{
  "best_metric": 0.006479598581790924,
  "best_model_checkpoint": "miner_id_24/checkpoint-200",
  "epoch": 0.029914370115544254,
  "eval_steps": 50,
  "global_step": 200,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.00014957185057772127,
      "grad_norm": 0.5308204889297485,
      "learning_rate": 3.3333333333333333e-06,
      "loss": 0.414,
      "step": 1
    },
    {
      "epoch": 0.00014957185057772127,
      "eval_loss": 0.3887909948825836,
      "eval_runtime": 595.5498,
      "eval_samples_per_second": 18.909,
      "eval_steps_per_second": 9.455,
      "step": 1
    },
    {
      "epoch": 0.00029914370115544255,
      "grad_norm": 0.5224118232727051,
      "learning_rate": 6.666666666666667e-06,
      "loss": 0.3502,
      "step": 2
    },
    {
      "epoch": 0.0004487155517331638,
      "grad_norm": 0.6008749604225159,
      "learning_rate": 1e-05,
      "loss": 0.3602,
      "step": 3
    },
    {
      "epoch": 0.0005982874023108851,
      "grad_norm": 0.5614318251609802,
      "learning_rate": 1.3333333333333333e-05,
      "loss": 0.3514,
      "step": 4
    },
    {
      "epoch": 0.0007478592528886063,
      "grad_norm": 0.5933046936988831,
      "learning_rate": 1.6666666666666667e-05,
      "loss": 0.3802,
      "step": 5
    },
    {
      "epoch": 0.0008974311034663276,
      "grad_norm": 0.569101095199585,
      "learning_rate": 2e-05,
      "loss": 0.3513,
      "step": 6
    },
    {
      "epoch": 0.0010470029540440488,
      "grad_norm": 0.5784810185432434,
      "learning_rate": 2.3333333333333336e-05,
      "loss": 0.3594,
      "step": 7
    },
    {
      "epoch": 0.0011965748046217702,
      "grad_norm": 0.6198071241378784,
      "learning_rate": 2.6666666666666667e-05,
      "loss": 0.3388,
      "step": 8
    },
    {
      "epoch": 0.0013461466551994916,
      "grad_norm": 0.5930509567260742,
      "learning_rate": 3e-05,
      "loss": 0.283,
      "step": 9
    },
    {
      "epoch": 0.0014957185057772127,
      "grad_norm": 0.6314247846603394,
      "learning_rate": 3.3333333333333335e-05,
      "loss": 0.2701,
      "step": 10
    },
    {
      "epoch": 0.001645290356354934,
      "grad_norm": 0.7138134241104126,
      "learning_rate": 3.6666666666666666e-05,
      "loss": 0.2652,
      "step": 11
    },
    {
      "epoch": 0.0017948622069326552,
      "grad_norm": 0.7084327340126038,
      "learning_rate": 4e-05,
      "loss": 0.1943,
      "step": 12
    },
    {
      "epoch": 0.0019444340575103765,
      "grad_norm": 0.6410165429115295,
      "learning_rate": 4.3333333333333334e-05,
      "loss": 0.1557,
      "step": 13
    },
    {
      "epoch": 0.0020940059080880977,
      "grad_norm": 0.5466600656509399,
      "learning_rate": 4.666666666666667e-05,
      "loss": 0.1457,
      "step": 14
    },
    {
      "epoch": 0.002243577758665819,
      "grad_norm": 0.5802261829376221,
      "learning_rate": 5e-05,
      "loss": 0.1235,
      "step": 15
    },
    {
      "epoch": 0.0023931496092435404,
      "grad_norm": 0.5169052481651306,
      "learning_rate": 5.333333333333333e-05,
      "loss": 0.1122,
      "step": 16
    },
    {
      "epoch": 0.0025427214598212618,
      "grad_norm": 0.4952888786792755,
      "learning_rate": 5.666666666666667e-05,
      "loss": 0.0689,
      "step": 17
    },
    {
      "epoch": 0.002692293310398983,
      "grad_norm": 0.545960009098053,
      "learning_rate": 6e-05,
      "loss": 0.0748,
      "step": 18
    },
    {
      "epoch": 0.002841865160976704,
      "grad_norm": 0.6058912873268127,
      "learning_rate": 6.333333333333333e-05,
      "loss": 0.0691,
      "step": 19
    },
    {
      "epoch": 0.0029914370115544254,
      "grad_norm": 0.7081538438796997,
      "learning_rate": 6.666666666666667e-05,
      "loss": 0.0525,
      "step": 20
    },
    {
      "epoch": 0.0031410088621321467,
      "grad_norm": 0.640294075012207,
      "learning_rate": 7e-05,
      "loss": 0.0424,
      "step": 21
    },
    {
      "epoch": 0.003290580712709868,
      "grad_norm": 0.47781896591186523,
      "learning_rate": 7.333333333333333e-05,
      "loss": 0.0403,
      "step": 22
    },
    {
      "epoch": 0.0034401525632875895,
      "grad_norm": 0.48246967792510986,
      "learning_rate": 7.666666666666667e-05,
      "loss": 0.048,
      "step": 23
    },
    {
      "epoch": 0.0035897244138653104,
      "grad_norm": 0.7142300009727478,
      "learning_rate": 8e-05,
      "loss": 0.0697,
      "step": 24
    },
    {
      "epoch": 0.0037392962644430317,
      "grad_norm": 0.46457439661026,
      "learning_rate": 8.333333333333334e-05,
      "loss": 0.0242,
      "step": 25
    },
    {
      "epoch": 0.003888868115020753,
      "grad_norm": 0.757646918296814,
      "learning_rate": 8.666666666666667e-05,
      "loss": 0.0318,
      "step": 26
    },
    {
      "epoch": 0.004038439965598474,
      "grad_norm": 0.457316517829895,
      "learning_rate": 9e-05,
      "loss": 0.0387,
      "step": 27
    },
    {
      "epoch": 0.004188011816176195,
      "grad_norm": 0.47733765840530396,
      "learning_rate": 9.333333333333334e-05,
      "loss": 0.0439,
      "step": 28
    },
    {
      "epoch": 0.004337583666753917,
      "grad_norm": 0.36536335945129395,
      "learning_rate": 9.666666666666667e-05,
      "loss": 0.0255,
      "step": 29
    },
    {
      "epoch": 0.004487155517331638,
      "grad_norm": 0.36387503147125244,
      "learning_rate": 0.0001,
      "loss": 0.018,
      "step": 30
    },
    {
      "epoch": 0.0046367273679093594,
      "grad_norm": 0.28365346789360046,
      "learning_rate": 9.999146252290264e-05,
      "loss": 0.0161,
      "step": 31
    },
    {
      "epoch": 0.004786299218487081,
      "grad_norm": 0.43167436122894287,
      "learning_rate": 9.996585300715116e-05,
      "loss": 0.032,
      "step": 32
    },
    {
      "epoch": 0.004935871069064802,
      "grad_norm": 0.40744444727897644,
      "learning_rate": 9.99231801983717e-05,
      "loss": 0.0313,
      "step": 33
    },
    {
      "epoch": 0.0050854429196425235,
      "grad_norm": 0.20926286280155182,
      "learning_rate": 9.986345866928941e-05,
      "loss": 0.0167,
      "step": 34
    },
    {
      "epoch": 0.005235014770220245,
      "grad_norm": 0.28823548555374146,
      "learning_rate": 9.978670881475172e-05,
      "loss": 0.0177,
      "step": 35
    },
    {
      "epoch": 0.005384586620797966,
      "grad_norm": 0.3377716541290283,
      "learning_rate": 9.96929568447637e-05,
      "loss": 0.0149,
      "step": 36
    },
    {
      "epoch": 0.005534158471375687,
      "grad_norm": 0.2543269991874695,
      "learning_rate": 9.958223477553714e-05,
      "loss": 0.0191,
      "step": 37
    },
    {
      "epoch": 0.005683730321953408,
      "grad_norm": 0.36039161682128906,
      "learning_rate": 9.94545804185573e-05,
      "loss": 0.0196,
      "step": 38
    },
    {
      "epoch": 0.005833302172531129,
      "grad_norm": 0.11637739837169647,
      "learning_rate": 9.931003736767013e-05,
      "loss": 0.0085,
      "step": 39
    },
    {
      "epoch": 0.005982874023108851,
      "grad_norm": 0.2684103846549988,
      "learning_rate": 9.91486549841951e-05,
      "loss": 0.0052,
      "step": 40
    },
    {
      "epoch": 0.006132445873686572,
      "grad_norm": 0.6549965739250183,
      "learning_rate": 9.89704883800683e-05,
      "loss": 0.0144,
      "step": 41
    },
    {
      "epoch": 0.0062820177242642935,
      "grad_norm": 0.1656181663274765,
      "learning_rate": 9.877559839902184e-05,
      "loss": 0.031,
      "step": 42
    },
    {
      "epoch": 0.006431589574842015,
      "grad_norm": 0.16201820969581604,
      "learning_rate": 9.85640515958057e-05,
      "loss": 0.0068,
      "step": 43
    },
    {
      "epoch": 0.006581161425419736,
      "grad_norm": 0.258662611246109,
      "learning_rate": 9.833592021345937e-05,
      "loss": 0.0162,
      "step": 44
    },
    {
      "epoch": 0.0067307332759974576,
      "grad_norm": 0.21120058000087738,
      "learning_rate": 9.809128215864097e-05,
      "loss": 0.0133,
      "step": 45
    },
    {
      "epoch": 0.006880305126575179,
      "grad_norm": 0.13957321643829346,
      "learning_rate": 9.783022097502204e-05,
      "loss": 0.0074,
      "step": 46
    },
    {
      "epoch": 0.007029876977152899,
      "grad_norm": 0.26101356744766235,
      "learning_rate": 9.755282581475769e-05,
      "loss": 0.0056,
      "step": 47
    },
    {
      "epoch": 0.007179448827730621,
      "grad_norm": 0.44964393973350525,
      "learning_rate": 9.725919140804099e-05,
      "loss": 0.0064,
      "step": 48
    },
    {
      "epoch": 0.007329020678308342,
      "grad_norm": 0.41840535402297974,
      "learning_rate": 9.694941803075283e-05,
      "loss": 0.0163,
      "step": 49
    },
    {
      "epoch": 0.0074785925288860635,
      "grad_norm": 0.2638077437877655,
      "learning_rate": 9.662361147021779e-05,
      "loss": 0.0067,
      "step": 50
    },
    {
      "epoch": 0.0074785925288860635,
      "eval_loss": 0.01790788397192955,
      "eval_runtime": 595.9715,
      "eval_samples_per_second": 18.895,
      "eval_steps_per_second": 9.448,
      "step": 50
    },
    {
      "epoch": 0.007628164379463785,
      "grad_norm": 0.42071086168289185,
      "learning_rate": 9.628188298907782e-05,
      "loss": 0.081,
      "step": 51
    },
    {
      "epoch": 0.007777736230041506,
      "grad_norm": 0.22494149208068848,
      "learning_rate": 9.592434928729616e-05,
      "loss": 0.035,
      "step": 52
    },
    {
      "epoch": 0.007927308080619228,
      "grad_norm": 0.2883397340774536,
      "learning_rate": 9.555113246230442e-05,
      "loss": 0.0375,
      "step": 53
    },
    {
      "epoch": 0.008076879931196948,
      "grad_norm": 0.1822877824306488,
      "learning_rate": 9.516235996730645e-05,
      "loss": 0.0182,
      "step": 54
    },
    {
      "epoch": 0.00822645178177467,
      "grad_norm": 0.4282134473323822,
      "learning_rate": 9.475816456775313e-05,
      "loss": 0.0239,
      "step": 55
    },
    {
      "epoch": 0.00837602363235239,
      "grad_norm": 0.20260415971279144,
      "learning_rate": 9.43386842960031e-05,
      "loss": 0.0165,
      "step": 56
    },
    {
      "epoch": 0.008525595482930113,
      "grad_norm": 0.1890808641910553,
      "learning_rate": 9.39040624041849e-05,
      "loss": 0.0203,
      "step": 57
    },
    {
      "epoch": 0.008675167333507833,
      "grad_norm": 0.25549623370170593,
      "learning_rate": 9.345444731527642e-05,
      "loss": 0.0141,
      "step": 58
    },
    {
      "epoch": 0.008824739184085556,
      "grad_norm": 0.41939401626586914,
      "learning_rate": 9.298999257241863e-05,
      "loss": 0.0138,
      "step": 59
    },
    {
      "epoch": 0.008974311034663276,
      "grad_norm": 0.1745770424604416,
      "learning_rate": 9.251085678648072e-05,
      "loss": 0.014,
      "step": 60
    },
    {
      "epoch": 0.009123882885240998,
      "grad_norm": 0.15685011446475983,
      "learning_rate": 9.201720358189464e-05,
      "loss": 0.0146,
      "step": 61
    },
    {
      "epoch": 0.009273454735818719,
      "grad_norm": 0.14342175424098969,
      "learning_rate": 9.150920154077754e-05,
      "loss": 0.017,
      "step": 62
    },
    {
      "epoch": 0.00942302658639644,
      "grad_norm": 0.3844296336174011,
      "learning_rate": 9.098702414536107e-05,
      "loss": 0.0175,
      "step": 63
    },
    {
      "epoch": 0.009572598436974162,
      "grad_norm": 0.2558370530605316,
      "learning_rate": 9.045084971874738e-05,
      "loss": 0.0139,
      "step": 64
    },
    {
      "epoch": 0.009722170287551882,
      "grad_norm": 0.16741563379764557,
      "learning_rate": 8.9900861364012e-05,
      "loss": 0.0143,
      "step": 65
    },
    {
      "epoch": 0.009871742138129604,
      "grad_norm": 0.12443399429321289,
      "learning_rate": 8.933724690167417e-05,
      "loss": 0.0113,
      "step": 66
    },
    {
      "epoch": 0.010021313988707325,
      "grad_norm": 0.17893032729625702,
      "learning_rate": 8.876019880555649e-05,
      "loss": 0.0171,
      "step": 67
    },
    {
      "epoch": 0.010170885839285047,
      "grad_norm": 0.1262056529521942,
      "learning_rate": 8.816991413705516e-05,
      "loss": 0.0096,
      "step": 68
    },
    {
      "epoch": 0.010320457689862768,
      "grad_norm": 0.13662129640579224,
      "learning_rate": 8.756659447784368e-05,
      "loss": 0.0166,
      "step": 69
    },
    {
      "epoch": 0.01047002954044049,
      "grad_norm": 0.16609983146190643,
      "learning_rate": 8.695044586103296e-05,
      "loss": 0.0064,
      "step": 70
    },
    {
      "epoch": 0.01061960139101821,
      "grad_norm": 0.15221911668777466,
      "learning_rate": 8.632167870081121e-05,
      "loss": 0.0272,
      "step": 71
    },
    {
      "epoch": 0.010769173241595932,
      "grad_norm": 0.123332679271698,
      "learning_rate": 8.568050772058762e-05,
      "loss": 0.0105,
      "step": 72
    },
    {
      "epoch": 0.010918745092173653,
      "grad_norm": 0.24244451522827148,
      "learning_rate": 8.502715187966455e-05,
      "loss": 0.0063,
      "step": 73
    },
    {
      "epoch": 0.011068316942751373,
      "grad_norm": 0.13439439237117767,
      "learning_rate": 8.436183429846313e-05,
      "loss": 0.0049,
      "step": 74
    },
    {
      "epoch": 0.011217888793329096,
      "grad_norm": 0.11952490359544754,
      "learning_rate": 8.368478218232787e-05,
      "loss": 0.0079,
      "step": 75
    },
    {
      "epoch": 0.011367460643906816,
      "grad_norm": 0.13263778388500214,
      "learning_rate": 8.299622674393614e-05,
      "loss": 0.0202,
      "step": 76
    },
    {
      "epoch": 0.011517032494484538,
      "grad_norm": 0.11364516615867615,
      "learning_rate": 8.229640312433937e-05,
      "loss": 0.0066,
      "step": 77
    },
    {
      "epoch": 0.011666604345062259,
      "grad_norm": 0.1084505096077919,
      "learning_rate": 8.158555031266254e-05,
      "loss": 0.0063,
      "step": 78
    },
    {
      "epoch": 0.011816176195639981,
      "grad_norm": 0.14993980526924133,
      "learning_rate": 8.086391106448965e-05,
      "loss": 0.0267,
      "step": 79
    },
    {
      "epoch": 0.011965748046217702,
      "grad_norm": 0.08508989214897156,
      "learning_rate": 8.013173181896283e-05,
      "loss": 0.0037,
      "step": 80
    },
    {
      "epoch": 0.012115319896795424,
      "grad_norm": 0.11003761738538742,
      "learning_rate": 7.938926261462366e-05,
      "loss": 0.007,
      "step": 81
    },
    {
      "epoch": 0.012264891747373144,
      "grad_norm": 0.11577136069536209,
      "learning_rate": 7.863675700402526e-05,
      "loss": 0.0056,
      "step": 82
    },
    {
      "epoch": 0.012414463597950866,
      "grad_norm": 0.09900005906820297,
      "learning_rate": 7.787447196714427e-05,
      "loss": 0.0057,
      "step": 83
    },
    {
      "epoch": 0.012564035448528587,
      "grad_norm": 0.08717920631170273,
      "learning_rate": 7.710266782362247e-05,
      "loss": 0.0063,
      "step": 84
    },
    {
      "epoch": 0.012713607299106307,
      "grad_norm": 0.0876622125506401,
      "learning_rate": 7.63216081438678e-05,
      "loss": 0.003,
      "step": 85
    },
    {
      "epoch": 0.01286317914968403,
      "grad_norm": 0.7834295034408569,
      "learning_rate": 7.553155965904535e-05,
      "loss": 0.0092,
      "step": 86
    },
    {
      "epoch": 0.01301275100026175,
      "grad_norm": 0.17819520831108093,
      "learning_rate": 7.473279216998895e-05,
      "loss": 0.0046,
      "step": 87
    },
    {
      "epoch": 0.013162322850839472,
      "grad_norm": 0.18168805539608002,
      "learning_rate": 7.392557845506432e-05,
      "loss": 0.0053,
      "step": 88
    },
    {
      "epoch": 0.013311894701417193,
      "grad_norm": 0.038727566599845886,
      "learning_rate": 7.311019417701566e-05,
      "loss": 0.0014,
      "step": 89
    },
    {
      "epoch": 0.013461466551994915,
      "grad_norm": 0.1316843181848526,
      "learning_rate": 7.228691778882693e-05,
      "loss": 0.0063,
      "step": 90
    },
    {
      "epoch": 0.013611038402572636,
      "grad_norm": 0.14724566042423248,
      "learning_rate": 7.145603043863045e-05,
      "loss": 0.0063,
      "step": 91
    },
    {
      "epoch": 0.013760610253150358,
      "grad_norm": 0.05180006101727486,
      "learning_rate": 7.061781587369519e-05,
      "loss": 0.0028,
      "step": 92
    },
    {
      "epoch": 0.013910182103728078,
      "grad_norm": 0.14283880591392517,
      "learning_rate": 6.977256034352712e-05,
      "loss": 0.0134,
      "step": 93
    },
    {
      "epoch": 0.014059753954305799,
      "grad_norm": 1.355584979057312,
      "learning_rate": 6.892055250211552e-05,
      "loss": 0.0058,
      "step": 94
    },
    {
      "epoch": 0.014209325804883521,
      "grad_norm": 0.06890705972909927,
      "learning_rate": 6.806208330935766e-05,
      "loss": 0.0017,
      "step": 95
    },
    {
      "epoch": 0.014358897655461242,
      "grad_norm": 0.10976633429527283,
      "learning_rate": 6.719744593169641e-05,
      "loss": 0.0113,
      "step": 96
    },
    {
      "epoch": 0.014508469506038964,
      "grad_norm": 0.09234730899333954,
      "learning_rate": 6.632693564200416e-05,
      "loss": 0.0075,
      "step": 97
    },
    {
      "epoch": 0.014658041356616684,
      "grad_norm": 0.04849664121866226,
      "learning_rate": 6.545084971874738e-05,
      "loss": 0.0012,
      "step": 98
    },
    {
      "epoch": 0.014807613207194406,
      "grad_norm": 0.055540088564157486,
      "learning_rate": 6.456948734446624e-05,
      "loss": 0.0009,
      "step": 99
    },
    {
      "epoch": 0.014957185057772127,
      "grad_norm": 0.1183815598487854,
      "learning_rate": 6.368314950360415e-05,
      "loss": 0.0017,
      "step": 100
    },
    {
      "epoch": 0.014957185057772127,
      "eval_loss": 0.009296631440520287,
      "eval_runtime": 596.5582,
      "eval_samples_per_second": 18.877,
      "eval_steps_per_second": 9.439,
      "step": 100
    },
    {
      "epoch": 0.01510675690834985,
      "grad_norm": 0.38418063521385193,
      "learning_rate": 6.279213887972179e-05,
      "loss": 0.0593,
      "step": 101
    },
    {
      "epoch": 0.01525632875892757,
      "grad_norm": 0.15076230466365814,
      "learning_rate": 6.189675975213094e-05,
      "loss": 0.0158,
      "step": 102
    },
    {
      "epoch": 0.015405900609505292,
      "grad_norm": 0.15164940059185028,
      "learning_rate": 6.099731789198344e-05,
      "loss": 0.0163,
      "step": 103
    },
    {
      "epoch": 0.015555472460083012,
      "grad_norm": 0.22811640799045563,
      "learning_rate": 6.009412045785051e-05,
      "loss": 0.0143,
      "step": 104
    },
    {
      "epoch": 0.015705044310660735,
      "grad_norm": 0.1102544367313385,
      "learning_rate": 5.918747589082853e-05,
      "loss": 0.0048,
      "step": 105
    },
    {
      "epoch": 0.015854616161238455,
      "grad_norm": 0.15529769659042358,
      "learning_rate": 5.82776938092065e-05,
      "loss": 0.0074,
      "step": 106
    },
    {
      "epoch": 0.016004188011816176,
      "grad_norm": 0.18479487299919128,
      "learning_rate": 5.736508490273188e-05,
      "loss": 0.0157,
      "step": 107
    },
    {
      "epoch": 0.016153759862393896,
      "grad_norm": 0.11037200689315796,
      "learning_rate": 5.644996082651017e-05,
      "loss": 0.013,
      "step": 108
    },
    {
      "epoch": 0.01630333171297162,
      "grad_norm": 0.13404931128025055,
      "learning_rate": 5.553263409457504e-05,
      "loss": 0.0137,
      "step": 109
    },
    {
      "epoch": 0.01645290356354934,
      "grad_norm": 0.08097627758979797,
      "learning_rate": 5.4613417973165106e-05,
      "loss": 0.0091,
      "step": 110
    },
    {
      "epoch": 0.01660247541412706,
      "grad_norm": 0.09218428283929825,
      "learning_rate": 5.3692626373743706e-05,
      "loss": 0.0053,
      "step": 111
    },
    {
      "epoch": 0.01675204726470478,
      "grad_norm": 0.12369544059038162,
      "learning_rate": 5.27705737457985e-05,
      "loss": 0.0072,
      "step": 112
    },
    {
      "epoch": 0.016901619115282505,
      "grad_norm": 0.11836303770542145,
      "learning_rate": 5.184757496945726e-05,
      "loss": 0.0041,
      "step": 113
    },
    {
      "epoch": 0.017051190965860226,
      "grad_norm": 0.27226316928863525,
      "learning_rate": 5.092394524795649e-05,
      "loss": 0.013,
      "step": 114
    },
    {
      "epoch": 0.017200762816437946,
      "grad_norm": 0.08969904482364655,
      "learning_rate": 5e-05,
      "loss": 0.0051,
      "step": 115
    },
    {
      "epoch": 0.017350334667015667,
      "grad_norm": 0.056998107582330704,
      "learning_rate": 4.907605475204352e-05,
      "loss": 0.0146,
      "step": 116
    },
    {
      "epoch": 0.017499906517593387,
      "grad_norm": 0.04792310670018196,
      "learning_rate": 4.8152425030542766e-05,
      "loss": 0.0031,
      "step": 117
    },
    {
      "epoch": 0.01764947836817111,
      "grad_norm": 0.07071925699710846,
      "learning_rate": 4.72294262542015e-05,
      "loss": 0.0056,
      "step": 118
    },
    {
      "epoch": 0.017799050218748832,
      "grad_norm": 0.053638752549886703,
      "learning_rate": 4.6307373626256306e-05,
      "loss": 0.0022,
      "step": 119
    },
    {
      "epoch": 0.017948622069326552,
      "grad_norm": 0.06185459718108177,
      "learning_rate": 4.5386582026834906e-05,
      "loss": 0.0047,
      "step": 120
    },
    {
      "epoch": 0.018098193919904273,
      "grad_norm": 0.06008853763341904,
      "learning_rate": 4.446736590542497e-05,
      "loss": 0.004,
      "step": 121
    },
    {
      "epoch": 0.018247765770481997,
      "grad_norm": 0.07498060166835785,
      "learning_rate": 4.3550039173489845e-05,
      "loss": 0.0041,
      "step": 122
    },
    {
      "epoch": 0.018397337621059717,
      "grad_norm": 0.0886349156498909,
      "learning_rate": 4.2634915097268115e-05,
      "loss": 0.008,
      "step": 123
    },
    {
      "epoch": 0.018546909471637438,
      "grad_norm": 0.19741423428058624,
      "learning_rate": 4.1722306190793495e-05,
      "loss": 0.0077,
      "step": 124
    },
    {
      "epoch": 0.018696481322215158,
      "grad_norm": 0.09049168229103088,
      "learning_rate": 4.0812524109171476e-05,
      "loss": 0.0037,
      "step": 125
    },
    {
      "epoch": 0.01884605317279288,
      "grad_norm": 0.08123178780078888,
      "learning_rate": 3.99058795421495e-05,
      "loss": 0.0121,
      "step": 126
    },
    {
      "epoch": 0.018995625023370603,
      "grad_norm": 0.13129158318042755,
      "learning_rate": 3.9002682108016585e-05,
      "loss": 0.0036,
      "step": 127
    },
    {
      "epoch": 0.019145196873948323,
      "grad_norm": 0.10272780805826187,
      "learning_rate": 3.8103240247869075e-05,
      "loss": 0.0163,
      "step": 128
    },
    {
      "epoch": 0.019294768724526044,
      "grad_norm": 0.11180511862039566,
      "learning_rate": 3.720786112027822e-05,
      "loss": 0.006,
      "step": 129
    },
    {
      "epoch": 0.019444340575103764,
      "grad_norm": 0.08938757330179214,
      "learning_rate": 3.631685049639586e-05,
      "loss": 0.0016,
      "step": 130
    },
    {
      "epoch": 0.019593912425681488,
      "grad_norm": 0.07780175656080246,
      "learning_rate": 3.543051265553377e-05,
      "loss": 0.0028,
      "step": 131
    },
    {
      "epoch": 0.01974348427625921,
      "grad_norm": 0.14631123840808868,
      "learning_rate": 3.4549150281252636e-05,
      "loss": 0.0331,
      "step": 132
    },
    {
      "epoch": 0.01989305612683693,
      "grad_norm": 0.06400536745786667,
      "learning_rate": 3.367306435799584e-05,
      "loss": 0.0017,
      "step": 133
    },
    {
      "epoch": 0.02004262797741465,
      "grad_norm": 0.07184699922800064,
      "learning_rate": 3.2802554068303596e-05,
      "loss": 0.0027,
      "step": 134
    },
    {
      "epoch": 0.020192199827992374,
      "grad_norm": 0.033161476254463196,
      "learning_rate": 3.1937916690642356e-05,
      "loss": 0.0014,
      "step": 135
    },
    {
      "epoch": 0.020341771678570094,
      "grad_norm": 0.05839020013809204,
      "learning_rate": 3.107944749788449e-05,
      "loss": 0.0031,
      "step": 136
    },
    {
      "epoch": 0.020491343529147815,
      "grad_norm": 0.026578811928629875,
      "learning_rate": 3.0227439656472877e-05,
      "loss": 0.0018,
      "step": 137
    },
    {
      "epoch": 0.020640915379725535,
      "grad_norm": 0.03774336352944374,
      "learning_rate": 2.9382184126304834e-05,
      "loss": 0.0019,
      "step": 138
    },
    {
      "epoch": 0.020790487230303255,
      "grad_norm": 0.10273198038339615,
      "learning_rate": 2.8543969561369556e-05,
      "loss": 0.0151,
      "step": 139
    },
    {
      "epoch": 0.02094005908088098,
      "grad_norm": 0.18658724427223206,
      "learning_rate": 2.771308221117309e-05,
      "loss": 0.0069,
      "step": 140
    },
    {
      "epoch": 0.0210896309314587,
      "grad_norm": 0.043363217264413834,
      "learning_rate": 2.688980582298435e-05,
      "loss": 0.0014,
      "step": 141
    },
    {
      "epoch": 0.02123920278203642,
      "grad_norm": 0.05898777395486832,
      "learning_rate": 2.607442154493568e-05,
      "loss": 0.0024,
      "step": 142
    },
    {
      "epoch": 0.02138877463261414,
      "grad_norm": 0.1663537472486496,
      "learning_rate": 2.5267207830011068e-05,
      "loss": 0.0038,
      "step": 143
    },
    {
      "epoch": 0.021538346483191865,
      "grad_norm": 0.04298669099807739,
      "learning_rate": 2.446844034095466e-05,
      "loss": 0.0042,
      "step": 144
    },
    {
      "epoch": 0.021687918333769585,
      "grad_norm": 0.027197590097784996,
      "learning_rate": 2.3678391856132204e-05,
      "loss": 0.0004,
      "step": 145
    },
    {
      "epoch": 0.021837490184347306,
      "grad_norm": 0.12252974510192871,
      "learning_rate": 2.2897332176377528e-05,
      "loss": 0.0049,
      "step": 146
    },
    {
      "epoch": 0.021987062034925026,
      "grad_norm": 0.10520424693822861,
      "learning_rate": 2.2125528032855724e-05,
      "loss": 0.0047,
      "step": 147
    },
    {
      "epoch": 0.022136633885502747,
      "grad_norm": 0.1015310063958168,
      "learning_rate": 2.136324299597474e-05,
      "loss": 0.012,
      "step": 148
    },
    {
      "epoch": 0.02228620573608047,
      "grad_norm": 0.1231570914387703,
      "learning_rate": 2.061073738537635e-05,
      "loss": 0.0023,
      "step": 149
    },
    {
      "epoch": 0.02243577758665819,
      "grad_norm": 0.06972265243530273,
      "learning_rate": 1.9868268181037185e-05,
      "loss": 0.0015,
      "step": 150
    },
    {
      "epoch": 0.02243577758665819,
      "eval_loss": 0.007565848529338837,
      "eval_runtime": 596.5694,
      "eval_samples_per_second": 18.876,
      "eval_steps_per_second": 9.439,
      "step": 150
    },
    {
      "epoch": 0.022585349437235912,
      "grad_norm": 0.26626017689704895,
      "learning_rate": 1.9136088935510362e-05,
      "loss": 0.0795,
      "step": 151
    },
    {
      "epoch": 0.022734921287813632,
      "grad_norm": 0.23198652267456055,
      "learning_rate": 1.8414449687337464e-05,
      "loss": 0.064,
      "step": 152
    },
    {
      "epoch": 0.022884493138391356,
      "grad_norm": 0.14866690337657928,
      "learning_rate": 1.7703596875660645e-05,
      "loss": 0.0123,
      "step": 153
    },
    {
      "epoch": 0.023034064988969077,
      "grad_norm": 0.21994277834892273,
      "learning_rate": 1.700377325606388e-05,
      "loss": 0.0148,
      "step": 154
    },
    {
      "epoch": 0.023183636839546797,
      "grad_norm": 0.15196453034877777,
      "learning_rate": 1.631521781767214e-05,
      "loss": 0.017,
      "step": 155
    },
    {
      "epoch": 0.023333208690124518,
      "grad_norm": 0.11059416830539703,
      "learning_rate": 1.5638165701536868e-05,
      "loss": 0.0076,
      "step": 156
    },
    {
      "epoch": 0.023482780540702238,
      "grad_norm": 0.13811571896076202,
      "learning_rate": 1.4972848120335453e-05,
      "loss": 0.0165,
      "step": 157
    },
    {
      "epoch": 0.023632352391279962,
      "grad_norm": 0.15618985891342163,
      "learning_rate": 1.4319492279412388e-05,
      "loss": 0.0112,
      "step": 158
    },
    {
      "epoch": 0.023781924241857683,
      "grad_norm": 0.16648827493190765,
      "learning_rate": 1.3678321299188801e-05,
      "loss": 0.0051,
      "step": 159
    },
    {
      "epoch": 0.023931496092435403,
      "grad_norm": 0.15495842695236206,
      "learning_rate": 1.3049554138967051e-05,
      "loss": 0.0097,
      "step": 160
    },
    {
      "epoch": 0.024081067943013124,
      "grad_norm": 0.15680111944675446,
      "learning_rate": 1.2433405522156332e-05,
      "loss": 0.0038,
      "step": 161
    },
    {
      "epoch": 0.024230639793590848,
      "grad_norm": 0.03453082963824272,
      "learning_rate": 1.183008586294485e-05,
      "loss": 0.0013,
      "step": 162
    },
    {
      "epoch": 0.024380211644168568,
      "grad_norm": 0.06157035753130913,
      "learning_rate": 1.1239801194443506e-05,
      "loss": 0.0036,
      "step": 163
    },
    {
      "epoch": 0.02452978349474629,
      "grad_norm": 0.08541398495435715,
      "learning_rate": 1.066275309832584e-05,
      "loss": 0.0044,
      "step": 164
    },
    {
      "epoch": 0.02467935534532401,
      "grad_norm": 0.06689931452274323,
      "learning_rate": 1.0099138635988026e-05,
      "loss": 0.0059,
      "step": 165
    },
    {
      "epoch": 0.024828927195901733,
      "grad_norm": 0.08399394154548645,
      "learning_rate": 9.549150281252633e-06,
      "loss": 0.0045,
      "step": 166
    },
    {
      "epoch": 0.024978499046479453,
      "grad_norm": 0.08573979139328003,
      "learning_rate": 9.012975854638949e-06,
      "loss": 0.0049,
      "step": 167
    },
    {
      "epoch": 0.025128070897057174,
      "grad_norm": 0.12518934905529022,
      "learning_rate": 8.490798459222476e-06,
      "loss": 0.0052,
      "step": 168
    },
    {
      "epoch": 0.025277642747634894,
      "grad_norm": 0.11779250204563141,
      "learning_rate": 7.982796418105371e-06,
      "loss": 0.0046,
      "step": 169
    },
    {
      "epoch": 0.025427214598212615,
      "grad_norm": 0.08262436091899872,
      "learning_rate": 7.489143213519301e-06,
      "loss": 0.0041,
      "step": 170
    },
    {
      "epoch": 0.02557678644879034,
      "grad_norm": 0.1106390580534935,
      "learning_rate": 7.010007427581378e-06,
      "loss": 0.0063,
      "step": 171
    },
    {
      "epoch": 0.02572635829936806,
      "grad_norm": 0.09198980033397675,
      "learning_rate": 6.5455526847235825e-06,
      "loss": 0.0074,
      "step": 172
    },
    {
      "epoch": 0.02587593014994578,
      "grad_norm": 0.06989353895187378,
      "learning_rate": 6.0959375958151045e-06,
      "loss": 0.0036,
      "step": 173
    },
    {
      "epoch": 0.0260255020005235,
      "grad_norm": 0.05770116299390793,
      "learning_rate": 5.6613157039969055e-06,
      "loss": 0.0047,
      "step": 174
    },
    {
      "epoch": 0.026175073851101224,
      "grad_norm": 0.10786422342061996,
      "learning_rate": 5.241835432246889e-06,
      "loss": 0.0097,
      "step": 175
    },
    {
      "epoch": 0.026324645701678945,
      "grad_norm": 0.13255083560943604,
      "learning_rate": 4.837640032693558e-06,
      "loss": 0.0048,
      "step": 176
    },
    {
      "epoch": 0.026474217552256665,
      "grad_norm": 0.18882180750370026,
      "learning_rate": 4.448867537695578e-06,
      "loss": 0.0153,
      "step": 177
    },
    {
      "epoch": 0.026623789402834386,
      "grad_norm": 0.14036519825458527,
      "learning_rate": 4.075650712703849e-06,
      "loss": 0.0033,
      "step": 178
    },
    {
      "epoch": 0.026773361253412106,
      "grad_norm": 0.10901960730552673,
      "learning_rate": 3.71811701092219e-06,
      "loss": 0.0105,
      "step": 179
    },
    {
      "epoch": 0.02692293310398983,
      "grad_norm": 0.11455794423818588,
      "learning_rate": 3.376388529782215e-06,
      "loss": 0.0169,
      "step": 180
    },
    {
      "epoch": 0.02707250495456755,
      "grad_norm": 0.0973815992474556,
      "learning_rate": 3.0505819692471792e-06,
      "loss": 0.0042,
      "step": 181
    },
    {
      "epoch": 0.02722207680514527,
      "grad_norm": 0.12800076603889465,
      "learning_rate": 2.7408085919590264e-06,
      "loss": 0.0048,
      "step": 182
    },
    {
      "epoch": 0.02737164865572299,
      "grad_norm": 0.07408041507005692,
      "learning_rate": 2.4471741852423237e-06,
      "loss": 0.0079,
      "step": 183
    },
    {
      "epoch": 0.027521220506300716,
      "grad_norm": 0.04624428227543831,
      "learning_rate": 2.1697790249779636e-06,
      "loss": 0.0018,
      "step": 184
    },
    {
      "epoch": 0.027670792356878436,
      "grad_norm": 0.08687931299209595,
      "learning_rate": 1.908717841359048e-06,
      "loss": 0.004,
      "step": 185
    },
    {
      "epoch": 0.027820364207456157,
      "grad_norm": 0.05964061990380287,
      "learning_rate": 1.6640797865406288e-06,
      "loss": 0.0025,
      "step": 186
    },
    {
      "epoch": 0.027969936058033877,
      "grad_norm": 0.019701970741152763,
      "learning_rate": 1.4359484041943038e-06,
      "loss": 0.0007,
      "step": 187
    },
    {
      "epoch": 0.028119507908611598,
      "grad_norm": 0.019625287503004074,
      "learning_rate": 1.2244016009781701e-06,
      "loss": 0.0008,
      "step": 188
    },
    {
      "epoch": 0.02826907975918932,
      "grad_norm": 0.07729034125804901,
      "learning_rate": 1.0295116199317057e-06,
      "loss": 0.0017,
      "step": 189
    },
    {
      "epoch": 0.028418651609767042,
      "grad_norm": 0.044346727430820465,
      "learning_rate": 8.513450158049108e-07,
      "loss": 0.0016,
      "step": 190
    },
    {
      "epoch": 0.028568223460344763,
      "grad_norm": 0.16363643109798431,
      "learning_rate": 6.899626323298713e-07,
      "loss": 0.0061,
      "step": 191
    },
    {
      "epoch": 0.028717795310922483,
      "grad_norm": 0.10228857398033142,
      "learning_rate": 5.454195814427021e-07,
      "loss": 0.0057,
      "step": 192
    },
    {
      "epoch": 0.028867367161500207,
      "grad_norm": 0.06308329105377197,
      "learning_rate": 4.177652244628627e-07,
      "loss": 0.0021,
      "step": 193
    },
    {
      "epoch": 0.029016939012077927,
      "grad_norm": 0.12209101021289825,
      "learning_rate": 3.0704315523631953e-07,
      "loss": 0.0079,
      "step": 194
    },
    {
      "epoch": 0.029166510862655648,
      "grad_norm": 0.08938577771186829,
      "learning_rate": 2.1329118524827662e-07,
      "loss": 0.0008,
      "step": 195
    },
    {
      "epoch": 0.02931608271323337,
      "grad_norm": 0.040771644562482834,
      "learning_rate": 1.3654133071059893e-07,
      "loss": 0.0041,
      "step": 196
    },
    {
      "epoch": 0.029465654563811092,
      "grad_norm": 0.08314965665340424,
      "learning_rate": 7.681980162830282e-08,
      "loss": 0.0037,
      "step": 197
    },
    {
      "epoch": 0.029615226414388813,
      "grad_norm": 0.08417963236570358,
      "learning_rate": 3.4146992848854695e-08,
      "loss": 0.0115,
      "step": 198
    },
    {
      "epoch": 0.029764798264966533,
      "grad_norm": 0.09368164092302322,
      "learning_rate": 8.537477097364522e-09,
      "loss": 0.0016,
      "step": 199
    },
    {
      "epoch": 0.029914370115544254,
      "grad_norm": 0.11873341351747513,
      "learning_rate": 0.0,
      "loss": 0.0021,
      "step": 200
    },
    {
      "epoch": 0.029914370115544254,
      "eval_loss": 0.006479598581790924,
      "eval_runtime": 596.6293,
      "eval_samples_per_second": 18.874,
      "eval_steps_per_second": 9.438,
      "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": 1.1410122874866893e+17,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}