{
  "best_metric": 0.8192576766014099,
  "best_model_checkpoint": "miner_id_24/checkpoint-200",
  "epoch": 0.3401360544217687,
  "eval_steps": 50,
  "global_step": 200,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0017006802721088435,
      "grad_norm": 0.5291147232055664,
      "learning_rate": 1e-05,
      "loss": 1.1941,
      "step": 1
    },
    {
      "epoch": 0.0017006802721088435,
      "eval_loss": 1.5710939168930054,
      "eval_runtime": 29.1209,
      "eval_samples_per_second": 33.996,
      "eval_steps_per_second": 8.516,
      "step": 1
    },
    {
      "epoch": 0.003401360544217687,
      "grad_norm": 0.653645932674408,
      "learning_rate": 2e-05,
      "loss": 1.3253,
      "step": 2
    },
    {
      "epoch": 0.00510204081632653,
      "grad_norm": 0.6522074341773987,
      "learning_rate": 3e-05,
      "loss": 1.4131,
      "step": 3
    },
    {
      "epoch": 0.006802721088435374,
      "grad_norm": 0.765129029750824,
      "learning_rate": 4e-05,
      "loss": 1.391,
      "step": 4
    },
    {
      "epoch": 0.008503401360544218,
      "grad_norm": 0.6822937726974487,
      "learning_rate": 5e-05,
      "loss": 1.4074,
      "step": 5
    },
    {
      "epoch": 0.01020408163265306,
      "grad_norm": 0.7309608459472656,
      "learning_rate": 6e-05,
      "loss": 1.3569,
      "step": 6
    },
    {
      "epoch": 0.011904761904761904,
      "grad_norm": 0.6975144743919373,
      "learning_rate": 7e-05,
      "loss": 1.3406,
      "step": 7
    },
    {
      "epoch": 0.013605442176870748,
      "grad_norm": 0.7133910059928894,
      "learning_rate": 8e-05,
      "loss": 1.3282,
      "step": 8
    },
    {
      "epoch": 0.015306122448979591,
      "grad_norm": 0.7860673666000366,
      "learning_rate": 9e-05,
      "loss": 1.2513,
      "step": 9
    },
    {
      "epoch": 0.017006802721088437,
      "grad_norm": 0.9281991720199585,
      "learning_rate": 0.0001,
      "loss": 1.3623,
      "step": 10
    },
    {
      "epoch": 0.01870748299319728,
      "grad_norm": 0.8078566193580627,
      "learning_rate": 9.999316524962345e-05,
      "loss": 1.3182,
      "step": 11
    },
    {
      "epoch": 0.02040816326530612,
      "grad_norm": 0.8770384788513184,
      "learning_rate": 9.997266286704631e-05,
      "loss": 1.2238,
      "step": 12
    },
    {
      "epoch": 0.022108843537414966,
      "grad_norm": 0.8294715881347656,
      "learning_rate": 9.993849845741524e-05,
      "loss": 1.2238,
      "step": 13
    },
    {
      "epoch": 0.023809523809523808,
      "grad_norm": 0.7330012321472168,
      "learning_rate": 9.989068136093873e-05,
      "loss": 1.1727,
      "step": 14
    },
    {
      "epoch": 0.025510204081632654,
      "grad_norm": 0.5644362568855286,
      "learning_rate": 9.98292246503335e-05,
      "loss": 0.9886,
      "step": 15
    },
    {
      "epoch": 0.027210884353741496,
      "grad_norm": 0.5972509980201721,
      "learning_rate": 9.975414512725057e-05,
      "loss": 1.065,
      "step": 16
    },
    {
      "epoch": 0.02891156462585034,
      "grad_norm": 0.6530568599700928,
      "learning_rate": 9.966546331768191e-05,
      "loss": 0.9915,
      "step": 17
    },
    {
      "epoch": 0.030612244897959183,
      "grad_norm": 0.6822307109832764,
      "learning_rate": 9.956320346634876e-05,
      "loss": 1.0735,
      "step": 18
    },
    {
      "epoch": 0.03231292517006803,
      "grad_norm": 0.556408703327179,
      "learning_rate": 9.944739353007344e-05,
      "loss": 1.0382,
      "step": 19
    },
    {
      "epoch": 0.034013605442176874,
      "grad_norm": 0.6571498513221741,
      "learning_rate": 9.931806517013612e-05,
      "loss": 1.1065,
      "step": 20
    },
    {
      "epoch": 0.03571428571428571,
      "grad_norm": 0.6030095815658569,
      "learning_rate": 9.917525374361912e-05,
      "loss": 1.0698,
      "step": 21
    },
    {
      "epoch": 0.03741496598639456,
      "grad_norm": 0.5490834712982178,
      "learning_rate": 9.901899829374047e-05,
      "loss": 0.9609,
      "step": 22
    },
    {
      "epoch": 0.0391156462585034,
      "grad_norm": 0.5671564936637878,
      "learning_rate": 9.884934153917997e-05,
      "loss": 0.9988,
      "step": 23
    },
    {
      "epoch": 0.04081632653061224,
      "grad_norm": 0.5630932450294495,
      "learning_rate": 9.86663298624003e-05,
      "loss": 0.8703,
      "step": 24
    },
    {
      "epoch": 0.04251700680272109,
      "grad_norm": 0.7171502709388733,
      "learning_rate": 9.847001329696653e-05,
      "loss": 0.8919,
      "step": 25
    },
    {
      "epoch": 0.04421768707482993,
      "grad_norm": 0.6116781830787659,
      "learning_rate": 9.826044551386744e-05,
      "loss": 0.8305,
      "step": 26
    },
    {
      "epoch": 0.04591836734693878,
      "grad_norm": 0.6103072166442871,
      "learning_rate": 9.803768380684242e-05,
      "loss": 0.9635,
      "step": 27
    },
    {
      "epoch": 0.047619047619047616,
      "grad_norm": 0.6139481663703918,
      "learning_rate": 9.780178907671789e-05,
      "loss": 0.8943,
      "step": 28
    },
    {
      "epoch": 0.04931972789115646,
      "grad_norm": 0.8213135004043579,
      "learning_rate": 9.755282581475769e-05,
      "loss": 1.0012,
      "step": 29
    },
    {
      "epoch": 0.05102040816326531,
      "grad_norm": 0.6028281450271606,
      "learning_rate": 9.729086208503174e-05,
      "loss": 0.9224,
      "step": 30
    },
    {
      "epoch": 0.05272108843537415,
      "grad_norm": 0.663382887840271,
      "learning_rate": 9.701596950580806e-05,
      "loss": 0.8873,
      "step": 31
    },
    {
      "epoch": 0.05442176870748299,
      "grad_norm": 0.5516164898872375,
      "learning_rate": 9.672822322997305e-05,
      "loss": 0.8317,
      "step": 32
    },
    {
      "epoch": 0.05612244897959184,
      "grad_norm": 0.6466988921165466,
      "learning_rate": 9.642770192448536e-05,
      "loss": 0.9492,
      "step": 33
    },
    {
      "epoch": 0.05782312925170068,
      "grad_norm": 0.596361517906189,
      "learning_rate": 9.611448774886924e-05,
      "loss": 0.802,
      "step": 34
    },
    {
      "epoch": 0.05952380952380952,
      "grad_norm": 0.6077542901039124,
      "learning_rate": 9.578866633275288e-05,
      "loss": 0.8223,
      "step": 35
    },
    {
      "epoch": 0.061224489795918366,
      "grad_norm": 0.7078118324279785,
      "learning_rate": 9.545032675245813e-05,
      "loss": 0.9258,
      "step": 36
    },
    {
      "epoch": 0.06292517006802721,
      "grad_norm": 0.6588369607925415,
      "learning_rate": 9.509956150664796e-05,
      "loss": 0.8658,
      "step": 37
    },
    {
      "epoch": 0.06462585034013606,
      "grad_norm": 0.6245062351226807,
      "learning_rate": 9.473646649103818e-05,
      "loss": 0.8549,
      "step": 38
    },
    {
      "epoch": 0.0663265306122449,
      "grad_norm": 0.6501139402389526,
      "learning_rate": 9.43611409721806e-05,
      "loss": 0.7985,
      "step": 39
    },
    {
      "epoch": 0.06802721088435375,
      "grad_norm": 0.7001845240592957,
      "learning_rate": 9.397368756032445e-05,
      "loss": 0.7897,
      "step": 40
    },
    {
      "epoch": 0.06972789115646258,
      "grad_norm": 0.7008475065231323,
      "learning_rate": 9.357421218136386e-05,
      "loss": 0.8317,
      "step": 41
    },
    {
      "epoch": 0.07142857142857142,
      "grad_norm": 0.6650017499923706,
      "learning_rate": 9.316282404787871e-05,
      "loss": 0.7758,
      "step": 42
    },
    {
      "epoch": 0.07312925170068027,
      "grad_norm": 0.6724229454994202,
      "learning_rate": 9.273963562927695e-05,
      "loss": 0.8147,
      "step": 43
    },
    {
      "epoch": 0.07482993197278912,
      "grad_norm": 0.762274980545044,
      "learning_rate": 9.230476262104677e-05,
      "loss": 0.7012,
      "step": 44
    },
    {
      "epoch": 0.07653061224489796,
      "grad_norm": 0.8012467622756958,
      "learning_rate": 9.185832391312644e-05,
      "loss": 0.7336,
      "step": 45
    },
    {
      "epoch": 0.0782312925170068,
      "grad_norm": 0.729831874370575,
      "learning_rate": 9.140044155740101e-05,
      "loss": 0.697,
      "step": 46
    },
    {
      "epoch": 0.07993197278911565,
      "grad_norm": 0.7739328742027283,
      "learning_rate": 9.093124073433463e-05,
      "loss": 0.7703,
      "step": 47
    },
    {
      "epoch": 0.08163265306122448,
      "grad_norm": 0.8301722407341003,
      "learning_rate": 9.045084971874738e-05,
      "loss": 0.6442,
      "step": 48
    },
    {
      "epoch": 0.08333333333333333,
      "grad_norm": 0.8829469084739685,
      "learning_rate": 8.995939984474624e-05,
      "loss": 0.8276,
      "step": 49
    },
    {
      "epoch": 0.08503401360544217,
      "grad_norm": 1.0848655700683594,
      "learning_rate": 8.945702546981969e-05,
      "loss": 0.8231,
      "step": 50
    },
    {
      "epoch": 0.08503401360544217,
      "eval_loss": 0.9598169326782227,
      "eval_runtime": 29.1874,
      "eval_samples_per_second": 33.919,
      "eval_steps_per_second": 8.497,
      "step": 50
    },
    {
      "epoch": 0.08673469387755102,
      "grad_norm": 0.7079697847366333,
      "learning_rate": 8.894386393810563e-05,
      "loss": 1.183,
      "step": 51
    },
    {
      "epoch": 0.08843537414965986,
      "grad_norm": 0.6948996186256409,
      "learning_rate": 8.842005554284296e-05,
      "loss": 1.1268,
      "step": 52
    },
    {
      "epoch": 0.09013605442176871,
      "grad_norm": 0.6077824831008911,
      "learning_rate": 8.788574348801675e-05,
      "loss": 1.1653,
      "step": 53
    },
    {
      "epoch": 0.09183673469387756,
      "grad_norm": 0.5523154735565186,
      "learning_rate": 8.73410738492077e-05,
      "loss": 1.1668,
      "step": 54
    },
    {
      "epoch": 0.0935374149659864,
      "grad_norm": 0.4991576075553894,
      "learning_rate": 8.678619553365659e-05,
      "loss": 1.1974,
      "step": 55
    },
    {
      "epoch": 0.09523809523809523,
      "grad_norm": 0.44966161251068115,
      "learning_rate": 8.622126023955446e-05,
      "loss": 0.9894,
      "step": 56
    },
    {
      "epoch": 0.09693877551020408,
      "grad_norm": 0.47389182448387146,
      "learning_rate": 8.564642241456986e-05,
      "loss": 1.0054,
      "step": 57
    },
    {
      "epoch": 0.09863945578231292,
      "grad_norm": 0.4813501834869385,
      "learning_rate": 8.506183921362443e-05,
      "loss": 1.0563,
      "step": 58
    },
    {
      "epoch": 0.10034013605442177,
      "grad_norm": 0.5305858850479126,
      "learning_rate": 8.44676704559283e-05,
      "loss": 1.1464,
      "step": 59
    },
    {
      "epoch": 0.10204081632653061,
      "grad_norm": 0.4995189905166626,
      "learning_rate": 8.386407858128706e-05,
      "loss": 0.9936,
      "step": 60
    },
    {
      "epoch": 0.10374149659863946,
      "grad_norm": 0.46828389167785645,
      "learning_rate": 8.32512286056924e-05,
      "loss": 1.0325,
      "step": 61
    },
    {
      "epoch": 0.1054421768707483,
      "grad_norm": 0.47875574231147766,
      "learning_rate": 8.262928807620843e-05,
      "loss": 1.0233,
      "step": 62
    },
    {
      "epoch": 0.10714285714285714,
      "grad_norm": 0.46664929389953613,
      "learning_rate": 8.199842702516583e-05,
      "loss": 1.0364,
      "step": 63
    },
    {
      "epoch": 0.10884353741496598,
      "grad_norm": 0.44881466031074524,
      "learning_rate": 8.135881792367686e-05,
      "loss": 0.9223,
      "step": 64
    },
    {
      "epoch": 0.11054421768707483,
      "grad_norm": 0.4559362828731537,
      "learning_rate": 8.07106356344834e-05,
      "loss": 0.9263,
      "step": 65
    },
    {
      "epoch": 0.11224489795918367,
      "grad_norm": 0.4596306383609772,
      "learning_rate": 8.005405736415126e-05,
      "loss": 1.0011,
      "step": 66
    },
    {
      "epoch": 0.11394557823129252,
      "grad_norm": 0.5003011226654053,
      "learning_rate": 7.938926261462366e-05,
      "loss": 1.0206,
      "step": 67
    },
    {
      "epoch": 0.11564625850340136,
      "grad_norm": 0.4770001173019409,
      "learning_rate": 7.871643313414718e-05,
      "loss": 0.9273,
      "step": 68
    },
    {
      "epoch": 0.11734693877551021,
      "grad_norm": 0.4754573404788971,
      "learning_rate": 7.803575286758364e-05,
      "loss": 0.8598,
      "step": 69
    },
    {
      "epoch": 0.11904761904761904,
      "grad_norm": 0.5027380585670471,
      "learning_rate": 7.734740790612136e-05,
      "loss": 0.8833,
      "step": 70
    },
    {
      "epoch": 0.12074829931972789,
      "grad_norm": 0.47251009941101074,
      "learning_rate": 7.66515864363997e-05,
      "loss": 0.8968,
      "step": 71
    },
    {
      "epoch": 0.12244897959183673,
      "grad_norm": 0.4740285873413086,
      "learning_rate": 7.594847868906076e-05,
      "loss": 0.8051,
      "step": 72
    },
    {
      "epoch": 0.12414965986394558,
      "grad_norm": 0.48850923776626587,
      "learning_rate": 7.52382768867422e-05,
      "loss": 0.8339,
      "step": 73
    },
    {
      "epoch": 0.12585034013605442,
      "grad_norm": 0.6182630062103271,
      "learning_rate": 7.452117519152542e-05,
      "loss": 0.9706,
      "step": 74
    },
    {
      "epoch": 0.12755102040816327,
      "grad_norm": 0.495595246553421,
      "learning_rate": 7.379736965185368e-05,
      "loss": 0.7567,
      "step": 75
    },
    {
      "epoch": 0.1292517006802721,
      "grad_norm": 0.5259597897529602,
      "learning_rate": 7.30670581489344e-05,
      "loss": 0.884,
      "step": 76
    },
    {
      "epoch": 0.13095238095238096,
      "grad_norm": 0.5288789868354797,
      "learning_rate": 7.233044034264034e-05,
      "loss": 0.7959,
      "step": 77
    },
    {
      "epoch": 0.1326530612244898,
      "grad_norm": 0.5319419503211975,
      "learning_rate": 7.158771761692464e-05,
      "loss": 0.866,
      "step": 78
    },
    {
      "epoch": 0.13435374149659865,
      "grad_norm": 0.5481342077255249,
      "learning_rate": 7.083909302476453e-05,
      "loss": 0.8444,
      "step": 79
    },
    {
      "epoch": 0.1360544217687075,
      "grad_norm": 0.5261763334274292,
      "learning_rate": 7.008477123264848e-05,
      "loss": 0.8278,
      "step": 80
    },
    {
      "epoch": 0.1377551020408163,
      "grad_norm": 0.5110121369361877,
      "learning_rate": 6.932495846462261e-05,
      "loss": 0.7718,
      "step": 81
    },
    {
      "epoch": 0.13945578231292516,
      "grad_norm": 0.5594261288642883,
      "learning_rate": 6.855986244591104e-05,
      "loss": 0.8174,
      "step": 82
    },
    {
      "epoch": 0.141156462585034,
      "grad_norm": 0.5700205564498901,
      "learning_rate": 6.778969234612584e-05,
      "loss": 0.8557,
      "step": 83
    },
    {
      "epoch": 0.14285714285714285,
      "grad_norm": 0.5226923227310181,
      "learning_rate": 6.701465872208216e-05,
      "loss": 0.7317,
      "step": 84
    },
    {
      "epoch": 0.1445578231292517,
      "grad_norm": 0.6211686134338379,
      "learning_rate": 6.623497346023418e-05,
      "loss": 0.7936,
      "step": 85
    },
    {
      "epoch": 0.14625850340136054,
      "grad_norm": 0.624346911907196,
      "learning_rate": 6.545084971874738e-05,
      "loss": 0.8725,
      "step": 86
    },
    {
      "epoch": 0.14795918367346939,
      "grad_norm": 0.5725211501121521,
      "learning_rate": 6.466250186922325e-05,
      "loss": 0.7662,
      "step": 87
    },
    {
      "epoch": 0.14965986394557823,
      "grad_norm": 0.5687521696090698,
      "learning_rate": 6.387014543809223e-05,
      "loss": 0.6982,
      "step": 88
    },
    {
      "epoch": 0.15136054421768708,
      "grad_norm": 0.5981340408325195,
      "learning_rate": 6.307399704769099e-05,
      "loss": 0.7483,
      "step": 89
    },
    {
      "epoch": 0.15306122448979592,
      "grad_norm": 0.6248530149459839,
      "learning_rate": 6.227427435703997e-05,
      "loss": 0.7649,
      "step": 90
    },
    {
      "epoch": 0.15476190476190477,
      "grad_norm": 0.6169067621231079,
      "learning_rate": 6.147119600233758e-05,
      "loss": 0.7878,
      "step": 91
    },
    {
      "epoch": 0.1564625850340136,
      "grad_norm": 0.6496368050575256,
      "learning_rate": 6.066498153718735e-05,
      "loss": 0.7488,
      "step": 92
    },
    {
      "epoch": 0.15816326530612246,
      "grad_norm": 0.6536640524864197,
      "learning_rate": 5.985585137257401e-05,
      "loss": 0.797,
      "step": 93
    },
    {
      "epoch": 0.1598639455782313,
      "grad_norm": 0.6514473557472229,
      "learning_rate": 5.90440267166055e-05,
      "loss": 0.7316,
      "step": 94
    },
    {
      "epoch": 0.16156462585034015,
      "grad_norm": 0.7200974822044373,
      "learning_rate": 5.8229729514036705e-05,
      "loss": 0.8242,
      "step": 95
    },
    {
      "epoch": 0.16326530612244897,
      "grad_norm": 0.6845313310623169,
      "learning_rate": 5.74131823855921e-05,
      "loss": 0.7905,
      "step": 96
    },
    {
      "epoch": 0.1649659863945578,
      "grad_norm": 0.6382232308387756,
      "learning_rate": 5.6594608567103456e-05,
      "loss": 0.6432,
      "step": 97
    },
    {
      "epoch": 0.16666666666666666,
      "grad_norm": 0.7161521911621094,
      "learning_rate": 5.577423184847932e-05,
      "loss": 0.7149,
      "step": 98
    },
    {
      "epoch": 0.1683673469387755,
      "grad_norm": 0.733022153377533,
      "learning_rate": 5.495227651252315e-05,
      "loss": 0.6413,
      "step": 99
    },
    {
      "epoch": 0.17006802721088435,
      "grad_norm": 0.9442101120948792,
      "learning_rate": 5.4128967273616625e-05,
      "loss": 0.758,
      "step": 100
    },
    {
      "epoch": 0.17006802721088435,
      "eval_loss": 0.8659837245941162,
      "eval_runtime": 29.1994,
      "eval_samples_per_second": 33.905,
      "eval_steps_per_second": 8.493,
      "step": 100
    },
    {
      "epoch": 0.1717687074829932,
      "grad_norm": 0.4905572533607483,
      "learning_rate": 5.330452921628497e-05,
      "loss": 1.0918,
      "step": 101
    },
    {
      "epoch": 0.17346938775510204,
      "grad_norm": 0.5327093005180359,
      "learning_rate": 5.247918773366112e-05,
      "loss": 1.099,
      "step": 102
    },
    {
      "epoch": 0.17517006802721088,
      "grad_norm": 0.5068239569664001,
      "learning_rate": 5.165316846586541e-05,
      "loss": 1.1438,
      "step": 103
    },
    {
      "epoch": 0.17687074829931973,
      "grad_norm": 0.5240384936332703,
      "learning_rate": 5.0826697238317935e-05,
      "loss": 1.0846,
      "step": 104
    },
    {
      "epoch": 0.17857142857142858,
      "grad_norm": 0.48864665627479553,
      "learning_rate": 5e-05,
      "loss": 1.1271,
      "step": 105
    },
    {
      "epoch": 0.18027210884353742,
      "grad_norm": 0.4766891598701477,
      "learning_rate": 4.917330276168208e-05,
      "loss": 1.1538,
      "step": 106
    },
    {
      "epoch": 0.18197278911564627,
      "grad_norm": 0.45236217975616455,
      "learning_rate": 4.834683153413459e-05,
      "loss": 1.015,
      "step": 107
    },
    {
      "epoch": 0.1836734693877551,
      "grad_norm": 0.43944251537323,
      "learning_rate": 4.7520812266338885e-05,
      "loss": 1.048,
      "step": 108
    },
    {
      "epoch": 0.18537414965986396,
      "grad_norm": 0.42950132489204407,
      "learning_rate": 4.669547078371504e-05,
      "loss": 0.9266,
      "step": 109
    },
    {
      "epoch": 0.1870748299319728,
      "grad_norm": 0.432943195104599,
      "learning_rate": 4.5871032726383386e-05,
      "loss": 0.9401,
      "step": 110
    },
    {
      "epoch": 0.18877551020408162,
      "grad_norm": 0.4478369355201721,
      "learning_rate": 4.504772348747687e-05,
      "loss": 0.9723,
      "step": 111
    },
    {
      "epoch": 0.19047619047619047,
      "grad_norm": 0.4469376802444458,
      "learning_rate": 4.4225768151520694e-05,
      "loss": 0.9838,
      "step": 112
    },
    {
      "epoch": 0.1921768707482993,
      "grad_norm": 0.47492969036102295,
      "learning_rate": 4.3405391432896555e-05,
      "loss": 1.0937,
      "step": 113
    },
    {
      "epoch": 0.19387755102040816,
      "grad_norm": 0.4947476089000702,
      "learning_rate": 4.2586817614407895e-05,
      "loss": 0.9338,
      "step": 114
    },
    {
      "epoch": 0.195578231292517,
      "grad_norm": 0.46984225511550903,
      "learning_rate": 4.17702704859633e-05,
      "loss": 0.9928,
      "step": 115
    },
    {
      "epoch": 0.19727891156462585,
      "grad_norm": 0.47430679202079773,
      "learning_rate": 4.095597328339452e-05,
      "loss": 0.9644,
      "step": 116
    },
    {
      "epoch": 0.1989795918367347,
      "grad_norm": 0.5142965316772461,
      "learning_rate": 4.0144148627425993e-05,
      "loss": 0.9438,
      "step": 117
    },
    {
      "epoch": 0.20068027210884354,
      "grad_norm": 0.46151089668273926,
      "learning_rate": 3.933501846281267e-05,
      "loss": 0.8537,
      "step": 118
    },
    {
      "epoch": 0.20238095238095238,
      "grad_norm": 0.4819258153438568,
      "learning_rate": 3.852880399766243e-05,
      "loss": 0.8695,
      "step": 119
    },
    {
      "epoch": 0.20408163265306123,
      "grad_norm": 0.5007303953170776,
      "learning_rate": 3.772572564296005e-05,
      "loss": 0.8373,
      "step": 120
    },
    {
      "epoch": 0.20578231292517007,
      "grad_norm": 0.48250338435173035,
      "learning_rate": 3.6926002952309016e-05,
      "loss": 0.8311,
      "step": 121
    },
    {
      "epoch": 0.20748299319727892,
      "grad_norm": 0.47793594002723694,
      "learning_rate": 3.612985456190778e-05,
      "loss": 0.8137,
      "step": 122
    },
    {
      "epoch": 0.20918367346938777,
      "grad_norm": 0.5131264925003052,
      "learning_rate": 3.533749813077677e-05,
      "loss": 0.8007,
      "step": 123
    },
    {
      "epoch": 0.2108843537414966,
      "grad_norm": 0.5198999047279358,
      "learning_rate": 3.4549150281252636e-05,
      "loss": 0.8515,
      "step": 124
    },
    {
      "epoch": 0.21258503401360543,
      "grad_norm": 0.4772438704967499,
      "learning_rate": 3.3765026539765834e-05,
      "loss": 0.7876,
      "step": 125
    },
    {
      "epoch": 0.21428571428571427,
      "grad_norm": 0.4969208538532257,
      "learning_rate": 3.298534127791785e-05,
      "loss": 0.8344,
      "step": 126
    },
    {
      "epoch": 0.21598639455782312,
      "grad_norm": 0.5793007612228394,
      "learning_rate": 3.221030765387417e-05,
      "loss": 0.9339,
      "step": 127
    },
    {
      "epoch": 0.21768707482993196,
      "grad_norm": 0.52213454246521,
      "learning_rate": 3.144013755408895e-05,
      "loss": 0.8138,
      "step": 128
    },
    {
      "epoch": 0.2193877551020408,
      "grad_norm": 0.5598412156105042,
      "learning_rate": 3.0675041535377405e-05,
      "loss": 0.864,
      "step": 129
    },
    {
      "epoch": 0.22108843537414966,
      "grad_norm": 0.5693469643592834,
      "learning_rate": 2.991522876735154e-05,
      "loss": 0.8186,
      "step": 130
    },
    {
      "epoch": 0.2227891156462585,
      "grad_norm": 0.583474338054657,
      "learning_rate": 2.916090697523549e-05,
      "loss": 0.8351,
      "step": 131
    },
    {
      "epoch": 0.22448979591836735,
      "grad_norm": 0.5242882370948792,
      "learning_rate": 2.8412282383075363e-05,
      "loss": 0.7212,
      "step": 132
    },
    {
      "epoch": 0.2261904761904762,
      "grad_norm": 0.6902099251747131,
      "learning_rate": 2.766955965735968e-05,
      "loss": 0.7975,
      "step": 133
    },
    {
      "epoch": 0.22789115646258504,
      "grad_norm": 0.5555305480957031,
      "learning_rate": 2.693294185106562e-05,
      "loss": 0.6611,
      "step": 134
    },
    {
      "epoch": 0.22959183673469388,
      "grad_norm": 0.561631441116333,
      "learning_rate": 2.6202630348146324e-05,
      "loss": 0.6696,
      "step": 135
    },
    {
      "epoch": 0.23129251700680273,
      "grad_norm": 0.5515864491462708,
      "learning_rate": 2.547882480847461e-05,
      "loss": 0.7148,
      "step": 136
    },
    {
      "epoch": 0.23299319727891157,
      "grad_norm": 0.5593742728233337,
      "learning_rate": 2.476172311325783e-05,
      "loss": 0.7317,
      "step": 137
    },
    {
      "epoch": 0.23469387755102042,
      "grad_norm": 0.589776873588562,
      "learning_rate": 2.405152131093926e-05,
      "loss": 0.7546,
      "step": 138
    },
    {
      "epoch": 0.23639455782312926,
      "grad_norm": 0.6155847311019897,
      "learning_rate": 2.3348413563600325e-05,
      "loss": 0.8132,
      "step": 139
    },
    {
      "epoch": 0.23809523809523808,
      "grad_norm": 0.6564325094223022,
      "learning_rate": 2.2652592093878666e-05,
      "loss": 0.7514,
      "step": 140
    },
    {
      "epoch": 0.23979591836734693,
      "grad_norm": 0.6407092213630676,
      "learning_rate": 2.196424713241637e-05,
      "loss": 0.7719,
      "step": 141
    },
    {
      "epoch": 0.24149659863945577,
      "grad_norm": 0.6713026762008667,
      "learning_rate": 2.128356686585282e-05,
      "loss": 0.7897,
      "step": 142
    },
    {
      "epoch": 0.24319727891156462,
      "grad_norm": 0.6115599870681763,
      "learning_rate": 2.061073738537635e-05,
      "loss": 0.7203,
      "step": 143
    },
    {
      "epoch": 0.24489795918367346,
      "grad_norm": 0.633370578289032,
      "learning_rate": 1.9945942635848748e-05,
      "loss": 0.6879,
      "step": 144
    },
    {
      "epoch": 0.2465986394557823,
      "grad_norm": 0.6437938809394836,
      "learning_rate": 1.928936436551661e-05,
      "loss": 0.7379,
      "step": 145
    },
    {
      "epoch": 0.24829931972789115,
      "grad_norm": 0.6858341693878174,
      "learning_rate": 1.8641182076323148e-05,
      "loss": 0.7448,
      "step": 146
    },
    {
      "epoch": 0.25,
      "grad_norm": 0.690157949924469,
      "learning_rate": 1.800157297483417e-05,
      "loss": 0.65,
      "step": 147
    },
    {
      "epoch": 0.25170068027210885,
      "grad_norm": 0.7275189161300659,
      "learning_rate": 1.7370711923791567e-05,
      "loss": 0.6745,
      "step": 148
    },
    {
      "epoch": 0.2534013605442177,
      "grad_norm": 0.747280478477478,
      "learning_rate": 1.6748771394307585e-05,
      "loss": 0.5559,
      "step": 149
    },
    {
      "epoch": 0.25510204081632654,
      "grad_norm": 1.0135223865509033,
      "learning_rate": 1.6135921418712956e-05,
      "loss": 0.6745,
      "step": 150
    },
    {
      "epoch": 0.25510204081632654,
      "eval_loss": 0.8297300338745117,
      "eval_runtime": 29.2131,
      "eval_samples_per_second": 33.889,
      "eval_steps_per_second": 8.489,
      "step": 150
    },
    {
      "epoch": 0.2568027210884354,
      "grad_norm": 0.37666839361190796,
      "learning_rate": 1.553232954407171e-05,
      "loss": 1.0637,
      "step": 151
    },
    {
      "epoch": 0.2585034013605442,
      "grad_norm": 0.4312518239021301,
      "learning_rate": 1.4938160786375572e-05,
      "loss": 1.0121,
      "step": 152
    },
    {
      "epoch": 0.2602040816326531,
      "grad_norm": 0.44942957162857056,
      "learning_rate": 1.435357758543015e-05,
      "loss": 1.0312,
      "step": 153
    },
    {
      "epoch": 0.2619047619047619,
      "grad_norm": 0.47704681754112244,
      "learning_rate": 1.3778739760445552e-05,
      "loss": 1.0223,
      "step": 154
    },
    {
      "epoch": 0.26360544217687076,
      "grad_norm": 0.48123621940612793,
      "learning_rate": 1.3213804466343421e-05,
      "loss": 1.0426,
      "step": 155
    },
    {
      "epoch": 0.2653061224489796,
      "grad_norm": 0.45062899589538574,
      "learning_rate": 1.2658926150792322e-05,
      "loss": 0.9471,
      "step": 156
    },
    {
      "epoch": 0.26700680272108845,
      "grad_norm": 0.46919381618499756,
      "learning_rate": 1.2114256511983274e-05,
      "loss": 0.9731,
      "step": 157
    },
    {
      "epoch": 0.2687074829931973,
      "grad_norm": 0.5117149949073792,
      "learning_rate": 1.157994445715706e-05,
      "loss": 1.0246,
      "step": 158
    },
    {
      "epoch": 0.27040816326530615,
      "grad_norm": 0.5050652027130127,
      "learning_rate": 1.1056136061894384e-05,
      "loss": 0.9546,
      "step": 159
    },
    {
      "epoch": 0.272108843537415,
      "grad_norm": 0.48009440302848816,
      "learning_rate": 1.0542974530180327e-05,
      "loss": 1.0148,
      "step": 160
    },
    {
      "epoch": 0.27380952380952384,
      "grad_norm": 0.4431731104850769,
      "learning_rate": 1.0040600155253765e-05,
      "loss": 0.8774,
      "step": 161
    },
    {
      "epoch": 0.2755102040816326,
      "grad_norm": 0.47435876727104187,
      "learning_rate": 9.549150281252633e-06,
      "loss": 0.9697,
      "step": 162
    },
    {
      "epoch": 0.27721088435374147,
      "grad_norm": 0.4978986084461212,
      "learning_rate": 9.068759265665384e-06,
      "loss": 0.9006,
      "step": 163
    },
    {
      "epoch": 0.2789115646258503,
      "grad_norm": 0.4990803301334381,
      "learning_rate": 8.599558442598998e-06,
      "loss": 0.9083,
      "step": 164
    },
    {
      "epoch": 0.28061224489795916,
      "grad_norm": 0.5072059631347656,
      "learning_rate": 8.141676086873572e-06,
      "loss": 0.894,
      "step": 165
    },
    {
      "epoch": 0.282312925170068,
      "grad_norm": 0.5156143307685852,
      "learning_rate": 7.695237378953223e-06,
      "loss": 0.8496,
      "step": 166
    },
    {
      "epoch": 0.28401360544217685,
      "grad_norm": 0.5260395407676697,
      "learning_rate": 7.260364370723044e-06,
      "loss": 0.9324,
      "step": 167
    },
    {
      "epoch": 0.2857142857142857,
      "grad_norm": 0.48563873767852783,
      "learning_rate": 6.837175952121306e-06,
      "loss": 0.8058,
      "step": 168
    },
    {
      "epoch": 0.28741496598639454,
      "grad_norm": 0.48891767859458923,
      "learning_rate": 6.425787818636131e-06,
      "loss": 0.8138,
      "step": 169
    },
    {
      "epoch": 0.2891156462585034,
      "grad_norm": 0.5247836112976074,
      "learning_rate": 6.026312439675552e-06,
      "loss": 0.9142,
      "step": 170
    },
    {
      "epoch": 0.29081632653061223,
      "grad_norm": 0.5213582515716553,
      "learning_rate": 5.6388590278194096e-06,
      "loss": 0.8352,
      "step": 171
    },
    {
      "epoch": 0.2925170068027211,
      "grad_norm": 0.5046089291572571,
      "learning_rate": 5.263533508961827e-06,
      "loss": 0.8214,
      "step": 172
    },
    {
      "epoch": 0.2942176870748299,
      "grad_norm": 0.5109598636627197,
      "learning_rate": 4.900438493352055e-06,
      "loss": 0.8454,
      "step": 173
    },
    {
      "epoch": 0.29591836734693877,
      "grad_norm": 0.5033755898475647,
      "learning_rate": 4.549673247541875e-06,
      "loss": 0.8359,
      "step": 174
    },
    {
      "epoch": 0.2976190476190476,
      "grad_norm": 0.5352942943572998,
      "learning_rate": 4.2113336672471245e-06,
      "loss": 0.8371,
      "step": 175
    },
    {
      "epoch": 0.29931972789115646,
      "grad_norm": 0.5231302976608276,
      "learning_rate": 3.885512251130763e-06,
      "loss": 0.7816,
      "step": 176
    },
    {
      "epoch": 0.3010204081632653,
      "grad_norm": 0.5124854445457458,
      "learning_rate": 3.5722980755146517e-06,
      "loss": 0.7893,
      "step": 177
    },
    {
      "epoch": 0.30272108843537415,
      "grad_norm": 0.5308873653411865,
      "learning_rate": 3.271776770026963e-06,
      "loss": 0.7597,
      "step": 178
    },
    {
      "epoch": 0.304421768707483,
      "grad_norm": 0.5928246974945068,
      "learning_rate": 2.9840304941919415e-06,
      "loss": 0.7582,
      "step": 179
    },
    {
      "epoch": 0.30612244897959184,
      "grad_norm": 0.5781289339065552,
      "learning_rate": 2.7091379149682685e-06,
      "loss": 0.8302,
      "step": 180
    },
    {
      "epoch": 0.3078231292517007,
      "grad_norm": 0.5236110091209412,
      "learning_rate": 2.4471741852423237e-06,
      "loss": 0.6843,
      "step": 181
    },
    {
      "epoch": 0.30952380952380953,
      "grad_norm": 0.573664128780365,
      "learning_rate": 2.1982109232821178e-06,
      "loss": 0.8224,
      "step": 182
    },
    {
      "epoch": 0.3112244897959184,
      "grad_norm": 0.5441963076591492,
      "learning_rate": 1.962316193157593e-06,
      "loss": 0.7148,
      "step": 183
    },
    {
      "epoch": 0.3129251700680272,
      "grad_norm": 0.5903492569923401,
      "learning_rate": 1.7395544861325718e-06,
      "loss": 0.7618,
      "step": 184
    },
    {
      "epoch": 0.31462585034013607,
      "grad_norm": 0.6290004253387451,
      "learning_rate": 1.5299867030334814e-06,
      "loss": 0.8693,
      "step": 185
    },
    {
      "epoch": 0.3163265306122449,
      "grad_norm": 0.5676831603050232,
      "learning_rate": 1.333670137599713e-06,
      "loss": 0.7774,
      "step": 186
    },
    {
      "epoch": 0.31802721088435376,
      "grad_norm": 0.5969007611274719,
      "learning_rate": 1.1506584608200367e-06,
      "loss": 0.7097,
      "step": 187
    },
    {
      "epoch": 0.3197278911564626,
      "grad_norm": 0.5773136019706726,
      "learning_rate": 9.810017062595322e-07,
      "loss": 0.7334,
      "step": 188
    },
    {
      "epoch": 0.32142857142857145,
      "grad_norm": 0.6240454912185669,
      "learning_rate": 8.247462563808817e-07,
      "loss": 0.7677,
      "step": 189
    },
    {
      "epoch": 0.3231292517006803,
      "grad_norm": 0.6159172654151917,
      "learning_rate": 6.819348298638839e-07,
      "loss": 0.6858,
      "step": 190
    },
    {
      "epoch": 0.32482993197278914,
      "grad_norm": 0.6205342411994934,
      "learning_rate": 5.526064699265753e-07,
      "loss": 0.6712,
      "step": 191
    },
    {
      "epoch": 0.32653061224489793,
      "grad_norm": 0.6334042549133301,
      "learning_rate": 4.367965336512403e-07,
      "loss": 0.7802,
      "step": 192
    },
    {
      "epoch": 0.3282312925170068,
      "grad_norm": 0.7085323333740234,
      "learning_rate": 3.3453668231809286e-07,
      "loss": 0.7871,
      "step": 193
    },
    {
      "epoch": 0.3299319727891156,
      "grad_norm": 0.5930947065353394,
      "learning_rate": 2.458548727494292e-07,
      "loss": 0.6609,
      "step": 194
    },
    {
      "epoch": 0.33163265306122447,
      "grad_norm": 0.6920778751373291,
      "learning_rate": 1.7077534966650766e-07,
      "loss": 0.7223,
      "step": 195
    },
    {
      "epoch": 0.3333333333333333,
      "grad_norm": 0.7101148366928101,
      "learning_rate": 1.0931863906127327e-07,
      "loss": 0.6343,
      "step": 196
    },
    {
      "epoch": 0.33503401360544216,
      "grad_norm": 0.6832766532897949,
      "learning_rate": 6.150154258476315e-08,
      "loss": 0.6356,
      "step": 197
    },
    {
      "epoch": 0.336734693877551,
      "grad_norm": 0.8196882009506226,
      "learning_rate": 2.7337132953697554e-08,
      "loss": 0.7428,
      "step": 198
    },
    {
      "epoch": 0.33843537414965985,
      "grad_norm": 0.8325486183166504,
      "learning_rate": 6.834750376549792e-09,
      "loss": 0.7237,
      "step": 199
    },
    {
      "epoch": 0.3401360544217687,
      "grad_norm": 0.9107606410980225,
      "learning_rate": 0.0,
      "loss": 0.7105,
      "step": 200
    },
    {
      "epoch": 0.3401360544217687,
      "eval_loss": 0.8192576766014099,
      "eval_runtime": 29.224,
      "eval_samples_per_second": 33.876,
      "eval_steps_per_second": 8.486,
      "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": 5.456501850243072e+16,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}