{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 1.3227513227513228,
  "eval_steps": 200,
  "global_step": 500,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0026455026455026454,
      "grad_norm": 1.1747032403945923,
      "learning_rate": 4e-05,
      "loss": 1.659,
      "step": 1
    },
    {
      "epoch": 0.005291005291005291,
      "grad_norm": 1.193225622177124,
      "learning_rate": 8e-05,
      "loss": 1.6561,
      "step": 2
    },
    {
      "epoch": 0.007936507936507936,
      "grad_norm": 0.9335116147994995,
      "learning_rate": 0.00012,
      "loss": 1.5989,
      "step": 3
    },
    {
      "epoch": 0.010582010582010581,
      "grad_norm": 0.905610203742981,
      "learning_rate": 0.00016,
      "loss": 1.5987,
      "step": 4
    },
    {
      "epoch": 0.013227513227513227,
      "grad_norm": 1.0402686595916748,
      "learning_rate": 0.0002,
      "loss": 1.5378,
      "step": 5
    },
    {
      "epoch": 0.015873015873015872,
      "grad_norm": 0.7273894548416138,
      "learning_rate": 0.00019973368841544607,
      "loss": 1.455,
      "step": 6
    },
    {
      "epoch": 0.018518518518518517,
      "grad_norm": 1.1512911319732666,
      "learning_rate": 0.00019946737683089217,
      "loss": 1.4295,
      "step": 7
    },
    {
      "epoch": 0.021164021164021163,
      "grad_norm": 1.6558116674423218,
      "learning_rate": 0.0001992010652463382,
      "loss": 1.4243,
      "step": 8
    },
    {
      "epoch": 0.023809523809523808,
      "grad_norm": 1.3095580339431763,
      "learning_rate": 0.0001989347536617843,
      "loss": 1.3701,
      "step": 9
    },
    {
      "epoch": 0.026455026455026454,
      "grad_norm": 0.8225361108779907,
      "learning_rate": 0.00019866844207723036,
      "loss": 1.3253,
      "step": 10
    },
    {
      "epoch": 0.0291005291005291,
      "grad_norm": 0.5447912216186523,
      "learning_rate": 0.00019840213049267645,
      "loss": 1.2765,
      "step": 11
    },
    {
      "epoch": 0.031746031746031744,
      "grad_norm": 0.5934835076332092,
      "learning_rate": 0.00019813581890812252,
      "loss": 1.2269,
      "step": 12
    },
    {
      "epoch": 0.03439153439153439,
      "grad_norm": 0.5302631258964539,
      "learning_rate": 0.00019786950732356858,
      "loss": 1.2732,
      "step": 13
    },
    {
      "epoch": 0.037037037037037035,
      "grad_norm": 0.5283780694007874,
      "learning_rate": 0.00019760319573901465,
      "loss": 1.2365,
      "step": 14
    },
    {
      "epoch": 0.03968253968253968,
      "grad_norm": 0.492745965719223,
      "learning_rate": 0.00019733688415446071,
      "loss": 1.168,
      "step": 15
    },
    {
      "epoch": 0.042328042328042326,
      "grad_norm": 0.38981908559799194,
      "learning_rate": 0.0001970705725699068,
      "loss": 1.2024,
      "step": 16
    },
    {
      "epoch": 0.04497354497354497,
      "grad_norm": 0.3651353716850281,
      "learning_rate": 0.00019680426098535287,
      "loss": 1.1871,
      "step": 17
    },
    {
      "epoch": 0.047619047619047616,
      "grad_norm": 0.35104984045028687,
      "learning_rate": 0.00019653794940079894,
      "loss": 1.1207,
      "step": 18
    },
    {
      "epoch": 0.05026455026455026,
      "grad_norm": 0.3698003888130188,
      "learning_rate": 0.00019627163781624503,
      "loss": 1.1056,
      "step": 19
    },
    {
      "epoch": 0.05291005291005291,
      "grad_norm": 0.33359289169311523,
      "learning_rate": 0.00019600532623169107,
      "loss": 1.1027,
      "step": 20
    },
    {
      "epoch": 0.05555555555555555,
      "grad_norm": 0.33576518297195435,
      "learning_rate": 0.00019573901464713716,
      "loss": 1.1471,
      "step": 21
    },
    {
      "epoch": 0.0582010582010582,
      "grad_norm": 0.32553064823150635,
      "learning_rate": 0.00019547270306258322,
      "loss": 1.0982,
      "step": 22
    },
    {
      "epoch": 0.06084656084656084,
      "grad_norm": 0.32208746671676636,
      "learning_rate": 0.00019520639147802932,
      "loss": 1.0578,
      "step": 23
    },
    {
      "epoch": 0.06349206349206349,
      "grad_norm": 0.29425886273384094,
      "learning_rate": 0.00019494007989347538,
      "loss": 1.094,
      "step": 24
    },
    {
      "epoch": 0.06613756613756613,
      "grad_norm": 0.29918986558914185,
      "learning_rate": 0.00019467376830892145,
      "loss": 1.1045,
      "step": 25
    },
    {
      "epoch": 0.06878306878306878,
      "grad_norm": 0.3173169493675232,
      "learning_rate": 0.0001944074567243675,
      "loss": 1.0707,
      "step": 26
    },
    {
      "epoch": 0.07142857142857142,
      "grad_norm": 0.29289600253105164,
      "learning_rate": 0.00019414114513981358,
      "loss": 1.0183,
      "step": 27
    },
    {
      "epoch": 0.07407407407407407,
      "grad_norm": 0.27134957909584045,
      "learning_rate": 0.00019387483355525967,
      "loss": 1.0738,
      "step": 28
    },
    {
      "epoch": 0.07671957671957672,
      "grad_norm": 0.28773605823516846,
      "learning_rate": 0.00019360852197070573,
      "loss": 1.0392,
      "step": 29
    },
    {
      "epoch": 0.07936507936507936,
      "grad_norm": 0.27970239520072937,
      "learning_rate": 0.00019334221038615183,
      "loss": 1.0643,
      "step": 30
    },
    {
      "epoch": 0.082010582010582,
      "grad_norm": 0.28050118684768677,
      "learning_rate": 0.0001930758988015979,
      "loss": 1.0471,
      "step": 31
    },
    {
      "epoch": 0.08465608465608465,
      "grad_norm": 0.2872134745121002,
      "learning_rate": 0.00019280958721704393,
      "loss": 1.0666,
      "step": 32
    },
    {
      "epoch": 0.0873015873015873,
      "grad_norm": 0.27781519293785095,
      "learning_rate": 0.00019254327563249002,
      "loss": 1.0654,
      "step": 33
    },
    {
      "epoch": 0.08994708994708994,
      "grad_norm": 0.27716726064682007,
      "learning_rate": 0.00019227696404793609,
      "loss": 1.0758,
      "step": 34
    },
    {
      "epoch": 0.09259259259259259,
      "grad_norm": 0.2795506715774536,
      "learning_rate": 0.00019201065246338218,
      "loss": 1.0536,
      "step": 35
    },
    {
      "epoch": 0.09523809523809523,
      "grad_norm": 0.26562824845314026,
      "learning_rate": 0.00019174434087882824,
      "loss": 1.0914,
      "step": 36
    },
    {
      "epoch": 0.09788359788359788,
      "grad_norm": 0.2639397084712982,
      "learning_rate": 0.0001914780292942743,
      "loss": 1.0554,
      "step": 37
    },
    {
      "epoch": 0.10052910052910052,
      "grad_norm": 0.2775086760520935,
      "learning_rate": 0.00019121171770972037,
      "loss": 1.049,
      "step": 38
    },
    {
      "epoch": 0.10317460317460317,
      "grad_norm": 0.27458131313323975,
      "learning_rate": 0.00019094540612516644,
      "loss": 0.984,
      "step": 39
    },
    {
      "epoch": 0.10582010582010581,
      "grad_norm": 0.26270249485969543,
      "learning_rate": 0.00019067909454061253,
      "loss": 1.025,
      "step": 40
    },
    {
      "epoch": 0.10846560846560846,
      "grad_norm": 0.29207131266593933,
      "learning_rate": 0.0001904127829560586,
      "loss": 0.9985,
      "step": 41
    },
    {
      "epoch": 0.1111111111111111,
      "grad_norm": 0.26398226618766785,
      "learning_rate": 0.0001901464713715047,
      "loss": 1.0306,
      "step": 42
    },
    {
      "epoch": 0.11375661375661375,
      "grad_norm": 0.29296690225601196,
      "learning_rate": 0.00018988015978695075,
      "loss": 1.0582,
      "step": 43
    },
    {
      "epoch": 0.1164021164021164,
      "grad_norm": 0.28397971391677856,
      "learning_rate": 0.00018961384820239682,
      "loss": 1.0201,
      "step": 44
    },
    {
      "epoch": 0.11904761904761904,
      "grad_norm": 0.26785364747047424,
      "learning_rate": 0.00018934753661784288,
      "loss": 0.9776,
      "step": 45
    },
    {
      "epoch": 0.12169312169312169,
      "grad_norm": 0.2898290455341339,
      "learning_rate": 0.00018908122503328895,
      "loss": 1.059,
      "step": 46
    },
    {
      "epoch": 0.12433862433862433,
      "grad_norm": 0.2818968594074249,
      "learning_rate": 0.00018881491344873504,
      "loss": 0.9709,
      "step": 47
    },
    {
      "epoch": 0.12698412698412698,
      "grad_norm": 0.27928805351257324,
      "learning_rate": 0.0001885486018641811,
      "loss": 1.0079,
      "step": 48
    },
    {
      "epoch": 0.12962962962962962,
      "grad_norm": 0.29027044773101807,
      "learning_rate": 0.00018828229027962717,
      "loss": 1.0307,
      "step": 49
    },
    {
      "epoch": 0.13227513227513227,
      "grad_norm": 0.28493452072143555,
      "learning_rate": 0.00018801597869507323,
      "loss": 1.0543,
      "step": 50
    },
    {
      "epoch": 0.1349206349206349,
      "grad_norm": 0.2731422185897827,
      "learning_rate": 0.0001877496671105193,
      "loss": 1.0688,
      "step": 51
    },
    {
      "epoch": 0.13756613756613756,
      "grad_norm": 0.28584980964660645,
      "learning_rate": 0.0001874833555259654,
      "loss": 0.9964,
      "step": 52
    },
    {
      "epoch": 0.1402116402116402,
      "grad_norm": 0.2896559536457062,
      "learning_rate": 0.00018721704394141146,
      "loss": 1.0587,
      "step": 53
    },
    {
      "epoch": 0.14285714285714285,
      "grad_norm": 0.27173537015914917,
      "learning_rate": 0.00018695073235685755,
      "loss": 1.0016,
      "step": 54
    },
    {
      "epoch": 0.1455026455026455,
      "grad_norm": 0.2858924865722656,
      "learning_rate": 0.00018668442077230361,
      "loss": 0.9414,
      "step": 55
    },
    {
      "epoch": 0.14814814814814814,
      "grad_norm": 0.2764526605606079,
      "learning_rate": 0.00018641810918774968,
      "loss": 0.9937,
      "step": 56
    },
    {
      "epoch": 0.15079365079365079,
      "grad_norm": 0.2818395793437958,
      "learning_rate": 0.00018615179760319574,
      "loss": 0.979,
      "step": 57
    },
    {
      "epoch": 0.15343915343915343,
      "grad_norm": 0.2785903811454773,
      "learning_rate": 0.0001858854860186418,
      "loss": 0.969,
      "step": 58
    },
    {
      "epoch": 0.15608465608465608,
      "grad_norm": 0.29127267003059387,
      "learning_rate": 0.0001856191744340879,
      "loss": 0.9408,
      "step": 59
    },
    {
      "epoch": 0.15873015873015872,
      "grad_norm": 0.2915956377983093,
      "learning_rate": 0.00018535286284953397,
      "loss": 0.9989,
      "step": 60
    },
    {
      "epoch": 0.16137566137566137,
      "grad_norm": 0.2813803255558014,
      "learning_rate": 0.00018508655126498006,
      "loss": 0.9975,
      "step": 61
    },
    {
      "epoch": 0.164021164021164,
      "grad_norm": 0.3066111207008362,
      "learning_rate": 0.0001848202396804261,
      "loss": 1.0374,
      "step": 62
    },
    {
      "epoch": 0.16666666666666666,
      "grad_norm": 0.2878720760345459,
      "learning_rate": 0.0001845539280958722,
      "loss": 1.0052,
      "step": 63
    },
    {
      "epoch": 0.1693121693121693,
      "grad_norm": 0.286018043756485,
      "learning_rate": 0.00018428761651131825,
      "loss": 1.014,
      "step": 64
    },
    {
      "epoch": 0.17195767195767195,
      "grad_norm": 0.3040521442890167,
      "learning_rate": 0.00018402130492676432,
      "loss": 0.9779,
      "step": 65
    },
    {
      "epoch": 0.1746031746031746,
      "grad_norm": 0.29262179136276245,
      "learning_rate": 0.0001837549933422104,
      "loss": 0.9195,
      "step": 66
    },
    {
      "epoch": 0.17724867724867724,
      "grad_norm": 0.3018079400062561,
      "learning_rate": 0.00018348868175765648,
      "loss": 0.9926,
      "step": 67
    },
    {
      "epoch": 0.17989417989417988,
      "grad_norm": 0.28605493903160095,
      "learning_rate": 0.00018322237017310254,
      "loss": 0.9932,
      "step": 68
    },
    {
      "epoch": 0.18253968253968253,
      "grad_norm": 0.29055798053741455,
      "learning_rate": 0.0001829560585885486,
      "loss": 1.0385,
      "step": 69
    },
    {
      "epoch": 0.18518518518518517,
      "grad_norm": 0.3057095408439636,
      "learning_rate": 0.00018268974700399467,
      "loss": 0.9866,
      "step": 70
    },
    {
      "epoch": 0.18783068783068782,
      "grad_norm": 0.27997255325317383,
      "learning_rate": 0.00018242343541944076,
      "loss": 0.9693,
      "step": 71
    },
    {
      "epoch": 0.19047619047619047,
      "grad_norm": 0.29187190532684326,
      "learning_rate": 0.00018215712383488683,
      "loss": 0.9615,
      "step": 72
    },
    {
      "epoch": 0.1931216931216931,
      "grad_norm": 0.2866925895214081,
      "learning_rate": 0.00018189081225033292,
      "loss": 0.9717,
      "step": 73
    },
    {
      "epoch": 0.19576719576719576,
      "grad_norm": 0.29582110047340393,
      "learning_rate": 0.00018162450066577896,
      "loss": 0.9161,
      "step": 74
    },
    {
      "epoch": 0.1984126984126984,
      "grad_norm": 0.29428231716156006,
      "learning_rate": 0.00018135818908122505,
      "loss": 0.9914,
      "step": 75
    },
    {
      "epoch": 0.20105820105820105,
      "grad_norm": 0.2943442165851593,
      "learning_rate": 0.00018109187749667111,
      "loss": 1.025,
      "step": 76
    },
    {
      "epoch": 0.2037037037037037,
      "grad_norm": 0.3043523132801056,
      "learning_rate": 0.00018082556591211718,
      "loss": 0.9918,
      "step": 77
    },
    {
      "epoch": 0.20634920634920634,
      "grad_norm": 0.29113250970840454,
      "learning_rate": 0.00018055925432756327,
      "loss": 0.9504,
      "step": 78
    },
    {
      "epoch": 0.20899470899470898,
      "grad_norm": 0.2882027328014374,
      "learning_rate": 0.0001802929427430093,
      "loss": 0.9185,
      "step": 79
    },
    {
      "epoch": 0.21164021164021163,
      "grad_norm": 0.2934989929199219,
      "learning_rate": 0.0001800266311584554,
      "loss": 0.9635,
      "step": 80
    },
    {
      "epoch": 0.21428571428571427,
      "grad_norm": 0.2960241734981537,
      "learning_rate": 0.00017976031957390147,
      "loss": 0.9983,
      "step": 81
    },
    {
      "epoch": 0.21693121693121692,
      "grad_norm": 0.30780884623527527,
      "learning_rate": 0.00017949400798934753,
      "loss": 0.9768,
      "step": 82
    },
    {
      "epoch": 0.21957671957671956,
      "grad_norm": 0.2874893844127655,
      "learning_rate": 0.00017922769640479362,
      "loss": 1.0133,
      "step": 83
    },
    {
      "epoch": 0.2222222222222222,
      "grad_norm": 0.28486186265945435,
      "learning_rate": 0.0001789613848202397,
      "loss": 0.9459,
      "step": 84
    },
    {
      "epoch": 0.22486772486772486,
      "grad_norm": 0.28974583745002747,
      "learning_rate": 0.00017869507323568575,
      "loss": 0.9642,
      "step": 85
    },
    {
      "epoch": 0.2275132275132275,
      "grad_norm": 0.2987074553966522,
      "learning_rate": 0.00017842876165113182,
      "loss": 0.9838,
      "step": 86
    },
    {
      "epoch": 0.23015873015873015,
      "grad_norm": 0.3286326825618744,
      "learning_rate": 0.0001781624500665779,
      "loss": 0.9163,
      "step": 87
    },
    {
      "epoch": 0.2328042328042328,
      "grad_norm": 0.2926485240459442,
      "learning_rate": 0.00017789613848202398,
      "loss": 0.9395,
      "step": 88
    },
    {
      "epoch": 0.23544973544973544,
      "grad_norm": 0.28627514839172363,
      "learning_rate": 0.00017762982689747004,
      "loss": 1.0011,
      "step": 89
    },
    {
      "epoch": 0.23809523809523808,
      "grad_norm": 0.3016904890537262,
      "learning_rate": 0.00017736351531291613,
      "loss": 0.929,
      "step": 90
    },
    {
      "epoch": 0.24074074074074073,
      "grad_norm": 0.29647526144981384,
      "learning_rate": 0.00017709720372836217,
      "loss": 0.9731,
      "step": 91
    },
    {
      "epoch": 0.24338624338624337,
      "grad_norm": 0.2880048453807831,
      "learning_rate": 0.00017683089214380826,
      "loss": 0.902,
      "step": 92
    },
    {
      "epoch": 0.24603174603174602,
      "grad_norm": 0.3583124279975891,
      "learning_rate": 0.00017656458055925433,
      "loss": 0.9541,
      "step": 93
    },
    {
      "epoch": 0.24867724867724866,
      "grad_norm": 0.3009599447250366,
      "learning_rate": 0.00017629826897470042,
      "loss": 0.9291,
      "step": 94
    },
    {
      "epoch": 0.25132275132275134,
      "grad_norm": 0.29124805331230164,
      "learning_rate": 0.00017603195739014649,
      "loss": 0.9695,
      "step": 95
    },
    {
      "epoch": 0.25396825396825395,
      "grad_norm": 0.29889848828315735,
      "learning_rate": 0.00017576564580559255,
      "loss": 0.9103,
      "step": 96
    },
    {
      "epoch": 0.2566137566137566,
      "grad_norm": 0.30669257044792175,
      "learning_rate": 0.00017549933422103862,
      "loss": 0.9564,
      "step": 97
    },
    {
      "epoch": 0.25925925925925924,
      "grad_norm": 0.3147302269935608,
      "learning_rate": 0.00017523302263648468,
      "loss": 0.9964,
      "step": 98
    },
    {
      "epoch": 0.2619047619047619,
      "grad_norm": 0.3032466173171997,
      "learning_rate": 0.00017496671105193077,
      "loss": 0.9284,
      "step": 99
    },
    {
      "epoch": 0.26455026455026454,
      "grad_norm": 0.30094724893569946,
      "learning_rate": 0.00017470039946737684,
      "loss": 0.9472,
      "step": 100
    },
    {
      "epoch": 0.2671957671957672,
      "grad_norm": 0.3017120957374573,
      "learning_rate": 0.0001744340878828229,
      "loss": 0.9773,
      "step": 101
    },
    {
      "epoch": 0.2698412698412698,
      "grad_norm": 0.3085327744483948,
      "learning_rate": 0.000174167776298269,
      "loss": 0.9039,
      "step": 102
    },
    {
      "epoch": 0.2724867724867725,
      "grad_norm": 0.2948116660118103,
      "learning_rate": 0.00017390146471371503,
      "loss": 0.9576,
      "step": 103
    },
    {
      "epoch": 0.2751322751322751,
      "grad_norm": 0.2965085804462433,
      "learning_rate": 0.00017363515312916113,
      "loss": 0.9172,
      "step": 104
    },
    {
      "epoch": 0.2777777777777778,
      "grad_norm": 0.30043408274650574,
      "learning_rate": 0.0001733688415446072,
      "loss": 0.8975,
      "step": 105
    },
    {
      "epoch": 0.2804232804232804,
      "grad_norm": 0.29271477460861206,
      "learning_rate": 0.00017310252996005328,
      "loss": 0.9351,
      "step": 106
    },
    {
      "epoch": 0.2830687830687831,
      "grad_norm": 0.3027021288871765,
      "learning_rate": 0.00017283621837549935,
      "loss": 1.0092,
      "step": 107
    },
    {
      "epoch": 0.2857142857142857,
      "grad_norm": 0.2956327497959137,
      "learning_rate": 0.0001725699067909454,
      "loss": 0.9548,
      "step": 108
    },
    {
      "epoch": 0.28835978835978837,
      "grad_norm": 0.29486629366874695,
      "learning_rate": 0.00017230359520639148,
      "loss": 0.9518,
      "step": 109
    },
    {
      "epoch": 0.291005291005291,
      "grad_norm": 0.2914023697376251,
      "learning_rate": 0.00017203728362183754,
      "loss": 1.0078,
      "step": 110
    },
    {
      "epoch": 0.29365079365079366,
      "grad_norm": 0.296137273311615,
      "learning_rate": 0.00017177097203728364,
      "loss": 0.9652,
      "step": 111
    },
    {
      "epoch": 0.2962962962962963,
      "grad_norm": 0.29895320534706116,
      "learning_rate": 0.0001715046604527297,
      "loss": 0.9359,
      "step": 112
    },
    {
      "epoch": 0.29894179894179895,
      "grad_norm": 0.3189530372619629,
      "learning_rate": 0.0001712383488681758,
      "loss": 0.9808,
      "step": 113
    },
    {
      "epoch": 0.30158730158730157,
      "grad_norm": 0.29777991771698,
      "learning_rate": 0.00017097203728362186,
      "loss": 0.9657,
      "step": 114
    },
    {
      "epoch": 0.30423280423280424,
      "grad_norm": 0.2951812446117401,
      "learning_rate": 0.00017070572569906792,
      "loss": 0.9524,
      "step": 115
    },
    {
      "epoch": 0.30687830687830686,
      "grad_norm": 0.3028695583343506,
      "learning_rate": 0.000170439414114514,
      "loss": 0.9862,
      "step": 116
    },
    {
      "epoch": 0.30952380952380953,
      "grad_norm": 0.2954007387161255,
      "learning_rate": 0.00017017310252996005,
      "loss": 0.9463,
      "step": 117
    },
    {
      "epoch": 0.31216931216931215,
      "grad_norm": 0.3298637866973877,
      "learning_rate": 0.00016990679094540614,
      "loss": 0.9238,
      "step": 118
    },
    {
      "epoch": 0.3148148148148148,
      "grad_norm": 0.28606554865837097,
      "learning_rate": 0.0001696404793608522,
      "loss": 0.8856,
      "step": 119
    },
    {
      "epoch": 0.31746031746031744,
      "grad_norm": 0.29628509283065796,
      "learning_rate": 0.00016937416777629827,
      "loss": 0.903,
      "step": 120
    },
    {
      "epoch": 0.3201058201058201,
      "grad_norm": 0.30181995034217834,
      "learning_rate": 0.00016910785619174434,
      "loss": 0.9255,
      "step": 121
    },
    {
      "epoch": 0.32275132275132273,
      "grad_norm": 0.2780914902687073,
      "learning_rate": 0.0001688415446071904,
      "loss": 0.8949,
      "step": 122
    },
    {
      "epoch": 0.3253968253968254,
      "grad_norm": 0.29049497842788696,
      "learning_rate": 0.0001685752330226365,
      "loss": 0.9764,
      "step": 123
    },
    {
      "epoch": 0.328042328042328,
      "grad_norm": 0.31094199419021606,
      "learning_rate": 0.00016830892143808256,
      "loss": 1.0107,
      "step": 124
    },
    {
      "epoch": 0.3306878306878307,
      "grad_norm": 0.31257522106170654,
      "learning_rate": 0.00016804260985352865,
      "loss": 0.9883,
      "step": 125
    },
    {
      "epoch": 0.3333333333333333,
      "grad_norm": 0.2883124053478241,
      "learning_rate": 0.00016777629826897472,
      "loss": 0.9179,
      "step": 126
    },
    {
      "epoch": 0.335978835978836,
      "grad_norm": 0.3087114989757538,
      "learning_rate": 0.00016750998668442078,
      "loss": 0.9741,
      "step": 127
    },
    {
      "epoch": 0.3386243386243386,
      "grad_norm": 0.29818522930145264,
      "learning_rate": 0.00016724367509986685,
      "loss": 0.9417,
      "step": 128
    },
    {
      "epoch": 0.3412698412698413,
      "grad_norm": 0.30048713088035583,
      "learning_rate": 0.00016697736351531291,
      "loss": 0.985,
      "step": 129
    },
    {
      "epoch": 0.3439153439153439,
      "grad_norm": 0.29243916273117065,
      "learning_rate": 0.000166711051930759,
      "loss": 0.8675,
      "step": 130
    },
    {
      "epoch": 0.34656084656084657,
      "grad_norm": 0.3162413537502289,
      "learning_rate": 0.00016644474034620507,
      "loss": 0.9806,
      "step": 131
    },
    {
      "epoch": 0.3492063492063492,
      "grad_norm": 0.30575287342071533,
      "learning_rate": 0.00016617842876165116,
      "loss": 0.9363,
      "step": 132
    },
    {
      "epoch": 0.35185185185185186,
      "grad_norm": 0.30893078446388245,
      "learning_rate": 0.0001659121171770972,
      "loss": 1.0569,
      "step": 133
    },
    {
      "epoch": 0.3544973544973545,
      "grad_norm": 0.2883886396884918,
      "learning_rate": 0.00016564580559254327,
      "loss": 0.9188,
      "step": 134
    },
    {
      "epoch": 0.35714285714285715,
      "grad_norm": 0.3047822117805481,
      "learning_rate": 0.00016537949400798936,
      "loss": 0.8535,
      "step": 135
    },
    {
      "epoch": 0.35978835978835977,
      "grad_norm": 0.29637783765792847,
      "learning_rate": 0.00016511318242343542,
      "loss": 0.9777,
      "step": 136
    },
    {
      "epoch": 0.36243386243386244,
      "grad_norm": 0.2985733449459076,
      "learning_rate": 0.00016484687083888152,
      "loss": 0.9419,
      "step": 137
    },
    {
      "epoch": 0.36507936507936506,
      "grad_norm": 0.3185897171497345,
      "learning_rate": 0.00016458055925432758,
      "loss": 0.9418,
      "step": 138
    },
    {
      "epoch": 0.36772486772486773,
      "grad_norm": 0.3095923960208893,
      "learning_rate": 0.00016431424766977365,
      "loss": 0.9189,
      "step": 139
    },
    {
      "epoch": 0.37037037037037035,
      "grad_norm": 0.30036240816116333,
      "learning_rate": 0.0001640479360852197,
      "loss": 0.9611,
      "step": 140
    },
    {
      "epoch": 0.373015873015873,
      "grad_norm": 0.30295637249946594,
      "learning_rate": 0.00016378162450066578,
      "loss": 0.9549,
      "step": 141
    },
    {
      "epoch": 0.37566137566137564,
      "grad_norm": 0.30549976229667664,
      "learning_rate": 0.00016351531291611187,
      "loss": 0.9129,
      "step": 142
    },
    {
      "epoch": 0.3783068783068783,
      "grad_norm": 0.29451197385787964,
      "learning_rate": 0.00016324900133155793,
      "loss": 1.0125,
      "step": 143
    },
    {
      "epoch": 0.38095238095238093,
      "grad_norm": 0.29042932391166687,
      "learning_rate": 0.000162982689747004,
      "loss": 0.9864,
      "step": 144
    },
    {
      "epoch": 0.3835978835978836,
      "grad_norm": 0.2863121032714844,
      "learning_rate": 0.00016271637816245006,
      "loss": 0.9104,
      "step": 145
    },
    {
      "epoch": 0.3862433862433862,
      "grad_norm": 0.31405770778656006,
      "learning_rate": 0.00016245006657789616,
      "loss": 0.9119,
      "step": 146
    },
    {
      "epoch": 0.3888888888888889,
      "grad_norm": 0.30320119857788086,
      "learning_rate": 0.00016218375499334222,
      "loss": 0.9916,
      "step": 147
    },
    {
      "epoch": 0.3915343915343915,
      "grad_norm": 0.289956271648407,
      "learning_rate": 0.00016191744340878829,
      "loss": 0.95,
      "step": 148
    },
    {
      "epoch": 0.3941798941798942,
      "grad_norm": 0.29359620809555054,
      "learning_rate": 0.00016165113182423438,
      "loss": 0.9225,
      "step": 149
    },
    {
      "epoch": 0.3968253968253968,
      "grad_norm": 0.29657161235809326,
      "learning_rate": 0.00016138482023968042,
      "loss": 0.9339,
      "step": 150
    },
    {
      "epoch": 0.3994708994708995,
      "grad_norm": 0.29414165019989014,
      "learning_rate": 0.0001611185086551265,
      "loss": 0.8998,
      "step": 151
    },
    {
      "epoch": 0.4021164021164021,
      "grad_norm": 0.29588285088539124,
      "learning_rate": 0.00016085219707057257,
      "loss": 0.9853,
      "step": 152
    },
    {
      "epoch": 0.40476190476190477,
      "grad_norm": 0.30724504590034485,
      "learning_rate": 0.00016058588548601864,
      "loss": 0.9174,
      "step": 153
    },
    {
      "epoch": 0.4074074074074074,
      "grad_norm": 0.3019733726978302,
      "learning_rate": 0.00016031957390146473,
      "loss": 0.8764,
      "step": 154
    },
    {
      "epoch": 0.41005291005291006,
      "grad_norm": 0.2877022325992584,
      "learning_rate": 0.0001600532623169108,
      "loss": 0.9164,
      "step": 155
    },
    {
      "epoch": 0.4126984126984127,
      "grad_norm": 0.30496105551719666,
      "learning_rate": 0.00015978695073235686,
      "loss": 0.8786,
      "step": 156
    },
    {
      "epoch": 0.41534391534391535,
      "grad_norm": 0.39060086011886597,
      "learning_rate": 0.00015952063914780292,
      "loss": 0.9086,
      "step": 157
    },
    {
      "epoch": 0.41798941798941797,
      "grad_norm": 0.2978059649467468,
      "learning_rate": 0.00015925432756324902,
      "loss": 0.9678,
      "step": 158
    },
    {
      "epoch": 0.42063492063492064,
      "grad_norm": 0.3026619553565979,
      "learning_rate": 0.00015898801597869508,
      "loss": 0.8831,
      "step": 159
    },
    {
      "epoch": 0.42328042328042326,
      "grad_norm": 0.3138423562049866,
      "learning_rate": 0.00015872170439414115,
      "loss": 0.924,
      "step": 160
    },
    {
      "epoch": 0.42592592592592593,
      "grad_norm": 0.30452167987823486,
      "learning_rate": 0.00015845539280958724,
      "loss": 0.984,
      "step": 161
    },
    {
      "epoch": 0.42857142857142855,
      "grad_norm": 0.3036138415336609,
      "learning_rate": 0.00015818908122503328,
      "loss": 0.9784,
      "step": 162
    },
    {
      "epoch": 0.4312169312169312,
      "grad_norm": 0.2976178526878357,
      "learning_rate": 0.00015792276964047937,
      "loss": 0.9338,
      "step": 163
    },
    {
      "epoch": 0.43386243386243384,
      "grad_norm": 0.2962900400161743,
      "learning_rate": 0.00015765645805592543,
      "loss": 0.9737,
      "step": 164
    },
    {
      "epoch": 0.4365079365079365,
      "grad_norm": 0.30100584030151367,
      "learning_rate": 0.00015739014647137153,
      "loss": 0.9426,
      "step": 165
    },
    {
      "epoch": 0.43915343915343913,
      "grad_norm": 0.30284544825553894,
      "learning_rate": 0.0001571238348868176,
      "loss": 0.9278,
      "step": 166
    },
    {
      "epoch": 0.4417989417989418,
      "grad_norm": 0.3027493357658386,
      "learning_rate": 0.00015685752330226366,
      "loss": 0.9749,
      "step": 167
    },
    {
      "epoch": 0.4444444444444444,
      "grad_norm": 0.3092235028743744,
      "learning_rate": 0.00015659121171770972,
      "loss": 0.9103,
      "step": 168
    },
    {
      "epoch": 0.4470899470899471,
      "grad_norm": 0.3082717955112457,
      "learning_rate": 0.0001563249001331558,
      "loss": 0.9097,
      "step": 169
    },
    {
      "epoch": 0.4497354497354497,
      "grad_norm": 0.3102925717830658,
      "learning_rate": 0.00015605858854860188,
      "loss": 0.9608,
      "step": 170
    },
    {
      "epoch": 0.4523809523809524,
      "grad_norm": 0.306264191865921,
      "learning_rate": 0.00015579227696404794,
      "loss": 0.9566,
      "step": 171
    },
    {
      "epoch": 0.455026455026455,
      "grad_norm": 0.29556524753570557,
      "learning_rate": 0.000155525965379494,
      "loss": 0.9336,
      "step": 172
    },
    {
      "epoch": 0.4576719576719577,
      "grad_norm": 0.2840050160884857,
      "learning_rate": 0.0001552596537949401,
      "loss": 0.926,
      "step": 173
    },
    {
      "epoch": 0.4603174603174603,
      "grad_norm": 0.29732030630111694,
      "learning_rate": 0.00015499334221038614,
      "loss": 0.907,
      "step": 174
    },
    {
      "epoch": 0.46296296296296297,
      "grad_norm": 0.2985256314277649,
      "learning_rate": 0.00015472703062583223,
      "loss": 0.9385,
      "step": 175
    },
    {
      "epoch": 0.4656084656084656,
      "grad_norm": 0.3027939200401306,
      "learning_rate": 0.0001544607190412783,
      "loss": 0.9052,
      "step": 176
    },
    {
      "epoch": 0.46825396825396826,
      "grad_norm": 0.29000991582870483,
      "learning_rate": 0.0001541944074567244,
      "loss": 0.9084,
      "step": 177
    },
    {
      "epoch": 0.4708994708994709,
      "grad_norm": 0.2917994260787964,
      "learning_rate": 0.00015392809587217045,
      "loss": 0.8864,
      "step": 178
    },
    {
      "epoch": 0.47354497354497355,
      "grad_norm": 0.3019108474254608,
      "learning_rate": 0.00015366178428761652,
      "loss": 0.9,
      "step": 179
    },
    {
      "epoch": 0.47619047619047616,
      "grad_norm": 0.3014208674430847,
      "learning_rate": 0.00015339547270306258,
      "loss": 0.9091,
      "step": 180
    },
    {
      "epoch": 0.47883597883597884,
      "grad_norm": 0.3073003888130188,
      "learning_rate": 0.00015312916111850865,
      "loss": 0.8533,
      "step": 181
    },
    {
      "epoch": 0.48148148148148145,
      "grad_norm": 0.3027694821357727,
      "learning_rate": 0.00015286284953395474,
      "loss": 0.9182,
      "step": 182
    },
    {
      "epoch": 0.48412698412698413,
      "grad_norm": 0.3077705502510071,
      "learning_rate": 0.0001525965379494008,
      "loss": 0.8886,
      "step": 183
    },
    {
      "epoch": 0.48677248677248675,
      "grad_norm": 0.31237298250198364,
      "learning_rate": 0.0001523302263648469,
      "loss": 0.9226,
      "step": 184
    },
    {
      "epoch": 0.4894179894179894,
      "grad_norm": 0.30701160430908203,
      "learning_rate": 0.00015206391478029296,
      "loss": 0.9331,
      "step": 185
    },
    {
      "epoch": 0.49206349206349204,
      "grad_norm": 0.30542266368865967,
      "learning_rate": 0.000151797603195739,
      "loss": 0.9895,
      "step": 186
    },
    {
      "epoch": 0.4947089947089947,
      "grad_norm": 0.3137788772583008,
      "learning_rate": 0.0001515312916111851,
      "loss": 0.9521,
      "step": 187
    },
    {
      "epoch": 0.4973544973544973,
      "grad_norm": 0.29560190439224243,
      "learning_rate": 0.00015126498002663116,
      "loss": 0.9112,
      "step": 188
    },
    {
      "epoch": 0.5,
      "grad_norm": 0.2956138253211975,
      "learning_rate": 0.00015099866844207725,
      "loss": 0.8934,
      "step": 189
    },
    {
      "epoch": 0.5026455026455027,
      "grad_norm": 0.3044353723526001,
      "learning_rate": 0.00015073235685752331,
      "loss": 0.8655,
      "step": 190
    },
    {
      "epoch": 0.5052910052910053,
      "grad_norm": 0.29127389192581177,
      "learning_rate": 0.00015046604527296938,
      "loss": 0.8985,
      "step": 191
    },
    {
      "epoch": 0.5079365079365079,
      "grad_norm": 0.3086501955986023,
      "learning_rate": 0.00015019973368841544,
      "loss": 0.8985,
      "step": 192
    },
    {
      "epoch": 0.5105820105820106,
      "grad_norm": 0.31071314215660095,
      "learning_rate": 0.0001499334221038615,
      "loss": 0.8798,
      "step": 193
    },
    {
      "epoch": 0.5132275132275133,
      "grad_norm": 0.3166221082210541,
      "learning_rate": 0.0001496671105193076,
      "loss": 0.9024,
      "step": 194
    },
    {
      "epoch": 0.5158730158730159,
      "grad_norm": 0.3039884567260742,
      "learning_rate": 0.00014940079893475367,
      "loss": 0.8463,
      "step": 195
    },
    {
      "epoch": 0.5185185185185185,
      "grad_norm": 0.29704445600509644,
      "learning_rate": 0.00014913448735019976,
      "loss": 0.9025,
      "step": 196
    },
    {
      "epoch": 0.5211640211640212,
      "grad_norm": 0.30685505270957947,
      "learning_rate": 0.00014886817576564582,
      "loss": 0.9085,
      "step": 197
    },
    {
      "epoch": 0.5238095238095238,
      "grad_norm": 0.29699406027793884,
      "learning_rate": 0.0001486018641810919,
      "loss": 0.9628,
      "step": 198
    },
    {
      "epoch": 0.5264550264550265,
      "grad_norm": 0.3087448477745056,
      "learning_rate": 0.00014833555259653795,
      "loss": 0.8856,
      "step": 199
    },
    {
      "epoch": 0.5291005291005291,
      "grad_norm": 0.3041601777076721,
      "learning_rate": 0.00014806924101198402,
      "loss": 0.8959,
      "step": 200
    },
    {
      "epoch": 0.5291005291005291,
      "eval_loss": 0.8902713656425476,
      "eval_runtime": 11.641,
      "eval_samples_per_second": 23.022,
      "eval_steps_per_second": 0.773,
      "step": 200
    },
    {
      "epoch": 0.5317460317460317,
      "grad_norm": 0.3018532395362854,
      "learning_rate": 0.0001478029294274301,
      "loss": 0.9457,
      "step": 201
    },
    {
      "epoch": 0.5343915343915344,
      "grad_norm": 0.3002660870552063,
      "learning_rate": 0.00014753661784287618,
      "loss": 0.915,
      "step": 202
    },
    {
      "epoch": 0.5370370370370371,
      "grad_norm": 0.3114616870880127,
      "learning_rate": 0.00014727030625832224,
      "loss": 0.9341,
      "step": 203
    },
    {
      "epoch": 0.5396825396825397,
      "grad_norm": 0.30542701482772827,
      "learning_rate": 0.0001470039946737683,
      "loss": 0.8466,
      "step": 204
    },
    {
      "epoch": 0.5423280423280423,
      "grad_norm": 0.29633527994155884,
      "learning_rate": 0.00014673768308921437,
      "loss": 0.9076,
      "step": 205
    },
    {
      "epoch": 0.544973544973545,
      "grad_norm": 0.304551899433136,
      "learning_rate": 0.00014647137150466046,
      "loss": 0.8959,
      "step": 206
    },
    {
      "epoch": 0.5476190476190477,
      "grad_norm": 0.321927011013031,
      "learning_rate": 0.00014620505992010653,
      "loss": 0.8979,
      "step": 207
    },
    {
      "epoch": 0.5502645502645502,
      "grad_norm": 0.31447145342826843,
      "learning_rate": 0.00014593874833555262,
      "loss": 0.8552,
      "step": 208
    },
    {
      "epoch": 0.5529100529100529,
      "grad_norm": 0.30765920877456665,
      "learning_rate": 0.00014567243675099869,
      "loss": 0.9696,
      "step": 209
    },
    {
      "epoch": 0.5555555555555556,
      "grad_norm": 0.3005291521549225,
      "learning_rate": 0.00014540612516644475,
      "loss": 0.89,
      "step": 210
    },
    {
      "epoch": 0.5582010582010583,
      "grad_norm": 0.2886287271976471,
      "learning_rate": 0.00014513981358189082,
      "loss": 0.8944,
      "step": 211
    },
    {
      "epoch": 0.5608465608465608,
      "grad_norm": 0.30935782194137573,
      "learning_rate": 0.00014487350199733688,
      "loss": 0.8431,
      "step": 212
    },
    {
      "epoch": 0.5634920634920635,
      "grad_norm": 0.30873075127601624,
      "learning_rate": 0.00014460719041278297,
      "loss": 0.9277,
      "step": 213
    },
    {
      "epoch": 0.5661375661375662,
      "grad_norm": 0.29618608951568604,
      "learning_rate": 0.00014434087882822904,
      "loss": 0.887,
      "step": 214
    },
    {
      "epoch": 0.5687830687830688,
      "grad_norm": 0.3181705176830292,
      "learning_rate": 0.0001440745672436751,
      "loss": 0.9469,
      "step": 215
    },
    {
      "epoch": 0.5714285714285714,
      "grad_norm": 0.31462034583091736,
      "learning_rate": 0.00014380825565912117,
      "loss": 0.8583,
      "step": 216
    },
    {
      "epoch": 0.5740740740740741,
      "grad_norm": 0.3188857138156891,
      "learning_rate": 0.00014354194407456726,
      "loss": 0.8607,
      "step": 217
    },
    {
      "epoch": 0.5767195767195767,
      "grad_norm": 0.2999894618988037,
      "learning_rate": 0.00014327563249001333,
      "loss": 0.8634,
      "step": 218
    },
    {
      "epoch": 0.5793650793650794,
      "grad_norm": 0.2952975928783417,
      "learning_rate": 0.0001430093209054594,
      "loss": 0.8698,
      "step": 219
    },
    {
      "epoch": 0.582010582010582,
      "grad_norm": 0.3010879456996918,
      "learning_rate": 0.00014274300932090548,
      "loss": 0.8849,
      "step": 220
    },
    {
      "epoch": 0.5846560846560847,
      "grad_norm": 0.30581486225128174,
      "learning_rate": 0.00014247669773635152,
      "loss": 0.9484,
      "step": 221
    },
    {
      "epoch": 0.5873015873015873,
      "grad_norm": 0.3189585506916046,
      "learning_rate": 0.0001422103861517976,
      "loss": 0.9289,
      "step": 222
    },
    {
      "epoch": 0.58994708994709,
      "grad_norm": 0.2941770851612091,
      "learning_rate": 0.00014194407456724368,
      "loss": 0.933,
      "step": 223
    },
    {
      "epoch": 0.5925925925925926,
      "grad_norm": 0.29809415340423584,
      "learning_rate": 0.00014167776298268974,
      "loss": 0.8945,
      "step": 224
    },
    {
      "epoch": 0.5952380952380952,
      "grad_norm": 0.3198634684085846,
      "learning_rate": 0.00014141145139813583,
      "loss": 0.9438,
      "step": 225
    },
    {
      "epoch": 0.5978835978835979,
      "grad_norm": 0.2994458079338074,
      "learning_rate": 0.0001411451398135819,
      "loss": 0.9364,
      "step": 226
    },
    {
      "epoch": 0.6005291005291006,
      "grad_norm": 0.3103165030479431,
      "learning_rate": 0.00014087882822902796,
      "loss": 0.8619,
      "step": 227
    },
    {
      "epoch": 0.6031746031746031,
      "grad_norm": 0.29631927609443665,
      "learning_rate": 0.00014061251664447403,
      "loss": 0.8738,
      "step": 228
    },
    {
      "epoch": 0.6058201058201058,
      "grad_norm": 0.30190715193748474,
      "learning_rate": 0.00014034620505992012,
      "loss": 0.866,
      "step": 229
    },
    {
      "epoch": 0.6084656084656085,
      "grad_norm": 0.3294380009174347,
      "learning_rate": 0.0001400798934753662,
      "loss": 0.8981,
      "step": 230
    },
    {
      "epoch": 0.6111111111111112,
      "grad_norm": 0.31856992840766907,
      "learning_rate": 0.00013981358189081225,
      "loss": 0.9303,
      "step": 231
    },
    {
      "epoch": 0.6137566137566137,
      "grad_norm": 0.30866724252700806,
      "learning_rate": 0.00013954727030625834,
      "loss": 0.8983,
      "step": 232
    },
    {
      "epoch": 0.6164021164021164,
      "grad_norm": 0.31105831265449524,
      "learning_rate": 0.00013928095872170438,
      "loss": 0.9754,
      "step": 233
    },
    {
      "epoch": 0.6190476190476191,
      "grad_norm": 0.29924359917640686,
      "learning_rate": 0.00013901464713715047,
      "loss": 0.8866,
      "step": 234
    },
    {
      "epoch": 0.6216931216931217,
      "grad_norm": 0.28959640860557556,
      "learning_rate": 0.00013874833555259654,
      "loss": 0.9084,
      "step": 235
    },
    {
      "epoch": 0.6243386243386243,
      "grad_norm": 0.3111019432544708,
      "learning_rate": 0.0001384820239680426,
      "loss": 0.8939,
      "step": 236
    },
    {
      "epoch": 0.626984126984127,
      "grad_norm": 0.3044912815093994,
      "learning_rate": 0.0001382157123834887,
      "loss": 0.8786,
      "step": 237
    },
    {
      "epoch": 0.6296296296296297,
      "grad_norm": 0.29759299755096436,
      "learning_rate": 0.00013794940079893476,
      "loss": 0.9221,
      "step": 238
    },
    {
      "epoch": 0.6322751322751323,
      "grad_norm": 0.28913435339927673,
      "learning_rate": 0.00013768308921438083,
      "loss": 0.9254,
      "step": 239
    },
    {
      "epoch": 0.6349206349206349,
      "grad_norm": 0.2931109368801117,
      "learning_rate": 0.0001374167776298269,
      "loss": 0.8275,
      "step": 240
    },
    {
      "epoch": 0.6375661375661376,
      "grad_norm": 0.3069958984851837,
      "learning_rate": 0.00013715046604527298,
      "loss": 0.8797,
      "step": 241
    },
    {
      "epoch": 0.6402116402116402,
      "grad_norm": 0.311829149723053,
      "learning_rate": 0.00013688415446071905,
      "loss": 0.8984,
      "step": 242
    },
    {
      "epoch": 0.6428571428571429,
      "grad_norm": 0.3024655878543854,
      "learning_rate": 0.00013661784287616511,
      "loss": 0.9008,
      "step": 243
    },
    {
      "epoch": 0.6455026455026455,
      "grad_norm": 0.301362007856369,
      "learning_rate": 0.0001363515312916112,
      "loss": 0.9078,
      "step": 244
    },
    {
      "epoch": 0.6481481481481481,
      "grad_norm": 0.3074656128883362,
      "learning_rate": 0.00013608521970705724,
      "loss": 0.86,
      "step": 245
    },
    {
      "epoch": 0.6507936507936508,
      "grad_norm": 0.3019891083240509,
      "learning_rate": 0.00013581890812250334,
      "loss": 0.9421,
      "step": 246
    },
    {
      "epoch": 0.6534391534391535,
      "grad_norm": 0.3009161353111267,
      "learning_rate": 0.0001355525965379494,
      "loss": 0.9076,
      "step": 247
    },
    {
      "epoch": 0.656084656084656,
      "grad_norm": 0.3028698265552521,
      "learning_rate": 0.0001352862849533955,
      "loss": 0.8877,
      "step": 248
    },
    {
      "epoch": 0.6587301587301587,
      "grad_norm": 0.30194738507270813,
      "learning_rate": 0.00013501997336884156,
      "loss": 0.8762,
      "step": 249
    },
    {
      "epoch": 0.6613756613756614,
      "grad_norm": 0.3077562749385834,
      "learning_rate": 0.00013475366178428762,
      "loss": 0.8805,
      "step": 250
    },
    {
      "epoch": 0.6640211640211641,
      "grad_norm": 0.3195575177669525,
      "learning_rate": 0.0001344873501997337,
      "loss": 0.8927,
      "step": 251
    },
    {
      "epoch": 0.6666666666666666,
      "grad_norm": 0.3138684034347534,
      "learning_rate": 0.00013422103861517975,
      "loss": 0.8214,
      "step": 252
    },
    {
      "epoch": 0.6693121693121693,
      "grad_norm": 0.30715471506118774,
      "learning_rate": 0.00013395472703062585,
      "loss": 0.8843,
      "step": 253
    },
    {
      "epoch": 0.671957671957672,
      "grad_norm": 0.3030779957771301,
      "learning_rate": 0.0001336884154460719,
      "loss": 0.8636,
      "step": 254
    },
    {
      "epoch": 0.6746031746031746,
      "grad_norm": 0.2956666052341461,
      "learning_rate": 0.00013342210386151798,
      "loss": 0.9178,
      "step": 255
    },
    {
      "epoch": 0.6772486772486772,
      "grad_norm": 0.30229073762893677,
      "learning_rate": 0.00013315579227696407,
      "loss": 0.8776,
      "step": 256
    },
    {
      "epoch": 0.6798941798941799,
      "grad_norm": 0.6680058836936951,
      "learning_rate": 0.0001328894806924101,
      "loss": 0.9373,
      "step": 257
    },
    {
      "epoch": 0.6825396825396826,
      "grad_norm": 0.29769212007522583,
      "learning_rate": 0.0001326231691078562,
      "loss": 0.979,
      "step": 258
    },
    {
      "epoch": 0.6851851851851852,
      "grad_norm": 0.3262118995189667,
      "learning_rate": 0.00013235685752330226,
      "loss": 0.9138,
      "step": 259
    },
    {
      "epoch": 0.6878306878306878,
      "grad_norm": 0.31053462624549866,
      "learning_rate": 0.00013209054593874836,
      "loss": 0.9025,
      "step": 260
    },
    {
      "epoch": 0.6904761904761905,
      "grad_norm": 0.295154869556427,
      "learning_rate": 0.00013182423435419442,
      "loss": 0.8766,
      "step": 261
    },
    {
      "epoch": 0.6931216931216931,
      "grad_norm": 0.31233900785446167,
      "learning_rate": 0.00013155792276964049,
      "loss": 0.8527,
      "step": 262
    },
    {
      "epoch": 0.6957671957671958,
      "grad_norm": 0.3208140432834625,
      "learning_rate": 0.00013129161118508655,
      "loss": 0.9174,
      "step": 263
    },
    {
      "epoch": 0.6984126984126984,
      "grad_norm": 0.3348202109336853,
      "learning_rate": 0.00013102529960053262,
      "loss": 0.8598,
      "step": 264
    },
    {
      "epoch": 0.701058201058201,
      "grad_norm": 0.3033234477043152,
      "learning_rate": 0.0001307589880159787,
      "loss": 0.8851,
      "step": 265
    },
    {
      "epoch": 0.7037037037037037,
      "grad_norm": 0.3031875789165497,
      "learning_rate": 0.00013049267643142477,
      "loss": 0.9026,
      "step": 266
    },
    {
      "epoch": 0.7063492063492064,
      "grad_norm": 0.30696120858192444,
      "learning_rate": 0.00013022636484687086,
      "loss": 0.925,
      "step": 267
    },
    {
      "epoch": 0.708994708994709,
      "grad_norm": 0.31377336382865906,
      "learning_rate": 0.00012996005326231693,
      "loss": 0.8718,
      "step": 268
    },
    {
      "epoch": 0.7116402116402116,
      "grad_norm": 0.2996474802494049,
      "learning_rate": 0.00012969374167776297,
      "loss": 0.8618,
      "step": 269
    },
    {
      "epoch": 0.7142857142857143,
      "grad_norm": 0.30813682079315186,
      "learning_rate": 0.00012942743009320906,
      "loss": 0.8802,
      "step": 270
    },
    {
      "epoch": 0.716931216931217,
      "grad_norm": 0.31186458468437195,
      "learning_rate": 0.00012916111850865512,
      "loss": 0.877,
      "step": 271
    },
    {
      "epoch": 0.7195767195767195,
      "grad_norm": 0.3049626052379608,
      "learning_rate": 0.00012889480692410122,
      "loss": 0.8148,
      "step": 272
    },
    {
      "epoch": 0.7222222222222222,
      "grad_norm": 0.30760645866394043,
      "learning_rate": 0.00012862849533954728,
      "loss": 0.8505,
      "step": 273
    },
    {
      "epoch": 0.7248677248677249,
      "grad_norm": 0.29829591512680054,
      "learning_rate": 0.00012836218375499335,
      "loss": 0.8789,
      "step": 274
    },
    {
      "epoch": 0.7275132275132276,
      "grad_norm": 0.30727919936180115,
      "learning_rate": 0.0001280958721704394,
      "loss": 0.9339,
      "step": 275
    },
    {
      "epoch": 0.7301587301587301,
      "grad_norm": 0.3146195411682129,
      "learning_rate": 0.00012782956058588548,
      "loss": 0.9047,
      "step": 276
    },
    {
      "epoch": 0.7328042328042328,
      "grad_norm": 0.2988054156303406,
      "learning_rate": 0.00012756324900133157,
      "loss": 0.8881,
      "step": 277
    },
    {
      "epoch": 0.7354497354497355,
      "grad_norm": 0.3081274628639221,
      "learning_rate": 0.00012729693741677763,
      "loss": 0.9157,
      "step": 278
    },
    {
      "epoch": 0.7380952380952381,
      "grad_norm": 0.30301836133003235,
      "learning_rate": 0.00012703062583222373,
      "loss": 0.8894,
      "step": 279
    },
    {
      "epoch": 0.7407407407407407,
      "grad_norm": 0.30307427048683167,
      "learning_rate": 0.00012676431424766976,
      "loss": 0.8438,
      "step": 280
    },
    {
      "epoch": 0.7433862433862434,
      "grad_norm": 0.3125646114349365,
      "learning_rate": 0.00012649800266311586,
      "loss": 0.8238,
      "step": 281
    },
    {
      "epoch": 0.746031746031746,
      "grad_norm": 0.3004276752471924,
      "learning_rate": 0.00012623169107856192,
      "loss": 0.918,
      "step": 282
    },
    {
      "epoch": 0.7486772486772487,
      "grad_norm": 0.3069279193878174,
      "learning_rate": 0.00012596537949400799,
      "loss": 0.9547,
      "step": 283
    },
    {
      "epoch": 0.7513227513227513,
      "grad_norm": 0.3121134638786316,
      "learning_rate": 0.00012569906790945408,
      "loss": 0.9013,
      "step": 284
    },
    {
      "epoch": 0.753968253968254,
      "grad_norm": 0.30534470081329346,
      "learning_rate": 0.00012543275632490014,
      "loss": 0.8669,
      "step": 285
    },
    {
      "epoch": 0.7566137566137566,
      "grad_norm": 0.3099939227104187,
      "learning_rate": 0.0001251664447403462,
      "loss": 0.8735,
      "step": 286
    },
    {
      "epoch": 0.7592592592592593,
      "grad_norm": 0.29624268412590027,
      "learning_rate": 0.00012490013315579227,
      "loss": 0.8581,
      "step": 287
    },
    {
      "epoch": 0.7619047619047619,
      "grad_norm": 0.3067234456539154,
      "learning_rate": 0.00012463382157123834,
      "loss": 0.878,
      "step": 288
    },
    {
      "epoch": 0.7645502645502645,
      "grad_norm": 0.30994749069213867,
      "learning_rate": 0.00012436750998668443,
      "loss": 0.8974,
      "step": 289
    },
    {
      "epoch": 0.7671957671957672,
      "grad_norm": 0.3059810400009155,
      "learning_rate": 0.0001241011984021305,
      "loss": 0.8328,
      "step": 290
    },
    {
      "epoch": 0.7698412698412699,
      "grad_norm": 0.3063666820526123,
      "learning_rate": 0.0001238348868175766,
      "loss": 0.9263,
      "step": 291
    },
    {
      "epoch": 0.7724867724867724,
      "grad_norm": 0.31066998839378357,
      "learning_rate": 0.00012356857523302263,
      "loss": 0.9789,
      "step": 292
    },
    {
      "epoch": 0.7751322751322751,
      "grad_norm": 0.3066621422767639,
      "learning_rate": 0.00012330226364846872,
      "loss": 0.8743,
      "step": 293
    },
    {
      "epoch": 0.7777777777777778,
      "grad_norm": 0.3092249035835266,
      "learning_rate": 0.00012303595206391478,
      "loss": 0.9392,
      "step": 294
    },
    {
      "epoch": 0.7804232804232805,
      "grad_norm": 0.30648186802864075,
      "learning_rate": 0.00012276964047936085,
      "loss": 0.8806,
      "step": 295
    },
    {
      "epoch": 0.783068783068783,
      "grad_norm": 0.3106636106967926,
      "learning_rate": 0.00012250332889480694,
      "loss": 0.8942,
      "step": 296
    },
    {
      "epoch": 0.7857142857142857,
      "grad_norm": 0.3162897527217865,
      "learning_rate": 0.000122237017310253,
      "loss": 0.9185,
      "step": 297
    },
    {
      "epoch": 0.7883597883597884,
      "grad_norm": 0.3027794063091278,
      "learning_rate": 0.00012197070572569907,
      "loss": 0.9013,
      "step": 298
    },
    {
      "epoch": 0.791005291005291,
      "grad_norm": 0.3065483272075653,
      "learning_rate": 0.00012170439414114514,
      "loss": 0.8984,
      "step": 299
    },
    {
      "epoch": 0.7936507936507936,
      "grad_norm": 0.31186428666114807,
      "learning_rate": 0.00012143808255659121,
      "loss": 0.9206,
      "step": 300
    },
    {
      "epoch": 0.7962962962962963,
      "grad_norm": 0.31579795479774475,
      "learning_rate": 0.00012117177097203729,
      "loss": 0.8425,
      "step": 301
    },
    {
      "epoch": 0.798941798941799,
      "grad_norm": 0.29713234305381775,
      "learning_rate": 0.00012090545938748337,
      "loss": 0.9032,
      "step": 302
    },
    {
      "epoch": 0.8015873015873016,
      "grad_norm": 0.3086577355861664,
      "learning_rate": 0.00012063914780292944,
      "loss": 0.9208,
      "step": 303
    },
    {
      "epoch": 0.8042328042328042,
      "grad_norm": 0.3003513216972351,
      "learning_rate": 0.0001203728362183755,
      "loss": 0.8656,
      "step": 304
    },
    {
      "epoch": 0.8068783068783069,
      "grad_norm": 0.3014473021030426,
      "learning_rate": 0.00012010652463382157,
      "loss": 0.8655,
      "step": 305
    },
    {
      "epoch": 0.8095238095238095,
      "grad_norm": 0.30755501985549927,
      "learning_rate": 0.00011984021304926764,
      "loss": 0.839,
      "step": 306
    },
    {
      "epoch": 0.8121693121693122,
      "grad_norm": 0.3207037150859833,
      "learning_rate": 0.00011957390146471372,
      "loss": 0.871,
      "step": 307
    },
    {
      "epoch": 0.8148148148148148,
      "grad_norm": 0.30852946639060974,
      "learning_rate": 0.0001193075898801598,
      "loss": 0.895,
      "step": 308
    },
    {
      "epoch": 0.8174603174603174,
      "grad_norm": 0.31728988885879517,
      "learning_rate": 0.00011904127829560587,
      "loss": 0.9669,
      "step": 309
    },
    {
      "epoch": 0.8201058201058201,
      "grad_norm": 0.32250693440437317,
      "learning_rate": 0.00011877496671105193,
      "loss": 0.9051,
      "step": 310
    },
    {
      "epoch": 0.8227513227513228,
      "grad_norm": 0.30779287219047546,
      "learning_rate": 0.000118508655126498,
      "loss": 0.8727,
      "step": 311
    },
    {
      "epoch": 0.8253968253968254,
      "grad_norm": 0.3224301040172577,
      "learning_rate": 0.00011824234354194408,
      "loss": 0.9636,
      "step": 312
    },
    {
      "epoch": 0.828042328042328,
      "grad_norm": 0.3030790388584137,
      "learning_rate": 0.00011797603195739015,
      "loss": 0.8689,
      "step": 313
    },
    {
      "epoch": 0.8306878306878307,
      "grad_norm": 0.30144137144088745,
      "learning_rate": 0.00011770972037283623,
      "loss": 0.9003,
      "step": 314
    },
    {
      "epoch": 0.8333333333333334,
      "grad_norm": 0.30648961663246155,
      "learning_rate": 0.00011744340878828231,
      "loss": 0.9084,
      "step": 315
    },
    {
      "epoch": 0.8359788359788359,
      "grad_norm": 0.3145175278186798,
      "learning_rate": 0.00011717709720372836,
      "loss": 0.8657,
      "step": 316
    },
    {
      "epoch": 0.8386243386243386,
      "grad_norm": 0.3246476352214813,
      "learning_rate": 0.00011691078561917443,
      "loss": 0.9416,
      "step": 317
    },
    {
      "epoch": 0.8412698412698413,
      "grad_norm": 0.3097095489501953,
      "learning_rate": 0.0001166444740346205,
      "loss": 0.8838,
      "step": 318
    },
    {
      "epoch": 0.843915343915344,
      "grad_norm": 0.3214356601238251,
      "learning_rate": 0.00011637816245006659,
      "loss": 0.9613,
      "step": 319
    },
    {
      "epoch": 0.8465608465608465,
      "grad_norm": 0.3110521733760834,
      "learning_rate": 0.00011611185086551266,
      "loss": 0.872,
      "step": 320
    },
    {
      "epoch": 0.8492063492063492,
      "grad_norm": 0.3107962906360626,
      "learning_rate": 0.00011584553928095874,
      "loss": 0.8591,
      "step": 321
    },
    {
      "epoch": 0.8518518518518519,
      "grad_norm": 0.3125939965248108,
      "learning_rate": 0.0001155792276964048,
      "loss": 0.8487,
      "step": 322
    },
    {
      "epoch": 0.8544973544973545,
      "grad_norm": 0.3120926320552826,
      "learning_rate": 0.00011531291611185087,
      "loss": 0.8888,
      "step": 323
    },
    {
      "epoch": 0.8571428571428571,
      "grad_norm": 0.3102680444717407,
      "learning_rate": 0.00011504660452729694,
      "loss": 0.9248,
      "step": 324
    },
    {
      "epoch": 0.8597883597883598,
      "grad_norm": 0.32510465383529663,
      "learning_rate": 0.00011478029294274302,
      "loss": 0.8467,
      "step": 325
    },
    {
      "epoch": 0.8624338624338624,
      "grad_norm": 0.3208559453487396,
      "learning_rate": 0.0001145139813581891,
      "loss": 0.9072,
      "step": 326
    },
    {
      "epoch": 0.8650793650793651,
      "grad_norm": 0.3086027204990387,
      "learning_rate": 0.00011424766977363517,
      "loss": 0.9031,
      "step": 327
    },
    {
      "epoch": 0.8677248677248677,
      "grad_norm": 0.30609098076820374,
      "learning_rate": 0.00011398135818908122,
      "loss": 0.8754,
      "step": 328
    },
    {
      "epoch": 0.8703703703703703,
      "grad_norm": 0.30393800139427185,
      "learning_rate": 0.0001137150466045273,
      "loss": 0.8644,
      "step": 329
    },
    {
      "epoch": 0.873015873015873,
      "grad_norm": 0.32252949476242065,
      "learning_rate": 0.00011344873501997337,
      "loss": 0.9678,
      "step": 330
    },
    {
      "epoch": 0.8756613756613757,
      "grad_norm": 0.32479429244995117,
      "learning_rate": 0.00011318242343541945,
      "loss": 0.9522,
      "step": 331
    },
    {
      "epoch": 0.8783068783068783,
      "grad_norm": 0.33188411593437195,
      "learning_rate": 0.00011291611185086553,
      "loss": 0.856,
      "step": 332
    },
    {
      "epoch": 0.8809523809523809,
      "grad_norm": 0.31102216243743896,
      "learning_rate": 0.0001126498002663116,
      "loss": 0.8514,
      "step": 333
    },
    {
      "epoch": 0.8835978835978836,
      "grad_norm": 0.31838613748550415,
      "learning_rate": 0.00011238348868175766,
      "loss": 0.8702,
      "step": 334
    },
    {
      "epoch": 0.8862433862433863,
      "grad_norm": 0.30849918723106384,
      "learning_rate": 0.00011211717709720373,
      "loss": 0.9113,
      "step": 335
    },
    {
      "epoch": 0.8888888888888888,
      "grad_norm": 0.3029126822948456,
      "learning_rate": 0.0001118508655126498,
      "loss": 0.8938,
      "step": 336
    },
    {
      "epoch": 0.8915343915343915,
      "grad_norm": 0.3151121437549591,
      "learning_rate": 0.00011158455392809588,
      "loss": 0.7804,
      "step": 337
    },
    {
      "epoch": 0.8941798941798942,
      "grad_norm": 0.3065084218978882,
      "learning_rate": 0.00011131824234354196,
      "loss": 0.8461,
      "step": 338
    },
    {
      "epoch": 0.8968253968253969,
      "grad_norm": 0.31881242990493774,
      "learning_rate": 0.00011105193075898803,
      "loss": 0.8663,
      "step": 339
    },
    {
      "epoch": 0.8994708994708994,
      "grad_norm": 0.3325503170490265,
      "learning_rate": 0.00011078561917443409,
      "loss": 0.9429,
      "step": 340
    },
    {
      "epoch": 0.9021164021164021,
      "grad_norm": 0.34082451462745667,
      "learning_rate": 0.00011051930758988016,
      "loss": 0.9473,
      "step": 341
    },
    {
      "epoch": 0.9047619047619048,
      "grad_norm": 0.3197919428348541,
      "learning_rate": 0.00011025299600532624,
      "loss": 0.8412,
      "step": 342
    },
    {
      "epoch": 0.9074074074074074,
      "grad_norm": 0.3088037669658661,
      "learning_rate": 0.00010998668442077231,
      "loss": 0.8921,
      "step": 343
    },
    {
      "epoch": 0.91005291005291,
      "grad_norm": 0.3107798099517822,
      "learning_rate": 0.00010972037283621839,
      "loss": 0.9173,
      "step": 344
    },
    {
      "epoch": 0.9126984126984127,
      "grad_norm": 0.30695486068725586,
      "learning_rate": 0.00010945406125166447,
      "loss": 0.9331,
      "step": 345
    },
    {
      "epoch": 0.9153439153439153,
      "grad_norm": 0.3198622167110443,
      "learning_rate": 0.00010918774966711052,
      "loss": 0.8906,
      "step": 346
    },
    {
      "epoch": 0.917989417989418,
      "grad_norm": 0.32462507486343384,
      "learning_rate": 0.0001089214380825566,
      "loss": 0.8374,
      "step": 347
    },
    {
      "epoch": 0.9206349206349206,
      "grad_norm": 0.31046628952026367,
      "learning_rate": 0.00010865512649800267,
      "loss": 0.9048,
      "step": 348
    },
    {
      "epoch": 0.9232804232804233,
      "grad_norm": 0.3244028687477112,
      "learning_rate": 0.00010838881491344874,
      "loss": 0.9614,
      "step": 349
    },
    {
      "epoch": 0.9259259259259259,
      "grad_norm": 0.3224370777606964,
      "learning_rate": 0.00010812250332889482,
      "loss": 0.9251,
      "step": 350
    },
    {
      "epoch": 0.9285714285714286,
      "grad_norm": 0.3109060525894165,
      "learning_rate": 0.00010785619174434087,
      "loss": 0.8648,
      "step": 351
    },
    {
      "epoch": 0.9312169312169312,
      "grad_norm": 0.31656232476234436,
      "learning_rate": 0.00010758988015978695,
      "loss": 0.8297,
      "step": 352
    },
    {
      "epoch": 0.9338624338624338,
      "grad_norm": 0.306945264339447,
      "learning_rate": 0.00010732356857523303,
      "loss": 0.8688,
      "step": 353
    },
    {
      "epoch": 0.9365079365079365,
      "grad_norm": 0.331643283367157,
      "learning_rate": 0.0001070572569906791,
      "loss": 0.9514,
      "step": 354
    },
    {
      "epoch": 0.9391534391534392,
      "grad_norm": 0.3157375156879425,
      "learning_rate": 0.00010679094540612517,
      "loss": 0.8058,
      "step": 355
    },
    {
      "epoch": 0.9417989417989417,
      "grad_norm": 0.3229646384716034,
      "learning_rate": 0.00010652463382157125,
      "loss": 0.8638,
      "step": 356
    },
    {
      "epoch": 0.9444444444444444,
      "grad_norm": 0.303498238325119,
      "learning_rate": 0.0001062583222370173,
      "loss": 0.815,
      "step": 357
    },
    {
      "epoch": 0.9470899470899471,
      "grad_norm": 0.3123476505279541,
      "learning_rate": 0.00010599201065246338,
      "loss": 0.9172,
      "step": 358
    },
    {
      "epoch": 0.9497354497354498,
      "grad_norm": 0.3163852393627167,
      "learning_rate": 0.00010572569906790946,
      "loss": 0.9334,
      "step": 359
    },
    {
      "epoch": 0.9523809523809523,
      "grad_norm": 0.30825522541999817,
      "learning_rate": 0.00010545938748335554,
      "loss": 0.9344,
      "step": 360
    },
    {
      "epoch": 0.955026455026455,
      "grad_norm": 0.3105718791484833,
      "learning_rate": 0.0001051930758988016,
      "loss": 0.8228,
      "step": 361
    },
    {
      "epoch": 0.9576719576719577,
      "grad_norm": 0.32398635149002075,
      "learning_rate": 0.00010492676431424768,
      "loss": 0.8711,
      "step": 362
    },
    {
      "epoch": 0.9603174603174603,
      "grad_norm": 0.3219504654407501,
      "learning_rate": 0.00010466045272969373,
      "loss": 0.7968,
      "step": 363
    },
    {
      "epoch": 0.9629629629629629,
      "grad_norm": 0.3158860206604004,
      "learning_rate": 0.00010439414114513981,
      "loss": 0.8854,
      "step": 364
    },
    {
      "epoch": 0.9656084656084656,
      "grad_norm": 0.3176465630531311,
      "learning_rate": 0.00010412782956058589,
      "loss": 0.9361,
      "step": 365
    },
    {
      "epoch": 0.9682539682539683,
      "grad_norm": 0.3120768666267395,
      "learning_rate": 0.00010386151797603197,
      "loss": 0.884,
      "step": 366
    },
    {
      "epoch": 0.9708994708994709,
      "grad_norm": 0.31948578357696533,
      "learning_rate": 0.00010359520639147805,
      "loss": 0.8207,
      "step": 367
    },
    {
      "epoch": 0.9735449735449735,
      "grad_norm": 0.3134777247905731,
      "learning_rate": 0.00010332889480692411,
      "loss": 0.8526,
      "step": 368
    },
    {
      "epoch": 0.9761904761904762,
      "grad_norm": 0.3139598071575165,
      "learning_rate": 0.00010306258322237016,
      "loss": 0.8924,
      "step": 369
    },
    {
      "epoch": 0.9788359788359788,
      "grad_norm": 0.3183022737503052,
      "learning_rate": 0.00010279627163781624,
      "loss": 0.9376,
      "step": 370
    },
    {
      "epoch": 0.9814814814814815,
      "grad_norm": 0.31615549325942993,
      "learning_rate": 0.00010252996005326232,
      "loss": 0.8238,
      "step": 371
    },
    {
      "epoch": 0.9841269841269841,
      "grad_norm": 0.30896544456481934,
      "learning_rate": 0.0001022636484687084,
      "loss": 0.8639,
      "step": 372
    },
    {
      "epoch": 0.9867724867724867,
      "grad_norm": 0.3213864266872406,
      "learning_rate": 0.00010199733688415448,
      "loss": 0.9124,
      "step": 373
    },
    {
      "epoch": 0.9894179894179894,
      "grad_norm": 0.32356566190719604,
      "learning_rate": 0.00010173102529960054,
      "loss": 0.9131,
      "step": 374
    },
    {
      "epoch": 0.9920634920634921,
      "grad_norm": 0.3211658000946045,
      "learning_rate": 0.0001014647137150466,
      "loss": 0.8773,
      "step": 375
    },
    {
      "epoch": 0.9947089947089947,
      "grad_norm": 0.31017354130744934,
      "learning_rate": 0.00010119840213049267,
      "loss": 0.8117,
      "step": 376
    },
    {
      "epoch": 0.9973544973544973,
      "grad_norm": 0.30409058928489685,
      "learning_rate": 0.00010093209054593875,
      "loss": 0.9135,
      "step": 377
    },
    {
      "epoch": 1.0,
      "grad_norm": 0.3237709403038025,
      "learning_rate": 0.00010066577896138483,
      "loss": 0.8696,
      "step": 378
    },
    {
      "epoch": 1.0026455026455026,
      "grad_norm": 0.3148645758628845,
      "learning_rate": 0.00010039946737683091,
      "loss": 0.8633,
      "step": 379
    },
    {
      "epoch": 1.0052910052910053,
      "grad_norm": 0.32021912932395935,
      "learning_rate": 0.00010013315579227697,
      "loss": 0.9003,
      "step": 380
    },
    {
      "epoch": 1.007936507936508,
      "grad_norm": 0.3162664771080017,
      "learning_rate": 9.986684420772304e-05,
      "loss": 0.8486,
      "step": 381
    },
    {
      "epoch": 1.0105820105820107,
      "grad_norm": 0.3128553628921509,
      "learning_rate": 9.96005326231691e-05,
      "loss": 0.8784,
      "step": 382
    },
    {
      "epoch": 1.0132275132275133,
      "grad_norm": 0.3180355429649353,
      "learning_rate": 9.933422103861518e-05,
      "loss": 0.8478,
      "step": 383
    },
    {
      "epoch": 1.0158730158730158,
      "grad_norm": 0.3104771673679352,
      "learning_rate": 9.906790945406126e-05,
      "loss": 0.8665,
      "step": 384
    },
    {
      "epoch": 1.0185185185185186,
      "grad_norm": 0.31845471262931824,
      "learning_rate": 9.880159786950732e-05,
      "loss": 0.829,
      "step": 385
    },
    {
      "epoch": 1.0211640211640212,
      "grad_norm": 0.31884345412254333,
      "learning_rate": 9.85352862849534e-05,
      "loss": 0.8559,
      "step": 386
    },
    {
      "epoch": 1.0238095238095237,
      "grad_norm": 0.31813544034957886,
      "learning_rate": 9.826897470039947e-05,
      "loss": 0.8804,
      "step": 387
    },
    {
      "epoch": 1.0264550264550265,
      "grad_norm": 0.3196096420288086,
      "learning_rate": 9.800266311584553e-05,
      "loss": 0.7957,
      "step": 388
    },
    {
      "epoch": 1.029100529100529,
      "grad_norm": 0.3271837532520294,
      "learning_rate": 9.773635153129161e-05,
      "loss": 0.8686,
      "step": 389
    },
    {
      "epoch": 1.0317460317460316,
      "grad_norm": 0.32073357701301575,
      "learning_rate": 9.747003994673769e-05,
      "loss": 0.8246,
      "step": 390
    },
    {
      "epoch": 1.0343915343915344,
      "grad_norm": 0.3081476390361786,
      "learning_rate": 9.720372836218376e-05,
      "loss": 0.8931,
      "step": 391
    },
    {
      "epoch": 1.037037037037037,
      "grad_norm": 0.3177444636821747,
      "learning_rate": 9.693741677762983e-05,
      "loss": 0.9465,
      "step": 392
    },
    {
      "epoch": 1.0396825396825398,
      "grad_norm": 0.32710400223731995,
      "learning_rate": 9.667110519307591e-05,
      "loss": 0.9391,
      "step": 393
    },
    {
      "epoch": 1.0423280423280423,
      "grad_norm": 0.3129173219203949,
      "learning_rate": 9.640479360852196e-05,
      "loss": 0.8474,
      "step": 394
    },
    {
      "epoch": 1.0449735449735449,
      "grad_norm": 0.31410863995552063,
      "learning_rate": 9.613848202396804e-05,
      "loss": 0.8551,
      "step": 395
    },
    {
      "epoch": 1.0476190476190477,
      "grad_norm": 0.31652548909187317,
      "learning_rate": 9.587217043941412e-05,
      "loss": 0.856,
      "step": 396
    },
    {
      "epoch": 1.0502645502645502,
      "grad_norm": 0.31849780678749084,
      "learning_rate": 9.560585885486019e-05,
      "loss": 0.8683,
      "step": 397
    },
    {
      "epoch": 1.052910052910053,
      "grad_norm": 0.3421895503997803,
      "learning_rate": 9.533954727030626e-05,
      "loss": 0.8699,
      "step": 398
    },
    {
      "epoch": 1.0555555555555556,
      "grad_norm": 0.3203166425228119,
      "learning_rate": 9.507323568575234e-05,
      "loss": 0.8113,
      "step": 399
    },
    {
      "epoch": 1.0582010582010581,
      "grad_norm": 0.3179725110530853,
      "learning_rate": 9.480692410119841e-05,
      "loss": 0.874,
      "step": 400
    },
    {
      "epoch": 1.0582010582010581,
      "eval_loss": 0.8516913056373596,
      "eval_runtime": 11.6291,
      "eval_samples_per_second": 23.046,
      "eval_steps_per_second": 0.774,
      "step": 400
    },
    {
      "epoch": 1.060846560846561,
      "grad_norm": 0.31590548157691956,
      "learning_rate": 9.454061251664447e-05,
      "loss": 0.885,
      "step": 401
    },
    {
      "epoch": 1.0634920634920635,
      "grad_norm": 0.3276865482330322,
      "learning_rate": 9.427430093209055e-05,
      "loss": 0.8614,
      "step": 402
    },
    {
      "epoch": 1.066137566137566,
      "grad_norm": 0.3142230808734894,
      "learning_rate": 9.400798934753662e-05,
      "loss": 0.8978,
      "step": 403
    },
    {
      "epoch": 1.0687830687830688,
      "grad_norm": 0.32969969511032104,
      "learning_rate": 9.37416777629827e-05,
      "loss": 0.887,
      "step": 404
    },
    {
      "epoch": 1.0714285714285714,
      "grad_norm": 0.31840041279792786,
      "learning_rate": 9.347536617842877e-05,
      "loss": 0.8579,
      "step": 405
    },
    {
      "epoch": 1.074074074074074,
      "grad_norm": 0.31856468319892883,
      "learning_rate": 9.320905459387484e-05,
      "loss": 0.8731,
      "step": 406
    },
    {
      "epoch": 1.0767195767195767,
      "grad_norm": 0.32590749859809875,
      "learning_rate": 9.29427430093209e-05,
      "loss": 0.8437,
      "step": 407
    },
    {
      "epoch": 1.0793650793650793,
      "grad_norm": 0.3118874132633209,
      "learning_rate": 9.267643142476698e-05,
      "loss": 0.8442,
      "step": 408
    },
    {
      "epoch": 1.082010582010582,
      "grad_norm": 0.31248170137405396,
      "learning_rate": 9.241011984021305e-05,
      "loss": 0.8745,
      "step": 409
    },
    {
      "epoch": 1.0846560846560847,
      "grad_norm": 0.31846755743026733,
      "learning_rate": 9.214380825565913e-05,
      "loss": 0.8253,
      "step": 410
    },
    {
      "epoch": 1.0873015873015872,
      "grad_norm": 0.3225628137588501,
      "learning_rate": 9.18774966711052e-05,
      "loss": 0.8492,
      "step": 411
    },
    {
      "epoch": 1.08994708994709,
      "grad_norm": 0.3207807242870331,
      "learning_rate": 9.161118508655127e-05,
      "loss": 0.8983,
      "step": 412
    },
    {
      "epoch": 1.0925925925925926,
      "grad_norm": 0.32318314909935,
      "learning_rate": 9.134487350199734e-05,
      "loss": 0.8427,
      "step": 413
    },
    {
      "epoch": 1.0952380952380953,
      "grad_norm": 0.32747864723205566,
      "learning_rate": 9.107856191744341e-05,
      "loss": 0.8967,
      "step": 414
    },
    {
      "epoch": 1.097883597883598,
      "grad_norm": 0.31591561436653137,
      "learning_rate": 9.081225033288948e-05,
      "loss": 0.8035,
      "step": 415
    },
    {
      "epoch": 1.1005291005291005,
      "grad_norm": 0.3249380588531494,
      "learning_rate": 9.054593874833556e-05,
      "loss": 0.8868,
      "step": 416
    },
    {
      "epoch": 1.1031746031746033,
      "grad_norm": 0.32012879848480225,
      "learning_rate": 9.027962716378164e-05,
      "loss": 0.8975,
      "step": 417
    },
    {
      "epoch": 1.1058201058201058,
      "grad_norm": 0.31586870551109314,
      "learning_rate": 9.00133155792277e-05,
      "loss": 0.819,
      "step": 418
    },
    {
      "epoch": 1.1084656084656084,
      "grad_norm": 0.3292704224586487,
      "learning_rate": 8.974700399467377e-05,
      "loss": 0.8932,
      "step": 419
    },
    {
      "epoch": 1.1111111111111112,
      "grad_norm": 0.34102240204811096,
      "learning_rate": 8.948069241011984e-05,
      "loss": 0.803,
      "step": 420
    },
    {
      "epoch": 1.1137566137566137,
      "grad_norm": 0.30595862865448,
      "learning_rate": 8.921438082556591e-05,
      "loss": 0.8617,
      "step": 421
    },
    {
      "epoch": 1.1164021164021163,
      "grad_norm": 0.33740949630737305,
      "learning_rate": 8.894806924101199e-05,
      "loss": 0.8834,
      "step": 422
    },
    {
      "epoch": 1.119047619047619,
      "grad_norm": 0.3332139849662781,
      "learning_rate": 8.868175765645807e-05,
      "loss": 0.8966,
      "step": 423
    },
    {
      "epoch": 1.1216931216931216,
      "grad_norm": 0.3209734857082367,
      "learning_rate": 8.841544607190413e-05,
      "loss": 0.9129,
      "step": 424
    },
    {
      "epoch": 1.1243386243386244,
      "grad_norm": 0.3197973370552063,
      "learning_rate": 8.814913448735021e-05,
      "loss": 0.7912,
      "step": 425
    },
    {
      "epoch": 1.126984126984127,
      "grad_norm": 0.31822705268859863,
      "learning_rate": 8.788282290279628e-05,
      "loss": 0.8722,
      "step": 426
    },
    {
      "epoch": 1.1296296296296295,
      "grad_norm": 0.3177018165588379,
      "learning_rate": 8.761651131824234e-05,
      "loss": 0.8178,
      "step": 427
    },
    {
      "epoch": 1.1322751322751323,
      "grad_norm": 0.3154067397117615,
      "learning_rate": 8.735019973368842e-05,
      "loss": 0.8676,
      "step": 428
    },
    {
      "epoch": 1.1349206349206349,
      "grad_norm": 0.33664777874946594,
      "learning_rate": 8.70838881491345e-05,
      "loss": 0.8665,
      "step": 429
    },
    {
      "epoch": 1.1375661375661377,
      "grad_norm": 0.32683131098747253,
      "learning_rate": 8.681757656458056e-05,
      "loss": 0.8101,
      "step": 430
    },
    {
      "epoch": 1.1402116402116402,
      "grad_norm": 0.34172523021698,
      "learning_rate": 8.655126498002664e-05,
      "loss": 0.8536,
      "step": 431
    },
    {
      "epoch": 1.1428571428571428,
      "grad_norm": 0.31345099210739136,
      "learning_rate": 8.62849533954727e-05,
      "loss": 0.8747,
      "step": 432
    },
    {
      "epoch": 1.1455026455026456,
      "grad_norm": 0.3167164921760559,
      "learning_rate": 8.601864181091877e-05,
      "loss": 0.932,
      "step": 433
    },
    {
      "epoch": 1.1481481481481481,
      "grad_norm": 0.31196045875549316,
      "learning_rate": 8.575233022636485e-05,
      "loss": 0.7874,
      "step": 434
    },
    {
      "epoch": 1.1507936507936507,
      "grad_norm": 0.31165504455566406,
      "learning_rate": 8.548601864181093e-05,
      "loss": 0.8387,
      "step": 435
    },
    {
      "epoch": 1.1534391534391535,
      "grad_norm": 0.31014612317085266,
      "learning_rate": 8.5219707057257e-05,
      "loss": 0.9158,
      "step": 436
    },
    {
      "epoch": 1.156084656084656,
      "grad_norm": 0.3139340579509735,
      "learning_rate": 8.495339547270307e-05,
      "loss": 0.9543,
      "step": 437
    },
    {
      "epoch": 1.1587301587301586,
      "grad_norm": 0.3149397671222687,
      "learning_rate": 8.468708388814914e-05,
      "loss": 0.8386,
      "step": 438
    },
    {
      "epoch": 1.1613756613756614,
      "grad_norm": 0.3234405517578125,
      "learning_rate": 8.44207723035952e-05,
      "loss": 0.7986,
      "step": 439
    },
    {
      "epoch": 1.164021164021164,
      "grad_norm": 0.31493526697158813,
      "learning_rate": 8.415446071904128e-05,
      "loss": 0.7737,
      "step": 440
    },
    {
      "epoch": 1.1666666666666667,
      "grad_norm": 0.3196837902069092,
      "learning_rate": 8.388814913448736e-05,
      "loss": 0.8849,
      "step": 441
    },
    {
      "epoch": 1.1693121693121693,
      "grad_norm": 0.3210322856903076,
      "learning_rate": 8.362183754993342e-05,
      "loss": 0.8629,
      "step": 442
    },
    {
      "epoch": 1.1719576719576719,
      "grad_norm": 0.31657370924949646,
      "learning_rate": 8.33555259653795e-05,
      "loss": 0.8636,
      "step": 443
    },
    {
      "epoch": 1.1746031746031746,
      "grad_norm": 0.3244485557079315,
      "learning_rate": 8.308921438082558e-05,
      "loss": 0.8988,
      "step": 444
    },
    {
      "epoch": 1.1772486772486772,
      "grad_norm": 0.31535056233406067,
      "learning_rate": 8.282290279627163e-05,
      "loss": 0.892,
      "step": 445
    },
    {
      "epoch": 1.17989417989418,
      "grad_norm": 0.3205958306789398,
      "learning_rate": 8.255659121171771e-05,
      "loss": 0.8784,
      "step": 446
    },
    {
      "epoch": 1.1825396825396826,
      "grad_norm": 0.3162279427051544,
      "learning_rate": 8.229027962716379e-05,
      "loss": 0.8428,
      "step": 447
    },
    {
      "epoch": 1.1851851851851851,
      "grad_norm": 0.31702524423599243,
      "learning_rate": 8.202396804260986e-05,
      "loss": 0.8394,
      "step": 448
    },
    {
      "epoch": 1.187830687830688,
      "grad_norm": 0.31440240144729614,
      "learning_rate": 8.175765645805593e-05,
      "loss": 0.8092,
      "step": 449
    },
    {
      "epoch": 1.1904761904761905,
      "grad_norm": 0.32274869084358215,
      "learning_rate": 8.1491344873502e-05,
      "loss": 0.906,
      "step": 450
    },
    {
      "epoch": 1.193121693121693,
      "grad_norm": 0.32396557927131653,
      "learning_rate": 8.122503328894808e-05,
      "loss": 0.9387,
      "step": 451
    },
    {
      "epoch": 1.1957671957671958,
      "grad_norm": 0.31886565685272217,
      "learning_rate": 8.095872170439414e-05,
      "loss": 0.8968,
      "step": 452
    },
    {
      "epoch": 1.1984126984126984,
      "grad_norm": 0.3235061764717102,
      "learning_rate": 8.069241011984021e-05,
      "loss": 0.8643,
      "step": 453
    },
    {
      "epoch": 1.201058201058201,
      "grad_norm": 0.3323003053665161,
      "learning_rate": 8.042609853528629e-05,
      "loss": 0.8564,
      "step": 454
    },
    {
      "epoch": 1.2037037037037037,
      "grad_norm": 0.337063729763031,
      "learning_rate": 8.015978695073236e-05,
      "loss": 0.8935,
      "step": 455
    },
    {
      "epoch": 1.2063492063492063,
      "grad_norm": 0.3210991621017456,
      "learning_rate": 7.989347536617843e-05,
      "loss": 0.7591,
      "step": 456
    },
    {
      "epoch": 1.208994708994709,
      "grad_norm": 0.32644540071487427,
      "learning_rate": 7.962716378162451e-05,
      "loss": 0.9319,
      "step": 457
    },
    {
      "epoch": 1.2116402116402116,
      "grad_norm": 0.3317578434944153,
      "learning_rate": 7.936085219707057e-05,
      "loss": 0.8196,
      "step": 458
    },
    {
      "epoch": 1.2142857142857142,
      "grad_norm": 0.33129122853279114,
      "learning_rate": 7.909454061251664e-05,
      "loss": 0.8732,
      "step": 459
    },
    {
      "epoch": 1.216931216931217,
      "grad_norm": 0.3191198706626892,
      "learning_rate": 7.882822902796272e-05,
      "loss": 0.9185,
      "step": 460
    },
    {
      "epoch": 1.2195767195767195,
      "grad_norm": 0.31837740540504456,
      "learning_rate": 7.85619174434088e-05,
      "loss": 0.8629,
      "step": 461
    },
    {
      "epoch": 1.2222222222222223,
      "grad_norm": 0.31698229908943176,
      "learning_rate": 7.829560585885486e-05,
      "loss": 0.8063,
      "step": 462
    },
    {
      "epoch": 1.2248677248677249,
      "grad_norm": 0.32381999492645264,
      "learning_rate": 7.802929427430094e-05,
      "loss": 0.866,
      "step": 463
    },
    {
      "epoch": 1.2275132275132274,
      "grad_norm": 0.31696459650993347,
      "learning_rate": 7.7762982689747e-05,
      "loss": 0.8456,
      "step": 464
    },
    {
      "epoch": 1.2301587301587302,
      "grad_norm": 0.3213856518268585,
      "learning_rate": 7.749667110519307e-05,
      "loss": 0.8555,
      "step": 465
    },
    {
      "epoch": 1.2328042328042328,
      "grad_norm": 0.32701292634010315,
      "learning_rate": 7.723035952063915e-05,
      "loss": 0.9146,
      "step": 466
    },
    {
      "epoch": 1.2354497354497354,
      "grad_norm": 0.3126266300678253,
      "learning_rate": 7.696404793608523e-05,
      "loss": 0.8883,
      "step": 467
    },
    {
      "epoch": 1.2380952380952381,
      "grad_norm": 0.3237346410751343,
      "learning_rate": 7.669773635153129e-05,
      "loss": 0.7913,
      "step": 468
    },
    {
      "epoch": 1.2407407407407407,
      "grad_norm": 0.33496561646461487,
      "learning_rate": 7.643142476697737e-05,
      "loss": 0.9342,
      "step": 469
    },
    {
      "epoch": 1.2433862433862433,
      "grad_norm": 0.33312124013900757,
      "learning_rate": 7.616511318242345e-05,
      "loss": 0.9119,
      "step": 470
    },
    {
      "epoch": 1.246031746031746,
      "grad_norm": 0.3311595618724823,
      "learning_rate": 7.58988015978695e-05,
      "loss": 0.9134,
      "step": 471
    },
    {
      "epoch": 1.2486772486772486,
      "grad_norm": 0.3365480601787567,
      "learning_rate": 7.563249001331558e-05,
      "loss": 0.9129,
      "step": 472
    },
    {
      "epoch": 1.2513227513227514,
      "grad_norm": 0.31995654106140137,
      "learning_rate": 7.536617842876166e-05,
      "loss": 0.8455,
      "step": 473
    },
    {
      "epoch": 1.253968253968254,
      "grad_norm": 0.3335689902305603,
      "learning_rate": 7.509986684420772e-05,
      "loss": 0.837,
      "step": 474
    },
    {
      "epoch": 1.2566137566137567,
      "grad_norm": 0.3230437934398651,
      "learning_rate": 7.48335552596538e-05,
      "loss": 0.8783,
      "step": 475
    },
    {
      "epoch": 1.2592592592592593,
      "grad_norm": 0.3222460150718689,
      "learning_rate": 7.456724367509988e-05,
      "loss": 0.8545,
      "step": 476
    },
    {
      "epoch": 1.2619047619047619,
      "grad_norm": 0.3277588486671448,
      "learning_rate": 7.430093209054594e-05,
      "loss": 0.8708,
      "step": 477
    },
    {
      "epoch": 1.2645502645502646,
      "grad_norm": 0.31482937932014465,
      "learning_rate": 7.403462050599201e-05,
      "loss": 0.8718,
      "step": 478
    },
    {
      "epoch": 1.2671957671957672,
      "grad_norm": 0.32420259714126587,
      "learning_rate": 7.376830892143809e-05,
      "loss": 0.8029,
      "step": 479
    },
    {
      "epoch": 1.2698412698412698,
      "grad_norm": 0.34023338556289673,
      "learning_rate": 7.350199733688415e-05,
      "loss": 0.8324,
      "step": 480
    },
    {
      "epoch": 1.2724867724867726,
      "grad_norm": 0.3185613751411438,
      "learning_rate": 7.323568575233023e-05,
      "loss": 0.8229,
      "step": 481
    },
    {
      "epoch": 1.2751322751322751,
      "grad_norm": 0.3134364187717438,
      "learning_rate": 7.296937416777631e-05,
      "loss": 0.8687,
      "step": 482
    },
    {
      "epoch": 1.2777777777777777,
      "grad_norm": 0.3260653614997864,
      "learning_rate": 7.270306258322238e-05,
      "loss": 0.7999,
      "step": 483
    },
    {
      "epoch": 1.2804232804232805,
      "grad_norm": 0.32025063037872314,
      "learning_rate": 7.243675099866844e-05,
      "loss": 0.8369,
      "step": 484
    },
    {
      "epoch": 1.283068783068783,
      "grad_norm": 0.3076188862323761,
      "learning_rate": 7.217043941411452e-05,
      "loss": 0.8255,
      "step": 485
    },
    {
      "epoch": 1.2857142857142856,
      "grad_norm": 0.32809892296791077,
      "learning_rate": 7.190412782956058e-05,
      "loss": 0.8114,
      "step": 486
    },
    {
      "epoch": 1.2883597883597884,
      "grad_norm": 0.31926530599594116,
      "learning_rate": 7.163781624500666e-05,
      "loss": 0.8412,
      "step": 487
    },
    {
      "epoch": 1.291005291005291,
      "grad_norm": 0.33254778385162354,
      "learning_rate": 7.137150466045274e-05,
      "loss": 0.8284,
      "step": 488
    },
    {
      "epoch": 1.2936507936507937,
      "grad_norm": 0.3310684561729431,
      "learning_rate": 7.11051930758988e-05,
      "loss": 0.8243,
      "step": 489
    },
    {
      "epoch": 1.2962962962962963,
      "grad_norm": 0.34273821115493774,
      "learning_rate": 7.083888149134487e-05,
      "loss": 0.8279,
      "step": 490
    },
    {
      "epoch": 1.298941798941799,
      "grad_norm": 0.33402296900749207,
      "learning_rate": 7.057256990679095e-05,
      "loss": 0.8431,
      "step": 491
    },
    {
      "epoch": 1.3015873015873016,
      "grad_norm": 0.32236984372138977,
      "learning_rate": 7.030625832223702e-05,
      "loss": 0.8864,
      "step": 492
    },
    {
      "epoch": 1.3042328042328042,
      "grad_norm": 0.3301045000553131,
      "learning_rate": 7.00399467376831e-05,
      "loss": 0.864,
      "step": 493
    },
    {
      "epoch": 1.306878306878307,
      "grad_norm": 0.32722216844558716,
      "learning_rate": 6.977363515312917e-05,
      "loss": 0.8433,
      "step": 494
    },
    {
      "epoch": 1.3095238095238095,
      "grad_norm": 0.3198992609977722,
      "learning_rate": 6.950732356857524e-05,
      "loss": 0.8383,
      "step": 495
    },
    {
      "epoch": 1.312169312169312,
      "grad_norm": 0.32679814100265503,
      "learning_rate": 6.92410119840213e-05,
      "loss": 0.8525,
      "step": 496
    },
    {
      "epoch": 1.3148148148148149,
      "grad_norm": 0.3187161982059479,
      "learning_rate": 6.897470039946738e-05,
      "loss": 0.8842,
      "step": 497
    },
    {
      "epoch": 1.3174603174603174,
      "grad_norm": 0.3252648413181305,
      "learning_rate": 6.870838881491345e-05,
      "loss": 0.8541,
      "step": 498
    },
    {
      "epoch": 1.32010582010582,
      "grad_norm": 0.32383859157562256,
      "learning_rate": 6.844207723035952e-05,
      "loss": 0.8419,
      "step": 499
    },
    {
      "epoch": 1.3227513227513228,
      "grad_norm": 0.33675965666770935,
      "learning_rate": 6.81757656458056e-05,
      "loss": 0.8749,
      "step": 500
    }
  ],
  "logging_steps": 1,
  "max_steps": 756,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 2,
  "save_steps": 500,
  "total_flos": 1.476868259708928e+18,
  "train_batch_size": 4,
  "trial_name": null,
  "trial_params": null
}