{
  "best_metric": 0.5939285159111023,
  "best_model_checkpoint": "miner_id_24/checkpoint-200",
  "epoch": 0.7835455435847208,
  "eval_steps": 50,
  "global_step": 200,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0039177277179236044,
      "grad_norm": 0.25638842582702637,
      "learning_rate": 1e-05,
      "loss": 0.9092,
      "step": 1
    },
    {
      "epoch": 0.0039177277179236044,
      "eval_loss": 1.1594817638397217,
      "eval_runtime": 5.9497,
      "eval_samples_per_second": 72.272,
      "eval_steps_per_second": 18.152,
      "step": 1
    },
    {
      "epoch": 0.007835455435847209,
      "grad_norm": 0.2762967050075531,
      "learning_rate": 2e-05,
      "loss": 0.9372,
      "step": 2
    },
    {
      "epoch": 0.011753183153770812,
      "grad_norm": 0.2591345012187958,
      "learning_rate": 3e-05,
      "loss": 0.9208,
      "step": 3
    },
    {
      "epoch": 0.015670910871694418,
      "grad_norm": 0.26761990785598755,
      "learning_rate": 4e-05,
      "loss": 0.9322,
      "step": 4
    },
    {
      "epoch": 0.019588638589618023,
      "grad_norm": 0.27551403641700745,
      "learning_rate": 5e-05,
      "loss": 0.9438,
      "step": 5
    },
    {
      "epoch": 0.023506366307541625,
      "grad_norm": 0.27751076221466064,
      "learning_rate": 6e-05,
      "loss": 1.0078,
      "step": 6
    },
    {
      "epoch": 0.02742409402546523,
      "grad_norm": 0.2724345326423645,
      "learning_rate": 7e-05,
      "loss": 0.9905,
      "step": 7
    },
    {
      "epoch": 0.031341821743388835,
      "grad_norm": 0.26035308837890625,
      "learning_rate": 8e-05,
      "loss": 0.9304,
      "step": 8
    },
    {
      "epoch": 0.03525954946131244,
      "grad_norm": 0.24459025263786316,
      "learning_rate": 9e-05,
      "loss": 0.9656,
      "step": 9
    },
    {
      "epoch": 0.039177277179236046,
      "grad_norm": 0.22326268255710602,
      "learning_rate": 0.0001,
      "loss": 0.8961,
      "step": 10
    },
    {
      "epoch": 0.043095004897159644,
      "grad_norm": 0.22168701887130737,
      "learning_rate": 9.999316524962345e-05,
      "loss": 0.918,
      "step": 11
    },
    {
      "epoch": 0.04701273261508325,
      "grad_norm": 0.2253589779138565,
      "learning_rate": 9.997266286704631e-05,
      "loss": 0.9451,
      "step": 12
    },
    {
      "epoch": 0.050930460333006855,
      "grad_norm": 0.20621508359909058,
      "learning_rate": 9.993849845741524e-05,
      "loss": 0.9156,
      "step": 13
    },
    {
      "epoch": 0.05484818805093046,
      "grad_norm": 0.19011004269123077,
      "learning_rate": 9.989068136093873e-05,
      "loss": 0.8598,
      "step": 14
    },
    {
      "epoch": 0.058765915768854066,
      "grad_norm": 0.19981749355793,
      "learning_rate": 9.98292246503335e-05,
      "loss": 0.8515,
      "step": 15
    },
    {
      "epoch": 0.06268364348677767,
      "grad_norm": 0.20265749096870422,
      "learning_rate": 9.975414512725057e-05,
      "loss": 0.8689,
      "step": 16
    },
    {
      "epoch": 0.06660137120470128,
      "grad_norm": 0.2108696550130844,
      "learning_rate": 9.966546331768191e-05,
      "loss": 0.8603,
      "step": 17
    },
    {
      "epoch": 0.07051909892262488,
      "grad_norm": 0.1922752410173416,
      "learning_rate": 9.956320346634876e-05,
      "loss": 0.823,
      "step": 18
    },
    {
      "epoch": 0.07443682664054849,
      "grad_norm": 0.2397651970386505,
      "learning_rate": 9.944739353007344e-05,
      "loss": 0.8936,
      "step": 19
    },
    {
      "epoch": 0.07835455435847209,
      "grad_norm": 0.22933229804039001,
      "learning_rate": 9.931806517013612e-05,
      "loss": 0.8413,
      "step": 20
    },
    {
      "epoch": 0.08227228207639568,
      "grad_norm": 0.2013111412525177,
      "learning_rate": 9.917525374361912e-05,
      "loss": 0.8408,
      "step": 21
    },
    {
      "epoch": 0.08619000979431929,
      "grad_norm": 0.1828652322292328,
      "learning_rate": 9.901899829374047e-05,
      "loss": 0.837,
      "step": 22
    },
    {
      "epoch": 0.0901077375122429,
      "grad_norm": 0.18464498221874237,
      "learning_rate": 9.884934153917997e-05,
      "loss": 0.7377,
      "step": 23
    },
    {
      "epoch": 0.0940254652301665,
      "grad_norm": 0.17250579595565796,
      "learning_rate": 9.86663298624003e-05,
      "loss": 0.7909,
      "step": 24
    },
    {
      "epoch": 0.0979431929480901,
      "grad_norm": 0.18242302536964417,
      "learning_rate": 9.847001329696653e-05,
      "loss": 0.7479,
      "step": 25
    },
    {
      "epoch": 0.10186092066601371,
      "grad_norm": 0.169388085603714,
      "learning_rate": 9.826044551386744e-05,
      "loss": 0.8028,
      "step": 26
    },
    {
      "epoch": 0.10577864838393732,
      "grad_norm": 0.16935759782791138,
      "learning_rate": 9.803768380684242e-05,
      "loss": 0.7492,
      "step": 27
    },
    {
      "epoch": 0.10969637610186092,
      "grad_norm": 0.16058318316936493,
      "learning_rate": 9.780178907671789e-05,
      "loss": 0.7879,
      "step": 28
    },
    {
      "epoch": 0.11361410381978453,
      "grad_norm": 0.15479320287704468,
      "learning_rate": 9.755282581475769e-05,
      "loss": 0.7484,
      "step": 29
    },
    {
      "epoch": 0.11753183153770813,
      "grad_norm": 0.17817170917987823,
      "learning_rate": 9.729086208503174e-05,
      "loss": 0.7546,
      "step": 30
    },
    {
      "epoch": 0.12144955925563174,
      "grad_norm": 0.16804228723049164,
      "learning_rate": 9.701596950580806e-05,
      "loss": 0.7109,
      "step": 31
    },
    {
      "epoch": 0.12536728697355534,
      "grad_norm": 0.17566139996051788,
      "learning_rate": 9.672822322997305e-05,
      "loss": 0.7833,
      "step": 32
    },
    {
      "epoch": 0.12928501469147893,
      "grad_norm": 0.19292809069156647,
      "learning_rate": 9.642770192448536e-05,
      "loss": 0.6886,
      "step": 33
    },
    {
      "epoch": 0.13320274240940255,
      "grad_norm": 0.16712266206741333,
      "learning_rate": 9.611448774886924e-05,
      "loss": 0.6839,
      "step": 34
    },
    {
      "epoch": 0.13712047012732614,
      "grad_norm": 0.1727849543094635,
      "learning_rate": 9.578866633275288e-05,
      "loss": 0.7202,
      "step": 35
    },
    {
      "epoch": 0.14103819784524976,
      "grad_norm": 0.18051785230636597,
      "learning_rate": 9.545032675245813e-05,
      "loss": 0.7788,
      "step": 36
    },
    {
      "epoch": 0.14495592556317335,
      "grad_norm": 0.17008085548877716,
      "learning_rate": 9.509956150664796e-05,
      "loss": 0.6767,
      "step": 37
    },
    {
      "epoch": 0.14887365328109697,
      "grad_norm": 0.16623499989509583,
      "learning_rate": 9.473646649103818e-05,
      "loss": 0.6987,
      "step": 38
    },
    {
      "epoch": 0.15279138099902057,
      "grad_norm": 0.19744740426540375,
      "learning_rate": 9.43611409721806e-05,
      "loss": 0.7546,
      "step": 39
    },
    {
      "epoch": 0.15670910871694418,
      "grad_norm": 0.1808963268995285,
      "learning_rate": 9.397368756032445e-05,
      "loss": 0.7098,
      "step": 40
    },
    {
      "epoch": 0.16062683643486778,
      "grad_norm": 0.18556351959705353,
      "learning_rate": 9.357421218136386e-05,
      "loss": 0.6717,
      "step": 41
    },
    {
      "epoch": 0.16454456415279137,
      "grad_norm": 0.19340215623378754,
      "learning_rate": 9.316282404787871e-05,
      "loss": 0.7051,
      "step": 42
    },
    {
      "epoch": 0.168462291870715,
      "grad_norm": 0.19674746692180634,
      "learning_rate": 9.273963562927695e-05,
      "loss": 0.6858,
      "step": 43
    },
    {
      "epoch": 0.17238001958863858,
      "grad_norm": 0.17004497349262238,
      "learning_rate": 9.230476262104677e-05,
      "loss": 0.6448,
      "step": 44
    },
    {
      "epoch": 0.1762977473065622,
      "grad_norm": 0.18559357523918152,
      "learning_rate": 9.185832391312644e-05,
      "loss": 0.6516,
      "step": 45
    },
    {
      "epoch": 0.1802154750244858,
      "grad_norm": 0.18312279880046844,
      "learning_rate": 9.140044155740101e-05,
      "loss": 0.7003,
      "step": 46
    },
    {
      "epoch": 0.1841332027424094,
      "grad_norm": 0.21078233420848846,
      "learning_rate": 9.093124073433463e-05,
      "loss": 0.7055,
      "step": 47
    },
    {
      "epoch": 0.188050930460333,
      "grad_norm": 0.21468901634216309,
      "learning_rate": 9.045084971874738e-05,
      "loss": 0.671,
      "step": 48
    },
    {
      "epoch": 0.19196865817825662,
      "grad_norm": 0.20386405289173126,
      "learning_rate": 8.995939984474624e-05,
      "loss": 0.6719,
      "step": 49
    },
    {
      "epoch": 0.1958863858961802,
      "grad_norm": 0.25821682810783386,
      "learning_rate": 8.945702546981969e-05,
      "loss": 0.7408,
      "step": 50
    },
    {
      "epoch": 0.1958863858961802,
      "eval_loss": 0.6790264844894409,
      "eval_runtime": 5.968,
      "eval_samples_per_second": 72.051,
      "eval_steps_per_second": 18.096,
      "step": 50
    },
    {
      "epoch": 0.19980411361410383,
      "grad_norm": 0.4285676181316376,
      "learning_rate": 8.894386393810563e-05,
      "loss": 0.7335,
      "step": 51
    },
    {
      "epoch": 0.20372184133202742,
      "grad_norm": 0.34651002287864685,
      "learning_rate": 8.842005554284296e-05,
      "loss": 0.7062,
      "step": 52
    },
    {
      "epoch": 0.20763956904995104,
      "grad_norm": 0.2882603108882904,
      "learning_rate": 8.788574348801675e-05,
      "loss": 0.663,
      "step": 53
    },
    {
      "epoch": 0.21155729676787463,
      "grad_norm": 0.20160110294818878,
      "learning_rate": 8.73410738492077e-05,
      "loss": 0.6206,
      "step": 54
    },
    {
      "epoch": 0.21547502448579825,
      "grad_norm": 0.17625008523464203,
      "learning_rate": 8.678619553365659e-05,
      "loss": 0.6397,
      "step": 55
    },
    {
      "epoch": 0.21939275220372184,
      "grad_norm": 0.17817693948745728,
      "learning_rate": 8.622126023955446e-05,
      "loss": 0.6409,
      "step": 56
    },
    {
      "epoch": 0.22331047992164543,
      "grad_norm": 0.20271912217140198,
      "learning_rate": 8.564642241456986e-05,
      "loss": 0.6703,
      "step": 57
    },
    {
      "epoch": 0.22722820763956905,
      "grad_norm": 0.19772851467132568,
      "learning_rate": 8.506183921362443e-05,
      "loss": 0.6608,
      "step": 58
    },
    {
      "epoch": 0.23114593535749264,
      "grad_norm": 0.1766524761915207,
      "learning_rate": 8.44676704559283e-05,
      "loss": 0.6311,
      "step": 59
    },
    {
      "epoch": 0.23506366307541626,
      "grad_norm": 0.1898297369480133,
      "learning_rate": 8.386407858128706e-05,
      "loss": 0.6842,
      "step": 60
    },
    {
      "epoch": 0.23898139079333985,
      "grad_norm": 0.17297406494617462,
      "learning_rate": 8.32512286056924e-05,
      "loss": 0.6712,
      "step": 61
    },
    {
      "epoch": 0.24289911851126347,
      "grad_norm": 0.15616728365421295,
      "learning_rate": 8.262928807620843e-05,
      "loss": 0.6439,
      "step": 62
    },
    {
      "epoch": 0.24681684622918706,
      "grad_norm": 0.16170133650302887,
      "learning_rate": 8.199842702516583e-05,
      "loss": 0.6547,
      "step": 63
    },
    {
      "epoch": 0.2507345739471107,
      "grad_norm": 0.14276544749736786,
      "learning_rate": 8.135881792367686e-05,
      "loss": 0.6188,
      "step": 64
    },
    {
      "epoch": 0.2546523016650343,
      "grad_norm": 0.1604994833469391,
      "learning_rate": 8.07106356344834e-05,
      "loss": 0.6512,
      "step": 65
    },
    {
      "epoch": 0.25857002938295787,
      "grad_norm": 0.15952415764331818,
      "learning_rate": 8.005405736415126e-05,
      "loss": 0.6158,
      "step": 66
    },
    {
      "epoch": 0.2624877571008815,
      "grad_norm": 0.16927486658096313,
      "learning_rate": 7.938926261462366e-05,
      "loss": 0.6314,
      "step": 67
    },
    {
      "epoch": 0.2664054848188051,
      "grad_norm": 0.18026085197925568,
      "learning_rate": 7.871643313414718e-05,
      "loss": 0.6372,
      "step": 68
    },
    {
      "epoch": 0.2703232125367287,
      "grad_norm": 0.17898353934288025,
      "learning_rate": 7.803575286758364e-05,
      "loss": 0.6315,
      "step": 69
    },
    {
      "epoch": 0.2742409402546523,
      "grad_norm": 0.13364596664905548,
      "learning_rate": 7.734740790612136e-05,
      "loss": 0.6392,
      "step": 70
    },
    {
      "epoch": 0.2781586679725759,
      "grad_norm": 0.13739272952079773,
      "learning_rate": 7.66515864363997e-05,
      "loss": 0.6264,
      "step": 71
    },
    {
      "epoch": 0.2820763956904995,
      "grad_norm": 0.1327698975801468,
      "learning_rate": 7.594847868906076e-05,
      "loss": 0.5729,
      "step": 72
    },
    {
      "epoch": 0.2859941234084231,
      "grad_norm": 0.13891570270061493,
      "learning_rate": 7.52382768867422e-05,
      "loss": 0.6401,
      "step": 73
    },
    {
      "epoch": 0.2899118511263467,
      "grad_norm": 0.14682020246982574,
      "learning_rate": 7.452117519152542e-05,
      "loss": 0.6131,
      "step": 74
    },
    {
      "epoch": 0.2938295788442703,
      "grad_norm": 0.1400882601737976,
      "learning_rate": 7.379736965185368e-05,
      "loss": 0.647,
      "step": 75
    },
    {
      "epoch": 0.29774730656219395,
      "grad_norm": 0.18822936713695526,
      "learning_rate": 7.30670581489344e-05,
      "loss": 0.6571,
      "step": 76
    },
    {
      "epoch": 0.30166503428011754,
      "grad_norm": 0.17665962874889374,
      "learning_rate": 7.233044034264034e-05,
      "loss": 0.6731,
      "step": 77
    },
    {
      "epoch": 0.30558276199804113,
      "grad_norm": 0.1692730188369751,
      "learning_rate": 7.158771761692464e-05,
      "loss": 0.6577,
      "step": 78
    },
    {
      "epoch": 0.3095004897159647,
      "grad_norm": 0.16148290038108826,
      "learning_rate": 7.083909302476453e-05,
      "loss": 0.6222,
      "step": 79
    },
    {
      "epoch": 0.31341821743388837,
      "grad_norm": 0.18257564306259155,
      "learning_rate": 7.008477123264848e-05,
      "loss": 0.636,
      "step": 80
    },
    {
      "epoch": 0.31733594515181196,
      "grad_norm": 0.14182758331298828,
      "learning_rate": 6.932495846462261e-05,
      "loss": 0.5575,
      "step": 81
    },
    {
      "epoch": 0.32125367286973555,
      "grad_norm": 0.16455811262130737,
      "learning_rate": 6.855986244591104e-05,
      "loss": 0.592,
      "step": 82
    },
    {
      "epoch": 0.32517140058765914,
      "grad_norm": 0.15356627106666565,
      "learning_rate": 6.778969234612584e-05,
      "loss": 0.6266,
      "step": 83
    },
    {
      "epoch": 0.32908912830558273,
      "grad_norm": 0.16224627196788788,
      "learning_rate": 6.701465872208216e-05,
      "loss": 0.5954,
      "step": 84
    },
    {
      "epoch": 0.3330068560235064,
      "grad_norm": 0.17523738741874695,
      "learning_rate": 6.623497346023418e-05,
      "loss": 0.6451,
      "step": 85
    },
    {
      "epoch": 0.33692458374143,
      "grad_norm": 0.1809830516576767,
      "learning_rate": 6.545084971874738e-05,
      "loss": 0.5885,
      "step": 86
    },
    {
      "epoch": 0.34084231145935356,
      "grad_norm": 0.1843116581439972,
      "learning_rate": 6.466250186922325e-05,
      "loss": 0.6183,
      "step": 87
    },
    {
      "epoch": 0.34476003917727716,
      "grad_norm": 0.1714847981929779,
      "learning_rate": 6.387014543809223e-05,
      "loss": 0.6359,
      "step": 88
    },
    {
      "epoch": 0.3486777668952008,
      "grad_norm": 0.16126644611358643,
      "learning_rate": 6.307399704769099e-05,
      "loss": 0.6361,
      "step": 89
    },
    {
      "epoch": 0.3525954946131244,
      "grad_norm": 0.18201346695423126,
      "learning_rate": 6.227427435703997e-05,
      "loss": 0.5968,
      "step": 90
    },
    {
      "epoch": 0.356513222331048,
      "grad_norm": 0.17374669015407562,
      "learning_rate": 6.147119600233758e-05,
      "loss": 0.6377,
      "step": 91
    },
    {
      "epoch": 0.3604309500489716,
      "grad_norm": 0.1851348578929901,
      "learning_rate": 6.066498153718735e-05,
      "loss": 0.5926,
      "step": 92
    },
    {
      "epoch": 0.3643486777668952,
      "grad_norm": 0.1739545315504074,
      "learning_rate": 5.985585137257401e-05,
      "loss": 0.6541,
      "step": 93
    },
    {
      "epoch": 0.3682664054848188,
      "grad_norm": 0.17895503342151642,
      "learning_rate": 5.90440267166055e-05,
      "loss": 0.5769,
      "step": 94
    },
    {
      "epoch": 0.3721841332027424,
      "grad_norm": 0.21226130425930023,
      "learning_rate": 5.8229729514036705e-05,
      "loss": 0.5936,
      "step": 95
    },
    {
      "epoch": 0.376101860920666,
      "grad_norm": 0.2255641371011734,
      "learning_rate": 5.74131823855921e-05,
      "loss": 0.632,
      "step": 96
    },
    {
      "epoch": 0.38001958863858964,
      "grad_norm": 0.20612813532352448,
      "learning_rate": 5.6594608567103456e-05,
      "loss": 0.6406,
      "step": 97
    },
    {
      "epoch": 0.38393731635651324,
      "grad_norm": 0.2061457484960556,
      "learning_rate": 5.577423184847932e-05,
      "loss": 0.6167,
      "step": 98
    },
    {
      "epoch": 0.3878550440744368,
      "grad_norm": 0.2192172110080719,
      "learning_rate": 5.495227651252315e-05,
      "loss": 0.5915,
      "step": 99
    },
    {
      "epoch": 0.3917727717923604,
      "grad_norm": 0.28485581278800964,
      "learning_rate": 5.4128967273616625e-05,
      "loss": 0.6596,
      "step": 100
    },
    {
      "epoch": 0.3917727717923604,
      "eval_loss": 0.6234792470932007,
      "eval_runtime": 5.9293,
      "eval_samples_per_second": 72.521,
      "eval_steps_per_second": 18.215,
      "step": 100
    },
    {
      "epoch": 0.395690499510284,
      "grad_norm": 0.37318548560142517,
      "learning_rate": 5.330452921628497e-05,
      "loss": 0.6704,
      "step": 101
    },
    {
      "epoch": 0.39960822722820766,
      "grad_norm": 0.32614532113075256,
      "learning_rate": 5.247918773366112e-05,
      "loss": 0.6843,
      "step": 102
    },
    {
      "epoch": 0.40352595494613125,
      "grad_norm": 0.29386618733406067,
      "learning_rate": 5.165316846586541e-05,
      "loss": 0.6736,
      "step": 103
    },
    {
      "epoch": 0.40744368266405484,
      "grad_norm": 0.27737972140312195,
      "learning_rate": 5.0826697238317935e-05,
      "loss": 0.6067,
      "step": 104
    },
    {
      "epoch": 0.41136141038197843,
      "grad_norm": 0.19978028535842896,
      "learning_rate": 5e-05,
      "loss": 0.6423,
      "step": 105
    },
    {
      "epoch": 0.4152791380999021,
      "grad_norm": 0.16679829359054565,
      "learning_rate": 4.917330276168208e-05,
      "loss": 0.6333,
      "step": 106
    },
    {
      "epoch": 0.41919686581782567,
      "grad_norm": 0.13995300233364105,
      "learning_rate": 4.834683153413459e-05,
      "loss": 0.6127,
      "step": 107
    },
    {
      "epoch": 0.42311459353574926,
      "grad_norm": 0.1457802653312683,
      "learning_rate": 4.7520812266338885e-05,
      "loss": 0.6083,
      "step": 108
    },
    {
      "epoch": 0.42703232125367285,
      "grad_norm": 0.1547180861234665,
      "learning_rate": 4.669547078371504e-05,
      "loss": 0.5879,
      "step": 109
    },
    {
      "epoch": 0.4309500489715965,
      "grad_norm": 0.19000352919101715,
      "learning_rate": 4.5871032726383386e-05,
      "loss": 0.6526,
      "step": 110
    },
    {
      "epoch": 0.4348677766895201,
      "grad_norm": 0.17386887967586517,
      "learning_rate": 4.504772348747687e-05,
      "loss": 0.6036,
      "step": 111
    },
    {
      "epoch": 0.4387855044074437,
      "grad_norm": 0.19534529745578766,
      "learning_rate": 4.4225768151520694e-05,
      "loss": 0.572,
      "step": 112
    },
    {
      "epoch": 0.4427032321253673,
      "grad_norm": 0.1662474125623703,
      "learning_rate": 4.3405391432896555e-05,
      "loss": 0.577,
      "step": 113
    },
    {
      "epoch": 0.44662095984329087,
      "grad_norm": 0.1831257939338684,
      "learning_rate": 4.2586817614407895e-05,
      "loss": 0.5981,
      "step": 114
    },
    {
      "epoch": 0.4505386875612145,
      "grad_norm": 0.16978959739208221,
      "learning_rate": 4.17702704859633e-05,
      "loss": 0.587,
      "step": 115
    },
    {
      "epoch": 0.4544564152791381,
      "grad_norm": 0.17314796149730682,
      "learning_rate": 4.095597328339452e-05,
      "loss": 0.6081,
      "step": 116
    },
    {
      "epoch": 0.4583741429970617,
      "grad_norm": 0.15215514600276947,
      "learning_rate": 4.0144148627425993e-05,
      "loss": 0.5905,
      "step": 117
    },
    {
      "epoch": 0.4622918707149853,
      "grad_norm": 0.15415742993354797,
      "learning_rate": 3.933501846281267e-05,
      "loss": 0.5964,
      "step": 118
    },
    {
      "epoch": 0.46620959843290893,
      "grad_norm": 0.1433228701353073,
      "learning_rate": 3.852880399766243e-05,
      "loss": 0.6376,
      "step": 119
    },
    {
      "epoch": 0.4701273261508325,
      "grad_norm": 0.16325964033603668,
      "learning_rate": 3.772572564296005e-05,
      "loss": 0.6376,
      "step": 120
    },
    {
      "epoch": 0.4740450538687561,
      "grad_norm": 0.14986704289913177,
      "learning_rate": 3.6926002952309016e-05,
      "loss": 0.6008,
      "step": 121
    },
    {
      "epoch": 0.4779627815866797,
      "grad_norm": 0.15410400927066803,
      "learning_rate": 3.612985456190778e-05,
      "loss": 0.579,
      "step": 122
    },
    {
      "epoch": 0.48188050930460335,
      "grad_norm": 0.16322776675224304,
      "learning_rate": 3.533749813077677e-05,
      "loss": 0.6128,
      "step": 123
    },
    {
      "epoch": 0.48579823702252695,
      "grad_norm": 0.1565704345703125,
      "learning_rate": 3.4549150281252636e-05,
      "loss": 0.6432,
      "step": 124
    },
    {
      "epoch": 0.48971596474045054,
      "grad_norm": 0.15959198772907257,
      "learning_rate": 3.3765026539765834e-05,
      "loss": 0.6235,
      "step": 125
    },
    {
      "epoch": 0.49363369245837413,
      "grad_norm": 0.14936403930187225,
      "learning_rate": 3.298534127791785e-05,
      "loss": 0.5608,
      "step": 126
    },
    {
      "epoch": 0.4975514201762977,
      "grad_norm": 0.1613105684518814,
      "learning_rate": 3.221030765387417e-05,
      "loss": 0.6073,
      "step": 127
    },
    {
      "epoch": 0.5014691478942214,
      "grad_norm": 0.15112361311912537,
      "learning_rate": 3.144013755408895e-05,
      "loss": 0.591,
      "step": 128
    },
    {
      "epoch": 0.5053868756121449,
      "grad_norm": 0.15241360664367676,
      "learning_rate": 3.0675041535377405e-05,
      "loss": 0.5941,
      "step": 129
    },
    {
      "epoch": 0.5093046033300686,
      "grad_norm": 0.15995562076568604,
      "learning_rate": 2.991522876735154e-05,
      "loss": 0.6589,
      "step": 130
    },
    {
      "epoch": 0.5132223310479922,
      "grad_norm": 0.15007995069026947,
      "learning_rate": 2.916090697523549e-05,
      "loss": 0.6275,
      "step": 131
    },
    {
      "epoch": 0.5171400587659157,
      "grad_norm": 0.1686083972454071,
      "learning_rate": 2.8412282383075363e-05,
      "loss": 0.6184,
      "step": 132
    },
    {
      "epoch": 0.5210577864838394,
      "grad_norm": 0.16540782153606415,
      "learning_rate": 2.766955965735968e-05,
      "loss": 0.5754,
      "step": 133
    },
    {
      "epoch": 0.524975514201763,
      "grad_norm": 0.18036416172981262,
      "learning_rate": 2.693294185106562e-05,
      "loss": 0.6265,
      "step": 134
    },
    {
      "epoch": 0.5288932419196866,
      "grad_norm": 0.16653621196746826,
      "learning_rate": 2.6202630348146324e-05,
      "loss": 0.5956,
      "step": 135
    },
    {
      "epoch": 0.5328109696376102,
      "grad_norm": 0.1652020663022995,
      "learning_rate": 2.547882480847461e-05,
      "loss": 0.6027,
      "step": 136
    },
    {
      "epoch": 0.5367286973555337,
      "grad_norm": 0.16848810017108917,
      "learning_rate": 2.476172311325783e-05,
      "loss": 0.5833,
      "step": 137
    },
    {
      "epoch": 0.5406464250734574,
      "grad_norm": 0.1777082085609436,
      "learning_rate": 2.405152131093926e-05,
      "loss": 0.6021,
      "step": 138
    },
    {
      "epoch": 0.544564152791381,
      "grad_norm": 0.192163348197937,
      "learning_rate": 2.3348413563600325e-05,
      "loss": 0.5494,
      "step": 139
    },
    {
      "epoch": 0.5484818805093046,
      "grad_norm": 0.17052263021469116,
      "learning_rate": 2.2652592093878666e-05,
      "loss": 0.5575,
      "step": 140
    },
    {
      "epoch": 0.5523996082272282,
      "grad_norm": 0.1905745416879654,
      "learning_rate": 2.196424713241637e-05,
      "loss": 0.5985,
      "step": 141
    },
    {
      "epoch": 0.5563173359451518,
      "grad_norm": 0.19184112548828125,
      "learning_rate": 2.128356686585282e-05,
      "loss": 0.5592,
      "step": 142
    },
    {
      "epoch": 0.5602350636630754,
      "grad_norm": 0.18394234776496887,
      "learning_rate": 2.061073738537635e-05,
      "loss": 0.5614,
      "step": 143
    },
    {
      "epoch": 0.564152791380999,
      "grad_norm": 0.21597835421562195,
      "learning_rate": 1.9945942635848748e-05,
      "loss": 0.6502,
      "step": 144
    },
    {
      "epoch": 0.5680705190989226,
      "grad_norm": 0.19436800479888916,
      "learning_rate": 1.928936436551661e-05,
      "loss": 0.6038,
      "step": 145
    },
    {
      "epoch": 0.5719882468168462,
      "grad_norm": 0.19521339237689972,
      "learning_rate": 1.8641182076323148e-05,
      "loss": 0.5935,
      "step": 146
    },
    {
      "epoch": 0.5759059745347699,
      "grad_norm": 0.1949096918106079,
      "learning_rate": 1.800157297483417e-05,
      "loss": 0.5427,
      "step": 147
    },
    {
      "epoch": 0.5798237022526934,
      "grad_norm": 0.2177155762910843,
      "learning_rate": 1.7370711923791567e-05,
      "loss": 0.6083,
      "step": 148
    },
    {
      "epoch": 0.5837414299706171,
      "grad_norm": 0.21610693633556366,
      "learning_rate": 1.6748771394307585e-05,
      "loss": 0.5304,
      "step": 149
    },
    {
      "epoch": 0.5876591576885406,
      "grad_norm": 0.2732427716255188,
      "learning_rate": 1.6135921418712956e-05,
      "loss": 0.6329,
      "step": 150
    },
    {
      "epoch": 0.5876591576885406,
      "eval_loss": 0.6000421643257141,
      "eval_runtime": 5.9359,
      "eval_samples_per_second": 72.44,
      "eval_steps_per_second": 18.194,
      "step": 150
    },
    {
      "epoch": 0.5915768854064642,
      "grad_norm": 0.289592981338501,
      "learning_rate": 1.553232954407171e-05,
      "loss": 0.6612,
      "step": 151
    },
    {
      "epoch": 0.5954946131243879,
      "grad_norm": 0.2455604523420334,
      "learning_rate": 1.4938160786375572e-05,
      "loss": 0.5864,
      "step": 152
    },
    {
      "epoch": 0.5994123408423114,
      "grad_norm": 0.283676415681839,
      "learning_rate": 1.435357758543015e-05,
      "loss": 0.657,
      "step": 153
    },
    {
      "epoch": 0.6033300685602351,
      "grad_norm": 0.2592833936214447,
      "learning_rate": 1.3778739760445552e-05,
      "loss": 0.6051,
      "step": 154
    },
    {
      "epoch": 0.6072477962781586,
      "grad_norm": 0.23298731446266174,
      "learning_rate": 1.3213804466343421e-05,
      "loss": 0.6057,
      "step": 155
    },
    {
      "epoch": 0.6111655239960823,
      "grad_norm": 0.24108311533927917,
      "learning_rate": 1.2658926150792322e-05,
      "loss": 0.5852,
      "step": 156
    },
    {
      "epoch": 0.6150832517140059,
      "grad_norm": 0.22434550523757935,
      "learning_rate": 1.2114256511983274e-05,
      "loss": 0.6549,
      "step": 157
    },
    {
      "epoch": 0.6190009794319294,
      "grad_norm": 0.21356070041656494,
      "learning_rate": 1.157994445715706e-05,
      "loss": 0.6382,
      "step": 158
    },
    {
      "epoch": 0.6229187071498531,
      "grad_norm": 0.1898113489151001,
      "learning_rate": 1.1056136061894384e-05,
      "loss": 0.5765,
      "step": 159
    },
    {
      "epoch": 0.6268364348677767,
      "grad_norm": 0.17581912875175476,
      "learning_rate": 1.0542974530180327e-05,
      "loss": 0.5859,
      "step": 160
    },
    {
      "epoch": 0.6307541625857003,
      "grad_norm": 0.16476130485534668,
      "learning_rate": 1.0040600155253765e-05,
      "loss": 0.608,
      "step": 161
    },
    {
      "epoch": 0.6346718903036239,
      "grad_norm": 0.1485903263092041,
      "learning_rate": 9.549150281252633e-06,
      "loss": 0.5889,
      "step": 162
    },
    {
      "epoch": 0.6385896180215475,
      "grad_norm": 0.1464112102985382,
      "learning_rate": 9.068759265665384e-06,
      "loss": 0.5781,
      "step": 163
    },
    {
      "epoch": 0.6425073457394711,
      "grad_norm": 0.1505204737186432,
      "learning_rate": 8.599558442598998e-06,
      "loss": 0.6206,
      "step": 164
    },
    {
      "epoch": 0.6464250734573947,
      "grad_norm": 0.1405332088470459,
      "learning_rate": 8.141676086873572e-06,
      "loss": 0.5882,
      "step": 165
    },
    {
      "epoch": 0.6503428011753183,
      "grad_norm": 0.14056198298931122,
      "learning_rate": 7.695237378953223e-06,
      "loss": 0.5976,
      "step": 166
    },
    {
      "epoch": 0.6542605288932419,
      "grad_norm": 0.13561733067035675,
      "learning_rate": 7.260364370723044e-06,
      "loss": 0.5677,
      "step": 167
    },
    {
      "epoch": 0.6581782566111655,
      "grad_norm": 0.13694676756858826,
      "learning_rate": 6.837175952121306e-06,
      "loss": 0.5478,
      "step": 168
    },
    {
      "epoch": 0.6620959843290891,
      "grad_norm": 0.15181538462638855,
      "learning_rate": 6.425787818636131e-06,
      "loss": 0.5712,
      "step": 169
    },
    {
      "epoch": 0.6660137120470128,
      "grad_norm": 0.1452825516462326,
      "learning_rate": 6.026312439675552e-06,
      "loss": 0.5799,
      "step": 170
    },
    {
      "epoch": 0.6699314397649363,
      "grad_norm": 0.13048894703388214,
      "learning_rate": 5.6388590278194096e-06,
      "loss": 0.5828,
      "step": 171
    },
    {
      "epoch": 0.67384916748286,
      "grad_norm": 0.16515865921974182,
      "learning_rate": 5.263533508961827e-06,
      "loss": 0.6076,
      "step": 172
    },
    {
      "epoch": 0.6777668952007836,
      "grad_norm": 0.14548875391483307,
      "learning_rate": 4.900438493352055e-06,
      "loss": 0.6133,
      "step": 173
    },
    {
      "epoch": 0.6816846229187071,
      "grad_norm": 0.14266423881053925,
      "learning_rate": 4.549673247541875e-06,
      "loss": 0.5989,
      "step": 174
    },
    {
      "epoch": 0.6856023506366308,
      "grad_norm": 0.14869347214698792,
      "learning_rate": 4.2113336672471245e-06,
      "loss": 0.5423,
      "step": 175
    },
    {
      "epoch": 0.6895200783545543,
      "grad_norm": 0.1848992258310318,
      "learning_rate": 3.885512251130763e-06,
      "loss": 0.5737,
      "step": 176
    },
    {
      "epoch": 0.693437806072478,
      "grad_norm": 0.17064626514911652,
      "learning_rate": 3.5722980755146517e-06,
      "loss": 0.6165,
      "step": 177
    },
    {
      "epoch": 0.6973555337904016,
      "grad_norm": 0.16314171254634857,
      "learning_rate": 3.271776770026963e-06,
      "loss": 0.6239,
      "step": 178
    },
    {
      "epoch": 0.7012732615083251,
      "grad_norm": 0.1614629030227661,
      "learning_rate": 2.9840304941919415e-06,
      "loss": 0.5836,
      "step": 179
    },
    {
      "epoch": 0.7051909892262488,
      "grad_norm": 0.19025197625160217,
      "learning_rate": 2.7091379149682685e-06,
      "loss": 0.5827,
      "step": 180
    },
    {
      "epoch": 0.7091087169441724,
      "grad_norm": 0.1722410023212433,
      "learning_rate": 2.4471741852423237e-06,
      "loss": 0.5983,
      "step": 181
    },
    {
      "epoch": 0.713026444662096,
      "grad_norm": 0.17831896245479584,
      "learning_rate": 2.1982109232821178e-06,
      "loss": 0.5358,
      "step": 182
    },
    {
      "epoch": 0.7169441723800196,
      "grad_norm": 0.1910993754863739,
      "learning_rate": 1.962316193157593e-06,
      "loss": 0.6044,
      "step": 183
    },
    {
      "epoch": 0.7208619000979432,
      "grad_norm": 0.17892290651798248,
      "learning_rate": 1.7395544861325718e-06,
      "loss": 0.5689,
      "step": 184
    },
    {
      "epoch": 0.7247796278158668,
      "grad_norm": 0.19452829658985138,
      "learning_rate": 1.5299867030334814e-06,
      "loss": 0.5841,
      "step": 185
    },
    {
      "epoch": 0.7286973555337904,
      "grad_norm": 0.20379012823104858,
      "learning_rate": 1.333670137599713e-06,
      "loss": 0.5948,
      "step": 186
    },
    {
      "epoch": 0.732615083251714,
      "grad_norm": 0.21492238342761993,
      "learning_rate": 1.1506584608200367e-06,
      "loss": 0.6185,
      "step": 187
    },
    {
      "epoch": 0.7365328109696376,
      "grad_norm": 0.18927186727523804,
      "learning_rate": 9.810017062595322e-07,
      "loss": 0.5662,
      "step": 188
    },
    {
      "epoch": 0.7404505386875612,
      "grad_norm": 0.21611472964286804,
      "learning_rate": 8.247462563808817e-07,
      "loss": 0.5906,
      "step": 189
    },
    {
      "epoch": 0.7443682664054848,
      "grad_norm": 0.19977721571922302,
      "learning_rate": 6.819348298638839e-07,
      "loss": 0.5734,
      "step": 190
    },
    {
      "epoch": 0.7482859941234085,
      "grad_norm": 0.20738379657268524,
      "learning_rate": 5.526064699265753e-07,
      "loss": 0.5466,
      "step": 191
    },
    {
      "epoch": 0.752203721841332,
      "grad_norm": 0.2219565361738205,
      "learning_rate": 4.367965336512403e-07,
      "loss": 0.5934,
      "step": 192
    },
    {
      "epoch": 0.7561214495592556,
      "grad_norm": 0.2512089014053345,
      "learning_rate": 3.3453668231809286e-07,
      "loss": 0.5328,
      "step": 193
    },
    {
      "epoch": 0.7600391772771793,
      "grad_norm": 0.2491757869720459,
      "learning_rate": 2.458548727494292e-07,
      "loss": 0.6292,
      "step": 194
    },
    {
      "epoch": 0.7639569049951028,
      "grad_norm": 0.26241135597229004,
      "learning_rate": 1.7077534966650766e-07,
      "loss": 0.6029,
      "step": 195
    },
    {
      "epoch": 0.7678746327130265,
      "grad_norm": 0.27278319001197815,
      "learning_rate": 1.0931863906127327e-07,
      "loss": 0.6125,
      "step": 196
    },
    {
      "epoch": 0.77179236043095,
      "grad_norm": 0.31411460041999817,
      "learning_rate": 6.150154258476315e-08,
      "loss": 0.6723,
      "step": 197
    },
    {
      "epoch": 0.7757100881488737,
      "grad_norm": 0.3309330344200134,
      "learning_rate": 2.7337132953697554e-08,
      "loss": 0.5655,
      "step": 198
    },
    {
      "epoch": 0.7796278158667973,
      "grad_norm": 0.33389514684677124,
      "learning_rate": 6.834750376549792e-09,
      "loss": 0.6058,
      "step": 199
    },
    {
      "epoch": 0.7835455435847208,
      "grad_norm": 0.40921080112457275,
      "learning_rate": 0.0,
      "loss": 0.6206,
      "step": 200
    },
    {
      "epoch": 0.7835455435847208,
      "eval_loss": 0.5939285159111023,
      "eval_runtime": 5.9129,
      "eval_samples_per_second": 72.722,
      "eval_steps_per_second": 18.265,
      "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": 5061780452671488.0,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}