{
  "best_metric": 0.10562604665756226,
  "best_model_checkpoint": "miner_id_24/checkpoint-200",
  "epoch": 1.6202020202020202,
  "eval_steps": 50,
  "global_step": 200,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.00808080808080808,
      "grad_norm": 7.182047367095947,
      "learning_rate": 3.3333333333333333e-06,
      "loss": 1.0239,
      "step": 1
    },
    {
      "epoch": 0.00808080808080808,
      "eval_loss": 1.828047513961792,
      "eval_runtime": 17.0841,
      "eval_samples_per_second": 12.234,
      "eval_steps_per_second": 6.146,
      "step": 1
    },
    {
      "epoch": 0.01616161616161616,
      "grad_norm": 7.59255313873291,
      "learning_rate": 6.666666666666667e-06,
      "loss": 1.1859,
      "step": 2
    },
    {
      "epoch": 0.024242424242424242,
      "grad_norm": 7.851306915283203,
      "learning_rate": 1e-05,
      "loss": 1.3498,
      "step": 3
    },
    {
      "epoch": 0.03232323232323232,
      "grad_norm": 7.867800235748291,
      "learning_rate": 1.3333333333333333e-05,
      "loss": 1.2602,
      "step": 4
    },
    {
      "epoch": 0.04040404040404041,
      "grad_norm": 7.8995490074157715,
      "learning_rate": 1.6666666666666667e-05,
      "loss": 1.2524,
      "step": 5
    },
    {
      "epoch": 0.048484848484848485,
      "grad_norm": 7.7629547119140625,
      "learning_rate": 2e-05,
      "loss": 1.1252,
      "step": 6
    },
    {
      "epoch": 0.05656565656565657,
      "grad_norm": 5.909687042236328,
      "learning_rate": 2.3333333333333336e-05,
      "loss": 0.8747,
      "step": 7
    },
    {
      "epoch": 0.06464646464646465,
      "grad_norm": 3.4731268882751465,
      "learning_rate": 2.6666666666666667e-05,
      "loss": 0.7672,
      "step": 8
    },
    {
      "epoch": 0.07272727272727272,
      "grad_norm": 1.8046791553497314,
      "learning_rate": 3e-05,
      "loss": 0.6521,
      "step": 9
    },
    {
      "epoch": 0.08080808080808081,
      "grad_norm": 1.0927221775054932,
      "learning_rate": 3.3333333333333335e-05,
      "loss": 0.508,
      "step": 10
    },
    {
      "epoch": 0.08888888888888889,
      "grad_norm": 1.1598454713821411,
      "learning_rate": 3.6666666666666666e-05,
      "loss": 0.5036,
      "step": 11
    },
    {
      "epoch": 0.09696969696969697,
      "grad_norm": 1.2271665334701538,
      "learning_rate": 4e-05,
      "loss": 0.4729,
      "step": 12
    },
    {
      "epoch": 0.10505050505050505,
      "grad_norm": 0.8970910906791687,
      "learning_rate": 4.3333333333333334e-05,
      "loss": 0.4137,
      "step": 13
    },
    {
      "epoch": 0.11313131313131314,
      "grad_norm": 0.9987834692001343,
      "learning_rate": 4.666666666666667e-05,
      "loss": 0.3563,
      "step": 14
    },
    {
      "epoch": 0.12121212121212122,
      "grad_norm": 0.9669414162635803,
      "learning_rate": 5e-05,
      "loss": 0.3481,
      "step": 15
    },
    {
      "epoch": 0.1292929292929293,
      "grad_norm": 0.8950324058532715,
      "learning_rate": 5.333333333333333e-05,
      "loss": 0.3161,
      "step": 16
    },
    {
      "epoch": 0.13737373737373737,
      "grad_norm": 0.7251394391059875,
      "learning_rate": 5.666666666666667e-05,
      "loss": 0.3425,
      "step": 17
    },
    {
      "epoch": 0.14545454545454545,
      "grad_norm": 0.8877692818641663,
      "learning_rate": 6e-05,
      "loss": 0.2995,
      "step": 18
    },
    {
      "epoch": 0.15353535353535352,
      "grad_norm": 0.4847090542316437,
      "learning_rate": 6.333333333333333e-05,
      "loss": 0.2751,
      "step": 19
    },
    {
      "epoch": 0.16161616161616163,
      "grad_norm": 0.7626209259033203,
      "learning_rate": 6.666666666666667e-05,
      "loss": 0.2428,
      "step": 20
    },
    {
      "epoch": 0.1696969696969697,
      "grad_norm": 0.4117037057876587,
      "learning_rate": 7e-05,
      "loss": 0.2282,
      "step": 21
    },
    {
      "epoch": 0.17777777777777778,
      "grad_norm": 0.4014205038547516,
      "learning_rate": 7.333333333333333e-05,
      "loss": 0.2317,
      "step": 22
    },
    {
      "epoch": 0.18585858585858586,
      "grad_norm": 0.36181142926216125,
      "learning_rate": 7.666666666666667e-05,
      "loss": 0.2714,
      "step": 23
    },
    {
      "epoch": 0.19393939393939394,
      "grad_norm": 0.3470182716846466,
      "learning_rate": 8e-05,
      "loss": 0.2396,
      "step": 24
    },
    {
      "epoch": 0.20202020202020202,
      "grad_norm": 0.29914993047714233,
      "learning_rate": 8.333333333333334e-05,
      "loss": 0.2378,
      "step": 25
    },
    {
      "epoch": 0.2101010101010101,
      "grad_norm": 0.3030761778354645,
      "learning_rate": 8.666666666666667e-05,
      "loss": 0.2178,
      "step": 26
    },
    {
      "epoch": 0.21818181818181817,
      "grad_norm": 0.2792094051837921,
      "learning_rate": 9e-05,
      "loss": 0.2075,
      "step": 27
    },
    {
      "epoch": 0.22626262626262628,
      "grad_norm": 0.31287625432014465,
      "learning_rate": 9.333333333333334e-05,
      "loss": 0.2249,
      "step": 28
    },
    {
      "epoch": 0.23434343434343435,
      "grad_norm": 0.23660235106945038,
      "learning_rate": 9.666666666666667e-05,
      "loss": 0.1979,
      "step": 29
    },
    {
      "epoch": 0.24242424242424243,
      "grad_norm": 0.2919103801250458,
      "learning_rate": 0.0001,
      "loss": 0.1342,
      "step": 30
    },
    {
      "epoch": 0.2505050505050505,
      "grad_norm": 0.2377624213695526,
      "learning_rate": 9.999146252290264e-05,
      "loss": 0.1531,
      "step": 31
    },
    {
      "epoch": 0.2585858585858586,
      "grad_norm": 0.264447420835495,
      "learning_rate": 9.996585300715116e-05,
      "loss": 0.1725,
      "step": 32
    },
    {
      "epoch": 0.26666666666666666,
      "grad_norm": 0.25005459785461426,
      "learning_rate": 9.99231801983717e-05,
      "loss": 0.1767,
      "step": 33
    },
    {
      "epoch": 0.27474747474747474,
      "grad_norm": 0.22258904576301575,
      "learning_rate": 9.986345866928941e-05,
      "loss": 0.1913,
      "step": 34
    },
    {
      "epoch": 0.2828282828282828,
      "grad_norm": 0.19586224853992462,
      "learning_rate": 9.978670881475172e-05,
      "loss": 0.1775,
      "step": 35
    },
    {
      "epoch": 0.2909090909090909,
      "grad_norm": 0.1971120685338974,
      "learning_rate": 9.96929568447637e-05,
      "loss": 0.1907,
      "step": 36
    },
    {
      "epoch": 0.298989898989899,
      "grad_norm": 0.20490896701812744,
      "learning_rate": 9.958223477553714e-05,
      "loss": 0.2077,
      "step": 37
    },
    {
      "epoch": 0.30707070707070705,
      "grad_norm": 0.19663837552070618,
      "learning_rate": 9.94545804185573e-05,
      "loss": 0.163,
      "step": 38
    },
    {
      "epoch": 0.3151515151515151,
      "grad_norm": 0.2599647045135498,
      "learning_rate": 9.931003736767013e-05,
      "loss": 0.1937,
      "step": 39
    },
    {
      "epoch": 0.32323232323232326,
      "grad_norm": 0.21243253350257874,
      "learning_rate": 9.91486549841951e-05,
      "loss": 0.1996,
      "step": 40
    },
    {
      "epoch": 0.33131313131313134,
      "grad_norm": 0.2396189123392105,
      "learning_rate": 9.89704883800683e-05,
      "loss": 0.221,
      "step": 41
    },
    {
      "epoch": 0.3393939393939394,
      "grad_norm": 0.20343106985092163,
      "learning_rate": 9.877559839902184e-05,
      "loss": 0.1915,
      "step": 42
    },
    {
      "epoch": 0.3474747474747475,
      "grad_norm": 0.17815084755420685,
      "learning_rate": 9.85640515958057e-05,
      "loss": 0.1528,
      "step": 43
    },
    {
      "epoch": 0.35555555555555557,
      "grad_norm": 0.19311825931072235,
      "learning_rate": 9.833592021345937e-05,
      "loss": 0.1839,
      "step": 44
    },
    {
      "epoch": 0.36363636363636365,
      "grad_norm": 0.17040830850601196,
      "learning_rate": 9.809128215864097e-05,
      "loss": 0.1464,
      "step": 45
    },
    {
      "epoch": 0.3717171717171717,
      "grad_norm": 0.192469522356987,
      "learning_rate": 9.783022097502204e-05,
      "loss": 0.192,
      "step": 46
    },
    {
      "epoch": 0.3797979797979798,
      "grad_norm": 0.1951480507850647,
      "learning_rate": 9.755282581475769e-05,
      "loss": 0.1898,
      "step": 47
    },
    {
      "epoch": 0.3878787878787879,
      "grad_norm": 0.20097962021827698,
      "learning_rate": 9.725919140804099e-05,
      "loss": 0.1636,
      "step": 48
    },
    {
      "epoch": 0.39595959595959596,
      "grad_norm": 0.21127808094024658,
      "learning_rate": 9.694941803075283e-05,
      "loss": 0.1603,
      "step": 49
    },
    {
      "epoch": 0.40404040404040403,
      "grad_norm": 0.1940772980451584,
      "learning_rate": 9.662361147021779e-05,
      "loss": 0.1429,
      "step": 50
    },
    {
      "epoch": 0.40404040404040403,
      "eval_loss": 0.15323185920715332,
      "eval_runtime": 17.37,
      "eval_samples_per_second": 12.032,
      "eval_steps_per_second": 6.045,
      "step": 50
    },
    {
      "epoch": 0.4121212121212121,
      "grad_norm": 0.1996546983718872,
      "learning_rate": 9.628188298907782e-05,
      "loss": 0.1655,
      "step": 51
    },
    {
      "epoch": 0.4202020202020202,
      "grad_norm": 0.22379761934280396,
      "learning_rate": 9.592434928729616e-05,
      "loss": 0.1884,
      "step": 52
    },
    {
      "epoch": 0.42828282828282827,
      "grad_norm": 0.25518515706062317,
      "learning_rate": 9.555113246230442e-05,
      "loss": 0.2154,
      "step": 53
    },
    {
      "epoch": 0.43636363636363634,
      "grad_norm": 0.23562446236610413,
      "learning_rate": 9.516235996730645e-05,
      "loss": 0.1696,
      "step": 54
    },
    {
      "epoch": 0.4444444444444444,
      "grad_norm": 0.2346881479024887,
      "learning_rate": 9.475816456775313e-05,
      "loss": 0.1753,
      "step": 55
    },
    {
      "epoch": 0.45252525252525255,
      "grad_norm": 0.22931183874607086,
      "learning_rate": 9.43386842960031e-05,
      "loss": 0.181,
      "step": 56
    },
    {
      "epoch": 0.46060606060606063,
      "grad_norm": 0.1929466873407364,
      "learning_rate": 9.39040624041849e-05,
      "loss": 0.1239,
      "step": 57
    },
    {
      "epoch": 0.4686868686868687,
      "grad_norm": 0.2485426813364029,
      "learning_rate": 9.345444731527642e-05,
      "loss": 0.1814,
      "step": 58
    },
    {
      "epoch": 0.4767676767676768,
      "grad_norm": 0.2541741728782654,
      "learning_rate": 9.298999257241863e-05,
      "loss": 0.1626,
      "step": 59
    },
    {
      "epoch": 0.48484848484848486,
      "grad_norm": 0.2248503416776657,
      "learning_rate": 9.251085678648072e-05,
      "loss": 0.1249,
      "step": 60
    },
    {
      "epoch": 0.49292929292929294,
      "grad_norm": 0.15903638303279877,
      "learning_rate": 9.201720358189464e-05,
      "loss": 0.1118,
      "step": 61
    },
    {
      "epoch": 0.501010101010101,
      "grad_norm": 0.16511444747447968,
      "learning_rate": 9.150920154077754e-05,
      "loss": 0.1424,
      "step": 62
    },
    {
      "epoch": 0.509090909090909,
      "grad_norm": 0.1778963953256607,
      "learning_rate": 9.098702414536107e-05,
      "loss": 0.1543,
      "step": 63
    },
    {
      "epoch": 0.5171717171717172,
      "grad_norm": 0.20222541689872742,
      "learning_rate": 9.045084971874738e-05,
      "loss": 0.19,
      "step": 64
    },
    {
      "epoch": 0.5252525252525253,
      "grad_norm": 0.15871159732341766,
      "learning_rate": 8.9900861364012e-05,
      "loss": 0.1482,
      "step": 65
    },
    {
      "epoch": 0.5333333333333333,
      "grad_norm": 0.15322594344615936,
      "learning_rate": 8.933724690167417e-05,
      "loss": 0.133,
      "step": 66
    },
    {
      "epoch": 0.5414141414141415,
      "grad_norm": 0.15998438000679016,
      "learning_rate": 8.876019880555649e-05,
      "loss": 0.1577,
      "step": 67
    },
    {
      "epoch": 0.5494949494949495,
      "grad_norm": 0.1458025574684143,
      "learning_rate": 8.816991413705516e-05,
      "loss": 0.1344,
      "step": 68
    },
    {
      "epoch": 0.5575757575757576,
      "grad_norm": 0.15559428930282593,
      "learning_rate": 8.756659447784368e-05,
      "loss": 0.1321,
      "step": 69
    },
    {
      "epoch": 0.5656565656565656,
      "grad_norm": 0.16007199883460999,
      "learning_rate": 8.695044586103296e-05,
      "loss": 0.1405,
      "step": 70
    },
    {
      "epoch": 0.5737373737373738,
      "grad_norm": 0.15814808011054993,
      "learning_rate": 8.632167870081121e-05,
      "loss": 0.1529,
      "step": 71
    },
    {
      "epoch": 0.5818181818181818,
      "grad_norm": 0.17004136741161346,
      "learning_rate": 8.568050772058762e-05,
      "loss": 0.1378,
      "step": 72
    },
    {
      "epoch": 0.5898989898989899,
      "grad_norm": 0.17806674540042877,
      "learning_rate": 8.502715187966455e-05,
      "loss": 0.1524,
      "step": 73
    },
    {
      "epoch": 0.597979797979798,
      "grad_norm": 0.19504055380821228,
      "learning_rate": 8.436183429846313e-05,
      "loss": 0.1957,
      "step": 74
    },
    {
      "epoch": 0.6060606060606061,
      "grad_norm": 0.1560707688331604,
      "learning_rate": 8.368478218232787e-05,
      "loss": 0.1365,
      "step": 75
    },
    {
      "epoch": 0.6141414141414141,
      "grad_norm": 0.17931629717350006,
      "learning_rate": 8.299622674393614e-05,
      "loss": 0.1854,
      "step": 76
    },
    {
      "epoch": 0.6222222222222222,
      "grad_norm": 0.19199472665786743,
      "learning_rate": 8.229640312433937e-05,
      "loss": 0.1469,
      "step": 77
    },
    {
      "epoch": 0.6303030303030303,
      "grad_norm": 0.1709621399641037,
      "learning_rate": 8.158555031266254e-05,
      "loss": 0.1606,
      "step": 78
    },
    {
      "epoch": 0.6383838383838384,
      "grad_norm": 0.2154240608215332,
      "learning_rate": 8.086391106448965e-05,
      "loss": 0.1598,
      "step": 79
    },
    {
      "epoch": 0.6464646464646465,
      "grad_norm": 0.1903470903635025,
      "learning_rate": 8.013173181896283e-05,
      "loss": 0.1363,
      "step": 80
    },
    {
      "epoch": 0.6545454545454545,
      "grad_norm": 0.191470667719841,
      "learning_rate": 7.938926261462366e-05,
      "loss": 0.1435,
      "step": 81
    },
    {
      "epoch": 0.6626262626262627,
      "grad_norm": 0.23396596312522888,
      "learning_rate": 7.863675700402526e-05,
      "loss": 0.1687,
      "step": 82
    },
    {
      "epoch": 0.6707070707070707,
      "grad_norm": 0.20243339240550995,
      "learning_rate": 7.787447196714427e-05,
      "loss": 0.1509,
      "step": 83
    },
    {
      "epoch": 0.6787878787878788,
      "grad_norm": 0.223025381565094,
      "learning_rate": 7.710266782362247e-05,
      "loss": 0.1366,
      "step": 84
    },
    {
      "epoch": 0.6868686868686869,
      "grad_norm": 0.2521728277206421,
      "learning_rate": 7.63216081438678e-05,
      "loss": 0.1559,
      "step": 85
    },
    {
      "epoch": 0.694949494949495,
      "grad_norm": 0.2113855630159378,
      "learning_rate": 7.553155965904535e-05,
      "loss": 0.1465,
      "step": 86
    },
    {
      "epoch": 0.703030303030303,
      "grad_norm": 0.2060379981994629,
      "learning_rate": 7.473279216998895e-05,
      "loss": 0.1162,
      "step": 87
    },
    {
      "epoch": 0.7111111111111111,
      "grad_norm": 0.2276727855205536,
      "learning_rate": 7.392557845506432e-05,
      "loss": 0.1228,
      "step": 88
    },
    {
      "epoch": 0.7191919191919192,
      "grad_norm": 0.27229180932044983,
      "learning_rate": 7.311019417701566e-05,
      "loss": 0.1637,
      "step": 89
    },
    {
      "epoch": 0.7272727272727273,
      "grad_norm": 0.26491472125053406,
      "learning_rate": 7.228691778882693e-05,
      "loss": 0.1376,
      "step": 90
    },
    {
      "epoch": 0.7353535353535353,
      "grad_norm": 0.17493240535259247,
      "learning_rate": 7.145603043863045e-05,
      "loss": 0.1176,
      "step": 91
    },
    {
      "epoch": 0.7434343434343434,
      "grad_norm": 0.17210565507411957,
      "learning_rate": 7.061781587369519e-05,
      "loss": 0.1463,
      "step": 92
    },
    {
      "epoch": 0.7515151515151515,
      "grad_norm": 0.1521655023097992,
      "learning_rate": 6.977256034352712e-05,
      "loss": 0.1522,
      "step": 93
    },
    {
      "epoch": 0.7595959595959596,
      "grad_norm": 0.15275168418884277,
      "learning_rate": 6.892055250211552e-05,
      "loss": 0.1377,
      "step": 94
    },
    {
      "epoch": 0.7676767676767676,
      "grad_norm": 0.15215955674648285,
      "learning_rate": 6.806208330935766e-05,
      "loss": 0.1283,
      "step": 95
    },
    {
      "epoch": 0.7757575757575758,
      "grad_norm": 0.14489221572875977,
      "learning_rate": 6.719744593169641e-05,
      "loss": 0.1158,
      "step": 96
    },
    {
      "epoch": 0.7838383838383839,
      "grad_norm": 0.19163498282432556,
      "learning_rate": 6.632693564200416e-05,
      "loss": 0.1588,
      "step": 97
    },
    {
      "epoch": 0.7919191919191919,
      "grad_norm": 0.19089291989803314,
      "learning_rate": 6.545084971874738e-05,
      "loss": 0.1673,
      "step": 98
    },
    {
      "epoch": 0.8,
      "grad_norm": 0.14703136682510376,
      "learning_rate": 6.456948734446624e-05,
      "loss": 0.1383,
      "step": 99
    },
    {
      "epoch": 0.8080808080808081,
      "grad_norm": 0.15113089978694916,
      "learning_rate": 6.368314950360415e-05,
      "loss": 0.1134,
      "step": 100
    },
    {
      "epoch": 0.8080808080808081,
      "eval_loss": 0.12535908818244934,
      "eval_runtime": 17.2256,
      "eval_samples_per_second": 12.133,
      "eval_steps_per_second": 6.096,
      "step": 100
    },
    {
      "epoch": 0.8161616161616162,
      "grad_norm": 0.16581574082374573,
      "learning_rate": 6.279213887972179e-05,
      "loss": 0.1527,
      "step": 101
    },
    {
      "epoch": 0.8242424242424242,
      "grad_norm": 0.16338536143302917,
      "learning_rate": 6.189675975213094e-05,
      "loss": 0.1264,
      "step": 102
    },
    {
      "epoch": 0.8323232323232324,
      "grad_norm": 0.1547755002975464,
      "learning_rate": 6.099731789198344e-05,
      "loss": 0.1383,
      "step": 103
    },
    {
      "epoch": 0.8404040404040404,
      "grad_norm": 0.16346782445907593,
      "learning_rate": 6.009412045785051e-05,
      "loss": 0.1301,
      "step": 104
    },
    {
      "epoch": 0.8484848484848485,
      "grad_norm": 0.1595148742198944,
      "learning_rate": 5.918747589082853e-05,
      "loss": 0.1096,
      "step": 105
    },
    {
      "epoch": 0.8565656565656565,
      "grad_norm": 0.17755745351314545,
      "learning_rate": 5.82776938092065e-05,
      "loss": 0.1391,
      "step": 106
    },
    {
      "epoch": 0.8646464646464647,
      "grad_norm": 0.1880967915058136,
      "learning_rate": 5.736508490273188e-05,
      "loss": 0.1461,
      "step": 107
    },
    {
      "epoch": 0.8727272727272727,
      "grad_norm": 0.207597553730011,
      "learning_rate": 5.644996082651017e-05,
      "loss": 0.1356,
      "step": 108
    },
    {
      "epoch": 0.8808080808080808,
      "grad_norm": 0.16595274209976196,
      "learning_rate": 5.553263409457504e-05,
      "loss": 0.1171,
      "step": 109
    },
    {
      "epoch": 0.8888888888888888,
      "grad_norm": 0.18696972727775574,
      "learning_rate": 5.4613417973165106e-05,
      "loss": 0.13,
      "step": 110
    },
    {
      "epoch": 0.896969696969697,
      "grad_norm": 0.1909806877374649,
      "learning_rate": 5.3692626373743706e-05,
      "loss": 0.1282,
      "step": 111
    },
    {
      "epoch": 0.9050505050505051,
      "grad_norm": 0.21812571585178375,
      "learning_rate": 5.27705737457985e-05,
      "loss": 0.1428,
      "step": 112
    },
    {
      "epoch": 0.9131313131313131,
      "grad_norm": 0.22041140496730804,
      "learning_rate": 5.184757496945726e-05,
      "loss": 0.1563,
      "step": 113
    },
    {
      "epoch": 0.9212121212121213,
      "grad_norm": 0.23546423017978668,
      "learning_rate": 5.092394524795649e-05,
      "loss": 0.1468,
      "step": 114
    },
    {
      "epoch": 0.9292929292929293,
      "grad_norm": 0.20770074427127838,
      "learning_rate": 5e-05,
      "loss": 0.1306,
      "step": 115
    },
    {
      "epoch": 0.9373737373737374,
      "grad_norm": 0.19079814851284027,
      "learning_rate": 4.907605475204352e-05,
      "loss": 0.1243,
      "step": 116
    },
    {
      "epoch": 0.9454545454545454,
      "grad_norm": 0.18580639362335205,
      "learning_rate": 4.8152425030542766e-05,
      "loss": 0.092,
      "step": 117
    },
    {
      "epoch": 0.9535353535353536,
      "grad_norm": 0.25704994797706604,
      "learning_rate": 4.72294262542015e-05,
      "loss": 0.1416,
      "step": 118
    },
    {
      "epoch": 0.9616161616161616,
      "grad_norm": 0.21285192668437958,
      "learning_rate": 4.6307373626256306e-05,
      "loss": 0.1155,
      "step": 119
    },
    {
      "epoch": 0.9696969696969697,
      "grad_norm": 0.2817244231700897,
      "learning_rate": 4.5386582026834906e-05,
      "loss": 0.0983,
      "step": 120
    },
    {
      "epoch": 0.9777777777777777,
      "grad_norm": 0.13769255578517914,
      "learning_rate": 4.446736590542497e-05,
      "loss": 0.1115,
      "step": 121
    },
    {
      "epoch": 0.9858585858585859,
      "grad_norm": 0.15998609364032745,
      "learning_rate": 4.3550039173489845e-05,
      "loss": 0.1204,
      "step": 122
    },
    {
      "epoch": 0.9939393939393939,
      "grad_norm": 0.21727117896080017,
      "learning_rate": 4.2634915097268115e-05,
      "loss": 0.1498,
      "step": 123
    },
    {
      "epoch": 1.006060606060606,
      "grad_norm": 0.3903018832206726,
      "learning_rate": 4.1722306190793495e-05,
      "loss": 0.1544,
      "step": 124
    },
    {
      "epoch": 1.0141414141414142,
      "grad_norm": 0.11540907621383667,
      "learning_rate": 4.0812524109171476e-05,
      "loss": 0.0935,
      "step": 125
    },
    {
      "epoch": 1.0222222222222221,
      "grad_norm": 0.14367812871932983,
      "learning_rate": 3.99058795421495e-05,
      "loss": 0.105,
      "step": 126
    },
    {
      "epoch": 1.0303030303030303,
      "grad_norm": 0.14474540948867798,
      "learning_rate": 3.9002682108016585e-05,
      "loss": 0.1237,
      "step": 127
    },
    {
      "epoch": 1.0383838383838384,
      "grad_norm": 0.15209715068340302,
      "learning_rate": 3.8103240247869075e-05,
      "loss": 0.1191,
      "step": 128
    },
    {
      "epoch": 1.0464646464646465,
      "grad_norm": 0.1337515115737915,
      "learning_rate": 3.720786112027822e-05,
      "loss": 0.1016,
      "step": 129
    },
    {
      "epoch": 1.0545454545454545,
      "grad_norm": 0.1540132761001587,
      "learning_rate": 3.631685049639586e-05,
      "loss": 0.1276,
      "step": 130
    },
    {
      "epoch": 1.0626262626262626,
      "grad_norm": 0.14906255900859833,
      "learning_rate": 3.543051265553377e-05,
      "loss": 0.1124,
      "step": 131
    },
    {
      "epoch": 1.0707070707070707,
      "grad_norm": 0.1601407527923584,
      "learning_rate": 3.4549150281252636e-05,
      "loss": 0.1183,
      "step": 132
    },
    {
      "epoch": 1.0787878787878789,
      "grad_norm": 0.15859104692935944,
      "learning_rate": 3.367306435799584e-05,
      "loss": 0.0856,
      "step": 133
    },
    {
      "epoch": 1.0868686868686868,
      "grad_norm": 0.1468411684036255,
      "learning_rate": 3.2802554068303596e-05,
      "loss": 0.1008,
      "step": 134
    },
    {
      "epoch": 1.094949494949495,
      "grad_norm": 0.1662897914648056,
      "learning_rate": 3.1937916690642356e-05,
      "loss": 0.1176,
      "step": 135
    },
    {
      "epoch": 1.103030303030303,
      "grad_norm": 0.1451275497674942,
      "learning_rate": 3.107944749788449e-05,
      "loss": 0.0865,
      "step": 136
    },
    {
      "epoch": 1.1111111111111112,
      "grad_norm": 0.14780522882938385,
      "learning_rate": 3.0227439656472877e-05,
      "loss": 0.0869,
      "step": 137
    },
    {
      "epoch": 1.1191919191919193,
      "grad_norm": 0.1837635636329651,
      "learning_rate": 2.9382184126304834e-05,
      "loss": 0.118,
      "step": 138
    },
    {
      "epoch": 1.1272727272727272,
      "grad_norm": 0.1539749652147293,
      "learning_rate": 2.8543969561369556e-05,
      "loss": 0.1039,
      "step": 139
    },
    {
      "epoch": 1.1353535353535353,
      "grad_norm": 0.17489545047283173,
      "learning_rate": 2.771308221117309e-05,
      "loss": 0.1032,
      "step": 140
    },
    {
      "epoch": 1.1434343434343435,
      "grad_norm": 0.18241524696350098,
      "learning_rate": 2.688980582298435e-05,
      "loss": 0.1115,
      "step": 141
    },
    {
      "epoch": 1.1515151515151516,
      "grad_norm": 0.1702713817358017,
      "learning_rate": 2.607442154493568e-05,
      "loss": 0.0934,
      "step": 142
    },
    {
      "epoch": 1.1595959595959595,
      "grad_norm": 0.17830723524093628,
      "learning_rate": 2.5267207830011068e-05,
      "loss": 0.0862,
      "step": 143
    },
    {
      "epoch": 1.1676767676767676,
      "grad_norm": 0.17552687227725983,
      "learning_rate": 2.446844034095466e-05,
      "loss": 0.0881,
      "step": 144
    },
    {
      "epoch": 1.1757575757575758,
      "grad_norm": 0.1744166612625122,
      "learning_rate": 2.3678391856132204e-05,
      "loss": 0.095,
      "step": 145
    },
    {
      "epoch": 1.183838383838384,
      "grad_norm": 0.18836869299411774,
      "learning_rate": 2.2897332176377528e-05,
      "loss": 0.1105,
      "step": 146
    },
    {
      "epoch": 1.1919191919191918,
      "grad_norm": 0.16465550661087036,
      "learning_rate": 2.2125528032855724e-05,
      "loss": 0.0664,
      "step": 147
    },
    {
      "epoch": 1.2,
      "grad_norm": 0.19188475608825684,
      "learning_rate": 2.136324299597474e-05,
      "loss": 0.0996,
      "step": 148
    },
    {
      "epoch": 1.208080808080808,
      "grad_norm": 0.1971476525068283,
      "learning_rate": 2.061073738537635e-05,
      "loss": 0.0924,
      "step": 149
    },
    {
      "epoch": 1.2161616161616162,
      "grad_norm": 0.1862366497516632,
      "learning_rate": 1.9868268181037185e-05,
      "loss": 0.0757,
      "step": 150
    },
    {
      "epoch": 1.2161616161616162,
      "eval_loss": 0.1097421795129776,
      "eval_runtime": 17.3569,
      "eval_samples_per_second": 12.041,
      "eval_steps_per_second": 6.049,
      "step": 150
    },
    {
      "epoch": 1.2242424242424241,
      "grad_norm": 0.21383655071258545,
      "learning_rate": 1.9136088935510362e-05,
      "loss": 0.0903,
      "step": 151
    },
    {
      "epoch": 1.2323232323232323,
      "grad_norm": 0.2474888265132904,
      "learning_rate": 1.8414449687337464e-05,
      "loss": 0.0863,
      "step": 152
    },
    {
      "epoch": 1.2404040404040404,
      "grad_norm": 0.26316407322883606,
      "learning_rate": 1.7703596875660645e-05,
      "loss": 0.073,
      "step": 153
    },
    {
      "epoch": 1.2484848484848485,
      "grad_norm": 0.1480526328086853,
      "learning_rate": 1.700377325606388e-05,
      "loss": 0.0754,
      "step": 154
    },
    {
      "epoch": 1.2565656565656567,
      "grad_norm": 0.1381223499774933,
      "learning_rate": 1.631521781767214e-05,
      "loss": 0.0833,
      "step": 155
    },
    {
      "epoch": 1.2646464646464646,
      "grad_norm": 0.15428437292575836,
      "learning_rate": 1.5638165701536868e-05,
      "loss": 0.097,
      "step": 156
    },
    {
      "epoch": 1.2727272727272727,
      "grad_norm": 0.16014143824577332,
      "learning_rate": 1.4972848120335453e-05,
      "loss": 0.1094,
      "step": 157
    },
    {
      "epoch": 1.2808080808080808,
      "grad_norm": 0.1464107632637024,
      "learning_rate": 1.4319492279412388e-05,
      "loss": 0.0946,
      "step": 158
    },
    {
      "epoch": 1.2888888888888888,
      "grad_norm": 0.1830904632806778,
      "learning_rate": 1.3678321299188801e-05,
      "loss": 0.1078,
      "step": 159
    },
    {
      "epoch": 1.2969696969696969,
      "grad_norm": 0.14985810220241547,
      "learning_rate": 1.3049554138967051e-05,
      "loss": 0.0754,
      "step": 160
    },
    {
      "epoch": 1.305050505050505,
      "grad_norm": 0.18282559514045715,
      "learning_rate": 1.2433405522156332e-05,
      "loss": 0.1189,
      "step": 161
    },
    {
      "epoch": 1.3131313131313131,
      "grad_norm": 0.17615680396556854,
      "learning_rate": 1.183008586294485e-05,
      "loss": 0.1047,
      "step": 162
    },
    {
      "epoch": 1.3212121212121213,
      "grad_norm": 0.17815805971622467,
      "learning_rate": 1.1239801194443506e-05,
      "loss": 0.0951,
      "step": 163
    },
    {
      "epoch": 1.3292929292929294,
      "grad_norm": 0.1688067764043808,
      "learning_rate": 1.066275309832584e-05,
      "loss": 0.1007,
      "step": 164
    },
    {
      "epoch": 1.3373737373737373,
      "grad_norm": 0.21036405861377716,
      "learning_rate": 1.0099138635988026e-05,
      "loss": 0.1233,
      "step": 165
    },
    {
      "epoch": 1.3454545454545455,
      "grad_norm": 0.16512730717658997,
      "learning_rate": 9.549150281252633e-06,
      "loss": 0.0937,
      "step": 166
    },
    {
      "epoch": 1.3535353535353536,
      "grad_norm": 0.1726326197385788,
      "learning_rate": 9.012975854638949e-06,
      "loss": 0.1027,
      "step": 167
    },
    {
      "epoch": 1.3616161616161615,
      "grad_norm": 0.19503282010555267,
      "learning_rate": 8.490798459222476e-06,
      "loss": 0.0962,
      "step": 168
    },
    {
      "epoch": 1.3696969696969696,
      "grad_norm": 0.18197757005691528,
      "learning_rate": 7.982796418105371e-06,
      "loss": 0.0896,
      "step": 169
    },
    {
      "epoch": 1.3777777777777778,
      "grad_norm": 0.18920281529426575,
      "learning_rate": 7.489143213519301e-06,
      "loss": 0.0985,
      "step": 170
    },
    {
      "epoch": 1.385858585858586,
      "grad_norm": 0.17614464461803436,
      "learning_rate": 7.010007427581378e-06,
      "loss": 0.0984,
      "step": 171
    },
    {
      "epoch": 1.393939393939394,
      "grad_norm": 0.2091018408536911,
      "learning_rate": 6.5455526847235825e-06,
      "loss": 0.108,
      "step": 172
    },
    {
      "epoch": 1.402020202020202,
      "grad_norm": 0.17564651370048523,
      "learning_rate": 6.0959375958151045e-06,
      "loss": 0.0846,
      "step": 173
    },
    {
      "epoch": 1.41010101010101,
      "grad_norm": 0.17826513946056366,
      "learning_rate": 5.6613157039969055e-06,
      "loss": 0.075,
      "step": 174
    },
    {
      "epoch": 1.4181818181818182,
      "grad_norm": 0.17571891844272614,
      "learning_rate": 5.241835432246889e-06,
      "loss": 0.0881,
      "step": 175
    },
    {
      "epoch": 1.4262626262626263,
      "grad_norm": 0.18698225915431976,
      "learning_rate": 4.837640032693558e-06,
      "loss": 0.0989,
      "step": 176
    },
    {
      "epoch": 1.4343434343434343,
      "grad_norm": 0.18535946309566498,
      "learning_rate": 4.448867537695578e-06,
      "loss": 0.0943,
      "step": 177
    },
    {
      "epoch": 1.4424242424242424,
      "grad_norm": 0.20316363871097565,
      "learning_rate": 4.075650712703849e-06,
      "loss": 0.0979,
      "step": 178
    },
    {
      "epoch": 1.4505050505050505,
      "grad_norm": 0.2010277807712555,
      "learning_rate": 3.71811701092219e-06,
      "loss": 0.0757,
      "step": 179
    },
    {
      "epoch": 1.4585858585858587,
      "grad_norm": 0.211753711104393,
      "learning_rate": 3.376388529782215e-06,
      "loss": 0.0959,
      "step": 180
    },
    {
      "epoch": 1.4666666666666668,
      "grad_norm": 0.18551602959632874,
      "learning_rate": 3.0505819692471792e-06,
      "loss": 0.0807,
      "step": 181
    },
    {
      "epoch": 1.4747474747474747,
      "grad_norm": 0.20515871047973633,
      "learning_rate": 2.7408085919590264e-06,
      "loss": 0.0706,
      "step": 182
    },
    {
      "epoch": 1.4828282828282828,
      "grad_norm": 0.2536952495574951,
      "learning_rate": 2.4471741852423237e-06,
      "loss": 0.0726,
      "step": 183
    },
    {
      "epoch": 1.490909090909091,
      "grad_norm": 0.13934241235256195,
      "learning_rate": 2.1697790249779636e-06,
      "loss": 0.0939,
      "step": 184
    },
    {
      "epoch": 1.4989898989898989,
      "grad_norm": 0.12157568335533142,
      "learning_rate": 1.908717841359048e-06,
      "loss": 0.0867,
      "step": 185
    },
    {
      "epoch": 1.507070707070707,
      "grad_norm": 0.16390369832515717,
      "learning_rate": 1.6640797865406288e-06,
      "loss": 0.1155,
      "step": 186
    },
    {
      "epoch": 1.5151515151515151,
      "grad_norm": 0.13862980902194977,
      "learning_rate": 1.4359484041943038e-06,
      "loss": 0.0839,
      "step": 187
    },
    {
      "epoch": 1.5232323232323233,
      "grad_norm": 0.1422128528356552,
      "learning_rate": 1.2244016009781701e-06,
      "loss": 0.0933,
      "step": 188
    },
    {
      "epoch": 1.5313131313131314,
      "grad_norm": 0.14362359046936035,
      "learning_rate": 1.0295116199317057e-06,
      "loss": 0.0839,
      "step": 189
    },
    {
      "epoch": 1.5393939393939395,
      "grad_norm": 0.1787264198064804,
      "learning_rate": 8.513450158049108e-07,
      "loss": 0.1168,
      "step": 190
    },
    {
      "epoch": 1.5474747474747474,
      "grad_norm": 0.15760783851146698,
      "learning_rate": 6.899626323298713e-07,
      "loss": 0.0831,
      "step": 191
    },
    {
      "epoch": 1.5555555555555556,
      "grad_norm": 0.1490466147661209,
      "learning_rate": 5.454195814427021e-07,
      "loss": 0.0852,
      "step": 192
    },
    {
      "epoch": 1.5636363636363635,
      "grad_norm": 0.16363099217414856,
      "learning_rate": 4.177652244628627e-07,
      "loss": 0.0964,
      "step": 193
    },
    {
      "epoch": 1.5717171717171716,
      "grad_norm": 0.17629890143871307,
      "learning_rate": 3.0704315523631953e-07,
      "loss": 0.0764,
      "step": 194
    },
    {
      "epoch": 1.5797979797979798,
      "grad_norm": 0.14521439373493195,
      "learning_rate": 2.1329118524827662e-07,
      "loss": 0.0802,
      "step": 195
    },
    {
      "epoch": 1.587878787878788,
      "grad_norm": 0.16949088871479034,
      "learning_rate": 1.3654133071059893e-07,
      "loss": 0.1004,
      "step": 196
    },
    {
      "epoch": 1.595959595959596,
      "grad_norm": 0.172135129570961,
      "learning_rate": 7.681980162830282e-08,
      "loss": 0.0983,
      "step": 197
    },
    {
      "epoch": 1.6040404040404042,
      "grad_norm": 0.16809795796871185,
      "learning_rate": 3.4146992848854695e-08,
      "loss": 0.0816,
      "step": 198
    },
    {
      "epoch": 1.612121212121212,
      "grad_norm": 0.18946799635887146,
      "learning_rate": 8.537477097364522e-09,
      "loss": 0.1041,
      "step": 199
    },
    {
      "epoch": 1.6202020202020202,
      "grad_norm": 0.1782253533601761,
      "learning_rate": 0.0,
      "loss": 0.0963,
      "step": 200
    },
    {
      "epoch": 1.6202020202020202,
      "eval_loss": 0.10562604665756226,
      "eval_runtime": 17.4917,
      "eval_samples_per_second": 11.949,
      "eval_steps_per_second": 6.003,
      "step": 200
    }
  ],
  "logging_steps": 1,
  "max_steps": 200,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 2,
  "save_steps": 50,
  "stateful_callbacks": {
    "EarlyStoppingCallback": {
      "args": {
        "early_stopping_patience": 5,
        "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": 2.74873033162752e+17,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}