{
  "best_metric": 0.579417884349823,
  "best_model_checkpoint": "miner_id_24/checkpoint-200",
  "epoch": 0.5475701574264202,
  "eval_steps": 50,
  "global_step": 200,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0027378507871321013,
      "grad_norm": 0.43517810106277466,
      "learning_rate": 1e-05,
      "loss": 0.3216,
      "step": 1
    },
    {
      "epoch": 0.0027378507871321013,
      "eval_loss": 0.926390528678894,
      "eval_runtime": 46.3656,
      "eval_samples_per_second": 13.264,
      "eval_steps_per_second": 3.321,
      "step": 1
    },
    {
      "epoch": 0.0054757015742642025,
      "grad_norm": 0.5427243113517761,
      "learning_rate": 2e-05,
      "loss": 0.4112,
      "step": 2
    },
    {
      "epoch": 0.008213552361396304,
      "grad_norm": 0.5720736980438232,
      "learning_rate": 3e-05,
      "loss": 0.3856,
      "step": 3
    },
    {
      "epoch": 0.010951403148528405,
      "grad_norm": 0.6458030343055725,
      "learning_rate": 4e-05,
      "loss": 0.4443,
      "step": 4
    },
    {
      "epoch": 0.013689253935660506,
      "grad_norm": 0.5775730609893799,
      "learning_rate": 5e-05,
      "loss": 0.4592,
      "step": 5
    },
    {
      "epoch": 0.01642710472279261,
      "grad_norm": 0.5384954214096069,
      "learning_rate": 6e-05,
      "loss": 0.4891,
      "step": 6
    },
    {
      "epoch": 0.019164955509924708,
      "grad_norm": 0.5841982960700989,
      "learning_rate": 7e-05,
      "loss": 0.5664,
      "step": 7
    },
    {
      "epoch": 0.02190280629705681,
      "grad_norm": 0.7082967758178711,
      "learning_rate": 8e-05,
      "loss": 0.4895,
      "step": 8
    },
    {
      "epoch": 0.024640657084188913,
      "grad_norm": 0.5473542809486389,
      "learning_rate": 9e-05,
      "loss": 0.5654,
      "step": 9
    },
    {
      "epoch": 0.02737850787132101,
      "grad_norm": 0.5628702044487,
      "learning_rate": 0.0001,
      "loss": 0.4941,
      "step": 10
    },
    {
      "epoch": 0.030116358658453114,
      "grad_norm": 0.4959581792354584,
      "learning_rate": 9.999316524962345e-05,
      "loss": 0.4333,
      "step": 11
    },
    {
      "epoch": 0.03285420944558522,
      "grad_norm": 0.6125951409339905,
      "learning_rate": 9.997266286704631e-05,
      "loss": 0.5806,
      "step": 12
    },
    {
      "epoch": 0.03559206023271732,
      "grad_norm": 0.48384684324264526,
      "learning_rate": 9.993849845741524e-05,
      "loss": 0.4892,
      "step": 13
    },
    {
      "epoch": 0.038329911019849415,
      "grad_norm": 0.5160670876502991,
      "learning_rate": 9.989068136093873e-05,
      "loss": 0.4425,
      "step": 14
    },
    {
      "epoch": 0.04106776180698152,
      "grad_norm": 0.6033713817596436,
      "learning_rate": 9.98292246503335e-05,
      "loss": 0.5603,
      "step": 15
    },
    {
      "epoch": 0.04380561259411362,
      "grad_norm": 0.5714883804321289,
      "learning_rate": 9.975414512725057e-05,
      "loss": 0.5684,
      "step": 16
    },
    {
      "epoch": 0.04654346338124572,
      "grad_norm": 0.605557382106781,
      "learning_rate": 9.966546331768191e-05,
      "loss": 0.5224,
      "step": 17
    },
    {
      "epoch": 0.049281314168377825,
      "grad_norm": 0.6435895562171936,
      "learning_rate": 9.956320346634876e-05,
      "loss": 0.6124,
      "step": 18
    },
    {
      "epoch": 0.05201916495550993,
      "grad_norm": 0.5654250979423523,
      "learning_rate": 9.944739353007344e-05,
      "loss": 0.4892,
      "step": 19
    },
    {
      "epoch": 0.05475701574264202,
      "grad_norm": 0.6192507147789001,
      "learning_rate": 9.931806517013612e-05,
      "loss": 0.5963,
      "step": 20
    },
    {
      "epoch": 0.057494866529774126,
      "grad_norm": 0.5936669111251831,
      "learning_rate": 9.917525374361912e-05,
      "loss": 0.5485,
      "step": 21
    },
    {
      "epoch": 0.06023271731690623,
      "grad_norm": 0.6007648706436157,
      "learning_rate": 9.901899829374047e-05,
      "loss": 0.5706,
      "step": 22
    },
    {
      "epoch": 0.06297056810403832,
      "grad_norm": 0.6136519908905029,
      "learning_rate": 9.884934153917997e-05,
      "loss": 0.6268,
      "step": 23
    },
    {
      "epoch": 0.06570841889117043,
      "grad_norm": 0.6226759552955627,
      "learning_rate": 9.86663298624003e-05,
      "loss": 0.6595,
      "step": 24
    },
    {
      "epoch": 0.06844626967830253,
      "grad_norm": 0.6184474229812622,
      "learning_rate": 9.847001329696653e-05,
      "loss": 0.5882,
      "step": 25
    },
    {
      "epoch": 0.07118412046543464,
      "grad_norm": 0.5875909924507141,
      "learning_rate": 9.826044551386744e-05,
      "loss": 0.6738,
      "step": 26
    },
    {
      "epoch": 0.07392197125256673,
      "grad_norm": 0.6501748561859131,
      "learning_rate": 9.803768380684242e-05,
      "loss": 0.6174,
      "step": 27
    },
    {
      "epoch": 0.07665982203969883,
      "grad_norm": 0.6310875415802002,
      "learning_rate": 9.780178907671789e-05,
      "loss": 0.6519,
      "step": 28
    },
    {
      "epoch": 0.07939767282683094,
      "grad_norm": 0.5908788442611694,
      "learning_rate": 9.755282581475769e-05,
      "loss": 0.6536,
      "step": 29
    },
    {
      "epoch": 0.08213552361396304,
      "grad_norm": 0.5551558136940002,
      "learning_rate": 9.729086208503174e-05,
      "loss": 0.6556,
      "step": 30
    },
    {
      "epoch": 0.08487337440109514,
      "grad_norm": 0.5629632472991943,
      "learning_rate": 9.701596950580806e-05,
      "loss": 0.6827,
      "step": 31
    },
    {
      "epoch": 0.08761122518822724,
      "grad_norm": 0.5703944563865662,
      "learning_rate": 9.672822322997305e-05,
      "loss": 0.6382,
      "step": 32
    },
    {
      "epoch": 0.09034907597535935,
      "grad_norm": 0.637473464012146,
      "learning_rate": 9.642770192448536e-05,
      "loss": 0.761,
      "step": 33
    },
    {
      "epoch": 0.09308692676249145,
      "grad_norm": 0.580679714679718,
      "learning_rate": 9.611448774886924e-05,
      "loss": 0.6359,
      "step": 34
    },
    {
      "epoch": 0.09582477754962354,
      "grad_norm": 0.6390615105628967,
      "learning_rate": 9.578866633275288e-05,
      "loss": 0.7359,
      "step": 35
    },
    {
      "epoch": 0.09856262833675565,
      "grad_norm": 0.6327382922172546,
      "learning_rate": 9.545032675245813e-05,
      "loss": 0.6657,
      "step": 36
    },
    {
      "epoch": 0.10130047912388775,
      "grad_norm": 0.724295973777771,
      "learning_rate": 9.509956150664796e-05,
      "loss": 0.8016,
      "step": 37
    },
    {
      "epoch": 0.10403832991101986,
      "grad_norm": 0.6537374258041382,
      "learning_rate": 9.473646649103818e-05,
      "loss": 0.6627,
      "step": 38
    },
    {
      "epoch": 0.10677618069815195,
      "grad_norm": 0.7102088332176208,
      "learning_rate": 9.43611409721806e-05,
      "loss": 0.6737,
      "step": 39
    },
    {
      "epoch": 0.10951403148528405,
      "grad_norm": 0.6802128553390503,
      "learning_rate": 9.397368756032445e-05,
      "loss": 0.6478,
      "step": 40
    },
    {
      "epoch": 0.11225188227241616,
      "grad_norm": 0.7987683415412903,
      "learning_rate": 9.357421218136386e-05,
      "loss": 0.6532,
      "step": 41
    },
    {
      "epoch": 0.11498973305954825,
      "grad_norm": 0.7601432204246521,
      "learning_rate": 9.316282404787871e-05,
      "loss": 0.6658,
      "step": 42
    },
    {
      "epoch": 0.11772758384668036,
      "grad_norm": 0.8191288113594055,
      "learning_rate": 9.273963562927695e-05,
      "loss": 0.6368,
      "step": 43
    },
    {
      "epoch": 0.12046543463381246,
      "grad_norm": 0.6822831630706787,
      "learning_rate": 9.230476262104677e-05,
      "loss": 0.6164,
      "step": 44
    },
    {
      "epoch": 0.12320328542094455,
      "grad_norm": 0.803491473197937,
      "learning_rate": 9.185832391312644e-05,
      "loss": 0.7305,
      "step": 45
    },
    {
      "epoch": 0.12594113620807665,
      "grad_norm": 0.8561087250709534,
      "learning_rate": 9.140044155740101e-05,
      "loss": 0.6755,
      "step": 46
    },
    {
      "epoch": 0.12867898699520877,
      "grad_norm": 0.8675937652587891,
      "learning_rate": 9.093124073433463e-05,
      "loss": 0.6851,
      "step": 47
    },
    {
      "epoch": 0.13141683778234087,
      "grad_norm": 0.8451431393623352,
      "learning_rate": 9.045084971874738e-05,
      "loss": 0.6557,
      "step": 48
    },
    {
      "epoch": 0.13415468856947296,
      "grad_norm": 0.9068272709846497,
      "learning_rate": 8.995939984474624e-05,
      "loss": 0.5305,
      "step": 49
    },
    {
      "epoch": 0.13689253935660506,
      "grad_norm": 1.224993109703064,
      "learning_rate": 8.945702546981969e-05,
      "loss": 0.5894,
      "step": 50
    },
    {
      "epoch": 0.13689253935660506,
      "eval_loss": 0.644649088382721,
      "eval_runtime": 47.1945,
      "eval_samples_per_second": 13.031,
      "eval_steps_per_second": 3.263,
      "step": 50
    },
    {
      "epoch": 0.13963039014373715,
      "grad_norm": 0.7921010255813599,
      "learning_rate": 8.894386393810563e-05,
      "loss": 0.4175,
      "step": 51
    },
    {
      "epoch": 0.14236824093086928,
      "grad_norm": 0.813897967338562,
      "learning_rate": 8.842005554284296e-05,
      "loss": 0.4333,
      "step": 52
    },
    {
      "epoch": 0.14510609171800137,
      "grad_norm": 0.7878113985061646,
      "learning_rate": 8.788574348801675e-05,
      "loss": 0.4463,
      "step": 53
    },
    {
      "epoch": 0.14784394250513347,
      "grad_norm": 0.566604733467102,
      "learning_rate": 8.73410738492077e-05,
      "loss": 0.463,
      "step": 54
    },
    {
      "epoch": 0.15058179329226556,
      "grad_norm": 0.4362064003944397,
      "learning_rate": 8.678619553365659e-05,
      "loss": 0.4526,
      "step": 55
    },
    {
      "epoch": 0.15331964407939766,
      "grad_norm": 0.4391869604587555,
      "learning_rate": 8.622126023955446e-05,
      "loss": 0.4836,
      "step": 56
    },
    {
      "epoch": 0.15605749486652978,
      "grad_norm": 0.617132306098938,
      "learning_rate": 8.564642241456986e-05,
      "loss": 0.5036,
      "step": 57
    },
    {
      "epoch": 0.15879534565366188,
      "grad_norm": 0.5929650664329529,
      "learning_rate": 8.506183921362443e-05,
      "loss": 0.4649,
      "step": 58
    },
    {
      "epoch": 0.16153319644079397,
      "grad_norm": 0.4837006628513336,
      "learning_rate": 8.44676704559283e-05,
      "loss": 0.4318,
      "step": 59
    },
    {
      "epoch": 0.16427104722792607,
      "grad_norm": 0.5933226346969604,
      "learning_rate": 8.386407858128706e-05,
      "loss": 0.4412,
      "step": 60
    },
    {
      "epoch": 0.16700889801505817,
      "grad_norm": 0.5108177065849304,
      "learning_rate": 8.32512286056924e-05,
      "loss": 0.4354,
      "step": 61
    },
    {
      "epoch": 0.1697467488021903,
      "grad_norm": 0.500123143196106,
      "learning_rate": 8.262928807620843e-05,
      "loss": 0.5675,
      "step": 62
    },
    {
      "epoch": 0.17248459958932238,
      "grad_norm": 0.5396602749824524,
      "learning_rate": 8.199842702516583e-05,
      "loss": 0.497,
      "step": 63
    },
    {
      "epoch": 0.17522245037645448,
      "grad_norm": 0.4962864816188812,
      "learning_rate": 8.135881792367686e-05,
      "loss": 0.525,
      "step": 64
    },
    {
      "epoch": 0.17796030116358658,
      "grad_norm": 0.4592442214488983,
      "learning_rate": 8.07106356344834e-05,
      "loss": 0.4767,
      "step": 65
    },
    {
      "epoch": 0.1806981519507187,
      "grad_norm": 0.5142685174942017,
      "learning_rate": 8.005405736415126e-05,
      "loss": 0.532,
      "step": 66
    },
    {
      "epoch": 0.1834360027378508,
      "grad_norm": 0.4658433496952057,
      "learning_rate": 7.938926261462366e-05,
      "loss": 0.5276,
      "step": 67
    },
    {
      "epoch": 0.1861738535249829,
      "grad_norm": 0.5266741514205933,
      "learning_rate": 7.871643313414718e-05,
      "loss": 0.6303,
      "step": 68
    },
    {
      "epoch": 0.188911704312115,
      "grad_norm": 0.5233520865440369,
      "learning_rate": 7.803575286758364e-05,
      "loss": 0.5421,
      "step": 69
    },
    {
      "epoch": 0.19164955509924708,
      "grad_norm": 0.5366149544715881,
      "learning_rate": 7.734740790612136e-05,
      "loss": 0.6719,
      "step": 70
    },
    {
      "epoch": 0.1943874058863792,
      "grad_norm": 0.4782525599002838,
      "learning_rate": 7.66515864363997e-05,
      "loss": 0.631,
      "step": 71
    },
    {
      "epoch": 0.1971252566735113,
      "grad_norm": 0.5469753742218018,
      "learning_rate": 7.594847868906076e-05,
      "loss": 0.5352,
      "step": 72
    },
    {
      "epoch": 0.1998631074606434,
      "grad_norm": 0.5301793217658997,
      "learning_rate": 7.52382768867422e-05,
      "loss": 0.5856,
      "step": 73
    },
    {
      "epoch": 0.2026009582477755,
      "grad_norm": 0.5326776504516602,
      "learning_rate": 7.452117519152542e-05,
      "loss": 0.616,
      "step": 74
    },
    {
      "epoch": 0.2053388090349076,
      "grad_norm": 0.5593509674072266,
      "learning_rate": 7.379736965185368e-05,
      "loss": 0.5797,
      "step": 75
    },
    {
      "epoch": 0.2080766598220397,
      "grad_norm": 0.5312638878822327,
      "learning_rate": 7.30670581489344e-05,
      "loss": 0.6376,
      "step": 76
    },
    {
      "epoch": 0.2108145106091718,
      "grad_norm": 0.5712041258811951,
      "learning_rate": 7.233044034264034e-05,
      "loss": 0.7024,
      "step": 77
    },
    {
      "epoch": 0.2135523613963039,
      "grad_norm": 0.5954808592796326,
      "learning_rate": 7.158771761692464e-05,
      "loss": 0.7057,
      "step": 78
    },
    {
      "epoch": 0.216290212183436,
      "grad_norm": 0.5758192539215088,
      "learning_rate": 7.083909302476453e-05,
      "loss": 0.6547,
      "step": 79
    },
    {
      "epoch": 0.2190280629705681,
      "grad_norm": 0.541934072971344,
      "learning_rate": 7.008477123264848e-05,
      "loss": 0.6639,
      "step": 80
    },
    {
      "epoch": 0.22176591375770022,
      "grad_norm": 0.5503019690513611,
      "learning_rate": 6.932495846462261e-05,
      "loss": 0.6194,
      "step": 81
    },
    {
      "epoch": 0.2245037645448323,
      "grad_norm": 0.579630434513092,
      "learning_rate": 6.855986244591104e-05,
      "loss": 0.6102,
      "step": 82
    },
    {
      "epoch": 0.2272416153319644,
      "grad_norm": 0.5917394161224365,
      "learning_rate": 6.778969234612584e-05,
      "loss": 0.6337,
      "step": 83
    },
    {
      "epoch": 0.2299794661190965,
      "grad_norm": 0.6438761949539185,
      "learning_rate": 6.701465872208216e-05,
      "loss": 0.7141,
      "step": 84
    },
    {
      "epoch": 0.2327173169062286,
      "grad_norm": 0.6107388138771057,
      "learning_rate": 6.623497346023418e-05,
      "loss": 0.7259,
      "step": 85
    },
    {
      "epoch": 0.23545516769336072,
      "grad_norm": 0.5899257659912109,
      "learning_rate": 6.545084971874738e-05,
      "loss": 0.6022,
      "step": 86
    },
    {
      "epoch": 0.23819301848049282,
      "grad_norm": 0.6176659464836121,
      "learning_rate": 6.466250186922325e-05,
      "loss": 0.7267,
      "step": 87
    },
    {
      "epoch": 0.24093086926762491,
      "grad_norm": 0.6755535006523132,
      "learning_rate": 6.387014543809223e-05,
      "loss": 0.7527,
      "step": 88
    },
    {
      "epoch": 0.243668720054757,
      "grad_norm": 0.6364076137542725,
      "learning_rate": 6.307399704769099e-05,
      "loss": 0.7547,
      "step": 89
    },
    {
      "epoch": 0.2464065708418891,
      "grad_norm": 0.5683395266532898,
      "learning_rate": 6.227427435703997e-05,
      "loss": 0.5567,
      "step": 90
    },
    {
      "epoch": 0.24914442162902123,
      "grad_norm": 0.6077064871788025,
      "learning_rate": 6.147119600233758e-05,
      "loss": 0.6636,
      "step": 91
    },
    {
      "epoch": 0.2518822724161533,
      "grad_norm": 0.6424183249473572,
      "learning_rate": 6.066498153718735e-05,
      "loss": 0.6276,
      "step": 92
    },
    {
      "epoch": 0.2546201232032854,
      "grad_norm": 0.6167230010032654,
      "learning_rate": 5.985585137257401e-05,
      "loss": 0.6197,
      "step": 93
    },
    {
      "epoch": 0.25735797399041754,
      "grad_norm": 0.6204406023025513,
      "learning_rate": 5.90440267166055e-05,
      "loss": 0.6442,
      "step": 94
    },
    {
      "epoch": 0.2600958247775496,
      "grad_norm": 0.6621037721633911,
      "learning_rate": 5.8229729514036705e-05,
      "loss": 0.6569,
      "step": 95
    },
    {
      "epoch": 0.26283367556468173,
      "grad_norm": 0.7806676626205444,
      "learning_rate": 5.74131823855921e-05,
      "loss": 0.5706,
      "step": 96
    },
    {
      "epoch": 0.2655715263518138,
      "grad_norm": 0.7557117342948914,
      "learning_rate": 5.6594608567103456e-05,
      "loss": 0.6183,
      "step": 97
    },
    {
      "epoch": 0.2683093771389459,
      "grad_norm": 0.8610388040542603,
      "learning_rate": 5.577423184847932e-05,
      "loss": 0.6069,
      "step": 98
    },
    {
      "epoch": 0.27104722792607805,
      "grad_norm": 0.8896455764770508,
      "learning_rate": 5.495227651252315e-05,
      "loss": 0.5797,
      "step": 99
    },
    {
      "epoch": 0.2737850787132101,
      "grad_norm": 0.9964320659637451,
      "learning_rate": 5.4128967273616625e-05,
      "loss": 0.5656,
      "step": 100
    },
    {
      "epoch": 0.2737850787132101,
      "eval_loss": 0.614917516708374,
      "eval_runtime": 46.9586,
      "eval_samples_per_second": 13.097,
      "eval_steps_per_second": 3.279,
      "step": 100
    },
    {
      "epoch": 0.27652292950034224,
      "grad_norm": 0.48303577303886414,
      "learning_rate": 5.330452921628497e-05,
      "loss": 0.3853,
      "step": 101
    },
    {
      "epoch": 0.2792607802874743,
      "grad_norm": 0.5548361539840698,
      "learning_rate": 5.247918773366112e-05,
      "loss": 0.4113,
      "step": 102
    },
    {
      "epoch": 0.28199863107460643,
      "grad_norm": 0.5756526589393616,
      "learning_rate": 5.165316846586541e-05,
      "loss": 0.4357,
      "step": 103
    },
    {
      "epoch": 0.28473648186173856,
      "grad_norm": 0.41660749912261963,
      "learning_rate": 5.0826697238317935e-05,
      "loss": 0.4322,
      "step": 104
    },
    {
      "epoch": 0.2874743326488706,
      "grad_norm": 0.4867987334728241,
      "learning_rate": 5e-05,
      "loss": 0.5057,
      "step": 105
    },
    {
      "epoch": 0.29021218343600275,
      "grad_norm": 0.3548595905303955,
      "learning_rate": 4.917330276168208e-05,
      "loss": 0.3582,
      "step": 106
    },
    {
      "epoch": 0.2929500342231348,
      "grad_norm": 0.37873682379722595,
      "learning_rate": 4.834683153413459e-05,
      "loss": 0.475,
      "step": 107
    },
    {
      "epoch": 0.29568788501026694,
      "grad_norm": 0.4003033936023712,
      "learning_rate": 4.7520812266338885e-05,
      "loss": 0.4763,
      "step": 108
    },
    {
      "epoch": 0.29842573579739906,
      "grad_norm": 0.4076235592365265,
      "learning_rate": 4.669547078371504e-05,
      "loss": 0.4791,
      "step": 109
    },
    {
      "epoch": 0.30116358658453113,
      "grad_norm": 0.4385930001735687,
      "learning_rate": 4.5871032726383386e-05,
      "loss": 0.452,
      "step": 110
    },
    {
      "epoch": 0.30390143737166325,
      "grad_norm": 0.505478024482727,
      "learning_rate": 4.504772348747687e-05,
      "loss": 0.461,
      "step": 111
    },
    {
      "epoch": 0.3066392881587953,
      "grad_norm": 0.5559423565864563,
      "learning_rate": 4.4225768151520694e-05,
      "loss": 0.5371,
      "step": 112
    },
    {
      "epoch": 0.30937713894592744,
      "grad_norm": 0.42501118779182434,
      "learning_rate": 4.3405391432896555e-05,
      "loss": 0.4882,
      "step": 113
    },
    {
      "epoch": 0.31211498973305957,
      "grad_norm": 0.4787626564502716,
      "learning_rate": 4.2586817614407895e-05,
      "loss": 0.4129,
      "step": 114
    },
    {
      "epoch": 0.31485284052019163,
      "grad_norm": 0.4444711208343506,
      "learning_rate": 4.17702704859633e-05,
      "loss": 0.4805,
      "step": 115
    },
    {
      "epoch": 0.31759069130732376,
      "grad_norm": 0.49078381061553955,
      "learning_rate": 4.095597328339452e-05,
      "loss": 0.5592,
      "step": 116
    },
    {
      "epoch": 0.3203285420944558,
      "grad_norm": 0.48520082235336304,
      "learning_rate": 4.0144148627425993e-05,
      "loss": 0.5818,
      "step": 117
    },
    {
      "epoch": 0.32306639288158795,
      "grad_norm": 0.5862752199172974,
      "learning_rate": 3.933501846281267e-05,
      "loss": 0.5289,
      "step": 118
    },
    {
      "epoch": 0.3258042436687201,
      "grad_norm": 0.4802629351615906,
      "learning_rate": 3.852880399766243e-05,
      "loss": 0.5038,
      "step": 119
    },
    {
      "epoch": 0.32854209445585214,
      "grad_norm": 0.5067372918128967,
      "learning_rate": 3.772572564296005e-05,
      "loss": 0.6878,
      "step": 120
    },
    {
      "epoch": 0.33127994524298426,
      "grad_norm": 0.5483866930007935,
      "learning_rate": 3.6926002952309016e-05,
      "loss": 0.5261,
      "step": 121
    },
    {
      "epoch": 0.33401779603011633,
      "grad_norm": 0.5017358064651489,
      "learning_rate": 3.612985456190778e-05,
      "loss": 0.6451,
      "step": 122
    },
    {
      "epoch": 0.33675564681724846,
      "grad_norm": 0.5086657404899597,
      "learning_rate": 3.533749813077677e-05,
      "loss": 0.6002,
      "step": 123
    },
    {
      "epoch": 0.3394934976043806,
      "grad_norm": 0.5248523950576782,
      "learning_rate": 3.4549150281252636e-05,
      "loss": 0.6267,
      "step": 124
    },
    {
      "epoch": 0.34223134839151265,
      "grad_norm": 0.5921753644943237,
      "learning_rate": 3.3765026539765834e-05,
      "loss": 0.5616,
      "step": 125
    },
    {
      "epoch": 0.34496919917864477,
      "grad_norm": 0.5002638697624207,
      "learning_rate": 3.298534127791785e-05,
      "loss": 0.6335,
      "step": 126
    },
    {
      "epoch": 0.34770704996577684,
      "grad_norm": 0.480435848236084,
      "learning_rate": 3.221030765387417e-05,
      "loss": 0.5823,
      "step": 127
    },
    {
      "epoch": 0.35044490075290896,
      "grad_norm": 0.5894069671630859,
      "learning_rate": 3.144013755408895e-05,
      "loss": 0.6518,
      "step": 128
    },
    {
      "epoch": 0.3531827515400411,
      "grad_norm": 0.4762018620967865,
      "learning_rate": 3.0675041535377405e-05,
      "loss": 0.6609,
      "step": 129
    },
    {
      "epoch": 0.35592060232717315,
      "grad_norm": 0.5682873725891113,
      "learning_rate": 2.991522876735154e-05,
      "loss": 0.609,
      "step": 130
    },
    {
      "epoch": 0.3586584531143053,
      "grad_norm": 0.5159348845481873,
      "learning_rate": 2.916090697523549e-05,
      "loss": 0.6969,
      "step": 131
    },
    {
      "epoch": 0.3613963039014374,
      "grad_norm": 0.5835972428321838,
      "learning_rate": 2.8412282383075363e-05,
      "loss": 0.646,
      "step": 132
    },
    {
      "epoch": 0.36413415468856947,
      "grad_norm": 0.5606144666671753,
      "learning_rate": 2.766955965735968e-05,
      "loss": 0.617,
      "step": 133
    },
    {
      "epoch": 0.3668720054757016,
      "grad_norm": 0.579714298248291,
      "learning_rate": 2.693294185106562e-05,
      "loss": 0.6353,
      "step": 134
    },
    {
      "epoch": 0.36960985626283366,
      "grad_norm": 0.5519105195999146,
      "learning_rate": 2.6202630348146324e-05,
      "loss": 0.6553,
      "step": 135
    },
    {
      "epoch": 0.3723477070499658,
      "grad_norm": 0.5206592679023743,
      "learning_rate": 2.547882480847461e-05,
      "loss": 0.6049,
      "step": 136
    },
    {
      "epoch": 0.3750855578370979,
      "grad_norm": 0.6127930283546448,
      "learning_rate": 2.476172311325783e-05,
      "loss": 0.67,
      "step": 137
    },
    {
      "epoch": 0.37782340862423,
      "grad_norm": 0.5896944403648376,
      "learning_rate": 2.405152131093926e-05,
      "loss": 0.6948,
      "step": 138
    },
    {
      "epoch": 0.3805612594113621,
      "grad_norm": 0.6119083166122437,
      "learning_rate": 2.3348413563600325e-05,
      "loss": 0.646,
      "step": 139
    },
    {
      "epoch": 0.38329911019849416,
      "grad_norm": 0.6493367552757263,
      "learning_rate": 2.2652592093878666e-05,
      "loss": 0.6156,
      "step": 140
    },
    {
      "epoch": 0.3860369609856263,
      "grad_norm": 0.6688011288642883,
      "learning_rate": 2.196424713241637e-05,
      "loss": 0.7724,
      "step": 141
    },
    {
      "epoch": 0.3887748117727584,
      "grad_norm": 0.6897553205490112,
      "learning_rate": 2.128356686585282e-05,
      "loss": 0.7065,
      "step": 142
    },
    {
      "epoch": 0.3915126625598905,
      "grad_norm": 0.716960608959198,
      "learning_rate": 2.061073738537635e-05,
      "loss": 0.7023,
      "step": 143
    },
    {
      "epoch": 0.3942505133470226,
      "grad_norm": 0.7197480201721191,
      "learning_rate": 1.9945942635848748e-05,
      "loss": 0.6764,
      "step": 144
    },
    {
      "epoch": 0.39698836413415467,
      "grad_norm": 0.6134107112884521,
      "learning_rate": 1.928936436551661e-05,
      "loss": 0.5805,
      "step": 145
    },
    {
      "epoch": 0.3997262149212868,
      "grad_norm": 0.6910088658332825,
      "learning_rate": 1.8641182076323148e-05,
      "loss": 0.6979,
      "step": 146
    },
    {
      "epoch": 0.4024640657084189,
      "grad_norm": 0.6125485301017761,
      "learning_rate": 1.800157297483417e-05,
      "loss": 0.519,
      "step": 147
    },
    {
      "epoch": 0.405201916495551,
      "grad_norm": 0.6933930516242981,
      "learning_rate": 1.7370711923791567e-05,
      "loss": 0.5607,
      "step": 148
    },
    {
      "epoch": 0.4079397672826831,
      "grad_norm": 0.8938409686088562,
      "learning_rate": 1.6748771394307585e-05,
      "loss": 0.6244,
      "step": 149
    },
    {
      "epoch": 0.4106776180698152,
      "grad_norm": 0.92192143201828,
      "learning_rate": 1.6135921418712956e-05,
      "loss": 0.5068,
      "step": 150
    },
    {
      "epoch": 0.4106776180698152,
      "eval_loss": 0.5806074738502502,
      "eval_runtime": 46.9176,
      "eval_samples_per_second": 13.108,
      "eval_steps_per_second": 3.282,
      "step": 150
    },
    {
      "epoch": 0.4134154688569473,
      "grad_norm": 0.30867281556129456,
      "learning_rate": 1.553232954407171e-05,
      "loss": 0.3624,
      "step": 151
    },
    {
      "epoch": 0.4161533196440794,
      "grad_norm": 0.3327908515930176,
      "learning_rate": 1.4938160786375572e-05,
      "loss": 0.3836,
      "step": 152
    },
    {
      "epoch": 0.4188911704312115,
      "grad_norm": 0.3034404516220093,
      "learning_rate": 1.435357758543015e-05,
      "loss": 0.5372,
      "step": 153
    },
    {
      "epoch": 0.4216290212183436,
      "grad_norm": 0.35872888565063477,
      "learning_rate": 1.3778739760445552e-05,
      "loss": 0.4157,
      "step": 154
    },
    {
      "epoch": 0.4243668720054757,
      "grad_norm": 0.36119580268859863,
      "learning_rate": 1.3213804466343421e-05,
      "loss": 0.4569,
      "step": 155
    },
    {
      "epoch": 0.4271047227926078,
      "grad_norm": 0.3833640217781067,
      "learning_rate": 1.2658926150792322e-05,
      "loss": 0.3625,
      "step": 156
    },
    {
      "epoch": 0.42984257357973993,
      "grad_norm": 0.4162719249725342,
      "learning_rate": 1.2114256511983274e-05,
      "loss": 0.4055,
      "step": 157
    },
    {
      "epoch": 0.432580424366872,
      "grad_norm": 0.40643706917762756,
      "learning_rate": 1.157994445715706e-05,
      "loss": 0.4304,
      "step": 158
    },
    {
      "epoch": 0.4353182751540041,
      "grad_norm": 0.4088394343852997,
      "learning_rate": 1.1056136061894384e-05,
      "loss": 0.5193,
      "step": 159
    },
    {
      "epoch": 0.4380561259411362,
      "grad_norm": 0.3853205442428589,
      "learning_rate": 1.0542974530180327e-05,
      "loss": 0.4765,
      "step": 160
    },
    {
      "epoch": 0.4407939767282683,
      "grad_norm": 0.3788997530937195,
      "learning_rate": 1.0040600155253765e-05,
      "loss": 0.4599,
      "step": 161
    },
    {
      "epoch": 0.44353182751540043,
      "grad_norm": 0.44248494505882263,
      "learning_rate": 9.549150281252633e-06,
      "loss": 0.5097,
      "step": 162
    },
    {
      "epoch": 0.4462696783025325,
      "grad_norm": 0.428284615278244,
      "learning_rate": 9.068759265665384e-06,
      "loss": 0.5318,
      "step": 163
    },
    {
      "epoch": 0.4490075290896646,
      "grad_norm": 0.36314842104911804,
      "learning_rate": 8.599558442598998e-06,
      "loss": 0.3789,
      "step": 164
    },
    {
      "epoch": 0.4517453798767967,
      "grad_norm": 0.3726077675819397,
      "learning_rate": 8.141676086873572e-06,
      "loss": 0.443,
      "step": 165
    },
    {
      "epoch": 0.4544832306639288,
      "grad_norm": 0.43893277645111084,
      "learning_rate": 7.695237378953223e-06,
      "loss": 0.6153,
      "step": 166
    },
    {
      "epoch": 0.45722108145106094,
      "grad_norm": 0.4690017104148865,
      "learning_rate": 7.260364370723044e-06,
      "loss": 0.6564,
      "step": 167
    },
    {
      "epoch": 0.459958932238193,
      "grad_norm": 0.4478749930858612,
      "learning_rate": 6.837175952121306e-06,
      "loss": 0.549,
      "step": 168
    },
    {
      "epoch": 0.46269678302532513,
      "grad_norm": 0.5050341486930847,
      "learning_rate": 6.425787818636131e-06,
      "loss": 0.4429,
      "step": 169
    },
    {
      "epoch": 0.4654346338124572,
      "grad_norm": 0.4265983998775482,
      "learning_rate": 6.026312439675552e-06,
      "loss": 0.579,
      "step": 170
    },
    {
      "epoch": 0.4681724845995893,
      "grad_norm": 0.4081089198589325,
      "learning_rate": 5.6388590278194096e-06,
      "loss": 0.6018,
      "step": 171
    },
    {
      "epoch": 0.47091033538672145,
      "grad_norm": 0.44113799929618835,
      "learning_rate": 5.263533508961827e-06,
      "loss": 0.5076,
      "step": 172
    },
    {
      "epoch": 0.4736481861738535,
      "grad_norm": 0.5111371874809265,
      "learning_rate": 4.900438493352055e-06,
      "loss": 0.6401,
      "step": 173
    },
    {
      "epoch": 0.47638603696098564,
      "grad_norm": 0.4455251097679138,
      "learning_rate": 4.549673247541875e-06,
      "loss": 0.5662,
      "step": 174
    },
    {
      "epoch": 0.4791238877481177,
      "grad_norm": 0.5298932790756226,
      "learning_rate": 4.2113336672471245e-06,
      "loss": 0.6069,
      "step": 175
    },
    {
      "epoch": 0.48186173853524983,
      "grad_norm": 0.4841381907463074,
      "learning_rate": 3.885512251130763e-06,
      "loss": 0.5805,
      "step": 176
    },
    {
      "epoch": 0.48459958932238195,
      "grad_norm": 0.528912365436554,
      "learning_rate": 3.5722980755146517e-06,
      "loss": 0.6935,
      "step": 177
    },
    {
      "epoch": 0.487337440109514,
      "grad_norm": 0.49814772605895996,
      "learning_rate": 3.271776770026963e-06,
      "loss": 0.6417,
      "step": 178
    },
    {
      "epoch": 0.49007529089664614,
      "grad_norm": 0.644501805305481,
      "learning_rate": 2.9840304941919415e-06,
      "loss": 0.7321,
      "step": 179
    },
    {
      "epoch": 0.4928131416837782,
      "grad_norm": 0.5219155550003052,
      "learning_rate": 2.7091379149682685e-06,
      "loss": 0.6499,
      "step": 180
    },
    {
      "epoch": 0.49555099247091033,
      "grad_norm": 0.5591123104095459,
      "learning_rate": 2.4471741852423237e-06,
      "loss": 0.6235,
      "step": 181
    },
    {
      "epoch": 0.49828884325804246,
      "grad_norm": 0.5643157362937927,
      "learning_rate": 2.1982109232821178e-06,
      "loss": 0.6322,
      "step": 182
    },
    {
      "epoch": 0.5010266940451745,
      "grad_norm": 0.525851845741272,
      "learning_rate": 1.962316193157593e-06,
      "loss": 0.6018,
      "step": 183
    },
    {
      "epoch": 0.5037645448323066,
      "grad_norm": 0.557957112789154,
      "learning_rate": 1.7395544861325718e-06,
      "loss": 0.6399,
      "step": 184
    },
    {
      "epoch": 0.5065023956194388,
      "grad_norm": 0.5874179005622864,
      "learning_rate": 1.5299867030334814e-06,
      "loss": 0.6415,
      "step": 185
    },
    {
      "epoch": 0.5092402464065708,
      "grad_norm": 0.543042778968811,
      "learning_rate": 1.333670137599713e-06,
      "loss": 0.6422,
      "step": 186
    },
    {
      "epoch": 0.5119780971937029,
      "grad_norm": 0.5876917839050293,
      "learning_rate": 1.1506584608200367e-06,
      "loss": 0.6594,
      "step": 187
    },
    {
      "epoch": 0.5147159479808351,
      "grad_norm": 0.6201353073120117,
      "learning_rate": 9.810017062595322e-07,
      "loss": 0.6686,
      "step": 188
    },
    {
      "epoch": 0.5174537987679672,
      "grad_norm": 0.5771745443344116,
      "learning_rate": 8.247462563808817e-07,
      "loss": 0.6264,
      "step": 189
    },
    {
      "epoch": 0.5201916495550992,
      "grad_norm": 0.5823987722396851,
      "learning_rate": 6.819348298638839e-07,
      "loss": 0.6398,
      "step": 190
    },
    {
      "epoch": 0.5229295003422314,
      "grad_norm": 0.696465015411377,
      "learning_rate": 5.526064699265753e-07,
      "loss": 0.7191,
      "step": 191
    },
    {
      "epoch": 0.5256673511293635,
      "grad_norm": 0.6874654293060303,
      "learning_rate": 4.367965336512403e-07,
      "loss": 0.6821,
      "step": 192
    },
    {
      "epoch": 0.5284052019164955,
      "grad_norm": 0.6809566020965576,
      "learning_rate": 3.3453668231809286e-07,
      "loss": 0.7152,
      "step": 193
    },
    {
      "epoch": 0.5311430527036276,
      "grad_norm": 0.6779336333274841,
      "learning_rate": 2.458548727494292e-07,
      "loss": 0.6317,
      "step": 194
    },
    {
      "epoch": 0.5338809034907598,
      "grad_norm": 0.7187902927398682,
      "learning_rate": 1.7077534966650766e-07,
      "loss": 0.7142,
      "step": 195
    },
    {
      "epoch": 0.5366187542778919,
      "grad_norm": 0.7348049283027649,
      "learning_rate": 1.0931863906127327e-07,
      "loss": 0.7586,
      "step": 196
    },
    {
      "epoch": 0.5393566050650239,
      "grad_norm": 0.825839102268219,
      "learning_rate": 6.150154258476315e-08,
      "loss": 0.6164,
      "step": 197
    },
    {
      "epoch": 0.5420944558521561,
      "grad_norm": 0.8022580742835999,
      "learning_rate": 2.7337132953697554e-08,
      "loss": 0.5633,
      "step": 198
    },
    {
      "epoch": 0.5448323066392882,
      "grad_norm": 0.8996812701225281,
      "learning_rate": 6.834750376549792e-09,
      "loss": 0.6302,
      "step": 199
    },
    {
      "epoch": 0.5475701574264202,
      "grad_norm": 1.0095319747924805,
      "learning_rate": 0.0,
      "loss": 0.4508,
      "step": 200
    },
    {
      "epoch": 0.5475701574264202,
      "eval_loss": 0.579417884349823,
      "eval_runtime": 47.2156,
      "eval_samples_per_second": 13.025,
      "eval_steps_per_second": 3.262,
      "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": 3.066053848800952e+17,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}