{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 4.887459807073955,
  "eval_steps": 500,
  "global_step": 190,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.02572347266881029,
      "grad_norm": 268.0186767578125,
      "learning_rate": 5.000000000000001e-07,
      "loss": 8.3599,
      "num_input_tokens_seen": 7120,
      "step": 1
    },
    {
      "epoch": 0.05144694533762058,
      "grad_norm": 277.9050598144531,
      "learning_rate": 1.0000000000000002e-06,
      "loss": 8.1891,
      "num_input_tokens_seen": 13888,
      "step": 2
    },
    {
      "epoch": 0.07717041800643087,
      "grad_norm": 277.69873046875,
      "learning_rate": 1.5e-06,
      "loss": 8.0792,
      "num_input_tokens_seen": 20656,
      "step": 3
    },
    {
      "epoch": 0.10289389067524116,
      "grad_norm": 267.486328125,
      "learning_rate": 2.0000000000000003e-06,
      "loss": 7.9682,
      "num_input_tokens_seen": 27184,
      "step": 4
    },
    {
      "epoch": 0.12861736334405144,
      "grad_norm": 301.225830078125,
      "learning_rate": 2.5e-06,
      "loss": 6.9482,
      "num_input_tokens_seen": 34416,
      "step": 5
    },
    {
      "epoch": 0.15434083601286175,
      "grad_norm": 137.74415588378906,
      "learning_rate": 3e-06,
      "loss": 5.1505,
      "num_input_tokens_seen": 41056,
      "step": 6
    },
    {
      "epoch": 0.18006430868167203,
      "grad_norm": 113.7622299194336,
      "learning_rate": 3.5e-06,
      "loss": 4.7491,
      "num_input_tokens_seen": 47536,
      "step": 7
    },
    {
      "epoch": 0.2057877813504823,
      "grad_norm": 109.39883422851562,
      "learning_rate": 4.000000000000001e-06,
      "loss": 3.2164,
      "num_input_tokens_seen": 54464,
      "step": 8
    },
    {
      "epoch": 0.2315112540192926,
      "grad_norm": 119.0561294555664,
      "learning_rate": 4.5e-06,
      "loss": 2.7761,
      "num_input_tokens_seen": 61520,
      "step": 9
    },
    {
      "epoch": 0.2572347266881029,
      "grad_norm": 111.31031036376953,
      "learning_rate": 5e-06,
      "loss": 0.6703,
      "num_input_tokens_seen": 68464,
      "step": 10
    },
    {
      "epoch": 0.2829581993569132,
      "grad_norm": 39.81684494018555,
      "learning_rate": 4.9996192378909785e-06,
      "loss": 0.3255,
      "num_input_tokens_seen": 75152,
      "step": 11
    },
    {
      "epoch": 0.3086816720257235,
      "grad_norm": 41.08443069458008,
      "learning_rate": 4.99847706754774e-06,
      "loss": 0.3301,
      "num_input_tokens_seen": 81888,
      "step": 12
    },
    {
      "epoch": 0.33440514469453375,
      "grad_norm": 17.01146125793457,
      "learning_rate": 4.9965738368864345e-06,
      "loss": 0.2121,
      "num_input_tokens_seen": 88688,
      "step": 13
    },
    {
      "epoch": 0.36012861736334406,
      "grad_norm": 73.99099731445312,
      "learning_rate": 4.993910125649561e-06,
      "loss": 1.1565,
      "num_input_tokens_seen": 95616,
      "step": 14
    },
    {
      "epoch": 0.3858520900321543,
      "grad_norm": 114.83367919921875,
      "learning_rate": 4.990486745229364e-06,
      "loss": 0.8054,
      "num_input_tokens_seen": 102144,
      "step": 15
    },
    {
      "epoch": 0.4115755627009646,
      "grad_norm": 18.247591018676758,
      "learning_rate": 4.986304738420684e-06,
      "loss": 0.2386,
      "num_input_tokens_seen": 109120,
      "step": 16
    },
    {
      "epoch": 0.43729903536977494,
      "grad_norm": 27.782032012939453,
      "learning_rate": 4.981365379103306e-06,
      "loss": 0.3161,
      "num_input_tokens_seen": 115744,
      "step": 17
    },
    {
      "epoch": 0.4630225080385852,
      "grad_norm": 21.16512107849121,
      "learning_rate": 4.975670171853926e-06,
      "loss": 0.2773,
      "num_input_tokens_seen": 122704,
      "step": 18
    },
    {
      "epoch": 0.4887459807073955,
      "grad_norm": 6.738564491271973,
      "learning_rate": 4.9692208514878445e-06,
      "loss": 0.2062,
      "num_input_tokens_seen": 129552,
      "step": 19
    },
    {
      "epoch": 0.5144694533762058,
      "grad_norm": 3.6603872776031494,
      "learning_rate": 4.962019382530521e-06,
      "loss": 0.1837,
      "num_input_tokens_seen": 136544,
      "step": 20
    },
    {
      "epoch": 0.5401929260450161,
      "grad_norm": 10.339789390563965,
      "learning_rate": 4.9540679586191605e-06,
      "loss": 0.1735,
      "num_input_tokens_seen": 143488,
      "step": 21
    },
    {
      "epoch": 0.5659163987138264,
      "grad_norm": 4.833702087402344,
      "learning_rate": 4.9453690018345144e-06,
      "loss": 0.1588,
      "num_input_tokens_seen": 150224,
      "step": 22
    },
    {
      "epoch": 0.5916398713826366,
      "grad_norm": 4.9161152839660645,
      "learning_rate": 4.935925161963089e-06,
      "loss": 0.1443,
      "num_input_tokens_seen": 157232,
      "step": 23
    },
    {
      "epoch": 0.617363344051447,
      "grad_norm": 9.033807754516602,
      "learning_rate": 4.925739315689991e-06,
      "loss": 0.157,
      "num_input_tokens_seen": 163776,
      "step": 24
    },
    {
      "epoch": 0.6430868167202572,
      "grad_norm": 4.518654823303223,
      "learning_rate": 4.914814565722671e-06,
      "loss": 0.1199,
      "num_input_tokens_seen": 170352,
      "step": 25
    },
    {
      "epoch": 0.6688102893890675,
      "grad_norm": 10.43909740447998,
      "learning_rate": 4.903154239845798e-06,
      "loss": 0.1539,
      "num_input_tokens_seen": 177120,
      "step": 26
    },
    {
      "epoch": 0.6945337620578779,
      "grad_norm": 9.000858306884766,
      "learning_rate": 4.890761889907589e-06,
      "loss": 0.1208,
      "num_input_tokens_seen": 184096,
      "step": 27
    },
    {
      "epoch": 0.7202572347266881,
      "grad_norm": 3.3685858249664307,
      "learning_rate": 4.8776412907378845e-06,
      "loss": 0.0954,
      "num_input_tokens_seen": 191040,
      "step": 28
    },
    {
      "epoch": 0.7459807073954984,
      "grad_norm": 6.876232147216797,
      "learning_rate": 4.863796438998293e-06,
      "loss": 0.1387,
      "num_input_tokens_seen": 198064,
      "step": 29
    },
    {
      "epoch": 0.7717041800643086,
      "grad_norm": 11.019433975219727,
      "learning_rate": 4.849231551964771e-06,
      "loss": 0.1484,
      "num_input_tokens_seen": 205136,
      "step": 30
    },
    {
      "epoch": 0.797427652733119,
      "grad_norm": 4.780524730682373,
      "learning_rate": 4.833951066243004e-06,
      "loss": 0.0998,
      "num_input_tokens_seen": 212000,
      "step": 31
    },
    {
      "epoch": 0.8231511254019293,
      "grad_norm": 3.613060235977173,
      "learning_rate": 4.817959636416969e-06,
      "loss": 0.1068,
      "num_input_tokens_seen": 218720,
      "step": 32
    },
    {
      "epoch": 0.8488745980707395,
      "grad_norm": 5.576949596405029,
      "learning_rate": 4.801262133631101e-06,
      "loss": 0.0801,
      "num_input_tokens_seen": 225856,
      "step": 33
    },
    {
      "epoch": 0.8745980707395499,
      "grad_norm": 3.3204915523529053,
      "learning_rate": 4.783863644106502e-06,
      "loss": 0.1066,
      "num_input_tokens_seen": 232640,
      "step": 34
    },
    {
      "epoch": 0.9003215434083601,
      "grad_norm": 3.090853452682495,
      "learning_rate": 4.765769467591626e-06,
      "loss": 0.1038,
      "num_input_tokens_seen": 239504,
      "step": 35
    },
    {
      "epoch": 0.9260450160771704,
      "grad_norm": 6.979610443115234,
      "learning_rate": 4.746985115747918e-06,
      "loss": 0.106,
      "num_input_tokens_seen": 246288,
      "step": 36
    },
    {
      "epoch": 0.9517684887459807,
      "grad_norm": 3.491868495941162,
      "learning_rate": 4.72751631047092e-06,
      "loss": 0.1107,
      "num_input_tokens_seen": 253136,
      "step": 37
    },
    {
      "epoch": 0.977491961414791,
      "grad_norm": 6.108020782470703,
      "learning_rate": 4.707368982147318e-06,
      "loss": 0.1372,
      "num_input_tokens_seen": 260160,
      "step": 38
    },
    {
      "epoch": 1.0032154340836013,
      "grad_norm": 1.9764081239700317,
      "learning_rate": 4.68654926784849e-06,
      "loss": 0.0816,
      "num_input_tokens_seen": 267120,
      "step": 39
    },
    {
      "epoch": 1.0289389067524115,
      "grad_norm": 2.5603554248809814,
      "learning_rate": 4.665063509461098e-06,
      "loss": 0.0743,
      "num_input_tokens_seen": 274112,
      "step": 40
    },
    {
      "epoch": 1.0546623794212218,
      "grad_norm": 5.457398414611816,
      "learning_rate": 4.642918251755281e-06,
      "loss": 0.072,
      "num_input_tokens_seen": 281136,
      "step": 41
    },
    {
      "epoch": 1.0803858520900322,
      "grad_norm": 4.488720417022705,
      "learning_rate": 4.620120240391065e-06,
      "loss": 0.0596,
      "num_input_tokens_seen": 288048,
      "step": 42
    },
    {
      "epoch": 1.1061093247588425,
      "grad_norm": 2.8057987689971924,
      "learning_rate": 4.596676419863561e-06,
      "loss": 0.0544,
      "num_input_tokens_seen": 295120,
      "step": 43
    },
    {
      "epoch": 1.1318327974276527,
      "grad_norm": 2.921278476715088,
      "learning_rate": 4.572593931387604e-06,
      "loss": 0.0342,
      "num_input_tokens_seen": 302000,
      "step": 44
    },
    {
      "epoch": 1.157556270096463,
      "grad_norm": 2.9281697273254395,
      "learning_rate": 4.54788011072248e-06,
      "loss": 0.0394,
      "num_input_tokens_seen": 308672,
      "step": 45
    },
    {
      "epoch": 1.1832797427652733,
      "grad_norm": 4.087917327880859,
      "learning_rate": 4.522542485937369e-06,
      "loss": 0.0196,
      "num_input_tokens_seen": 315600,
      "step": 46
    },
    {
      "epoch": 1.2090032154340835,
      "grad_norm": 3.390829086303711,
      "learning_rate": 4.496588775118232e-06,
      "loss": 0.0411,
      "num_input_tokens_seen": 322464,
      "step": 47
    },
    {
      "epoch": 1.234726688102894,
      "grad_norm": 4.550433158874512,
      "learning_rate": 4.470026884016805e-06,
      "loss": 0.0257,
      "num_input_tokens_seen": 329024,
      "step": 48
    },
    {
      "epoch": 1.2604501607717042,
      "grad_norm": 6.6677446365356445,
      "learning_rate": 4.442864903642428e-06,
      "loss": 0.0289,
      "num_input_tokens_seen": 336032,
      "step": 49
    },
    {
      "epoch": 1.2861736334405145,
      "grad_norm": 7.874734878540039,
      "learning_rate": 4.415111107797445e-06,
      "loss": 0.1193,
      "num_input_tokens_seen": 342704,
      "step": 50
    },
    {
      "epoch": 1.3118971061093248,
      "grad_norm": 5.971132278442383,
      "learning_rate": 4.386773950556931e-06,
      "loss": 0.0883,
      "num_input_tokens_seen": 349472,
      "step": 51
    },
    {
      "epoch": 1.337620578778135,
      "grad_norm": 4.0566725730896,
      "learning_rate": 4.357862063693486e-06,
      "loss": 0.0377,
      "num_input_tokens_seen": 356272,
      "step": 52
    },
    {
      "epoch": 1.3633440514469453,
      "grad_norm": 5.443573474884033,
      "learning_rate": 4.328384254047927e-06,
      "loss": 0.0602,
      "num_input_tokens_seen": 363040,
      "step": 53
    },
    {
      "epoch": 1.3890675241157555,
      "grad_norm": 6.038252353668213,
      "learning_rate": 4.2983495008466285e-06,
      "loss": 0.083,
      "num_input_tokens_seen": 369664,
      "step": 54
    },
    {
      "epoch": 1.414790996784566,
      "grad_norm": 2.8046696186065674,
      "learning_rate": 4.267766952966369e-06,
      "loss": 0.0358,
      "num_input_tokens_seen": 376704,
      "step": 55
    },
    {
      "epoch": 1.4405144694533762,
      "grad_norm": 2.451719284057617,
      "learning_rate": 4.236645926147493e-06,
      "loss": 0.0321,
      "num_input_tokens_seen": 383600,
      "step": 56
    },
    {
      "epoch": 1.4662379421221865,
      "grad_norm": 3.4111475944519043,
      "learning_rate": 4.204995900156247e-06,
      "loss": 0.0452,
      "num_input_tokens_seen": 390592,
      "step": 57
    },
    {
      "epoch": 1.4919614147909968,
      "grad_norm": 3.065139055252075,
      "learning_rate": 4.172826515897146e-06,
      "loss": 0.0915,
      "num_input_tokens_seen": 397360,
      "step": 58
    },
    {
      "epoch": 1.517684887459807,
      "grad_norm": 3.0692198276519775,
      "learning_rate": 4.140147572476269e-06,
      "loss": 0.0651,
      "num_input_tokens_seen": 404048,
      "step": 59
    },
    {
      "epoch": 1.5434083601286175,
      "grad_norm": 3.6201350688934326,
      "learning_rate": 4.106969024216348e-06,
      "loss": 0.0868,
      "num_input_tokens_seen": 410960,
      "step": 60
    },
    {
      "epoch": 1.5691318327974275,
      "grad_norm": 2.289900779724121,
      "learning_rate": 4.073300977624594e-06,
      "loss": 0.0554,
      "num_input_tokens_seen": 417888,
      "step": 61
    },
    {
      "epoch": 1.594855305466238,
      "grad_norm": 1.4743808507919312,
      "learning_rate": 4.039153688314146e-06,
      "loss": 0.0336,
      "num_input_tokens_seen": 424880,
      "step": 62
    },
    {
      "epoch": 1.6205787781350482,
      "grad_norm": 2.1891098022460938,
      "learning_rate": 4.0045375578801216e-06,
      "loss": 0.0455,
      "num_input_tokens_seen": 432000,
      "step": 63
    },
    {
      "epoch": 1.6463022508038585,
      "grad_norm": 1.8203191757202148,
      "learning_rate": 3.969463130731183e-06,
      "loss": 0.0406,
      "num_input_tokens_seen": 438672,
      "step": 64
    },
    {
      "epoch": 1.6720257234726688,
      "grad_norm": 2.453317165374756,
      "learning_rate": 3.933941090877615e-06,
      "loss": 0.0461,
      "num_input_tokens_seen": 445440,
      "step": 65
    },
    {
      "epoch": 1.697749196141479,
      "grad_norm": 2.035806894302368,
      "learning_rate": 3.897982258676867e-06,
      "loss": 0.0466,
      "num_input_tokens_seen": 452064,
      "step": 66
    },
    {
      "epoch": 1.7234726688102895,
      "grad_norm": 3.169175386428833,
      "learning_rate": 3.861597587537568e-06,
      "loss": 0.0382,
      "num_input_tokens_seen": 458992,
      "step": 67
    },
    {
      "epoch": 1.7491961414790995,
      "grad_norm": 2.0320234298706055,
      "learning_rate": 3.824798160583012e-06,
      "loss": 0.0426,
      "num_input_tokens_seen": 465568,
      "step": 68
    },
    {
      "epoch": 1.77491961414791,
      "grad_norm": 4.094840049743652,
      "learning_rate": 3.787595187275136e-06,
      "loss": 0.0264,
      "num_input_tokens_seen": 472496,
      "step": 69
    },
    {
      "epoch": 1.8006430868167203,
      "grad_norm": 4.245150089263916,
      "learning_rate": 3.7500000000000005e-06,
      "loss": 0.0567,
      "num_input_tokens_seen": 479392,
      "step": 70
    },
    {
      "epoch": 1.8263665594855305,
      "grad_norm": 3.226271152496338,
      "learning_rate": 3.7120240506158433e-06,
      "loss": 0.0688,
      "num_input_tokens_seen": 486416,
      "step": 71
    },
    {
      "epoch": 1.852090032154341,
      "grad_norm": 2.070322275161743,
      "learning_rate": 3.6736789069647273e-06,
      "loss": 0.0351,
      "num_input_tokens_seen": 492896,
      "step": 72
    },
    {
      "epoch": 1.877813504823151,
      "grad_norm": 2.4622035026550293,
      "learning_rate": 3.634976249348867e-06,
      "loss": 0.0246,
      "num_input_tokens_seen": 499760,
      "step": 73
    },
    {
      "epoch": 1.9035369774919615,
      "grad_norm": 3.902181625366211,
      "learning_rate": 3.595927866972694e-06,
      "loss": 0.0364,
      "num_input_tokens_seen": 506816,
      "step": 74
    },
    {
      "epoch": 1.9292604501607717,
      "grad_norm": 4.0147480964660645,
      "learning_rate": 3.556545654351749e-06,
      "loss": 0.0352,
      "num_input_tokens_seen": 513648,
      "step": 75
    },
    {
      "epoch": 1.954983922829582,
      "grad_norm": 3.6791763305664062,
      "learning_rate": 3.516841607689501e-06,
      "loss": 0.0915,
      "num_input_tokens_seen": 520480,
      "step": 76
    },
    {
      "epoch": 1.9807073954983923,
      "grad_norm": 1.641350269317627,
      "learning_rate": 3.476827821223184e-06,
      "loss": 0.0327,
      "num_input_tokens_seen": 527056,
      "step": 77
    },
    {
      "epoch": 2.0064308681672025,
      "grad_norm": 3.6227402687072754,
      "learning_rate": 3.436516483539781e-06,
      "loss": 0.0448,
      "num_input_tokens_seen": 534112,
      "step": 78
    },
    {
      "epoch": 2.032154340836013,
      "grad_norm": 1.654789924621582,
      "learning_rate": 3.39591987386325e-06,
      "loss": 0.0186,
      "num_input_tokens_seen": 541024,
      "step": 79
    },
    {
      "epoch": 2.057877813504823,
      "grad_norm": 2.0418519973754883,
      "learning_rate": 3.3550503583141726e-06,
      "loss": 0.0342,
      "num_input_tokens_seen": 547888,
      "step": 80
    },
    {
      "epoch": 2.0836012861736335,
      "grad_norm": 1.0242717266082764,
      "learning_rate": 3.313920386142892e-06,
      "loss": 0.0079,
      "num_input_tokens_seen": 554592,
      "step": 81
    },
    {
      "epoch": 2.1093247588424435,
      "grad_norm": 1.59933602809906,
      "learning_rate": 3.272542485937369e-06,
      "loss": 0.0177,
      "num_input_tokens_seen": 561296,
      "step": 82
    },
    {
      "epoch": 2.135048231511254,
      "grad_norm": 1.83909273147583,
      "learning_rate": 3.230929261806842e-06,
      "loss": 0.0139,
      "num_input_tokens_seen": 567872,
      "step": 83
    },
    {
      "epoch": 2.1607717041800645,
      "grad_norm": 1.933048963546753,
      "learning_rate": 3.189093389542498e-06,
      "loss": 0.0103,
      "num_input_tokens_seen": 575072,
      "step": 84
    },
    {
      "epoch": 2.1864951768488745,
      "grad_norm": 2.1397433280944824,
      "learning_rate": 3.147047612756302e-06,
      "loss": 0.0221,
      "num_input_tokens_seen": 582080,
      "step": 85
    },
    {
      "epoch": 2.212218649517685,
      "grad_norm": 0.7958673238754272,
      "learning_rate": 3.1048047389991693e-06,
      "loss": 0.0021,
      "num_input_tokens_seen": 588816,
      "step": 86
    },
    {
      "epoch": 2.237942122186495,
      "grad_norm": 1.8060617446899414,
      "learning_rate": 3.062377635859663e-06,
      "loss": 0.011,
      "num_input_tokens_seen": 596032,
      "step": 87
    },
    {
      "epoch": 2.2636655948553055,
      "grad_norm": 1.7997971773147583,
      "learning_rate": 3.019779227044398e-06,
      "loss": 0.0081,
      "num_input_tokens_seen": 602672,
      "step": 88
    },
    {
      "epoch": 2.289389067524116,
      "grad_norm": 2.0229434967041016,
      "learning_rate": 2.9770224884413625e-06,
      "loss": 0.0149,
      "num_input_tokens_seen": 609424,
      "step": 89
    },
    {
      "epoch": 2.315112540192926,
      "grad_norm": 0.5248342156410217,
      "learning_rate": 2.9341204441673267e-06,
      "loss": 0.001,
      "num_input_tokens_seen": 616448,
      "step": 90
    },
    {
      "epoch": 2.3408360128617365,
      "grad_norm": 1.1899443864822388,
      "learning_rate": 2.8910861626005774e-06,
      "loss": 0.007,
      "num_input_tokens_seen": 623296,
      "step": 91
    },
    {
      "epoch": 2.3665594855305465,
      "grad_norm": 3.1920082569122314,
      "learning_rate": 2.847932752400164e-06,
      "loss": 0.0089,
      "num_input_tokens_seen": 630064,
      "step": 92
    },
    {
      "epoch": 2.392282958199357,
      "grad_norm": 0.37337368726730347,
      "learning_rate": 2.804673358512869e-06,
      "loss": 0.0013,
      "num_input_tokens_seen": 637088,
      "step": 93
    },
    {
      "epoch": 2.418006430868167,
      "grad_norm": 4.124266147613525,
      "learning_rate": 2.761321158169134e-06,
      "loss": 0.0267,
      "num_input_tokens_seen": 644080,
      "step": 94
    },
    {
      "epoch": 2.4437299035369775,
      "grad_norm": 1.9108864068984985,
      "learning_rate": 2.717889356869146e-06,
      "loss": 0.0171,
      "num_input_tokens_seen": 650848,
      "step": 95
    },
    {
      "epoch": 2.469453376205788,
      "grad_norm": 3.225116729736328,
      "learning_rate": 2.6743911843603134e-06,
      "loss": 0.0375,
      "num_input_tokens_seen": 657424,
      "step": 96
    },
    {
      "epoch": 2.495176848874598,
      "grad_norm": 1.8133978843688965,
      "learning_rate": 2.6308398906073603e-06,
      "loss": 0.0101,
      "num_input_tokens_seen": 664128,
      "step": 97
    },
    {
      "epoch": 2.5209003215434085,
      "grad_norm": 3.179337739944458,
      "learning_rate": 2.587248741756253e-06,
      "loss": 0.0282,
      "num_input_tokens_seen": 671120,
      "step": 98
    },
    {
      "epoch": 2.5466237942122185,
      "grad_norm": 1.5852500200271606,
      "learning_rate": 2.543631016093209e-06,
      "loss": 0.0069,
      "num_input_tokens_seen": 677920,
      "step": 99
    },
    {
      "epoch": 2.572347266881029,
      "grad_norm": 2.1428685188293457,
      "learning_rate": 2.5e-06,
      "loss": 0.0135,
      "num_input_tokens_seen": 684960,
      "step": 100
    },
    {
      "epoch": 2.598070739549839,
      "grad_norm": 1.0775537490844727,
      "learning_rate": 2.4563689839067913e-06,
      "loss": 0.0062,
      "num_input_tokens_seen": 691856,
      "step": 101
    },
    {
      "epoch": 2.6237942122186495,
      "grad_norm": 1.5073256492614746,
      "learning_rate": 2.4127512582437486e-06,
      "loss": 0.005,
      "num_input_tokens_seen": 698512,
      "step": 102
    },
    {
      "epoch": 2.64951768488746,
      "grad_norm": 1.7251828908920288,
      "learning_rate": 2.3691601093926406e-06,
      "loss": 0.0285,
      "num_input_tokens_seen": 705440,
      "step": 103
    },
    {
      "epoch": 2.67524115755627,
      "grad_norm": 2.271348237991333,
      "learning_rate": 2.325608815639687e-06,
      "loss": 0.0225,
      "num_input_tokens_seen": 712528,
      "step": 104
    },
    {
      "epoch": 2.7009646302250805,
      "grad_norm": 0.9558768272399902,
      "learning_rate": 2.2821106431308546e-06,
      "loss": 0.028,
      "num_input_tokens_seen": 719168,
      "step": 105
    },
    {
      "epoch": 2.7266881028938905,
      "grad_norm": 2.1378886699676514,
      "learning_rate": 2.238678841830867e-06,
      "loss": 0.0176,
      "num_input_tokens_seen": 725904,
      "step": 106
    },
    {
      "epoch": 2.752411575562701,
      "grad_norm": 0.9674012660980225,
      "learning_rate": 2.195326641487132e-06,
      "loss": 0.0047,
      "num_input_tokens_seen": 732480,
      "step": 107
    },
    {
      "epoch": 2.778135048231511,
      "grad_norm": 0.6068861484527588,
      "learning_rate": 2.1520672475998374e-06,
      "loss": 0.0135,
      "num_input_tokens_seen": 739184,
      "step": 108
    },
    {
      "epoch": 2.8038585209003215,
      "grad_norm": 0.833519458770752,
      "learning_rate": 2.1089138373994226e-06,
      "loss": 0.0044,
      "num_input_tokens_seen": 746320,
      "step": 109
    },
    {
      "epoch": 2.829581993569132,
      "grad_norm": 1.4018948078155518,
      "learning_rate": 2.0658795558326745e-06,
      "loss": 0.0252,
      "num_input_tokens_seen": 753136,
      "step": 110
    },
    {
      "epoch": 2.855305466237942,
      "grad_norm": 1.5698492527008057,
      "learning_rate": 2.022977511558638e-06,
      "loss": 0.0249,
      "num_input_tokens_seen": 760096,
      "step": 111
    },
    {
      "epoch": 2.8810289389067525,
      "grad_norm": 2.051377534866333,
      "learning_rate": 1.9802207729556023e-06,
      "loss": 0.0146,
      "num_input_tokens_seen": 767104,
      "step": 112
    },
    {
      "epoch": 2.906752411575563,
      "grad_norm": 0.48683854937553406,
      "learning_rate": 1.937622364140338e-06,
      "loss": 0.0044,
      "num_input_tokens_seen": 773872,
      "step": 113
    },
    {
      "epoch": 2.932475884244373,
      "grad_norm": 0.9895896911621094,
      "learning_rate": 1.895195261000831e-06,
      "loss": 0.0054,
      "num_input_tokens_seen": 780736,
      "step": 114
    },
    {
      "epoch": 2.958199356913183,
      "grad_norm": 0.8025338053703308,
      "learning_rate": 1.852952387243698e-06,
      "loss": 0.0106,
      "num_input_tokens_seen": 787424,
      "step": 115
    },
    {
      "epoch": 2.9839228295819935,
      "grad_norm": 1.7318856716156006,
      "learning_rate": 1.8109066104575023e-06,
      "loss": 0.0167,
      "num_input_tokens_seen": 794224,
      "step": 116
    },
    {
      "epoch": 3.009646302250804,
      "grad_norm": 1.5407195091247559,
      "learning_rate": 1.7690707381931585e-06,
      "loss": 0.009,
      "num_input_tokens_seen": 801088,
      "step": 117
    },
    {
      "epoch": 3.035369774919614,
      "grad_norm": 0.25947141647338867,
      "learning_rate": 1.7274575140626318e-06,
      "loss": 0.0024,
      "num_input_tokens_seen": 808048,
      "step": 118
    },
    {
      "epoch": 3.0610932475884245,
      "grad_norm": 2.6516857147216797,
      "learning_rate": 1.686079613857109e-06,
      "loss": 0.0235,
      "num_input_tokens_seen": 814800,
      "step": 119
    },
    {
      "epoch": 3.0868167202572345,
      "grad_norm": 0.9633734822273254,
      "learning_rate": 1.6449496416858285e-06,
      "loss": 0.0179,
      "num_input_tokens_seen": 821536,
      "step": 120
    },
    {
      "epoch": 3.112540192926045,
      "grad_norm": 1.0766749382019043,
      "learning_rate": 1.6040801261367494e-06,
      "loss": 0.0059,
      "num_input_tokens_seen": 828128,
      "step": 121
    },
    {
      "epoch": 3.1382636655948555,
      "grad_norm": 0.2934500277042389,
      "learning_rate": 1.56348351646022e-06,
      "loss": 0.0017,
      "num_input_tokens_seen": 834608,
      "step": 122
    },
    {
      "epoch": 3.1639871382636655,
      "grad_norm": 0.3029981553554535,
      "learning_rate": 1.5231721787768162e-06,
      "loss": 0.0018,
      "num_input_tokens_seen": 841360,
      "step": 123
    },
    {
      "epoch": 3.189710610932476,
      "grad_norm": 0.44817763566970825,
      "learning_rate": 1.4831583923105e-06,
      "loss": 0.0032,
      "num_input_tokens_seen": 848496,
      "step": 124
    },
    {
      "epoch": 3.215434083601286,
      "grad_norm": 0.21245715022087097,
      "learning_rate": 1.443454345648252e-06,
      "loss": 0.0019,
      "num_input_tokens_seen": 855424,
      "step": 125
    },
    {
      "epoch": 3.2411575562700965,
      "grad_norm": 0.22589029371738434,
      "learning_rate": 1.4040721330273063e-06,
      "loss": 0.0014,
      "num_input_tokens_seen": 862224,
      "step": 126
    },
    {
      "epoch": 3.266881028938907,
      "grad_norm": 0.5972980856895447,
      "learning_rate": 1.3650237506511333e-06,
      "loss": 0.0052,
      "num_input_tokens_seen": 869312,
      "step": 127
    },
    {
      "epoch": 3.292604501607717,
      "grad_norm": 0.06931939721107483,
      "learning_rate": 1.3263210930352737e-06,
      "loss": 0.0005,
      "num_input_tokens_seen": 876272,
      "step": 128
    },
    {
      "epoch": 3.3183279742765275,
      "grad_norm": 1.2623660564422607,
      "learning_rate": 1.2879759493841577e-06,
      "loss": 0.0131,
      "num_input_tokens_seen": 883072,
      "step": 129
    },
    {
      "epoch": 3.3440514469453375,
      "grad_norm": 0.5440672636032104,
      "learning_rate": 1.2500000000000007e-06,
      "loss": 0.0009,
      "num_input_tokens_seen": 889920,
      "step": 130
    },
    {
      "epoch": 3.369774919614148,
      "grad_norm": 0.6807874441146851,
      "learning_rate": 1.2124048127248644e-06,
      "loss": 0.0057,
      "num_input_tokens_seen": 896896,
      "step": 131
    },
    {
      "epoch": 3.395498392282958,
      "grad_norm": 0.03898243606090546,
      "learning_rate": 1.1752018394169882e-06,
      "loss": 0.0002,
      "num_input_tokens_seen": 903600,
      "step": 132
    },
    {
      "epoch": 3.4212218649517685,
      "grad_norm": 0.0243828147649765,
      "learning_rate": 1.1384024124624324e-06,
      "loss": 0.0002,
      "num_input_tokens_seen": 910208,
      "step": 133
    },
    {
      "epoch": 3.446945337620579,
      "grad_norm": 2.5577075481414795,
      "learning_rate": 1.1020177413231334e-06,
      "loss": 0.0145,
      "num_input_tokens_seen": 917328,
      "step": 134
    },
    {
      "epoch": 3.472668810289389,
      "grad_norm": 1.2599172592163086,
      "learning_rate": 1.0660589091223854e-06,
      "loss": 0.0034,
      "num_input_tokens_seen": 924192,
      "step": 135
    },
    {
      "epoch": 3.4983922829581995,
      "grad_norm": 1.3292278051376343,
      "learning_rate": 1.0305368692688175e-06,
      "loss": 0.0156,
      "num_input_tokens_seen": 930784,
      "step": 136
    },
    {
      "epoch": 3.5241157556270095,
      "grad_norm": 0.2977862060070038,
      "learning_rate": 9.95462442119879e-07,
      "loss": 0.0013,
      "num_input_tokens_seen": 937856,
      "step": 137
    },
    {
      "epoch": 3.54983922829582,
      "grad_norm": 0.3527968227863312,
      "learning_rate": 9.608463116858544e-07,
      "loss": 0.0007,
      "num_input_tokens_seen": 944640,
      "step": 138
    },
    {
      "epoch": 3.57556270096463,
      "grad_norm": 0.16851164400577545,
      "learning_rate": 9.266990223754069e-07,
      "loss": 0.0005,
      "num_input_tokens_seen": 951504,
      "step": 139
    },
    {
      "epoch": 3.6012861736334405,
      "grad_norm": 0.4394027292728424,
      "learning_rate": 8.930309757836517e-07,
      "loss": 0.0034,
      "num_input_tokens_seen": 958240,
      "step": 140
    },
    {
      "epoch": 3.627009646302251,
      "grad_norm": 0.0209315475076437,
      "learning_rate": 8.598524275237321e-07,
      "loss": 0.0001,
      "num_input_tokens_seen": 964912,
      "step": 141
    },
    {
      "epoch": 3.652733118971061,
      "grad_norm": 0.35701486468315125,
      "learning_rate": 8.271734841028553e-07,
      "loss": 0.001,
      "num_input_tokens_seen": 971872,
      "step": 142
    },
    {
      "epoch": 3.6784565916398715,
      "grad_norm": 2.0450756549835205,
      "learning_rate": 7.950040998437541e-07,
      "loss": 0.0123,
      "num_input_tokens_seen": 978640,
      "step": 143
    },
    {
      "epoch": 3.7041800643086815,
      "grad_norm": 0.057205893099308014,
      "learning_rate": 7.633540738525066e-07,
      "loss": 0.0002,
      "num_input_tokens_seen": 985328,
      "step": 144
    },
    {
      "epoch": 3.729903536977492,
      "grad_norm": 1.7251015901565552,
      "learning_rate": 7.322330470336314e-07,
      "loss": 0.011,
      "num_input_tokens_seen": 992224,
      "step": 145
    },
    {
      "epoch": 3.755627009646302,
      "grad_norm": 0.417669415473938,
      "learning_rate": 7.016504991533727e-07,
      "loss": 0.0008,
      "num_input_tokens_seen": 998688,
      "step": 146
    },
    {
      "epoch": 3.7813504823151125,
      "grad_norm": 0.06796720623970032,
      "learning_rate": 6.716157459520739e-07,
      "loss": 0.0003,
      "num_input_tokens_seen": 1006032,
      "step": 147
    },
    {
      "epoch": 3.807073954983923,
      "grad_norm": 0.5570574998855591,
      "learning_rate": 6.421379363065142e-07,
      "loss": 0.0018,
      "num_input_tokens_seen": 1012944,
      "step": 148
    },
    {
      "epoch": 3.832797427652733,
      "grad_norm": 0.557479977607727,
      "learning_rate": 6.1322604944307e-07,
      "loss": 0.0016,
      "num_input_tokens_seen": 1019856,
      "step": 149
    },
    {
      "epoch": 3.8585209003215435,
      "grad_norm": 0.48776909708976746,
      "learning_rate": 5.848888922025553e-07,
      "loss": 0.0021,
      "num_input_tokens_seen": 1026656,
      "step": 150
    },
    {
      "epoch": 3.884244372990354,
      "grad_norm": 0.025394350290298462,
      "learning_rate": 5.571350963575728e-07,
      "loss": 0.0001,
      "num_input_tokens_seen": 1033696,
      "step": 151
    },
    {
      "epoch": 3.909967845659164,
      "grad_norm": 0.03195232152938843,
      "learning_rate": 5.299731159831953e-07,
      "loss": 0.0001,
      "num_input_tokens_seen": 1040240,
      "step": 152
    },
    {
      "epoch": 3.935691318327974,
      "grad_norm": 0.0676019936800003,
      "learning_rate": 5.034112248817685e-07,
      "loss": 0.0003,
      "num_input_tokens_seen": 1046992,
      "step": 153
    },
    {
      "epoch": 3.9614147909967845,
      "grad_norm": 0.04871657118201256,
      "learning_rate": 4.774575140626317e-07,
      "loss": 0.0002,
      "num_input_tokens_seen": 1053936,
      "step": 154
    },
    {
      "epoch": 3.987138263665595,
      "grad_norm": 0.08272106945514679,
      "learning_rate": 4.5211988927752026e-07,
      "loss": 0.0002,
      "num_input_tokens_seen": 1060576,
      "step": 155
    },
    {
      "epoch": 4.012861736334405,
      "grad_norm": 0.009170151315629482,
      "learning_rate": 4.27406068612396e-07,
      "loss": 0.0,
      "num_input_tokens_seen": 1067648,
      "step": 156
    },
    {
      "epoch": 4.038585209003215,
      "grad_norm": 0.10544967651367188,
      "learning_rate": 4.033235801364402e-07,
      "loss": 0.0003,
      "num_input_tokens_seen": 1074512,
      "step": 157
    },
    {
      "epoch": 4.064308681672026,
      "grad_norm": 0.04709336906671524,
      "learning_rate": 3.798797596089351e-07,
      "loss": 0.0002,
      "num_input_tokens_seen": 1081296,
      "step": 158
    },
    {
      "epoch": 4.090032154340836,
      "grad_norm": 0.042879387736320496,
      "learning_rate": 3.5708174824471947e-07,
      "loss": 0.0001,
      "num_input_tokens_seen": 1087888,
      "step": 159
    },
    {
      "epoch": 4.115755627009646,
      "grad_norm": 0.03649509325623512,
      "learning_rate": 3.3493649053890325e-07,
      "loss": 0.0001,
      "num_input_tokens_seen": 1094960,
      "step": 160
    },
    {
      "epoch": 4.141479099678457,
      "grad_norm": 0.01273419987410307,
      "learning_rate": 3.134507321515107e-07,
      "loss": 0.0001,
      "num_input_tokens_seen": 1101776,
      "step": 161
    },
    {
      "epoch": 4.167202572347267,
      "grad_norm": 0.006498055998235941,
      "learning_rate": 2.9263101785268253e-07,
      "loss": 0.0,
      "num_input_tokens_seen": 1108736,
      "step": 162
    },
    {
      "epoch": 4.192926045016077,
      "grad_norm": 0.027757082134485245,
      "learning_rate": 2.7248368952908055e-07,
      "loss": 0.0001,
      "num_input_tokens_seen": 1115744,
      "step": 163
    },
    {
      "epoch": 4.218649517684887,
      "grad_norm": 0.005632288288325071,
      "learning_rate": 2.53014884252083e-07,
      "loss": 0.0,
      "num_input_tokens_seen": 1122592,
      "step": 164
    },
    {
      "epoch": 4.244372990353698,
      "grad_norm": 0.014449907466769218,
      "learning_rate": 2.3423053240837518e-07,
      "loss": 0.0001,
      "num_input_tokens_seen": 1129136,
      "step": 165
    },
    {
      "epoch": 4.270096463022508,
      "grad_norm": 0.013245908543467522,
      "learning_rate": 2.1613635589349756e-07,
      "loss": 0.0001,
      "num_input_tokens_seen": 1136080,
      "step": 166
    },
    {
      "epoch": 4.295819935691318,
      "grad_norm": 0.12783974409103394,
      "learning_rate": 1.9873786636889908e-07,
      "loss": 0.0002,
      "num_input_tokens_seen": 1142976,
      "step": 167
    },
    {
      "epoch": 4.321543408360129,
      "grad_norm": 0.08086368441581726,
      "learning_rate": 1.8204036358303173e-07,
      "loss": 0.0002,
      "num_input_tokens_seen": 1149712,
      "step": 168
    },
    {
      "epoch": 4.347266881028939,
      "grad_norm": 0.018286822363734245,
      "learning_rate": 1.6604893375699594e-07,
      "loss": 0.0001,
      "num_input_tokens_seen": 1156336,
      "step": 169
    },
    {
      "epoch": 4.372990353697749,
      "grad_norm": 0.009972570464015007,
      "learning_rate": 1.507684480352292e-07,
      "loss": 0.0001,
      "num_input_tokens_seen": 1163120,
      "step": 170
    },
    {
      "epoch": 4.39871382636656,
      "grad_norm": 0.9909194707870483,
      "learning_rate": 1.362035610017079e-07,
      "loss": 0.0115,
      "num_input_tokens_seen": 1170032,
      "step": 171
    },
    {
      "epoch": 4.42443729903537,
      "grad_norm": 0.21059785783290863,
      "learning_rate": 1.223587092621162e-07,
      "loss": 0.0005,
      "num_input_tokens_seen": 1176832,
      "step": 172
    },
    {
      "epoch": 4.45016077170418,
      "grad_norm": 0.08872511237859726,
      "learning_rate": 1.0923811009241142e-07,
      "loss": 0.0003,
      "num_input_tokens_seen": 1183856,
      "step": 173
    },
    {
      "epoch": 4.47588424437299,
      "grad_norm": 0.7515408396720886,
      "learning_rate": 9.684576015420277e-08,
      "loss": 0.005,
      "num_input_tokens_seen": 1190544,
      "step": 174
    },
    {
      "epoch": 4.501607717041801,
      "grad_norm": 0.0772569328546524,
      "learning_rate": 8.518543427732951e-08,
      "loss": 0.0003,
      "num_input_tokens_seen": 1197168,
      "step": 175
    },
    {
      "epoch": 4.527331189710611,
      "grad_norm": 0.19207893311977386,
      "learning_rate": 7.426068431000883e-08,
      "loss": 0.0008,
      "num_input_tokens_seen": 1203776,
      "step": 176
    },
    {
      "epoch": 4.553054662379421,
      "grad_norm": 0.007837573066353798,
      "learning_rate": 6.407483803691216e-08,
      "loss": 0.0,
      "num_input_tokens_seen": 1210816,
      "step": 177
    },
    {
      "epoch": 4.578778135048232,
      "grad_norm": 0.009602434933185577,
      "learning_rate": 5.463099816548578e-08,
      "loss": 0.0,
      "num_input_tokens_seen": 1217696,
      "step": 178
    },
    {
      "epoch": 4.604501607717042,
      "grad_norm": 1.3553417921066284,
      "learning_rate": 4.593204138084006e-08,
      "loss": 0.0042,
      "num_input_tokens_seen": 1224704,
      "step": 179
    },
    {
      "epoch": 4.630225080385852,
      "grad_norm": 0.17981038987636566,
      "learning_rate": 3.798061746947995e-08,
      "loss": 0.0004,
      "num_input_tokens_seen": 1231664,
      "step": 180
    },
    {
      "epoch": 4.655948553054662,
      "grad_norm": 0.04047521948814392,
      "learning_rate": 3.077914851215585e-08,
      "loss": 0.0001,
      "num_input_tokens_seen": 1238240,
      "step": 181
    },
    {
      "epoch": 4.681672025723473,
      "grad_norm": 0.02045159973204136,
      "learning_rate": 2.4329828146074096e-08,
      "loss": 0.0001,
      "num_input_tokens_seen": 1244832,
      "step": 182
    },
    {
      "epoch": 4.707395498392283,
      "grad_norm": 0.10965674370527267,
      "learning_rate": 1.8634620896695044e-08,
      "loss": 0.0004,
      "num_input_tokens_seen": 1251296,
      "step": 183
    },
    {
      "epoch": 4.733118971061093,
      "grad_norm": 0.008195169270038605,
      "learning_rate": 1.3695261579316776e-08,
      "loss": 0.0,
      "num_input_tokens_seen": 1257968,
      "step": 184
    },
    {
      "epoch": 4.758842443729904,
      "grad_norm": 0.25205764174461365,
      "learning_rate": 9.513254770636138e-09,
      "loss": 0.0009,
      "num_input_tokens_seen": 1264928,
      "step": 185
    },
    {
      "epoch": 4.784565916398714,
      "grad_norm": 0.031606338918209076,
      "learning_rate": 6.089874350439507e-09,
      "loss": 0.0001,
      "num_input_tokens_seen": 1271792,
      "step": 186
    },
    {
      "epoch": 4.810289389067524,
      "grad_norm": 0.19231323897838593,
      "learning_rate": 3.4261631135654174e-09,
      "loss": 0.0004,
      "num_input_tokens_seen": 1279024,
      "step": 187
    },
    {
      "epoch": 4.836012861736334,
      "grad_norm": 0.06766192615032196,
      "learning_rate": 1.5229324522605949e-09,
      "loss": 0.0002,
      "num_input_tokens_seen": 1285792,
      "step": 188
    },
    {
      "epoch": 4.861736334405145,
      "grad_norm": 0.005693785380572081,
      "learning_rate": 3.8076210902182607e-10,
      "loss": 0.0,
      "num_input_tokens_seen": 1292576,
      "step": 189
    },
    {
      "epoch": 4.887459807073955,
      "grad_norm": 0.02735370770096779,
      "learning_rate": 0.0,
      "loss": 0.0001,
      "num_input_tokens_seen": 1299392,
      "step": 190
    },
    {
      "epoch": 4.887459807073955,
      "num_input_tokens_seen": 1299392,
      "step": 190,
      "total_flos": 5.151317702790349e+16,
      "train_loss": 0.3433768034317166,
      "train_runtime": 2162.0959,
      "train_samples_per_second": 11.489,
      "train_steps_per_second": 0.088
    }
  ],
  "logging_steps": 1,
  "max_steps": 190,
  "num_input_tokens_seen": 1299392,
  "num_train_epochs": 5,
  "save_steps": 1000,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 5.151317702790349e+16,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}