{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.5208333333333334,
  "eval_steps": 9,
  "global_step": 100,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.005208333333333333,
      "grad_norm": 1.149965763092041,
      "learning_rate": 2.0000000000000003e-06,
      "loss": 3.1312,
      "step": 1
    },
    {
      "epoch": 0.005208333333333333,
      "eval_loss": 3.160311460494995,
      "eval_runtime": 2.6854,
      "eval_samples_per_second": 60.326,
      "eval_steps_per_second": 7.82,
      "step": 1
    },
    {
      "epoch": 0.010416666666666666,
      "grad_norm": 1.072540521621704,
      "learning_rate": 4.000000000000001e-06,
      "loss": 3.1759,
      "step": 2
    },
    {
      "epoch": 0.015625,
      "grad_norm": 1.0272471904754639,
      "learning_rate": 6e-06,
      "loss": 3.1055,
      "step": 3
    },
    {
      "epoch": 0.020833333333333332,
      "grad_norm": 1.1299035549163818,
      "learning_rate": 8.000000000000001e-06,
      "loss": 3.2217,
      "step": 4
    },
    {
      "epoch": 0.026041666666666668,
      "grad_norm": 0.9919382929801941,
      "learning_rate": 1e-05,
      "loss": 3.028,
      "step": 5
    },
    {
      "epoch": 0.03125,
      "grad_norm": 1.0636495351791382,
      "learning_rate": 1.2e-05,
      "loss": 3.2194,
      "step": 6
    },
    {
      "epoch": 0.036458333333333336,
      "grad_norm": 1.0188517570495605,
      "learning_rate": 1.4e-05,
      "loss": 3.1403,
      "step": 7
    },
    {
      "epoch": 0.041666666666666664,
      "grad_norm": 1.1026723384857178,
      "learning_rate": 1.6000000000000003e-05,
      "loss": 3.1992,
      "step": 8
    },
    {
      "epoch": 0.046875,
      "grad_norm": 0.966528058052063,
      "learning_rate": 1.8e-05,
      "loss": 3.0237,
      "step": 9
    },
    {
      "epoch": 0.046875,
      "eval_loss": 3.1478817462921143,
      "eval_runtime": 2.0938,
      "eval_samples_per_second": 77.372,
      "eval_steps_per_second": 10.03,
      "step": 9
    },
    {
      "epoch": 0.052083333333333336,
      "grad_norm": 0.8940801620483398,
      "learning_rate": 2e-05,
      "loss": 3.0852,
      "step": 10
    },
    {
      "epoch": 0.057291666666666664,
      "grad_norm": 1.0513722896575928,
      "learning_rate": 1.999390827019096e-05,
      "loss": 3.2125,
      "step": 11
    },
    {
      "epoch": 0.0625,
      "grad_norm": 0.9304180145263672,
      "learning_rate": 1.9975640502598243e-05,
      "loss": 3.1098,
      "step": 12
    },
    {
      "epoch": 0.06770833333333333,
      "grad_norm": 0.7351564168930054,
      "learning_rate": 1.9945218953682736e-05,
      "loss": 3.0332,
      "step": 13
    },
    {
      "epoch": 0.07291666666666667,
      "grad_norm": 0.862900972366333,
      "learning_rate": 1.9902680687415704e-05,
      "loss": 3.173,
      "step": 14
    },
    {
      "epoch": 0.078125,
      "grad_norm": 0.7154681086540222,
      "learning_rate": 1.9848077530122083e-05,
      "loss": 3.0754,
      "step": 15
    },
    {
      "epoch": 0.08333333333333333,
      "grad_norm": 0.8201392889022827,
      "learning_rate": 1.9781476007338058e-05,
      "loss": 3.1666,
      "step": 16
    },
    {
      "epoch": 0.08854166666666667,
      "grad_norm": 0.7526658177375793,
      "learning_rate": 1.9702957262759964e-05,
      "loss": 3.0601,
      "step": 17
    },
    {
      "epoch": 0.09375,
      "grad_norm": 0.7286026477813721,
      "learning_rate": 1.961261695938319e-05,
      "loss": 3.0727,
      "step": 18
    },
    {
      "epoch": 0.09375,
      "eval_loss": 3.06829571723938,
      "eval_runtime": 2.1125,
      "eval_samples_per_second": 76.688,
      "eval_steps_per_second": 9.941,
      "step": 18
    },
    {
      "epoch": 0.09895833333333333,
      "grad_norm": 0.6828358769416809,
      "learning_rate": 1.9510565162951538e-05,
      "loss": 3.0873,
      "step": 19
    },
    {
      "epoch": 0.10416666666666667,
      "grad_norm": 0.7122036814689636,
      "learning_rate": 1.9396926207859085e-05,
      "loss": 3.042,
      "step": 20
    },
    {
      "epoch": 0.109375,
      "grad_norm": 0.642253577709198,
      "learning_rate": 1.9271838545667876e-05,
      "loss": 3.0086,
      "step": 21
    },
    {
      "epoch": 0.11458333333333333,
      "grad_norm": 0.7375343441963196,
      "learning_rate": 1.913545457642601e-05,
      "loss": 3.0629,
      "step": 22
    },
    {
      "epoch": 0.11979166666666667,
      "grad_norm": 0.6836945414543152,
      "learning_rate": 1.8987940462991673e-05,
      "loss": 3.0095,
      "step": 23
    },
    {
      "epoch": 0.125,
      "grad_norm": 0.8602219820022583,
      "learning_rate": 1.8829475928589272e-05,
      "loss": 3.0885,
      "step": 24
    },
    {
      "epoch": 0.13020833333333334,
      "grad_norm": 0.6618623733520508,
      "learning_rate": 1.866025403784439e-05,
      "loss": 2.9082,
      "step": 25
    },
    {
      "epoch": 0.13541666666666666,
      "grad_norm": 0.7362732887268066,
      "learning_rate": 1.848048096156426e-05,
      "loss": 2.9769,
      "step": 26
    },
    {
      "epoch": 0.140625,
      "grad_norm": 0.6465035080909729,
      "learning_rate": 1.8290375725550417e-05,
      "loss": 2.946,
      "step": 27
    },
    {
      "epoch": 0.140625,
      "eval_loss": 2.9850566387176514,
      "eval_runtime": 2.1389,
      "eval_samples_per_second": 75.74,
      "eval_steps_per_second": 9.818,
      "step": 27
    },
    {
      "epoch": 0.14583333333333334,
      "grad_norm": 0.6484801769256592,
      "learning_rate": 1.8090169943749477e-05,
      "loss": 2.9388,
      "step": 28
    },
    {
      "epoch": 0.15104166666666666,
      "grad_norm": 0.6423029899597168,
      "learning_rate": 1.788010753606722e-05,
      "loss": 2.874,
      "step": 29
    },
    {
      "epoch": 0.15625,
      "grad_norm": 0.641499936580658,
      "learning_rate": 1.766044443118978e-05,
      "loss": 2.961,
      "step": 30
    },
    {
      "epoch": 0.16145833333333334,
      "grad_norm": 0.669302225112915,
      "learning_rate": 1.7431448254773943e-05,
      "loss": 2.918,
      "step": 31
    },
    {
      "epoch": 0.16666666666666666,
      "grad_norm": 0.5931358933448792,
      "learning_rate": 1.7193398003386514e-05,
      "loss": 2.9327,
      "step": 32
    },
    {
      "epoch": 0.171875,
      "grad_norm": 0.6197303533554077,
      "learning_rate": 1.6946583704589973e-05,
      "loss": 2.8986,
      "step": 33
    },
    {
      "epoch": 0.17708333333333334,
      "grad_norm": 0.5762773752212524,
      "learning_rate": 1.6691306063588583e-05,
      "loss": 2.8925,
      "step": 34
    },
    {
      "epoch": 0.18229166666666666,
      "grad_norm": 0.5871465802192688,
      "learning_rate": 1.6427876096865394e-05,
      "loss": 2.9471,
      "step": 35
    },
    {
      "epoch": 0.1875,
      "grad_norm": 0.6552653312683105,
      "learning_rate": 1.6156614753256583e-05,
      "loss": 2.9724,
      "step": 36
    },
    {
      "epoch": 0.1875,
      "eval_loss": 2.9104537963867188,
      "eval_runtime": 2.0723,
      "eval_samples_per_second": 78.172,
      "eval_steps_per_second": 10.133,
      "step": 36
    },
    {
      "epoch": 0.19270833333333334,
      "grad_norm": 0.6476786732673645,
      "learning_rate": 1.5877852522924733e-05,
      "loss": 2.9259,
      "step": 37
    },
    {
      "epoch": 0.19791666666666666,
      "grad_norm": 0.6450286507606506,
      "learning_rate": 1.5591929034707468e-05,
      "loss": 2.8913,
      "step": 38
    },
    {
      "epoch": 0.203125,
      "grad_norm": 0.5890446901321411,
      "learning_rate": 1.529919264233205e-05,
      "loss": 2.9457,
      "step": 39
    },
    {
      "epoch": 0.20833333333333334,
      "grad_norm": 0.6238468885421753,
      "learning_rate": 1.5000000000000002e-05,
      "loss": 2.8409,
      "step": 40
    },
    {
      "epoch": 0.21354166666666666,
      "grad_norm": 0.5730621814727783,
      "learning_rate": 1.469471562785891e-05,
      "loss": 2.7774,
      "step": 41
    },
    {
      "epoch": 0.21875,
      "grad_norm": 0.5432677268981934,
      "learning_rate": 1.4383711467890776e-05,
      "loss": 2.8458,
      "step": 42
    },
    {
      "epoch": 0.22395833333333334,
      "grad_norm": 0.5576301217079163,
      "learning_rate": 1.4067366430758004e-05,
      "loss": 2.888,
      "step": 43
    },
    {
      "epoch": 0.22916666666666666,
      "grad_norm": 0.5752390027046204,
      "learning_rate": 1.3746065934159123e-05,
      "loss": 2.8943,
      "step": 44
    },
    {
      "epoch": 0.234375,
      "grad_norm": 0.5436639785766602,
      "learning_rate": 1.342020143325669e-05,
      "loss": 2.8378,
      "step": 45
    },
    {
      "epoch": 0.234375,
      "eval_loss": 2.8462777137756348,
      "eval_runtime": 2.0769,
      "eval_samples_per_second": 78.0,
      "eval_steps_per_second": 10.111,
      "step": 45
    },
    {
      "epoch": 0.23958333333333334,
      "grad_norm": 0.5786373615264893,
      "learning_rate": 1.3090169943749475e-05,
      "loss": 2.8375,
      "step": 46
    },
    {
      "epoch": 0.24479166666666666,
      "grad_norm": 0.5880608558654785,
      "learning_rate": 1.2756373558169992e-05,
      "loss": 2.8433,
      "step": 47
    },
    {
      "epoch": 0.25,
      "grad_norm": 0.5975544452667236,
      "learning_rate": 1.2419218955996677e-05,
      "loss": 2.7899,
      "step": 48
    },
    {
      "epoch": 0.2552083333333333,
      "grad_norm": 0.5674802660942078,
      "learning_rate": 1.2079116908177592e-05,
      "loss": 2.8498,
      "step": 49
    },
    {
      "epoch": 0.2604166666666667,
      "grad_norm": 0.5659404397010803,
      "learning_rate": 1.1736481776669307e-05,
      "loss": 2.8706,
      "step": 50
    },
    {
      "epoch": 0.265625,
      "grad_norm": 0.5767154693603516,
      "learning_rate": 1.1391731009600655e-05,
      "loss": 2.7859,
      "step": 51
    },
    {
      "epoch": 0.2708333333333333,
      "grad_norm": 0.5515008568763733,
      "learning_rate": 1.1045284632676535e-05,
      "loss": 2.6711,
      "step": 52
    },
    {
      "epoch": 0.2760416666666667,
      "grad_norm": 0.6159852147102356,
      "learning_rate": 1.0697564737441254e-05,
      "loss": 2.8207,
      "step": 53
    },
    {
      "epoch": 0.28125,
      "grad_norm": 0.5904491543769836,
      "learning_rate": 1.0348994967025012e-05,
      "loss": 2.7894,
      "step": 54
    },
    {
      "epoch": 0.28125,
      "eval_loss": 2.7952194213867188,
      "eval_runtime": 2.0781,
      "eval_samples_per_second": 77.957,
      "eval_steps_per_second": 10.106,
      "step": 54
    },
    {
      "epoch": 0.2864583333333333,
      "grad_norm": 0.5953256487846375,
      "learning_rate": 1e-05,
      "loss": 2.753,
      "step": 55
    },
    {
      "epoch": 0.2916666666666667,
      "grad_norm": 0.6080588102340698,
      "learning_rate": 9.651005032974994e-06,
      "loss": 2.7811,
      "step": 56
    },
    {
      "epoch": 0.296875,
      "grad_norm": 0.6133514642715454,
      "learning_rate": 9.302435262558748e-06,
      "loss": 2.8155,
      "step": 57
    },
    {
      "epoch": 0.3020833333333333,
      "grad_norm": 0.5619336366653442,
      "learning_rate": 8.954715367323468e-06,
      "loss": 2.8096,
      "step": 58
    },
    {
      "epoch": 0.3072916666666667,
      "grad_norm": 0.6014407277107239,
      "learning_rate": 8.60826899039935e-06,
      "loss": 2.8114,
      "step": 59
    },
    {
      "epoch": 0.3125,
      "grad_norm": 0.6610764861106873,
      "learning_rate": 8.263518223330698e-06,
      "loss": 2.7468,
      "step": 60
    },
    {
      "epoch": 0.3177083333333333,
      "grad_norm": 0.5688837766647339,
      "learning_rate": 7.92088309182241e-06,
      "loss": 2.8023,
      "step": 61
    },
    {
      "epoch": 0.3229166666666667,
      "grad_norm": 0.5620987415313721,
      "learning_rate": 7.580781044003324e-06,
      "loss": 2.7155,
      "step": 62
    },
    {
      "epoch": 0.328125,
      "grad_norm": 0.5661582946777344,
      "learning_rate": 7.243626441830009e-06,
      "loss": 2.8304,
      "step": 63
    },
    {
      "epoch": 0.328125,
      "eval_loss": 2.757814645767212,
      "eval_runtime": 2.085,
      "eval_samples_per_second": 77.698,
      "eval_steps_per_second": 10.072,
      "step": 63
    },
    {
      "epoch": 0.3333333333333333,
      "grad_norm": 0.5300706624984741,
      "learning_rate": 6.909830056250527e-06,
      "loss": 2.6727,
      "step": 64
    },
    {
      "epoch": 0.3385416666666667,
      "grad_norm": 0.6273490190505981,
      "learning_rate": 6.579798566743314e-06,
      "loss": 2.8153,
      "step": 65
    },
    {
      "epoch": 0.34375,
      "grad_norm": 0.5960977077484131,
      "learning_rate": 6.25393406584088e-06,
      "loss": 2.7715,
      "step": 66
    },
    {
      "epoch": 0.3489583333333333,
      "grad_norm": 0.5524370670318604,
      "learning_rate": 5.932633569242e-06,
      "loss": 2.809,
      "step": 67
    },
    {
      "epoch": 0.3541666666666667,
      "grad_norm": 0.5498830676078796,
      "learning_rate": 5.616288532109225e-06,
      "loss": 2.8073,
      "step": 68
    },
    {
      "epoch": 0.359375,
      "grad_norm": 0.5716202855110168,
      "learning_rate": 5.305284372141095e-06,
      "loss": 2.7527,
      "step": 69
    },
    {
      "epoch": 0.3645833333333333,
      "grad_norm": 0.6267365217208862,
      "learning_rate": 5.000000000000003e-06,
      "loss": 2.6112,
      "step": 70
    },
    {
      "epoch": 0.3697916666666667,
      "grad_norm": 0.5582669973373413,
      "learning_rate": 4.700807357667953e-06,
      "loss": 2.6915,
      "step": 71
    },
    {
      "epoch": 0.375,
      "grad_norm": 0.5531418323516846,
      "learning_rate": 4.408070965292534e-06,
      "loss": 2.6571,
      "step": 72
    },
    {
      "epoch": 0.375,
      "eval_loss": 2.7321271896362305,
      "eval_runtime": 2.0813,
      "eval_samples_per_second": 77.837,
      "eval_steps_per_second": 10.09,
      "step": 72
    },
    {
      "epoch": 0.3802083333333333,
      "grad_norm": 0.6036546230316162,
      "learning_rate": 4.12214747707527e-06,
      "loss": 2.7487,
      "step": 73
    },
    {
      "epoch": 0.3854166666666667,
      "grad_norm": 0.5189100503921509,
      "learning_rate": 3.8433852467434175e-06,
      "loss": 2.7094,
      "step": 74
    },
    {
      "epoch": 0.390625,
      "grad_norm": 0.5724009871482849,
      "learning_rate": 3.5721239031346067e-06,
      "loss": 2.6401,
      "step": 75
    },
    {
      "epoch": 0.3958333333333333,
      "grad_norm": 0.6095809936523438,
      "learning_rate": 3.308693936411421e-06,
      "loss": 2.7599,
      "step": 76
    },
    {
      "epoch": 0.4010416666666667,
      "grad_norm": 0.5742631554603577,
      "learning_rate": 3.0534162954100264e-06,
      "loss": 2.6972,
      "step": 77
    },
    {
      "epoch": 0.40625,
      "grad_norm": 0.5903258919715881,
      "learning_rate": 2.8066019966134907e-06,
      "loss": 2.6778,
      "step": 78
    },
    {
      "epoch": 0.4114583333333333,
      "grad_norm": 0.603958010673523,
      "learning_rate": 2.5685517452260566e-06,
      "loss": 2.665,
      "step": 79
    },
    {
      "epoch": 0.4166666666666667,
      "grad_norm": 0.613657534122467,
      "learning_rate": 2.339555568810221e-06,
      "loss": 2.7079,
      "step": 80
    },
    {
      "epoch": 0.421875,
      "grad_norm": 0.6130823493003845,
      "learning_rate": 2.119892463932781e-06,
      "loss": 2.7365,
      "step": 81
    },
    {
      "epoch": 0.421875,
      "eval_loss": 2.718648672103882,
      "eval_runtime": 2.1208,
      "eval_samples_per_second": 76.385,
      "eval_steps_per_second": 9.902,
      "step": 81
    },
    {
      "epoch": 0.4270833333333333,
      "grad_norm": 0.5892557501792908,
      "learning_rate": 1.9098300562505266e-06,
      "loss": 2.7435,
      "step": 82
    },
    {
      "epoch": 0.4322916666666667,
      "grad_norm": 0.6382349133491516,
      "learning_rate": 1.709624274449584e-06,
      "loss": 2.7304,
      "step": 83
    },
    {
      "epoch": 0.4375,
      "grad_norm": 0.6454895734786987,
      "learning_rate": 1.5195190384357405e-06,
      "loss": 2.7867,
      "step": 84
    },
    {
      "epoch": 0.4427083333333333,
      "grad_norm": 0.5571866035461426,
      "learning_rate": 1.339745962155613e-06,
      "loss": 2.6963,
      "step": 85
    },
    {
      "epoch": 0.4479166666666667,
      "grad_norm": 0.544607937335968,
      "learning_rate": 1.1705240714107301e-06,
      "loss": 2.6594,
      "step": 86
    },
    {
      "epoch": 0.453125,
      "grad_norm": 0.5853146314620972,
      "learning_rate": 1.012059537008332e-06,
      "loss": 2.6857,
      "step": 87
    },
    {
      "epoch": 0.4583333333333333,
      "grad_norm": 0.5569471716880798,
      "learning_rate": 8.645454235739903e-07,
      "loss": 2.6542,
      "step": 88
    },
    {
      "epoch": 0.4635416666666667,
      "grad_norm": 0.5549748539924622,
      "learning_rate": 7.281614543321269e-07,
      "loss": 2.7433,
      "step": 89
    },
    {
      "epoch": 0.46875,
      "grad_norm": 0.584230899810791,
      "learning_rate": 6.030737921409169e-07,
      "loss": 2.7141,
      "step": 90
    },
    {
      "epoch": 0.46875,
      "eval_loss": 2.7120678424835205,
      "eval_runtime": 2.1462,
      "eval_samples_per_second": 75.483,
      "eval_steps_per_second": 9.785,
      "step": 90
    },
    {
      "epoch": 0.4739583333333333,
      "grad_norm": 0.5945222973823547,
      "learning_rate": 4.894348370484648e-07,
      "loss": 2.7239,
      "step": 91
    },
    {
      "epoch": 0.4791666666666667,
      "grad_norm": 0.6125372052192688,
      "learning_rate": 3.8738304061681107e-07,
      "loss": 2.6631,
      "step": 92
    },
    {
      "epoch": 0.484375,
      "grad_norm": 0.5539056658744812,
      "learning_rate": 2.970427372400353e-07,
      "loss": 2.6647,
      "step": 93
    },
    {
      "epoch": 0.4895833333333333,
      "grad_norm": 0.5954320430755615,
      "learning_rate": 2.1852399266194312e-07,
      "loss": 2.7845,
      "step": 94
    },
    {
      "epoch": 0.4947916666666667,
      "grad_norm": 0.5771157145500183,
      "learning_rate": 1.519224698779198e-07,
      "loss": 2.7396,
      "step": 95
    },
    {
      "epoch": 0.5,
      "grad_norm": 0.5784287452697754,
      "learning_rate": 9.731931258429638e-08,
      "loss": 2.6544,
      "step": 96
    },
    {
      "epoch": 0.5052083333333334,
      "grad_norm": 0.5514799952507019,
      "learning_rate": 5.4781046317267103e-08,
      "loss": 2.7321,
      "step": 97
    },
    {
      "epoch": 0.5104166666666666,
      "grad_norm": 0.5833736658096313,
      "learning_rate": 2.4359497401758026e-08,
      "loss": 2.763,
      "step": 98
    },
    {
      "epoch": 0.515625,
      "grad_norm": 0.5531443357467651,
      "learning_rate": 6.091729809042379e-09,
      "loss": 2.7092,
      "step": 99
    },
    {
      "epoch": 0.515625,
      "eval_loss": 2.711505651473999,
      "eval_runtime": 2.1245,
      "eval_samples_per_second": 76.254,
      "eval_steps_per_second": 9.885,
      "step": 99
    },
    {
      "epoch": 0.5208333333333334,
      "grad_norm": 0.5679538249969482,
      "learning_rate": 0.0,
      "loss": 2.6643,
      "step": 100
    }
  ],
  "logging_steps": 1,
  "max_steps": 100,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 25,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 2027028756824064.0,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}