{
  "best_metric": 1.1267578601837158,
  "best_model_checkpoint": "miner_id_24/checkpoint-200",
  "epoch": 0.45454545454545453,
  "eval_steps": 50,
  "global_step": 200,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0022727272727272726,
      "grad_norm": 0.12057740986347198,
      "learning_rate": 1e-05,
      "loss": 0.7837,
      "step": 1
    },
    {
      "epoch": 0.0022727272727272726,
      "eval_loss": 1.3961470127105713,
      "eval_runtime": 25.0127,
      "eval_samples_per_second": 29.625,
      "eval_steps_per_second": 7.436,
      "step": 1
    },
    {
      "epoch": 0.004545454545454545,
      "grad_norm": 0.16642504930496216,
      "learning_rate": 2e-05,
      "loss": 0.9355,
      "step": 2
    },
    {
      "epoch": 0.006818181818181818,
      "grad_norm": 0.1952921450138092,
      "learning_rate": 3e-05,
      "loss": 1.158,
      "step": 3
    },
    {
      "epoch": 0.00909090909090909,
      "grad_norm": 0.2508404850959778,
      "learning_rate": 4e-05,
      "loss": 1.1104,
      "step": 4
    },
    {
      "epoch": 0.011363636363636364,
      "grad_norm": 0.21424071490764618,
      "learning_rate": 5e-05,
      "loss": 1.0916,
      "step": 5
    },
    {
      "epoch": 0.013636363636363636,
      "grad_norm": 0.20132502913475037,
      "learning_rate": 6e-05,
      "loss": 1.2617,
      "step": 6
    },
    {
      "epoch": 0.015909090909090907,
      "grad_norm": 0.18928009271621704,
      "learning_rate": 7e-05,
      "loss": 1.263,
      "step": 7
    },
    {
      "epoch": 0.01818181818181818,
      "grad_norm": 0.19222809374332428,
      "learning_rate": 8e-05,
      "loss": 1.0911,
      "step": 8
    },
    {
      "epoch": 0.020454545454545454,
      "grad_norm": 0.17531785368919373,
      "learning_rate": 9e-05,
      "loss": 1.1378,
      "step": 9
    },
    {
      "epoch": 0.022727272727272728,
      "grad_norm": 0.16878601908683777,
      "learning_rate": 0.0001,
      "loss": 1.0045,
      "step": 10
    },
    {
      "epoch": 0.025,
      "grad_norm": 0.1825711876153946,
      "learning_rate": 9.999316524962345e-05,
      "loss": 0.9699,
      "step": 11
    },
    {
      "epoch": 0.02727272727272727,
      "grad_norm": 0.1796250194311142,
      "learning_rate": 9.997266286704631e-05,
      "loss": 1.1535,
      "step": 12
    },
    {
      "epoch": 0.029545454545454545,
      "grad_norm": 0.22119615972042084,
      "learning_rate": 9.993849845741524e-05,
      "loss": 1.1981,
      "step": 13
    },
    {
      "epoch": 0.031818181818181815,
      "grad_norm": 0.19232602417469025,
      "learning_rate": 9.989068136093873e-05,
      "loss": 1.1612,
      "step": 14
    },
    {
      "epoch": 0.03409090909090909,
      "grad_norm": 0.2048940509557724,
      "learning_rate": 9.98292246503335e-05,
      "loss": 1.1687,
      "step": 15
    },
    {
      "epoch": 0.03636363636363636,
      "grad_norm": 0.19359134137630463,
      "learning_rate": 9.975414512725057e-05,
      "loss": 1.1564,
      "step": 16
    },
    {
      "epoch": 0.038636363636363635,
      "grad_norm": 0.21436509490013123,
      "learning_rate": 9.966546331768191e-05,
      "loss": 1.2182,
      "step": 17
    },
    {
      "epoch": 0.04090909090909091,
      "grad_norm": 0.20783087611198425,
      "learning_rate": 9.956320346634876e-05,
      "loss": 1.0506,
      "step": 18
    },
    {
      "epoch": 0.04318181818181818,
      "grad_norm": 0.20649276673793793,
      "learning_rate": 9.944739353007344e-05,
      "loss": 1.1196,
      "step": 19
    },
    {
      "epoch": 0.045454545454545456,
      "grad_norm": 0.18903961777687073,
      "learning_rate": 9.931806517013612e-05,
      "loss": 1.1296,
      "step": 20
    },
    {
      "epoch": 0.04772727272727273,
      "grad_norm": 0.19049355387687683,
      "learning_rate": 9.917525374361912e-05,
      "loss": 1.0333,
      "step": 21
    },
    {
      "epoch": 0.05,
      "grad_norm": 0.23408401012420654,
      "learning_rate": 9.901899829374047e-05,
      "loss": 1.092,
      "step": 22
    },
    {
      "epoch": 0.05227272727272727,
      "grad_norm": 0.23035134375095367,
      "learning_rate": 9.884934153917997e-05,
      "loss": 1.1661,
      "step": 23
    },
    {
      "epoch": 0.05454545454545454,
      "grad_norm": 0.24822844564914703,
      "learning_rate": 9.86663298624003e-05,
      "loss": 1.2073,
      "step": 24
    },
    {
      "epoch": 0.056818181818181816,
      "grad_norm": 0.22768764197826385,
      "learning_rate": 9.847001329696653e-05,
      "loss": 1.1851,
      "step": 25
    },
    {
      "epoch": 0.05909090909090909,
      "grad_norm": 0.2231784164905548,
      "learning_rate": 9.826044551386744e-05,
      "loss": 1.0968,
      "step": 26
    },
    {
      "epoch": 0.06136363636363636,
      "grad_norm": 0.2116321474313736,
      "learning_rate": 9.803768380684242e-05,
      "loss": 1.0946,
      "step": 27
    },
    {
      "epoch": 0.06363636363636363,
      "grad_norm": 0.2256927341222763,
      "learning_rate": 9.780178907671789e-05,
      "loss": 1.1604,
      "step": 28
    },
    {
      "epoch": 0.0659090909090909,
      "grad_norm": 0.213430717587471,
      "learning_rate": 9.755282581475769e-05,
      "loss": 1.191,
      "step": 29
    },
    {
      "epoch": 0.06818181818181818,
      "grad_norm": 0.26663199067115784,
      "learning_rate": 9.729086208503174e-05,
      "loss": 1.2157,
      "step": 30
    },
    {
      "epoch": 0.07045454545454545,
      "grad_norm": 0.24154269695281982,
      "learning_rate": 9.701596950580806e-05,
      "loss": 1.1043,
      "step": 31
    },
    {
      "epoch": 0.07272727272727272,
      "grad_norm": 0.267121821641922,
      "learning_rate": 9.672822322997305e-05,
      "loss": 1.1349,
      "step": 32
    },
    {
      "epoch": 0.075,
      "grad_norm": 0.2720530033111572,
      "learning_rate": 9.642770192448536e-05,
      "loss": 1.1907,
      "step": 33
    },
    {
      "epoch": 0.07727272727272727,
      "grad_norm": 0.2692214250564575,
      "learning_rate": 9.611448774886924e-05,
      "loss": 1.206,
      "step": 34
    },
    {
      "epoch": 0.07954545454545454,
      "grad_norm": 0.28792816400527954,
      "learning_rate": 9.578866633275288e-05,
      "loss": 1.2247,
      "step": 35
    },
    {
      "epoch": 0.08181818181818182,
      "grad_norm": 0.2922234535217285,
      "learning_rate": 9.545032675245813e-05,
      "loss": 1.1436,
      "step": 36
    },
    {
      "epoch": 0.08409090909090909,
      "grad_norm": 0.3062233030796051,
      "learning_rate": 9.509956150664796e-05,
      "loss": 1.1098,
      "step": 37
    },
    {
      "epoch": 0.08636363636363636,
      "grad_norm": 0.3466585874557495,
      "learning_rate": 9.473646649103818e-05,
      "loss": 1.191,
      "step": 38
    },
    {
      "epoch": 0.08863636363636364,
      "grad_norm": 0.3178981840610504,
      "learning_rate": 9.43611409721806e-05,
      "loss": 1.1869,
      "step": 39
    },
    {
      "epoch": 0.09090909090909091,
      "grad_norm": 0.3621369004249573,
      "learning_rate": 9.397368756032445e-05,
      "loss": 1.222,
      "step": 40
    },
    {
      "epoch": 0.09318181818181819,
      "grad_norm": 0.4619542062282562,
      "learning_rate": 9.357421218136386e-05,
      "loss": 1.1478,
      "step": 41
    },
    {
      "epoch": 0.09545454545454546,
      "grad_norm": 0.410416841506958,
      "learning_rate": 9.316282404787871e-05,
      "loss": 1.1577,
      "step": 42
    },
    {
      "epoch": 0.09772727272727273,
      "grad_norm": 0.49987027049064636,
      "learning_rate": 9.273963562927695e-05,
      "loss": 1.3343,
      "step": 43
    },
    {
      "epoch": 0.1,
      "grad_norm": 0.5508790016174316,
      "learning_rate": 9.230476262104677e-05,
      "loss": 1.1428,
      "step": 44
    },
    {
      "epoch": 0.10227272727272728,
      "grad_norm": 0.6187532544136047,
      "learning_rate": 9.185832391312644e-05,
      "loss": 1.263,
      "step": 45
    },
    {
      "epoch": 0.10454545454545454,
      "grad_norm": 0.6520056128501892,
      "learning_rate": 9.140044155740101e-05,
      "loss": 1.1509,
      "step": 46
    },
    {
      "epoch": 0.10681818181818181,
      "grad_norm": 0.6843658089637756,
      "learning_rate": 9.093124073433463e-05,
      "loss": 1.2692,
      "step": 47
    },
    {
      "epoch": 0.10909090909090909,
      "grad_norm": 1.0884649753570557,
      "learning_rate": 9.045084971874738e-05,
      "loss": 1.5549,
      "step": 48
    },
    {
      "epoch": 0.11136363636363636,
      "grad_norm": 1.0043234825134277,
      "learning_rate": 8.995939984474624e-05,
      "loss": 1.639,
      "step": 49
    },
    {
      "epoch": 0.11363636363636363,
      "grad_norm": 1.6276733875274658,
      "learning_rate": 8.945702546981969e-05,
      "loss": 1.9353,
      "step": 50
    },
    {
      "epoch": 0.11363636363636363,
      "eval_loss": 1.411944031715393,
      "eval_runtime": 24.9639,
      "eval_samples_per_second": 29.683,
      "eval_steps_per_second": 7.451,
      "step": 50
    },
    {
      "epoch": 0.1159090909090909,
      "grad_norm": 2.1535348892211914,
      "learning_rate": 8.894386393810563e-05,
      "loss": 1.1815,
      "step": 51
    },
    {
      "epoch": 0.11818181818181818,
      "grad_norm": 1.7080495357513428,
      "learning_rate": 8.842005554284296e-05,
      "loss": 1.1274,
      "step": 52
    },
    {
      "epoch": 0.12045454545454545,
      "grad_norm": 0.8043599128723145,
      "learning_rate": 8.788574348801675e-05,
      "loss": 1.0691,
      "step": 53
    },
    {
      "epoch": 0.12272727272727273,
      "grad_norm": 0.405164897441864,
      "learning_rate": 8.73410738492077e-05,
      "loss": 0.945,
      "step": 54
    },
    {
      "epoch": 0.125,
      "grad_norm": 0.3201294541358948,
      "learning_rate": 8.678619553365659e-05,
      "loss": 1.1127,
      "step": 55
    },
    {
      "epoch": 0.12727272727272726,
      "grad_norm": 0.27228617668151855,
      "learning_rate": 8.622126023955446e-05,
      "loss": 1.2467,
      "step": 56
    },
    {
      "epoch": 0.12954545454545455,
      "grad_norm": 0.21418097615242004,
      "learning_rate": 8.564642241456986e-05,
      "loss": 1.2055,
      "step": 57
    },
    {
      "epoch": 0.1318181818181818,
      "grad_norm": 0.205101877450943,
      "learning_rate": 8.506183921362443e-05,
      "loss": 1.064,
      "step": 58
    },
    {
      "epoch": 0.1340909090909091,
      "grad_norm": 0.1783040165901184,
      "learning_rate": 8.44676704559283e-05,
      "loss": 0.9673,
      "step": 59
    },
    {
      "epoch": 0.13636363636363635,
      "grad_norm": 0.2013094127178192,
      "learning_rate": 8.386407858128706e-05,
      "loss": 1.054,
      "step": 60
    },
    {
      "epoch": 0.13863636363636364,
      "grad_norm": 0.2072862833738327,
      "learning_rate": 8.32512286056924e-05,
      "loss": 1.0028,
      "step": 61
    },
    {
      "epoch": 0.1409090909090909,
      "grad_norm": 0.19704577326774597,
      "learning_rate": 8.262928807620843e-05,
      "loss": 1.0835,
      "step": 62
    },
    {
      "epoch": 0.1431818181818182,
      "grad_norm": 0.19232650101184845,
      "learning_rate": 8.199842702516583e-05,
      "loss": 1.1347,
      "step": 63
    },
    {
      "epoch": 0.14545454545454545,
      "grad_norm": 0.18673360347747803,
      "learning_rate": 8.135881792367686e-05,
      "loss": 1.0958,
      "step": 64
    },
    {
      "epoch": 0.14772727272727273,
      "grad_norm": 0.21381448209285736,
      "learning_rate": 8.07106356344834e-05,
      "loss": 0.9817,
      "step": 65
    },
    {
      "epoch": 0.15,
      "grad_norm": 0.20259332656860352,
      "learning_rate": 8.005405736415126e-05,
      "loss": 1.0237,
      "step": 66
    },
    {
      "epoch": 0.15227272727272728,
      "grad_norm": 0.18276585638523102,
      "learning_rate": 7.938926261462366e-05,
      "loss": 1.0984,
      "step": 67
    },
    {
      "epoch": 0.15454545454545454,
      "grad_norm": 0.19122764468193054,
      "learning_rate": 7.871643313414718e-05,
      "loss": 1.0585,
      "step": 68
    },
    {
      "epoch": 0.15681818181818183,
      "grad_norm": 0.1698465347290039,
      "learning_rate": 7.803575286758364e-05,
      "loss": 1.1868,
      "step": 69
    },
    {
      "epoch": 0.1590909090909091,
      "grad_norm": 0.18604332208633423,
      "learning_rate": 7.734740790612136e-05,
      "loss": 1.1172,
      "step": 70
    },
    {
      "epoch": 0.16136363636363638,
      "grad_norm": 0.19983096420764923,
      "learning_rate": 7.66515864363997e-05,
      "loss": 1.1629,
      "step": 71
    },
    {
      "epoch": 0.16363636363636364,
      "grad_norm": 0.1862115114927292,
      "learning_rate": 7.594847868906076e-05,
      "loss": 1.1873,
      "step": 72
    },
    {
      "epoch": 0.16590909090909092,
      "grad_norm": 0.18106940388679504,
      "learning_rate": 7.52382768867422e-05,
      "loss": 1.0378,
      "step": 73
    },
    {
      "epoch": 0.16818181818181818,
      "grad_norm": 0.19374078512191772,
      "learning_rate": 7.452117519152542e-05,
      "loss": 1.179,
      "step": 74
    },
    {
      "epoch": 0.17045454545454544,
      "grad_norm": 0.17689508199691772,
      "learning_rate": 7.379736965185368e-05,
      "loss": 1.2045,
      "step": 75
    },
    {
      "epoch": 0.17272727272727273,
      "grad_norm": 0.2028038203716278,
      "learning_rate": 7.30670581489344e-05,
      "loss": 1.1344,
      "step": 76
    },
    {
      "epoch": 0.175,
      "grad_norm": 0.2121182233095169,
      "learning_rate": 7.233044034264034e-05,
      "loss": 1.0461,
      "step": 77
    },
    {
      "epoch": 0.17727272727272728,
      "grad_norm": 0.18945012986660004,
      "learning_rate": 7.158771761692464e-05,
      "loss": 1.1269,
      "step": 78
    },
    {
      "epoch": 0.17954545454545454,
      "grad_norm": 0.21081632375717163,
      "learning_rate": 7.083909302476453e-05,
      "loss": 1.1308,
      "step": 79
    },
    {
      "epoch": 0.18181818181818182,
      "grad_norm": 0.20955480635166168,
      "learning_rate": 7.008477123264848e-05,
      "loss": 1.0296,
      "step": 80
    },
    {
      "epoch": 0.18409090909090908,
      "grad_norm": 0.21830624341964722,
      "learning_rate": 6.932495846462261e-05,
      "loss": 1.0248,
      "step": 81
    },
    {
      "epoch": 0.18636363636363637,
      "grad_norm": 0.24975615739822388,
      "learning_rate": 6.855986244591104e-05,
      "loss": 1.1637,
      "step": 82
    },
    {
      "epoch": 0.18863636363636363,
      "grad_norm": 0.23850086331367493,
      "learning_rate": 6.778969234612584e-05,
      "loss": 1.2706,
      "step": 83
    },
    {
      "epoch": 0.19090909090909092,
      "grad_norm": 0.22355328500270844,
      "learning_rate": 6.701465872208216e-05,
      "loss": 1.0584,
      "step": 84
    },
    {
      "epoch": 0.19318181818181818,
      "grad_norm": 0.26635459065437317,
      "learning_rate": 6.623497346023418e-05,
      "loss": 1.2007,
      "step": 85
    },
    {
      "epoch": 0.19545454545454546,
      "grad_norm": 0.25110507011413574,
      "learning_rate": 6.545084971874738e-05,
      "loss": 1.1436,
      "step": 86
    },
    {
      "epoch": 0.19772727272727272,
      "grad_norm": 0.27750837802886963,
      "learning_rate": 6.466250186922325e-05,
      "loss": 1.0665,
      "step": 87
    },
    {
      "epoch": 0.2,
      "grad_norm": 0.2995053231716156,
      "learning_rate": 6.387014543809223e-05,
      "loss": 1.2626,
      "step": 88
    },
    {
      "epoch": 0.20227272727272727,
      "grad_norm": 0.3170616030693054,
      "learning_rate": 6.307399704769099e-05,
      "loss": 1.1905,
      "step": 89
    },
    {
      "epoch": 0.20454545454545456,
      "grad_norm": 0.3603406548500061,
      "learning_rate": 6.227427435703997e-05,
      "loss": 1.3118,
      "step": 90
    },
    {
      "epoch": 0.20681818181818182,
      "grad_norm": 0.38694408535957336,
      "learning_rate": 6.147119600233758e-05,
      "loss": 1.1317,
      "step": 91
    },
    {
      "epoch": 0.20909090909090908,
      "grad_norm": 0.39918217062950134,
      "learning_rate": 6.066498153718735e-05,
      "loss": 1.1613,
      "step": 92
    },
    {
      "epoch": 0.21136363636363636,
      "grad_norm": 0.45765581727027893,
      "learning_rate": 5.985585137257401e-05,
      "loss": 1.2338,
      "step": 93
    },
    {
      "epoch": 0.21363636363636362,
      "grad_norm": 0.4584449231624603,
      "learning_rate": 5.90440267166055e-05,
      "loss": 1.2163,
      "step": 94
    },
    {
      "epoch": 0.2159090909090909,
      "grad_norm": 0.4652494788169861,
      "learning_rate": 5.8229729514036705e-05,
      "loss": 1.1751,
      "step": 95
    },
    {
      "epoch": 0.21818181818181817,
      "grad_norm": 0.5524594187736511,
      "learning_rate": 5.74131823855921e-05,
      "loss": 1.2927,
      "step": 96
    },
    {
      "epoch": 0.22045454545454546,
      "grad_norm": 0.5378203392028809,
      "learning_rate": 5.6594608567103456e-05,
      "loss": 1.2996,
      "step": 97
    },
    {
      "epoch": 0.22272727272727272,
      "grad_norm": 0.6692656874656677,
      "learning_rate": 5.577423184847932e-05,
      "loss": 1.4053,
      "step": 98
    },
    {
      "epoch": 0.225,
      "grad_norm": 0.8895469903945923,
      "learning_rate": 5.495227651252315e-05,
      "loss": 1.2667,
      "step": 99
    },
    {
      "epoch": 0.22727272727272727,
      "grad_norm": 1.7360968589782715,
      "learning_rate": 5.4128967273616625e-05,
      "loss": 1.9857,
      "step": 100
    },
    {
      "epoch": 0.22727272727272727,
      "eval_loss": 1.1818054914474487,
      "eval_runtime": 24.9737,
      "eval_samples_per_second": 29.671,
      "eval_steps_per_second": 7.448,
      "step": 100
    },
    {
      "epoch": 0.22954545454545455,
      "grad_norm": 0.21592825651168823,
      "learning_rate": 5.330452921628497e-05,
      "loss": 0.8215,
      "step": 101
    },
    {
      "epoch": 0.2318181818181818,
      "grad_norm": 0.2819373905658722,
      "learning_rate": 5.247918773366112e-05,
      "loss": 1.0145,
      "step": 102
    },
    {
      "epoch": 0.2340909090909091,
      "grad_norm": 0.3169407844543457,
      "learning_rate": 5.165316846586541e-05,
      "loss": 0.942,
      "step": 103
    },
    {
      "epoch": 0.23636363636363636,
      "grad_norm": 0.37479594349861145,
      "learning_rate": 5.0826697238317935e-05,
      "loss": 1.2772,
      "step": 104
    },
    {
      "epoch": 0.23863636363636365,
      "grad_norm": 0.3948274254798889,
      "learning_rate": 5e-05,
      "loss": 1.2353,
      "step": 105
    },
    {
      "epoch": 0.2409090909090909,
      "grad_norm": 0.4166310429573059,
      "learning_rate": 4.917330276168208e-05,
      "loss": 1.3214,
      "step": 106
    },
    {
      "epoch": 0.2431818181818182,
      "grad_norm": 0.37061458826065063,
      "learning_rate": 4.834683153413459e-05,
      "loss": 1.2892,
      "step": 107
    },
    {
      "epoch": 0.24545454545454545,
      "grad_norm": 0.2859272360801697,
      "learning_rate": 4.7520812266338885e-05,
      "loss": 1.0849,
      "step": 108
    },
    {
      "epoch": 0.24772727272727274,
      "grad_norm": 0.29247981309890747,
      "learning_rate": 4.669547078371504e-05,
      "loss": 1.0765,
      "step": 109
    },
    {
      "epoch": 0.25,
      "grad_norm": 0.25067824125289917,
      "learning_rate": 4.5871032726383386e-05,
      "loss": 1.0028,
      "step": 110
    },
    {
      "epoch": 0.25227272727272726,
      "grad_norm": 0.2163337767124176,
      "learning_rate": 4.504772348747687e-05,
      "loss": 0.9828,
      "step": 111
    },
    {
      "epoch": 0.2545454545454545,
      "grad_norm": 0.22771242260932922,
      "learning_rate": 4.4225768151520694e-05,
      "loss": 1.1033,
      "step": 112
    },
    {
      "epoch": 0.25681818181818183,
      "grad_norm": 0.20823155343532562,
      "learning_rate": 4.3405391432896555e-05,
      "loss": 0.9563,
      "step": 113
    },
    {
      "epoch": 0.2590909090909091,
      "grad_norm": 0.18508701026439667,
      "learning_rate": 4.2586817614407895e-05,
      "loss": 1.0218,
      "step": 114
    },
    {
      "epoch": 0.26136363636363635,
      "grad_norm": 0.19247791171073914,
      "learning_rate": 4.17702704859633e-05,
      "loss": 0.9894,
      "step": 115
    },
    {
      "epoch": 0.2636363636363636,
      "grad_norm": 0.17805472016334534,
      "learning_rate": 4.095597328339452e-05,
      "loss": 1.0711,
      "step": 116
    },
    {
      "epoch": 0.26590909090909093,
      "grad_norm": 0.19113686680793762,
      "learning_rate": 4.0144148627425993e-05,
      "loss": 1.0685,
      "step": 117
    },
    {
      "epoch": 0.2681818181818182,
      "grad_norm": 0.1743973344564438,
      "learning_rate": 3.933501846281267e-05,
      "loss": 1.0307,
      "step": 118
    },
    {
      "epoch": 0.27045454545454545,
      "grad_norm": 0.200986847281456,
      "learning_rate": 3.852880399766243e-05,
      "loss": 1.0836,
      "step": 119
    },
    {
      "epoch": 0.2727272727272727,
      "grad_norm": 0.18652981519699097,
      "learning_rate": 3.772572564296005e-05,
      "loss": 1.1088,
      "step": 120
    },
    {
      "epoch": 0.275,
      "grad_norm": 0.19419550895690918,
      "learning_rate": 3.6926002952309016e-05,
      "loss": 1.0424,
      "step": 121
    },
    {
      "epoch": 0.2772727272727273,
      "grad_norm": 0.20542936027050018,
      "learning_rate": 3.612985456190778e-05,
      "loss": 1.1133,
      "step": 122
    },
    {
      "epoch": 0.27954545454545454,
      "grad_norm": 0.20454029738903046,
      "learning_rate": 3.533749813077677e-05,
      "loss": 1.1232,
      "step": 123
    },
    {
      "epoch": 0.2818181818181818,
      "grad_norm": 0.20409062504768372,
      "learning_rate": 3.4549150281252636e-05,
      "loss": 1.1285,
      "step": 124
    },
    {
      "epoch": 0.2840909090909091,
      "grad_norm": 0.21091577410697937,
      "learning_rate": 3.3765026539765834e-05,
      "loss": 1.0257,
      "step": 125
    },
    {
      "epoch": 0.2863636363636364,
      "grad_norm": 0.2222558706998825,
      "learning_rate": 3.298534127791785e-05,
      "loss": 1.1046,
      "step": 126
    },
    {
      "epoch": 0.28863636363636364,
      "grad_norm": 0.22695103287696838,
      "learning_rate": 3.221030765387417e-05,
      "loss": 1.098,
      "step": 127
    },
    {
      "epoch": 0.2909090909090909,
      "grad_norm": 0.23505467176437378,
      "learning_rate": 3.144013755408895e-05,
      "loss": 1.0471,
      "step": 128
    },
    {
      "epoch": 0.29318181818181815,
      "grad_norm": 0.23115943372249603,
      "learning_rate": 3.0675041535377405e-05,
      "loss": 1.1686,
      "step": 129
    },
    {
      "epoch": 0.29545454545454547,
      "grad_norm": 0.2321702390909195,
      "learning_rate": 2.991522876735154e-05,
      "loss": 1.127,
      "step": 130
    },
    {
      "epoch": 0.29772727272727273,
      "grad_norm": 0.2716781198978424,
      "learning_rate": 2.916090697523549e-05,
      "loss": 1.0597,
      "step": 131
    },
    {
      "epoch": 0.3,
      "grad_norm": 0.253913551568985,
      "learning_rate": 2.8412282383075363e-05,
      "loss": 1.0815,
      "step": 132
    },
    {
      "epoch": 0.30227272727272725,
      "grad_norm": 0.2480076402425766,
      "learning_rate": 2.766955965735968e-05,
      "loss": 1.1935,
      "step": 133
    },
    {
      "epoch": 0.30454545454545456,
      "grad_norm": 0.2901071310043335,
      "learning_rate": 2.693294185106562e-05,
      "loss": 1.1719,
      "step": 134
    },
    {
      "epoch": 0.3068181818181818,
      "grad_norm": 0.30989769101142883,
      "learning_rate": 2.6202630348146324e-05,
      "loss": 1.2853,
      "step": 135
    },
    {
      "epoch": 0.3090909090909091,
      "grad_norm": 0.3367677927017212,
      "learning_rate": 2.547882480847461e-05,
      "loss": 1.0924,
      "step": 136
    },
    {
      "epoch": 0.31136363636363634,
      "grad_norm": 0.29563796520233154,
      "learning_rate": 2.476172311325783e-05,
      "loss": 1.1297,
      "step": 137
    },
    {
      "epoch": 0.31363636363636366,
      "grad_norm": 0.33408239483833313,
      "learning_rate": 2.405152131093926e-05,
      "loss": 1.3,
      "step": 138
    },
    {
      "epoch": 0.3159090909090909,
      "grad_norm": 0.33940908312797546,
      "learning_rate": 2.3348413563600325e-05,
      "loss": 1.2332,
      "step": 139
    },
    {
      "epoch": 0.3181818181818182,
      "grad_norm": 0.3681314289569855,
      "learning_rate": 2.2652592093878666e-05,
      "loss": 1.1938,
      "step": 140
    },
    {
      "epoch": 0.32045454545454544,
      "grad_norm": 0.38737952709198,
      "learning_rate": 2.196424713241637e-05,
      "loss": 1.1995,
      "step": 141
    },
    {
      "epoch": 0.32272727272727275,
      "grad_norm": 0.4649614989757538,
      "learning_rate": 2.128356686585282e-05,
      "loss": 1.2655,
      "step": 142
    },
    {
      "epoch": 0.325,
      "grad_norm": 0.484040230512619,
      "learning_rate": 2.061073738537635e-05,
      "loss": 1.2165,
      "step": 143
    },
    {
      "epoch": 0.32727272727272727,
      "grad_norm": 0.455758273601532,
      "learning_rate": 1.9945942635848748e-05,
      "loss": 0.9995,
      "step": 144
    },
    {
      "epoch": 0.32954545454545453,
      "grad_norm": 0.5230006575584412,
      "learning_rate": 1.928936436551661e-05,
      "loss": 1.1176,
      "step": 145
    },
    {
      "epoch": 0.33181818181818185,
      "grad_norm": 0.5094504952430725,
      "learning_rate": 1.8641182076323148e-05,
      "loss": 1.2364,
      "step": 146
    },
    {
      "epoch": 0.3340909090909091,
      "grad_norm": 0.5399109721183777,
      "learning_rate": 1.800157297483417e-05,
      "loss": 1.2752,
      "step": 147
    },
    {
      "epoch": 0.33636363636363636,
      "grad_norm": 0.6901865601539612,
      "learning_rate": 1.7370711923791567e-05,
      "loss": 1.3819,
      "step": 148
    },
    {
      "epoch": 0.3386363636363636,
      "grad_norm": 1.062111735343933,
      "learning_rate": 1.6748771394307585e-05,
      "loss": 1.6641,
      "step": 149
    },
    {
      "epoch": 0.3409090909090909,
      "grad_norm": 1.426699161529541,
      "learning_rate": 1.6135921418712956e-05,
      "loss": 1.7215,
      "step": 150
    },
    {
      "epoch": 0.3409090909090909,
      "eval_loss": 1.1302974224090576,
      "eval_runtime": 24.8824,
      "eval_samples_per_second": 29.78,
      "eval_steps_per_second": 7.475,
      "step": 150
    },
    {
      "epoch": 0.3431818181818182,
      "grad_norm": 0.08924370259046555,
      "learning_rate": 1.553232954407171e-05,
      "loss": 0.5672,
      "step": 151
    },
    {
      "epoch": 0.34545454545454546,
      "grad_norm": 0.12934063374996185,
      "learning_rate": 1.4938160786375572e-05,
      "loss": 0.8492,
      "step": 152
    },
    {
      "epoch": 0.3477272727272727,
      "grad_norm": 0.15847529470920563,
      "learning_rate": 1.435357758543015e-05,
      "loss": 0.8241,
      "step": 153
    },
    {
      "epoch": 0.35,
      "grad_norm": 0.20704495906829834,
      "learning_rate": 1.3778739760445552e-05,
      "loss": 0.9654,
      "step": 154
    },
    {
      "epoch": 0.3522727272727273,
      "grad_norm": 0.2169083207845688,
      "learning_rate": 1.3213804466343421e-05,
      "loss": 1.0545,
      "step": 155
    },
    {
      "epoch": 0.35454545454545455,
      "grad_norm": 0.14799341559410095,
      "learning_rate": 1.2658926150792322e-05,
      "loss": 1.0547,
      "step": 156
    },
    {
      "epoch": 0.3568181818181818,
      "grad_norm": 0.14607037603855133,
      "learning_rate": 1.2114256511983274e-05,
      "loss": 1.1522,
      "step": 157
    },
    {
      "epoch": 0.35909090909090907,
      "grad_norm": 0.16301359236240387,
      "learning_rate": 1.157994445715706e-05,
      "loss": 1.0422,
      "step": 158
    },
    {
      "epoch": 0.3613636363636364,
      "grad_norm": 0.17882244288921356,
      "learning_rate": 1.1056136061894384e-05,
      "loss": 0.9776,
      "step": 159
    },
    {
      "epoch": 0.36363636363636365,
      "grad_norm": 0.1662423312664032,
      "learning_rate": 1.0542974530180327e-05,
      "loss": 0.9514,
      "step": 160
    },
    {
      "epoch": 0.3659090909090909,
      "grad_norm": 0.16598089039325714,
      "learning_rate": 1.0040600155253765e-05,
      "loss": 0.9324,
      "step": 161
    },
    {
      "epoch": 0.36818181818181817,
      "grad_norm": 0.17198492586612701,
      "learning_rate": 9.549150281252633e-06,
      "loss": 1.006,
      "step": 162
    },
    {
      "epoch": 0.3704545454545455,
      "grad_norm": 0.17896981537342072,
      "learning_rate": 9.068759265665384e-06,
      "loss": 1.1174,
      "step": 163
    },
    {
      "epoch": 0.37272727272727274,
      "grad_norm": 0.18816745281219482,
      "learning_rate": 8.599558442598998e-06,
      "loss": 0.9771,
      "step": 164
    },
    {
      "epoch": 0.375,
      "grad_norm": 0.20828911662101746,
      "learning_rate": 8.141676086873572e-06,
      "loss": 1.0129,
      "step": 165
    },
    {
      "epoch": 0.37727272727272726,
      "grad_norm": 0.21062462031841278,
      "learning_rate": 7.695237378953223e-06,
      "loss": 1.0948,
      "step": 166
    },
    {
      "epoch": 0.3795454545454545,
      "grad_norm": 0.20821909606456757,
      "learning_rate": 7.260364370723044e-06,
      "loss": 1.1989,
      "step": 167
    },
    {
      "epoch": 0.38181818181818183,
      "grad_norm": 0.18839111924171448,
      "learning_rate": 6.837175952121306e-06,
      "loss": 0.978,
      "step": 168
    },
    {
      "epoch": 0.3840909090909091,
      "grad_norm": 0.1895921379327774,
      "learning_rate": 6.425787818636131e-06,
      "loss": 1.0873,
      "step": 169
    },
    {
      "epoch": 0.38636363636363635,
      "grad_norm": 0.20680470764636993,
      "learning_rate": 6.026312439675552e-06,
      "loss": 1.0964,
      "step": 170
    },
    {
      "epoch": 0.3886363636363636,
      "grad_norm": 0.19969810545444489,
      "learning_rate": 5.6388590278194096e-06,
      "loss": 1.1957,
      "step": 171
    },
    {
      "epoch": 0.39090909090909093,
      "grad_norm": 0.200290709733963,
      "learning_rate": 5.263533508961827e-06,
      "loss": 0.9491,
      "step": 172
    },
    {
      "epoch": 0.3931818181818182,
      "grad_norm": 0.22019080817699432,
      "learning_rate": 4.900438493352055e-06,
      "loss": 1.1749,
      "step": 173
    },
    {
      "epoch": 0.39545454545454545,
      "grad_norm": 0.2039121836423874,
      "learning_rate": 4.549673247541875e-06,
      "loss": 1.1317,
      "step": 174
    },
    {
      "epoch": 0.3977272727272727,
      "grad_norm": 0.2096068263053894,
      "learning_rate": 4.2113336672471245e-06,
      "loss": 1.0686,
      "step": 175
    },
    {
      "epoch": 0.4,
      "grad_norm": 0.24238021671772003,
      "learning_rate": 3.885512251130763e-06,
      "loss": 1.101,
      "step": 176
    },
    {
      "epoch": 0.4022727272727273,
      "grad_norm": 0.22032850980758667,
      "learning_rate": 3.5722980755146517e-06,
      "loss": 1.0394,
      "step": 177
    },
    {
      "epoch": 0.40454545454545454,
      "grad_norm": 0.23046588897705078,
      "learning_rate": 3.271776770026963e-06,
      "loss": 1.0868,
      "step": 178
    },
    {
      "epoch": 0.4068181818181818,
      "grad_norm": 0.24861113727092743,
      "learning_rate": 2.9840304941919415e-06,
      "loss": 0.9723,
      "step": 179
    },
    {
      "epoch": 0.4090909090909091,
      "grad_norm": 0.2443162500858307,
      "learning_rate": 2.7091379149682685e-06,
      "loss": 1.1113,
      "step": 180
    },
    {
      "epoch": 0.4113636363636364,
      "grad_norm": 0.2506013810634613,
      "learning_rate": 2.4471741852423237e-06,
      "loss": 1.042,
      "step": 181
    },
    {
      "epoch": 0.41363636363636364,
      "grad_norm": 0.25118905305862427,
      "learning_rate": 2.1982109232821178e-06,
      "loss": 1.1599,
      "step": 182
    },
    {
      "epoch": 0.4159090909090909,
      "grad_norm": 0.2597385048866272,
      "learning_rate": 1.962316193157593e-06,
      "loss": 1.1815,
      "step": 183
    },
    {
      "epoch": 0.41818181818181815,
      "grad_norm": 0.2688179016113281,
      "learning_rate": 1.7395544861325718e-06,
      "loss": 1.0924,
      "step": 184
    },
    {
      "epoch": 0.42045454545454547,
      "grad_norm": 0.30122846364974976,
      "learning_rate": 1.5299867030334814e-06,
      "loss": 1.0809,
      "step": 185
    },
    {
      "epoch": 0.42272727272727273,
      "grad_norm": 0.2834639847278595,
      "learning_rate": 1.333670137599713e-06,
      "loss": 1.0707,
      "step": 186
    },
    {
      "epoch": 0.425,
      "grad_norm": 0.31759223341941833,
      "learning_rate": 1.1506584608200367e-06,
      "loss": 1.179,
      "step": 187
    },
    {
      "epoch": 0.42727272727272725,
      "grad_norm": 0.3102632761001587,
      "learning_rate": 9.810017062595322e-07,
      "loss": 1.2155,
      "step": 188
    },
    {
      "epoch": 0.42954545454545456,
      "grad_norm": 0.3525193929672241,
      "learning_rate": 8.247462563808817e-07,
      "loss": 1.2165,
      "step": 189
    },
    {
      "epoch": 0.4318181818181818,
      "grad_norm": 0.3488246500492096,
      "learning_rate": 6.819348298638839e-07,
      "loss": 1.2216,
      "step": 190
    },
    {
      "epoch": 0.4340909090909091,
      "grad_norm": 0.39676520228385925,
      "learning_rate": 5.526064699265753e-07,
      "loss": 1.23,
      "step": 191
    },
    {
      "epoch": 0.43636363636363634,
      "grad_norm": 0.40854334831237793,
      "learning_rate": 4.367965336512403e-07,
      "loss": 1.0743,
      "step": 192
    },
    {
      "epoch": 0.43863636363636366,
      "grad_norm": 0.5004187822341919,
      "learning_rate": 3.3453668231809286e-07,
      "loss": 1.0437,
      "step": 193
    },
    {
      "epoch": 0.4409090909090909,
      "grad_norm": 0.47272375226020813,
      "learning_rate": 2.458548727494292e-07,
      "loss": 1.097,
      "step": 194
    },
    {
      "epoch": 0.4431818181818182,
      "grad_norm": 0.5150394439697266,
      "learning_rate": 1.7077534966650766e-07,
      "loss": 1.223,
      "step": 195
    },
    {
      "epoch": 0.44545454545454544,
      "grad_norm": 0.5412110686302185,
      "learning_rate": 1.0931863906127327e-07,
      "loss": 1.2319,
      "step": 196
    },
    {
      "epoch": 0.44772727272727275,
      "grad_norm": 0.6978278160095215,
      "learning_rate": 6.150154258476315e-08,
      "loss": 1.361,
      "step": 197
    },
    {
      "epoch": 0.45,
      "grad_norm": 0.9302064776420593,
      "learning_rate": 2.7337132953697554e-08,
      "loss": 1.6652,
      "step": 198
    },
    {
      "epoch": 0.45227272727272727,
      "grad_norm": 1.0024001598358154,
      "learning_rate": 6.834750376549792e-09,
      "loss": 1.4581,
      "step": 199
    },
    {
      "epoch": 0.45454545454545453,
      "grad_norm": 1.4170377254486084,
      "learning_rate": 0.0,
      "loss": 1.7837,
      "step": 200
    },
    {
      "epoch": 0.45454545454545453,
      "eval_loss": 1.1267578601837158,
      "eval_runtime": 25.0742,
      "eval_samples_per_second": 29.552,
      "eval_steps_per_second": 7.418,
      "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": 7.602519641004442e+16,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}