{
  "best_metric": 0.7060645222663879,
  "best_model_checkpoint": "miner_id_24/checkpoint-150",
  "epoch": 0.4106776180698152,
  "eval_steps": 50,
  "global_step": 150,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0027378507871321013,
      "grad_norm": 0.9710871577262878,
      "learning_rate": 1e-05,
      "loss": 0.5533,
      "step": 1
    },
    {
      "epoch": 0.0027378507871321013,
      "eval_loss": 0.9184706211090088,
      "eval_runtime": 11.0562,
      "eval_samples_per_second": 55.625,
      "eval_steps_per_second": 13.929,
      "step": 1
    },
    {
      "epoch": 0.0054757015742642025,
      "grad_norm": 0.9385483860969543,
      "learning_rate": 2e-05,
      "loss": 0.5711,
      "step": 2
    },
    {
      "epoch": 0.008213552361396304,
      "grad_norm": 1.0512588024139404,
      "learning_rate": 3e-05,
      "loss": 0.6732,
      "step": 3
    },
    {
      "epoch": 0.010951403148528405,
      "grad_norm": 0.7945834398269653,
      "learning_rate": 4e-05,
      "loss": 0.7595,
      "step": 4
    },
    {
      "epoch": 0.013689253935660506,
      "grad_norm": 0.7034925818443298,
      "learning_rate": 5e-05,
      "loss": 0.6172,
      "step": 5
    },
    {
      "epoch": 0.01642710472279261,
      "grad_norm": 0.7490125894546509,
      "learning_rate": 6e-05,
      "loss": 0.6789,
      "step": 6
    },
    {
      "epoch": 0.019164955509924708,
      "grad_norm": 0.780720591545105,
      "learning_rate": 7e-05,
      "loss": 0.7765,
      "step": 7
    },
    {
      "epoch": 0.02190280629705681,
      "grad_norm": 0.7458310127258301,
      "learning_rate": 8e-05,
      "loss": 0.7024,
      "step": 8
    },
    {
      "epoch": 0.024640657084188913,
      "grad_norm": 0.8663569688796997,
      "learning_rate": 9e-05,
      "loss": 0.801,
      "step": 9
    },
    {
      "epoch": 0.02737850787132101,
      "grad_norm": 0.8324133157730103,
      "learning_rate": 0.0001,
      "loss": 0.6362,
      "step": 10
    },
    {
      "epoch": 0.030116358658453114,
      "grad_norm": 0.884905993938446,
      "learning_rate": 9.999316524962345e-05,
      "loss": 0.8263,
      "step": 11
    },
    {
      "epoch": 0.03285420944558522,
      "grad_norm": 0.8968943357467651,
      "learning_rate": 9.997266286704631e-05,
      "loss": 0.6745,
      "step": 12
    },
    {
      "epoch": 0.03559206023271732,
      "grad_norm": 1.1455942392349243,
      "learning_rate": 9.993849845741524e-05,
      "loss": 0.9046,
      "step": 13
    },
    {
      "epoch": 0.038329911019849415,
      "grad_norm": 1.0147850513458252,
      "learning_rate": 9.989068136093873e-05,
      "loss": 0.5788,
      "step": 14
    },
    {
      "epoch": 0.04106776180698152,
      "grad_norm": 0.9432833790779114,
      "learning_rate": 9.98292246503335e-05,
      "loss": 0.7017,
      "step": 15
    },
    {
      "epoch": 0.04380561259411362,
      "grad_norm": 0.932563304901123,
      "learning_rate": 9.975414512725057e-05,
      "loss": 0.7411,
      "step": 16
    },
    {
      "epoch": 0.04654346338124572,
      "grad_norm": 0.8591864705085754,
      "learning_rate": 9.966546331768191e-05,
      "loss": 0.6733,
      "step": 17
    },
    {
      "epoch": 0.049281314168377825,
      "grad_norm": 0.8480203151702881,
      "learning_rate": 9.956320346634876e-05,
      "loss": 0.8064,
      "step": 18
    },
    {
      "epoch": 0.05201916495550993,
      "grad_norm": 1.026196002960205,
      "learning_rate": 9.944739353007344e-05,
      "loss": 0.7017,
      "step": 19
    },
    {
      "epoch": 0.05475701574264202,
      "grad_norm": 0.8576517105102539,
      "learning_rate": 9.931806517013612e-05,
      "loss": 0.7407,
      "step": 20
    },
    {
      "epoch": 0.057494866529774126,
      "grad_norm": 0.9678177237510681,
      "learning_rate": 9.917525374361912e-05,
      "loss": 0.677,
      "step": 21
    },
    {
      "epoch": 0.06023271731690623,
      "grad_norm": 0.8701350688934326,
      "learning_rate": 9.901899829374047e-05,
      "loss": 0.7409,
      "step": 22
    },
    {
      "epoch": 0.06297056810403832,
      "grad_norm": 0.9118332862854004,
      "learning_rate": 9.884934153917997e-05,
      "loss": 0.6503,
      "step": 23
    },
    {
      "epoch": 0.06570841889117043,
      "grad_norm": 1.0603328943252563,
      "learning_rate": 9.86663298624003e-05,
      "loss": 0.8028,
      "step": 24
    },
    {
      "epoch": 0.06844626967830253,
      "grad_norm": 1.175284504890442,
      "learning_rate": 9.847001329696653e-05,
      "loss": 0.8249,
      "step": 25
    },
    {
      "epoch": 0.07118412046543464,
      "grad_norm": 1.0997846126556396,
      "learning_rate": 9.826044551386744e-05,
      "loss": 0.7329,
      "step": 26
    },
    {
      "epoch": 0.07392197125256673,
      "grad_norm": 1.0848057270050049,
      "learning_rate": 9.803768380684242e-05,
      "loss": 0.8143,
      "step": 27
    },
    {
      "epoch": 0.07665982203969883,
      "grad_norm": 1.005101203918457,
      "learning_rate": 9.780178907671789e-05,
      "loss": 0.7425,
      "step": 28
    },
    {
      "epoch": 0.07939767282683094,
      "grad_norm": 1.0229833126068115,
      "learning_rate": 9.755282581475769e-05,
      "loss": 0.7883,
      "step": 29
    },
    {
      "epoch": 0.08213552361396304,
      "grad_norm": 0.9990108013153076,
      "learning_rate": 9.729086208503174e-05,
      "loss": 0.7621,
      "step": 30
    },
    {
      "epoch": 0.08487337440109514,
      "grad_norm": 0.9670853614807129,
      "learning_rate": 9.701596950580806e-05,
      "loss": 0.8083,
      "step": 31
    },
    {
      "epoch": 0.08761122518822724,
      "grad_norm": 1.0964628458023071,
      "learning_rate": 9.672822322997305e-05,
      "loss": 0.8271,
      "step": 32
    },
    {
      "epoch": 0.09034907597535935,
      "grad_norm": 1.0905699729919434,
      "learning_rate": 9.642770192448536e-05,
      "loss": 0.7535,
      "step": 33
    },
    {
      "epoch": 0.09308692676249145,
      "grad_norm": 1.0368388891220093,
      "learning_rate": 9.611448774886924e-05,
      "loss": 0.827,
      "step": 34
    },
    {
      "epoch": 0.09582477754962354,
      "grad_norm": 1.13470458984375,
      "learning_rate": 9.578866633275288e-05,
      "loss": 0.7213,
      "step": 35
    },
    {
      "epoch": 0.09856262833675565,
      "grad_norm": 1.0915230512619019,
      "learning_rate": 9.545032675245813e-05,
      "loss": 0.8227,
      "step": 36
    },
    {
      "epoch": 0.10130047912388775,
      "grad_norm": 1.163077473640442,
      "learning_rate": 9.509956150664796e-05,
      "loss": 0.7965,
      "step": 37
    },
    {
      "epoch": 0.10403832991101986,
      "grad_norm": 1.1757965087890625,
      "learning_rate": 9.473646649103818e-05,
      "loss": 0.8041,
      "step": 38
    },
    {
      "epoch": 0.10677618069815195,
      "grad_norm": 1.2303431034088135,
      "learning_rate": 9.43611409721806e-05,
      "loss": 0.8658,
      "step": 39
    },
    {
      "epoch": 0.10951403148528405,
      "grad_norm": 1.3274123668670654,
      "learning_rate": 9.397368756032445e-05,
      "loss": 0.7651,
      "step": 40
    },
    {
      "epoch": 0.11225188227241616,
      "grad_norm": 1.3344517946243286,
      "learning_rate": 9.357421218136386e-05,
      "loss": 0.661,
      "step": 41
    },
    {
      "epoch": 0.11498973305954825,
      "grad_norm": 1.290546178817749,
      "learning_rate": 9.316282404787871e-05,
      "loss": 0.8379,
      "step": 42
    },
    {
      "epoch": 0.11772758384668036,
      "grad_norm": 1.2908949851989746,
      "learning_rate": 9.273963562927695e-05,
      "loss": 0.7408,
      "step": 43
    },
    {
      "epoch": 0.12046543463381246,
      "grad_norm": 1.4095467329025269,
      "learning_rate": 9.230476262104677e-05,
      "loss": 0.7609,
      "step": 44
    },
    {
      "epoch": 0.12320328542094455,
      "grad_norm": 1.4463351964950562,
      "learning_rate": 9.185832391312644e-05,
      "loss": 0.7771,
      "step": 45
    },
    {
      "epoch": 0.12594113620807665,
      "grad_norm": 1.5638494491577148,
      "learning_rate": 9.140044155740101e-05,
      "loss": 0.8059,
      "step": 46
    },
    {
      "epoch": 0.12867898699520877,
      "grad_norm": 1.4064388275146484,
      "learning_rate": 9.093124073433463e-05,
      "loss": 0.7445,
      "step": 47
    },
    {
      "epoch": 0.13141683778234087,
      "grad_norm": 1.4971377849578857,
      "learning_rate": 9.045084971874738e-05,
      "loss": 0.7049,
      "step": 48
    },
    {
      "epoch": 0.13415468856947296,
      "grad_norm": 1.7316209077835083,
      "learning_rate": 8.995939984474624e-05,
      "loss": 0.6491,
      "step": 49
    },
    {
      "epoch": 0.13689253935660506,
      "grad_norm": 2.0464813709259033,
      "learning_rate": 8.945702546981969e-05,
      "loss": 0.6879,
      "step": 50
    },
    {
      "epoch": 0.13689253935660506,
      "eval_loss": 0.746486485004425,
      "eval_runtime": 11.0519,
      "eval_samples_per_second": 55.647,
      "eval_steps_per_second": 13.934,
      "step": 50
    },
    {
      "epoch": 0.13963039014373715,
      "grad_norm": 0.7343839406967163,
      "learning_rate": 8.894386393810563e-05,
      "loss": 0.6763,
      "step": 51
    },
    {
      "epoch": 0.14236824093086928,
      "grad_norm": 0.7680174112319946,
      "learning_rate": 8.842005554284296e-05,
      "loss": 0.6844,
      "step": 52
    },
    {
      "epoch": 0.14510609171800137,
      "grad_norm": 0.7536041140556335,
      "learning_rate": 8.788574348801675e-05,
      "loss": 0.7487,
      "step": 53
    },
    {
      "epoch": 0.14784394250513347,
      "grad_norm": 0.6180784106254578,
      "learning_rate": 8.73410738492077e-05,
      "loss": 0.7359,
      "step": 54
    },
    {
      "epoch": 0.15058179329226556,
      "grad_norm": 0.5442507266998291,
      "learning_rate": 8.678619553365659e-05,
      "loss": 0.6516,
      "step": 55
    },
    {
      "epoch": 0.15331964407939766,
      "grad_norm": 0.5638648271560669,
      "learning_rate": 8.622126023955446e-05,
      "loss": 0.7652,
      "step": 56
    },
    {
      "epoch": 0.15605749486652978,
      "grad_norm": 0.5675374865531921,
      "learning_rate": 8.564642241456986e-05,
      "loss": 0.7639,
      "step": 57
    },
    {
      "epoch": 0.15879534565366188,
      "grad_norm": 0.5510876178741455,
      "learning_rate": 8.506183921362443e-05,
      "loss": 0.7272,
      "step": 58
    },
    {
      "epoch": 0.16153319644079397,
      "grad_norm": 0.6208220720291138,
      "learning_rate": 8.44676704559283e-05,
      "loss": 0.647,
      "step": 59
    },
    {
      "epoch": 0.16427104722792607,
      "grad_norm": 0.5863213539123535,
      "learning_rate": 8.386407858128706e-05,
      "loss": 0.7173,
      "step": 60
    },
    {
      "epoch": 0.16700889801505817,
      "grad_norm": 0.6554663777351379,
      "learning_rate": 8.32512286056924e-05,
      "loss": 0.699,
      "step": 61
    },
    {
      "epoch": 0.1697467488021903,
      "grad_norm": 0.6188967823982239,
      "learning_rate": 8.262928807620843e-05,
      "loss": 0.7935,
      "step": 62
    },
    {
      "epoch": 0.17248459958932238,
      "grad_norm": 0.6799103021621704,
      "learning_rate": 8.199842702516583e-05,
      "loss": 0.7849,
      "step": 63
    },
    {
      "epoch": 0.17522245037645448,
      "grad_norm": 0.7120746970176697,
      "learning_rate": 8.135881792367686e-05,
      "loss": 0.6189,
      "step": 64
    },
    {
      "epoch": 0.17796030116358658,
      "grad_norm": 0.6796399354934692,
      "learning_rate": 8.07106356344834e-05,
      "loss": 0.7657,
      "step": 65
    },
    {
      "epoch": 0.1806981519507187,
      "grad_norm": 0.6758213043212891,
      "learning_rate": 8.005405736415126e-05,
      "loss": 0.6917,
      "step": 66
    },
    {
      "epoch": 0.1834360027378508,
      "grad_norm": 0.7220732569694519,
      "learning_rate": 7.938926261462366e-05,
      "loss": 0.6763,
      "step": 67
    },
    {
      "epoch": 0.1861738535249829,
      "grad_norm": 0.7917080521583557,
      "learning_rate": 7.871643313414718e-05,
      "loss": 0.6939,
      "step": 68
    },
    {
      "epoch": 0.188911704312115,
      "grad_norm": 0.8571744561195374,
      "learning_rate": 7.803575286758364e-05,
      "loss": 0.8874,
      "step": 69
    },
    {
      "epoch": 0.19164955509924708,
      "grad_norm": 0.8108315467834473,
      "learning_rate": 7.734740790612136e-05,
      "loss": 0.7505,
      "step": 70
    },
    {
      "epoch": 0.1943874058863792,
      "grad_norm": 0.8167513012886047,
      "learning_rate": 7.66515864363997e-05,
      "loss": 0.7796,
      "step": 71
    },
    {
      "epoch": 0.1971252566735113,
      "grad_norm": 0.9787366390228271,
      "learning_rate": 7.594847868906076e-05,
      "loss": 0.7776,
      "step": 72
    },
    {
      "epoch": 0.1998631074606434,
      "grad_norm": 0.8110655546188354,
      "learning_rate": 7.52382768867422e-05,
      "loss": 0.6408,
      "step": 73
    },
    {
      "epoch": 0.2026009582477755,
      "grad_norm": 0.9293725490570068,
      "learning_rate": 7.452117519152542e-05,
      "loss": 0.7747,
      "step": 74
    },
    {
      "epoch": 0.2053388090349076,
      "grad_norm": 0.8938537836074829,
      "learning_rate": 7.379736965185368e-05,
      "loss": 0.7778,
      "step": 75
    },
    {
      "epoch": 0.2080766598220397,
      "grad_norm": 0.9039812088012695,
      "learning_rate": 7.30670581489344e-05,
      "loss": 0.6699,
      "step": 76
    },
    {
      "epoch": 0.2108145106091718,
      "grad_norm": 0.8710380792617798,
      "learning_rate": 7.233044034264034e-05,
      "loss": 0.6916,
      "step": 77
    },
    {
      "epoch": 0.2135523613963039,
      "grad_norm": 0.9332929849624634,
      "learning_rate": 7.158771761692464e-05,
      "loss": 0.7266,
      "step": 78
    },
    {
      "epoch": 0.216290212183436,
      "grad_norm": 0.8793050050735474,
      "learning_rate": 7.083909302476453e-05,
      "loss": 0.6217,
      "step": 79
    },
    {
      "epoch": 0.2190280629705681,
      "grad_norm": 0.8633202314376831,
      "learning_rate": 7.008477123264848e-05,
      "loss": 0.7759,
      "step": 80
    },
    {
      "epoch": 0.22176591375770022,
      "grad_norm": 0.9199454188346863,
      "learning_rate": 6.932495846462261e-05,
      "loss": 0.7166,
      "step": 81
    },
    {
      "epoch": 0.2245037645448323,
      "grad_norm": 0.9272769689559937,
      "learning_rate": 6.855986244591104e-05,
      "loss": 0.7296,
      "step": 82
    },
    {
      "epoch": 0.2272416153319644,
      "grad_norm": 1.0266982316970825,
      "learning_rate": 6.778969234612584e-05,
      "loss": 0.7349,
      "step": 83
    },
    {
      "epoch": 0.2299794661190965,
      "grad_norm": 0.9878594875335693,
      "learning_rate": 6.701465872208216e-05,
      "loss": 0.7432,
      "step": 84
    },
    {
      "epoch": 0.2327173169062286,
      "grad_norm": 1.0579707622528076,
      "learning_rate": 6.623497346023418e-05,
      "loss": 0.706,
      "step": 85
    },
    {
      "epoch": 0.23545516769336072,
      "grad_norm": 1.1569671630859375,
      "learning_rate": 6.545084971874738e-05,
      "loss": 0.7895,
      "step": 86
    },
    {
      "epoch": 0.23819301848049282,
      "grad_norm": 1.123779058456421,
      "learning_rate": 6.466250186922325e-05,
      "loss": 0.8604,
      "step": 87
    },
    {
      "epoch": 0.24093086926762491,
      "grad_norm": 1.0186105966567993,
      "learning_rate": 6.387014543809223e-05,
      "loss": 0.6544,
      "step": 88
    },
    {
      "epoch": 0.243668720054757,
      "grad_norm": 1.1565487384796143,
      "learning_rate": 6.307399704769099e-05,
      "loss": 0.726,
      "step": 89
    },
    {
      "epoch": 0.2464065708418891,
      "grad_norm": 1.1514602899551392,
      "learning_rate": 6.227427435703997e-05,
      "loss": 0.7513,
      "step": 90
    },
    {
      "epoch": 0.24914442162902123,
      "grad_norm": 1.1755257844924927,
      "learning_rate": 6.147119600233758e-05,
      "loss": 0.7479,
      "step": 91
    },
    {
      "epoch": 0.2518822724161533,
      "grad_norm": 1.1915388107299805,
      "learning_rate": 6.066498153718735e-05,
      "loss": 0.7041,
      "step": 92
    },
    {
      "epoch": 0.2546201232032854,
      "grad_norm": 1.2216668128967285,
      "learning_rate": 5.985585137257401e-05,
      "loss": 0.7764,
      "step": 93
    },
    {
      "epoch": 0.25735797399041754,
      "grad_norm": 1.2057803869247437,
      "learning_rate": 5.90440267166055e-05,
      "loss": 0.6637,
      "step": 94
    },
    {
      "epoch": 0.2600958247775496,
      "grad_norm": 1.2013019323349,
      "learning_rate": 5.8229729514036705e-05,
      "loss": 0.6736,
      "step": 95
    },
    {
      "epoch": 0.26283367556468173,
      "grad_norm": 1.2963463068008423,
      "learning_rate": 5.74131823855921e-05,
      "loss": 0.8023,
      "step": 96
    },
    {
      "epoch": 0.2655715263518138,
      "grad_norm": 1.360404133796692,
      "learning_rate": 5.6594608567103456e-05,
      "loss": 0.6959,
      "step": 97
    },
    {
      "epoch": 0.2683093771389459,
      "grad_norm": 1.569697380065918,
      "learning_rate": 5.577423184847932e-05,
      "loss": 0.7658,
      "step": 98
    },
    {
      "epoch": 0.27104722792607805,
      "grad_norm": 1.9754431247711182,
      "learning_rate": 5.495227651252315e-05,
      "loss": 0.6752,
      "step": 99
    },
    {
      "epoch": 0.2737850787132101,
      "grad_norm": 1.8012800216674805,
      "learning_rate": 5.4128967273616625e-05,
      "loss": 0.5313,
      "step": 100
    },
    {
      "epoch": 0.2737850787132101,
      "eval_loss": 0.7279215455055237,
      "eval_runtime": 11.0475,
      "eval_samples_per_second": 55.669,
      "eval_steps_per_second": 13.94,
      "step": 100
    },
    {
      "epoch": 0.27652292950034224,
      "grad_norm": 0.48348718881607056,
      "learning_rate": 5.330452921628497e-05,
      "loss": 0.607,
      "step": 101
    },
    {
      "epoch": 0.2792607802874743,
      "grad_norm": 0.6778792142868042,
      "learning_rate": 5.247918773366112e-05,
      "loss": 0.594,
      "step": 102
    },
    {
      "epoch": 0.28199863107460643,
      "grad_norm": 0.5933652520179749,
      "learning_rate": 5.165316846586541e-05,
      "loss": 0.6822,
      "step": 103
    },
    {
      "epoch": 0.28473648186173856,
      "grad_norm": 0.602213978767395,
      "learning_rate": 5.0826697238317935e-05,
      "loss": 0.7372,
      "step": 104
    },
    {
      "epoch": 0.2874743326488706,
      "grad_norm": 0.5698598027229309,
      "learning_rate": 5e-05,
      "loss": 0.6893,
      "step": 105
    },
    {
      "epoch": 0.29021218343600275,
      "grad_norm": 0.6202980875968933,
      "learning_rate": 4.917330276168208e-05,
      "loss": 0.7992,
      "step": 106
    },
    {
      "epoch": 0.2929500342231348,
      "grad_norm": 0.6215944886207581,
      "learning_rate": 4.834683153413459e-05,
      "loss": 0.7788,
      "step": 107
    },
    {
      "epoch": 0.29568788501026694,
      "grad_norm": 0.5982862114906311,
      "learning_rate": 4.7520812266338885e-05,
      "loss": 0.6545,
      "step": 108
    },
    {
      "epoch": 0.29842573579739906,
      "grad_norm": 0.5499609112739563,
      "learning_rate": 4.669547078371504e-05,
      "loss": 0.6628,
      "step": 109
    },
    {
      "epoch": 0.30116358658453113,
      "grad_norm": 0.6254652142524719,
      "learning_rate": 4.5871032726383386e-05,
      "loss": 0.6556,
      "step": 110
    },
    {
      "epoch": 0.30390143737166325,
      "grad_norm": 0.6358831524848938,
      "learning_rate": 4.504772348747687e-05,
      "loss": 0.7529,
      "step": 111
    },
    {
      "epoch": 0.3066392881587953,
      "grad_norm": 0.6264432668685913,
      "learning_rate": 4.4225768151520694e-05,
      "loss": 0.5991,
      "step": 112
    },
    {
      "epoch": 0.30937713894592744,
      "grad_norm": 0.6257435083389282,
      "learning_rate": 4.3405391432896555e-05,
      "loss": 0.6131,
      "step": 113
    },
    {
      "epoch": 0.31211498973305957,
      "grad_norm": 0.6443232893943787,
      "learning_rate": 4.2586817614407895e-05,
      "loss": 0.682,
      "step": 114
    },
    {
      "epoch": 0.31485284052019163,
      "grad_norm": 0.628891110420227,
      "learning_rate": 4.17702704859633e-05,
      "loss": 0.6473,
      "step": 115
    },
    {
      "epoch": 0.31759069130732376,
      "grad_norm": 0.8461789488792419,
      "learning_rate": 4.095597328339452e-05,
      "loss": 0.698,
      "step": 116
    },
    {
      "epoch": 0.3203285420944558,
      "grad_norm": 0.706031858921051,
      "learning_rate": 4.0144148627425993e-05,
      "loss": 0.6836,
      "step": 117
    },
    {
      "epoch": 0.32306639288158795,
      "grad_norm": 0.7250199317932129,
      "learning_rate": 3.933501846281267e-05,
      "loss": 0.6621,
      "step": 118
    },
    {
      "epoch": 0.3258042436687201,
      "grad_norm": 0.8346610069274902,
      "learning_rate": 3.852880399766243e-05,
      "loss": 0.8166,
      "step": 119
    },
    {
      "epoch": 0.32854209445585214,
      "grad_norm": 0.7170034646987915,
      "learning_rate": 3.772572564296005e-05,
      "loss": 0.7067,
      "step": 120
    },
    {
      "epoch": 0.33127994524298426,
      "grad_norm": 1.05123770236969,
      "learning_rate": 3.6926002952309016e-05,
      "loss": 0.8281,
      "step": 121
    },
    {
      "epoch": 0.33401779603011633,
      "grad_norm": 0.7747244238853455,
      "learning_rate": 3.612985456190778e-05,
      "loss": 0.6587,
      "step": 122
    },
    {
      "epoch": 0.33675564681724846,
      "grad_norm": 0.7813602089881897,
      "learning_rate": 3.533749813077677e-05,
      "loss": 0.7036,
      "step": 123
    },
    {
      "epoch": 0.3394934976043806,
      "grad_norm": 0.980412483215332,
      "learning_rate": 3.4549150281252636e-05,
      "loss": 0.7797,
      "step": 124
    },
    {
      "epoch": 0.34223134839151265,
      "grad_norm": 0.8119041919708252,
      "learning_rate": 3.3765026539765834e-05,
      "loss": 0.6477,
      "step": 125
    },
    {
      "epoch": 0.34496919917864477,
      "grad_norm": 0.8684152960777283,
      "learning_rate": 3.298534127791785e-05,
      "loss": 0.875,
      "step": 126
    },
    {
      "epoch": 0.34770704996577684,
      "grad_norm": 0.8191859126091003,
      "learning_rate": 3.221030765387417e-05,
      "loss": 0.6749,
      "step": 127
    },
    {
      "epoch": 0.35044490075290896,
      "grad_norm": 0.9072121977806091,
      "learning_rate": 3.144013755408895e-05,
      "loss": 0.8203,
      "step": 128
    },
    {
      "epoch": 0.3531827515400411,
      "grad_norm": 0.9402368068695068,
      "learning_rate": 3.0675041535377405e-05,
      "loss": 0.7332,
      "step": 129
    },
    {
      "epoch": 0.35592060232717315,
      "grad_norm": 0.9398963451385498,
      "learning_rate": 2.991522876735154e-05,
      "loss": 0.6696,
      "step": 130
    },
    {
      "epoch": 0.3586584531143053,
      "grad_norm": 0.9291687607765198,
      "learning_rate": 2.916090697523549e-05,
      "loss": 0.7615,
      "step": 131
    },
    {
      "epoch": 0.3613963039014374,
      "grad_norm": 0.9258692860603333,
      "learning_rate": 2.8412282383075363e-05,
      "loss": 0.762,
      "step": 132
    },
    {
      "epoch": 0.36413415468856947,
      "grad_norm": 1.0227291584014893,
      "learning_rate": 2.766955965735968e-05,
      "loss": 0.7206,
      "step": 133
    },
    {
      "epoch": 0.3668720054757016,
      "grad_norm": 0.9726768732070923,
      "learning_rate": 2.693294185106562e-05,
      "loss": 0.7093,
      "step": 134
    },
    {
      "epoch": 0.36960985626283366,
      "grad_norm": 1.0100514888763428,
      "learning_rate": 2.6202630348146324e-05,
      "loss": 0.7379,
      "step": 135
    },
    {
      "epoch": 0.3723477070499658,
      "grad_norm": 1.0931297540664673,
      "learning_rate": 2.547882480847461e-05,
      "loss": 0.7643,
      "step": 136
    },
    {
      "epoch": 0.3750855578370979,
      "grad_norm": 1.0363917350769043,
      "learning_rate": 2.476172311325783e-05,
      "loss": 0.7482,
      "step": 137
    },
    {
      "epoch": 0.37782340862423,
      "grad_norm": 1.0541198253631592,
      "learning_rate": 2.405152131093926e-05,
      "loss": 0.7396,
      "step": 138
    },
    {
      "epoch": 0.3805612594113621,
      "grad_norm": 1.0495165586471558,
      "learning_rate": 2.3348413563600325e-05,
      "loss": 0.751,
      "step": 139
    },
    {
      "epoch": 0.38329911019849416,
      "grad_norm": 1.0822211503982544,
      "learning_rate": 2.2652592093878666e-05,
      "loss": 0.6872,
      "step": 140
    },
    {
      "epoch": 0.3860369609856263,
      "grad_norm": 1.1589404344558716,
      "learning_rate": 2.196424713241637e-05,
      "loss": 0.7507,
      "step": 141
    },
    {
      "epoch": 0.3887748117727584,
      "grad_norm": 1.1483508348464966,
      "learning_rate": 2.128356686585282e-05,
      "loss": 0.7354,
      "step": 142
    },
    {
      "epoch": 0.3915126625598905,
      "grad_norm": 1.2113616466522217,
      "learning_rate": 2.061073738537635e-05,
      "loss": 0.6965,
      "step": 143
    },
    {
      "epoch": 0.3942505133470226,
      "grad_norm": 1.378213882446289,
      "learning_rate": 1.9945942635848748e-05,
      "loss": 0.6861,
      "step": 144
    },
    {
      "epoch": 0.39698836413415467,
      "grad_norm": 1.2625421285629272,
      "learning_rate": 1.928936436551661e-05,
      "loss": 0.698,
      "step": 145
    },
    {
      "epoch": 0.3997262149212868,
      "grad_norm": 1.355000615119934,
      "learning_rate": 1.8641182076323148e-05,
      "loss": 0.7843,
      "step": 146
    },
    {
      "epoch": 0.4024640657084189,
      "grad_norm": 1.2747864723205566,
      "learning_rate": 1.800157297483417e-05,
      "loss": 0.5931,
      "step": 147
    },
    {
      "epoch": 0.405201916495551,
      "grad_norm": 1.3510576486587524,
      "learning_rate": 1.7370711923791567e-05,
      "loss": 0.5957,
      "step": 148
    },
    {
      "epoch": 0.4079397672826831,
      "grad_norm": 1.5325325727462769,
      "learning_rate": 1.6748771394307585e-05,
      "loss": 0.6309,
      "step": 149
    },
    {
      "epoch": 0.4106776180698152,
      "grad_norm": 2.0681326389312744,
      "learning_rate": 1.6135921418712956e-05,
      "loss": 0.5206,
      "step": 150
    },
    {
      "epoch": 0.4106776180698152,
      "eval_loss": 0.7060645222663879,
      "eval_runtime": 11.0462,
      "eval_samples_per_second": 55.675,
      "eval_steps_per_second": 13.941,
      "step": 150
    }
  ],
  "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": false
      },
      "attributes": {}
    }
  },
  "total_flos": 1.1843899326726144e+16,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}