{
  "best_metric": 0.8340469002723694,
  "best_model_checkpoint": "miner_id_24/checkpoint-200",
  "epoch": 0.037778617302606725,
  "eval_steps": 50,
  "global_step": 200,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.00018889308651303362,
      "grad_norm": 0.2365526258945465,
      "learning_rate": 1e-05,
      "loss": 0.8047,
      "step": 1
    },
    {
      "epoch": 0.00018889308651303362,
      "eval_loss": 1.1662101745605469,
      "eval_runtime": 680.1893,
      "eval_samples_per_second": 13.108,
      "eval_steps_per_second": 3.277,
      "step": 1
    },
    {
      "epoch": 0.00037778617302606723,
      "grad_norm": 0.25760653614997864,
      "learning_rate": 2e-05,
      "loss": 0.8538,
      "step": 2
    },
    {
      "epoch": 0.0005666792595391009,
      "grad_norm": 0.25213247537612915,
      "learning_rate": 3e-05,
      "loss": 0.8604,
      "step": 3
    },
    {
      "epoch": 0.0007555723460521345,
      "grad_norm": 0.2592501640319824,
      "learning_rate": 4e-05,
      "loss": 0.8956,
      "step": 4
    },
    {
      "epoch": 0.0009444654325651682,
      "grad_norm": 0.22476615011692047,
      "learning_rate": 5e-05,
      "loss": 0.8862,
      "step": 5
    },
    {
      "epoch": 0.0011333585190782018,
      "grad_norm": 0.2306501716375351,
      "learning_rate": 6e-05,
      "loss": 0.7962,
      "step": 6
    },
    {
      "epoch": 0.0013222516055912353,
      "grad_norm": 0.30281689763069153,
      "learning_rate": 7e-05,
      "loss": 0.8594,
      "step": 7
    },
    {
      "epoch": 0.001511144692104269,
      "grad_norm": 0.35325440764427185,
      "learning_rate": 8e-05,
      "loss": 0.8801,
      "step": 8
    },
    {
      "epoch": 0.0017000377786173025,
      "grad_norm": 0.30120182037353516,
      "learning_rate": 9e-05,
      "loss": 0.887,
      "step": 9
    },
    {
      "epoch": 0.0018889308651303363,
      "grad_norm": 0.24626582860946655,
      "learning_rate": 0.0001,
      "loss": 0.8206,
      "step": 10
    },
    {
      "epoch": 0.00207782395164337,
      "grad_norm": 0.24035654962062836,
      "learning_rate": 9.999316524962345e-05,
      "loss": 0.8187,
      "step": 11
    },
    {
      "epoch": 0.0022667170381564035,
      "grad_norm": 0.22883300483226776,
      "learning_rate": 9.997266286704631e-05,
      "loss": 0.8408,
      "step": 12
    },
    {
      "epoch": 0.002455610124669437,
      "grad_norm": 0.2578384578227997,
      "learning_rate": 9.993849845741524e-05,
      "loss": 0.8655,
      "step": 13
    },
    {
      "epoch": 0.0026445032111824707,
      "grad_norm": 0.2670535743236542,
      "learning_rate": 9.989068136093873e-05,
      "loss": 0.8923,
      "step": 14
    },
    {
      "epoch": 0.0028333962976955043,
      "grad_norm": 0.23146213591098785,
      "learning_rate": 9.98292246503335e-05,
      "loss": 0.7943,
      "step": 15
    },
    {
      "epoch": 0.003022289384208538,
      "grad_norm": 0.2345472127199173,
      "learning_rate": 9.975414512725057e-05,
      "loss": 0.7124,
      "step": 16
    },
    {
      "epoch": 0.0032111824707215715,
      "grad_norm": 0.23258577287197113,
      "learning_rate": 9.966546331768191e-05,
      "loss": 0.8434,
      "step": 17
    },
    {
      "epoch": 0.003400075557234605,
      "grad_norm": 0.2512246072292328,
      "learning_rate": 9.956320346634876e-05,
      "loss": 0.7858,
      "step": 18
    },
    {
      "epoch": 0.0035889686437476386,
      "grad_norm": 0.27466732263565063,
      "learning_rate": 9.944739353007344e-05,
      "loss": 0.7924,
      "step": 19
    },
    {
      "epoch": 0.0037778617302606727,
      "grad_norm": 0.26982584595680237,
      "learning_rate": 9.931806517013612e-05,
      "loss": 0.8202,
      "step": 20
    },
    {
      "epoch": 0.003966754816773706,
      "grad_norm": 0.2928573191165924,
      "learning_rate": 9.917525374361912e-05,
      "loss": 0.9017,
      "step": 21
    },
    {
      "epoch": 0.00415564790328674,
      "grad_norm": 0.2863548994064331,
      "learning_rate": 9.901899829374047e-05,
      "loss": 0.8025,
      "step": 22
    },
    {
      "epoch": 0.004344540989799773,
      "grad_norm": 0.2609410285949707,
      "learning_rate": 9.884934153917997e-05,
      "loss": 0.9968,
      "step": 23
    },
    {
      "epoch": 0.004533434076312807,
      "grad_norm": 0.2783195674419403,
      "learning_rate": 9.86663298624003e-05,
      "loss": 1.0531,
      "step": 24
    },
    {
      "epoch": 0.004722327162825841,
      "grad_norm": 0.29257631301879883,
      "learning_rate": 9.847001329696653e-05,
      "loss": 1.1217,
      "step": 25
    },
    {
      "epoch": 0.004911220249338874,
      "grad_norm": 0.2476598173379898,
      "learning_rate": 9.826044551386744e-05,
      "loss": 1.2237,
      "step": 26
    },
    {
      "epoch": 0.005100113335851908,
      "grad_norm": 0.26545795798301697,
      "learning_rate": 9.803768380684242e-05,
      "loss": 1.0575,
      "step": 27
    },
    {
      "epoch": 0.005289006422364941,
      "grad_norm": 0.26557809114456177,
      "learning_rate": 9.780178907671789e-05,
      "loss": 1.0836,
      "step": 28
    },
    {
      "epoch": 0.005477899508877975,
      "grad_norm": 0.28814858198165894,
      "learning_rate": 9.755282581475769e-05,
      "loss": 1.0354,
      "step": 29
    },
    {
      "epoch": 0.0056667925953910086,
      "grad_norm": 0.316249817609787,
      "learning_rate": 9.729086208503174e-05,
      "loss": 1.1825,
      "step": 30
    },
    {
      "epoch": 0.005855685681904042,
      "grad_norm": 0.3811712861061096,
      "learning_rate": 9.701596950580806e-05,
      "loss": 1.2441,
      "step": 31
    },
    {
      "epoch": 0.006044578768417076,
      "grad_norm": 0.47901180386543274,
      "learning_rate": 9.672822322997305e-05,
      "loss": 1.0408,
      "step": 32
    },
    {
      "epoch": 0.006233471854930109,
      "grad_norm": 0.4569139778614044,
      "learning_rate": 9.642770192448536e-05,
      "loss": 1.0301,
      "step": 33
    },
    {
      "epoch": 0.006422364941443143,
      "grad_norm": 0.4628117084503174,
      "learning_rate": 9.611448774886924e-05,
      "loss": 1.0874,
      "step": 34
    },
    {
      "epoch": 0.0066112580279561765,
      "grad_norm": 0.4379255175590515,
      "learning_rate": 9.578866633275288e-05,
      "loss": 1.0898,
      "step": 35
    },
    {
      "epoch": 0.00680015111446921,
      "grad_norm": 0.3870719075202942,
      "learning_rate": 9.545032675245813e-05,
      "loss": 1.0337,
      "step": 36
    },
    {
      "epoch": 0.006989044200982244,
      "grad_norm": 0.40470239520072937,
      "learning_rate": 9.509956150664796e-05,
      "loss": 0.9495,
      "step": 37
    },
    {
      "epoch": 0.007177937287495277,
      "grad_norm": 0.46601027250289917,
      "learning_rate": 9.473646649103818e-05,
      "loss": 1.0491,
      "step": 38
    },
    {
      "epoch": 0.007366830374008312,
      "grad_norm": 0.47722557187080383,
      "learning_rate": 9.43611409721806e-05,
      "loss": 1.1242,
      "step": 39
    },
    {
      "epoch": 0.007555723460521345,
      "grad_norm": 0.392415851354599,
      "learning_rate": 9.397368756032445e-05,
      "loss": 0.9221,
      "step": 40
    },
    {
      "epoch": 0.007744616547034379,
      "grad_norm": 0.4962768852710724,
      "learning_rate": 9.357421218136386e-05,
      "loss": 0.957,
      "step": 41
    },
    {
      "epoch": 0.007933509633547412,
      "grad_norm": 0.5256131291389465,
      "learning_rate": 9.316282404787871e-05,
      "loss": 0.9528,
      "step": 42
    },
    {
      "epoch": 0.008122402720060446,
      "grad_norm": 0.5197751522064209,
      "learning_rate": 9.273963562927695e-05,
      "loss": 1.0529,
      "step": 43
    },
    {
      "epoch": 0.00831129580657348,
      "grad_norm": 0.5906340479850769,
      "learning_rate": 9.230476262104677e-05,
      "loss": 1.0416,
      "step": 44
    },
    {
      "epoch": 0.008500188893086513,
      "grad_norm": 0.6508529186248779,
      "learning_rate": 9.185832391312644e-05,
      "loss": 0.9649,
      "step": 45
    },
    {
      "epoch": 0.008689081979599547,
      "grad_norm": 0.5225167870521545,
      "learning_rate": 9.140044155740101e-05,
      "loss": 0.7859,
      "step": 46
    },
    {
      "epoch": 0.00887797506611258,
      "grad_norm": 0.6129855513572693,
      "learning_rate": 9.093124073433463e-05,
      "loss": 0.8274,
      "step": 47
    },
    {
      "epoch": 0.009066868152625614,
      "grad_norm": 0.6664934754371643,
      "learning_rate": 9.045084971874738e-05,
      "loss": 1.0285,
      "step": 48
    },
    {
      "epoch": 0.009255761239138648,
      "grad_norm": 1.0035603046417236,
      "learning_rate": 8.995939984474624e-05,
      "loss": 0.8315,
      "step": 49
    },
    {
      "epoch": 0.009444654325651681,
      "grad_norm": 0.9724960923194885,
      "learning_rate": 8.945702546981969e-05,
      "loss": 0.8103,
      "step": 50
    },
    {
      "epoch": 0.009444654325651681,
      "eval_loss": 0.9625772833824158,
      "eval_runtime": 684.5183,
      "eval_samples_per_second": 13.025,
      "eval_steps_per_second": 3.256,
      "step": 50
    },
    {
      "epoch": 0.009633547412164715,
      "grad_norm": 0.6039254069328308,
      "learning_rate": 8.894386393810563e-05,
      "loss": 0.7947,
      "step": 51
    },
    {
      "epoch": 0.009822440498677748,
      "grad_norm": 0.5020398497581482,
      "learning_rate": 8.842005554284296e-05,
      "loss": 0.8942,
      "step": 52
    },
    {
      "epoch": 0.010011333585190782,
      "grad_norm": 0.32938215136528015,
      "learning_rate": 8.788574348801675e-05,
      "loss": 0.8416,
      "step": 53
    },
    {
      "epoch": 0.010200226671703816,
      "grad_norm": 0.2480783462524414,
      "learning_rate": 8.73410738492077e-05,
      "loss": 0.803,
      "step": 54
    },
    {
      "epoch": 0.01038911975821685,
      "grad_norm": 0.23534205555915833,
      "learning_rate": 8.678619553365659e-05,
      "loss": 0.7567,
      "step": 55
    },
    {
      "epoch": 0.010578012844729883,
      "grad_norm": 0.22843892872333527,
      "learning_rate": 8.622126023955446e-05,
      "loss": 0.7609,
      "step": 56
    },
    {
      "epoch": 0.010766905931242916,
      "grad_norm": 0.215877965092659,
      "learning_rate": 8.564642241456986e-05,
      "loss": 0.7846,
      "step": 57
    },
    {
      "epoch": 0.01095579901775595,
      "grad_norm": 0.20943300426006317,
      "learning_rate": 8.506183921362443e-05,
      "loss": 0.7764,
      "step": 58
    },
    {
      "epoch": 0.011144692104268984,
      "grad_norm": 0.21023142337799072,
      "learning_rate": 8.44676704559283e-05,
      "loss": 0.8044,
      "step": 59
    },
    {
      "epoch": 0.011333585190782017,
      "grad_norm": 0.1964731216430664,
      "learning_rate": 8.386407858128706e-05,
      "loss": 0.7931,
      "step": 60
    },
    {
      "epoch": 0.01152247827729505,
      "grad_norm": 0.19113020598888397,
      "learning_rate": 8.32512286056924e-05,
      "loss": 0.7401,
      "step": 61
    },
    {
      "epoch": 0.011711371363808084,
      "grad_norm": 0.19157230854034424,
      "learning_rate": 8.262928807620843e-05,
      "loss": 0.742,
      "step": 62
    },
    {
      "epoch": 0.011900264450321118,
      "grad_norm": 0.2000613957643509,
      "learning_rate": 8.199842702516583e-05,
      "loss": 0.7201,
      "step": 63
    },
    {
      "epoch": 0.012089157536834151,
      "grad_norm": 0.22514985501766205,
      "learning_rate": 8.135881792367686e-05,
      "loss": 0.8257,
      "step": 64
    },
    {
      "epoch": 0.012278050623347185,
      "grad_norm": 0.21435140073299408,
      "learning_rate": 8.07106356344834e-05,
      "loss": 0.7816,
      "step": 65
    },
    {
      "epoch": 0.012466943709860219,
      "grad_norm": 0.2407785803079605,
      "learning_rate": 8.005405736415126e-05,
      "loss": 0.7715,
      "step": 66
    },
    {
      "epoch": 0.012655836796373252,
      "grad_norm": 0.23289081454277039,
      "learning_rate": 7.938926261462366e-05,
      "loss": 0.6712,
      "step": 67
    },
    {
      "epoch": 0.012844729882886286,
      "grad_norm": 0.2270701676607132,
      "learning_rate": 7.871643313414718e-05,
      "loss": 0.7137,
      "step": 68
    },
    {
      "epoch": 0.01303362296939932,
      "grad_norm": 0.250667542219162,
      "learning_rate": 7.803575286758364e-05,
      "loss": 0.7182,
      "step": 69
    },
    {
      "epoch": 0.013222516055912353,
      "grad_norm": 0.26808521151542664,
      "learning_rate": 7.734740790612136e-05,
      "loss": 0.7709,
      "step": 70
    },
    {
      "epoch": 0.013411409142425387,
      "grad_norm": 0.33871325850486755,
      "learning_rate": 7.66515864363997e-05,
      "loss": 0.8712,
      "step": 71
    },
    {
      "epoch": 0.01360030222893842,
      "grad_norm": 0.36736801266670227,
      "learning_rate": 7.594847868906076e-05,
      "loss": 0.9743,
      "step": 72
    },
    {
      "epoch": 0.013789195315451454,
      "grad_norm": 0.38367268443107605,
      "learning_rate": 7.52382768867422e-05,
      "loss": 1.0487,
      "step": 73
    },
    {
      "epoch": 0.013978088401964487,
      "grad_norm": 0.31157296895980835,
      "learning_rate": 7.452117519152542e-05,
      "loss": 1.045,
      "step": 74
    },
    {
      "epoch": 0.014166981488477521,
      "grad_norm": 0.30637556314468384,
      "learning_rate": 7.379736965185368e-05,
      "loss": 0.8609,
      "step": 75
    },
    {
      "epoch": 0.014355874574990555,
      "grad_norm": 0.35716745257377625,
      "learning_rate": 7.30670581489344e-05,
      "loss": 1.0383,
      "step": 76
    },
    {
      "epoch": 0.014544767661503588,
      "grad_norm": 0.27694424986839294,
      "learning_rate": 7.233044034264034e-05,
      "loss": 1.0066,
      "step": 77
    },
    {
      "epoch": 0.014733660748016623,
      "grad_norm": 0.2513771653175354,
      "learning_rate": 7.158771761692464e-05,
      "loss": 0.9385,
      "step": 78
    },
    {
      "epoch": 0.014922553834529657,
      "grad_norm": 0.33505845069885254,
      "learning_rate": 7.083909302476453e-05,
      "loss": 0.9246,
      "step": 79
    },
    {
      "epoch": 0.01511144692104269,
      "grad_norm": 0.32148250937461853,
      "learning_rate": 7.008477123264848e-05,
      "loss": 1.0222,
      "step": 80
    },
    {
      "epoch": 0.015300340007555724,
      "grad_norm": 0.3722675144672394,
      "learning_rate": 6.932495846462261e-05,
      "loss": 1.1772,
      "step": 81
    },
    {
      "epoch": 0.015489233094068758,
      "grad_norm": 0.36733385920524597,
      "learning_rate": 6.855986244591104e-05,
      "loss": 0.9825,
      "step": 82
    },
    {
      "epoch": 0.01567812618058179,
      "grad_norm": 0.36384737491607666,
      "learning_rate": 6.778969234612584e-05,
      "loss": 0.9794,
      "step": 83
    },
    {
      "epoch": 0.015867019267094825,
      "grad_norm": 0.36260420083999634,
      "learning_rate": 6.701465872208216e-05,
      "loss": 1.0312,
      "step": 84
    },
    {
      "epoch": 0.016055912353607857,
      "grad_norm": 0.34085217118263245,
      "learning_rate": 6.623497346023418e-05,
      "loss": 0.936,
      "step": 85
    },
    {
      "epoch": 0.016244805440120892,
      "grad_norm": 0.3456466495990753,
      "learning_rate": 6.545084971874738e-05,
      "loss": 1.0809,
      "step": 86
    },
    {
      "epoch": 0.016433698526633924,
      "grad_norm": 0.3374823033809662,
      "learning_rate": 6.466250186922325e-05,
      "loss": 0.9306,
      "step": 87
    },
    {
      "epoch": 0.01662259161314696,
      "grad_norm": 0.3832341432571411,
      "learning_rate": 6.387014543809223e-05,
      "loss": 1.0203,
      "step": 88
    },
    {
      "epoch": 0.01681148469965999,
      "grad_norm": 0.4110691547393799,
      "learning_rate": 6.307399704769099e-05,
      "loss": 0.9777,
      "step": 89
    },
    {
      "epoch": 0.017000377786173027,
      "grad_norm": 0.45048367977142334,
      "learning_rate": 6.227427435703997e-05,
      "loss": 1.1184,
      "step": 90
    },
    {
      "epoch": 0.01718927087268606,
      "grad_norm": 0.45625239610671997,
      "learning_rate": 6.147119600233758e-05,
      "loss": 1.0255,
      "step": 91
    },
    {
      "epoch": 0.017378163959199094,
      "grad_norm": 0.4320775270462036,
      "learning_rate": 6.066498153718735e-05,
      "loss": 1.0618,
      "step": 92
    },
    {
      "epoch": 0.017567057045712126,
      "grad_norm": 0.4299164116382599,
      "learning_rate": 5.985585137257401e-05,
      "loss": 1.0335,
      "step": 93
    },
    {
      "epoch": 0.01775595013222516,
      "grad_norm": 0.43909603357315063,
      "learning_rate": 5.90440267166055e-05,
      "loss": 0.9414,
      "step": 94
    },
    {
      "epoch": 0.017944843218738193,
      "grad_norm": 0.4726046919822693,
      "learning_rate": 5.8229729514036705e-05,
      "loss": 0.9477,
      "step": 95
    },
    {
      "epoch": 0.018133736305251228,
      "grad_norm": 0.49260762333869934,
      "learning_rate": 5.74131823855921e-05,
      "loss": 0.8155,
      "step": 96
    },
    {
      "epoch": 0.01832262939176426,
      "grad_norm": 0.5460562705993652,
      "learning_rate": 5.6594608567103456e-05,
      "loss": 0.957,
      "step": 97
    },
    {
      "epoch": 0.018511522478277295,
      "grad_norm": 0.5830492377281189,
      "learning_rate": 5.577423184847932e-05,
      "loss": 0.7284,
      "step": 98
    },
    {
      "epoch": 0.018700415564790327,
      "grad_norm": 1.008601188659668,
      "learning_rate": 5.495227651252315e-05,
      "loss": 0.95,
      "step": 99
    },
    {
      "epoch": 0.018889308651303362,
      "grad_norm": 1.1210812330245972,
      "learning_rate": 5.4128967273616625e-05,
      "loss": 0.9971,
      "step": 100
    },
    {
      "epoch": 0.018889308651303362,
      "eval_loss": 0.8739294409751892,
      "eval_runtime": 683.7536,
      "eval_samples_per_second": 13.04,
      "eval_steps_per_second": 3.26,
      "step": 100
    },
    {
      "epoch": 0.019078201737816394,
      "grad_norm": 0.2663755416870117,
      "learning_rate": 5.330452921628497e-05,
      "loss": 0.7277,
      "step": 101
    },
    {
      "epoch": 0.01926709482432943,
      "grad_norm": 0.2440682053565979,
      "learning_rate": 5.247918773366112e-05,
      "loss": 0.7907,
      "step": 102
    },
    {
      "epoch": 0.01945598791084246,
      "grad_norm": 0.22063758969306946,
      "learning_rate": 5.165316846586541e-05,
      "loss": 0.7859,
      "step": 103
    },
    {
      "epoch": 0.019644880997355497,
      "grad_norm": 0.21121470630168915,
      "learning_rate": 5.0826697238317935e-05,
      "loss": 0.7497,
      "step": 104
    },
    {
      "epoch": 0.019833774083868532,
      "grad_norm": 0.19087187945842743,
      "learning_rate": 5e-05,
      "loss": 0.7711,
      "step": 105
    },
    {
      "epoch": 0.020022667170381564,
      "grad_norm": 0.18585823476314545,
      "learning_rate": 4.917330276168208e-05,
      "loss": 0.7721,
      "step": 106
    },
    {
      "epoch": 0.0202115602568946,
      "grad_norm": 0.19607923924922943,
      "learning_rate": 4.834683153413459e-05,
      "loss": 0.7797,
      "step": 107
    },
    {
      "epoch": 0.02040045334340763,
      "grad_norm": 0.1984383910894394,
      "learning_rate": 4.7520812266338885e-05,
      "loss": 0.7016,
      "step": 108
    },
    {
      "epoch": 0.020589346429920666,
      "grad_norm": 0.20382624864578247,
      "learning_rate": 4.669547078371504e-05,
      "loss": 0.803,
      "step": 109
    },
    {
      "epoch": 0.0207782395164337,
      "grad_norm": 0.1814393252134323,
      "learning_rate": 4.5871032726383386e-05,
      "loss": 0.7532,
      "step": 110
    },
    {
      "epoch": 0.020967132602946734,
      "grad_norm": 0.1894480139017105,
      "learning_rate": 4.504772348747687e-05,
      "loss": 0.7371,
      "step": 111
    },
    {
      "epoch": 0.021156025689459765,
      "grad_norm": 0.20538750290870667,
      "learning_rate": 4.4225768151520694e-05,
      "loss": 0.7314,
      "step": 112
    },
    {
      "epoch": 0.0213449187759728,
      "grad_norm": 0.18640796840190887,
      "learning_rate": 4.3405391432896555e-05,
      "loss": 0.7238,
      "step": 113
    },
    {
      "epoch": 0.021533811862485833,
      "grad_norm": 0.19289430975914001,
      "learning_rate": 4.2586817614407895e-05,
      "loss": 0.7265,
      "step": 114
    },
    {
      "epoch": 0.021722704948998868,
      "grad_norm": 0.19596557319164276,
      "learning_rate": 4.17702704859633e-05,
      "loss": 0.7495,
      "step": 115
    },
    {
      "epoch": 0.0219115980355119,
      "grad_norm": 0.21075484156608582,
      "learning_rate": 4.095597328339452e-05,
      "loss": 0.6892,
      "step": 116
    },
    {
      "epoch": 0.022100491122024935,
      "grad_norm": 0.21976560354232788,
      "learning_rate": 4.0144148627425993e-05,
      "loss": 0.7421,
      "step": 117
    },
    {
      "epoch": 0.022289384208537967,
      "grad_norm": 0.26314544677734375,
      "learning_rate": 3.933501846281267e-05,
      "loss": 0.8357,
      "step": 118
    },
    {
      "epoch": 0.022478277295051002,
      "grad_norm": 0.2347910851240158,
      "learning_rate": 3.852880399766243e-05,
      "loss": 0.8239,
      "step": 119
    },
    {
      "epoch": 0.022667170381564034,
      "grad_norm": 0.2701406478881836,
      "learning_rate": 3.772572564296005e-05,
      "loss": 0.8439,
      "step": 120
    },
    {
      "epoch": 0.02285606346807707,
      "grad_norm": 0.31313392519950867,
      "learning_rate": 3.6926002952309016e-05,
      "loss": 0.8315,
      "step": 121
    },
    {
      "epoch": 0.0230449565545901,
      "grad_norm": 0.29862433671951294,
      "learning_rate": 3.612985456190778e-05,
      "loss": 0.8799,
      "step": 122
    },
    {
      "epoch": 0.023233849641103137,
      "grad_norm": 0.30738958716392517,
      "learning_rate": 3.533749813077677e-05,
      "loss": 0.9597,
      "step": 123
    },
    {
      "epoch": 0.02342274272761617,
      "grad_norm": 0.3207195997238159,
      "learning_rate": 3.4549150281252636e-05,
      "loss": 0.9804,
      "step": 124
    },
    {
      "epoch": 0.023611635814129204,
      "grad_norm": 0.363346129655838,
      "learning_rate": 3.3765026539765834e-05,
      "loss": 0.9653,
      "step": 125
    },
    {
      "epoch": 0.023800528900642236,
      "grad_norm": 0.3312750458717346,
      "learning_rate": 3.298534127791785e-05,
      "loss": 1.1009,
      "step": 126
    },
    {
      "epoch": 0.02398942198715527,
      "grad_norm": 0.33067265152931213,
      "learning_rate": 3.221030765387417e-05,
      "loss": 0.9755,
      "step": 127
    },
    {
      "epoch": 0.024178315073668303,
      "grad_norm": 0.336321085691452,
      "learning_rate": 3.144013755408895e-05,
      "loss": 0.938,
      "step": 128
    },
    {
      "epoch": 0.024367208160181338,
      "grad_norm": 0.3281109631061554,
      "learning_rate": 3.0675041535377405e-05,
      "loss": 1.0373,
      "step": 129
    },
    {
      "epoch": 0.02455610124669437,
      "grad_norm": 0.3369291126728058,
      "learning_rate": 2.991522876735154e-05,
      "loss": 1.0944,
      "step": 130
    },
    {
      "epoch": 0.024744994333207405,
      "grad_norm": 0.33766067028045654,
      "learning_rate": 2.916090697523549e-05,
      "loss": 1.0389,
      "step": 131
    },
    {
      "epoch": 0.024933887419720437,
      "grad_norm": 0.34034523367881775,
      "learning_rate": 2.8412282383075363e-05,
      "loss": 1.0102,
      "step": 132
    },
    {
      "epoch": 0.025122780506233473,
      "grad_norm": 0.3260619044303894,
      "learning_rate": 2.766955965735968e-05,
      "loss": 0.9467,
      "step": 133
    },
    {
      "epoch": 0.025311673592746504,
      "grad_norm": 0.3526521623134613,
      "learning_rate": 2.693294185106562e-05,
      "loss": 0.904,
      "step": 134
    },
    {
      "epoch": 0.02550056667925954,
      "grad_norm": 0.37381765246391296,
      "learning_rate": 2.6202630348146324e-05,
      "loss": 1.0147,
      "step": 135
    },
    {
      "epoch": 0.02568945976577257,
      "grad_norm": 0.3538430631160736,
      "learning_rate": 2.547882480847461e-05,
      "loss": 0.9958,
      "step": 136
    },
    {
      "epoch": 0.025878352852285607,
      "grad_norm": 0.349799245595932,
      "learning_rate": 2.476172311325783e-05,
      "loss": 1.0473,
      "step": 137
    },
    {
      "epoch": 0.02606724593879864,
      "grad_norm": 0.3795941174030304,
      "learning_rate": 2.405152131093926e-05,
      "loss": 0.9772,
      "step": 138
    },
    {
      "epoch": 0.026256139025311674,
      "grad_norm": 0.3527810275554657,
      "learning_rate": 2.3348413563600325e-05,
      "loss": 0.9225,
      "step": 139
    },
    {
      "epoch": 0.026445032111824706,
      "grad_norm": 0.3993825316429138,
      "learning_rate": 2.2652592093878666e-05,
      "loss": 1.0339,
      "step": 140
    },
    {
      "epoch": 0.02663392519833774,
      "grad_norm": 0.39415210485458374,
      "learning_rate": 2.196424713241637e-05,
      "loss": 0.9485,
      "step": 141
    },
    {
      "epoch": 0.026822818284850773,
      "grad_norm": 0.4297633469104767,
      "learning_rate": 2.128356686585282e-05,
      "loss": 0.9148,
      "step": 142
    },
    {
      "epoch": 0.02701171137136381,
      "grad_norm": 0.469872385263443,
      "learning_rate": 2.061073738537635e-05,
      "loss": 0.9611,
      "step": 143
    },
    {
      "epoch": 0.02720060445787684,
      "grad_norm": 0.45051535964012146,
      "learning_rate": 1.9945942635848748e-05,
      "loss": 0.9085,
      "step": 144
    },
    {
      "epoch": 0.027389497544389876,
      "grad_norm": 0.5274796485900879,
      "learning_rate": 1.928936436551661e-05,
      "loss": 0.9168,
      "step": 145
    },
    {
      "epoch": 0.027578390630902908,
      "grad_norm": 0.5532828569412231,
      "learning_rate": 1.8641182076323148e-05,
      "loss": 0.7323,
      "step": 146
    },
    {
      "epoch": 0.027767283717415943,
      "grad_norm": 0.5611801743507385,
      "learning_rate": 1.800157297483417e-05,
      "loss": 0.825,
      "step": 147
    },
    {
      "epoch": 0.027956176803928975,
      "grad_norm": 0.6933366656303406,
      "learning_rate": 1.7370711923791567e-05,
      "loss": 0.6398,
      "step": 148
    },
    {
      "epoch": 0.02814506989044201,
      "grad_norm": 0.7904859185218811,
      "learning_rate": 1.6748771394307585e-05,
      "loss": 0.6446,
      "step": 149
    },
    {
      "epoch": 0.028333962976955042,
      "grad_norm": 1.0897783041000366,
      "learning_rate": 1.6135921418712956e-05,
      "loss": 0.9363,
      "step": 150
    },
    {
      "epoch": 0.028333962976955042,
      "eval_loss": 0.8392544984817505,
      "eval_runtime": 684.1928,
      "eval_samples_per_second": 13.031,
      "eval_steps_per_second": 3.258,
      "step": 150
    },
    {
      "epoch": 0.028522856063468077,
      "grad_norm": 0.18557631969451904,
      "learning_rate": 1.553232954407171e-05,
      "loss": 0.7137,
      "step": 151
    },
    {
      "epoch": 0.02871174914998111,
      "grad_norm": 0.18314556777477264,
      "learning_rate": 1.4938160786375572e-05,
      "loss": 0.7358,
      "step": 152
    },
    {
      "epoch": 0.028900642236494144,
      "grad_norm": 0.18942657113075256,
      "learning_rate": 1.435357758543015e-05,
      "loss": 0.7487,
      "step": 153
    },
    {
      "epoch": 0.029089535323007176,
      "grad_norm": 0.18606656789779663,
      "learning_rate": 1.3778739760445552e-05,
      "loss": 0.6791,
      "step": 154
    },
    {
      "epoch": 0.02927842840952021,
      "grad_norm": 0.19102618098258972,
      "learning_rate": 1.3213804466343421e-05,
      "loss": 0.7564,
      "step": 155
    },
    {
      "epoch": 0.029467321496033247,
      "grad_norm": 0.19206982851028442,
      "learning_rate": 1.2658926150792322e-05,
      "loss": 0.6811,
      "step": 156
    },
    {
      "epoch": 0.02965621458254628,
      "grad_norm": 0.21195319294929504,
      "learning_rate": 1.2114256511983274e-05,
      "loss": 0.7301,
      "step": 157
    },
    {
      "epoch": 0.029845107669059314,
      "grad_norm": 0.19442345201969147,
      "learning_rate": 1.157994445715706e-05,
      "loss": 0.6653,
      "step": 158
    },
    {
      "epoch": 0.030034000755572346,
      "grad_norm": 0.20352543890476227,
      "learning_rate": 1.1056136061894384e-05,
      "loss": 0.7339,
      "step": 159
    },
    {
      "epoch": 0.03022289384208538,
      "grad_norm": 0.19563524425029755,
      "learning_rate": 1.0542974530180327e-05,
      "loss": 0.719,
      "step": 160
    },
    {
      "epoch": 0.030411786928598413,
      "grad_norm": 0.20714694261550903,
      "learning_rate": 1.0040600155253765e-05,
      "loss": 0.7167,
      "step": 161
    },
    {
      "epoch": 0.03060068001511145,
      "grad_norm": 0.22485299408435822,
      "learning_rate": 9.549150281252633e-06,
      "loss": 0.736,
      "step": 162
    },
    {
      "epoch": 0.03078957310162448,
      "grad_norm": 0.21638621389865875,
      "learning_rate": 9.068759265665384e-06,
      "loss": 0.7712,
      "step": 163
    },
    {
      "epoch": 0.030978466188137516,
      "grad_norm": 0.2256501317024231,
      "learning_rate": 8.599558442598998e-06,
      "loss": 0.7546,
      "step": 164
    },
    {
      "epoch": 0.031167359274650547,
      "grad_norm": 0.21444948017597198,
      "learning_rate": 8.141676086873572e-06,
      "loss": 0.7444,
      "step": 165
    },
    {
      "epoch": 0.03135625236116358,
      "grad_norm": 0.24297460913658142,
      "learning_rate": 7.695237378953223e-06,
      "loss": 0.6502,
      "step": 166
    },
    {
      "epoch": 0.031545145447676615,
      "grad_norm": 0.2639843821525574,
      "learning_rate": 7.260364370723044e-06,
      "loss": 0.7096,
      "step": 167
    },
    {
      "epoch": 0.03173403853418965,
      "grad_norm": 0.24791322648525238,
      "learning_rate": 6.837175952121306e-06,
      "loss": 0.6803,
      "step": 168
    },
    {
      "epoch": 0.031922931620702685,
      "grad_norm": 0.2526553273200989,
      "learning_rate": 6.425787818636131e-06,
      "loss": 0.7499,
      "step": 169
    },
    {
      "epoch": 0.032111824707215714,
      "grad_norm": 0.28135135769844055,
      "learning_rate": 6.026312439675552e-06,
      "loss": 0.8043,
      "step": 170
    },
    {
      "epoch": 0.03230071779372875,
      "grad_norm": 0.29138562083244324,
      "learning_rate": 5.6388590278194096e-06,
      "loss": 0.8423,
      "step": 171
    },
    {
      "epoch": 0.032489610880241784,
      "grad_norm": 0.3155459463596344,
      "learning_rate": 5.263533508961827e-06,
      "loss": 0.8951,
      "step": 172
    },
    {
      "epoch": 0.03267850396675482,
      "grad_norm": 0.30968669056892395,
      "learning_rate": 4.900438493352055e-06,
      "loss": 0.9254,
      "step": 173
    },
    {
      "epoch": 0.03286739705326785,
      "grad_norm": 0.32539382576942444,
      "learning_rate": 4.549673247541875e-06,
      "loss": 0.9078,
      "step": 174
    },
    {
      "epoch": 0.03305629013978088,
      "grad_norm": 0.3305417001247406,
      "learning_rate": 4.2113336672471245e-06,
      "loss": 0.8918,
      "step": 175
    },
    {
      "epoch": 0.03324518322629392,
      "grad_norm": 0.3253591060638428,
      "learning_rate": 3.885512251130763e-06,
      "loss": 1.0398,
      "step": 176
    },
    {
      "epoch": 0.033434076312806954,
      "grad_norm": 0.3353084921836853,
      "learning_rate": 3.5722980755146517e-06,
      "loss": 0.9624,
      "step": 177
    },
    {
      "epoch": 0.03362296939931998,
      "grad_norm": 0.3261201083660126,
      "learning_rate": 3.271776770026963e-06,
      "loss": 0.959,
      "step": 178
    },
    {
      "epoch": 0.03381186248583302,
      "grad_norm": 0.3118917644023895,
      "learning_rate": 2.9840304941919415e-06,
      "loss": 0.9395,
      "step": 179
    },
    {
      "epoch": 0.03400075557234605,
      "grad_norm": 0.3256894052028656,
      "learning_rate": 2.7091379149682685e-06,
      "loss": 0.9747,
      "step": 180
    },
    {
      "epoch": 0.03418964865885909,
      "grad_norm": 0.43814370036125183,
      "learning_rate": 2.4471741852423237e-06,
      "loss": 0.978,
      "step": 181
    },
    {
      "epoch": 0.03437854174537212,
      "grad_norm": 0.3633352816104889,
      "learning_rate": 2.1982109232821178e-06,
      "loss": 1.0443,
      "step": 182
    },
    {
      "epoch": 0.03456743483188515,
      "grad_norm": 0.38509902358055115,
      "learning_rate": 1.962316193157593e-06,
      "loss": 1.1039,
      "step": 183
    },
    {
      "epoch": 0.03475632791839819,
      "grad_norm": 0.3899953067302704,
      "learning_rate": 1.7395544861325718e-06,
      "loss": 0.9487,
      "step": 184
    },
    {
      "epoch": 0.03494522100491122,
      "grad_norm": 0.3715680241584778,
      "learning_rate": 1.5299867030334814e-06,
      "loss": 1.0049,
      "step": 185
    },
    {
      "epoch": 0.03513411409142425,
      "grad_norm": 0.35529640316963196,
      "learning_rate": 1.333670137599713e-06,
      "loss": 0.9963,
      "step": 186
    },
    {
      "epoch": 0.035323007177937286,
      "grad_norm": 0.37186896800994873,
      "learning_rate": 1.1506584608200367e-06,
      "loss": 1.0285,
      "step": 187
    },
    {
      "epoch": 0.03551190026445032,
      "grad_norm": 0.36430537700653076,
      "learning_rate": 9.810017062595322e-07,
      "loss": 0.8947,
      "step": 188
    },
    {
      "epoch": 0.03570079335096336,
      "grad_norm": 0.40131473541259766,
      "learning_rate": 8.247462563808817e-07,
      "loss": 1.0366,
      "step": 189
    },
    {
      "epoch": 0.035889686437476385,
      "grad_norm": 0.39426207542419434,
      "learning_rate": 6.819348298638839e-07,
      "loss": 0.9157,
      "step": 190
    },
    {
      "epoch": 0.03607857952398942,
      "grad_norm": 0.39184221625328064,
      "learning_rate": 5.526064699265753e-07,
      "loss": 0.9106,
      "step": 191
    },
    {
      "epoch": 0.036267472610502456,
      "grad_norm": 0.40606141090393066,
      "learning_rate": 4.367965336512403e-07,
      "loss": 1.0535,
      "step": 192
    },
    {
      "epoch": 0.03645636569701549,
      "grad_norm": 0.4045559763908386,
      "learning_rate": 3.3453668231809286e-07,
      "loss": 0.9366,
      "step": 193
    },
    {
      "epoch": 0.03664525878352852,
      "grad_norm": 0.4183933138847351,
      "learning_rate": 2.458548727494292e-07,
      "loss": 0.8466,
      "step": 194
    },
    {
      "epoch": 0.036834151870041555,
      "grad_norm": 0.4623907804489136,
      "learning_rate": 1.7077534966650766e-07,
      "loss": 0.9692,
      "step": 195
    },
    {
      "epoch": 0.03702304495655459,
      "grad_norm": 0.4654881954193115,
      "learning_rate": 1.0931863906127327e-07,
      "loss": 0.8566,
      "step": 196
    },
    {
      "epoch": 0.037211938043067626,
      "grad_norm": 0.5641815066337585,
      "learning_rate": 6.150154258476315e-08,
      "loss": 0.9895,
      "step": 197
    },
    {
      "epoch": 0.037400831129580654,
      "grad_norm": 0.6316211223602295,
      "learning_rate": 2.7337132953697554e-08,
      "loss": 0.8973,
      "step": 198
    },
    {
      "epoch": 0.03758972421609369,
      "grad_norm": 0.7114399671554565,
      "learning_rate": 6.834750376549792e-09,
      "loss": 0.7913,
      "step": 199
    },
    {
      "epoch": 0.037778617302606725,
      "grad_norm": 1.0434236526489258,
      "learning_rate": 0.0,
      "loss": 1.1422,
      "step": 200
    },
    {
      "epoch": 0.037778617302606725,
      "eval_loss": 0.8340469002723694,
      "eval_runtime": 684.8847,
      "eval_samples_per_second": 13.018,
      "eval_steps_per_second": 3.255,
      "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": 2.8672183935329894e+17,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}