{
  "best_metric": 0.3646468222141266,
  "best_model_checkpoint": "miner_id_24/checkpoint-200",
  "epoch": 0.008380122349786306,
  "eval_steps": 50,
  "global_step": 200,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 4.1900611748931536e-05,
      "grad_norm": 12.401717185974121,
      "learning_rate": 1e-05,
      "loss": 2.061,
      "step": 1
    },
    {
      "epoch": 4.1900611748931536e-05,
      "eval_loss": 2.11004638671875,
      "eval_runtime": 692.2473,
      "eval_samples_per_second": 58.066,
      "eval_steps_per_second": 14.516,
      "step": 1
    },
    {
      "epoch": 8.380122349786307e-05,
      "grad_norm": 12.52931022644043,
      "learning_rate": 2e-05,
      "loss": 2.0749,
      "step": 2
    },
    {
      "epoch": 0.00012570183524679462,
      "grad_norm": 11.506692886352539,
      "learning_rate": 3e-05,
      "loss": 2.0324,
      "step": 3
    },
    {
      "epoch": 0.00016760244699572614,
      "grad_norm": 8.164826393127441,
      "learning_rate": 4e-05,
      "loss": 1.7553,
      "step": 4
    },
    {
      "epoch": 0.00020950305874465767,
      "grad_norm": 6.681891441345215,
      "learning_rate": 5e-05,
      "loss": 1.4661,
      "step": 5
    },
    {
      "epoch": 0.00025140367049358923,
      "grad_norm": 4.889027118682861,
      "learning_rate": 6e-05,
      "loss": 1.2743,
      "step": 6
    },
    {
      "epoch": 0.00029330428224252073,
      "grad_norm": 3.842980146408081,
      "learning_rate": 7e-05,
      "loss": 1.1415,
      "step": 7
    },
    {
      "epoch": 0.0003352048939914523,
      "grad_norm": 2.804058313369751,
      "learning_rate": 8e-05,
      "loss": 1.0483,
      "step": 8
    },
    {
      "epoch": 0.0003771055057403838,
      "grad_norm": 3.046818971633911,
      "learning_rate": 9e-05,
      "loss": 0.938,
      "step": 9
    },
    {
      "epoch": 0.00041900611748931535,
      "grad_norm": 4.104994773864746,
      "learning_rate": 0.0001,
      "loss": 0.9117,
      "step": 10
    },
    {
      "epoch": 0.0004609067292382469,
      "grad_norm": 2.3753490447998047,
      "learning_rate": 9.999316524962345e-05,
      "loss": 0.866,
      "step": 11
    },
    {
      "epoch": 0.0005028073409871785,
      "grad_norm": 2.4568893909454346,
      "learning_rate": 9.997266286704631e-05,
      "loss": 0.8204,
      "step": 12
    },
    {
      "epoch": 0.0005447079527361099,
      "grad_norm": 1.7458099126815796,
      "learning_rate": 9.993849845741524e-05,
      "loss": 0.7604,
      "step": 13
    },
    {
      "epoch": 0.0005866085644850415,
      "grad_norm": 6.724311351776123,
      "learning_rate": 9.989068136093873e-05,
      "loss": 0.8606,
      "step": 14
    },
    {
      "epoch": 0.000628509176233973,
      "grad_norm": 4.7568159103393555,
      "learning_rate": 9.98292246503335e-05,
      "loss": 0.7796,
      "step": 15
    },
    {
      "epoch": 0.0006704097879829046,
      "grad_norm": 1.8319369554519653,
      "learning_rate": 9.975414512725057e-05,
      "loss": 0.7134,
      "step": 16
    },
    {
      "epoch": 0.0007123103997318361,
      "grad_norm": 2.7333900928497314,
      "learning_rate": 9.966546331768191e-05,
      "loss": 0.705,
      "step": 17
    },
    {
      "epoch": 0.0007542110114807676,
      "grad_norm": 2.1540844440460205,
      "learning_rate": 9.956320346634876e-05,
      "loss": 0.7115,
      "step": 18
    },
    {
      "epoch": 0.0007961116232296991,
      "grad_norm": 1.64785635471344,
      "learning_rate": 9.944739353007344e-05,
      "loss": 0.6477,
      "step": 19
    },
    {
      "epoch": 0.0008380122349786307,
      "grad_norm": 2.0590991973876953,
      "learning_rate": 9.931806517013612e-05,
      "loss": 0.626,
      "step": 20
    },
    {
      "epoch": 0.0008799128467275623,
      "grad_norm": 2.685298442840576,
      "learning_rate": 9.917525374361912e-05,
      "loss": 0.6309,
      "step": 21
    },
    {
      "epoch": 0.0009218134584764938,
      "grad_norm": 1.4915673732757568,
      "learning_rate": 9.901899829374047e-05,
      "loss": 0.6027,
      "step": 22
    },
    {
      "epoch": 0.0009637140702254253,
      "grad_norm": 1.5001156330108643,
      "learning_rate": 9.884934153917997e-05,
      "loss": 0.6043,
      "step": 23
    },
    {
      "epoch": 0.001005614681974357,
      "grad_norm": 1.620923399925232,
      "learning_rate": 9.86663298624003e-05,
      "loss": 0.5616,
      "step": 24
    },
    {
      "epoch": 0.0010475152937232883,
      "grad_norm": 1.9177049398422241,
      "learning_rate": 9.847001329696653e-05,
      "loss": 0.5861,
      "step": 25
    },
    {
      "epoch": 0.0010894159054722198,
      "grad_norm": 2.3297927379608154,
      "learning_rate": 9.826044551386744e-05,
      "loss": 0.5632,
      "step": 26
    },
    {
      "epoch": 0.0011313165172211514,
      "grad_norm": 1.8214315176010132,
      "learning_rate": 9.803768380684242e-05,
      "loss": 0.5403,
      "step": 27
    },
    {
      "epoch": 0.001173217128970083,
      "grad_norm": 1.155811071395874,
      "learning_rate": 9.780178907671789e-05,
      "loss": 0.4964,
      "step": 28
    },
    {
      "epoch": 0.0012151177407190145,
      "grad_norm": 1.4073199033737183,
      "learning_rate": 9.755282581475769e-05,
      "loss": 0.4767,
      "step": 29
    },
    {
      "epoch": 0.001257018352467946,
      "grad_norm": 1.3528127670288086,
      "learning_rate": 9.729086208503174e-05,
      "loss": 0.4711,
      "step": 30
    },
    {
      "epoch": 0.0012989189642168776,
      "grad_norm": 1.9988888502120972,
      "learning_rate": 9.701596950580806e-05,
      "loss": 0.5098,
      "step": 31
    },
    {
      "epoch": 0.0013408195759658092,
      "grad_norm": 1.3981701135635376,
      "learning_rate": 9.672822322997305e-05,
      "loss": 0.457,
      "step": 32
    },
    {
      "epoch": 0.0013827201877147407,
      "grad_norm": 1.3816455602645874,
      "learning_rate": 9.642770192448536e-05,
      "loss": 0.4554,
      "step": 33
    },
    {
      "epoch": 0.0014246207994636723,
      "grad_norm": 1.7540465593338013,
      "learning_rate": 9.611448774886924e-05,
      "loss": 0.4801,
      "step": 34
    },
    {
      "epoch": 0.0014665214112126036,
      "grad_norm": 1.3476214408874512,
      "learning_rate": 9.578866633275288e-05,
      "loss": 0.4531,
      "step": 35
    },
    {
      "epoch": 0.0015084220229615352,
      "grad_norm": 1.5144597291946411,
      "learning_rate": 9.545032675245813e-05,
      "loss": 0.455,
      "step": 36
    },
    {
      "epoch": 0.0015503226347104667,
      "grad_norm": 1.5056521892547607,
      "learning_rate": 9.509956150664796e-05,
      "loss": 0.4432,
      "step": 37
    },
    {
      "epoch": 0.0015922232464593983,
      "grad_norm": 0.9943171143531799,
      "learning_rate": 9.473646649103818e-05,
      "loss": 0.4233,
      "step": 38
    },
    {
      "epoch": 0.0016341238582083298,
      "grad_norm": 1.269155740737915,
      "learning_rate": 9.43611409721806e-05,
      "loss": 0.4383,
      "step": 39
    },
    {
      "epoch": 0.0016760244699572614,
      "grad_norm": 0.78570556640625,
      "learning_rate": 9.397368756032445e-05,
      "loss": 0.4268,
      "step": 40
    },
    {
      "epoch": 0.001717925081706193,
      "grad_norm": 1.1826995611190796,
      "learning_rate": 9.357421218136386e-05,
      "loss": 0.4396,
      "step": 41
    },
    {
      "epoch": 0.0017598256934551245,
      "grad_norm": 1.1438935995101929,
      "learning_rate": 9.316282404787871e-05,
      "loss": 0.4056,
      "step": 42
    },
    {
      "epoch": 0.001801726305204056,
      "grad_norm": 1.2345468997955322,
      "learning_rate": 9.273963562927695e-05,
      "loss": 0.4194,
      "step": 43
    },
    {
      "epoch": 0.0018436269169529876,
      "grad_norm": 0.8941552042961121,
      "learning_rate": 9.230476262104677e-05,
      "loss": 0.3862,
      "step": 44
    },
    {
      "epoch": 0.001885527528701919,
      "grad_norm": 0.8636603355407715,
      "learning_rate": 9.185832391312644e-05,
      "loss": 0.4137,
      "step": 45
    },
    {
      "epoch": 0.0019274281404508505,
      "grad_norm": 1.251181721687317,
      "learning_rate": 9.140044155740101e-05,
      "loss": 0.416,
      "step": 46
    },
    {
      "epoch": 0.0019693287521997823,
      "grad_norm": 1.2790541648864746,
      "learning_rate": 9.093124073433463e-05,
      "loss": 0.3989,
      "step": 47
    },
    {
      "epoch": 0.002011229363948714,
      "grad_norm": 0.7371829152107239,
      "learning_rate": 9.045084971874738e-05,
      "loss": 0.4066,
      "step": 48
    },
    {
      "epoch": 0.0020531299756976454,
      "grad_norm": 0.8136070966720581,
      "learning_rate": 8.995939984474624e-05,
      "loss": 0.4134,
      "step": 49
    },
    {
      "epoch": 0.0020950305874465765,
      "grad_norm": 1.1840046644210815,
      "learning_rate": 8.945702546981969e-05,
      "loss": 0.4251,
      "step": 50
    },
    {
      "epoch": 0.0020950305874465765,
      "eval_loss": 0.4079367518424988,
      "eval_runtime": 692.3157,
      "eval_samples_per_second": 58.06,
      "eval_steps_per_second": 14.515,
      "step": 50
    },
    {
      "epoch": 0.002136931199195508,
      "grad_norm": 1.161297082901001,
      "learning_rate": 8.894386393810563e-05,
      "loss": 0.4142,
      "step": 51
    },
    {
      "epoch": 0.0021788318109444396,
      "grad_norm": 1.1976879835128784,
      "learning_rate": 8.842005554284296e-05,
      "loss": 0.4044,
      "step": 52
    },
    {
      "epoch": 0.002220732422693371,
      "grad_norm": 0.7049624919891357,
      "learning_rate": 8.788574348801675e-05,
      "loss": 0.3883,
      "step": 53
    },
    {
      "epoch": 0.0022626330344423027,
      "grad_norm": 0.7691147327423096,
      "learning_rate": 8.73410738492077e-05,
      "loss": 0.4064,
      "step": 54
    },
    {
      "epoch": 0.0023045336461912343,
      "grad_norm": 1.1453278064727783,
      "learning_rate": 8.678619553365659e-05,
      "loss": 0.4126,
      "step": 55
    },
    {
      "epoch": 0.002346434257940166,
      "grad_norm": 0.7199950218200684,
      "learning_rate": 8.622126023955446e-05,
      "loss": 0.3924,
      "step": 56
    },
    {
      "epoch": 0.0023883348696890974,
      "grad_norm": 0.9202678203582764,
      "learning_rate": 8.564642241456986e-05,
      "loss": 0.3932,
      "step": 57
    },
    {
      "epoch": 0.002430235481438029,
      "grad_norm": 0.7786675095558167,
      "learning_rate": 8.506183921362443e-05,
      "loss": 0.3985,
      "step": 58
    },
    {
      "epoch": 0.0024721360931869605,
      "grad_norm": 0.7222663164138794,
      "learning_rate": 8.44676704559283e-05,
      "loss": 0.3705,
      "step": 59
    },
    {
      "epoch": 0.002514036704935892,
      "grad_norm": 1.0414471626281738,
      "learning_rate": 8.386407858128706e-05,
      "loss": 0.3923,
      "step": 60
    },
    {
      "epoch": 0.0025559373166848236,
      "grad_norm": 0.953230082988739,
      "learning_rate": 8.32512286056924e-05,
      "loss": 0.3928,
      "step": 61
    },
    {
      "epoch": 0.002597837928433755,
      "grad_norm": 0.7045029997825623,
      "learning_rate": 8.262928807620843e-05,
      "loss": 0.3899,
      "step": 62
    },
    {
      "epoch": 0.0026397385401826868,
      "grad_norm": 0.5819854140281677,
      "learning_rate": 8.199842702516583e-05,
      "loss": 0.3722,
      "step": 63
    },
    {
      "epoch": 0.0026816391519316183,
      "grad_norm": 0.6675421595573425,
      "learning_rate": 8.135881792367686e-05,
      "loss": 0.3885,
      "step": 64
    },
    {
      "epoch": 0.00272353976368055,
      "grad_norm": 0.5888473987579346,
      "learning_rate": 8.07106356344834e-05,
      "loss": 0.3793,
      "step": 65
    },
    {
      "epoch": 0.0027654403754294814,
      "grad_norm": 0.6285983920097351,
      "learning_rate": 8.005405736415126e-05,
      "loss": 0.3713,
      "step": 66
    },
    {
      "epoch": 0.002807340987178413,
      "grad_norm": 0.5629648566246033,
      "learning_rate": 7.938926261462366e-05,
      "loss": 0.3762,
      "step": 67
    },
    {
      "epoch": 0.0028492415989273445,
      "grad_norm": 0.8168434500694275,
      "learning_rate": 7.871643313414718e-05,
      "loss": 0.3882,
      "step": 68
    },
    {
      "epoch": 0.0028911422106762757,
      "grad_norm": 0.8386833071708679,
      "learning_rate": 7.803575286758364e-05,
      "loss": 0.3925,
      "step": 69
    },
    {
      "epoch": 0.0029330428224252072,
      "grad_norm": 0.6754161715507507,
      "learning_rate": 7.734740790612136e-05,
      "loss": 0.3858,
      "step": 70
    },
    {
      "epoch": 0.0029749434341741388,
      "grad_norm": 0.5120207667350769,
      "learning_rate": 7.66515864363997e-05,
      "loss": 0.3717,
      "step": 71
    },
    {
      "epoch": 0.0030168440459230703,
      "grad_norm": 0.5557418465614319,
      "learning_rate": 7.594847868906076e-05,
      "loss": 0.3718,
      "step": 72
    },
    {
      "epoch": 0.003058744657672002,
      "grad_norm": 0.8242805004119873,
      "learning_rate": 7.52382768867422e-05,
      "loss": 0.378,
      "step": 73
    },
    {
      "epoch": 0.0031006452694209334,
      "grad_norm": 0.5544095635414124,
      "learning_rate": 7.452117519152542e-05,
      "loss": 0.3855,
      "step": 74
    },
    {
      "epoch": 0.003142545881169865,
      "grad_norm": 0.46886885166168213,
      "learning_rate": 7.379736965185368e-05,
      "loss": 0.381,
      "step": 75
    },
    {
      "epoch": 0.0031844464929187966,
      "grad_norm": 0.46993863582611084,
      "learning_rate": 7.30670581489344e-05,
      "loss": 0.3642,
      "step": 76
    },
    {
      "epoch": 0.003226347104667728,
      "grad_norm": 0.48749837279319763,
      "learning_rate": 7.233044034264034e-05,
      "loss": 0.365,
      "step": 77
    },
    {
      "epoch": 0.0032682477164166597,
      "grad_norm": 0.6306229829788208,
      "learning_rate": 7.158771761692464e-05,
      "loss": 0.3683,
      "step": 78
    },
    {
      "epoch": 0.0033101483281655912,
      "grad_norm": 0.8397689461708069,
      "learning_rate": 7.083909302476453e-05,
      "loss": 0.3828,
      "step": 79
    },
    {
      "epoch": 0.0033520489399145228,
      "grad_norm": 0.614453136920929,
      "learning_rate": 7.008477123264848e-05,
      "loss": 0.3867,
      "step": 80
    },
    {
      "epoch": 0.0033939495516634543,
      "grad_norm": 0.49757665395736694,
      "learning_rate": 6.932495846462261e-05,
      "loss": 0.3801,
      "step": 81
    },
    {
      "epoch": 0.003435850163412386,
      "grad_norm": 0.4922657310962677,
      "learning_rate": 6.855986244591104e-05,
      "loss": 0.3729,
      "step": 82
    },
    {
      "epoch": 0.0034777507751613175,
      "grad_norm": 0.5341781377792358,
      "learning_rate": 6.778969234612584e-05,
      "loss": 0.3788,
      "step": 83
    },
    {
      "epoch": 0.003519651386910249,
      "grad_norm": 0.5263535380363464,
      "learning_rate": 6.701465872208216e-05,
      "loss": 0.3688,
      "step": 84
    },
    {
      "epoch": 0.0035615519986591806,
      "grad_norm": 0.49736541509628296,
      "learning_rate": 6.623497346023418e-05,
      "loss": 0.3621,
      "step": 85
    },
    {
      "epoch": 0.003603452610408112,
      "grad_norm": 0.6529773473739624,
      "learning_rate": 6.545084971874738e-05,
      "loss": 0.377,
      "step": 86
    },
    {
      "epoch": 0.0036453532221570437,
      "grad_norm": 0.5781784653663635,
      "learning_rate": 6.466250186922325e-05,
      "loss": 0.3622,
      "step": 87
    },
    {
      "epoch": 0.0036872538339059752,
      "grad_norm": 0.46664315462112427,
      "learning_rate": 6.387014543809223e-05,
      "loss": 0.3768,
      "step": 88
    },
    {
      "epoch": 0.0037291544456549064,
      "grad_norm": 0.40756192803382874,
      "learning_rate": 6.307399704769099e-05,
      "loss": 0.3637,
      "step": 89
    },
    {
      "epoch": 0.003771055057403838,
      "grad_norm": 0.3784383237361908,
      "learning_rate": 6.227427435703997e-05,
      "loss": 0.3657,
      "step": 90
    },
    {
      "epoch": 0.0038129556691527695,
      "grad_norm": 0.8758529424667358,
      "learning_rate": 6.147119600233758e-05,
      "loss": 0.3745,
      "step": 91
    },
    {
      "epoch": 0.003854856280901701,
      "grad_norm": 0.3926626741886139,
      "learning_rate": 6.066498153718735e-05,
      "loss": 0.37,
      "step": 92
    },
    {
      "epoch": 0.0038967568926506326,
      "grad_norm": 0.3462725579738617,
      "learning_rate": 5.985585137257401e-05,
      "loss": 0.374,
      "step": 93
    },
    {
      "epoch": 0.003938657504399565,
      "grad_norm": 0.39854007959365845,
      "learning_rate": 5.90440267166055e-05,
      "loss": 0.3665,
      "step": 94
    },
    {
      "epoch": 0.003980558116148496,
      "grad_norm": 1.051824688911438,
      "learning_rate": 5.8229729514036705e-05,
      "loss": 0.4037,
      "step": 95
    },
    {
      "epoch": 0.004022458727897428,
      "grad_norm": 0.41116276383399963,
      "learning_rate": 5.74131823855921e-05,
      "loss": 0.3734,
      "step": 96
    },
    {
      "epoch": 0.004064359339646359,
      "grad_norm": 0.6195436120033264,
      "learning_rate": 5.6594608567103456e-05,
      "loss": 0.3706,
      "step": 97
    },
    {
      "epoch": 0.004106259951395291,
      "grad_norm": 0.42274677753448486,
      "learning_rate": 5.577423184847932e-05,
      "loss": 0.3623,
      "step": 98
    },
    {
      "epoch": 0.004148160563144222,
      "grad_norm": 0.5260018706321716,
      "learning_rate": 5.495227651252315e-05,
      "loss": 0.3814,
      "step": 99
    },
    {
      "epoch": 0.004190061174893153,
      "grad_norm": 0.5149572491645813,
      "learning_rate": 5.4128967273616625e-05,
      "loss": 0.385,
      "step": 100
    },
    {
      "epoch": 0.004190061174893153,
      "eval_loss": 0.3764027953147888,
      "eval_runtime": 692.9373,
      "eval_samples_per_second": 58.008,
      "eval_steps_per_second": 14.502,
      "step": 100
    },
    {
      "epoch": 0.004231961786642085,
      "grad_norm": 0.6027266383171082,
      "learning_rate": 5.330452921628497e-05,
      "loss": 0.3808,
      "step": 101
    },
    {
      "epoch": 0.004273862398391016,
      "grad_norm": 0.4798916280269623,
      "learning_rate": 5.247918773366112e-05,
      "loss": 0.3603,
      "step": 102
    },
    {
      "epoch": 0.004315763010139948,
      "grad_norm": 0.7150884866714478,
      "learning_rate": 5.165316846586541e-05,
      "loss": 0.3881,
      "step": 103
    },
    {
      "epoch": 0.004357663621888879,
      "grad_norm": 0.3941900432109833,
      "learning_rate": 5.0826697238317935e-05,
      "loss": 0.3736,
      "step": 104
    },
    {
      "epoch": 0.004399564233637811,
      "grad_norm": 0.46804314851760864,
      "learning_rate": 5e-05,
      "loss": 0.3802,
      "step": 105
    },
    {
      "epoch": 0.004441464845386742,
      "grad_norm": 0.3976142108440399,
      "learning_rate": 4.917330276168208e-05,
      "loss": 0.3802,
      "step": 106
    },
    {
      "epoch": 0.004483365457135674,
      "grad_norm": 0.47338852286338806,
      "learning_rate": 4.834683153413459e-05,
      "loss": 0.3784,
      "step": 107
    },
    {
      "epoch": 0.0045252660688846055,
      "grad_norm": 0.4946283996105194,
      "learning_rate": 4.7520812266338885e-05,
      "loss": 0.3702,
      "step": 108
    },
    {
      "epoch": 0.0045671666806335375,
      "grad_norm": 0.46376827359199524,
      "learning_rate": 4.669547078371504e-05,
      "loss": 0.3723,
      "step": 109
    },
    {
      "epoch": 0.004609067292382469,
      "grad_norm": 0.4808342754840851,
      "learning_rate": 4.5871032726383386e-05,
      "loss": 0.362,
      "step": 110
    },
    {
      "epoch": 0.004650967904131401,
      "grad_norm": 0.41980302333831787,
      "learning_rate": 4.504772348747687e-05,
      "loss": 0.3745,
      "step": 111
    },
    {
      "epoch": 0.004692868515880332,
      "grad_norm": 0.41989701986312866,
      "learning_rate": 4.4225768151520694e-05,
      "loss": 0.3772,
      "step": 112
    },
    {
      "epoch": 0.004734769127629264,
      "grad_norm": 0.44435012340545654,
      "learning_rate": 4.3405391432896555e-05,
      "loss": 0.3841,
      "step": 113
    },
    {
      "epoch": 0.004776669739378195,
      "grad_norm": 0.4629721939563751,
      "learning_rate": 4.2586817614407895e-05,
      "loss": 0.3728,
      "step": 114
    },
    {
      "epoch": 0.004818570351127127,
      "grad_norm": 0.42354342341423035,
      "learning_rate": 4.17702704859633e-05,
      "loss": 0.36,
      "step": 115
    },
    {
      "epoch": 0.004860470962876058,
      "grad_norm": 0.44069820642471313,
      "learning_rate": 4.095597328339452e-05,
      "loss": 0.3694,
      "step": 116
    },
    {
      "epoch": 0.00490237157462499,
      "grad_norm": 0.3773685693740845,
      "learning_rate": 4.0144148627425993e-05,
      "loss": 0.3663,
      "step": 117
    },
    {
      "epoch": 0.004944272186373921,
      "grad_norm": 0.4707624018192291,
      "learning_rate": 3.933501846281267e-05,
      "loss": 0.3601,
      "step": 118
    },
    {
      "epoch": 0.004986172798122852,
      "grad_norm": 0.45369499921798706,
      "learning_rate": 3.852880399766243e-05,
      "loss": 0.3699,
      "step": 119
    },
    {
      "epoch": 0.005028073409871784,
      "grad_norm": 0.4905252158641815,
      "learning_rate": 3.772572564296005e-05,
      "loss": 0.3649,
      "step": 120
    },
    {
      "epoch": 0.005069974021620715,
      "grad_norm": 0.4178149104118347,
      "learning_rate": 3.6926002952309016e-05,
      "loss": 0.3607,
      "step": 121
    },
    {
      "epoch": 0.005111874633369647,
      "grad_norm": 0.7921212315559387,
      "learning_rate": 3.612985456190778e-05,
      "loss": 0.3804,
      "step": 122
    },
    {
      "epoch": 0.005153775245118578,
      "grad_norm": 0.4230062663555145,
      "learning_rate": 3.533749813077677e-05,
      "loss": 0.3662,
      "step": 123
    },
    {
      "epoch": 0.00519567585686751,
      "grad_norm": 0.3610653281211853,
      "learning_rate": 3.4549150281252636e-05,
      "loss": 0.365,
      "step": 124
    },
    {
      "epoch": 0.0052375764686164415,
      "grad_norm": 0.37206318974494934,
      "learning_rate": 3.3765026539765834e-05,
      "loss": 0.3642,
      "step": 125
    },
    {
      "epoch": 0.0052794770803653735,
      "grad_norm": 0.3862723708152771,
      "learning_rate": 3.298534127791785e-05,
      "loss": 0.3688,
      "step": 126
    },
    {
      "epoch": 0.005321377692114305,
      "grad_norm": 0.6313711404800415,
      "learning_rate": 3.221030765387417e-05,
      "loss": 0.3804,
      "step": 127
    },
    {
      "epoch": 0.005363278303863237,
      "grad_norm": 0.3333760201931,
      "learning_rate": 3.144013755408895e-05,
      "loss": 0.3583,
      "step": 128
    },
    {
      "epoch": 0.005405178915612168,
      "grad_norm": 0.3670137822628021,
      "learning_rate": 3.0675041535377405e-05,
      "loss": 0.3686,
      "step": 129
    },
    {
      "epoch": 0.0054470795273611,
      "grad_norm": 0.3866000175476074,
      "learning_rate": 2.991522876735154e-05,
      "loss": 0.363,
      "step": 130
    },
    {
      "epoch": 0.005488980139110031,
      "grad_norm": 0.45716607570648193,
      "learning_rate": 2.916090697523549e-05,
      "loss": 0.3602,
      "step": 131
    },
    {
      "epoch": 0.005530880750858963,
      "grad_norm": 0.38701626658439636,
      "learning_rate": 2.8412282383075363e-05,
      "loss": 0.3688,
      "step": 132
    },
    {
      "epoch": 0.005572781362607894,
      "grad_norm": 0.3579891324043274,
      "learning_rate": 2.766955965735968e-05,
      "loss": 0.3595,
      "step": 133
    },
    {
      "epoch": 0.005614681974356826,
      "grad_norm": 0.4002384841442108,
      "learning_rate": 2.693294185106562e-05,
      "loss": 0.3617,
      "step": 134
    },
    {
      "epoch": 0.005656582586105757,
      "grad_norm": 0.3796548843383789,
      "learning_rate": 2.6202630348146324e-05,
      "loss": 0.3752,
      "step": 135
    },
    {
      "epoch": 0.005698483197854689,
      "grad_norm": 0.3744058907032013,
      "learning_rate": 2.547882480847461e-05,
      "loss": 0.3697,
      "step": 136
    },
    {
      "epoch": 0.00574038380960362,
      "grad_norm": 0.3978886306285858,
      "learning_rate": 2.476172311325783e-05,
      "loss": 0.3671,
      "step": 137
    },
    {
      "epoch": 0.005782284421352551,
      "grad_norm": 0.36514753103256226,
      "learning_rate": 2.405152131093926e-05,
      "loss": 0.3698,
      "step": 138
    },
    {
      "epoch": 0.005824185033101483,
      "grad_norm": 0.4446398913860321,
      "learning_rate": 2.3348413563600325e-05,
      "loss": 0.3562,
      "step": 139
    },
    {
      "epoch": 0.0058660856448504144,
      "grad_norm": 0.6335402727127075,
      "learning_rate": 2.2652592093878666e-05,
      "loss": 0.3711,
      "step": 140
    },
    {
      "epoch": 0.005907986256599346,
      "grad_norm": 0.39303654432296753,
      "learning_rate": 2.196424713241637e-05,
      "loss": 0.3612,
      "step": 141
    },
    {
      "epoch": 0.0059498868683482775,
      "grad_norm": 0.458608478307724,
      "learning_rate": 2.128356686585282e-05,
      "loss": 0.3657,
      "step": 142
    },
    {
      "epoch": 0.0059917874800972095,
      "grad_norm": 0.33949828147888184,
      "learning_rate": 2.061073738537635e-05,
      "loss": 0.3651,
      "step": 143
    },
    {
      "epoch": 0.006033688091846141,
      "grad_norm": 0.41564124822616577,
      "learning_rate": 1.9945942635848748e-05,
      "loss": 0.3564,
      "step": 144
    },
    {
      "epoch": 0.006075588703595073,
      "grad_norm": 0.4284324049949646,
      "learning_rate": 1.928936436551661e-05,
      "loss": 0.3699,
      "step": 145
    },
    {
      "epoch": 0.006117489315344004,
      "grad_norm": 0.5253200531005859,
      "learning_rate": 1.8641182076323148e-05,
      "loss": 0.3781,
      "step": 146
    },
    {
      "epoch": 0.006159389927092936,
      "grad_norm": 0.3606500029563904,
      "learning_rate": 1.800157297483417e-05,
      "loss": 0.3694,
      "step": 147
    },
    {
      "epoch": 0.006201290538841867,
      "grad_norm": 0.32398709654808044,
      "learning_rate": 1.7370711923791567e-05,
      "loss": 0.3786,
      "step": 148
    },
    {
      "epoch": 0.006243191150590799,
      "grad_norm": 0.4401916265487671,
      "learning_rate": 1.6748771394307585e-05,
      "loss": 0.3932,
      "step": 149
    },
    {
      "epoch": 0.00628509176233973,
      "grad_norm": 0.48635241389274597,
      "learning_rate": 1.6135921418712956e-05,
      "loss": 0.3987,
      "step": 150
    },
    {
      "epoch": 0.00628509176233973,
      "eval_loss": 0.36657968163490295,
      "eval_runtime": 692.7293,
      "eval_samples_per_second": 58.026,
      "eval_steps_per_second": 14.506,
      "step": 150
    },
    {
      "epoch": 0.006326992374088662,
      "grad_norm": 0.3790470063686371,
      "learning_rate": 1.553232954407171e-05,
      "loss": 0.3643,
      "step": 151
    },
    {
      "epoch": 0.006368892985837593,
      "grad_norm": 0.4393303692340851,
      "learning_rate": 1.4938160786375572e-05,
      "loss": 0.3707,
      "step": 152
    },
    {
      "epoch": 0.006410793597586525,
      "grad_norm": 0.3993956446647644,
      "learning_rate": 1.435357758543015e-05,
      "loss": 0.3618,
      "step": 153
    },
    {
      "epoch": 0.006452694209335456,
      "grad_norm": 0.3912157118320465,
      "learning_rate": 1.3778739760445552e-05,
      "loss": 0.3621,
      "step": 154
    },
    {
      "epoch": 0.006494594821084388,
      "grad_norm": 0.40146297216415405,
      "learning_rate": 1.3213804466343421e-05,
      "loss": 0.3607,
      "step": 155
    },
    {
      "epoch": 0.006536495432833319,
      "grad_norm": 0.3602310121059418,
      "learning_rate": 1.2658926150792322e-05,
      "loss": 0.3631,
      "step": 156
    },
    {
      "epoch": 0.006578396044582251,
      "grad_norm": 0.35525843501091003,
      "learning_rate": 1.2114256511983274e-05,
      "loss": 0.3577,
      "step": 157
    },
    {
      "epoch": 0.0066202966563311825,
      "grad_norm": 0.518125057220459,
      "learning_rate": 1.157994445715706e-05,
      "loss": 0.3728,
      "step": 158
    },
    {
      "epoch": 0.006662197268080114,
      "grad_norm": 0.38681668043136597,
      "learning_rate": 1.1056136061894384e-05,
      "loss": 0.3642,
      "step": 159
    },
    {
      "epoch": 0.0067040978798290456,
      "grad_norm": 0.7894763946533203,
      "learning_rate": 1.0542974530180327e-05,
      "loss": 0.3822,
      "step": 160
    },
    {
      "epoch": 0.006745998491577977,
      "grad_norm": 0.4261036515235901,
      "learning_rate": 1.0040600155253765e-05,
      "loss": 0.3767,
      "step": 161
    },
    {
      "epoch": 0.006787899103326909,
      "grad_norm": 0.37567344307899475,
      "learning_rate": 9.549150281252633e-06,
      "loss": 0.3727,
      "step": 162
    },
    {
      "epoch": 0.00682979971507584,
      "grad_norm": 0.37848037481307983,
      "learning_rate": 9.068759265665384e-06,
      "loss": 0.3578,
      "step": 163
    },
    {
      "epoch": 0.006871700326824772,
      "grad_norm": 0.3375943601131439,
      "learning_rate": 8.599558442598998e-06,
      "loss": 0.3659,
      "step": 164
    },
    {
      "epoch": 0.006913600938573703,
      "grad_norm": 0.3530254364013672,
      "learning_rate": 8.141676086873572e-06,
      "loss": 0.3587,
      "step": 165
    },
    {
      "epoch": 0.006955501550322635,
      "grad_norm": 0.3661386966705322,
      "learning_rate": 7.695237378953223e-06,
      "loss": 0.3707,
      "step": 166
    },
    {
      "epoch": 0.006997402162071566,
      "grad_norm": 0.3463679254055023,
      "learning_rate": 7.260364370723044e-06,
      "loss": 0.3644,
      "step": 167
    },
    {
      "epoch": 0.007039302773820498,
      "grad_norm": 0.3842766582965851,
      "learning_rate": 6.837175952121306e-06,
      "loss": 0.3617,
      "step": 168
    },
    {
      "epoch": 0.007081203385569429,
      "grad_norm": 0.44086405634880066,
      "learning_rate": 6.425787818636131e-06,
      "loss": 0.3583,
      "step": 169
    },
    {
      "epoch": 0.007123103997318361,
      "grad_norm": 0.5864846110343933,
      "learning_rate": 6.026312439675552e-06,
      "loss": 0.3706,
      "step": 170
    },
    {
      "epoch": 0.007165004609067292,
      "grad_norm": 0.3484610319137573,
      "learning_rate": 5.6388590278194096e-06,
      "loss": 0.3537,
      "step": 171
    },
    {
      "epoch": 0.007206905220816224,
      "grad_norm": 0.34717440605163574,
      "learning_rate": 5.263533508961827e-06,
      "loss": 0.3597,
      "step": 172
    },
    {
      "epoch": 0.007248805832565155,
      "grad_norm": 0.4218187630176544,
      "learning_rate": 4.900438493352055e-06,
      "loss": 0.3615,
      "step": 173
    },
    {
      "epoch": 0.007290706444314087,
      "grad_norm": 0.36104816198349,
      "learning_rate": 4.549673247541875e-06,
      "loss": 0.3697,
      "step": 174
    },
    {
      "epoch": 0.0073326070560630185,
      "grad_norm": 0.36783576011657715,
      "learning_rate": 4.2113336672471245e-06,
      "loss": 0.3634,
      "step": 175
    },
    {
      "epoch": 0.0073745076678119505,
      "grad_norm": 0.3596624433994293,
      "learning_rate": 3.885512251130763e-06,
      "loss": 0.3654,
      "step": 176
    },
    {
      "epoch": 0.007416408279560882,
      "grad_norm": 0.3116663098335266,
      "learning_rate": 3.5722980755146517e-06,
      "loss": 0.3628,
      "step": 177
    },
    {
      "epoch": 0.007458308891309813,
      "grad_norm": 0.3371797204017639,
      "learning_rate": 3.271776770026963e-06,
      "loss": 0.3681,
      "step": 178
    },
    {
      "epoch": 0.007500209503058745,
      "grad_norm": 0.374452143907547,
      "learning_rate": 2.9840304941919415e-06,
      "loss": 0.3543,
      "step": 179
    },
    {
      "epoch": 0.007542110114807676,
      "grad_norm": 0.3471692204475403,
      "learning_rate": 2.7091379149682685e-06,
      "loss": 0.3588,
      "step": 180
    },
    {
      "epoch": 0.007584010726556608,
      "grad_norm": 0.37220466136932373,
      "learning_rate": 2.4471741852423237e-06,
      "loss": 0.3689,
      "step": 181
    },
    {
      "epoch": 0.007625911338305539,
      "grad_norm": 0.39862167835235596,
      "learning_rate": 2.1982109232821178e-06,
      "loss": 0.367,
      "step": 182
    },
    {
      "epoch": 0.007667811950054471,
      "grad_norm": 0.37802115082740784,
      "learning_rate": 1.962316193157593e-06,
      "loss": 0.3578,
      "step": 183
    },
    {
      "epoch": 0.007709712561803402,
      "grad_norm": 0.3749293386936188,
      "learning_rate": 1.7395544861325718e-06,
      "loss": 0.3645,
      "step": 184
    },
    {
      "epoch": 0.007751613173552334,
      "grad_norm": 0.3764847218990326,
      "learning_rate": 1.5299867030334814e-06,
      "loss": 0.3627,
      "step": 185
    },
    {
      "epoch": 0.007793513785301265,
      "grad_norm": 0.39325788617134094,
      "learning_rate": 1.333670137599713e-06,
      "loss": 0.3637,
      "step": 186
    },
    {
      "epoch": 0.007835414397050197,
      "grad_norm": 0.41122153401374817,
      "learning_rate": 1.1506584608200367e-06,
      "loss": 0.3675,
      "step": 187
    },
    {
      "epoch": 0.00787731500879913,
      "grad_norm": 0.4208770990371704,
      "learning_rate": 9.810017062595322e-07,
      "loss": 0.3705,
      "step": 188
    },
    {
      "epoch": 0.00791921562054806,
      "grad_norm": 0.3626030683517456,
      "learning_rate": 8.247462563808817e-07,
      "loss": 0.3595,
      "step": 189
    },
    {
      "epoch": 0.007961116232296991,
      "grad_norm": 0.36591896414756775,
      "learning_rate": 6.819348298638839e-07,
      "loss": 0.3608,
      "step": 190
    },
    {
      "epoch": 0.008003016844045923,
      "grad_norm": 0.365206241607666,
      "learning_rate": 5.526064699265753e-07,
      "loss": 0.3729,
      "step": 191
    },
    {
      "epoch": 0.008044917455794855,
      "grad_norm": 0.394902765750885,
      "learning_rate": 4.367965336512403e-07,
      "loss": 0.3681,
      "step": 192
    },
    {
      "epoch": 0.008086818067543786,
      "grad_norm": 0.4147816300392151,
      "learning_rate": 3.3453668231809286e-07,
      "loss": 0.3744,
      "step": 193
    },
    {
      "epoch": 0.008128718679292718,
      "grad_norm": 0.4281652569770813,
      "learning_rate": 2.458548727494292e-07,
      "loss": 0.3683,
      "step": 194
    },
    {
      "epoch": 0.00817061929104165,
      "grad_norm": 0.4012470841407776,
      "learning_rate": 1.7077534966650766e-07,
      "loss": 0.3723,
      "step": 195
    },
    {
      "epoch": 0.008212519902790582,
      "grad_norm": 0.3961266279220581,
      "learning_rate": 1.0931863906127327e-07,
      "loss": 0.3677,
      "step": 196
    },
    {
      "epoch": 0.008254420514539512,
      "grad_norm": 0.4153655767440796,
      "learning_rate": 6.150154258476315e-08,
      "loss": 0.3827,
      "step": 197
    },
    {
      "epoch": 0.008296321126288444,
      "grad_norm": 0.4204557240009308,
      "learning_rate": 2.7337132953697554e-08,
      "loss": 0.3799,
      "step": 198
    },
    {
      "epoch": 0.008338221738037376,
      "grad_norm": 0.43716534972190857,
      "learning_rate": 6.834750376549792e-09,
      "loss": 0.3762,
      "step": 199
    },
    {
      "epoch": 0.008380122349786306,
      "grad_norm": 0.5038236975669861,
      "learning_rate": 0.0,
      "loss": 0.3883,
      "step": 200
    },
    {
      "epoch": 0.008380122349786306,
      "eval_loss": 0.3646468222141266,
      "eval_runtime": 694.3148,
      "eval_samples_per_second": 57.893,
      "eval_steps_per_second": 14.473,
      "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": 1.5476286069669888e+16,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}