{
  "best_metric": 0.5850035548210144,
  "best_model_checkpoint": "miner_id_24/checkpoint-200",
  "epoch": 0.016763756757889443,
  "eval_steps": 200,
  "global_step": 200,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 8.381878378944722e-05,
      "grad_norm": 0.27757102251052856,
      "learning_rate": 6.666666666666667e-06,
      "loss": 0.9889,
      "step": 1
    },
    {
      "epoch": 8.381878378944722e-05,
      "eval_loss": 1.0523896217346191,
      "eval_runtime": 72.4023,
      "eval_samples_per_second": 13.259,
      "eval_steps_per_second": 6.63,
      "step": 1
    },
    {
      "epoch": 0.00016763756757889444,
      "grad_norm": 0.19584745168685913,
      "learning_rate": 1.3333333333333333e-05,
      "loss": 0.9186,
      "step": 2
    },
    {
      "epoch": 0.00025145635136834165,
      "grad_norm": 0.22289425134658813,
      "learning_rate": 2e-05,
      "loss": 1.1034,
      "step": 3
    },
    {
      "epoch": 0.0003352751351577889,
      "grad_norm": 0.2269897311925888,
      "learning_rate": 2.6666666666666667e-05,
      "loss": 1.0487,
      "step": 4
    },
    {
      "epoch": 0.00041909391894723606,
      "grad_norm": 0.21217933297157288,
      "learning_rate": 3.3333333333333335e-05,
      "loss": 1.055,
      "step": 5
    },
    {
      "epoch": 0.0005029127027366833,
      "grad_norm": 0.24146650731563568,
      "learning_rate": 4e-05,
      "loss": 1.0042,
      "step": 6
    },
    {
      "epoch": 0.0005867314865261305,
      "grad_norm": 0.23820246756076813,
      "learning_rate": 4.666666666666667e-05,
      "loss": 1.0763,
      "step": 7
    },
    {
      "epoch": 0.0006705502703155778,
      "grad_norm": 0.23663344979286194,
      "learning_rate": 5.333333333333333e-05,
      "loss": 1.0472,
      "step": 8
    },
    {
      "epoch": 0.0007543690541050249,
      "grad_norm": 0.23628108203411102,
      "learning_rate": 6e-05,
      "loss": 1.0014,
      "step": 9
    },
    {
      "epoch": 0.0008381878378944721,
      "grad_norm": 0.22541089355945587,
      "learning_rate": 6.666666666666667e-05,
      "loss": 0.9657,
      "step": 10
    },
    {
      "epoch": 0.0009220066216839194,
      "grad_norm": 0.23435266315937042,
      "learning_rate": 7.333333333333333e-05,
      "loss": 0.9257,
      "step": 11
    },
    {
      "epoch": 0.0010058254054733666,
      "grad_norm": 0.24410228431224823,
      "learning_rate": 8e-05,
      "loss": 0.9821,
      "step": 12
    },
    {
      "epoch": 0.0010896441892628138,
      "grad_norm": 0.30946725606918335,
      "learning_rate": 8.666666666666667e-05,
      "loss": 0.9895,
      "step": 13
    },
    {
      "epoch": 0.001173462973052261,
      "grad_norm": 0.30411282181739807,
      "learning_rate": 9.333333333333334e-05,
      "loss": 0.9322,
      "step": 14
    },
    {
      "epoch": 0.0012572817568417083,
      "grad_norm": 0.30061978101730347,
      "learning_rate": 0.0001,
      "loss": 0.9628,
      "step": 15
    },
    {
      "epoch": 0.0013411005406311555,
      "grad_norm": 0.3827131688594818,
      "learning_rate": 0.00010666666666666667,
      "loss": 0.9569,
      "step": 16
    },
    {
      "epoch": 0.0014249193244206028,
      "grad_norm": 0.34471532702445984,
      "learning_rate": 0.00011333333333333334,
      "loss": 0.9253,
      "step": 17
    },
    {
      "epoch": 0.0015087381082100498,
      "grad_norm": 0.33342617750167847,
      "learning_rate": 0.00012,
      "loss": 0.9488,
      "step": 18
    },
    {
      "epoch": 0.001592556891999497,
      "grad_norm": 0.4072156548500061,
      "learning_rate": 0.00012666666666666666,
      "loss": 0.9456,
      "step": 19
    },
    {
      "epoch": 0.0016763756757889442,
      "grad_norm": 0.3623020052909851,
      "learning_rate": 0.00013333333333333334,
      "loss": 0.8934,
      "step": 20
    },
    {
      "epoch": 0.0017601944595783915,
      "grad_norm": 0.36454543471336365,
      "learning_rate": 0.00014,
      "loss": 0.8892,
      "step": 21
    },
    {
      "epoch": 0.0018440132433678387,
      "grad_norm": 0.3363465964794159,
      "learning_rate": 0.00014666666666666666,
      "loss": 0.9094,
      "step": 22
    },
    {
      "epoch": 0.001927832027157286,
      "grad_norm": 0.391088604927063,
      "learning_rate": 0.00015333333333333334,
      "loss": 0.8786,
      "step": 23
    },
    {
      "epoch": 0.002011650810946733,
      "grad_norm": 0.35799694061279297,
      "learning_rate": 0.00016,
      "loss": 0.8913,
      "step": 24
    },
    {
      "epoch": 0.0020954695947361804,
      "grad_norm": 0.3244224190711975,
      "learning_rate": 0.0001666666666666667,
      "loss": 0.8457,
      "step": 25
    },
    {
      "epoch": 0.0021792883785256277,
      "grad_norm": 0.3201601803302765,
      "learning_rate": 0.00017333333333333334,
      "loss": 0.7892,
      "step": 26
    },
    {
      "epoch": 0.002263107162315075,
      "grad_norm": 0.3770645558834076,
      "learning_rate": 0.00018,
      "loss": 0.8746,
      "step": 27
    },
    {
      "epoch": 0.002346925946104522,
      "grad_norm": 0.3332349956035614,
      "learning_rate": 0.0001866666666666667,
      "loss": 0.8062,
      "step": 28
    },
    {
      "epoch": 0.0024307447298939694,
      "grad_norm": 0.36013785004615784,
      "learning_rate": 0.00019333333333333333,
      "loss": 0.859,
      "step": 29
    },
    {
      "epoch": 0.0025145635136834166,
      "grad_norm": 0.32501301169395447,
      "learning_rate": 0.0002,
      "loss": 0.8042,
      "step": 30
    },
    {
      "epoch": 0.002598382297472864,
      "grad_norm": 0.35549408197402954,
      "learning_rate": 0.00019999999961410007,
      "loss": 0.8141,
      "step": 31
    },
    {
      "epoch": 0.002682201081262311,
      "grad_norm": 0.30180633068084717,
      "learning_rate": 0.00019999999845640018,
      "loss": 0.7334,
      "step": 32
    },
    {
      "epoch": 0.0027660198650517583,
      "grad_norm": 0.3518891930580139,
      "learning_rate": 0.00019999999652690043,
      "loss": 0.7901,
      "step": 33
    },
    {
      "epoch": 0.0028498386488412055,
      "grad_norm": 0.315463125705719,
      "learning_rate": 0.00019999999382560077,
      "loss": 0.8001,
      "step": 34
    },
    {
      "epoch": 0.0029336574326306523,
      "grad_norm": 0.39683935046195984,
      "learning_rate": 0.00019999999035250125,
      "loss": 0.8298,
      "step": 35
    },
    {
      "epoch": 0.0030174762164200996,
      "grad_norm": 0.3712059557437897,
      "learning_rate": 0.0001999999861076019,
      "loss": 0.809,
      "step": 36
    },
    {
      "epoch": 0.003101295000209547,
      "grad_norm": 0.37395918369293213,
      "learning_rate": 0.00019999998109090274,
      "loss": 0.7571,
      "step": 37
    },
    {
      "epoch": 0.003185113783998994,
      "grad_norm": 0.36986619234085083,
      "learning_rate": 0.00019999997530240383,
      "loss": 0.7827,
      "step": 38
    },
    {
      "epoch": 0.0032689325677884413,
      "grad_norm": 0.33779916167259216,
      "learning_rate": 0.00019999996874210516,
      "loss": 0.7813,
      "step": 39
    },
    {
      "epoch": 0.0033527513515778885,
      "grad_norm": 0.4386044144630432,
      "learning_rate": 0.00019999996141000686,
      "loss": 0.7938,
      "step": 40
    },
    {
      "epoch": 0.0034365701353673357,
      "grad_norm": 0.37323451042175293,
      "learning_rate": 0.00019999995330610893,
      "loss": 0.7399,
      "step": 41
    },
    {
      "epoch": 0.003520388919156783,
      "grad_norm": 0.4099224805831909,
      "learning_rate": 0.00019999994443041145,
      "loss": 0.7335,
      "step": 42
    },
    {
      "epoch": 0.00360420770294623,
      "grad_norm": 0.3600141406059265,
      "learning_rate": 0.00019999993478291445,
      "loss": 0.7422,
      "step": 43
    },
    {
      "epoch": 0.0036880264867356774,
      "grad_norm": 0.3903872072696686,
      "learning_rate": 0.00019999992436361809,
      "loss": 0.7856,
      "step": 44
    },
    {
      "epoch": 0.0037718452705251247,
      "grad_norm": 0.396414190530777,
      "learning_rate": 0.0001999999131725224,
      "loss": 0.6654,
      "step": 45
    },
    {
      "epoch": 0.003855664054314572,
      "grad_norm": 0.400010883808136,
      "learning_rate": 0.00019999990120962743,
      "loss": 0.7255,
      "step": 46
    },
    {
      "epoch": 0.003939482838104019,
      "grad_norm": 0.44128134846687317,
      "learning_rate": 0.00019999988847493335,
      "loss": 0.6785,
      "step": 47
    },
    {
      "epoch": 0.004023301621893466,
      "grad_norm": 0.41837194561958313,
      "learning_rate": 0.0001999998749684402,
      "loss": 0.7781,
      "step": 48
    },
    {
      "epoch": 0.004107120405682913,
      "grad_norm": 0.41986000537872314,
      "learning_rate": 0.00019999986069014808,
      "loss": 0.7551,
      "step": 49
    },
    {
      "epoch": 0.004190939189472361,
      "grad_norm": 0.42051857709884644,
      "learning_rate": 0.00019999984564005719,
      "loss": 0.6863,
      "step": 50
    },
    {
      "epoch": 0.004274757973261808,
      "grad_norm": 0.45879051089286804,
      "learning_rate": 0.00019999982981816752,
      "loss": 0.7231,
      "step": 51
    },
    {
      "epoch": 0.004358576757051255,
      "grad_norm": 0.4096977710723877,
      "learning_rate": 0.00019999981322447926,
      "loss": 0.7251,
      "step": 52
    },
    {
      "epoch": 0.004442395540840702,
      "grad_norm": 0.3889429271221161,
      "learning_rate": 0.00019999979585899253,
      "loss": 0.705,
      "step": 53
    },
    {
      "epoch": 0.00452621432463015,
      "grad_norm": 0.4109675884246826,
      "learning_rate": 0.00019999977772170748,
      "loss": 0.8223,
      "step": 54
    },
    {
      "epoch": 0.004610033108419597,
      "grad_norm": 0.36757218837738037,
      "learning_rate": 0.00019999975881262422,
      "loss": 0.7199,
      "step": 55
    },
    {
      "epoch": 0.004693851892209044,
      "grad_norm": 0.354303777217865,
      "learning_rate": 0.00019999973913174292,
      "loss": 0.7307,
      "step": 56
    },
    {
      "epoch": 0.004777670675998491,
      "grad_norm": 0.35140958428382874,
      "learning_rate": 0.00019999971867906374,
      "loss": 0.6613,
      "step": 57
    },
    {
      "epoch": 0.004861489459787939,
      "grad_norm": 0.3868594765663147,
      "learning_rate": 0.00019999969745458675,
      "loss": 0.8173,
      "step": 58
    },
    {
      "epoch": 0.0049453082435773855,
      "grad_norm": 0.39044278860092163,
      "learning_rate": 0.00019999967545831224,
      "loss": 0.7112,
      "step": 59
    },
    {
      "epoch": 0.005029127027366833,
      "grad_norm": 0.3526187241077423,
      "learning_rate": 0.0001999996526902403,
      "loss": 0.6876,
      "step": 60
    },
    {
      "epoch": 0.00511294581115628,
      "grad_norm": 0.3618951439857483,
      "learning_rate": 0.00019999962915037114,
      "loss": 0.7278,
      "step": 61
    },
    {
      "epoch": 0.005196764594945728,
      "grad_norm": 0.36353206634521484,
      "learning_rate": 0.00019999960483870494,
      "loss": 0.7196,
      "step": 62
    },
    {
      "epoch": 0.0052805833787351745,
      "grad_norm": 0.3637101650238037,
      "learning_rate": 0.00019999957975524185,
      "loss": 0.7769,
      "step": 63
    },
    {
      "epoch": 0.005364402162524622,
      "grad_norm": 0.39588281512260437,
      "learning_rate": 0.0001999995538999821,
      "loss": 0.6826,
      "step": 64
    },
    {
      "epoch": 0.005448220946314069,
      "grad_norm": 0.34947100281715393,
      "learning_rate": 0.0001999995272729259,
      "loss": 0.6786,
      "step": 65
    },
    {
      "epoch": 0.005532039730103517,
      "grad_norm": 0.3472554385662079,
      "learning_rate": 0.00019999949987407342,
      "loss": 0.6916,
      "step": 66
    },
    {
      "epoch": 0.005615858513892963,
      "grad_norm": 0.39982104301452637,
      "learning_rate": 0.0001999994717034249,
      "loss": 0.7373,
      "step": 67
    },
    {
      "epoch": 0.005699677297682411,
      "grad_norm": 0.42642131447792053,
      "learning_rate": 0.00019999944276098052,
      "loss": 0.6841,
      "step": 68
    },
    {
      "epoch": 0.005783496081471858,
      "grad_norm": 0.4198484718799591,
      "learning_rate": 0.00019999941304674055,
      "loss": 0.6736,
      "step": 69
    },
    {
      "epoch": 0.005867314865261305,
      "grad_norm": 0.3833945393562317,
      "learning_rate": 0.0001999993825607052,
      "loss": 0.725,
      "step": 70
    },
    {
      "epoch": 0.005951133649050752,
      "grad_norm": 0.38403427600860596,
      "learning_rate": 0.0001999993513028747,
      "loss": 0.705,
      "step": 71
    },
    {
      "epoch": 0.006034952432840199,
      "grad_norm": 0.3781890273094177,
      "learning_rate": 0.00019999931927324927,
      "loss": 0.6423,
      "step": 72
    },
    {
      "epoch": 0.006118771216629647,
      "grad_norm": 0.3689814805984497,
      "learning_rate": 0.0001999992864718292,
      "loss": 0.712,
      "step": 73
    },
    {
      "epoch": 0.006202590000419094,
      "grad_norm": 0.3470766544342041,
      "learning_rate": 0.00019999925289861472,
      "loss": 0.68,
      "step": 74
    },
    {
      "epoch": 0.006286408784208541,
      "grad_norm": 0.3905583322048187,
      "learning_rate": 0.00019999921855360611,
      "loss": 0.7494,
      "step": 75
    },
    {
      "epoch": 0.006370227567997988,
      "grad_norm": 0.3560260236263275,
      "learning_rate": 0.0001999991834368036,
      "loss": 0.6565,
      "step": 76
    },
    {
      "epoch": 0.006454046351787436,
      "grad_norm": 0.4494559168815613,
      "learning_rate": 0.0001999991475482075,
      "loss": 0.8018,
      "step": 77
    },
    {
      "epoch": 0.0065378651355768825,
      "grad_norm": 0.4152557849884033,
      "learning_rate": 0.00019999911088781805,
      "loss": 0.6491,
      "step": 78
    },
    {
      "epoch": 0.00662168391936633,
      "grad_norm": 0.358479380607605,
      "learning_rate": 0.00019999907345563558,
      "loss": 0.5953,
      "step": 79
    },
    {
      "epoch": 0.006705502703155777,
      "grad_norm": 0.37004393339157104,
      "learning_rate": 0.0001999990352516603,
      "loss": 0.6361,
      "step": 80
    },
    {
      "epoch": 0.006789321486945225,
      "grad_norm": 0.3782244324684143,
      "learning_rate": 0.00019999899627589257,
      "loss": 0.6749,
      "step": 81
    },
    {
      "epoch": 0.0068731402707346715,
      "grad_norm": 0.4424068033695221,
      "learning_rate": 0.0001999989565283327,
      "loss": 0.8067,
      "step": 82
    },
    {
      "epoch": 0.006956959054524119,
      "grad_norm": 0.37774088978767395,
      "learning_rate": 0.00019999891600898094,
      "loss": 0.6129,
      "step": 83
    },
    {
      "epoch": 0.007040777838313566,
      "grad_norm": 0.38917186856269836,
      "learning_rate": 0.00019999887471783766,
      "loss": 0.7225,
      "step": 84
    },
    {
      "epoch": 0.007124596622103014,
      "grad_norm": 0.39635327458381653,
      "learning_rate": 0.00019999883265490312,
      "loss": 0.646,
      "step": 85
    },
    {
      "epoch": 0.00720841540589246,
      "grad_norm": 0.37512996792793274,
      "learning_rate": 0.0001999987898201777,
      "loss": 0.6986,
      "step": 86
    },
    {
      "epoch": 0.007292234189681908,
      "grad_norm": 0.3769257962703705,
      "learning_rate": 0.00019999874621366172,
      "loss": 0.7278,
      "step": 87
    },
    {
      "epoch": 0.007376052973471355,
      "grad_norm": 0.40142300724983215,
      "learning_rate": 0.0001999987018353555,
      "loss": 0.7329,
      "step": 88
    },
    {
      "epoch": 0.0074598717572608025,
      "grad_norm": 0.41919413208961487,
      "learning_rate": 0.00019999865668525937,
      "loss": 0.6644,
      "step": 89
    },
    {
      "epoch": 0.007543690541050249,
      "grad_norm": 0.389901340007782,
      "learning_rate": 0.0001999986107633737,
      "loss": 0.6515,
      "step": 90
    },
    {
      "epoch": 0.007627509324839697,
      "grad_norm": 0.400664746761322,
      "learning_rate": 0.00019999856406969886,
      "loss": 0.6257,
      "step": 91
    },
    {
      "epoch": 0.007711328108629144,
      "grad_norm": 0.3897579610347748,
      "learning_rate": 0.00019999851660423517,
      "loss": 0.6097,
      "step": 92
    },
    {
      "epoch": 0.007795146892418591,
      "grad_norm": 0.4384418725967407,
      "learning_rate": 0.000199998468366983,
      "loss": 0.6513,
      "step": 93
    },
    {
      "epoch": 0.007878965676208037,
      "grad_norm": 0.48361653089523315,
      "learning_rate": 0.00019999841935794277,
      "loss": 0.6687,
      "step": 94
    },
    {
      "epoch": 0.007962784459997485,
      "grad_norm": 0.4900784492492676,
      "learning_rate": 0.00019999836957711482,
      "loss": 0.6444,
      "step": 95
    },
    {
      "epoch": 0.008046603243786933,
      "grad_norm": 0.46883895993232727,
      "learning_rate": 0.00019999831902449953,
      "loss": 0.7507,
      "step": 96
    },
    {
      "epoch": 0.00813042202757638,
      "grad_norm": 0.4509626030921936,
      "learning_rate": 0.00019999826770009728,
      "loss": 0.6217,
      "step": 97
    },
    {
      "epoch": 0.008214240811365826,
      "grad_norm": 0.43415379524230957,
      "learning_rate": 0.00019999821560390854,
      "loss": 0.6334,
      "step": 98
    },
    {
      "epoch": 0.008298059595155274,
      "grad_norm": 0.40865573287010193,
      "learning_rate": 0.00019999816273593362,
      "loss": 0.6475,
      "step": 99
    },
    {
      "epoch": 0.008381878378944722,
      "grad_norm": 0.41777169704437256,
      "learning_rate": 0.000199998109096173,
      "loss": 0.6292,
      "step": 100
    },
    {
      "epoch": 0.00846569716273417,
      "grad_norm": 0.5066778063774109,
      "learning_rate": 0.00019999805468462706,
      "loss": 0.6657,
      "step": 101
    },
    {
      "epoch": 0.008549515946523615,
      "grad_norm": 0.4618004560470581,
      "learning_rate": 0.0001999979995012962,
      "loss": 0.6777,
      "step": 102
    },
    {
      "epoch": 0.008633334730313063,
      "grad_norm": 0.3739679455757141,
      "learning_rate": 0.00019999794354618087,
      "loss": 0.576,
      "step": 103
    },
    {
      "epoch": 0.00871715351410251,
      "grad_norm": 0.41847363114356995,
      "learning_rate": 0.0001999978868192815,
      "loss": 0.6138,
      "step": 104
    },
    {
      "epoch": 0.008800972297891958,
      "grad_norm": 0.5172164440155029,
      "learning_rate": 0.0001999978293205985,
      "loss": 0.6733,
      "step": 105
    },
    {
      "epoch": 0.008884791081681404,
      "grad_norm": 0.46301916241645813,
      "learning_rate": 0.0001999977710501324,
      "loss": 0.6609,
      "step": 106
    },
    {
      "epoch": 0.008968609865470852,
      "grad_norm": 0.3812422454357147,
      "learning_rate": 0.00019999771200788355,
      "loss": 0.6295,
      "step": 107
    },
    {
      "epoch": 0.0090524286492603,
      "grad_norm": 0.46059998869895935,
      "learning_rate": 0.00019999765219385246,
      "loss": 0.6627,
      "step": 108
    },
    {
      "epoch": 0.009136247433049747,
      "grad_norm": 0.4367014467716217,
      "learning_rate": 0.00019999759160803957,
      "loss": 0.673,
      "step": 109
    },
    {
      "epoch": 0.009220066216839193,
      "grad_norm": 0.36745861172676086,
      "learning_rate": 0.00019999753025044538,
      "loss": 0.6178,
      "step": 110
    },
    {
      "epoch": 0.00930388500062864,
      "grad_norm": 0.4328370988368988,
      "learning_rate": 0.00019999746812107033,
      "loss": 0.66,
      "step": 111
    },
    {
      "epoch": 0.009387703784418088,
      "grad_norm": 0.4689805209636688,
      "learning_rate": 0.0001999974052199149,
      "loss": 0.6913,
      "step": 112
    },
    {
      "epoch": 0.009471522568207536,
      "grad_norm": 0.41220545768737793,
      "learning_rate": 0.00019999734154697957,
      "loss": 0.7184,
      "step": 113
    },
    {
      "epoch": 0.009555341351996982,
      "grad_norm": 0.3851276636123657,
      "learning_rate": 0.00019999727710226487,
      "loss": 0.517,
      "step": 114
    },
    {
      "epoch": 0.00963916013578643,
      "grad_norm": 0.4229526221752167,
      "learning_rate": 0.00019999721188577126,
      "loss": 0.6139,
      "step": 115
    },
    {
      "epoch": 0.009722978919575877,
      "grad_norm": 0.4038490056991577,
      "learning_rate": 0.00019999714589749929,
      "loss": 0.6514,
      "step": 116
    },
    {
      "epoch": 0.009806797703365323,
      "grad_norm": 0.4235230088233948,
      "learning_rate": 0.00019999707913744938,
      "loss": 0.6682,
      "step": 117
    },
    {
      "epoch": 0.009890616487154771,
      "grad_norm": 0.42150190472602844,
      "learning_rate": 0.00019999701160562213,
      "loss": 0.7157,
      "step": 118
    },
    {
      "epoch": 0.009974435270944219,
      "grad_norm": 0.36696770787239075,
      "learning_rate": 0.00019999694330201804,
      "loss": 0.5452,
      "step": 119
    },
    {
      "epoch": 0.010058254054733666,
      "grad_norm": 0.4220931828022003,
      "learning_rate": 0.0001999968742266376,
      "loss": 0.6425,
      "step": 120
    },
    {
      "epoch": 0.010142072838523112,
      "grad_norm": 0.4050016403198242,
      "learning_rate": 0.0001999968043794814,
      "loss": 0.6318,
      "step": 121
    },
    {
      "epoch": 0.01022589162231256,
      "grad_norm": 0.4053823947906494,
      "learning_rate": 0.00019999673376054996,
      "loss": 0.6353,
      "step": 122
    },
    {
      "epoch": 0.010309710406102008,
      "grad_norm": 0.42942366003990173,
      "learning_rate": 0.00019999666236984376,
      "loss": 0.6268,
      "step": 123
    },
    {
      "epoch": 0.010393529189891455,
      "grad_norm": 0.46669450402259827,
      "learning_rate": 0.00019999659020736345,
      "loss": 0.6819,
      "step": 124
    },
    {
      "epoch": 0.010477347973680901,
      "grad_norm": 0.46410807967185974,
      "learning_rate": 0.00019999651727310955,
      "loss": 0.679,
      "step": 125
    },
    {
      "epoch": 0.010561166757470349,
      "grad_norm": 0.41605374217033386,
      "learning_rate": 0.00019999644356708261,
      "loss": 0.6749,
      "step": 126
    },
    {
      "epoch": 0.010644985541259797,
      "grad_norm": 0.3687427043914795,
      "learning_rate": 0.0001999963690892832,
      "loss": 0.6075,
      "step": 127
    },
    {
      "epoch": 0.010728804325049244,
      "grad_norm": 0.7310292720794678,
      "learning_rate": 0.00019999629383971192,
      "loss": 0.5929,
      "step": 128
    },
    {
      "epoch": 0.01081262310883869,
      "grad_norm": 0.37816864252090454,
      "learning_rate": 0.0001999962178183693,
      "loss": 0.5695,
      "step": 129
    },
    {
      "epoch": 0.010896441892628138,
      "grad_norm": 0.4322754144668579,
      "learning_rate": 0.00019999614102525598,
      "loss": 0.5907,
      "step": 130
    },
    {
      "epoch": 0.010980260676417586,
      "grad_norm": 0.4653779864311218,
      "learning_rate": 0.00019999606346037254,
      "loss": 0.655,
      "step": 131
    },
    {
      "epoch": 0.011064079460207033,
      "grad_norm": 0.4298158884048462,
      "learning_rate": 0.00019999598512371956,
      "loss": 0.6899,
      "step": 132
    },
    {
      "epoch": 0.011147898243996479,
      "grad_norm": 0.4481755495071411,
      "learning_rate": 0.00019999590601529766,
      "loss": 0.5979,
      "step": 133
    },
    {
      "epoch": 0.011231717027785927,
      "grad_norm": 0.38479623198509216,
      "learning_rate": 0.0001999958261351074,
      "loss": 0.6148,
      "step": 134
    },
    {
      "epoch": 0.011315535811575374,
      "grad_norm": 0.4027901589870453,
      "learning_rate": 0.0001999957454831495,
      "loss": 0.6186,
      "step": 135
    },
    {
      "epoch": 0.011399354595364822,
      "grad_norm": 0.40999603271484375,
      "learning_rate": 0.00019999566405942449,
      "loss": 0.6039,
      "step": 136
    },
    {
      "epoch": 0.011483173379154268,
      "grad_norm": 0.4183693528175354,
      "learning_rate": 0.00019999558186393305,
      "loss": 0.5818,
      "step": 137
    },
    {
      "epoch": 0.011566992162943716,
      "grad_norm": 0.4464079737663269,
      "learning_rate": 0.00019999549889667583,
      "loss": 0.7183,
      "step": 138
    },
    {
      "epoch": 0.011650810946733163,
      "grad_norm": 0.5179542303085327,
      "learning_rate": 0.00019999541515765336,
      "loss": 0.581,
      "step": 139
    },
    {
      "epoch": 0.01173462973052261,
      "grad_norm": 0.43612146377563477,
      "learning_rate": 0.0001999953306468664,
      "loss": 0.6107,
      "step": 140
    },
    {
      "epoch": 0.011818448514312057,
      "grad_norm": 0.49582237005233765,
      "learning_rate": 0.00019999524536431557,
      "loss": 0.6494,
      "step": 141
    },
    {
      "epoch": 0.011902267298101505,
      "grad_norm": 0.4569728374481201,
      "learning_rate": 0.00019999515931000154,
      "loss": 0.7132,
      "step": 142
    },
    {
      "epoch": 0.011986086081890952,
      "grad_norm": 0.42012691497802734,
      "learning_rate": 0.00019999507248392493,
      "loss": 0.6026,
      "step": 143
    },
    {
      "epoch": 0.012069904865680398,
      "grad_norm": 0.37710806727409363,
      "learning_rate": 0.00019999498488608645,
      "loss": 0.532,
      "step": 144
    },
    {
      "epoch": 0.012153723649469846,
      "grad_norm": 0.40027210116386414,
      "learning_rate": 0.00019999489651648678,
      "loss": 0.6026,
      "step": 145
    },
    {
      "epoch": 0.012237542433259294,
      "grad_norm": 0.40094059705734253,
      "learning_rate": 0.00019999480737512655,
      "loss": 0.6724,
      "step": 146
    },
    {
      "epoch": 0.012321361217048741,
      "grad_norm": 0.4241228401660919,
      "learning_rate": 0.00019999471746200652,
      "loss": 0.6257,
      "step": 147
    },
    {
      "epoch": 0.012405180000838187,
      "grad_norm": 0.4401513338088989,
      "learning_rate": 0.00019999462677712732,
      "loss": 0.6943,
      "step": 148
    },
    {
      "epoch": 0.012488998784627635,
      "grad_norm": 0.41752320528030396,
      "learning_rate": 0.00019999453532048967,
      "loss": 0.5822,
      "step": 149
    },
    {
      "epoch": 0.012572817568417083,
      "grad_norm": 0.40670299530029297,
      "learning_rate": 0.00019999444309209432,
      "loss": 0.5196,
      "step": 150
    },
    {
      "epoch": 0.01265663635220653,
      "grad_norm": 0.40677449107170105,
      "learning_rate": 0.00019999435009194195,
      "loss": 0.5703,
      "step": 151
    },
    {
      "epoch": 0.012740455135995976,
      "grad_norm": 0.41137218475341797,
      "learning_rate": 0.00019999425632003326,
      "loss": 0.6015,
      "step": 152
    },
    {
      "epoch": 0.012824273919785424,
      "grad_norm": 0.4242498576641083,
      "learning_rate": 0.000199994161776369,
      "loss": 0.5224,
      "step": 153
    },
    {
      "epoch": 0.012908092703574871,
      "grad_norm": 0.4747777581214905,
      "learning_rate": 0.00019999406646094986,
      "loss": 0.6646,
      "step": 154
    },
    {
      "epoch": 0.012991911487364319,
      "grad_norm": 0.49199265241622925,
      "learning_rate": 0.0001999939703737766,
      "loss": 0.6439,
      "step": 155
    },
    {
      "epoch": 0.013075730271153765,
      "grad_norm": 0.46028921008110046,
      "learning_rate": 0.00019999387351484998,
      "loss": 0.6672,
      "step": 156
    },
    {
      "epoch": 0.013159549054943213,
      "grad_norm": 0.4229322671890259,
      "learning_rate": 0.00019999377588417072,
      "loss": 0.6634,
      "step": 157
    },
    {
      "epoch": 0.01324336783873266,
      "grad_norm": 0.3744605779647827,
      "learning_rate": 0.0001999936774817396,
      "loss": 0.5383,
      "step": 158
    },
    {
      "epoch": 0.013327186622522108,
      "grad_norm": 0.4224749505519867,
      "learning_rate": 0.00019999357830755737,
      "loss": 0.5746,
      "step": 159
    },
    {
      "epoch": 0.013411005406311554,
      "grad_norm": 0.4154312312602997,
      "learning_rate": 0.00019999347836162476,
      "loss": 0.6082,
      "step": 160
    },
    {
      "epoch": 0.013494824190101002,
      "grad_norm": 0.3839002549648285,
      "learning_rate": 0.0001999933776439426,
      "loss": 0.5698,
      "step": 161
    },
    {
      "epoch": 0.01357864297389045,
      "grad_norm": 0.41232922673225403,
      "learning_rate": 0.00019999327615451162,
      "loss": 0.6699,
      "step": 162
    },
    {
      "epoch": 0.013662461757679895,
      "grad_norm": 0.42452681064605713,
      "learning_rate": 0.00019999317389333263,
      "loss": 0.5422,
      "step": 163
    },
    {
      "epoch": 0.013746280541469343,
      "grad_norm": 0.40243658423423767,
      "learning_rate": 0.00019999307086040644,
      "loss": 0.5516,
      "step": 164
    },
    {
      "epoch": 0.01383009932525879,
      "grad_norm": 0.4310331344604492,
      "learning_rate": 0.00019999296705573377,
      "loss": 0.63,
      "step": 165
    },
    {
      "epoch": 0.013913918109048238,
      "grad_norm": 0.4185257852077484,
      "learning_rate": 0.0001999928624793155,
      "loss": 0.5422,
      "step": 166
    },
    {
      "epoch": 0.013997736892837684,
      "grad_norm": 0.47764432430267334,
      "learning_rate": 0.0001999927571311524,
      "loss": 0.5868,
      "step": 167
    },
    {
      "epoch": 0.014081555676627132,
      "grad_norm": 0.4489617645740509,
      "learning_rate": 0.00019999265101124526,
      "loss": 0.5505,
      "step": 168
    },
    {
      "epoch": 0.01416537446041658,
      "grad_norm": 0.41629061102867126,
      "learning_rate": 0.000199992544119595,
      "loss": 0.6057,
      "step": 169
    },
    {
      "epoch": 0.014249193244206027,
      "grad_norm": 0.4056180417537689,
      "learning_rate": 0.00019999243645620228,
      "loss": 0.5226,
      "step": 170
    },
    {
      "epoch": 0.014333012027995473,
      "grad_norm": 0.6868446469306946,
      "learning_rate": 0.0001999923280210681,
      "loss": 0.5663,
      "step": 171
    },
    {
      "epoch": 0.01441683081178492,
      "grad_norm": 0.41823476552963257,
      "learning_rate": 0.00019999221881419316,
      "loss": 0.5507,
      "step": 172
    },
    {
      "epoch": 0.014500649595574368,
      "grad_norm": 0.4336549639701843,
      "learning_rate": 0.00019999210883557837,
      "loss": 0.7068,
      "step": 173
    },
    {
      "epoch": 0.014584468379363816,
      "grad_norm": 0.4319654703140259,
      "learning_rate": 0.0001999919980852246,
      "loss": 0.5919,
      "step": 174
    },
    {
      "epoch": 0.014668287163153262,
      "grad_norm": 0.41016024351119995,
      "learning_rate": 0.00019999188656313267,
      "loss": 0.6592,
      "step": 175
    },
    {
      "epoch": 0.01475210594694271,
      "grad_norm": 0.44406187534332275,
      "learning_rate": 0.00019999177426930346,
      "loss": 0.6662,
      "step": 176
    },
    {
      "epoch": 0.014835924730732157,
      "grad_norm": 0.4186304211616516,
      "learning_rate": 0.0001999916612037378,
      "loss": 0.6732,
      "step": 177
    },
    {
      "epoch": 0.014919743514521605,
      "grad_norm": 0.4186432957649231,
      "learning_rate": 0.0001999915473664366,
      "loss": 0.6145,
      "step": 178
    },
    {
      "epoch": 0.015003562298311051,
      "grad_norm": 0.39996975660324097,
      "learning_rate": 0.00019999143275740072,
      "loss": 0.5389,
      "step": 179
    },
    {
      "epoch": 0.015087381082100499,
      "grad_norm": 0.4699569344520569,
      "learning_rate": 0.00019999131737663103,
      "loss": 0.6019,
      "step": 180
    },
    {
      "epoch": 0.015171199865889946,
      "grad_norm": 0.40459325909614563,
      "learning_rate": 0.00019999120122412845,
      "loss": 0.6086,
      "step": 181
    },
    {
      "epoch": 0.015255018649679394,
      "grad_norm": 0.45147839188575745,
      "learning_rate": 0.0001999910842998939,
      "loss": 0.6694,
      "step": 182
    },
    {
      "epoch": 0.01533883743346884,
      "grad_norm": 0.4492567181587219,
      "learning_rate": 0.00019999096660392823,
      "loss": 0.5922,
      "step": 183
    },
    {
      "epoch": 0.015422656217258288,
      "grad_norm": 0.5045160055160522,
      "learning_rate": 0.00019999084813623235,
      "loss": 0.6584,
      "step": 184
    },
    {
      "epoch": 0.015506475001047735,
      "grad_norm": 0.4199374318122864,
      "learning_rate": 0.0001999907288968072,
      "loss": 0.6403,
      "step": 185
    },
    {
      "epoch": 0.015590293784837181,
      "grad_norm": 0.40507498383522034,
      "learning_rate": 0.00019999060888565372,
      "loss": 0.5457,
      "step": 186
    },
    {
      "epoch": 0.01567411256862663,
      "grad_norm": 0.45399683713912964,
      "learning_rate": 0.00019999048810277276,
      "loss": 0.6807,
      "step": 187
    },
    {
      "epoch": 0.015757931352416075,
      "grad_norm": 0.42870524525642395,
      "learning_rate": 0.00019999036654816534,
      "loss": 0.7152,
      "step": 188
    },
    {
      "epoch": 0.015841750136205524,
      "grad_norm": 0.4508127272129059,
      "learning_rate": 0.00019999024422183233,
      "loss": 0.6002,
      "step": 189
    },
    {
      "epoch": 0.01592556891999497,
      "grad_norm": 0.41447100043296814,
      "learning_rate": 0.00019999012112377473,
      "loss": 0.609,
      "step": 190
    },
    {
      "epoch": 0.01600938770378442,
      "grad_norm": 0.4508996307849884,
      "learning_rate": 0.00019998999725399347,
      "loss": 0.5942,
      "step": 191
    },
    {
      "epoch": 0.016093206487573865,
      "grad_norm": 0.4333980977535248,
      "learning_rate": 0.00019998987261248945,
      "loss": 0.5505,
      "step": 192
    },
    {
      "epoch": 0.01617702527136331,
      "grad_norm": 0.4588097035884857,
      "learning_rate": 0.00019998974719926372,
      "loss": 0.66,
      "step": 193
    },
    {
      "epoch": 0.01626084405515276,
      "grad_norm": 0.45392629504203796,
      "learning_rate": 0.0001999896210143172,
      "loss": 0.5844,
      "step": 194
    },
    {
      "epoch": 0.016344662838942207,
      "grad_norm": 0.4095288813114166,
      "learning_rate": 0.00019998949405765086,
      "loss": 0.5651,
      "step": 195
    },
    {
      "epoch": 0.016428481622731653,
      "grad_norm": 0.4155382513999939,
      "learning_rate": 0.0001999893663292657,
      "loss": 0.6008,
      "step": 196
    },
    {
      "epoch": 0.016512300406521102,
      "grad_norm": 0.42157071828842163,
      "learning_rate": 0.00019998923782916272,
      "loss": 0.5341,
      "step": 197
    },
    {
      "epoch": 0.016596119190310548,
      "grad_norm": 0.4294929504394531,
      "learning_rate": 0.00019998910855734288,
      "loss": 0.5335,
      "step": 198
    },
    {
      "epoch": 0.016679937974099997,
      "grad_norm": 0.49815112352371216,
      "learning_rate": 0.00019998897851380716,
      "loss": 0.5502,
      "step": 199
    },
    {
      "epoch": 0.016763756757889443,
      "grad_norm": 0.44708141684532166,
      "learning_rate": 0.00019998884769855662,
      "loss": 0.5398,
      "step": 200
    },
    {
      "epoch": 0.016763756757889443,
      "eval_loss": 0.5850035548210144,
      "eval_runtime": 72.573,
      "eval_samples_per_second": 13.228,
      "eval_steps_per_second": 6.614,
      "step": 200
    }
  ],
  "logging_steps": 1,
  "max_steps": 35790,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 3,
  "save_steps": 200,
  "stateful_callbacks": {
    "EarlyStoppingCallback": {
      "args": {
        "early_stopping_patience": 3,
        "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": false
      },
      "attributes": {}
    }
  },
  "total_flos": 1.31896902156288e+16,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}