{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 2.1006564551422318,
  "eval_steps": 50,
  "global_step": 150,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.01400437636761488,
      "grad_norm": 61.57242965698242,
      "learning_rate": 7.499999999999999e-06,
      "loss": 74.331,
      "step": 1
    },
    {
      "epoch": 0.01400437636761488,
      "eval_loss": 2.3031234741210938,
      "eval_runtime": 37.3633,
      "eval_samples_per_second": 6.45,
      "eval_steps_per_second": 3.238,
      "step": 1
    },
    {
      "epoch": 0.02800875273522976,
      "grad_norm": 61.468421936035156,
      "learning_rate": 1.4999999999999999e-05,
      "loss": 75.5051,
      "step": 2
    },
    {
      "epoch": 0.04201312910284464,
      "grad_norm": 63.76738739013672,
      "learning_rate": 2.2499999999999998e-05,
      "loss": 73.1192,
      "step": 3
    },
    {
      "epoch": 0.05601750547045952,
      "grad_norm": 56.45806884765625,
      "learning_rate": 2.9999999999999997e-05,
      "loss": 69.8715,
      "step": 4
    },
    {
      "epoch": 0.0700218818380744,
      "grad_norm": 58.627620697021484,
      "learning_rate": 3.75e-05,
      "loss": 69.0347,
      "step": 5
    },
    {
      "epoch": 0.08402625820568928,
      "grad_norm": 60.42095947265625,
      "learning_rate": 4.4999999999999996e-05,
      "loss": 66.3695,
      "step": 6
    },
    {
      "epoch": 0.09803063457330416,
      "grad_norm": 57.68213653564453,
      "learning_rate": 5.2499999999999995e-05,
      "loss": 56.7572,
      "step": 7
    },
    {
      "epoch": 0.11203501094091904,
      "grad_norm": 56.33690643310547,
      "learning_rate": 5.9999999999999995e-05,
      "loss": 51.2878,
      "step": 8
    },
    {
      "epoch": 0.12603938730853392,
      "grad_norm": 52.97846221923828,
      "learning_rate": 6.75e-05,
      "loss": 36.918,
      "step": 9
    },
    {
      "epoch": 0.1400437636761488,
      "grad_norm": 46.914066314697266,
      "learning_rate": 7.5e-05,
      "loss": 27.3805,
      "step": 10
    },
    {
      "epoch": 0.1540481400437637,
      "grad_norm": 44.001502990722656,
      "learning_rate": 8.25e-05,
      "loss": 23.6946,
      "step": 11
    },
    {
      "epoch": 0.16805251641137856,
      "grad_norm": 30.6370849609375,
      "learning_rate": 8.999999999999999e-05,
      "loss": 15.6086,
      "step": 12
    },
    {
      "epoch": 0.18205689277899342,
      "grad_norm": 51.051727294921875,
      "learning_rate": 9.75e-05,
      "loss": 16.2046,
      "step": 13
    },
    {
      "epoch": 0.19606126914660832,
      "grad_norm": 64.03682708740234,
      "learning_rate": 0.00010499999999999999,
      "loss": 13.2331,
      "step": 14
    },
    {
      "epoch": 0.2100656455142232,
      "grad_norm": 34.19150924682617,
      "learning_rate": 0.0001125,
      "loss": 11.2453,
      "step": 15
    },
    {
      "epoch": 0.22407002188183808,
      "grad_norm": 34.346343994140625,
      "learning_rate": 0.00011999999999999999,
      "loss": 9.5668,
      "step": 16
    },
    {
      "epoch": 0.23807439824945295,
      "grad_norm": 26.109838485717773,
      "learning_rate": 0.00012749999999999998,
      "loss": 6.7749,
      "step": 17
    },
    {
      "epoch": 0.25207877461706785,
      "grad_norm": 17.14702606201172,
      "learning_rate": 0.000135,
      "loss": 6.2887,
      "step": 18
    },
    {
      "epoch": 0.2660831509846827,
      "grad_norm": 15.40426254272461,
      "learning_rate": 0.0001425,
      "loss": 5.1345,
      "step": 19
    },
    {
      "epoch": 0.2800875273522976,
      "grad_norm": 13.663360595703125,
      "learning_rate": 0.00015,
      "loss": 4.3361,
      "step": 20
    },
    {
      "epoch": 0.29409190371991245,
      "grad_norm": 14.994868278503418,
      "learning_rate": 0.00014997810105601446,
      "loss": 3.2669,
      "step": 21
    },
    {
      "epoch": 0.3080962800875274,
      "grad_norm": 17.923627853393555,
      "learning_rate": 0.0001499124170124245,
      "loss": 2.8837,
      "step": 22
    },
    {
      "epoch": 0.32210065645514224,
      "grad_norm": 10.781777381896973,
      "learning_rate": 0.00014980298622686183,
      "loss": 2.5867,
      "step": 23
    },
    {
      "epoch": 0.3361050328227571,
      "grad_norm": 17.933012008666992,
      "learning_rate": 0.00014964987260382363,
      "loss": 3.79,
      "step": 24
    },
    {
      "epoch": 0.350109409190372,
      "grad_norm": 14.919720649719238,
      "learning_rate": 0.00014945316555735403,
      "loss": 3.5252,
      "step": 25
    },
    {
      "epoch": 0.36411378555798685,
      "grad_norm": 13.19090747833252,
      "learning_rate": 0.0001492129799588288,
      "loss": 2.2783,
      "step": 26
    },
    {
      "epoch": 0.37811816192560177,
      "grad_norm": 14.870774269104004,
      "learning_rate": 0.0001489294560698738,
      "loss": 3.1369,
      "step": 27
    },
    {
      "epoch": 0.39212253829321664,
      "grad_norm": 14.277947425842285,
      "learning_rate": 0.000148602759460456,
      "loss": 2.5122,
      "step": 28
    },
    {
      "epoch": 0.4061269146608315,
      "grad_norm": 17.441390991210938,
      "learning_rate": 0.0001482330809121954,
      "loss": 2.9346,
      "step": 29
    },
    {
      "epoch": 0.4201312910284464,
      "grad_norm": 10.07897663116455,
      "learning_rate": 0.00014782063630695388,
      "loss": 2.3027,
      "step": 30
    },
    {
      "epoch": 0.43413566739606124,
      "grad_norm": 9.020223617553711,
      "learning_rate": 0.00014736566650076636,
      "loss": 1.944,
      "step": 31
    },
    {
      "epoch": 0.44814004376367617,
      "grad_norm": 12.858219146728516,
      "learning_rate": 0.00014686843718318744,
      "loss": 1.5195,
      "step": 32
    },
    {
      "epoch": 0.46214442013129103,
      "grad_norm": 10.95540714263916,
      "learning_rate": 0.00014632923872213652,
      "loss": 2.419,
      "step": 33
    },
    {
      "epoch": 0.4761487964989059,
      "grad_norm": 10.858210563659668,
      "learning_rate": 0.0001457483859943307,
      "loss": 2.6077,
      "step": 34
    },
    {
      "epoch": 0.49015317286652077,
      "grad_norm": 7.009860515594482,
      "learning_rate": 0.00014512621820140611,
      "loss": 2.3664,
      "step": 35
    },
    {
      "epoch": 0.5041575492341357,
      "grad_norm": 6.658543109893799,
      "learning_rate": 0.0001444630986718332,
      "loss": 1.1082,
      "step": 36
    },
    {
      "epoch": 0.5181619256017506,
      "grad_norm": 5.971487998962402,
      "learning_rate": 0.00014375941464874368,
      "loss": 1.558,
      "step": 37
    },
    {
      "epoch": 0.5321663019693654,
      "grad_norm": 7.628395080566406,
      "learning_rate": 0.0001430155770637909,
      "loss": 1.949,
      "step": 38
    },
    {
      "epoch": 0.5461706783369803,
      "grad_norm": 14.131255149841309,
      "learning_rate": 0.00014223202029717776,
      "loss": 2.6442,
      "step": 39
    },
    {
      "epoch": 0.5601750547045952,
      "grad_norm": 7.39982271194458,
      "learning_rate": 0.0001414092019239907,
      "loss": 1.7663,
      "step": 40
    },
    {
      "epoch": 0.57417943107221,
      "grad_norm": 8.183086395263672,
      "learning_rate": 0.00014054760244698884,
      "loss": 1.7819,
      "step": 41
    },
    {
      "epoch": 0.5881838074398249,
      "grad_norm": 6.441479682922363,
      "learning_rate": 0.00013964772501600368,
      "loss": 1.7133,
      "step": 42
    },
    {
      "epoch": 0.6021881838074398,
      "grad_norm": 11.74283504486084,
      "learning_rate": 0.00013871009513411408,
      "loss": 2.4207,
      "step": 43
    },
    {
      "epoch": 0.6161925601750547,
      "grad_norm": 6.086061477661133,
      "learning_rate": 0.00013773526035076698,
      "loss": 1.271,
      "step": 44
    },
    {
      "epoch": 0.6301969365426696,
      "grad_norm": 8.047619819641113,
      "learning_rate": 0.00013672378994202423,
      "loss": 1.837,
      "step": 45
    },
    {
      "epoch": 0.6442013129102845,
      "grad_norm": 11.720404624938965,
      "learning_rate": 0.00013567627457812106,
      "loss": 1.9628,
      "step": 46
    },
    {
      "epoch": 0.6582056892778994,
      "grad_norm": 7.418464660644531,
      "learning_rate": 0.00013459332597853157,
      "loss": 2.1906,
      "step": 47
    },
    {
      "epoch": 0.6722100656455142,
      "grad_norm": 5.253023147583008,
      "learning_rate": 0.00013347557655474167,
      "loss": 1.2249,
      "step": 48
    },
    {
      "epoch": 0.6862144420131291,
      "grad_norm": 6.372616291046143,
      "learning_rate": 0.0001323236790409386,
      "loss": 1.5337,
      "step": 49
    },
    {
      "epoch": 0.700218818380744,
      "grad_norm": 6.444860458374023,
      "learning_rate": 0.00013113830611283258,
      "loss": 1.9269,
      "step": 50
    },
    {
      "epoch": 0.700218818380744,
      "eval_loss": 0.06303766369819641,
      "eval_runtime": 37.4056,
      "eval_samples_per_second": 6.443,
      "eval_steps_per_second": 3.235,
      "step": 50
    },
    {
      "epoch": 0.7142231947483588,
      "grad_norm": 6.532812118530273,
      "learning_rate": 0.00012992014999483302,
      "loss": 1.7148,
      "step": 51
    },
    {
      "epoch": 0.7282275711159737,
      "grad_norm": 5.408838748931885,
      "learning_rate": 0.00012866992205580908,
      "loss": 2.6251,
      "step": 52
    },
    {
      "epoch": 0.7422319474835887,
      "grad_norm": 8.420281410217285,
      "learning_rate": 0.00012738835239367027,
      "loss": 1.8761,
      "step": 53
    },
    {
      "epoch": 0.7562363238512035,
      "grad_norm": 5.919778347015381,
      "learning_rate": 0.00012607618940900977,
      "loss": 1.8202,
      "step": 54
    },
    {
      "epoch": 0.7702407002188184,
      "grad_norm": 7.590326309204102,
      "learning_rate": 0.00012473419936805962,
      "loss": 2.0368,
      "step": 55
    },
    {
      "epoch": 0.7842450765864333,
      "grad_norm": 5.551327228546143,
      "learning_rate": 0.0001233631659552128,
      "loss": 1.5056,
      "step": 56
    },
    {
      "epoch": 0.7982494529540481,
      "grad_norm": 4.756547451019287,
      "learning_rate": 0.00012196388981537352,
      "loss": 1.9188,
      "step": 57
    },
    {
      "epoch": 0.812253829321663,
      "grad_norm": 5.172512054443359,
      "learning_rate": 0.00012053718808640333,
      "loss": 1.4091,
      "step": 58
    },
    {
      "epoch": 0.8262582056892779,
      "grad_norm": 8.058588981628418,
      "learning_rate": 0.00011908389392193547,
      "loss": 2.8933,
      "step": 59
    },
    {
      "epoch": 0.8402625820568927,
      "grad_norm": 5.907708168029785,
      "learning_rate": 0.00011760485600483667,
      "loss": 1.4843,
      "step": 60
    },
    {
      "epoch": 0.8542669584245076,
      "grad_norm": 6.655636310577393,
      "learning_rate": 0.00011610093805160025,
      "loss": 2.0464,
      "step": 61
    },
    {
      "epoch": 0.8682713347921225,
      "grad_norm": 7.76405668258667,
      "learning_rate": 0.00011457301830795994,
      "loss": 2.042,
      "step": 62
    },
    {
      "epoch": 0.8822757111597375,
      "grad_norm": 8.136941909790039,
      "learning_rate": 0.00011302198903601928,
      "loss": 1.8616,
      "step": 63
    },
    {
      "epoch": 0.8962800875273523,
      "grad_norm": 4.971902370452881,
      "learning_rate": 0.00011144875599319543,
      "loss": 1.8062,
      "step": 64
    },
    {
      "epoch": 0.9102844638949672,
      "grad_norm": 4.203851222991943,
      "learning_rate": 0.00010985423790328263,
      "loss": 1.1645,
      "step": 65
    },
    {
      "epoch": 0.9242888402625821,
      "grad_norm": 5.031311988830566,
      "learning_rate": 0.0001082393659199431,
      "loss": 1.5574,
      "step": 66
    },
    {
      "epoch": 0.9382932166301969,
      "grad_norm": 3.0670523643493652,
      "learning_rate": 0.00010660508308293968,
      "loss": 1.1308,
      "step": 67
    },
    {
      "epoch": 0.9522975929978118,
      "grad_norm": 6.76988410949707,
      "learning_rate": 0.00010495234376742714,
      "loss": 2.2786,
      "step": 68
    },
    {
      "epoch": 0.9663019693654267,
      "grad_norm": 5.402833938598633,
      "learning_rate": 0.00010328211312662403,
      "loss": 1.8765,
      "step": 69
    },
    {
      "epoch": 0.9803063457330415,
      "grad_norm": 2.743725299835205,
      "learning_rate": 0.00010159536652819016,
      "loss": 1.0839,
      "step": 70
    },
    {
      "epoch": 0.9943107221006564,
      "grad_norm": 8.331803321838379,
      "learning_rate": 9.989308898463963e-05,
      "loss": 2.9521,
      "step": 71
    },
    {
      "epoch": 1.0083150984682714,
      "grad_norm": 5.500734329223633,
      "learning_rate": 9.817627457812105e-05,
      "loss": 1.688,
      "step": 72
    },
    {
      "epoch": 1.0223194748358861,
      "grad_norm": 3.8026185035705566,
      "learning_rate": 9.644592587990168e-05,
      "loss": 0.9849,
      "step": 73
    },
    {
      "epoch": 1.0363238512035011,
      "grad_norm": 5.581955909729004,
      "learning_rate": 9.470305336489401e-05,
      "loss": 1.4484,
      "step": 74
    },
    {
      "epoch": 1.0503282275711159,
      "grad_norm": 4.310107231140137,
      "learning_rate": 9.294867482156682e-05,
      "loss": 1.399,
      "step": 75
    },
    {
      "epoch": 1.0643326039387309,
      "grad_norm": 3.703099489212036,
      "learning_rate": 9.118381475758547e-05,
      "loss": 1.0415,
      "step": 76
    },
    {
      "epoch": 1.0783369803063456,
      "grad_norm": 5.746537685394287,
      "learning_rate": 8.940950380152812e-05,
      "loss": 1.2911,
      "step": 77
    },
    {
      "epoch": 1.0923413566739606,
      "grad_norm": 6.078587055206299,
      "learning_rate": 8.762677810102787e-05,
      "loss": 1.3952,
      "step": 78
    },
    {
      "epoch": 1.1063457330415756,
      "grad_norm": 4.206238269805908,
      "learning_rate": 8.583667871769158e-05,
      "loss": 0.8058,
      "step": 79
    },
    {
      "epoch": 1.1203501094091903,
      "grad_norm": 5.329077243804932,
      "learning_rate": 8.404025101914921e-05,
      "loss": 1.4109,
      "step": 80
    },
    {
      "epoch": 1.1343544857768053,
      "grad_norm": 3.1190714836120605,
      "learning_rate": 8.223854406858862e-05,
      "loss": 1.0588,
      "step": 81
    },
    {
      "epoch": 1.14835886214442,
      "grad_norm": 4.825378894805908,
      "learning_rate": 8.043261001213218e-05,
      "loss": 1.3509,
      "step": 82
    },
    {
      "epoch": 1.162363238512035,
      "grad_norm": 2.4683196544647217,
      "learning_rate": 7.862350346441302e-05,
      "loss": 0.6952,
      "step": 83
    },
    {
      "epoch": 1.1763676148796498,
      "grad_norm": 2.656954050064087,
      "learning_rate": 7.681228089270991e-05,
      "loss": 0.5187,
      "step": 84
    },
    {
      "epoch": 1.1903719912472648,
      "grad_norm": 3.4884138107299805,
      "learning_rate": 7.5e-05,
      "loss": 1.5719,
      "step": 85
    },
    {
      "epoch": 1.2043763676148798,
      "grad_norm": 2.804727077484131,
      "learning_rate": 7.318771910729009e-05,
      "loss": 0.617,
      "step": 86
    },
    {
      "epoch": 1.2183807439824945,
      "grad_norm": 8.740808486938477,
      "learning_rate": 7.137649653558697e-05,
      "loss": 2.1117,
      "step": 87
    },
    {
      "epoch": 1.2323851203501095,
      "grad_norm": 4.6273040771484375,
      "learning_rate": 6.956738998786783e-05,
      "loss": 1.5451,
      "step": 88
    },
    {
      "epoch": 1.2463894967177243,
      "grad_norm": 4.325751304626465,
      "learning_rate": 6.776145593141136e-05,
      "loss": 0.6505,
      "step": 89
    },
    {
      "epoch": 1.2603938730853392,
      "grad_norm": 5.652192115783691,
      "learning_rate": 6.595974898085078e-05,
      "loss": 0.8753,
      "step": 90
    },
    {
      "epoch": 1.274398249452954,
      "grad_norm": 3.6028363704681396,
      "learning_rate": 6.416332128230842e-05,
      "loss": 1.332,
      "step": 91
    },
    {
      "epoch": 1.288402625820569,
      "grad_norm": 2.2218270301818848,
      "learning_rate": 6.23732218989721e-05,
      "loss": 0.987,
      "step": 92
    },
    {
      "epoch": 1.3024070021881837,
      "grad_norm": 6.646122932434082,
      "learning_rate": 6.059049619847186e-05,
      "loss": 1.5389,
      "step": 93
    },
    {
      "epoch": 1.3164113785557987,
      "grad_norm": 7.777625560760498,
      "learning_rate": 5.881618524241454e-05,
      "loss": 1.1984,
      "step": 94
    },
    {
      "epoch": 1.3304157549234135,
      "grad_norm": 4.249261856079102,
      "learning_rate": 5.7051325178433185e-05,
      "loss": 1.2531,
      "step": 95
    },
    {
      "epoch": 1.3444201312910284,
      "grad_norm": 4.338534355163574,
      "learning_rate": 5.5296946635105976e-05,
      "loss": 1.2022,
      "step": 96
    },
    {
      "epoch": 1.3584245076586434,
      "grad_norm": 4.526888370513916,
      "learning_rate": 5.355407412009831e-05,
      "loss": 1.2918,
      "step": 97
    },
    {
      "epoch": 1.3724288840262582,
      "grad_norm": 1.903158187866211,
      "learning_rate": 5.182372542187895e-05,
      "loss": 0.6883,
      "step": 98
    },
    {
      "epoch": 1.3864332603938732,
      "grad_norm": 2.0173211097717285,
      "learning_rate": 5.0106911015360376e-05,
      "loss": 0.4112,
      "step": 99
    },
    {
      "epoch": 1.400437636761488,
      "grad_norm": 3.6843745708465576,
      "learning_rate": 4.840463347180982e-05,
      "loss": 0.8737,
      "step": 100
    },
    {
      "epoch": 1.400437636761488,
      "eval_loss": 0.041964393109083176,
      "eval_runtime": 37.3672,
      "eval_samples_per_second": 6.45,
      "eval_steps_per_second": 3.238,
      "step": 100
    },
    {
      "epoch": 1.414442013129103,
      "grad_norm": 3.548274040222168,
      "learning_rate": 4.671788687337597e-05,
      "loss": 0.7798,
      "step": 101
    },
    {
      "epoch": 1.4284463894967177,
      "grad_norm": 4.813600063323975,
      "learning_rate": 4.5047656232572844e-05,
      "loss": 1.1566,
      "step": 102
    },
    {
      "epoch": 1.4424507658643326,
      "grad_norm": 4.773122787475586,
      "learning_rate": 4.339491691706033e-05,
      "loss": 1.3804,
      "step": 103
    },
    {
      "epoch": 1.4564551422319476,
      "grad_norm": 3.3103699684143066,
      "learning_rate": 4.176063408005691e-05,
      "loss": 1.4077,
      "step": 104
    },
    {
      "epoch": 1.4704595185995624,
      "grad_norm": 3.6766433715820312,
      "learning_rate": 4.014576209671735e-05,
      "loss": 0.5923,
      "step": 105
    },
    {
      "epoch": 1.4844638949671771,
      "grad_norm": 6.134750843048096,
      "learning_rate": 3.855124400680454e-05,
      "loss": 1.2521,
      "step": 106
    },
    {
      "epoch": 1.498468271334792,
      "grad_norm": 2.034276247024536,
      "learning_rate": 3.697801096398074e-05,
      "loss": 0.9222,
      "step": 107
    },
    {
      "epoch": 1.512472647702407,
      "grad_norm": 2.5875349044799805,
      "learning_rate": 3.542698169204003e-05,
      "loss": 1.0509,
      "step": 108
    },
    {
      "epoch": 1.5264770240700218,
      "grad_norm": 3.653195858001709,
      "learning_rate": 3.389906194839976e-05,
      "loss": 0.8065,
      "step": 109
    },
    {
      "epoch": 1.5404814004376368,
      "grad_norm": 2.953291893005371,
      "learning_rate": 3.239514399516332e-05,
      "loss": 0.8004,
      "step": 110
    },
    {
      "epoch": 1.5544857768052518,
      "grad_norm": 2.7536041736602783,
      "learning_rate": 3.091610607806452e-05,
      "loss": 0.9096,
      "step": 111
    },
    {
      "epoch": 1.5684901531728666,
      "grad_norm": 2.2399890422821045,
      "learning_rate": 2.946281191359666e-05,
      "loss": 0.6533,
      "step": 112
    },
    {
      "epoch": 1.5824945295404813,
      "grad_norm": 3.7951953411102295,
      "learning_rate": 2.803611018462647e-05,
      "loss": 1.3043,
      "step": 113
    },
    {
      "epoch": 1.5964989059080963,
      "grad_norm": 2.8344790935516357,
      "learning_rate": 2.663683404478722e-05,
      "loss": 0.8993,
      "step": 114
    },
    {
      "epoch": 1.6105032822757113,
      "grad_norm": 5.360260963439941,
      "learning_rate": 2.5265800631940373e-05,
      "loss": 0.9569,
      "step": 115
    },
    {
      "epoch": 1.624507658643326,
      "grad_norm": 3.68491792678833,
      "learning_rate": 2.3923810590990202e-05,
      "loss": 1.1964,
      "step": 116
    },
    {
      "epoch": 1.6385120350109408,
      "grad_norm": 3.5502588748931885,
      "learning_rate": 2.2611647606329732e-05,
      "loss": 0.6952,
      "step": 117
    },
    {
      "epoch": 1.6525164113785558,
      "grad_norm": 3.651139259338379,
      "learning_rate": 2.1330077944190924e-05,
      "loss": 0.8322,
      "step": 118
    },
    {
      "epoch": 1.6665207877461707,
      "grad_norm": 2.139017105102539,
      "learning_rate": 2.0079850005167007e-05,
      "loss": 0.8639,
      "step": 119
    },
    {
      "epoch": 1.6805251641137855,
      "grad_norm": 2.7729721069335938,
      "learning_rate": 1.8861693887167408e-05,
      "loss": 0.9181,
      "step": 120
    },
    {
      "epoch": 1.6945295404814005,
      "grad_norm": 6.1828694343566895,
      "learning_rate": 1.767632095906137e-05,
      "loss": 0.9663,
      "step": 121
    },
    {
      "epoch": 1.7085339168490155,
      "grad_norm": 4.041149616241455,
      "learning_rate": 1.652442344525833e-05,
      "loss": 0.8917,
      "step": 122
    },
    {
      "epoch": 1.7225382932166302,
      "grad_norm": 3.7865874767303467,
      "learning_rate": 1.5406674021468438e-05,
      "loss": 0.6371,
      "step": 123
    },
    {
      "epoch": 1.736542669584245,
      "grad_norm": 4.79685640335083,
      "learning_rate": 1.4323725421878949e-05,
      "loss": 1.9381,
      "step": 124
    },
    {
      "epoch": 1.75054704595186,
      "grad_norm": 5.138647556304932,
      "learning_rate": 1.3276210057975772e-05,
      "loss": 1.5856,
      "step": 125
    },
    {
      "epoch": 1.764551422319475,
      "grad_norm": 4.413456916809082,
      "learning_rate": 1.2264739649232993e-05,
      "loss": 0.8713,
      "step": 126
    },
    {
      "epoch": 1.7785557986870897,
      "grad_norm": 4.086208820343018,
      "learning_rate": 1.1289904865885935e-05,
      "loss": 1.2824,
      "step": 127
    },
    {
      "epoch": 1.7925601750547044,
      "grad_norm": 3.734248638153076,
      "learning_rate": 1.0352274983996303e-05,
      "loss": 1.2958,
      "step": 128
    },
    {
      "epoch": 1.8065645514223194,
      "grad_norm": 3.341744899749756,
      "learning_rate": 9.452397553011157e-06,
      "loss": 1.1603,
      "step": 129
    },
    {
      "epoch": 1.8205689277899344,
      "grad_norm": 3.1986019611358643,
      "learning_rate": 8.590798076009264e-06,
      "loss": 0.9917,
      "step": 130
    },
    {
      "epoch": 1.8345733041575492,
      "grad_norm": 3.3532114028930664,
      "learning_rate": 7.767979702822217e-06,
      "loss": 1.2726,
      "step": 131
    },
    {
      "epoch": 1.8485776805251641,
      "grad_norm": 3.4645676612854004,
      "learning_rate": 6.984422936209094e-06,
      "loss": 1.4443,
      "step": 132
    },
    {
      "epoch": 1.8625820568927791,
      "grad_norm": 2.8891472816467285,
      "learning_rate": 6.240585351256319e-06,
      "loss": 0.617,
      "step": 133
    },
    {
      "epoch": 1.8765864332603939,
      "grad_norm": 1.9834930896759033,
      "learning_rate": 5.536901328166773e-06,
      "loss": 0.9543,
      "step": 134
    },
    {
      "epoch": 1.8905908096280086,
      "grad_norm": 2.3800172805786133,
      "learning_rate": 4.8737817985938955e-06,
      "loss": 0.6986,
      "step": 135
    },
    {
      "epoch": 1.9045951859956236,
      "grad_norm": 3.166862964630127,
      "learning_rate": 4.251614005669263e-06,
      "loss": 0.8229,
      "step": 136
    },
    {
      "epoch": 1.9185995623632386,
      "grad_norm": 3.0179944038391113,
      "learning_rate": 3.670761277863485e-06,
      "loss": 0.9884,
      "step": 137
    },
    {
      "epoch": 1.9326039387308533,
      "grad_norm": 2.6429646015167236,
      "learning_rate": 3.131562816812533e-06,
      "loss": 0.8383,
      "step": 138
    },
    {
      "epoch": 1.9466083150984683,
      "grad_norm": 4.193005561828613,
      "learning_rate": 2.6343334992336485e-06,
      "loss": 0.942,
      "step": 139
    },
    {
      "epoch": 1.9606126914660833,
      "grad_norm": 3.3709728717803955,
      "learning_rate": 2.179363693046099e-06,
      "loss": 1.0905,
      "step": 140
    },
    {
      "epoch": 1.974617067833698,
      "grad_norm": 6.372537612915039,
      "learning_rate": 1.7669190878045914e-06,
      "loss": 1.1225,
      "step": 141
    },
    {
      "epoch": 1.9886214442013128,
      "grad_norm": 3.8733949661254883,
      "learning_rate": 1.3972405395439922e-06,
      "loss": 1.4751,
      "step": 142
    },
    {
      "epoch": 2.0026258205689276,
      "grad_norm": 3.375497341156006,
      "learning_rate": 1.0705439301261887e-06,
      "loss": 0.9681,
      "step": 143
    },
    {
      "epoch": 2.0166301969365428,
      "grad_norm": 2.1956636905670166,
      "learning_rate": 7.870200411711658e-07,
      "loss": 0.97,
      "step": 144
    },
    {
      "epoch": 2.0306345733041575,
      "grad_norm": 2.438053607940674,
      "learning_rate": 5.46834442645952e-07,
      "loss": 0.9683,
      "step": 145
    },
    {
      "epoch": 2.0446389496717723,
      "grad_norm": 4.763875484466553,
      "learning_rate": 3.501273961763529e-07,
      "loss": 1.1133,
      "step": 146
    },
    {
      "epoch": 2.0586433260393875,
      "grad_norm": 1.9470134973526,
      "learning_rate": 1.9701377313817158e-07,
      "loss": 0.6127,
      "step": 147
    },
    {
      "epoch": 2.0726477024070022,
      "grad_norm": 2.1176681518554688,
      "learning_rate": 8.758298757550186e-08,
      "loss": 0.9606,
      "step": 148
    },
    {
      "epoch": 2.086652078774617,
      "grad_norm": 2.0052874088287354,
      "learning_rate": 2.1898943985529384e-08,
      "loss": 0.6702,
      "step": 149
    },
    {
      "epoch": 2.1006564551422318,
      "grad_norm": 1.8249067068099976,
      "learning_rate": 0.0,
      "loss": 0.4741,
      "step": 150
    },
    {
      "epoch": 2.1006564551422318,
      "eval_loss": 0.03468266502022743,
      "eval_runtime": 37.372,
      "eval_samples_per_second": 6.449,
      "eval_steps_per_second": 3.238,
      "step": 150
    }
  ],
  "logging_steps": 1,
  "max_steps": 150,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 3,
  "save_steps": 13,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 1.530862239744e+18,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}