{
  "best_metric": 0.8949966430664062,
  "best_model_checkpoint": "miner_id_24/checkpoint-200",
  "epoch": 0.6756756756756757,
  "eval_steps": 50,
  "global_step": 200,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0033783783783783786,
      "grad_norm": 3.744501829147339,
      "learning_rate": 5e-06,
      "loss": 1.4948,
      "step": 1
    },
    {
      "epoch": 0.0033783783783783786,
      "eval_loss": 2.366645336151123,
      "eval_runtime": 45.2682,
      "eval_samples_per_second": 11.023,
      "eval_steps_per_second": 5.523,
      "step": 1
    },
    {
      "epoch": 0.006756756756756757,
      "grad_norm": 4.236947059631348,
      "learning_rate": 1e-05,
      "loss": 1.6839,
      "step": 2
    },
    {
      "epoch": 0.010135135135135136,
      "grad_norm": 4.039941787719727,
      "learning_rate": 1.5e-05,
      "loss": 1.5778,
      "step": 3
    },
    {
      "epoch": 0.013513513513513514,
      "grad_norm": 3.9487149715423584,
      "learning_rate": 2e-05,
      "loss": 1.5416,
      "step": 4
    },
    {
      "epoch": 0.016891891891891893,
      "grad_norm": 3.413524627685547,
      "learning_rate": 2.5e-05,
      "loss": 1.5397,
      "step": 5
    },
    {
      "epoch": 0.02027027027027027,
      "grad_norm": 2.798722267150879,
      "learning_rate": 3e-05,
      "loss": 1.3799,
      "step": 6
    },
    {
      "epoch": 0.02364864864864865,
      "grad_norm": 2.1076104640960693,
      "learning_rate": 3.5e-05,
      "loss": 1.2598,
      "step": 7
    },
    {
      "epoch": 0.02702702702702703,
      "grad_norm": 1.5505497455596924,
      "learning_rate": 4e-05,
      "loss": 1.28,
      "step": 8
    },
    {
      "epoch": 0.030405405405405407,
      "grad_norm": 1.3251761198043823,
      "learning_rate": 4.5e-05,
      "loss": 1.1612,
      "step": 9
    },
    {
      "epoch": 0.033783783783783786,
      "grad_norm": 1.4571374654769897,
      "learning_rate": 5e-05,
      "loss": 1.1367,
      "step": 10
    },
    {
      "epoch": 0.037162162162162164,
      "grad_norm": 1.326081395149231,
      "learning_rate": 5.500000000000001e-05,
      "loss": 1.0907,
      "step": 11
    },
    {
      "epoch": 0.04054054054054054,
      "grad_norm": 1.5680633783340454,
      "learning_rate": 6e-05,
      "loss": 1.0995,
      "step": 12
    },
    {
      "epoch": 0.04391891891891892,
      "grad_norm": 1.3775849342346191,
      "learning_rate": 6.500000000000001e-05,
      "loss": 1.0456,
      "step": 13
    },
    {
      "epoch": 0.0472972972972973,
      "grad_norm": 1.1460962295532227,
      "learning_rate": 7e-05,
      "loss": 1.0217,
      "step": 14
    },
    {
      "epoch": 0.05067567567567568,
      "grad_norm": 1.0644354820251465,
      "learning_rate": 7.500000000000001e-05,
      "loss": 1.0813,
      "step": 15
    },
    {
      "epoch": 0.05405405405405406,
      "grad_norm": 1.1402639150619507,
      "learning_rate": 8e-05,
      "loss": 1.0695,
      "step": 16
    },
    {
      "epoch": 0.057432432432432436,
      "grad_norm": 1.1812214851379395,
      "learning_rate": 8.5e-05,
      "loss": 1.0509,
      "step": 17
    },
    {
      "epoch": 0.060810810810810814,
      "grad_norm": 1.1104124784469604,
      "learning_rate": 9e-05,
      "loss": 1.1742,
      "step": 18
    },
    {
      "epoch": 0.06418918918918919,
      "grad_norm": 1.1839892864227295,
      "learning_rate": 9.5e-05,
      "loss": 1.2315,
      "step": 19
    },
    {
      "epoch": 0.06756756756756757,
      "grad_norm": 1.0097914934158325,
      "learning_rate": 0.0001,
      "loss": 0.9635,
      "step": 20
    },
    {
      "epoch": 0.07094594594594594,
      "grad_norm": 1.007724404335022,
      "learning_rate": 9.999238475781957e-05,
      "loss": 1.0362,
      "step": 21
    },
    {
      "epoch": 0.07432432432432433,
      "grad_norm": 1.0983017683029175,
      "learning_rate": 9.99695413509548e-05,
      "loss": 0.994,
      "step": 22
    },
    {
      "epoch": 0.0777027027027027,
      "grad_norm": 1.2512664794921875,
      "learning_rate": 9.99314767377287e-05,
      "loss": 1.1185,
      "step": 23
    },
    {
      "epoch": 0.08108108108108109,
      "grad_norm": 1.1611964702606201,
      "learning_rate": 9.987820251299122e-05,
      "loss": 1.1192,
      "step": 24
    },
    {
      "epoch": 0.08445945945945946,
      "grad_norm": 1.2372798919677734,
      "learning_rate": 9.980973490458728e-05,
      "loss": 1.0742,
      "step": 25
    },
    {
      "epoch": 0.08783783783783784,
      "grad_norm": 1.7029861211776733,
      "learning_rate": 9.972609476841367e-05,
      "loss": 1.1158,
      "step": 26
    },
    {
      "epoch": 0.09121621621621621,
      "grad_norm": 1.5453083515167236,
      "learning_rate": 9.962730758206611e-05,
      "loss": 1.0227,
      "step": 27
    },
    {
      "epoch": 0.0945945945945946,
      "grad_norm": 1.3983490467071533,
      "learning_rate": 9.951340343707852e-05,
      "loss": 1.1769,
      "step": 28
    },
    {
      "epoch": 0.09797297297297297,
      "grad_norm": 1.379359483718872,
      "learning_rate": 9.938441702975689e-05,
      "loss": 1.0721,
      "step": 29
    },
    {
      "epoch": 0.10135135135135136,
      "grad_norm": 1.6246654987335205,
      "learning_rate": 9.924038765061042e-05,
      "loss": 1.2902,
      "step": 30
    },
    {
      "epoch": 0.10472972972972973,
      "grad_norm": 1.4009028673171997,
      "learning_rate": 9.908135917238321e-05,
      "loss": 1.1992,
      "step": 31
    },
    {
      "epoch": 0.10810810810810811,
      "grad_norm": 1.4103702306747437,
      "learning_rate": 9.890738003669029e-05,
      "loss": 1.2155,
      "step": 32
    },
    {
      "epoch": 0.11148648648648649,
      "grad_norm": 1.9476141929626465,
      "learning_rate": 9.871850323926177e-05,
      "loss": 1.1234,
      "step": 33
    },
    {
      "epoch": 0.11486486486486487,
      "grad_norm": 1.5474672317504883,
      "learning_rate": 9.851478631379982e-05,
      "loss": 1.2764,
      "step": 34
    },
    {
      "epoch": 0.11824324324324324,
      "grad_norm": 1.7086366415023804,
      "learning_rate": 9.829629131445342e-05,
      "loss": 1.1167,
      "step": 35
    },
    {
      "epoch": 0.12162162162162163,
      "grad_norm": 1.9206814765930176,
      "learning_rate": 9.806308479691595e-05,
      "loss": 1.1906,
      "step": 36
    },
    {
      "epoch": 0.125,
      "grad_norm": 1.7579545974731445,
      "learning_rate": 9.781523779815179e-05,
      "loss": 1.1311,
      "step": 37
    },
    {
      "epoch": 0.12837837837837837,
      "grad_norm": 1.751266598701477,
      "learning_rate": 9.755282581475769e-05,
      "loss": 1.0927,
      "step": 38
    },
    {
      "epoch": 0.13175675675675674,
      "grad_norm": 2.1313395500183105,
      "learning_rate": 9.727592877996585e-05,
      "loss": 1.2224,
      "step": 39
    },
    {
      "epoch": 0.13513513513513514,
      "grad_norm": 1.9591072797775269,
      "learning_rate": 9.698463103929542e-05,
      "loss": 1.1981,
      "step": 40
    },
    {
      "epoch": 0.13851351351351351,
      "grad_norm": 1.7385376691818237,
      "learning_rate": 9.667902132486009e-05,
      "loss": 1.0732,
      "step": 41
    },
    {
      "epoch": 0.14189189189189189,
      "grad_norm": 1.8894368410110474,
      "learning_rate": 9.635919272833938e-05,
      "loss": 1.0556,
      "step": 42
    },
    {
      "epoch": 0.14527027027027026,
      "grad_norm": 1.993202805519104,
      "learning_rate": 9.602524267262203e-05,
      "loss": 1.0809,
      "step": 43
    },
    {
      "epoch": 0.14864864864864866,
      "grad_norm": 2.6242268085479736,
      "learning_rate": 9.567727288213005e-05,
      "loss": 1.2124,
      "step": 44
    },
    {
      "epoch": 0.15202702702702703,
      "grad_norm": 2.2804272174835205,
      "learning_rate": 9.53153893518325e-05,
      "loss": 0.8962,
      "step": 45
    },
    {
      "epoch": 0.1554054054054054,
      "grad_norm": 2.2582497596740723,
      "learning_rate": 9.493970231495835e-05,
      "loss": 0.9141,
      "step": 46
    },
    {
      "epoch": 0.15878378378378377,
      "grad_norm": 2.63997745513916,
      "learning_rate": 9.45503262094184e-05,
      "loss": 0.9049,
      "step": 47
    },
    {
      "epoch": 0.16216216216216217,
      "grad_norm": 2.960585117340088,
      "learning_rate": 9.414737964294636e-05,
      "loss": 0.9491,
      "step": 48
    },
    {
      "epoch": 0.16554054054054054,
      "grad_norm": 3.667393922805786,
      "learning_rate": 9.373098535696979e-05,
      "loss": 1.166,
      "step": 49
    },
    {
      "epoch": 0.16891891891891891,
      "grad_norm": 3.813143253326416,
      "learning_rate": 9.330127018922194e-05,
      "loss": 0.9567,
      "step": 50
    },
    {
      "epoch": 0.16891891891891891,
      "eval_loss": 1.1352548599243164,
      "eval_runtime": 46.0456,
      "eval_samples_per_second": 10.837,
      "eval_steps_per_second": 5.429,
      "step": 50
    },
    {
      "epoch": 0.17229729729729729,
      "grad_norm": 1.6696974039077759,
      "learning_rate": 9.285836503510562e-05,
      "loss": 0.9759,
      "step": 51
    },
    {
      "epoch": 0.17567567567567569,
      "grad_norm": 1.5998507738113403,
      "learning_rate": 9.24024048078213e-05,
      "loss": 1.0373,
      "step": 52
    },
    {
      "epoch": 0.17905405405405406,
      "grad_norm": 0.9118627309799194,
      "learning_rate": 9.193352839727121e-05,
      "loss": 0.921,
      "step": 53
    },
    {
      "epoch": 0.18243243243243243,
      "grad_norm": 0.7134009599685669,
      "learning_rate": 9.145187862775209e-05,
      "loss": 0.7223,
      "step": 54
    },
    {
      "epoch": 0.1858108108108108,
      "grad_norm": 0.9054052233695984,
      "learning_rate": 9.09576022144496e-05,
      "loss": 0.9962,
      "step": 55
    },
    {
      "epoch": 0.1891891891891892,
      "grad_norm": 0.8865036964416504,
      "learning_rate": 9.045084971874738e-05,
      "loss": 0.9926,
      "step": 56
    },
    {
      "epoch": 0.19256756756756757,
      "grad_norm": 1.1260945796966553,
      "learning_rate": 8.993177550236464e-05,
      "loss": 0.9893,
      "step": 57
    },
    {
      "epoch": 0.19594594594594594,
      "grad_norm": 0.9342796802520752,
      "learning_rate": 8.940053768033609e-05,
      "loss": 0.8856,
      "step": 58
    },
    {
      "epoch": 0.19932432432432431,
      "grad_norm": 0.8070133924484253,
      "learning_rate": 8.885729807284856e-05,
      "loss": 0.8627,
      "step": 59
    },
    {
      "epoch": 0.20270270270270271,
      "grad_norm": 0.7861827611923218,
      "learning_rate": 8.83022221559489e-05,
      "loss": 0.9044,
      "step": 60
    },
    {
      "epoch": 0.20608108108108109,
      "grad_norm": 0.8653984665870667,
      "learning_rate": 8.773547901113862e-05,
      "loss": 0.9646,
      "step": 61
    },
    {
      "epoch": 0.20945945945945946,
      "grad_norm": 0.7122342586517334,
      "learning_rate": 8.715724127386972e-05,
      "loss": 0.851,
      "step": 62
    },
    {
      "epoch": 0.21283783783783783,
      "grad_norm": 0.7715885043144226,
      "learning_rate": 8.656768508095853e-05,
      "loss": 0.9403,
      "step": 63
    },
    {
      "epoch": 0.21621621621621623,
      "grad_norm": 0.9805060625076294,
      "learning_rate": 8.596699001693255e-05,
      "loss": 0.9221,
      "step": 64
    },
    {
      "epoch": 0.2195945945945946,
      "grad_norm": 0.8389323353767395,
      "learning_rate": 8.535533905932738e-05,
      "loss": 0.8891,
      "step": 65
    },
    {
      "epoch": 0.22297297297297297,
      "grad_norm": 0.8703292608261108,
      "learning_rate": 8.473291852294987e-05,
      "loss": 0.8504,
      "step": 66
    },
    {
      "epoch": 0.22635135135135134,
      "grad_norm": 1.067031979560852,
      "learning_rate": 8.409991800312493e-05,
      "loss": 0.9348,
      "step": 67
    },
    {
      "epoch": 0.22972972972972974,
      "grad_norm": 0.8430051803588867,
      "learning_rate": 8.345653031794292e-05,
      "loss": 0.9183,
      "step": 68
    },
    {
      "epoch": 0.23310810810810811,
      "grad_norm": 0.892875611782074,
      "learning_rate": 8.280295144952536e-05,
      "loss": 0.9269,
      "step": 69
    },
    {
      "epoch": 0.23648648648648649,
      "grad_norm": 0.9631092548370361,
      "learning_rate": 8.213938048432697e-05,
      "loss": 0.9245,
      "step": 70
    },
    {
      "epoch": 0.23986486486486486,
      "grad_norm": 1.025659203529358,
      "learning_rate": 8.146601955249188e-05,
      "loss": 1.0386,
      "step": 71
    },
    {
      "epoch": 0.24324324324324326,
      "grad_norm": 0.929277777671814,
      "learning_rate": 8.07830737662829e-05,
      "loss": 0.9812,
      "step": 72
    },
    {
      "epoch": 0.24662162162162163,
      "grad_norm": 0.9579569101333618,
      "learning_rate": 8.009075115760243e-05,
      "loss": 0.9292,
      "step": 73
    },
    {
      "epoch": 0.25,
      "grad_norm": 1.3032071590423584,
      "learning_rate": 7.938926261462366e-05,
      "loss": 0.9401,
      "step": 74
    },
    {
      "epoch": 0.2533783783783784,
      "grad_norm": 1.2386891841888428,
      "learning_rate": 7.86788218175523e-05,
      "loss": 1.1717,
      "step": 75
    },
    {
      "epoch": 0.25675675675675674,
      "grad_norm": 1.0636472702026367,
      "learning_rate": 7.795964517353735e-05,
      "loss": 0.8654,
      "step": 76
    },
    {
      "epoch": 0.26013513513513514,
      "grad_norm": 1.0517919063568115,
      "learning_rate": 7.723195175075136e-05,
      "loss": 0.9766,
      "step": 77
    },
    {
      "epoch": 0.2635135135135135,
      "grad_norm": 1.3352515697479248,
      "learning_rate": 7.649596321166024e-05,
      "loss": 1.0346,
      "step": 78
    },
    {
      "epoch": 0.2668918918918919,
      "grad_norm": 1.2450820207595825,
      "learning_rate": 7.575190374550272e-05,
      "loss": 1.0913,
      "step": 79
    },
    {
      "epoch": 0.2702702702702703,
      "grad_norm": 1.1723278760910034,
      "learning_rate": 7.500000000000001e-05,
      "loss": 1.1201,
      "step": 80
    },
    {
      "epoch": 0.27364864864864863,
      "grad_norm": 1.3349324464797974,
      "learning_rate": 7.424048101231686e-05,
      "loss": 1.1728,
      "step": 81
    },
    {
      "epoch": 0.27702702702702703,
      "grad_norm": 1.497829556465149,
      "learning_rate": 7.347357813929454e-05,
      "loss": 1.237,
      "step": 82
    },
    {
      "epoch": 0.28040540540540543,
      "grad_norm": 1.295419692993164,
      "learning_rate": 7.269952498697734e-05,
      "loss": 1.0679,
      "step": 83
    },
    {
      "epoch": 0.28378378378378377,
      "grad_norm": 1.3698307275772095,
      "learning_rate": 7.191855733945387e-05,
      "loss": 1.0085,
      "step": 84
    },
    {
      "epoch": 0.28716216216216217,
      "grad_norm": 1.447948932647705,
      "learning_rate": 7.113091308703498e-05,
      "loss": 1.0445,
      "step": 85
    },
    {
      "epoch": 0.2905405405405405,
      "grad_norm": 1.2832486629486084,
      "learning_rate": 7.033683215379002e-05,
      "loss": 0.9843,
      "step": 86
    },
    {
      "epoch": 0.2939189189189189,
      "grad_norm": 1.3851889371871948,
      "learning_rate": 6.953655642446368e-05,
      "loss": 0.9874,
      "step": 87
    },
    {
      "epoch": 0.2972972972972973,
      "grad_norm": 1.500678300857544,
      "learning_rate": 6.873032967079561e-05,
      "loss": 1.0615,
      "step": 88
    },
    {
      "epoch": 0.30067567567567566,
      "grad_norm": 1.6516691446304321,
      "learning_rate": 6.7918397477265e-05,
      "loss": 1.121,
      "step": 89
    },
    {
      "epoch": 0.30405405405405406,
      "grad_norm": 1.90969979763031,
      "learning_rate": 6.710100716628344e-05,
      "loss": 1.1665,
      "step": 90
    },
    {
      "epoch": 0.30743243243243246,
      "grad_norm": 1.6873974800109863,
      "learning_rate": 6.627840772285784e-05,
      "loss": 0.8706,
      "step": 91
    },
    {
      "epoch": 0.3108108108108108,
      "grad_norm": 1.6982275247573853,
      "learning_rate": 6.545084971874738e-05,
      "loss": 1.0512,
      "step": 92
    },
    {
      "epoch": 0.3141891891891892,
      "grad_norm": 1.8306528329849243,
      "learning_rate": 6.461858523613684e-05,
      "loss": 0.8927,
      "step": 93
    },
    {
      "epoch": 0.31756756756756754,
      "grad_norm": 1.7691174745559692,
      "learning_rate": 6.378186779084995e-05,
      "loss": 0.9589,
      "step": 94
    },
    {
      "epoch": 0.32094594594594594,
      "grad_norm": 1.7679611444473267,
      "learning_rate": 6.294095225512603e-05,
      "loss": 0.9641,
      "step": 95
    },
    {
      "epoch": 0.32432432432432434,
      "grad_norm": 2.6409804821014404,
      "learning_rate": 6.209609477998338e-05,
      "loss": 0.8601,
      "step": 96
    },
    {
      "epoch": 0.3277027027027027,
      "grad_norm": 2.0474467277526855,
      "learning_rate": 6.124755271719325e-05,
      "loss": 0.7398,
      "step": 97
    },
    {
      "epoch": 0.3310810810810811,
      "grad_norm": 2.3656604290008545,
      "learning_rate": 6.0395584540887963e-05,
      "loss": 0.7571,
      "step": 98
    },
    {
      "epoch": 0.3344594594594595,
      "grad_norm": 2.5002782344818115,
      "learning_rate": 5.9540449768827246e-05,
      "loss": 0.8314,
      "step": 99
    },
    {
      "epoch": 0.33783783783783783,
      "grad_norm": 3.700169086456299,
      "learning_rate": 5.868240888334653e-05,
      "loss": 1.0022,
      "step": 100
    },
    {
      "epoch": 0.33783783783783783,
      "eval_loss": 0.9985164999961853,
      "eval_runtime": 46.0756,
      "eval_samples_per_second": 10.83,
      "eval_steps_per_second": 5.426,
      "step": 100
    },
    {
      "epoch": 0.34121621621621623,
      "grad_norm": 1.0377089977264404,
      "learning_rate": 5.782172325201155e-05,
      "loss": 0.8462,
      "step": 101
    },
    {
      "epoch": 0.34459459459459457,
      "grad_norm": 0.9041997194290161,
      "learning_rate": 5.695865504800327e-05,
      "loss": 0.832,
      "step": 102
    },
    {
      "epoch": 0.34797297297297297,
      "grad_norm": 0.7395469546318054,
      "learning_rate": 5.6093467170257374e-05,
      "loss": 0.772,
      "step": 103
    },
    {
      "epoch": 0.35135135135135137,
      "grad_norm": 0.7768586277961731,
      "learning_rate": 5.522642316338268e-05,
      "loss": 0.8626,
      "step": 104
    },
    {
      "epoch": 0.3547297297297297,
      "grad_norm": 0.7545685768127441,
      "learning_rate": 5.435778713738292e-05,
      "loss": 0.8628,
      "step": 105
    },
    {
      "epoch": 0.3581081081081081,
      "grad_norm": 0.7042768001556396,
      "learning_rate": 5.348782368720626e-05,
      "loss": 0.8853,
      "step": 106
    },
    {
      "epoch": 0.3614864864864865,
      "grad_norm": 0.7246413826942444,
      "learning_rate": 5.26167978121472e-05,
      "loss": 0.849,
      "step": 107
    },
    {
      "epoch": 0.36486486486486486,
      "grad_norm": 3.7040340900421143,
      "learning_rate": 5.174497483512506e-05,
      "loss": 0.8975,
      "step": 108
    },
    {
      "epoch": 0.36824324324324326,
      "grad_norm": 0.8027128577232361,
      "learning_rate": 5.0872620321864185e-05,
      "loss": 0.8713,
      "step": 109
    },
    {
      "epoch": 0.3716216216216216,
      "grad_norm": 0.9056793451309204,
      "learning_rate": 5e-05,
      "loss": 0.927,
      "step": 110
    },
    {
      "epoch": 0.375,
      "grad_norm": 0.9082245230674744,
      "learning_rate": 4.912737967813583e-05,
      "loss": 0.9092,
      "step": 111
    },
    {
      "epoch": 0.3783783783783784,
      "grad_norm": 0.7679075598716736,
      "learning_rate": 4.825502516487497e-05,
      "loss": 0.8778,
      "step": 112
    },
    {
      "epoch": 0.38175675675675674,
      "grad_norm": 1.0147924423217773,
      "learning_rate": 4.738320218785281e-05,
      "loss": 0.9393,
      "step": 113
    },
    {
      "epoch": 0.38513513513513514,
      "grad_norm": 1.2093980312347412,
      "learning_rate": 4.6512176312793736e-05,
      "loss": 0.977,
      "step": 114
    },
    {
      "epoch": 0.3885135135135135,
      "grad_norm": 1.0028644800186157,
      "learning_rate": 4.564221286261709e-05,
      "loss": 0.996,
      "step": 115
    },
    {
      "epoch": 0.3918918918918919,
      "grad_norm": 0.8029702305793762,
      "learning_rate": 4.477357683661734e-05,
      "loss": 0.8958,
      "step": 116
    },
    {
      "epoch": 0.3952702702702703,
      "grad_norm": 0.8842869997024536,
      "learning_rate": 4.390653282974264e-05,
      "loss": 0.9729,
      "step": 117
    },
    {
      "epoch": 0.39864864864864863,
      "grad_norm": 1.141502022743225,
      "learning_rate": 4.3041344951996746e-05,
      "loss": 1.0818,
      "step": 118
    },
    {
      "epoch": 0.40202702702702703,
      "grad_norm": 0.8530824780464172,
      "learning_rate": 4.2178276747988446e-05,
      "loss": 0.9098,
      "step": 119
    },
    {
      "epoch": 0.40540540540540543,
      "grad_norm": 0.8405656814575195,
      "learning_rate": 4.131759111665349e-05,
      "loss": 0.9642,
      "step": 120
    },
    {
      "epoch": 0.40878378378378377,
      "grad_norm": 0.877079963684082,
      "learning_rate": 4.045955023117276e-05,
      "loss": 0.9022,
      "step": 121
    },
    {
      "epoch": 0.41216216216216217,
      "grad_norm": 0.9758852124214172,
      "learning_rate": 3.960441545911204e-05,
      "loss": 1.0644,
      "step": 122
    },
    {
      "epoch": 0.4155405405405405,
      "grad_norm": 0.955123782157898,
      "learning_rate": 3.875244728280676e-05,
      "loss": 1.0663,
      "step": 123
    },
    {
      "epoch": 0.4189189189189189,
      "grad_norm": 1.1201103925704956,
      "learning_rate": 3.790390522001662e-05,
      "loss": 0.9873,
      "step": 124
    },
    {
      "epoch": 0.4222972972972973,
      "grad_norm": 0.9429944753646851,
      "learning_rate": 3.705904774487396e-05,
      "loss": 0.9156,
      "step": 125
    },
    {
      "epoch": 0.42567567567567566,
      "grad_norm": 1.001926064491272,
      "learning_rate": 3.6218132209150045e-05,
      "loss": 0.9075,
      "step": 126
    },
    {
      "epoch": 0.42905405405405406,
      "grad_norm": 0.9807978272438049,
      "learning_rate": 3.5381414763863166e-05,
      "loss": 0.9553,
      "step": 127
    },
    {
      "epoch": 0.43243243243243246,
      "grad_norm": 1.2464756965637207,
      "learning_rate": 3.4549150281252636e-05,
      "loss": 1.1636,
      "step": 128
    },
    {
      "epoch": 0.4358108108108108,
      "grad_norm": 1.0817270278930664,
      "learning_rate": 3.372159227714218e-05,
      "loss": 0.9701,
      "step": 129
    },
    {
      "epoch": 0.4391891891891892,
      "grad_norm": 1.2720826864242554,
      "learning_rate": 3.289899283371657e-05,
      "loss": 1.0393,
      "step": 130
    },
    {
      "epoch": 0.44256756756756754,
      "grad_norm": 1.2283689975738525,
      "learning_rate": 3.2081602522734986e-05,
      "loss": 0.9868,
      "step": 131
    },
    {
      "epoch": 0.44594594594594594,
      "grad_norm": 1.1629105806350708,
      "learning_rate": 3.12696703292044e-05,
      "loss": 0.9667,
      "step": 132
    },
    {
      "epoch": 0.44932432432432434,
      "grad_norm": 1.2187542915344238,
      "learning_rate": 3.046344357553632e-05,
      "loss": 0.9859,
      "step": 133
    },
    {
      "epoch": 0.4527027027027027,
      "grad_norm": 1.2236980199813843,
      "learning_rate": 2.9663167846209998e-05,
      "loss": 1.0059,
      "step": 134
    },
    {
      "epoch": 0.4560810810810811,
      "grad_norm": 1.3778389692306519,
      "learning_rate": 2.886908691296504e-05,
      "loss": 1.0905,
      "step": 135
    },
    {
      "epoch": 0.4594594594594595,
      "grad_norm": 1.3661246299743652,
      "learning_rate": 2.8081442660546125e-05,
      "loss": 1.0668,
      "step": 136
    },
    {
      "epoch": 0.46283783783783783,
      "grad_norm": 1.7316638231277466,
      "learning_rate": 2.7300475013022663e-05,
      "loss": 1.1291,
      "step": 137
    },
    {
      "epoch": 0.46621621621621623,
      "grad_norm": 1.511131763458252,
      "learning_rate": 2.6526421860705473e-05,
      "loss": 1.0699,
      "step": 138
    },
    {
      "epoch": 0.46959459459459457,
      "grad_norm": 1.598746418952942,
      "learning_rate": 2.575951898768315e-05,
      "loss": 1.1566,
      "step": 139
    },
    {
      "epoch": 0.47297297297297297,
      "grad_norm": 1.7504431009292603,
      "learning_rate": 2.500000000000001e-05,
      "loss": 1.0676,
      "step": 140
    },
    {
      "epoch": 0.47635135135135137,
      "grad_norm": 1.5073328018188477,
      "learning_rate": 2.4248096254497288e-05,
      "loss": 0.9039,
      "step": 141
    },
    {
      "epoch": 0.4797297297297297,
      "grad_norm": 1.7294800281524658,
      "learning_rate": 2.350403678833976e-05,
      "loss": 0.9129,
      "step": 142
    },
    {
      "epoch": 0.4831081081081081,
      "grad_norm": 1.962022304534912,
      "learning_rate": 2.2768048249248648e-05,
      "loss": 0.9903,
      "step": 143
    },
    {
      "epoch": 0.4864864864864865,
      "grad_norm": 1.758473515510559,
      "learning_rate": 2.2040354826462668e-05,
      "loss": 0.9652,
      "step": 144
    },
    {
      "epoch": 0.48986486486486486,
      "grad_norm": 1.8504688739776611,
      "learning_rate": 2.132117818244771e-05,
      "loss": 0.9808,
      "step": 145
    },
    {
      "epoch": 0.49324324324324326,
      "grad_norm": 1.923115611076355,
      "learning_rate": 2.061073738537635e-05,
      "loss": 0.9479,
      "step": 146
    },
    {
      "epoch": 0.4966216216216216,
      "grad_norm": 2.064173936843872,
      "learning_rate": 1.9909248842397584e-05,
      "loss": 0.808,
      "step": 147
    },
    {
      "epoch": 0.5,
      "grad_norm": 2.720120906829834,
      "learning_rate": 1.9216926233717085e-05,
      "loss": 0.8824,
      "step": 148
    },
    {
      "epoch": 0.5033783783783784,
      "grad_norm": 3.0430357456207275,
      "learning_rate": 1.8533980447508137e-05,
      "loss": 1.0976,
      "step": 149
    },
    {
      "epoch": 0.5067567567567568,
      "grad_norm": 4.151440620422363,
      "learning_rate": 1.7860619515673033e-05,
      "loss": 0.9557,
      "step": 150
    },
    {
      "epoch": 0.5067567567567568,
      "eval_loss": 0.9131522178649902,
      "eval_runtime": 46.0341,
      "eval_samples_per_second": 10.84,
      "eval_steps_per_second": 5.431,
      "step": 150
    },
    {
      "epoch": 0.5101351351351351,
      "grad_norm": 0.6414157748222351,
      "learning_rate": 1.7197048550474643e-05,
      "loss": 0.7276,
      "step": 151
    },
    {
      "epoch": 0.5135135135135135,
      "grad_norm": 0.8255054354667664,
      "learning_rate": 1.6543469682057106e-05,
      "loss": 0.9528,
      "step": 152
    },
    {
      "epoch": 0.5168918918918919,
      "grad_norm": 0.6534758806228638,
      "learning_rate": 1.5900081996875083e-05,
      "loss": 0.7602,
      "step": 153
    },
    {
      "epoch": 0.5202702702702703,
      "grad_norm": 0.6519982814788818,
      "learning_rate": 1.526708147705013e-05,
      "loss": 0.8021,
      "step": 154
    },
    {
      "epoch": 0.5236486486486487,
      "grad_norm": 0.6611419916152954,
      "learning_rate": 1.4644660940672627e-05,
      "loss": 0.8233,
      "step": 155
    },
    {
      "epoch": 0.527027027027027,
      "grad_norm": 0.6791012287139893,
      "learning_rate": 1.4033009983067452e-05,
      "loss": 0.8613,
      "step": 156
    },
    {
      "epoch": 0.5304054054054054,
      "grad_norm": 0.686221182346344,
      "learning_rate": 1.3432314919041478e-05,
      "loss": 0.8536,
      "step": 157
    },
    {
      "epoch": 0.5337837837837838,
      "grad_norm": 0.8385734558105469,
      "learning_rate": 1.2842758726130283e-05,
      "loss": 0.8431,
      "step": 158
    },
    {
      "epoch": 0.5371621621621622,
      "grad_norm": 0.7144952416419983,
      "learning_rate": 1.22645209888614e-05,
      "loss": 0.8897,
      "step": 159
    },
    {
      "epoch": 0.5405405405405406,
      "grad_norm": 0.7294721007347107,
      "learning_rate": 1.1697777844051105e-05,
      "loss": 0.8941,
      "step": 160
    },
    {
      "epoch": 0.543918918918919,
      "grad_norm": 0.8123903870582581,
      "learning_rate": 1.1142701927151456e-05,
      "loss": 0.8263,
      "step": 161
    },
    {
      "epoch": 0.5472972972972973,
      "grad_norm": 0.8005977272987366,
      "learning_rate": 1.0599462319663905e-05,
      "loss": 0.9233,
      "step": 162
    },
    {
      "epoch": 0.5506756756756757,
      "grad_norm": 0.7909176349639893,
      "learning_rate": 1.006822449763537e-05,
      "loss": 0.8405,
      "step": 163
    },
    {
      "epoch": 0.5540540540540541,
      "grad_norm": 0.805918276309967,
      "learning_rate": 9.549150281252633e-06,
      "loss": 0.8933,
      "step": 164
    },
    {
      "epoch": 0.5574324324324325,
      "grad_norm": 0.8915834426879883,
      "learning_rate": 9.042397785550405e-06,
      "loss": 0.8968,
      "step": 165
    },
    {
      "epoch": 0.5608108108108109,
      "grad_norm": 0.7567748427391052,
      "learning_rate": 8.548121372247918e-06,
      "loss": 0.8833,
      "step": 166
    },
    {
      "epoch": 0.5641891891891891,
      "grad_norm": 0.8642418384552002,
      "learning_rate": 8.066471602728803e-06,
      "loss": 0.9339,
      "step": 167
    },
    {
      "epoch": 0.5675675675675675,
      "grad_norm": 0.830711305141449,
      "learning_rate": 7.597595192178702e-06,
      "loss": 0.9309,
      "step": 168
    },
    {
      "epoch": 0.5709459459459459,
      "grad_norm": 0.7903837561607361,
      "learning_rate": 7.1416349648943894e-06,
      "loss": 0.836,
      "step": 169
    },
    {
      "epoch": 0.5743243243243243,
      "grad_norm": 0.859325647354126,
      "learning_rate": 6.698729810778065e-06,
      "loss": 0.9374,
      "step": 170
    },
    {
      "epoch": 0.5777027027027027,
      "grad_norm": 0.9100458025932312,
      "learning_rate": 6.269014643030213e-06,
      "loss": 0.9975,
      "step": 171
    },
    {
      "epoch": 0.581081081081081,
      "grad_norm": 0.8569390773773193,
      "learning_rate": 5.852620357053651e-06,
      "loss": 0.8616,
      "step": 172
    },
    {
      "epoch": 0.5844594594594594,
      "grad_norm": 1.0101906061172485,
      "learning_rate": 5.449673790581611e-06,
      "loss": 1.0039,
      "step": 173
    },
    {
      "epoch": 0.5878378378378378,
      "grad_norm": 0.9508276581764221,
      "learning_rate": 5.060297685041659e-06,
      "loss": 0.9166,
      "step": 174
    },
    {
      "epoch": 0.5912162162162162,
      "grad_norm": 0.9959359169006348,
      "learning_rate": 4.684610648167503e-06,
      "loss": 0.9819,
      "step": 175
    },
    {
      "epoch": 0.5945945945945946,
      "grad_norm": 1.2211215496063232,
      "learning_rate": 4.322727117869951e-06,
      "loss": 1.1135,
      "step": 176
    },
    {
      "epoch": 0.597972972972973,
      "grad_norm": 1.0754196643829346,
      "learning_rate": 3.974757327377981e-06,
      "loss": 0.9525,
      "step": 177
    },
    {
      "epoch": 0.6013513513513513,
      "grad_norm": 1.080495834350586,
      "learning_rate": 3.6408072716606346e-06,
      "loss": 1.0761,
      "step": 178
    },
    {
      "epoch": 0.6047297297297297,
      "grad_norm": 1.0381531715393066,
      "learning_rate": 3.3209786751399187e-06,
      "loss": 0.977,
      "step": 179
    },
    {
      "epoch": 0.6081081081081081,
      "grad_norm": 1.1167261600494385,
      "learning_rate": 3.0153689607045845e-06,
      "loss": 0.9827,
      "step": 180
    },
    {
      "epoch": 0.6114864864864865,
      "grad_norm": 1.2164942026138306,
      "learning_rate": 2.724071220034158e-06,
      "loss": 0.9943,
      "step": 181
    },
    {
      "epoch": 0.6148648648648649,
      "grad_norm": 1.2718250751495361,
      "learning_rate": 2.4471741852423237e-06,
      "loss": 1.0472,
      "step": 182
    },
    {
      "epoch": 0.6182432432432432,
      "grad_norm": 1.3220036029815674,
      "learning_rate": 2.1847622018482283e-06,
      "loss": 1.0063,
      "step": 183
    },
    {
      "epoch": 0.6216216216216216,
      "grad_norm": 1.2563388347625732,
      "learning_rate": 1.9369152030840556e-06,
      "loss": 1.0378,
      "step": 184
    },
    {
      "epoch": 0.625,
      "grad_norm": 1.3848549127578735,
      "learning_rate": 1.70370868554659e-06,
      "loss": 1.0336,
      "step": 185
    },
    {
      "epoch": 0.6283783783783784,
      "grad_norm": 1.3267947435379028,
      "learning_rate": 1.4852136862001764e-06,
      "loss": 0.9134,
      "step": 186
    },
    {
      "epoch": 0.6317567567567568,
      "grad_norm": 1.3245331048965454,
      "learning_rate": 1.2814967607382432e-06,
      "loss": 0.9814,
      "step": 187
    },
    {
      "epoch": 0.6351351351351351,
      "grad_norm": 1.4889888763427734,
      "learning_rate": 1.0926199633097157e-06,
      "loss": 1.0287,
      "step": 188
    },
    {
      "epoch": 0.6385135135135135,
      "grad_norm": 1.4858009815216064,
      "learning_rate": 9.186408276168013e-07,
      "loss": 1.0367,
      "step": 189
    },
    {
      "epoch": 0.6418918918918919,
      "grad_norm": 1.4568663835525513,
      "learning_rate": 7.596123493895991e-07,
      "loss": 0.9433,
      "step": 190
    },
    {
      "epoch": 0.6452702702702703,
      "grad_norm": 1.4762650728225708,
      "learning_rate": 6.15582970243117e-07,
      "loss": 0.9156,
      "step": 191
    },
    {
      "epoch": 0.6486486486486487,
      "grad_norm": 1.6088173389434814,
      "learning_rate": 4.865965629214819e-07,
      "loss": 0.9533,
      "step": 192
    },
    {
      "epoch": 0.652027027027027,
      "grad_norm": 1.798325777053833,
      "learning_rate": 3.7269241793390085e-07,
      "loss": 0.8845,
      "step": 193
    },
    {
      "epoch": 0.6554054054054054,
      "grad_norm": 2.0476438999176025,
      "learning_rate": 2.7390523158633554e-07,
      "loss": 1.0159,
      "step": 194
    },
    {
      "epoch": 0.6587837837837838,
      "grad_norm": 2.168297290802002,
      "learning_rate": 1.9026509541272275e-07,
      "loss": 0.9675,
      "step": 195
    },
    {
      "epoch": 0.6621621621621622,
      "grad_norm": 1.7735626697540283,
      "learning_rate": 1.2179748700879012e-07,
      "loss": 0.8036,
      "step": 196
    },
    {
      "epoch": 0.6655405405405406,
      "grad_norm": 1.9138069152832031,
      "learning_rate": 6.852326227130834e-08,
      "loss": 0.9033,
      "step": 197
    },
    {
      "epoch": 0.668918918918919,
      "grad_norm": 2.1288278102874756,
      "learning_rate": 3.04586490452119e-08,
      "loss": 0.7308,
      "step": 198
    },
    {
      "epoch": 0.6722972972972973,
      "grad_norm": 2.4816396236419678,
      "learning_rate": 7.615242180436522e-09,
      "loss": 0.9089,
      "step": 199
    },
    {
      "epoch": 0.6756756756756757,
      "grad_norm": 3.8006317615509033,
      "learning_rate": 0.0,
      "loss": 0.9367,
      "step": 200
    },
    {
      "epoch": 0.6756756756756757,
      "eval_loss": 0.8949966430664062,
      "eval_runtime": 46.0594,
      "eval_samples_per_second": 10.834,
      "eval_steps_per_second": 5.428,
      "step": 200
    }
  ],
  "logging_steps": 1,
  "max_steps": 200,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 50,
  "stateful_callbacks": {
    "EarlyStoppingCallback": {
      "args": {
        "early_stopping_patience": 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": 3.1421973496489574e+17,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}