{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 2.0,
  "eval_steps": 500,
  "global_step": 234,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.008547008547008548,
      "grad_norm": 0.17424613237380981,
      "learning_rate": 2e-05,
      "loss": 1.7889,
      "step": 1
    },
    {
      "epoch": 0.017094017094017096,
      "grad_norm": 0.1736629158258438,
      "learning_rate": 4e-05,
      "loss": 1.3589,
      "step": 2
    },
    {
      "epoch": 0.02564102564102564,
      "grad_norm": 0.1898377388715744,
      "learning_rate": 6e-05,
      "loss": 1.8064,
      "step": 3
    },
    {
      "epoch": 0.03418803418803419,
      "grad_norm": 0.203221395611763,
      "learning_rate": 8e-05,
      "loss": 2.0415,
      "step": 4
    },
    {
      "epoch": 0.042735042735042736,
      "grad_norm": 0.1799948662519455,
      "learning_rate": 0.0001,
      "loss": 1.6291,
      "step": 5
    },
    {
      "epoch": 0.05128205128205128,
      "grad_norm": 0.17798663675785065,
      "learning_rate": 0.00012,
      "loss": 2.0392,
      "step": 6
    },
    {
      "epoch": 0.05982905982905983,
      "grad_norm": 0.18702112138271332,
      "learning_rate": 0.00014,
      "loss": 1.6122,
      "step": 7
    },
    {
      "epoch": 0.06837606837606838,
      "grad_norm": 0.15779322385787964,
      "learning_rate": 0.00016,
      "loss": 1.6366,
      "step": 8
    },
    {
      "epoch": 0.07692307692307693,
      "grad_norm": 0.16097557544708252,
      "learning_rate": 0.00018,
      "loss": 1.4243,
      "step": 9
    },
    {
      "epoch": 0.08547008547008547,
      "grad_norm": 0.24233727157115936,
      "learning_rate": 0.0002,
      "loss": 1.8261,
      "step": 10
    },
    {
      "epoch": 0.09401709401709402,
      "grad_norm": 0.21837319433689117,
      "learning_rate": 0.0001999976474595967,
      "loss": 1.8375,
      "step": 11
    },
    {
      "epoch": 0.10256410256410256,
      "grad_norm": 0.1537744700908661,
      "learning_rate": 0.00019999058994907564,
      "loss": 1.4731,
      "step": 12
    },
    {
      "epoch": 0.1111111111111111,
      "grad_norm": 0.170364648103714,
      "learning_rate": 0.00019997882780049847,
      "loss": 1.5884,
      "step": 13
    },
    {
      "epoch": 0.11965811965811966,
      "grad_norm": 0.15152305364608765,
      "learning_rate": 0.0001999623615672837,
      "loss": 1.8465,
      "step": 14
    },
    {
      "epoch": 0.1282051282051282,
      "grad_norm": 0.15080629289150238,
      "learning_rate": 0.00019994119202418098,
      "loss": 1.7975,
      "step": 15
    },
    {
      "epoch": 0.13675213675213677,
      "grad_norm": 0.14586149156093597,
      "learning_rate": 0.00019991532016723439,
      "loss": 1.4316,
      "step": 16
    },
    {
      "epoch": 0.1452991452991453,
      "grad_norm": 0.143412247300148,
      "learning_rate": 0.00019988474721373568,
      "loss": 1.9093,
      "step": 17
    },
    {
      "epoch": 0.15384615384615385,
      "grad_norm": 0.1399279683828354,
      "learning_rate": 0.00019984947460216707,
      "loss": 1.2154,
      "step": 18
    },
    {
      "epoch": 0.1623931623931624,
      "grad_norm": 0.17332254350185394,
      "learning_rate": 0.00019980950399213344,
      "loss": 1.5147,
      "step": 19
    },
    {
      "epoch": 0.17094017094017094,
      "grad_norm": 0.15907926857471466,
      "learning_rate": 0.00019976483726428422,
      "loss": 1.22,
      "step": 20
    },
    {
      "epoch": 0.1794871794871795,
      "grad_norm": 0.17602041363716125,
      "learning_rate": 0.0001997154765202251,
      "loss": 1.2712,
      "step": 21
    },
    {
      "epoch": 0.18803418803418803,
      "grad_norm": 0.1826002299785614,
      "learning_rate": 0.00019966142408241901,
      "loss": 1.5025,
      "step": 22
    },
    {
      "epoch": 0.19658119658119658,
      "grad_norm": 0.19422835111618042,
      "learning_rate": 0.00019960268249407675,
      "loss": 1.5527,
      "step": 23
    },
    {
      "epoch": 0.20512820512820512,
      "grad_norm": 0.18412941694259644,
      "learning_rate": 0.00019953925451903756,
      "loss": 1.4429,
      "step": 24
    },
    {
      "epoch": 0.21367521367521367,
      "grad_norm": 0.17428062856197357,
      "learning_rate": 0.0001994711431416389,
      "loss": 2.1797,
      "step": 25
    },
    {
      "epoch": 0.2222222222222222,
      "grad_norm": 0.17244970798492432,
      "learning_rate": 0.00019939835156657616,
      "loss": 1.9712,
      "step": 26
    },
    {
      "epoch": 0.23076923076923078,
      "grad_norm": 0.14775343239307404,
      "learning_rate": 0.00019932088321875172,
      "loss": 1.4019,
      "step": 27
    },
    {
      "epoch": 0.23931623931623933,
      "grad_norm": 0.17615348100662231,
      "learning_rate": 0.00019923874174311394,
      "loss": 1.1836,
      "step": 28
    },
    {
      "epoch": 0.24786324786324787,
      "grad_norm": 0.14396396279335022,
      "learning_rate": 0.0001991519310044857,
      "loss": 1.7511,
      "step": 29
    },
    {
      "epoch": 0.2564102564102564,
      "grad_norm": 0.1678997278213501,
      "learning_rate": 0.00019906045508738228,
      "loss": 1.6097,
      "step": 30
    },
    {
      "epoch": 0.26495726495726496,
      "grad_norm": 0.140168696641922,
      "learning_rate": 0.0001989643182958196,
      "loss": 1.2644,
      "step": 31
    },
    {
      "epoch": 0.27350427350427353,
      "grad_norm": 0.1790284663438797,
      "learning_rate": 0.00019886352515311134,
      "loss": 1.3387,
      "step": 32
    },
    {
      "epoch": 0.28205128205128205,
      "grad_norm": 0.160356342792511,
      "learning_rate": 0.0001987580804016563,
      "loss": 1.6599,
      "step": 33
    },
    {
      "epoch": 0.2905982905982906,
      "grad_norm": 0.16769911348819733,
      "learning_rate": 0.00019864798900271532,
      "loss": 1.5747,
      "step": 34
    },
    {
      "epoch": 0.29914529914529914,
      "grad_norm": 0.1620282530784607,
      "learning_rate": 0.0001985332561361776,
      "loss": 1.3,
      "step": 35
    },
    {
      "epoch": 0.3076923076923077,
      "grad_norm": 0.14948143064975739,
      "learning_rate": 0.00019841388720031727,
      "loss": 1.1657,
      "step": 36
    },
    {
      "epoch": 0.3162393162393162,
      "grad_norm": 0.1771283745765686,
      "learning_rate": 0.00019828988781153917,
      "loss": 1.4809,
      "step": 37
    },
    {
      "epoch": 0.3247863247863248,
      "grad_norm": 0.16619449853897095,
      "learning_rate": 0.00019816126380411476,
      "loss": 1.3213,
      "step": 38
    },
    {
      "epoch": 0.3333333333333333,
      "grad_norm": 0.15086504817008972,
      "learning_rate": 0.00019802802122990758,
      "loss": 1.3772,
      "step": 39
    },
    {
      "epoch": 0.3418803418803419,
      "grad_norm": 0.18030764162540436,
      "learning_rate": 0.00019789016635808837,
      "loss": 1.4383,
      "step": 40
    },
    {
      "epoch": 0.3504273504273504,
      "grad_norm": 0.1466120481491089,
      "learning_rate": 0.00019774770567484022,
      "loss": 1.4808,
      "step": 41
    },
    {
      "epoch": 0.358974358974359,
      "grad_norm": 0.14574064314365387,
      "learning_rate": 0.00019760064588305345,
      "loss": 1.2758,
      "step": 42
    },
    {
      "epoch": 0.36752136752136755,
      "grad_norm": 0.1460503488779068,
      "learning_rate": 0.00019744899390201006,
      "loss": 1.2585,
      "step": 43
    },
    {
      "epoch": 0.37606837606837606,
      "grad_norm": 0.15577222406864166,
      "learning_rate": 0.0001972927568670583,
      "loss": 1.7296,
      "step": 44
    },
    {
      "epoch": 0.38461538461538464,
      "grad_norm": 0.16191129386425018,
      "learning_rate": 0.00019713194212927696,
      "loss": 1.4425,
      "step": 45
    },
    {
      "epoch": 0.39316239316239315,
      "grad_norm": 0.180201917886734,
      "learning_rate": 0.00019696655725512933,
      "loss": 1.3318,
      "step": 46
    },
    {
      "epoch": 0.4017094017094017,
      "grad_norm": 0.17621096968650818,
      "learning_rate": 0.00019679661002610743,
      "loss": 1.3787,
      "step": 47
    },
    {
      "epoch": 0.41025641025641024,
      "grad_norm": 0.15179012715816498,
      "learning_rate": 0.00019662210843836574,
      "loss": 1.2288,
      "step": 48
    },
    {
      "epoch": 0.4188034188034188,
      "grad_norm": 0.17625261843204498,
      "learning_rate": 0.0001964430607023449,
      "loss": 1.362,
      "step": 49
    },
    {
      "epoch": 0.42735042735042733,
      "grad_norm": 0.2081981599330902,
      "learning_rate": 0.00019625947524238563,
      "loss": 1.7481,
      "step": 50
    },
    {
      "epoch": 0.4358974358974359,
      "grad_norm": 0.16698336601257324,
      "learning_rate": 0.00019607136069633212,
      "loss": 1.3257,
      "step": 51
    },
    {
      "epoch": 0.4444444444444444,
      "grad_norm": 0.15349215269088745,
      "learning_rate": 0.0001958787259151258,
      "loss": 1.2898,
      "step": 52
    },
    {
      "epoch": 0.452991452991453,
      "grad_norm": 0.1789768785238266,
      "learning_rate": 0.00019568157996238884,
      "loss": 1.3996,
      "step": 53
    },
    {
      "epoch": 0.46153846153846156,
      "grad_norm": 0.14934459328651428,
      "learning_rate": 0.0001954799321139975,
      "loss": 1.7246,
      "step": 54
    },
    {
      "epoch": 0.4700854700854701,
      "grad_norm": 0.15673181414604187,
      "learning_rate": 0.00019527379185764612,
      "loss": 1.2129,
      "step": 55
    },
    {
      "epoch": 0.47863247863247865,
      "grad_norm": 0.19993078708648682,
      "learning_rate": 0.00019506316889240027,
      "loss": 1.7753,
      "step": 56
    },
    {
      "epoch": 0.48717948717948717,
      "grad_norm": 0.1767326444387436,
      "learning_rate": 0.00019484807312824067,
      "loss": 1.1891,
      "step": 57
    },
    {
      "epoch": 0.49572649572649574,
      "grad_norm": 0.2193121314048767,
      "learning_rate": 0.0001946285146855968,
      "loss": 1.4018,
      "step": 58
    },
    {
      "epoch": 0.5042735042735043,
      "grad_norm": 0.18395313620567322,
      "learning_rate": 0.0001944045038948709,
      "loss": 1.2613,
      "step": 59
    },
    {
      "epoch": 0.5128205128205128,
      "grad_norm": 0.19356532394886017,
      "learning_rate": 0.00019417605129595157,
      "loss": 1.1606,
      "step": 60
    },
    {
      "epoch": 0.5213675213675214,
      "grad_norm": 0.20749132335186005,
      "learning_rate": 0.0001939431676377183,
      "loss": 1.2299,
      "step": 61
    },
    {
      "epoch": 0.5299145299145299,
      "grad_norm": 0.1726475954055786,
      "learning_rate": 0.0001937058638775353,
      "loss": 1.0828,
      "step": 62
    },
    {
      "epoch": 0.5384615384615384,
      "grad_norm": 0.1452275812625885,
      "learning_rate": 0.00019346415118073632,
      "loss": 1.9403,
      "step": 63
    },
    {
      "epoch": 0.5470085470085471,
      "grad_norm": 0.20886297523975372,
      "learning_rate": 0.00019321804092009906,
      "loss": 1.3598,
      "step": 64
    },
    {
      "epoch": 0.5555555555555556,
      "grad_norm": 0.19738954305648804,
      "learning_rate": 0.00019296754467531014,
      "loss": 1.2469,
      "step": 65
    },
    {
      "epoch": 0.5641025641025641,
      "grad_norm": 0.23291267454624176,
      "learning_rate": 0.00019271267423242024,
      "loss": 1.1946,
      "step": 66
    },
    {
      "epoch": 0.5726495726495726,
      "grad_norm": 0.2172214835882187,
      "learning_rate": 0.00019245344158328972,
      "loss": 1.5041,
      "step": 67
    },
    {
      "epoch": 0.5811965811965812,
      "grad_norm": 0.2076561003923416,
      "learning_rate": 0.0001921898589250242,
      "loss": 1.2608,
      "step": 68
    },
    {
      "epoch": 0.5897435897435898,
      "grad_norm": 0.187509685754776,
      "learning_rate": 0.0001919219386594007,
      "loss": 1.2722,
      "step": 69
    },
    {
      "epoch": 0.5982905982905983,
      "grad_norm": 0.19337813556194305,
      "learning_rate": 0.00019164969339228422,
      "loss": 1.3573,
      "step": 70
    },
    {
      "epoch": 0.6068376068376068,
      "grad_norm": 0.2286800742149353,
      "learning_rate": 0.00019137313593303463,
      "loss": 1.3611,
      "step": 71
    },
    {
      "epoch": 0.6153846153846154,
      "grad_norm": 0.17622244358062744,
      "learning_rate": 0.00019109227929390378,
      "loss": 2.1658,
      "step": 72
    },
    {
      "epoch": 0.6239316239316239,
      "grad_norm": 0.2051881104707718,
      "learning_rate": 0.00019080713668942356,
      "loss": 1.2844,
      "step": 73
    },
    {
      "epoch": 0.6324786324786325,
      "grad_norm": 0.20667484402656555,
      "learning_rate": 0.00019051772153578389,
      "loss": 1.1692,
      "step": 74
    },
    {
      "epoch": 0.6410256410256411,
      "grad_norm": 0.21888047456741333,
      "learning_rate": 0.00019022404745020163,
      "loss": 1.1527,
      "step": 75
    },
    {
      "epoch": 0.6495726495726496,
      "grad_norm": 0.1887664496898651,
      "learning_rate": 0.00018992612825027976,
      "loss": 1.2714,
      "step": 76
    },
    {
      "epoch": 0.6581196581196581,
      "grad_norm": 0.25063708424568176,
      "learning_rate": 0.0001896239779533575,
      "loss": 1.3904,
      "step": 77
    },
    {
      "epoch": 0.6666666666666666,
      "grad_norm": 0.2010890245437622,
      "learning_rate": 0.00018931761077585035,
      "loss": 1.1843,
      "step": 78
    },
    {
      "epoch": 0.6752136752136753,
      "grad_norm": 0.20284424722194672,
      "learning_rate": 0.00018900704113258165,
      "loss": 1.0914,
      "step": 79
    },
    {
      "epoch": 0.6837606837606838,
      "grad_norm": 0.20292750000953674,
      "learning_rate": 0.00018869228363610404,
      "loss": 1.1945,
      "step": 80
    },
    {
      "epoch": 0.6923076923076923,
      "grad_norm": 0.2656649649143219,
      "learning_rate": 0.00018837335309601213,
      "loss": 1.3174,
      "step": 81
    },
    {
      "epoch": 0.7008547008547008,
      "grad_norm": 0.19038134813308716,
      "learning_rate": 0.00018805026451824546,
      "loss": 1.8758,
      "step": 82
    },
    {
      "epoch": 0.7094017094017094,
      "grad_norm": 0.19635434448719025,
      "learning_rate": 0.00018772303310438275,
      "loss": 1.7643,
      "step": 83
    },
    {
      "epoch": 0.717948717948718,
      "grad_norm": 0.20333418250083923,
      "learning_rate": 0.00018739167425092644,
      "loss": 1.7937,
      "step": 84
    },
    {
      "epoch": 0.7264957264957265,
      "grad_norm": 0.2025371640920639,
      "learning_rate": 0.00018705620354857833,
      "loss": 1.1183,
      "step": 85
    },
    {
      "epoch": 0.7350427350427351,
      "grad_norm": 0.22109034657478333,
      "learning_rate": 0.00018671663678150607,
      "loss": 1.0984,
      "step": 86
    },
    {
      "epoch": 0.7435897435897436,
      "grad_norm": 0.207436203956604,
      "learning_rate": 0.0001863729899266004,
      "loss": 1.1577,
      "step": 87
    },
    {
      "epoch": 0.7521367521367521,
      "grad_norm": 0.23750126361846924,
      "learning_rate": 0.0001860252791527236,
      "loss": 1.635,
      "step": 88
    },
    {
      "epoch": 0.7606837606837606,
      "grad_norm": 0.18621255457401276,
      "learning_rate": 0.00018567352081994852,
      "loss": 1.7687,
      "step": 89
    },
    {
      "epoch": 0.7692307692307693,
      "grad_norm": 0.18724265694618225,
      "learning_rate": 0.00018531773147878895,
      "loss": 1.7867,
      "step": 90
    },
    {
      "epoch": 0.7777777777777778,
      "grad_norm": 0.22778168320655823,
      "learning_rate": 0.0001849579278694209,
      "loss": 1.2273,
      "step": 91
    },
    {
      "epoch": 0.7863247863247863,
      "grad_norm": 0.22308748960494995,
      "learning_rate": 0.00018459412692089494,
      "loss": 1.2479,
      "step": 92
    },
    {
      "epoch": 0.7948717948717948,
      "grad_norm": 0.21641641855239868,
      "learning_rate": 0.0001842263457503397,
      "loss": 1.1156,
      "step": 93
    },
    {
      "epoch": 0.8034188034188035,
      "grad_norm": 0.24323439598083496,
      "learning_rate": 0.00018385460166215638,
      "loss": 1.3997,
      "step": 94
    },
    {
      "epoch": 0.811965811965812,
      "grad_norm": 0.2553081810474396,
      "learning_rate": 0.00018347891214720477,
      "loss": 1.1956,
      "step": 95
    },
    {
      "epoch": 0.8205128205128205,
      "grad_norm": 0.192823588848114,
      "learning_rate": 0.00018309929488198012,
      "loss": 1.813,
      "step": 96
    },
    {
      "epoch": 0.8290598290598291,
      "grad_norm": 0.24415500462055206,
      "learning_rate": 0.00018271576772778154,
      "loss": 1.2135,
      "step": 97
    },
    {
      "epoch": 0.8376068376068376,
      "grad_norm": 0.22568519413471222,
      "learning_rate": 0.00018232834872987147,
      "loss": 1.8256,
      "step": 98
    },
    {
      "epoch": 0.8461538461538461,
      "grad_norm": 0.2517865002155304,
      "learning_rate": 0.00018193705611662696,
      "loss": 1.2788,
      "step": 99
    },
    {
      "epoch": 0.8547008547008547,
      "grad_norm": 0.2798250913619995,
      "learning_rate": 0.0001815419082986815,
      "loss": 1.4225,
      "step": 100
    },
    {
      "epoch": 0.8632478632478633,
      "grad_norm": 0.20875456929206848,
      "learning_rate": 0.00018114292386805936,
      "loss": 1.6024,
      "step": 101
    },
    {
      "epoch": 0.8717948717948718,
      "grad_norm": 0.1969788372516632,
      "learning_rate": 0.00018074012159730032,
      "loss": 1.8428,
      "step": 102
    },
    {
      "epoch": 0.8803418803418803,
      "grad_norm": 0.20729199051856995,
      "learning_rate": 0.00018033352043857675,
      "loss": 1.4009,
      "step": 103
    },
    {
      "epoch": 0.8888888888888888,
      "grad_norm": 0.21610009670257568,
      "learning_rate": 0.00017992313952280172,
      "loss": 1.769,
      "step": 104
    },
    {
      "epoch": 0.8974358974358975,
      "grad_norm": 0.21818678081035614,
      "learning_rate": 0.00017950899815872892,
      "loss": 1.919,
      "step": 105
    },
    {
      "epoch": 0.905982905982906,
      "grad_norm": 0.3048407733440399,
      "learning_rate": 0.00017909111583204422,
      "loss": 1.7712,
      "step": 106
    },
    {
      "epoch": 0.9145299145299145,
      "grad_norm": 0.3431422710418701,
      "learning_rate": 0.0001786695122044487,
      "loss": 1.3565,
      "step": 107
    },
    {
      "epoch": 0.9230769230769231,
      "grad_norm": 0.2217400223016739,
      "learning_rate": 0.0001782442071127338,
      "loss": 1.7571,
      "step": 108
    },
    {
      "epoch": 0.9316239316239316,
      "grad_norm": 0.29589998722076416,
      "learning_rate": 0.0001778152205678477,
      "loss": 1.7932,
      "step": 109
    },
    {
      "epoch": 0.9401709401709402,
      "grad_norm": 0.2844977080821991,
      "learning_rate": 0.00017738257275395404,
      "loss": 1.3841,
      "step": 110
    },
    {
      "epoch": 0.9487179487179487,
      "grad_norm": 0.24854885041713715,
      "learning_rate": 0.00017694628402748202,
      "loss": 1.1902,
      "step": 111
    },
    {
      "epoch": 0.9572649572649573,
      "grad_norm": 0.2537485957145691,
      "learning_rate": 0.0001765063749161688,
      "loss": 1.2673,
      "step": 112
    },
    {
      "epoch": 0.9658119658119658,
      "grad_norm": 0.2731517255306244,
      "learning_rate": 0.00017606286611809353,
      "loss": 1.2555,
      "step": 113
    },
    {
      "epoch": 0.9743589743589743,
      "grad_norm": 0.24051187932491302,
      "learning_rate": 0.00017561577850070355,
      "loss": 1.3397,
      "step": 114
    },
    {
      "epoch": 0.9829059829059829,
      "grad_norm": 0.2200351357460022,
      "learning_rate": 0.00017516513309983253,
      "loss": 1.1119,
      "step": 115
    },
    {
      "epoch": 0.9914529914529915,
      "grad_norm": 0.29839056730270386,
      "learning_rate": 0.00017471095111871074,
      "loss": 1.3709,
      "step": 116
    },
    {
      "epoch": 1.0,
      "grad_norm": 0.23434622585773468,
      "learning_rate": 0.0001742532539269674,
      "loss": 1.1741,
      "step": 117
    },
    {
      "epoch": 1.0085470085470085,
      "grad_norm": 0.23401354253292084,
      "learning_rate": 0.00017379206305962526,
      "loss": 1.0751,
      "step": 118
    },
    {
      "epoch": 1.017094017094017,
      "grad_norm": 0.24140281975269318,
      "learning_rate": 0.00017332740021608722,
      "loss": 1.077,
      "step": 119
    },
    {
      "epoch": 1.0256410256410255,
      "grad_norm": 0.27418169379234314,
      "learning_rate": 0.00017285928725911562,
      "loss": 1.1409,
      "step": 120
    },
    {
      "epoch": 1.0341880341880343,
      "grad_norm": 0.3128631114959717,
      "learning_rate": 0.00017238774621380337,
      "loss": 1.1578,
      "step": 121
    },
    {
      "epoch": 1.0427350427350428,
      "grad_norm": 0.23959437012672424,
      "learning_rate": 0.00017191279926653761,
      "loss": 1.988,
      "step": 122
    },
    {
      "epoch": 1.0512820512820513,
      "grad_norm": 0.259440541267395,
      "learning_rate": 0.00017143446876395602,
      "loss": 1.7755,
      "step": 123
    },
    {
      "epoch": 1.0598290598290598,
      "grad_norm": 0.22774603962898254,
      "learning_rate": 0.00017095277721189528,
      "loss": 1.7069,
      "step": 124
    },
    {
      "epoch": 1.0683760683760684,
      "grad_norm": 0.2853987216949463,
      "learning_rate": 0.00017046774727433222,
      "loss": 1.1868,
      "step": 125
    },
    {
      "epoch": 1.0769230769230769,
      "grad_norm": 0.2648456394672394,
      "learning_rate": 0.00016997940177231722,
      "loss": 1.0607,
      "step": 126
    },
    {
      "epoch": 1.0854700854700854,
      "grad_norm": 0.21033689379692078,
      "learning_rate": 0.00016948776368290084,
      "loss": 1.7483,
      "step": 127
    },
    {
      "epoch": 1.0940170940170941,
      "grad_norm": 0.2851806581020355,
      "learning_rate": 0.00016899285613805246,
      "loss": 0.9906,
      "step": 128
    },
    {
      "epoch": 1.1025641025641026,
      "grad_norm": 0.29302412271499634,
      "learning_rate": 0.00016849470242357196,
      "loss": 1.0733,
      "step": 129
    },
    {
      "epoch": 1.1111111111111112,
      "grad_norm": 0.2884501516819,
      "learning_rate": 0.00016799332597799413,
      "loss": 1.1676,
      "step": 130
    },
    {
      "epoch": 1.1196581196581197,
      "grad_norm": 0.26243993639945984,
      "learning_rate": 0.00016748875039148593,
      "loss": 1.5788,
      "step": 131
    },
    {
      "epoch": 1.1282051282051282,
      "grad_norm": 0.2301926463842392,
      "learning_rate": 0.0001669809994047364,
      "loss": 1.6793,
      "step": 132
    },
    {
      "epoch": 1.1367521367521367,
      "grad_norm": 0.2946681082248688,
      "learning_rate": 0.0001664700969078398,
      "loss": 1.2275,
      "step": 133
    },
    {
      "epoch": 1.1452991452991452,
      "grad_norm": 0.2194235473871231,
      "learning_rate": 0.00016595606693917142,
      "loss": 1.6844,
      "step": 134
    },
    {
      "epoch": 1.1538461538461537,
      "grad_norm": 0.24949957430362701,
      "learning_rate": 0.00016543893368425666,
      "loss": 1.0142,
      "step": 135
    },
    {
      "epoch": 1.1623931623931625,
      "grad_norm": 0.29410868883132935,
      "learning_rate": 0.00016491872147463306,
      "loss": 1.0962,
      "step": 136
    },
    {
      "epoch": 1.170940170940171,
      "grad_norm": 0.21689262986183167,
      "learning_rate": 0.00016439545478670543,
      "loss": 2.3927,
      "step": 137
    },
    {
      "epoch": 1.1794871794871795,
      "grad_norm": 0.28670018911361694,
      "learning_rate": 0.00016386915824059427,
      "loss": 1.0522,
      "step": 138
    },
    {
      "epoch": 1.188034188034188,
      "grad_norm": 0.25839945673942566,
      "learning_rate": 0.00016333985659897735,
      "loss": 0.9783,
      "step": 139
    },
    {
      "epoch": 1.1965811965811965,
      "grad_norm": 0.3567582964897156,
      "learning_rate": 0.00016280757476592466,
      "loss": 1.1115,
      "step": 140
    },
    {
      "epoch": 1.205128205128205,
      "grad_norm": 0.2851192355155945,
      "learning_rate": 0.0001622723377857265,
      "loss": 1.1181,
      "step": 141
    },
    {
      "epoch": 1.2136752136752136,
      "grad_norm": 0.23090043663978577,
      "learning_rate": 0.00016173417084171536,
      "loss": 1.7546,
      "step": 142
    },
    {
      "epoch": 1.2222222222222223,
      "grad_norm": 0.2993018329143524,
      "learning_rate": 0.00016119309925508078,
      "loss": 1.12,
      "step": 143
    },
    {
      "epoch": 1.2307692307692308,
      "grad_norm": 0.3502201437950134,
      "learning_rate": 0.0001606491484836782,
      "loss": 1.1383,
      "step": 144
    },
    {
      "epoch": 1.2393162393162394,
      "grad_norm": 0.3279533386230469,
      "learning_rate": 0.00016010234412083086,
      "loss": 1.116,
      "step": 145
    },
    {
      "epoch": 1.2478632478632479,
      "grad_norm": 0.30735889077186584,
      "learning_rate": 0.00015955271189412598,
      "loss": 1.2025,
      "step": 146
    },
    {
      "epoch": 1.2564102564102564,
      "grad_norm": 0.3305642008781433,
      "learning_rate": 0.00015900027766420393,
      "loss": 1.1144,
      "step": 147
    },
    {
      "epoch": 1.264957264957265,
      "grad_norm": 0.3071320354938507,
      "learning_rate": 0.00015844506742354164,
      "loss": 1.1524,
      "step": 148
    },
    {
      "epoch": 1.2735042735042734,
      "grad_norm": 0.20446474850177765,
      "learning_rate": 0.00015788710729522953,
      "loss": 1.5036,
      "step": 149
    },
    {
      "epoch": 1.282051282051282,
      "grad_norm": 0.3168157637119293,
      "learning_rate": 0.00015732642353174259,
      "loss": 1.6971,
      "step": 150
    },
    {
      "epoch": 1.2905982905982907,
      "grad_norm": 0.2681102156639099,
      "learning_rate": 0.0001567630425137049,
      "loss": 0.898,
      "step": 151
    },
    {
      "epoch": 1.2991452991452992,
      "grad_norm": 0.3173544406890869,
      "learning_rate": 0.00015619699074864864,
      "loss": 0.9953,
      "step": 152
    },
    {
      "epoch": 1.3076923076923077,
      "grad_norm": 0.355228990316391,
      "learning_rate": 0.00015562829486976673,
      "loss": 1.2261,
      "step": 153
    },
    {
      "epoch": 1.3162393162393162,
      "grad_norm": 0.31110596656799316,
      "learning_rate": 0.00015505698163465986,
      "loss": 1.4145,
      "step": 154
    },
    {
      "epoch": 1.3247863247863247,
      "grad_norm": 0.34020379185676575,
      "learning_rate": 0.00015448307792407734,
      "loss": 1.0687,
      "step": 155
    },
    {
      "epoch": 1.3333333333333333,
      "grad_norm": 0.29489684104919434,
      "learning_rate": 0.00015390661074065256,
      "loss": 1.0736,
      "step": 156
    },
    {
      "epoch": 1.341880341880342,
      "grad_norm": 0.26536640524864197,
      "learning_rate": 0.00015332760720763232,
      "loss": 1.7907,
      "step": 157
    },
    {
      "epoch": 1.3504273504273505,
      "grad_norm": 0.37698546051979065,
      "learning_rate": 0.00015274609456760073,
      "loss": 1.1021,
      "step": 158
    },
    {
      "epoch": 1.358974358974359,
      "grad_norm": 0.3642312288284302,
      "learning_rate": 0.00015216210018119733,
      "loss": 1.3004,
      "step": 159
    },
    {
      "epoch": 1.3675213675213675,
      "grad_norm": 0.3472050726413727,
      "learning_rate": 0.00015157565152583002,
      "loss": 0.9691,
      "step": 160
    },
    {
      "epoch": 1.376068376068376,
      "grad_norm": 0.33574604988098145,
      "learning_rate": 0.0001509867761943818,
      "loss": 1.2569,
      "step": 161
    },
    {
      "epoch": 1.3846153846153846,
      "grad_norm": 0.36424562335014343,
      "learning_rate": 0.00015039550189391298,
      "loss": 1.0695,
      "step": 162
    },
    {
      "epoch": 1.393162393162393,
      "grad_norm": 0.2944134771823883,
      "learning_rate": 0.0001498018564443571,
      "loss": 1.488,
      "step": 163
    },
    {
      "epoch": 1.4017094017094016,
      "grad_norm": 0.3835750222206116,
      "learning_rate": 0.0001492058677772123,
      "loss": 1.4408,
      "step": 164
    },
    {
      "epoch": 1.4102564102564101,
      "grad_norm": 0.3394653797149658,
      "learning_rate": 0.000148607563934227,
      "loss": 1.1648,
      "step": 165
    },
    {
      "epoch": 1.4188034188034189,
      "grad_norm": 0.2613736391067505,
      "learning_rate": 0.00014800697306608044,
      "loss": 0.8816,
      "step": 166
    },
    {
      "epoch": 1.4273504273504274,
      "grad_norm": 0.31841540336608887,
      "learning_rate": 0.00014740412343105828,
      "loss": 1.3399,
      "step": 167
    },
    {
      "epoch": 1.435897435897436,
      "grad_norm": 0.33013221621513367,
      "learning_rate": 0.00014679904339372302,
      "loss": 1.0821,
      "step": 168
    },
    {
      "epoch": 1.4444444444444444,
      "grad_norm": 0.35095587372779846,
      "learning_rate": 0.00014619176142357935,
      "loss": 1.0055,
      "step": 169
    },
    {
      "epoch": 1.452991452991453,
      "grad_norm": 0.3409000635147095,
      "learning_rate": 0.0001455823060937347,
      "loss": 1.1507,
      "step": 170
    },
    {
      "epoch": 1.4615384615384617,
      "grad_norm": 0.3400250971317291,
      "learning_rate": 0.00014497070607955476,
      "loss": 1.0127,
      "step": 171
    },
    {
      "epoch": 1.4700854700854702,
      "grad_norm": 0.3428599536418915,
      "learning_rate": 0.00014435699015731448,
      "loss": 1.0493,
      "step": 172
    },
    {
      "epoch": 1.4786324786324787,
      "grad_norm": 0.3085605502128601,
      "learning_rate": 0.00014374118720284388,
      "loss": 1.2153,
      "step": 173
    },
    {
      "epoch": 1.4871794871794872,
      "grad_norm": 0.26580706238746643,
      "learning_rate": 0.00014312332619016965,
      "loss": 1.3625,
      "step": 174
    },
    {
      "epoch": 1.4957264957264957,
      "grad_norm": 0.34680411219596863,
      "learning_rate": 0.0001425034361901516,
      "loss": 1.1775,
      "step": 175
    },
    {
      "epoch": 1.5042735042735043,
      "grad_norm": 0.317070335149765,
      "learning_rate": 0.00014188154636911524,
      "loss": 1.7189,
      "step": 176
    },
    {
      "epoch": 1.5128205128205128,
      "grad_norm": 0.39725956320762634,
      "learning_rate": 0.0001412576859874791,
      "loss": 1.0802,
      "step": 177
    },
    {
      "epoch": 1.5213675213675213,
      "grad_norm": 0.3366641402244568,
      "learning_rate": 0.00014063188439837832,
      "loss": 1.0153,
      "step": 178
    },
    {
      "epoch": 1.5299145299145298,
      "grad_norm": 0.3365512490272522,
      "learning_rate": 0.0001400041710462833,
      "loss": 1.0023,
      "step": 179
    },
    {
      "epoch": 1.5384615384615383,
      "grad_norm": 0.3443971872329712,
      "learning_rate": 0.0001393745754656146,
      "loss": 1.0784,
      "step": 180
    },
    {
      "epoch": 1.547008547008547,
      "grad_norm": 0.3158676028251648,
      "learning_rate": 0.00013874312727935292,
      "loss": 1.0342,
      "step": 181
    },
    {
      "epoch": 1.5555555555555556,
      "grad_norm": 0.3261699676513672,
      "learning_rate": 0.00013810985619764572,
      "loss": 1.7786,
      "step": 182
    },
    {
      "epoch": 1.564102564102564,
      "grad_norm": 0.3323323428630829,
      "learning_rate": 0.00013747479201640914,
      "loss": 0.984,
      "step": 183
    },
    {
      "epoch": 1.5726495726495726,
      "grad_norm": 0.39274442195892334,
      "learning_rate": 0.00013683796461592604,
      "loss": 1.104,
      "step": 184
    },
    {
      "epoch": 1.5811965811965814,
      "grad_norm": 0.3277168273925781,
      "learning_rate": 0.00013619940395944027,
      "loss": 1.1087,
      "step": 185
    },
    {
      "epoch": 1.5897435897435899,
      "grad_norm": 0.3574274480342865,
      "learning_rate": 0.00013555914009174663,
      "loss": 1.0967,
      "step": 186
    },
    {
      "epoch": 1.5982905982905984,
      "grad_norm": 0.3351602852344513,
      "learning_rate": 0.00013491720313777756,
      "loss": 1.5144,
      "step": 187
    },
    {
      "epoch": 1.606837606837607,
      "grad_norm": 0.35201290249824524,
      "learning_rate": 0.00013427362330118543,
      "loss": 1.0471,
      "step": 188
    },
    {
      "epoch": 1.6153846153846154,
      "grad_norm": 0.3592745065689087,
      "learning_rate": 0.0001336284308629216,
      "loss": 1.315,
      "step": 189
    },
    {
      "epoch": 1.623931623931624,
      "grad_norm": 0.3243856728076935,
      "learning_rate": 0.00013298165617981172,
      "loss": 1.345,
      "step": 190
    },
    {
      "epoch": 1.6324786324786325,
      "grad_norm": 0.3796270787715912,
      "learning_rate": 0.00013233332968312715,
      "loss": 1.4821,
      "step": 191
    },
    {
      "epoch": 1.641025641025641,
      "grad_norm": 0.36001330614089966,
      "learning_rate": 0.0001316834818771535,
      "loss": 1.1569,
      "step": 192
    },
    {
      "epoch": 1.6495726495726495,
      "grad_norm": 0.39287564158439636,
      "learning_rate": 0.00013103214333775521,
      "loss": 1.1965,
      "step": 193
    },
    {
      "epoch": 1.658119658119658,
      "grad_norm": 0.38017645478248596,
      "learning_rate": 0.00013037934471093682,
      "loss": 1.0135,
      "step": 194
    },
    {
      "epoch": 1.6666666666666665,
      "grad_norm": 0.3751702606678009,
      "learning_rate": 0.00012972511671140125,
      "loss": 1.0617,
      "step": 195
    },
    {
      "epoch": 1.6752136752136753,
      "grad_norm": 0.3148857355117798,
      "learning_rate": 0.00012906949012110456,
      "loss": 1.3559,
      "step": 196
    },
    {
      "epoch": 1.6837606837606838,
      "grad_norm": 0.44921553134918213,
      "learning_rate": 0.00012841249578780757,
      "loss": 1.3055,
      "step": 197
    },
    {
      "epoch": 1.6923076923076923,
      "grad_norm": 0.2940453588962555,
      "learning_rate": 0.00012775416462362457,
      "loss": 1.1186,
      "step": 198
    },
    {
      "epoch": 1.7008547008547008,
      "grad_norm": 0.31202247738838196,
      "learning_rate": 0.00012709452760356884,
      "loss": 1.6689,
      "step": 199
    },
    {
      "epoch": 1.7094017094017095,
      "grad_norm": 0.34548264741897583,
      "learning_rate": 0.00012643361576409516,
      "loss": 1.0929,
      "step": 200
    },
    {
      "epoch": 1.717948717948718,
      "grad_norm": 0.36168211698532104,
      "learning_rate": 0.00012577146020163968,
      "loss": 1.1417,
      "step": 201
    },
    {
      "epoch": 1.7264957264957266,
      "grad_norm": 0.40510398149490356,
      "learning_rate": 0.00012510809207115666,
      "loss": 1.0695,
      "step": 202
    },
    {
      "epoch": 1.735042735042735,
      "grad_norm": 0.3778018653392792,
      "learning_rate": 0.00012444354258465268,
      "loss": 1.0432,
      "step": 203
    },
    {
      "epoch": 1.7435897435897436,
      "grad_norm": 0.3535318672657013,
      "learning_rate": 0.00012377784300971807,
      "loss": 1.5086,
      "step": 204
    },
    {
      "epoch": 1.7521367521367521,
      "grad_norm": 0.33403706550598145,
      "learning_rate": 0.0001231110246680558,
      "loss": 1.8465,
      "step": 205
    },
    {
      "epoch": 1.7606837606837606,
      "grad_norm": 0.41274493932724,
      "learning_rate": 0.00012244311893400763,
      "loss": 1.2511,
      "step": 206
    },
    {
      "epoch": 1.7692307692307692,
      "grad_norm": 0.40675127506256104,
      "learning_rate": 0.00012177415723307808,
      "loss": 1.1954,
      "step": 207
    },
    {
      "epoch": 1.7777777777777777,
      "grad_norm": 0.33072736859321594,
      "learning_rate": 0.00012110417104045575,
      "loss": 0.9234,
      "step": 208
    },
    {
      "epoch": 1.7863247863247862,
      "grad_norm": 0.33449140191078186,
      "learning_rate": 0.00012043319187953241,
      "loss": 1.1381,
      "step": 209
    },
    {
      "epoch": 1.7948717948717947,
      "grad_norm": 0.3770657181739807,
      "learning_rate": 0.00011976125132041974,
      "loss": 1.1838,
      "step": 210
    },
    {
      "epoch": 1.8034188034188035,
      "grad_norm": 0.39121079444885254,
      "learning_rate": 0.00011908838097846404,
      "loss": 1.2558,
      "step": 211
    },
    {
      "epoch": 1.811965811965812,
      "grad_norm": 0.3337252736091614,
      "learning_rate": 0.00011841461251275867,
      "loss": 1.3797,
      "step": 212
    },
    {
      "epoch": 1.8205128205128205,
      "grad_norm": 0.39863598346710205,
      "learning_rate": 0.00011773997762465429,
      "loss": 1.0192,
      "step": 213
    },
    {
      "epoch": 1.8290598290598292,
      "grad_norm": 0.3270687162876129,
      "learning_rate": 0.0001170645080562676,
      "loss": 1.0908,
      "step": 214
    },
    {
      "epoch": 1.8376068376068377,
      "grad_norm": 0.3414366543292999,
      "learning_rate": 0.00011638823558898762,
      "loss": 0.9952,
      "step": 215
    },
    {
      "epoch": 1.8461538461538463,
      "grad_norm": 0.37312328815460205,
      "learning_rate": 0.00011571119204198037,
      "loss": 1.0204,
      "step": 216
    },
    {
      "epoch": 1.8547008547008548,
      "grad_norm": 0.3227859139442444,
      "learning_rate": 0.00011503340927069189,
      "loss": 1.1573,
      "step": 217
    },
    {
      "epoch": 1.8632478632478633,
      "grad_norm": 0.3155539333820343,
      "learning_rate": 0.00011435491916534919,
      "loss": 1.0304,
      "step": 218
    },
    {
      "epoch": 1.8717948717948718,
      "grad_norm": 0.3540095090866089,
      "learning_rate": 0.00011367575364946006,
      "loss": 1.0772,
      "step": 219
    },
    {
      "epoch": 1.8803418803418803,
      "grad_norm": 0.39118003845214844,
      "learning_rate": 0.00011299594467831078,
      "loss": 1.0519,
      "step": 220
    },
    {
      "epoch": 1.8888888888888888,
      "grad_norm": 0.38508284091949463,
      "learning_rate": 0.00011231552423746283,
      "loss": 1.1445,
      "step": 221
    },
    {
      "epoch": 1.8974358974358974,
      "grad_norm": 0.33124974370002747,
      "learning_rate": 0.00011163452434124773,
      "loss": 1.071,
      "step": 222
    },
    {
      "epoch": 1.9059829059829059,
      "grad_norm": 0.3828192353248596,
      "learning_rate": 0.00011095297703126093,
      "loss": 1.0704,
      "step": 223
    },
    {
      "epoch": 1.9145299145299144,
      "grad_norm": 0.35031619668006897,
      "learning_rate": 0.00011027091437485404,
      "loss": 1.2472,
      "step": 224
    },
    {
      "epoch": 1.9230769230769231,
      "grad_norm": 0.32266342639923096,
      "learning_rate": 0.00010958836846362621,
      "loss": 1.3921,
      "step": 225
    },
    {
      "epoch": 1.9316239316239316,
      "grad_norm": 0.387516587972641,
      "learning_rate": 0.00010890537141191417,
      "loss": 0.9988,
      "step": 226
    },
    {
      "epoch": 1.9401709401709402,
      "grad_norm": 0.3335883915424347,
      "learning_rate": 0.00010822195535528106,
      "loss": 1.568,
      "step": 227
    },
    {
      "epoch": 1.9487179487179487,
      "grad_norm": 0.3533664345741272,
      "learning_rate": 0.00010753815244900458,
      "loss": 0.9217,
      "step": 228
    },
    {
      "epoch": 1.9572649572649574,
      "grad_norm": 0.40452811121940613,
      "learning_rate": 0.00010685399486656406,
      "loss": 1.2411,
      "step": 229
    },
    {
      "epoch": 1.965811965811966,
      "grad_norm": 0.3665294051170349,
      "learning_rate": 0.00010616951479812658,
      "loss": 1.0943,
      "step": 230
    },
    {
      "epoch": 1.9743589743589745,
      "grad_norm": 0.39548802375793457,
      "learning_rate": 0.00010548474444903247,
      "loss": 1.0392,
      "step": 231
    },
    {
      "epoch": 1.982905982905983,
      "grad_norm": 0.3631138503551483,
      "learning_rate": 0.00010479971603828,
      "loss": 1.103,
      "step": 232
    },
    {
      "epoch": 1.9914529914529915,
      "grad_norm": 0.3368523120880127,
      "learning_rate": 0.00010411446179700943,
      "loss": 1.0023,
      "step": 233
    },
    {
      "epoch": 2.0,
      "grad_norm": 0.508499264717102,
      "learning_rate": 0.00010342901396698659,
      "loss": 1.2164,
      "step": 234
    }
  ],
  "logging_steps": 1,
  "max_steps": 468,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 4,
  "save_steps": 117,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 3.099140301835469e+16,
  "train_batch_size": 1,
  "trial_name": null,
  "trial_params": null
}