{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 1.9988795518207283,
  "eval_steps": 500,
  "global_step": 892,
  "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
    },
    {
      "epoch": 1.0016806722689076,
      "grad_norm": 0.25578224658966064,
      "learning_rate": 0.00018647183530370415,
      "loss": 0.9027,
      "step": 447
    },
    {
      "epoch": 1.003921568627451,
      "grad_norm": 0.24953621625900269,
      "learning_rate": 0.00018637342041102718,
      "loss": 0.6952,
      "step": 448
    },
    {
      "epoch": 1.0061624649859944,
      "grad_norm": 0.24714386463165283,
      "learning_rate": 0.0001862746750052764,
      "loss": 0.6983,
      "step": 449
    },
    {
      "epoch": 1.0084033613445378,
      "grad_norm": 0.2614993155002594,
      "learning_rate": 0.00018617559946430706,
      "loss": 0.7272,
      "step": 450
    },
    {
      "epoch": 1.0106442577030812,
      "grad_norm": 0.27017897367477417,
      "learning_rate": 0.00018607619416723765,
      "loss": 0.7644,
      "step": 451
    },
    {
      "epoch": 1.0128851540616246,
      "grad_norm": 0.28906649351119995,
      "learning_rate": 0.0001859764594944485,
      "loss": 0.7651,
      "step": 452
    },
    {
      "epoch": 1.015126050420168,
      "grad_norm": 0.28600478172302246,
      "learning_rate": 0.00018587639582758031,
      "loss": 0.732,
      "step": 453
    },
    {
      "epoch": 1.0173669467787114,
      "grad_norm": 0.28704679012298584,
      "learning_rate": 0.0001857760035495327,
      "loss": 0.713,
      "step": 454
    },
    {
      "epoch": 1.0196078431372548,
      "grad_norm": 0.36615249514579773,
      "learning_rate": 0.0001856752830444628,
      "loss": 0.8691,
      "step": 455
    },
    {
      "epoch": 1.0218487394957982,
      "grad_norm": 0.28983429074287415,
      "learning_rate": 0.00018557423469778357,
      "loss": 0.7513,
      "step": 456
    },
    {
      "epoch": 1.0240896358543417,
      "grad_norm": 0.2740822732448578,
      "learning_rate": 0.0001854728588961626,
      "loss": 0.7319,
      "step": 457
    },
    {
      "epoch": 1.026330532212885,
      "grad_norm": 0.26059162616729736,
      "learning_rate": 0.00018537115602752053,
      "loss": 0.7727,
      "step": 458
    },
    {
      "epoch": 1.0285714285714285,
      "grad_norm": 0.25983962416648865,
      "learning_rate": 0.00018526912648102943,
      "loss": 0.7428,
      "step": 459
    },
    {
      "epoch": 1.0308123249299719,
      "grad_norm": 0.2570248246192932,
      "learning_rate": 0.0001851667706471115,
      "loss": 0.8065,
      "step": 460
    },
    {
      "epoch": 1.0330532212885155,
      "grad_norm": 0.2523268163204193,
      "learning_rate": 0.0001850640889174375,
      "loss": 0.729,
      "step": 461
    },
    {
      "epoch": 1.035294117647059,
      "grad_norm": 0.2655740976333618,
      "learning_rate": 0.0001849610816849252,
      "loss": 0.7717,
      "step": 462
    },
    {
      "epoch": 1.0375350140056023,
      "grad_norm": 0.2684931755065918,
      "learning_rate": 0.0001848577493437379,
      "loss": 0.6862,
      "step": 463
    },
    {
      "epoch": 1.0397759103641457,
      "grad_norm": 0.29195067286491394,
      "learning_rate": 0.00018475409228928312,
      "loss": 0.7204,
      "step": 464
    },
    {
      "epoch": 1.0420168067226891,
      "grad_norm": 0.299556165933609,
      "learning_rate": 0.00018465011091821072,
      "loss": 0.8587,
      "step": 465
    },
    {
      "epoch": 1.0442577030812326,
      "grad_norm": 0.2898513078689575,
      "learning_rate": 0.00018454580562841163,
      "loss": 0.7628,
      "step": 466
    },
    {
      "epoch": 1.046498599439776,
      "grad_norm": 0.30156147480010986,
      "learning_rate": 0.00018444117681901638,
      "loss": 0.7437,
      "step": 467
    },
    {
      "epoch": 1.0487394957983194,
      "grad_norm": 0.2778584361076355,
      "learning_rate": 0.00018433622489039334,
      "loss": 0.6211,
      "step": 468
    },
    {
      "epoch": 1.0509803921568628,
      "grad_norm": 0.29723167419433594,
      "learning_rate": 0.00018423095024414733,
      "loss": 0.6958,
      "step": 469
    },
    {
      "epoch": 1.0532212885154062,
      "grad_norm": 0.27120769023895264,
      "learning_rate": 0.00018412535328311814,
      "loss": 0.8491,
      "step": 470
    },
    {
      "epoch": 1.0554621848739496,
      "grad_norm": 0.28341060876846313,
      "learning_rate": 0.00018401943441137886,
      "loss": 0.65,
      "step": 471
    },
    {
      "epoch": 1.057703081232493,
      "grad_norm": 0.3047507107257843,
      "learning_rate": 0.00018391319403423436,
      "loss": 0.7248,
      "step": 472
    },
    {
      "epoch": 1.0599439775910364,
      "grad_norm": 0.41425445675849915,
      "learning_rate": 0.00018380663255821995,
      "loss": 0.7587,
      "step": 473
    },
    {
      "epoch": 1.0621848739495798,
      "grad_norm": 0.29975569248199463,
      "learning_rate": 0.00018369975039109936,
      "loss": 0.75,
      "step": 474
    },
    {
      "epoch": 1.0644257703081232,
      "grad_norm": 0.2992658317089081,
      "learning_rate": 0.0001835925479418637,
      "loss": 0.7145,
      "step": 475
    },
    {
      "epoch": 1.0666666666666667,
      "grad_norm": 0.29061266779899597,
      "learning_rate": 0.00018348502562072955,
      "loss": 0.7085,
      "step": 476
    },
    {
      "epoch": 1.06890756302521,
      "grad_norm": 0.2972713112831116,
      "learning_rate": 0.00018337718383913752,
      "loss": 0.6741,
      "step": 477
    },
    {
      "epoch": 1.0711484593837535,
      "grad_norm": 0.33825528621673584,
      "learning_rate": 0.0001832690230097506,
      "loss": 0.9284,
      "step": 478
    },
    {
      "epoch": 1.0733893557422969,
      "grad_norm": 0.439996600151062,
      "learning_rate": 0.00018316054354645283,
      "loss": 0.7515,
      "step": 479
    },
    {
      "epoch": 1.0756302521008403,
      "grad_norm": 0.28441861271858215,
      "learning_rate": 0.00018305174586434725,
      "loss": 0.73,
      "step": 480
    },
    {
      "epoch": 1.0778711484593837,
      "grad_norm": 0.26948654651641846,
      "learning_rate": 0.00018294263037975475,
      "loss": 0.6871,
      "step": 481
    },
    {
      "epoch": 1.080112044817927,
      "grad_norm": 0.29222843050956726,
      "learning_rate": 0.00018283319751021232,
      "loss": 0.6827,
      "step": 482
    },
    {
      "epoch": 1.0823529411764705,
      "grad_norm": 0.31007933616638184,
      "learning_rate": 0.00018272344767447134,
      "loss": 0.793,
      "step": 483
    },
    {
      "epoch": 1.084593837535014,
      "grad_norm": 0.29892498254776,
      "learning_rate": 0.0001826133812924962,
      "loss": 0.6541,
      "step": 484
    },
    {
      "epoch": 1.0868347338935573,
      "grad_norm": 0.3294057250022888,
      "learning_rate": 0.00018250299878546245,
      "loss": 0.7719,
      "step": 485
    },
    {
      "epoch": 1.0890756302521007,
      "grad_norm": 0.2897263765335083,
      "learning_rate": 0.00018239230057575542,
      "loss": 0.7306,
      "step": 486
    },
    {
      "epoch": 1.0913165266106442,
      "grad_norm": 0.2852244973182678,
      "learning_rate": 0.00018228128708696844,
      "loss": 0.6512,
      "step": 487
    },
    {
      "epoch": 1.0935574229691878,
      "grad_norm": 0.3132948577404022,
      "learning_rate": 0.00018216995874390128,
      "loss": 0.6859,
      "step": 488
    },
    {
      "epoch": 1.0957983193277312,
      "grad_norm": 0.33552494645118713,
      "learning_rate": 0.0001820583159725585,
      "loss": 0.7039,
      "step": 489
    },
    {
      "epoch": 1.0980392156862746,
      "grad_norm": 0.3188576102256775,
      "learning_rate": 0.0001819463592001479,
      "loss": 0.702,
      "step": 490
    },
    {
      "epoch": 1.100280112044818,
      "grad_norm": 0.3157289922237396,
      "learning_rate": 0.00018183408885507873,
      "loss": 0.706,
      "step": 491
    },
    {
      "epoch": 1.1025210084033614,
      "grad_norm": 0.27868008613586426,
      "learning_rate": 0.00018172150536696025,
      "loss": 0.6802,
      "step": 492
    },
    {
      "epoch": 1.1047619047619048,
      "grad_norm": 0.29156798124313354,
      "learning_rate": 0.0001816086091665999,
      "loss": 0.7465,
      "step": 493
    },
    {
      "epoch": 1.1070028011204482,
      "grad_norm": 0.2826281487941742,
      "learning_rate": 0.00018149540068600182,
      "loss": 0.7023,
      "step": 494
    },
    {
      "epoch": 1.1092436974789917,
      "grad_norm": 0.3162992596626282,
      "learning_rate": 0.00018138188035836497,
      "loss": 0.7039,
      "step": 495
    },
    {
      "epoch": 1.111484593837535,
      "grad_norm": 0.2732091248035431,
      "learning_rate": 0.00018126804861808176,
      "loss": 0.7372,
      "step": 496
    },
    {
      "epoch": 1.1137254901960785,
      "grad_norm": 0.3039727807044983,
      "learning_rate": 0.0001811539059007361,
      "loss": 0.7148,
      "step": 497
    },
    {
      "epoch": 1.1159663865546219,
      "grad_norm": 0.29023319482803345,
      "learning_rate": 0.00018103945264310204,
      "loss": 0.644,
      "step": 498
    },
    {
      "epoch": 1.1182072829131653,
      "grad_norm": 0.2907212972640991,
      "learning_rate": 0.00018092468928314172,
      "loss": 0.7281,
      "step": 499
    },
    {
      "epoch": 1.1204481792717087,
      "grad_norm": 0.2867254912853241,
      "learning_rate": 0.0001808096162600041,
      "loss": 0.7652,
      "step": 500
    },
    {
      "epoch": 1.122689075630252,
      "grad_norm": 0.29929518699645996,
      "learning_rate": 0.000180694234014023,
      "loss": 0.713,
      "step": 501
    },
    {
      "epoch": 1.1249299719887955,
      "grad_norm": 0.3078075647354126,
      "learning_rate": 0.00018057854298671546,
      "loss": 0.7255,
      "step": 502
    },
    {
      "epoch": 1.127170868347339,
      "grad_norm": 0.3214311897754669,
      "learning_rate": 0.0001804625436207802,
      "loss": 0.7369,
      "step": 503
    },
    {
      "epoch": 1.1294117647058823,
      "grad_norm": 0.3541346490383148,
      "learning_rate": 0.00018034623636009568,
      "loss": 0.8864,
      "step": 504
    },
    {
      "epoch": 1.1316526610644257,
      "grad_norm": 0.31777986884117126,
      "learning_rate": 0.00018022962164971867,
      "loss": 0.7382,
      "step": 505
    },
    {
      "epoch": 1.1338935574229692,
      "grad_norm": 0.3204372525215149,
      "learning_rate": 0.00018011269993588232,
      "loss": 0.7998,
      "step": 506
    },
    {
      "epoch": 1.1361344537815126,
      "grad_norm": 0.30363792181015015,
      "learning_rate": 0.0001799954716659946,
      "loss": 0.7145,
      "step": 507
    },
    {
      "epoch": 1.138375350140056,
      "grad_norm": 0.3061518371105194,
      "learning_rate": 0.00017987793728863651,
      "loss": 0.7217,
      "step": 508
    },
    {
      "epoch": 1.1406162464985994,
      "grad_norm": 0.3020443618297577,
      "learning_rate": 0.00017976009725356038,
      "loss": 0.6765,
      "step": 509
    },
    {
      "epoch": 1.1428571428571428,
      "grad_norm": 0.324278861284256,
      "learning_rate": 0.00017964195201168817,
      "loss": 0.8419,
      "step": 510
    },
    {
      "epoch": 1.1450980392156862,
      "grad_norm": 0.3056583106517792,
      "learning_rate": 0.00017952350201510978,
      "loss": 0.8153,
      "step": 511
    },
    {
      "epoch": 1.1473389355742296,
      "grad_norm": 0.3339795470237732,
      "learning_rate": 0.00017940474771708115,
      "loss": 0.8701,
      "step": 512
    },
    {
      "epoch": 1.149579831932773,
      "grad_norm": 0.2845865488052368,
      "learning_rate": 0.00017928568957202278,
      "loss": 0.6865,
      "step": 513
    },
    {
      "epoch": 1.1518207282913164,
      "grad_norm": 0.3049021065235138,
      "learning_rate": 0.0001791663280355178,
      "loss": 0.6772,
      "step": 514
    },
    {
      "epoch": 1.1540616246498598,
      "grad_norm": 0.2814830541610718,
      "learning_rate": 0.00017904666356431028,
      "loss": 0.7092,
      "step": 515
    },
    {
      "epoch": 1.1563025210084033,
      "grad_norm": 0.2870534360408783,
      "learning_rate": 0.0001789266966163035,
      "loss": 0.7056,
      "step": 516
    },
    {
      "epoch": 1.1585434173669467,
      "grad_norm": 0.2947506606578827,
      "learning_rate": 0.00017880642765055816,
      "loss": 0.7208,
      "step": 517
    },
    {
      "epoch": 1.1607843137254903,
      "grad_norm": 0.29607728123664856,
      "learning_rate": 0.00017868585712729068,
      "loss": 0.7441,
      "step": 518
    },
    {
      "epoch": 1.1630252100840337,
      "grad_norm": 0.3445536494255066,
      "learning_rate": 0.00017856498550787144,
      "loss": 0.7116,
      "step": 519
    },
    {
      "epoch": 1.165266106442577,
      "grad_norm": 0.3803198039531708,
      "learning_rate": 0.0001784438132548229,
      "loss": 0.7871,
      "step": 520
    },
    {
      "epoch": 1.1675070028011205,
      "grad_norm": 0.37584301829338074,
      "learning_rate": 0.00017832234083181795,
      "loss": 0.7877,
      "step": 521
    },
    {
      "epoch": 1.169747899159664,
      "grad_norm": 0.3182366192340851,
      "learning_rate": 0.0001782005687036781,
      "loss": 0.7112,
      "step": 522
    },
    {
      "epoch": 1.1719887955182073,
      "grad_norm": 0.3022582530975342,
      "learning_rate": 0.00017807849733637176,
      "loss": 0.7275,
      "step": 523
    },
    {
      "epoch": 1.1742296918767507,
      "grad_norm": 0.31011196970939636,
      "learning_rate": 0.00017795612719701226,
      "loss": 0.7439,
      "step": 524
    },
    {
      "epoch": 1.1764705882352942,
      "grad_norm": 0.30964523553848267,
      "learning_rate": 0.00017783345875385634,
      "loss": 0.7788,
      "step": 525
    },
    {
      "epoch": 1.1787114845938376,
      "grad_norm": 0.29043567180633545,
      "learning_rate": 0.00017771049247630215,
      "loss": 0.7925,
      "step": 526
    },
    {
      "epoch": 1.180952380952381,
      "grad_norm": 0.28265780210494995,
      "learning_rate": 0.00017758722883488745,
      "loss": 0.8563,
      "step": 527
    },
    {
      "epoch": 1.1831932773109244,
      "grad_norm": 0.2864142060279846,
      "learning_rate": 0.00017746366830128803,
      "loss": 0.6427,
      "step": 528
    },
    {
      "epoch": 1.1854341736694678,
      "grad_norm": 0.28759056329727173,
      "learning_rate": 0.00017733981134831567,
      "loss": 0.6629,
      "step": 529
    },
    {
      "epoch": 1.1876750700280112,
      "grad_norm": 0.3355376422405243,
      "learning_rate": 0.00017721565844991643,
      "loss": 0.7418,
      "step": 530
    },
    {
      "epoch": 1.1899159663865546,
      "grad_norm": 0.3486466109752655,
      "learning_rate": 0.0001770912100811688,
      "loss": 0.7885,
      "step": 531
    },
    {
      "epoch": 1.192156862745098,
      "grad_norm": 0.2857566475868225,
      "learning_rate": 0.000176966466718282,
      "loss": 0.6359,
      "step": 532
    },
    {
      "epoch": 1.1943977591036414,
      "grad_norm": 0.3142206072807312,
      "learning_rate": 0.00017684142883859388,
      "loss": 0.6964,
      "step": 533
    },
    {
      "epoch": 1.1966386554621848,
      "grad_norm": 0.3039001524448395,
      "learning_rate": 0.00017671609692056946,
      "loss": 0.6951,
      "step": 534
    },
    {
      "epoch": 1.1988795518207283,
      "grad_norm": 0.31849658489227295,
      "learning_rate": 0.00017659047144379878,
      "loss": 0.7428,
      "step": 535
    },
    {
      "epoch": 1.2011204481792717,
      "grad_norm": 0.2935810983181,
      "learning_rate": 0.00017646455288899534,
      "loss": 0.7668,
      "step": 536
    },
    {
      "epoch": 1.203361344537815,
      "grad_norm": 0.2911589443683624,
      "learning_rate": 0.00017633834173799403,
      "loss": 0.7237,
      "step": 537
    },
    {
      "epoch": 1.2056022408963585,
      "grad_norm": 0.28567075729370117,
      "learning_rate": 0.00017621183847374935,
      "loss": 0.7464,
      "step": 538
    },
    {
      "epoch": 1.2078431372549019,
      "grad_norm": 0.299709677696228,
      "learning_rate": 0.00017608504358033363,
      "loss": 0.7176,
      "step": 539
    },
    {
      "epoch": 1.2100840336134453,
      "grad_norm": 0.2959325313568115,
      "learning_rate": 0.00017595795754293513,
      "loss": 0.6807,
      "step": 540
    },
    {
      "epoch": 1.2123249299719887,
      "grad_norm": 0.27634045481681824,
      "learning_rate": 0.00017583058084785625,
      "loss": 0.6773,
      "step": 541
    },
    {
      "epoch": 1.2145658263305321,
      "grad_norm": 0.33680498600006104,
      "learning_rate": 0.00017570291398251152,
      "loss": 0.7985,
      "step": 542
    },
    {
      "epoch": 1.2168067226890757,
      "grad_norm": 0.318645179271698,
      "learning_rate": 0.00017557495743542585,
      "loss": 0.6376,
      "step": 543
    },
    {
      "epoch": 1.2190476190476192,
      "grad_norm": 0.31514203548431396,
      "learning_rate": 0.0001754467116962326,
      "loss": 0.7327,
      "step": 544
    },
    {
      "epoch": 1.2212885154061626,
      "grad_norm": 0.32726311683654785,
      "learning_rate": 0.0001753181772556719,
      "loss": 0.7329,
      "step": 545
    },
    {
      "epoch": 1.223529411764706,
      "grad_norm": 0.3274557292461395,
      "learning_rate": 0.00017518935460558838,
      "loss": 0.6818,
      "step": 546
    },
    {
      "epoch": 1.2257703081232494,
      "grad_norm": 0.3218080699443817,
      "learning_rate": 0.0001750602442389297,
      "loss": 0.734,
      "step": 547
    },
    {
      "epoch": 1.2280112044817928,
      "grad_norm": 0.3002873659133911,
      "learning_rate": 0.0001749308466497444,
      "loss": 0.617,
      "step": 548
    },
    {
      "epoch": 1.2302521008403362,
      "grad_norm": 0.30696091055870056,
      "learning_rate": 0.00017480116233318014,
      "loss": 0.7417,
      "step": 549
    },
    {
      "epoch": 1.2324929971988796,
      "grad_norm": 0.341802716255188,
      "learning_rate": 0.0001746711917854817,
      "loss": 0.7806,
      "step": 550
    },
    {
      "epoch": 1.234733893557423,
      "grad_norm": 0.3180257976055145,
      "learning_rate": 0.00017454093550398918,
      "loss": 0.6813,
      "step": 551
    },
    {
      "epoch": 1.2369747899159664,
      "grad_norm": 0.3485969007015228,
      "learning_rate": 0.00017441039398713608,
      "loss": 0.7385,
      "step": 552
    },
    {
      "epoch": 1.2392156862745098,
      "grad_norm": 0.3271244466304779,
      "learning_rate": 0.00017427956773444732,
      "loss": 0.6891,
      "step": 553
    },
    {
      "epoch": 1.2414565826330533,
      "grad_norm": 0.31936562061309814,
      "learning_rate": 0.00017414845724653743,
      "loss": 0.683,
      "step": 554
    },
    {
      "epoch": 1.2436974789915967,
      "grad_norm": 0.33722570538520813,
      "learning_rate": 0.0001740170630251085,
      "loss": 0.8026,
      "step": 555
    },
    {
      "epoch": 1.24593837535014,
      "grad_norm": 0.3108736276626587,
      "learning_rate": 0.00017388538557294852,
      "loss": 0.6923,
      "step": 556
    },
    {
      "epoch": 1.2481792717086835,
      "grad_norm": 0.32877469062805176,
      "learning_rate": 0.00017375342539392903,
      "loss": 0.7007,
      "step": 557
    },
    {
      "epoch": 1.250420168067227,
      "grad_norm": 0.3236118257045746,
      "learning_rate": 0.00017362118299300361,
      "loss": 0.6852,
      "step": 558
    },
    {
      "epoch": 1.2526610644257703,
      "grad_norm": 0.30720242857933044,
      "learning_rate": 0.00017348865887620573,
      "loss": 0.6665,
      "step": 559
    },
    {
      "epoch": 1.2549019607843137,
      "grad_norm": 0.32177719473838806,
      "learning_rate": 0.00017335585355064692,
      "loss": 0.7097,
      "step": 560
    },
    {
      "epoch": 1.2571428571428571,
      "grad_norm": 0.31638845801353455,
      "learning_rate": 0.0001732227675245147,
      "loss": 0.6966,
      "step": 561
    },
    {
      "epoch": 1.2593837535014005,
      "grad_norm": 0.3173747956752777,
      "learning_rate": 0.00017308940130707069,
      "loss": 0.6972,
      "step": 562
    },
    {
      "epoch": 1.261624649859944,
      "grad_norm": 0.31755855679512024,
      "learning_rate": 0.00017295575540864877,
      "loss": 0.7192,
      "step": 563
    },
    {
      "epoch": 1.2638655462184873,
      "grad_norm": 0.30816033482551575,
      "learning_rate": 0.00017282183034065296,
      "loss": 0.6723,
      "step": 564
    },
    {
      "epoch": 1.2661064425770308,
      "grad_norm": 0.3106657564640045,
      "learning_rate": 0.00017268762661555557,
      "loss": 0.754,
      "step": 565
    },
    {
      "epoch": 1.2683473389355742,
      "grad_norm": 0.3460423946380615,
      "learning_rate": 0.00017255314474689523,
      "loss": 0.7836,
      "step": 566
    },
    {
      "epoch": 1.2705882352941176,
      "grad_norm": 0.33377137780189514,
      "learning_rate": 0.00017241838524927484,
      "loss": 0.8304,
      "step": 567
    },
    {
      "epoch": 1.272829131652661,
      "grad_norm": 0.3150513470172882,
      "learning_rate": 0.0001722833486383597,
      "loss": 0.9003,
      "step": 568
    },
    {
      "epoch": 1.2750700280112044,
      "grad_norm": 0.2992112934589386,
      "learning_rate": 0.00017214803543087555,
      "loss": 0.7655,
      "step": 569
    },
    {
      "epoch": 1.2773109243697478,
      "grad_norm": 0.2952958345413208,
      "learning_rate": 0.00017201244614460643,
      "loss": 0.6524,
      "step": 570
    },
    {
      "epoch": 1.2795518207282912,
      "grad_norm": 0.31578466296195984,
      "learning_rate": 0.00017187658129839294,
      "loss": 0.7415,
      "step": 571
    },
    {
      "epoch": 1.2817927170868346,
      "grad_norm": 0.33429616689682007,
      "learning_rate": 0.00017174044141213,
      "loss": 0.8142,
      "step": 572
    },
    {
      "epoch": 1.284033613445378,
      "grad_norm": 0.32365548610687256,
      "learning_rate": 0.0001716040270067651,
      "loss": 0.6806,
      "step": 573
    },
    {
      "epoch": 1.2862745098039214,
      "grad_norm": 0.3116409182548523,
      "learning_rate": 0.00017146733860429612,
      "loss": 0.6899,
      "step": 574
    },
    {
      "epoch": 1.2885154061624648,
      "grad_norm": 0.35744285583496094,
      "learning_rate": 0.00017133037672776942,
      "loss": 0.74,
      "step": 575
    },
    {
      "epoch": 1.2907563025210085,
      "grad_norm": 0.2882843613624573,
      "learning_rate": 0.00017119314190127788,
      "loss": 0.6437,
      "step": 576
    },
    {
      "epoch": 1.292997198879552,
      "grad_norm": 0.31813856959342957,
      "learning_rate": 0.00017105563464995873,
      "loss": 0.6738,
      "step": 577
    },
    {
      "epoch": 1.2952380952380953,
      "grad_norm": 0.32429373264312744,
      "learning_rate": 0.00017091785549999176,
      "loss": 0.8131,
      "step": 578
    },
    {
      "epoch": 1.2974789915966387,
      "grad_norm": 0.32878828048706055,
      "learning_rate": 0.00017077980497859713,
      "loss": 0.6904,
      "step": 579
    },
    {
      "epoch": 1.2997198879551821,
      "grad_norm": 0.30764883756637573,
      "learning_rate": 0.00017064148361403347,
      "loss": 0.7343,
      "step": 580
    },
    {
      "epoch": 1.3019607843137255,
      "grad_norm": 0.319346159696579,
      "learning_rate": 0.00017050289193559578,
      "loss": 0.6926,
      "step": 581
    },
    {
      "epoch": 1.304201680672269,
      "grad_norm": 0.31245169043540955,
      "learning_rate": 0.00017036403047361335,
      "loss": 0.7876,
      "step": 582
    },
    {
      "epoch": 1.3064425770308123,
      "grad_norm": 0.29874372482299805,
      "learning_rate": 0.000170224899759448,
      "loss": 0.6569,
      "step": 583
    },
    {
      "epoch": 1.3086834733893558,
      "grad_norm": 0.3087962865829468,
      "learning_rate": 0.00017008550032549167,
      "loss": 0.6892,
      "step": 584
    },
    {
      "epoch": 1.3109243697478992,
      "grad_norm": 0.31366726756095886,
      "learning_rate": 0.0001699458327051647,
      "loss": 0.7782,
      "step": 585
    },
    {
      "epoch": 1.3131652661064426,
      "grad_norm": 0.304023802280426,
      "learning_rate": 0.00016980589743291363,
      "loss": 0.7213,
      "step": 586
    },
    {
      "epoch": 1.315406162464986,
      "grad_norm": 0.2973663806915283,
      "learning_rate": 0.00016966569504420914,
      "loss": 0.6942,
      "step": 587
    },
    {
      "epoch": 1.3176470588235294,
      "grad_norm": 0.3077528178691864,
      "learning_rate": 0.0001695252260755441,
      "loss": 0.7192,
      "step": 588
    },
    {
      "epoch": 1.3198879551820728,
      "grad_norm": 0.3302268087863922,
      "learning_rate": 0.00016938449106443138,
      "loss": 0.7904,
      "step": 589
    },
    {
      "epoch": 1.3221288515406162,
      "grad_norm": 0.3201766312122345,
      "learning_rate": 0.00016924349054940204,
      "loss": 0.6851,
      "step": 590
    },
    {
      "epoch": 1.3243697478991596,
      "grad_norm": 0.31299325823783875,
      "learning_rate": 0.00016910222507000294,
      "loss": 0.6355,
      "step": 591
    },
    {
      "epoch": 1.326610644257703,
      "grad_norm": 0.3279891610145569,
      "learning_rate": 0.00016896069516679493,
      "loss": 0.7587,
      "step": 592
    },
    {
      "epoch": 1.3288515406162464,
      "grad_norm": 0.3423704206943512,
      "learning_rate": 0.0001688189013813507,
      "loss": 0.7352,
      "step": 593
    },
    {
      "epoch": 1.3310924369747898,
      "grad_norm": 0.3414992690086365,
      "learning_rate": 0.00016867684425625262,
      "loss": 0.6362,
      "step": 594
    },
    {
      "epoch": 1.3333333333333333,
      "grad_norm": 0.3365124464035034,
      "learning_rate": 0.00016853452433509086,
      "loss": 0.7817,
      "step": 595
    },
    {
      "epoch": 1.3355742296918767,
      "grad_norm": 0.3402608633041382,
      "learning_rate": 0.00016839194216246108,
      "loss": 0.713,
      "step": 596
    },
    {
      "epoch": 1.3378151260504203,
      "grad_norm": 0.3226512670516968,
      "learning_rate": 0.00016824909828396255,
      "loss": 0.6853,
      "step": 597
    },
    {
      "epoch": 1.3400560224089637,
      "grad_norm": 0.3510406017303467,
      "learning_rate": 0.0001681059932461959,
      "loss": 0.7548,
      "step": 598
    },
    {
      "epoch": 1.3422969187675071,
      "grad_norm": 0.3165980875492096,
      "learning_rate": 0.00016796262759676117,
      "loss": 0.6952,
      "step": 599
    },
    {
      "epoch": 1.3445378151260505,
      "grad_norm": 0.3366287052631378,
      "learning_rate": 0.00016781900188425562,
      "loss": 0.7872,
      "step": 600
    },
    {
      "epoch": 1.346778711484594,
      "grad_norm": 0.30944567918777466,
      "learning_rate": 0.00016767511665827166,
      "loss": 0.6944,
      "step": 601
    },
    {
      "epoch": 1.3490196078431373,
      "grad_norm": 0.31927919387817383,
      "learning_rate": 0.00016753097246939474,
      "loss": 0.6778,
      "step": 602
    },
    {
      "epoch": 1.3512605042016808,
      "grad_norm": 0.36404141783714294,
      "learning_rate": 0.0001673865698692012,
      "loss": 0.8198,
      "step": 603
    },
    {
      "epoch": 1.3535014005602242,
      "grad_norm": 0.28067895770072937,
      "learning_rate": 0.00016724190941025627,
      "loss": 0.6561,
      "step": 604
    },
    {
      "epoch": 1.3557422969187676,
      "grad_norm": 0.33814799785614014,
      "learning_rate": 0.00016709699164611192,
      "loss": 0.725,
      "step": 605
    },
    {
      "epoch": 1.357983193277311,
      "grad_norm": 0.3168368935585022,
      "learning_rate": 0.0001669518171313046,
      "loss": 0.7295,
      "step": 606
    },
    {
      "epoch": 1.3602240896358544,
      "grad_norm": 0.37248319387435913,
      "learning_rate": 0.00016680638642135336,
      "loss": 0.7566,
      "step": 607
    },
    {
      "epoch": 1.3624649859943978,
      "grad_norm": 0.32318514585494995,
      "learning_rate": 0.00016666070007275748,
      "loss": 0.6949,
      "step": 608
    },
    {
      "epoch": 1.3647058823529412,
      "grad_norm": 0.34030449390411377,
      "learning_rate": 0.00016651475864299452,
      "loss": 0.6823,
      "step": 609
    },
    {
      "epoch": 1.3669467787114846,
      "grad_norm": 0.3123067319393158,
      "learning_rate": 0.00016636856269051814,
      "loss": 0.7236,
      "step": 610
    },
    {
      "epoch": 1.369187675070028,
      "grad_norm": 0.32035380601882935,
      "learning_rate": 0.0001662221127747559,
      "loss": 0.7254,
      "step": 611
    },
    {
      "epoch": 1.3714285714285714,
      "grad_norm": 0.3208359181880951,
      "learning_rate": 0.00016607540945610722,
      "loss": 0.7309,
      "step": 612
    },
    {
      "epoch": 1.3736694677871149,
      "grad_norm": 0.31935855746269226,
      "learning_rate": 0.00016592845329594112,
      "loss": 0.8216,
      "step": 613
    },
    {
      "epoch": 1.3759103641456583,
      "grad_norm": 0.2906378209590912,
      "learning_rate": 0.00016578124485659414,
      "loss": 0.7283,
      "step": 614
    },
    {
      "epoch": 1.3781512605042017,
      "grad_norm": 0.3059033751487732,
      "learning_rate": 0.00016563378470136822,
      "loss": 0.7455,
      "step": 615
    },
    {
      "epoch": 1.380392156862745,
      "grad_norm": 0.30803483724594116,
      "learning_rate": 0.00016548607339452853,
      "loss": 0.6463,
      "step": 616
    },
    {
      "epoch": 1.3826330532212885,
      "grad_norm": 0.32379990816116333,
      "learning_rate": 0.00016533811150130117,
      "loss": 0.7454,
      "step": 617
    },
    {
      "epoch": 1.384873949579832,
      "grad_norm": 0.3142244815826416,
      "learning_rate": 0.00016518989958787126,
      "loss": 0.7142,
      "step": 618
    },
    {
      "epoch": 1.3871148459383753,
      "grad_norm": 0.32228538393974304,
      "learning_rate": 0.00016504143822138056,
      "loss": 0.626,
      "step": 619
    },
    {
      "epoch": 1.3893557422969187,
      "grad_norm": 0.3554072082042694,
      "learning_rate": 0.00016489272796992537,
      "loss": 0.6818,
      "step": 620
    },
    {
      "epoch": 1.3915966386554621,
      "grad_norm": 0.3763510584831238,
      "learning_rate": 0.00016474376940255444,
      "loss": 0.7584,
      "step": 621
    },
    {
      "epoch": 1.3938375350140055,
      "grad_norm": 0.3938269317150116,
      "learning_rate": 0.0001645945630892666,
      "loss": 0.815,
      "step": 622
    },
    {
      "epoch": 1.396078431372549,
      "grad_norm": 0.32350701093673706,
      "learning_rate": 0.00016444510960100879,
      "loss": 0.7073,
      "step": 623
    },
    {
      "epoch": 1.3983193277310924,
      "grad_norm": 0.33908578753471375,
      "learning_rate": 0.00016429540950967371,
      "loss": 0.8126,
      "step": 624
    },
    {
      "epoch": 1.4005602240896358,
      "grad_norm": 0.32018956542015076,
      "learning_rate": 0.0001641454633880978,
      "loss": 0.7489,
      "step": 625
    },
    {
      "epoch": 1.4028011204481792,
      "grad_norm": 0.324883371591568,
      "learning_rate": 0.0001639952718100589,
      "loss": 0.7915,
      "step": 626
    },
    {
      "epoch": 1.4050420168067226,
      "grad_norm": 0.3411893844604492,
      "learning_rate": 0.000163844835350274,
      "loss": 0.7736,
      "step": 627
    },
    {
      "epoch": 1.407282913165266,
      "grad_norm": 0.3181053400039673,
      "learning_rate": 0.0001636941545843973,
      "loss": 0.7398,
      "step": 628
    },
    {
      "epoch": 1.4095238095238094,
      "grad_norm": 0.3206365704536438,
      "learning_rate": 0.00016354323008901776,
      "loss": 0.7825,
      "step": 629
    },
    {
      "epoch": 1.4117647058823528,
      "grad_norm": 0.30065983533859253,
      "learning_rate": 0.00016339206244165704,
      "loss": 0.714,
      "step": 630
    },
    {
      "epoch": 1.4140056022408962,
      "grad_norm": 0.3132588565349579,
      "learning_rate": 0.00016324065222076718,
      "loss": 0.8118,
      "step": 631
    },
    {
      "epoch": 1.4162464985994399,
      "grad_norm": 0.3143763840198517,
      "learning_rate": 0.00016308900000572851,
      "loss": 0.7045,
      "step": 632
    },
    {
      "epoch": 1.4184873949579833,
      "grad_norm": 0.3230004608631134,
      "learning_rate": 0.00016293710637684732,
      "loss": 0.5901,
      "step": 633
    },
    {
      "epoch": 1.4207282913165267,
      "grad_norm": 0.31268176436424255,
      "learning_rate": 0.00016278497191535364,
      "loss": 0.7745,
      "step": 634
    },
    {
      "epoch": 1.42296918767507,
      "grad_norm": 0.33265724778175354,
      "learning_rate": 0.00016263259720339916,
      "loss": 0.7444,
      "step": 635
    },
    {
      "epoch": 1.4252100840336135,
      "grad_norm": 0.32188957929611206,
      "learning_rate": 0.00016247998282405485,
      "loss": 0.7899,
      "step": 636
    },
    {
      "epoch": 1.427450980392157,
      "grad_norm": 0.3007752001285553,
      "learning_rate": 0.0001623271293613088,
      "loss": 0.6891,
      "step": 637
    },
    {
      "epoch": 1.4296918767507003,
      "grad_norm": 0.29558807611465454,
      "learning_rate": 0.0001621740374000639,
      "loss": 0.7253,
      "step": 638
    },
    {
      "epoch": 1.4319327731092437,
      "grad_norm": 0.32872480154037476,
      "learning_rate": 0.0001620207075261358,
      "loss": 0.7858,
      "step": 639
    },
    {
      "epoch": 1.4341736694677871,
      "grad_norm": 0.30687081813812256,
      "learning_rate": 0.00016186714032625035,
      "loss": 0.7395,
      "step": 640
    },
    {
      "epoch": 1.4364145658263305,
      "grad_norm": 0.31080397963523865,
      "learning_rate": 0.00016171333638804176,
      "loss": 0.7491,
      "step": 641
    },
    {
      "epoch": 1.438655462184874,
      "grad_norm": 0.3163350820541382,
      "learning_rate": 0.00016155929630004996,
      "loss": 0.7222,
      "step": 642
    },
    {
      "epoch": 1.4408963585434174,
      "grad_norm": 0.3228285610675812,
      "learning_rate": 0.00016140502065171863,
      "loss": 0.722,
      "step": 643
    },
    {
      "epoch": 1.4431372549019608,
      "grad_norm": 0.3150191605091095,
      "learning_rate": 0.00016125051003339276,
      "loss": 0.8325,
      "step": 644
    },
    {
      "epoch": 1.4453781512605042,
      "grad_norm": 0.2988094687461853,
      "learning_rate": 0.00016109576503631646,
      "loss": 0.6268,
      "step": 645
    },
    {
      "epoch": 1.4476190476190476,
      "grad_norm": 0.3043825030326843,
      "learning_rate": 0.00016094078625263083,
      "loss": 0.6615,
      "step": 646
    },
    {
      "epoch": 1.449859943977591,
      "grad_norm": 0.3339695930480957,
      "learning_rate": 0.00016078557427537144,
      "loss": 0.7564,
      "step": 647
    },
    {
      "epoch": 1.4521008403361344,
      "grad_norm": 0.37711572647094727,
      "learning_rate": 0.00016063012969846625,
      "loss": 0.8914,
      "step": 648
    },
    {
      "epoch": 1.4543417366946778,
      "grad_norm": 0.3254697322845459,
      "learning_rate": 0.0001604744531167332,
      "loss": 0.7375,
      "step": 649
    },
    {
      "epoch": 1.4565826330532212,
      "grad_norm": 0.30244678258895874,
      "learning_rate": 0.0001603185451258781,
      "loss": 0.649,
      "step": 650
    },
    {
      "epoch": 1.4588235294117646,
      "grad_norm": 0.3273305892944336,
      "learning_rate": 0.00016016240632249224,
      "loss": 0.7635,
      "step": 651
    },
    {
      "epoch": 1.4610644257703083,
      "grad_norm": 0.3089764714241028,
      "learning_rate": 0.00016000603730405012,
      "loss": 0.7321,
      "step": 652
    },
    {
      "epoch": 1.4633053221288517,
      "grad_norm": 0.3246336579322815,
      "learning_rate": 0.00015984943866890718,
      "loss": 0.7163,
      "step": 653
    },
    {
      "epoch": 1.465546218487395,
      "grad_norm": 0.29445281624794006,
      "learning_rate": 0.00015969261101629742,
      "loss": 0.7109,
      "step": 654
    },
    {
      "epoch": 1.4677871148459385,
      "grad_norm": 0.3255884051322937,
      "learning_rate": 0.00015953555494633136,
      "loss": 0.7698,
      "step": 655
    },
    {
      "epoch": 1.470028011204482,
      "grad_norm": 0.3040069043636322,
      "learning_rate": 0.00015937827105999336,
      "loss": 0.7155,
      "step": 656
    },
    {
      "epoch": 1.4722689075630253,
      "grad_norm": 0.30603310465812683,
      "learning_rate": 0.00015922075995913974,
      "loss": 0.7512,
      "step": 657
    },
    {
      "epoch": 1.4745098039215687,
      "grad_norm": 0.3210160732269287,
      "learning_rate": 0.00015906302224649615,
      "loss": 0.7153,
      "step": 658
    },
    {
      "epoch": 1.4767507002801121,
      "grad_norm": 0.3401980996131897,
      "learning_rate": 0.0001589050585256554,
      "loss": 0.705,
      "step": 659
    },
    {
      "epoch": 1.4789915966386555,
      "grad_norm": 0.3499704599380493,
      "learning_rate": 0.00015874686940107506,
      "loss": 0.7966,
      "step": 660
    },
    {
      "epoch": 1.481232492997199,
      "grad_norm": 0.31771430373191833,
      "learning_rate": 0.00015858845547807543,
      "loss": 0.7383,
      "step": 661
    },
    {
      "epoch": 1.4834733893557424,
      "grad_norm": 0.3159136474132538,
      "learning_rate": 0.00015842981736283686,
      "loss": 0.6415,
      "step": 662
    },
    {
      "epoch": 1.4857142857142858,
      "grad_norm": 0.3231973946094513,
      "learning_rate": 0.0001582709556623976,
      "loss": 0.7462,
      "step": 663
    },
    {
      "epoch": 1.4879551820728292,
      "grad_norm": 0.3222534954547882,
      "learning_rate": 0.0001581118709846514,
      "loss": 0.6833,
      "step": 664
    },
    {
      "epoch": 1.4901960784313726,
      "grad_norm": 0.34087467193603516,
      "learning_rate": 0.00015795256393834545,
      "loss": 0.7325,
      "step": 665
    },
    {
      "epoch": 1.492436974789916,
      "grad_norm": 0.33144867420196533,
      "learning_rate": 0.00015779303513307764,
      "loss": 0.7278,
      "step": 666
    },
    {
      "epoch": 1.4946778711484594,
      "grad_norm": 0.3868750035762787,
      "learning_rate": 0.0001576332851792945,
      "loss": 0.9117,
      "step": 667
    },
    {
      "epoch": 1.4969187675070028,
      "grad_norm": 0.3211595118045807,
      "learning_rate": 0.00015747331468828887,
      "loss": 0.7015,
      "step": 668
    },
    {
      "epoch": 1.4991596638655462,
      "grad_norm": 0.30169111490249634,
      "learning_rate": 0.00015731312427219737,
      "loss": 0.8056,
      "step": 669
    },
    {
      "epoch": 1.5014005602240896,
      "grad_norm": 0.30103328824043274,
      "learning_rate": 0.0001571527145439983,
      "loss": 0.6391,
      "step": 670
    },
    {
      "epoch": 1.503641456582633,
      "grad_norm": 0.3065439462661743,
      "learning_rate": 0.00015699208611750902,
      "loss": 0.7279,
      "step": 671
    },
    {
      "epoch": 1.5058823529411764,
      "grad_norm": 0.3444465100765228,
      "learning_rate": 0.00015683123960738392,
      "loss": 0.7274,
      "step": 672
    },
    {
      "epoch": 1.5081232492997199,
      "grad_norm": 0.3165910542011261,
      "learning_rate": 0.00015667017562911176,
      "loss": 0.6784,
      "step": 673
    },
    {
      "epoch": 1.5103641456582633,
      "grad_norm": 0.3377099335193634,
      "learning_rate": 0.00015650889479901356,
      "loss": 0.8188,
      "step": 674
    },
    {
      "epoch": 1.5126050420168067,
      "grad_norm": 0.3051726818084717,
      "learning_rate": 0.00015634739773424006,
      "loss": 0.657,
      "step": 675
    },
    {
      "epoch": 1.51484593837535,
      "grad_norm": 0.3249804675579071,
      "learning_rate": 0.00015618568505276946,
      "loss": 0.7148,
      "step": 676
    },
    {
      "epoch": 1.5170868347338935,
      "grad_norm": 0.3395232856273651,
      "learning_rate": 0.00015602375737340507,
      "loss": 0.6749,
      "step": 677
    },
    {
      "epoch": 1.519327731092437,
      "grad_norm": 0.33914825320243835,
      "learning_rate": 0.0001558616153157728,
      "loss": 0.7133,
      "step": 678
    },
    {
      "epoch": 1.5215686274509803,
      "grad_norm": 0.3608812689781189,
      "learning_rate": 0.00015569925950031908,
      "loss": 0.7519,
      "step": 679
    },
    {
      "epoch": 1.5238095238095237,
      "grad_norm": 0.37755894660949707,
      "learning_rate": 0.00015553669054830805,
      "loss": 0.757,
      "step": 680
    },
    {
      "epoch": 1.5260504201680671,
      "grad_norm": 0.313101589679718,
      "learning_rate": 0.0001553739090818196,
      "loss": 0.7849,
      "step": 681
    },
    {
      "epoch": 1.5282913165266105,
      "grad_norm": 0.2970316410064697,
      "learning_rate": 0.0001552109157237468,
      "loss": 0.6365,
      "step": 682
    },
    {
      "epoch": 1.530532212885154,
      "grad_norm": 0.3263746201992035,
      "learning_rate": 0.00015504771109779348,
      "loss": 0.6997,
      "step": 683
    },
    {
      "epoch": 1.5327731092436974,
      "grad_norm": 0.3154606521129608,
      "learning_rate": 0.00015488429582847192,
      "loss": 0.7298,
      "step": 684
    },
    {
      "epoch": 1.5350140056022408,
      "grad_norm": 0.3260630965232849,
      "learning_rate": 0.00015472067054110052,
      "loss": 0.7921,
      "step": 685
    },
    {
      "epoch": 1.5372549019607842,
      "grad_norm": 0.32374054193496704,
      "learning_rate": 0.00015455683586180116,
      "loss": 0.718,
      "step": 686
    },
    {
      "epoch": 1.5394957983193276,
      "grad_norm": 0.3299919366836548,
      "learning_rate": 0.00015439279241749715,
      "loss": 0.7179,
      "step": 687
    },
    {
      "epoch": 1.541736694677871,
      "grad_norm": 0.32276657223701477,
      "learning_rate": 0.0001542285408359105,
      "loss": 0.7589,
      "step": 688
    },
    {
      "epoch": 1.5439775910364144,
      "grad_norm": 0.3329083323478699,
      "learning_rate": 0.00015406408174555976,
      "loss": 0.7549,
      "step": 689
    },
    {
      "epoch": 1.5462184873949578,
      "grad_norm": 0.3457712233066559,
      "learning_rate": 0.00015389941577575753,
      "loss": 0.7139,
      "step": 690
    },
    {
      "epoch": 1.5484593837535015,
      "grad_norm": 0.3504430949687958,
      "learning_rate": 0.00015373454355660802,
      "loss": 0.788,
      "step": 691
    },
    {
      "epoch": 1.5507002801120449,
      "grad_norm": 0.3265605866909027,
      "learning_rate": 0.00015356946571900464,
      "loss": 0.7077,
      "step": 692
    },
    {
      "epoch": 1.5529411764705883,
      "grad_norm": 0.3154314458370209,
      "learning_rate": 0.00015340418289462764,
      "loss": 0.7,
      "step": 693
    },
    {
      "epoch": 1.5551820728291317,
      "grad_norm": 0.3218802511692047,
      "learning_rate": 0.00015323869571594166,
      "loss": 0.7735,
      "step": 694
    },
    {
      "epoch": 1.557422969187675,
      "grad_norm": 0.31704089045524597,
      "learning_rate": 0.00015307300481619333,
      "loss": 0.7946,
      "step": 695
    },
    {
      "epoch": 1.5596638655462185,
      "grad_norm": 0.3201853632926941,
      "learning_rate": 0.0001529071108294088,
      "loss": 0.7154,
      "step": 696
    },
    {
      "epoch": 1.561904761904762,
      "grad_norm": 0.3154377341270447,
      "learning_rate": 0.00015274101439039138,
      "loss": 0.6905,
      "step": 697
    },
    {
      "epoch": 1.5641456582633053,
      "grad_norm": 0.30675947666168213,
      "learning_rate": 0.00015257471613471906,
      "loss": 0.6897,
      "step": 698
    },
    {
      "epoch": 1.5663865546218487,
      "grad_norm": 0.30410274863243103,
      "learning_rate": 0.00015240821669874202,
      "loss": 0.7181,
      "step": 699
    },
    {
      "epoch": 1.5686274509803921,
      "grad_norm": 0.3099222779273987,
      "learning_rate": 0.00015224151671958043,
      "loss": 0.732,
      "step": 700
    },
    {
      "epoch": 1.5708683473389355,
      "grad_norm": 0.32526805996894836,
      "learning_rate": 0.00015207461683512175,
      "loss": 0.7442,
      "step": 701
    },
    {
      "epoch": 1.573109243697479,
      "grad_norm": 0.3597675859928131,
      "learning_rate": 0.00015190751768401833,
      "loss": 0.7059,
      "step": 702
    },
    {
      "epoch": 1.5753501400560224,
      "grad_norm": 0.34002843499183655,
      "learning_rate": 0.00015174021990568517,
      "loss": 0.7309,
      "step": 703
    },
    {
      "epoch": 1.5775910364145658,
      "grad_norm": 0.3448459804058075,
      "learning_rate": 0.0001515727241402972,
      "loss": 0.7543,
      "step": 704
    },
    {
      "epoch": 1.5798319327731094,
      "grad_norm": 0.3388139605522156,
      "learning_rate": 0.000151405031028787,
      "loss": 0.6604,
      "step": 705
    },
    {
      "epoch": 1.5820728291316528,
      "grad_norm": 0.33875682950019836,
      "learning_rate": 0.0001512371412128424,
      "loss": 0.7234,
      "step": 706
    },
    {
      "epoch": 1.5843137254901962,
      "grad_norm": 0.3654973804950714,
      "learning_rate": 0.00015106905533490372,
      "loss": 0.8452,
      "step": 707
    },
    {
      "epoch": 1.5865546218487396,
      "grad_norm": 0.31986573338508606,
      "learning_rate": 0.00015090077403816178,
      "loss": 0.6683,
      "step": 708
    },
    {
      "epoch": 1.588795518207283,
      "grad_norm": 0.29579469561576843,
      "learning_rate": 0.00015073229796655504,
      "loss": 0.723,
      "step": 709
    },
    {
      "epoch": 1.5910364145658265,
      "grad_norm": 0.31319934129714966,
      "learning_rate": 0.0001505636277647672,
      "loss": 0.7384,
      "step": 710
    },
    {
      "epoch": 1.5932773109243699,
      "grad_norm": 0.30319178104400635,
      "learning_rate": 0.00015039476407822502,
      "loss": 0.7044,
      "step": 711
    },
    {
      "epoch": 1.5955182072829133,
      "grad_norm": 0.3266353905200958,
      "learning_rate": 0.0001502257075530954,
      "loss": 0.7777,
      "step": 712
    },
    {
      "epoch": 1.5977591036414567,
      "grad_norm": 0.3113664388656616,
      "learning_rate": 0.00015005645883628342,
      "loss": 0.7394,
      "step": 713
    },
    {
      "epoch": 1.6,
      "grad_norm": 0.29923635721206665,
      "learning_rate": 0.00014988701857542933,
      "loss": 0.6867,
      "step": 714
    },
    {
      "epoch": 1.6022408963585435,
      "grad_norm": 0.32305604219436646,
      "learning_rate": 0.00014971738741890647,
      "loss": 0.7512,
      "step": 715
    },
    {
      "epoch": 1.604481792717087,
      "grad_norm": 0.30608245730400085,
      "learning_rate": 0.0001495475660158187,
      "loss": 0.7076,
      "step": 716
    },
    {
      "epoch": 1.6067226890756303,
      "grad_norm": 0.3273196220397949,
      "learning_rate": 0.00014937755501599772,
      "loss": 0.7259,
      "step": 717
    },
    {
      "epoch": 1.6089635854341737,
      "grad_norm": 0.3238683342933655,
      "learning_rate": 0.0001492073550700009,
      "loss": 0.716,
      "step": 718
    },
    {
      "epoch": 1.6112044817927171,
      "grad_norm": 0.3258748948574066,
      "learning_rate": 0.00014903696682910846,
      "loss": 0.739,
      "step": 719
    },
    {
      "epoch": 1.6134453781512605,
      "grad_norm": 0.32485276460647583,
      "learning_rate": 0.00014886639094532128,
      "loss": 0.681,
      "step": 720
    },
    {
      "epoch": 1.615686274509804,
      "grad_norm": 0.3358374536037445,
      "learning_rate": 0.0001486956280713582,
      "loss": 0.7625,
      "step": 721
    },
    {
      "epoch": 1.6179271708683474,
      "grad_norm": 0.30938801169395447,
      "learning_rate": 0.00014852467886065357,
      "loss": 0.6942,
      "step": 722
    },
    {
      "epoch": 1.6201680672268908,
      "grad_norm": 0.35836121439933777,
      "learning_rate": 0.00014835354396735482,
      "loss": 0.7397,
      "step": 723
    },
    {
      "epoch": 1.6224089635854342,
      "grad_norm": 0.3162292540073395,
      "learning_rate": 0.00014818222404631992,
      "loss": 0.7071,
      "step": 724
    },
    {
      "epoch": 1.6246498599439776,
      "grad_norm": 0.32497039437294006,
      "learning_rate": 0.0001480107197531148,
      "loss": 0.7396,
      "step": 725
    },
    {
      "epoch": 1.626890756302521,
      "grad_norm": 0.33408358693122864,
      "learning_rate": 0.00014783903174401085,
      "loss": 0.7593,
      "step": 726
    },
    {
      "epoch": 1.6291316526610644,
      "grad_norm": 0.3246319591999054,
      "learning_rate": 0.00014766716067598262,
      "loss": 0.7302,
      "step": 727
    },
    {
      "epoch": 1.6313725490196078,
      "grad_norm": 0.32565364241600037,
      "learning_rate": 0.00014749510720670506,
      "loss": 0.8113,
      "step": 728
    },
    {
      "epoch": 1.6336134453781512,
      "grad_norm": 0.32790714502334595,
      "learning_rate": 0.00014732287199455103,
      "loss": 0.7884,
      "step": 729
    },
    {
      "epoch": 1.6358543417366946,
      "grad_norm": 0.3148501217365265,
      "learning_rate": 0.00014715045569858894,
      "loss": 0.7214,
      "step": 730
    },
    {
      "epoch": 1.638095238095238,
      "grad_norm": 0.30682241916656494,
      "learning_rate": 0.00014697785897858012,
      "loss": 0.725,
      "step": 731
    },
    {
      "epoch": 1.6403361344537815,
      "grad_norm": 0.3391934037208557,
      "learning_rate": 0.00014680508249497622,
      "loss": 0.84,
      "step": 732
    },
    {
      "epoch": 1.6425770308123249,
      "grad_norm": 0.31384411454200745,
      "learning_rate": 0.0001466321269089168,
      "loss": 0.6867,
      "step": 733
    },
    {
      "epoch": 1.6448179271708683,
      "grad_norm": 0.33052271604537964,
      "learning_rate": 0.00014645899288222687,
      "loss": 0.7761,
      "step": 734
    },
    {
      "epoch": 1.6470588235294117,
      "grad_norm": 0.3304360806941986,
      "learning_rate": 0.00014628568107741407,
      "loss": 0.8817,
      "step": 735
    },
    {
      "epoch": 1.649299719887955,
      "grad_norm": 0.34404993057250977,
      "learning_rate": 0.0001461121921576665,
      "loss": 0.8155,
      "step": 736
    },
    {
      "epoch": 1.6515406162464985,
      "grad_norm": 0.33394402265548706,
      "learning_rate": 0.00014593852678684984,
      "loss": 0.7656,
      "step": 737
    },
    {
      "epoch": 1.653781512605042,
      "grad_norm": 0.35093650221824646,
      "learning_rate": 0.0001457646856295051,
      "loss": 0.8171,
      "step": 738
    },
    {
      "epoch": 1.6560224089635853,
      "grad_norm": 0.31678837537765503,
      "learning_rate": 0.00014559066935084588,
      "loss": 0.7061,
      "step": 739
    },
    {
      "epoch": 1.6582633053221287,
      "grad_norm": 0.3170653283596039,
      "learning_rate": 0.00014541647861675592,
      "loss": 0.7351,
      "step": 740
    },
    {
      "epoch": 1.6605042016806721,
      "grad_norm": 0.34166768193244934,
      "learning_rate": 0.0001452421140937865,
      "loss": 0.7937,
      "step": 741
    },
    {
      "epoch": 1.6627450980392156,
      "grad_norm": 0.3269054591655731,
      "learning_rate": 0.00014506757644915393,
      "loss": 0.8038,
      "step": 742
    },
    {
      "epoch": 1.664985994397759,
      "grad_norm": 0.3237577974796295,
      "learning_rate": 0.00014489286635073693,
      "loss": 0.657,
      "step": 743
    },
    {
      "epoch": 1.6672268907563024,
      "grad_norm": 0.3239234685897827,
      "learning_rate": 0.00014471798446707426,
      "loss": 0.6732,
      "step": 744
    },
    {
      "epoch": 1.6694677871148458,
      "grad_norm": 0.30346667766571045,
      "learning_rate": 0.00014454293146736187,
      "loss": 0.669,
      "step": 745
    },
    {
      "epoch": 1.6717086834733892,
      "grad_norm": 0.32579341530799866,
      "learning_rate": 0.00014436770802145059,
      "loss": 0.6693,
      "step": 746
    },
    {
      "epoch": 1.6739495798319328,
      "grad_norm": 0.34438079595565796,
      "learning_rate": 0.0001441923147998434,
      "loss": 0.8594,
      "step": 747
    },
    {
      "epoch": 1.6761904761904762,
      "grad_norm": 0.3287278115749359,
      "learning_rate": 0.00014401675247369307,
      "loss": 0.7633,
      "step": 748
    },
    {
      "epoch": 1.6784313725490196,
      "grad_norm": 0.34410589933395386,
      "learning_rate": 0.0001438410217147993,
      "loss": 0.7815,
      "step": 749
    },
    {
      "epoch": 1.680672268907563,
      "grad_norm": 0.4113364815711975,
      "learning_rate": 0.0001436651231956064,
      "loss": 0.7617,
      "step": 750
    },
    {
      "epoch": 1.6829131652661065,
      "grad_norm": 0.3100757598876953,
      "learning_rate": 0.0001434890575892006,
      "loss": 0.673,
      "step": 751
    },
    {
      "epoch": 1.6851540616246499,
      "grad_norm": 0.32215428352355957,
      "learning_rate": 0.0001433128255693075,
      "loss": 0.7694,
      "step": 752
    },
    {
      "epoch": 1.6873949579831933,
      "grad_norm": 0.3526766002178192,
      "learning_rate": 0.00014313642781028953,
      "loss": 0.7397,
      "step": 753
    },
    {
      "epoch": 1.6896358543417367,
      "grad_norm": 0.3373475968837738,
      "learning_rate": 0.00014295986498714326,
      "loss": 0.8275,
      "step": 754
    },
    {
      "epoch": 1.69187675070028,
      "grad_norm": 0.32114461064338684,
      "learning_rate": 0.0001427831377754969,
      "loss": 0.7225,
      "step": 755
    },
    {
      "epoch": 1.6941176470588235,
      "grad_norm": 0.320982426404953,
      "learning_rate": 0.00014260624685160777,
      "loss": 0.7966,
      "step": 756
    },
    {
      "epoch": 1.696358543417367,
      "grad_norm": 0.28297820687294006,
      "learning_rate": 0.0001424291928923596,
      "loss": 0.6789,
      "step": 757
    },
    {
      "epoch": 1.6985994397759103,
      "grad_norm": 0.31439271569252014,
      "learning_rate": 0.00014225197657525995,
      "loss": 0.7194,
      "step": 758
    },
    {
      "epoch": 1.7008403361344537,
      "grad_norm": 0.33543679118156433,
      "learning_rate": 0.0001420745985784377,
      "loss": 0.8552,
      "step": 759
    },
    {
      "epoch": 1.7030812324929971,
      "grad_norm": 0.33300474286079407,
      "learning_rate": 0.0001418970595806404,
      "loss": 0.867,
      "step": 760
    },
    {
      "epoch": 1.7053221288515408,
      "grad_norm": 0.3134838938713074,
      "learning_rate": 0.00014171936026123168,
      "loss": 0.6651,
      "step": 761
    },
    {
      "epoch": 1.7075630252100842,
      "grad_norm": 0.32312485575675964,
      "learning_rate": 0.00014154150130018866,
      "loss": 0.7978,
      "step": 762
    },
    {
      "epoch": 1.7098039215686276,
      "grad_norm": 0.3270231783390045,
      "learning_rate": 0.00014136348337809927,
      "loss": 0.7574,
      "step": 763
    },
    {
      "epoch": 1.712044817927171,
      "grad_norm": 0.32470935583114624,
      "learning_rate": 0.0001411853071761598,
      "loss": 0.6881,
      "step": 764
    },
    {
      "epoch": 1.7142857142857144,
      "grad_norm": 0.3110044300556183,
      "learning_rate": 0.00014100697337617217,
      "loss": 0.6684,
      "step": 765
    },
    {
      "epoch": 1.7165266106442578,
      "grad_norm": 0.344539076089859,
      "learning_rate": 0.00014082848266054135,
      "loss": 0.7387,
      "step": 766
    },
    {
      "epoch": 1.7187675070028012,
      "grad_norm": 0.3174740672111511,
      "learning_rate": 0.0001406498357122728,
      "loss": 0.6459,
      "step": 767
    },
    {
      "epoch": 1.7210084033613446,
      "grad_norm": 0.339348167181015,
      "learning_rate": 0.00014047103321496976,
      "loss": 0.658,
      "step": 768
    },
    {
      "epoch": 1.723249299719888,
      "grad_norm": 0.3239974081516266,
      "learning_rate": 0.0001402920758528307,
      "loss": 0.6356,
      "step": 769
    },
    {
      "epoch": 1.7254901960784315,
      "grad_norm": 0.33558371663093567,
      "learning_rate": 0.00014011296431064676,
      "loss": 0.7531,
      "step": 770
    },
    {
      "epoch": 1.7277310924369749,
      "grad_norm": 0.35468053817749023,
      "learning_rate": 0.0001399336992737989,
      "loss": 0.783,
      "step": 771
    },
    {
      "epoch": 1.7299719887955183,
      "grad_norm": 0.34820565581321716,
      "learning_rate": 0.0001397542814282556,
      "loss": 0.7227,
      "step": 772
    },
    {
      "epoch": 1.7322128851540617,
      "grad_norm": 0.3655050992965698,
      "learning_rate": 0.00013957471146056998,
      "loss": 0.7366,
      "step": 773
    },
    {
      "epoch": 1.734453781512605,
      "grad_norm": 0.3187251389026642,
      "learning_rate": 0.00013939499005787736,
      "loss": 0.7304,
      "step": 774
    },
    {
      "epoch": 1.7366946778711485,
      "grad_norm": 0.3165695071220398,
      "learning_rate": 0.00013921511790789234,
      "loss": 0.7757,
      "step": 775
    },
    {
      "epoch": 1.738935574229692,
      "grad_norm": 0.3043893873691559,
      "learning_rate": 0.00013903509569890662,
      "loss": 0.7689,
      "step": 776
    },
    {
      "epoch": 1.7411764705882353,
      "grad_norm": 0.30263444781303406,
      "learning_rate": 0.0001388549241197859,
      "loss": 0.6638,
      "step": 777
    },
    {
      "epoch": 1.7434173669467787,
      "grad_norm": 0.3344278931617737,
      "learning_rate": 0.00013867460385996754,
      "loss": 0.7027,
      "step": 778
    },
    {
      "epoch": 1.7456582633053221,
      "grad_norm": 0.309756338596344,
      "learning_rate": 0.00013849413560945787,
      "loss": 0.7662,
      "step": 779
    },
    {
      "epoch": 1.7478991596638656,
      "grad_norm": 0.33109283447265625,
      "learning_rate": 0.00013831352005882946,
      "loss": 0.7888,
      "step": 780
    },
    {
      "epoch": 1.750140056022409,
      "grad_norm": 0.32347214221954346,
      "learning_rate": 0.00013813275789921855,
      "loss": 0.7313,
      "step": 781
    },
    {
      "epoch": 1.7523809523809524,
      "grad_norm": 0.3274037539958954,
      "learning_rate": 0.00013795184982232233,
      "loss": 0.779,
      "step": 782
    },
    {
      "epoch": 1.7546218487394958,
      "grad_norm": 0.3241097927093506,
      "learning_rate": 0.0001377707965203965,
      "loss": 0.744,
      "step": 783
    },
    {
      "epoch": 1.7568627450980392,
      "grad_norm": 0.32738566398620605,
      "learning_rate": 0.00013758959868625232,
      "loss": 0.7585,
      "step": 784
    },
    {
      "epoch": 1.7591036414565826,
      "grad_norm": 0.3516925275325775,
      "learning_rate": 0.00013740825701325418,
      "loss": 0.7445,
      "step": 785
    },
    {
      "epoch": 1.761344537815126,
      "grad_norm": 0.33777570724487305,
      "learning_rate": 0.00013722677219531683,
      "loss": 0.7038,
      "step": 786
    },
    {
      "epoch": 1.7635854341736694,
      "grad_norm": 0.35104092955589294,
      "learning_rate": 0.0001370451449269029,
      "loss": 0.7527,
      "step": 787
    },
    {
      "epoch": 1.7658263305322128,
      "grad_norm": 0.33028444647789,
      "learning_rate": 0.00013686337590301995,
      "loss": 0.7227,
      "step": 788
    },
    {
      "epoch": 1.7680672268907562,
      "grad_norm": 0.3553149104118347,
      "learning_rate": 0.0001366814658192181,
      "loss": 0.6937,
      "step": 789
    },
    {
      "epoch": 1.7703081232492996,
      "grad_norm": 0.32514214515686035,
      "learning_rate": 0.0001364994153715872,
      "loss": 0.7198,
      "step": 790
    },
    {
      "epoch": 1.772549019607843,
      "grad_norm": 0.3584795892238617,
      "learning_rate": 0.00013631722525675412,
      "loss": 0.8049,
      "step": 791
    },
    {
      "epoch": 1.7747899159663865,
      "grad_norm": 0.3179537057876587,
      "learning_rate": 0.0001361348961718804,
      "loss": 0.7795,
      "step": 792
    },
    {
      "epoch": 1.7770308123249299,
      "grad_norm": 0.2919451594352722,
      "learning_rate": 0.0001359524288146591,
      "loss": 0.6553,
      "step": 793
    },
    {
      "epoch": 1.7792717086834733,
      "grad_norm": 0.31730496883392334,
      "learning_rate": 0.0001357698238833126,
      "loss": 0.812,
      "step": 794
    },
    {
      "epoch": 1.7815126050420167,
      "grad_norm": 0.31148526072502136,
      "learning_rate": 0.00013558708207658948,
      "loss": 0.6558,
      "step": 795
    },
    {
      "epoch": 1.78375350140056,
      "grad_norm": 0.3431221544742584,
      "learning_rate": 0.00013540420409376236,
      "loss": 0.766,
      "step": 796
    },
    {
      "epoch": 1.7859943977591035,
      "grad_norm": 0.32656344771385193,
      "learning_rate": 0.00013522119063462482,
      "loss": 0.744,
      "step": 797
    },
    {
      "epoch": 1.788235294117647,
      "grad_norm": 0.3525942862033844,
      "learning_rate": 0.00013503804239948874,
      "loss": 0.7954,
      "step": 798
    },
    {
      "epoch": 1.7904761904761903,
      "grad_norm": 0.3282519280910492,
      "learning_rate": 0.00013485476008918184,
      "loss": 0.72,
      "step": 799
    },
    {
      "epoch": 1.7927170868347337,
      "grad_norm": 0.3348991870880127,
      "learning_rate": 0.00013467134440504495,
      "loss": 0.6925,
      "step": 800
    },
    {
      "epoch": 1.7949579831932772,
      "grad_norm": 0.325764000415802,
      "learning_rate": 0.00013448779604892917,
      "loss": 0.7261,
      "step": 801
    },
    {
      "epoch": 1.7971988795518208,
      "grad_norm": 0.33784714341163635,
      "learning_rate": 0.00013430411572319323,
      "loss": 0.7637,
      "step": 802
    },
    {
      "epoch": 1.7994397759103642,
      "grad_norm": 0.31615525484085083,
      "learning_rate": 0.00013412030413070095,
      "loss": 0.649,
      "step": 803
    },
    {
      "epoch": 1.8016806722689076,
      "grad_norm": 0.30358991026878357,
      "learning_rate": 0.00013393636197481842,
      "loss": 0.6566,
      "step": 804
    },
    {
      "epoch": 1.803921568627451,
      "grad_norm": 0.3021032512187958,
      "learning_rate": 0.00013375228995941133,
      "loss": 0.7694,
      "step": 805
    },
    {
      "epoch": 1.8061624649859944,
      "grad_norm": 0.3464861810207367,
      "learning_rate": 0.00013356808878884228,
      "loss": 0.7604,
      "step": 806
    },
    {
      "epoch": 1.8084033613445378,
      "grad_norm": 0.3448963165283203,
      "learning_rate": 0.00013338375916796812,
      "loss": 0.7434,
      "step": 807
    },
    {
      "epoch": 1.8106442577030812,
      "grad_norm": 0.3179613947868347,
      "learning_rate": 0.00013319930180213712,
      "loss": 0.6885,
      "step": 808
    },
    {
      "epoch": 1.8128851540616246,
      "grad_norm": 0.31533604860305786,
      "learning_rate": 0.0001330147173971866,
      "loss": 0.6736,
      "step": 809
    },
    {
      "epoch": 1.815126050420168,
      "grad_norm": 0.3316449224948883,
      "learning_rate": 0.00013283000665943972,
      "loss": 0.7354,
      "step": 810
    },
    {
      "epoch": 1.8173669467787115,
      "grad_norm": 0.3497374951839447,
      "learning_rate": 0.00013264517029570324,
      "loss": 0.7956,
      "step": 811
    },
    {
      "epoch": 1.8196078431372549,
      "grad_norm": 0.33198150992393494,
      "learning_rate": 0.00013246020901326464,
      "loss": 0.7105,
      "step": 812
    },
    {
      "epoch": 1.8218487394957983,
      "grad_norm": 0.3188040554523468,
      "learning_rate": 0.00013227512351988925,
      "loss": 0.7141,
      "step": 813
    },
    {
      "epoch": 1.8240896358543417,
      "grad_norm": 0.30372536182403564,
      "learning_rate": 0.00013208991452381798,
      "loss": 0.7223,
      "step": 814
    },
    {
      "epoch": 1.826330532212885,
      "grad_norm": 0.6289974451065063,
      "learning_rate": 0.00013190458273376404,
      "loss": 0.7972,
      "step": 815
    },
    {
      "epoch": 1.8285714285714287,
      "grad_norm": 0.3201170563697815,
      "learning_rate": 0.00013171912885891063,
      "loss": 0.7433,
      "step": 816
    },
    {
      "epoch": 1.8308123249299721,
      "grad_norm": 0.35013505816459656,
      "learning_rate": 0.00013153355360890815,
      "loss": 0.7361,
      "step": 817
    },
    {
      "epoch": 1.8330532212885156,
      "grad_norm": 0.34328508377075195,
      "learning_rate": 0.00013134785769387147,
      "loss": 0.7031,
      "step": 818
    },
    {
      "epoch": 1.835294117647059,
      "grad_norm": 0.3286396265029907,
      "learning_rate": 0.0001311620418243771,
      "loss": 0.7657,
      "step": 819
    },
    {
      "epoch": 1.8375350140056024,
      "grad_norm": 0.3106536567211151,
      "learning_rate": 0.00013097610671146065,
      "loss": 0.7554,
      "step": 820
    },
    {
      "epoch": 1.8397759103641458,
      "grad_norm": 0.3301306366920471,
      "learning_rate": 0.0001307900530666139,
      "loss": 0.7126,
      "step": 821
    },
    {
      "epoch": 1.8420168067226892,
      "grad_norm": 0.34890398383140564,
      "learning_rate": 0.00013060388160178235,
      "loss": 0.7953,
      "step": 822
    },
    {
      "epoch": 1.8442577030812326,
      "grad_norm": 0.31672972440719604,
      "learning_rate": 0.0001304175930293623,
      "loss": 0.7359,
      "step": 823
    },
    {
      "epoch": 1.846498599439776,
      "grad_norm": 0.3178110122680664,
      "learning_rate": 0.0001302311880621981,
      "loss": 0.7662,
      "step": 824
    },
    {
      "epoch": 1.8487394957983194,
      "grad_norm": 0.35035309195518494,
      "learning_rate": 0.0001300446674135795,
      "loss": 0.7105,
      "step": 825
    },
    {
      "epoch": 1.8509803921568628,
      "grad_norm": 0.3116212785243988,
      "learning_rate": 0.00012985803179723903,
      "loss": 0.7424,
      "step": 826
    },
    {
      "epoch": 1.8532212885154062,
      "grad_norm": 0.34882014989852905,
      "learning_rate": 0.00012967128192734902,
      "loss": 0.7574,
      "step": 827
    },
    {
      "epoch": 1.8554621848739496,
      "grad_norm": 0.31585201621055603,
      "learning_rate": 0.0001294844185185191,
      "loss": 0.805,
      "step": 828
    },
    {
      "epoch": 1.857703081232493,
      "grad_norm": 0.314979612827301,
      "learning_rate": 0.00012929744228579323,
      "loss": 0.5924,
      "step": 829
    },
    {
      "epoch": 1.8599439775910365,
      "grad_norm": 0.3267279863357544,
      "learning_rate": 0.00012911035394464723,
      "loss": 0.763,
      "step": 830
    },
    {
      "epoch": 1.8621848739495799,
      "grad_norm": 0.3523454964160919,
      "learning_rate": 0.00012892315421098586,
      "loss": 0.8221,
      "step": 831
    },
    {
      "epoch": 1.8644257703081233,
      "grad_norm": 0.31915390491485596,
      "learning_rate": 0.00012873584380114012,
      "loss": 0.8081,
      "step": 832
    },
    {
      "epoch": 1.8666666666666667,
      "grad_norm": 0.32959550619125366,
      "learning_rate": 0.00012854842343186455,
      "loss": 0.7208,
      "step": 833
    },
    {
      "epoch": 1.86890756302521,
      "grad_norm": 0.32218843698501587,
      "learning_rate": 0.0001283608938203344,
      "loss": 0.7514,
      "step": 834
    },
    {
      "epoch": 1.8711484593837535,
      "grad_norm": 0.3358590602874756,
      "learning_rate": 0.00012817325568414297,
      "loss": 0.7401,
      "step": 835
    },
    {
      "epoch": 1.873389355742297,
      "grad_norm": 0.3331390917301178,
      "learning_rate": 0.00012798550974129887,
      "loss": 0.6833,
      "step": 836
    },
    {
      "epoch": 1.8756302521008403,
      "grad_norm": 0.33320388197898865,
      "learning_rate": 0.00012779765671022325,
      "loss": 0.6287,
      "step": 837
    },
    {
      "epoch": 1.8778711484593837,
      "grad_norm": 0.3285226821899414,
      "learning_rate": 0.00012760969730974694,
      "loss": 0.6698,
      "step": 838
    },
    {
      "epoch": 1.8801120448179272,
      "grad_norm": 0.3503000736236572,
      "learning_rate": 0.0001274216322591078,
      "loss": 0.6997,
      "step": 839
    },
    {
      "epoch": 1.8823529411764706,
      "grad_norm": 0.35233861207962036,
      "learning_rate": 0.00012723346227794816,
      "loss": 0.7241,
      "step": 840
    },
    {
      "epoch": 1.884593837535014,
      "grad_norm": 0.3368009924888611,
      "learning_rate": 0.00012704518808631166,
      "loss": 0.7379,
      "step": 841
    },
    {
      "epoch": 1.8868347338935574,
      "grad_norm": 0.3214666247367859,
      "learning_rate": 0.0001268568104046408,
      "loss": 0.6946,
      "step": 842
    },
    {
      "epoch": 1.8890756302521008,
      "grad_norm": 0.3163416385650635,
      "learning_rate": 0.0001266683299537741,
      "loss": 0.7044,
      "step": 843
    },
    {
      "epoch": 1.8913165266106442,
      "grad_norm": 0.3129757046699524,
      "learning_rate": 0.0001264797474549433,
      "loss": 0.6105,
      "step": 844
    },
    {
      "epoch": 1.8935574229691876,
      "grad_norm": 0.35761409997940063,
      "learning_rate": 0.00012629106362977064,
      "loss": 0.8279,
      "step": 845
    },
    {
      "epoch": 1.895798319327731,
      "grad_norm": 0.3365795314311981,
      "learning_rate": 0.00012610227920026608,
      "loss": 0.6859,
      "step": 846
    },
    {
      "epoch": 1.8980392156862744,
      "grad_norm": 0.3187201917171478,
      "learning_rate": 0.00012591339488882456,
      "loss": 0.6907,
      "step": 847
    },
    {
      "epoch": 1.9002801120448178,
      "grad_norm": 0.31638118624687195,
      "learning_rate": 0.0001257244114182232,
      "loss": 0.7243,
      "step": 848
    },
    {
      "epoch": 1.9025210084033612,
      "grad_norm": 0.34840863943099976,
      "learning_rate": 0.0001255353295116187,
      "loss": 0.687,
      "step": 849
    },
    {
      "epoch": 1.9047619047619047,
      "grad_norm": 0.3138674199581146,
      "learning_rate": 0.00012534614989254423,
      "loss": 0.7198,
      "step": 850
    },
    {
      "epoch": 1.907002801120448,
      "grad_norm": 0.362076997756958,
      "learning_rate": 0.00012515687328490695,
      "loss": 0.7757,
      "step": 851
    },
    {
      "epoch": 1.9092436974789915,
      "grad_norm": 0.32191118597984314,
      "learning_rate": 0.00012496750041298516,
      "loss": 0.7103,
      "step": 852
    },
    {
      "epoch": 1.9114845938375349,
      "grad_norm": 0.3364141583442688,
      "learning_rate": 0.0001247780320014255,
      "loss": 0.7509,
      "step": 853
    },
    {
      "epoch": 1.9137254901960783,
      "grad_norm": 0.35079094767570496,
      "learning_rate": 0.00012458846877524024,
      "loss": 0.6844,
      "step": 854
    },
    {
      "epoch": 1.9159663865546217,
      "grad_norm": 0.33669090270996094,
      "learning_rate": 0.00012439881145980444,
      "loss": 0.6801,
      "step": 855
    },
    {
      "epoch": 1.9182072829131651,
      "grad_norm": 0.31381383538246155,
      "learning_rate": 0.00012420906078085316,
      "loss": 0.6341,
      "step": 856
    },
    {
      "epoch": 1.9204481792717085,
      "grad_norm": 0.3355211615562439,
      "learning_rate": 0.00012401921746447872,
      "loss": 0.7244,
      "step": 857
    },
    {
      "epoch": 1.9226890756302522,
      "grad_norm": 0.3467940092086792,
      "learning_rate": 0.00012382928223712806,
      "loss": 0.7195,
      "step": 858
    },
    {
      "epoch": 1.9249299719887956,
      "grad_norm": 0.33815139532089233,
      "learning_rate": 0.00012363925582559968,
      "loss": 0.704,
      "step": 859
    },
    {
      "epoch": 1.927170868347339,
      "grad_norm": 0.315331369638443,
      "learning_rate": 0.00012344913895704097,
      "loss": 0.6618,
      "step": 860
    },
    {
      "epoch": 1.9294117647058824,
      "grad_norm": 0.3420298099517822,
      "learning_rate": 0.00012325893235894564,
      "loss": 0.7005,
      "step": 861
    },
    {
      "epoch": 1.9316526610644258,
      "grad_norm": 0.33387431502342224,
      "learning_rate": 0.00012306863675915056,
      "loss": 0.8085,
      "step": 862
    },
    {
      "epoch": 1.9338935574229692,
      "grad_norm": 0.35296881198883057,
      "learning_rate": 0.0001228782528858333,
      "loss": 0.7798,
      "step": 863
    },
    {
      "epoch": 1.9361344537815126,
      "grad_norm": 0.3383727967739105,
      "learning_rate": 0.00012268778146750915,
      "loss": 0.6835,
      "step": 864
    },
    {
      "epoch": 1.938375350140056,
      "grad_norm": 0.33279767632484436,
      "learning_rate": 0.00012249722323302842,
      "loss": 0.7388,
      "step": 865
    },
    {
      "epoch": 1.9406162464985994,
      "grad_norm": 0.3255688548088074,
      "learning_rate": 0.00012230657891157363,
      "loss": 0.7167,
      "step": 866
    },
    {
      "epoch": 1.9428571428571428,
      "grad_norm": 0.34093961119651794,
      "learning_rate": 0.00012211584923265672,
      "loss": 0.7139,
      "step": 867
    },
    {
      "epoch": 1.9450980392156862,
      "grad_norm": 0.3231501281261444,
      "learning_rate": 0.00012192503492611625,
      "loss": 0.6996,
      "step": 868
    },
    {
      "epoch": 1.9473389355742297,
      "grad_norm": 0.3145335614681244,
      "learning_rate": 0.00012173413672211458,
      "loss": 0.7754,
      "step": 869
    },
    {
      "epoch": 1.949579831932773,
      "grad_norm": 0.32647013664245605,
      "learning_rate": 0.00012154315535113511,
      "loss": 0.6923,
      "step": 870
    },
    {
      "epoch": 1.9518207282913165,
      "grad_norm": 0.3004699647426605,
      "learning_rate": 0.00012135209154397962,
      "loss": 0.6856,
      "step": 871
    },
    {
      "epoch": 1.95406162464986,
      "grad_norm": 0.33689776062965393,
      "learning_rate": 0.00012116094603176513,
      "loss": 0.7621,
      "step": 872
    },
    {
      "epoch": 1.9563025210084035,
      "grad_norm": 0.30934080481529236,
      "learning_rate": 0.00012096971954592145,
      "loss": 0.7126,
      "step": 873
    },
    {
      "epoch": 1.958543417366947,
      "grad_norm": 0.346757173538208,
      "learning_rate": 0.00012077841281818816,
      "loss": 0.708,
      "step": 874
    },
    {
      "epoch": 1.9607843137254903,
      "grad_norm": 0.3257780075073242,
      "learning_rate": 0.00012058702658061197,
      "loss": 0.6621,
      "step": 875
    },
    {
      "epoch": 1.9630252100840337,
      "grad_norm": 0.3402419090270996,
      "learning_rate": 0.0001203955615655438,
      "loss": 0.7003,
      "step": 876
    },
    {
      "epoch": 1.9652661064425772,
      "grad_norm": 0.3437844514846802,
      "learning_rate": 0.00012020401850563596,
      "loss": 0.7469,
      "step": 877
    },
    {
      "epoch": 1.9675070028011206,
      "grad_norm": 0.3671571612358093,
      "learning_rate": 0.00012001239813383951,
      "loss": 0.785,
      "step": 878
    },
    {
      "epoch": 1.969747899159664,
      "grad_norm": 0.32898640632629395,
      "learning_rate": 0.00011982070118340127,
      "loss": 0.7292,
      "step": 879
    },
    {
      "epoch": 1.9719887955182074,
      "grad_norm": 0.3525889217853546,
      "learning_rate": 0.00011962892838786115,
      "loss": 0.7226,
      "step": 880
    },
    {
      "epoch": 1.9742296918767508,
      "grad_norm": 0.33842483162879944,
      "learning_rate": 0.00011943708048104922,
      "loss": 0.6483,
      "step": 881
    },
    {
      "epoch": 1.9764705882352942,
      "grad_norm": 0.3088597357273102,
      "learning_rate": 0.000119245158197083,
      "loss": 0.6449,
      "step": 882
    },
    {
      "epoch": 1.9787114845938376,
      "grad_norm": 0.32097896933555603,
      "learning_rate": 0.00011905316227036465,
      "loss": 0.7823,
      "step": 883
    },
    {
      "epoch": 1.980952380952381,
      "grad_norm": 0.316945880651474,
      "learning_rate": 0.00011886109343557808,
      "loss": 0.6802,
      "step": 884
    },
    {
      "epoch": 1.9831932773109244,
      "grad_norm": 0.3052690327167511,
      "learning_rate": 0.00011866895242768621,
      "loss": 0.6601,
      "step": 885
    },
    {
      "epoch": 1.9854341736694678,
      "grad_norm": 0.3162146210670471,
      "learning_rate": 0.00011847673998192815,
      "loss": 0.7377,
      "step": 886
    },
    {
      "epoch": 1.9876750700280112,
      "grad_norm": 0.3386717736721039,
      "learning_rate": 0.00011828445683381628,
      "loss": 0.7741,
      "step": 887
    },
    {
      "epoch": 1.9899159663865547,
      "grad_norm": 0.36137786507606506,
      "learning_rate": 0.00011809210371913368,
      "loss": 0.765,
      "step": 888
    },
    {
      "epoch": 1.992156862745098,
      "grad_norm": 0.37440425157546997,
      "learning_rate": 0.00011789968137393108,
      "loss": 0.7596,
      "step": 889
    },
    {
      "epoch": 1.9943977591036415,
      "grad_norm": 0.36767804622650146,
      "learning_rate": 0.00011770719053452407,
      "loss": 0.761,
      "step": 890
    },
    {
      "epoch": 1.9966386554621849,
      "grad_norm": 0.39699792861938477,
      "learning_rate": 0.00011751463193749044,
      "loss": 0.7781,
      "step": 891
    },
    {
      "epoch": 1.9988795518207283,
      "grad_norm": 0.35793137550354004,
      "learning_rate": 0.00011732200631966716,
      "loss": 0.7117,
      "step": 892
    }
  ],
  "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": 4.621244232105984e+17,
  "train_batch_size": 1,
  "trial_name": null,
  "trial_params": null
}