{
  "best_metric": 0.7094779014587402,
  "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": 0.9658456444740295,
      "learning_rate": 1e-05,
      "loss": 0.5772,
      "step": 1
    },
    {
      "epoch": 0.0027378507871321013,
      "eval_loss": 0.929009735584259,
      "eval_runtime": 11.1426,
      "eval_samples_per_second": 55.193,
      "eval_steps_per_second": 13.821,
      "step": 1
    },
    {
      "epoch": 0.0054757015742642025,
      "grad_norm": 1.3500820398330688,
      "learning_rate": 2e-05,
      "loss": 0.6447,
      "step": 2
    },
    {
      "epoch": 0.008213552361396304,
      "grad_norm": 1.0925943851470947,
      "learning_rate": 3e-05,
      "loss": 0.6973,
      "step": 3
    },
    {
      "epoch": 0.010951403148528405,
      "grad_norm": 0.7716025710105896,
      "learning_rate": 4e-05,
      "loss": 0.708,
      "step": 4
    },
    {
      "epoch": 0.013689253935660506,
      "grad_norm": 0.7066163420677185,
      "learning_rate": 5e-05,
      "loss": 0.7476,
      "step": 5
    },
    {
      "epoch": 0.01642710472279261,
      "grad_norm": 0.8003386855125427,
      "learning_rate": 6e-05,
      "loss": 0.7058,
      "step": 6
    },
    {
      "epoch": 0.019164955509924708,
      "grad_norm": 0.8472021818161011,
      "learning_rate": 7e-05,
      "loss": 0.7514,
      "step": 7
    },
    {
      "epoch": 0.02190280629705681,
      "grad_norm": 0.9536767601966858,
      "learning_rate": 8e-05,
      "loss": 0.8067,
      "step": 8
    },
    {
      "epoch": 0.024640657084188913,
      "grad_norm": 0.7618087530136108,
      "learning_rate": 9e-05,
      "loss": 0.6588,
      "step": 9
    },
    {
      "epoch": 0.02737850787132101,
      "grad_norm": 0.8190032243728638,
      "learning_rate": 0.0001,
      "loss": 0.638,
      "step": 10
    },
    {
      "epoch": 0.030116358658453114,
      "grad_norm": 0.9457001686096191,
      "learning_rate": 9.999316524962345e-05,
      "loss": 0.6986,
      "step": 11
    },
    {
      "epoch": 0.03285420944558522,
      "grad_norm": 0.8576842546463013,
      "learning_rate": 9.997266286704631e-05,
      "loss": 0.6826,
      "step": 12
    },
    {
      "epoch": 0.03559206023271732,
      "grad_norm": 0.9162773489952087,
      "learning_rate": 9.993849845741524e-05,
      "loss": 0.7612,
      "step": 13
    },
    {
      "epoch": 0.038329911019849415,
      "grad_norm": 0.9779077172279358,
      "learning_rate": 9.989068136093873e-05,
      "loss": 0.6449,
      "step": 14
    },
    {
      "epoch": 0.04106776180698152,
      "grad_norm": 0.893581748008728,
      "learning_rate": 9.98292246503335e-05,
      "loss": 0.7743,
      "step": 15
    },
    {
      "epoch": 0.04380561259411362,
      "grad_norm": 0.9086719751358032,
      "learning_rate": 9.975414512725057e-05,
      "loss": 0.6744,
      "step": 16
    },
    {
      "epoch": 0.04654346338124572,
      "grad_norm": 0.8590047955513,
      "learning_rate": 9.966546331768191e-05,
      "loss": 0.6867,
      "step": 17
    },
    {
      "epoch": 0.049281314168377825,
      "grad_norm": 0.8588681817054749,
      "learning_rate": 9.956320346634876e-05,
      "loss": 0.6462,
      "step": 18
    },
    {
      "epoch": 0.05201916495550993,
      "grad_norm": 0.7994069457054138,
      "learning_rate": 9.944739353007344e-05,
      "loss": 0.8088,
      "step": 19
    },
    {
      "epoch": 0.05475701574264202,
      "grad_norm": 0.9434356093406677,
      "learning_rate": 9.931806517013612e-05,
      "loss": 0.7477,
      "step": 20
    },
    {
      "epoch": 0.057494866529774126,
      "grad_norm": 0.9234486818313599,
      "learning_rate": 9.917525374361912e-05,
      "loss": 0.8436,
      "step": 21
    },
    {
      "epoch": 0.06023271731690623,
      "grad_norm": 0.9644221663475037,
      "learning_rate": 9.901899829374047e-05,
      "loss": 0.7964,
      "step": 22
    },
    {
      "epoch": 0.06297056810403832,
      "grad_norm": 0.9162356853485107,
      "learning_rate": 9.884934153917997e-05,
      "loss": 0.7044,
      "step": 23
    },
    {
      "epoch": 0.06570841889117043,
      "grad_norm": 0.9346621036529541,
      "learning_rate": 9.86663298624003e-05,
      "loss": 0.7853,
      "step": 24
    },
    {
      "epoch": 0.06844626967830253,
      "grad_norm": 1.016625165939331,
      "learning_rate": 9.847001329696653e-05,
      "loss": 0.7065,
      "step": 25
    },
    {
      "epoch": 0.07118412046543464,
      "grad_norm": 1.0262483358383179,
      "learning_rate": 9.826044551386744e-05,
      "loss": 0.7614,
      "step": 26
    },
    {
      "epoch": 0.07392197125256673,
      "grad_norm": 1.0150127410888672,
      "learning_rate": 9.803768380684242e-05,
      "loss": 0.8218,
      "step": 27
    },
    {
      "epoch": 0.07665982203969883,
      "grad_norm": 1.0476619005203247,
      "learning_rate": 9.780178907671789e-05,
      "loss": 0.7207,
      "step": 28
    },
    {
      "epoch": 0.07939767282683094,
      "grad_norm": 1.077161192893982,
      "learning_rate": 9.755282581475769e-05,
      "loss": 0.893,
      "step": 29
    },
    {
      "epoch": 0.08213552361396304,
      "grad_norm": 1.032679557800293,
      "learning_rate": 9.729086208503174e-05,
      "loss": 0.7676,
      "step": 30
    },
    {
      "epoch": 0.08487337440109514,
      "grad_norm": 1.1500176191329956,
      "learning_rate": 9.701596950580806e-05,
      "loss": 0.7649,
      "step": 31
    },
    {
      "epoch": 0.08761122518822724,
      "grad_norm": 1.0963420867919922,
      "learning_rate": 9.672822322997305e-05,
      "loss": 0.7758,
      "step": 32
    },
    {
      "epoch": 0.09034907597535935,
      "grad_norm": 1.0377020835876465,
      "learning_rate": 9.642770192448536e-05,
      "loss": 0.7865,
      "step": 33
    },
    {
      "epoch": 0.09308692676249145,
      "grad_norm": 1.1485481262207031,
      "learning_rate": 9.611448774886924e-05,
      "loss": 0.8313,
      "step": 34
    },
    {
      "epoch": 0.09582477754962354,
      "grad_norm": 1.106980323791504,
      "learning_rate": 9.578866633275288e-05,
      "loss": 0.7648,
      "step": 35
    },
    {
      "epoch": 0.09856262833675565,
      "grad_norm": 1.2446861267089844,
      "learning_rate": 9.545032675245813e-05,
      "loss": 0.7919,
      "step": 36
    },
    {
      "epoch": 0.10130047912388775,
      "grad_norm": 1.1486124992370605,
      "learning_rate": 9.509956150664796e-05,
      "loss": 0.6852,
      "step": 37
    },
    {
      "epoch": 0.10403832991101986,
      "grad_norm": 1.1084544658660889,
      "learning_rate": 9.473646649103818e-05,
      "loss": 0.7173,
      "step": 38
    },
    {
      "epoch": 0.10677618069815195,
      "grad_norm": 1.2043566703796387,
      "learning_rate": 9.43611409721806e-05,
      "loss": 0.7867,
      "step": 39
    },
    {
      "epoch": 0.10951403148528405,
      "grad_norm": 1.2409218549728394,
      "learning_rate": 9.397368756032445e-05,
      "loss": 0.6951,
      "step": 40
    },
    {
      "epoch": 0.11225188227241616,
      "grad_norm": 1.181588053703308,
      "learning_rate": 9.357421218136386e-05,
      "loss": 0.7233,
      "step": 41
    },
    {
      "epoch": 0.11498973305954825,
      "grad_norm": 1.2346372604370117,
      "learning_rate": 9.316282404787871e-05,
      "loss": 0.6692,
      "step": 42
    },
    {
      "epoch": 0.11772758384668036,
      "grad_norm": 1.3046445846557617,
      "learning_rate": 9.273963562927695e-05,
      "loss": 0.849,
      "step": 43
    },
    {
      "epoch": 0.12046543463381246,
      "grad_norm": 1.3855444192886353,
      "learning_rate": 9.230476262104677e-05,
      "loss": 0.8679,
      "step": 44
    },
    {
      "epoch": 0.12320328542094455,
      "grad_norm": 1.380177617073059,
      "learning_rate": 9.185832391312644e-05,
      "loss": 0.8419,
      "step": 45
    },
    {
      "epoch": 0.12594113620807665,
      "grad_norm": 1.347255825996399,
      "learning_rate": 9.140044155740101e-05,
      "loss": 0.6917,
      "step": 46
    },
    {
      "epoch": 0.12867898699520877,
      "grad_norm": 1.5654364824295044,
      "learning_rate": 9.093124073433463e-05,
      "loss": 0.8457,
      "step": 47
    },
    {
      "epoch": 0.13141683778234087,
      "grad_norm": 1.557848334312439,
      "learning_rate": 9.045084971874738e-05,
      "loss": 0.6834,
      "step": 48
    },
    {
      "epoch": 0.13415468856947296,
      "grad_norm": 1.9580930471420288,
      "learning_rate": 8.995939984474624e-05,
      "loss": 0.6818,
      "step": 49
    },
    {
      "epoch": 0.13689253935660506,
      "grad_norm": 1.9732745885849,
      "learning_rate": 8.945702546981969e-05,
      "loss": 0.6808,
      "step": 50
    },
    {
      "epoch": 0.13689253935660506,
      "eval_loss": 0.7642375230789185,
      "eval_runtime": 11.1662,
      "eval_samples_per_second": 55.077,
      "eval_steps_per_second": 13.792,
      "step": 50
    },
    {
      "epoch": 0.13963039014373715,
      "grad_norm": 0.907207190990448,
      "learning_rate": 8.894386393810563e-05,
      "loss": 0.6663,
      "step": 51
    },
    {
      "epoch": 0.14236824093086928,
      "grad_norm": 0.8791018128395081,
      "learning_rate": 8.842005554284296e-05,
      "loss": 0.6652,
      "step": 52
    },
    {
      "epoch": 0.14510609171800137,
      "grad_norm": 0.718735933303833,
      "learning_rate": 8.788574348801675e-05,
      "loss": 0.6956,
      "step": 53
    },
    {
      "epoch": 0.14784394250513347,
      "grad_norm": 0.621556282043457,
      "learning_rate": 8.73410738492077e-05,
      "loss": 0.6846,
      "step": 54
    },
    {
      "epoch": 0.15058179329226556,
      "grad_norm": 0.5743134021759033,
      "learning_rate": 8.678619553365659e-05,
      "loss": 0.6797,
      "step": 55
    },
    {
      "epoch": 0.15331964407939766,
      "grad_norm": 0.5687192678451538,
      "learning_rate": 8.622126023955446e-05,
      "loss": 0.7532,
      "step": 56
    },
    {
      "epoch": 0.15605749486652978,
      "grad_norm": 0.6007315516471863,
      "learning_rate": 8.564642241456986e-05,
      "loss": 0.6394,
      "step": 57
    },
    {
      "epoch": 0.15879534565366188,
      "grad_norm": 0.6537332534790039,
      "learning_rate": 8.506183921362443e-05,
      "loss": 0.6549,
      "step": 58
    },
    {
      "epoch": 0.16153319644079397,
      "grad_norm": 0.6303588151931763,
      "learning_rate": 8.44676704559283e-05,
      "loss": 0.7424,
      "step": 59
    },
    {
      "epoch": 0.16427104722792607,
      "grad_norm": 0.6427813172340393,
      "learning_rate": 8.386407858128706e-05,
      "loss": 0.6965,
      "step": 60
    },
    {
      "epoch": 0.16700889801505817,
      "grad_norm": 0.7468997240066528,
      "learning_rate": 8.32512286056924e-05,
      "loss": 0.7886,
      "step": 61
    },
    {
      "epoch": 0.1697467488021903,
      "grad_norm": 0.7126947641372681,
      "learning_rate": 8.262928807620843e-05,
      "loss": 0.8976,
      "step": 62
    },
    {
      "epoch": 0.17248459958932238,
      "grad_norm": 0.7447794675827026,
      "learning_rate": 8.199842702516583e-05,
      "loss": 0.7241,
      "step": 63
    },
    {
      "epoch": 0.17522245037645448,
      "grad_norm": 0.6995065808296204,
      "learning_rate": 8.135881792367686e-05,
      "loss": 0.679,
      "step": 64
    },
    {
      "epoch": 0.17796030116358658,
      "grad_norm": 0.7055516242980957,
      "learning_rate": 8.07106356344834e-05,
      "loss": 0.6631,
      "step": 65
    },
    {
      "epoch": 0.1806981519507187,
      "grad_norm": 0.7748335599899292,
      "learning_rate": 8.005405736415126e-05,
      "loss": 0.7398,
      "step": 66
    },
    {
      "epoch": 0.1834360027378508,
      "grad_norm": 0.8008682727813721,
      "learning_rate": 7.938926261462366e-05,
      "loss": 0.8216,
      "step": 67
    },
    {
      "epoch": 0.1861738535249829,
      "grad_norm": 0.7823235392570496,
      "learning_rate": 7.871643313414718e-05,
      "loss": 0.7764,
      "step": 68
    },
    {
      "epoch": 0.188911704312115,
      "grad_norm": 0.7573645710945129,
      "learning_rate": 7.803575286758364e-05,
      "loss": 0.7909,
      "step": 69
    },
    {
      "epoch": 0.19164955509924708,
      "grad_norm": 0.713489294052124,
      "learning_rate": 7.734740790612136e-05,
      "loss": 0.7913,
      "step": 70
    },
    {
      "epoch": 0.1943874058863792,
      "grad_norm": 0.8689866065979004,
      "learning_rate": 7.66515864363997e-05,
      "loss": 0.7664,
      "step": 71
    },
    {
      "epoch": 0.1971252566735113,
      "grad_norm": 0.8085822463035583,
      "learning_rate": 7.594847868906076e-05,
      "loss": 0.6262,
      "step": 72
    },
    {
      "epoch": 0.1998631074606434,
      "grad_norm": 0.821539580821991,
      "learning_rate": 7.52382768867422e-05,
      "loss": 0.6898,
      "step": 73
    },
    {
      "epoch": 0.2026009582477755,
      "grad_norm": 0.8535922765731812,
      "learning_rate": 7.452117519152542e-05,
      "loss": 0.7487,
      "step": 74
    },
    {
      "epoch": 0.2053388090349076,
      "grad_norm": 0.7795343995094299,
      "learning_rate": 7.379736965185368e-05,
      "loss": 0.6355,
      "step": 75
    },
    {
      "epoch": 0.2080766598220397,
      "grad_norm": 0.861770510673523,
      "learning_rate": 7.30670581489344e-05,
      "loss": 0.7566,
      "step": 76
    },
    {
      "epoch": 0.2108145106091718,
      "grad_norm": 0.9425360560417175,
      "learning_rate": 7.233044034264034e-05,
      "loss": 0.6402,
      "step": 77
    },
    {
      "epoch": 0.2135523613963039,
      "grad_norm": 0.9633281230926514,
      "learning_rate": 7.158771761692464e-05,
      "loss": 0.7773,
      "step": 78
    },
    {
      "epoch": 0.216290212183436,
      "grad_norm": 0.9081418514251709,
      "learning_rate": 7.083909302476453e-05,
      "loss": 0.7489,
      "step": 79
    },
    {
      "epoch": 0.2190280629705681,
      "grad_norm": 0.9595448970794678,
      "learning_rate": 7.008477123264848e-05,
      "loss": 0.7968,
      "step": 80
    },
    {
      "epoch": 0.22176591375770022,
      "grad_norm": 0.9442641139030457,
      "learning_rate": 6.932495846462261e-05,
      "loss": 0.7322,
      "step": 81
    },
    {
      "epoch": 0.2245037645448323,
      "grad_norm": 1.036850094795227,
      "learning_rate": 6.855986244591104e-05,
      "loss": 0.719,
      "step": 82
    },
    {
      "epoch": 0.2272416153319644,
      "grad_norm": 1.0352271795272827,
      "learning_rate": 6.778969234612584e-05,
      "loss": 0.7645,
      "step": 83
    },
    {
      "epoch": 0.2299794661190965,
      "grad_norm": 1.047561764717102,
      "learning_rate": 6.701465872208216e-05,
      "loss": 0.7152,
      "step": 84
    },
    {
      "epoch": 0.2327173169062286,
      "grad_norm": 1.1346429586410522,
      "learning_rate": 6.623497346023418e-05,
      "loss": 0.7856,
      "step": 85
    },
    {
      "epoch": 0.23545516769336072,
      "grad_norm": 1.0335546731948853,
      "learning_rate": 6.545084971874738e-05,
      "loss": 0.7373,
      "step": 86
    },
    {
      "epoch": 0.23819301848049282,
      "grad_norm": 1.0438271760940552,
      "learning_rate": 6.466250186922325e-05,
      "loss": 0.7004,
      "step": 87
    },
    {
      "epoch": 0.24093086926762491,
      "grad_norm": 1.024743914604187,
      "learning_rate": 6.387014543809223e-05,
      "loss": 0.7099,
      "step": 88
    },
    {
      "epoch": 0.243668720054757,
      "grad_norm": 1.0877102613449097,
      "learning_rate": 6.307399704769099e-05,
      "loss": 0.7734,
      "step": 89
    },
    {
      "epoch": 0.2464065708418891,
      "grad_norm": 0.9928415417671204,
      "learning_rate": 6.227427435703997e-05,
      "loss": 0.6201,
      "step": 90
    },
    {
      "epoch": 0.24914442162902123,
      "grad_norm": 1.138893961906433,
      "learning_rate": 6.147119600233758e-05,
      "loss": 0.8048,
      "step": 91
    },
    {
      "epoch": 0.2518822724161533,
      "grad_norm": 1.1380290985107422,
      "learning_rate": 6.066498153718735e-05,
      "loss": 0.7174,
      "step": 92
    },
    {
      "epoch": 0.2546201232032854,
      "grad_norm": 1.19147789478302,
      "learning_rate": 5.985585137257401e-05,
      "loss": 0.7171,
      "step": 93
    },
    {
      "epoch": 0.25735797399041754,
      "grad_norm": 1.3129031658172607,
      "learning_rate": 5.90440267166055e-05,
      "loss": 0.7751,
      "step": 94
    },
    {
      "epoch": 0.2600958247775496,
      "grad_norm": 1.297154188156128,
      "learning_rate": 5.8229729514036705e-05,
      "loss": 0.7836,
      "step": 95
    },
    {
      "epoch": 0.26283367556468173,
      "grad_norm": 1.1628834009170532,
      "learning_rate": 5.74131823855921e-05,
      "loss": 0.6177,
      "step": 96
    },
    {
      "epoch": 0.2655715263518138,
      "grad_norm": 1.4592561721801758,
      "learning_rate": 5.6594608567103456e-05,
      "loss": 0.7772,
      "step": 97
    },
    {
      "epoch": 0.2683093771389459,
      "grad_norm": 1.4401648044586182,
      "learning_rate": 5.577423184847932e-05,
      "loss": 0.6217,
      "step": 98
    },
    {
      "epoch": 0.27104722792607805,
      "grad_norm": 1.591920018196106,
      "learning_rate": 5.495227651252315e-05,
      "loss": 0.6362,
      "step": 99
    },
    {
      "epoch": 0.2737850787132101,
      "grad_norm": 1.880920648574829,
      "learning_rate": 5.4128967273616625e-05,
      "loss": 0.6219,
      "step": 100
    },
    {
      "epoch": 0.2737850787132101,
      "eval_loss": 0.7305797934532166,
      "eval_runtime": 11.1215,
      "eval_samples_per_second": 55.298,
      "eval_steps_per_second": 13.847,
      "step": 100
    },
    {
      "epoch": 0.27652292950034224,
      "grad_norm": 0.5455410480499268,
      "learning_rate": 5.330452921628497e-05,
      "loss": 0.6095,
      "step": 101
    },
    {
      "epoch": 0.2792607802874743,
      "grad_norm": 0.5593652725219727,
      "learning_rate": 5.247918773366112e-05,
      "loss": 0.7271,
      "step": 102
    },
    {
      "epoch": 0.28199863107460643,
      "grad_norm": 0.5539401173591614,
      "learning_rate": 5.165316846586541e-05,
      "loss": 0.7156,
      "step": 103
    },
    {
      "epoch": 0.28473648186173856,
      "grad_norm": 0.5743287205696106,
      "learning_rate": 5.0826697238317935e-05,
      "loss": 0.7605,
      "step": 104
    },
    {
      "epoch": 0.2874743326488706,
      "grad_norm": 0.5593162178993225,
      "learning_rate": 5e-05,
      "loss": 0.6799,
      "step": 105
    },
    {
      "epoch": 0.29021218343600275,
      "grad_norm": 0.531743049621582,
      "learning_rate": 4.917330276168208e-05,
      "loss": 0.6794,
      "step": 106
    },
    {
      "epoch": 0.2929500342231348,
      "grad_norm": 0.5206313133239746,
      "learning_rate": 4.834683153413459e-05,
      "loss": 0.746,
      "step": 107
    },
    {
      "epoch": 0.29568788501026694,
      "grad_norm": 0.5450119972229004,
      "learning_rate": 4.7520812266338885e-05,
      "loss": 0.7264,
      "step": 108
    },
    {
      "epoch": 0.29842573579739906,
      "grad_norm": 0.5496265292167664,
      "learning_rate": 4.669547078371504e-05,
      "loss": 0.6667,
      "step": 109
    },
    {
      "epoch": 0.30116358658453113,
      "grad_norm": 0.5745857357978821,
      "learning_rate": 4.5871032726383386e-05,
      "loss": 0.6375,
      "step": 110
    },
    {
      "epoch": 0.30390143737166325,
      "grad_norm": 0.5768544673919678,
      "learning_rate": 4.504772348747687e-05,
      "loss": 0.7287,
      "step": 111
    },
    {
      "epoch": 0.3066392881587953,
      "grad_norm": 0.6241164803504944,
      "learning_rate": 4.4225768151520694e-05,
      "loss": 0.8212,
      "step": 112
    },
    {
      "epoch": 0.30937713894592744,
      "grad_norm": 0.6139326095581055,
      "learning_rate": 4.3405391432896555e-05,
      "loss": 0.6601,
      "step": 113
    },
    {
      "epoch": 0.31211498973305957,
      "grad_norm": 0.6339772939682007,
      "learning_rate": 4.2586817614407895e-05,
      "loss": 0.687,
      "step": 114
    },
    {
      "epoch": 0.31485284052019163,
      "grad_norm": 0.6579389572143555,
      "learning_rate": 4.17702704859633e-05,
      "loss": 0.6941,
      "step": 115
    },
    {
      "epoch": 0.31759069130732376,
      "grad_norm": 0.589053213596344,
      "learning_rate": 4.095597328339452e-05,
      "loss": 0.666,
      "step": 116
    },
    {
      "epoch": 0.3203285420944558,
      "grad_norm": 0.7462738156318665,
      "learning_rate": 4.0144148627425993e-05,
      "loss": 0.7054,
      "step": 117
    },
    {
      "epoch": 0.32306639288158795,
      "grad_norm": 0.7249307036399841,
      "learning_rate": 3.933501846281267e-05,
      "loss": 0.638,
      "step": 118
    },
    {
      "epoch": 0.3258042436687201,
      "grad_norm": 0.753004789352417,
      "learning_rate": 3.852880399766243e-05,
      "loss": 0.6969,
      "step": 119
    },
    {
      "epoch": 0.32854209445585214,
      "grad_norm": 0.7332877516746521,
      "learning_rate": 3.772572564296005e-05,
      "loss": 0.7471,
      "step": 120
    },
    {
      "epoch": 0.33127994524298426,
      "grad_norm": 0.7496098279953003,
      "learning_rate": 3.6926002952309016e-05,
      "loss": 0.7528,
      "step": 121
    },
    {
      "epoch": 0.33401779603011633,
      "grad_norm": 0.8590617775917053,
      "learning_rate": 3.612985456190778e-05,
      "loss": 0.7361,
      "step": 122
    },
    {
      "epoch": 0.33675564681724846,
      "grad_norm": 0.7786666750907898,
      "learning_rate": 3.533749813077677e-05,
      "loss": 0.6806,
      "step": 123
    },
    {
      "epoch": 0.3394934976043806,
      "grad_norm": 0.8297228217124939,
      "learning_rate": 3.4549150281252636e-05,
      "loss": 0.8234,
      "step": 124
    },
    {
      "epoch": 0.34223134839151265,
      "grad_norm": 0.865557074546814,
      "learning_rate": 3.3765026539765834e-05,
      "loss": 0.7561,
      "step": 125
    },
    {
      "epoch": 0.34496919917864477,
      "grad_norm": 0.8818473815917969,
      "learning_rate": 3.298534127791785e-05,
      "loss": 0.8114,
      "step": 126
    },
    {
      "epoch": 0.34770704996577684,
      "grad_norm": 0.9206457734107971,
      "learning_rate": 3.221030765387417e-05,
      "loss": 0.6707,
      "step": 127
    },
    {
      "epoch": 0.35044490075290896,
      "grad_norm": 0.924068033695221,
      "learning_rate": 3.144013755408895e-05,
      "loss": 0.6838,
      "step": 128
    },
    {
      "epoch": 0.3531827515400411,
      "grad_norm": 0.9633898735046387,
      "learning_rate": 3.0675041535377405e-05,
      "loss": 0.6657,
      "step": 129
    },
    {
      "epoch": 0.35592060232717315,
      "grad_norm": 0.8816400766372681,
      "learning_rate": 2.991522876735154e-05,
      "loss": 0.6878,
      "step": 130
    },
    {
      "epoch": 0.3586584531143053,
      "grad_norm": 1.0485888719558716,
      "learning_rate": 2.916090697523549e-05,
      "loss": 0.848,
      "step": 131
    },
    {
      "epoch": 0.3613963039014374,
      "grad_norm": 0.9204696416854858,
      "learning_rate": 2.8412282383075363e-05,
      "loss": 0.6988,
      "step": 132
    },
    {
      "epoch": 0.36413415468856947,
      "grad_norm": 0.9640058279037476,
      "learning_rate": 2.766955965735968e-05,
      "loss": 0.8151,
      "step": 133
    },
    {
      "epoch": 0.3668720054757016,
      "grad_norm": 0.9525370597839355,
      "learning_rate": 2.693294185106562e-05,
      "loss": 0.7574,
      "step": 134
    },
    {
      "epoch": 0.36960985626283366,
      "grad_norm": 1.0117409229278564,
      "learning_rate": 2.6202630348146324e-05,
      "loss": 0.8077,
      "step": 135
    },
    {
      "epoch": 0.3723477070499658,
      "grad_norm": 1.0807509422302246,
      "learning_rate": 2.547882480847461e-05,
      "loss": 0.667,
      "step": 136
    },
    {
      "epoch": 0.3750855578370979,
      "grad_norm": 1.0277572870254517,
      "learning_rate": 2.476172311325783e-05,
      "loss": 0.7796,
      "step": 137
    },
    {
      "epoch": 0.37782340862423,
      "grad_norm": 1.1651215553283691,
      "learning_rate": 2.405152131093926e-05,
      "loss": 0.8676,
      "step": 138
    },
    {
      "epoch": 0.3805612594113621,
      "grad_norm": 1.1641194820404053,
      "learning_rate": 2.3348413563600325e-05,
      "loss": 0.72,
      "step": 139
    },
    {
      "epoch": 0.38329911019849416,
      "grad_norm": 1.214687466621399,
      "learning_rate": 2.2652592093878666e-05,
      "loss": 0.7884,
      "step": 140
    },
    {
      "epoch": 0.3860369609856263,
      "grad_norm": 1.071173071861267,
      "learning_rate": 2.196424713241637e-05,
      "loss": 0.8182,
      "step": 141
    },
    {
      "epoch": 0.3887748117727584,
      "grad_norm": 1.3576570749282837,
      "learning_rate": 2.128356686585282e-05,
      "loss": 0.6822,
      "step": 142
    },
    {
      "epoch": 0.3915126625598905,
      "grad_norm": 1.2568634748458862,
      "learning_rate": 2.061073738537635e-05,
      "loss": 0.7833,
      "step": 143
    },
    {
      "epoch": 0.3942505133470226,
      "grad_norm": 1.2279695272445679,
      "learning_rate": 1.9945942635848748e-05,
      "loss": 0.7372,
      "step": 144
    },
    {
      "epoch": 0.39698836413415467,
      "grad_norm": 1.226128101348877,
      "learning_rate": 1.928936436551661e-05,
      "loss": 0.6946,
      "step": 145
    },
    {
      "epoch": 0.3997262149212868,
      "grad_norm": 1.3002983331680298,
      "learning_rate": 1.8641182076323148e-05,
      "loss": 0.6956,
      "step": 146
    },
    {
      "epoch": 0.4024640657084189,
      "grad_norm": 1.4256408214569092,
      "learning_rate": 1.800157297483417e-05,
      "loss": 0.6917,
      "step": 147
    },
    {
      "epoch": 0.405201916495551,
      "grad_norm": 1.3785923719406128,
      "learning_rate": 1.7370711923791567e-05,
      "loss": 0.5773,
      "step": 148
    },
    {
      "epoch": 0.4079397672826831,
      "grad_norm": 1.5628350973129272,
      "learning_rate": 1.6748771394307585e-05,
      "loss": 0.5852,
      "step": 149
    },
    {
      "epoch": 0.4106776180698152,
      "grad_norm": 1.708213210105896,
      "learning_rate": 1.6135921418712956e-05,
      "loss": 0.4781,
      "step": 150
    },
    {
      "epoch": 0.4106776180698152,
      "eval_loss": 0.712312638759613,
      "eval_runtime": 11.1936,
      "eval_samples_per_second": 54.942,
      "eval_steps_per_second": 13.758,
      "step": 150
    },
    {
      "epoch": 0.4134154688569473,
      "grad_norm": 0.3916042745113373,
      "learning_rate": 1.553232954407171e-05,
      "loss": 0.59,
      "step": 151
    },
    {
      "epoch": 0.4161533196440794,
      "grad_norm": 0.47071221470832825,
      "learning_rate": 1.4938160786375572e-05,
      "loss": 0.6413,
      "step": 152
    },
    {
      "epoch": 0.4188911704312115,
      "grad_norm": 0.45059722661972046,
      "learning_rate": 1.435357758543015e-05,
      "loss": 0.5981,
      "step": 153
    },
    {
      "epoch": 0.4216290212183436,
      "grad_norm": 0.5252667665481567,
      "learning_rate": 1.3778739760445552e-05,
      "loss": 0.6837,
      "step": 154
    },
    {
      "epoch": 0.4243668720054757,
      "grad_norm": 0.5077136158943176,
      "learning_rate": 1.3213804466343421e-05,
      "loss": 0.6868,
      "step": 155
    },
    {
      "epoch": 0.4271047227926078,
      "grad_norm": 0.5179348587989807,
      "learning_rate": 1.2658926150792322e-05,
      "loss": 0.648,
      "step": 156
    },
    {
      "epoch": 0.42984257357973993,
      "grad_norm": 0.5505326986312866,
      "learning_rate": 1.2114256511983274e-05,
      "loss": 0.6495,
      "step": 157
    },
    {
      "epoch": 0.432580424366872,
      "grad_norm": 0.6914063096046448,
      "learning_rate": 1.157994445715706e-05,
      "loss": 0.8135,
      "step": 158
    },
    {
      "epoch": 0.4353182751540041,
      "grad_norm": 0.6254498362541199,
      "learning_rate": 1.1056136061894384e-05,
      "loss": 0.6301,
      "step": 159
    },
    {
      "epoch": 0.4380561259411362,
      "grad_norm": 0.6221128702163696,
      "learning_rate": 1.0542974530180327e-05,
      "loss": 0.6345,
      "step": 160
    },
    {
      "epoch": 0.4407939767282683,
      "grad_norm": 0.636313259601593,
      "learning_rate": 1.0040600155253765e-05,
      "loss": 0.7169,
      "step": 161
    },
    {
      "epoch": 0.44353182751540043,
      "grad_norm": 0.6307430863380432,
      "learning_rate": 9.549150281252633e-06,
      "loss": 0.6071,
      "step": 162
    },
    {
      "epoch": 0.4462696783025325,
      "grad_norm": 0.6934825778007507,
      "learning_rate": 9.068759265665384e-06,
      "loss": 0.8119,
      "step": 163
    },
    {
      "epoch": 0.4490075290896646,
      "grad_norm": 0.6461997032165527,
      "learning_rate": 8.599558442598998e-06,
      "loss": 0.6616,
      "step": 164
    },
    {
      "epoch": 0.4517453798767967,
      "grad_norm": 0.7000399231910706,
      "learning_rate": 8.141676086873572e-06,
      "loss": 0.7645,
      "step": 165
    },
    {
      "epoch": 0.4544832306639288,
      "grad_norm": 0.6412184238433838,
      "learning_rate": 7.695237378953223e-06,
      "loss": 0.7128,
      "step": 166
    },
    {
      "epoch": 0.45722108145106094,
      "grad_norm": 0.7489016056060791,
      "learning_rate": 7.260364370723044e-06,
      "loss": 0.8056,
      "step": 167
    },
    {
      "epoch": 0.459958932238193,
      "grad_norm": 0.7062328457832336,
      "learning_rate": 6.837175952121306e-06,
      "loss": 0.77,
      "step": 168
    },
    {
      "epoch": 0.46269678302532513,
      "grad_norm": 0.7059637308120728,
      "learning_rate": 6.425787818636131e-06,
      "loss": 0.6342,
      "step": 169
    },
    {
      "epoch": 0.4654346338124572,
      "grad_norm": 0.7433047294616699,
      "learning_rate": 6.026312439675552e-06,
      "loss": 0.6938,
      "step": 170
    },
    {
      "epoch": 0.4681724845995893,
      "grad_norm": 0.7717205882072449,
      "learning_rate": 5.6388590278194096e-06,
      "loss": 0.7873,
      "step": 171
    },
    {
      "epoch": 0.47091033538672145,
      "grad_norm": 0.7079321146011353,
      "learning_rate": 5.263533508961827e-06,
      "loss": 0.687,
      "step": 172
    },
    {
      "epoch": 0.4736481861738535,
      "grad_norm": 0.7240985631942749,
      "learning_rate": 4.900438493352055e-06,
      "loss": 0.6722,
      "step": 173
    },
    {
      "epoch": 0.47638603696098564,
      "grad_norm": 0.7886562347412109,
      "learning_rate": 4.549673247541875e-06,
      "loss": 0.8016,
      "step": 174
    },
    {
      "epoch": 0.4791238877481177,
      "grad_norm": 0.7509475946426392,
      "learning_rate": 4.2113336672471245e-06,
      "loss": 0.7197,
      "step": 175
    },
    {
      "epoch": 0.48186173853524983,
      "grad_norm": 0.8307033181190491,
      "learning_rate": 3.885512251130763e-06,
      "loss": 0.8664,
      "step": 176
    },
    {
      "epoch": 0.48459958932238195,
      "grad_norm": 0.8040542602539062,
      "learning_rate": 3.5722980755146517e-06,
      "loss": 0.7164,
      "step": 177
    },
    {
      "epoch": 0.487337440109514,
      "grad_norm": 0.8656935095787048,
      "learning_rate": 3.271776770026963e-06,
      "loss": 0.7971,
      "step": 178
    },
    {
      "epoch": 0.49007529089664614,
      "grad_norm": 0.8408097624778748,
      "learning_rate": 2.9840304941919415e-06,
      "loss": 0.8361,
      "step": 179
    },
    {
      "epoch": 0.4928131416837782,
      "grad_norm": 0.8071446418762207,
      "learning_rate": 2.7091379149682685e-06,
      "loss": 0.6949,
      "step": 180
    },
    {
      "epoch": 0.49555099247091033,
      "grad_norm": 0.8963772654533386,
      "learning_rate": 2.4471741852423237e-06,
      "loss": 0.6599,
      "step": 181
    },
    {
      "epoch": 0.49828884325804246,
      "grad_norm": 0.8209460973739624,
      "learning_rate": 2.1982109232821178e-06,
      "loss": 0.6653,
      "step": 182
    },
    {
      "epoch": 0.5010266940451745,
      "grad_norm": 0.9228564500808716,
      "learning_rate": 1.962316193157593e-06,
      "loss": 0.7178,
      "step": 183
    },
    {
      "epoch": 0.5037645448323066,
      "grad_norm": 0.9539773464202881,
      "learning_rate": 1.7395544861325718e-06,
      "loss": 0.7823,
      "step": 184
    },
    {
      "epoch": 0.5065023956194388,
      "grad_norm": 0.8803650736808777,
      "learning_rate": 1.5299867030334814e-06,
      "loss": 0.6388,
      "step": 185
    },
    {
      "epoch": 0.5092402464065708,
      "grad_norm": 1.0057401657104492,
      "learning_rate": 1.333670137599713e-06,
      "loss": 0.846,
      "step": 186
    },
    {
      "epoch": 0.5119780971937029,
      "grad_norm": 1.0012176036834717,
      "learning_rate": 1.1506584608200367e-06,
      "loss": 0.694,
      "step": 187
    },
    {
      "epoch": 0.5147159479808351,
      "grad_norm": 0.9890592098236084,
      "learning_rate": 9.810017062595322e-07,
      "loss": 0.7395,
      "step": 188
    },
    {
      "epoch": 0.5174537987679672,
      "grad_norm": 1.0873342752456665,
      "learning_rate": 8.247462563808817e-07,
      "loss": 0.67,
      "step": 189
    },
    {
      "epoch": 0.5201916495550992,
      "grad_norm": 1.0610255002975464,
      "learning_rate": 6.819348298638839e-07,
      "loss": 0.7157,
      "step": 190
    },
    {
      "epoch": 0.5229295003422314,
      "grad_norm": 1.0484579801559448,
      "learning_rate": 5.526064699265753e-07,
      "loss": 0.7507,
      "step": 191
    },
    {
      "epoch": 0.5256673511293635,
      "grad_norm": 1.0727518796920776,
      "learning_rate": 4.367965336512403e-07,
      "loss": 0.7159,
      "step": 192
    },
    {
      "epoch": 0.5284052019164955,
      "grad_norm": 1.185022234916687,
      "learning_rate": 3.3453668231809286e-07,
      "loss": 0.826,
      "step": 193
    },
    {
      "epoch": 0.5311430527036276,
      "grad_norm": 1.190055012702942,
      "learning_rate": 2.458548727494292e-07,
      "loss": 0.743,
      "step": 194
    },
    {
      "epoch": 0.5338809034907598,
      "grad_norm": 1.146109700202942,
      "learning_rate": 1.7077534966650766e-07,
      "loss": 0.711,
      "step": 195
    },
    {
      "epoch": 0.5366187542778919,
      "grad_norm": 1.3299866914749146,
      "learning_rate": 1.0931863906127327e-07,
      "loss": 0.7303,
      "step": 196
    },
    {
      "epoch": 0.5393566050650239,
      "grad_norm": 1.2582592964172363,
      "learning_rate": 6.150154258476315e-08,
      "loss": 0.6568,
      "step": 197
    },
    {
      "epoch": 0.5420944558521561,
      "grad_norm": 1.3358622789382935,
      "learning_rate": 2.7337132953697554e-08,
      "loss": 0.6375,
      "step": 198
    },
    {
      "epoch": 0.5448323066392882,
      "grad_norm": 1.5216338634490967,
      "learning_rate": 6.834750376549792e-09,
      "loss": 0.6125,
      "step": 199
    },
    {
      "epoch": 0.5475701574264202,
      "grad_norm": 1.889561414718628,
      "learning_rate": 0.0,
      "loss": 0.6032,
      "step": 200
    },
    {
      "epoch": 0.5475701574264202,
      "eval_loss": 0.7094779014587402,
      "eval_runtime": 11.0636,
      "eval_samples_per_second": 55.588,
      "eval_steps_per_second": 13.92,
      "step": 200
    }
  ],
  "logging_steps": 1,
  "max_steps": 200,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 50,
  "stateful_callbacks": {
    "EarlyStoppingCallback": {
      "args": {
        "early_stopping_patience": 5,
        "early_stopping_threshold": 0.0
      },
      "attributes": {
        "early_stopping_patience_counter": 0
      }
    },
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 1.5766104160862208e+16,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}