{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.9997097242380262,
  "eval_steps": 500,
  "global_step": 861,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "completion_length": 724.58984375,
      "epoch": 0.0011611030478955006,
      "grad_norm": 0.7112110585443041,
      "kl": 0.0009012222290039062,
      "learning_rate": 3.846153846153846e-08,
      "loss": 0.0,
      "reward": 0.046875,
      "reward_std": 0.06733439117670059,
      "rewards/correctness_reward_func": 0.0390625,
      "rewards/strict_format_reward_func": 0.0078125,
      "step": 1
    },
    {
      "completion_length": 708.56640625,
      "epoch": 0.0023222060957910013,
      "grad_norm": 0.12068406687948798,
      "kl": 0.000453948974609375,
      "learning_rate": 7.692307692307692e-08,
      "loss": 0.0,
      "reward": 0.033203125,
      "reward_std": 0.06640625,
      "rewards/correctness_reward_func": 0.03125,
      "rewards/strict_format_reward_func": 0.001953125,
      "step": 2
    },
    {
      "completion_length": 742.65625,
      "epoch": 0.0034833091436865023,
      "grad_norm": 0.7976659386050398,
      "kl": 0.0007343292236328125,
      "learning_rate": 1.1538461538461539e-07,
      "loss": 0.0,
      "reward": 0.0234375,
      "reward_std": 0.046875,
      "rewards/correctness_reward_func": 0.015625,
      "rewards/strict_format_reward_func": 0.0078125,
      "step": 3
    },
    {
      "completion_length": 808.21875,
      "epoch": 0.0046444121915820025,
      "grad_norm": 0.40112277888275455,
      "kl": 0.00063323974609375,
      "learning_rate": 1.5384615384615385e-07,
      "loss": 0.0,
      "reward": 0.060546875,
      "reward_std": 0.1078859455883503,
      "rewards/correctness_reward_func": 0.0546875,
      "rewards/strict_format_reward_func": 0.005859375,
      "step": 4
    },
    {
      "completion_length": 654.234375,
      "epoch": 0.005805515239477504,
      "grad_norm": 0.39725912723012635,
      "kl": 0.0004980564117431641,
      "learning_rate": 1.9230769230769231e-07,
      "loss": 0.0,
      "reward": 0.044921875,
      "reward_std": 0.08984375,
      "rewards/correctness_reward_func": 0.03125,
      "rewards/strict_format_reward_func": 0.013671875,
      "step": 5
    },
    {
      "completion_length": 772.68359375,
      "epoch": 0.006966618287373005,
      "grad_norm": 0.14294736924830026,
      "kl": 0.0004153251647949219,
      "learning_rate": 2.3076923076923078e-07,
      "loss": 0.0,
      "reward": 0.046875,
      "reward_std": 0.0805421955883503,
      "rewards/correctness_reward_func": 0.0390625,
      "rewards/strict_format_reward_func": 0.0078125,
      "step": 6
    },
    {
      "completion_length": 745.203125,
      "epoch": 0.008127721335268505,
      "grad_norm": 0.16815060965909404,
      "kl": 0.0009188652038574219,
      "learning_rate": 2.692307692307692e-07,
      "loss": 0.0,
      "reward": 0.021484375,
      "reward_std": 0.029760945588350296,
      "rewards/correctness_reward_func": 0.015625,
      "rewards/strict_format_reward_func": 0.005859375,
      "step": 7
    },
    {
      "completion_length": 744.265625,
      "epoch": 0.009288824383164005,
      "grad_norm": 12.779442066715234,
      "kl": 0.00357818603515625,
      "learning_rate": 3.076923076923077e-07,
      "loss": 0.0001,
      "reward": 0.03125,
      "reward_std": 0.049292195588350296,
      "rewards/correctness_reward_func": 0.03125,
      "rewards/strict_format_reward_func": 0.0,
      "step": 8
    },
    {
      "completion_length": 704.51953125,
      "epoch": 0.010449927431059507,
      "grad_norm": 0.2475578183097461,
      "kl": 0.0035419464111328125,
      "learning_rate": 3.461538461538461e-07,
      "loss": 0.0001,
      "reward": 0.060546875,
      "reward_std": 0.1078859455883503,
      "rewards/correctness_reward_func": 0.0546875,
      "rewards/strict_format_reward_func": 0.005859375,
      "step": 9
    },
    {
      "completion_length": 759.2890625,
      "epoch": 0.011611030478955007,
      "grad_norm": 0.3357083329970443,
      "kl": 0.00310516357421875,
      "learning_rate": 3.8461538461538463e-07,
      "loss": 0.0001,
      "reward": 0.00390625,
      "reward_std": 0.0078125,
      "rewards/correctness_reward_func": 0.0,
      "rewards/strict_format_reward_func": 0.00390625,
      "step": 10
    },
    {
      "completion_length": 746.0703125,
      "epoch": 0.012772133526850507,
      "grad_norm": 0.2657165785401948,
      "kl": 0.00334930419921875,
      "learning_rate": 4.2307692307692304e-07,
      "loss": 0.0001,
      "reward": 0.017578125,
      "reward_std": 0.03515625,
      "rewards/correctness_reward_func": 0.015625,
      "rewards/strict_format_reward_func": 0.001953125,
      "step": 11
    },
    {
      "completion_length": 702.21875,
      "epoch": 0.01393323657474601,
      "grad_norm": 1.2656634353615759,
      "kl": 0.0019159317016601562,
      "learning_rate": 4.6153846153846156e-07,
      "loss": 0.0001,
      "reward": 0.033203125,
      "reward_std": 0.06640625,
      "rewards/correctness_reward_func": 0.03125,
      "rewards/strict_format_reward_func": 0.001953125,
      "step": 12
    },
    {
      "completion_length": 735.78515625,
      "epoch": 0.01509433962264151,
      "grad_norm": 0.5357650576255997,
      "kl": 0.005596160888671875,
      "learning_rate": 5e-07,
      "loss": 0.0002,
      "reward": 0.06640625,
      "reward_std": 0.1280700732022524,
      "rewards/correctness_reward_func": 0.0546875,
      "rewards/strict_format_reward_func": 0.01171875,
      "step": 13
    },
    {
      "completion_length": 802.51953125,
      "epoch": 0.01625544267053701,
      "grad_norm": 1.9685839556774372,
      "kl": 0.00266265869140625,
      "learning_rate": 5.384615384615384e-07,
      "loss": 0.0001,
      "reward": 0.03125,
      "reward_std": 0.059198048897087574,
      "rewards/correctness_reward_func": 0.015625,
      "rewards/strict_format_reward_func": 0.015625,
      "step": 14
    },
    {
      "completion_length": 702.47265625,
      "epoch": 0.01741654571843251,
      "grad_norm": 0.3022926592468717,
      "kl": 0.00206756591796875,
      "learning_rate": 5.769230769230768e-07,
      "loss": 0.0001,
      "reward": 0.03125,
      "reward_std": 0.049292195588350296,
      "rewards/correctness_reward_func": 0.0234375,
      "rewards/strict_format_reward_func": 0.0078125,
      "step": 15
    },
    {
      "completion_length": 714.55859375,
      "epoch": 0.01857764876632801,
      "grad_norm": 0.67295700611606,
      "kl": 0.006526947021484375,
      "learning_rate": 6.153846153846154e-07,
      "loss": 0.0003,
      "reward": 0.0546875,
      "reward_std": 0.04213257320225239,
      "rewards/correctness_reward_func": 0.046875,
      "rewards/strict_format_reward_func": 0.0078125,
      "step": 16
    },
    {
      "completion_length": 728.94921875,
      "epoch": 0.019738751814223514,
      "grad_norm": 0.12683035812623522,
      "kl": 0.003253936767578125,
      "learning_rate": 6.538461538461538e-07,
      "loss": 0.0001,
      "reward": 0.041015625,
      "reward_std": 0.0688234455883503,
      "rewards/correctness_reward_func": 0.03125,
      "rewards/strict_format_reward_func": 0.009765625,
      "step": 17
    },
    {
      "completion_length": 752.4609375,
      "epoch": 0.020899854862119014,
      "grad_norm": 0.7572918382078203,
      "kl": 0.002063751220703125,
      "learning_rate": 6.923076923076922e-07,
      "loss": 0.0001,
      "reward": 0.01953125,
      "reward_std": 0.0390625,
      "rewards/correctness_reward_func": 0.015625,
      "rewards/strict_format_reward_func": 0.00390625,
      "step": 18
    },
    {
      "completion_length": 686.39453125,
      "epoch": 0.022060957910014514,
      "grad_norm": 0.366311042586646,
      "kl": 0.00254058837890625,
      "learning_rate": 7.307692307692307e-07,
      "loss": 0.0001,
      "reward": 0.037109375,
      "reward_std": 0.07421875,
      "rewards/correctness_reward_func": 0.03125,
      "rewards/strict_format_reward_func": 0.005859375,
      "step": 19
    },
    {
      "completion_length": 814.58203125,
      "epoch": 0.023222060957910014,
      "grad_norm": 0.39037265038987773,
      "kl": 0.0024509429931640625,
      "learning_rate": 7.692307692307693e-07,
      "loss": 0.0001,
      "reward": 0.056640625,
      "reward_std": 0.1000734455883503,
      "rewards/correctness_reward_func": 0.046875,
      "rewards/strict_format_reward_func": 0.009765625,
      "step": 20
    },
    {
      "completion_length": 790.58203125,
      "epoch": 0.024383164005805515,
      "grad_norm": 0.16449028843577287,
      "kl": 0.0017910003662109375,
      "learning_rate": 8.076923076923077e-07,
      "loss": 0.0001,
      "reward": 0.021484375,
      "reward_std": 0.04296875,
      "rewards/correctness_reward_func": 0.015625,
      "rewards/strict_format_reward_func": 0.005859375,
      "step": 21
    },
    {
      "completion_length": 720.109375,
      "epoch": 0.025544267053701015,
      "grad_norm": 0.16050190810020273,
      "kl": 0.000865936279296875,
      "learning_rate": 8.461538461538461e-07,
      "loss": 0.0,
      "reward": 0.041015625,
      "reward_std": 0.08203125,
      "rewards/correctness_reward_func": 0.03125,
      "rewards/strict_format_reward_func": 0.009765625,
      "step": 22
    },
    {
      "completion_length": 772.921875,
      "epoch": 0.026705370101596515,
      "grad_norm": 1.022693227541973,
      "kl": 0.010603904724121094,
      "learning_rate": 8.846153846153846e-07,
      "loss": 0.0004,
      "reward": 0.0234375,
      "reward_std": 0.046875,
      "rewards/correctness_reward_func": 0.015625,
      "rewards/strict_format_reward_func": 0.0078125,
      "step": 23
    },
    {
      "completion_length": 785.9296875,
      "epoch": 0.02786647314949202,
      "grad_norm": 0.4975098781878154,
      "kl": 0.0006268024444580078,
      "learning_rate": 9.230769230769231e-07,
      "loss": 0.0,
      "reward": 0.0546875,
      "reward_std": 0.10463257133960724,
      "rewards/correctness_reward_func": 0.046875,
      "rewards/strict_format_reward_func": 0.0078125,
      "step": 24
    },
    {
      "completion_length": 808.91796875,
      "epoch": 0.02902757619738752,
      "grad_norm": 0.07636536312105723,
      "kl": 0.0006952285766601562,
      "learning_rate": 9.615384615384615e-07,
      "loss": 0.0,
      "reward": 0.03515625,
      "reward_std": 0.055702777579426765,
      "rewards/correctness_reward_func": 0.0234375,
      "rewards/strict_format_reward_func": 0.01171875,
      "step": 25
    },
    {
      "completion_length": 677.65234375,
      "epoch": 0.03018867924528302,
      "grad_norm": 105.92855708885655,
      "kl": 0.048847198486328125,
      "learning_rate": 1e-06,
      "loss": 0.002,
      "reward": 0.033203125,
      "reward_std": 0.06640625,
      "rewards/correctness_reward_func": 0.015625,
      "rewards/strict_format_reward_func": 0.017578125,
      "step": 26
    },
    {
      "completion_length": 657.85546875,
      "epoch": 0.03134978229317852,
      "grad_norm": 0.0861458003290139,
      "kl": 0.004261970520019531,
      "learning_rate": 9.999964611162971e-07,
      "loss": 0.0002,
      "reward": 0.009765625,
      "reward_std": 0.01953125,
      "rewards/correctness_reward_func": 0.0078125,
      "rewards/strict_format_reward_func": 0.001953125,
      "step": 27
    },
    {
      "completion_length": 726.2421875,
      "epoch": 0.03251088534107402,
      "grad_norm": 0.14527394620380304,
      "kl": 0.00072479248046875,
      "learning_rate": 9.999858445152839e-07,
      "loss": 0.0,
      "reward": 0.033203125,
      "reward_std": 0.053198445588350296,
      "rewards/correctness_reward_func": 0.03125,
      "rewards/strict_format_reward_func": 0.001953125,
      "step": 28
    },
    {
      "completion_length": 646.53125,
      "epoch": 0.03367198838896952,
      "grad_norm": 0.4038815325919152,
      "kl": 0.008038520812988281,
      "learning_rate": 9.999681503472433e-07,
      "loss": 0.0003,
      "reward": 0.02734375,
      "reward_std": 0.043573048897087574,
      "rewards/correctness_reward_func": 0.015625,
      "rewards/strict_format_reward_func": 0.01171875,
      "step": 29
    },
    {
      "completion_length": 676.234375,
      "epoch": 0.03483309143686502,
      "grad_norm": 24.530460542475996,
      "kl": 0.08559513092041016,
      "learning_rate": 9.99943378862646e-07,
      "loss": 0.0034,
      "reward": 0.076171875,
      "reward_std": 0.1358339935541153,
      "rewards/correctness_reward_func": 0.0625,
      "rewards/strict_format_reward_func": 0.013671875,
      "step": 30
    },
    {
      "completion_length": 669.62890625,
      "epoch": 0.035994194484760524,
      "grad_norm": 12.948432597412872,
      "kl": 0.0016450881958007812,
      "learning_rate": 9.999115304121457e-07,
      "loss": 0.0001,
      "reward": 0.033203125,
      "reward_std": 0.06640625,
      "rewards/correctness_reward_func": 0.0234375,
      "rewards/strict_format_reward_func": 0.009765625,
      "step": 31
    },
    {
      "completion_length": 632.80078125,
      "epoch": 0.03715529753265602,
      "grad_norm": 0.14738843577567481,
      "kl": 0.0011644363403320312,
      "learning_rate": 9.998726054465744e-07,
      "loss": 0.0,
      "reward": 0.0546875,
      "reward_std": 0.106073047965765,
      "rewards/correctness_reward_func": 0.0390625,
      "rewards/strict_format_reward_func": 0.015625,
      "step": 32
    },
    {
      "completion_length": 686.90234375,
      "epoch": 0.038316400580551524,
      "grad_norm": 6.995419155886516,
      "kl": 0.056095123291015625,
      "learning_rate": 9.998266045169354e-07,
      "loss": 0.0022,
      "reward": 0.052734375,
      "reward_std": 0.0922609455883503,
      "rewards/correctness_reward_func": 0.0390625,
      "rewards/strict_format_reward_func": 0.013671875,
      "step": 33
    },
    {
      "completion_length": 655.90234375,
      "epoch": 0.03947750362844703,
      "grad_norm": 3.5735767009613224,
      "kl": 0.013265609741210938,
      "learning_rate": 9.997735282743968e-07,
      "loss": 0.0005,
      "reward": 0.076171875,
      "reward_std": 0.13439351692795753,
      "rewards/correctness_reward_func": 0.0625,
      "rewards/strict_format_reward_func": 0.013671875,
      "step": 34
    },
    {
      "completion_length": 639.82421875,
      "epoch": 0.040638606676342524,
      "grad_norm": 1.8475352137430245,
      "kl": 0.0025959014892578125,
      "learning_rate": 9.997133774702812e-07,
      "loss": 0.0001,
      "reward": 0.05078125,
      "reward_std": 0.09682007133960724,
      "rewards/correctness_reward_func": 0.03125,
      "rewards/strict_format_reward_func": 0.01953125,
      "step": 35
    },
    {
      "completion_length": 715.3125,
      "epoch": 0.04179970972423803,
      "grad_norm": 13.632018237363075,
      "kl": 0.21777725219726562,
      "learning_rate": 9.996461529560552e-07,
      "loss": 0.0087,
      "reward": 0.0390625,
      "reward_std": 0.078125,
      "rewards/correctness_reward_func": 0.0234375,
      "rewards/strict_format_reward_func": 0.015625,
      "step": 36
    },
    {
      "completion_length": 631.8203125,
      "epoch": 0.042960812772133525,
      "grad_norm": 10.015816840984483,
      "kl": 0.00942230224609375,
      "learning_rate": 9.995718556833178e-07,
      "loss": 0.0004,
      "reward": 0.072265625,
      "reward_std": 0.141229297965765,
      "rewards/correctness_reward_func": 0.046875,
      "rewards/strict_format_reward_func": 0.025390625,
      "step": 37
    },
    {
      "completion_length": 636.9140625,
      "epoch": 0.04412191582002903,
      "grad_norm": 0.18443450708075712,
      "kl": 0.001720428466796875,
      "learning_rate": 9.994904867037865e-07,
      "loss": 0.0001,
      "reward": 0.033203125,
      "reward_std": 0.046594543382525444,
      "rewards/correctness_reward_func": 0.015625,
      "rewards/strict_format_reward_func": 0.017578125,
      "step": 38
    },
    {
      "completion_length": 667.6484375,
      "epoch": 0.045283018867924525,
      "grad_norm": 0.7286107675191874,
      "kl": 0.027004241943359375,
      "learning_rate": 9.994020471692832e-07,
      "loss": 0.0011,
      "reward": 0.0625,
      "reward_std": 0.10044586285948753,
      "rewards/correctness_reward_func": 0.0390625,
      "rewards/strict_format_reward_func": 0.0234375,
      "step": 39
    },
    {
      "completion_length": 695.68359375,
      "epoch": 0.04644412191582003,
      "grad_norm": 0.7697487269128109,
      "kl": 0.002681732177734375,
      "learning_rate": 9.993065383317162e-07,
      "loss": 0.0001,
      "reward": 0.078125,
      "reward_std": 0.12407248839735985,
      "rewards/correctness_reward_func": 0.0546875,
      "rewards/strict_format_reward_func": 0.0234375,
      "step": 40
    },
    {
      "completion_length": 678.390625,
      "epoch": 0.04760522496371553,
      "grad_norm": 0.33385332935798095,
      "kl": 0.0028896331787109375,
      "learning_rate": 9.992039615430648e-07,
      "loss": 0.0001,
      "reward": 0.06640625,
      "reward_std": 0.1137621309608221,
      "rewards/correctness_reward_func": 0.046875,
      "rewards/strict_format_reward_func": 0.01953125,
      "step": 41
    },
    {
      "completion_length": 660.2421875,
      "epoch": 0.04876632801161103,
      "grad_norm": 5.2234598338711615,
      "kl": 0.03473663330078125,
      "learning_rate": 9.990943182553578e-07,
      "loss": 0.0014,
      "reward": 0.05859375,
      "reward_std": 0.11058359593153,
      "rewards/correctness_reward_func": 0.0234375,
      "rewards/strict_format_reward_func": 0.03515625,
      "step": 42
    },
    {
      "completion_length": 599.66015625,
      "epoch": 0.04992743105950653,
      "grad_norm": 0.3125631745813204,
      "kl": 0.0029144287109375,
      "learning_rate": 9.989776100206547e-07,
      "loss": 0.0001,
      "reward": 0.087890625,
      "reward_std": 0.1592714935541153,
      "rewards/correctness_reward_func": 0.0546875,
      "rewards/strict_format_reward_func": 0.033203125,
      "step": 43
    },
    {
      "completion_length": 695.41015625,
      "epoch": 0.05108853410740203,
      "grad_norm": 0.31129440427202076,
      "kl": 0.002468109130859375,
      "learning_rate": 9.98853838491023e-07,
      "loss": 0.0001,
      "reward": 0.046875,
      "reward_std": 0.08240367192775011,
      "rewards/correctness_reward_func": 0.0234375,
      "rewards/strict_format_reward_func": 0.0234375,
      "step": 44
    },
    {
      "completion_length": 594.67578125,
      "epoch": 0.05224963715529753,
      "grad_norm": 0.2962376329942141,
      "kl": 0.00382232666015625,
      "learning_rate": 9.98723005418515e-07,
      "loss": 0.0002,
      "reward": 0.091796875,
      "reward_std": 0.1253724191337824,
      "rewards/correctness_reward_func": 0.046875,
      "rewards/strict_format_reward_func": 0.044921875,
      "step": 45
    },
    {
      "completion_length": 672.73046875,
      "epoch": 0.05341074020319303,
      "grad_norm": 3.778170631942383,
      "kl": 0.077880859375,
      "learning_rate": 9.985851126551428e-07,
      "loss": 0.0031,
      "reward": 0.103515625,
      "reward_std": 0.1781556848436594,
      "rewards/correctness_reward_func": 0.0625,
      "rewards/strict_format_reward_func": 0.041015625,
      "step": 46
    },
    {
      "completion_length": 603.15625,
      "epoch": 0.054571843251088534,
      "grad_norm": 0.3069672598383264,
      "kl": 0.006290435791015625,
      "learning_rate": 9.98440162152852e-07,
      "loss": 0.0003,
      "reward": 0.08984375,
      "reward_std": 0.1551719233393669,
      "rewards/correctness_reward_func": 0.046875,
      "rewards/strict_format_reward_func": 0.04296875,
      "step": 47
    },
    {
      "completion_length": 632.2890625,
      "epoch": 0.05573294629898404,
      "grad_norm": 1.2667105724676624,
      "kl": 0.029102325439453125,
      "learning_rate": 9.982881559634946e-07,
      "loss": 0.0012,
      "reward": 0.08203125,
      "reward_std": 0.14755274169147015,
      "rewards/correctness_reward_func": 0.03125,
      "rewards/strict_format_reward_func": 0.05078125,
      "step": 48
    },
    {
      "completion_length": 571.69921875,
      "epoch": 0.056894049346879534,
      "grad_norm": 51.00112062221978,
      "kl": 0.9501419067382812,
      "learning_rate": 9.981290962387997e-07,
      "loss": 0.0379,
      "reward": 0.07421875,
      "reward_std": 0.12532384134829044,
      "rewards/correctness_reward_func": 0.015625,
      "rewards/strict_format_reward_func": 0.05859375,
      "step": 49
    },
    {
      "completion_length": 595.40234375,
      "epoch": 0.05805515239477504,
      "grad_norm": 1.04581231978298,
      "kl": 0.01190185546875,
      "learning_rate": 9.979629852303425e-07,
      "loss": 0.0005,
      "reward": 0.11328125,
      "reward_std": 0.18154333159327507,
      "rewards/correctness_reward_func": 0.03125,
      "rewards/strict_format_reward_func": 0.08203125,
      "step": 50
    },
    {
      "completion_length": 561.47265625,
      "epoch": 0.059216255442670535,
      "grad_norm": 0.7109293653864751,
      "kl": 0.0103302001953125,
      "learning_rate": 9.977898252895134e-07,
      "loss": 0.0004,
      "reward": 0.13671875,
      "reward_std": 0.2260015867650509,
      "rewards/correctness_reward_func": 0.0390625,
      "rewards/strict_format_reward_func": 0.09765625,
      "step": 51
    },
    {
      "completion_length": 589.95703125,
      "epoch": 0.06037735849056604,
      "grad_norm": 2.9062465124154735,
      "kl": 0.00753021240234375,
      "learning_rate": 9.976096188674836e-07,
      "loss": 0.0003,
      "reward": 0.12890625,
      "reward_std": 0.19242635369300842,
      "rewards/correctness_reward_func": 0.0234375,
      "rewards/strict_format_reward_func": 0.10546875,
      "step": 52
    },
    {
      "completion_length": 537.0234375,
      "epoch": 0.06153846153846154,
      "grad_norm": 22.409980149466673,
      "kl": 0.2718505859375,
      "learning_rate": 9.974223685151718e-07,
      "loss": 0.0109,
      "reward": 0.12890625,
      "reward_std": 0.1836371347308159,
      "rewards/correctness_reward_func": 0.0234375,
      "rewards/strict_format_reward_func": 0.10546875,
      "step": 53
    },
    {
      "completion_length": 531.80859375,
      "epoch": 0.06269956458635705,
      "grad_norm": 2.8826743442454297,
      "kl": 0.122955322265625,
      "learning_rate": 9.972280768832067e-07,
      "loss": 0.0049,
      "reward": 0.220703125,
      "reward_std": 0.3008614853024483,
      "rewards/correctness_reward_func": 0.09375,
      "rewards/strict_format_reward_func": 0.126953125,
      "step": 54
    },
    {
      "completion_length": 611.5,
      "epoch": 0.06386066763425254,
      "grad_norm": 2.352779269743852,
      "kl": 0.02130889892578125,
      "learning_rate": 9.970267467218902e-07,
      "loss": 0.0009,
      "reward": 0.232421875,
      "reward_std": 0.2863368093967438,
      "rewards/correctness_reward_func": 0.0546875,
      "rewards/strict_format_reward_func": 0.177734375,
      "step": 55
    },
    {
      "completion_length": 555.91796875,
      "epoch": 0.06502177068214804,
      "grad_norm": 0.9680034082980018,
      "kl": 0.01513671875,
      "learning_rate": 9.968183808811585e-07,
      "loss": 0.0006,
      "reward": 0.24609375,
      "reward_std": 0.3278784677386284,
      "rewards/correctness_reward_func": 0.0703125,
      "rewards/strict_format_reward_func": 0.17578125,
      "step": 56
    },
    {
      "completion_length": 561.3203125,
      "epoch": 0.06618287373004354,
      "grad_norm": 5.155662797346911,
      "kl": 0.1178741455078125,
      "learning_rate": 9.966029823105415e-07,
      "loss": 0.0047,
      "reward": 0.291015625,
      "reward_std": 0.3391275480389595,
      "rewards/correctness_reward_func": 0.09375,
      "rewards/strict_format_reward_func": 0.197265625,
      "step": 57
    },
    {
      "completion_length": 574.9453125,
      "epoch": 0.06734397677793905,
      "grad_norm": 3.5240176122453306,
      "kl": 0.0246734619140625,
      "learning_rate": 9.96380554059121e-07,
      "loss": 0.001,
      "reward": 0.291015625,
      "reward_std": 0.31832827627658844,
      "rewards/correctness_reward_func": 0.078125,
      "rewards/strict_format_reward_func": 0.212890625,
      "step": 58
    },
    {
      "completion_length": 583.93359375,
      "epoch": 0.06850507982583454,
      "grad_norm": 3.558262716521494,
      "kl": 0.0449981689453125,
      "learning_rate": 9.961510992754882e-07,
      "loss": 0.0018,
      "reward": 0.28515625,
      "reward_std": 0.26169369369745255,
      "rewards/correctness_reward_func": 0.0703125,
      "rewards/strict_format_reward_func": 0.21484375,
      "step": 59
    },
    {
      "completion_length": 498.65625,
      "epoch": 0.06966618287373004,
      "grad_norm": 2.811935806633887,
      "kl": 0.0194091796875,
      "learning_rate": 9.959146212076978e-07,
      "loss": 0.0008,
      "reward": 0.33984375,
      "reward_std": 0.314444862306118,
      "rewards/correctness_reward_func": 0.0625,
      "rewards/strict_format_reward_func": 0.27734375,
      "step": 60
    },
    {
      "completion_length": 478.53125,
      "epoch": 0.07082728592162554,
      "grad_norm": 4.984861468141312,
      "kl": 0.107757568359375,
      "learning_rate": 9.95671123203224e-07,
      "loss": 0.0043,
      "reward": 0.361328125,
      "reward_std": 0.33764002099633217,
      "rewards/correctness_reward_func": 0.09375,
      "rewards/strict_format_reward_func": 0.267578125,
      "step": 61
    },
    {
      "completion_length": 512.39453125,
      "epoch": 0.07198838896952105,
      "grad_norm": 1.007778929339388,
      "kl": 0.01971435546875,
      "learning_rate": 9.954206087089105e-07,
      "loss": 0.0008,
      "reward": 0.3203125,
      "reward_std": 0.2790137939155102,
      "rewards/correctness_reward_func": 0.046875,
      "rewards/strict_format_reward_func": 0.2734375,
      "step": 62
    },
    {
      "completion_length": 516.03515625,
      "epoch": 0.07314949201741655,
      "grad_norm": 0.5960945531101304,
      "kl": 0.0254974365234375,
      "learning_rate": 9.951630812709244e-07,
      "loss": 0.001,
      "reward": 0.373046875,
      "reward_std": 0.3191210627555847,
      "rewards/correctness_reward_func": 0.09375,
      "rewards/strict_format_reward_func": 0.279296875,
      "step": 63
    },
    {
      "completion_length": 478.65625,
      "epoch": 0.07431059506531204,
      "grad_norm": 3.3120058314917094,
      "kl": 0.027435302734375,
      "learning_rate": 9.948985445347044e-07,
      "loss": 0.0011,
      "reward": 0.396484375,
      "reward_std": 0.30096181109547615,
      "rewards/correctness_reward_func": 0.0703125,
      "rewards/strict_format_reward_func": 0.326171875,
      "step": 64
    },
    {
      "completion_length": 453.5390625,
      "epoch": 0.07547169811320754,
      "grad_norm": 10.565800054920043,
      "kl": 0.06463623046875,
      "learning_rate": 9.946270022449093e-07,
      "loss": 0.0026,
      "reward": 0.40234375,
      "reward_std": 0.30288316309452057,
      "rewards/correctness_reward_func": 0.0703125,
      "rewards/strict_format_reward_func": 0.33203125,
      "step": 65
    },
    {
      "completion_length": 467.4609375,
      "epoch": 0.07663280116110305,
      "grad_norm": 8.848702328863897,
      "kl": 0.026763916015625,
      "learning_rate": 9.94348458245365e-07,
      "loss": 0.0011,
      "reward": 0.484375,
      "reward_std": 0.3539407253265381,
      "rewards/correctness_reward_func": 0.1640625,
      "rewards/strict_format_reward_func": 0.3203125,
      "step": 66
    },
    {
      "completion_length": 460.51171875,
      "epoch": 0.07779390420899855,
      "grad_norm": 0.8276997968349737,
      "kl": 0.028564453125,
      "learning_rate": 9.940629164790118e-07,
      "loss": 0.0011,
      "reward": 0.390625,
      "reward_std": 0.2685689851641655,
      "rewards/correctness_reward_func": 0.0546875,
      "rewards/strict_format_reward_func": 0.3359375,
      "step": 67
    },
    {
      "completion_length": 432.30078125,
      "epoch": 0.07895500725689406,
      "grad_norm": 1.6501741381150759,
      "kl": 0.068115234375,
      "learning_rate": 9.937703809878454e-07,
      "loss": 0.0027,
      "reward": 0.447265625,
      "reward_std": 0.32472314685583115,
      "rewards/correctness_reward_func": 0.109375,
      "rewards/strict_format_reward_func": 0.337890625,
      "step": 68
    },
    {
      "completion_length": 433.5625,
      "epoch": 0.08011611030478955,
      "grad_norm": 5.548040313902584,
      "kl": 0.0538330078125,
      "learning_rate": 9.934708559128622e-07,
      "loss": 0.0022,
      "reward": 0.48046875,
      "reward_std": 0.3404357209801674,
      "rewards/correctness_reward_func": 0.1171875,
      "rewards/strict_format_reward_func": 0.36328125,
      "step": 69
    },
    {
      "completion_length": 411.9921875,
      "epoch": 0.08127721335268505,
      "grad_norm": 4.54760002369526,
      "kl": 0.0399169921875,
      "learning_rate": 9.931643454939998e-07,
      "loss": 0.0016,
      "reward": 0.505859375,
      "reward_std": 0.3411124534904957,
      "rewards/correctness_reward_func": 0.1484375,
      "rewards/strict_format_reward_func": 0.357421875,
      "step": 70
    },
    {
      "completion_length": 374.98828125,
      "epoch": 0.08243831640058055,
      "grad_norm": 0.7476462962662087,
      "kl": 0.06536865234375,
      "learning_rate": 9.928508540700772e-07,
      "loss": 0.0026,
      "reward": 0.458984375,
      "reward_std": 0.2434551902115345,
      "rewards/correctness_reward_func": 0.09375,
      "rewards/strict_format_reward_func": 0.365234375,
      "step": 71
    },
    {
      "completion_length": 371.80859375,
      "epoch": 0.08359941944847606,
      "grad_norm": 0.31697483250235303,
      "kl": 0.04022216796875,
      "learning_rate": 9.925303860787333e-07,
      "loss": 0.0016,
      "reward": 0.427734375,
      "reward_std": 0.24097520112991333,
      "rewards/correctness_reward_func": 0.0546875,
      "rewards/strict_format_reward_func": 0.373046875,
      "step": 72
    },
    {
      "completion_length": 408.953125,
      "epoch": 0.08476052249637156,
      "grad_norm": 2.342541131973969,
      "kl": 0.0394287109375,
      "learning_rate": 9.92202946056364e-07,
      "loss": 0.0016,
      "reward": 0.447265625,
      "reward_std": 0.2658774182200432,
      "rewards/correctness_reward_func": 0.0625,
      "rewards/strict_format_reward_func": 0.384765625,
      "step": 73
    },
    {
      "completion_length": 367.03125,
      "epoch": 0.08592162554426705,
      "grad_norm": 0.457004333832563,
      "kl": 0.05194091796875,
      "learning_rate": 9.918685386380572e-07,
      "loss": 0.0021,
      "reward": 0.478515625,
      "reward_std": 0.22598736733198166,
      "rewards/correctness_reward_func": 0.078125,
      "rewards/strict_format_reward_func": 0.400390625,
      "step": 74
    },
    {
      "completion_length": 423.35546875,
      "epoch": 0.08708272859216255,
      "grad_norm": 81.83417853597544,
      "kl": 0.247314453125,
      "learning_rate": 9.915271685575296e-07,
      "loss": 0.0099,
      "reward": 0.48828125,
      "reward_std": 0.3054451234638691,
      "rewards/correctness_reward_func": 0.1015625,
      "rewards/strict_format_reward_func": 0.38671875,
      "step": 75
    },
    {
      "completion_length": 312.484375,
      "epoch": 0.08824383164005806,
      "grad_norm": 1.780578379981416,
      "kl": 0.0880126953125,
      "learning_rate": 9.911788406470568e-07,
      "loss": 0.0035,
      "reward": 0.548828125,
      "reward_std": 0.32934778556227684,
      "rewards/correctness_reward_func": 0.125,
      "rewards/strict_format_reward_func": 0.423828125,
      "step": 76
    },
    {
      "completion_length": 338.2421875,
      "epoch": 0.08940493468795356,
      "grad_norm": 0.6544200585420813,
      "kl": 0.0731201171875,
      "learning_rate": 9.908235598374068e-07,
      "loss": 0.0029,
      "reward": 0.45703125,
      "reward_std": 0.1958453767001629,
      "rewards/correctness_reward_func": 0.0390625,
      "rewards/strict_format_reward_func": 0.41796875,
      "step": 77
    },
    {
      "completion_length": 268.171875,
      "epoch": 0.09056603773584905,
      "grad_norm": 0.5879416696261314,
      "kl": 0.108642578125,
      "learning_rate": 9.904613311577695e-07,
      "loss": 0.0044,
      "reward": 0.556640625,
      "reward_std": 0.22046153992414474,
      "rewards/correctness_reward_func": 0.140625,
      "rewards/strict_format_reward_func": 0.416015625,
      "step": 78
    },
    {
      "completion_length": 231.109375,
      "epoch": 0.09172714078374455,
      "grad_norm": 0.8976017470783989,
      "kl": 0.18408203125,
      "learning_rate": 9.900921597356855e-07,
      "loss": 0.0074,
      "reward": 0.515625,
      "reward_std": 0.20618988201022148,
      "rewards/correctness_reward_func": 0.0859375,
      "rewards/strict_format_reward_func": 0.4296875,
      "step": 79
    },
    {
      "completion_length": 196.59765625,
      "epoch": 0.09288824383164006,
      "grad_norm": 17.77907159035059,
      "kl": 0.263916015625,
      "learning_rate": 9.897160507969735e-07,
      "loss": 0.0106,
      "reward": 0.47265625,
      "reward_std": 0.19209052622318268,
      "rewards/correctness_reward_func": 0.0546875,
      "rewards/strict_format_reward_func": 0.41796875,
      "step": 80
    },
    {
      "completion_length": 110.4609375,
      "epoch": 0.09404934687953556,
      "grad_norm": 1.3276411102732406,
      "kl": 0.3662109375,
      "learning_rate": 9.893330096656573e-07,
      "loss": 0.0147,
      "reward": 0.578125,
      "reward_std": 0.27833693847060204,
      "rewards/correctness_reward_func": 0.140625,
      "rewards/strict_format_reward_func": 0.4375,
      "step": 81
    },
    {
      "completion_length": 77.88671875,
      "epoch": 0.09521044992743107,
      "grad_norm": 1.9379785150930775,
      "kl": 0.51953125,
      "learning_rate": 9.889430417638883e-07,
      "loss": 0.0208,
      "reward": 0.51171875,
      "reward_std": 0.1544804871082306,
      "rewards/correctness_reward_func": 0.0546875,
      "rewards/strict_format_reward_func": 0.45703125,
      "step": 82
    },
    {
      "completion_length": 73.9375,
      "epoch": 0.09637155297532655,
      "grad_norm": 0.8473473359273695,
      "kl": 0.48486328125,
      "learning_rate": 9.885461526118713e-07,
      "loss": 0.0194,
      "reward": 0.50390625,
      "reward_std": 0.14182795584201813,
      "rewards/correctness_reward_func": 0.046875,
      "rewards/strict_format_reward_func": 0.45703125,
      "step": 83
    },
    {
      "completion_length": 56.2109375,
      "epoch": 0.09753265602322206,
      "grad_norm": 2.281085454498393,
      "kl": 0.49072265625,
      "learning_rate": 9.88142347827784e-07,
      "loss": 0.0196,
      "reward": 0.4765625,
      "reward_std": 0.12851098738610744,
      "rewards/correctness_reward_func": 0.0234375,
      "rewards/strict_format_reward_func": 0.453125,
      "step": 84
    },
    {
      "completion_length": 37.875,
      "epoch": 0.09869375907111756,
      "grad_norm": 0.5788019582854786,
      "kl": 0.5927734375,
      "learning_rate": 9.877316331276993e-07,
      "loss": 0.0237,
      "reward": 0.470703125,
      "reward_std": 0.055291797965765,
      "rewards/correctness_reward_func": 0.0,
      "rewards/strict_format_reward_func": 0.470703125,
      "step": 85
    },
    {
      "completion_length": 33.50390625,
      "epoch": 0.09985486211901307,
      "grad_norm": 6.104259815482374,
      "kl": 0.5439453125,
      "learning_rate": 9.873140143255034e-07,
      "loss": 0.0217,
      "reward": 0.517578125,
      "reward_std": 0.07212539482861757,
      "rewards/correctness_reward_func": 0.046875,
      "rewards/strict_format_reward_func": 0.470703125,
      "step": 86
    },
    {
      "completion_length": 20.76171875,
      "epoch": 0.10101596516690857,
      "grad_norm": 0.507931311814518,
      "kl": 0.5947265625,
      "learning_rate": 9.86889497332814e-07,
      "loss": 0.0238,
      "reward": 0.486328125,
      "reward_std": 0.02734375,
      "rewards/correctness_reward_func": 0.0,
      "rewards/strict_format_reward_func": 0.486328125,
      "step": 87
    },
    {
      "completion_length": 16.58203125,
      "epoch": 0.10217706821480406,
      "grad_norm": 0.45325431756004353,
      "kl": 0.6630859375,
      "learning_rate": 9.864580881588958e-07,
      "loss": 0.0265,
      "reward": 0.501953125,
      "reward_std": 0.024041798897087574,
      "rewards/correctness_reward_func": 0.0078125,
      "rewards/strict_format_reward_func": 0.494140625,
      "step": 88
    },
    {
      "completion_length": 16.12109375,
      "epoch": 0.10333817126269956,
      "grad_norm": 0.38014072113379394,
      "kl": 0.6513671875,
      "learning_rate": 9.860197929105767e-07,
      "loss": 0.0261,
      "reward": 0.49609375,
      "reward_std": 0.0078125,
      "rewards/correctness_reward_func": 0.0,
      "rewards/strict_format_reward_func": 0.49609375,
      "step": 89
    },
    {
      "completion_length": 19.7265625,
      "epoch": 0.10449927431059507,
      "grad_norm": 3.246980620297076,
      "kl": 0.6064453125,
      "learning_rate": 9.8557461779216e-07,
      "loss": 0.0243,
      "reward": 0.48828125,
      "reward_std": 0.0234375,
      "rewards/correctness_reward_func": 0.0,
      "rewards/strict_format_reward_func": 0.48828125,
      "step": 90
    },
    {
      "completion_length": 15.8359375,
      "epoch": 0.10566037735849057,
      "grad_norm": 1.125767741710113,
      "kl": 0.6162109375,
      "learning_rate": 9.85122569105338e-07,
      "loss": 0.0247,
      "reward": 0.49609375,
      "reward_std": 0.0078125,
      "rewards/correctness_reward_func": 0.0,
      "rewards/strict_format_reward_func": 0.49609375,
      "step": 91
    },
    {
      "completion_length": 22.44921875,
      "epoch": 0.10682148040638606,
      "grad_norm": 0.44874987843781083,
      "kl": 0.6083984375,
      "learning_rate": 9.846636532491012e-07,
      "loss": 0.0243,
      "reward": 0.48828125,
      "reward_std": 0.0234375,
      "rewards/correctness_reward_func": 0.0,
      "rewards/strict_format_reward_func": 0.48828125,
      "step": 92
    },
    {
      "completion_length": 16.21484375,
      "epoch": 0.10798258345428156,
      "grad_norm": 2.7244778647827363,
      "kl": 0.796875,
      "learning_rate": 9.841978767196493e-07,
      "loss": 0.0319,
      "reward": 0.494140625,
      "reward_std": 0.01171875,
      "rewards/correctness_reward_func": 0.0,
      "rewards/strict_format_reward_func": 0.494140625,
      "step": 93
    },
    {
      "completion_length": 18.08984375,
      "epoch": 0.10914368650217707,
      "grad_norm": 0.900717061581606,
      "kl": 0.5712890625,
      "learning_rate": 9.83725246110298e-07,
      "loss": 0.0229,
      "reward": 0.49609375,
      "reward_std": 0.0234375,
      "rewards/correctness_reward_func": 0.0078125,
      "rewards/strict_format_reward_func": 0.48828125,
      "step": 94
    },
    {
      "completion_length": 19.921875,
      "epoch": 0.11030478955007257,
      "grad_norm": 0.2922094758318377,
      "kl": 0.62109375,
      "learning_rate": 9.832457681113865e-07,
      "loss": 0.0249,
      "reward": 0.51953125,
      "reward_std": 0.0546875,
      "rewards/correctness_reward_func": 0.03125,
      "rewards/strict_format_reward_func": 0.48828125,
      "step": 95
    },
    {
      "completion_length": 22.48828125,
      "epoch": 0.11146589259796807,
      "grad_norm": 1.5719055280514225,
      "kl": 0.5966796875,
      "learning_rate": 9.827594495101822e-07,
      "loss": 0.0239,
      "reward": 0.53125,
      "reward_std": 0.049292195588350296,
      "rewards/correctness_reward_func": 0.0390625,
      "rewards/strict_format_reward_func": 0.4921875,
      "step": 96
    },
    {
      "completion_length": 21.078125,
      "epoch": 0.11262699564586356,
      "grad_norm": 1.875138112811585,
      "kl": 0.62890625,
      "learning_rate": 9.822662971907852e-07,
      "loss": 0.0252,
      "reward": 0.505859375,
      "reward_std": 0.047479298897087574,
      "rewards/correctness_reward_func": 0.015625,
      "rewards/strict_format_reward_func": 0.490234375,
      "step": 97
    },
    {
      "completion_length": 20.328125,
      "epoch": 0.11378809869375907,
      "grad_norm": 0.46440948422543626,
      "kl": 0.5703125,
      "learning_rate": 9.8176631813403e-07,
      "loss": 0.0228,
      "reward": 0.5078125,
      "reward_std": 0.015625,
      "rewards/correctness_reward_func": 0.0078125,
      "rewards/strict_format_reward_func": 0.5,
      "step": 98
    },
    {
      "completion_length": 17.6953125,
      "epoch": 0.11494920174165457,
      "grad_norm": 2.350666772323524,
      "kl": 0.6298828125,
      "learning_rate": 9.812595194173874e-07,
      "loss": 0.0252,
      "reward": 0.50390625,
      "reward_std": 0.0234375,
      "rewards/correctness_reward_func": 0.0078125,
      "rewards/strict_format_reward_func": 0.49609375,
      "step": 99
    },
    {
      "completion_length": 30.88671875,
      "epoch": 0.11611030478955008,
      "grad_norm": 0.6769899791454503,
      "kl": 0.537109375,
      "learning_rate": 9.807459082148648e-07,
      "loss": 0.0215,
      "reward": 0.56640625,
      "reward_std": 0.0804273895919323,
      "rewards/correctness_reward_func": 0.078125,
      "rewards/strict_format_reward_func": 0.48828125,
      "step": 100
    },
    {
      "completion_length": 38.8203125,
      "epoch": 0.11727140783744558,
      "grad_norm": 9.613286964921125,
      "kl": 0.53515625,
      "learning_rate": 9.802254917969032e-07,
      "loss": 0.0214,
      "reward": 0.5390625,
      "reward_std": 0.1328125,
      "rewards/correctness_reward_func": 0.0546875,
      "rewards/strict_format_reward_func": 0.484375,
      "step": 101
    },
    {
      "completion_length": 21.05078125,
      "epoch": 0.11843251088534107,
      "grad_norm": 0.383590636095333,
      "kl": 0.5419921875,
      "learning_rate": 9.796982775302754e-07,
      "loss": 0.0217,
      "reward": 0.52734375,
      "reward_std": 0.057104695588350296,
      "rewards/correctness_reward_func": 0.03125,
      "rewards/strict_format_reward_func": 0.49609375,
      "step": 102
    },
    {
      "completion_length": 26.5234375,
      "epoch": 0.11959361393323657,
      "grad_norm": 0.45036244814830856,
      "kl": 0.53759765625,
      "learning_rate": 9.79164272877981e-07,
      "loss": 0.0215,
      "reward": 0.53125,
      "reward_std": 0.090448047965765,
      "rewards/correctness_reward_func": 0.046875,
      "rewards/strict_format_reward_func": 0.484375,
      "step": 103
    },
    {
      "completion_length": 23.54296875,
      "epoch": 0.12075471698113208,
      "grad_norm": 2.2388808963947713,
      "kl": 0.5615234375,
      "learning_rate": 9.786234853991418e-07,
      "loss": 0.0224,
      "reward": 0.56640625,
      "reward_std": 0.08606802299618721,
      "rewards/correctness_reward_func": 0.078125,
      "rewards/strict_format_reward_func": 0.48828125,
      "step": 104
    },
    {
      "completion_length": 53.6875,
      "epoch": 0.12191582002902758,
      "grad_norm": 1.3962986009964624,
      "kl": 0.515625,
      "learning_rate": 9.780759227488937e-07,
      "loss": 0.0207,
      "reward": 0.55859375,
      "reward_std": 0.1321367770433426,
      "rewards/correctness_reward_func": 0.078125,
      "rewards/strict_format_reward_func": 0.48046875,
      "step": 105
    },
    {
      "completion_length": 45.9140625,
      "epoch": 0.12307692307692308,
      "grad_norm": 0.6991087377799369,
      "kl": 0.5751953125,
      "learning_rate": 9.775215926782787e-07,
      "loss": 0.023,
      "reward": 0.5390625,
      "reward_std": 0.12271332554519176,
      "rewards/correctness_reward_func": 0.0546875,
      "rewards/strict_format_reward_func": 0.484375,
      "step": 106
    },
    {
      "completion_length": 41.71484375,
      "epoch": 0.12423802612481857,
      "grad_norm": 1.113559415990131,
      "kl": 0.501953125,
      "learning_rate": 9.769605030341355e-07,
      "loss": 0.0201,
      "reward": 0.494140625,
      "reward_std": 0.039666798897087574,
      "rewards/correctness_reward_func": 0.0078125,
      "rewards/strict_format_reward_func": 0.486328125,
      "step": 107
    },
    {
      "completion_length": 30.234375,
      "epoch": 0.1253991291727141,
      "grad_norm": 9.444282741370284,
      "kl": 0.52587890625,
      "learning_rate": 9.763926617589884e-07,
      "loss": 0.021,
      "reward": 0.529296875,
      "reward_std": 0.09918868914246559,
      "rewards/correctness_reward_func": 0.046875,
      "rewards/strict_format_reward_func": 0.482421875,
      "step": 108
    },
    {
      "completion_length": 36.328125,
      "epoch": 0.12656023222060958,
      "grad_norm": 0.5876435788826965,
      "kl": 0.49365234375,
      "learning_rate": 9.758180768909336e-07,
      "loss": 0.0198,
      "reward": 0.5625,
      "reward_std": 0.1117921955883503,
      "rewards/correctness_reward_func": 0.0703125,
      "rewards/strict_format_reward_func": 0.4921875,
      "step": 109
    },
    {
      "completion_length": 45.109375,
      "epoch": 0.12772133526850507,
      "grad_norm": 0.6967401340285807,
      "kl": 0.58203125,
      "learning_rate": 9.75236756563528e-07,
      "loss": 0.0233,
      "reward": 0.564453125,
      "reward_std": 0.1313234455883503,
      "rewards/correctness_reward_func": 0.0859375,
      "rewards/strict_format_reward_func": 0.478515625,
      "step": 110
    },
    {
      "completion_length": 22.265625,
      "epoch": 0.1288824383164006,
      "grad_norm": 4.157806679866693,
      "kl": 0.5859375,
      "learning_rate": 9.746487090056712e-07,
      "loss": 0.0235,
      "reward": 0.57421875,
      "reward_std": 0.1376468911767006,
      "rewards/correctness_reward_func": 0.0859375,
      "rewards/strict_format_reward_func": 0.48828125,
      "step": 111
    },
    {
      "completion_length": 43.33203125,
      "epoch": 0.13004354136429608,
      "grad_norm": 1.3608549571109825,
      "kl": 0.52099609375,
      "learning_rate": 9.740539425414911e-07,
      "loss": 0.0208,
      "reward": 0.548828125,
      "reward_std": 0.1078859455883503,
      "rewards/correctness_reward_func": 0.0546875,
      "rewards/strict_format_reward_func": 0.494140625,
      "step": 112
    },
    {
      "completion_length": 27.4609375,
      "epoch": 0.1312046444121916,
      "grad_norm": 0.9303195344407332,
      "kl": 0.5302734375,
      "learning_rate": 9.734524655902252e-07,
      "loss": 0.0212,
      "reward": 0.5,
      "reward_std": 0.03125,
      "rewards/correctness_reward_func": 0.0078125,
      "rewards/strict_format_reward_func": 0.4921875,
      "step": 113
    },
    {
      "completion_length": 44.421875,
      "epoch": 0.13236574746008709,
      "grad_norm": 2.5989058419028512,
      "kl": 0.5224609375,
      "learning_rate": 9.728442866661012e-07,
      "loss": 0.0209,
      "reward": 0.5390625,
      "reward_std": 0.09286524448543787,
      "rewards/correctness_reward_func": 0.0546875,
      "rewards/strict_format_reward_func": 0.484375,
      "step": 114
    },
    {
      "completion_length": 55.43359375,
      "epoch": 0.13352685050798258,
      "grad_norm": 4.35900633763163,
      "kl": 0.513671875,
      "learning_rate": 9.722294143782171e-07,
      "loss": 0.0205,
      "reward": 0.5234375,
      "reward_std": 0.09476527757942677,
      "rewards/correctness_reward_func": 0.0390625,
      "rewards/strict_format_reward_func": 0.484375,
      "step": 115
    },
    {
      "completion_length": 32.14453125,
      "epoch": 0.1346879535558781,
      "grad_norm": 2.5576115813189664,
      "kl": 0.48486328125,
      "learning_rate": 9.71607857430419e-07,
      "loss": 0.0194,
      "reward": 0.548828125,
      "reward_std": 0.1358339935541153,
      "rewards/correctness_reward_func": 0.0625,
      "rewards/strict_format_reward_func": 0.486328125,
      "step": 116
    },
    {
      "completion_length": 40.48828125,
      "epoch": 0.13584905660377358,
      "grad_norm": 5.3055382808430025,
      "kl": 0.55078125,
      "learning_rate": 9.709796246211776e-07,
      "loss": 0.022,
      "reward": 0.599609375,
      "reward_std": 0.1770055592060089,
      "rewards/correctness_reward_func": 0.1171875,
      "rewards/strict_format_reward_func": 0.482421875,
      "step": 117
    },
    {
      "completion_length": 48.4296875,
      "epoch": 0.13701015965166907,
      "grad_norm": 1.9357783363747145,
      "kl": 0.52734375,
      "learning_rate": 9.70344724843465e-07,
      "loss": 0.0211,
      "reward": 0.623046875,
      "reward_std": 0.0844484455883503,
      "rewards/correctness_reward_func": 0.1328125,
      "rewards/strict_format_reward_func": 0.490234375,
      "step": 118
    },
    {
      "completion_length": 33.06640625,
      "epoch": 0.1381712626995646,
      "grad_norm": 0.9093609363691819,
      "kl": 0.48876953125,
      "learning_rate": 9.697031670846264e-07,
      "loss": 0.0195,
      "reward": 0.595703125,
      "reward_std": 0.1571781411767006,
      "rewards/correctness_reward_func": 0.109375,
      "rewards/strict_format_reward_func": 0.486328125,
      "step": 119
    },
    {
      "completion_length": 26.15234375,
      "epoch": 0.13933236574746008,
      "grad_norm": 1.2956378319464605,
      "kl": 0.52490234375,
      "learning_rate": 9.690549604262554e-07,
      "loss": 0.021,
      "reward": 0.611328125,
      "reward_std": 0.1670839935541153,
      "rewards/correctness_reward_func": 0.1171875,
      "rewards/strict_format_reward_func": 0.494140625,
      "step": 120
    },
    {
      "completion_length": 23.31640625,
      "epoch": 0.1404934687953556,
      "grad_norm": 1.0404878413954166,
      "kl": 0.53173828125,
      "learning_rate": 9.684001140440638e-07,
      "loss": 0.0213,
      "reward": 0.533203125,
      "reward_std": 0.08553362637758255,
      "rewards/correctness_reward_func": 0.046875,
      "rewards/strict_format_reward_func": 0.486328125,
      "step": 121
    },
    {
      "completion_length": 33.63671875,
      "epoch": 0.1416545718432511,
      "grad_norm": 0.5491271196977439,
      "kl": 0.5263671875,
      "learning_rate": 9.677386372077523e-07,
      "loss": 0.0211,
      "reward": 0.537109375,
      "reward_std": 0.0798230916261673,
      "rewards/correctness_reward_func": 0.046875,
      "rewards/strict_format_reward_func": 0.490234375,
      "step": 122
    },
    {
      "completion_length": 27.7578125,
      "epoch": 0.14281567489114658,
      "grad_norm": 1.4086546997823266,
      "kl": 0.49462890625,
      "learning_rate": 9.670705392808795e-07,
      "loss": 0.0198,
      "reward": 0.642578125,
      "reward_std": 0.14176217839121819,
      "rewards/correctness_reward_func": 0.15625,
      "rewards/strict_format_reward_func": 0.486328125,
      "step": 123
    },
    {
      "completion_length": 46.31640625,
      "epoch": 0.1439767779390421,
      "grad_norm": 0.44935314029572543,
      "kl": 0.4541015625,
      "learning_rate": 9.663958297207285e-07,
      "loss": 0.0181,
      "reward": 0.5390625,
      "reward_std": 0.12601527571678162,
      "rewards/correctness_reward_func": 0.0546875,
      "rewards/strict_format_reward_func": 0.484375,
      "step": 124
    },
    {
      "completion_length": 42.33203125,
      "epoch": 0.14513788098693758,
      "grad_norm": 4.134753027574554,
      "kl": 0.45703125,
      "learning_rate": 9.657145180781742e-07,
      "loss": 0.0183,
      "reward": 0.513671875,
      "reward_std": 0.06089614052325487,
      "rewards/correctness_reward_func": 0.0234375,
      "rewards/strict_format_reward_func": 0.490234375,
      "step": 125
    },
    {
      "completion_length": 42.03515625,
      "epoch": 0.1462989840348331,
      "grad_norm": 0.4544547991850145,
      "kl": 0.40625,
      "learning_rate": 9.650266139975473e-07,
      "loss": 0.0163,
      "reward": 0.5703125,
      "reward_std": 0.12411524076014757,
      "rewards/correctness_reward_func": 0.0859375,
      "rewards/strict_format_reward_func": 0.484375,
      "step": 126
    },
    {
      "completion_length": 31.16796875,
      "epoch": 0.1474600870827286,
      "grad_norm": 1.6260031691388108,
      "kl": 0.486328125,
      "learning_rate": 9.64332127216498e-07,
      "loss": 0.0194,
      "reward": 0.51171875,
      "reward_std": 0.0390625,
      "rewards/correctness_reward_func": 0.0234375,
      "rewards/strict_format_reward_func": 0.48828125,
      "step": 127
    },
    {
      "completion_length": 32.0,
      "epoch": 0.14862119013062408,
      "grad_norm": 0.5382173674869626,
      "kl": 0.4267578125,
      "learning_rate": 9.63631067565858e-07,
      "loss": 0.0171,
      "reward": 0.529296875,
      "reward_std": 0.053198445588350296,
      "rewards/correctness_reward_func": 0.046875,
      "rewards/strict_format_reward_func": 0.482421875,
      "step": 128
    },
    {
      "completion_length": 44.75390625,
      "epoch": 0.1497822931785196,
      "grad_norm": 0.7683808964372313,
      "kl": 0.4228515625,
      "learning_rate": 9.629234449695015e-07,
      "loss": 0.0169,
      "reward": 0.5625,
      "reward_std": 0.1478765867650509,
      "rewards/correctness_reward_func": 0.078125,
      "rewards/strict_format_reward_func": 0.484375,
      "step": 129
    },
    {
      "completion_length": 40.52734375,
      "epoch": 0.1509433962264151,
      "grad_norm": 1.0117014376716735,
      "kl": 0.45263671875,
      "learning_rate": 9.62209269444205e-07,
      "loss": 0.0181,
      "reward": 0.65625,
      "reward_std": 0.218528650701046,
      "rewards/correctness_reward_func": 0.171875,
      "rewards/strict_format_reward_func": 0.484375,
      "step": 130
    },
    {
      "completion_length": 28.6484375,
      "epoch": 0.1521044992743106,
      "grad_norm": 0.42513248914448737,
      "kl": 0.35986328125,
      "learning_rate": 9.614885510995047e-07,
      "loss": 0.0144,
      "reward": 0.5390625,
      "reward_std": 0.10979307442903519,
      "rewards/correctness_reward_func": 0.0546875,
      "rewards/strict_format_reward_func": 0.484375,
      "step": 131
    },
    {
      "completion_length": 48.9765625,
      "epoch": 0.1532656023222061,
      "grad_norm": 0.3690713785403208,
      "kl": 0.443359375,
      "learning_rate": 9.607613001375545e-07,
      "loss": 0.0177,
      "reward": 0.6015625,
      "reward_std": 0.1454593911767006,
      "rewards/correctness_reward_func": 0.1171875,
      "rewards/strict_format_reward_func": 0.484375,
      "step": 132
    },
    {
      "completion_length": 40.62890625,
      "epoch": 0.15442670537010159,
      "grad_norm": 0.3570306428369935,
      "kl": 0.40283203125,
      "learning_rate": 9.600275268529806e-07,
      "loss": 0.0161,
      "reward": 0.595703125,
      "reward_std": 0.0766359455883503,
      "rewards/correctness_reward_func": 0.1015625,
      "rewards/strict_format_reward_func": 0.494140625,
      "step": 133
    },
    {
      "completion_length": 48.47265625,
      "epoch": 0.1555878084179971,
      "grad_norm": 0.6699794243427841,
      "kl": 0.40283203125,
      "learning_rate": 9.592872416327364e-07,
      "loss": 0.0161,
      "reward": 0.537109375,
      "reward_std": 0.1280214972794056,
      "rewards/correctness_reward_func": 0.0546875,
      "rewards/strict_format_reward_func": 0.482421875,
      "step": 134
    },
    {
      "completion_length": 43.74609375,
      "epoch": 0.1567489114658926,
      "grad_norm": 0.8744900024283108,
      "kl": 0.42919921875,
      "learning_rate": 9.58540454955955e-07,
      "loss": 0.0172,
      "reward": 0.568359375,
      "reward_std": 0.12251138500869274,
      "rewards/correctness_reward_func": 0.09375,
      "rewards/strict_format_reward_func": 0.474609375,
      "step": 135
    },
    {
      "completion_length": 35.98828125,
      "epoch": 0.1579100145137881,
      "grad_norm": 10.83989251533941,
      "kl": 0.43994140625,
      "learning_rate": 9.57787177393801e-07,
      "loss": 0.0176,
      "reward": 0.59765625,
      "reward_std": 0.1689911223948002,
      "rewards/correctness_reward_func": 0.1171875,
      "rewards/strict_format_reward_func": 0.48046875,
      "step": 136
    },
    {
      "completion_length": 47.265625,
      "epoch": 0.1590711175616836,
      "grad_norm": 1.3945795045826723,
      "kl": 0.4638671875,
      "learning_rate": 9.570274196093216e-07,
      "loss": 0.0186,
      "reward": 0.5,
      "reward_std": 0.051385548897087574,
      "rewards/correctness_reward_func": 0.015625,
      "rewards/strict_format_reward_func": 0.484375,
      "step": 137
    },
    {
      "completion_length": 37.30859375,
      "epoch": 0.1602322206095791,
      "grad_norm": 1.2085779669420207,
      "kl": 0.4755859375,
      "learning_rate": 9.562611923572943e-07,
      "loss": 0.019,
      "reward": 0.587890625,
      "reward_std": 0.16475876048207283,
      "rewards/correctness_reward_func": 0.109375,
      "rewards/strict_format_reward_func": 0.478515625,
      "step": 138
    },
    {
      "completion_length": 62.33203125,
      "epoch": 0.1613933236574746,
      "grad_norm": 0.6440211313776459,
      "kl": 0.419921875,
      "learning_rate": 9.554885064840755e-07,
      "loss": 0.0168,
      "reward": 0.51171875,
      "reward_std": 0.129510547965765,
      "rewards/correctness_reward_func": 0.0390625,
      "rewards/strict_format_reward_func": 0.47265625,
      "step": 139
    },
    {
      "completion_length": 42.2734375,
      "epoch": 0.1625544267053701,
      "grad_norm": 4.184412362449491,
      "kl": 0.458984375,
      "learning_rate": 9.547093729274473e-07,
      "loss": 0.0183,
      "reward": 0.56640625,
      "reward_std": 0.1319277435541153,
      "rewards/correctness_reward_func": 0.0859375,
      "rewards/strict_format_reward_func": 0.48046875,
      "step": 140
    },
    {
      "completion_length": 30.3203125,
      "epoch": 0.16371552975326562,
      "grad_norm": 0.9148362673963394,
      "kl": 0.4169921875,
      "learning_rate": 9.539238027164618e-07,
      "loss": 0.0167,
      "reward": 0.513671875,
      "reward_std": 0.053198445588350296,
      "rewards/correctness_reward_func": 0.0234375,
      "rewards/strict_format_reward_func": 0.490234375,
      "step": 141
    },
    {
      "completion_length": 26.02734375,
      "epoch": 0.1648766328011611,
      "grad_norm": 23.339183218639594,
      "kl": 0.4833984375,
      "learning_rate": 9.531318069712853e-07,
      "loss": 0.0193,
      "reward": 0.599609375,
      "reward_std": 0.15335902571678162,
      "rewards/correctness_reward_func": 0.1171875,
      "rewards/strict_format_reward_func": 0.482421875,
      "step": 142
    },
    {
      "completion_length": 39.70703125,
      "epoch": 0.1660377358490566,
      "grad_norm": 4.918732336995348,
      "kl": 0.546875,
      "learning_rate": 9.523333969030412e-07,
      "loss": 0.0219,
      "reward": 0.623046875,
      "reward_std": 0.18786722049117088,
      "rewards/correctness_reward_func": 0.1328125,
      "rewards/strict_format_reward_func": 0.490234375,
      "step": 143
    },
    {
      "completion_length": 24.69140625,
      "epoch": 0.1671988388969521,
      "grad_norm": 2.3195586374061645,
      "kl": 0.46875,
      "learning_rate": 9.51528583813651e-07,
      "loss": 0.0187,
      "reward": 0.58203125,
      "reward_std": 0.13684775680303574,
      "rewards/correctness_reward_func": 0.09375,
      "rewards/strict_format_reward_func": 0.48828125,
      "step": 144
    },
    {
      "completion_length": 40.7109375,
      "epoch": 0.1683599419448476,
      "grad_norm": 0.6860447379166801,
      "kl": 0.49267578125,
      "learning_rate": 9.507173790956745e-07,
      "loss": 0.0197,
      "reward": 0.583984375,
      "reward_std": 0.1592714935541153,
      "rewards/correctness_reward_func": 0.1015625,
      "rewards/strict_format_reward_func": 0.482421875,
      "step": 145
    },
    {
      "completion_length": 60.76953125,
      "epoch": 0.16952104499274312,
      "grad_norm": 1.208065145658311,
      "kl": 0.55859375,
      "learning_rate": 9.498997942321483e-07,
      "loss": 0.0223,
      "reward": 0.5390625,
      "reward_std": 0.1552504375576973,
      "rewards/correctness_reward_func": 0.0703125,
      "rewards/strict_format_reward_func": 0.46875,
      "step": 146
    },
    {
      "completion_length": 34.5859375,
      "epoch": 0.1706821480406386,
      "grad_norm": 2.412402656297087,
      "kl": 0.5146484375,
      "learning_rate": 9.490758407964233e-07,
      "loss": 0.0206,
      "reward": 0.65234375,
      "reward_std": 0.14944713562726974,
      "rewards/correctness_reward_func": 0.171875,
      "rewards/strict_format_reward_func": 0.48046875,
      "step": 147
    },
    {
      "completion_length": 33.71875,
      "epoch": 0.1718432510885341,
      "grad_norm": 1.3484678762791356,
      "kl": 0.5146484375,
      "learning_rate": 9.482455304520012e-07,
      "loss": 0.0206,
      "reward": 0.50390625,
      "reward_std": 0.033667195588350296,
      "rewards/correctness_reward_func": 0.015625,
      "rewards/strict_format_reward_func": 0.48828125,
      "step": 148
    },
    {
      "completion_length": 43.68359375,
      "epoch": 0.17300435413642962,
      "grad_norm": 4.476292060280118,
      "kl": 0.5556640625,
      "learning_rate": 9.474088749523687e-07,
      "loss": 0.0222,
      "reward": 0.51953125,
      "reward_std": 0.051385547965765,
      "rewards/correctness_reward_func": 0.0390625,
      "rewards/strict_format_reward_func": 0.48046875,
      "step": 149
    },
    {
      "completion_length": 57.0078125,
      "epoch": 0.1741654571843251,
      "grad_norm": 3.243977251886513,
      "kl": 0.470703125,
      "learning_rate": 9.465658861408323e-07,
      "loss": 0.0188,
      "reward": 0.5703125,
      "reward_std": 0.1800113394856453,
      "rewards/correctness_reward_func": 0.09375,
      "rewards/strict_format_reward_func": 0.4765625,
      "step": 150
    },
    {
      "completion_length": 48.234375,
      "epoch": 0.1753265602322206,
      "grad_norm": 3.965397946904913,
      "kl": 0.51220703125,
      "learning_rate": 9.457165759503491e-07,
      "loss": 0.0204,
      "reward": 0.576171875,
      "reward_std": 0.14397033769637346,
      "rewards/correctness_reward_func": 0.09375,
      "rewards/strict_format_reward_func": 0.482421875,
      "step": 151
    },
    {
      "completion_length": 27.34765625,
      "epoch": 0.1764876632801161,
      "grad_norm": 5.956710202169321,
      "kl": 0.52734375,
      "learning_rate": 9.448609564033593e-07,
      "loss": 0.0211,
      "reward": 0.521484375,
      "reward_std": 0.13792734686285257,
      "rewards/correctness_reward_func": 0.046875,
      "rewards/strict_format_reward_func": 0.474609375,
      "step": 152
    },
    {
      "completion_length": 55.0234375,
      "epoch": 0.1776487663280116,
      "grad_norm": 1.9878758706657031,
      "kl": 0.625,
      "learning_rate": 9.439990396116148e-07,
      "loss": 0.025,
      "reward": 0.486328125,
      "reward_std": 0.1357191875576973,
      "rewards/correctness_reward_func": 0.03125,
      "rewards/strict_format_reward_func": 0.455078125,
      "step": 153
    },
    {
      "completion_length": 47.39453125,
      "epoch": 0.17880986937590712,
      "grad_norm": 0.3506677329292148,
      "kl": 0.568359375,
      "learning_rate": 9.431308377760093e-07,
      "loss": 0.0228,
      "reward": 0.587890625,
      "reward_std": 0.2043701931834221,
      "rewards/correctness_reward_func": 0.1171875,
      "rewards/strict_format_reward_func": 0.470703125,
      "step": 154
    },
    {
      "completion_length": 34.31640625,
      "epoch": 0.1799709724238026,
      "grad_norm": 3.844767491669304,
      "kl": 0.51953125,
      "learning_rate": 9.422563631864037e-07,
      "loss": 0.0208,
      "reward": 0.513671875,
      "reward_std": 0.1123964935541153,
      "rewards/correctness_reward_func": 0.0390625,
      "rewards/strict_format_reward_func": 0.474609375,
      "step": 155
    },
    {
      "completion_length": 35.26171875,
      "epoch": 0.1811320754716981,
      "grad_norm": 10.543061352265745,
      "kl": 0.66748046875,
      "learning_rate": 9.413756282214537e-07,
      "loss": 0.0267,
      "reward": 0.560546875,
      "reward_std": 0.2216724045574665,
      "rewards/correctness_reward_func": 0.09375,
      "rewards/strict_format_reward_func": 0.466796875,
      "step": 156
    },
    {
      "completion_length": 53.375,
      "epoch": 0.18229317851959362,
      "grad_norm": 0.6406847195030275,
      "kl": 0.51416015625,
      "learning_rate": 9.404886453484335e-07,
      "loss": 0.0206,
      "reward": 0.486328125,
      "reward_std": 0.12331762351095676,
      "rewards/correctness_reward_func": 0.03125,
      "rewards/strict_format_reward_func": 0.455078125,
      "step": 157
    },
    {
      "completion_length": 33.31640625,
      "epoch": 0.1834542815674891,
      "grad_norm": 1.254136142861394,
      "kl": 0.6044921875,
      "learning_rate": 9.395954271230603e-07,
      "loss": 0.0242,
      "reward": 0.55078125,
      "reward_std": 0.1352296955883503,
      "rewards/correctness_reward_func": 0.0703125,
      "rewards/strict_format_reward_func": 0.48046875,
      "step": 158
    },
    {
      "completion_length": 38.45703125,
      "epoch": 0.18461538461538463,
      "grad_norm": 1.1951784005374884,
      "kl": 0.580078125,
      "learning_rate": 9.386959861893157e-07,
      "loss": 0.0232,
      "reward": 0.5,
      "reward_std": 0.09967818111181259,
      "rewards/correctness_reward_func": 0.03125,
      "rewards/strict_format_reward_func": 0.46875,
      "step": 159
    },
    {
      "completion_length": 49.9921875,
      "epoch": 0.18577648766328012,
      "grad_norm": 1.0186965999705826,
      "kl": 0.611328125,
      "learning_rate": 9.377903352792671e-07,
      "loss": 0.0244,
      "reward": 0.599609375,
      "reward_std": 0.19500285387039185,
      "rewards/correctness_reward_func": 0.1328125,
      "rewards/strict_format_reward_func": 0.466796875,
      "step": 160
    },
    {
      "completion_length": 25.6953125,
      "epoch": 0.1869375907111756,
      "grad_norm": 0.9553165570763839,
      "kl": 0.6337890625,
      "learning_rate": 9.368784872128876e-07,
      "loss": 0.0253,
      "reward": 0.65625,
      "reward_std": 0.23248206824064255,
      "rewards/correctness_reward_func": 0.1796875,
      "rewards/strict_format_reward_func": 0.4765625,
      "step": 161
    },
    {
      "completion_length": 29.96484375,
      "epoch": 0.18809869375907112,
      "grad_norm": 1.320529298833274,
      "kl": 0.677734375,
      "learning_rate": 9.359604548978741e-07,
      "loss": 0.0271,
      "reward": 0.546875,
      "reward_std": 0.1555742807686329,
      "rewards/correctness_reward_func": 0.0703125,
      "rewards/strict_format_reward_func": 0.4765625,
      "step": 162
    },
    {
      "completion_length": 37.44921875,
      "epoch": 0.1892597968069666,
      "grad_norm": 2.2124875651885754,
      "kl": 0.6181640625,
      "learning_rate": 9.35036251329465e-07,
      "loss": 0.0247,
      "reward": 0.513671875,
      "reward_std": 0.09588673710823059,
      "rewards/correctness_reward_func": 0.0390625,
      "rewards/strict_format_reward_func": 0.474609375,
      "step": 163
    },
    {
      "completion_length": 30.9609375,
      "epoch": 0.19042089985486213,
      "grad_norm": 0.7762326728671275,
      "kl": 0.755859375,
      "learning_rate": 9.341058895902562e-07,
      "loss": 0.0303,
      "reward": 0.615234375,
      "reward_std": 0.18324187397956848,
      "rewards/correctness_reward_func": 0.1328125,
      "rewards/strict_format_reward_func": 0.482421875,
      "step": 164
    },
    {
      "completion_length": 39.90234375,
      "epoch": 0.19158200290275762,
      "grad_norm": 1.5333968229845967,
      "kl": 0.681640625,
      "learning_rate": 9.331693828500158e-07,
      "loss": 0.0273,
      "reward": 0.53125,
      "reward_std": 0.11541798710823059,
      "rewards/correctness_reward_func": 0.0546875,
      "rewards/strict_format_reward_func": 0.4765625,
      "step": 165
    },
    {
      "completion_length": 39.2265625,
      "epoch": 0.1927431059506531,
      "grad_norm": 3.341316216605523,
      "kl": 0.6484375,
      "learning_rate": 9.322267443654972e-07,
      "loss": 0.026,
      "reward": 0.552734375,
      "reward_std": 0.13462539482861757,
      "rewards/correctness_reward_func": 0.078125,
      "rewards/strict_format_reward_func": 0.474609375,
      "step": 166
    },
    {
      "completion_length": 41.33203125,
      "epoch": 0.19390420899854863,
      "grad_norm": 0.8334577080111663,
      "kl": 0.689453125,
      "learning_rate": 9.312779874802525e-07,
      "loss": 0.0276,
      "reward": 0.72265625,
      "reward_std": 0.2527032420039177,
      "rewards/correctness_reward_func": 0.2578125,
      "rewards/strict_format_reward_func": 0.46484375,
      "step": 167
    },
    {
      "completion_length": 27.4296875,
      "epoch": 0.19506531204644412,
      "grad_norm": 0.6225355591311358,
      "kl": 0.6796875,
      "learning_rate": 9.303231256244428e-07,
      "loss": 0.0272,
      "reward": 0.572265625,
      "reward_std": 0.1169070415198803,
      "rewards/correctness_reward_func": 0.09375,
      "rewards/strict_format_reward_func": 0.478515625,
      "step": 168
    },
    {
      "completion_length": 26.65625,
      "epoch": 0.19622641509433963,
      "grad_norm": 0.31164342343966356,
      "kl": 0.701171875,
      "learning_rate": 9.293621723146484e-07,
      "loss": 0.0281,
      "reward": 0.595703125,
      "reward_std": 0.1571781374514103,
      "rewards/correctness_reward_func": 0.109375,
      "rewards/strict_format_reward_func": 0.486328125,
      "step": 169
    },
    {
      "completion_length": 32.9609375,
      "epoch": 0.19738751814223512,
      "grad_norm": 0.8220338043159918,
      "kl": 0.6875,
      "learning_rate": 9.283951411536772e-07,
      "loss": 0.0274,
      "reward": 0.59375,
      "reward_std": 0.15472763776779175,
      "rewards/correctness_reward_func": 0.1171875,
      "rewards/strict_format_reward_func": 0.4765625,
      "step": 170
    },
    {
      "completion_length": 29.8984375,
      "epoch": 0.19854862119013061,
      "grad_norm": 3.2547872245531146,
      "kl": 0.7255859375,
      "learning_rate": 9.274220458303726e-07,
      "loss": 0.029,
      "reward": 0.609375,
      "reward_std": 0.2199743092060089,
      "rewards/correctness_reward_func": 0.1328125,
      "rewards/strict_format_reward_func": 0.4765625,
      "step": 171
    },
    {
      "completion_length": 22.08203125,
      "epoch": 0.19970972423802613,
      "grad_norm": 1.0413843485165826,
      "kl": 0.7294921875,
      "learning_rate": 9.264429001194192e-07,
      "loss": 0.0292,
      "reward": 0.595703125,
      "reward_std": 0.2031683847308159,
      "rewards/correctness_reward_func": 0.1171875,
      "rewards/strict_format_reward_func": 0.478515625,
      "step": 172
    },
    {
      "completion_length": 51.3671875,
      "epoch": 0.20087082728592162,
      "grad_norm": 3.778010417040405,
      "kl": 0.6826171875,
      "learning_rate": 9.254577178811482e-07,
      "loss": 0.0273,
      "reward": 0.6015625,
      "reward_std": 0.1914496347308159,
      "rewards/correctness_reward_func": 0.1328125,
      "rewards/strict_format_reward_func": 0.46875,
      "step": 173
    },
    {
      "completion_length": 44.84765625,
      "epoch": 0.20203193033381714,
      "grad_norm": 2.305304587495654,
      "kl": 0.7666015625,
      "learning_rate": 9.24466513061341e-07,
      "loss": 0.0307,
      "reward": 0.59375,
      "reward_std": 0.1900114268064499,
      "rewards/correctness_reward_func": 0.1171875,
      "rewards/strict_format_reward_func": 0.4765625,
      "step": 174
    },
    {
      "completion_length": 36.86328125,
      "epoch": 0.20319303338171263,
      "grad_norm": 0.7728198355409298,
      "kl": 0.712890625,
      "learning_rate": 9.234692996910323e-07,
      "loss": 0.0285,
      "reward": 0.62890625,
      "reward_std": 0.1866152435541153,
      "rewards/correctness_reward_func": 0.1484375,
      "rewards/strict_format_reward_func": 0.48046875,
      "step": 175
    },
    {
      "completion_length": 29.98828125,
      "epoch": 0.20435413642960812,
      "grad_norm": 1.289972465399101,
      "kl": 0.6865234375,
      "learning_rate": 9.224660918863103e-07,
      "loss": 0.0275,
      "reward": 0.595703125,
      "reward_std": 0.13913594186306,
      "rewards/correctness_reward_func": 0.109375,
      "rewards/strict_format_reward_func": 0.486328125,
      "step": 176
    },
    {
      "completion_length": 34.23046875,
      "epoch": 0.20551523947750364,
      "grad_norm": 0.5793735600612212,
      "kl": 0.759765625,
      "learning_rate": 9.214569038481181e-07,
      "loss": 0.0304,
      "reward": 0.5625,
      "reward_std": 0.1687820851802826,
      "rewards/correctness_reward_func": 0.0859375,
      "rewards/strict_format_reward_func": 0.4765625,
      "step": 177
    },
    {
      "completion_length": 31.23828125,
      "epoch": 0.20667634252539913,
      "grad_norm": 0.5984526162665614,
      "kl": 0.771484375,
      "learning_rate": 9.20441749862052e-07,
      "loss": 0.0309,
      "reward": 0.68359375,
      "reward_std": 0.1762864589691162,
      "rewards/correctness_reward_func": 0.1953125,
      "rewards/strict_format_reward_func": 0.48828125,
      "step": 178
    },
    {
      "completion_length": 38.296875,
      "epoch": 0.20783744557329464,
      "grad_norm": 1.181839300217833,
      "kl": 0.7099609375,
      "learning_rate": 9.1942064429816e-07,
      "loss": 0.0284,
      "reward": 0.548828125,
      "reward_std": 0.10820978879928589,
      "rewards/correctness_reward_func": 0.078125,
      "rewards/strict_format_reward_func": 0.470703125,
      "step": 179
    },
    {
      "completion_length": 35.44921875,
      "epoch": 0.20899854862119013,
      "grad_norm": 7.06190367002311,
      "kl": 0.7001953125,
      "learning_rate": 9.18393601610737e-07,
      "loss": 0.028,
      "reward": 0.56640625,
      "reward_std": 0.1620996668934822,
      "rewards/correctness_reward_func": 0.0859375,
      "rewards/strict_format_reward_func": 0.48046875,
      "step": 180
    },
    {
      "completion_length": 24.76953125,
      "epoch": 0.21015965166908562,
      "grad_norm": 0.4282018680025159,
      "kl": 0.7275390625,
      "learning_rate": 9.173606363381218e-07,
      "loss": 0.0291,
      "reward": 0.654296875,
      "reward_std": 0.2599649503827095,
      "rewards/correctness_reward_func": 0.1640625,
      "rewards/strict_format_reward_func": 0.490234375,
      "step": 181
    },
    {
      "completion_length": 61.73046875,
      "epoch": 0.21132075471698114,
      "grad_norm": 0.666578405400966,
      "kl": 0.705078125,
      "learning_rate": 9.1632176310249e-07,
      "loss": 0.0283,
      "reward": 0.54296875,
      "reward_std": 0.1953125,
      "rewards/correctness_reward_func": 0.078125,
      "rewards/strict_format_reward_func": 0.46484375,
      "step": 182
    },
    {
      "completion_length": 41.6875,
      "epoch": 0.21248185776487663,
      "grad_norm": 2.4086312779043495,
      "kl": 0.6748046875,
      "learning_rate": 9.152769966096481e-07,
      "loss": 0.027,
      "reward": 0.65625,
      "reward_std": 0.2158661186695099,
      "rewards/correctness_reward_func": 0.1796875,
      "rewards/strict_format_reward_func": 0.4765625,
      "step": 183
    },
    {
      "completion_length": 47.5078125,
      "epoch": 0.21364296081277212,
      "grad_norm": 0.7460531004888707,
      "kl": 0.6865234375,
      "learning_rate": 9.142263516488244e-07,
      "loss": 0.0275,
      "reward": 0.53125,
      "reward_std": 0.1276262328028679,
      "rewards/correctness_reward_func": 0.0546875,
      "rewards/strict_format_reward_func": 0.4765625,
      "step": 184
    },
    {
      "completion_length": 38.33203125,
      "epoch": 0.21480406386066764,
      "grad_norm": 1.677852493854183,
      "kl": 0.6611328125,
      "learning_rate": 9.131698430924605e-07,
      "loss": 0.0264,
      "reward": 0.6015625,
      "reward_std": 0.1689911223948002,
      "rewards/correctness_reward_func": 0.1171875,
      "rewards/strict_format_reward_func": 0.484375,
      "step": 185
    },
    {
      "completion_length": 31.5859375,
      "epoch": 0.21596516690856313,
      "grad_norm": 21.23887712764663,
      "kl": 0.689453125,
      "learning_rate": 9.121074858959996e-07,
      "loss": 0.0275,
      "reward": 0.564453125,
      "reward_std": 0.09907388500869274,
      "rewards/correctness_reward_func": 0.0859375,
      "rewards/strict_format_reward_func": 0.478515625,
      "step": 186
    },
    {
      "completion_length": 41.9453125,
      "epoch": 0.21712626995645865,
      "grad_norm": 0.6508903252265714,
      "kl": 0.6748046875,
      "learning_rate": 9.110392950976764e-07,
      "loss": 0.027,
      "reward": 0.5234375,
      "reward_std": 0.137323047965765,
      "rewards/correctness_reward_func": 0.0546875,
      "rewards/strict_format_reward_func": 0.46875,
      "step": 187
    },
    {
      "completion_length": 62.2109375,
      "epoch": 0.21828737300435413,
      "grad_norm": 1.1278006956369315,
      "kl": 0.673828125,
      "learning_rate": 9.099652858183027e-07,
      "loss": 0.027,
      "reward": 0.56640625,
      "reward_std": 0.1318129375576973,
      "rewards/correctness_reward_func": 0.1015625,
      "rewards/strict_format_reward_func": 0.46484375,
      "step": 188
    },
    {
      "completion_length": 46.51171875,
      "epoch": 0.21944847605224962,
      "grad_norm": 1.1019281044279183,
      "kl": 0.7548828125,
      "learning_rate": 9.088854732610542e-07,
      "loss": 0.0302,
      "reward": 0.572265625,
      "reward_std": 0.1169070415198803,
      "rewards/correctness_reward_func": 0.09375,
      "rewards/strict_format_reward_func": 0.478515625,
      "step": 189
    },
    {
      "completion_length": 35.03125,
      "epoch": 0.22060957910014514,
      "grad_norm": 14.962735092929739,
      "kl": 0.6845703125,
      "learning_rate": 9.077998727112552e-07,
      "loss": 0.0274,
      "reward": 0.564453125,
      "reward_std": 0.1369277872145176,
      "rewards/correctness_reward_func": 0.09375,
      "rewards/strict_format_reward_func": 0.470703125,
      "step": 190
    },
    {
      "completion_length": 55.27734375,
      "epoch": 0.22177068214804063,
      "grad_norm": 0.3504770063047999,
      "kl": 0.654296875,
      "learning_rate": 9.067084995361623e-07,
      "loss": 0.0262,
      "reward": 0.55078125,
      "reward_std": 0.1510637328028679,
      "rewards/correctness_reward_func": 0.078125,
      "rewards/strict_format_reward_func": 0.47265625,
      "step": 191
    },
    {
      "completion_length": 47.34375,
      "epoch": 0.22293178519593615,
      "grad_norm": 1.8159467800873224,
      "kl": 0.7333984375,
      "learning_rate": 9.05611369184746e-07,
      "loss": 0.0293,
      "reward": 0.57421875,
      "reward_std": 0.1376468911767006,
      "rewards/correctness_reward_func": 0.09375,
      "rewards/strict_format_reward_func": 0.48046875,
      "step": 192
    },
    {
      "completion_length": 49.0390625,
      "epoch": 0.22409288824383164,
      "grad_norm": 3.120448246962212,
      "kl": 0.69140625,
      "learning_rate": 9.045084971874737e-07,
      "loss": 0.0277,
      "reward": 0.609375,
      "reward_std": 0.1610843911767006,
      "rewards/correctness_reward_func": 0.1328125,
      "rewards/strict_format_reward_func": 0.4765625,
      "step": 193
    },
    {
      "completion_length": 33.7421875,
      "epoch": 0.22525399129172713,
      "grad_norm": 2.5542170019130244,
      "kl": 0.6787109375,
      "learning_rate": 9.03399899156088e-07,
      "loss": 0.0272,
      "reward": 0.58984375,
      "reward_std": 0.1015625,
      "rewards/correctness_reward_func": 0.1015625,
      "rewards/strict_format_reward_func": 0.48828125,
      "step": 194
    },
    {
      "completion_length": 54.81640625,
      "epoch": 0.22641509433962265,
      "grad_norm": 0.6406888848138048,
      "kl": 0.7216796875,
      "learning_rate": 9.022855907833871e-07,
      "loss": 0.0288,
      "reward": 0.5390625,
      "reward_std": 0.1084902435541153,
      "rewards/correctness_reward_func": 0.0703125,
      "rewards/strict_format_reward_func": 0.46875,
      "step": 195
    },
    {
      "completion_length": 33.41796875,
      "epoch": 0.22757619738751814,
      "grad_norm": 0.3997318900990298,
      "kl": 0.7177734375,
      "learning_rate": 9.011655878430018e-07,
      "loss": 0.0287,
      "reward": 0.587890625,
      "reward_std": 0.16475242003798485,
      "rewards/correctness_reward_func": 0.109375,
      "rewards/strict_format_reward_func": 0.478515625,
      "step": 196
    },
    {
      "completion_length": 62.3671875,
      "epoch": 0.22873730043541365,
      "grad_norm": 1.585750352753696,
      "kl": 0.71484375,
      "learning_rate": 9.000399061891728e-07,
      "loss": 0.0286,
      "reward": 0.630859375,
      "reward_std": 0.141229297965765,
      "rewards/correctness_reward_func": 0.1484375,
      "rewards/strict_format_reward_func": 0.482421875,
      "step": 197
    },
    {
      "completion_length": 38.67578125,
      "epoch": 0.22989840348330914,
      "grad_norm": 5.358536856283286,
      "kl": 0.6640625,
      "learning_rate": 8.98908561756526e-07,
      "loss": 0.0265,
      "reward": 0.517578125,
      "reward_std": 0.055291798897087574,
      "rewards/correctness_reward_func": 0.0390625,
      "rewards/strict_format_reward_func": 0.478515625,
      "step": 198
    },
    {
      "completion_length": 30.2109375,
      "epoch": 0.23105950653120463,
      "grad_norm": 0.39601285118928503,
      "kl": 0.720703125,
      "learning_rate": 8.977715705598467e-07,
      "loss": 0.0288,
      "reward": 0.54296875,
      "reward_std": 0.09165100753307343,
      "rewards/correctness_reward_func": 0.0625,
      "rewards/strict_format_reward_func": 0.48046875,
      "step": 199
    },
    {
      "completion_length": 29.21484375,
      "epoch": 0.23222060957910015,
      "grad_norm": 1.491626514094341,
      "kl": 0.73046875,
      "learning_rate": 8.966289486938536e-07,
      "loss": 0.0292,
      "reward": 0.63671875,
      "reward_std": 0.1542871668934822,
      "rewards/correctness_reward_func": 0.15625,
      "rewards/strict_format_reward_func": 0.48046875,
      "step": 200
    },
    {
      "completion_length": 46.3046875,
      "epoch": 0.23338171262699564,
      "grad_norm": 0.6565437407352915,
      "kl": 0.6962890625,
      "learning_rate": 8.954807123329703e-07,
      "loss": 0.0278,
      "reward": 0.51953125,
      "reward_std": 0.1006777435541153,
      "rewards/correctness_reward_func": 0.046875,
      "rewards/strict_format_reward_func": 0.47265625,
      "step": 201
    },
    {
      "completion_length": 30.859375,
      "epoch": 0.23454281567489116,
      "grad_norm": 0.32433472081782594,
      "kl": 0.6640625,
      "learning_rate": 8.943268777310964e-07,
      "loss": 0.0266,
      "reward": 0.515625,
      "reward_std": 0.09375,
      "rewards/correctness_reward_func": 0.03125,
      "rewards/strict_format_reward_func": 0.484375,
      "step": 202
    },
    {
      "completion_length": 38.45703125,
      "epoch": 0.23570391872278665,
      "grad_norm": 0.41559508425580927,
      "kl": 0.6484375,
      "learning_rate": 8.931674612213778e-07,
      "loss": 0.0259,
      "reward": 0.55078125,
      "reward_std": 0.082635547965765,
      "rewards/correctness_reward_func": 0.0703125,
      "rewards/strict_format_reward_func": 0.48046875,
      "step": 203
    },
    {
      "completion_length": 43.28515625,
      "epoch": 0.23686502177068214,
      "grad_norm": 0.8867725325822029,
      "kl": 0.6962890625,
      "learning_rate": 8.920024792159754e-07,
      "loss": 0.0279,
      "reward": 0.51953125,
      "reward_std": 0.11871993914246559,
      "rewards/correctness_reward_func": 0.046875,
      "rewards/strict_format_reward_func": 0.47265625,
      "step": 204
    },
    {
      "completion_length": 23.59375,
      "epoch": 0.23802612481857766,
      "grad_norm": 0.510002854031267,
      "kl": 0.748046875,
      "learning_rate": 8.908319482058324e-07,
      "loss": 0.0299,
      "reward": 0.578125,
      "reward_std": 0.10628208518028259,
      "rewards/correctness_reward_func": 0.09375,
      "rewards/strict_format_reward_func": 0.484375,
      "step": 205
    },
    {
      "completion_length": 32.55078125,
      "epoch": 0.23918722786647315,
      "grad_norm": 0.35776972668521406,
      "kl": 0.775390625,
      "learning_rate": 8.896558847604413e-07,
      "loss": 0.031,
      "reward": 0.6875,
      "reward_std": 0.2245633751153946,
      "rewards/correctness_reward_func": 0.1953125,
      "rewards/strict_format_reward_func": 0.4921875,
      "step": 206
    },
    {
      "completion_length": 29.95703125,
      "epoch": 0.24034833091436866,
      "grad_norm": 1.1414350140139438,
      "kl": 0.755859375,
      "learning_rate": 8.884743055276091e-07,
      "loss": 0.0302,
      "reward": 0.6171875,
      "reward_std": 0.1635015830397606,
      "rewards/correctness_reward_func": 0.1328125,
      "rewards/strict_format_reward_func": 0.484375,
      "step": 207
    },
    {
      "completion_length": 34.19921875,
      "epoch": 0.24150943396226415,
      "grad_norm": 0.44449352427969546,
      "kl": 0.7802734375,
      "learning_rate": 8.872872272332219e-07,
      "loss": 0.0312,
      "reward": 0.6171875,
      "reward_std": 0.1620996706187725,
      "rewards/correctness_reward_func": 0.1328125,
      "rewards/strict_format_reward_func": 0.484375,
      "step": 208
    },
    {
      "completion_length": 57.421875,
      "epoch": 0.24267053701015964,
      "grad_norm": 0.8888526828073323,
      "kl": 0.693359375,
      "learning_rate": 8.860946666810077e-07,
      "loss": 0.0277,
      "reward": 0.546875,
      "reward_std": 0.115094143897295,
      "rewards/correctness_reward_func": 0.078125,
      "rewards/strict_format_reward_func": 0.46875,
      "step": 209
    },
    {
      "completion_length": 49.26953125,
      "epoch": 0.24383164005805516,
      "grad_norm": 0.4662997492945863,
      "kl": 0.6845703125,
      "learning_rate": 8.848966407522991e-07,
      "loss": 0.0274,
      "reward": 0.515625,
      "reward_std": 0.0893336832523346,
      "rewards/correctness_reward_func": 0.0390625,
      "rewards/strict_format_reward_func": 0.4765625,
      "step": 210
    },
    {
      "completion_length": 46.41796875,
      "epoch": 0.24499274310595065,
      "grad_norm": 0.330950605212178,
      "kl": 0.701171875,
      "learning_rate": 8.836931664057934e-07,
      "loss": 0.0281,
      "reward": 0.576171875,
      "reward_std": 0.1290367692708969,
      "rewards/correctness_reward_func": 0.09375,
      "rewards/strict_format_reward_func": 0.482421875,
      "step": 211
    },
    {
      "completion_length": 48.34765625,
      "epoch": 0.24615384615384617,
      "grad_norm": 0.4398380701808975,
      "kl": 0.6806640625,
      "learning_rate": 8.824842606773141e-07,
      "loss": 0.0272,
      "reward": 0.546875,
      "reward_std": 0.1642715372145176,
      "rewards/correctness_reward_func": 0.078125,
      "rewards/strict_format_reward_func": 0.46875,
      "step": 212
    },
    {
      "completion_length": 34.70703125,
      "epoch": 0.24731494920174166,
      "grad_norm": 0.5212809108263435,
      "kl": 0.7197265625,
      "learning_rate": 8.81269940679568e-07,
      "loss": 0.0288,
      "reward": 0.572265625,
      "reward_std": 0.0900527872145176,
      "rewards/correctness_reward_func": 0.09375,
      "rewards/strict_format_reward_func": 0.478515625,
      "step": 213
    },
    {
      "completion_length": 36.984375,
      "epoch": 0.24847605224963715,
      "grad_norm": 0.4642489160745716,
      "kl": 0.7744140625,
      "learning_rate": 8.800502236019043e-07,
      "loss": 0.031,
      "reward": 0.634765625,
      "reward_std": 0.17212741822004318,
      "rewards/correctness_reward_func": 0.15625,
      "rewards/strict_format_reward_func": 0.478515625,
      "step": 214
    },
    {
      "completion_length": 43.8046875,
      "epoch": 0.24963715529753266,
      "grad_norm": 0.548886691397983,
      "kl": 0.640625,
      "learning_rate": 8.788251267100704e-07,
      "loss": 0.0256,
      "reward": 0.537109375,
      "reward_std": 0.14466177113354206,
      "rewards/correctness_reward_func": 0.0625,
      "rewards/strict_format_reward_func": 0.474609375,
      "step": 215
    },
    {
      "completion_length": 30.15234375,
      "epoch": 0.2507982583454282,
      "grad_norm": 0.2595648862557409,
      "kl": 0.7314453125,
      "learning_rate": 8.77594667345968e-07,
      "loss": 0.0293,
      "reward": 0.59765625,
      "reward_std": 0.1171875,
      "rewards/correctness_reward_func": 0.1171875,
      "rewards/strict_format_reward_func": 0.48046875,
      "step": 216
    },
    {
      "completion_length": 54.96875,
      "epoch": 0.25195936139332364,
      "grad_norm": 2.2269504312204096,
      "kl": 0.6982421875,
      "learning_rate": 8.763588629274076e-07,
      "loss": 0.0279,
      "reward": 0.541015625,
      "reward_std": 0.125604297965765,
      "rewards/correctness_reward_func": 0.0703125,
      "rewards/strict_format_reward_func": 0.470703125,
      "step": 217
    },
    {
      "completion_length": 45.328125,
      "epoch": 0.25312046444121916,
      "grad_norm": 0.622963472385017,
      "kl": 0.65625,
      "learning_rate": 8.751177309478617e-07,
      "loss": 0.0262,
      "reward": 0.49609375,
      "reward_std": 0.12400043848901987,
      "rewards/correctness_reward_func": 0.03125,
      "rewards/strict_format_reward_func": 0.46484375,
      "step": 218
    },
    {
      "completion_length": 48.9140625,
      "epoch": 0.2542815674891147,
      "grad_norm": 0.3953561223214397,
      "kl": 0.740234375,
      "learning_rate": 8.73871288976217e-07,
      "loss": 0.0296,
      "reward": 0.5859375,
      "reward_std": 0.1987086832523346,
      "rewards/correctness_reward_func": 0.1171875,
      "rewards/strict_format_reward_func": 0.46875,
      "step": 219
    },
    {
      "completion_length": 42.93359375,
      "epoch": 0.25544267053701014,
      "grad_norm": 0.346216440100207,
      "kl": 0.7021484375,
      "learning_rate": 8.726195546565262e-07,
      "loss": 0.0281,
      "reward": 0.5390625,
      "reward_std": 0.140625,
      "rewards/correctness_reward_func": 0.0625,
      "rewards/strict_format_reward_func": 0.4765625,
      "step": 220
    },
    {
      "completion_length": 36.3046875,
      "epoch": 0.25660377358490566,
      "grad_norm": 1.5813028590873024,
      "kl": 0.7578125,
      "learning_rate": 8.713625457077585e-07,
      "loss": 0.0303,
      "reward": 0.568359375,
      "reward_std": 0.12771336920559406,
      "rewards/correctness_reward_func": 0.078125,
      "rewards/strict_format_reward_func": 0.490234375,
      "step": 221
    },
    {
      "completion_length": 44.7265625,
      "epoch": 0.2577648766328012,
      "grad_norm": 1.9405311075755103,
      "kl": 0.8466796875,
      "learning_rate": 8.701002799235474e-07,
      "loss": 0.0339,
      "reward": 0.59375,
      "reward_std": 0.17461559176445007,
      "rewards/correctness_reward_func": 0.125,
      "rewards/strict_format_reward_func": 0.46875,
      "step": 222
    },
    {
      "completion_length": 44.08203125,
      "epoch": 0.25892597968069664,
      "grad_norm": 0.7411664029084547,
      "kl": 0.7255859375,
      "learning_rate": 8.688327751719402e-07,
      "loss": 0.029,
      "reward": 0.552734375,
      "reward_std": 0.1280214935541153,
      "rewards/correctness_reward_func": 0.078125,
      "rewards/strict_format_reward_func": 0.474609375,
      "step": 223
    },
    {
      "completion_length": 52.69921875,
      "epoch": 0.26008708272859216,
      "grad_norm": 0.46133780141282477,
      "kl": 0.7353515625,
      "learning_rate": 8.675600493951447e-07,
      "loss": 0.0294,
      "reward": 0.609375,
      "reward_std": 0.1139797791838646,
      "rewards/correctness_reward_func": 0.140625,
      "rewards/strict_format_reward_func": 0.46875,
      "step": 224
    },
    {
      "completion_length": 38.2578125,
      "epoch": 0.2612481857764877,
      "grad_norm": 1.0318467725501794,
      "kl": 0.6982421875,
      "learning_rate": 8.662821206092747e-07,
      "loss": 0.0279,
      "reward": 0.587890625,
      "reward_std": 0.2320011854171753,
      "rewards/correctness_reward_func": 0.109375,
      "rewards/strict_format_reward_func": 0.478515625,
      "step": 225
    },
    {
      "completion_length": 45.69140625,
      "epoch": 0.2624092888243832,
      "grad_norm": 0.22277480044336392,
      "kl": 0.75,
      "learning_rate": 8.64999006904096e-07,
      "loss": 0.03,
      "reward": 0.513671875,
      "reward_std": 0.094354297965765,
      "rewards/correctness_reward_func": 0.0390625,
      "rewards/strict_format_reward_func": 0.474609375,
      "step": 226
    },
    {
      "completion_length": 32.74609375,
      "epoch": 0.26357039187227865,
      "grad_norm": 0.4780303420088376,
      "kl": 0.7216796875,
      "learning_rate": 8.637107264427688e-07,
      "loss": 0.0289,
      "reward": 0.587890625,
      "reward_std": 0.2041836604475975,
      "rewards/correctness_reward_func": 0.109375,
      "rewards/strict_format_reward_func": 0.478515625,
      "step": 227
    },
    {
      "completion_length": 29.2421875,
      "epoch": 0.26473149492017417,
      "grad_norm": 0.38056082312023104,
      "kl": 0.8544921875,
      "learning_rate": 8.624172974615926e-07,
      "loss": 0.0342,
      "reward": 0.5859375,
      "reward_std": 0.2013554833829403,
      "rewards/correctness_reward_func": 0.109375,
      "rewards/strict_format_reward_func": 0.4765625,
      "step": 228
    },
    {
      "completion_length": 44.23828125,
      "epoch": 0.2658925979680697,
      "grad_norm": 0.39159055696334416,
      "kl": 0.794921875,
      "learning_rate": 8.611187382697458e-07,
      "loss": 0.0317,
      "reward": 0.548828125,
      "reward_std": 0.08323984593153,
      "rewards/correctness_reward_func": 0.078125,
      "rewards/strict_format_reward_func": 0.470703125,
      "step": 229
    },
    {
      "completion_length": 44.40625,
      "epoch": 0.26705370101596515,
      "grad_norm": 0.34689298597919604,
      "kl": 0.7890625,
      "learning_rate": 8.598150672490288e-07,
      "loss": 0.0316,
      "reward": 0.59765625,
      "reward_std": 0.1017715372145176,
      "rewards/correctness_reward_func": 0.1171875,
      "rewards/strict_format_reward_func": 0.48046875,
      "step": 230
    },
    {
      "completion_length": 35.9921875,
      "epoch": 0.26821480406386067,
      "grad_norm": 0.45517531147810925,
      "kl": 0.7734375,
      "learning_rate": 8.585063028536015e-07,
      "loss": 0.0309,
      "reward": 0.564453125,
      "reward_std": 0.1468336395919323,
      "rewards/correctness_reward_func": 0.09375,
      "rewards/strict_format_reward_func": 0.470703125,
      "step": 231
    },
    {
      "completion_length": 36.65625,
      "epoch": 0.2693759071117562,
      "grad_norm": 2.8712605854584963,
      "kl": 0.765625,
      "learning_rate": 8.571924636097243e-07,
      "loss": 0.0307,
      "reward": 0.56640625,
      "reward_std": 0.1352296955883503,
      "rewards/correctness_reward_func": 0.078125,
      "rewards/strict_format_reward_func": 0.48828125,
      "step": 232
    },
    {
      "completion_length": 25.33203125,
      "epoch": 0.27053701015965165,
      "grad_norm": 0.24431120059016243,
      "kl": 0.79296875,
      "learning_rate": 8.558735681154943e-07,
      "loss": 0.0317,
      "reward": 0.578125,
      "reward_std": 0.1430421955883503,
      "rewards/correctness_reward_func": 0.0859375,
      "rewards/strict_format_reward_func": 0.4921875,
      "step": 233
    },
    {
      "completion_length": 25.3203125,
      "epoch": 0.27169811320754716,
      "grad_norm": 1.2698794348386706,
      "kl": 0.802734375,
      "learning_rate": 8.545496350405824e-07,
      "loss": 0.0321,
      "reward": 0.55078125,
      "reward_std": 0.11388554889708757,
      "rewards/correctness_reward_func": 0.0703125,
      "rewards/strict_format_reward_func": 0.48046875,
      "step": 234
    },
    {
      "completion_length": 21.9140625,
      "epoch": 0.2728592162554427,
      "grad_norm": 0.2651240813655857,
      "kl": 0.798828125,
      "learning_rate": 8.532206831259695e-07,
      "loss": 0.032,
      "reward": 0.546875,
      "reward_std": 0.11332463473081589,
      "rewards/correctness_reward_func": 0.0625,
      "rewards/strict_format_reward_func": 0.484375,
      "step": 235
    },
    {
      "completion_length": 25.6015625,
      "epoch": 0.27402031930333814,
      "grad_norm": 0.6783750195102723,
      "kl": 0.7880859375,
      "learning_rate": 8.518867311836807e-07,
      "loss": 0.0315,
      "reward": 0.673828125,
      "reward_std": 0.23925277311354876,
      "rewards/correctness_reward_func": 0.1875,
      "rewards/strict_format_reward_func": 0.486328125,
      "step": 236
    },
    {
      "completion_length": 47.40625,
      "epoch": 0.27518142235123366,
      "grad_norm": 0.4433767128864105,
      "kl": 0.814453125,
      "learning_rate": 8.50547798096519e-07,
      "loss": 0.0326,
      "reward": 0.5234375,
      "reward_std": 0.11280747503042221,
      "rewards/correctness_reward_func": 0.046875,
      "rewards/strict_format_reward_func": 0.4765625,
      "step": 237
    },
    {
      "completion_length": 27.6796875,
      "epoch": 0.2763425253991292,
      "grad_norm": 0.39357743446474786,
      "kl": 0.7763671875,
      "learning_rate": 8.492039028177984e-07,
      "loss": 0.031,
      "reward": 0.591796875,
      "reward_std": 0.1605743244290352,
      "rewards/correctness_reward_func": 0.109375,
      "rewards/strict_format_reward_func": 0.482421875,
      "step": 238
    },
    {
      "completion_length": 23.9453125,
      "epoch": 0.2775036284470247,
      "grad_norm": 0.32648390222909296,
      "kl": 0.767578125,
      "learning_rate": 8.478550643710753e-07,
      "loss": 0.0307,
      "reward": 0.60546875,
      "reward_std": 0.1869390830397606,
      "rewards/correctness_reward_func": 0.1171875,
      "rewards/strict_format_reward_func": 0.48828125,
      "step": 239
    },
    {
      "completion_length": 37.671875,
      "epoch": 0.27866473149492016,
      "grad_norm": 0.35588615244881977,
      "kl": 0.8017578125,
      "learning_rate": 8.465013018498794e-07,
      "loss": 0.0321,
      "reward": 0.560546875,
      "reward_std": 0.16015625,
      "rewards/correctness_reward_func": 0.078125,
      "rewards/strict_format_reward_func": 0.482421875,
      "step": 240
    },
    {
      "completion_length": 31.61328125,
      "epoch": 0.2798258345428157,
      "grad_norm": 0.4154855280252823,
      "kl": 0.8212890625,
      "learning_rate": 8.451426344174432e-07,
      "loss": 0.0328,
      "reward": 0.57421875,
      "reward_std": 0.17284834384918213,
      "rewards/correctness_reward_func": 0.09375,
      "rewards/strict_format_reward_func": 0.48046875,
      "step": 241
    },
    {
      "completion_length": 21.45703125,
      "epoch": 0.2809869375907112,
      "grad_norm": 0.2962320153426291,
      "kl": 0.85546875,
      "learning_rate": 8.437790813064305e-07,
      "loss": 0.0342,
      "reward": 0.65234375,
      "reward_std": 0.1420426331460476,
      "rewards/correctness_reward_func": 0.171875,
      "rewards/strict_format_reward_func": 0.48046875,
      "step": 242
    },
    {
      "completion_length": 29.56640625,
      "epoch": 0.28214804063860666,
      "grad_norm": 0.5104498326555604,
      "kl": 0.75,
      "learning_rate": 8.424106618186653e-07,
      "loss": 0.03,
      "reward": 0.59765625,
      "reward_std": 0.1532718911767006,
      "rewards/correctness_reward_func": 0.109375,
      "rewards/strict_format_reward_func": 0.48828125,
      "step": 243
    },
    {
      "completion_length": 28.71875,
      "epoch": 0.2833091436865022,
      "grad_norm": 1.3952647871604391,
      "kl": 0.7685546875,
      "learning_rate": 8.410373953248568e-07,
      "loss": 0.0308,
      "reward": 0.5390625,
      "reward_std": 0.10100158676505089,
      "rewards/correctness_reward_func": 0.0546875,
      "rewards/strict_format_reward_func": 0.484375,
      "step": 244
    },
    {
      "completion_length": 25.4765625,
      "epoch": 0.2844702467343977,
      "grad_norm": 0.3488892885570999,
      "kl": 0.759765625,
      "learning_rate": 8.396593012643271e-07,
      "loss": 0.0304,
      "reward": 0.55078125,
      "reward_std": 0.1039796955883503,
      "rewards/correctness_reward_func": 0.0625,
      "rewards/strict_format_reward_func": 0.48828125,
      "step": 245
    },
    {
      "completion_length": 36.640625,
      "epoch": 0.28563134978229315,
      "grad_norm": 0.8252384593648274,
      "kl": 0.7177734375,
      "learning_rate": 8.382763991447343e-07,
      "loss": 0.0287,
      "reward": 0.580078125,
      "reward_std": 0.1716102585196495,
      "rewards/correctness_reward_func": 0.1015625,
      "rewards/strict_format_reward_func": 0.478515625,
      "step": 246
    },
    {
      "completion_length": 39.62109375,
      "epoch": 0.28679245283018867,
      "grad_norm": 9.474712584278485,
      "kl": 0.697265625,
      "learning_rate": 8.368887085417977e-07,
      "loss": 0.0279,
      "reward": 0.560546875,
      "reward_std": 0.1315324828028679,
      "rewards/correctness_reward_func": 0.078125,
      "rewards/strict_format_reward_func": 0.482421875,
      "step": 247
    },
    {
      "completion_length": 32.84375,
      "epoch": 0.2879535558780842,
      "grad_norm": 0.5120202650685787,
      "kl": 0.7353515625,
      "learning_rate": 8.354962490990201e-07,
      "loss": 0.0294,
      "reward": 0.513671875,
      "reward_std": 0.0844484455883503,
      "rewards/correctness_reward_func": 0.03125,
      "rewards/strict_format_reward_func": 0.482421875,
      "step": 248
    },
    {
      "completion_length": 20.99609375,
      "epoch": 0.2891146589259797,
      "grad_norm": 1.0700667980733463,
      "kl": 0.6875,
      "learning_rate": 8.340990405274091e-07,
      "loss": 0.0275,
      "reward": 0.53125,
      "reward_std": 0.0805421955883503,
      "rewards/correctness_reward_func": 0.0390625,
      "rewards/strict_format_reward_func": 0.4921875,
      "step": 249
    },
    {
      "completion_length": 35.40234375,
      "epoch": 0.29027576197387517,
      "grad_norm": 1.0418024319085948,
      "kl": 0.91015625,
      "learning_rate": 8.326971026051999e-07,
      "loss": 0.0364,
      "reward": 0.55859375,
      "reward_std": 0.09979298897087574,
      "rewards/correctness_reward_func": 0.0703125,
      "rewards/strict_format_reward_func": 0.48828125,
      "step": 250
    },
    {
      "completion_length": 23.42578125,
      "epoch": 0.2914368650217707,
      "grad_norm": 0.9720263563682217,
      "kl": 0.873046875,
      "learning_rate": 8.31290455177573e-07,
      "loss": 0.0349,
      "reward": 0.576171875,
      "reward_std": 0.14594027400016785,
      "rewards/correctness_reward_func": 0.09375,
      "rewards/strict_format_reward_func": 0.482421875,
      "step": 251
    },
    {
      "completion_length": 30.20703125,
      "epoch": 0.2925979680696662,
      "grad_norm": 0.773176913897642,
      "kl": 0.6806640625,
      "learning_rate": 8.298791181563754e-07,
      "loss": 0.0273,
      "reward": 0.583984375,
      "reward_std": 0.11811564117670059,
      "rewards/correctness_reward_func": 0.09375,
      "rewards/strict_format_reward_func": 0.490234375,
      "step": 252
    },
    {
      "completion_length": 46.68359375,
      "epoch": 0.29375907111756167,
      "grad_norm": 1.003168597159282,
      "kl": 0.6484375,
      "learning_rate": 8.28463111519837e-07,
      "loss": 0.0259,
      "reward": 0.5234375,
      "reward_std": 0.1175113394856453,
      "rewards/correctness_reward_func": 0.046875,
      "rewards/strict_format_reward_func": 0.4765625,
      "step": 253
    },
    {
      "completion_length": 28.07421875,
      "epoch": 0.2949201741654572,
      "grad_norm": 0.4721784825997983,
      "kl": 0.6435546875,
      "learning_rate": 8.270424553122898e-07,
      "loss": 0.0257,
      "reward": 0.544921875,
      "reward_std": 0.0844484455883503,
      "rewards/correctness_reward_func": 0.0546875,
      "rewards/strict_format_reward_func": 0.490234375,
      "step": 254
    },
    {
      "completion_length": 29.39453125,
      "epoch": 0.2960812772133527,
      "grad_norm": 0.8645019103999428,
      "kl": 0.654296875,
      "learning_rate": 8.256171696438816e-07,
      "loss": 0.0261,
      "reward": 0.578125,
      "reward_std": 0.1610843874514103,
      "rewards/correctness_reward_func": 0.09375,
      "rewards/strict_format_reward_func": 0.484375,
      "step": 255
    },
    {
      "completion_length": 31.328125,
      "epoch": 0.29724238026124816,
      "grad_norm": 1.0576590786193392,
      "kl": 0.6591796875,
      "learning_rate": 8.241872746902934e-07,
      "loss": 0.0263,
      "reward": 0.5234375,
      "reward_std": 0.09175087884068489,
      "rewards/correctness_reward_func": 0.0390625,
      "rewards/strict_format_reward_func": 0.484375,
      "step": 256
    },
    {
      "completion_length": 49.671875,
      "epoch": 0.2984034833091437,
      "grad_norm": 2.5033828252696915,
      "kl": 0.6357421875,
      "learning_rate": 8.22752790692453e-07,
      "loss": 0.0254,
      "reward": 0.56640625,
      "reward_std": 0.1518699713051319,
      "rewards/correctness_reward_func": 0.0859375,
      "rewards/strict_format_reward_func": 0.48046875,
      "step": 257
    },
    {
      "completion_length": 31.375,
      "epoch": 0.2995645863570392,
      "grad_norm": 2.0790046459772817,
      "kl": 0.72265625,
      "learning_rate": 8.213137379562485e-07,
      "loss": 0.0289,
      "reward": 0.580078125,
      "reward_std": 0.20096022635698318,
      "rewards/correctness_reward_func": 0.1171875,
      "rewards/strict_format_reward_func": 0.462890625,
      "step": 258
    },
    {
      "completion_length": 74.29296875,
      "epoch": 0.3007256894049347,
      "grad_norm": 0.6853475598496406,
      "kl": 0.7080078125,
      "learning_rate": 8.198701368522412e-07,
      "loss": 0.0283,
      "reward": 0.54296875,
      "reward_std": 0.15424226596951485,
      "rewards/correctness_reward_func": 0.078125,
      "rewards/strict_format_reward_func": 0.46484375,
      "step": 259
    },
    {
      "completion_length": 38.55078125,
      "epoch": 0.3018867924528302,
      "grad_norm": 3.7197912494854255,
      "kl": 0.7197265625,
      "learning_rate": 8.184220078153768e-07,
      "loss": 0.0288,
      "reward": 0.564453125,
      "reward_std": 0.1538761891424656,
      "rewards/correctness_reward_func": 0.09375,
      "rewards/strict_format_reward_func": 0.470703125,
      "step": 260
    },
    {
      "completion_length": 35.63671875,
      "epoch": 0.3030478955007257,
      "grad_norm": 4.452860398190473,
      "kl": 0.72265625,
      "learning_rate": 8.169693713446959e-07,
      "loss": 0.0289,
      "reward": 0.599609375,
      "reward_std": 0.14453125,
      "rewards/correctness_reward_func": 0.1171875,
      "rewards/strict_format_reward_func": 0.482421875,
      "step": 261
    },
    {
      "completion_length": 28.71484375,
      "epoch": 0.3042089985486212,
      "grad_norm": 0.39968494901525564,
      "kl": 0.73828125,
      "learning_rate": 8.155122480030452e-07,
      "loss": 0.0296,
      "reward": 0.61328125,
      "reward_std": 0.2245996594429016,
      "rewards/correctness_reward_func": 0.1328125,
      "rewards/strict_format_reward_func": 0.48046875,
      "step": 262
    },
    {
      "completion_length": 53.375,
      "epoch": 0.3053701015965167,
      "grad_norm": 2.851724228639477,
      "kl": 0.771484375,
      "learning_rate": 8.140506584167844e-07,
      "loss": 0.0309,
      "reward": 0.529296875,
      "reward_std": 0.1715945415198803,
      "rewards/correctness_reward_func": 0.0625,
      "rewards/strict_format_reward_func": 0.466796875,
      "step": 263
    },
    {
      "completion_length": 53.05078125,
      "epoch": 0.3065312046444122,
      "grad_norm": 1.7213671620214588,
      "kl": 0.6494140625,
      "learning_rate": 8.12584623275496e-07,
      "loss": 0.026,
      "reward": 0.544921875,
      "reward_std": 0.1769692748785019,
      "rewards/correctness_reward_func": 0.078125,
      "rewards/strict_format_reward_func": 0.466796875,
      "step": 264
    },
    {
      "completion_length": 50.8359375,
      "epoch": 0.3076923076923077,
      "grad_norm": 0.442713159312425,
      "kl": 0.6513671875,
      "learning_rate": 8.111141633316914e-07,
      "loss": 0.0261,
      "reward": 0.611328125,
      "reward_std": 0.18654337525367737,
      "rewards/correctness_reward_func": 0.140625,
      "rewards/strict_format_reward_func": 0.470703125,
      "step": 265
    },
    {
      "completion_length": 57.09375,
      "epoch": 0.30885341074020317,
      "grad_norm": 0.5370252752945665,
      "kl": 0.6982421875,
      "learning_rate": 8.096392994005176e-07,
      "loss": 0.0279,
      "reward": 0.5234375,
      "reward_std": 0.1663648895919323,
      "rewards/correctness_reward_func": 0.0703125,
      "rewards/strict_format_reward_func": 0.453125,
      "step": 266
    },
    {
      "completion_length": 38.22265625,
      "epoch": 0.3100145137880987,
      "grad_norm": 0.38559708214902666,
      "kl": 0.703125,
      "learning_rate": 8.08160052359462e-07,
      "loss": 0.0281,
      "reward": 0.607421875,
      "reward_std": 0.2017301730811596,
      "rewards/correctness_reward_func": 0.1328125,
      "rewards/strict_format_reward_func": 0.474609375,
      "step": 267
    },
    {
      "completion_length": 43.53515625,
      "epoch": 0.3111756168359942,
      "grad_norm": 0.8317974710954902,
      "kl": 0.7470703125,
      "learning_rate": 8.066764431480583e-07,
      "loss": 0.0299,
      "reward": 0.5703125,
      "reward_std": 0.1564590334892273,
      "rewards/correctness_reward_func": 0.09375,
      "rewards/strict_format_reward_func": 0.4765625,
      "step": 268
    },
    {
      "completion_length": 55.6484375,
      "epoch": 0.31233671988388967,
      "grad_norm": 0.674478273947861,
      "kl": 0.734375,
      "learning_rate": 8.051884927675877e-07,
      "loss": 0.0294,
      "reward": 0.5390625,
      "reward_std": 0.1821046955883503,
      "rewards/correctness_reward_func": 0.0859375,
      "rewards/strict_format_reward_func": 0.453125,
      "step": 269
    },
    {
      "completion_length": 30.5703125,
      "epoch": 0.3134978229317852,
      "grad_norm": 7.412108279999894,
      "kl": 0.759765625,
      "learning_rate": 8.036962222807837e-07,
      "loss": 0.0304,
      "reward": 0.58984375,
      "reward_std": 0.1655949391424656,
      "rewards/correctness_reward_func": 0.1171875,
      "rewards/strict_format_reward_func": 0.47265625,
      "step": 270
    },
    {
      "completion_length": 27.45703125,
      "epoch": 0.3146589259796807,
      "grad_norm": 0.35968132821390736,
      "kl": 0.73828125,
      "learning_rate": 8.021996528115333e-07,
      "loss": 0.0295,
      "reward": 0.541015625,
      "reward_std": 0.1393449790775776,
      "rewards/correctness_reward_func": 0.0625,
      "rewards/strict_format_reward_func": 0.478515625,
      "step": 271
    },
    {
      "completion_length": 35.44140625,
      "epoch": 0.3158200290275762,
      "grad_norm": 0.23026737567150152,
      "kl": 0.7548828125,
      "learning_rate": 8.006988055445778e-07,
      "loss": 0.0301,
      "reward": 0.541015625,
      "reward_std": 0.07784454245120287,
      "rewards/correctness_reward_func": 0.0625,
      "rewards/strict_format_reward_func": 0.478515625,
      "step": 272
    },
    {
      "completion_length": 33.1484375,
      "epoch": 0.3169811320754717,
      "grad_norm": 0.31612172425026225,
      "kl": 0.7666015625,
      "learning_rate": 7.991937017252126e-07,
      "loss": 0.0307,
      "reward": 0.640625,
      "reward_std": 0.16107875108718872,
      "rewards/correctness_reward_func": 0.1640625,
      "rewards/strict_format_reward_func": 0.4765625,
      "step": 273
    },
    {
      "completion_length": 44.54296875,
      "epoch": 0.3181422351233672,
      "grad_norm": 0.6776325232505502,
      "kl": 0.763671875,
      "learning_rate": 7.976843626589874e-07,
      "loss": 0.0306,
      "reward": 0.671875,
      "reward_std": 0.17429219186306,
      "rewards/correctness_reward_func": 0.1953125,
      "rewards/strict_format_reward_func": 0.4765625,
      "step": 274
    },
    {
      "completion_length": 21.1328125,
      "epoch": 0.3193033381712627,
      "grad_norm": 0.3348417539199389,
      "kl": 0.8203125,
      "learning_rate": 7.961708097114039e-07,
      "loss": 0.0328,
      "reward": 0.642578125,
      "reward_std": 0.21827621944248676,
      "rewards/correctness_reward_func": 0.15625,
      "rewards/strict_format_reward_func": 0.486328125,
      "step": 275
    },
    {
      "completion_length": 29.984375,
      "epoch": 0.3204644412191582,
      "grad_norm": 0.19295177951085285,
      "kl": 0.7841796875,
      "learning_rate": 7.946530643076137e-07,
      "loss": 0.0314,
      "reward": 0.591796875,
      "reward_std": 0.1156984455883503,
      "rewards/correctness_reward_func": 0.109375,
      "rewards/strict_format_reward_func": 0.482421875,
      "step": 276
    },
    {
      "completion_length": 32.6484375,
      "epoch": 0.3216255442670537,
      "grad_norm": 0.24812441240225833,
      "kl": 0.7890625,
      "learning_rate": 7.931311479321143e-07,
      "loss": 0.0316,
      "reward": 0.642578125,
      "reward_std": 0.1479274332523346,
      "rewards/correctness_reward_func": 0.15625,
      "rewards/strict_format_reward_func": 0.486328125,
      "step": 277
    },
    {
      "completion_length": 51.703125,
      "epoch": 0.3227866473149492,
      "grad_norm": 0.24875270584616957,
      "kl": 0.7470703125,
      "learning_rate": 7.916050821284462e-07,
      "loss": 0.0299,
      "reward": 0.55078125,
      "reward_std": 0.1319277435541153,
      "rewards/correctness_reward_func": 0.0703125,
      "rewards/strict_format_reward_func": 0.48046875,
      "step": 278
    },
    {
      "completion_length": 25.44140625,
      "epoch": 0.3239477503628447,
      "grad_norm": 0.41045591923433544,
      "kl": 0.8203125,
      "learning_rate": 7.90074888498887e-07,
      "loss": 0.0329,
      "reward": 0.6640625,
      "reward_std": 0.20949183404445648,
      "rewards/correctness_reward_func": 0.1796875,
      "rewards/strict_format_reward_func": 0.484375,
      "step": 279
    },
    {
      "completion_length": 33.265625,
      "epoch": 0.3251088534107402,
      "grad_norm": 0.5921301270100346,
      "kl": 0.794921875,
      "learning_rate": 7.885405887041459e-07,
      "loss": 0.0318,
      "reward": 0.556640625,
      "reward_std": 0.1345105916261673,
      "rewards/correctness_reward_func": 0.078125,
      "rewards/strict_format_reward_func": 0.478515625,
      "step": 280
    },
    {
      "completion_length": 43.90234375,
      "epoch": 0.3262699564586357,
      "grad_norm": 0.6987483029959047,
      "kl": 0.787109375,
      "learning_rate": 7.870022044630568e-07,
      "loss": 0.0315,
      "reward": 0.572265625,
      "reward_std": 0.1548914648592472,
      "rewards/correctness_reward_func": 0.09375,
      "rewards/strict_format_reward_func": 0.478515625,
      "step": 281
    },
    {
      "completion_length": 27.69140625,
      "epoch": 0.32743105950653123,
      "grad_norm": 0.9294871394333097,
      "kl": 0.78515625,
      "learning_rate": 7.854597575522717e-07,
      "loss": 0.0314,
      "reward": 0.625,
      "reward_std": 0.2526262328028679,
      "rewards/correctness_reward_func": 0.140625,
      "rewards/strict_format_reward_func": 0.484375,
      "step": 282
    },
    {
      "completion_length": 46.27734375,
      "epoch": 0.3285921625544267,
      "grad_norm": 3.7732561147670802,
      "kl": 0.72265625,
      "learning_rate": 7.839132698059514e-07,
      "loss": 0.0289,
      "reward": 0.603515625,
      "reward_std": 0.1705949828028679,
      "rewards/correctness_reward_func": 0.109375,
      "rewards/strict_format_reward_func": 0.494140625,
      "step": 283
    },
    {
      "completion_length": 46.1953125,
      "epoch": 0.3297532656023222,
      "grad_norm": 0.3556241277311047,
      "kl": 0.76171875,
      "learning_rate": 7.82362763115457e-07,
      "loss": 0.0305,
      "reward": 0.58203125,
      "reward_std": 0.1598757915198803,
      "rewards/correctness_reward_func": 0.1015625,
      "rewards/strict_format_reward_func": 0.48046875,
      "step": 284
    },
    {
      "completion_length": 43.4921875,
      "epoch": 0.3309143686502177,
      "grad_norm": 0.3342258795715177,
      "kl": 0.7685546875,
      "learning_rate": 7.808082594290402e-07,
      "loss": 0.0308,
      "reward": 0.609375,
      "reward_std": 0.15624435618519783,
      "rewards/correctness_reward_func": 0.125,
      "rewards/strict_format_reward_func": 0.484375,
      "step": 285
    },
    {
      "completion_length": 27.234375,
      "epoch": 0.3320754716981132,
      "grad_norm": 3.5943102994163274,
      "kl": 0.7783203125,
      "learning_rate": 7.792497807515316e-07,
      "loss": 0.0311,
      "reward": 0.64453125,
      "reward_std": 0.18605433031916618,
      "rewards/correctness_reward_func": 0.15625,
      "rewards/strict_format_reward_func": 0.48828125,
      "step": 286
    },
    {
      "completion_length": 43.7734375,
      "epoch": 0.3332365747460087,
      "grad_norm": 0.24602456316761495,
      "kl": 0.7333984375,
      "learning_rate": 7.776873491440307e-07,
      "loss": 0.0293,
      "reward": 0.60546875,
      "reward_std": 0.1486465372145176,
      "rewards/correctness_reward_func": 0.1171875,
      "rewards/strict_format_reward_func": 0.48828125,
      "step": 287
    },
    {
      "completion_length": 42.15625,
      "epoch": 0.3343976777939042,
      "grad_norm": 0.600530335279195,
      "kl": 0.7314453125,
      "learning_rate": 7.761209867235923e-07,
      "loss": 0.0293,
      "reward": 0.609375,
      "reward_std": 0.2011621668934822,
      "rewards/correctness_reward_func": 0.125,
      "rewards/strict_format_reward_func": 0.484375,
      "step": 288
    },
    {
      "completion_length": 39.6796875,
      "epoch": 0.3355587808417997,
      "grad_norm": 0.2995300813353396,
      "kl": 0.736328125,
      "learning_rate": 7.745507156629144e-07,
      "loss": 0.0294,
      "reward": 0.626953125,
      "reward_std": 0.1818399503827095,
      "rewards/correctness_reward_func": 0.140625,
      "rewards/strict_format_reward_func": 0.486328125,
      "step": 289
    },
    {
      "completion_length": 38.13671875,
      "epoch": 0.3367198838896952,
      "grad_norm": 1.044126937484855,
      "kl": 0.6904296875,
      "learning_rate": 7.729765581900235e-07,
      "loss": 0.0277,
      "reward": 0.544921875,
      "reward_std": 0.11239649448543787,
      "rewards/correctness_reward_func": 0.0625,
      "rewards/strict_format_reward_func": 0.482421875,
      "step": 290
    },
    {
      "completion_length": 49.296875,
      "epoch": 0.3378809869375907,
      "grad_norm": 0.2824327700655812,
      "kl": 0.703125,
      "learning_rate": 7.713985365879605e-07,
      "loss": 0.0281,
      "reward": 0.58203125,
      "reward_std": 0.20035592839121819,
      "rewards/correctness_reward_func": 0.1015625,
      "rewards/strict_format_reward_func": 0.48046875,
      "step": 291
    },
    {
      "completion_length": 65.84765625,
      "epoch": 0.33904208998548624,
      "grad_norm": 0.247824658119491,
      "kl": 0.716796875,
      "learning_rate": 7.698166731944653e-07,
      "loss": 0.0286,
      "reward": 0.533203125,
      "reward_std": 0.08323984593153,
      "rewards/correctness_reward_func": 0.0546875,
      "rewards/strict_format_reward_func": 0.478515625,
      "step": 292
    },
    {
      "completion_length": 38.046875,
      "epoch": 0.3402031930333817,
      "grad_norm": 0.2895158117455258,
      "kl": 0.693359375,
      "learning_rate": 7.682309904016599e-07,
      "loss": 0.0277,
      "reward": 0.517578125,
      "reward_std": 0.0766359455883503,
      "rewards/correctness_reward_func": 0.03125,
      "rewards/strict_format_reward_func": 0.486328125,
      "step": 293
    },
    {
      "completion_length": 47.41796875,
      "epoch": 0.3413642960812772,
      "grad_norm": 0.4958137248441807,
      "kl": 0.7646484375,
      "learning_rate": 7.666415106557327e-07,
      "loss": 0.0305,
      "reward": 0.544921875,
      "reward_std": 0.11095601879060268,
      "rewards/correctness_reward_func": 0.0625,
      "rewards/strict_format_reward_func": 0.482421875,
      "step": 294
    },
    {
      "completion_length": 67.2265625,
      "epoch": 0.34252539912917274,
      "grad_norm": 0.4138009604439513,
      "kl": 0.6845703125,
      "learning_rate": 7.650482564566192e-07,
      "loss": 0.0274,
      "reward": 0.57421875,
      "reward_std": 0.2022402435541153,
      "rewards/correctness_reward_func": 0.1015625,
      "rewards/strict_format_reward_func": 0.47265625,
      "step": 295
    },
    {
      "completion_length": 35.2421875,
      "epoch": 0.3436865021770682,
      "grad_norm": 1.3963827489118958,
      "kl": 0.77734375,
      "learning_rate": 7.634512503576849e-07,
      "loss": 0.0311,
      "reward": 0.6171875,
      "reward_std": 0.109375,
      "rewards/correctness_reward_func": 0.1328125,
      "rewards/strict_format_reward_func": 0.484375,
      "step": 296
    },
    {
      "completion_length": 42.29296875,
      "epoch": 0.3448476052249637,
      "grad_norm": 0.2378588696433431,
      "kl": 0.6171875,
      "learning_rate": 7.618505149654051e-07,
      "loss": 0.0247,
      "reward": 0.52734375,
      "reward_std": 0.0703125,
      "rewards/correctness_reward_func": 0.046875,
      "rewards/strict_format_reward_func": 0.48046875,
      "step": 297
    },
    {
      "completion_length": 55.24609375,
      "epoch": 0.34600870827285923,
      "grad_norm": 1.6488130875167075,
      "kl": 0.908203125,
      "learning_rate": 7.602460729390454e-07,
      "loss": 0.0363,
      "reward": 0.607421875,
      "reward_std": 0.2039383314549923,
      "rewards/correctness_reward_func": 0.1328125,
      "rewards/strict_format_reward_func": 0.474609375,
      "step": 298
    },
    {
      "completion_length": 57.0390625,
      "epoch": 0.3471698113207547,
      "grad_norm": 0.28158042067891265,
      "kl": 0.67578125,
      "learning_rate": 7.586379469903408e-07,
      "loss": 0.027,
      "reward": 0.5390625,
      "reward_std": 0.1252090372145176,
      "rewards/correctness_reward_func": 0.0546875,
      "rewards/strict_format_reward_func": 0.484375,
      "step": 299
    },
    {
      "completion_length": 70.46484375,
      "epoch": 0.3483309143686502,
      "grad_norm": 0.4201728799059877,
      "kl": 0.65234375,
      "learning_rate": 7.570261598831742e-07,
      "loss": 0.0261,
      "reward": 0.619140625,
      "reward_std": 0.19710255414247513,
      "rewards/correctness_reward_func": 0.140625,
      "rewards/strict_format_reward_func": 0.478515625,
      "step": 300
    },
    {
      "completion_length": 52.83984375,
      "epoch": 0.34949201741654573,
      "grad_norm": 0.2803079731494032,
      "kl": 0.6904296875,
      "learning_rate": 7.554107344332538e-07,
      "loss": 0.0276,
      "reward": 0.609375,
      "reward_std": 0.1758246347308159,
      "rewards/correctness_reward_func": 0.125,
      "rewards/strict_format_reward_func": 0.484375,
      "step": 301
    },
    {
      "completion_length": 72.19921875,
      "epoch": 0.3506531204644412,
      "grad_norm": 0.32997263344841316,
      "kl": 0.6591796875,
      "learning_rate": 7.537916935077913e-07,
      "loss": 0.0264,
      "reward": 0.55078125,
      "reward_std": 0.1532718874514103,
      "rewards/correctness_reward_func": 0.0703125,
      "rewards/strict_format_reward_func": 0.48046875,
      "step": 302
    },
    {
      "completion_length": 59.51953125,
      "epoch": 0.3518142235123367,
      "grad_norm": 0.32482961945010463,
      "kl": 0.6728515625,
      "learning_rate": 7.521690600251764e-07,
      "loss": 0.0269,
      "reward": 0.556640625,
      "reward_std": 0.1361735537648201,
      "rewards/correctness_reward_func": 0.078125,
      "rewards/strict_format_reward_func": 0.478515625,
      "step": 303
    },
    {
      "completion_length": 71.43359375,
      "epoch": 0.3529753265602322,
      "grad_norm": 0.21926170187871932,
      "kl": 0.6142578125,
      "learning_rate": 7.505428569546542e-07,
      "loss": 0.0246,
      "reward": 0.578125,
      "reward_std": 0.1251305192708969,
      "rewards/correctness_reward_func": 0.1015625,
      "rewards/strict_format_reward_func": 0.4765625,
      "step": 304
    },
    {
      "completion_length": 83.47265625,
      "epoch": 0.35413642960812775,
      "grad_norm": 1.2095295337441825,
      "kl": 0.57421875,
      "learning_rate": 7.489131073159987e-07,
      "loss": 0.0229,
      "reward": 0.583984375,
      "reward_std": 0.22483637183904648,
      "rewards/correctness_reward_func": 0.1171875,
      "rewards/strict_format_reward_func": 0.466796875,
      "step": 305
    },
    {
      "completion_length": 66.84765625,
      "epoch": 0.3552975326560232,
      "grad_norm": 0.2892214943510883,
      "kl": 0.55126953125,
      "learning_rate": 7.472798341791876e-07,
      "loss": 0.0221,
      "reward": 0.5546875,
      "reward_std": 0.20070216432213783,
      "rewards/correctness_reward_func": 0.0859375,
      "rewards/strict_format_reward_func": 0.46875,
      "step": 306
    },
    {
      "completion_length": 64.0703125,
      "epoch": 0.3564586357039187,
      "grad_norm": 0.27395677460271195,
      "kl": 0.533203125,
      "learning_rate": 7.456430606640757e-07,
      "loss": 0.0214,
      "reward": 0.533203125,
      "reward_std": 0.15057423803955317,
      "rewards/correctness_reward_func": 0.0625,
      "rewards/strict_format_reward_func": 0.470703125,
      "step": 307
    },
    {
      "completion_length": 93.12890625,
      "epoch": 0.35761973875181424,
      "grad_norm": 0.2623932543969406,
      "kl": 0.4482421875,
      "learning_rate": 7.440028099400676e-07,
      "loss": 0.0179,
      "reward": 0.53515625,
      "reward_std": 0.18847334384918213,
      "rewards/correctness_reward_func": 0.078125,
      "rewards/strict_format_reward_func": 0.45703125,
      "step": 308
    },
    {
      "completion_length": 96.703125,
      "epoch": 0.3587808417997097,
      "grad_norm": 0.421598782981462,
      "kl": 0.60205078125,
      "learning_rate": 7.423591052257893e-07,
      "loss": 0.024,
      "reward": 0.640625,
      "reward_std": 0.2437199391424656,
      "rewards/correctness_reward_func": 0.171875,
      "rewards/strict_format_reward_func": 0.46875,
      "step": 309
    },
    {
      "completion_length": 79.5,
      "epoch": 0.3599419448476052,
      "grad_norm": 0.3744214040179616,
      "kl": 0.51318359375,
      "learning_rate": 7.407119697887601e-07,
      "loss": 0.0205,
      "reward": 0.556640625,
      "reward_std": 0.07905314117670059,
      "rewards/correctness_reward_func": 0.0703125,
      "rewards/strict_format_reward_func": 0.486328125,
      "step": 310
    },
    {
      "completion_length": 91.90625,
      "epoch": 0.36110304789550074,
      "grad_norm": 0.29732270177076153,
      "kl": 0.4931640625,
      "learning_rate": 7.390614269450632e-07,
      "loss": 0.0197,
      "reward": 0.53515625,
      "reward_std": 0.19749262183904648,
      "rewards/correctness_reward_func": 0.0859375,
      "rewards/strict_format_reward_func": 0.44921875,
      "step": 311
    },
    {
      "completion_length": 90.94140625,
      "epoch": 0.3622641509433962,
      "grad_norm": 0.39324171683243425,
      "kl": 0.45166015625,
      "learning_rate": 7.374075000590155e-07,
      "loss": 0.0181,
      "reward": 0.5703125,
      "reward_std": 0.2068813145160675,
      "rewards/correctness_reward_func": 0.109375,
      "rewards/strict_format_reward_func": 0.4609375,
      "step": 312
    },
    {
      "completion_length": 88.10546875,
      "epoch": 0.3634252539912917,
      "grad_norm": 0.3999210759287133,
      "kl": 0.50537109375,
      "learning_rate": 7.357502125428358e-07,
      "loss": 0.0203,
      "reward": 0.611328125,
      "reward_std": 0.2668927013874054,
      "rewards/correctness_reward_func": 0.1484375,
      "rewards/strict_format_reward_func": 0.462890625,
      "step": 313
    },
    {
      "completion_length": 78.578125,
      "epoch": 0.36458635703918724,
      "grad_norm": 0.2934147726421681,
      "kl": 0.5,
      "learning_rate": 7.340895878563161e-07,
      "loss": 0.02,
      "reward": 0.59375,
      "reward_std": 0.20618987828493118,
      "rewards/correctness_reward_func": 0.125,
      "rewards/strict_format_reward_func": 0.46875,
      "step": 314
    },
    {
      "completion_length": 88.6484375,
      "epoch": 0.36574746008708275,
      "grad_norm": 0.304036568316934,
      "kl": 0.484375,
      "learning_rate": 7.324256495064866e-07,
      "loss": 0.0194,
      "reward": 0.595703125,
      "reward_std": 0.1582719311118126,
      "rewards/correctness_reward_func": 0.1328125,
      "rewards/strict_format_reward_func": 0.462890625,
      "step": 315
    },
    {
      "completion_length": 77.09375,
      "epoch": 0.3669085631349782,
      "grad_norm": 0.27730249987885874,
      "kl": 0.51171875,
      "learning_rate": 7.307584210472843e-07,
      "loss": 0.0205,
      "reward": 0.59375,
      "reward_std": 0.19424450024962425,
      "rewards/correctness_reward_func": 0.1171875,
      "rewards/strict_format_reward_func": 0.4765625,
      "step": 316
    },
    {
      "completion_length": 79.24609375,
      "epoch": 0.36806966618287373,
      "grad_norm": 1.1443891203152459,
      "kl": 0.5205078125,
      "learning_rate": 7.290879260792202e-07,
      "loss": 0.0209,
      "reward": 0.599609375,
      "reward_std": 0.2074493207037449,
      "rewards/correctness_reward_func": 0.1171875,
      "rewards/strict_format_reward_func": 0.482421875,
      "step": 317
    },
    {
      "completion_length": 85.109375,
      "epoch": 0.36923076923076925,
      "grad_norm": 0.8272363687978308,
      "kl": 0.53515625,
      "learning_rate": 7.274141882490435e-07,
      "loss": 0.0214,
      "reward": 0.623046875,
      "reward_std": 0.2066008560359478,
      "rewards/correctness_reward_func": 0.1640625,
      "rewards/strict_format_reward_func": 0.458984375,
      "step": 318
    },
    {
      "completion_length": 75.828125,
      "epoch": 0.3703918722786647,
      "grad_norm": 0.39409786758012594,
      "kl": 0.57666015625,
      "learning_rate": 7.257372312494087e-07,
      "loss": 0.0231,
      "reward": 0.677734375,
      "reward_std": 0.22956114634871483,
      "rewards/correctness_reward_func": 0.2109375,
      "rewards/strict_format_reward_func": 0.466796875,
      "step": 319
    },
    {
      "completion_length": 90.39453125,
      "epoch": 0.37155297532656023,
      "grad_norm": 0.5705020970860728,
      "kl": 0.5244140625,
      "learning_rate": 7.240570788185387e-07,
      "loss": 0.021,
      "reward": 0.64453125,
      "reward_std": 0.20728367194533348,
      "rewards/correctness_reward_func": 0.171875,
      "rewards/strict_format_reward_func": 0.47265625,
      "step": 320
    },
    {
      "completion_length": 112.0703125,
      "epoch": 0.37271407837445575,
      "grad_norm": 0.2780015737724446,
      "kl": 0.46728515625,
      "learning_rate": 7.223737547398897e-07,
      "loss": 0.0187,
      "reward": 0.552734375,
      "reward_std": 0.1929386854171753,
      "rewards/correctness_reward_func": 0.0859375,
      "rewards/strict_format_reward_func": 0.466796875,
      "step": 321
    },
    {
      "completion_length": 99.4140625,
      "epoch": 0.3738751814223512,
      "grad_norm": 3.609413827943461,
      "kl": 0.5478515625,
      "learning_rate": 7.206872828418146e-07,
      "loss": 0.0219,
      "reward": 0.580078125,
      "reward_std": 0.1582719311118126,
      "rewards/correctness_reward_func": 0.109375,
      "rewards/strict_format_reward_func": 0.470703125,
      "step": 322
    },
    {
      "completion_length": 78.84375,
      "epoch": 0.37503628447024673,
      "grad_norm": 0.3837761508066674,
      "kl": 0.51171875,
      "learning_rate": 7.189976869972247e-07,
      "loss": 0.0205,
      "reward": 0.568359375,
      "reward_std": 0.2117508314549923,
      "rewards/correctness_reward_func": 0.09375,
      "rewards/strict_format_reward_func": 0.474609375,
      "step": 323
    },
    {
      "completion_length": 101.32421875,
      "epoch": 0.37619738751814225,
      "grad_norm": 0.35836358831864257,
      "kl": 0.466796875,
      "learning_rate": 7.173049911232532e-07,
      "loss": 0.0187,
      "reward": 0.60546875,
      "reward_std": 0.2125641666352749,
      "rewards/correctness_reward_func": 0.1328125,
      "rewards/strict_format_reward_func": 0.47265625,
      "step": 324
    },
    {
      "completion_length": 93.78515625,
      "epoch": 0.37735849056603776,
      "grad_norm": 0.3954539999395301,
      "kl": 0.49169921875,
      "learning_rate": 7.156092191809151e-07,
      "loss": 0.0197,
      "reward": 0.6015625,
      "reward_std": 0.2178652472794056,
      "rewards/correctness_reward_func": 0.1328125,
      "rewards/strict_format_reward_func": 0.46875,
      "step": 325
    },
    {
      "completion_length": 95.578125,
      "epoch": 0.3785195936139332,
      "grad_norm": 0.30020285338127595,
      "kl": 0.4892578125,
      "learning_rate": 7.139103951747693e-07,
      "loss": 0.0195,
      "reward": 0.568359375,
      "reward_std": 0.1592714935541153,
      "rewards/correctness_reward_func": 0.1015625,
      "rewards/strict_format_reward_func": 0.466796875,
      "step": 326
    },
    {
      "completion_length": 94.33203125,
      "epoch": 0.37968069666182874,
      "grad_norm": 5.739385305144668,
      "kl": 0.4619140625,
      "learning_rate": 7.122085431525784e-07,
      "loss": 0.0185,
      "reward": 0.6171875,
      "reward_std": 0.2212977111339569,
      "rewards/correctness_reward_func": 0.1484375,
      "rewards/strict_format_reward_func": 0.46875,
      "step": 327
    },
    {
      "completion_length": 106.83984375,
      "epoch": 0.38084179970972426,
      "grad_norm": 0.2968677909998634,
      "kl": 0.45458984375,
      "learning_rate": 7.105036872049674e-07,
      "loss": 0.0182,
      "reward": 0.541015625,
      "reward_std": 0.17575840838253498,
      "rewards/correctness_reward_func": 0.078125,
      "rewards/strict_format_reward_func": 0.462890625,
      "step": 328
    },
    {
      "completion_length": 107.59765625,
      "epoch": 0.3820029027576197,
      "grad_norm": 0.3016049016709202,
      "kl": 0.46240234375,
      "learning_rate": 7.087958514650845e-07,
      "loss": 0.0185,
      "reward": 0.5703125,
      "reward_std": 0.1934281848371029,
      "rewards/correctness_reward_func": 0.1171875,
      "rewards/strict_format_reward_func": 0.453125,
      "step": 329
    },
    {
      "completion_length": 86.56640625,
      "epoch": 0.38316400580551524,
      "grad_norm": 0.37897850223634566,
      "kl": 0.43017578125,
      "learning_rate": 7.070850601082577e-07,
      "loss": 0.0172,
      "reward": 0.578125,
      "reward_std": 0.1868242770433426,
      "rewards/correctness_reward_func": 0.1015625,
      "rewards/strict_format_reward_func": 0.4765625,
      "step": 330
    },
    {
      "completion_length": 115.5,
      "epoch": 0.38432510885341076,
      "grad_norm": 0.3956516881732845,
      "kl": 0.4375,
      "learning_rate": 7.053713373516536e-07,
      "loss": 0.0175,
      "reward": 0.572265625,
      "reward_std": 0.2532305307686329,
      "rewards/correctness_reward_func": 0.1171875,
      "rewards/strict_format_reward_func": 0.455078125,
      "step": 331
    },
    {
      "completion_length": 92.05078125,
      "epoch": 0.3854862119013062,
      "grad_norm": 0.41709412462477324,
      "kl": 0.45458984375,
      "learning_rate": 7.036547074539347e-07,
      "loss": 0.0182,
      "reward": 0.5390625,
      "reward_std": 0.15031468868255615,
      "rewards/correctness_reward_func": 0.0703125,
      "rewards/strict_format_reward_func": 0.46875,
      "step": 332
    },
    {
      "completion_length": 99.34375,
      "epoch": 0.38664731494920174,
      "grad_norm": 0.26970793568837187,
      "kl": 0.4599609375,
      "learning_rate": 7.019351947149148e-07,
      "loss": 0.0184,
      "reward": 0.587890625,
      "reward_std": 0.2085794061422348,
      "rewards/correctness_reward_func": 0.125,
      "rewards/strict_format_reward_func": 0.462890625,
      "step": 333
    },
    {
      "completion_length": 91.33984375,
      "epoch": 0.38780841799709725,
      "grad_norm": 0.2837827283437701,
      "kl": 0.4306640625,
      "learning_rate": 7.002128234752166e-07,
      "loss": 0.0172,
      "reward": 0.578125,
      "reward_std": 0.1831898745149374,
      "rewards/correctness_reward_func": 0.1015625,
      "rewards/strict_format_reward_func": 0.4765625,
      "step": 334
    },
    {
      "completion_length": 94.125,
      "epoch": 0.3889695210449927,
      "grad_norm": 0.32889522420728007,
      "kl": 0.482421875,
      "learning_rate": 6.98487618115926e-07,
      "loss": 0.0193,
      "reward": 0.615234375,
      "reward_std": 0.1920539326965809,
      "rewards/correctness_reward_func": 0.140625,
      "rewards/strict_format_reward_func": 0.474609375,
      "step": 335
    },
    {
      "completion_length": 76.578125,
      "epoch": 0.39013062409288823,
      "grad_norm": 0.18090910204917746,
      "kl": 0.48193359375,
      "learning_rate": 6.967596030582477e-07,
      "loss": 0.0193,
      "reward": 0.564453125,
      "reward_std": 0.1259281411767006,
      "rewards/correctness_reward_func": 0.078125,
      "rewards/strict_format_reward_func": 0.486328125,
      "step": 336
    },
    {
      "completion_length": 109.40234375,
      "epoch": 0.39129172714078375,
      "grad_norm": 0.3527865653632661,
      "kl": 0.458984375,
      "learning_rate": 6.950288027631588e-07,
      "loss": 0.0184,
      "reward": 0.5703125,
      "reward_std": 0.16358720511198044,
      "rewards/correctness_reward_func": 0.109375,
      "rewards/strict_format_reward_func": 0.4609375,
      "step": 337
    },
    {
      "completion_length": 94.62890625,
      "epoch": 0.39245283018867927,
      "grad_norm": 0.32886929993323977,
      "kl": 0.50439453125,
      "learning_rate": 6.932952417310633e-07,
      "loss": 0.0202,
      "reward": 0.62109375,
      "reward_std": 0.20156452432274818,
      "rewards/correctness_reward_func": 0.1484375,
      "rewards/strict_format_reward_func": 0.47265625,
      "step": 338
    },
    {
      "completion_length": 62.5546875,
      "epoch": 0.39361393323657473,
      "grad_norm": 0.26246261432123036,
      "kl": 0.568359375,
      "learning_rate": 6.915589445014447e-07,
      "loss": 0.0228,
      "reward": 0.6015625,
      "reward_std": 0.1454593911767006,
      "rewards/correctness_reward_func": 0.125,
      "rewards/strict_format_reward_func": 0.4765625,
      "step": 339
    },
    {
      "completion_length": 71.5390625,
      "epoch": 0.39477503628447025,
      "grad_norm": 0.3297390493081332,
      "kl": 0.53564453125,
      "learning_rate": 6.89819935652519e-07,
      "loss": 0.0214,
      "reward": 0.521484375,
      "reward_std": 0.0485730916261673,
      "rewards/correctness_reward_func": 0.0390625,
      "rewards/strict_format_reward_func": 0.482421875,
      "step": 340
    },
    {
      "completion_length": 67.6875,
      "epoch": 0.39593613933236577,
      "grad_norm": 0.23108857562613203,
      "kl": 0.5341796875,
      "learning_rate": 6.88078239800886e-07,
      "loss": 0.0214,
      "reward": 0.52734375,
      "reward_std": 0.125,
      "rewards/correctness_reward_func": 0.046875,
      "rewards/strict_format_reward_func": 0.48046875,
      "step": 341
    },
    {
      "completion_length": 91.25,
      "epoch": 0.39709724238026123,
      "grad_norm": 0.25101702051238745,
      "kl": 0.48583984375,
      "learning_rate": 6.863338816011826e-07,
      "loss": 0.0194,
      "reward": 0.60546875,
      "reward_std": 0.18848609179258347,
      "rewards/correctness_reward_func": 0.125,
      "rewards/strict_format_reward_func": 0.48046875,
      "step": 342
    },
    {
      "completion_length": 75.06640625,
      "epoch": 0.39825834542815675,
      "grad_norm": 0.34327999543664667,
      "kl": 0.501953125,
      "learning_rate": 6.845868857457316e-07,
      "loss": 0.0201,
      "reward": 0.556640625,
      "reward_std": 0.12956623174250126,
      "rewards/correctness_reward_func": 0.0859375,
      "rewards/strict_format_reward_func": 0.470703125,
      "step": 343
    },
    {
      "completion_length": 88.91796875,
      "epoch": 0.39941944847605226,
      "grad_norm": 0.2879937533350012,
      "kl": 0.556640625,
      "learning_rate": 6.828372769641937e-07,
      "loss": 0.0222,
      "reward": 0.623046875,
      "reward_std": 0.18819626234471798,
      "rewards/correctness_reward_func": 0.1484375,
      "rewards/strict_format_reward_func": 0.474609375,
      "step": 344
    },
    {
      "completion_length": 86.1171875,
      "epoch": 0.4005805515239477,
      "grad_norm": 0.24685342319592915,
      "kl": 0.5478515625,
      "learning_rate": 6.810850800232171e-07,
      "loss": 0.0219,
      "reward": 0.54296875,
      "reward_std": 0.12476811930537224,
      "rewards/correctness_reward_func": 0.078125,
      "rewards/strict_format_reward_func": 0.46484375,
      "step": 345
    },
    {
      "completion_length": 73.68359375,
      "epoch": 0.40174165457184324,
      "grad_norm": 0.3263375483303881,
      "kl": 0.6025390625,
      "learning_rate": 6.793303197260864e-07,
      "loss": 0.0241,
      "reward": 0.513671875,
      "reward_std": 0.07893833611160517,
      "rewards/correctness_reward_func": 0.03125,
      "rewards/strict_format_reward_func": 0.482421875,
      "step": 346
    },
    {
      "completion_length": 83.9375,
      "epoch": 0.40290275761973876,
      "grad_norm": 0.25136463736995274,
      "kl": 0.54296875,
      "learning_rate": 6.775730209123722e-07,
      "loss": 0.0218,
      "reward": 0.6796875,
      "reward_std": 0.2113918662071228,
      "rewards/correctness_reward_func": 0.1953125,
      "rewards/strict_format_reward_func": 0.484375,
      "step": 347
    },
    {
      "completion_length": 81.56640625,
      "epoch": 0.4040638606676343,
      "grad_norm": 0.2501886439839053,
      "kl": 0.5732421875,
      "learning_rate": 6.75813208457579e-07,
      "loss": 0.0229,
      "reward": 0.552734375,
      "reward_std": 0.1773136854171753,
      "rewards/correctness_reward_func": 0.078125,
      "rewards/strict_format_reward_func": 0.474609375,
      "step": 348
    },
    {
      "completion_length": 66.9765625,
      "epoch": 0.40522496371552974,
      "grad_norm": 0.5109927263281991,
      "kl": 0.6396484375,
      "learning_rate": 6.74050907272793e-07,
      "loss": 0.0256,
      "reward": 0.58203125,
      "reward_std": 0.1532718911767006,
      "rewards/correctness_reward_func": 0.09375,
      "rewards/strict_format_reward_func": 0.48828125,
      "step": 349
    },
    {
      "completion_length": 69.9609375,
      "epoch": 0.40638606676342526,
      "grad_norm": 0.22913115713166626,
      "kl": 0.623046875,
      "learning_rate": 6.722861423043305e-07,
      "loss": 0.0249,
      "reward": 0.54296875,
      "reward_std": 0.12951054889708757,
      "rewards/correctness_reward_func": 0.0625,
      "rewards/strict_format_reward_func": 0.48046875,
      "step": 350
    },
    {
      "completion_length": 57.07421875,
      "epoch": 0.4075471698113208,
      "grad_norm": 0.43448597905440733,
      "kl": 0.6708984375,
      "learning_rate": 6.70518938533383e-07,
      "loss": 0.0268,
      "reward": 0.765625,
      "reward_std": 0.21839812025427818,
      "rewards/correctness_reward_func": 0.28125,
      "rewards/strict_format_reward_func": 0.484375,
      "step": 351
    },
    {
      "completion_length": 71.8984375,
      "epoch": 0.40870827285921624,
      "grad_norm": 0.5438789424715308,
      "kl": 0.6162109375,
      "learning_rate": 6.687493209756652e-07,
      "loss": 0.0247,
      "reward": 0.56640625,
      "reward_std": 0.2113555707037449,
      "rewards/correctness_reward_func": 0.1015625,
      "rewards/strict_format_reward_func": 0.46484375,
      "step": 352
    },
    {
      "completion_length": 78.9453125,
      "epoch": 0.40986937590711175,
      "grad_norm": 0.3643681813722083,
      "kl": 0.54638671875,
      "learning_rate": 6.669773146810598e-07,
      "loss": 0.0219,
      "reward": 0.595703125,
      "reward_std": 0.20702560991048813,
      "rewards/correctness_reward_func": 0.1171875,
      "rewards/strict_format_reward_func": 0.478515625,
      "step": 353
    },
    {
      "completion_length": 74.796875,
      "epoch": 0.4110304789550073,
      "grad_norm": 0.24296888261067365,
      "kl": 0.58984375,
      "learning_rate": 6.652029447332641e-07,
      "loss": 0.0236,
      "reward": 0.619140625,
      "reward_std": 0.1514589935541153,
      "rewards/correctness_reward_func": 0.1484375,
      "rewards/strict_format_reward_func": 0.470703125,
      "step": 354
    },
    {
      "completion_length": 76.3203125,
      "epoch": 0.41219158200290273,
      "grad_norm": 0.3098307099636997,
      "kl": 0.6201171875,
      "learning_rate": 6.634262362494332e-07,
      "loss": 0.0248,
      "reward": 0.634765625,
      "reward_std": 0.1970105916261673,
      "rewards/correctness_reward_func": 0.15625,
      "rewards/strict_format_reward_func": 0.478515625,
      "step": 355
    },
    {
      "completion_length": 109.6796875,
      "epoch": 0.41335268505079825,
      "grad_norm": 0.22986280827840255,
      "kl": 0.53564453125,
      "learning_rate": 6.61647214379826e-07,
      "loss": 0.0214,
      "reward": 0.548828125,
      "reward_std": 0.1738184168934822,
      "rewards/correctness_reward_func": 0.078125,
      "rewards/strict_format_reward_func": 0.470703125,
      "step": 356
    },
    {
      "completion_length": 101.62890625,
      "epoch": 0.41451378809869377,
      "grad_norm": 0.3167144536185835,
      "kl": 0.564453125,
      "learning_rate": 6.598659043074486e-07,
      "loss": 0.0225,
      "reward": 0.546875,
      "reward_std": 0.17615367099642754,
      "rewards/correctness_reward_func": 0.078125,
      "rewards/strict_format_reward_func": 0.46875,
      "step": 357
    },
    {
      "completion_length": 76.7734375,
      "epoch": 0.4156748911465893,
      "grad_norm": 0.24303041290839197,
      "kl": 0.54638671875,
      "learning_rate": 6.580823312476975e-07,
      "loss": 0.0218,
      "reward": 0.521484375,
      "reward_std": 0.10546875,
      "rewards/correctness_reward_func": 0.0390625,
      "rewards/strict_format_reward_func": 0.482421875,
      "step": 358
    },
    {
      "completion_length": 125.3671875,
      "epoch": 0.41683599419448475,
      "grad_norm": 0.7081131603026585,
      "kl": 0.52880859375,
      "learning_rate": 6.562965204480037e-07,
      "loss": 0.0211,
      "reward": 0.6171875,
      "reward_std": 0.2204914726316929,
      "rewards/correctness_reward_func": 0.1484375,
      "rewards/strict_format_reward_func": 0.46875,
      "step": 359
    },
    {
      "completion_length": 82.41796875,
      "epoch": 0.41799709724238027,
      "grad_norm": 0.4357938018159004,
      "kl": 0.54443359375,
      "learning_rate": 6.545084971874736e-07,
      "loss": 0.0218,
      "reward": 0.646484375,
      "reward_std": 0.19245435670018196,
      "rewards/correctness_reward_func": 0.1796875,
      "rewards/strict_format_reward_func": 0.466796875,
      "step": 360
    },
    {
      "completion_length": 105.57421875,
      "epoch": 0.4191582002902758,
      "grad_norm": 0.4400020096023354,
      "kl": 0.45703125,
      "learning_rate": 6.527182867765332e-07,
      "loss": 0.0183,
      "reward": 0.62890625,
      "reward_std": 0.2650640867650509,
      "rewards/correctness_reward_func": 0.15625,
      "rewards/strict_format_reward_func": 0.47265625,
      "step": 361
    },
    {
      "completion_length": 101.62109375,
      "epoch": 0.42031930333817125,
      "grad_norm": 0.4513218352418108,
      "kl": 0.5908203125,
      "learning_rate": 6.50925914556568e-07,
      "loss": 0.0236,
      "reward": 0.591796875,
      "reward_std": 0.20470601320266724,
      "rewards/correctness_reward_func": 0.1171875,
      "rewards/strict_format_reward_func": 0.474609375,
      "step": 362
    },
    {
      "completion_length": 114.00390625,
      "epoch": 0.42148040638606676,
      "grad_norm": 0.2773760092777871,
      "kl": 0.55859375,
      "learning_rate": 6.491314058995652e-07,
      "loss": 0.0224,
      "reward": 0.61328125,
      "reward_std": 0.15206329338252544,
      "rewards/correctness_reward_func": 0.140625,
      "rewards/strict_format_reward_func": 0.47265625,
      "step": 363
    },
    {
      "completion_length": 142.7265625,
      "epoch": 0.4226415094339623,
      "grad_norm": 0.27616972801783,
      "kl": 0.50244140625,
      "learning_rate": 6.473347862077551e-07,
      "loss": 0.0201,
      "reward": 0.54296875,
      "reward_std": 0.1957305707037449,
      "rewards/correctness_reward_func": 0.0859375,
      "rewards/strict_format_reward_func": 0.45703125,
      "step": 364
    },
    {
      "completion_length": 94.98046875,
      "epoch": 0.42380261248185774,
      "grad_norm": 0.18555372496203534,
      "kl": 0.5654296875,
      "learning_rate": 6.455360809132497e-07,
      "loss": 0.0226,
      "reward": 0.576171875,
      "reward_std": 0.06310429889708757,
      "rewards/correctness_reward_func": 0.1015625,
      "rewards/strict_format_reward_func": 0.474609375,
      "step": 365
    },
    {
      "completion_length": 87.3515625,
      "epoch": 0.42496371552975326,
      "grad_norm": 0.4239263725202524,
      "kl": 0.57421875,
      "learning_rate": 6.437353154776848e-07,
      "loss": 0.023,
      "reward": 0.564453125,
      "reward_std": 0.14582546427845955,
      "rewards/correctness_reward_func": 0.1015625,
      "rewards/strict_format_reward_func": 0.462890625,
      "step": 366
    },
    {
      "completion_length": 94.11328125,
      "epoch": 0.4261248185776488,
      "grad_norm": 0.5104772858886346,
      "kl": 0.5341796875,
      "learning_rate": 6.41932515391858e-07,
      "loss": 0.0214,
      "reward": 0.583984375,
      "reward_std": 0.21658522635698318,
      "rewards/correctness_reward_func": 0.109375,
      "rewards/strict_format_reward_func": 0.474609375,
      "step": 367
    },
    {
      "completion_length": 71.8828125,
      "epoch": 0.42728592162554424,
      "grad_norm": 0.37470581187227664,
      "kl": 0.638671875,
      "learning_rate": 6.401277061753688e-07,
      "loss": 0.0255,
      "reward": 0.66796875,
      "reward_std": 0.2147723287343979,
      "rewards/correctness_reward_func": 0.1953125,
      "rewards/strict_format_reward_func": 0.47265625,
      "step": 368
    },
    {
      "completion_length": 98.078125,
      "epoch": 0.42844702467343976,
      "grad_norm": 0.2383430376592154,
      "kl": 0.5888671875,
      "learning_rate": 6.383209133762568e-07,
      "loss": 0.0236,
      "reward": 0.517578125,
      "reward_std": 0.11481368914246559,
      "rewards/correctness_reward_func": 0.046875,
      "rewards/strict_format_reward_func": 0.470703125,
      "step": 369
    },
    {
      "completion_length": 78.734375,
      "epoch": 0.4296081277213353,
      "grad_norm": 0.2147373893634736,
      "kl": 0.6044921875,
      "learning_rate": 6.365121625706404e-07,
      "loss": 0.0242,
      "reward": 0.580078125,
      "reward_std": 0.1355258673429489,
      "rewards/correctness_reward_func": 0.1015625,
      "rewards/strict_format_reward_func": 0.478515625,
      "step": 370
    },
    {
      "completion_length": 126.3359375,
      "epoch": 0.4307692307692308,
      "grad_norm": 0.29213327316917803,
      "kl": 0.57421875,
      "learning_rate": 6.347014793623548e-07,
      "loss": 0.023,
      "reward": 0.625,
      "reward_std": 0.1084902435541153,
      "rewards/correctness_reward_func": 0.1484375,
      "rewards/strict_format_reward_func": 0.4765625,
      "step": 371
    },
    {
      "completion_length": 82.0078125,
      "epoch": 0.43193033381712626,
      "grad_norm": 0.2485460820708867,
      "kl": 0.5703125,
      "learning_rate": 6.328888893825887e-07,
      "loss": 0.0228,
      "reward": 0.64453125,
      "reward_std": 0.1776098608970642,
      "rewards/correctness_reward_func": 0.1640625,
      "rewards/strict_format_reward_func": 0.48046875,
      "step": 372
    },
    {
      "completion_length": 59.90625,
      "epoch": 0.4330914368650218,
      "grad_norm": 0.2750923880024312,
      "kl": 0.58984375,
      "learning_rate": 6.31074418289523e-07,
      "loss": 0.0236,
      "reward": 0.607421875,
      "reward_std": 0.17719027400016785,
      "rewards/correctness_reward_func": 0.1171875,
      "rewards/strict_format_reward_func": 0.490234375,
      "step": 373
    },
    {
      "completion_length": 110.38671875,
      "epoch": 0.4342525399129173,
      "grad_norm": 0.25779538772802885,
      "kl": 0.5966796875,
      "learning_rate": 6.292580917679664e-07,
      "loss": 0.0239,
      "reward": 0.583984375,
      "reward_std": 0.1581571288406849,
      "rewards/correctness_reward_func": 0.1015625,
      "rewards/strict_format_reward_func": 0.482421875,
      "step": 374
    },
    {
      "completion_length": 96.2578125,
      "epoch": 0.43541364296081275,
      "grad_norm": 0.5070325029886389,
      "kl": 0.6025390625,
      "learning_rate": 6.274399355289923e-07,
      "loss": 0.0241,
      "reward": 0.6015625,
      "reward_std": 0.18991719186306,
      "rewards/correctness_reward_func": 0.125,
      "rewards/strict_format_reward_func": 0.4765625,
      "step": 375
    },
    {
      "completion_length": 111.56640625,
      "epoch": 0.43657474600870827,
      "grad_norm": 0.31442374214756924,
      "kl": 0.55810546875,
      "learning_rate": 6.256199753095745e-07,
      "loss": 0.0223,
      "reward": 0.5703125,
      "reward_std": 0.1655949391424656,
      "rewards/correctness_reward_func": 0.1015625,
      "rewards/strict_format_reward_func": 0.46875,
      "step": 376
    },
    {
      "completion_length": 93.6640625,
      "epoch": 0.4377358490566038,
      "grad_norm": 6.9371543727247005,
      "kl": 0.609375,
      "learning_rate": 6.237982368722231e-07,
      "loss": 0.0244,
      "reward": 0.671875,
      "reward_std": 0.3408661223948002,
      "rewards/correctness_reward_func": 0.203125,
      "rewards/strict_format_reward_func": 0.46875,
      "step": 377
    },
    {
      "completion_length": 106.3046875,
      "epoch": 0.43889695210449925,
      "grad_norm": 0.48230199921643463,
      "kl": 0.5869140625,
      "learning_rate": 6.219747460046202e-07,
      "loss": 0.0235,
      "reward": 0.666015625,
      "reward_std": 0.17466461658477783,
      "rewards/correctness_reward_func": 0.1953125,
      "rewards/strict_format_reward_func": 0.470703125,
      "step": 378
    },
    {
      "completion_length": 99.83984375,
      "epoch": 0.44005805515239477,
      "grad_norm": 0.25761065472308364,
      "kl": 0.54541015625,
      "learning_rate": 6.201495285192542e-07,
      "loss": 0.0218,
      "reward": 0.568359375,
      "reward_std": 0.15420002862811089,
      "rewards/correctness_reward_func": 0.0859375,
      "rewards/strict_format_reward_func": 0.482421875,
      "step": 379
    },
    {
      "completion_length": 87.4921875,
      "epoch": 0.4412191582002903,
      "grad_norm": 1.029791050074705,
      "kl": 0.5869140625,
      "learning_rate": 6.183226102530546e-07,
      "loss": 0.0235,
      "reward": 0.587890625,
      "reward_std": 0.2398294061422348,
      "rewards/correctness_reward_func": 0.1171875,
      "rewards/strict_format_reward_func": 0.470703125,
      "step": 380
    },
    {
      "completion_length": 83.20703125,
      "epoch": 0.4423802612481858,
      "grad_norm": 0.2982447065274822,
      "kl": 0.6044921875,
      "learning_rate": 6.164940170670265e-07,
      "loss": 0.0242,
      "reward": 0.671875,
      "reward_std": 0.2199743092060089,
      "rewards/correctness_reward_func": 0.1875,
      "rewards/strict_format_reward_func": 0.484375,
      "step": 381
    },
    {
      "completion_length": 86.09765625,
      "epoch": 0.44354136429608126,
      "grad_norm": 0.9321126474041298,
      "kl": 0.6240234375,
      "learning_rate": 6.146637748458848e-07,
      "loss": 0.025,
      "reward": 0.61328125,
      "reward_std": 0.18747715651988983,
      "rewards/correctness_reward_func": 0.1328125,
      "rewards/strict_format_reward_func": 0.48046875,
      "step": 382
    },
    {
      "completion_length": 134.3671875,
      "epoch": 0.4447024673439768,
      "grad_norm": 0.45890211100180406,
      "kl": 0.5546875,
      "learning_rate": 6.128319094976868e-07,
      "loss": 0.0222,
      "reward": 0.548828125,
      "reward_std": 0.15234375,
      "rewards/correctness_reward_func": 0.078125,
      "rewards/strict_format_reward_func": 0.470703125,
      "step": 383
    },
    {
      "completion_length": 81.24609375,
      "epoch": 0.4458635703918723,
      "grad_norm": 2.248668131010746,
      "kl": 0.62890625,
      "learning_rate": 6.10998446953466e-07,
      "loss": 0.0252,
      "reward": 0.6171875,
      "reward_std": 0.21718952059745789,
      "rewards/correctness_reward_func": 0.140625,
      "rewards/strict_format_reward_func": 0.4765625,
      "step": 384
    },
    {
      "completion_length": 146.41796875,
      "epoch": 0.44702467343976776,
      "grad_norm": 0.2598233426911348,
      "kl": 0.6171875,
      "learning_rate": 6.091634131668651e-07,
      "loss": 0.0247,
      "reward": 0.615234375,
      "reward_std": 0.19898167252540588,
      "rewards/correctness_reward_func": 0.1484375,
      "rewards/strict_format_reward_func": 0.466796875,
      "step": 385
    },
    {
      "completion_length": 120.53125,
      "epoch": 0.4481857764876633,
      "grad_norm": 0.5394807067049577,
      "kl": 0.58203125,
      "learning_rate": 6.073268341137693e-07,
      "loss": 0.0233,
      "reward": 0.640625,
      "reward_std": 0.18835671991109848,
      "rewards/correctness_reward_func": 0.1640625,
      "rewards/strict_format_reward_func": 0.4765625,
      "step": 386
    },
    {
      "completion_length": 113.140625,
      "epoch": 0.4493468795355588,
      "grad_norm": 0.24295613961307327,
      "kl": 0.552734375,
      "learning_rate": 6.05488735791937e-07,
      "loss": 0.0221,
      "reward": 0.572265625,
      "reward_std": 0.21658522635698318,
      "rewards/correctness_reward_func": 0.1015625,
      "rewards/strict_format_reward_func": 0.470703125,
      "step": 387
    },
    {
      "completion_length": 120.71484375,
      "epoch": 0.45050798258345426,
      "grad_norm": 0.2607770576009339,
      "kl": 0.48095703125,
      "learning_rate": 6.036491442206329e-07,
      "loss": 0.0192,
      "reward": 0.587890625,
      "reward_std": 0.20744071155786514,
      "rewards/correctness_reward_func": 0.125,
      "rewards/strict_format_reward_func": 0.462890625,
      "step": 388
    },
    {
      "completion_length": 99.9453125,
      "epoch": 0.4516690856313498,
      "grad_norm": 16.372003186126687,
      "kl": 0.56005859375,
      "learning_rate": 6.018080854402599e-07,
      "loss": 0.0224,
      "reward": 0.669921875,
      "reward_std": 0.22427431121468544,
      "rewards/correctness_reward_func": 0.1953125,
      "rewards/strict_format_reward_func": 0.474609375,
      "step": 389
    },
    {
      "completion_length": 194.45703125,
      "epoch": 0.4528301886792453,
      "grad_norm": 0.3000541660710553,
      "kl": 0.4609375,
      "learning_rate": 5.999655855119892e-07,
      "loss": 0.0184,
      "reward": 0.634765625,
      "reward_std": 0.23597173392772675,
      "rewards/correctness_reward_func": 0.1875,
      "rewards/strict_format_reward_func": 0.447265625,
      "step": 390
    },
    {
      "completion_length": 184.12109375,
      "epoch": 0.4539912917271408,
      "grad_norm": 0.3095778168804227,
      "kl": 0.51953125,
      "learning_rate": 5.981216705173929e-07,
      "loss": 0.0208,
      "reward": 0.62890625,
      "reward_std": 0.2303973250091076,
      "rewards/correctness_reward_func": 0.1796875,
      "rewards/strict_format_reward_func": 0.44921875,
      "step": 391
    },
    {
      "completion_length": 119.00390625,
      "epoch": 0.4551523947750363,
      "grad_norm": 0.2428265662631221,
      "kl": 0.6015625,
      "learning_rate": 5.96276366558074e-07,
      "loss": 0.0241,
      "reward": 0.6171875,
      "reward_std": 0.22125915624201298,
      "rewards/correctness_reward_func": 0.140625,
      "rewards/strict_format_reward_func": 0.4765625,
      "step": 392
    },
    {
      "completion_length": 127.8125,
      "epoch": 0.4563134978229318,
      "grad_norm": 1.0186163125450653,
      "kl": 0.46484375,
      "learning_rate": 5.944296997552967e-07,
      "loss": 0.0186,
      "reward": 0.708984375,
      "reward_std": 0.2689474932849407,
      "rewards/correctness_reward_func": 0.2421875,
      "rewards/strict_format_reward_func": 0.466796875,
      "step": 393
    },
    {
      "completion_length": 126.64453125,
      "epoch": 0.4574746008708273,
      "grad_norm": 0.2738447873229587,
      "kl": 0.47021484375,
      "learning_rate": 5.925816962496174e-07,
      "loss": 0.0188,
      "reward": 0.666015625,
      "reward_std": 0.2515758164227009,
      "rewards/correctness_reward_func": 0.1953125,
      "rewards/strict_format_reward_func": 0.470703125,
      "step": 394
    },
    {
      "completion_length": 120.52734375,
      "epoch": 0.45863570391872277,
      "grad_norm": 0.2081853966183399,
      "kl": 0.52197265625,
      "learning_rate": 5.907323822005139e-07,
      "loss": 0.0209,
      "reward": 0.6640625,
      "reward_std": 0.16162246465682983,
      "rewards/correctness_reward_func": 0.1875,
      "rewards/strict_format_reward_func": 0.4765625,
      "step": 395
    },
    {
      "completion_length": 126.0625,
      "epoch": 0.4597968069666183,
      "grad_norm": 0.41377371550793696,
      "kl": 0.5361328125,
      "learning_rate": 5.888817837860156e-07,
      "loss": 0.0214,
      "reward": 0.560546875,
      "reward_std": 0.13253204245120287,
      "rewards/correctness_reward_func": 0.1015625,
      "rewards/strict_format_reward_func": 0.458984375,
      "step": 396
    },
    {
      "completion_length": 120.0703125,
      "epoch": 0.4609579100145138,
      "grad_norm": 0.2171941952922665,
      "kl": 0.52978515625,
      "learning_rate": 5.870299272023329e-07,
      "loss": 0.0212,
      "reward": 0.5234375,
      "reward_std": 0.1531570851802826,
      "rewards/correctness_reward_func": 0.0546875,
      "rewards/strict_format_reward_func": 0.46875,
      "step": 397
    },
    {
      "completion_length": 141.9453125,
      "epoch": 0.46211901306240927,
      "grad_norm": 3.0625655639219964,
      "kl": 0.6064453125,
      "learning_rate": 5.851768386634862e-07,
      "loss": 0.0242,
      "reward": 0.5390625,
      "reward_std": 0.19876068457961082,
      "rewards/correctness_reward_func": 0.09375,
      "rewards/strict_format_reward_func": 0.4453125,
      "step": 398
    },
    {
      "completion_length": 90.546875,
      "epoch": 0.4632801161103048,
      "grad_norm": 1.1905377467292104,
      "kl": 0.6103515625,
      "learning_rate": 5.833225444009347e-07,
      "loss": 0.0244,
      "reward": 0.5703125,
      "reward_std": 0.1565895602107048,
      "rewards/correctness_reward_func": 0.1015625,
      "rewards/strict_format_reward_func": 0.46875,
      "step": 399
    },
    {
      "completion_length": 123.75,
      "epoch": 0.4644412191582003,
      "grad_norm": 0.23261666216565308,
      "kl": 0.5498046875,
      "learning_rate": 5.814670706632053e-07,
      "loss": 0.022,
      "reward": 0.533203125,
      "reward_std": 0.11901611275970936,
      "rewards/correctness_reward_func": 0.0546875,
      "rewards/strict_format_reward_func": 0.478515625,
      "step": 400
    },
    {
      "completion_length": 83.55078125,
      "epoch": 0.46560232220609576,
      "grad_norm": 0.3251282808642471,
      "kl": 0.5439453125,
      "learning_rate": 5.796104437155212e-07,
      "loss": 0.0218,
      "reward": 0.52734375,
      "reward_std": 0.1310429871082306,
      "rewards/correctness_reward_func": 0.0546875,
      "rewards/strict_format_reward_func": 0.47265625,
      "step": 401
    },
    {
      "completion_length": 105.5,
      "epoch": 0.4667634252539913,
      "grad_norm": 0.3433865139123553,
      "kl": 0.6171875,
      "learning_rate": 5.777526898394297e-07,
      "loss": 0.0247,
      "reward": 0.615234375,
      "reward_std": 0.13207055255770683,
      "rewards/correctness_reward_func": 0.140625,
      "rewards/strict_format_reward_func": 0.474609375,
      "step": 402
    },
    {
      "completion_length": 99.375,
      "epoch": 0.4679245283018868,
      "grad_norm": 0.2867961718173002,
      "kl": 0.650390625,
      "learning_rate": 5.758938353324307e-07,
      "loss": 0.026,
      "reward": 0.66015625,
      "reward_std": 0.25097334384918213,
      "rewards/correctness_reward_func": 0.1953125,
      "rewards/strict_format_reward_func": 0.46484375,
      "step": 403
    },
    {
      "completion_length": 110.90234375,
      "epoch": 0.4690856313497823,
      "grad_norm": 0.25941228950541284,
      "kl": 0.5791015625,
      "learning_rate": 5.740339065076035e-07,
      "loss": 0.0231,
      "reward": 0.607421875,
      "reward_std": 0.22418304905295372,
      "rewards/correctness_reward_func": 0.140625,
      "rewards/strict_format_reward_func": 0.466796875,
      "step": 404
    },
    {
      "completion_length": 91.671875,
      "epoch": 0.4702467343976778,
      "grad_norm": 0.17119294583261166,
      "kl": 0.5859375,
      "learning_rate": 5.721729296932358e-07,
      "loss": 0.0235,
      "reward": 0.58984375,
      "reward_std": 0.13499781861901283,
      "rewards/correctness_reward_func": 0.1171875,
      "rewards/strict_format_reward_func": 0.47265625,
      "step": 405
    },
    {
      "completion_length": 86.109375,
      "epoch": 0.4714078374455733,
      "grad_norm": 2.3791162162843316,
      "kl": 0.591796875,
      "learning_rate": 5.703109312324493e-07,
      "loss": 0.0237,
      "reward": 0.611328125,
      "reward_std": 0.2250734455883503,
      "rewards/correctness_reward_func": 0.140625,
      "rewards/strict_format_reward_func": 0.470703125,
      "step": 406
    },
    {
      "completion_length": 75.9375,
      "epoch": 0.4725689404934688,
      "grad_norm": 0.30293428290117747,
      "kl": 0.62353515625,
      "learning_rate": 5.684479374828279e-07,
      "loss": 0.0249,
      "reward": 0.58984375,
      "reward_std": 0.1640625,
      "rewards/correctness_reward_func": 0.1015625,
      "rewards/strict_format_reward_func": 0.48828125,
      "step": 407
    },
    {
      "completion_length": 80.2578125,
      "epoch": 0.4737300435413643,
      "grad_norm": 1.7784821777234308,
      "kl": 0.57421875,
      "learning_rate": 5.665839748160449e-07,
      "loss": 0.023,
      "reward": 0.56640625,
      "reward_std": 0.15922246873378754,
      "rewards/correctness_reward_func": 0.09375,
      "rewards/strict_format_reward_func": 0.47265625,
      "step": 408
    },
    {
      "completion_length": 71.09765625,
      "epoch": 0.4748911465892598,
      "grad_norm": 0.39986755868079144,
      "kl": 0.646484375,
      "learning_rate": 5.647190696174885e-07,
      "loss": 0.0258,
      "reward": 0.65625,
      "reward_std": 0.2336001843214035,
      "rewards/correctness_reward_func": 0.1796875,
      "rewards/strict_format_reward_func": 0.4765625,
      "step": 409
    },
    {
      "completion_length": 108.62890625,
      "epoch": 0.4760522496371553,
      "grad_norm": 0.27988176271183773,
      "kl": 0.5859375,
      "learning_rate": 5.628532482858894e-07,
      "loss": 0.0235,
      "reward": 0.666015625,
      "reward_std": 0.2695032060146332,
      "rewards/correctness_reward_func": 0.1953125,
      "rewards/strict_format_reward_func": 0.470703125,
      "step": 410
    },
    {
      "completion_length": 90.609375,
      "epoch": 0.4772133526850508,
      "grad_norm": 0.33190523566822816,
      "kl": 0.5986328125,
      "learning_rate": 5.60986537232946e-07,
      "loss": 0.0239,
      "reward": 0.611328125,
      "reward_std": 0.11901611089706421,
      "rewards/correctness_reward_func": 0.140625,
      "rewards/strict_format_reward_func": 0.470703125,
      "step": 411
    },
    {
      "completion_length": 98.34765625,
      "epoch": 0.4783744557329463,
      "grad_norm": 0.25096513394134173,
      "kl": 0.6357421875,
      "learning_rate": 5.591189628829518e-07,
      "loss": 0.0255,
      "reward": 0.65234375,
      "reward_std": 0.1687820851802826,
      "rewards/correctness_reward_func": 0.1796875,
      "rewards/strict_format_reward_func": 0.47265625,
      "step": 412
    },
    {
      "completion_length": 90.95703125,
      "epoch": 0.4795355587808418,
      "grad_norm": 0.2950630948270237,
      "kl": 0.59228515625,
      "learning_rate": 5.572505516724206e-07,
      "loss": 0.0237,
      "reward": 0.591796875,
      "reward_std": 0.17752272635698318,
      "rewards/correctness_reward_func": 0.1171875,
      "rewards/strict_format_reward_func": 0.474609375,
      "step": 413
    },
    {
      "completion_length": 117.80859375,
      "epoch": 0.4806966618287373,
      "grad_norm": 0.22283075045582074,
      "kl": 0.6103515625,
      "learning_rate": 5.553813300497121e-07,
      "loss": 0.0244,
      "reward": 0.576171875,
      "reward_std": 0.16830831486731768,
      "rewards/correctness_reward_func": 0.109375,
      "rewards/strict_format_reward_func": 0.466796875,
      "step": 414
    },
    {
      "completion_length": 82.5,
      "epoch": 0.4818577648766328,
      "grad_norm": 2.708288870234853,
      "kl": 0.6279296875,
      "learning_rate": 5.535113244746584e-07,
      "loss": 0.0252,
      "reward": 0.650390625,
      "reward_std": 0.21767901629209518,
      "rewards/correctness_reward_func": 0.171875,
      "rewards/strict_format_reward_func": 0.478515625,
      "step": 415
    },
    {
      "completion_length": 125.0390625,
      "epoch": 0.4830188679245283,
      "grad_norm": 0.3717685493286654,
      "kl": 0.603515625,
      "learning_rate": 5.516405614181882e-07,
      "loss": 0.0241,
      "reward": 0.587890625,
      "reward_std": 0.1971411146223545,
      "rewards/correctness_reward_func": 0.125,
      "rewards/strict_format_reward_func": 0.462890625,
      "step": 416
    },
    {
      "completion_length": 100.421875,
      "epoch": 0.4841799709724238,
      "grad_norm": 0.3368441987227057,
      "kl": 0.63671875,
      "learning_rate": 5.497690673619532e-07,
      "loss": 0.0255,
      "reward": 0.55078125,
      "reward_std": 0.13785592839121819,
      "rewards/correctness_reward_func": 0.0703125,
      "rewards/strict_format_reward_func": 0.48046875,
      "step": 417
    },
    {
      "completion_length": 83.203125,
      "epoch": 0.4853410740203193,
      "grad_norm": 1.800297924833497,
      "kl": 0.78125,
      "learning_rate": 5.478968687979526e-07,
      "loss": 0.0313,
      "reward": 0.625,
      "reward_std": 0.19386683404445648,
      "rewards/correctness_reward_func": 0.140625,
      "rewards/strict_format_reward_func": 0.484375,
      "step": 418
    },
    {
      "completion_length": 95.33984375,
      "epoch": 0.4865021770682148,
      "grad_norm": 0.3208741021756397,
      "kl": 0.53173828125,
      "learning_rate": 5.460239922281585e-07,
      "loss": 0.0213,
      "reward": 0.5390625,
      "reward_std": 0.12601527571678162,
      "rewards/correctness_reward_func": 0.0625,
      "rewards/strict_format_reward_func": 0.4765625,
      "step": 419
    },
    {
      "completion_length": 106.984375,
      "epoch": 0.4876632801161103,
      "grad_norm": 2.923421786623883,
      "kl": 0.6376953125,
      "learning_rate": 5.441504641641403e-07,
      "loss": 0.0255,
      "reward": 0.55859375,
      "reward_std": 0.1687820851802826,
      "rewards/correctness_reward_func": 0.09375,
      "rewards/strict_format_reward_func": 0.46484375,
      "step": 420
    },
    {
      "completion_length": 89.94140625,
      "epoch": 0.4888243831640058,
      "grad_norm": 0.37932984060353353,
      "kl": 0.5498046875,
      "learning_rate": 5.422763111266895e-07,
      "loss": 0.022,
      "reward": 0.595703125,
      "reward_std": 0.1780836395919323,
      "rewards/correctness_reward_func": 0.1171875,
      "rewards/strict_format_reward_func": 0.478515625,
      "step": 421
    },
    {
      "completion_length": 139.48046875,
      "epoch": 0.4899854862119013,
      "grad_norm": 0.31586562597880474,
      "kl": 0.5703125,
      "learning_rate": 5.40401559645445e-07,
      "loss": 0.0228,
      "reward": 0.5703125,
      "reward_std": 0.22344674542546272,
      "rewards/correctness_reward_func": 0.1171875,
      "rewards/strict_format_reward_func": 0.453125,
      "step": 422
    },
    {
      "completion_length": 103.46484375,
      "epoch": 0.4911465892597968,
      "grad_norm": 2.0019542893541753,
      "kl": 0.748046875,
      "learning_rate": 5.385262362585165e-07,
      "loss": 0.0299,
      "reward": 0.51171875,
      "reward_std": 0.1497403308749199,
      "rewards/correctness_reward_func": 0.046875,
      "rewards/strict_format_reward_func": 0.46484375,
      "step": 423
    },
    {
      "completion_length": 104.76171875,
      "epoch": 0.49230769230769234,
      "grad_norm": 0.25068122195182274,
      "kl": 0.6220703125,
      "learning_rate": 5.366503675121095e-07,
      "loss": 0.0249,
      "reward": 0.517578125,
      "reward_std": 0.117791797965765,
      "rewards/correctness_reward_func": 0.046875,
      "rewards/strict_format_reward_func": 0.470703125,
      "step": 424
    },
    {
      "completion_length": 82.609375,
      "epoch": 0.4934687953555878,
      "grad_norm": 0.18239908683354564,
      "kl": 0.6357421875,
      "learning_rate": 5.347739799601493e-07,
      "loss": 0.0254,
      "reward": 0.60546875,
      "reward_std": 0.1652868092060089,
      "rewards/correctness_reward_func": 0.125,
      "rewards/strict_format_reward_func": 0.48046875,
      "step": 425
    },
    {
      "completion_length": 101.734375,
      "epoch": 0.4946298984034833,
      "grad_norm": 0.36802962206954004,
      "kl": 0.638671875,
      "learning_rate": 5.328971001639053e-07,
      "loss": 0.0256,
      "reward": 0.642578125,
      "reward_std": 0.308487206697464,
      "rewards/correctness_reward_func": 0.1796875,
      "rewards/strict_format_reward_func": 0.462890625,
      "step": 426
    },
    {
      "completion_length": 97.42578125,
      "epoch": 0.49579100145137883,
      "grad_norm": 0.2713643804207668,
      "kl": 0.609375,
      "learning_rate": 5.310197546916148e-07,
      "loss": 0.0244,
      "reward": 0.59765625,
      "reward_std": 0.1586671955883503,
      "rewards/correctness_reward_func": 0.1171875,
      "rewards/strict_format_reward_func": 0.48046875,
      "step": 427
    },
    {
      "completion_length": 81.59375,
      "epoch": 0.4969521044992743,
      "grad_norm": 0.1763118578972696,
      "kl": 0.5771484375,
      "learning_rate": 5.291419701181068e-07,
      "loss": 0.0231,
      "reward": 0.49609375,
      "reward_std": 0.0703125,
      "rewards/correctness_reward_func": 0.015625,
      "rewards/strict_format_reward_func": 0.48046875,
      "step": 428
    },
    {
      "completion_length": 100.453125,
      "epoch": 0.4981132075471698,
      "grad_norm": 0.24197504544289827,
      "kl": 0.6044921875,
      "learning_rate": 5.272637730244265e-07,
      "loss": 0.0242,
      "reward": 0.564453125,
      "reward_std": 0.2028602659702301,
      "rewards/correctness_reward_func": 0.09375,
      "rewards/strict_format_reward_func": 0.470703125,
      "step": 429
    },
    {
      "completion_length": 125.37109375,
      "epoch": 0.49927431059506533,
      "grad_norm": 0.3264991170936551,
      "kl": 0.6611328125,
      "learning_rate": 5.25385189997458e-07,
      "loss": 0.0264,
      "reward": 0.6171875,
      "reward_std": 0.22718099877238274,
      "rewards/correctness_reward_func": 0.15625,
      "rewards/strict_format_reward_func": 0.4609375,
      "step": 430
    },
    {
      "completion_length": 91.078125,
      "epoch": 0.5004354136429608,
      "grad_norm": 0.20692383149444513,
      "kl": 0.681640625,
      "learning_rate": 5.235062476295487e-07,
      "loss": 0.0272,
      "reward": 0.61328125,
      "reward_std": 0.12202189117670059,
      "rewards/correctness_reward_func": 0.1328125,
      "rewards/strict_format_reward_func": 0.48046875,
      "step": 431
    },
    {
      "completion_length": 72.07421875,
      "epoch": 0.5015965166908564,
      "grad_norm": 3.3769242846685636,
      "kl": 0.6669921875,
      "learning_rate": 5.216269725181329e-07,
      "loss": 0.0267,
      "reward": 0.625,
      "reward_std": 0.1284324675798416,
      "rewards/correctness_reward_func": 0.140625,
      "rewards/strict_format_reward_func": 0.484375,
      "step": 432
    },
    {
      "completion_length": 81.73828125,
      "epoch": 0.5027576197387518,
      "grad_norm": 3.6254322138472626,
      "kl": 0.685546875,
      "learning_rate": 5.197473912653548e-07,
      "loss": 0.0274,
      "reward": 0.640625,
      "reward_std": 0.1610843911767006,
      "rewards/correctness_reward_func": 0.15625,
      "rewards/strict_format_reward_func": 0.484375,
      "step": 433
    },
    {
      "completion_length": 73.97265625,
      "epoch": 0.5039187227866473,
      "grad_norm": 0.3057421931404266,
      "kl": 0.642578125,
      "learning_rate": 5.178675304776923e-07,
      "loss": 0.0257,
      "reward": 0.576171875,
      "reward_std": 0.14880991727113724,
      "rewards/correctness_reward_func": 0.09375,
      "rewards/strict_format_reward_func": 0.482421875,
      "step": 434
    },
    {
      "completion_length": 71.95703125,
      "epoch": 0.5050798258345428,
      "grad_norm": 0.5954928121710219,
      "kl": 0.630859375,
      "learning_rate": 5.159874167655799e-07,
      "loss": 0.0252,
      "reward": 0.578125,
      "reward_std": 0.1533661223948002,
      "rewards/correctness_reward_func": 0.1015625,
      "rewards/strict_format_reward_func": 0.4765625,
      "step": 435
    },
    {
      "completion_length": 73.546875,
      "epoch": 0.5062409288824383,
      "grad_norm": 0.34322427092970875,
      "kl": 0.685546875,
      "learning_rate": 5.14107076743033e-07,
      "loss": 0.0274,
      "reward": 0.712890625,
      "reward_std": 0.19313911721110344,
      "rewards/correctness_reward_func": 0.234375,
      "rewards/strict_format_reward_func": 0.478515625,
      "step": 436
    },
    {
      "completion_length": 99.0546875,
      "epoch": 0.5074020319303338,
      "grad_norm": 0.26077299543075405,
      "kl": 0.6650390625,
      "learning_rate": 5.122265370272703e-07,
      "loss": 0.0266,
      "reward": 0.67578125,
      "reward_std": 0.2539496347308159,
      "rewards/correctness_reward_func": 0.203125,
      "rewards/strict_format_reward_func": 0.47265625,
      "step": 437
    },
    {
      "completion_length": 96.2578125,
      "epoch": 0.5085631349782294,
      "grad_norm": 0.2442517472901473,
      "kl": 0.6591796875,
      "learning_rate": 5.103458242383371e-07,
      "loss": 0.0264,
      "reward": 0.61328125,
      "reward_std": 0.1598757915198803,
      "rewards/correctness_reward_func": 0.140625,
      "rewards/strict_format_reward_func": 0.47265625,
      "step": 438
    },
    {
      "completion_length": 109.55078125,
      "epoch": 0.5097242380261248,
      "grad_norm": 0.41904978648228075,
      "kl": 0.59033203125,
      "learning_rate": 5.084649649987284e-07,
      "loss": 0.0237,
      "reward": 0.611328125,
      "reward_std": 0.2097722813487053,
      "rewards/correctness_reward_func": 0.140625,
      "rewards/strict_format_reward_func": 0.470703125,
      "step": 439
    },
    {
      "completion_length": 90.296875,
      "epoch": 0.5108853410740203,
      "grad_norm": 0.2330615779966042,
      "kl": 0.6318359375,
      "learning_rate": 5.065839859330133e-07,
      "loss": 0.0253,
      "reward": 0.568359375,
      "reward_std": 0.16442972794175148,
      "rewards/correctness_reward_func": 0.09375,
      "rewards/strict_format_reward_func": 0.474609375,
      "step": 440
    },
    {
      "completion_length": 90.328125,
      "epoch": 0.5120464441219158,
      "grad_norm": 0.3702871607828062,
      "kl": 0.654296875,
      "learning_rate": 5.047029136674562e-07,
      "loss": 0.0261,
      "reward": 0.630859375,
      "reward_std": 0.2150527872145176,
      "rewards/correctness_reward_func": 0.15625,
      "rewards/strict_format_reward_func": 0.474609375,
      "step": 441
    },
    {
      "completion_length": 118.54296875,
      "epoch": 0.5132075471698113,
      "grad_norm": 0.2404788938610637,
      "kl": 0.6533203125,
      "learning_rate": 5.028217748296408e-07,
      "loss": 0.0261,
      "reward": 0.576171875,
      "reward_std": 0.19962820783257484,
      "rewards/correctness_reward_func": 0.1171875,
      "rewards/strict_format_reward_func": 0.458984375,
      "step": 442
    },
    {
      "completion_length": 113.48828125,
      "epoch": 0.5143686502177068,
      "grad_norm": 0.2793793247289244,
      "kl": 0.6533203125,
      "learning_rate": 5.009405960480937e-07,
      "loss": 0.0262,
      "reward": 0.68359375,
      "reward_std": 0.23072117567062378,
      "rewards/correctness_reward_func": 0.2109375,
      "rewards/strict_format_reward_func": 0.47265625,
      "step": 443
    },
    {
      "completion_length": 123.69140625,
      "epoch": 0.5155297532656024,
      "grad_norm": 0.3133392420781594,
      "kl": 0.6689453125,
      "learning_rate": 4.990594039519062e-07,
      "loss": 0.0268,
      "reward": 0.5703125,
      "reward_std": 0.1823294460773468,
      "rewards/correctness_reward_func": 0.1171875,
      "rewards/strict_format_reward_func": 0.453125,
      "step": 444
    },
    {
      "completion_length": 108.68359375,
      "epoch": 0.5166908563134979,
      "grad_norm": 0.17528759702001992,
      "kl": 0.6123046875,
      "learning_rate": 4.971782251703591e-07,
      "loss": 0.0245,
      "reward": 0.53515625,
      "reward_std": 0.1444598287343979,
      "rewards/correctness_reward_func": 0.0625,
      "rewards/strict_format_reward_func": 0.47265625,
      "step": 445
    },
    {
      "completion_length": 94.32421875,
      "epoch": 0.5178519593613933,
      "grad_norm": 0.2200463460967348,
      "kl": 0.583984375,
      "learning_rate": 4.952970863325439e-07,
      "loss": 0.0234,
      "reward": 0.572265625,
      "reward_std": 0.1793864667415619,
      "rewards/correctness_reward_func": 0.09375,
      "rewards/strict_format_reward_func": 0.478515625,
      "step": 446
    },
    {
      "completion_length": 98.12109375,
      "epoch": 0.5190130624092888,
      "grad_norm": 14.341599478702637,
      "kl": 0.640625,
      "learning_rate": 4.934160140669867e-07,
      "loss": 0.0256,
      "reward": 0.61328125,
      "reward_std": 0.1855371631681919,
      "rewards/correctness_reward_func": 0.140625,
      "rewards/strict_format_reward_func": 0.47265625,
      "step": 447
    },
    {
      "completion_length": 103.93359375,
      "epoch": 0.5201741654571843,
      "grad_norm": 0.2315349437053847,
      "kl": 0.607421875,
      "learning_rate": 4.915350350012714e-07,
      "loss": 0.0243,
      "reward": 0.572265625,
      "reward_std": 0.1807098686695099,
      "rewards/correctness_reward_func": 0.109375,
      "rewards/strict_format_reward_func": 0.462890625,
      "step": 448
    },
    {
      "completion_length": 50.27734375,
      "epoch": 0.5213352685050798,
      "grad_norm": 0.4363187934129076,
      "kl": 0.7607421875,
      "learning_rate": 4.896541757616631e-07,
      "loss": 0.0304,
      "reward": 0.6640625,
      "reward_std": 0.19000916182994843,
      "rewards/correctness_reward_func": 0.1796875,
      "rewards/strict_format_reward_func": 0.484375,
      "step": 449
    },
    {
      "completion_length": 122.5,
      "epoch": 0.5224963715529753,
      "grad_norm": 0.27240641904706797,
      "kl": 0.6513671875,
      "learning_rate": 4.877734629727298e-07,
      "loss": 0.026,
      "reward": 0.6171875,
      "reward_std": 0.2428351789712906,
      "rewards/correctness_reward_func": 0.15625,
      "rewards/strict_format_reward_func": 0.4609375,
      "step": 450
    },
    {
      "completion_length": 106.953125,
      "epoch": 0.5236574746008709,
      "grad_norm": 0.7466963728614375,
      "kl": 0.681640625,
      "learning_rate": 4.858929232569671e-07,
      "loss": 0.0273,
      "reward": 0.640625,
      "reward_std": 0.23390831053256989,
      "rewards/correctness_reward_func": 0.1640625,
      "rewards/strict_format_reward_func": 0.4765625,
      "step": 451
    },
    {
      "completion_length": 118.61328125,
      "epoch": 0.5248185776487664,
      "grad_norm": 0.3275580243731746,
      "kl": 0.662109375,
      "learning_rate": 4.840125832344201e-07,
      "loss": 0.0265,
      "reward": 0.572265625,
      "reward_std": 0.1805008351802826,
      "rewards/correctness_reward_func": 0.1015625,
      "rewards/strict_format_reward_func": 0.470703125,
      "step": 452
    },
    {
      "completion_length": 123.99609375,
      "epoch": 0.5259796806966618,
      "grad_norm": 0.22504369725172343,
      "kl": 0.6162109375,
      "learning_rate": 4.821324695223079e-07,
      "loss": 0.0247,
      "reward": 0.57421875,
      "reward_std": 0.13543873000890017,
      "rewards/correctness_reward_func": 0.109375,
      "rewards/strict_format_reward_func": 0.46484375,
      "step": 453
    },
    {
      "completion_length": 99.609375,
      "epoch": 0.5271407837445573,
      "grad_norm": 0.25601660047677527,
      "kl": 0.6689453125,
      "learning_rate": 4.802526087346452e-07,
      "loss": 0.0268,
      "reward": 0.658203125,
      "reward_std": 0.2322102226316929,
      "rewards/correctness_reward_func": 0.1875,
      "rewards/strict_format_reward_func": 0.470703125,
      "step": 454
    },
    {
      "completion_length": 106.09375,
      "epoch": 0.5283018867924528,
      "grad_norm": 0.19144165890158837,
      "kl": 0.6103515625,
      "learning_rate": 4.78373027481867e-07,
      "loss": 0.0244,
      "reward": 0.576171875,
      "reward_std": 0.1737821288406849,
      "rewards/correctness_reward_func": 0.1015625,
      "rewards/strict_format_reward_func": 0.474609375,
      "step": 455
    },
    {
      "completion_length": 68.82421875,
      "epoch": 0.5294629898403483,
      "grad_norm": 0.2601320397450299,
      "kl": 0.7265625,
      "learning_rate": 4.764937523704513e-07,
      "loss": 0.0291,
      "reward": 0.533203125,
      "reward_std": 0.1303238831460476,
      "rewards/correctness_reward_func": 0.0546875,
      "rewards/strict_format_reward_func": 0.478515625,
      "step": 456
    },
    {
      "completion_length": 133.7578125,
      "epoch": 0.5306240928882439,
      "grad_norm": 0.3893303471437102,
      "kl": 0.6640625,
      "learning_rate": 4.746148100025421e-07,
      "loss": 0.0266,
      "reward": 0.595703125,
      "reward_std": 0.23836983740329742,
      "rewards/correctness_reward_func": 0.140625,
      "rewards/strict_format_reward_func": 0.455078125,
      "step": 457
    },
    {
      "completion_length": 86.609375,
      "epoch": 0.5317851959361394,
      "grad_norm": 0.28861765982938503,
      "kl": 0.6826171875,
      "learning_rate": 4.7273622697557354e-07,
      "loss": 0.0273,
      "reward": 0.654296875,
      "reward_std": 0.16015625,
      "rewards/correctness_reward_func": 0.1796875,
      "rewards/strict_format_reward_func": 0.474609375,
      "step": 458
    },
    {
      "completion_length": 55.125,
      "epoch": 0.5329462989840348,
      "grad_norm": 0.21933796321810384,
      "kl": 0.7421875,
      "learning_rate": 4.708580298818931e-07,
      "loss": 0.0297,
      "reward": 0.6015625,
      "reward_std": 0.1586671955883503,
      "rewards/correctness_reward_func": 0.1171875,
      "rewards/strict_format_reward_func": 0.484375,
      "step": 459
    },
    {
      "completion_length": 91.5546875,
      "epoch": 0.5341074020319303,
      "grad_norm": 0.27297403937189646,
      "kl": 0.7138671875,
      "learning_rate": 4.6898024530838526e-07,
      "loss": 0.0286,
      "reward": 0.537109375,
      "reward_std": 0.1423230916261673,
      "rewards/correctness_reward_func": 0.0625,
      "rewards/strict_format_reward_func": 0.474609375,
      "step": 460
    },
    {
      "completion_length": 89.921875,
      "epoch": 0.5352685050798258,
      "grad_norm": 0.19980133696706576,
      "kl": 0.6689453125,
      "learning_rate": 4.671028998360947e-07,
      "loss": 0.0267,
      "reward": 0.62109375,
      "reward_std": 0.18879421800374985,
      "rewards/correctness_reward_func": 0.140625,
      "rewards/strict_format_reward_func": 0.48046875,
      "step": 461
    },
    {
      "completion_length": 92.10546875,
      "epoch": 0.5364296081277213,
      "grad_norm": 0.26301943391522115,
      "kl": 0.69140625,
      "learning_rate": 4.652260200398507e-07,
      "loss": 0.0277,
      "reward": 0.580078125,
      "reward_std": 0.1538761891424656,
      "rewards/correctness_reward_func": 0.1015625,
      "rewards/strict_format_reward_func": 0.478515625,
      "step": 462
    },
    {
      "completion_length": 86.55078125,
      "epoch": 0.5375907111756169,
      "grad_norm": 0.33345824111150424,
      "kl": 0.6689453125,
      "learning_rate": 4.6334963248789057e-07,
      "loss": 0.0267,
      "reward": 0.64453125,
      "reward_std": 0.1520632952451706,
      "rewards/correctness_reward_func": 0.171875,
      "rewards/strict_format_reward_func": 0.47265625,
      "step": 463
    },
    {
      "completion_length": 75.31640625,
      "epoch": 0.5387518142235124,
      "grad_norm": 0.28475868388912284,
      "kl": 0.7099609375,
      "learning_rate": 4.6147376374148354e-07,
      "loss": 0.0284,
      "reward": 0.568359375,
      "reward_std": 0.1368129812180996,
      "rewards/correctness_reward_func": 0.09375,
      "rewards/strict_format_reward_func": 0.474609375,
      "step": 464
    },
    {
      "completion_length": 89.29296875,
      "epoch": 0.5399129172714079,
      "grad_norm": 22.770106944872303,
      "kl": 1.541015625,
      "learning_rate": 4.59598440354555e-07,
      "loss": 0.0616,
      "reward": 0.529296875,
      "reward_std": 0.1436464935541153,
      "rewards/correctness_reward_func": 0.0546875,
      "rewards/strict_format_reward_func": 0.474609375,
      "step": 465
    },
    {
      "completion_length": 95.08203125,
      "epoch": 0.5410740203193033,
      "grad_norm": 0.19937500115731033,
      "kl": 0.6279296875,
      "learning_rate": 4.5772368887331043e-07,
      "loss": 0.0251,
      "reward": 0.546875,
      "reward_std": 0.1227918416261673,
      "rewards/correctness_reward_func": 0.078125,
      "rewards/strict_format_reward_func": 0.46875,
      "step": 466
    },
    {
      "completion_length": 71.48046875,
      "epoch": 0.5422351233671988,
      "grad_norm": 0.31179156026777827,
      "kl": 0.5966796875,
      "learning_rate": 4.5584953583585984e-07,
      "loss": 0.0239,
      "reward": 0.611328125,
      "reward_std": 0.2108660750091076,
      "rewards/correctness_reward_func": 0.140625,
      "rewards/strict_format_reward_func": 0.470703125,
      "step": 467
    },
    {
      "completion_length": 115.35546875,
      "epoch": 0.5433962264150943,
      "grad_norm": 0.37340776262314684,
      "kl": 0.6376953125,
      "learning_rate": 4.5397600777184153e-07,
      "loss": 0.0255,
      "reward": 0.662109375,
      "reward_std": 0.2925383485853672,
      "rewards/correctness_reward_func": 0.1953125,
      "rewards/strict_format_reward_func": 0.466796875,
      "step": 468
    },
    {
      "completion_length": 97.09765625,
      "epoch": 0.5445573294629898,
      "grad_norm": 0.3775660849606198,
      "kl": 0.669921875,
      "learning_rate": 4.521031312020473e-07,
      "loss": 0.0268,
      "reward": 0.642578125,
      "reward_std": 0.2465481087565422,
      "rewards/correctness_reward_func": 0.171875,
      "rewards/strict_format_reward_func": 0.470703125,
      "step": 469
    },
    {
      "completion_length": 86.3984375,
      "epoch": 0.5457184325108854,
      "grad_norm": 0.33718500400954116,
      "kl": 0.6708984375,
      "learning_rate": 4.5023093263804696e-07,
      "loss": 0.0268,
      "reward": 0.55859375,
      "reward_std": 0.1652868129312992,
      "rewards/correctness_reward_func": 0.09375,
      "rewards/strict_format_reward_func": 0.46484375,
      "step": 470
    },
    {
      "completion_length": 72.75,
      "epoch": 0.5468795355587809,
      "grad_norm": 0.3331032225194283,
      "kl": 0.666015625,
      "learning_rate": 4.483594385818118e-07,
      "loss": 0.0267,
      "reward": 0.677734375,
      "reward_std": 0.2409074828028679,
      "rewards/correctness_reward_func": 0.1875,
      "rewards/strict_format_reward_func": 0.490234375,
      "step": 471
    },
    {
      "completion_length": 106.66796875,
      "epoch": 0.5480406386066763,
      "grad_norm": 0.32162672320515157,
      "kl": 0.6640625,
      "learning_rate": 4.4648867552534157e-07,
      "loss": 0.0266,
      "reward": 0.7421875,
      "reward_std": 0.3212840221822262,
      "rewards/correctness_reward_func": 0.2734375,
      "rewards/strict_format_reward_func": 0.46875,
      "step": 472
    },
    {
      "completion_length": 96.6328125,
      "epoch": 0.5492017416545718,
      "grad_norm": 0.38404552006214343,
      "kl": 0.677734375,
      "learning_rate": 4.4461866995028776e-07,
      "loss": 0.0271,
      "reward": 0.65234375,
      "reward_std": 0.18847153056412935,
      "rewards/correctness_reward_func": 0.1796875,
      "rewards/strict_format_reward_func": 0.47265625,
      "step": 473
    },
    {
      "completion_length": 106.49609375,
      "epoch": 0.5503628447024673,
      "grad_norm": 0.731125898112846,
      "kl": 0.697265625,
      "learning_rate": 4.4274944832757954e-07,
      "loss": 0.0279,
      "reward": 0.55859375,
      "reward_std": 0.1173965372145176,
      "rewards/correctness_reward_func": 0.09375,
      "rewards/strict_format_reward_func": 0.46484375,
      "step": 474
    },
    {
      "completion_length": 77.82421875,
      "epoch": 0.5515239477503628,
      "grad_norm": 0.2752168048978263,
      "kl": 0.728515625,
      "learning_rate": 4.4088103711704827e-07,
      "loss": 0.0292,
      "reward": 0.66015625,
      "reward_std": 0.22907165437936783,
      "rewards/correctness_reward_func": 0.1796875,
      "rewards/strict_format_reward_func": 0.48046875,
      "step": 475
    },
    {
      "completion_length": 90.25390625,
      "epoch": 0.5526850507982584,
      "grad_norm": 0.2516326790077021,
      "kl": 0.65234375,
      "learning_rate": 4.39013462767054e-07,
      "loss": 0.0261,
      "reward": 0.609375,
      "reward_std": 0.15163809433579445,
      "rewards/correctness_reward_func": 0.140625,
      "rewards/strict_format_reward_func": 0.46875,
      "step": 476
    },
    {
      "completion_length": 113.10546875,
      "epoch": 0.5538461538461539,
      "grad_norm": 0.33411548900394306,
      "kl": 0.7216796875,
      "learning_rate": 4.3714675171411075e-07,
      "loss": 0.0289,
      "reward": 0.578125,
      "reward_std": 0.1923138126730919,
      "rewards/correctness_reward_func": 0.1171875,
      "rewards/strict_format_reward_func": 0.4609375,
      "step": 477
    },
    {
      "completion_length": 120.6796875,
      "epoch": 0.5550072568940494,
      "grad_norm": 0.2671470128969857,
      "kl": 0.6669921875,
      "learning_rate": 4.3528093038251145e-07,
      "loss": 0.0267,
      "reward": 0.626953125,
      "reward_std": 0.1575019806623459,
      "rewards/correctness_reward_func": 0.1640625,
      "rewards/strict_format_reward_func": 0.462890625,
      "step": 478
    },
    {
      "completion_length": 91.18359375,
      "epoch": 0.5561683599419448,
      "grad_norm": 0.24040047063332448,
      "kl": 0.7021484375,
      "learning_rate": 4.334160251839551e-07,
      "loss": 0.028,
      "reward": 0.54296875,
      "reward_std": 0.1354387328028679,
      "rewards/correctness_reward_func": 0.0625,
      "rewards/strict_format_reward_func": 0.48046875,
      "step": 479
    },
    {
      "completion_length": 102.54296875,
      "epoch": 0.5573294629898403,
      "grad_norm": 0.2281751554678181,
      "kl": 0.658203125,
      "learning_rate": 4.31552062517172e-07,
      "loss": 0.0263,
      "reward": 0.5625,
      "reward_std": 0.07173013407737017,
      "rewards/correctness_reward_func": 0.0859375,
      "rewards/strict_format_reward_func": 0.4765625,
      "step": 480
    },
    {
      "completion_length": 140.546875,
      "epoch": 0.5584905660377358,
      "grad_norm": 5.6864627093571665,
      "kl": 0.72265625,
      "learning_rate": 4.2968906876755096e-07,
      "loss": 0.0289,
      "reward": 0.6171875,
      "reward_std": 0.19704535976052284,
      "rewards/correctness_reward_func": 0.15625,
      "rewards/strict_format_reward_func": 0.4609375,
      "step": 481
    },
    {
      "completion_length": 117.86328125,
      "epoch": 0.5596516690856314,
      "grad_norm": 0.2327568479550059,
      "kl": 0.6552734375,
      "learning_rate": 4.2782707030676436e-07,
      "loss": 0.0262,
      "reward": 0.6015625,
      "reward_std": 0.22982780635356903,
      "rewards/correctness_reward_func": 0.1328125,
      "rewards/strict_format_reward_func": 0.46875,
      "step": 482
    },
    {
      "completion_length": 110.19921875,
      "epoch": 0.5608127721335269,
      "grad_norm": 0.28194791579227246,
      "kl": 0.6455078125,
      "learning_rate": 4.259660934923964e-07,
      "loss": 0.0258,
      "reward": 0.630859375,
      "reward_std": 0.1794070415198803,
      "rewards/correctness_reward_func": 0.15625,
      "rewards/strict_format_reward_func": 0.474609375,
      "step": 483
    },
    {
      "completion_length": 122.24609375,
      "epoch": 0.5619738751814224,
      "grad_norm": 0.21710328837385925,
      "kl": 0.673828125,
      "learning_rate": 4.2410616466756944e-07,
      "loss": 0.027,
      "reward": 0.568359375,
      "reward_std": 0.19203336164355278,
      "rewards/correctness_reward_func": 0.09375,
      "rewards/strict_format_reward_func": 0.474609375,
      "step": 484
    },
    {
      "completion_length": 106.68359375,
      "epoch": 0.5631349782293179,
      "grad_norm": 0.26421099791096914,
      "kl": 0.6884765625,
      "learning_rate": 4.2224731016057023e-07,
      "loss": 0.0275,
      "reward": 0.666015625,
      "reward_std": 0.275704313069582,
      "rewards/correctness_reward_func": 0.1953125,
      "rewards/strict_format_reward_func": 0.470703125,
      "step": 485
    },
    {
      "completion_length": 111.27734375,
      "epoch": 0.5642960812772133,
      "grad_norm": 3.5394009270390296,
      "kl": 0.720703125,
      "learning_rate": 4.203895562844788e-07,
      "loss": 0.0288,
      "reward": 0.572265625,
      "reward_std": 0.20700840651988983,
      "rewards/correctness_reward_func": 0.109375,
      "rewards/strict_format_reward_func": 0.462890625,
      "step": 486
    },
    {
      "completion_length": 118.1640625,
      "epoch": 0.5654571843251088,
      "grad_norm": 0.36634775461506897,
      "kl": 0.7265625,
      "learning_rate": 4.1853292933679466e-07,
      "loss": 0.0291,
      "reward": 0.630859375,
      "reward_std": 0.23488731682300568,
      "rewards/correctness_reward_func": 0.1796875,
      "rewards/strict_format_reward_func": 0.451171875,
      "step": 487
    },
    {
      "completion_length": 101.1953125,
      "epoch": 0.5666182873730043,
      "grad_norm": 0.2538063482686055,
      "kl": 0.7099609375,
      "learning_rate": 4.1667745559906535e-07,
      "loss": 0.0284,
      "reward": 0.509765625,
      "reward_std": 0.1716887727379799,
      "rewards/correctness_reward_func": 0.0546875,
      "rewards/strict_format_reward_func": 0.455078125,
      "step": 488
    },
    {
      "completion_length": 88.83203125,
      "epoch": 0.5677793904208999,
      "grad_norm": 0.32416368927353967,
      "kl": 0.7216796875,
      "learning_rate": 4.1482316133651373e-07,
      "loss": 0.0289,
      "reward": 0.68359375,
      "reward_std": 0.22665445506572723,
      "rewards/correctness_reward_func": 0.2109375,
      "rewards/strict_format_reward_func": 0.47265625,
      "step": 489
    },
    {
      "completion_length": 101.05078125,
      "epoch": 0.5689404934687954,
      "grad_norm": 0.279513532888465,
      "kl": 0.67578125,
      "learning_rate": 4.12970072797667e-07,
      "loss": 0.027,
      "reward": 0.59765625,
      "reward_std": 0.1319277435541153,
      "rewards/correctness_reward_func": 0.125,
      "rewards/strict_format_reward_func": 0.47265625,
      "step": 490
    },
    {
      "completion_length": 45.97265625,
      "epoch": 0.5701015965166909,
      "grad_norm": 22.07420367608219,
      "kl": 0.8447265625,
      "learning_rate": 4.1111821621398443e-07,
      "loss": 0.0338,
      "reward": 0.677734375,
      "reward_std": 0.2320011854171753,
      "rewards/correctness_reward_func": 0.1953125,
      "rewards/strict_format_reward_func": 0.482421875,
      "step": 491
    },
    {
      "completion_length": 103.33203125,
      "epoch": 0.5712626995645863,
      "grad_norm": 0.23161473927623535,
      "kl": 0.640625,
      "learning_rate": 4.092676177994862e-07,
      "loss": 0.0256,
      "reward": 0.552734375,
      "reward_std": 0.17663796991109848,
      "rewards/correctness_reward_func": 0.0859375,
      "rewards/strict_format_reward_func": 0.466796875,
      "step": 492
    },
    {
      "completion_length": 107.51953125,
      "epoch": 0.5724238026124818,
      "grad_norm": 0.8256710817677838,
      "kl": 0.7421875,
      "learning_rate": 4.0741830375038264e-07,
      "loss": 0.0296,
      "reward": 0.59375,
      "reward_std": 0.2444898895919323,
      "rewards/correctness_reward_func": 0.125,
      "rewards/strict_format_reward_func": 0.46875,
      "step": 493
    },
    {
      "completion_length": 68.80078125,
      "epoch": 0.5735849056603773,
      "grad_norm": 0.2857385195982699,
      "kl": 0.75,
      "learning_rate": 4.0557030024470324e-07,
      "loss": 0.03,
      "reward": 0.59765625,
      "reward_std": 0.18851527571678162,
      "rewards/correctness_reward_func": 0.1171875,
      "rewards/strict_format_reward_func": 0.48046875,
      "step": 494
    },
    {
      "completion_length": 92.06640625,
      "epoch": 0.5747460087082729,
      "grad_norm": 0.313037378738364,
      "kl": 0.7197265625,
      "learning_rate": 4.0372363344192606e-07,
      "loss": 0.0288,
      "reward": 0.671875,
      "reward_std": 0.22357874736189842,
      "rewards/correctness_reward_func": 0.1953125,
      "rewards/strict_format_reward_func": 0.4765625,
      "step": 495
    },
    {
      "completion_length": 96.0,
      "epoch": 0.5759071117561684,
      "grad_norm": 0.24952171289710004,
      "kl": 0.7197265625,
      "learning_rate": 4.0187832948260705e-07,
      "loss": 0.0288,
      "reward": 0.681640625,
      "reward_std": 0.21595098450779915,
      "rewards/correctness_reward_func": 0.203125,
      "rewards/strict_format_reward_func": 0.478515625,
      "step": 496
    },
    {
      "completion_length": 77.86328125,
      "epoch": 0.5770682148040639,
      "grad_norm": 0.36012882972016,
      "kl": 0.767578125,
      "learning_rate": 4.0003441448801077e-07,
      "loss": 0.0308,
      "reward": 0.564453125,
      "reward_std": 0.16201253235340118,
      "rewards/correctness_reward_func": 0.0859375,
      "rewards/strict_format_reward_func": 0.478515625,
      "step": 497
    },
    {
      "completion_length": 78.453125,
      "epoch": 0.5782293178519594,
      "grad_norm": 0.3140598121085828,
      "kl": 0.759765625,
      "learning_rate": 3.9819191455974034e-07,
      "loss": 0.0304,
      "reward": 0.6484375,
      "reward_std": 0.2492457665503025,
      "rewards/correctness_reward_func": 0.1796875,
      "rewards/strict_format_reward_func": 0.46875,
      "step": 498
    },
    {
      "completion_length": 103.27734375,
      "epoch": 0.5793904208998548,
      "grad_norm": 0.4245669463312936,
      "kl": 0.7685546875,
      "learning_rate": 3.96350855779367e-07,
      "loss": 0.0307,
      "reward": 0.755859375,
      "reward_std": 0.25158101320266724,
      "rewards/correctness_reward_func": 0.2890625,
      "rewards/strict_format_reward_func": 0.466796875,
      "step": 499
    },
    {
      "completion_length": 62.60546875,
      "epoch": 0.5805515239477503,
      "grad_norm": 0.21490042541967444,
      "kl": 0.7412109375,
      "learning_rate": 3.9451126420806304e-07,
      "loss": 0.0296,
      "reward": 0.625,
      "reward_std": 0.1408340372145176,
      "rewards/correctness_reward_func": 0.1484375,
      "rewards/strict_format_reward_func": 0.4765625,
      "step": 500
    },
    {
      "completion_length": 46.42578125,
      "epoch": 0.5817126269956459,
      "grad_norm": 0.27527957231709527,
      "kl": 0.7333984375,
      "learning_rate": 3.926731658862307e-07,
      "loss": 0.0293,
      "reward": 0.666015625,
      "reward_std": 0.23232503235340118,
      "rewards/correctness_reward_func": 0.1875,
      "rewards/strict_format_reward_func": 0.478515625,
      "step": 501
    },
    {
      "completion_length": 93.38671875,
      "epoch": 0.5828737300435414,
      "grad_norm": 0.3392934972190868,
      "kl": 0.7421875,
      "learning_rate": 3.9083658683313496e-07,
      "loss": 0.0297,
      "reward": 0.515625,
      "reward_std": 0.1632719710469246,
      "rewards/correctness_reward_func": 0.0546875,
      "rewards/strict_format_reward_func": 0.4609375,
      "step": 502
    },
    {
      "completion_length": 143.33984375,
      "epoch": 0.5840348330914369,
      "grad_norm": 0.33148255963349393,
      "kl": 0.7841796875,
      "learning_rate": 3.8900155304653416e-07,
      "loss": 0.0313,
      "reward": 0.6328125,
      "reward_std": 0.1914496347308159,
      "rewards/correctness_reward_func": 0.1640625,
      "rewards/strict_format_reward_func": 0.46875,
      "step": 503
    },
    {
      "completion_length": 61.53125,
      "epoch": 0.5851959361393324,
      "grad_norm": 0.3945137195430909,
      "kl": 0.7099609375,
      "learning_rate": 3.8716809050231325e-07,
      "loss": 0.0284,
      "reward": 0.6171875,
      "reward_std": 0.23632550612092018,
      "rewards/correctness_reward_func": 0.140625,
      "rewards/strict_format_reward_func": 0.4765625,
      "step": 504
    },
    {
      "completion_length": 79.01953125,
      "epoch": 0.5863570391872278,
      "grad_norm": 0.3373755714899385,
      "kl": 0.7412109375,
      "learning_rate": 3.8533622515411526e-07,
      "loss": 0.0297,
      "reward": 0.65625,
      "reward_std": 0.2918977700173855,
      "rewards/correctness_reward_func": 0.1796875,
      "rewards/strict_format_reward_func": 0.4765625,
      "step": 505
    },
    {
      "completion_length": 91.30859375,
      "epoch": 0.5875181422351233,
      "grad_norm": 0.5209616255528962,
      "kl": 0.7177734375,
      "learning_rate": 3.8350598293297345e-07,
      "loss": 0.0287,
      "reward": 0.57421875,
      "reward_std": 0.14908518362790346,
      "rewards/correctness_reward_func": 0.1015625,
      "rewards/strict_format_reward_func": 0.47265625,
      "step": 506
    },
    {
      "completion_length": 82.078125,
      "epoch": 0.5886792452830188,
      "grad_norm": 0.27492045142658567,
      "kl": 0.7236328125,
      "learning_rate": 3.8167738974694533e-07,
      "loss": 0.0289,
      "reward": 0.677734375,
      "reward_std": 0.1695011891424656,
      "rewards/correctness_reward_func": 0.203125,
      "rewards/strict_format_reward_func": 0.474609375,
      "step": 507
    },
    {
      "completion_length": 77.76953125,
      "epoch": 0.5898403483309144,
      "grad_norm": 0.21950971900424004,
      "kl": 0.701171875,
      "learning_rate": 3.798504714807458e-07,
      "loss": 0.028,
      "reward": 0.6328125,
      "reward_std": 0.22641966119408607,
      "rewards/correctness_reward_func": 0.15625,
      "rewards/strict_format_reward_func": 0.4765625,
      "step": 508
    },
    {
      "completion_length": 80.00390625,
      "epoch": 0.5910014513788099,
      "grad_norm": 0.22939719513267132,
      "kl": 0.705078125,
      "learning_rate": 3.7802525399537996e-07,
      "loss": 0.0282,
      "reward": 0.513671875,
      "reward_std": 0.11767135001718998,
      "rewards/correctness_reward_func": 0.046875,
      "rewards/strict_format_reward_func": 0.466796875,
      "step": 509
    },
    {
      "completion_length": 74.4140625,
      "epoch": 0.5921625544267054,
      "grad_norm": 0.28268345508901205,
      "kl": 0.7919921875,
      "learning_rate": 3.7620176312777697e-07,
      "loss": 0.0317,
      "reward": 0.60546875,
      "reward_std": 0.2383246347308159,
      "rewards/correctness_reward_func": 0.125,
      "rewards/strict_format_reward_func": 0.48046875,
      "step": 510
    },
    {
      "completion_length": 143.99609375,
      "epoch": 0.5933236574746009,
      "grad_norm": 0.34496477716764284,
      "kl": 0.71875,
      "learning_rate": 3.7438002469042564e-07,
      "loss": 0.0287,
      "reward": 0.56640625,
      "reward_std": 0.23446358367800713,
      "rewards/correctness_reward_func": 0.109375,
      "rewards/strict_format_reward_func": 0.45703125,
      "step": 511
    },
    {
      "completion_length": 92.41796875,
      "epoch": 0.5944847605224963,
      "grad_norm": 0.5645159724407465,
      "kl": 0.779296875,
      "learning_rate": 3.725600644710077e-07,
      "loss": 0.0312,
      "reward": 0.615234375,
      "reward_std": 0.21855516359210014,
      "rewards/correctness_reward_func": 0.140625,
      "rewards/strict_format_reward_func": 0.474609375,
      "step": 512
    },
    {
      "completion_length": 90.6875,
      "epoch": 0.5956458635703918,
      "grad_norm": 0.4498728998535081,
      "kl": 0.845703125,
      "learning_rate": 3.7074190823203354e-07,
      "loss": 0.0338,
      "reward": 0.60546875,
      "reward_std": 0.2192828767001629,
      "rewards/correctness_reward_func": 0.140625,
      "rewards/strict_format_reward_func": 0.46484375,
      "step": 513
    },
    {
      "completion_length": 102.54296875,
      "epoch": 0.5968069666182874,
      "grad_norm": 0.3189647735230763,
      "kl": 0.736328125,
      "learning_rate": 3.6892558171047696e-07,
      "loss": 0.0295,
      "reward": 0.658203125,
      "reward_std": 0.216376181691885,
      "rewards/correctness_reward_func": 0.1875,
      "rewards/strict_format_reward_func": 0.470703125,
      "step": 514
    },
    {
      "completion_length": 91.5234375,
      "epoch": 0.5979680696661829,
      "grad_norm": 0.5293232256976855,
      "kl": 0.8369140625,
      "learning_rate": 3.671111106174113e-07,
      "loss": 0.0335,
      "reward": 0.642578125,
      "reward_std": 0.22121058404445648,
      "rewards/correctness_reward_func": 0.1796875,
      "rewards/strict_format_reward_func": 0.462890625,
      "step": 515
    },
    {
      "completion_length": 89.3984375,
      "epoch": 0.5991291727140784,
      "grad_norm": 0.2576839169226953,
      "kl": 0.7763671875,
      "learning_rate": 3.6529852063764545e-07,
      "loss": 0.0311,
      "reward": 0.50390625,
      "reward_std": 0.11056302487850189,
      "rewards/correctness_reward_func": 0.03125,
      "rewards/strict_format_reward_func": 0.47265625,
      "step": 516
    },
    {
      "completion_length": 76.55859375,
      "epoch": 0.6002902757619739,
      "grad_norm": 0.24881581240568054,
      "kl": 0.8251953125,
      "learning_rate": 3.6348783742935965e-07,
      "loss": 0.033,
      "reward": 0.568359375,
      "reward_std": 0.16738725639879704,
      "rewards/correctness_reward_func": 0.0859375,
      "rewards/strict_format_reward_func": 0.482421875,
      "step": 517
    },
    {
      "completion_length": 117.5703125,
      "epoch": 0.6014513788098694,
      "grad_norm": 0.3251042441482894,
      "kl": 0.73046875,
      "learning_rate": 3.6167908662374327e-07,
      "loss": 0.0292,
      "reward": 0.53515625,
      "reward_std": 0.15920007228851318,
      "rewards/correctness_reward_func": 0.0703125,
      "rewards/strict_format_reward_func": 0.46484375,
      "step": 518
    },
    {
      "completion_length": 117.08984375,
      "epoch": 0.6026124818577648,
      "grad_norm": 0.2592011648782837,
      "kl": 0.7294921875,
      "learning_rate": 3.5987229382463137e-07,
      "loss": 0.0292,
      "reward": 0.548828125,
      "reward_std": 0.1694021001458168,
      "rewards/correctness_reward_func": 0.078125,
      "rewards/strict_format_reward_func": 0.470703125,
      "step": 519
    },
    {
      "completion_length": 96.18359375,
      "epoch": 0.6037735849056604,
      "grad_norm": 0.2798201862819926,
      "kl": 0.732421875,
      "learning_rate": 3.580674846081421e-07,
      "loss": 0.0293,
      "reward": 0.6484375,
      "reward_std": 0.22707253694534302,
      "rewards/correctness_reward_func": 0.1796875,
      "rewards/strict_format_reward_func": 0.46875,
      "step": 520
    },
    {
      "completion_length": 61.9765625,
      "epoch": 0.6049346879535559,
      "grad_norm": 0.27655267282397455,
      "kl": 0.779296875,
      "learning_rate": 3.562646845223153e-07,
      "loss": 0.0312,
      "reward": 0.755859375,
      "reward_std": 0.2233039326965809,
      "rewards/correctness_reward_func": 0.2734375,
      "rewards/strict_format_reward_func": 0.482421875,
      "step": 521
    },
    {
      "completion_length": 89.08203125,
      "epoch": 0.6060957910014514,
      "grad_norm": 0.3139530079672393,
      "kl": 0.763671875,
      "learning_rate": 3.5446391908675035e-07,
      "loss": 0.0306,
      "reward": 0.560546875,
      "reward_std": 0.1780836395919323,
      "rewards/correctness_reward_func": 0.0859375,
      "rewards/strict_format_reward_func": 0.474609375,
      "step": 522
    },
    {
      "completion_length": 118.93359375,
      "epoch": 0.6072568940493469,
      "grad_norm": 0.32088181645373987,
      "kl": 0.751953125,
      "learning_rate": 3.52665213792245e-07,
      "loss": 0.0301,
      "reward": 0.583984375,
      "reward_std": 0.2228652834892273,
      "rewards/correctness_reward_func": 0.1171875,
      "rewards/strict_format_reward_func": 0.466796875,
      "step": 523
    },
    {
      "completion_length": 74.390625,
      "epoch": 0.6084179970972424,
      "grad_norm": 0.6311615888394548,
      "kl": 0.853515625,
      "learning_rate": 3.508685941004347e-07,
      "loss": 0.0341,
      "reward": 0.669921875,
      "reward_std": 0.1918243244290352,
      "rewards/correctness_reward_func": 0.1875,
      "rewards/strict_format_reward_func": 0.482421875,
      "step": 524
    },
    {
      "completion_length": 114.4296875,
      "epoch": 0.6095791001451378,
      "grad_norm": 0.2382437905015168,
      "kl": 0.7763671875,
      "learning_rate": 3.4907408544343205e-07,
      "loss": 0.0311,
      "reward": 0.611328125,
      "reward_std": 0.16716961562633514,
      "rewards/correctness_reward_func": 0.140625,
      "rewards/strict_format_reward_func": 0.470703125,
      "step": 525
    },
    {
      "completion_length": 114.7109375,
      "epoch": 0.6107402031930333,
      "grad_norm": 0.26249196987129064,
      "kl": 0.7529296875,
      "learning_rate": 3.4728171322346687e-07,
      "loss": 0.0301,
      "reward": 0.583984375,
      "reward_std": 0.1302090771496296,
      "rewards/correctness_reward_func": 0.1171875,
      "rewards/strict_format_reward_func": 0.466796875,
      "step": 526
    },
    {
      "completion_length": 90.40234375,
      "epoch": 0.6119013062409289,
      "grad_norm": 0.2850100968247729,
      "kl": 0.794921875,
      "learning_rate": 3.454915028125263e-07,
      "loss": 0.0318,
      "reward": 0.671875,
      "reward_std": 0.2048608362674713,
      "rewards/correctness_reward_func": 0.1953125,
      "rewards/strict_format_reward_func": 0.4765625,
      "step": 527
    },
    {
      "completion_length": 84.62890625,
      "epoch": 0.6130624092888244,
      "grad_norm": 0.4222727814047971,
      "kl": 0.896484375,
      "learning_rate": 3.437034795519963e-07,
      "loss": 0.0359,
      "reward": 0.630859375,
      "reward_std": 0.19412671402096748,
      "rewards/correctness_reward_func": 0.15625,
      "rewards/strict_format_reward_func": 0.474609375,
      "step": 528
    },
    {
      "completion_length": 129.66015625,
      "epoch": 0.6142235123367199,
      "grad_norm": 0.33615487307939873,
      "kl": 0.7724609375,
      "learning_rate": 3.419176687523023e-07,
      "loss": 0.0309,
      "reward": 0.66796875,
      "reward_std": 0.20937702432274818,
      "rewards/correctness_reward_func": 0.203125,
      "rewards/strict_format_reward_func": 0.46484375,
      "step": 529
    },
    {
      "completion_length": 86.2265625,
      "epoch": 0.6153846153846154,
      "grad_norm": 0.24923071190945661,
      "kl": 0.771484375,
      "learning_rate": 3.401340956925515e-07,
      "loss": 0.0308,
      "reward": 0.6015625,
      "reward_std": 0.19100237637758255,
      "rewards/correctness_reward_func": 0.125,
      "rewards/strict_format_reward_func": 0.4765625,
      "step": 530
    },
    {
      "completion_length": 143.02734375,
      "epoch": 0.6165457184325109,
      "grad_norm": 0.3276298256772566,
      "kl": 0.71484375,
      "learning_rate": 3.38352785620174e-07,
      "loss": 0.0286,
      "reward": 0.587890625,
      "reward_std": 0.14297077432274818,
      "rewards/correctness_reward_func": 0.125,
      "rewards/strict_format_reward_func": 0.462890625,
      "step": 531
    },
    {
      "completion_length": 80.32421875,
      "epoch": 0.6177068214804063,
      "grad_norm": 0.29222365935331085,
      "kl": 0.7666015625,
      "learning_rate": 3.365737637505668e-07,
      "loss": 0.0306,
      "reward": 0.57421875,
      "reward_std": 0.2067302167415619,
      "rewards/correctness_reward_func": 0.1015625,
      "rewards/strict_format_reward_func": 0.47265625,
      "step": 532
    },
    {
      "completion_length": 100.42578125,
      "epoch": 0.6188679245283019,
      "grad_norm": 0.32019384583432065,
      "kl": 0.775390625,
      "learning_rate": 3.347970552667361e-07,
      "loss": 0.031,
      "reward": 0.63671875,
      "reward_std": 0.1853860728442669,
      "rewards/correctness_reward_func": 0.1640625,
      "rewards/strict_format_reward_func": 0.47265625,
      "step": 533
    },
    {
      "completion_length": 93.1171875,
      "epoch": 0.6200290275761974,
      "grad_norm": 0.3149784457430484,
      "kl": 0.8046875,
      "learning_rate": 3.330226853189402e-07,
      "loss": 0.0322,
      "reward": 0.609375,
      "reward_std": 0.2033340372145176,
      "rewards/correctness_reward_func": 0.140625,
      "rewards/strict_format_reward_func": 0.46875,
      "step": 534
    },
    {
      "completion_length": 64.44140625,
      "epoch": 0.6211901306240929,
      "grad_norm": 0.22216317375828598,
      "kl": 0.796875,
      "learning_rate": 3.312506790243348e-07,
      "loss": 0.0319,
      "reward": 0.58984375,
      "reward_std": 0.1585523895919323,
      "rewards/correctness_reward_func": 0.109375,
      "rewards/strict_format_reward_func": 0.48046875,
      "step": 535
    },
    {
      "completion_length": 150.09375,
      "epoch": 0.6223512336719884,
      "grad_norm": 0.37055445073619725,
      "kl": 0.7080078125,
      "learning_rate": 3.29481061466617e-07,
      "loss": 0.0284,
      "reward": 0.57421875,
      "reward_std": 0.25864865258336067,
      "rewards/correctness_reward_func": 0.125,
      "rewards/strict_format_reward_func": 0.44921875,
      "step": 536
    },
    {
      "completion_length": 83.33203125,
      "epoch": 0.6235123367198839,
      "grad_norm": 0.40236396723438866,
      "kl": 0.7880859375,
      "learning_rate": 3.277138576956697e-07,
      "loss": 0.0315,
      "reward": 0.6796875,
      "reward_std": 0.1830664612352848,
      "rewards/correctness_reward_func": 0.203125,
      "rewards/strict_format_reward_func": 0.4765625,
      "step": 537
    },
    {
      "completion_length": 106.4140625,
      "epoch": 0.6246734397677793,
      "grad_norm": 0.4305850554064533,
      "kl": 0.798828125,
      "learning_rate": 3.259490927272071e-07,
      "loss": 0.032,
      "reward": 0.642578125,
      "reward_std": 0.2163761891424656,
      "rewards/correctness_reward_func": 0.171875,
      "rewards/strict_format_reward_func": 0.470703125,
      "step": 538
    },
    {
      "completion_length": 111.453125,
      "epoch": 0.6258345428156749,
      "grad_norm": 0.4968286851594966,
      "kl": 0.7705078125,
      "learning_rate": 3.2418679154242105e-07,
      "loss": 0.0308,
      "reward": 0.65234375,
      "reward_std": 0.1947672963142395,
      "rewards/correctness_reward_func": 0.1875,
      "rewards/strict_format_reward_func": 0.46484375,
      "step": 539
    },
    {
      "completion_length": 140.27734375,
      "epoch": 0.6269956458635704,
      "grad_norm": 0.30929121029274015,
      "kl": 0.740234375,
      "learning_rate": 3.2242697908762795e-07,
      "loss": 0.0296,
      "reward": 0.572265625,
      "reward_std": 0.1594805307686329,
      "rewards/correctness_reward_func": 0.109375,
      "rewards/strict_format_reward_func": 0.462890625,
      "step": 540
    },
    {
      "completion_length": 115.62109375,
      "epoch": 0.6281567489114659,
      "grad_norm": 0.2924679895655973,
      "kl": 0.7314453125,
      "learning_rate": 3.206696802739137e-07,
      "loss": 0.0292,
      "reward": 0.72265625,
      "reward_std": 0.23018264397978783,
      "rewards/correctness_reward_func": 0.25,
      "rewards/strict_format_reward_func": 0.47265625,
      "step": 541
    },
    {
      "completion_length": 84.73828125,
      "epoch": 0.6293178519593614,
      "grad_norm": 0.3181286988717935,
      "kl": 0.8525390625,
      "learning_rate": 3.18914919976783e-07,
      "loss": 0.034,
      "reward": 0.57421875,
      "reward_std": 0.14425079245120287,
      "rewards/correctness_reward_func": 0.1015625,
      "rewards/strict_format_reward_func": 0.47265625,
      "step": 542
    },
    {
      "completion_length": 113.25,
      "epoch": 0.6304789550072569,
      "grad_norm": 0.3544746561033556,
      "kl": 0.814453125,
      "learning_rate": 3.1716272303580625e-07,
      "loss": 0.0325,
      "reward": 0.681640625,
      "reward_std": 0.22174865007400513,
      "rewards/correctness_reward_func": 0.2109375,
      "rewards/strict_format_reward_func": 0.470703125,
      "step": 543
    },
    {
      "completion_length": 86.546875,
      "epoch": 0.6316400580551524,
      "grad_norm": 0.43468852900315424,
      "kl": 0.8271484375,
      "learning_rate": 3.1541311425426855e-07,
      "loss": 0.0331,
      "reward": 0.693359375,
      "reward_std": 0.3203558847308159,
      "rewards/correctness_reward_func": 0.21875,
      "rewards/strict_format_reward_func": 0.474609375,
      "step": 544
    },
    {
      "completion_length": 144.4296875,
      "epoch": 0.6328011611030478,
      "grad_norm": 0.39631426045364027,
      "kl": 0.73828125,
      "learning_rate": 3.1366611839881745e-07,
      "loss": 0.0296,
      "reward": 0.5859375,
      "reward_std": 0.2090531773865223,
      "rewards/correctness_reward_func": 0.125,
      "rewards/strict_format_reward_func": 0.4609375,
      "step": 545
    },
    {
      "completion_length": 127.109375,
      "epoch": 0.6339622641509434,
      "grad_norm": 0.5018523484254885,
      "kl": 0.7646484375,
      "learning_rate": 3.1192176019911387e-07,
      "loss": 0.0306,
      "reward": 0.552734375,
      "reward_std": 0.165875393897295,
      "rewards/correctness_reward_func": 0.09375,
      "rewards/strict_format_reward_func": 0.458984375,
      "step": 546
    },
    {
      "completion_length": 125.80078125,
      "epoch": 0.6351233671988389,
      "grad_norm": 0.32438467916853886,
      "kl": 0.783203125,
      "learning_rate": 3.1018006434748114e-07,
      "loss": 0.0313,
      "reward": 0.607421875,
      "reward_std": 0.1340644806623459,
      "rewards/correctness_reward_func": 0.140625,
      "rewards/strict_format_reward_func": 0.466796875,
      "step": 547
    },
    {
      "completion_length": 166.15234375,
      "epoch": 0.6362844702467344,
      "grad_norm": 0.6799049264236043,
      "kl": 0.8193359375,
      "learning_rate": 3.0844105549855527e-07,
      "loss": 0.0328,
      "reward": 0.59375,
      "reward_std": 0.23213880509138107,
      "rewards/correctness_reward_func": 0.140625,
      "rewards/strict_format_reward_func": 0.453125,
      "step": 548
    },
    {
      "completion_length": 120.953125,
      "epoch": 0.6374455732946299,
      "grad_norm": 0.8053970461223089,
      "kl": 0.8115234375,
      "learning_rate": 3.0670475826893663e-07,
      "loss": 0.0325,
      "reward": 0.685546875,
      "reward_std": 0.2441309168934822,
      "rewards/correctness_reward_func": 0.21875,
      "rewards/strict_format_reward_func": 0.466796875,
      "step": 549
    },
    {
      "completion_length": 123.76953125,
      "epoch": 0.6386066763425254,
      "grad_norm": 0.3809562503974432,
      "kl": 0.83203125,
      "learning_rate": 3.0497119723684106e-07,
      "loss": 0.0333,
      "reward": 0.61328125,
      "reward_std": 0.22830397635698318,
      "rewards/correctness_reward_func": 0.140625,
      "rewards/strict_format_reward_func": 0.47265625,
      "step": 550
    },
    {
      "completion_length": 96.953125,
      "epoch": 0.639767779390421,
      "grad_norm": 0.36235845770847946,
      "kl": 0.8798828125,
      "learning_rate": 3.032403969417523e-07,
      "loss": 0.0352,
      "reward": 0.6875,
      "reward_std": 0.24855432659387589,
      "rewards/correctness_reward_func": 0.21875,
      "rewards/strict_format_reward_func": 0.46875,
      "step": 551
    },
    {
      "completion_length": 118.91015625,
      "epoch": 0.6409288824383164,
      "grad_norm": 0.40551720324657914,
      "kl": 0.765625,
      "learning_rate": 3.01512381884074e-07,
      "loss": 0.0306,
      "reward": 0.56640625,
      "reward_std": 0.1730835996568203,
      "rewards/correctness_reward_func": 0.09375,
      "rewards/strict_format_reward_func": 0.47265625,
      "step": 552
    },
    {
      "completion_length": 98.63671875,
      "epoch": 0.6420899854862119,
      "grad_norm": 0.35277815473325297,
      "kl": 0.748046875,
      "learning_rate": 2.9978717652478343e-07,
      "loss": 0.03,
      "reward": 0.623046875,
      "reward_std": 0.2643606886267662,
      "rewards/correctness_reward_func": 0.15625,
      "rewards/strict_format_reward_func": 0.466796875,
      "step": 553
    },
    {
      "completion_length": 122.046875,
      "epoch": 0.6432510885341074,
      "grad_norm": 0.4948739984006025,
      "kl": 0.84765625,
      "learning_rate": 2.9806480528508516e-07,
      "loss": 0.0339,
      "reward": 0.587890625,
      "reward_std": 0.134200194850564,
      "rewards/correctness_reward_func": 0.1328125,
      "rewards/strict_format_reward_func": 0.455078125,
      "step": 554
    },
    {
      "completion_length": 185.56640625,
      "epoch": 0.6444121915820029,
      "grad_norm": 0.5645859646675913,
      "kl": 0.783203125,
      "learning_rate": 2.963452925460654e-07,
      "loss": 0.0314,
      "reward": 0.5390625,
      "reward_std": 0.2068450227379799,
      "rewards/correctness_reward_func": 0.09375,
      "rewards/strict_format_reward_func": 0.4453125,
      "step": 555
    },
    {
      "completion_length": 124.65625,
      "epoch": 0.6455732946298984,
      "grad_norm": 0.4012378372804515,
      "kl": 0.744140625,
      "learning_rate": 2.946286626483463e-07,
      "loss": 0.0298,
      "reward": 0.630859375,
      "reward_std": 0.18404811434447765,
      "rewards/correctness_reward_func": 0.171875,
      "rewards/strict_format_reward_func": 0.458984375,
      "step": 556
    },
    {
      "completion_length": 128.75390625,
      "epoch": 0.646734397677794,
      "grad_norm": 0.3075654967509157,
      "kl": 0.732421875,
      "learning_rate": 2.9291493989174233e-07,
      "loss": 0.0293,
      "reward": 0.642578125,
      "reward_std": 0.2429017424583435,
      "rewards/correctness_reward_func": 0.1796875,
      "rewards/strict_format_reward_func": 0.462890625,
      "step": 557
    },
    {
      "completion_length": 111.25,
      "epoch": 0.6478955007256894,
      "grad_norm": 0.3344369220791603,
      "kl": 0.7705078125,
      "learning_rate": 2.9120414853491573e-07,
      "loss": 0.0308,
      "reward": 0.705078125,
      "reward_std": 0.19529308751225471,
      "rewards/correctness_reward_func": 0.234375,
      "rewards/strict_format_reward_func": 0.470703125,
      "step": 558
    },
    {
      "completion_length": 93.69140625,
      "epoch": 0.6490566037735849,
      "grad_norm": 0.3134451908969852,
      "kl": 0.8515625,
      "learning_rate": 2.894963127950326e-07,
      "loss": 0.034,
      "reward": 0.548828125,
      "reward_std": 0.1425684168934822,
      "rewards/correctness_reward_func": 0.0703125,
      "rewards/strict_format_reward_func": 0.478515625,
      "step": 559
    },
    {
      "completion_length": 131.15625,
      "epoch": 0.6502177068214804,
      "grad_norm": 0.3759495135718941,
      "kl": 0.751953125,
      "learning_rate": 2.877914568474218e-07,
      "loss": 0.0301,
      "reward": 0.54296875,
      "reward_std": 0.1755007915198803,
      "rewards/correctness_reward_func": 0.078125,
      "rewards/strict_format_reward_func": 0.46484375,
      "step": 560
    },
    {
      "completion_length": 97.53125,
      "epoch": 0.6513788098693759,
      "grad_norm": 0.4252154608271463,
      "kl": 0.8330078125,
      "learning_rate": 2.860896048252305e-07,
      "loss": 0.0333,
      "reward": 0.693359375,
      "reward_std": 0.20679417625069618,
      "rewards/correctness_reward_func": 0.2265625,
      "rewards/strict_format_reward_func": 0.466796875,
      "step": 561
    },
    {
      "completion_length": 113.796875,
      "epoch": 0.6525399129172714,
      "grad_norm": 1.6638479120441956,
      "kl": 0.8017578125,
      "learning_rate": 2.843907808190849e-07,
      "loss": 0.0321,
      "reward": 0.63671875,
      "reward_std": 0.2197117656469345,
      "rewards/correctness_reward_func": 0.171875,
      "rewards/strict_format_reward_func": 0.46484375,
      "step": 562
    },
    {
      "completion_length": 125.1015625,
      "epoch": 0.6537010159651669,
      "grad_norm": 0.31143152290023274,
      "kl": 0.78125,
      "learning_rate": 2.8269500887674687e-07,
      "loss": 0.0312,
      "reward": 0.59375,
      "reward_std": 0.2034645527601242,
      "rewards/correctness_reward_func": 0.125,
      "rewards/strict_format_reward_func": 0.46875,
      "step": 563
    },
    {
      "completion_length": 60.859375,
      "epoch": 0.6548621190130625,
      "grad_norm": 0.2951948703992535,
      "kl": 0.8623046875,
      "learning_rate": 2.810023130027751e-07,
      "loss": 0.0345,
      "reward": 0.6484375,
      "reward_std": 0.15392476320266724,
      "rewards/correctness_reward_func": 0.1640625,
      "rewards/strict_format_reward_func": 0.484375,
      "step": 564
    },
    {
      "completion_length": 112.69921875,
      "epoch": 0.6560232220609579,
      "grad_norm": 0.35852376412198944,
      "kl": 0.779296875,
      "learning_rate": 2.793127171581854e-07,
      "loss": 0.0312,
      "reward": 0.72265625,
      "reward_std": 0.2782718874514103,
      "rewards/correctness_reward_func": 0.265625,
      "rewards/strict_format_reward_func": 0.45703125,
      "step": 565
    },
    {
      "completion_length": 100.54296875,
      "epoch": 0.6571843251088534,
      "grad_norm": 1.7472095383075714,
      "kl": 0.8642578125,
      "learning_rate": 2.7762624526011033e-07,
      "loss": 0.0346,
      "reward": 0.638671875,
      "reward_std": 0.24772042408585548,
      "rewards/correctness_reward_func": 0.171875,
      "rewards/strict_format_reward_func": 0.466796875,
      "step": 566
    },
    {
      "completion_length": 94.70703125,
      "epoch": 0.6583454281567489,
      "grad_norm": 0.33221993519231496,
      "kl": 0.796875,
      "learning_rate": 2.7594292118146133e-07,
      "loss": 0.0319,
      "reward": 0.677734375,
      "reward_std": 0.2187933810055256,
      "rewards/correctness_reward_func": 0.203125,
      "rewards/strict_format_reward_func": 0.474609375,
      "step": 567
    },
    {
      "completion_length": 111.25,
      "epoch": 0.6595065312046444,
      "grad_norm": 0.37554072866643406,
      "kl": 0.8359375,
      "learning_rate": 2.742627687505914e-07,
      "loss": 0.0335,
      "reward": 0.55859375,
      "reward_std": 0.1490851826965809,
      "rewards/correctness_reward_func": 0.09375,
      "rewards/strict_format_reward_func": 0.46484375,
      "step": 568
    },
    {
      "completion_length": 135.15234375,
      "epoch": 0.6606676342525399,
      "grad_norm": 0.31078338414130907,
      "kl": 0.8017578125,
      "learning_rate": 2.725858117509565e-07,
      "loss": 0.032,
      "reward": 0.55078125,
      "reward_std": 0.15206329245120287,
      "rewards/correctness_reward_func": 0.0859375,
      "rewards/strict_format_reward_func": 0.46484375,
      "step": 569
    },
    {
      "completion_length": 116.90234375,
      "epoch": 0.6618287373004355,
      "grad_norm": 0.7761591709804665,
      "kl": 0.90625,
      "learning_rate": 2.7091207392077975e-07,
      "loss": 0.0363,
      "reward": 0.60546875,
      "reward_std": 0.22258482966572046,
      "rewards/correctness_reward_func": 0.1328125,
      "rewards/strict_format_reward_func": 0.47265625,
      "step": 570
    },
    {
      "completion_length": 161.4765625,
      "epoch": 0.6629898403483309,
      "grad_norm": 0.33110926569559884,
      "kl": 0.8115234375,
      "learning_rate": 2.692415789527156e-07,
      "loss": 0.0325,
      "reward": 0.63671875,
      "reward_std": 0.2062407284975052,
      "rewards/correctness_reward_func": 0.1796875,
      "rewards/strict_format_reward_func": 0.45703125,
      "step": 571
    },
    {
      "completion_length": 109.30078125,
      "epoch": 0.6641509433962264,
      "grad_norm": 0.5937955608654133,
      "kl": 0.7333984375,
      "learning_rate": 2.675743504935135e-07,
      "loss": 0.0294,
      "reward": 0.587890625,
      "reward_std": 0.2096731960773468,
      "rewards/correctness_reward_func": 0.125,
      "rewards/strict_format_reward_func": 0.462890625,
      "step": 572
    },
    {
      "completion_length": 141.70703125,
      "epoch": 0.6653120464441219,
      "grad_norm": 0.3083899324453768,
      "kl": 0.8232421875,
      "learning_rate": 2.6591041214368383e-07,
      "loss": 0.0329,
      "reward": 0.62109375,
      "reward_std": 0.2068813145160675,
      "rewards/correctness_reward_func": 0.15625,
      "rewards/strict_format_reward_func": 0.46484375,
      "step": 573
    },
    {
      "completion_length": 117.8828125,
      "epoch": 0.6664731494920174,
      "grad_norm": 5.496557107193086,
      "kl": 1.4677734375,
      "learning_rate": 2.642497874571641e-07,
      "loss": 0.0586,
      "reward": 0.546875,
      "reward_std": 0.18655245006084442,
      "rewards/correctness_reward_func": 0.0859375,
      "rewards/strict_format_reward_func": 0.4609375,
      "step": 574
    },
    {
      "completion_length": 105.4921875,
      "epoch": 0.6676342525399129,
      "grad_norm": 0.9459378819495122,
      "kl": 0.837890625,
      "learning_rate": 2.6259249994098455e-07,
      "loss": 0.0335,
      "reward": 0.5703125,
      "reward_std": 0.20398172363638878,
      "rewards/correctness_reward_func": 0.1015625,
      "rewards/strict_format_reward_func": 0.46875,
      "step": 575
    },
    {
      "completion_length": 114.7421875,
      "epoch": 0.6687953555878084,
      "grad_norm": 0.5860644850597821,
      "kl": 0.7861328125,
      "learning_rate": 2.609385730549366e-07,
      "loss": 0.0314,
      "reward": 0.546875,
      "reward_std": 0.16403965651988983,
      "rewards/correctness_reward_func": 0.0859375,
      "rewards/strict_format_reward_func": 0.4609375,
      "step": 576
    },
    {
      "completion_length": 103.98828125,
      "epoch": 0.669956458635704,
      "grad_norm": 0.30321957508452857,
      "kl": 0.7509765625,
      "learning_rate": 2.5928803021123984e-07,
      "loss": 0.03,
      "reward": 0.521484375,
      "reward_std": 0.1570633351802826,
      "rewards/correctness_reward_func": 0.0546875,
      "rewards/strict_format_reward_func": 0.466796875,
      "step": 577
    },
    {
      "completion_length": 123.64453125,
      "epoch": 0.6711175616835994,
      "grad_norm": 0.4480179729355144,
      "kl": 0.7392578125,
      "learning_rate": 2.5764089477421065e-07,
      "loss": 0.0296,
      "reward": 0.509765625,
      "reward_std": 0.1547609455883503,
      "rewards/correctness_reward_func": 0.046875,
      "rewards/strict_format_reward_func": 0.462890625,
      "step": 578
    },
    {
      "completion_length": 140.44140625,
      "epoch": 0.6722786647314949,
      "grad_norm": 0.4127354979482719,
      "kl": 0.8017578125,
      "learning_rate": 2.559971900599326e-07,
      "loss": 0.0321,
      "reward": 0.5859375,
      "reward_std": 0.15745859593153,
      "rewards/correctness_reward_func": 0.125,
      "rewards/strict_format_reward_func": 0.4609375,
      "step": 579
    },
    {
      "completion_length": 134.2109375,
      "epoch": 0.6734397677793904,
      "grad_norm": 0.6899142664067114,
      "kl": 0.8291015625,
      "learning_rate": 2.543569393359243e-07,
      "loss": 0.0331,
      "reward": 0.578125,
      "reward_std": 0.2110317312180996,
      "rewards/correctness_reward_func": 0.1171875,
      "rewards/strict_format_reward_func": 0.4609375,
      "step": 580
    },
    {
      "completion_length": 129.54296875,
      "epoch": 0.6746008708272859,
      "grad_norm": 0.3747165190436483,
      "kl": 0.765625,
      "learning_rate": 2.5272016582081237e-07,
      "loss": 0.0306,
      "reward": 0.65234375,
      "reward_std": 0.24451905488967896,
      "rewards/correctness_reward_func": 0.1953125,
      "rewards/strict_format_reward_func": 0.45703125,
      "step": 581
    },
    {
      "completion_length": 92.94921875,
      "epoch": 0.6757619738751814,
      "grad_norm": 0.7183104698620123,
      "kl": 0.845703125,
      "learning_rate": 2.510868926840013e-07,
      "loss": 0.0338,
      "reward": 0.68359375,
      "reward_std": 0.2225848250091076,
      "rewards/correctness_reward_func": 0.2109375,
      "rewards/strict_format_reward_func": 0.47265625,
      "step": 582
    },
    {
      "completion_length": 71.83203125,
      "epoch": 0.676923076923077,
      "grad_norm": 0.32048135800050814,
      "kl": 0.7236328125,
      "learning_rate": 2.4945714304534583e-07,
      "loss": 0.029,
      "reward": 0.68359375,
      "reward_std": 0.2103765793144703,
      "rewards/correctness_reward_func": 0.203125,
      "rewards/strict_format_reward_func": 0.48046875,
      "step": 583
    },
    {
      "completion_length": 113.4921875,
      "epoch": 0.6780841799709725,
      "grad_norm": 0.3330261902397524,
      "kl": 0.7314453125,
      "learning_rate": 2.478309399748236e-07,
      "loss": 0.0293,
      "reward": 0.52734375,
      "reward_std": 0.1343449391424656,
      "rewards/correctness_reward_func": 0.0546875,
      "rewards/strict_format_reward_func": 0.47265625,
      "step": 584
    },
    {
      "completion_length": 176.30859375,
      "epoch": 0.6792452830188679,
      "grad_norm": 0.5550760405394316,
      "kl": 0.7978515625,
      "learning_rate": 2.462083064922087e-07,
      "loss": 0.0319,
      "reward": 0.572265625,
      "reward_std": 0.2500590980052948,
      "rewards/correctness_reward_func": 0.125,
      "rewards/strict_format_reward_func": 0.447265625,
      "step": 585
    },
    {
      "completion_length": 124.91015625,
      "epoch": 0.6804063860667634,
      "grad_norm": 0.3771609976174977,
      "kl": 0.8779296875,
      "learning_rate": 2.445892655667461e-07,
      "loss": 0.0351,
      "reward": 0.646484375,
      "reward_std": 0.1759117692708969,
      "rewards/correctness_reward_func": 0.1796875,
      "rewards/strict_format_reward_func": 0.466796875,
      "step": 586
    },
    {
      "completion_length": 110.48828125,
      "epoch": 0.6815674891146589,
      "grad_norm": 0.3555137507571062,
      "kl": 0.7646484375,
      "learning_rate": 2.429738401168259e-07,
      "loss": 0.0306,
      "reward": 0.599609375,
      "reward_std": 0.1680629849433899,
      "rewards/correctness_reward_func": 0.1328125,
      "rewards/strict_format_reward_func": 0.466796875,
      "step": 587
    },
    {
      "completion_length": 120.1875,
      "epoch": 0.6827285921625544,
      "grad_norm": 0.3358319267980713,
      "kl": 0.763671875,
      "learning_rate": 2.4136205300965916e-07,
      "loss": 0.0305,
      "reward": 0.587890625,
      "reward_std": 0.17168877366930246,
      "rewards/correctness_reward_func": 0.125,
      "rewards/strict_format_reward_func": 0.462890625,
      "step": 588
    },
    {
      "completion_length": 125.984375,
      "epoch": 0.68388969521045,
      "grad_norm": 0.3869178035583199,
      "kl": 0.7568359375,
      "learning_rate": 2.397539270609544e-07,
      "loss": 0.0303,
      "reward": 0.642578125,
      "reward_std": 0.21251928061246872,
      "rewards/correctness_reward_func": 0.1875,
      "rewards/strict_format_reward_func": 0.455078125,
      "step": 589
    },
    {
      "completion_length": 102.40625,
      "epoch": 0.6850507982583455,
      "grad_norm": 0.540197816244504,
      "kl": 0.8115234375,
      "learning_rate": 2.3814948503459503e-07,
      "loss": 0.0325,
      "reward": 0.576171875,
      "reward_std": 0.1830328367650509,
      "rewards/correctness_reward_func": 0.1015625,
      "rewards/strict_format_reward_func": 0.474609375,
      "step": 590
    },
    {
      "completion_length": 113.63671875,
      "epoch": 0.6862119013062409,
      "grad_norm": 0.6794056586284541,
      "kl": 0.8212890625,
      "learning_rate": 2.3654874964231514e-07,
      "loss": 0.0328,
      "reward": 0.61328125,
      "reward_std": 0.16177582368254662,
      "rewards/correctness_reward_func": 0.140625,
      "rewards/strict_format_reward_func": 0.47265625,
      "step": 591
    },
    {
      "completion_length": 135.59375,
      "epoch": 0.6873730043541364,
      "grad_norm": 0.4533405370760341,
      "kl": 0.7822265625,
      "learning_rate": 2.3495174354338081e-07,
      "loss": 0.0313,
      "reward": 0.6015625,
      "reward_std": 0.2237934246659279,
      "rewards/correctness_reward_func": 0.140625,
      "rewards/strict_format_reward_func": 0.4609375,
      "step": 592
    },
    {
      "completion_length": 130.640625,
      "epoch": 0.6885341074020319,
      "grad_norm": 1.5709007087190123,
      "kl": 0.9248046875,
      "learning_rate": 2.3335848934426743e-07,
      "loss": 0.037,
      "reward": 0.6015625,
      "reward_std": 0.21124077215790749,
      "rewards/correctness_reward_func": 0.1328125,
      "rewards/strict_format_reward_func": 0.46875,
      "step": 593
    },
    {
      "completion_length": 147.8125,
      "epoch": 0.6896952104499274,
      "grad_norm": 0.38044053562473673,
      "kl": 0.8388671875,
      "learning_rate": 2.3176900959834e-07,
      "loss": 0.0336,
      "reward": 0.5859375,
      "reward_std": 0.1877090372145176,
      "rewards/correctness_reward_func": 0.125,
      "rewards/strict_format_reward_func": 0.4609375,
      "step": 594
    },
    {
      "completion_length": 74.2734375,
      "epoch": 0.690856313497823,
      "grad_norm": 0.37860644515599634,
      "kl": 0.8515625,
      "learning_rate": 2.3018332680553477e-07,
      "loss": 0.0341,
      "reward": 0.591796875,
      "reward_std": 0.15892481058835983,
      "rewards/correctness_reward_func": 0.1171875,
      "rewards/strict_format_reward_func": 0.474609375,
      "step": 595
    },
    {
      "completion_length": 112.4375,
      "epoch": 0.6920174165457185,
      "grad_norm": 0.8378828702264284,
      "kl": 0.8515625,
      "learning_rate": 2.2860146341203934e-07,
      "loss": 0.0341,
      "reward": 0.625,
      "reward_std": 0.14115743339061737,
      "rewards/correctness_reward_func": 0.1484375,
      "rewards/strict_format_reward_func": 0.4765625,
      "step": 596
    },
    {
      "completion_length": 104.59765625,
      "epoch": 0.693178519593614,
      "grad_norm": 0.5810522013869516,
      "kl": 0.7666015625,
      "learning_rate": 2.2702344180997647e-07,
      "loss": 0.0306,
      "reward": 0.546875,
      "reward_std": 0.1475684605538845,
      "rewards/correctness_reward_func": 0.0859375,
      "rewards/strict_format_reward_func": 0.4609375,
      "step": 597
    },
    {
      "completion_length": 102.33203125,
      "epoch": 0.6943396226415094,
      "grad_norm": 0.3462812805687336,
      "kl": 0.7490234375,
      "learning_rate": 2.2544928433708565e-07,
      "loss": 0.03,
      "reward": 0.625,
      "reward_std": 0.1645168662071228,
      "rewards/correctness_reward_func": 0.1484375,
      "rewards/strict_format_reward_func": 0.4765625,
      "step": 598
    },
    {
      "completion_length": 72.26171875,
      "epoch": 0.6955007256894049,
      "grad_norm": 0.6395028028106833,
      "kl": 0.96484375,
      "learning_rate": 2.2387901327640756e-07,
      "loss": 0.0386,
      "reward": 0.576171875,
      "reward_std": 0.0876355916261673,
      "rewards/correctness_reward_func": 0.09375,
      "rewards/strict_format_reward_func": 0.482421875,
      "step": 599
    },
    {
      "completion_length": 80.95703125,
      "epoch": 0.6966618287373004,
      "grad_norm": 0.2992491852330507,
      "kl": 0.740234375,
      "learning_rate": 2.2231265085596934e-07,
      "loss": 0.0296,
      "reward": 0.5546875,
      "reward_std": 0.1241152435541153,
      "rewards/correctness_reward_func": 0.078125,
      "rewards/strict_format_reward_func": 0.4765625,
      "step": 600
    },
    {
      "completion_length": 73.4140625,
      "epoch": 0.6978229317851959,
      "grad_norm": 0.5129742207056275,
      "kl": 0.822265625,
      "learning_rate": 2.2075021924846847e-07,
      "loss": 0.0329,
      "reward": 0.681640625,
      "reward_std": 0.2886443957686424,
      "rewards/correctness_reward_func": 0.2109375,
      "rewards/strict_format_reward_func": 0.470703125,
      "step": 601
    },
    {
      "completion_length": 150.35546875,
      "epoch": 0.6989840348330915,
      "grad_norm": 0.3018666082484326,
      "kl": 0.76171875,
      "learning_rate": 2.191917405709598e-07,
      "loss": 0.0305,
      "reward": 0.548828125,
      "reward_std": 0.17431792989373207,
      "rewards/correctness_reward_func": 0.0859375,
      "rewards/strict_format_reward_func": 0.462890625,
      "step": 602
    },
    {
      "completion_length": 142.640625,
      "epoch": 0.700145137880987,
      "grad_norm": 0.45343471735700863,
      "kl": 0.765625,
      "learning_rate": 2.1763723688454294e-07,
      "loss": 0.0306,
      "reward": 0.56640625,
      "reward_std": 0.1462293416261673,
      "rewards/correctness_reward_func": 0.1015625,
      "rewards/strict_format_reward_func": 0.46484375,
      "step": 603
    },
    {
      "completion_length": 109.328125,
      "epoch": 0.7013062409288824,
      "grad_norm": 0.2774407307493229,
      "kl": 0.748046875,
      "learning_rate": 2.1608673019404865e-07,
      "loss": 0.03,
      "reward": 0.595703125,
      "reward_std": 0.18677525594830513,
      "rewards/correctness_reward_func": 0.125,
      "rewards/strict_format_reward_func": 0.470703125,
      "step": 604
    },
    {
      "completion_length": 90.23828125,
      "epoch": 0.7024673439767779,
      "grad_norm": 0.37352016460296883,
      "kl": 0.8818359375,
      "learning_rate": 2.145402424477283e-07,
      "loss": 0.0353,
      "reward": 0.537109375,
      "reward_std": 0.1471574790775776,
      "rewards/correctness_reward_func": 0.0625,
      "rewards/strict_format_reward_func": 0.474609375,
      "step": 605
    },
    {
      "completion_length": 87.64453125,
      "epoch": 0.7036284470246734,
      "grad_norm": 0.5449127684339466,
      "kl": 0.77734375,
      "learning_rate": 2.129977955369432e-07,
      "loss": 0.0311,
      "reward": 0.595703125,
      "reward_std": 0.15903327241539955,
      "rewards/correctness_reward_func": 0.1171875,
      "rewards/strict_format_reward_func": 0.478515625,
      "step": 606
    },
    {
      "completion_length": 83.5390625,
      "epoch": 0.7047895500725689,
      "grad_norm": 0.4137964394650753,
      "kl": 0.7587890625,
      "learning_rate": 2.114594112958543e-07,
      "loss": 0.0303,
      "reward": 0.669921875,
      "reward_std": 0.1266980916261673,
      "rewards/correctness_reward_func": 0.1953125,
      "rewards/strict_format_reward_func": 0.474609375,
      "step": 607
    },
    {
      "completion_length": 95.5078125,
      "epoch": 0.7059506531204645,
      "grad_norm": 0.4026269789728574,
      "kl": 0.8671875,
      "learning_rate": 2.0992511150111298e-07,
      "loss": 0.0347,
      "reward": 0.64453125,
      "reward_std": 0.1741773895919323,
      "rewards/correctness_reward_func": 0.1640625,
      "rewards/strict_format_reward_func": 0.48046875,
      "step": 608
    },
    {
      "completion_length": 105.2109375,
      "epoch": 0.70711175616836,
      "grad_norm": 0.3106950074100804,
      "kl": 0.724609375,
      "learning_rate": 2.0839491787155383e-07,
      "loss": 0.029,
      "reward": 0.59765625,
      "reward_std": 0.1454593874514103,
      "rewards/correctness_reward_func": 0.125,
      "rewards/strict_format_reward_func": 0.47265625,
      "step": 609
    },
    {
      "completion_length": 119.51953125,
      "epoch": 0.7082728592162555,
      "grad_norm": 10.781887103639233,
      "kl": 1.60546875,
      "learning_rate": 2.0686885206788563e-07,
      "loss": 0.0642,
      "reward": 0.58203125,
      "reward_std": 0.1908176653087139,
      "rewards/correctness_reward_func": 0.1171875,
      "rewards/strict_format_reward_func": 0.46484375,
      "step": 610
    },
    {
      "completion_length": 104.62109375,
      "epoch": 0.7094339622641509,
      "grad_norm": 0.30432234906251737,
      "kl": 0.755859375,
      "learning_rate": 2.0534693569238648e-07,
      "loss": 0.0302,
      "reward": 0.55078125,
      "reward_std": 0.19439855962991714,
      "rewards/correctness_reward_func": 0.0859375,
      "rewards/strict_format_reward_func": 0.46484375,
      "step": 611
    },
    {
      "completion_length": 110.07421875,
      "epoch": 0.7105950653120464,
      "grad_norm": 0.42086764072830113,
      "kl": 0.8095703125,
      "learning_rate": 2.0382919028859603e-07,
      "loss": 0.0324,
      "reward": 0.650390625,
      "reward_std": 0.24562706053256989,
      "rewards/correctness_reward_func": 0.1875,
      "rewards/strict_format_reward_func": 0.462890625,
      "step": 612
    },
    {
      "completion_length": 65.91796875,
      "epoch": 0.7117561683599419,
      "grad_norm": 0.2697629145553527,
      "kl": 0.798828125,
      "learning_rate": 2.0231563734101242e-07,
      "loss": 0.032,
      "reward": 0.568359375,
      "reward_std": 0.1592714935541153,
      "rewards/correctness_reward_func": 0.0859375,
      "rewards/strict_format_reward_func": 0.482421875,
      "step": 613
    },
    {
      "completion_length": 104.83203125,
      "epoch": 0.7129172714078374,
      "grad_norm": 0.4367888289791503,
      "kl": 0.802734375,
      "learning_rate": 2.0080629827478752e-07,
      "loss": 0.0321,
      "reward": 0.56640625,
      "reward_std": 0.1809118166565895,
      "rewards/correctness_reward_func": 0.1015625,
      "rewards/strict_format_reward_func": 0.46484375,
      "step": 614
    },
    {
      "completion_length": 106.74609375,
      "epoch": 0.714078374455733,
      "grad_norm": 0.27971706332267343,
      "kl": 0.7548828125,
      "learning_rate": 1.9930119445542225e-07,
      "loss": 0.0302,
      "reward": 0.6640625,
      "reward_std": 0.22319775074720383,
      "rewards/correctness_reward_func": 0.1875,
      "rewards/strict_format_reward_func": 0.4765625,
      "step": 615
    },
    {
      "completion_length": 97.359375,
      "epoch": 0.7152394775036285,
      "grad_norm": 0.3503713788853395,
      "kl": 0.7861328125,
      "learning_rate": 1.978003471884665e-07,
      "loss": 0.0315,
      "reward": 0.650390625,
      "reward_std": 0.23462742194533348,
      "rewards/correctness_reward_func": 0.1796875,
      "rewards/strict_format_reward_func": 0.470703125,
      "step": 616
    },
    {
      "completion_length": 87.03125,
      "epoch": 0.716400580551524,
      "grad_norm": 0.2781016717749834,
      "kl": 0.80078125,
      "learning_rate": 1.963037777192162e-07,
      "loss": 0.032,
      "reward": 0.611328125,
      "reward_std": 0.21262994781136513,
      "rewards/correctness_reward_func": 0.1328125,
      "rewards/strict_format_reward_func": 0.478515625,
      "step": 617
    },
    {
      "completion_length": 72.4453125,
      "epoch": 0.7175616835994194,
      "grad_norm": 0.27247453589769716,
      "kl": 0.7724609375,
      "learning_rate": 1.9481150723241236e-07,
      "loss": 0.0309,
      "reward": 0.5703125,
      "reward_std": 0.1274171955883503,
      "rewards/correctness_reward_func": 0.0859375,
      "rewards/strict_format_reward_func": 0.484375,
      "step": 618
    },
    {
      "completion_length": 118.8671875,
      "epoch": 0.7187227866473149,
      "grad_norm": 0.37415980905497,
      "kl": 0.822265625,
      "learning_rate": 1.933235568519418e-07,
      "loss": 0.0329,
      "reward": 0.5625,
      "reward_std": 0.1865161508321762,
      "rewards/correctness_reward_func": 0.0859375,
      "rewards/strict_format_reward_func": 0.4765625,
      "step": 619
    },
    {
      "completion_length": 125.58203125,
      "epoch": 0.7198838896952104,
      "grad_norm": 0.48696811711873145,
      "kl": 0.8173828125,
      "learning_rate": 1.918399476405378e-07,
      "loss": 0.0327,
      "reward": 0.654296875,
      "reward_std": 0.26282261684536934,
      "rewards/correctness_reward_func": 0.1875,
      "rewards/strict_format_reward_func": 0.466796875,
      "step": 620
    },
    {
      "completion_length": 137.51171875,
      "epoch": 0.721044992743106,
      "grad_norm": 0.46046953819836745,
      "kl": 0.7587890625,
      "learning_rate": 1.903607005994825e-07,
      "loss": 0.0304,
      "reward": 0.60546875,
      "reward_std": 0.2034488432109356,
      "rewards/correctness_reward_func": 0.1484375,
      "rewards/strict_format_reward_func": 0.45703125,
      "step": 621
    },
    {
      "completion_length": 143.83984375,
      "epoch": 0.7222060957910015,
      "grad_norm": 0.4022310273441478,
      "kl": 0.818359375,
      "learning_rate": 1.8888583666830876e-07,
      "loss": 0.0328,
      "reward": 0.61328125,
      "reward_std": 0.1825055480003357,
      "rewards/correctness_reward_func": 0.15625,
      "rewards/strict_format_reward_func": 0.45703125,
      "step": 622
    },
    {
      "completion_length": 130.59375,
      "epoch": 0.723367198838897,
      "grad_norm": 0.35507879719847374,
      "kl": 0.830078125,
      "learning_rate": 1.8741537672450402e-07,
      "loss": 0.0332,
      "reward": 0.689453125,
      "reward_std": 0.2737841531634331,
      "rewards/correctness_reward_func": 0.2265625,
      "rewards/strict_format_reward_func": 0.462890625,
      "step": 623
    },
    {
      "completion_length": 143.5625,
      "epoch": 0.7245283018867924,
      "grad_norm": 0.3620776833289833,
      "kl": 0.8056640625,
      "learning_rate": 1.8594934158321568e-07,
      "loss": 0.0322,
      "reward": 0.630859375,
      "reward_std": 0.2736899144947529,
      "rewards/correctness_reward_func": 0.1640625,
      "rewards/strict_format_reward_func": 0.466796875,
      "step": 624
    },
    {
      "completion_length": 145.53515625,
      "epoch": 0.7256894049346879,
      "grad_norm": 0.4945101469082341,
      "kl": 0.8701171875,
      "learning_rate": 1.84487751996955e-07,
      "loss": 0.0348,
      "reward": 0.623046875,
      "reward_std": 0.17498211562633514,
      "rewards/correctness_reward_func": 0.1640625,
      "rewards/strict_format_reward_func": 0.458984375,
      "step": 625
    },
    {
      "completion_length": 88.48828125,
      "epoch": 0.7268505079825834,
      "grad_norm": 0.3989227075920521,
      "kl": 0.8447265625,
      "learning_rate": 1.8303062865530404e-07,
      "loss": 0.0338,
      "reward": 0.65625,
      "reward_std": 0.2573458179831505,
      "rewards/correctness_reward_func": 0.1796875,
      "rewards/strict_format_reward_func": 0.4765625,
      "step": 626
    },
    {
      "completion_length": 103.88671875,
      "epoch": 0.728011611030479,
      "grad_norm": 0.3531836802235862,
      "kl": 0.8203125,
      "learning_rate": 1.8157799218462334e-07,
      "loss": 0.0328,
      "reward": 0.59765625,
      "reward_std": 0.163177739828825,
      "rewards/correctness_reward_func": 0.125,
      "rewards/strict_format_reward_func": 0.47265625,
      "step": 627
    },
    {
      "completion_length": 119.58984375,
      "epoch": 0.7291727140783745,
      "grad_norm": 0.34465585850141295,
      "kl": 0.8095703125,
      "learning_rate": 1.8012986314775885e-07,
      "loss": 0.0324,
      "reward": 0.619140625,
      "reward_std": 0.17278257012367249,
      "rewards/correctness_reward_func": 0.1484375,
      "rewards/strict_format_reward_func": 0.470703125,
      "step": 628
    },
    {
      "completion_length": 67.828125,
      "epoch": 0.73033381712627,
      "grad_norm": 1.1066688406357255,
      "kl": 0.97265625,
      "learning_rate": 1.786862620437515e-07,
      "loss": 0.0389,
      "reward": 0.6484375,
      "reward_std": 0.24062702432274818,
      "rewards/correctness_reward_func": 0.171875,
      "rewards/strict_format_reward_func": 0.4765625,
      "step": 629
    },
    {
      "completion_length": 62.18359375,
      "epoch": 0.7314949201741655,
      "grad_norm": 0.3072708372985615,
      "kl": 0.8173828125,
      "learning_rate": 1.7724720930754712e-07,
      "loss": 0.0327,
      "reward": 0.580078125,
      "reward_std": 0.1829180270433426,
      "rewards/correctness_reward_func": 0.1015625,
      "rewards/strict_format_reward_func": 0.478515625,
      "step": 630
    },
    {
      "completion_length": 126.93359375,
      "epoch": 0.7326560232220609,
      "grad_norm": 0.45721087328589566,
      "kl": 0.806640625,
      "learning_rate": 1.7581272530970663e-07,
      "loss": 0.0323,
      "reward": 0.59765625,
      "reward_std": 0.24525238201022148,
      "rewards/correctness_reward_func": 0.1328125,
      "rewards/strict_format_reward_func": 0.46484375,
      "step": 631
    },
    {
      "completion_length": 112.29296875,
      "epoch": 0.7338171262699564,
      "grad_norm": 0.4069211334828044,
      "kl": 0.822265625,
      "learning_rate": 1.7438283035611846e-07,
      "loss": 0.0329,
      "reward": 0.6015625,
      "reward_std": 0.1910109855234623,
      "rewards/correctness_reward_func": 0.140625,
      "rewards/strict_format_reward_func": 0.4609375,
      "step": 632
    },
    {
      "completion_length": 78.06640625,
      "epoch": 0.734978229317852,
      "grad_norm": 0.3872774627910471,
      "kl": 0.841796875,
      "learning_rate": 1.7295754468771023e-07,
      "loss": 0.0337,
      "reward": 0.6875,
      "reward_std": 0.13423013128340244,
      "rewards/correctness_reward_func": 0.2109375,
      "rewards/strict_format_reward_func": 0.4765625,
      "step": 633
    },
    {
      "completion_length": 85.40234375,
      "epoch": 0.7361393323657475,
      "grad_norm": 0.28775416216569427,
      "kl": 0.7587890625,
      "learning_rate": 1.7153688848016273e-07,
      "loss": 0.0304,
      "reward": 0.546875,
      "reward_std": 0.14304219186306,
      "rewards/correctness_reward_func": 0.0703125,
      "rewards/strict_format_reward_func": 0.4765625,
      "step": 634
    },
    {
      "completion_length": 91.6328125,
      "epoch": 0.737300435413643,
      "grad_norm": 0.3652872991766868,
      "kl": 0.8759765625,
      "learning_rate": 1.7012088184362466e-07,
      "loss": 0.035,
      "reward": 0.697265625,
      "reward_std": 0.2570653632283211,
      "rewards/correctness_reward_func": 0.2265625,
      "rewards/strict_format_reward_func": 0.470703125,
      "step": 635
    },
    {
      "completion_length": 97.35546875,
      "epoch": 0.7384615384615385,
      "grad_norm": 0.35834731218277194,
      "kl": 0.8310546875,
      "learning_rate": 1.6870954482242706e-07,
      "loss": 0.0333,
      "reward": 0.67578125,
      "reward_std": 0.19375202432274818,
      "rewards/correctness_reward_func": 0.203125,
      "rewards/strict_format_reward_func": 0.47265625,
      "step": 636
    },
    {
      "completion_length": 82.265625,
      "epoch": 0.7396226415094339,
      "grad_norm": 0.42021111102788483,
      "kl": 0.8154296875,
      "learning_rate": 1.6730289739480015e-07,
      "loss": 0.0326,
      "reward": 0.58984375,
      "reward_std": 0.10639689117670059,
      "rewards/correctness_reward_func": 0.109375,
      "rewards/strict_format_reward_func": 0.48046875,
      "step": 637
    },
    {
      "completion_length": 119.06640625,
      "epoch": 0.7407837445573294,
      "grad_norm": 0.5073274675354564,
      "kl": 0.94921875,
      "learning_rate": 1.6590095947259082e-07,
      "loss": 0.038,
      "reward": 0.599609375,
      "reward_std": 0.1641058810055256,
      "rewards/correctness_reward_func": 0.1328125,
      "rewards/strict_format_reward_func": 0.466796875,
      "step": 638
    },
    {
      "completion_length": 102.80859375,
      "epoch": 0.7419448476052249,
      "grad_norm": 0.6166927982454318,
      "kl": 0.8076171875,
      "learning_rate": 1.6450375090098002e-07,
      "loss": 0.0323,
      "reward": 0.59375,
      "reward_std": 0.16834116727113724,
      "rewards/correctness_reward_func": 0.1328125,
      "rewards/strict_format_reward_func": 0.4609375,
      "step": 639
    },
    {
      "completion_length": 122.734375,
      "epoch": 0.7431059506531205,
      "grad_norm": 0.4769120017126504,
      "kl": 0.9443359375,
      "learning_rate": 1.631112914582022e-07,
      "loss": 0.0378,
      "reward": 0.568359375,
      "reward_std": 0.1784074828028679,
      "rewards/correctness_reward_func": 0.1015625,
      "rewards/strict_format_reward_func": 0.466796875,
      "step": 640
    },
    {
      "completion_length": 95.71484375,
      "epoch": 0.744267053701016,
      "grad_norm": 1.2684641303125554,
      "kl": 0.88671875,
      "learning_rate": 1.6172360085526566e-07,
      "loss": 0.0355,
      "reward": 0.634765625,
      "reward_std": 0.2206934131681919,
      "rewards/correctness_reward_func": 0.15625,
      "rewards/strict_format_reward_func": 0.478515625,
      "step": 641
    },
    {
      "completion_length": 118.07421875,
      "epoch": 0.7454281567489115,
      "grad_norm": 0.40524408731497596,
      "kl": 0.904296875,
      "learning_rate": 1.6034069873567303e-07,
      "loss": 0.0362,
      "reward": 0.607421875,
      "reward_std": 0.1679844707250595,
      "rewards/correctness_reward_func": 0.140625,
      "rewards/strict_format_reward_func": 0.466796875,
      "step": 642
    },
    {
      "completion_length": 73.421875,
      "epoch": 0.746589259796807,
      "grad_norm": 0.3988212797379941,
      "kl": 0.85546875,
      "learning_rate": 1.5896260467514332e-07,
      "loss": 0.0342,
      "reward": 0.63671875,
      "reward_std": 0.2374555952847004,
      "rewards/correctness_reward_func": 0.1640625,
      "rewards/strict_format_reward_func": 0.47265625,
      "step": 643
    },
    {
      "completion_length": 105.23046875,
      "epoch": 0.7477503628447024,
      "grad_norm": 0.2995251915940851,
      "kl": 0.857421875,
      "learning_rate": 1.575893381813348e-07,
      "loss": 0.0343,
      "reward": 0.619140625,
      "reward_std": 0.164666797965765,
      "rewards/correctness_reward_func": 0.1484375,
      "rewards/strict_format_reward_func": 0.470703125,
      "step": 644
    },
    {
      "completion_length": 105.09765625,
      "epoch": 0.7489114658925979,
      "grad_norm": 0.35434090386261663,
      "kl": 0.85546875,
      "learning_rate": 1.5622091869356934e-07,
      "loss": 0.0342,
      "reward": 0.537109375,
      "reward_std": 0.12331762164831161,
      "rewards/correctness_reward_func": 0.0703125,
      "rewards/strict_format_reward_func": 0.466796875,
      "step": 645
    },
    {
      "completion_length": 93.640625,
      "epoch": 0.7500725689404935,
      "grad_norm": 0.26450183122824994,
      "kl": 0.798828125,
      "learning_rate": 1.5485736558255696e-07,
      "loss": 0.032,
      "reward": 0.6171875,
      "reward_std": 0.1988392099738121,
      "rewards/correctness_reward_func": 0.140625,
      "rewards/strict_format_reward_func": 0.4765625,
      "step": 646
    },
    {
      "completion_length": 110.05078125,
      "epoch": 0.751233671988389,
      "grad_norm": 0.39376375602639996,
      "kl": 0.7685546875,
      "learning_rate": 1.534986981501205e-07,
      "loss": 0.0308,
      "reward": 0.5625,
      "reward_std": 0.13168952241539955,
      "rewards/correctness_reward_func": 0.09375,
      "rewards/strict_format_reward_func": 0.46875,
      "step": 647
    },
    {
      "completion_length": 99.66796875,
      "epoch": 0.7523947750362845,
      "grad_norm": 0.4610447092941834,
      "kl": 0.8623046875,
      "learning_rate": 1.521449356289245e-07,
      "loss": 0.0345,
      "reward": 0.6328125,
      "reward_std": 0.1877090372145176,
      "rewards/correctness_reward_func": 0.1640625,
      "rewards/strict_format_reward_func": 0.46875,
      "step": 648
    },
    {
      "completion_length": 148.6640625,
      "epoch": 0.75355587808418,
      "grad_norm": 0.3821358699546131,
      "kl": 0.8388671875,
      "learning_rate": 1.5079609718220166e-07,
      "loss": 0.0336,
      "reward": 0.568359375,
      "reward_std": 0.21911904774606228,
      "rewards/correctness_reward_func": 0.109375,
      "rewards/strict_format_reward_func": 0.458984375,
      "step": 649
    },
    {
      "completion_length": 97.39453125,
      "epoch": 0.7547169811320755,
      "grad_norm": 0.39162434384391126,
      "kl": 0.86328125,
      "learning_rate": 1.4945220190348102e-07,
      "loss": 0.0345,
      "reward": 0.619140625,
      "reward_std": 0.1525527834892273,
      "rewards/correctness_reward_func": 0.140625,
      "rewards/strict_format_reward_func": 0.478515625,
      "step": 650
    },
    {
      "completion_length": 153.38671875,
      "epoch": 0.7558780841799709,
      "grad_norm": 0.31183397484407377,
      "kl": 0.7568359375,
      "learning_rate": 1.4811326881631936e-07,
      "loss": 0.0303,
      "reward": 0.591796875,
      "reward_std": 0.1777455434203148,
      "rewards/correctness_reward_func": 0.1328125,
      "rewards/strict_format_reward_func": 0.458984375,
      "step": 651
    },
    {
      "completion_length": 108.91015625,
      "epoch": 0.7570391872278665,
      "grad_norm": 1.192821656694925,
      "kl": 0.9521484375,
      "learning_rate": 1.4677931687403046e-07,
      "loss": 0.0381,
      "reward": 0.615234375,
      "reward_std": 0.1413598209619522,
      "rewards/correctness_reward_func": 0.1484375,
      "rewards/strict_format_reward_func": 0.466796875,
      "step": 652
    },
    {
      "completion_length": 87.5,
      "epoch": 0.758200290275762,
      "grad_norm": 0.2829598124323536,
      "kl": 0.80859375,
      "learning_rate": 1.454503649594176e-07,
      "loss": 0.0323,
      "reward": 0.630859375,
      "reward_std": 0.1457555592060089,
      "rewards/correctness_reward_func": 0.15625,
      "rewards/strict_format_reward_func": 0.474609375,
      "step": 653
    },
    {
      "completion_length": 73.93359375,
      "epoch": 0.7593613933236575,
      "grad_norm": 0.2916766549828714,
      "kl": 0.798828125,
      "learning_rate": 1.441264318845058e-07,
      "loss": 0.0319,
      "reward": 0.6015625,
      "reward_std": 0.2035430744290352,
      "rewards/correctness_reward_func": 0.1171875,
      "rewards/strict_format_reward_func": 0.484375,
      "step": 654
    },
    {
      "completion_length": 78.125,
      "epoch": 0.760522496371553,
      "grad_norm": 0.3063656804899638,
      "kl": 0.8583984375,
      "learning_rate": 1.4280753639027565e-07,
      "loss": 0.0344,
      "reward": 0.595703125,
      "reward_std": 0.1648758314549923,
      "rewards/correctness_reward_func": 0.125,
      "rewards/strict_format_reward_func": 0.470703125,
      "step": 655
    },
    {
      "completion_length": 91.37890625,
      "epoch": 0.7616835994194485,
      "grad_norm": 0.34808719658813214,
      "kl": 0.8515625,
      "learning_rate": 1.4149369714639852e-07,
      "loss": 0.034,
      "reward": 0.6640625,
      "reward_std": 0.21233456209301949,
      "rewards/correctness_reward_func": 0.1875,
      "rewards/strict_format_reward_func": 0.4765625,
      "step": 656
    },
    {
      "completion_length": 123.1640625,
      "epoch": 0.7628447024673439,
      "grad_norm": 1.5186351718866946,
      "kl": 0.8779296875,
      "learning_rate": 1.4018493275097136e-07,
      "loss": 0.0352,
      "reward": 0.6640625,
      "reward_std": 0.20601226761937141,
      "rewards/correctness_reward_func": 0.1953125,
      "rewards/strict_format_reward_func": 0.46875,
      "step": 657
    },
    {
      "completion_length": 101.6640625,
      "epoch": 0.7640058055152394,
      "grad_norm": 0.3170824302287278,
      "kl": 0.7978515625,
      "learning_rate": 1.388812617302541e-07,
      "loss": 0.0319,
      "reward": 0.591796875,
      "reward_std": 0.12890625,
      "rewards/correctness_reward_func": 0.1171875,
      "rewards/strict_format_reward_func": 0.474609375,
      "step": 658
    },
    {
      "completion_length": 95.109375,
      "epoch": 0.765166908563135,
      "grad_norm": 0.29987573383614635,
      "kl": 0.80078125,
      "learning_rate": 1.3758270253840741e-07,
      "loss": 0.032,
      "reward": 0.626953125,
      "reward_std": 0.2196938581764698,
      "rewards/correctness_reward_func": 0.15625,
      "rewards/strict_format_reward_func": 0.470703125,
      "step": 659
    },
    {
      "completion_length": 85.1171875,
      "epoch": 0.7663280116110305,
      "grad_norm": 0.3204939090437886,
      "kl": 0.828125,
      "learning_rate": 1.3628927355723113e-07,
      "loss": 0.0331,
      "reward": 0.671875,
      "reward_std": 0.2067665085196495,
      "rewards/correctness_reward_func": 0.1953125,
      "rewards/strict_format_reward_func": 0.4765625,
      "step": 660
    },
    {
      "completion_length": 60.2421875,
      "epoch": 0.767489114658926,
      "grad_norm": 0.25940530528077377,
      "kl": 0.8427734375,
      "learning_rate": 1.3500099309590396e-07,
      "loss": 0.0337,
      "reward": 0.697265625,
      "reward_std": 0.195916797965765,
      "rewards/correctness_reward_func": 0.2109375,
      "rewards/strict_format_reward_func": 0.486328125,
      "step": 661
    },
    {
      "completion_length": 129.23828125,
      "epoch": 0.7686502177068215,
      "grad_norm": 0.38255708042283804,
      "kl": 0.9130859375,
      "learning_rate": 1.337178793907252e-07,
      "loss": 0.0366,
      "reward": 0.669921875,
      "reward_std": 0.2848043739795685,
      "rewards/correctness_reward_func": 0.2109375,
      "rewards/strict_format_reward_func": 0.458984375,
      "step": 662
    },
    {
      "completion_length": 133.609375,
      "epoch": 0.769811320754717,
      "grad_norm": 0.3634385778266288,
      "kl": 0.8583984375,
      "learning_rate": 1.3243995060485537e-07,
      "loss": 0.0344,
      "reward": 0.689453125,
      "reward_std": 0.2657989040017128,
      "rewards/correctness_reward_func": 0.2265625,
      "rewards/strict_format_reward_func": 0.462890625,
      "step": 663
    },
    {
      "completion_length": 128.98828125,
      "epoch": 0.7709724238026124,
      "grad_norm": 0.3393260481215263,
      "kl": 0.84375,
      "learning_rate": 1.311672248280597e-07,
      "loss": 0.0338,
      "reward": 0.61328125,
      "reward_std": 0.20212543942034245,
      "rewards/correctness_reward_func": 0.1484375,
      "rewards/strict_format_reward_func": 0.46484375,
      "step": 664
    },
    {
      "completion_length": 79.77734375,
      "epoch": 0.772133526850508,
      "grad_norm": 0.4273347901612395,
      "kl": 0.828125,
      "learning_rate": 1.2989972007645262e-07,
      "loss": 0.0331,
      "reward": 0.669921875,
      "reward_std": 0.1436464935541153,
      "rewards/correctness_reward_func": 0.1953125,
      "rewards/strict_format_reward_func": 0.474609375,
      "step": 665
    },
    {
      "completion_length": 96.37890625,
      "epoch": 0.7732946298984035,
      "grad_norm": 0.3778672477337748,
      "kl": 0.8916015625,
      "learning_rate": 1.2863745429224142e-07,
      "loss": 0.0357,
      "reward": 0.583984375,
      "reward_std": 0.11151173710823059,
      "rewards/correctness_reward_func": 0.109375,
      "rewards/strict_format_reward_func": 0.474609375,
      "step": 666
    },
    {
      "completion_length": 120.078125,
      "epoch": 0.774455732946299,
      "grad_norm": 0.368322742002669,
      "kl": 0.828125,
      "learning_rate": 1.2738044534347365e-07,
      "loss": 0.0331,
      "reward": 0.619140625,
      "reward_std": 0.11800083518028259,
      "rewards/correctness_reward_func": 0.1484375,
      "rewards/strict_format_reward_func": 0.470703125,
      "step": 667
    },
    {
      "completion_length": 129.0,
      "epoch": 0.7756168359941945,
      "grad_norm": 0.3858423079363714,
      "kl": 0.8369140625,
      "learning_rate": 1.2612871102378303e-07,
      "loss": 0.0334,
      "reward": 0.62890625,
      "reward_std": 0.2507419101893902,
      "rewards/correctness_reward_func": 0.1640625,
      "rewards/strict_format_reward_func": 0.46484375,
      "step": 668
    },
    {
      "completion_length": 122.16796875,
      "epoch": 0.77677793904209,
      "grad_norm": 0.38799518590542537,
      "kl": 0.763671875,
      "learning_rate": 1.2488226905213828e-07,
      "loss": 0.0306,
      "reward": 0.560546875,
      "reward_std": 0.17471889406442642,
      "rewards/correctness_reward_func": 0.1015625,
      "rewards/strict_format_reward_func": 0.458984375,
      "step": 669
    },
    {
      "completion_length": 132.37890625,
      "epoch": 0.7779390420899854,
      "grad_norm": 4.650054405606549,
      "kl": 1.2529296875,
      "learning_rate": 1.236411370725925e-07,
      "loss": 0.0502,
      "reward": 0.515625,
      "reward_std": 0.1161879375576973,
      "rewards/correctness_reward_func": 0.0546875,
      "rewards/strict_format_reward_func": 0.4609375,
      "step": 670
    },
    {
      "completion_length": 89.125,
      "epoch": 0.779100145137881,
      "grad_norm": 1.2443794297338948,
      "kl": 1.00390625,
      "learning_rate": 1.2240533265403197e-07,
      "loss": 0.0402,
      "reward": 0.5390625,
      "reward_std": 0.1351148895919323,
      "rewards/correctness_reward_func": 0.0703125,
      "rewards/strict_format_reward_func": 0.46875,
      "step": 671
    },
    {
      "completion_length": 106.33203125,
      "epoch": 0.7802612481857765,
      "grad_norm": 0.3768066721661794,
      "kl": 0.830078125,
      "learning_rate": 1.2117487328992954e-07,
      "loss": 0.0332,
      "reward": 0.59765625,
      "reward_std": 0.18670720607042313,
      "rewards/correctness_reward_func": 0.1328125,
      "rewards/strict_format_reward_func": 0.46484375,
      "step": 672
    },
    {
      "completion_length": 73.0078125,
      "epoch": 0.781422351233672,
      "grad_norm": 0.3033471234158143,
      "kl": 0.8369140625,
      "learning_rate": 1.1994977639809574e-07,
      "loss": 0.0335,
      "reward": 0.583984375,
      "reward_std": 0.1368129812180996,
      "rewards/correctness_reward_func": 0.109375,
      "rewards/strict_format_reward_func": 0.474609375,
      "step": 673
    },
    {
      "completion_length": 90.390625,
      "epoch": 0.7825834542815675,
      "grad_norm": 0.39200428460223574,
      "kl": 0.806640625,
      "learning_rate": 1.18730059320432e-07,
      "loss": 0.0323,
      "reward": 0.619140625,
      "reward_std": 0.15685429889708757,
      "rewards/correctness_reward_func": 0.1484375,
      "rewards/strict_format_reward_func": 0.470703125,
      "step": 674
    },
    {
      "completion_length": 93.703125,
      "epoch": 0.783744557329463,
      "grad_norm": 0.36906619960173287,
      "kl": 0.7998046875,
      "learning_rate": 1.1751573932268588e-07,
      "loss": 0.032,
      "reward": 0.611328125,
      "reward_std": 0.2286001555621624,
      "rewards/correctness_reward_func": 0.140625,
      "rewards/strict_format_reward_func": 0.470703125,
      "step": 675
    },
    {
      "completion_length": 86.109375,
      "epoch": 0.7849056603773585,
      "grad_norm": 0.2825261098528152,
      "kl": 0.7998046875,
      "learning_rate": 1.1630683359420652e-07,
      "loss": 0.032,
      "reward": 0.615234375,
      "reward_std": 0.1761993244290352,
      "rewards/correctness_reward_func": 0.140625,
      "rewards/strict_format_reward_func": 0.474609375,
      "step": 676
    },
    {
      "completion_length": 84.46484375,
      "epoch": 0.786066763425254,
      "grad_norm": 0.37341054453407235,
      "kl": 0.8720703125,
      "learning_rate": 1.1510335924770103e-07,
      "loss": 0.0349,
      "reward": 0.58984375,
      "reward_std": 0.1486465372145176,
      "rewards/correctness_reward_func": 0.109375,
      "rewards/strict_format_reward_func": 0.48046875,
      "step": 677
    },
    {
      "completion_length": 171.29296875,
      "epoch": 0.7872278664731495,
      "grad_norm": 0.40944501176012393,
      "kl": 0.876953125,
      "learning_rate": 1.1390533331899232e-07,
      "loss": 0.0351,
      "reward": 0.546875,
      "reward_std": 0.1912200264632702,
      "rewards/correctness_reward_func": 0.0859375,
      "rewards/strict_format_reward_func": 0.4609375,
      "step": 678
    },
    {
      "completion_length": 109.578125,
      "epoch": 0.788388969521045,
      "grad_norm": 0.4135678802989366,
      "kl": 0.865234375,
      "learning_rate": 1.1271277276677804e-07,
      "loss": 0.0347,
      "reward": 0.63671875,
      "reward_std": 0.1935429908335209,
      "rewards/correctness_reward_func": 0.171875,
      "rewards/strict_format_reward_func": 0.46484375,
      "step": 679
    },
    {
      "completion_length": 86.01171875,
      "epoch": 0.7895500725689405,
      "grad_norm": 0.4428409895944163,
      "kl": 0.890625,
      "learning_rate": 1.1152569447239074e-07,
      "loss": 0.0357,
      "reward": 0.69140625,
      "reward_std": 0.24195043183863163,
      "rewards/correctness_reward_func": 0.21875,
      "rewards/strict_format_reward_func": 0.47265625,
      "step": 680
    },
    {
      "completion_length": 91.73828125,
      "epoch": 0.790711175616836,
      "grad_norm": 0.36474797299468686,
      "kl": 0.87890625,
      "learning_rate": 1.1034411523955878e-07,
      "loss": 0.0352,
      "reward": 0.52734375,
      "reward_std": 0.11820277571678162,
      "rewards/correctness_reward_func": 0.0625,
      "rewards/strict_format_reward_func": 0.46484375,
      "step": 681
    },
    {
      "completion_length": 91.578125,
      "epoch": 0.7918722786647315,
      "grad_norm": 0.30438496908383467,
      "kl": 0.853515625,
      "learning_rate": 1.091680517941676e-07,
      "loss": 0.0341,
      "reward": 0.599609375,
      "reward_std": 0.1368492729961872,
      "rewards/correctness_reward_func": 0.125,
      "rewards/strict_format_reward_func": 0.474609375,
      "step": 682
    },
    {
      "completion_length": 81.98828125,
      "epoch": 0.793033381712627,
      "grad_norm": 0.4016546110744922,
      "kl": 0.890625,
      "learning_rate": 1.0799752078402469e-07,
      "loss": 0.0357,
      "reward": 0.595703125,
      "reward_std": 0.22009621560573578,
      "rewards/correctness_reward_func": 0.1171875,
      "rewards/strict_format_reward_func": 0.478515625,
      "step": 683
    },
    {
      "completion_length": 91.68359375,
      "epoch": 0.7941944847605225,
      "grad_norm": 0.34531752680526245,
      "kl": 0.8857421875,
      "learning_rate": 1.0683253877862224e-07,
      "loss": 0.0354,
      "reward": 0.654296875,
      "reward_std": 0.17212924361228943,
      "rewards/correctness_reward_func": 0.1796875,
      "rewards/strict_format_reward_func": 0.474609375,
      "step": 684
    },
    {
      "completion_length": 113.8984375,
      "epoch": 0.795355587808418,
      "grad_norm": 0.3325794848861182,
      "kl": 0.8623046875,
      "learning_rate": 1.0567312226890362e-07,
      "loss": 0.0345,
      "reward": 0.689453125,
      "reward_std": 0.24585667252540588,
      "rewards/correctness_reward_func": 0.21875,
      "rewards/strict_format_reward_func": 0.470703125,
      "step": 685
    },
    {
      "completion_length": 109.2109375,
      "epoch": 0.7965166908563135,
      "grad_norm": 0.3816469115839622,
      "kl": 0.8759765625,
      "learning_rate": 1.0451928766702977e-07,
      "loss": 0.035,
      "reward": 0.61328125,
      "reward_std": 0.18561004288494587,
      "rewards/correctness_reward_func": 0.1484375,
      "rewards/strict_format_reward_func": 0.46484375,
      "step": 686
    },
    {
      "completion_length": 78.7578125,
      "epoch": 0.797677793904209,
      "grad_norm": 0.3781995295250306,
      "kl": 0.85546875,
      "learning_rate": 1.0337105130614626e-07,
      "loss": 0.0342,
      "reward": 0.603515625,
      "reward_std": 0.22742783650755882,
      "rewards/correctness_reward_func": 0.1328125,
      "rewards/strict_format_reward_func": 0.470703125,
      "step": 687
    },
    {
      "completion_length": 67.31640625,
      "epoch": 0.7988388969521045,
      "grad_norm": 0.27560896099716947,
      "kl": 0.8232421875,
      "learning_rate": 1.0222842944015325e-07,
      "loss": 0.033,
      "reward": 0.5703125,
      "reward_std": 0.1366473287343979,
      "rewards/correctness_reward_func": 0.09375,
      "rewards/strict_format_reward_func": 0.4765625,
      "step": 688
    },
    {
      "completion_length": 81.35546875,
      "epoch": 0.8,
      "grad_norm": 0.3710290697097015,
      "kl": 0.90625,
      "learning_rate": 1.010914382434741e-07,
      "loss": 0.0362,
      "reward": 0.619140625,
      "reward_std": 0.19230107963085175,
      "rewards/correctness_reward_func": 0.1484375,
      "rewards/strict_format_reward_func": 0.470703125,
      "step": 689
    },
    {
      "completion_length": 96.5703125,
      "epoch": 0.8011611030478955,
      "grad_norm": 0.33819772399021036,
      "kl": 0.8447265625,
      "learning_rate": 9.996009381082716e-08,
      "loss": 0.0338,
      "reward": 0.693359375,
      "reward_std": 0.1427617371082306,
      "rewards/correctness_reward_func": 0.2265625,
      "rewards/strict_format_reward_func": 0.466796875,
      "step": 690
    },
    {
      "completion_length": 119.90625,
      "epoch": 0.802322206095791,
      "grad_norm": 0.3098810879891267,
      "kl": 0.7880859375,
      "learning_rate": 9.883441215699823e-08,
      "loss": 0.0315,
      "reward": 0.578125,
      "reward_std": 0.21376415342092514,
      "rewards/correctness_reward_func": 0.1171875,
      "rewards/strict_format_reward_func": 0.4609375,
      "step": 691
    },
    {
      "completion_length": 69.38671875,
      "epoch": 0.8034833091436865,
      "grad_norm": 0.29637237245922027,
      "kl": 0.88671875,
      "learning_rate": 9.7714409216613e-08,
      "loss": 0.0355,
      "reward": 0.716796875,
      "reward_std": 0.243147075176239,
      "rewards/correctness_reward_func": 0.2421875,
      "rewards/strict_format_reward_func": 0.474609375,
      "step": 692
    },
    {
      "completion_length": 98.0859375,
      "epoch": 0.804644412191582,
      "grad_norm": 0.3453976145246881,
      "kl": 0.826171875,
      "learning_rate": 9.660010084391196e-08,
      "loss": 0.033,
      "reward": 0.689453125,
      "reward_std": 0.2292758673429489,
      "rewards/correctness_reward_func": 0.2109375,
      "rewards/strict_format_reward_func": 0.478515625,
      "step": 693
    },
    {
      "completion_length": 150.8828125,
      "epoch": 0.8058055152394775,
      "grad_norm": 0.49458355230210627,
      "kl": 0.8310546875,
      "learning_rate": 9.549150281252632e-08,
      "loss": 0.0332,
      "reward": 0.583984375,
      "reward_std": 0.2516195774078369,
      "rewards/correctness_reward_func": 0.125,
      "rewards/strict_format_reward_func": 0.458984375,
      "step": 694
    },
    {
      "completion_length": 82.14453125,
      "epoch": 0.806966618287373,
      "grad_norm": 0.5683216611051071,
      "kl": 0.818359375,
      "learning_rate": 9.438863081525395e-08,
      "loss": 0.0327,
      "reward": 0.623046875,
      "reward_std": 0.2734808810055256,
      "rewards/correctness_reward_func": 0.15625,
      "rewards/strict_format_reward_func": 0.466796875,
      "step": 695
    },
    {
      "completion_length": 111.15234375,
      "epoch": 0.8081277213352686,
      "grad_norm": 0.578326956844259,
      "kl": 0.908203125,
      "learning_rate": 9.329150046383772e-08,
      "loss": 0.0363,
      "reward": 0.59765625,
      "reward_std": 0.21070042997598648,
      "rewards/correctness_reward_func": 0.1328125,
      "rewards/strict_format_reward_func": 0.46484375,
      "step": 696
    },
    {
      "completion_length": 98.828125,
      "epoch": 0.809288824383164,
      "grad_norm": 0.30831173588867594,
      "kl": 0.822265625,
      "learning_rate": 9.22001272887447e-08,
      "loss": 0.0329,
      "reward": 0.552734375,
      "reward_std": 0.1660059206187725,
      "rewards/correctness_reward_func": 0.078125,
      "rewards/strict_format_reward_func": 0.474609375,
      "step": 697
    },
    {
      "completion_length": 145.61328125,
      "epoch": 0.8104499274310595,
      "grad_norm": 0.40079918720039537,
      "kl": 0.9345703125,
      "learning_rate": 9.111452673894587e-08,
      "loss": 0.0374,
      "reward": 0.5703125,
      "reward_std": 0.2244485728442669,
      "rewards/correctness_reward_func": 0.109375,
      "rewards/strict_format_reward_func": 0.4609375,
      "step": 698
    },
    {
      "completion_length": 111.46484375,
      "epoch": 0.811611030478955,
      "grad_norm": 0.39303874596386,
      "kl": 0.76953125,
      "learning_rate": 9.003471418169734e-08,
      "loss": 0.0308,
      "reward": 0.55859375,
      "reward_std": 0.1015625,
      "rewards/correctness_reward_func": 0.0859375,
      "rewards/strict_format_reward_func": 0.47265625,
      "step": 699
    },
    {
      "completion_length": 88.8671875,
      "epoch": 0.8127721335268505,
      "grad_norm": 0.3209233289682911,
      "kl": 0.7978515625,
      "learning_rate": 8.89607049023236e-08,
      "loss": 0.0319,
      "reward": 0.626953125,
      "reward_std": 0.21469229832291603,
      "rewards/correctness_reward_func": 0.15625,
      "rewards/strict_format_reward_func": 0.470703125,
      "step": 700
    },
    {
      "completion_length": 70.05078125,
      "epoch": 0.813933236574746,
      "grad_norm": 0.24093749080319501,
      "kl": 0.8203125,
      "learning_rate": 8.789251410400023e-08,
      "loss": 0.0328,
      "reward": 0.630859375,
      "reward_std": 0.1773136891424656,
      "rewards/correctness_reward_func": 0.1484375,
      "rewards/strict_format_reward_func": 0.482421875,
      "step": 701
    },
    {
      "completion_length": 68.48046875,
      "epoch": 0.8150943396226416,
      "grad_norm": 0.29111869296671533,
      "kl": 0.8544921875,
      "learning_rate": 8.683015690753958e-08,
      "loss": 0.0342,
      "reward": 0.603515625,
      "reward_std": 0.1235109455883503,
      "rewards/correctness_reward_func": 0.1171875,
      "rewards/strict_format_reward_func": 0.486328125,
      "step": 702
    },
    {
      "completion_length": 123.8359375,
      "epoch": 0.816255442670537,
      "grad_norm": 0.317421344876871,
      "kl": 0.841796875,
      "learning_rate": 8.577364835117551e-08,
      "loss": 0.0337,
      "reward": 0.583984375,
      "reward_std": 0.17950127460062504,
      "rewards/correctness_reward_func": 0.1171875,
      "rewards/strict_format_reward_func": 0.466796875,
      "step": 703
    },
    {
      "completion_length": 87.76953125,
      "epoch": 0.8174165457184325,
      "grad_norm": 0.3774441379520027,
      "kl": 0.8544921875,
      "learning_rate": 8.472300339035177e-08,
      "loss": 0.0342,
      "reward": 0.646484375,
      "reward_std": 0.2578558810055256,
      "rewards/correctness_reward_func": 0.171875,
      "rewards/strict_format_reward_func": 0.474609375,
      "step": 704
    },
    {
      "completion_length": 87.96875,
      "epoch": 0.818577648766328,
      "grad_norm": 0.35897902148414035,
      "kl": 0.853515625,
      "learning_rate": 8.367823689751007e-08,
      "loss": 0.0341,
      "reward": 0.576171875,
      "reward_std": 0.1748964935541153,
      "rewards/correctness_reward_func": 0.1015625,
      "rewards/strict_format_reward_func": 0.474609375,
      "step": 705
    },
    {
      "completion_length": 82.328125,
      "epoch": 0.8197387518142235,
      "grad_norm": 0.3899964296067063,
      "kl": 0.8408203125,
      "learning_rate": 8.263936366187824e-08,
      "loss": 0.0336,
      "reward": 0.59765625,
      "reward_std": 0.1878032684326172,
      "rewards/correctness_reward_func": 0.1171875,
      "rewards/strict_format_reward_func": 0.48046875,
      "step": 706
    },
    {
      "completion_length": 77.4296875,
      "epoch": 0.820899854862119,
      "grad_norm": 0.271782457714001,
      "kl": 0.822265625,
      "learning_rate": 8.160639838926292e-08,
      "loss": 0.033,
      "reward": 0.6640625,
      "reward_std": 0.12257716432213783,
      "rewards/correctness_reward_func": 0.1875,
      "rewards/strict_format_reward_func": 0.4765625,
      "step": 707
    },
    {
      "completion_length": 117.19921875,
      "epoch": 0.8220609579100145,
      "grad_norm": 0.40027395230777063,
      "kl": 0.880859375,
      "learning_rate": 8.057935570183999e-08,
      "loss": 0.0352,
      "reward": 0.62890625,
      "reward_std": 0.2415117733180523,
      "rewards/correctness_reward_func": 0.15625,
      "rewards/strict_format_reward_func": 0.47265625,
      "step": 708
    },
    {
      "completion_length": 93.54296875,
      "epoch": 0.8232220609579101,
      "grad_norm": 2.838439293265793,
      "kl": 1.041015625,
      "learning_rate": 7.955825013794793e-08,
      "loss": 0.0416,
      "reward": 0.66015625,
      "reward_std": 0.19596018642187119,
      "rewards/correctness_reward_func": 0.1875,
      "rewards/strict_format_reward_func": 0.47265625,
      "step": 709
    },
    {
      "completion_length": 145.3984375,
      "epoch": 0.8243831640058055,
      "grad_norm": 0.461098784060527,
      "kl": 0.8125,
      "learning_rate": 7.854309615188199e-08,
      "loss": 0.0325,
      "reward": 0.56640625,
      "reward_std": 0.2225063145160675,
      "rewards/correctness_reward_func": 0.1171875,
      "rewards/strict_format_reward_func": 0.44921875,
      "step": 710
    },
    {
      "completion_length": 128.7734375,
      "epoch": 0.825544267053701,
      "grad_norm": 0.33025422922626735,
      "kl": 0.865234375,
      "learning_rate": 7.753390811368971e-08,
      "loss": 0.0346,
      "reward": 0.662109375,
      "reward_std": 0.1802689554169774,
      "rewards/correctness_reward_func": 0.1875,
      "rewards/strict_format_reward_func": 0.474609375,
      "step": 711
    },
    {
      "completion_length": 122.16796875,
      "epoch": 0.8267053701015965,
      "grad_norm": 0.4138201771487941,
      "kl": 0.841796875,
      "learning_rate": 7.653070030896774e-08,
      "loss": 0.0336,
      "reward": 0.6640625,
      "reward_std": 0.23485219106078148,
      "rewards/correctness_reward_func": 0.1953125,
      "rewards/strict_format_reward_func": 0.46875,
      "step": 712
    },
    {
      "completion_length": 101.9375,
      "epoch": 0.827866473149492,
      "grad_norm": 0.29971842254223263,
      "kl": 0.845703125,
      "learning_rate": 7.553348693865896e-08,
      "loss": 0.0338,
      "reward": 0.654296875,
      "reward_std": 0.17498845607042313,
      "rewards/correctness_reward_func": 0.1796875,
      "rewards/strict_format_reward_func": 0.474609375,
      "step": 713
    },
    {
      "completion_length": 103.515625,
      "epoch": 0.8290275761973875,
      "grad_norm": 0.4372840733566366,
      "kl": 0.80859375,
      "learning_rate": 7.454228211885184e-08,
      "loss": 0.0324,
      "reward": 0.693359375,
      "reward_std": 0.31086810678243637,
      "rewards/correctness_reward_func": 0.2265625,
      "rewards/strict_format_reward_func": 0.466796875,
      "step": 714
    },
    {
      "completion_length": 107.81640625,
      "epoch": 0.8301886792452831,
      "grad_norm": 0.7010596324486005,
      "kl": 0.8828125,
      "learning_rate": 7.35570998805809e-08,
      "loss": 0.0353,
      "reward": 0.6015625,
      "reward_std": 0.1734074391424656,
      "rewards/correctness_reward_func": 0.1328125,
      "rewards/strict_format_reward_func": 0.46875,
      "step": 715
    },
    {
      "completion_length": 97.84375,
      "epoch": 0.8313497822931786,
      "grad_norm": 0.3722714567919084,
      "kl": 0.87890625,
      "learning_rate": 7.257795416962753e-08,
      "loss": 0.0352,
      "reward": 0.681640625,
      "reward_std": 0.17906035482883453,
      "rewards/correctness_reward_func": 0.2109375,
      "rewards/strict_format_reward_func": 0.470703125,
      "step": 716
    },
    {
      "completion_length": 105.953125,
      "epoch": 0.832510885341074,
      "grad_norm": 0.6941920168627885,
      "kl": 0.9736328125,
      "learning_rate": 7.160485884632278e-08,
      "loss": 0.0389,
      "reward": 0.568359375,
      "reward_std": 0.1460636891424656,
      "rewards/correctness_reward_func": 0.09375,
      "rewards/strict_format_reward_func": 0.474609375,
      "step": 717
    },
    {
      "completion_length": 60.42578125,
      "epoch": 0.8336719883889695,
      "grad_norm": 0.3463695793328205,
      "kl": 0.8623046875,
      "learning_rate": 7.06378276853516e-08,
      "loss": 0.0345,
      "reward": 0.630859375,
      "reward_std": 0.1916152834892273,
      "rewards/correctness_reward_func": 0.1484375,
      "rewards/strict_format_reward_func": 0.482421875,
      "step": 718
    },
    {
      "completion_length": 36.25,
      "epoch": 0.834833091436865,
      "grad_norm": 0.2757357728725883,
      "kl": 0.84375,
      "learning_rate": 6.967687437555719e-08,
      "loss": 0.0338,
      "reward": 0.615234375,
      "reward_std": 0.1361578367650509,
      "rewards/correctness_reward_func": 0.125,
      "rewards/strict_format_reward_func": 0.490234375,
      "step": 719
    },
    {
      "completion_length": 108.78515625,
      "epoch": 0.8359941944847605,
      "grad_norm": 0.3629857930478192,
      "kl": 0.8310546875,
      "learning_rate": 6.872201251974747e-08,
      "loss": 0.0333,
      "reward": 0.5625,
      "reward_std": 0.125,
      "rewards/correctness_reward_func": 0.0859375,
      "rewards/strict_format_reward_func": 0.4765625,
      "step": 720
    },
    {
      "completion_length": 128.12890625,
      "epoch": 0.837155297532656,
      "grad_norm": 0.5412499440749308,
      "kl": 0.873046875,
      "learning_rate": 6.777325563450282e-08,
      "loss": 0.0349,
      "reward": 0.5625,
      "reward_std": 0.17582463566213846,
      "rewards/correctness_reward_func": 0.09375,
      "rewards/strict_format_reward_func": 0.46875,
      "step": 721
    },
    {
      "completion_length": 55.49609375,
      "epoch": 0.8383164005805516,
      "grad_norm": 0.298523542107817,
      "kl": 0.8330078125,
      "learning_rate": 6.683061714998418e-08,
      "loss": 0.0333,
      "reward": 0.640625,
      "reward_std": 0.1901262328028679,
      "rewards/correctness_reward_func": 0.15625,
      "rewards/strict_format_reward_func": 0.484375,
      "step": 722
    },
    {
      "completion_length": 138.83984375,
      "epoch": 0.839477503628447,
      "grad_norm": 0.38182038293187587,
      "kl": 0.8828125,
      "learning_rate": 6.589411040974369e-08,
      "loss": 0.0353,
      "reward": 0.693359375,
      "reward_std": 0.15025749430060387,
      "rewards/correctness_reward_func": 0.234375,
      "rewards/strict_format_reward_func": 0.458984375,
      "step": 723
    },
    {
      "completion_length": 116.60546875,
      "epoch": 0.8406386066763425,
      "grad_norm": 0.5251304132710377,
      "kl": 0.888671875,
      "learning_rate": 6.496374867053494e-08,
      "loss": 0.0356,
      "reward": 0.7421875,
      "reward_std": 0.2569434605538845,
      "rewards/correctness_reward_func": 0.28125,
      "rewards/strict_format_reward_func": 0.4609375,
      "step": 724
    },
    {
      "completion_length": 87.703125,
      "epoch": 0.841799709724238,
      "grad_norm": 0.9309811418375833,
      "kl": 1.0439453125,
      "learning_rate": 6.403954510212584e-08,
      "loss": 0.0418,
      "reward": 0.603515625,
      "reward_std": 0.1639910787343979,
      "rewards/correctness_reward_func": 0.125,
      "rewards/strict_format_reward_func": 0.478515625,
      "step": 725
    },
    {
      "completion_length": 132.98828125,
      "epoch": 0.8429608127721335,
      "grad_norm": 0.37860493020615493,
      "kl": 0.8310546875,
      "learning_rate": 6.312151278711236e-08,
      "loss": 0.0333,
      "reward": 0.66796875,
      "reward_std": 0.2280949354171753,
      "rewards/correctness_reward_func": 0.203125,
      "rewards/strict_format_reward_func": 0.46484375,
      "step": 726
    },
    {
      "completion_length": 110.14453125,
      "epoch": 0.844121915820029,
      "grad_norm": 0.39513992484629906,
      "kl": 0.8291015625,
      "learning_rate": 6.220966472073286e-08,
      "loss": 0.0332,
      "reward": 0.615234375,
      "reward_std": 0.2082555666565895,
      "rewards/correctness_reward_func": 0.1484375,
      "rewards/strict_format_reward_func": 0.466796875,
      "step": 727
    },
    {
      "completion_length": 60.37890625,
      "epoch": 0.8452830188679246,
      "grad_norm": 0.24926100527588751,
      "kl": 0.8466796875,
      "learning_rate": 6.130401381068423e-08,
      "loss": 0.0339,
      "reward": 0.60546875,
      "reward_std": 0.15413607377558947,
      "rewards/correctness_reward_func": 0.125,
      "rewards/strict_format_reward_func": 0.48046875,
      "step": 728
    },
    {
      "completion_length": 149.68359375,
      "epoch": 0.8464441219158201,
      "grad_norm": 0.5866381761310681,
      "kl": 0.9462890625,
      "learning_rate": 6.040457287693962e-08,
      "loss": 0.0378,
      "reward": 0.560546875,
      "reward_std": 0.1693863831460476,
      "rewards/correctness_reward_func": 0.1015625,
      "rewards/strict_format_reward_func": 0.458984375,
      "step": 729
    },
    {
      "completion_length": 117.4453125,
      "epoch": 0.8476052249637155,
      "grad_norm": 1.3423765498491478,
      "kl": 1.078125,
      "learning_rate": 5.951135465156648e-08,
      "loss": 0.0431,
      "reward": 0.591796875,
      "reward_std": 0.19777307659387589,
      "rewards/correctness_reward_func": 0.125,
      "rewards/strict_format_reward_func": 0.466796875,
      "step": 730
    },
    {
      "completion_length": 100.66015625,
      "epoch": 0.848766328011611,
      "grad_norm": 0.3023496282744632,
      "kl": 0.8603515625,
      "learning_rate": 5.862437177854629e-08,
      "loss": 0.0344,
      "reward": 0.5703125,
      "reward_std": 0.13071350753307343,
      "rewards/correctness_reward_func": 0.1015625,
      "rewards/strict_format_reward_func": 0.46875,
      "step": 731
    },
    {
      "completion_length": 102.25390625,
      "epoch": 0.8499274310595065,
      "grad_norm": 0.3554509683102431,
      "kl": 0.8720703125,
      "learning_rate": 5.774363681359623e-08,
      "loss": 0.0348,
      "reward": 0.6484375,
      "reward_std": 0.2057512328028679,
      "rewards/correctness_reward_func": 0.1796875,
      "rewards/strict_format_reward_func": 0.46875,
      "step": 732
    },
    {
      "completion_length": 83.84375,
      "epoch": 0.851088534107402,
      "grad_norm": 0.35043141548796536,
      "kl": 0.8095703125,
      "learning_rate": 5.6869162223990686e-08,
      "loss": 0.0324,
      "reward": 0.587890625,
      "reward_std": 0.1982349008321762,
      "rewards/correctness_reward_func": 0.109375,
      "rewards/strict_format_reward_func": 0.478515625,
      "step": 733
    },
    {
      "completion_length": 107.328125,
      "epoch": 0.8522496371552976,
      "grad_norm": 0.6732821554063042,
      "kl": 1.033203125,
      "learning_rate": 5.600096038838509e-08,
      "loss": 0.0413,
      "reward": 0.517578125,
      "reward_std": 0.117791797965765,
      "rewards/correctness_reward_func": 0.046875,
      "rewards/strict_format_reward_func": 0.470703125,
      "step": 734
    },
    {
      "completion_length": 56.12890625,
      "epoch": 0.8534107402031931,
      "grad_norm": 0.1938757134432352,
      "kl": 0.833984375,
      "learning_rate": 5.5139043596640736e-08,
      "loss": 0.0334,
      "reward": 0.5390625,
      "reward_std": 0.078125,
      "rewards/correctness_reward_func": 0.0546875,
      "rewards/strict_format_reward_func": 0.484375,
      "step": 735
    },
    {
      "completion_length": 115.99609375,
      "epoch": 0.8545718432510885,
      "grad_norm": 0.37019269560696955,
      "kl": 0.8720703125,
      "learning_rate": 5.428342404965075e-08,
      "loss": 0.0349,
      "reward": 0.689453125,
      "reward_std": 0.15133557468652725,
      "rewards/correctness_reward_func": 0.21875,
      "rewards/strict_format_reward_func": 0.470703125,
      "step": 736
    },
    {
      "completion_length": 96.6015625,
      "epoch": 0.855732946298984,
      "grad_norm": 0.3968720685757775,
      "kl": 0.828125,
      "learning_rate": 5.343411385916769e-08,
      "loss": 0.0331,
      "reward": 0.611328125,
      "reward_std": 0.1983339935541153,
      "rewards/correctness_reward_func": 0.140625,
      "rewards/strict_format_reward_func": 0.470703125,
      "step": 737
    },
    {
      "completion_length": 52.546875,
      "epoch": 0.8568940493468795,
      "grad_norm": 0.27400809134336784,
      "kl": 0.8642578125,
      "learning_rate": 5.259112504763113e-08,
      "loss": 0.0346,
      "reward": 0.6953125,
      "reward_std": 0.1730993129312992,
      "rewards/correctness_reward_func": 0.2109375,
      "rewards/strict_format_reward_func": 0.484375,
      "step": 738
    },
    {
      "completion_length": 108.91796875,
      "epoch": 0.858055152394775,
      "grad_norm": 0.2616932569923174,
      "kl": 0.82421875,
      "learning_rate": 5.175446954799873e-08,
      "loss": 0.033,
      "reward": 0.515625,
      "reward_std": 0.0859375,
      "rewards/correctness_reward_func": 0.0390625,
      "rewards/strict_format_reward_func": 0.4765625,
      "step": 739
    },
    {
      "completion_length": 137.52734375,
      "epoch": 0.8592162554426706,
      "grad_norm": 0.41547332296681727,
      "kl": 0.8330078125,
      "learning_rate": 5.0924159203576733e-08,
      "loss": 0.0333,
      "reward": 0.5625,
      "reward_std": 0.1944277435541153,
      "rewards/correctness_reward_func": 0.1015625,
      "rewards/strict_format_reward_func": 0.4609375,
      "step": 740
    },
    {
      "completion_length": 116.578125,
      "epoch": 0.8603773584905661,
      "grad_norm": 0.3954740200586102,
      "kl": 0.890625,
      "learning_rate": 5.010020576785173e-08,
      "loss": 0.0356,
      "reward": 0.5859375,
      "reward_std": 0.12927866727113724,
      "rewards/correctness_reward_func": 0.1171875,
      "rewards/strict_format_reward_func": 0.46875,
      "step": 741
    },
    {
      "completion_length": 99.07421875,
      "epoch": 0.8615384615384616,
      "grad_norm": 0.4800189606784902,
      "kl": 0.88671875,
      "learning_rate": 4.928262090432556e-08,
      "loss": 0.0355,
      "reward": 0.615234375,
      "reward_std": 0.14453125,
      "rewards/correctness_reward_func": 0.140625,
      "rewards/strict_format_reward_func": 0.474609375,
      "step": 742
    },
    {
      "completion_length": 96.54296875,
      "epoch": 0.862699564586357,
      "grad_norm": 0.27953086788774073,
      "kl": 0.857421875,
      "learning_rate": 4.847141618634898e-08,
      "loss": 0.0343,
      "reward": 0.6640625,
      "reward_std": 0.2247929871082306,
      "rewards/correctness_reward_func": 0.1875,
      "rewards/strict_format_reward_func": 0.4765625,
      "step": 743
    },
    {
      "completion_length": 121.08984375,
      "epoch": 0.8638606676342525,
      "grad_norm": 0.31997362767862425,
      "kl": 0.8857421875,
      "learning_rate": 4.766660309695886e-08,
      "loss": 0.0354,
      "reward": 0.654296875,
      "reward_std": 0.1282305307686329,
      "rewards/correctness_reward_func": 0.1875,
      "rewards/strict_format_reward_func": 0.466796875,
      "step": 744
    },
    {
      "completion_length": 132.96875,
      "epoch": 0.865021770682148,
      "grad_norm": 0.36717875821852475,
      "kl": 0.8427734375,
      "learning_rate": 4.6868193028714806e-08,
      "loss": 0.0337,
      "reward": 0.60546875,
      "reward_std": 0.2403188981115818,
      "rewards/correctness_reward_func": 0.140625,
      "rewards/strict_format_reward_func": 0.46484375,
      "step": 745
    },
    {
      "completion_length": 78.734375,
      "epoch": 0.8661828737300435,
      "grad_norm": 0.3209715504775341,
      "kl": 0.8369140625,
      "learning_rate": 4.607619728353818e-08,
      "loss": 0.0335,
      "reward": 0.59375,
      "reward_std": 0.13168952148407698,
      "rewards/correctness_reward_func": 0.125,
      "rewards/strict_format_reward_func": 0.46875,
      "step": 746
    },
    {
      "completion_length": 85.09765625,
      "epoch": 0.8673439767779391,
      "grad_norm": 0.5261176315274854,
      "kl": 0.859375,
      "learning_rate": 4.52906270725526e-08,
      "loss": 0.0344,
      "reward": 0.611328125,
      "reward_std": 0.149041797965765,
      "rewards/correctness_reward_func": 0.1328125,
      "rewards/strict_format_reward_func": 0.478515625,
      "step": 747
    },
    {
      "completion_length": 72.74609375,
      "epoch": 0.8685050798258346,
      "grad_norm": 0.33108557580102815,
      "kl": 0.900390625,
      "learning_rate": 4.451149351592437e-08,
      "loss": 0.036,
      "reward": 0.6328125,
      "reward_std": 0.137323047965765,
      "rewards/correctness_reward_func": 0.15625,
      "rewards/strict_format_reward_func": 0.4765625,
      "step": 748
    },
    {
      "completion_length": 117.0234375,
      "epoch": 0.8696661828737301,
      "grad_norm": 0.9847956361469886,
      "kl": 0.9208984375,
      "learning_rate": 4.373880764270566e-08,
      "loss": 0.0369,
      "reward": 0.7265625,
      "reward_std": 0.267157431691885,
      "rewards/correctness_reward_func": 0.2578125,
      "rewards/strict_format_reward_func": 0.46875,
      "step": 749
    },
    {
      "completion_length": 58.50390625,
      "epoch": 0.8708272859216255,
      "grad_norm": 0.36193365798344973,
      "kl": 0.876953125,
      "learning_rate": 4.2972580390678305e-08,
      "loss": 0.0351,
      "reward": 0.580078125,
      "reward_std": 0.1549699828028679,
      "rewards/correctness_reward_func": 0.1015625,
      "rewards/strict_format_reward_func": 0.478515625,
      "step": 750
    },
    {
      "completion_length": 58.89453125,
      "epoch": 0.871988388969521,
      "grad_norm": 0.2718822080427941,
      "kl": 0.8310546875,
      "learning_rate": 4.2212822606198907e-08,
      "loss": 0.0332,
      "reward": 0.58984375,
      "reward_std": 0.1354387328028679,
      "rewards/correctness_reward_func": 0.109375,
      "rewards/strict_format_reward_func": 0.48046875,
      "step": 751
    },
    {
      "completion_length": 101.46484375,
      "epoch": 0.8731494920174165,
      "grad_norm": 0.3328293442050494,
      "kl": 0.9501953125,
      "learning_rate": 4.145954504404497e-08,
      "loss": 0.0379,
      "reward": 0.615234375,
      "reward_std": 0.1905214935541153,
      "rewards/correctness_reward_func": 0.1484375,
      "rewards/strict_format_reward_func": 0.466796875,
      "step": 752
    },
    {
      "completion_length": 100.5546875,
      "epoch": 0.8743105950653121,
      "grad_norm": 0.4147352126887946,
      "kl": 0.8125,
      "learning_rate": 4.0712758367263564e-08,
      "loss": 0.0325,
      "reward": 0.55859375,
      "reward_std": 0.1644805744290352,
      "rewards/correctness_reward_func": 0.09375,
      "rewards/strict_format_reward_func": 0.46484375,
      "step": 753
    },
    {
      "completion_length": 105.0625,
      "epoch": 0.8754716981132076,
      "grad_norm": 0.2871923597819101,
      "kl": 0.8798828125,
      "learning_rate": 3.997247314701935e-08,
      "loss": 0.0352,
      "reward": 0.541015625,
      "reward_std": 0.10559927299618721,
      "rewards/correctness_reward_func": 0.0703125,
      "rewards/strict_format_reward_func": 0.470703125,
      "step": 754
    },
    {
      "completion_length": 93.4375,
      "epoch": 0.8766328011611031,
      "grad_norm": 0.2517708568748144,
      "kl": 0.888671875,
      "learning_rate": 3.923869986244549e-08,
      "loss": 0.0355,
      "reward": 0.578125,
      "reward_std": 0.1408340372145176,
      "rewards/correctness_reward_func": 0.1015625,
      "rewards/strict_format_reward_func": 0.4765625,
      "step": 755
    },
    {
      "completion_length": 91.66796875,
      "epoch": 0.8777939042089985,
      "grad_norm": 0.28777708295493654,
      "kl": 0.8037109375,
      "learning_rate": 3.851144890049535e-08,
      "loss": 0.0321,
      "reward": 0.56640625,
      "reward_std": 0.18891763407737017,
      "rewards/correctness_reward_func": 0.09375,
      "rewards/strict_format_reward_func": 0.47265625,
      "step": 756
    },
    {
      "completion_length": 96.96875,
      "epoch": 0.878955007256894,
      "grad_norm": 0.4033326821077829,
      "kl": 0.8525390625,
      "learning_rate": 3.779073055579507e-08,
      "loss": 0.0341,
      "reward": 0.69921875,
      "reward_std": 0.3341301940381527,
      "rewards/correctness_reward_func": 0.21875,
      "rewards/strict_format_reward_func": 0.48046875,
      "step": 757
    },
    {
      "completion_length": 90.125,
      "epoch": 0.8801161103047895,
      "grad_norm": 0.4138064447501863,
      "kl": 0.955078125,
      "learning_rate": 3.70765550304985e-08,
      "loss": 0.0382,
      "reward": 0.587890625,
      "reward_std": 0.16178292036056519,
      "rewards/correctness_reward_func": 0.1171875,
      "rewards/strict_format_reward_func": 0.470703125,
      "step": 758
    },
    {
      "completion_length": 107.13671875,
      "epoch": 0.881277213352685,
      "grad_norm": 0.3536492305302017,
      "kl": 0.8046875,
      "learning_rate": 3.6368932434142076e-08,
      "loss": 0.0322,
      "reward": 0.634765625,
      "reward_std": 0.1602867692708969,
      "rewards/correctness_reward_func": 0.1640625,
      "rewards/strict_format_reward_func": 0.470703125,
      "step": 759
    },
    {
      "completion_length": 82.01953125,
      "epoch": 0.8824383164005806,
      "grad_norm": 0.26739941706593773,
      "kl": 0.837890625,
      "learning_rate": 3.566787278350192e-08,
      "loss": 0.0335,
      "reward": 0.58203125,
      "reward_std": 0.1730630248785019,
      "rewards/correctness_reward_func": 0.1015625,
      "rewards/strict_format_reward_func": 0.48046875,
      "step": 760
    },
    {
      "completion_length": 151.15234375,
      "epoch": 0.8835994194484761,
      "grad_norm": 0.3859173481286709,
      "kl": 0.8564453125,
      "learning_rate": 3.497338600245253e-08,
      "loss": 0.0343,
      "reward": 0.65234375,
      "reward_std": 0.2904173284769058,
      "rewards/correctness_reward_func": 0.1875,
      "rewards/strict_format_reward_func": 0.46484375,
      "step": 761
    },
    {
      "completion_length": 113.03515625,
      "epoch": 0.8847605224963716,
      "grad_norm": 0.33861985876359746,
      "kl": 0.8310546875,
      "learning_rate": 3.4285481921825675e-08,
      "loss": 0.0332,
      "reward": 0.59375,
      "reward_std": 0.1474379375576973,
      "rewards/correctness_reward_func": 0.125,
      "rewards/strict_format_reward_func": 0.46875,
      "step": 762
    },
    {
      "completion_length": 98.26953125,
      "epoch": 0.885921625544267,
      "grad_norm": 3.086460898222375,
      "kl": 1.279296875,
      "learning_rate": 3.360417027927137e-08,
      "loss": 0.0512,
      "reward": 0.693359375,
      "reward_std": 0.23098105564713478,
      "rewards/correctness_reward_func": 0.21875,
      "rewards/strict_format_reward_func": 0.474609375,
      "step": 763
    },
    {
      "completion_length": 103.6484375,
      "epoch": 0.8870827285921625,
      "grad_norm": 0.3042226602534025,
      "kl": 0.8056640625,
      "learning_rate": 3.292946071912051e-08,
      "loss": 0.0323,
      "reward": 0.650390625,
      "reward_std": 0.16333775594830513,
      "rewards/correctness_reward_func": 0.1796875,
      "rewards/strict_format_reward_func": 0.470703125,
      "step": 764
    },
    {
      "completion_length": 96.12890625,
      "epoch": 0.888243831640058,
      "grad_norm": 0.3115470374077141,
      "kl": 0.8701171875,
      "learning_rate": 3.2261362792247614e-08,
      "loss": 0.0348,
      "reward": 0.587890625,
      "reward_std": 0.19600241631269455,
      "rewards/correctness_reward_func": 0.109375,
      "rewards/strict_format_reward_func": 0.478515625,
      "step": 765
    },
    {
      "completion_length": 65.73046875,
      "epoch": 0.8894049346879536,
      "grad_norm": 0.19515285439760716,
      "kl": 0.775390625,
      "learning_rate": 3.159988595593616e-08,
      "loss": 0.031,
      "reward": 0.552734375,
      "reward_std": 0.1110730916261673,
      "rewards/correctness_reward_func": 0.0625,
      "rewards/strict_format_reward_func": 0.490234375,
      "step": 766
    },
    {
      "completion_length": 60.69140625,
      "epoch": 0.8905660377358491,
      "grad_norm": 0.4817801187999935,
      "kl": 0.833984375,
      "learning_rate": 3.0945039573744556e-08,
      "loss": 0.0334,
      "reward": 0.681640625,
      "reward_std": 0.16919306479394436,
      "rewards/correctness_reward_func": 0.1953125,
      "rewards/strict_format_reward_func": 0.486328125,
      "step": 767
    },
    {
      "completion_length": 135.18359375,
      "epoch": 0.8917271407837446,
      "grad_norm": 0.3069568851769649,
      "kl": 0.8017578125,
      "learning_rate": 3.0296832915373494e-08,
      "loss": 0.0321,
      "reward": 0.59375,
      "reward_std": 0.1645168662071228,
      "rewards/correctness_reward_func": 0.125,
      "rewards/strict_format_reward_func": 0.46875,
      "step": 768
    },
    {
      "completion_length": 124.8515625,
      "epoch": 0.89288824383164,
      "grad_norm": 0.36166684235838226,
      "kl": 0.9619140625,
      "learning_rate": 2.9655275156535098e-08,
      "loss": 0.0384,
      "reward": 0.626953125,
      "reward_std": 0.22230437397956848,
      "rewards/correctness_reward_func": 0.15625,
      "rewards/strict_format_reward_func": 0.470703125,
      "step": 769
    },
    {
      "completion_length": 130.91015625,
      "epoch": 0.8940493468795355,
      "grad_norm": 0.3646459508311893,
      "kl": 0.8642578125,
      "learning_rate": 2.9020375378822292e-08,
      "loss": 0.0346,
      "reward": 0.615234375,
      "reward_std": 0.19709917902946472,
      "rewards/correctness_reward_func": 0.1484375,
      "rewards/strict_format_reward_func": 0.466796875,
      "step": 770
    },
    {
      "completion_length": 72.31640625,
      "epoch": 0.895210449927431,
      "grad_norm": 1.1520705233796806,
      "kl": 1.099609375,
      "learning_rate": 2.8392142569581058e-08,
      "loss": 0.044,
      "reward": 0.61328125,
      "reward_std": 0.113885547965765,
      "rewards/correctness_reward_func": 0.1328125,
      "rewards/strict_format_reward_func": 0.48046875,
      "step": 771
    },
    {
      "completion_length": 102.953125,
      "epoch": 0.8963715529753266,
      "grad_norm": 0.30684550241296005,
      "kl": 0.8369140625,
      "learning_rate": 2.7770585621782972e-08,
      "loss": 0.0335,
      "reward": 0.580078125,
      "reward_std": 0.1571781411767006,
      "rewards/correctness_reward_func": 0.1015625,
      "rewards/strict_format_reward_func": 0.478515625,
      "step": 772
    },
    {
      "completion_length": 111.9375,
      "epoch": 0.8975326560232221,
      "grad_norm": 0.3952179748605268,
      "kl": 0.8720703125,
      "learning_rate": 2.7155713333898822e-08,
      "loss": 0.0348,
      "reward": 0.634765625,
      "reward_std": 0.2604035958647728,
      "rewards/correctness_reward_func": 0.1640625,
      "rewards/strict_format_reward_func": 0.470703125,
      "step": 773
    },
    {
      "completion_length": 115.57421875,
      "epoch": 0.8986937590711176,
      "grad_norm": 0.2528483309577429,
      "kl": 0.8154296875,
      "learning_rate": 2.6547534409774808e-08,
      "loss": 0.0326,
      "reward": 0.62109375,
      "reward_std": 0.16768829338252544,
      "rewards/correctness_reward_func": 0.1484375,
      "rewards/strict_format_reward_func": 0.47265625,
      "step": 774
    },
    {
      "completion_length": 137.1015625,
      "epoch": 0.8998548621190131,
      "grad_norm": 0.9483694344963964,
      "kl": 0.9296875,
      "learning_rate": 2.5946057458508752e-08,
      "loss": 0.0373,
      "reward": 0.59375,
      "reward_std": 0.17067647725343704,
      "rewards/correctness_reward_func": 0.1328125,
      "rewards/strict_format_reward_func": 0.4609375,
      "step": 775
    },
    {
      "completion_length": 74.74609375,
      "epoch": 0.9010159651669085,
      "grad_norm": 0.31295843515727634,
      "kl": 0.8623046875,
      "learning_rate": 2.53512909943287e-08,
      "loss": 0.0345,
      "reward": 0.642578125,
      "reward_std": 0.1460636891424656,
      "rewards/correctness_reward_func": 0.1640625,
      "rewards/strict_format_reward_func": 0.478515625,
      "step": 776
    },
    {
      "completion_length": 99.1328125,
      "epoch": 0.902177068214804,
      "grad_norm": 0.3275089442227349,
      "kl": 0.8896484375,
      "learning_rate": 2.4763243436472014e-08,
      "loss": 0.0356,
      "reward": 0.576171875,
      "reward_std": 0.156854297965765,
      "rewards/correctness_reward_func": 0.09375,
      "rewards/strict_format_reward_func": 0.482421875,
      "step": 777
    },
    {
      "completion_length": 135.328125,
      "epoch": 0.9033381712626996,
      "grad_norm": 0.3489118171327631,
      "kl": 0.8154296875,
      "learning_rate": 2.4181923109066248e-08,
      "loss": 0.0326,
      "reward": 0.609375,
      "reward_std": 0.2034645564854145,
      "rewards/correctness_reward_func": 0.140625,
      "rewards/strict_format_reward_func": 0.46875,
      "step": 778
    },
    {
      "completion_length": 96.91015625,
      "epoch": 0.9044992743105951,
      "grad_norm": 0.2826526438797628,
      "kl": 0.8251953125,
      "learning_rate": 2.3607338241011743e-08,
      "loss": 0.033,
      "reward": 0.638671875,
      "reward_std": 0.2095789574086666,
      "rewards/correctness_reward_func": 0.1640625,
      "rewards/strict_format_reward_func": 0.474609375,
      "step": 779
    },
    {
      "completion_length": 101.43359375,
      "epoch": 0.9056603773584906,
      "grad_norm": 0.3245546365713591,
      "kl": 0.865234375,
      "learning_rate": 2.3039496965864435e-08,
      "loss": 0.0347,
      "reward": 0.578125,
      "reward_std": 0.16394205391407013,
      "rewards/correctness_reward_func": 0.1015625,
      "rewards/strict_format_reward_func": 0.4765625,
      "step": 780
    },
    {
      "completion_length": 147.94921875,
      "epoch": 0.9068214804063861,
      "grad_norm": 0.4160583573667952,
      "kl": 0.88671875,
      "learning_rate": 2.2478407321721293e-08,
      "loss": 0.0355,
      "reward": 0.5703125,
      "reward_std": 0.1833132915198803,
      "rewards/correctness_reward_func": 0.109375,
      "rewards/strict_format_reward_func": 0.4609375,
      "step": 781
    },
    {
      "completion_length": 125.9609375,
      "epoch": 0.9079825834542816,
      "grad_norm": 0.3099810465985578,
      "kl": 0.8720703125,
      "learning_rate": 2.1924077251106345e-08,
      "loss": 0.0349,
      "reward": 0.673828125,
      "reward_std": 0.21206606924533844,
      "rewards/correctness_reward_func": 0.203125,
      "rewards/strict_format_reward_func": 0.470703125,
      "step": 782
    },
    {
      "completion_length": 73.4609375,
      "epoch": 0.909143686502177,
      "grad_norm": 0.26803082231819897,
      "kl": 0.8154296875,
      "learning_rate": 2.1376514600858207e-08,
      "loss": 0.0326,
      "reward": 0.6015625,
      "reward_std": 0.106073047965765,
      "rewards/correctness_reward_func": 0.1171875,
      "rewards/strict_format_reward_func": 0.484375,
      "step": 783
    },
    {
      "completion_length": 74.61328125,
      "epoch": 0.9103047895500725,
      "grad_norm": 0.28287368034712124,
      "kl": 0.7314453125,
      "learning_rate": 2.0835727122018975e-08,
      "loss": 0.0293,
      "reward": 0.576171875,
      "reward_std": 0.14627272728830576,
      "rewards/correctness_reward_func": 0.09375,
      "rewards/strict_format_reward_func": 0.482421875,
      "step": 784
    },
    {
      "completion_length": 76.41015625,
      "epoch": 0.9114658925979681,
      "grad_norm": 0.32731653713313796,
      "kl": 0.763671875,
      "learning_rate": 2.0301722469724724e-08,
      "loss": 0.0305,
      "reward": 0.623046875,
      "reward_std": 0.11723088473081589,
      "rewards/correctness_reward_func": 0.140625,
      "rewards/strict_format_reward_func": 0.482421875,
      "step": 785
    },
    {
      "completion_length": 137.48046875,
      "epoch": 0.9126269956458636,
      "grad_norm": 0.33924040034839253,
      "kl": 0.845703125,
      "learning_rate": 1.977450820309684e-08,
      "loss": 0.0339,
      "reward": 0.6484375,
      "reward_std": 0.2167508751153946,
      "rewards/correctness_reward_func": 0.1796875,
      "rewards/strict_format_reward_func": 0.46875,
      "step": 786
    },
    {
      "completion_length": 89.78515625,
      "epoch": 0.9137880986937591,
      "grad_norm": 0.41401402146997324,
      "kl": 0.9169921875,
      "learning_rate": 1.9254091785135152e-08,
      "loss": 0.0367,
      "reward": 0.685546875,
      "reward_std": 0.2290230728685856,
      "rewards/correctness_reward_func": 0.2109375,
      "rewards/strict_format_reward_func": 0.474609375,
      "step": 787
    },
    {
      "completion_length": 91.046875,
      "epoch": 0.9149492017416546,
      "grad_norm": 0.38833395155629735,
      "kl": 0.85546875,
      "learning_rate": 1.8740480582612517e-08,
      "loss": 0.0342,
      "reward": 0.625,
      "reward_std": 0.2033340372145176,
      "rewards/correctness_reward_func": 0.1484375,
      "rewards/strict_format_reward_func": 0.4765625,
      "step": 788
    },
    {
      "completion_length": 71.3359375,
      "epoch": 0.91611030478955,
      "grad_norm": 0.28829450344699553,
      "kl": 0.84765625,
      "learning_rate": 1.8233681865970073e-08,
      "loss": 0.0339,
      "reward": 0.609375,
      "reward_std": 0.2081684246659279,
      "rewards/correctness_reward_func": 0.1328125,
      "rewards/strict_format_reward_func": 0.4765625,
      "step": 789
    },
    {
      "completion_length": 76.7421875,
      "epoch": 0.9172714078374455,
      "grad_norm": 0.3932509546388982,
      "kl": 0.8134765625,
      "learning_rate": 1.7733702809214825e-08,
      "loss": 0.0325,
      "reward": 0.681640625,
      "reward_std": 0.2139589935541153,
      "rewards/correctness_reward_func": 0.203125,
      "rewards/strict_format_reward_func": 0.478515625,
      "step": 790
    },
    {
      "completion_length": 140.046875,
      "epoch": 0.9184325108853411,
      "grad_norm": 57.36190593628536,
      "kl": 8.8427734375,
      "learning_rate": 1.724055048981765e-08,
      "loss": 0.3533,
      "reward": 0.705078125,
      "reward_std": 0.2947102300822735,
      "rewards/correctness_reward_func": 0.2421875,
      "rewards/strict_format_reward_func": 0.462890625,
      "step": 791
    },
    {
      "completion_length": 102.0703125,
      "epoch": 0.9195936139332366,
      "grad_norm": 0.43521318791044,
      "kl": 0.919921875,
      "learning_rate": 1.67542318886133e-08,
      "loss": 0.0367,
      "reward": 0.58984375,
      "reward_std": 0.1946367807686329,
      "rewards/correctness_reward_func": 0.1171875,
      "rewards/strict_format_reward_func": 0.47265625,
      "step": 792
    },
    {
      "completion_length": 107.8671875,
      "epoch": 0.9207547169811321,
      "grad_norm": 0.31420243164425915,
      "kl": 0.7900390625,
      "learning_rate": 1.6274753889701897e-08,
      "loss": 0.0316,
      "reward": 0.6328125,
      "reward_std": 0.2123551368713379,
      "rewards/correctness_reward_func": 0.15625,
      "rewards/strict_format_reward_func": 0.4765625,
      "step": 793
    },
    {
      "completion_length": 109.35546875,
      "epoch": 0.9219158200290276,
      "grad_norm": 0.5966249446506182,
      "kl": 0.9755859375,
      "learning_rate": 1.5802123280350632e-08,
      "loss": 0.039,
      "reward": 0.578125,
      "reward_std": 0.19939784705638885,
      "rewards/correctness_reward_func": 0.109375,
      "rewards/strict_format_reward_func": 0.46875,
      "step": 794
    },
    {
      "completion_length": 73.0625,
      "epoch": 0.9230769230769231,
      "grad_norm": 0.32377652330343726,
      "kl": 0.873046875,
      "learning_rate": 1.5336346750898675e-08,
      "loss": 0.035,
      "reward": 0.630859375,
      "reward_std": 0.2299078330397606,
      "rewards/correctness_reward_func": 0.1484375,
      "rewards/strict_format_reward_func": 0.482421875,
      "step": 795
    },
    {
      "completion_length": 140.60546875,
      "epoch": 0.9242380261248185,
      "grad_norm": 0.6638253019122143,
      "kl": 0.9365234375,
      "learning_rate": 1.4877430894662035e-08,
      "loss": 0.0374,
      "reward": 0.662109375,
      "reward_std": 0.2453395165503025,
      "rewards/correctness_reward_func": 0.1953125,
      "rewards/strict_format_reward_func": 0.466796875,
      "step": 796
    },
    {
      "completion_length": 121.9765625,
      "epoch": 0.925399129172714,
      "grad_norm": 0.37286415601252304,
      "kl": 0.892578125,
      "learning_rate": 1.4425382207839953e-08,
      "loss": 0.0357,
      "reward": 0.607421875,
      "reward_std": 0.1759902834892273,
      "rewards/correctness_reward_func": 0.140625,
      "rewards/strict_format_reward_func": 0.466796875,
      "step": 797
    },
    {
      "completion_length": 127.89453125,
      "epoch": 0.9265602322206096,
      "grad_norm": 0.3511284284933478,
      "kl": 0.8671875,
      "learning_rate": 1.3980207089423325e-08,
      "loss": 0.0347,
      "reward": 0.6171875,
      "reward_std": 0.21108373254537582,
      "rewards/correctness_reward_func": 0.15625,
      "rewards/strict_format_reward_func": 0.4609375,
      "step": 798
    },
    {
      "completion_length": 133.30859375,
      "epoch": 0.9277213352685051,
      "grad_norm": 0.4177305070006306,
      "kl": 0.833984375,
      "learning_rate": 1.3541911841104148e-08,
      "loss": 0.0333,
      "reward": 0.56640625,
      "reward_std": 0.1565738394856453,
      "rewards/correctness_reward_func": 0.1015625,
      "rewards/strict_format_reward_func": 0.46484375,
      "step": 799
    },
    {
      "completion_length": 134.81640625,
      "epoch": 0.9288824383164006,
      "grad_norm": 0.2915355076966808,
      "kl": 0.806640625,
      "learning_rate": 1.3110502667185996e-08,
      "loss": 0.0322,
      "reward": 0.560546875,
      "reward_std": 0.1247195415198803,
      "rewards/correctness_reward_func": 0.09375,
      "rewards/strict_format_reward_func": 0.466796875,
      "step": 800
    },
    {
      "completion_length": 119.68359375,
      "epoch": 0.9300435413642961,
      "grad_norm": 0.37309570760400174,
      "kl": 0.8740234375,
      "learning_rate": 1.2685985674496469e-08,
      "loss": 0.035,
      "reward": 0.6796875,
      "reward_std": 0.2160957306623459,
      "rewards/correctness_reward_func": 0.2109375,
      "rewards/strict_format_reward_func": 0.46875,
      "step": 801
    },
    {
      "completion_length": 119.69140625,
      "epoch": 0.9312046444121915,
      "grad_norm": 0.35257890249919704,
      "kl": 0.8994140625,
      "learning_rate": 1.2268366872300595e-08,
      "loss": 0.036,
      "reward": 0.55859375,
      "reward_std": 0.1443813145160675,
      "rewards/correctness_reward_func": 0.09375,
      "rewards/strict_format_reward_func": 0.46484375,
      "step": 802
    },
    {
      "completion_length": 112.7421875,
      "epoch": 0.932365747460087,
      "grad_norm": 0.2502773826043032,
      "kl": 0.8193359375,
      "learning_rate": 1.1857652172215904e-08,
      "loss": 0.0328,
      "reward": 0.646484375,
      "reward_std": 0.1603652834892273,
      "rewards/correctness_reward_func": 0.171875,
      "rewards/strict_format_reward_func": 0.474609375,
      "step": 803
    },
    {
      "completion_length": 108.6328125,
      "epoch": 0.9335268505079826,
      "grad_norm": 0.2921139382408479,
      "kl": 0.8671875,
      "learning_rate": 1.1453847388128713e-08,
      "loss": 0.0347,
      "reward": 0.62890625,
      "reward_std": 0.1576676331460476,
      "rewards/correctness_reward_func": 0.15625,
      "rewards/strict_format_reward_func": 0.47265625,
      "step": 804
    },
    {
      "completion_length": 91.30078125,
      "epoch": 0.9346879535558781,
      "grad_norm": 0.2473391493395937,
      "kl": 0.8837890625,
      "learning_rate": 1.1056958236111525e-08,
      "loss": 0.0354,
      "reward": 0.62890625,
      "reward_std": 0.1664796955883503,
      "rewards/correctness_reward_func": 0.1484375,
      "rewards/strict_format_reward_func": 0.48046875,
      "step": 805
    },
    {
      "completion_length": 65.33984375,
      "epoch": 0.9358490566037736,
      "grad_norm": 0.2911922343487728,
      "kl": 0.806640625,
      "learning_rate": 1.0666990334342707e-08,
      "loss": 0.0323,
      "reward": 0.64453125,
      "reward_std": 0.1796875,
      "rewards/correctness_reward_func": 0.15625,
      "rewards/strict_format_reward_func": 0.48828125,
      "step": 806
    },
    {
      "completion_length": 93.46484375,
      "epoch": 0.9370101596516691,
      "grad_norm": 0.3304531524117945,
      "kl": 0.7822265625,
      "learning_rate": 1.0283949203026331e-08,
      "loss": 0.0313,
      "reward": 0.64453125,
      "reward_std": 0.22718960791826248,
      "rewards/correctness_reward_func": 0.171875,
      "rewards/strict_format_reward_func": 0.47265625,
      "step": 807
    },
    {
      "completion_length": 63.3359375,
      "epoch": 0.9381712626995646,
      "grad_norm": 0.33826535178669853,
      "kl": 0.9033203125,
      "learning_rate": 9.90784026431457e-09,
      "loss": 0.0361,
      "reward": 0.619140625,
      "reward_std": 0.23572121560573578,
      "rewards/correctness_reward_func": 0.1328125,
      "rewards/strict_format_reward_func": 0.486328125,
      "step": 808
    },
    {
      "completion_length": 68.55859375,
      "epoch": 0.93933236574746,
      "grad_norm": 0.5083665913372343,
      "kl": 0.986328125,
      "learning_rate": 9.538668842230535e-09,
      "loss": 0.0394,
      "reward": 0.642578125,
      "reward_std": 0.23288594186306,
      "rewards/correctness_reward_func": 0.1640625,
      "rewards/strict_format_reward_func": 0.478515625,
      "step": 809
    },
    {
      "completion_length": 82.4453125,
      "epoch": 0.9404934687953556,
      "grad_norm": 0.3235621252242022,
      "kl": 0.88671875,
      "learning_rate": 9.176440162593169e-09,
      "loss": 0.0355,
      "reward": 0.607421875,
      "reward_std": 0.11095601879060268,
      "rewards/correctness_reward_func": 0.1328125,
      "rewards/strict_format_reward_func": 0.474609375,
      "step": 810
    },
    {
      "completion_length": 131.6328125,
      "epoch": 0.9416545718432511,
      "grad_norm": 0.5460278784883479,
      "kl": 0.935546875,
      "learning_rate": 8.821159352943142e-09,
      "loss": 0.0375,
      "reward": 0.5546875,
      "reward_std": 0.17860377952456474,
      "rewards/correctness_reward_func": 0.09375,
      "rewards/strict_format_reward_func": 0.4609375,
      "step": 811
    },
    {
      "completion_length": 112.1796875,
      "epoch": 0.9428156748911466,
      "grad_norm": 0.35049024150199853,
      "kl": 0.9091796875,
      "learning_rate": 8.472831442470407e-09,
      "loss": 0.0363,
      "reward": 0.58203125,
      "reward_std": 0.2102617807686329,
      "rewards/correctness_reward_func": 0.1171875,
      "rewards/strict_format_reward_func": 0.46484375,
      "step": 812
    },
    {
      "completion_length": 111.98828125,
      "epoch": 0.9439767779390421,
      "grad_norm": 0.4719456131161758,
      "kl": 0.8212890625,
      "learning_rate": 8.13146136194265e-09,
      "loss": 0.0329,
      "reward": 0.6171875,
      "reward_std": 0.24546660669147968,
      "rewards/correctness_reward_func": 0.1484375,
      "rewards/strict_format_reward_func": 0.46875,
      "step": 813
    },
    {
      "completion_length": 97.08203125,
      "epoch": 0.9451378809869376,
      "grad_norm": 2.468832428625385,
      "kl": 1.30859375,
      "learning_rate": 7.797053943636111e-09,
      "loss": 0.0524,
      "reward": 0.595703125,
      "reward_std": 0.1423230916261673,
      "rewards/correctness_reward_func": 0.125,
      "rewards/strict_format_reward_func": 0.470703125,
      "step": 814
    },
    {
      "completion_length": 94.7890625,
      "epoch": 0.9462989840348331,
      "grad_norm": 0.29510804539208974,
      "kl": 0.7900390625,
      "learning_rate": 7.469613921266548e-09,
      "loss": 0.0316,
      "reward": 0.576171875,
      "reward_std": 0.1627824790775776,
      "rewards/correctness_reward_func": 0.1015625,
      "rewards/strict_format_reward_func": 0.474609375,
      "step": 815
    },
    {
      "completion_length": 59.66796875,
      "epoch": 0.9474600870827286,
      "grad_norm": 0.30897751995306894,
      "kl": 0.853515625,
      "learning_rate": 7.149145929922606e-09,
      "loss": 0.0342,
      "reward": 0.669921875,
      "reward_std": 0.2142828367650509,
      "rewards/correctness_reward_func": 0.1796875,
      "rewards/strict_format_reward_func": 0.490234375,
      "step": 816
    },
    {
      "completion_length": 74.8671875,
      "epoch": 0.9486211901306241,
      "grad_norm": 0.32290789641457124,
      "kl": 0.9072265625,
      "learning_rate": 6.835654506000099e-09,
      "loss": 0.0363,
      "reward": 0.697265625,
      "reward_std": 0.18480234593153,
      "rewards/correctness_reward_func": 0.21875,
      "rewards/strict_format_reward_func": 0.478515625,
      "step": 817
    },
    {
      "completion_length": 113.609375,
      "epoch": 0.9497822931785196,
      "grad_norm": 0.37895997533917175,
      "kl": 0.880859375,
      "learning_rate": 6.529144087137839e-09,
      "loss": 0.0353,
      "reward": 0.548828125,
      "reward_std": 0.1672145128250122,
      "rewards/correctness_reward_func": 0.0859375,
      "rewards/strict_format_reward_func": 0.462890625,
      "step": 818
    },
    {
      "completion_length": 75.7421875,
      "epoch": 0.9509433962264151,
      "grad_norm": 0.29250546268959143,
      "kl": 0.828125,
      "learning_rate": 6.229619012154574e-09,
      "loss": 0.0331,
      "reward": 0.615234375,
      "reward_std": 0.1581571288406849,
      "rewards/correctness_reward_func": 0.140625,
      "rewards/strict_format_reward_func": 0.474609375,
      "step": 819
    },
    {
      "completion_length": 104.1640625,
      "epoch": 0.9521044992743106,
      "grad_norm": 0.519394512392808,
      "kl": 0.9765625,
      "learning_rate": 5.937083520988151e-09,
      "loss": 0.0391,
      "reward": 0.693359375,
      "reward_std": 0.23276549577713013,
      "rewards/correctness_reward_func": 0.2265625,
      "rewards/strict_format_reward_func": 0.466796875,
      "step": 820
    },
    {
      "completion_length": 113.57421875,
      "epoch": 0.9532656023222061,
      "grad_norm": 0.3357111920350683,
      "kl": 0.8408203125,
      "learning_rate": 5.6515417546347255e-09,
      "loss": 0.0336,
      "reward": 0.544921875,
      "reward_std": 0.149227992631495,
      "rewards/correctness_reward_func": 0.078125,
      "rewards/strict_format_reward_func": 0.466796875,
      "step": 821
    },
    {
      "completion_length": 111.52734375,
      "epoch": 0.9544267053701015,
      "grad_norm": 0.4302254258520084,
      "kl": 0.875,
      "learning_rate": 5.372997755090758e-09,
      "loss": 0.035,
      "reward": 0.611328125,
      "reward_std": 0.2646845318377018,
      "rewards/correctness_reward_func": 0.140625,
      "rewards/strict_format_reward_func": 0.470703125,
      "step": 822
    },
    {
      "completion_length": 112.49609375,
      "epoch": 0.9555878084179971,
      "grad_norm": 0.51227854793276,
      "kl": 0.83203125,
      "learning_rate": 5.1014554652955564e-09,
      "loss": 0.0333,
      "reward": 0.61328125,
      "reward_std": 0.1937520168721676,
      "rewards/correctness_reward_func": 0.140625,
      "rewards/strict_format_reward_func": 0.47265625,
      "step": 823
    },
    {
      "completion_length": 98.59375,
      "epoch": 0.9567489114658926,
      "grad_norm": 0.2863234328656348,
      "kl": 0.8125,
      "learning_rate": 4.836918729075434e-09,
      "loss": 0.0325,
      "reward": 0.6640625,
      "reward_std": 0.15062281489372253,
      "rewards/correctness_reward_func": 0.1875,
      "rewards/strict_format_reward_func": 0.4765625,
      "step": 824
    },
    {
      "completion_length": 72.92578125,
      "epoch": 0.9579100145137881,
      "grad_norm": 0.30746256694506124,
      "kl": 0.876953125,
      "learning_rate": 4.579391291089418e-09,
      "loss": 0.0351,
      "reward": 0.677734375,
      "reward_std": 0.17993991822004318,
      "rewards/correctness_reward_func": 0.1953125,
      "rewards/strict_format_reward_func": 0.482421875,
      "step": 825
    },
    {
      "completion_length": 94.88671875,
      "epoch": 0.9590711175616836,
      "grad_norm": 0.35607780345994633,
      "kl": 0.876953125,
      "learning_rate": 4.328876796776071e-09,
      "loss": 0.035,
      "reward": 0.603515625,
      "reward_std": 0.158062893897295,
      "rewards/correctness_reward_func": 0.1328125,
      "rewards/strict_format_reward_func": 0.470703125,
      "step": 826
    },
    {
      "completion_length": 89.44921875,
      "epoch": 0.9602322206095791,
      "grad_norm": 0.28073591983941715,
      "kl": 0.9326171875,
      "learning_rate": 4.0853787923020296e-09,
      "loss": 0.0373,
      "reward": 0.599609375,
      "reward_std": 0.109979297965765,
      "rewards/correctness_reward_func": 0.125,
      "rewards/strict_format_reward_func": 0.474609375,
      "step": 827
    },
    {
      "completion_length": 105.15625,
      "epoch": 0.9613933236574747,
      "grad_norm": 0.30598863625049205,
      "kl": 0.80859375,
      "learning_rate": 3.848900724511827e-09,
      "loss": 0.0324,
      "reward": 0.630859375,
      "reward_std": 0.21339807752519846,
      "rewards/correctness_reward_func": 0.15625,
      "rewards/strict_format_reward_func": 0.474609375,
      "step": 828
    },
    {
      "completion_length": 97.5234375,
      "epoch": 0.9625544267053701,
      "grad_norm": 0.24367232412752368,
      "kl": 0.81640625,
      "learning_rate": 3.619445940878929e-09,
      "loss": 0.0327,
      "reward": 0.5390625,
      "reward_std": 0.14545938931405544,
      "rewards/correctness_reward_func": 0.0703125,
      "rewards/strict_format_reward_func": 0.46875,
      "step": 829
    },
    {
      "completion_length": 93.57421875,
      "epoch": 0.9637155297532656,
      "grad_norm": 0.6408521441678474,
      "kl": 1.0009765625,
      "learning_rate": 3.397017689458548e-09,
      "loss": 0.04,
      "reward": 0.56640625,
      "reward_std": 0.1466679871082306,
      "rewards/correctness_reward_func": 0.09375,
      "rewards/strict_format_reward_func": 0.47265625,
      "step": 830
    },
    {
      "completion_length": 94.140625,
      "epoch": 0.9648766328011611,
      "grad_norm": 0.3060174903240232,
      "kl": 0.8447265625,
      "learning_rate": 3.1816191188415164e-09,
      "loss": 0.0337,
      "reward": 0.58984375,
      "reward_std": 0.1130007915198803,
      "rewards/correctness_reward_func": 0.1171875,
      "rewards/strict_format_reward_func": 0.47265625,
      "step": 831
    },
    {
      "completion_length": 84.5,
      "epoch": 0.9660377358490566,
      "grad_norm": 0.3719462449618252,
      "kl": 0.9189453125,
      "learning_rate": 2.9732532781097665e-09,
      "loss": 0.0368,
      "reward": 0.67578125,
      "reward_std": 0.2143699675798416,
      "rewards/correctness_reward_func": 0.203125,
      "rewards/strict_format_reward_func": 0.47265625,
      "step": 832
    },
    {
      "completion_length": 134.98046875,
      "epoch": 0.9671988388969521,
      "grad_norm": 1.5222913967472582,
      "kl": 0.9765625,
      "learning_rate": 2.7719231167933065e-09,
      "loss": 0.0391,
      "reward": 0.5703125,
      "reward_std": 0.1568976826965809,
      "rewards/correctness_reward_func": 0.1015625,
      "rewards/strict_format_reward_func": 0.46875,
      "step": 833
    },
    {
      "completion_length": 72.28125,
      "epoch": 0.9683599419448476,
      "grad_norm": 0.3236286383858434,
      "kl": 0.8720703125,
      "learning_rate": 2.577631484828147e-09,
      "loss": 0.0349,
      "reward": 0.642578125,
      "reward_std": 0.1885586567223072,
      "rewards/correctness_reward_func": 0.1640625,
      "rewards/strict_format_reward_func": 0.478515625,
      "step": 834
    },
    {
      "completion_length": 76.41015625,
      "epoch": 0.969521044992743,
      "grad_norm": 0.18782496692048403,
      "kl": 0.8173828125,
      "learning_rate": 2.390381132516328e-09,
      "loss": 0.0327,
      "reward": 0.576171875,
      "reward_std": 0.156854297965765,
      "rewards/correctness_reward_func": 0.09375,
      "rewards/strict_format_reward_func": 0.482421875,
      "step": 835
    },
    {
      "completion_length": 83.72265625,
      "epoch": 0.9706821480406386,
      "grad_norm": 0.3639072104226485,
      "kl": 0.857421875,
      "learning_rate": 2.2101747104866785e-09,
      "loss": 0.0343,
      "reward": 0.65234375,
      "reward_std": 0.2084137573838234,
      "rewards/correctness_reward_func": 0.171875,
      "rewards/strict_format_reward_func": 0.48046875,
      "step": 836
    },
    {
      "completion_length": 95.7109375,
      "epoch": 0.9718432510885341,
      "grad_norm": 0.4076540368897721,
      "kl": 0.896484375,
      "learning_rate": 2.0370147696574526e-09,
      "loss": 0.0358,
      "reward": 0.544921875,
      "reward_std": 0.13527308031916618,
      "rewards/correctness_reward_func": 0.0703125,
      "rewards/strict_format_reward_func": 0.474609375,
      "step": 837
    },
    {
      "completion_length": 108.83984375,
      "epoch": 0.9730043541364296,
      "grad_norm": 0.3250167750155122,
      "kl": 0.822265625,
      "learning_rate": 1.8709037612003044e-09,
      "loss": 0.0329,
      "reward": 0.583984375,
      "reward_std": 0.21328327059745789,
      "rewards/correctness_reward_func": 0.1171875,
      "rewards/strict_format_reward_func": 0.466796875,
      "step": 838
    },
    {
      "completion_length": 96.1953125,
      "epoch": 0.9741654571843251,
      "grad_norm": 0.43045334103112415,
      "kl": 0.927734375,
      "learning_rate": 1.7118440365053722e-09,
      "loss": 0.0371,
      "reward": 0.69140625,
      "reward_std": 0.1812199354171753,
      "rewards/correctness_reward_func": 0.21875,
      "rewards/strict_format_reward_func": 0.47265625,
      "step": 839
    },
    {
      "completion_length": 79.9453125,
      "epoch": 0.9753265602322206,
      "grad_norm": 0.42436925951799076,
      "kl": 0.8583984375,
      "learning_rate": 1.5598378471480266e-09,
      "loss": 0.0344,
      "reward": 0.708984375,
      "reward_std": 0.2938254699110985,
      "rewards/correctness_reward_func": 0.234375,
      "rewards/strict_format_reward_func": 0.474609375,
      "step": 840
    },
    {
      "completion_length": 95.3203125,
      "epoch": 0.9764876632801162,
      "grad_norm": 0.3518468319993105,
      "kl": 0.876953125,
      "learning_rate": 1.4148873448573406e-09,
      "loss": 0.0351,
      "reward": 0.5703125,
      "reward_std": 0.15490375459194183,
      "rewards/correctness_reward_func": 0.09375,
      "rewards/strict_format_reward_func": 0.4765625,
      "step": 841
    },
    {
      "completion_length": 114.3125,
      "epoch": 0.9776487663280116,
      "grad_norm": 0.31679474821502085,
      "kl": 0.82421875,
      "learning_rate": 1.276994581485058e-09,
      "loss": 0.0329,
      "reward": 0.626953125,
      "reward_std": 0.2185637727379799,
      "rewards/correctness_reward_func": 0.1640625,
      "rewards/strict_format_reward_func": 0.462890625,
      "step": 842
    },
    {
      "completion_length": 103.19140625,
      "epoch": 0.9788098693759071,
      "grad_norm": 0.3027225420172307,
      "kl": 0.861328125,
      "learning_rate": 1.146161508977006e-09,
      "loss": 0.0345,
      "reward": 0.658203125,
      "reward_std": 0.211541797965765,
      "rewards/correctness_reward_func": 0.1875,
      "rewards/strict_format_reward_func": 0.470703125,
      "step": 843
    },
    {
      "completion_length": 130.390625,
      "epoch": 0.9799709724238026,
      "grad_norm": 0.28442281852866536,
      "kl": 0.775390625,
      "learning_rate": 1.022389979345395e-09,
      "loss": 0.031,
      "reward": 0.513671875,
      "reward_std": 0.1524379812180996,
      "rewards/correctness_reward_func": 0.046875,
      "rewards/strict_format_reward_func": 0.466796875,
      "step": 844
    },
    {
      "completion_length": 94.06640625,
      "epoch": 0.9811320754716981,
      "grad_norm": 0.8826859176334945,
      "kl": 0.9638671875,
      "learning_rate": 9.056817446422837e-10,
      "loss": 0.0385,
      "reward": 0.654296875,
      "reward_std": 0.1974649541079998,
      "rewards/correctness_reward_func": 0.1796875,
      "rewards/strict_format_reward_func": 0.474609375,
      "step": 845
    },
    {
      "completion_length": 79.28125,
      "epoch": 0.9822931785195936,
      "grad_norm": 0.3791539684323128,
      "kl": 0.9267578125,
      "learning_rate": 7.960384569353218e-10,
      "loss": 0.0371,
      "reward": 0.71484375,
      "reward_std": 0.21047081053256989,
      "rewards/correctness_reward_func": 0.234375,
      "rewards/strict_format_reward_func": 0.48046875,
      "step": 846
    },
    {
      "completion_length": 108.08203125,
      "epoch": 0.9834542815674892,
      "grad_norm": 0.3422747010711721,
      "kl": 0.8076171875,
      "learning_rate": 6.934616682837124e-10,
      "loss": 0.0323,
      "reward": 0.603515625,
      "reward_std": 0.1937086433172226,
      "rewards/correctness_reward_func": 0.1328125,
      "rewards/strict_format_reward_func": 0.470703125,
      "step": 847
    },
    {
      "completion_length": 97.17578125,
      "epoch": 0.9846153846153847,
      "grad_norm": 0.33149012384593757,
      "kl": 0.8212890625,
      "learning_rate": 5.979528307168413e-10,
      "loss": 0.0328,
      "reward": 0.6015625,
      "reward_std": 0.2046574354171753,
      "rewards/correctness_reward_func": 0.125,
      "rewards/strict_format_reward_func": 0.4765625,
      "step": 848
    },
    {
      "completion_length": 84.66796875,
      "epoch": 0.9857764876632801,
      "grad_norm": 0.33266210082696895,
      "kl": 0.849609375,
      "learning_rate": 5.095132962134041e-10,
      "loss": 0.034,
      "reward": 0.595703125,
      "reward_std": 0.12041803076863289,
      "rewards/correctness_reward_func": 0.1171875,
      "rewards/strict_format_reward_func": 0.478515625,
      "step": 849
    },
    {
      "completion_length": 97.4375,
      "epoch": 0.9869375907111756,
      "grad_norm": 0.3597098418523715,
      "kl": 0.904296875,
      "learning_rate": 4.281443166822551e-10,
      "loss": 0.0362,
      "reward": 0.5703125,
      "reward_std": 0.1608547791838646,
      "rewards/correctness_reward_func": 0.1015625,
      "rewards/strict_format_reward_func": 0.46875,
      "step": 850
    },
    {
      "completion_length": 100.85546875,
      "epoch": 0.9880986937590711,
      "grad_norm": 0.2561116808287349,
      "kl": 0.8583984375,
      "learning_rate": 3.5384704394481046e-10,
      "loss": 0.0343,
      "reward": 0.650390625,
      "reward_std": 0.18460902571678162,
      "rewards/correctness_reward_func": 0.171875,
      "rewards/strict_format_reward_func": 0.478515625,
      "step": 851
    },
    {
      "completion_length": 140.99609375,
      "epoch": 0.9892597968069666,
      "grad_norm": 1.4218780130474322,
      "kl": 1.0869140625,
      "learning_rate": 2.86622529718783e-10,
      "loss": 0.0435,
      "reward": 0.62890625,
      "reward_std": 0.1686672791838646,
      "rewards/correctness_reward_func": 0.171875,
      "rewards/strict_format_reward_func": 0.45703125,
      "step": 852
    },
    {
      "completion_length": 101.203125,
      "epoch": 0.9904208998548621,
      "grad_norm": 0.3886808376336542,
      "kl": 0.8095703125,
      "learning_rate": 2.2647172560308348e-10,
      "loss": 0.0324,
      "reward": 0.58984375,
      "reward_std": 0.1622929871082306,
      "rewards/correctness_reward_func": 0.1171875,
      "rewards/strict_format_reward_func": 0.47265625,
      "step": 853
    },
    {
      "completion_length": 95.56640625,
      "epoch": 0.9915820029027577,
      "grad_norm": 0.2910736695098456,
      "kl": 0.814453125,
      "learning_rate": 1.733954830644979e-10,
      "loss": 0.0326,
      "reward": 0.6640625,
      "reward_std": 0.22238586843013763,
      "rewards/correctness_reward_func": 0.1953125,
      "rewards/strict_format_reward_func": 0.46875,
      "step": 854
    },
    {
      "completion_length": 68.96484375,
      "epoch": 0.9927431059506531,
      "grad_norm": 0.22791001970995417,
      "kl": 0.791015625,
      "learning_rate": 1.2739455342558602e-10,
      "loss": 0.0316,
      "reward": 0.576171875,
      "reward_std": 0.09435429889708757,
      "rewards/correctness_reward_func": 0.09375,
      "rewards/strict_format_reward_func": 0.482421875,
      "step": 855
    },
    {
      "completion_length": 115.5625,
      "epoch": 0.9939042089985486,
      "grad_norm": 0.2720242704283282,
      "kl": 0.8046875,
      "learning_rate": 8.846958785418968e-11,
      "loss": 0.0322,
      "reward": 0.587890625,
      "reward_std": 0.21255707368254662,
      "rewards/correctness_reward_func": 0.1171875,
      "rewards/strict_format_reward_func": 0.470703125,
      "step": 856
    },
    {
      "completion_length": 178.5078125,
      "epoch": 0.9950653120464441,
      "grad_norm": 0.37942844211985594,
      "kl": 0.8994140625,
      "learning_rate": 5.6621137353940475e-11,
      "loss": 0.0359,
      "reward": 0.580078125,
      "reward_std": 0.1714797392487526,
      "rewards/correctness_reward_func": 0.125,
      "rewards/strict_format_reward_func": 0.455078125,
      "step": 857
    },
    {
      "completion_length": 108.4921875,
      "epoch": 0.9962264150943396,
      "grad_norm": 0.2655317280309368,
      "kl": 0.8046875,
      "learning_rate": 3.184965275676577e-11,
      "loss": 0.0322,
      "reward": 0.607421875,
      "reward_std": 0.1775227226316929,
      "rewards/correctness_reward_func": 0.1328125,
      "rewards/strict_format_reward_func": 0.474609375,
      "step": 858
    },
    {
      "completion_length": 79.0625,
      "epoch": 0.9973875181422351,
      "grad_norm": 0.38554037341055036,
      "kl": 0.8310546875,
      "learning_rate": 1.4155484716227295e-11,
      "loss": 0.0332,
      "reward": 0.70703125,
      "reward_std": 0.30047275498509407,
      "rewards/correctness_reward_func": 0.2265625,
      "rewards/strict_format_reward_func": 0.48046875,
      "step": 859
    },
    {
      "completion_length": 85.84375,
      "epoch": 0.9985486211901307,
      "grad_norm": 0.25703163189433775,
      "kl": 0.826171875,
      "learning_rate": 3.5388837027472418e-12,
      "loss": 0.0331,
      "reward": 0.65234375,
      "reward_std": 0.1968449354171753,
      "rewards/correctness_reward_func": 0.171875,
      "rewards/strict_format_reward_func": 0.48046875,
      "step": 860
    },
    {
      "completion_length": 78.97265625,
      "epoch": 0.9997097242380262,
      "grad_norm": 0.22828009089944065,
      "kl": 0.8037109375,
      "learning_rate": 0.0,
      "loss": 0.0322,
      "reward": 0.724609375,
      "reward_std": 0.16763926669955254,
      "rewards/correctness_reward_func": 0.2421875,
      "rewards/strict_format_reward_func": 0.482421875,
      "step": 861
    }
  ],
  "logging_steps": 1,
  "max_steps": 861,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 100,
  "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": 4,
  "trial_name": null,
  "trial_params": null
}