,
      "step": 197
    },
    {
      "epoch": 0.4436974789915966,
      "grad_norm": 0.26215213537216187,
      "learning_rate": 0.0001999234785372324,
      "loss": 0.8432,
      "step": 198
    },
    {
      "epoch": 0.4459383753501401,
      "grad_norm": 0.24869990348815918,
      "learning_rate": 0.00019991563619031508,
      "loss": 0.8786,
      "step": 199
    },
    {
      "epoch": 0.4481792717086835,
      "grad_norm": 0.23765677213668823,
      "learning_rate": 0.00019990741151022301,
      "loss": 0.9402,
      "step": 200
    },
    {
      "epoch": 0.4504201680672269,
      "grad_norm": 0.24099862575531006,
      "learning_rate": 0.00019989880452842847,
      "loss": 0.9192,
      "step": 201
    },
    {
      "epoch": 0.4526610644257703,
      "grad_norm": 0.2570018172264099,
      "learning_rate": 0.00019988981527786654,
      "loss": 0.846,
      "step": 202
    },
    {
      "epoch": 0.4549019607843137,
      "grad_norm": 0.2420913279056549,
      "learning_rate": 0.00019988044379293523,
      "loss": 0.9021,
      "step": 203
    },
    {
      "epoch": 0.45714285714285713,
      "grad_norm": 0.25546249747276306,
      "learning_rate": 0.00019987069010949496,
      "loss": 0.9191,
      "step": 204
    },
    {
      "epoch": 0.45938375350140054,
      "grad_norm": 0.25439539551734924,
      "learning_rate": 0.00019986055426486887,
      "loss": 0.9046,
      "step": 205
    },
    {
      "epoch": 0.461624649859944,
      "grad_norm": 0.23050928115844727,
      "learning_rate": 0.00019985003629784237,
      "loss": 0.7777,
      "step": 206
    },
    {
      "epoch": 0.4638655462184874,
      "grad_norm": 0.25798794627189636,
      "learning_rate": 0.00019983913624866304,
      "loss": 0.9232,
      "step": 207
    },
    {
      "epoch": 0.4661064425770308,
      "grad_norm": 0.2508363127708435,
      "learning_rate": 0.00019982785415904064,
      "loss": 0.9924,
      "step": 208
    },
    {
      "epoch": 0.46834733893557423,
      "grad_norm": 0.25454050302505493,
      "learning_rate": 0.00019981619007214673,
      "loss": 0.9056,
      "step": 209
    },
    {
      "epoch": 0.47058823529411764,
      "grad_norm": 0.24120093882083893,
      "learning_rate": 0.0001998041440326146,
      "loss": 0.8339,
      "step": 210
    },
    {
      "epoch": 0.47282913165266105,
      "grad_norm": 0.2521376609802246,
      "learning_rate": 0.00019979171608653924,
      "loss": 0.7907,
      "step": 211
    },
    {
      "epoch": 0.47507002801120446,
      "grad_norm": 0.2513487637042999,
      "learning_rate": 0.00019977890628147682,
      "loss": 0.9142,
      "step": 212
    },
    {
      "epoch": 0.4773109243697479,
      "grad_norm": 0.2808438241481781,
      "learning_rate": 0.00019976571466644492,
      "loss": 0.8708,
      "step": 213
    },
    {
      "epoch": 0.47955182072829133,
      "grad_norm": 0.2564331293106079,
      "learning_rate": 0.00019975214129192196,
      "loss": 0.8726,
      "step": 214
    },
    {
      "epoch": 0.48179271708683474,
      "grad_norm": 0.2591661214828491,
      "learning_rate": 0.00019973818620984738,
      "loss": 0.791,
      "step": 215
    },
    {
      "epoch": 0.48403361344537815,
      "grad_norm": 0.2555089592933655,
      "learning_rate": 0.00019972384947362101,
      "loss": 0.9129,
      "step": 216
    },
    {
      "epoch": 0.48627450980392156,
      "grad_norm": 0.2542738616466522,
      "learning_rate": 0.00019970913113810334,
      "loss": 0.8097,
      "step": 217
    },
    {
      "epoch": 0.48851540616246497,
      "grad_norm": 0.26333680748939514,
      "learning_rate": 0.0001996940312596149,
      "loss": 0.8342,
      "step": 218
    },
    {
      "epoch": 0.4907563025210084,
      "grad_norm": 0.24918504059314728,
      "learning_rate": 0.00019967854989593633,
      "loss": 0.8441,
      "step": 219
    },
    {
      "epoch": 0.49299719887955185,
      "grad_norm": 0.26157376170158386,
      "learning_rate": 0.00019966268710630797,
      "loss": 0.8891,
      "step": 220
    },
    {
      "epoch": 0.49523809523809526,
      "grad_norm": 0.277658611536026,
      "learning_rate": 0.00019964644295142968,
      "loss": 0.8862,
      "step": 221
    },
    {
      "epoch": 0.49747899159663866,
      "grad_norm": 0.2798251211643219,
      "learning_rate": 0.00019962981749346078,
      "loss": 0.8742,
      "step": 222
    },
    {
      "epoch": 0.4997198879551821,
      "grad_norm": 0.28391703963279724,
      "learning_rate": 0.00019961281079601957,
      "loss": 0.8928,
      "step": 223
    },
    {
      "epoch": 0.5019607843137255,
      "grad_norm": 0.2569884955883026,
      "learning_rate": 0.00019959542292418317,
      "loss": 0.8289,
      "step": 224
    },
    {
      "epoch": 0.5042016806722689,
      "grad_norm": 0.2689199447631836,
      "learning_rate": 0.00019957765394448728,
      "loss": 0.8002,
      "step": 225
    },
    {
      "epoch": 0.5064425770308123,
      "grad_norm": 0.2564886510372162,
      "learning_rate": 0.00019955950392492604,
      "loss": 0.8817,
      "step": 226
    },
    {
      "epoch": 0.5086834733893557,
      "grad_norm": 0.2417922168970108,
      "learning_rate": 0.00019954097293495155,
      "loss": 0.8838,
      "step": 227
    },
    {
      "epoch": 0.5109243697478991,
      "grad_norm": 0.22530929744243622,
      "learning_rate": 0.00019952206104547376,
      "loss": 0.7967,
      "step": 228
    },
    {
      "epoch": 0.5131652661064425,
      "grad_norm": 0.23360571265220642,
      "learning_rate": 0.00019950276832886017,
      "loss": 0.8364,
      "step": 229
    },
    {
      "epoch": 0.5154061624649859,
      "grad_norm": 0.2611772418022156,
      "learning_rate": 0.00019948309485893549,
      "loss": 0.8786,
      "step": 230
    },
    {
      "epoch": 0.5176470588235295,
      "grad_norm": 0.24788020551204681,
      "learning_rate": 0.00019946304071098142,
      "loss": 0.86,
      "step": 231
    },
    {
      "epoch": 0.5198879551820729,
      "grad_norm": 0.23259863257408142,
      "learning_rate": 0.00019944260596173641,
      "loss": 0.822,
      "step": 232
    },
    {
      "epoch": 0.5221288515406163,
      "grad_norm": 0.2678159773349762,
      "learning_rate": 0.0001994217906893952,
      "loss": 0.8522,
      "step": 233
    },
    {
      "epoch": 0.5243697478991597,
      "grad_norm": 0.268537312746048,
      "learning_rate": 0.00019940059497360873,
      "loss": 0.8638,
      "step": 234
    },
    {
      "epoch": 0.5266106442577031,
      "grad_norm": 0.26122671365737915,
      "learning_rate": 0.0001993790188954836,
      "loss": 0.8509,
      "step": 235
    },
    {
      "epoch": 0.5288515406162465,
      "grad_norm": 0.38401761651039124,
      "learning_rate": 0.00019935706253758207,
      "loss": 0.8184,
      "step": 236
    },
    {
      "epoch": 0.5310924369747899,
      "grad_norm": 0.2459888607263565,
      "learning_rate": 0.00019933472598392138,
      "loss": 0.8042,
      "step": 237
    },
    {
      "epoch": 0.5333333333333333,
      "grad_norm": 0.27041634917259216,
      "learning_rate": 0.0001993120093199737,
      "loss": 0.9426,
      "step": 238
    },
    {
      "epoch": 0.5355742296918767,
      "grad_norm": 0.2503630220890045,
      "learning_rate": 0.00019928891263266578,
      "loss": 0.901,
      "step": 239
    },
    {
      "epoch": 0.5378151260504201,
      "grad_norm": 0.2358655333518982,
      "learning_rate": 0.00019926543601037842,
      "loss": 0.8165,
      "step": 240
    },
    {
      "epoch": 0.5400560224089636,
      "grad_norm": 0.24630171060562134,
      "learning_rate": 0.00019924157954294628,
      "loss": 0.8083,
      "step": 241
    },
    {
      "epoch": 0.542296918767507,
      "grad_norm": 0.2504923939704895,
      "learning_rate": 0.00019921734332165766,
      "loss": 0.7973,
      "step": 242
    },
    {
      "epoch": 0.5445378151260504,
      "grad_norm": 0.2728249132633209,
      "learning_rate": 0.00019919272743925385,
      "loss": 0.8817,
      "step": 243
    },
    {
      "epoch": 0.5467787114845938,
      "grad_norm": 0.2694825828075409,
      "learning_rate": 0.000199167731989929,
      "loss": 0.8458,
      "step": 244
    },
    {
      "epoch": 0.5490196078431373,
      "grad_norm": 0.31109780073165894,
      "learning_rate": 0.00019914235706932972,
      "loss": 0.939,
      "step": 245
    },
    {
      "epoch": 0.5512605042016807,
      "grad_norm": 0.25847890973091125,
      "learning_rate": 0.0001991166027745547,
      "loss": 0.8704,
      "step": 246
    },
    {
      "epoch": 0.5535014005602241,
      "grad_norm": 0.2678435742855072,
      "learning_rate": 0.00019909046920415423,
      "loss": 0.7445,
      "step": 247
    },
    {
      "epoch": 0.5557422969187675,
      "grad_norm": 0.25951921939849854,
      "learning_rate": 0.00019906395645812998,
      "loss": 0.8869,
      "step": 248
    },
    {
      "epoch": 0.5579831932773109,
      "grad_norm": 0.25794005393981934,
      "learning_rate": 0.00019903706463793462,
      "loss": 0.9506,
      "step": 249
    },
    {
      "epoch": 0.5602240896358543,
      "grad_norm": 0.2340375930070877,
      "learning_rate": 0.00019900979384647127,
      "loss": 0.811,
      "step": 250
    },
    {
      "epoch": 0.5624649859943978,
      "grad_norm": 0.25867462158203125,
      "learning_rate": 0.0001989821441880933,
      "loss": 0.8621,
      "step": 251
    },
    {
      "epoch": 0.5647058823529412,
      "grad_norm": 0.2387334555387497,
      "learning_rate": 0.0001989541157686037,
      "loss": 0.8514,
      "step": 252
    },
    {
      "epoch": 0.5669467787114846,
      "grad_norm": 0.26006007194519043,
      "learning_rate": 0.00019892570869525496,
      "loss": 0.8946,
      "step": 253
    },
    {
      "epoch": 0.569187675070028,
      "grad_norm": 0.2735587954521179,
      "learning_rate": 0.00019889692307674845,
      "loss": 0.8605,
      "step": 254
    },
    {
      "epoch": 0.5714285714285714,
      "grad_norm": 0.28292015194892883,
      "learning_rate": 0.00019886775902323405,
      "loss": 1.0231,
      "step": 255
    },
    {
      "epoch": 0.5736694677871148,
      "grad_norm": 0.2500753402709961,
      "learning_rate": 0.00019883821664630976,
      "loss": 0.9155,
      "step": 256
    },
    {
      "epoch": 0.5759103641456582,
      "grad_norm": 0.23072321712970734,
      "learning_rate": 0.00019880829605902126,
      "loss": 0.8268,
      "step": 257
    },
    {
      "epoch": 0.5781512605042017,
      "grad_norm": 0.25353720784187317,
      "learning_rate": 0.0001987779973758615,
      "loss": 0.9315,
      "step": 258
    },
    {
      "epoch": 0.5803921568627451,
      "grad_norm": 0.24684756994247437,
      "learning_rate": 0.00019874732071277013,
      "loss": 0.8652,
      "step": 259
    },
    {
      "epoch": 0.5826330532212886,
      "grad_norm": 0.2583218812942505,
      "learning_rate": 0.0001987162661871333,
      "loss": 0.7722,
      "step": 260
    },
    {
      "epoch": 0.584873949579832,
      "grad_norm": 0.23789426684379578,
      "learning_rate": 0.00019868483391778302,
      "loss": 0.9084,
      "step": 261
    },
    {
      "epoch": 0.5871148459383754,
      "grad_norm": 0.24503661692142487,
      "learning_rate": 0.00019865302402499678,
      "loss": 0.8683,
      "step": 262
    },
    {
      "epoch": 0.5893557422969188,
      "grad_norm": 0.2724620997905731,
      "learning_rate": 0.00019862083663049694,
      "loss": 0.8323,
      "step": 263
    },
    {
      "epoch": 0.5915966386554622,
      "grad_norm": 0.27704504132270813,
      "learning_rate": 0.0001985882718574506,
      "loss": 0.9132,
      "step": 264
    },
    {
      "epoch": 0.5938375350140056,
      "grad_norm": 0.2760598063468933,
      "learning_rate": 0.00019855532983046876,
      "loss": 0.7416,
      "step": 265
    },
    {
      "epoch": 0.596078431372549,
      "grad_norm": 0.26945289969444275,
      "learning_rate": 0.00019852201067560606,
      "loss": 0.965,
      "step": 266
    },
    {
      "epoch": 0.5983193277310924,
      "grad_norm": 0.2512185573577881,
      "learning_rate": 0.0001984883145203603,
      "loss": 0.8582,
      "step": 267
    },
    {
      "epoch": 0.6005602240896358,
      "grad_norm": 0.24201013147830963,
      "learning_rate": 0.00019845424149367177,
      "loss": 0.8433,
      "step": 268
    },
    {
      "epoch": 0.6028011204481792,
      "grad_norm": 0.24099834263324738,
      "learning_rate": 0.000198419791725923,
      "loss": 0.9501,
      "step": 269
    },
    {
      "epoch": 0.6050420168067226,
      "grad_norm": 0.24521470069885254,
      "learning_rate": 0.00019838496534893806,
      "loss": 0.8458,
      "step": 270
    },
    {
      "epoch": 0.6072829131652661,
      "grad_norm": 0.2377120554447174,
      "learning_rate": 0.00019834976249598221,
      "loss": 0.8934,
      "step": 271
    },
    {
      "epoch": 0.6095238095238096,
      "grad_norm": 0.2444024235010147,
      "learning_rate": 0.00019831418330176125,
      "loss": 0.8326,
      "step": 272
    },
    {
      "epoch": 0.611764705882353,
      "grad_norm": 0.23458163440227509,
      "learning_rate": 0.0001982782279024211,
      "loss": 0.8743,
      "step": 273
    },
    {
      "epoch": 0.6140056022408964,
      "grad_norm": 0.2571447491645813,
      "learning_rate": 0.00019824189643554725,
      "loss": 0.8265,
      "step": 274
    },
    {
      "epoch": 0.6162464985994398,
      "grad_norm": 0.25711604952812195,
      "learning_rate": 0.00019820518904016426,
      "loss": 0.8418,
      "step": 275
    },
    {
      "epoch": 0.6184873949579832,
      "grad_norm": 0.26878827810287476,
      "learning_rate": 0.00019816810585673514,
      "loss": 0.8007,
      "step": 276
    },
    {
      "epoch": 0.6207282913165266,
      "grad_norm": 0.2555851638317108,
      "learning_rate": 0.00019813064702716094,
      "loss": 0.8536,
      "step": 277
    },
    {
      "epoch": 0.62296918767507,
      "grad_norm": 0.2718588411808014,
      "learning_rate": 0.00019809281269478012,
      "loss": 0.8884,
      "step": 278
    },
    {
      "epoch": 0.6252100840336134,
      "grad_norm": 0.25706928968429565,
      "learning_rate": 0.00019805460300436803,
      "loss": 0.8729,
      "step": 279
    },
    {
      "epoch": 0.6274509803921569,
      "grad_norm": 0.23707084357738495,
      "learning_rate": 0.00019801601810213635,
      "loss": 0.8268,
      "step": 280
    },
    {
      "epoch": 0.6296918767507003,
      "grad_norm": 0.24094390869140625,
      "learning_rate": 0.00019797705813573245,
      "loss": 0.8457,
      "step": 281
    },
    {
      "epoch": 0.6319327731092437,
      "grad_norm": 0.24794656038284302,
      "learning_rate": 0.00019793772325423908,
      "loss": 0.8495,
      "step": 282
    },
    {
      "epoch": 0.6341736694677871,
      "grad_norm": 0.2355436086654663,
      "learning_rate": 0.00019789801360817346,
      "loss": 0.8167,
      "step": 283
    },
    {
      "epoch": 0.6364145658263305,
      "grad_norm": 0.24097253382205963,
      "learning_rate": 0.00019785792934948695,
      "loss": 0.8887,
      "step": 284
    },
    {
      "epoch": 0.6386554621848739,
      "grad_norm": 0.23715715110301971,
      "learning_rate": 0.00019781747063156435,
      "loss": 0.8205,
      "step": 285
    },
    {
      "epoch": 0.6408963585434174,
      "grad_norm": 0.2627374529838562,
      "learning_rate": 0.00019777663760922343,
      "loss": 0.9175,
      "step": 286
    },
    {
      "epoch": 0.6431372549019608,
      "grad_norm": 0.25734400749206543,
      "learning_rate": 0.00019773543043871412,
      "loss": 0.8104,
      "step": 287
    },
    {
      "epoch": 0.6453781512605042,
      "grad_norm": 0.2477787584066391,
      "learning_rate": 0.0001976938492777182,
      "loss": 0.9969,
      "step": 288
    },
    {
      "epoch": 0.6476190476190476,
      "grad_norm": 0.2440386414527893,
      "learning_rate": 0.0001976518942853484,
      "loss": 0.8084,
      "step": 289
    },
    {
      "epoch": 0.6498599439775911,
      "grad_norm": 0.2703987956047058,
      "learning_rate": 0.00019760956562214806,
      "loss": 0.7827,
      "step": 290
    },
    {
      "epoch": 0.6521008403361345,
      "grad_norm": 0.29450032114982605,
      "learning_rate": 0.0001975668634500904,
      "loss": 0.8807,
      "step": 291
    },
    {
      "epoch": 0.6543417366946779,
      "grad_norm": 0.27439677715301514,
      "learning_rate": 0.00019752378793257776,
      "loss": 0.8152,
      "step": 292
    },
    {
      "epoch": 0.6565826330532213,
      "grad_norm": 0.2940295338630676,
      "learning_rate": 0.00019748033923444122,
      "loss": 0.9051,
      "step": 293
    },
    {
      "epoch": 0.6588235294117647,
      "grad_norm": 0.2529405355453491,
      "learning_rate": 0.00019743651752193982,
      "loss": 0.7429,
      "step": 294
    },
    {
      "epoch": 0.6610644257703081,
      "grad_norm": 0.26964515447616577,
      "learning_rate": 0.00019739232296276003,
      "loss": 0.8584,
      "step": 295
    },
    {
      "epoch": 0.6633053221288515,
      "grad_norm": 0.24733929336071014,
      "learning_rate": 0.00019734775572601487,
      "loss": 0.8465,
      "step": 296
    },
    {
      "epoch": 0.6655462184873949,
      "grad_norm": 0.2559841275215149,
      "learning_rate": 0.00019730281598224364,
      "loss": 0.883,
      "step": 297
    },
    {
      "epoch": 0.6677871148459383,
      "grad_norm": 0.24375739693641663,
      "learning_rate": 0.00019725750390341094,
      "loss": 0.8042,
      "step": 298
    },
    {
      "epoch": 0.6700280112044817,
      "grad_norm": 0.25603991746902466,
      "learning_rate": 0.00019721181966290613,
      "loss": 0.9363,
      "step": 299
    },
    {
      "epoch": 0.6722689075630253,
      "grad_norm": 0.2391873151063919,
      "learning_rate": 0.00019716576343554274,
      "loss": 0.9364,
      "step": 300
    },
    {
      "epoch": 0.6745098039215687,
      "grad_norm": 0.24241115152835846,
      "learning_rate": 0.00019711933539755765,
      "loss": 0.8168,
      "step": 301
    },
    {
      "epoch": 0.6767507002801121,
      "grad_norm": 0.2441554218530655,
      "learning_rate": 0.00019707253572661055,
      "loss": 0.9179,
      "step": 302
    },
    {
      "epoch": 0.6789915966386555,
      "grad_norm": 0.2645583748817444,
      "learning_rate": 0.00019702536460178318,
      "loss": 0.7971,
      "step": 303
    },
    {
      "epoch": 0.6812324929971989,
      "grad_norm": 0.2557383179664612,
      "learning_rate": 0.0001969778222035787,
      "loss": 0.9112,
      "step": 304
    },
    {
      "epoch": 0.6834733893557423,
      "grad_norm": 0.25000718235969543,
      "learning_rate": 0.0001969299087139209,
      "loss": 0.7842,
      "step": 305
    },
    {
      "epoch": 0.6857142857142857,
      "grad_norm": 0.23475897312164307,
      "learning_rate": 0.00019688162431615367,
      "loss": 0.7806,
      "step": 306
    },
    {
      "epoch": 0.6879551820728291,
      "grad_norm": 0.2505607306957245,
      "learning_rate": 0.00019683296919504012,
      "loss": 0.922,
      "step": 307
    },
    {
      "epoch": 0.6901960784313725,
      "grad_norm": 0.2522655725479126,
      "learning_rate": 0.00019678394353676203,
      "loss": 0.7934,
      "step": 308
    },
    {
      "epoch": 0.692436974789916,
      "grad_norm": 0.2722029387950897,
      "learning_rate": 0.000196734547528919,
      "loss": 0.8775,
      "step": 309
    },
    {
      "epoch": 0.6946778711484594,
      "grad_norm": 0.26442402601242065,
      "learning_rate": 0.00019668478136052774,
      "loss": 0.8696,
      "step": 310
    },
    {
      "epoch": 0.6969187675070028,
      "grad_norm": 0.26388052105903625,
      "learning_rate": 0.00019663464522202162,
      "loss": 0.8569,
      "step": 311
    },
    {
      "epoch": 0.6991596638655462,
      "grad_norm": 0.26141613721847534,
      "learning_rate": 0.00019658413930524952,
      "loss": 0.8485,
      "step": 312
    },
    {
      "epoch": 0.7014005602240896,
      "grad_norm": 0.23456323146820068,
      "learning_rate": 0.00019653326380347533,
      "loss": 0.8913,
      "step": 313
    },
    {
      "epoch": 0.7036414565826331,
      "grad_norm": 0.24977454543113708,
      "learning_rate": 0.00019648201891137723,
      "loss": 0.8729,
      "step": 314
    },
    {
      "epoch": 0.7058823529411765,
      "grad_norm": 0.22706039249897003,
      "learning_rate": 0.0001964304048250469,
      "loss": 0.7885,
      "step": 315
    },
    {
      "epoch": 0.7081232492997199,
      "grad_norm": 0.24601607024669647,
      "learning_rate": 0.00019637842174198867,
      "loss": 0.8387,
      "step": 316
    },
    {
      "epoch": 0.7103641456582633,
      "grad_norm": 0.2545998990535736,
      "learning_rate": 0.000196326069861119,
      "loss": 0.8114,
      "step": 317
    },
    {
      "epoch": 0.7126050420168067,
      "grad_norm": 0.24375082552433014,
      "learning_rate": 0.00019627334938276546,
      "loss": 0.843,
      "step": 318
    },
    {
      "epoch": 0.7148459383753502,
      "grad_norm": 0.2519029378890991,
      "learning_rate": 0.00019622026050866614,
      "loss": 0.9088,
      "step": 319
    },
    {
      "epoch": 0.7170868347338936,
      "grad_norm": 0.27405208349227905,
      "learning_rate": 0.0001961668034419688,
      "loss": 0.958,
      "step": 320
    },
    {
      "epoch": 0.719327731092437,
      "grad_norm": 0.25491318106651306,
      "learning_rate": 0.0001961129783872301,
      "loss": 0.7692,
      "step": 321
    },
    {
      "epoch": 0.7215686274509804,
      "grad_norm": 0.250347375869751,
      "learning_rate": 0.00019605878555041485,
      "loss": 0.8321,
      "step": 322
    },
    {
      "epoch": 0.7238095238095238,
      "grad_norm": 0.24250715970993042,
      "learning_rate": 0.00019600422513889516,
      "loss": 0.7832,
      "step": 323
    },
    {
      "epoch": 0.7260504201680672,
      "grad_norm": 0.2599019706249237,
      "learning_rate": 0.00019594929736144976,
      "loss": 0.8736,
      "step": 324
    },
    {
      "epoch": 0.7282913165266106,
      "grad_norm": 0.25766611099243164,
      "learning_rate": 0.00019589400242826305,
      "loss": 0.7419,
      "step": 325
    },
    {
      "epoch": 0.730532212885154,
      "grad_norm": 0.254658967256546,
      "learning_rate": 0.00019583834055092445,
      "loss": 0.9058,
      "step": 326
    },
    {
      "epoch": 0.7327731092436974,
      "grad_norm": 0.2731349468231201,
      "learning_rate": 0.00019578231194242743,
      "loss": 0.9683,
      "step": 327
    },
    {
      "epoch": 0.735014005602241,
      "grad_norm": 0.22153563797473907,
      "learning_rate": 0.00019572591681716887,
      "loss": 0.8146,
      "step": 328
    },
    {
      "epoch": 0.7372549019607844,
      "grad_norm": 0.24707463383674622,
      "learning_rate": 0.00019566915539094803,
      "loss": 0.8204,
      "step": 329
    },
    {
      "epoch": 0.7394957983193278,
      "grad_norm": 0.2541884779930115,
      "learning_rate": 0.00019561202788096597,
      "loss": 0.7638,
      "step": 330
    },
    {
      "epoch": 0.7417366946778712,
      "grad_norm": 0.2314218282699585,
      "learning_rate": 0.00019555453450582452,
      "loss": 0.7502,
      "step": 331
    },
    {
      "epoch": 0.7439775910364146,
      "grad_norm": 0.24334260821342468,
      "learning_rate": 0.00019549667548552556,
      "loss": 0.912,
      "step": 332
    },
    {
      "epoch": 0.746218487394958,
      "grad_norm": 0.24473878741264343,
      "learning_rate": 0.00019543845104147,
      "loss": 0.7558,
      "step": 333
    },
    {
      "epoch": 0.7484593837535014,
      "grad_norm": 0.25403597950935364,
      "learning_rate": 0.00019537986139645726,
      "loss": 0.8406,
      "step": 334
    },
    {
      "epoch": 0.7507002801120448,
      "grad_norm": 0.24638508260250092,
      "learning_rate": 0.0001953209067746841,
      "loss": 0.736,
      "step": 335
    },
    {
      "epoch": 0.7529411764705882,
      "grad_norm": 0.25604501366615295,
      "learning_rate": 0.00019526158740174393,
      "loss": 0.867,
      "step": 336
    },
    {
      "epoch": 0.7551820728291316,
      "grad_norm": 0.2617231011390686,
      "learning_rate": 0.00019520190350462584,
      "loss": 0.8654,
      "step": 337
    },
    {
      "epoch": 0.757422969187675,
      "grad_norm": 0.2620690166950226,
      "learning_rate": 0.0001951418553117139,
      "loss": 0.8428,
      "step": 338
    },
    {
      "epoch": 0.7596638655462185,
      "grad_norm": 0.25454917550086975,
      "learning_rate": 0.0001950814430527861,
      "loss": 0.8676,
      "step": 339
    },
    {
      "epoch": 0.7619047619047619,
      "grad_norm": 0.26449549198150635,
      "learning_rate": 0.00019502066695901358,
      "loss": 0.8709,
      "step": 340
    },
    {
      "epoch": 0.7641456582633053,
      "grad_norm": 0.24709953367710114,
      "learning_rate": 0.0001949595272629597,
      "loss": 0.8312,
      "step": 341
    },
    {
      "epoch": 0.7663865546218488,
      "grad_norm": 0.2593318819999695,
      "learning_rate": 0.00019489802419857917,
      "loss": 0.8274,
      "step": 342
    },
    {
      "epoch": 0.7686274509803922,
      "grad_norm": 0.2448015958070755,
      "learning_rate": 0.00019483615800121716,
      "loss": 0.8226,
      "step": 343
    },
    {
      "epoch": 0.7708683473389356,
      "grad_norm": 0.26445460319519043,
      "learning_rate": 0.00019477392890760839,
      "loss": 0.8492,
      "step": 344
    },
    {
      "epoch": 0.773109243697479,
      "grad_norm": 0.2573208808898926,
      "learning_rate": 0.00019471133715587622,
      "loss": 0.8294,
      "step": 345
    },
    {
      "epoch": 0.7753501400560224,
      "grad_norm": 0.26753151416778564,
      "learning_rate": 0.00019464838298553173,
      "loss": 0.8446,
      "step": 346
    },
    {
      "epoch": 0.7775910364145658,
      "grad_norm": 0.2667967975139618,
      "learning_rate": 0.00019458506663747285,
      "loss": 0.8388,
      "step": 347
    },
    {
      "epoch": 0.7798319327731092,
      "grad_norm": 0.25934740900993347,
      "learning_rate": 0.00019452138835398332,
      "loss": 0.8149,
      "step": 348
    },
    {
      "epoch": 0.7820728291316527,
      "grad_norm": 0.2525850832462311,
      "learning_rate": 0.00019445734837873202,
      "loss": 0.8325,
      "step": 349
    },
    {
      "epoch": 0.7843137254901961,
      "grad_norm": 0.2837854325771332,
      "learning_rate": 0.00019439294695677167,
      "loss": 0.8795,
      "step": 350
    },
    {
      "epoch": 0.7865546218487395,
      "grad_norm": 0.26006975769996643,
      "learning_rate": 0.00019432818433453818,
      "loss": 0.8267,
      "step": 351
    },
    {
      "epoch": 0.7887955182072829,
      "grad_norm": 0.24872632324695587,
      "learning_rate": 0.00019426306075984965,
      "loss": 0.8553,
      "step": 352
    },
    {
      "epoch": 0.7910364145658263,
      "grad_norm": 0.23633168637752533,
      "learning_rate": 0.00019419757648190533,
      "loss": 0.8544,
      "step": 353
    },
    {
      "epoch": 0.7932773109243697,
      "grad_norm": 0.2425261288881302,
      "learning_rate": 0.00019413173175128473,
      "loss": 0.8645,
      "step": 354
    },
    {
      "epoch": 0.7955182072829131,
      "grad_norm": 0.23861053586006165,
      "learning_rate": 0.00019406552681994663,
      "loss": 0.8363,
      "step": 355
    },
    {
      "epoch": 0.7977591036414566,
      "grad_norm": 0.24729354679584503,
      "learning_rate": 0.00019399896194122822,
      "loss": 0.8401,
      "step": 356
    },
    {
      "epoch": 0.8,
      "grad_norm": 0.23853589594364166,
      "learning_rate": 0.000193932037369844,
      "loss": 0.8237,
      "step": 357
    },
    {
      "epoch": 0.8022408963585435,
      "grad_norm": 0.2654939293861389,
      "learning_rate": 0.00019386475336188484,
      "loss": 0.7491,
      "step": 358
    },
    {
      "epoch": 0.8044817927170869,
      "grad_norm": 0.27639004588127136,
      "learning_rate": 0.000193797110174817,
      "loss": 0.8755,
      "step": 359
    },
    {
      "epoch": 0.8067226890756303,
      "grad_norm": 0.23675435781478882,
      "learning_rate": 0.00019372910806748125,
      "loss": 0.8292,
      "step": 360
    },
    {
      "epoch": 0.8089635854341737,
      "grad_norm": 0.2371446043252945,
      "learning_rate": 0.0001936607473000917,
      "loss": 0.809,
      "step": 361
    },
    {
      "epoch": 0.8112044817927171,
      "grad_norm": 0.2529555559158325,
      "learning_rate": 0.0001935920281342349,
      "loss": 0.8403,
      "step": 362
    },
    {
      "epoch": 0.8134453781512605,
      "grad_norm": 0.2568047344684601,
      "learning_rate": 0.00019352295083286896,
      "loss": 0.7848,
      "step": 363
    },
    {
      "epoch": 0.8156862745098039,
      "grad_norm": 0.2613024413585663,
      "learning_rate": 0.0001934535156603222,
      "loss": 0.844,
      "step": 364
    },
    {
      "epoch": 0.8179271708683473,
      "grad_norm": 0.24079741537570953,
      "learning_rate": 0.0001933837228822925,
      "loss": 0.8029,
      "step": 365
    },
    {
      "epoch": 0.8201680672268907,
      "grad_norm": 0.24890519678592682,
      "learning_rate": 0.0001933135727658462,
      "loss": 0.8712,
      "step": 366
    },
    {
      "epoch": 0.8224089635854341,
      "grad_norm": 0.25198838114738464,
      "learning_rate": 0.00019324306557941682,
      "loss": 0.8368,
      "step": 367
    },
    {
      "epoch": 0.8246498599439775,
      "grad_norm": 0.2470208704471588,
      "learning_rate": 0.0001931722015928044,
      "loss": 0.8896,
      "step": 368
    },
    {
      "epoch": 0.826890756302521,
      "grad_norm": 0.25046589970588684,
      "learning_rate": 0.00019310098107717418,
      "loss": 0.7602,
      "step": 369
    },
    {
      "epoch": 0.8291316526610645,
      "grad_norm": 0.28005844354629517,
      "learning_rate": 0.0001930294043050558,
      "loss": 0.9443,
      "step": 370
    },
    {
      "epoch": 0.8313725490196079,
      "grad_norm": 0.6102829575538635,
      "learning_rate": 0.00019295747155034202,
      "loss": 0.911,
      "step": 371
    },
    {
      "epoch": 0.8336134453781513,
      "grad_norm": 0.2472289353609085,
      "learning_rate": 0.0001928851830882879,
      "loss": 0.8271,
      "step": 372
    },
    {
      "epoch": 0.8358543417366947,
      "grad_norm": 0.24470177292823792,
      "learning_rate": 0.0001928125391955095,
      "loss": 0.7837,
      "step": 373
    },
    {
      "epoch": 0.8380952380952381,
      "grad_norm": 0.2458019107580185,
      "learning_rate": 0.00019273954014998308,
      "loss": 0.8496,
      "step": 374
    },
    {
      "epoch": 0.8403361344537815,
      "grad_norm": 0.249577596783638,
      "learning_rate": 0.00019266618623104385,
      "loss": 0.7729,
      "step": 375
    },
    {
      "epoch": 0.8425770308123249,
      "grad_norm": 0.2461290806531906,
      "learning_rate": 0.000192592477719385,
      "loss": 0.7955,
      "step": 376
    },
    {
      "epoch": 0.8448179271708683,
      "grad_norm": 0.27021750807762146,
      "learning_rate": 0.00019251841489705655,
      "loss": 0.9384,
      "step": 377
    },
    {
      "epoch": 0.8470588235294118,
      "grad_norm": 0.2547335624694824,
      "learning_rate": 0.00019244399804746435,
      "loss": 0.8254,
      "step": 378
    },
    {
      "epoch": 0.8492997198879552,
      "grad_norm": 0.2620961368083954,
      "learning_rate": 0.0001923692274553689,
      "loss": 0.8587,
      "step": 379
    },
    {
      "epoch": 0.8515406162464986,
      "grad_norm": 0.25756919384002686,
      "learning_rate": 0.0001922941034068844,
      "loss": 0.7906,
      "step": 380
    },
    {
      "epoch": 0.853781512605042,
      "grad_norm": 0.25694355368614197,
      "learning_rate": 0.0001922186261894775,
      "loss": 0.7887,
      "step": 381
    },
    {
      "epoch": 0.8560224089635854,
      "grad_norm": 0.2538197636604309,
      "learning_rate": 0.0001921427960919663,
      "loss": 0.8861,
      "step": 382
    },
    {
      "epoch": 0.8582633053221288,
      "grad_norm": 0.2463122308254242,
      "learning_rate": 0.00019206661340451925,
      "loss": 0.8175,
      "step": 383
    },
    {
      "epoch": 0.8605042016806723,
      "grad_norm": 0.23905646800994873,
      "learning_rate": 0.00019199007841865396,
      "loss": 0.7914,
      "step": 384
    },
    {
      "epoch": 0.8627450980392157,
      "grad_norm": 0.2590409517288208,
      "learning_rate": 0.0001919131914272361,
      "loss": 0.8385,
      "step": 385
    },
    {
      "epoch": 0.8649859943977591,
      "grad_norm": 0.2520500719547272,
      "learning_rate": 0.00019183595272447842,
      "loss": 0.7961,
      "step": 386
    },
    {
      "epoch": 0.8672268907563025,
      "grad_norm": 0.2568177878856659,
      "learning_rate": 0.00019175836260593938,
      "loss": 0.8051,
      "step": 387
    },
    {
      "epoch": 0.869467787114846,
      "grad_norm": 0.27684271335601807,
      "learning_rate": 0.00019168042136852228,
      "loss": 0.8953,
      "step": 388
    },
    {
      "epoch": 0.8717086834733894,
      "grad_norm": 0.26281246542930603,
      "learning_rate": 0.0001916021293104739,
      "loss": 0.8602,
      "step": 389
    },
    {
      "epoch": 0.8739495798319328,
      "grad_norm": 0.29199978709220886,
      "learning_rate": 0.00019152348673138353,
      "loss": 0.9776,
      "step": 390
    },
    {
      "epoch": 0.8761904761904762,
      "grad_norm": 0.25914543867111206,
      "learning_rate": 0.0001914444939321817,
      "loss": 0.8394,
      "step": 391
    },
    {
      "epoch": 0.8784313725490196,
      "grad_norm": 0.2472960352897644,
      "learning_rate": 0.0001913651512151391,
      "loss": 0.7995,
      "step": 392
    },
    {
      "epoch": 0.880672268907563,
      "grad_norm": 0.24599507451057434,
      "learning_rate": 0.00019128545888386536,
      "loss": 0.7801,
      "step": 393
    },
    {
      "epoch": 0.8829131652661064,
      "grad_norm": 0.23776014149188995,
      "learning_rate": 0.00019120541724330803,
      "loss": 0.8068,
      "step": 394
    },
    {
      "epoch": 0.8851540616246498,
      "grad_norm": 0.27298274636268616,
      "learning_rate": 0.0001911250265997512,
      "loss": 0.9139,
      "step": 395
    },
    {
      "epoch": 0.8873949579831932,
      "grad_norm": 0.2653828561306,
      "learning_rate": 0.0001910442872608145,
      "loss": 0.8917,
      "step": 396
    },
    {
      "epoch": 0.8896358543417366,
      "grad_norm": 0.25794684886932373,
      "learning_rate": 0.00019096319953545185,
      "loss": 0.819,
      "step": 397
    },
    {
      "epoch": 0.8918767507002802,
      "grad_norm": 0.24696165323257446,
      "learning_rate": 0.0001908817637339503,
      "loss": 0.7535,
      "step": 398
    },
    {
      "epoch": 0.8941176470588236,
      "grad_norm": 0.2529006898403168,
      "learning_rate": 0.00019079998016792885,
      "loss": 0.7379,
      "step": 399
    },
    {
      "epoch": 0.896358543417367,
      "grad_norm": 0.24874147772789001,
      "learning_rate": 0.00019071784915033717,
      "loss": 0.8973,
      "step": 400
    },
    {
      "epoch": 0.8985994397759104,
      "grad_norm": 0.27747422456741333,
      "learning_rate": 0.00019063537099545455,
      "loss": 0.8685,
      "step": 401
    },
    {
      "epoch": 0.9008403361344538,
      "grad_norm": 0.25184211134910583,
      "learning_rate": 0.00019055254601888866,
      "loss": 0.7937,
      "step": 402
    },
    {
      "epoch": 0.9030812324929972,
      "grad_norm": 0.2565883994102478,
      "learning_rate": 0.00019046937453757413,
      "loss": 0.8677,
      "step": 403
    },
    {
      "epoch": 0.9053221288515406,
      "grad_norm": 0.24833756685256958,
      "learning_rate": 0.00019038585686977167,
      "loss": 0.8777,
      "step": 404
    },
    {
      "epoch": 0.907563025210084,
      "grad_norm": 0.24929295480251312,
      "learning_rate": 0.00019030199333506666,
      "loss": 0.8167,
      "step": 405
    },
    {
      "epoch": 0.9098039215686274,
      "grad_norm": 0.24500809609889984,
      "learning_rate": 0.00019021778425436795,
      "loss": 0.8675,
      "step": 406
    },
    {
      "epoch": 0.9120448179271708,
      "grad_norm": 0.25895681977272034,
      "learning_rate": 0.0001901332299499066,
      "loss": 0.8718,
      "step": 407
    },
    {
      "epoch": 0.9142857142857143,
      "grad_norm": 0.22836971282958984,
      "learning_rate": 0.00019004833074523478,
      "loss": 0.8602,
      "step": 408
    },
    {
      "epoch": 0.9165266106442577,
      "grad_norm": 0.26318010687828064,
      "learning_rate": 0.00018996308696522433,
      "loss": 0.838,
      "step": 409
    },
    {
      "epoch": 0.9187675070028011,
      "grad_norm": 0.24389663338661194,
      "learning_rate": 0.00018987749893606575,
      "loss": 0.7798,
      "step": 410
    },
    {
      "epoch": 0.9210084033613445,
      "grad_norm": 0.26448702812194824,
      "learning_rate": 0.0001897915669852667,
      "loss": 0.8053,
      "step": 411
    },
    {
      "epoch": 0.923249299719888,
      "grad_norm": 0.25245535373687744,
      "learning_rate": 0.000189705291441651,
      "loss": 0.7915,
      "step": 412
    },
    {
      "epoch": 0.9254901960784314,
      "grad_norm": 0.25623124837875366,
      "learning_rate": 0.00018961867263535715,
      "loss": 0.9167,
      "step": 413
    },
    {
      "epoch": 0.9277310924369748,
      "grad_norm": 0.25271835923194885,
      "learning_rate": 0.00018953171089783723,
      "loss": 0.8663,
      "step": 414
    },
    {
      "epoch": 0.9299719887955182,
      "grad_norm": 0.24757803976535797,
      "learning_rate": 0.00018944440656185556,
      "loss": 0.8411,
      "step": 415
    },
    {
      "epoch": 0.9322128851540616,
      "grad_norm": 0.23879915475845337,
      "learning_rate": 0.00018935675996148738,
      "loss": 0.8071,
      "step": 416
    },
    {
      "epoch": 0.934453781512605,
      "grad_norm": 0.3934721350669861,
      "learning_rate": 0.0001892687714321177,
      "loss": 0.7911,
      "step": 417
    },
    {
      "epoch": 0.9366946778711485,
      "grad_norm": 0.27968111634254456,
      "learning_rate": 0.00018918044131043985,
      "loss": 0.8452,
      "step": 418
    },
    {
      "epoch": 0.9389355742296919,
      "grad_norm": 0.2701101303100586,
      "learning_rate": 0.00018909176993445442,
      "loss": 0.8723,
      "step": 419
    },
    {
      "epoch": 0.9411764705882353,
      "grad_norm": 0.2606533169746399,
      "learning_rate": 0.00018900275764346768,
      "loss": 0.7908,
      "step": 420
    },
    {
      "epoch": 0.9434173669467787,
      "grad_norm": 0.2672193944454193,
      "learning_rate": 0.00018891340477809055,
      "loss": 0.9491,
      "step": 421
    },
    {
      "epoch": 0.9456582633053221,
      "grad_norm": 0.2676648795604706,
      "learning_rate": 0.00018882371168023706,
      "loss": 0.8352,
      "step": 422
    },
    {
      "epoch": 0.9478991596638655,
      "grad_norm": 0.265023410320282,
      "learning_rate": 0.0001887336786931233,
      "loss": 0.7894,
      "step": 423
    },
    {
      "epoch": 0.9501400560224089,
      "grad_norm": 0.24014434218406677,
      "learning_rate": 0.00018864330616126586,
      "loss": 0.8394,
      "step": 424
    },
    {
      "epoch": 0.9523809523809523,
      "grad_norm": 0.24389366805553436,
      "learning_rate": 0.00018855259443048067,
      "loss": 0.7857,
      "step": 425
    },
    {
      "epoch": 0.9546218487394958,
      "grad_norm": 0.2471270114183426,
      "learning_rate": 0.00018846154384788162,
      "loss": 0.8576,
      "step": 426
    },
    {
      "epoch": 0.9568627450980393,
      "grad_norm": 0.2577723264694214,
      "learning_rate": 0.00018837015476187916,
      "loss": 0.8377,
      "step": 427
    },
    {
      "epoch": 0.9591036414565827,
      "grad_norm": 0.3224787414073944,
      "learning_rate": 0.00018827842752217917,
      "loss": 0.8801,
      "step": 428
    },
    {
      "epoch": 0.9613445378151261,
      "grad_norm": 0.25494757294654846,
      "learning_rate": 0.00018818636247978145,
      "loss": 0.8173,
      "step": 429
    },
    {
      "epoch": 0.9635854341736695,
      "grad_norm": 0.24220331013202667,
      "learning_rate": 0.00018809395998697833,
      "loss": 0.7747,
      "step": 430
    },
    {
      "epoch": 0.9658263305322129,
      "grad_norm": 0.2741996645927429,
      "learning_rate": 0.00018800122039735358,
      "loss": 0.8636,
      "step": 431
    },
    {
      "epoch": 0.9680672268907563,
      "grad_norm": 0.2558667063713074,
      "learning_rate": 0.0001879081440657807,
      "loss": 0.8456,
      "step": 432
    },
    {
      "epoch": 0.9703081232492997,
      "grad_norm": 0.25905126333236694,
      "learning_rate": 0.00018781473134842197,
      "loss": 0.7961,
      "step": 433
    },
    {
      "epoch": 0.9725490196078431,
      "grad_norm": 0.23688547313213348,
      "learning_rate": 0.00018772098260272667,
      "loss": 0.7555,
      "step": 434
    },
    {
      "epoch": 0.9747899159663865,
      "grad_norm": 0.2701859176158905,
      "learning_rate": 0.00018762689818743007,
      "loss": 0.9353,
      "step": 435
    },
    {
      "epoch": 0.9770308123249299,
      "grad_norm": 0.24914319813251495,
      "learning_rate": 0.00018753247846255174,
      "loss": 0.7678,
      "step": 436
    },
    {
      "epoch": 0.9792717086834734,
      "grad_norm": 0.26182475686073303,
      "learning_rate": 0.00018743772378939448,
      "loss": 0.8374,
      "step": 437
    },
    {
      "epoch": 0.9815126050420168,
      "grad_norm": 0.2661891281604767,
      "learning_rate": 0.00018734263453054273,
      "loss": 0.8816,
      "step": 438
    },
    {
      "epoch": 0.9837535014005602,
      "grad_norm": 0.24797801673412323,
      "learning_rate": 0.0001872472110498612,
      "loss": 0.8069,
      "step": 439
    },
    {
      "epoch": 0.9859943977591037,
      "grad_norm": 0.24370808899402618,
      "learning_rate": 0.0001871514537124936,
      "loss": 0.7405,
      "step": 440
    },
    {
      "epoch": 0.9882352941176471,
      "grad_norm": 0.2744685709476471,
      "learning_rate": 0.00018705536288486118,
      "loss": 0.7706,
      "step": 441
    },
    {
      "epoch": 0.9904761904761905,
      "grad_norm": 0.265438437461853,
      "learning_rate": 0.0001869589389346611,
      "loss": 0.8649,
      "step": 442
    },
    {
      "epoch": 0.9927170868347339,
      "grad_norm": 0.24661187827587128,
      "learning_rate": 0.0001868621822308655,
      "loss": 0.8138,
      "step": 443
    },
    {
      "epoch": 0.9949579831932773,
      "grad_norm": 0.2580495774745941,
      "learning_rate": 0.00018676509314371974,
      "loss": 0.7765,
      "step": 444
    },
    {
      "epoch": 0.9971988795518207,
      "grad_norm": 0.2546556293964386,
      "learning_rate": 0.00018666767204474094,
      "loss": 0.8873,
      "step": 445
    },
    {
      "epoch": 0.9994397759103641,
      "grad_norm": 0.25944411754608154,
      "learning_rate": 0.00018656991930671686,
      "loss": 0.8651,
      "step": 446
    }
  ],
  "logging_steps": 1,
  "max_steps": 1784,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 4,
  "save_steps": 446,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 2.310622116052992e+17,
  "train_batch_size": 1,
  "trial_name": null,
  "trial_params": null
}