{
  "best_metric": 1.284598708152771,
  "best_model_checkpoint": "miner_id_24/checkpoint-200",
  "epoch": 0.006826113296415437,
  "eval_steps": 50,
  "global_step": 200,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 3.413056648207719e-05,
      "grad_norm": 0.44594427943229675,
      "learning_rate": 1e-05,
      "loss": 1.2863,
      "step": 1
    },
    {
      "epoch": 3.413056648207719e-05,
      "eval_loss": 1.5722088813781738,
      "eval_runtime": 1610.3713,
      "eval_samples_per_second": 30.643,
      "eval_steps_per_second": 7.661,
      "step": 1
    },
    {
      "epoch": 6.826113296415438e-05,
      "grad_norm": 0.46026965975761414,
      "learning_rate": 2e-05,
      "loss": 1.2411,
      "step": 2
    },
    {
      "epoch": 0.00010239169944623155,
      "grad_norm": 0.6382265090942383,
      "learning_rate": 3e-05,
      "loss": 1.4992,
      "step": 3
    },
    {
      "epoch": 0.00013652226592830876,
      "grad_norm": 0.5791121125221252,
      "learning_rate": 4e-05,
      "loss": 1.3482,
      "step": 4
    },
    {
      "epoch": 0.00017065283241038593,
      "grad_norm": 0.5219406485557556,
      "learning_rate": 5e-05,
      "loss": 1.2532,
      "step": 5
    },
    {
      "epoch": 0.0002047833988924631,
      "grad_norm": 0.5231647491455078,
      "learning_rate": 6e-05,
      "loss": 1.2907,
      "step": 6
    },
    {
      "epoch": 0.0002389139653745403,
      "grad_norm": 0.3957732915878296,
      "learning_rate": 7e-05,
      "loss": 1.183,
      "step": 7
    },
    {
      "epoch": 0.0002730445318566175,
      "grad_norm": 0.400023877620697,
      "learning_rate": 8e-05,
      "loss": 1.1117,
      "step": 8
    },
    {
      "epoch": 0.0003071750983386947,
      "grad_norm": 0.47502192854881287,
      "learning_rate": 9e-05,
      "loss": 1.1937,
      "step": 9
    },
    {
      "epoch": 0.00034130566482077187,
      "grad_norm": 0.4597507119178772,
      "learning_rate": 0.0001,
      "loss": 1.2562,
      "step": 10
    },
    {
      "epoch": 0.00037543623130284904,
      "grad_norm": 0.4608520567417145,
      "learning_rate": 9.999316524962345e-05,
      "loss": 1.2301,
      "step": 11
    },
    {
      "epoch": 0.0004095667977849262,
      "grad_norm": 0.4520881175994873,
      "learning_rate": 9.997266286704631e-05,
      "loss": 1.2709,
      "step": 12
    },
    {
      "epoch": 0.00044369736426700345,
      "grad_norm": 0.41737860441207886,
      "learning_rate": 9.993849845741524e-05,
      "loss": 1.1905,
      "step": 13
    },
    {
      "epoch": 0.0004778279307490806,
      "grad_norm": 0.3545536994934082,
      "learning_rate": 9.989068136093873e-05,
      "loss": 1.3463,
      "step": 14
    },
    {
      "epoch": 0.0005119584972311578,
      "grad_norm": 0.3553808033466339,
      "learning_rate": 9.98292246503335e-05,
      "loss": 1.216,
      "step": 15
    },
    {
      "epoch": 0.000546089063713235,
      "grad_norm": 0.40968960523605347,
      "learning_rate": 9.975414512725057e-05,
      "loss": 1.3641,
      "step": 16
    },
    {
      "epoch": 0.0005802196301953121,
      "grad_norm": 0.42688941955566406,
      "learning_rate": 9.966546331768191e-05,
      "loss": 1.1641,
      "step": 17
    },
    {
      "epoch": 0.0006143501966773894,
      "grad_norm": 0.42863839864730835,
      "learning_rate": 9.956320346634876e-05,
      "loss": 1.2128,
      "step": 18
    },
    {
      "epoch": 0.0006484807631594665,
      "grad_norm": 0.42905810475349426,
      "learning_rate": 9.944739353007344e-05,
      "loss": 1.1894,
      "step": 19
    },
    {
      "epoch": 0.0006826113296415437,
      "grad_norm": 0.3967270255088806,
      "learning_rate": 9.931806517013612e-05,
      "loss": 1.2708,
      "step": 20
    },
    {
      "epoch": 0.000716741896123621,
      "grad_norm": 0.3916252851486206,
      "learning_rate": 9.917525374361912e-05,
      "loss": 1.2985,
      "step": 21
    },
    {
      "epoch": 0.0007508724626056981,
      "grad_norm": 0.3845914602279663,
      "learning_rate": 9.901899829374047e-05,
      "loss": 1.2068,
      "step": 22
    },
    {
      "epoch": 0.0007850030290877753,
      "grad_norm": 0.41597360372543335,
      "learning_rate": 9.884934153917997e-05,
      "loss": 1.2379,
      "step": 23
    },
    {
      "epoch": 0.0008191335955698524,
      "grad_norm": 0.43235287070274353,
      "learning_rate": 9.86663298624003e-05,
      "loss": 1.2474,
      "step": 24
    },
    {
      "epoch": 0.0008532641620519297,
      "grad_norm": 0.43992671370506287,
      "learning_rate": 9.847001329696653e-05,
      "loss": 1.2688,
      "step": 25
    },
    {
      "epoch": 0.0008873947285340069,
      "grad_norm": 0.4149838089942932,
      "learning_rate": 9.826044551386744e-05,
      "loss": 1.186,
      "step": 26
    },
    {
      "epoch": 0.000921525295016084,
      "grad_norm": 0.42388981580734253,
      "learning_rate": 9.803768380684242e-05,
      "loss": 1.2362,
      "step": 27
    },
    {
      "epoch": 0.0009556558614981612,
      "grad_norm": 0.43185508251190186,
      "learning_rate": 9.780178907671789e-05,
      "loss": 1.2924,
      "step": 28
    },
    {
      "epoch": 0.0009897864279802384,
      "grad_norm": 0.5838025808334351,
      "learning_rate": 9.755282581475769e-05,
      "loss": 1.5337,
      "step": 29
    },
    {
      "epoch": 0.0010239169944623156,
      "grad_norm": 0.44131457805633545,
      "learning_rate": 9.729086208503174e-05,
      "loss": 1.5396,
      "step": 30
    },
    {
      "epoch": 0.0010580475609443928,
      "grad_norm": 0.4512113928794861,
      "learning_rate": 9.701596950580806e-05,
      "loss": 1.2793,
      "step": 31
    },
    {
      "epoch": 0.00109217812742647,
      "grad_norm": 0.46696820855140686,
      "learning_rate": 9.672822322997305e-05,
      "loss": 1.1158,
      "step": 32
    },
    {
      "epoch": 0.001126308693908547,
      "grad_norm": 0.44508466124534607,
      "learning_rate": 9.642770192448536e-05,
      "loss": 1.2374,
      "step": 33
    },
    {
      "epoch": 0.0011604392603906243,
      "grad_norm": 0.4683876037597656,
      "learning_rate": 9.611448774886924e-05,
      "loss": 1.1863,
      "step": 34
    },
    {
      "epoch": 0.0011945698268727015,
      "grad_norm": 0.5023918151855469,
      "learning_rate": 9.578866633275288e-05,
      "loss": 1.3757,
      "step": 35
    },
    {
      "epoch": 0.0012287003933547788,
      "grad_norm": 0.4710521697998047,
      "learning_rate": 9.545032675245813e-05,
      "loss": 1.188,
      "step": 36
    },
    {
      "epoch": 0.001262830959836856,
      "grad_norm": 0.5157263278961182,
      "learning_rate": 9.509956150664796e-05,
      "loss": 1.5428,
      "step": 37
    },
    {
      "epoch": 0.001296961526318933,
      "grad_norm": 0.518281102180481,
      "learning_rate": 9.473646649103818e-05,
      "loss": 1.421,
      "step": 38
    },
    {
      "epoch": 0.0013310920928010102,
      "grad_norm": 0.5908358693122864,
      "learning_rate": 9.43611409721806e-05,
      "loss": 1.4305,
      "step": 39
    },
    {
      "epoch": 0.0013652226592830875,
      "grad_norm": 0.5308020114898682,
      "learning_rate": 9.397368756032445e-05,
      "loss": 1.3517,
      "step": 40
    },
    {
      "epoch": 0.0013993532257651647,
      "grad_norm": 0.5744770169258118,
      "learning_rate": 9.357421218136386e-05,
      "loss": 1.389,
      "step": 41
    },
    {
      "epoch": 0.001433483792247242,
      "grad_norm": 0.6788293719291687,
      "learning_rate": 9.316282404787871e-05,
      "loss": 1.3143,
      "step": 42
    },
    {
      "epoch": 0.001467614358729319,
      "grad_norm": 0.5195122361183167,
      "learning_rate": 9.273963562927695e-05,
      "loss": 1.1217,
      "step": 43
    },
    {
      "epoch": 0.0015017449252113962,
      "grad_norm": 0.6682026982307434,
      "learning_rate": 9.230476262104677e-05,
      "loss": 1.4026,
      "step": 44
    },
    {
      "epoch": 0.0015358754916934734,
      "grad_norm": 0.690555214881897,
      "learning_rate": 9.185832391312644e-05,
      "loss": 1.4181,
      "step": 45
    },
    {
      "epoch": 0.0015700060581755506,
      "grad_norm": 0.745463490486145,
      "learning_rate": 9.140044155740101e-05,
      "loss": 1.3662,
      "step": 46
    },
    {
      "epoch": 0.0016041366246576279,
      "grad_norm": 0.6858728528022766,
      "learning_rate": 9.093124073433463e-05,
      "loss": 1.5098,
      "step": 47
    },
    {
      "epoch": 0.0016382671911397049,
      "grad_norm": 0.7358869910240173,
      "learning_rate": 9.045084971874738e-05,
      "loss": 1.3523,
      "step": 48
    },
    {
      "epoch": 0.001672397757621782,
      "grad_norm": 0.7893625497817993,
      "learning_rate": 8.995939984474624e-05,
      "loss": 1.5544,
      "step": 49
    },
    {
      "epoch": 0.0017065283241038593,
      "grad_norm": 0.8945049047470093,
      "learning_rate": 8.945702546981969e-05,
      "loss": 1.4609,
      "step": 50
    },
    {
      "epoch": 0.0017065283241038593,
      "eval_loss": 1.3237718343734741,
      "eval_runtime": 1618.0666,
      "eval_samples_per_second": 30.498,
      "eval_steps_per_second": 7.625,
      "step": 50
    },
    {
      "epoch": 0.0017406588905859366,
      "grad_norm": 0.31223592162132263,
      "learning_rate": 8.894386393810563e-05,
      "loss": 1.0558,
      "step": 51
    },
    {
      "epoch": 0.0017747894570680138,
      "grad_norm": 0.3674425780773163,
      "learning_rate": 8.842005554284296e-05,
      "loss": 1.1294,
      "step": 52
    },
    {
      "epoch": 0.0018089200235500908,
      "grad_norm": 0.42357581853866577,
      "learning_rate": 8.788574348801675e-05,
      "loss": 1.2837,
      "step": 53
    },
    {
      "epoch": 0.001843050590032168,
      "grad_norm": 0.38247671723365784,
      "learning_rate": 8.73410738492077e-05,
      "loss": 1.1485,
      "step": 54
    },
    {
      "epoch": 0.0018771811565142453,
      "grad_norm": 0.3712633550167084,
      "learning_rate": 8.678619553365659e-05,
      "loss": 1.2744,
      "step": 55
    },
    {
      "epoch": 0.0019113117229963225,
      "grad_norm": 0.3071327805519104,
      "learning_rate": 8.622126023955446e-05,
      "loss": 1.1759,
      "step": 56
    },
    {
      "epoch": 0.0019454422894783997,
      "grad_norm": 0.3012136220932007,
      "learning_rate": 8.564642241456986e-05,
      "loss": 1.2486,
      "step": 57
    },
    {
      "epoch": 0.0019795728559604767,
      "grad_norm": 0.30189332365989685,
      "learning_rate": 8.506183921362443e-05,
      "loss": 1.3821,
      "step": 58
    },
    {
      "epoch": 0.002013703422442554,
      "grad_norm": 0.31529420614242554,
      "learning_rate": 8.44676704559283e-05,
      "loss": 1.023,
      "step": 59
    },
    {
      "epoch": 0.002047833988924631,
      "grad_norm": 0.328961580991745,
      "learning_rate": 8.386407858128706e-05,
      "loss": 1.2987,
      "step": 60
    },
    {
      "epoch": 0.0020819645554067084,
      "grad_norm": 0.36653995513916016,
      "learning_rate": 8.32512286056924e-05,
      "loss": 1.1651,
      "step": 61
    },
    {
      "epoch": 0.0021160951218887857,
      "grad_norm": 0.30454298853874207,
      "learning_rate": 8.262928807620843e-05,
      "loss": 1.1648,
      "step": 62
    },
    {
      "epoch": 0.002150225688370863,
      "grad_norm": 0.32735389471054077,
      "learning_rate": 8.199842702516583e-05,
      "loss": 1.0601,
      "step": 63
    },
    {
      "epoch": 0.00218435625485294,
      "grad_norm": 0.33563855290412903,
      "learning_rate": 8.135881792367686e-05,
      "loss": 1.15,
      "step": 64
    },
    {
      "epoch": 0.002218486821335017,
      "grad_norm": 0.342314749956131,
      "learning_rate": 8.07106356344834e-05,
      "loss": 1.1782,
      "step": 65
    },
    {
      "epoch": 0.002252617387817094,
      "grad_norm": 0.37911802530288696,
      "learning_rate": 8.005405736415126e-05,
      "loss": 1.3051,
      "step": 66
    },
    {
      "epoch": 0.0022867479542991714,
      "grad_norm": 0.3477848470211029,
      "learning_rate": 7.938926261462366e-05,
      "loss": 1.3239,
      "step": 67
    },
    {
      "epoch": 0.0023208785207812486,
      "grad_norm": 0.40505796670913696,
      "learning_rate": 7.871643313414718e-05,
      "loss": 1.2536,
      "step": 68
    },
    {
      "epoch": 0.002355009087263326,
      "grad_norm": 0.3553071916103363,
      "learning_rate": 7.803575286758364e-05,
      "loss": 1.2349,
      "step": 69
    },
    {
      "epoch": 0.002389139653745403,
      "grad_norm": 0.359052836894989,
      "learning_rate": 7.734740790612136e-05,
      "loss": 1.3748,
      "step": 70
    },
    {
      "epoch": 0.0024232702202274803,
      "grad_norm": 0.3827054500579834,
      "learning_rate": 7.66515864363997e-05,
      "loss": 1.3906,
      "step": 71
    },
    {
      "epoch": 0.0024574007867095575,
      "grad_norm": 0.4195806682109833,
      "learning_rate": 7.594847868906076e-05,
      "loss": 1.2736,
      "step": 72
    },
    {
      "epoch": 0.0024915313531916347,
      "grad_norm": 0.36370524764060974,
      "learning_rate": 7.52382768867422e-05,
      "loss": 1.3726,
      "step": 73
    },
    {
      "epoch": 0.002525661919673712,
      "grad_norm": 0.37772655487060547,
      "learning_rate": 7.452117519152542e-05,
      "loss": 1.2047,
      "step": 74
    },
    {
      "epoch": 0.0025597924861557888,
      "grad_norm": 0.4216993451118469,
      "learning_rate": 7.379736965185368e-05,
      "loss": 1.3595,
      "step": 75
    },
    {
      "epoch": 0.002593923052637866,
      "grad_norm": 0.485747754573822,
      "learning_rate": 7.30670581489344e-05,
      "loss": 1.3527,
      "step": 76
    },
    {
      "epoch": 0.0026280536191199432,
      "grad_norm": 0.3874759078025818,
      "learning_rate": 7.233044034264034e-05,
      "loss": 1.2473,
      "step": 77
    },
    {
      "epoch": 0.0026621841856020205,
      "grad_norm": 0.41956737637519836,
      "learning_rate": 7.158771761692464e-05,
      "loss": 1.3199,
      "step": 78
    },
    {
      "epoch": 0.0026963147520840977,
      "grad_norm": 0.4455489218235016,
      "learning_rate": 7.083909302476453e-05,
      "loss": 1.3745,
      "step": 79
    },
    {
      "epoch": 0.002730445318566175,
      "grad_norm": 0.46923041343688965,
      "learning_rate": 7.008477123264848e-05,
      "loss": 1.2943,
      "step": 80
    },
    {
      "epoch": 0.002764575885048252,
      "grad_norm": 0.4096168577671051,
      "learning_rate": 6.932495846462261e-05,
      "loss": 1.3311,
      "step": 81
    },
    {
      "epoch": 0.0027987064515303294,
      "grad_norm": 0.4408420920372009,
      "learning_rate": 6.855986244591104e-05,
      "loss": 1.2125,
      "step": 82
    },
    {
      "epoch": 0.0028328370180124066,
      "grad_norm": 0.4137131869792938,
      "learning_rate": 6.778969234612584e-05,
      "loss": 1.3847,
      "step": 83
    },
    {
      "epoch": 0.002866967584494484,
      "grad_norm": 0.46820157766342163,
      "learning_rate": 6.701465872208216e-05,
      "loss": 1.468,
      "step": 84
    },
    {
      "epoch": 0.0029010981509765606,
      "grad_norm": 0.4669029712677002,
      "learning_rate": 6.623497346023418e-05,
      "loss": 1.4026,
      "step": 85
    },
    {
      "epoch": 0.002935228717458638,
      "grad_norm": 0.4239863455295563,
      "learning_rate": 6.545084971874738e-05,
      "loss": 1.3297,
      "step": 86
    },
    {
      "epoch": 0.002969359283940715,
      "grad_norm": 0.5485544800758362,
      "learning_rate": 6.466250186922325e-05,
      "loss": 1.2713,
      "step": 87
    },
    {
      "epoch": 0.0030034898504227923,
      "grad_norm": 0.4871569573879242,
      "learning_rate": 6.387014543809223e-05,
      "loss": 1.3044,
      "step": 88
    },
    {
      "epoch": 0.0030376204169048696,
      "grad_norm": 0.45997199416160583,
      "learning_rate": 6.307399704769099e-05,
      "loss": 1.2952,
      "step": 89
    },
    {
      "epoch": 0.003071750983386947,
      "grad_norm": 0.5230398774147034,
      "learning_rate": 6.227427435703997e-05,
      "loss": 1.3958,
      "step": 90
    },
    {
      "epoch": 0.003105881549869024,
      "grad_norm": 0.5710857510566711,
      "learning_rate": 6.147119600233758e-05,
      "loss": 1.3733,
      "step": 91
    },
    {
      "epoch": 0.0031400121163511012,
      "grad_norm": 0.5563080906867981,
      "learning_rate": 6.066498153718735e-05,
      "loss": 1.2037,
      "step": 92
    },
    {
      "epoch": 0.0031741426828331785,
      "grad_norm": 0.5526666045188904,
      "learning_rate": 5.985585137257401e-05,
      "loss": 1.3215,
      "step": 93
    },
    {
      "epoch": 0.0032082732493152557,
      "grad_norm": 0.5478617548942566,
      "learning_rate": 5.90440267166055e-05,
      "loss": 1.4201,
      "step": 94
    },
    {
      "epoch": 0.0032424038157973325,
      "grad_norm": 0.6000781655311584,
      "learning_rate": 5.8229729514036705e-05,
      "loss": 1.5723,
      "step": 95
    },
    {
      "epoch": 0.0032765343822794097,
      "grad_norm": 0.5676822662353516,
      "learning_rate": 5.74131823855921e-05,
      "loss": 1.4396,
      "step": 96
    },
    {
      "epoch": 0.003310664948761487,
      "grad_norm": 0.5717068314552307,
      "learning_rate": 5.6594608567103456e-05,
      "loss": 1.4501,
      "step": 97
    },
    {
      "epoch": 0.003344795515243564,
      "grad_norm": 0.7923446297645569,
      "learning_rate": 5.577423184847932e-05,
      "loss": 1.4407,
      "step": 98
    },
    {
      "epoch": 0.0033789260817256414,
      "grad_norm": 0.7019022107124329,
      "learning_rate": 5.495227651252315e-05,
      "loss": 1.5061,
      "step": 99
    },
    {
      "epoch": 0.0034130566482077187,
      "grad_norm": 0.753588855266571,
      "learning_rate": 5.4128967273616625e-05,
      "loss": 1.4598,
      "step": 100
    },
    {
      "epoch": 0.0034130566482077187,
      "eval_loss": 1.2931729555130005,
      "eval_runtime": 1618.5571,
      "eval_samples_per_second": 30.488,
      "eval_steps_per_second": 7.622,
      "step": 100
    },
    {
      "epoch": 0.003447187214689796,
      "grad_norm": 0.21361371874809265,
      "learning_rate": 5.330452921628497e-05,
      "loss": 1.1346,
      "step": 101
    },
    {
      "epoch": 0.003481317781171873,
      "grad_norm": 0.2689608335494995,
      "learning_rate": 5.247918773366112e-05,
      "loss": 1.2523,
      "step": 102
    },
    {
      "epoch": 0.0035154483476539503,
      "grad_norm": 0.2706867456436157,
      "learning_rate": 5.165316846586541e-05,
      "loss": 1.0295,
      "step": 103
    },
    {
      "epoch": 0.0035495789141360276,
      "grad_norm": 0.3404642641544342,
      "learning_rate": 5.0826697238317935e-05,
      "loss": 1.0159,
      "step": 104
    },
    {
      "epoch": 0.0035837094806181044,
      "grad_norm": 0.3048684895038605,
      "learning_rate": 5e-05,
      "loss": 1.1554,
      "step": 105
    },
    {
      "epoch": 0.0036178400471001816,
      "grad_norm": 0.30554166436195374,
      "learning_rate": 4.917330276168208e-05,
      "loss": 1.193,
      "step": 106
    },
    {
      "epoch": 0.003651970613582259,
      "grad_norm": 0.2992115616798401,
      "learning_rate": 4.834683153413459e-05,
      "loss": 1.0538,
      "step": 107
    },
    {
      "epoch": 0.003686101180064336,
      "grad_norm": 0.311595618724823,
      "learning_rate": 4.7520812266338885e-05,
      "loss": 1.2201,
      "step": 108
    },
    {
      "epoch": 0.0037202317465464133,
      "grad_norm": 0.2934740483760834,
      "learning_rate": 4.669547078371504e-05,
      "loss": 1.218,
      "step": 109
    },
    {
      "epoch": 0.0037543623130284905,
      "grad_norm": 0.32242047786712646,
      "learning_rate": 4.5871032726383386e-05,
      "loss": 1.1889,
      "step": 110
    },
    {
      "epoch": 0.0037884928795105677,
      "grad_norm": 0.30930933356285095,
      "learning_rate": 4.504772348747687e-05,
      "loss": 1.0954,
      "step": 111
    },
    {
      "epoch": 0.003822623445992645,
      "grad_norm": 0.3188520073890686,
      "learning_rate": 4.4225768151520694e-05,
      "loss": 1.2221,
      "step": 112
    },
    {
      "epoch": 0.003856754012474722,
      "grad_norm": 0.37747716903686523,
      "learning_rate": 4.3405391432896555e-05,
      "loss": 1.1932,
      "step": 113
    },
    {
      "epoch": 0.0038908845789567994,
      "grad_norm": 0.315521240234375,
      "learning_rate": 4.2586817614407895e-05,
      "loss": 1.174,
      "step": 114
    },
    {
      "epoch": 0.003925015145438877,
      "grad_norm": 0.36168909072875977,
      "learning_rate": 4.17702704859633e-05,
      "loss": 1.4362,
      "step": 115
    },
    {
      "epoch": 0.0039591457119209535,
      "grad_norm": 0.3890553116798401,
      "learning_rate": 4.095597328339452e-05,
      "loss": 1.2651,
      "step": 116
    },
    {
      "epoch": 0.003993276278403031,
      "grad_norm": 0.372367799282074,
      "learning_rate": 4.0144148627425993e-05,
      "loss": 1.1706,
      "step": 117
    },
    {
      "epoch": 0.004027406844885108,
      "grad_norm": 0.3782535195350647,
      "learning_rate": 3.933501846281267e-05,
      "loss": 1.3138,
      "step": 118
    },
    {
      "epoch": 0.004061537411367186,
      "grad_norm": 0.3837883174419403,
      "learning_rate": 3.852880399766243e-05,
      "loss": 1.3965,
      "step": 119
    },
    {
      "epoch": 0.004095667977849262,
      "grad_norm": 0.34615853428840637,
      "learning_rate": 3.772572564296005e-05,
      "loss": 1.1693,
      "step": 120
    },
    {
      "epoch": 0.004129798544331339,
      "grad_norm": 0.4134136140346527,
      "learning_rate": 3.6926002952309016e-05,
      "loss": 1.3328,
      "step": 121
    },
    {
      "epoch": 0.004163929110813417,
      "grad_norm": 0.44440752267837524,
      "learning_rate": 3.612985456190778e-05,
      "loss": 1.2767,
      "step": 122
    },
    {
      "epoch": 0.004198059677295494,
      "grad_norm": 0.36634060740470886,
      "learning_rate": 3.533749813077677e-05,
      "loss": 1.1117,
      "step": 123
    },
    {
      "epoch": 0.004232190243777571,
      "grad_norm": 0.392229825258255,
      "learning_rate": 3.4549150281252636e-05,
      "loss": 1.2552,
      "step": 124
    },
    {
      "epoch": 0.004266320810259648,
      "grad_norm": 0.3841002583503723,
      "learning_rate": 3.3765026539765834e-05,
      "loss": 1.2483,
      "step": 125
    },
    {
      "epoch": 0.004300451376741726,
      "grad_norm": 0.39788320660591125,
      "learning_rate": 3.298534127791785e-05,
      "loss": 1.3653,
      "step": 126
    },
    {
      "epoch": 0.0043345819432238026,
      "grad_norm": 0.40383124351501465,
      "learning_rate": 3.221030765387417e-05,
      "loss": 1.2413,
      "step": 127
    },
    {
      "epoch": 0.00436871250970588,
      "grad_norm": 0.4268058240413666,
      "learning_rate": 3.144013755408895e-05,
      "loss": 1.3326,
      "step": 128
    },
    {
      "epoch": 0.004402843076187957,
      "grad_norm": 0.41969579458236694,
      "learning_rate": 3.0675041535377405e-05,
      "loss": 1.4618,
      "step": 129
    },
    {
      "epoch": 0.004436973642670034,
      "grad_norm": 0.40193435549736023,
      "learning_rate": 2.991522876735154e-05,
      "loss": 1.3925,
      "step": 130
    },
    {
      "epoch": 0.0044711042091521115,
      "grad_norm": 0.44596028327941895,
      "learning_rate": 2.916090697523549e-05,
      "loss": 1.3146,
      "step": 131
    },
    {
      "epoch": 0.004505234775634188,
      "grad_norm": 0.42286020517349243,
      "learning_rate": 2.8412282383075363e-05,
      "loss": 1.3824,
      "step": 132
    },
    {
      "epoch": 0.004539365342116266,
      "grad_norm": 0.5087577104568481,
      "learning_rate": 2.766955965735968e-05,
      "loss": 1.4045,
      "step": 133
    },
    {
      "epoch": 0.004573495908598343,
      "grad_norm": 0.4941883087158203,
      "learning_rate": 2.693294185106562e-05,
      "loss": 1.2844,
      "step": 134
    },
    {
      "epoch": 0.00460762647508042,
      "grad_norm": 0.4566398859024048,
      "learning_rate": 2.6202630348146324e-05,
      "loss": 1.3141,
      "step": 135
    },
    {
      "epoch": 0.004641757041562497,
      "grad_norm": 0.48468443751335144,
      "learning_rate": 2.547882480847461e-05,
      "loss": 1.5077,
      "step": 136
    },
    {
      "epoch": 0.004675887608044575,
      "grad_norm": 0.46569719910621643,
      "learning_rate": 2.476172311325783e-05,
      "loss": 1.4478,
      "step": 137
    },
    {
      "epoch": 0.004710018174526652,
      "grad_norm": 0.49201467633247375,
      "learning_rate": 2.405152131093926e-05,
      "loss": 1.3089,
      "step": 138
    },
    {
      "epoch": 0.004744148741008729,
      "grad_norm": 0.505203902721405,
      "learning_rate": 2.3348413563600325e-05,
      "loss": 1.324,
      "step": 139
    },
    {
      "epoch": 0.004778279307490806,
      "grad_norm": 0.5393547415733337,
      "learning_rate": 2.2652592093878666e-05,
      "loss": 1.6897,
      "step": 140
    },
    {
      "epoch": 0.004812409873972883,
      "grad_norm": 0.46957552433013916,
      "learning_rate": 2.196424713241637e-05,
      "loss": 1.1522,
      "step": 141
    },
    {
      "epoch": 0.004846540440454961,
      "grad_norm": 0.5212751030921936,
      "learning_rate": 2.128356686585282e-05,
      "loss": 1.3623,
      "step": 142
    },
    {
      "epoch": 0.004880671006937037,
      "grad_norm": 0.5395988821983337,
      "learning_rate": 2.061073738537635e-05,
      "loss": 1.3394,
      "step": 143
    },
    {
      "epoch": 0.004914801573419115,
      "grad_norm": 0.5298926830291748,
      "learning_rate": 1.9945942635848748e-05,
      "loss": 1.3597,
      "step": 144
    },
    {
      "epoch": 0.004948932139901192,
      "grad_norm": 0.5359431505203247,
      "learning_rate": 1.928936436551661e-05,
      "loss": 1.3546,
      "step": 145
    },
    {
      "epoch": 0.0049830627063832695,
      "grad_norm": 0.6278144121170044,
      "learning_rate": 1.8641182076323148e-05,
      "loss": 1.365,
      "step": 146
    },
    {
      "epoch": 0.005017193272865346,
      "grad_norm": 0.646981418132782,
      "learning_rate": 1.800157297483417e-05,
      "loss": 1.4498,
      "step": 147
    },
    {
      "epoch": 0.005051323839347424,
      "grad_norm": 0.5855222344398499,
      "learning_rate": 1.7370711923791567e-05,
      "loss": 1.3973,
      "step": 148
    },
    {
      "epoch": 0.005085454405829501,
      "grad_norm": 0.7290293574333191,
      "learning_rate": 1.6748771394307585e-05,
      "loss": 1.6799,
      "step": 149
    },
    {
      "epoch": 0.0051195849723115775,
      "grad_norm": 0.8321658968925476,
      "learning_rate": 1.6135921418712956e-05,
      "loss": 1.6338,
      "step": 150
    },
    {
      "epoch": 0.0051195849723115775,
      "eval_loss": 1.2857680320739746,
      "eval_runtime": 1616.0774,
      "eval_samples_per_second": 30.535,
      "eval_steps_per_second": 7.634,
      "step": 150
    },
    {
      "epoch": 0.005153715538793655,
      "grad_norm": 0.20292364060878754,
      "learning_rate": 1.553232954407171e-05,
      "loss": 1.071,
      "step": 151
    },
    {
      "epoch": 0.005187846105275732,
      "grad_norm": 0.22954697906970978,
      "learning_rate": 1.4938160786375572e-05,
      "loss": 1.1002,
      "step": 152
    },
    {
      "epoch": 0.00522197667175781,
      "grad_norm": 0.2702932059764862,
      "learning_rate": 1.435357758543015e-05,
      "loss": 1.2949,
      "step": 153
    },
    {
      "epoch": 0.0052561072382398865,
      "grad_norm": 0.44548317790031433,
      "learning_rate": 1.3778739760445552e-05,
      "loss": 1.2602,
      "step": 154
    },
    {
      "epoch": 0.005290237804721964,
      "grad_norm": 0.3724050223827362,
      "learning_rate": 1.3213804466343421e-05,
      "loss": 1.2083,
      "step": 155
    },
    {
      "epoch": 0.005324368371204041,
      "grad_norm": 0.3160119354724884,
      "learning_rate": 1.2658926150792322e-05,
      "loss": 1.2519,
      "step": 156
    },
    {
      "epoch": 0.005358498937686119,
      "grad_norm": 0.27721965312957764,
      "learning_rate": 1.2114256511983274e-05,
      "loss": 1.2035,
      "step": 157
    },
    {
      "epoch": 0.005392629504168195,
      "grad_norm": 0.2958066761493683,
      "learning_rate": 1.157994445715706e-05,
      "loss": 1.3437,
      "step": 158
    },
    {
      "epoch": 0.005426760070650273,
      "grad_norm": 0.30009925365448,
      "learning_rate": 1.1056136061894384e-05,
      "loss": 1.1908,
      "step": 159
    },
    {
      "epoch": 0.00546089063713235,
      "grad_norm": 0.34238624572753906,
      "learning_rate": 1.0542974530180327e-05,
      "loss": 1.2945,
      "step": 160
    },
    {
      "epoch": 0.005495021203614427,
      "grad_norm": 0.3141269385814667,
      "learning_rate": 1.0040600155253765e-05,
      "loss": 1.0959,
      "step": 161
    },
    {
      "epoch": 0.005529151770096504,
      "grad_norm": 0.29361629486083984,
      "learning_rate": 9.549150281252633e-06,
      "loss": 1.0722,
      "step": 162
    },
    {
      "epoch": 0.005563282336578581,
      "grad_norm": 0.3349563479423523,
      "learning_rate": 9.068759265665384e-06,
      "loss": 1.3526,
      "step": 163
    },
    {
      "epoch": 0.005597412903060659,
      "grad_norm": 0.35232019424438477,
      "learning_rate": 8.599558442598998e-06,
      "loss": 1.3667,
      "step": 164
    },
    {
      "epoch": 0.0056315434695427356,
      "grad_norm": 0.36815640330314636,
      "learning_rate": 8.141676086873572e-06,
      "loss": 1.2818,
      "step": 165
    },
    {
      "epoch": 0.005665674036024813,
      "grad_norm": 0.4468331038951874,
      "learning_rate": 7.695237378953223e-06,
      "loss": 1.4774,
      "step": 166
    },
    {
      "epoch": 0.00569980460250689,
      "grad_norm": 0.3803599178791046,
      "learning_rate": 7.260364370723044e-06,
      "loss": 1.2564,
      "step": 167
    },
    {
      "epoch": 0.005733935168988968,
      "grad_norm": 0.3637125492095947,
      "learning_rate": 6.837175952121306e-06,
      "loss": 1.1024,
      "step": 168
    },
    {
      "epoch": 0.0057680657354710445,
      "grad_norm": 0.36403417587280273,
      "learning_rate": 6.425787818636131e-06,
      "loss": 1.1804,
      "step": 169
    },
    {
      "epoch": 0.005802196301953121,
      "grad_norm": 0.40999406576156616,
      "learning_rate": 6.026312439675552e-06,
      "loss": 1.5286,
      "step": 170
    },
    {
      "epoch": 0.005836326868435199,
      "grad_norm": 0.3812612295150757,
      "learning_rate": 5.6388590278194096e-06,
      "loss": 1.3586,
      "step": 171
    },
    {
      "epoch": 0.005870457434917276,
      "grad_norm": 0.35636425018310547,
      "learning_rate": 5.263533508961827e-06,
      "loss": 1.2715,
      "step": 172
    },
    {
      "epoch": 0.005904588001399353,
      "grad_norm": 0.40908992290496826,
      "learning_rate": 4.900438493352055e-06,
      "loss": 1.4648,
      "step": 173
    },
    {
      "epoch": 0.00593871856788143,
      "grad_norm": 0.38302552700042725,
      "learning_rate": 4.549673247541875e-06,
      "loss": 1.3154,
      "step": 174
    },
    {
      "epoch": 0.005972849134363508,
      "grad_norm": 0.3900665044784546,
      "learning_rate": 4.2113336672471245e-06,
      "loss": 1.4876,
      "step": 175
    },
    {
      "epoch": 0.006006979700845585,
      "grad_norm": 0.4690256714820862,
      "learning_rate": 3.885512251130763e-06,
      "loss": 1.3807,
      "step": 176
    },
    {
      "epoch": 0.006041110267327662,
      "grad_norm": 0.41209375858306885,
      "learning_rate": 3.5722980755146517e-06,
      "loss": 1.0445,
      "step": 177
    },
    {
      "epoch": 0.006075240833809739,
      "grad_norm": 0.39221101999282837,
      "learning_rate": 3.271776770026963e-06,
      "loss": 1.1444,
      "step": 178
    },
    {
      "epoch": 0.006109371400291816,
      "grad_norm": 0.4169705808162689,
      "learning_rate": 2.9840304941919415e-06,
      "loss": 1.2882,
      "step": 179
    },
    {
      "epoch": 0.006143501966773894,
      "grad_norm": 0.4122096598148346,
      "learning_rate": 2.7091379149682685e-06,
      "loss": 1.3848,
      "step": 180
    },
    {
      "epoch": 0.00617763253325597,
      "grad_norm": 0.3993953764438629,
      "learning_rate": 2.4471741852423237e-06,
      "loss": 1.2617,
      "step": 181
    },
    {
      "epoch": 0.006211763099738048,
      "grad_norm": 0.5413970947265625,
      "learning_rate": 2.1982109232821178e-06,
      "loss": 1.4804,
      "step": 182
    },
    {
      "epoch": 0.006245893666220125,
      "grad_norm": 0.4104618430137634,
      "learning_rate": 1.962316193157593e-06,
      "loss": 1.231,
      "step": 183
    },
    {
      "epoch": 0.0062800242327022025,
      "grad_norm": 0.4876774251461029,
      "learning_rate": 1.7395544861325718e-06,
      "loss": 1.2455,
      "step": 184
    },
    {
      "epoch": 0.006314154799184279,
      "grad_norm": 0.44276532530784607,
      "learning_rate": 1.5299867030334814e-06,
      "loss": 1.2322,
      "step": 185
    },
    {
      "epoch": 0.006348285365666357,
      "grad_norm": 0.4874870777130127,
      "learning_rate": 1.333670137599713e-06,
      "loss": 1.3524,
      "step": 186
    },
    {
      "epoch": 0.006382415932148434,
      "grad_norm": 0.5349838733673096,
      "learning_rate": 1.1506584608200367e-06,
      "loss": 1.231,
      "step": 187
    },
    {
      "epoch": 0.006416546498630511,
      "grad_norm": 0.4433724582195282,
      "learning_rate": 9.810017062595322e-07,
      "loss": 1.2613,
      "step": 188
    },
    {
      "epoch": 0.006450677065112588,
      "grad_norm": 0.4934666156768799,
      "learning_rate": 8.247462563808817e-07,
      "loss": 1.348,
      "step": 189
    },
    {
      "epoch": 0.006484807631594665,
      "grad_norm": 0.5140841603279114,
      "learning_rate": 6.819348298638839e-07,
      "loss": 1.1634,
      "step": 190
    },
    {
      "epoch": 0.006518938198076743,
      "grad_norm": 0.5503444075584412,
      "learning_rate": 5.526064699265753e-07,
      "loss": 1.4757,
      "step": 191
    },
    {
      "epoch": 0.0065530687645588195,
      "grad_norm": 0.5057629346847534,
      "learning_rate": 4.367965336512403e-07,
      "loss": 1.3663,
      "step": 192
    },
    {
      "epoch": 0.006587199331040897,
      "grad_norm": 0.5920835733413696,
      "learning_rate": 3.3453668231809286e-07,
      "loss": 1.3937,
      "step": 193
    },
    {
      "epoch": 0.006621329897522974,
      "grad_norm": 0.5021880865097046,
      "learning_rate": 2.458548727494292e-07,
      "loss": 1.3377,
      "step": 194
    },
    {
      "epoch": 0.006655460464005052,
      "grad_norm": 0.6006019711494446,
      "learning_rate": 1.7077534966650766e-07,
      "loss": 1.3383,
      "step": 195
    },
    {
      "epoch": 0.006689591030487128,
      "grad_norm": 0.5368791818618774,
      "learning_rate": 1.0931863906127327e-07,
      "loss": 1.2476,
      "step": 196
    },
    {
      "epoch": 0.006723721596969206,
      "grad_norm": 0.5480520129203796,
      "learning_rate": 6.150154258476315e-08,
      "loss": 1.3689,
      "step": 197
    },
    {
      "epoch": 0.006757852163451283,
      "grad_norm": 0.6008732318878174,
      "learning_rate": 2.7337132953697554e-08,
      "loss": 1.398,
      "step": 198
    },
    {
      "epoch": 0.00679198272993336,
      "grad_norm": 0.6981407403945923,
      "learning_rate": 6.834750376549792e-09,
      "loss": 1.5422,
      "step": 199
    },
    {
      "epoch": 0.006826113296415437,
      "grad_norm": 0.7063643932342529,
      "learning_rate": 0.0,
      "loss": 1.6255,
      "step": 200
    },
    {
      "epoch": 0.006826113296415437,
      "eval_loss": 1.284598708152771,
      "eval_runtime": 1618.0775,
      "eval_samples_per_second": 30.497,
      "eval_steps_per_second": 7.624,
      "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": 6.028005784682496e+16,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}