{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": null,
  "global_step": 0,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.01,
      "learning_rate": 2.9997541914704325e-05,
      "loss": 0.0855,
      "reward": 0.814,
      "step": 49
    },
    {
      "epoch": 0.01,
      "learning_rate": 2.9989966819651966e-05,
      "loss": 0.0814,
      "reward": 0.9376,
      "step": 99
    },
    {
      "epoch": 0.02,
      "learning_rate": 2.9977276276102345e-05,
      "loss": 0.0734,
      "reward": 0.8684,
      "step": 149
    },
    {
      "epoch": 0.02,
      "learning_rate": 2.995947461480701e-05,
      "loss": 0.0716,
      "reward": 0.8537,
      "step": 199
    },
    {
      "epoch": 0.03,
      "learning_rate": 2.9936567910728124e-05,
      "loss": 0.0603,
      "reward": 0.6429,
      "step": 249
    },
    {
      "epoch": 0.04,
      "learning_rate": 2.9908563980965393e-05,
      "loss": 0.0624,
      "reward": 0.641,
      "step": 299
    },
    {
      "epoch": 0.04,
      "learning_rate": 2.9875472382088355e-05,
      "loss": 0.0631,
      "reward": 0.8062,
      "step": 349
    },
    {
      "epoch": 0.05,
      "learning_rate": 2.9837304406875167e-05,
      "loss": 0.0577,
      "reward": 0.5326,
      "step": 399
    },
    {
      "epoch": 0.05,
      "learning_rate": 2.9794073080458815e-05,
      "loss": 0.0556,
      "reward": 0.9085,
      "step": 449
    },
    {
      "epoch": 0.06,
      "learning_rate": 2.9745793155882214e-05,
      "loss": 0.055,
      "reward": 0.9616,
      "step": 499
    },
    {
      "epoch": 0.06,
      "learning_rate": 2.9692481109063605e-05,
      "loss": 0.0525,
      "reward": 0.899,
      "step": 549
    },
    {
      "epoch": 0.07,
      "learning_rate": 2.963415513317399e-05,
      "loss": 0.0518,
      "reward": 0.6793,
      "step": 599
    },
    {
      "epoch": 0.08,
      "learning_rate": 2.9570835132428594e-05,
      "loss": 0.0546,
      "reward": 0.8445,
      "step": 649
    },
    {
      "epoch": 0.08,
      "learning_rate": 2.9502542715294366e-05,
      "loss": 0.0532,
      "reward": 0.7952,
      "step": 699
    },
    {
      "epoch": 0.09,
      "learning_rate": 2.942930118711593e-05,
      "loss": 0.0515,
      "reward": 0.8009,
      "step": 749
    },
    {
      "epoch": 0.09,
      "learning_rate": 2.9351135542162432e-05,
      "loss": 0.0445,
      "reward": 1.1039,
      "step": 799
    },
    {
      "epoch": 0.1,
      "learning_rate": 2.9268072455098065e-05,
      "loss": 0.0447,
      "reward": 0.858,
      "step": 849
    },
    {
      "epoch": 0.11,
      "learning_rate": 2.918014027187909e-05,
      "loss": 0.0455,
      "reward": 0.9129,
      "step": 899
    },
    {
      "epoch": 0.11,
      "learning_rate": 2.9087369000080567e-05,
      "loss": 0.0459,
      "reward": 0.9215,
      "step": 949
    },
    {
      "epoch": 0.12,
      "learning_rate": 2.898979029865602e-05,
      "loss": 0.0424,
      "reward": 0.8282,
      "step": 999
    },
    {
      "epoch": 0.12,
      "learning_rate": 2.888743746713357e-05,
      "loss": 0.0437,
      "reward": 0.9707,
      "step": 1049
    },
    {
      "epoch": 0.13,
      "learning_rate": 2.8780345434252185e-05,
      "loss": 0.041,
      "reward": 0.796,
      "step": 1099
    },
    {
      "epoch": 0.14,
      "learning_rate": 2.8668550746041966e-05,
      "loss": 0.0468,
      "reward": 0.9538,
      "step": 1149
    },
    {
      "epoch": 0.14,
      "learning_rate": 2.8552091553352533e-05,
      "loss": 0.0409,
      "reward": 0.8948,
      "step": 1199
    },
    {
      "epoch": 0.15,
      "learning_rate": 2.8431007598833705e-05,
      "loss": 0.0408,
      "reward": 0.7338,
      "step": 1249
    },
    {
      "epoch": 0.15,
      "learning_rate": 2.830534020337303e-05,
      "loss": 0.0392,
      "reward": 0.8156,
      "step": 1299
    },
    {
      "epoch": 0.16,
      "learning_rate": 2.817513225199466e-05,
      "loss": 0.0375,
      "reward": 0.7625,
      "step": 1349
    },
    {
      "epoch": 0.16,
      "learning_rate": 2.8040428179224528e-05,
      "loss": 0.04,
      "reward": 0.9719,
      "step": 1399
    },
    {
      "epoch": 0.17,
      "learning_rate": 2.790127395392666e-05,
      "loss": 0.034,
      "reward": 0.8545,
      "step": 1449
    },
    {
      "epoch": 0.18,
      "learning_rate": 2.7757717063615962e-05,
      "loss": 0.0437,
      "reward": 0.8889,
      "step": 1499
    },
    {
      "epoch": 0.18,
      "learning_rate": 2.7609806498252692e-05,
      "loss": 0.0355,
      "reward": 1.2005,
      "step": 1549
    },
    {
      "epoch": 0.19,
      "learning_rate": 2.745759273352425e-05,
      "loss": 0.0368,
      "reward": 1.0282,
      "step": 1599
    },
    {
      "epoch": 0.19,
      "learning_rate": 2.7301127713619938e-05,
      "loss": 0.0346,
      "reward": 0.9873,
      "step": 1649
    },
    {
      "epoch": 0.2,
      "learning_rate": 2.7140464833504564e-05,
      "loss": 0.034,
      "reward": 0.7074,
      "step": 1699
    },
    {
      "epoch": 0.21,
      "learning_rate": 2.6975658920697006e-05,
      "loss": 0.0334,
      "reward": 0.9238,
      "step": 1749
    },
    {
      "epoch": 0.21,
      "learning_rate": 2.680676621655984e-05,
      "loss": 0.0317,
      "reward": 0.8791,
      "step": 1799
    },
    {
      "epoch": 0.22,
      "learning_rate": 2.663384435710654e-05,
      "loss": 0.0348,
      "reward": 1.1593,
      "step": 1849
    },
    {
      "epoch": 0.22,
      "learning_rate": 2.6456952353332712e-05,
      "loss": 0.0309,
      "reward": 1.0537,
      "step": 1899
    },
    {
      "epoch": 0.23,
      "learning_rate": 2.6276150571078108e-05,
      "loss": 0.0333,
      "reward": 1.0686,
      "step": 1949
    },
    {
      "epoch": 0.24,
      "learning_rate": 2.6091500710426278e-05,
      "loss": 0.0355,
      "reward": 1.0331,
      "step": 1999
    },
    {
      "epoch": 0.24,
      "learning_rate": 2.5903065784648947e-05,
      "loss": 0.0331,
      "reward": 0.8029,
      "step": 2049
    },
    {
      "epoch": 0.25,
      "learning_rate": 2.5710910098702187e-05,
      "loss": 0.0324,
      "reward": 0.9726,
      "step": 2099
    },
    {
      "epoch": 0.25,
      "learning_rate": 2.5515099227281836e-05,
      "loss": 0.0322,
      "reward": 0.9616,
      "step": 2149
    },
    {
      "epoch": 0.26,
      "learning_rate": 2.5315699992445617e-05,
      "loss": 0.0322,
      "reward": 0.9011,
      "step": 2199
    },
    {
      "epoch": 0.26,
      "learning_rate": 2.511278044080954e-05,
      "loss": 0.0314,
      "reward": 0.7529,
      "step": 2249
    },
    {
      "epoch": 0.27,
      "learning_rate": 2.4906409820326436e-05,
      "loss": 0.0286,
      "reward": 1.1313,
      "step": 2299
    },
    {
      "epoch": 0.28,
      "learning_rate": 2.4696658556654575e-05,
      "loss": 0.0285,
      "reward": 1.032,
      "step": 2349
    },
    {
      "epoch": 0.28,
      "learning_rate": 2.4483598229124274e-05,
      "loss": 0.0296,
      "reward": 1.0514,
      "step": 2399
    },
    {
      "epoch": 0.29,
      "learning_rate": 2.42673015463109e-05,
      "loss": 0.0308,
      "reward": 1.1721,
      "step": 2449
    },
    {
      "epoch": 0.29,
      "learning_rate": 2.404784232122248e-05,
      "loss": 0.0288,
      "reward": 1.2602,
      "step": 2499
    },
    {
      "epoch": 0.3,
      "learning_rate": 2.382529544611038e-05,
      "loss": 0.0274,
      "reward": 1.3181,
      "step": 2549
    },
    {
      "epoch": 0.31,
      "learning_rate": 2.3599736866911756e-05,
      "loss": 0.0302,
      "reward": 0.8566,
      "step": 2599
    },
    {
      "epoch": 0.31,
      "learning_rate": 2.3371243557332333e-05,
      "loss": 0.0324,
      "reward": 1.1646,
      "step": 2649
    },
    {
      "epoch": 0.32,
      "learning_rate": 2.313989349257855e-05,
      "loss": 0.028,
      "reward": 1.3095,
      "step": 2699
    },
    {
      "epoch": 0.32,
      "learning_rate": 2.2905765622747843e-05,
      "loss": 0.0294,
      "reward": 0.9202,
      "step": 2749
    },
    {
      "epoch": 0.33,
      "learning_rate": 2.266893984588631e-05,
      "loss": 0.0299,
      "reward": 0.9073,
      "step": 2799
    },
    {
      "epoch": 0.34,
      "learning_rate": 2.242949698072283e-05,
      "loss": 0.0264,
      "reward": 1.0046,
      "step": 2849
    },
    {
      "epoch": 0.34,
      "learning_rate": 2.2187518739089033e-05,
      "loss": 0.0317,
      "reward": 1.1227,
      "step": 2899
    },
    {
      "epoch": 0.35,
      "learning_rate": 2.194308769803444e-05,
      "loss": 0.0276,
      "reward": 1.0356,
      "step": 2949
    },
    {
      "epoch": 0.35,
      "learning_rate": 2.1696287271646406e-05,
      "loss": 0.0253,
      "reward": 1.1648,
      "step": 2999
    },
    {
      "epoch": 0.36,
      "learning_rate": 2.1447201682584356e-05,
      "loss": 0.026,
      "reward": 1.155,
      "step": 3049
    },
    {
      "epoch": 0.36,
      "learning_rate": 2.1195915933338133e-05,
      "loss": 0.0265,
      "reward": 0.9532,
      "step": 3099
    },
    {
      "epoch": 0.37,
      "learning_rate": 2.0942515777220186e-05,
      "loss": 0.0278,
      "reward": 1.1358,
      "step": 3149
    },
    {
      "epoch": 0.38,
      "learning_rate": 2.0687087689101562e-05,
      "loss": 0.0258,
      "reward": 1.0723,
      "step": 3199
    },
    {
      "epoch": 0.38,
      "learning_rate": 2.0429718835901672e-05,
      "loss": 0.029,
      "reward": 1.3277,
      "step": 3249
    },
    {
      "epoch": 0.39,
      "learning_rate": 2.0170497046841824e-05,
      "loss": 0.0281,
      "reward": 1.2176,
      "step": 3299
    },
    {
      "epoch": 0.39,
      "learning_rate": 1.9909510783472825e-05,
      "loss": 0.0258,
      "reward": 1.3399,
      "step": 3349
    },
    {
      "epoch": 0.4,
      "learning_rate": 1.964684910948672e-05,
      "loss": 0.0279,
      "reward": 1.1264,
      "step": 3399
    },
    {
      "epoch": 0.41,
      "learning_rate": 1.9382601660323124e-05,
      "loss": 0.0259,
      "reward": 1.0383,
      "step": 3449
    },
    {
      "epoch": 0.41,
      "learning_rate": 1.911685861258034e-05,
      "loss": 0.0244,
      "reward": 1.135,
      "step": 3499
    },
    {
      "epoch": 0.42,
      "learning_rate": 1.8849710653241923e-05,
      "loss": 0.0246,
      "reward": 1.0922,
      "step": 3549
    },
    {
      "epoch": 0.42,
      "learning_rate": 1.858124894872895e-05,
      "loss": 0.0243,
      "reward": 1.1385,
      "step": 3599
    },
    {
      "epoch": 0.43,
      "learning_rate": 1.8311565113788777e-05,
      "loss": 0.0255,
      "reward": 0.9836,
      "step": 3649
    },
    {
      "epoch": 0.44,
      "learning_rate": 1.804075118023072e-05,
      "loss": 0.0244,
      "reward": 1.0459,
      "step": 3699
    },
    {
      "epoch": 0.44,
      "learning_rate": 1.7768899565519493e-05,
      "loss": 0.0233,
      "reward": 1.1805,
      "step": 3749
    },
    {
      "epoch": 0.45,
      "learning_rate": 1.749610304123695e-05,
      "loss": 0.0264,
      "reward": 1.305,
      "step": 3799
    },
    {
      "epoch": 0.45,
      "learning_rate": 1.7222454701423068e-05,
      "loss": 0.0237,
      "reward": 1.0362,
      "step": 3849
    },
    {
      "epoch": 0.46,
      "learning_rate": 1.694804793080681e-05,
      "loss": 0.0236,
      "reward": 1.2275,
      "step": 3899
    },
    {
      "epoch": 0.46,
      "learning_rate": 1.6672976372937838e-05,
      "loss": 0.0238,
      "reward": 1.2652,
      "step": 3949
    },
    {
      "epoch": 0.47,
      "learning_rate": 1.63973338982299e-05,
      "loss": 0.0235,
      "reward": 1.1863,
      "step": 3999
    },
    {
      "epoch": 0.48,
      "learning_rate": 1.6121214571926765e-05,
      "loss": 0.0253,
      "reward": 1.4457,
      "step": 4049
    },
    {
      "epoch": 0.48,
      "learning_rate": 1.5844712622001708e-05,
      "loss": 0.0241,
      "reward": 1.3766,
      "step": 4099
    },
    {
      "epoch": 0.49,
      "learning_rate": 1.5567922407001432e-05,
      "loss": 0.0228,
      "reward": 1.2514,
      "step": 4149
    },
    {
      "epoch": 0.49,
      "learning_rate": 1.5290938383845442e-05,
      "loss": 0.0237,
      "reward": 1.2308,
      "step": 4199
    },
    {
      "epoch": 0.5,
      "learning_rate": 1.5013855075591872e-05,
      "loss": 0.0219,
      "reward": 1.3735,
      "step": 4249
    },
    {
      "epoch": 0.51,
      "learning_rate": 1.4736767039180697e-05,
      "loss": 0.0239,
      "reward": 1.1207,
      "step": 4299
    },
    {
      "epoch": 0.51,
      "learning_rate": 1.4459768833165414e-05,
      "loss": 0.0219,
      "reward": 1.1005,
      "step": 4349
    },
    {
      "epoch": 0.52,
      "learning_rate": 1.4182954985444172e-05,
      "loss": 0.023,
      "reward": 1.4297,
      "step": 4399
    },
    {
      "epoch": 0.52,
      "learning_rate": 1.3906419961001339e-05,
      "loss": 0.0238,
      "reward": 1.289,
      "step": 4449
    },
    {
      "epoch": 0.53,
      "learning_rate": 1.3630258129670565e-05,
      "loss": 0.0221,
      "reward": 1.3299,
      "step": 4499
    },
    {
      "epoch": 0.54,
      "learning_rate": 1.3354563733930315e-05,
      "loss": 0.0221,
      "reward": 1.5207,
      "step": 4549
    },
    {
      "epoch": 0.54,
      "learning_rate": 1.3079430856742829e-05,
      "loss": 0.0207,
      "reward": 1.3068,
      "step": 4599
    },
    {
      "epoch": 0.55,
      "learning_rate": 1.2804953389447579e-05,
      "loss": 0.0228,
      "reward": 1.2289,
      "step": 4649
    },
    {
      "epoch": 0.55,
      "learning_rate": 1.2531224999720032e-05,
      "loss": 0.0222,
      "reward": 1.1784,
      "step": 4699
    },
    {
      "epoch": 0.56,
      "learning_rate": 1.2258339099606862e-05,
      "loss": 0.0208,
      "reward": 1.1996,
      "step": 4749
    },
    {
      "epoch": 0.56,
      "learning_rate": 1.198638881364825e-05,
      "loss": 0.0213,
      "reward": 1.2377,
      "step": 4799
    },
    {
      "epoch": 0.57,
      "learning_rate": 1.1715466947098438e-05,
      "loss": 0.0217,
      "reward": 1.1597,
      "step": 4849
    },
    {
      "epoch": 0.58,
      "learning_rate": 1.1445665954255139e-05,
      "loss": 0.02,
      "reward": 1.2,
      "step": 4899
    },
    {
      "epoch": 0.58,
      "learning_rate": 1.1177077906908772e-05,
      "loss": 0.0233,
      "reward": 1.3867,
      "step": 4949
    },
    {
      "epoch": 0.59,
      "learning_rate": 1.0909794462922214e-05,
      "loss": 0.0213,
      "reward": 1.3454,
      "step": 4999
    },
    {
      "epoch": 0.59,
      "learning_rate": 1.064390683495178e-05,
      "loss": 0.0212,
      "reward": 1.2913,
      "step": 5049
    },
    {
      "epoch": 0.6,
      "learning_rate": 1.0379505759320209e-05,
      "loss": 0.0215,
      "reward": 1.1036,
      "step": 5099
    },
    {
      "epoch": 0.61,
      "learning_rate": 1.0116681465052087e-05,
      "loss": 0.0211,
      "reward": 1.5439,
      "step": 5149
    },
    {
      "epoch": 0.61,
      "learning_rate": 9.855523643082532e-06,
      "loss": 0.0204,
      "reward": 1.2613,
      "step": 5199
    },
    {
      "epoch": 0.62,
      "learning_rate": 9.596121415649359e-06,
      "loss": 0.0219,
      "reward": 1.4101,
      "step": 5249
    },
    {
      "epoch": 0.62,
      "learning_rate": 9.33856330587944e-06,
      "loss": 0.022,
      "reward": 1.4715,
      "step": 5299
    },
    {
      "epoch": 0.63,
      "learning_rate": 9.082937207579442e-06,
      "loss": 0.0227,
      "reward": 1.3201,
      "step": 5349
    },
    {
      "epoch": 0.64,
      "learning_rate": 8.82933035524135e-06,
      "loss": 0.0194,
      "reward": 1.2946,
      "step": 5399
    },
    {
      "epoch": 0.64,
      "learning_rate": 8.577829294272992e-06,
      "loss": 0.0206,
      "reward": 1.4951,
      "step": 5449
    },
    {
      "epoch": 0.65,
      "learning_rate": 8.328519851463702e-06,
      "loss": 0.0207,
      "reward": 1.5987,
      "step": 5499
    },
    {
      "epoch": 0.65,
      "learning_rate": 8.08148710569524e-06,
      "loss": 0.0202,
      "reward": 1.5224,
      "step": 5549
    },
    {
      "epoch": 0.66,
      "learning_rate": 7.836815358907908e-06,
      "loss": 0.0195,
      "reward": 1.5981,
      "step": 5599
    },
    {
      "epoch": 0.66,
      "learning_rate": 7.594588107331857e-06,
      "loss": 0.0198,
      "reward": 1.3337,
      "step": 5649
    },
    {
      "epoch": 0.67,
      "learning_rate": 7.354888012993293e-06,
      "loss": 0.0194,
      "reward": 1.503,
      "step": 5699
    },
    {
      "epoch": 0.68,
      "learning_rate": 7.117796875505393e-06,
      "loss": 0.0192,
      "reward": 1.3961,
      "step": 5749
    },
    {
      "epoch": 0.68,
      "learning_rate": 6.883395604153524e-06,
      "loss": 0.0204,
      "reward": 1.5568,
      "step": 5799
    },
    {
      "epoch": 0.69,
      "learning_rate": 6.651764190284266e-06,
      "loss": 0.0195,
      "reward": 1.4106,
      "step": 5849
    },
    {
      "epoch": 0.69,
      "learning_rate": 6.422981680007759e-06,
      "loss": 0.0191,
      "reward": 1.5962,
      "step": 5899
    },
    {
      "epoch": 0.7,
      "learning_rate": 6.197126147222517e-06,
      "loss": 0.0208,
      "reward": 1.5746,
      "step": 5949
    },
    {
      "epoch": 0.71,
      "learning_rate": 5.974274666972112e-06,
      "loss": 0.0201,
      "reward": 1.2134,
      "step": 5999
    },
    {
      "epoch": 0.71,
      "learning_rate": 5.754503289142692e-06,
      "loss": 0.0198,
      "reward": 1.6037,
      "step": 6049
    },
    {
      "epoch": 0.72,
      "learning_rate": 5.537887012510291e-06,
      "loss": 0.0199,
      "reward": 1.5427,
      "step": 6099
    },
    {
      "epoch": 0.72,
      "learning_rate": 5.324499759146934e-06,
      "loss": 0.0202,
      "reward": 1.5012,
      "step": 6149
    },
    {
      "epoch": 0.73,
      "learning_rate": 5.11441434919409e-06,
      "loss": 0.019,
      "reward": 1.6545,
      "step": 6199
    },
    {
      "epoch": 0.74,
      "learning_rate": 4.907702476012234e-06,
      "loss": 0.0187,
      "reward": 1.529,
      "step": 6249
    },
    {
      "epoch": 0.74,
      "learning_rate": 4.704434681714884e-06,
      "loss": 0.0195,
      "reward": 1.7154,
      "step": 6299
    },
    {
      "epoch": 0.75,
      "learning_rate": 4.504680333095542e-06,
      "loss": 0.0206,
      "reward": 1.549,
      "step": 6349
    },
    {
      "epoch": 0.75,
      "learning_rate": 4.308507597955685e-06,
      "loss": 0.0194,
      "reward": 1.7198,
      "step": 6399
    },
    {
      "epoch": 0.76,
      "learning_rate": 4.115983421841979e-06,
      "loss": 0.0194,
      "reward": 1.298,
      "step": 6449
    },
    {
      "epoch": 0.76,
      "learning_rate": 3.927173505200547e-06,
      "loss": 0.0196,
      "reward": 1.5776,
      "step": 6499
    },
    {
      "epoch": 0.77,
      "learning_rate": 3.742142280956153e-06,
      "loss": 0.0194,
      "reward": 1.4295,
      "step": 6549
    },
    {
      "epoch": 0.78,
      "learning_rate": 3.5609528925239476e-06,
      "loss": 0.0194,
      "reward": 1.4245,
      "step": 6599
    },
    {
      "epoch": 0.78,
      "learning_rate": 3.3836671722612646e-06,
      "loss": 0.0194,
      "reward": 1.5306,
      "step": 6649
    },
    {
      "epoch": 0.79,
      "learning_rate": 3.2103456203668223e-06,
      "loss": 0.0201,
      "reward": 1.4046,
      "step": 6699
    },
    {
      "epoch": 0.79,
      "learning_rate": 3.041047384234521e-06,
      "loss": 0.0178,
      "reward": 1.5582,
      "step": 6749
    },
    {
      "epoch": 0.8,
      "learning_rate": 2.875830238268942e-06,
      "loss": 0.0193,
      "reward": 1.4851,
      "step": 6799
    },
    {
      "epoch": 0.81,
      "learning_rate": 2.714750564169339e-06,
      "loss": 0.019,
      "reward": 1.5795,
      "step": 6849
    },
    {
      "epoch": 0.81,
      "learning_rate": 2.557863331688927e-06,
      "loss": 0.0193,
      "reward": 1.5771,
      "step": 6899
    },
    {
      "epoch": 0.82,
      "learning_rate": 2.405222079876017e-06,
      "loss": 0.0197,
      "reward": 1.4866,
      "step": 6949
    },
    {
      "epoch": 0.82,
      "learning_rate": 2.256878898803354e-06,
      "loss": 0.0198,
      "reward": 1.4232,
      "step": 6999
    },
    {
      "epoch": 0.83,
      "learning_rate": 2.112884411791984e-06,
      "loss": 0.0196,
      "reward": 1.5922,
      "step": 7049
    },
    {
      "epoch": 0.83,
      "learning_rate": 1.9732877581356075e-06,
      "loss": 0.0196,
      "reward": 1.5317,
      "step": 7099
    },
    {
      "epoch": 0.84,
      "learning_rate": 1.8381365763314151e-06,
      "loss": 0.019,
      "reward": 1.4884,
      "step": 7149
    },
    {
      "epoch": 0.85,
      "learning_rate": 1.7074769878230494e-06,
      "loss": 0.0181,
      "reward": 1.589,
      "step": 7199
    },
    {
      "epoch": 0.85,
      "learning_rate": 1.5813535812612856e-06,
      "loss": 0.019,
      "reward": 1.5272,
      "step": 7249
    },
    {
      "epoch": 0.86,
      "learning_rate": 1.4598093972878007e-06,
      "loss": 0.0204,
      "reward": 1.5452,
      "step": 7299
    },
    {
      "epoch": 0.86,
      "learning_rate": 1.3428859138471839e-06,
      "loss": 0.0188,
      "reward": 1.6511,
      "step": 7349
    },
    {
      "epoch": 0.87,
      "learning_rate": 1.2306230320322798e-06,
      "loss": 0.0192,
      "reward": 1.3072,
      "step": 7399
    },
    {
      "epoch": 0.88,
      "learning_rate": 1.1230590624675747e-06,
      "loss": 0.0194,
      "reward": 1.6043,
      "step": 7449
    },
    {
      "epoch": 0.88,
      "learning_rate": 1.0202307122354288e-06,
      "loss": 0.0185,
      "reward": 1.5806,
      "step": 7499
    },
    {
      "epoch": 0.89,
      "learning_rate": 9.221730723494504e-07,
      "loss": 0.0187,
      "reward": 1.3901,
      "step": 7549
    },
    {
      "epoch": 0.89,
      "learning_rate": 8.289196057794096e-07,
      "loss": 0.019,
      "reward": 1.6659,
      "step": 7599
    },
    {
      "epoch": 0.9,
      "learning_rate": 7.405021360317366e-07,
      "loss": 0.0192,
      "reward": 1.3981,
      "step": 7649
    },
    {
      "epoch": 0.91,
      "learning_rate": 6.569508362894783e-07,
      "loss": 0.0182,
      "reward": 1.6831,
      "step": 7699
    },
    {
      "epoch": 0.91,
      "learning_rate": 5.782942191154622e-07,
      "loss": 0.0188,
      "reward": 1.4812,
      "step": 7749
    },
    {
      "epoch": 0.92,
      "learning_rate": 5.045591267221461e-07,
      "loss": 0.0187,
      "reward": 1.7532,
      "step": 7799
    },
    {
      "epoch": 0.92,
      "learning_rate": 4.3577072181150035e-07,
      "loss": 0.0185,
      "reward": 1.6008,
      "step": 7849
    },
    {
      "epoch": 0.93,
      "learning_rate": 3.719524789880202e-07,
      "loss": 0.0192,
      "reward": 1.8267,
      "step": 7899
    },
    {
      "epoch": 0.93,
      "learning_rate": 3.1312617674783385e-07,
      "loss": 0.0188,
      "reward": 1.8393,
      "step": 7949
    },
    {
      "epoch": 0.94,
      "learning_rate": 2.5931189004661406e-07,
      "loss": 0.0182,
      "reward": 1.4103,
      "step": 7999
    },
    {
      "epoch": 0.95,
      "learning_rate": 2.1052798344882495e-07,
      "loss": 0.0187,
      "reward": 1.4023,
      "step": 8049
    },
    {
      "epoch": 0.95,
      "learning_rate": 1.667911048606785e-07,
      "loss": 0.0192,
      "reward": 1.5402,
      "step": 8099
    },
    {
      "epoch": 0.96,
      "learning_rate": 1.2811617984889056e-07,
      "loss": 0.0182,
      "reward": 1.5328,
      "step": 8149
    },
    {
      "epoch": 0.96,
      "learning_rate": 9.451640654721538e-08,
      "loss": 0.0183,
      "reward": 1.7633,
      "step": 8199
    },
    {
      "epoch": 0.97,
      "learning_rate": 6.600325115246831e-08,
      "loss": 0.0183,
      "reward": 1.5819,
      "step": 8249
    },
    {
      "epoch": 0.98,
      "learning_rate": 4.2586444011600835e-08,
      "loss": 0.0183,
      "reward": 1.6798,
      "step": 8299
    },
    {
      "epoch": 0.98,
      "learning_rate": 2.4273976301131818e-08,
      "loss": 0.0193,
      "reward": 1.742,
      "step": 8349
    },
    {
      "epoch": 0.99,
      "learning_rate": 1.1072097300102168e-08,
      "loss": 0.0189,
      "reward": 1.4572,
      "step": 8399
    },
    {
      "epoch": 0.99,
      "learning_rate": 2.98531225744747e-09,
      "loss": 0.0179,
      "reward": 1.4872,
      "step": 8449
    },
    {
      "epoch": 1.0,
      "learning_rate": 1.6380854554465253e-11,
      "loss": 0.0185,
      "reward": 1.9113,
      "step": 8499
    }
  ],
  "max_steps": 8502,
  "num_train_epochs": 1.0,
  "total_flos": 0,
  "trial_name": null,
  "trial_params": null
}