{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 1.0031746031746032,
  "eval_steps": 60,
  "global_step": 237,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.004232804232804233,
      "grad_norm": 8.339679718017578,
      "learning_rate": 2e-05,
      "loss": 12.0884,
      "step": 1
    },
    {
      "epoch": 0.004232804232804233,
      "eval_loss": 3.1359505653381348,
      "eval_runtime": 1.6738,
      "eval_samples_per_second": 59.746,
      "eval_steps_per_second": 29.873,
      "step": 1
    },
    {
      "epoch": 0.008465608465608466,
      "grad_norm": 8.656473159790039,
      "learning_rate": 4e-05,
      "loss": 11.4697,
      "step": 2
    },
    {
      "epoch": 0.012698412698412698,
      "grad_norm": 8.756606101989746,
      "learning_rate": 6e-05,
      "loss": 12.5172,
      "step": 3
    },
    {
      "epoch": 0.016931216931216932,
      "grad_norm": 8.386862754821777,
      "learning_rate": 8e-05,
      "loss": 11.8534,
      "step": 4
    },
    {
      "epoch": 0.021164021164021163,
      "grad_norm": 8.861122131347656,
      "learning_rate": 0.0001,
      "loss": 12.1626,
      "step": 5
    },
    {
      "epoch": 0.025396825396825397,
      "grad_norm": 9.796011924743652,
      "learning_rate": 0.00012,
      "loss": 10.7331,
      "step": 6
    },
    {
      "epoch": 0.02962962962962963,
      "grad_norm": 9.846778869628906,
      "learning_rate": 0.00014,
      "loss": 11.1434,
      "step": 7
    },
    {
      "epoch": 0.033862433862433865,
      "grad_norm": 9.62647819519043,
      "learning_rate": 0.00016,
      "loss": 10.0273,
      "step": 8
    },
    {
      "epoch": 0.0380952380952381,
      "grad_norm": 8.98582649230957,
      "learning_rate": 0.00018,
      "loss": 8.0522,
      "step": 9
    },
    {
      "epoch": 0.042328042328042326,
      "grad_norm": 11.316237449645996,
      "learning_rate": 0.0002,
      "loss": 6.9703,
      "step": 10
    },
    {
      "epoch": 0.04656084656084656,
      "grad_norm": 13.630404472351074,
      "learning_rate": 0.0001999904234053922,
      "loss": 6.6376,
      "step": 11
    },
    {
      "epoch": 0.050793650793650794,
      "grad_norm": 12.950980186462402,
      "learning_rate": 0.00019996169545579207,
      "loss": 6.0849,
      "step": 12
    },
    {
      "epoch": 0.05502645502645503,
      "grad_norm": 19.049598693847656,
      "learning_rate": 0.00019991382165351814,
      "loss": 6.77,
      "step": 13
    },
    {
      "epoch": 0.05925925925925926,
      "grad_norm": 22.145090103149414,
      "learning_rate": 0.00019984681116793038,
      "loss": 5.2266,
      "step": 14
    },
    {
      "epoch": 0.06349206349206349,
      "grad_norm": 21.943340301513672,
      "learning_rate": 0.00019976067683367385,
      "loss": 4.879,
      "step": 15
    },
    {
      "epoch": 0.06772486772486773,
      "grad_norm": 16.66893196105957,
      "learning_rate": 0.00019965543514822062,
      "loss": 4.4982,
      "step": 16
    },
    {
      "epoch": 0.07195767195767196,
      "grad_norm": 13.6140775680542,
      "learning_rate": 0.00019953110626870979,
      "loss": 4.3959,
      "step": 17
    },
    {
      "epoch": 0.0761904761904762,
      "grad_norm": 10.918610572814941,
      "learning_rate": 0.0001993877140080869,
      "loss": 3.4703,
      "step": 18
    },
    {
      "epoch": 0.08042328042328042,
      "grad_norm": 12.967055320739746,
      "learning_rate": 0.000199225285830543,
      "loss": 4.2057,
      "step": 19
    },
    {
      "epoch": 0.08465608465608465,
      "grad_norm": 9.552641868591309,
      "learning_rate": 0.00019904385284625424,
      "loss": 4.2712,
      "step": 20
    },
    {
      "epoch": 0.08888888888888889,
      "grad_norm": 10.664836883544922,
      "learning_rate": 0.00019884344980542338,
      "loss": 4.7087,
      "step": 21
    },
    {
      "epoch": 0.09312169312169312,
      "grad_norm": 11.91759967803955,
      "learning_rate": 0.00019862411509162406,
      "loss": 4.1182,
      "step": 22
    },
    {
      "epoch": 0.09735449735449736,
      "grad_norm": 10.108726501464844,
      "learning_rate": 0.00019838589071444903,
      "loss": 3.8068,
      "step": 23
    },
    {
      "epoch": 0.10158730158730159,
      "grad_norm": 8.553269386291504,
      "learning_rate": 0.00019812882230146398,
      "loss": 4.3751,
      "step": 24
    },
    {
      "epoch": 0.10582010582010581,
      "grad_norm": 8.621305465698242,
      "learning_rate": 0.00019785295908946848,
      "loss": 4.6038,
      "step": 25
    },
    {
      "epoch": 0.11005291005291006,
      "grad_norm": 9.57108211517334,
      "learning_rate": 0.0001975583539150655,
      "loss": 4.3676,
      "step": 26
    },
    {
      "epoch": 0.11428571428571428,
      "grad_norm": 11.07767105102539,
      "learning_rate": 0.00019724506320454153,
      "loss": 4.0119,
      "step": 27
    },
    {
      "epoch": 0.11851851851851852,
      "grad_norm": 8.06057071685791,
      "learning_rate": 0.00019691314696305913,
      "loss": 3.4733,
      "step": 28
    },
    {
      "epoch": 0.12275132275132275,
      "grad_norm": 7.482003688812256,
      "learning_rate": 0.0001965626687631641,
      "loss": 2.8737,
      "step": 29
    },
    {
      "epoch": 0.12698412698412698,
      "grad_norm": 8.371393203735352,
      "learning_rate": 0.00019619369573260924,
      "loss": 4.1994,
      "step": 30
    },
    {
      "epoch": 0.1312169312169312,
      "grad_norm": 7.981700420379639,
      "learning_rate": 0.0001958062985414972,
      "loss": 3.8828,
      "step": 31
    },
    {
      "epoch": 0.13544973544973546,
      "grad_norm": 7.8459553718566895,
      "learning_rate": 0.00019540055138874505,
      "loss": 4.5477,
      "step": 32
    },
    {
      "epoch": 0.13968253968253969,
      "grad_norm": 6.732693672180176,
      "learning_rate": 0.00019497653198787264,
      "loss": 3.1885,
      "step": 33
    },
    {
      "epoch": 0.1439153439153439,
      "grad_norm": 8.484853744506836,
      "learning_rate": 0.0001945343215521182,
      "loss": 4.5848,
      "step": 34
    },
    {
      "epoch": 0.14814814814814814,
      "grad_norm": 8.848865509033203,
      "learning_rate": 0.00019407400477888315,
      "loss": 3.8193,
      "step": 35
    },
    {
      "epoch": 0.1523809523809524,
      "grad_norm": 6.862664699554443,
      "learning_rate": 0.00019359566983351013,
      "loss": 3.642,
      "step": 36
    },
    {
      "epoch": 0.15661375661375662,
      "grad_norm": 8.599493026733398,
      "learning_rate": 0.00019309940833239626,
      "loss": 3.8207,
      "step": 37
    },
    {
      "epoch": 0.16084656084656085,
      "grad_norm": 6.17228364944458,
      "learning_rate": 0.00019258531532544585,
      "loss": 3.4436,
      "step": 38
    },
    {
      "epoch": 0.16507936507936508,
      "grad_norm": 6.4504218101501465,
      "learning_rate": 0.00019205348927786532,
      "loss": 3.5989,
      "step": 39
    },
    {
      "epoch": 0.1693121693121693,
      "grad_norm": 8.696142196655273,
      "learning_rate": 0.00019150403205130383,
      "loss": 3.4248,
      "step": 40
    },
    {
      "epoch": 0.17354497354497356,
      "grad_norm": 6.755009651184082,
      "learning_rate": 0.0001909370488843436,
      "loss": 3.2755,
      "step": 41
    },
    {
      "epoch": 0.17777777777777778,
      "grad_norm": 8.537405014038086,
      "learning_rate": 0.00019035264837234347,
      "loss": 3.4524,
      "step": 42
    },
    {
      "epoch": 0.182010582010582,
      "grad_norm": 7.411169528961182,
      "learning_rate": 0.0001897509424466393,
      "loss": 3.1735,
      "step": 43
    },
    {
      "epoch": 0.18624338624338624,
      "grad_norm": 6.806912899017334,
      "learning_rate": 0.0001891320463531055,
      "loss": 3.5254,
      "step": 44
    },
    {
      "epoch": 0.19047619047619047,
      "grad_norm": 6.919985771179199,
      "learning_rate": 0.00018849607863008193,
      "loss": 2.5783,
      "step": 45
    },
    {
      "epoch": 0.19470899470899472,
      "grad_norm": 7.950442790985107,
      "learning_rate": 0.00018784316108566996,
      "loss": 4.1414,
      "step": 46
    },
    {
      "epoch": 0.19894179894179895,
      "grad_norm": 6.57389497756958,
      "learning_rate": 0.00018717341877440226,
      "loss": 3.3177,
      "step": 47
    },
    {
      "epoch": 0.20317460317460317,
      "grad_norm": 5.671192169189453,
      "learning_rate": 0.000186486979973291,
      "loss": 3.1265,
      "step": 48
    },
    {
      "epoch": 0.2074074074074074,
      "grad_norm": 6.347925186157227,
      "learning_rate": 0.0001857839761572586,
      "loss": 3.3136,
      "step": 49
    },
    {
      "epoch": 0.21164021164021163,
      "grad_norm": 6.390537261962891,
      "learning_rate": 0.00018506454197395606,
      "loss": 3.0955,
      "step": 50
    },
    {
      "epoch": 0.21587301587301588,
      "grad_norm": 9.167473793029785,
      "learning_rate": 0.0001843288152179739,
      "loss": 3.5882,
      "step": 51
    },
    {
      "epoch": 0.2201058201058201,
      "grad_norm": 6.599748611450195,
      "learning_rate": 0.00018357693680444976,
      "loss": 4.0846,
      "step": 52
    },
    {
      "epoch": 0.22433862433862434,
      "grad_norm": 6.614915370941162,
      "learning_rate": 0.00018280905074207884,
      "loss": 3.6121,
      "step": 53
    },
    {
      "epoch": 0.22857142857142856,
      "grad_norm": 5.948615074157715,
      "learning_rate": 0.00018202530410553163,
      "loss": 3.0863,
      "step": 54
    },
    {
      "epoch": 0.2328042328042328,
      "grad_norm": 6.1136369705200195,
      "learning_rate": 0.00018122584700728443,
      "loss": 2.8571,
      "step": 55
    },
    {
      "epoch": 0.23703703703703705,
      "grad_norm": 6.114598274230957,
      "learning_rate": 0.0001804108325688679,
      "loss": 2.6631,
      "step": 56
    },
    {
      "epoch": 0.24126984126984127,
      "grad_norm": 6.398357391357422,
      "learning_rate": 0.0001795804168915396,
      "loss": 3.3081,
      "step": 57
    },
    {
      "epoch": 0.2455026455026455,
      "grad_norm": 7.428066730499268,
      "learning_rate": 0.00017873475902638553,
      "loss": 3.35,
      "step": 58
    },
    {
      "epoch": 0.24973544973544973,
      "grad_norm": 5.939016342163086,
      "learning_rate": 0.00017787402094385666,
      "loss": 3.1656,
      "step": 59
    },
    {
      "epoch": 0.25396825396825395,
      "grad_norm": 7.398441314697266,
      "learning_rate": 0.00017699836750274662,
      "loss": 2.7543,
      "step": 60
    },
    {
      "epoch": 0.25396825396825395,
      "eval_loss": 0.8399143815040588,
      "eval_runtime": 1.4778,
      "eval_samples_per_second": 67.668,
      "eval_steps_per_second": 33.834,
      "step": 60
    },
    {
      "epoch": 0.2582010582010582,
      "grad_norm": 7.3944573402404785,
      "learning_rate": 0.00017610796641861581,
      "loss": 2.9368,
      "step": 61
    },
    {
      "epoch": 0.2624338624338624,
      "grad_norm": 8.78125,
      "learning_rate": 0.00017520298823166873,
      "loss": 4.1083,
      "step": 62
    },
    {
      "epoch": 0.26666666666666666,
      "grad_norm": 6.919495582580566,
      "learning_rate": 0.00017428360627408978,
      "loss": 2.3915,
      "step": 63
    },
    {
      "epoch": 0.2708994708994709,
      "grad_norm": 6.8133697509765625,
      "learning_rate": 0.00017334999663684504,
      "loss": 3.6482,
      "step": 64
    },
    {
      "epoch": 0.2751322751322751,
      "grad_norm": 8.588729858398438,
      "learning_rate": 0.00017240233813595478,
      "loss": 3.3691,
      "step": 65
    },
    {
      "epoch": 0.27936507936507937,
      "grad_norm": 9.81425666809082,
      "learning_rate": 0.0001714408122782448,
      "loss": 3.4734,
      "step": 66
    },
    {
      "epoch": 0.28359788359788357,
      "grad_norm": 10.689726829528809,
      "learning_rate": 0.000170465603226582,
      "loss": 2.813,
      "step": 67
    },
    {
      "epoch": 0.2878306878306878,
      "grad_norm": 9.723061561584473,
      "learning_rate": 0.0001694768977646013,
      "loss": 3.0244,
      "step": 68
    },
    {
      "epoch": 0.2920634920634921,
      "grad_norm": 6.483892440795898,
      "learning_rate": 0.0001684748852609306,
      "loss": 2.986,
      "step": 69
    },
    {
      "epoch": 0.2962962962962963,
      "grad_norm": 6.737588405609131,
      "learning_rate": 0.0001674597576329207,
      "loss": 2.5691,
      "step": 70
    },
    {
      "epoch": 0.30052910052910053,
      "grad_norm": 5.918189525604248,
      "learning_rate": 0.00016643170930988698,
      "loss": 3.1275,
      "step": 71
    },
    {
      "epoch": 0.3047619047619048,
      "grad_norm": 8.802118301391602,
      "learning_rate": 0.00016539093719586994,
      "loss": 4.5713,
      "step": 72
    },
    {
      "epoch": 0.308994708994709,
      "grad_norm": 7.090899467468262,
      "learning_rate": 0.00016433764063192194,
      "loss": 2.7131,
      "step": 73
    },
    {
      "epoch": 0.31322751322751324,
      "grad_norm": 5.637731552124023,
      "learning_rate": 0.00016327202135792685,
      "loss": 3.2843,
      "step": 74
    },
    {
      "epoch": 0.31746031746031744,
      "grad_norm": 6.375069618225098,
      "learning_rate": 0.00016219428347396053,
      "loss": 3.2342,
      "step": 75
    },
    {
      "epoch": 0.3216931216931217,
      "grad_norm": 5.949819564819336,
      "learning_rate": 0.00016110463340119913,
      "loss": 2.9549,
      "step": 76
    },
    {
      "epoch": 0.32592592592592595,
      "grad_norm": 5.934611797332764,
      "learning_rate": 0.00016000327984238292,
      "loss": 2.8051,
      "step": 77
    },
    {
      "epoch": 0.33015873015873015,
      "grad_norm": 6.7256669998168945,
      "learning_rate": 0.00015889043374184286,
      "loss": 3.0315,
      "step": 78
    },
    {
      "epoch": 0.3343915343915344,
      "grad_norm": 6.445525169372559,
      "learning_rate": 0.0001577663082450984,
      "loss": 2.9355,
      "step": 79
    },
    {
      "epoch": 0.3386243386243386,
      "grad_norm": 6.864555835723877,
      "learning_rate": 0.00015663111865803285,
      "loss": 3.5455,
      "step": 80
    },
    {
      "epoch": 0.34285714285714286,
      "grad_norm": 5.600425720214844,
      "learning_rate": 0.00015548508240565583,
      "loss": 2.4814,
      "step": 81
    },
    {
      "epoch": 0.3470899470899471,
      "grad_norm": 6.538332939147949,
      "learning_rate": 0.0001543284189904592,
      "loss": 2.8366,
      "step": 82
    },
    {
      "epoch": 0.3513227513227513,
      "grad_norm": 5.535585880279541,
      "learning_rate": 0.00015316134995037545,
      "loss": 2.8065,
      "step": 83
    },
    {
      "epoch": 0.35555555555555557,
      "grad_norm": 7.128277778625488,
      "learning_rate": 0.00015198409881634617,
      "loss": 4.0691,
      "step": 84
    },
    {
      "epoch": 0.35978835978835977,
      "grad_norm": 5.540020942687988,
      "learning_rate": 0.00015079689106950854,
      "loss": 2.589,
      "step": 85
    },
    {
      "epoch": 0.364021164021164,
      "grad_norm": 5.084954261779785,
      "learning_rate": 0.00014959995409800873,
      "loss": 2.452,
      "step": 86
    },
    {
      "epoch": 0.3682539682539683,
      "grad_norm": 6.272806167602539,
      "learning_rate": 0.00014839351715344968,
      "loss": 3.016,
      "step": 87
    },
    {
      "epoch": 0.3724867724867725,
      "grad_norm": 6.030159950256348,
      "learning_rate": 0.00014717781130698212,
      "loss": 2.3207,
      "step": 88
    },
    {
      "epoch": 0.37671957671957673,
      "grad_norm": 6.719594955444336,
      "learning_rate": 0.00014595306940504716,
      "loss": 2.726,
      "step": 89
    },
    {
      "epoch": 0.38095238095238093,
      "grad_norm": 7.502119541168213,
      "learning_rate": 0.00014471952602477866,
      "loss": 3.7479,
      "step": 90
    },
    {
      "epoch": 0.3851851851851852,
      "grad_norm": 6.710303783416748,
      "learning_rate": 0.00014347741742907433,
      "loss": 3.0886,
      "step": 91
    },
    {
      "epoch": 0.38941798941798944,
      "grad_norm": 5.254584789276123,
      "learning_rate": 0.00014222698152134374,
      "loss": 2.2029,
      "step": 92
    },
    {
      "epoch": 0.39365079365079364,
      "grad_norm": 8.094197273254395,
      "learning_rate": 0.0001409684577999423,
      "loss": 3.5344,
      "step": 93
    },
    {
      "epoch": 0.3978835978835979,
      "grad_norm": 6.4049787521362305,
      "learning_rate": 0.00013970208731229974,
      "loss": 2.7305,
      "step": 94
    },
    {
      "epoch": 0.4021164021164021,
      "grad_norm": 6.382630825042725,
      "learning_rate": 0.00013842811260875168,
      "loss": 2.7879,
      "step": 95
    },
    {
      "epoch": 0.40634920634920635,
      "grad_norm": 8.750246047973633,
      "learning_rate": 0.0001371467776960837,
      "loss": 3.3345,
      "step": 96
    },
    {
      "epoch": 0.4105820105820106,
      "grad_norm": 11.902384757995605,
      "learning_rate": 0.0001358583279907961,
      "loss": 3.1273,
      "step": 97
    },
    {
      "epoch": 0.4148148148148148,
      "grad_norm": 8.249228477478027,
      "learning_rate": 0.00013456301027209882,
      "loss": 3.9496,
      "step": 98
    },
    {
      "epoch": 0.41904761904761906,
      "grad_norm": 6.53847074508667,
      "learning_rate": 0.00013326107263464558,
      "loss": 2.6358,
      "step": 99
    },
    {
      "epoch": 0.42328042328042326,
      "grad_norm": 5.403112888336182,
      "learning_rate": 0.00013195276444101547,
      "loss": 2.5196,
      "step": 100
    },
    {
      "epoch": 0.4275132275132275,
      "grad_norm": 6.2557902336120605,
      "learning_rate": 0.0001306383362739523,
      "loss": 2.2791,
      "step": 101
    },
    {
      "epoch": 0.43174603174603177,
      "grad_norm": 6.666345596313477,
      "learning_rate": 0.0001293180398883701,
      "loss": 2.5917,
      "step": 102
    },
    {
      "epoch": 0.43597883597883597,
      "grad_norm": 6.088561534881592,
      "learning_rate": 0.00012799212816313376,
      "loss": 2.429,
      "step": 103
    },
    {
      "epoch": 0.4402116402116402,
      "grad_norm": 6.642639636993408,
      "learning_rate": 0.00012666085505262485,
      "loss": 2.7601,
      "step": 104
    },
    {
      "epoch": 0.4444444444444444,
      "grad_norm": 6.388784885406494,
      "learning_rate": 0.00012532447553810126,
      "loss": 2.6417,
      "step": 105
    },
    {
      "epoch": 0.4486772486772487,
      "grad_norm": 6.257534027099609,
      "learning_rate": 0.00012398324557885994,
      "loss": 2.7325,
      "step": 106
    },
    {
      "epoch": 0.45291005291005293,
      "grad_norm": 7.561567783355713,
      "learning_rate": 0.00012263742206321287,
      "loss": 2.8665,
      "step": 107
    },
    {
      "epoch": 0.45714285714285713,
      "grad_norm": 6.717538833618164,
      "learning_rate": 0.0001212872627592845,
      "loss": 2.8393,
      "step": 108
    },
    {
      "epoch": 0.4613756613756614,
      "grad_norm": 7.155213832855225,
      "learning_rate": 0.00011993302626564102,
      "loss": 2.6633,
      "step": 109
    },
    {
      "epoch": 0.4656084656084656,
      "grad_norm": 9.459369659423828,
      "learning_rate": 0.00011857497196176049,
      "loss": 3.1022,
      "step": 110
    },
    {
      "epoch": 0.46984126984126984,
      "grad_norm": 8.846125602722168,
      "learning_rate": 0.00011721335995835336,
      "loss": 3.3787,
      "step": 111
    },
    {
      "epoch": 0.4740740740740741,
      "grad_norm": 6.257829666137695,
      "learning_rate": 0.00011584845104754304,
      "loss": 2.4346,
      "step": 112
    },
    {
      "epoch": 0.4783068783068783,
      "grad_norm": 8.1566743850708,
      "learning_rate": 0.00011448050665291587,
      "loss": 3.8527,
      "step": 113
    },
    {
      "epoch": 0.48253968253968255,
      "grad_norm": 7.203742504119873,
      "learning_rate": 0.00011310978877945007,
      "loss": 2.7847,
      "step": 114
    },
    {
      "epoch": 0.48677248677248675,
      "grad_norm": 6.576760292053223,
      "learning_rate": 0.00011173655996333357,
      "loss": 2.974,
      "step": 115
    },
    {
      "epoch": 0.491005291005291,
      "grad_norm": 6.616902828216553,
      "learning_rate": 0.00011036108322167988,
      "loss": 3.1308,
      "step": 116
    },
    {
      "epoch": 0.49523809523809526,
      "grad_norm": 7.1346964836120605,
      "learning_rate": 0.00010898362200215197,
      "loss": 2.7605,
      "step": 117
    },
    {
      "epoch": 0.49947089947089945,
      "grad_norm": 6.845986366271973,
      "learning_rate": 0.0001076044401325036,
      "loss": 2.7492,
      "step": 118
    },
    {
      "epoch": 0.5037037037037037,
      "grad_norm": 6.537270545959473,
      "learning_rate": 0.0001062238017700478,
      "loss": 3.0198,
      "step": 119
    },
    {
      "epoch": 0.5079365079365079,
      "grad_norm": 6.494214057922363,
      "learning_rate": 0.00010484197135106263,
      "loss": 2.9296,
      "step": 120
    },
    {
      "epoch": 0.5079365079365079,
      "eval_loss": 0.7603757977485657,
      "eval_runtime": 1.4646,
      "eval_samples_per_second": 68.276,
      "eval_steps_per_second": 34.138,
      "step": 120
    },
    {
      "epoch": 0.5121693121693122,
      "grad_norm": 6.1614179611206055,
      "learning_rate": 0.00010345921354014279,
      "loss": 2.3125,
      "step": 121
    },
    {
      "epoch": 0.5164021164021164,
      "grad_norm": 6.870548248291016,
      "learning_rate": 0.00010207579317950827,
      "loss": 3.2397,
      "step": 122
    },
    {
      "epoch": 0.5206349206349207,
      "grad_norm": 6.253408432006836,
      "learning_rate": 0.00010069197523827833,
      "loss": 2.5337,
      "step": 123
    },
    {
      "epoch": 0.5248677248677248,
      "grad_norm": 5.668649673461914,
      "learning_rate": 9.930802476172169e-05,
      "loss": 2.7208,
      "step": 124
    },
    {
      "epoch": 0.5291005291005291,
      "grad_norm": 6.12328577041626,
      "learning_rate": 9.792420682049174e-05,
      "loss": 3.0095,
      "step": 125
    },
    {
      "epoch": 0.5333333333333333,
      "grad_norm": 5.932798862457275,
      "learning_rate": 9.654078645985722e-05,
      "loss": 2.7453,
      "step": 126
    },
    {
      "epoch": 0.5375661375661376,
      "grad_norm": 6.215381622314453,
      "learning_rate": 9.515802864893739e-05,
      "loss": 2.7157,
      "step": 127
    },
    {
      "epoch": 0.5417989417989418,
      "grad_norm": 5.750072002410889,
      "learning_rate": 9.377619822995219e-05,
      "loss": 2.4893,
      "step": 128
    },
    {
      "epoch": 0.546031746031746,
      "grad_norm": 5.339773178100586,
      "learning_rate": 9.239555986749645e-05,
      "loss": 2.3928,
      "step": 129
    },
    {
      "epoch": 0.5502645502645502,
      "grad_norm": 7.058696746826172,
      "learning_rate": 9.101637799784804e-05,
      "loss": 3.6404,
      "step": 130
    },
    {
      "epoch": 0.5544973544973545,
      "grad_norm": 6.0547380447387695,
      "learning_rate": 8.963891677832011e-05,
      "loss": 3.3968,
      "step": 131
    },
    {
      "epoch": 0.5587301587301587,
      "grad_norm": 6.519040107727051,
      "learning_rate": 8.826344003666647e-05,
      "loss": 2.5037,
      "step": 132
    },
    {
      "epoch": 0.562962962962963,
      "grad_norm": 5.659784317016602,
      "learning_rate": 8.689021122054996e-05,
      "loss": 2.1445,
      "step": 133
    },
    {
      "epoch": 0.5671957671957671,
      "grad_norm": 4.586825370788574,
      "learning_rate": 8.551949334708415e-05,
      "loss": 2.3438,
      "step": 134
    },
    {
      "epoch": 0.5714285714285714,
      "grad_norm": 6.876895904541016,
      "learning_rate": 8.415154895245697e-05,
      "loss": 2.9263,
      "step": 135
    },
    {
      "epoch": 0.5756613756613757,
      "grad_norm": 5.955794334411621,
      "learning_rate": 8.278664004164665e-05,
      "loss": 2.9779,
      "step": 136
    },
    {
      "epoch": 0.5798941798941799,
      "grad_norm": 6.474263668060303,
      "learning_rate": 8.142502803823955e-05,
      "loss": 3.2006,
      "step": 137
    },
    {
      "epoch": 0.5841269841269842,
      "grad_norm": 7.228113651275635,
      "learning_rate": 8.0066973734359e-05,
      "loss": 3.3374,
      "step": 138
    },
    {
      "epoch": 0.5883597883597883,
      "grad_norm": 6.262153625488281,
      "learning_rate": 7.871273724071553e-05,
      "loss": 2.923,
      "step": 139
    },
    {
      "epoch": 0.5925925925925926,
      "grad_norm": 5.991569995880127,
      "learning_rate": 7.736257793678714e-05,
      "loss": 2.6618,
      "step": 140
    },
    {
      "epoch": 0.5968253968253968,
      "grad_norm": 5.463779449462891,
      "learning_rate": 7.601675442114009e-05,
      "loss": 2.5396,
      "step": 141
    },
    {
      "epoch": 0.6010582010582011,
      "grad_norm": 5.527047157287598,
      "learning_rate": 7.46755244618988e-05,
      "loss": 2.9924,
      "step": 142
    },
    {
      "epoch": 0.6052910052910053,
      "grad_norm": 6.64261531829834,
      "learning_rate": 7.333914494737514e-05,
      "loss": 2.9435,
      "step": 143
    },
    {
      "epoch": 0.6095238095238096,
      "grad_norm": 5.987970352172852,
      "learning_rate": 7.200787183686625e-05,
      "loss": 2.2986,
      "step": 144
    },
    {
      "epoch": 0.6137566137566137,
      "grad_norm": 5.603074550628662,
      "learning_rate": 7.068196011162994e-05,
      "loss": 2.9165,
      "step": 145
    },
    {
      "epoch": 0.617989417989418,
      "grad_norm": 5.258119583129883,
      "learning_rate": 6.936166372604773e-05,
      "loss": 2.5301,
      "step": 146
    },
    {
      "epoch": 0.6222222222222222,
      "grad_norm": 5.807767868041992,
      "learning_rate": 6.804723555898458e-05,
      "loss": 2.2787,
      "step": 147
    },
    {
      "epoch": 0.6264550264550265,
      "grad_norm": 5.4776458740234375,
      "learning_rate": 6.673892736535448e-05,
      "loss": 2.5575,
      "step": 148
    },
    {
      "epoch": 0.6306878306878307,
      "grad_norm": 7.408624172210693,
      "learning_rate": 6.543698972790117e-05,
      "loss": 2.983,
      "step": 149
    },
    {
      "epoch": 0.6349206349206349,
      "grad_norm": 7.4598822593688965,
      "learning_rate": 6.414167200920391e-05,
      "loss": 3.2846,
      "step": 150
    },
    {
      "epoch": 0.6391534391534391,
      "grad_norm": 6.593167304992676,
      "learning_rate": 6.28532223039163e-05,
      "loss": 2.8205,
      "step": 151
    },
    {
      "epoch": 0.6433862433862434,
      "grad_norm": 6.006547451019287,
      "learning_rate": 6.157188739124834e-05,
      "loss": 2.516,
      "step": 152
    },
    {
      "epoch": 0.6476190476190476,
      "grad_norm": 6.059658527374268,
      "learning_rate": 6.029791268770029e-05,
      "loss": 3.0748,
      "step": 153
    },
    {
      "epoch": 0.6518518518518519,
      "grad_norm": 7.798333644866943,
      "learning_rate": 5.903154220005771e-05,
      "loss": 3.0236,
      "step": 154
    },
    {
      "epoch": 0.656084656084656,
      "grad_norm": 7.253503322601318,
      "learning_rate": 5.777301847865629e-05,
      "loss": 3.1012,
      "step": 155
    },
    {
      "epoch": 0.6603174603174603,
      "grad_norm": 6.767838478088379,
      "learning_rate": 5.652258257092569e-05,
      "loss": 2.7472,
      "step": 156
    },
    {
      "epoch": 0.6645502645502646,
      "grad_norm": 7.5445075035095215,
      "learning_rate": 5.528047397522133e-05,
      "loss": 3.3653,
      "step": 157
    },
    {
      "epoch": 0.6687830687830688,
      "grad_norm": 5.806185245513916,
      "learning_rate": 5.404693059495285e-05,
      "loss": 2.4521,
      "step": 158
    },
    {
      "epoch": 0.6730158730158731,
      "grad_norm": 6.993499755859375,
      "learning_rate": 5.282218869301788e-05,
      "loss": 2.208,
      "step": 159
    },
    {
      "epoch": 0.6772486772486772,
      "grad_norm": 6.5682291984558105,
      "learning_rate": 5.160648284655032e-05,
      "loss": 3.1349,
      "step": 160
    },
    {
      "epoch": 0.6814814814814815,
      "grad_norm": 7.076966285705566,
      "learning_rate": 5.040004590199128e-05,
      "loss": 2.1814,
      "step": 161
    },
    {
      "epoch": 0.6857142857142857,
      "grad_norm": 6.995006084442139,
      "learning_rate": 4.920310893049146e-05,
      "loss": 3.5624,
      "step": 162
    },
    {
      "epoch": 0.68994708994709,
      "grad_norm": 5.643093585968018,
      "learning_rate": 4.801590118365383e-05,
      "loss": 2.5031,
      "step": 163
    },
    {
      "epoch": 0.6941798941798942,
      "grad_norm": 6.644287109375,
      "learning_rate": 4.683865004962452e-05,
      "loss": 3.3723,
      "step": 164
    },
    {
      "epoch": 0.6984126984126984,
      "grad_norm": 5.435771465301514,
      "learning_rate": 4.567158100954083e-05,
      "loss": 2.5943,
      "step": 165
    },
    {
      "epoch": 0.7026455026455026,
      "grad_norm": 5.321238994598389,
      "learning_rate": 4.4514917594344184e-05,
      "loss": 2.6608,
      "step": 166
    },
    {
      "epoch": 0.7068783068783069,
      "grad_norm": 7.867081642150879,
      "learning_rate": 4.3368881341967135e-05,
      "loss": 2.8102,
      "step": 167
    },
    {
      "epoch": 0.7111111111111111,
      "grad_norm": 5.821238040924072,
      "learning_rate": 4.223369175490162e-05,
      "loss": 2.5893,
      "step": 168
    },
    {
      "epoch": 0.7153439153439154,
      "grad_norm": 8.490909576416016,
      "learning_rate": 4.110956625815713e-05,
      "loss": 3.1689,
      "step": 169
    },
    {
      "epoch": 0.7195767195767195,
      "grad_norm": 6.265698432922363,
      "learning_rate": 3.9996720157617094e-05,
      "loss": 2.9221,
      "step": 170
    },
    {
      "epoch": 0.7238095238095238,
      "grad_norm": 6.983982086181641,
      "learning_rate": 3.8895366598800896e-05,
      "loss": 2.6009,
      "step": 171
    },
    {
      "epoch": 0.728042328042328,
      "grad_norm": 4.839448928833008,
      "learning_rate": 3.780571652603949e-05,
      "loss": 2.0182,
      "step": 172
    },
    {
      "epoch": 0.7322751322751323,
      "grad_norm": 5.678360939025879,
      "learning_rate": 3.672797864207316e-05,
      "loss": 2.5529,
      "step": 173
    },
    {
      "epoch": 0.7365079365079366,
      "grad_norm": 7.290799617767334,
      "learning_rate": 3.566235936807808e-05,
      "loss": 3.0144,
      "step": 174
    },
    {
      "epoch": 0.7407407407407407,
      "grad_norm": 6.965991497039795,
      "learning_rate": 3.460906280413007e-05,
      "loss": 2.6523,
      "step": 175
    },
    {
      "epoch": 0.744973544973545,
      "grad_norm": 6.397098541259766,
      "learning_rate": 3.3568290690113034e-05,
      "loss": 3.0583,
      "step": 176
    },
    {
      "epoch": 0.7492063492063492,
      "grad_norm": 5.7884840965271,
      "learning_rate": 3.25402423670793e-05,
      "loss": 2.8212,
      "step": 177
    },
    {
      "epoch": 0.7534391534391535,
      "grad_norm": 6.100215435028076,
      "learning_rate": 3.1525114739069415e-05,
      "loss": 2.8382,
      "step": 178
    },
    {
      "epoch": 0.7576719576719577,
      "grad_norm": 6.165123462677002,
      "learning_rate": 3.0523102235398714e-05,
      "loss": 2.5392,
      "step": 179
    },
    {
      "epoch": 0.7619047619047619,
      "grad_norm": 6.871748447418213,
      "learning_rate": 2.9534396773417994e-05,
      "loss": 3.4976,
      "step": 180
    },
    {
      "epoch": 0.7619047619047619,
      "eval_loss": 0.7208923101425171,
      "eval_runtime": 1.4631,
      "eval_samples_per_second": 68.347,
      "eval_steps_per_second": 34.173,
      "step": 180
    },
    {
      "epoch": 0.7661375661375661,
      "grad_norm": 7.957937240600586,
      "learning_rate": 2.855918772175522e-05,
      "loss": 3.4826,
      "step": 181
    },
    {
      "epoch": 0.7703703703703704,
      "grad_norm": 6.855284690856934,
      "learning_rate": 2.7597661864045233e-05,
      "loss": 3.4164,
      "step": 182
    },
    {
      "epoch": 0.7746031746031746,
      "grad_norm": 5.783848285675049,
      "learning_rate": 2.6650003363154963e-05,
      "loss": 2.3278,
      "step": 183
    },
    {
      "epoch": 0.7788359788359789,
      "grad_norm": 15.872426986694336,
      "learning_rate": 2.5716393725910215e-05,
      "loss": 3.0732,
      "step": 184
    },
    {
      "epoch": 0.783068783068783,
      "grad_norm": 6.1523871421813965,
      "learning_rate": 2.47970117683313e-05,
      "loss": 2.9557,
      "step": 185
    },
    {
      "epoch": 0.7873015873015873,
      "grad_norm": 8.40322494506836,
      "learning_rate": 2.389203358138419e-05,
      "loss": 3.7876,
      "step": 186
    },
    {
      "epoch": 0.7915343915343915,
      "grad_norm": 6.189878463745117,
      "learning_rate": 2.3001632497253424e-05,
      "loss": 2.9313,
      "step": 187
    },
    {
      "epoch": 0.7957671957671958,
      "grad_norm": 4.903008460998535,
      "learning_rate": 2.2125979056143364e-05,
      "loss": 1.6503,
      "step": 188
    },
    {
      "epoch": 0.8,
      "grad_norm": 8.661479949951172,
      "learning_rate": 2.1265240973614486e-05,
      "loss": 3.0821,
      "step": 189
    },
    {
      "epoch": 0.8042328042328042,
      "grad_norm": 5.910584926605225,
      "learning_rate": 2.0419583108460418e-05,
      "loss": 2.6028,
      "step": 190
    },
    {
      "epoch": 0.8084656084656084,
      "grad_norm": 6.254149436950684,
      "learning_rate": 1.958916743113214e-05,
      "loss": 2.7991,
      "step": 191
    },
    {
      "epoch": 0.8126984126984127,
      "grad_norm": 7.573146820068359,
      "learning_rate": 1.877415299271561e-05,
      "loss": 2.5724,
      "step": 192
    },
    {
      "epoch": 0.816931216931217,
      "grad_norm": 5.690131187438965,
      "learning_rate": 1.7974695894468384e-05,
      "loss": 2.2762,
      "step": 193
    },
    {
      "epoch": 0.8211640211640212,
      "grad_norm": 5.798933982849121,
      "learning_rate": 1.7190949257921196e-05,
      "loss": 2.1385,
      "step": 194
    },
    {
      "epoch": 0.8253968253968254,
      "grad_norm": 7.621517658233643,
      "learning_rate": 1.642306319555027e-05,
      "loss": 2.5064,
      "step": 195
    },
    {
      "epoch": 0.8296296296296296,
      "grad_norm": 7.2165350914001465,
      "learning_rate": 1.5671184782026106e-05,
      "loss": 2.7742,
      "step": 196
    },
    {
      "epoch": 0.8338624338624339,
      "grad_norm": 6.8323211669921875,
      "learning_rate": 1.4935458026043959e-05,
      "loss": 2.869,
      "step": 197
    },
    {
      "epoch": 0.8380952380952381,
      "grad_norm": 6.338479042053223,
      "learning_rate": 1.4216023842741455e-05,
      "loss": 2.9435,
      "step": 198
    },
    {
      "epoch": 0.8423280423280424,
      "grad_norm": 6.278661727905273,
      "learning_rate": 1.3513020026709023e-05,
      "loss": 2.7868,
      "step": 199
    },
    {
      "epoch": 0.8465608465608465,
      "grad_norm": 5.375467300415039,
      "learning_rate": 1.2826581225597767e-05,
      "loss": 2.6017,
      "step": 200
    },
    {
      "epoch": 0.8507936507936508,
      "grad_norm": 7.244228839874268,
      "learning_rate": 1.2156838914330072e-05,
      "loss": 3.1561,
      "step": 201
    },
    {
      "epoch": 0.855026455026455,
      "grad_norm": 6.201519012451172,
      "learning_rate": 1.1503921369918091e-05,
      "loss": 2.5623,
      "step": 202
    },
    {
      "epoch": 0.8592592592592593,
      "grad_norm": 5.793484210968018,
      "learning_rate": 1.0867953646894525e-05,
      "loss": 2.8732,
      "step": 203
    },
    {
      "epoch": 0.8634920634920635,
      "grad_norm": 7.211161136627197,
      "learning_rate": 1.0249057553360742e-05,
      "loss": 3.4671,
      "step": 204
    },
    {
      "epoch": 0.8677248677248677,
      "grad_norm": 6.088332176208496,
      "learning_rate": 9.647351627656543e-06,
      "loss": 1.7759,
      "step": 205
    },
    {
      "epoch": 0.8719576719576719,
      "grad_norm": 6.6968488693237305,
      "learning_rate": 9.062951115656403e-06,
      "loss": 3.3001,
      "step": 206
    },
    {
      "epoch": 0.8761904761904762,
      "grad_norm": 5.636354446411133,
      "learning_rate": 8.495967948696192e-06,
      "loss": 2.7173,
      "step": 207
    },
    {
      "epoch": 0.8804232804232804,
      "grad_norm": 5.944347858428955,
      "learning_rate": 7.946510722134692e-06,
      "loss": 2.454,
      "step": 208
    },
    {
      "epoch": 0.8846560846560847,
      "grad_norm": 6.995573997497559,
      "learning_rate": 7.4146846745541506e-06,
      "loss": 3.2652,
      "step": 209
    },
    {
      "epoch": 0.8888888888888888,
      "grad_norm": 7.945988178253174,
      "learning_rate": 6.900591667603751e-06,
      "loss": 3.5859,
      "step": 210
    },
    {
      "epoch": 0.8931216931216931,
      "grad_norm": 5.948593616485596,
      "learning_rate": 6.40433016648988e-06,
      "loss": 2.3406,
      "step": 211
    },
    {
      "epoch": 0.8973544973544973,
      "grad_norm": 6.893688201904297,
      "learning_rate": 5.925995221116853e-06,
      "loss": 2.5966,
      "step": 212
    },
    {
      "epoch": 0.9015873015873016,
      "grad_norm": 6.056822776794434,
      "learning_rate": 5.465678447881828e-06,
      "loss": 3.1498,
      "step": 213
    },
    {
      "epoch": 0.9058201058201059,
      "grad_norm": 5.484859943389893,
      "learning_rate": 5.023468012127364e-06,
      "loss": 2.3254,
      "step": 214
    },
    {
      "epoch": 0.91005291005291,
      "grad_norm": 5.663562774658203,
      "learning_rate": 4.599448611254964e-06,
      "loss": 2.4197,
      "step": 215
    },
    {
      "epoch": 0.9142857142857143,
      "grad_norm": 7.122875690460205,
      "learning_rate": 4.193701458502807e-06,
      "loss": 3.4631,
      "step": 216
    },
    {
      "epoch": 0.9185185185185185,
      "grad_norm": 5.062466621398926,
      "learning_rate": 3.80630426739077e-06,
      "loss": 2.0242,
      "step": 217
    },
    {
      "epoch": 0.9227513227513228,
      "grad_norm": 6.852725505828857,
      "learning_rate": 3.4373312368358944e-06,
      "loss": 2.3947,
      "step": 218
    },
    {
      "epoch": 0.926984126984127,
      "grad_norm": 6.722269058227539,
      "learning_rate": 3.086853036940862e-06,
      "loss": 2.9278,
      "step": 219
    },
    {
      "epoch": 0.9312169312169312,
      "grad_norm": 7.214760780334473,
      "learning_rate": 2.754936795458485e-06,
      "loss": 2.5268,
      "step": 220
    },
    {
      "epoch": 0.9354497354497354,
      "grad_norm": 7.218380451202393,
      "learning_rate": 2.4416460849345123e-06,
      "loss": 2.9904,
      "step": 221
    },
    {
      "epoch": 0.9396825396825397,
      "grad_norm": 6.950320720672607,
      "learning_rate": 2.1470409105315283e-06,
      "loss": 2.7091,
      "step": 222
    },
    {
      "epoch": 0.9439153439153439,
      "grad_norm": 5.87589168548584,
      "learning_rate": 1.8711776985360308e-06,
      "loss": 2.4052,
      "step": 223
    },
    {
      "epoch": 0.9481481481481482,
      "grad_norm": 5.747050762176514,
      "learning_rate": 1.61410928555098e-06,
      "loss": 2.5603,
      "step": 224
    },
    {
      "epoch": 0.9523809523809523,
      "grad_norm": 6.162868976593018,
      "learning_rate": 1.3758849083759352e-06,
      "loss": 2.5383,
      "step": 225
    },
    {
      "epoch": 0.9566137566137566,
      "grad_norm": 6.223538875579834,
      "learning_rate": 1.1565501945766222e-06,
      "loss": 2.7093,
      "step": 226
    },
    {
      "epoch": 0.9608465608465608,
      "grad_norm": 6.424678802490234,
      "learning_rate": 9.56147153745779e-07,
      "loss": 2.2974,
      "step": 227
    },
    {
      "epoch": 0.9650793650793651,
      "grad_norm": 8.89910888671875,
      "learning_rate": 7.747141694570026e-07,
      "loss": 3.2458,
      "step": 228
    },
    {
      "epoch": 0.9693121693121693,
      "grad_norm": 5.710629463195801,
      "learning_rate": 6.122859919130974e-07,
      "loss": 3.1255,
      "step": 229
    },
    {
      "epoch": 0.9735449735449735,
      "grad_norm": 5.598289489746094,
      "learning_rate": 4.6889373129022085e-07,
      "loss": 2.3627,
      "step": 230
    },
    {
      "epoch": 0.9777777777777777,
      "grad_norm": 6.710612773895264,
      "learning_rate": 3.445648517793942e-07,
      "loss": 2.4085,
      "step": 231
    },
    {
      "epoch": 0.982010582010582,
      "grad_norm": 6.431200981140137,
      "learning_rate": 2.3932316632614416e-07,
      "loss": 2.8684,
      "step": 232
    },
    {
      "epoch": 0.9862433862433863,
      "grad_norm": 6.007854461669922,
      "learning_rate": 1.5318883206962842e-07,
      "loss": 2.7014,
      "step": 233
    },
    {
      "epoch": 0.9904761904761905,
      "grad_norm": 5.230172634124756,
      "learning_rate": 8.617834648185774e-08,
      "loss": 2.6608,
      "step": 234
    },
    {
      "epoch": 0.9947089947089947,
      "grad_norm": 6.711563587188721,
      "learning_rate": 3.8304544207945495e-08,
      "loss": 2.612,
      "step": 235
    },
    {
      "epoch": 0.9989417989417989,
      "grad_norm": 5.968123912811279,
      "learning_rate": 9.576594607807465e-09,
      "loss": 2.2378,
      "step": 236
    },
    {
      "epoch": 1.0031746031746032,
      "grad_norm": 6.985171318054199,
      "learning_rate": 0.0,
      "loss": 2.7958,
      "step": 237
    }
  ],
  "logging_steps": 1,
  "max_steps": 237,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 2,
  "save_steps": 60,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 7072432993075200.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}