{
  "best_metric": 0.005237467121332884,
  "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": 0.2335718274116516,
      "learning_rate": 1e-05,
      "loss": 0.3244,
      "step": 1
    },
    {
      "epoch": 0.00029914370115544255,
      "grad_norm": 0.24669764935970306,
      "learning_rate": 2e-05,
      "loss": 0.2655,
      "step": 2
    },
    {
      "epoch": 0.0004487155517331638,
      "grad_norm": 0.3066674768924713,
      "learning_rate": 3e-05,
      "loss": 0.2877,
      "step": 3
    },
    {
      "epoch": 0.0005982874023108851,
      "grad_norm": 0.33075475692749023,
      "learning_rate": 4e-05,
      "loss": 0.2945,
      "step": 4
    },
    {
      "epoch": 0.0007478592528886063,
      "grad_norm": 0.3672390282154083,
      "learning_rate": 5e-05,
      "loss": 0.2783,
      "step": 5
    },
    {
      "epoch": 0.0008974311034663276,
      "grad_norm": 0.3381255269050598,
      "learning_rate": 6e-05,
      "loss": 0.2516,
      "step": 6
    },
    {
      "epoch": 0.0010470029540440488,
      "grad_norm": 0.36011070013046265,
      "learning_rate": 7e-05,
      "loss": 0.2251,
      "step": 7
    },
    {
      "epoch": 0.0011965748046217702,
      "grad_norm": 0.24679383635520935,
      "learning_rate": 8e-05,
      "loss": 0.1804,
      "step": 8
    },
    {
      "epoch": 0.0013461466551994916,
      "grad_norm": 0.23981304466724396,
      "learning_rate": 9e-05,
      "loss": 0.1368,
      "step": 9
    },
    {
      "epoch": 0.0014957185057772127,
      "grad_norm": 0.2410302758216858,
      "learning_rate": 0.0001,
      "loss": 0.1138,
      "step": 10
    },
    {
      "epoch": 0.001645290356354934,
      "grad_norm": 0.20694035291671753,
      "learning_rate": 9.999316524962345e-05,
      "loss": 0.0737,
      "step": 11
    },
    {
      "epoch": 0.0017948622069326552,
      "grad_norm": 0.191515251994133,
      "learning_rate": 9.997266286704631e-05,
      "loss": 0.05,
      "step": 12
    },
    {
      "epoch": 0.0019444340575103765,
      "grad_norm": 0.2231999933719635,
      "learning_rate": 9.993849845741524e-05,
      "loss": 0.0553,
      "step": 13
    },
    {
      "epoch": 0.0020940059080880977,
      "grad_norm": 0.18548688292503357,
      "learning_rate": 9.989068136093873e-05,
      "loss": 0.0385,
      "step": 14
    },
    {
      "epoch": 0.002243577758665819,
      "grad_norm": 0.18379780650138855,
      "learning_rate": 9.98292246503335e-05,
      "loss": 0.0413,
      "step": 15
    },
    {
      "epoch": 0.0023931496092435404,
      "grad_norm": 0.13541050255298615,
      "learning_rate": 9.975414512725057e-05,
      "loss": 0.0376,
      "step": 16
    },
    {
      "epoch": 0.0025427214598212618,
      "grad_norm": 0.36702731251716614,
      "learning_rate": 9.966546331768191e-05,
      "loss": 0.0209,
      "step": 17
    },
    {
      "epoch": 0.002692293310398983,
      "grad_norm": 0.18282711505889893,
      "learning_rate": 9.956320346634876e-05,
      "loss": 0.0397,
      "step": 18
    },
    {
      "epoch": 0.002841865160976704,
      "grad_norm": 0.1637088656425476,
      "learning_rate": 9.944739353007344e-05,
      "loss": 0.0278,
      "step": 19
    },
    {
      "epoch": 0.0029914370115544254,
      "grad_norm": 0.12681163847446442,
      "learning_rate": 9.931806517013612e-05,
      "loss": 0.0188,
      "step": 20
    },
    {
      "epoch": 0.0031410088621321467,
      "grad_norm": 0.12179907411336899,
      "learning_rate": 9.917525374361912e-05,
      "loss": 0.0191,
      "step": 21
    },
    {
      "epoch": 0.003290580712709868,
      "grad_norm": 0.1537581831216812,
      "learning_rate": 9.901899829374047e-05,
      "loss": 0.0299,
      "step": 22
    },
    {
      "epoch": 0.0034401525632875895,
      "grad_norm": 0.08640659600496292,
      "learning_rate": 9.884934153917997e-05,
      "loss": 0.0178,
      "step": 23
    },
    {
      "epoch": 0.0035897244138653104,
      "grad_norm": 0.12365993857383728,
      "learning_rate": 9.86663298624003e-05,
      "loss": 0.0294,
      "step": 24
    },
    {
      "epoch": 0.0037392962644430317,
      "grad_norm": 0.11540157347917557,
      "learning_rate": 9.847001329696653e-05,
      "loss": 0.0294,
      "step": 25
    },
    {
      "epoch": 0.003888868115020753,
      "grad_norm": 0.09166237711906433,
      "learning_rate": 9.826044551386744e-05,
      "loss": 0.0186,
      "step": 26
    },
    {
      "epoch": 0.004038439965598474,
      "grad_norm": 0.10461744666099548,
      "learning_rate": 9.803768380684242e-05,
      "loss": 0.0174,
      "step": 27
    },
    {
      "epoch": 0.004188011816176195,
      "grad_norm": 0.07264848053455353,
      "learning_rate": 9.780178907671789e-05,
      "loss": 0.0153,
      "step": 28
    },
    {
      "epoch": 0.004337583666753917,
      "grad_norm": 0.07782348990440369,
      "learning_rate": 9.755282581475769e-05,
      "loss": 0.0088,
      "step": 29
    },
    {
      "epoch": 0.004487155517331638,
      "grad_norm": 0.09824693948030472,
      "learning_rate": 9.729086208503174e-05,
      "loss": 0.0292,
      "step": 30
    },
    {
      "epoch": 0.0046367273679093594,
      "grad_norm": 0.0825524553656578,
      "learning_rate": 9.701596950580806e-05,
      "loss": 0.013,
      "step": 31
    },
    {
      "epoch": 0.004786299218487081,
      "grad_norm": 0.0793503150343895,
      "learning_rate": 9.672822322997305e-05,
      "loss": 0.012,
      "step": 32
    },
    {
      "epoch": 0.004935871069064802,
      "grad_norm": 0.06858407706022263,
      "learning_rate": 9.642770192448536e-05,
      "loss": 0.0103,
      "step": 33
    },
    {
      "epoch": 0.0050854429196425235,
      "grad_norm": 0.05604421719908714,
      "learning_rate": 9.611448774886924e-05,
      "loss": 0.0164,
      "step": 34
    },
    {
      "epoch": 0.005235014770220245,
      "grad_norm": 0.06667090207338333,
      "learning_rate": 9.578866633275288e-05,
      "loss": 0.0101,
      "step": 35
    },
    {
      "epoch": 0.005384586620797966,
      "grad_norm": 0.05359822139143944,
      "learning_rate": 9.545032675245813e-05,
      "loss": 0.0042,
      "step": 36
    },
    {
      "epoch": 0.005534158471375687,
      "grad_norm": 0.08033403754234314,
      "learning_rate": 9.509956150664796e-05,
      "loss": 0.0092,
      "step": 37
    },
    {
      "epoch": 0.005683730321953408,
      "grad_norm": 0.05404312536120415,
      "learning_rate": 9.473646649103818e-05,
      "loss": 0.0075,
      "step": 38
    },
    {
      "epoch": 0.005833302172531129,
      "grad_norm": 0.06979276239871979,
      "learning_rate": 9.43611409721806e-05,
      "loss": 0.0051,
      "step": 39
    },
    {
      "epoch": 0.005982874023108851,
      "grad_norm": 0.09354138374328613,
      "learning_rate": 9.397368756032445e-05,
      "loss": 0.0163,
      "step": 40
    },
    {
      "epoch": 0.006132445873686572,
      "grad_norm": 0.05592981353402138,
      "learning_rate": 9.357421218136386e-05,
      "loss": 0.0131,
      "step": 41
    },
    {
      "epoch": 0.0062820177242642935,
      "grad_norm": 0.07511667907238007,
      "learning_rate": 9.316282404787871e-05,
      "loss": 0.0056,
      "step": 42
    },
    {
      "epoch": 0.006431589574842015,
      "grad_norm": 0.033979903906583786,
      "learning_rate": 9.273963562927695e-05,
      "loss": 0.003,
      "step": 43
    },
    {
      "epoch": 0.006581161425419736,
      "grad_norm": 0.014988441951572895,
      "learning_rate": 9.230476262104677e-05,
      "loss": 0.0012,
      "step": 44
    },
    {
      "epoch": 0.0067307332759974576,
      "grad_norm": 0.04492829740047455,
      "learning_rate": 9.185832391312644e-05,
      "loss": 0.0022,
      "step": 45
    },
    {
      "epoch": 0.006880305126575179,
      "grad_norm": 0.07551133632659912,
      "learning_rate": 9.140044155740101e-05,
      "loss": 0.0119,
      "step": 46
    },
    {
      "epoch": 0.007029876977152899,
      "grad_norm": 0.06041828915476799,
      "learning_rate": 9.093124073433463e-05,
      "loss": 0.004,
      "step": 47
    },
    {
      "epoch": 0.007179448827730621,
      "grad_norm": 0.04725939407944679,
      "learning_rate": 9.045084971874738e-05,
      "loss": 0.0043,
      "step": 48
    },
    {
      "epoch": 0.007329020678308342,
      "grad_norm": 0.019574977457523346,
      "learning_rate": 8.995939984474624e-05,
      "loss": 0.001,
      "step": 49
    },
    {
      "epoch": 0.0074785925288860635,
      "grad_norm": 0.2806149125099182,
      "learning_rate": 8.945702546981969e-05,
      "loss": 0.0042,
      "step": 50
    },
    {
      "epoch": 0.0074785925288860635,
      "eval_loss": 0.011959722265601158,
      "eval_runtime": 981.3101,
      "eval_samples_per_second": 11.475,
      "eval_steps_per_second": 2.87,
      "step": 50
    },
    {
      "epoch": 0.007628164379463785,
      "grad_norm": 0.24844548106193542,
      "learning_rate": 8.894386393810563e-05,
      "loss": 0.0576,
      "step": 51
    },
    {
      "epoch": 0.007777736230041506,
      "grad_norm": 0.16677170991897583,
      "learning_rate": 8.842005554284296e-05,
      "loss": 0.0199,
      "step": 52
    },
    {
      "epoch": 0.007927308080619228,
      "grad_norm": 0.11410771310329437,
      "learning_rate": 8.788574348801675e-05,
      "loss": 0.026,
      "step": 53
    },
    {
      "epoch": 0.008076879931196948,
      "grad_norm": 0.12455239146947861,
      "learning_rate": 8.73410738492077e-05,
      "loss": 0.0276,
      "step": 54
    },
    {
      "epoch": 0.00822645178177467,
      "grad_norm": 0.07864409685134888,
      "learning_rate": 8.678619553365659e-05,
      "loss": 0.0103,
      "step": 55
    },
    {
      "epoch": 0.00837602363235239,
      "grad_norm": 0.08136087656021118,
      "learning_rate": 8.622126023955446e-05,
      "loss": 0.0097,
      "step": 56
    },
    {
      "epoch": 0.008525595482930113,
      "grad_norm": 0.09274493157863617,
      "learning_rate": 8.564642241456986e-05,
      "loss": 0.011,
      "step": 57
    },
    {
      "epoch": 0.008675167333507833,
      "grad_norm": 0.06602936238050461,
      "learning_rate": 8.506183921362443e-05,
      "loss": 0.0094,
      "step": 58
    },
    {
      "epoch": 0.008824739184085556,
      "grad_norm": 0.07856868207454681,
      "learning_rate": 8.44676704559283e-05,
      "loss": 0.0129,
      "step": 59
    },
    {
      "epoch": 0.008974311034663276,
      "grad_norm": 0.07968848943710327,
      "learning_rate": 8.386407858128706e-05,
      "loss": 0.0095,
      "step": 60
    },
    {
      "epoch": 0.009123882885240998,
      "grad_norm": 0.08761177211999893,
      "learning_rate": 8.32512286056924e-05,
      "loss": 0.014,
      "step": 61
    },
    {
      "epoch": 0.009273454735818719,
      "grad_norm": 0.08636616170406342,
      "learning_rate": 8.262928807620843e-05,
      "loss": 0.0069,
      "step": 62
    },
    {
      "epoch": 0.00942302658639644,
      "grad_norm": 0.10641941428184509,
      "learning_rate": 8.199842702516583e-05,
      "loss": 0.0068,
      "step": 63
    },
    {
      "epoch": 0.009572598436974162,
      "grad_norm": 0.09750671684741974,
      "learning_rate": 8.135881792367686e-05,
      "loss": 0.0093,
      "step": 64
    },
    {
      "epoch": 0.009722170287551882,
      "grad_norm": 0.14316971600055695,
      "learning_rate": 8.07106356344834e-05,
      "loss": 0.006,
      "step": 65
    },
    {
      "epoch": 0.009871742138129604,
      "grad_norm": 0.053067490458488464,
      "learning_rate": 8.005405736415126e-05,
      "loss": 0.0079,
      "step": 66
    },
    {
      "epoch": 0.010021313988707325,
      "grad_norm": 0.05899115651845932,
      "learning_rate": 7.938926261462366e-05,
      "loss": 0.0155,
      "step": 67
    },
    {
      "epoch": 0.010170885839285047,
      "grad_norm": 0.0471423864364624,
      "learning_rate": 7.871643313414718e-05,
      "loss": 0.005,
      "step": 68
    },
    {
      "epoch": 0.010320457689862768,
      "grad_norm": 0.054195620119571686,
      "learning_rate": 7.803575286758364e-05,
      "loss": 0.0107,
      "step": 69
    },
    {
      "epoch": 0.01047002954044049,
      "grad_norm": 0.08941451460123062,
      "learning_rate": 7.734740790612136e-05,
      "loss": 0.0153,
      "step": 70
    },
    {
      "epoch": 0.01061960139101821,
      "grad_norm": 0.04382981359958649,
      "learning_rate": 7.66515864363997e-05,
      "loss": 0.0053,
      "step": 71
    },
    {
      "epoch": 0.010769173241595932,
      "grad_norm": 0.06176731362938881,
      "learning_rate": 7.594847868906076e-05,
      "loss": 0.0086,
      "step": 72
    },
    {
      "epoch": 0.010918745092173653,
      "grad_norm": 0.06019255146384239,
      "learning_rate": 7.52382768867422e-05,
      "loss": 0.0047,
      "step": 73
    },
    {
      "epoch": 0.011068316942751373,
      "grad_norm": 0.09464941173791885,
      "learning_rate": 7.452117519152542e-05,
      "loss": 0.0156,
      "step": 74
    },
    {
      "epoch": 0.011217888793329096,
      "grad_norm": 0.06692983955144882,
      "learning_rate": 7.379736965185368e-05,
      "loss": 0.0146,
      "step": 75
    },
    {
      "epoch": 0.011367460643906816,
      "grad_norm": 0.03981421887874603,
      "learning_rate": 7.30670581489344e-05,
      "loss": 0.0055,
      "step": 76
    },
    {
      "epoch": 0.011517032494484538,
      "grad_norm": 0.045137710869312286,
      "learning_rate": 7.233044034264034e-05,
      "loss": 0.0044,
      "step": 77
    },
    {
      "epoch": 0.011666604345062259,
      "grad_norm": 0.04282338544726372,
      "learning_rate": 7.158771761692464e-05,
      "loss": 0.0033,
      "step": 78
    },
    {
      "epoch": 0.011816176195639981,
      "grad_norm": 0.07697294652462006,
      "learning_rate": 7.083909302476453e-05,
      "loss": 0.0082,
      "step": 79
    },
    {
      "epoch": 0.011965748046217702,
      "grad_norm": 0.09696398675441742,
      "learning_rate": 7.008477123264848e-05,
      "loss": 0.0255,
      "step": 80
    },
    {
      "epoch": 0.012115319896795424,
      "grad_norm": 0.03255205228924751,
      "learning_rate": 6.932495846462261e-05,
      "loss": 0.0024,
      "step": 81
    },
    {
      "epoch": 0.012264891747373144,
      "grad_norm": 0.0711100623011589,
      "learning_rate": 6.855986244591104e-05,
      "loss": 0.0063,
      "step": 82
    },
    {
      "epoch": 0.012414463597950866,
      "grad_norm": 0.04751328378915787,
      "learning_rate": 6.778969234612584e-05,
      "loss": 0.0023,
      "step": 83
    },
    {
      "epoch": 0.012564035448528587,
      "grad_norm": 0.03660387918353081,
      "learning_rate": 6.701465872208216e-05,
      "loss": 0.0035,
      "step": 84
    },
    {
      "epoch": 0.012713607299106307,
      "grad_norm": 0.03452017903327942,
      "learning_rate": 6.623497346023418e-05,
      "loss": 0.002,
      "step": 85
    },
    {
      "epoch": 0.01286317914968403,
      "grad_norm": 0.0757698267698288,
      "learning_rate": 6.545084971874738e-05,
      "loss": 0.0073,
      "step": 86
    },
    {
      "epoch": 0.01301275100026175,
      "grad_norm": 0.05622588098049164,
      "learning_rate": 6.466250186922325e-05,
      "loss": 0.0049,
      "step": 87
    },
    {
      "epoch": 0.013162322850839472,
      "grad_norm": 0.06924626976251602,
      "learning_rate": 6.387014543809223e-05,
      "loss": 0.0068,
      "step": 88
    },
    {
      "epoch": 0.013311894701417193,
      "grad_norm": 0.06929722428321838,
      "learning_rate": 6.307399704769099e-05,
      "loss": 0.007,
      "step": 89
    },
    {
      "epoch": 0.013461466551994915,
      "grad_norm": 0.07837231457233429,
      "learning_rate": 6.227427435703997e-05,
      "loss": 0.0026,
      "step": 90
    },
    {
      "epoch": 0.013611038402572636,
      "grad_norm": 0.05379178747534752,
      "learning_rate": 6.147119600233758e-05,
      "loss": 0.0054,
      "step": 91
    },
    {
      "epoch": 0.013760610253150358,
      "grad_norm": 0.024465255439281464,
      "learning_rate": 6.066498153718735e-05,
      "loss": 0.0038,
      "step": 92
    },
    {
      "epoch": 0.013910182103728078,
      "grad_norm": 0.04232843220233917,
      "learning_rate": 5.985585137257401e-05,
      "loss": 0.0104,
      "step": 93
    },
    {
      "epoch": 0.014059753954305799,
      "grad_norm": 0.07749313116073608,
      "learning_rate": 5.90440267166055e-05,
      "loss": 0.0039,
      "step": 94
    },
    {
      "epoch": 0.014209325804883521,
      "grad_norm": 0.050073325634002686,
      "learning_rate": 5.8229729514036705e-05,
      "loss": 0.0034,
      "step": 95
    },
    {
      "epoch": 0.014358897655461242,
      "grad_norm": 0.09997029602527618,
      "learning_rate": 5.74131823855921e-05,
      "loss": 0.0024,
      "step": 96
    },
    {
      "epoch": 0.014508469506038964,
      "grad_norm": 0.0829552486538887,
      "learning_rate": 5.6594608567103456e-05,
      "loss": 0.0033,
      "step": 97
    },
    {
      "epoch": 0.014658041356616684,
      "grad_norm": 0.0437268428504467,
      "learning_rate": 5.577423184847932e-05,
      "loss": 0.0012,
      "step": 98
    },
    {
      "epoch": 0.014807613207194406,
      "grad_norm": 0.04025645926594734,
      "learning_rate": 5.495227651252315e-05,
      "loss": 0.0011,
      "step": 99
    },
    {
      "epoch": 0.014957185057772127,
      "grad_norm": 0.06813428550958633,
      "learning_rate": 5.4128967273616625e-05,
      "loss": 0.0025,
      "step": 100
    },
    {
      "epoch": 0.014957185057772127,
      "eval_loss": 0.007293121423572302,
      "eval_runtime": 979.0849,
      "eval_samples_per_second": 11.502,
      "eval_steps_per_second": 2.876,
      "step": 100
    },
    {
      "epoch": 0.01510675690834985,
      "grad_norm": 0.11526782065629959,
      "learning_rate": 5.330452921628497e-05,
      "loss": 0.0389,
      "step": 101
    },
    {
      "epoch": 0.01525632875892757,
      "grad_norm": 0.07979279011487961,
      "learning_rate": 5.247918773366112e-05,
      "loss": 0.0129,
      "step": 102
    },
    {
      "epoch": 0.015405900609505292,
      "grad_norm": 0.057435400784015656,
      "learning_rate": 5.165316846586541e-05,
      "loss": 0.0094,
      "step": 103
    },
    {
      "epoch": 0.015555472460083012,
      "grad_norm": 0.05251561850309372,
      "learning_rate": 5.0826697238317935e-05,
      "loss": 0.0095,
      "step": 104
    },
    {
      "epoch": 0.015705044310660735,
      "grad_norm": 0.06069431081414223,
      "learning_rate": 5e-05,
      "loss": 0.0073,
      "step": 105
    },
    {
      "epoch": 0.015854616161238455,
      "grad_norm": 0.05534122511744499,
      "learning_rate": 4.917330276168208e-05,
      "loss": 0.0073,
      "step": 106
    },
    {
      "epoch": 0.016004188011816176,
      "grad_norm": 0.05790477246046066,
      "learning_rate": 4.834683153413459e-05,
      "loss": 0.0065,
      "step": 107
    },
    {
      "epoch": 0.016153759862393896,
      "grad_norm": 0.07611574232578278,
      "learning_rate": 4.7520812266338885e-05,
      "loss": 0.0068,
      "step": 108
    },
    {
      "epoch": 0.01630333171297162,
      "grad_norm": 0.03928947448730469,
      "learning_rate": 4.669547078371504e-05,
      "loss": 0.0037,
      "step": 109
    },
    {
      "epoch": 0.01645290356354934,
      "grad_norm": 0.07120589166879654,
      "learning_rate": 4.5871032726383386e-05,
      "loss": 0.0151,
      "step": 110
    },
    {
      "epoch": 0.01660247541412706,
      "grad_norm": 0.06420360505580902,
      "learning_rate": 4.504772348747687e-05,
      "loss": 0.008,
      "step": 111
    },
    {
      "epoch": 0.01675204726470478,
      "grad_norm": 0.06623335927724838,
      "learning_rate": 4.4225768151520694e-05,
      "loss": 0.0039,
      "step": 112
    },
    {
      "epoch": 0.016901619115282505,
      "grad_norm": 0.06353968381881714,
      "learning_rate": 4.3405391432896555e-05,
      "loss": 0.0064,
      "step": 113
    },
    {
      "epoch": 0.017051190965860226,
      "grad_norm": 0.053835246711969376,
      "learning_rate": 4.2586817614407895e-05,
      "loss": 0.0092,
      "step": 114
    },
    {
      "epoch": 0.017200762816437946,
      "grad_norm": 0.05195113644003868,
      "learning_rate": 4.17702704859633e-05,
      "loss": 0.0038,
      "step": 115
    },
    {
      "epoch": 0.017350334667015667,
      "grad_norm": 0.050349172204732895,
      "learning_rate": 4.095597328339452e-05,
      "loss": 0.0049,
      "step": 116
    },
    {
      "epoch": 0.017499906517593387,
      "grad_norm": 0.07217245548963547,
      "learning_rate": 4.0144148627425993e-05,
      "loss": 0.0078,
      "step": 117
    },
    {
      "epoch": 0.01764947836817111,
      "grad_norm": 0.04450047016143799,
      "learning_rate": 3.933501846281267e-05,
      "loss": 0.0083,
      "step": 118
    },
    {
      "epoch": 0.017799050218748832,
      "grad_norm": 0.0540819987654686,
      "learning_rate": 3.852880399766243e-05,
      "loss": 0.0043,
      "step": 119
    },
    {
      "epoch": 0.017948622069326552,
      "grad_norm": 0.03682225942611694,
      "learning_rate": 3.772572564296005e-05,
      "loss": 0.0037,
      "step": 120
    },
    {
      "epoch": 0.018098193919904273,
      "grad_norm": 0.07784504443407059,
      "learning_rate": 3.6926002952309016e-05,
      "loss": 0.0076,
      "step": 121
    },
    {
      "epoch": 0.018247765770481997,
      "grad_norm": 0.016290148720145226,
      "learning_rate": 3.612985456190778e-05,
      "loss": 0.001,
      "step": 122
    },
    {
      "epoch": 0.018397337621059717,
      "grad_norm": 0.026618272066116333,
      "learning_rate": 3.533749813077677e-05,
      "loss": 0.0045,
      "step": 123
    },
    {
      "epoch": 0.018546909471637438,
      "grad_norm": 0.07027376443147659,
      "learning_rate": 3.4549150281252636e-05,
      "loss": 0.0057,
      "step": 124
    },
    {
      "epoch": 0.018696481322215158,
      "grad_norm": 0.031118270009756088,
      "learning_rate": 3.3765026539765834e-05,
      "loss": 0.0021,
      "step": 125
    },
    {
      "epoch": 0.01884605317279288,
      "grad_norm": 0.041747208684682846,
      "learning_rate": 3.298534127791785e-05,
      "loss": 0.0057,
      "step": 126
    },
    {
      "epoch": 0.018995625023370603,
      "grad_norm": 0.03801221027970314,
      "learning_rate": 3.221030765387417e-05,
      "loss": 0.0026,
      "step": 127
    },
    {
      "epoch": 0.019145196873948323,
      "grad_norm": 0.0467122457921505,
      "learning_rate": 3.144013755408895e-05,
      "loss": 0.0051,
      "step": 128
    },
    {
      "epoch": 0.019294768724526044,
      "grad_norm": 0.05798231065273285,
      "learning_rate": 3.0675041535377405e-05,
      "loss": 0.0061,
      "step": 129
    },
    {
      "epoch": 0.019444340575103764,
      "grad_norm": 0.1306389719247818,
      "learning_rate": 2.991522876735154e-05,
      "loss": 0.0365,
      "step": 130
    },
    {
      "epoch": 0.019593912425681488,
      "grad_norm": 0.05191555619239807,
      "learning_rate": 2.916090697523549e-05,
      "loss": 0.0048,
      "step": 131
    },
    {
      "epoch": 0.01974348427625921,
      "grad_norm": 0.03966742381453514,
      "learning_rate": 2.8412282383075363e-05,
      "loss": 0.004,
      "step": 132
    },
    {
      "epoch": 0.01989305612683693,
      "grad_norm": 0.050630126148462296,
      "learning_rate": 2.766955965735968e-05,
      "loss": 0.0032,
      "step": 133
    },
    {
      "epoch": 0.02004262797741465,
      "grad_norm": 0.013350145891308784,
      "learning_rate": 2.693294185106562e-05,
      "loss": 0.0007,
      "step": 134
    },
    {
      "epoch": 0.020192199827992374,
      "grad_norm": 0.06373170018196106,
      "learning_rate": 2.6202630348146324e-05,
      "loss": 0.0151,
      "step": 135
    },
    {
      "epoch": 0.020341771678570094,
      "grad_norm": 0.0341380275785923,
      "learning_rate": 2.547882480847461e-05,
      "loss": 0.0024,
      "step": 136
    },
    {
      "epoch": 0.020491343529147815,
      "grad_norm": 0.03135700151324272,
      "learning_rate": 2.476172311325783e-05,
      "loss": 0.0016,
      "step": 137
    },
    {
      "epoch": 0.020640915379725535,
      "grad_norm": 0.05378114804625511,
      "learning_rate": 2.405152131093926e-05,
      "loss": 0.0025,
      "step": 138
    },
    {
      "epoch": 0.020790487230303255,
      "grad_norm": 0.031162045896053314,
      "learning_rate": 2.3348413563600325e-05,
      "loss": 0.0047,
      "step": 139
    },
    {
      "epoch": 0.02094005908088098,
      "grad_norm": 0.0838971957564354,
      "learning_rate": 2.2652592093878666e-05,
      "loss": 0.0018,
      "step": 140
    },
    {
      "epoch": 0.0210896309314587,
      "grad_norm": 0.06200795620679855,
      "learning_rate": 2.196424713241637e-05,
      "loss": 0.0045,
      "step": 141
    },
    {
      "epoch": 0.02123920278203642,
      "grad_norm": 0.03556717932224274,
      "learning_rate": 2.128356686585282e-05,
      "loss": 0.0021,
      "step": 142
    },
    {
      "epoch": 0.02138877463261414,
      "grad_norm": 0.020485658198595047,
      "learning_rate": 2.061073738537635e-05,
      "loss": 0.0022,
      "step": 143
    },
    {
      "epoch": 0.021538346483191865,
      "grad_norm": 0.04211965203285217,
      "learning_rate": 1.9945942635848748e-05,
      "loss": 0.0077,
      "step": 144
    },
    {
      "epoch": 0.021687918333769585,
      "grad_norm": 0.01763017475605011,
      "learning_rate": 1.928936436551661e-05,
      "loss": 0.0009,
      "step": 145
    },
    {
      "epoch": 0.021837490184347306,
      "grad_norm": 0.054575420916080475,
      "learning_rate": 1.8641182076323148e-05,
      "loss": 0.0011,
      "step": 146
    },
    {
      "epoch": 0.021987062034925026,
      "grad_norm": 0.019162116572260857,
      "learning_rate": 1.800157297483417e-05,
      "loss": 0.0009,
      "step": 147
    },
    {
      "epoch": 0.022136633885502747,
      "grad_norm": 0.046215735375881195,
      "learning_rate": 1.7370711923791567e-05,
      "loss": 0.0027,
      "step": 148
    },
    {
      "epoch": 0.02228620573608047,
      "grad_norm": 0.04071297124028206,
      "learning_rate": 1.6748771394307585e-05,
      "loss": 0.008,
      "step": 149
    },
    {
      "epoch": 0.02243577758665819,
      "grad_norm": 0.024444211274385452,
      "learning_rate": 1.6135921418712956e-05,
      "loss": 0.0027,
      "step": 150
    },
    {
      "epoch": 0.02243577758665819,
      "eval_loss": 0.005612719338387251,
      "eval_runtime": 981.8471,
      "eval_samples_per_second": 11.469,
      "eval_steps_per_second": 2.868,
      "step": 150
    },
    {
      "epoch": 0.022585349437235912,
      "grad_norm": 0.16142116487026215,
      "learning_rate": 1.553232954407171e-05,
      "loss": 0.0563,
      "step": 151
    },
    {
      "epoch": 0.022734921287813632,
      "grad_norm": 0.0977514386177063,
      "learning_rate": 1.4938160786375572e-05,
      "loss": 0.0412,
      "step": 152
    },
    {
      "epoch": 0.022884493138391356,
      "grad_norm": 0.07195427268743515,
      "learning_rate": 1.435357758543015e-05,
      "loss": 0.0097,
      "step": 153
    },
    {
      "epoch": 0.023034064988969077,
      "grad_norm": 0.07662596553564072,
      "learning_rate": 1.3778739760445552e-05,
      "loss": 0.0073,
      "step": 154
    },
    {
      "epoch": 0.023183636839546797,
      "grad_norm": 0.057943496853113174,
      "learning_rate": 1.3213804466343421e-05,
      "loss": 0.0111,
      "step": 155
    },
    {
      "epoch": 0.023333208690124518,
      "grad_norm": 0.10002079606056213,
      "learning_rate": 1.2658926150792322e-05,
      "loss": 0.0115,
      "step": 156
    },
    {
      "epoch": 0.023482780540702238,
      "grad_norm": 0.032223351299762726,
      "learning_rate": 1.2114256511983274e-05,
      "loss": 0.003,
      "step": 157
    },
    {
      "epoch": 0.023632352391279962,
      "grad_norm": 0.07704512029886246,
      "learning_rate": 1.157994445715706e-05,
      "loss": 0.0129,
      "step": 158
    },
    {
      "epoch": 0.023781924241857683,
      "grad_norm": 0.045840613543987274,
      "learning_rate": 1.1056136061894384e-05,
      "loss": 0.0081,
      "step": 159
    },
    {
      "epoch": 0.023931496092435403,
      "grad_norm": 0.03816791996359825,
      "learning_rate": 1.0542974530180327e-05,
      "loss": 0.0047,
      "step": 160
    },
    {
      "epoch": 0.024081067943013124,
      "grad_norm": 0.034477926790714264,
      "learning_rate": 1.0040600155253765e-05,
      "loss": 0.0016,
      "step": 161
    },
    {
      "epoch": 0.024230639793590848,
      "grad_norm": 0.03615734353661537,
      "learning_rate": 9.549150281252633e-06,
      "loss": 0.0019,
      "step": 162
    },
    {
      "epoch": 0.024380211644168568,
      "grad_norm": 0.0535636804997921,
      "learning_rate": 9.068759265665384e-06,
      "loss": 0.0049,
      "step": 163
    },
    {
      "epoch": 0.02452978349474629,
      "grad_norm": 0.03363847732543945,
      "learning_rate": 8.599558442598998e-06,
      "loss": 0.0015,
      "step": 164
    },
    {
      "epoch": 0.02467935534532401,
      "grad_norm": 0.05758949741721153,
      "learning_rate": 8.141676086873572e-06,
      "loss": 0.0053,
      "step": 165
    },
    {
      "epoch": 0.024828927195901733,
      "grad_norm": 0.05610790103673935,
      "learning_rate": 7.695237378953223e-06,
      "loss": 0.0045,
      "step": 166
    },
    {
      "epoch": 0.024978499046479453,
      "grad_norm": 0.03818892315030098,
      "learning_rate": 7.260364370723044e-06,
      "loss": 0.0036,
      "step": 167
    },
    {
      "epoch": 0.025128070897057174,
      "grad_norm": 0.04449839144945145,
      "learning_rate": 6.837175952121306e-06,
      "loss": 0.0054,
      "step": 168
    },
    {
      "epoch": 0.025277642747634894,
      "grad_norm": 0.04502438008785248,
      "learning_rate": 6.425787818636131e-06,
      "loss": 0.0024,
      "step": 169
    },
    {
      "epoch": 0.025427214598212615,
      "grad_norm": 0.03147340938448906,
      "learning_rate": 6.026312439675552e-06,
      "loss": 0.0021,
      "step": 170
    },
    {
      "epoch": 0.02557678644879034,
      "grad_norm": 0.05934036150574684,
      "learning_rate": 5.6388590278194096e-06,
      "loss": 0.0064,
      "step": 171
    },
    {
      "epoch": 0.02572635829936806,
      "grad_norm": 0.0459320992231369,
      "learning_rate": 5.263533508961827e-06,
      "loss": 0.0032,
      "step": 172
    },
    {
      "epoch": 0.02587593014994578,
      "grad_norm": 0.04286656528711319,
      "learning_rate": 4.900438493352055e-06,
      "loss": 0.0064,
      "step": 173
    },
    {
      "epoch": 0.0260255020005235,
      "grad_norm": 0.07162647694349289,
      "learning_rate": 4.549673247541875e-06,
      "loss": 0.0073,
      "step": 174
    },
    {
      "epoch": 0.026175073851101224,
      "grad_norm": 0.013858659192919731,
      "learning_rate": 4.2113336672471245e-06,
      "loss": 0.0011,
      "step": 175
    },
    {
      "epoch": 0.026324645701678945,
      "grad_norm": 0.054190125316381454,
      "learning_rate": 3.885512251130763e-06,
      "loss": 0.0048,
      "step": 176
    },
    {
      "epoch": 0.026474217552256665,
      "grad_norm": 0.05851425603032112,
      "learning_rate": 3.5722980755146517e-06,
      "loss": 0.0081,
      "step": 177
    },
    {
      "epoch": 0.026623789402834386,
      "grad_norm": 0.0624123178422451,
      "learning_rate": 3.271776770026963e-06,
      "loss": 0.0041,
      "step": 178
    },
    {
      "epoch": 0.026773361253412106,
      "grad_norm": 0.04809097573161125,
      "learning_rate": 2.9840304941919415e-06,
      "loss": 0.0059,
      "step": 179
    },
    {
      "epoch": 0.02692293310398983,
      "grad_norm": 0.07402875274419785,
      "learning_rate": 2.7091379149682685e-06,
      "loss": 0.0118,
      "step": 180
    },
    {
      "epoch": 0.02707250495456755,
      "grad_norm": 0.039009373635053635,
      "learning_rate": 2.4471741852423237e-06,
      "loss": 0.0019,
      "step": 181
    },
    {
      "epoch": 0.02722207680514527,
      "grad_norm": 0.053678274154663086,
      "learning_rate": 2.1982109232821178e-06,
      "loss": 0.0075,
      "step": 182
    },
    {
      "epoch": 0.02737164865572299,
      "grad_norm": 0.04033803194761276,
      "learning_rate": 1.962316193157593e-06,
      "loss": 0.007,
      "step": 183
    },
    {
      "epoch": 0.027521220506300716,
      "grad_norm": 0.02706719934940338,
      "learning_rate": 1.7395544861325718e-06,
      "loss": 0.0015,
      "step": 184
    },
    {
      "epoch": 0.027670792356878436,
      "grad_norm": 0.08121436834335327,
      "learning_rate": 1.5299867030334814e-06,
      "loss": 0.014,
      "step": 185
    },
    {
      "epoch": 0.027820364207456157,
      "grad_norm": 0.05873577296733856,
      "learning_rate": 1.333670137599713e-06,
      "loss": 0.0035,
      "step": 186
    },
    {
      "epoch": 0.027969936058033877,
      "grad_norm": 0.031511470675468445,
      "learning_rate": 1.1506584608200367e-06,
      "loss": 0.0019,
      "step": 187
    },
    {
      "epoch": 0.028119507908611598,
      "grad_norm": 0.035707294940948486,
      "learning_rate": 9.810017062595322e-07,
      "loss": 0.002,
      "step": 188
    },
    {
      "epoch": 0.02826907975918932,
      "grad_norm": 0.0599973164498806,
      "learning_rate": 8.247462563808817e-07,
      "loss": 0.0035,
      "step": 189
    },
    {
      "epoch": 0.028418651609767042,
      "grad_norm": 0.02252264879643917,
      "learning_rate": 6.819348298638839e-07,
      "loss": 0.0014,
      "step": 190
    },
    {
      "epoch": 0.028568223460344763,
      "grad_norm": 0.06435447186231613,
      "learning_rate": 5.526064699265753e-07,
      "loss": 0.0061,
      "step": 191
    },
    {
      "epoch": 0.028717795310922483,
      "grad_norm": 0.025119544938206673,
      "learning_rate": 4.367965336512403e-07,
      "loss": 0.0037,
      "step": 192
    },
    {
      "epoch": 0.028867367161500207,
      "grad_norm": 0.04047815129160881,
      "learning_rate": 3.3453668231809286e-07,
      "loss": 0.0028,
      "step": 193
    },
    {
      "epoch": 0.029016939012077927,
      "grad_norm": 0.03127357363700867,
      "learning_rate": 2.458548727494292e-07,
      "loss": 0.0026,
      "step": 194
    },
    {
      "epoch": 0.029166510862655648,
      "grad_norm": 0.051997654139995575,
      "learning_rate": 1.7077534966650766e-07,
      "loss": 0.0091,
      "step": 195
    },
    {
      "epoch": 0.02931608271323337,
      "grad_norm": 0.05788138881325722,
      "learning_rate": 1.0931863906127327e-07,
      "loss": 0.0024,
      "step": 196
    },
    {
      "epoch": 0.029465654563811092,
      "grad_norm": 0.03511486575007439,
      "learning_rate": 6.150154258476315e-08,
      "loss": 0.0057,
      "step": 197
    },
    {
      "epoch": 0.029615226414388813,
      "grad_norm": 0.050071828067302704,
      "learning_rate": 2.7337132953697554e-08,
      "loss": 0.0035,
      "step": 198
    },
    {
      "epoch": 0.029764798264966533,
      "grad_norm": 0.06265247613191605,
      "learning_rate": 6.834750376549792e-09,
      "loss": 0.0025,
      "step": 199
    },
    {
      "epoch": 0.029914370115544254,
      "grad_norm": 0.007875422015786171,
      "learning_rate": 0.0,
      "loss": 0.0003,
      "step": 200
    },
    {
      "epoch": 0.029914370115544254,
      "eval_loss": 0.005237467121332884,
      "eval_runtime": 980.6804,
      "eval_samples_per_second": 11.483,
      "eval_steps_per_second": 2.871,
      "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": 5.1892179638943744e+17,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}