{
  "best_metric": 0.6727603077888489,
  "best_model_checkpoint": "miner_id_24/checkpoint-150",
  "epoch": 0.007652280379553107,
  "eval_steps": 50,
  "global_step": 150,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 5.1015202530354045e-05,
      "grad_norm": 3.800206422805786,
      "learning_rate": 1e-05,
      "loss": 2.7129,
      "step": 1
    },
    {
      "epoch": 5.1015202530354045e-05,
      "eval_loss": 2.350785493850708,
      "eval_runtime": 1424.8744,
      "eval_samples_per_second": 23.17,
      "eval_steps_per_second": 5.793,
      "step": 1
    },
    {
      "epoch": 0.00010203040506070809,
      "grad_norm": 3.281677722930908,
      "learning_rate": 2e-05,
      "loss": 2.4538,
      "step": 2
    },
    {
      "epoch": 0.00015304560759106213,
      "grad_norm": 3.6411774158477783,
      "learning_rate": 3e-05,
      "loss": 2.4151,
      "step": 3
    },
    {
      "epoch": 0.00020406081012141618,
      "grad_norm": 3.5843217372894287,
      "learning_rate": 4e-05,
      "loss": 2.252,
      "step": 4
    },
    {
      "epoch": 0.0002550760126517702,
      "grad_norm": 3.169598340988159,
      "learning_rate": 5e-05,
      "loss": 1.9558,
      "step": 5
    },
    {
      "epoch": 0.00030609121518212427,
      "grad_norm": 3.250075101852417,
      "learning_rate": 6e-05,
      "loss": 1.8867,
      "step": 6
    },
    {
      "epoch": 0.0003571064177124783,
      "grad_norm": 3.237321376800537,
      "learning_rate": 7e-05,
      "loss": 1.8729,
      "step": 7
    },
    {
      "epoch": 0.00040812162024283236,
      "grad_norm": 2.891801595687866,
      "learning_rate": 8e-05,
      "loss": 1.5532,
      "step": 8
    },
    {
      "epoch": 0.0004591368227731864,
      "grad_norm": 2.5424184799194336,
      "learning_rate": 9e-05,
      "loss": 1.3424,
      "step": 9
    },
    {
      "epoch": 0.0005101520253035404,
      "grad_norm": 2.7391488552093506,
      "learning_rate": 0.0001,
      "loss": 1.1392,
      "step": 10
    },
    {
      "epoch": 0.0005611672278338945,
      "grad_norm": 3.11933970451355,
      "learning_rate": 9.999316524962345e-05,
      "loss": 1.097,
      "step": 11
    },
    {
      "epoch": 0.0006121824303642485,
      "grad_norm": 2.733593225479126,
      "learning_rate": 9.997266286704631e-05,
      "loss": 1.179,
      "step": 12
    },
    {
      "epoch": 0.0006631976328946026,
      "grad_norm": 2.412281036376953,
      "learning_rate": 9.993849845741524e-05,
      "loss": 0.9229,
      "step": 13
    },
    {
      "epoch": 0.0007142128354249566,
      "grad_norm": 2.164652109146118,
      "learning_rate": 9.989068136093873e-05,
      "loss": 0.8309,
      "step": 14
    },
    {
      "epoch": 0.0007652280379553107,
      "grad_norm": 1.5523101091384888,
      "learning_rate": 9.98292246503335e-05,
      "loss": 0.8383,
      "step": 15
    },
    {
      "epoch": 0.0008162432404856647,
      "grad_norm": 1.7428220510482788,
      "learning_rate": 9.975414512725057e-05,
      "loss": 0.9078,
      "step": 16
    },
    {
      "epoch": 0.0008672584430160188,
      "grad_norm": 1.519983172416687,
      "learning_rate": 9.966546331768191e-05,
      "loss": 0.79,
      "step": 17
    },
    {
      "epoch": 0.0009182736455463728,
      "grad_norm": 1.3394166231155396,
      "learning_rate": 9.956320346634876e-05,
      "loss": 0.8219,
      "step": 18
    },
    {
      "epoch": 0.0009692888480767269,
      "grad_norm": 1.2191200256347656,
      "learning_rate": 9.944739353007344e-05,
      "loss": 0.7611,
      "step": 19
    },
    {
      "epoch": 0.001020304050607081,
      "grad_norm": 1.1729331016540527,
      "learning_rate": 9.931806517013612e-05,
      "loss": 0.6446,
      "step": 20
    },
    {
      "epoch": 0.0010713192531374349,
      "grad_norm": 1.1357612609863281,
      "learning_rate": 9.917525374361912e-05,
      "loss": 0.6577,
      "step": 21
    },
    {
      "epoch": 0.001122334455667789,
      "grad_norm": 1.401937484741211,
      "learning_rate": 9.901899829374047e-05,
      "loss": 0.6925,
      "step": 22
    },
    {
      "epoch": 0.001173349658198143,
      "grad_norm": 1.1007620096206665,
      "learning_rate": 9.884934153917997e-05,
      "loss": 0.6172,
      "step": 23
    },
    {
      "epoch": 0.001224364860728497,
      "grad_norm": 1.1781193017959595,
      "learning_rate": 9.86663298624003e-05,
      "loss": 0.5771,
      "step": 24
    },
    {
      "epoch": 0.001275380063258851,
      "grad_norm": 1.3466699123382568,
      "learning_rate": 9.847001329696653e-05,
      "loss": 0.6716,
      "step": 25
    },
    {
      "epoch": 0.0013263952657892053,
      "grad_norm": 1.357923984527588,
      "learning_rate": 9.826044551386744e-05,
      "loss": 0.7701,
      "step": 26
    },
    {
      "epoch": 0.0013774104683195593,
      "grad_norm": 1.2542227506637573,
      "learning_rate": 9.803768380684242e-05,
      "loss": 0.6805,
      "step": 27
    },
    {
      "epoch": 0.0014284256708499133,
      "grad_norm": 1.3870052099227905,
      "learning_rate": 9.780178907671789e-05,
      "loss": 0.698,
      "step": 28
    },
    {
      "epoch": 0.0014794408733802672,
      "grad_norm": 1.4804044961929321,
      "learning_rate": 9.755282581475769e-05,
      "loss": 0.7735,
      "step": 29
    },
    {
      "epoch": 0.0015304560759106215,
      "grad_norm": 1.1976419687271118,
      "learning_rate": 9.729086208503174e-05,
      "loss": 0.6421,
      "step": 30
    },
    {
      "epoch": 0.0015814712784409754,
      "grad_norm": 1.2338988780975342,
      "learning_rate": 9.701596950580806e-05,
      "loss": 0.6437,
      "step": 31
    },
    {
      "epoch": 0.0016324864809713294,
      "grad_norm": 1.2348625659942627,
      "learning_rate": 9.672822322997305e-05,
      "loss": 0.624,
      "step": 32
    },
    {
      "epoch": 0.0016835016835016834,
      "grad_norm": 1.2287312746047974,
      "learning_rate": 9.642770192448536e-05,
      "loss": 0.637,
      "step": 33
    },
    {
      "epoch": 0.0017345168860320376,
      "grad_norm": 1.1607104539871216,
      "learning_rate": 9.611448774886924e-05,
      "loss": 0.6903,
      "step": 34
    },
    {
      "epoch": 0.0017855320885623916,
      "grad_norm": 1.2106231451034546,
      "learning_rate": 9.578866633275288e-05,
      "loss": 0.6011,
      "step": 35
    },
    {
      "epoch": 0.0018365472910927456,
      "grad_norm": 1.1197235584259033,
      "learning_rate": 9.545032675245813e-05,
      "loss": 0.6303,
      "step": 36
    },
    {
      "epoch": 0.0018875624936230996,
      "grad_norm": 1.070656180381775,
      "learning_rate": 9.509956150664796e-05,
      "loss": 0.6045,
      "step": 37
    },
    {
      "epoch": 0.0019385776961534538,
      "grad_norm": 1.0808786153793335,
      "learning_rate": 9.473646649103818e-05,
      "loss": 0.6459,
      "step": 38
    },
    {
      "epoch": 0.0019895928986838076,
      "grad_norm": 1.2845101356506348,
      "learning_rate": 9.43611409721806e-05,
      "loss": 0.6695,
      "step": 39
    },
    {
      "epoch": 0.002040608101214162,
      "grad_norm": 1.2291234731674194,
      "learning_rate": 9.397368756032445e-05,
      "loss": 0.6527,
      "step": 40
    },
    {
      "epoch": 0.002091623303744516,
      "grad_norm": 1.2499144077301025,
      "learning_rate": 9.357421218136386e-05,
      "loss": 0.6887,
      "step": 41
    },
    {
      "epoch": 0.0021426385062748698,
      "grad_norm": 1.2308804988861084,
      "learning_rate": 9.316282404787871e-05,
      "loss": 0.6048,
      "step": 42
    },
    {
      "epoch": 0.002193653708805224,
      "grad_norm": 1.240252137184143,
      "learning_rate": 9.273963562927695e-05,
      "loss": 0.6776,
      "step": 43
    },
    {
      "epoch": 0.002244668911335578,
      "grad_norm": 1.2400046586990356,
      "learning_rate": 9.230476262104677e-05,
      "loss": 0.6426,
      "step": 44
    },
    {
      "epoch": 0.002295684113865932,
      "grad_norm": 1.1629558801651,
      "learning_rate": 9.185832391312644e-05,
      "loss": 0.6444,
      "step": 45
    },
    {
      "epoch": 0.002346699316396286,
      "grad_norm": 1.1924700736999512,
      "learning_rate": 9.140044155740101e-05,
      "loss": 0.6443,
      "step": 46
    },
    {
      "epoch": 0.00239771451892664,
      "grad_norm": 1.4758155345916748,
      "learning_rate": 9.093124073433463e-05,
      "loss": 0.7347,
      "step": 47
    },
    {
      "epoch": 0.002448729721456994,
      "grad_norm": 1.3901947736740112,
      "learning_rate": 9.045084971874738e-05,
      "loss": 0.7117,
      "step": 48
    },
    {
      "epoch": 0.0024997449239873484,
      "grad_norm": 1.4077956676483154,
      "learning_rate": 8.995939984474624e-05,
      "loss": 0.7526,
      "step": 49
    },
    {
      "epoch": 0.002550760126517702,
      "grad_norm": 1.6829890012741089,
      "learning_rate": 8.945702546981969e-05,
      "loss": 0.7598,
      "step": 50
    },
    {
      "epoch": 0.002550760126517702,
      "eval_loss": 0.7583083510398865,
      "eval_runtime": 1433.6555,
      "eval_samples_per_second": 23.028,
      "eval_steps_per_second": 5.757,
      "step": 50
    },
    {
      "epoch": 0.0026017753290480563,
      "grad_norm": 2.367197275161743,
      "learning_rate": 8.894386393810563e-05,
      "loss": 1.5955,
      "step": 51
    },
    {
      "epoch": 0.0026527905315784106,
      "grad_norm": 1.655700922012329,
      "learning_rate": 8.842005554284296e-05,
      "loss": 1.1209,
      "step": 52
    },
    {
      "epoch": 0.0027038057341087643,
      "grad_norm": 1.7417899370193481,
      "learning_rate": 8.788574348801675e-05,
      "loss": 0.9548,
      "step": 53
    },
    {
      "epoch": 0.0027548209366391185,
      "grad_norm": 1.4532091617584229,
      "learning_rate": 8.73410738492077e-05,
      "loss": 0.8967,
      "step": 54
    },
    {
      "epoch": 0.0028058361391694723,
      "grad_norm": 1.184683918952942,
      "learning_rate": 8.678619553365659e-05,
      "loss": 0.8828,
      "step": 55
    },
    {
      "epoch": 0.0028568513416998265,
      "grad_norm": 1.2943260669708252,
      "learning_rate": 8.622126023955446e-05,
      "loss": 0.7884,
      "step": 56
    },
    {
      "epoch": 0.0029078665442301807,
      "grad_norm": 1.4289363622665405,
      "learning_rate": 8.564642241456986e-05,
      "loss": 0.964,
      "step": 57
    },
    {
      "epoch": 0.0029588817467605345,
      "grad_norm": 1.3355457782745361,
      "learning_rate": 8.506183921362443e-05,
      "loss": 0.9107,
      "step": 58
    },
    {
      "epoch": 0.0030098969492908887,
      "grad_norm": 1.2480206489562988,
      "learning_rate": 8.44676704559283e-05,
      "loss": 0.99,
      "step": 59
    },
    {
      "epoch": 0.003060912151821243,
      "grad_norm": 1.253343105316162,
      "learning_rate": 8.386407858128706e-05,
      "loss": 0.8802,
      "step": 60
    },
    {
      "epoch": 0.0031119273543515967,
      "grad_norm": 1.1792048215866089,
      "learning_rate": 8.32512286056924e-05,
      "loss": 0.8684,
      "step": 61
    },
    {
      "epoch": 0.003162942556881951,
      "grad_norm": 1.4219132661819458,
      "learning_rate": 8.262928807620843e-05,
      "loss": 0.8953,
      "step": 62
    },
    {
      "epoch": 0.0032139577594123047,
      "grad_norm": 1.0520647764205933,
      "learning_rate": 8.199842702516583e-05,
      "loss": 0.7349,
      "step": 63
    },
    {
      "epoch": 0.003264972961942659,
      "grad_norm": 1.0161808729171753,
      "learning_rate": 8.135881792367686e-05,
      "loss": 0.7194,
      "step": 64
    },
    {
      "epoch": 0.003315988164473013,
      "grad_norm": 1.1097899675369263,
      "learning_rate": 8.07106356344834e-05,
      "loss": 0.8444,
      "step": 65
    },
    {
      "epoch": 0.003367003367003367,
      "grad_norm": 0.9742171764373779,
      "learning_rate": 8.005405736415126e-05,
      "loss": 0.6395,
      "step": 66
    },
    {
      "epoch": 0.003418018569533721,
      "grad_norm": 1.095369577407837,
      "learning_rate": 7.938926261462366e-05,
      "loss": 0.79,
      "step": 67
    },
    {
      "epoch": 0.0034690337720640753,
      "grad_norm": 1.0745102167129517,
      "learning_rate": 7.871643313414718e-05,
      "loss": 0.6555,
      "step": 68
    },
    {
      "epoch": 0.003520048974594429,
      "grad_norm": 1.1682138442993164,
      "learning_rate": 7.803575286758364e-05,
      "loss": 0.7564,
      "step": 69
    },
    {
      "epoch": 0.0035710641771247833,
      "grad_norm": 0.9457067251205444,
      "learning_rate": 7.734740790612136e-05,
      "loss": 0.5688,
      "step": 70
    },
    {
      "epoch": 0.003622079379655137,
      "grad_norm": 1.058748483657837,
      "learning_rate": 7.66515864363997e-05,
      "loss": 0.7264,
      "step": 71
    },
    {
      "epoch": 0.0036730945821854912,
      "grad_norm": 1.111148476600647,
      "learning_rate": 7.594847868906076e-05,
      "loss": 0.7099,
      "step": 72
    },
    {
      "epoch": 0.0037241097847158454,
      "grad_norm": 1.155498743057251,
      "learning_rate": 7.52382768867422e-05,
      "loss": 0.659,
      "step": 73
    },
    {
      "epoch": 0.003775124987246199,
      "grad_norm": 1.0034657716751099,
      "learning_rate": 7.452117519152542e-05,
      "loss": 0.6234,
      "step": 74
    },
    {
      "epoch": 0.0038261401897765534,
      "grad_norm": 0.9839001297950745,
      "learning_rate": 7.379736965185368e-05,
      "loss": 0.6588,
      "step": 75
    },
    {
      "epoch": 0.0038771553923069076,
      "grad_norm": 0.9003528952598572,
      "learning_rate": 7.30670581489344e-05,
      "loss": 0.5224,
      "step": 76
    },
    {
      "epoch": 0.003928170594837262,
      "grad_norm": 1.137490153312683,
      "learning_rate": 7.233044034264034e-05,
      "loss": 0.6979,
      "step": 77
    },
    {
      "epoch": 0.003979185797367615,
      "grad_norm": 1.0123627185821533,
      "learning_rate": 7.158771761692464e-05,
      "loss": 0.6084,
      "step": 78
    },
    {
      "epoch": 0.004030200999897969,
      "grad_norm": 0.9710042476654053,
      "learning_rate": 7.083909302476453e-05,
      "loss": 0.5265,
      "step": 79
    },
    {
      "epoch": 0.004081216202428324,
      "grad_norm": 0.852706789970398,
      "learning_rate": 7.008477123264848e-05,
      "loss": 0.5406,
      "step": 80
    },
    {
      "epoch": 0.004132231404958678,
      "grad_norm": 1.2595216035842896,
      "learning_rate": 6.932495846462261e-05,
      "loss": 0.713,
      "step": 81
    },
    {
      "epoch": 0.004183246607489032,
      "grad_norm": 0.9067636728286743,
      "learning_rate": 6.855986244591104e-05,
      "loss": 0.5898,
      "step": 82
    },
    {
      "epoch": 0.004234261810019385,
      "grad_norm": 1.0178347826004028,
      "learning_rate": 6.778969234612584e-05,
      "loss": 0.6771,
      "step": 83
    },
    {
      "epoch": 0.0042852770125497396,
      "grad_norm": 1.1163185834884644,
      "learning_rate": 6.701465872208216e-05,
      "loss": 0.5688,
      "step": 84
    },
    {
      "epoch": 0.004336292215080094,
      "grad_norm": 0.9268144965171814,
      "learning_rate": 6.623497346023418e-05,
      "loss": 0.5357,
      "step": 85
    },
    {
      "epoch": 0.004387307417610448,
      "grad_norm": 1.1120328903198242,
      "learning_rate": 6.545084971874738e-05,
      "loss": 0.616,
      "step": 86
    },
    {
      "epoch": 0.004438322620140802,
      "grad_norm": 1.1013883352279663,
      "learning_rate": 6.466250186922325e-05,
      "loss": 0.5996,
      "step": 87
    },
    {
      "epoch": 0.004489337822671156,
      "grad_norm": 1.110445261001587,
      "learning_rate": 6.387014543809223e-05,
      "loss": 0.533,
      "step": 88
    },
    {
      "epoch": 0.00454035302520151,
      "grad_norm": 1.1144078969955444,
      "learning_rate": 6.307399704769099e-05,
      "loss": 0.6819,
      "step": 89
    },
    {
      "epoch": 0.004591368227731864,
      "grad_norm": 0.9260347485542297,
      "learning_rate": 6.227427435703997e-05,
      "loss": 0.5444,
      "step": 90
    },
    {
      "epoch": 0.004642383430262218,
      "grad_norm": 1.0573139190673828,
      "learning_rate": 6.147119600233758e-05,
      "loss": 0.6318,
      "step": 91
    },
    {
      "epoch": 0.004693398632792572,
      "grad_norm": 1.043210744857788,
      "learning_rate": 6.066498153718735e-05,
      "loss": 0.5157,
      "step": 92
    },
    {
      "epoch": 0.0047444138353229266,
      "grad_norm": 1.0416425466537476,
      "learning_rate": 5.985585137257401e-05,
      "loss": 0.5391,
      "step": 93
    },
    {
      "epoch": 0.00479542903785328,
      "grad_norm": 1.2475289106369019,
      "learning_rate": 5.90440267166055e-05,
      "loss": 0.6276,
      "step": 94
    },
    {
      "epoch": 0.004846444240383634,
      "grad_norm": 1.0211669206619263,
      "learning_rate": 5.8229729514036705e-05,
      "loss": 0.5017,
      "step": 95
    },
    {
      "epoch": 0.004897459442913988,
      "grad_norm": 1.3028045892715454,
      "learning_rate": 5.74131823855921e-05,
      "loss": 0.7187,
      "step": 96
    },
    {
      "epoch": 0.0049484746454443425,
      "grad_norm": 1.1932437419891357,
      "learning_rate": 5.6594608567103456e-05,
      "loss": 0.591,
      "step": 97
    },
    {
      "epoch": 0.004999489847974697,
      "grad_norm": 1.2623156309127808,
      "learning_rate": 5.577423184847932e-05,
      "loss": 0.6682,
      "step": 98
    },
    {
      "epoch": 0.005050505050505051,
      "grad_norm": 1.8324122428894043,
      "learning_rate": 5.495227651252315e-05,
      "loss": 0.7281,
      "step": 99
    },
    {
      "epoch": 0.005101520253035404,
      "grad_norm": 1.7937883138656616,
      "learning_rate": 5.4128967273616625e-05,
      "loss": 0.6457,
      "step": 100
    },
    {
      "epoch": 0.005101520253035404,
      "eval_loss": 0.7207558155059814,
      "eval_runtime": 1433.8662,
      "eval_samples_per_second": 23.024,
      "eval_steps_per_second": 5.756,
      "step": 100
    },
    {
      "epoch": 0.0051525354555657585,
      "grad_norm": 1.8114409446716309,
      "learning_rate": 5.330452921628497e-05,
      "loss": 1.4519,
      "step": 101
    },
    {
      "epoch": 0.005203550658096113,
      "grad_norm": 1.3645156621932983,
      "learning_rate": 5.247918773366112e-05,
      "loss": 0.9355,
      "step": 102
    },
    {
      "epoch": 0.005254565860626467,
      "grad_norm": 1.6342055797576904,
      "learning_rate": 5.165316846586541e-05,
      "loss": 1.1483,
      "step": 103
    },
    {
      "epoch": 0.005305581063156821,
      "grad_norm": 1.4563757181167603,
      "learning_rate": 5.0826697238317935e-05,
      "loss": 1.0416,
      "step": 104
    },
    {
      "epoch": 0.0053565962656871744,
      "grad_norm": 1.3042280673980713,
      "learning_rate": 5e-05,
      "loss": 0.9037,
      "step": 105
    },
    {
      "epoch": 0.005407611468217529,
      "grad_norm": 1.167454481124878,
      "learning_rate": 4.917330276168208e-05,
      "loss": 0.8422,
      "step": 106
    },
    {
      "epoch": 0.005458626670747883,
      "grad_norm": 1.5215885639190674,
      "learning_rate": 4.834683153413459e-05,
      "loss": 0.8697,
      "step": 107
    },
    {
      "epoch": 0.005509641873278237,
      "grad_norm": 1.1718409061431885,
      "learning_rate": 4.7520812266338885e-05,
      "loss": 0.8225,
      "step": 108
    },
    {
      "epoch": 0.005560657075808591,
      "grad_norm": 1.1947486400604248,
      "learning_rate": 4.669547078371504e-05,
      "loss": 0.9246,
      "step": 109
    },
    {
      "epoch": 0.005611672278338945,
      "grad_norm": 1.2682052850723267,
      "learning_rate": 4.5871032726383386e-05,
      "loss": 0.8374,
      "step": 110
    },
    {
      "epoch": 0.005662687480869299,
      "grad_norm": 1.0839130878448486,
      "learning_rate": 4.504772348747687e-05,
      "loss": 0.8509,
      "step": 111
    },
    {
      "epoch": 0.005713702683399653,
      "grad_norm": 1.0443567037582397,
      "learning_rate": 4.4225768151520694e-05,
      "loss": 0.8311,
      "step": 112
    },
    {
      "epoch": 0.005764717885930007,
      "grad_norm": 0.9204378724098206,
      "learning_rate": 4.3405391432896555e-05,
      "loss": 0.6479,
      "step": 113
    },
    {
      "epoch": 0.0058157330884603614,
      "grad_norm": 1.0801767110824585,
      "learning_rate": 4.2586817614407895e-05,
      "loss": 0.6897,
      "step": 114
    },
    {
      "epoch": 0.005866748290990716,
      "grad_norm": 0.9096378684043884,
      "learning_rate": 4.17702704859633e-05,
      "loss": 0.6534,
      "step": 115
    },
    {
      "epoch": 0.005917763493521069,
      "grad_norm": 0.9231741428375244,
      "learning_rate": 4.095597328339452e-05,
      "loss": 0.6428,
      "step": 116
    },
    {
      "epoch": 0.005968778696051423,
      "grad_norm": 1.1641801595687866,
      "learning_rate": 4.0144148627425993e-05,
      "loss": 0.8048,
      "step": 117
    },
    {
      "epoch": 0.006019793898581777,
      "grad_norm": 0.9723463654518127,
      "learning_rate": 3.933501846281267e-05,
      "loss": 0.6917,
      "step": 118
    },
    {
      "epoch": 0.006070809101112132,
      "grad_norm": 0.8771831393241882,
      "learning_rate": 3.852880399766243e-05,
      "loss": 0.6006,
      "step": 119
    },
    {
      "epoch": 0.006121824303642486,
      "grad_norm": 0.9439581036567688,
      "learning_rate": 3.772572564296005e-05,
      "loss": 0.6236,
      "step": 120
    },
    {
      "epoch": 0.006172839506172839,
      "grad_norm": 0.8829584717750549,
      "learning_rate": 3.6926002952309016e-05,
      "loss": 0.5982,
      "step": 121
    },
    {
      "epoch": 0.006223854708703193,
      "grad_norm": 0.9171614050865173,
      "learning_rate": 3.612985456190778e-05,
      "loss": 0.5895,
      "step": 122
    },
    {
      "epoch": 0.006274869911233548,
      "grad_norm": 0.8911136984825134,
      "learning_rate": 3.533749813077677e-05,
      "loss": 0.5654,
      "step": 123
    },
    {
      "epoch": 0.006325885113763902,
      "grad_norm": 0.8596011996269226,
      "learning_rate": 3.4549150281252636e-05,
      "loss": 0.6283,
      "step": 124
    },
    {
      "epoch": 0.006376900316294256,
      "grad_norm": 0.9068416357040405,
      "learning_rate": 3.3765026539765834e-05,
      "loss": 0.6281,
      "step": 125
    },
    {
      "epoch": 0.006427915518824609,
      "grad_norm": 0.9677693247795105,
      "learning_rate": 3.298534127791785e-05,
      "loss": 0.6103,
      "step": 126
    },
    {
      "epoch": 0.0064789307213549635,
      "grad_norm": 0.8677883744239807,
      "learning_rate": 3.221030765387417e-05,
      "loss": 0.55,
      "step": 127
    },
    {
      "epoch": 0.006529945923885318,
      "grad_norm": 1.0917985439300537,
      "learning_rate": 3.144013755408895e-05,
      "loss": 0.6188,
      "step": 128
    },
    {
      "epoch": 0.006580961126415672,
      "grad_norm": 0.8520172834396362,
      "learning_rate": 3.0675041535377405e-05,
      "loss": 0.5346,
      "step": 129
    },
    {
      "epoch": 0.006631976328946026,
      "grad_norm": 1.0461883544921875,
      "learning_rate": 2.991522876735154e-05,
      "loss": 0.6786,
      "step": 130
    },
    {
      "epoch": 0.00668299153147638,
      "grad_norm": 1.1208341121673584,
      "learning_rate": 2.916090697523549e-05,
      "loss": 0.6343,
      "step": 131
    },
    {
      "epoch": 0.006734006734006734,
      "grad_norm": 0.9349234700202942,
      "learning_rate": 2.8412282383075363e-05,
      "loss": 0.501,
      "step": 132
    },
    {
      "epoch": 0.006785021936537088,
      "grad_norm": 1.0781103372573853,
      "learning_rate": 2.766955965735968e-05,
      "loss": 0.7478,
      "step": 133
    },
    {
      "epoch": 0.006836037139067442,
      "grad_norm": 0.9444073438644409,
      "learning_rate": 2.693294185106562e-05,
      "loss": 0.5975,
      "step": 134
    },
    {
      "epoch": 0.006887052341597796,
      "grad_norm": 1.1122676134109497,
      "learning_rate": 2.6202630348146324e-05,
      "loss": 0.7441,
      "step": 135
    },
    {
      "epoch": 0.0069380675441281505,
      "grad_norm": 0.890365481376648,
      "learning_rate": 2.547882480847461e-05,
      "loss": 0.5508,
      "step": 136
    },
    {
      "epoch": 0.006989082746658504,
      "grad_norm": 1.0402615070343018,
      "learning_rate": 2.476172311325783e-05,
      "loss": 0.62,
      "step": 137
    },
    {
      "epoch": 0.007040097949188858,
      "grad_norm": 0.8860926628112793,
      "learning_rate": 2.405152131093926e-05,
      "loss": 0.5367,
      "step": 138
    },
    {
      "epoch": 0.007091113151719212,
      "grad_norm": 1.0476042032241821,
      "learning_rate": 2.3348413563600325e-05,
      "loss": 0.5839,
      "step": 139
    },
    {
      "epoch": 0.0071421283542495665,
      "grad_norm": 0.866302490234375,
      "learning_rate": 2.2652592093878666e-05,
      "loss": 0.5287,
      "step": 140
    },
    {
      "epoch": 0.007193143556779921,
      "grad_norm": 1.0551623106002808,
      "learning_rate": 2.196424713241637e-05,
      "loss": 0.5768,
      "step": 141
    },
    {
      "epoch": 0.007244158759310274,
      "grad_norm": 1.14937162399292,
      "learning_rate": 2.128356686585282e-05,
      "loss": 0.6421,
      "step": 142
    },
    {
      "epoch": 0.007295173961840628,
      "grad_norm": 0.9636757373809814,
      "learning_rate": 2.061073738537635e-05,
      "loss": 0.6001,
      "step": 143
    },
    {
      "epoch": 0.0073461891643709825,
      "grad_norm": 0.8499124646186829,
      "learning_rate": 1.9945942635848748e-05,
      "loss": 0.525,
      "step": 144
    },
    {
      "epoch": 0.007397204366901337,
      "grad_norm": 1.1190030574798584,
      "learning_rate": 1.928936436551661e-05,
      "loss": 0.6799,
      "step": 145
    },
    {
      "epoch": 0.007448219569431691,
      "grad_norm": 1.0400668382644653,
      "learning_rate": 1.8641182076323148e-05,
      "loss": 0.5394,
      "step": 146
    },
    {
      "epoch": 0.007499234771962045,
      "grad_norm": 1.0704658031463623,
      "learning_rate": 1.800157297483417e-05,
      "loss": 0.4973,
      "step": 147
    },
    {
      "epoch": 0.007550249974492398,
      "grad_norm": 0.9756684303283691,
      "learning_rate": 1.7370711923791567e-05,
      "loss": 0.5394,
      "step": 148
    },
    {
      "epoch": 0.007601265177022753,
      "grad_norm": 1.161603569984436,
      "learning_rate": 1.6748771394307585e-05,
      "loss": 0.5637,
      "step": 149
    },
    {
      "epoch": 0.007652280379553107,
      "grad_norm": 1.4681497812271118,
      "learning_rate": 1.6135921418712956e-05,
      "loss": 0.5215,
      "step": 150
    },
    {
      "epoch": 0.007652280379553107,
      "eval_loss": 0.6727603077888489,
      "eval_runtime": 1432.5915,
      "eval_samples_per_second": 23.045,
      "eval_steps_per_second": 5.762,
      "step": 150
    }
  ],
  "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": false
      },
      "attributes": {}
    }
  },
  "total_flos": 1.0153543433453568e+17,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}