{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.05337247314697445,
  "eval_steps": 7,
  "global_step": 100,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0005337247314697444,
      "grad_norm": 0.3629896640777588,
      "learning_rate": 2e-05,
      "loss": 1.3023,
      "step": 1
    },
    {
      "epoch": 0.0005337247314697444,
      "eval_loss": 1.6696527004241943,
      "eval_runtime": 138.2798,
      "eval_samples_per_second": 11.412,
      "eval_steps_per_second": 5.706,
      "step": 1
    },
    {
      "epoch": 0.0010674494629394889,
      "grad_norm": 0.37523019313812256,
      "learning_rate": 4e-05,
      "loss": 1.3966,
      "step": 2
    },
    {
      "epoch": 0.0016011741944092334,
      "grad_norm": 0.39908841252326965,
      "learning_rate": 6e-05,
      "loss": 1.2988,
      "step": 3
    },
    {
      "epoch": 0.0021348989258789777,
      "grad_norm": 0.44918331503868103,
      "learning_rate": 8e-05,
      "loss": 1.8351,
      "step": 4
    },
    {
      "epoch": 0.0026686236573487225,
      "grad_norm": 0.4540751874446869,
      "learning_rate": 0.0001,
      "loss": 1.6159,
      "step": 5
    },
    {
      "epoch": 0.003202348388818467,
      "grad_norm": 0.48438403010368347,
      "learning_rate": 0.00012,
      "loss": 1.7997,
      "step": 6
    },
    {
      "epoch": 0.003736073120288211,
      "grad_norm": 0.47967973351478577,
      "learning_rate": 0.00014,
      "loss": 1.848,
      "step": 7
    },
    {
      "epoch": 0.003736073120288211,
      "eval_loss": 1.5880990028381348,
      "eval_runtime": 136.8431,
      "eval_samples_per_second": 11.531,
      "eval_steps_per_second": 5.766,
      "step": 7
    },
    {
      "epoch": 0.0042697978517579555,
      "grad_norm": 0.443247526884079,
      "learning_rate": 0.00016,
      "loss": 1.3893,
      "step": 8
    },
    {
      "epoch": 0.004803522583227701,
      "grad_norm": 0.4176405370235443,
      "learning_rate": 0.00018,
      "loss": 1.6137,
      "step": 9
    },
    {
      "epoch": 0.005337247314697445,
      "grad_norm": 0.42031896114349365,
      "learning_rate": 0.0002,
      "loss": 1.5092,
      "step": 10
    },
    {
      "epoch": 0.005870972046167189,
      "grad_norm": 0.3552657961845398,
      "learning_rate": 0.0001999390827019096,
      "loss": 1.4142,
      "step": 11
    },
    {
      "epoch": 0.006404696777636934,
      "grad_norm": 0.5527915358543396,
      "learning_rate": 0.00019975640502598244,
      "loss": 1.6114,
      "step": 12
    },
    {
      "epoch": 0.006938421509106678,
      "grad_norm": 0.4900396168231964,
      "learning_rate": 0.00019945218953682734,
      "loss": 1.3065,
      "step": 13
    },
    {
      "epoch": 0.007472146240576422,
      "grad_norm": 0.41337817907333374,
      "learning_rate": 0.00019902680687415705,
      "loss": 1.3956,
      "step": 14
    },
    {
      "epoch": 0.007472146240576422,
      "eval_loss": 1.3877164125442505,
      "eval_runtime": 132.633,
      "eval_samples_per_second": 11.897,
      "eval_steps_per_second": 5.949,
      "step": 14
    },
    {
      "epoch": 0.008005870972046168,
      "grad_norm": 0.44572773575782776,
      "learning_rate": 0.00019848077530122083,
      "loss": 1.5852,
      "step": 15
    },
    {
      "epoch": 0.008539595703515911,
      "grad_norm": 0.413870632648468,
      "learning_rate": 0.00019781476007338058,
      "loss": 1.2316,
      "step": 16
    },
    {
      "epoch": 0.009073320434985656,
      "grad_norm": 0.41110166907310486,
      "learning_rate": 0.00019702957262759965,
      "loss": 1.4972,
      "step": 17
    },
    {
      "epoch": 0.009607045166455401,
      "grad_norm": 0.3463555872440338,
      "learning_rate": 0.0001961261695938319,
      "loss": 1.1697,
      "step": 18
    },
    {
      "epoch": 0.010140769897925145,
      "grad_norm": 0.3517301678657532,
      "learning_rate": 0.00019510565162951537,
      "loss": 1.2792,
      "step": 19
    },
    {
      "epoch": 0.01067449462939489,
      "grad_norm": 0.3800961375236511,
      "learning_rate": 0.00019396926207859084,
      "loss": 1.3721,
      "step": 20
    },
    {
      "epoch": 0.011208219360864633,
      "grad_norm": 0.46215319633483887,
      "learning_rate": 0.00019271838545667876,
      "loss": 1.2391,
      "step": 21
    },
    {
      "epoch": 0.011208219360864633,
      "eval_loss": 1.3272384405136108,
      "eval_runtime": 142.2392,
      "eval_samples_per_second": 11.094,
      "eval_steps_per_second": 5.547,
      "step": 21
    },
    {
      "epoch": 0.011741944092334379,
      "grad_norm": 0.4401664733886719,
      "learning_rate": 0.0001913545457642601,
      "loss": 1.279,
      "step": 22
    },
    {
      "epoch": 0.012275668823804124,
      "grad_norm": 0.4027818441390991,
      "learning_rate": 0.0001898794046299167,
      "loss": 1.3049,
      "step": 23
    },
    {
      "epoch": 0.012809393555273867,
      "grad_norm": 0.4447319209575653,
      "learning_rate": 0.00018829475928589271,
      "loss": 1.5177,
      "step": 24
    },
    {
      "epoch": 0.013343118286743613,
      "grad_norm": 0.4240773618221283,
      "learning_rate": 0.00018660254037844388,
      "loss": 1.2123,
      "step": 25
    },
    {
      "epoch": 0.013876843018213356,
      "grad_norm": 0.39182350039482117,
      "learning_rate": 0.0001848048096156426,
      "loss": 1.2975,
      "step": 26
    },
    {
      "epoch": 0.014410567749683101,
      "grad_norm": 0.3561626374721527,
      "learning_rate": 0.00018290375725550417,
      "loss": 1.3176,
      "step": 27
    },
    {
      "epoch": 0.014944292481152845,
      "grad_norm": 0.41868481040000916,
      "learning_rate": 0.00018090169943749476,
      "loss": 1.497,
      "step": 28
    },
    {
      "epoch": 0.014944292481152845,
      "eval_loss": 1.2778455018997192,
      "eval_runtime": 133.835,
      "eval_samples_per_second": 11.791,
      "eval_steps_per_second": 5.895,
      "step": 28
    },
    {
      "epoch": 0.01547801721262259,
      "grad_norm": 0.39559242129325867,
      "learning_rate": 0.00017880107536067218,
      "loss": 1.5544,
      "step": 29
    },
    {
      "epoch": 0.016011741944092335,
      "grad_norm": 0.4642369747161865,
      "learning_rate": 0.0001766044443118978,
      "loss": 1.5329,
      "step": 30
    },
    {
      "epoch": 0.01654546667556208,
      "grad_norm": 0.4452536404132843,
      "learning_rate": 0.00017431448254773944,
      "loss": 1.4477,
      "step": 31
    },
    {
      "epoch": 0.017079191407031822,
      "grad_norm": 0.4180367588996887,
      "learning_rate": 0.0001719339800338651,
      "loss": 1.5047,
      "step": 32
    },
    {
      "epoch": 0.017612916138501567,
      "grad_norm": 0.34123241901397705,
      "learning_rate": 0.00016946583704589973,
      "loss": 1.2064,
      "step": 33
    },
    {
      "epoch": 0.018146640869971312,
      "grad_norm": 0.4111071228981018,
      "learning_rate": 0.00016691306063588583,
      "loss": 1.5182,
      "step": 34
    },
    {
      "epoch": 0.018680365601441058,
      "grad_norm": 0.3765980899333954,
      "learning_rate": 0.00016427876096865394,
      "loss": 1.4533,
      "step": 35
    },
    {
      "epoch": 0.018680365601441058,
      "eval_loss": 1.2552332878112793,
      "eval_runtime": 133.9537,
      "eval_samples_per_second": 11.78,
      "eval_steps_per_second": 5.89,
      "step": 35
    },
    {
      "epoch": 0.019214090332910803,
      "grad_norm": 0.35214561223983765,
      "learning_rate": 0.0001615661475325658,
      "loss": 1.3882,
      "step": 36
    },
    {
      "epoch": 0.019747815064380544,
      "grad_norm": 0.36351558566093445,
      "learning_rate": 0.00015877852522924732,
      "loss": 1.2277,
      "step": 37
    },
    {
      "epoch": 0.02028153979585029,
      "grad_norm": 0.4065183997154236,
      "learning_rate": 0.0001559192903470747,
      "loss": 0.9644,
      "step": 38
    },
    {
      "epoch": 0.020815264527320035,
      "grad_norm": 0.31548288464546204,
      "learning_rate": 0.0001529919264233205,
      "loss": 1.2103,
      "step": 39
    },
    {
      "epoch": 0.02134898925878978,
      "grad_norm": 0.34691786766052246,
      "learning_rate": 0.00015000000000000001,
      "loss": 1.2275,
      "step": 40
    },
    {
      "epoch": 0.021882713990259525,
      "grad_norm": 0.3332786560058594,
      "learning_rate": 0.00014694715627858908,
      "loss": 1.3469,
      "step": 41
    },
    {
      "epoch": 0.022416438721729267,
      "grad_norm": 0.3993981182575226,
      "learning_rate": 0.00014383711467890774,
      "loss": 1.2165,
      "step": 42
    },
    {
      "epoch": 0.022416438721729267,
      "eval_loss": 1.240829586982727,
      "eval_runtime": 139.0014,
      "eval_samples_per_second": 11.352,
      "eval_steps_per_second": 5.676,
      "step": 42
    },
    {
      "epoch": 0.022950163453199012,
      "grad_norm": 0.3627195358276367,
      "learning_rate": 0.00014067366430758004,
      "loss": 1.1394,
      "step": 43
    },
    {
      "epoch": 0.023483888184668757,
      "grad_norm": 0.31742554903030396,
      "learning_rate": 0.00013746065934159123,
      "loss": 1.1885,
      "step": 44
    },
    {
      "epoch": 0.024017612916138503,
      "grad_norm": 0.3838454782962799,
      "learning_rate": 0.00013420201433256689,
      "loss": 1.3044,
      "step": 45
    },
    {
      "epoch": 0.024551337647608248,
      "grad_norm": 0.3152655363082886,
      "learning_rate": 0.00013090169943749476,
      "loss": 1.2796,
      "step": 46
    },
    {
      "epoch": 0.02508506237907799,
      "grad_norm": 0.34708547592163086,
      "learning_rate": 0.0001275637355816999,
      "loss": 1.2463,
      "step": 47
    },
    {
      "epoch": 0.025618787110547735,
      "grad_norm": 0.36045414209365845,
      "learning_rate": 0.00012419218955996676,
      "loss": 1.4435,
      "step": 48
    },
    {
      "epoch": 0.02615251184201748,
      "grad_norm": 0.3756614625453949,
      "learning_rate": 0.00012079116908177593,
      "loss": 1.1767,
      "step": 49
    },
    {
      "epoch": 0.02615251184201748,
      "eval_loss": 1.2297325134277344,
      "eval_runtime": 143.2278,
      "eval_samples_per_second": 11.017,
      "eval_steps_per_second": 5.509,
      "step": 49
    },
    {
      "epoch": 0.026686236573487225,
      "grad_norm": 0.4282926023006439,
      "learning_rate": 0.00011736481776669306,
      "loss": 1.3075,
      "step": 50
    },
    {
      "epoch": 0.027219961304956967,
      "grad_norm": 0.3769337236881256,
      "learning_rate": 0.00011391731009600654,
      "loss": 1.2137,
      "step": 51
    },
    {
      "epoch": 0.027753686036426712,
      "grad_norm": 0.3585554361343384,
      "learning_rate": 0.00011045284632676536,
      "loss": 1.1048,
      "step": 52
    },
    {
      "epoch": 0.028287410767896457,
      "grad_norm": 0.3299272954463959,
      "learning_rate": 0.00010697564737441252,
      "loss": 1.2815,
      "step": 53
    },
    {
      "epoch": 0.028821135499366202,
      "grad_norm": 0.3429305851459503,
      "learning_rate": 0.00010348994967025012,
      "loss": 1.2823,
      "step": 54
    },
    {
      "epoch": 0.029354860230835948,
      "grad_norm": 0.39360129833221436,
      "learning_rate": 0.0001,
      "loss": 1.0352,
      "step": 55
    },
    {
      "epoch": 0.02988858496230569,
      "grad_norm": 0.34267058968544006,
      "learning_rate": 9.651005032974994e-05,
      "loss": 0.9731,
      "step": 56
    },
    {
      "epoch": 0.02988858496230569,
      "eval_loss": 1.2223201990127563,
      "eval_runtime": 143.2351,
      "eval_samples_per_second": 11.017,
      "eval_steps_per_second": 5.508,
      "step": 56
    },
    {
      "epoch": 0.030422309693775434,
      "grad_norm": 0.39054739475250244,
      "learning_rate": 9.302435262558747e-05,
      "loss": 1.1894,
      "step": 57
    },
    {
      "epoch": 0.03095603442524518,
      "grad_norm": 0.3081369400024414,
      "learning_rate": 8.954715367323468e-05,
      "loss": 0.9732,
      "step": 58
    },
    {
      "epoch": 0.031489759156714925,
      "grad_norm": 0.43032369017601013,
      "learning_rate": 8.608268990399349e-05,
      "loss": 0.9788,
      "step": 59
    },
    {
      "epoch": 0.03202348388818467,
      "grad_norm": 0.3782951831817627,
      "learning_rate": 8.263518223330697e-05,
      "loss": 1.1651,
      "step": 60
    },
    {
      "epoch": 0.032557208619654415,
      "grad_norm": 0.3738667964935303,
      "learning_rate": 7.920883091822408e-05,
      "loss": 0.8571,
      "step": 61
    },
    {
      "epoch": 0.03309093335112416,
      "grad_norm": 0.3225691616535187,
      "learning_rate": 7.580781044003324e-05,
      "loss": 0.9112,
      "step": 62
    },
    {
      "epoch": 0.033624658082593906,
      "grad_norm": 0.2828129827976227,
      "learning_rate": 7.243626441830009e-05,
      "loss": 0.8316,
      "step": 63
    },
    {
      "epoch": 0.033624658082593906,
      "eval_loss": 1.2188873291015625,
      "eval_runtime": 142.4739,
      "eval_samples_per_second": 11.076,
      "eval_steps_per_second": 5.538,
      "step": 63
    },
    {
      "epoch": 0.034158382814063644,
      "grad_norm": 0.4024946391582489,
      "learning_rate": 6.909830056250527e-05,
      "loss": 1.4719,
      "step": 64
    },
    {
      "epoch": 0.03469210754553339,
      "grad_norm": 0.43514999747276306,
      "learning_rate": 6.579798566743314e-05,
      "loss": 1.3543,
      "step": 65
    },
    {
      "epoch": 0.035225832277003134,
      "grad_norm": 0.3096754550933838,
      "learning_rate": 6.25393406584088e-05,
      "loss": 0.9926,
      "step": 66
    },
    {
      "epoch": 0.03575955700847288,
      "grad_norm": 0.3676164448261261,
      "learning_rate": 5.9326335692419995e-05,
      "loss": 1.5319,
      "step": 67
    },
    {
      "epoch": 0.036293281739942625,
      "grad_norm": 0.4387390911579132,
      "learning_rate": 5.616288532109225e-05,
      "loss": 1.5463,
      "step": 68
    },
    {
      "epoch": 0.03682700647141237,
      "grad_norm": 0.38703230023384094,
      "learning_rate": 5.305284372141095e-05,
      "loss": 1.6212,
      "step": 69
    },
    {
      "epoch": 0.037360731202882115,
      "grad_norm": 0.3590051829814911,
      "learning_rate": 5.000000000000002e-05,
      "loss": 1.3272,
      "step": 70
    },
    {
      "epoch": 0.037360731202882115,
      "eval_loss": 1.2139812707901,
      "eval_runtime": 148.838,
      "eval_samples_per_second": 10.602,
      "eval_steps_per_second": 5.301,
      "step": 70
    },
    {
      "epoch": 0.03789445593435186,
      "grad_norm": 0.3637433350086212,
      "learning_rate": 4.700807357667952e-05,
      "loss": 1.1114,
      "step": 71
    },
    {
      "epoch": 0.038428180665821605,
      "grad_norm": 0.3315064013004303,
      "learning_rate": 4.4080709652925336e-05,
      "loss": 1.3231,
      "step": 72
    },
    {
      "epoch": 0.038961905397291344,
      "grad_norm": 0.4271906912326813,
      "learning_rate": 4.12214747707527e-05,
      "loss": 1.6108,
      "step": 73
    },
    {
      "epoch": 0.03949563012876109,
      "grad_norm": 0.4011762738227844,
      "learning_rate": 3.843385246743417e-05,
      "loss": 1.3892,
      "step": 74
    },
    {
      "epoch": 0.040029354860230834,
      "grad_norm": 0.35736286640167236,
      "learning_rate": 3.5721239031346066e-05,
      "loss": 1.1504,
      "step": 75
    },
    {
      "epoch": 0.04056307959170058,
      "grad_norm": 0.29981729388237,
      "learning_rate": 3.308693936411421e-05,
      "loss": 0.9346,
      "step": 76
    },
    {
      "epoch": 0.041096804323170325,
      "grad_norm": 0.32428425550460815,
      "learning_rate": 3.053416295410026e-05,
      "loss": 1.1467,
      "step": 77
    },
    {
      "epoch": 0.041096804323170325,
      "eval_loss": 1.2112306356430054,
      "eval_runtime": 132.0592,
      "eval_samples_per_second": 11.949,
      "eval_steps_per_second": 5.975,
      "step": 77
    },
    {
      "epoch": 0.04163052905464007,
      "grad_norm": 0.31357115507125854,
      "learning_rate": 2.8066019966134904e-05,
      "loss": 1.1449,
      "step": 78
    },
    {
      "epoch": 0.042164253786109815,
      "grad_norm": 0.28956103324890137,
      "learning_rate": 2.5685517452260567e-05,
      "loss": 0.9929,
      "step": 79
    },
    {
      "epoch": 0.04269797851757956,
      "grad_norm": 0.3215799927711487,
      "learning_rate": 2.339555568810221e-05,
      "loss": 0.95,
      "step": 80
    },
    {
      "epoch": 0.043231703249049305,
      "grad_norm": 0.32306861877441406,
      "learning_rate": 2.119892463932781e-05,
      "loss": 1.3405,
      "step": 81
    },
    {
      "epoch": 0.04376542798051905,
      "grad_norm": 0.34628739953041077,
      "learning_rate": 1.9098300562505266e-05,
      "loss": 1.3823,
      "step": 82
    },
    {
      "epoch": 0.04429915271198879,
      "grad_norm": 0.41880619525909424,
      "learning_rate": 1.7096242744495837e-05,
      "loss": 1.2145,
      "step": 83
    },
    {
      "epoch": 0.044832877443458534,
      "grad_norm": 0.34489524364471436,
      "learning_rate": 1.5195190384357404e-05,
      "loss": 1.2043,
      "step": 84
    },
    {
      "epoch": 0.044832877443458534,
      "eval_loss": 1.209867000579834,
      "eval_runtime": 131.1054,
      "eval_samples_per_second": 12.036,
      "eval_steps_per_second": 6.018,
      "step": 84
    },
    {
      "epoch": 0.04536660217492828,
      "grad_norm": 0.3454246520996094,
      "learning_rate": 1.339745962155613e-05,
      "loss": 1.4326,
      "step": 85
    },
    {
      "epoch": 0.045900326906398024,
      "grad_norm": 0.34903326630592346,
      "learning_rate": 1.1705240714107302e-05,
      "loss": 1.2395,
      "step": 86
    },
    {
      "epoch": 0.04643405163786777,
      "grad_norm": 0.36401617527008057,
      "learning_rate": 1.0120595370083318e-05,
      "loss": 1.1309,
      "step": 87
    },
    {
      "epoch": 0.046967776369337515,
      "grad_norm": 0.3476174473762512,
      "learning_rate": 8.645454235739903e-06,
      "loss": 1.1396,
      "step": 88
    },
    {
      "epoch": 0.04750150110080726,
      "grad_norm": 0.3433617353439331,
      "learning_rate": 7.281614543321269e-06,
      "loss": 1.3106,
      "step": 89
    },
    {
      "epoch": 0.048035225832277005,
      "grad_norm": 0.3952890932559967,
      "learning_rate": 6.030737921409169e-06,
      "loss": 1.3647,
      "step": 90
    },
    {
      "epoch": 0.04856895056374675,
      "grad_norm": 0.3324783444404602,
      "learning_rate": 4.8943483704846475e-06,
      "loss": 1.3629,
      "step": 91
    },
    {
      "epoch": 0.04856895056374675,
      "eval_loss": 1.209067463874817,
      "eval_runtime": 131.1887,
      "eval_samples_per_second": 12.028,
      "eval_steps_per_second": 6.014,
      "step": 91
    },
    {
      "epoch": 0.049102675295216495,
      "grad_norm": 0.3305179476737976,
      "learning_rate": 3.873830406168111e-06,
      "loss": 0.9684,
      "step": 92
    },
    {
      "epoch": 0.049636400026686234,
      "grad_norm": 0.3130112290382385,
      "learning_rate": 2.970427372400353e-06,
      "loss": 1.4122,
      "step": 93
    },
    {
      "epoch": 0.05017012475815598,
      "grad_norm": 0.4082207977771759,
      "learning_rate": 2.1852399266194314e-06,
      "loss": 1.0472,
      "step": 94
    },
    {
      "epoch": 0.050703849489625724,
      "grad_norm": 0.37707728147506714,
      "learning_rate": 1.5192246987791981e-06,
      "loss": 1.3998,
      "step": 95
    },
    {
      "epoch": 0.05123757422109547,
      "grad_norm": 0.3092212677001953,
      "learning_rate": 9.731931258429638e-07,
      "loss": 1.3452,
      "step": 96
    },
    {
      "epoch": 0.051771298952565215,
      "grad_norm": 0.31625714898109436,
      "learning_rate": 5.478104631726711e-07,
      "loss": 1.3001,
      "step": 97
    },
    {
      "epoch": 0.05230502368403496,
      "grad_norm": 0.39429420232772827,
      "learning_rate": 2.4359497401758024e-07,
      "loss": 1.2862,
      "step": 98
    },
    {
      "epoch": 0.05230502368403496,
      "eval_loss": 1.2093968391418457,
      "eval_runtime": 131.0498,
      "eval_samples_per_second": 12.041,
      "eval_steps_per_second": 6.021,
      "step": 98
    },
    {
      "epoch": 0.052838748415504705,
      "grad_norm": 0.3808484375476837,
      "learning_rate": 6.09172980904238e-08,
      "loss": 1.3516,
      "step": 99
    },
    {
      "epoch": 0.05337247314697445,
      "grad_norm": 0.33221495151519775,
      "learning_rate": 0.0,
      "loss": 0.9949,
      "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": 8056777010577408.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}