{
  "best_metric": 0.9890570640563965,
  "best_model_checkpoint": "miner_id_24/checkpoint-200",
  "epoch": 0.3784295175023652,
  "eval_steps": 50,
  "global_step": 200,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.001892147587511826,
      "grad_norm": 1.7183340787887573,
      "learning_rate": 7e-06,
      "loss": 1.53,
      "step": 1
    },
    {
      "epoch": 0.001892147587511826,
      "eval_loss": 1.6379868984222412,
      "eval_runtime": 65.7709,
      "eval_samples_per_second": 13.532,
      "eval_steps_per_second": 3.391,
      "step": 1
    },
    {
      "epoch": 0.003784295175023652,
      "grad_norm": 2.3774640560150146,
      "learning_rate": 1.4e-05,
      "loss": 1.5484,
      "step": 2
    },
    {
      "epoch": 0.005676442762535478,
      "grad_norm": 2.0960612297058105,
      "learning_rate": 2.1e-05,
      "loss": 1.5744,
      "step": 3
    },
    {
      "epoch": 0.007568590350047304,
      "grad_norm": 1.7372477054595947,
      "learning_rate": 2.8e-05,
      "loss": 1.5914,
      "step": 4
    },
    {
      "epoch": 0.00946073793755913,
      "grad_norm": 1.374696969985962,
      "learning_rate": 3.5e-05,
      "loss": 1.5184,
      "step": 5
    },
    {
      "epoch": 0.011352885525070956,
      "grad_norm": 1.1096769571304321,
      "learning_rate": 4.2e-05,
      "loss": 1.4652,
      "step": 6
    },
    {
      "epoch": 0.013245033112582781,
      "grad_norm": 0.8825443983078003,
      "learning_rate": 4.899999999999999e-05,
      "loss": 1.4137,
      "step": 7
    },
    {
      "epoch": 0.015137180700094607,
      "grad_norm": 0.9961705803871155,
      "learning_rate": 5.6e-05,
      "loss": 1.3318,
      "step": 8
    },
    {
      "epoch": 0.017029328287606435,
      "grad_norm": 0.9280786514282227,
      "learning_rate": 6.3e-05,
      "loss": 1.335,
      "step": 9
    },
    {
      "epoch": 0.01892147587511826,
      "grad_norm": 0.9114319682121277,
      "learning_rate": 7e-05,
      "loss": 1.2643,
      "step": 10
    },
    {
      "epoch": 0.020813623462630087,
      "grad_norm": 0.8190340995788574,
      "learning_rate": 6.999521567473641e-05,
      "loss": 1.2255,
      "step": 11
    },
    {
      "epoch": 0.02270577105014191,
      "grad_norm": 0.8544096350669861,
      "learning_rate": 6.998086400693241e-05,
      "loss": 1.2271,
      "step": 12
    },
    {
      "epoch": 0.02459791863765374,
      "grad_norm": 0.8797690868377686,
      "learning_rate": 6.995694892019065e-05,
      "loss": 1.254,
      "step": 13
    },
    {
      "epoch": 0.026490066225165563,
      "grad_norm": 0.8253311514854431,
      "learning_rate": 6.99234769526571e-05,
      "loss": 1.241,
      "step": 14
    },
    {
      "epoch": 0.02838221381267739,
      "grad_norm": 0.7804929614067078,
      "learning_rate": 6.988045725523343e-05,
      "loss": 1.2559,
      "step": 15
    },
    {
      "epoch": 0.030274361400189215,
      "grad_norm": 0.7397488951683044,
      "learning_rate": 6.982790158907539e-05,
      "loss": 1.2618,
      "step": 16
    },
    {
      "epoch": 0.03216650898770104,
      "grad_norm": 0.7259308695793152,
      "learning_rate": 6.976582432237733e-05,
      "loss": 1.1883,
      "step": 17
    },
    {
      "epoch": 0.03405865657521287,
      "grad_norm": 0.7094874978065491,
      "learning_rate": 6.969424242644413e-05,
      "loss": 1.1966,
      "step": 18
    },
    {
      "epoch": 0.03595080416272469,
      "grad_norm": 0.6165516972541809,
      "learning_rate": 6.961317547105138e-05,
      "loss": 1.1519,
      "step": 19
    },
    {
      "epoch": 0.03784295175023652,
      "grad_norm": 0.6611038446426392,
      "learning_rate": 6.952264561909527e-05,
      "loss": 1.1464,
      "step": 20
    },
    {
      "epoch": 0.039735099337748346,
      "grad_norm": 0.6444376111030579,
      "learning_rate": 6.942267762053337e-05,
      "loss": 1.1444,
      "step": 21
    },
    {
      "epoch": 0.041627246925260174,
      "grad_norm": 0.6641740202903748,
      "learning_rate": 6.931329880561832e-05,
      "loss": 1.1829,
      "step": 22
    },
    {
      "epoch": 0.043519394512771994,
      "grad_norm": 0.649354100227356,
      "learning_rate": 6.919453907742597e-05,
      "loss": 1.1602,
      "step": 23
    },
    {
      "epoch": 0.04541154210028382,
      "grad_norm": 0.632627546787262,
      "learning_rate": 6.90664309036802e-05,
      "loss": 1.1318,
      "step": 24
    },
    {
      "epoch": 0.04730368968779565,
      "grad_norm": 0.6628597378730774,
      "learning_rate": 6.892900930787656e-05,
      "loss": 1.1549,
      "step": 25
    },
    {
      "epoch": 0.04919583727530748,
      "grad_norm": 0.6973292827606201,
      "learning_rate": 6.87823118597072e-05,
      "loss": 1.1234,
      "step": 26
    },
    {
      "epoch": 0.0510879848628193,
      "grad_norm": 0.6472594141960144,
      "learning_rate": 6.862637866478969e-05,
      "loss": 1.133,
      "step": 27
    },
    {
      "epoch": 0.052980132450331126,
      "grad_norm": 0.6975822448730469,
      "learning_rate": 6.846125235370252e-05,
      "loss": 1.1477,
      "step": 28
    },
    {
      "epoch": 0.05487228003784295,
      "grad_norm": 0.6724961400032043,
      "learning_rate": 6.828697807033038e-05,
      "loss": 1.1292,
      "step": 29
    },
    {
      "epoch": 0.05676442762535478,
      "grad_norm": 0.6681162118911743,
      "learning_rate": 6.81036034595222e-05,
      "loss": 1.0868,
      "step": 30
    },
    {
      "epoch": 0.0586565752128666,
      "grad_norm": 0.6874375343322754,
      "learning_rate": 6.791117865406564e-05,
      "loss": 1.1337,
      "step": 31
    },
    {
      "epoch": 0.06054872280037843,
      "grad_norm": 0.6532557606697083,
      "learning_rate": 6.770975626098112e-05,
      "loss": 1.1283,
      "step": 32
    },
    {
      "epoch": 0.06244087038789026,
      "grad_norm": 0.6504979729652405,
      "learning_rate": 6.749939134713974e-05,
      "loss": 1.1327,
      "step": 33
    },
    {
      "epoch": 0.06433301797540208,
      "grad_norm": 0.6140085458755493,
      "learning_rate": 6.728014142420846e-05,
      "loss": 1.0243,
      "step": 34
    },
    {
      "epoch": 0.06622516556291391,
      "grad_norm": 0.6468620896339417,
      "learning_rate": 6.7052066432927e-05,
      "loss": 1.0735,
      "step": 35
    },
    {
      "epoch": 0.06811731315042574,
      "grad_norm": 0.6787900328636169,
      "learning_rate": 6.681522872672069e-05,
      "loss": 1.0682,
      "step": 36
    },
    {
      "epoch": 0.07000946073793755,
      "grad_norm": 0.6539909243583679,
      "learning_rate": 6.656969305465356e-05,
      "loss": 1.0441,
      "step": 37
    },
    {
      "epoch": 0.07190160832544938,
      "grad_norm": 0.6474837064743042,
      "learning_rate": 6.631552654372672e-05,
      "loss": 1.0899,
      "step": 38
    },
    {
      "epoch": 0.07379375591296121,
      "grad_norm": 0.663303792476654,
      "learning_rate": 6.60527986805264e-05,
      "loss": 1.0812,
      "step": 39
    },
    {
      "epoch": 0.07568590350047304,
      "grad_norm": 0.6546894311904907,
      "learning_rate": 6.578158129222711e-05,
      "loss": 1.0616,
      "step": 40
    },
    {
      "epoch": 0.07757805108798486,
      "grad_norm": 0.6684050559997559,
      "learning_rate": 6.550194852695469e-05,
      "loss": 1.0906,
      "step": 41
    },
    {
      "epoch": 0.07947019867549669,
      "grad_norm": 0.6097457408905029,
      "learning_rate": 6.521397683351509e-05,
      "loss": 1.0821,
      "step": 42
    },
    {
      "epoch": 0.08136234626300852,
      "grad_norm": 0.674848198890686,
      "learning_rate": 6.491774494049386e-05,
      "loss": 1.0742,
      "step": 43
    },
    {
      "epoch": 0.08325449385052035,
      "grad_norm": 0.7025091648101807,
      "learning_rate": 6.461333383473272e-05,
      "loss": 1.1055,
      "step": 44
    },
    {
      "epoch": 0.08514664143803216,
      "grad_norm": 0.6967143416404724,
      "learning_rate": 6.430082673918849e-05,
      "loss": 1.098,
      "step": 45
    },
    {
      "epoch": 0.08703878902554399,
      "grad_norm": 0.689311146736145,
      "learning_rate": 6.398030909018069e-05,
      "loss": 1.073,
      "step": 46
    },
    {
      "epoch": 0.08893093661305582,
      "grad_norm": 0.698433518409729,
      "learning_rate": 6.365186851403423e-05,
      "loss": 1.057,
      "step": 47
    },
    {
      "epoch": 0.09082308420056764,
      "grad_norm": 0.7176862955093384,
      "learning_rate": 6.331559480312315e-05,
      "loss": 1.0624,
      "step": 48
    },
    {
      "epoch": 0.09271523178807947,
      "grad_norm": 0.6786813735961914,
      "learning_rate": 6.297157989132236e-05,
      "loss": 1.083,
      "step": 49
    },
    {
      "epoch": 0.0946073793755913,
      "grad_norm": 0.7144589424133301,
      "learning_rate": 6.261991782887377e-05,
      "loss": 1.0397,
      "step": 50
    },
    {
      "epoch": 0.0946073793755913,
      "eval_loss": 1.0758204460144043,
      "eval_runtime": 66.7971,
      "eval_samples_per_second": 13.324,
      "eval_steps_per_second": 3.338,
      "step": 50
    },
    {
      "epoch": 0.09649952696310313,
      "grad_norm": 0.9547327756881714,
      "learning_rate": 6.226070475667393e-05,
      "loss": 1.1167,
      "step": 51
    },
    {
      "epoch": 0.09839167455061495,
      "grad_norm": 0.6827020049095154,
      "learning_rate": 6.189403887999006e-05,
      "loss": 1.1166,
      "step": 52
    },
    {
      "epoch": 0.10028382213812677,
      "grad_norm": 0.7102746963500977,
      "learning_rate": 6.152002044161171e-05,
      "loss": 1.1028,
      "step": 53
    },
    {
      "epoch": 0.1021759697256386,
      "grad_norm": 0.660106360912323,
      "learning_rate": 6.113875169444539e-05,
      "loss": 1.0771,
      "step": 54
    },
    {
      "epoch": 0.10406811731315042,
      "grad_norm": 0.70867520570755,
      "learning_rate": 6.0750336873559605e-05,
      "loss": 1.0949,
      "step": 55
    },
    {
      "epoch": 0.10596026490066225,
      "grad_norm": 0.6938849687576294,
      "learning_rate": 6.035488216768811e-05,
      "loss": 1.0239,
      "step": 56
    },
    {
      "epoch": 0.10785241248817408,
      "grad_norm": 0.6359347701072693,
      "learning_rate": 5.9952495690198894e-05,
      "loss": 1.0392,
      "step": 57
    },
    {
      "epoch": 0.1097445600756859,
      "grad_norm": 0.5934792160987854,
      "learning_rate": 5.954328744953709e-05,
      "loss": 1.0695,
      "step": 58
    },
    {
      "epoch": 0.11163670766319773,
      "grad_norm": 0.5965879559516907,
      "learning_rate": 5.91273693191498e-05,
      "loss": 1.0317,
      "step": 59
    },
    {
      "epoch": 0.11352885525070956,
      "grad_norm": 0.6218136548995972,
      "learning_rate": 5.870485500690094e-05,
      "loss": 1.0395,
      "step": 60
    },
    {
      "epoch": 0.11542100283822138,
      "grad_norm": 0.630561113357544,
      "learning_rate": 5.827586002398468e-05,
      "loss": 1.0414,
      "step": 61
    },
    {
      "epoch": 0.1173131504257332,
      "grad_norm": 0.6242802739143372,
      "learning_rate": 5.784050165334589e-05,
      "loss": 1.0914,
      "step": 62
    },
    {
      "epoch": 0.11920529801324503,
      "grad_norm": 0.5879487991333008,
      "learning_rate": 5.739889891761608e-05,
      "loss": 1.0141,
      "step": 63
    },
    {
      "epoch": 0.12109744560075686,
      "grad_norm": 0.5882847905158997,
      "learning_rate": 5.6951172546573794e-05,
      "loss": 1.0511,
      "step": 64
    },
    {
      "epoch": 0.12298959318826869,
      "grad_norm": 0.5669646263122559,
      "learning_rate": 5.6497444944138376e-05,
      "loss": 1.0395,
      "step": 65
    },
    {
      "epoch": 0.12488174077578051,
      "grad_norm": 0.631564736366272,
      "learning_rate": 5.603784015490587e-05,
      "loss": 1.0377,
      "step": 66
    },
    {
      "epoch": 0.12677388836329234,
      "grad_norm": 0.5925982594490051,
      "learning_rate": 5.557248383023655e-05,
      "loss": 1.0853,
      "step": 67
    },
    {
      "epoch": 0.12866603595080417,
      "grad_norm": 0.590632438659668,
      "learning_rate": 5.510150319390302e-05,
      "loss": 1.0706,
      "step": 68
    },
    {
      "epoch": 0.130558183538316,
      "grad_norm": 0.5787473917007446,
      "learning_rate": 5.4625027007308546e-05,
      "loss": 1.0662,
      "step": 69
    },
    {
      "epoch": 0.13245033112582782,
      "grad_norm": 0.5866360068321228,
      "learning_rate": 5.414318553428494e-05,
      "loss": 1.05,
      "step": 70
    },
    {
      "epoch": 0.13434247871333965,
      "grad_norm": 0.5667306184768677,
      "learning_rate": 5.3656110505479776e-05,
      "loss": 1.0318,
      "step": 71
    },
    {
      "epoch": 0.13623462630085148,
      "grad_norm": 0.6099268198013306,
      "learning_rate": 5.316393508234253e-05,
      "loss": 1.0206,
      "step": 72
    },
    {
      "epoch": 0.13812677388836328,
      "grad_norm": 0.6034222841262817,
      "learning_rate": 5.266679382071953e-05,
      "loss": 1.0269,
      "step": 73
    },
    {
      "epoch": 0.1400189214758751,
      "grad_norm": 0.6092371344566345,
      "learning_rate": 5.216482263406778e-05,
      "loss": 1.0406,
      "step": 74
    },
    {
      "epoch": 0.14191106906338694,
      "grad_norm": 0.5967000126838684,
      "learning_rate": 5.1658158756297576e-05,
      "loss": 1.0413,
      "step": 75
    },
    {
      "epoch": 0.14380321665089876,
      "grad_norm": 0.5979546904563904,
      "learning_rate": 5.114694070425407e-05,
      "loss": 1.0492,
      "step": 76
    },
    {
      "epoch": 0.1456953642384106,
      "grad_norm": 0.617870569229126,
      "learning_rate": 5.063130823984823e-05,
      "loss": 1.0603,
      "step": 77
    },
    {
      "epoch": 0.14758751182592242,
      "grad_norm": 0.6513817310333252,
      "learning_rate": 5.011140233184724e-05,
      "loss": 1.0702,
      "step": 78
    },
    {
      "epoch": 0.14947965941343425,
      "grad_norm": 0.5981159806251526,
      "learning_rate": 4.958736511733516e-05,
      "loss": 1.0464,
      "step": 79
    },
    {
      "epoch": 0.15137180700094607,
      "grad_norm": 0.5964122414588928,
      "learning_rate": 4.905933986285393e-05,
      "loss": 1.0161,
      "step": 80
    },
    {
      "epoch": 0.1532639545884579,
      "grad_norm": 0.6203078627586365,
      "learning_rate": 4.8527470925235824e-05,
      "loss": 1.0508,
      "step": 81
    },
    {
      "epoch": 0.15515610217596973,
      "grad_norm": 0.5957093238830566,
      "learning_rate": 4.799190371213772e-05,
      "loss": 1.0237,
      "step": 82
    },
    {
      "epoch": 0.15704824976348156,
      "grad_norm": 0.6095653176307678,
      "learning_rate": 4.745278464228808e-05,
      "loss": 1.0381,
      "step": 83
    },
    {
      "epoch": 0.15894039735099338,
      "grad_norm": 0.6099610328674316,
      "learning_rate": 4.69102611054575e-05,
      "loss": 1.0025,
      "step": 84
    },
    {
      "epoch": 0.1608325449385052,
      "grad_norm": 0.6160475611686707,
      "learning_rate": 4.6364481422163926e-05,
      "loss": 1.0305,
      "step": 85
    },
    {
      "epoch": 0.16272469252601704,
      "grad_norm": 0.6210997700691223,
      "learning_rate": 4.581559480312316e-05,
      "loss": 1.0211,
      "step": 86
    },
    {
      "epoch": 0.16461684011352887,
      "grad_norm": 0.6311046481132507,
      "learning_rate": 4.526375130845627e-05,
      "loss": 1.0296,
      "step": 87
    },
    {
      "epoch": 0.1665089877010407,
      "grad_norm": 0.6322853565216064,
      "learning_rate": 4.4709101806664554e-05,
      "loss": 1.0387,
      "step": 88
    },
    {
      "epoch": 0.1684011352885525,
      "grad_norm": 0.6399142146110535,
      "learning_rate": 4.4151797933383685e-05,
      "loss": 1.0542,
      "step": 89
    },
    {
      "epoch": 0.17029328287606432,
      "grad_norm": 0.6472105383872986,
      "learning_rate": 4.359199204992797e-05,
      "loss": 1.0096,
      "step": 90
    },
    {
      "epoch": 0.17218543046357615,
      "grad_norm": 0.6191582083702087,
      "learning_rate": 4.30298372016363e-05,
      "loss": 1.0696,
      "step": 91
    },
    {
      "epoch": 0.17407757805108798,
      "grad_norm": 0.6059530973434448,
      "learning_rate": 4.246548707603114e-05,
      "loss": 0.9819,
      "step": 92
    },
    {
      "epoch": 0.1759697256385998,
      "grad_norm": 0.6591618657112122,
      "learning_rate": 4.1899095960801805e-05,
      "loss": 1.0488,
      "step": 93
    },
    {
      "epoch": 0.17786187322611163,
      "grad_norm": 0.6547838449478149,
      "learning_rate": 4.133081870162385e-05,
      "loss": 1.0116,
      "step": 94
    },
    {
      "epoch": 0.17975402081362346,
      "grad_norm": 0.6359401941299438,
      "learning_rate": 4.076081065982569e-05,
      "loss": 1.0204,
      "step": 95
    },
    {
      "epoch": 0.1816461684011353,
      "grad_norm": 0.646925687789917,
      "learning_rate": 4.018922766991447e-05,
      "loss": 1.0486,
      "step": 96
    },
    {
      "epoch": 0.18353831598864712,
      "grad_norm": 0.6780849695205688,
      "learning_rate": 3.961622599697241e-05,
      "loss": 1.0551,
      "step": 97
    },
    {
      "epoch": 0.18543046357615894,
      "grad_norm": 0.6998917460441589,
      "learning_rate": 3.9041962293935516e-05,
      "loss": 1.0471,
      "step": 98
    },
    {
      "epoch": 0.18732261116367077,
      "grad_norm": 0.7020998001098633,
      "learning_rate": 3.84665935587662e-05,
      "loss": 0.9769,
      "step": 99
    },
    {
      "epoch": 0.1892147587511826,
      "grad_norm": 0.6970370411872864,
      "learning_rate": 3.7890277091531636e-05,
      "loss": 0.9868,
      "step": 100
    },
    {
      "epoch": 0.1892147587511826,
      "eval_loss": 1.0246082544326782,
      "eval_runtime": 66.7905,
      "eval_samples_per_second": 13.325,
      "eval_steps_per_second": 3.339,
      "step": 100
    },
    {
      "epoch": 0.19110690633869443,
      "grad_norm": 0.8647973537445068,
      "learning_rate": 3.7313170451399475e-05,
      "loss": 1.0912,
      "step": 101
    },
    {
      "epoch": 0.19299905392620625,
      "grad_norm": 0.7811133861541748,
      "learning_rate": 3.673543141356278e-05,
      "loss": 1.0621,
      "step": 102
    },
    {
      "epoch": 0.19489120151371808,
      "grad_norm": 0.6623404622077942,
      "learning_rate": 3.6157217926105783e-05,
      "loss": 1.0165,
      "step": 103
    },
    {
      "epoch": 0.1967833491012299,
      "grad_norm": 0.581591010093689,
      "learning_rate": 3.557868806682255e-05,
      "loss": 1.045,
      "step": 104
    },
    {
      "epoch": 0.1986754966887417,
      "grad_norm": 0.5817117094993591,
      "learning_rate": 3.5e-05,
      "loss": 1.001,
      "step": 105
    },
    {
      "epoch": 0.20056764427625354,
      "grad_norm": 0.6245970726013184,
      "learning_rate": 3.442131193317745e-05,
      "loss": 1.0591,
      "step": 106
    },
    {
      "epoch": 0.20245979186376536,
      "grad_norm": 0.636500358581543,
      "learning_rate": 3.384278207389421e-05,
      "loss": 1.0144,
      "step": 107
    },
    {
      "epoch": 0.2043519394512772,
      "grad_norm": 0.6458229422569275,
      "learning_rate": 3.3264568586437216e-05,
      "loss": 1.0251,
      "step": 108
    },
    {
      "epoch": 0.20624408703878902,
      "grad_norm": 0.6455327868461609,
      "learning_rate": 3.268682954860052e-05,
      "loss": 1.0541,
      "step": 109
    },
    {
      "epoch": 0.20813623462630085,
      "grad_norm": 0.6135246753692627,
      "learning_rate": 3.210972290846837e-05,
      "loss": 1.0339,
      "step": 110
    },
    {
      "epoch": 0.21002838221381268,
      "grad_norm": 0.5690136551856995,
      "learning_rate": 3.15334064412338e-05,
      "loss": 1.0123,
      "step": 111
    },
    {
      "epoch": 0.2119205298013245,
      "grad_norm": 0.5633889436721802,
      "learning_rate": 3.0958037706064485e-05,
      "loss": 0.9791,
      "step": 112
    },
    {
      "epoch": 0.21381267738883633,
      "grad_norm": 0.5846208930015564,
      "learning_rate": 3.038377400302758e-05,
      "loss": 1.0211,
      "step": 113
    },
    {
      "epoch": 0.21570482497634816,
      "grad_norm": 0.6093853116035461,
      "learning_rate": 2.9810772330085524e-05,
      "loss": 1.0399,
      "step": 114
    },
    {
      "epoch": 0.21759697256385999,
      "grad_norm": 0.5736932754516602,
      "learning_rate": 2.9239189340174306e-05,
      "loss": 0.9788,
      "step": 115
    },
    {
      "epoch": 0.2194891201513718,
      "grad_norm": 0.606311559677124,
      "learning_rate": 2.8669181298376163e-05,
      "loss": 1.016,
      "step": 116
    },
    {
      "epoch": 0.22138126773888364,
      "grad_norm": 0.5913999080657959,
      "learning_rate": 2.8100904039198193e-05,
      "loss": 0.998,
      "step": 117
    },
    {
      "epoch": 0.22327341532639547,
      "grad_norm": 0.6164299249649048,
      "learning_rate": 2.7534512923968863e-05,
      "loss": 1.0475,
      "step": 118
    },
    {
      "epoch": 0.2251655629139073,
      "grad_norm": 0.599840521812439,
      "learning_rate": 2.6970162798363695e-05,
      "loss": 1.0138,
      "step": 119
    },
    {
      "epoch": 0.22705771050141912,
      "grad_norm": 0.622111439704895,
      "learning_rate": 2.640800795007203e-05,
      "loss": 1.0192,
      "step": 120
    },
    {
      "epoch": 0.22894985808893092,
      "grad_norm": 0.6139826774597168,
      "learning_rate": 2.5848202066616305e-05,
      "loss": 1.0056,
      "step": 121
    },
    {
      "epoch": 0.23084200567644275,
      "grad_norm": 0.6069412231445312,
      "learning_rate": 2.5290898193335446e-05,
      "loss": 0.9934,
      "step": 122
    },
    {
      "epoch": 0.23273415326395458,
      "grad_norm": 0.7315534949302673,
      "learning_rate": 2.4736248691543736e-05,
      "loss": 1.0084,
      "step": 123
    },
    {
      "epoch": 0.2346263008514664,
      "grad_norm": 0.6033068299293518,
      "learning_rate": 2.4184405196876842e-05,
      "loss": 0.9859,
      "step": 124
    },
    {
      "epoch": 0.23651844843897823,
      "grad_norm": 0.5995269417762756,
      "learning_rate": 2.363551857783608e-05,
      "loss": 0.9896,
      "step": 125
    },
    {
      "epoch": 0.23841059602649006,
      "grad_norm": 0.6208170056343079,
      "learning_rate": 2.308973889454249e-05,
      "loss": 1.0614,
      "step": 126
    },
    {
      "epoch": 0.2403027436140019,
      "grad_norm": 0.6329922676086426,
      "learning_rate": 2.2547215357711918e-05,
      "loss": 0.9696,
      "step": 127
    },
    {
      "epoch": 0.24219489120151372,
      "grad_norm": 0.6048612594604492,
      "learning_rate": 2.2008096287862266e-05,
      "loss": 0.988,
      "step": 128
    },
    {
      "epoch": 0.24408703878902555,
      "grad_norm": 0.6055971384048462,
      "learning_rate": 2.1472529074764177e-05,
      "loss": 0.9974,
      "step": 129
    },
    {
      "epoch": 0.24597918637653737,
      "grad_norm": 0.6034923791885376,
      "learning_rate": 2.0940660137146074e-05,
      "loss": 1.0242,
      "step": 130
    },
    {
      "epoch": 0.2478713339640492,
      "grad_norm": 0.6091806292533875,
      "learning_rate": 2.041263488266484e-05,
      "loss": 1.0557,
      "step": 131
    },
    {
      "epoch": 0.24976348155156103,
      "grad_norm": 0.610476553440094,
      "learning_rate": 1.988859766815275e-05,
      "loss": 1.011,
      "step": 132
    },
    {
      "epoch": 0.25165562913907286,
      "grad_norm": 0.6271877884864807,
      "learning_rate": 1.9368691760151773e-05,
      "loss": 1.001,
      "step": 133
    },
    {
      "epoch": 0.2535477767265847,
      "grad_norm": 0.6196108460426331,
      "learning_rate": 1.885305929574593e-05,
      "loss": 1.02,
      "step": 134
    },
    {
      "epoch": 0.2554399243140965,
      "grad_norm": 0.617040753364563,
      "learning_rate": 1.8341841243702424e-05,
      "loss": 1.0172,
      "step": 135
    },
    {
      "epoch": 0.25733207190160834,
      "grad_norm": 0.6176308393478394,
      "learning_rate": 1.7835177365932225e-05,
      "loss": 1.0317,
      "step": 136
    },
    {
      "epoch": 0.25922421948912017,
      "grad_norm": 0.6212584376335144,
      "learning_rate": 1.7333206179280478e-05,
      "loss": 1.0457,
      "step": 137
    },
    {
      "epoch": 0.261116367076632,
      "grad_norm": 0.625037670135498,
      "learning_rate": 1.6836064917657478e-05,
      "loss": 1.0236,
      "step": 138
    },
    {
      "epoch": 0.2630085146641438,
      "grad_norm": 0.6162792444229126,
      "learning_rate": 1.6343889494520224e-05,
      "loss": 0.9993,
      "step": 139
    },
    {
      "epoch": 0.26490066225165565,
      "grad_norm": 0.6135765910148621,
      "learning_rate": 1.5856814465715064e-05,
      "loss": 0.9788,
      "step": 140
    },
    {
      "epoch": 0.2667928098391675,
      "grad_norm": 0.6448305249214172,
      "learning_rate": 1.5374972992691458e-05,
      "loss": 0.9969,
      "step": 141
    },
    {
      "epoch": 0.2686849574266793,
      "grad_norm": 0.6576701402664185,
      "learning_rate": 1.4898496806096974e-05,
      "loss": 0.9495,
      "step": 142
    },
    {
      "epoch": 0.27057710501419113,
      "grad_norm": 0.6453391909599304,
      "learning_rate": 1.4427516169763444e-05,
      "loss": 0.9968,
      "step": 143
    },
    {
      "epoch": 0.27246925260170296,
      "grad_norm": 0.6164287328720093,
      "learning_rate": 1.396215984509412e-05,
      "loss": 0.9762,
      "step": 144
    },
    {
      "epoch": 0.27436140018921473,
      "grad_norm": 0.6524091958999634,
      "learning_rate": 1.3502555055861625e-05,
      "loss": 1.0093,
      "step": 145
    },
    {
      "epoch": 0.27625354777672656,
      "grad_norm": 0.659598171710968,
      "learning_rate": 1.3048827453426203e-05,
      "loss": 0.9434,
      "step": 146
    },
    {
      "epoch": 0.2781456953642384,
      "grad_norm": 0.6762367486953735,
      "learning_rate": 1.2601101082383917e-05,
      "loss": 1.068,
      "step": 147
    },
    {
      "epoch": 0.2800378429517502,
      "grad_norm": 0.6729089021682739,
      "learning_rate": 1.2159498346654094e-05,
      "loss": 1.0132,
      "step": 148
    },
    {
      "epoch": 0.28192999053926204,
      "grad_norm": 0.6752368211746216,
      "learning_rate": 1.1724139976015306e-05,
      "loss": 0.9843,
      "step": 149
    },
    {
      "epoch": 0.28382213812677387,
      "grad_norm": 0.6980991363525391,
      "learning_rate": 1.1295144993099068e-05,
      "loss": 0.9744,
      "step": 150
    },
    {
      "epoch": 0.28382213812677387,
      "eval_loss": 0.9972198009490967,
      "eval_runtime": 66.7731,
      "eval_samples_per_second": 13.329,
      "eval_steps_per_second": 3.34,
      "step": 150
    },
    {
      "epoch": 0.2857142857142857,
      "grad_norm": 0.6985642910003662,
      "learning_rate": 1.0872630680850196e-05,
      "loss": 1.0573,
      "step": 151
    },
    {
      "epoch": 0.2876064333017975,
      "grad_norm": 0.7041015028953552,
      "learning_rate": 1.0456712550462898e-05,
      "loss": 1.0789,
      "step": 152
    },
    {
      "epoch": 0.28949858088930935,
      "grad_norm": 0.6472409963607788,
      "learning_rate": 1.0047504309801104e-05,
      "loss": 0.9891,
      "step": 153
    },
    {
      "epoch": 0.2913907284768212,
      "grad_norm": 0.6147633790969849,
      "learning_rate": 9.645117832311886e-06,
      "loss": 1.0303,
      "step": 154
    },
    {
      "epoch": 0.293282876064333,
      "grad_norm": 0.6217051148414612,
      "learning_rate": 9.249663126440394e-06,
      "loss": 0.9709,
      "step": 155
    },
    {
      "epoch": 0.29517502365184484,
      "grad_norm": 0.6143440008163452,
      "learning_rate": 8.861248305554624e-06,
      "loss": 1.0401,
      "step": 156
    },
    {
      "epoch": 0.29706717123935666,
      "grad_norm": 0.6004726886749268,
      "learning_rate": 8.47997955838829e-06,
      "loss": 1.0357,
      "step": 157
    },
    {
      "epoch": 0.2989593188268685,
      "grad_norm": 0.5790233612060547,
      "learning_rate": 8.10596112000994e-06,
      "loss": 1.0231,
      "step": 158
    },
    {
      "epoch": 0.3008514664143803,
      "grad_norm": 0.5863821506500244,
      "learning_rate": 7.739295243326067e-06,
      "loss": 0.9916,
      "step": 159
    },
    {
      "epoch": 0.30274361400189215,
      "grad_norm": 0.5931087732315063,
      "learning_rate": 7.380082171126228e-06,
      "loss": 0.9918,
      "step": 160
    },
    {
      "epoch": 0.304635761589404,
      "grad_norm": 0.5857900381088257,
      "learning_rate": 7.028420108677635e-06,
      "loss": 0.971,
      "step": 161
    },
    {
      "epoch": 0.3065279091769158,
      "grad_norm": 0.602518618106842,
      "learning_rate": 6.684405196876842e-06,
      "loss": 1.0088,
      "step": 162
    },
    {
      "epoch": 0.30842005676442763,
      "grad_norm": 0.6160874962806702,
      "learning_rate": 6.3481314859657675e-06,
      "loss": 0.98,
      "step": 163
    },
    {
      "epoch": 0.31031220435193946,
      "grad_norm": 0.6301847100257874,
      "learning_rate": 6.019690909819298e-06,
      "loss": 1.0249,
      "step": 164
    },
    {
      "epoch": 0.3122043519394513,
      "grad_norm": 0.6426919102668762,
      "learning_rate": 5.6991732608115e-06,
      "loss": 0.988,
      "step": 165
    },
    {
      "epoch": 0.3140964995269631,
      "grad_norm": 0.633261501789093,
      "learning_rate": 5.386666165267256e-06,
      "loss": 1.0227,
      "step": 166
    },
    {
      "epoch": 0.31598864711447494,
      "grad_norm": 0.6106787919998169,
      "learning_rate": 5.08225505950613e-06,
      "loss": 0.9981,
      "step": 167
    },
    {
      "epoch": 0.31788079470198677,
      "grad_norm": 0.613427460193634,
      "learning_rate": 4.786023166484913e-06,
      "loss": 0.986,
      "step": 168
    },
    {
      "epoch": 0.3197729422894986,
      "grad_norm": 0.6015135645866394,
      "learning_rate": 4.498051473045291e-06,
      "loss": 0.9887,
      "step": 169
    },
    {
      "epoch": 0.3216650898770104,
      "grad_norm": 0.6138702034950256,
      "learning_rate": 4.218418707772886e-06,
      "loss": 1.0025,
      "step": 170
    },
    {
      "epoch": 0.32355723746452225,
      "grad_norm": 0.6031901836395264,
      "learning_rate": 3.947201319473587e-06,
      "loss": 0.9645,
      "step": 171
    },
    {
      "epoch": 0.3254493850520341,
      "grad_norm": 0.5855473279953003,
      "learning_rate": 3.684473456273278e-06,
      "loss": 0.9843,
      "step": 172
    },
    {
      "epoch": 0.3273415326395459,
      "grad_norm": 0.6010551452636719,
      "learning_rate": 3.4303069453464383e-06,
      "loss": 0.9744,
      "step": 173
    },
    {
      "epoch": 0.32923368022705773,
      "grad_norm": 0.6140182614326477,
      "learning_rate": 3.184771273279312e-06,
      "loss": 1.0002,
      "step": 174
    },
    {
      "epoch": 0.33112582781456956,
      "grad_norm": 0.6224749684333801,
      "learning_rate": 2.947933567072987e-06,
      "loss": 1.0287,
      "step": 175
    },
    {
      "epoch": 0.3330179754020814,
      "grad_norm": 0.6068156957626343,
      "learning_rate": 2.719858575791534e-06,
      "loss": 0.9889,
      "step": 176
    },
    {
      "epoch": 0.33491012298959316,
      "grad_norm": 0.6290980577468872,
      "learning_rate": 2.500608652860256e-06,
      "loss": 1.0303,
      "step": 177
    },
    {
      "epoch": 0.336802270577105,
      "grad_norm": 0.5990263819694519,
      "learning_rate": 2.2902437390188737e-06,
      "loss": 0.9933,
      "step": 178
    },
    {
      "epoch": 0.3386944181646168,
      "grad_norm": 0.6128520369529724,
      "learning_rate": 2.0888213459343587e-06,
      "loss": 0.9768,
      "step": 179
    },
    {
      "epoch": 0.34058656575212864,
      "grad_norm": 0.6209462285041809,
      "learning_rate": 1.8963965404777875e-06,
      "loss": 0.9888,
      "step": 180
    },
    {
      "epoch": 0.3424787133396405,
      "grad_norm": 0.6090012192726135,
      "learning_rate": 1.7130219296696263e-06,
      "loss": 1.0038,
      "step": 181
    },
    {
      "epoch": 0.3443708609271523,
      "grad_norm": 0.6358945965766907,
      "learning_rate": 1.5387476462974824e-06,
      "loss": 1.0175,
      "step": 182
    },
    {
      "epoch": 0.34626300851466413,
      "grad_norm": 0.6231580376625061,
      "learning_rate": 1.3736213352103147e-06,
      "loss": 0.9537,
      "step": 183
    },
    {
      "epoch": 0.34815515610217596,
      "grad_norm": 0.5991582274436951,
      "learning_rate": 1.2176881402928002e-06,
      "loss": 0.98,
      "step": 184
    },
    {
      "epoch": 0.3500473036896878,
      "grad_norm": 0.6204809546470642,
      "learning_rate": 1.0709906921234367e-06,
      "loss": 0.988,
      "step": 185
    },
    {
      "epoch": 0.3519394512771996,
      "grad_norm": 0.6237450838088989,
      "learning_rate": 9.33569096319799e-07,
      "loss": 0.9573,
      "step": 186
    },
    {
      "epoch": 0.35383159886471144,
      "grad_norm": 0.630352258682251,
      "learning_rate": 8.054609225740255e-07,
      "loss": 1.002,
      "step": 187
    },
    {
      "epoch": 0.35572374645222327,
      "grad_norm": 0.6284891963005066,
      "learning_rate": 6.867011943816724e-07,
      "loss": 0.9972,
      "step": 188
    },
    {
      "epoch": 0.3576158940397351,
      "grad_norm": 0.6370323896408081,
      "learning_rate": 5.77322379466617e-07,
      "loss": 0.9853,
      "step": 189
    },
    {
      "epoch": 0.3595080416272469,
      "grad_norm": 0.6147187948226929,
      "learning_rate": 4.773543809047186e-07,
      "loss": 0.9919,
      "step": 190
    },
    {
      "epoch": 0.36140018921475875,
      "grad_norm": 0.6740887761116028,
      "learning_rate": 3.868245289486027e-07,
      "loss": 1.0164,
      "step": 191
    },
    {
      "epoch": 0.3632923368022706,
      "grad_norm": 0.6504529118537903,
      "learning_rate": 3.0575757355586817e-07,
      "loss": 0.9722,
      "step": 192
    },
    {
      "epoch": 0.3651844843897824,
      "grad_norm": 0.6464083194732666,
      "learning_rate": 2.3417567762266497e-07,
      "loss": 0.9877,
      "step": 193
    },
    {
      "epoch": 0.36707663197729423,
      "grad_norm": 0.6853861808776855,
      "learning_rate": 1.7209841092460043e-07,
      "loss": 1.0176,
      "step": 194
    },
    {
      "epoch": 0.36896877956480606,
      "grad_norm": 0.6388038396835327,
      "learning_rate": 1.1954274476655534e-07,
      "loss": 0.9854,
      "step": 195
    },
    {
      "epoch": 0.3708609271523179,
      "grad_norm": 0.6803230047225952,
      "learning_rate": 7.652304734289127e-08,
      "loss": 0.9718,
      "step": 196
    },
    {
      "epoch": 0.3727530747398297,
      "grad_norm": 0.672921895980835,
      "learning_rate": 4.30510798093342e-08,
      "loss": 1.0099,
      "step": 197
    },
    {
      "epoch": 0.37464522232734154,
      "grad_norm": 0.7199356555938721,
      "learning_rate": 1.9135993067588284e-08,
      "loss": 1.035,
      "step": 198
    },
    {
      "epoch": 0.37653736991485337,
      "grad_norm": 0.703244149684906,
      "learning_rate": 4.784325263584854e-09,
      "loss": 0.9615,
      "step": 199
    },
    {
      "epoch": 0.3784295175023652,
      "grad_norm": 0.8193345665931702,
      "learning_rate": 0.0,
      "loss": 0.9844,
      "step": 200
    },
    {
      "epoch": 0.3784295175023652,
      "eval_loss": 0.9890570640563965,
      "eval_runtime": 66.7897,
      "eval_samples_per_second": 13.325,
      "eval_steps_per_second": 3.339,
      "step": 200
    }
  ],
  "logging_steps": 1,
  "max_steps": 200,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 50,
  "stateful_callbacks": {
    "EarlyStoppingCallback": {
      "args": {
        "early_stopping_patience": 4,
        "early_stopping_threshold": 0.0
      },
      "attributes": {
        "early_stopping_patience_counter": 0
      }
    },
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 3.017027157491712e+17,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}