{
  "best_metric": 2.660818836375256e-06,
  "best_model_checkpoint": "miner_id_24/checkpoint-200",
  "epoch": 0.4417753848277766,
  "eval_steps": 25,
  "global_step": 200,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0022088769241388833,
      "grad_norm": 17.61588478088379,
      "learning_rate": 1.25e-05,
      "loss": 3.9116,
      "step": 1
    },
    {
      "epoch": 0.0022088769241388833,
      "eval_loss": 5.86042594909668,
      "eval_runtime": 2.0601,
      "eval_samples_per_second": 24.27,
      "eval_steps_per_second": 6.31,
      "step": 1
    },
    {
      "epoch": 0.0044177538482777666,
      "grad_norm": 18.221654891967773,
      "learning_rate": 2.5e-05,
      "loss": 4.2731,
      "step": 2
    },
    {
      "epoch": 0.006626630772416649,
      "grad_norm": 18.73583984375,
      "learning_rate": 3.7500000000000003e-05,
      "loss": 4.2538,
      "step": 3
    },
    {
      "epoch": 0.008835507696555533,
      "grad_norm": 16.894182205200195,
      "learning_rate": 5e-05,
      "loss": 3.5849,
      "step": 4
    },
    {
      "epoch": 0.011044384620694415,
      "grad_norm": 13.671380996704102,
      "learning_rate": 6.25e-05,
      "loss": 2.4494,
      "step": 5
    },
    {
      "epoch": 0.013253261544833299,
      "grad_norm": 14.39706039428711,
      "learning_rate": 7.500000000000001e-05,
      "loss": 1.5397,
      "step": 6
    },
    {
      "epoch": 0.015462138468972183,
      "grad_norm": 36.43305587768555,
      "learning_rate": 8.75e-05,
      "loss": 4.0588,
      "step": 7
    },
    {
      "epoch": 0.017671015393111066,
      "grad_norm": 29.52732276916504,
      "learning_rate": 0.0001,
      "loss": 2.5498,
      "step": 8
    },
    {
      "epoch": 0.019879892317249948,
      "grad_norm": 15.871655464172363,
      "learning_rate": 9.999397620593029e-05,
      "loss": 0.7469,
      "step": 9
    },
    {
      "epoch": 0.02208876924138883,
      "grad_norm": 37.426918029785156,
      "learning_rate": 9.997590643643647e-05,
      "loss": 0.2828,
      "step": 10
    },
    {
      "epoch": 0.024297646165527716,
      "grad_norm": 38.68975830078125,
      "learning_rate": 9.994579552923277e-05,
      "loss": 0.4165,
      "step": 11
    },
    {
      "epoch": 0.026506523089666598,
      "grad_norm": 3.2423059940338135,
      "learning_rate": 9.990365154573717e-05,
      "loss": 0.0656,
      "step": 12
    },
    {
      "epoch": 0.02871540001380548,
      "grad_norm": 21.096725463867188,
      "learning_rate": 9.984948576891312e-05,
      "loss": 1.0799,
      "step": 13
    },
    {
      "epoch": 0.030924276937944365,
      "grad_norm": 10.848109245300293,
      "learning_rate": 9.978331270024886e-05,
      "loss": 0.4541,
      "step": 14
    },
    {
      "epoch": 0.033133153862083244,
      "grad_norm": 3.0925045013427734,
      "learning_rate": 9.9705150055875e-05,
      "loss": 0.0921,
      "step": 15
    },
    {
      "epoch": 0.03534203078622213,
      "grad_norm": 0.7270008325576782,
      "learning_rate": 9.961501876182148e-05,
      "loss": 0.012,
      "step": 16
    },
    {
      "epoch": 0.037550907710361014,
      "grad_norm": 2.127373695373535,
      "learning_rate": 9.951294294841516e-05,
      "loss": 0.006,
      "step": 17
    },
    {
      "epoch": 0.039759784634499896,
      "grad_norm": 13.903672218322754,
      "learning_rate": 9.939894994381957e-05,
      "loss": 0.0372,
      "step": 18
    },
    {
      "epoch": 0.04196866155863878,
      "grad_norm": 0.047538336366415024,
      "learning_rate": 9.927307026671848e-05,
      "loss": 0.0005,
      "step": 19
    },
    {
      "epoch": 0.04417753848277766,
      "grad_norm": 0.12976495921611786,
      "learning_rate": 9.913533761814537e-05,
      "loss": 0.0015,
      "step": 20
    },
    {
      "epoch": 0.04638641540691654,
      "grad_norm": 0.053914595395326614,
      "learning_rate": 9.898578887246075e-05,
      "loss": 0.0006,
      "step": 21
    },
    {
      "epoch": 0.04859529233105543,
      "grad_norm": 0.016516996547579765,
      "learning_rate": 9.882446406748002e-05,
      "loss": 0.0002,
      "step": 22
    },
    {
      "epoch": 0.05080416925519431,
      "grad_norm": 0.004742575343698263,
      "learning_rate": 9.865140639375449e-05,
      "loss": 0.0,
      "step": 23
    },
    {
      "epoch": 0.053013046179333195,
      "grad_norm": 0.001722239889204502,
      "learning_rate": 9.846666218300807e-05,
      "loss": 0.0,
      "step": 24
    },
    {
      "epoch": 0.05522192310347208,
      "grad_norm": 0.0011573476949706674,
      "learning_rate": 9.827028089573329e-05,
      "loss": 0.0,
      "step": 25
    },
    {
      "epoch": 0.05522192310347208,
      "eval_loss": 0.22512628138065338,
      "eval_runtime": 2.0717,
      "eval_samples_per_second": 24.135,
      "eval_steps_per_second": 6.275,
      "step": 25
    },
    {
      "epoch": 0.05743080002761096,
      "grad_norm": 0.7982810735702515,
      "learning_rate": 9.80623151079494e-05,
      "loss": 0.002,
      "step": 26
    },
    {
      "epoch": 0.05963967695174984,
      "grad_norm": 0.04265284910798073,
      "learning_rate": 9.78428204971266e-05,
      "loss": 0.0005,
      "step": 27
    },
    {
      "epoch": 0.06184855387588873,
      "grad_norm": 0.02398202195763588,
      "learning_rate": 9.761185582727977e-05,
      "loss": 0.0003,
      "step": 28
    },
    {
      "epoch": 0.06405743080002761,
      "grad_norm": 0.020716844126582146,
      "learning_rate": 9.736948293323593e-05,
      "loss": 0.0003,
      "step": 29
    },
    {
      "epoch": 0.06626630772416649,
      "grad_norm": 0.012970969080924988,
      "learning_rate": 9.711576670407965e-05,
      "loss": 0.0002,
      "step": 30
    },
    {
      "epoch": 0.06847518464830538,
      "grad_norm": 0.0036041405983269215,
      "learning_rate": 9.685077506578055e-05,
      "loss": 0.0,
      "step": 31
    },
    {
      "epoch": 0.07068406157244427,
      "grad_norm": 0.0019516213797032833,
      "learning_rate": 9.657457896300791e-05,
      "loss": 0.0,
      "step": 32
    },
    {
      "epoch": 0.07289293849658314,
      "grad_norm": 0.0024989373050630093,
      "learning_rate": 9.62872523401371e-05,
      "loss": 0.0,
      "step": 33
    },
    {
      "epoch": 0.07510181542072203,
      "grad_norm": 0.002753888489678502,
      "learning_rate": 9.598887212145291e-05,
      "loss": 0.0,
      "step": 34
    },
    {
      "epoch": 0.0773106923448609,
      "grad_norm": 0.0028842987958341837,
      "learning_rate": 9.567951819055496e-05,
      "loss": 0.0,
      "step": 35
    },
    {
      "epoch": 0.07951956926899979,
      "grad_norm": 0.0026685006450861692,
      "learning_rate": 9.535927336897098e-05,
      "loss": 0.0,
      "step": 36
    },
    {
      "epoch": 0.08172844619313868,
      "grad_norm": 0.002319728024303913,
      "learning_rate": 9.502822339398353e-05,
      "loss": 0.0,
      "step": 37
    },
    {
      "epoch": 0.08393732311727756,
      "grad_norm": 0.0013683955185115337,
      "learning_rate": 9.468645689567598e-05,
      "loss": 0.0,
      "step": 38
    },
    {
      "epoch": 0.08614620004141645,
      "grad_norm": 0.007890756241977215,
      "learning_rate": 9.433406537320415e-05,
      "loss": 0.0,
      "step": 39
    },
    {
      "epoch": 0.08835507696555532,
      "grad_norm": 0.005061345640569925,
      "learning_rate": 9.397114317029975e-05,
      "loss": 0.0,
      "step": 40
    },
    {
      "epoch": 0.09056395388969421,
      "grad_norm": 0.0023479792289435863,
      "learning_rate": 9.359778745001225e-05,
      "loss": 0.0,
      "step": 41
    },
    {
      "epoch": 0.09277283081383308,
      "grad_norm": 0.0018866774626076221,
      "learning_rate": 9.321409816869605e-05,
      "loss": 0.0,
      "step": 42
    },
    {
      "epoch": 0.09498170773797197,
      "grad_norm": 0.0013167414581403136,
      "learning_rate": 9.282017804924972e-05,
      "loss": 0.0,
      "step": 43
    },
    {
      "epoch": 0.09719058466211086,
      "grad_norm": 0.07475938647985458,
      "learning_rate": 9.241613255361455e-05,
      "loss": 0.0001,
      "step": 44
    },
    {
      "epoch": 0.09939946158624974,
      "grad_norm": 0.0007279085111804307,
      "learning_rate": 9.200206985453987e-05,
      "loss": 0.0,
      "step": 45
    },
    {
      "epoch": 0.10160833851038863,
      "grad_norm": 0.0006586903473362327,
      "learning_rate": 9.157810080662269e-05,
      "loss": 0.0,
      "step": 46
    },
    {
      "epoch": 0.1038172154345275,
      "grad_norm": 0.0005882774712517858,
      "learning_rate": 9.114433891662902e-05,
      "loss": 0.0,
      "step": 47
    },
    {
      "epoch": 0.10602609235866639,
      "grad_norm": 0.0005312666180543602,
      "learning_rate": 9.070090031310558e-05,
      "loss": 0.0,
      "step": 48
    },
    {
      "epoch": 0.10823496928280528,
      "grad_norm": 0.0004986180574633181,
      "learning_rate": 9.024790371528927e-05,
      "loss": 0.0,
      "step": 49
    },
    {
      "epoch": 0.11044384620694415,
      "grad_norm": 0.0004686967877205461,
      "learning_rate": 8.978547040132317e-05,
      "loss": 0.0,
      "step": 50
    },
    {
      "epoch": 0.11044384620694415,
      "eval_loss": 6.856966138002463e-06,
      "eval_runtime": 2.084,
      "eval_samples_per_second": 23.992,
      "eval_steps_per_second": 6.238,
      "step": 50
    },
    {
      "epoch": 0.11265272313108304,
      "grad_norm": 0.00035957881482318044,
      "learning_rate": 8.931372417578747e-05,
      "loss": 0.0,
      "step": 51
    },
    {
      "epoch": 0.11486160005522192,
      "grad_norm": 0.0005644855555146933,
      "learning_rate": 8.883279133655399e-05,
      "loss": 0.0,
      "step": 52
    },
    {
      "epoch": 0.11707047697936081,
      "grad_norm": 0.000498141860589385,
      "learning_rate": 8.834280064097317e-05,
      "loss": 0.0,
      "step": 53
    },
    {
      "epoch": 0.11927935390349968,
      "grad_norm": 0.0004631740739569068,
      "learning_rate": 8.78438832714026e-05,
      "loss": 0.0,
      "step": 54
    },
    {
      "epoch": 0.12148823082763857,
      "grad_norm": 0.0005917078233323991,
      "learning_rate": 8.733617280008642e-05,
      "loss": 0.0,
      "step": 55
    },
    {
      "epoch": 0.12369710775177746,
      "grad_norm": 0.0012398248072713614,
      "learning_rate": 8.681980515339464e-05,
      "loss": 0.0,
      "step": 56
    },
    {
      "epoch": 0.12590598467591635,
      "grad_norm": 0.00034377642441540956,
      "learning_rate": 8.629491857543253e-05,
      "loss": 0.0,
      "step": 57
    },
    {
      "epoch": 0.12811486160005522,
      "grad_norm": 0.0002728489344008267,
      "learning_rate": 8.57616535910292e-05,
      "loss": 0.0,
      "step": 58
    },
    {
      "epoch": 0.1303237385241941,
      "grad_norm": 0.0002754317538347095,
      "learning_rate": 8.522015296811584e-05,
      "loss": 0.0,
      "step": 59
    },
    {
      "epoch": 0.13253261544833297,
      "grad_norm": 0.0002577640407253057,
      "learning_rate": 8.467056167950311e-05,
      "loss": 0.0,
      "step": 60
    },
    {
      "epoch": 0.13474149237247188,
      "grad_norm": 0.00025405758060514927,
      "learning_rate": 8.411302686406859e-05,
      "loss": 0.0,
      "step": 61
    },
    {
      "epoch": 0.13695036929661075,
      "grad_norm": 0.0002456019283272326,
      "learning_rate": 8.354769778736406e-05,
      "loss": 0.0,
      "step": 62
    },
    {
      "epoch": 0.13915924622074963,
      "grad_norm": 0.0002701326156966388,
      "learning_rate": 8.29747258016535e-05,
      "loss": 0.0,
      "step": 63
    },
    {
      "epoch": 0.14136812314488853,
      "grad_norm": 0.0004698407428804785,
      "learning_rate": 8.239426430539243e-05,
      "loss": 0.0,
      "step": 64
    },
    {
      "epoch": 0.1435770000690274,
      "grad_norm": 0.00043744893628172576,
      "learning_rate": 8.180646870215952e-05,
      "loss": 0.0,
      "step": 65
    },
    {
      "epoch": 0.14578587699316628,
      "grad_norm": 0.0004982824320904911,
      "learning_rate": 8.12114963590511e-05,
      "loss": 0.0,
      "step": 66
    },
    {
      "epoch": 0.14799475391730518,
      "grad_norm": 0.0004062750958837569,
      "learning_rate": 8.060950656455043e-05,
      "loss": 0.0,
      "step": 67
    },
    {
      "epoch": 0.15020363084144406,
      "grad_norm": 0.00123576819896698,
      "learning_rate": 8.000066048588211e-05,
      "loss": 0.0,
      "step": 68
    },
    {
      "epoch": 0.15241250776558293,
      "grad_norm": 0.0007974767941050231,
      "learning_rate": 7.938512112586383e-05,
      "loss": 0.0,
      "step": 69
    },
    {
      "epoch": 0.1546213846897218,
      "grad_norm": 0.0001897720358101651,
      "learning_rate": 7.876305327926657e-05,
      "loss": 0.0,
      "step": 70
    },
    {
      "epoch": 0.1568302616138607,
      "grad_norm": 0.0001893111621029675,
      "learning_rate": 7.813462348869497e-05,
      "loss": 0.0,
      "step": 71
    },
    {
      "epoch": 0.15903913853799959,
      "grad_norm": 0.00018786548753269017,
      "learning_rate": 7.75e-05,
      "loss": 0.0,
      "step": 72
    },
    {
      "epoch": 0.16124801546213846,
      "grad_norm": 0.00018544185149949044,
      "learning_rate": 7.68593527172353e-05,
      "loss": 0.0,
      "step": 73
    },
    {
      "epoch": 0.16345689238627736,
      "grad_norm": 0.00018172743148170412,
      "learning_rate": 7.62128531571699e-05,
      "loss": 0.0,
      "step": 74
    },
    {
      "epoch": 0.16566576931041624,
      "grad_norm": 0.0001720397121971473,
      "learning_rate": 7.556067440336894e-05,
      "loss": 0.0,
      "step": 75
    },
    {
      "epoch": 0.16566576931041624,
      "eval_loss": 4.231893854012014e-06,
      "eval_runtime": 2.1042,
      "eval_samples_per_second": 23.762,
      "eval_steps_per_second": 6.178,
      "step": 75
    },
    {
      "epoch": 0.1678746462345551,
      "grad_norm": 0.0003285811108071357,
      "learning_rate": 7.490299105985507e-05,
      "loss": 0.0,
      "step": 76
    },
    {
      "epoch": 0.170083523158694,
      "grad_norm": 0.00037658450310118496,
      "learning_rate": 7.42399792043627e-05,
      "loss": 0.0,
      "step": 77
    },
    {
      "epoch": 0.1722924000828329,
      "grad_norm": 0.00041075507760979235,
      "learning_rate": 7.357181634119777e-05,
      "loss": 0.0,
      "step": 78
    },
    {
      "epoch": 0.17450127700697177,
      "grad_norm": 0.0002939265687018633,
      "learning_rate": 7.28986813537155e-05,
      "loss": 0.0,
      "step": 79
    },
    {
      "epoch": 0.17671015393111064,
      "grad_norm": 0.00039604472112841904,
      "learning_rate": 7.222075445642904e-05,
      "loss": 0.0,
      "step": 80
    },
    {
      "epoch": 0.17891903085524954,
      "grad_norm": 0.0007199989049695432,
      "learning_rate": 7.153821714676166e-05,
      "loss": 0.0,
      "step": 81
    },
    {
      "epoch": 0.18112790777938842,
      "grad_norm": 0.0003389615740161389,
      "learning_rate": 7.085125215645552e-05,
      "loss": 0.0,
      "step": 82
    },
    {
      "epoch": 0.1833367847035273,
      "grad_norm": 0.00015800297842361033,
      "learning_rate": 7.01600434026499e-05,
      "loss": 0.0,
      "step": 83
    },
    {
      "epoch": 0.18554566162766617,
      "grad_norm": 0.00016026933735702187,
      "learning_rate": 6.946477593864228e-05,
      "loss": 0.0,
      "step": 84
    },
    {
      "epoch": 0.18775453855180507,
      "grad_norm": 0.00015380079275928438,
      "learning_rate": 6.876563590434491e-05,
      "loss": 0.0,
      "step": 85
    },
    {
      "epoch": 0.18996341547594395,
      "grad_norm": 0.00014766880485694855,
      "learning_rate": 6.80628104764508e-05,
      "loss": 0.0,
      "step": 86
    },
    {
      "epoch": 0.19217229240008282,
      "grad_norm": 0.00014809212007094175,
      "learning_rate": 6.735648781832196e-05,
      "loss": 0.0,
      "step": 87
    },
    {
      "epoch": 0.19438116932422173,
      "grad_norm": 0.00012480569421313703,
      "learning_rate": 6.664685702961344e-05,
      "loss": 0.0,
      "step": 88
    },
    {
      "epoch": 0.1965900462483606,
      "grad_norm": 0.000344978179782629,
      "learning_rate": 6.593410809564689e-05,
      "loss": 0.0,
      "step": 89
    },
    {
      "epoch": 0.19879892317249948,
      "grad_norm": 0.00035067732096649706,
      "learning_rate": 6.52184318365468e-05,
      "loss": 0.0,
      "step": 90
    },
    {
      "epoch": 0.20100780009663838,
      "grad_norm": 0.00028731199563480914,
      "learning_rate": 6.450001985615342e-05,
      "loss": 0.0,
      "step": 91
    },
    {
      "epoch": 0.20321667702077725,
      "grad_norm": 0.0003451658121775836,
      "learning_rate": 6.377906449072578e-05,
      "loss": 0.0,
      "step": 92
    },
    {
      "epoch": 0.20542555394491613,
      "grad_norm": 0.0005577579722739756,
      "learning_rate": 6.305575875744848e-05,
      "loss": 0.0,
      "step": 93
    },
    {
      "epoch": 0.207634430869055,
      "grad_norm": 0.0003858502604998648,
      "learning_rate": 6.23302963027565e-05,
      "loss": 0.0,
      "step": 94
    },
    {
      "epoch": 0.2098433077931939,
      "grad_norm": 0.00013492356811184436,
      "learning_rate": 6.160287135049127e-05,
      "loss": 0.0,
      "step": 95
    },
    {
      "epoch": 0.21205218471733278,
      "grad_norm": 0.00013036909513175488,
      "learning_rate": 6.087367864990233e-05,
      "loss": 0.0,
      "step": 96
    },
    {
      "epoch": 0.21426106164147166,
      "grad_norm": 0.00013071863213554025,
      "learning_rate": 6.01429134235081e-05,
      "loss": 0.0,
      "step": 97
    },
    {
      "epoch": 0.21646993856561056,
      "grad_norm": 0.00013250780466478318,
      "learning_rate": 5.941077131483025e-05,
      "loss": 0.0,
      "step": 98
    },
    {
      "epoch": 0.21867881548974943,
      "grad_norm": 0.00012893717212136835,
      "learning_rate": 5.867744833601507e-05,
      "loss": 0.0,
      "step": 99
    },
    {
      "epoch": 0.2208876924138883,
      "grad_norm": 0.00012246635742485523,
      "learning_rate": 5.794314081535644e-05,
      "loss": 0.0,
      "step": 100
    },
    {
      "epoch": 0.2208876924138883,
      "eval_loss": 3.5253201531304512e-06,
      "eval_runtime": 2.1031,
      "eval_samples_per_second": 23.775,
      "eval_steps_per_second": 6.181,
      "step": 100
    },
    {
      "epoch": 0.22309656933802718,
      "grad_norm": 0.000191736122360453,
      "learning_rate": 5.720804534473382e-05,
      "loss": 0.0,
      "step": 101
    },
    {
      "epoch": 0.2253054462621661,
      "grad_norm": 0.0002980089630000293,
      "learning_rate": 5.6472358726979935e-05,
      "loss": 0.0,
      "step": 102
    },
    {
      "epoch": 0.22751432318630496,
      "grad_norm": 0.0003073852858506143,
      "learning_rate": 5.5736277923191916e-05,
      "loss": 0.0,
      "step": 103
    },
    {
      "epoch": 0.22972320011044384,
      "grad_norm": 0.00027709436835721135,
      "learning_rate": 5.500000000000001e-05,
      "loss": 0.0,
      "step": 104
    },
    {
      "epoch": 0.23193207703458274,
      "grad_norm": 0.00034520094050094485,
      "learning_rate": 5.42637220768081e-05,
      "loss": 0.0,
      "step": 105
    },
    {
      "epoch": 0.23414095395872161,
      "grad_norm": 0.0005847822758369148,
      "learning_rate": 5.352764127302008e-05,
      "loss": 0.0,
      "step": 106
    },
    {
      "epoch": 0.2363498308828605,
      "grad_norm": 0.00017146494064945728,
      "learning_rate": 5.27919546552662e-05,
      "loss": 0.0,
      "step": 107
    },
    {
      "epoch": 0.23855870780699936,
      "grad_norm": 0.00011689545499393716,
      "learning_rate": 5.205685918464356e-05,
      "loss": 0.0,
      "step": 108
    },
    {
      "epoch": 0.24076758473113827,
      "grad_norm": 0.00011620977602433413,
      "learning_rate": 5.1322551663984955e-05,
      "loss": 0.0,
      "step": 109
    },
    {
      "epoch": 0.24297646165527714,
      "grad_norm": 0.00011741516209440306,
      "learning_rate": 5.058922868516978e-05,
      "loss": 0.0,
      "step": 110
    },
    {
      "epoch": 0.24518533857941602,
      "grad_norm": 0.00011821599036920816,
      "learning_rate": 4.985708657649191e-05,
      "loss": 0.0,
      "step": 111
    },
    {
      "epoch": 0.24739421550355492,
      "grad_norm": 0.00011795986938523129,
      "learning_rate": 4.912632135009769e-05,
      "loss": 0.0,
      "step": 112
    },
    {
      "epoch": 0.2496030924276938,
      "grad_norm": 0.00014575726527255028,
      "learning_rate": 4.839712864950873e-05,
      "loss": 0.0,
      "step": 113
    },
    {
      "epoch": 0.2518119693518327,
      "grad_norm": 0.00030223472276702523,
      "learning_rate": 4.7669703697243516e-05,
      "loss": 0.0,
      "step": 114
    },
    {
      "epoch": 0.25402084627597155,
      "grad_norm": 0.0002797936904244125,
      "learning_rate": 4.6944241242551546e-05,
      "loss": 0.0,
      "step": 115
    },
    {
      "epoch": 0.25622972320011045,
      "grad_norm": 0.0002620798768475652,
      "learning_rate": 4.6220935509274235e-05,
      "loss": 0.0,
      "step": 116
    },
    {
      "epoch": 0.25843860012424935,
      "grad_norm": 0.00028032332193106413,
      "learning_rate": 4.5499980143846564e-05,
      "loss": 0.0,
      "step": 117
    },
    {
      "epoch": 0.2606474770483882,
      "grad_norm": 0.0003947988443542272,
      "learning_rate": 4.478156816345321e-05,
      "loss": 0.0,
      "step": 118
    },
    {
      "epoch": 0.2628563539725271,
      "grad_norm": 0.00045703398063778877,
      "learning_rate": 4.406589190435313e-05,
      "loss": 0.0,
      "step": 119
    },
    {
      "epoch": 0.26506523089666595,
      "grad_norm": 0.0001099837027140893,
      "learning_rate": 4.3353142970386564e-05,
      "loss": 0.0,
      "step": 120
    },
    {
      "epoch": 0.26727410782080485,
      "grad_norm": 0.00010697261313907802,
      "learning_rate": 4.2643512181678056e-05,
      "loss": 0.0,
      "step": 121
    },
    {
      "epoch": 0.26948298474494375,
      "grad_norm": 0.0001075834225048311,
      "learning_rate": 4.19371895235492e-05,
      "loss": 0.0,
      "step": 122
    },
    {
      "epoch": 0.2716918616690826,
      "grad_norm": 0.00010644174471963197,
      "learning_rate": 4.12343640956551e-05,
      "loss": 0.0,
      "step": 123
    },
    {
      "epoch": 0.2739007385932215,
      "grad_norm": 0.00010687617032090202,
      "learning_rate": 4.053522406135775e-05,
      "loss": 0.0,
      "step": 124
    },
    {
      "epoch": 0.2761096155173604,
      "grad_norm": 0.00010714936070144176,
      "learning_rate": 3.98399565973501e-05,
      "loss": 0.0,
      "step": 125
    },
    {
      "epoch": 0.2761096155173604,
      "eval_loss": 3.0905191579222446e-06,
      "eval_runtime": 2.0999,
      "eval_samples_per_second": 23.81,
      "eval_steps_per_second": 6.191,
      "step": 125
    },
    {
      "epoch": 0.27831849244149925,
      "grad_norm": 0.0002063347928924486,
      "learning_rate": 3.9148747843544495e-05,
      "loss": 0.0,
      "step": 126
    },
    {
      "epoch": 0.28052736936563816,
      "grad_norm": 0.00025974729214794934,
      "learning_rate": 3.846178285323835e-05,
      "loss": 0.0,
      "step": 127
    },
    {
      "epoch": 0.28273624628977706,
      "grad_norm": 0.00024177682644221932,
      "learning_rate": 3.777924554357096e-05,
      "loss": 0.0,
      "step": 128
    },
    {
      "epoch": 0.2849451232139159,
      "grad_norm": 0.0002588094212114811,
      "learning_rate": 3.710131864628451e-05,
      "loss": 0.0,
      "step": 129
    },
    {
      "epoch": 0.2871540001380548,
      "grad_norm": 0.0002662424521986395,
      "learning_rate": 3.642818365880224e-05,
      "loss": 0.0,
      "step": 130
    },
    {
      "epoch": 0.2893628770621937,
      "grad_norm": 0.0004572535108309239,
      "learning_rate": 3.576002079563732e-05,
      "loss": 0.0,
      "step": 131
    },
    {
      "epoch": 0.29157175398633256,
      "grad_norm": 0.00027820674586109817,
      "learning_rate": 3.509700894014496e-05,
      "loss": 0.0,
      "step": 132
    },
    {
      "epoch": 0.29378063091047146,
      "grad_norm": 0.00010199982352787629,
      "learning_rate": 3.443932559663107e-05,
      "loss": 0.0,
      "step": 133
    },
    {
      "epoch": 0.29598950783461037,
      "grad_norm": 0.00010178149386774749,
      "learning_rate": 3.378714684283011e-05,
      "loss": 0.0,
      "step": 134
    },
    {
      "epoch": 0.2981983847587492,
      "grad_norm": 0.00010338863648939878,
      "learning_rate": 3.31406472827647e-05,
      "loss": 0.0,
      "step": 135
    },
    {
      "epoch": 0.3004072616828881,
      "grad_norm": 0.0001027277103275992,
      "learning_rate": 3.250000000000001e-05,
      "loss": 0.0,
      "step": 136
    },
    {
      "epoch": 0.30261613860702696,
      "grad_norm": 0.00010317438864149153,
      "learning_rate": 3.186537651130503e-05,
      "loss": 0.0,
      "step": 137
    },
    {
      "epoch": 0.30482501553116587,
      "grad_norm": 0.00016677897656336427,
      "learning_rate": 3.123694672073344e-05,
      "loss": 0.0,
      "step": 138
    },
    {
      "epoch": 0.30703389245530477,
      "grad_norm": 0.00022237653320189565,
      "learning_rate": 3.061487887413619e-05,
      "loss": 0.0,
      "step": 139
    },
    {
      "epoch": 0.3092427693794436,
      "grad_norm": 0.00023152329958975315,
      "learning_rate": 2.9999339514117912e-05,
      "loss": 0.0,
      "step": 140
    },
    {
      "epoch": 0.3114516463035825,
      "grad_norm": 0.00022528883710037917,
      "learning_rate": 2.9390493435449572e-05,
      "loss": 0.0,
      "step": 141
    },
    {
      "epoch": 0.3136605232277214,
      "grad_norm": 0.00024947745259851217,
      "learning_rate": 2.8788503640948912e-05,
      "loss": 0.0,
      "step": 142
    },
    {
      "epoch": 0.31586940015186027,
      "grad_norm": 0.00043007542262785137,
      "learning_rate": 2.8193531297840503e-05,
      "loss": 0.0,
      "step": 143
    },
    {
      "epoch": 0.31807827707599917,
      "grad_norm": 0.00035726267378777266,
      "learning_rate": 2.760573569460757e-05,
      "loss": 0.0,
      "step": 144
    },
    {
      "epoch": 0.3202871540001381,
      "grad_norm": 9.570374095346779e-05,
      "learning_rate": 2.702527419834653e-05,
      "loss": 0.0,
      "step": 145
    },
    {
      "epoch": 0.3224960309242769,
      "grad_norm": 9.726483403937891e-05,
      "learning_rate": 2.645230221263596e-05,
      "loss": 0.0,
      "step": 146
    },
    {
      "epoch": 0.3247049078484158,
      "grad_norm": 9.980611503124237e-05,
      "learning_rate": 2.5886973135931425e-05,
      "loss": 0.0,
      "step": 147
    },
    {
      "epoch": 0.3269137847725547,
      "grad_norm": 9.672047599451616e-05,
      "learning_rate": 2.53294383204969e-05,
      "loss": 0.0,
      "step": 148
    },
    {
      "epoch": 0.3291226616966936,
      "grad_norm": 9.55902723944746e-05,
      "learning_rate": 2.4779847031884175e-05,
      "loss": 0.0,
      "step": 149
    },
    {
      "epoch": 0.3313315386208325,
      "grad_norm": 9.5816605607979e-05,
      "learning_rate": 2.423834640897079e-05,
      "loss": 0.0,
      "step": 150
    },
    {
      "epoch": 0.3313315386208325,
      "eval_loss": 2.842964704541373e-06,
      "eval_runtime": 2.1034,
      "eval_samples_per_second": 23.771,
      "eval_steps_per_second": 6.18,
      "step": 150
    },
    {
      "epoch": 0.3335404155449714,
      "grad_norm": 0.000154680063133128,
      "learning_rate": 2.370508142456748e-05,
      "loss": 0.0,
      "step": 151
    },
    {
      "epoch": 0.3357492924691102,
      "grad_norm": 0.00023134062939789146,
      "learning_rate": 2.3180194846605367e-05,
      "loss": 0.0,
      "step": 152
    },
    {
      "epoch": 0.33795816939324913,
      "grad_norm": 0.00024014056543819606,
      "learning_rate": 2.2663827199913588e-05,
      "loss": 0.0,
      "step": 153
    },
    {
      "epoch": 0.340167046317388,
      "grad_norm": 0.00021546079369727522,
      "learning_rate": 2.215611672859741e-05,
      "loss": 0.0,
      "step": 154
    },
    {
      "epoch": 0.3423759232415269,
      "grad_norm": 0.00024820741964504123,
      "learning_rate": 2.165719935902685e-05,
      "loss": 0.0,
      "step": 155
    },
    {
      "epoch": 0.3445848001656658,
      "grad_norm": 0.00044995194184593856,
      "learning_rate": 2.1167208663446025e-05,
      "loss": 0.0,
      "step": 156
    },
    {
      "epoch": 0.34679367708980463,
      "grad_norm": 0.00015662639634683728,
      "learning_rate": 2.068627582421254e-05,
      "loss": 0.0,
      "step": 157
    },
    {
      "epoch": 0.34900255401394353,
      "grad_norm": 9.385013981955126e-05,
      "learning_rate": 2.0214529598676836e-05,
      "loss": 0.0,
      "step": 158
    },
    {
      "epoch": 0.35121143093808244,
      "grad_norm": 9.166620293399319e-05,
      "learning_rate": 1.9752096284710738e-05,
      "loss": 0.0,
      "step": 159
    },
    {
      "epoch": 0.3534203078622213,
      "grad_norm": 9.074221452465281e-05,
      "learning_rate": 1.9299099686894423e-05,
      "loss": 0.0,
      "step": 160
    },
    {
      "epoch": 0.3556291847863602,
      "grad_norm": 9.394592780154198e-05,
      "learning_rate": 1.8855661083370986e-05,
      "loss": 0.0,
      "step": 161
    },
    {
      "epoch": 0.3578380617104991,
      "grad_norm": 9.24318956094794e-05,
      "learning_rate": 1.842189919337732e-05,
      "loss": 0.0,
      "step": 162
    },
    {
      "epoch": 0.36004693863463794,
      "grad_norm": 0.00011218286090297624,
      "learning_rate": 1.7997930145460136e-05,
      "loss": 0.0,
      "step": 163
    },
    {
      "epoch": 0.36225581555877684,
      "grad_norm": 0.00019017797603737563,
      "learning_rate": 1.758386744638546e-05,
      "loss": 0.0,
      "step": 164
    },
    {
      "epoch": 0.36446469248291574,
      "grad_norm": 0.00019140807853545994,
      "learning_rate": 1.7179821950750284e-05,
      "loss": 0.0,
      "step": 165
    },
    {
      "epoch": 0.3666735694070546,
      "grad_norm": 0.00020481123647186905,
      "learning_rate": 1.6785901831303956e-05,
      "loss": 0.0,
      "step": 166
    },
    {
      "epoch": 0.3688824463311935,
      "grad_norm": 0.00022451799304690212,
      "learning_rate": 1.6402212549987762e-05,
      "loss": 0.0,
      "step": 167
    },
    {
      "epoch": 0.37109132325533234,
      "grad_norm": 0.00030974153196439147,
      "learning_rate": 1.602885682970026e-05,
      "loss": 0.0,
      "step": 168
    },
    {
      "epoch": 0.37330020017947124,
      "grad_norm": 0.00048727114335633814,
      "learning_rate": 1.566593462679586e-05,
      "loss": 0.0,
      "step": 169
    },
    {
      "epoch": 0.37550907710361014,
      "grad_norm": 9.068298095371574e-05,
      "learning_rate": 1.531354310432403e-05,
      "loss": 0.0,
      "step": 170
    },
    {
      "epoch": 0.377717954027749,
      "grad_norm": 9.067923383554444e-05,
      "learning_rate": 1.4971776606016482e-05,
      "loss": 0.0,
      "step": 171
    },
    {
      "epoch": 0.3799268309518879,
      "grad_norm": 9.05448105186224e-05,
      "learning_rate": 1.464072663102903e-05,
      "loss": 0.0,
      "step": 172
    },
    {
      "epoch": 0.3821357078760268,
      "grad_norm": 9.20113452593796e-05,
      "learning_rate": 1.4320481809445051e-05,
      "loss": 0.0,
      "step": 173
    },
    {
      "epoch": 0.38434458480016565,
      "grad_norm": 9.098761074710637e-05,
      "learning_rate": 1.4011127878547087e-05,
      "loss": 0.0,
      "step": 174
    },
    {
      "epoch": 0.38655346172430455,
      "grad_norm": 9.139224857790396e-05,
      "learning_rate": 1.3712747659862896e-05,
      "loss": 0.0,
      "step": 175
    },
    {
      "epoch": 0.38655346172430455,
      "eval_loss": 2.7154196686751675e-06,
      "eval_runtime": 2.0847,
      "eval_samples_per_second": 23.985,
      "eval_steps_per_second": 6.236,
      "step": 175
    },
    {
      "epoch": 0.38876233864844345,
      "grad_norm": 0.0001819442113628611,
      "learning_rate": 1.3425421036992098e-05,
      "loss": 0.0,
      "step": 176
    },
    {
      "epoch": 0.3909712155725823,
      "grad_norm": 0.00019746804900933057,
      "learning_rate": 1.314922493421946e-05,
      "loss": 0.0,
      "step": 177
    },
    {
      "epoch": 0.3931800924967212,
      "grad_norm": 0.0002262179768877104,
      "learning_rate": 1.2884233295920353e-05,
      "loss": 0.0,
      "step": 178
    },
    {
      "epoch": 0.3953889694208601,
      "grad_norm": 0.00020046616555191576,
      "learning_rate": 1.2630517066764069e-05,
      "loss": 0.0,
      "step": 179
    },
    {
      "epoch": 0.39759784634499895,
      "grad_norm": 0.0002561356814112514,
      "learning_rate": 1.2388144172720251e-05,
      "loss": 0.0,
      "step": 180
    },
    {
      "epoch": 0.39980672326913785,
      "grad_norm": 0.0003955549036618322,
      "learning_rate": 1.2157179502873409e-05,
      "loss": 0.0,
      "step": 181
    },
    {
      "epoch": 0.40201560019327676,
      "grad_norm": 0.00018629009719006717,
      "learning_rate": 1.1937684892050604e-05,
      "loss": 0.0,
      "step": 182
    },
    {
      "epoch": 0.4042244771174156,
      "grad_norm": 9.03993786778301e-05,
      "learning_rate": 1.172971910426671e-05,
      "loss": 0.0,
      "step": 183
    },
    {
      "epoch": 0.4064333540415545,
      "grad_norm": 8.99579026736319e-05,
      "learning_rate": 1.1533337816991932e-05,
      "loss": 0.0,
      "step": 184
    },
    {
      "epoch": 0.40864223096569335,
      "grad_norm": 8.806282130535692e-05,
      "learning_rate": 1.1348593606245522e-05,
      "loss": 0.0,
      "step": 185
    },
    {
      "epoch": 0.41085110788983226,
      "grad_norm": 8.73383687576279e-05,
      "learning_rate": 1.1175535932519987e-05,
      "loss": 0.0,
      "step": 186
    },
    {
      "epoch": 0.41305998481397116,
      "grad_norm": 8.832193998387083e-05,
      "learning_rate": 1.1014211127539271e-05,
      "loss": 0.0,
      "step": 187
    },
    {
      "epoch": 0.41526886173811,
      "grad_norm": 0.00011703837662935257,
      "learning_rate": 1.0864662381854632e-05,
      "loss": 0.0,
      "step": 188
    },
    {
      "epoch": 0.4174777386622489,
      "grad_norm": 0.0002513094514142722,
      "learning_rate": 1.0726929733281515e-05,
      "loss": 0.0,
      "step": 189
    },
    {
      "epoch": 0.4196866155863878,
      "grad_norm": 0.00021101209858898073,
      "learning_rate": 1.0601050056180447e-05,
      "loss": 0.0,
      "step": 190
    },
    {
      "epoch": 0.42189549251052666,
      "grad_norm": 0.00020866327395197004,
      "learning_rate": 1.0487057051584856e-05,
      "loss": 0.0,
      "step": 191
    },
    {
      "epoch": 0.42410436943466556,
      "grad_norm": 0.00022013194393366575,
      "learning_rate": 1.0384981238178534e-05,
      "loss": 0.0,
      "step": 192
    },
    {
      "epoch": 0.42631324635880447,
      "grad_norm": 0.00032330441172234714,
      "learning_rate": 1.0294849944125004e-05,
      "loss": 0.0,
      "step": 193
    },
    {
      "epoch": 0.4285221232829433,
      "grad_norm": 0.00035217651748098433,
      "learning_rate": 1.0216687299751144e-05,
      "loss": 0.0,
      "step": 194
    },
    {
      "epoch": 0.4307310002070822,
      "grad_norm": 8.39560671010986e-05,
      "learning_rate": 1.0150514231086887e-05,
      "loss": 0.0,
      "step": 195
    },
    {
      "epoch": 0.4329398771312211,
      "grad_norm": 8.635565609438345e-05,
      "learning_rate": 1.0096348454262845e-05,
      "loss": 0.0,
      "step": 196
    },
    {
      "epoch": 0.43514875405535997,
      "grad_norm": 8.677168807480484e-05,
      "learning_rate": 1.0054204470767243e-05,
      "loss": 0.0,
      "step": 197
    },
    {
      "epoch": 0.43735763097949887,
      "grad_norm": 8.660169260110706e-05,
      "learning_rate": 1.0024093563563546e-05,
      "loss": 0.0,
      "step": 198
    },
    {
      "epoch": 0.43956650790363777,
      "grad_norm": 8.837666246108711e-05,
      "learning_rate": 1.000602379406972e-05,
      "loss": 0.0,
      "step": 199
    },
    {
      "epoch": 0.4417753848277766,
      "grad_norm": 8.881120447767898e-05,
      "learning_rate": 1e-05,
      "loss": 0.0,
      "step": 200
    },
    {
      "epoch": 0.4417753848277766,
      "eval_loss": 2.660818836375256e-06,
      "eval_runtime": 2.0833,
      "eval_samples_per_second": 24.001,
      "eval_steps_per_second": 6.24,
      "step": 200
    }
  ],
  "logging_steps": 1,
  "max_steps": 200,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 25,
  "stateful_callbacks": {
    "EarlyStoppingCallback": {
      "args": {
        "early_stopping_patience": 1,
        "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": 6.49923578036224e+17,
  "train_batch_size": 1,
  "trial_name": null,
  "trial_params": null
}