{
  "best_metric": 1.3825855255126953,
  "best_model_checkpoint": "miner_id_24/checkpoint-200",
  "epoch": 0.02160818950382195,
  "eval_steps": 50,
  "global_step": 200,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.00010804094751910974,
      "grad_norm": 0.6415199041366577,
      "learning_rate": 1e-05,
      "loss": 1.5052,
      "step": 1
    },
    {
      "epoch": 0.00010804094751910974,
      "eval_loss": 1.7889565229415894,
      "eval_runtime": 537.2434,
      "eval_samples_per_second": 29.017,
      "eval_steps_per_second": 7.256,
      "step": 1
    },
    {
      "epoch": 0.00021608189503821948,
      "grad_norm": 0.8521920442581177,
      "learning_rate": 2e-05,
      "loss": 1.6454,
      "step": 2
    },
    {
      "epoch": 0.00032412284255732923,
      "grad_norm": 0.8223775029182434,
      "learning_rate": 3e-05,
      "loss": 1.5582,
      "step": 3
    },
    {
      "epoch": 0.00043216379007643895,
      "grad_norm": 0.8699358105659485,
      "learning_rate": 4e-05,
      "loss": 1.6797,
      "step": 4
    },
    {
      "epoch": 0.0005402047375955487,
      "grad_norm": 0.8815155029296875,
      "learning_rate": 5e-05,
      "loss": 1.7997,
      "step": 5
    },
    {
      "epoch": 0.0006482456851146585,
      "grad_norm": 0.8338640928268433,
      "learning_rate": 6e-05,
      "loss": 1.8765,
      "step": 6
    },
    {
      "epoch": 0.0007562866326337682,
      "grad_norm": 0.8748787641525269,
      "learning_rate": 7e-05,
      "loss": 1.8333,
      "step": 7
    },
    {
      "epoch": 0.0008643275801528779,
      "grad_norm": 0.8721147179603577,
      "learning_rate": 8e-05,
      "loss": 1.8533,
      "step": 8
    },
    {
      "epoch": 0.0009723685276719876,
      "grad_norm": 0.8479627370834351,
      "learning_rate": 9e-05,
      "loss": 1.7849,
      "step": 9
    },
    {
      "epoch": 0.0010804094751910975,
      "grad_norm": 0.8160336017608643,
      "learning_rate": 0.0001,
      "loss": 1.8225,
      "step": 10
    },
    {
      "epoch": 0.001188450422710207,
      "grad_norm": 0.8395606875419617,
      "learning_rate": 9.999316524962345e-05,
      "loss": 1.8297,
      "step": 11
    },
    {
      "epoch": 0.001296491370229317,
      "grad_norm": 0.8652035593986511,
      "learning_rate": 9.997266286704631e-05,
      "loss": 1.8271,
      "step": 12
    },
    {
      "epoch": 0.0014045323177484267,
      "grad_norm": 0.886954665184021,
      "learning_rate": 9.993849845741524e-05,
      "loss": 1.8807,
      "step": 13
    },
    {
      "epoch": 0.0015125732652675364,
      "grad_norm": 0.8809394240379333,
      "learning_rate": 9.989068136093873e-05,
      "loss": 1.693,
      "step": 14
    },
    {
      "epoch": 0.0016206142127866462,
      "grad_norm": 0.8126670122146606,
      "learning_rate": 9.98292246503335e-05,
      "loss": 1.7641,
      "step": 15
    },
    {
      "epoch": 0.0017286551603057558,
      "grad_norm": 0.7971594929695129,
      "learning_rate": 9.975414512725057e-05,
      "loss": 1.7402,
      "step": 16
    },
    {
      "epoch": 0.0018366961078248656,
      "grad_norm": 0.7426121830940247,
      "learning_rate": 9.966546331768191e-05,
      "loss": 1.8472,
      "step": 17
    },
    {
      "epoch": 0.0019447370553439753,
      "grad_norm": 0.6951826214790344,
      "learning_rate": 9.956320346634876e-05,
      "loss": 1.61,
      "step": 18
    },
    {
      "epoch": 0.002052778002863085,
      "grad_norm": 0.6750522255897522,
      "learning_rate": 9.944739353007344e-05,
      "loss": 1.6732,
      "step": 19
    },
    {
      "epoch": 0.002160818950382195,
      "grad_norm": 0.7343971729278564,
      "learning_rate": 9.931806517013612e-05,
      "loss": 1.7991,
      "step": 20
    },
    {
      "epoch": 0.0022688598979013048,
      "grad_norm": 0.776883065700531,
      "learning_rate": 9.917525374361912e-05,
      "loss": 1.7459,
      "step": 21
    },
    {
      "epoch": 0.002376900845420414,
      "grad_norm": 0.7518102526664734,
      "learning_rate": 9.901899829374047e-05,
      "loss": 1.6107,
      "step": 22
    },
    {
      "epoch": 0.002484941792939524,
      "grad_norm": 0.7257257699966431,
      "learning_rate": 9.884934153917997e-05,
      "loss": 1.4054,
      "step": 23
    },
    {
      "epoch": 0.002592982740458634,
      "grad_norm": 0.670935332775116,
      "learning_rate": 9.86663298624003e-05,
      "loss": 1.3288,
      "step": 24
    },
    {
      "epoch": 0.0027010236879777437,
      "grad_norm": 0.7361525893211365,
      "learning_rate": 9.847001329696653e-05,
      "loss": 1.5796,
      "step": 25
    },
    {
      "epoch": 0.0028090646354968535,
      "grad_norm": 0.618930995464325,
      "learning_rate": 9.826044551386744e-05,
      "loss": 1.3538,
      "step": 26
    },
    {
      "epoch": 0.002917105583015963,
      "grad_norm": 0.720412015914917,
      "learning_rate": 9.803768380684242e-05,
      "loss": 1.3964,
      "step": 27
    },
    {
      "epoch": 0.0030251465305350727,
      "grad_norm": 0.7066967487335205,
      "learning_rate": 9.780178907671789e-05,
      "loss": 1.3783,
      "step": 28
    },
    {
      "epoch": 0.0031331874780541826,
      "grad_norm": 0.6013177037239075,
      "learning_rate": 9.755282581475769e-05,
      "loss": 1.3645,
      "step": 29
    },
    {
      "epoch": 0.0032412284255732924,
      "grad_norm": 0.5303290486335754,
      "learning_rate": 9.729086208503174e-05,
      "loss": 1.3098,
      "step": 30
    },
    {
      "epoch": 0.0033492693730924022,
      "grad_norm": 0.5884146690368652,
      "learning_rate": 9.701596950580806e-05,
      "loss": 1.3078,
      "step": 31
    },
    {
      "epoch": 0.0034573103206115116,
      "grad_norm": 0.5457096099853516,
      "learning_rate": 9.672822322997305e-05,
      "loss": 1.2292,
      "step": 32
    },
    {
      "epoch": 0.0035653512681306215,
      "grad_norm": 0.511433482170105,
      "learning_rate": 9.642770192448536e-05,
      "loss": 1.2423,
      "step": 33
    },
    {
      "epoch": 0.0036733922156497313,
      "grad_norm": 0.5473808646202087,
      "learning_rate": 9.611448774886924e-05,
      "loss": 1.4144,
      "step": 34
    },
    {
      "epoch": 0.003781433163168841,
      "grad_norm": 0.5527665019035339,
      "learning_rate": 9.578866633275288e-05,
      "loss": 1.265,
      "step": 35
    },
    {
      "epoch": 0.0038894741106879505,
      "grad_norm": 0.6155807375907898,
      "learning_rate": 9.545032675245813e-05,
      "loss": 1.3821,
      "step": 36
    },
    {
      "epoch": 0.003997515058207061,
      "grad_norm": 0.5555019974708557,
      "learning_rate": 9.509956150664796e-05,
      "loss": 1.4058,
      "step": 37
    },
    {
      "epoch": 0.00410555600572617,
      "grad_norm": 0.6044601202011108,
      "learning_rate": 9.473646649103818e-05,
      "loss": 1.3862,
      "step": 38
    },
    {
      "epoch": 0.00421359695324528,
      "grad_norm": 0.5915887951850891,
      "learning_rate": 9.43611409721806e-05,
      "loss": 1.3146,
      "step": 39
    },
    {
      "epoch": 0.00432163790076439,
      "grad_norm": 0.629720151424408,
      "learning_rate": 9.397368756032445e-05,
      "loss": 1.2807,
      "step": 40
    },
    {
      "epoch": 0.004429678848283499,
      "grad_norm": 0.6004234552383423,
      "learning_rate": 9.357421218136386e-05,
      "loss": 1.4081,
      "step": 41
    },
    {
      "epoch": 0.0045377197958026095,
      "grad_norm": 0.6049290895462036,
      "learning_rate": 9.316282404787871e-05,
      "loss": 1.3027,
      "step": 42
    },
    {
      "epoch": 0.004645760743321719,
      "grad_norm": 0.5715786218643188,
      "learning_rate": 9.273963562927695e-05,
      "loss": 1.3404,
      "step": 43
    },
    {
      "epoch": 0.004753801690840828,
      "grad_norm": 0.5859559774398804,
      "learning_rate": 9.230476262104677e-05,
      "loss": 1.2835,
      "step": 44
    },
    {
      "epoch": 0.004861842638359939,
      "grad_norm": 0.5575425624847412,
      "learning_rate": 9.185832391312644e-05,
      "loss": 1.3771,
      "step": 45
    },
    {
      "epoch": 0.004969883585879048,
      "grad_norm": 0.5925589799880981,
      "learning_rate": 9.140044155740101e-05,
      "loss": 1.3302,
      "step": 46
    },
    {
      "epoch": 0.005077924533398158,
      "grad_norm": 0.5659224987030029,
      "learning_rate": 9.093124073433463e-05,
      "loss": 1.232,
      "step": 47
    },
    {
      "epoch": 0.005185965480917268,
      "grad_norm": 0.5538299083709717,
      "learning_rate": 9.045084971874738e-05,
      "loss": 1.2068,
      "step": 48
    },
    {
      "epoch": 0.005294006428436377,
      "grad_norm": 0.5453095436096191,
      "learning_rate": 8.995939984474624e-05,
      "loss": 1.1096,
      "step": 49
    },
    {
      "epoch": 0.005402047375955487,
      "grad_norm": 0.611444354057312,
      "learning_rate": 8.945702546981969e-05,
      "loss": 1.3321,
      "step": 50
    },
    {
      "epoch": 0.005402047375955487,
      "eval_loss": 1.447165608406067,
      "eval_runtime": 540.6281,
      "eval_samples_per_second": 28.835,
      "eval_steps_per_second": 7.21,
      "step": 50
    },
    {
      "epoch": 0.005510088323474597,
      "grad_norm": 0.5688340067863464,
      "learning_rate": 8.894386393810563e-05,
      "loss": 1.5719,
      "step": 51
    },
    {
      "epoch": 0.005618129270993707,
      "grad_norm": 0.5210719108581543,
      "learning_rate": 8.842005554284296e-05,
      "loss": 1.6076,
      "step": 52
    },
    {
      "epoch": 0.005726170218512816,
      "grad_norm": 0.511421263217926,
      "learning_rate": 8.788574348801675e-05,
      "loss": 1.4057,
      "step": 53
    },
    {
      "epoch": 0.005834211166031926,
      "grad_norm": 0.49161919951438904,
      "learning_rate": 8.73410738492077e-05,
      "loss": 1.4458,
      "step": 54
    },
    {
      "epoch": 0.005942252113551036,
      "grad_norm": 0.5113609433174133,
      "learning_rate": 8.678619553365659e-05,
      "loss": 1.4941,
      "step": 55
    },
    {
      "epoch": 0.0060502930610701455,
      "grad_norm": 0.5481279492378235,
      "learning_rate": 8.622126023955446e-05,
      "loss": 1.6012,
      "step": 56
    },
    {
      "epoch": 0.006158334008589256,
      "grad_norm": 0.581607460975647,
      "learning_rate": 8.564642241456986e-05,
      "loss": 1.746,
      "step": 57
    },
    {
      "epoch": 0.006266374956108365,
      "grad_norm": 0.5547131299972534,
      "learning_rate": 8.506183921362443e-05,
      "loss": 1.5946,
      "step": 58
    },
    {
      "epoch": 0.0063744159036274745,
      "grad_norm": 0.5091062784194946,
      "learning_rate": 8.44676704559283e-05,
      "loss": 1.6127,
      "step": 59
    },
    {
      "epoch": 0.006482456851146585,
      "grad_norm": 0.498210072517395,
      "learning_rate": 8.386407858128706e-05,
      "loss": 1.6903,
      "step": 60
    },
    {
      "epoch": 0.006590497798665694,
      "grad_norm": 0.5570873022079468,
      "learning_rate": 8.32512286056924e-05,
      "loss": 1.7277,
      "step": 61
    },
    {
      "epoch": 0.0066985387461848045,
      "grad_norm": 0.5334456562995911,
      "learning_rate": 8.262928807620843e-05,
      "loss": 1.6454,
      "step": 62
    },
    {
      "epoch": 0.006806579693703914,
      "grad_norm": 0.5603283047676086,
      "learning_rate": 8.199842702516583e-05,
      "loss": 1.6887,
      "step": 63
    },
    {
      "epoch": 0.006914620641223023,
      "grad_norm": 0.5815354585647583,
      "learning_rate": 8.135881792367686e-05,
      "loss": 1.6811,
      "step": 64
    },
    {
      "epoch": 0.0070226615887421335,
      "grad_norm": 0.6031367182731628,
      "learning_rate": 8.07106356344834e-05,
      "loss": 1.762,
      "step": 65
    },
    {
      "epoch": 0.007130702536261243,
      "grad_norm": 0.5612961053848267,
      "learning_rate": 8.005405736415126e-05,
      "loss": 1.4651,
      "step": 66
    },
    {
      "epoch": 0.007238743483780352,
      "grad_norm": 0.5815284848213196,
      "learning_rate": 7.938926261462366e-05,
      "loss": 1.52,
      "step": 67
    },
    {
      "epoch": 0.007346784431299463,
      "grad_norm": 0.6054347157478333,
      "learning_rate": 7.871643313414718e-05,
      "loss": 1.5381,
      "step": 68
    },
    {
      "epoch": 0.007454825378818572,
      "grad_norm": 0.6322120428085327,
      "learning_rate": 7.803575286758364e-05,
      "loss": 1.5772,
      "step": 69
    },
    {
      "epoch": 0.007562866326337682,
      "grad_norm": 0.6227050423622131,
      "learning_rate": 7.734740790612136e-05,
      "loss": 1.5912,
      "step": 70
    },
    {
      "epoch": 0.007670907273856792,
      "grad_norm": 0.6908897757530212,
      "learning_rate": 7.66515864363997e-05,
      "loss": 1.7654,
      "step": 71
    },
    {
      "epoch": 0.007778948221375901,
      "grad_norm": 0.6655283570289612,
      "learning_rate": 7.594847868906076e-05,
      "loss": 1.5201,
      "step": 72
    },
    {
      "epoch": 0.007886989168895011,
      "grad_norm": 0.623812735080719,
      "learning_rate": 7.52382768867422e-05,
      "loss": 1.3675,
      "step": 73
    },
    {
      "epoch": 0.007995030116414122,
      "grad_norm": 0.732862651348114,
      "learning_rate": 7.452117519152542e-05,
      "loss": 1.3879,
      "step": 74
    },
    {
      "epoch": 0.00810307106393323,
      "grad_norm": 0.6354972124099731,
      "learning_rate": 7.379736965185368e-05,
      "loss": 1.3212,
      "step": 75
    },
    {
      "epoch": 0.00821111201145234,
      "grad_norm": 0.6733678579330444,
      "learning_rate": 7.30670581489344e-05,
      "loss": 1.3844,
      "step": 76
    },
    {
      "epoch": 0.00831915295897145,
      "grad_norm": 0.5374462604522705,
      "learning_rate": 7.233044034264034e-05,
      "loss": 1.282,
      "step": 77
    },
    {
      "epoch": 0.00842719390649056,
      "grad_norm": 0.5634145140647888,
      "learning_rate": 7.158771761692464e-05,
      "loss": 1.3645,
      "step": 78
    },
    {
      "epoch": 0.00853523485400967,
      "grad_norm": 0.5989744663238525,
      "learning_rate": 7.083909302476453e-05,
      "loss": 1.3069,
      "step": 79
    },
    {
      "epoch": 0.00864327580152878,
      "grad_norm": 0.6431207656860352,
      "learning_rate": 7.008477123264848e-05,
      "loss": 1.4154,
      "step": 80
    },
    {
      "epoch": 0.00875131674904789,
      "grad_norm": 0.576560378074646,
      "learning_rate": 6.932495846462261e-05,
      "loss": 1.4004,
      "step": 81
    },
    {
      "epoch": 0.008859357696566999,
      "grad_norm": 0.5035609602928162,
      "learning_rate": 6.855986244591104e-05,
      "loss": 1.3765,
      "step": 82
    },
    {
      "epoch": 0.008967398644086109,
      "grad_norm": 0.5013503432273865,
      "learning_rate": 6.778969234612584e-05,
      "loss": 1.2795,
      "step": 83
    },
    {
      "epoch": 0.009075439591605219,
      "grad_norm": 0.5409559607505798,
      "learning_rate": 6.701465872208216e-05,
      "loss": 1.1887,
      "step": 84
    },
    {
      "epoch": 0.009183480539124328,
      "grad_norm": 0.5471685528755188,
      "learning_rate": 6.623497346023418e-05,
      "loss": 1.2804,
      "step": 85
    },
    {
      "epoch": 0.009291521486643438,
      "grad_norm": 0.4861477315425873,
      "learning_rate": 6.545084971874738e-05,
      "loss": 1.1793,
      "step": 86
    },
    {
      "epoch": 0.009399562434162548,
      "grad_norm": 0.5238993763923645,
      "learning_rate": 6.466250186922325e-05,
      "loss": 1.2911,
      "step": 87
    },
    {
      "epoch": 0.009507603381681657,
      "grad_norm": 0.5179485082626343,
      "learning_rate": 6.387014543809223e-05,
      "loss": 1.1557,
      "step": 88
    },
    {
      "epoch": 0.009615644329200767,
      "grad_norm": 0.4949568510055542,
      "learning_rate": 6.307399704769099e-05,
      "loss": 1.2441,
      "step": 89
    },
    {
      "epoch": 0.009723685276719877,
      "grad_norm": 0.5107378363609314,
      "learning_rate": 6.227427435703997e-05,
      "loss": 1.2139,
      "step": 90
    },
    {
      "epoch": 0.009831726224238986,
      "grad_norm": 0.5022399425506592,
      "learning_rate": 6.147119600233758e-05,
      "loss": 1.1874,
      "step": 91
    },
    {
      "epoch": 0.009939767171758096,
      "grad_norm": 0.5593945384025574,
      "learning_rate": 6.066498153718735e-05,
      "loss": 1.3381,
      "step": 92
    },
    {
      "epoch": 0.010047808119277206,
      "grad_norm": 0.4912715256214142,
      "learning_rate": 5.985585137257401e-05,
      "loss": 1.2173,
      "step": 93
    },
    {
      "epoch": 0.010155849066796317,
      "grad_norm": 0.5319995284080505,
      "learning_rate": 5.90440267166055e-05,
      "loss": 1.3107,
      "step": 94
    },
    {
      "epoch": 0.010263890014315425,
      "grad_norm": 0.5391354560852051,
      "learning_rate": 5.8229729514036705e-05,
      "loss": 1.3668,
      "step": 95
    },
    {
      "epoch": 0.010371930961834535,
      "grad_norm": 0.5007675290107727,
      "learning_rate": 5.74131823855921e-05,
      "loss": 1.1811,
      "step": 96
    },
    {
      "epoch": 0.010479971909353646,
      "grad_norm": 0.504580020904541,
      "learning_rate": 5.6594608567103456e-05,
      "loss": 1.2471,
      "step": 97
    },
    {
      "epoch": 0.010588012856872754,
      "grad_norm": 0.559918224811554,
      "learning_rate": 5.577423184847932e-05,
      "loss": 1.2678,
      "step": 98
    },
    {
      "epoch": 0.010696053804391864,
      "grad_norm": 0.5348510146141052,
      "learning_rate": 5.495227651252315e-05,
      "loss": 1.1917,
      "step": 99
    },
    {
      "epoch": 0.010804094751910975,
      "grad_norm": 0.5929791927337646,
      "learning_rate": 5.4128967273616625e-05,
      "loss": 1.1949,
      "step": 100
    },
    {
      "epoch": 0.010804094751910975,
      "eval_loss": 1.4099128246307373,
      "eval_runtime": 540.6702,
      "eval_samples_per_second": 28.833,
      "eval_steps_per_second": 7.21,
      "step": 100
    },
    {
      "epoch": 0.010912135699430083,
      "grad_norm": 0.5656149983406067,
      "learning_rate": 5.330452921628497e-05,
      "loss": 1.5696,
      "step": 101
    },
    {
      "epoch": 0.011020176646949193,
      "grad_norm": 0.49733293056488037,
      "learning_rate": 5.247918773366112e-05,
      "loss": 1.4308,
      "step": 102
    },
    {
      "epoch": 0.011128217594468304,
      "grad_norm": 0.5382848381996155,
      "learning_rate": 5.165316846586541e-05,
      "loss": 1.5589,
      "step": 103
    },
    {
      "epoch": 0.011236258541987414,
      "grad_norm": 0.5079208016395569,
      "learning_rate": 5.0826697238317935e-05,
      "loss": 1.5096,
      "step": 104
    },
    {
      "epoch": 0.011344299489506523,
      "grad_norm": 0.4609176516532898,
      "learning_rate": 5e-05,
      "loss": 1.5021,
      "step": 105
    },
    {
      "epoch": 0.011452340437025633,
      "grad_norm": 0.519070565700531,
      "learning_rate": 4.917330276168208e-05,
      "loss": 1.3619,
      "step": 106
    },
    {
      "epoch": 0.011560381384544743,
      "grad_norm": 0.5244966745376587,
      "learning_rate": 4.834683153413459e-05,
      "loss": 1.6287,
      "step": 107
    },
    {
      "epoch": 0.011668422332063852,
      "grad_norm": 0.5126777291297913,
      "learning_rate": 4.7520812266338885e-05,
      "loss": 1.4502,
      "step": 108
    },
    {
      "epoch": 0.011776463279582962,
      "grad_norm": 0.5889363288879395,
      "learning_rate": 4.669547078371504e-05,
      "loss": 1.7702,
      "step": 109
    },
    {
      "epoch": 0.011884504227102072,
      "grad_norm": 0.536626935005188,
      "learning_rate": 4.5871032726383386e-05,
      "loss": 1.4888,
      "step": 110
    },
    {
      "epoch": 0.01199254517462118,
      "grad_norm": 0.5674733519554138,
      "learning_rate": 4.504772348747687e-05,
      "loss": 1.579,
      "step": 111
    },
    {
      "epoch": 0.012100586122140291,
      "grad_norm": 0.6189550757408142,
      "learning_rate": 4.4225768151520694e-05,
      "loss": 1.617,
      "step": 112
    },
    {
      "epoch": 0.012208627069659401,
      "grad_norm": 0.5478515028953552,
      "learning_rate": 4.3405391432896555e-05,
      "loss": 1.5958,
      "step": 113
    },
    {
      "epoch": 0.012316668017178511,
      "grad_norm": 0.5639758110046387,
      "learning_rate": 4.2586817614407895e-05,
      "loss": 1.582,
      "step": 114
    },
    {
      "epoch": 0.01242470896469762,
      "grad_norm": 0.5738075971603394,
      "learning_rate": 4.17702704859633e-05,
      "loss": 1.5276,
      "step": 115
    },
    {
      "epoch": 0.01253274991221673,
      "grad_norm": 0.5698167085647583,
      "learning_rate": 4.095597328339452e-05,
      "loss": 1.6875,
      "step": 116
    },
    {
      "epoch": 0.01264079085973584,
      "grad_norm": 0.5533928871154785,
      "learning_rate": 4.0144148627425993e-05,
      "loss": 1.6031,
      "step": 117
    },
    {
      "epoch": 0.012748831807254949,
      "grad_norm": 0.5695083737373352,
      "learning_rate": 3.933501846281267e-05,
      "loss": 1.6042,
      "step": 118
    },
    {
      "epoch": 0.01285687275477406,
      "grad_norm": 0.5909783244132996,
      "learning_rate": 3.852880399766243e-05,
      "loss": 1.5882,
      "step": 119
    },
    {
      "epoch": 0.01296491370229317,
      "grad_norm": 0.604316234588623,
      "learning_rate": 3.772572564296005e-05,
      "loss": 1.5856,
      "step": 120
    },
    {
      "epoch": 0.013072954649812278,
      "grad_norm": 0.5558900237083435,
      "learning_rate": 3.6926002952309016e-05,
      "loss": 1.4502,
      "step": 121
    },
    {
      "epoch": 0.013180995597331388,
      "grad_norm": 0.6198839545249939,
      "learning_rate": 3.612985456190778e-05,
      "loss": 1.395,
      "step": 122
    },
    {
      "epoch": 0.013289036544850499,
      "grad_norm": 0.7289469838142395,
      "learning_rate": 3.533749813077677e-05,
      "loss": 1.5156,
      "step": 123
    },
    {
      "epoch": 0.013397077492369609,
      "grad_norm": 0.5558703541755676,
      "learning_rate": 3.4549150281252636e-05,
      "loss": 1.4275,
      "step": 124
    },
    {
      "epoch": 0.013505118439888717,
      "grad_norm": 0.5798810124397278,
      "learning_rate": 3.3765026539765834e-05,
      "loss": 1.3125,
      "step": 125
    },
    {
      "epoch": 0.013613159387407828,
      "grad_norm": 0.5648987293243408,
      "learning_rate": 3.298534127791785e-05,
      "loss": 1.341,
      "step": 126
    },
    {
      "epoch": 0.013721200334926938,
      "grad_norm": 0.5494349598884583,
      "learning_rate": 3.221030765387417e-05,
      "loss": 1.321,
      "step": 127
    },
    {
      "epoch": 0.013829241282446047,
      "grad_norm": 0.5381960868835449,
      "learning_rate": 3.144013755408895e-05,
      "loss": 1.3856,
      "step": 128
    },
    {
      "epoch": 0.013937282229965157,
      "grad_norm": 0.5390709638595581,
      "learning_rate": 3.0675041535377405e-05,
      "loss": 1.3397,
      "step": 129
    },
    {
      "epoch": 0.014045323177484267,
      "grad_norm": 0.51526939868927,
      "learning_rate": 2.991522876735154e-05,
      "loss": 1.3445,
      "step": 130
    },
    {
      "epoch": 0.014153364125003376,
      "grad_norm": 0.5244969725608826,
      "learning_rate": 2.916090697523549e-05,
      "loss": 1.3052,
      "step": 131
    },
    {
      "epoch": 0.014261405072522486,
      "grad_norm": 0.47933128476142883,
      "learning_rate": 2.8412282383075363e-05,
      "loss": 1.192,
      "step": 132
    },
    {
      "epoch": 0.014369446020041596,
      "grad_norm": 0.4810992479324341,
      "learning_rate": 2.766955965735968e-05,
      "loss": 1.2083,
      "step": 133
    },
    {
      "epoch": 0.014477486967560705,
      "grad_norm": 0.5163156986236572,
      "learning_rate": 2.693294185106562e-05,
      "loss": 1.3219,
      "step": 134
    },
    {
      "epoch": 0.014585527915079815,
      "grad_norm": 0.5238019824028015,
      "learning_rate": 2.6202630348146324e-05,
      "loss": 1.2748,
      "step": 135
    },
    {
      "epoch": 0.014693568862598925,
      "grad_norm": 0.5952757596969604,
      "learning_rate": 2.547882480847461e-05,
      "loss": 1.2459,
      "step": 136
    },
    {
      "epoch": 0.014801609810118035,
      "grad_norm": 0.5043328404426575,
      "learning_rate": 2.476172311325783e-05,
      "loss": 1.1788,
      "step": 137
    },
    {
      "epoch": 0.014909650757637144,
      "grad_norm": 0.5275827050209045,
      "learning_rate": 2.405152131093926e-05,
      "loss": 1.2503,
      "step": 138
    },
    {
      "epoch": 0.015017691705156254,
      "grad_norm": 0.5203622579574585,
      "learning_rate": 2.3348413563600325e-05,
      "loss": 1.2131,
      "step": 139
    },
    {
      "epoch": 0.015125732652675365,
      "grad_norm": 0.6354079842567444,
      "learning_rate": 2.2652592093878666e-05,
      "loss": 1.3439,
      "step": 140
    },
    {
      "epoch": 0.015233773600194473,
      "grad_norm": 0.52004075050354,
      "learning_rate": 2.196424713241637e-05,
      "loss": 1.245,
      "step": 141
    },
    {
      "epoch": 0.015341814547713583,
      "grad_norm": 0.5602080225944519,
      "learning_rate": 2.128356686585282e-05,
      "loss": 1.2635,
      "step": 142
    },
    {
      "epoch": 0.015449855495232694,
      "grad_norm": 0.5309022068977356,
      "learning_rate": 2.061073738537635e-05,
      "loss": 1.1048,
      "step": 143
    },
    {
      "epoch": 0.015557896442751802,
      "grad_norm": 0.5232879519462585,
      "learning_rate": 1.9945942635848748e-05,
      "loss": 1.2626,
      "step": 144
    },
    {
      "epoch": 0.015665937390270914,
      "grad_norm": 0.5605840682983398,
      "learning_rate": 1.928936436551661e-05,
      "loss": 1.2634,
      "step": 145
    },
    {
      "epoch": 0.015773978337790023,
      "grad_norm": 0.570547878742218,
      "learning_rate": 1.8641182076323148e-05,
      "loss": 1.2459,
      "step": 146
    },
    {
      "epoch": 0.01588201928530913,
      "grad_norm": 0.489162415266037,
      "learning_rate": 1.800157297483417e-05,
      "loss": 1.108,
      "step": 147
    },
    {
      "epoch": 0.015990060232828243,
      "grad_norm": 0.5336431264877319,
      "learning_rate": 1.7370711923791567e-05,
      "loss": 1.1773,
      "step": 148
    },
    {
      "epoch": 0.01609810118034735,
      "grad_norm": 0.5383755564689636,
      "learning_rate": 1.6748771394307585e-05,
      "loss": 1.0803,
      "step": 149
    },
    {
      "epoch": 0.01620614212786646,
      "grad_norm": 0.6291366219520569,
      "learning_rate": 1.6135921418712956e-05,
      "loss": 1.2595,
      "step": 150
    },
    {
      "epoch": 0.01620614212786646,
      "eval_loss": 1.3889561891555786,
      "eval_runtime": 540.8179,
      "eval_samples_per_second": 28.825,
      "eval_steps_per_second": 7.208,
      "step": 150
    },
    {
      "epoch": 0.016314183075385572,
      "grad_norm": 0.6279352903366089,
      "learning_rate": 1.553232954407171e-05,
      "loss": 1.6062,
      "step": 151
    },
    {
      "epoch": 0.01642222402290468,
      "grad_norm": 0.5585036873817444,
      "learning_rate": 1.4938160786375572e-05,
      "loss": 1.4728,
      "step": 152
    },
    {
      "epoch": 0.01653026497042379,
      "grad_norm": 0.5232642889022827,
      "learning_rate": 1.435357758543015e-05,
      "loss": 1.4732,
      "step": 153
    },
    {
      "epoch": 0.0166383059179429,
      "grad_norm": 0.48461011052131653,
      "learning_rate": 1.3778739760445552e-05,
      "loss": 1.4053,
      "step": 154
    },
    {
      "epoch": 0.01674634686546201,
      "grad_norm": 0.5245410203933716,
      "learning_rate": 1.3213804466343421e-05,
      "loss": 1.5156,
      "step": 155
    },
    {
      "epoch": 0.01685438781298112,
      "grad_norm": 0.5326631665229797,
      "learning_rate": 1.2658926150792322e-05,
      "loss": 1.5703,
      "step": 156
    },
    {
      "epoch": 0.01696242876050023,
      "grad_norm": 0.5400073528289795,
      "learning_rate": 1.2114256511983274e-05,
      "loss": 1.5237,
      "step": 157
    },
    {
      "epoch": 0.01707046970801934,
      "grad_norm": 0.5429589748382568,
      "learning_rate": 1.157994445715706e-05,
      "loss": 1.5572,
      "step": 158
    },
    {
      "epoch": 0.017178510655538447,
      "grad_norm": 0.5342143177986145,
      "learning_rate": 1.1056136061894384e-05,
      "loss": 1.6343,
      "step": 159
    },
    {
      "epoch": 0.01728655160305756,
      "grad_norm": 0.627686619758606,
      "learning_rate": 1.0542974530180327e-05,
      "loss": 1.6671,
      "step": 160
    },
    {
      "epoch": 0.017394592550576668,
      "grad_norm": 0.566863477230072,
      "learning_rate": 1.0040600155253765e-05,
      "loss": 1.5729,
      "step": 161
    },
    {
      "epoch": 0.01750263349809578,
      "grad_norm": 0.587979793548584,
      "learning_rate": 9.549150281252633e-06,
      "loss": 1.4455,
      "step": 162
    },
    {
      "epoch": 0.01761067444561489,
      "grad_norm": 0.5256617069244385,
      "learning_rate": 9.068759265665384e-06,
      "loss": 1.4453,
      "step": 163
    },
    {
      "epoch": 0.017718715393133997,
      "grad_norm": 0.6064791679382324,
      "learning_rate": 8.599558442598998e-06,
      "loss": 1.6278,
      "step": 164
    },
    {
      "epoch": 0.01782675634065311,
      "grad_norm": 0.5769029855728149,
      "learning_rate": 8.141676086873572e-06,
      "loss": 1.6778,
      "step": 165
    },
    {
      "epoch": 0.017934797288172218,
      "grad_norm": 0.624455451965332,
      "learning_rate": 7.695237378953223e-06,
      "loss": 1.5823,
      "step": 166
    },
    {
      "epoch": 0.018042838235691326,
      "grad_norm": 0.6557711958885193,
      "learning_rate": 7.260364370723044e-06,
      "loss": 1.7149,
      "step": 167
    },
    {
      "epoch": 0.018150879183210438,
      "grad_norm": 0.6654251217842102,
      "learning_rate": 6.837175952121306e-06,
      "loss": 1.6441,
      "step": 168
    },
    {
      "epoch": 0.018258920130729547,
      "grad_norm": 0.6032689213752747,
      "learning_rate": 6.425787818636131e-06,
      "loss": 1.5394,
      "step": 169
    },
    {
      "epoch": 0.018366961078248655,
      "grad_norm": 0.7282447814941406,
      "learning_rate": 6.026312439675552e-06,
      "loss": 1.6469,
      "step": 170
    },
    {
      "epoch": 0.018475002025767767,
      "grad_norm": 0.6971535682678223,
      "learning_rate": 5.6388590278194096e-06,
      "loss": 1.5682,
      "step": 171
    },
    {
      "epoch": 0.018583042973286876,
      "grad_norm": 0.6798433065414429,
      "learning_rate": 5.263533508961827e-06,
      "loss": 1.5807,
      "step": 172
    },
    {
      "epoch": 0.018691083920805984,
      "grad_norm": 0.5623297691345215,
      "learning_rate": 4.900438493352055e-06,
      "loss": 1.4366,
      "step": 173
    },
    {
      "epoch": 0.018799124868325096,
      "grad_norm": 0.5957369208335876,
      "learning_rate": 4.549673247541875e-06,
      "loss": 1.4116,
      "step": 174
    },
    {
      "epoch": 0.018907165815844205,
      "grad_norm": 0.5290876030921936,
      "learning_rate": 4.2113336672471245e-06,
      "loss": 1.3933,
      "step": 175
    },
    {
      "epoch": 0.019015206763363313,
      "grad_norm": 0.4679022431373596,
      "learning_rate": 3.885512251130763e-06,
      "loss": 1.2569,
      "step": 176
    },
    {
      "epoch": 0.019123247710882425,
      "grad_norm": 0.44044697284698486,
      "learning_rate": 3.5722980755146517e-06,
      "loss": 1.0855,
      "step": 177
    },
    {
      "epoch": 0.019231288658401534,
      "grad_norm": 0.480378121137619,
      "learning_rate": 3.271776770026963e-06,
      "loss": 1.2141,
      "step": 178
    },
    {
      "epoch": 0.019339329605920642,
      "grad_norm": 0.446628600358963,
      "learning_rate": 2.9840304941919415e-06,
      "loss": 1.1291,
      "step": 179
    },
    {
      "epoch": 0.019447370553439754,
      "grad_norm": 0.5069640278816223,
      "learning_rate": 2.7091379149682685e-06,
      "loss": 1.3104,
      "step": 180
    },
    {
      "epoch": 0.019555411500958863,
      "grad_norm": 0.48359909653663635,
      "learning_rate": 2.4471741852423237e-06,
      "loss": 1.1975,
      "step": 181
    },
    {
      "epoch": 0.01966345244847797,
      "grad_norm": 0.5178685784339905,
      "learning_rate": 2.1982109232821178e-06,
      "loss": 1.3529,
      "step": 182
    },
    {
      "epoch": 0.019771493395997083,
      "grad_norm": 0.47977468371391296,
      "learning_rate": 1.962316193157593e-06,
      "loss": 1.1846,
      "step": 183
    },
    {
      "epoch": 0.019879534343516192,
      "grad_norm": 0.5151256322860718,
      "learning_rate": 1.7395544861325718e-06,
      "loss": 1.3717,
      "step": 184
    },
    {
      "epoch": 0.019987575291035304,
      "grad_norm": 0.5376985669136047,
      "learning_rate": 1.5299867030334814e-06,
      "loss": 1.3392,
      "step": 185
    },
    {
      "epoch": 0.020095616238554413,
      "grad_norm": 0.5357360243797302,
      "learning_rate": 1.333670137599713e-06,
      "loss": 1.3287,
      "step": 186
    },
    {
      "epoch": 0.02020365718607352,
      "grad_norm": 0.47518178820610046,
      "learning_rate": 1.1506584608200367e-06,
      "loss": 1.2227,
      "step": 187
    },
    {
      "epoch": 0.020311698133592633,
      "grad_norm": 0.5164097547531128,
      "learning_rate": 9.810017062595322e-07,
      "loss": 1.2823,
      "step": 188
    },
    {
      "epoch": 0.02041973908111174,
      "grad_norm": 0.5112942457199097,
      "learning_rate": 8.247462563808817e-07,
      "loss": 1.279,
      "step": 189
    },
    {
      "epoch": 0.02052778002863085,
      "grad_norm": 0.5349648594856262,
      "learning_rate": 6.819348298638839e-07,
      "loss": 1.3044,
      "step": 190
    },
    {
      "epoch": 0.020635820976149962,
      "grad_norm": 0.5205196142196655,
      "learning_rate": 5.526064699265753e-07,
      "loss": 1.3626,
      "step": 191
    },
    {
      "epoch": 0.02074386192366907,
      "grad_norm": 0.4847419559955597,
      "learning_rate": 4.367965336512403e-07,
      "loss": 1.2482,
      "step": 192
    },
    {
      "epoch": 0.02085190287118818,
      "grad_norm": 0.5579021573066711,
      "learning_rate": 3.3453668231809286e-07,
      "loss": 1.3529,
      "step": 193
    },
    {
      "epoch": 0.02095994381870729,
      "grad_norm": 0.501562237739563,
      "learning_rate": 2.458548727494292e-07,
      "loss": 1.1616,
      "step": 194
    },
    {
      "epoch": 0.0210679847662264,
      "grad_norm": 0.5366082787513733,
      "learning_rate": 1.7077534966650766e-07,
      "loss": 1.2078,
      "step": 195
    },
    {
      "epoch": 0.021176025713745508,
      "grad_norm": 0.5153544545173645,
      "learning_rate": 1.0931863906127327e-07,
      "loss": 1.2226,
      "step": 196
    },
    {
      "epoch": 0.02128406666126462,
      "grad_norm": 0.5714104175567627,
      "learning_rate": 6.150154258476315e-08,
      "loss": 1.282,
      "step": 197
    },
    {
      "epoch": 0.02139210760878373,
      "grad_norm": 0.5491760969161987,
      "learning_rate": 2.7337132953697554e-08,
      "loss": 1.3005,
      "step": 198
    },
    {
      "epoch": 0.021500148556302837,
      "grad_norm": 0.5525445342063904,
      "learning_rate": 6.834750376549792e-09,
      "loss": 1.2546,
      "step": 199
    },
    {
      "epoch": 0.02160818950382195,
      "grad_norm": 0.5474685430526733,
      "learning_rate": 0.0,
      "loss": 1.2259,
      "step": 200
    },
    {
      "epoch": 0.02160818950382195,
      "eval_loss": 1.3825855255126953,
      "eval_runtime": 540.8239,
      "eval_samples_per_second": 28.825,
      "eval_steps_per_second": 7.208,
      "step": 200
    }
  ],
  "logging_steps": 1,
  "max_steps": 200,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 50,
  "stateful_callbacks": {
    "EarlyStoppingCallback": {
      "args": {
        "early_stopping_patience": 5,
        "early_stopping_threshold": 0.0
      },
      "attributes": {
        "early_stopping_patience_counter": 0
      }
    },
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 7.8039887118336e+16,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}