{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 1.992,
  "eval_steps": 500,
  "global_step": 125,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "completion_length": 140.9583396911621,
      "epoch": 0.016,
      "grad_norm": 1.4258953228320013,
      "kl": 0.0,
      "learning_rate": 1.25e-07,
      "loss": 0.0,
      "reward": 0.5152640044689178,
      "reward_std": 0.5508254170417786,
      "rewards/correct_code_reward_func": 0.2291666716337204,
      "rewards/len_reward_func": 0.28609737753868103,
      "step": 1
    },
    {
      "completion_length": 131.50000762939453,
      "epoch": 0.032,
      "grad_norm": 1.1519258687122351,
      "kl": 0.0,
      "learning_rate": 2.5e-07,
      "loss": 0.0,
      "reward": 0.541226252913475,
      "reward_std": 0.5189632624387741,
      "rewards/correct_code_reward_func": 0.2500000111758709,
      "rewards/len_reward_func": 0.29122625291347504,
      "step": 2
    },
    {
      "completion_length": 108.83333587646484,
      "epoch": 0.048,
      "grad_norm": 1.467116667329371,
      "kl": 0.00013637542724609375,
      "learning_rate": 3.75e-07,
      "loss": 0.0,
      "reward": 0.7587994039058685,
      "reward_std": 0.5140225142240524,
      "rewards/correct_code_reward_func": 0.5416666865348816,
      "rewards/len_reward_func": 0.21713273972272873,
      "step": 3
    },
    {
      "completion_length": 159.81250762939453,
      "epoch": 0.064,
      "grad_norm": 1.2682485669137435,
      "kl": 0.00018215179443359375,
      "learning_rate": 5e-07,
      "loss": 0.0,
      "reward": 0.5178248882293701,
      "reward_std": 0.4526914358139038,
      "rewards/correct_code_reward_func": 0.1666666716337204,
      "rewards/len_reward_func": 0.3511582016944885,
      "step": 4
    },
    {
      "completion_length": 176.56250762939453,
      "epoch": 0.08,
      "grad_norm": 1.2033440109589688,
      "kl": 0.00014066696166992188,
      "learning_rate": 4.999157413258781e-07,
      "loss": 0.0,
      "reward": 0.32241350412368774,
      "reward_std": 0.32281263172626495,
      "rewards/correct_code_reward_func": 0.02083333395421505,
      "rewards/len_reward_func": 0.30158019065856934,
      "step": 5
    },
    {
      "completion_length": 124.87500762939453,
      "epoch": 0.096,
      "grad_norm": 1.5120707071506325,
      "kl": 0.00016808509826660156,
      "learning_rate": 4.996630220997057e-07,
      "loss": 0.0,
      "reward": 0.746085911989212,
      "reward_std": 0.5452268123626709,
      "rewards/correct_code_reward_func": 0.4583333432674408,
      "rewards/len_reward_func": 0.28775252401828766,
      "step": 6
    },
    {
      "completion_length": 169.9166717529297,
      "epoch": 0.112,
      "grad_norm": 0.9079518632617903,
      "kl": 0.00011348724365234375,
      "learning_rate": 4.992420126717784e-07,
      "loss": 0.0,
      "reward": 0.36989694088697433,
      "reward_std": 0.45903605222702026,
      "rewards/correct_code_reward_func": 0.125,
      "rewards/len_reward_func": 0.24489693343639374,
      "step": 7
    },
    {
      "completion_length": 219.43750762939453,
      "epoch": 0.128,
      "grad_norm": 1.2633142753352289,
      "kl": 0.0002155303955078125,
      "learning_rate": 4.986529968316653e-07,
      "loss": 0.0,
      "reward": 0.44794920086860657,
      "reward_std": 0.385338693857193,
      "rewards/correct_code_reward_func": 0.1250000037252903,
      "rewards/len_reward_func": 0.3229491859674454,
      "step": 8
    },
    {
      "completion_length": 227.91667938232422,
      "epoch": 0.144,
      "grad_norm": 1.0211344567101885,
      "kl": 0.00011777877807617188,
      "learning_rate": 4.978963716169165e-07,
      "loss": 0.0,
      "reward": 0.6235890090465546,
      "reward_std": 0.5187947303056717,
      "rewards/correct_code_reward_func": 0.3125,
      "rewards/len_reward_func": 0.31108900904655457,
      "step": 9
    },
    {
      "completion_length": 188.25000762939453,
      "epoch": 0.16,
      "grad_norm": 1.0353822839723037,
      "kl": 0.00011730194091796875,
      "learning_rate": 4.969726470454313e-07,
      "loss": 0.0,
      "reward": 0.6911160051822662,
      "reward_std": 0.5456923246383667,
      "rewards/correct_code_reward_func": 0.4166666865348816,
      "rewards/len_reward_func": 0.27444930374622345,
      "step": 10
    },
    {
      "completion_length": 168.27083587646484,
      "epoch": 0.176,
      "grad_norm": 1.7856755608823207,
      "kl": 0.00018310546875,
      "learning_rate": 4.958824457716706e-07,
      "loss": 0.0,
      "reward": 0.4588584154844284,
      "reward_std": 0.40716809034347534,
      "rewards/correct_code_reward_func": 0.1875,
      "rewards/len_reward_func": 0.271358385682106,
      "step": 11
    },
    {
      "completion_length": 203.08333587646484,
      "epoch": 0.192,
      "grad_norm": 0.9296992149271633,
      "kl": 0.00016641616821289062,
      "learning_rate": 4.946265026669454e-07,
      "loss": 0.0,
      "reward": 0.3501324951648712,
      "reward_std": 0.49003708362579346,
      "rewards/correct_code_reward_func": 0.1041666679084301,
      "rewards/len_reward_func": 0.245965838432312,
      "step": 12
    },
    {
      "completion_length": 115.66666793823242,
      "epoch": 0.208,
      "grad_norm": 1.4335533212366607,
      "kl": 0.00016570091247558594,
      "learning_rate": 4.932056643240618e-07,
      "loss": 0.0,
      "reward": 0.7853705883026123,
      "reward_std": 0.46111349761486053,
      "rewards/correct_code_reward_func": 0.5000000149011612,
      "rewards/len_reward_func": 0.2853705883026123,
      "step": 13
    },
    {
      "completion_length": 169.95833587646484,
      "epoch": 0.224,
      "grad_norm": 1.2723280538596287,
      "kl": 0.00021076202392578125,
      "learning_rate": 4.916208884866592e-07,
      "loss": 0.0,
      "reward": 0.5324039310216904,
      "reward_std": 0.5338821411132812,
      "rewards/correct_code_reward_func": 0.2708333432674408,
      "rewards/len_reward_func": 0.26157061755657196,
      "step": 14
    },
    {
      "completion_length": 154.58333587646484,
      "epoch": 0.24,
      "grad_norm": 1.2578666329332273,
      "kl": 0.00019168853759765625,
      "learning_rate": 4.898732434036243e-07,
      "loss": 0.0,
      "reward": 0.5949100255966187,
      "reward_std": 0.5048613250255585,
      "rewards/correct_code_reward_func": 0.3125000149011612,
      "rewards/len_reward_func": 0.28241002559661865,
      "step": 15
    },
    {
      "completion_length": 173.1875114440918,
      "epoch": 0.256,
      "grad_norm": 1.1230347862341579,
      "kl": 0.00029277801513671875,
      "learning_rate": 4.879639071090173e-07,
      "loss": 0.0,
      "reward": 0.4564344882965088,
      "reward_std": 0.4671656936407089,
      "rewards/correct_code_reward_func": 0.1666666679084301,
      "rewards/len_reward_func": 0.2897678166627884,
      "step": 16
    },
    {
      "completion_length": 169.375,
      "epoch": 0.272,
      "grad_norm": 1.3041956300758726,
      "kl": 0.0002574920654296875,
      "learning_rate": 4.858941666279955e-07,
      "loss": 0.0,
      "reward": 0.6347246468067169,
      "reward_std": 0.5289804339408875,
      "rewards/correct_code_reward_func": 0.3541666716337204,
      "rewards/len_reward_func": 0.2805579602718353,
      "step": 17
    },
    {
      "completion_length": 133.25000762939453,
      "epoch": 0.288,
      "grad_norm": 1.354822217310785,
      "kl": 0.0002689361572265625,
      "learning_rate": 4.836654171092682e-07,
      "loss": 0.0,
      "reward": 0.5779364109039307,
      "reward_std": 0.4782462567090988,
      "rewards/correct_code_reward_func": 0.2916666716337204,
      "rewards/len_reward_func": 0.2862697243690491,
      "step": 18
    },
    {
      "completion_length": 99.41667175292969,
      "epoch": 0.304,
      "grad_norm": 1.4087777232916079,
      "kl": 0.00031757354736328125,
      "learning_rate": 4.812791608846709e-07,
      "loss": 0.0,
      "reward": 0.5035808980464935,
      "reward_std": 0.46289560198783875,
      "rewards/correct_code_reward_func": 0.229166679084301,
      "rewards/len_reward_func": 0.27441420406103134,
      "step": 19
    },
    {
      "completion_length": 170.7291717529297,
      "epoch": 0.32,
      "grad_norm": 0.9923230664440412,
      "kl": 0.00028705596923828125,
      "learning_rate": 4.787370064564882e-07,
      "loss": 0.0,
      "reward": 0.5567075908184052,
      "reward_std": 0.44439028203487396,
      "rewards/correct_code_reward_func": 0.2083333432674408,
      "rewards/len_reward_func": 0.34837424755096436,
      "step": 20
    },
    {
      "completion_length": 124.72917175292969,
      "epoch": 0.336,
      "grad_norm": 1.2245791922735345,
      "kl": 0.00035572052001953125,
      "learning_rate": 4.7604066741321253e-07,
      "loss": 0.0,
      "reward": 0.8560027182102203,
      "reward_std": 0.6356588900089264,
      "rewards/correct_code_reward_func": 0.5416666865348816,
      "rewards/len_reward_func": 0.31433598697185516,
      "step": 21
    },
    {
      "completion_length": 123.64583969116211,
      "epoch": 0.352,
      "grad_norm": 1.2080469812565267,
      "kl": 0.00035858154296875,
      "learning_rate": 4.731919612744659e-07,
      "loss": 0.0,
      "reward": 0.7242447733879089,
      "reward_std": 0.4742405414581299,
      "rewards/correct_code_reward_func": 0.3958333432674408,
      "rewards/len_reward_func": 0.32841143012046814,
      "step": 22
    },
    {
      "completion_length": 146.2916717529297,
      "epoch": 0.368,
      "grad_norm": 1.2440640880474592,
      "kl": 0.00040721893310546875,
      "learning_rate": 4.7019280826586604e-07,
      "loss": 0.0,
      "reward": 0.5270938575267792,
      "reward_std": 0.4260385036468506,
      "rewards/correct_code_reward_func": 0.2291666679084301,
      "rewards/len_reward_func": 0.2979271858930588,
      "step": 23
    },
    {
      "completion_length": 141.9166717529297,
      "epoch": 0.384,
      "grad_norm": 1.455943571941334,
      "kl": 0.0006427764892578125,
      "learning_rate": 4.6704523002466094e-07,
      "loss": 0.0,
      "reward": 0.5917265266180038,
      "reward_std": 0.47722122073173523,
      "rewards/correct_code_reward_func": 0.3333333358168602,
      "rewards/len_reward_func": 0.25839313119649887,
      "step": 24
    },
    {
      "completion_length": 240.85417938232422,
      "epoch": 0.4,
      "grad_norm": 0.8411889507435418,
      "kl": 0.0003604888916015625,
      "learning_rate": 4.6375134823700503e-07,
      "loss": 0.0,
      "reward": 0.3353981524705887,
      "reward_std": 0.351834774017334,
      "rewards/correct_code_reward_func": 0.0833333358168602,
      "rewards/len_reward_func": 0.2520648390054703,
      "step": 25
    },
    {
      "completion_length": 97.31250381469727,
      "epoch": 0.416,
      "grad_norm": 1.374585753278975,
      "kl": 0.0008258819580078125,
      "learning_rate": 4.603133832077953e-07,
      "loss": 0.0,
      "reward": 0.6881800889968872,
      "reward_std": 0.5626422464847565,
      "rewards/correct_code_reward_func": 0.4375,
      "rewards/len_reward_func": 0.2506800442934036,
      "step": 26
    },
    {
      "completion_length": 131.08333587646484,
      "epoch": 0.432,
      "grad_norm": 1.5040369557196518,
      "kl": 0.0006847381591796875,
      "learning_rate": 4.5673365236403216e-07,
      "loss": 0.0,
      "reward": 0.6470239758491516,
      "reward_std": 0.39606642723083496,
      "rewards/correct_code_reward_func": 0.4375,
      "rewards/len_reward_func": 0.20952393114566803,
      "step": 27
    },
    {
      "completion_length": 198.06250762939453,
      "epoch": 0.448,
      "grad_norm": 1.1110007536297855,
      "kl": 0.00054168701171875,
      "learning_rate": 4.530145686927125e-07,
      "loss": 0.0,
      "reward": 0.5166794955730438,
      "reward_std": 0.504486620426178,
      "rewards/correct_code_reward_func": 0.2500000149011612,
      "rewards/len_reward_func": 0.2666794955730438,
      "step": 28
    },
    {
      "completion_length": 152.52083587646484,
      "epoch": 0.464,
      "grad_norm": 1.134262039216797,
      "kl": 0.00078582763671875,
      "learning_rate": 4.4915863911430897e-07,
      "loss": 0.0,
      "reward": 0.5144253522157669,
      "reward_std": 0.4733017832040787,
      "rewards/correct_code_reward_func": 0.1875000111758709,
      "rewards/len_reward_func": 0.3269253224134445,
      "step": 29
    },
    {
      "completion_length": 139.7916717529297,
      "epoch": 0.48,
      "grad_norm": 1.010573889887009,
      "kl": 0.0007152557373046875,
      "learning_rate": 4.45168462792932e-07,
      "loss": 0.0,
      "reward": 0.5882390439510345,
      "reward_std": 0.43310636281967163,
      "rewards/correct_code_reward_func": 0.2500000074505806,
      "rewards/len_reward_func": 0.33823904395103455,
      "step": 30
    },
    {
      "completion_length": 87.41666793823242,
      "epoch": 0.496,
      "grad_norm": 1.540244950569226,
      "kl": 0.0012340545654296875,
      "learning_rate": 4.4104672938431223e-07,
      "loss": 0.0,
      "reward": 0.7711681425571442,
      "reward_std": 0.4805651605129242,
      "rewards/correct_code_reward_func": 0.5833333432674408,
      "rewards/len_reward_func": 0.18783476203680038,
      "step": 31
    },
    {
      "completion_length": 101.43750381469727,
      "epoch": 0.512,
      "grad_norm": 2.3673085026520297,
      "kl": 0.0012607574462890625,
      "learning_rate": 4.367962172227866e-07,
      "loss": 0.0,
      "reward": 0.7279457449913025,
      "reward_std": 0.4627054035663605,
      "rewards/correct_code_reward_func": 0.4583333432674408,
      "rewards/len_reward_func": 0.2696124166250229,
      "step": 32
    },
    {
      "completion_length": 155.2291717529297,
      "epoch": 0.528,
      "grad_norm": 1.2624598609488873,
      "kl": 0.00139617919921875,
      "learning_rate": 4.324197914485075e-07,
      "loss": 0.0,
      "reward": 0.6401492655277252,
      "reward_std": 0.515736848115921,
      "rewards/correct_code_reward_func": 0.375,
      "rewards/len_reward_func": 0.26514923572540283,
      "step": 33
    },
    {
      "completion_length": 252.91667938232422,
      "epoch": 0.544,
      "grad_norm": 1.043728438493038,
      "kl": 0.0008392333984375,
      "learning_rate": 4.2792040207614e-07,
      "loss": 0.0,
      "reward": 0.6339870393276215,
      "reward_std": 0.5688490867614746,
      "rewards/correct_code_reward_func": 0.3333333432674408,
      "rewards/len_reward_func": 0.30065372586250305,
      "step": 34
    },
    {
      "completion_length": 178.25,
      "epoch": 0.56,
      "grad_norm": 1.2442169258805433,
      "kl": 0.00205230712890625,
      "learning_rate": 4.2330108200634723e-07,
      "loss": 0.0,
      "reward": 0.43357332795858383,
      "reward_std": 0.3690243661403656,
      "rewards/correct_code_reward_func": 0.16666667722165585,
      "rewards/len_reward_func": 0.26690666377544403,
      "step": 35
    },
    {
      "completion_length": 150.1666717529297,
      "epoch": 0.576,
      "grad_norm": 1.0937981889230137,
      "kl": 0.0016021728515625,
      "learning_rate": 4.185649449814045e-07,
      "loss": 0.0,
      "reward": 0.8725252151489258,
      "reward_std": 0.5368492603302002,
      "rewards/correct_code_reward_func": 0.5416666865348816,
      "rewards/len_reward_func": 0.3308584541082382,
      "step": 36
    },
    {
      "completion_length": 74.41666793823242,
      "epoch": 0.592,
      "grad_norm": 1.4560552034278569,
      "kl": 0.0020904541015625,
      "learning_rate": 4.137151834863213e-07,
      "loss": 0.0,
      "reward": 0.7634576857089996,
      "reward_std": 0.5292592346668243,
      "rewards/correct_code_reward_func": 0.5416666716337204,
      "rewards/len_reward_func": 0.22179099917411804,
      "step": 37
    },
    {
      "completion_length": 111.77083587646484,
      "epoch": 0.608,
      "grad_norm": 1.6125607277054597,
      "kl": 0.002716064453125,
      "learning_rate": 4.087550665968846e-07,
      "loss": 0.0,
      "reward": 0.6047167330980301,
      "reward_std": 0.4415762424468994,
      "rewards/correct_code_reward_func": 0.2916666865348816,
      "rewards/len_reward_func": 0.3130500763654709,
      "step": 38
    },
    {
      "completion_length": 87.0625,
      "epoch": 0.624,
      "grad_norm": 2.0747921723056026,
      "kl": 0.0023193359375,
      "learning_rate": 4.036879377760752e-07,
      "loss": 0.0,
      "reward": 0.7261738479137421,
      "reward_std": 0.6433705389499664,
      "rewards/correct_code_reward_func": 0.520833358168602,
      "rewards/len_reward_func": 0.20534051209688187,
      "step": 39
    },
    {
      "completion_length": 128.0833396911621,
      "epoch": 0.64,
      "grad_norm": 1.352520841789316,
      "kl": 0.00229644775390625,
      "learning_rate": 3.9851721262034157e-07,
      "loss": 0.0,
      "reward": 0.49166351556777954,
      "reward_std": 0.4290030002593994,
      "rewards/correct_code_reward_func": 0.18750000558793545,
      "rewards/len_reward_func": 0.30416350066661835,
      "step": 40
    },
    {
      "completion_length": 117.33333587646484,
      "epoch": 0.656,
      "grad_norm": 1.5281074207353524,
      "kl": 0.003509521484375,
      "learning_rate": 3.932463765572505e-07,
      "loss": 0.0,
      "reward": 0.5800679922103882,
      "reward_std": 0.5416670143604279,
      "rewards/correct_code_reward_func": 0.3125000149011612,
      "rewards/len_reward_func": 0.2675679475069046,
      "step": 41
    },
    {
      "completion_length": 112.43750381469727,
      "epoch": 0.672,
      "grad_norm": 1.2084984435618142,
      "kl": 0.00252532958984375,
      "learning_rate": 3.8787898249606767e-07,
      "loss": 0.0,
      "reward": 0.42490366101264954,
      "reward_std": 0.46323399245738983,
      "rewards/correct_code_reward_func": 0.14583333395421505,
      "rewards/len_reward_func": 0.27907034754753113,
      "step": 42
    },
    {
      "completion_length": 56.85416793823242,
      "epoch": 0.688,
      "grad_norm": 1.8756323954488632,
      "kl": 0.00452423095703125,
      "learning_rate": 3.8241864843284964e-07,
      "loss": 0.0,
      "reward": 0.7274035811424255,
      "reward_std": 0.5209662765264511,
      "rewards/correct_code_reward_func": 0.5000000149011612,
      "rewards/len_reward_func": 0.22740358859300613,
      "step": 43
    },
    {
      "completion_length": 153.68750762939453,
      "epoch": 0.704,
      "grad_norm": 1.785627080388602,
      "kl": 0.0055084228515625,
      "learning_rate": 3.768690550116639e-07,
      "loss": 0.0,
      "reward": 0.49254634976387024,
      "reward_std": 0.4052678644657135,
      "rewards/correct_code_reward_func": 0.1666666716337204,
      "rewards/len_reward_func": 0.32587967813014984,
      "step": 44
    },
    {
      "completion_length": 170.1041717529297,
      "epoch": 0.72,
      "grad_norm": 1.2057879792669277,
      "kl": 0.0038299560546875,
      "learning_rate": 3.712339430435792e-07,
      "loss": 0.0,
      "reward": 0.5373264253139496,
      "reward_std": 0.4612013250589371,
      "rewards/correct_code_reward_func": 0.2708333432674408,
      "rewards/len_reward_func": 0.2664930745959282,
      "step": 45
    },
    {
      "completion_length": 122.79167175292969,
      "epoch": 0.736,
      "grad_norm": 1.23844328247912,
      "kl": 0.00384521484375,
      "learning_rate": 3.65517110985099e-07,
      "loss": 0.0,
      "reward": 0.6534424722194672,
      "reward_std": 0.5896010398864746,
      "rewards/correct_code_reward_func": 0.354166679084301,
      "rewards/len_reward_func": 0.29927581548690796,
      "step": 46
    },
    {
      "completion_length": 73.39583396911621,
      "epoch": 0.752,
      "grad_norm": 2.222315006145743,
      "kl": 0.0058135986328125,
      "learning_rate": 3.597224123777389e-07,
      "loss": 0.0,
      "reward": 0.7357015609741211,
      "reward_std": 0.5119403451681137,
      "rewards/correct_code_reward_func": 0.4583333432674408,
      "rewards/len_reward_func": 0.2773682177066803,
      "step": 47
    },
    {
      "completion_length": 75.54166793823242,
      "epoch": 0.768,
      "grad_norm": 1.9981519435567456,
      "kl": 0.0053863525390625,
      "learning_rate": 3.5385375325047163e-07,
      "loss": 0.0,
      "reward": 0.6428782939910889,
      "reward_std": 0.6202229559421539,
      "rewards/correct_code_reward_func": 0.3958333432674408,
      "rewards/len_reward_func": 0.24704494327306747,
      "step": 48
    },
    {
      "completion_length": 73.27083587646484,
      "epoch": 0.784,
      "grad_norm": 2.073070842958071,
      "kl": 0.00554656982421875,
      "learning_rate": 3.479150894867926e-07,
      "loss": 0.0,
      "reward": 0.8005061745643616,
      "reward_std": 0.5489170849323273,
      "rewards/correct_code_reward_func": 0.5416666865348816,
      "rewards/len_reward_func": 0.25883948802948,
      "step": 49
    },
    {
      "completion_length": 93.62500381469727,
      "epoch": 0.8,
      "grad_norm": 1.7280406240103203,
      "kl": 0.0070953369140625,
      "learning_rate": 3.4191042415818e-07,
      "loss": 0.0,
      "reward": 0.6382943987846375,
      "reward_std": 0.4014574736356735,
      "rewards/correct_code_reward_func": 0.3750000149011612,
      "rewards/len_reward_func": 0.26329439133405685,
      "step": 50
    },
    {
      "completion_length": 110.31250381469727,
      "epoch": 0.816,
      "grad_norm": 1.5732703630042588,
      "kl": 0.008453369140625,
      "learning_rate": 3.3584380482574717e-07,
      "loss": 0.0,
      "reward": 0.8389279842376709,
      "reward_std": 0.6495693922042847,
      "rewards/correct_code_reward_func": 0.5208333432674408,
      "rewards/len_reward_func": 0.31809471547603607,
      "step": 51
    },
    {
      "completion_length": 81.4375,
      "epoch": 0.832,
      "grad_norm": 1.3555162901411408,
      "kl": 0.0072479248046875,
      "learning_rate": 3.297193208119047e-07,
      "loss": 0.0,
      "reward": 0.7050519585609436,
      "reward_std": 0.522288054227829,
      "rewards/correct_code_reward_func": 0.4375000298023224,
      "rewards/len_reward_func": 0.2675519585609436,
      "step": 52
    },
    {
      "completion_length": 145.2291717529297,
      "epoch": 0.848,
      "grad_norm": 1.2256688073258564,
      "kl": 0.00726318359375,
      "learning_rate": 3.235411004438741e-07,
      "loss": 0.0,
      "reward": 0.6400169730186462,
      "reward_std": 0.5816708207130432,
      "rewards/correct_code_reward_func": 0.3541666716337204,
      "rewards/len_reward_func": 0.28585030883550644,
      "step": 53
    },
    {
      "completion_length": 120.20833587646484,
      "epoch": 0.864,
      "grad_norm": 1.8462631631415796,
      "kl": 0.0084991455078125,
      "learning_rate": 3.173133082709086e-07,
      "loss": 0.0,
      "reward": 0.643402487039566,
      "reward_std": 0.3417808264493942,
      "rewards/correct_code_reward_func": 0.3333333432674408,
      "rewards/len_reward_func": 0.31006917357444763,
      "step": 54
    },
    {
      "completion_length": 55.56250190734863,
      "epoch": 0.88,
      "grad_norm": 1.7370166581779802,
      "kl": 0.01177978515625,
      "learning_rate": 3.1104014225709784e-07,
      "loss": 0.0,
      "reward": 0.9137917459011078,
      "reward_std": 0.5003669559955597,
      "rewards/correct_code_reward_func": 0.583333358168602,
      "rewards/len_reward_func": 0.3304583728313446,
      "step": 55
    },
    {
      "completion_length": 189.25000762939453,
      "epoch": 0.896,
      "grad_norm": 1.2196760565152192,
      "kl": 0.0058441162109375,
      "learning_rate": 3.0472583095164873e-07,
      "loss": 0.0,
      "reward": 0.4673280417919159,
      "reward_std": 0.4577627182006836,
      "rewards/correct_code_reward_func": 0.1666666716337204,
      "rewards/len_reward_func": 0.3006613999605179,
      "step": 56
    },
    {
      "completion_length": 57.37500190734863,
      "epoch": 0.912,
      "grad_norm": 2.0919947468048976,
      "kl": 0.010162353515625,
      "learning_rate": 2.983746306385499e-07,
      "loss": 0.0,
      "reward": 0.6931174695491791,
      "reward_std": 0.5172313153743744,
      "rewards/correct_code_reward_func": 0.4791666865348816,
      "rewards/len_reward_func": 0.21395081281661987,
      "step": 57
    },
    {
      "completion_length": 86.00000190734863,
      "epoch": 0.928,
      "grad_norm": 1.5907089477428527,
      "kl": 0.0113677978515625,
      "learning_rate": 2.919908224675412e-07,
      "loss": 0.0,
      "reward": 0.5865814685821533,
      "reward_std": 0.5177368223667145,
      "rewards/correct_code_reward_func": 0.3125000149011612,
      "rewards/len_reward_func": 0.27408143877983093,
      "step": 58
    },
    {
      "completion_length": 90.72916793823242,
      "epoch": 0.944,
      "grad_norm": 1.1269292807249032,
      "kl": 0.00830078125,
      "learning_rate": 2.8557870956832133e-07,
      "loss": 0.0,
      "reward": 0.4935041069984436,
      "reward_std": 0.41843119263648987,
      "rewards/correct_code_reward_func": 0.2083333432674408,
      "rewards/len_reward_func": 0.285170778632164,
      "step": 59
    },
    {
      "completion_length": 85.60416793823242,
      "epoch": 0.96,
      "grad_norm": 2.320388470663489,
      "kl": 0.014678955078125,
      "learning_rate": 2.7914261414993976e-07,
      "loss": 0.0,
      "reward": 0.7554058134555817,
      "reward_std": 0.5069911777973175,
      "rewards/correct_code_reward_func": 0.4166666716337204,
      "rewards/len_reward_func": 0.3387391269207001,
      "step": 60
    },
    {
      "completion_length": 63.375,
      "epoch": 0.976,
      "grad_norm": 1.7319214973496064,
      "kl": 0.02532958984375,
      "learning_rate": 2.726868745873286e-07,
      "loss": 0.0,
      "reward": 0.7839343547821045,
      "reward_std": 0.6209487617015839,
      "rewards/correct_code_reward_func": 0.4791666716337204,
      "rewards/len_reward_func": 0.3047676384449005,
      "step": 61
    },
    {
      "completion_length": 87.14583587646484,
      "epoch": 0.992,
      "grad_norm": 1.8272498546531741,
      "kl": 0.0134735107421875,
      "learning_rate": 2.662158424969357e-07,
      "loss": 0.0,
      "reward": 0.8219521045684814,
      "reward_std": 0.6945097148418427,
      "rewards/correct_code_reward_func": 0.5416666865348816,
      "rewards/len_reward_func": 0.28028544783592224,
      "step": 62
    },
    {
      "completion_length": 55.66666793823242,
      "epoch": 1.0,
      "grad_norm": 1.8272498546531741,
      "kl": 0.02587890625,
      "learning_rate": 2.597338798034344e-07,
      "loss": 0.0,
      "reward": 0.713922381401062,
      "reward_std": 0.519837498664856,
      "rewards/correct_code_reward_func": 0.4166666865348816,
      "rewards/len_reward_func": 0.29725566506385803,
      "step": 63
    },
    {
      "completion_length": 88.75000381469727,
      "epoch": 1.016,
      "grad_norm": 1.6950346991160663,
      "kl": 0.0108642578125,
      "learning_rate": 2.532453557994827e-07,
      "loss": 0.0,
      "reward": 0.5927524715662003,
      "reward_std": 0.39128445088863373,
      "rewards/correct_code_reward_func": 0.3750000149011612,
      "rewards/len_reward_func": 0.21775247156620026,
      "step": 64
    },
    {
      "completion_length": 151.7291717529297,
      "epoch": 1.032,
      "grad_norm": 1.6408461481438466,
      "kl": 0.011138916015625,
      "learning_rate": 2.467546442005173e-07,
      "loss": 0.0,
      "reward": 0.6122622489929199,
      "reward_std": 0.5165137350559235,
      "rewards/correct_code_reward_func": 0.3125000149011612,
      "rewards/len_reward_func": 0.2997622489929199,
      "step": 65
    },
    {
      "completion_length": 104.85417175292969,
      "epoch": 1.048,
      "grad_norm": 1.1573620161491798,
      "kl": 0.01092529296875,
      "learning_rate": 2.4026612019656556e-07,
      "loss": 0.0,
      "reward": 0.8486100733280182,
      "reward_std": 0.3942585438489914,
      "rewards/correct_code_reward_func": 0.5,
      "rewards/len_reward_func": 0.348610058426857,
      "step": 66
    },
    {
      "completion_length": 62.47916793823242,
      "epoch": 1.064,
      "grad_norm": 2.1966023559129266,
      "kl": 0.018798828125,
      "learning_rate": 2.337841575030642e-07,
      "loss": 0.0,
      "reward": 0.8105108737945557,
      "reward_std": 0.4338831454515457,
      "rewards/correct_code_reward_func": 0.4583333432674408,
      "rewards/len_reward_func": 0.35217756032943726,
      "step": 67
    },
    {
      "completion_length": 74.95833587646484,
      "epoch": 1.08,
      "grad_norm": 1.796160832910341,
      "kl": 0.02294921875,
      "learning_rate": 2.2731312541267143e-07,
      "loss": 0.0,
      "reward": 0.549996554851532,
      "reward_std": 0.3687018007040024,
      "rewards/correct_code_reward_func": 0.2083333358168602,
      "rewards/len_reward_func": 0.3416632413864136,
      "step": 68
    },
    {
      "completion_length": 80.14583587646484,
      "epoch": 1.096,
      "grad_norm": 2.1344146728324653,
      "kl": 0.02447509765625,
      "learning_rate": 2.2085738585006021e-07,
      "loss": 0.0,
      "reward": 0.8650955259799957,
      "reward_std": 0.4139704555273056,
      "rewards/correct_code_reward_func": 0.5208333432674408,
      "rewards/len_reward_func": 0.34426216781139374,
      "step": 69
    },
    {
      "completion_length": 60.958335876464844,
      "epoch": 1.112,
      "grad_norm": 1.6686676921157912,
      "kl": 0.025634765625,
      "learning_rate": 2.1442129043167873e-07,
      "loss": 0.0,
      "reward": 0.6947443187236786,
      "reward_std": 0.5725615322589874,
      "rewards/correct_code_reward_func": 0.375,
      "rewards/len_reward_func": 0.319744348526001,
      "step": 70
    },
    {
      "completion_length": 108.1875,
      "epoch": 1.1280000000000001,
      "grad_norm": 1.7272596794076989,
      "kl": 0.0130615234375,
      "learning_rate": 2.0800917753245875e-07,
      "loss": 0.0,
      "reward": 0.7587291896343231,
      "reward_std": 0.5232284665107727,
      "rewards/correct_code_reward_func": 0.4166666865348816,
      "rewards/len_reward_func": 0.3420625329017639,
      "step": 71
    },
    {
      "completion_length": 108.04167175292969,
      "epoch": 1.144,
      "grad_norm": 1.6272563745253346,
      "kl": 0.01654052734375,
      "learning_rate": 2.0162536936145008e-07,
      "loss": 0.0,
      "reward": 0.5046872794628143,
      "reward_std": 0.3378771096467972,
      "rewards/correct_code_reward_func": 0.1666666679084301,
      "rewards/len_reward_func": 0.33802059292793274,
      "step": 72
    },
    {
      "completion_length": 54.02083396911621,
      "epoch": 1.16,
      "grad_norm": 1.9418689539056528,
      "kl": 0.0308837890625,
      "learning_rate": 1.9527416904835132e-07,
      "loss": 0.0,
      "reward": 0.9055829644203186,
      "reward_std": 0.3730238378047943,
      "rewards/correct_code_reward_func": 0.5,
      "rewards/len_reward_func": 0.405582919716835,
      "step": 73
    },
    {
      "completion_length": 94.31250381469727,
      "epoch": 1.176,
      "grad_norm": 1.5576616620611914,
      "kl": 0.02215576171875,
      "learning_rate": 1.889598577429022e-07,
      "loss": 0.0,
      "reward": 0.9071804285049438,
      "reward_std": 0.44920457899570465,
      "rewards/correct_code_reward_func": 0.5000000298023224,
      "rewards/len_reward_func": 0.40718045830726624,
      "step": 74
    },
    {
      "completion_length": 53.79166793823242,
      "epoch": 1.192,
      "grad_norm": 2.3725141345867544,
      "kl": 0.03057861328125,
      "learning_rate": 1.8268669172909136e-07,
      "loss": 0.0,
      "reward": 0.9221459329128265,
      "reward_std": 0.4697086811065674,
      "rewards/correct_code_reward_func": 0.5000000298023224,
      "rewards/len_reward_func": 0.42214588820934296,
      "step": 75
    },
    {
      "completion_length": 89.79167175292969,
      "epoch": 1.208,
      "grad_norm": 2.003223060045919,
      "kl": 0.03094482421875,
      "learning_rate": 1.7645889955612592e-07,
      "loss": 0.0,
      "reward": 1.0163878798484802,
      "reward_std": 0.43504565954208374,
      "rewards/correct_code_reward_func": 0.6250000298023224,
      "rewards/len_reward_func": 0.3913878947496414,
      "step": 76
    },
    {
      "completion_length": 68.79166984558105,
      "epoch": 1.224,
      "grad_norm": 2.361523245499291,
      "kl": 0.0457763671875,
      "learning_rate": 1.7028067918809535e-07,
      "loss": 0.0,
      "reward": 0.7535229325294495,
      "reward_std": 0.47849828004837036,
      "rewards/correct_code_reward_func": 0.375,
      "rewards/len_reward_func": 0.3785228729248047,
      "step": 77
    },
    {
      "completion_length": 54.14583396911621,
      "epoch": 1.24,
      "grad_norm": 2.120116927446423,
      "kl": 0.0394287109375,
      "learning_rate": 1.6415619517425294e-07,
      "loss": 0.0,
      "reward": 0.8538325130939484,
      "reward_std": 0.44848716259002686,
      "rewards/correct_code_reward_func": 0.4791666865348816,
      "rewards/len_reward_func": 0.3746658265590668,
      "step": 78
    },
    {
      "completion_length": 89.0,
      "epoch": 1.256,
      "grad_norm": 1.2055136830985975,
      "kl": 0.0272216796875,
      "learning_rate": 1.5808957584181994e-07,
      "loss": 0.0,
      "reward": 0.755169004201889,
      "reward_std": 0.4014817923307419,
      "rewards/correct_code_reward_func": 0.3541666716337204,
      "rewards/len_reward_func": 0.40100236237049103,
      "step": 79
    },
    {
      "completion_length": 99.39583969116211,
      "epoch": 1.272,
      "grad_norm": 1.84690544945913,
      "kl": 0.024322509765625,
      "learning_rate": 1.5208491051320744e-07,
      "loss": 0.0,
      "reward": 0.7356246709823608,
      "reward_std": 0.47616493701934814,
      "rewards/correct_code_reward_func": 0.3958333432674408,
      "rewards/len_reward_func": 0.33979131281375885,
      "step": 80
    },
    {
      "completion_length": 73.04166793823242,
      "epoch": 1.288,
      "grad_norm": 1.7278725529442787,
      "kl": 0.0439453125,
      "learning_rate": 1.461462467495284e-07,
      "loss": 0.0,
      "reward": 0.7051982879638672,
      "reward_std": 0.48877203464508057,
      "rewards/correct_code_reward_func": 0.3125,
      "rewards/len_reward_func": 0.3926983177661896,
      "step": 81
    },
    {
      "completion_length": 59.354169845581055,
      "epoch": 1.304,
      "grad_norm": 2.077567652472909,
      "kl": 0.0345458984375,
      "learning_rate": 1.4027758762226107e-07,
      "loss": 0.0,
      "reward": 0.816185712814331,
      "reward_std": 0.4705541431903839,
      "rewards/correct_code_reward_func": 0.4791666865348816,
      "rewards/len_reward_func": 0.3370189964771271,
      "step": 82
    },
    {
      "completion_length": 81.58333587646484,
      "epoch": 1.32,
      "grad_norm": 1.609719907980881,
      "kl": 0.0234375,
      "learning_rate": 1.3448288901490092e-07,
      "loss": 0.0,
      "reward": 0.7908000648021698,
      "reward_std": 0.45585089921951294,
      "rewards/correct_code_reward_func": 0.4166666716337204,
      "rewards/len_reward_func": 0.374133437871933,
      "step": 83
    },
    {
      "completion_length": 87.33333587646484,
      "epoch": 1.336,
      "grad_norm": 1.6587537084233746,
      "kl": 0.02667236328125,
      "learning_rate": 1.2876605695642084e-07,
      "loss": 0.0,
      "reward": 0.6749401688575745,
      "reward_std": 0.42905712127685547,
      "rewards/correct_code_reward_func": 0.3541666716337204,
      "rewards/len_reward_func": 0.3207734525203705,
      "step": 84
    },
    {
      "completion_length": 95.20833587646484,
      "epoch": 1.3519999999999999,
      "grad_norm": 2.538472018686139,
      "kl": 0.02581787109375,
      "learning_rate": 1.231309449883361e-07,
      "loss": 0.0,
      "reward": 0.7594759464263916,
      "reward_std": 0.5746750831604004,
      "rewards/correct_code_reward_func": 0.3750000149011612,
      "rewards/len_reward_func": 0.3844759315252304,
      "step": 85
    },
    {
      "completion_length": 55.43750190734863,
      "epoch": 1.3679999999999999,
      "grad_norm": 1.797373425635401,
      "kl": 0.03289794921875,
      "learning_rate": 1.1758135156715041e-07,
      "loss": 0.0,
      "reward": 0.9961144328117371,
      "reward_std": 0.5648430436849594,
      "rewards/correct_code_reward_func": 0.6250000298023224,
      "rewards/len_reward_func": 0.37111443281173706,
      "step": 86
    },
    {
      "completion_length": 121.25000762939453,
      "epoch": 1.384,
      "grad_norm": 1.7119982491506713,
      "kl": 0.0286865234375,
      "learning_rate": 1.1212101750393235e-07,
      "loss": 0.0,
      "reward": 0.7243427634239197,
      "reward_std": 0.3805614560842514,
      "rewards/correct_code_reward_func": 0.3333333358168602,
      "rewards/len_reward_func": 0.39100944995880127,
      "step": 87
    },
    {
      "completion_length": 57.35416793823242,
      "epoch": 1.4,
      "grad_norm": 1.7713124187158098,
      "kl": 0.034912109375,
      "learning_rate": 1.0675362344274952e-07,
      "loss": 0.0,
      "reward": 0.7016758322715759,
      "reward_std": 0.5317542552947998,
      "rewards/correct_code_reward_func": 0.3541666865348816,
      "rewards/len_reward_func": 0.34750914573669434,
      "step": 88
    },
    {
      "completion_length": 59.0625,
      "epoch": 1.416,
      "grad_norm": 1.6492634665708499,
      "kl": 0.034423828125,
      "learning_rate": 1.0148278737965844e-07,
      "loss": 0.0,
      "reward": 0.7394144237041473,
      "reward_std": 0.4491709917783737,
      "rewards/correct_code_reward_func": 0.3541666716337204,
      "rewards/len_reward_func": 0.38524775207042694,
      "step": 89
    },
    {
      "completion_length": 48.6875,
      "epoch": 1.432,
      "grad_norm": 1.9432473699712165,
      "kl": 0.06494140625,
      "learning_rate": 9.631206222392479e-08,
      "loss": 0.0001,
      "reward": 0.8676341474056244,
      "reward_std": 0.3966159522533417,
      "rewards/correct_code_reward_func": 0.4791666865348816,
      "rewards/len_reward_func": 0.388467475771904,
      "step": 90
    },
    {
      "completion_length": 91.62500381469727,
      "epoch": 1.448,
      "grad_norm": 1.9189293687085252,
      "kl": 0.13482666015625,
      "learning_rate": 9.124493340311537e-08,
      "loss": 0.0001,
      "reward": 0.7231810688972473,
      "reward_std": 0.4981995224952698,
      "rewards/correct_code_reward_func": 0.3333333432674408,
      "rewards/len_reward_func": 0.3898477256298065,
      "step": 91
    },
    {
      "completion_length": 60.729169845581055,
      "epoch": 1.464,
      "grad_norm": 1.9825880271843388,
      "kl": 0.03424072265625,
      "learning_rate": 8.628481651367875e-08,
      "loss": 0.0,
      "reward": 0.8303024768829346,
      "reward_std": 0.40181903541088104,
      "rewards/correct_code_reward_func": 0.4375000149011612,
      "rewards/len_reward_func": 0.39280249178409576,
      "step": 92
    },
    {
      "completion_length": 58.22916793823242,
      "epoch": 1.48,
      "grad_norm": 1.8747344082688029,
      "kl": 0.0426025390625,
      "learning_rate": 8.143505501859551e-08,
      "loss": 0.0,
      "reward": 0.7909549474716187,
      "reward_std": 0.4536728262901306,
      "rewards/correct_code_reward_func": 0.458333358168602,
      "rewards/len_reward_func": 0.33262157440185547,
      "step": 93
    },
    {
      "completion_length": 125.10417175292969,
      "epoch": 1.496,
      "grad_norm": 1.5754029745287528,
      "kl": 0.02886962890625,
      "learning_rate": 7.669891799365282e-08,
      "loss": 0.0,
      "reward": 0.6297820806503296,
      "reward_std": 0.5051470398902893,
      "rewards/correct_code_reward_func": 0.2708333432674408,
      "rewards/len_reward_func": 0.3589487075805664,
      "step": 94
    },
    {
      "completion_length": 89.27083587646484,
      "epoch": 1.512,
      "grad_norm": 1.698829198816419,
      "kl": 0.02362060546875,
      "learning_rate": 7.207959792385998e-08,
      "loss": 0.0,
      "reward": 0.7924558222293854,
      "reward_std": 0.42506614327430725,
      "rewards/correct_code_reward_func": 0.3541666865348816,
      "rewards/len_reward_func": 0.4382891356945038,
      "step": 95
    },
    {
      "completion_length": 82.18750381469727,
      "epoch": 1.528,
      "grad_norm": 1.4031599496951968,
      "kl": 0.03643798828125,
      "learning_rate": 6.758020855149249e-08,
      "loss": 0.0,
      "reward": 0.6851500123739243,
      "reward_std": 0.2974398583173752,
      "rewards/correct_code_reward_func": 0.25000000558793545,
      "rewards/len_reward_func": 0.43515002727508545,
      "step": 96
    },
    {
      "completion_length": 54.6875,
      "epoch": 1.544,
      "grad_norm": 1.4467008481635895,
      "kl": 0.039306640625,
      "learning_rate": 6.320378277721342e-08,
      "loss": 0.0,
      "reward": 0.7509966492652893,
      "reward_std": 0.3042096644639969,
      "rewards/correct_code_reward_func": 0.3125,
      "rewards/len_reward_func": 0.4384966343641281,
      "step": 97
    },
    {
      "completion_length": 68.08333587646484,
      "epoch": 1.56,
      "grad_norm": 2.082709482850275,
      "kl": 0.03460693359375,
      "learning_rate": 5.895327061568775e-08,
      "loss": 0.0,
      "reward": 0.7968247532844543,
      "reward_std": 0.36605267226696014,
      "rewards/correct_code_reward_func": 0.3750000149011612,
      "rewards/len_reward_func": 0.42182472348213196,
      "step": 98
    },
    {
      "completion_length": 56.020835876464844,
      "epoch": 1.576,
      "grad_norm": 2.726579074776626,
      "kl": 0.0662841796875,
      "learning_rate": 5.483153720706798e-08,
      "loss": 0.0001,
      "reward": 0.8111520707607269,
      "reward_std": 0.548240602016449,
      "rewards/correct_code_reward_func": 0.4166666716337204,
      "rewards/len_reward_func": 0.3944854289293289,
      "step": 99
    },
    {
      "completion_length": 54.25000190734863,
      "epoch": 1.592,
      "grad_norm": 2.079061824739654,
      "kl": 0.0452880859375,
      "learning_rate": 5.0841360885690996e-08,
      "loss": 0.0,
      "reward": 0.9174363613128662,
      "reward_std": 0.46667972207069397,
      "rewards/correct_code_reward_func": 0.5416666865348816,
      "rewards/len_reward_func": 0.375769704580307,
      "step": 100
    },
    {
      "completion_length": 65.72916793823242,
      "epoch": 1.608,
      "grad_norm": 1.5292386933354263,
      "kl": 0.04522705078125,
      "learning_rate": 4.698543130728755e-08,
      "loss": 0.0,
      "reward": 0.8213175535202026,
      "reward_std": 0.38392098248004913,
      "rewards/correct_code_reward_func": 0.458333358168602,
      "rewards/len_reward_func": 0.3629842549562454,
      "step": 101
    },
    {
      "completion_length": 67.77083587646484,
      "epoch": 1.624,
      "grad_norm": 1.352325105446135,
      "kl": 0.0390625,
      "learning_rate": 4.326634763596784e-08,
      "loss": 0.0,
      "reward": 0.7263242900371552,
      "reward_std": 0.37168650329113007,
      "rewards/correct_code_reward_func": 0.31250002048909664,
      "rewards/len_reward_func": 0.41382429003715515,
      "step": 102
    },
    {
      "completion_length": 64.10416793823242,
      "epoch": 1.6400000000000001,
      "grad_norm": 1.9987254276022863,
      "kl": 0.02880859375,
      "learning_rate": 3.968661679220467e-08,
      "loss": 0.0,
      "reward": 1.174392580986023,
      "reward_std": 0.4813085198402405,
      "rewards/correct_code_reward_func": 0.7500000298023224,
      "rewards/len_reward_func": 0.42439255118370056,
      "step": 103
    },
    {
      "completion_length": 57.437503814697266,
      "epoch": 1.6560000000000001,
      "grad_norm": 1.5506203528349733,
      "kl": 0.041015625,
      "learning_rate": 3.624865176299499e-08,
      "loss": 0.0,
      "reward": 0.9918626546859741,
      "reward_std": 0.5309067815542221,
      "rewards/correct_code_reward_func": 0.6666666865348816,
      "rewards/len_reward_func": 0.3251959830522537,
      "step": 104
    },
    {
      "completion_length": 114.50000762939453,
      "epoch": 1.6720000000000002,
      "grad_norm": 1.538301941895194,
      "kl": 0.0245361328125,
      "learning_rate": 3.295476997533905e-08,
      "loss": 0.0,
      "reward": 0.9100688099861145,
      "reward_std": 0.29824198782444,
      "rewards/correct_code_reward_func": 0.4583333432674408,
      "rewards/len_reward_func": 0.4517354816198349,
      "step": 105
    },
    {
      "completion_length": 129.81250381469727,
      "epoch": 1.688,
      "grad_norm": 1.3867754807731443,
      "kl": 0.0283203125,
      "learning_rate": 2.980719173413396e-08,
      "loss": 0.0,
      "reward": 0.818383663892746,
      "reward_std": 0.5115247815847397,
      "rewards/correct_code_reward_func": 0.4166666716337204,
      "rewards/len_reward_func": 0.4017169624567032,
      "step": 106
    },
    {
      "completion_length": 73.33333587646484,
      "epoch": 1.704,
      "grad_norm": 2.2267187145460765,
      "kl": 0.04461669921875,
      "learning_rate": 2.680803872553408e-08,
      "loss": 0.0,
      "reward": 0.8567679226398468,
      "reward_std": 0.51302769780159,
      "rewards/correct_code_reward_func": 0.4375,
      "rewards/len_reward_func": 0.4192679077386856,
      "step": 107
    },
    {
      "completion_length": 53.54166793823242,
      "epoch": 1.72,
      "grad_norm": 3.1940102299602953,
      "kl": 0.0521240234375,
      "learning_rate": 2.395933258678745e-08,
      "loss": 0.0001,
      "reward": 0.9940223693847656,
      "reward_std": 0.46572498977184296,
      "rewards/correct_code_reward_func": 0.6041666865348816,
      "rewards/len_reward_func": 0.3898557126522064,
      "step": 108
    },
    {
      "completion_length": 41.52083396911621,
      "epoch": 1.736,
      "grad_norm": 2.0727978566546295,
      "kl": 0.0655517578125,
      "learning_rate": 2.1262993543511715e-08,
      "loss": 0.0001,
      "reward": 0.9489125609397888,
      "reward_std": 0.5604254603385925,
      "rewards/correct_code_reward_func": 0.6250000298023224,
      "rewards/len_reward_func": 0.32391248643398285,
      "step": 109
    },
    {
      "completion_length": 106.08333587646484,
      "epoch": 1.752,
      "grad_norm": 2.3414859603625806,
      "kl": 0.03424072265625,
      "learning_rate": 1.872083911532907e-08,
      "loss": 0.0,
      "reward": 0.5710697174072266,
      "reward_std": 0.4303289204835892,
      "rewards/correct_code_reward_func": 0.1666666679084301,
      "rewards/len_reward_func": 0.4044030159711838,
      "step": 110
    },
    {
      "completion_length": 60.437503814697266,
      "epoch": 1.768,
      "grad_norm": 1.5494191116212308,
      "kl": 0.046875,
      "learning_rate": 1.6334582890731697e-08,
      "loss": 0.0,
      "reward": 1.0543819665908813,
      "reward_std": 0.4688963294029236,
      "rewards/correct_code_reward_func": 0.6666666865348816,
      "rewards/len_reward_func": 0.38771532475948334,
      "step": 111
    },
    {
      "completion_length": 139.43750381469727,
      "epoch": 1.784,
      "grad_norm": 1.8975149766982131,
      "kl": 0.0323486328125,
      "learning_rate": 1.4105833372004523e-08,
      "loss": 0.0,
      "reward": 0.7198583781719208,
      "reward_std": 0.2770904451608658,
      "rewards/correct_code_reward_func": 0.2708333395421505,
      "rewards/len_reward_func": 0.4490250498056412,
      "step": 112
    },
    {
      "completion_length": 71.87500190734863,
      "epoch": 1.8,
      "grad_norm": 1.8779975481307012,
      "kl": 0.0350341796875,
      "learning_rate": 1.2036092890982619e-08,
      "loss": 0.0,
      "reward": 0.6213224828243256,
      "reward_std": 0.39381173253059387,
      "rewards/correct_code_reward_func": 0.25,
      "rewards/len_reward_func": 0.3713224530220032,
      "step": 113
    },
    {
      "completion_length": 73.16666793823242,
      "epoch": 1.8159999999999998,
      "grad_norm": 1.625916920606493,
      "kl": 0.04345703125,
      "learning_rate": 1.0126756596375685e-08,
      "loss": 0.0,
      "reward": 0.8906111121177673,
      "reward_std": 0.5251133739948273,
      "rewards/correct_code_reward_func": 0.4791666865348816,
      "rewards/len_reward_func": 0.41144441068172455,
      "step": 114
    },
    {
      "completion_length": 39.85416793823242,
      "epoch": 1.8319999999999999,
      "grad_norm": 1.8155165345051183,
      "kl": 0.0440673828125,
      "learning_rate": 8.379111513340753e-09,
      "loss": 0.0,
      "reward": 0.8687795996665955,
      "reward_std": 0.4838385283946991,
      "rewards/correct_code_reward_func": 0.4583333358168602,
      "rewards/len_reward_func": 0.41044625639915466,
      "step": 115
    },
    {
      "completion_length": 75.58333396911621,
      "epoch": 1.8479999999999999,
      "grad_norm": 1.8222797961879316,
      "kl": 0.03985595703125,
      "learning_rate": 6.7943356759381785e-09,
      "loss": 0.0,
      "reward": 0.9320607483386993,
      "reward_std": 0.5384509861469269,
      "rewards/correct_code_reward_func": 0.5416666865348816,
      "rewards/len_reward_func": 0.39039406180381775,
      "step": 116
    },
    {
      "completion_length": 68.54166984558105,
      "epoch": 1.8639999999999999,
      "grad_norm": 2.0020075086567775,
      "kl": 0.031982421875,
      "learning_rate": 5.373497333054616e-09,
      "loss": 0.0,
      "reward": 0.9275134801864624,
      "reward_std": 0.4482097327709198,
      "rewards/correct_code_reward_func": 0.5000000298023224,
      "rewards/len_reward_func": 0.4275134950876236,
      "step": 117
    },
    {
      "completion_length": 73.91666793823242,
      "epoch": 1.88,
      "grad_norm": 1.7788611304062052,
      "kl": 0.03240966796875,
      "learning_rate": 4.117554228329406e-09,
      "loss": 0.0,
      "reward": 0.9304822385311127,
      "reward_std": 0.5174555033445358,
      "rewards/correct_code_reward_func": 0.5416666865348816,
      "rewards/len_reward_func": 0.38881558179855347,
      "step": 118
    },
    {
      "completion_length": 56.20833396911621,
      "epoch": 1.896,
      "grad_norm": 2.1126141119280257,
      "kl": 0.0341796875,
      "learning_rate": 3.0273529545687125e-09,
      "loss": 0.0,
      "reward": 0.7594221532344818,
      "reward_std": 0.480338990688324,
      "rewards/correct_code_reward_func": 0.3958333432674408,
      "rewards/len_reward_func": 0.3635888248682022,
      "step": 119
    },
    {
      "completion_length": 72.47916793823242,
      "epoch": 1.912,
      "grad_norm": 1.4598566413193612,
      "kl": 0.03466796875,
      "learning_rate": 2.1036283830834224e-09,
      "loss": 0.0,
      "reward": 0.7889427244663239,
      "reward_std": 0.48503294587135315,
      "rewards/correct_code_reward_func": 0.3958333432674408,
      "rewards/len_reward_func": 0.39310936629772186,
      "step": 120
    },
    {
      "completion_length": 40.85416793823242,
      "epoch": 1.928,
      "grad_norm": 2.335195303935002,
      "kl": 0.056640625,
      "learning_rate": 1.347003168334665e-09,
      "loss": 0.0001,
      "reward": 1.0662382543087006,
      "reward_std": 0.2768351137638092,
      "rewards/correct_code_reward_func": 0.6250000149011612,
      "rewards/len_reward_func": 0.44123825430870056,
      "step": 121
    },
    {
      "completion_length": 50.62500190734863,
      "epoch": 1.944,
      "grad_norm": 1.8386331097859265,
      "kl": 0.03173828125,
      "learning_rate": 7.579873282216598e-10,
      "loss": 0.0,
      "reward": 0.8906074166297913,
      "reward_std": 0.5252098143100739,
      "rewards/correct_code_reward_func": 0.5833333730697632,
      "rewards/len_reward_func": 0.30727406591176987,
      "step": 122
    },
    {
      "completion_length": 99.4375057220459,
      "epoch": 1.96,
      "grad_norm": 1.621045537411182,
      "kl": 0.0238037109375,
      "learning_rate": 3.3697790029424413e-10,
      "loss": 0.0,
      "reward": 0.9505272507667542,
      "reward_std": 0.5842320024967194,
      "rewards/correct_code_reward_func": 0.5833333432674408,
      "rewards/len_reward_func": 0.36719387769699097,
      "step": 123
    },
    {
      "completion_length": 63.000003814697266,
      "epoch": 1.976,
      "grad_norm": 2.157350197672568,
      "kl": 0.0465087890625,
      "learning_rate": 8.425867412190091e-11,
      "loss": 0.0,
      "reward": 0.9762873649597168,
      "reward_std": 0.5066816210746765,
      "rewards/correct_code_reward_func": 0.5833333432674408,
      "rewards/len_reward_func": 0.3929540067911148,
      "step": 124
    },
    {
      "completion_length": 126.97917175292969,
      "epoch": 1.992,
      "grad_norm": 1.7642641467833304,
      "kl": 0.02130126953125,
      "learning_rate": 0.0,
      "loss": 0.0,
      "reward": 0.7899810075759888,
      "reward_std": 0.38732415437698364,
      "rewards/correct_code_reward_func": 0.3750000149011612,
      "rewards/len_reward_func": 0.41498102247714996,
      "step": 125
    },
    {
      "epoch": 1.992,
      "step": 125,
      "total_flos": 0.0,
      "train_loss": 1.9367338650191358e-05,
      "train_runtime": 3648.0047,
      "train_samples_per_second": 0.206,
      "train_steps_per_second": 0.034
    }
  ],
  "logging_steps": 1,
  "max_steps": 125,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 3,
  "save_steps": 25,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 0.0,
  "train_batch_size": 1,
  "trial_name": null,
  "trial_params": null
}