{
  "best_global_step": null,
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 2.0,
  "eval_steps": 500,
  "global_step": 126,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.015873015873015872,
      "grad_norm": 2.355871594757968,
      "learning_rate": 0.0,
      "loss": 1.0469,
      "step": 1
    },
    {
      "epoch": 0.031746031746031744,
      "grad_norm": 2.29666205825573,
      "learning_rate": 1.5625e-06,
      "loss": 0.9929,
      "step": 2
    },
    {
      "epoch": 0.047619047619047616,
      "grad_norm": 2.535252155158116,
      "learning_rate": 3.125e-06,
      "loss": 1.0185,
      "step": 3
    },
    {
      "epoch": 0.06349206349206349,
      "grad_norm": 2.106429965859871,
      "learning_rate": 4.6875000000000004e-06,
      "loss": 0.9046,
      "step": 4
    },
    {
      "epoch": 0.07936507936507936,
      "grad_norm": 1.7754252196610092,
      "learning_rate": 6.25e-06,
      "loss": 1.0312,
      "step": 5
    },
    {
      "epoch": 0.09523809523809523,
      "grad_norm": 1.5212254656019404,
      "learning_rate": 7.8125e-06,
      "loss": 0.9741,
      "step": 6
    },
    {
      "epoch": 0.1111111111111111,
      "grad_norm": 1.2286700272250457,
      "learning_rate": 9.375000000000001e-06,
      "loss": 0.924,
      "step": 7
    },
    {
      "epoch": 0.12698412698412698,
      "grad_norm": 1.239763672997659,
      "learning_rate": 1.09375e-05,
      "loss": 0.9112,
      "step": 8
    },
    {
      "epoch": 0.14285714285714285,
      "grad_norm": 1.7804807603399884,
      "learning_rate": 1.25e-05,
      "loss": 0.9631,
      "step": 9
    },
    {
      "epoch": 0.15873015873015872,
      "grad_norm": 1.6096276860914913,
      "learning_rate": 1.4062500000000001e-05,
      "loss": 0.8914,
      "step": 10
    },
    {
      "epoch": 0.1746031746031746,
      "grad_norm": 1.4685478602306294,
      "learning_rate": 1.5625e-05,
      "loss": 0.8313,
      "step": 11
    },
    {
      "epoch": 0.19047619047619047,
      "grad_norm": 1.797675338951107,
      "learning_rate": 1.71875e-05,
      "loss": 0.9572,
      "step": 12
    },
    {
      "epoch": 0.20634920634920634,
      "grad_norm": 1.5020710264445867,
      "learning_rate": 1.8750000000000002e-05,
      "loss": 0.8929,
      "step": 13
    },
    {
      "epoch": 0.2222222222222222,
      "grad_norm": 1.389913325647765,
      "learning_rate": 2.0312500000000002e-05,
      "loss": 1.0575,
      "step": 14
    },
    {
      "epoch": 0.23809523809523808,
      "grad_norm": 1.0364172775494112,
      "learning_rate": 2.1875e-05,
      "loss": 0.9367,
      "step": 15
    },
    {
      "epoch": 0.25396825396825395,
      "grad_norm": 1.1754008678466592,
      "learning_rate": 2.34375e-05,
      "loss": 1.0082,
      "step": 16
    },
    {
      "epoch": 0.2698412698412698,
      "grad_norm": 1.0227204004003465,
      "learning_rate": 2.5e-05,
      "loss": 0.9148,
      "step": 17
    },
    {
      "epoch": 0.2857142857142857,
      "grad_norm": 1.0820292890536618,
      "learning_rate": 2.6562500000000002e-05,
      "loss": 0.9748,
      "step": 18
    },
    {
      "epoch": 0.30158730158730157,
      "grad_norm": 0.945837076799249,
      "learning_rate": 2.8125000000000003e-05,
      "loss": 0.7132,
      "step": 19
    },
    {
      "epoch": 0.31746031746031744,
      "grad_norm": 1.0248571882025115,
      "learning_rate": 2.96875e-05,
      "loss": 0.8881,
      "step": 20
    },
    {
      "epoch": 0.3333333333333333,
      "grad_norm": 0.7825673389448284,
      "learning_rate": 3.125e-05,
      "loss": 0.9596,
      "step": 21
    },
    {
      "epoch": 0.3492063492063492,
      "grad_norm": 0.9610289643147956,
      "learning_rate": 3.2812500000000005e-05,
      "loss": 1.0261,
      "step": 22
    },
    {
      "epoch": 0.36507936507936506,
      "grad_norm": 0.9669319262880848,
      "learning_rate": 3.4375e-05,
      "loss": 0.8504,
      "step": 23
    },
    {
      "epoch": 0.38095238095238093,
      "grad_norm": 0.7449356400588687,
      "learning_rate": 3.59375e-05,
      "loss": 0.8124,
      "step": 24
    },
    {
      "epoch": 0.3968253968253968,
      "grad_norm": 0.83693613965816,
      "learning_rate": 3.7500000000000003e-05,
      "loss": 1.0061,
      "step": 25
    },
    {
      "epoch": 0.4126984126984127,
      "grad_norm": 0.732383235323442,
      "learning_rate": 3.90625e-05,
      "loss": 0.8433,
      "step": 26
    },
    {
      "epoch": 0.42857142857142855,
      "grad_norm": 0.7794935876422098,
      "learning_rate": 4.0625000000000005e-05,
      "loss": 0.7042,
      "step": 27
    },
    {
      "epoch": 0.4444444444444444,
      "grad_norm": 0.7604958575268047,
      "learning_rate": 4.21875e-05,
      "loss": 0.9629,
      "step": 28
    },
    {
      "epoch": 0.4603174603174603,
      "grad_norm": 0.6984385536231642,
      "learning_rate": 4.375e-05,
      "loss": 0.8909,
      "step": 29
    },
    {
      "epoch": 0.47619047619047616,
      "grad_norm": 0.7941140442495155,
      "learning_rate": 4.5312500000000004e-05,
      "loss": 0.9318,
      "step": 30
    },
    {
      "epoch": 0.49206349206349204,
      "grad_norm": 0.7485507149365567,
      "learning_rate": 4.6875e-05,
      "loss": 0.9032,
      "step": 31
    },
    {
      "epoch": 0.5079365079365079,
      "grad_norm": 0.7312955579208906,
      "learning_rate": 4.8437500000000005e-05,
      "loss": 0.8793,
      "step": 32
    },
    {
      "epoch": 0.5238095238095238,
      "grad_norm": 0.728955139017027,
      "learning_rate": 5e-05,
      "loss": 1.0292,
      "step": 33
    },
    {
      "epoch": 0.5396825396825397,
      "grad_norm": 0.6223071714803796,
      "learning_rate": 4.999845960383972e-05,
      "loss": 0.829,
      "step": 34
    },
    {
      "epoch": 0.5555555555555556,
      "grad_norm": 0.7081482857388056,
      "learning_rate": 4.999383860518451e-05,
      "loss": 0.821,
      "step": 35
    },
    {
      "epoch": 0.5714285714285714,
      "grad_norm": 0.7021438050343367,
      "learning_rate": 4.998613757348784e-05,
      "loss": 0.9658,
      "step": 36
    },
    {
      "epoch": 0.5873015873015873,
      "grad_norm": 0.6005545292155794,
      "learning_rate": 4.9975357457760896e-05,
      "loss": 0.9805,
      "step": 37
    },
    {
      "epoch": 0.6031746031746031,
      "grad_norm": 0.66159765943155,
      "learning_rate": 4.9961499586455584e-05,
      "loss": 0.8479,
      "step": 38
    },
    {
      "epoch": 0.6190476190476191,
      "grad_norm": 0.6859851915992995,
      "learning_rate": 4.994456566730085e-05,
      "loss": 0.9104,
      "step": 39
    },
    {
      "epoch": 0.6349206349206349,
      "grad_norm": 0.5770937588145084,
      "learning_rate": 4.9924557787092216e-05,
      "loss": 0.7705,
      "step": 40
    },
    {
      "epoch": 0.6507936507936508,
      "grad_norm": 0.5587380636863567,
      "learning_rate": 4.990147841143462e-05,
      "loss": 0.8406,
      "step": 41
    },
    {
      "epoch": 0.6666666666666666,
      "grad_norm": 0.5939117737515469,
      "learning_rate": 4.9875330384438604e-05,
      "loss": 0.9143,
      "step": 42
    },
    {
      "epoch": 0.6825396825396826,
      "grad_norm": 0.5421902034671652,
      "learning_rate": 4.984611692836979e-05,
      "loss": 0.8323,
      "step": 43
    },
    {
      "epoch": 0.6984126984126984,
      "grad_norm": 0.5523631282552526,
      "learning_rate": 4.9813841643251836e-05,
      "loss": 0.7557,
      "step": 44
    },
    {
      "epoch": 0.7142857142857143,
      "grad_norm": 0.5991896816540728,
      "learning_rate": 4.977850850642275e-05,
      "loss": 0.8471,
      "step": 45
    },
    {
      "epoch": 0.7301587301587301,
      "grad_norm": 0.6364621652121066,
      "learning_rate": 4.97401218720448e-05,
      "loss": 0.8013,
      "step": 46
    },
    {
      "epoch": 0.746031746031746,
      "grad_norm": 0.5534873919742207,
      "learning_rate": 4.969868647056792e-05,
      "loss": 0.8996,
      "step": 47
    },
    {
      "epoch": 0.7619047619047619,
      "grad_norm": 0.5035034360883922,
      "learning_rate": 4.965420740814679e-05,
      "loss": 0.8944,
      "step": 48
    },
    {
      "epoch": 0.7777777777777778,
      "grad_norm": 0.5729489774574688,
      "learning_rate": 4.9606690166011546e-05,
      "loss": 0.7887,
      "step": 49
    },
    {
      "epoch": 0.7936507936507936,
      "grad_norm": 0.6004405465949967,
      "learning_rate": 4.95561405997924e-05,
      "loss": 0.831,
      "step": 50
    },
    {
      "epoch": 0.8095238095238095,
      "grad_norm": 0.725673276310606,
      "learning_rate": 4.9502564938797946e-05,
      "loss": 0.8849,
      "step": 51
    },
    {
      "epoch": 0.8253968253968254,
      "grad_norm": 0.4990176056299948,
      "learning_rate": 4.9445969785247595e-05,
      "loss": 0.8298,
      "step": 52
    },
    {
      "epoch": 0.8412698412698413,
      "grad_norm": 0.6071056927514447,
      "learning_rate": 4.938636211345792e-05,
      "loss": 0.944,
      "step": 53
    },
    {
      "epoch": 0.8571428571428571,
      "grad_norm": 0.6345636016627114,
      "learning_rate": 4.932374926898321e-05,
      "loss": 0.8069,
      "step": 54
    },
    {
      "epoch": 0.873015873015873,
      "grad_norm": 0.6333202856879505,
      "learning_rate": 4.9258138967710306e-05,
      "loss": 0.7373,
      "step": 55
    },
    {
      "epoch": 0.8888888888888888,
      "grad_norm": 0.5152048396222051,
      "learning_rate": 4.918953929490768e-05,
      "loss": 0.8855,
      "step": 56
    },
    {
      "epoch": 0.9047619047619048,
      "grad_norm": 0.5806639114473304,
      "learning_rate": 4.9117958704229154e-05,
      "loss": 0.8731,
      "step": 57
    },
    {
      "epoch": 0.9206349206349206,
      "grad_norm": 0.6001547400645247,
      "learning_rate": 4.904340601667208e-05,
      "loss": 0.816,
      "step": 58
    },
    {
      "epoch": 0.9365079365079365,
      "grad_norm": 0.470270082255384,
      "learning_rate": 4.8965890419490354e-05,
      "loss": 0.8847,
      "step": 59
    },
    {
      "epoch": 0.9523809523809523,
      "grad_norm": 0.5015222585808989,
      "learning_rate": 4.8885421465062236e-05,
      "loss": 0.8507,
      "step": 60
    },
    {
      "epoch": 0.9682539682539683,
      "grad_norm": 0.48808541077856465,
      "learning_rate": 4.88020090697132e-05,
      "loss": 0.774,
      "step": 61
    },
    {
      "epoch": 0.9841269841269841,
      "grad_norm": 0.5837250225569859,
      "learning_rate": 4.871566351249393e-05,
      "loss": 0.8844,
      "step": 62
    },
    {
      "epoch": 1.0,
      "grad_norm": 0.5121395435398158,
      "learning_rate": 4.86263954339136e-05,
      "loss": 0.7565,
      "step": 63
    },
    {
      "epoch": 1.0158730158730158,
      "grad_norm": 0.858989786993005,
      "learning_rate": 4.853421583462866e-05,
      "loss": 0.7147,
      "step": 64
    },
    {
      "epoch": 1.0317460317460316,
      "grad_norm": 0.6819369439457027,
      "learning_rate": 4.843913607408717e-05,
      "loss": 0.7632,
      "step": 65
    },
    {
      "epoch": 1.0476190476190477,
      "grad_norm": 0.8758215098676306,
      "learning_rate": 4.834116786912897e-05,
      "loss": 0.7952,
      "step": 66
    },
    {
      "epoch": 1.0634920634920635,
      "grad_norm": 0.5971995504609642,
      "learning_rate": 4.82403232925418e-05,
      "loss": 0.6327,
      "step": 67
    },
    {
      "epoch": 1.0793650793650793,
      "grad_norm": 0.5651140794936931,
      "learning_rate": 4.8136614771573554e-05,
      "loss": 0.6429,
      "step": 68
    },
    {
      "epoch": 1.0952380952380953,
      "grad_norm": 0.882155318220025,
      "learning_rate": 4.8030055086400826e-05,
      "loss": 0.8083,
      "step": 69
    },
    {
      "epoch": 1.1111111111111112,
      "grad_norm": 0.7712424011094504,
      "learning_rate": 4.7920657368554e-05,
      "loss": 0.6792,
      "step": 70
    },
    {
      "epoch": 1.126984126984127,
      "grad_norm": 0.5624839067932064,
      "learning_rate": 4.7808435099299045e-05,
      "loss": 0.6928,
      "step": 71
    },
    {
      "epoch": 1.1428571428571428,
      "grad_norm": 0.5634668991057131,
      "learning_rate": 4.7693402107976174e-05,
      "loss": 0.7191,
      "step": 72
    },
    {
      "epoch": 1.1587301587301586,
      "grad_norm": 0.6557940355672685,
      "learning_rate": 4.757557257029564e-05,
      "loss": 0.7138,
      "step": 73
    },
    {
      "epoch": 1.1746031746031746,
      "grad_norm": 0.5576756408219278,
      "learning_rate": 4.745496100659082e-05,
      "loss": 0.6904,
      "step": 74
    },
    {
      "epoch": 1.1904761904761905,
      "grad_norm": 0.5394945009236098,
      "learning_rate": 4.7331582280028906e-05,
      "loss": 0.6684,
      "step": 75
    },
    {
      "epoch": 1.2063492063492063,
      "grad_norm": 0.5616484225088534,
      "learning_rate": 4.720545159477922e-05,
      "loss": 0.6123,
      "step": 76
    },
    {
      "epoch": 1.2222222222222223,
      "grad_norm": 0.6137522865571288,
      "learning_rate": 4.7076584494139606e-05,
      "loss": 0.6639,
      "step": 77
    },
    {
      "epoch": 1.2380952380952381,
      "grad_norm": 0.5520563824703866,
      "learning_rate": 4.694499685862106e-05,
      "loss": 0.7504,
      "step": 78
    },
    {
      "epoch": 1.253968253968254,
      "grad_norm": 0.6398395502333153,
      "learning_rate": 4.6810704903990634e-05,
      "loss": 0.8063,
      "step": 79
    },
    {
      "epoch": 1.2698412698412698,
      "grad_norm": 0.5170068764903927,
      "learning_rate": 4.667372517927323e-05,
      "loss": 0.682,
      "step": 80
    },
    {
      "epoch": 1.2857142857142856,
      "grad_norm": 0.5470142100714379,
      "learning_rate": 4.653407456471222e-05,
      "loss": 0.74,
      "step": 81
    },
    {
      "epoch": 1.3015873015873016,
      "grad_norm": 0.5344699813999502,
      "learning_rate": 4.6391770269689236e-05,
      "loss": 0.7019,
      "step": 82
    },
    {
      "epoch": 1.3174603174603174,
      "grad_norm": 0.572242361510543,
      "learning_rate": 4.6246829830603454e-05,
      "loss": 0.7612,
      "step": 83
    },
    {
      "epoch": 1.3333333333333333,
      "grad_norm": 0.5918389811121451,
      "learning_rate": 4.609927110871053e-05,
      "loss": 0.7285,
      "step": 84
    },
    {
      "epoch": 1.3492063492063493,
      "grad_norm": 0.4866622733839569,
      "learning_rate": 4.594911228792156e-05,
      "loss": 0.656,
      "step": 85
    },
    {
      "epoch": 1.3650793650793651,
      "grad_norm": 0.5275973128412808,
      "learning_rate": 4.579637187256222e-05,
      "loss": 0.576,
      "step": 86
    },
    {
      "epoch": 1.380952380952381,
      "grad_norm": 0.5488033313933244,
      "learning_rate": 4.564106868509246e-05,
      "loss": 0.7176,
      "step": 87
    },
    {
      "epoch": 1.3968253968253967,
      "grad_norm": 0.6920680886388099,
      "learning_rate": 4.548322186378697e-05,
      "loss": 0.7926,
      "step": 88
    },
    {
      "epoch": 1.4126984126984126,
      "grad_norm": 0.774236286341856,
      "learning_rate": 4.532285086037674e-05,
      "loss": 0.7313,
      "step": 89
    },
    {
      "epoch": 1.4285714285714286,
      "grad_norm": 0.7799985101441093,
      "learning_rate": 4.5159975437652017e-05,
      "loss": 0.717,
      "step": 90
    },
    {
      "epoch": 1.4444444444444444,
      "grad_norm": 0.5542880474504607,
      "learning_rate": 4.499461566702685e-05,
      "loss": 0.5701,
      "step": 91
    },
    {
      "epoch": 1.4603174603174602,
      "grad_norm": 0.6118784803715336,
      "learning_rate": 4.48267919260657e-05,
      "loss": 0.7026,
      "step": 92
    },
    {
      "epoch": 1.4761904761904763,
      "grad_norm": 0.6649407372701752,
      "learning_rate": 4.4656524895972255e-05,
      "loss": 0.7061,
      "step": 93
    },
    {
      "epoch": 1.492063492063492,
      "grad_norm": 0.47895549061427817,
      "learning_rate": 4.448383555904088e-05,
      "loss": 0.6387,
      "step": 94
    },
    {
      "epoch": 1.507936507936508,
      "grad_norm": 0.5811905127982857,
      "learning_rate": 4.430874519607089e-05,
      "loss": 0.8295,
      "step": 95
    },
    {
      "epoch": 1.5238095238095237,
      "grad_norm": 0.6782303990614583,
      "learning_rate": 4.413127538374411e-05,
      "loss": 0.7571,
      "step": 96
    },
    {
      "epoch": 1.5396825396825395,
      "grad_norm": 0.5127521378901643,
      "learning_rate": 4.395144799196593e-05,
      "loss": 0.6259,
      "step": 97
    },
    {
      "epoch": 1.5555555555555556,
      "grad_norm": 1.1333047155488623,
      "learning_rate": 4.376928518117027e-05,
      "loss": 0.7263,
      "step": 98
    },
    {
      "epoch": 1.5714285714285714,
      "grad_norm": 0.9285725347831506,
      "learning_rate": 4.358480939958867e-05,
      "loss": 0.6652,
      "step": 99
    },
    {
      "epoch": 1.5873015873015874,
      "grad_norm": 0.5756004852981952,
      "learning_rate": 4.3398043380483965e-05,
      "loss": 0.7045,
      "step": 100
    },
    {
      "epoch": 1.6031746031746033,
      "grad_norm": 0.5732214165272889,
      "learning_rate": 4.320901013934887e-05,
      "loss": 0.7096,
      "step": 101
    },
    {
      "epoch": 1.619047619047619,
      "grad_norm": 0.5729960942540637,
      "learning_rate": 4.3017732971069674e-05,
      "loss": 0.7797,
      "step": 102
    },
    {
      "epoch": 1.6349206349206349,
      "grad_norm": 0.6414711093856016,
      "learning_rate": 4.282423544705564e-05,
      "loss": 0.75,
      "step": 103
    },
    {
      "epoch": 1.6507936507936507,
      "grad_norm": 0.48208643464721207,
      "learning_rate": 4.262854141233419e-05,
      "loss": 0.7566,
      "step": 104
    },
    {
      "epoch": 1.6666666666666665,
      "grad_norm": 0.5650935089244651,
      "learning_rate": 4.2430674982612506e-05,
      "loss": 0.7282,
      "step": 105
    },
    {
      "epoch": 1.6825396825396826,
      "grad_norm": 0.6266660832902915,
      "learning_rate": 4.223066054130568e-05,
      "loss": 0.7098,
      "step": 106
    },
    {
      "epoch": 1.6984126984126984,
      "grad_norm": 1.1721379739857851,
      "learning_rate": 4.2028522736531895e-05,
      "loss": 0.7244,
      "step": 107
    },
    {
      "epoch": 1.7142857142857144,
      "grad_norm": 0.5821734258045642,
      "learning_rate": 4.1824286478075025e-05,
      "loss": 0.7918,
      "step": 108
    },
    {
      "epoch": 1.7301587301587302,
      "grad_norm": 0.5675713145707344,
      "learning_rate": 4.161797693431493e-05,
      "loss": 0.7271,
      "step": 109
    },
    {
      "epoch": 1.746031746031746,
      "grad_norm": 0.5948316073979433,
      "learning_rate": 4.140961952912594e-05,
      "loss": 0.6585,
      "step": 110
    },
    {
      "epoch": 1.7619047619047619,
      "grad_norm": 0.6142301353494962,
      "learning_rate": 4.1199239938743797e-05,
      "loss": 0.6636,
      "step": 111
    },
    {
      "epoch": 1.7777777777777777,
      "grad_norm": 0.6089779675550376,
      "learning_rate": 4.0986864088601564e-05,
      "loss": 0.6483,
      "step": 112
    },
    {
      "epoch": 1.7936507936507935,
      "grad_norm": 0.5407284417083653,
      "learning_rate": 4.077251815013477e-05,
      "loss": 0.6273,
      "step": 113
    },
    {
      "epoch": 1.8095238095238095,
      "grad_norm": 0.5554496556982176,
      "learning_rate": 4.0556228537556266e-05,
      "loss": 0.6301,
      "step": 114
    },
    {
      "epoch": 1.8253968253968254,
      "grad_norm": 0.5507291755794801,
      "learning_rate": 4.0338021904601145e-05,
      "loss": 0.6909,
      "step": 115
    },
    {
      "epoch": 1.8412698412698414,
      "grad_norm": 0.4537046958331062,
      "learning_rate": 4.0117925141242174e-05,
      "loss": 0.7491,
      "step": 116
    },
    {
      "epoch": 1.8571428571428572,
      "grad_norm": 0.5463750469400513,
      "learning_rate": 3.9895965370376076e-05,
      "loss": 0.8075,
      "step": 117
    },
    {
      "epoch": 1.873015873015873,
      "grad_norm": 0.5027853264982712,
      "learning_rate": 3.9672169944481165e-05,
      "loss": 0.5601,
      "step": 118
    },
    {
      "epoch": 1.8888888888888888,
      "grad_norm": 0.5661467536668536,
      "learning_rate": 3.944656644224661e-05,
      "loss": 0.7353,
      "step": 119
    },
    {
      "epoch": 1.9047619047619047,
      "grad_norm": 0.48806777854236366,
      "learning_rate": 3.921918266517391e-05,
      "loss": 0.6765,
      "step": 120
    },
    {
      "epoch": 1.9206349206349205,
      "grad_norm": 0.5877767380659309,
      "learning_rate": 3.899004663415084e-05,
      "loss": 0.707,
      "step": 121
    },
    {
      "epoch": 1.9365079365079365,
      "grad_norm": 0.5311318468752881,
      "learning_rate": 3.875918658599837e-05,
      "loss": 0.7882,
      "step": 122
    },
    {
      "epoch": 1.9523809523809523,
      "grad_norm": 0.5682753083153059,
      "learning_rate": 3.8526630969991035e-05,
      "loss": 0.6445,
      "step": 123
    },
    {
      "epoch": 1.9682539682539684,
      "grad_norm": 0.4740591298744526,
      "learning_rate": 3.8292408444351094e-05,
      "loss": 0.6718,
      "step": 124
    },
    {
      "epoch": 1.9841269841269842,
      "grad_norm": 0.45882583861407755,
      "learning_rate": 3.805654787271686e-05,
      "loss": 0.6762,
      "step": 125
    },
    {
      "epoch": 2.0,
      "grad_norm": 0.5675883245832433,
      "learning_rate": 3.781907832058587e-05,
      "loss": 0.7781,
      "step": 126
    }
  ],
  "logging_steps": 1,
  "max_steps": 315,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 5,
  "save_steps": 500,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 31413415968768.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}