{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 2.962025316455696,
  "eval_steps": 500,
  "global_step": 117,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.02531645569620253,
      "grad_norm": 0.28381249212278864,
      "learning_rate": 8.333333333333334e-06,
      "loss": 0.527,
      "step": 1
    },
    {
      "epoch": 0.05063291139240506,
      "grad_norm": 0.29332876337801134,
      "learning_rate": 1.6666666666666667e-05,
      "loss": 0.5152,
      "step": 2
    },
    {
      "epoch": 0.0759493670886076,
      "grad_norm": 0.42097245913011233,
      "learning_rate": 2.5e-05,
      "loss": 0.5138,
      "step": 3
    },
    {
      "epoch": 0.10126582278481013,
      "grad_norm": 0.31373613965244807,
      "learning_rate": 3.3333333333333335e-05,
      "loss": 0.4898,
      "step": 4
    },
    {
      "epoch": 0.12658227848101267,
      "grad_norm": 0.38811861849958174,
      "learning_rate": 4.166666666666667e-05,
      "loss": 0.4976,
      "step": 5
    },
    {
      "epoch": 0.1518987341772152,
      "grad_norm": 0.3665975538958321,
      "learning_rate": 5e-05,
      "loss": 0.4886,
      "step": 6
    },
    {
      "epoch": 0.17721518987341772,
      "grad_norm": 0.28812556883203455,
      "learning_rate": 5.833333333333334e-05,
      "loss": 0.4605,
      "step": 7
    },
    {
      "epoch": 0.20253164556962025,
      "grad_norm": 0.3161799363224881,
      "learning_rate": 6.666666666666667e-05,
      "loss": 0.4187,
      "step": 8
    },
    {
      "epoch": 0.22784810126582278,
      "grad_norm": 0.30351099872377285,
      "learning_rate": 7.500000000000001e-05,
      "loss": 0.3898,
      "step": 9
    },
    {
      "epoch": 0.25316455696202533,
      "grad_norm": 0.20421030715908728,
      "learning_rate": 8.333333333333334e-05,
      "loss": 0.2981,
      "step": 10
    },
    {
      "epoch": 0.27848101265822783,
      "grad_norm": 0.2622244347847273,
      "learning_rate": 9.166666666666667e-05,
      "loss": 0.2359,
      "step": 11
    },
    {
      "epoch": 0.3037974683544304,
      "grad_norm": 0.20123682547622748,
      "learning_rate": 0.0001,
      "loss": 0.3136,
      "step": 12
    },
    {
      "epoch": 0.3291139240506329,
      "grad_norm": 0.19424698101984617,
      "learning_rate": 9.997762161417517e-05,
      "loss": 0.2814,
      "step": 13
    },
    {
      "epoch": 0.35443037974683544,
      "grad_norm": 0.2138956216522083,
      "learning_rate": 9.991050648838675e-05,
      "loss": 0.2265,
      "step": 14
    },
    {
      "epoch": 0.379746835443038,
      "grad_norm": 0.23993237439220805,
      "learning_rate": 9.979871469976196e-05,
      "loss": 0.2007,
      "step": 15
    },
    {
      "epoch": 0.4050632911392405,
      "grad_norm": 0.20626020803621276,
      "learning_rate": 9.964234631709187e-05,
      "loss": 0.2496,
      "step": 16
    },
    {
      "epoch": 0.43037974683544306,
      "grad_norm": 0.16885750202973263,
      "learning_rate": 9.944154131125642e-05,
      "loss": 0.216,
      "step": 17
    },
    {
      "epoch": 0.45569620253164556,
      "grad_norm": 0.20604877553838427,
      "learning_rate": 9.919647942993148e-05,
      "loss": 0.2173,
      "step": 18
    },
    {
      "epoch": 0.4810126582278481,
      "grad_norm": 0.17817294328866598,
      "learning_rate": 9.890738003669029e-05,
      "loss": 0.2012,
      "step": 19
    },
    {
      "epoch": 0.5063291139240507,
      "grad_norm": 0.169371216914731,
      "learning_rate": 9.857450191464337e-05,
      "loss": 0.2249,
      "step": 20
    },
    {
      "epoch": 0.5316455696202531,
      "grad_norm": 0.16863849651520665,
      "learning_rate": 9.819814303479267e-05,
      "loss": 0.1928,
      "step": 21
    },
    {
      "epoch": 0.5569620253164557,
      "grad_norm": 0.15933923390114604,
      "learning_rate": 9.777864028930705e-05,
      "loss": 0.2231,
      "step": 22
    },
    {
      "epoch": 0.5822784810126582,
      "grad_norm": 0.1578071135366508,
      "learning_rate": 9.731636918995821e-05,
      "loss": 0.2078,
      "step": 23
    },
    {
      "epoch": 0.6075949367088608,
      "grad_norm": 0.14721022380875914,
      "learning_rate": 9.681174353198687e-05,
      "loss": 0.2151,
      "step": 24
    },
    {
      "epoch": 0.6329113924050633,
      "grad_norm": 0.16015977971909204,
      "learning_rate": 9.626521502369984e-05,
      "loss": 0.2108,
      "step": 25
    },
    {
      "epoch": 0.6582278481012658,
      "grad_norm": 0.22236247508590176,
      "learning_rate": 9.567727288213005e-05,
      "loss": 0.2015,
      "step": 26
    },
    {
      "epoch": 0.6835443037974683,
      "grad_norm": 0.12808123195714893,
      "learning_rate": 9.504844339512095e-05,
      "loss": 0.1715,
      "step": 27
    },
    {
      "epoch": 0.7088607594936709,
      "grad_norm": 0.14385399140847496,
      "learning_rate": 9.437928945022771e-05,
      "loss": 0.2256,
      "step": 28
    },
    {
      "epoch": 0.7341772151898734,
      "grad_norm": 0.1362215128043263,
      "learning_rate": 9.367041003085649e-05,
      "loss": 0.1813,
      "step": 29
    },
    {
      "epoch": 0.759493670886076,
      "grad_norm": 0.14186669882045214,
      "learning_rate": 9.292243968009331e-05,
      "loss": 0.2053,
      "step": 30
    },
    {
      "epoch": 0.7848101265822784,
      "grad_norm": 0.13378456553677073,
      "learning_rate": 9.213604793270196e-05,
      "loss": 0.2085,
      "step": 31
    },
    {
      "epoch": 0.810126582278481,
      "grad_norm": 0.14358937888813622,
      "learning_rate": 9.131193871579975e-05,
      "loss": 0.2008,
      "step": 32
    },
    {
      "epoch": 0.8354430379746836,
      "grad_norm": 0.147823569949849,
      "learning_rate": 9.045084971874738e-05,
      "loss": 0.2539,
      "step": 33
    },
    {
      "epoch": 0.8607594936708861,
      "grad_norm": 0.13623356559268837,
      "learning_rate": 8.955355173281708e-05,
      "loss": 0.1863,
      "step": 34
    },
    {
      "epoch": 0.8860759493670886,
      "grad_norm": 0.13948008252693808,
      "learning_rate": 8.862084796122998e-05,
      "loss": 0.1463,
      "step": 35
    },
    {
      "epoch": 0.9113924050632911,
      "grad_norm": 0.1339429888742059,
      "learning_rate": 8.765357330018056e-05,
      "loss": 0.1592,
      "step": 36
    },
    {
      "epoch": 0.9367088607594937,
      "grad_norm": 0.1602446905039844,
      "learning_rate": 8.665259359149132e-05,
      "loss": 0.2199,
      "step": 37
    },
    {
      "epoch": 0.9620253164556962,
      "grad_norm": 0.13728548840884053,
      "learning_rate": 8.561880484756725e-05,
      "loss": 0.178,
      "step": 38
    },
    {
      "epoch": 0.9873417721518988,
      "grad_norm": 0.13701462745977658,
      "learning_rate": 8.455313244934324e-05,
      "loss": 0.1739,
      "step": 39
    },
    {
      "epoch": 1.0126582278481013,
      "grad_norm": 0.2072023638259741,
      "learning_rate": 8.345653031794292e-05,
      "loss": 0.2222,
      "step": 40
    },
    {
      "epoch": 1.0379746835443038,
      "grad_norm": 0.15105393513368087,
      "learning_rate": 8.232998006078997e-05,
      "loss": 0.1479,
      "step": 41
    },
    {
      "epoch": 1.0632911392405062,
      "grad_norm": 0.15569390641449965,
      "learning_rate": 8.117449009293668e-05,
      "loss": 0.2338,
      "step": 42
    },
    {
      "epoch": 1.0886075949367089,
      "grad_norm": 0.16038992744587696,
      "learning_rate": 7.999109473439569e-05,
      "loss": 0.2465,
      "step": 43
    },
    {
      "epoch": 1.1139240506329113,
      "grad_norm": 0.14681811778410783,
      "learning_rate": 7.878085328428369e-05,
      "loss": 0.1957,
      "step": 44
    },
    {
      "epoch": 1.139240506329114,
      "grad_norm": 0.16734148603665647,
      "learning_rate": 7.754484907260513e-05,
      "loss": 0.2047,
      "step": 45
    },
    {
      "epoch": 1.1645569620253164,
      "grad_norm": 0.14760531374441424,
      "learning_rate": 7.628418849052523e-05,
      "loss": 0.149,
      "step": 46
    },
    {
      "epoch": 1.189873417721519,
      "grad_norm": 0.3076003175984034,
      "learning_rate": 7.500000000000001e-05,
      "loss": 0.1874,
      "step": 47
    },
    {
      "epoch": 1.2151898734177216,
      "grad_norm": 0.1342886833257913,
      "learning_rate": 7.369343312364993e-05,
      "loss": 0.1225,
      "step": 48
    },
    {
      "epoch": 1.240506329113924,
      "grad_norm": 0.1565758288110148,
      "learning_rate": 7.236565741578163e-05,
      "loss": 0.1709,
      "step": 49
    },
    {
      "epoch": 1.2658227848101267,
      "grad_norm": 0.12936285098939904,
      "learning_rate": 7.101786141547828e-05,
      "loss": 0.0952,
      "step": 50
    },
    {
      "epoch": 1.2911392405063291,
      "grad_norm": 0.1651361450780901,
      "learning_rate": 6.965125158269619e-05,
      "loss": 0.1798,
      "step": 51
    },
    {
      "epoch": 1.3164556962025316,
      "grad_norm": 0.18294240175450024,
      "learning_rate": 6.826705121831976e-05,
      "loss": 0.2146,
      "step": 52
    },
    {
      "epoch": 1.3417721518987342,
      "grad_norm": 0.15907649925734338,
      "learning_rate": 6.686649936914152e-05,
      "loss": 0.1651,
      "step": 53
    },
    {
      "epoch": 1.3670886075949367,
      "grad_norm": 0.15265125027320092,
      "learning_rate": 6.545084971874738e-05,
      "loss": 0.1318,
      "step": 54
    },
    {
      "epoch": 1.3924050632911391,
      "grad_norm": 0.15507370320317093,
      "learning_rate": 6.402136946530014e-05,
      "loss": 0.1396,
      "step": 55
    },
    {
      "epoch": 1.4177215189873418,
      "grad_norm": 0.17930905252960624,
      "learning_rate": 6.257933818722543e-05,
      "loss": 0.1627,
      "step": 56
    },
    {
      "epoch": 1.4430379746835442,
      "grad_norm": 0.1950350507388175,
      "learning_rate": 6.112604669781572e-05,
      "loss": 0.1178,
      "step": 57
    },
    {
      "epoch": 1.4683544303797469,
      "grad_norm": 0.16629437997930713,
      "learning_rate": 5.9662795889777666e-05,
      "loss": 0.1708,
      "step": 58
    },
    {
      "epoch": 1.4936708860759493,
      "grad_norm": 0.20546299378777336,
      "learning_rate": 5.819089557075689e-05,
      "loss": 0.1567,
      "step": 59
    },
    {
      "epoch": 1.518987341772152,
      "grad_norm": 0.15069790201742334,
      "learning_rate": 5.6711663290882776e-05,
      "loss": 0.1153,
      "step": 60
    },
    {
      "epoch": 1.5443037974683544,
      "grad_norm": 0.1819232976665009,
      "learning_rate": 5.522642316338268e-05,
      "loss": 0.2024,
      "step": 61
    },
    {
      "epoch": 1.5696202531645569,
      "grad_norm": 0.15124842383808745,
      "learning_rate": 5.373650467932122e-05,
      "loss": 0.1006,
      "step": 62
    },
    {
      "epoch": 1.5949367088607596,
      "grad_norm": 0.17606437452474172,
      "learning_rate": 5.2243241517525754e-05,
      "loss": 0.1583,
      "step": 63
    },
    {
      "epoch": 1.620253164556962,
      "grad_norm": 0.203467245813199,
      "learning_rate": 5.074797035076319e-05,
      "loss": 0.1928,
      "step": 64
    },
    {
      "epoch": 1.6455696202531644,
      "grad_norm": 0.17192119281095727,
      "learning_rate": 4.925202964923683e-05,
      "loss": 0.1186,
      "step": 65
    },
    {
      "epoch": 1.6708860759493671,
      "grad_norm": 0.16287577101677936,
      "learning_rate": 4.775675848247427e-05,
      "loss": 0.1179,
      "step": 66
    },
    {
      "epoch": 1.6962025316455698,
      "grad_norm": 0.16446919781752384,
      "learning_rate": 4.626349532067879e-05,
      "loss": 0.1128,
      "step": 67
    },
    {
      "epoch": 1.721518987341772,
      "grad_norm": 0.21462405849921243,
      "learning_rate": 4.477357683661734e-05,
      "loss": 0.1284,
      "step": 68
    },
    {
      "epoch": 1.7468354430379747,
      "grad_norm": 0.13999924246549017,
      "learning_rate": 4.328833670911724e-05,
      "loss": 0.1145,
      "step": 69
    },
    {
      "epoch": 1.7721518987341773,
      "grad_norm": 0.18064769980074544,
      "learning_rate": 4.180910442924312e-05,
      "loss": 0.1655,
      "step": 70
    },
    {
      "epoch": 1.7974683544303798,
      "grad_norm": 0.16541787975736866,
      "learning_rate": 4.0337204110222346e-05,
      "loss": 0.1204,
      "step": 71
    },
    {
      "epoch": 1.8227848101265822,
      "grad_norm": 0.17309004286105295,
      "learning_rate": 3.887395330218429e-05,
      "loss": 0.1118,
      "step": 72
    },
    {
      "epoch": 1.8481012658227849,
      "grad_norm": 0.17513841600341226,
      "learning_rate": 3.742066181277458e-05,
      "loss": 0.1424,
      "step": 73
    },
    {
      "epoch": 1.8734177215189873,
      "grad_norm": 0.19362821096770938,
      "learning_rate": 3.597863053469987e-05,
      "loss": 0.1682,
      "step": 74
    },
    {
      "epoch": 1.8987341772151898,
      "grad_norm": 0.20119249367834352,
      "learning_rate": 3.4549150281252636e-05,
      "loss": 0.1173,
      "step": 75
    },
    {
      "epoch": 1.9240506329113924,
      "grad_norm": 0.2085780534303345,
      "learning_rate": 3.313350063085851e-05,
      "loss": 0.1657,
      "step": 76
    },
    {
      "epoch": 1.9493670886075949,
      "grad_norm": 0.18223304941420868,
      "learning_rate": 3.173294878168025e-05,
      "loss": 0.1797,
      "step": 77
    },
    {
      "epoch": 1.9746835443037973,
      "grad_norm": 0.1891158533084314,
      "learning_rate": 3.0348748417303823e-05,
      "loss": 0.1319,
      "step": 78
    },
    {
      "epoch": 2.0,
      "grad_norm": 0.27462058932982153,
      "learning_rate": 2.8982138584521735e-05,
      "loss": 0.1609,
      "step": 79
    },
    {
      "epoch": 2.0253164556962027,
      "grad_norm": 0.18602374184501738,
      "learning_rate": 2.7634342584218365e-05,
      "loss": 0.099,
      "step": 80
    },
    {
      "epoch": 2.050632911392405,
      "grad_norm": 0.17573647458638603,
      "learning_rate": 2.630656687635007e-05,
      "loss": 0.1269,
      "step": 81
    },
    {
      "epoch": 2.0759493670886076,
      "grad_norm": 0.170011474839188,
      "learning_rate": 2.500000000000001e-05,
      "loss": 0.1492,
      "step": 82
    },
    {
      "epoch": 2.1012658227848102,
      "grad_norm": 0.16455052655933264,
      "learning_rate": 2.371581150947476e-05,
      "loss": 0.086,
      "step": 83
    },
    {
      "epoch": 2.1265822784810124,
      "grad_norm": 0.16183814372981142,
      "learning_rate": 2.245515092739488e-05,
      "loss": 0.0894,
      "step": 84
    },
    {
      "epoch": 2.151898734177215,
      "grad_norm": 0.1845809186683481,
      "learning_rate": 2.1219146715716332e-05,
      "loss": 0.1312,
      "step": 85
    },
    {
      "epoch": 2.1772151898734178,
      "grad_norm": 0.17513589542519134,
      "learning_rate": 2.0008905265604316e-05,
      "loss": 0.0934,
      "step": 86
    },
    {
      "epoch": 2.2025316455696204,
      "grad_norm": 0.2109199799220023,
      "learning_rate": 1.8825509907063327e-05,
      "loss": 0.093,
      "step": 87
    },
    {
      "epoch": 2.2278481012658227,
      "grad_norm": 0.17669643474539057,
      "learning_rate": 1.7670019939210024e-05,
      "loss": 0.087,
      "step": 88
    },
    {
      "epoch": 2.2531645569620253,
      "grad_norm": 0.21167114503852452,
      "learning_rate": 1.6543469682057106e-05,
      "loss": 0.114,
      "step": 89
    },
    {
      "epoch": 2.278481012658228,
      "grad_norm": 0.21139669768919672,
      "learning_rate": 1.544686755065677e-05,
      "loss": 0.1003,
      "step": 90
    },
    {
      "epoch": 2.3037974683544302,
      "grad_norm": 0.17912893970040897,
      "learning_rate": 1.438119515243277e-05,
      "loss": 0.1023,
      "step": 91
    },
    {
      "epoch": 2.329113924050633,
      "grad_norm": 0.19961182766357477,
      "learning_rate": 1.3347406408508695e-05,
      "loss": 0.0989,
      "step": 92
    },
    {
      "epoch": 2.3544303797468356,
      "grad_norm": 0.18672908810203143,
      "learning_rate": 1.2346426699819458e-05,
      "loss": 0.0865,
      "step": 93
    },
    {
      "epoch": 2.379746835443038,
      "grad_norm": 0.1970580774900479,
      "learning_rate": 1.137915203877003e-05,
      "loss": 0.0954,
      "step": 94
    },
    {
      "epoch": 2.4050632911392404,
      "grad_norm": 0.15997868673482188,
      "learning_rate": 1.0446448267182952e-05,
      "loss": 0.0751,
      "step": 95
    },
    {
      "epoch": 2.430379746835443,
      "grad_norm": 0.22896720413179728,
      "learning_rate": 9.549150281252633e-06,
      "loss": 0.0888,
      "step": 96
    },
    {
      "epoch": 2.4556962025316453,
      "grad_norm": 0.1837419155509244,
      "learning_rate": 8.688061284200266e-06,
      "loss": 0.091,
      "step": 97
    },
    {
      "epoch": 2.481012658227848,
      "grad_norm": 0.21793351897040644,
      "learning_rate": 7.863952067298042e-06,
      "loss": 0.0892,
      "step": 98
    },
    {
      "epoch": 2.5063291139240507,
      "grad_norm": 0.19632949222949325,
      "learning_rate": 7.077560319906695e-06,
      "loss": 0.088,
      "step": 99
    },
    {
      "epoch": 2.5316455696202533,
      "grad_norm": 0.21767182823620418,
      "learning_rate": 6.329589969143518e-06,
      "loss": 0.1415,
      "step": 100
    },
    {
      "epoch": 2.5569620253164556,
      "grad_norm": 0.2195952213656607,
      "learning_rate": 5.620710549772295e-06,
      "loss": 0.1036,
      "step": 101
    },
    {
      "epoch": 2.5822784810126582,
      "grad_norm": 0.19933172837107496,
      "learning_rate": 4.951556604879048e-06,
      "loss": 0.074,
      "step": 102
    },
    {
      "epoch": 2.607594936708861,
      "grad_norm": 0.20549095019371302,
      "learning_rate": 4.322727117869951e-06,
      "loss": 0.087,
      "step": 103
    },
    {
      "epoch": 2.632911392405063,
      "grad_norm": 0.19724008187075792,
      "learning_rate": 3.734784976300165e-06,
      "loss": 0.1255,
      "step": 104
    },
    {
      "epoch": 2.6582278481012658,
      "grad_norm": 0.22735257344640358,
      "learning_rate": 3.18825646801314e-06,
      "loss": 0.1352,
      "step": 105
    },
    {
      "epoch": 2.6835443037974684,
      "grad_norm": 0.20013828861070956,
      "learning_rate": 2.6836308100417873e-06,
      "loss": 0.0766,
      "step": 106
    },
    {
      "epoch": 2.708860759493671,
      "grad_norm": 0.20899162992915188,
      "learning_rate": 2.221359710692961e-06,
      "loss": 0.1113,
      "step": 107
    },
    {
      "epoch": 2.7341772151898733,
      "grad_norm": 0.22623291377890534,
      "learning_rate": 1.8018569652073381e-06,
      "loss": 0.1064,
      "step": 108
    },
    {
      "epoch": 2.759493670886076,
      "grad_norm": 0.24976299644855401,
      "learning_rate": 1.4254980853566247e-06,
      "loss": 0.109,
      "step": 109
    },
    {
      "epoch": 2.7848101265822782,
      "grad_norm": 0.20046850962635593,
      "learning_rate": 1.0926199633097157e-06,
      "loss": 0.1121,
      "step": 110
    },
    {
      "epoch": 2.810126582278481,
      "grad_norm": 0.21161953723512844,
      "learning_rate": 8.035205700685167e-07,
      "loss": 0.0884,
      "step": 111
    },
    {
      "epoch": 2.8354430379746836,
      "grad_norm": 0.23714913658575656,
      "learning_rate": 5.584586887435739e-07,
      "loss": 0.0868,
      "step": 112
    },
    {
      "epoch": 2.8607594936708862,
      "grad_norm": 0.20860035989411196,
      "learning_rate": 3.576536829081323e-07,
      "loss": 0.0945,
      "step": 113
    },
    {
      "epoch": 2.8860759493670884,
      "grad_norm": 0.264811602754133,
      "learning_rate": 2.012853002380466e-07,
      "loss": 0.1285,
      "step": 114
    },
    {
      "epoch": 2.911392405063291,
      "grad_norm": 0.21080729209863774,
      "learning_rate": 8.949351161324227e-08,
      "loss": 0.0733,
      "step": 115
    },
    {
      "epoch": 2.9367088607594938,
      "grad_norm": 0.21648721660730044,
      "learning_rate": 2.237838582483387e-08,
      "loss": 0.106,
      "step": 116
    },
    {
      "epoch": 2.962025316455696,
      "grad_norm": 0.20297309807693178,
      "learning_rate": 0.0,
      "loss": 0.11,
      "step": 117
    }
  ],
  "logging_steps": 1,
  "max_steps": 117,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 3,
  "save_steps": 500,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 480077453852672.0,
  "train_batch_size": 1,
  "trial_name": null,
  "trial_params": null
}