{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.9942363112391931,
  "eval_steps": 500,
  "global_step": 115,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.008645533141210375,
      "grad_norm": 34.72848892211914,
      "learning_rate": 5.0000000000000004e-08,
      "loss": 2.477,
      "step": 1
    },
    {
      "epoch": 0.01729106628242075,
      "grad_norm": 33.733909606933594,
      "learning_rate": 1.0000000000000001e-07,
      "loss": 2.4134,
      "step": 2
    },
    {
      "epoch": 0.025936599423631124,
      "grad_norm": 34.543819427490234,
      "learning_rate": 1.5000000000000002e-07,
      "loss": 2.4467,
      "step": 3
    },
    {
      "epoch": 0.0345821325648415,
      "grad_norm": 35.37831115722656,
      "learning_rate": 2.0000000000000002e-07,
      "loss": 2.4801,
      "step": 4
    },
    {
      "epoch": 0.043227665706051875,
      "grad_norm": 33.97856140136719,
      "learning_rate": 2.5000000000000004e-07,
      "loss": 2.4422,
      "step": 5
    },
    {
      "epoch": 0.05187319884726225,
      "grad_norm": 34.11160659790039,
      "learning_rate": 3.0000000000000004e-07,
      "loss": 2.4003,
      "step": 6
    },
    {
      "epoch": 0.06051873198847262,
      "grad_norm": 34.086463928222656,
      "learning_rate": 3.5000000000000004e-07,
      "loss": 2.4211,
      "step": 7
    },
    {
      "epoch": 0.069164265129683,
      "grad_norm": 33.96665573120117,
      "learning_rate": 4.0000000000000003e-07,
      "loss": 2.4054,
      "step": 8
    },
    {
      "epoch": 0.07780979827089338,
      "grad_norm": 34.871307373046875,
      "learning_rate": 4.5000000000000003e-07,
      "loss": 2.4077,
      "step": 9
    },
    {
      "epoch": 0.08645533141210375,
      "grad_norm": 33.91160583496094,
      "learning_rate": 5.000000000000001e-07,
      "loss": 2.3598,
      "step": 10
    },
    {
      "epoch": 0.09510086455331412,
      "grad_norm": 33.40217971801758,
      "learning_rate": 5.5e-07,
      "loss": 2.3209,
      "step": 11
    },
    {
      "epoch": 0.1037463976945245,
      "grad_norm": 33.771121978759766,
      "learning_rate": 6.000000000000001e-07,
      "loss": 2.3178,
      "step": 12
    },
    {
      "epoch": 0.11239193083573487,
      "grad_norm": 33.577476501464844,
      "learning_rate": 6.5e-07,
      "loss": 2.3107,
      "step": 13
    },
    {
      "epoch": 0.12103746397694524,
      "grad_norm": 31.330514907836914,
      "learning_rate": 7.000000000000001e-07,
      "loss": 2.095,
      "step": 14
    },
    {
      "epoch": 0.12968299711815562,
      "grad_norm": 33.60646057128906,
      "learning_rate": 7.5e-07,
      "loss": 2.1663,
      "step": 15
    },
    {
      "epoch": 0.138328530259366,
      "grad_norm": 31.96607208251953,
      "learning_rate": 8.000000000000001e-07,
      "loss": 1.9986,
      "step": 16
    },
    {
      "epoch": 0.14697406340057637,
      "grad_norm": 32.33183288574219,
      "learning_rate": 8.500000000000001e-07,
      "loss": 1.9401,
      "step": 17
    },
    {
      "epoch": 0.15561959654178675,
      "grad_norm": 33.50197219848633,
      "learning_rate": 9.000000000000001e-07,
      "loss": 1.8529,
      "step": 18
    },
    {
      "epoch": 0.1642651296829971,
      "grad_norm": 33.55098342895508,
      "learning_rate": 9.500000000000001e-07,
      "loss": 1.7087,
      "step": 19
    },
    {
      "epoch": 0.1729106628242075,
      "grad_norm": 33.90129852294922,
      "learning_rate": 1.0000000000000002e-06,
      "loss": 1.6324,
      "step": 20
    },
    {
      "epoch": 0.18155619596541786,
      "grad_norm": 33.738037109375,
      "learning_rate": 1.0500000000000001e-06,
      "loss": 1.4896,
      "step": 21
    },
    {
      "epoch": 0.19020172910662825,
      "grad_norm": 33.6258659362793,
      "learning_rate": 1.1e-06,
      "loss": 1.3664,
      "step": 22
    },
    {
      "epoch": 0.1988472622478386,
      "grad_norm": 30.822349548339844,
      "learning_rate": 1.1500000000000002e-06,
      "loss": 1.2193,
      "step": 23
    },
    {
      "epoch": 0.207492795389049,
      "grad_norm": 29.608501434326172,
      "learning_rate": 1.2000000000000002e-06,
      "loss": 1.074,
      "step": 24
    },
    {
      "epoch": 0.21613832853025935,
      "grad_norm": 27.651105880737305,
      "learning_rate": 1.25e-06,
      "loss": 0.938,
      "step": 25
    },
    {
      "epoch": 0.22478386167146974,
      "grad_norm": 29.479637145996094,
      "learning_rate": 1.3e-06,
      "loss": 0.7728,
      "step": 26
    },
    {
      "epoch": 0.2334293948126801,
      "grad_norm": 29.068634033203125,
      "learning_rate": 1.3500000000000002e-06,
      "loss": 0.6051,
      "step": 27
    },
    {
      "epoch": 0.2420749279538905,
      "grad_norm": 24.850099563598633,
      "learning_rate": 1.4000000000000001e-06,
      "loss": 0.4463,
      "step": 28
    },
    {
      "epoch": 0.2507204610951009,
      "grad_norm": 22.095216751098633,
      "learning_rate": 1.45e-06,
      "loss": 0.3489,
      "step": 29
    },
    {
      "epoch": 0.25936599423631124,
      "grad_norm": 19.491201400756836,
      "learning_rate": 1.5e-06,
      "loss": 0.261,
      "step": 30
    },
    {
      "epoch": 0.2680115273775216,
      "grad_norm": 14.492341041564941,
      "learning_rate": 1.5500000000000002e-06,
      "loss": 0.1707,
      "step": 31
    },
    {
      "epoch": 0.276657060518732,
      "grad_norm": 6.020577907562256,
      "learning_rate": 1.6000000000000001e-06,
      "loss": 0.1151,
      "step": 32
    },
    {
      "epoch": 0.28530259365994237,
      "grad_norm": 2.90791916847229,
      "learning_rate": 1.6500000000000003e-06,
      "loss": 0.0976,
      "step": 33
    },
    {
      "epoch": 0.29394812680115273,
      "grad_norm": 2.637803554534912,
      "learning_rate": 1.7000000000000002e-06,
      "loss": 0.0911,
      "step": 34
    },
    {
      "epoch": 0.3025936599423631,
      "grad_norm": 1.804861068725586,
      "learning_rate": 1.75e-06,
      "loss": 0.0834,
      "step": 35
    },
    {
      "epoch": 0.3112391930835735,
      "grad_norm": 2.049024820327759,
      "learning_rate": 1.8000000000000001e-06,
      "loss": 0.0842,
      "step": 36
    },
    {
      "epoch": 0.31988472622478387,
      "grad_norm": 1.3263498544692993,
      "learning_rate": 1.85e-06,
      "loss": 0.0744,
      "step": 37
    },
    {
      "epoch": 0.3285302593659942,
      "grad_norm": 1.7187089920043945,
      "learning_rate": 1.9000000000000002e-06,
      "loss": 0.0783,
      "step": 38
    },
    {
      "epoch": 0.3371757925072046,
      "grad_norm": 1.3925131559371948,
      "learning_rate": 1.9500000000000004e-06,
      "loss": 0.073,
      "step": 39
    },
    {
      "epoch": 0.345821325648415,
      "grad_norm": 1.2181739807128906,
      "learning_rate": 2.0000000000000003e-06,
      "loss": 0.0749,
      "step": 40
    },
    {
      "epoch": 0.35446685878962536,
      "grad_norm": 1.0519245862960815,
      "learning_rate": 2.05e-06,
      "loss": 0.0692,
      "step": 41
    },
    {
      "epoch": 0.3631123919308357,
      "grad_norm": 0.9188923835754395,
      "learning_rate": 2.1000000000000002e-06,
      "loss": 0.0726,
      "step": 42
    },
    {
      "epoch": 0.37175792507204614,
      "grad_norm": 0.8273228406906128,
      "learning_rate": 2.15e-06,
      "loss": 0.0651,
      "step": 43
    },
    {
      "epoch": 0.3804034582132565,
      "grad_norm": 0.9098994135856628,
      "learning_rate": 2.2e-06,
      "loss": 0.066,
      "step": 44
    },
    {
      "epoch": 0.38904899135446686,
      "grad_norm": 0.8456838726997375,
      "learning_rate": 2.25e-06,
      "loss": 0.0646,
      "step": 45
    },
    {
      "epoch": 0.3976945244956772,
      "grad_norm": 0.8240940570831299,
      "learning_rate": 2.3000000000000004e-06,
      "loss": 0.0604,
      "step": 46
    },
    {
      "epoch": 0.40634005763688763,
      "grad_norm": 1.111759901046753,
      "learning_rate": 2.35e-06,
      "loss": 0.0589,
      "step": 47
    },
    {
      "epoch": 0.414985590778098,
      "grad_norm": 0.9933035373687744,
      "learning_rate": 2.4000000000000003e-06,
      "loss": 0.0613,
      "step": 48
    },
    {
      "epoch": 0.42363112391930835,
      "grad_norm": 0.7491716742515564,
      "learning_rate": 2.4500000000000003e-06,
      "loss": 0.0583,
      "step": 49
    },
    {
      "epoch": 0.4322766570605187,
      "grad_norm": 0.9089523553848267,
      "learning_rate": 2.5e-06,
      "loss": 0.0558,
      "step": 50
    },
    {
      "epoch": 0.4409221902017291,
      "grad_norm": 0.7088611721992493,
      "learning_rate": 2.55e-06,
      "loss": 0.0553,
      "step": 51
    },
    {
      "epoch": 0.4495677233429395,
      "grad_norm": 0.7892571091651917,
      "learning_rate": 2.6e-06,
      "loss": 0.064,
      "step": 52
    },
    {
      "epoch": 0.45821325648414984,
      "grad_norm": 0.9248467087745667,
      "learning_rate": 2.6500000000000005e-06,
      "loss": 0.0653,
      "step": 53
    },
    {
      "epoch": 0.4668587896253602,
      "grad_norm": 0.7224969863891602,
      "learning_rate": 2.7000000000000004e-06,
      "loss": 0.0611,
      "step": 54
    },
    {
      "epoch": 0.4755043227665706,
      "grad_norm": 0.8231533765792847,
      "learning_rate": 2.7500000000000004e-06,
      "loss": 0.0617,
      "step": 55
    },
    {
      "epoch": 0.484149855907781,
      "grad_norm": 0.7306967973709106,
      "learning_rate": 2.8000000000000003e-06,
      "loss": 0.0571,
      "step": 56
    },
    {
      "epoch": 0.49279538904899134,
      "grad_norm": 0.8415323495864868,
      "learning_rate": 2.85e-06,
      "loss": 0.0548,
      "step": 57
    },
    {
      "epoch": 0.5014409221902018,
      "grad_norm": 1.5560295581817627,
      "learning_rate": 2.9e-06,
      "loss": 0.0672,
      "step": 58
    },
    {
      "epoch": 0.5100864553314121,
      "grad_norm": 0.9170955419540405,
      "learning_rate": 2.95e-06,
      "loss": 0.068,
      "step": 59
    },
    {
      "epoch": 0.5187319884726225,
      "grad_norm": 0.6508005857467651,
      "learning_rate": 3e-06,
      "loss": 0.057,
      "step": 60
    },
    {
      "epoch": 0.5273775216138329,
      "grad_norm": 0.8307355642318726,
      "learning_rate": 3.05e-06,
      "loss": 0.0598,
      "step": 61
    },
    {
      "epoch": 0.5360230547550432,
      "grad_norm": 1.11078679561615,
      "learning_rate": 3.1000000000000004e-06,
      "loss": 0.0575,
      "step": 62
    },
    {
      "epoch": 0.5446685878962536,
      "grad_norm": 1.0765758752822876,
      "learning_rate": 3.1500000000000003e-06,
      "loss": 0.0615,
      "step": 63
    },
    {
      "epoch": 0.553314121037464,
      "grad_norm": 0.8381508588790894,
      "learning_rate": 3.2000000000000003e-06,
      "loss": 0.0606,
      "step": 64
    },
    {
      "epoch": 0.5619596541786743,
      "grad_norm": 1.007628321647644,
      "learning_rate": 3.2500000000000002e-06,
      "loss": 0.0572,
      "step": 65
    },
    {
      "epoch": 0.5706051873198847,
      "grad_norm": 0.7254197597503662,
      "learning_rate": 3.3000000000000006e-06,
      "loss": 0.0543,
      "step": 66
    },
    {
      "epoch": 0.579250720461095,
      "grad_norm": 0.5906903147697449,
      "learning_rate": 3.3500000000000005e-06,
      "loss": 0.0557,
      "step": 67
    },
    {
      "epoch": 0.5878962536023055,
      "grad_norm": 0.6791537404060364,
      "learning_rate": 3.4000000000000005e-06,
      "loss": 0.0516,
      "step": 68
    },
    {
      "epoch": 0.5965417867435159,
      "grad_norm": 0.6390945315361023,
      "learning_rate": 3.45e-06,
      "loss": 0.0529,
      "step": 69
    },
    {
      "epoch": 0.6051873198847262,
      "grad_norm": 0.61552494764328,
      "learning_rate": 3.5e-06,
      "loss": 0.0554,
      "step": 70
    },
    {
      "epoch": 0.6138328530259366,
      "grad_norm": 0.6545206308364868,
      "learning_rate": 3.5500000000000003e-06,
      "loss": 0.0545,
      "step": 71
    },
    {
      "epoch": 0.622478386167147,
      "grad_norm": 0.9062793254852295,
      "learning_rate": 3.6000000000000003e-06,
      "loss": 0.0559,
      "step": 72
    },
    {
      "epoch": 0.6311239193083573,
      "grad_norm": 0.9642562866210938,
      "learning_rate": 3.65e-06,
      "loss": 0.0485,
      "step": 73
    },
    {
      "epoch": 0.6397694524495677,
      "grad_norm": 0.7286660075187683,
      "learning_rate": 3.7e-06,
      "loss": 0.0564,
      "step": 74
    },
    {
      "epoch": 0.6484149855907781,
      "grad_norm": 0.6356053948402405,
      "learning_rate": 3.7500000000000005e-06,
      "loss": 0.053,
      "step": 75
    },
    {
      "epoch": 0.6570605187319885,
      "grad_norm": 0.706794261932373,
      "learning_rate": 3.8000000000000005e-06,
      "loss": 0.0531,
      "step": 76
    },
    {
      "epoch": 0.6657060518731989,
      "grad_norm": 0.6616448163986206,
      "learning_rate": 3.85e-06,
      "loss": 0.0504,
      "step": 77
    },
    {
      "epoch": 0.6743515850144092,
      "grad_norm": 0.7465748190879822,
      "learning_rate": 3.900000000000001e-06,
      "loss": 0.0495,
      "step": 78
    },
    {
      "epoch": 0.6829971181556196,
      "grad_norm": 0.8153467774391174,
      "learning_rate": 3.95e-06,
      "loss": 0.0495,
      "step": 79
    },
    {
      "epoch": 0.69164265129683,
      "grad_norm": 0.7728897333145142,
      "learning_rate": 4.000000000000001e-06,
      "loss": 0.0434,
      "step": 80
    },
    {
      "epoch": 0.7002881844380403,
      "grad_norm": 0.6173391938209534,
      "learning_rate": 4.05e-06,
      "loss": 0.0432,
      "step": 81
    },
    {
      "epoch": 0.7089337175792507,
      "grad_norm": 0.7128047943115234,
      "learning_rate": 4.1e-06,
      "loss": 0.0512,
      "step": 82
    },
    {
      "epoch": 0.7175792507204611,
      "grad_norm": 0.6098653674125671,
      "learning_rate": 4.15e-06,
      "loss": 0.0415,
      "step": 83
    },
    {
      "epoch": 0.7262247838616714,
      "grad_norm": 0.7464293241500854,
      "learning_rate": 4.2000000000000004e-06,
      "loss": 0.0453,
      "step": 84
    },
    {
      "epoch": 0.7348703170028819,
      "grad_norm": 0.8350300788879395,
      "learning_rate": 4.25e-06,
      "loss": 0.0463,
      "step": 85
    },
    {
      "epoch": 0.7435158501440923,
      "grad_norm": 0.7880110740661621,
      "learning_rate": 4.3e-06,
      "loss": 0.0426,
      "step": 86
    },
    {
      "epoch": 0.7521613832853026,
      "grad_norm": 0.77886962890625,
      "learning_rate": 4.350000000000001e-06,
      "loss": 0.0476,
      "step": 87
    },
    {
      "epoch": 0.760806916426513,
      "grad_norm": 1.0404386520385742,
      "learning_rate": 4.4e-06,
      "loss": 0.0501,
      "step": 88
    },
    {
      "epoch": 0.7694524495677233,
      "grad_norm": 0.5827208757400513,
      "learning_rate": 4.450000000000001e-06,
      "loss": 0.0396,
      "step": 89
    },
    {
      "epoch": 0.7780979827089337,
      "grad_norm": 0.5928618907928467,
      "learning_rate": 4.5e-06,
      "loss": 0.0438,
      "step": 90
    },
    {
      "epoch": 0.7867435158501441,
      "grad_norm": 0.5311946272850037,
      "learning_rate": 4.5500000000000005e-06,
      "loss": 0.0388,
      "step": 91
    },
    {
      "epoch": 0.7953890489913544,
      "grad_norm": 0.7609073519706726,
      "learning_rate": 4.600000000000001e-06,
      "loss": 0.0403,
      "step": 92
    },
    {
      "epoch": 0.8040345821325648,
      "grad_norm": 0.6055853962898254,
      "learning_rate": 4.65e-06,
      "loss": 0.0402,
      "step": 93
    },
    {
      "epoch": 0.8126801152737753,
      "grad_norm": 0.8020023703575134,
      "learning_rate": 4.7e-06,
      "loss": 0.0415,
      "step": 94
    },
    {
      "epoch": 0.8213256484149856,
      "grad_norm": 0.9083772301673889,
      "learning_rate": 4.75e-06,
      "loss": 0.0428,
      "step": 95
    },
    {
      "epoch": 0.829971181556196,
      "grad_norm": 0.6658433079719543,
      "learning_rate": 4.800000000000001e-06,
      "loss": 0.0381,
      "step": 96
    },
    {
      "epoch": 0.8386167146974063,
      "grad_norm": 0.925826907157898,
      "learning_rate": 4.85e-06,
      "loss": 0.0465,
      "step": 97
    },
    {
      "epoch": 0.8472622478386167,
      "grad_norm": 0.5956787467002869,
      "learning_rate": 4.9000000000000005e-06,
      "loss": 0.0429,
      "step": 98
    },
    {
      "epoch": 0.8559077809798271,
      "grad_norm": 0.8485273718833923,
      "learning_rate": 4.95e-06,
      "loss": 0.0465,
      "step": 99
    },
    {
      "epoch": 0.8645533141210374,
      "grad_norm": 0.7477124333381653,
      "learning_rate": 5e-06,
      "loss": 0.0407,
      "step": 100
    },
    {
      "epoch": 0.8731988472622478,
      "grad_norm": 0.624204695224762,
      "learning_rate": 4.999964559102694e-06,
      "loss": 0.0433,
      "step": 101
    },
    {
      "epoch": 0.8818443804034583,
      "grad_norm": 0.6230912804603577,
      "learning_rate": 4.999858237415621e-06,
      "loss": 0.0364,
      "step": 102
    },
    {
      "epoch": 0.8904899135446686,
      "grad_norm": 0.9286472201347351,
      "learning_rate": 4.999681037953289e-06,
      "loss": 0.0385,
      "step": 103
    },
    {
      "epoch": 0.899135446685879,
      "grad_norm": 1.0528490543365479,
      "learning_rate": 4.999432965739786e-06,
      "loss": 0.0406,
      "step": 104
    },
    {
      "epoch": 0.9077809798270894,
      "grad_norm": 1.1465263366699219,
      "learning_rate": 4.999114027808632e-06,
      "loss": 0.0526,
      "step": 105
    },
    {
      "epoch": 0.9164265129682997,
      "grad_norm": 0.7173194885253906,
      "learning_rate": 4.998724233202585e-06,
      "loss": 0.05,
      "step": 106
    },
    {
      "epoch": 0.9250720461095101,
      "grad_norm": 0.7150623798370361,
      "learning_rate": 4.998263592973382e-06,
      "loss": 0.0392,
      "step": 107
    },
    {
      "epoch": 0.9337175792507204,
      "grad_norm": 0.6749414801597595,
      "learning_rate": 4.9977321201814235e-06,
      "loss": 0.0381,
      "step": 108
    },
    {
      "epoch": 0.9423631123919308,
      "grad_norm": 0.7057478427886963,
      "learning_rate": 4.997129829895409e-06,
      "loss": 0.0427,
      "step": 109
    },
    {
      "epoch": 0.9510086455331412,
      "grad_norm": 0.8370860815048218,
      "learning_rate": 4.996456739191905e-06,
      "loss": 0.0353,
      "step": 110
    },
    {
      "epoch": 0.9596541786743515,
      "grad_norm": 0.8583172559738159,
      "learning_rate": 4.995712867154863e-06,
      "loss": 0.0366,
      "step": 111
    },
    {
      "epoch": 0.968299711815562,
      "grad_norm": 0.9564568400382996,
      "learning_rate": 4.994898234875075e-06,
      "loss": 0.0463,
      "step": 112
    },
    {
      "epoch": 0.9769452449567724,
      "grad_norm": 0.7943828105926514,
      "learning_rate": 4.9940128654495826e-06,
      "loss": 0.0366,
      "step": 113
    },
    {
      "epoch": 0.9855907780979827,
      "grad_norm": 0.9387117624282837,
      "learning_rate": 4.9930567839810125e-06,
      "loss": 0.0433,
      "step": 114
    },
    {
      "epoch": 0.9942363112391931,
      "grad_norm": 0.5982036590576172,
      "learning_rate": 4.992030017576876e-06,
      "loss": 0.0311,
      "step": 115
    }
  ],
  "logging_steps": 1,
  "max_steps": 690,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 6,
  "save_steps": 115,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 2.904942201274368e+17,
  "train_batch_size": 4,
  "trial_name": null,
  "trial_params": null
}