{
  "best_metric": 0.8677911162376404,
  "best_model_checkpoint": "miner_id_24/checkpoint-200",
  "epoch": 0.9291521486643438,
  "eval_steps": 50,
  "global_step": 200,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.004645760743321719,
      "grad_norm": 0.12248758226633072,
      "learning_rate": 1e-05,
      "loss": 0.7942,
      "step": 1
    },
    {
      "epoch": 0.004645760743321719,
      "eval_loss": 0.9500295519828796,
      "eval_runtime": 34.7892,
      "eval_samples_per_second": 10.434,
      "eval_steps_per_second": 2.616,
      "step": 1
    },
    {
      "epoch": 0.009291521486643438,
      "grad_norm": 0.11588914692401886,
      "learning_rate": 2e-05,
      "loss": 0.8336,
      "step": 2
    },
    {
      "epoch": 0.013937282229965157,
      "grad_norm": 0.1286679357290268,
      "learning_rate": 3e-05,
      "loss": 0.8657,
      "step": 3
    },
    {
      "epoch": 0.018583042973286876,
      "grad_norm": 0.12290673702955246,
      "learning_rate": 4e-05,
      "loss": 0.8704,
      "step": 4
    },
    {
      "epoch": 0.023228803716608595,
      "grad_norm": 0.12627536058425903,
      "learning_rate": 5e-05,
      "loss": 0.8947,
      "step": 5
    },
    {
      "epoch": 0.027874564459930314,
      "grad_norm": 0.11196531355381012,
      "learning_rate": 6e-05,
      "loss": 0.796,
      "step": 6
    },
    {
      "epoch": 0.032520325203252036,
      "grad_norm": 0.11358628422021866,
      "learning_rate": 7e-05,
      "loss": 0.848,
      "step": 7
    },
    {
      "epoch": 0.03716608594657375,
      "grad_norm": 0.1119382381439209,
      "learning_rate": 8e-05,
      "loss": 0.8811,
      "step": 8
    },
    {
      "epoch": 0.041811846689895474,
      "grad_norm": 0.12059886753559113,
      "learning_rate": 9e-05,
      "loss": 0.9657,
      "step": 9
    },
    {
      "epoch": 0.04645760743321719,
      "grad_norm": 0.12331760674715042,
      "learning_rate": 0.0001,
      "loss": 0.8336,
      "step": 10
    },
    {
      "epoch": 0.05110336817653891,
      "grad_norm": 0.11843911558389664,
      "learning_rate": 9.999316524962345e-05,
      "loss": 0.8764,
      "step": 11
    },
    {
      "epoch": 0.05574912891986063,
      "grad_norm": 0.11719655245542526,
      "learning_rate": 9.997266286704631e-05,
      "loss": 0.8356,
      "step": 12
    },
    {
      "epoch": 0.06039488966318235,
      "grad_norm": 0.1061839684844017,
      "learning_rate": 9.993849845741524e-05,
      "loss": 0.7588,
      "step": 13
    },
    {
      "epoch": 0.06504065040650407,
      "grad_norm": 0.11150655150413513,
      "learning_rate": 9.989068136093873e-05,
      "loss": 0.8804,
      "step": 14
    },
    {
      "epoch": 0.06968641114982578,
      "grad_norm": 0.11808854341506958,
      "learning_rate": 9.98292246503335e-05,
      "loss": 0.9446,
      "step": 15
    },
    {
      "epoch": 0.0743321718931475,
      "grad_norm": 0.12123532593250275,
      "learning_rate": 9.975414512725057e-05,
      "loss": 0.8478,
      "step": 16
    },
    {
      "epoch": 0.07897793263646923,
      "grad_norm": 0.11964865773916245,
      "learning_rate": 9.966546331768191e-05,
      "loss": 0.8603,
      "step": 17
    },
    {
      "epoch": 0.08362369337979095,
      "grad_norm": 0.10562190413475037,
      "learning_rate": 9.956320346634876e-05,
      "loss": 0.8734,
      "step": 18
    },
    {
      "epoch": 0.08826945412311266,
      "grad_norm": 0.10028873383998871,
      "learning_rate": 9.944739353007344e-05,
      "loss": 0.7716,
      "step": 19
    },
    {
      "epoch": 0.09291521486643438,
      "grad_norm": 0.11776239424943924,
      "learning_rate": 9.931806517013612e-05,
      "loss": 0.8745,
      "step": 20
    },
    {
      "epoch": 0.0975609756097561,
      "grad_norm": 0.12444399297237396,
      "learning_rate": 9.917525374361912e-05,
      "loss": 0.954,
      "step": 21
    },
    {
      "epoch": 0.10220673635307782,
      "grad_norm": 0.12520965933799744,
      "learning_rate": 9.901899829374047e-05,
      "loss": 0.8432,
      "step": 22
    },
    {
      "epoch": 0.10685249709639953,
      "grad_norm": 0.13316883146762848,
      "learning_rate": 9.884934153917997e-05,
      "loss": 0.8304,
      "step": 23
    },
    {
      "epoch": 0.11149825783972125,
      "grad_norm": 0.14664626121520996,
      "learning_rate": 9.86663298624003e-05,
      "loss": 0.7786,
      "step": 24
    },
    {
      "epoch": 0.11614401858304298,
      "grad_norm": 0.14996041357517242,
      "learning_rate": 9.847001329696653e-05,
      "loss": 0.7468,
      "step": 25
    },
    {
      "epoch": 0.1207897793263647,
      "grad_norm": 0.14190909266471863,
      "learning_rate": 9.826044551386744e-05,
      "loss": 0.711,
      "step": 26
    },
    {
      "epoch": 0.1254355400696864,
      "grad_norm": 0.1657562106847763,
      "learning_rate": 9.803768380684242e-05,
      "loss": 0.8648,
      "step": 27
    },
    {
      "epoch": 0.13008130081300814,
      "grad_norm": 0.14185082912445068,
      "learning_rate": 9.780178907671789e-05,
      "loss": 0.7591,
      "step": 28
    },
    {
      "epoch": 0.13472706155632985,
      "grad_norm": 0.1636614352464676,
      "learning_rate": 9.755282581475769e-05,
      "loss": 0.8205,
      "step": 29
    },
    {
      "epoch": 0.13937282229965156,
      "grad_norm": 0.1705957055091858,
      "learning_rate": 9.729086208503174e-05,
      "loss": 0.8165,
      "step": 30
    },
    {
      "epoch": 0.1440185830429733,
      "grad_norm": 0.16744568943977356,
      "learning_rate": 9.701596950580806e-05,
      "loss": 0.8324,
      "step": 31
    },
    {
      "epoch": 0.148664343786295,
      "grad_norm": 0.17183375358581543,
      "learning_rate": 9.672822322997305e-05,
      "loss": 0.7845,
      "step": 32
    },
    {
      "epoch": 0.15331010452961671,
      "grad_norm": 0.19279760122299194,
      "learning_rate": 9.642770192448536e-05,
      "loss": 0.7747,
      "step": 33
    },
    {
      "epoch": 0.15795586527293845,
      "grad_norm": 0.18345697224140167,
      "learning_rate": 9.611448774886924e-05,
      "loss": 0.8358,
      "step": 34
    },
    {
      "epoch": 0.16260162601626016,
      "grad_norm": 0.19526341557502747,
      "learning_rate": 9.578866633275288e-05,
      "loss": 0.9509,
      "step": 35
    },
    {
      "epoch": 0.1672473867595819,
      "grad_norm": 0.19021165370941162,
      "learning_rate": 9.545032675245813e-05,
      "loss": 0.8134,
      "step": 36
    },
    {
      "epoch": 0.1718931475029036,
      "grad_norm": 0.20221421122550964,
      "learning_rate": 9.509956150664796e-05,
      "loss": 0.7797,
      "step": 37
    },
    {
      "epoch": 0.1765389082462253,
      "grad_norm": 0.22488248348236084,
      "learning_rate": 9.473646649103818e-05,
      "loss": 0.7188,
      "step": 38
    },
    {
      "epoch": 0.18118466898954705,
      "grad_norm": 0.2047199159860611,
      "learning_rate": 9.43611409721806e-05,
      "loss": 0.8951,
      "step": 39
    },
    {
      "epoch": 0.18583042973286876,
      "grad_norm": 0.21489404141902924,
      "learning_rate": 9.397368756032445e-05,
      "loss": 0.8818,
      "step": 40
    },
    {
      "epoch": 0.19047619047619047,
      "grad_norm": 0.24582022428512573,
      "learning_rate": 9.357421218136386e-05,
      "loss": 1.0106,
      "step": 41
    },
    {
      "epoch": 0.1951219512195122,
      "grad_norm": 0.23751594126224518,
      "learning_rate": 9.316282404787871e-05,
      "loss": 0.9811,
      "step": 42
    },
    {
      "epoch": 0.1997677119628339,
      "grad_norm": 0.27702727913856506,
      "learning_rate": 9.273963562927695e-05,
      "loss": 0.9305,
      "step": 43
    },
    {
      "epoch": 0.20441347270615565,
      "grad_norm": 0.26859357953071594,
      "learning_rate": 9.230476262104677e-05,
      "loss": 0.9204,
      "step": 44
    },
    {
      "epoch": 0.20905923344947736,
      "grad_norm": 0.27607783675193787,
      "learning_rate": 9.185832391312644e-05,
      "loss": 0.9933,
      "step": 45
    },
    {
      "epoch": 0.21370499419279906,
      "grad_norm": 0.342403382062912,
      "learning_rate": 9.140044155740101e-05,
      "loss": 0.9606,
      "step": 46
    },
    {
      "epoch": 0.2183507549361208,
      "grad_norm": 0.36429300904273987,
      "learning_rate": 9.093124073433463e-05,
      "loss": 1.1438,
      "step": 47
    },
    {
      "epoch": 0.2229965156794425,
      "grad_norm": 0.4303102195262909,
      "learning_rate": 9.045084971874738e-05,
      "loss": 1.1657,
      "step": 48
    },
    {
      "epoch": 0.22764227642276422,
      "grad_norm": 0.5270444750785828,
      "learning_rate": 8.995939984474624e-05,
      "loss": 1.1606,
      "step": 49
    },
    {
      "epoch": 0.23228803716608595,
      "grad_norm": 0.8345721960067749,
      "learning_rate": 8.945702546981969e-05,
      "loss": 1.4175,
      "step": 50
    },
    {
      "epoch": 0.23228803716608595,
      "eval_loss": 0.8853886127471924,
      "eval_runtime": 35.1825,
      "eval_samples_per_second": 10.318,
      "eval_steps_per_second": 2.587,
      "step": 50
    },
    {
      "epoch": 0.23693379790940766,
      "grad_norm": 0.14753635227680206,
      "learning_rate": 8.894386393810563e-05,
      "loss": 0.958,
      "step": 51
    },
    {
      "epoch": 0.2415795586527294,
      "grad_norm": 0.13887369632720947,
      "learning_rate": 8.842005554284296e-05,
      "loss": 0.653,
      "step": 52
    },
    {
      "epoch": 0.2462253193960511,
      "grad_norm": 0.1636919528245926,
      "learning_rate": 8.788574348801675e-05,
      "loss": 0.8807,
      "step": 53
    },
    {
      "epoch": 0.2508710801393728,
      "grad_norm": 0.14415013790130615,
      "learning_rate": 8.73410738492077e-05,
      "loss": 0.846,
      "step": 54
    },
    {
      "epoch": 0.25551684088269455,
      "grad_norm": 0.1366504728794098,
      "learning_rate": 8.678619553365659e-05,
      "loss": 0.6806,
      "step": 55
    },
    {
      "epoch": 0.2601626016260163,
      "grad_norm": 0.11705049127340317,
      "learning_rate": 8.622126023955446e-05,
      "loss": 0.7397,
      "step": 56
    },
    {
      "epoch": 0.26480836236933797,
      "grad_norm": 0.12336675822734833,
      "learning_rate": 8.564642241456986e-05,
      "loss": 0.7548,
      "step": 57
    },
    {
      "epoch": 0.2694541231126597,
      "grad_norm": 0.12091846764087677,
      "learning_rate": 8.506183921362443e-05,
      "loss": 0.9128,
      "step": 58
    },
    {
      "epoch": 0.27409988385598144,
      "grad_norm": 0.11321322619915009,
      "learning_rate": 8.44676704559283e-05,
      "loss": 0.8901,
      "step": 59
    },
    {
      "epoch": 0.2787456445993031,
      "grad_norm": 0.11016193777322769,
      "learning_rate": 8.386407858128706e-05,
      "loss": 0.9241,
      "step": 60
    },
    {
      "epoch": 0.28339140534262486,
      "grad_norm": 0.10698598623275757,
      "learning_rate": 8.32512286056924e-05,
      "loss": 0.8907,
      "step": 61
    },
    {
      "epoch": 0.2880371660859466,
      "grad_norm": 0.10707106441259384,
      "learning_rate": 8.262928807620843e-05,
      "loss": 0.8498,
      "step": 62
    },
    {
      "epoch": 0.2926829268292683,
      "grad_norm": 0.11155840009450912,
      "learning_rate": 8.199842702516583e-05,
      "loss": 0.7976,
      "step": 63
    },
    {
      "epoch": 0.29732868757259,
      "grad_norm": 0.10202828049659729,
      "learning_rate": 8.135881792367686e-05,
      "loss": 0.8585,
      "step": 64
    },
    {
      "epoch": 0.30197444831591175,
      "grad_norm": 0.11714151501655579,
      "learning_rate": 8.07106356344834e-05,
      "loss": 0.817,
      "step": 65
    },
    {
      "epoch": 0.30662020905923343,
      "grad_norm": 0.10279451310634613,
      "learning_rate": 8.005405736415126e-05,
      "loss": 0.7803,
      "step": 66
    },
    {
      "epoch": 0.31126596980255516,
      "grad_norm": 0.10880623757839203,
      "learning_rate": 7.938926261462366e-05,
      "loss": 0.8819,
      "step": 67
    },
    {
      "epoch": 0.3159117305458769,
      "grad_norm": 0.10310228914022446,
      "learning_rate": 7.871643313414718e-05,
      "loss": 0.7834,
      "step": 68
    },
    {
      "epoch": 0.3205574912891986,
      "grad_norm": 0.1109737902879715,
      "learning_rate": 7.803575286758364e-05,
      "loss": 0.7166,
      "step": 69
    },
    {
      "epoch": 0.3252032520325203,
      "grad_norm": 0.11841745674610138,
      "learning_rate": 7.734740790612136e-05,
      "loss": 0.7829,
      "step": 70
    },
    {
      "epoch": 0.32984901277584205,
      "grad_norm": 0.1297767162322998,
      "learning_rate": 7.66515864363997e-05,
      "loss": 0.7764,
      "step": 71
    },
    {
      "epoch": 0.3344947735191638,
      "grad_norm": 0.1227758377790451,
      "learning_rate": 7.594847868906076e-05,
      "loss": 0.707,
      "step": 72
    },
    {
      "epoch": 0.33914053426248547,
      "grad_norm": 0.13544820249080658,
      "learning_rate": 7.52382768867422e-05,
      "loss": 0.8454,
      "step": 73
    },
    {
      "epoch": 0.3437862950058072,
      "grad_norm": 0.1268458068370819,
      "learning_rate": 7.452117519152542e-05,
      "loss": 0.7319,
      "step": 74
    },
    {
      "epoch": 0.34843205574912894,
      "grad_norm": 0.13013871014118195,
      "learning_rate": 7.379736965185368e-05,
      "loss": 0.7981,
      "step": 75
    },
    {
      "epoch": 0.3530778164924506,
      "grad_norm": 0.1546456515789032,
      "learning_rate": 7.30670581489344e-05,
      "loss": 0.7556,
      "step": 76
    },
    {
      "epoch": 0.35772357723577236,
      "grad_norm": 0.14676199853420258,
      "learning_rate": 7.233044034264034e-05,
      "loss": 0.7872,
      "step": 77
    },
    {
      "epoch": 0.3623693379790941,
      "grad_norm": 0.14500990509986877,
      "learning_rate": 7.158771761692464e-05,
      "loss": 0.9039,
      "step": 78
    },
    {
      "epoch": 0.3670150987224158,
      "grad_norm": 0.1635589599609375,
      "learning_rate": 7.083909302476453e-05,
      "loss": 0.7036,
      "step": 79
    },
    {
      "epoch": 0.3716608594657375,
      "grad_norm": 0.16299131512641907,
      "learning_rate": 7.008477123264848e-05,
      "loss": 0.8043,
      "step": 80
    },
    {
      "epoch": 0.37630662020905925,
      "grad_norm": 0.1477063000202179,
      "learning_rate": 6.932495846462261e-05,
      "loss": 0.7513,
      "step": 81
    },
    {
      "epoch": 0.38095238095238093,
      "grad_norm": 0.17232096195220947,
      "learning_rate": 6.855986244591104e-05,
      "loss": 0.7715,
      "step": 82
    },
    {
      "epoch": 0.38559814169570267,
      "grad_norm": 0.17469638586044312,
      "learning_rate": 6.778969234612584e-05,
      "loss": 0.9285,
      "step": 83
    },
    {
      "epoch": 0.3902439024390244,
      "grad_norm": 0.16923201084136963,
      "learning_rate": 6.701465872208216e-05,
      "loss": 0.7327,
      "step": 84
    },
    {
      "epoch": 0.3948896631823461,
      "grad_norm": 0.1980726420879364,
      "learning_rate": 6.623497346023418e-05,
      "loss": 0.7601,
      "step": 85
    },
    {
      "epoch": 0.3995354239256678,
      "grad_norm": 0.20499838888645172,
      "learning_rate": 6.545084971874738e-05,
      "loss": 0.9292,
      "step": 86
    },
    {
      "epoch": 0.40418118466898956,
      "grad_norm": 0.2034449428319931,
      "learning_rate": 6.466250186922325e-05,
      "loss": 0.9332,
      "step": 87
    },
    {
      "epoch": 0.4088269454123113,
      "grad_norm": 0.22591711580753326,
      "learning_rate": 6.387014543809223e-05,
      "loss": 1.0875,
      "step": 88
    },
    {
      "epoch": 0.413472706155633,
      "grad_norm": 0.2202339917421341,
      "learning_rate": 6.307399704769099e-05,
      "loss": 0.8283,
      "step": 89
    },
    {
      "epoch": 0.4181184668989547,
      "grad_norm": 0.2351447194814682,
      "learning_rate": 6.227427435703997e-05,
      "loss": 0.8803,
      "step": 90
    },
    {
      "epoch": 0.42276422764227645,
      "grad_norm": 0.22027833759784698,
      "learning_rate": 6.147119600233758e-05,
      "loss": 0.9161,
      "step": 91
    },
    {
      "epoch": 0.4274099883855981,
      "grad_norm": 0.2328965663909912,
      "learning_rate": 6.066498153718735e-05,
      "loss": 0.8979,
      "step": 92
    },
    {
      "epoch": 0.43205574912891986,
      "grad_norm": 0.26121312379837036,
      "learning_rate": 5.985585137257401e-05,
      "loss": 0.9793,
      "step": 93
    },
    {
      "epoch": 0.4367015098722416,
      "grad_norm": 0.28046953678131104,
      "learning_rate": 5.90440267166055e-05,
      "loss": 1.0957,
      "step": 94
    },
    {
      "epoch": 0.4413472706155633,
      "grad_norm": 0.285359650850296,
      "learning_rate": 5.8229729514036705e-05,
      "loss": 1.0233,
      "step": 95
    },
    {
      "epoch": 0.445993031358885,
      "grad_norm": 0.28869330883026123,
      "learning_rate": 5.74131823855921e-05,
      "loss": 1.0457,
      "step": 96
    },
    {
      "epoch": 0.45063879210220675,
      "grad_norm": 0.3298930823802948,
      "learning_rate": 5.6594608567103456e-05,
      "loss": 1.1204,
      "step": 97
    },
    {
      "epoch": 0.45528455284552843,
      "grad_norm": 0.3415940999984741,
      "learning_rate": 5.577423184847932e-05,
      "loss": 1.0313,
      "step": 98
    },
    {
      "epoch": 0.45993031358885017,
      "grad_norm": 0.6324352025985718,
      "learning_rate": 5.495227651252315e-05,
      "loss": 1.2237,
      "step": 99
    },
    {
      "epoch": 0.4645760743321719,
      "grad_norm": 0.7398970723152161,
      "learning_rate": 5.4128967273616625e-05,
      "loss": 1.2192,
      "step": 100
    },
    {
      "epoch": 0.4645760743321719,
      "eval_loss": 0.871712327003479,
      "eval_runtime": 35.4234,
      "eval_samples_per_second": 10.247,
      "eval_steps_per_second": 2.569,
      "step": 100
    },
    {
      "epoch": 0.4692218350754936,
      "grad_norm": 0.11145634204149246,
      "learning_rate": 5.330452921628497e-05,
      "loss": 0.7969,
      "step": 101
    },
    {
      "epoch": 0.4738675958188153,
      "grad_norm": 0.12094812095165253,
      "learning_rate": 5.247918773366112e-05,
      "loss": 0.8162,
      "step": 102
    },
    {
      "epoch": 0.47851335656213706,
      "grad_norm": 0.12575285136699677,
      "learning_rate": 5.165316846586541e-05,
      "loss": 0.9359,
      "step": 103
    },
    {
      "epoch": 0.4831591173054588,
      "grad_norm": 0.1298871636390686,
      "learning_rate": 5.0826697238317935e-05,
      "loss": 0.8214,
      "step": 104
    },
    {
      "epoch": 0.4878048780487805,
      "grad_norm": 0.1339699625968933,
      "learning_rate": 5e-05,
      "loss": 0.9323,
      "step": 105
    },
    {
      "epoch": 0.4924506387921022,
      "grad_norm": 0.11761663109064102,
      "learning_rate": 4.917330276168208e-05,
      "loss": 0.748,
      "step": 106
    },
    {
      "epoch": 0.49709639953542395,
      "grad_norm": 0.11723273247480392,
      "learning_rate": 4.834683153413459e-05,
      "loss": 0.83,
      "step": 107
    },
    {
      "epoch": 0.5017421602787456,
      "grad_norm": 0.10937295109033585,
      "learning_rate": 4.7520812266338885e-05,
      "loss": 0.869,
      "step": 108
    },
    {
      "epoch": 0.5063879210220673,
      "grad_norm": 0.11733722686767578,
      "learning_rate": 4.669547078371504e-05,
      "loss": 0.8163,
      "step": 109
    },
    {
      "epoch": 0.5110336817653891,
      "grad_norm": 0.11457250267267227,
      "learning_rate": 4.5871032726383386e-05,
      "loss": 0.8858,
      "step": 110
    },
    {
      "epoch": 0.5156794425087108,
      "grad_norm": 0.11726170033216476,
      "learning_rate": 4.504772348747687e-05,
      "loss": 0.9477,
      "step": 111
    },
    {
      "epoch": 0.5203252032520326,
      "grad_norm": 0.10370782017707825,
      "learning_rate": 4.4225768151520694e-05,
      "loss": 0.8283,
      "step": 112
    },
    {
      "epoch": 0.5249709639953543,
      "grad_norm": 0.11202286928892136,
      "learning_rate": 4.3405391432896555e-05,
      "loss": 0.888,
      "step": 113
    },
    {
      "epoch": 0.5296167247386759,
      "grad_norm": 0.11793085932731628,
      "learning_rate": 4.2586817614407895e-05,
      "loss": 0.8826,
      "step": 114
    },
    {
      "epoch": 0.5342624854819977,
      "grad_norm": 0.10904623568058014,
      "learning_rate": 4.17702704859633e-05,
      "loss": 0.8906,
      "step": 115
    },
    {
      "epoch": 0.5389082462253194,
      "grad_norm": 0.10171744227409363,
      "learning_rate": 4.095597328339452e-05,
      "loss": 0.7867,
      "step": 116
    },
    {
      "epoch": 0.5435540069686411,
      "grad_norm": 0.10408619046211243,
      "learning_rate": 4.0144148627425993e-05,
      "loss": 0.9097,
      "step": 117
    },
    {
      "epoch": 0.5481997677119629,
      "grad_norm": 0.1031450629234314,
      "learning_rate": 3.933501846281267e-05,
      "loss": 0.8447,
      "step": 118
    },
    {
      "epoch": 0.5528455284552846,
      "grad_norm": 0.11930621415376663,
      "learning_rate": 3.852880399766243e-05,
      "loss": 0.8626,
      "step": 119
    },
    {
      "epoch": 0.5574912891986062,
      "grad_norm": 0.1154748946428299,
      "learning_rate": 3.772572564296005e-05,
      "loss": 0.8797,
      "step": 120
    },
    {
      "epoch": 0.562137049941928,
      "grad_norm": 0.10599689930677414,
      "learning_rate": 3.6926002952309016e-05,
      "loss": 0.6912,
      "step": 121
    },
    {
      "epoch": 0.5667828106852497,
      "grad_norm": 0.10911935567855835,
      "learning_rate": 3.612985456190778e-05,
      "loss": 0.6975,
      "step": 122
    },
    {
      "epoch": 0.5714285714285714,
      "grad_norm": 0.12081928551197052,
      "learning_rate": 3.533749813077677e-05,
      "loss": 0.8419,
      "step": 123
    },
    {
      "epoch": 0.5760743321718932,
      "grad_norm": 0.13225339353084564,
      "learning_rate": 3.4549150281252636e-05,
      "loss": 0.7519,
      "step": 124
    },
    {
      "epoch": 0.5807200929152149,
      "grad_norm": 0.12407319992780685,
      "learning_rate": 3.3765026539765834e-05,
      "loss": 0.8843,
      "step": 125
    },
    {
      "epoch": 0.5853658536585366,
      "grad_norm": 0.14300796389579773,
      "learning_rate": 3.298534127791785e-05,
      "loss": 0.7694,
      "step": 126
    },
    {
      "epoch": 0.5900116144018583,
      "grad_norm": 0.15102261304855347,
      "learning_rate": 3.221030765387417e-05,
      "loss": 0.8374,
      "step": 127
    },
    {
      "epoch": 0.59465737514518,
      "grad_norm": 0.15869556367397308,
      "learning_rate": 3.144013755408895e-05,
      "loss": 0.7161,
      "step": 128
    },
    {
      "epoch": 0.5993031358885017,
      "grad_norm": 0.14537778496742249,
      "learning_rate": 3.0675041535377405e-05,
      "loss": 0.7727,
      "step": 129
    },
    {
      "epoch": 0.6039488966318235,
      "grad_norm": 0.15524469316005707,
      "learning_rate": 2.991522876735154e-05,
      "loss": 0.8891,
      "step": 130
    },
    {
      "epoch": 0.6085946573751452,
      "grad_norm": 0.15899863839149475,
      "learning_rate": 2.916090697523549e-05,
      "loss": 0.6929,
      "step": 131
    },
    {
      "epoch": 0.6132404181184669,
      "grad_norm": 0.1513189971446991,
      "learning_rate": 2.8412282383075363e-05,
      "loss": 0.7647,
      "step": 132
    },
    {
      "epoch": 0.6178861788617886,
      "grad_norm": 0.16603240370750427,
      "learning_rate": 2.766955965735968e-05,
      "loss": 0.7718,
      "step": 133
    },
    {
      "epoch": 0.6225319396051103,
      "grad_norm": 0.18982014060020447,
      "learning_rate": 2.693294185106562e-05,
      "loss": 1.0007,
      "step": 134
    },
    {
      "epoch": 0.627177700348432,
      "grad_norm": 0.15879637002944946,
      "learning_rate": 2.6202630348146324e-05,
      "loss": 0.8562,
      "step": 135
    },
    {
      "epoch": 0.6318234610917538,
      "grad_norm": 0.1893901377916336,
      "learning_rate": 2.547882480847461e-05,
      "loss": 0.7898,
      "step": 136
    },
    {
      "epoch": 0.6364692218350755,
      "grad_norm": 0.19009214639663696,
      "learning_rate": 2.476172311325783e-05,
      "loss": 0.8707,
      "step": 137
    },
    {
      "epoch": 0.6411149825783972,
      "grad_norm": 0.18650825321674347,
      "learning_rate": 2.405152131093926e-05,
      "loss": 0.9732,
      "step": 138
    },
    {
      "epoch": 0.645760743321719,
      "grad_norm": 0.19181600213050842,
      "learning_rate": 2.3348413563600325e-05,
      "loss": 0.7562,
      "step": 139
    },
    {
      "epoch": 0.6504065040650406,
      "grad_norm": 0.22567430138587952,
      "learning_rate": 2.2652592093878666e-05,
      "loss": 0.8456,
      "step": 140
    },
    {
      "epoch": 0.6550522648083623,
      "grad_norm": 0.2378416806459427,
      "learning_rate": 2.196424713241637e-05,
      "loss": 0.8294,
      "step": 141
    },
    {
      "epoch": 0.6596980255516841,
      "grad_norm": 0.238148033618927,
      "learning_rate": 2.128356686585282e-05,
      "loss": 0.9285,
      "step": 142
    },
    {
      "epoch": 0.6643437862950058,
      "grad_norm": 0.2520192861557007,
      "learning_rate": 2.061073738537635e-05,
      "loss": 0.891,
      "step": 143
    },
    {
      "epoch": 0.6689895470383276,
      "grad_norm": 0.2329062968492508,
      "learning_rate": 1.9945942635848748e-05,
      "loss": 0.8908,
      "step": 144
    },
    {
      "epoch": 0.6736353077816493,
      "grad_norm": 0.33517736196517944,
      "learning_rate": 1.928936436551661e-05,
      "loss": 1.1426,
      "step": 145
    },
    {
      "epoch": 0.6782810685249709,
      "grad_norm": 0.2958681881427765,
      "learning_rate": 1.8641182076323148e-05,
      "loss": 1.0457,
      "step": 146
    },
    {
      "epoch": 0.6829268292682927,
      "grad_norm": 0.31920844316482544,
      "learning_rate": 1.800157297483417e-05,
      "loss": 1.1051,
      "step": 147
    },
    {
      "epoch": 0.6875725900116144,
      "grad_norm": 0.44857126474380493,
      "learning_rate": 1.7370711923791567e-05,
      "loss": 0.978,
      "step": 148
    },
    {
      "epoch": 0.6922183507549361,
      "grad_norm": 0.39416614174842834,
      "learning_rate": 1.6748771394307585e-05,
      "loss": 1.1277,
      "step": 149
    },
    {
      "epoch": 0.6968641114982579,
      "grad_norm": 0.7254365086555481,
      "learning_rate": 1.6135921418712956e-05,
      "loss": 1.3075,
      "step": 150
    },
    {
      "epoch": 0.6968641114982579,
      "eval_loss": 0.8703346848487854,
      "eval_runtime": 35.163,
      "eval_samples_per_second": 10.323,
      "eval_steps_per_second": 2.588,
      "step": 150
    },
    {
      "epoch": 0.7015098722415796,
      "grad_norm": 0.09920774400234222,
      "learning_rate": 1.553232954407171e-05,
      "loss": 0.7414,
      "step": 151
    },
    {
      "epoch": 0.7061556329849012,
      "grad_norm": 0.10195594280958176,
      "learning_rate": 1.4938160786375572e-05,
      "loss": 0.6654,
      "step": 152
    },
    {
      "epoch": 0.710801393728223,
      "grad_norm": 0.09995036572217941,
      "learning_rate": 1.435357758543015e-05,
      "loss": 0.6587,
      "step": 153
    },
    {
      "epoch": 0.7154471544715447,
      "grad_norm": 0.110610730946064,
      "learning_rate": 1.3778739760445552e-05,
      "loss": 0.87,
      "step": 154
    },
    {
      "epoch": 0.7200929152148664,
      "grad_norm": 0.1068836972117424,
      "learning_rate": 1.3213804466343421e-05,
      "loss": 0.7795,
      "step": 155
    },
    {
      "epoch": 0.7247386759581882,
      "grad_norm": 0.10642016679048538,
      "learning_rate": 1.2658926150792322e-05,
      "loss": 0.8141,
      "step": 156
    },
    {
      "epoch": 0.7293844367015099,
      "grad_norm": 0.1015360951423645,
      "learning_rate": 1.2114256511983274e-05,
      "loss": 0.8231,
      "step": 157
    },
    {
      "epoch": 0.7340301974448316,
      "grad_norm": 0.10452908277511597,
      "learning_rate": 1.157994445715706e-05,
      "loss": 0.7661,
      "step": 158
    },
    {
      "epoch": 0.7386759581881533,
      "grad_norm": 0.10662119835615158,
      "learning_rate": 1.1056136061894384e-05,
      "loss": 0.9089,
      "step": 159
    },
    {
      "epoch": 0.743321718931475,
      "grad_norm": 0.09893326461315155,
      "learning_rate": 1.0542974530180327e-05,
      "loss": 0.9098,
      "step": 160
    },
    {
      "epoch": 0.7479674796747967,
      "grad_norm": 0.1019243448972702,
      "learning_rate": 1.0040600155253765e-05,
      "loss": 0.8816,
      "step": 161
    },
    {
      "epoch": 0.7526132404181185,
      "grad_norm": 0.10434772074222565,
      "learning_rate": 9.549150281252633e-06,
      "loss": 0.9843,
      "step": 162
    },
    {
      "epoch": 0.7572590011614402,
      "grad_norm": 0.10745610296726227,
      "learning_rate": 9.068759265665384e-06,
      "loss": 0.8181,
      "step": 163
    },
    {
      "epoch": 0.7619047619047619,
      "grad_norm": 0.10147396475076675,
      "learning_rate": 8.599558442598998e-06,
      "loss": 0.8781,
      "step": 164
    },
    {
      "epoch": 0.7665505226480837,
      "grad_norm": 0.10110560804605484,
      "learning_rate": 8.141676086873572e-06,
      "loss": 0.7941,
      "step": 165
    },
    {
      "epoch": 0.7711962833914053,
      "grad_norm": 0.1035153791308403,
      "learning_rate": 7.695237378953223e-06,
      "loss": 0.8485,
      "step": 166
    },
    {
      "epoch": 0.775842044134727,
      "grad_norm": 0.10403966903686523,
      "learning_rate": 7.260364370723044e-06,
      "loss": 0.9418,
      "step": 167
    },
    {
      "epoch": 0.7804878048780488,
      "grad_norm": 0.11510627716779709,
      "learning_rate": 6.837175952121306e-06,
      "loss": 0.8597,
      "step": 168
    },
    {
      "epoch": 0.7851335656213705,
      "grad_norm": 0.1006569191813469,
      "learning_rate": 6.425787818636131e-06,
      "loss": 0.6556,
      "step": 169
    },
    {
      "epoch": 0.7897793263646922,
      "grad_norm": 0.12186460196971893,
      "learning_rate": 6.026312439675552e-06,
      "loss": 0.8747,
      "step": 170
    },
    {
      "epoch": 0.794425087108014,
      "grad_norm": 0.11013081669807434,
      "learning_rate": 5.6388590278194096e-06,
      "loss": 0.84,
      "step": 171
    },
    {
      "epoch": 0.7990708478513356,
      "grad_norm": 0.19421261548995972,
      "learning_rate": 5.263533508961827e-06,
      "loss": 0.6677,
      "step": 172
    },
    {
      "epoch": 0.8037166085946573,
      "grad_norm": 0.12273123115301132,
      "learning_rate": 4.900438493352055e-06,
      "loss": 0.7794,
      "step": 173
    },
    {
      "epoch": 0.8083623693379791,
      "grad_norm": 0.1216207817196846,
      "learning_rate": 4.549673247541875e-06,
      "loss": 0.7554,
      "step": 174
    },
    {
      "epoch": 0.8130081300813008,
      "grad_norm": 0.1327364295721054,
      "learning_rate": 4.2113336672471245e-06,
      "loss": 0.762,
      "step": 175
    },
    {
      "epoch": 0.8176538908246226,
      "grad_norm": 0.1243305653333664,
      "learning_rate": 3.885512251130763e-06,
      "loss": 0.6187,
      "step": 176
    },
    {
      "epoch": 0.8222996515679443,
      "grad_norm": 0.14136387407779694,
      "learning_rate": 3.5722980755146517e-06,
      "loss": 0.6697,
      "step": 177
    },
    {
      "epoch": 0.826945412311266,
      "grad_norm": 0.15945646166801453,
      "learning_rate": 3.271776770026963e-06,
      "loss": 0.8131,
      "step": 178
    },
    {
      "epoch": 0.8315911730545877,
      "grad_norm": 0.1525261551141739,
      "learning_rate": 2.9840304941919415e-06,
      "loss": 0.7759,
      "step": 179
    },
    {
      "epoch": 0.8362369337979094,
      "grad_norm": 0.1584528386592865,
      "learning_rate": 2.7091379149682685e-06,
      "loss": 0.718,
      "step": 180
    },
    {
      "epoch": 0.8408826945412311,
      "grad_norm": 0.1641009896993637,
      "learning_rate": 2.4471741852423237e-06,
      "loss": 0.7943,
      "step": 181
    },
    {
      "epoch": 0.8455284552845529,
      "grad_norm": 0.17796602845191956,
      "learning_rate": 2.1982109232821178e-06,
      "loss": 0.8005,
      "step": 182
    },
    {
      "epoch": 0.8501742160278746,
      "grad_norm": 0.16884498298168182,
      "learning_rate": 1.962316193157593e-06,
      "loss": 0.9923,
      "step": 183
    },
    {
      "epoch": 0.8548199767711963,
      "grad_norm": 0.17720551788806915,
      "learning_rate": 1.7395544861325718e-06,
      "loss": 0.6913,
      "step": 184
    },
    {
      "epoch": 0.859465737514518,
      "grad_norm": 0.1785539835691452,
      "learning_rate": 1.5299867030334814e-06,
      "loss": 0.6999,
      "step": 185
    },
    {
      "epoch": 0.8641114982578397,
      "grad_norm": 0.18429091572761536,
      "learning_rate": 1.333670137599713e-06,
      "loss": 0.8961,
      "step": 186
    },
    {
      "epoch": 0.8687572590011614,
      "grad_norm": 0.20377536118030548,
      "learning_rate": 1.1506584608200367e-06,
      "loss": 0.829,
      "step": 187
    },
    {
      "epoch": 0.8734030197444832,
      "grad_norm": 0.19523970782756805,
      "learning_rate": 9.810017062595322e-07,
      "loss": 0.9514,
      "step": 188
    },
    {
      "epoch": 0.8780487804878049,
      "grad_norm": 0.20550040900707245,
      "learning_rate": 8.247462563808817e-07,
      "loss": 0.8534,
      "step": 189
    },
    {
      "epoch": 0.8826945412311266,
      "grad_norm": 0.24723635613918304,
      "learning_rate": 6.819348298638839e-07,
      "loss": 1.0393,
      "step": 190
    },
    {
      "epoch": 0.8873403019744484,
      "grad_norm": 0.2195415198802948,
      "learning_rate": 5.526064699265753e-07,
      "loss": 0.8628,
      "step": 191
    },
    {
      "epoch": 0.89198606271777,
      "grad_norm": 0.23869915306568146,
      "learning_rate": 4.367965336512403e-07,
      "loss": 0.9591,
      "step": 192
    },
    {
      "epoch": 0.8966318234610917,
      "grad_norm": 0.26264917850494385,
      "learning_rate": 3.3453668231809286e-07,
      "loss": 1.0685,
      "step": 193
    },
    {
      "epoch": 0.9012775842044135,
      "grad_norm": 0.2624903619289398,
      "learning_rate": 2.458548727494292e-07,
      "loss": 1.0451,
      "step": 194
    },
    {
      "epoch": 0.9059233449477352,
      "grad_norm": 0.26787304878234863,
      "learning_rate": 1.7077534966650766e-07,
      "loss": 0.9713,
      "step": 195
    },
    {
      "epoch": 0.9105691056910569,
      "grad_norm": 0.3720742464065552,
      "learning_rate": 1.0931863906127327e-07,
      "loss": 1.0691,
      "step": 196
    },
    {
      "epoch": 0.9152148664343787,
      "grad_norm": 0.29646360874176025,
      "learning_rate": 6.150154258476315e-08,
      "loss": 1.102,
      "step": 197
    },
    {
      "epoch": 0.9198606271777003,
      "grad_norm": 0.42121291160583496,
      "learning_rate": 2.7337132953697554e-08,
      "loss": 1.0281,
      "step": 198
    },
    {
      "epoch": 0.924506387921022,
      "grad_norm": 0.43570250272750854,
      "learning_rate": 6.834750376549792e-09,
      "loss": 1.0586,
      "step": 199
    },
    {
      "epoch": 0.9291521486643438,
      "grad_norm": 0.6069658994674683,
      "learning_rate": 0.0,
      "loss": 1.2413,
      "step": 200
    },
    {
      "epoch": 0.9291521486643438,
      "eval_loss": 0.8677911162376404,
      "eval_runtime": 35.168,
      "eval_samples_per_second": 10.322,
      "eval_steps_per_second": 2.588,
      "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": 3.853318337278771e+17,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}