{
  "best_metric": 12.420499801635742,
  "best_model_checkpoint": "miner_id_24/checkpoint-200",
  "epoch": 0.19029495718363462,
  "eval_steps": 50,
  "global_step": 200,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0009514747859181732,
      "grad_norm": 0.010148156434297562,
      "learning_rate": 1e-05,
      "loss": 12.4569,
      "step": 1
    },
    {
      "epoch": 0.0009514747859181732,
      "eval_loss": 12.457457542419434,
      "eval_runtime": 15.4829,
      "eval_samples_per_second": 114.32,
      "eval_steps_per_second": 28.612,
      "step": 1
    },
    {
      "epoch": 0.0019029495718363464,
      "grad_norm": 0.00874076597392559,
      "learning_rate": 2e-05,
      "loss": 12.4583,
      "step": 2
    },
    {
      "epoch": 0.0028544243577545195,
      "grad_norm": 0.00966893881559372,
      "learning_rate": 3e-05,
      "loss": 12.4593,
      "step": 3
    },
    {
      "epoch": 0.003805899143672693,
      "grad_norm": 0.008433160372078419,
      "learning_rate": 4e-05,
      "loss": 12.4592,
      "step": 4
    },
    {
      "epoch": 0.004757373929590866,
      "grad_norm": 0.009546985849738121,
      "learning_rate": 5e-05,
      "loss": 12.459,
      "step": 5
    },
    {
      "epoch": 0.005708848715509039,
      "grad_norm": 0.009319175966084003,
      "learning_rate": 6e-05,
      "loss": 12.4583,
      "step": 6
    },
    {
      "epoch": 0.006660323501427212,
      "grad_norm": 0.008564868941903114,
      "learning_rate": 7e-05,
      "loss": 12.4579,
      "step": 7
    },
    {
      "epoch": 0.007611798287345386,
      "grad_norm": 0.009465880692005157,
      "learning_rate": 8e-05,
      "loss": 12.4592,
      "step": 8
    },
    {
      "epoch": 0.008563273073263558,
      "grad_norm": 0.008005841635167599,
      "learning_rate": 9e-05,
      "loss": 12.4569,
      "step": 9
    },
    {
      "epoch": 0.009514747859181731,
      "grad_norm": 0.007771589327603579,
      "learning_rate": 0.0001,
      "loss": 12.4589,
      "step": 10
    },
    {
      "epoch": 0.010466222645099905,
      "grad_norm": 0.007404860574752092,
      "learning_rate": 9.999316524962345e-05,
      "loss": 12.457,
      "step": 11
    },
    {
      "epoch": 0.011417697431018078,
      "grad_norm": 0.008672460913658142,
      "learning_rate": 9.997266286704631e-05,
      "loss": 12.459,
      "step": 12
    },
    {
      "epoch": 0.012369172216936251,
      "grad_norm": 0.00864437036216259,
      "learning_rate": 9.993849845741524e-05,
      "loss": 12.4591,
      "step": 13
    },
    {
      "epoch": 0.013320647002854425,
      "grad_norm": 0.00821571797132492,
      "learning_rate": 9.989068136093873e-05,
      "loss": 12.4586,
      "step": 14
    },
    {
      "epoch": 0.014272121788772598,
      "grad_norm": 0.007817390374839306,
      "learning_rate": 9.98292246503335e-05,
      "loss": 12.4583,
      "step": 15
    },
    {
      "epoch": 0.015223596574690771,
      "grad_norm": 0.00932572316378355,
      "learning_rate": 9.975414512725057e-05,
      "loss": 12.4583,
      "step": 16
    },
    {
      "epoch": 0.016175071360608945,
      "grad_norm": 0.009060027077794075,
      "learning_rate": 9.966546331768191e-05,
      "loss": 12.4566,
      "step": 17
    },
    {
      "epoch": 0.017126546146527116,
      "grad_norm": 0.01142190396785736,
      "learning_rate": 9.956320346634876e-05,
      "loss": 12.4568,
      "step": 18
    },
    {
      "epoch": 0.01807802093244529,
      "grad_norm": 0.009290213696658611,
      "learning_rate": 9.944739353007344e-05,
      "loss": 12.4583,
      "step": 19
    },
    {
      "epoch": 0.019029495718363463,
      "grad_norm": 0.011630688793957233,
      "learning_rate": 9.931806517013612e-05,
      "loss": 12.4574,
      "step": 20
    },
    {
      "epoch": 0.019980970504281638,
      "grad_norm": 0.011584783904254436,
      "learning_rate": 9.917525374361912e-05,
      "loss": 12.4545,
      "step": 21
    },
    {
      "epoch": 0.02093244529019981,
      "grad_norm": 0.011504785157740116,
      "learning_rate": 9.901899829374047e-05,
      "loss": 12.457,
      "step": 22
    },
    {
      "epoch": 0.021883920076117985,
      "grad_norm": 0.011379599571228027,
      "learning_rate": 9.884934153917997e-05,
      "loss": 12.4602,
      "step": 23
    },
    {
      "epoch": 0.022835394862036156,
      "grad_norm": 0.011644704267382622,
      "learning_rate": 9.86663298624003e-05,
      "loss": 12.4579,
      "step": 24
    },
    {
      "epoch": 0.023786869647954328,
      "grad_norm": 0.013753018341958523,
      "learning_rate": 9.847001329696653e-05,
      "loss": 12.4575,
      "step": 25
    },
    {
      "epoch": 0.024738344433872503,
      "grad_norm": 0.01294392254203558,
      "learning_rate": 9.826044551386744e-05,
      "loss": 12.4555,
      "step": 26
    },
    {
      "epoch": 0.025689819219790674,
      "grad_norm": 0.01452360488474369,
      "learning_rate": 9.803768380684242e-05,
      "loss": 12.4566,
      "step": 27
    },
    {
      "epoch": 0.02664129400570885,
      "grad_norm": 0.014984522014856339,
      "learning_rate": 9.780178907671789e-05,
      "loss": 12.4565,
      "step": 28
    },
    {
      "epoch": 0.02759276879162702,
      "grad_norm": 0.016579551622271538,
      "learning_rate": 9.755282581475769e-05,
      "loss": 12.4573,
      "step": 29
    },
    {
      "epoch": 0.028544243577545196,
      "grad_norm": 0.015176886692643166,
      "learning_rate": 9.729086208503174e-05,
      "loss": 12.4591,
      "step": 30
    },
    {
      "epoch": 0.029495718363463368,
      "grad_norm": 0.017412887886166573,
      "learning_rate": 9.701596950580806e-05,
      "loss": 12.4561,
      "step": 31
    },
    {
      "epoch": 0.030447193149381543,
      "grad_norm": 0.016807230189442635,
      "learning_rate": 9.672822322997305e-05,
      "loss": 12.4567,
      "step": 32
    },
    {
      "epoch": 0.03139866793529972,
      "grad_norm": 0.019727198407053947,
      "learning_rate": 9.642770192448536e-05,
      "loss": 12.453,
      "step": 33
    },
    {
      "epoch": 0.03235014272121789,
      "grad_norm": 0.019882963970303535,
      "learning_rate": 9.611448774886924e-05,
      "loss": 12.4564,
      "step": 34
    },
    {
      "epoch": 0.03330161750713606,
      "grad_norm": 0.021717727184295654,
      "learning_rate": 9.578866633275288e-05,
      "loss": 12.4568,
      "step": 35
    },
    {
      "epoch": 0.03425309229305423,
      "grad_norm": 0.0235682874917984,
      "learning_rate": 9.545032675245813e-05,
      "loss": 12.4541,
      "step": 36
    },
    {
      "epoch": 0.035204567078972404,
      "grad_norm": 0.023003190755844116,
      "learning_rate": 9.509956150664796e-05,
      "loss": 12.4575,
      "step": 37
    },
    {
      "epoch": 0.03615604186489058,
      "grad_norm": 0.027334408834576607,
      "learning_rate": 9.473646649103818e-05,
      "loss": 12.4538,
      "step": 38
    },
    {
      "epoch": 0.037107516650808754,
      "grad_norm": 0.02758219465613365,
      "learning_rate": 9.43611409721806e-05,
      "loss": 12.4567,
      "step": 39
    },
    {
      "epoch": 0.038058991436726926,
      "grad_norm": 0.025947609916329384,
      "learning_rate": 9.397368756032445e-05,
      "loss": 12.4521,
      "step": 40
    },
    {
      "epoch": 0.0390104662226451,
      "grad_norm": 0.029927227646112442,
      "learning_rate": 9.357421218136386e-05,
      "loss": 12.4564,
      "step": 41
    },
    {
      "epoch": 0.039961941008563276,
      "grad_norm": 0.03311825916171074,
      "learning_rate": 9.316282404787871e-05,
      "loss": 12.4545,
      "step": 42
    },
    {
      "epoch": 0.04091341579448145,
      "grad_norm": 0.029400333762168884,
      "learning_rate": 9.273963562927695e-05,
      "loss": 12.4574,
      "step": 43
    },
    {
      "epoch": 0.04186489058039962,
      "grad_norm": 0.03190409019589424,
      "learning_rate": 9.230476262104677e-05,
      "loss": 12.4538,
      "step": 44
    },
    {
      "epoch": 0.04281636536631779,
      "grad_norm": 0.032248351722955704,
      "learning_rate": 9.185832391312644e-05,
      "loss": 12.4525,
      "step": 45
    },
    {
      "epoch": 0.04376784015223597,
      "grad_norm": 0.0355122834444046,
      "learning_rate": 9.140044155740101e-05,
      "loss": 12.453,
      "step": 46
    },
    {
      "epoch": 0.04471931493815414,
      "grad_norm": 0.036473359912633896,
      "learning_rate": 9.093124073433463e-05,
      "loss": 12.4557,
      "step": 47
    },
    {
      "epoch": 0.04567078972407231,
      "grad_norm": 0.03410250321030617,
      "learning_rate": 9.045084971874738e-05,
      "loss": 12.4535,
      "step": 48
    },
    {
      "epoch": 0.046622264509990484,
      "grad_norm": 0.03929661214351654,
      "learning_rate": 8.995939984474624e-05,
      "loss": 12.447,
      "step": 49
    },
    {
      "epoch": 0.047573739295908656,
      "grad_norm": 0.03646567463874817,
      "learning_rate": 8.945702546981969e-05,
      "loss": 12.4563,
      "step": 50
    },
    {
      "epoch": 0.047573739295908656,
      "eval_loss": 12.453710556030273,
      "eval_runtime": 15.552,
      "eval_samples_per_second": 113.812,
      "eval_steps_per_second": 28.485,
      "step": 50
    },
    {
      "epoch": 0.048525214081826834,
      "grad_norm": 0.04241883382201195,
      "learning_rate": 8.894386393810563e-05,
      "loss": 12.453,
      "step": 51
    },
    {
      "epoch": 0.049476688867745006,
      "grad_norm": 0.040811438113451004,
      "learning_rate": 8.842005554284296e-05,
      "loss": 12.4532,
      "step": 52
    },
    {
      "epoch": 0.05042816365366318,
      "grad_norm": 0.04538936913013458,
      "learning_rate": 8.788574348801675e-05,
      "loss": 12.4549,
      "step": 53
    },
    {
      "epoch": 0.05137963843958135,
      "grad_norm": 0.04279905930161476,
      "learning_rate": 8.73410738492077e-05,
      "loss": 12.4553,
      "step": 54
    },
    {
      "epoch": 0.05233111322549953,
      "grad_norm": 0.04463065788149834,
      "learning_rate": 8.678619553365659e-05,
      "loss": 12.4545,
      "step": 55
    },
    {
      "epoch": 0.0532825880114177,
      "grad_norm": 0.045460935682058334,
      "learning_rate": 8.622126023955446e-05,
      "loss": 12.4536,
      "step": 56
    },
    {
      "epoch": 0.05423406279733587,
      "grad_norm": 0.04949776828289032,
      "learning_rate": 8.564642241456986e-05,
      "loss": 12.453,
      "step": 57
    },
    {
      "epoch": 0.05518553758325404,
      "grad_norm": 0.048668451607227325,
      "learning_rate": 8.506183921362443e-05,
      "loss": 12.4534,
      "step": 58
    },
    {
      "epoch": 0.056137012369172214,
      "grad_norm": 0.05029277876019478,
      "learning_rate": 8.44676704559283e-05,
      "loss": 12.4509,
      "step": 59
    },
    {
      "epoch": 0.05708848715509039,
      "grad_norm": 0.04988345131278038,
      "learning_rate": 8.386407858128706e-05,
      "loss": 12.4542,
      "step": 60
    },
    {
      "epoch": 0.058039961941008564,
      "grad_norm": 0.057984285056591034,
      "learning_rate": 8.32512286056924e-05,
      "loss": 12.4528,
      "step": 61
    },
    {
      "epoch": 0.058991436726926735,
      "grad_norm": 0.055844224989414215,
      "learning_rate": 8.262928807620843e-05,
      "loss": 12.4509,
      "step": 62
    },
    {
      "epoch": 0.05994291151284491,
      "grad_norm": 0.05761745199561119,
      "learning_rate": 8.199842702516583e-05,
      "loss": 12.4493,
      "step": 63
    },
    {
      "epoch": 0.060894386298763085,
      "grad_norm": 0.056190405040979385,
      "learning_rate": 8.135881792367686e-05,
      "loss": 12.4529,
      "step": 64
    },
    {
      "epoch": 0.06184586108468126,
      "grad_norm": 0.06360480189323425,
      "learning_rate": 8.07106356344834e-05,
      "loss": 12.4507,
      "step": 65
    },
    {
      "epoch": 0.06279733587059944,
      "grad_norm": 0.06286083161830902,
      "learning_rate": 8.005405736415126e-05,
      "loss": 12.4494,
      "step": 66
    },
    {
      "epoch": 0.06374881065651761,
      "grad_norm": 0.06642145663499832,
      "learning_rate": 7.938926261462366e-05,
      "loss": 12.4516,
      "step": 67
    },
    {
      "epoch": 0.06470028544243578,
      "grad_norm": 0.06627269089221954,
      "learning_rate": 7.871643313414718e-05,
      "loss": 12.4492,
      "step": 68
    },
    {
      "epoch": 0.06565176022835395,
      "grad_norm": 0.07501520216464996,
      "learning_rate": 7.803575286758364e-05,
      "loss": 12.4477,
      "step": 69
    },
    {
      "epoch": 0.06660323501427212,
      "grad_norm": 0.07477276027202606,
      "learning_rate": 7.734740790612136e-05,
      "loss": 12.4466,
      "step": 70
    },
    {
      "epoch": 0.0675547098001903,
      "grad_norm": 0.0773748978972435,
      "learning_rate": 7.66515864363997e-05,
      "loss": 12.4473,
      "step": 71
    },
    {
      "epoch": 0.06850618458610847,
      "grad_norm": 0.0730040967464447,
      "learning_rate": 7.594847868906076e-05,
      "loss": 12.4467,
      "step": 72
    },
    {
      "epoch": 0.06945765937202664,
      "grad_norm": 0.07389922440052032,
      "learning_rate": 7.52382768867422e-05,
      "loss": 12.4449,
      "step": 73
    },
    {
      "epoch": 0.07040913415794481,
      "grad_norm": 0.08344914764165878,
      "learning_rate": 7.452117519152542e-05,
      "loss": 12.4473,
      "step": 74
    },
    {
      "epoch": 0.071360608943863,
      "grad_norm": 0.08166919648647308,
      "learning_rate": 7.379736965185368e-05,
      "loss": 12.4463,
      "step": 75
    },
    {
      "epoch": 0.07231208372978117,
      "grad_norm": 0.07941465824842453,
      "learning_rate": 7.30670581489344e-05,
      "loss": 12.4457,
      "step": 76
    },
    {
      "epoch": 0.07326355851569934,
      "grad_norm": 0.08082740008831024,
      "learning_rate": 7.233044034264034e-05,
      "loss": 12.4444,
      "step": 77
    },
    {
      "epoch": 0.07421503330161751,
      "grad_norm": 0.08413875848054886,
      "learning_rate": 7.158771761692464e-05,
      "loss": 12.4461,
      "step": 78
    },
    {
      "epoch": 0.07516650808753568,
      "grad_norm": 0.09172741323709488,
      "learning_rate": 7.083909302476453e-05,
      "loss": 12.4452,
      "step": 79
    },
    {
      "epoch": 0.07611798287345385,
      "grad_norm": 0.09037219732999802,
      "learning_rate": 7.008477123264848e-05,
      "loss": 12.4443,
      "step": 80
    },
    {
      "epoch": 0.07706945765937202,
      "grad_norm": 0.09228965640068054,
      "learning_rate": 6.932495846462261e-05,
      "loss": 12.4366,
      "step": 81
    },
    {
      "epoch": 0.0780209324452902,
      "grad_norm": 0.08169149607419968,
      "learning_rate": 6.855986244591104e-05,
      "loss": 12.4429,
      "step": 82
    },
    {
      "epoch": 0.07897240723120837,
      "grad_norm": 0.09187179803848267,
      "learning_rate": 6.778969234612584e-05,
      "loss": 12.4403,
      "step": 83
    },
    {
      "epoch": 0.07992388201712655,
      "grad_norm": 0.09605192393064499,
      "learning_rate": 6.701465872208216e-05,
      "loss": 12.44,
      "step": 84
    },
    {
      "epoch": 0.08087535680304472,
      "grad_norm": 0.1012379601597786,
      "learning_rate": 6.623497346023418e-05,
      "loss": 12.4397,
      "step": 85
    },
    {
      "epoch": 0.0818268315889629,
      "grad_norm": 0.09477464854717255,
      "learning_rate": 6.545084971874738e-05,
      "loss": 12.4398,
      "step": 86
    },
    {
      "epoch": 0.08277830637488107,
      "grad_norm": 0.09537472575902939,
      "learning_rate": 6.466250186922325e-05,
      "loss": 12.4408,
      "step": 87
    },
    {
      "epoch": 0.08372978116079924,
      "grad_norm": 0.09693397581577301,
      "learning_rate": 6.387014543809223e-05,
      "loss": 12.4391,
      "step": 88
    },
    {
      "epoch": 0.08468125594671741,
      "grad_norm": 0.09416460990905762,
      "learning_rate": 6.307399704769099e-05,
      "loss": 12.4377,
      "step": 89
    },
    {
      "epoch": 0.08563273073263558,
      "grad_norm": 0.09926611185073853,
      "learning_rate": 6.227427435703997e-05,
      "loss": 12.4386,
      "step": 90
    },
    {
      "epoch": 0.08658420551855375,
      "grad_norm": 0.09036323428153992,
      "learning_rate": 6.147119600233758e-05,
      "loss": 12.439,
      "step": 91
    },
    {
      "epoch": 0.08753568030447194,
      "grad_norm": 0.09396945685148239,
      "learning_rate": 6.066498153718735e-05,
      "loss": 12.436,
      "step": 92
    },
    {
      "epoch": 0.08848715509039011,
      "grad_norm": 0.10250120609998703,
      "learning_rate": 5.985585137257401e-05,
      "loss": 12.4326,
      "step": 93
    },
    {
      "epoch": 0.08943862987630828,
      "grad_norm": 0.09737430512905121,
      "learning_rate": 5.90440267166055e-05,
      "loss": 12.4376,
      "step": 94
    },
    {
      "epoch": 0.09039010466222645,
      "grad_norm": 0.098517045378685,
      "learning_rate": 5.8229729514036705e-05,
      "loss": 12.4316,
      "step": 95
    },
    {
      "epoch": 0.09134157944814462,
      "grad_norm": 0.09766911715269089,
      "learning_rate": 5.74131823855921e-05,
      "loss": 12.4382,
      "step": 96
    },
    {
      "epoch": 0.0922930542340628,
      "grad_norm": 0.10806909203529358,
      "learning_rate": 5.6594608567103456e-05,
      "loss": 12.4331,
      "step": 97
    },
    {
      "epoch": 0.09324452901998097,
      "grad_norm": 0.08718223124742508,
      "learning_rate": 5.577423184847932e-05,
      "loss": 12.4352,
      "step": 98
    },
    {
      "epoch": 0.09419600380589914,
      "grad_norm": 0.09523314237594604,
      "learning_rate": 5.495227651252315e-05,
      "loss": 12.4348,
      "step": 99
    },
    {
      "epoch": 0.09514747859181731,
      "grad_norm": 0.09032314270734787,
      "learning_rate": 5.4128967273616625e-05,
      "loss": 12.4365,
      "step": 100
    },
    {
      "epoch": 0.09514747859181731,
      "eval_loss": 12.433951377868652,
      "eval_runtime": 15.6067,
      "eval_samples_per_second": 113.413,
      "eval_steps_per_second": 28.385,
      "step": 100
    },
    {
      "epoch": 0.0960989533777355,
      "grad_norm": 0.09497902542352676,
      "learning_rate": 5.330452921628497e-05,
      "loss": 12.4359,
      "step": 101
    },
    {
      "epoch": 0.09705042816365367,
      "grad_norm": 0.09944572299718857,
      "learning_rate": 5.247918773366112e-05,
      "loss": 12.4335,
      "step": 102
    },
    {
      "epoch": 0.09800190294957184,
      "grad_norm": 0.09011027961969376,
      "learning_rate": 5.165316846586541e-05,
      "loss": 12.4373,
      "step": 103
    },
    {
      "epoch": 0.09895337773549001,
      "grad_norm": 0.09865716099739075,
      "learning_rate": 5.0826697238317935e-05,
      "loss": 12.4338,
      "step": 104
    },
    {
      "epoch": 0.09990485252140818,
      "grad_norm": 0.10097349435091019,
      "learning_rate": 5e-05,
      "loss": 12.4338,
      "step": 105
    },
    {
      "epoch": 0.10085632730732635,
      "grad_norm": 0.09969794005155563,
      "learning_rate": 4.917330276168208e-05,
      "loss": 12.4327,
      "step": 106
    },
    {
      "epoch": 0.10180780209324453,
      "grad_norm": 0.1018582209944725,
      "learning_rate": 4.834683153413459e-05,
      "loss": 12.4325,
      "step": 107
    },
    {
      "epoch": 0.1027592768791627,
      "grad_norm": 0.0932171493768692,
      "learning_rate": 4.7520812266338885e-05,
      "loss": 12.4355,
      "step": 108
    },
    {
      "epoch": 0.10371075166508087,
      "grad_norm": 0.09889080375432968,
      "learning_rate": 4.669547078371504e-05,
      "loss": 12.4293,
      "step": 109
    },
    {
      "epoch": 0.10466222645099905,
      "grad_norm": 0.10099539905786514,
      "learning_rate": 4.5871032726383386e-05,
      "loss": 12.4321,
      "step": 110
    },
    {
      "epoch": 0.10561370123691723,
      "grad_norm": 0.09008205682039261,
      "learning_rate": 4.504772348747687e-05,
      "loss": 12.4311,
      "step": 111
    },
    {
      "epoch": 0.1065651760228354,
      "grad_norm": 0.08855817466974258,
      "learning_rate": 4.4225768151520694e-05,
      "loss": 12.4351,
      "step": 112
    },
    {
      "epoch": 0.10751665080875357,
      "grad_norm": 0.10250566899776459,
      "learning_rate": 4.3405391432896555e-05,
      "loss": 12.4302,
      "step": 113
    },
    {
      "epoch": 0.10846812559467174,
      "grad_norm": 0.10185489803552628,
      "learning_rate": 4.2586817614407895e-05,
      "loss": 12.4319,
      "step": 114
    },
    {
      "epoch": 0.10941960038058991,
      "grad_norm": 0.09495784342288971,
      "learning_rate": 4.17702704859633e-05,
      "loss": 12.4274,
      "step": 115
    },
    {
      "epoch": 0.11037107516650808,
      "grad_norm": 0.09465058892965317,
      "learning_rate": 4.095597328339452e-05,
      "loss": 12.4305,
      "step": 116
    },
    {
      "epoch": 0.11132254995242626,
      "grad_norm": 0.10025542974472046,
      "learning_rate": 4.0144148627425993e-05,
      "loss": 12.4281,
      "step": 117
    },
    {
      "epoch": 0.11227402473834443,
      "grad_norm": 0.09566202759742737,
      "learning_rate": 3.933501846281267e-05,
      "loss": 12.4259,
      "step": 118
    },
    {
      "epoch": 0.11322549952426261,
      "grad_norm": 0.09907243400812149,
      "learning_rate": 3.852880399766243e-05,
      "loss": 12.4262,
      "step": 119
    },
    {
      "epoch": 0.11417697431018078,
      "grad_norm": 0.09314558655023575,
      "learning_rate": 3.772572564296005e-05,
      "loss": 12.4311,
      "step": 120
    },
    {
      "epoch": 0.11512844909609896,
      "grad_norm": 0.09395626187324524,
      "learning_rate": 3.6926002952309016e-05,
      "loss": 12.4293,
      "step": 121
    },
    {
      "epoch": 0.11607992388201713,
      "grad_norm": 0.09918255358934402,
      "learning_rate": 3.612985456190778e-05,
      "loss": 12.4235,
      "step": 122
    },
    {
      "epoch": 0.1170313986679353,
      "grad_norm": 0.09812726825475693,
      "learning_rate": 3.533749813077677e-05,
      "loss": 12.4294,
      "step": 123
    },
    {
      "epoch": 0.11798287345385347,
      "grad_norm": 0.08929837495088577,
      "learning_rate": 3.4549150281252636e-05,
      "loss": 12.4269,
      "step": 124
    },
    {
      "epoch": 0.11893434823977164,
      "grad_norm": 0.08941438794136047,
      "learning_rate": 3.3765026539765834e-05,
      "loss": 12.4285,
      "step": 125
    },
    {
      "epoch": 0.11988582302568981,
      "grad_norm": 0.09126895666122437,
      "learning_rate": 3.298534127791785e-05,
      "loss": 12.4261,
      "step": 126
    },
    {
      "epoch": 0.120837297811608,
      "grad_norm": 0.08844456076622009,
      "learning_rate": 3.221030765387417e-05,
      "loss": 12.4307,
      "step": 127
    },
    {
      "epoch": 0.12178877259752617,
      "grad_norm": 0.0888495072722435,
      "learning_rate": 3.144013755408895e-05,
      "loss": 12.4242,
      "step": 128
    },
    {
      "epoch": 0.12274024738344434,
      "grad_norm": 0.088569276034832,
      "learning_rate": 3.0675041535377405e-05,
      "loss": 12.4232,
      "step": 129
    },
    {
      "epoch": 0.12369172216936251,
      "grad_norm": 0.09507988393306732,
      "learning_rate": 2.991522876735154e-05,
      "loss": 12.4232,
      "step": 130
    },
    {
      "epoch": 0.12464319695528069,
      "grad_norm": 0.09729907661676407,
      "learning_rate": 2.916090697523549e-05,
      "loss": 12.4234,
      "step": 131
    },
    {
      "epoch": 0.12559467174119887,
      "grad_norm": 0.09437138587236404,
      "learning_rate": 2.8412282383075363e-05,
      "loss": 12.4256,
      "step": 132
    },
    {
      "epoch": 0.12654614652711704,
      "grad_norm": 0.09187323600053787,
      "learning_rate": 2.766955965735968e-05,
      "loss": 12.4238,
      "step": 133
    },
    {
      "epoch": 0.12749762131303521,
      "grad_norm": 0.08367627114057541,
      "learning_rate": 2.693294185106562e-05,
      "loss": 12.426,
      "step": 134
    },
    {
      "epoch": 0.12844909609895339,
      "grad_norm": 0.09664832800626755,
      "learning_rate": 2.6202630348146324e-05,
      "loss": 12.4266,
      "step": 135
    },
    {
      "epoch": 0.12940057088487156,
      "grad_norm": 0.08929263055324554,
      "learning_rate": 2.547882480847461e-05,
      "loss": 12.4252,
      "step": 136
    },
    {
      "epoch": 0.13035204567078973,
      "grad_norm": 0.08494222164154053,
      "learning_rate": 2.476172311325783e-05,
      "loss": 12.4247,
      "step": 137
    },
    {
      "epoch": 0.1313035204567079,
      "grad_norm": 0.09214748442173004,
      "learning_rate": 2.405152131093926e-05,
      "loss": 12.4231,
      "step": 138
    },
    {
      "epoch": 0.13225499524262607,
      "grad_norm": 0.09231774508953094,
      "learning_rate": 2.3348413563600325e-05,
      "loss": 12.4218,
      "step": 139
    },
    {
      "epoch": 0.13320647002854424,
      "grad_norm": 0.09352681785821915,
      "learning_rate": 2.2652592093878666e-05,
      "loss": 12.4249,
      "step": 140
    },
    {
      "epoch": 0.13415794481446242,
      "grad_norm": 0.09825602918863297,
      "learning_rate": 2.196424713241637e-05,
      "loss": 12.4228,
      "step": 141
    },
    {
      "epoch": 0.1351094196003806,
      "grad_norm": 0.08893214911222458,
      "learning_rate": 2.128356686585282e-05,
      "loss": 12.4227,
      "step": 142
    },
    {
      "epoch": 0.13606089438629876,
      "grad_norm": 0.09150007367134094,
      "learning_rate": 2.061073738537635e-05,
      "loss": 12.4206,
      "step": 143
    },
    {
      "epoch": 0.13701236917221693,
      "grad_norm": 0.09207893908023834,
      "learning_rate": 1.9945942635848748e-05,
      "loss": 12.4254,
      "step": 144
    },
    {
      "epoch": 0.1379638439581351,
      "grad_norm": 0.09610553085803986,
      "learning_rate": 1.928936436551661e-05,
      "loss": 12.4251,
      "step": 145
    },
    {
      "epoch": 0.13891531874405327,
      "grad_norm": 0.09315261989831924,
      "learning_rate": 1.8641182076323148e-05,
      "loss": 12.4204,
      "step": 146
    },
    {
      "epoch": 0.13986679352997144,
      "grad_norm": 0.0996289998292923,
      "learning_rate": 1.800157297483417e-05,
      "loss": 12.4256,
      "step": 147
    },
    {
      "epoch": 0.14081826831588962,
      "grad_norm": 0.08555201441049576,
      "learning_rate": 1.7370711923791567e-05,
      "loss": 12.4218,
      "step": 148
    },
    {
      "epoch": 0.14176974310180782,
      "grad_norm": 0.0928102433681488,
      "learning_rate": 1.6748771394307585e-05,
      "loss": 12.4219,
      "step": 149
    },
    {
      "epoch": 0.142721217887726,
      "grad_norm": 0.09874225407838821,
      "learning_rate": 1.6135921418712956e-05,
      "loss": 12.4215,
      "step": 150
    },
    {
      "epoch": 0.142721217887726,
      "eval_loss": 12.422270774841309,
      "eval_runtime": 15.4682,
      "eval_samples_per_second": 114.428,
      "eval_steps_per_second": 28.639,
      "step": 150
    },
    {
      "epoch": 0.14367269267364416,
      "grad_norm": 0.09273713827133179,
      "learning_rate": 1.553232954407171e-05,
      "loss": 12.4253,
      "step": 151
    },
    {
      "epoch": 0.14462416745956233,
      "grad_norm": 0.09292459487915039,
      "learning_rate": 1.4938160786375572e-05,
      "loss": 12.4231,
      "step": 152
    },
    {
      "epoch": 0.1455756422454805,
      "grad_norm": 0.09946370869874954,
      "learning_rate": 1.435357758543015e-05,
      "loss": 12.4228,
      "step": 153
    },
    {
      "epoch": 0.14652711703139867,
      "grad_norm": 0.09532055258750916,
      "learning_rate": 1.3778739760445552e-05,
      "loss": 12.4248,
      "step": 154
    },
    {
      "epoch": 0.14747859181731685,
      "grad_norm": 0.09795553982257843,
      "learning_rate": 1.3213804466343421e-05,
      "loss": 12.4244,
      "step": 155
    },
    {
      "epoch": 0.14843006660323502,
      "grad_norm": 0.09874273836612701,
      "learning_rate": 1.2658926150792322e-05,
      "loss": 12.4208,
      "step": 156
    },
    {
      "epoch": 0.1493815413891532,
      "grad_norm": 0.10250060260295868,
      "learning_rate": 1.2114256511983274e-05,
      "loss": 12.4227,
      "step": 157
    },
    {
      "epoch": 0.15033301617507136,
      "grad_norm": 0.09086371213197708,
      "learning_rate": 1.157994445715706e-05,
      "loss": 12.4231,
      "step": 158
    },
    {
      "epoch": 0.15128449096098953,
      "grad_norm": 0.10825308412313461,
      "learning_rate": 1.1056136061894384e-05,
      "loss": 12.4194,
      "step": 159
    },
    {
      "epoch": 0.1522359657469077,
      "grad_norm": 0.09416839480400085,
      "learning_rate": 1.0542974530180327e-05,
      "loss": 12.4209,
      "step": 160
    },
    {
      "epoch": 0.15318744053282587,
      "grad_norm": 0.10014671087265015,
      "learning_rate": 1.0040600155253765e-05,
      "loss": 12.4201,
      "step": 161
    },
    {
      "epoch": 0.15413891531874405,
      "grad_norm": 0.09511859714984894,
      "learning_rate": 9.549150281252633e-06,
      "loss": 12.4193,
      "step": 162
    },
    {
      "epoch": 0.15509039010466222,
      "grad_norm": 0.09378856420516968,
      "learning_rate": 9.068759265665384e-06,
      "loss": 12.4209,
      "step": 163
    },
    {
      "epoch": 0.1560418648905804,
      "grad_norm": 0.08971430361270905,
      "learning_rate": 8.599558442598998e-06,
      "loss": 12.4264,
      "step": 164
    },
    {
      "epoch": 0.15699333967649856,
      "grad_norm": 0.10229922831058502,
      "learning_rate": 8.141676086873572e-06,
      "loss": 12.4231,
      "step": 165
    },
    {
      "epoch": 0.15794481446241673,
      "grad_norm": 0.0955134704709053,
      "learning_rate": 7.695237378953223e-06,
      "loss": 12.4237,
      "step": 166
    },
    {
      "epoch": 0.15889628924833493,
      "grad_norm": 0.09622351080179214,
      "learning_rate": 7.260364370723044e-06,
      "loss": 12.4219,
      "step": 167
    },
    {
      "epoch": 0.1598477640342531,
      "grad_norm": 0.09816249459981918,
      "learning_rate": 6.837175952121306e-06,
      "loss": 12.4183,
      "step": 168
    },
    {
      "epoch": 0.16079923882017128,
      "grad_norm": 0.09571335464715958,
      "learning_rate": 6.425787818636131e-06,
      "loss": 12.4213,
      "step": 169
    },
    {
      "epoch": 0.16175071360608945,
      "grad_norm": 0.08884340524673462,
      "learning_rate": 6.026312439675552e-06,
      "loss": 12.4226,
      "step": 170
    },
    {
      "epoch": 0.16270218839200762,
      "grad_norm": 0.09456470608711243,
      "learning_rate": 5.6388590278194096e-06,
      "loss": 12.4196,
      "step": 171
    },
    {
      "epoch": 0.1636536631779258,
      "grad_norm": 0.09501412510871887,
      "learning_rate": 5.263533508961827e-06,
      "loss": 12.4228,
      "step": 172
    },
    {
      "epoch": 0.16460513796384396,
      "grad_norm": 0.0949086919426918,
      "learning_rate": 4.900438493352055e-06,
      "loss": 12.4217,
      "step": 173
    },
    {
      "epoch": 0.16555661274976213,
      "grad_norm": 0.09755706787109375,
      "learning_rate": 4.549673247541875e-06,
      "loss": 12.4153,
      "step": 174
    },
    {
      "epoch": 0.1665080875356803,
      "grad_norm": 0.10222338885068893,
      "learning_rate": 4.2113336672471245e-06,
      "loss": 12.4226,
      "step": 175
    },
    {
      "epoch": 0.16745956232159848,
      "grad_norm": 0.09313151985406876,
      "learning_rate": 3.885512251130763e-06,
      "loss": 12.422,
      "step": 176
    },
    {
      "epoch": 0.16841103710751665,
      "grad_norm": 0.0906304121017456,
      "learning_rate": 3.5722980755146517e-06,
      "loss": 12.4197,
      "step": 177
    },
    {
      "epoch": 0.16936251189343482,
      "grad_norm": 0.08964324742555618,
      "learning_rate": 3.271776770026963e-06,
      "loss": 12.4203,
      "step": 178
    },
    {
      "epoch": 0.170313986679353,
      "grad_norm": 0.10286598652601242,
      "learning_rate": 2.9840304941919415e-06,
      "loss": 12.4213,
      "step": 179
    },
    {
      "epoch": 0.17126546146527116,
      "grad_norm": 0.10211426019668579,
      "learning_rate": 2.7091379149682685e-06,
      "loss": 12.4179,
      "step": 180
    },
    {
      "epoch": 0.17221693625118933,
      "grad_norm": 0.08623471856117249,
      "learning_rate": 2.4471741852423237e-06,
      "loss": 12.4191,
      "step": 181
    },
    {
      "epoch": 0.1731684110371075,
      "grad_norm": 0.08864640444517136,
      "learning_rate": 2.1982109232821178e-06,
      "loss": 12.4218,
      "step": 182
    },
    {
      "epoch": 0.17411988582302568,
      "grad_norm": 0.09065700322389603,
      "learning_rate": 1.962316193157593e-06,
      "loss": 12.4216,
      "step": 183
    },
    {
      "epoch": 0.17507136060894388,
      "grad_norm": 0.09477610886096954,
      "learning_rate": 1.7395544861325718e-06,
      "loss": 12.4199,
      "step": 184
    },
    {
      "epoch": 0.17602283539486205,
      "grad_norm": 0.09666874259710312,
      "learning_rate": 1.5299867030334814e-06,
      "loss": 12.4218,
      "step": 185
    },
    {
      "epoch": 0.17697431018078022,
      "grad_norm": 0.08862237632274628,
      "learning_rate": 1.333670137599713e-06,
      "loss": 12.4185,
      "step": 186
    },
    {
      "epoch": 0.1779257849666984,
      "grad_norm": 0.09780198335647583,
      "learning_rate": 1.1506584608200367e-06,
      "loss": 12.4204,
      "step": 187
    },
    {
      "epoch": 0.17887725975261656,
      "grad_norm": 0.0867682471871376,
      "learning_rate": 9.810017062595322e-07,
      "loss": 12.4253,
      "step": 188
    },
    {
      "epoch": 0.17982873453853473,
      "grad_norm": 0.09105724096298218,
      "learning_rate": 8.247462563808817e-07,
      "loss": 12.4224,
      "step": 189
    },
    {
      "epoch": 0.1807802093244529,
      "grad_norm": 0.08529210835695267,
      "learning_rate": 6.819348298638839e-07,
      "loss": 12.4232,
      "step": 190
    },
    {
      "epoch": 0.18173168411037108,
      "grad_norm": 0.10350967198610306,
      "learning_rate": 5.526064699265753e-07,
      "loss": 12.4253,
      "step": 191
    },
    {
      "epoch": 0.18268315889628925,
      "grad_norm": 0.10518278181552887,
      "learning_rate": 4.367965336512403e-07,
      "loss": 12.4188,
      "step": 192
    },
    {
      "epoch": 0.18363463368220742,
      "grad_norm": 0.09514354914426804,
      "learning_rate": 3.3453668231809286e-07,
      "loss": 12.4225,
      "step": 193
    },
    {
      "epoch": 0.1845861084681256,
      "grad_norm": 0.08841454982757568,
      "learning_rate": 2.458548727494292e-07,
      "loss": 12.4183,
      "step": 194
    },
    {
      "epoch": 0.18553758325404376,
      "grad_norm": 0.0847589522600174,
      "learning_rate": 1.7077534966650766e-07,
      "loss": 12.4237,
      "step": 195
    },
    {
      "epoch": 0.18648905803996194,
      "grad_norm": 0.1080126240849495,
      "learning_rate": 1.0931863906127327e-07,
      "loss": 12.4242,
      "step": 196
    },
    {
      "epoch": 0.1874405328258801,
      "grad_norm": 0.09209670126438141,
      "learning_rate": 6.150154258476315e-08,
      "loss": 12.4161,
      "step": 197
    },
    {
      "epoch": 0.18839200761179828,
      "grad_norm": 0.09520721435546875,
      "learning_rate": 2.7337132953697554e-08,
      "loss": 12.4214,
      "step": 198
    },
    {
      "epoch": 0.18934348239771645,
      "grad_norm": 0.0942104160785675,
      "learning_rate": 6.834750376549792e-09,
      "loss": 12.4258,
      "step": 199
    },
    {
      "epoch": 0.19029495718363462,
      "grad_norm": 0.09318140894174576,
      "learning_rate": 0.0,
      "loss": 12.4234,
      "step": 200
    },
    {
      "epoch": 0.19029495718363462,
      "eval_loss": 12.420499801635742,
      "eval_runtime": 15.4777,
      "eval_samples_per_second": 114.358,
      "eval_steps_per_second": 28.622,
      "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": 887996547072.0,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}