{
  "best_metric": 0.18071845173835754,
  "best_model_checkpoint": "miner_id_24/checkpoint-200",
  "epoch": 0.05739292632183084,
  "eval_steps": 50,
  "global_step": 200,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.00028696463160915415,
      "grad_norm": 0.5229994058609009,
      "learning_rate": 1e-05,
      "loss": 0.6193,
      "step": 1
    },
    {
      "epoch": 0.00028696463160915415,
      "eval_loss": 1.0751729011535645,
      "eval_runtime": 704.0175,
      "eval_samples_per_second": 8.336,
      "eval_steps_per_second": 2.085,
      "step": 1
    },
    {
      "epoch": 0.0005739292632183083,
      "grad_norm": 0.5277003645896912,
      "learning_rate": 2e-05,
      "loss": 0.6414,
      "step": 2
    },
    {
      "epoch": 0.0008608938948274625,
      "grad_norm": 0.5209378600120544,
      "learning_rate": 3e-05,
      "loss": 0.6512,
      "step": 3
    },
    {
      "epoch": 0.0011478585264366166,
      "grad_norm": 0.48514431715011597,
      "learning_rate": 4e-05,
      "loss": 0.5938,
      "step": 4
    },
    {
      "epoch": 0.001434823158045771,
      "grad_norm": 0.43488216400146484,
      "learning_rate": 5e-05,
      "loss": 0.5713,
      "step": 5
    },
    {
      "epoch": 0.001721787789654925,
      "grad_norm": 0.35605230927467346,
      "learning_rate": 6e-05,
      "loss": 0.5095,
      "step": 6
    },
    {
      "epoch": 0.002008752421264079,
      "grad_norm": 0.3742581009864807,
      "learning_rate": 7e-05,
      "loss": 0.4965,
      "step": 7
    },
    {
      "epoch": 0.002295717052873233,
      "grad_norm": 0.4569806456565857,
      "learning_rate": 8e-05,
      "loss": 0.4454,
      "step": 8
    },
    {
      "epoch": 0.0025826816844823877,
      "grad_norm": 0.4318329691886902,
      "learning_rate": 9e-05,
      "loss": 0.4077,
      "step": 9
    },
    {
      "epoch": 0.002869646316091542,
      "grad_norm": 0.3778272867202759,
      "learning_rate": 0.0001,
      "loss": 0.3788,
      "step": 10
    },
    {
      "epoch": 0.003156610947700696,
      "grad_norm": 0.3034924566745758,
      "learning_rate": 9.999316524962345e-05,
      "loss": 0.3272,
      "step": 11
    },
    {
      "epoch": 0.00344357557930985,
      "grad_norm": 0.31499189138412476,
      "learning_rate": 9.997266286704631e-05,
      "loss": 0.3145,
      "step": 12
    },
    {
      "epoch": 0.003730540210919004,
      "grad_norm": 0.2762828469276428,
      "learning_rate": 9.993849845741524e-05,
      "loss": 0.3143,
      "step": 13
    },
    {
      "epoch": 0.004017504842528158,
      "grad_norm": 0.24831600487232208,
      "learning_rate": 9.989068136093873e-05,
      "loss": 0.3012,
      "step": 14
    },
    {
      "epoch": 0.004304469474137313,
      "grad_norm": 0.24490486085414886,
      "learning_rate": 9.98292246503335e-05,
      "loss": 0.2943,
      "step": 15
    },
    {
      "epoch": 0.004591434105746466,
      "grad_norm": 0.20159794390201569,
      "learning_rate": 9.975414512725057e-05,
      "loss": 0.2567,
      "step": 16
    },
    {
      "epoch": 0.004878398737355621,
      "grad_norm": 0.23322193324565887,
      "learning_rate": 9.966546331768191e-05,
      "loss": 0.2875,
      "step": 17
    },
    {
      "epoch": 0.0051653633689647755,
      "grad_norm": 0.24555742740631104,
      "learning_rate": 9.956320346634876e-05,
      "loss": 0.2993,
      "step": 18
    },
    {
      "epoch": 0.005452328000573929,
      "grad_norm": 0.20733901858329773,
      "learning_rate": 9.944739353007344e-05,
      "loss": 0.2677,
      "step": 19
    },
    {
      "epoch": 0.005739292632183084,
      "grad_norm": 0.223092719912529,
      "learning_rate": 9.931806517013612e-05,
      "loss": 0.2546,
      "step": 20
    },
    {
      "epoch": 0.006026257263792237,
      "grad_norm": 0.2321721762418747,
      "learning_rate": 9.917525374361912e-05,
      "loss": 0.2512,
      "step": 21
    },
    {
      "epoch": 0.006313221895401392,
      "grad_norm": 0.2086208611726761,
      "learning_rate": 9.901899829374047e-05,
      "loss": 0.2705,
      "step": 22
    },
    {
      "epoch": 0.0066001865270105455,
      "grad_norm": 0.23189643025398254,
      "learning_rate": 9.884934153917997e-05,
      "loss": 0.2775,
      "step": 23
    },
    {
      "epoch": 0.0068871511586197,
      "grad_norm": 0.2565009295940399,
      "learning_rate": 9.86663298624003e-05,
      "loss": 0.2563,
      "step": 24
    },
    {
      "epoch": 0.007174115790228855,
      "grad_norm": 0.24817073345184326,
      "learning_rate": 9.847001329696653e-05,
      "loss": 0.2712,
      "step": 25
    },
    {
      "epoch": 0.007461080421838008,
      "grad_norm": 0.23539327085018158,
      "learning_rate": 9.826044551386744e-05,
      "loss": 0.2813,
      "step": 26
    },
    {
      "epoch": 0.007748045053447163,
      "grad_norm": 0.2583278715610504,
      "learning_rate": 9.803768380684242e-05,
      "loss": 0.2749,
      "step": 27
    },
    {
      "epoch": 0.008035009685056316,
      "grad_norm": 0.2330855429172516,
      "learning_rate": 9.780178907671789e-05,
      "loss": 0.2674,
      "step": 28
    },
    {
      "epoch": 0.008321974316665471,
      "grad_norm": 0.23105184733867645,
      "learning_rate": 9.755282581475769e-05,
      "loss": 0.2464,
      "step": 29
    },
    {
      "epoch": 0.008608938948274625,
      "grad_norm": 0.29990822076797485,
      "learning_rate": 9.729086208503174e-05,
      "loss": 0.2866,
      "step": 30
    },
    {
      "epoch": 0.00889590357988378,
      "grad_norm": 0.3129001557826996,
      "learning_rate": 9.701596950580806e-05,
      "loss": 0.1918,
      "step": 31
    },
    {
      "epoch": 0.009182868211492933,
      "grad_norm": 0.2960960566997528,
      "learning_rate": 9.672822322997305e-05,
      "loss": 0.2391,
      "step": 32
    },
    {
      "epoch": 0.009469832843102087,
      "grad_norm": 0.2717934846878052,
      "learning_rate": 9.642770192448536e-05,
      "loss": 0.2459,
      "step": 33
    },
    {
      "epoch": 0.009756797474711242,
      "grad_norm": 0.32052090764045715,
      "learning_rate": 9.611448774886924e-05,
      "loss": 0.2482,
      "step": 34
    },
    {
      "epoch": 0.010043762106320396,
      "grad_norm": 0.44271981716156006,
      "learning_rate": 9.578866633275288e-05,
      "loss": 0.1704,
      "step": 35
    },
    {
      "epoch": 0.010330726737929551,
      "grad_norm": 0.23712387681007385,
      "learning_rate": 9.545032675245813e-05,
      "loss": 0.2121,
      "step": 36
    },
    {
      "epoch": 0.010617691369538704,
      "grad_norm": 0.3437686562538147,
      "learning_rate": 9.509956150664796e-05,
      "loss": 0.2551,
      "step": 37
    },
    {
      "epoch": 0.010904656001147858,
      "grad_norm": 0.379600465297699,
      "learning_rate": 9.473646649103818e-05,
      "loss": 0.2825,
      "step": 38
    },
    {
      "epoch": 0.011191620632757013,
      "grad_norm": 0.36234280467033386,
      "learning_rate": 9.43611409721806e-05,
      "loss": 0.3062,
      "step": 39
    },
    {
      "epoch": 0.011478585264366167,
      "grad_norm": 0.35884663462638855,
      "learning_rate": 9.397368756032445e-05,
      "loss": 0.2462,
      "step": 40
    },
    {
      "epoch": 0.011765549895975322,
      "grad_norm": 0.34565645456314087,
      "learning_rate": 9.357421218136386e-05,
      "loss": 0.2685,
      "step": 41
    },
    {
      "epoch": 0.012052514527584475,
      "grad_norm": 0.3510606586933136,
      "learning_rate": 9.316282404787871e-05,
      "loss": 0.2549,
      "step": 42
    },
    {
      "epoch": 0.01233947915919363,
      "grad_norm": 0.4026327431201935,
      "learning_rate": 9.273963562927695e-05,
      "loss": 0.2185,
      "step": 43
    },
    {
      "epoch": 0.012626443790802784,
      "grad_norm": 0.49996432662010193,
      "learning_rate": 9.230476262104677e-05,
      "loss": 0.3016,
      "step": 44
    },
    {
      "epoch": 0.012913408422411938,
      "grad_norm": 0.43853244185447693,
      "learning_rate": 9.185832391312644e-05,
      "loss": 0.2657,
      "step": 45
    },
    {
      "epoch": 0.013200373054021091,
      "grad_norm": 0.5363871455192566,
      "learning_rate": 9.140044155740101e-05,
      "loss": 0.352,
      "step": 46
    },
    {
      "epoch": 0.013487337685630246,
      "grad_norm": 0.6242479085922241,
      "learning_rate": 9.093124073433463e-05,
      "loss": 0.2277,
      "step": 47
    },
    {
      "epoch": 0.0137743023172394,
      "grad_norm": 0.6121565699577332,
      "learning_rate": 9.045084971874738e-05,
      "loss": 0.1486,
      "step": 48
    },
    {
      "epoch": 0.014061266948848555,
      "grad_norm": 0.4884735643863678,
      "learning_rate": 8.995939984474624e-05,
      "loss": 0.1968,
      "step": 49
    },
    {
      "epoch": 0.01434823158045771,
      "grad_norm": 1.2371174097061157,
      "learning_rate": 8.945702546981969e-05,
      "loss": 0.4361,
      "step": 50
    },
    {
      "epoch": 0.01434823158045771,
      "eval_loss": 0.31488773226737976,
      "eval_runtime": 708.2977,
      "eval_samples_per_second": 8.286,
      "eval_steps_per_second": 2.073,
      "step": 50
    },
    {
      "epoch": 0.014635196212066862,
      "grad_norm": 0.5216653347015381,
      "learning_rate": 8.894386393810563e-05,
      "loss": 0.3245,
      "step": 51
    },
    {
      "epoch": 0.014922160843676016,
      "grad_norm": 0.3779897093772888,
      "learning_rate": 8.842005554284296e-05,
      "loss": 0.3183,
      "step": 52
    },
    {
      "epoch": 0.015209125475285171,
      "grad_norm": 0.20228858292102814,
      "learning_rate": 8.788574348801675e-05,
      "loss": 0.2493,
      "step": 53
    },
    {
      "epoch": 0.015496090106894326,
      "grad_norm": 0.1568831205368042,
      "learning_rate": 8.73410738492077e-05,
      "loss": 0.2606,
      "step": 54
    },
    {
      "epoch": 0.01578305473850348,
      "grad_norm": 0.1864292025566101,
      "learning_rate": 8.678619553365659e-05,
      "loss": 0.2427,
      "step": 55
    },
    {
      "epoch": 0.016070019370112633,
      "grad_norm": 0.16999222338199615,
      "learning_rate": 8.622126023955446e-05,
      "loss": 0.2346,
      "step": 56
    },
    {
      "epoch": 0.016356984001721787,
      "grad_norm": 0.16926024854183197,
      "learning_rate": 8.564642241456986e-05,
      "loss": 0.2498,
      "step": 57
    },
    {
      "epoch": 0.016643948633330942,
      "grad_norm": 0.15306591987609863,
      "learning_rate": 8.506183921362443e-05,
      "loss": 0.2147,
      "step": 58
    },
    {
      "epoch": 0.016930913264940096,
      "grad_norm": 0.16391609609127045,
      "learning_rate": 8.44676704559283e-05,
      "loss": 0.2347,
      "step": 59
    },
    {
      "epoch": 0.01721787789654925,
      "grad_norm": 0.14865294098854065,
      "learning_rate": 8.386407858128706e-05,
      "loss": 0.2343,
      "step": 60
    },
    {
      "epoch": 0.017504842528158406,
      "grad_norm": 0.12811127305030823,
      "learning_rate": 8.32512286056924e-05,
      "loss": 0.21,
      "step": 61
    },
    {
      "epoch": 0.01779180715976756,
      "grad_norm": 0.12115540355443954,
      "learning_rate": 8.262928807620843e-05,
      "loss": 0.218,
      "step": 62
    },
    {
      "epoch": 0.01807877179137671,
      "grad_norm": 0.12110285460948944,
      "learning_rate": 8.199842702516583e-05,
      "loss": 0.2327,
      "step": 63
    },
    {
      "epoch": 0.018365736422985866,
      "grad_norm": 0.12485136091709137,
      "learning_rate": 8.135881792367686e-05,
      "loss": 0.2065,
      "step": 64
    },
    {
      "epoch": 0.01865270105459502,
      "grad_norm": 0.12094296514987946,
      "learning_rate": 8.07106356344834e-05,
      "loss": 0.2127,
      "step": 65
    },
    {
      "epoch": 0.018939665686204175,
      "grad_norm": 0.1227046474814415,
      "learning_rate": 8.005405736415126e-05,
      "loss": 0.198,
      "step": 66
    },
    {
      "epoch": 0.01922663031781333,
      "grad_norm": 0.15381614863872528,
      "learning_rate": 7.938926261462366e-05,
      "loss": 0.2209,
      "step": 67
    },
    {
      "epoch": 0.019513594949422484,
      "grad_norm": 0.12911836802959442,
      "learning_rate": 7.871643313414718e-05,
      "loss": 0.2048,
      "step": 68
    },
    {
      "epoch": 0.01980055958103164,
      "grad_norm": 0.14704543352127075,
      "learning_rate": 7.803575286758364e-05,
      "loss": 0.2111,
      "step": 69
    },
    {
      "epoch": 0.020087524212640793,
      "grad_norm": 0.12387403100728989,
      "learning_rate": 7.734740790612136e-05,
      "loss": 0.2276,
      "step": 70
    },
    {
      "epoch": 0.020374488844249947,
      "grad_norm": 0.1372983306646347,
      "learning_rate": 7.66515864363997e-05,
      "loss": 0.2008,
      "step": 71
    },
    {
      "epoch": 0.020661453475859102,
      "grad_norm": 0.13901743292808533,
      "learning_rate": 7.594847868906076e-05,
      "loss": 0.2176,
      "step": 72
    },
    {
      "epoch": 0.020948418107468253,
      "grad_norm": 0.14263680577278137,
      "learning_rate": 7.52382768867422e-05,
      "loss": 0.2181,
      "step": 73
    },
    {
      "epoch": 0.021235382739077407,
      "grad_norm": 0.13881926238536835,
      "learning_rate": 7.452117519152542e-05,
      "loss": 0.2194,
      "step": 74
    },
    {
      "epoch": 0.021522347370686562,
      "grad_norm": 0.15550597012043,
      "learning_rate": 7.379736965185368e-05,
      "loss": 0.2167,
      "step": 75
    },
    {
      "epoch": 0.021809312002295717,
      "grad_norm": 0.162664532661438,
      "learning_rate": 7.30670581489344e-05,
      "loss": 0.2285,
      "step": 76
    },
    {
      "epoch": 0.02209627663390487,
      "grad_norm": 0.15334895253181458,
      "learning_rate": 7.233044034264034e-05,
      "loss": 0.2374,
      "step": 77
    },
    {
      "epoch": 0.022383241265514026,
      "grad_norm": 0.15148641169071198,
      "learning_rate": 7.158771761692464e-05,
      "loss": 0.2173,
      "step": 78
    },
    {
      "epoch": 0.02267020589712318,
      "grad_norm": 0.17409859597682953,
      "learning_rate": 7.083909302476453e-05,
      "loss": 0.2115,
      "step": 79
    },
    {
      "epoch": 0.022957170528732335,
      "grad_norm": 0.1602027863264084,
      "learning_rate": 7.008477123264848e-05,
      "loss": 0.1831,
      "step": 80
    },
    {
      "epoch": 0.02324413516034149,
      "grad_norm": 0.16173700988292694,
      "learning_rate": 6.932495846462261e-05,
      "loss": 0.1953,
      "step": 81
    },
    {
      "epoch": 0.023531099791950644,
      "grad_norm": 0.15456171333789825,
      "learning_rate": 6.855986244591104e-05,
      "loss": 0.159,
      "step": 82
    },
    {
      "epoch": 0.023818064423559795,
      "grad_norm": 0.15866632759571075,
      "learning_rate": 6.778969234612584e-05,
      "loss": 0.1914,
      "step": 83
    },
    {
      "epoch": 0.02410502905516895,
      "grad_norm": 0.16335618495941162,
      "learning_rate": 6.701465872208216e-05,
      "loss": 0.1881,
      "step": 84
    },
    {
      "epoch": 0.024391993686778104,
      "grad_norm": 0.19362057745456696,
      "learning_rate": 6.623497346023418e-05,
      "loss": 0.1432,
      "step": 85
    },
    {
      "epoch": 0.02467895831838726,
      "grad_norm": 0.1901354342699051,
      "learning_rate": 6.545084971874738e-05,
      "loss": 0.1384,
      "step": 86
    },
    {
      "epoch": 0.024965922949996413,
      "grad_norm": 0.20158971846103668,
      "learning_rate": 6.466250186922325e-05,
      "loss": 0.2359,
      "step": 87
    },
    {
      "epoch": 0.025252887581605567,
      "grad_norm": 0.21462437510490417,
      "learning_rate": 6.387014543809223e-05,
      "loss": 0.1992,
      "step": 88
    },
    {
      "epoch": 0.025539852213214722,
      "grad_norm": 0.26754477620124817,
      "learning_rate": 6.307399704769099e-05,
      "loss": 0.2365,
      "step": 89
    },
    {
      "epoch": 0.025826816844823876,
      "grad_norm": 0.28357595205307007,
      "learning_rate": 6.227427435703997e-05,
      "loss": 0.2122,
      "step": 90
    },
    {
      "epoch": 0.02611378147643303,
      "grad_norm": 0.26988905668258667,
      "learning_rate": 6.147119600233758e-05,
      "loss": 0.2436,
      "step": 91
    },
    {
      "epoch": 0.026400746108042182,
      "grad_norm": 0.27435871958732605,
      "learning_rate": 6.066498153718735e-05,
      "loss": 0.1599,
      "step": 92
    },
    {
      "epoch": 0.026687710739651337,
      "grad_norm": 0.2062823623418808,
      "learning_rate": 5.985585137257401e-05,
      "loss": 0.1371,
      "step": 93
    },
    {
      "epoch": 0.02697467537126049,
      "grad_norm": 0.3089089095592499,
      "learning_rate": 5.90440267166055e-05,
      "loss": 0.2122,
      "step": 94
    },
    {
      "epoch": 0.027261640002869646,
      "grad_norm": 0.29551589488983154,
      "learning_rate": 5.8229729514036705e-05,
      "loss": 0.2291,
      "step": 95
    },
    {
      "epoch": 0.0275486046344788,
      "grad_norm": 0.39308205246925354,
      "learning_rate": 5.74131823855921e-05,
      "loss": 0.2541,
      "step": 96
    },
    {
      "epoch": 0.027835569266087955,
      "grad_norm": 0.44186562299728394,
      "learning_rate": 5.6594608567103456e-05,
      "loss": 0.1932,
      "step": 97
    },
    {
      "epoch": 0.02812253389769711,
      "grad_norm": 0.37216901779174805,
      "learning_rate": 5.577423184847932e-05,
      "loss": 0.0937,
      "step": 98
    },
    {
      "epoch": 0.028409498529306264,
      "grad_norm": 0.5349317789077759,
      "learning_rate": 5.495227651252315e-05,
      "loss": 0.2026,
      "step": 99
    },
    {
      "epoch": 0.02869646316091542,
      "grad_norm": 0.7212300896644592,
      "learning_rate": 5.4128967273616625e-05,
      "loss": 0.3075,
      "step": 100
    },
    {
      "epoch": 0.02869646316091542,
      "eval_loss": 0.25692251324653625,
      "eval_runtime": 709.1627,
      "eval_samples_per_second": 8.276,
      "eval_steps_per_second": 2.07,
      "step": 100
    },
    {
      "epoch": 0.028983427792524573,
      "grad_norm": 0.3828531801700592,
      "learning_rate": 5.330452921628497e-05,
      "loss": 0.2604,
      "step": 101
    },
    {
      "epoch": 0.029270392424133724,
      "grad_norm": 0.3181626498699188,
      "learning_rate": 5.247918773366112e-05,
      "loss": 0.2743,
      "step": 102
    },
    {
      "epoch": 0.02955735705574288,
      "grad_norm": 0.21627208590507507,
      "learning_rate": 5.165316846586541e-05,
      "loss": 0.247,
      "step": 103
    },
    {
      "epoch": 0.029844321687352033,
      "grad_norm": 0.15220759809017181,
      "learning_rate": 5.0826697238317935e-05,
      "loss": 0.2216,
      "step": 104
    },
    {
      "epoch": 0.030131286318961188,
      "grad_norm": 0.12166014313697815,
      "learning_rate": 5e-05,
      "loss": 0.2225,
      "step": 105
    },
    {
      "epoch": 0.030418250950570342,
      "grad_norm": 0.10366802662611008,
      "learning_rate": 4.917330276168208e-05,
      "loss": 0.2112,
      "step": 106
    },
    {
      "epoch": 0.030705215582179497,
      "grad_norm": 0.1254051774740219,
      "learning_rate": 4.834683153413459e-05,
      "loss": 0.195,
      "step": 107
    },
    {
      "epoch": 0.03099218021378865,
      "grad_norm": 0.14223499596118927,
      "learning_rate": 4.7520812266338885e-05,
      "loss": 0.2118,
      "step": 108
    },
    {
      "epoch": 0.0312791448453978,
      "grad_norm": 0.12292707711458206,
      "learning_rate": 4.669547078371504e-05,
      "loss": 0.1969,
      "step": 109
    },
    {
      "epoch": 0.03156610947700696,
      "grad_norm": 0.1324101835489273,
      "learning_rate": 4.5871032726383386e-05,
      "loss": 0.1904,
      "step": 110
    },
    {
      "epoch": 0.03185307410861611,
      "grad_norm": 0.114923395216465,
      "learning_rate": 4.504772348747687e-05,
      "loss": 0.1917,
      "step": 111
    },
    {
      "epoch": 0.032140038740225266,
      "grad_norm": 0.11760342866182327,
      "learning_rate": 4.4225768151520694e-05,
      "loss": 0.202,
      "step": 112
    },
    {
      "epoch": 0.03242700337183442,
      "grad_norm": 0.11858177930116653,
      "learning_rate": 4.3405391432896555e-05,
      "loss": 0.2133,
      "step": 113
    },
    {
      "epoch": 0.032713968003443575,
      "grad_norm": 0.1077466681599617,
      "learning_rate": 4.2586817614407895e-05,
      "loss": 0.2014,
      "step": 114
    },
    {
      "epoch": 0.03300093263505273,
      "grad_norm": 0.11777017265558243,
      "learning_rate": 4.17702704859633e-05,
      "loss": 0.1825,
      "step": 115
    },
    {
      "epoch": 0.033287897266661884,
      "grad_norm": 0.11433833837509155,
      "learning_rate": 4.095597328339452e-05,
      "loss": 0.206,
      "step": 116
    },
    {
      "epoch": 0.03357486189827104,
      "grad_norm": 0.10720719397068024,
      "learning_rate": 4.0144148627425993e-05,
      "loss": 0.1769,
      "step": 117
    },
    {
      "epoch": 0.03386182652988019,
      "grad_norm": 0.10495130717754364,
      "learning_rate": 3.933501846281267e-05,
      "loss": 0.1905,
      "step": 118
    },
    {
      "epoch": 0.03414879116148935,
      "grad_norm": 0.1098421961069107,
      "learning_rate": 3.852880399766243e-05,
      "loss": 0.193,
      "step": 119
    },
    {
      "epoch": 0.0344357557930985,
      "grad_norm": 0.12833455204963684,
      "learning_rate": 3.772572564296005e-05,
      "loss": 0.2133,
      "step": 120
    },
    {
      "epoch": 0.034722720424707657,
      "grad_norm": 0.12317852675914764,
      "learning_rate": 3.6926002952309016e-05,
      "loss": 0.2151,
      "step": 121
    },
    {
      "epoch": 0.03500968505631681,
      "grad_norm": 0.13000623881816864,
      "learning_rate": 3.612985456190778e-05,
      "loss": 0.2186,
      "step": 122
    },
    {
      "epoch": 0.035296649687925966,
      "grad_norm": 0.13759087026119232,
      "learning_rate": 3.533749813077677e-05,
      "loss": 0.2214,
      "step": 123
    },
    {
      "epoch": 0.03558361431953512,
      "grad_norm": 0.13046890497207642,
      "learning_rate": 3.4549150281252636e-05,
      "loss": 0.199,
      "step": 124
    },
    {
      "epoch": 0.035870578951144275,
      "grad_norm": 0.11978602409362793,
      "learning_rate": 3.3765026539765834e-05,
      "loss": 0.2111,
      "step": 125
    },
    {
      "epoch": 0.03615754358275342,
      "grad_norm": 0.14002515375614166,
      "learning_rate": 3.298534127791785e-05,
      "loss": 0.2086,
      "step": 126
    },
    {
      "epoch": 0.03644450821436258,
      "grad_norm": 0.14103305339813232,
      "learning_rate": 3.221030765387417e-05,
      "loss": 0.2041,
      "step": 127
    },
    {
      "epoch": 0.03673147284597173,
      "grad_norm": 0.14168894290924072,
      "learning_rate": 3.144013755408895e-05,
      "loss": 0.1983,
      "step": 128
    },
    {
      "epoch": 0.037018437477580886,
      "grad_norm": 0.1231461763381958,
      "learning_rate": 3.0675041535377405e-05,
      "loss": 0.1856,
      "step": 129
    },
    {
      "epoch": 0.03730540210919004,
      "grad_norm": 0.13945582509040833,
      "learning_rate": 2.991522876735154e-05,
      "loss": 0.1284,
      "step": 130
    },
    {
      "epoch": 0.037592366740799195,
      "grad_norm": 0.1356101632118225,
      "learning_rate": 2.916090697523549e-05,
      "loss": 0.1521,
      "step": 131
    },
    {
      "epoch": 0.03787933137240835,
      "grad_norm": 0.13012702763080597,
      "learning_rate": 2.8412282383075363e-05,
      "loss": 0.1829,
      "step": 132
    },
    {
      "epoch": 0.038166296004017504,
      "grad_norm": 0.141743004322052,
      "learning_rate": 2.766955965735968e-05,
      "loss": 0.1671,
      "step": 133
    },
    {
      "epoch": 0.03845326063562666,
      "grad_norm": 0.12610375881195068,
      "learning_rate": 2.693294185106562e-05,
      "loss": 0.1536,
      "step": 134
    },
    {
      "epoch": 0.03874022526723581,
      "grad_norm": 0.15423394739627838,
      "learning_rate": 2.6202630348146324e-05,
      "loss": 0.1142,
      "step": 135
    },
    {
      "epoch": 0.03902718989884497,
      "grad_norm": 0.1594805270433426,
      "learning_rate": 2.547882480847461e-05,
      "loss": 0.1746,
      "step": 136
    },
    {
      "epoch": 0.03931415453045412,
      "grad_norm": 0.15287446975708008,
      "learning_rate": 2.476172311325783e-05,
      "loss": 0.2131,
      "step": 137
    },
    {
      "epoch": 0.03960111916206328,
      "grad_norm": 0.2132658064365387,
      "learning_rate": 2.405152131093926e-05,
      "loss": 0.2069,
      "step": 138
    },
    {
      "epoch": 0.03988808379367243,
      "grad_norm": 0.20114755630493164,
      "learning_rate": 2.3348413563600325e-05,
      "loss": 0.2075,
      "step": 139
    },
    {
      "epoch": 0.040175048425281586,
      "grad_norm": 0.21833276748657227,
      "learning_rate": 2.2652592093878666e-05,
      "loss": 0.1893,
      "step": 140
    },
    {
      "epoch": 0.04046201305689074,
      "grad_norm": 0.1935897320508957,
      "learning_rate": 2.196424713241637e-05,
      "loss": 0.2026,
      "step": 141
    },
    {
      "epoch": 0.040748977688499895,
      "grad_norm": 0.2028902918100357,
      "learning_rate": 2.128356686585282e-05,
      "loss": 0.1797,
      "step": 142
    },
    {
      "epoch": 0.04103594232010905,
      "grad_norm": 0.22900693118572235,
      "learning_rate": 2.061073738537635e-05,
      "loss": 0.1406,
      "step": 143
    },
    {
      "epoch": 0.041322906951718204,
      "grad_norm": 0.24136166274547577,
      "learning_rate": 1.9945942635848748e-05,
      "loss": 0.1894,
      "step": 144
    },
    {
      "epoch": 0.04160987158332736,
      "grad_norm": 0.2650553584098816,
      "learning_rate": 1.928936436551661e-05,
      "loss": 0.1944,
      "step": 145
    },
    {
      "epoch": 0.041896836214936506,
      "grad_norm": 0.2891697883605957,
      "learning_rate": 1.8641182076323148e-05,
      "loss": 0.2186,
      "step": 146
    },
    {
      "epoch": 0.04218380084654566,
      "grad_norm": 0.3081960380077362,
      "learning_rate": 1.800157297483417e-05,
      "loss": 0.184,
      "step": 147
    },
    {
      "epoch": 0.042470765478154815,
      "grad_norm": 0.398459792137146,
      "learning_rate": 1.7370711923791567e-05,
      "loss": 0.1211,
      "step": 148
    },
    {
      "epoch": 0.04275773010976397,
      "grad_norm": 0.36123889684677124,
      "learning_rate": 1.6748771394307585e-05,
      "loss": 0.1088,
      "step": 149
    },
    {
      "epoch": 0.043044694741373124,
      "grad_norm": 0.32032233476638794,
      "learning_rate": 1.6135921418712956e-05,
      "loss": 0.2068,
      "step": 150
    },
    {
      "epoch": 0.043044694741373124,
      "eval_loss": 0.1970216929912567,
      "eval_runtime": 708.655,
      "eval_samples_per_second": 8.282,
      "eval_steps_per_second": 2.072,
      "step": 150
    },
    {
      "epoch": 0.04333165937298228,
      "grad_norm": 0.20966850221157074,
      "learning_rate": 1.553232954407171e-05,
      "loss": 0.2381,
      "step": 151
    },
    {
      "epoch": 0.04361862400459143,
      "grad_norm": 0.20415854454040527,
      "learning_rate": 1.4938160786375572e-05,
      "loss": 0.2215,
      "step": 152
    },
    {
      "epoch": 0.04390558863620059,
      "grad_norm": 0.21057139337062836,
      "learning_rate": 1.435357758543015e-05,
      "loss": 0.2293,
      "step": 153
    },
    {
      "epoch": 0.04419255326780974,
      "grad_norm": 0.17874518036842346,
      "learning_rate": 1.3778739760445552e-05,
      "loss": 0.2203,
      "step": 154
    },
    {
      "epoch": 0.0444795178994189,
      "grad_norm": 0.16336949169635773,
      "learning_rate": 1.3213804466343421e-05,
      "loss": 0.2073,
      "step": 155
    },
    {
      "epoch": 0.04476648253102805,
      "grad_norm": 0.1575133502483368,
      "learning_rate": 1.2658926150792322e-05,
      "loss": 0.2177,
      "step": 156
    },
    {
      "epoch": 0.045053447162637206,
      "grad_norm": 0.16577646136283875,
      "learning_rate": 1.2114256511983274e-05,
      "loss": 0.1946,
      "step": 157
    },
    {
      "epoch": 0.04534041179424636,
      "grad_norm": 0.14570212364196777,
      "learning_rate": 1.157994445715706e-05,
      "loss": 0.1934,
      "step": 158
    },
    {
      "epoch": 0.045627376425855515,
      "grad_norm": 0.13147036731243134,
      "learning_rate": 1.1056136061894384e-05,
      "loss": 0.1959,
      "step": 159
    },
    {
      "epoch": 0.04591434105746467,
      "grad_norm": 0.14665886759757996,
      "learning_rate": 1.0542974530180327e-05,
      "loss": 0.1674,
      "step": 160
    },
    {
      "epoch": 0.046201305689073824,
      "grad_norm": 0.12598645687103271,
      "learning_rate": 1.0040600155253765e-05,
      "loss": 0.1862,
      "step": 161
    },
    {
      "epoch": 0.04648827032068298,
      "grad_norm": 0.12150160223245621,
      "learning_rate": 9.549150281252633e-06,
      "loss": 0.1681,
      "step": 162
    },
    {
      "epoch": 0.04677523495229213,
      "grad_norm": 0.1218348816037178,
      "learning_rate": 9.068759265665384e-06,
      "loss": 0.1943,
      "step": 163
    },
    {
      "epoch": 0.04706219958390129,
      "grad_norm": 0.1285686194896698,
      "learning_rate": 8.599558442598998e-06,
      "loss": 0.193,
      "step": 164
    },
    {
      "epoch": 0.047349164215510435,
      "grad_norm": 0.13187286257743835,
      "learning_rate": 8.141676086873572e-06,
      "loss": 0.1827,
      "step": 165
    },
    {
      "epoch": 0.04763612884711959,
      "grad_norm": 0.11616555601358414,
      "learning_rate": 7.695237378953223e-06,
      "loss": 0.1633,
      "step": 166
    },
    {
      "epoch": 0.047923093478728744,
      "grad_norm": 0.1436556726694107,
      "learning_rate": 7.260364370723044e-06,
      "loss": 0.1938,
      "step": 167
    },
    {
      "epoch": 0.0482100581103379,
      "grad_norm": 0.1302369385957718,
      "learning_rate": 6.837175952121306e-06,
      "loss": 0.1852,
      "step": 168
    },
    {
      "epoch": 0.04849702274194705,
      "grad_norm": 0.13114623725414276,
      "learning_rate": 6.425787818636131e-06,
      "loss": 0.1828,
      "step": 169
    },
    {
      "epoch": 0.04878398737355621,
      "grad_norm": 0.13654778897762299,
      "learning_rate": 6.026312439675552e-06,
      "loss": 0.1765,
      "step": 170
    },
    {
      "epoch": 0.04907095200516536,
      "grad_norm": 0.15567849576473236,
      "learning_rate": 5.6388590278194096e-06,
      "loss": 0.183,
      "step": 171
    },
    {
      "epoch": 0.04935791663677452,
      "grad_norm": 0.1441982537508011,
      "learning_rate": 5.263533508961827e-06,
      "loss": 0.205,
      "step": 172
    },
    {
      "epoch": 0.04964488126838367,
      "grad_norm": 0.15008683502674103,
      "learning_rate": 4.900438493352055e-06,
      "loss": 0.1861,
      "step": 173
    },
    {
      "epoch": 0.049931845899992826,
      "grad_norm": 0.1488954722881317,
      "learning_rate": 4.549673247541875e-06,
      "loss": 0.1791,
      "step": 174
    },
    {
      "epoch": 0.05021881053160198,
      "grad_norm": 0.1452937126159668,
      "learning_rate": 4.2113336672471245e-06,
      "loss": 0.1832,
      "step": 175
    },
    {
      "epoch": 0.050505775163211135,
      "grad_norm": 0.16919949650764465,
      "learning_rate": 3.885512251130763e-06,
      "loss": 0.1958,
      "step": 176
    },
    {
      "epoch": 0.05079273979482029,
      "grad_norm": 0.18855352699756622,
      "learning_rate": 3.5722980755146517e-06,
      "loss": 0.2263,
      "step": 177
    },
    {
      "epoch": 0.051079704426429444,
      "grad_norm": 0.1491154134273529,
      "learning_rate": 3.271776770026963e-06,
      "loss": 0.1946,
      "step": 178
    },
    {
      "epoch": 0.0513666690580386,
      "grad_norm": 0.15859520435333252,
      "learning_rate": 2.9840304941919415e-06,
      "loss": 0.1861,
      "step": 179
    },
    {
      "epoch": 0.05165363368964775,
      "grad_norm": 0.14665690064430237,
      "learning_rate": 2.7091379149682685e-06,
      "loss": 0.1685,
      "step": 180
    },
    {
      "epoch": 0.05194059832125691,
      "grad_norm": 0.17621669173240662,
      "learning_rate": 2.4471741852423237e-06,
      "loss": 0.1423,
      "step": 181
    },
    {
      "epoch": 0.05222756295286606,
      "grad_norm": 0.15288934111595154,
      "learning_rate": 2.1982109232821178e-06,
      "loss": 0.1705,
      "step": 182
    },
    {
      "epoch": 0.05251452758447522,
      "grad_norm": 0.15100058913230896,
      "learning_rate": 1.962316193157593e-06,
      "loss": 0.1514,
      "step": 183
    },
    {
      "epoch": 0.052801492216084364,
      "grad_norm": 0.20457962155342102,
      "learning_rate": 1.7395544861325718e-06,
      "loss": 0.1273,
      "step": 184
    },
    {
      "epoch": 0.05308845684769352,
      "grad_norm": 0.22922560572624207,
      "learning_rate": 1.5299867030334814e-06,
      "loss": 0.0905,
      "step": 185
    },
    {
      "epoch": 0.05337542147930267,
      "grad_norm": 0.16776305437088013,
      "learning_rate": 1.333670137599713e-06,
      "loss": 0.1836,
      "step": 186
    },
    {
      "epoch": 0.05366238611091183,
      "grad_norm": 0.1918102651834488,
      "learning_rate": 1.1506584608200367e-06,
      "loss": 0.1751,
      "step": 187
    },
    {
      "epoch": 0.05394935074252098,
      "grad_norm": 0.2102634757757187,
      "learning_rate": 9.810017062595322e-07,
      "loss": 0.2,
      "step": 188
    },
    {
      "epoch": 0.05423631537413014,
      "grad_norm": 0.232077494263649,
      "learning_rate": 8.247462563808817e-07,
      "loss": 0.2066,
      "step": 189
    },
    {
      "epoch": 0.05452328000573929,
      "grad_norm": 0.2770179212093353,
      "learning_rate": 6.819348298638839e-07,
      "loss": 0.2033,
      "step": 190
    },
    {
      "epoch": 0.054810244637348446,
      "grad_norm": 0.22220300137996674,
      "learning_rate": 5.526064699265753e-07,
      "loss": 0.2033,
      "step": 191
    },
    {
      "epoch": 0.0550972092689576,
      "grad_norm": 0.23497681319713593,
      "learning_rate": 4.367965336512403e-07,
      "loss": 0.1519,
      "step": 192
    },
    {
      "epoch": 0.055384173900566755,
      "grad_norm": 0.21643763780593872,
      "learning_rate": 3.3453668231809286e-07,
      "loss": 0.1114,
      "step": 193
    },
    {
      "epoch": 0.05567113853217591,
      "grad_norm": 0.25806841254234314,
      "learning_rate": 2.458548727494292e-07,
      "loss": 0.1697,
      "step": 194
    },
    {
      "epoch": 0.055958103163785064,
      "grad_norm": 0.3005545735359192,
      "learning_rate": 1.7077534966650766e-07,
      "loss": 0.1833,
      "step": 195
    },
    {
      "epoch": 0.05624506779539422,
      "grad_norm": 0.3337264955043793,
      "learning_rate": 1.0931863906127327e-07,
      "loss": 0.2217,
      "step": 196
    },
    {
      "epoch": 0.05653203242700337,
      "grad_norm": 0.31904494762420654,
      "learning_rate": 6.150154258476315e-08,
      "loss": 0.1406,
      "step": 197
    },
    {
      "epoch": 0.05681899705861253,
      "grad_norm": 0.28676968812942505,
      "learning_rate": 2.7337132953697554e-08,
      "loss": 0.0613,
      "step": 198
    },
    {
      "epoch": 0.05710596169022168,
      "grad_norm": 0.33095583319664,
      "learning_rate": 6.834750376549792e-09,
      "loss": 0.1833,
      "step": 199
    },
    {
      "epoch": 0.05739292632183084,
      "grad_norm": 0.4375268816947937,
      "learning_rate": 0.0,
      "loss": 0.1523,
      "step": 200
    },
    {
      "epoch": 0.05739292632183084,
      "eval_loss": 0.18071845173835754,
      "eval_runtime": 708.8086,
      "eval_samples_per_second": 8.28,
      "eval_steps_per_second": 2.071,
      "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": 4.3951831168057344e+17,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}