{
  "best_metric": 1.5952566862106323,
  "best_model_checkpoint": "miner_id_24/checkpoint-200",
  "epoch": 0.19627085377821393,
  "eval_steps": 50,
  "global_step": 200,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0009813542688910696,
      "grad_norm": 1.546113133430481,
      "learning_rate": 1e-05,
      "loss": 2.5285,
      "step": 1
    },
    {
      "epoch": 0.0009813542688910696,
      "eval_loss": 4.116623401641846,
      "eval_runtime": 123.9075,
      "eval_samples_per_second": 13.849,
      "eval_steps_per_second": 3.462,
      "step": 1
    },
    {
      "epoch": 0.001962708537782139,
      "grad_norm": 0.9781582951545715,
      "learning_rate": 2e-05,
      "loss": 3.5733,
      "step": 2
    },
    {
      "epoch": 0.002944062806673209,
      "grad_norm": 0.7824115753173828,
      "learning_rate": 3e-05,
      "loss": 3.4788,
      "step": 3
    },
    {
      "epoch": 0.003925417075564278,
      "grad_norm": 0.7483214139938354,
      "learning_rate": 4e-05,
      "loss": 3.4776,
      "step": 4
    },
    {
      "epoch": 0.004906771344455349,
      "grad_norm": 0.8340680003166199,
      "learning_rate": 5e-05,
      "loss": 3.5792,
      "step": 5
    },
    {
      "epoch": 0.005888125613346418,
      "grad_norm": 0.8057698607444763,
      "learning_rate": 6e-05,
      "loss": 3.2183,
      "step": 6
    },
    {
      "epoch": 0.0068694798822374874,
      "grad_norm": 0.7268650531768799,
      "learning_rate": 7e-05,
      "loss": 3.4514,
      "step": 7
    },
    {
      "epoch": 0.007850834151128557,
      "grad_norm": 0.6580367684364319,
      "learning_rate": 8e-05,
      "loss": 3.3637,
      "step": 8
    },
    {
      "epoch": 0.008832188420019628,
      "grad_norm": 0.7277189493179321,
      "learning_rate": 9e-05,
      "loss": 3.6629,
      "step": 9
    },
    {
      "epoch": 0.009813542688910697,
      "grad_norm": 0.7673052549362183,
      "learning_rate": 0.0001,
      "loss": 3.2481,
      "step": 10
    },
    {
      "epoch": 0.010794896957801767,
      "grad_norm": 0.8904625773429871,
      "learning_rate": 9.999316524962345e-05,
      "loss": 3.0924,
      "step": 11
    },
    {
      "epoch": 0.011776251226692836,
      "grad_norm": 1.102980613708496,
      "learning_rate": 9.997266286704631e-05,
      "loss": 3.2389,
      "step": 12
    },
    {
      "epoch": 0.012757605495583905,
      "grad_norm": 1.2999459505081177,
      "learning_rate": 9.993849845741524e-05,
      "loss": 3.3008,
      "step": 13
    },
    {
      "epoch": 0.013738959764474975,
      "grad_norm": 1.367265224456787,
      "learning_rate": 9.989068136093873e-05,
      "loss": 3.3073,
      "step": 14
    },
    {
      "epoch": 0.014720314033366046,
      "grad_norm": 1.1843202114105225,
      "learning_rate": 9.98292246503335e-05,
      "loss": 2.6763,
      "step": 15
    },
    {
      "epoch": 0.015701668302257114,
      "grad_norm": 1.428940773010254,
      "learning_rate": 9.975414512725057e-05,
      "loss": 3.1981,
      "step": 16
    },
    {
      "epoch": 0.016683022571148183,
      "grad_norm": 1.3143913745880127,
      "learning_rate": 9.966546331768191e-05,
      "loss": 2.8286,
      "step": 17
    },
    {
      "epoch": 0.017664376840039256,
      "grad_norm": 1.1334483623504639,
      "learning_rate": 9.956320346634876e-05,
      "loss": 2.9316,
      "step": 18
    },
    {
      "epoch": 0.018645731108930325,
      "grad_norm": 1.4827356338500977,
      "learning_rate": 9.944739353007344e-05,
      "loss": 3.1141,
      "step": 19
    },
    {
      "epoch": 0.019627085377821395,
      "grad_norm": 1.2810909748077393,
      "learning_rate": 9.931806517013612e-05,
      "loss": 2.8626,
      "step": 20
    },
    {
      "epoch": 0.020608439646712464,
      "grad_norm": 1.276486873626709,
      "learning_rate": 9.917525374361912e-05,
      "loss": 2.7303,
      "step": 21
    },
    {
      "epoch": 0.021589793915603533,
      "grad_norm": 1.3323583602905273,
      "learning_rate": 9.901899829374047e-05,
      "loss": 2.8712,
      "step": 22
    },
    {
      "epoch": 0.022571148184494603,
      "grad_norm": 1.0349979400634766,
      "learning_rate": 9.884934153917997e-05,
      "loss": 2.6555,
      "step": 23
    },
    {
      "epoch": 0.023552502453385672,
      "grad_norm": 1.224134922027588,
      "learning_rate": 9.86663298624003e-05,
      "loss": 2.7481,
      "step": 24
    },
    {
      "epoch": 0.02453385672227674,
      "grad_norm": 1.3956490755081177,
      "learning_rate": 9.847001329696653e-05,
      "loss": 2.432,
      "step": 25
    },
    {
      "epoch": 0.02551521099116781,
      "grad_norm": 1.542784571647644,
      "learning_rate": 9.826044551386744e-05,
      "loss": 2.6201,
      "step": 26
    },
    {
      "epoch": 0.02649656526005888,
      "grad_norm": 1.3909921646118164,
      "learning_rate": 9.803768380684242e-05,
      "loss": 2.8418,
      "step": 27
    },
    {
      "epoch": 0.02747791952894995,
      "grad_norm": 1.4771311283111572,
      "learning_rate": 9.780178907671789e-05,
      "loss": 2.4117,
      "step": 28
    },
    {
      "epoch": 0.02845927379784102,
      "grad_norm": 1.2797276973724365,
      "learning_rate": 9.755282581475769e-05,
      "loss": 2.5078,
      "step": 29
    },
    {
      "epoch": 0.029440628066732092,
      "grad_norm": 1.337188720703125,
      "learning_rate": 9.729086208503174e-05,
      "loss": 2.579,
      "step": 30
    },
    {
      "epoch": 0.03042198233562316,
      "grad_norm": 1.548021912574768,
      "learning_rate": 9.701596950580806e-05,
      "loss": 2.5096,
      "step": 31
    },
    {
      "epoch": 0.03140333660451423,
      "grad_norm": 1.535007357597351,
      "learning_rate": 9.672822322997305e-05,
      "loss": 2.3247,
      "step": 32
    },
    {
      "epoch": 0.0323846908734053,
      "grad_norm": 1.5082093477249146,
      "learning_rate": 9.642770192448536e-05,
      "loss": 2.4694,
      "step": 33
    },
    {
      "epoch": 0.033366045142296366,
      "grad_norm": 1.3266172409057617,
      "learning_rate": 9.611448774886924e-05,
      "loss": 2.3672,
      "step": 34
    },
    {
      "epoch": 0.03434739941118744,
      "grad_norm": 1.584723949432373,
      "learning_rate": 9.578866633275288e-05,
      "loss": 2.1237,
      "step": 35
    },
    {
      "epoch": 0.03532875368007851,
      "grad_norm": 1.589551329612732,
      "learning_rate": 9.545032675245813e-05,
      "loss": 2.3828,
      "step": 36
    },
    {
      "epoch": 0.03631010794896958,
      "grad_norm": 2.0490105152130127,
      "learning_rate": 9.509956150664796e-05,
      "loss": 2.3846,
      "step": 37
    },
    {
      "epoch": 0.03729146221786065,
      "grad_norm": 2.1672327518463135,
      "learning_rate": 9.473646649103818e-05,
      "loss": 2.5246,
      "step": 38
    },
    {
      "epoch": 0.038272816486751716,
      "grad_norm": 1.6294152736663818,
      "learning_rate": 9.43611409721806e-05,
      "loss": 2.2541,
      "step": 39
    },
    {
      "epoch": 0.03925417075564279,
      "grad_norm": 2.5821709632873535,
      "learning_rate": 9.397368756032445e-05,
      "loss": 2.4122,
      "step": 40
    },
    {
      "epoch": 0.040235525024533855,
      "grad_norm": 2.182114362716675,
      "learning_rate": 9.357421218136386e-05,
      "loss": 2.6733,
      "step": 41
    },
    {
      "epoch": 0.04121687929342493,
      "grad_norm": 2.807626962661743,
      "learning_rate": 9.316282404787871e-05,
      "loss": 2.9761,
      "step": 42
    },
    {
      "epoch": 0.042198233562315994,
      "grad_norm": 5.441572666168213,
      "learning_rate": 9.273963562927695e-05,
      "loss": 2.8915,
      "step": 43
    },
    {
      "epoch": 0.04317958783120707,
      "grad_norm": 4.535706520080566,
      "learning_rate": 9.230476262104677e-05,
      "loss": 3.1256,
      "step": 44
    },
    {
      "epoch": 0.04416094210009813,
      "grad_norm": 3.6611711978912354,
      "learning_rate": 9.185832391312644e-05,
      "loss": 3.6394,
      "step": 45
    },
    {
      "epoch": 0.045142296368989206,
      "grad_norm": 4.499100208282471,
      "learning_rate": 9.140044155740101e-05,
      "loss": 3.3638,
      "step": 46
    },
    {
      "epoch": 0.04612365063788027,
      "grad_norm": 5.103353023529053,
      "learning_rate": 9.093124073433463e-05,
      "loss": 3.2527,
      "step": 47
    },
    {
      "epoch": 0.047105004906771344,
      "grad_norm": 6.462408542633057,
      "learning_rate": 9.045084971874738e-05,
      "loss": 3.0869,
      "step": 48
    },
    {
      "epoch": 0.04808635917566242,
      "grad_norm": 10.468620300292969,
      "learning_rate": 8.995939984474624e-05,
      "loss": 3.9519,
      "step": 49
    },
    {
      "epoch": 0.04906771344455348,
      "grad_norm": 10.87414264678955,
      "learning_rate": 8.945702546981969e-05,
      "loss": 4.0492,
      "step": 50
    },
    {
      "epoch": 0.04906771344455348,
      "eval_loss": 2.413959264755249,
      "eval_runtime": 125.2831,
      "eval_samples_per_second": 13.697,
      "eval_steps_per_second": 3.424,
      "step": 50
    },
    {
      "epoch": 0.050049067713444556,
      "grad_norm": 2.6405813694000244,
      "learning_rate": 8.894386393810563e-05,
      "loss": 1.6079,
      "step": 51
    },
    {
      "epoch": 0.05103042198233562,
      "grad_norm": 4.144077301025391,
      "learning_rate": 8.842005554284296e-05,
      "loss": 2.6192,
      "step": 52
    },
    {
      "epoch": 0.052011776251226695,
      "grad_norm": 2.4645867347717285,
      "learning_rate": 8.788574348801675e-05,
      "loss": 2.3886,
      "step": 53
    },
    {
      "epoch": 0.05299313052011776,
      "grad_norm": 2.954893112182617,
      "learning_rate": 8.73410738492077e-05,
      "loss": 2.2645,
      "step": 54
    },
    {
      "epoch": 0.053974484789008834,
      "grad_norm": 2.670161724090576,
      "learning_rate": 8.678619553365659e-05,
      "loss": 2.1464,
      "step": 55
    },
    {
      "epoch": 0.0549558390578999,
      "grad_norm": 1.9667296409606934,
      "learning_rate": 8.622126023955446e-05,
      "loss": 2.1089,
      "step": 56
    },
    {
      "epoch": 0.05593719332679097,
      "grad_norm": 1.3890385627746582,
      "learning_rate": 8.564642241456986e-05,
      "loss": 2.2497,
      "step": 57
    },
    {
      "epoch": 0.05691854759568204,
      "grad_norm": 1.8218597173690796,
      "learning_rate": 8.506183921362443e-05,
      "loss": 2.0819,
      "step": 58
    },
    {
      "epoch": 0.05789990186457311,
      "grad_norm": 1.4386028051376343,
      "learning_rate": 8.44676704559283e-05,
      "loss": 2.0864,
      "step": 59
    },
    {
      "epoch": 0.058881256133464184,
      "grad_norm": 1.1889140605926514,
      "learning_rate": 8.386407858128706e-05,
      "loss": 2.006,
      "step": 60
    },
    {
      "epoch": 0.05986261040235525,
      "grad_norm": 1.6814196109771729,
      "learning_rate": 8.32512286056924e-05,
      "loss": 2.3159,
      "step": 61
    },
    {
      "epoch": 0.06084396467124632,
      "grad_norm": 1.1525319814682007,
      "learning_rate": 8.262928807620843e-05,
      "loss": 2.0515,
      "step": 62
    },
    {
      "epoch": 0.06182531894013739,
      "grad_norm": 1.1632955074310303,
      "learning_rate": 8.199842702516583e-05,
      "loss": 2.0899,
      "step": 63
    },
    {
      "epoch": 0.06280667320902845,
      "grad_norm": 1.31984543800354,
      "learning_rate": 8.135881792367686e-05,
      "loss": 1.7192,
      "step": 64
    },
    {
      "epoch": 0.06378802747791953,
      "grad_norm": 1.2690753936767578,
      "learning_rate": 8.07106356344834e-05,
      "loss": 2.033,
      "step": 65
    },
    {
      "epoch": 0.0647693817468106,
      "grad_norm": 1.1561932563781738,
      "learning_rate": 8.005405736415126e-05,
      "loss": 2.0399,
      "step": 66
    },
    {
      "epoch": 0.06575073601570167,
      "grad_norm": 1.1579644680023193,
      "learning_rate": 7.938926261462366e-05,
      "loss": 2.1031,
      "step": 67
    },
    {
      "epoch": 0.06673209028459273,
      "grad_norm": 1.1684629917144775,
      "learning_rate": 7.871643313414718e-05,
      "loss": 1.9643,
      "step": 68
    },
    {
      "epoch": 0.06771344455348381,
      "grad_norm": 1.0963152647018433,
      "learning_rate": 7.803575286758364e-05,
      "loss": 2.0383,
      "step": 69
    },
    {
      "epoch": 0.06869479882237488,
      "grad_norm": 1.074663519859314,
      "learning_rate": 7.734740790612136e-05,
      "loss": 1.8781,
      "step": 70
    },
    {
      "epoch": 0.06967615309126594,
      "grad_norm": 1.2264729738235474,
      "learning_rate": 7.66515864363997e-05,
      "loss": 2.0301,
      "step": 71
    },
    {
      "epoch": 0.07065750736015702,
      "grad_norm": 1.2751593589782715,
      "learning_rate": 7.594847868906076e-05,
      "loss": 2.106,
      "step": 72
    },
    {
      "epoch": 0.07163886162904809,
      "grad_norm": 1.2248733043670654,
      "learning_rate": 7.52382768867422e-05,
      "loss": 2.081,
      "step": 73
    },
    {
      "epoch": 0.07262021589793916,
      "grad_norm": 1.2606966495513916,
      "learning_rate": 7.452117519152542e-05,
      "loss": 2.0002,
      "step": 74
    },
    {
      "epoch": 0.07360157016683022,
      "grad_norm": 1.2409543991088867,
      "learning_rate": 7.379736965185368e-05,
      "loss": 1.7935,
      "step": 75
    },
    {
      "epoch": 0.0745829244357213,
      "grad_norm": 1.2148642539978027,
      "learning_rate": 7.30670581489344e-05,
      "loss": 1.992,
      "step": 76
    },
    {
      "epoch": 0.07556427870461237,
      "grad_norm": 1.1542283296585083,
      "learning_rate": 7.233044034264034e-05,
      "loss": 2.0292,
      "step": 77
    },
    {
      "epoch": 0.07654563297350343,
      "grad_norm": 1.1644940376281738,
      "learning_rate": 7.158771761692464e-05,
      "loss": 1.7538,
      "step": 78
    },
    {
      "epoch": 0.0775269872423945,
      "grad_norm": 1.76322340965271,
      "learning_rate": 7.083909302476453e-05,
      "loss": 2.0472,
      "step": 79
    },
    {
      "epoch": 0.07850834151128558,
      "grad_norm": 1.1627639532089233,
      "learning_rate": 7.008477123264848e-05,
      "loss": 1.8383,
      "step": 80
    },
    {
      "epoch": 0.07948969578017664,
      "grad_norm": 1.3644332885742188,
      "learning_rate": 6.932495846462261e-05,
      "loss": 1.6297,
      "step": 81
    },
    {
      "epoch": 0.08047105004906771,
      "grad_norm": 1.8236889839172363,
      "learning_rate": 6.855986244591104e-05,
      "loss": 2.1794,
      "step": 82
    },
    {
      "epoch": 0.08145240431795878,
      "grad_norm": 1.5599297285079956,
      "learning_rate": 6.778969234612584e-05,
      "loss": 1.8115,
      "step": 83
    },
    {
      "epoch": 0.08243375858684986,
      "grad_norm": 1.5765913724899292,
      "learning_rate": 6.701465872208216e-05,
      "loss": 1.8358,
      "step": 84
    },
    {
      "epoch": 0.08341511285574092,
      "grad_norm": 1.516957402229309,
      "learning_rate": 6.623497346023418e-05,
      "loss": 1.6606,
      "step": 85
    },
    {
      "epoch": 0.08439646712463199,
      "grad_norm": 1.713661789894104,
      "learning_rate": 6.545084971874738e-05,
      "loss": 1.5828,
      "step": 86
    },
    {
      "epoch": 0.08537782139352307,
      "grad_norm": 1.7577728033065796,
      "learning_rate": 6.466250186922325e-05,
      "loss": 2.1284,
      "step": 87
    },
    {
      "epoch": 0.08635917566241413,
      "grad_norm": 1.7137880325317383,
      "learning_rate": 6.387014543809223e-05,
      "loss": 1.8194,
      "step": 88
    },
    {
      "epoch": 0.0873405299313052,
      "grad_norm": 1.77389395236969,
      "learning_rate": 6.307399704769099e-05,
      "loss": 1.467,
      "step": 89
    },
    {
      "epoch": 0.08832188420019627,
      "grad_norm": 2.0468060970306396,
      "learning_rate": 6.227427435703997e-05,
      "loss": 1.8765,
      "step": 90
    },
    {
      "epoch": 0.08930323846908735,
      "grad_norm": 2.220963716506958,
      "learning_rate": 6.147119600233758e-05,
      "loss": 1.8327,
      "step": 91
    },
    {
      "epoch": 0.09028459273797841,
      "grad_norm": 2.4728939533233643,
      "learning_rate": 6.066498153718735e-05,
      "loss": 2.1738,
      "step": 92
    },
    {
      "epoch": 0.09126594700686948,
      "grad_norm": 3.722900867462158,
      "learning_rate": 5.985585137257401e-05,
      "loss": 2.6764,
      "step": 93
    },
    {
      "epoch": 0.09224730127576054,
      "grad_norm": 4.079922676086426,
      "learning_rate": 5.90440267166055e-05,
      "loss": 2.6081,
      "step": 94
    },
    {
      "epoch": 0.09322865554465162,
      "grad_norm": 3.2575161457061768,
      "learning_rate": 5.8229729514036705e-05,
      "loss": 2.4936,
      "step": 95
    },
    {
      "epoch": 0.09421000981354269,
      "grad_norm": 3.6793999671936035,
      "learning_rate": 5.74131823855921e-05,
      "loss": 2.5164,
      "step": 96
    },
    {
      "epoch": 0.09519136408243375,
      "grad_norm": 5.089241027832031,
      "learning_rate": 5.6594608567103456e-05,
      "loss": 2.3142,
      "step": 97
    },
    {
      "epoch": 0.09617271835132483,
      "grad_norm": 4.23569393157959,
      "learning_rate": 5.577423184847932e-05,
      "loss": 2.0815,
      "step": 98
    },
    {
      "epoch": 0.0971540726202159,
      "grad_norm": 6.123030662536621,
      "learning_rate": 5.495227651252315e-05,
      "loss": 2.2837,
      "step": 99
    },
    {
      "epoch": 0.09813542688910697,
      "grad_norm": 7.837590217590332,
      "learning_rate": 5.4128967273616625e-05,
      "loss": 2.5126,
      "step": 100
    },
    {
      "epoch": 0.09813542688910697,
      "eval_loss": 1.8393434286117554,
      "eval_runtime": 125.0846,
      "eval_samples_per_second": 13.719,
      "eval_steps_per_second": 3.43,
      "step": 100
    },
    {
      "epoch": 0.09911678115799803,
      "grad_norm": 1.3058151006698608,
      "learning_rate": 5.330452921628497e-05,
      "loss": 1.51,
      "step": 101
    },
    {
      "epoch": 0.10009813542688911,
      "grad_norm": 1.823264241218567,
      "learning_rate": 5.247918773366112e-05,
      "loss": 1.9407,
      "step": 102
    },
    {
      "epoch": 0.10107948969578018,
      "grad_norm": 1.1570013761520386,
      "learning_rate": 5.165316846586541e-05,
      "loss": 1.8509,
      "step": 103
    },
    {
      "epoch": 0.10206084396467124,
      "grad_norm": 1.28945791721344,
      "learning_rate": 5.0826697238317935e-05,
      "loss": 1.9971,
      "step": 104
    },
    {
      "epoch": 0.10304219823356231,
      "grad_norm": 1.2577980756759644,
      "learning_rate": 5e-05,
      "loss": 1.8568,
      "step": 105
    },
    {
      "epoch": 0.10402355250245339,
      "grad_norm": 1.1281801462173462,
      "learning_rate": 4.917330276168208e-05,
      "loss": 1.5951,
      "step": 106
    },
    {
      "epoch": 0.10500490677134446,
      "grad_norm": 1.1188132762908936,
      "learning_rate": 4.834683153413459e-05,
      "loss": 1.9834,
      "step": 107
    },
    {
      "epoch": 0.10598626104023552,
      "grad_norm": 1.0456913709640503,
      "learning_rate": 4.7520812266338885e-05,
      "loss": 1.8276,
      "step": 108
    },
    {
      "epoch": 0.1069676153091266,
      "grad_norm": 1.2189621925354004,
      "learning_rate": 4.669547078371504e-05,
      "loss": 2.0568,
      "step": 109
    },
    {
      "epoch": 0.10794896957801767,
      "grad_norm": 1.1453945636749268,
      "learning_rate": 4.5871032726383386e-05,
      "loss": 1.6509,
      "step": 110
    },
    {
      "epoch": 0.10893032384690873,
      "grad_norm": 1.0300899744033813,
      "learning_rate": 4.504772348747687e-05,
      "loss": 1.8223,
      "step": 111
    },
    {
      "epoch": 0.1099116781157998,
      "grad_norm": 1.2452465295791626,
      "learning_rate": 4.4225768151520694e-05,
      "loss": 1.6015,
      "step": 112
    },
    {
      "epoch": 0.11089303238469088,
      "grad_norm": 0.9570682048797607,
      "learning_rate": 4.3405391432896555e-05,
      "loss": 1.7628,
      "step": 113
    },
    {
      "epoch": 0.11187438665358194,
      "grad_norm": 1.1326767206192017,
      "learning_rate": 4.2586817614407895e-05,
      "loss": 1.8425,
      "step": 114
    },
    {
      "epoch": 0.11285574092247301,
      "grad_norm": 1.0238566398620605,
      "learning_rate": 4.17702704859633e-05,
      "loss": 1.43,
      "step": 115
    },
    {
      "epoch": 0.11383709519136408,
      "grad_norm": 1.257036566734314,
      "learning_rate": 4.095597328339452e-05,
      "loss": 1.7311,
      "step": 116
    },
    {
      "epoch": 0.11481844946025516,
      "grad_norm": 1.3208574056625366,
      "learning_rate": 4.0144148627425993e-05,
      "loss": 1.7593,
      "step": 117
    },
    {
      "epoch": 0.11579980372914622,
      "grad_norm": 1.221962332725525,
      "learning_rate": 3.933501846281267e-05,
      "loss": 1.7956,
      "step": 118
    },
    {
      "epoch": 0.11678115799803729,
      "grad_norm": 1.3392610549926758,
      "learning_rate": 3.852880399766243e-05,
      "loss": 1.7931,
      "step": 119
    },
    {
      "epoch": 0.11776251226692837,
      "grad_norm": 1.2010247707366943,
      "learning_rate": 3.772572564296005e-05,
      "loss": 1.6175,
      "step": 120
    },
    {
      "epoch": 0.11874386653581943,
      "grad_norm": 1.3963546752929688,
      "learning_rate": 3.6926002952309016e-05,
      "loss": 1.7383,
      "step": 121
    },
    {
      "epoch": 0.1197252208047105,
      "grad_norm": 1.3015258312225342,
      "learning_rate": 3.612985456190778e-05,
      "loss": 1.7939,
      "step": 122
    },
    {
      "epoch": 0.12070657507360157,
      "grad_norm": 1.5166168212890625,
      "learning_rate": 3.533749813077677e-05,
      "loss": 1.7108,
      "step": 123
    },
    {
      "epoch": 0.12168792934249265,
      "grad_norm": 1.2579107284545898,
      "learning_rate": 3.4549150281252636e-05,
      "loss": 1.6325,
      "step": 124
    },
    {
      "epoch": 0.12266928361138371,
      "grad_norm": 1.3208256959915161,
      "learning_rate": 3.3765026539765834e-05,
      "loss": 1.806,
      "step": 125
    },
    {
      "epoch": 0.12365063788027478,
      "grad_norm": 1.196277379989624,
      "learning_rate": 3.298534127791785e-05,
      "loss": 1.8013,
      "step": 126
    },
    {
      "epoch": 0.12463199214916584,
      "grad_norm": 1.4352422952651978,
      "learning_rate": 3.221030765387417e-05,
      "loss": 1.9207,
      "step": 127
    },
    {
      "epoch": 0.1256133464180569,
      "grad_norm": 1.7007992267608643,
      "learning_rate": 3.144013755408895e-05,
      "loss": 1.6291,
      "step": 128
    },
    {
      "epoch": 0.12659470068694798,
      "grad_norm": 1.5303325653076172,
      "learning_rate": 3.0675041535377405e-05,
      "loss": 1.7942,
      "step": 129
    },
    {
      "epoch": 0.12757605495583907,
      "grad_norm": 1.5655077695846558,
      "learning_rate": 2.991522876735154e-05,
      "loss": 1.6409,
      "step": 130
    },
    {
      "epoch": 0.12855740922473013,
      "grad_norm": 1.2664812803268433,
      "learning_rate": 2.916090697523549e-05,
      "loss": 1.5198,
      "step": 131
    },
    {
      "epoch": 0.1295387634936212,
      "grad_norm": 1.5933117866516113,
      "learning_rate": 2.8412282383075363e-05,
      "loss": 1.7494,
      "step": 132
    },
    {
      "epoch": 0.13052011776251227,
      "grad_norm": 1.5473688840866089,
      "learning_rate": 2.766955965735968e-05,
      "loss": 1.4154,
      "step": 133
    },
    {
      "epoch": 0.13150147203140333,
      "grad_norm": 1.4446943998336792,
      "learning_rate": 2.693294185106562e-05,
      "loss": 1.6315,
      "step": 134
    },
    {
      "epoch": 0.1324828263002944,
      "grad_norm": 1.7432982921600342,
      "learning_rate": 2.6202630348146324e-05,
      "loss": 1.5761,
      "step": 135
    },
    {
      "epoch": 0.13346418056918546,
      "grad_norm": 1.6057446002960205,
      "learning_rate": 2.547882480847461e-05,
      "loss": 1.4562,
      "step": 136
    },
    {
      "epoch": 0.13444553483807656,
      "grad_norm": 1.843237042427063,
      "learning_rate": 2.476172311325783e-05,
      "loss": 1.6693,
      "step": 137
    },
    {
      "epoch": 0.13542688910696762,
      "grad_norm": 1.7279915809631348,
      "learning_rate": 2.405152131093926e-05,
      "loss": 1.6052,
      "step": 138
    },
    {
      "epoch": 0.1364082433758587,
      "grad_norm": 1.403794288635254,
      "learning_rate": 2.3348413563600325e-05,
      "loss": 1.5552,
      "step": 139
    },
    {
      "epoch": 0.13738959764474976,
      "grad_norm": 2.1310362815856934,
      "learning_rate": 2.2652592093878666e-05,
      "loss": 1.8025,
      "step": 140
    },
    {
      "epoch": 0.13837095191364082,
      "grad_norm": 2.0410852432250977,
      "learning_rate": 2.196424713241637e-05,
      "loss": 1.7874,
      "step": 141
    },
    {
      "epoch": 0.1393523061825319,
      "grad_norm": 2.4357564449310303,
      "learning_rate": 2.128356686585282e-05,
      "loss": 1.9004,
      "step": 142
    },
    {
      "epoch": 0.14033366045142295,
      "grad_norm": 2.8178184032440186,
      "learning_rate": 2.061073738537635e-05,
      "loss": 1.8923,
      "step": 143
    },
    {
      "epoch": 0.14131501472031405,
      "grad_norm": 3.6915547847747803,
      "learning_rate": 1.9945942635848748e-05,
      "loss": 2.0565,
      "step": 144
    },
    {
      "epoch": 0.1422963689892051,
      "grad_norm": 3.509272336959839,
      "learning_rate": 1.928936436551661e-05,
      "loss": 1.9227,
      "step": 145
    },
    {
      "epoch": 0.14327772325809618,
      "grad_norm": 3.532844305038452,
      "learning_rate": 1.8641182076323148e-05,
      "loss": 2.0565,
      "step": 146
    },
    {
      "epoch": 0.14425907752698724,
      "grad_norm": 5.242225170135498,
      "learning_rate": 1.800157297483417e-05,
      "loss": 1.8213,
      "step": 147
    },
    {
      "epoch": 0.1452404317958783,
      "grad_norm": 4.219196319580078,
      "learning_rate": 1.7370711923791567e-05,
      "loss": 1.4891,
      "step": 148
    },
    {
      "epoch": 0.14622178606476938,
      "grad_norm": 4.781096935272217,
      "learning_rate": 1.6748771394307585e-05,
      "loss": 1.3004,
      "step": 149
    },
    {
      "epoch": 0.14720314033366044,
      "grad_norm": 5.950371265411377,
      "learning_rate": 1.6135921418712956e-05,
      "loss": 1.647,
      "step": 150
    },
    {
      "epoch": 0.14720314033366044,
      "eval_loss": 1.6349378824234009,
      "eval_runtime": 125.2978,
      "eval_samples_per_second": 13.695,
      "eval_steps_per_second": 3.424,
      "step": 150
    },
    {
      "epoch": 0.1481844946025515,
      "grad_norm": 0.7931824326515198,
      "learning_rate": 1.553232954407171e-05,
      "loss": 1.1945,
      "step": 151
    },
    {
      "epoch": 0.1491658488714426,
      "grad_norm": 1.1617341041564941,
      "learning_rate": 1.4938160786375572e-05,
      "loss": 1.6768,
      "step": 152
    },
    {
      "epoch": 0.15014720314033367,
      "grad_norm": 1.1608675718307495,
      "learning_rate": 1.435357758543015e-05,
      "loss": 1.723,
      "step": 153
    },
    {
      "epoch": 0.15112855740922473,
      "grad_norm": 1.1515305042266846,
      "learning_rate": 1.3778739760445552e-05,
      "loss": 1.865,
      "step": 154
    },
    {
      "epoch": 0.1521099116781158,
      "grad_norm": 1.1226379871368408,
      "learning_rate": 1.3213804466343421e-05,
      "loss": 1.7876,
      "step": 155
    },
    {
      "epoch": 0.15309126594700687,
      "grad_norm": 1.1973044872283936,
      "learning_rate": 1.2658926150792322e-05,
      "loss": 1.666,
      "step": 156
    },
    {
      "epoch": 0.15407262021589793,
      "grad_norm": 1.3679039478302002,
      "learning_rate": 1.2114256511983274e-05,
      "loss": 1.6943,
      "step": 157
    },
    {
      "epoch": 0.155053974484789,
      "grad_norm": 1.2026727199554443,
      "learning_rate": 1.157994445715706e-05,
      "loss": 1.5028,
      "step": 158
    },
    {
      "epoch": 0.1560353287536801,
      "grad_norm": 1.1329495906829834,
      "learning_rate": 1.1056136061894384e-05,
      "loss": 1.8944,
      "step": 159
    },
    {
      "epoch": 0.15701668302257116,
      "grad_norm": 1.0366361141204834,
      "learning_rate": 1.0542974530180327e-05,
      "loss": 1.5771,
      "step": 160
    },
    {
      "epoch": 0.15799803729146222,
      "grad_norm": 1.235419750213623,
      "learning_rate": 1.0040600155253765e-05,
      "loss": 1.8073,
      "step": 161
    },
    {
      "epoch": 0.1589793915603533,
      "grad_norm": 1.1439399719238281,
      "learning_rate": 9.549150281252633e-06,
      "loss": 1.6163,
      "step": 162
    },
    {
      "epoch": 0.15996074582924436,
      "grad_norm": 1.2010005712509155,
      "learning_rate": 9.068759265665384e-06,
      "loss": 1.6157,
      "step": 163
    },
    {
      "epoch": 0.16094210009813542,
      "grad_norm": 1.0463441610336304,
      "learning_rate": 8.599558442598998e-06,
      "loss": 1.782,
      "step": 164
    },
    {
      "epoch": 0.1619234543670265,
      "grad_norm": 0.9857537150382996,
      "learning_rate": 8.141676086873572e-06,
      "loss": 1.448,
      "step": 165
    },
    {
      "epoch": 0.16290480863591755,
      "grad_norm": 1.1752471923828125,
      "learning_rate": 7.695237378953223e-06,
      "loss": 1.8328,
      "step": 166
    },
    {
      "epoch": 0.16388616290480865,
      "grad_norm": 1.247128963470459,
      "learning_rate": 7.260364370723044e-06,
      "loss": 1.774,
      "step": 167
    },
    {
      "epoch": 0.1648675171736997,
      "grad_norm": 1.2425484657287598,
      "learning_rate": 6.837175952121306e-06,
      "loss": 1.6887,
      "step": 168
    },
    {
      "epoch": 0.16584887144259078,
      "grad_norm": 1.2244716882705688,
      "learning_rate": 6.425787818636131e-06,
      "loss": 1.8182,
      "step": 169
    },
    {
      "epoch": 0.16683022571148184,
      "grad_norm": 1.1033352613449097,
      "learning_rate": 6.026312439675552e-06,
      "loss": 1.5954,
      "step": 170
    },
    {
      "epoch": 0.1678115799803729,
      "grad_norm": 1.274817943572998,
      "learning_rate": 5.6388590278194096e-06,
      "loss": 1.529,
      "step": 171
    },
    {
      "epoch": 0.16879293424926398,
      "grad_norm": 1.4762018918991089,
      "learning_rate": 5.263533508961827e-06,
      "loss": 1.635,
      "step": 172
    },
    {
      "epoch": 0.16977428851815504,
      "grad_norm": 1.4434161186218262,
      "learning_rate": 4.900438493352055e-06,
      "loss": 1.8666,
      "step": 173
    },
    {
      "epoch": 0.17075564278704614,
      "grad_norm": 1.204027771949768,
      "learning_rate": 4.549673247541875e-06,
      "loss": 1.5221,
      "step": 174
    },
    {
      "epoch": 0.1717369970559372,
      "grad_norm": 1.0852041244506836,
      "learning_rate": 4.2113336672471245e-06,
      "loss": 1.4859,
      "step": 175
    },
    {
      "epoch": 0.17271835132482827,
      "grad_norm": 1.3346103429794312,
      "learning_rate": 3.885512251130763e-06,
      "loss": 1.5991,
      "step": 176
    },
    {
      "epoch": 0.17369970559371933,
      "grad_norm": 1.3467015027999878,
      "learning_rate": 3.5722980755146517e-06,
      "loss": 1.755,
      "step": 177
    },
    {
      "epoch": 0.1746810598626104,
      "grad_norm": 1.4287385940551758,
      "learning_rate": 3.271776770026963e-06,
      "loss": 1.6653,
      "step": 178
    },
    {
      "epoch": 0.17566241413150147,
      "grad_norm": 1.2467063665390015,
      "learning_rate": 2.9840304941919415e-06,
      "loss": 1.4256,
      "step": 179
    },
    {
      "epoch": 0.17664376840039253,
      "grad_norm": 1.4375609159469604,
      "learning_rate": 2.7091379149682685e-06,
      "loss": 1.6628,
      "step": 180
    },
    {
      "epoch": 0.17762512266928362,
      "grad_norm": 1.5163654088974,
      "learning_rate": 2.4471741852423237e-06,
      "loss": 1.6683,
      "step": 181
    },
    {
      "epoch": 0.1786064769381747,
      "grad_norm": 1.2792954444885254,
      "learning_rate": 2.1982109232821178e-06,
      "loss": 1.5655,
      "step": 182
    },
    {
      "epoch": 0.17958783120706576,
      "grad_norm": 1.5046882629394531,
      "learning_rate": 1.962316193157593e-06,
      "loss": 1.656,
      "step": 183
    },
    {
      "epoch": 0.18056918547595682,
      "grad_norm": 1.5116846561431885,
      "learning_rate": 1.7395544861325718e-06,
      "loss": 1.7521,
      "step": 184
    },
    {
      "epoch": 0.1815505397448479,
      "grad_norm": 2.1853580474853516,
      "learning_rate": 1.5299867030334814e-06,
      "loss": 1.7129,
      "step": 185
    },
    {
      "epoch": 0.18253189401373895,
      "grad_norm": 1.405174732208252,
      "learning_rate": 1.333670137599713e-06,
      "loss": 1.3447,
      "step": 186
    },
    {
      "epoch": 0.18351324828263002,
      "grad_norm": 1.6939140558242798,
      "learning_rate": 1.1506584608200367e-06,
      "loss": 1.5955,
      "step": 187
    },
    {
      "epoch": 0.1844946025515211,
      "grad_norm": 1.9692758321762085,
      "learning_rate": 9.810017062595322e-07,
      "loss": 1.7164,
      "step": 188
    },
    {
      "epoch": 0.18547595682041218,
      "grad_norm": 1.6777070760726929,
      "learning_rate": 8.247462563808817e-07,
      "loss": 1.4854,
      "step": 189
    },
    {
      "epoch": 0.18645731108930325,
      "grad_norm": 1.978770136833191,
      "learning_rate": 6.819348298638839e-07,
      "loss": 1.3896,
      "step": 190
    },
    {
      "epoch": 0.1874386653581943,
      "grad_norm": 1.7185646295547485,
      "learning_rate": 5.526064699265753e-07,
      "loss": 1.5248,
      "step": 191
    },
    {
      "epoch": 0.18842001962708538,
      "grad_norm": 2.043696403503418,
      "learning_rate": 4.367965336512403e-07,
      "loss": 1.6041,
      "step": 192
    },
    {
      "epoch": 0.18940137389597644,
      "grad_norm": 2.69663405418396,
      "learning_rate": 3.3453668231809286e-07,
      "loss": 1.8083,
      "step": 193
    },
    {
      "epoch": 0.1903827281648675,
      "grad_norm": 3.4714674949645996,
      "learning_rate": 2.458548727494292e-07,
      "loss": 1.8765,
      "step": 194
    },
    {
      "epoch": 0.19136408243375858,
      "grad_norm": 3.1443798542022705,
      "learning_rate": 1.7077534966650766e-07,
      "loss": 1.754,
      "step": 195
    },
    {
      "epoch": 0.19234543670264967,
      "grad_norm": 2.8399949073791504,
      "learning_rate": 1.0931863906127327e-07,
      "loss": 1.7381,
      "step": 196
    },
    {
      "epoch": 0.19332679097154074,
      "grad_norm": 3.7051687240600586,
      "learning_rate": 6.150154258476315e-08,
      "loss": 1.5523,
      "step": 197
    },
    {
      "epoch": 0.1943081452404318,
      "grad_norm": 4.091912269592285,
      "learning_rate": 2.7337132953697554e-08,
      "loss": 1.5518,
      "step": 198
    },
    {
      "epoch": 0.19528949950932287,
      "grad_norm": 4.399522304534912,
      "learning_rate": 6.834750376549792e-09,
      "loss": 1.3735,
      "step": 199
    },
    {
      "epoch": 0.19627085377821393,
      "grad_norm": 6.8812408447265625,
      "learning_rate": 0.0,
      "loss": 1.773,
      "step": 200
    },
    {
      "epoch": 0.19627085377821393,
      "eval_loss": 1.5952566862106323,
      "eval_runtime": 125.0495,
      "eval_samples_per_second": 13.723,
      "eval_steps_per_second": 3.431,
      "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": 2.893543474672435e+17,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}