{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 3.994671403197158,
  "eval_steps": 500,
  "global_step": 281,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "completion_length": 443.4687614440918,
      "epoch": 0.014209591474245116,
      "grad_norm": 0.09125881615550695,
      "kl": 0.0,
      "learning_rate": 1.111111111111111e-07,
      "loss": -0.0,
      "reward": 0.3576304567977786,
      "reward_std": 0.4616274796426296,
      "rewards/correct_code_reward_func": 0.23437500465661287,
      "rewards/len_reward_func": 0.12325544544728473,
      "step": 1
    },
    {
      "completion_length": 398.92188262939453,
      "epoch": 0.028419182948490232,
      "grad_norm": 0.13757195488497995,
      "kl": 0.0,
      "learning_rate": 2.222222222222222e-07,
      "loss": 0.0,
      "reward": 0.47792164236307144,
      "reward_std": 0.4201408177614212,
      "rewards/correct_code_reward_func": 0.2812500027939677,
      "rewards/len_reward_func": 0.19667163444682956,
      "step": 2
    },
    {
      "completion_length": 402.58334732055664,
      "epoch": 0.04262877442273535,
      "grad_norm": 0.13511963471501504,
      "kl": -7.124617695808411e-06,
      "learning_rate": 3.333333333333333e-07,
      "loss": -0.0,
      "reward": 0.3930035997182131,
      "reward_std": 0.46411602199077606,
      "rewards/correct_code_reward_func": 0.22395833861082792,
      "rewards/len_reward_func": 0.16904525645077229,
      "step": 3
    },
    {
      "completion_length": 310.3541774749756,
      "epoch": 0.056838365896980464,
      "grad_norm": 0.07806157009719873,
      "kl": -1.957640051841736e-06,
      "learning_rate": 4.444444444444444e-07,
      "loss": -0.0,
      "reward": 0.38591789826750755,
      "reward_std": 0.42719122767448425,
      "rewards/correct_code_reward_func": 0.17708333767950535,
      "rewards/len_reward_func": 0.20883454754948616,
      "step": 4
    },
    {
      "completion_length": 404.723970413208,
      "epoch": 0.07104795737122557,
      "grad_norm": 0.07571975205495458,
      "kl": -6.429851055145264e-06,
      "learning_rate": 5.555555555555555e-07,
      "loss": -0.0,
      "reward": 0.36262219585478306,
      "reward_std": 0.4432934559881687,
      "rewards/correct_code_reward_func": 0.20833334000781178,
      "rewards/len_reward_func": 0.15428885607980192,
      "step": 5
    },
    {
      "completion_length": 363.6823043823242,
      "epoch": 0.0852575488454707,
      "grad_norm": 0.06865688249821604,
      "kl": -9.018927812576294e-06,
      "learning_rate": 6.666666666666666e-07,
      "loss": -0.0,
      "reward": 0.38828960061073303,
      "reward_std": 0.4154902696609497,
      "rewards/correct_code_reward_func": 0.1927083395421505,
      "rewards/len_reward_func": 0.19558126479387283,
      "step": 6
    },
    {
      "completion_length": 343.91667556762695,
      "epoch": 0.0994671403197158,
      "grad_norm": 0.09109306059846616,
      "kl": -1.0896474123001099e-05,
      "learning_rate": 7.777777777777778e-07,
      "loss": -0.0,
      "reward": 0.4306595250964165,
      "reward_std": 0.4264567568898201,
      "rewards/correct_code_reward_func": 0.2083333395421505,
      "rewards/len_reward_func": 0.22232618182897568,
      "step": 7
    },
    {
      "completion_length": 377.8177146911621,
      "epoch": 0.11367673179396093,
      "grad_norm": 0.06511134144287685,
      "kl": -2.1182000637054443e-05,
      "learning_rate": 8.888888888888888e-07,
      "loss": -0.0,
      "reward": 0.36623864248394966,
      "reward_std": 0.46032407879829407,
      "rewards/correct_code_reward_func": 0.1979166748933494,
      "rewards/len_reward_func": 0.168321980163455,
      "step": 8
    },
    {
      "completion_length": 371.4218864440918,
      "epoch": 0.12788632326820604,
      "grad_norm": 0.07213043933363646,
      "kl": 1.1237338185310364e-05,
      "learning_rate": 1e-06,
      "loss": -0.0,
      "reward": 0.3946306835860014,
      "reward_std": 0.46948346123099327,
      "rewards/correct_code_reward_func": 0.1822916716337204,
      "rewards/len_reward_func": 0.21233901381492615,
      "step": 9
    },
    {
      "completion_length": 388.5989685058594,
      "epoch": 0.14209591474245115,
      "grad_norm": 0.09680404123453559,
      "kl": -3.0547380447387695e-06,
      "learning_rate": 9.999666499017256e-07,
      "loss": -0.0,
      "reward": 0.3841761089861393,
      "reward_std": 0.41449498757719994,
      "rewards/correct_code_reward_func": 0.20833334047347307,
      "rewards/len_reward_func": 0.17584276013076305,
      "step": 10
    },
    {
      "completion_length": 351.66666984558105,
      "epoch": 0.15630550621669628,
      "grad_norm": 0.07784385567252304,
      "kl": 2.8794631361961365e-05,
      "learning_rate": 9.998666040558186e-07,
      "loss": 0.0,
      "reward": 0.3436309564858675,
      "reward_std": 0.3878885917365551,
      "rewards/correct_code_reward_func": 0.12500000186264515,
      "rewards/len_reward_func": 0.2186309490352869,
      "step": 11
    },
    {
      "completion_length": 371.5989646911621,
      "epoch": 0.1705150976909414,
      "grad_norm": 0.07107832746878774,
      "kl": 8.022040128707886e-05,
      "learning_rate": 9.996998758084343e-07,
      "loss": 0.0,
      "reward": 0.5266022570431232,
      "reward_std": 0.4455077052116394,
      "rewards/correct_code_reward_func": 0.33854167722165585,
      "rewards/len_reward_func": 0.188060587272048,
      "step": 12
    },
    {
      "completion_length": 340.2291717529297,
      "epoch": 0.1847246891651865,
      "grad_norm": 0.08891181548954005,
      "kl": 7.667392492294312e-05,
      "learning_rate": 9.994664874011861e-07,
      "loss": 0.0,
      "reward": 0.4206070154905319,
      "reward_std": 0.4813660904765129,
      "rewards/correct_code_reward_func": 0.2135416753590107,
      "rewards/len_reward_func": 0.20706532802432775,
      "step": 13
    },
    {
      "completion_length": 341.02605056762695,
      "epoch": 0.1989342806394316,
      "grad_norm": 0.0680645892449702,
      "kl": 0.00022267550230026245,
      "learning_rate": 9.991664699681798e-07,
      "loss": 0.0,
      "reward": 0.4131320230662823,
      "reward_std": 0.3749092798680067,
      "rewards/correct_code_reward_func": 0.1666666711680591,
      "rewards/len_reward_func": 0.24646534025669098,
      "step": 14
    },
    {
      "completion_length": 358.53647232055664,
      "epoch": 0.21314387211367672,
      "grad_norm": 0.07220625439947133,
      "kl": 0.00030153989791870117,
      "learning_rate": 9.987998635318584e-07,
      "loss": 0.0,
      "reward": 0.4057324044406414,
      "reward_std": 0.4519721567630768,
      "rewards/correct_code_reward_func": 0.21354167209938169,
      "rewards/len_reward_func": 0.19219073839485645,
      "step": 15
    },
    {
      "completion_length": 279.0572967529297,
      "epoch": 0.22735346358792186,
      "grad_norm": 0.1213168372448653,
      "kl": 0.0009036064147949219,
      "learning_rate": 9.983667169976649e-07,
      "loss": 0.0,
      "reward": 0.3864438720047474,
      "reward_std": 0.42899639159440994,
      "rewards/correct_code_reward_func": 0.15104167256504297,
      "rewards/len_reward_func": 0.23540219850838184,
      "step": 16
    },
    {
      "completion_length": 280.5260486602783,
      "epoch": 0.24156305506216696,
      "grad_norm": 0.09303958992639275,
      "kl": 0.0010909438133239746,
      "learning_rate": 9.978670881475172e-07,
      "loss": 0.0,
      "reward": 0.48882297798991203,
      "reward_std": 0.41413741931319237,
      "rewards/correct_code_reward_func": 0.2395833395421505,
      "rewards/len_reward_func": 0.24923964380286634,
      "step": 17
    },
    {
      "completion_length": 275.44792556762695,
      "epoch": 0.2557726465364121,
      "grad_norm": 0.05827968961957391,
      "kl": 0.0009391307830810547,
      "learning_rate": 9.973010436321003e-07,
      "loss": 0.0,
      "reward": 0.367222061380744,
      "reward_std": 0.44822756946086884,
      "rewards/correct_code_reward_func": 0.1822916711680591,
      "rewards/len_reward_func": 0.18493039719760418,
      "step": 18
    },
    {
      "completion_length": 260.27084159851074,
      "epoch": 0.2699822380106572,
      "grad_norm": 0.08631562115264406,
      "kl": 0.0020546913146972656,
      "learning_rate": 9.966686589619748e-07,
      "loss": 0.0,
      "reward": 0.33929781429469585,
      "reward_std": 0.35473988577723503,
      "rewards/correct_code_reward_func": 0.07291666744276881,
      "rewards/len_reward_func": 0.2663811491802335,
      "step": 19
    },
    {
      "completion_length": 256.89584159851074,
      "epoch": 0.2841918294849023,
      "grad_norm": 0.050726444938546694,
      "kl": 0.002056598663330078,
      "learning_rate": 9.959700184975048e-07,
      "loss": 0.0,
      "reward": 0.39015788212418556,
      "reward_std": 0.3878217041492462,
      "rewards/correct_code_reward_func": 0.14062500419095159,
      "rewards/len_reward_func": 0.24953287653625011,
      "step": 20
    },
    {
      "completion_length": 243.08334159851074,
      "epoch": 0.2984014209591474,
      "grad_norm": 0.0963623792658915,
      "kl": 0.0028510093688964844,
      "learning_rate": 9.952052154376024e-07,
      "loss": 0.0,
      "reward": 0.440104853361845,
      "reward_std": 0.4077576696872711,
      "rewards/correct_code_reward_func": 0.18750000279396772,
      "rewards/len_reward_func": 0.25260484032332897,
      "step": 21
    },
    {
      "completion_length": 245.48958778381348,
      "epoch": 0.31261101243339257,
      "grad_norm": 0.12136742708320991,
      "kl": 0.004702091217041016,
      "learning_rate": 9.94374351807297e-07,
      "loss": 0.0,
      "reward": 0.4119306458160281,
      "reward_std": 0.43577412888407707,
      "rewards/correct_code_reward_func": 0.18750000558793545,
      "rewards/len_reward_func": 0.22443064954131842,
      "step": 22
    },
    {
      "completion_length": 299.6562614440918,
      "epoch": 0.3268206039076377,
      "grad_norm": 0.08926890755633274,
      "kl": 0.0042743682861328125,
      "learning_rate": 9.934775384441228e-07,
      "loss": 0.0,
      "reward": 0.43541758693754673,
      "reward_std": 0.47669555619359016,
      "rewards/correct_code_reward_func": 0.19791667396202683,
      "rewards/len_reward_func": 0.23750090412795544,
      "step": 23
    },
    {
      "completion_length": 290.75000953674316,
      "epoch": 0.3410301953818828,
      "grad_norm": 0.07822771432587206,
      "kl": 0.004744529724121094,
      "learning_rate": 9.925148949833354e-07,
      "loss": 0.0,
      "reward": 0.4482608884572983,
      "reward_std": 0.40951015427708626,
      "rewards/correct_code_reward_func": 0.19791667442768812,
      "rewards/len_reward_func": 0.250344205647707,
      "step": 24
    },
    {
      "completion_length": 205.45312881469727,
      "epoch": 0.3552397868561279,
      "grad_norm": 0.09162770064611905,
      "kl": 0.003983497619628906,
      "learning_rate": 9.91486549841951e-07,
      "loss": 0.0,
      "reward": 0.4542126916348934,
      "reward_std": 0.3957964666187763,
      "rewards/correct_code_reward_func": 0.1770833390764892,
      "rewards/len_reward_func": 0.27712935395538807,
      "step": 25
    },
    {
      "completion_length": 231.85417366027832,
      "epoch": 0.369449378330373,
      "grad_norm": 0.07898133106509024,
      "kl": 0.0061969757080078125,
      "learning_rate": 9.90392640201615e-07,
      "loss": 0.0,
      "reward": 0.30801666900515556,
      "reward_std": 0.3691173493862152,
      "rewards/correct_code_reward_func": 0.06770833488553762,
      "rewards/len_reward_func": 0.24030832201242447,
      "step": 26
    },
    {
      "completion_length": 174.432297706604,
      "epoch": 0.3836589698046181,
      "grad_norm": 0.11620857548867602,
      "kl": 0.00966644287109375,
      "learning_rate": 9.892333119903046e-07,
      "loss": 0.0,
      "reward": 0.4265779182314873,
      "reward_std": 0.4265328720211983,
      "rewards/correct_code_reward_func": 0.18229166977107525,
      "rewards/len_reward_func": 0.24428623914718628,
      "step": 27
    },
    {
      "completion_length": 177.34375762939453,
      "epoch": 0.3978685612788632,
      "grad_norm": 0.08550813110975443,
      "kl": 0.01479339599609375,
      "learning_rate": 9.880087198628577e-07,
      "loss": 0.0,
      "reward": 0.47751085087656975,
      "reward_std": 0.4276348613202572,
      "rewards/correct_code_reward_func": 0.17708333721384406,
      "rewards/len_reward_func": 0.3004274982959032,
      "step": 28
    },
    {
      "completion_length": 177.1927146911621,
      "epoch": 0.41207815275310833,
      "grad_norm": 0.1412405836607863,
      "kl": 0.013334274291992188,
      "learning_rate": 9.867190271803463e-07,
      "loss": 0.0,
      "reward": 0.49972818046808243,
      "reward_std": 0.37847696989774704,
      "rewards/correct_code_reward_func": 0.19270833767950535,
      "rewards/len_reward_func": 0.307019853964448,
      "step": 29
    },
    {
      "completion_length": 178.61458492279053,
      "epoch": 0.42628774422735344,
      "grad_norm": 0.12602362538408282,
      "kl": 0.009374618530273438,
      "learning_rate": 9.85364405988281e-07,
      "loss": 0.0,
      "reward": 0.41962936148047447,
      "reward_std": 0.37547097727656364,
      "rewards/correct_code_reward_func": 0.1666666711680591,
      "rewards/len_reward_func": 0.2529626935720444,
      "step": 30
    },
    {
      "completion_length": 171.29687786102295,
      "epoch": 0.4404973357015986,
      "grad_norm": 0.10051103076388204,
      "kl": 0.02468109130859375,
      "learning_rate": 9.839450369936612e-07,
      "loss": 0.0,
      "reward": 0.5187188200652599,
      "reward_std": 0.38609882444143295,
      "rewards/correct_code_reward_func": 0.19270833861082792,
      "rewards/len_reward_func": 0.32601046934723854,
      "step": 31
    },
    {
      "completion_length": 142.96875381469727,
      "epoch": 0.4547069271758437,
      "grad_norm": 0.1461472119334927,
      "kl": 0.023895263671875,
      "learning_rate": 9.824611095408688e-07,
      "loss": 0.0,
      "reward": 0.4322962500154972,
      "reward_std": 0.330787168815732,
      "rewards/correct_code_reward_func": 0.1250000037252903,
      "rewards/len_reward_func": 0.3072962611913681,
      "step": 32
    },
    {
      "completion_length": 108.0364637374878,
      "epoch": 0.4689165186500888,
      "grad_norm": 0.11429748123014816,
      "kl": 0.032318115234375,
      "learning_rate": 9.809128215864096e-07,
      "loss": 0.0,
      "reward": 0.5177840702235699,
      "reward_std": 0.37513144314289093,
      "rewards/correct_code_reward_func": 0.2031250069849193,
      "rewards/len_reward_func": 0.31465907394886017,
      "step": 33
    },
    {
      "completion_length": 134.35416984558105,
      "epoch": 0.48312611012433393,
      "grad_norm": 0.08200955548466611,
      "kl": 0.0293426513671875,
      "learning_rate": 9.793003796725049e-07,
      "loss": 0.0,
      "reward": 0.5121603533625603,
      "reward_std": 0.3688562586903572,
      "rewards/correct_code_reward_func": 0.20312500651925802,
      "rewards/len_reward_func": 0.3090353347361088,
      "step": 34
    },
    {
      "completion_length": 132.31250476837158,
      "epoch": 0.49733570159857904,
      "grad_norm": 0.14542346263016798,
      "kl": 0.0428619384765625,
      "learning_rate": 9.776239988995399e-07,
      "loss": 0.0,
      "reward": 0.5000036209821701,
      "reward_std": 0.44860122352838516,
      "rewards/correct_code_reward_func": 0.21354167349636555,
      "rewards/len_reward_func": 0.28646195307374,
      "step": 35
    },
    {
      "completion_length": 138.38021183013916,
      "epoch": 0.5115452930728241,
      "grad_norm": 0.09021595554817276,
      "kl": 0.03460693359375,
      "learning_rate": 9.75883902897369e-07,
      "loss": 0.0,
      "reward": 0.470582939684391,
      "reward_std": 0.35864984430372715,
      "rewards/correct_code_reward_func": 0.16145833721384406,
      "rewards/len_reward_func": 0.3091245945543051,
      "step": 36
    },
    {
      "completion_length": 125.23958778381348,
      "epoch": 0.5257548845470693,
      "grad_norm": 0.10126711996612395,
      "kl": 0.02475738525390625,
      "learning_rate": 9.74080323795483e-07,
      "loss": 0.0,
      "reward": 0.5447370000183582,
      "reward_std": 0.36313992738723755,
      "rewards/correct_code_reward_func": 0.22916667675599456,
      "rewards/len_reward_func": 0.3155703376978636,
      "step": 37
    },
    {
      "completion_length": 124.05208730697632,
      "epoch": 0.5399644760213144,
      "grad_norm": 0.10613084894426801,
      "kl": 0.030467987060546875,
      "learning_rate": 9.722135021920425e-07,
      "loss": 0.0,
      "reward": 0.5184498019516468,
      "reward_std": 0.37687110528349876,
      "rewards/correct_code_reward_func": 0.20833333767950535,
      "rewards/len_reward_func": 0.3101164661347866,
      "step": 38
    },
    {
      "completion_length": 88.67708492279053,
      "epoch": 0.5541740674955595,
      "grad_norm": 0.12506147123844602,
      "kl": 0.046875,
      "learning_rate": 9.702836871217837e-07,
      "loss": 0.0,
      "reward": 0.5259646214544773,
      "reward_std": 0.3721216693520546,
      "rewards/correct_code_reward_func": 0.20312500465661287,
      "rewards/len_reward_func": 0.32283961959183216,
      "step": 39
    },
    {
      "completion_length": 143.83854579925537,
      "epoch": 0.5683836589698046,
      "grad_norm": 0.08253691455975531,
      "kl": 0.026611328125,
      "learning_rate": 9.682911360227957e-07,
      "loss": 0.0,
      "reward": 0.4295451957732439,
      "reward_std": 0.3187869042158127,
      "rewards/correct_code_reward_func": 0.13541667209938169,
      "rewards/len_reward_func": 0.2941285436972976,
      "step": 40
    },
    {
      "completion_length": 66.96875143051147,
      "epoch": 0.5825932504440497,
      "grad_norm": 0.16529176168556395,
      "kl": 0.07354736328125,
      "learning_rate": 9.66236114702178e-07,
      "loss": 0.0001,
      "reward": 0.5539138279855251,
      "reward_std": 0.3036817517131567,
      "rewards/correct_code_reward_func": 0.18229167209938169,
      "rewards/len_reward_func": 0.37162213400006294,
      "step": 41
    },
    {
      "completion_length": 97.65104341506958,
      "epoch": 0.5968028419182948,
      "grad_norm": 0.12555763789025295,
      "kl": 0.0460357666015625,
      "learning_rate": 9.641188973005824e-07,
      "loss": 0.0,
      "reward": 0.4990990087389946,
      "reward_std": 0.36859178356826305,
      "rewards/correct_code_reward_func": 0.13541666977107525,
      "rewards/len_reward_func": 0.3636823371052742,
      "step": 42
    },
    {
      "completion_length": 77.14583587646484,
      "epoch": 0.61101243339254,
      "grad_norm": 0.18606703940393493,
      "kl": 0.0560302734375,
      "learning_rate": 9.619397662556433e-07,
      "loss": 0.0001,
      "reward": 0.3705504834651947,
      "reward_std": 0.3101746551692486,
      "rewards/correct_code_reward_func": 0.03645833441987634,
      "rewards/len_reward_func": 0.334092129021883,
      "step": 43
    },
    {
      "completion_length": 85.13541746139526,
      "epoch": 0.6252220248667851,
      "grad_norm": 0.10932044749872093,
      "kl": 0.0731201171875,
      "learning_rate": 9.596990122642983e-07,
      "loss": 0.0001,
      "reward": 0.5129675306379795,
      "reward_std": 0.25492589524947107,
      "rewards/correct_code_reward_func": 0.11979166930541396,
      "rewards/len_reward_func": 0.3931758664548397,
      "step": 44
    },
    {
      "completion_length": 92.78125190734863,
      "epoch": 0.6394316163410302,
      "grad_norm": 0.22754838147242173,
      "kl": 0.0522308349609375,
      "learning_rate": 9.573969342440105e-07,
      "loss": 0.0001,
      "reward": 0.44260110706090927,
      "reward_std": 0.21846961742267013,
      "rewards/correct_code_reward_func": 0.0677083358168602,
      "rewards/len_reward_func": 0.3748927637934685,
      "step": 45
    },
    {
      "completion_length": 68.50521087646484,
      "epoch": 0.6536412078152753,
      "grad_norm": 0.14113739167300077,
      "kl": 0.058868408203125,
      "learning_rate": 9.55033839292893e-07,
      "loss": 0.0001,
      "reward": 0.48271963745355606,
      "reward_std": 0.2195771150290966,
      "rewards/correct_code_reward_func": 0.10937500279396772,
      "rewards/len_reward_func": 0.37334463000297546,
      "step": 46
    },
    {
      "completion_length": 73.24479246139526,
      "epoch": 0.6678507992895204,
      "grad_norm": 0.09997534256979927,
      "kl": 0.0683746337890625,
      "learning_rate": 9.526100426487409e-07,
      "loss": 0.0001,
      "reward": 0.43251994252204895,
      "reward_std": 0.2856837445870042,
      "rewards/correct_code_reward_func": 0.06250000186264515,
      "rewards/len_reward_func": 0.37001994624733925,
      "step": 47
    },
    {
      "completion_length": 63.61458444595337,
      "epoch": 0.6820603907637656,
      "grad_norm": 0.1260299239963017,
      "kl": 0.097869873046875,
      "learning_rate": 9.501258676469799e-07,
      "loss": 0.0001,
      "reward": 0.49302147701382637,
      "reward_std": 0.24349567480385303,
      "rewards/correct_code_reward_func": 0.0937500037252903,
      "rewards/len_reward_func": 0.39927147328853607,
      "step": 48
    },
    {
      "completion_length": 79.98437690734863,
      "epoch": 0.6962699822380106,
      "grad_norm": 0.10585381946360697,
      "kl": 0.0675506591796875,
      "learning_rate": 9.475816456775312e-07,
      "loss": 0.0001,
      "reward": 0.5251170843839645,
      "reward_std": 0.19920349679887295,
      "rewards/correct_code_reward_func": 0.10937500186264515,
      "rewards/len_reward_func": 0.41574207693338394,
      "step": 49
    },
    {
      "completion_length": 55.687500953674316,
      "epoch": 0.7104795737122558,
      "grad_norm": 0.10630012529950177,
      "kl": 0.09686279296875,
      "learning_rate": 9.449777161406059e-07,
      "loss": 0.0001,
      "reward": 0.5236603431403637,
      "reward_std": 0.22042104415595531,
      "rewards/correct_code_reward_func": 0.10416667023673654,
      "rewards/len_reward_func": 0.4194936640560627,
      "step": 50
    },
    {
      "completion_length": 64.39062786102295,
      "epoch": 0.7246891651865008,
      "grad_norm": 0.12145027836621486,
      "kl": 0.13330078125,
      "learning_rate": 9.423144264014276e-07,
      "loss": 0.0001,
      "reward": 0.48604343831539154,
      "reward_std": 0.1757725104689598,
      "rewards/correct_code_reward_func": 0.0572916679084301,
      "rewards/len_reward_func": 0.42875177413225174,
      "step": 51
    },
    {
      "completion_length": 52.031251430511475,
      "epoch": 0.738898756660746,
      "grad_norm": 0.09937588952090468,
      "kl": 0.23095703125,
      "learning_rate": 9.395921317438948e-07,
      "loss": 0.0002,
      "reward": 0.49487581849098206,
      "reward_std": 0.14651049487292767,
      "rewards/correct_code_reward_func": 0.052083334885537624,
      "rewards/len_reward_func": 0.44279248267412186,
      "step": 52
    },
    {
      "completion_length": 51.97916793823242,
      "epoch": 0.7531083481349912,
      "grad_norm": 0.2073171274630726,
      "kl": 0.14617919921875,
      "learning_rate": 9.368111953231847e-07,
      "loss": 0.0001,
      "reward": 0.4552471898496151,
      "reward_std": 0.21764121856540442,
      "rewards/correct_code_reward_func": 0.046875000931322575,
      "rewards/len_reward_func": 0.4083721898496151,
      "step": 53
    },
    {
      "completion_length": 39.45833492279053,
      "epoch": 0.7673179396092362,
      "grad_norm": 0.1510287888805774,
      "kl": 0.16766357421875,
      "learning_rate": 9.339719881173092e-07,
      "loss": 0.0002,
      "reward": 0.48997437581419945,
      "reward_std": 0.1961837261915207,
      "rewards/correct_code_reward_func": 0.07812500139698386,
      "rewards/len_reward_func": 0.41184937581419945,
      "step": 54
    },
    {
      "completion_length": 34.36458420753479,
      "epoch": 0.7815275310834814,
      "grad_norm": 0.11097808564279629,
      "kl": 0.19464111328125,
      "learning_rate": 9.310748888776253e-07,
      "loss": 0.0002,
      "reward": 0.5031399428844452,
      "reward_std": 0.17305096052587032,
      "rewards/correct_code_reward_func": 0.06250000093132257,
      "rewards/len_reward_func": 0.4406399391591549,
      "step": 55
    },
    {
      "completion_length": 38.05208396911621,
      "epoch": 0.7957371225577264,
      "grad_norm": 0.1434588390630502,
      "kl": 0.2225341796875,
      "learning_rate": 9.281202840783107e-07,
      "loss": 0.0002,
      "reward": 0.5194280631840229,
      "reward_std": 0.1683953907340765,
      "rewards/correct_code_reward_func": 0.08333333628252149,
      "rewards/len_reward_func": 0.436094731092453,
      "step": 56
    },
    {
      "completion_length": 43.125001430511475,
      "epoch": 0.8099467140319716,
      "grad_norm": 0.14649580967562786,
      "kl": 0.22430419921875,
      "learning_rate": 9.251085678648071e-07,
      "loss": 0.0002,
      "reward": 0.568339828401804,
      "reward_std": 0.15078179351985455,
      "rewards/correct_code_reward_func": 0.10416666697710752,
      "rewards/len_reward_func": 0.4641731530427933,
      "step": 57
    },
    {
      "completion_length": 38.47395944595337,
      "epoch": 0.8241563055062167,
      "grad_norm": 0.11844283379393566,
      "kl": 0.25048828125,
      "learning_rate": 9.220401420012411e-07,
      "loss": 0.0003,
      "reward": 0.5053429566323757,
      "reward_std": 0.11593597289174795,
      "rewards/correct_code_reward_func": 0.03645833441987634,
      "rewards/len_reward_func": 0.4688846208155155,
      "step": 58
    },
    {
      "completion_length": 27.572917222976685,
      "epoch": 0.8383658969804618,
      "grad_norm": 0.1439696310067313,
      "kl": 0.25439453125,
      "learning_rate": 9.18915415816829e-07,
      "loss": 0.0002,
      "reward": 0.5478983893990517,
      "reward_std": 0.10674282722175121,
      "rewards/correct_code_reward_func": 0.08854166930541396,
      "rewards/len_reward_func": 0.45935671776533127,
      "step": 59
    },
    {
      "completion_length": 28.1145840883255,
      "epoch": 0.8525754884547069,
      "grad_norm": 0.08280380649643064,
      "kl": 0.2420654296875,
      "learning_rate": 9.157348061512726e-07,
      "loss": 0.0002,
      "reward": 0.5279654115438461,
      "reward_std": 0.11856044083833694,
      "rewards/correct_code_reward_func": 0.06250000093132257,
      "rewards/len_reward_func": 0.46546541526913643,
      "step": 60
    },
    {
      "completion_length": 30.338542699813843,
      "epoch": 0.866785079928952,
      "grad_norm": 0.08853844426495436,
      "kl": 0.3074951171875,
      "learning_rate": 9.124987372991511e-07,
      "loss": 0.0003,
      "reward": 0.4923493415117264,
      "reward_std": 0.08056489750742912,
      "rewards/correct_code_reward_func": 0.026041667442768812,
      "rewards/len_reward_func": 0.4663076810538769,
      "step": 61
    },
    {
      "completion_length": 28.75520920753479,
      "epoch": 0.8809946714031972,
      "grad_norm": 0.11091875740930289,
      "kl": 0.3428955078125,
      "learning_rate": 9.092076409533217e-07,
      "loss": 0.0003,
      "reward": 0.5182585716247559,
      "reward_std": 0.08795862831175327,
      "rewards/correct_code_reward_func": 0.03645833348855376,
      "rewards/len_reward_func": 0.48180023580789566,
      "step": 62
    },
    {
      "completion_length": 27.28645896911621,
      "epoch": 0.8952042628774423,
      "grad_norm": 0.11318375215447404,
      "kl": 0.298828125,
      "learning_rate": 9.058619561473306e-07,
      "loss": 0.0003,
      "reward": 0.5727054588496685,
      "reward_std": 0.13964871875941753,
      "rewards/correct_code_reward_func": 0.13020833767950535,
      "rewards/len_reward_func": 0.442497119307518,
      "step": 63
    },
    {
      "completion_length": 31.02083396911621,
      "epoch": 0.9094138543516874,
      "grad_norm": 0.1413294842874292,
      "kl": 0.270751953125,
      "learning_rate": 9.024621291968459e-07,
      "loss": 0.0003,
      "reward": 0.5525660812854767,
      "reward_std": 0.10817053186474368,
      "rewards/correct_code_reward_func": 0.07291667023673654,
      "rewards/len_reward_func": 0.4796494096517563,
      "step": 64
    },
    {
      "completion_length": 24.729167461395264,
      "epoch": 0.9236234458259325,
      "grad_norm": 0.21140332993990038,
      "kl": 0.35986328125,
      "learning_rate": 8.990086136401198e-07,
      "loss": 0.0004,
      "reward": 0.5117918439209461,
      "reward_std": 0.1768820770084858,
      "rewards/correct_code_reward_func": 0.052083334885537624,
      "rewards/len_reward_func": 0.4597085155546665,
      "step": 65
    },
    {
      "completion_length": 24.781250953674316,
      "epoch": 0.9378330373001776,
      "grad_norm": 0.10476750014203806,
      "kl": 0.4080810546875,
      "learning_rate": 8.955018701774846e-07,
      "loss": 0.0004,
      "reward": 0.536896102130413,
      "reward_std": 0.050523663870990276,
      "rewards/correct_code_reward_func": 0.06770833535119891,
      "rewards/len_reward_func": 0.46918775886297226,
      "step": 66
    },
    {
      "completion_length": 20.031250715255737,
      "epoch": 0.9520426287744227,
      "grad_norm": 0.2900012436857854,
      "kl": 0.4141845703125,
      "learning_rate": 8.919423666098969e-07,
      "loss": 0.0004,
      "reward": 0.5438988991081715,
      "reward_std": 0.12458856729790568,
      "rewards/correct_code_reward_func": 0.06250000186264515,
      "rewards/len_reward_func": 0.48139889165759087,
      "step": 67
    },
    {
      "completion_length": 21.760417222976685,
      "epoch": 0.9662522202486679,
      "grad_norm": 0.07393572026461089,
      "kl": 0.430419921875,
      "learning_rate": 8.883305777765317e-07,
      "loss": 0.0004,
      "reward": 0.5052083358168602,
      "reward_std": 0.044194173999130726,
      "rewards/correct_code_reward_func": 0.010416666977107525,
      "rewards/len_reward_func": 0.4947916679084301,
      "step": 68
    },
    {
      "completion_length": 21.057292222976685,
      "epoch": 0.9804618117229129,
      "grad_norm": 0.07068798291957223,
      "kl": 0.4051513671875,
      "learning_rate": 8.846669854914395e-07,
      "loss": 0.0004,
      "reward": 0.5047180242836475,
      "reward_std": 0.054715657606720924,
      "rewards/correct_code_reward_func": 0.031250000931322575,
      "rewards/len_reward_func": 0.47346802055835724,
      "step": 69
    },
    {
      "completion_length": 20.281250715255737,
      "epoch": 0.9946714031971581,
      "grad_norm": 0.10477200152886265,
      "kl": 0.474609375,
      "learning_rate": 8.809520784792709e-07,
      "loss": 0.0005,
      "reward": 0.5332689955830574,
      "reward_std": 0.10397791676223278,
      "rewards/correct_code_reward_func": 0.05208333395421505,
      "rewards/len_reward_func": 0.4811856485903263,
      "step": 70
    },
    {
      "completion_length": 17.222222646077473,
      "epoch": 1.0,
      "grad_norm": 0.10477200152886265,
      "kl": 0.6875,
      "learning_rate": 8.77186352310082e-07,
      "loss": 0.0003,
      "reward": 0.47803618510564166,
      "reward_std": 0.06212307761112849,
      "rewards/correct_code_reward_func": 0.0,
      "rewards/len_reward_func": 0.47803618510564166,
      "step": 71
    },
    {
      "completion_length": 19.182292342185974,
      "epoch": 1.0284191829484903,
      "grad_norm": 0.42476559750129594,
      "kl": 0.3858642578125,
      "learning_rate": 8.733703093332237e-07,
      "loss": 0.0004,
      "reward": 0.5539821274578571,
      "reward_std": 0.13098727632313967,
      "rewards/correct_code_reward_func": 0.09375000046566129,
      "rewards/len_reward_func": 0.46023212373256683,
      "step": 72
    },
    {
      "completion_length": 26.421875715255737,
      "epoch": 1.0426287744227354,
      "grad_norm": 0.2804083875710029,
      "kl": 0.3704833984375,
      "learning_rate": 8.695044586103295e-07,
      "loss": 0.0004,
      "reward": 0.5208719931542873,
      "reward_std": 0.12229002360254526,
      "rewards/correct_code_reward_func": 0.057291666977107525,
      "rewards/len_reward_func": 0.46358032524585724,
      "step": 73
    },
    {
      "completion_length": 21.098958730697632,
      "epoch": 1.0568383658969804,
      "grad_norm": 0.11314579736817262,
      "kl": 0.4814453125,
      "learning_rate": 8.655893158474054e-07,
      "loss": 0.0005,
      "reward": 0.5233512111008167,
      "reward_std": 0.059182871133089066,
      "rewards/correct_code_reward_func": 0.036458334885537624,
      "rewards/len_reward_func": 0.48689287155866623,
      "step": 74
    },
    {
      "completion_length": 19.729167103767395,
      "epoch": 1.0710479573712255,
      "grad_norm": 0.1058063111365568,
      "kl": 0.4874267578125,
      "learning_rate": 8.616254033260349e-07,
      "loss": 0.0005,
      "reward": 0.4835846647620201,
      "reward_std": 0.07345024310052395,
      "rewards/correct_code_reward_func": 0.010416666977107525,
      "rewards/len_reward_func": 0.47316799685359,
      "step": 75
    },
    {
      "completion_length": 30.052083730697632,
      "epoch": 1.0852575488454708,
      "grad_norm": 0.11588772133432072,
      "kl": 0.423583984375,
      "learning_rate": 8.576132498337067e-07,
      "loss": 0.0004,
      "reward": 0.5196206644177437,
      "reward_std": 0.05846347566694021,
      "rewards/correct_code_reward_func": 0.03645833395421505,
      "rewards/len_reward_func": 0.4831623286008835,
      "step": 76
    },
    {
      "completion_length": 23.541666984558105,
      "epoch": 1.0994671403197158,
      "grad_norm": 0.2267504620372045,
      "kl": 0.41455078125,
      "learning_rate": 8.535533905932737e-07,
      "loss": 0.0004,
      "reward": 0.6491265371441841,
      "reward_std": 0.14991778368130326,
      "rewards/correct_code_reward_func": 0.18750000512227416,
      "rewards/len_reward_func": 0.4616265334188938,
      "step": 77
    },
    {
      "completion_length": 23.432292342185974,
      "epoch": 1.1136767317939609,
      "grad_norm": 0.34562125964675733,
      "kl": 0.358154296875,
      "learning_rate": 8.494463671915546e-07,
      "loss": 0.0004,
      "reward": 0.5485623404383659,
      "reward_std": 0.12520829681307077,
      "rewards/correct_code_reward_func": 0.06770833441987634,
      "rewards/len_reward_func": 0.48085399344563484,
      "step": 78
    },
    {
      "completion_length": 20.5208340883255,
      "epoch": 1.1278863232682061,
      "grad_norm": 0.37433720129627873,
      "kl": 0.375732421875,
      "learning_rate": 8.452927275070857e-07,
      "loss": 0.0004,
      "reward": 0.6064328253269196,
      "reward_std": 0.1047948959749192,
      "rewards/correct_code_reward_func": 0.12500000139698386,
      "rewards/len_reward_func": 0.48143281042575836,
      "step": 79
    },
    {
      "completion_length": 19.781250715255737,
      "epoch": 1.1420959147424512,
      "grad_norm": 0.26978585250676396,
      "kl": 0.4266357421875,
      "learning_rate": 8.410930256370336e-07,
      "loss": 0.0004,
      "reward": 0.580853771418333,
      "reward_std": 0.12168336287140846,
      "rewards/correct_code_reward_func": 0.09375000465661287,
      "rewards/len_reward_func": 0.48710376396775246,
      "step": 80
    },
    {
      "completion_length": 19.838542222976685,
      "epoch": 1.1563055062166963,
      "grad_norm": 0.1937495108650144,
      "kl": 0.2789306640625,
      "learning_rate": 8.368478218232787e-07,
      "loss": 0.0003,
      "reward": 0.5655725002288818,
      "reward_std": 0.15722376480698586,
      "rewards/correct_code_reward_func": 0.08854166977107525,
      "rewards/len_reward_func": 0.47703082486987114,
      "step": 81
    },
    {
      "completion_length": 19.687500476837158,
      "epoch": 1.1705150976909413,
      "grad_norm": 0.9394417750605193,
      "kl": 0.384765625,
      "learning_rate": 8.325576823776783e-07,
      "loss": 0.0004,
      "reward": 0.5903935320675373,
      "reward_std": 0.16198670957237482,
      "rewards/correct_code_reward_func": 0.11458333674818277,
      "rewards/len_reward_func": 0.4758101888000965,
      "step": 82
    },
    {
      "completion_length": 27.416667222976685,
      "epoch": 1.1847246891651866,
      "grad_norm": 0.2585312839971323,
      "kl": 0.3731689453125,
      "learning_rate": 8.282231796065213e-07,
      "loss": 0.0004,
      "reward": 0.5114198848605156,
      "reward_std": 0.12062019482254982,
      "rewards/correct_code_reward_func": 0.04166666837409139,
      "rewards/len_reward_func": 0.4697532132267952,
      "step": 83
    },
    {
      "completion_length": 21.890625715255737,
      "epoch": 1.1989342806394316,
      "grad_norm": 0.2357685224671537,
      "kl": 0.433837890625,
      "learning_rate": 8.238448917341809e-07,
      "loss": 0.0004,
      "reward": 0.55494699254632,
      "reward_std": 0.10912239830940962,
      "rewards/correct_code_reward_func": 0.07812500139698386,
      "rewards/len_reward_func": 0.47682198882102966,
      "step": 84
    },
    {
      "completion_length": 28.380208790302277,
      "epoch": 1.2131438721136767,
      "grad_norm": 3.7100785272025143,
      "kl": 0.4244384765625,
      "learning_rate": 8.194234028259806e-07,
      "loss": 0.0004,
      "reward": 0.578259814530611,
      "reward_std": 0.14407706912606955,
      "rewards/correct_code_reward_func": 0.10937500186264515,
      "rewards/len_reward_func": 0.46888479217886925,
      "step": 85
    },
    {
      "completion_length": 38.44270920753479,
      "epoch": 1.2273534635879217,
      "grad_norm": 0.08273586468761443,
      "kl": 0.2978515625,
      "learning_rate": 8.149593027102788e-07,
      "loss": 0.0003,
      "reward": 0.5054225027561188,
      "reward_std": 0.12200409080833197,
      "rewards/correct_code_reward_func": 0.052083334885537624,
      "rewards/len_reward_func": 0.4533391706645489,
      "step": 86
    },
    {
      "completion_length": 25.322917938232422,
      "epoch": 1.241563055062167,
      "grad_norm": 0.7410755448183389,
      "kl": 0.24755859375,
      "learning_rate": 8.104531868997857e-07,
      "loss": 0.0002,
      "reward": 0.6100272089242935,
      "reward_std": 0.1286178290611133,
      "rewards/correct_code_reward_func": 0.13541667070239782,
      "rewards/len_reward_func": 0.4746105372905731,
      "step": 87
    },
    {
      "completion_length": 28.526042699813843,
      "epoch": 1.255772646536412,
      "grad_norm": 0.7585334872161575,
      "kl": 0.2691650390625,
      "learning_rate": 8.059056565121216e-07,
      "loss": 0.0003,
      "reward": 0.554522205144167,
      "reward_std": 0.12499295035377145,
      "rewards/correct_code_reward_func": 0.07812500325962901,
      "rewards/len_reward_func": 0.47639719769358635,
      "step": 88
    },
    {
      "completion_length": 31.135417938232422,
      "epoch": 1.2699822380106571,
      "grad_norm": 0.2699973643217227,
      "kl": 0.43157958984375,
      "learning_rate": 8.013173181896282e-07,
      "loss": 0.0004,
      "reward": 0.5836589224636555,
      "reward_std": 0.16798501182347536,
      "rewards/correct_code_reward_func": 0.10416667116805911,
      "rewards/len_reward_func": 0.4794922508299351,
      "step": 89
    },
    {
      "completion_length": 33.22395873069763,
      "epoch": 1.2841918294849024,
      "grad_norm": 0.5166673966387376,
      "kl": 0.3289794921875,
      "learning_rate": 7.966887840184411e-07,
      "loss": 0.0003,
      "reward": 0.6293128579854965,
      "reward_std": 0.17439470178214833,
      "rewards/correct_code_reward_func": 0.16666667256504297,
      "rewards/len_reward_func": 0.4626461751759052,
      "step": 90
    },
    {
      "completion_length": 22.588541984558105,
      "epoch": 1.2984014209591475,
      "grad_norm": 0.7957237408238673,
      "kl": 0.342529296875,
      "learning_rate": 7.920206714468383e-07,
      "loss": 0.0003,
      "reward": 0.6837037652730942,
      "reward_std": 0.22920069005340338,
      "rewards/correct_code_reward_func": 0.21875000605359674,
      "rewards/len_reward_func": 0.464953750371933,
      "step": 91
    },
    {
      "completion_length": 28.56770896911621,
      "epoch": 1.3126110124333925,
      "grad_norm": 0.33944221024019544,
      "kl": 0.265380859375,
      "learning_rate": 7.873136032028719e-07,
      "loss": 0.0003,
      "reward": 0.627902016043663,
      "reward_std": 0.17426282120868564,
      "rewards/correct_code_reward_func": 0.16666667722165585,
      "rewards/len_reward_func": 0.4612353481352329,
      "step": 92
    },
    {
      "completion_length": 29.734375476837158,
      "epoch": 1.3268206039076378,
      "grad_norm": 0.589334296961701,
      "kl": 0.33642578125,
      "learning_rate": 7.825682072112959e-07,
      "loss": 0.0003,
      "reward": 0.6710074618458748,
      "reward_std": 0.18177487421780825,
      "rewards/correct_code_reward_func": 0.21354166977107525,
      "rewards/len_reward_func": 0.4574657753109932,
      "step": 93
    },
    {
      "completion_length": 28.385417222976685,
      "epoch": 1.3410301953818828,
      "grad_norm": 0.42565995779148763,
      "kl": 0.3681640625,
      "learning_rate": 7.777851165098011e-07,
      "loss": 0.0004,
      "reward": 0.6528402864933014,
      "reward_std": 0.12080586049705744,
      "rewards/correct_code_reward_func": 0.16145833674818277,
      "rewards/len_reward_func": 0.4913819544017315,
      "step": 94
    },
    {
      "completion_length": 40.94270992279053,
      "epoch": 1.355239786856128,
      "grad_norm": 46.74774955764724,
      "kl": 46.2210693359375,
      "learning_rate": 7.729649691645672e-07,
      "loss": 0.0462,
      "reward": 0.6083209253847599,
      "reward_std": 0.2534871955867857,
      "rewards/correct_code_reward_func": 0.15625000465661287,
      "rewards/len_reward_func": 0.4520709253847599,
      "step": 95
    },
    {
      "completion_length": 38.60937583446503,
      "epoch": 1.369449378330373,
      "grad_norm": 0.4280395178418657,
      "kl": 0.2998046875,
      "learning_rate": 7.681084081851449e-07,
      "loss": 0.0003,
      "reward": 0.645279448479414,
      "reward_std": 0.21305734617635608,
      "rewards/correct_code_reward_func": 0.18750000512227416,
      "rewards/len_reward_func": 0.4577794410288334,
      "step": 96
    },
    {
      "completion_length": 25.416666984558105,
      "epoch": 1.383658969804618,
      "grad_norm": 0.8066482440910797,
      "kl": 0.27935791015625,
      "learning_rate": 7.632160814386779e-07,
      "loss": 0.0003,
      "reward": 0.7548199370503426,
      "reward_std": 0.24243795592337847,
      "rewards/correct_code_reward_func": 0.3020833386108279,
      "rewards/len_reward_func": 0.45273659378290176,
      "step": 97
    },
    {
      "completion_length": 30.97395944595337,
      "epoch": 1.3978685612788633,
      "grad_norm": 1.0983607583838806,
      "kl": 0.3016357421875,
      "learning_rate": 7.582886415634772e-07,
      "loss": 0.0003,
      "reward": 0.626206062734127,
      "reward_std": 0.1191985565237701,
      "rewards/correct_code_reward_func": 0.14583333767950535,
      "rewards/len_reward_func": 0.48037271201610565,
      "step": 98
    },
    {
      "completion_length": 34.015626192092896,
      "epoch": 1.4120781527531083,
      "grad_norm": 0.3663503819496649,
      "kl": 0.2886962890625,
      "learning_rate": 7.533267458819597e-07,
      "loss": 0.0003,
      "reward": 0.5679033361375332,
      "reward_std": 0.15581144578754902,
      "rewards/correct_code_reward_func": 0.09375000232830644,
      "rewards/len_reward_func": 0.4741533286869526,
      "step": 99
    },
    {
      "completion_length": 27.713542699813843,
      "epoch": 1.4262877442273534,
      "grad_norm": 0.4424492827570524,
      "kl": 0.39984130859375,
      "learning_rate": 7.483310563129591e-07,
      "loss": 0.0004,
      "reward": 0.5821606032550335,
      "reward_std": 0.13503185659646988,
      "rewards/correct_code_reward_func": 0.10416667023673654,
      "rewards/len_reward_func": 0.4779939204454422,
      "step": 100
    },
    {
      "completion_length": 27.666666984558105,
      "epoch": 1.4404973357015987,
      "grad_norm": 0.6653549818926682,
      "kl": 0.342529296875,
      "learning_rate": 7.43302239283428e-07,
      "loss": 0.0003,
      "reward": 0.7003941461443901,
      "reward_std": 0.1859769206494093,
      "rewards/correct_code_reward_func": 0.2291666753590107,
      "rewards/len_reward_func": 0.4712274558842182,
      "step": 101
    },
    {
      "completion_length": 29.42708420753479,
      "epoch": 1.4547069271758437,
      "grad_norm": 0.45141211142552334,
      "kl": 0.413330078125,
      "learning_rate": 7.382409656395352e-07,
      "loss": 0.0004,
      "reward": 0.6614639535546303,
      "reward_std": 0.15897755045443773,
      "rewards/correct_code_reward_func": 0.18229167629033327,
      "rewards/len_reward_func": 0.4791722781956196,
      "step": 102
    },
    {
      "completion_length": 30.276043176651,
      "epoch": 1.4689165186500888,
      "grad_norm": 0.6261531117653325,
      "kl": 0.2916259765625,
      "learning_rate": 7.33147910557174e-07,
      "loss": 0.0003,
      "reward": 0.6399556696414948,
      "reward_std": 0.20324960071593523,
      "rewards/correct_code_reward_func": 0.1614583353511989,
      "rewards/len_reward_func": 0.47849733382463455,
      "step": 103
    },
    {
      "completion_length": 32.03125047683716,
      "epoch": 1.483126110124334,
      "grad_norm": 0.489614499222203,
      "kl": 0.33404541015625,
      "learning_rate": 7.280237534518947e-07,
      "loss": 0.0003,
      "reward": 0.6721345707774162,
      "reward_std": 0.17973713018000126,
      "rewards/correct_code_reward_func": 0.1927083390764892,
      "rewards/len_reward_func": 0.47942622005939484,
      "step": 104
    },
    {
      "completion_length": 27.244792699813843,
      "epoch": 1.497335701598579,
      "grad_norm": 0.7237941037540044,
      "kl": 1.3876953125,
      "learning_rate": 7.228691778882692e-07,
      "loss": 0.0014,
      "reward": 0.607978418469429,
      "reward_std": 0.12438533711247146,
      "rewards/correct_code_reward_func": 0.12500000558793545,
      "rewards/len_reward_func": 0.4829784110188484,
      "step": 105
    },
    {
      "completion_length": 39.96875071525574,
      "epoch": 1.5115452930728241,
      "grad_norm": 0.2537904251082308,
      "kl": 0.329833984375,
      "learning_rate": 7.17684871488704e-07,
      "loss": 0.0003,
      "reward": 0.6410444527864456,
      "reward_std": 0.13352404907345772,
      "rewards/correct_code_reward_func": 0.1510416683740914,
      "rewards/len_reward_func": 0.4900027699768543,
      "step": 106
    },
    {
      "completion_length": 30.77083396911621,
      "epoch": 1.5257548845470694,
      "grad_norm": 0.5151072338350047,
      "kl": 0.423095703125,
      "learning_rate": 7.12471525841711e-07,
      "loss": 0.0004,
      "reward": 0.6993984878063202,
      "reward_std": 0.2649619020521641,
      "rewards/correct_code_reward_func": 0.23437500791624188,
      "rewards/len_reward_func": 0.4650234878063202,
      "step": 107
    },
    {
      "completion_length": 29.234375834465027,
      "epoch": 1.5399644760213143,
      "grad_norm": 0.5054486695261823,
      "kl": 0.4119873046875,
      "learning_rate": 7.072298364096485e-07,
      "loss": 0.0004,
      "reward": 0.760426938533783,
      "reward_std": 0.2561119059100747,
      "rewards/correct_code_reward_func": 0.27604168094694614,
      "rewards/len_reward_func": 0.48438524082303047,
      "step": 108
    },
    {
      "completion_length": 38.40104293823242,
      "epoch": 1.5541740674955595,
      "grad_norm": 0.4154161303239759,
      "kl": 0.2667236328125,
      "learning_rate": 7.019605024359474e-07,
      "loss": 0.0003,
      "reward": 0.647948831319809,
      "reward_std": 0.22292076144367456,
      "rewards/correct_code_reward_func": 0.19791667442768812,
      "rewards/len_reward_func": 0.45003215223550797,
      "step": 109
    },
    {
      "completion_length": 24.432291984558105,
      "epoch": 1.5683836589698046,
      "grad_norm": 0.28369234273858945,
      "kl": 0.5726318359375,
      "learning_rate": 6.966642268518313e-07,
      "loss": 0.0006,
      "reward": 0.6249856986105442,
      "reward_std": 0.1378673780709505,
      "rewards/correct_code_reward_func": 0.1406250069849193,
      "rewards/len_reward_func": 0.4843606911599636,
      "step": 110
    },
    {
      "completion_length": 36.22395980358124,
      "epoch": 1.5825932504440496,
      "grad_norm": 0.3398966236307633,
      "kl": 0.5732421875,
      "learning_rate": 6.913417161825449e-07,
      "loss": 0.0006,
      "reward": 0.7521518208086491,
      "reward_std": 0.26491443905979395,
      "rewards/correct_code_reward_func": 0.29687500931322575,
      "rewards/len_reward_func": 0.455276794731617,
      "step": 111
    },
    {
      "completion_length": 32.24479269981384,
      "epoch": 1.596802841918295,
      "grad_norm": 1.8347104056901153,
      "kl": 0.525634765625,
      "learning_rate": 6.859936804531038e-07,
      "loss": 0.0005,
      "reward": 0.7088249772787094,
      "reward_std": 0.2052869671024382,
      "rewards/correct_code_reward_func": 0.22916667768731713,
      "rewards/len_reward_func": 0.4796582944691181,
      "step": 112
    },
    {
      "completion_length": 41.156251430511475,
      "epoch": 1.61101243339254,
      "grad_norm": 0.6650497379051065,
      "kl": 0.8709716796875,
      "learning_rate": 6.806208330935766e-07,
      "loss": 0.0009,
      "reward": 0.6770701035857201,
      "reward_std": 0.2167337741702795,
      "rewards/correct_code_reward_func": 0.20833333861082792,
      "rewards/len_reward_func": 0.46873674914240837,
      "step": 113
    },
    {
      "completion_length": 46.052085399627686,
      "epoch": 1.625222024866785,
      "grad_norm": 0.6147925519531567,
      "kl": 0.452880859375,
      "learning_rate": 6.75223890843913e-07,
      "loss": 0.0005,
      "reward": 0.7727432176470757,
      "reward_std": 0.2623151782900095,
      "rewards/correct_code_reward_func": 0.30729168094694614,
      "rewards/len_reward_func": 0.46545154228806496,
      "step": 114
    },
    {
      "completion_length": 36.55208444595337,
      "epoch": 1.6394316163410303,
      "grad_norm": 2.8176275189378903,
      "kl": 5.8782958984375,
      "learning_rate": 6.698035736583306e-07,
      "loss": 0.0059,
      "reward": 0.6791222430765629,
      "reward_std": 0.25123584270477295,
      "rewards/correct_code_reward_func": 0.20312500465661287,
      "rewards/len_reward_func": 0.4759972207248211,
      "step": 115
    },
    {
      "completion_length": 44.781251192092896,
      "epoch": 1.6536412078152753,
      "grad_norm": 1.0142479035947602,
      "kl": 0.3837890625,
      "learning_rate": 6.643606046092731e-07,
      "loss": 0.0004,
      "reward": 0.7076524421572685,
      "reward_std": 0.26893263310194016,
      "rewards/correct_code_reward_func": 0.2500000102445483,
      "rewards/len_reward_func": 0.45765242725610733,
      "step": 116
    },
    {
      "completion_length": 43.72395968437195,
      "epoch": 1.6678507992895204,
      "grad_norm": 0.7005011696899197,
      "kl": 0.929931640625,
      "learning_rate": 6.588957097909507e-07,
      "loss": 0.0009,
      "reward": 0.6929139494895935,
      "reward_std": 0.141124508343637,
      "rewards/correct_code_reward_func": 0.20833334466442466,
      "rewards/len_reward_func": 0.4845805950462818,
      "step": 117
    },
    {
      "completion_length": 37.104167461395264,
      "epoch": 1.6820603907637657,
      "grad_norm": 1.2824494455811193,
      "kl": 1.44451904296875,
      "learning_rate": 6.534096182224808e-07,
      "loss": 0.0014,
      "reward": 0.84166669100523,
      "reward_std": 0.2773868013173342,
      "rewards/correct_code_reward_func": 0.3645833432674408,
      "rewards/len_reward_func": 0.47708334028720856,
      "step": 118
    },
    {
      "completion_length": 26.947917461395264,
      "epoch": 1.6962699822380105,
      "grad_norm": 1.9770555338030174,
      "kl": 0.467041015625,
      "learning_rate": 6.479030617506353e-07,
      "loss": 0.0005,
      "reward": 0.8274821788072586,
      "reward_std": 0.20418882556259632,
      "rewards/correct_code_reward_func": 0.3437500111758709,
      "rewards/len_reward_func": 0.4837321601808071,
      "step": 119
    },
    {
      "completion_length": 48.453126668930054,
      "epoch": 1.7104795737122558,
      "grad_norm": 2.506108274768271,
      "kl": 3.62835693359375,
      "learning_rate": 6.423767749522116e-07,
      "loss": 0.0036,
      "reward": 0.666666679084301,
      "reward_std": 0.15956056583672762,
      "rewards/correct_code_reward_func": 0.17187500232830644,
      "rewards/len_reward_func": 0.4947916679084301,
      "step": 120
    },
    {
      "completion_length": 35.822918176651,
      "epoch": 1.7246891651865008,
      "grad_norm": 1.8560376852510014,
      "kl": 4.44952392578125,
      "learning_rate": 6.368314950360415e-07,
      "loss": 0.0044,
      "reward": 0.7552083507180214,
      "reward_std": 0.15536189917474985,
      "rewards/correct_code_reward_func": 0.26041666930541396,
      "rewards/len_reward_func": 0.4947916679084301,
      "step": 121
    },
    {
      "completion_length": 33.70833444595337,
      "epoch": 1.738898756660746,
      "grad_norm": 0.45904672551268966,
      "kl": 0.5078125,
      "learning_rate": 6.312679617446452e-07,
      "loss": 0.0005,
      "reward": 0.7182956114411354,
      "reward_std": 0.1718872282654047,
      "rewards/correct_code_reward_func": 0.22395834233611822,
      "rewards/len_reward_func": 0.4943372532725334,
      "step": 122
    },
    {
      "completion_length": 32.88020873069763,
      "epoch": 1.7531083481349912,
      "grad_norm": 3.1831501565158478,
      "kl": 0.71435546875,
      "learning_rate": 6.256869172555513e-07,
      "loss": 0.0007,
      "reward": 0.8484800308942795,
      "reward_std": 0.24278247635811567,
      "rewards/correct_code_reward_func": 0.3593750074505806,
      "rewards/len_reward_func": 0.4891050197184086,
      "step": 123
    },
    {
      "completion_length": 44.86458444595337,
      "epoch": 1.7673179396092362,
      "grad_norm": 0.2782728331881645,
      "kl": 0.677734375,
      "learning_rate": 6.200891060822883e-07,
      "loss": 0.0007,
      "reward": 0.6989736668765545,
      "reward_std": 0.13764089718461037,
      "rewards/correct_code_reward_func": 0.20833333721384406,
      "rewards/len_reward_func": 0.4906403236091137,
      "step": 124
    },
    {
      "completion_length": 39.890625953674316,
      "epoch": 1.7815275310834813,
      "grad_norm": 0.4432863477791258,
      "kl": 1.2607421875,
      "learning_rate": 6.14475274975067e-07,
      "loss": 0.0013,
      "reward": 0.6557575240731239,
      "reward_std": 0.17638042569160461,
      "rewards/correct_code_reward_func": 0.17187500512227416,
      "rewards/len_reward_func": 0.48388250917196274,
      "step": 125
    },
    {
      "completion_length": 43.05729269981384,
      "epoch": 1.7957371225577266,
      "grad_norm": 0.9393860102080899,
      "kl": 5.0101318359375,
      "learning_rate": 6.088461728211641e-07,
      "loss": 0.005,
      "reward": 0.8028015419840813,
      "reward_std": 0.2515926621854305,
      "rewards/correct_code_reward_func": 0.3125000074505806,
      "rewards/len_reward_func": 0.4903015121817589,
      "step": 126
    },
    {
      "completion_length": 39.744792461395264,
      "epoch": 1.8099467140319716,
      "grad_norm": 0.30414354196646987,
      "kl": 1.528076171875,
      "learning_rate": 6.032025505450198e-07,
      "loss": 0.0015,
      "reward": 0.7219976708292961,
      "reward_std": 0.17846525833010674,
      "rewards/correct_code_reward_func": 0.2343750069849193,
      "rewards/len_reward_func": 0.4876226633787155,
      "step": 127
    },
    {
      "completion_length": 48.145835161209106,
      "epoch": 1.8241563055062167,
      "grad_norm": 0.9616807353931508,
      "kl": 2.9498291015625,
      "learning_rate": 5.975451610080642e-07,
      "loss": 0.003,
      "reward": 0.7878343798220158,
      "reward_std": 0.2312192926183343,
      "rewards/correct_code_reward_func": 0.3177083432674408,
      "rewards/len_reward_func": 0.47012604400515556,
      "step": 128
    },
    {
      "completion_length": 32.947917222976685,
      "epoch": 1.838365896980462,
      "grad_norm": 0.33574263810210525,
      "kl": 0.8221435546875,
      "learning_rate": 5.918747589082852e-07,
      "loss": 0.0008,
      "reward": 0.7830323353409767,
      "reward_std": 0.2828069757670164,
      "rewards/correct_code_reward_func": 0.31250000512227416,
      "rewards/len_reward_func": 0.4705323241651058,
      "step": 129
    },
    {
      "completion_length": 37.70833444595337,
      "epoch": 1.8525754884547068,
      "grad_norm": 0.7681491620069113,
      "kl": 0.31298828125,
      "learning_rate": 5.861921006795521e-07,
      "loss": 0.0003,
      "reward": 0.8222656548023224,
      "reward_std": 0.24159616511315107,
      "rewards/correct_code_reward_func": 0.32812500931322575,
      "rewards/len_reward_func": 0.4941406287252903,
      "step": 130
    },
    {
      "completion_length": 33.23958432674408,
      "epoch": 1.866785079928952,
      "grad_norm": 0.6430281428056408,
      "kl": 1.143310546875,
      "learning_rate": 5.804979443907064e-07,
      "loss": 0.0011,
      "reward": 0.7285900413990021,
      "reward_std": 0.17855742387473583,
      "rewards/correct_code_reward_func": 0.23958334373310208,
      "rewards/len_reward_func": 0.4890067018568516,
      "step": 131
    },
    {
      "completion_length": 24.104167222976685,
      "epoch": 1.8809946714031973,
      "grad_norm": 0.24041644743408275,
      "kl": 1.277099609375,
      "learning_rate": 5.747930496444356e-07,
      "loss": 0.0013,
      "reward": 0.8438289314508438,
      "reward_std": 0.19152645766735077,
      "rewards/correct_code_reward_func": 0.354166679084301,
      "rewards/len_reward_func": 0.4896622523665428,
      "step": 132
    },
    {
      "completion_length": 43.38541769981384,
      "epoch": 1.8952042628774421,
      "grad_norm": 0.6431641395148254,
      "kl": 0.939697265625,
      "learning_rate": 5.690781774759412e-07,
      "loss": 0.0009,
      "reward": 0.6867811977863312,
      "reward_std": 0.1539960578083992,
      "rewards/correct_code_reward_func": 0.21875000512227416,
      "rewards/len_reward_func": 0.4680311977863312,
      "step": 133
    },
    {
      "completion_length": 44.48437547683716,
      "epoch": 1.9094138543516874,
      "grad_norm": 0.21833096723094597,
      "kl": 0.998779296875,
      "learning_rate": 5.633540902514169e-07,
      "loss": 0.001,
      "reward": 0.7760416977107525,
      "reward_std": 0.17763367015868425,
      "rewards/correct_code_reward_func": 0.2864583432674408,
      "rewards/len_reward_func": 0.4895833358168602,
      "step": 134
    },
    {
      "completion_length": 47.80729293823242,
      "epoch": 1.9236234458259325,
      "grad_norm": 21.399250710183935,
      "kl": 33.49798583984375,
      "learning_rate": 5.576215515663488e-07,
      "loss": 0.0337,
      "reward": 0.8613281324505806,
      "reward_std": 0.27823825646191835,
      "rewards/correct_code_reward_func": 0.385416679084301,
      "rewards/len_reward_func": 0.4759114645421505,
      "step": 135
    },
    {
      "completion_length": 39.23958420753479,
      "epoch": 1.9378330373001775,
      "grad_norm": 1.0397469628530305,
      "kl": 3.8271484375,
      "learning_rate": 5.518813261436509e-07,
      "loss": 0.0038,
      "reward": 0.8433021306991577,
      "reward_std": 0.28113674372434616,
      "rewards/correct_code_reward_func": 0.3541666744276881,
      "rewards/len_reward_func": 0.4891354478895664,
      "step": 136
    },
    {
      "completion_length": 39.906251192092896,
      "epoch": 1.9520426287744228,
      "grad_norm": 0.4423722033923989,
      "kl": 2.48828125,
      "learning_rate": 5.46134179731651e-07,
      "loss": 0.0025,
      "reward": 0.745168749243021,
      "reward_std": 0.19209052313817665,
      "rewards/correct_code_reward_func": 0.2552083432674408,
      "rewards/len_reward_func": 0.4899603873491287,
      "step": 137
    },
    {
      "completion_length": 39.01041769981384,
      "epoch": 1.9662522202486679,
      "grad_norm": 0.6503067727209519,
      "kl": 3.81982421875,
      "learning_rate": 5.403808790019397e-07,
      "loss": 0.0038,
      "reward": 0.7963728755712509,
      "reward_std": 0.19714439380913973,
      "rewards/correct_code_reward_func": 0.31250000838190317,
      "rewards/len_reward_func": 0.4838728532195091,
      "step": 138
    },
    {
      "completion_length": 37.9114590883255,
      "epoch": 1.980461811722913,
      "grad_norm": 24.787021841302984,
      "kl": 57.88232421875,
      "learning_rate": 5.346221914470958e-07,
      "loss": 0.0579,
      "reward": 0.7864583656191826,
      "reward_std": 0.24389999359846115,
      "rewards/correct_code_reward_func": 0.2916666781529784,
      "rewards/len_reward_func": 0.4947916679084301,
      "step": 139
    },
    {
      "completion_length": 41.328126192092896,
      "epoch": 1.9946714031971582,
      "grad_norm": 0.7937636640763135,
      "kl": 3.69189453125,
      "learning_rate": 5.28858885278303e-07,
      "loss": 0.0037,
      "reward": 0.9266427755355835,
      "reward_std": 0.29586102720350027,
      "rewards/correct_code_reward_func": 0.43229168048128486,
      "rewards/len_reward_func": 0.4943510703742504,
      "step": 140
    },
    {
      "completion_length": 39.33333466269753,
      "epoch": 2.0142095914742453,
      "grad_norm": 0.2768424230561695,
      "kl": 0.9209872159090909,
      "learning_rate": 5.230917293228698e-07,
      "loss": 0.0013,
      "reward": 0.8532484119588678,
      "reward_std": 0.20929343727501956,
      "rewards/correct_code_reward_func": 0.3636363704096187,
      "rewards/len_reward_func": 0.489612032066692,
      "step": 141
    },
    {
      "completion_length": 39.546875953674316,
      "epoch": 2.02841918294849,
      "grad_norm": 0.16952169342643555,
      "kl": 0.705078125,
      "learning_rate": 5.173214929216676e-07,
      "loss": 0.0007,
      "reward": 0.7856172472238541,
      "reward_std": 0.24064217414706945,
      "rewards/correct_code_reward_func": 0.30729167675599456,
      "rewards/len_reward_func": 0.47832557559013367,
      "step": 142
    },
    {
      "completion_length": 44.83854293823242,
      "epoch": 2.0426287744227354,
      "grad_norm": 1.0337544965149752,
      "kl": 0.47821044921875,
      "learning_rate": 5.115489458265005e-07,
      "loss": 0.0005,
      "reward": 0.9237679168581963,
      "reward_std": 0.29668530635535717,
      "rewards/correct_code_reward_func": 0.4531250111758709,
      "rewards/len_reward_func": 0.47064292058348656,
      "step": 143
    },
    {
      "completion_length": 51.05208373069763,
      "epoch": 2.0568383658969807,
      "grad_norm": 0.46558060707856164,
      "kl": 3.0306396484375,
      "learning_rate": 5.057748580974204e-07,
      "loss": 0.003,
      "reward": 0.7902894243597984,
      "reward_std": 0.27399154007434845,
      "rewards/correct_code_reward_func": 0.2968750069849193,
      "rewards/len_reward_func": 0.49341440945863724,
      "step": 144
    },
    {
      "completion_length": 64.25521087646484,
      "epoch": 2.0710479573712255,
      "grad_norm": 2.832947418992901,
      "kl": 0.54052734375,
      "learning_rate": 5e-07,
      "loss": 0.0005,
      "reward": 0.7385099269449711,
      "reward_std": 0.22076672816183418,
      "rewards/correct_code_reward_func": 0.2708333395421505,
      "rewards/len_reward_func": 0.4676765874028206,
      "step": 145
    },
    {
      "completion_length": 37.42708468437195,
      "epoch": 2.0852575488454708,
      "grad_norm": 0.3157493333671525,
      "kl": 2.2481689453125,
      "learning_rate": 4.942251419025797e-07,
      "loss": 0.0023,
      "reward": 0.802083358168602,
      "reward_std": 0.19236505404114723,
      "rewards/correct_code_reward_func": 0.30208334093913436,
      "rewards/len_reward_func": 0.5,
      "step": 146
    },
    {
      "completion_length": 41.718751192092896,
      "epoch": 2.0994671403197156,
      "grad_norm": 1.107213732783492,
      "kl": 0.7342529296875,
      "learning_rate": 4.884510541734994e-07,
      "loss": 0.0007,
      "reward": 0.8593750298023224,
      "reward_std": 0.20375474449247122,
      "rewards/correct_code_reward_func": 0.35937501303851604,
      "rewards/len_reward_func": 0.5,
      "step": 147
    },
    {
      "completion_length": 40.63541793823242,
      "epoch": 2.113676731793961,
      "grad_norm": 0.7145373701563043,
      "kl": 2.3194580078125,
      "learning_rate": 4.826785070783326e-07,
      "loss": 0.0023,
      "reward": 0.8897242248058319,
      "reward_std": 0.2690112553536892,
      "rewards/correct_code_reward_func": 0.4010416781529784,
      "rewards/len_reward_func": 0.4886825196444988,
      "step": 148
    },
    {
      "completion_length": 32.07291769981384,
      "epoch": 2.127886323268206,
      "grad_norm": 0.31462107153591495,
      "kl": 0.665771484375,
      "learning_rate": 4.769082706771303e-07,
      "loss": 0.0007,
      "reward": 0.9681454822421074,
      "reward_std": 0.24282564595341682,
      "rewards/correct_code_reward_func": 0.47395834885537624,
      "rewards/len_reward_func": 0.4941871277987957,
      "step": 149
    },
    {
      "completion_length": 38.260418176651,
      "epoch": 2.142095914742451,
      "grad_norm": 1.103169258480424,
      "kl": 0.5745849609375,
      "learning_rate": 4.711411147216969e-07,
      "loss": 0.0006,
      "reward": 0.8335540443658829,
      "reward_std": 0.2559899231418967,
      "rewards/correct_code_reward_func": 0.3489583390764892,
      "rewards/len_reward_func": 0.4845956936478615,
      "step": 150
    },
    {
      "completion_length": 37.04166769981384,
      "epoch": 2.1563055062166963,
      "grad_norm": 10.180643820226365,
      "kl": 13.5958251953125,
      "learning_rate": 4.653778085529042e-07,
      "loss": 0.0136,
      "reward": 0.8042732700705528,
      "reward_std": 0.147595196031034,
      "rewards/correct_code_reward_func": 0.30729167675599456,
      "rewards/len_reward_func": 0.49698158353567123,
      "step": 151
    },
    {
      "completion_length": 45.47395896911621,
      "epoch": 2.1705150976909415,
      "grad_norm": 0.8489598031308032,
      "kl": 0.3529052734375,
      "learning_rate": 4.596191209980603e-07,
      "loss": 0.0004,
      "reward": 0.7601608335971832,
      "reward_std": 0.28048667032271624,
      "rewards/correct_code_reward_func": 0.26562500512227416,
      "rewards/len_reward_func": 0.49453581869602203,
      "step": 152
    },
    {
      "completion_length": 41.432292461395264,
      "epoch": 2.1847246891651864,
      "grad_norm": 3.1369790309071353,
      "kl": 0.77783203125,
      "learning_rate": 4.5386582026834904e-07,
      "loss": 0.0008,
      "reward": 0.8266517594456673,
      "reward_std": 0.19582488853484392,
      "rewards/correct_code_reward_func": 0.3281250139698386,
      "rewards/len_reward_func": 0.4985267296433449,
      "step": 153
    },
    {
      "completion_length": 51.72395992279053,
      "epoch": 2.1989342806394316,
      "grad_norm": 0.5844119599007116,
      "kl": 4.0391845703125,
      "learning_rate": 4.481186738563491e-07,
      "loss": 0.004,
      "reward": 0.6927604451775551,
      "reward_std": 0.22623706236481667,
      "rewards/correct_code_reward_func": 0.20833334000781178,
      "rewards/len_reward_func": 0.4844270870089531,
      "step": 154
    },
    {
      "completion_length": 41.750001430511475,
      "epoch": 2.213143872113677,
      "grad_norm": 0.6110965881466496,
      "kl": 0.89599609375,
      "learning_rate": 4.423784484336512e-07,
      "loss": 0.0009,
      "reward": 0.8773777335882187,
      "reward_std": 0.2839722502976656,
      "rewards/correct_code_reward_func": 0.39583334513008595,
      "rewards/len_reward_func": 0.4815443903207779,
      "step": 155
    },
    {
      "completion_length": 38.104167222976685,
      "epoch": 2.2273534635879217,
      "grad_norm": 0.2550807520293701,
      "kl": 1.1385498046875,
      "learning_rate": 4.366459097485831e-07,
      "loss": 0.0011,
      "reward": 0.9322917014360428,
      "reward_std": 0.1595638357102871,
      "rewards/correct_code_reward_func": 0.432291679084301,
      "rewards/len_reward_func": 0.5,
      "step": 156
    },
    {
      "completion_length": 41.901042461395264,
      "epoch": 2.241563055062167,
      "grad_norm": 0.22395601103120769,
      "kl": 1.453369140625,
      "learning_rate": 4.30921822524059e-07,
      "loss": 0.0015,
      "reward": 0.851693332195282,
      "reward_std": 0.22127470280975103,
      "rewards/correct_code_reward_func": 0.3593750111758709,
      "rewards/len_reward_func": 0.4923183061182499,
      "step": 157
    },
    {
      "completion_length": 41.791667461395264,
      "epoch": 2.2557726465364123,
      "grad_norm": 0.6799732648924857,
      "kl": 0.6934814453125,
      "learning_rate": 4.252069503555644e-07,
      "loss": 0.0007,
      "reward": 0.8672677129507065,
      "reward_std": 0.2567566800862551,
      "rewards/correct_code_reward_func": 0.38020834513008595,
      "rewards/len_reward_func": 0.4870593473315239,
      "step": 158
    },
    {
      "completion_length": 53.156250953674316,
      "epoch": 2.269982238010657,
      "grad_norm": 0.20435817979893578,
      "kl": 9.634033203125,
      "learning_rate": 4.1950205560929346e-07,
      "loss": 0.0096,
      "reward": 0.908984400331974,
      "reward_std": 0.17828166484832764,
      "rewards/correct_code_reward_func": 0.4218750111758709,
      "rewards/len_reward_func": 0.48710937425494194,
      "step": 159
    },
    {
      "completion_length": 51.16145992279053,
      "epoch": 2.2841918294849024,
      "grad_norm": 3.803907096451742,
      "kl": 1.4273681640625,
      "learning_rate": 4.138078993204479e-07,
      "loss": 0.0014,
      "reward": 0.6979166865348816,
      "reward_std": 0.13870323821902275,
      "rewards/correct_code_reward_func": 0.19791667349636555,
      "rewards/len_reward_func": 0.5,
      "step": 160
    },
    {
      "completion_length": 59.05729389190674,
      "epoch": 2.2984014209591472,
      "grad_norm": 0.7167592493540498,
      "kl": 3.62890625,
      "learning_rate": 4.0812524109171475e-07,
      "loss": 0.0036,
      "reward": 0.7500000223517418,
      "reward_std": 0.25635149516165257,
      "rewards/correct_code_reward_func": 0.25520833767950535,
      "rewards/len_reward_func": 0.4947916679084301,
      "step": 161
    },
    {
      "completion_length": 43.44270944595337,
      "epoch": 2.3126110124333925,
      "grad_norm": 0.3153275312496973,
      "kl": 1.86962890625,
      "learning_rate": 4.0245483899193586e-07,
      "loss": 0.0019,
      "reward": 0.8561735972762108,
      "reward_std": 0.2931099245324731,
      "rewards/correct_code_reward_func": 0.369791679084301,
      "rewards/len_reward_func": 0.4863819107413292,
      "step": 162
    },
    {
      "completion_length": 39.890625953674316,
      "epoch": 2.326820603907638,
      "grad_norm": 0.4190244971062534,
      "kl": 3.064697265625,
      "learning_rate": 3.967974494549802e-07,
      "loss": 0.0031,
      "reward": 0.8042862862348557,
      "reward_std": 0.1808705097064376,
      "rewards/correct_code_reward_func": 0.3072916795499623,
      "rewards/len_reward_func": 0.49699458479881287,
      "step": 163
    },
    {
      "completion_length": 41.197918176651,
      "epoch": 2.3410301953818826,
      "grad_norm": 0.404874418021672,
      "kl": 0.9036865234375,
      "learning_rate": 3.9115382717883583e-07,
      "loss": 0.0009,
      "reward": 0.8468539044260979,
      "reward_std": 0.2628004178404808,
      "rewards/correct_code_reward_func": 0.3645833400078118,
      "rewards/len_reward_func": 0.4822705388069153,
      "step": 164
    },
    {
      "completion_length": 37.432291984558105,
      "epoch": 2.355239786856128,
      "grad_norm": 63.834283690985856,
      "kl": 209.67138671875,
      "learning_rate": 3.8552472502493306e-07,
      "loss": 0.21,
      "reward": 0.8125000298023224,
      "reward_std": 0.11344761867076159,
      "rewards/correct_code_reward_func": 0.31250001257285476,
      "rewards/len_reward_func": 0.5,
      "step": 165
    },
    {
      "completion_length": 44.80729341506958,
      "epoch": 2.369449378330373,
      "grad_norm": 0.3804074748777271,
      "kl": 0.6700439453125,
      "learning_rate": 3.799108939177118e-07,
      "loss": 0.0007,
      "reward": 0.9006362631917,
      "reward_std": 0.22100094705820084,
      "rewards/correct_code_reward_func": 0.4114583497866988,
      "rewards/len_reward_func": 0.4891778938472271,
      "step": 166
    },
    {
      "completion_length": 40.88541793823242,
      "epoch": 2.383658969804618,
      "grad_norm": 3.058303353601836,
      "kl": 7.721435546875,
      "learning_rate": 3.743130827444486e-07,
      "loss": 0.0077,
      "reward": 0.7770512029528618,
      "reward_std": 0.23528988752514124,
      "rewards/correct_code_reward_func": 0.2916666711680591,
      "rewards/len_reward_func": 0.4853845275938511,
      "step": 167
    },
    {
      "completion_length": 44.93229293823242,
      "epoch": 2.3978685612788633,
      "grad_norm": 0.22413557209543042,
      "kl": 0.57763671875,
      "learning_rate": 3.687320382553547e-07,
      "loss": 0.0006,
      "reward": 0.7187500223517418,
      "reward_std": 0.1465982012450695,
      "rewards/correct_code_reward_func": 0.21875000558793545,
      "rewards/len_reward_func": 0.5,
      "step": 168
    },
    {
      "completion_length": 41.963542222976685,
      "epoch": 2.412078152753108,
      "grad_norm": 0.14010353539214773,
      "kl": 1.7593994140625,
      "learning_rate": 3.6316850496395855e-07,
      "loss": 0.0018,
      "reward": 0.7978501804172993,
      "reward_std": 0.2182563552632928,
      "rewards/correct_code_reward_func": 0.3072916753590107,
      "rewards/len_reward_func": 0.490558497607708,
      "step": 169
    },
    {
      "completion_length": 33.28645920753479,
      "epoch": 2.4262877442273534,
      "grad_norm": 0.6688998892951643,
      "kl": 1.3453369140625,
      "learning_rate": 3.5762322504778843e-07,
      "loss": 0.0014,
      "reward": 0.8706771209836006,
      "reward_std": 0.27033482026308775,
      "rewards/correct_code_reward_func": 0.3854166786186397,
      "rewards/len_reward_func": 0.48526042327284813,
      "step": 170
    },
    {
      "completion_length": 54.61458492279053,
      "epoch": 2.4404973357015987,
      "grad_norm": 25.55850989003896,
      "kl": 33.40087890625,
      "learning_rate": 3.520969382493648e-07,
      "loss": 0.0334,
      "reward": 0.7340934947133064,
      "reward_std": 0.22803436033427715,
      "rewards/correct_code_reward_func": 0.24479167815297842,
      "rewards/len_reward_func": 0.48930180445313454,
      "step": 171
    },
    {
      "completion_length": 50.75520968437195,
      "epoch": 2.4547069271758435,
      "grad_norm": 1.0993433115329139,
      "kl": 0.52197265625,
      "learning_rate": 3.4659038177751916e-07,
      "loss": 0.0005,
      "reward": 0.8320630416274071,
      "reward_std": 0.33004763070493937,
      "rewards/correct_code_reward_func": 0.3385416748933494,
      "rewards/len_reward_func": 0.4935213439166546,
      "step": 172
    },
    {
      "completion_length": 33.56250071525574,
      "epoch": 2.4689165186500888,
      "grad_norm": 0.27986368427021807,
      "kl": 0.5650634765625,
      "learning_rate": 3.4110429020904916e-07,
      "loss": 0.0006,
      "reward": 0.8020833507180214,
      "reward_std": 0.25357052125036716,
      "rewards/correct_code_reward_func": 0.3125000074505806,
      "rewards/len_reward_func": 0.4895833358168602,
      "step": 173
    },
    {
      "completion_length": 45.864585161209106,
      "epoch": 2.483126110124334,
      "grad_norm": 0.5428500069552784,
      "kl": 0.302978515625,
      "learning_rate": 3.3563939539072707e-07,
      "loss": 0.0003,
      "reward": 0.92354666441679,
      "reward_std": 0.2541873175650835,
      "rewards/correct_code_reward_func": 0.4270833432674408,
      "rewards/len_reward_func": 0.4964633099734783,
      "step": 174
    },
    {
      "completion_length": 42.20833420753479,
      "epoch": 2.497335701598579,
      "grad_norm": 0.17239852403039482,
      "kl": 1.567138671875,
      "learning_rate": 3.3019642634166925e-07,
      "loss": 0.0016,
      "reward": 0.8260380998253822,
      "reward_std": 0.304103652946651,
      "rewards/correct_code_reward_func": 0.3489583395421505,
      "rewards/len_reward_func": 0.47707975283265114,
      "step": 175
    },
    {
      "completion_length": 46.84375190734863,
      "epoch": 2.511545293072824,
      "grad_norm": 0.5116759066919949,
      "kl": 0.441650390625,
      "learning_rate": 3.24776109156087e-07,
      "loss": 0.0004,
      "reward": 0.7602619901299477,
      "reward_std": 0.23501227423548698,
      "rewards/correct_code_reward_func": 0.26562500931322575,
      "rewards/len_reward_func": 0.4946369640529156,
      "step": 176
    },
    {
      "completion_length": 37.171875953674316,
      "epoch": 2.5257548845470694,
      "grad_norm": 0.2731372372030952,
      "kl": 0.846923828125,
      "learning_rate": 3.1937916690642355e-07,
      "loss": 0.0008,
      "reward": 0.8064460530877113,
      "reward_std": 0.20957951620221138,
      "rewards/correct_code_reward_func": 0.3177083362825215,
      "rewards/len_reward_func": 0.48873770982027054,
      "step": 177
    },
    {
      "completion_length": 48.114585161209106,
      "epoch": 2.5399644760213143,
      "grad_norm": 0.18020857417244746,
      "kl": 0.5279541015625,
      "learning_rate": 3.140063195468962e-07,
      "loss": 0.0005,
      "reward": 0.8477237969636917,
      "reward_std": 0.22288063261657953,
      "rewards/correct_code_reward_func": 0.3541666786186397,
      "rewards/len_reward_func": 0.4935570992529392,
      "step": 178
    },
    {
      "completion_length": 43.734376430511475,
      "epoch": 2.5541740674955595,
      "grad_norm": 15.313566775633127,
      "kl": 29.7022705078125,
      "learning_rate": 3.086582838174551e-07,
      "loss": 0.0298,
      "reward": 0.8531691208481789,
      "reward_std": 0.23031365312635899,
      "rewards/correct_code_reward_func": 0.35937501257285476,
      "rewards/len_reward_func": 0.4937940947711468,
      "step": 179
    },
    {
      "completion_length": 39.89583432674408,
      "epoch": 2.568383658969805,
      "grad_norm": 112515.52153399677,
      "kl": 139298.5975341797,
      "learning_rate": 3.0333577314816875e-07,
      "loss": 139.3682,
      "reward": 0.989583358168602,
      "reward_std": 0.3011222751811147,
      "rewards/correct_code_reward_func": 0.5000000111758709,
      "rewards/len_reward_func": 0.4895833358168602,
      "step": 180
    },
    {
      "completion_length": 38.44270944595337,
      "epoch": 2.5825932504440496,
      "grad_norm": 0.1599191853306774,
      "kl": 0.4254150390625,
      "learning_rate": 2.9803949756405254e-07,
      "loss": 0.0004,
      "reward": 0.8020833358168602,
      "reward_std": 0.16973543167114258,
      "rewards/correct_code_reward_func": 0.3020833358168602,
      "rewards/len_reward_func": 0.5,
      "step": 181
    },
    {
      "completion_length": 54.33333468437195,
      "epoch": 2.596802841918295,
      "grad_norm": 0.31649564819934856,
      "kl": 1.3349609375,
      "learning_rate": 2.9277016359035163e-07,
      "loss": 0.0013,
      "reward": 0.8594289347529411,
      "reward_std": 0.22909861989319324,
      "rewards/correct_code_reward_func": 0.36979167349636555,
      "rewards/len_reward_func": 0.48963725194334984,
      "step": 182
    },
    {
      "completion_length": 50.95833468437195,
      "epoch": 2.61101243339254,
      "grad_norm": 0.5145196306499781,
      "kl": 0.6405029296875,
      "learning_rate": 2.875284741582892e-07,
      "loss": 0.0006,
      "reward": 0.8060533851385117,
      "reward_std": 0.2804380664601922,
      "rewards/correct_code_reward_func": 0.33333333721384406,
      "rewards/len_reward_func": 0.47272003069519997,
      "step": 183
    },
    {
      "completion_length": 42.838542461395264,
      "epoch": 2.625222024866785,
      "grad_norm": 0.22208711166004375,
      "kl": 0.6759033203125,
      "learning_rate": 2.823151285112959e-07,
      "loss": 0.0007,
      "reward": 0.8385416865348816,
      "reward_std": 0.2426884388551116,
      "rewards/correct_code_reward_func": 0.34375000838190317,
      "rewards/len_reward_func": 0.4947916679084301,
      "step": 184
    },
    {
      "completion_length": 47.47916793823242,
      "epoch": 2.6394316163410303,
      "grad_norm": 0.6222604426382311,
      "kl": 71.3514404296875,
      "learning_rate": 2.771308221117309e-07,
      "loss": 0.0714,
      "reward": 0.8202716186642647,
      "reward_std": 0.30131243355572224,
      "rewards/correct_code_reward_func": 0.328125006519258,
      "rewards/len_reward_func": 0.4921466000378132,
      "step": 185
    },
    {
      "completion_length": 50.89583444595337,
      "epoch": 2.6536412078152756,
      "grad_norm": 48.546398517399325,
      "kl": 0.80908203125,
      "learning_rate": 2.7197624654810546e-07,
      "loss": 0.0008,
      "reward": 0.901041716337204,
      "reward_std": 0.2770571205765009,
      "rewards/correct_code_reward_func": 0.4062500149011612,
      "rewards/len_reward_func": 0.4947916679084301,
      "step": 186
    },
    {
      "completion_length": 48.78645992279053,
      "epoch": 2.6678507992895204,
      "grad_norm": 0.9346680475903489,
      "kl": 0.44091796875,
      "learning_rate": 2.668520894428259e-07,
      "loss": 0.0004,
      "reward": 0.8802083507180214,
      "reward_std": 0.3098616087809205,
      "rewards/correct_code_reward_func": 0.3906250037252903,
      "rewards/len_reward_func": 0.4895833358168602,
      "step": 187
    },
    {
      "completion_length": 45.61458444595337,
      "epoch": 2.6820603907637657,
      "grad_norm": 82.14841075144975,
      "kl": 259.4200439453125,
      "learning_rate": 2.6175903436046474e-07,
      "loss": 0.2596,
      "reward": 0.947916716337204,
      "reward_std": 0.20077416393905878,
      "rewards/correct_code_reward_func": 0.45312502002343535,
      "rewards/len_reward_func": 0.4947916679084301,
      "step": 188
    },
    {
      "completion_length": 31.109375715255737,
      "epoch": 2.6962699822380105,
      "grad_norm": 7.335460633947408,
      "kl": 11.451416015625,
      "learning_rate": 2.566977607165719e-07,
      "loss": 0.0114,
      "reward": 0.9093469232320786,
      "reward_std": 0.17798435501754284,
      "rewards/correct_code_reward_func": 0.4270833423361182,
      "rewards/len_reward_func": 0.48226356878876686,
      "step": 189
    },
    {
      "completion_length": 55.67708373069763,
      "epoch": 2.710479573712256,
      "grad_norm": 1.1753891580581173,
      "kl": 0.35736083984375,
      "learning_rate": 2.516689436870409e-07,
      "loss": 0.0004,
      "reward": 0.8493160903453827,
      "reward_std": 0.2846128651872277,
      "rewards/correct_code_reward_func": 0.36979167675599456,
      "rewards/len_reward_func": 0.4795243963599205,
      "step": 190
    },
    {
      "completion_length": 50.421875953674316,
      "epoch": 2.7246891651865006,
      "grad_norm": 2.960071630098768,
      "kl": 13.67919921875,
      "learning_rate": 2.4667325411804036e-07,
      "loss": 0.0137,
      "reward": 0.8125000223517418,
      "reward_std": 0.14746366068720818,
      "rewards/correct_code_reward_func": 0.31770834093913436,
      "rewards/len_reward_func": 0.4947916679084301,
      "step": 191
    },
    {
      "completion_length": 37.04687571525574,
      "epoch": 2.738898756660746,
      "grad_norm": 0.1669736440647054,
      "kl": 1.35009765625,
      "learning_rate": 2.417113584365225e-07,
      "loss": 0.0014,
      "reward": 0.9415922686457634,
      "reward_std": 0.19716626964509487,
      "rewards/correct_code_reward_func": 0.4531250027939677,
      "rewards/len_reward_func": 0.4884672649204731,
      "step": 192
    },
    {
      "completion_length": 49.98958492279053,
      "epoch": 2.753108348134991,
      "grad_norm": 1.0320355915126407,
      "kl": 0.497802734375,
      "learning_rate": 2.3678391856132202e-07,
      "loss": 0.0005,
      "reward": 0.7982630506157875,
      "reward_std": 0.28407367691397667,
      "rewards/correct_code_reward_func": 0.30729167629033327,
      "rewards/len_reward_func": 0.4909713715314865,
      "step": 193
    },
    {
      "completion_length": 56.12500214576721,
      "epoch": 2.767317939609236,
      "grad_norm": 0.5525240092695006,
      "kl": 2.7349853515625,
      "learning_rate": 2.3189159181485511e-07,
      "loss": 0.0027,
      "reward": 0.9010416865348816,
      "reward_std": 0.2404085397720337,
      "rewards/correct_code_reward_func": 0.4062500111758709,
      "rewards/len_reward_func": 0.4947916679084301,
      "step": 194
    },
    {
      "completion_length": 42.75520992279053,
      "epoch": 2.7815275310834813,
      "grad_norm": 0.572524088783038,
      "kl": 1.264892578125,
      "learning_rate": 2.2703503083543285e-07,
      "loss": 0.0013,
      "reward": 0.7187500111758709,
      "reward_std": 0.2014781143516302,
      "rewards/correct_code_reward_func": 0.22916666697710752,
      "rewards/len_reward_func": 0.4895833358168602,
      "step": 195
    },
    {
      "completion_length": 41.687501192092896,
      "epoch": 2.7957371225577266,
      "grad_norm": 1.9076571581064141,
      "kl": 3.22705078125,
      "learning_rate": 2.2221488349019902e-07,
      "loss": 0.0032,
      "reward": 0.906250037252903,
      "reward_std": 0.26040368247777224,
      "rewards/correct_code_reward_func": 0.4114583507180214,
      "rewards/len_reward_func": 0.4947916679084301,
      "step": 196
    },
    {
      "completion_length": 50.78125047683716,
      "epoch": 2.8099467140319714,
      "grad_norm": 0.2925242241129777,
      "kl": 0.4791259765625,
      "learning_rate": 2.1743179278870406e-07,
      "loss": 0.0005,
      "reward": 0.771132156252861,
      "reward_std": 0.24617953225970268,
      "rewards/correct_code_reward_func": 0.2812500102445483,
      "rewards/len_reward_func": 0.48988213390111923,
      "step": 197
    },
    {
      "completion_length": 43.81250190734863,
      "epoch": 2.8241563055062167,
      "grad_norm": 0.4585182436296359,
      "kl": 0.4405517578125,
      "learning_rate": 2.1268639679712813e-07,
      "loss": 0.0004,
      "reward": 0.9768589586019516,
      "reward_std": 0.1660878909751773,
      "rewards/correct_code_reward_func": 0.4791666828095913,
      "rewards/len_reward_func": 0.4976922422647476,
      "step": 198
    },
    {
      "completion_length": 37.01562571525574,
      "epoch": 2.838365896980462,
      "grad_norm": 0.7655822014190156,
      "kl": 5.3253173828125,
      "learning_rate": 2.079793285531618e-07,
      "loss": 0.0053,
      "reward": 0.7916666977107525,
      "reward_std": 0.1390610933303833,
      "rewards/correct_code_reward_func": 0.29687500884756446,
      "rewards/len_reward_func": 0.4947916679084301,
      "step": 199
    },
    {
      "completion_length": 53.74479413032532,
      "epoch": 2.8525754884547068,
      "grad_norm": 0.45661864295296545,
      "kl": 1.05712890625,
      "learning_rate": 2.0331121598155904e-07,
      "loss": 0.0011,
      "reward": 0.875000037252903,
      "reward_std": 0.22781990841031075,
      "rewards/correct_code_reward_func": 0.38020834885537624,
      "rewards/len_reward_func": 0.4947916679084301,
      "step": 200
    },
    {
      "completion_length": 45.645835638046265,
      "epoch": 2.866785079928952,
      "grad_norm": 0.48651527407332873,
      "kl": 1.75341796875,
      "learning_rate": 1.9868268181037184e-07,
      "loss": 0.0018,
      "reward": 0.7708333507180214,
      "reward_std": 0.13678119890391827,
      "rewards/correct_code_reward_func": 0.2708333390764892,
      "rewards/len_reward_func": 0.5,
      "step": 201
    },
    {
      "completion_length": 41.406251192092896,
      "epoch": 2.8809946714031973,
      "grad_norm": 0.878376430404186,
      "kl": 2.983642578125,
      "learning_rate": 1.9409434348787824e-07,
      "loss": 0.003,
      "reward": 0.94061429053545,
      "reward_std": 0.2256631813943386,
      "rewards/correct_code_reward_func": 0.447916679084301,
      "rewards/len_reward_func": 0.4926975965499878,
      "step": 202
    },
    {
      "completion_length": 42.510417461395264,
      "epoch": 2.895204262877442,
      "grad_norm": 1.1422482589666494,
      "kl": 1.164794921875,
      "learning_rate": 1.895468131002143e-07,
      "loss": 0.0012,
      "reward": 0.7031250074505806,
      "reward_std": 0.1651789052411914,
      "rewards/correct_code_reward_func": 0.203125003259629,
      "rewards/len_reward_func": 0.5,
      "step": 203
    },
    {
      "completion_length": 54.83854341506958,
      "epoch": 2.9094138543516874,
      "grad_norm": 0.8345541671777533,
      "kl": 0.595703125,
      "learning_rate": 1.8504069728972122e-07,
      "loss": 0.0006,
      "reward": 0.910145677626133,
      "reward_std": 0.27820600755512714,
      "rewards/correct_code_reward_func": 0.4166666716337204,
      "rewards/len_reward_func": 0.49347899854183197,
      "step": 204
    },
    {
      "completion_length": 49.46354293823242,
      "epoch": 2.9236234458259327,
      "grad_norm": 1.2302166960375758,
      "kl": 0.9273681640625,
      "learning_rate": 1.8057659717401946e-07,
      "loss": 0.0009,
      "reward": 0.786458358168602,
      "reward_std": 0.23023366834968328,
      "rewards/correct_code_reward_func": 0.2864583432674408,
      "rewards/len_reward_func": 0.5,
      "step": 205
    },
    {
      "completion_length": 46.86979293823242,
      "epoch": 2.9378330373001775,
      "grad_norm": 0.1249737333020878,
      "kl": 0.6566162109375,
      "learning_rate": 1.7615510826581903e-07,
      "loss": 0.0007,
      "reward": 0.8119391277432442,
      "reward_std": 0.2090762620791793,
      "rewards/correct_code_reward_func": 0.32291667303070426,
      "rewards/len_reward_func": 0.4890224374830723,
      "step": 206
    },
    {
      "completion_length": 42.25520896911621,
      "epoch": 2.952042628774423,
      "grad_norm": 3.621296330131346,
      "kl": 0.477294921875,
      "learning_rate": 1.7177682039347873e-07,
      "loss": 0.0005,
      "reward": 0.9947916865348816,
      "reward_std": 0.2800409598276019,
      "rewards/correct_code_reward_func": 0.5000000111758709,
      "rewards/len_reward_func": 0.4947916679084301,
      "step": 207
    },
    {
      "completion_length": 40.276042461395264,
      "epoch": 2.966252220248668,
      "grad_norm": 1.1618881730971975,
      "kl": 2.3177490234375,
      "learning_rate": 1.6744231762232176e-07,
      "loss": 0.0023,
      "reward": 0.8541666939854622,
      "reward_std": 0.15571126155555248,
      "rewards/correct_code_reward_func": 0.35416667349636555,
      "rewards/len_reward_func": 0.5,
      "step": 208
    },
    {
      "completion_length": 41.76041841506958,
      "epoch": 2.980461811722913,
      "grad_norm": 0.12730259920443027,
      "kl": 0.673828125,
      "learning_rate": 1.631521781767214e-07,
      "loss": 0.0007,
      "reward": 0.881994940340519,
      "reward_std": 0.23983055353164673,
      "rewards/correct_code_reward_func": 0.3906250176951289,
      "rewards/len_reward_func": 0.49136991426348686,
      "step": 209
    },
    {
      "completion_length": 51.20833492279053,
      "epoch": 2.994671403197158,
      "grad_norm": 0.34499595252081194,
      "kl": 0.808349609375,
      "learning_rate": 1.5890697436296645e-07,
      "loss": 0.0008,
      "reward": 0.812827505171299,
      "reward_std": 0.1982624065130949,
      "rewards/correct_code_reward_func": 0.3281250074505806,
      "rewards/len_reward_func": 0.4847024828195572,
      "step": 210
    },
    {
      "completion_length": 50.583334604899086,
      "epoch": 3.0,
      "grad_norm": 0.34499595252081194,
      "kl": 0.2890625,
      "learning_rate": 1.5470727249291422e-07,
      "loss": 0.0001,
      "reward": 0.9023265639940897,
      "reward_std": 0.2996095319588979,
      "rewards/correct_code_reward_func": 0.4027777910232544,
      "rewards/len_reward_func": 0.499548743168513,
      "step": 211
    },
    {
      "completion_length": 45.44791841506958,
      "epoch": 3.0142095914742453,
      "grad_norm": 0.5341987315778469,
      "kl": 0.485595703125,
      "learning_rate": 1.505536328084453e-07,
      "loss": 0.0005,
      "reward": 0.8854166865348816,
      "reward_std": 0.19464496430009604,
      "rewards/correct_code_reward_func": 0.38541667303070426,
      "rewards/len_reward_func": 0.5,
      "step": 212
    },
    {
      "completion_length": 44.875001668930054,
      "epoch": 3.02841918294849,
      "grad_norm": 0.2863245800425785,
      "kl": 1.21875,
      "learning_rate": 1.4644660940672627e-07,
      "loss": 0.0012,
      "reward": 0.7656250149011612,
      "reward_std": 0.1757064014673233,
      "rewards/correct_code_reward_func": 0.2760416744276881,
      "rewards/len_reward_func": 0.4895833358168602,
      "step": 213
    },
    {
      "completion_length": 45.666667461395264,
      "epoch": 3.0426287744227354,
      "grad_norm": 0.3746292030692342,
      "kl": 1.8707275390625,
      "learning_rate": 1.4238675016629336e-07,
      "loss": 0.0019,
      "reward": 0.817708358168602,
      "reward_std": 0.24829828273504972,
      "rewards/correct_code_reward_func": 0.32291668048128486,
      "rewards/len_reward_func": 0.4947916679084301,
      "step": 214
    },
    {
      "completion_length": 44.47395920753479,
      "epoch": 3.0568383658969807,
      "grad_norm": 0.784441267858788,
      "kl": 1.3236083984375,
      "learning_rate": 1.3837459667396517e-07,
      "loss": 0.0013,
      "reward": 0.8854166939854622,
      "reward_std": 0.2861669007688761,
      "rewards/correct_code_reward_func": 0.3906250149011612,
      "rewards/len_reward_func": 0.4947916679084301,
      "step": 215
    },
    {
      "completion_length": 38.88541793823242,
      "epoch": 3.0710479573712255,
      "grad_norm": 0.20790015109496335,
      "kl": 2.206298828125,
      "learning_rate": 1.344106841525946e-07,
      "loss": 0.0022,
      "reward": 0.9601633101701736,
      "reward_std": 0.28697047755122185,
      "rewards/correct_code_reward_func": 0.4635416828095913,
      "rewards/len_reward_func": 0.49662161991000175,
      "step": 216
    },
    {
      "completion_length": 44.47395944595337,
      "epoch": 3.0852575488454708,
      "grad_norm": 0.6911394155457643,
      "kl": 4.766357421875,
      "learning_rate": 1.304955413896705e-07,
      "loss": 0.0048,
      "reward": 0.8329957202076912,
      "reward_std": 0.186056193895638,
      "rewards/correct_code_reward_func": 0.3385416832752526,
      "rewards/len_reward_func": 0.4944540336728096,
      "step": 217
    },
    {
      "completion_length": 44.73437690734863,
      "epoch": 3.0994671403197156,
      "grad_norm": 0.9192557895819068,
      "kl": 0.651611328125,
      "learning_rate": 1.2662969066677621e-07,
      "loss": 0.0007,
      "reward": 0.8593750447034836,
      "reward_std": 0.2593386024236679,
      "rewards/correct_code_reward_func": 0.3645833437331021,
      "rewards/len_reward_func": 0.4947916679084301,
      "step": 218
    },
    {
      "completion_length": 57.218751192092896,
      "epoch": 3.113676731793961,
      "grad_norm": 0.2574079640390334,
      "kl": 1.1007080078125,
      "learning_rate": 1.2281364768991804e-07,
      "loss": 0.0011,
      "reward": 0.7343742251396179,
      "reward_std": 0.21236247196793556,
      "rewards/correct_code_reward_func": 0.25520834466442466,
      "rewards/len_reward_func": 0.47916587069630623,
      "step": 219
    },
    {
      "completion_length": 46.046876430511475,
      "epoch": 3.127886323268206,
      "grad_norm": 2.0904566419493444,
      "kl": 2.238525390625,
      "learning_rate": 1.1904792152072912e-07,
      "loss": 0.0022,
      "reward": 0.9270833656191826,
      "reward_std": 0.23989244643598795,
      "rewards/correct_code_reward_func": 0.43229167675599456,
      "rewards/len_reward_func": 0.4947916679084301,
      "step": 220
    },
    {
      "completion_length": 44.68750047683716,
      "epoch": 3.142095914742451,
      "grad_norm": 0.13444904722147802,
      "kl": 1.0106201171875,
      "learning_rate": 1.1533301450856053e-07,
      "loss": 0.001,
      "reward": 0.8319229185581207,
      "reward_std": 0.22844316437840462,
      "rewards/correct_code_reward_func": 0.33854167722165585,
      "rewards/len_reward_func": 0.49338123202323914,
      "step": 221
    },
    {
      "completion_length": 48.16145944595337,
      "epoch": 3.1563055062166963,
      "grad_norm": 0.41181203893806084,
      "kl": 1.3980712890625,
      "learning_rate": 1.1166942222346826e-07,
      "loss": 0.0014,
      "reward": 0.7636535055935383,
      "reward_std": 0.22669691406190395,
      "rewards/correct_code_reward_func": 0.2708333390764892,
      "rewards/len_reward_func": 0.4928201548755169,
      "step": 222
    },
    {
      "completion_length": 48.75000214576721,
      "epoch": 3.1705150976909415,
      "grad_norm": 1.248440761102657,
      "kl": 0.5626220703125,
      "learning_rate": 1.0805763339010327e-07,
      "loss": 0.0006,
      "reward": 0.9284223094582558,
      "reward_std": 0.14435529988259077,
      "rewards/correct_code_reward_func": 0.4427083507180214,
      "rewards/len_reward_func": 0.48571396991610527,
      "step": 223
    },
    {
      "completion_length": 53.17708492279053,
      "epoch": 3.1847246891651864,
      "grad_norm": 0.16193688793698843,
      "kl": 0.4945068359375,
      "learning_rate": 1.0449812982251554e-07,
      "loss": 0.0005,
      "reward": 0.81609146296978,
      "reward_std": 0.18448682688176632,
      "rewards/correct_code_reward_func": 0.3177083386108279,
      "rewards/len_reward_func": 0.498383104801178,
      "step": 224
    },
    {
      "completion_length": 47.44791769981384,
      "epoch": 3.1989342806394316,
      "grad_norm": 0.5847586668509419,
      "kl": 44.950439453125,
      "learning_rate": 1.0099138635988024e-07,
      "loss": 0.0452,
      "reward": 0.822036612778902,
      "reward_std": 0.2441820139065385,
      "rewards/correct_code_reward_func": 0.3385416720993817,
      "rewards/len_reward_func": 0.48349493369460106,
      "step": 225
    },
    {
      "completion_length": 43.578126430511475,
      "epoch": 3.213143872113677,
      "grad_norm": 35.078623310693565,
      "kl": 1.111083984375,
      "learning_rate": 9.753787080315385e-08,
      "loss": 0.0011,
      "reward": 0.9579768925905228,
      "reward_std": 0.3044539736583829,
      "rewards/correct_code_reward_func": 0.4687500111758709,
      "rewards/len_reward_func": 0.4892268776893616,
      "step": 226
    },
    {
      "completion_length": 40.07291877269745,
      "epoch": 3.2273534635879217,
      "grad_norm": 1.037122944672265,
      "kl": 2.140380859375,
      "learning_rate": 9.413804385266939e-08,
      "loss": 0.0021,
      "reward": 0.8727592378854752,
      "reward_std": 0.1667407499626279,
      "rewards/correct_code_reward_func": 0.3750000074505806,
      "rewards/len_reward_func": 0.4977592043578625,
      "step": 227
    },
    {
      "completion_length": 49.677085161209106,
      "epoch": 3.241563055062167,
      "grad_norm": 0.5833402123777717,
      "kl": 1.079345703125,
      "learning_rate": 9.079235904667825e-08,
      "loss": 0.0011,
      "reward": 0.8535077124834061,
      "reward_std": 0.2195202987641096,
      "rewards/correct_code_reward_func": 0.4010416818782687,
      "rewards/len_reward_func": 0.4524660259485245,
      "step": 228
    },
    {
      "completion_length": 58.843751430511475,
      "epoch": 3.2557726465364123,
      "grad_norm": 0.3147528942512585,
      "kl": 2.2379150390625,
      "learning_rate": 8.75012627008489e-08,
      "loss": 0.0022,
      "reward": 0.9322916939854622,
      "reward_std": 0.2747772177681327,
      "rewards/correct_code_reward_func": 0.4375000111758709,
      "rewards/len_reward_func": 0.4947916679084301,
      "step": 229
    },
    {
      "completion_length": 44.140626192092896,
      "epoch": 3.269982238010657,
      "grad_norm": 1.5346703995653477,
      "kl": 0.49658203125,
      "learning_rate": 8.426519384872732e-08,
      "loss": 0.0005,
      "reward": 0.8302317634224892,
      "reward_std": 0.266538561321795,
      "rewards/correct_code_reward_func": 0.33333334140479565,
      "rewards/len_reward_func": 0.4968984089791775,
      "step": 230
    },
    {
      "completion_length": 49.25000178813934,
      "epoch": 3.2841918294849024,
      "grad_norm": 0.4281621451147006,
      "kl": 494.783203125,
      "learning_rate": 8.108458418317088e-08,
      "loss": 0.4939,
      "reward": 0.8093860596418381,
      "reward_std": 0.22010277584195137,
      "rewards/correct_code_reward_func": 0.3125000111758709,
      "rewards/len_reward_func": 0.4968860261142254,
      "step": 231
    },
    {
      "completion_length": 56.864585399627686,
      "epoch": 3.2984014209591472,
      "grad_norm": 198.79113548542654,
      "kl": 1.9140625,
      "learning_rate": 7.795985799875898e-08,
      "loss": 0.0019,
      "reward": 0.8116681799292564,
      "reward_std": 0.232976489700377,
      "rewards/correct_code_reward_func": 0.32291666977107525,
      "rewards/len_reward_func": 0.48875150457024574,
      "step": 232
    },
    {
      "completion_length": 33.66666793823242,
      "epoch": 3.3126110124333925,
      "grad_norm": 0.9552505868651456,
      "kl": 1.68994140625,
      "learning_rate": 7.4891432135193e-08,
      "loss": 0.0017,
      "reward": 0.8243930637836456,
      "reward_std": 0.195878223516047,
      "rewards/correct_code_reward_func": 0.3281250102445483,
      "rewards/len_reward_func": 0.49626804515719414,
      "step": 233
    },
    {
      "completion_length": 51.34375190734863,
      "epoch": 3.326820603907638,
      "grad_norm": 0.4456482049602369,
      "kl": 0.7779541015625,
      "learning_rate": 7.187971592168934e-08,
      "loss": 0.0008,
      "reward": 0.7219517193734646,
      "reward_std": 0.1749192081624642,
      "rewards/correct_code_reward_func": 0.23437500651925802,
      "rewards/len_reward_func": 0.4875767044723034,
      "step": 234
    },
    {
      "completion_length": 61.15625238418579,
      "epoch": 3.3410301953818826,
      "grad_norm": 0.32419354347659146,
      "kl": 9.3094482421875,
      "learning_rate": 6.89251111223747e-08,
      "loss": 0.0093,
      "reward": 0.7473166286945343,
      "reward_std": 0.22721262462437153,
      "rewards/correct_code_reward_func": 0.2552083423361182,
      "rewards/len_reward_func": 0.4921082742512226,
      "step": 235
    },
    {
      "completion_length": 42.31770968437195,
      "epoch": 3.355239786856128,
      "grad_norm": 0.4538956651064026,
      "kl": 2.867431640625,
      "learning_rate": 6.60280118826908e-08,
      "loss": 0.0029,
      "reward": 0.8854166865348816,
      "reward_std": 0.1522198049351573,
      "rewards/correct_code_reward_func": 0.39062501257285476,
      "rewards/len_reward_func": 0.4947916679084301,
      "step": 236
    },
    {
      "completion_length": 56.11979293823242,
      "epoch": 3.369449378330373,
      "grad_norm": 0.9726666923969292,
      "kl": 0.4404296875,
      "learning_rate": 6.318880467681526e-08,
      "loss": 0.0004,
      "reward": 0.83645249158144,
      "reward_std": 0.29575006011873484,
      "rewards/correct_code_reward_func": 0.354166679084301,
      "rewards/len_reward_func": 0.4822858013212681,
      "step": 237
    },
    {
      "completion_length": 46.02604341506958,
      "epoch": 3.383658969804618,
      "grad_norm": 0.33496216070372276,
      "kl": 0.4874267578125,
      "learning_rate": 6.040786825610517e-08,
      "loss": 0.0005,
      "reward": 0.8958333507180214,
      "reward_std": 0.26774444058537483,
      "rewards/correct_code_reward_func": 0.3958333395421505,
      "rewards/len_reward_func": 0.5,
      "step": 238
    },
    {
      "completion_length": 43.19270992279053,
      "epoch": 3.3978685612788633,
      "grad_norm": 0.5050928301026154,
      "kl": 2.2333984375,
      "learning_rate": 5.76855735985724e-08,
      "loss": 0.0022,
      "reward": 0.7075844705104828,
      "reward_std": 0.20798933878540993,
      "rewards/correct_code_reward_func": 0.21875000791624188,
      "rewards/len_reward_func": 0.4888344518840313,
      "step": 239
    },
    {
      "completion_length": 43.765626192092896,
      "epoch": 3.412078152753108,
      "grad_norm": 0.2983468152500676,
      "kl": 2.171630859375,
      "learning_rate": 5.502228385939417e-08,
      "loss": 0.0022,
      "reward": 0.7999647110700607,
      "reward_std": 0.21641080733388662,
      "rewards/correct_code_reward_func": 0.3177083432674408,
      "rewards/len_reward_func": 0.48225635662674904,
      "step": 240
    },
    {
      "completion_length": 54.781250953674316,
      "epoch": 3.4262877442273534,
      "grad_norm": 0.36490238911088607,
      "kl": 0.4703369140625,
      "learning_rate": 5.2418354322468884e-08,
      "loss": 0.0005,
      "reward": 0.9130137860774994,
      "reward_std": 0.26248283311724663,
      "rewards/correct_code_reward_func": 0.4166666753590107,
      "rewards/len_reward_func": 0.4963470995426178,
      "step": 241
    },
    {
      "completion_length": 40.03645944595337,
      "epoch": 3.4404973357015987,
      "grad_norm": 0.16488515230964834,
      "kl": 0.821044921875,
      "learning_rate": 4.987413235302024e-08,
      "loss": 0.0008,
      "reward": 0.875726692378521,
      "reward_std": 0.25851976312696934,
      "rewards/correct_code_reward_func": 0.39062501303851604,
      "rewards/len_reward_func": 0.4851016625761986,
      "step": 242
    },
    {
      "completion_length": 44.83854365348816,
      "epoch": 3.4547069271758435,
      "grad_norm": 0.4843065129937312,
      "kl": 0.6356201171875,
      "learning_rate": 4.7389957351258944e-08,
      "loss": 0.0006,
      "reward": 0.8385416939854622,
      "reward_std": 0.24971272889524698,
      "rewards/correct_code_reward_func": 0.3489583507180214,
      "rewards/len_reward_func": 0.4895833358168602,
      "step": 243
    },
    {
      "completion_length": 44.963542461395264,
      "epoch": 3.4689165186500888,
      "grad_norm": 0.586157830499415,
      "kl": 1.402587890625,
      "learning_rate": 4.4966160707107073e-08,
      "loss": 0.0014,
      "reward": 0.8906250223517418,
      "reward_std": 0.18446683045476675,
      "rewards/correct_code_reward_func": 0.4010416753590107,
      "rewards/len_reward_func": 0.4895833358168602,
      "step": 244
    },
    {
      "completion_length": 42.84895992279053,
      "epoch": 3.483126110124334,
      "grad_norm": 0.41279174954334164,
      "kl": 1.044189453125,
      "learning_rate": 4.2603065755989484e-08,
      "loss": 0.001,
      "reward": 0.8204832896590233,
      "reward_std": 0.21049257181584835,
      "rewards/correct_code_reward_func": 0.3281250102445483,
      "rewards/len_reward_func": 0.4923582673072815,
      "step": 245
    },
    {
      "completion_length": 38.58333444595337,
      "epoch": 3.497335701598579,
      "grad_norm": 0.15781453889206523,
      "kl": 2801.0478515625,
      "learning_rate": 4.030098773570173e-08,
      "loss": 2.7963,
      "reward": 0.854166679084301,
      "reward_std": 0.1560691138729453,
      "rewards/correct_code_reward_func": 0.35416667303070426,
      "rewards/len_reward_func": 0.5,
      "step": 246
    },
    {
      "completion_length": 34.60416769981384,
      "epoch": 3.511545293072824,
      "grad_norm": 3804.5442280672096,
      "kl": 22.07958984375,
      "learning_rate": 3.806023374435663e-08,
      "loss": 0.0221,
      "reward": 0.9427083507180214,
      "reward_std": 0.21392960660159588,
      "rewards/correct_code_reward_func": 0.4427083469927311,
      "rewards/len_reward_func": 0.5,
      "step": 247
    },
    {
      "completion_length": 50.82291793823242,
      "epoch": 3.5257548845470694,
      "grad_norm": 1.0012457049302241,
      "kl": 0.417724609375,
      "learning_rate": 3.5881102699417466e-08,
      "loss": 0.0004,
      "reward": 0.8072258271276951,
      "reward_std": 0.2475466374307871,
      "rewards/correct_code_reward_func": 0.32291667629033327,
      "rewards/len_reward_func": 0.4843091182410717,
      "step": 248
    },
    {
      "completion_length": 43.619792222976685,
      "epoch": 3.5399644760213143,
      "grad_norm": 1.2942485305126314,
      "kl": 1.679443359375,
      "learning_rate": 3.376388529782215e-08,
      "loss": 0.0017,
      "reward": 0.8229166977107525,
      "reward_std": 0.23094089701771736,
      "rewards/correct_code_reward_func": 0.32812501257285476,
      "rewards/len_reward_func": 0.4947916679084301,
      "step": 249
    },
    {
      "completion_length": 39.82812547683716,
      "epoch": 3.5541740674955595,
      "grad_norm": 0.30228196280940167,
      "kl": 1.0738525390625,
      "learning_rate": 3.170886397720435e-08,
      "loss": 0.0011,
      "reward": 0.901041679084301,
      "reward_std": 0.26845165714621544,
      "rewards/correct_code_reward_func": 0.4010416753590107,
      "rewards/len_reward_func": 0.5,
      "step": 250
    },
    {
      "completion_length": 46.510418176651,
      "epoch": 3.568383658969805,
      "grad_norm": 0.8200506569476771,
      "kl": 0.637939453125,
      "learning_rate": 2.9716312878216187e-08,
      "loss": 0.0006,
      "reward": 0.8281250298023224,
      "reward_std": 0.17814126797020435,
      "rewards/correct_code_reward_func": 0.3281250102445483,
      "rewards/len_reward_func": 0.5,
      "step": 251
    },
    {
      "completion_length": 47.82291841506958,
      "epoch": 3.5825932504440496,
      "grad_norm": 0.10844345022988316,
      "kl": 0.9287109375,
      "learning_rate": 2.7786497807957386e-08,
      "loss": 0.0009,
      "reward": 0.9101763144135475,
      "reward_std": 0.1877366304397583,
      "rewards/correct_code_reward_func": 0.42187501257285476,
      "rewards/len_reward_func": 0.48830128461122513,
      "step": 252
    },
    {
      "completion_length": 48.07291865348816,
      "epoch": 3.596802841918295,
      "grad_norm": 0.5084473429432326,
      "kl": 9.809814453125,
      "learning_rate": 2.591967620451707e-08,
      "loss": 0.0098,
      "reward": 0.7748463377356529,
      "reward_std": 0.2692983113229275,
      "rewards/correct_code_reward_func": 0.276041672565043,
      "rewards/len_reward_func": 0.49880464375019073,
      "step": 253
    },
    {
      "completion_length": 32.765625953674316,
      "epoch": 3.61101243339254,
      "grad_norm": 3.951132610904558,
      "kl": 0.872314453125,
      "learning_rate": 2.4116097102630906e-08,
      "loss": 0.0009,
      "reward": 0.968750037252903,
      "reward_std": 0.18553190026432276,
      "rewards/correct_code_reward_func": 0.47395834513008595,
      "rewards/len_reward_func": 0.4947916679084301,
      "step": 254
    },
    {
      "completion_length": 43.69791793823242,
      "epoch": 3.625222024866785,
      "grad_norm": 1.4069394496568932,
      "kl": 1.546630859375,
      "learning_rate": 2.237600110046001e-08,
      "loss": 0.0015,
      "reward": 0.8232645876705647,
      "reward_std": 0.15157399233430624,
      "rewards/correct_code_reward_func": 0.3385416753590107,
      "rewards/len_reward_func": 0.48472290113568306,
      "step": 255
    },
    {
      "completion_length": 40.17187571525574,
      "epoch": 3.6394316163410303,
      "grad_norm": 0.16308475825332436,
      "kl": 9.180908203125,
      "learning_rate": 2.0699620327495172e-08,
      "loss": 0.0092,
      "reward": 0.890625037252903,
      "reward_std": 0.26794405467808247,
      "rewards/correct_code_reward_func": 0.3906250149011612,
      "rewards/len_reward_func": 0.5,
      "step": 256
    },
    {
      "completion_length": 45.145835161209106,
      "epoch": 3.6536412078152756,
      "grad_norm": 2.916569118369544,
      "kl": 0.723388671875,
      "learning_rate": 1.9087178413590476e-08,
      "loss": 0.0007,
      "reward": 0.8898493200540543,
      "reward_std": 0.31095184944570065,
      "rewards/correct_code_reward_func": 0.390625006519258,
      "rewards/len_reward_func": 0.4992242902517319,
      "step": 257
    },
    {
      "completion_length": 41.47916841506958,
      "epoch": 3.6678507992895204,
      "grad_norm": 0.6930015320130729,
      "kl": 1.2630615234375,
      "learning_rate": 1.7538890459131096e-08,
      "loss": 0.0013,
      "reward": 0.8784802556037903,
      "reward_std": 0.28579425904899836,
      "rewards/correct_code_reward_func": 0.38541667349636555,
      "rewards/len_reward_func": 0.4930635616183281,
      "step": 258
    },
    {
      "completion_length": 46.708335161209106,
      "epoch": 3.6820603907637657,
      "grad_norm": 2.6485859637763323,
      "kl": 1.714599609375,
      "learning_rate": 1.605496300633874e-08,
      "loss": 0.0017,
      "reward": 0.9218750149011612,
      "reward_std": 0.35549131594598293,
      "rewards/correct_code_reward_func": 0.4322916753590107,
      "rewards/len_reward_func": 0.4895833358168602,
      "step": 259
    },
    {
      "completion_length": 37.78645968437195,
      "epoch": 3.6962699822380105,
      "grad_norm": 0.4431164780858953,
      "kl": 0.720703125,
      "learning_rate": 1.4635594011718933e-08,
      "loss": 0.0007,
      "reward": 0.7785784117877483,
      "reward_std": 0.1691737649962306,
      "rewards/correct_code_reward_func": 0.2864583390764892,
      "rewards/len_reward_func": 0.49212006852030754,
      "step": 260
    },
    {
      "completion_length": 58.66145920753479,
      "epoch": 3.710479573712256,
      "grad_norm": 0.24284031920399382,
      "kl": 0.4285888671875,
      "learning_rate": 1.328097281965357e-08,
      "loss": 0.0004,
      "reward": 0.8645833730697632,
      "reward_std": 0.254782073199749,
      "rewards/correct_code_reward_func": 0.36458335164934397,
      "rewards/len_reward_func": 0.5,
      "step": 261
    },
    {
      "completion_length": 40.468751430511475,
      "epoch": 3.7246891651865006,
      "grad_norm": 0.7226335420973098,
      "kl": 0.6552734375,
      "learning_rate": 1.199128013714218e-08,
      "loss": 0.0007,
      "reward": 0.8658262491226196,
      "reward_std": 0.27739427238702774,
      "rewards/correct_code_reward_func": 0.36979167675599456,
      "rewards/len_reward_func": 0.49603455513715744,
      "step": 262
    },
    {
      "completion_length": 40.21354269981384,
      "epoch": 3.738898756660746,
      "grad_norm": 0.2636563214023569,
      "kl": 0.779052734375,
      "learning_rate": 1.0766688009695546e-08,
      "loss": 0.0008,
      "reward": 0.9107385128736496,
      "reward_std": 0.2840042728930712,
      "rewards/correct_code_reward_func": 0.4114583469927311,
      "rewards/len_reward_func": 0.4992801509797573,
      "step": 263
    },
    {
      "completion_length": 39.14583468437195,
      "epoch": 3.753108348134991,
      "grad_norm": 1.3852023559333326,
      "kl": 1.404296875,
      "learning_rate": 9.607359798384784e-09,
      "loss": 0.0014,
      "reward": 0.8802083656191826,
      "reward_std": 0.2298758141696453,
      "rewards/correct_code_reward_func": 0.3802083507180214,
      "rewards/len_reward_func": 0.5,
      "step": 264
    },
    {
      "completion_length": 51.89583396911621,
      "epoch": 3.767317939609236,
      "grad_norm": 0.7354734246895569,
      "kl": 2.147705078125,
      "learning_rate": 8.513450158049106e-09,
      "loss": 0.0021,
      "reward": 0.8189271837472916,
      "reward_std": 0.23382446821779013,
      "rewards/correct_code_reward_func": 0.328125006519258,
      "rewards/len_reward_func": 0.49080217257142067,
      "step": 265
    },
    {
      "completion_length": 42.30208396911621,
      "epoch": 3.7815275310834813,
      "grad_norm": 1.0336784411098245,
      "kl": 0.518310546875,
      "learning_rate": 7.48510501666455e-09,
      "loss": 0.0005,
      "reward": 0.8310648053884506,
      "reward_std": 0.21503725834190845,
      "rewards/correct_code_reward_func": 0.34895834513008595,
      "rewards/len_reward_func": 0.48210645094513893,
      "step": 266
    },
    {
      "completion_length": 40.651041984558105,
      "epoch": 3.7957371225577266,
      "grad_norm": 0.21942916262842363,
      "kl": 1.46337890625,
      "learning_rate": 6.522461555877212e-09,
      "loss": 0.0015,
      "reward": 0.9635416939854622,
      "reward_std": 0.20901849307119846,
      "rewards/correct_code_reward_func": 0.4739583469927311,
      "rewards/len_reward_func": 0.4895833358168602,
      "step": 267
    },
    {
      "completion_length": 45.51041793823242,
      "epoch": 3.8099467140319714,
      "grad_norm": 1.3696117193786157,
      "kl": 5.1806640625,
      "learning_rate": 5.6256481927031145e-09,
      "loss": 0.0052,
      "reward": 0.7851962372660637,
      "reward_std": 0.20054008439183235,
      "rewards/correct_code_reward_func": 0.2916666753590107,
      "rewards/len_reward_func": 0.4935295581817627,
      "step": 268
    },
    {
      "completion_length": 49.65625190734863,
      "epoch": 3.8241563055062167,
      "grad_norm": 0.2580048251632083,
      "kl": 0.594482421875,
      "learning_rate": 4.794784562397458e-09,
      "loss": 0.0006,
      "reward": 0.6697429306805134,
      "reward_std": 0.11862718407064676,
      "rewards/correct_code_reward_func": 0.18750000232830644,
      "rewards/len_reward_func": 0.4822429232299328,
      "step": 269
    },
    {
      "completion_length": 42.09895968437195,
      "epoch": 3.838365896980462,
      "grad_norm": 0.10431433868999475,
      "kl": 0.319580078125,
      "learning_rate": 4.029981502495117e-09,
      "loss": 0.0003,
      "reward": 0.875000037252903,
      "reward_std": 0.260045831091702,
      "rewards/correct_code_reward_func": 0.3802083432674408,
      "rewards/len_reward_func": 0.4947916679084301,
      "step": 270
    },
    {
      "completion_length": 48.96354341506958,
      "epoch": 3.8525754884547068,
      "grad_norm": 1.2059599028177783,
      "kl": 4.60296630859375,
      "learning_rate": 3.331341038025015e-09,
      "loss": 0.0046,
      "reward": 0.9531250447034836,
      "reward_std": 0.2836446315050125,
      "rewards/correct_code_reward_func": 0.4583333469927311,
      "rewards/len_reward_func": 0.4947916679084301,
      "step": 271
    },
    {
      "completion_length": 48.15104293823242,
      "epoch": 3.866785079928952,
      "grad_norm": 0.3767229746929915,
      "kl": 2.6429443359375,
      "learning_rate": 2.698956367899685e-09,
      "loss": 0.0027,
      "reward": 0.8484268859028816,
      "reward_std": 0.12056915764696896,
      "rewards/correct_code_reward_func": 0.359375006519258,
      "rewards/len_reward_func": 0.48905187100172043,
      "step": 272
    },
    {
      "completion_length": 53.84375190734863,
      "epoch": 3.8809946714031973,
      "grad_norm": 0.6582745117981772,
      "kl": 1.384521484375,
      "learning_rate": 2.132911852482766e-09,
      "loss": 0.0014,
      "reward": 0.7473396807909012,
      "reward_std": 0.15864008571952581,
      "rewards/correct_code_reward_func": 0.26562500512227416,
      "rewards/len_reward_func": 0.48171466588974,
      "step": 273
    },
    {
      "completion_length": 50.89062571525574,
      "epoch": 3.895204262877442,
      "grad_norm": 0.9047094986684052,
      "kl": 0.7672119140625,
      "learning_rate": 1.6332830023350065e-09,
      "loss": 0.0008,
      "reward": 0.8645833507180214,
      "reward_std": 0.24531116150319576,
      "rewards/correct_code_reward_func": 0.3697916748933494,
      "rewards/len_reward_func": 0.4947916679084301,
      "step": 274
    },
    {
      "completion_length": 37.96354341506958,
      "epoch": 3.9094138543516874,
      "grad_norm": 0.15097179399717223,
      "kl": 1.36083984375,
      "learning_rate": 1.2001364681415437e-09,
      "loss": 0.0014,
      "reward": 0.9035415947437286,
      "reward_std": 0.17085538990795612,
      "rewards/correct_code_reward_func": 0.41145834885537624,
      "rewards/len_reward_func": 0.49208322539925575,
      "step": 275
    },
    {
      "completion_length": 42.27083444595337,
      "epoch": 3.9236234458259327,
      "grad_norm": 0.8720972867035206,
      "kl": 0.8348388671875,
      "learning_rate": 8.335300318201843e-10,
      "loss": 0.0008,
      "reward": 0.9018715992569923,
      "reward_std": 0.2843793909996748,
      "rewards/correct_code_reward_func": 0.4114583460614085,
      "rewards/len_reward_func": 0.49041321873664856,
      "step": 276
    },
    {
      "completion_length": 50.3281272649765,
      "epoch": 3.9378330373001775,
      "grad_norm": 0.3282895627508182,
      "kl": 1.2498779296875,
      "learning_rate": 5.335125988137901e-10,
      "loss": 0.0013,
      "reward": 0.8521379828453064,
      "reward_std": 0.22308472823351622,
      "rewards/correct_code_reward_func": 0.3541666786186397,
      "rewards/len_reward_func": 0.4979712888598442,
      "step": 277
    },
    {
      "completion_length": 61.86979365348816,
      "epoch": 3.952042628774423,
      "grad_norm": 0.5255301323359298,
      "kl": 0.330810546875,
      "learning_rate": 3.0012419156572044e-10,
      "loss": 0.0003,
      "reward": 0.7462186440825462,
      "reward_std": 0.2975779678672552,
      "rewards/correct_code_reward_func": 0.2656250111758709,
      "rewards/len_reward_func": 0.48059362545609474,
      "step": 278
    },
    {
      "completion_length": 42.97916841506958,
      "epoch": 3.966252220248668,
      "grad_norm": 0.2430830179161846,
      "kl": 1.0477294921875,
      "learning_rate": 1.3339594418138035e-10,
      "loss": 0.0011,
      "reward": 0.817708358168602,
      "reward_std": 0.17044265381991863,
      "rewards/correct_code_reward_func": 0.32291667629033327,
      "rewards/len_reward_func": 0.4947916679084301,
      "step": 279
    },
    {
      "completion_length": 44.713542461395264,
      "epoch": 3.980461811722913,
      "grad_norm": 0.2208833900914939,
      "kl": 0.505126953125,
      "learning_rate": 3.335009827437618e-11,
      "loss": 0.0005,
      "reward": 0.7343750223517418,
      "reward_std": 0.21322566084563732,
      "rewards/correct_code_reward_func": 0.23437501024454832,
      "rewards/len_reward_func": 0.5,
      "step": 280
    },
    {
      "completion_length": 39.609376668930054,
      "epoch": 3.994671403197158,
      "grad_norm": 0.23818487709061198,
      "kl": 0.8494873046875,
      "learning_rate": 0.0,
      "loss": 0.0009,
      "reward": 0.8797741681337357,
      "reward_std": 0.3059078399091959,
      "rewards/correct_code_reward_func": 0.3906250111758709,
      "rewards/len_reward_func": 0.48914914950728416,
      "step": 281
    },
    {
      "epoch": 3.994671403197158,
      "step": 281,
      "total_flos": 0.0,
      "train_loss": 0.5116655665984335,
      "train_runtime": 18793.8029,
      "train_samples_per_second": 0.359,
      "train_steps_per_second": 0.015
    }
  ],
  "logging_steps": 1,
  "max_steps": 281,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 5,
  "save_steps": 500,
  "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
}