{
  "best_metric": 10.213754653930664,
  "best_model_checkpoint": "miner_id_24/checkpoint-200",
  "epoch": 0.15597582374731916,
  "eval_steps": 50,
  "global_step": 200,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0007798791187365958,
      "grad_norm": 2.715223550796509,
      "learning_rate": 1e-05,
      "loss": 41.5167,
      "step": 1
    },
    {
      "epoch": 0.0007798791187365958,
      "eval_loss": 10.37878131866455,
      "eval_runtime": 5.7123,
      "eval_samples_per_second": 378.132,
      "eval_steps_per_second": 94.533,
      "step": 1
    },
    {
      "epoch": 0.0015597582374731916,
      "grad_norm": 2.905325174331665,
      "learning_rate": 2e-05,
      "loss": 41.525,
      "step": 2
    },
    {
      "epoch": 0.0023396373562097877,
      "grad_norm": 2.424551248550415,
      "learning_rate": 3e-05,
      "loss": 41.5224,
      "step": 3
    },
    {
      "epoch": 0.003119516474946383,
      "grad_norm": 3.3444395065307617,
      "learning_rate": 4e-05,
      "loss": 41.4805,
      "step": 4
    },
    {
      "epoch": 0.003899395593682979,
      "grad_norm": 2.509641408920288,
      "learning_rate": 5e-05,
      "loss": 41.5164,
      "step": 5
    },
    {
      "epoch": 0.004679274712419575,
      "grad_norm": 2.1646931171417236,
      "learning_rate": 6e-05,
      "loss": 41.4963,
      "step": 6
    },
    {
      "epoch": 0.00545915383115617,
      "grad_norm": 1.798095464706421,
      "learning_rate": 7e-05,
      "loss": 41.5456,
      "step": 7
    },
    {
      "epoch": 0.006239032949892766,
      "grad_norm": 2.056730270385742,
      "learning_rate": 8e-05,
      "loss": 41.4564,
      "step": 8
    },
    {
      "epoch": 0.007018912068629362,
      "grad_norm": 2.5751936435699463,
      "learning_rate": 9e-05,
      "loss": 41.4834,
      "step": 9
    },
    {
      "epoch": 0.007798791187365958,
      "grad_norm": 2.699554204940796,
      "learning_rate": 0.0001,
      "loss": 41.4634,
      "step": 10
    },
    {
      "epoch": 0.008578670306102555,
      "grad_norm": 3.3361618518829346,
      "learning_rate": 9.999316524962345e-05,
      "loss": 41.4264,
      "step": 11
    },
    {
      "epoch": 0.00935854942483915,
      "grad_norm": 2.6799867153167725,
      "learning_rate": 9.997266286704631e-05,
      "loss": 41.4656,
      "step": 12
    },
    {
      "epoch": 0.010138428543575747,
      "grad_norm": 2.99436092376709,
      "learning_rate": 9.993849845741524e-05,
      "loss": 41.4127,
      "step": 13
    },
    {
      "epoch": 0.01091830766231234,
      "grad_norm": 3.0660603046417236,
      "learning_rate": 9.989068136093873e-05,
      "loss": 41.4148,
      "step": 14
    },
    {
      "epoch": 0.011698186781048937,
      "grad_norm": 3.333158493041992,
      "learning_rate": 9.98292246503335e-05,
      "loss": 41.3847,
      "step": 15
    },
    {
      "epoch": 0.012478065899785533,
      "grad_norm": 3.595855236053467,
      "learning_rate": 9.975414512725057e-05,
      "loss": 41.3979,
      "step": 16
    },
    {
      "epoch": 0.013257945018522128,
      "grad_norm": 3.9648728370666504,
      "learning_rate": 9.966546331768191e-05,
      "loss": 41.3387,
      "step": 17
    },
    {
      "epoch": 0.014037824137258724,
      "grad_norm": 3.6955621242523193,
      "learning_rate": 9.956320346634876e-05,
      "loss": 41.362,
      "step": 18
    },
    {
      "epoch": 0.01481770325599532,
      "grad_norm": 4.27481746673584,
      "learning_rate": 9.944739353007344e-05,
      "loss": 41.3244,
      "step": 19
    },
    {
      "epoch": 0.015597582374731916,
      "grad_norm": 4.21629524230957,
      "learning_rate": 9.931806517013612e-05,
      "loss": 41.301,
      "step": 20
    },
    {
      "epoch": 0.016377461493468512,
      "grad_norm": 4.189397811889648,
      "learning_rate": 9.917525374361912e-05,
      "loss": 41.3174,
      "step": 21
    },
    {
      "epoch": 0.01715734061220511,
      "grad_norm": 4.369172096252441,
      "learning_rate": 9.901899829374047e-05,
      "loss": 41.2773,
      "step": 22
    },
    {
      "epoch": 0.017937219730941704,
      "grad_norm": 4.497531414031982,
      "learning_rate": 9.884934153917997e-05,
      "loss": 41.251,
      "step": 23
    },
    {
      "epoch": 0.0187170988496783,
      "grad_norm": 4.064614772796631,
      "learning_rate": 9.86663298624003e-05,
      "loss": 41.2308,
      "step": 24
    },
    {
      "epoch": 0.019496977968414896,
      "grad_norm": 4.091201305389404,
      "learning_rate": 9.847001329696653e-05,
      "loss": 41.2181,
      "step": 25
    },
    {
      "epoch": 0.020276857087151493,
      "grad_norm": 4.379391670227051,
      "learning_rate": 9.826044551386744e-05,
      "loss": 41.1513,
      "step": 26
    },
    {
      "epoch": 0.021056736205888087,
      "grad_norm": 4.101278781890869,
      "learning_rate": 9.803768380684242e-05,
      "loss": 41.1668,
      "step": 27
    },
    {
      "epoch": 0.02183661532462468,
      "grad_norm": 3.9262936115264893,
      "learning_rate": 9.780178907671789e-05,
      "loss": 41.1705,
      "step": 28
    },
    {
      "epoch": 0.02261649444336128,
      "grad_norm": 3.789227247238159,
      "learning_rate": 9.755282581475769e-05,
      "loss": 41.1134,
      "step": 29
    },
    {
      "epoch": 0.023396373562097873,
      "grad_norm": 3.420815944671631,
      "learning_rate": 9.729086208503174e-05,
      "loss": 41.1102,
      "step": 30
    },
    {
      "epoch": 0.02417625268083447,
      "grad_norm": 3.464881420135498,
      "learning_rate": 9.701596950580806e-05,
      "loss": 41.0591,
      "step": 31
    },
    {
      "epoch": 0.024956131799571065,
      "grad_norm": 3.2205071449279785,
      "learning_rate": 9.672822322997305e-05,
      "loss": 41.0656,
      "step": 32
    },
    {
      "epoch": 0.025736010918307663,
      "grad_norm": 3.3068740367889404,
      "learning_rate": 9.642770192448536e-05,
      "loss": 41.0548,
      "step": 33
    },
    {
      "epoch": 0.026515890037044257,
      "grad_norm": 3.021029472351074,
      "learning_rate": 9.611448774886924e-05,
      "loss": 41.0205,
      "step": 34
    },
    {
      "epoch": 0.027295769155780854,
      "grad_norm": 2.7231557369232178,
      "learning_rate": 9.578866633275288e-05,
      "loss": 41.0036,
      "step": 35
    },
    {
      "epoch": 0.02807564827451745,
      "grad_norm": 2.374765157699585,
      "learning_rate": 9.545032675245813e-05,
      "loss": 41.0004,
      "step": 36
    },
    {
      "epoch": 0.028855527393254046,
      "grad_norm": 2.4742703437805176,
      "learning_rate": 9.509956150664796e-05,
      "loss": 40.9551,
      "step": 37
    },
    {
      "epoch": 0.02963540651199064,
      "grad_norm": 1.8893934488296509,
      "learning_rate": 9.473646649103818e-05,
      "loss": 41.0072,
      "step": 38
    },
    {
      "epoch": 0.030415285630727238,
      "grad_norm": 1.9732555150985718,
      "learning_rate": 9.43611409721806e-05,
      "loss": 41.012,
      "step": 39
    },
    {
      "epoch": 0.031195164749463832,
      "grad_norm": 2.1147286891937256,
      "learning_rate": 9.397368756032445e-05,
      "loss": 40.9549,
      "step": 40
    },
    {
      "epoch": 0.03197504386820043,
      "grad_norm": 1.999768853187561,
      "learning_rate": 9.357421218136386e-05,
      "loss": 40.9153,
      "step": 41
    },
    {
      "epoch": 0.032754922986937024,
      "grad_norm": 1.7699193954467773,
      "learning_rate": 9.316282404787871e-05,
      "loss": 40.929,
      "step": 42
    },
    {
      "epoch": 0.03353480210567362,
      "grad_norm": 1.528317928314209,
      "learning_rate": 9.273963562927695e-05,
      "loss": 40.905,
      "step": 43
    },
    {
      "epoch": 0.03431468122441022,
      "grad_norm": 1.6290485858917236,
      "learning_rate": 9.230476262104677e-05,
      "loss": 40.9135,
      "step": 44
    },
    {
      "epoch": 0.03509456034314681,
      "grad_norm": 1.426215648651123,
      "learning_rate": 9.185832391312644e-05,
      "loss": 40.9352,
      "step": 45
    },
    {
      "epoch": 0.03587443946188341,
      "grad_norm": 1.3820502758026123,
      "learning_rate": 9.140044155740101e-05,
      "loss": 40.8827,
      "step": 46
    },
    {
      "epoch": 0.03665431858062,
      "grad_norm": 1.4418771266937256,
      "learning_rate": 9.093124073433463e-05,
      "loss": 40.9877,
      "step": 47
    },
    {
      "epoch": 0.0374341976993566,
      "grad_norm": 1.064051866531372,
      "learning_rate": 9.045084971874738e-05,
      "loss": 40.9316,
      "step": 48
    },
    {
      "epoch": 0.0382140768180932,
      "grad_norm": 1.7976652383804321,
      "learning_rate": 8.995939984474624e-05,
      "loss": 40.8165,
      "step": 49
    },
    {
      "epoch": 0.03899395593682979,
      "grad_norm": 1.1343622207641602,
      "learning_rate": 8.945702546981969e-05,
      "loss": 40.8667,
      "step": 50
    },
    {
      "epoch": 0.03899395593682979,
      "eval_loss": 10.228208541870117,
      "eval_runtime": 5.6865,
      "eval_samples_per_second": 379.847,
      "eval_steps_per_second": 94.962,
      "step": 50
    },
    {
      "epoch": 0.039773835055566385,
      "grad_norm": 1.1780071258544922,
      "learning_rate": 8.894386393810563e-05,
      "loss": 40.9287,
      "step": 51
    },
    {
      "epoch": 0.040553714174302986,
      "grad_norm": 1.0647155046463013,
      "learning_rate": 8.842005554284296e-05,
      "loss": 40.9226,
      "step": 52
    },
    {
      "epoch": 0.04133359329303958,
      "grad_norm": 1.1737453937530518,
      "learning_rate": 8.788574348801675e-05,
      "loss": 40.8977,
      "step": 53
    },
    {
      "epoch": 0.042113472411776175,
      "grad_norm": 1.0228190422058105,
      "learning_rate": 8.73410738492077e-05,
      "loss": 40.9237,
      "step": 54
    },
    {
      "epoch": 0.04289335153051277,
      "grad_norm": 1.8137887716293335,
      "learning_rate": 8.678619553365659e-05,
      "loss": 40.7676,
      "step": 55
    },
    {
      "epoch": 0.04367323064924936,
      "grad_norm": 1.014417052268982,
      "learning_rate": 8.622126023955446e-05,
      "loss": 40.9275,
      "step": 56
    },
    {
      "epoch": 0.044453109767985964,
      "grad_norm": 0.9988589882850647,
      "learning_rate": 8.564642241456986e-05,
      "loss": 40.9781,
      "step": 57
    },
    {
      "epoch": 0.04523298888672256,
      "grad_norm": 0.9781436324119568,
      "learning_rate": 8.506183921362443e-05,
      "loss": 41.0015,
      "step": 58
    },
    {
      "epoch": 0.04601286800545915,
      "grad_norm": 1.5599066019058228,
      "learning_rate": 8.44676704559283e-05,
      "loss": 41.0043,
      "step": 59
    },
    {
      "epoch": 0.04679274712419575,
      "grad_norm": 1.499716877937317,
      "learning_rate": 8.386407858128706e-05,
      "loss": 40.9588,
      "step": 60
    },
    {
      "epoch": 0.04757262624293235,
      "grad_norm": 1.4234154224395752,
      "learning_rate": 8.32512286056924e-05,
      "loss": 40.915,
      "step": 61
    },
    {
      "epoch": 0.04835250536166894,
      "grad_norm": 1.6705865859985352,
      "learning_rate": 8.262928807620843e-05,
      "loss": 40.8582,
      "step": 62
    },
    {
      "epoch": 0.049132384480405536,
      "grad_norm": 1.5686525106430054,
      "learning_rate": 8.199842702516583e-05,
      "loss": 40.8509,
      "step": 63
    },
    {
      "epoch": 0.04991226359914213,
      "grad_norm": 0.7974070906639099,
      "learning_rate": 8.135881792367686e-05,
      "loss": 40.8878,
      "step": 64
    },
    {
      "epoch": 0.05069214271787873,
      "grad_norm": 0.8495602607727051,
      "learning_rate": 8.07106356344834e-05,
      "loss": 40.9022,
      "step": 65
    },
    {
      "epoch": 0.051472021836615325,
      "grad_norm": 0.7446238994598389,
      "learning_rate": 8.005405736415126e-05,
      "loss": 40.9368,
      "step": 66
    },
    {
      "epoch": 0.05225190095535192,
      "grad_norm": 0.6731091737747192,
      "learning_rate": 7.938926261462366e-05,
      "loss": 40.9081,
      "step": 67
    },
    {
      "epoch": 0.053031780074088514,
      "grad_norm": 0.7269465327262878,
      "learning_rate": 7.871643313414718e-05,
      "loss": 40.8877,
      "step": 68
    },
    {
      "epoch": 0.053811659192825115,
      "grad_norm": 0.5409484505653381,
      "learning_rate": 7.803575286758364e-05,
      "loss": 40.9051,
      "step": 69
    },
    {
      "epoch": 0.05459153831156171,
      "grad_norm": 0.6834560632705688,
      "learning_rate": 7.734740790612136e-05,
      "loss": 40.8777,
      "step": 70
    },
    {
      "epoch": 0.0553714174302983,
      "grad_norm": 0.6990256905555725,
      "learning_rate": 7.66515864363997e-05,
      "loss": 40.8638,
      "step": 71
    },
    {
      "epoch": 0.0561512965490349,
      "grad_norm": 0.5950748324394226,
      "learning_rate": 7.594847868906076e-05,
      "loss": 40.9198,
      "step": 72
    },
    {
      "epoch": 0.0569311756677715,
      "grad_norm": 0.6048076152801514,
      "learning_rate": 7.52382768867422e-05,
      "loss": 40.8468,
      "step": 73
    },
    {
      "epoch": 0.05771105478650809,
      "grad_norm": 0.6301882266998291,
      "learning_rate": 7.452117519152542e-05,
      "loss": 40.8878,
      "step": 74
    },
    {
      "epoch": 0.05849093390524469,
      "grad_norm": 0.6338295340538025,
      "learning_rate": 7.379736965185368e-05,
      "loss": 40.875,
      "step": 75
    },
    {
      "epoch": 0.05927081302398128,
      "grad_norm": 0.6559311747550964,
      "learning_rate": 7.30670581489344e-05,
      "loss": 40.963,
      "step": 76
    },
    {
      "epoch": 0.06005069214271788,
      "grad_norm": 0.5824295878410339,
      "learning_rate": 7.233044034264034e-05,
      "loss": 40.8572,
      "step": 77
    },
    {
      "epoch": 0.060830571261454476,
      "grad_norm": 0.5482730269432068,
      "learning_rate": 7.158771761692464e-05,
      "loss": 40.906,
      "step": 78
    },
    {
      "epoch": 0.06161045038019107,
      "grad_norm": 0.5890397429466248,
      "learning_rate": 7.083909302476453e-05,
      "loss": 40.9053,
      "step": 79
    },
    {
      "epoch": 0.062390329498927664,
      "grad_norm": 0.6110520958900452,
      "learning_rate": 7.008477123264848e-05,
      "loss": 40.9135,
      "step": 80
    },
    {
      "epoch": 0.06317020861766426,
      "grad_norm": 0.5619910955429077,
      "learning_rate": 6.932495846462261e-05,
      "loss": 40.9086,
      "step": 81
    },
    {
      "epoch": 0.06395008773640086,
      "grad_norm": 0.521420419216156,
      "learning_rate": 6.855986244591104e-05,
      "loss": 40.8481,
      "step": 82
    },
    {
      "epoch": 0.06472996685513745,
      "grad_norm": 0.5547891855239868,
      "learning_rate": 6.778969234612584e-05,
      "loss": 40.9008,
      "step": 83
    },
    {
      "epoch": 0.06550984597387405,
      "grad_norm": 0.426893413066864,
      "learning_rate": 6.701465872208216e-05,
      "loss": 40.8734,
      "step": 84
    },
    {
      "epoch": 0.06628972509261065,
      "grad_norm": 0.5992282032966614,
      "learning_rate": 6.623497346023418e-05,
      "loss": 40.8469,
      "step": 85
    },
    {
      "epoch": 0.06706960421134724,
      "grad_norm": 0.6388483643531799,
      "learning_rate": 6.545084971874738e-05,
      "loss": 40.8863,
      "step": 86
    },
    {
      "epoch": 0.06784948333008384,
      "grad_norm": 0.5074741244316101,
      "learning_rate": 6.466250186922325e-05,
      "loss": 40.9046,
      "step": 87
    },
    {
      "epoch": 0.06862936244882044,
      "grad_norm": 0.5847423672676086,
      "learning_rate": 6.387014543809223e-05,
      "loss": 40.8975,
      "step": 88
    },
    {
      "epoch": 0.06940924156755703,
      "grad_norm": 0.5725265741348267,
      "learning_rate": 6.307399704769099e-05,
      "loss": 40.9042,
      "step": 89
    },
    {
      "epoch": 0.07018912068629363,
      "grad_norm": 0.6477412581443787,
      "learning_rate": 6.227427435703997e-05,
      "loss": 40.8924,
      "step": 90
    },
    {
      "epoch": 0.07096899980503021,
      "grad_norm": 0.5658476948738098,
      "learning_rate": 6.147119600233758e-05,
      "loss": 40.8872,
      "step": 91
    },
    {
      "epoch": 0.07174887892376682,
      "grad_norm": 0.7225454449653625,
      "learning_rate": 6.066498153718735e-05,
      "loss": 40.908,
      "step": 92
    },
    {
      "epoch": 0.07252875804250342,
      "grad_norm": 0.5799012184143066,
      "learning_rate": 5.985585137257401e-05,
      "loss": 40.8696,
      "step": 93
    },
    {
      "epoch": 0.07330863716124,
      "grad_norm": 0.7230017185211182,
      "learning_rate": 5.90440267166055e-05,
      "loss": 40.9175,
      "step": 94
    },
    {
      "epoch": 0.0740885162799766,
      "grad_norm": 0.556864857673645,
      "learning_rate": 5.8229729514036705e-05,
      "loss": 40.9128,
      "step": 95
    },
    {
      "epoch": 0.0748683953987132,
      "grad_norm": 0.6577595472335815,
      "learning_rate": 5.74131823855921e-05,
      "loss": 40.886,
      "step": 96
    },
    {
      "epoch": 0.07564827451744979,
      "grad_norm": 0.8356653451919556,
      "learning_rate": 5.6594608567103456e-05,
      "loss": 40.9435,
      "step": 97
    },
    {
      "epoch": 0.0764281536361864,
      "grad_norm": 0.7458975315093994,
      "learning_rate": 5.577423184847932e-05,
      "loss": 40.8364,
      "step": 98
    },
    {
      "epoch": 0.07720803275492298,
      "grad_norm": 0.782666027545929,
      "learning_rate": 5.495227651252315e-05,
      "loss": 40.8249,
      "step": 99
    },
    {
      "epoch": 0.07798791187365958,
      "grad_norm": 0.9611329436302185,
      "learning_rate": 5.4128967273616625e-05,
      "loss": 40.9458,
      "step": 100
    },
    {
      "epoch": 0.07798791187365958,
      "eval_loss": 10.22016716003418,
      "eval_runtime": 5.7017,
      "eval_samples_per_second": 378.835,
      "eval_steps_per_second": 94.709,
      "step": 100
    },
    {
      "epoch": 0.07876779099239618,
      "grad_norm": 0.6759684085845947,
      "learning_rate": 5.330452921628497e-05,
      "loss": 40.8909,
      "step": 101
    },
    {
      "epoch": 0.07954767011113277,
      "grad_norm": 0.6461939811706543,
      "learning_rate": 5.247918773366112e-05,
      "loss": 40.9316,
      "step": 102
    },
    {
      "epoch": 0.08032754922986937,
      "grad_norm": 0.6997358798980713,
      "learning_rate": 5.165316846586541e-05,
      "loss": 40.8891,
      "step": 103
    },
    {
      "epoch": 0.08110742834860597,
      "grad_norm": 0.678714394569397,
      "learning_rate": 5.0826697238317935e-05,
      "loss": 40.8529,
      "step": 104
    },
    {
      "epoch": 0.08188730746734256,
      "grad_norm": 1.836343765258789,
      "learning_rate": 5e-05,
      "loss": 40.6876,
      "step": 105
    },
    {
      "epoch": 0.08266718658607916,
      "grad_norm": 0.6615349054336548,
      "learning_rate": 4.917330276168208e-05,
      "loss": 40.8481,
      "step": 106
    },
    {
      "epoch": 0.08344706570481575,
      "grad_norm": 0.7867639064788818,
      "learning_rate": 4.834683153413459e-05,
      "loss": 40.8877,
      "step": 107
    },
    {
      "epoch": 0.08422694482355235,
      "grad_norm": 0.8478949666023254,
      "learning_rate": 4.7520812266338885e-05,
      "loss": 40.9754,
      "step": 108
    },
    {
      "epoch": 0.08500682394228895,
      "grad_norm": 1.0905472040176392,
      "learning_rate": 4.669547078371504e-05,
      "loss": 40.9847,
      "step": 109
    },
    {
      "epoch": 0.08578670306102554,
      "grad_norm": 1.2664451599121094,
      "learning_rate": 4.5871032726383386e-05,
      "loss": 40.9787,
      "step": 110
    },
    {
      "epoch": 0.08656658217976214,
      "grad_norm": 1.9054292440414429,
      "learning_rate": 4.504772348747687e-05,
      "loss": 40.8521,
      "step": 111
    },
    {
      "epoch": 0.08734646129849873,
      "grad_norm": 2.2079150676727295,
      "learning_rate": 4.4225768151520694e-05,
      "loss": 40.7565,
      "step": 112
    },
    {
      "epoch": 0.08812634041723533,
      "grad_norm": 0.5081892013549805,
      "learning_rate": 4.3405391432896555e-05,
      "loss": 40.8528,
      "step": 113
    },
    {
      "epoch": 0.08890621953597193,
      "grad_norm": 0.6036549210548401,
      "learning_rate": 4.2586817614407895e-05,
      "loss": 40.8839,
      "step": 114
    },
    {
      "epoch": 0.08968609865470852,
      "grad_norm": 0.6098009347915649,
      "learning_rate": 4.17702704859633e-05,
      "loss": 40.8933,
      "step": 115
    },
    {
      "epoch": 0.09046597777344512,
      "grad_norm": 0.5978115200996399,
      "learning_rate": 4.095597328339452e-05,
      "loss": 40.8339,
      "step": 116
    },
    {
      "epoch": 0.09124585689218172,
      "grad_norm": 0.6828585863113403,
      "learning_rate": 4.0144148627425993e-05,
      "loss": 40.8163,
      "step": 117
    },
    {
      "epoch": 0.0920257360109183,
      "grad_norm": 0.7058219313621521,
      "learning_rate": 3.933501846281267e-05,
      "loss": 40.8641,
      "step": 118
    },
    {
      "epoch": 0.0928056151296549,
      "grad_norm": 0.5530610084533691,
      "learning_rate": 3.852880399766243e-05,
      "loss": 40.8911,
      "step": 119
    },
    {
      "epoch": 0.0935854942483915,
      "grad_norm": 0.5361206531524658,
      "learning_rate": 3.772572564296005e-05,
      "loss": 40.8915,
      "step": 120
    },
    {
      "epoch": 0.0943653733671281,
      "grad_norm": 0.6475891470909119,
      "learning_rate": 3.6926002952309016e-05,
      "loss": 40.8878,
      "step": 121
    },
    {
      "epoch": 0.0951452524858647,
      "grad_norm": 0.7406931519508362,
      "learning_rate": 3.612985456190778e-05,
      "loss": 40.8217,
      "step": 122
    },
    {
      "epoch": 0.09592513160460128,
      "grad_norm": 0.5868107080459595,
      "learning_rate": 3.533749813077677e-05,
      "loss": 40.8544,
      "step": 123
    },
    {
      "epoch": 0.09670501072333788,
      "grad_norm": 0.5925986766815186,
      "learning_rate": 3.4549150281252636e-05,
      "loss": 40.8574,
      "step": 124
    },
    {
      "epoch": 0.09748488984207448,
      "grad_norm": 0.6214819550514221,
      "learning_rate": 3.3765026539765834e-05,
      "loss": 40.8133,
      "step": 125
    },
    {
      "epoch": 0.09826476896081107,
      "grad_norm": 0.7242192625999451,
      "learning_rate": 3.298534127791785e-05,
      "loss": 40.8444,
      "step": 126
    },
    {
      "epoch": 0.09904464807954767,
      "grad_norm": 0.711138129234314,
      "learning_rate": 3.221030765387417e-05,
      "loss": 40.8327,
      "step": 127
    },
    {
      "epoch": 0.09982452719828426,
      "grad_norm": 0.5590301752090454,
      "learning_rate": 3.144013755408895e-05,
      "loss": 40.8405,
      "step": 128
    },
    {
      "epoch": 0.10060440631702086,
      "grad_norm": 0.5557286739349365,
      "learning_rate": 3.0675041535377405e-05,
      "loss": 40.8442,
      "step": 129
    },
    {
      "epoch": 0.10138428543575746,
      "grad_norm": 0.58502596616745,
      "learning_rate": 2.991522876735154e-05,
      "loss": 40.8647,
      "step": 130
    },
    {
      "epoch": 0.10216416455449405,
      "grad_norm": 0.5808131098747253,
      "learning_rate": 2.916090697523549e-05,
      "loss": 40.8416,
      "step": 131
    },
    {
      "epoch": 0.10294404367323065,
      "grad_norm": 0.6121821403503418,
      "learning_rate": 2.8412282383075363e-05,
      "loss": 40.8192,
      "step": 132
    },
    {
      "epoch": 0.10372392279196725,
      "grad_norm": 0.8356872797012329,
      "learning_rate": 2.766955965735968e-05,
      "loss": 40.8188,
      "step": 133
    },
    {
      "epoch": 0.10450380191070384,
      "grad_norm": 0.6568262577056885,
      "learning_rate": 2.693294185106562e-05,
      "loss": 40.9009,
      "step": 134
    },
    {
      "epoch": 0.10528368102944044,
      "grad_norm": 0.5388801097869873,
      "learning_rate": 2.6202630348146324e-05,
      "loss": 40.8361,
      "step": 135
    },
    {
      "epoch": 0.10606356014817703,
      "grad_norm": 0.6164289712905884,
      "learning_rate": 2.547882480847461e-05,
      "loss": 40.9073,
      "step": 136
    },
    {
      "epoch": 0.10684343926691363,
      "grad_norm": 0.5783153772354126,
      "learning_rate": 2.476172311325783e-05,
      "loss": 40.8662,
      "step": 137
    },
    {
      "epoch": 0.10762331838565023,
      "grad_norm": 0.7010378241539001,
      "learning_rate": 2.405152131093926e-05,
      "loss": 40.8108,
      "step": 138
    },
    {
      "epoch": 0.10840319750438682,
      "grad_norm": 0.6553699970245361,
      "learning_rate": 2.3348413563600325e-05,
      "loss": 40.8368,
      "step": 139
    },
    {
      "epoch": 0.10918307662312342,
      "grad_norm": 0.6953468322753906,
      "learning_rate": 2.2652592093878666e-05,
      "loss": 40.863,
      "step": 140
    },
    {
      "epoch": 0.10996295574186,
      "grad_norm": 0.6208988428115845,
      "learning_rate": 2.196424713241637e-05,
      "loss": 40.8207,
      "step": 141
    },
    {
      "epoch": 0.1107428348605966,
      "grad_norm": 0.9228166341781616,
      "learning_rate": 2.128356686585282e-05,
      "loss": 40.8668,
      "step": 142
    },
    {
      "epoch": 0.11152271397933321,
      "grad_norm": 0.5602784156799316,
      "learning_rate": 2.061073738537635e-05,
      "loss": 40.8524,
      "step": 143
    },
    {
      "epoch": 0.1123025930980698,
      "grad_norm": 1.0398088693618774,
      "learning_rate": 1.9945942635848748e-05,
      "loss": 40.9283,
      "step": 144
    },
    {
      "epoch": 0.1130824722168064,
      "grad_norm": 0.758428156375885,
      "learning_rate": 1.928936436551661e-05,
      "loss": 40.8296,
      "step": 145
    },
    {
      "epoch": 0.113862351335543,
      "grad_norm": 0.5899196863174438,
      "learning_rate": 1.8641182076323148e-05,
      "loss": 40.827,
      "step": 146
    },
    {
      "epoch": 0.11464223045427958,
      "grad_norm": 0.7224665880203247,
      "learning_rate": 1.800157297483417e-05,
      "loss": 40.8553,
      "step": 147
    },
    {
      "epoch": 0.11542210957301619,
      "grad_norm": 0.8558909296989441,
      "learning_rate": 1.7370711923791567e-05,
      "loss": 40.8478,
      "step": 148
    },
    {
      "epoch": 0.11620198869175277,
      "grad_norm": 0.8357587456703186,
      "learning_rate": 1.6748771394307585e-05,
      "loss": 40.8605,
      "step": 149
    },
    {
      "epoch": 0.11698186781048937,
      "grad_norm": 0.8920717835426331,
      "learning_rate": 1.6135921418712956e-05,
      "loss": 40.8519,
      "step": 150
    },
    {
      "epoch": 0.11698186781048937,
      "eval_loss": 10.214188575744629,
      "eval_runtime": 5.6767,
      "eval_samples_per_second": 380.5,
      "eval_steps_per_second": 95.125,
      "step": 150
    },
    {
      "epoch": 0.11776174692922597,
      "grad_norm": 0.6067152619361877,
      "learning_rate": 1.553232954407171e-05,
      "loss": 40.8839,
      "step": 151
    },
    {
      "epoch": 0.11854162604796256,
      "grad_norm": 0.591748058795929,
      "learning_rate": 1.4938160786375572e-05,
      "loss": 40.8981,
      "step": 152
    },
    {
      "epoch": 0.11932150516669916,
      "grad_norm": 0.7085707783699036,
      "learning_rate": 1.435357758543015e-05,
      "loss": 40.8714,
      "step": 153
    },
    {
      "epoch": 0.12010138428543576,
      "grad_norm": 0.6638601422309875,
      "learning_rate": 1.3778739760445552e-05,
      "loss": 40.7719,
      "step": 154
    },
    {
      "epoch": 0.12088126340417235,
      "grad_norm": 2.498633861541748,
      "learning_rate": 1.3213804466343421e-05,
      "loss": 40.5888,
      "step": 155
    },
    {
      "epoch": 0.12166114252290895,
      "grad_norm": 0.6192601323127747,
      "learning_rate": 1.2658926150792322e-05,
      "loss": 40.8332,
      "step": 156
    },
    {
      "epoch": 0.12244102164164554,
      "grad_norm": 0.7879806756973267,
      "learning_rate": 1.2114256511983274e-05,
      "loss": 40.9101,
      "step": 157
    },
    {
      "epoch": 0.12322090076038214,
      "grad_norm": 0.7687163949012756,
      "learning_rate": 1.157994445715706e-05,
      "loss": 40.9282,
      "step": 158
    },
    {
      "epoch": 0.12400077987911874,
      "grad_norm": 1.4127614498138428,
      "learning_rate": 1.1056136061894384e-05,
      "loss": 41.0365,
      "step": 159
    },
    {
      "epoch": 0.12478065899785533,
      "grad_norm": 1.3477866649627686,
      "learning_rate": 1.0542974530180327e-05,
      "loss": 40.9209,
      "step": 160
    },
    {
      "epoch": 0.12556053811659193,
      "grad_norm": 2.60963773727417,
      "learning_rate": 1.0040600155253765e-05,
      "loss": 40.9242,
      "step": 161
    },
    {
      "epoch": 0.12634041723532852,
      "grad_norm": 1.668428659439087,
      "learning_rate": 9.549150281252633e-06,
      "loss": 40.8168,
      "step": 162
    },
    {
      "epoch": 0.12712029635406513,
      "grad_norm": 0.5948562026023865,
      "learning_rate": 9.068759265665384e-06,
      "loss": 40.8513,
      "step": 163
    },
    {
      "epoch": 0.12790017547280172,
      "grad_norm": 0.6063466668128967,
      "learning_rate": 8.599558442598998e-06,
      "loss": 40.8619,
      "step": 164
    },
    {
      "epoch": 0.1286800545915383,
      "grad_norm": 0.6097084283828735,
      "learning_rate": 8.141676086873572e-06,
      "loss": 40.794,
      "step": 165
    },
    {
      "epoch": 0.1294599337102749,
      "grad_norm": 0.487762451171875,
      "learning_rate": 7.695237378953223e-06,
      "loss": 40.8706,
      "step": 166
    },
    {
      "epoch": 0.1302398128290115,
      "grad_norm": 0.7122682332992554,
      "learning_rate": 7.260364370723044e-06,
      "loss": 40.8438,
      "step": 167
    },
    {
      "epoch": 0.1310196919477481,
      "grad_norm": 0.7653970122337341,
      "learning_rate": 6.837175952121306e-06,
      "loss": 40.7622,
      "step": 168
    },
    {
      "epoch": 0.13179957106648468,
      "grad_norm": 0.7336371541023254,
      "learning_rate": 6.425787818636131e-06,
      "loss": 40.8553,
      "step": 169
    },
    {
      "epoch": 0.1325794501852213,
      "grad_norm": 0.7477111220359802,
      "learning_rate": 6.026312439675552e-06,
      "loss": 40.8684,
      "step": 170
    },
    {
      "epoch": 0.13335932930395789,
      "grad_norm": 0.7059416174888611,
      "learning_rate": 5.6388590278194096e-06,
      "loss": 40.8433,
      "step": 171
    },
    {
      "epoch": 0.13413920842269447,
      "grad_norm": 0.8016827702522278,
      "learning_rate": 5.263533508961827e-06,
      "loss": 40.8584,
      "step": 172
    },
    {
      "epoch": 0.1349190875414311,
      "grad_norm": 0.5337439775466919,
      "learning_rate": 4.900438493352055e-06,
      "loss": 40.8059,
      "step": 173
    },
    {
      "epoch": 0.13569896666016767,
      "grad_norm": 0.6732336282730103,
      "learning_rate": 4.549673247541875e-06,
      "loss": 40.8148,
      "step": 174
    },
    {
      "epoch": 0.13647884577890426,
      "grad_norm": 0.5739663243293762,
      "learning_rate": 4.2113336672471245e-06,
      "loss": 40.7815,
      "step": 175
    },
    {
      "epoch": 0.13725872489764088,
      "grad_norm": 0.5491018891334534,
      "learning_rate": 3.885512251130763e-06,
      "loss": 40.8219,
      "step": 176
    },
    {
      "epoch": 0.13803860401637746,
      "grad_norm": 0.5932657122612,
      "learning_rate": 3.5722980755146517e-06,
      "loss": 40.7948,
      "step": 177
    },
    {
      "epoch": 0.13881848313511405,
      "grad_norm": 0.550597608089447,
      "learning_rate": 3.271776770026963e-06,
      "loss": 40.7899,
      "step": 178
    },
    {
      "epoch": 0.13959836225385067,
      "grad_norm": 0.6118540167808533,
      "learning_rate": 2.9840304941919415e-06,
      "loss": 40.7929,
      "step": 179
    },
    {
      "epoch": 0.14037824137258725,
      "grad_norm": 0.6819950938224792,
      "learning_rate": 2.7091379149682685e-06,
      "loss": 40.8775,
      "step": 180
    },
    {
      "epoch": 0.14115812049132384,
      "grad_norm": 0.5696614384651184,
      "learning_rate": 2.4471741852423237e-06,
      "loss": 40.7882,
      "step": 181
    },
    {
      "epoch": 0.14193799961006043,
      "grad_norm": 0.626808226108551,
      "learning_rate": 2.1982109232821178e-06,
      "loss": 40.7953,
      "step": 182
    },
    {
      "epoch": 0.14271787872879704,
      "grad_norm": 0.8155060410499573,
      "learning_rate": 1.962316193157593e-06,
      "loss": 40.8196,
      "step": 183
    },
    {
      "epoch": 0.14349775784753363,
      "grad_norm": 0.709487795829773,
      "learning_rate": 1.7395544861325718e-06,
      "loss": 40.8767,
      "step": 184
    },
    {
      "epoch": 0.14427763696627022,
      "grad_norm": 0.5449469685554504,
      "learning_rate": 1.5299867030334814e-06,
      "loss": 40.8318,
      "step": 185
    },
    {
      "epoch": 0.14505751608500683,
      "grad_norm": 0.7718833088874817,
      "learning_rate": 1.333670137599713e-06,
      "loss": 40.8636,
      "step": 186
    },
    {
      "epoch": 0.14583739520374342,
      "grad_norm": 0.7619443535804749,
      "learning_rate": 1.1506584608200367e-06,
      "loss": 40.84,
      "step": 187
    },
    {
      "epoch": 0.14661727432248,
      "grad_norm": 0.6360137462615967,
      "learning_rate": 9.810017062595322e-07,
      "loss": 40.8242,
      "step": 188
    },
    {
      "epoch": 0.14739715344121662,
      "grad_norm": 0.8346300721168518,
      "learning_rate": 8.247462563808817e-07,
      "loss": 40.8598,
      "step": 189
    },
    {
      "epoch": 0.1481770325599532,
      "grad_norm": 0.5493375658988953,
      "learning_rate": 6.819348298638839e-07,
      "loss": 40.836,
      "step": 190
    },
    {
      "epoch": 0.1489569116786898,
      "grad_norm": 0.5633793473243713,
      "learning_rate": 5.526064699265753e-07,
      "loss": 40.8911,
      "step": 191
    },
    {
      "epoch": 0.1497367907974264,
      "grad_norm": 0.6366061568260193,
      "learning_rate": 4.367965336512403e-07,
      "loss": 40.8756,
      "step": 192
    },
    {
      "epoch": 0.150516669916163,
      "grad_norm": 0.9743773937225342,
      "learning_rate": 3.3453668231809286e-07,
      "loss": 40.7972,
      "step": 193
    },
    {
      "epoch": 0.15129654903489959,
      "grad_norm": 0.6744830012321472,
      "learning_rate": 2.458548727494292e-07,
      "loss": 40.7767,
      "step": 194
    },
    {
      "epoch": 0.15207642815363617,
      "grad_norm": 0.6363139152526855,
      "learning_rate": 1.7077534966650766e-07,
      "loss": 40.8682,
      "step": 195
    },
    {
      "epoch": 0.1528563072723728,
      "grad_norm": 0.9359460473060608,
      "learning_rate": 1.0931863906127327e-07,
      "loss": 40.796,
      "step": 196
    },
    {
      "epoch": 0.15363618639110938,
      "grad_norm": 0.6317999362945557,
      "learning_rate": 6.150154258476315e-08,
      "loss": 40.8471,
      "step": 197
    },
    {
      "epoch": 0.15441606550984596,
      "grad_norm": 0.6729257106781006,
      "learning_rate": 2.7337132953697554e-08,
      "loss": 40.8845,
      "step": 198
    },
    {
      "epoch": 0.15519594462858258,
      "grad_norm": 0.7495298385620117,
      "learning_rate": 6.834750376549792e-09,
      "loss": 40.7612,
      "step": 199
    },
    {
      "epoch": 0.15597582374731916,
      "grad_norm": 1.0517314672470093,
      "learning_rate": 0.0,
      "loss": 40.7398,
      "step": 200
    },
    {
      "epoch": 0.15597582374731916,
      "eval_loss": 10.213754653930664,
      "eval_runtime": 5.6758,
      "eval_samples_per_second": 380.56,
      "eval_steps_per_second": 95.14,
      "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": 53326379483136.0,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}