{
  "best_metric": 0.016778385266661644,
  "best_model_checkpoint": "miner_id_24/checkpoint-200",
  "epoch": 0.017970259220989264,
  "eval_steps": 50,
  "global_step": 200,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 8.985129610494631e-05,
      "grad_norm": 2.388788938522339,
      "learning_rate": 1e-05,
      "loss": 1.5408,
      "step": 1
    },
    {
      "epoch": 8.985129610494631e-05,
      "eval_loss": 1.4799306392669678,
      "eval_runtime": 901.4276,
      "eval_samples_per_second": 20.795,
      "eval_steps_per_second": 5.2,
      "step": 1
    },
    {
      "epoch": 0.00017970259220989262,
      "grad_norm": 2.8213908672332764,
      "learning_rate": 2e-05,
      "loss": 1.7609,
      "step": 2
    },
    {
      "epoch": 0.00026955388831483896,
      "grad_norm": 3.2226476669311523,
      "learning_rate": 3e-05,
      "loss": 2.1178,
      "step": 3
    },
    {
      "epoch": 0.00035940518441978525,
      "grad_norm": 3.3700153827667236,
      "learning_rate": 4e-05,
      "loss": 2.1118,
      "step": 4
    },
    {
      "epoch": 0.0004492564805247316,
      "grad_norm": 3.527953624725342,
      "learning_rate": 5e-05,
      "loss": 1.9904,
      "step": 5
    },
    {
      "epoch": 0.0005391077766296779,
      "grad_norm": 3.702324390411377,
      "learning_rate": 6e-05,
      "loss": 1.9364,
      "step": 6
    },
    {
      "epoch": 0.0006289590727346242,
      "grad_norm": 3.1446261405944824,
      "learning_rate": 7e-05,
      "loss": 1.5929,
      "step": 7
    },
    {
      "epoch": 0.0007188103688395705,
      "grad_norm": 2.7797582149505615,
      "learning_rate": 8e-05,
      "loss": 1.3322,
      "step": 8
    },
    {
      "epoch": 0.0008086616649445168,
      "grad_norm": 1.7103683948516846,
      "learning_rate": 9e-05,
      "loss": 0.9137,
      "step": 9
    },
    {
      "epoch": 0.0008985129610494632,
      "grad_norm": 1.6252132654190063,
      "learning_rate": 0.0001,
      "loss": 0.9555,
      "step": 10
    },
    {
      "epoch": 0.0009883642571544094,
      "grad_norm": 2.3974406719207764,
      "learning_rate": 9.999316524962345e-05,
      "loss": 0.804,
      "step": 11
    },
    {
      "epoch": 0.0010782155532593559,
      "grad_norm": 1.7891347408294678,
      "learning_rate": 9.997266286704631e-05,
      "loss": 0.7281,
      "step": 12
    },
    {
      "epoch": 0.0011680668493643021,
      "grad_norm": 1.5614227056503296,
      "learning_rate": 9.993849845741524e-05,
      "loss": 0.6241,
      "step": 13
    },
    {
      "epoch": 0.0012579181454692484,
      "grad_norm": 1.5713458061218262,
      "learning_rate": 9.989068136093873e-05,
      "loss": 0.462,
      "step": 14
    },
    {
      "epoch": 0.0013477694415741947,
      "grad_norm": 1.1358058452606201,
      "learning_rate": 9.98292246503335e-05,
      "loss": 0.3021,
      "step": 15
    },
    {
      "epoch": 0.001437620737679141,
      "grad_norm": 1.0922521352767944,
      "learning_rate": 9.975414512725057e-05,
      "loss": 0.2806,
      "step": 16
    },
    {
      "epoch": 0.0015274720337840873,
      "grad_norm": 1.394178032875061,
      "learning_rate": 9.966546331768191e-05,
      "loss": 0.3656,
      "step": 17
    },
    {
      "epoch": 0.0016173233298890336,
      "grad_norm": 1.058937907218933,
      "learning_rate": 9.956320346634876e-05,
      "loss": 0.1882,
      "step": 18
    },
    {
      "epoch": 0.00170717462599398,
      "grad_norm": 1.3172550201416016,
      "learning_rate": 9.944739353007344e-05,
      "loss": 0.2863,
      "step": 19
    },
    {
      "epoch": 0.0017970259220989263,
      "grad_norm": 1.8061860799789429,
      "learning_rate": 9.931806517013612e-05,
      "loss": 0.349,
      "step": 20
    },
    {
      "epoch": 0.0018868772182038726,
      "grad_norm": 1.3081026077270508,
      "learning_rate": 9.917525374361912e-05,
      "loss": 0.1169,
      "step": 21
    },
    {
      "epoch": 0.0019767285143088187,
      "grad_norm": 1.8801676034927368,
      "learning_rate": 9.901899829374047e-05,
      "loss": 0.3773,
      "step": 22
    },
    {
      "epoch": 0.0020665798104137654,
      "grad_norm": 1.2898595333099365,
      "learning_rate": 9.884934153917997e-05,
      "loss": 0.1644,
      "step": 23
    },
    {
      "epoch": 0.0021564311065187117,
      "grad_norm": 2.21494197845459,
      "learning_rate": 9.86663298624003e-05,
      "loss": 0.2302,
      "step": 24
    },
    {
      "epoch": 0.002246282402623658,
      "grad_norm": 1.060278296470642,
      "learning_rate": 9.847001329696653e-05,
      "loss": 0.1159,
      "step": 25
    },
    {
      "epoch": 0.0023361336987286043,
      "grad_norm": 1.4339865446090698,
      "learning_rate": 9.826044551386744e-05,
      "loss": 0.1716,
      "step": 26
    },
    {
      "epoch": 0.0024259849948335506,
      "grad_norm": 0.9997158646583557,
      "learning_rate": 9.803768380684242e-05,
      "loss": 0.037,
      "step": 27
    },
    {
      "epoch": 0.002515836290938497,
      "grad_norm": 2.287733554840088,
      "learning_rate": 9.780178907671789e-05,
      "loss": 0.1358,
      "step": 28
    },
    {
      "epoch": 0.002605687587043443,
      "grad_norm": 0.4436582028865814,
      "learning_rate": 9.755282581475769e-05,
      "loss": 0.0291,
      "step": 29
    },
    {
      "epoch": 0.0026955388831483894,
      "grad_norm": 0.5807464718818665,
      "learning_rate": 9.729086208503174e-05,
      "loss": 0.0194,
      "step": 30
    },
    {
      "epoch": 0.0027853901792533357,
      "grad_norm": 1.409766435623169,
      "learning_rate": 9.701596950580806e-05,
      "loss": 0.0657,
      "step": 31
    },
    {
      "epoch": 0.002875241475358282,
      "grad_norm": 1.207972526550293,
      "learning_rate": 9.672822322997305e-05,
      "loss": 0.1951,
      "step": 32
    },
    {
      "epoch": 0.0029650927714632283,
      "grad_norm": 0.8214380741119385,
      "learning_rate": 9.642770192448536e-05,
      "loss": 0.1156,
      "step": 33
    },
    {
      "epoch": 0.0030549440675681746,
      "grad_norm": 1.9357601404190063,
      "learning_rate": 9.611448774886924e-05,
      "loss": 0.0873,
      "step": 34
    },
    {
      "epoch": 0.003144795363673121,
      "grad_norm": 2.1450936794281006,
      "learning_rate": 9.578866633275288e-05,
      "loss": 0.2288,
      "step": 35
    },
    {
      "epoch": 0.003234646659778067,
      "grad_norm": 0.5352392792701721,
      "learning_rate": 9.545032675245813e-05,
      "loss": 0.0288,
      "step": 36
    },
    {
      "epoch": 0.0033244979558830134,
      "grad_norm": 2.8170526027679443,
      "learning_rate": 9.509956150664796e-05,
      "loss": 0.3828,
      "step": 37
    },
    {
      "epoch": 0.00341434925198796,
      "grad_norm": 1.006988286972046,
      "learning_rate": 9.473646649103818e-05,
      "loss": 0.0432,
      "step": 38
    },
    {
      "epoch": 0.0035042005480929064,
      "grad_norm": 1.629753828048706,
      "learning_rate": 9.43611409721806e-05,
      "loss": 0.2112,
      "step": 39
    },
    {
      "epoch": 0.0035940518441978527,
      "grad_norm": 1.1105238199234009,
      "learning_rate": 9.397368756032445e-05,
      "loss": 0.073,
      "step": 40
    },
    {
      "epoch": 0.003683903140302799,
      "grad_norm": 2.558805465698242,
      "learning_rate": 9.357421218136386e-05,
      "loss": 0.4426,
      "step": 41
    },
    {
      "epoch": 0.0037737544364077453,
      "grad_norm": 1.6937123537063599,
      "learning_rate": 9.316282404787871e-05,
      "loss": 0.0511,
      "step": 42
    },
    {
      "epoch": 0.0038636057325126916,
      "grad_norm": 0.47619715332984924,
      "learning_rate": 9.273963562927695e-05,
      "loss": 0.0292,
      "step": 43
    },
    {
      "epoch": 0.003953457028617637,
      "grad_norm": 3.6469249725341797,
      "learning_rate": 9.230476262104677e-05,
      "loss": 0.1238,
      "step": 44
    },
    {
      "epoch": 0.0040433083247225846,
      "grad_norm": 1.2075451612472534,
      "learning_rate": 9.185832391312644e-05,
      "loss": 0.0635,
      "step": 45
    },
    {
      "epoch": 0.004133159620827531,
      "grad_norm": 2.7494451999664307,
      "learning_rate": 9.140044155740101e-05,
      "loss": 0.4871,
      "step": 46
    },
    {
      "epoch": 0.004223010916932477,
      "grad_norm": 3.211578607559204,
      "learning_rate": 9.093124073433463e-05,
      "loss": 0.4836,
      "step": 47
    },
    {
      "epoch": 0.004312862213037423,
      "grad_norm": 3.217000722885132,
      "learning_rate": 9.045084971874738e-05,
      "loss": 0.3402,
      "step": 48
    },
    {
      "epoch": 0.00440271350914237,
      "grad_norm": 6.685438632965088,
      "learning_rate": 8.995939984474624e-05,
      "loss": 1.1275,
      "step": 49
    },
    {
      "epoch": 0.004492564805247316,
      "grad_norm": 40.79585647583008,
      "learning_rate": 8.945702546981969e-05,
      "loss": 6.6405,
      "step": 50
    },
    {
      "epoch": 0.004492564805247316,
      "eval_loss": 0.04590430483222008,
      "eval_runtime": 906.7297,
      "eval_samples_per_second": 20.673,
      "eval_steps_per_second": 5.169,
      "step": 50
    },
    {
      "epoch": 0.004582416101352262,
      "grad_norm": 1.1166143417358398,
      "learning_rate": 8.894386393810563e-05,
      "loss": 0.1223,
      "step": 51
    },
    {
      "epoch": 0.0046722673974572086,
      "grad_norm": 0.6125300526618958,
      "learning_rate": 8.842005554284296e-05,
      "loss": 0.0423,
      "step": 52
    },
    {
      "epoch": 0.004762118693562155,
      "grad_norm": 0.3190569579601288,
      "learning_rate": 8.788574348801675e-05,
      "loss": 0.0359,
      "step": 53
    },
    {
      "epoch": 0.004851969989667101,
      "grad_norm": 0.26611465215682983,
      "learning_rate": 8.73410738492077e-05,
      "loss": 0.0395,
      "step": 54
    },
    {
      "epoch": 0.004941821285772047,
      "grad_norm": 0.716010332107544,
      "learning_rate": 8.678619553365659e-05,
      "loss": 0.1418,
      "step": 55
    },
    {
      "epoch": 0.005031672581876994,
      "grad_norm": 0.40194588899612427,
      "learning_rate": 8.622126023955446e-05,
      "loss": 0.0803,
      "step": 56
    },
    {
      "epoch": 0.00512152387798194,
      "grad_norm": 0.3210628926753998,
      "learning_rate": 8.564642241456986e-05,
      "loss": 0.0357,
      "step": 57
    },
    {
      "epoch": 0.005211375174086886,
      "grad_norm": 0.25224635004997253,
      "learning_rate": 8.506183921362443e-05,
      "loss": 0.0167,
      "step": 58
    },
    {
      "epoch": 0.0053012264701918325,
      "grad_norm": 0.48702114820480347,
      "learning_rate": 8.44676704559283e-05,
      "loss": 0.1195,
      "step": 59
    },
    {
      "epoch": 0.005391077766296779,
      "grad_norm": 1.2477227449417114,
      "learning_rate": 8.386407858128706e-05,
      "loss": 0.0533,
      "step": 60
    },
    {
      "epoch": 0.005480929062401725,
      "grad_norm": 0.1762041598558426,
      "learning_rate": 8.32512286056924e-05,
      "loss": 0.0161,
      "step": 61
    },
    {
      "epoch": 0.005570780358506671,
      "grad_norm": 0.3423959016799927,
      "learning_rate": 8.262928807620843e-05,
      "loss": 0.0157,
      "step": 62
    },
    {
      "epoch": 0.005660631654611618,
      "grad_norm": 0.2721407413482666,
      "learning_rate": 8.199842702516583e-05,
      "loss": 0.0301,
      "step": 63
    },
    {
      "epoch": 0.005750482950716564,
      "grad_norm": 0.6348956823348999,
      "learning_rate": 8.135881792367686e-05,
      "loss": 0.074,
      "step": 64
    },
    {
      "epoch": 0.00584033424682151,
      "grad_norm": 0.482307106256485,
      "learning_rate": 8.07106356344834e-05,
      "loss": 0.0722,
      "step": 65
    },
    {
      "epoch": 0.0059301855429264565,
      "grad_norm": 0.8486773371696472,
      "learning_rate": 8.005405736415126e-05,
      "loss": 0.0326,
      "step": 66
    },
    {
      "epoch": 0.006020036839031403,
      "grad_norm": 0.2876744866371155,
      "learning_rate": 7.938926261462366e-05,
      "loss": 0.0139,
      "step": 67
    },
    {
      "epoch": 0.006109888135136349,
      "grad_norm": 0.5865163803100586,
      "learning_rate": 7.871643313414718e-05,
      "loss": 0.0635,
      "step": 68
    },
    {
      "epoch": 0.006199739431241295,
      "grad_norm": 0.6363226175308228,
      "learning_rate": 7.803575286758364e-05,
      "loss": 0.0291,
      "step": 69
    },
    {
      "epoch": 0.006289590727346242,
      "grad_norm": 0.704571545124054,
      "learning_rate": 7.734740790612136e-05,
      "loss": 0.105,
      "step": 70
    },
    {
      "epoch": 0.006379442023451188,
      "grad_norm": 0.3582151532173157,
      "learning_rate": 7.66515864363997e-05,
      "loss": 0.0587,
      "step": 71
    },
    {
      "epoch": 0.006469293319556134,
      "grad_norm": 1.0419330596923828,
      "learning_rate": 7.594847868906076e-05,
      "loss": 0.0825,
      "step": 72
    },
    {
      "epoch": 0.0065591446156610805,
      "grad_norm": 0.2622736096382141,
      "learning_rate": 7.52382768867422e-05,
      "loss": 0.0131,
      "step": 73
    },
    {
      "epoch": 0.006648995911766027,
      "grad_norm": 0.5100119709968567,
      "learning_rate": 7.452117519152542e-05,
      "loss": 0.0415,
      "step": 74
    },
    {
      "epoch": 0.006738847207870974,
      "grad_norm": 0.7604436874389648,
      "learning_rate": 7.379736965185368e-05,
      "loss": 0.1246,
      "step": 75
    },
    {
      "epoch": 0.00682869850397592,
      "grad_norm": 1.4707365036010742,
      "learning_rate": 7.30670581489344e-05,
      "loss": 0.0988,
      "step": 76
    },
    {
      "epoch": 0.0069185498000808665,
      "grad_norm": 0.5223230123519897,
      "learning_rate": 7.233044034264034e-05,
      "loss": 0.0888,
      "step": 77
    },
    {
      "epoch": 0.007008401096185813,
      "grad_norm": 0.8577005863189697,
      "learning_rate": 7.158771761692464e-05,
      "loss": 0.1326,
      "step": 78
    },
    {
      "epoch": 0.007098252392290759,
      "grad_norm": 0.7848546504974365,
      "learning_rate": 7.083909302476453e-05,
      "loss": 0.1195,
      "step": 79
    },
    {
      "epoch": 0.007188103688395705,
      "grad_norm": 1.269745945930481,
      "learning_rate": 7.008477123264848e-05,
      "loss": 0.0861,
      "step": 80
    },
    {
      "epoch": 0.007277954984500652,
      "grad_norm": 0.9416220188140869,
      "learning_rate": 6.932495846462261e-05,
      "loss": 0.0694,
      "step": 81
    },
    {
      "epoch": 0.007367806280605598,
      "grad_norm": 0.2914826571941376,
      "learning_rate": 6.855986244591104e-05,
      "loss": 0.0156,
      "step": 82
    },
    {
      "epoch": 0.007457657576710544,
      "grad_norm": 0.2817656099796295,
      "learning_rate": 6.778969234612584e-05,
      "loss": 0.017,
      "step": 83
    },
    {
      "epoch": 0.0075475088728154905,
      "grad_norm": 0.5657321810722351,
      "learning_rate": 6.701465872208216e-05,
      "loss": 0.0838,
      "step": 84
    },
    {
      "epoch": 0.007637360168920437,
      "grad_norm": 0.6380274295806885,
      "learning_rate": 6.623497346023418e-05,
      "loss": 0.0491,
      "step": 85
    },
    {
      "epoch": 0.007727211465025383,
      "grad_norm": 0.12880580127239227,
      "learning_rate": 6.545084971874738e-05,
      "loss": 0.0103,
      "step": 86
    },
    {
      "epoch": 0.007817062761130329,
      "grad_norm": 0.8266147375106812,
      "learning_rate": 6.466250186922325e-05,
      "loss": 0.0544,
      "step": 87
    },
    {
      "epoch": 0.007906914057235275,
      "grad_norm": 1.2824567556381226,
      "learning_rate": 6.387014543809223e-05,
      "loss": 0.0906,
      "step": 88
    },
    {
      "epoch": 0.007996765353340221,
      "grad_norm": 0.32709047198295593,
      "learning_rate": 6.307399704769099e-05,
      "loss": 0.0208,
      "step": 89
    },
    {
      "epoch": 0.008086616649445169,
      "grad_norm": 0.7845993041992188,
      "learning_rate": 6.227427435703997e-05,
      "loss": 0.0463,
      "step": 90
    },
    {
      "epoch": 0.008176467945550115,
      "grad_norm": 0.763830840587616,
      "learning_rate": 6.147119600233758e-05,
      "loss": 0.0373,
      "step": 91
    },
    {
      "epoch": 0.008266319241655062,
      "grad_norm": 1.1305898427963257,
      "learning_rate": 6.066498153718735e-05,
      "loss": 0.057,
      "step": 92
    },
    {
      "epoch": 0.008356170537760008,
      "grad_norm": 0.14523261785507202,
      "learning_rate": 5.985585137257401e-05,
      "loss": 0.0084,
      "step": 93
    },
    {
      "epoch": 0.008446021833864954,
      "grad_norm": 0.43409788608551025,
      "learning_rate": 5.90440267166055e-05,
      "loss": 0.0102,
      "step": 94
    },
    {
      "epoch": 0.0085358731299699,
      "grad_norm": 0.17463582754135132,
      "learning_rate": 5.8229729514036705e-05,
      "loss": 0.0082,
      "step": 95
    },
    {
      "epoch": 0.008625724426074847,
      "grad_norm": 0.49445804953575134,
      "learning_rate": 5.74131823855921e-05,
      "loss": 0.0166,
      "step": 96
    },
    {
      "epoch": 0.008715575722179793,
      "grad_norm": 0.18184508383274078,
      "learning_rate": 5.6594608567103456e-05,
      "loss": 0.0058,
      "step": 97
    },
    {
      "epoch": 0.00880542701828474,
      "grad_norm": 1.2803819179534912,
      "learning_rate": 5.577423184847932e-05,
      "loss": 0.0343,
      "step": 98
    },
    {
      "epoch": 0.008895278314389686,
      "grad_norm": 1.0309510231018066,
      "learning_rate": 5.495227651252315e-05,
      "loss": 0.0285,
      "step": 99
    },
    {
      "epoch": 0.008985129610494632,
      "grad_norm": 27.885900497436523,
      "learning_rate": 5.4128967273616625e-05,
      "loss": 4.6107,
      "step": 100
    },
    {
      "epoch": 0.008985129610494632,
      "eval_loss": 0.025695189833641052,
      "eval_runtime": 906.657,
      "eval_samples_per_second": 20.675,
      "eval_steps_per_second": 5.17,
      "step": 100
    },
    {
      "epoch": 0.009074980906599578,
      "grad_norm": 0.3603351414203644,
      "learning_rate": 5.330452921628497e-05,
      "loss": 0.0495,
      "step": 101
    },
    {
      "epoch": 0.009164832202704525,
      "grad_norm": 0.14788700640201569,
      "learning_rate": 5.247918773366112e-05,
      "loss": 0.0081,
      "step": 102
    },
    {
      "epoch": 0.00925468349880947,
      "grad_norm": 0.3788295090198517,
      "learning_rate": 5.165316846586541e-05,
      "loss": 0.0845,
      "step": 103
    },
    {
      "epoch": 0.009344534794914417,
      "grad_norm": 0.541358232498169,
      "learning_rate": 5.0826697238317935e-05,
      "loss": 0.0861,
      "step": 104
    },
    {
      "epoch": 0.009434386091019363,
      "grad_norm": 0.06525766104459763,
      "learning_rate": 5e-05,
      "loss": 0.0023,
      "step": 105
    },
    {
      "epoch": 0.00952423738712431,
      "grad_norm": 7.902554512023926,
      "learning_rate": 4.917330276168208e-05,
      "loss": 0.0945,
      "step": 106
    },
    {
      "epoch": 0.009614088683229256,
      "grad_norm": 0.060054849833250046,
      "learning_rate": 4.834683153413459e-05,
      "loss": 0.0042,
      "step": 107
    },
    {
      "epoch": 0.009703939979334202,
      "grad_norm": 0.8934226632118225,
      "learning_rate": 4.7520812266338885e-05,
      "loss": 0.2003,
      "step": 108
    },
    {
      "epoch": 0.009793791275439149,
      "grad_norm": 0.48377078771591187,
      "learning_rate": 4.669547078371504e-05,
      "loss": 0.0312,
      "step": 109
    },
    {
      "epoch": 0.009883642571544095,
      "grad_norm": 0.11235053092241287,
      "learning_rate": 4.5871032726383386e-05,
      "loss": 0.0052,
      "step": 110
    },
    {
      "epoch": 0.009973493867649041,
      "grad_norm": 0.15674369037151337,
      "learning_rate": 4.504772348747687e-05,
      "loss": 0.0065,
      "step": 111
    },
    {
      "epoch": 0.010063345163753987,
      "grad_norm": 0.13642801344394684,
      "learning_rate": 4.4225768151520694e-05,
      "loss": 0.0073,
      "step": 112
    },
    {
      "epoch": 0.010153196459858934,
      "grad_norm": 1.1502249240875244,
      "learning_rate": 4.3405391432896555e-05,
      "loss": 0.0665,
      "step": 113
    },
    {
      "epoch": 0.01024304775596388,
      "grad_norm": 0.4164653420448303,
      "learning_rate": 4.2586817614407895e-05,
      "loss": 0.0166,
      "step": 114
    },
    {
      "epoch": 0.010332899052068826,
      "grad_norm": 0.29311686754226685,
      "learning_rate": 4.17702704859633e-05,
      "loss": 0.026,
      "step": 115
    },
    {
      "epoch": 0.010422750348173773,
      "grad_norm": 1.3062735795974731,
      "learning_rate": 4.095597328339452e-05,
      "loss": 0.091,
      "step": 116
    },
    {
      "epoch": 0.010512601644278719,
      "grad_norm": 0.3029405474662781,
      "learning_rate": 4.0144148627425993e-05,
      "loss": 0.053,
      "step": 117
    },
    {
      "epoch": 0.010602452940383665,
      "grad_norm": 0.08126576244831085,
      "learning_rate": 3.933501846281267e-05,
      "loss": 0.0032,
      "step": 118
    },
    {
      "epoch": 0.010692304236488611,
      "grad_norm": 2.6398396492004395,
      "learning_rate": 3.852880399766243e-05,
      "loss": 0.0262,
      "step": 119
    },
    {
      "epoch": 0.010782155532593558,
      "grad_norm": 1.9561644792556763,
      "learning_rate": 3.772572564296005e-05,
      "loss": 0.0381,
      "step": 120
    },
    {
      "epoch": 0.010872006828698504,
      "grad_norm": 0.723412036895752,
      "learning_rate": 3.6926002952309016e-05,
      "loss": 0.0563,
      "step": 121
    },
    {
      "epoch": 0.01096185812480345,
      "grad_norm": 1.8104438781738281,
      "learning_rate": 3.612985456190778e-05,
      "loss": 0.1271,
      "step": 122
    },
    {
      "epoch": 0.011051709420908397,
      "grad_norm": 0.12050595879554749,
      "learning_rate": 3.533749813077677e-05,
      "loss": 0.0046,
      "step": 123
    },
    {
      "epoch": 0.011141560717013343,
      "grad_norm": 0.18473798036575317,
      "learning_rate": 3.4549150281252636e-05,
      "loss": 0.0068,
      "step": 124
    },
    {
      "epoch": 0.011231412013118289,
      "grad_norm": 1.3061293363571167,
      "learning_rate": 3.3765026539765834e-05,
      "loss": 0.0727,
      "step": 125
    },
    {
      "epoch": 0.011321263309223235,
      "grad_norm": 0.827674150466919,
      "learning_rate": 3.298534127791785e-05,
      "loss": 0.1182,
      "step": 126
    },
    {
      "epoch": 0.011411114605328182,
      "grad_norm": 1.8033653497695923,
      "learning_rate": 3.221030765387417e-05,
      "loss": 0.0416,
      "step": 127
    },
    {
      "epoch": 0.011500965901433128,
      "grad_norm": 0.8880636096000671,
      "learning_rate": 3.144013755408895e-05,
      "loss": 0.015,
      "step": 128
    },
    {
      "epoch": 0.011590817197538074,
      "grad_norm": 0.27589327096939087,
      "learning_rate": 3.0675041535377405e-05,
      "loss": 0.0695,
      "step": 129
    },
    {
      "epoch": 0.01168066849364302,
      "grad_norm": 0.7286954522132874,
      "learning_rate": 2.991522876735154e-05,
      "loss": 0.0176,
      "step": 130
    },
    {
      "epoch": 0.011770519789747967,
      "grad_norm": 0.5940603017807007,
      "learning_rate": 2.916090697523549e-05,
      "loss": 0.0625,
      "step": 131
    },
    {
      "epoch": 0.011860371085852913,
      "grad_norm": 0.3715779781341553,
      "learning_rate": 2.8412282383075363e-05,
      "loss": 0.0726,
      "step": 132
    },
    {
      "epoch": 0.01195022238195786,
      "grad_norm": 0.1934714913368225,
      "learning_rate": 2.766955965735968e-05,
      "loss": 0.0079,
      "step": 133
    },
    {
      "epoch": 0.012040073678062806,
      "grad_norm": 0.5433386564254761,
      "learning_rate": 2.693294185106562e-05,
      "loss": 0.0224,
      "step": 134
    },
    {
      "epoch": 0.012129924974167752,
      "grad_norm": 0.09182822704315186,
      "learning_rate": 2.6202630348146324e-05,
      "loss": 0.0046,
      "step": 135
    },
    {
      "epoch": 0.012219776270272698,
      "grad_norm": 0.15049512684345245,
      "learning_rate": 2.547882480847461e-05,
      "loss": 0.0077,
      "step": 136
    },
    {
      "epoch": 0.012309627566377645,
      "grad_norm": 0.7672333717346191,
      "learning_rate": 2.476172311325783e-05,
      "loss": 0.0116,
      "step": 137
    },
    {
      "epoch": 0.01239947886248259,
      "grad_norm": 2.007136821746826,
      "learning_rate": 2.405152131093926e-05,
      "loss": 0.031,
      "step": 138
    },
    {
      "epoch": 0.012489330158587537,
      "grad_norm": 0.1672549694776535,
      "learning_rate": 2.3348413563600325e-05,
      "loss": 0.0081,
      "step": 139
    },
    {
      "epoch": 0.012579181454692483,
      "grad_norm": 1.327528715133667,
      "learning_rate": 2.2652592093878666e-05,
      "loss": 0.1087,
      "step": 140
    },
    {
      "epoch": 0.01266903275079743,
      "grad_norm": 0.04769575595855713,
      "learning_rate": 2.196424713241637e-05,
      "loss": 0.0029,
      "step": 141
    },
    {
      "epoch": 0.012758884046902376,
      "grad_norm": 6.449910640716553,
      "learning_rate": 2.128356686585282e-05,
      "loss": 0.3223,
      "step": 142
    },
    {
      "epoch": 0.012848735343007322,
      "grad_norm": 0.5963060855865479,
      "learning_rate": 2.061073738537635e-05,
      "loss": 0.024,
      "step": 143
    },
    {
      "epoch": 0.012938586639112269,
      "grad_norm": 0.7222399115562439,
      "learning_rate": 1.9945942635848748e-05,
      "loss": 0.0116,
      "step": 144
    },
    {
      "epoch": 0.013028437935217215,
      "grad_norm": 1.6211422681808472,
      "learning_rate": 1.928936436551661e-05,
      "loss": 0.1589,
      "step": 145
    },
    {
      "epoch": 0.013118289231322161,
      "grad_norm": 6.503261089324951,
      "learning_rate": 1.8641182076323148e-05,
      "loss": 0.1503,
      "step": 146
    },
    {
      "epoch": 0.013208140527427107,
      "grad_norm": 4.7277655601501465,
      "learning_rate": 1.800157297483417e-05,
      "loss": 0.3816,
      "step": 147
    },
    {
      "epoch": 0.013297991823532054,
      "grad_norm": 2.368058204650879,
      "learning_rate": 1.7370711923791567e-05,
      "loss": 0.1548,
      "step": 148
    },
    {
      "epoch": 0.013387843119637,
      "grad_norm": 2.8131978511810303,
      "learning_rate": 1.6748771394307585e-05,
      "loss": 0.1363,
      "step": 149
    },
    {
      "epoch": 0.013477694415741948,
      "grad_norm": 8.33768081665039,
      "learning_rate": 1.6135921418712956e-05,
      "loss": 0.509,
      "step": 150
    },
    {
      "epoch": 0.013477694415741948,
      "eval_loss": 0.017778942361474037,
      "eval_runtime": 906.674,
      "eval_samples_per_second": 20.674,
      "eval_steps_per_second": 5.169,
      "step": 150
    },
    {
      "epoch": 0.013567545711846894,
      "grad_norm": 0.10080209374427795,
      "learning_rate": 1.553232954407171e-05,
      "loss": 0.0108,
      "step": 151
    },
    {
      "epoch": 0.01365739700795184,
      "grad_norm": 0.312481552362442,
      "learning_rate": 1.4938160786375572e-05,
      "loss": 0.0405,
      "step": 152
    },
    {
      "epoch": 0.013747248304056787,
      "grad_norm": 0.2579997777938843,
      "learning_rate": 1.435357758543015e-05,
      "loss": 0.0204,
      "step": 153
    },
    {
      "epoch": 0.013837099600161733,
      "grad_norm": 0.060103848576545715,
      "learning_rate": 1.3778739760445552e-05,
      "loss": 0.0047,
      "step": 154
    },
    {
      "epoch": 0.01392695089626668,
      "grad_norm": 0.13043758273124695,
      "learning_rate": 1.3213804466343421e-05,
      "loss": 0.0249,
      "step": 155
    },
    {
      "epoch": 0.014016802192371626,
      "grad_norm": 0.12874490022659302,
      "learning_rate": 1.2658926150792322e-05,
      "loss": 0.0077,
      "step": 156
    },
    {
      "epoch": 0.014106653488476572,
      "grad_norm": 0.26878345012664795,
      "learning_rate": 1.2114256511983274e-05,
      "loss": 0.0194,
      "step": 157
    },
    {
      "epoch": 0.014196504784581518,
      "grad_norm": 0.43331095576286316,
      "learning_rate": 1.157994445715706e-05,
      "loss": 0.0139,
      "step": 158
    },
    {
      "epoch": 0.014286356080686465,
      "grad_norm": 0.047336332499980927,
      "learning_rate": 1.1056136061894384e-05,
      "loss": 0.0035,
      "step": 159
    },
    {
      "epoch": 0.01437620737679141,
      "grad_norm": 0.28494513034820557,
      "learning_rate": 1.0542974530180327e-05,
      "loss": 0.0271,
      "step": 160
    },
    {
      "epoch": 0.014466058672896357,
      "grad_norm": 0.23257948458194733,
      "learning_rate": 1.0040600155253765e-05,
      "loss": 0.034,
      "step": 161
    },
    {
      "epoch": 0.014555909969001303,
      "grad_norm": 0.4412113130092621,
      "learning_rate": 9.549150281252633e-06,
      "loss": 0.0228,
      "step": 162
    },
    {
      "epoch": 0.01464576126510625,
      "grad_norm": 0.047674208879470825,
      "learning_rate": 9.068759265665384e-06,
      "loss": 0.0035,
      "step": 163
    },
    {
      "epoch": 0.014735612561211196,
      "grad_norm": 0.1899782121181488,
      "learning_rate": 8.599558442598998e-06,
      "loss": 0.0267,
      "step": 164
    },
    {
      "epoch": 0.014825463857316142,
      "grad_norm": 0.47985538840293884,
      "learning_rate": 8.141676086873572e-06,
      "loss": 0.0164,
      "step": 165
    },
    {
      "epoch": 0.014915315153421089,
      "grad_norm": 0.05335060879588127,
      "learning_rate": 7.695237378953223e-06,
      "loss": 0.0046,
      "step": 166
    },
    {
      "epoch": 0.015005166449526035,
      "grad_norm": 0.03223126009106636,
      "learning_rate": 7.260364370723044e-06,
      "loss": 0.0025,
      "step": 167
    },
    {
      "epoch": 0.015095017745630981,
      "grad_norm": 0.17355498671531677,
      "learning_rate": 6.837175952121306e-06,
      "loss": 0.0038,
      "step": 168
    },
    {
      "epoch": 0.015184869041735927,
      "grad_norm": 0.07277701795101166,
      "learning_rate": 6.425787818636131e-06,
      "loss": 0.005,
      "step": 169
    },
    {
      "epoch": 0.015274720337840874,
      "grad_norm": 0.5137363076210022,
      "learning_rate": 6.026312439675552e-06,
      "loss": 0.0095,
      "step": 170
    },
    {
      "epoch": 0.01536457163394582,
      "grad_norm": 0.7476804256439209,
      "learning_rate": 5.6388590278194096e-06,
      "loss": 0.0672,
      "step": 171
    },
    {
      "epoch": 0.015454422930050766,
      "grad_norm": 0.2768092453479767,
      "learning_rate": 5.263533508961827e-06,
      "loss": 0.0253,
      "step": 172
    },
    {
      "epoch": 0.015544274226155712,
      "grad_norm": 0.3162822723388672,
      "learning_rate": 4.900438493352055e-06,
      "loss": 0.0256,
      "step": 173
    },
    {
      "epoch": 0.015634125522260657,
      "grad_norm": 0.3331214189529419,
      "learning_rate": 4.549673247541875e-06,
      "loss": 0.0045,
      "step": 174
    },
    {
      "epoch": 0.015723976818365605,
      "grad_norm": 1.1327694654464722,
      "learning_rate": 4.2113336672471245e-06,
      "loss": 0.0691,
      "step": 175
    },
    {
      "epoch": 0.01581382811447055,
      "grad_norm": 0.1509418487548828,
      "learning_rate": 3.885512251130763e-06,
      "loss": 0.0072,
      "step": 176
    },
    {
      "epoch": 0.015903679410575498,
      "grad_norm": 0.04906731843948364,
      "learning_rate": 3.5722980755146517e-06,
      "loss": 0.0027,
      "step": 177
    },
    {
      "epoch": 0.015993530706680442,
      "grad_norm": 0.92961585521698,
      "learning_rate": 3.271776770026963e-06,
      "loss": 0.0656,
      "step": 178
    },
    {
      "epoch": 0.01608338200278539,
      "grad_norm": 2.2797720432281494,
      "learning_rate": 2.9840304941919415e-06,
      "loss": 0.2057,
      "step": 179
    },
    {
      "epoch": 0.016173233298890338,
      "grad_norm": 0.9214937686920166,
      "learning_rate": 2.7091379149682685e-06,
      "loss": 0.0203,
      "step": 180
    },
    {
      "epoch": 0.016263084594995283,
      "grad_norm": 0.06326153874397278,
      "learning_rate": 2.4471741852423237e-06,
      "loss": 0.0025,
      "step": 181
    },
    {
      "epoch": 0.01635293589110023,
      "grad_norm": 1.3029299974441528,
      "learning_rate": 2.1982109232821178e-06,
      "loss": 0.0769,
      "step": 182
    },
    {
      "epoch": 0.016442787187205175,
      "grad_norm": 0.2207779437303543,
      "learning_rate": 1.962316193157593e-06,
      "loss": 0.0104,
      "step": 183
    },
    {
      "epoch": 0.016532638483310123,
      "grad_norm": 0.5205898284912109,
      "learning_rate": 1.7395544861325718e-06,
      "loss": 0.0582,
      "step": 184
    },
    {
      "epoch": 0.016622489779415068,
      "grad_norm": 0.03599848225712776,
      "learning_rate": 1.5299867030334814e-06,
      "loss": 0.0023,
      "step": 185
    },
    {
      "epoch": 0.016712341075520016,
      "grad_norm": 1.8744527101516724,
      "learning_rate": 1.333670137599713e-06,
      "loss": 0.2159,
      "step": 186
    },
    {
      "epoch": 0.01680219237162496,
      "grad_norm": 0.6588272452354431,
      "learning_rate": 1.1506584608200367e-06,
      "loss": 0.0249,
      "step": 187
    },
    {
      "epoch": 0.01689204366772991,
      "grad_norm": 0.033258359879255295,
      "learning_rate": 9.810017062595322e-07,
      "loss": 0.0022,
      "step": 188
    },
    {
      "epoch": 0.016981894963834853,
      "grad_norm": 0.6500144600868225,
      "learning_rate": 8.247462563808817e-07,
      "loss": 0.0188,
      "step": 189
    },
    {
      "epoch": 0.0170717462599398,
      "grad_norm": 1.4565364122390747,
      "learning_rate": 6.819348298638839e-07,
      "loss": 0.1415,
      "step": 190
    },
    {
      "epoch": 0.017161597556044746,
      "grad_norm": 1.8110523223876953,
      "learning_rate": 5.526064699265753e-07,
      "loss": 0.1761,
      "step": 191
    },
    {
      "epoch": 0.017251448852149694,
      "grad_norm": 2.1345620155334473,
      "learning_rate": 4.367965336512403e-07,
      "loss": 0.0734,
      "step": 192
    },
    {
      "epoch": 0.017341300148254638,
      "grad_norm": 0.07298266887664795,
      "learning_rate": 3.3453668231809286e-07,
      "loss": 0.0025,
      "step": 193
    },
    {
      "epoch": 0.017431151444359586,
      "grad_norm": 0.7774335145950317,
      "learning_rate": 2.458548727494292e-07,
      "loss": 0.1058,
      "step": 194
    },
    {
      "epoch": 0.01752100274046453,
      "grad_norm": 0.24526986479759216,
      "learning_rate": 1.7077534966650766e-07,
      "loss": 0.0053,
      "step": 195
    },
    {
      "epoch": 0.01761085403656948,
      "grad_norm": 1.7338122129440308,
      "learning_rate": 1.0931863906127327e-07,
      "loss": 0.2799,
      "step": 196
    },
    {
      "epoch": 0.017700705332674423,
      "grad_norm": 1.8040050268173218,
      "learning_rate": 6.150154258476315e-08,
      "loss": 0.0754,
      "step": 197
    },
    {
      "epoch": 0.01779055662877937,
      "grad_norm": 0.5155476927757263,
      "learning_rate": 2.7337132953697554e-08,
      "loss": 0.018,
      "step": 198
    },
    {
      "epoch": 0.017880407924884316,
      "grad_norm": 3.3247833251953125,
      "learning_rate": 6.834750376549792e-09,
      "loss": 0.5668,
      "step": 199
    },
    {
      "epoch": 0.017970259220989264,
      "grad_norm": 7.674947738647461,
      "learning_rate": 0.0,
      "loss": 2.3338,
      "step": 200
    },
    {
      "epoch": 0.017970259220989264,
      "eval_loss": 0.016778385266661644,
      "eval_runtime": 906.9438,
      "eval_samples_per_second": 20.668,
      "eval_steps_per_second": 5.168,
      "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": 1.510781724131328e+17,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}