{
  "best_metric": 0.28198570013046265,
  "best_model_checkpoint": "miner_id_24/checkpoint-200",
  "epoch": 0.08219459570533237,
  "eval_steps": 50,
  "global_step": 200,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0004109729785266619,
      "grad_norm": 100.7002182006836,
      "learning_rate": 1e-05,
      "loss": 8.6848,
      "step": 1
    },
    {
      "epoch": 0.0004109729785266619,
      "eval_loss": 2.258553981781006,
      "eval_runtime": 301.1451,
      "eval_samples_per_second": 13.611,
      "eval_steps_per_second": 3.404,
      "step": 1
    },
    {
      "epoch": 0.0008219459570533238,
      "grad_norm": 103.55078887939453,
      "learning_rate": 2e-05,
      "loss": 8.7141,
      "step": 2
    },
    {
      "epoch": 0.0012329189355799856,
      "grad_norm": 88.785888671875,
      "learning_rate": 3e-05,
      "loss": 7.6889,
      "step": 3
    },
    {
      "epoch": 0.0016438919141066476,
      "grad_norm": 67.29983520507812,
      "learning_rate": 4e-05,
      "loss": 6.2523,
      "step": 4
    },
    {
      "epoch": 0.0020548648926333093,
      "grad_norm": 38.551822662353516,
      "learning_rate": 5e-05,
      "loss": 4.8237,
      "step": 5
    },
    {
      "epoch": 0.0024658378711599712,
      "grad_norm": 47.25086975097656,
      "learning_rate": 6e-05,
      "loss": 3.4706,
      "step": 6
    },
    {
      "epoch": 0.002876810849686633,
      "grad_norm": 22.67792510986328,
      "learning_rate": 7e-05,
      "loss": 2.8056,
      "step": 7
    },
    {
      "epoch": 0.003287783828213295,
      "grad_norm": 10.82424545288086,
      "learning_rate": 8e-05,
      "loss": 2.336,
      "step": 8
    },
    {
      "epoch": 0.003698756806739957,
      "grad_norm": 18.788007736206055,
      "learning_rate": 9e-05,
      "loss": 1.9716,
      "step": 9
    },
    {
      "epoch": 0.0041097297852666186,
      "grad_norm": 13.260298728942871,
      "learning_rate": 0.0001,
      "loss": 1.9455,
      "step": 10
    },
    {
      "epoch": 0.004520702763793281,
      "grad_norm": 6.758195400238037,
      "learning_rate": 9.999316524962345e-05,
      "loss": 1.7574,
      "step": 11
    },
    {
      "epoch": 0.0049316757423199424,
      "grad_norm": 4.906612873077393,
      "learning_rate": 9.997266286704631e-05,
      "loss": 1.5134,
      "step": 12
    },
    {
      "epoch": 0.005342648720846604,
      "grad_norm": 5.037084579467773,
      "learning_rate": 9.993849845741524e-05,
      "loss": 1.4795,
      "step": 13
    },
    {
      "epoch": 0.005753621699373266,
      "grad_norm": 4.863501071929932,
      "learning_rate": 9.989068136093873e-05,
      "loss": 1.5169,
      "step": 14
    },
    {
      "epoch": 0.006164594677899928,
      "grad_norm": 4.348726749420166,
      "learning_rate": 9.98292246503335e-05,
      "loss": 1.3721,
      "step": 15
    },
    {
      "epoch": 0.00657556765642659,
      "grad_norm": 4.154992580413818,
      "learning_rate": 9.975414512725057e-05,
      "loss": 1.35,
      "step": 16
    },
    {
      "epoch": 0.006986540634953252,
      "grad_norm": 4.274117469787598,
      "learning_rate": 9.966546331768191e-05,
      "loss": 1.3843,
      "step": 17
    },
    {
      "epoch": 0.007397513613479914,
      "grad_norm": 3.519045114517212,
      "learning_rate": 9.956320346634876e-05,
      "loss": 1.5003,
      "step": 18
    },
    {
      "epoch": 0.007808486592006576,
      "grad_norm": 3.3767342567443848,
      "learning_rate": 9.944739353007344e-05,
      "loss": 1.4397,
      "step": 19
    },
    {
      "epoch": 0.008219459570533237,
      "grad_norm": 16.54059410095215,
      "learning_rate": 9.931806517013612e-05,
      "loss": 1.568,
      "step": 20
    },
    {
      "epoch": 0.008630432549059899,
      "grad_norm": 463.7588195800781,
      "learning_rate": 9.917525374361912e-05,
      "loss": 1.8716,
      "step": 21
    },
    {
      "epoch": 0.009041405527586562,
      "grad_norm": 210.9742889404297,
      "learning_rate": 9.901899829374047e-05,
      "loss": 1.9626,
      "step": 22
    },
    {
      "epoch": 0.009452378506113223,
      "grad_norm": 108.00894165039062,
      "learning_rate": 9.884934153917997e-05,
      "loss": 1.5453,
      "step": 23
    },
    {
      "epoch": 0.009863351484639885,
      "grad_norm": 8.511551856994629,
      "learning_rate": 9.86663298624003e-05,
      "loss": 1.5442,
      "step": 24
    },
    {
      "epoch": 0.010274324463166546,
      "grad_norm": 3.917236804962158,
      "learning_rate": 9.847001329696653e-05,
      "loss": 1.5593,
      "step": 25
    },
    {
      "epoch": 0.010685297441693208,
      "grad_norm": 3.110708713531494,
      "learning_rate": 9.826044551386744e-05,
      "loss": 1.4166,
      "step": 26
    },
    {
      "epoch": 0.011096270420219871,
      "grad_norm": 3.5363030433654785,
      "learning_rate": 9.803768380684242e-05,
      "loss": 1.4778,
      "step": 27
    },
    {
      "epoch": 0.011507243398746533,
      "grad_norm": 3.1175782680511475,
      "learning_rate": 9.780178907671789e-05,
      "loss": 1.4838,
      "step": 28
    },
    {
      "epoch": 0.011918216377273194,
      "grad_norm": 2.7159860134124756,
      "learning_rate": 9.755282581475769e-05,
      "loss": 1.3906,
      "step": 29
    },
    {
      "epoch": 0.012329189355799856,
      "grad_norm": 2.892106056213379,
      "learning_rate": 9.729086208503174e-05,
      "loss": 1.3906,
      "step": 30
    },
    {
      "epoch": 0.012740162334326517,
      "grad_norm": 2.565208911895752,
      "learning_rate": 9.701596950580806e-05,
      "loss": 1.424,
      "step": 31
    },
    {
      "epoch": 0.01315113531285318,
      "grad_norm": 2.788456916809082,
      "learning_rate": 9.672822322997305e-05,
      "loss": 1.2917,
      "step": 32
    },
    {
      "epoch": 0.013562108291379842,
      "grad_norm": 2.244171619415283,
      "learning_rate": 9.642770192448536e-05,
      "loss": 1.185,
      "step": 33
    },
    {
      "epoch": 0.013973081269906503,
      "grad_norm": 3.326965093612671,
      "learning_rate": 9.611448774886924e-05,
      "loss": 1.4477,
      "step": 34
    },
    {
      "epoch": 0.014384054248433165,
      "grad_norm": 29.571603775024414,
      "learning_rate": 9.578866633275288e-05,
      "loss": 1.2372,
      "step": 35
    },
    {
      "epoch": 0.014795027226959828,
      "grad_norm": 16.422863006591797,
      "learning_rate": 9.545032675245813e-05,
      "loss": 2.2193,
      "step": 36
    },
    {
      "epoch": 0.01520600020548649,
      "grad_norm": 19.547088623046875,
      "learning_rate": 9.509956150664796e-05,
      "loss": 1.5097,
      "step": 37
    },
    {
      "epoch": 0.015616973184013151,
      "grad_norm": 3.1591155529022217,
      "learning_rate": 9.473646649103818e-05,
      "loss": 1.2472,
      "step": 38
    },
    {
      "epoch": 0.016027946162539813,
      "grad_norm": 2.547860622406006,
      "learning_rate": 9.43611409721806e-05,
      "loss": 1.4625,
      "step": 39
    },
    {
      "epoch": 0.016438919141066474,
      "grad_norm": 2.396812915802002,
      "learning_rate": 9.397368756032445e-05,
      "loss": 1.1863,
      "step": 40
    },
    {
      "epoch": 0.016849892119593136,
      "grad_norm": 2.143462657928467,
      "learning_rate": 9.357421218136386e-05,
      "loss": 1.1457,
      "step": 41
    },
    {
      "epoch": 0.017260865098119797,
      "grad_norm": 2.3512415885925293,
      "learning_rate": 9.316282404787871e-05,
      "loss": 1.1932,
      "step": 42
    },
    {
      "epoch": 0.017671838076646462,
      "grad_norm": 2.20404314994812,
      "learning_rate": 9.273963562927695e-05,
      "loss": 1.1953,
      "step": 43
    },
    {
      "epoch": 0.018082811055173124,
      "grad_norm": 2.105229616165161,
      "learning_rate": 9.230476262104677e-05,
      "loss": 1.2026,
      "step": 44
    },
    {
      "epoch": 0.018493784033699785,
      "grad_norm": 2.073624610900879,
      "learning_rate": 9.185832391312644e-05,
      "loss": 1.0846,
      "step": 45
    },
    {
      "epoch": 0.018904757012226447,
      "grad_norm": 2.151745557785034,
      "learning_rate": 9.140044155740101e-05,
      "loss": 1.0837,
      "step": 46
    },
    {
      "epoch": 0.019315729990753108,
      "grad_norm": 1.8985224962234497,
      "learning_rate": 9.093124073433463e-05,
      "loss": 1.0625,
      "step": 47
    },
    {
      "epoch": 0.01972670296927977,
      "grad_norm": 1.7590411901474,
      "learning_rate": 9.045084971874738e-05,
      "loss": 1.0998,
      "step": 48
    },
    {
      "epoch": 0.02013767594780643,
      "grad_norm": 1.843559741973877,
      "learning_rate": 8.995939984474624e-05,
      "loss": 1.0132,
      "step": 49
    },
    {
      "epoch": 0.020548648926333093,
      "grad_norm": 1.7941235303878784,
      "learning_rate": 8.945702546981969e-05,
      "loss": 1.0124,
      "step": 50
    },
    {
      "epoch": 0.020548648926333093,
      "eval_loss": 0.4138473570346832,
      "eval_runtime": 303.3682,
      "eval_samples_per_second": 13.512,
      "eval_steps_per_second": 3.379,
      "step": 50
    },
    {
      "epoch": 0.020959621904859754,
      "grad_norm": 12.342080116271973,
      "learning_rate": 8.894386393810563e-05,
      "loss": 2.4146,
      "step": 51
    },
    {
      "epoch": 0.021370594883386416,
      "grad_norm": 6.080272197723389,
      "learning_rate": 8.842005554284296e-05,
      "loss": 1.8887,
      "step": 52
    },
    {
      "epoch": 0.02178156786191308,
      "grad_norm": 3.8052139282226562,
      "learning_rate": 8.788574348801675e-05,
      "loss": 1.5046,
      "step": 53
    },
    {
      "epoch": 0.022192540840439742,
      "grad_norm": 2.571850299835205,
      "learning_rate": 8.73410738492077e-05,
      "loss": 1.3564,
      "step": 54
    },
    {
      "epoch": 0.022603513818966404,
      "grad_norm": 2.810466766357422,
      "learning_rate": 8.678619553365659e-05,
      "loss": 1.4813,
      "step": 55
    },
    {
      "epoch": 0.023014486797493065,
      "grad_norm": 2.573469877243042,
      "learning_rate": 8.622126023955446e-05,
      "loss": 1.3625,
      "step": 56
    },
    {
      "epoch": 0.023425459776019727,
      "grad_norm": 2.7407968044281006,
      "learning_rate": 8.564642241456986e-05,
      "loss": 1.4922,
      "step": 57
    },
    {
      "epoch": 0.02383643275454639,
      "grad_norm": 2.315983295440674,
      "learning_rate": 8.506183921362443e-05,
      "loss": 1.3607,
      "step": 58
    },
    {
      "epoch": 0.02424740573307305,
      "grad_norm": 2.314702272415161,
      "learning_rate": 8.44676704559283e-05,
      "loss": 1.3143,
      "step": 59
    },
    {
      "epoch": 0.02465837871159971,
      "grad_norm": 2.3891677856445312,
      "learning_rate": 8.386407858128706e-05,
      "loss": 1.3717,
      "step": 60
    },
    {
      "epoch": 0.025069351690126373,
      "grad_norm": 2.1026391983032227,
      "learning_rate": 8.32512286056924e-05,
      "loss": 1.3662,
      "step": 61
    },
    {
      "epoch": 0.025480324668653034,
      "grad_norm": 2.3388073444366455,
      "learning_rate": 8.262928807620843e-05,
      "loss": 1.3363,
      "step": 62
    },
    {
      "epoch": 0.0258912976471797,
      "grad_norm": 2.0514118671417236,
      "learning_rate": 8.199842702516583e-05,
      "loss": 1.1694,
      "step": 63
    },
    {
      "epoch": 0.02630227062570636,
      "grad_norm": 2.41292667388916,
      "learning_rate": 8.135881792367686e-05,
      "loss": 1.2284,
      "step": 64
    },
    {
      "epoch": 0.026713243604233022,
      "grad_norm": 2.4270639419555664,
      "learning_rate": 8.07106356344834e-05,
      "loss": 1.4271,
      "step": 65
    },
    {
      "epoch": 0.027124216582759684,
      "grad_norm": 2.5759642124176025,
      "learning_rate": 8.005405736415126e-05,
      "loss": 1.2959,
      "step": 66
    },
    {
      "epoch": 0.027535189561286345,
      "grad_norm": 2.39304780960083,
      "learning_rate": 7.938926261462366e-05,
      "loss": 1.1937,
      "step": 67
    },
    {
      "epoch": 0.027946162539813007,
      "grad_norm": 2.2705135345458984,
      "learning_rate": 7.871643313414718e-05,
      "loss": 1.2459,
      "step": 68
    },
    {
      "epoch": 0.02835713551833967,
      "grad_norm": 2.4148080348968506,
      "learning_rate": 7.803575286758364e-05,
      "loss": 1.2989,
      "step": 69
    },
    {
      "epoch": 0.02876810849686633,
      "grad_norm": 2.030571460723877,
      "learning_rate": 7.734740790612136e-05,
      "loss": 1.2639,
      "step": 70
    },
    {
      "epoch": 0.02917908147539299,
      "grad_norm": 2.2056310176849365,
      "learning_rate": 7.66515864363997e-05,
      "loss": 1.2337,
      "step": 71
    },
    {
      "epoch": 0.029590054453919656,
      "grad_norm": 2.6393370628356934,
      "learning_rate": 7.594847868906076e-05,
      "loss": 1.4412,
      "step": 72
    },
    {
      "epoch": 0.030001027432446318,
      "grad_norm": 1.976220965385437,
      "learning_rate": 7.52382768867422e-05,
      "loss": 1.2788,
      "step": 73
    },
    {
      "epoch": 0.03041200041097298,
      "grad_norm": 2.2979400157928467,
      "learning_rate": 7.452117519152542e-05,
      "loss": 1.3334,
      "step": 74
    },
    {
      "epoch": 0.03082297338949964,
      "grad_norm": 1.8376797437667847,
      "learning_rate": 7.379736965185368e-05,
      "loss": 1.2085,
      "step": 75
    },
    {
      "epoch": 0.031233946368026302,
      "grad_norm": 2.161620616912842,
      "learning_rate": 7.30670581489344e-05,
      "loss": 1.3036,
      "step": 76
    },
    {
      "epoch": 0.03164491934655297,
      "grad_norm": 1.7936217784881592,
      "learning_rate": 7.233044034264034e-05,
      "loss": 1.1837,
      "step": 77
    },
    {
      "epoch": 0.032055892325079625,
      "grad_norm": 2.5552217960357666,
      "learning_rate": 7.158771761692464e-05,
      "loss": 1.5987,
      "step": 78
    },
    {
      "epoch": 0.03246686530360629,
      "grad_norm": 2.120462656021118,
      "learning_rate": 7.083909302476453e-05,
      "loss": 1.2969,
      "step": 79
    },
    {
      "epoch": 0.03287783828213295,
      "grad_norm": 1.996077537536621,
      "learning_rate": 7.008477123264848e-05,
      "loss": 1.3274,
      "step": 80
    },
    {
      "epoch": 0.03328881126065961,
      "grad_norm": 1.8100478649139404,
      "learning_rate": 6.932495846462261e-05,
      "loss": 1.3179,
      "step": 81
    },
    {
      "epoch": 0.03369978423918627,
      "grad_norm": 1.971675992012024,
      "learning_rate": 6.855986244591104e-05,
      "loss": 1.3049,
      "step": 82
    },
    {
      "epoch": 0.034110757217712936,
      "grad_norm": 2.0137078762054443,
      "learning_rate": 6.778969234612584e-05,
      "loss": 1.2078,
      "step": 83
    },
    {
      "epoch": 0.034521730196239594,
      "grad_norm": 2.2327828407287598,
      "learning_rate": 6.701465872208216e-05,
      "loss": 1.2199,
      "step": 84
    },
    {
      "epoch": 0.03493270317476626,
      "grad_norm": 2.3494155406951904,
      "learning_rate": 6.623497346023418e-05,
      "loss": 1.2796,
      "step": 85
    },
    {
      "epoch": 0.035343676153292924,
      "grad_norm": 1.7998632192611694,
      "learning_rate": 6.545084971874738e-05,
      "loss": 1.2157,
      "step": 86
    },
    {
      "epoch": 0.03575464913181958,
      "grad_norm": 2.1565279960632324,
      "learning_rate": 6.466250186922325e-05,
      "loss": 1.1824,
      "step": 87
    },
    {
      "epoch": 0.03616562211034625,
      "grad_norm": 2.000291109085083,
      "learning_rate": 6.387014543809223e-05,
      "loss": 1.1575,
      "step": 88
    },
    {
      "epoch": 0.036576595088872906,
      "grad_norm": 2.0263590812683105,
      "learning_rate": 6.307399704769099e-05,
      "loss": 1.2279,
      "step": 89
    },
    {
      "epoch": 0.03698756806739957,
      "grad_norm": 2.2121741771698,
      "learning_rate": 6.227427435703997e-05,
      "loss": 1.1393,
      "step": 90
    },
    {
      "epoch": 0.03739854104592623,
      "grad_norm": 1.6476695537567139,
      "learning_rate": 6.147119600233758e-05,
      "loss": 1.0791,
      "step": 91
    },
    {
      "epoch": 0.037809514024452893,
      "grad_norm": 2.098963975906372,
      "learning_rate": 6.066498153718735e-05,
      "loss": 1.2437,
      "step": 92
    },
    {
      "epoch": 0.03822048700297955,
      "grad_norm": 1.7796459197998047,
      "learning_rate": 5.985585137257401e-05,
      "loss": 1.1393,
      "step": 93
    },
    {
      "epoch": 0.038631459981506217,
      "grad_norm": 1.9552690982818604,
      "learning_rate": 5.90440267166055e-05,
      "loss": 1.0573,
      "step": 94
    },
    {
      "epoch": 0.039042432960032875,
      "grad_norm": 1.4341356754302979,
      "learning_rate": 5.8229729514036705e-05,
      "loss": 0.9289,
      "step": 95
    },
    {
      "epoch": 0.03945340593855954,
      "grad_norm": 1.6645524501800537,
      "learning_rate": 5.74131823855921e-05,
      "loss": 1.1177,
      "step": 96
    },
    {
      "epoch": 0.039864378917086205,
      "grad_norm": 1.5547387599945068,
      "learning_rate": 5.6594608567103456e-05,
      "loss": 1.0653,
      "step": 97
    },
    {
      "epoch": 0.04027535189561286,
      "grad_norm": 1.818339467048645,
      "learning_rate": 5.577423184847932e-05,
      "loss": 1.0471,
      "step": 98
    },
    {
      "epoch": 0.04068632487413953,
      "grad_norm": 1.5988365411758423,
      "learning_rate": 5.495227651252315e-05,
      "loss": 0.9549,
      "step": 99
    },
    {
      "epoch": 0.041097297852666186,
      "grad_norm": 1.8590444326400757,
      "learning_rate": 5.4128967273616625e-05,
      "loss": 0.9896,
      "step": 100
    },
    {
      "epoch": 0.041097297852666186,
      "eval_loss": 0.3455173075199127,
      "eval_runtime": 303.2543,
      "eval_samples_per_second": 13.517,
      "eval_steps_per_second": 3.38,
      "step": 100
    },
    {
      "epoch": 0.04150827083119285,
      "grad_norm": 5.274952411651611,
      "learning_rate": 5.330452921628497e-05,
      "loss": 1.6208,
      "step": 101
    },
    {
      "epoch": 0.04191924380971951,
      "grad_norm": 4.08144998550415,
      "learning_rate": 5.247918773366112e-05,
      "loss": 1.4864,
      "step": 102
    },
    {
      "epoch": 0.042330216788246174,
      "grad_norm": 2.737884044647217,
      "learning_rate": 5.165316846586541e-05,
      "loss": 1.443,
      "step": 103
    },
    {
      "epoch": 0.04274118976677283,
      "grad_norm": 2.1988816261291504,
      "learning_rate": 5.0826697238317935e-05,
      "loss": 1.3324,
      "step": 104
    },
    {
      "epoch": 0.0431521627452995,
      "grad_norm": 2.2960410118103027,
      "learning_rate": 5e-05,
      "loss": 1.2426,
      "step": 105
    },
    {
      "epoch": 0.04356313572382616,
      "grad_norm": 2.2390687465667725,
      "learning_rate": 4.917330276168208e-05,
      "loss": 1.2828,
      "step": 106
    },
    {
      "epoch": 0.04397410870235282,
      "grad_norm": 2.3960556983947754,
      "learning_rate": 4.834683153413459e-05,
      "loss": 1.4194,
      "step": 107
    },
    {
      "epoch": 0.044385081680879485,
      "grad_norm": 2.0492103099823,
      "learning_rate": 4.7520812266338885e-05,
      "loss": 1.2888,
      "step": 108
    },
    {
      "epoch": 0.04479605465940614,
      "grad_norm": 2.0121076107025146,
      "learning_rate": 4.669547078371504e-05,
      "loss": 1.3162,
      "step": 109
    },
    {
      "epoch": 0.04520702763793281,
      "grad_norm": 2.2901666164398193,
      "learning_rate": 4.5871032726383386e-05,
      "loss": 1.3905,
      "step": 110
    },
    {
      "epoch": 0.045618000616459466,
      "grad_norm": 1.9342862367630005,
      "learning_rate": 4.504772348747687e-05,
      "loss": 1.2849,
      "step": 111
    },
    {
      "epoch": 0.04602897359498613,
      "grad_norm": 1.832655906677246,
      "learning_rate": 4.4225768151520694e-05,
      "loss": 1.203,
      "step": 112
    },
    {
      "epoch": 0.04643994657351279,
      "grad_norm": 1.8826347589492798,
      "learning_rate": 4.3405391432896555e-05,
      "loss": 1.2088,
      "step": 113
    },
    {
      "epoch": 0.046850919552039454,
      "grad_norm": 1.752295732498169,
      "learning_rate": 4.2586817614407895e-05,
      "loss": 1.1605,
      "step": 114
    },
    {
      "epoch": 0.04726189253056612,
      "grad_norm": 2.0863845348358154,
      "learning_rate": 4.17702704859633e-05,
      "loss": 1.285,
      "step": 115
    },
    {
      "epoch": 0.04767286550909278,
      "grad_norm": 1.8261597156524658,
      "learning_rate": 4.095597328339452e-05,
      "loss": 1.2279,
      "step": 116
    },
    {
      "epoch": 0.04808383848761944,
      "grad_norm": 1.960571050643921,
      "learning_rate": 4.0144148627425993e-05,
      "loss": 1.2573,
      "step": 117
    },
    {
      "epoch": 0.0484948114661461,
      "grad_norm": 2.176847219467163,
      "learning_rate": 3.933501846281267e-05,
      "loss": 1.2994,
      "step": 118
    },
    {
      "epoch": 0.048905784444672765,
      "grad_norm": 2.2963430881500244,
      "learning_rate": 3.852880399766243e-05,
      "loss": 1.3262,
      "step": 119
    },
    {
      "epoch": 0.04931675742319942,
      "grad_norm": 1.8424094915390015,
      "learning_rate": 3.772572564296005e-05,
      "loss": 1.1288,
      "step": 120
    },
    {
      "epoch": 0.04972773040172609,
      "grad_norm": 1.966762661933899,
      "learning_rate": 3.6926002952309016e-05,
      "loss": 1.3157,
      "step": 121
    },
    {
      "epoch": 0.050138703380252746,
      "grad_norm": 2.4863340854644775,
      "learning_rate": 3.612985456190778e-05,
      "loss": 1.3588,
      "step": 122
    },
    {
      "epoch": 0.05054967635877941,
      "grad_norm": 1.7269797325134277,
      "learning_rate": 3.533749813077677e-05,
      "loss": 1.2165,
      "step": 123
    },
    {
      "epoch": 0.05096064933730607,
      "grad_norm": 1.803267002105713,
      "learning_rate": 3.4549150281252636e-05,
      "loss": 1.2079,
      "step": 124
    },
    {
      "epoch": 0.051371622315832734,
      "grad_norm": 1.9960136413574219,
      "learning_rate": 3.3765026539765834e-05,
      "loss": 1.3995,
      "step": 125
    },
    {
      "epoch": 0.0517825952943594,
      "grad_norm": 1.9701896905899048,
      "learning_rate": 3.298534127791785e-05,
      "loss": 1.3375,
      "step": 126
    },
    {
      "epoch": 0.05219356827288606,
      "grad_norm": 2.303657293319702,
      "learning_rate": 3.221030765387417e-05,
      "loss": 1.2451,
      "step": 127
    },
    {
      "epoch": 0.05260454125141272,
      "grad_norm": 1.9838213920593262,
      "learning_rate": 3.144013755408895e-05,
      "loss": 1.2861,
      "step": 128
    },
    {
      "epoch": 0.05301551422993938,
      "grad_norm": 1.9161285161972046,
      "learning_rate": 3.0675041535377405e-05,
      "loss": 1.2781,
      "step": 129
    },
    {
      "epoch": 0.053426487208466045,
      "grad_norm": 1.9126702547073364,
      "learning_rate": 2.991522876735154e-05,
      "loss": 1.2527,
      "step": 130
    },
    {
      "epoch": 0.0538374601869927,
      "grad_norm": 1.754321575164795,
      "learning_rate": 2.916090697523549e-05,
      "loss": 1.1144,
      "step": 131
    },
    {
      "epoch": 0.05424843316551937,
      "grad_norm": 1.589983582496643,
      "learning_rate": 2.8412282383075363e-05,
      "loss": 1.1775,
      "step": 132
    },
    {
      "epoch": 0.054659406144046026,
      "grad_norm": 1.8121100664138794,
      "learning_rate": 2.766955965735968e-05,
      "loss": 1.2395,
      "step": 133
    },
    {
      "epoch": 0.05507037912257269,
      "grad_norm": 1.5348248481750488,
      "learning_rate": 2.693294185106562e-05,
      "loss": 1.0873,
      "step": 134
    },
    {
      "epoch": 0.055481352101099356,
      "grad_norm": 1.7048112154006958,
      "learning_rate": 2.6202630348146324e-05,
      "loss": 1.2059,
      "step": 135
    },
    {
      "epoch": 0.055892325079626014,
      "grad_norm": 1.6508110761642456,
      "learning_rate": 2.547882480847461e-05,
      "loss": 1.1109,
      "step": 136
    },
    {
      "epoch": 0.05630329805815268,
      "grad_norm": 1.7701857089996338,
      "learning_rate": 2.476172311325783e-05,
      "loss": 1.1188,
      "step": 137
    },
    {
      "epoch": 0.05671427103667934,
      "grad_norm": 1.6648733615875244,
      "learning_rate": 2.405152131093926e-05,
      "loss": 1.1481,
      "step": 138
    },
    {
      "epoch": 0.057125244015206,
      "grad_norm": 1.6659666299819946,
      "learning_rate": 2.3348413563600325e-05,
      "loss": 1.0526,
      "step": 139
    },
    {
      "epoch": 0.05753621699373266,
      "grad_norm": 1.4453469514846802,
      "learning_rate": 2.2652592093878666e-05,
      "loss": 1.0307,
      "step": 140
    },
    {
      "epoch": 0.057947189972259325,
      "grad_norm": 1.6568886041641235,
      "learning_rate": 2.196424713241637e-05,
      "loss": 1.0075,
      "step": 141
    },
    {
      "epoch": 0.05835816295078598,
      "grad_norm": 1.710189700126648,
      "learning_rate": 2.128356686585282e-05,
      "loss": 1.1886,
      "step": 142
    },
    {
      "epoch": 0.05876913592931265,
      "grad_norm": 1.6561558246612549,
      "learning_rate": 2.061073738537635e-05,
      "loss": 1.0218,
      "step": 143
    },
    {
      "epoch": 0.05918010890783931,
      "grad_norm": 1.780678629875183,
      "learning_rate": 1.9945942635848748e-05,
      "loss": 1.0088,
      "step": 144
    },
    {
      "epoch": 0.05959108188636597,
      "grad_norm": 1.5461232662200928,
      "learning_rate": 1.928936436551661e-05,
      "loss": 0.9732,
      "step": 145
    },
    {
      "epoch": 0.060002054864892636,
      "grad_norm": 1.5056289434432983,
      "learning_rate": 1.8641182076323148e-05,
      "loss": 0.9288,
      "step": 146
    },
    {
      "epoch": 0.060413027843419294,
      "grad_norm": 1.5496935844421387,
      "learning_rate": 1.800157297483417e-05,
      "loss": 0.9537,
      "step": 147
    },
    {
      "epoch": 0.06082400082194596,
      "grad_norm": 1.5166020393371582,
      "learning_rate": 1.7370711923791567e-05,
      "loss": 0.8448,
      "step": 148
    },
    {
      "epoch": 0.06123497380047262,
      "grad_norm": 1.8695980310440063,
      "learning_rate": 1.6748771394307585e-05,
      "loss": 0.9564,
      "step": 149
    },
    {
      "epoch": 0.06164594677899928,
      "grad_norm": 1.3109105825424194,
      "learning_rate": 1.6135921418712956e-05,
      "loss": 0.8316,
      "step": 150
    },
    {
      "epoch": 0.06164594677899928,
      "eval_loss": 0.3154841363430023,
      "eval_runtime": 303.3515,
      "eval_samples_per_second": 13.512,
      "eval_steps_per_second": 3.379,
      "step": 150
    },
    {
      "epoch": 0.06205691975752594,
      "grad_norm": 4.3704657554626465,
      "learning_rate": 1.553232954407171e-05,
      "loss": 1.5542,
      "step": 151
    },
    {
      "epoch": 0.062467892736052605,
      "grad_norm": 3.7245233058929443,
      "learning_rate": 1.4938160786375572e-05,
      "loss": 1.4012,
      "step": 152
    },
    {
      "epoch": 0.06287886571457926,
      "grad_norm": 2.927494764328003,
      "learning_rate": 1.435357758543015e-05,
      "loss": 1.3899,
      "step": 153
    },
    {
      "epoch": 0.06328983869310593,
      "grad_norm": 2.695345163345337,
      "learning_rate": 1.3778739760445552e-05,
      "loss": 1.3374,
      "step": 154
    },
    {
      "epoch": 0.06370081167163259,
      "grad_norm": 4.965470314025879,
      "learning_rate": 1.3213804466343421e-05,
      "loss": 1.4011,
      "step": 155
    },
    {
      "epoch": 0.06411178465015925,
      "grad_norm": 2.1832683086395264,
      "learning_rate": 1.2658926150792322e-05,
      "loss": 1.2434,
      "step": 156
    },
    {
      "epoch": 0.06452275762868591,
      "grad_norm": 2.6303791999816895,
      "learning_rate": 1.2114256511983274e-05,
      "loss": 1.4201,
      "step": 157
    },
    {
      "epoch": 0.06493373060721258,
      "grad_norm": 2.4186301231384277,
      "learning_rate": 1.157994445715706e-05,
      "loss": 1.4211,
      "step": 158
    },
    {
      "epoch": 0.06534470358573924,
      "grad_norm": 2.208402395248413,
      "learning_rate": 1.1056136061894384e-05,
      "loss": 1.2533,
      "step": 159
    },
    {
      "epoch": 0.0657556765642659,
      "grad_norm": 1.9956814050674438,
      "learning_rate": 1.0542974530180327e-05,
      "loss": 1.3004,
      "step": 160
    },
    {
      "epoch": 0.06616664954279255,
      "grad_norm": 1.9075251817703247,
      "learning_rate": 1.0040600155253765e-05,
      "loss": 1.271,
      "step": 161
    },
    {
      "epoch": 0.06657762252131923,
      "grad_norm": 1.5910518169403076,
      "learning_rate": 9.549150281252633e-06,
      "loss": 1.1409,
      "step": 162
    },
    {
      "epoch": 0.06698859549984588,
      "grad_norm": 1.4548826217651367,
      "learning_rate": 9.068759265665384e-06,
      "loss": 1.1023,
      "step": 163
    },
    {
      "epoch": 0.06739956847837254,
      "grad_norm": 1.6431039571762085,
      "learning_rate": 8.599558442598998e-06,
      "loss": 1.0703,
      "step": 164
    },
    {
      "epoch": 0.06781054145689921,
      "grad_norm": 2.21774959564209,
      "learning_rate": 8.141676086873572e-06,
      "loss": 1.2489,
      "step": 165
    },
    {
      "epoch": 0.06822151443542587,
      "grad_norm": 2.038455009460449,
      "learning_rate": 7.695237378953223e-06,
      "loss": 1.2841,
      "step": 166
    },
    {
      "epoch": 0.06863248741395253,
      "grad_norm": 1.6020883321762085,
      "learning_rate": 7.260364370723044e-06,
      "loss": 1.0487,
      "step": 167
    },
    {
      "epoch": 0.06904346039247919,
      "grad_norm": 1.745267391204834,
      "learning_rate": 6.837175952121306e-06,
      "loss": 1.1634,
      "step": 168
    },
    {
      "epoch": 0.06945443337100586,
      "grad_norm": 1.9748502969741821,
      "learning_rate": 6.425787818636131e-06,
      "loss": 1.2733,
      "step": 169
    },
    {
      "epoch": 0.06986540634953252,
      "grad_norm": 1.791924238204956,
      "learning_rate": 6.026312439675552e-06,
      "loss": 1.2162,
      "step": 170
    },
    {
      "epoch": 0.07027637932805918,
      "grad_norm": 1.6656522750854492,
      "learning_rate": 5.6388590278194096e-06,
      "loss": 1.1565,
      "step": 171
    },
    {
      "epoch": 0.07068735230658585,
      "grad_norm": 1.8356313705444336,
      "learning_rate": 5.263533508961827e-06,
      "loss": 1.1868,
      "step": 172
    },
    {
      "epoch": 0.0710983252851125,
      "grad_norm": 1.7833075523376465,
      "learning_rate": 4.900438493352055e-06,
      "loss": 1.1971,
      "step": 173
    },
    {
      "epoch": 0.07150929826363916,
      "grad_norm": 1.7517731189727783,
      "learning_rate": 4.549673247541875e-06,
      "loss": 1.1361,
      "step": 174
    },
    {
      "epoch": 0.07192027124216582,
      "grad_norm": 1.8282188177108765,
      "learning_rate": 4.2113336672471245e-06,
      "loss": 1.1655,
      "step": 175
    },
    {
      "epoch": 0.0723312442206925,
      "grad_norm": 2.0048489570617676,
      "learning_rate": 3.885512251130763e-06,
      "loss": 1.2894,
      "step": 176
    },
    {
      "epoch": 0.07274221719921915,
      "grad_norm": 1.8666342496871948,
      "learning_rate": 3.5722980755146517e-06,
      "loss": 1.171,
      "step": 177
    },
    {
      "epoch": 0.07315319017774581,
      "grad_norm": 1.7299134731292725,
      "learning_rate": 3.271776770026963e-06,
      "loss": 1.1706,
      "step": 178
    },
    {
      "epoch": 0.07356416315627247,
      "grad_norm": 1.87256920337677,
      "learning_rate": 2.9840304941919415e-06,
      "loss": 1.1961,
      "step": 179
    },
    {
      "epoch": 0.07397513613479914,
      "grad_norm": 1.7400177717208862,
      "learning_rate": 2.7091379149682685e-06,
      "loss": 1.1313,
      "step": 180
    },
    {
      "epoch": 0.0743861091133258,
      "grad_norm": 1.7896977663040161,
      "learning_rate": 2.4471741852423237e-06,
      "loss": 1.2215,
      "step": 181
    },
    {
      "epoch": 0.07479708209185246,
      "grad_norm": 1.8336591720581055,
      "learning_rate": 2.1982109232821178e-06,
      "loss": 1.2107,
      "step": 182
    },
    {
      "epoch": 0.07520805507037913,
      "grad_norm": 1.7827222347259521,
      "learning_rate": 1.962316193157593e-06,
      "loss": 1.2527,
      "step": 183
    },
    {
      "epoch": 0.07561902804890579,
      "grad_norm": 1.7178598642349243,
      "learning_rate": 1.7395544861325718e-06,
      "loss": 1.1959,
      "step": 184
    },
    {
      "epoch": 0.07603000102743245,
      "grad_norm": 1.7649455070495605,
      "learning_rate": 1.5299867030334814e-06,
      "loss": 1.1241,
      "step": 185
    },
    {
      "epoch": 0.0764409740059591,
      "grad_norm": 1.777260661125183,
      "learning_rate": 1.333670137599713e-06,
      "loss": 1.2056,
      "step": 186
    },
    {
      "epoch": 0.07685194698448577,
      "grad_norm": 1.6076605319976807,
      "learning_rate": 1.1506584608200367e-06,
      "loss": 1.0337,
      "step": 187
    },
    {
      "epoch": 0.07726291996301243,
      "grad_norm": 1.9871001243591309,
      "learning_rate": 9.810017062595322e-07,
      "loss": 1.1355,
      "step": 188
    },
    {
      "epoch": 0.07767389294153909,
      "grad_norm": 1.827332854270935,
      "learning_rate": 8.247462563808817e-07,
      "loss": 1.1584,
      "step": 189
    },
    {
      "epoch": 0.07808486592006575,
      "grad_norm": 1.5034656524658203,
      "learning_rate": 6.819348298638839e-07,
      "loss": 0.9699,
      "step": 190
    },
    {
      "epoch": 0.07849583889859242,
      "grad_norm": 1.887949824333191,
      "learning_rate": 5.526064699265753e-07,
      "loss": 1.09,
      "step": 191
    },
    {
      "epoch": 0.07890681187711908,
      "grad_norm": 1.7921802997589111,
      "learning_rate": 4.367965336512403e-07,
      "loss": 1.1076,
      "step": 192
    },
    {
      "epoch": 0.07931778485564574,
      "grad_norm": 1.7191362380981445,
      "learning_rate": 3.3453668231809286e-07,
      "loss": 1.0853,
      "step": 193
    },
    {
      "epoch": 0.07972875783417241,
      "grad_norm": 1.6274025440216064,
      "learning_rate": 2.458548727494292e-07,
      "loss": 1.0448,
      "step": 194
    },
    {
      "epoch": 0.08013973081269907,
      "grad_norm": 1.864425778388977,
      "learning_rate": 1.7077534966650766e-07,
      "loss": 1.0151,
      "step": 195
    },
    {
      "epoch": 0.08055070379122573,
      "grad_norm": 1.6735941171646118,
      "learning_rate": 1.0931863906127327e-07,
      "loss": 1.022,
      "step": 196
    },
    {
      "epoch": 0.08096167676975238,
      "grad_norm": 1.7238972187042236,
      "learning_rate": 6.150154258476315e-08,
      "loss": 1.0656,
      "step": 197
    },
    {
      "epoch": 0.08137264974827906,
      "grad_norm": 1.7387648820877075,
      "learning_rate": 2.7337132953697554e-08,
      "loss": 1.0072,
      "step": 198
    },
    {
      "epoch": 0.08178362272680571,
      "grad_norm": 1.8777408599853516,
      "learning_rate": 6.834750376549792e-09,
      "loss": 1.0887,
      "step": 199
    },
    {
      "epoch": 0.08219459570533237,
      "grad_norm": 2.0369558334350586,
      "learning_rate": 0.0,
      "loss": 1.005,
      "step": 200
    },
    {
      "epoch": 0.08219459570533237,
      "eval_loss": 0.28198570013046265,
      "eval_runtime": 303.2419,
      "eval_samples_per_second": 13.517,
      "eval_steps_per_second": 3.38,
      "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": 2.861999239200768e+17,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}