{
  "best_metric": 0.9374632239341736,
  "best_model_checkpoint": "miner_id_24/checkpoint-200",
  "epoch": 0.04497161167013323,
  "eval_steps": 50,
  "global_step": 200,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.00022485805835066613,
      "grad_norm": 1.8806191682815552,
      "learning_rate": 1e-05,
      "loss": 1.2579,
      "step": 1
    },
    {
      "epoch": 0.00022485805835066613,
      "eval_loss": 1.3786506652832031,
      "eval_runtime": 568.1781,
      "eval_samples_per_second": 13.182,
      "eval_steps_per_second": 3.297,
      "step": 1
    },
    {
      "epoch": 0.00044971611670133226,
      "grad_norm": 2.5830066204071045,
      "learning_rate": 2e-05,
      "loss": 1.2788,
      "step": 2
    },
    {
      "epoch": 0.0006745741750519984,
      "grad_norm": 1.615217924118042,
      "learning_rate": 3e-05,
      "loss": 1.2435,
      "step": 3
    },
    {
      "epoch": 0.0008994322334026645,
      "grad_norm": 2.476015329360962,
      "learning_rate": 4e-05,
      "loss": 1.2402,
      "step": 4
    },
    {
      "epoch": 0.0011242902917533307,
      "grad_norm": 0.8700243234634399,
      "learning_rate": 5e-05,
      "loss": 1.1849,
      "step": 5
    },
    {
      "epoch": 0.001349148350103997,
      "grad_norm": 0.7422791123390198,
      "learning_rate": 6e-05,
      "loss": 1.182,
      "step": 6
    },
    {
      "epoch": 0.001574006408454663,
      "grad_norm": 0.6578545570373535,
      "learning_rate": 7e-05,
      "loss": 1.0817,
      "step": 7
    },
    {
      "epoch": 0.001798864466805329,
      "grad_norm": 0.9152142405509949,
      "learning_rate": 8e-05,
      "loss": 1.0839,
      "step": 8
    },
    {
      "epoch": 0.0020237225251559954,
      "grad_norm": 0.6503143906593323,
      "learning_rate": 9e-05,
      "loss": 1.0567,
      "step": 9
    },
    {
      "epoch": 0.0022485805835066614,
      "grad_norm": 0.7820642590522766,
      "learning_rate": 0.0001,
      "loss": 1.0048,
      "step": 10
    },
    {
      "epoch": 0.0024734386418573274,
      "grad_norm": 0.56891268491745,
      "learning_rate": 9.999316524962345e-05,
      "loss": 1.0555,
      "step": 11
    },
    {
      "epoch": 0.002698296700207994,
      "grad_norm": 0.546521008014679,
      "learning_rate": 9.997266286704631e-05,
      "loss": 1.0427,
      "step": 12
    },
    {
      "epoch": 0.0029231547585586598,
      "grad_norm": 0.5124958753585815,
      "learning_rate": 9.993849845741524e-05,
      "loss": 1.0157,
      "step": 13
    },
    {
      "epoch": 0.003148012816909326,
      "grad_norm": 0.49736088514328003,
      "learning_rate": 9.989068136093873e-05,
      "loss": 1.0018,
      "step": 14
    },
    {
      "epoch": 0.003372870875259992,
      "grad_norm": 0.5623443126678467,
      "learning_rate": 9.98292246503335e-05,
      "loss": 1.0274,
      "step": 15
    },
    {
      "epoch": 0.003597728933610658,
      "grad_norm": 0.5166621804237366,
      "learning_rate": 9.975414512725057e-05,
      "loss": 0.9927,
      "step": 16
    },
    {
      "epoch": 0.0038225869919613245,
      "grad_norm": 0.45535698533058167,
      "learning_rate": 9.966546331768191e-05,
      "loss": 0.8682,
      "step": 17
    },
    {
      "epoch": 0.004047445050311991,
      "grad_norm": 0.4689866900444031,
      "learning_rate": 9.956320346634876e-05,
      "loss": 0.9739,
      "step": 18
    },
    {
      "epoch": 0.004272303108662657,
      "grad_norm": 0.47900810837745667,
      "learning_rate": 9.944739353007344e-05,
      "loss": 0.957,
      "step": 19
    },
    {
      "epoch": 0.004497161167013323,
      "grad_norm": 0.5019671320915222,
      "learning_rate": 9.931806517013612e-05,
      "loss": 1.0251,
      "step": 20
    },
    {
      "epoch": 0.004722019225363989,
      "grad_norm": 0.49780118465423584,
      "learning_rate": 9.917525374361912e-05,
      "loss": 0.9817,
      "step": 21
    },
    {
      "epoch": 0.004946877283714655,
      "grad_norm": 0.516036868095398,
      "learning_rate": 9.901899829374047e-05,
      "loss": 1.012,
      "step": 22
    },
    {
      "epoch": 0.005171735342065322,
      "grad_norm": 0.4902551472187042,
      "learning_rate": 9.884934153917997e-05,
      "loss": 0.9516,
      "step": 23
    },
    {
      "epoch": 0.005396593400415988,
      "grad_norm": 0.5016360878944397,
      "learning_rate": 9.86663298624003e-05,
      "loss": 0.9072,
      "step": 24
    },
    {
      "epoch": 0.0056214514587666535,
      "grad_norm": 0.5010817050933838,
      "learning_rate": 9.847001329696653e-05,
      "loss": 0.9979,
      "step": 25
    },
    {
      "epoch": 0.0058463095171173195,
      "grad_norm": 0.47437718510627747,
      "learning_rate": 9.826044551386744e-05,
      "loss": 0.9814,
      "step": 26
    },
    {
      "epoch": 0.0060711675754679855,
      "grad_norm": 0.499470055103302,
      "learning_rate": 9.803768380684242e-05,
      "loss": 0.9873,
      "step": 27
    },
    {
      "epoch": 0.006296025633818652,
      "grad_norm": 0.4734216630458832,
      "learning_rate": 9.780178907671789e-05,
      "loss": 0.9551,
      "step": 28
    },
    {
      "epoch": 0.006520883692169318,
      "grad_norm": 0.5559307336807251,
      "learning_rate": 9.755282581475769e-05,
      "loss": 0.9976,
      "step": 29
    },
    {
      "epoch": 0.006745741750519984,
      "grad_norm": 0.5389547944068909,
      "learning_rate": 9.729086208503174e-05,
      "loss": 0.996,
      "step": 30
    },
    {
      "epoch": 0.00697059980887065,
      "grad_norm": 0.5211666226387024,
      "learning_rate": 9.701596950580806e-05,
      "loss": 0.9822,
      "step": 31
    },
    {
      "epoch": 0.007195457867221316,
      "grad_norm": 0.5321973562240601,
      "learning_rate": 9.672822322997305e-05,
      "loss": 0.9878,
      "step": 32
    },
    {
      "epoch": 0.007420315925571983,
      "grad_norm": 0.5040099620819092,
      "learning_rate": 9.642770192448536e-05,
      "loss": 0.9692,
      "step": 33
    },
    {
      "epoch": 0.007645173983922649,
      "grad_norm": 0.5069547295570374,
      "learning_rate": 9.611448774886924e-05,
      "loss": 0.9299,
      "step": 34
    },
    {
      "epoch": 0.007870032042273316,
      "grad_norm": 0.5000737905502319,
      "learning_rate": 9.578866633275288e-05,
      "loss": 0.9669,
      "step": 35
    },
    {
      "epoch": 0.008094890100623982,
      "grad_norm": 0.5586211085319519,
      "learning_rate": 9.545032675245813e-05,
      "loss": 0.9673,
      "step": 36
    },
    {
      "epoch": 0.008319748158974648,
      "grad_norm": 0.5464363098144531,
      "learning_rate": 9.509956150664796e-05,
      "loss": 1.0051,
      "step": 37
    },
    {
      "epoch": 0.008544606217325314,
      "grad_norm": 0.5479859709739685,
      "learning_rate": 9.473646649103818e-05,
      "loss": 0.9787,
      "step": 38
    },
    {
      "epoch": 0.00876946427567598,
      "grad_norm": 0.5399601459503174,
      "learning_rate": 9.43611409721806e-05,
      "loss": 0.9772,
      "step": 39
    },
    {
      "epoch": 0.008994322334026646,
      "grad_norm": 0.5699008107185364,
      "learning_rate": 9.397368756032445e-05,
      "loss": 1.0054,
      "step": 40
    },
    {
      "epoch": 0.009219180392377312,
      "grad_norm": 0.5823690891265869,
      "learning_rate": 9.357421218136386e-05,
      "loss": 0.9262,
      "step": 41
    },
    {
      "epoch": 0.009444038450727978,
      "grad_norm": 0.5686464309692383,
      "learning_rate": 9.316282404787871e-05,
      "loss": 0.9975,
      "step": 42
    },
    {
      "epoch": 0.009668896509078644,
      "grad_norm": 0.5725706219673157,
      "learning_rate": 9.273963562927695e-05,
      "loss": 1.0302,
      "step": 43
    },
    {
      "epoch": 0.00989375456742931,
      "grad_norm": 0.6007263660430908,
      "learning_rate": 9.230476262104677e-05,
      "loss": 0.9456,
      "step": 44
    },
    {
      "epoch": 0.010118612625779977,
      "grad_norm": 0.5712608695030212,
      "learning_rate": 9.185832391312644e-05,
      "loss": 0.9307,
      "step": 45
    },
    {
      "epoch": 0.010343470684130643,
      "grad_norm": 0.6367188096046448,
      "learning_rate": 9.140044155740101e-05,
      "loss": 0.9927,
      "step": 46
    },
    {
      "epoch": 0.01056832874248131,
      "grad_norm": 0.8078854084014893,
      "learning_rate": 9.093124073433463e-05,
      "loss": 0.9477,
      "step": 47
    },
    {
      "epoch": 0.010793186800831975,
      "grad_norm": 0.6796431541442871,
      "learning_rate": 9.045084971874738e-05,
      "loss": 1.0419,
      "step": 48
    },
    {
      "epoch": 0.011018044859182641,
      "grad_norm": 0.7045455574989319,
      "learning_rate": 8.995939984474624e-05,
      "loss": 0.9817,
      "step": 49
    },
    {
      "epoch": 0.011242902917533307,
      "grad_norm": 0.8687090873718262,
      "learning_rate": 8.945702546981969e-05,
      "loss": 0.9828,
      "step": 50
    },
    {
      "epoch": 0.011242902917533307,
      "eval_loss": 0.9971754550933838,
      "eval_runtime": 571.5536,
      "eval_samples_per_second": 13.105,
      "eval_steps_per_second": 3.277,
      "step": 50
    },
    {
      "epoch": 0.011467760975883973,
      "grad_norm": 0.7446148991584778,
      "learning_rate": 8.894386393810563e-05,
      "loss": 0.9677,
      "step": 51
    },
    {
      "epoch": 0.011692619034234639,
      "grad_norm": 0.5402625203132629,
      "learning_rate": 8.842005554284296e-05,
      "loss": 1.008,
      "step": 52
    },
    {
      "epoch": 0.011917477092585305,
      "grad_norm": 0.4295448660850525,
      "learning_rate": 8.788574348801675e-05,
      "loss": 1.0036,
      "step": 53
    },
    {
      "epoch": 0.012142335150935971,
      "grad_norm": 0.4327336549758911,
      "learning_rate": 8.73410738492077e-05,
      "loss": 0.992,
      "step": 54
    },
    {
      "epoch": 0.012367193209286639,
      "grad_norm": 0.4199539124965668,
      "learning_rate": 8.678619553365659e-05,
      "loss": 0.9341,
      "step": 55
    },
    {
      "epoch": 0.012592051267637305,
      "grad_norm": 0.3991791903972626,
      "learning_rate": 8.622126023955446e-05,
      "loss": 1.0042,
      "step": 56
    },
    {
      "epoch": 0.01281690932598797,
      "grad_norm": 0.3713171184062958,
      "learning_rate": 8.564642241456986e-05,
      "loss": 0.9268,
      "step": 57
    },
    {
      "epoch": 0.013041767384338637,
      "grad_norm": 0.39422792196273804,
      "learning_rate": 8.506183921362443e-05,
      "loss": 0.9693,
      "step": 58
    },
    {
      "epoch": 0.013266625442689303,
      "grad_norm": 0.37149858474731445,
      "learning_rate": 8.44676704559283e-05,
      "loss": 0.9771,
      "step": 59
    },
    {
      "epoch": 0.013491483501039968,
      "grad_norm": 0.39656326174736023,
      "learning_rate": 8.386407858128706e-05,
      "loss": 0.9493,
      "step": 60
    },
    {
      "epoch": 0.013716341559390634,
      "grad_norm": 0.38199350237846375,
      "learning_rate": 8.32512286056924e-05,
      "loss": 0.9163,
      "step": 61
    },
    {
      "epoch": 0.0139411996177413,
      "grad_norm": 0.4138825833797455,
      "learning_rate": 8.262928807620843e-05,
      "loss": 0.9293,
      "step": 62
    },
    {
      "epoch": 0.014166057676091966,
      "grad_norm": 0.4193970263004303,
      "learning_rate": 8.199842702516583e-05,
      "loss": 0.9536,
      "step": 63
    },
    {
      "epoch": 0.014390915734442632,
      "grad_norm": 0.4680027365684509,
      "learning_rate": 8.135881792367686e-05,
      "loss": 0.9753,
      "step": 64
    },
    {
      "epoch": 0.0146157737927933,
      "grad_norm": 0.3954637944698334,
      "learning_rate": 8.07106356344834e-05,
      "loss": 0.9783,
      "step": 65
    },
    {
      "epoch": 0.014840631851143966,
      "grad_norm": 0.40615153312683105,
      "learning_rate": 8.005405736415126e-05,
      "loss": 0.9515,
      "step": 66
    },
    {
      "epoch": 0.015065489909494632,
      "grad_norm": 0.4088502824306488,
      "learning_rate": 7.938926261462366e-05,
      "loss": 0.94,
      "step": 67
    },
    {
      "epoch": 0.015290347967845298,
      "grad_norm": 0.42128804326057434,
      "learning_rate": 7.871643313414718e-05,
      "loss": 0.9922,
      "step": 68
    },
    {
      "epoch": 0.015515206026195964,
      "grad_norm": 0.39310500025749207,
      "learning_rate": 7.803575286758364e-05,
      "loss": 0.9647,
      "step": 69
    },
    {
      "epoch": 0.01574006408454663,
      "grad_norm": 0.3965868055820465,
      "learning_rate": 7.734740790612136e-05,
      "loss": 0.9258,
      "step": 70
    },
    {
      "epoch": 0.015964922142897298,
      "grad_norm": 0.4081268012523651,
      "learning_rate": 7.66515864363997e-05,
      "loss": 0.8691,
      "step": 71
    },
    {
      "epoch": 0.016189780201247964,
      "grad_norm": 0.39910760521888733,
      "learning_rate": 7.594847868906076e-05,
      "loss": 0.9237,
      "step": 72
    },
    {
      "epoch": 0.01641463825959863,
      "grad_norm": 0.4301849901676178,
      "learning_rate": 7.52382768867422e-05,
      "loss": 0.9559,
      "step": 73
    },
    {
      "epoch": 0.016639496317949296,
      "grad_norm": 0.41685670614242554,
      "learning_rate": 7.452117519152542e-05,
      "loss": 0.9708,
      "step": 74
    },
    {
      "epoch": 0.01686435437629996,
      "grad_norm": 0.4297255277633667,
      "learning_rate": 7.379736965185368e-05,
      "loss": 0.9999,
      "step": 75
    },
    {
      "epoch": 0.017089212434650627,
      "grad_norm": 0.43522655963897705,
      "learning_rate": 7.30670581489344e-05,
      "loss": 1.0075,
      "step": 76
    },
    {
      "epoch": 0.017314070493001293,
      "grad_norm": 0.42515212297439575,
      "learning_rate": 7.233044034264034e-05,
      "loss": 0.9256,
      "step": 77
    },
    {
      "epoch": 0.01753892855135196,
      "grad_norm": 0.44875699281692505,
      "learning_rate": 7.158771761692464e-05,
      "loss": 0.9232,
      "step": 78
    },
    {
      "epoch": 0.017763786609702625,
      "grad_norm": 0.43430301547050476,
      "learning_rate": 7.083909302476453e-05,
      "loss": 0.8872,
      "step": 79
    },
    {
      "epoch": 0.01798864466805329,
      "grad_norm": 0.456939697265625,
      "learning_rate": 7.008477123264848e-05,
      "loss": 0.927,
      "step": 80
    },
    {
      "epoch": 0.018213502726403957,
      "grad_norm": 0.4357711970806122,
      "learning_rate": 6.932495846462261e-05,
      "loss": 0.9442,
      "step": 81
    },
    {
      "epoch": 0.018438360784754623,
      "grad_norm": 0.47479766607284546,
      "learning_rate": 6.855986244591104e-05,
      "loss": 1.0109,
      "step": 82
    },
    {
      "epoch": 0.01866321884310529,
      "grad_norm": 0.47166144847869873,
      "learning_rate": 6.778969234612584e-05,
      "loss": 0.9001,
      "step": 83
    },
    {
      "epoch": 0.018888076901455955,
      "grad_norm": 0.4973955452442169,
      "learning_rate": 6.701465872208216e-05,
      "loss": 0.9628,
      "step": 84
    },
    {
      "epoch": 0.01911293495980662,
      "grad_norm": 0.608281135559082,
      "learning_rate": 6.623497346023418e-05,
      "loss": 1.0058,
      "step": 85
    },
    {
      "epoch": 0.019337793018157287,
      "grad_norm": 0.5094743967056274,
      "learning_rate": 6.545084971874738e-05,
      "loss": 0.9292,
      "step": 86
    },
    {
      "epoch": 0.019562651076507953,
      "grad_norm": 0.5177169442176819,
      "learning_rate": 6.466250186922325e-05,
      "loss": 0.9035,
      "step": 87
    },
    {
      "epoch": 0.01978750913485862,
      "grad_norm": 0.4601903259754181,
      "learning_rate": 6.387014543809223e-05,
      "loss": 0.9548,
      "step": 88
    },
    {
      "epoch": 0.020012367193209285,
      "grad_norm": 0.4744357764720917,
      "learning_rate": 6.307399704769099e-05,
      "loss": 0.9315,
      "step": 89
    },
    {
      "epoch": 0.020237225251559954,
      "grad_norm": 0.49908632040023804,
      "learning_rate": 6.227427435703997e-05,
      "loss": 0.9448,
      "step": 90
    },
    {
      "epoch": 0.02046208330991062,
      "grad_norm": 0.48518458008766174,
      "learning_rate": 6.147119600233758e-05,
      "loss": 0.908,
      "step": 91
    },
    {
      "epoch": 0.020686941368261286,
      "grad_norm": 0.5182993412017822,
      "learning_rate": 6.066498153718735e-05,
      "loss": 0.9394,
      "step": 92
    },
    {
      "epoch": 0.020911799426611952,
      "grad_norm": 0.5653586983680725,
      "learning_rate": 5.985585137257401e-05,
      "loss": 1.0121,
      "step": 93
    },
    {
      "epoch": 0.02113665748496262,
      "grad_norm": 0.5557526350021362,
      "learning_rate": 5.90440267166055e-05,
      "loss": 0.9834,
      "step": 94
    },
    {
      "epoch": 0.021361515543313284,
      "grad_norm": 0.5737510323524475,
      "learning_rate": 5.8229729514036705e-05,
      "loss": 0.8839,
      "step": 95
    },
    {
      "epoch": 0.02158637360166395,
      "grad_norm": 0.5179717540740967,
      "learning_rate": 5.74131823855921e-05,
      "loss": 0.9293,
      "step": 96
    },
    {
      "epoch": 0.021811231660014616,
      "grad_norm": 0.567559540271759,
      "learning_rate": 5.6594608567103456e-05,
      "loss": 0.9413,
      "step": 97
    },
    {
      "epoch": 0.022036089718365282,
      "grad_norm": 0.6300162076950073,
      "learning_rate": 5.577423184847932e-05,
      "loss": 1.0136,
      "step": 98
    },
    {
      "epoch": 0.022260947776715948,
      "grad_norm": 0.6745202541351318,
      "learning_rate": 5.495227651252315e-05,
      "loss": 0.9981,
      "step": 99
    },
    {
      "epoch": 0.022485805835066614,
      "grad_norm": 0.7574002742767334,
      "learning_rate": 5.4128967273616625e-05,
      "loss": 1.0943,
      "step": 100
    },
    {
      "epoch": 0.022485805835066614,
      "eval_loss": 0.9752497673034668,
      "eval_runtime": 571.003,
      "eval_samples_per_second": 13.117,
      "eval_steps_per_second": 3.28,
      "step": 100
    },
    {
      "epoch": 0.02271066389341728,
      "grad_norm": 0.6196216940879822,
      "learning_rate": 5.330452921628497e-05,
      "loss": 0.9975,
      "step": 101
    },
    {
      "epoch": 0.022935521951767946,
      "grad_norm": 0.59757399559021,
      "learning_rate": 5.247918773366112e-05,
      "loss": 0.9745,
      "step": 102
    },
    {
      "epoch": 0.023160380010118612,
      "grad_norm": 0.48381441831588745,
      "learning_rate": 5.165316846586541e-05,
      "loss": 0.9699,
      "step": 103
    },
    {
      "epoch": 0.023385238068469278,
      "grad_norm": 0.3899124264717102,
      "learning_rate": 5.0826697238317935e-05,
      "loss": 0.953,
      "step": 104
    },
    {
      "epoch": 0.023610096126819944,
      "grad_norm": 0.35935091972351074,
      "learning_rate": 5e-05,
      "loss": 0.9624,
      "step": 105
    },
    {
      "epoch": 0.02383495418517061,
      "grad_norm": 0.3418393135070801,
      "learning_rate": 4.917330276168208e-05,
      "loss": 0.9085,
      "step": 106
    },
    {
      "epoch": 0.024059812243521276,
      "grad_norm": 0.35070767998695374,
      "learning_rate": 4.834683153413459e-05,
      "loss": 0.9194,
      "step": 107
    },
    {
      "epoch": 0.024284670301871942,
      "grad_norm": 0.38445037603378296,
      "learning_rate": 4.7520812266338885e-05,
      "loss": 0.9778,
      "step": 108
    },
    {
      "epoch": 0.024509528360222608,
      "grad_norm": 0.3916020095348358,
      "learning_rate": 4.669547078371504e-05,
      "loss": 0.9254,
      "step": 109
    },
    {
      "epoch": 0.024734386418573277,
      "grad_norm": 0.36393749713897705,
      "learning_rate": 4.5871032726383386e-05,
      "loss": 0.9987,
      "step": 110
    },
    {
      "epoch": 0.024959244476923943,
      "grad_norm": 0.38105857372283936,
      "learning_rate": 4.504772348747687e-05,
      "loss": 0.9539,
      "step": 111
    },
    {
      "epoch": 0.02518410253527461,
      "grad_norm": 0.38950514793395996,
      "learning_rate": 4.4225768151520694e-05,
      "loss": 0.9325,
      "step": 112
    },
    {
      "epoch": 0.025408960593625275,
      "grad_norm": 0.37209662795066833,
      "learning_rate": 4.3405391432896555e-05,
      "loss": 0.9816,
      "step": 113
    },
    {
      "epoch": 0.02563381865197594,
      "grad_norm": 0.35272645950317383,
      "learning_rate": 4.2586817614407895e-05,
      "loss": 0.8965,
      "step": 114
    },
    {
      "epoch": 0.025858676710326607,
      "grad_norm": 0.36095669865608215,
      "learning_rate": 4.17702704859633e-05,
      "loss": 0.9352,
      "step": 115
    },
    {
      "epoch": 0.026083534768677273,
      "grad_norm": 0.36486682295799255,
      "learning_rate": 4.095597328339452e-05,
      "loss": 0.9505,
      "step": 116
    },
    {
      "epoch": 0.02630839282702794,
      "grad_norm": 0.3896653652191162,
      "learning_rate": 4.0144148627425993e-05,
      "loss": 0.9374,
      "step": 117
    },
    {
      "epoch": 0.026533250885378605,
      "grad_norm": 0.37614402174949646,
      "learning_rate": 3.933501846281267e-05,
      "loss": 0.8867,
      "step": 118
    },
    {
      "epoch": 0.02675810894372927,
      "grad_norm": 0.3754301369190216,
      "learning_rate": 3.852880399766243e-05,
      "loss": 0.9452,
      "step": 119
    },
    {
      "epoch": 0.026982967002079937,
      "grad_norm": 0.4079149067401886,
      "learning_rate": 3.772572564296005e-05,
      "loss": 0.9692,
      "step": 120
    },
    {
      "epoch": 0.027207825060430603,
      "grad_norm": 0.38498255610466003,
      "learning_rate": 3.6926002952309016e-05,
      "loss": 0.9134,
      "step": 121
    },
    {
      "epoch": 0.02743268311878127,
      "grad_norm": 0.39194753766059875,
      "learning_rate": 3.612985456190778e-05,
      "loss": 0.9304,
      "step": 122
    },
    {
      "epoch": 0.027657541177131935,
      "grad_norm": 0.377787709236145,
      "learning_rate": 3.533749813077677e-05,
      "loss": 0.8504,
      "step": 123
    },
    {
      "epoch": 0.0278823992354826,
      "grad_norm": 0.4129648208618164,
      "learning_rate": 3.4549150281252636e-05,
      "loss": 0.949,
      "step": 124
    },
    {
      "epoch": 0.028107257293833267,
      "grad_norm": 0.4060305655002594,
      "learning_rate": 3.3765026539765834e-05,
      "loss": 0.94,
      "step": 125
    },
    {
      "epoch": 0.028332115352183933,
      "grad_norm": 0.46018579602241516,
      "learning_rate": 3.298534127791785e-05,
      "loss": 0.9199,
      "step": 126
    },
    {
      "epoch": 0.0285569734105346,
      "grad_norm": 0.4293648898601532,
      "learning_rate": 3.221030765387417e-05,
      "loss": 0.9277,
      "step": 127
    },
    {
      "epoch": 0.028781831468885265,
      "grad_norm": 0.4215858578681946,
      "learning_rate": 3.144013755408895e-05,
      "loss": 0.8617,
      "step": 128
    },
    {
      "epoch": 0.02900668952723593,
      "grad_norm": 0.4051620662212372,
      "learning_rate": 3.0675041535377405e-05,
      "loss": 0.9274,
      "step": 129
    },
    {
      "epoch": 0.0292315475855866,
      "grad_norm": 0.4426076412200928,
      "learning_rate": 2.991522876735154e-05,
      "loss": 0.8612,
      "step": 130
    },
    {
      "epoch": 0.029456405643937266,
      "grad_norm": 0.4157659709453583,
      "learning_rate": 2.916090697523549e-05,
      "loss": 0.9196,
      "step": 131
    },
    {
      "epoch": 0.029681263702287932,
      "grad_norm": 0.46329042315483093,
      "learning_rate": 2.8412282383075363e-05,
      "loss": 0.8455,
      "step": 132
    },
    {
      "epoch": 0.029906121760638598,
      "grad_norm": 0.4324726462364197,
      "learning_rate": 2.766955965735968e-05,
      "loss": 0.921,
      "step": 133
    },
    {
      "epoch": 0.030130979818989264,
      "grad_norm": 0.44565272331237793,
      "learning_rate": 2.693294185106562e-05,
      "loss": 0.9685,
      "step": 134
    },
    {
      "epoch": 0.03035583787733993,
      "grad_norm": 0.46471086144447327,
      "learning_rate": 2.6202630348146324e-05,
      "loss": 0.9386,
      "step": 135
    },
    {
      "epoch": 0.030580695935690596,
      "grad_norm": 0.453244686126709,
      "learning_rate": 2.547882480847461e-05,
      "loss": 0.863,
      "step": 136
    },
    {
      "epoch": 0.030805553994041262,
      "grad_norm": 0.48785701394081116,
      "learning_rate": 2.476172311325783e-05,
      "loss": 1.0332,
      "step": 137
    },
    {
      "epoch": 0.031030412052391928,
      "grad_norm": 0.45043039321899414,
      "learning_rate": 2.405152131093926e-05,
      "loss": 0.9906,
      "step": 138
    },
    {
      "epoch": 0.03125527011074259,
      "grad_norm": 0.4798925518989563,
      "learning_rate": 2.3348413563600325e-05,
      "loss": 0.9672,
      "step": 139
    },
    {
      "epoch": 0.03148012816909326,
      "grad_norm": 0.5111128687858582,
      "learning_rate": 2.2652592093878666e-05,
      "loss": 0.9239,
      "step": 140
    },
    {
      "epoch": 0.03170498622744393,
      "grad_norm": 0.4969828724861145,
      "learning_rate": 2.196424713241637e-05,
      "loss": 0.9697,
      "step": 141
    },
    {
      "epoch": 0.031929844285794595,
      "grad_norm": 0.5612659454345703,
      "learning_rate": 2.128356686585282e-05,
      "loss": 0.982,
      "step": 142
    },
    {
      "epoch": 0.03215470234414526,
      "grad_norm": 0.5021900534629822,
      "learning_rate": 2.061073738537635e-05,
      "loss": 0.9667,
      "step": 143
    },
    {
      "epoch": 0.03237956040249593,
      "grad_norm": 0.5489165782928467,
      "learning_rate": 1.9945942635848748e-05,
      "loss": 0.9758,
      "step": 144
    },
    {
      "epoch": 0.03260441846084659,
      "grad_norm": 0.5908274054527283,
      "learning_rate": 1.928936436551661e-05,
      "loss": 1.0102,
      "step": 145
    },
    {
      "epoch": 0.03282927651919726,
      "grad_norm": 0.5742616653442383,
      "learning_rate": 1.8641182076323148e-05,
      "loss": 1.0206,
      "step": 146
    },
    {
      "epoch": 0.033054134577547925,
      "grad_norm": 0.565596878528595,
      "learning_rate": 1.800157297483417e-05,
      "loss": 0.9866,
      "step": 147
    },
    {
      "epoch": 0.03327899263589859,
      "grad_norm": 0.6190233826637268,
      "learning_rate": 1.7370711923791567e-05,
      "loss": 0.9242,
      "step": 148
    },
    {
      "epoch": 0.03350385069424926,
      "grad_norm": 0.7298147082328796,
      "learning_rate": 1.6748771394307585e-05,
      "loss": 1.0115,
      "step": 149
    },
    {
      "epoch": 0.03372870875259992,
      "grad_norm": 0.8240206241607666,
      "learning_rate": 1.6135921418712956e-05,
      "loss": 0.9919,
      "step": 150
    },
    {
      "epoch": 0.03372870875259992,
      "eval_loss": 0.9440723061561584,
      "eval_runtime": 571.2848,
      "eval_samples_per_second": 13.111,
      "eval_steps_per_second": 3.279,
      "step": 150
    },
    {
      "epoch": 0.03395356681095059,
      "grad_norm": 0.4282836616039276,
      "learning_rate": 1.553232954407171e-05,
      "loss": 0.9762,
      "step": 151
    },
    {
      "epoch": 0.034178424869301255,
      "grad_norm": 0.40817877650260925,
      "learning_rate": 1.4938160786375572e-05,
      "loss": 0.9298,
      "step": 152
    },
    {
      "epoch": 0.03440328292765192,
      "grad_norm": 0.4109857380390167,
      "learning_rate": 1.435357758543015e-05,
      "loss": 0.9347,
      "step": 153
    },
    {
      "epoch": 0.03462814098600259,
      "grad_norm": 0.42893314361572266,
      "learning_rate": 1.3778739760445552e-05,
      "loss": 0.9505,
      "step": 154
    },
    {
      "epoch": 0.03485299904435325,
      "grad_norm": 0.43512511253356934,
      "learning_rate": 1.3213804466343421e-05,
      "loss": 0.9328,
      "step": 155
    },
    {
      "epoch": 0.03507785710270392,
      "grad_norm": 0.3928248882293701,
      "learning_rate": 1.2658926150792322e-05,
      "loss": 0.9798,
      "step": 156
    },
    {
      "epoch": 0.035302715161054585,
      "grad_norm": 0.39213746786117554,
      "learning_rate": 1.2114256511983274e-05,
      "loss": 0.9029,
      "step": 157
    },
    {
      "epoch": 0.03552757321940525,
      "grad_norm": 0.35876545310020447,
      "learning_rate": 1.157994445715706e-05,
      "loss": 0.9589,
      "step": 158
    },
    {
      "epoch": 0.03575243127775592,
      "grad_norm": 0.3770306706428528,
      "learning_rate": 1.1056136061894384e-05,
      "loss": 0.9798,
      "step": 159
    },
    {
      "epoch": 0.03597728933610658,
      "grad_norm": 0.34038081765174866,
      "learning_rate": 1.0542974530180327e-05,
      "loss": 0.908,
      "step": 160
    },
    {
      "epoch": 0.03620214739445725,
      "grad_norm": 0.37104249000549316,
      "learning_rate": 1.0040600155253765e-05,
      "loss": 0.9635,
      "step": 161
    },
    {
      "epoch": 0.036427005452807915,
      "grad_norm": 0.35004961490631104,
      "learning_rate": 9.549150281252633e-06,
      "loss": 0.9621,
      "step": 162
    },
    {
      "epoch": 0.03665186351115858,
      "grad_norm": 0.3390391767024994,
      "learning_rate": 9.068759265665384e-06,
      "loss": 0.8428,
      "step": 163
    },
    {
      "epoch": 0.036876721569509247,
      "grad_norm": 0.3623657524585724,
      "learning_rate": 8.599558442598998e-06,
      "loss": 0.9374,
      "step": 164
    },
    {
      "epoch": 0.03710157962785991,
      "grad_norm": 0.382797509431839,
      "learning_rate": 8.141676086873572e-06,
      "loss": 1.0065,
      "step": 165
    },
    {
      "epoch": 0.03732643768621058,
      "grad_norm": 0.38626664876937866,
      "learning_rate": 7.695237378953223e-06,
      "loss": 0.8628,
      "step": 166
    },
    {
      "epoch": 0.037551295744561244,
      "grad_norm": 0.3437883257865906,
      "learning_rate": 7.260364370723044e-06,
      "loss": 0.8957,
      "step": 167
    },
    {
      "epoch": 0.03777615380291191,
      "grad_norm": 0.36651861667633057,
      "learning_rate": 6.837175952121306e-06,
      "loss": 0.8681,
      "step": 168
    },
    {
      "epoch": 0.038001011861262576,
      "grad_norm": 0.3958579897880554,
      "learning_rate": 6.425787818636131e-06,
      "loss": 0.9642,
      "step": 169
    },
    {
      "epoch": 0.03822586991961324,
      "grad_norm": 0.4236045181751251,
      "learning_rate": 6.026312439675552e-06,
      "loss": 0.9815,
      "step": 170
    },
    {
      "epoch": 0.03845072797796391,
      "grad_norm": 0.3872464597225189,
      "learning_rate": 5.6388590278194096e-06,
      "loss": 0.907,
      "step": 171
    },
    {
      "epoch": 0.038675586036314574,
      "grad_norm": 0.4050854742527008,
      "learning_rate": 5.263533508961827e-06,
      "loss": 0.9439,
      "step": 172
    },
    {
      "epoch": 0.03890044409466524,
      "grad_norm": 0.39427775144577026,
      "learning_rate": 4.900438493352055e-06,
      "loss": 0.9351,
      "step": 173
    },
    {
      "epoch": 0.039125302153015906,
      "grad_norm": 0.3943425118923187,
      "learning_rate": 4.549673247541875e-06,
      "loss": 0.9114,
      "step": 174
    },
    {
      "epoch": 0.03935016021136657,
      "grad_norm": 0.5857791900634766,
      "learning_rate": 4.2113336672471245e-06,
      "loss": 0.9581,
      "step": 175
    },
    {
      "epoch": 0.03957501826971724,
      "grad_norm": 0.41377490758895874,
      "learning_rate": 3.885512251130763e-06,
      "loss": 0.8835,
      "step": 176
    },
    {
      "epoch": 0.039799876328067904,
      "grad_norm": 0.40625879168510437,
      "learning_rate": 3.5722980755146517e-06,
      "loss": 0.9659,
      "step": 177
    },
    {
      "epoch": 0.04002473438641857,
      "grad_norm": 0.4174712300300598,
      "learning_rate": 3.271776770026963e-06,
      "loss": 0.8942,
      "step": 178
    },
    {
      "epoch": 0.040249592444769236,
      "grad_norm": 0.4268491864204407,
      "learning_rate": 2.9840304941919415e-06,
      "loss": 0.9541,
      "step": 179
    },
    {
      "epoch": 0.04047445050311991,
      "grad_norm": 0.41554200649261475,
      "learning_rate": 2.7091379149682685e-06,
      "loss": 0.9705,
      "step": 180
    },
    {
      "epoch": 0.040699308561470575,
      "grad_norm": 0.4735603630542755,
      "learning_rate": 2.4471741852423237e-06,
      "loss": 0.9155,
      "step": 181
    },
    {
      "epoch": 0.04092416661982124,
      "grad_norm": 0.4195253849029541,
      "learning_rate": 2.1982109232821178e-06,
      "loss": 0.9913,
      "step": 182
    },
    {
      "epoch": 0.04114902467817191,
      "grad_norm": 0.4348553419113159,
      "learning_rate": 1.962316193157593e-06,
      "loss": 0.9285,
      "step": 183
    },
    {
      "epoch": 0.04137388273652257,
      "grad_norm": 0.4121484160423279,
      "learning_rate": 1.7395544861325718e-06,
      "loss": 0.8916,
      "step": 184
    },
    {
      "epoch": 0.04159874079487324,
      "grad_norm": 0.455618679523468,
      "learning_rate": 1.5299867030334814e-06,
      "loss": 0.9604,
      "step": 185
    },
    {
      "epoch": 0.041823598853223905,
      "grad_norm": 0.43906110525131226,
      "learning_rate": 1.333670137599713e-06,
      "loss": 0.9414,
      "step": 186
    },
    {
      "epoch": 0.04204845691157457,
      "grad_norm": 0.4594693183898926,
      "learning_rate": 1.1506584608200367e-06,
      "loss": 0.9729,
      "step": 187
    },
    {
      "epoch": 0.04227331496992524,
      "grad_norm": 0.45113545656204224,
      "learning_rate": 9.810017062595322e-07,
      "loss": 0.9503,
      "step": 188
    },
    {
      "epoch": 0.0424981730282759,
      "grad_norm": 0.48221638798713684,
      "learning_rate": 8.247462563808817e-07,
      "loss": 0.9329,
      "step": 189
    },
    {
      "epoch": 0.04272303108662657,
      "grad_norm": 0.5008561611175537,
      "learning_rate": 6.819348298638839e-07,
      "loss": 0.9516,
      "step": 190
    },
    {
      "epoch": 0.042947889144977235,
      "grad_norm": 0.5354289412498474,
      "learning_rate": 5.526064699265753e-07,
      "loss": 0.8798,
      "step": 191
    },
    {
      "epoch": 0.0431727472033279,
      "grad_norm": 0.5152722001075745,
      "learning_rate": 4.367965336512403e-07,
      "loss": 0.9689,
      "step": 192
    },
    {
      "epoch": 0.043397605261678567,
      "grad_norm": 0.4716539978981018,
      "learning_rate": 3.3453668231809286e-07,
      "loss": 0.9073,
      "step": 193
    },
    {
      "epoch": 0.04362246332002923,
      "grad_norm": 0.5449787974357605,
      "learning_rate": 2.458548727494292e-07,
      "loss": 0.9834,
      "step": 194
    },
    {
      "epoch": 0.0438473213783799,
      "grad_norm": 0.5265944600105286,
      "learning_rate": 1.7077534966650766e-07,
      "loss": 0.9185,
      "step": 195
    },
    {
      "epoch": 0.044072179436730564,
      "grad_norm": 0.5747174620628357,
      "learning_rate": 1.0931863906127327e-07,
      "loss": 0.9268,
      "step": 196
    },
    {
      "epoch": 0.04429703749508123,
      "grad_norm": 0.6175982356071472,
      "learning_rate": 6.150154258476315e-08,
      "loss": 0.9133,
      "step": 197
    },
    {
      "epoch": 0.044521895553431896,
      "grad_norm": 0.6425139904022217,
      "learning_rate": 2.7337132953697554e-08,
      "loss": 0.9113,
      "step": 198
    },
    {
      "epoch": 0.04474675361178256,
      "grad_norm": 0.6688318848609924,
      "learning_rate": 6.834750376549792e-09,
      "loss": 0.9092,
      "step": 199
    },
    {
      "epoch": 0.04497161167013323,
      "grad_norm": 0.7794017791748047,
      "learning_rate": 0.0,
      "loss": 0.9803,
      "step": 200
    },
    {
      "epoch": 0.04497161167013323,
      "eval_loss": 0.9374632239341736,
      "eval_runtime": 571.082,
      "eval_samples_per_second": 13.115,
      "eval_steps_per_second": 3.28,
      "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": 3.024569725385441e+17,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}