{
  "best_metric": 0.5603324174880981,
  "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": 0.44517195224761963,
      "learning_rate": 1e-05,
      "loss": 0.3451,
      "step": 1
    },
    {
      "epoch": 0.0027378507871321013,
      "eval_loss": 0.908491313457489,
      "eval_runtime": 47.5437,
      "eval_samples_per_second": 12.935,
      "eval_steps_per_second": 3.239,
      "step": 1
    },
    {
      "epoch": 0.0054757015742642025,
      "grad_norm": 0.6226160526275635,
      "learning_rate": 2e-05,
      "loss": 0.4674,
      "step": 2
    },
    {
      "epoch": 0.008213552361396304,
      "grad_norm": 0.5933786034584045,
      "learning_rate": 3e-05,
      "loss": 0.4453,
      "step": 3
    },
    {
      "epoch": 0.010951403148528405,
      "grad_norm": 0.5683208703994751,
      "learning_rate": 4e-05,
      "loss": 0.4284,
      "step": 4
    },
    {
      "epoch": 0.013689253935660506,
      "grad_norm": 0.5960337519645691,
      "learning_rate": 5e-05,
      "loss": 0.5571,
      "step": 5
    },
    {
      "epoch": 0.01642710472279261,
      "grad_norm": 0.5610281229019165,
      "learning_rate": 6e-05,
      "loss": 0.5627,
      "step": 6
    },
    {
      "epoch": 0.019164955509924708,
      "grad_norm": 0.5370285511016846,
      "learning_rate": 7e-05,
      "loss": 0.5947,
      "step": 7
    },
    {
      "epoch": 0.02190280629705681,
      "grad_norm": 0.5266485214233398,
      "learning_rate": 8e-05,
      "loss": 0.5063,
      "step": 8
    },
    {
      "epoch": 0.024640657084188913,
      "grad_norm": 0.6736491322517395,
      "learning_rate": 9e-05,
      "loss": 0.449,
      "step": 9
    },
    {
      "epoch": 0.02737850787132101,
      "grad_norm": 0.6154465675354004,
      "learning_rate": 0.0001,
      "loss": 0.4578,
      "step": 10
    },
    {
      "epoch": 0.030116358658453114,
      "grad_norm": 0.5138362646102905,
      "learning_rate": 9.999316524962345e-05,
      "loss": 0.5113,
      "step": 11
    },
    {
      "epoch": 0.03285420944558522,
      "grad_norm": 0.5208541750907898,
      "learning_rate": 9.997266286704631e-05,
      "loss": 0.4104,
      "step": 12
    },
    {
      "epoch": 0.03559206023271732,
      "grad_norm": 0.5574676990509033,
      "learning_rate": 9.993849845741524e-05,
      "loss": 0.5945,
      "step": 13
    },
    {
      "epoch": 0.038329911019849415,
      "grad_norm": 0.5410133004188538,
      "learning_rate": 9.989068136093873e-05,
      "loss": 0.4791,
      "step": 14
    },
    {
      "epoch": 0.04106776180698152,
      "grad_norm": 0.5948134660720825,
      "learning_rate": 9.98292246503335e-05,
      "loss": 0.5572,
      "step": 15
    },
    {
      "epoch": 0.04380561259411362,
      "grad_norm": 0.6016925573348999,
      "learning_rate": 9.975414512725057e-05,
      "loss": 0.52,
      "step": 16
    },
    {
      "epoch": 0.04654346338124572,
      "grad_norm": 0.5930290818214417,
      "learning_rate": 9.966546331768191e-05,
      "loss": 0.4846,
      "step": 17
    },
    {
      "epoch": 0.049281314168377825,
      "grad_norm": 0.6097877025604248,
      "learning_rate": 9.956320346634876e-05,
      "loss": 0.5501,
      "step": 18
    },
    {
      "epoch": 0.05201916495550993,
      "grad_norm": 0.629488468170166,
      "learning_rate": 9.944739353007344e-05,
      "loss": 0.6306,
      "step": 19
    },
    {
      "epoch": 0.05475701574264202,
      "grad_norm": 0.5882799029350281,
      "learning_rate": 9.931806517013612e-05,
      "loss": 0.6652,
      "step": 20
    },
    {
      "epoch": 0.057494866529774126,
      "grad_norm": 0.5683525800704956,
      "learning_rate": 9.917525374361912e-05,
      "loss": 0.5877,
      "step": 21
    },
    {
      "epoch": 0.06023271731690623,
      "grad_norm": 0.611910879611969,
      "learning_rate": 9.901899829374047e-05,
      "loss": 0.6859,
      "step": 22
    },
    {
      "epoch": 0.06297056810403832,
      "grad_norm": 0.5431378483772278,
      "learning_rate": 9.884934153917997e-05,
      "loss": 0.6126,
      "step": 23
    },
    {
      "epoch": 0.06570841889117043,
      "grad_norm": 0.593131422996521,
      "learning_rate": 9.86663298624003e-05,
      "loss": 0.5671,
      "step": 24
    },
    {
      "epoch": 0.06844626967830253,
      "grad_norm": 0.5980007648468018,
      "learning_rate": 9.847001329696653e-05,
      "loss": 0.6767,
      "step": 25
    },
    {
      "epoch": 0.07118412046543464,
      "grad_norm": 0.6015020608901978,
      "learning_rate": 9.826044551386744e-05,
      "loss": 0.6186,
      "step": 26
    },
    {
      "epoch": 0.07392197125256673,
      "grad_norm": 0.6686574220657349,
      "learning_rate": 9.803768380684242e-05,
      "loss": 0.5999,
      "step": 27
    },
    {
      "epoch": 0.07665982203969883,
      "grad_norm": 0.6998065710067749,
      "learning_rate": 9.780178907671789e-05,
      "loss": 0.7941,
      "step": 28
    },
    {
      "epoch": 0.07939767282683094,
      "grad_norm": 0.6200966238975525,
      "learning_rate": 9.755282581475769e-05,
      "loss": 0.6351,
      "step": 29
    },
    {
      "epoch": 0.08213552361396304,
      "grad_norm": 0.6407759189605713,
      "learning_rate": 9.729086208503174e-05,
      "loss": 0.6587,
      "step": 30
    },
    {
      "epoch": 0.08487337440109514,
      "grad_norm": 0.5995775461196899,
      "learning_rate": 9.701596950580806e-05,
      "loss": 0.6941,
      "step": 31
    },
    {
      "epoch": 0.08761122518822724,
      "grad_norm": 0.6013270020484924,
      "learning_rate": 9.672822322997305e-05,
      "loss": 0.5917,
      "step": 32
    },
    {
      "epoch": 0.09034907597535935,
      "grad_norm": 0.6291948556900024,
      "learning_rate": 9.642770192448536e-05,
      "loss": 0.7504,
      "step": 33
    },
    {
      "epoch": 0.09308692676249145,
      "grad_norm": 0.5939675569534302,
      "learning_rate": 9.611448774886924e-05,
      "loss": 0.6356,
      "step": 34
    },
    {
      "epoch": 0.09582477754962354,
      "grad_norm": 0.6644618511199951,
      "learning_rate": 9.578866633275288e-05,
      "loss": 0.7144,
      "step": 35
    },
    {
      "epoch": 0.09856262833675565,
      "grad_norm": 0.6365941762924194,
      "learning_rate": 9.545032675245813e-05,
      "loss": 0.6763,
      "step": 36
    },
    {
      "epoch": 0.10130047912388775,
      "grad_norm": 0.6137032508850098,
      "learning_rate": 9.509956150664796e-05,
      "loss": 0.7061,
      "step": 37
    },
    {
      "epoch": 0.10403832991101986,
      "grad_norm": 0.6387527585029602,
      "learning_rate": 9.473646649103818e-05,
      "loss": 0.6996,
      "step": 38
    },
    {
      "epoch": 0.10677618069815195,
      "grad_norm": 0.7062498927116394,
      "learning_rate": 9.43611409721806e-05,
      "loss": 0.6068,
      "step": 39
    },
    {
      "epoch": 0.10951403148528405,
      "grad_norm": 0.7002606987953186,
      "learning_rate": 9.397368756032445e-05,
      "loss": 0.6846,
      "step": 40
    },
    {
      "epoch": 0.11225188227241616,
      "grad_norm": 0.7696377038955688,
      "learning_rate": 9.357421218136386e-05,
      "loss": 0.6498,
      "step": 41
    },
    {
      "epoch": 0.11498973305954825,
      "grad_norm": 0.6596897840499878,
      "learning_rate": 9.316282404787871e-05,
      "loss": 0.7131,
      "step": 42
    },
    {
      "epoch": 0.11772758384668036,
      "grad_norm": 0.7211071252822876,
      "learning_rate": 9.273963562927695e-05,
      "loss": 0.6932,
      "step": 43
    },
    {
      "epoch": 0.12046543463381246,
      "grad_norm": 0.821337878704071,
      "learning_rate": 9.230476262104677e-05,
      "loss": 0.7969,
      "step": 44
    },
    {
      "epoch": 0.12320328542094455,
      "grad_norm": 0.7658767700195312,
      "learning_rate": 9.185832391312644e-05,
      "loss": 0.7245,
      "step": 45
    },
    {
      "epoch": 0.12594113620807665,
      "grad_norm": 0.7776049971580505,
      "learning_rate": 9.140044155740101e-05,
      "loss": 0.6924,
      "step": 46
    },
    {
      "epoch": 0.12867898699520877,
      "grad_norm": 0.7346661686897278,
      "learning_rate": 9.093124073433463e-05,
      "loss": 0.6851,
      "step": 47
    },
    {
      "epoch": 0.13141683778234087,
      "grad_norm": 0.8507068157196045,
      "learning_rate": 9.045084971874738e-05,
      "loss": 0.6627,
      "step": 48
    },
    {
      "epoch": 0.13415468856947296,
      "grad_norm": 0.875177800655365,
      "learning_rate": 8.995939984474624e-05,
      "loss": 0.6334,
      "step": 49
    },
    {
      "epoch": 0.13689253935660506,
      "grad_norm": 0.889796257019043,
      "learning_rate": 8.945702546981969e-05,
      "loss": 0.6334,
      "step": 50
    },
    {
      "epoch": 0.13689253935660506,
      "eval_loss": 0.6425667405128479,
      "eval_runtime": 48.3003,
      "eval_samples_per_second": 12.733,
      "eval_steps_per_second": 3.188,
      "step": 50
    },
    {
      "epoch": 0.13963039014373715,
      "grad_norm": 0.844247043132782,
      "learning_rate": 8.894386393810563e-05,
      "loss": 0.4031,
      "step": 51
    },
    {
      "epoch": 0.14236824093086928,
      "grad_norm": 0.5820806622505188,
      "learning_rate": 8.842005554284296e-05,
      "loss": 0.4638,
      "step": 52
    },
    {
      "epoch": 0.14510609171800137,
      "grad_norm": 0.566764771938324,
      "learning_rate": 8.788574348801675e-05,
      "loss": 0.4813,
      "step": 53
    },
    {
      "epoch": 0.14784394250513347,
      "grad_norm": 0.4588389992713928,
      "learning_rate": 8.73410738492077e-05,
      "loss": 0.3922,
      "step": 54
    },
    {
      "epoch": 0.15058179329226556,
      "grad_norm": 0.3991678059101105,
      "learning_rate": 8.678619553365659e-05,
      "loss": 0.5259,
      "step": 55
    },
    {
      "epoch": 0.15331964407939766,
      "grad_norm": 0.46561309695243835,
      "learning_rate": 8.622126023955446e-05,
      "loss": 0.4653,
      "step": 56
    },
    {
      "epoch": 0.15605749486652978,
      "grad_norm": 0.5909699201583862,
      "learning_rate": 8.564642241456986e-05,
      "loss": 0.4833,
      "step": 57
    },
    {
      "epoch": 0.15879534565366188,
      "grad_norm": 0.5626156330108643,
      "learning_rate": 8.506183921362443e-05,
      "loss": 0.4268,
      "step": 58
    },
    {
      "epoch": 0.16153319644079397,
      "grad_norm": 0.5996052622795105,
      "learning_rate": 8.44676704559283e-05,
      "loss": 0.4868,
      "step": 59
    },
    {
      "epoch": 0.16427104722792607,
      "grad_norm": 0.5262600779533386,
      "learning_rate": 8.386407858128706e-05,
      "loss": 0.4627,
      "step": 60
    },
    {
      "epoch": 0.16700889801505817,
      "grad_norm": 0.6106951236724854,
      "learning_rate": 8.32512286056924e-05,
      "loss": 0.6943,
      "step": 61
    },
    {
      "epoch": 0.1697467488021903,
      "grad_norm": 0.7453521490097046,
      "learning_rate": 8.262928807620843e-05,
      "loss": 0.5761,
      "step": 62
    },
    {
      "epoch": 0.17248459958932238,
      "grad_norm": 0.5354063510894775,
      "learning_rate": 8.199842702516583e-05,
      "loss": 0.5746,
      "step": 63
    },
    {
      "epoch": 0.17522245037645448,
      "grad_norm": 0.46529680490493774,
      "learning_rate": 8.135881792367686e-05,
      "loss": 0.4092,
      "step": 64
    },
    {
      "epoch": 0.17796030116358658,
      "grad_norm": 0.5710752606391907,
      "learning_rate": 8.07106356344834e-05,
      "loss": 0.5175,
      "step": 65
    },
    {
      "epoch": 0.1806981519507187,
      "grad_norm": 0.5328500270843506,
      "learning_rate": 8.005405736415126e-05,
      "loss": 0.6461,
      "step": 66
    },
    {
      "epoch": 0.1834360027378508,
      "grad_norm": 0.571149468421936,
      "learning_rate": 7.938926261462366e-05,
      "loss": 0.5596,
      "step": 67
    },
    {
      "epoch": 0.1861738535249829,
      "grad_norm": 0.5339324474334717,
      "learning_rate": 7.871643313414718e-05,
      "loss": 0.5303,
      "step": 68
    },
    {
      "epoch": 0.188911704312115,
      "grad_norm": 0.6434739232063293,
      "learning_rate": 7.803575286758364e-05,
      "loss": 0.5518,
      "step": 69
    },
    {
      "epoch": 0.19164955509924708,
      "grad_norm": 0.5670827031135559,
      "learning_rate": 7.734740790612136e-05,
      "loss": 0.618,
      "step": 70
    },
    {
      "epoch": 0.1943874058863792,
      "grad_norm": 0.512898862361908,
      "learning_rate": 7.66515864363997e-05,
      "loss": 0.524,
      "step": 71
    },
    {
      "epoch": 0.1971252566735113,
      "grad_norm": 0.6344662308692932,
      "learning_rate": 7.594847868906076e-05,
      "loss": 0.5645,
      "step": 72
    },
    {
      "epoch": 0.1998631074606434,
      "grad_norm": 0.4935149848461151,
      "learning_rate": 7.52382768867422e-05,
      "loss": 0.6053,
      "step": 73
    },
    {
      "epoch": 0.2026009582477755,
      "grad_norm": 0.5701279044151306,
      "learning_rate": 7.452117519152542e-05,
      "loss": 0.6284,
      "step": 74
    },
    {
      "epoch": 0.2053388090349076,
      "grad_norm": 0.5761316418647766,
      "learning_rate": 7.379736965185368e-05,
      "loss": 0.499,
      "step": 75
    },
    {
      "epoch": 0.2080766598220397,
      "grad_norm": 0.5786774754524231,
      "learning_rate": 7.30670581489344e-05,
      "loss": 0.5389,
      "step": 76
    },
    {
      "epoch": 0.2108145106091718,
      "grad_norm": 0.6124125123023987,
      "learning_rate": 7.233044034264034e-05,
      "loss": 0.7289,
      "step": 77
    },
    {
      "epoch": 0.2135523613963039,
      "grad_norm": 0.5064036250114441,
      "learning_rate": 7.158771761692464e-05,
      "loss": 0.599,
      "step": 78
    },
    {
      "epoch": 0.216290212183436,
      "grad_norm": 0.5362352728843689,
      "learning_rate": 7.083909302476453e-05,
      "loss": 0.6196,
      "step": 79
    },
    {
      "epoch": 0.2190280629705681,
      "grad_norm": 0.6147336363792419,
      "learning_rate": 7.008477123264848e-05,
      "loss": 0.6641,
      "step": 80
    },
    {
      "epoch": 0.22176591375770022,
      "grad_norm": 0.597585141658783,
      "learning_rate": 6.932495846462261e-05,
      "loss": 0.6222,
      "step": 81
    },
    {
      "epoch": 0.2245037645448323,
      "grad_norm": 0.6162816286087036,
      "learning_rate": 6.855986244591104e-05,
      "loss": 0.6771,
      "step": 82
    },
    {
      "epoch": 0.2272416153319644,
      "grad_norm": 0.5572537779808044,
      "learning_rate": 6.778969234612584e-05,
      "loss": 0.6536,
      "step": 83
    },
    {
      "epoch": 0.2299794661190965,
      "grad_norm": 0.5686996579170227,
      "learning_rate": 6.701465872208216e-05,
      "loss": 0.6136,
      "step": 84
    },
    {
      "epoch": 0.2327173169062286,
      "grad_norm": 0.5509069561958313,
      "learning_rate": 6.623497346023418e-05,
      "loss": 0.5289,
      "step": 85
    },
    {
      "epoch": 0.23545516769336072,
      "grad_norm": 0.6756793856620789,
      "learning_rate": 6.545084971874738e-05,
      "loss": 0.7809,
      "step": 86
    },
    {
      "epoch": 0.23819301848049282,
      "grad_norm": 0.6623716950416565,
      "learning_rate": 6.466250186922325e-05,
      "loss": 0.7026,
      "step": 87
    },
    {
      "epoch": 0.24093086926762491,
      "grad_norm": 0.6078564524650574,
      "learning_rate": 6.387014543809223e-05,
      "loss": 0.6284,
      "step": 88
    },
    {
      "epoch": 0.243668720054757,
      "grad_norm": 0.5939504504203796,
      "learning_rate": 6.307399704769099e-05,
      "loss": 0.6526,
      "step": 89
    },
    {
      "epoch": 0.2464065708418891,
      "grad_norm": 0.7013550400733948,
      "learning_rate": 6.227427435703997e-05,
      "loss": 0.6582,
      "step": 90
    },
    {
      "epoch": 0.24914442162902123,
      "grad_norm": 0.5962901711463928,
      "learning_rate": 6.147119600233758e-05,
      "loss": 0.6444,
      "step": 91
    },
    {
      "epoch": 0.2518822724161533,
      "grad_norm": 0.7413282990455627,
      "learning_rate": 6.066498153718735e-05,
      "loss": 0.6981,
      "step": 92
    },
    {
      "epoch": 0.2546201232032854,
      "grad_norm": 0.7161607146263123,
      "learning_rate": 5.985585137257401e-05,
      "loss": 0.6812,
      "step": 93
    },
    {
      "epoch": 0.25735797399041754,
      "grad_norm": 0.7952245473861694,
      "learning_rate": 5.90440267166055e-05,
      "loss": 0.7068,
      "step": 94
    },
    {
      "epoch": 0.2600958247775496,
      "grad_norm": 0.6638028025627136,
      "learning_rate": 5.8229729514036705e-05,
      "loss": 0.6078,
      "step": 95
    },
    {
      "epoch": 0.26283367556468173,
      "grad_norm": 0.802947461605072,
      "learning_rate": 5.74131823855921e-05,
      "loss": 0.7225,
      "step": 96
    },
    {
      "epoch": 0.2655715263518138,
      "grad_norm": 0.7005895376205444,
      "learning_rate": 5.6594608567103456e-05,
      "loss": 0.6568,
      "step": 97
    },
    {
      "epoch": 0.2683093771389459,
      "grad_norm": 0.7152554392814636,
      "learning_rate": 5.577423184847932e-05,
      "loss": 0.5274,
      "step": 98
    },
    {
      "epoch": 0.27104722792607805,
      "grad_norm": 0.9021908640861511,
      "learning_rate": 5.495227651252315e-05,
      "loss": 0.6019,
      "step": 99
    },
    {
      "epoch": 0.2737850787132101,
      "grad_norm": 0.9411377310752869,
      "learning_rate": 5.4128967273616625e-05,
      "loss": 0.5534,
      "step": 100
    },
    {
      "epoch": 0.2737850787132101,
      "eval_loss": 0.6070587635040283,
      "eval_runtime": 48.3414,
      "eval_samples_per_second": 12.722,
      "eval_steps_per_second": 3.186,
      "step": 100
    },
    {
      "epoch": 0.27652292950034224,
      "grad_norm": 0.5230233073234558,
      "learning_rate": 5.330452921628497e-05,
      "loss": 0.3855,
      "step": 101
    },
    {
      "epoch": 0.2792607802874743,
      "grad_norm": 0.7609291672706604,
      "learning_rate": 5.247918773366112e-05,
      "loss": 0.3915,
      "step": 102
    },
    {
      "epoch": 0.28199863107460643,
      "grad_norm": 0.5623911023139954,
      "learning_rate": 5.165316846586541e-05,
      "loss": 0.4421,
      "step": 103
    },
    {
      "epoch": 0.28473648186173856,
      "grad_norm": 0.5977270603179932,
      "learning_rate": 5.0826697238317935e-05,
      "loss": 0.4371,
      "step": 104
    },
    {
      "epoch": 0.2874743326488706,
      "grad_norm": 0.45768290758132935,
      "learning_rate": 5e-05,
      "loss": 0.3833,
      "step": 105
    },
    {
      "epoch": 0.29021218343600275,
      "grad_norm": 0.4676385223865509,
      "learning_rate": 4.917330276168208e-05,
      "loss": 0.4422,
      "step": 106
    },
    {
      "epoch": 0.2929500342231348,
      "grad_norm": 0.38329142332077026,
      "learning_rate": 4.834683153413459e-05,
      "loss": 0.5287,
      "step": 107
    },
    {
      "epoch": 0.29568788501026694,
      "grad_norm": 0.45707041025161743,
      "learning_rate": 4.7520812266338885e-05,
      "loss": 0.4282,
      "step": 108
    },
    {
      "epoch": 0.29842573579739906,
      "grad_norm": 0.38882988691329956,
      "learning_rate": 4.669547078371504e-05,
      "loss": 0.4646,
      "step": 109
    },
    {
      "epoch": 0.30116358658453113,
      "grad_norm": 0.5387020707130432,
      "learning_rate": 4.5871032726383386e-05,
      "loss": 0.4946,
      "step": 110
    },
    {
      "epoch": 0.30390143737166325,
      "grad_norm": 0.454576313495636,
      "learning_rate": 4.504772348747687e-05,
      "loss": 0.5042,
      "step": 111
    },
    {
      "epoch": 0.3066392881587953,
      "grad_norm": 0.5192990303039551,
      "learning_rate": 4.4225768151520694e-05,
      "loss": 0.546,
      "step": 112
    },
    {
      "epoch": 0.30937713894592744,
      "grad_norm": 0.5698233246803284,
      "learning_rate": 4.3405391432896555e-05,
      "loss": 0.4545,
      "step": 113
    },
    {
      "epoch": 0.31211498973305957,
      "grad_norm": 0.47137224674224854,
      "learning_rate": 4.2586817614407895e-05,
      "loss": 0.429,
      "step": 114
    },
    {
      "epoch": 0.31485284052019163,
      "grad_norm": 0.5510035753250122,
      "learning_rate": 4.17702704859633e-05,
      "loss": 0.4647,
      "step": 115
    },
    {
      "epoch": 0.31759069130732376,
      "grad_norm": 0.4703759551048279,
      "learning_rate": 4.095597328339452e-05,
      "loss": 0.4513,
      "step": 116
    },
    {
      "epoch": 0.3203285420944558,
      "grad_norm": 0.5935600399971008,
      "learning_rate": 4.0144148627425993e-05,
      "loss": 0.5646,
      "step": 117
    },
    {
      "epoch": 0.32306639288158795,
      "grad_norm": 0.5967937707901001,
      "learning_rate": 3.933501846281267e-05,
      "loss": 0.5536,
      "step": 118
    },
    {
      "epoch": 0.3258042436687201,
      "grad_norm": 0.5264293551445007,
      "learning_rate": 3.852880399766243e-05,
      "loss": 0.547,
      "step": 119
    },
    {
      "epoch": 0.32854209445585214,
      "grad_norm": 0.49485263228416443,
      "learning_rate": 3.772572564296005e-05,
      "loss": 0.6083,
      "step": 120
    },
    {
      "epoch": 0.33127994524298426,
      "grad_norm": 0.5543188452720642,
      "learning_rate": 3.6926002952309016e-05,
      "loss": 0.5968,
      "step": 121
    },
    {
      "epoch": 0.33401779603011633,
      "grad_norm": 0.5830169916152954,
      "learning_rate": 3.612985456190778e-05,
      "loss": 0.5873,
      "step": 122
    },
    {
      "epoch": 0.33675564681724846,
      "grad_norm": 0.6509431004524231,
      "learning_rate": 3.533749813077677e-05,
      "loss": 0.6912,
      "step": 123
    },
    {
      "epoch": 0.3394934976043806,
      "grad_norm": 0.5517375469207764,
      "learning_rate": 3.4549150281252636e-05,
      "loss": 0.5786,
      "step": 124
    },
    {
      "epoch": 0.34223134839151265,
      "grad_norm": 0.5132136344909668,
      "learning_rate": 3.3765026539765834e-05,
      "loss": 0.5833,
      "step": 125
    },
    {
      "epoch": 0.34496919917864477,
      "grad_norm": 0.5352369546890259,
      "learning_rate": 3.298534127791785e-05,
      "loss": 0.6216,
      "step": 126
    },
    {
      "epoch": 0.34770704996577684,
      "grad_norm": 0.540799081325531,
      "learning_rate": 3.221030765387417e-05,
      "loss": 0.7188,
      "step": 127
    },
    {
      "epoch": 0.35044490075290896,
      "grad_norm": 0.5320147275924683,
      "learning_rate": 3.144013755408895e-05,
      "loss": 0.5715,
      "step": 128
    },
    {
      "epoch": 0.3531827515400411,
      "grad_norm": 0.5330955386161804,
      "learning_rate": 3.0675041535377405e-05,
      "loss": 0.5822,
      "step": 129
    },
    {
      "epoch": 0.35592060232717315,
      "grad_norm": 0.505825400352478,
      "learning_rate": 2.991522876735154e-05,
      "loss": 0.6386,
      "step": 130
    },
    {
      "epoch": 0.3586584531143053,
      "grad_norm": 0.5382667779922485,
      "learning_rate": 2.916090697523549e-05,
      "loss": 0.6179,
      "step": 131
    },
    {
      "epoch": 0.3613963039014374,
      "grad_norm": 0.5516997575759888,
      "learning_rate": 2.8412282383075363e-05,
      "loss": 0.712,
      "step": 132
    },
    {
      "epoch": 0.36413415468856947,
      "grad_norm": 0.6067245006561279,
      "learning_rate": 2.766955965735968e-05,
      "loss": 0.6802,
      "step": 133
    },
    {
      "epoch": 0.3668720054757016,
      "grad_norm": 0.5953978896141052,
      "learning_rate": 2.693294185106562e-05,
      "loss": 0.6697,
      "step": 134
    },
    {
      "epoch": 0.36960985626283366,
      "grad_norm": 0.5540339350700378,
      "learning_rate": 2.6202630348146324e-05,
      "loss": 0.6567,
      "step": 135
    },
    {
      "epoch": 0.3723477070499658,
      "grad_norm": 0.5926216244697571,
      "learning_rate": 2.547882480847461e-05,
      "loss": 0.6919,
      "step": 136
    },
    {
      "epoch": 0.3750855578370979,
      "grad_norm": 0.6322088837623596,
      "learning_rate": 2.476172311325783e-05,
      "loss": 0.6634,
      "step": 137
    },
    {
      "epoch": 0.37782340862423,
      "grad_norm": 0.5847892761230469,
      "learning_rate": 2.405152131093926e-05,
      "loss": 0.6313,
      "step": 138
    },
    {
      "epoch": 0.3805612594113621,
      "grad_norm": 0.6394610404968262,
      "learning_rate": 2.3348413563600325e-05,
      "loss": 0.7373,
      "step": 139
    },
    {
      "epoch": 0.38329911019849416,
      "grad_norm": 0.6412941217422485,
      "learning_rate": 2.2652592093878666e-05,
      "loss": 0.6371,
      "step": 140
    },
    {
      "epoch": 0.3860369609856263,
      "grad_norm": 0.695872962474823,
      "learning_rate": 2.196424713241637e-05,
      "loss": 0.6709,
      "step": 141
    },
    {
      "epoch": 0.3887748117727584,
      "grad_norm": 0.6236642599105835,
      "learning_rate": 2.128356686585282e-05,
      "loss": 0.6169,
      "step": 142
    },
    {
      "epoch": 0.3915126625598905,
      "grad_norm": 0.6770881414413452,
      "learning_rate": 2.061073738537635e-05,
      "loss": 0.6676,
      "step": 143
    },
    {
      "epoch": 0.3942505133470226,
      "grad_norm": 0.7197895050048828,
      "learning_rate": 1.9945942635848748e-05,
      "loss": 0.7375,
      "step": 144
    },
    {
      "epoch": 0.39698836413415467,
      "grad_norm": 0.7547468543052673,
      "learning_rate": 1.928936436551661e-05,
      "loss": 0.6311,
      "step": 145
    },
    {
      "epoch": 0.3997262149212868,
      "grad_norm": 0.7545773983001709,
      "learning_rate": 1.8641182076323148e-05,
      "loss": 0.6525,
      "step": 146
    },
    {
      "epoch": 0.4024640657084189,
      "grad_norm": 0.709048867225647,
      "learning_rate": 1.800157297483417e-05,
      "loss": 0.5913,
      "step": 147
    },
    {
      "epoch": 0.405201916495551,
      "grad_norm": 0.7805970907211304,
      "learning_rate": 1.7370711923791567e-05,
      "loss": 0.5176,
      "step": 148
    },
    {
      "epoch": 0.4079397672826831,
      "grad_norm": 0.9611072540283203,
      "learning_rate": 1.6748771394307585e-05,
      "loss": 0.6059,
      "step": 149
    },
    {
      "epoch": 0.4106776180698152,
      "grad_norm": 0.8799304962158203,
      "learning_rate": 1.6135921418712956e-05,
      "loss": 0.4174,
      "step": 150
    },
    {
      "epoch": 0.4106776180698152,
      "eval_loss": 0.5674667954444885,
      "eval_runtime": 48.3346,
      "eval_samples_per_second": 12.724,
      "eval_steps_per_second": 3.186,
      "step": 150
    },
    {
      "epoch": 0.4134154688569473,
      "grad_norm": 0.3186338543891907,
      "learning_rate": 1.553232954407171e-05,
      "loss": 0.3614,
      "step": 151
    },
    {
      "epoch": 0.4161533196440794,
      "grad_norm": 0.3189704716205597,
      "learning_rate": 1.4938160786375572e-05,
      "loss": 0.3626,
      "step": 152
    },
    {
      "epoch": 0.4188911704312115,
      "grad_norm": 0.3453632593154907,
      "learning_rate": 1.435357758543015e-05,
      "loss": 0.385,
      "step": 153
    },
    {
      "epoch": 0.4216290212183436,
      "grad_norm": 0.40697982907295227,
      "learning_rate": 1.3778739760445552e-05,
      "loss": 0.3799,
      "step": 154
    },
    {
      "epoch": 0.4243668720054757,
      "grad_norm": 0.35187625885009766,
      "learning_rate": 1.3213804466343421e-05,
      "loss": 0.4445,
      "step": 155
    },
    {
      "epoch": 0.4271047227926078,
      "grad_norm": 0.36519932746887207,
      "learning_rate": 1.2658926150792322e-05,
      "loss": 0.4098,
      "step": 156
    },
    {
      "epoch": 0.42984257357973993,
      "grad_norm": 0.4484277069568634,
      "learning_rate": 1.2114256511983274e-05,
      "loss": 0.3937,
      "step": 157
    },
    {
      "epoch": 0.432580424366872,
      "grad_norm": 0.48228248953819275,
      "learning_rate": 1.157994445715706e-05,
      "loss": 0.4479,
      "step": 158
    },
    {
      "epoch": 0.4353182751540041,
      "grad_norm": 0.40722009539604187,
      "learning_rate": 1.1056136061894384e-05,
      "loss": 0.4932,
      "step": 159
    },
    {
      "epoch": 0.4380561259411362,
      "grad_norm": 0.3470662534236908,
      "learning_rate": 1.0542974530180327e-05,
      "loss": 0.4341,
      "step": 160
    },
    {
      "epoch": 0.4407939767282683,
      "grad_norm": 0.42807695269584656,
      "learning_rate": 1.0040600155253765e-05,
      "loss": 0.4627,
      "step": 161
    },
    {
      "epoch": 0.44353182751540043,
      "grad_norm": 0.468558132648468,
      "learning_rate": 9.549150281252633e-06,
      "loss": 0.5681,
      "step": 162
    },
    {
      "epoch": 0.4462696783025325,
      "grad_norm": 0.41909855604171753,
      "learning_rate": 9.068759265665384e-06,
      "loss": 0.5541,
      "step": 163
    },
    {
      "epoch": 0.4490075290896646,
      "grad_norm": 0.4584798216819763,
      "learning_rate": 8.599558442598998e-06,
      "loss": 0.4829,
      "step": 164
    },
    {
      "epoch": 0.4517453798767967,
      "grad_norm": 0.46981048583984375,
      "learning_rate": 8.141676086873572e-06,
      "loss": 0.5093,
      "step": 165
    },
    {
      "epoch": 0.4544832306639288,
      "grad_norm": 0.48367220163345337,
      "learning_rate": 7.695237378953223e-06,
      "loss": 0.5918,
      "step": 166
    },
    {
      "epoch": 0.45722108145106094,
      "grad_norm": 0.6180182695388794,
      "learning_rate": 7.260364370723044e-06,
      "loss": 0.7186,
      "step": 167
    },
    {
      "epoch": 0.459958932238193,
      "grad_norm": 0.5367054343223572,
      "learning_rate": 6.837175952121306e-06,
      "loss": 0.5499,
      "step": 168
    },
    {
      "epoch": 0.46269678302532513,
      "grad_norm": 0.4292324185371399,
      "learning_rate": 6.425787818636131e-06,
      "loss": 0.5205,
      "step": 169
    },
    {
      "epoch": 0.4654346338124572,
      "grad_norm": 0.5100758671760559,
      "learning_rate": 6.026312439675552e-06,
      "loss": 0.5521,
      "step": 170
    },
    {
      "epoch": 0.4681724845995893,
      "grad_norm": 0.4200759828090668,
      "learning_rate": 5.6388590278194096e-06,
      "loss": 0.5601,
      "step": 171
    },
    {
      "epoch": 0.47091033538672145,
      "grad_norm": 0.45699870586395264,
      "learning_rate": 5.263533508961827e-06,
      "loss": 0.4619,
      "step": 172
    },
    {
      "epoch": 0.4736481861738535,
      "grad_norm": 0.5097396969795227,
      "learning_rate": 4.900438493352055e-06,
      "loss": 0.5887,
      "step": 173
    },
    {
      "epoch": 0.47638603696098564,
      "grad_norm": 0.5263314843177795,
      "learning_rate": 4.549673247541875e-06,
      "loss": 0.6774,
      "step": 174
    },
    {
      "epoch": 0.4791238877481177,
      "grad_norm": 0.5347668528556824,
      "learning_rate": 4.2113336672471245e-06,
      "loss": 0.6667,
      "step": 175
    },
    {
      "epoch": 0.48186173853524983,
      "grad_norm": 0.483928918838501,
      "learning_rate": 3.885512251130763e-06,
      "loss": 0.5861,
      "step": 176
    },
    {
      "epoch": 0.48459958932238195,
      "grad_norm": 0.5712993144989014,
      "learning_rate": 3.5722980755146517e-06,
      "loss": 0.7098,
      "step": 177
    },
    {
      "epoch": 0.487337440109514,
      "grad_norm": 0.4939136207103729,
      "learning_rate": 3.271776770026963e-06,
      "loss": 0.6206,
      "step": 178
    },
    {
      "epoch": 0.49007529089664614,
      "grad_norm": 0.5515397191047668,
      "learning_rate": 2.9840304941919415e-06,
      "loss": 0.6509,
      "step": 179
    },
    {
      "epoch": 0.4928131416837782,
      "grad_norm": 0.4958609342575073,
      "learning_rate": 2.7091379149682685e-06,
      "loss": 0.6093,
      "step": 180
    },
    {
      "epoch": 0.49555099247091033,
      "grad_norm": 0.6256906390190125,
      "learning_rate": 2.4471741852423237e-06,
      "loss": 0.6875,
      "step": 181
    },
    {
      "epoch": 0.49828884325804246,
      "grad_norm": 0.551245391368866,
      "learning_rate": 2.1982109232821178e-06,
      "loss": 0.5607,
      "step": 182
    },
    {
      "epoch": 0.5010266940451745,
      "grad_norm": 0.5044541954994202,
      "learning_rate": 1.962316193157593e-06,
      "loss": 0.634,
      "step": 183
    },
    {
      "epoch": 0.5037645448323066,
      "grad_norm": 0.5074310302734375,
      "learning_rate": 1.7395544861325718e-06,
      "loss": 0.6159,
      "step": 184
    },
    {
      "epoch": 0.5065023956194388,
      "grad_norm": 0.587372362613678,
      "learning_rate": 1.5299867030334814e-06,
      "loss": 0.7186,
      "step": 185
    },
    {
      "epoch": 0.5092402464065708,
      "grad_norm": 0.6532719731330872,
      "learning_rate": 1.333670137599713e-06,
      "loss": 0.6233,
      "step": 186
    },
    {
      "epoch": 0.5119780971937029,
      "grad_norm": 0.5603979825973511,
      "learning_rate": 1.1506584608200367e-06,
      "loss": 0.5982,
      "step": 187
    },
    {
      "epoch": 0.5147159479808351,
      "grad_norm": 0.689376175403595,
      "learning_rate": 9.810017062595322e-07,
      "loss": 0.6169,
      "step": 188
    },
    {
      "epoch": 0.5174537987679672,
      "grad_norm": 0.6060811281204224,
      "learning_rate": 8.247462563808817e-07,
      "loss": 0.6332,
      "step": 189
    },
    {
      "epoch": 0.5201916495550992,
      "grad_norm": 0.6343385577201843,
      "learning_rate": 6.819348298638839e-07,
      "loss": 0.6499,
      "step": 190
    },
    {
      "epoch": 0.5229295003422314,
      "grad_norm": 0.6669483184814453,
      "learning_rate": 5.526064699265753e-07,
      "loss": 0.7339,
      "step": 191
    },
    {
      "epoch": 0.5256673511293635,
      "grad_norm": 0.6815745830535889,
      "learning_rate": 4.367965336512403e-07,
      "loss": 0.6623,
      "step": 192
    },
    {
      "epoch": 0.5284052019164955,
      "grad_norm": 0.7650976777076721,
      "learning_rate": 3.3453668231809286e-07,
      "loss": 0.7077,
      "step": 193
    },
    {
      "epoch": 0.5311430527036276,
      "grad_norm": 0.712662398815155,
      "learning_rate": 2.458548727494292e-07,
      "loss": 0.6734,
      "step": 194
    },
    {
      "epoch": 0.5338809034907598,
      "grad_norm": 0.7315998673439026,
      "learning_rate": 1.7077534966650766e-07,
      "loss": 0.6757,
      "step": 195
    },
    {
      "epoch": 0.5366187542778919,
      "grad_norm": 0.7836390733718872,
      "learning_rate": 1.0931863906127327e-07,
      "loss": 0.5714,
      "step": 196
    },
    {
      "epoch": 0.5393566050650239,
      "grad_norm": 0.7166030406951904,
      "learning_rate": 6.150154258476315e-08,
      "loss": 0.6424,
      "step": 197
    },
    {
      "epoch": 0.5420944558521561,
      "grad_norm": 0.7888336777687073,
      "learning_rate": 2.7337132953697554e-08,
      "loss": 0.5341,
      "step": 198
    },
    {
      "epoch": 0.5448323066392882,
      "grad_norm": 0.8671044111251831,
      "learning_rate": 6.834750376549792e-09,
      "loss": 0.5818,
      "step": 199
    },
    {
      "epoch": 0.5475701574264202,
      "grad_norm": 1.0252623558044434,
      "learning_rate": 0.0,
      "loss": 0.5732,
      "step": 200
    },
    {
      "epoch": 0.5475701574264202,
      "eval_loss": 0.5603324174880981,
      "eval_runtime": 48.0269,
      "eval_samples_per_second": 12.805,
      "eval_steps_per_second": 3.207,
      "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": 3.069825132747817e+17,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}