{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 5.0,
  "eval_steps": 500,
  "global_step": 125,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.04,
      "grad_norm": 1.5257668495178223,
      "learning_rate": 2.857142857142857e-05,
      "loss": 0.9817,
      "step": 1
    },
    {
      "epoch": 0.08,
      "grad_norm": 1.4205083847045898,
      "learning_rate": 5.714285714285714e-05,
      "loss": 0.9677,
      "step": 2
    },
    {
      "epoch": 0.12,
      "grad_norm": 1.4500166177749634,
      "learning_rate": 8.571428571428571e-05,
      "loss": 0.9229,
      "step": 3
    },
    {
      "epoch": 0.16,
      "grad_norm": 1.1406153440475464,
      "learning_rate": 0.00011428571428571428,
      "loss": 0.8997,
      "step": 4
    },
    {
      "epoch": 0.2,
      "grad_norm": 0.9545271396636963,
      "learning_rate": 0.00014285714285714287,
      "loss": 0.8483,
      "step": 5
    },
    {
      "epoch": 0.24,
      "grad_norm": 0.8234877586364746,
      "learning_rate": 0.00017142857142857143,
      "loss": 0.8351,
      "step": 6
    },
    {
      "epoch": 0.28,
      "grad_norm": 0.6187587380409241,
      "learning_rate": 0.0002,
      "loss": 0.7575,
      "step": 7
    },
    {
      "epoch": 0.32,
      "grad_norm": 0.4950176775455475,
      "learning_rate": 0.00019996456111234527,
      "loss": 0.7344,
      "step": 8
    },
    {
      "epoch": 0.36,
      "grad_norm": 0.43441540002822876,
      "learning_rate": 0.0001998582695676762,
      "loss": 0.7035,
      "step": 9
    },
    {
      "epoch": 0.4,
      "grad_norm": 0.4230976402759552,
      "learning_rate": 0.000199681200703075,
      "loss": 0.7492,
      "step": 10
    },
    {
      "epoch": 0.44,
      "grad_norm": 0.3713449239730835,
      "learning_rate": 0.00019943348002101371,
      "loss": 0.6831,
      "step": 11
    },
    {
      "epoch": 0.48,
      "grad_norm": 0.3475893437862396,
      "learning_rate": 0.00019911528310040074,
      "loss": 0.7153,
      "step": 12
    },
    {
      "epoch": 0.52,
      "grad_norm": 0.3414737582206726,
      "learning_rate": 0.00019872683547213446,
      "loss": 0.6943,
      "step": 13
    },
    {
      "epoch": 0.56,
      "grad_norm": 0.3290707767009735,
      "learning_rate": 0.00019826841245925212,
      "loss": 0.6698,
      "step": 14
    },
    {
      "epoch": 0.6,
      "grad_norm": 0.3098256587982178,
      "learning_rate": 0.00019774033898178667,
      "loss": 0.6385,
      "step": 15
    },
    {
      "epoch": 0.64,
      "grad_norm": 0.31097927689552307,
      "learning_rate": 0.00019714298932647098,
      "loss": 0.6694,
      "step": 16
    },
    {
      "epoch": 0.68,
      "grad_norm": 0.32695478200912476,
      "learning_rate": 0.0001964767868814516,
      "loss": 0.6702,
      "step": 17
    },
    {
      "epoch": 0.72,
      "grad_norm": 0.30651360750198364,
      "learning_rate": 0.00019574220383620055,
      "loss": 0.6172,
      "step": 18
    },
    {
      "epoch": 0.76,
      "grad_norm": 0.31658628582954407,
      "learning_rate": 0.00019493976084683813,
      "loss": 0.6248,
      "step": 19
    },
    {
      "epoch": 0.8,
      "grad_norm": 0.30691343545913696,
      "learning_rate": 0.00019407002666710336,
      "loss": 0.6281,
      "step": 20
    },
    {
      "epoch": 0.84,
      "grad_norm": 0.29928600788116455,
      "learning_rate": 0.00019313361774523385,
      "loss": 0.6208,
      "step": 21
    },
    {
      "epoch": 0.88,
      "grad_norm": 0.30110830068588257,
      "learning_rate": 0.00019213119778704128,
      "loss": 0.5995,
      "step": 22
    },
    {
      "epoch": 0.92,
      "grad_norm": 0.2957627475261688,
      "learning_rate": 0.00019106347728549135,
      "loss": 0.6016,
      "step": 23
    },
    {
      "epoch": 0.96,
      "grad_norm": 0.29468321800231934,
      "learning_rate": 0.00018993121301712193,
      "loss": 0.5997,
      "step": 24
    },
    {
      "epoch": 1.0,
      "grad_norm": 0.2975432276725769,
      "learning_rate": 0.00018873520750565718,
      "loss": 0.6106,
      "step": 25
    },
    {
      "epoch": 1.04,
      "grad_norm": 0.31368955969810486,
      "learning_rate": 0.00018747630845319612,
      "loss": 0.4904,
      "step": 26
    },
    {
      "epoch": 1.08,
      "grad_norm": 0.31520742177963257,
      "learning_rate": 0.0001861554081393806,
      "loss": 0.5047,
      "step": 27
    },
    {
      "epoch": 1.12,
      "grad_norm": 0.3065387010574341,
      "learning_rate": 0.0001847734427889671,
      "loss": 0.4789,
      "step": 28
    },
    {
      "epoch": 1.16,
      "grad_norm": 0.2928008437156677,
      "learning_rate": 0.0001833313919082515,
      "loss": 0.4898,
      "step": 29
    },
    {
      "epoch": 1.2,
      "grad_norm": 0.2972809672355652,
      "learning_rate": 0.0001818302775908169,
      "loss": 0.4904,
      "step": 30
    },
    {
      "epoch": 1.24,
      "grad_norm": 0.2960495948791504,
      "learning_rate": 0.00018027116379309638,
      "loss": 0.4629,
      "step": 31
    },
    {
      "epoch": 1.28,
      "grad_norm": 0.28314685821533203,
      "learning_rate": 0.00017865515558026428,
      "loss": 0.4483,
      "step": 32
    },
    {
      "epoch": 1.32,
      "grad_norm": 0.2923860549926758,
      "learning_rate": 0.00017698339834299061,
      "loss": 0.4602,
      "step": 33
    },
    {
      "epoch": 1.3599999999999999,
      "grad_norm": 0.2865493893623352,
      "learning_rate": 0.00017525707698561385,
      "loss": 0.4565,
      "step": 34
    },
    {
      "epoch": 1.4,
      "grad_norm": 0.29644760489463806,
      "learning_rate": 0.00017347741508630672,
      "loss": 0.4491,
      "step": 35
    },
    {
      "epoch": 1.44,
      "grad_norm": 0.2860000729560852,
      "learning_rate": 0.00017164567402983152,
      "loss": 0.444,
      "step": 36
    },
    {
      "epoch": 1.48,
      "grad_norm": 0.2956458330154419,
      "learning_rate": 0.0001697631521134985,
      "loss": 0.464,
      "step": 37
    },
    {
      "epoch": 1.52,
      "grad_norm": 0.30596640706062317,
      "learning_rate": 0.00016783118362696163,
      "loss": 0.4596,
      "step": 38
    },
    {
      "epoch": 1.56,
      "grad_norm": 0.31658679246902466,
      "learning_rate": 0.00016585113790650388,
      "loss": 0.4184,
      "step": 39
    },
    {
      "epoch": 1.6,
      "grad_norm": 0.3067062497138977,
      "learning_rate": 0.00016382441836448202,
      "loss": 0.3952,
      "step": 40
    },
    {
      "epoch": 1.6400000000000001,
      "grad_norm": 0.30973076820373535,
      "learning_rate": 0.0001617524614946192,
      "loss": 0.4109,
      "step": 41
    },
    {
      "epoch": 1.6800000000000002,
      "grad_norm": 0.30597272515296936,
      "learning_rate": 0.00015963673585385016,
      "loss": 0.3853,
      "step": 42
    },
    {
      "epoch": 1.72,
      "grad_norm": 0.3238050639629364,
      "learning_rate": 0.0001574787410214407,
      "loss": 0.4074,
      "step": 43
    },
    {
      "epoch": 1.76,
      "grad_norm": 0.32239633798599243,
      "learning_rate": 0.00015528000653611935,
      "loss": 0.421,
      "step": 44
    },
    {
      "epoch": 1.8,
      "grad_norm": 0.322157084941864,
      "learning_rate": 0.00015304209081197425,
      "loss": 0.4156,
      "step": 45
    },
    {
      "epoch": 1.8399999999999999,
      "grad_norm": 0.32195115089416504,
      "learning_rate": 0.000150766580033884,
      "loss": 0.3955,
      "step": 46
    },
    {
      "epoch": 1.88,
      "grad_norm": 0.312031626701355,
      "learning_rate": 0.00014845508703326504,
      "loss": 0.3814,
      "step": 47
    },
    {
      "epoch": 1.92,
      "grad_norm": 0.31998252868652344,
      "learning_rate": 0.0001461092501449326,
      "loss": 0.4039,
      "step": 48
    },
    {
      "epoch": 1.96,
      "grad_norm": 0.32456570863723755,
      "learning_rate": 0.00014373073204588556,
      "loss": 0.3963,
      "step": 49
    },
    {
      "epoch": 2.0,
      "grad_norm": 0.32449814677238464,
      "learning_rate": 0.00014132121857683783,
      "loss": 0.3845,
      "step": 50
    },
    {
      "epoch": 2.04,
      "grad_norm": 0.31362128257751465,
      "learning_rate": 0.00013888241754733208,
      "loss": 0.3138,
      "step": 51
    },
    {
      "epoch": 2.08,
      "grad_norm": 0.30638328194618225,
      "learning_rate": 0.00013641605752528224,
      "loss": 0.317,
      "step": 52
    },
    {
      "epoch": 2.12,
      "grad_norm": 0.32126715779304504,
      "learning_rate": 0.00013392388661180303,
      "loss": 0.3004,
      "step": 53
    },
    {
      "epoch": 2.16,
      "grad_norm": 0.28879204392433167,
      "learning_rate": 0.0001314076712021949,
      "loss": 0.2997,
      "step": 54
    },
    {
      "epoch": 2.2,
      "grad_norm": 0.29814431071281433,
      "learning_rate": 0.0001288691947339621,
      "loss": 0.2934,
      "step": 55
    },
    {
      "epoch": 2.24,
      "grad_norm": 0.28737854957580566,
      "learning_rate": 0.00012631025642275212,
      "loss": 0.3185,
      "step": 56
    },
    {
      "epoch": 2.2800000000000002,
      "grad_norm": 0.30604204535484314,
      "learning_rate": 0.0001237326699871115,
      "loss": 0.3059,
      "step": 57
    },
    {
      "epoch": 2.32,
      "grad_norm": 0.2846826910972595,
      "learning_rate": 0.00012113826236296244,
      "loss": 0.2779,
      "step": 58
    },
    {
      "epoch": 2.36,
      "grad_norm": 0.3072626292705536,
      "learning_rate": 0.00011852887240871145,
      "loss": 0.2958,
      "step": 59
    },
    {
      "epoch": 2.4,
      "grad_norm": 0.30152225494384766,
      "learning_rate": 0.00011590634960190721,
      "loss": 0.276,
      "step": 60
    },
    {
      "epoch": 2.44,
      "grad_norm": 0.31316888332366943,
      "learning_rate": 0.00011327255272837221,
      "loss": 0.2863,
      "step": 61
    },
    {
      "epoch": 2.48,
      "grad_norm": 0.33458268642425537,
      "learning_rate": 0.00011062934856473655,
      "loss": 0.2999,
      "step": 62
    },
    {
      "epoch": 2.52,
      "grad_norm": 0.3459411561489105,
      "learning_rate": 0.00010797861055530831,
      "loss": 0.2861,
      "step": 63
    },
    {
      "epoch": 2.56,
      "grad_norm": 0.34091514348983765,
      "learning_rate": 0.00010532221748421787,
      "loss": 0.2697,
      "step": 64
    },
    {
      "epoch": 2.6,
      "grad_norm": 0.3289962708950043,
      "learning_rate": 0.00010266205214377748,
      "loss": 0.2722,
      "step": 65
    },
    {
      "epoch": 2.64,
      "grad_norm": 0.324381023645401,
      "learning_rate": 0.0001,
      "loss": 0.2864,
      "step": 66
    },
    {
      "epoch": 2.68,
      "grad_norm": 0.34481576085090637,
      "learning_rate": 9.733794785622253e-05,
      "loss": 0.3002,
      "step": 67
    },
    {
      "epoch": 2.7199999999999998,
      "grad_norm": 0.33097216486930847,
      "learning_rate": 9.467778251578217e-05,
      "loss": 0.2915,
      "step": 68
    },
    {
      "epoch": 2.76,
      "grad_norm": 0.3260320723056793,
      "learning_rate": 9.202138944469168e-05,
      "loss": 0.2962,
      "step": 69
    },
    {
      "epoch": 2.8,
      "grad_norm": 0.3088409900665283,
      "learning_rate": 8.937065143526347e-05,
      "loss": 0.2725,
      "step": 70
    },
    {
      "epoch": 2.84,
      "grad_norm": 0.32543686032295227,
      "learning_rate": 8.672744727162781e-05,
      "loss": 0.2916,
      "step": 71
    },
    {
      "epoch": 2.88,
      "grad_norm": 0.329887717962265,
      "learning_rate": 8.409365039809281e-05,
      "loss": 0.2883,
      "step": 72
    },
    {
      "epoch": 2.92,
      "grad_norm": 0.33566269278526306,
      "learning_rate": 8.147112759128859e-05,
      "loss": 0.2912,
      "step": 73
    },
    {
      "epoch": 2.96,
      "grad_norm": 0.31171417236328125,
      "learning_rate": 7.886173763703757e-05,
      "loss": 0.2812,
      "step": 74
    },
    {
      "epoch": 3.0,
      "grad_norm": 0.31463706493377686,
      "learning_rate": 7.626733001288851e-05,
      "loss": 0.289,
      "step": 75
    },
    {
      "epoch": 3.04,
      "grad_norm": 0.3288837671279907,
      "learning_rate": 7.368974357724789e-05,
      "loss": 0.2407,
      "step": 76
    },
    {
      "epoch": 3.08,
      "grad_norm": 0.3028244376182556,
      "learning_rate": 7.113080526603792e-05,
      "loss": 0.214,
      "step": 77
    },
    {
      "epoch": 3.12,
      "grad_norm": 0.31008780002593994,
      "learning_rate": 6.859232879780515e-05,
      "loss": 0.2133,
      "step": 78
    },
    {
      "epoch": 3.16,
      "grad_norm": 0.32053515315055847,
      "learning_rate": 6.607611338819697e-05,
      "loss": 0.209,
      "step": 79
    },
    {
      "epoch": 3.2,
      "grad_norm": 0.2950594425201416,
      "learning_rate": 6.358394247471778e-05,
      "loss": 0.213,
      "step": 80
    },
    {
      "epoch": 3.24,
      "grad_norm": 0.30111971497535706,
      "learning_rate": 6.111758245266794e-05,
      "loss": 0.2218,
      "step": 81
    },
    {
      "epoch": 3.2800000000000002,
      "grad_norm": 0.28454694151878357,
      "learning_rate": 5.867878142316221e-05,
      "loss": 0.2061,
      "step": 82
    },
    {
      "epoch": 3.32,
      "grad_norm": 0.29927462339401245,
      "learning_rate": 5.626926795411447e-05,
      "loss": 0.2181,
      "step": 83
    },
    {
      "epoch": 3.36,
      "grad_norm": 0.2855587899684906,
      "learning_rate": 5.38907498550674e-05,
      "loss": 0.2293,
      "step": 84
    },
    {
      "epoch": 3.4,
      "grad_norm": 0.2874046862125397,
      "learning_rate": 5.1544912966734994e-05,
      "loss": 0.2089,
      "step": 85
    },
    {
      "epoch": 3.44,
      "grad_norm": 0.3082650303840637,
      "learning_rate": 4.9233419966116036e-05,
      "loss": 0.213,
      "step": 86
    },
    {
      "epoch": 3.48,
      "grad_norm": 0.30149927735328674,
      "learning_rate": 4.695790918802576e-05,
      "loss": 0.2061,
      "step": 87
    },
    {
      "epoch": 3.52,
      "grad_norm": 0.32016074657440186,
      "learning_rate": 4.47199934638807e-05,
      "loss": 0.2284,
      "step": 88
    },
    {
      "epoch": 3.56,
      "grad_norm": 0.30953240394592285,
      "learning_rate": 4.252125897855932e-05,
      "loss": 0.2231,
      "step": 89
    },
    {
      "epoch": 3.6,
      "grad_norm": 0.2966735363006592,
      "learning_rate": 4.036326414614985e-05,
      "loss": 0.2047,
      "step": 90
    },
    {
      "epoch": 3.64,
      "grad_norm": 0.31812402606010437,
      "learning_rate": 3.824753850538082e-05,
      "loss": 0.2067,
      "step": 91
    },
    {
      "epoch": 3.68,
      "grad_norm": 0.3114762604236603,
      "learning_rate": 3.617558163551802e-05,
      "loss": 0.199,
      "step": 92
    },
    {
      "epoch": 3.7199999999999998,
      "grad_norm": 0.31614482402801514,
      "learning_rate": 3.414886209349615e-05,
      "loss": 0.2188,
      "step": 93
    },
    {
      "epoch": 3.76,
      "grad_norm": 0.2987557053565979,
      "learning_rate": 3.216881637303839e-05,
      "loss": 0.1926,
      "step": 94
    },
    {
      "epoch": 3.8,
      "grad_norm": 0.3159599304199219,
      "learning_rate": 3.0236847886501542e-05,
      "loss": 0.2143,
      "step": 95
    },
    {
      "epoch": 3.84,
      "grad_norm": 0.3066674470901489,
      "learning_rate": 2.8354325970168484e-05,
      "loss": 0.2035,
      "step": 96
    },
    {
      "epoch": 3.88,
      "grad_norm": 0.3181123435497284,
      "learning_rate": 2.6522584913693294e-05,
      "loss": 0.1922,
      "step": 97
    },
    {
      "epoch": 3.92,
      "grad_norm": 0.31559616327285767,
      "learning_rate": 2.4742923014386156e-05,
      "loss": 0.2322,
      "step": 98
    },
    {
      "epoch": 3.96,
      "grad_norm": 0.3333965539932251,
      "learning_rate": 2.301660165700936e-05,
      "loss": 0.2285,
      "step": 99
    },
    {
      "epoch": 4.0,
      "grad_norm": 0.30800747871398926,
      "learning_rate": 2.1344844419735755e-05,
      "loss": 0.2196,
      "step": 100
    },
    {
      "epoch": 4.04,
      "grad_norm": 0.28937435150146484,
      "learning_rate": 1.9728836206903656e-05,
      "loss": 0.1743,
      "step": 101
    },
    {
      "epoch": 4.08,
      "grad_norm": 0.2849326729774475,
      "learning_rate": 1.8169722409183097e-05,
      "loss": 0.1679,
      "step": 102
    },
    {
      "epoch": 4.12,
      "grad_norm": 0.28659793734550476,
      "learning_rate": 1.6668608091748495e-05,
      "loss": 0.193,
      "step": 103
    },
    {
      "epoch": 4.16,
      "grad_norm": 0.28456950187683105,
      "learning_rate": 1.522655721103291e-05,
      "loss": 0.1816,
      "step": 104
    },
    {
      "epoch": 4.2,
      "grad_norm": 0.2843972444534302,
      "learning_rate": 1.3844591860619383e-05,
      "loss": 0.1712,
      "step": 105
    },
    {
      "epoch": 4.24,
      "grad_norm": 0.28796839714050293,
      "learning_rate": 1.2523691546803873e-05,
      "loss": 0.1802,
      "step": 106
    },
    {
      "epoch": 4.28,
      "grad_norm": 0.2841332256793976,
      "learning_rate": 1.1264792494342857e-05,
      "loss": 0.1833,
      "step": 107
    },
    {
      "epoch": 4.32,
      "grad_norm": 0.2956565022468567,
      "learning_rate": 1.0068786982878087e-05,
      "loss": 0.1845,
      "step": 108
    },
    {
      "epoch": 4.36,
      "grad_norm": 0.28327876329421997,
      "learning_rate": 8.936522714508678e-06,
      "loss": 0.1769,
      "step": 109
    },
    {
      "epoch": 4.4,
      "grad_norm": 0.2768532335758209,
      "learning_rate": 7.868802212958703e-06,
      "loss": 0.1745,
      "step": 110
    },
    {
      "epoch": 4.44,
      "grad_norm": 0.27693644165992737,
      "learning_rate": 6.866382254766157e-06,
      "loss": 0.1818,
      "step": 111
    },
    {
      "epoch": 4.48,
      "grad_norm": 0.2891138792037964,
      "learning_rate": 5.929973332896677e-06,
      "loss": 0.1858,
      "step": 112
    },
    {
      "epoch": 4.52,
      "grad_norm": 0.2900177538394928,
      "learning_rate": 5.060239153161872e-06,
      "loss": 0.1811,
      "step": 113
    },
    {
      "epoch": 4.5600000000000005,
      "grad_norm": 0.27316245436668396,
      "learning_rate": 4.257796163799455e-06,
      "loss": 0.1609,
      "step": 114
    },
    {
      "epoch": 4.6,
      "grad_norm": 0.2771458923816681,
      "learning_rate": 3.5232131185484076e-06,
      "loss": 0.183,
      "step": 115
    },
    {
      "epoch": 4.64,
      "grad_norm": 0.28434255719184875,
      "learning_rate": 2.857010673529015e-06,
      "loss": 0.1834,
      "step": 116
    },
    {
      "epoch": 4.68,
      "grad_norm": 0.2891601026058197,
      "learning_rate": 2.259661018213333e-06,
      "loss": 0.1848,
      "step": 117
    },
    {
      "epoch": 4.72,
      "grad_norm": 0.2810252010822296,
      "learning_rate": 1.7315875407479032e-06,
      "loss": 0.1866,
      "step": 118
    },
    {
      "epoch": 4.76,
      "grad_norm": 0.28846290707588196,
      "learning_rate": 1.2731645278655445e-06,
      "loss": 0.1815,
      "step": 119
    },
    {
      "epoch": 4.8,
      "grad_norm": 0.2806852459907532,
      "learning_rate": 8.847168995992916e-07,
      "loss": 0.1865,
      "step": 120
    },
    {
      "epoch": 4.84,
      "grad_norm": 0.27965104579925537,
      "learning_rate": 5.665199789862907e-07,
      "loss": 0.1803,
      "step": 121
    },
    {
      "epoch": 4.88,
      "grad_norm": 0.2856048345565796,
      "learning_rate": 3.1879929692498757e-07,
      "loss": 0.1848,
      "step": 122
    },
    {
      "epoch": 4.92,
      "grad_norm": 0.2768332064151764,
      "learning_rate": 1.4173043232380557e-07,
      "loss": 0.1866,
      "step": 123
    },
    {
      "epoch": 4.96,
      "grad_norm": 0.2879635691642761,
      "learning_rate": 3.5438887654737355e-08,
      "loss": 0.1807,
      "step": 124
    },
    {
      "epoch": 5.0,
      "grad_norm": 0.2879068851470947,
      "learning_rate": 0.0,
      "loss": 0.1706,
      "step": 125
    }
  ],
  "logging_steps": 1,
  "max_steps": 125,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 5,
  "save_steps": 500,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 1.9085560601370624e+17,
  "train_batch_size": 1,
  "trial_name": null,
  "trial_params": null
}