{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.03448228300299306,
  "eval_steps": 500,
  "global_step": 2500,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "all_correct": 0.25,
      "all_wrong": 0.0,
      "completion_length": 330.09375,
      "epoch": 1.3792913201197225e-05,
      "grad_norm": 2.238956052403626,
      "kl": 0.0,
      "learning_rate": 9.999999995305906e-07,
      "loss": 0.0,
      "reward": 1.9106249809265137,
      "reward_std": 0.18016189336776733,
      "rewards/accuracy_reward": 0.7918750047683716,
      "rewards/format_reward": 1.0,
      "step": 1
    },
    {
      "all_correct": 0.0,
      "all_wrong": 0.0,
      "completion_length": 376.03125,
      "epoch": 2.758582640239445e-05,
      "grad_norm": 2.425725981909806,
      "kl": 0.00069427490234375,
      "learning_rate": 9.999999981223625e-07,
      "loss": 0.0,
      "reward": 1.8987188339233398,
      "reward_std": 0.1683354675769806,
      "rewards/accuracy_reward": 0.7549687027931213,
      "rewards/format_reward": 1.0,
      "step": 2
    },
    {
      "all_correct": 0.0,
      "all_wrong": 0.0,
      "completion_length": 343.71875,
      "epoch": 4.137873960359168e-05,
      "grad_norm": 2.6361672047505698,
      "kl": 0.000736236572265625,
      "learning_rate": 9.999999957753156e-07,
      "loss": 0.0,
      "reward": 1.870500087738037,
      "reward_std": 0.13440653681755066,
      "rewards/accuracy_reward": 0.7267500162124634,
      "rewards/format_reward": 1.0,
      "step": 3
    },
    {
      "all_correct": 0.0,
      "all_wrong": 0.0,
      "completion_length": 346.5,
      "epoch": 5.51716528047889e-05,
      "grad_norm": 1.920993511756084,
      "kl": 0.000751495361328125,
      "learning_rate": 9.9999999248945e-07,
      "loss": 0.0,
      "reward": 2.0257186889648438,
      "reward_std": 0.10654528439044952,
      "rewards/accuracy_reward": 0.8944687247276306,
      "rewards/format_reward": 1.0,
      "step": 4
    },
    {
      "all_correct": 0.0,
      "all_wrong": 0.0,
      "completion_length": 386.375,
      "epoch": 6.896456600598612e-05,
      "grad_norm": 6.553090219822929,
      "kl": 0.0008087158203125,
      "learning_rate": 9.999999882647657e-07,
      "loss": 0.0,
      "reward": 1.8300312757492065,
      "reward_std": 0.2219369113445282,
      "rewards/accuracy_reward": 0.7112812399864197,
      "rewards/format_reward": 0.96875,
      "step": 5
    },
    {
      "all_correct": 0.0,
      "all_wrong": 0.0,
      "completion_length": 384.4375,
      "epoch": 8.275747920718336e-05,
      "grad_norm": 2.8837391275739344,
      "kl": 0.00110626220703125,
      "learning_rate": 9.999999831012624e-07,
      "loss": 0.0,
      "reward": 1.9354686737060547,
      "reward_std": 0.14949820935726166,
      "rewards/accuracy_reward": 0.7729687690734863,
      "rewards/format_reward": 1.0,
      "step": 6
    },
    {
      "all_correct": 0.0,
      "all_wrong": 0.0,
      "completion_length": 384.84375,
      "epoch": 9.655039240838057e-05,
      "grad_norm": 4.733787626862378,
      "kl": 0.001739501953125,
      "learning_rate": 9.999999769989408e-07,
      "loss": 0.0001,
      "reward": 1.861781358718872,
      "reward_std": 0.14443737268447876,
      "rewards/accuracy_reward": 0.6992812752723694,
      "rewards/format_reward": 1.0,
      "step": 7
    },
    {
      "all_correct": 0.25,
      "all_wrong": 0.0,
      "completion_length": 387.59375,
      "epoch": 0.0001103433056095778,
      "grad_norm": 1.9859377598029717,
      "kl": 0.001922607421875,
      "learning_rate": 9.999999699578e-07,
      "loss": 0.0001,
      "reward": 2.033656358718872,
      "reward_std": 0.09668964147567749,
      "rewards/accuracy_reward": 0.8774062991142273,
      "rewards/format_reward": 1.0,
      "step": 8
    },
    {
      "all_correct": 0.0,
      "all_wrong": 0.0,
      "completion_length": 404.21875,
      "epoch": 0.00012413621881077503,
      "grad_norm": 2.2445824718340517,
      "kl": 0.001953125,
      "learning_rate": 9.99999961977841e-07,
      "loss": 0.0001,
      "reward": 2.036250114440918,
      "reward_std": 0.10071505606174469,
      "rewards/accuracy_reward": 0.8487499356269836,
      "rewards/format_reward": 1.0,
      "step": 9
    },
    {
      "all_correct": 0.0,
      "all_wrong": 0.0,
      "completion_length": 393.15625,
      "epoch": 0.00013792913201197225,
      "grad_norm": 2.0067474304549084,
      "kl": 0.0026397705078125,
      "learning_rate": 9.99999953059063e-07,
      "loss": 0.0001,
      "reward": 1.9812188148498535,
      "reward_std": 0.16516642272472382,
      "rewards/accuracy_reward": 0.8124687671661377,
      "rewards/format_reward": 1.0,
      "step": 10
    },
    {
      "all_correct": 0.0,
      "all_wrong": 0.0,
      "completion_length": 405.9375,
      "epoch": 0.00015172204521316947,
      "grad_norm": 1.8764629345450639,
      "kl": 0.0032501220703125,
      "learning_rate": 9.999999432014664e-07,
      "loss": 0.0001,
      "reward": 1.925624966621399,
      "reward_std": 0.20176257193088531,
      "rewards/accuracy_reward": 0.7693750262260437,
      "rewards/format_reward": 1.0,
      "step": 11
    },
    {
      "all_correct": 0.0,
      "all_wrong": 0.0,
      "completion_length": 434.90625,
      "epoch": 0.0001655149584143667,
      "grad_norm": 1.9816398853663497,
      "kl": 0.0036163330078125,
      "learning_rate": 9.999999324050513e-07,
      "loss": 0.0001,
      "reward": 1.9718124866485596,
      "reward_std": 0.15928256511688232,
      "rewards/accuracy_reward": 0.8155624270439148,
      "rewards/format_reward": 1.0,
      "step": 12
    },
    {
      "all_correct": 0.0,
      "all_wrong": 0.0,
      "completion_length": 448.9375,
      "epoch": 0.00017930787161556393,
      "grad_norm": 2.235913774661294,
      "kl": 0.00537109375,
      "learning_rate": 9.999999206698174e-07,
      "loss": 0.0002,
      "reward": 1.8944687843322754,
      "reward_std": 0.13046111166477203,
      "rewards/accuracy_reward": 0.7444687485694885,
      "rewards/format_reward": 1.0,
      "step": 13
    },
    {
      "all_correct": 0.0,
      "all_wrong": 0.0,
      "completion_length": 449.0625,
      "epoch": 0.00019310078481676114,
      "grad_norm": 2.1547272625309453,
      "kl": 0.00537109375,
      "learning_rate": 9.99999907995765e-07,
      "loss": 0.0002,
      "reward": 1.9081875085830688,
      "reward_std": 0.17851057648658752,
      "rewards/accuracy_reward": 0.7456874847412109,
      "rewards/format_reward": 1.0,
      "step": 14
    },
    {
      "all_correct": 0.0,
      "all_wrong": 0.0,
      "completion_length": 454.03125,
      "epoch": 0.00020689369801795836,
      "grad_norm": 1.8688326807239954,
      "kl": 0.00531005859375,
      "learning_rate": 9.99999894382894e-07,
      "loss": 0.0002,
      "reward": 1.847000002861023,
      "reward_std": 0.29689547419548035,
      "rewards/accuracy_reward": 0.7095000147819519,
      "rewards/format_reward": 0.96875,
      "step": 15
    },
    {
      "all_correct": 0.0,
      "all_wrong": 0.0,
      "completion_length": 448.90625,
      "epoch": 0.0002206866112191556,
      "grad_norm": 1.877697097527582,
      "kl": 0.006103515625,
      "learning_rate": 9.999998798312043e-07,
      "loss": 0.0002,
      "reward": 1.8849375247955322,
      "reward_std": 0.18553191423416138,
      "rewards/accuracy_reward": 0.7224375605583191,
      "rewards/format_reward": 1.0,
      "step": 16
    },
    {
      "all_correct": 0.0,
      "all_wrong": 0.0,
      "completion_length": 446.53125,
      "epoch": 0.00023447952442035282,
      "grad_norm": 2.948823192525603,
      "kl": 0.006011962890625,
      "learning_rate": 9.999998643406962e-07,
      "loss": 0.0002,
      "reward": 1.9022188186645508,
      "reward_std": 0.1289326548576355,
      "rewards/accuracy_reward": 0.7147186994552612,
      "rewards/format_reward": 1.0,
      "step": 17
    },
    {
      "all_correct": 0.0,
      "all_wrong": 0.0,
      "completion_length": 449.9375,
      "epoch": 0.00024827243762155007,
      "grad_norm": 2.3773367391075633,
      "kl": 0.006011962890625,
      "learning_rate": 9.999998479113697e-07,
      "loss": 0.0002,
      "reward": 1.9257500171661377,
      "reward_std": 0.17228159308433533,
      "rewards/accuracy_reward": 0.750749945640564,
      "rewards/format_reward": 1.0,
      "step": 18
    },
    {
      "all_correct": 0.0,
      "all_wrong": 0.0,
      "completion_length": 449.6875,
      "epoch": 0.0002620653508227473,
      "grad_norm": 1.9233344476825995,
      "kl": 0.005584716796875,
      "learning_rate": 9.999998305432246e-07,
      "loss": 0.0002,
      "reward": 1.9933750629425049,
      "reward_std": 0.17885765433311462,
      "rewards/accuracy_reward": 0.8246250152587891,
      "rewards/format_reward": 1.0,
      "step": 19
    },
    {
      "all_correct": 0.0,
      "all_wrong": 0.0,
      "completion_length": 438.75,
      "epoch": 0.0002758582640239445,
      "grad_norm": 2.0098045856353592,
      "kl": 0.00653076171875,
      "learning_rate": 9.999998122362611e-07,
      "loss": 0.0003,
      "reward": 1.9439375400543213,
      "reward_std": 0.1554916799068451,
      "rewards/accuracy_reward": 0.7814374566078186,
      "rewards/format_reward": 1.0,
      "step": 20
    },
    {
      "all_correct": 0.0,
      "all_wrong": 0.0,
      "completion_length": 424.75,
      "epoch": 0.0002896511772251417,
      "grad_norm": 2.0840967435424096,
      "kl": 0.007080078125,
      "learning_rate": 9.999997929904793e-07,
      "loss": 0.0003,
      "reward": 1.913562536239624,
      "reward_std": 0.21141326427459717,
      "rewards/accuracy_reward": 0.7760624885559082,
      "rewards/format_reward": 0.96875,
      "step": 21
    },
    {
      "all_correct": 0.25,
      "all_wrong": 0.0,
      "completion_length": 427.46875,
      "epoch": 0.00030344409042633893,
      "grad_norm": 2.441428436063154,
      "kl": 0.00701904296875,
      "learning_rate": 9.99999772805879e-07,
      "loss": 0.0003,
      "reward": 2.0033750534057617,
      "reward_std": 0.09448859095573425,
      "rewards/accuracy_reward": 0.8408750295639038,
      "rewards/format_reward": 1.0,
      "step": 22
    },
    {
      "all_correct": 0.0,
      "all_wrong": 0.0,
      "completion_length": 439.75,
      "epoch": 0.00031723700362753615,
      "grad_norm": 3.8166061083190286,
      "kl": 0.00726318359375,
      "learning_rate": 9.999997516824604e-07,
      "loss": 0.0003,
      "reward": 1.8932501077651978,
      "reward_std": 0.18665450811386108,
      "rewards/accuracy_reward": 0.7120000123977661,
      "rewards/format_reward": 1.0,
      "step": 23
    },
    {
      "all_correct": 0.0,
      "all_wrong": 0.0,
      "completion_length": 409.625,
      "epoch": 0.0003310299168287334,
      "grad_norm": 2.1091114967614555,
      "kl": 0.006134033203125,
      "learning_rate": 9.999997296202233e-07,
      "loss": 0.0002,
      "reward": 1.9282188415527344,
      "reward_std": 0.20147812366485596,
      "rewards/accuracy_reward": 0.7782187461853027,
      "rewards/format_reward": 1.0,
      "step": 24
    },
    {
      "all_correct": 0.25,
      "all_wrong": 0.0,
      "completion_length": 419.9375,
      "epoch": 0.00034482283002993064,
      "grad_norm": 1.8649375597170077,
      "kl": 0.005859375,
      "learning_rate": 9.999997066191683e-07,
      "loss": 0.0002,
      "reward": 2.001406192779541,
      "reward_std": 0.1283920705318451,
      "rewards/accuracy_reward": 0.8264062404632568,
      "rewards/format_reward": 1.0,
      "step": 25
    },
    {
      "all_correct": 0.0,
      "all_wrong": 0.0,
      "completion_length": 413.0625,
      "epoch": 0.00035861574323112785,
      "grad_norm": 2.0908467800291706,
      "kl": 0.00714111328125,
      "learning_rate": 9.999996826792949e-07,
      "loss": 0.0003,
      "reward": 1.9485938549041748,
      "reward_std": 0.15018907189369202,
      "rewards/accuracy_reward": 0.7735937833786011,
      "rewards/format_reward": 1.0,
      "step": 26
    },
    {
      "all_correct": 0.0,
      "all_wrong": 0.0,
      "completion_length": 437.75,
      "epoch": 0.00037240865643232507,
      "grad_norm": 2.1459856824688344,
      "kl": 0.00726318359375,
      "learning_rate": 9.999996578006036e-07,
      "loss": 0.0003,
      "reward": 1.926218867301941,
      "reward_std": 0.13377031683921814,
      "rewards/accuracy_reward": 0.7824687957763672,
      "rewards/format_reward": 1.0,
      "step": 27
    },
    {
      "all_correct": 0.25,
      "all_wrong": 0.0,
      "completion_length": 393.46875,
      "epoch": 0.0003862015696335223,
      "grad_norm": 1.660251827892846,
      "kl": 0.00738525390625,
      "learning_rate": 9.99999631983094e-07,
      "loss": 0.0003,
      "reward": 2.0258748531341553,
      "reward_std": 0.09291009604930878,
      "rewards/accuracy_reward": 0.8383749723434448,
      "rewards/format_reward": 1.0,
      "step": 28
    },
    {
      "all_correct": 0.0,
      "all_wrong": 0.0,
      "completion_length": 428.3125,
      "epoch": 0.0003999944828347195,
      "grad_norm": 2.4442043129587425,
      "kl": 0.00701904296875,
      "learning_rate": 9.999996052267663e-07,
      "loss": 0.0003,
      "reward": 1.8992187976837158,
      "reward_std": 0.15343788266181946,
      "rewards/accuracy_reward": 0.7242187261581421,
      "rewards/format_reward": 1.0,
      "step": 29
    },
    {
      "all_correct": 0.0,
      "all_wrong": 0.0,
      "completion_length": 408.46875,
      "epoch": 0.0004137873960359167,
      "grad_norm": 1.941546303448589,
      "kl": 0.006744384765625,
      "learning_rate": 9.999995775316205e-07,
      "loss": 0.0003,
      "reward": 1.9279687404632568,
      "reward_std": 0.23424255847930908,
      "rewards/accuracy_reward": 0.8092187643051147,
      "rewards/format_reward": 0.96875,
      "step": 30
    },
    {
      "all_correct": 0.0,
      "all_wrong": 0.0,
      "completion_length": 410.15625,
      "epoch": 0.000427580309237114,
      "grad_norm": 1.939380030838396,
      "kl": 0.007568359375,
      "learning_rate": 9.99999548897657e-07,
      "loss": 0.0003,
      "reward": 1.9720938205718994,
      "reward_std": 0.1112823337316513,
      "rewards/accuracy_reward": 0.7908437252044678,
      "rewards/format_reward": 1.0,
      "step": 31
    },
    {
      "all_correct": 0.0,
      "all_wrong": 0.0,
      "completion_length": 401.6875,
      "epoch": 0.0004413732224383112,
      "grad_norm": 1.8102874359675372,
      "kl": 0.006561279296875,
      "learning_rate": 9.999995193248753e-07,
      "loss": 0.0003,
      "reward": 1.8945938348770142,
      "reward_std": 0.20895081758499146,
      "rewards/accuracy_reward": 0.7320938110351562,
      "rewards/format_reward": 1.0,
      "step": 32
    },
    {
      "all_correct": 0.25,
      "all_wrong": 0.0,
      "completion_length": 417.28125,
      "epoch": 0.0004551661356395084,
      "grad_norm": 2.440861370440923,
      "kl": 0.0078125,
      "learning_rate": 9.99999488813276e-07,
      "loss": 0.0003,
      "reward": 1.9929375648498535,
      "reward_std": 0.14452257752418518,
      "rewards/accuracy_reward": 0.7991874814033508,
      "rewards/format_reward": 1.0,
      "step": 33
    },
    {
      "all_correct": 0.25,
      "all_wrong": 0.0,
      "completion_length": 431.96875,
      "epoch": 0.00046895904884070564,
      "grad_norm": 2.634597469540262,
      "kl": 0.00665283203125,
      "learning_rate": 9.999994573628587e-07,
      "loss": 0.0003,
      "reward": 2.0103750228881836,
      "reward_std": 0.1038256287574768,
      "rewards/accuracy_reward": 0.8353750109672546,
      "rewards/format_reward": 1.0,
      "step": 34
    },
    {
      "all_correct": 0.25,
      "all_wrong": 0.0,
      "completion_length": 403.625,
      "epoch": 0.00048275196204190286,
      "grad_norm": 1.9498064618486233,
      "kl": 0.00811767578125,
      "learning_rate": 9.99999424973624e-07,
      "loss": 0.0003,
      "reward": 1.9167187213897705,
      "reward_std": 0.13575075566768646,
      "rewards/accuracy_reward": 0.7292187809944153,
      "rewards/format_reward": 1.0,
      "step": 35
    },
    {
      "all_correct": 0.0,
      "all_wrong": 0.0,
      "completion_length": 398.59375,
      "epoch": 0.0004965448752431001,
      "grad_norm": 1.97400223525883,
      "kl": 0.00732421875,
      "learning_rate": 9.999993916455714e-07,
      "loss": 0.0003,
      "reward": 1.9462811946868896,
      "reward_std": 0.21417558193206787,
      "rewards/accuracy_reward": 0.7712812423706055,
      "rewards/format_reward": 1.0,
      "step": 36
    },
    {
      "all_correct": 0.0,
      "all_wrong": 0.0,
      "completion_length": 412.4375,
      "epoch": 0.0005103377884442973,
      "grad_norm": 1.96676548570803,
      "kl": 0.007598876953125,
      "learning_rate": 9.99999357378701e-07,
      "loss": 0.0003,
      "reward": 1.9428437948226929,
      "reward_std": 0.1451302170753479,
      "rewards/accuracy_reward": 0.7553436756134033,
      "rewards/format_reward": 1.0,
      "step": 37
    },
    {
      "all_correct": 0.25,
      "all_wrong": 0.0,
      "completion_length": 406.25,
      "epoch": 0.0005241307016454946,
      "grad_norm": 1.8500098748913225,
      "kl": 0.0087890625,
      "learning_rate": 9.999993221730135e-07,
      "loss": 0.0004,
      "reward": 1.9378750324249268,
      "reward_std": 0.099956214427948,
      "rewards/accuracy_reward": 0.750374972820282,
      "rewards/format_reward": 1.0,
      "step": 38
    },
    {
      "all_correct": 0.0,
      "all_wrong": 0.0,
      "completion_length": 418.1875,
      "epoch": 0.0005379236148466917,
      "grad_norm": 2.228539734236883,
      "kl": 0.007568359375,
      "learning_rate": 9.99999286028508e-07,
      "loss": 0.0003,
      "reward": 1.815812587738037,
      "reward_std": 0.11345121264457703,
      "rewards/accuracy_reward": 0.6470625400543213,
      "rewards/format_reward": 1.0,
      "step": 39
    },
    {
      "all_correct": 0.0,
      "all_wrong": 0.0,
      "completion_length": 389.71875,
      "epoch": 0.000551716528047889,
      "grad_norm": 2.050035893914353,
      "kl": 0.007354736328125,
      "learning_rate": 9.999992489451854e-07,
      "loss": 0.0003,
      "reward": 1.8904376029968262,
      "reward_std": 0.15531973540782928,
      "rewards/accuracy_reward": 0.7216874957084656,
      "rewards/format_reward": 1.0,
      "step": 40
    },
    {
      "all_correct": 0.25,
      "all_wrong": 0.0,
      "completion_length": 434.0,
      "epoch": 0.0005655094412490863,
      "grad_norm": 2.2963652984261387,
      "kl": 0.00872802734375,
      "learning_rate": 9.999992109230455e-07,
      "loss": 0.0003,
      "reward": 1.9235312938690186,
      "reward_std": 0.10360515117645264,
      "rewards/accuracy_reward": 0.7297812104225159,
      "rewards/format_reward": 1.0,
      "step": 41
    },
    {
      "all_correct": 0.25,
      "all_wrong": 0.0,
      "completion_length": 404.5,
      "epoch": 0.0005793023544502834,
      "grad_norm": 1.9915290036304918,
      "kl": 0.00872802734375,
      "learning_rate": 9.999991719620882e-07,
      "loss": 0.0003,
      "reward": 2.003124952316284,
      "reward_std": 0.14130809903144836,
      "rewards/accuracy_reward": 0.8218749761581421,
      "rewards/format_reward": 1.0,
      "step": 42
    },
    {
      "all_correct": 0.25,
      "all_wrong": 0.0,
      "completion_length": 380.0,
      "epoch": 0.0005930952676514807,
      "grad_norm": 2.0683840656172783,
      "kl": 0.0103759765625,
      "learning_rate": 9.999991320623139e-07,
      "loss": 0.0004,
      "reward": 2.047468900680542,
      "reward_std": 0.10697433352470398,
      "rewards/accuracy_reward": 0.8662187457084656,
      "rewards/format_reward": 1.0,
      "step": 43
    },
    {
      "all_correct": 0.25,
      "all_wrong": 0.0,
      "completion_length": 397.1875,
      "epoch": 0.0006068881808526779,
      "grad_norm": 2.794135333481504,
      "kl": 0.00933837890625,
      "learning_rate": 9.999990912237223e-07,
      "loss": 0.0004,
      "reward": 1.9695312976837158,
      "reward_std": 0.1284584403038025,
      "rewards/accuracy_reward": 0.76953125,
      "rewards/format_reward": 1.0,
      "step": 44
    },
    {
      "all_correct": 0.25,
      "all_wrong": 0.0,
      "completion_length": 417.0,
      "epoch": 0.0006206810940538751,
      "grad_norm": 3.3140997714530607,
      "kl": 0.00872802734375,
      "learning_rate": 9.999990494463137e-07,
      "loss": 0.0003,
      "reward": 2.109499931335449,
      "reward_std": 0.08382292836904526,
      "rewards/accuracy_reward": 0.934499979019165,
      "rewards/format_reward": 1.0,
      "step": 45
    },
    {
      "all_correct": 0.0,
      "all_wrong": 0.0,
      "completion_length": 409.03125,
      "epoch": 0.0006344740072550723,
      "grad_norm": 1.9271837639283826,
      "kl": 0.00933837890625,
      "learning_rate": 9.999990067300881e-07,
      "loss": 0.0004,
      "reward": 1.7727187871932983,
      "reward_std": 0.15261155366897583,
      "rewards/accuracy_reward": 0.5914687514305115,
      "rewards/format_reward": 1.0,
      "step": 46
    },
    {
      "all_correct": 0.25,
      "all_wrong": 0.0,
      "completion_length": 408.6875,
      "epoch": 0.0006482669204562696,
      "grad_norm": 1.9746881047259788,
      "kl": 0.00860595703125,
      "learning_rate": 9.999989630750455e-07,
      "loss": 0.0003,
      "reward": 1.9672812223434448,
      "reward_std": 0.1265501081943512,
      "rewards/accuracy_reward": 0.7860312461853027,
      "rewards/format_reward": 1.0,
      "step": 47
    },
    {
      "all_correct": 0.0,
      "all_wrong": 0.0,
      "completion_length": 401.125,
      "epoch": 0.0006620598336574668,
      "grad_norm": 2.16103713753327,
      "kl": 0.0093994140625,
      "learning_rate": 9.999989184811863e-07,
      "loss": 0.0004,
      "reward": 1.9534375667572021,
      "reward_std": 0.14682571589946747,
      "rewards/accuracy_reward": 0.7721874713897705,
      "rewards/format_reward": 1.0,
      "step": 48
    },
    {
      "all_correct": 0.25,
      "all_wrong": 0.0,
      "completion_length": 405.28125,
      "epoch": 0.000675852746858664,
      "grad_norm": 4.506059479243003,
      "kl": 0.009765625,
      "learning_rate": 9.999988729485103e-07,
      "loss": 0.0004,
      "reward": 2.007718801498413,
      "reward_std": 0.10468215495347977,
      "rewards/accuracy_reward": 0.8202187418937683,
      "rewards/format_reward": 1.0,
      "step": 49
    },
    {
      "all_correct": 0.25,
      "all_wrong": 0.0,
      "completion_length": 396.1875,
      "epoch": 0.0006896456600598613,
      "grad_norm": 2.7545928479935124,
      "kl": 0.00830078125,
      "learning_rate": 9.999988264770175e-07,
      "loss": 0.0003,
      "reward": 1.9384374618530273,
      "reward_std": 0.15367849171161652,
      "rewards/accuracy_reward": 0.7696875333786011,
      "rewards/format_reward": 1.0,
      "step": 50
    },
    {
      "all_correct": 0.0,
      "all_wrong": 0.0,
      "completion_length": 396.0625,
      "epoch": 0.0007034385732610584,
      "grad_norm": 2.06060525063386,
      "kl": 0.0115966796875,
      "learning_rate": 9.999987790667086e-07,
      "loss": 0.0005,
      "reward": 1.9795312881469727,
      "reward_std": 0.1289536952972412,
      "rewards/accuracy_reward": 0.8295312523841858,
      "rewards/format_reward": 1.0,
      "step": 51
    },
    {
      "all_correct": 0.0,
      "all_wrong": 0.0,
      "completion_length": 391.46875,
      "epoch": 0.0007172314864622557,
      "grad_norm": 2.201080580950615,
      "kl": 0.01141357421875,
      "learning_rate": 9.999987307175828e-07,
      "loss": 0.0005,
      "reward": 2.025031328201294,
      "reward_std": 0.12147818505764008,
      "rewards/accuracy_reward": 0.8375312685966492,
      "rewards/format_reward": 1.0,
      "step": 52
    },
    {
      "all_correct": 0.25,
      "all_wrong": 0.0,
      "completion_length": 402.40625,
      "epoch": 0.0007310243996634529,
      "grad_norm": 2.789599554476296,
      "kl": 0.01031494140625,
      "learning_rate": 9.999986814296409e-07,
      "loss": 0.0004,
      "reward": 2.0395936965942383,
      "reward_std": 0.12432658672332764,
      "rewards/accuracy_reward": 0.8645938038825989,
      "rewards/format_reward": 1.0,
      "step": 53
    },
    {
      "all_correct": 0.0,
      "all_wrong": 0.0,
      "completion_length": 403.75,
      "epoch": 0.0007448173128646501,
      "grad_norm": 2.0780164567674855,
      "kl": 0.0103759765625,
      "learning_rate": 9.999986312028826e-07,
      "loss": 0.0004,
      "reward": 1.9655625820159912,
      "reward_std": 0.09623858332633972,
      "rewards/accuracy_reward": 0.7718124985694885,
      "rewards/format_reward": 1.0,
      "step": 54
    },
    {
      "all_correct": 0.0,
      "all_wrong": 0.0,
      "completion_length": 403.0625,
      "epoch": 0.0007586102260658474,
      "grad_norm": 2.034057056271373,
      "kl": 0.0113525390625,
      "learning_rate": 9.99998580037308e-07,
      "loss": 0.0005,
      "reward": 2.0223751068115234,
      "reward_std": 0.10908350348472595,
      "rewards/accuracy_reward": 0.8348749876022339,
      "rewards/format_reward": 1.0,
      "step": 55
    },
    {
      "all_correct": 0.25,
      "all_wrong": 0.0,
      "completion_length": 412.09375,
      "epoch": 0.0007724031392670446,
      "grad_norm": 3.5188726986869936,
      "kl": 0.01123046875,
      "learning_rate": 9.999985279329174e-07,
      "loss": 0.0004,
      "reward": 1.953125,
      "reward_std": 0.1149853765964508,
      "rewards/accuracy_reward": 0.7593749761581421,
      "rewards/format_reward": 1.0,
      "step": 56
    },
    {
      "all_correct": 0.0,
      "all_wrong": 0.0,
      "completion_length": 405.28125,
      "epoch": 0.0007861960524682418,
      "grad_norm": 2.234293267617364,
      "kl": 0.0118408203125,
      "learning_rate": 9.999984748897108e-07,
      "loss": 0.0005,
      "reward": 1.9143438339233398,
      "reward_std": 0.12217641621828079,
      "rewards/accuracy_reward": 0.7205937504768372,
      "rewards/format_reward": 1.0,
      "step": 57
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.0,
      "completion_length": 396.65625,
      "epoch": 0.000799988965669439,
      "grad_norm": 1.9985754265007123,
      "kl": 0.0120849609375,
      "learning_rate": 9.999984209076883e-07,
      "loss": 0.0005,
      "reward": 2.0999374389648438,
      "reward_std": 0.06573973596096039,
      "rewards/accuracy_reward": 0.9061875343322754,
      "rewards/format_reward": 1.0,
      "step": 58
    },
    {
      "all_correct": 0.0,
      "all_wrong": 0.0,
      "completion_length": 406.125,
      "epoch": 0.0008137818788706363,
      "grad_norm": 2.51497917133664,
      "kl": 0.0128173828125,
      "learning_rate": 9.999983659868502e-07,
      "loss": 0.0005,
      "reward": 1.9672188758850098,
      "reward_std": 0.1114722415804863,
      "rewards/accuracy_reward": 0.7734687328338623,
      "rewards/format_reward": 1.0,
      "step": 59
    },
    {
      "all_correct": 0.0,
      "all_wrong": 0.0,
      "completion_length": 411.3125,
      "epoch": 0.0008275747920718334,
      "grad_norm": 2.382568986637134,
      "kl": 0.01434326171875,
      "learning_rate": 9.999983101271964e-07,
      "loss": 0.0006,
      "reward": 1.9099063873291016,
      "reward_std": 0.11956294625997543,
      "rewards/accuracy_reward": 0.7161562442779541,
      "rewards/format_reward": 1.0,
      "step": 60
    },
    {
      "all_correct": 0.0,
      "all_wrong": 0.0,
      "completion_length": 419.34375,
      "epoch": 0.0008413677052730307,
      "grad_norm": 2.3339976498187918,
      "kl": 0.01361083984375,
      "learning_rate": 9.999982533287268e-07,
      "loss": 0.0005,
      "reward": 1.914156436920166,
      "reward_std": 0.11630599945783615,
      "rewards/accuracy_reward": 0.7204062342643738,
      "rewards/format_reward": 1.0,
      "step": 61
    },
    {
      "all_correct": 0.0,
      "all_wrong": 0.0,
      "completion_length": 414.1875,
      "epoch": 0.000855160618474228,
      "grad_norm": 2.0397915840923666,
      "kl": 0.0125732421875,
      "learning_rate": 9.999981955914419e-07,
      "loss": 0.0005,
      "reward": 2.0025625228881836,
      "reward_std": 0.09353870898485184,
      "rewards/accuracy_reward": 0.8025624752044678,
      "rewards/format_reward": 1.0,
      "step": 62
    },
    {
      "all_correct": 0.0,
      "all_wrong": 0.0,
      "completion_length": 406.6875,
      "epoch": 0.0008689535316754251,
      "grad_norm": 2.7440557394184113,
      "kl": 0.0137939453125,
      "learning_rate": 9.999981369153415e-07,
      "loss": 0.0006,
      "reward": 1.9893436431884766,
      "reward_std": 0.10104025900363922,
      "rewards/accuracy_reward": 0.8018437623977661,
      "rewards/format_reward": 1.0,
      "step": 63
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.0,
      "completion_length": 400.34375,
      "epoch": 0.0008827464448766224,
      "grad_norm": 3.187129970062904,
      "kl": 0.0137939453125,
      "learning_rate": 9.99998077300426e-07,
      "loss": 0.0006,
      "reward": 2.0980000495910645,
      "reward_std": 0.08940361440181732,
      "rewards/accuracy_reward": 0.9104999899864197,
      "rewards/format_reward": 1.0,
      "step": 64
    },
    {
      "all_correct": 0.25,
      "all_wrong": 0.0,
      "completion_length": 382.90625,
      "epoch": 0.0008965393580778196,
      "grad_norm": 2.2765766881694027,
      "kl": 0.01507568359375,
      "learning_rate": 9.99998016746695e-07,
      "loss": 0.0006,
      "reward": 2.0280938148498535,
      "reward_std": 0.12347737699747086,
      "rewards/accuracy_reward": 0.8593437671661377,
      "rewards/format_reward": 1.0,
      "step": 65
    },
    {
      "all_correct": 0.25,
      "all_wrong": 0.0,
      "completion_length": 406.03125,
      "epoch": 0.0009103322712790169,
      "grad_norm": 2.059881050081888,
      "kl": 0.01513671875,
      "learning_rate": 9.999979552541493e-07,
      "loss": 0.0006,
      "reward": 1.9948437213897705,
      "reward_std": 0.09006933122873306,
      "rewards/accuracy_reward": 0.8010937571525574,
      "rewards/format_reward": 1.0,
      "step": 66
    },
    {
      "all_correct": 0.25,
      "all_wrong": 0.0,
      "completion_length": 392.78125,
      "epoch": 0.000924125184480214,
      "grad_norm": 1.9240285675429754,
      "kl": 0.0142822265625,
      "learning_rate": 9.999978928227889e-07,
      "loss": 0.0006,
      "reward": 2.0140626430511475,
      "reward_std": 0.08456151187419891,
      "rewards/accuracy_reward": 0.8265625238418579,
      "rewards/format_reward": 1.0,
      "step": 67
    },
    {
      "all_correct": 0.0,
      "all_wrong": 0.0,
      "completion_length": 398.625,
      "epoch": 0.0009379180976814113,
      "grad_norm": 2.063638176454996,
      "kl": 0.015625,
      "learning_rate": 9.999978294526131e-07,
      "loss": 0.0006,
      "reward": 1.9393125772476196,
      "reward_std": 0.11400812119245529,
      "rewards/accuracy_reward": 0.770562469959259,
      "rewards/format_reward": 1.0,
      "step": 68
    },
    {
      "all_correct": 0.25,
      "all_wrong": 0.0,
      "completion_length": 413.21875,
      "epoch": 0.0009517110108826086,
      "grad_norm": 2.364884988934533,
      "kl": 0.0167236328125,
      "learning_rate": 9.999977651436231e-07,
      "loss": 0.0007,
      "reward": 2.0544376373291016,
      "reward_std": 0.09280771017074585,
      "rewards/accuracy_reward": 0.866937518119812,
      "rewards/format_reward": 1.0,
      "step": 69
    },
    {
      "all_correct": 0.0,
      "all_wrong": 0.0,
      "completion_length": 404.59375,
      "epoch": 0.0009655039240838057,
      "grad_norm": 1.9801870748243584,
      "kl": 0.017333984375,
      "learning_rate": 9.999976998958184e-07,
      "loss": 0.0007,
      "reward": 1.9036874771118164,
      "reward_std": 0.07547667622566223,
      "rewards/accuracy_reward": 0.7224375009536743,
      "rewards/format_reward": 1.0,
      "step": 70
    },
    {
      "all_correct": 0.25,
      "all_wrong": 0.0,
      "completion_length": 420.84375,
      "epoch": 0.000979296837285003,
      "grad_norm": 2.2231607732222174,
      "kl": 0.0177001953125,
      "learning_rate": 9.999976337091992e-07,
      "loss": 0.0007,
      "reward": 1.9744688272476196,
      "reward_std": 0.11905109882354736,
      "rewards/accuracy_reward": 0.793218731880188,
      "rewards/format_reward": 1.0,
      "step": 71
    },
    {
      "all_correct": 0.0,
      "all_wrong": 0.0,
      "completion_length": 406.03125,
      "epoch": 0.0009930897504862003,
      "grad_norm": 1.9324225599040201,
      "kl": 0.01806640625,
      "learning_rate": 9.999975665837658e-07,
      "loss": 0.0007,
      "reward": 1.916468858718872,
      "reward_std": 0.13691526651382446,
      "rewards/accuracy_reward": 0.7352187037467957,
      "rewards/format_reward": 1.0,
      "step": 72
    },
    {
      "all_correct": 0.0,
      "all_wrong": 0.0,
      "completion_length": 403.65625,
      "epoch": 0.0010068826636873973,
      "grad_norm": 2.1967236353102644,
      "kl": 0.0189208984375,
      "learning_rate": 9.999974985195181e-07,
      "loss": 0.0008,
      "reward": 1.9445313215255737,
      "reward_std": 0.09076535701751709,
      "rewards/accuracy_reward": 0.7445312738418579,
      "rewards/format_reward": 1.0,
      "step": 73
    },
    {
      "all_correct": 0.25,
      "all_wrong": 0.0,
      "completion_length": 386.53125,
      "epoch": 0.0010206755768885946,
      "grad_norm": 1.975824500724877,
      "kl": 0.0196533203125,
      "learning_rate": 9.999974295164566e-07,
      "loss": 0.0008,
      "reward": 1.9469687938690186,
      "reward_std": 0.12988199293613434,
      "rewards/accuracy_reward": 0.7844687700271606,
      "rewards/format_reward": 1.0,
      "step": 74
    },
    {
      "all_correct": 0.25,
      "all_wrong": 0.0,
      "completion_length": 406.09375,
      "epoch": 0.0010344684900897919,
      "grad_norm": 2.0425062104358624,
      "kl": 0.0177001953125,
      "learning_rate": 9.999973595745808e-07,
      "loss": 0.0007,
      "reward": 2.0570626258850098,
      "reward_std": 0.10216653347015381,
      "rewards/accuracy_reward": 0.8633125424385071,
      "rewards/format_reward": 1.0,
      "step": 75
    },
    {
      "all_correct": 0.0,
      "all_wrong": 0.0,
      "completion_length": 405.21875,
      "epoch": 0.0010482614032909891,
      "grad_norm": 2.48173438610056,
      "kl": 0.0191650390625,
      "learning_rate": 9.999972886938914e-07,
      "loss": 0.0008,
      "reward": 2.0001564025878906,
      "reward_std": 0.11471109092235565,
      "rewards/accuracy_reward": 0.8064062595367432,
      "rewards/format_reward": 1.0,
      "step": 76
    },
    {
      "all_correct": 0.0,
      "all_wrong": 0.0,
      "completion_length": 409.0625,
      "epoch": 0.0010620543164921864,
      "grad_norm": 2.2211721391522454,
      "kl": 0.018798828125,
      "learning_rate": 9.999972168743885e-07,
      "loss": 0.0008,
      "reward": 1.893031358718872,
      "reward_std": 0.07950831949710846,
      "rewards/accuracy_reward": 0.6992812156677246,
      "rewards/format_reward": 1.0,
      "step": 77
    },
    {
      "all_correct": 0.25,
      "all_wrong": 0.0,
      "completion_length": 413.59375,
      "epoch": 0.0010758472296933835,
      "grad_norm": 6.5477114597357335,
      "kl": 0.0205078125,
      "learning_rate": 9.999971441160716e-07,
      "loss": 0.0008,
      "reward": 1.9737812280654907,
      "reward_std": 0.07410921156406403,
      "rewards/accuracy_reward": 0.7800312638282776,
      "rewards/format_reward": 1.0,
      "step": 78
    },
    {
      "all_correct": 0.25,
      "all_wrong": 0.0,
      "completion_length": 405.46875,
      "epoch": 0.0010896401428945807,
      "grad_norm": 2.0330019258334375,
      "kl": 0.0194091796875,
      "learning_rate": 9.999970704189418e-07,
      "loss": 0.0008,
      "reward": 2.061781167984009,
      "reward_std": 0.10087407380342484,
      "rewards/accuracy_reward": 0.8805313110351562,
      "rewards/format_reward": 1.0,
      "step": 79
    },
    {
      "all_correct": 0.25,
      "all_wrong": 0.0,
      "completion_length": 391.3125,
      "epoch": 0.001103433056095778,
      "grad_norm": 2.607390388875823,
      "kl": 0.0216064453125,
      "learning_rate": 9.999969957829985e-07,
      "loss": 0.0009,
      "reward": 1.98046875,
      "reward_std": 0.09627526253461838,
      "rewards/accuracy_reward": 0.7992187738418579,
      "rewards/format_reward": 1.0,
      "step": 80
    },
    {
      "all_correct": 0.25,
      "all_wrong": 0.0,
      "completion_length": 373.4375,
      "epoch": 0.0011172259692969753,
      "grad_norm": 1.876950641564629,
      "kl": 0.02001953125,
      "learning_rate": 9.999969202082422e-07,
      "loss": 0.0008,
      "reward": 1.9832813739776611,
      "reward_std": 0.1238895058631897,
      "rewards/accuracy_reward": 0.8020312190055847,
      "rewards/format_reward": 1.0,
      "step": 81
    },
    {
      "all_correct": 0.0,
      "all_wrong": 0.0,
      "completion_length": 408.09375,
      "epoch": 0.0011310188824981725,
      "grad_norm": 2.0206454330604857,
      "kl": 0.020751953125,
      "learning_rate": 9.99996843694673e-07,
      "loss": 0.0008,
      "reward": 1.8744688034057617,
      "reward_std": 0.12994661927223206,
      "rewards/accuracy_reward": 0.6807186603546143,
      "rewards/format_reward": 1.0,
      "step": 82
    },
    {
      "all_correct": 0.0,
      "all_wrong": 0.0,
      "completion_length": 418.0625,
      "epoch": 0.0011448117956993696,
      "grad_norm": 3.293451538465561,
      "kl": 0.0186767578125,
      "learning_rate": 9.999967662422907e-07,
      "loss": 0.0007,
      "reward": 1.883750081062317,
      "reward_std": 0.1281936764717102,
      "rewards/accuracy_reward": 0.7024999856948853,
      "rewards/format_reward": 1.0,
      "step": 83
    },
    {
      "all_correct": 0.0,
      "all_wrong": 0.0,
      "completion_length": 434.375,
      "epoch": 0.0011586047089005669,
      "grad_norm": 2.8365982056535293,
      "kl": 0.020263671875,
      "learning_rate": 9.999966878510959e-07,
      "loss": 0.0008,
      "reward": 1.9679062366485596,
      "reward_std": 0.10362934321165085,
      "rewards/accuracy_reward": 0.7804062366485596,
      "rewards/format_reward": 1.0,
      "step": 84
    },
    {
      "all_correct": 0.0,
      "all_wrong": 0.0,
      "completion_length": 438.25,
      "epoch": 0.0011723976221017641,
      "grad_norm": 1.903995909966491,
      "kl": 0.02099609375,
      "learning_rate": 9.999966085210885e-07,
      "loss": 0.0008,
      "reward": 1.9658124446868896,
      "reward_std": 0.10568737983703613,
      "rewards/accuracy_reward": 0.7908124923706055,
      "rewards/format_reward": 1.0,
      "step": 85
    },
    {
      "all_correct": 0.25,
      "all_wrong": 0.0,
      "completion_length": 421.5625,
      "epoch": 0.0011861905353029614,
      "grad_norm": 1.914680102222218,
      "kl": 0.019287109375,
      "learning_rate": 9.999965282522687e-07,
      "loss": 0.0008,
      "reward": 1.9978125095367432,
      "reward_std": 0.10486941784620285,
      "rewards/accuracy_reward": 0.8103125095367432,
      "rewards/format_reward": 1.0,
      "step": 86
    },
    {
      "all_correct": 0.0,
      "all_wrong": 0.0,
      "completion_length": 437.90625,
      "epoch": 0.0011999834485041585,
      "grad_norm": 2.2162677073510375,
      "kl": 0.0224609375,
      "learning_rate": 9.999964470446366e-07,
      "loss": 0.0009,
      "reward": 2.030156135559082,
      "reward_std": 0.1169753447175026,
      "rewards/accuracy_reward": 0.8426562547683716,
      "rewards/format_reward": 1.0,
      "step": 87
    },
    {
      "all_correct": 0.25,
      "all_wrong": 0.0,
      "completion_length": 438.78125,
      "epoch": 0.0012137763617053557,
      "grad_norm": 1.7977164346728522,
      "kl": 0.0211181640625,
      "learning_rate": 9.999963648981926e-07,
      "loss": 0.0008,
      "reward": 2.1032187938690186,
      "reward_std": 0.08337854593992233,
      "rewards/accuracy_reward": 0.9157187342643738,
      "rewards/format_reward": 1.0,
      "step": 88
    },
    {
      "all_correct": 0.0,
      "all_wrong": 0.0,
      "completion_length": 432.84375,
      "epoch": 0.001227569274906553,
      "grad_norm": 1.9561962964755193,
      "kl": 0.022216796875,
      "learning_rate": 9.999962818129368e-07,
      "loss": 0.0009,
      "reward": 1.8780937194824219,
      "reward_std": 0.10173892974853516,
      "rewards/accuracy_reward": 0.7030937075614929,
      "rewards/format_reward": 1.0,
      "step": 89
    },
    {
      "all_correct": 0.25,
      "all_wrong": 0.0,
      "completion_length": 423.4375,
      "epoch": 0.0012413621881077503,
      "grad_norm": 2.1335825875575956,
      "kl": 0.020263671875,
      "learning_rate": 9.99996197788869e-07,
      "loss": 0.0008,
      "reward": 2.015125036239624,
      "reward_std": 0.11473339051008224,
      "rewards/accuracy_reward": 0.8338750004768372,
      "rewards/format_reward": 1.0,
      "step": 90
    },
    {
      "all_correct": 0.0,
      "all_wrong": 0.0,
      "completion_length": 416.125,
      "epoch": 0.0012551551013089475,
      "grad_norm": 2.0916217890362807,
      "kl": 0.02099609375,
      "learning_rate": 9.999961128259895e-07,
      "loss": 0.0008,
      "reward": 2.062406063079834,
      "reward_std": 0.10356153547763824,
      "rewards/accuracy_reward": 0.8811562061309814,
      "rewards/format_reward": 1.0,
      "step": 91
    },
    {
      "all_correct": 0.25,
      "all_wrong": 0.0,
      "completion_length": 407.84375,
      "epoch": 0.0012689480145101446,
      "grad_norm": 1.87796792518994,
      "kl": 0.0198974609375,
      "learning_rate": 9.999960269242986e-07,
      "loss": 0.0008,
      "reward": 2.0895938873291016,
      "reward_std": 0.08552618324756622,
      "rewards/accuracy_reward": 0.889593780040741,
      "rewards/format_reward": 1.0,
      "step": 92
    },
    {
      "all_correct": 0.0,
      "all_wrong": 0.0,
      "completion_length": 430.125,
      "epoch": 0.0012827409277113419,
      "grad_norm": 2.092998703269986,
      "kl": 0.0216064453125,
      "learning_rate": 9.999959400837966e-07,
      "loss": 0.0009,
      "reward": 2.058500051498413,
      "reward_std": 0.0773710161447525,
      "rewards/accuracy_reward": 0.8772499561309814,
      "rewards/format_reward": 1.0,
      "step": 93
    },
    {
      "all_correct": 0.0,
      "all_wrong": 0.0,
      "completion_length": 398.9375,
      "epoch": 0.0012965338409125391,
      "grad_norm": 2.1335825161203554,
      "kl": 0.02001953125,
      "learning_rate": 9.999958523044833e-07,
      "loss": 0.0008,
      "reward": 2.0511250495910645,
      "reward_std": 0.08750750869512558,
      "rewards/accuracy_reward": 0.8636249303817749,
      "rewards/format_reward": 1.0,
      "step": 94
    },
    {
      "all_correct": 0.0,
      "all_wrong": 0.0,
      "completion_length": 397.25,
      "epoch": 0.0013103267541137364,
      "grad_norm": 3.2133359318335737,
      "kl": 0.0250244140625,
      "learning_rate": 9.999957635863591e-07,
      "loss": 0.001,
      "reward": 1.8879687786102295,
      "reward_std": 0.10368669033050537,
      "rewards/accuracy_reward": 0.7067187428474426,
      "rewards/format_reward": 1.0,
      "step": 95
    },
    {
      "all_correct": 0.0,
      "all_wrong": 0.0,
      "completion_length": 406.0625,
      "epoch": 0.0013241196673149337,
      "grad_norm": 1.9467134814363738,
      "kl": 0.0194091796875,
      "learning_rate": 9.99995673929424e-07,
      "loss": 0.0008,
      "reward": 1.98046875,
      "reward_std": 0.12112919986248016,
      "rewards/accuracy_reward": 0.7992187142372131,
      "rewards/format_reward": 1.0,
      "step": 96
    },
    {
      "all_correct": 0.25,
      "all_wrong": 0.0,
      "completion_length": 411.125,
      "epoch": 0.0013379125805161307,
      "grad_norm": 1.97315248003581,
      "kl": 0.0198974609375,
      "learning_rate": 9.999955833336784e-07,
      "loss": 0.0008,
      "reward": 2.066281318664551,
      "reward_std": 0.09585392475128174,
      "rewards/accuracy_reward": 0.8850312829017639,
      "rewards/format_reward": 1.0,
      "step": 97
    },
    {
      "all_correct": 0.25,
      "all_wrong": 0.0,
      "completion_length": 417.21875,
      "epoch": 0.001351705493717328,
      "grad_norm": 1.90936454331302,
      "kl": 0.019287109375,
      "learning_rate": 9.999954917991222e-07,
      "loss": 0.0008,
      "reward": 2.0439374446868896,
      "reward_std": 0.08787743002176285,
      "rewards/accuracy_reward": 0.8626875281333923,
      "rewards/format_reward": 1.0,
      "step": 98
    },
    {
      "all_correct": 0.25,
      "all_wrong": 0.0,
      "completion_length": 411.875,
      "epoch": 0.0013654984069185253,
      "grad_norm": 2.3092667844613226,
      "kl": 0.023193359375,
      "learning_rate": 9.999953993257558e-07,
      "loss": 0.0009,
      "reward": 2.052999973297119,
      "reward_std": 0.09241437166929245,
      "rewards/accuracy_reward": 0.8530000448226929,
      "rewards/format_reward": 1.0,
      "step": 99
    },
    {
      "all_correct": 0.25,
      "all_wrong": 0.0,
      "completion_length": 387.0625,
      "epoch": 0.0013792913201197226,
      "grad_norm": 2.245471536346899,
      "kl": 0.022705078125,
      "learning_rate": 9.999953059135794e-07,
      "loss": 0.0009,
      "reward": 2.028250217437744,
      "reward_std": 0.10045875608921051,
      "rewards/accuracy_reward": 0.8470000624656677,
      "rewards/format_reward": 1.0,
      "step": 100
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.0,
      "completion_length": 409.1875,
      "epoch": 0.0013930842333209196,
      "grad_norm": 3.7452978064396247,
      "kl": 0.018310546875,
      "learning_rate": 9.99995211562593e-07,
      "loss": 0.0007,
      "reward": 2.0342187881469727,
      "reward_std": 0.07907479256391525,
      "rewards/accuracy_reward": 0.8404687643051147,
      "rewards/format_reward": 1.0,
      "step": 101
    },
    {
      "all_correct": 0.25,
      "all_wrong": 0.0,
      "completion_length": 423.25,
      "epoch": 0.0014068771465221169,
      "grad_norm": 3.3520192881557844,
      "kl": 0.0189208984375,
      "learning_rate": 9.999951162727967e-07,
      "loss": 0.0008,
      "reward": 1.8736562728881836,
      "reward_std": 0.10261452943086624,
      "rewards/accuracy_reward": 0.6861562728881836,
      "rewards/format_reward": 1.0,
      "step": 102
    },
    {
      "all_correct": 0.0,
      "all_wrong": 0.0,
      "completion_length": 432.0625,
      "epoch": 0.0014206700597233141,
      "grad_norm": 2.6809604380851657,
      "kl": 0.019287109375,
      "learning_rate": 9.999950200441909e-07,
      "loss": 0.0008,
      "reward": 1.965343713760376,
      "reward_std": 0.09344343841075897,
      "rewards/accuracy_reward": 0.7715936899185181,
      "rewards/format_reward": 1.0,
      "step": 103
    },
    {
      "all_correct": 0.25,
      "all_wrong": 0.0,
      "completion_length": 419.59375,
      "epoch": 0.0014344629729245114,
      "grad_norm": 2.0950174630499228,
      "kl": 0.0205078125,
      "learning_rate": 9.999949228767756e-07,
      "loss": 0.0008,
      "reward": 2.0600624084472656,
      "reward_std": 0.07353753596544266,
      "rewards/accuracy_reward": 0.8850624561309814,
      "rewards/format_reward": 1.0,
      "step": 104
    },
    {
      "all_correct": 0.75,
      "all_wrong": 0.0,
      "completion_length": 417.15625,
      "epoch": 0.0014482558861257087,
      "grad_norm": 1.9462977496641147,
      "kl": 0.0198974609375,
      "learning_rate": 9.999948247705514e-07,
      "loss": 0.0008,
      "reward": 2.112968683242798,
      "reward_std": 0.06496657431125641,
      "rewards/accuracy_reward": 0.9192187786102295,
      "rewards/format_reward": 1.0,
      "step": 105
    },
    {
      "all_correct": 0.0,
      "all_wrong": 0.0,
      "completion_length": 421.34375,
      "epoch": 0.0014620487993269057,
      "grad_norm": 2.2271402027862055,
      "kl": 0.0191650390625,
      "learning_rate": 9.99994725725518e-07,
      "loss": 0.0008,
      "reward": 2.018531322479248,
      "reward_std": 0.10074889659881592,
      "rewards/accuracy_reward": 0.8310312032699585,
      "rewards/format_reward": 1.0,
      "step": 106
    },
    {
      "all_correct": 0.0,
      "all_wrong": 0.0,
      "completion_length": 445.71875,
      "epoch": 0.001475841712528103,
      "grad_norm": 1.845138686309047,
      "kl": 0.017333984375,
      "learning_rate": 9.999946257416756e-07,
      "loss": 0.0007,
      "reward": 1.9974374771118164,
      "reward_std": 0.09323931485414505,
      "rewards/accuracy_reward": 0.8099374771118164,
      "rewards/format_reward": 1.0,
      "step": 107
    },
    {
      "all_correct": 0.25,
      "all_wrong": 0.0,
      "completion_length": 399.96875,
      "epoch": 0.0014896346257293003,
      "grad_norm": 2.2346418957871577,
      "kl": 0.019287109375,
      "learning_rate": 9.999945248190245e-07,
      "loss": 0.0008,
      "reward": 2.0425000190734863,
      "reward_std": 0.07148788869380951,
      "rewards/accuracy_reward": 0.8487499952316284,
      "rewards/format_reward": 1.0,
      "step": 108
    },
    {
      "all_correct": 0.0,
      "all_wrong": 0.0,
      "completion_length": 434.1875,
      "epoch": 0.0015034275389304976,
      "grad_norm": 2.7485539956635097,
      "kl": 0.01904296875,
      "learning_rate": 9.99994422957565e-07,
      "loss": 0.0008,
      "reward": 1.946812629699707,
      "reward_std": 0.11658565700054169,
      "rewards/accuracy_reward": 0.7780625224113464,
      "rewards/format_reward": 1.0,
      "step": 109
    },
    {
      "all_correct": 0.0,
      "all_wrong": 0.0,
      "completion_length": 430.4375,
      "epoch": 0.0015172204521316948,
      "grad_norm": 1.6256790468322975,
      "kl": 0.0203857421875,
      "learning_rate": 9.999943201572973e-07,
      "loss": 0.0008,
      "reward": 1.9387812614440918,
      "reward_std": 0.07584629952907562,
      "rewards/accuracy_reward": 0.751281201839447,
      "rewards/format_reward": 1.0,
      "step": 110
    },
    {
      "all_correct": 0.0,
      "all_wrong": 0.0,
      "completion_length": 426.9375,
      "epoch": 0.0015310133653328919,
      "grad_norm": 2.267961508359044,
      "kl": 0.021484375,
      "learning_rate": 9.999942164182216e-07,
      "loss": 0.0009,
      "reward": 1.9941250085830688,
      "reward_std": 0.09937582910060883,
      "rewards/accuracy_reward": 0.8128750324249268,
      "rewards/format_reward": 1.0,
      "step": 111
    },
    {
      "all_correct": 0.0,
      "all_wrong": 0.0,
      "completion_length": 412.9375,
      "epoch": 0.0015448062785340892,
      "grad_norm": 2.0581790967612847,
      "kl": 0.0196533203125,
      "learning_rate": 9.999941117403378e-07,
      "loss": 0.0008,
      "reward": 2.0332813262939453,
      "reward_std": 0.17447586357593536,
      "rewards/accuracy_reward": 0.8520312309265137,
      "rewards/format_reward": 1.0,
      "step": 112
    },
    {
      "all_correct": 0.0,
      "all_wrong": 0.0,
      "completion_length": 445.21875,
      "epoch": 0.0015585991917352864,
      "grad_norm": 5.766110130139589,
      "kl": 0.018310546875,
      "learning_rate": 9.999940061236465e-07,
      "loss": 0.0007,
      "reward": 2.015812397003174,
      "reward_std": 0.10099396109580994,
      "rewards/accuracy_reward": 0.8408124446868896,
      "rewards/format_reward": 1.0,
      "step": 113
    },
    {
      "all_correct": 0.25,
      "all_wrong": 0.0,
      "completion_length": 399.78125,
      "epoch": 0.0015723921049364837,
      "grad_norm": 2.028823496278505,
      "kl": 0.0198974609375,
      "learning_rate": 9.999938995681475e-07,
      "loss": 0.0008,
      "reward": 2.068406343460083,
      "reward_std": 0.07293745130300522,
      "rewards/accuracy_reward": 0.8809062242507935,
      "rewards/format_reward": 1.0,
      "step": 114
    },
    {
      "all_correct": 0.25,
      "all_wrong": 0.0,
      "completion_length": 408.25,
      "epoch": 0.001586185018137681,
      "grad_norm": 2.262979988843303,
      "kl": 0.023193359375,
      "learning_rate": 9.999937920738415e-07,
      "loss": 0.0009,
      "reward": 2.0093436241149902,
      "reward_std": 0.08357476443052292,
      "rewards/accuracy_reward": 0.8280937671661377,
      "rewards/format_reward": 1.0,
      "step": 115
    },
    {
      "all_correct": 0.0,
      "all_wrong": 0.0,
      "completion_length": 385.1875,
      "epoch": 0.001599977931338878,
      "grad_norm": 2.2396106340034927,
      "kl": 0.021484375,
      "learning_rate": 9.999936836407281e-07,
      "loss": 0.0009,
      "reward": 1.9998438358306885,
      "reward_std": 0.06379185616970062,
      "rewards/accuracy_reward": 0.8060937523841858,
      "rewards/format_reward": 1.0,
      "step": 116
    },
    {
      "all_correct": 0.25,
      "all_wrong": 0.0,
      "completion_length": 418.3125,
      "epoch": 0.0016137708445400753,
      "grad_norm": 2.0190076027293506,
      "kl": 0.02197265625,
      "learning_rate": 9.99993574268808e-07,
      "loss": 0.0009,
      "reward": 2.029125213623047,
      "reward_std": 0.11474525928497314,
      "rewards/accuracy_reward": 0.8478749990463257,
      "rewards/format_reward": 1.0,
      "step": 117
    },
    {
      "all_correct": 0.0,
      "all_wrong": 0.0,
      "completion_length": 404.875,
      "epoch": 0.0016275637577412726,
      "grad_norm": 2.984145460599882,
      "kl": 0.02294921875,
      "learning_rate": 9.99993463958081e-07,
      "loss": 0.0009,
      "reward": 1.9973125457763672,
      "reward_std": 0.11626149713993073,
      "rewards/accuracy_reward": 0.8098124861717224,
      "rewards/format_reward": 1.0,
      "step": 118
    },
    {
      "all_correct": 0.25,
      "all_wrong": 0.0,
      "completion_length": 411.125,
      "epoch": 0.0016413566709424698,
      "grad_norm": 2.227864110534936,
      "kl": 0.025634765625,
      "learning_rate": 9.999933527085475e-07,
      "loss": 0.001,
      "reward": 1.988968849182129,
      "reward_std": 0.0794340968132019,
      "rewards/accuracy_reward": 0.8139687776565552,
      "rewards/format_reward": 1.0,
      "step": 119
    },
    {
      "all_correct": 0.0,
      "all_wrong": 0.0,
      "completion_length": 428.9375,
      "epoch": 0.0016551495841436669,
      "grad_norm": 2.1287258166421252,
      "kl": 0.01904296875,
      "learning_rate": 9.99993240520208e-07,
      "loss": 0.0008,
      "reward": 2.0016250610351562,
      "reward_std": 0.10000091791152954,
      "rewards/accuracy_reward": 0.8266250491142273,
      "rewards/format_reward": 1.0,
      "step": 120
    },
    {
      "all_correct": 0.25,
      "all_wrong": 0.0,
      "completion_length": 428.8125,
      "epoch": 0.0016689424973448642,
      "grad_norm": 2.2238376452996795,
      "kl": 0.0233154296875,
      "learning_rate": 9.999931273930624e-07,
      "loss": 0.0009,
      "reward": 2.0781874656677246,
      "reward_std": 0.066957026720047,
      "rewards/accuracy_reward": 0.8969375491142273,
      "rewards/format_reward": 1.0,
      "step": 121
    },
    {
      "all_correct": 0.0,
      "all_wrong": 0.0,
      "completion_length": 415.75,
      "epoch": 0.0016827354105460614,
      "grad_norm": 5.494504448483442,
      "kl": 0.0244140625,
      "learning_rate": 9.99993013327111e-07,
      "loss": 0.001,
      "reward": 2.0068438053131104,
      "reward_std": 0.13612675666809082,
      "rewards/accuracy_reward": 0.8318437933921814,
      "rewards/format_reward": 1.0,
      "step": 122
    },
    {
      "all_correct": 0.25,
      "all_wrong": 0.0,
      "completion_length": 420.125,
      "epoch": 0.0016965283237472587,
      "grad_norm": 1.9577923727826128,
      "kl": 0.0233154296875,
      "learning_rate": 9.999928983223537e-07,
      "loss": 0.0009,
      "reward": 2.02371883392334,
      "reward_std": 0.08236443251371384,
      "rewards/accuracy_reward": 0.8299687504768372,
      "rewards/format_reward": 1.0,
      "step": 123
    },
    {
      "all_correct": 0.25,
      "all_wrong": 0.0,
      "completion_length": 419.3125,
      "epoch": 0.001710321236948456,
      "grad_norm": 1.9724912522052493,
      "kl": 0.0242919921875,
      "learning_rate": 9.99992782378791e-07,
      "loss": 0.001,
      "reward": 1.937093734741211,
      "reward_std": 0.07229560613632202,
      "rewards/accuracy_reward": 0.7558437585830688,
      "rewards/format_reward": 1.0,
      "step": 124
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.0,
      "completion_length": 403.53125,
      "epoch": 0.001724114150149653,
      "grad_norm": 2.0354778997109513,
      "kl": 0.020263671875,
      "learning_rate": 9.999926654964233e-07,
      "loss": 0.0008,
      "reward": 2.110375165939331,
      "reward_std": 0.0669713169336319,
      "rewards/accuracy_reward": 0.9228750467300415,
      "rewards/format_reward": 1.0,
      "step": 125
    },
    {
      "all_correct": 0.25,
      "all_wrong": 0.0,
      "completion_length": 416.0,
      "epoch": 0.0017379070633508503,
      "grad_norm": 1.902770269444391,
      "kl": 0.02490234375,
      "learning_rate": 9.999925476752503e-07,
      "loss": 0.001,
      "reward": 2.0635311603546143,
      "reward_std": 0.05498639866709709,
      "rewards/accuracy_reward": 0.8760312795639038,
      "rewards/format_reward": 1.0,
      "step": 126
    },
    {
      "all_correct": 0.0,
      "all_wrong": 0.0,
      "completion_length": 396.75,
      "epoch": 0.0017516999765520476,
      "grad_norm": 1.8958305262248902,
      "kl": 0.0263671875,
      "learning_rate": 9.99992428915273e-07,
      "loss": 0.0011,
      "reward": 1.9792187213897705,
      "reward_std": 0.10229627043008804,
      "rewards/accuracy_reward": 0.7917187809944153,
      "rewards/format_reward": 1.0,
      "step": 127
    },
    {
      "all_correct": 0.25,
      "all_wrong": 0.0,
      "completion_length": 401.59375,
      "epoch": 0.0017654928897532448,
      "grad_norm": 2.742346947447369,
      "kl": 0.0245361328125,
      "learning_rate": 9.999923092164907e-07,
      "loss": 0.001,
      "reward": 1.9277499914169312,
      "reward_std": 0.09760669618844986,
      "rewards/accuracy_reward": 0.7340000867843628,
      "rewards/format_reward": 1.0,
      "step": 128
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.0,
      "completion_length": 418.625,
      "epoch": 0.0017792858029544421,
      "grad_norm": 2.1089655193726706,
      "kl": 0.0234375,
      "learning_rate": 9.999921885789044e-07,
      "loss": 0.0009,
      "reward": 2.0311875343322754,
      "reward_std": 0.04695471376180649,
      "rewards/accuracy_reward": 0.8311874866485596,
      "rewards/format_reward": 1.0,
      "step": 129
    },
    {
      "all_correct": 0.25,
      "all_wrong": 0.0,
      "completion_length": 420.53125,
      "epoch": 0.0017930787161556392,
      "grad_norm": 2.1255558819924354,
      "kl": 0.021240234375,
      "learning_rate": 9.999920670025139e-07,
      "loss": 0.0008,
      "reward": 2.0605311393737793,
      "reward_std": 0.10061533004045486,
      "rewards/accuracy_reward": 0.8667812943458557,
      "rewards/format_reward": 1.0,
      "step": 130
    },
    {
      "all_correct": 0.75,
      "all_wrong": 0.0,
      "completion_length": 406.65625,
      "epoch": 0.0018068716293568364,
      "grad_norm": 2.3191532175637786,
      "kl": 0.02587890625,
      "learning_rate": 9.999919444873198e-07,
      "loss": 0.001,
      "reward": 2.0655312538146973,
      "reward_std": 0.05533017963171005,
      "rewards/accuracy_reward": 0.8655312657356262,
      "rewards/format_reward": 1.0,
      "step": 131
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.0,
      "completion_length": 416.6875,
      "epoch": 0.0018206645425580337,
      "grad_norm": 2.2065081261455477,
      "kl": 0.0247802734375,
      "learning_rate": 9.999918210333217e-07,
      "loss": 0.001,
      "reward": 1.9338126182556152,
      "reward_std": 0.06746178865432739,
      "rewards/accuracy_reward": 0.7338124513626099,
      "rewards/format_reward": 1.0,
      "step": 132
    },
    {
      "all_correct": 0.25,
      "all_wrong": 0.0,
      "completion_length": 421.65625,
      "epoch": 0.001834457455759231,
      "grad_norm": 2.006884300591598,
      "kl": 0.025390625,
      "learning_rate": 9.999916966405205e-07,
      "loss": 0.001,
      "reward": 1.9874374866485596,
      "reward_std": 0.08689753711223602,
      "rewards/accuracy_reward": 0.7999374866485596,
      "rewards/format_reward": 1.0,
      "step": 133
    },
    {
      "all_correct": 0.0,
      "all_wrong": 0.0,
      "completion_length": 412.15625,
      "epoch": 0.001848250368960428,
      "grad_norm": 2.352634186327791,
      "kl": 0.02587890625,
      "learning_rate": 9.999915713089159e-07,
      "loss": 0.001,
      "reward": 1.9622812271118164,
      "reward_std": 0.09301012754440308,
      "rewards/accuracy_reward": 0.7685312032699585,
      "rewards/format_reward": 1.0,
      "step": 134
    },
    {
      "all_correct": 0.25,
      "all_wrong": 0.0,
      "completion_length": 407.4375,
      "epoch": 0.0018620432821616253,
      "grad_norm": 2.062812479729722,
      "kl": 0.0230712890625,
      "learning_rate": 9.999914450385084e-07,
      "loss": 0.0009,
      "reward": 1.9440312385559082,
      "reward_std": 0.08110732585191727,
      "rewards/accuracy_reward": 0.7440312504768372,
      "rewards/format_reward": 1.0,
      "step": 135
    },
    {
      "all_correct": 0.0,
      "all_wrong": 0.0,
      "completion_length": 421.25,
      "epoch": 0.0018758361953628226,
      "grad_norm": 2.490263680455753,
      "kl": 0.023681640625,
      "learning_rate": 9.999913178292983e-07,
      "loss": 0.0009,
      "reward": 1.92787504196167,
      "reward_std": 0.11337137222290039,
      "rewards/accuracy_reward": 0.7466249465942383,
      "rewards/format_reward": 1.0,
      "step": 136
    },
    {
      "all_correct": 0.0,
      "all_wrong": 0.0,
      "completion_length": 421.875,
      "epoch": 0.0018896291085640198,
      "grad_norm": 2.067767356062963,
      "kl": 0.0264892578125,
      "learning_rate": 9.999911896812856e-07,
      "loss": 0.0011,
      "reward": 2.0640313625335693,
      "reward_std": 0.0756748840212822,
      "rewards/accuracy_reward": 0.8765312433242798,
      "rewards/format_reward": 1.0,
      "step": 137
    },
    {
      "all_correct": 0.25,
      "all_wrong": 0.0,
      "completion_length": 417.34375,
      "epoch": 0.0019034220217652171,
      "grad_norm": 3.6049516017328935,
      "kl": 0.0245361328125,
      "learning_rate": 9.99991060594471e-07,
      "loss": 0.001,
      "reward": 1.9338126182556152,
      "reward_std": 0.09241359680891037,
      "rewards/accuracy_reward": 0.7400625348091125,
      "rewards/format_reward": 1.0,
      "step": 138
    },
    {
      "all_correct": 0.75,
      "all_wrong": 0.0,
      "completion_length": 418.59375,
      "epoch": 0.0019172149349664142,
      "grad_norm": 3.1162742378502424,
      "kl": 0.027099609375,
      "learning_rate": 9.99990930568854e-07,
      "loss": 0.0011,
      "reward": 2.0812811851501465,
      "reward_std": 0.0551903173327446,
      "rewards/accuracy_reward": 0.8875312805175781,
      "rewards/format_reward": 1.0,
      "step": 139
    },
    {
      "all_correct": 0.0,
      "all_wrong": 0.0,
      "completion_length": 417.96875,
      "epoch": 0.0019310078481676114,
      "grad_norm": 2.0380321462001407,
      "kl": 0.026611328125,
      "learning_rate": 9.999907996044357e-07,
      "loss": 0.0011,
      "reward": 1.9214375019073486,
      "reward_std": 0.0846758633852005,
      "rewards/accuracy_reward": 0.7214374542236328,
      "rewards/format_reward": 1.0,
      "step": 140
    },
    {
      "all_correct": 0.25,
      "all_wrong": 0.0,
      "completion_length": 428.5,
      "epoch": 0.0019448007613688087,
      "grad_norm": 2.1448785744585814,
      "kl": 0.024658203125,
      "learning_rate": 9.999906677012157e-07,
      "loss": 0.001,
      "reward": 2.0080313682556152,
      "reward_std": 0.08222126960754395,
      "rewards/accuracy_reward": 0.8142812252044678,
      "rewards/format_reward": 1.0,
      "step": 141
    },
    {
      "all_correct": 0.25,
      "all_wrong": 0.0,
      "completion_length": 414.3125,
      "epoch": 0.001958593674570006,
      "grad_norm": 1.9206734428203467,
      "kl": 0.0277099609375,
      "learning_rate": 9.999905348591946e-07,
      "loss": 0.0011,
      "reward": 2.040156126022339,
      "reward_std": 0.09859336912631989,
      "rewards/accuracy_reward": 0.8464062809944153,
      "rewards/format_reward": 1.0,
      "step": 142
    },
    {
      "all_correct": 0.0,
      "all_wrong": 0.0,
      "completion_length": 408.375,
      "epoch": 0.0019723865877712033,
      "grad_norm": 2.4906914721485616,
      "kl": 0.028076171875,
      "learning_rate": 9.999904010783723e-07,
      "loss": 0.0011,
      "reward": 1.946218729019165,
      "reward_std": 0.1150365024805069,
      "rewards/accuracy_reward": 0.764968752861023,
      "rewards/format_reward": 1.0,
      "step": 143
    },
    {
      "all_correct": 0.25,
      "all_wrong": 0.0,
      "completion_length": 421.5625,
      "epoch": 0.0019861795009724005,
      "grad_norm": 2.170189757636946,
      "kl": 0.025634765625,
      "learning_rate": 9.999902663587494e-07,
      "loss": 0.001,
      "reward": 1.9680312871932983,
      "reward_std": 0.09352342784404755,
      "rewards/accuracy_reward": 0.7805312275886536,
      "rewards/format_reward": 1.0,
      "step": 144
    },
    {
      "all_correct": 0.25,
      "all_wrong": 0.0,
      "completion_length": 408.3125,
      "epoch": 0.001999972414173598,
      "grad_norm": 2.908442735405397,
      "kl": 0.031494140625,
      "learning_rate": 9.99990130700326e-07,
      "loss": 0.0013,
      "reward": 2.0344998836517334,
      "reward_std": 0.05818683281540871,
      "rewards/accuracy_reward": 0.8407500386238098,
      "rewards/format_reward": 1.0,
      "step": 145
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.0,
      "completion_length": 397.71875,
      "epoch": 0.0020137653273747946,
      "grad_norm": 2.0502885124902677,
      "kl": 0.03076171875,
      "learning_rate": 9.999899941031024e-07,
      "loss": 0.0012,
      "reward": 1.9617501497268677,
      "reward_std": 0.06440916657447815,
      "rewards/accuracy_reward": 0.7617500424385071,
      "rewards/format_reward": 1.0,
      "step": 146
    },
    {
      "all_correct": 0.25,
      "all_wrong": 0.0,
      "completion_length": 400.125,
      "epoch": 0.002027558240575992,
      "grad_norm": 2.2132029324250677,
      "kl": 0.031005859375,
      "learning_rate": 9.999898565670788e-07,
      "loss": 0.0012,
      "reward": 1.7540313005447388,
      "reward_std": 0.08751586079597473,
      "rewards/accuracy_reward": 0.5602812767028809,
      "rewards/format_reward": 1.0,
      "step": 147
    },
    {
      "all_correct": 0.25,
      "all_wrong": 0.0,
      "completion_length": 409.96875,
      "epoch": 0.002041351153777189,
      "grad_norm": 3.884026341687608,
      "kl": 0.03125,
      "learning_rate": 9.999897180922556e-07,
      "loss": 0.0012,
      "reward": 2.0512187480926514,
      "reward_std": 0.09547102451324463,
      "rewards/accuracy_reward": 0.8512187004089355,
      "rewards/format_reward": 1.0,
      "step": 148
    },
    {
      "all_correct": 0.0,
      "all_wrong": 0.0,
      "completion_length": 407.4375,
      "epoch": 0.0020551440669783864,
      "grad_norm": 2.7578436540602835,
      "kl": 0.02783203125,
      "learning_rate": 9.99989578678633e-07,
      "loss": 0.0011,
      "reward": 1.974812626838684,
      "reward_std": 0.08471481502056122,
      "rewards/accuracy_reward": 0.7935625314712524,
      "rewards/format_reward": 1.0,
      "step": 149
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.0,
      "completion_length": 421.125,
      "epoch": 0.0020689369801795837,
      "grad_norm": 2.332294025572221,
      "kl": 0.031005859375,
      "learning_rate": 9.99989438326211e-07,
      "loss": 0.0012,
      "reward": 2.0224063396453857,
      "reward_std": 0.05896058678627014,
      "rewards/accuracy_reward": 0.8286561965942383,
      "rewards/format_reward": 1.0,
      "step": 150
    },
    {
      "all_correct": 0.0,
      "all_wrong": 0.0,
      "completion_length": 386.0,
      "epoch": 0.002082729893380781,
      "grad_norm": 41.82757073680713,
      "kl": 0.02685546875,
      "learning_rate": 9.9998929703499e-07,
      "loss": 0.0011,
      "reward": 1.8978750705718994,
      "reward_std": 0.07568147033452988,
      "rewards/accuracy_reward": 0.7041249871253967,
      "rewards/format_reward": 1.0,
      "step": 151
    },
    {
      "all_correct": 0.0,
      "all_wrong": 0.0,
      "completion_length": 422.0625,
      "epoch": 0.0020965228065819783,
      "grad_norm": 1.8603595195863625,
      "kl": 0.02685546875,
      "learning_rate": 9.999891548049706e-07,
      "loss": 0.0011,
      "reward": 1.8349063396453857,
      "reward_std": 0.047719232738018036,
      "rewards/accuracy_reward": 0.6349062919616699,
      "rewards/format_reward": 1.0,
      "step": 152
    },
    {
      "all_correct": 0.25,
      "all_wrong": 0.0,
      "completion_length": 419.25,
      "epoch": 0.0021103157197831755,
      "grad_norm": 2.053950040665595,
      "kl": 0.03125,
      "learning_rate": 9.999890116361529e-07,
      "loss": 0.0012,
      "reward": 1.8634687662124634,
      "reward_std": 0.09209747612476349,
      "rewards/accuracy_reward": 0.6697187423706055,
      "rewards/format_reward": 1.0,
      "step": 153
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.0,
      "completion_length": 408.71875,
      "epoch": 0.002124108632984373,
      "grad_norm": 2.557083491821594,
      "kl": 0.0341796875,
      "learning_rate": 9.999888675285368e-07,
      "loss": 0.0014,
      "reward": 2.0903749465942383,
      "reward_std": 0.06731757521629333,
      "rewards/accuracy_reward": 0.8903749585151672,
      "rewards/format_reward": 1.0,
      "step": 154
    },
    {
      "all_correct": 0.0,
      "all_wrong": 0.0,
      "completion_length": 394.65625,
      "epoch": 0.0021379015461855696,
      "grad_norm": 1.6808665412799852,
      "kl": 0.0238037109375,
      "learning_rate": 9.99988722482123e-07,
      "loss": 0.001,
      "reward": 1.9673436880111694,
      "reward_std": 0.05538776516914368,
      "rewards/accuracy_reward": 0.7860937118530273,
      "rewards/format_reward": 1.0,
      "step": 155
    },
    {
      "all_correct": 0.0,
      "all_wrong": 0.0,
      "completion_length": 396.9375,
      "epoch": 0.002151694459386767,
      "grad_norm": 9.801379640847554,
      "kl": 0.029052734375,
      "learning_rate": 9.999885764969117e-07,
      "loss": 0.0012,
      "reward": 1.9736251831054688,
      "reward_std": 0.08686383068561554,
      "rewards/accuracy_reward": 0.7798749804496765,
      "rewards/format_reward": 1.0,
      "step": 156
    },
    {
      "all_correct": 0.25,
      "all_wrong": 0.0,
      "completion_length": 389.625,
      "epoch": 0.002165487372587964,
      "grad_norm": 1.864255705124676,
      "kl": 0.024658203125,
      "learning_rate": 9.999884295729028e-07,
      "loss": 0.001,
      "reward": 2.064687728881836,
      "reward_std": 0.07195336371660233,
      "rewards/accuracy_reward": 0.8709374666213989,
      "rewards/format_reward": 1.0,
      "step": 157
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.0,
      "completion_length": 385.65625,
      "epoch": 0.0021792802857891615,
      "grad_norm": 2.648487411963937,
      "kl": 0.027099609375,
      "learning_rate": 9.99988281710097e-07,
      "loss": 0.0011,
      "reward": 1.9994688034057617,
      "reward_std": 0.0530242919921875,
      "rewards/accuracy_reward": 0.7994687557220459,
      "rewards/format_reward": 1.0,
      "step": 158
    },
    {
      "all_correct": 0.25,
      "all_wrong": 0.0,
      "completion_length": 399.96875,
      "epoch": 0.0021930731989903587,
      "grad_norm": 3.135546230672736,
      "kl": 0.0250244140625,
      "learning_rate": 9.999881329084944e-07,
      "loss": 0.001,
      "reward": 2.0918750762939453,
      "reward_std": 0.06598945707082748,
      "rewards/accuracy_reward": 0.8981249928474426,
      "rewards/format_reward": 1.0,
      "step": 159
    },
    {
      "all_correct": 0.0,
      "all_wrong": 0.0,
      "completion_length": 374.25,
      "epoch": 0.002206866112191556,
      "grad_norm": 2.831192695495464,
      "kl": 0.0274658203125,
      "learning_rate": 9.999879831680955e-07,
      "loss": 0.0011,
      "reward": 2.026031494140625,
      "reward_std": 0.09407088905572891,
      "rewards/accuracy_reward": 0.8510312438011169,
      "rewards/format_reward": 1.0,
      "step": 160
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.0,
      "completion_length": 397.5625,
      "epoch": 0.0022206590253927533,
      "grad_norm": 2.162999953097895,
      "kl": 0.0244140625,
      "learning_rate": 9.999878324889003e-07,
      "loss": 0.001,
      "reward": 2.0853123664855957,
      "reward_std": 0.08686895668506622,
      "rewards/accuracy_reward": 0.8978124856948853,
      "rewards/format_reward": 1.0,
      "step": 161
    },
    {
      "all_correct": 0.25,
      "all_wrong": 0.0,
      "completion_length": 382.28125,
      "epoch": 0.0022344519385939505,
      "grad_norm": 2.597197155988873,
      "kl": 0.0263671875,
      "learning_rate": 9.999876808709093e-07,
      "loss": 0.0011,
      "reward": 2.0526249408721924,
      "reward_std": 0.08961372822523117,
      "rewards/accuracy_reward": 0.8713749647140503,
      "rewards/format_reward": 1.0,
      "step": 162
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.0,
      "completion_length": 385.71875,
      "epoch": 0.002248244851795148,
      "grad_norm": 2.7874941055827342,
      "kl": 0.0255126953125,
      "learning_rate": 9.999875283141226e-07,
      "loss": 0.001,
      "reward": 2.056093692779541,
      "reward_std": 0.07780696451663971,
      "rewards/accuracy_reward": 0.8748437762260437,
      "rewards/format_reward": 1.0,
      "step": 163
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.0,
      "completion_length": 390.1875,
      "epoch": 0.002262037764996345,
      "grad_norm": 2.14309924891198,
      "kl": 0.0277099609375,
      "learning_rate": 9.999873748185406e-07,
      "loss": 0.0011,
      "reward": 2.0775938034057617,
      "reward_std": 0.06876933574676514,
      "rewards/accuracy_reward": 0.8900938034057617,
      "rewards/format_reward": 1.0,
      "step": 164
    },
    {
      "all_correct": 0.25,
      "all_wrong": 0.0,
      "completion_length": 395.03125,
      "epoch": 0.002275830678197542,
      "grad_norm": 2.387474108703245,
      "kl": 0.0286865234375,
      "learning_rate": 9.999872203841635e-07,
      "loss": 0.0011,
      "reward": 1.8728125095367432,
      "reward_std": 0.07647205889225006,
      "rewards/accuracy_reward": 0.6790624856948853,
      "rewards/format_reward": 1.0,
      "step": 165
    },
    {
      "all_correct": 0.25,
      "all_wrong": 0.0,
      "completion_length": 385.8125,
      "epoch": 0.002289623591398739,
      "grad_norm": 6.624381647171409,
      "kl": 0.026123046875,
      "learning_rate": 9.999870650109917e-07,
      "loss": 0.001,
      "reward": 1.9303126335144043,
      "reward_std": 0.0732966959476471,
      "rewards/accuracy_reward": 0.7428125739097595,
      "rewards/format_reward": 1.0,
      "step": 166
    },
    {
      "all_correct": 0.25,
      "all_wrong": 0.0,
      "completion_length": 375.3125,
      "epoch": 0.0023034165045999365,
      "grad_norm": 2.229535096022293,
      "kl": 0.0267333984375,
      "learning_rate": 9.999869086990253e-07,
      "loss": 0.0011,
      "reward": 2.0582189559936523,
      "reward_std": 0.09584961086511612,
      "rewards/accuracy_reward": 0.8769687414169312,
      "rewards/format_reward": 1.0,
      "step": 167
    },
    {
      "all_correct": 0.0,
      "all_wrong": 0.0,
      "completion_length": 395.65625,
      "epoch": 0.0023172094178011337,
      "grad_norm": 2.0984437457196923,
      "kl": 0.02783203125,
      "learning_rate": 9.99986751448265e-07,
      "loss": 0.0011,
      "reward": 2.0131874084472656,
      "reward_std": 0.07278886437416077,
      "rewards/accuracy_reward": 0.8131875395774841,
      "rewards/format_reward": 1.0,
      "step": 168
    },
    {
      "all_correct": 0.25,
      "all_wrong": 0.0,
      "completion_length": 405.5,
      "epoch": 0.002331002331002331,
      "grad_norm": 2.128063773187203,
      "kl": 0.0269775390625,
      "learning_rate": 9.999865932587107e-07,
      "loss": 0.0011,
      "reward": 2.0375938415527344,
      "reward_std": 0.08132210373878479,
      "rewards/accuracy_reward": 0.8500937819480896,
      "rewards/format_reward": 1.0,
      "step": 169
    },
    {
      "all_correct": 0.0,
      "all_wrong": 0.0,
      "completion_length": 417.75,
      "epoch": 0.0023447952442035283,
      "grad_norm": 2.067958849274226,
      "kl": 0.0289306640625,
      "learning_rate": 9.999864341303627e-07,
      "loss": 0.0012,
      "reward": 2.0456666946411133,
      "reward_std": 0.08951409161090851,
      "rewards/accuracy_reward": 0.8519166707992554,
      "rewards/format_reward": 1.0,
      "step": 170
    },
    {
      "all_correct": 0.25,
      "all_wrong": 0.0,
      "completion_length": 383.6875,
      "epoch": 0.0023585881574047255,
      "grad_norm": 2.3054266852830847,
      "kl": 0.0296630859375,
      "learning_rate": 9.999862740632214e-07,
      "loss": 0.0012,
      "reward": 2.0493438243865967,
      "reward_std": 0.06850887835025787,
      "rewards/accuracy_reward": 0.868093729019165,
      "rewards/format_reward": 1.0,
      "step": 171
    },
    {
      "all_correct": 0.25,
      "all_wrong": 0.0,
      "completion_length": 423.125,
      "epoch": 0.002372381070605923,
      "grad_norm": 2.3135349276359407,
      "kl": 0.029296875,
      "learning_rate": 9.999861130572873e-07,
      "loss": 0.0012,
      "reward": 2.0240001678466797,
      "reward_std": 0.07183652371168137,
      "rewards/accuracy_reward": 0.8364999890327454,
      "rewards/format_reward": 1.0,
      "step": 172
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.0,
      "completion_length": 412.03125,
      "epoch": 0.00238617398380712,
      "grad_norm": 2.187890007907099,
      "kl": 0.03125,
      "learning_rate": 9.999859511125604e-07,
      "loss": 0.0012,
      "reward": 2.056281089782715,
      "reward_std": 0.058351606130599976,
      "rewards/accuracy_reward": 0.8562811613082886,
      "rewards/format_reward": 1.0,
      "step": 173
    },
    {
      "all_correct": 0.0,
      "all_wrong": 0.0,
      "completion_length": 426.28125,
      "epoch": 0.002399966897008317,
      "grad_norm": 9.685102075276307,
      "kl": 0.031982421875,
      "learning_rate": 9.999857882290412e-07,
      "loss": 0.0013,
      "reward": 1.9387187957763672,
      "reward_std": 0.10506308078765869,
      "rewards/accuracy_reward": 0.7449687123298645,
      "rewards/format_reward": 1.0,
      "step": 174
    },
    {
      "all_correct": 0.25,
      "all_wrong": 0.0,
      "completion_length": 433.5625,
      "epoch": 0.002413759810209514,
      "grad_norm": 1.9759584974122304,
      "kl": 0.029296875,
      "learning_rate": 9.999856244067297e-07,
      "loss": 0.0012,
      "reward": 1.9013750553131104,
      "reward_std": 0.07270276546478271,
      "rewards/accuracy_reward": 0.7201250195503235,
      "rewards/format_reward": 1.0,
      "step": 175
    },
    {
      "all_correct": 0.0,
      "all_wrong": 0.0,
      "completion_length": 404.53125,
      "epoch": 0.0024275527234107115,
      "grad_norm": 2.1868257980136767,
      "kl": 0.029541015625,
      "learning_rate": 9.999854596456268e-07,
      "loss": 0.0012,
      "reward": 2.0413126945495605,
      "reward_std": 0.09028618782758713,
      "rewards/accuracy_reward": 0.8600624799728394,
      "rewards/format_reward": 1.0,
      "step": 176
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.0,
      "completion_length": 425.90625,
      "epoch": 0.0024413456366119087,
      "grad_norm": 2.3516971050666235,
      "kl": 0.0303955078125,
      "learning_rate": 9.999852939457323e-07,
      "loss": 0.0012,
      "reward": 1.9848124980926514,
      "reward_std": 0.07637369632720947,
      "rewards/accuracy_reward": 0.8035625219345093,
      "rewards/format_reward": 1.0,
      "step": 177
    },
    {
      "all_correct": 0.25,
      "all_wrong": 0.0,
      "completion_length": 415.53125,
      "epoch": 0.002455138549813106,
      "grad_norm": 1.930799227540862,
      "kl": 0.02978515625,
      "learning_rate": 9.999851273070466e-07,
      "loss": 0.0012,
      "reward": 1.9667500257492065,
      "reward_std": 0.06736990064382553,
      "rewards/accuracy_reward": 0.7667499780654907,
      "rewards/format_reward": 1.0,
      "step": 178
    },
    {
      "all_correct": 0.25,
      "all_wrong": 0.0,
      "completion_length": 414.46875,
      "epoch": 0.0024689314630143033,
      "grad_norm": 2.098250753067024,
      "kl": 0.03271484375,
      "learning_rate": 9.9998495972957e-07,
      "loss": 0.0013,
      "reward": 1.9832812547683716,
      "reward_std": 0.04954220727086067,
      "rewards/accuracy_reward": 0.7832812070846558,
      "rewards/format_reward": 1.0,
      "step": 179
    },
    {
      "all_correct": 0.0,
      "all_wrong": 0.0,
      "completion_length": 417.59375,
      "epoch": 0.0024827243762155005,
      "grad_norm": 2.2996429439129265,
      "kl": 0.031494140625,
      "learning_rate": 9.99984791213303e-07,
      "loss": 0.0013,
      "reward": 2.0596561431884766,
      "reward_std": 0.07544936239719391,
      "rewards/accuracy_reward": 0.8596562147140503,
      "rewards/format_reward": 1.0,
      "step": 180
    },
    {
      "all_correct": 0.25,
      "all_wrong": 0.0,
      "completion_length": 419.59375,
      "epoch": 0.002496517289416698,
      "grad_norm": 4.634416433331346,
      "kl": 0.033447265625,
      "learning_rate": 9.999846217582459e-07,
      "loss": 0.0013,
      "reward": 2.0994374752044678,
      "reward_std": 0.08039168268442154,
      "rewards/accuracy_reward": 0.9119374752044678,
      "rewards/format_reward": 1.0,
      "step": 181
    },
    {
      "all_correct": 1.0,
      "all_wrong": 0.0,
      "completion_length": 409.9375,
      "epoch": 0.002510310202617895,
      "grad_norm": 4.544426596764613,
      "kl": 0.03076171875,
      "learning_rate": 9.999844513643989e-07,
      "loss": 0.0012,
      "reward": 2.1343436241149902,
      "reward_std": 0.03114665299654007,
      "rewards/accuracy_reward": 0.934343695640564,
      "rewards/format_reward": 1.0,
      "step": 182
    },
    {
      "all_correct": 0.0,
      "all_wrong": 0.0,
      "completion_length": 426.40625,
      "epoch": 0.0025241031158190924,
      "grad_norm": 1.935963583219852,
      "kl": 0.032958984375,
      "learning_rate": 9.999842800317621e-07,
      "loss": 0.0013,
      "reward": 1.8970000743865967,
      "reward_std": 0.07467754185199738,
      "rewards/accuracy_reward": 0.715749979019165,
      "rewards/format_reward": 1.0,
      "step": 183
    },
    {
      "all_correct": 0.25,
      "all_wrong": 0.0,
      "completion_length": 423.5,
      "epoch": 0.002537896029020289,
      "grad_norm": 2.3059422667549065,
      "kl": 0.0296630859375,
      "learning_rate": 9.999841077603362e-07,
      "loss": 0.0012,
      "reward": 1.9113438129425049,
      "reward_std": 0.07229673862457275,
      "rewards/accuracy_reward": 0.7113437652587891,
      "rewards/format_reward": 1.0,
      "step": 184
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.0,
      "completion_length": 414.03125,
      "epoch": 0.0025516889422214865,
      "grad_norm": 1.8840305479355008,
      "kl": 0.031982421875,
      "learning_rate": 9.999839345501216e-07,
      "loss": 0.0013,
      "reward": 2.0431251525878906,
      "reward_std": 0.032546259462833405,
      "rewards/accuracy_reward": 0.8431249856948853,
      "rewards/format_reward": 1.0,
      "step": 185
    },
    {
      "all_correct": 0.75,
      "all_wrong": 0.0,
      "completion_length": 415.90625,
      "epoch": 0.0025654818554226837,
      "grad_norm": 2.8036313506148747,
      "kl": 0.03515625,
      "learning_rate": 9.99983760401118e-07,
      "loss": 0.0014,
      "reward": 2.1312499046325684,
      "reward_std": 0.029460545629262924,
      "rewards/accuracy_reward": 0.9312500357627869,
      "rewards/format_reward": 1.0,
      "step": 186
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.0,
      "completion_length": 399.84375,
      "epoch": 0.002579274768623881,
      "grad_norm": 2.3846755043463865,
      "kl": 0.0322265625,
      "learning_rate": 9.999835853133264e-07,
      "loss": 0.0013,
      "reward": 2.05440616607666,
      "reward_std": 0.05262136459350586,
      "rewards/accuracy_reward": 0.8544061779975891,
      "rewards/format_reward": 1.0,
      "step": 187
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.0,
      "completion_length": 406.09375,
      "epoch": 0.0025930676818250783,
      "grad_norm": 3.0644871241090827,
      "kl": 0.033447265625,
      "learning_rate": 9.99983409286747e-07,
      "loss": 0.0013,
      "reward": 2.025156259536743,
      "reward_std": 0.04958387464284897,
      "rewards/accuracy_reward": 0.8251562118530273,
      "rewards/format_reward": 1.0,
      "step": 188
    },
    {
      "all_correct": 0.25,
      "all_wrong": 0.0,
      "completion_length": 394.5,
      "epoch": 0.0026068605950262756,
      "grad_norm": 3.5594640926602206,
      "kl": 0.03369140625,
      "learning_rate": 9.999832323213797e-07,
      "loss": 0.0013,
      "reward": 2.0376248359680176,
      "reward_std": 0.08755264431238174,
      "rewards/accuracy_reward": 0.8438750505447388,
      "rewards/format_reward": 1.0,
      "step": 189
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.0,
      "completion_length": 376.40625,
      "epoch": 0.002620653508227473,
      "grad_norm": 1.7232180978453093,
      "kl": 0.033203125,
      "learning_rate": 9.999830544172252e-07,
      "loss": 0.0013,
      "reward": 2.0407187938690186,
      "reward_std": 0.05778937414288521,
      "rewards/accuracy_reward": 0.8657187223434448,
      "rewards/format_reward": 1.0,
      "step": 190
    },
    {
      "all_correct": 0.25,
      "all_wrong": 0.0,
      "completion_length": 397.6875,
      "epoch": 0.00263444642142867,
      "grad_norm": 2.6276855645539037,
      "kl": 0.0289306640625,
      "learning_rate": 9.999828755742839e-07,
      "loss": 0.0012,
      "reward": 2.010031223297119,
      "reward_std": 0.059785306453704834,
      "rewards/accuracy_reward": 0.816281259059906,
      "rewards/format_reward": 1.0,
      "step": 191
    },
    {
      "all_correct": 0.75,
      "all_wrong": 0.0,
      "completion_length": 374.40625,
      "epoch": 0.0026482393346298674,
      "grad_norm": 1.886602129302959,
      "kl": 0.03564453125,
      "learning_rate": 9.99982695792556e-07,
      "loss": 0.0014,
      "reward": 2.1299374103546143,
      "reward_std": 0.04402173310518265,
      "rewards/accuracy_reward": 0.9361875057220459,
      "rewards/format_reward": 1.0,
      "step": 192
    },
    {
      "all_correct": 0.25,
      "all_wrong": 0.0,
      "completion_length": 384.75,
      "epoch": 0.002662032247831064,
      "grad_norm": 2.5563845759958874,
      "kl": 0.034423828125,
      "learning_rate": 9.999825150720416e-07,
      "loss": 0.0014,
      "reward": 2.0019376277923584,
      "reward_std": 0.05592333897948265,
      "rewards/accuracy_reward": 0.8144375085830688,
      "rewards/format_reward": 1.0,
      "step": 193
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.0,
      "completion_length": 393.375,
      "epoch": 0.0026758251610322615,
      "grad_norm": 1.9214993976702013,
      "kl": 0.034423828125,
      "learning_rate": 9.999823334127415e-07,
      "loss": 0.0014,
      "reward": 2.020249843597412,
      "reward_std": 0.07798199355602264,
      "rewards/accuracy_reward": 0.8264999985694885,
      "rewards/format_reward": 1.0,
      "step": 194
    },
    {
      "all_correct": 0.75,
      "all_wrong": 0.0,
      "completion_length": 391.46875,
      "epoch": 0.0026896180742334587,
      "grad_norm": 2.8003295562485913,
      "kl": 0.03515625,
      "learning_rate": 9.999821508146558e-07,
      "loss": 0.0014,
      "reward": 2.056593894958496,
      "reward_std": 0.0458025187253952,
      "rewards/accuracy_reward": 0.8565937280654907,
      "rewards/format_reward": 1.0,
      "step": 195
    },
    {
      "all_correct": 0.25,
      "all_wrong": 0.0,
      "completion_length": 398.4375,
      "epoch": 0.002703410987434656,
      "grad_norm": 2.148460935015114,
      "kl": 0.038330078125,
      "learning_rate": 9.999819672777847e-07,
      "loss": 0.0015,
      "reward": 1.9625625610351562,
      "reward_std": 0.0632413849234581,
      "rewards/accuracy_reward": 0.7625625133514404,
      "rewards/format_reward": 1.0,
      "step": 196
    },
    {
      "all_correct": 0.0,
      "all_wrong": 0.0,
      "completion_length": 375.90625,
      "epoch": 0.0027172039006358533,
      "grad_norm": 2.074352951106199,
      "kl": 0.0341796875,
      "learning_rate": 9.99981782802129e-07,
      "loss": 0.0014,
      "reward": 1.9881561994552612,
      "reward_std": 0.05798901617527008,
      "rewards/accuracy_reward": 0.7944062948226929,
      "rewards/format_reward": 1.0,
      "step": 197
    },
    {
      "all_correct": 0.75,
      "all_wrong": 0.0,
      "completion_length": 399.21875,
      "epoch": 0.0027309968138370506,
      "grad_norm": 2.220833697202844,
      "kl": 0.036865234375,
      "learning_rate": 9.999815973876887e-07,
      "loss": 0.0015,
      "reward": 2.0797812938690186,
      "reward_std": 0.030554696917533875,
      "rewards/accuracy_reward": 0.8797812461853027,
      "rewards/format_reward": 1.0,
      "step": 198
    },
    {
      "all_correct": 0.25,
      "all_wrong": 0.0,
      "completion_length": 385.0,
      "epoch": 0.002744789727038248,
      "grad_norm": 2.778379290637898,
      "kl": 0.03515625,
      "learning_rate": 9.99981411034464e-07,
      "loss": 0.0014,
      "reward": 1.9388437271118164,
      "reward_std": 0.09497188031673431,
      "rewards/accuracy_reward": 0.7450937628746033,
      "rewards/format_reward": 1.0,
      "step": 199
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.0,
      "completion_length": 391.28125,
      "epoch": 0.002758582640239445,
      "grad_norm": 2.967158316469084,
      "kl": 0.03515625,
      "learning_rate": 9.999812237424554e-07,
      "loss": 0.0014,
      "reward": 2.109405994415283,
      "reward_std": 0.05784162878990173,
      "rewards/accuracy_reward": 0.9156562089920044,
      "rewards/format_reward": 1.0,
      "step": 200
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.0,
      "completion_length": 386.65625,
      "epoch": 0.0027723755534406424,
      "grad_norm": 2.4155405988825294,
      "kl": 0.0390625,
      "learning_rate": 9.999810355116635e-07,
      "loss": 0.0016,
      "reward": 1.9998124837875366,
      "reward_std": 0.07975615561008453,
      "rewards/accuracy_reward": 0.8060624599456787,
      "rewards/format_reward": 1.0,
      "step": 201
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.0,
      "completion_length": 401.09375,
      "epoch": 0.002786168466641839,
      "grad_norm": 4.856548535126516,
      "kl": 0.036376953125,
      "learning_rate": 9.999808463420884e-07,
      "loss": 0.0015,
      "reward": 2.0610313415527344,
      "reward_std": 0.07405795156955719,
      "rewards/accuracy_reward": 0.8610312342643738,
      "rewards/format_reward": 1.0,
      "step": 202
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.0,
      "completion_length": 387.46875,
      "epoch": 0.0027999613798430365,
      "grad_norm": 2.030169334494783,
      "kl": 0.03759765625,
      "learning_rate": 9.999806562337306e-07,
      "loss": 0.0015,
      "reward": 2.0602500438690186,
      "reward_std": 0.04804185777902603,
      "rewards/accuracy_reward": 0.8602499961853027,
      "rewards/format_reward": 1.0,
      "step": 203
    },
    {
      "all_correct": 0.25,
      "all_wrong": 0.0,
      "completion_length": 390.71875,
      "epoch": 0.0028137542930442338,
      "grad_norm": 2.3858643652998035,
      "kl": 0.03515625,
      "learning_rate": 9.999804651865903e-07,
      "loss": 0.0014,
      "reward": 2.0386874675750732,
      "reward_std": 0.10029025375843048,
      "rewards/accuracy_reward": 0.8511874675750732,
      "rewards/format_reward": 1.0,
      "step": 204
    },
    {
      "all_correct": 0.75,
      "all_wrong": 0.0,
      "completion_length": 398.71875,
      "epoch": 0.002827547206245431,
      "grad_norm": 2.231389844202713,
      "kl": 0.036376953125,
      "learning_rate": 9.999802732006677e-07,
      "loss": 0.0015,
      "reward": 2.1243438720703125,
      "reward_std": 0.04526836425065994,
      "rewards/accuracy_reward": 0.930593729019165,
      "rewards/format_reward": 1.0,
      "step": 205
    },
    {
      "all_correct": 1.0,
      "all_wrong": 0.0,
      "completion_length": 415.71875,
      "epoch": 0.0028413401194466283,
      "grad_norm": 2.0523450510676393,
      "kl": 0.0400390625,
      "learning_rate": 9.999800802759637e-07,
      "loss": 0.0016,
      "reward": 2.1100001335144043,
      "reward_std": 0.03178774192929268,
      "rewards/accuracy_reward": 0.9100000262260437,
      "rewards/format_reward": 1.0,
      "step": 206
    },
    {
      "all_correct": 0.25,
      "all_wrong": 0.0,
      "completion_length": 388.1875,
      "epoch": 0.0028551330326478256,
      "grad_norm": 2.7988057223980514,
      "kl": 0.038818359375,
      "learning_rate": 9.999798864124782e-07,
      "loss": 0.0016,
      "reward": 1.982968807220459,
      "reward_std": 0.05906786024570465,
      "rewards/accuracy_reward": 0.8017187118530273,
      "rewards/format_reward": 1.0,
      "step": 207
    },
    {
      "all_correct": 0.75,
      "all_wrong": 0.0,
      "completion_length": 399.6875,
      "epoch": 0.002868925945849023,
      "grad_norm": 2.5171061772943553,
      "kl": 0.04150390625,
      "learning_rate": 9.999796916102117e-07,
      "loss": 0.0017,
      "reward": 2.094249963760376,
      "reward_std": 0.0296689011156559,
      "rewards/accuracy_reward": 0.8942500352859497,
      "rewards/format_reward": 1.0,
      "step": 208
    },
    {
      "all_correct": 1.0,
      "all_wrong": 0.0,
      "completion_length": 399.28125,
      "epoch": 0.00288271885905022,
      "grad_norm": 2.094314720403659,
      "kl": 0.041748046875,
      "learning_rate": 9.999794958691644e-07,
      "loss": 0.0017,
      "reward": 2.1491875648498535,
      "reward_std": 0.03765999525785446,
      "rewards/accuracy_reward": 0.9554375410079956,
      "rewards/format_reward": 1.0,
      "step": 209
    },
    {
      "all_correct": 0.25,
      "all_wrong": 0.0,
      "completion_length": 392.9375,
      "epoch": 0.0028965117722514174,
      "grad_norm": 1.6503501456992873,
      "kl": 0.040283203125,
      "learning_rate": 9.999792991893372e-07,
      "loss": 0.0016,
      "reward": 1.9469687938690186,
      "reward_std": 0.017904702574014664,
      "rewards/accuracy_reward": 0.7469687461853027,
      "rewards/format_reward": 1.0,
      "step": 210
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.0,
      "completion_length": 407.34375,
      "epoch": 0.0029103046854526146,
      "grad_norm": 2.8394906789667065,
      "kl": 0.03564453125,
      "learning_rate": 9.9997910157073e-07,
      "loss": 0.0014,
      "reward": 2.040562629699707,
      "reward_std": 0.025202153250575066,
      "rewards/accuracy_reward": 0.8405624628067017,
      "rewards/format_reward": 1.0,
      "step": 211
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.0,
      "completion_length": 422.8125,
      "epoch": 0.0029240975986538115,
      "grad_norm": 2.810870263184083,
      "kl": 0.035888671875,
      "learning_rate": 9.999789030133433e-07,
      "loss": 0.0014,
      "reward": 2.0199687480926514,
      "reward_std": 0.033414311707019806,
      "rewards/accuracy_reward": 0.8199687004089355,
      "rewards/format_reward": 1.0,
      "step": 212
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.0,
      "completion_length": 428.25,
      "epoch": 0.0029378905118550088,
      "grad_norm": 3.6223491183378544,
      "kl": 0.0361328125,
      "learning_rate": 9.999787035171775e-07,
      "loss": 0.0014,
      "reward": 2.042468786239624,
      "reward_std": 0.06639298796653748,
      "rewards/accuracy_reward": 0.8487187623977661,
      "rewards/format_reward": 1.0,
      "step": 213
    },
    {
      "all_correct": 0.75,
      "all_wrong": 0.0,
      "completion_length": 423.09375,
      "epoch": 0.002951683425056206,
      "grad_norm": 2.5290957847109166,
      "kl": 0.040283203125,
      "learning_rate": 9.999785030822327e-07,
      "loss": 0.0016,
      "reward": 2.0207812786102295,
      "reward_std": 0.009096596390008926,
      "rewards/accuracy_reward": 0.8207812905311584,
      "rewards/format_reward": 1.0,
      "step": 214
    },
    {
      "all_correct": 0.0,
      "all_wrong": 0.0,
      "completion_length": 441.34375,
      "epoch": 0.0029654763382574033,
      "grad_norm": 2.324018121666656,
      "kl": 0.0380859375,
      "learning_rate": 9.999783017085097e-07,
      "loss": 0.0015,
      "reward": 1.940250039100647,
      "reward_std": 0.08123809099197388,
      "rewards/accuracy_reward": 0.7527499794960022,
      "rewards/format_reward": 1.0,
      "step": 215
    },
    {
      "all_correct": 0.25,
      "all_wrong": 0.0,
      "completion_length": 439.0,
      "epoch": 0.0029792692514586006,
      "grad_norm": 2.941181310819628,
      "kl": 0.044189453125,
      "learning_rate": 9.999780993960087e-07,
      "loss": 0.0018,
      "reward": 2.0858750343322754,
      "reward_std": 0.05253898352384567,
      "rewards/accuracy_reward": 0.8858749866485596,
      "rewards/format_reward": 1.0,
      "step": 216
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.0,
      "completion_length": 429.65625,
      "epoch": 0.002993062164659798,
      "grad_norm": 4.198951692269727,
      "kl": 0.037841796875,
      "learning_rate": 9.9997789614473e-07,
      "loss": 0.0015,
      "reward": 2.0808751583099365,
      "reward_std": 0.06408786028623581,
      "rewards/accuracy_reward": 0.8933749198913574,
      "rewards/format_reward": 1.0,
      "step": 217
    },
    {
      "all_correct": 0.0,
      "all_wrong": 0.0,
      "completion_length": 436.84375,
      "epoch": 0.003006855077860995,
      "grad_norm": 2.1481688044496385,
      "kl": 0.0390625,
      "learning_rate": 9.999776919546741e-07,
      "loss": 0.0016,
      "reward": 1.968843698501587,
      "reward_std": 0.061460018157958984,
      "rewards/accuracy_reward": 0.7813437581062317,
      "rewards/format_reward": 1.0,
      "step": 218
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.0,
      "completion_length": 426.9375,
      "epoch": 0.0030206479910621924,
      "grad_norm": 2.6496714616841377,
      "kl": 0.034912109375,
      "learning_rate": 9.999774868258415e-07,
      "loss": 0.0014,
      "reward": 2.1024374961853027,
      "reward_std": 0.05336809158325195,
      "rewards/accuracy_reward": 0.9086875319480896,
      "rewards/format_reward": 1.0,
      "step": 219
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.0,
      "completion_length": 433.15625,
      "epoch": 0.0030344409042633897,
      "grad_norm": 3.146872570782692,
      "kl": 0.0361328125,
      "learning_rate": 9.99977280758232e-07,
      "loss": 0.0014,
      "reward": 2.088718891143799,
      "reward_std": 0.04650425165891647,
      "rewards/accuracy_reward": 0.8887187838554382,
      "rewards/format_reward": 1.0,
      "step": 220
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.0,
      "completion_length": 441.15625,
      "epoch": 0.0030482338174645865,
      "grad_norm": 3.6577890864718205,
      "kl": 0.035888671875,
      "learning_rate": 9.999770737518467e-07,
      "loss": 0.0014,
      "reward": 1.9315937757492065,
      "reward_std": 0.05462124943733215,
      "rewards/accuracy_reward": 0.7378437519073486,
      "rewards/format_reward": 1.0,
      "step": 221
    },
    {
      "all_correct": 0.0,
      "all_wrong": 0.0,
      "completion_length": 406.875,
      "epoch": 0.0030620267306657838,
      "grad_norm": 2.3048021507859753,
      "kl": 0.0390625,
      "learning_rate": 9.999768658066856e-07,
      "loss": 0.0016,
      "reward": 1.9279687404632568,
      "reward_std": 0.035580676048994064,
      "rewards/accuracy_reward": 0.7279687523841858,
      "rewards/format_reward": 1.0,
      "step": 222
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.0,
      "completion_length": 436.625,
      "epoch": 0.003075819643866981,
      "grad_norm": 2.110741351371158,
      "kl": 0.03466796875,
      "learning_rate": 9.999766569227492e-07,
      "loss": 0.0014,
      "reward": 2.1274685859680176,
      "reward_std": 0.04286646842956543,
      "rewards/accuracy_reward": 0.9337186813354492,
      "rewards/format_reward": 1.0,
      "step": 223
    },
    {
      "all_correct": 0.25,
      "all_wrong": 0.0,
      "completion_length": 437.4375,
      "epoch": 0.0030896125570681783,
      "grad_norm": 2.836998473383281,
      "kl": 0.035400390625,
      "learning_rate": 9.99976447100038e-07,
      "loss": 0.0014,
      "reward": 2.083156108856201,
      "reward_std": 0.08227825164794922,
      "rewards/accuracy_reward": 0.9144062399864197,
      "rewards/format_reward": 1.0,
      "step": 224
    },
    {
      "all_correct": 0.25,
      "all_wrong": 0.0,
      "completion_length": 429.5625,
      "epoch": 0.0031034054702693756,
      "grad_norm": 2.7430622755902547,
      "kl": 0.03466796875,
      "learning_rate": 9.999762363385522e-07,
      "loss": 0.0014,
      "reward": 1.981812596321106,
      "reward_std": 0.050020813941955566,
      "rewards/accuracy_reward": 0.7880625128746033,
      "rewards/format_reward": 1.0,
      "step": 225
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.0,
      "completion_length": 419.28125,
      "epoch": 0.003117198383470573,
      "grad_norm": 1.9800776020396267,
      "kl": 0.03515625,
      "learning_rate": 9.999760246382923e-07,
      "loss": 0.0014,
      "reward": 1.9923436641693115,
      "reward_std": 0.03193720430135727,
      "rewards/accuracy_reward": 0.79234379529953,
      "rewards/format_reward": 1.0,
      "step": 226
    },
    {
      "all_correct": 0.25,
      "all_wrong": 0.0,
      "completion_length": 416.28125,
      "epoch": 0.00313099129667177,
      "grad_norm": 3.840783521055594,
      "kl": 0.037109375,
      "learning_rate": 9.999758119992585e-07,
      "loss": 0.0015,
      "reward": 2.0612502098083496,
      "reward_std": 0.05794785916805267,
      "rewards/accuracy_reward": 0.8675000071525574,
      "rewards/format_reward": 1.0,
      "step": 227
    },
    {
      "all_correct": 0.25,
      "all_wrong": 0.0,
      "completion_length": 401.6875,
      "epoch": 0.0031447842098729674,
      "grad_norm": 2.8702125160240683,
      "kl": 0.033203125,
      "learning_rate": 9.999755984214516e-07,
      "loss": 0.0013,
      "reward": 1.9457812309265137,
      "reward_std": 0.04222777858376503,
      "rewards/accuracy_reward": 0.7520312070846558,
      "rewards/format_reward": 1.0,
      "step": 228
    },
    {
      "all_correct": 0.75,
      "all_wrong": 0.0,
      "completion_length": 412.1875,
      "epoch": 0.0031585771230741647,
      "grad_norm": 2.286887849107822,
      "kl": 0.03271484375,
      "learning_rate": 9.999753839048714e-07,
      "loss": 0.0013,
      "reward": 2.0785627365112305,
      "reward_std": 0.05187535285949707,
      "rewards/accuracy_reward": 0.8785625100135803,
      "rewards/format_reward": 1.0,
      "step": 229
    },
    {
      "all_correct": 0.25,
      "all_wrong": 0.0,
      "completion_length": 409.78125,
      "epoch": 0.003172370036275362,
      "grad_norm": 2.6577956362347734,
      "kl": 0.0361328125,
      "learning_rate": 9.99975168449519e-07,
      "loss": 0.0014,
      "reward": 1.9205312728881836,
      "reward_std": 0.06479774415493011,
      "rewards/accuracy_reward": 0.7267812490463257,
      "rewards/format_reward": 1.0,
      "step": 230
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.0,
      "completion_length": 410.96875,
      "epoch": 0.0031861629494765588,
      "grad_norm": 2.126939914195246,
      "kl": 0.034423828125,
      "learning_rate": 9.999749520553944e-07,
      "loss": 0.0014,
      "reward": 2.0932188034057617,
      "reward_std": 0.04308244585990906,
      "rewards/accuracy_reward": 0.8932187557220459,
      "rewards/format_reward": 1.0,
      "step": 231
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.0,
      "completion_length": 399.5625,
      "epoch": 0.003199955862677756,
      "grad_norm": 2.2119580904414464,
      "kl": 0.03955078125,
      "learning_rate": 9.999747347224981e-07,
      "loss": 0.0016,
      "reward": 2.0918750762939453,
      "reward_std": 0.05328710377216339,
      "rewards/accuracy_reward": 0.8918749690055847,
      "rewards/format_reward": 1.0,
      "step": 232
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.0,
      "completion_length": 388.3125,
      "epoch": 0.0032137487758789533,
      "grad_norm": 2.3851822614862614,
      "kl": 0.0361328125,
      "learning_rate": 9.999745164508304e-07,
      "loss": 0.0014,
      "reward": 2.1035313606262207,
      "reward_std": 0.03318953141570091,
      "rewards/accuracy_reward": 0.9035312533378601,
      "rewards/format_reward": 1.0,
      "step": 233
    },
    {
      "all_correct": 0.0,
      "all_wrong": 0.0,
      "completion_length": 406.6875,
      "epoch": 0.0032275416890801506,
      "grad_norm": 2.9115246098203573,
      "kl": 0.0361328125,
      "learning_rate": 9.999742972403918e-07,
      "loss": 0.0014,
      "reward": 1.9703125953674316,
      "reward_std": 0.05693824589252472,
      "rewards/accuracy_reward": 0.770312488079071,
      "rewards/format_reward": 1.0,
      "step": 234
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.0,
      "completion_length": 402.78125,
      "epoch": 0.003241334602281348,
      "grad_norm": 2.2069067408045258,
      "kl": 0.03564453125,
      "learning_rate": 9.999740770911827e-07,
      "loss": 0.0014,
      "reward": 2.0199062824249268,
      "reward_std": 0.045900505036115646,
      "rewards/accuracy_reward": 0.8199062347412109,
      "rewards/format_reward": 1.0,
      "step": 235
    },
    {
      "all_correct": 0.25,
      "all_wrong": 0.0,
      "completion_length": 404.875,
      "epoch": 0.003255127515482545,
      "grad_norm": 2.7380543468041236,
      "kl": 0.040283203125,
      "learning_rate": 9.999738560032035e-07,
      "loss": 0.0016,
      "reward": 2.006593704223633,
      "reward_std": 0.0754980742931366,
      "rewards/accuracy_reward": 0.8128437399864197,
      "rewards/format_reward": 1.0,
      "step": 236
    },
    {
      "all_correct": 0.25,
      "all_wrong": 0.0,
      "completion_length": 408.34375,
      "epoch": 0.0032689204286837424,
      "grad_norm": 2.378886141549322,
      "kl": 0.04150390625,
      "learning_rate": 9.999736339764546e-07,
      "loss": 0.0017,
      "reward": 2.0571250915527344,
      "reward_std": 0.07030831277370453,
      "rewards/accuracy_reward": 0.8633750081062317,
      "rewards/format_reward": 1.0,
      "step": 237
    },
    {
      "all_correct": 0.25,
      "all_wrong": 0.0,
      "completion_length": 385.46875,
      "epoch": 0.0032827133418849397,
      "grad_norm": 2.518868413202874,
      "kl": 0.0380859375,
      "learning_rate": 9.999734110109366e-07,
      "loss": 0.0015,
      "reward": 2.006500244140625,
      "reward_std": 0.07023480534553528,
      "rewards/accuracy_reward": 0.8127500414848328,
      "rewards/format_reward": 1.0,
      "step": 238
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.0,
      "completion_length": 425.65625,
      "epoch": 0.003296506255086137,
      "grad_norm": 2.398354781072295,
      "kl": 0.044921875,
      "learning_rate": 9.999731871066497e-07,
      "loss": 0.0018,
      "reward": 2.0112500190734863,
      "reward_std": 0.05328204482793808,
      "rewards/accuracy_reward": 0.8112499713897705,
      "rewards/format_reward": 1.0,
      "step": 239
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.0,
      "completion_length": 403.65625,
      "epoch": 0.0033102991682873338,
      "grad_norm": 2.030876481703043,
      "kl": 0.0341796875,
      "learning_rate": 9.999729622635945e-07,
      "loss": 0.0014,
      "reward": 2.0425000190734863,
      "reward_std": 0.04199083149433136,
      "rewards/accuracy_reward": 0.8425000309944153,
      "rewards/format_reward": 1.0,
      "step": 240
    },
    {
      "all_correct": 0.0,
      "all_wrong": 0.0,
      "completion_length": 391.3125,
      "epoch": 0.003324092081488531,
      "grad_norm": 3.0114917592564114,
      "kl": 0.036376953125,
      "learning_rate": 9.999727364817711e-07,
      "loss": 0.0015,
      "reward": 1.9598751068115234,
      "reward_std": 0.07175479829311371,
      "rewards/accuracy_reward": 0.7723749876022339,
      "rewards/format_reward": 1.0,
      "step": 241
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.0,
      "completion_length": 412.59375,
      "epoch": 0.0033378849946897283,
      "grad_norm": 2.23632288724753,
      "kl": 0.036376953125,
      "learning_rate": 9.999725097611803e-07,
      "loss": 0.0015,
      "reward": 2.0199689865112305,
      "reward_std": 0.04627995938062668,
      "rewards/accuracy_reward": 0.8262187242507935,
      "rewards/format_reward": 1.0,
      "step": 242
    },
    {
      "all_correct": 0.0,
      "all_wrong": 0.0,
      "completion_length": 410.40625,
      "epoch": 0.0033516779078909256,
      "grad_norm": 2.086962635355399,
      "kl": 0.033203125,
      "learning_rate": 9.999722821018225e-07,
      "loss": 0.0013,
      "reward": 2.01981258392334,
      "reward_std": 0.052031271159648895,
      "rewards/accuracy_reward": 0.8260624408721924,
      "rewards/format_reward": 1.0,
      "step": 243
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.0,
      "completion_length": 435.84375,
      "epoch": 0.003365470821092123,
      "grad_norm": 2.1725635795225635,
      "kl": 0.033447265625,
      "learning_rate": 9.999720535036976e-07,
      "loss": 0.0013,
      "reward": 2.106781482696533,
      "reward_std": 0.07235150039196014,
      "rewards/accuracy_reward": 0.9130312204360962,
      "rewards/format_reward": 1.0,
      "step": 244
    },
    {
      "all_correct": 0.0,
      "all_wrong": 0.0,
      "completion_length": 405.71875,
      "epoch": 0.00337926373429332,
      "grad_norm": 2.057129382744587,
      "kl": 0.038330078125,
      "learning_rate": 9.999718239668067e-07,
      "loss": 0.0015,
      "reward": 1.9260313510894775,
      "reward_std": 0.08792833238840103,
      "rewards/accuracy_reward": 0.7447812557220459,
      "rewards/format_reward": 1.0,
      "step": 245
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.0,
      "completion_length": 401.625,
      "epoch": 0.0033930566474945174,
      "grad_norm": 2.652843441716905,
      "kl": 0.032470703125,
      "learning_rate": 9.999715934911499e-07,
      "loss": 0.0013,
      "reward": 2.0135936737060547,
      "reward_std": 0.059460051357746124,
      "rewards/accuracy_reward": 0.8198436498641968,
      "rewards/format_reward": 1.0,
      "step": 246
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.0,
      "completion_length": 411.46875,
      "epoch": 0.0034068495606957147,
      "grad_norm": 2.295464281374007,
      "kl": 0.03515625,
      "learning_rate": 9.999713620767277e-07,
      "loss": 0.0014,
      "reward": 2.00028133392334,
      "reward_std": 0.06256881356239319,
      "rewards/accuracy_reward": 0.8065312504768372,
      "rewards/format_reward": 1.0,
      "step": 247
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.0,
      "completion_length": 412.3125,
      "epoch": 0.003420642473896912,
      "grad_norm": 2.0800237727160855,
      "kl": 0.03662109375,
      "learning_rate": 9.999711297235406e-07,
      "loss": 0.0015,
      "reward": 1.9807811975479126,
      "reward_std": 0.04289881885051727,
      "rewards/accuracy_reward": 0.7807812690734863,
      "rewards/format_reward": 1.0,
      "step": 248
    },
    {
      "all_correct": 0.0,
      "all_wrong": 0.0,
      "completion_length": 426.4375,
      "epoch": 0.0034344353870981088,
      "grad_norm": 2.199975124800715,
      "kl": 0.037109375,
      "learning_rate": 9.999708964315887e-07,
      "loss": 0.0015,
      "reward": 2.0427188873291016,
      "reward_std": 0.0730399638414383,
      "rewards/accuracy_reward": 0.8489687442779541,
      "rewards/format_reward": 1.0,
      "step": 249
    },
    {
      "all_correct": 0.25,
      "all_wrong": 0.0,
      "completion_length": 425.0,
      "epoch": 0.003448228300299306,
      "grad_norm": 2.0438191738697555,
      "kl": 0.03515625,
      "learning_rate": 9.999706622008729e-07,
      "loss": 0.0014,
      "reward": 2.087437629699707,
      "reward_std": 0.07310131192207336,
      "rewards/accuracy_reward": 0.8936874866485596,
      "rewards/format_reward": 1.0,
      "step": 250
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.0,
      "completion_length": 395.46875,
      "epoch": 0.0034620212135005033,
      "grad_norm": 2.1852266242442493,
      "kl": 0.034423828125,
      "learning_rate": 9.999704270313933e-07,
      "loss": 0.0014,
      "reward": 2.0613436698913574,
      "reward_std": 0.05800023674964905,
      "rewards/accuracy_reward": 0.8613438010215759,
      "rewards/format_reward": 1.0,
      "step": 251
    },
    {
      "all_correct": 0.25,
      "all_wrong": 0.0,
      "completion_length": 405.65625,
      "epoch": 0.0034758141267017006,
      "grad_norm": 2.0023596759487896,
      "kl": 0.037353515625,
      "learning_rate": 9.999701909231505e-07,
      "loss": 0.0015,
      "reward": 2.0703749656677246,
      "reward_std": 0.062112633138895035,
      "rewards/accuracy_reward": 0.8766250014305115,
      "rewards/format_reward": 1.0,
      "step": 252
    },
    {
      "all_correct": 0.75,
      "all_wrong": 0.0,
      "completion_length": 404.65625,
      "epoch": 0.003489607039902898,
      "grad_norm": 2.109790177842566,
      "kl": 0.039306640625,
      "learning_rate": 9.99969953876145e-07,
      "loss": 0.0016,
      "reward": 2.0616250038146973,
      "reward_std": 0.04189714789390564,
      "rewards/accuracy_reward": 0.8616250157356262,
      "rewards/format_reward": 1.0,
      "step": 253
    },
    {
      "all_correct": 0.25,
      "all_wrong": 0.0,
      "completion_length": 409.65625,
      "epoch": 0.003503399953104095,
      "grad_norm": 3.798202910178685,
      "kl": 0.043212890625,
      "learning_rate": 9.99969715890377e-07,
      "loss": 0.0017,
      "reward": 2.021312713623047,
      "reward_std": 0.058766983449459076,
      "rewards/accuracy_reward": 0.8213124871253967,
      "rewards/format_reward": 1.0,
      "step": 254
    },
    {
      "all_correct": 0.25,
      "all_wrong": 0.0,
      "completion_length": 421.3125,
      "epoch": 0.0035171928663052924,
      "grad_norm": 2.5956728171758354,
      "kl": 0.04541015625,
      "learning_rate": 9.999694769658473e-07,
      "loss": 0.0018,
      "reward": 2.014124870300293,
      "reward_std": 0.0557776540517807,
      "rewards/accuracy_reward": 0.8141250610351562,
      "rewards/format_reward": 1.0,
      "step": 255
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.0,
      "completion_length": 398.09375,
      "epoch": 0.0035309857795064897,
      "grad_norm": 2.2923097999579665,
      "kl": 0.04248046875,
      "learning_rate": 9.99969237102556e-07,
      "loss": 0.0017,
      "reward": 2.091750144958496,
      "reward_std": 0.04986914247274399,
      "rewards/accuracy_reward": 0.8917499780654907,
      "rewards/format_reward": 1.0,
      "step": 256
    },
    {
      "all_correct": 0.0,
      "all_wrong": 0.0,
      "completion_length": 402.25,
      "epoch": 0.003544778692707687,
      "grad_norm": 2.571075561943788,
      "kl": 0.041259765625,
      "learning_rate": 9.99968996300504e-07,
      "loss": 0.0017,
      "reward": 1.8308438062667847,
      "reward_std": 0.07887184619903564,
      "rewards/accuracy_reward": 0.637093722820282,
      "rewards/format_reward": 1.0,
      "step": 257
    },
    {
      "all_correct": 0.25,
      "all_wrong": 0.0,
      "completion_length": 409.3125,
      "epoch": 0.0035585716059088842,
      "grad_norm": 2.544621956527065,
      "kl": 0.041259765625,
      "learning_rate": 9.999687545596911e-07,
      "loss": 0.0016,
      "reward": 2.010499954223633,
      "reward_std": 0.05066101253032684,
      "rewards/accuracy_reward": 0.8167500495910645,
      "rewards/format_reward": 1.0,
      "step": 258
    },
    {
      "all_correct": 0.75,
      "all_wrong": 0.0,
      "completion_length": 416.9375,
      "epoch": 0.003572364519110081,
      "grad_norm": 2.4619144524351153,
      "kl": 0.052734375,
      "learning_rate": 9.999685118801182e-07,
      "loss": 0.0021,
      "reward": 2.0476250648498535,
      "reward_std": 0.04513250291347504,
      "rewards/accuracy_reward": 0.8538749814033508,
      "rewards/format_reward": 1.0,
      "step": 259
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.0,
      "completion_length": 407.5625,
      "epoch": 0.0035861574323112783,
      "grad_norm": 2.6809247747108422,
      "kl": 0.04052734375,
      "learning_rate": 9.999682682617857e-07,
      "loss": 0.0016,
      "reward": 2.0165936946868896,
      "reward_std": 0.05982508882880211,
      "rewards/accuracy_reward": 0.8165937662124634,
      "rewards/format_reward": 1.0,
      "step": 260
    },
    {
      "all_correct": 1.0,
      "all_wrong": 0.0,
      "completion_length": 410.3125,
      "epoch": 0.0035999503455124756,
      "grad_norm": 2.167779313567494,
      "kl": 0.04345703125,
      "learning_rate": 9.999680237046943e-07,
      "loss": 0.0017,
      "reward": 2.0805938243865967,
      "reward_std": 0.03542504459619522,
      "rewards/accuracy_reward": 0.8805937767028809,
      "rewards/format_reward": 1.0,
      "step": 261
    },
    {
      "all_correct": 0.25,
      "all_wrong": 0.0,
      "completion_length": 418.96875,
      "epoch": 0.003613743258713673,
      "grad_norm": 2.3331276442507054,
      "kl": 0.051025390625,
      "learning_rate": 9.99967778208844e-07,
      "loss": 0.002,
      "reward": 2.005687713623047,
      "reward_std": 0.05576542019844055,
      "rewards/accuracy_reward": 0.8119375109672546,
      "rewards/format_reward": 1.0,
      "step": 262
    },
    {
      "all_correct": 0.0,
      "all_wrong": 0.0,
      "completion_length": 398.8125,
      "epoch": 0.00362753617191487,
      "grad_norm": 2.0182493850384673,
      "kl": 0.039306640625,
      "learning_rate": 9.999675317742354e-07,
      "loss": 0.0016,
      "reward": 1.909406304359436,
      "reward_std": 0.0761910229921341,
      "rewards/accuracy_reward": 0.7156562805175781,
      "rewards/format_reward": 1.0,
      "step": 263
    },
    {
      "all_correct": 0.75,
      "all_wrong": 0.0,
      "completion_length": 398.5625,
      "epoch": 0.0036413290851160674,
      "grad_norm": 2.2441006666586385,
      "kl": 0.0419921875,
      "learning_rate": 9.999672844008688e-07,
      "loss": 0.0017,
      "reward": 2.105343818664551,
      "reward_std": 0.05280838906764984,
      "rewards/accuracy_reward": 0.9115937948226929,
      "rewards/format_reward": 1.0,
      "step": 264
    },
    {
      "all_correct": 0.25,
      "all_wrong": 0.0,
      "completion_length": 411.0625,
      "epoch": 0.0036551219983172647,
      "grad_norm": 1.9324917564079633,
      "kl": 0.047607421875,
      "learning_rate": 9.999670360887451e-07,
      "loss": 0.0019,
      "reward": 1.9695937633514404,
      "reward_std": 0.06791258603334427,
      "rewards/accuracy_reward": 0.7883437871932983,
      "rewards/format_reward": 1.0,
      "step": 265
    },
    {
      "all_correct": 0.75,
      "all_wrong": 0.0,
      "completion_length": 405.28125,
      "epoch": 0.003668914911518462,
      "grad_norm": 3.0008398320119687,
      "kl": 0.049072265625,
      "learning_rate": 9.999667868378646e-07,
      "loss": 0.002,
      "reward": 2.1115000247955322,
      "reward_std": 0.04329709708690643,
      "rewards/accuracy_reward": 0.9114999771118164,
      "rewards/format_reward": 1.0,
      "step": 266
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.0,
      "completion_length": 417.90625,
      "epoch": 0.0036827078247196592,
      "grad_norm": 1.9823630409894832,
      "kl": 0.039794921875,
      "learning_rate": 9.999665366482277e-07,
      "loss": 0.0016,
      "reward": 2.0032811164855957,
      "reward_std": 0.046205341815948486,
      "rewards/accuracy_reward": 0.8157812356948853,
      "rewards/format_reward": 1.0,
      "step": 267
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.0,
      "completion_length": 403.84375,
      "epoch": 0.003696500737920856,
      "grad_norm": 2.831452106077776,
      "kl": 0.037109375,
      "learning_rate": 9.999662855198347e-07,
      "loss": 0.0015,
      "reward": 2.02303147315979,
      "reward_std": 0.04871858283877373,
      "rewards/accuracy_reward": 0.829281210899353,
      "rewards/format_reward": 1.0,
      "step": 268
    },
    {
      "all_correct": 1.0,
      "all_wrong": 0.0,
      "completion_length": 412.34375,
      "epoch": 0.0037102936511220533,
      "grad_norm": 3.2184165746431113,
      "kl": 0.0400390625,
      "learning_rate": 9.999660334526865e-07,
      "loss": 0.0016,
      "reward": 2.145625114440918,
      "reward_std": 0.03861492872238159,
      "rewards/accuracy_reward": 0.9456250071525574,
      "rewards/format_reward": 1.0,
      "step": 269
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.0,
      "completion_length": 398.375,
      "epoch": 0.0037240865643232506,
      "grad_norm": 2.5247440595860047,
      "kl": 0.041748046875,
      "learning_rate": 9.999657804467831e-07,
      "loss": 0.0017,
      "reward": 2.060500144958496,
      "reward_std": 0.0684417188167572,
      "rewards/accuracy_reward": 0.8604999780654907,
      "rewards/format_reward": 1.0,
      "step": 270
    },
    {
      "all_correct": 0.25,
      "all_wrong": 0.0,
      "completion_length": 417.0625,
      "epoch": 0.003737879477524448,
      "grad_norm": 3.294549136546471,
      "kl": 0.048828125,
      "learning_rate": 9.999655265021254e-07,
      "loss": 0.002,
      "reward": 2.0664689540863037,
      "reward_std": 0.059139810502529144,
      "rewards/accuracy_reward": 0.8789687752723694,
      "rewards/format_reward": 1.0,
      "step": 271
    },
    {
      "all_correct": 0.75,
      "all_wrong": 0.0,
      "completion_length": 403.96875,
      "epoch": 0.003751672390725645,
      "grad_norm": 2.2085419354877507,
      "kl": 0.0419921875,
      "learning_rate": 9.999652716187134e-07,
      "loss": 0.0017,
      "reward": 2.113156318664551,
      "reward_std": 0.054125670343637466,
      "rewards/accuracy_reward": 0.913156270980835,
      "rewards/format_reward": 1.0,
      "step": 272
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.0,
      "completion_length": 418.59375,
      "epoch": 0.0037654653039268424,
      "grad_norm": 2.0449996029290514,
      "kl": 0.045166015625,
      "learning_rate": 9.999650157965483e-07,
      "loss": 0.0018,
      "reward": 2.01143741607666,
      "reward_std": 0.034549862146377563,
      "rewards/accuracy_reward": 0.8114374876022339,
      "rewards/format_reward": 1.0,
      "step": 273
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.0,
      "completion_length": 406.875,
      "epoch": 0.0037792582171280397,
      "grad_norm": 2.3059778358426963,
      "kl": 0.041259765625,
      "learning_rate": 9.999647590356297e-07,
      "loss": 0.0016,
      "reward": 2.101250171661377,
      "reward_std": 0.05277696251869202,
      "rewards/accuracy_reward": 0.9012499451637268,
      "rewards/format_reward": 1.0,
      "step": 274
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.0,
      "completion_length": 395.65625,
      "epoch": 0.003793051130329237,
      "grad_norm": 2.349047338736593,
      "kl": 0.0439453125,
      "learning_rate": 9.999645013359587e-07,
      "loss": 0.0018,
      "reward": 2.070218801498413,
      "reward_std": 0.0551038421690464,
      "rewards/accuracy_reward": 0.8702187538146973,
      "rewards/format_reward": 1.0,
      "step": 275
    },
    {
      "all_correct": 0.0,
      "all_wrong": 0.0,
      "completion_length": 379.53125,
      "epoch": 0.0038068440435304342,
      "grad_norm": 2.7461992071751595,
      "kl": 0.0458984375,
      "learning_rate": 9.999642426975357e-07,
      "loss": 0.0018,
      "reward": 1.9736876487731934,
      "reward_std": 0.07994268089532852,
      "rewards/accuracy_reward": 0.7861874103546143,
      "rewards/format_reward": 1.0,
      "step": 276
    },
    {
      "all_correct": 0.25,
      "all_wrong": 0.0,
      "completion_length": 416.21875,
      "epoch": 0.0038206369567316315,
      "grad_norm": 1.9620647616642628,
      "kl": 0.04443359375,
      "learning_rate": 9.999639831203607e-07,
      "loss": 0.0018,
      "reward": 2.0954062938690186,
      "reward_std": 0.07648126780986786,
      "rewards/accuracy_reward": 0.907906174659729,
      "rewards/format_reward": 1.0,
      "step": 277
    },
    {
      "all_correct": 0.25,
      "all_wrong": 0.0,
      "completion_length": 407.4375,
      "epoch": 0.0038344298699328283,
      "grad_norm": 2.202497343212584,
      "kl": 0.04931640625,
      "learning_rate": 9.999637226044352e-07,
      "loss": 0.002,
      "reward": 1.9760937690734863,
      "reward_std": 0.060630109161138535,
      "rewards/accuracy_reward": 0.7823437452316284,
      "rewards/format_reward": 1.0,
      "step": 278
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.0,
      "completion_length": 391.34375,
      "epoch": 0.0038482227831340256,
      "grad_norm": 2.1483645409790677,
      "kl": 0.0439453125,
      "learning_rate": 9.999634611497585e-07,
      "loss": 0.0018,
      "reward": 2.135937452316284,
      "reward_std": 0.0832315981388092,
      "rewards/accuracy_reward": 0.948437511920929,
      "rewards/format_reward": 1.0,
      "step": 279
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.0,
      "completion_length": 393.8125,
      "epoch": 0.003862015696335223,
      "grad_norm": 2.417496874935089,
      "kl": 0.0498046875,
      "learning_rate": 9.999631987563319e-07,
      "loss": 0.002,
      "reward": 2.0570626258850098,
      "reward_std": 0.04688289389014244,
      "rewards/accuracy_reward": 0.857062578201294,
      "rewards/format_reward": 1.0,
      "step": 280
    },
    {
      "all_correct": 0.0,
      "all_wrong": 0.0,
      "completion_length": 413.3125,
      "epoch": 0.00387580860953642,
      "grad_norm": 1.95025615979101,
      "kl": 0.04541015625,
      "learning_rate": 9.999629354241556e-07,
      "loss": 0.0018,
      "reward": 2.0249063968658447,
      "reward_std": 0.060103025287389755,
      "rewards/accuracy_reward": 0.8249062895774841,
      "rewards/format_reward": 1.0,
      "step": 281
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.0,
      "completion_length": 417.625,
      "epoch": 0.0038896015227376174,
      "grad_norm": 2.5190439820102304,
      "kl": 0.0517578125,
      "learning_rate": 9.999626711532301e-07,
      "loss": 0.0021,
      "reward": 2.060281276702881,
      "reward_std": 0.05729492008686066,
      "rewards/accuracy_reward": 0.860281229019165,
      "rewards/format_reward": 1.0,
      "step": 282
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.0,
      "completion_length": 396.59375,
      "epoch": 0.0039033944359388147,
      "grad_norm": 2.455990250729256,
      "kl": 0.0517578125,
      "learning_rate": 9.99962405943556e-07,
      "loss": 0.0021,
      "reward": 2.0301876068115234,
      "reward_std": 0.03979829326272011,
      "rewards/accuracy_reward": 0.8301875591278076,
      "rewards/format_reward": 1.0,
      "step": 283
    },
    {
      "all_correct": 0.25,
      "all_wrong": 0.0,
      "completion_length": 406.375,
      "epoch": 0.003917187349140012,
      "grad_norm": 2.208309017099772,
      "kl": 0.05078125,
      "learning_rate": 9.999621397951337e-07,
      "loss": 0.002,
      "reward": 1.9785938262939453,
      "reward_std": 0.07059404999017715,
      "rewards/accuracy_reward": 0.7785937786102295,
      "rewards/format_reward": 1.0,
      "step": 284
    },
    {
      "all_correct": 0.75,
      "all_wrong": 0.0,
      "completion_length": 403.46875,
      "epoch": 0.003930980262341209,
      "grad_norm": 2.1968476853910732,
      "kl": 0.0458984375,
      "learning_rate": 9.999618727079638e-07,
      "loss": 0.0018,
      "reward": 2.0583438873291016,
      "reward_std": 0.048853449523448944,
      "rewards/accuracy_reward": 0.8583437204360962,
      "rewards/format_reward": 1.0,
      "step": 285
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.0,
      "completion_length": 393.15625,
      "epoch": 0.0039447731755424065,
      "grad_norm": 1.6202956060079958,
      "kl": 0.046142578125,
      "learning_rate": 9.999616046820466e-07,
      "loss": 0.0018,
      "reward": 2.0592501163482666,
      "reward_std": 0.032233476638793945,
      "rewards/accuracy_reward": 0.859250009059906,
      "rewards/format_reward": 1.0,
      "step": 286
    },
    {
      "all_correct": 0.25,
      "all_wrong": 0.0,
      "completion_length": 414.4375,
      "epoch": 0.003958566088743604,
      "grad_norm": 2.0637169765745687,
      "kl": 0.0498046875,
      "learning_rate": 9.99961335717383e-07,
      "loss": 0.002,
      "reward": 2.1058125495910645,
      "reward_std": 0.06778968125581741,
      "rewards/accuracy_reward": 0.9183124303817749,
      "rewards/format_reward": 1.0,
      "step": 287
    },
    {
      "all_correct": 0.0,
      "all_wrong": 0.0,
      "completion_length": 410.96875,
      "epoch": 0.003972359001944801,
      "grad_norm": 1.9067833192651293,
      "kl": 0.045654296875,
      "learning_rate": 9.99961065813973e-07,
      "loss": 0.0018,
      "reward": 1.8669687509536743,
      "reward_std": 0.08422042429447174,
      "rewards/accuracy_reward": 0.6732187271118164,
      "rewards/format_reward": 1.0,
      "step": 288
    },
    {
      "all_correct": 0.75,
      "all_wrong": 0.0,
      "completion_length": 401.4375,
      "epoch": 0.003986151915145998,
      "grad_norm": 5.707133364027419,
      "kl": 0.0498046875,
      "learning_rate": 9.999607949718175e-07,
      "loss": 0.002,
      "reward": 2.1269373893737793,
      "reward_std": 0.06713393330574036,
      "rewards/accuracy_reward": 0.9331874847412109,
      "rewards/format_reward": 1.0,
      "step": 289
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.0,
      "completion_length": 387.96875,
      "epoch": 0.003999944828347196,
      "grad_norm": 1.9552374066531522,
      "kl": 0.0439453125,
      "learning_rate": 9.999605231909166e-07,
      "loss": 0.0018,
      "reward": 2.0127501487731934,
      "reward_std": 0.05280975252389908,
      "rewards/accuracy_reward": 0.825249969959259,
      "rewards/format_reward": 1.0,
      "step": 290
    },
    {
      "all_correct": 0.0,
      "all_wrong": 0.0,
      "completion_length": 403.84375,
      "epoch": 0.004013737741548393,
      "grad_norm": 1.8859779206151355,
      "kl": 0.0458984375,
      "learning_rate": 9.99960250471271e-07,
      "loss": 0.0018,
      "reward": 1.9792814254760742,
      "reward_std": 0.03198267146945,
      "rewards/accuracy_reward": 0.7792812585830688,
      "rewards/format_reward": 1.0,
      "step": 291
    },
    {
      "all_correct": 0.0,
      "all_wrong": 0.0,
      "completion_length": 424.40625,
      "epoch": 0.004027530654749589,
      "grad_norm": 2.9301732040098734,
      "kl": 0.04638671875,
      "learning_rate": 9.999599768128819e-07,
      "loss": 0.0019,
      "reward": 2.021250009536743,
      "reward_std": 0.07541981339454651,
      "rewards/accuracy_reward": 0.8212499618530273,
      "rewards/format_reward": 1.0,
      "step": 292
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.0,
      "completion_length": 403.96875,
      "epoch": 0.0040413235679507865,
      "grad_norm": 2.170009226320114,
      "kl": 0.049560546875,
      "learning_rate": 9.999597022157487e-07,
      "loss": 0.002,
      "reward": 2.079031467437744,
      "reward_std": 0.03810182213783264,
      "rewards/accuracy_reward": 0.8852812647819519,
      "rewards/format_reward": 1.0,
      "step": 293
    },
    {
      "all_correct": 0.0,
      "all_wrong": 0.0,
      "completion_length": 410.8125,
      "epoch": 0.004055116481151984,
      "grad_norm": 2.1153812969661048,
      "kl": 0.0478515625,
      "learning_rate": 9.999594266798726e-07,
      "loss": 0.0019,
      "reward": 2.0100626945495605,
      "reward_std": 0.07581374794244766,
      "rewards/accuracy_reward": 0.8163124918937683,
      "rewards/format_reward": 1.0,
      "step": 294
    },
    {
      "all_correct": 0.75,
      "all_wrong": 0.0,
      "completion_length": 412.75,
      "epoch": 0.004068909394353181,
      "grad_norm": 1.5327578299175344,
      "kl": 0.0419921875,
      "learning_rate": 9.999591502052539e-07,
      "loss": 0.0017,
      "reward": 2.111968755722046,
      "reward_std": 0.03029218688607216,
      "rewards/accuracy_reward": 0.9119687676429749,
      "rewards/format_reward": 1.0,
      "step": 295
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.0,
      "completion_length": 396.3125,
      "epoch": 0.004082702307554378,
      "grad_norm": 2.3809873329560984,
      "kl": 0.044921875,
      "learning_rate": 9.99958872791893e-07,
      "loss": 0.0018,
      "reward": 2.0056562423706055,
      "reward_std": 0.050386276096105576,
      "rewards/accuracy_reward": 0.8056562542915344,
      "rewards/format_reward": 1.0,
      "step": 296
    },
    {
      "all_correct": 0.25,
      "all_wrong": 0.0,
      "completion_length": 400.46875,
      "epoch": 0.004096495220755576,
      "grad_norm": 2.259090133781256,
      "kl": 0.04443359375,
      "learning_rate": 9.999585944397908e-07,
      "loss": 0.0018,
      "reward": 1.942562460899353,
      "reward_std": 0.06388393044471741,
      "rewards/accuracy_reward": 0.7425624132156372,
      "rewards/format_reward": 1.0,
      "step": 297
    },
    {
      "all_correct": 0.25,
      "all_wrong": 0.0,
      "completion_length": 406.0625,
      "epoch": 0.004110288133956773,
      "grad_norm": 2.187301874035118,
      "kl": 0.039306640625,
      "learning_rate": 9.999583151489474e-07,
      "loss": 0.0016,
      "reward": 2.076937437057495,
      "reward_std": 0.06230815127491951,
      "rewards/accuracy_reward": 0.8769375085830688,
      "rewards/format_reward": 1.0,
      "step": 298
    },
    {
      "all_correct": 0.25,
      "all_wrong": 0.0,
      "completion_length": 421.0625,
      "epoch": 0.00412408104715797,
      "grad_norm": 2.9053013740819162,
      "kl": 0.03857421875,
      "learning_rate": 9.999580349193636e-07,
      "loss": 0.0016,
      "reward": 2.093437671661377,
      "reward_std": 0.06497351825237274,
      "rewards/accuracy_reward": 0.8996874690055847,
      "rewards/format_reward": 1.0,
      "step": 299
    },
    {
      "all_correct": 0.75,
      "all_wrong": 0.0,
      "completion_length": 402.71875,
      "epoch": 0.0041378739603591674,
      "grad_norm": 2.295198209247636,
      "kl": 0.04150390625,
      "learning_rate": 9.999577537510399e-07,
      "loss": 0.0017,
      "reward": 2.132187604904175,
      "reward_std": 0.04672250896692276,
      "rewards/accuracy_reward": 0.9384374618530273,
      "rewards/format_reward": 1.0,
      "step": 300
    },
    {
      "all_correct": 0.75,
      "all_wrong": 0.0,
      "completion_length": 403.46875,
      "epoch": 0.004151666873560365,
      "grad_norm": 2.6954721125938272,
      "kl": 0.03857421875,
      "learning_rate": 9.999574716439767e-07,
      "loss": 0.0015,
      "reward": 2.0789687633514404,
      "reward_std": 0.04196634143590927,
      "rewards/accuracy_reward": 0.8789687752723694,
      "rewards/format_reward": 1.0,
      "step": 301
    },
    {
      "all_correct": 0.25,
      "all_wrong": 0.0,
      "completion_length": 388.25,
      "epoch": 0.004165459786761562,
      "grad_norm": 7.385240465238868,
      "kl": 0.04443359375,
      "learning_rate": 9.999571885981745e-07,
      "loss": 0.0018,
      "reward": 2.0588436126708984,
      "reward_std": 0.06431737542152405,
      "rewards/accuracy_reward": 0.871343731880188,
      "rewards/format_reward": 1.0,
      "step": 302
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.0,
      "completion_length": 392.75,
      "epoch": 0.004179252699962759,
      "grad_norm": 2.3460991055713345,
      "kl": 0.04052734375,
      "learning_rate": 9.999569046136342e-07,
      "loss": 0.0016,
      "reward": 2.053500175476074,
      "reward_std": 0.044138554483652115,
      "rewards/accuracy_reward": 0.8535000085830688,
      "rewards/format_reward": 1.0,
      "step": 303
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.0,
      "completion_length": 404.90625,
      "epoch": 0.0041930456131639565,
      "grad_norm": 2.1793114997339096,
      "kl": 0.03759765625,
      "learning_rate": 9.999566196903558e-07,
      "loss": 0.0015,
      "reward": 2.0028750896453857,
      "reward_std": 0.05084363371133804,
      "rewards/accuracy_reward": 0.8028749227523804,
      "rewards/format_reward": 1.0,
      "step": 304
    },
    {
      "all_correct": 0.25,
      "all_wrong": 0.0,
      "completion_length": 378.78125,
      "epoch": 0.004206838526365154,
      "grad_norm": 2.1235652494656043,
      "kl": 0.041748046875,
      "learning_rate": 9.999563338283403e-07,
      "loss": 0.0017,
      "reward": 1.9711250066757202,
      "reward_std": 0.06680046021938324,
      "rewards/accuracy_reward": 0.7961249947547913,
      "rewards/format_reward": 1.0,
      "step": 305
    },
    {
      "all_correct": 0.75,
      "all_wrong": 0.0,
      "completion_length": 402.03125,
      "epoch": 0.004220631439566351,
      "grad_norm": 2.4226850161928932,
      "kl": 0.0419921875,
      "learning_rate": 9.99956047027588e-07,
      "loss": 0.0017,
      "reward": 2.0967187881469727,
      "reward_std": 0.04176875203847885,
      "rewards/accuracy_reward": 0.8967186808586121,
      "rewards/format_reward": 1.0,
      "step": 306
    },
    {
      "all_correct": 0.75,
      "all_wrong": 0.0,
      "completion_length": 392.375,
      "epoch": 0.004234424352767548,
      "grad_norm": 2.003513508773817,
      "kl": 0.03564453125,
      "learning_rate": 9.999557592880993e-07,
      "loss": 0.0014,
      "reward": 2.124812602996826,
      "reward_std": 0.032197341322898865,
      "rewards/accuracy_reward": 0.9248125553131104,
      "rewards/format_reward": 1.0,
      "step": 307
    },
    {
      "all_correct": 0.75,
      "all_wrong": 0.0,
      "completion_length": 404.40625,
      "epoch": 0.004248217265968746,
      "grad_norm": 1.9352775343816293,
      "kl": 0.035400390625,
      "learning_rate": 9.99955470609875e-07,
      "loss": 0.0014,
      "reward": 2.034749984741211,
      "reward_std": 0.038731303066015244,
      "rewards/accuracy_reward": 0.8347500562667847,
      "rewards/format_reward": 1.0,
      "step": 308
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.0,
      "completion_length": 411.4375,
      "epoch": 0.004262010179169943,
      "grad_norm": 2.302998863040488,
      "kl": 0.04052734375,
      "learning_rate": 9.999551809929157e-07,
      "loss": 0.0016,
      "reward": 2.0734689235687256,
      "reward_std": 0.03724667429924011,
      "rewards/accuracy_reward": 0.8734687566757202,
      "rewards/format_reward": 1.0,
      "step": 309
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.0,
      "completion_length": 398.625,
      "epoch": 0.004275803092371139,
      "grad_norm": 2.0008945162862513,
      "kl": 0.0400390625,
      "learning_rate": 9.999548904372217e-07,
      "loss": 0.0016,
      "reward": 2.108562469482422,
      "reward_std": 0.040712036192417145,
      "rewards/accuracy_reward": 0.9148125052452087,
      "rewards/format_reward": 1.0,
      "step": 310
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.0,
      "completion_length": 398.3125,
      "epoch": 0.0042895960055723365,
      "grad_norm": 2.561165946126311,
      "kl": 0.03857421875,
      "learning_rate": 9.999545989427936e-07,
      "loss": 0.0015,
      "reward": 2.0611250400543213,
      "reward_std": 0.04077856242656708,
      "rewards/accuracy_reward": 0.8611249923706055,
      "rewards/format_reward": 1.0,
      "step": 311
    },
    {
      "all_correct": 0.25,
      "all_wrong": 0.0,
      "completion_length": 403.96875,
      "epoch": 0.004303388918773534,
      "grad_norm": 2.351894978732953,
      "kl": 0.041748046875,
      "learning_rate": 9.999543065096318e-07,
      "loss": 0.0017,
      "reward": 1.9397813081741333,
      "reward_std": 0.07170985639095306,
      "rewards/accuracy_reward": 0.7460312843322754,
      "rewards/format_reward": 1.0,
      "step": 312
    },
    {
      "all_correct": 0.75,
      "all_wrong": 0.0,
      "completion_length": 409.4375,
      "epoch": 0.004317181831974731,
      "grad_norm": 1.9769740402968916,
      "kl": 0.03759765625,
      "learning_rate": 9.999540131377374e-07,
      "loss": 0.0015,
      "reward": 2.079843759536743,
      "reward_std": 0.032624490559101105,
      "rewards/accuracy_reward": 0.8798437714576721,
      "rewards/format_reward": 1.0,
      "step": 313
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.0,
      "completion_length": 376.75,
      "epoch": 0.004330974745175928,
      "grad_norm": 2.7979880124967864,
      "kl": 0.04345703125,
      "learning_rate": 9.999537188271105e-07,
      "loss": 0.0017,
      "reward": 1.9039688110351562,
      "reward_std": 0.05473501235246658,
      "rewards/accuracy_reward": 0.7164687514305115,
      "rewards/format_reward": 1.0,
      "step": 314
    },
    {
      "all_correct": 0.25,
      "all_wrong": 0.0,
      "completion_length": 408.0625,
      "epoch": 0.004344767658377126,
      "grad_norm": 2.0207158163206063,
      "kl": 0.04345703125,
      "learning_rate": 9.999534235777517e-07,
      "loss": 0.0017,
      "reward": 2.02524995803833,
      "reward_std": 0.06028753146529198,
      "rewards/accuracy_reward": 0.8315000534057617,
      "rewards/format_reward": 1.0,
      "step": 315
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.0,
      "completion_length": 386.75,
      "epoch": 0.004358560571578323,
      "grad_norm": 2.0737064057327186,
      "kl": 0.0390625,
      "learning_rate": 9.999531273896615e-07,
      "loss": 0.0016,
      "reward": 1.9908437728881836,
      "reward_std": 0.07311345636844635,
      "rewards/accuracy_reward": 0.8158438205718994,
      "rewards/format_reward": 1.0,
      "step": 316
    },
    {
      "all_correct": 0.25,
      "all_wrong": 0.0,
      "completion_length": 412.09375,
      "epoch": 0.00437235348477952,
      "grad_norm": 2.2448866082612784,
      "kl": 0.038818359375,
      "learning_rate": 9.999528302628408e-07,
      "loss": 0.0016,
      "reward": 2.05831241607666,
      "reward_std": 0.05879085510969162,
      "rewards/accuracy_reward": 0.8645625114440918,
      "rewards/format_reward": 1.0,
      "step": 317
    },
    {
      "all_correct": 0.25,
      "all_wrong": 0.0,
      "completion_length": 405.5625,
      "epoch": 0.0043861463979807174,
      "grad_norm": 3.378150797647078,
      "kl": 0.042236328125,
      "learning_rate": 9.999525321972898e-07,
      "loss": 0.0017,
      "reward": 1.940500020980835,
      "reward_std": 0.04734080284833908,
      "rewards/accuracy_reward": 0.746749997138977,
      "rewards/format_reward": 1.0,
      "step": 318
    },
    {
      "all_correct": 0.25,
      "all_wrong": 0.0,
      "completion_length": 429.875,
      "epoch": 0.004399939311181915,
      "grad_norm": 1.5939155190729113,
      "kl": 0.037109375,
      "learning_rate": 9.99952233193009e-07,
      "loss": 0.0015,
      "reward": 2.0513124465942383,
      "reward_std": 0.037394169718027115,
      "rewards/accuracy_reward": 0.8575624823570251,
      "rewards/format_reward": 1.0,
      "step": 319
    },
    {
      "all_correct": 0.75,
      "all_wrong": 0.0,
      "completion_length": 412.8125,
      "epoch": 0.004413732224383112,
      "grad_norm": 2.331498153024052,
      "kl": 0.043701171875,
      "learning_rate": 9.999519332499994e-07,
      "loss": 0.0018,
      "reward": 2.0784687995910645,
      "reward_std": 0.02493938058614731,
      "rewards/accuracy_reward": 0.8784687519073486,
      "rewards/format_reward": 1.0,
      "step": 320
    },
    {
      "all_correct": 0.0,
      "all_wrong": 0.0,
      "completion_length": 430.25,
      "epoch": 0.004427525137584309,
      "grad_norm": 2.185404643560563,
      "kl": 0.048583984375,
      "learning_rate": 9.999516323682612e-07,
      "loss": 0.0019,
      "reward": 1.9275312423706055,
      "reward_std": 0.08080125600099564,
      "rewards/accuracy_reward": 0.7400312423706055,
      "rewards/format_reward": 1.0,
      "step": 321
    },
    {
      "all_correct": 0.0,
      "all_wrong": 0.0,
      "completion_length": 399.4375,
      "epoch": 0.0044413180507855065,
      "grad_norm": 2.0086037914799943,
      "kl": 0.042724609375,
      "learning_rate": 9.99951330547795e-07,
      "loss": 0.0017,
      "reward": 1.9912811517715454,
      "reward_std": 0.07223745435476303,
      "rewards/accuracy_reward": 0.797531247138977,
      "rewards/format_reward": 1.0,
      "step": 322
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.0,
      "completion_length": 417.75,
      "epoch": 0.004455110963986704,
      "grad_norm": 3.5915516694367207,
      "kl": 0.04638671875,
      "learning_rate": 9.999510277886015e-07,
      "loss": 0.0019,
      "reward": 2.042468786239624,
      "reward_std": 0.05185335874557495,
      "rewards/accuracy_reward": 0.8424687385559082,
      "rewards/format_reward": 1.0,
      "step": 323
    },
    {
      "all_correct": 0.75,
      "all_wrong": 0.0,
      "completion_length": 398.03125,
      "epoch": 0.004468903877187901,
      "grad_norm": 2.077750974468366,
      "kl": 0.038818359375,
      "learning_rate": 9.999507240906812e-07,
      "loss": 0.0016,
      "reward": 2.135718822479248,
      "reward_std": 0.045622505247592926,
      "rewards/accuracy_reward": 0.9419687390327454,
      "rewards/format_reward": 1.0,
      "step": 324
    },
    {
      "all_correct": 0.75,
      "all_wrong": 0.0,
      "completion_length": 411.53125,
      "epoch": 0.004482696790389098,
      "grad_norm": 3.597813350929996,
      "kl": 0.042236328125,
      "learning_rate": 9.999504194540346e-07,
      "loss": 0.0017,
      "reward": 2.029062509536743,
      "reward_std": 0.03845563158392906,
      "rewards/accuracy_reward": 0.8290624618530273,
      "rewards/format_reward": 1.0,
      "step": 325
    },
    {
      "all_correct": 0.25,
      "all_wrong": 0.0,
      "completion_length": 415.125,
      "epoch": 0.004496489703590296,
      "grad_norm": 2.6370243583822095,
      "kl": 0.0458984375,
      "learning_rate": 9.999501138786624e-07,
      "loss": 0.0018,
      "reward": 1.999406337738037,
      "reward_std": 0.032154206186532974,
      "rewards/accuracy_reward": 0.7994062900543213,
      "rewards/format_reward": 1.0,
      "step": 326
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.0,
      "completion_length": 394.375,
      "epoch": 0.004510282616791493,
      "grad_norm": 3.7311115387817164,
      "kl": 0.044189453125,
      "learning_rate": 9.999498073645652e-07,
      "loss": 0.0018,
      "reward": 2.040843963623047,
      "reward_std": 0.06184101104736328,
      "rewards/accuracy_reward": 0.8470938205718994,
      "rewards/format_reward": 1.0,
      "step": 327
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.0,
      "completion_length": 416.78125,
      "epoch": 0.00452407552999269,
      "grad_norm": 2.6801280911897805,
      "kl": 0.052490234375,
      "learning_rate": 9.999494999117433e-07,
      "loss": 0.0021,
      "reward": 2.0666344165802,
      "reward_std": 0.03997699171304703,
      "rewards/accuracy_reward": 0.8666344285011292,
      "rewards/format_reward": 1.0,
      "step": 328
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.0,
      "completion_length": 419.78125,
      "epoch": 0.0045378684431938866,
      "grad_norm": 5.340731461425449,
      "kl": 0.0419921875,
      "learning_rate": 9.999491915201976e-07,
      "loss": 0.0017,
      "reward": 2.1009063720703125,
      "reward_std": 0.04983200132846832,
      "rewards/accuracy_reward": 0.9009062051773071,
      "rewards/format_reward": 1.0,
      "step": 329
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.0,
      "completion_length": 416.75,
      "epoch": 0.004551661356395084,
      "grad_norm": 2.1024504570922193,
      "kl": 0.044677734375,
      "learning_rate": 9.999488821899285e-07,
      "loss": 0.0018,
      "reward": 2.0531249046325684,
      "reward_std": 0.05571488291025162,
      "rewards/accuracy_reward": 0.859375,
      "rewards/format_reward": 1.0,
      "step": 330
    },
    {
      "all_correct": 0.75,
      "all_wrong": 0.0,
      "completion_length": 407.625,
      "epoch": 0.004565454269596281,
      "grad_norm": 1.9024488830001074,
      "kl": 0.04345703125,
      "learning_rate": 9.999485719209366e-07,
      "loss": 0.0017,
      "reward": 2.124000072479248,
      "reward_std": 0.04417997598648071,
      "rewards/accuracy_reward": 0.9239999651908875,
      "rewards/format_reward": 1.0,
      "step": 331
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.0,
      "completion_length": 413.5,
      "epoch": 0.004579247182797478,
      "grad_norm": 2.763695348323022,
      "kl": 0.04296875,
      "learning_rate": 9.999482607132226e-07,
      "loss": 0.0017,
      "reward": 2.043750047683716,
      "reward_std": 0.05617400258779526,
      "rewards/accuracy_reward": 0.84375,
      "rewards/format_reward": 1.0,
      "step": 332
    },
    {
      "all_correct": 0.25,
      "all_wrong": 0.0,
      "completion_length": 415.8125,
      "epoch": 0.004593040095998676,
      "grad_norm": 2.3001319702998178,
      "kl": 0.04345703125,
      "learning_rate": 9.99947948566787e-07,
      "loss": 0.0017,
      "reward": 1.8749687671661377,
      "reward_std": 0.07037438452243805,
      "rewards/accuracy_reward": 0.6749687790870667,
      "rewards/format_reward": 1.0,
      "step": 333
    },
    {
      "all_correct": 0.75,
      "all_wrong": 0.0,
      "completion_length": 396.90625,
      "epoch": 0.004606833009199873,
      "grad_norm": 2.268465115773429,
      "kl": 0.04345703125,
      "learning_rate": 9.999476354816304e-07,
      "loss": 0.0017,
      "reward": 2.1285624504089355,
      "reward_std": 0.026720412075519562,
      "rewards/accuracy_reward": 0.9285624027252197,
      "rewards/format_reward": 1.0,
      "step": 334
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.0,
      "completion_length": 408.5625,
      "epoch": 0.00462062592240107,
      "grad_norm": 2.4107656291581705,
      "kl": 0.03955078125,
      "learning_rate": 9.99947321457753e-07,
      "loss": 0.0016,
      "reward": 2.097562313079834,
      "reward_std": 0.06343509256839752,
      "rewards/accuracy_reward": 0.897562563419342,
      "rewards/format_reward": 1.0,
      "step": 335
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.0,
      "completion_length": 390.53125,
      "epoch": 0.0046344188356022675,
      "grad_norm": 2.1513955728976346,
      "kl": 0.04150390625,
      "learning_rate": 9.999470064951562e-07,
      "loss": 0.0017,
      "reward": 2.031625270843506,
      "reward_std": 0.035630617290735245,
      "rewards/accuracy_reward": 0.8378750681877136,
      "rewards/format_reward": 1.0,
      "step": 336
    },
    {
      "all_correct": 0.75,
      "all_wrong": 0.0,
      "completion_length": 412.875,
      "epoch": 0.004648211748803465,
      "grad_norm": 2.4460731986358324,
      "kl": 0.043701171875,
      "learning_rate": 9.9994669059384e-07,
      "loss": 0.0018,
      "reward": 2.067187786102295,
      "reward_std": 0.027138758450746536,
      "rewards/accuracy_reward": 0.8671875,
      "rewards/format_reward": 1.0,
      "step": 337
    },
    {
      "all_correct": 0.75,
      "all_wrong": 0.0,
      "completion_length": 397.25,
      "epoch": 0.004662004662004662,
      "grad_norm": 1.9375163075273105,
      "kl": 0.03857421875,
      "learning_rate": 9.999463737538052e-07,
      "loss": 0.0015,
      "reward": 2.0592501163482666,
      "reward_std": 0.059936925768852234,
      "rewards/accuracy_reward": 0.859250009059906,
      "rewards/format_reward": 1.0,
      "step": 338
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.0,
      "completion_length": 396.0,
      "epoch": 0.004675797575205859,
      "grad_norm": 2.1572194579167627,
      "kl": 0.043701171875,
      "learning_rate": 9.999460559750523e-07,
      "loss": 0.0017,
      "reward": 2.0362813472747803,
      "reward_std": 0.05789932236075401,
      "rewards/accuracy_reward": 0.8487812280654907,
      "rewards/format_reward": 1.0,
      "step": 339
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.0,
      "completion_length": 413.34375,
      "epoch": 0.0046895904884070565,
      "grad_norm": 2.231367884501955,
      "kl": 0.044677734375,
      "learning_rate": 9.999457372575818e-07,
      "loss": 0.0018,
      "reward": 1.9827499389648438,
      "reward_std": 0.05621706694364548,
      "rewards/accuracy_reward": 0.7827500104904175,
      "rewards/format_reward": 1.0,
      "step": 340
    },
    {
      "all_correct": 0.25,
      "all_wrong": 0.0,
      "completion_length": 415.75,
      "epoch": 0.004703383401608254,
      "grad_norm": 1.8589563338021162,
      "kl": 0.039306640625,
      "learning_rate": 9.999454176013947e-07,
      "loss": 0.0016,
      "reward": 1.9488749504089355,
      "reward_std": 0.03878430649638176,
      "rewards/accuracy_reward": 0.7488750219345093,
      "rewards/format_reward": 1.0,
      "step": 341
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.0,
      "completion_length": 403.53125,
      "epoch": 0.004717176314809451,
      "grad_norm": 2.380589736078398,
      "kl": 0.043212890625,
      "learning_rate": 9.999450970064912e-07,
      "loss": 0.0017,
      "reward": 2.026750087738037,
      "reward_std": 0.047637972980737686,
      "rewards/accuracy_reward": 0.8267499804496765,
      "rewards/format_reward": 1.0,
      "step": 342
    },
    {
      "all_correct": 0.25,
      "all_wrong": 0.0,
      "completion_length": 396.9375,
      "epoch": 0.004730969228010648,
      "grad_norm": 2.577813399230479,
      "kl": 0.0419921875,
      "learning_rate": 9.99944775472872e-07,
      "loss": 0.0017,
      "reward": 2.017937660217285,
      "reward_std": 0.0620587095618248,
      "rewards/accuracy_reward": 0.8241875171661377,
      "rewards/format_reward": 1.0,
      "step": 343
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.0,
      "completion_length": 416.5,
      "epoch": 0.004744762141211846,
      "grad_norm": 2.0542204616794226,
      "kl": 0.0390625,
      "learning_rate": 9.999444530005378e-07,
      "loss": 0.0016,
      "reward": 2.076906204223633,
      "reward_std": 0.0624992698431015,
      "rewards/accuracy_reward": 0.8769062757492065,
      "rewards/format_reward": 1.0,
      "step": 344
    },
    {
      "all_correct": 0.75,
      "all_wrong": 0.0,
      "completion_length": 409.96875,
      "epoch": 0.004758555054413043,
      "grad_norm": 2.174883181770073,
      "kl": 0.045654296875,
      "learning_rate": 9.99944129589489e-07,
      "loss": 0.0018,
      "reward": 2.1073126792907715,
      "reward_std": 0.03396311402320862,
      "rewards/accuracy_reward": 0.9073124527931213,
      "rewards/format_reward": 1.0,
      "step": 345
    },
    {
      "all_correct": 1.0,
      "all_wrong": 0.0,
      "completion_length": 417.375,
      "epoch": 0.00477234796761424,
      "grad_norm": 1.4385540274746251,
      "kl": 0.048828125,
      "learning_rate": 9.999438052397266e-07,
      "loss": 0.0019,
      "reward": 2.12890625,
      "reward_std": 0.01819523051381111,
      "rewards/accuracy_reward": 0.9289062023162842,
      "rewards/format_reward": 1.0,
      "step": 346
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.0,
      "completion_length": 428.53125,
      "epoch": 0.0047861408808154374,
      "grad_norm": 2.0095998521417147,
      "kl": 0.0419921875,
      "learning_rate": 9.999434799512506e-07,
      "loss": 0.0017,
      "reward": 2.0420937538146973,
      "reward_std": 0.051832351833581924,
      "rewards/accuracy_reward": 0.8483437299728394,
      "rewards/format_reward": 1.0,
      "step": 347
    },
    {
      "all_correct": 0.75,
      "all_wrong": 0.0,
      "completion_length": 413.4375,
      "epoch": 0.004799933794016634,
      "grad_norm": 1.8658504636043052,
      "kl": 0.039794921875,
      "learning_rate": 9.999431537240623e-07,
      "loss": 0.0016,
      "reward": 2.1078126430511475,
      "reward_std": 0.03130917623639107,
      "rewards/accuracy_reward": 0.9078124761581421,
      "rewards/format_reward": 1.0,
      "step": 348
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.0,
      "completion_length": 418.375,
      "epoch": 0.004813726707217831,
      "grad_norm": 2.259989569398058,
      "kl": 0.0458984375,
      "learning_rate": 9.99942826558162e-07,
      "loss": 0.0018,
      "reward": 2.055500030517578,
      "reward_std": 0.034889351576566696,
      "rewards/accuracy_reward": 0.8555000424385071,
      "rewards/format_reward": 1.0,
      "step": 349
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.0,
      "completion_length": 424.0625,
      "epoch": 0.004827519620419028,
      "grad_norm": 2.6212407829420052,
      "kl": 0.048095703125,
      "learning_rate": 9.9994249845355e-07,
      "loss": 0.0019,
      "reward": 2.0044689178466797,
      "reward_std": 0.043663956224918365,
      "rewards/accuracy_reward": 0.8107187747955322,
      "rewards/format_reward": 1.0,
      "step": 350
    },
    {
      "all_correct": 0.75,
      "all_wrong": 0.0,
      "completion_length": 410.0625,
      "epoch": 0.004841312533620226,
      "grad_norm": 1.6811831343354653,
      "kl": 0.04345703125,
      "learning_rate": 9.999421694102275e-07,
      "loss": 0.0017,
      "reward": 2.1256561279296875,
      "reward_std": 0.027446215972304344,
      "rewards/accuracy_reward": 0.9256561994552612,
      "rewards/format_reward": 1.0,
      "step": 351
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.0,
      "completion_length": 439.3125,
      "epoch": 0.004855105446821423,
      "grad_norm": 2.7644306360908684,
      "kl": 0.05419921875,
      "learning_rate": 9.999418394281946e-07,
      "loss": 0.0022,
      "reward": 2.0047812461853027,
      "reward_std": 0.06064669042825699,
      "rewards/accuracy_reward": 0.8172812461853027,
      "rewards/format_reward": 1.0,
      "step": 352
    },
    {
      "all_correct": 0.25,
      "all_wrong": 0.0,
      "completion_length": 452.3125,
      "epoch": 0.00486889836002262,
      "grad_norm": 2.1979924323956057,
      "kl": 0.04638671875,
      "learning_rate": 9.999415085074523e-07,
      "loss": 0.0019,
      "reward": 1.979468822479248,
      "reward_std": 0.06920531392097473,
      "rewards/accuracy_reward": 0.7919687628746033,
      "rewards/format_reward": 1.0,
      "step": 353
    },
    {
      "all_correct": 0.25,
      "all_wrong": 0.0,
      "completion_length": 418.625,
      "epoch": 0.0048826912732238175,
      "grad_norm": 1.9030704052930756,
      "kl": 0.0380859375,
      "learning_rate": 9.99941176648001e-07,
      "loss": 0.0015,
      "reward": 1.8941562175750732,
      "reward_std": 0.050667401403188705,
      "rewards/accuracy_reward": 0.7004062533378601,
      "rewards/format_reward": 1.0,
      "step": 354
    },
    {
      "all_correct": 0.0,
      "all_wrong": 0.0,
      "completion_length": 453.40625,
      "epoch": 0.004896484186425015,
      "grad_norm": 1.9964212543638618,
      "kl": 0.046875,
      "learning_rate": 9.999408438498415e-07,
      "loss": 0.0019,
      "reward": 1.894718885421753,
      "reward_std": 0.06702862679958344,
      "rewards/accuracy_reward": 0.7134687304496765,
      "rewards/format_reward": 1.0,
      "step": 355
    },
    {
      "all_correct": 0.25,
      "all_wrong": 0.0,
      "completion_length": 443.5,
      "epoch": 0.004910277099626212,
      "grad_norm": 4.939967998037341,
      "kl": 0.0458984375,
      "learning_rate": 9.999405101129742e-07,
      "loss": 0.0018,
      "reward": 1.9465625286102295,
      "reward_std": 0.03200867399573326,
      "rewards/accuracy_reward": 0.7528125047683716,
      "rewards/format_reward": 1.0,
      "step": 356
    },
    {
      "all_correct": 0.75,
      "all_wrong": 0.0,
      "completion_length": 426.375,
      "epoch": 0.004924070012827409,
      "grad_norm": 2.501571141337024,
      "kl": 0.050048828125,
      "learning_rate": 9.999401754373999e-07,
      "loss": 0.002,
      "reward": 2.0984063148498535,
      "reward_std": 0.037641845643520355,
      "rewards/accuracy_reward": 0.8984062671661377,
      "rewards/format_reward": 1.0,
      "step": 357
    },
    {
      "all_correct": 0.0,
      "all_wrong": 0.0,
      "completion_length": 423.8125,
      "epoch": 0.0049378629260286066,
      "grad_norm": 2.255679817205866,
      "kl": 0.0498046875,
      "learning_rate": 9.999398398231195e-07,
      "loss": 0.002,
      "reward": 1.9163438081741333,
      "reward_std": 0.049837008118629456,
      "rewards/accuracy_reward": 0.7288438081741333,
      "rewards/format_reward": 1.0,
      "step": 358
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.0,
      "completion_length": 414.5625,
      "epoch": 0.004951655839229804,
      "grad_norm": 2.2703938311771057,
      "kl": 0.0439453125,
      "learning_rate": 9.999395032701328e-07,
      "loss": 0.0018,
      "reward": 1.9667813777923584,
      "reward_std": 0.04559829831123352,
      "rewards/accuracy_reward": 0.766781210899353,
      "rewards/format_reward": 1.0,
      "step": 359
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.0,
      "completion_length": 400.375,
      "epoch": 0.004965448752431001,
      "grad_norm": 1.8878858364150628,
      "kl": 0.044677734375,
      "learning_rate": 9.99939165778441e-07,
      "loss": 0.0018,
      "reward": 2.121593713760376,
      "reward_std": 0.05778314173221588,
      "rewards/accuracy_reward": 0.9403437972068787,
      "rewards/format_reward": 1.0,
      "step": 360
    },
    {
      "all_correct": 0.75,
      "all_wrong": 0.0,
      "completion_length": 425.5625,
      "epoch": 0.004979241665632198,
      "grad_norm": 2.219397048364965,
      "kl": 0.043701171875,
      "learning_rate": 9.999388273480449e-07,
      "loss": 0.0018,
      "reward": 2.0616250038146973,
      "reward_std": 0.02956487610936165,
      "rewards/accuracy_reward": 0.8616249561309814,
      "rewards/format_reward": 1.0,
      "step": 361
    },
    {
      "all_correct": 0.25,
      "all_wrong": 0.0,
      "completion_length": 415.90625,
      "epoch": 0.004993034578833396,
      "grad_norm": 2.568471466949617,
      "kl": 0.043212890625,
      "learning_rate": 9.999384879789447e-07,
      "loss": 0.0017,
      "reward": 1.998687505722046,
      "reward_std": 0.0748109221458435,
      "rewards/accuracy_reward": 0.8111875057220459,
      "rewards/format_reward": 1.0,
      "step": 362
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.0,
      "completion_length": 395.8125,
      "epoch": 0.005006827492034593,
      "grad_norm": 2.2353484256112996,
      "kl": 0.047607421875,
      "learning_rate": 9.999381476711414e-07,
      "loss": 0.0019,
      "reward": 2.039968967437744,
      "reward_std": 0.052057087421417236,
      "rewards/accuracy_reward": 0.8462187051773071,
      "rewards/format_reward": 1.0,
      "step": 363
    },
    {
      "all_correct": 0.75,
      "all_wrong": 0.0,
      "completion_length": 409.90625,
      "epoch": 0.00502062040523579,
      "grad_norm": 2.013509558162626,
      "kl": 0.044921875,
      "learning_rate": 9.999378064246355e-07,
      "loss": 0.0018,
      "reward": 2.121593713760376,
      "reward_std": 0.0262024886906147,
      "rewards/accuracy_reward": 0.9215937256813049,
      "rewards/format_reward": 1.0,
      "step": 364
    },
    {
      "all_correct": 0.75,
      "all_wrong": 0.0,
      "completion_length": 388.53125,
      "epoch": 0.0050344133184369875,
      "grad_norm": 2.4318810132785944,
      "kl": 0.04736328125,
      "learning_rate": 9.999374642394275e-07,
      "loss": 0.0019,
      "reward": 2.132781505584717,
      "reward_std": 0.040902525186538696,
      "rewards/accuracy_reward": 0.9390312433242798,
      "rewards/format_reward": 1.0,
      "step": 365
    },
    {
      "all_correct": 0.75,
      "all_wrong": 0.0,
      "completion_length": 409.40625,
      "epoch": 0.005048206231638185,
      "grad_norm": 2.2564770978193964,
      "kl": 0.038818359375,
      "learning_rate": 9.999371211155184e-07,
      "loss": 0.0016,
      "reward": 2.109250068664551,
      "reward_std": 0.038611844182014465,
      "rewards/accuracy_reward": 0.9092499613761902,
      "rewards/format_reward": 1.0,
      "step": 366
    },
    {
      "all_correct": 0.25,
      "all_wrong": 0.0,
      "completion_length": 391.5625,
      "epoch": 0.005061999144839381,
      "grad_norm": 2.1334353736703653,
      "kl": 0.04150390625,
      "learning_rate": 9.999367770529083e-07,
      "loss": 0.0017,
      "reward": 1.989531397819519,
      "reward_std": 0.041811294853687286,
      "rewards/accuracy_reward": 0.7895312309265137,
      "rewards/format_reward": 1.0,
      "step": 367
    },
    {
      "all_correct": 0.0,
      "all_wrong": 0.0,
      "completion_length": 398.1875,
      "epoch": 0.005075792058040578,
      "grad_norm": 3.16430389961693,
      "kl": 0.03955078125,
      "learning_rate": 9.999364320515982e-07,
      "loss": 0.0016,
      "reward": 2.0073437690734863,
      "reward_std": 0.04476203769445419,
      "rewards/accuracy_reward": 0.8073437213897705,
      "rewards/format_reward": 1.0,
      "step": 368
    },
    {
      "all_correct": 0.25,
      "all_wrong": 0.0,
      "completion_length": 388.375,
      "epoch": 0.005089584971241776,
      "grad_norm": 8.463507163029279,
      "kl": 0.03662109375,
      "learning_rate": 9.99936086111589e-07,
      "loss": 0.0015,
      "reward": 1.9731249809265137,
      "reward_std": 0.07198931276798248,
      "rewards/accuracy_reward": 0.7918750047683716,
      "rewards/format_reward": 1.0,
      "step": 369
    },
    {
      "all_correct": 0.25,
      "all_wrong": 0.0,
      "completion_length": 387.375,
      "epoch": 0.005103377884442973,
      "grad_norm": 2.1602753956462197,
      "kl": 0.03955078125,
      "learning_rate": 9.999357392328806e-07,
      "loss": 0.0016,
      "reward": 1.9954688549041748,
      "reward_std": 0.06441701948642731,
      "rewards/accuracy_reward": 0.8079687356948853,
      "rewards/format_reward": 1.0,
      "step": 370
    },
    {
      "all_correct": 0.75,
      "all_wrong": 0.0,
      "completion_length": 412.65625,
      "epoch": 0.00511717079764417,
      "grad_norm": 2.1322790083067895,
      "kl": 0.04296875,
      "learning_rate": 9.999353914154744e-07,
      "loss": 0.0017,
      "reward": 2.1139376163482666,
      "reward_std": 0.03282049298286438,
      "rewards/accuracy_reward": 0.9139375686645508,
      "rewards/format_reward": 1.0,
      "step": 371
    },
    {
      "all_correct": 0.0,
      "all_wrong": 0.0,
      "completion_length": 393.5,
      "epoch": 0.0051309637108453675,
      "grad_norm": 2.271743717303218,
      "kl": 0.04296875,
      "learning_rate": 9.999350426593707e-07,
      "loss": 0.0017,
      "reward": 2.0196876525878906,
      "reward_std": 0.0655524730682373,
      "rewards/accuracy_reward": 0.8384374976158142,
      "rewards/format_reward": 1.0,
      "step": 372
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.0,
      "completion_length": 397.125,
      "epoch": 0.005144756624046565,
      "grad_norm": 2.2815111538786086,
      "kl": 0.041015625,
      "learning_rate": 9.999346929645704e-07,
      "loss": 0.0016,
      "reward": 2.080031394958496,
      "reward_std": 0.03502483665943146,
      "rewards/accuracy_reward": 0.8800312876701355,
      "rewards/format_reward": 1.0,
      "step": 373
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.0,
      "completion_length": 386.84375,
      "epoch": 0.005158549537247762,
      "grad_norm": 2.2168277123145987,
      "kl": 0.0439453125,
      "learning_rate": 9.999343423310738e-07,
      "loss": 0.0018,
      "reward": 1.9021875858306885,
      "reward_std": 0.060183122754096985,
      "rewards/accuracy_reward": 0.7084375023841858,
      "rewards/format_reward": 1.0,
      "step": 374
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.0,
      "completion_length": 405.65625,
      "epoch": 0.005172342450448959,
      "grad_norm": 4.977231438046553,
      "kl": 0.040771484375,
      "learning_rate": 9.999339907588816e-07,
      "loss": 0.0016,
      "reward": 1.981562614440918,
      "reward_std": 0.04548982158303261,
      "rewards/accuracy_reward": 0.7878125309944153,
      "rewards/format_reward": 1.0,
      "step": 375
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.0,
      "completion_length": 403.0,
      "epoch": 0.0051861353636501566,
      "grad_norm": 2.0692604557532834,
      "kl": 0.0439453125,
      "learning_rate": 9.999336382479947e-07,
      "loss": 0.0018,
      "reward": 2.0643439292907715,
      "reward_std": 0.04345225915312767,
      "rewards/accuracy_reward": 0.8643437623977661,
      "rewards/format_reward": 1.0,
      "step": 376
    },
    {
      "all_correct": 0.0,
      "all_wrong": 0.0,
      "completion_length": 396.84375,
      "epoch": 0.005199928276851354,
      "grad_norm": 3.214504459599678,
      "kl": 0.04248046875,
      "learning_rate": 9.999332847984137e-07,
      "loss": 0.0017,
      "reward": 1.96303129196167,
      "reward_std": 0.07805295288562775,
      "rewards/accuracy_reward": 0.769281268119812,
      "rewards/format_reward": 1.0,
      "step": 377
    },
    {
      "all_correct": 0.25,
      "all_wrong": 0.0,
      "completion_length": 412.34375,
      "epoch": 0.005213721190052551,
      "grad_norm": 3.1058204816038035,
      "kl": 0.041015625,
      "learning_rate": 9.999329304101393e-07,
      "loss": 0.0016,
      "reward": 2.0320000648498535,
      "reward_std": 0.043971847742795944,
      "rewards/accuracy_reward": 0.8320000171661377,
      "rewards/format_reward": 1.0,
      "step": 378
    },
    {
      "all_correct": 0.25,
      "all_wrong": 0.0,
      "completion_length": 412.25,
      "epoch": 0.005227514103253748,
      "grad_norm": 11.441206366840744,
      "kl": 0.041259765625,
      "learning_rate": 9.99932575083172e-07,
      "loss": 0.0017,
      "reward": 2.026218891143799,
      "reward_std": 0.03904066979885101,
      "rewards/accuracy_reward": 0.8262187242507935,
      "rewards/format_reward": 1.0,
      "step": 379
    },
    {
      "all_correct": 0.75,
      "all_wrong": 0.0,
      "completion_length": 397.9375,
      "epoch": 0.005241307016454946,
      "grad_norm": 3.050170450819848,
      "kl": 0.040283203125,
      "learning_rate": 9.999322188175123e-07,
      "loss": 0.0016,
      "reward": 2.0570626258850098,
      "reward_std": 0.03695041313767433,
      "rewards/accuracy_reward": 0.8570624589920044,
      "rewards/format_reward": 1.0,
      "step": 380
    },
    {
      "all_correct": 0.25,
      "all_wrong": 0.0,
      "completion_length": 400.8125,
      "epoch": 0.005255099929656143,
      "grad_norm": 3.2452300025301293,
      "kl": 0.044921875,
      "learning_rate": 9.999318616131614e-07,
      "loss": 0.0018,
      "reward": 2.020031213760376,
      "reward_std": 0.04126669466495514,
      "rewards/accuracy_reward": 0.8200312852859497,
      "rewards/format_reward": 1.0,
      "step": 381
    },
    {
      "all_correct": 0.75,
      "all_wrong": 0.0,
      "completion_length": 405.40625,
      "epoch": 0.00526889284285734,
      "grad_norm": 2.584916142265051,
      "kl": 0.0419921875,
      "learning_rate": 9.999315034701196e-07,
      "loss": 0.0017,
      "reward": 2.0535311698913574,
      "reward_std": 0.022014515474438667,
      "rewards/accuracy_reward": 0.8535313010215759,
      "rewards/format_reward": 1.0,
      "step": 382
    },
    {
      "all_correct": 0.75,
      "all_wrong": 0.0,
      "completion_length": 391.5625,
      "epoch": 0.0052826857560585375,
      "grad_norm": 2.9664971784253353,
      "kl": 0.04150390625,
      "learning_rate": 9.999311443883877e-07,
      "loss": 0.0017,
      "reward": 2.0848751068115234,
      "reward_std": 0.040109068155288696,
      "rewards/accuracy_reward": 0.891124963760376,
      "rewards/format_reward": 1.0,
      "step": 383
    },
    {
      "all_correct": 0.75,
      "all_wrong": 0.0,
      "completion_length": 423.1875,
      "epoch": 0.005296478669259735,
      "grad_norm": 2.664493953814492,
      "kl": 0.03955078125,
      "learning_rate": 9.999307843679664e-07,
      "loss": 0.0016,
      "reward": 2.1409687995910645,
      "reward_std": 0.02972692996263504,
      "rewards/accuracy_reward": 0.9409687519073486,
      "rewards/format_reward": 1.0,
      "step": 384
    },
    {
      "all_correct": 0.75,
      "all_wrong": 0.0,
      "completion_length": 424.90625,
      "epoch": 0.005310271582460932,
      "grad_norm": 2.3277999910080545,
      "kl": 0.03955078125,
      "learning_rate": 9.999304234088561e-07,
      "loss": 0.0016,
      "reward": 2.0722498893737793,
      "reward_std": 0.025868508964776993,
      "rewards/accuracy_reward": 0.872249960899353,
      "rewards/format_reward": 1.0,
      "step": 385
    },
    {
      "all_correct": 1.0,
      "all_wrong": 0.0,
      "completion_length": 425.15625,
      "epoch": 0.005324064495662128,
      "grad_norm": 2.252197062196045,
      "kl": 0.046875,
      "learning_rate": 9.999300615110578e-07,
      "loss": 0.0019,
      "reward": 2.1024062633514404,
      "reward_std": 0.035415079444646835,
      "rewards/accuracy_reward": 0.9024063348770142,
      "rewards/format_reward": 1.0,
      "step": 386
    },
    {
      "all_correct": 0.25,
      "all_wrong": 0.0,
      "completion_length": 406.1875,
      "epoch": 0.005337857408863326,
      "grad_norm": 2.2820609701546597,
      "kl": 0.0419921875,
      "learning_rate": 9.99929698674572e-07,
      "loss": 0.0017,
      "reward": 2.0091562271118164,
      "reward_std": 0.05368387699127197,
      "rewards/accuracy_reward": 0.8154062628746033,
      "rewards/format_reward": 1.0,
      "step": 387
    },
    {
      "all_correct": 0.75,
      "all_wrong": 0.0,
      "completion_length": 410.28125,
      "epoch": 0.005351650322064523,
      "grad_norm": 2.182767295668779,
      "kl": 0.041259765625,
      "learning_rate": 9.999293348993995e-07,
      "loss": 0.0017,
      "reward": 2.0722813606262207,
      "reward_std": 0.02592349424958229,
      "rewards/accuracy_reward": 0.8722812533378601,
      "rewards/format_reward": 1.0,
      "step": 388
    },
    {
      "all_correct": 0.0,
      "all_wrong": 0.0,
      "completion_length": 423.5,
      "epoch": 0.00536544323526572,
      "grad_norm": 2.582314560405083,
      "kl": 0.04150390625,
      "learning_rate": 9.999289701855409e-07,
      "loss": 0.0017,
      "reward": 1.9242812395095825,
      "reward_std": 0.050751689821481705,
      "rewards/accuracy_reward": 0.7305312156677246,
      "rewards/format_reward": 1.0,
      "step": 389
    },
    {
      "all_correct": 0.75,
      "all_wrong": 0.0,
      "completion_length": 408.3125,
      "epoch": 0.0053792361484669175,
      "grad_norm": 3.4203531627122596,
      "kl": 0.04150390625,
      "learning_rate": 9.99928604532997e-07,
      "loss": 0.0017,
      "reward": 2.04087495803833,
      "reward_std": 0.06903257966041565,
      "rewards/accuracy_reward": 0.859624981880188,
      "rewards/format_reward": 1.0,
      "step": 390
    },
    {
      "all_correct": 0.25,
      "all_wrong": 0.0,
      "completion_length": 418.34375,
      "epoch": 0.005393029061668115,
      "grad_norm": 13.1145601444951,
      "kl": 0.04638671875,
      "learning_rate": 9.999282379417685e-07,
      "loss": 0.0019,
      "reward": 2.032437562942505,
      "reward_std": 0.04002109915018082,
      "rewards/accuracy_reward": 0.8324375152587891,
      "rewards/format_reward": 1.0,
      "step": 391
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.0,
      "completion_length": 431.25,
      "epoch": 0.005406821974869312,
      "grad_norm": 2.993019833017041,
      "kl": 0.05029296875,
      "learning_rate": 9.999278704118556e-07,
      "loss": 0.002,
      "reward": 2.044187545776367,
      "reward_std": 0.039664123207330704,
      "rewards/accuracy_reward": 0.8441874980926514,
      "rewards/format_reward": 1.0,
      "step": 392
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.0,
      "completion_length": 417.5625,
      "epoch": 0.005420614888070509,
      "grad_norm": 2.613621488610164,
      "kl": 0.044189453125,
      "learning_rate": 9.999275019432598e-07,
      "loss": 0.0018,
      "reward": 2.0289688110351562,
      "reward_std": 0.04123665764927864,
      "rewards/accuracy_reward": 0.8289687633514404,
      "rewards/format_reward": 1.0,
      "step": 393
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.0,
      "completion_length": 402.46875,
      "epoch": 0.005434407801271707,
      "grad_norm": 2.747261864536508,
      "kl": 0.04638671875,
      "learning_rate": 9.999271325359812e-07,
      "loss": 0.0019,
      "reward": 2.077437400817871,
      "reward_std": 0.04278936609625816,
      "rewards/accuracy_reward": 0.8836874961853027,
      "rewards/format_reward": 1.0,
      "step": 394
    },
    {
      "all_correct": 0.75,
      "all_wrong": 0.0,
      "completion_length": 428.34375,
      "epoch": 0.005448200714472904,
      "grad_norm": 2.764727325870423,
      "kl": 0.053466796875,
      "learning_rate": 9.999267621900207e-07,
      "loss": 0.0021,
      "reward": 2.0797812938690186,
      "reward_std": 0.03863271698355675,
      "rewards/accuracy_reward": 0.8797813057899475,
      "rewards/format_reward": 1.0,
      "step": 395
    },
    {
      "all_correct": 0.75,
      "all_wrong": 0.0,
      "completion_length": 427.625,
      "epoch": 0.005461993627674101,
      "grad_norm": 3.18083080677714,
      "kl": 0.048828125,
      "learning_rate": 9.999263909053789e-07,
      "loss": 0.002,
      "reward": 2.1059374809265137,
      "reward_std": 0.05786753445863724,
      "rewards/accuracy_reward": 0.9184374809265137,
      "rewards/format_reward": 1.0,
      "step": 396
    },
    {
      "all_correct": 0.25,
      "all_wrong": 0.0,
      "completion_length": 446.15625,
      "epoch": 0.005475786540875298,
      "grad_norm": 2.755189236401332,
      "kl": 0.04736328125,
      "learning_rate": 9.999260186820564e-07,
      "loss": 0.0019,
      "reward": 2.053593635559082,
      "reward_std": 0.06484928727149963,
      "rewards/accuracy_reward": 0.8723437786102295,
      "rewards/format_reward": 1.0,
      "step": 397
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.0,
      "completion_length": 406.53125,
      "epoch": 0.005489579454076496,
      "grad_norm": 2.3753921659387363,
      "kl": 0.048828125,
      "learning_rate": 9.999256455200544e-07,
      "loss": 0.002,
      "reward": 1.9841562509536743,
      "reward_std": 0.032505325973033905,
      "rewards/accuracy_reward": 0.7841562032699585,
      "rewards/format_reward": 1.0,
      "step": 398
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.0,
      "completion_length": 407.96875,
      "epoch": 0.005503372367277693,
      "grad_norm": 27.35305851641293,
      "kl": 0.04833984375,
      "learning_rate": 9.99925271419373e-07,
      "loss": 0.0019,
      "reward": 2.0696873664855957,
      "reward_std": 0.03292178362607956,
      "rewards/accuracy_reward": 0.869687557220459,
      "rewards/format_reward": 1.0,
      "step": 399
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.0,
      "completion_length": 393.6875,
      "epoch": 0.00551716528047889,
      "grad_norm": 2.285216972280409,
      "kl": 0.04931640625,
      "learning_rate": 9.999248963800133e-07,
      "loss": 0.002,
      "reward": 2.0543124675750732,
      "reward_std": 0.04364452138543129,
      "rewards/accuracy_reward": 0.8605625033378601,
      "rewards/format_reward": 1.0,
      "step": 400
    },
    {
      "all_correct": 0.75,
      "all_wrong": 0.0,
      "completion_length": 409.5625,
      "epoch": 0.0055309581936800875,
      "grad_norm": 2.3404213310167585,
      "kl": 0.0478515625,
      "learning_rate": 9.999245204019757e-07,
      "loss": 0.0019,
      "reward": 2.086937427520752,
      "reward_std": 0.0445425920188427,
      "rewards/accuracy_reward": 0.8931875228881836,
      "rewards/format_reward": 1.0,
      "step": 401
    },
    {
      "all_correct": 0.25,
      "all_wrong": 0.0,
      "completion_length": 402.8125,
      "epoch": 0.005544751106881285,
      "grad_norm": 2.484126481563818,
      "kl": 0.055908203125,
      "learning_rate": 9.999241434852613e-07,
      "loss": 0.0022,
      "reward": 1.904750108718872,
      "reward_std": 0.055736370384693146,
      "rewards/accuracy_reward": 0.7172499895095825,
      "rewards/format_reward": 1.0,
      "step": 402
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.0,
      "completion_length": 420.3125,
      "epoch": 0.005558544020082482,
      "grad_norm": 2.144216494759608,
      "kl": 0.04638671875,
      "learning_rate": 9.999237656298705e-07,
      "loss": 0.0019,
      "reward": 2.0600311756134033,
      "reward_std": 0.04742245748639107,
      "rewards/accuracy_reward": 0.866281270980835,
      "rewards/format_reward": 1.0,
      "step": 403
    },
    {
      "all_correct": 0.75,
      "all_wrong": 0.0,
      "completion_length": 412.5625,
      "epoch": 0.005572336933283678,
      "grad_norm": 2.560120333611293,
      "kl": 0.051513671875,
      "learning_rate": 9.999233868358041e-07,
      "loss": 0.0021,
      "reward": 2.1044373512268066,
      "reward_std": 0.04191218316555023,
      "rewards/accuracy_reward": 0.9044374823570251,
      "rewards/format_reward": 1.0,
      "step": 404
    },
    {
      "all_correct": 0.25,
      "all_wrong": 0.0,
      "completion_length": 430.03125,
      "epoch": 0.005586129846484876,
      "grad_norm": 2.395959713089716,
      "kl": 0.048095703125,
      "learning_rate": 9.999230071030626e-07,
      "loss": 0.0019,
      "reward": 2.0335311889648438,
      "reward_std": 0.0669226422905922,
      "rewards/accuracy_reward": 0.8460313081741333,
      "rewards/format_reward": 1.0,
      "step": 405
    },
    {
      "all_correct": 0.75,
      "all_wrong": 0.0,
      "completion_length": 422.4375,
      "epoch": 0.005599922759686073,
      "grad_norm": 2.3524984561926985,
      "kl": 0.053466796875,
      "learning_rate": 9.999226264316472e-07,
      "loss": 0.0021,
      "reward": 2.025937557220459,
      "reward_std": 0.03249998390674591,
      "rewards/accuracy_reward": 0.8259375095367432,
      "rewards/format_reward": 1.0,
      "step": 406
    },
    {
      "all_correct": 0.75,
      "all_wrong": 0.0,
      "completion_length": 396.5625,
      "epoch": 0.00561371567288727,
      "grad_norm": 2.5520112059443054,
      "kl": 0.0478515625,
      "learning_rate": 9.999222448215582e-07,
      "loss": 0.0019,
      "reward": 1.997406244277954,
      "reward_std": 0.06406331062316895,
      "rewards/accuracy_reward": 0.7974063158035278,
      "rewards/format_reward": 1.0,
      "step": 407
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.0,
      "completion_length": 409.25,
      "epoch": 0.0056275085860884675,
      "grad_norm": 2.472502912832956,
      "kl": 0.0498046875,
      "learning_rate": 9.999218622727963e-07,
      "loss": 0.002,
      "reward": 2.0297188758850098,
      "reward_std": 0.038563478738069534,
      "rewards/accuracy_reward": 0.8297187089920044,
      "rewards/format_reward": 1.0,
      "step": 408
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.0,
      "completion_length": 404.6875,
      "epoch": 0.005641301499289665,
      "grad_norm": 2.3682474499912076,
      "kl": 0.04541015625,
      "learning_rate": 9.999214787853625e-07,
      "loss": 0.0018,
      "reward": 2.0352814197540283,
      "reward_std": 0.04013541340827942,
      "rewards/accuracy_reward": 0.8477813005447388,
      "rewards/format_reward": 1.0,
      "step": 409
    },
    {
      "all_correct": 0.25,
      "all_wrong": 0.0,
      "completion_length": 392.0,
      "epoch": 0.005655094412490862,
      "grad_norm": 3.2076033592997977,
      "kl": 0.047607421875,
      "learning_rate": 9.999210943592576e-07,
      "loss": 0.0019,
      "reward": 1.9645936489105225,
      "reward_std": 0.06348051130771637,
      "rewards/accuracy_reward": 0.7708437442779541,
      "rewards/format_reward": 1.0,
      "step": 410
    },
    {
      "all_correct": 0.25,
      "all_wrong": 0.0,
      "completion_length": 412.71875,
      "epoch": 0.005668887325692059,
      "grad_norm": 2.212895591864534,
      "kl": 0.051025390625,
      "learning_rate": 9.999207089944818e-07,
      "loss": 0.002,
      "reward": 2.05790638923645,
      "reward_std": 0.06455381959676743,
      "rewards/accuracy_reward": 0.8579062223434448,
      "rewards/format_reward": 1.0,
      "step": 411
    },
    {
      "all_correct": 0.25,
      "all_wrong": 0.0,
      "completion_length": 401.9375,
      "epoch": 0.005682680238893257,
      "grad_norm": 3.206891930895078,
      "kl": 0.051513671875,
      "learning_rate": 9.999203226910361e-07,
      "loss": 0.0021,
      "reward": 1.9501874446868896,
      "reward_std": 0.05105041712522507,
      "rewards/accuracy_reward": 0.7501874566078186,
      "rewards/format_reward": 1.0,
      "step": 412
    },
    {
      "all_correct": 0.0,
      "all_wrong": 0.0,
      "completion_length": 403.125,
      "epoch": 0.005696473152094454,
      "grad_norm": 2.9394324763953406,
      "kl": 0.050048828125,
      "learning_rate": 9.999199354489215e-07,
      "loss": 0.002,
      "reward": 2.016031265258789,
      "reward_std": 0.07761611044406891,
      "rewards/accuracy_reward": 0.8285312652587891,
      "rewards/format_reward": 1.0,
      "step": 413
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.0,
      "completion_length": 404.3125,
      "epoch": 0.005710266065295651,
      "grad_norm": 2.5975645006089283,
      "kl": 0.048828125,
      "learning_rate": 9.999195472681383e-07,
      "loss": 0.002,
      "reward": 2.047968864440918,
      "reward_std": 0.038813669234514236,
      "rewards/accuracy_reward": 0.8479686975479126,
      "rewards/format_reward": 1.0,
      "step": 414
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.0,
      "completion_length": 403.4375,
      "epoch": 0.005724058978496848,
      "grad_norm": 2.988920329252644,
      "kl": 0.046142578125,
      "learning_rate": 9.999191581486875e-07,
      "loss": 0.0018,
      "reward": 2.096531391143799,
      "reward_std": 0.047278836369514465,
      "rewards/accuracy_reward": 0.9027812480926514,
      "rewards/format_reward": 1.0,
      "step": 415
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.0,
      "completion_length": 373.28125,
      "epoch": 0.005737851891698046,
      "grad_norm": 2.2908968722017558,
      "kl": 0.050048828125,
      "learning_rate": 9.999187680905697e-07,
      "loss": 0.002,
      "reward": 2.0340938568115234,
      "reward_std": 0.05671568959951401,
      "rewards/accuracy_reward": 0.8465937376022339,
      "rewards/format_reward": 1.0,
      "step": 416
    },
    {
      "all_correct": 0.75,
      "all_wrong": 0.0,
      "completion_length": 398.75,
      "epoch": 0.005751644804899243,
      "grad_norm": 2.799105331097807,
      "kl": 0.049560546875,
      "learning_rate": 9.999183770937856e-07,
      "loss": 0.002,
      "reward": 2.045562505722046,
      "reward_std": 0.04838100075721741,
      "rewards/accuracy_reward": 0.8455624580383301,
      "rewards/format_reward": 1.0,
      "step": 417
    },
    {
      "all_correct": 0.0,
      "all_wrong": 0.0,
      "completion_length": 416.90625,
      "epoch": 0.00576543771810044,
      "grad_norm": 7.657015311901752,
      "kl": 0.051513671875,
      "learning_rate": 9.99917985158336e-07,
      "loss": 0.0021,
      "reward": 1.9908125400543213,
      "reward_std": 0.0635077953338623,
      "rewards/accuracy_reward": 0.8033124804496765,
      "rewards/format_reward": 1.0,
      "step": 418
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.0,
      "completion_length": 402.8125,
      "epoch": 0.0057792306313016375,
      "grad_norm": 17.26965223929346,
      "kl": 0.04736328125,
      "learning_rate": 9.999175922842217e-07,
      "loss": 0.0019,
      "reward": 2.061718702316284,
      "reward_std": 0.05310092866420746,
      "rewards/accuracy_reward": 0.867968738079071,
      "rewards/format_reward": 1.0,
      "step": 419
    },
    {
      "all_correct": 0.25,
      "all_wrong": 0.0,
      "completion_length": 414.0,
      "epoch": 0.005793023544502835,
      "grad_norm": 2.4078115494238856,
      "kl": 0.04833984375,
      "learning_rate": 9.999171984714434e-07,
      "loss": 0.0019,
      "reward": 2.0330312252044678,
      "reward_std": 0.05156610161066055,
      "rewards/accuracy_reward": 0.8330312967300415,
      "rewards/format_reward": 1.0,
      "step": 420
    },
    {
      "all_correct": 0.0,
      "all_wrong": 0.0,
      "completion_length": 396.96875,
      "epoch": 0.005806816457704032,
      "grad_norm": 3.8663835271196727,
      "kl": 0.049072265625,
      "learning_rate": 9.99916803720002e-07,
      "loss": 0.002,
      "reward": 1.8866875171661377,
      "reward_std": 0.0813208669424057,
      "rewards/accuracy_reward": 0.7054375410079956,
      "rewards/format_reward": 1.0,
      "step": 421
    },
    {
      "all_correct": 0.25,
      "all_wrong": 0.0,
      "completion_length": 395.0625,
      "epoch": 0.005820609370905229,
      "grad_norm": 2.4911639617772825,
      "kl": 0.0498046875,
      "learning_rate": 9.999164080298977e-07,
      "loss": 0.002,
      "reward": 2.026343822479248,
      "reward_std": 0.0677998960018158,
      "rewards/accuracy_reward": 0.8450937271118164,
      "rewards/format_reward": 1.0,
      "step": 422
    },
    {
      "all_correct": 0.25,
      "all_wrong": 0.0,
      "completion_length": 417.25,
      "epoch": 0.005834402284106426,
      "grad_norm": 2.259744774870326,
      "kl": 0.048828125,
      "learning_rate": 9.999160114011318e-07,
      "loss": 0.0019,
      "reward": 1.9805938005447388,
      "reward_std": 0.050225235521793365,
      "rewards/accuracy_reward": 0.7868437170982361,
      "rewards/format_reward": 1.0,
      "step": 423
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.0,
      "completion_length": 403.28125,
      "epoch": 0.005848195197307623,
      "grad_norm": 2.55697890877962,
      "kl": 0.053955078125,
      "learning_rate": 9.999156138337048e-07,
      "loss": 0.0022,
      "reward": 2.0245938301086426,
      "reward_std": 0.06332585215568542,
      "rewards/accuracy_reward": 0.8308436870574951,
      "rewards/format_reward": 1.0,
      "step": 424
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.0,
      "completion_length": 407.625,
      "epoch": 0.00586198811050882,
      "grad_norm": 3.5955161814072785,
      "kl": 0.05859375,
      "learning_rate": 9.999152153276175e-07,
      "loss": 0.0023,
      "reward": 2.0122499465942383,
      "reward_std": 0.04555346816778183,
      "rewards/accuracy_reward": 0.812250018119812,
      "rewards/format_reward": 1.0,
      "step": 425
    },
    {
      "all_correct": 0.75,
      "all_wrong": 0.0,
      "completion_length": 414.0,
      "epoch": 0.0058757810237100175,
      "grad_norm": 3.9940446175369098,
      "kl": 0.04638671875,
      "learning_rate": 9.999148158828707e-07,
      "loss": 0.0019,
      "reward": 2.091156244277954,
      "reward_std": 0.039717383682727814,
      "rewards/accuracy_reward": 0.8911562561988831,
      "rewards/format_reward": 1.0,
      "step": 426
    },
    {
      "all_correct": 0.25,
      "all_wrong": 0.0,
      "completion_length": 409.84375,
      "epoch": 0.005889573936911215,
      "grad_norm": 1.9947022310523848,
      "kl": 0.0517578125,
      "learning_rate": 9.999144154994649e-07,
      "loss": 0.0021,
      "reward": 2.0534374713897705,
      "reward_std": 0.055101994425058365,
      "rewards/accuracy_reward": 0.8596875071525574,
      "rewards/format_reward": 1.0,
      "step": 427
    },
    {
      "all_correct": 0.75,
      "all_wrong": 0.0,
      "completion_length": 409.75,
      "epoch": 0.005903366850112412,
      "grad_norm": 2.2748465518839103,
      "kl": 0.049072265625,
      "learning_rate": 9.999140141774013e-07,
      "loss": 0.002,
      "reward": 2.068281412124634,
      "reward_std": 0.0704391598701477,
      "rewards/accuracy_reward": 0.8807811737060547,
      "rewards/format_reward": 1.0,
      "step": 428
    },
    {
      "all_correct": 0.25,
      "all_wrong": 0.0,
      "completion_length": 417.0625,
      "epoch": 0.005917159763313609,
      "grad_norm": 2.1250621120886413,
      "kl": 0.05224609375,
      "learning_rate": 9.999136119166803e-07,
      "loss": 0.0021,
      "reward": 2.05649995803833,
      "reward_std": 0.06229133531451225,
      "rewards/accuracy_reward": 0.8565000295639038,
      "rewards/format_reward": 1.0,
      "step": 429
    },
    {
      "all_correct": 0.75,
      "all_wrong": 0.0,
      "completion_length": 426.5625,
      "epoch": 0.005930952676514807,
      "grad_norm": 2.182701815111434,
      "kl": 0.0546875,
      "learning_rate": 9.999132087173027e-07,
      "loss": 0.0022,
      "reward": 2.063281297683716,
      "reward_std": 0.04120098426938057,
      "rewards/accuracy_reward": 0.8632813096046448,
      "rewards/format_reward": 1.0,
      "step": 430
    },
    {
      "all_correct": 0.75,
      "all_wrong": 0.0,
      "completion_length": 414.40625,
      "epoch": 0.005944745589716004,
      "grad_norm": 2.1766653424223033,
      "kl": 0.053955078125,
      "learning_rate": 9.999128045792693e-07,
      "loss": 0.0022,
      "reward": 2.0586562156677246,
      "reward_std": 0.047504741698503494,
      "rewards/accuracy_reward": 0.8586562871932983,
      "rewards/format_reward": 1.0,
      "step": 431
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.0,
      "completion_length": 418.6875,
      "epoch": 0.005958538502917201,
      "grad_norm": 5.4769351934029755,
      "kl": 0.0576171875,
      "learning_rate": 9.999123995025808e-07,
      "loss": 0.0023,
      "reward": 2.085343837738037,
      "reward_std": 0.045142896473407745,
      "rewards/accuracy_reward": 0.8853437900543213,
      "rewards/format_reward": 1.0,
      "step": 432
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.0,
      "completion_length": 434.9375,
      "epoch": 0.005972331416118398,
      "grad_norm": 1.4272156281185926,
      "kl": 0.04833984375,
      "learning_rate": 9.999119934872383e-07,
      "loss": 0.0019,
      "reward": 2.1294686794281006,
      "reward_std": 0.0611511692404747,
      "rewards/accuracy_reward": 0.9482187032699585,
      "rewards/format_reward": 1.0,
      "step": 433
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.0,
      "completion_length": 417.46875,
      "epoch": 0.005986124329319596,
      "grad_norm": 1.6671806587009248,
      "kl": 0.0517578125,
      "learning_rate": 9.999115865332422e-07,
      "loss": 0.0021,
      "reward": 2.0610625743865967,
      "reward_std": 0.0455532930791378,
      "rewards/accuracy_reward": 0.8735624551773071,
      "rewards/format_reward": 1.0,
      "step": 434
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.0,
      "completion_length": 414.875,
      "epoch": 0.005999917242520793,
      "grad_norm": 1.6128763317018815,
      "kl": 0.053466796875,
      "learning_rate": 9.99911178640593e-07,
      "loss": 0.0021,
      "reward": 2.0390000343322754,
      "reward_std": 0.03209829330444336,
      "rewards/accuracy_reward": 0.8452500104904175,
      "rewards/format_reward": 1.0,
      "step": 435
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.0,
      "completion_length": 442.875,
      "epoch": 0.00601371015572199,
      "grad_norm": 2.0306932014553265,
      "kl": 0.05322265625,
      "learning_rate": 9.999107698092923e-07,
      "loss": 0.0021,
      "reward": 2.022843837738037,
      "reward_std": 0.05230832099914551,
      "rewards/accuracy_reward": 0.8415937423706055,
      "rewards/format_reward": 1.0,
      "step": 436
    },
    {
      "all_correct": 0.25,
      "all_wrong": 0.0,
      "completion_length": 430.90625,
      "epoch": 0.0060275030689231875,
      "grad_norm": 2.6002569606902983,
      "kl": 0.0546875,
      "learning_rate": 9.9991036003934e-07,
      "loss": 0.0022,
      "reward": 2.075031280517578,
      "reward_std": 0.09695666283369064,
      "rewards/accuracy_reward": 0.8812812566757202,
      "rewards/format_reward": 1.0,
      "step": 437
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.0,
      "completion_length": 428.96875,
      "epoch": 0.006041295982124385,
      "grad_norm": 2.190925618443959,
      "kl": 0.0537109375,
      "learning_rate": 9.999099493307377e-07,
      "loss": 0.0021,
      "reward": 2.0072813034057617,
      "reward_std": 0.05058792978525162,
      "rewards/accuracy_reward": 0.8135312795639038,
      "rewards/format_reward": 1.0,
      "step": 438
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.0,
      "completion_length": 441.625,
      "epoch": 0.006055088895325582,
      "grad_norm": 2.43781612677234,
      "kl": 0.051513671875,
      "learning_rate": 9.999095376834854e-07,
      "loss": 0.0021,
      "reward": 1.889875054359436,
      "reward_std": 0.04314005374908447,
      "rewards/accuracy_reward": 0.689875066280365,
      "rewards/format_reward": 1.0,
      "step": 439
    },
    {
      "all_correct": 0.75,
      "all_wrong": 0.0,
      "completion_length": 419.125,
      "epoch": 0.006068881808526779,
      "grad_norm": 2.273550710187853,
      "kl": 0.0478515625,
      "learning_rate": 9.999091250975845e-07,
      "loss": 0.0019,
      "reward": 2.0492501258850098,
      "reward_std": 0.06178450956940651,
      "rewards/accuracy_reward": 0.8617500066757202,
      "rewards/format_reward": 1.0,
      "step": 440
    },
    {
      "all_correct": 0.0,
      "all_wrong": 0.0,
      "completion_length": 430.90625,
      "epoch": 0.006082674721727977,
      "grad_norm": 2.594133576549036,
      "kl": 0.05322265625,
      "learning_rate": 9.99908711573035e-07,
      "loss": 0.0021,
      "reward": 1.9610939025878906,
      "reward_std": 0.06257952749729156,
      "rewards/accuracy_reward": 0.7610937356948853,
      "rewards/format_reward": 1.0,
      "step": 441
    },
    {
      "all_correct": 0.75,
      "all_wrong": 0.0,
      "completion_length": 429.46875,
      "epoch": 0.006096467634929173,
      "grad_norm": 2.1549078081288497,
      "kl": 0.052734375,
      "learning_rate": 9.999082971098384e-07,
      "loss": 0.0021,
      "reward": 2.1158125400543213,
      "reward_std": 0.051042407751083374,
      "rewards/accuracy_reward": 0.9220625162124634,
      "rewards/format_reward": 1.0,
      "step": 442
    },
    {
      "all_correct": 0.75,
      "all_wrong": 0.0,
      "completion_length": 445.84375,
      "epoch": 0.00611026054813037,
      "grad_norm": 2.765044228336083,
      "kl": 0.052001953125,
      "learning_rate": 9.999078817079953e-07,
      "loss": 0.0021,
      "reward": 2.124281406402588,
      "reward_std": 0.04940464347600937,
      "rewards/accuracy_reward": 0.9305312633514404,
      "rewards/format_reward": 1.0,
      "step": 443
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.0,
      "completion_length": 410.15625,
      "epoch": 0.0061240534613315675,
      "grad_norm": 1.822265017896965,
      "kl": 0.048095703125,
      "learning_rate": 9.999074653675064e-07,
      "loss": 0.0019,
      "reward": 1.9833126068115234,
      "reward_std": 0.02417147159576416,
      "rewards/accuracy_reward": 0.7833124399185181,
      "rewards/format_reward": 1.0,
      "step": 444
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.0,
      "completion_length": 441.84375,
      "epoch": 0.006137846374532765,
      "grad_norm": 2.4254309036744006,
      "kl": 0.04541015625,
      "learning_rate": 9.999070480883725e-07,
      "loss": 0.0018,
      "reward": 2.0770626068115234,
      "reward_std": 0.0522807240486145,
      "rewards/accuracy_reward": 0.895812451839447,
      "rewards/format_reward": 1.0,
      "step": 445
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.0,
      "completion_length": 438.4375,
      "epoch": 0.006151639287733962,
      "grad_norm": 2.483291261014134,
      "kl": 0.051513671875,
      "learning_rate": 9.999066298705942e-07,
      "loss": 0.0021,
      "reward": 2.022125005722046,
      "reward_std": 0.03747022897005081,
      "rewards/accuracy_reward": 0.8283750414848328,
      "rewards/format_reward": 1.0,
      "step": 446
    },
    {
      "all_correct": 0.75,
      "all_wrong": 0.0,
      "completion_length": 426.4375,
      "epoch": 0.006165432200935159,
      "grad_norm": 2.1841883574910206,
      "kl": 0.050537109375,
      "learning_rate": 9.999062107141727e-07,
      "loss": 0.002,
      "reward": 2.1225314140319824,
      "reward_std": 0.03400640934705734,
      "rewards/accuracy_reward": 0.922531247138977,
      "rewards/format_reward": 1.0,
      "step": 447
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.0,
      "completion_length": 423.78125,
      "epoch": 0.006179225114136357,
      "grad_norm": 2.078285857002367,
      "kl": 0.048583984375,
      "learning_rate": 9.999057906191084e-07,
      "loss": 0.0019,
      "reward": 2.0131564140319824,
      "reward_std": 0.1357610672712326,
      "rewards/accuracy_reward": 0.8506562113761902,
      "rewards/format_reward": 0.96875,
      "step": 448
    },
    {
      "all_correct": 0.25,
      "all_wrong": 0.0,
      "completion_length": 438.3125,
      "epoch": 0.006193018027337554,
      "grad_norm": 2.044171548114657,
      "kl": 0.053955078125,
      "learning_rate": 9.999053695854023e-07,
      "loss": 0.0022,
      "reward": 2.037374973297119,
      "reward_std": 0.05236751586198807,
      "rewards/accuracy_reward": 0.8498750329017639,
      "rewards/format_reward": 1.0,
      "step": 449
    },
    {
      "all_correct": 0.25,
      "all_wrong": 0.0,
      "completion_length": 420.53125,
      "epoch": 0.006206810940538751,
      "grad_norm": 2.060034989431705,
      "kl": 0.0517578125,
      "learning_rate": 9.999049476130551e-07,
      "loss": 0.0021,
      "reward": 2.0882186889648438,
      "reward_std": 0.05290935933589935,
      "rewards/accuracy_reward": 0.8944686651229858,
      "rewards/format_reward": 1.0,
      "step": 450
    },
    {
      "all_correct": 1.0,
      "all_wrong": 0.0,
      "completion_length": 434.90625,
      "epoch": 0.006220603853739948,
      "grad_norm": 2.3513103702450238,
      "kl": 0.04833984375,
      "learning_rate": 9.999045247020678e-07,
      "loss": 0.0019,
      "reward": 2.1145312786102295,
      "reward_std": 0.041993848979473114,
      "rewards/accuracy_reward": 0.9145312905311584,
      "rewards/format_reward": 1.0,
      "step": 451
    },
    {
      "all_correct": 0.25,
      "all_wrong": 0.0,
      "completion_length": 407.4375,
      "epoch": 0.006234396766941146,
      "grad_norm": 54.847513188480065,
      "kl": 0.05078125,
      "learning_rate": 9.999041008524406e-07,
      "loss": 0.002,
      "reward": 2.066093921661377,
      "reward_std": 0.053901515901088715,
      "rewards/accuracy_reward": 0.8660937547683716,
      "rewards/format_reward": 1.0,
      "step": 452
    },
    {
      "all_correct": 0.75,
      "all_wrong": 0.0,
      "completion_length": 411.46875,
      "epoch": 0.006248189680142343,
      "grad_norm": 2.132592722549295,
      "kl": 0.04736328125,
      "learning_rate": 9.999036760641752e-07,
      "loss": 0.0019,
      "reward": 2.060699939727783,
      "reward_std": 0.041433461010456085,
      "rewards/accuracy_reward": 0.8669500350952148,
      "rewards/format_reward": 1.0,
      "step": 453
    },
    {
      "all_correct": 0.25,
      "all_wrong": 0.0,
      "completion_length": 410.90625,
      "epoch": 0.00626198259334354,
      "grad_norm": 2.4284293083629755,
      "kl": 0.05126953125,
      "learning_rate": 9.999032503372715e-07,
      "loss": 0.002,
      "reward": 1.9245938062667847,
      "reward_std": 0.06403053551912308,
      "rewards/accuracy_reward": 0.7245937585830688,
      "rewards/format_reward": 1.0,
      "step": 454
    },
    {
      "all_correct": 1.0,
      "all_wrong": 0.0,
      "completion_length": 416.6875,
      "epoch": 0.0062757755065447375,
      "grad_norm": 2.3561161361147223,
      "kl": 0.0478515625,
      "learning_rate": 9.99902823671731e-07,
      "loss": 0.0019,
      "reward": 2.154250144958496,
      "reward_std": 0.029831662774086,
      "rewards/accuracy_reward": 0.9542500376701355,
      "rewards/format_reward": 1.0,
      "step": 455
    },
    {
      "all_correct": 0.75,
      "all_wrong": 0.0,
      "completion_length": 418.5625,
      "epoch": 0.006289568419745935,
      "grad_norm": 1.5929271765042643,
      "kl": 0.052978515625,
      "learning_rate": 9.99902396067554e-07,
      "loss": 0.0021,
      "reward": 2.1213748455047607,
      "reward_std": 0.020033225417137146,
      "rewards/accuracy_reward": 0.921375036239624,
      "rewards/format_reward": 1.0,
      "step": 456
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.0,
      "completion_length": 413.40625,
      "epoch": 0.006303361332947132,
      "grad_norm": 1.9981365615948745,
      "kl": 0.046630859375,
      "learning_rate": 9.999019675247416e-07,
      "loss": 0.0019,
      "reward": 2.0269999504089355,
      "reward_std": 0.02967972122132778,
      "rewards/accuracy_reward": 0.8270000219345093,
      "rewards/format_reward": 1.0,
      "step": 457
    },
    {
      "all_correct": 1.0,
      "all_wrong": 0.0,
      "completion_length": 410.15625,
      "epoch": 0.006317154246148329,
      "grad_norm": 4.794670641556352,
      "kl": 0.04931640625,
      "learning_rate": 9.999015380432946e-07,
      "loss": 0.002,
      "reward": 2.1294374465942383,
      "reward_std": 0.03062836267054081,
      "rewards/accuracy_reward": 0.929437518119812,
      "rewards/format_reward": 1.0,
      "step": 458
    },
    {
      "all_correct": 0.25,
      "all_wrong": 0.0,
      "completion_length": 433.09375,
      "epoch": 0.006330947159349527,
      "grad_norm": 7.432220349255496,
      "kl": 0.0556640625,
      "learning_rate": 9.999011076232136e-07,
      "loss": 0.0022,
      "reward": 2.0531561374664307,
      "reward_std": 0.05647537112236023,
      "rewards/accuracy_reward": 0.8656562566757202,
      "rewards/format_reward": 1.0,
      "step": 459
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.0,
      "completion_length": 414.46875,
      "epoch": 0.006344740072550724,
      "grad_norm": 2.945291083078629,
      "kl": 0.0546875,
      "learning_rate": 9.999006762644997e-07,
      "loss": 0.0022,
      "reward": 1.9413437843322754,
      "reward_std": 0.053651705384254456,
      "rewards/accuracy_reward": 0.7475937604904175,
      "rewards/format_reward": 1.0,
      "step": 460
    },
    {
      "all_correct": 0.75,
      "all_wrong": 0.0,
      "completion_length": 402.03125,
      "epoch": 0.00635853298575192,
      "grad_norm": 2.1417502172964897,
      "kl": 0.048828125,
      "learning_rate": 9.999002439671533e-07,
      "loss": 0.0019,
      "reward": 2.0660624504089355,
      "reward_std": 0.04758208990097046,
      "rewards/accuracy_reward": 0.8660625219345093,
      "rewards/format_reward": 1.0,
      "step": 461
    },
    {
      "all_correct": 1.0,
      "all_wrong": 0.0,
      "completion_length": 406.09375,
      "epoch": 0.0063723258989531175,
      "grad_norm": 3.6130355249633133,
      "kl": 0.05029296875,
      "learning_rate": 9.998998107311757e-07,
      "loss": 0.002,
      "reward": 2.1443750858306885,
      "reward_std": 0.036351725459098816,
      "rewards/accuracy_reward": 0.9443750381469727,
      "rewards/format_reward": 1.0,
      "step": 462
    },
    {
      "all_correct": 0.25,
      "all_wrong": 0.0,
      "completion_length": 411.125,
      "epoch": 0.006386118812154315,
      "grad_norm": 10.246810969712243,
      "kl": 0.052734375,
      "learning_rate": 9.998993765565672e-07,
      "loss": 0.0021,
      "reward": 1.9857499599456787,
      "reward_std": 0.05506417155265808,
      "rewards/accuracy_reward": 0.7920000553131104,
      "rewards/format_reward": 1.0,
      "step": 463
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.0,
      "completion_length": 413.53125,
      "epoch": 0.006399911725355512,
      "grad_norm": 2.820966804537115,
      "kl": 0.05029296875,
      "learning_rate": 9.99898941443329e-07,
      "loss": 0.002,
      "reward": 2.0905938148498535,
      "reward_std": 0.05303804576396942,
      "rewards/accuracy_reward": 0.8968437910079956,
      "rewards/format_reward": 1.0,
      "step": 464
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.0,
      "completion_length": 411.6875,
      "epoch": 0.006413704638556709,
      "grad_norm": 2.5974919895731445,
      "kl": 0.0458984375,
      "learning_rate": 9.998985053914617e-07,
      "loss": 0.0018,
      "reward": 2.091843843460083,
      "reward_std": 0.027569973841309547,
      "rewards/accuracy_reward": 0.8918437957763672,
      "rewards/format_reward": 1.0,
      "step": 465
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.0,
      "completion_length": 397.5,
      "epoch": 0.006427497551757907,
      "grad_norm": 6.75225842098542,
      "kl": 0.05517578125,
      "learning_rate": 9.998980684009663e-07,
      "loss": 0.0022,
      "reward": 2.0234999656677246,
      "reward_std": 0.041552476584911346,
      "rewards/accuracy_reward": 0.8235000371932983,
      "rewards/format_reward": 1.0,
      "step": 466
    },
    {
      "all_correct": 1.0,
      "all_wrong": 0.0,
      "completion_length": 406.0,
      "epoch": 0.006441290464959104,
      "grad_norm": 1.9156503328528103,
      "kl": 0.046142578125,
      "learning_rate": 9.998976304718435e-07,
      "loss": 0.0018,
      "reward": 2.1222500801086426,
      "reward_std": 0.05393138527870178,
      "rewards/accuracy_reward": 0.9284999370574951,
      "rewards/format_reward": 1.0,
      "step": 467
    },
    {
      "all_correct": 0.25,
      "all_wrong": 0.0,
      "completion_length": 399.53125,
      "epoch": 0.006455083378160301,
      "grad_norm": 2.5002545029316927,
      "kl": 0.04931640625,
      "learning_rate": 9.998971916040944e-07,
      "loss": 0.002,
      "reward": 2.0030627250671387,
      "reward_std": 0.05505741760134697,
      "rewards/accuracy_reward": 0.8030624985694885,
      "rewards/format_reward": 1.0,
      "step": 468
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.0,
      "completion_length": 409.96875,
      "epoch": 0.0064688762913614984,
      "grad_norm": 1.9322153099956494,
      "kl": 0.0478515625,
      "learning_rate": 9.998967517977195e-07,
      "loss": 0.0019,
      "reward": 2.015937566757202,
      "reward_std": 0.030973389744758606,
      "rewards/accuracy_reward": 0.8159375786781311,
      "rewards/format_reward": 1.0,
      "step": 469
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.0,
      "completion_length": 388.40625,
      "epoch": 0.006482669204562696,
      "grad_norm": 15.973614871242363,
      "kl": 0.046875,
      "learning_rate": 9.998963110527196e-07,
      "loss": 0.0019,
      "reward": 2.044156312942505,
      "reward_std": 0.07589149475097656,
      "rewards/accuracy_reward": 0.8504062294960022,
      "rewards/format_reward": 1.0,
      "step": 470
    },
    {
      "all_correct": 0.0,
      "all_wrong": 0.0,
      "completion_length": 383.6875,
      "epoch": 0.006496462117763893,
      "grad_norm": 2.4809930255128667,
      "kl": 0.04833984375,
      "learning_rate": 9.998958693690956e-07,
      "loss": 0.0019,
      "reward": 2.0883126258850098,
      "reward_std": 0.08860978484153748,
      "rewards/accuracy_reward": 0.913312554359436,
      "rewards/format_reward": 1.0,
      "step": 471
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.0,
      "completion_length": 402.71875,
      "epoch": 0.00651025503096509,
      "grad_norm": 2.4286191548195295,
      "kl": 0.04736328125,
      "learning_rate": 9.998954267468485e-07,
      "loss": 0.0019,
      "reward": 2.0695624351501465,
      "reward_std": 0.04460033029317856,
      "rewards/accuracy_reward": 0.8695625066757202,
      "rewards/format_reward": 1.0,
      "step": 472
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.0,
      "completion_length": 398.25,
      "epoch": 0.0065240479441662875,
      "grad_norm": 2.00547489336181,
      "kl": 0.047119140625,
      "learning_rate": 9.998949831859789e-07,
      "loss": 0.0019,
      "reward": 2.0764999389648438,
      "reward_std": 0.04215770214796066,
      "rewards/accuracy_reward": 0.8827499151229858,
      "rewards/format_reward": 1.0,
      "step": 473
    },
    {
      "all_correct": 0.75,
      "all_wrong": 0.0,
      "completion_length": 408.15625,
      "epoch": 0.006537840857367485,
      "grad_norm": 1.83465881304083,
      "kl": 0.048095703125,
      "learning_rate": 9.998945386864876e-07,
      "loss": 0.0019,
      "reward": 2.137765407562256,
      "reward_std": 0.04565926268696785,
      "rewards/accuracy_reward": 0.9377655982971191,
      "rewards/format_reward": 1.0,
      "step": 474
    },
    {
      "all_correct": 0.0,
      "all_wrong": 0.0,
      "completion_length": 415.375,
      "epoch": 0.006551633770568682,
      "grad_norm": 2.3609545535445804,
      "kl": 0.047119140625,
      "learning_rate": 9.998940932483757e-07,
      "loss": 0.0019,
      "reward": 1.948468804359436,
      "reward_std": 0.09645549207925797,
      "rewards/accuracy_reward": 0.7672187089920044,
      "rewards/format_reward": 1.0,
      "step": 475
    },
    {
      "all_correct": 0.25,
      "all_wrong": 0.0,
      "completion_length": 417.5625,
      "epoch": 0.006565426683769879,
      "grad_norm": 3.0135915486887495,
      "kl": 0.049072265625,
      "learning_rate": 9.99893646871644e-07,
      "loss": 0.002,
      "reward": 1.86328125,
      "reward_std": 0.05664583295583725,
      "rewards/accuracy_reward": 0.663281261920929,
      "rewards/format_reward": 1.0,
      "step": 476
    },
    {
      "all_correct": 1.0,
      "all_wrong": 0.0,
      "completion_length": 421.71875,
      "epoch": 0.006579219596971077,
      "grad_norm": 2.192085318113336,
      "kl": 0.050048828125,
      "learning_rate": 9.99893199556293e-07,
      "loss": 0.002,
      "reward": 2.126999855041504,
      "reward_std": 0.029108930379152298,
      "rewards/accuracy_reward": 0.9269999861717224,
      "rewards/format_reward": 1.0,
      "step": 477
    },
    {
      "all_correct": 0.75,
      "all_wrong": 0.0,
      "completion_length": 406.375,
      "epoch": 0.006593012510172274,
      "grad_norm": 2.421470546729685,
      "kl": 0.04345703125,
      "learning_rate": 9.99892751302324e-07,
      "loss": 0.0017,
      "reward": 2.1214687824249268,
      "reward_std": 0.05782489478588104,
      "rewards/accuracy_reward": 0.9214688539505005,
      "rewards/format_reward": 1.0,
      "step": 478
    },
    {
      "all_correct": 0.0,
      "all_wrong": 0.0,
      "completion_length": 394.46875,
      "epoch": 0.00660680542337347,
      "grad_norm": 2.366607752823309,
      "kl": 0.05419921875,
      "learning_rate": 9.998923021097375e-07,
      "loss": 0.0022,
      "reward": 2.006187677383423,
      "reward_std": 0.052849989384412766,
      "rewards/accuracy_reward": 0.8186875581741333,
      "rewards/format_reward": 1.0,
      "step": 479
    },
    {
      "all_correct": 0.75,
      "all_wrong": 0.0,
      "completion_length": 399.9375,
      "epoch": 0.0066205983365746676,
      "grad_norm": 2.112964470212882,
      "kl": 0.050537109375,
      "learning_rate": 9.998918519785347e-07,
      "loss": 0.002,
      "reward": 2.0928125381469727,
      "reward_std": 0.031509097665548325,
      "rewards/accuracy_reward": 0.8928124308586121,
      "rewards/format_reward": 1.0,
      "step": 480
    },
    {
      "all_correct": 0.25,
      "all_wrong": 0.0,
      "completion_length": 421.25,
      "epoch": 0.006634391249775865,
      "grad_norm": 2.353844124839015,
      "kl": 0.04638671875,
      "learning_rate": 9.99891400908716e-07,
      "loss": 0.0018,
      "reward": 1.9729686975479126,
      "reward_std": 0.0887097418308258,
      "rewards/accuracy_reward": 0.7917186617851257,
      "rewards/format_reward": 1.0,
      "step": 481
    },
    {
      "all_correct": 0.25,
      "all_wrong": 0.0,
      "completion_length": 428.4375,
      "epoch": 0.006648184162977062,
      "grad_norm": 2.3856310335426376,
      "kl": 0.047607421875,
      "learning_rate": 9.998909489002825e-07,
      "loss": 0.0019,
      "reward": 2.118406295776367,
      "reward_std": 0.059468068182468414,
      "rewards/accuracy_reward": 0.9309061765670776,
      "rewards/format_reward": 1.0,
      "step": 482
    },
    {
      "all_correct": 0.0,
      "all_wrong": 0.0,
      "completion_length": 427.4375,
      "epoch": 0.006661977076178259,
      "grad_norm": 2.4610388604462736,
      "kl": 0.0439453125,
      "learning_rate": 9.99890495953235e-07,
      "loss": 0.0018,
      "reward": 1.9573438167572021,
      "reward_std": 0.08177557587623596,
      "rewards/accuracy_reward": 0.7635937929153442,
      "rewards/format_reward": 1.0,
      "step": 483
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.0,
      "completion_length": 397.28125,
      "epoch": 0.006675769989379457,
      "grad_norm": 2.6556486767346716,
      "kl": 0.04736328125,
      "learning_rate": 9.998900420675744e-07,
      "loss": 0.0019,
      "reward": 2.0717501640319824,
      "reward_std": 0.038730934262275696,
      "rewards/accuracy_reward": 0.8779999017715454,
      "rewards/format_reward": 1.0,
      "step": 484
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.0,
      "completion_length": 414.65625,
      "epoch": 0.006689562902580654,
      "grad_norm": 1.2580648206517744,
      "kl": 0.04443359375,
      "learning_rate": 9.998895872433013e-07,
      "loss": 0.0018,
      "reward": 2.110187530517578,
      "reward_std": 0.031248370185494423,
      "rewards/accuracy_reward": 0.9226875305175781,
      "rewards/format_reward": 1.0,
      "step": 485
    },
    {
      "all_correct": 0.75,
      "all_wrong": 0.0,
      "completion_length": 420.09375,
      "epoch": 0.006703355815781851,
      "grad_norm": 2.2712597437977213,
      "kl": 0.046142578125,
      "learning_rate": 9.99889131480417e-07,
      "loss": 0.0018,
      "reward": 2.094531297683716,
      "reward_std": 0.030032359063625336,
      "rewards/accuracy_reward": 0.89453125,
      "rewards/format_reward": 1.0,
      "step": 486
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.0,
      "completion_length": 414.40625,
      "epoch": 0.0067171487289830484,
      "grad_norm": 5.188655484010513,
      "kl": 0.04296875,
      "learning_rate": 9.998886747789221e-07,
      "loss": 0.0017,
      "reward": 2.039187431335449,
      "reward_std": 0.05987890064716339,
      "rewards/accuracy_reward": 0.839187502861023,
      "rewards/format_reward": 1.0,
      "step": 487
    },
    {
      "all_correct": 0.75,
      "all_wrong": 0.0,
      "completion_length": 403.21875,
      "epoch": 0.006730941642184246,
      "grad_norm": 1.7779537936075132,
      "kl": 0.04541015625,
      "learning_rate": 9.998882171388174e-07,
      "loss": 0.0018,
      "reward": 2.005812406539917,
      "reward_std": 0.02743227779865265,
      "rewards/accuracy_reward": 0.8058124780654907,
      "rewards/format_reward": 1.0,
      "step": 488
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.0,
      "completion_length": 415.59375,
      "epoch": 0.006744734555385443,
      "grad_norm": 2.0033902325526656,
      "kl": 0.048095703125,
      "learning_rate": 9.998877585601037e-07,
      "loss": 0.0019,
      "reward": 2.11118745803833,
      "reward_std": 0.06951781362295151,
      "rewards/accuracy_reward": 0.9236875176429749,
      "rewards/format_reward": 1.0,
      "step": 489
    },
    {
      "all_correct": 0.25,
      "all_wrong": 0.0,
      "completion_length": 414.90625,
      "epoch": 0.00675852746858664,
      "grad_norm": 2.103699142971979,
      "kl": 0.0478515625,
      "learning_rate": 9.998872990427823e-07,
      "loss": 0.0019,
      "reward": 2.0332188606262207,
      "reward_std": 0.043987613171339035,
      "rewards/accuracy_reward": 0.8332188129425049,
      "rewards/format_reward": 1.0,
      "step": 490
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.0,
      "completion_length": 429.875,
      "epoch": 0.0067723203817878375,
      "grad_norm": 2.35698790048424,
      "kl": 0.04541015625,
      "learning_rate": 9.998868385868535e-07,
      "loss": 0.0018,
      "reward": 2.0375938415527344,
      "reward_std": 0.04837675765156746,
      "rewards/accuracy_reward": 0.8375937342643738,
      "rewards/format_reward": 1.0,
      "step": 491
    },
    {
      "all_correct": 0.75,
      "all_wrong": 0.0,
      "completion_length": 402.6875,
      "epoch": 0.006786113294989035,
      "grad_norm": 2.1787245823489956,
      "kl": 0.0537109375,
      "learning_rate": 9.998863771923186e-07,
      "loss": 0.0021,
      "reward": 2.114500045776367,
      "reward_std": 0.02211102284491062,
      "rewards/accuracy_reward": 0.9144999980926514,
      "rewards/format_reward": 1.0,
      "step": 492
    },
    {
      "all_correct": 0.75,
      "all_wrong": 0.0,
      "completion_length": 391.09375,
      "epoch": 0.006799906208190232,
      "grad_norm": 2.5024222784834946,
      "kl": 0.04638671875,
      "learning_rate": 9.998859148591782e-07,
      "loss": 0.0019,
      "reward": 2.083078384399414,
      "reward_std": 0.03898228704929352,
      "rewards/accuracy_reward": 0.8830780982971191,
      "rewards/format_reward": 1.0,
      "step": 493
    },
    {
      "all_correct": 0.75,
      "all_wrong": 0.0,
      "completion_length": 410.75,
      "epoch": 0.006813699121391429,
      "grad_norm": 2.0398652968046016,
      "kl": 0.048828125,
      "learning_rate": 9.998854515874332e-07,
      "loss": 0.0019,
      "reward": 2.024218797683716,
      "reward_std": 0.039963144809007645,
      "rewards/accuracy_reward": 0.82421875,
      "rewards/format_reward": 1.0,
      "step": 494
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.0,
      "completion_length": 388.71875,
      "epoch": 0.006827492034592627,
      "grad_norm": 3.065915206828661,
      "kl": 0.046630859375,
      "learning_rate": 9.998849873770847e-07,
      "loss": 0.0019,
      "reward": 1.9901562929153442,
      "reward_std": 0.04621211811900139,
      "rewards/accuracy_reward": 0.7901562452316284,
      "rewards/format_reward": 1.0,
      "step": 495
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.0,
      "completion_length": 400.28125,
      "epoch": 0.006841284947793824,
      "grad_norm": 7.75104781114931,
      "kl": 0.0419921875,
      "learning_rate": 9.998845222281332e-07,
      "loss": 0.0017,
      "reward": 2.046968698501587,
      "reward_std": 0.033911436796188354,
      "rewards/accuracy_reward": 0.8469687700271606,
      "rewards/format_reward": 1.0,
      "step": 496
    },
    {
      "all_correct": 0.75,
      "all_wrong": 0.0,
      "completion_length": 392.8125,
      "epoch": 0.006855077860995021,
      "grad_norm": 2.496730990316503,
      "kl": 0.05029296875,
      "learning_rate": 9.998840561405799e-07,
      "loss": 0.002,
      "reward": 2.03920316696167,
      "reward_std": 0.04264325648546219,
      "rewards/accuracy_reward": 0.8392031192779541,
      "rewards/format_reward": 1.0,
      "step": 497
    },
    {
      "all_correct": 0.75,
      "all_wrong": 0.0,
      "completion_length": 425.0,
      "epoch": 0.0068688707741962176,
      "grad_norm": 1.8806490360063974,
      "kl": 0.047119140625,
      "learning_rate": 9.998835891144255e-07,
      "loss": 0.0019,
      "reward": 2.025240659713745,
      "reward_std": 0.017883004620671272,
      "rewards/accuracy_reward": 0.8252406120300293,
      "rewards/format_reward": 1.0,
      "step": 498
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.0,
      "completion_length": 392.6875,
      "epoch": 0.006882663687397415,
      "grad_norm": 2.891641914101987,
      "kl": 0.04638671875,
      "learning_rate": 9.99883121149671e-07,
      "loss": 0.0019,
      "reward": 2.1169686317443848,
      "reward_std": 0.058275140821933746,
      "rewards/accuracy_reward": 0.9232187271118164,
      "rewards/format_reward": 1.0,
      "step": 499
    },
    {
      "all_correct": 0.25,
      "all_wrong": 0.0,
      "completion_length": 395.9375,
      "epoch": 0.006896456600598612,
      "grad_norm": 2.022715313742651,
      "kl": 0.0380859375,
      "learning_rate": 9.99882652246317e-07,
      "loss": 0.0015,
      "reward": 1.9176876544952393,
      "reward_std": 0.04783179238438606,
      "rewards/accuracy_reward": 0.7176874876022339,
      "rewards/format_reward": 1.0,
      "step": 500
    },
    {
      "all_correct": 0.25,
      "all_wrong": 0.0,
      "completion_length": 386.875,
      "epoch": 0.006910249513799809,
      "grad_norm": 2.396821625155436,
      "kl": 0.0478515625,
      "learning_rate": 9.998821824043647e-07,
      "loss": 0.0019,
      "reward": 2.0275156497955322,
      "reward_std": 0.0573999360203743,
      "rewards/accuracy_reward": 0.8400155901908875,
      "rewards/format_reward": 1.0,
      "step": 501
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.0,
      "completion_length": 410.0,
      "epoch": 0.006924042427001007,
      "grad_norm": 2.548935980002161,
      "kl": 0.045166015625,
      "learning_rate": 9.99881711623815e-07,
      "loss": 0.0018,
      "reward": 2.0393593311309814,
      "reward_std": 0.06705594062805176,
      "rewards/accuracy_reward": 0.8456093668937683,
      "rewards/format_reward": 1.0,
      "step": 502
    },
    {
      "all_correct": 0.25,
      "all_wrong": 0.0,
      "completion_length": 407.03125,
      "epoch": 0.006937835340202204,
      "grad_norm": 2.644585106614417,
      "kl": 0.048095703125,
      "learning_rate": 9.998812399046686e-07,
      "loss": 0.0019,
      "reward": 1.9927188158035278,
      "reward_std": 0.03509826958179474,
      "rewards/accuracy_reward": 0.7927187085151672,
      "rewards/format_reward": 1.0,
      "step": 503
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.0,
      "completion_length": 403.875,
      "epoch": 0.006951628253403401,
      "grad_norm": 2.228992746332528,
      "kl": 0.0439453125,
      "learning_rate": 9.998807672469264e-07,
      "loss": 0.0018,
      "reward": 2.08760929107666,
      "reward_std": 0.04669293761253357,
      "rewards/accuracy_reward": 0.8876093626022339,
      "rewards/format_reward": 1.0,
      "step": 504
    },
    {
      "all_correct": 0.25,
      "all_wrong": 0.0,
      "completion_length": 412.375,
      "epoch": 0.0069654211666045985,
      "grad_norm": 2.3573872042973876,
      "kl": 0.044189453125,
      "learning_rate": 9.998802936505892e-07,
      "loss": 0.0018,
      "reward": 2.047621965408325,
      "reward_std": 0.045699793845415115,
      "rewards/accuracy_reward": 0.8538718223571777,
      "rewards/format_reward": 1.0,
      "step": 505
    },
    {
      "all_correct": 0.75,
      "all_wrong": 0.0,
      "completion_length": 405.25,
      "epoch": 0.006979214079805796,
      "grad_norm": 21.711347732871292,
      "kl": 0.05078125,
      "learning_rate": 9.99879819115658e-07,
      "loss": 0.002,
      "reward": 2.074406385421753,
      "reward_std": 0.0406007245182991,
      "rewards/accuracy_reward": 0.8744062781333923,
      "rewards/format_reward": 1.0,
      "step": 506
    },
    {
      "all_correct": 0.75,
      "all_wrong": 0.0,
      "completion_length": 397.84375,
      "epoch": 0.006993006993006993,
      "grad_norm": 7.091894304132117,
      "kl": 0.04296875,
      "learning_rate": 9.99879343642134e-07,
      "loss": 0.0017,
      "reward": 2.1401562690734863,
      "reward_std": 0.06220386177301407,
      "rewards/accuracy_reward": 0.9589062333106995,
      "rewards/format_reward": 1.0,
      "step": 507
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.0,
      "completion_length": 395.625,
      "epoch": 0.00700679990620819,
      "grad_norm": 3.450136063015016,
      "kl": 0.0439453125,
      "learning_rate": 9.998788672300176e-07,
      "loss": 0.0018,
      "reward": 2.0445780754089355,
      "reward_std": 0.029390225186944008,
      "rewards/accuracy_reward": 0.8508281707763672,
      "rewards/format_reward": 1.0,
      "step": 508
    },
    {
      "all_correct": 0.25,
      "all_wrong": 0.0,
      "completion_length": 410.40625,
      "epoch": 0.0070205928194093875,
      "grad_norm": 2.7480832171875726,
      "kl": 0.04541015625,
      "learning_rate": 9.9987838987931e-07,
      "loss": 0.0018,
      "reward": 2.0546250343322754,
      "reward_std": 0.05259440466761589,
      "rewards/accuracy_reward": 0.8608750104904175,
      "rewards/format_reward": 1.0,
      "step": 509
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.0,
      "completion_length": 409.125,
      "epoch": 0.007034385732610585,
      "grad_norm": 2.3446414048484945,
      "kl": 0.050048828125,
      "learning_rate": 9.998779115900118e-07,
      "loss": 0.002,
      "reward": 1.953874945640564,
      "reward_std": 0.053261689841747284,
      "rewards/accuracy_reward": 0.7538750171661377,
      "rewards/format_reward": 1.0,
      "step": 510
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.0,
      "completion_length": 401.71875,
      "epoch": 0.007048178645811782,
      "grad_norm": 3.770161456594712,
      "kl": 0.048828125,
      "learning_rate": 9.998774323621242e-07,
      "loss": 0.002,
      "reward": 2.022125244140625,
      "reward_std": 0.07293341308832169,
      "rewards/accuracy_reward": 0.8221249580383301,
      "rewards/format_reward": 1.0,
      "step": 511
    },
    {
      "all_correct": 0.75,
      "all_wrong": 0.0,
      "completion_length": 407.65625,
      "epoch": 0.007061971559012979,
      "grad_norm": 2.2196594447780655,
      "kl": 0.049560546875,
      "learning_rate": 9.998769521956479e-07,
      "loss": 0.002,
      "reward": 2.0625157356262207,
      "reward_std": 0.02569575235247612,
      "rewards/accuracy_reward": 0.8625156283378601,
      "rewards/format_reward": 1.0,
      "step": 512
    },
    {
      "all_correct": 0.25,
      "all_wrong": 0.0,
      "completion_length": 427.0,
      "epoch": 0.007075764472214177,
      "grad_norm": 3.0104084161712774,
      "kl": 0.047607421875,
      "learning_rate": 9.99876471090584e-07,
      "loss": 0.0019,
      "reward": 2.020812511444092,
      "reward_std": 0.07906971871852875,
      "rewards/accuracy_reward": 0.8208125233650208,
      "rewards/format_reward": 1.0,
      "step": 513
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.0,
      "completion_length": 405.0,
      "epoch": 0.007089557385415374,
      "grad_norm": 1.7182882745387882,
      "kl": 0.04541015625,
      "learning_rate": 9.998759890469332e-07,
      "loss": 0.0018,
      "reward": 2.116781234741211,
      "reward_std": 0.04438205435872078,
      "rewards/accuracy_reward": 0.9292812347412109,
      "rewards/format_reward": 1.0,
      "step": 514
    },
    {
      "all_correct": 1.0,
      "all_wrong": 0.0,
      "completion_length": 419.71875,
      "epoch": 0.007103350298616571,
      "grad_norm": 2.1946667402693576,
      "kl": 0.0458984375,
      "learning_rate": 9.998755060646966e-07,
      "loss": 0.0018,
      "reward": 2.1357030868530273,
      "reward_std": 0.03673718869686127,
      "rewards/accuracy_reward": 0.9357030987739563,
      "rewards/format_reward": 1.0,
      "step": 515
    },
    {
      "all_correct": 0.75,
      "all_wrong": 0.0,
      "completion_length": 415.90625,
      "epoch": 0.0071171432118177684,
      "grad_norm": 1.9680148320871198,
      "kl": 0.048828125,
      "learning_rate": 9.99875022143875e-07,
      "loss": 0.002,
      "reward": 2.1181249618530273,
      "reward_std": 0.023759758099913597,
      "rewards/accuracy_reward": 0.9181250333786011,
      "rewards/format_reward": 1.0,
      "step": 516
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.0,
      "completion_length": 426.5625,
      "epoch": 0.007130936125018965,
      "grad_norm": 2.649771244215759,
      "kl": 0.04736328125,
      "learning_rate": 9.99874537284469e-07,
      "loss": 0.0019,
      "reward": 2.0860157012939453,
      "reward_std": 0.04784229397773743,
      "rewards/accuracy_reward": 0.8922655582427979,
      "rewards/format_reward": 1.0,
      "step": 517
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.0,
      "completion_length": 429.96875,
      "epoch": 0.007144729038220162,
      "grad_norm": 1.9292168486626,
      "kl": 0.053466796875,
      "learning_rate": 9.998740514864804e-07,
      "loss": 0.0021,
      "reward": 2.099353313446045,
      "reward_std": 0.05245669186115265,
      "rewards/accuracy_reward": 0.9118530750274658,
      "rewards/format_reward": 1.0,
      "step": 518
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.0,
      "completion_length": 433.65625,
      "epoch": 0.007158521951421359,
      "grad_norm": 2.1064973619491525,
      "kl": 0.04541015625,
      "learning_rate": 9.99873564749909e-07,
      "loss": 0.0018,
      "reward": 2.109562397003174,
      "reward_std": 0.04888321831822395,
      "rewards/accuracy_reward": 0.9158124923706055,
      "rewards/format_reward": 1.0,
      "step": 519
    },
    {
      "all_correct": 0.0,
      "all_wrong": 0.0,
      "completion_length": 406.5625,
      "epoch": 0.007172314864622557,
      "grad_norm": 1.714197419561755,
      "kl": 0.04736328125,
      "learning_rate": 9.998730770747564e-07,
      "loss": 0.0019,
      "reward": 1.8421564102172852,
      "reward_std": 0.012847058475017548,
      "rewards/accuracy_reward": 0.6421562433242798,
      "rewards/format_reward": 1.0,
      "step": 520
    },
    {
      "all_correct": 0.75,
      "all_wrong": 0.0,
      "completion_length": 425.71875,
      "epoch": 0.007186107777823754,
      "grad_norm": 3.646128183924181,
      "kl": 0.053955078125,
      "learning_rate": 9.998725884610236e-07,
      "loss": 0.0022,
      "reward": 2.101968765258789,
      "reward_std": 0.03896723687648773,
      "rewards/accuracy_reward": 0.901968777179718,
      "rewards/format_reward": 1.0,
      "step": 521
    },
    {
      "all_correct": 0.75,
      "all_wrong": 0.0,
      "completion_length": 408.21875,
      "epoch": 0.007199900691024951,
      "grad_norm": 1.7398977275314433,
      "kl": 0.045166015625,
      "learning_rate": 9.998720989087109e-07,
      "loss": 0.0018,
      "reward": 2.095125198364258,
      "reward_std": 0.04365184158086777,
      "rewards/accuracy_reward": 0.8951250314712524,
      "rewards/format_reward": 1.0,
      "step": 522
    },
    {
      "all_correct": 0.75,
      "all_wrong": 0.0,
      "completion_length": 411.46875,
      "epoch": 0.0072136936042261485,
      "grad_norm": 3.76395542902141,
      "kl": 0.048095703125,
      "learning_rate": 9.998716084178198e-07,
      "loss": 0.0019,
      "reward": 2.0667343139648438,
      "reward_std": 0.033452246338129044,
      "rewards/accuracy_reward": 0.8667343854904175,
      "rewards/format_reward": 1.0,
      "step": 523
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.0,
      "completion_length": 414.78125,
      "epoch": 0.007227486517427346,
      "grad_norm": 2.6288636793019116,
      "kl": 0.044677734375,
      "learning_rate": 9.99871116988351e-07,
      "loss": 0.0018,
      "reward": 2.0741562843322754,
      "reward_std": 0.04550555348396301,
      "rewards/accuracy_reward": 0.8741562366485596,
      "rewards/format_reward": 1.0,
      "step": 524
    },
    {
      "all_correct": 0.25,
      "all_wrong": 0.0,
      "completion_length": 437.21875,
      "epoch": 0.007241279430628543,
      "grad_norm": 1.9456527226226872,
      "kl": 0.053466796875,
      "learning_rate": 9.998706246203054e-07,
      "loss": 0.0021,
      "reward": 1.9760468006134033,
      "reward_std": 0.052287109196186066,
      "rewards/accuracy_reward": 0.7885469198226929,
      "rewards/format_reward": 1.0,
      "step": 525
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.0,
      "completion_length": 424.6875,
      "epoch": 0.00725507234382974,
      "grad_norm": 1.470474537643452,
      "kl": 0.0458984375,
      "learning_rate": 9.998701313136842e-07,
      "loss": 0.0018,
      "reward": 1.93568754196167,
      "reward_std": 0.02510208822786808,
      "rewards/accuracy_reward": 0.7356874942779541,
      "rewards/format_reward": 1.0,
      "step": 526
    },
    {
      "all_correct": 0.75,
      "all_wrong": 0.0,
      "completion_length": 427.40625,
      "epoch": 0.0072688652570309376,
      "grad_norm": 2.282278706418286,
      "kl": 0.0478515625,
      "learning_rate": 9.998696370684877e-07,
      "loss": 0.0019,
      "reward": 2.0772969722747803,
      "reward_std": 0.04258961230516434,
      "rewards/accuracy_reward": 0.8772968053817749,
      "rewards/format_reward": 1.0,
      "step": 527
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.0,
      "completion_length": 415.8125,
      "epoch": 0.007282658170232135,
      "grad_norm": 4.049097356206214,
      "kl": 0.050537109375,
      "learning_rate": 9.998691418847176e-07,
      "loss": 0.002,
      "reward": 2.0915937423706055,
      "reward_std": 0.0461568646132946,
      "rewards/accuracy_reward": 0.8978437781333923,
      "rewards/format_reward": 1.0,
      "step": 528
    },
    {
      "all_correct": 0.75,
      "all_wrong": 0.0,
      "completion_length": 411.0625,
      "epoch": 0.007296451083433332,
      "grad_norm": 2.0837389439725857,
      "kl": 0.046630859375,
      "learning_rate": 9.998686457623741e-07,
      "loss": 0.0019,
      "reward": 2.094156265258789,
      "reward_std": 0.0520988292992115,
      "rewards/accuracy_reward": 0.9004062414169312,
      "rewards/format_reward": 1.0,
      "step": 529
    },
    {
      "all_correct": 0.25,
      "all_wrong": 0.0,
      "completion_length": 404.90625,
      "epoch": 0.007310243996634529,
      "grad_norm": 2.120102960432839,
      "kl": 0.05517578125,
      "learning_rate": 9.99868148701459e-07,
      "loss": 0.0022,
      "reward": 1.9691874980926514,
      "reward_std": 0.03907351940870285,
      "rewards/accuracy_reward": 0.7691875100135803,
      "rewards/format_reward": 1.0,
      "step": 530
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.0,
      "completion_length": 405.84375,
      "epoch": 0.007324036909835727,
      "grad_norm": 2.579244437249799,
      "kl": 0.04345703125,
      "learning_rate": 9.998676507019721e-07,
      "loss": 0.0017,
      "reward": 2.128000020980835,
      "reward_std": 0.048519209027290344,
      "rewards/accuracy_reward": 0.940500020980835,
      "rewards/format_reward": 1.0,
      "step": 531
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.0,
      "completion_length": 425.59375,
      "epoch": 0.007337829823036924,
      "grad_norm": 1.9874039520070204,
      "kl": 0.046875,
      "learning_rate": 9.998671517639152e-07,
      "loss": 0.0019,
      "reward": 2.0330939292907715,
      "reward_std": 0.03748145326972008,
      "rewards/accuracy_reward": 0.839343786239624,
      "rewards/format_reward": 1.0,
      "step": 532
    },
    {
      "all_correct": 1.0,
      "all_wrong": 0.0,
      "completion_length": 412.75,
      "epoch": 0.007351622736238121,
      "grad_norm": 2.813131197338738,
      "kl": 0.047607421875,
      "learning_rate": 9.998666518872892e-07,
      "loss": 0.0019,
      "reward": 2.1248438358306885,
      "reward_std": 0.023312415927648544,
      "rewards/accuracy_reward": 0.9248437881469727,
      "rewards/format_reward": 1.0,
      "step": 533
    },
    {
      "all_correct": 1.0,
      "all_wrong": 0.0,
      "completion_length": 402.0,
      "epoch": 0.0073654156494393185,
      "grad_norm": 3.513338571103898,
      "kl": 0.044921875,
      "learning_rate": 9.998661510720944e-07,
      "loss": 0.0018,
      "reward": 2.1324687004089355,
      "reward_std": 0.027532529085874557,
      "rewards/accuracy_reward": 0.9324687123298645,
      "rewards/format_reward": 1.0,
      "step": 534
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.0,
      "completion_length": 383.96875,
      "epoch": 0.007379208562640516,
      "grad_norm": 2.3471973342292993,
      "kl": 0.049560546875,
      "learning_rate": 9.998656493183325e-07,
      "loss": 0.002,
      "reward": 2.1390936374664307,
      "reward_std": 0.043466780334711075,
      "rewards/accuracy_reward": 0.9515937566757202,
      "rewards/format_reward": 1.0,
      "step": 535
    },
    {
      "all_correct": 0.75,
      "all_wrong": 0.0,
      "completion_length": 408.65625,
      "epoch": 0.007393001475841712,
      "grad_norm": 2.340795022088105,
      "kl": 0.04443359375,
      "learning_rate": 9.99865146626004e-07,
      "loss": 0.0018,
      "reward": 2.1158437728881836,
      "reward_std": 0.04573627561330795,
      "rewards/accuracy_reward": 0.9158437252044678,
      "rewards/format_reward": 1.0,
      "step": 536
    },
    {
      "all_correct": 0.75,
      "all_wrong": 0.0,
      "completion_length": 404.6875,
      "epoch": 0.007406794389042909,
      "grad_norm": 2.522644604003013,
      "kl": 0.0478515625,
      "learning_rate": 9.9986464299511e-07,
      "loss": 0.0019,
      "reward": 2.0786561965942383,
      "reward_std": 0.03554216027259827,
      "rewards/accuracy_reward": 0.878656268119812,
      "rewards/format_reward": 1.0,
      "step": 537
    },
    {
      "all_correct": 0.75,
      "all_wrong": 0.0,
      "completion_length": 402.6875,
      "epoch": 0.007420587302244107,
      "grad_norm": 3.7604491957785813,
      "kl": 0.05322265625,
      "learning_rate": 9.998641384256515e-07,
      "loss": 0.0021,
      "reward": 2.0857813358306885,
      "reward_std": 0.01673278957605362,
      "rewards/accuracy_reward": 0.8857812285423279,
      "rewards/format_reward": 1.0,
      "step": 538
    },
    {
      "all_correct": 0.75,
      "all_wrong": 0.0,
      "completion_length": 409.78125,
      "epoch": 0.007434380215445304,
      "grad_norm": 2.664318274849365,
      "kl": 0.048583984375,
      "learning_rate": 9.99863632917629e-07,
      "loss": 0.0019,
      "reward": 2.107687473297119,
      "reward_std": 0.04941736161708832,
      "rewards/accuracy_reward": 0.913937509059906,
      "rewards/format_reward": 1.0,
      "step": 539
    },
    {
      "all_correct": 0.0,
      "all_wrong": 0.0,
      "completion_length": 409.5625,
      "epoch": 0.007448173128646501,
      "grad_norm": 7.968877856206847,
      "kl": 0.046875,
      "learning_rate": 9.998631264710441e-07,
      "loss": 0.0019,
      "reward": 1.9662500619888306,
      "reward_std": 0.048946212977170944,
      "rewards/accuracy_reward": 0.778749942779541,
      "rewards/format_reward": 1.0,
      "step": 540
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.0,
      "completion_length": 416.28125,
      "epoch": 0.0074619660418476985,
      "grad_norm": 2.7712626618404315,
      "kl": 0.055419921875,
      "learning_rate": 9.998626190858974e-07,
      "loss": 0.0022,
      "reward": 1.972359538078308,
      "reward_std": 0.02387489750981331,
      "rewards/accuracy_reward": 0.7723593711853027,
      "rewards/format_reward": 1.0,
      "step": 541
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.0,
      "completion_length": 406.8125,
      "epoch": 0.007475758955048896,
      "grad_norm": 1.505516232952706,
      "kl": 0.04638671875,
      "learning_rate": 9.998621107621898e-07,
      "loss": 0.0019,
      "reward": 2.043093681335449,
      "reward_std": 0.015246758237481117,
      "rewards/accuracy_reward": 0.843093752861023,
      "rewards/format_reward": 1.0,
      "step": 542
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.0,
      "completion_length": 411.78125,
      "epoch": 0.007489551868250093,
      "grad_norm": 2.65668605502793,
      "kl": 0.047119140625,
      "learning_rate": 9.998616014999225e-07,
      "loss": 0.0019,
      "reward": 2.042343854904175,
      "reward_std": 0.029045548290014267,
      "rewards/accuracy_reward": 0.8423437476158142,
      "rewards/format_reward": 1.0,
      "step": 543
    },
    {
      "all_correct": 0.75,
      "all_wrong": 0.0,
      "completion_length": 424.75,
      "epoch": 0.00750334478145129,
      "grad_norm": 2.5744088646619203,
      "kl": 0.047607421875,
      "learning_rate": 9.998610912990962e-07,
      "loss": 0.0019,
      "reward": 2.082843780517578,
      "reward_std": 0.030678531154990196,
      "rewards/accuracy_reward": 0.8890937566757202,
      "rewards/format_reward": 1.0,
      "step": 544
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.0,
      "completion_length": 408.5,
      "epoch": 0.0075171376946524876,
      "grad_norm": 2.2398843932794756,
      "kl": 0.052490234375,
      "learning_rate": 9.99860580159712e-07,
      "loss": 0.0021,
      "reward": 2.0209062099456787,
      "reward_std": 0.03538673743605614,
      "rewards/accuracy_reward": 0.8271562457084656,
      "rewards/format_reward": 1.0,
      "step": 545
    },
    {
      "all_correct": 0.25,
      "all_wrong": 0.0,
      "completion_length": 419.34375,
      "epoch": 0.007530930607853685,
      "grad_norm": 4.85026224221038,
      "kl": 0.04541015625,
      "learning_rate": 9.998600680817708e-07,
      "loss": 0.0018,
      "reward": 1.9804999828338623,
      "reward_std": 0.05869058519601822,
      "rewards/accuracy_reward": 0.7929999828338623,
      "rewards/format_reward": 1.0,
      "step": 546
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.0,
      "completion_length": 424.34375,
      "epoch": 0.007544723521054882,
      "grad_norm": 2.268057446881576,
      "kl": 0.04541015625,
      "learning_rate": 9.998595550652735e-07,
      "loss": 0.0018,
      "reward": 2.0225625038146973,
      "reward_std": 0.05491924285888672,
      "rewards/accuracy_reward": 0.8288125395774841,
      "rewards/format_reward": 1.0,
      "step": 547
    },
    {
      "all_correct": 0.75,
      "all_wrong": 0.0,
      "completion_length": 417.25,
      "epoch": 0.007558516434256079,
      "grad_norm": 2.1995625009748023,
      "kl": 0.040283203125,
      "learning_rate": 9.998590411102213e-07,
      "loss": 0.0016,
      "reward": 2.057593822479248,
      "reward_std": 0.036069631576538086,
      "rewards/accuracy_reward": 0.8575937747955322,
      "rewards/format_reward": 1.0,
      "step": 548
    },
    {
      "all_correct": 0.25,
      "all_wrong": 0.0,
      "completion_length": 402.8125,
      "epoch": 0.007572309347457277,
      "grad_norm": 3.191414361308829,
      "kl": 0.04833984375,
      "learning_rate": 9.99858526216615e-07,
      "loss": 0.0019,
      "reward": 1.9870312213897705,
      "reward_std": 0.053150027990341187,
      "rewards/accuracy_reward": 0.7995312213897705,
      "rewards/format_reward": 1.0,
      "step": 549
    },
    {
      "all_correct": 1.0,
      "all_wrong": 0.0,
      "completion_length": 413.25,
      "epoch": 0.007586102260658474,
      "grad_norm": 1.712975265678163,
      "kl": 0.049560546875,
      "learning_rate": 9.998580103844556e-07,
      "loss": 0.002,
      "reward": 2.132093906402588,
      "reward_std": 0.01549484208226204,
      "rewards/accuracy_reward": 0.9320937395095825,
      "rewards/format_reward": 1.0,
      "step": 550
    },
    {
      "all_correct": 0.75,
      "all_wrong": 0.0,
      "completion_length": 421.15625,
      "epoch": 0.007599895173859671,
      "grad_norm": 2.742542474097328,
      "kl": 0.044677734375,
      "learning_rate": 9.99857493613744e-07,
      "loss": 0.0018,
      "reward": 2.094437599182129,
      "reward_std": 0.040200125426054,
      "rewards/accuracy_reward": 0.900687575340271,
      "rewards/format_reward": 1.0,
      "step": 551
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.0,
      "completion_length": 437.90625,
      "epoch": 0.0076136880870608685,
      "grad_norm": 2.808473489984914,
      "kl": 0.044921875,
      "learning_rate": 9.998569759044813e-07,
      "loss": 0.0018,
      "reward": 1.9765312671661377,
      "reward_std": 0.043738193809986115,
      "rewards/accuracy_reward": 0.7765312194824219,
      "rewards/format_reward": 1.0,
      "step": 552
    },
    {
      "all_correct": 0.0,
      "all_wrong": 0.0,
      "completion_length": 436.875,
      "epoch": 0.007627481000262066,
      "grad_norm": 5.35527647118084,
      "kl": 0.0458984375,
      "learning_rate": 9.998564572566682e-07,
      "loss": 0.0018,
      "reward": 2.000718832015991,
      "reward_std": 0.05669596791267395,
      "rewards/accuracy_reward": 0.8132187724113464,
      "rewards/format_reward": 1.0,
      "step": 553
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.0,
      "completion_length": 406.5625,
      "epoch": 0.007641273913463263,
      "grad_norm": 5.8873742580104675,
      "kl": 0.047119140625,
      "learning_rate": 9.99855937670306e-07,
      "loss": 0.0019,
      "reward": 1.9873125553131104,
      "reward_std": 0.03839386999607086,
      "rewards/accuracy_reward": 0.7873125076293945,
      "rewards/format_reward": 1.0,
      "step": 554
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.0,
      "completion_length": 418.21875,
      "epoch": 0.007655066826664459,
      "grad_norm": 2.6317964034594405,
      "kl": 0.042724609375,
      "learning_rate": 9.998554171453956e-07,
      "loss": 0.0017,
      "reward": 2.015031337738037,
      "reward_std": 0.034210801124572754,
      "rewards/accuracy_reward": 0.8150312900543213,
      "rewards/format_reward": 1.0,
      "step": 555
    },
    {
      "all_correct": 0.75,
      "all_wrong": 0.0,
      "completion_length": 417.0,
      "epoch": 0.007668859739865657,
      "grad_norm": 2.805422766664735,
      "kl": 0.0478515625,
      "learning_rate": 9.998548956819379e-07,
      "loss": 0.0019,
      "reward": 2.1157655715942383,
      "reward_std": 0.03818315640091896,
      "rewards/accuracy_reward": 0.915765643119812,
      "rewards/format_reward": 1.0,
      "step": 556
    },
    {
      "all_correct": 0.75,
      "all_wrong": 0.0,
      "completion_length": 405.03125,
      "epoch": 0.007682652653066854,
      "grad_norm": 2.18048530097695,
      "kl": 0.044921875,
      "learning_rate": 9.998543732799337e-07,
      "loss": 0.0018,
      "reward": 2.094156265258789,
      "reward_std": 0.019788896664977074,
      "rewards/accuracy_reward": 0.8941562175750732,
      "rewards/format_reward": 1.0,
      "step": 557
    },
    {
      "all_correct": 1.0,
      "all_wrong": 0.0,
      "completion_length": 412.71875,
      "epoch": 0.007696445566268051,
      "grad_norm": 1.8605141579173605,
      "kl": 0.044921875,
      "learning_rate": 9.998538499393845e-07,
      "loss": 0.0018,
      "reward": 2.1350936889648438,
      "reward_std": 0.0146458949893713,
      "rewards/accuracy_reward": 0.9350938200950623,
      "rewards/format_reward": 1.0,
      "step": 558
    },
    {
      "all_correct": 0.75,
      "all_wrong": 0.0,
      "completion_length": 416.6875,
      "epoch": 0.0077102384794692485,
      "grad_norm": 2.5594732844938166,
      "kl": 0.0478515625,
      "learning_rate": 9.998533256602907e-07,
      "loss": 0.0019,
      "reward": 2.0703125,
      "reward_std": 0.045187897980213165,
      "rewards/accuracy_reward": 0.8765624761581421,
      "rewards/format_reward": 1.0,
      "step": 559
    },
    {
      "all_correct": 0.75,
      "all_wrong": 0.0,
      "completion_length": 406.125,
      "epoch": 0.007724031392670446,
      "grad_norm": 2.4909544263021246,
      "kl": 0.045654296875,
      "learning_rate": 9.998528004426535e-07,
      "loss": 0.0018,
      "reward": 2.095250129699707,
      "reward_std": 0.03287772461771965,
      "rewards/accuracy_reward": 0.8952499628067017,
      "rewards/format_reward": 1.0,
      "step": 560
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.0,
      "completion_length": 410.8125,
      "epoch": 0.007737824305871643,
      "grad_norm": 2.6299525536405604,
      "kl": 0.05078125,
      "learning_rate": 9.998522742864744e-07,
      "loss": 0.002,
      "reward": 2.1489062309265137,
      "reward_std": 0.06338509917259216,
      "rewards/accuracy_reward": 0.9676562547683716,
      "rewards/format_reward": 1.0,
      "step": 561
    },
    {
      "all_correct": 1.0,
      "all_wrong": 0.0,
      "completion_length": 414.125,
      "epoch": 0.00775161721907284,
      "grad_norm": 2.503623458440712,
      "kl": 0.04638671875,
      "learning_rate": 9.998517471917534e-07,
      "loss": 0.0019,
      "reward": 2.1376876831054688,
      "reward_std": 0.02024393156170845,
      "rewards/accuracy_reward": 0.9376875162124634,
      "rewards/format_reward": 1.0,
      "step": 562
    },
    {
      "all_correct": 0.25,
      "all_wrong": 0.0,
      "completion_length": 395.71875,
      "epoch": 0.007765410132274038,
      "grad_norm": 2.4726764911485266,
      "kl": 0.050537109375,
      "learning_rate": 9.998512191584923e-07,
      "loss": 0.002,
      "reward": 2.056906223297119,
      "reward_std": 0.05861155688762665,
      "rewards/accuracy_reward": 0.8694062232971191,
      "rewards/format_reward": 1.0,
      "step": 563
    },
    {
      "all_correct": 1.0,
      "all_wrong": 0.0,
      "completion_length": 404.90625,
      "epoch": 0.007779203045475235,
      "grad_norm": 2.799259390912739,
      "kl": 0.0546875,
      "learning_rate": 9.998506901866916e-07,
      "loss": 0.0022,
      "reward": 2.133718967437744,
      "reward_std": 0.03177863731980324,
      "rewards/accuracy_reward": 0.933718740940094,
      "rewards/format_reward": 1.0,
      "step": 564
    },
    {
      "all_correct": 0.75,
      "all_wrong": 0.0,
      "completion_length": 395.21875,
      "epoch": 0.007792995958676432,
      "grad_norm": 1.957420647806705,
      "kl": 0.05615234375,
      "learning_rate": 9.998501602763528e-07,
      "loss": 0.0022,
      "reward": 2.0997812747955322,
      "reward_std": 0.031323112547397614,
      "rewards/accuracy_reward": 0.9060313105583191,
      "rewards/format_reward": 1.0,
      "step": 565
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.0,
      "completion_length": 406.3125,
      "epoch": 0.007806788871877629,
      "grad_norm": 2.6253991100437184,
      "kl": 0.053466796875,
      "learning_rate": 9.998496294274762e-07,
      "loss": 0.0021,
      "reward": 1.976812481880188,
      "reward_std": 0.0234046820551157,
      "rewards/accuracy_reward": 0.7768125534057617,
      "rewards/format_reward": 1.0,
      "step": 566
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.0,
      "completion_length": 399.25,
      "epoch": 0.007820581785078827,
      "grad_norm": 2.466158240513804,
      "kl": 0.050048828125,
      "learning_rate": 9.998490976400635e-07,
      "loss": 0.002,
      "reward": 2.0518438816070557,
      "reward_std": 0.05854339152574539,
      "rewards/accuracy_reward": 0.8643437623977661,
      "rewards/format_reward": 1.0,
      "step": 567
    },
    {
      "all_correct": 0.75,
      "all_wrong": 0.0,
      "completion_length": 414.90625,
      "epoch": 0.007834374698280024,
      "grad_norm": 5.0992276416627424,
      "kl": 0.052490234375,
      "learning_rate": 9.998485649141153e-07,
      "loss": 0.0021,
      "reward": 2.113156318664551,
      "reward_std": 0.03319736570119858,
      "rewards/accuracy_reward": 0.9194062948226929,
      "rewards/format_reward": 1.0,
      "step": 568
    },
    {
      "all_correct": 0.75,
      "all_wrong": 0.0,
      "completion_length": 421.5625,
      "epoch": 0.007848167611481221,
      "grad_norm": 3.491355031460062,
      "kl": 0.05322265625,
      "learning_rate": 9.998480312496327e-07,
      "loss": 0.0021,
      "reward": 2.1549062728881836,
      "reward_std": 0.038089293986558914,
      "rewards/accuracy_reward": 0.9611562490463257,
      "rewards/format_reward": 1.0,
      "step": 569
    },
    {
      "all_correct": 0.25,
      "all_wrong": 0.0,
      "completion_length": 402.5,
      "epoch": 0.007861960524682418,
      "grad_norm": 4.589181752927826,
      "kl": 0.05126953125,
      "learning_rate": 9.998474966466166e-07,
      "loss": 0.0021,
      "reward": 1.9963749647140503,
      "reward_std": 0.12457430362701416,
      "rewards/accuracy_reward": 0.827625036239624,
      "rewards/format_reward": 0.96875,
      "step": 570
    },
    {
      "all_correct": 1.0,
      "all_wrong": 0.0,
      "completion_length": 419.875,
      "epoch": 0.007875753437883616,
      "grad_norm": 7.388231714019175,
      "kl": 0.045166015625,
      "learning_rate": 9.998469611050682e-07,
      "loss": 0.0018,
      "reward": 2.157437562942505,
      "reward_std": 0.019397925585508347,
      "rewards/accuracy_reward": 0.9574375152587891,
      "rewards/format_reward": 1.0,
      "step": 571
    },
    {
      "all_correct": 0.75,
      "all_wrong": 0.0,
      "completion_length": 398.34375,
      "epoch": 0.007889546351084813,
      "grad_norm": 2.2361473804468326,
      "kl": 0.052734375,
      "learning_rate": 9.998464246249883e-07,
      "loss": 0.0021,
      "reward": 2.0688905715942383,
      "reward_std": 0.042852070182561874,
      "rewards/accuracy_reward": 0.8751406073570251,
      "rewards/format_reward": 1.0,
      "step": 572
    },
    {
      "all_correct": 0.25,
      "all_wrong": 0.0,
      "completion_length": 432.65625,
      "epoch": 0.00790333926428601,
      "grad_norm": 2.0423230135814423,
      "kl": 0.052490234375,
      "learning_rate": 9.998458872063782e-07,
      "loss": 0.0021,
      "reward": 1.9822500944137573,
      "reward_std": 0.04722994565963745,
      "rewards/accuracy_reward": 0.8009999990463257,
      "rewards/format_reward": 1.0,
      "step": 573
    },
    {
      "all_correct": 0.75,
      "all_wrong": 0.0,
      "completion_length": 418.75,
      "epoch": 0.007917132177487208,
      "grad_norm": 7.335567290498138,
      "kl": 0.051025390625,
      "learning_rate": 9.998453488492385e-07,
      "loss": 0.002,
      "reward": 2.095125198364258,
      "reward_std": 0.03222516179084778,
      "rewards/accuracy_reward": 0.8951249718666077,
      "rewards/format_reward": 1.0,
      "step": 574
    },
    {
      "all_correct": 0.75,
      "all_wrong": 0.0,
      "completion_length": 412.78125,
      "epoch": 0.007930925090688405,
      "grad_norm": 2.407204150396676,
      "kl": 0.04541015625,
      "learning_rate": 9.998448095535705e-07,
      "loss": 0.0018,
      "reward": 2.1214687824249268,
      "reward_std": 0.025431903079152107,
      "rewards/accuracy_reward": 0.9214687943458557,
      "rewards/format_reward": 1.0,
      "step": 575
    },
    {
      "all_correct": 0.25,
      "all_wrong": 0.0,
      "completion_length": 402.0625,
      "epoch": 0.007944718003889602,
      "grad_norm": 3.705734717247417,
      "kl": 0.051513671875,
      "learning_rate": 9.998442693193752e-07,
      "loss": 0.0021,
      "reward": 1.989281177520752,
      "reward_std": 0.04195724055171013,
      "rewards/accuracy_reward": 0.7892812490463257,
      "rewards/format_reward": 1.0,
      "step": 576
    },
    {
      "all_correct": 0.75,
      "all_wrong": 0.0,
      "completion_length": 420.625,
      "epoch": 0.0079585109170908,
      "grad_norm": 1.9764430736463567,
      "kl": 0.048828125,
      "learning_rate": 9.998437281466533e-07,
      "loss": 0.002,
      "reward": 2.122041702270508,
      "reward_std": 0.03430842235684395,
      "rewards/accuracy_reward": 0.9282916784286499,
      "rewards/format_reward": 1.0,
      "step": 577
    },
    {
      "all_correct": 0.25,
      "all_wrong": 0.0,
      "completion_length": 416.625,
      "epoch": 0.007972303830291997,
      "grad_norm": 3.2722723537661915,
      "kl": 0.04736328125,
      "learning_rate": 9.998431860354065e-07,
      "loss": 0.0019,
      "reward": 2.022031307220459,
      "reward_std": 0.0205271877348423,
      "rewards/accuracy_reward": 0.8220312595367432,
      "rewards/format_reward": 1.0,
      "step": 578
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.0,
      "completion_length": 394.625,
      "epoch": 0.007986096743493194,
      "grad_norm": 2.7244174426346754,
      "kl": 0.04931640625,
      "learning_rate": 9.99842642985635e-07,
      "loss": 0.002,
      "reward": 2.069000244140625,
      "reward_std": 0.04791932925581932,
      "rewards/accuracy_reward": 0.875249981880188,
      "rewards/format_reward": 1.0,
      "step": 579
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.0,
      "completion_length": 406.0,
      "epoch": 0.007999889656694391,
      "grad_norm": 2.5004396849143933,
      "kl": 0.05078125,
      "learning_rate": 9.998420989973404e-07,
      "loss": 0.002,
      "reward": 1.9372186660766602,
      "reward_std": 0.04446589946746826,
      "rewards/accuracy_reward": 0.7497186660766602,
      "rewards/format_reward": 1.0,
      "step": 580
    },
    {
      "all_correct": 0.25,
      "all_wrong": 0.0,
      "completion_length": 418.53125,
      "epoch": 0.008013682569895588,
      "grad_norm": 2.0668142836736125,
      "kl": 0.04638671875,
      "learning_rate": 9.998415540705234e-07,
      "loss": 0.0019,
      "reward": 1.9620938301086426,
      "reward_std": 0.01525508426129818,
      "rewards/accuracy_reward": 0.7620937824249268,
      "rewards/format_reward": 1.0,
      "step": 581
    },
    {
      "all_correct": 0.75,
      "all_wrong": 0.0,
      "completion_length": 422.21875,
      "epoch": 0.008027475483096786,
      "grad_norm": 2.201531762063597,
      "kl": 0.05029296875,
      "learning_rate": 9.998410082051853e-07,
      "loss": 0.002,
      "reward": 2.103203296661377,
      "reward_std": 0.030211403965950012,
      "rewards/accuracy_reward": 0.9032031297683716,
      "rewards/format_reward": 1.0,
      "step": 582
    },
    {
      "all_correct": 0.25,
      "all_wrong": 0.0,
      "completion_length": 400.875,
      "epoch": 0.008041268396297981,
      "grad_norm": 2.386786833331952,
      "kl": 0.043701171875,
      "learning_rate": 9.99840461401327e-07,
      "loss": 0.0017,
      "reward": 1.972453236579895,
      "reward_std": 0.03474128618836403,
      "rewards/accuracy_reward": 0.7787030935287476,
      "rewards/format_reward": 1.0,
      "step": 583
    },
    {
      "all_correct": 0.75,
      "all_wrong": 0.0,
      "completion_length": 407.46875,
      "epoch": 0.008055061309499179,
      "grad_norm": 3.68525999391454,
      "kl": 0.04443359375,
      "learning_rate": 9.998399136589495e-07,
      "loss": 0.0018,
      "reward": 2.1013126373291016,
      "reward_std": 0.023903727531433105,
      "rewards/accuracy_reward": 0.9013124704360962,
      "rewards/format_reward": 1.0,
      "step": 584
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.0,
      "completion_length": 429.8125,
      "epoch": 0.008068854222700376,
      "grad_norm": 2.245951540590924,
      "kl": 0.04833984375,
      "learning_rate": 9.998393649780537e-07,
      "loss": 0.0019,
      "reward": 1.9754688739776611,
      "reward_std": 0.03574752062559128,
      "rewards/accuracy_reward": 0.7754687070846558,
      "rewards/format_reward": 1.0,
      "step": 585
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.0,
      "completion_length": 395.625,
      "epoch": 0.008082647135901573,
      "grad_norm": 2.127053984711338,
      "kl": 0.049072265625,
      "learning_rate": 9.998388153586408e-07,
      "loss": 0.002,
      "reward": 2.1194686889648438,
      "reward_std": 0.01943955570459366,
      "rewards/accuracy_reward": 0.9194687008857727,
      "rewards/format_reward": 1.0,
      "step": 586
    },
    {
      "all_correct": 0.0,
      "all_wrong": 0.0,
      "completion_length": 411.84375,
      "epoch": 0.00809644004910277,
      "grad_norm": 2.7237821133610662,
      "kl": 0.050537109375,
      "learning_rate": 9.998382648007117e-07,
      "loss": 0.002,
      "reward": 1.993346929550171,
      "reward_std": 0.036785904318094254,
      "rewards/accuracy_reward": 0.7933468222618103,
      "rewards/format_reward": 1.0,
      "step": 587
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.0,
      "completion_length": 401.6875,
      "epoch": 0.008110232962303968,
      "grad_norm": 2.2448973926877733,
      "kl": 0.0595703125,
      "learning_rate": 9.998377133042676e-07,
      "loss": 0.0024,
      "reward": 2.096874952316284,
      "reward_std": 0.044183891266584396,
      "rewards/accuracy_reward": 0.903124988079071,
      "rewards/format_reward": 1.0,
      "step": 588
    },
    {
      "all_correct": 0.75,
      "all_wrong": 0.0,
      "completion_length": 388.34375,
      "epoch": 0.008124025875505165,
      "grad_norm": 2.308035815596835,
      "kl": 0.05126953125,
      "learning_rate": 9.998371608693095e-07,
      "loss": 0.0021,
      "reward": 2.079078197479248,
      "reward_std": 0.017626050859689713,
      "rewards/accuracy_reward": 0.8790781497955322,
      "rewards/format_reward": 1.0,
      "step": 589
    },
    {
      "all_correct": 0.25,
      "all_wrong": 0.0,
      "completion_length": 397.625,
      "epoch": 0.008137818788706362,
      "grad_norm": 2.745135395407473,
      "kl": 0.058349609375,
      "learning_rate": 9.998366074958383e-07,
      "loss": 0.0023,
      "reward": 1.977515697479248,
      "reward_std": 0.0437779426574707,
      "rewards/accuracy_reward": 0.7837656140327454,
      "rewards/format_reward": 1.0,
      "step": 590
    },
    {
      "all_correct": 0.0,
      "all_wrong": 0.0,
      "completion_length": 385.65625,
      "epoch": 0.00815161170190756,
      "grad_norm": 2.5060009700025354,
      "kl": 0.05810546875,
      "learning_rate": 9.998360531838552e-07,
      "loss": 0.0023,
      "reward": 1.8797187805175781,
      "reward_std": 0.033545564860105515,
      "rewards/accuracy_reward": 0.6859687566757202,
      "rewards/format_reward": 1.0,
      "step": 591
    },
    {
      "all_correct": 0.25,
      "all_wrong": 0.0,
      "completion_length": 392.03125,
      "epoch": 0.008165404615108757,
      "grad_norm": 2.232988056890812,
      "kl": 0.049072265625,
      "learning_rate": 9.998354979333613e-07,
      "loss": 0.002,
      "reward": 2.045015811920166,
      "reward_std": 0.037566304206848145,
      "rewards/accuracy_reward": 0.8512656092643738,
      "rewards/format_reward": 1.0,
      "step": 592
    },
    {
      "all_correct": 0.75,
      "all_wrong": 0.0,
      "completion_length": 386.40625,
      "epoch": 0.008179197528309954,
      "grad_norm": 2.572411783666988,
      "kl": 0.053955078125,
      "learning_rate": 9.998349417443575e-07,
      "loss": 0.0022,
      "reward": 2.107781410217285,
      "reward_std": 0.030380673706531525,
      "rewards/accuracy_reward": 0.9140312075614929,
      "rewards/format_reward": 1.0,
      "step": 593
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.0,
      "completion_length": 384.75,
      "epoch": 0.008192990441511151,
      "grad_norm": 2.674710046087842,
      "kl": 0.05322265625,
      "learning_rate": 9.998343846168447e-07,
      "loss": 0.0021,
      "reward": 2.0847561359405518,
      "reward_std": 0.06284406781196594,
      "rewards/accuracy_reward": 0.8910062313079834,
      "rewards/format_reward": 1.0,
      "step": 594
    },
    {
      "all_correct": 0.75,
      "all_wrong": 0.0,
      "completion_length": 387.71875,
      "epoch": 0.008206783354712349,
      "grad_norm": 2.0566682170283324,
      "kl": 0.04931640625,
      "learning_rate": 9.998338265508243e-07,
      "loss": 0.002,
      "reward": 2.059046983718872,
      "reward_std": 0.031089063733816147,
      "rewards/accuracy_reward": 0.8590468764305115,
      "rewards/format_reward": 1.0,
      "step": 595
    },
    {
      "all_correct": 0.75,
      "all_wrong": 0.0,
      "completion_length": 386.40625,
      "epoch": 0.008220576267913546,
      "grad_norm": 1.8868328817765734,
      "kl": 0.05224609375,
      "learning_rate": 9.99833267546297e-07,
      "loss": 0.0021,
      "reward": 2.0136561393737793,
      "reward_std": 0.04053781181573868,
      "rewards/accuracy_reward": 0.8199062347412109,
      "rewards/format_reward": 1.0,
      "step": 596
    },
    {
      "all_correct": 0.25,
      "all_wrong": 0.0,
      "completion_length": 395.1875,
      "epoch": 0.008234369181114743,
      "grad_norm": 2.2404098172490117,
      "kl": 0.05810546875,
      "learning_rate": 9.998327076032642e-07,
      "loss": 0.0023,
      "reward": 1.9520626068115234,
      "reward_std": 0.037759751081466675,
      "rewards/accuracy_reward": 0.7583125233650208,
      "rewards/format_reward": 1.0,
      "step": 597
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.0,
      "completion_length": 391.3125,
      "epoch": 0.00824816209431594,
      "grad_norm": 2.047875516471587,
      "kl": 0.053466796875,
      "learning_rate": 9.998321467217266e-07,
      "loss": 0.0021,
      "reward": 2.0779218673706055,
      "reward_std": 0.03276470676064491,
      "rewards/accuracy_reward": 0.8779218792915344,
      "rewards/format_reward": 1.0,
      "step": 598
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.0,
      "completion_length": 398.3125,
      "epoch": 0.008261955007517138,
      "grad_norm": 6.302417864383523,
      "kl": 0.046875,
      "learning_rate": 9.998315849016854e-07,
      "loss": 0.0019,
      "reward": 2.083718776702881,
      "reward_std": 0.044975195080041885,
      "rewards/accuracy_reward": 0.889968752861023,
      "rewards/format_reward": 1.0,
      "step": 599
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.0,
      "completion_length": 387.96875,
      "epoch": 0.008275747920718335,
      "grad_norm": 2.2765073500433557,
      "kl": 0.052978515625,
      "learning_rate": 9.998310221431418e-07,
      "loss": 0.0021,
      "reward": 2.118281364440918,
      "reward_std": 0.043207887560129166,
      "rewards/accuracy_reward": 0.9245312213897705,
      "rewards/format_reward": 1.0,
      "step": 600
    },
    {
      "all_correct": 0.75,
      "all_wrong": 0.0,
      "completion_length": 390.875,
      "epoch": 0.008289540833919532,
      "grad_norm": 2.6319948678517413,
      "kl": 0.0537109375,
      "learning_rate": 9.998304584460966e-07,
      "loss": 0.0021,
      "reward": 2.1271250247955322,
      "reward_std": 0.03652356564998627,
      "rewards/accuracy_reward": 0.9333750605583191,
      "rewards/format_reward": 1.0,
      "step": 601
    },
    {
      "all_correct": 0.75,
      "all_wrong": 0.0,
      "completion_length": 403.15625,
      "epoch": 0.00830333374712073,
      "grad_norm": 2.7994406243118433,
      "kl": 0.05224609375,
      "learning_rate": 9.99829893810551e-07,
      "loss": 0.0021,
      "reward": 2.113593816757202,
      "reward_std": 0.017072822898626328,
      "rewards/accuracy_reward": 0.9135937094688416,
      "rewards/format_reward": 1.0,
      "step": 602
    },
    {
      "all_correct": 0.25,
      "all_wrong": 0.0,
      "completion_length": 381.8125,
      "epoch": 0.008317126660321927,
      "grad_norm": 2.4668808887652482,
      "kl": 0.05712890625,
      "learning_rate": 9.99829328236506e-07,
      "loss": 0.0023,
      "reward": 1.9726030826568604,
      "reward_std": 0.04915139079093933,
      "rewards/accuracy_reward": 0.7851030826568604,
      "rewards/format_reward": 1.0,
      "step": 603
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.0,
      "completion_length": 390.3125,
      "epoch": 0.008330919573523124,
      "grad_norm": 2.690390285458535,
      "kl": 0.056640625,
      "learning_rate": 9.998287617239629e-07,
      "loss": 0.0023,
      "reward": 2.0758280754089355,
      "reward_std": 0.0338432677090168,
      "rewards/accuracy_reward": 0.8758281469345093,
      "rewards/format_reward": 1.0,
      "step": 604
    },
    {
      "all_correct": 1.0,
      "all_wrong": 0.0,
      "completion_length": 391.8125,
      "epoch": 0.008344712486724321,
      "grad_norm": 3.099596010851626,
      "kl": 0.0537109375,
      "learning_rate": 9.998281942729226e-07,
      "loss": 0.0021,
      "reward": 2.1123032569885254,
      "reward_std": 0.04457748681306839,
      "rewards/accuracy_reward": 0.9185531139373779,
      "rewards/format_reward": 1.0,
      "step": 605
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.0,
      "completion_length": 380.84375,
      "epoch": 0.008358505399925518,
      "grad_norm": 2.85370263563775,
      "kl": 0.055419921875,
      "learning_rate": 9.998276258833858e-07,
      "loss": 0.0022,
      "reward": 2.034712553024292,
      "reward_std": 0.04444105923175812,
      "rewards/accuracy_reward": 0.8347125053405762,
      "rewards/format_reward": 1.0,
      "step": 606
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.0,
      "completion_length": 393.0625,
      "epoch": 0.008372298313126716,
      "grad_norm": 3.112604431728429,
      "kl": 0.05810546875,
      "learning_rate": 9.998270565553542e-07,
      "loss": 0.0023,
      "reward": 2.0184688568115234,
      "reward_std": 0.03241810202598572,
      "rewards/accuracy_reward": 0.8184688091278076,
      "rewards/format_reward": 1.0,
      "step": 607
    },
    {
      "all_correct": 0.75,
      "all_wrong": 0.0,
      "completion_length": 376.40625,
      "epoch": 0.008386091226327913,
      "grad_norm": 2.126485543392029,
      "kl": 0.054931640625,
      "learning_rate": 9.998264862888284e-07,
      "loss": 0.0022,
      "reward": 2.105687379837036,
      "reward_std": 0.033524829894304276,
      "rewards/accuracy_reward": 0.9056875109672546,
      "rewards/format_reward": 1.0,
      "step": 608
    },
    {
      "all_correct": 1.0,
      "all_wrong": 0.0,
      "completion_length": 388.125,
      "epoch": 0.00839988413952911,
      "grad_norm": 1.9499234816441722,
      "kl": 0.05859375,
      "learning_rate": 9.998259150838097e-07,
      "loss": 0.0024,
      "reward": 2.1235408782958984,
      "reward_std": 0.02109311707317829,
      "rewards/accuracy_reward": 0.9235406517982483,
      "rewards/format_reward": 1.0,
      "step": 609
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.0,
      "completion_length": 386.09375,
      "epoch": 0.008413677052730308,
      "grad_norm": 2.8183770161704684,
      "kl": 0.05810546875,
      "learning_rate": 9.998253429402993e-07,
      "loss": 0.0023,
      "reward": 2.0257344245910645,
      "reward_std": 0.03893623873591423,
      "rewards/accuracy_reward": 0.8257343769073486,
      "rewards/format_reward": 1.0,
      "step": 610
    },
    {
      "all_correct": 0.25,
      "all_wrong": 0.0,
      "completion_length": 397.25,
      "epoch": 0.008427469965931505,
      "grad_norm": 2.9721138095369093,
      "kl": 0.060302734375,
      "learning_rate": 9.998247698582977e-07,
      "loss": 0.0024,
      "reward": 2.031135320663452,
      "reward_std": 0.055596478283405304,
      "rewards/accuracy_reward": 0.8436354398727417,
      "rewards/format_reward": 1.0,
      "step": 611
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.0,
      "completion_length": 380.15625,
      "epoch": 0.008441262879132702,
      "grad_norm": 2.4769072314650846,
      "kl": 0.06640625,
      "learning_rate": 9.998241958378066e-07,
      "loss": 0.0026,
      "reward": 2.059593677520752,
      "reward_std": 0.020894348621368408,
      "rewards/accuracy_reward": 0.8595937490463257,
      "rewards/format_reward": 1.0,
      "step": 612
    },
    {
      "all_correct": 0.25,
      "all_wrong": 0.0,
      "completion_length": 390.3125,
      "epoch": 0.0084550557923339,
      "grad_norm": 2.163008190514058,
      "kl": 0.064453125,
      "learning_rate": 9.998236208788268e-07,
      "loss": 0.0026,
      "reward": 1.9688438177108765,
      "reward_std": 0.04034517705440521,
      "rewards/accuracy_reward": 0.7750937342643738,
      "rewards/format_reward": 1.0,
      "step": 613
    },
    {
      "all_correct": 0.25,
      "all_wrong": 0.0,
      "completion_length": 390.375,
      "epoch": 0.008468848705535097,
      "grad_norm": 2.478480975850513,
      "kl": 0.06494140625,
      "learning_rate": 9.998230449813596e-07,
      "loss": 0.0026,
      "reward": 1.978431224822998,
      "reward_std": 0.05483083054423332,
      "rewards/accuracy_reward": 0.7846812605857849,
      "rewards/format_reward": 1.0,
      "step": 614
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.0,
      "completion_length": 401.5625,
      "epoch": 0.008482641618736294,
      "grad_norm": 2.682396192807337,
      "kl": 0.05615234375,
      "learning_rate": 9.998224681454056e-07,
      "loss": 0.0022,
      "reward": 2.003499984741211,
      "reward_std": 0.04995805397629738,
      "rewards/accuracy_reward": 0.8097500801086426,
      "rewards/format_reward": 1.0,
      "step": 615
    },
    {
      "all_correct": 0.0,
      "all_wrong": 0.0,
      "completion_length": 387.96875,
      "epoch": 0.008496434531937491,
      "grad_norm": 2.4011236279659522,
      "kl": 0.0546875,
      "learning_rate": 9.998218903709665e-07,
      "loss": 0.0022,
      "reward": 2.003406286239624,
      "reward_std": 0.04750627651810646,
      "rewards/accuracy_reward": 0.8096562623977661,
      "rewards/format_reward": 1.0,
      "step": 616
    },
    {
      "all_correct": 0.75,
      "all_wrong": 0.0,
      "completion_length": 397.09375,
      "epoch": 0.008510227445138688,
      "grad_norm": 2.3404149875572053,
      "kl": 0.06103515625,
      "learning_rate": 9.99821311658043e-07,
      "loss": 0.0024,
      "reward": 2.1420626640319824,
      "reward_std": 0.033706601709127426,
      "rewards/accuracy_reward": 0.942062497138977,
      "rewards/format_reward": 1.0,
      "step": 617
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.0,
      "completion_length": 388.53125,
      "epoch": 0.008524020358339886,
      "grad_norm": 2.914850768053351,
      "kl": 0.04833984375,
      "learning_rate": 9.99820732006636e-07,
      "loss": 0.0019,
      "reward": 2.055187463760376,
      "reward_std": 0.0450524240732193,
      "rewards/accuracy_reward": 0.8614375591278076,
      "rewards/format_reward": 1.0,
      "step": 618
    },
    {
      "all_correct": 0.25,
      "all_wrong": 0.0,
      "completion_length": 397.78125,
      "epoch": 0.008537813271541083,
      "grad_norm": 4.106220920970892,
      "kl": 0.055908203125,
      "learning_rate": 9.99820151416747e-07,
      "loss": 0.0022,
      "reward": 2.0269689559936523,
      "reward_std": 0.044902682304382324,
      "rewards/accuracy_reward": 0.8332187533378601,
      "rewards/format_reward": 1.0,
      "step": 619
    },
    {
      "all_correct": 1.0,
      "all_wrong": 0.0,
      "completion_length": 400.125,
      "epoch": 0.008551606184742279,
      "grad_norm": 1.9764547817206366,
      "kl": 0.052490234375,
      "learning_rate": 9.998195698883771e-07,
      "loss": 0.0021,
      "reward": 2.1538748741149902,
      "reward_std": 0.015444188378751278,
      "rewards/accuracy_reward": 0.953874945640564,
      "rewards/format_reward": 1.0,
      "step": 620
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.0,
      "completion_length": 415.4375,
      "epoch": 0.008565399097943476,
      "grad_norm": 5.064746496796814,
      "kl": 0.0537109375,
      "learning_rate": 9.99818987421527e-07,
      "loss": 0.0021,
      "reward": 2.0861563682556152,
      "reward_std": 0.03293747082352638,
      "rewards/accuracy_reward": 0.8861562013626099,
      "rewards/format_reward": 1.0,
      "step": 621
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.0,
      "completion_length": 400.34375,
      "epoch": 0.008579192011144673,
      "grad_norm": 2.147137270741646,
      "kl": 0.05517578125,
      "learning_rate": 9.99818404016198e-07,
      "loss": 0.0022,
      "reward": 2.0408437252044678,
      "reward_std": 0.05207609012722969,
      "rewards/accuracy_reward": 0.8470937013626099,
      "rewards/format_reward": 1.0,
      "step": 622
    },
    {
      "all_correct": 0.75,
      "all_wrong": 0.0,
      "completion_length": 400.4375,
      "epoch": 0.00859298492434587,
      "grad_norm": 1.626374703900478,
      "kl": 0.052978515625,
      "learning_rate": 9.998178196723914e-07,
      "loss": 0.0021,
      "reward": 2.0898125171661377,
      "reward_std": 0.015274680219590664,
      "rewards/accuracy_reward": 0.8898124694824219,
      "rewards/format_reward": 1.0,
      "step": 623
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.0,
      "completion_length": 415.78125,
      "epoch": 0.008606777837547068,
      "grad_norm": 2.023997008424375,
      "kl": 0.06005859375,
      "learning_rate": 9.998172343901082e-07,
      "loss": 0.0024,
      "reward": 2.0917811393737793,
      "reward_std": 0.04930365830659866,
      "rewards/accuracy_reward": 0.8980312347412109,
      "rewards/format_reward": 1.0,
      "step": 624
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.0,
      "completion_length": 421.71875,
      "epoch": 0.008620570750748265,
      "grad_norm": 2.2693899267378077,
      "kl": 0.05859375,
      "learning_rate": 9.998166481693492e-07,
      "loss": 0.0024,
      "reward": 1.9982812404632568,
      "reward_std": 0.03485594689846039,
      "rewards/accuracy_reward": 0.798281192779541,
      "rewards/format_reward": 1.0,
      "step": 625
    },
    {
      "all_correct": 0.75,
      "all_wrong": 0.0,
      "completion_length": 420.875,
      "epoch": 0.008634363663949462,
      "grad_norm": 2.5685082513863056,
      "kl": 0.052734375,
      "learning_rate": 9.998160610101158e-07,
      "loss": 0.0021,
      "reward": 2.138312578201294,
      "reward_std": 0.034911856055259705,
      "rewards/accuracy_reward": 0.944562554359436,
      "rewards/format_reward": 1.0,
      "step": 626
    },
    {
      "all_correct": 0.75,
      "all_wrong": 0.0,
      "completion_length": 439.78125,
      "epoch": 0.00864815657715066,
      "grad_norm": 2.4530750930755456,
      "kl": 0.0595703125,
      "learning_rate": 9.99815472912409e-07,
      "loss": 0.0024,
      "reward": 2.0868124961853027,
      "reward_std": 0.034031230956315994,
      "rewards/accuracy_reward": 0.8868125081062317,
      "rewards/format_reward": 1.0,
      "step": 627
    },
    {
      "all_correct": 1.0,
      "all_wrong": 0.0,
      "completion_length": 421.25,
      "epoch": 0.008661949490351857,
      "grad_norm": 2.078663632867618,
      "kl": 0.05517578125,
      "learning_rate": 9.9981488387623e-07,
      "loss": 0.0022,
      "reward": 2.15415620803833,
      "reward_std": 0.022934025153517723,
      "rewards/accuracy_reward": 0.9541562795639038,
      "rewards/format_reward": 1.0,
      "step": 628
    },
    {
      "all_correct": 1.0,
      "all_wrong": 0.0,
      "completion_length": 418.15625,
      "epoch": 0.008675742403553054,
      "grad_norm": 2.7524826792569055,
      "kl": 0.05615234375,
      "learning_rate": 9.998142939015798e-07,
      "loss": 0.0023,
      "reward": 2.1138124465942383,
      "reward_std": 0.039046578109264374,
      "rewards/accuracy_reward": 0.913812518119812,
      "rewards/format_reward": 1.0,
      "step": 629
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.0,
      "completion_length": 425.40625,
      "epoch": 0.008689535316754251,
      "grad_norm": 2.22296900028479,
      "kl": 0.0576171875,
      "learning_rate": 9.998137029884592e-07,
      "loss": 0.0023,
      "reward": 2.1036875247955322,
      "reward_std": 0.04939688369631767,
      "rewards/accuracy_reward": 0.9099375009536743,
      "rewards/format_reward": 1.0,
      "step": 630
    },
    {
      "all_correct": 0.25,
      "all_wrong": 0.0,
      "completion_length": 429.78125,
      "epoch": 0.008703328229955449,
      "grad_norm": 2.5642466104647212,
      "kl": 0.051513671875,
      "learning_rate": 9.9981311113687e-07,
      "loss": 0.0021,
      "reward": 1.984781265258789,
      "reward_std": 0.05748384818434715,
      "rewards/accuracy_reward": 0.7972812652587891,
      "rewards/format_reward": 1.0,
      "step": 631
    },
    {
      "all_correct": 0.75,
      "all_wrong": 0.0,
      "completion_length": 428.46875,
      "epoch": 0.008717121143156646,
      "grad_norm": 1.8367440728380107,
      "kl": 0.053466796875,
      "learning_rate": 9.998125183468128e-07,
      "loss": 0.0021,
      "reward": 2.0717811584472656,
      "reward_std": 0.03157765418291092,
      "rewards/accuracy_reward": 0.8717812299728394,
      "rewards/format_reward": 1.0,
      "step": 632
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.0,
      "completion_length": 416.28125,
      "epoch": 0.008730914056357843,
      "grad_norm": 2.438469423462321,
      "kl": 0.056884765625,
      "learning_rate": 9.99811924618289e-07,
      "loss": 0.0023,
      "reward": 2.087296962738037,
      "reward_std": 0.03855868801474571,
      "rewards/accuracy_reward": 0.8935469388961792,
      "rewards/format_reward": 1.0,
      "step": 633
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.0,
      "completion_length": 426.625,
      "epoch": 0.00874470696955904,
      "grad_norm": 2.771776532314638,
      "kl": 0.04833984375,
      "learning_rate": 9.998113299512996e-07,
      "loss": 0.0019,
      "reward": 2.056421995162964,
      "reward_std": 0.03198815882205963,
      "rewards/accuracy_reward": 0.8564218878746033,
      "rewards/format_reward": 1.0,
      "step": 634
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.0,
      "completion_length": 429.40625,
      "epoch": 0.008758499882760238,
      "grad_norm": 2.1101736607696138,
      "kl": 0.05126953125,
      "learning_rate": 9.998107343458456e-07,
      "loss": 0.0021,
      "reward": 2.0679280757904053,
      "reward_std": 0.01697995699942112,
      "rewards/accuracy_reward": 0.867928147315979,
      "rewards/format_reward": 1.0,
      "step": 635
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.0,
      "completion_length": 415.5,
      "epoch": 0.008772292795961435,
      "grad_norm": 2.3569885993940654,
      "kl": 0.05859375,
      "learning_rate": 9.998101378019284e-07,
      "loss": 0.0023,
      "reward": 1.9881563186645508,
      "reward_std": 0.04332330450415611,
      "rewards/accuracy_reward": 0.7944062352180481,
      "rewards/format_reward": 1.0,
      "step": 636
    },
    {
      "all_correct": 1.0,
      "all_wrong": 0.0,
      "completion_length": 403.65625,
      "epoch": 0.008786085709162632,
      "grad_norm": 2.090929273324986,
      "kl": 0.052490234375,
      "learning_rate": 9.998095403195487e-07,
      "loss": 0.0021,
      "reward": 2.1616876125335693,
      "reward_std": 0.03680138662457466,
      "rewards/accuracy_reward": 0.9679374694824219,
      "rewards/format_reward": 1.0,
      "step": 637
    },
    {
      "all_correct": 0.25,
      "all_wrong": 0.0,
      "completion_length": 408.1875,
      "epoch": 0.00879987862236383,
      "grad_norm": 2.214879025935309,
      "kl": 0.055908203125,
      "learning_rate": 9.99808941898708e-07,
      "loss": 0.0022,
      "reward": 2.037156105041504,
      "reward_std": 0.03522922843694687,
      "rewards/accuracy_reward": 0.8434063196182251,
      "rewards/format_reward": 1.0,
      "step": 638
    },
    {
      "all_correct": 0.75,
      "all_wrong": 0.0,
      "completion_length": 422.0625,
      "epoch": 0.008813671535565027,
      "grad_norm": 2.1205317647208646,
      "kl": 0.05224609375,
      "learning_rate": 9.998083425394072e-07,
      "loss": 0.0021,
      "reward": 2.1116719245910645,
      "reward_std": 0.04663609713315964,
      "rewards/accuracy_reward": 0.9179219007492065,
      "rewards/format_reward": 1.0,
      "step": 639
    },
    {
      "all_correct": 0.25,
      "all_wrong": 0.0,
      "completion_length": 418.78125,
      "epoch": 0.008827464448766224,
      "grad_norm": 2.042338839071063,
      "kl": 0.05517578125,
      "learning_rate": 9.998077422416476e-07,
      "loss": 0.0022,
      "reward": 1.876499891281128,
      "reward_std": 0.03659955412149429,
      "rewards/accuracy_reward": 0.6827499270439148,
      "rewards/format_reward": 1.0,
      "step": 640
    },
    {
      "all_correct": 1.0,
      "all_wrong": 0.0,
      "completion_length": 415.0,
      "epoch": 0.008841257361967421,
      "grad_norm": 2.1692973668032036,
      "kl": 0.052001953125,
      "learning_rate": 9.9980714100543e-07,
      "loss": 0.0021,
      "reward": 2.0929999351501465,
      "reward_std": 0.020299028605222702,
      "rewards/accuracy_reward": 0.8929999470710754,
      "rewards/format_reward": 1.0,
      "step": 641
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.0,
      "completion_length": 410.15625,
      "epoch": 0.008855050275168619,
      "grad_norm": 8.145238013831461,
      "kl": 0.05419921875,
      "learning_rate": 9.99806538830756e-07,
      "loss": 0.0022,
      "reward": 1.9901564121246338,
      "reward_std": 0.027446966618299484,
      "rewards/accuracy_reward": 0.7901561856269836,
      "rewards/format_reward": 1.0,
      "step": 642
    },
    {
      "all_correct": 0.25,
      "all_wrong": 0.0,
      "completion_length": 391.46875,
      "epoch": 0.008868843188369816,
      "grad_norm": 3.5870141350540905,
      "kl": 0.05322265625,
      "learning_rate": 9.998059357176264e-07,
      "loss": 0.0021,
      "reward": 1.9034688472747803,
      "reward_std": 0.10066314041614532,
      "rewards/accuracy_reward": 0.7159687280654907,
      "rewards/format_reward": 1.0,
      "step": 643
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.0,
      "completion_length": 411.4375,
      "epoch": 0.008882636101571013,
      "grad_norm": 5.5183408870639825,
      "kl": 0.052734375,
      "learning_rate": 9.998053316660427e-07,
      "loss": 0.0021,
      "reward": 2.071718692779541,
      "reward_std": 0.051681824028491974,
      "rewards/accuracy_reward": 0.8717188239097595,
      "rewards/format_reward": 1.0,
      "step": 644
    },
    {
      "all_correct": 0.25,
      "all_wrong": 0.0,
      "completion_length": 419.9375,
      "epoch": 0.00889642901477221,
      "grad_norm": 3.3821479870666344,
      "kl": 0.0595703125,
      "learning_rate": 9.998047266760055e-07,
      "loss": 0.0024,
      "reward": 2.026750087738037,
      "reward_std": 0.0515354759991169,
      "rewards/accuracy_reward": 0.8267500400543213,
      "rewards/format_reward": 1.0,
      "step": 645
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.0,
      "completion_length": 415.34375,
      "epoch": 0.008910221927973408,
      "grad_norm": 2.653034654723109,
      "kl": 0.0537109375,
      "learning_rate": 9.998041207475162e-07,
      "loss": 0.0022,
      "reward": 2.0444374084472656,
      "reward_std": 0.03171418607234955,
      "rewards/accuracy_reward": 0.8444375991821289,
      "rewards/format_reward": 1.0,
      "step": 646
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.0,
      "completion_length": 400.53125,
      "epoch": 0.008924014841174605,
      "grad_norm": 4.232587551749829,
      "kl": 0.05224609375,
      "learning_rate": 9.99803513880576e-07,
      "loss": 0.0021,
      "reward": 2.1110939979553223,
      "reward_std": 0.011543495580554008,
      "rewards/accuracy_reward": 0.9110937714576721,
      "rewards/format_reward": 1.0,
      "step": 647
    },
    {
      "all_correct": 0.75,
      "all_wrong": 0.0,
      "completion_length": 405.46875,
      "epoch": 0.008937807754375802,
      "grad_norm": 2.1555621268191216,
      "kl": 0.053955078125,
      "learning_rate": 9.99802906075186e-07,
      "loss": 0.0022,
      "reward": 2.139343738555908,
      "reward_std": 0.04276597499847412,
      "rewards/accuracy_reward": 0.9518437385559082,
      "rewards/format_reward": 1.0,
      "step": 648
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.0,
      "completion_length": 419.875,
      "epoch": 0.008951600667577,
      "grad_norm": 9.638718561777605,
      "kl": 0.050048828125,
      "learning_rate": 9.998022973313471e-07,
      "loss": 0.002,
      "reward": 2.0935935974121094,
      "reward_std": 0.035451896488666534,
      "rewards/accuracy_reward": 0.899843692779541,
      "rewards/format_reward": 1.0,
      "step": 649
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.0,
      "completion_length": 426.5625,
      "epoch": 0.008965393580778197,
      "grad_norm": 2.136015591482648,
      "kl": 0.05615234375,
      "learning_rate": 9.998016876490608e-07,
      "loss": 0.0023,
      "reward": 2.0662031173706055,
      "reward_std": 0.022263051941990852,
      "rewards/accuracy_reward": 0.8662031292915344,
      "rewards/format_reward": 1.0,
      "step": 650
    },
    {
      "all_correct": 1.0,
      "all_wrong": 0.0,
      "completion_length": 429.125,
      "epoch": 0.008979186493979394,
      "grad_norm": 2.5408916769689975,
      "kl": 0.052001953125,
      "learning_rate": 9.998010770283283e-07,
      "loss": 0.0021,
      "reward": 2.123812675476074,
      "reward_std": 0.01799178309738636,
      "rewards/accuracy_reward": 0.9238125085830688,
      "rewards/format_reward": 1.0,
      "step": 651
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.0,
      "completion_length": 410.3125,
      "epoch": 0.008992979407180591,
      "grad_norm": 1.713585949738345,
      "kl": 0.05712890625,
      "learning_rate": 9.998004654691504e-07,
      "loss": 0.0023,
      "reward": 2.0980000495910645,
      "reward_std": 0.011981104500591755,
      "rewards/accuracy_reward": 0.8980000019073486,
      "rewards/format_reward": 1.0,
      "step": 652
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.0,
      "completion_length": 424.59375,
      "epoch": 0.009006772320381789,
      "grad_norm": 1.8164043796813294,
      "kl": 0.05517578125,
      "learning_rate": 9.997998529715284e-07,
      "loss": 0.0022,
      "reward": 2.093562602996826,
      "reward_std": 0.03193996101617813,
      "rewards/accuracy_reward": 0.8935624957084656,
      "rewards/format_reward": 1.0,
      "step": 653
    },
    {
      "all_correct": 1.0,
      "all_wrong": 0.0,
      "completion_length": 412.5625,
      "epoch": 0.009020565233582986,
      "grad_norm": 2.1294364480088603,
      "kl": 0.050537109375,
      "learning_rate": 9.997992395354634e-07,
      "loss": 0.002,
      "reward": 2.134812355041504,
      "reward_std": 0.02538403868675232,
      "rewards/accuracy_reward": 0.9348125457763672,
      "rewards/format_reward": 1.0,
      "step": 654
    },
    {
      "all_correct": 0.75,
      "all_wrong": 0.0,
      "completion_length": 423.59375,
      "epoch": 0.009034358146784183,
      "grad_norm": 1.9213315905645845,
      "kl": 0.0498046875,
      "learning_rate": 9.997986251609567e-07,
      "loss": 0.002,
      "reward": 2.1349687576293945,
      "reward_std": 0.04420100897550583,
      "rewards/accuracy_reward": 0.9412187933921814,
      "rewards/format_reward": 1.0,
      "step": 655
    },
    {
      "all_correct": 0.75,
      "all_wrong": 0.0,
      "completion_length": 423.5,
      "epoch": 0.00904815105998538,
      "grad_norm": 2.391636972620343,
      "kl": 0.0537109375,
      "learning_rate": 9.997980098480092e-07,
      "loss": 0.0021,
      "reward": 2.0859999656677246,
      "reward_std": 0.02876342460513115,
      "rewards/accuracy_reward": 0.8860000371932983,
      "rewards/format_reward": 1.0,
      "step": 656
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.0,
      "completion_length": 398.46875,
      "epoch": 0.009061943973186578,
      "grad_norm": 2.517320094983817,
      "kl": 0.052001953125,
      "learning_rate": 9.997973935966224e-07,
      "loss": 0.0021,
      "reward": 2.0307188034057617,
      "reward_std": 0.04952946677803993,
      "rewards/accuracy_reward": 0.8369687795639038,
      "rewards/format_reward": 1.0,
      "step": 657
    },
    {
      "all_correct": 0.25,
      "all_wrong": 0.0,
      "completion_length": 404.65625,
      "epoch": 0.009075736886387773,
      "grad_norm": 2.891569112880208,
      "kl": 0.060546875,
      "learning_rate": 9.997967764067972e-07,
      "loss": 0.0024,
      "reward": 2.065577983856201,
      "reward_std": 0.05062235891819,
      "rewards/accuracy_reward": 0.8718281388282776,
      "rewards/format_reward": 1.0,
      "step": 658
    },
    {
      "all_correct": 0.75,
      "all_wrong": 0.0,
      "completion_length": 418.625,
      "epoch": 0.00908952979958897,
      "grad_norm": 3.7156255359803385,
      "kl": 0.05859375,
      "learning_rate": 9.99796158278535e-07,
      "loss": 0.0023,
      "reward": 2.0514373779296875,
      "reward_std": 0.02630566619336605,
      "rewards/accuracy_reward": 0.851437509059906,
      "rewards/format_reward": 1.0,
      "step": 659
    },
    {
      "all_correct": 0.0,
      "all_wrong": 0.0,
      "completion_length": 428.65625,
      "epoch": 0.009103322712790168,
      "grad_norm": 2.9580197043360426,
      "kl": 0.05419921875,
      "learning_rate": 9.997955392118365e-07,
      "loss": 0.0022,
      "reward": 1.9528437852859497,
      "reward_std": 0.044448766857385635,
      "rewards/accuracy_reward": 0.7528437376022339,
      "rewards/format_reward": 1.0,
      "step": 660
    },
    {
      "all_correct": 1.0,
      "all_wrong": 0.0,
      "completion_length": 413.25,
      "epoch": 0.009117115625991365,
      "grad_norm": 2.851442801582792,
      "kl": 0.052734375,
      "learning_rate": 9.997949192067032e-07,
      "loss": 0.0021,
      "reward": 2.1162500381469727,
      "reward_std": 0.026071693748235703,
      "rewards/accuracy_reward": 0.9162500500679016,
      "rewards/format_reward": 1.0,
      "step": 661
    },
    {
      "all_correct": 0.75,
      "all_wrong": 0.0,
      "completion_length": 414.71875,
      "epoch": 0.009130908539192562,
      "grad_norm": 4.329190577327829,
      "kl": 0.060546875,
      "learning_rate": 9.997942982631363e-07,
      "loss": 0.0024,
      "reward": 2.097062587738037,
      "reward_std": 0.03074048087000847,
      "rewards/accuracy_reward": 0.9033124446868896,
      "rewards/format_reward": 1.0,
      "step": 662
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.0,
      "completion_length": 405.65625,
      "epoch": 0.00914470145239376,
      "grad_norm": 2.6330735040202415,
      "kl": 0.05810546875,
      "learning_rate": 9.997936763811367e-07,
      "loss": 0.0023,
      "reward": 1.959281325340271,
      "reward_std": 0.07087946683168411,
      "rewards/accuracy_reward": 0.7717812061309814,
      "rewards/format_reward": 1.0,
      "step": 663
    },
    {
      "all_correct": 0.25,
      "all_wrong": 0.0,
      "completion_length": 410.5625,
      "epoch": 0.009158494365594957,
      "grad_norm": 4.4723131732354355,
      "kl": 0.052734375,
      "learning_rate": 9.99793053560706e-07,
      "loss": 0.0021,
      "reward": 1.8886876106262207,
      "reward_std": 0.04330645874142647,
      "rewards/accuracy_reward": 0.6886875629425049,
      "rewards/format_reward": 1.0,
      "step": 664
    },
    {
      "all_correct": 0.75,
      "all_wrong": 0.0,
      "completion_length": 408.71875,
      "epoch": 0.009172287278796154,
      "grad_norm": 2.5958242763529604,
      "kl": 0.05517578125,
      "learning_rate": 9.99792429801845e-07,
      "loss": 0.0022,
      "reward": 2.057281255722046,
      "reward_std": 0.034680403769016266,
      "rewards/accuracy_reward": 0.8572812676429749,
      "rewards/format_reward": 1.0,
      "step": 665
    },
    {
      "all_correct": 0.75,
      "all_wrong": 0.0,
      "completion_length": 422.28125,
      "epoch": 0.009186080191997351,
      "grad_norm": 2.6017487494919274,
      "kl": 0.06298828125,
      "learning_rate": 9.99791805104555e-07,
      "loss": 0.0025,
      "reward": 2.075312614440918,
      "reward_std": 0.029237957671284676,
      "rewards/accuracy_reward": 0.8753124475479126,
      "rewards/format_reward": 1.0,
      "step": 666
    },
    {
      "all_correct": 1.0,
      "all_wrong": 0.0,
      "completion_length": 417.21875,
      "epoch": 0.009199873105198549,
      "grad_norm": 2.6924402370209854,
      "kl": 0.05615234375,
      "learning_rate": 9.997911794688372e-07,
      "loss": 0.0022,
      "reward": 2.1150624752044678,
      "reward_std": 0.020551782101392746,
      "rewards/accuracy_reward": 0.9150625467300415,
      "rewards/format_reward": 1.0,
      "step": 667
    },
    {
      "all_correct": 0.25,
      "all_wrong": 0.0,
      "completion_length": 447.5,
      "epoch": 0.009213666018399746,
      "grad_norm": 2.170205277153537,
      "kl": 0.059326171875,
      "learning_rate": 9.997905528946927e-07,
      "loss": 0.0024,
      "reward": 1.9899688959121704,
      "reward_std": 0.08910458534955978,
      "rewards/accuracy_reward": 0.821218729019165,
      "rewards/format_reward": 1.0,
      "step": 668
    },
    {
      "all_correct": 0.25,
      "all_wrong": 0.0,
      "completion_length": 402.125,
      "epoch": 0.009227458931600943,
      "grad_norm": 2.2706751225097332,
      "kl": 0.05126953125,
      "learning_rate": 9.997899253821227e-07,
      "loss": 0.002,
      "reward": 2.0256874561309814,
      "reward_std": 0.01520544197410345,
      "rewards/accuracy_reward": 0.8256875276565552,
      "rewards/format_reward": 1.0,
      "step": 669
    },
    {
      "all_correct": 0.25,
      "all_wrong": 0.0,
      "completion_length": 437.4375,
      "epoch": 0.00924125184480214,
      "grad_norm": 4.737529312533587,
      "kl": 0.05810546875,
      "learning_rate": 9.997892969311284e-07,
      "loss": 0.0023,
      "reward": 1.9027812480926514,
      "reward_std": 0.04217426851391792,
      "rewards/accuracy_reward": 0.7027812600135803,
      "rewards/format_reward": 1.0,
      "step": 670
    },
    {
      "all_correct": 0.75,
      "all_wrong": 0.0,
      "completion_length": 416.5625,
      "epoch": 0.009255044758003338,
      "grad_norm": 1.6125817235718418,
      "kl": 0.053466796875,
      "learning_rate": 9.997886675417108e-07,
      "loss": 0.0021,
      "reward": 2.13212513923645,
      "reward_std": 0.03144735097885132,
      "rewards/accuracy_reward": 0.9321250319480896,
      "rewards/format_reward": 1.0,
      "step": 671
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.0,
      "completion_length": 424.375,
      "epoch": 0.009268837671204535,
      "grad_norm": 2.6187150115702686,
      "kl": 0.0595703125,
      "learning_rate": 9.997880372138716e-07,
      "loss": 0.0024,
      "reward": 1.999000072479248,
      "reward_std": 0.021543916314840317,
      "rewards/accuracy_reward": 0.7990000247955322,
      "rewards/format_reward": 1.0,
      "step": 672
    },
    {
      "all_correct": 0.75,
      "all_wrong": 0.0,
      "completion_length": 435.78125,
      "epoch": 0.009282630584405732,
      "grad_norm": 2.228889154565372,
      "kl": 0.05615234375,
      "learning_rate": 9.997874059476114e-07,
      "loss": 0.0023,
      "reward": 2.0667500495910645,
      "reward_std": 0.0515543594956398,
      "rewards/accuracy_reward": 0.8730000257492065,
      "rewards/format_reward": 1.0,
      "step": 673
    },
    {
      "all_correct": 0.75,
      "all_wrong": 0.0,
      "completion_length": 413.0625,
      "epoch": 0.00929642349760693,
      "grad_norm": 1.6510331416126716,
      "kl": 0.05322265625,
      "learning_rate": 9.997867737429317e-07,
      "loss": 0.0021,
      "reward": 2.1133124828338623,
      "reward_std": 0.019771721214056015,
      "rewards/accuracy_reward": 0.913312554359436,
      "rewards/format_reward": 1.0,
      "step": 674
    },
    {
      "all_correct": 0.25,
      "all_wrong": 0.0,
      "completion_length": 429.28125,
      "epoch": 0.009310216410808127,
      "grad_norm": 1.6296588009543245,
      "kl": 0.05712890625,
      "learning_rate": 9.997861405998336e-07,
      "loss": 0.0023,
      "reward": 1.954437494277954,
      "reward_std": 0.02436612918972969,
      "rewards/accuracy_reward": 0.7544374465942383,
      "rewards/format_reward": 1.0,
      "step": 675
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.0,
      "completion_length": 416.75,
      "epoch": 0.009324009324009324,
      "grad_norm": 1.6872785109755712,
      "kl": 0.052978515625,
      "learning_rate": 9.997855065183182e-07,
      "loss": 0.0021,
      "reward": 2.0685625076293945,
      "reward_std": 0.015411928296089172,
      "rewards/accuracy_reward": 0.8685625195503235,
      "rewards/format_reward": 1.0,
      "step": 676
    },
    {
      "all_correct": 0.75,
      "all_wrong": 0.0,
      "completion_length": 431.125,
      "epoch": 0.009337802237210521,
      "grad_norm": 2.2346468409405906,
      "kl": 0.05712890625,
      "learning_rate": 9.99784871498387e-07,
      "loss": 0.0023,
      "reward": 2.0950937271118164,
      "reward_std": 0.034140318632125854,
      "rewards/accuracy_reward": 0.8950937986373901,
      "rewards/format_reward": 1.0,
      "step": 677
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.0,
      "completion_length": 433.78125,
      "epoch": 0.009351595150411719,
      "grad_norm": 2.0608301032918446,
      "kl": 0.05126953125,
      "learning_rate": 9.997842355400407e-07,
      "loss": 0.002,
      "reward": 2.0921249389648438,
      "reward_std": 0.04572833329439163,
      "rewards/accuracy_reward": 0.8983750343322754,
      "rewards/format_reward": 1.0,
      "step": 678
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.0,
      "completion_length": 425.4375,
      "epoch": 0.009365388063612916,
      "grad_norm": 2.551873666217073,
      "kl": 0.053466796875,
      "learning_rate": 9.99783598643281e-07,
      "loss": 0.0021,
      "reward": 1.9982187747955322,
      "reward_std": 0.030461709946393967,
      "rewards/accuracy_reward": 0.7982187271118164,
      "rewards/format_reward": 1.0,
      "step": 679
    },
    {
      "all_correct": 1.0,
      "all_wrong": 0.0,
      "completion_length": 427.71875,
      "epoch": 0.009379180976814113,
      "grad_norm": 2.2994885154254847,
      "kl": 0.0556640625,
      "learning_rate": 9.997829608081088e-07,
      "loss": 0.0022,
      "reward": 2.111656427383423,
      "reward_std": 0.01765572652220726,
      "rewards/accuracy_reward": 0.9116563200950623,
      "rewards/format_reward": 1.0,
      "step": 680
    },
    {
      "all_correct": 0.75,
      "all_wrong": 0.0,
      "completion_length": 428.90625,
      "epoch": 0.00939297389001531,
      "grad_norm": 1.755166055642458,
      "kl": 0.060546875,
      "learning_rate": 9.997823220345255e-07,
      "loss": 0.0024,
      "reward": 2.1281561851501465,
      "reward_std": 0.01356419362127781,
      "rewards/accuracy_reward": 0.9281562566757202,
      "rewards/format_reward": 1.0,
      "step": 681
    },
    {
      "all_correct": 0.75,
      "all_wrong": 0.0,
      "completion_length": 427.75,
      "epoch": 0.009406766803216508,
      "grad_norm": 2.439398119219092,
      "kl": 0.052734375,
      "learning_rate": 9.99781682322532e-07,
      "loss": 0.0021,
      "reward": 2.07603120803833,
      "reward_std": 0.0280348751693964,
      "rewards/accuracy_reward": 0.876031219959259,
      "rewards/format_reward": 1.0,
      "step": 682
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.0,
      "completion_length": 414.25,
      "epoch": 0.009420559716417705,
      "grad_norm": 2.0539492625115163,
      "kl": 0.05419921875,
      "learning_rate": 9.997810416721296e-07,
      "loss": 0.0022,
      "reward": 2.0603437423706055,
      "reward_std": 0.068871408700943,
      "rewards/accuracy_reward": 0.8790937662124634,
      "rewards/format_reward": 1.0,
      "step": 683
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.0,
      "completion_length": 434.65625,
      "epoch": 0.009434352629618902,
      "grad_norm": 3.80888034345577,
      "kl": 0.05517578125,
      "learning_rate": 9.997804000833197e-07,
      "loss": 0.0022,
      "reward": 2.1111249923706055,
      "reward_std": 0.0444219671189785,
      "rewards/accuracy_reward": 0.9236249923706055,
      "rewards/format_reward": 1.0,
      "step": 684
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.0,
      "completion_length": 416.0,
      "epoch": 0.0094481455428201,
      "grad_norm": 2.0338356248523928,
      "kl": 0.056640625,
      "learning_rate": 9.997797575561033e-07,
      "loss": 0.0023,
      "reward": 1.9871562719345093,
      "reward_std": 0.025368230417370796,
      "rewards/accuracy_reward": 0.7871562242507935,
      "rewards/format_reward": 1.0,
      "step": 685
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.0,
      "completion_length": 433.90625,
      "epoch": 0.009461938456021297,
      "grad_norm": 14.893743614147475,
      "kl": 0.046630859375,
      "learning_rate": 9.99779114090482e-07,
      "loss": 0.0019,
      "reward": 2.054281234741211,
      "reward_std": 0.03852001577615738,
      "rewards/accuracy_reward": 0.860531210899353,
      "rewards/format_reward": 1.0,
      "step": 686
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.0,
      "completion_length": 427.59375,
      "epoch": 0.009475731369222494,
      "grad_norm": 4.024717281836114,
      "kl": 0.05712890625,
      "learning_rate": 9.997784696864563e-07,
      "loss": 0.0023,
      "reward": 1.9925625324249268,
      "reward_std": 0.034247685223817825,
      "rewards/accuracy_reward": 0.7925624847412109,
      "rewards/format_reward": 1.0,
      "step": 687
    },
    {
      "all_correct": 0.25,
      "all_wrong": 0.0,
      "completion_length": 441.5,
      "epoch": 0.009489524282423691,
      "grad_norm": 1.9772025997395857,
      "kl": 0.047119140625,
      "learning_rate": 9.99777824344028e-07,
      "loss": 0.0019,
      "reward": 2.0151562690734863,
      "reward_std": 0.06658585369586945,
      "rewards/accuracy_reward": 0.8276562690734863,
      "rewards/format_reward": 1.0,
      "step": 688
    },
    {
      "all_correct": 1.0,
      "all_wrong": 0.0,
      "completion_length": 420.78125,
      "epoch": 0.009503317195624889,
      "grad_norm": 1.988712217809896,
      "kl": 0.0546875,
      "learning_rate": 9.99777178063198e-07,
      "loss": 0.0022,
      "reward": 2.114187717437744,
      "reward_std": 0.026240374892950058,
      "rewards/accuracy_reward": 0.9141875505447388,
      "rewards/format_reward": 1.0,
      "step": 689
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.0,
      "completion_length": 431.6875,
      "epoch": 0.009517110108826086,
      "grad_norm": 2.703541324250646,
      "kl": 0.05419921875,
      "learning_rate": 9.997765308439677e-07,
      "loss": 0.0022,
      "reward": 2.0669374465942383,
      "reward_std": 0.03413967788219452,
      "rewards/accuracy_reward": 0.8731874227523804,
      "rewards/format_reward": 1.0,
      "step": 690
    },
    {
      "all_correct": 0.75,
      "all_wrong": 0.0,
      "completion_length": 414.6875,
      "epoch": 0.009530903022027283,
      "grad_norm": 3.6799241491006187,
      "kl": 0.05810546875,
      "learning_rate": 9.99775882686338e-07,
      "loss": 0.0023,
      "reward": 2.0754687786102295,
      "reward_std": 0.02775740996003151,
      "rewards/accuracy_reward": 0.8754687309265137,
      "rewards/format_reward": 1.0,
      "step": 691
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.0,
      "completion_length": 431.21875,
      "epoch": 0.00954469593522848,
      "grad_norm": 1.890937507143549,
      "kl": 0.049560546875,
      "learning_rate": 9.997752335903106e-07,
      "loss": 0.002,
      "reward": 2.0451250076293945,
      "reward_std": 0.0170753076672554,
      "rewards/accuracy_reward": 0.8451249599456787,
      "rewards/format_reward": 1.0,
      "step": 692
    },
    {
      "all_correct": 1.0,
      "all_wrong": 0.0,
      "completion_length": 405.8125,
      "epoch": 0.009558488848429678,
      "grad_norm": 3.194346189271351,
      "kl": 0.05517578125,
      "learning_rate": 9.997745835558865e-07,
      "loss": 0.0022,
      "reward": 2.118000030517578,
      "reward_std": 0.03149932622909546,
      "rewards/accuracy_reward": 0.9180000424385071,
      "rewards/format_reward": 1.0,
      "step": 693
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.0,
      "completion_length": 414.375,
      "epoch": 0.009572281761630875,
      "grad_norm": 2.331340300265999,
      "kl": 0.0546875,
      "learning_rate": 9.997739325830668e-07,
      "loss": 0.0022,
      "reward": 1.9761874675750732,
      "reward_std": 0.022366223856806755,
      "rewards/accuracy_reward": 0.776187539100647,
      "rewards/format_reward": 1.0,
      "step": 694
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.0,
      "completion_length": 425.34375,
      "epoch": 0.00958607467483207,
      "grad_norm": 3.8794420702626975,
      "kl": 0.05322265625,
      "learning_rate": 9.997732806718528e-07,
      "loss": 0.0021,
      "reward": 2.000906467437744,
      "reward_std": 0.03193633258342743,
      "rewards/accuracy_reward": 0.8009061813354492,
      "rewards/format_reward": 1.0,
      "step": 695
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.0,
      "completion_length": 424.0625,
      "epoch": 0.009599867588033268,
      "grad_norm": 2.201290748917426,
      "kl": 0.0498046875,
      "learning_rate": 9.997726278222459e-07,
      "loss": 0.002,
      "reward": 2.079531192779541,
      "reward_std": 0.03386136516928673,
      "rewards/accuracy_reward": 0.87953120470047,
      "rewards/format_reward": 1.0,
      "step": 696
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.0,
      "completion_length": 410.875,
      "epoch": 0.009613660501234465,
      "grad_norm": 2.1247553847038083,
      "kl": 0.060546875,
      "learning_rate": 9.997719740342472e-07,
      "loss": 0.0024,
      "reward": 2.0337185859680176,
      "reward_std": 0.025783026590943336,
      "rewards/accuracy_reward": 0.8399688005447388,
      "rewards/format_reward": 1.0,
      "step": 697
    },
    {
      "all_correct": 0.25,
      "all_wrong": 0.0,
      "completion_length": 419.4375,
      "epoch": 0.009627453414435662,
      "grad_norm": 2.356167965383202,
      "kl": 0.0634765625,
      "learning_rate": 9.997713193078577e-07,
      "loss": 0.0025,
      "reward": 2.0381250381469727,
      "reward_std": 0.06399115175008774,
      "rewards/accuracy_reward": 0.8506250381469727,
      "rewards/format_reward": 1.0,
      "step": 698
    },
    {
      "all_correct": 1.0,
      "all_wrong": 0.0,
      "completion_length": 395.625,
      "epoch": 0.00964124632763686,
      "grad_norm": 3.843978059591917,
      "kl": 0.056396484375,
      "learning_rate": 9.99770663643079e-07,
      "loss": 0.0023,
      "reward": 2.1421561241149902,
      "reward_std": 0.04591123387217522,
      "rewards/accuracy_reward": 0.9484062790870667,
      "rewards/format_reward": 1.0,
      "step": 699
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.0,
      "completion_length": 407.65625,
      "epoch": 0.009655039240838057,
      "grad_norm": 2.255131334928212,
      "kl": 0.05615234375,
      "learning_rate": 9.99770007039912e-07,
      "loss": 0.0022,
      "reward": 2.0332188606262207,
      "reward_std": 0.03118271194398403,
      "rewards/accuracy_reward": 0.8394687175750732,
      "rewards/format_reward": 1.0,
      "step": 700
    },
    {
      "all_correct": 0.25,
      "all_wrong": 0.0,
      "completion_length": 398.75,
      "epoch": 0.009668832154039254,
      "grad_norm": 1.6758072177209355,
      "kl": 0.05712890625,
      "learning_rate": 9.997693494983582e-07,
      "loss": 0.0023,
      "reward": 1.9993125200271606,
      "reward_std": 0.03307871147990227,
      "rewards/accuracy_reward": 0.8055624961853027,
      "rewards/format_reward": 1.0,
      "step": 701
    },
    {
      "all_correct": 0.25,
      "all_wrong": 0.0,
      "completion_length": 418.84375,
      "epoch": 0.009682625067240451,
      "grad_norm": 10.804572953693194,
      "kl": 0.0537109375,
      "learning_rate": 9.997686910184185e-07,
      "loss": 0.0021,
      "reward": 1.9668437242507935,
      "reward_std": 0.04112984985113144,
      "rewards/accuracy_reward": 0.7730937600135803,
      "rewards/format_reward": 1.0,
      "step": 702
    },
    {
      "all_correct": 0.75,
      "all_wrong": 0.0,
      "completion_length": 426.25,
      "epoch": 0.009696417980441649,
      "grad_norm": 2.089305158194791,
      "kl": 0.0498046875,
      "learning_rate": 9.997680316000946e-07,
      "loss": 0.002,
      "reward": 2.128281354904175,
      "reward_std": 0.036959290504455566,
      "rewards/accuracy_reward": 0.9345312118530273,
      "rewards/format_reward": 1.0,
      "step": 703
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.0,
      "completion_length": 398.03125,
      "epoch": 0.009710210893642846,
      "grad_norm": 2.3470899762622564,
      "kl": 0.05712890625,
      "learning_rate": 9.997673712433874e-07,
      "loss": 0.0023,
      "reward": 1.9417812824249268,
      "reward_std": 0.02425316348671913,
      "rewards/accuracy_reward": 0.7417812347412109,
      "rewards/format_reward": 1.0,
      "step": 704
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.0,
      "completion_length": 402.15625,
      "epoch": 0.009724003806844043,
      "grad_norm": 3.184750897642642,
      "kl": 0.05859375,
      "learning_rate": 9.997667099482983e-07,
      "loss": 0.0023,
      "reward": 2.01743745803833,
      "reward_std": 0.026041537523269653,
      "rewards/accuracy_reward": 0.8174375295639038,
      "rewards/format_reward": 1.0,
      "step": 705
    },
    {
      "all_correct": 0.75,
      "all_wrong": 0.0,
      "completion_length": 398.25,
      "epoch": 0.00973779672004524,
      "grad_norm": 2.278684680388614,
      "kl": 0.0625,
      "learning_rate": 9.997660477148284e-07,
      "loss": 0.0025,
      "reward": 2.0754687786102295,
      "reward_std": 0.039515845477581024,
      "rewards/accuracy_reward": 0.8754687905311584,
      "rewards/format_reward": 1.0,
      "step": 706
    },
    {
      "all_correct": 0.75,
      "all_wrong": 0.0,
      "completion_length": 405.1875,
      "epoch": 0.009751589633246438,
      "grad_norm": 1.8181294863490107,
      "kl": 0.052734375,
      "learning_rate": 9.997653845429792e-07,
      "loss": 0.0021,
      "reward": 2.13993763923645,
      "reward_std": 0.015603876672685146,
      "rewards/accuracy_reward": 0.9399375319480896,
      "rewards/format_reward": 1.0,
      "step": 707
    },
    {
      "all_correct": 0.25,
      "all_wrong": 0.0,
      "completion_length": 410.75,
      "epoch": 0.009765382546447635,
      "grad_norm": 4.958501690518395,
      "kl": 0.0615234375,
      "learning_rate": 9.997647204327515e-07,
      "loss": 0.0025,
      "reward": 1.9874688386917114,
      "reward_std": 0.023501278832554817,
      "rewards/accuracy_reward": 0.7874687910079956,
      "rewards/format_reward": 1.0,
      "step": 708
    },
    {
      "all_correct": 0.75,
      "all_wrong": 0.0,
      "completion_length": 430.96875,
      "epoch": 0.009779175459648832,
      "grad_norm": 2.9193274904743327,
      "kl": 0.0498046875,
      "learning_rate": 9.997640553841471e-07,
      "loss": 0.002,
      "reward": 2.1104063987731934,
      "reward_std": 0.04291394725441933,
      "rewards/accuracy_reward": 0.9291562438011169,
      "rewards/format_reward": 1.0,
      "step": 709
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.0,
      "completion_length": 399.65625,
      "epoch": 0.00979296837285003,
      "grad_norm": 3.403500909492158,
      "kl": 0.059326171875,
      "learning_rate": 9.997633893971668e-07,
      "loss": 0.0024,
      "reward": 2.084843873977661,
      "reward_std": 0.04556925222277641,
      "rewards/accuracy_reward": 0.8973437547683716,
      "rewards/format_reward": 1.0,
      "step": 710
    },
    {
      "all_correct": 0.75,
      "all_wrong": 0.0,
      "completion_length": 413.3125,
      "epoch": 0.009806761286051227,
      "grad_norm": 6.669534614538442,
      "kl": 0.05615234375,
      "learning_rate": 9.99762722471812e-07,
      "loss": 0.0023,
      "reward": 2.0758438110351562,
      "reward_std": 0.029760783538222313,
      "rewards/accuracy_reward": 0.8758436441421509,
      "rewards/format_reward": 1.0,
      "step": 711
    },
    {
      "all_correct": 0.75,
      "all_wrong": 0.0,
      "completion_length": 411.34375,
      "epoch": 0.009820554199252424,
      "grad_norm": 2.5793884394451636,
      "kl": 0.051513671875,
      "learning_rate": 9.99762054608084e-07,
      "loss": 0.0021,
      "reward": 2.076531410217285,
      "reward_std": 0.051275793462991714,
      "rewards/accuracy_reward": 0.8890312910079956,
      "rewards/format_reward": 1.0,
      "step": 712
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.0,
      "completion_length": 402.21875,
      "epoch": 0.009834347112453621,
      "grad_norm": 3.030314055937417,
      "kl": 0.052001953125,
      "learning_rate": 9.997613858059842e-07,
      "loss": 0.0021,
      "reward": 2.060281276702881,
      "reward_std": 0.055342938750982285,
      "rewards/accuracy_reward": 0.8727812767028809,
      "rewards/format_reward": 1.0,
      "step": 713
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.0,
      "completion_length": 406.84375,
      "epoch": 0.009848140025654819,
      "grad_norm": 4.943337065676028,
      "kl": 0.052490234375,
      "learning_rate": 9.997607160655133e-07,
      "loss": 0.0021,
      "reward": 2.0074687004089355,
      "reward_std": 0.014242958277463913,
      "rewards/accuracy_reward": 0.8074687719345093,
      "rewards/format_reward": 1.0,
      "step": 714
    },
    {
      "all_correct": 0.75,
      "all_wrong": 0.0,
      "completion_length": 400.53125,
      "epoch": 0.009861932938856016,
      "grad_norm": 1.8960911088419596,
      "kl": 0.05517578125,
      "learning_rate": 9.997600453866732e-07,
      "loss": 0.0022,
      "reward": 2.0877187252044678,
      "reward_std": 0.021724281832575798,
      "rewards/accuracy_reward": 0.8939687609672546,
      "rewards/format_reward": 1.0,
      "step": 715
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.0,
      "completion_length": 392.125,
      "epoch": 0.009875725852057213,
      "grad_norm": 6.662629453034917,
      "kl": 0.0556640625,
      "learning_rate": 9.99759373769465e-07,
      "loss": 0.0022,
      "reward": 2.0525624752044678,
      "reward_std": 0.031142540276050568,
      "rewards/accuracy_reward": 0.8525625467300415,
      "rewards/format_reward": 1.0,
      "step": 716
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.0,
      "completion_length": 388.75,
      "epoch": 0.00988951876525841,
      "grad_norm": 5.982517409715113,
      "kl": 0.056396484375,
      "learning_rate": 9.997587012138895e-07,
      "loss": 0.0023,
      "reward": 1.9877188205718994,
      "reward_std": 0.0749661847949028,
      "rewards/accuracy_reward": 0.8002187609672546,
      "rewards/format_reward": 1.0,
      "step": 717
    },
    {
      "all_correct": 0.75,
      "all_wrong": 0.0,
      "completion_length": 406.53125,
      "epoch": 0.009903311678459608,
      "grad_norm": 2.10317602669681,
      "kl": 0.06103515625,
      "learning_rate": 9.997580277199486e-07,
      "loss": 0.0024,
      "reward": 2.118468761444092,
      "reward_std": 0.02256305329501629,
      "rewards/accuracy_reward": 0.918468713760376,
      "rewards/format_reward": 1.0,
      "step": 718
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.0,
      "completion_length": 399.625,
      "epoch": 0.009917104591660805,
      "grad_norm": 1.5453569358256356,
      "kl": 0.05322265625,
      "learning_rate": 9.99757353287643e-07,
      "loss": 0.0021,
      "reward": 2.0855937004089355,
      "reward_std": 0.019628841429948807,
      "rewards/accuracy_reward": 0.8918437957763672,
      "rewards/format_reward": 1.0,
      "step": 719
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.0,
      "completion_length": 396.46875,
      "epoch": 0.009930897504862002,
      "grad_norm": 2.899620411999658,
      "kl": 0.048828125,
      "learning_rate": 9.997566779169746e-07,
      "loss": 0.002,
      "reward": 2.058375120162964,
      "reward_std": 0.018247393891215324,
      "rewards/accuracy_reward": 0.8583749532699585,
      "rewards/format_reward": 1.0,
      "step": 720
    },
    {
      "all_correct": 0.25,
      "all_wrong": 0.0,
      "completion_length": 402.71875,
      "epoch": 0.0099446904180632,
      "grad_norm": 5.34747389152533,
      "kl": 0.05908203125,
      "learning_rate": 9.997560016079442e-07,
      "loss": 0.0024,
      "reward": 2.0670623779296875,
      "reward_std": 0.04352187365293503,
      "rewards/accuracy_reward": 0.8733124732971191,
      "rewards/format_reward": 1.0,
      "step": 721
    },
    {
      "all_correct": 0.75,
      "all_wrong": 0.0,
      "completion_length": 391.21875,
      "epoch": 0.009958483331264397,
      "grad_norm": 4.095829187926484,
      "kl": 0.06494140625,
      "learning_rate": 9.997553243605532e-07,
      "loss": 0.0026,
      "reward": 2.0938751697540283,
      "reward_std": 0.036793891340494156,
      "rewards/accuracy_reward": 0.893875002861023,
      "rewards/format_reward": 1.0,
      "step": 722
    },
    {
      "all_correct": 0.25,
      "all_wrong": 0.0,
      "completion_length": 400.15625,
      "epoch": 0.009972276244465594,
      "grad_norm": 2.8405226678825852,
      "kl": 0.052734375,
      "learning_rate": 9.997546461748028e-07,
      "loss": 0.0021,
      "reward": 2.002812385559082,
      "reward_std": 0.03477508947253227,
      "rewards/accuracy_reward": 0.8028125762939453,
      "rewards/format_reward": 1.0,
      "step": 723
    },
    {
      "all_correct": 0.75,
      "all_wrong": 0.0,
      "completion_length": 409.0625,
      "epoch": 0.009986069157666791,
      "grad_norm": 2.184283144518582,
      "kl": 0.050537109375,
      "learning_rate": 9.997539670506942e-07,
      "loss": 0.002,
      "reward": 2.029843807220459,
      "reward_std": 0.01599831134080887,
      "rewards/accuracy_reward": 0.8298437595367432,
      "rewards/format_reward": 1.0,
      "step": 724
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.0,
      "completion_length": 405.96875,
      "epoch": 0.009999862070867989,
      "grad_norm": 2.7305813676528734,
      "kl": 0.0595703125,
      "learning_rate": 9.99753286988229e-07,
      "loss": 0.0024,
      "reward": 2.0062499046325684,
      "reward_std": 0.011853743344545364,
      "rewards/accuracy_reward": 0.8062499761581421,
      "rewards/format_reward": 1.0,
      "step": 725
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.0,
      "completion_length": 403.75,
      "epoch": 0.010013654984069186,
      "grad_norm": 6.0307912306653595,
      "kl": 0.05029296875,
      "learning_rate": 9.997526059874084e-07,
      "loss": 0.002,
      "reward": 2.0692501068115234,
      "reward_std": 0.03133557736873627,
      "rewards/accuracy_reward": 0.8755000233650208,
      "rewards/format_reward": 1.0,
      "step": 726
    },
    {
      "all_correct": 0.75,
      "all_wrong": 0.0,
      "completion_length": 407.375,
      "epoch": 0.010027447897270383,
      "grad_norm": 2.588161925113926,
      "kl": 0.059814453125,
      "learning_rate": 9.997519240482333e-07,
      "loss": 0.0024,
      "reward": 2.10756254196167,
      "reward_std": 0.020189443603157997,
      "rewards/accuracy_reward": 0.9075624942779541,
      "rewards/format_reward": 1.0,
      "step": 727
    },
    {
      "all_correct": 0.75,
      "all_wrong": 0.0,
      "completion_length": 408.6875,
      "epoch": 0.01004124081047158,
      "grad_norm": 8.244247699201978,
      "kl": 0.05322265625,
      "learning_rate": 9.997512411707055e-07,
      "loss": 0.0021,
      "reward": 2.0844063758850098,
      "reward_std": 0.026970503851771355,
      "rewards/accuracy_reward": 0.8844062089920044,
      "rewards/format_reward": 1.0,
      "step": 728
    },
    {
      "all_correct": 1.0,
      "all_wrong": 0.0,
      "completion_length": 394.40625,
      "epoch": 0.010055033723672778,
      "grad_norm": 2.2085553536407003,
      "kl": 0.05126953125,
      "learning_rate": 9.997505573548258e-07,
      "loss": 0.0021,
      "reward": 2.1332812309265137,
      "reward_std": 0.028340646997094154,
      "rewards/accuracy_reward": 0.9332813024520874,
      "rewards/format_reward": 1.0,
      "step": 729
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.0,
      "completion_length": 418.875,
      "epoch": 0.010068826636873975,
      "grad_norm": 3.971849469983568,
      "kl": 0.056396484375,
      "learning_rate": 9.997498726005957e-07,
      "loss": 0.0023,
      "reward": 1.9782187938690186,
      "reward_std": 0.05522511154413223,
      "rewards/accuracy_reward": 0.7782187461853027,
      "rewards/format_reward": 1.0,
      "step": 730
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.0,
      "completion_length": 410.4375,
      "epoch": 0.010082619550075172,
      "grad_norm": 2.5351340929204755,
      "kl": 0.0576171875,
      "learning_rate": 9.997491869080166e-07,
      "loss": 0.0023,
      "reward": 2.088562488555908,
      "reward_std": 0.0400303453207016,
      "rewards/accuracy_reward": 0.8948124647140503,
      "rewards/format_reward": 1.0,
      "step": 731
    },
    {
      "all_correct": 0.75,
      "all_wrong": 0.0,
      "completion_length": 416.8125,
      "epoch": 0.01009641246327637,
      "grad_norm": 3.3568771007081986,
      "kl": 0.05517578125,
      "learning_rate": 9.997485002770898e-07,
      "loss": 0.0022,
      "reward": 2.0677499771118164,
      "reward_std": 0.024040717631578445,
      "rewards/accuracy_reward": 0.8677499890327454,
      "rewards/format_reward": 1.0,
      "step": 732
    },
    {
      "all_correct": 0.75,
      "all_wrong": 0.0,
      "completion_length": 403.1875,
      "epoch": 0.010110205376477565,
      "grad_norm": 4.250653356173924,
      "kl": 0.057373046875,
      "learning_rate": 9.997478127078162e-07,
      "loss": 0.0023,
      "reward": 2.102656364440918,
      "reward_std": 0.01822405681014061,
      "rewards/accuracy_reward": 0.9026561975479126,
      "rewards/format_reward": 1.0,
      "step": 733
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.0,
      "completion_length": 400.1875,
      "epoch": 0.010123998289678762,
      "grad_norm": 1.8931909200220496,
      "kl": 0.052978515625,
      "learning_rate": 9.997471242001975e-07,
      "loss": 0.0021,
      "reward": 2.045187473297119,
      "reward_std": 0.027692124247550964,
      "rewards/accuracy_reward": 0.8451874852180481,
      "rewards/format_reward": 1.0,
      "step": 734
    },
    {
      "all_correct": 1.0,
      "all_wrong": 0.0,
      "completion_length": 406.53125,
      "epoch": 0.01013779120287996,
      "grad_norm": 2.076250263276435,
      "kl": 0.0498046875,
      "learning_rate": 9.997464347542348e-07,
      "loss": 0.002,
      "reward": 2.143531322479248,
      "reward_std": 0.03511849790811539,
      "rewards/accuracy_reward": 0.943531334400177,
      "rewards/format_reward": 1.0,
      "step": 735
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.0,
      "completion_length": 401.96875,
      "epoch": 0.010151584116081157,
      "grad_norm": 2.531616358469332,
      "kl": 0.061279296875,
      "learning_rate": 9.997457443699296e-07,
      "loss": 0.0025,
      "reward": 2.0248751640319824,
      "reward_std": 0.028868505731225014,
      "rewards/accuracy_reward": 0.824874997138977,
      "rewards/format_reward": 1.0,
      "step": 736
    },
    {
      "all_correct": 0.75,
      "all_wrong": 0.0,
      "completion_length": 388.84375,
      "epoch": 0.010165377029282354,
      "grad_norm": 2.2248606975885394,
      "kl": 0.052734375,
      "learning_rate": 9.997450530472829e-07,
      "loss": 0.0021,
      "reward": 2.115875244140625,
      "reward_std": 0.024346042424440384,
      "rewards/accuracy_reward": 0.9158750176429749,
      "rewards/format_reward": 1.0,
      "step": 737
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.0,
      "completion_length": 419.4375,
      "epoch": 0.010179169942483551,
      "grad_norm": 3.990291579350817,
      "kl": 0.06396484375,
      "learning_rate": 9.997443607862961e-07,
      "loss": 0.0026,
      "reward": 2.0698437690734863,
      "reward_std": 0.030115721747279167,
      "rewards/accuracy_reward": 0.8698437213897705,
      "rewards/format_reward": 1.0,
      "step": 738
    },
    {
      "all_correct": 0.75,
      "all_wrong": 0.0,
      "completion_length": 404.0625,
      "epoch": 0.010192962855684749,
      "grad_norm": 2.1648224720026317,
      "kl": 0.0546875,
      "learning_rate": 9.997436675869708e-07,
      "loss": 0.0022,
      "reward": 2.111593723297119,
      "reward_std": 0.01349850557744503,
      "rewards/accuracy_reward": 0.9115937948226929,
      "rewards/format_reward": 1.0,
      "step": 739
    },
    {
      "all_correct": 0.75,
      "all_wrong": 0.0,
      "completion_length": 400.875,
      "epoch": 0.010206755768885946,
      "grad_norm": 8.778738681829669,
      "kl": 0.05322265625,
      "learning_rate": 9.997429734493078e-07,
      "loss": 0.0021,
      "reward": 2.0667500495910645,
      "reward_std": 0.03505605831742287,
      "rewards/accuracy_reward": 0.8667500019073486,
      "rewards/format_reward": 1.0,
      "step": 740
    },
    {
      "all_correct": 1.0,
      "all_wrong": 0.0,
      "completion_length": 409.65625,
      "epoch": 0.010220548682087143,
      "grad_norm": 3.157562387234862,
      "kl": 0.0693359375,
      "learning_rate": 9.997422783733088e-07,
      "loss": 0.0028,
      "reward": 2.147312641143799,
      "reward_std": 0.01136963814496994,
      "rewards/accuracy_reward": 0.9473124742507935,
      "rewards/format_reward": 1.0,
      "step": 741
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.0,
      "completion_length": 405.5,
      "epoch": 0.01023434159528834,
      "grad_norm": 3.628114583517919,
      "kl": 0.060546875,
      "learning_rate": 9.997415823589749e-07,
      "loss": 0.0024,
      "reward": 2.0112812519073486,
      "reward_std": 0.037713997066020966,
      "rewards/accuracy_reward": 0.8112813234329224,
      "rewards/format_reward": 1.0,
      "step": 742
    },
    {
      "all_correct": 1.0,
      "all_wrong": 0.0,
      "completion_length": 402.25,
      "epoch": 0.010248134508489538,
      "grad_norm": 2.744615880699793,
      "kl": 0.054931640625,
      "learning_rate": 9.997408854063074e-07,
      "loss": 0.0022,
      "reward": 2.139531373977661,
      "reward_std": 0.02022724784910679,
      "rewards/accuracy_reward": 0.9395312666893005,
      "rewards/format_reward": 1.0,
      "step": 743
    },
    {
      "all_correct": 1.0,
      "all_wrong": 0.0,
      "completion_length": 420.875,
      "epoch": 0.010261927421690735,
      "grad_norm": 2.3453082636299487,
      "kl": 0.05419921875,
      "learning_rate": 9.997401875153077e-07,
      "loss": 0.0022,
      "reward": 2.168062686920166,
      "reward_std": 0.012410825118422508,
      "rewards/accuracy_reward": 0.9680625200271606,
      "rewards/format_reward": 1.0,
      "step": 744
    },
    {
      "all_correct": 0.75,
      "all_wrong": 0.0,
      "completion_length": 421.21875,
      "epoch": 0.010275720334891932,
      "grad_norm": 7.420707809296835,
      "kl": 0.051025390625,
      "learning_rate": 9.99739488685977e-07,
      "loss": 0.002,
      "reward": 2.1364688873291016,
      "reward_std": 0.018790986388921738,
      "rewards/accuracy_reward": 0.936468780040741,
      "rewards/format_reward": 1.0,
      "step": 745
    },
    {
      "all_correct": 0.75,
      "all_wrong": 0.0,
      "completion_length": 413.28125,
      "epoch": 0.01028951324809313,
      "grad_norm": 2.5412024334759855,
      "kl": 0.058837890625,
      "learning_rate": 9.99738788918317e-07,
      "loss": 0.0023,
      "reward": 2.1006250381469727,
      "reward_std": 0.029206018894910812,
      "rewards/accuracy_reward": 0.9068750143051147,
      "rewards/format_reward": 1.0,
      "step": 746
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.0,
      "completion_length": 395.40625,
      "epoch": 0.010303306161294327,
      "grad_norm": 2.6938347949444337,
      "kl": 0.058837890625,
      "learning_rate": 9.997380882123285e-07,
      "loss": 0.0024,
      "reward": 1.9860000610351562,
      "reward_std": 0.033022359013557434,
      "rewards/accuracy_reward": 0.7860000133514404,
      "rewards/format_reward": 1.0,
      "step": 747
    },
    {
      "all_correct": 0.75,
      "all_wrong": 0.0,
      "completion_length": 399.6875,
      "epoch": 0.010317099074495524,
      "grad_norm": 3.2975122364936538,
      "kl": 0.053466796875,
      "learning_rate": 9.99737386568013e-07,
      "loss": 0.0021,
      "reward": 2.0756564140319824,
      "reward_std": 0.016209229826927185,
      "rewards/accuracy_reward": 0.875656247138977,
      "rewards/format_reward": 1.0,
      "step": 748
    },
    {
      "all_correct": 0.25,
      "all_wrong": 0.0,
      "completion_length": 385.0625,
      "epoch": 0.010330891987696721,
      "grad_norm": 3.0682635457077487,
      "kl": 0.056640625,
      "learning_rate": 9.997366839853718e-07,
      "loss": 0.0023,
      "reward": 1.97740638256073,
      "reward_std": 0.04185992479324341,
      "rewards/accuracy_reward": 0.7899062633514404,
      "rewards/format_reward": 1.0,
      "step": 749
    },
    {
      "all_correct": 0.75,
      "all_wrong": 0.0,
      "completion_length": 396.78125,
      "epoch": 0.010344684900897919,
      "grad_norm": 7.465632250146028,
      "kl": 0.0517578125,
      "learning_rate": 9.997359804644064e-07,
      "loss": 0.0021,
      "reward": 2.0840938091278076,
      "reward_std": 0.021526526659727097,
      "rewards/accuracy_reward": 0.8840937614440918,
      "rewards/format_reward": 1.0,
      "step": 750
    },
    {
      "all_correct": 1.0,
      "all_wrong": 0.0,
      "completion_length": 396.0,
      "epoch": 0.010358477814099116,
      "grad_norm": 2.715302356725908,
      "kl": 0.05419921875,
      "learning_rate": 9.997352760051178e-07,
      "loss": 0.0022,
      "reward": 2.1145310401916504,
      "reward_std": 0.03436526656150818,
      "rewards/accuracy_reward": 0.9207813143730164,
      "rewards/format_reward": 1.0,
      "step": 751
    },
    {
      "all_correct": 0.75,
      "all_wrong": 0.0,
      "completion_length": 396.5,
      "epoch": 0.010372270727300313,
      "grad_norm": 2.3986932526547644,
      "kl": 0.052001953125,
      "learning_rate": 9.997345706075077e-07,
      "loss": 0.0021,
      "reward": 2.1231250762939453,
      "reward_std": 0.015583636239171028,
      "rewards/accuracy_reward": 0.9231250286102295,
      "rewards/format_reward": 1.0,
      "step": 752
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.0,
      "completion_length": 384.3125,
      "epoch": 0.01038606364050151,
      "grad_norm": 2.4024529943184145,
      "kl": 0.0537109375,
      "learning_rate": 9.997338642715771e-07,
      "loss": 0.0022,
      "reward": 2.122406244277954,
      "reward_std": 0.04960613697767258,
      "rewards/accuracy_reward": 0.9349062442779541,
      "rewards/format_reward": 1.0,
      "step": 753
    },
    {
      "all_correct": 0.75,
      "all_wrong": 0.0,
      "completion_length": 398.875,
      "epoch": 0.010399856553702708,
      "grad_norm": 3.143490293985404,
      "kl": 0.0517578125,
      "learning_rate": 9.997331569973274e-07,
      "loss": 0.0021,
      "reward": 2.130312442779541,
      "reward_std": 0.018957635387778282,
      "rewards/accuracy_reward": 0.9303125143051147,
      "rewards/format_reward": 1.0,
      "step": 754
    },
    {
      "all_correct": 0.75,
      "all_wrong": 0.0,
      "completion_length": 404.96875,
      "epoch": 0.010413649466903905,
      "grad_norm": 4.741382801510338,
      "kl": 0.06298828125,
      "learning_rate": 9.997324487847603e-07,
      "loss": 0.0025,
      "reward": 2.081218719482422,
      "reward_std": 0.023498455062508583,
      "rewards/accuracy_reward": 0.8812187314033508,
      "rewards/format_reward": 1.0,
      "step": 755
    },
    {
      "all_correct": 0.25,
      "all_wrong": 0.0,
      "completion_length": 406.9375,
      "epoch": 0.010427442380105102,
      "grad_norm": 2.928107559033569,
      "kl": 0.07666015625,
      "learning_rate": 9.997317396338764e-07,
      "loss": 0.0031,
      "reward": 1.9674999713897705,
      "reward_std": 0.03542211651802063,
      "rewards/accuracy_reward": 0.7737500071525574,
      "rewards/format_reward": 1.0,
      "step": 756
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.0,
      "completion_length": 406.59375,
      "epoch": 0.0104412352933063,
      "grad_norm": 3.3315302316357243,
      "kl": 0.05419921875,
      "learning_rate": 9.997310295446777e-07,
      "loss": 0.0022,
      "reward": 1.958031177520752,
      "reward_std": 0.015777796506881714,
      "rewards/accuracy_reward": 0.7642812728881836,
      "rewards/format_reward": 1.0,
      "step": 757
    },
    {
      "all_correct": 0.25,
      "all_wrong": 0.0,
      "completion_length": 411.78125,
      "epoch": 0.010455028206507497,
      "grad_norm": 18.474726687302905,
      "kl": 0.068359375,
      "learning_rate": 9.997303185171653e-07,
      "loss": 0.0027,
      "reward": 1.986781120300293,
      "reward_std": 0.015298012644052505,
      "rewards/accuracy_reward": 0.7867811918258667,
      "rewards/format_reward": 1.0,
      "step": 758
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.0,
      "completion_length": 415.53125,
      "epoch": 0.010468821119708694,
      "grad_norm": 2.1589338309340205,
      "kl": 0.060791015625,
      "learning_rate": 9.997296065513403e-07,
      "loss": 0.0024,
      "reward": 2.0800938606262207,
      "reward_std": 0.01615123450756073,
      "rewards/accuracy_reward": 0.8800936937332153,
      "rewards/format_reward": 1.0,
      "step": 759
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.0,
      "completion_length": 407.28125,
      "epoch": 0.010482614032909891,
      "grad_norm": 3.384677172187868,
      "kl": 0.055419921875,
      "learning_rate": 9.997288936472043e-07,
      "loss": 0.0022,
      "reward": 2.0602502822875977,
      "reward_std": 0.03399854525923729,
      "rewards/accuracy_reward": 0.8665000200271606,
      "rewards/format_reward": 1.0,
      "step": 760
    },
    {
      "all_correct": 0.25,
      "all_wrong": 0.0,
      "completion_length": 442.5,
      "epoch": 0.010496406946111089,
      "grad_norm": 2.8940173775264744,
      "kl": 0.0625,
      "learning_rate": 9.997281798047588e-07,
      "loss": 0.0025,
      "reward": 1.9320937395095825,
      "reward_std": 0.22109809517860413,
      "rewards/accuracy_reward": 0.7820937633514404,
      "rewards/format_reward": 0.96875,
      "step": 761
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.0,
      "completion_length": 402.59375,
      "epoch": 0.010510199859312286,
      "grad_norm": 2.32633618140947,
      "kl": 0.05517578125,
      "learning_rate": 9.997274650240046e-07,
      "loss": 0.0022,
      "reward": 1.9946562051773071,
      "reward_std": 0.02311072126030922,
      "rewards/accuracy_reward": 0.7946562767028809,
      "rewards/format_reward": 1.0,
      "step": 762
    },
    {
      "all_correct": 0.25,
      "all_wrong": 0.0,
      "completion_length": 438.0,
      "epoch": 0.010523992772513483,
      "grad_norm": 3.7825694959885685,
      "kl": 0.054931640625,
      "learning_rate": 9.997267493049438e-07,
      "loss": 0.0022,
      "reward": 1.994343638420105,
      "reward_std": 0.040323495864868164,
      "rewards/accuracy_reward": 0.8005937337875366,
      "rewards/format_reward": 1.0,
      "step": 763
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.0,
      "completion_length": 416.96875,
      "epoch": 0.01053778568571468,
      "grad_norm": 3.688005427656586,
      "kl": 0.06005859375,
      "learning_rate": 9.99726032647577e-07,
      "loss": 0.0024,
      "reward": 2.0537500381469727,
      "reward_std": 0.01016139890998602,
      "rewards/accuracy_reward": 0.8537499904632568,
      "rewards/format_reward": 1.0,
      "step": 764
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.0,
      "completion_length": 424.40625,
      "epoch": 0.010551578598915878,
      "grad_norm": 2.3420805541161553,
      "kl": 0.060791015625,
      "learning_rate": 9.99725315051906e-07,
      "loss": 0.0024,
      "reward": 2.053562641143799,
      "reward_std": 0.029797010123729706,
      "rewards/accuracy_reward": 0.8598124980926514,
      "rewards/format_reward": 1.0,
      "step": 765
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.0,
      "completion_length": 440.71875,
      "epoch": 0.010565371512117075,
      "grad_norm": 2.7380140124259524,
      "kl": 0.05224609375,
      "learning_rate": 9.997245965179316e-07,
      "loss": 0.0021,
      "reward": 2.095156192779541,
      "reward_std": 0.032796021550893784,
      "rewards/accuracy_reward": 0.9014062881469727,
      "rewards/format_reward": 1.0,
      "step": 766
    },
    {
      "all_correct": 0.75,
      "all_wrong": 0.0,
      "completion_length": 435.28125,
      "epoch": 0.010579164425318272,
      "grad_norm": 2.1085361831035407,
      "kl": 0.050048828125,
      "learning_rate": 9.997238770456562e-07,
      "loss": 0.002,
      "reward": 2.065093755722046,
      "reward_std": 0.010781139135360718,
      "rewards/accuracy_reward": 0.8650937080383301,
      "rewards/format_reward": 1.0,
      "step": 767
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.0,
      "completion_length": 429.4375,
      "epoch": 0.01059295733851947,
      "grad_norm": 3.910167632589713,
      "kl": 0.052978515625,
      "learning_rate": 9.997231566350802e-07,
      "loss": 0.0021,
      "reward": 2.0673437118530273,
      "reward_std": 0.01724417693912983,
      "rewards/accuracy_reward": 0.8673437237739563,
      "rewards/format_reward": 1.0,
      "step": 768
    },
    {
      "all_correct": 0.75,
      "all_wrong": 0.0,
      "completion_length": 434.3125,
      "epoch": 0.010606750251720667,
      "grad_norm": 2.3933112136668817,
      "kl": 0.054931640625,
      "learning_rate": 9.997224352862051e-07,
      "loss": 0.0022,
      "reward": 2.1377811431884766,
      "reward_std": 0.02724858559668064,
      "rewards/accuracy_reward": 0.9440312385559082,
      "rewards/format_reward": 1.0,
      "step": 769
    },
    {
      "all_correct": 1.0,
      "all_wrong": 0.0,
      "completion_length": 419.75,
      "epoch": 0.010620543164921864,
      "grad_norm": 1.7710301641581008,
      "kl": 0.05859375,
      "learning_rate": 9.997217129990325e-07,
      "loss": 0.0023,
      "reward": 2.1596250534057617,
      "reward_std": 0.030992865562438965,
      "rewards/accuracy_reward": 0.9596250057220459,
      "rewards/format_reward": 1.0,
      "step": 770
    },
    {
      "all_correct": 0.25,
      "all_wrong": 0.0,
      "completion_length": 432.25,
      "epoch": 0.01063433607812306,
      "grad_norm": 2.2610593796980893,
      "kl": 0.053955078125,
      "learning_rate": 9.997209897735638e-07,
      "loss": 0.0022,
      "reward": 2.0071563720703125,
      "reward_std": 0.028937727212905884,
      "rewards/accuracy_reward": 0.813406229019165,
      "rewards/format_reward": 1.0,
      "step": 771
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.0,
      "completion_length": 421.59375,
      "epoch": 0.010648128991324257,
      "grad_norm": 4.389775969791669,
      "kl": 0.060791015625,
      "learning_rate": 9.997202656098e-07,
      "loss": 0.0024,
      "reward": 2.0327188968658447,
      "reward_std": 0.016570717096328735,
      "rewards/accuracy_reward": 0.8327187299728394,
      "rewards/format_reward": 1.0,
      "step": 772
    },
    {
      "all_correct": 0.75,
      "all_wrong": 0.0,
      "completion_length": 421.90625,
      "epoch": 0.010661921904525454,
      "grad_norm": 1.8096586543252338,
      "kl": 0.06103515625,
      "learning_rate": 9.99719540507743e-07,
      "loss": 0.0024,
      "reward": 2.1250314712524414,
      "reward_std": 0.013041210360825062,
      "rewards/accuracy_reward": 0.9250311851501465,
      "rewards/format_reward": 1.0,
      "step": 773
    },
    {
      "all_correct": 1.0,
      "all_wrong": 0.0,
      "completion_length": 438.75,
      "epoch": 0.010675714817726651,
      "grad_norm": 2.3171812940722973,
      "kl": 0.05712890625,
      "learning_rate": 9.997188144673936e-07,
      "loss": 0.0023,
      "reward": 2.1441874504089355,
      "reward_std": 0.01430035475641489,
      "rewards/accuracy_reward": 0.9441875219345093,
      "rewards/format_reward": 1.0,
      "step": 774
    },
    {
      "all_correct": 0.25,
      "all_wrong": 0.0,
      "completion_length": 437.21875,
      "epoch": 0.010689507730927849,
      "grad_norm": 1.8798741361342544,
      "kl": 0.0556640625,
      "learning_rate": 9.997180874887535e-07,
      "loss": 0.0022,
      "reward": 2.028437614440918,
      "reward_std": 0.03181103616952896,
      "rewards/accuracy_reward": 0.8346875309944153,
      "rewards/format_reward": 1.0,
      "step": 775
    },
    {
      "all_correct": 0.25,
      "all_wrong": 0.0,
      "completion_length": 434.09375,
      "epoch": 0.010703300644129046,
      "grad_norm": 2.7731798347383156,
      "kl": 0.057373046875,
      "learning_rate": 9.99717359571824e-07,
      "loss": 0.0023,
      "reward": 2.0172500610351562,
      "reward_std": 0.017019499093294144,
      "rewards/accuracy_reward": 0.8172500133514404,
      "rewards/format_reward": 1.0,
      "step": 776
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.0,
      "completion_length": 416.125,
      "epoch": 0.010717093557330243,
      "grad_norm": 1.9326760231771256,
      "kl": 0.05908203125,
      "learning_rate": 9.997166307166065e-07,
      "loss": 0.0024,
      "reward": 2.0292813777923584,
      "reward_std": 0.012397769838571548,
      "rewards/accuracy_reward": 0.8292812705039978,
      "rewards/format_reward": 1.0,
      "step": 777
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.0,
      "completion_length": 420.5,
      "epoch": 0.01073088647053144,
      "grad_norm": 8.312144053152865,
      "kl": 0.064453125,
      "learning_rate": 9.997159009231022e-07,
      "loss": 0.0026,
      "reward": 2.036656379699707,
      "reward_std": 0.020144039765000343,
      "rewards/accuracy_reward": 0.8366562128067017,
      "rewards/format_reward": 1.0,
      "step": 778
    },
    {
      "all_correct": 0.75,
      "all_wrong": 0.0,
      "completion_length": 423.40625,
      "epoch": 0.010744679383732638,
      "grad_norm": 2.4564014575073263,
      "kl": 0.057373046875,
      "learning_rate": 9.997151701913127e-07,
      "loss": 0.0023,
      "reward": 2.1264376640319824,
      "reward_std": 0.0199674554169178,
      "rewards/accuracy_reward": 0.926437497138977,
      "rewards/format_reward": 1.0,
      "step": 779
    },
    {
      "all_correct": 0.75,
      "all_wrong": 0.0,
      "completion_length": 421.125,
      "epoch": 0.010758472296933835,
      "grad_norm": 1.9556915207208514,
      "kl": 0.07080078125,
      "learning_rate": 9.99714438521239e-07,
      "loss": 0.0028,
      "reward": 2.0612499713897705,
      "reward_std": 0.029282229021191597,
      "rewards/accuracy_reward": 0.8737499713897705,
      "rewards/format_reward": 1.0,
      "step": 780
    },
    {
      "all_correct": 0.75,
      "all_wrong": 0.0,
      "completion_length": 421.28125,
      "epoch": 0.010772265210135032,
      "grad_norm": 3.3048727893573897,
      "kl": 0.0576171875,
      "learning_rate": 9.997137059128828e-07,
      "loss": 0.0023,
      "reward": 2.105250120162964,
      "reward_std": 0.02463524043560028,
      "rewards/accuracy_reward": 0.9052500128746033,
      "rewards/format_reward": 1.0,
      "step": 781
    },
    {
      "all_correct": 0.75,
      "all_wrong": 0.0,
      "completion_length": 417.78125,
      "epoch": 0.01078605812333623,
      "grad_norm": 2.3225690396165812,
      "kl": 0.060791015625,
      "learning_rate": 9.997129723662456e-07,
      "loss": 0.0024,
      "reward": 2.0871875286102295,
      "reward_std": 0.007724268361926079,
      "rewards/accuracy_reward": 0.8871874809265137,
      "rewards/format_reward": 1.0,
      "step": 782
    },
    {
      "all_correct": 1.0,
      "all_wrong": 0.0,
      "completion_length": 415.71875,
      "epoch": 0.010799851036537427,
      "grad_norm": 2.1293625413705377,
      "kl": 0.056640625,
      "learning_rate": 9.997122378813284e-07,
      "loss": 0.0023,
      "reward": 2.0953125953674316,
      "reward_std": 0.008481588214635849,
      "rewards/accuracy_reward": 0.8953125476837158,
      "rewards/format_reward": 1.0,
      "step": 783
    },
    {
      "all_correct": 0.75,
      "all_wrong": 0.0,
      "completion_length": 413.0,
      "epoch": 0.010813643949738624,
      "grad_norm": 2.6298404697775455,
      "kl": 0.05908203125,
      "learning_rate": 9.997115024581327e-07,
      "loss": 0.0024,
      "reward": 2.0637500286102295,
      "reward_std": 0.023685740306973457,
      "rewards/accuracy_reward": 0.8637499809265137,
      "rewards/format_reward": 1.0,
      "step": 784
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.0,
      "completion_length": 391.625,
      "epoch": 0.010827436862939821,
      "grad_norm": 2.928644321807091,
      "kl": 0.06787109375,
      "learning_rate": 9.997107660966605e-07,
      "loss": 0.0027,
      "reward": 2.034656286239624,
      "reward_std": 0.03632409870624542,
      "rewards/accuracy_reward": 0.8409062623977661,
      "rewards/format_reward": 1.0,
      "step": 785
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.0,
      "completion_length": 405.71875,
      "epoch": 0.010841229776141019,
      "grad_norm": 2.513664047183415,
      "kl": 0.056396484375,
      "learning_rate": 9.99710028796912e-07,
      "loss": 0.0023,
      "reward": 2.0606563091278076,
      "reward_std": 0.01943240500986576,
      "rewards/accuracy_reward": 0.8606562614440918,
      "rewards/format_reward": 1.0,
      "step": 786
    },
    {
      "all_correct": 0.75,
      "all_wrong": 0.0,
      "completion_length": 405.09375,
      "epoch": 0.010855022689342216,
      "grad_norm": 3.0382393213583283,
      "kl": 0.05712890625,
      "learning_rate": 9.997092905588895e-07,
      "loss": 0.0023,
      "reward": 2.1013126373291016,
      "reward_std": 0.027132606133818626,
      "rewards/accuracy_reward": 0.901312530040741,
      "rewards/format_reward": 1.0,
      "step": 787
    },
    {
      "all_correct": 0.75,
      "all_wrong": 0.0,
      "completion_length": 407.0625,
      "epoch": 0.010868815602543413,
      "grad_norm": 2.0098023395296742,
      "kl": 0.059814453125,
      "learning_rate": 9.99708551382594e-07,
      "loss": 0.0024,
      "reward": 2.1075313091278076,
      "reward_std": 0.00969760399311781,
      "rewards/accuracy_reward": 0.9075312614440918,
      "rewards/format_reward": 1.0,
      "step": 788
    },
    {
      "all_correct": 1.0,
      "all_wrong": 0.0,
      "completion_length": 393.84375,
      "epoch": 0.01088260851574461,
      "grad_norm": 2.468200383692465,
      "kl": 0.06298828125,
      "learning_rate": 9.997078112680268e-07,
      "loss": 0.0025,
      "reward": 2.1681876182556152,
      "reward_std": 0.028210487216711044,
      "rewards/accuracy_reward": 0.9744374752044678,
      "rewards/format_reward": 1.0,
      "step": 789
    },
    {
      "all_correct": 0.75,
      "all_wrong": 0.0,
      "completion_length": 399.875,
      "epoch": 0.010896401428945808,
      "grad_norm": 7.955372158556385,
      "kl": 0.057861328125,
      "learning_rate": 9.997070702151897e-07,
      "loss": 0.0023,
      "reward": 2.0388126373291016,
      "reward_std": 0.039768535643815994,
      "rewards/accuracy_reward": 0.8513124585151672,
      "rewards/format_reward": 1.0,
      "step": 790
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.0,
      "completion_length": 389.34375,
      "epoch": 0.010910194342147005,
      "grad_norm": 9.622073724562869,
      "kl": 0.06640625,
      "learning_rate": 9.997063282240839e-07,
      "loss": 0.0027,
      "reward": 1.9733126163482666,
      "reward_std": 0.0383220799267292,
      "rewards/accuracy_reward": 0.7858125567436218,
      "rewards/format_reward": 1.0,
      "step": 791
    },
    {
      "all_correct": 0.75,
      "all_wrong": 0.0,
      "completion_length": 416.75,
      "epoch": 0.010923987255348202,
      "grad_norm": 3.022145262903997,
      "kl": 0.04931640625,
      "learning_rate": 9.997055852947107e-07,
      "loss": 0.002,
      "reward": 2.092062473297119,
      "reward_std": 0.015360655263066292,
      "rewards/accuracy_reward": 0.8920624852180481,
      "rewards/format_reward": 1.0,
      "step": 792
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.0,
      "completion_length": 404.5,
      "epoch": 0.0109377801685494,
      "grad_norm": 2.6928963768556,
      "kl": 0.06005859375,
      "learning_rate": 9.997048414270715e-07,
      "loss": 0.0024,
      "reward": 2.125593662261963,
      "reward_std": 0.0725117027759552,
      "rewards/accuracy_reward": 0.9443436861038208,
      "rewards/format_reward": 1.0,
      "step": 793
    },
    {
      "all_correct": 0.75,
      "all_wrong": 0.0,
      "completion_length": 390.71875,
      "epoch": 0.010951573081750597,
      "grad_norm": 3.8755091129550374,
      "kl": 0.0654296875,
      "learning_rate": 9.997040966211678e-07,
      "loss": 0.0026,
      "reward": 2.0360002517700195,
      "reward_std": 0.01876935362815857,
      "rewards/accuracy_reward": 0.8359999060630798,
      "rewards/format_reward": 1.0,
      "step": 794
    },
    {
      "all_correct": 1.0,
      "all_wrong": 0.0,
      "completion_length": 407.28125,
      "epoch": 0.010965365994951794,
      "grad_norm": 3.137693646907833,
      "kl": 0.062255859375,
      "learning_rate": 9.99703350877001e-07,
      "loss": 0.0025,
      "reward": 2.1158437728881836,
      "reward_std": 0.015870871022343636,
      "rewards/accuracy_reward": 0.9158438444137573,
      "rewards/format_reward": 1.0,
      "step": 795
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.0,
      "completion_length": 411.5625,
      "epoch": 0.010979158908152991,
      "grad_norm": 2.965191977296174,
      "kl": 0.053466796875,
      "learning_rate": 9.997026041945722e-07,
      "loss": 0.0021,
      "reward": 2.046750068664551,
      "reward_std": 0.03168531507253647,
      "rewards/accuracy_reward": 0.846750020980835,
      "rewards/format_reward": 1.0,
      "step": 796
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.0,
      "completion_length": 409.65625,
      "epoch": 0.010992951821354189,
      "grad_norm": 4.391176315479191,
      "kl": 0.0625,
      "learning_rate": 9.997018565738833e-07,
      "loss": 0.0025,
      "reward": 2.0003747940063477,
      "reward_std": 0.015776025131344795,
      "rewards/accuracy_reward": 0.8003749847412109,
      "rewards/format_reward": 1.0,
      "step": 797
    },
    {
      "all_correct": 0.75,
      "all_wrong": 0.0,
      "completion_length": 407.96875,
      "epoch": 0.011006744734555386,
      "grad_norm": 3.0627841943932474,
      "kl": 0.06494140625,
      "learning_rate": 9.997011080149354e-07,
      "loss": 0.0026,
      "reward": 2.069531202316284,
      "reward_std": 0.013713781721889973,
      "rewards/accuracy_reward": 0.8695312738418579,
      "rewards/format_reward": 1.0,
      "step": 798
    },
    {
      "all_correct": 0.25,
      "all_wrong": 0.0,
      "completion_length": 401.5,
      "epoch": 0.011020537647756583,
      "grad_norm": 3.137509558475994,
      "kl": 0.06103515625,
      "learning_rate": 9.9970035851773e-07,
      "loss": 0.0024,
      "reward": 1.9291250705718994,
      "reward_std": 0.01993734948337078,
      "rewards/accuracy_reward": 0.7291249632835388,
      "rewards/format_reward": 1.0,
      "step": 799
    },
    {
      "all_correct": 0.25,
      "all_wrong": 0.0,
      "completion_length": 416.625,
      "epoch": 0.01103433056095778,
      "grad_norm": 2.4419319351111484,
      "kl": 0.0595703125,
      "learning_rate": 9.996996080822683e-07,
      "loss": 0.0024,
      "reward": 1.959031105041504,
      "reward_std": 0.03270441293716431,
      "rewards/accuracy_reward": 0.7652812600135803,
      "rewards/format_reward": 1.0,
      "step": 800
    },
    {
      "all_correct": 0.25,
      "all_wrong": 0.0,
      "completion_length": 395.5,
      "epoch": 0.011048123474158978,
      "grad_norm": 5.040142494393657,
      "kl": 0.06884765625,
      "learning_rate": 9.99698856708552e-07,
      "loss": 0.0028,
      "reward": 2.0515313148498535,
      "reward_std": 0.04230183735489845,
      "rewards/accuracy_reward": 0.8640312552452087,
      "rewards/format_reward": 1.0,
      "step": 801
    },
    {
      "all_correct": 0.25,
      "all_wrong": 0.0,
      "completion_length": 412.03125,
      "epoch": 0.011061916387360175,
      "grad_norm": 3.5266963973312677,
      "kl": 0.0625,
      "learning_rate": 9.996981043965824e-07,
      "loss": 0.0025,
      "reward": 1.939250111579895,
      "reward_std": 0.015386686660349369,
      "rewards/accuracy_reward": 0.7392499446868896,
      "rewards/format_reward": 1.0,
      "step": 802
    },
    {
      "all_correct": 1.0,
      "all_wrong": 0.0,
      "completion_length": 414.21875,
      "epoch": 0.011075709300561372,
      "grad_norm": 2.166008242138284,
      "kl": 0.061767578125,
      "learning_rate": 9.996973511463607e-07,
      "loss": 0.0025,
      "reward": 2.100281238555908,
      "reward_std": 0.019825290888547897,
      "rewards/accuracy_reward": 0.9002813100814819,
      "rewards/format_reward": 1.0,
      "step": 803
    },
    {
      "all_correct": 0.25,
      "all_wrong": 0.0,
      "completion_length": 415.40625,
      "epoch": 0.01108950221376257,
      "grad_norm": 3.7846259799298223,
      "kl": 0.056396484375,
      "learning_rate": 9.996965969578887e-07,
      "loss": 0.0023,
      "reward": 2.0434062480926514,
      "reward_std": 0.025049176067113876,
      "rewards/accuracy_reward": 0.8434062004089355,
      "rewards/format_reward": 1.0,
      "step": 804
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.0,
      "completion_length": 403.71875,
      "epoch": 0.011103295126963767,
      "grad_norm": 2.9322276210941207,
      "kl": 0.06640625,
      "learning_rate": 9.996958418311676e-07,
      "loss": 0.0026,
      "reward": 2.0053439140319824,
      "reward_std": 0.025423455983400345,
      "rewards/accuracy_reward": 0.805343747138977,
      "rewards/format_reward": 1.0,
      "step": 805
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.0,
      "completion_length": 406.3125,
      "epoch": 0.011117088040164964,
      "grad_norm": 4.336962125472765,
      "kl": 0.06103515625,
      "learning_rate": 9.996950857661987e-07,
      "loss": 0.0024,
      "reward": 1.9846094846725464,
      "reward_std": 0.023516319692134857,
      "rewards/accuracy_reward": 0.784609317779541,
      "rewards/format_reward": 1.0,
      "step": 806
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.0,
      "completion_length": 400.21875,
      "epoch": 0.011130880953366161,
      "grad_norm": 3.1024691624259213,
      "kl": 0.0634765625,
      "learning_rate": 9.996943287629837e-07,
      "loss": 0.0025,
      "reward": 1.9855624437332153,
      "reward_std": 0.01902967132627964,
      "rewards/accuracy_reward": 0.7855624556541443,
      "rewards/format_reward": 1.0,
      "step": 807
    },
    {
      "all_correct": 0.75,
      "all_wrong": 0.0,
      "completion_length": 413.34375,
      "epoch": 0.011144673866567357,
      "grad_norm": 1.9870172080452198,
      "kl": 0.0615234375,
      "learning_rate": 9.99693570821524e-07,
      "loss": 0.0025,
      "reward": 2.084656238555908,
      "reward_std": 0.014451270923018456,
      "rewards/accuracy_reward": 0.8846561908721924,
      "rewards/format_reward": 1.0,
      "step": 808
    },
    {
      "all_correct": 0.75,
      "all_wrong": 0.0,
      "completion_length": 418.53125,
      "epoch": 0.011158466779768554,
      "grad_norm": 2.8292219474356006,
      "kl": 0.056640625,
      "learning_rate": 9.996928119418208e-07,
      "loss": 0.0023,
      "reward": 2.094749927520752,
      "reward_std": 0.017461363226175308,
      "rewards/accuracy_reward": 0.8947499394416809,
      "rewards/format_reward": 1.0,
      "step": 809
    },
    {
      "all_correct": 0.75,
      "all_wrong": 0.0,
      "completion_length": 407.625,
      "epoch": 0.011172259692969751,
      "grad_norm": 2.007332182198467,
      "kl": 0.0625,
      "learning_rate": 9.996920521238757e-07,
      "loss": 0.0025,
      "reward": 2.117062568664551,
      "reward_std": 0.011572951450943947,
      "rewards/accuracy_reward": 0.917062520980835,
      "rewards/format_reward": 1.0,
      "step": 810
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.0,
      "completion_length": 421.46875,
      "epoch": 0.011186052606170949,
      "grad_norm": 2.7758068869060026,
      "kl": 0.06005859375,
      "learning_rate": 9.9969129136769e-07,
      "loss": 0.0024,
      "reward": 1.9802188873291016,
      "reward_std": 0.01374787651002407,
      "rewards/accuracy_reward": 0.780218780040741,
      "rewards/format_reward": 1.0,
      "step": 811
    },
    {
      "all_correct": 0.25,
      "all_wrong": 0.0,
      "completion_length": 433.78125,
      "epoch": 0.011199845519372146,
      "grad_norm": 2.6216665583719974,
      "kl": 0.06494140625,
      "learning_rate": 9.996905296732652e-07,
      "loss": 0.0026,
      "reward": 2.0626251697540283,
      "reward_std": 0.04599296674132347,
      "rewards/accuracy_reward": 0.8876250386238098,
      "rewards/format_reward": 1.0,
      "step": 812
    },
    {
      "all_correct": 0.75,
      "all_wrong": 0.0,
      "completion_length": 424.0625,
      "epoch": 0.011213638432573343,
      "grad_norm": 4.126874798021307,
      "kl": 0.072265625,
      "learning_rate": 9.996897670406025e-07,
      "loss": 0.0029,
      "reward": 2.089968681335449,
      "reward_std": 0.02616027556359768,
      "rewards/accuracy_reward": 0.889968752861023,
      "rewards/format_reward": 1.0,
      "step": 813
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.0,
      "completion_length": 420.40625,
      "epoch": 0.01122743134577454,
      "grad_norm": 4.051032796367354,
      "kl": 0.0654296875,
      "learning_rate": 9.996890034697039e-07,
      "loss": 0.0026,
      "reward": 1.9441564083099365,
      "reward_std": 0.024097414687275887,
      "rewards/accuracy_reward": 0.7441562414169312,
      "rewards/format_reward": 1.0,
      "step": 814
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.0,
      "completion_length": 427.5625,
      "epoch": 0.011241224258975738,
      "grad_norm": 27.221526178339026,
      "kl": 0.0595703125,
      "learning_rate": 9.996882389605703e-07,
      "loss": 0.0024,
      "reward": 1.9472500085830688,
      "reward_std": 0.02749377116560936,
      "rewards/accuracy_reward": 0.7534999847412109,
      "rewards/format_reward": 1.0,
      "step": 815
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.0,
      "completion_length": 421.03125,
      "epoch": 0.011255017172176935,
      "grad_norm": 2.322686938851381,
      "kl": 0.06298828125,
      "learning_rate": 9.996874735132034e-07,
      "loss": 0.0025,
      "reward": 1.9621562957763672,
      "reward_std": 0.01175643876194954,
      "rewards/accuracy_reward": 0.7621562480926514,
      "rewards/format_reward": 1.0,
      "step": 816
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.0,
      "completion_length": 412.8125,
      "epoch": 0.011268810085378132,
      "grad_norm": 2.611679718853567,
      "kl": 0.05810546875,
      "learning_rate": 9.996867071276046e-07,
      "loss": 0.0023,
      "reward": 1.9129687547683716,
      "reward_std": 0.01250208169221878,
      "rewards/accuracy_reward": 0.7129687070846558,
      "rewards/format_reward": 1.0,
      "step": 817
    },
    {
      "all_correct": 0.25,
      "all_wrong": 0.0,
      "completion_length": 420.75,
      "epoch": 0.01128260299857933,
      "grad_norm": 2.867111393698513,
      "kl": 0.05908203125,
      "learning_rate": 9.99685939803775e-07,
      "loss": 0.0024,
      "reward": 1.986781120300293,
      "reward_std": 0.013479959219694138,
      "rewards/accuracy_reward": 0.7867813110351562,
      "rewards/format_reward": 1.0,
      "step": 818
    },
    {
      "all_correct": 0.75,
      "all_wrong": 0.0,
      "completion_length": 408.25,
      "epoch": 0.011296395911780527,
      "grad_norm": 2.394077205499161,
      "kl": 0.0625,
      "learning_rate": 9.996851715417168e-07,
      "loss": 0.0025,
      "reward": 2.090437650680542,
      "reward_std": 0.02494914084672928,
      "rewards/accuracy_reward": 0.8966874480247498,
      "rewards/format_reward": 1.0,
      "step": 819
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.0,
      "completion_length": 433.34375,
      "epoch": 0.011310188824981724,
      "grad_norm": 2.5090999757553365,
      "kl": 0.05810546875,
      "learning_rate": 9.996844023414306e-07,
      "loss": 0.0023,
      "reward": 2.0095937252044678,
      "reward_std": 0.03689955547451973,
      "rewards/accuracy_reward": 0.8158438205718994,
      "rewards/format_reward": 1.0,
      "step": 820
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.0,
      "completion_length": 418.96875,
      "epoch": 0.011323981738182921,
      "grad_norm": 2.3564867853669687,
      "kl": 0.060791015625,
      "learning_rate": 9.996836322029182e-07,
      "loss": 0.0024,
      "reward": 1.9346563816070557,
      "reward_std": 0.040891990065574646,
      "rewards/accuracy_reward": 0.7471562623977661,
      "rewards/format_reward": 1.0,
      "step": 821
    },
    {
      "all_correct": 0.75,
      "all_wrong": 0.0,
      "completion_length": 417.0,
      "epoch": 0.011337774651384119,
      "grad_norm": 4.562292658819249,
      "kl": 0.059814453125,
      "learning_rate": 9.996828611261814e-07,
      "loss": 0.0024,
      "reward": 2.146843910217285,
      "reward_std": 0.03361503407359123,
      "rewards/accuracy_reward": 0.9530937075614929,
      "rewards/format_reward": 1.0,
      "step": 822
    },
    {
      "all_correct": 0.75,
      "all_wrong": 0.0,
      "completion_length": 426.625,
      "epoch": 0.011351567564585316,
      "grad_norm": 6.197307201792726,
      "kl": 0.0615234375,
      "learning_rate": 9.996820891112212e-07,
      "loss": 0.0025,
      "reward": 2.099874973297119,
      "reward_std": 0.009361280128359795,
      "rewards/accuracy_reward": 0.8998750448226929,
      "rewards/format_reward": 1.0,
      "step": 823
    },
    {
      "all_correct": 0.75,
      "all_wrong": 0.0,
      "completion_length": 431.4375,
      "epoch": 0.011365360477786513,
      "grad_norm": 2.558265503139382,
      "kl": 0.06640625,
      "learning_rate": 9.996813161580391e-07,
      "loss": 0.0027,
      "reward": 2.0712499618530273,
      "reward_std": 0.013410200364887714,
      "rewards/accuracy_reward": 0.8712499737739563,
      "rewards/format_reward": 1.0,
      "step": 824
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.0,
      "completion_length": 423.0,
      "epoch": 0.01137915339098771,
      "grad_norm": 3.465438261958482,
      "kl": 0.06787109375,
      "learning_rate": 9.996805422666365e-07,
      "loss": 0.0027,
      "reward": 1.999906301498413,
      "reward_std": 0.03800682723522186,
      "rewards/accuracy_reward": 0.8061562776565552,
      "rewards/format_reward": 1.0,
      "step": 825
    },
    {
      "all_correct": 0.25,
      "all_wrong": 0.0,
      "completion_length": 417.4375,
      "epoch": 0.011392946304188908,
      "grad_norm": 2.3990857135518113,
      "kl": 0.06640625,
      "learning_rate": 9.996797674370151e-07,
      "loss": 0.0027,
      "reward": 1.9601249694824219,
      "reward_std": 0.024164855480194092,
      "rewards/accuracy_reward": 0.7663750648498535,
      "rewards/format_reward": 1.0,
      "step": 826
    },
    {
      "all_correct": 0.75,
      "all_wrong": 0.0,
      "completion_length": 420.5625,
      "epoch": 0.011406739217390105,
      "grad_norm": 2.6271078590462245,
      "kl": 0.0693359375,
      "learning_rate": 9.996789916691764e-07,
      "loss": 0.0028,
      "reward": 2.061406373977661,
      "reward_std": 0.01364709623157978,
      "rewards/accuracy_reward": 0.8614062070846558,
      "rewards/format_reward": 1.0,
      "step": 827
    },
    {
      "all_correct": 0.25,
      "all_wrong": 0.0,
      "completion_length": 417.4375,
      "epoch": 0.011420532130591302,
      "grad_norm": 3.3369275583686573,
      "kl": 0.0625,
      "learning_rate": 9.996782149631215e-07,
      "loss": 0.0025,
      "reward": 1.9078125953674316,
      "reward_std": 0.05367925018072128,
      "rewards/accuracy_reward": 0.7203124761581421,
      "rewards/format_reward": 1.0,
      "step": 828
    },
    {
      "all_correct": 0.75,
      "all_wrong": 0.0,
      "completion_length": 428.625,
      "epoch": 0.0114343250437925,
      "grad_norm": 2.778753896514087,
      "kl": 0.06884765625,
      "learning_rate": 9.996774373188521e-07,
      "loss": 0.0028,
      "reward": 2.059906482696533,
      "reward_std": 0.025252975523471832,
      "rewards/accuracy_reward": 0.8599063158035278,
      "rewards/format_reward": 1.0,
      "step": 829
    },
    {
      "all_correct": 0.75,
      "all_wrong": 0.0,
      "completion_length": 419.8125,
      "epoch": 0.011448117956993697,
      "grad_norm": 2.7857368868609194,
      "kl": 0.06298828125,
      "learning_rate": 9.996766587363695e-07,
      "loss": 0.0025,
      "reward": 2.059281349182129,
      "reward_std": 0.01778646931052208,
      "rewards/accuracy_reward": 0.8592813014984131,
      "rewards/format_reward": 1.0,
      "step": 830
    },
    {
      "all_correct": 0.75,
      "all_wrong": 0.0,
      "completion_length": 424.0625,
      "epoch": 0.011461910870194894,
      "grad_norm": 8.051504435818483,
      "kl": 0.0615234375,
      "learning_rate": 9.996758792156753e-07,
      "loss": 0.0025,
      "reward": 2.1093125343322754,
      "reward_std": 0.008717061020433903,
      "rewards/accuracy_reward": 0.9093124866485596,
      "rewards/format_reward": 1.0,
      "step": 831
    },
    {
      "all_correct": 1.0,
      "all_wrong": 0.0,
      "completion_length": 407.46875,
      "epoch": 0.011475703783396091,
      "grad_norm": 1.604738557307816,
      "kl": 0.06396484375,
      "learning_rate": 9.99675098756771e-07,
      "loss": 0.0026,
      "reward": 2.133124828338623,
      "reward_std": 0.010685278102755547,
      "rewards/accuracy_reward": 0.9331250190734863,
      "rewards/format_reward": 1.0,
      "step": 832
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.0,
      "completion_length": 404.65625,
      "epoch": 0.011489496696597289,
      "grad_norm": 2.7699740294123867,
      "kl": 0.05859375,
      "learning_rate": 9.99674317359658e-07,
      "loss": 0.0023,
      "reward": 2.027468681335449,
      "reward_std": 0.032107800245285034,
      "rewards/accuracy_reward": 0.8274686932563782,
      "rewards/format_reward": 1.0,
      "step": 833
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.0,
      "completion_length": 403.15625,
      "epoch": 0.011503289609798486,
      "grad_norm": 1.3438355317644886,
      "kl": 0.0556640625,
      "learning_rate": 9.996735350243378e-07,
      "loss": 0.0022,
      "reward": 1.981156349182129,
      "reward_std": 0.0073362309485673904,
      "rewards/accuracy_reward": 0.7811562418937683,
      "rewards/format_reward": 1.0,
      "step": 834
    },
    {
      "all_correct": 0.75,
      "all_wrong": 0.0,
      "completion_length": 400.0625,
      "epoch": 0.011517082522999683,
      "grad_norm": 3.5618758890444435,
      "kl": 0.06103515625,
      "learning_rate": 9.996727517508116e-07,
      "loss": 0.0024,
      "reward": 2.1022188663482666,
      "reward_std": 0.03714028745889664,
      "rewards/accuracy_reward": 0.9022186994552612,
      "rewards/format_reward": 1.0,
      "step": 835
    },
    {
      "all_correct": 0.25,
      "all_wrong": 0.0,
      "completion_length": 394.375,
      "epoch": 0.01153087543620088,
      "grad_norm": 8.264618607993818,
      "kl": 0.057373046875,
      "learning_rate": 9.996719675390814e-07,
      "loss": 0.0023,
      "reward": 1.9329688549041748,
      "reward_std": 0.013602283783257008,
      "rewards/accuracy_reward": 0.7329687476158142,
      "rewards/format_reward": 1.0,
      "step": 836
    },
    {
      "all_correct": 0.75,
      "all_wrong": 0.0,
      "completion_length": 397.46875,
      "epoch": 0.011544668349402078,
      "grad_norm": 2.1389286903577553,
      "kl": 0.058837890625,
      "learning_rate": 9.996711823891481e-07,
      "loss": 0.0024,
      "reward": 2.0406875610351562,
      "reward_std": 0.02286362834274769,
      "rewards/accuracy_reward": 0.8406875133514404,
      "rewards/format_reward": 1.0,
      "step": 837
    },
    {
      "all_correct": 0.25,
      "all_wrong": 0.0,
      "completion_length": 402.0,
      "epoch": 0.011558461262603275,
      "grad_norm": 2.0762559763495485,
      "kl": 0.0654296875,
      "learning_rate": 9.996703963010136e-07,
      "loss": 0.0026,
      "reward": 2.048468828201294,
      "reward_std": 0.03429223597049713,
      "rewards/accuracy_reward": 0.8547187447547913,
      "rewards/format_reward": 1.0,
      "step": 838
    },
    {
      "all_correct": 1.0,
      "all_wrong": 0.0,
      "completion_length": 392.5,
      "epoch": 0.011572254175804472,
      "grad_norm": 2.382663184085568,
      "kl": 0.06298828125,
      "learning_rate": 9.996696092746794e-07,
      "loss": 0.0025,
      "reward": 2.084249973297119,
      "reward_std": 0.028589671477675438,
      "rewards/accuracy_reward": 0.8842499852180481,
      "rewards/format_reward": 1.0,
      "step": 839
    },
    {
      "all_correct": 1.0,
      "all_wrong": 0.0,
      "completion_length": 388.90625,
      "epoch": 0.01158604708900567,
      "grad_norm": 2.1591170321915554,
      "kl": 0.060791015625,
      "learning_rate": 9.996688213101464e-07,
      "loss": 0.0024,
      "reward": 2.12709379196167,
      "reward_std": 0.010218516923487186,
      "rewards/accuracy_reward": 0.9270937442779541,
      "rewards/format_reward": 1.0,
      "step": 840
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.0,
      "completion_length": 401.1875,
      "epoch": 0.011599840002206867,
      "grad_norm": 3.377154698949668,
      "kl": 0.0537109375,
      "learning_rate": 9.996680324074167e-07,
      "loss": 0.0021,
      "reward": 2.074718952178955,
      "reward_std": 0.046328362077474594,
      "rewards/accuracy_reward": 0.8809687495231628,
      "rewards/format_reward": 1.0,
      "step": 841
    },
    {
      "all_correct": 0.75,
      "all_wrong": 0.0,
      "completion_length": 391.625,
      "epoch": 0.011613632915408064,
      "grad_norm": 4.962266065521929,
      "kl": 0.068359375,
      "learning_rate": 9.996672425664915e-07,
      "loss": 0.0027,
      "reward": 2.075937509536743,
      "reward_std": 0.027525397017598152,
      "rewards/accuracy_reward": 0.8821874856948853,
      "rewards/format_reward": 1.0,
      "step": 842
    },
    {
      "all_correct": 1.0,
      "all_wrong": 0.0,
      "completion_length": 401.59375,
      "epoch": 0.011627425828609261,
      "grad_norm": 2.8390598240275886,
      "kl": 0.06201171875,
      "learning_rate": 9.996664517873725e-07,
      "loss": 0.0025,
      "reward": 2.1173439025878906,
      "reward_std": 0.028220897540450096,
      "rewards/accuracy_reward": 0.9173436760902405,
      "rewards/format_reward": 1.0,
      "step": 843
    },
    {
      "all_correct": 0.75,
      "all_wrong": 0.0,
      "completion_length": 390.5,
      "epoch": 0.011641218741810459,
      "grad_norm": 1.6394258138671067,
      "kl": 0.060302734375,
      "learning_rate": 9.996656600700607e-07,
      "loss": 0.0024,
      "reward": 2.0991873741149902,
      "reward_std": 0.007098478265106678,
      "rewards/accuracy_reward": 0.8991875648498535,
      "rewards/format_reward": 1.0,
      "step": 844
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.0,
      "completion_length": 400.40625,
      "epoch": 0.011655011655011656,
      "grad_norm": 2.733876167820925,
      "kl": 0.06640625,
      "learning_rate": 9.996648674145583e-07,
      "loss": 0.0026,
      "reward": 2.0859375,
      "reward_std": 0.034203723073005676,
      "rewards/accuracy_reward": 0.8859374523162842,
      "rewards/format_reward": 1.0,
      "step": 845
    },
    {
      "all_correct": 0.75,
      "all_wrong": 0.0,
      "completion_length": 381.65625,
      "epoch": 0.011668804568212851,
      "grad_norm": 2.0153972049353643,
      "kl": 0.06201171875,
      "learning_rate": 9.996640738208661e-07,
      "loss": 0.0025,
      "reward": 2.0403125286102295,
      "reward_std": 0.02131342887878418,
      "rewards/accuracy_reward": 0.8465625047683716,
      "rewards/format_reward": 1.0,
      "step": 846
    },
    {
      "all_correct": 1.0,
      "all_wrong": 0.0,
      "completion_length": 393.25,
      "epoch": 0.011682597481414049,
      "grad_norm": 2.581256825259971,
      "kl": 0.05810546875,
      "learning_rate": 9.99663279288986e-07,
      "loss": 0.0023,
      "reward": 2.120093822479248,
      "reward_std": 0.014586973935365677,
      "rewards/accuracy_reward": 0.9200937747955322,
      "rewards/format_reward": 1.0,
      "step": 847
    },
    {
      "all_correct": 0.25,
      "all_wrong": 0.0,
      "completion_length": 381.375,
      "epoch": 0.011696390394615246,
      "grad_norm": 3.506499437442312,
      "kl": 0.06982421875,
      "learning_rate": 9.996624838189196e-07,
      "loss": 0.0028,
      "reward": 2.129031181335449,
      "reward_std": 0.07114508748054504,
      "rewards/accuracy_reward": 0.9477812051773071,
      "rewards/format_reward": 1.0,
      "step": 848
    },
    {
      "all_correct": 0.75,
      "all_wrong": 0.0,
      "completion_length": 370.09375,
      "epoch": 0.011710183307816443,
      "grad_norm": 1.6740805467648918,
      "kl": 0.05908203125,
      "learning_rate": 9.99661687410668e-07,
      "loss": 0.0024,
      "reward": 2.091562509536743,
      "reward_std": 0.02857976034283638,
      "rewards/accuracy_reward": 0.9040625095367432,
      "rewards/format_reward": 1.0,
      "step": 849
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.0,
      "completion_length": 384.28125,
      "epoch": 0.01172397622101764,
      "grad_norm": 1.9296226836547883,
      "kl": 0.06884765625,
      "learning_rate": 9.996608900642328e-07,
      "loss": 0.0028,
      "reward": 1.8899062871932983,
      "reward_std": 0.03519243001937866,
      "rewards/accuracy_reward": 0.6961562633514404,
      "rewards/format_reward": 1.0,
      "step": 850
    },
    {
      "all_correct": 0.25,
      "all_wrong": 0.0,
      "completion_length": 381.09375,
      "epoch": 0.011737769134218838,
      "grad_norm": 3.350627610732348,
      "kl": 0.06103515625,
      "learning_rate": 9.996600917796156e-07,
      "loss": 0.0024,
      "reward": 2.073437452316284,
      "reward_std": 0.03993368148803711,
      "rewards/accuracy_reward": 0.8796875476837158,
      "rewards/format_reward": 1.0,
      "step": 851
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.0,
      "completion_length": 410.65625,
      "epoch": 0.011751562047420035,
      "grad_norm": 2.6447759856591144,
      "kl": 0.05517578125,
      "learning_rate": 9.99659292556818e-07,
      "loss": 0.0022,
      "reward": 1.9443750381469727,
      "reward_std": 0.01881929114460945,
      "rewards/accuracy_reward": 0.7443750500679016,
      "rewards/format_reward": 1.0,
      "step": 852
    },
    {
      "all_correct": 0.25,
      "all_wrong": 0.0,
      "completion_length": 395.65625,
      "epoch": 0.011765354960621232,
      "grad_norm": 3.1281596440526633,
      "kl": 0.06591796875,
      "learning_rate": 9.996584923958413e-07,
      "loss": 0.0026,
      "reward": 2.0310001373291016,
      "reward_std": 0.03758327290415764,
      "rewards/accuracy_reward": 0.8372499346733093,
      "rewards/format_reward": 1.0,
      "step": 853
    },
    {
      "all_correct": 0.75,
      "all_wrong": 0.0,
      "completion_length": 387.46875,
      "epoch": 0.01177914787382243,
      "grad_norm": 6.6734576809864965,
      "kl": 0.06201171875,
      "learning_rate": 9.99657691296687e-07,
      "loss": 0.0025,
      "reward": 2.076843738555908,
      "reward_std": 0.02001909539103508,
      "rewards/accuracy_reward": 0.8768438100814819,
      "rewards/format_reward": 1.0,
      "step": 854
    },
    {
      "all_correct": 0.75,
      "all_wrong": 0.0,
      "completion_length": 397.40625,
      "epoch": 0.011792940787023627,
      "grad_norm": 6.191875399836288,
      "kl": 0.06689453125,
      "learning_rate": 9.996568892593568e-07,
      "loss": 0.0027,
      "reward": 2.0779685974121094,
      "reward_std": 0.013660861179232597,
      "rewards/accuracy_reward": 0.8779687881469727,
      "rewards/format_reward": 1.0,
      "step": 855
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.0,
      "completion_length": 417.1875,
      "epoch": 0.011806733700224824,
      "grad_norm": 2.5483785326216037,
      "kl": 0.0615234375,
      "learning_rate": 9.996560862838518e-07,
      "loss": 0.0025,
      "reward": 2.1045312881469727,
      "reward_std": 0.0539567694067955,
      "rewards/accuracy_reward": 0.9170312881469727,
      "rewards/format_reward": 1.0,
      "step": 856
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.0,
      "completion_length": 398.46875,
      "epoch": 0.011820526613426021,
      "grad_norm": 2.418062418205007,
      "kl": 0.068359375,
      "learning_rate": 9.99655282370174e-07,
      "loss": 0.0027,
      "reward": 1.9567968845367432,
      "reward_std": 0.034331951290369034,
      "rewards/accuracy_reward": 0.7630468606948853,
      "rewards/format_reward": 1.0,
      "step": 857
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.0,
      "completion_length": 403.6875,
      "epoch": 0.011834319526627219,
      "grad_norm": 1.7809773108215838,
      "kl": 0.0634765625,
      "learning_rate": 9.99654477518325e-07,
      "loss": 0.0025,
      "reward": 1.9782187938690186,
      "reward_std": 0.009585888125002384,
      "rewards/accuracy_reward": 0.7782187461853027,
      "rewards/format_reward": 1.0,
      "step": 858
    },
    {
      "all_correct": 0.25,
      "all_wrong": 0.0,
      "completion_length": 411.875,
      "epoch": 0.011848112439828416,
      "grad_norm": 0.11383412686078949,
      "kl": 0.06298828125,
      "learning_rate": 9.996536717283055e-07,
      "loss": 0.0025,
      "reward": 1.9325000047683716,
      "reward_std": 0.0,
      "rewards/accuracy_reward": 0.7325000166893005,
      "rewards/format_reward": 1.0,
      "step": 859
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.0,
      "completion_length": 445.21875,
      "epoch": 0.011861905353029613,
      "grad_norm": 2.972591786302114,
      "kl": 0.05322265625,
      "learning_rate": 9.99652865000118e-07,
      "loss": 0.0021,
      "reward": 2.0732500553131104,
      "reward_std": 0.0530330166220665,
      "rewards/accuracy_reward": 0.8919999599456787,
      "rewards/format_reward": 1.0,
      "step": 860
    },
    {
      "all_correct": 1.0,
      "all_wrong": 0.0,
      "completion_length": 421.90625,
      "epoch": 0.01187569826623081,
      "grad_norm": 2.0954102476111642,
      "kl": 0.060546875,
      "learning_rate": 9.996520573337631e-07,
      "loss": 0.0024,
      "reward": 2.117062568664551,
      "reward_std": 0.012381434440612793,
      "rewards/accuracy_reward": 0.917062520980835,
      "rewards/format_reward": 1.0,
      "step": 861
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.0,
      "completion_length": 429.78125,
      "epoch": 0.011889491179432008,
      "grad_norm": 2.9585560613407336,
      "kl": 0.06689453125,
      "learning_rate": 9.99651248729243e-07,
      "loss": 0.0027,
      "reward": 2.0201563835144043,
      "reward_std": 0.03696242719888687,
      "rewards/accuracy_reward": 0.8264062404632568,
      "rewards/format_reward": 1.0,
      "step": 862
    },
    {
      "all_correct": 0.75,
      "all_wrong": 0.0,
      "completion_length": 431.3125,
      "epoch": 0.011903284092633205,
      "grad_norm": 2.0811959755561227,
      "kl": 0.0625,
      "learning_rate": 9.99650439186559e-07,
      "loss": 0.0025,
      "reward": 2.0782814025878906,
      "reward_std": 0.03882887214422226,
      "rewards/accuracy_reward": 0.8845313191413879,
      "rewards/format_reward": 1.0,
      "step": 863
    },
    {
      "all_correct": 0.75,
      "all_wrong": 0.0,
      "completion_length": 423.1875,
      "epoch": 0.011917077005834402,
      "grad_norm": 1.9242990768048855,
      "kl": 0.0732421875,
      "learning_rate": 9.996496287057127e-07,
      "loss": 0.0029,
      "reward": 2.073765754699707,
      "reward_std": 0.012184280902147293,
      "rewards/accuracy_reward": 0.8737655878067017,
      "rewards/format_reward": 1.0,
      "step": 864
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.0,
      "completion_length": 424.59375,
      "epoch": 0.0119308699190356,
      "grad_norm": 6.091985250089945,
      "kl": 0.0615234375,
      "learning_rate": 9.99648817286705e-07,
      "loss": 0.0025,
      "reward": 2.0103437900543213,
      "reward_std": 0.011906002648174763,
      "rewards/accuracy_reward": 0.8103437423706055,
      "rewards/format_reward": 1.0,
      "step": 865
    },
    {
      "all_correct": 0.75,
      "all_wrong": 0.0,
      "completion_length": 418.625,
      "epoch": 0.011944662832236797,
      "grad_norm": 1.981395523690396,
      "kl": 0.0615234375,
      "learning_rate": 9.996480049295384e-07,
      "loss": 0.0025,
      "reward": 2.0708751678466797,
      "reward_std": 0.014063848182559013,
      "rewards/accuracy_reward": 0.8708749413490295,
      "rewards/format_reward": 1.0,
      "step": 866
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.0,
      "completion_length": 426.3125,
      "epoch": 0.011958455745437994,
      "grad_norm": 1.7563604014664984,
      "kl": 0.05712890625,
      "learning_rate": 9.99647191634214e-07,
      "loss": 0.0023,
      "reward": 2.0634374618530273,
      "reward_std": 0.012944048270583153,
      "rewards/accuracy_reward": 0.8634375333786011,
      "rewards/format_reward": 1.0,
      "step": 867
    },
    {
      "all_correct": 0.75,
      "all_wrong": 0.0,
      "completion_length": 435.5625,
      "epoch": 0.011972248658639191,
      "grad_norm": 2.4674253728508218,
      "kl": 0.057861328125,
      "learning_rate": 9.996463774007331e-07,
      "loss": 0.0023,
      "reward": 2.109468936920166,
      "reward_std": 0.027734071016311646,
      "rewards/accuracy_reward": 0.915718674659729,
      "rewards/format_reward": 1.0,
      "step": 868
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.0,
      "completion_length": 430.96875,
      "epoch": 0.011986041571840389,
      "grad_norm": 11.56900616999347,
      "kl": 0.06298828125,
      "learning_rate": 9.996455622290975e-07,
      "loss": 0.0025,
      "reward": 1.950562596321106,
      "reward_std": 0.007412286940962076,
      "rewards/accuracy_reward": 0.7505625486373901,
      "rewards/format_reward": 1.0,
      "step": 869
    },
    {
      "all_correct": 0.75,
      "all_wrong": 0.0,
      "completion_length": 418.875,
      "epoch": 0.011999834485041586,
      "grad_norm": 2.2332283400516744,
      "kl": 0.05712890625,
      "learning_rate": 9.996447461193084e-07,
      "loss": 0.0023,
      "reward": 2.0629374980926514,
      "reward_std": 0.014496359042823315,
      "rewards/accuracy_reward": 0.8629374504089355,
      "rewards/format_reward": 1.0,
      "step": 870
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.0,
      "completion_length": 416.84375,
      "epoch": 0.012013627398242783,
      "grad_norm": 2.1193121691806938,
      "kl": 0.0537109375,
      "learning_rate": 9.996439290713677e-07,
      "loss": 0.0021,
      "reward": 2.001906394958496,
      "reward_std": 0.03647825866937637,
      "rewards/accuracy_reward": 0.8081561923027039,
      "rewards/format_reward": 1.0,
      "step": 871
    },
    {
      "all_correct": 1.0,
      "all_wrong": 0.0,
      "completion_length": 411.78125,
      "epoch": 0.01202742031144398,
      "grad_norm": 3.803337052059349,
      "kl": 0.06103515625,
      "learning_rate": 9.996431110852773e-07,
      "loss": 0.0024,
      "reward": 2.1410937309265137,
      "reward_std": 0.014491010457277298,
      "rewards/accuracy_reward": 0.9410936832427979,
      "rewards/format_reward": 1.0,
      "step": 872
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.0,
      "completion_length": 417.59375,
      "epoch": 0.012041213224645178,
      "grad_norm": 4.082902419146474,
      "kl": 0.0576171875,
      "learning_rate": 9.996422921610377e-07,
      "loss": 0.0023,
      "reward": 2.0197501182556152,
      "reward_std": 0.016605820506811142,
      "rewards/accuracy_reward": 0.8197500705718994,
      "rewards/format_reward": 1.0,
      "step": 873
    },
    {
      "all_correct": 0.25,
      "all_wrong": 0.0,
      "completion_length": 423.21875,
      "epoch": 0.012055006137846375,
      "grad_norm": 2.6139498597955195,
      "kl": 0.056884765625,
      "learning_rate": 9.996414722986513e-07,
      "loss": 0.0023,
      "reward": 2.0,
      "reward_std": 0.02214580774307251,
      "rewards/accuracy_reward": 0.800000011920929,
      "rewards/format_reward": 1.0,
      "step": 874
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.0,
      "completion_length": 419.1875,
      "epoch": 0.012068799051047572,
      "grad_norm": 7.07829282131875,
      "kl": 0.057373046875,
      "learning_rate": 9.99640651498119e-07,
      "loss": 0.0023,
      "reward": 2.0888748168945312,
      "reward_std": 0.01722707599401474,
      "rewards/accuracy_reward": 0.8888750076293945,
      "rewards/format_reward": 1.0,
      "step": 875
    },
    {
      "all_correct": 0.75,
      "all_wrong": 0.0,
      "completion_length": 418.21875,
      "epoch": 0.01208259196424877,
      "grad_norm": 10.635125583071112,
      "kl": 0.064453125,
      "learning_rate": 9.996398297594428e-07,
      "loss": 0.0026,
      "reward": 2.069718837738037,
      "reward_std": 0.02198335900902748,
      "rewards/accuracy_reward": 0.8697187900543213,
      "rewards/format_reward": 1.0,
      "step": 876
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.0,
      "completion_length": 402.9375,
      "epoch": 0.012096384877449967,
      "grad_norm": 2.6385402371431486,
      "kl": 0.0654296875,
      "learning_rate": 9.996390070826243e-07,
      "loss": 0.0026,
      "reward": 1.980375051498413,
      "reward_std": 0.010692941024899483,
      "rewards/accuracy_reward": 0.7803750038146973,
      "rewards/format_reward": 1.0,
      "step": 877
    },
    {
      "all_correct": 0.0,
      "all_wrong": 0.0,
      "completion_length": 414.84375,
      "epoch": 0.012110177790651164,
      "grad_norm": 1.3571584832192531,
      "kl": 0.0654296875,
      "learning_rate": 9.996381834676647e-07,
      "loss": 0.0026,
      "reward": 1.8616876602172852,
      "reward_std": 0.08793481439352036,
      "rewards/accuracy_reward": 0.6929374933242798,
      "rewards/format_reward": 0.96875,
      "step": 878
    },
    {
      "all_correct": 0.25,
      "all_wrong": 0.0,
      "completion_length": 396.875,
      "epoch": 0.012123970703852361,
      "grad_norm": 4.154217259597983,
      "kl": 0.0537109375,
      "learning_rate": 9.99637358914566e-07,
      "loss": 0.0021,
      "reward": 1.8893749713897705,
      "reward_std": 0.015821736305952072,
      "rewards/accuracy_reward": 0.6893750429153442,
      "rewards/format_reward": 1.0,
      "step": 879
    },
    {
      "all_correct": 0.25,
      "all_wrong": 0.0,
      "completion_length": 411.46875,
      "epoch": 0.012137763617053559,
      "grad_norm": 2.6638918320464606,
      "kl": 0.06298828125,
      "learning_rate": 9.99636533423329e-07,
      "loss": 0.0025,
      "reward": 1.9846875667572021,
      "reward_std": 0.029697462916374207,
      "rewards/accuracy_reward": 0.7909375429153442,
      "rewards/format_reward": 1.0,
      "step": 880
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.0,
      "completion_length": 390.25,
      "epoch": 0.012151556530254756,
      "grad_norm": 3.9387543821551096,
      "kl": 0.06201171875,
      "learning_rate": 9.99635706993956e-07,
      "loss": 0.0025,
      "reward": 2.0455312728881836,
      "reward_std": 0.027177492156624794,
      "rewards/accuracy_reward": 0.8517812490463257,
      "rewards/format_reward": 1.0,
      "step": 881
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.0,
      "completion_length": 410.71875,
      "epoch": 0.012165349443455953,
      "grad_norm": 1.654394573300401,
      "kl": 0.06201171875,
      "learning_rate": 9.996348796264481e-07,
      "loss": 0.0025,
      "reward": 1.9733750820159912,
      "reward_std": 0.002965821884572506,
      "rewards/accuracy_reward": 0.7733750343322754,
      "rewards/format_reward": 1.0,
      "step": 882
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.0,
      "completion_length": 400.125,
      "epoch": 0.012179142356657149,
      "grad_norm": 2.99262038300314,
      "kl": 0.064453125,
      "learning_rate": 9.996340513208073e-07,
      "loss": 0.0026,
      "reward": 2.025437593460083,
      "reward_std": 0.01931835152208805,
      "rewards/accuracy_reward": 0.8254374861717224,
      "rewards/format_reward": 1.0,
      "step": 883
    },
    {
      "all_correct": 1.0,
      "all_wrong": 0.0,
      "completion_length": 396.34375,
      "epoch": 0.012192935269858346,
      "grad_norm": 1.4806723113233027,
      "kl": 0.058349609375,
      "learning_rate": 9.996332220770344e-07,
      "loss": 0.0023,
      "reward": 2.1595935821533203,
      "reward_std": 0.0035929977893829346,
      "rewards/accuracy_reward": 0.9595937728881836,
      "rewards/format_reward": 1.0,
      "step": 884
    },
    {
      "all_correct": 1.0,
      "all_wrong": 0.0,
      "completion_length": 406.3125,
      "epoch": 0.012206728183059543,
      "grad_norm": 3.947854212704794,
      "kl": 0.064453125,
      "learning_rate": 9.996323918951317e-07,
      "loss": 0.0026,
      "reward": 2.083718776702881,
      "reward_std": 0.028584294021129608,
      "rewards/accuracy_reward": 0.883718729019165,
      "rewards/format_reward": 1.0,
      "step": 885
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.0,
      "completion_length": 385.125,
      "epoch": 0.01222052109626074,
      "grad_norm": 2.096519763186262,
      "kl": 0.055908203125,
      "learning_rate": 9.996315607751006e-07,
      "loss": 0.0022,
      "reward": 2.052896022796631,
      "reward_std": 0.03550507500767708,
      "rewards/accuracy_reward": 0.8653957843780518,
      "rewards/format_reward": 1.0,
      "step": 886
    },
    {
      "all_correct": 0.75,
      "all_wrong": 0.0,
      "completion_length": 397.59375,
      "epoch": 0.012234314009461938,
      "grad_norm": 4.83163986635347,
      "kl": 0.061279296875,
      "learning_rate": 9.996307287169422e-07,
      "loss": 0.0025,
      "reward": 2.0966875553131104,
      "reward_std": 0.023463400080800056,
      "rewards/accuracy_reward": 0.8966875076293945,
      "rewards/format_reward": 1.0,
      "step": 887
    },
    {
      "all_correct": 0.75,
      "all_wrong": 0.0,
      "completion_length": 403.25,
      "epoch": 0.012248106922663135,
      "grad_norm": 3.505408970866594,
      "kl": 0.0634765625,
      "learning_rate": 9.996298957206589e-07,
      "loss": 0.0025,
      "reward": 2.085625171661377,
      "reward_std": 0.009287193417549133,
      "rewards/accuracy_reward": 0.8856250643730164,
      "rewards/format_reward": 1.0,
      "step": 888
    },
    {
      "all_correct": 0.25,
      "all_wrong": 0.0,
      "completion_length": 397.6875,
      "epoch": 0.012261899835864332,
      "grad_norm": 1.884075769266571,
      "kl": 0.06494140625,
      "learning_rate": 9.996290617862513e-07,
      "loss": 0.0026,
      "reward": 1.9230313301086426,
      "reward_std": 0.028416823595762253,
      "rewards/accuracy_reward": 0.7292811870574951,
      "rewards/format_reward": 1.0,
      "step": 889
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.0,
      "completion_length": 406.09375,
      "epoch": 0.01227569274906553,
      "grad_norm": 2.6083843425710413,
      "kl": 0.061279296875,
      "learning_rate": 9.996282269137218e-07,
      "loss": 0.0025,
      "reward": 2.0739998817443848,
      "reward_std": 0.04287020117044449,
      "rewards/accuracy_reward": 0.8865000009536743,
      "rewards/format_reward": 1.0,
      "step": 890
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.0,
      "completion_length": 407.75,
      "epoch": 0.012289485662266727,
      "grad_norm": 1.848640109992965,
      "kl": 0.08251953125,
      "learning_rate": 9.996273911030713e-07,
      "loss": 0.0033,
      "reward": 2.0134999752044678,
      "reward_std": 0.015919554978609085,
      "rewards/accuracy_reward": 0.8134999871253967,
      "rewards/format_reward": 1.0,
      "step": 891
    },
    {
      "all_correct": 0.75,
      "all_wrong": 0.0,
      "completion_length": 393.03125,
      "epoch": 0.012303278575467924,
      "grad_norm": 1.0093428303797902,
      "kl": 0.06298828125,
      "learning_rate": 9.996265543543017e-07,
      "loss": 0.0025,
      "reward": 2.1414999961853027,
      "reward_std": 0.01834392361342907,
      "rewards/accuracy_reward": 0.9477500319480896,
      "rewards/format_reward": 1.0,
      "step": 892
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.0,
      "completion_length": 416.71875,
      "epoch": 0.012317071488669121,
      "grad_norm": 4.051860570895975,
      "kl": 0.0693359375,
      "learning_rate": 9.996257166674148e-07,
      "loss": 0.0028,
      "reward": 2.0829687118530273,
      "reward_std": 0.03916406258940697,
      "rewards/accuracy_reward": 0.889218807220459,
      "rewards/format_reward": 1.0,
      "step": 893
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.0,
      "completion_length": 409.9375,
      "epoch": 0.012330864401870319,
      "grad_norm": 2.0765005631738265,
      "kl": 0.05126953125,
      "learning_rate": 9.996248780424117e-07,
      "loss": 0.0021,
      "reward": 2.066218852996826,
      "reward_std": 0.024836335331201553,
      "rewards/accuracy_reward": 0.8724687099456787,
      "rewards/format_reward": 1.0,
      "step": 894
    },
    {
      "all_correct": 0.25,
      "all_wrong": 0.0,
      "completion_length": 405.3125,
      "epoch": 0.012344657315071516,
      "grad_norm": 2.7762864087935673,
      "kl": 0.060546875,
      "learning_rate": 9.996240384792943e-07,
      "loss": 0.0024,
      "reward": 2.015218734741211,
      "reward_std": 0.016221510246396065,
      "rewards/accuracy_reward": 0.8152186870574951,
      "rewards/format_reward": 1.0,
      "step": 895
    },
    {
      "all_correct": 0.75,
      "all_wrong": 0.0,
      "completion_length": 396.78125,
      "epoch": 0.012358450228272713,
      "grad_norm": 3.3850701091769158,
      "kl": 0.0546875,
      "learning_rate": 9.996231979780638e-07,
      "loss": 0.0022,
      "reward": 2.149437665939331,
      "reward_std": 0.03538715839385986,
      "rewards/accuracy_reward": 0.9494374990463257,
      "rewards/format_reward": 1.0,
      "step": 896
    },
    {
      "all_correct": 0.75,
      "all_wrong": 0.0,
      "completion_length": 397.5625,
      "epoch": 0.01237224314147391,
      "grad_norm": 2.405693173402508,
      "kl": 0.060546875,
      "learning_rate": 9.996223565387222e-07,
      "loss": 0.0024,
      "reward": 2.0840935707092285,
      "reward_std": 0.02343052811920643,
      "rewards/accuracy_reward": 0.8840937614440918,
      "rewards/format_reward": 1.0,
      "step": 897
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.0,
      "completion_length": 412.625,
      "epoch": 0.012386036054675108,
      "grad_norm": 2.416222684892916,
      "kl": 0.06689453125,
      "learning_rate": 9.99621514161271e-07,
      "loss": 0.0027,
      "reward": 2.0687499046325684,
      "reward_std": 0.01389754842966795,
      "rewards/accuracy_reward": 0.8687499761581421,
      "rewards/format_reward": 1.0,
      "step": 898
    },
    {
      "all_correct": 1.0,
      "all_wrong": 0.0,
      "completion_length": 393.0625,
      "epoch": 0.012399828967876305,
      "grad_norm": 3.563209303421202,
      "kl": 0.048583984375,
      "learning_rate": 9.996206708457117e-07,
      "loss": 0.0019,
      "reward": 2.1583125591278076,
      "reward_std": 0.021028826013207436,
      "rewards/accuracy_reward": 0.958312451839447,
      "rewards/format_reward": 1.0,
      "step": 899
    },
    {
      "all_correct": 0.75,
      "all_wrong": 0.0,
      "completion_length": 410.65625,
      "epoch": 0.012413621881077502,
      "grad_norm": 2.5939201074146974,
      "kl": 0.06640625,
      "learning_rate": 9.996198265920458e-07,
      "loss": 0.0027,
      "reward": 2.1188435554504395,
      "reward_std": 0.017672449350357056,
      "rewards/accuracy_reward": 0.9188437461853027,
      "rewards/format_reward": 1.0,
      "step": 900
    },
    {
      "all_correct": 0.25,
      "all_wrong": 0.0,
      "completion_length": 408.5,
      "epoch": 0.0124274147942787,
      "grad_norm": 1.8443103195923343,
      "kl": 0.06201171875,
      "learning_rate": 9.996189814002752e-07,
      "loss": 0.0025,
      "reward": 1.930375099182129,
      "reward_std": 0.009614366106688976,
      "rewards/accuracy_reward": 0.7303749918937683,
      "rewards/format_reward": 1.0,
      "step": 901
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.0,
      "completion_length": 427.03125,
      "epoch": 0.012441207707479897,
      "grad_norm": 3.4247984712235717,
      "kl": 0.0625,
      "learning_rate": 9.99618135270401e-07,
      "loss": 0.0025,
      "reward": 2.0033750534057617,
      "reward_std": 0.030553072690963745,
      "rewards/accuracy_reward": 0.8096249103546143,
      "rewards/format_reward": 1.0,
      "step": 902
    },
    {
      "all_correct": 1.0,
      "all_wrong": 0.0,
      "completion_length": 405.5,
      "epoch": 0.012455000620681094,
      "grad_norm": 1.7692753261289533,
      "kl": 0.07080078125,
      "learning_rate": 9.996172882024252e-07,
      "loss": 0.0028,
      "reward": 2.14634370803833,
      "reward_std": 0.007679288275539875,
      "rewards/accuracy_reward": 0.946343719959259,
      "rewards/format_reward": 1.0,
      "step": 903
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.0,
      "completion_length": 402.25,
      "epoch": 0.012468793533882291,
      "grad_norm": 7.304207242130528,
      "kl": 0.06396484375,
      "learning_rate": 9.99616440196349e-07,
      "loss": 0.0025,
      "reward": 1.9845623970031738,
      "reward_std": 0.018476715311408043,
      "rewards/accuracy_reward": 0.7845624685287476,
      "rewards/format_reward": 1.0,
      "step": 904
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.0,
      "completion_length": 412.75,
      "epoch": 0.012482586447083489,
      "grad_norm": 3.3505590735640407,
      "kl": 0.0595703125,
      "learning_rate": 9.996155912521747e-07,
      "loss": 0.0024,
      "reward": 2.034374952316284,
      "reward_std": 0.01827695034444332,
      "rewards/accuracy_reward": 0.8343750834465027,
      "rewards/format_reward": 1.0,
      "step": 905
    },
    {
      "all_correct": 1.0,
      "all_wrong": 0.0,
      "completion_length": 404.6875,
      "epoch": 0.012496379360284686,
      "grad_norm": 2.71514943542268,
      "kl": 0.060302734375,
      "learning_rate": 9.99614741369903e-07,
      "loss": 0.0024,
      "reward": 2.1310312747955322,
      "reward_std": 0.011738812550902367,
      "rewards/accuracy_reward": 0.9310312271118164,
      "rewards/format_reward": 1.0,
      "step": 906
    },
    {
      "all_correct": 1.0,
      "all_wrong": 0.0,
      "completion_length": 398.34375,
      "epoch": 0.012510172273485883,
      "grad_norm": 1.8794806001105664,
      "kl": 0.064453125,
      "learning_rate": 9.996138905495363e-07,
      "loss": 0.0026,
      "reward": 2.1114375591278076,
      "reward_std": 0.01660860888659954,
      "rewards/accuracy_reward": 0.9114375114440918,
      "rewards/format_reward": 1.0,
      "step": 907
    },
    {
      "all_correct": 1.0,
      "all_wrong": 0.0,
      "completion_length": 398.15625,
      "epoch": 0.01252396518668708,
      "grad_norm": 3.447373044399844,
      "kl": 0.059814453125,
      "learning_rate": 9.996130387910754e-07,
      "loss": 0.0024,
      "reward": 2.13700008392334,
      "reward_std": 0.014783509075641632,
      "rewards/accuracy_reward": 0.9369999170303345,
      "rewards/format_reward": 1.0,
      "step": 908
    },
    {
      "all_correct": 0.75,
      "all_wrong": 0.0,
      "completion_length": 401.375,
      "epoch": 0.012537758099888278,
      "grad_norm": 2.017053033461348,
      "kl": 0.052978515625,
      "learning_rate": 9.996121860945226e-07,
      "loss": 0.0021,
      "reward": 2.1075313091278076,
      "reward_std": 0.018499501049518585,
      "rewards/accuracy_reward": 0.9075311422348022,
      "rewards/format_reward": 1.0,
      "step": 909
    },
    {
      "all_correct": 1.0,
      "all_wrong": 0.0,
      "completion_length": 399.9375,
      "epoch": 0.012551551013089475,
      "grad_norm": 2.0980386920138114,
      "kl": 0.072265625,
      "learning_rate": 9.996113324598791e-07,
      "loss": 0.0029,
      "reward": 2.106375217437744,
      "reward_std": 0.00542815588414669,
      "rewards/accuracy_reward": 0.9063750505447388,
      "rewards/format_reward": 1.0,
      "step": 910
    },
    {
      "all_correct": 0.75,
      "all_wrong": 0.0,
      "completion_length": 401.46875,
      "epoch": 0.012565343926290672,
      "grad_norm": 4.705855992698426,
      "kl": 0.056884765625,
      "learning_rate": 9.996104778871467e-07,
      "loss": 0.0023,
      "reward": 2.1244688034057617,
      "reward_std": 0.023335276171565056,
      "rewards/accuracy_reward": 0.9244687557220459,
      "rewards/format_reward": 1.0,
      "step": 911
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.0,
      "completion_length": 400.1875,
      "epoch": 0.01257913683949187,
      "grad_norm": 2.2043250916135095,
      "kl": 0.06201171875,
      "learning_rate": 9.996096223763269e-07,
      "loss": 0.0025,
      "reward": 2.062812566757202,
      "reward_std": 0.009765689261257648,
      "rewards/accuracy_reward": 0.8628124594688416,
      "rewards/format_reward": 1.0,
      "step": 912
    },
    {
      "all_correct": 1.0,
      "all_wrong": 0.0,
      "completion_length": 400.21875,
      "epoch": 0.012592929752693067,
      "grad_norm": 1.788314218410025,
      "kl": 0.05712890625,
      "learning_rate": 9.996087659274213e-07,
      "loss": 0.0023,
      "reward": 2.172468662261963,
      "reward_std": 0.024640899151563644,
      "rewards/accuracy_reward": 0.9724687337875366,
      "rewards/format_reward": 1.0,
      "step": 913
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.0,
      "completion_length": 406.0,
      "epoch": 0.012606722665894264,
      "grad_norm": 1.8442002636505592,
      "kl": 0.0556640625,
      "learning_rate": 9.996079085404316e-07,
      "loss": 0.0022,
      "reward": 2.065312623977661,
      "reward_std": 0.006495218258351088,
      "rewards/accuracy_reward": 0.8653125166893005,
      "rewards/format_reward": 1.0,
      "step": 914
    },
    {
      "all_correct": 0.75,
      "all_wrong": 0.0,
      "completion_length": 396.53125,
      "epoch": 0.012620515579095461,
      "grad_norm": 2.4493533125284195,
      "kl": 0.060791015625,
      "learning_rate": 9.996070502153593e-07,
      "loss": 0.0024,
      "reward": 2.0648751258850098,
      "reward_std": 0.016605194658041,
      "rewards/accuracy_reward": 0.8648750185966492,
      "rewards/format_reward": 1.0,
      "step": 915
    },
    {
      "all_correct": 0.75,
      "all_wrong": 0.0,
      "completion_length": 392.3125,
      "epoch": 0.012634308492296659,
      "grad_norm": 1.874395525977322,
      "kl": 0.060302734375,
      "learning_rate": 9.996061909522062e-07,
      "loss": 0.0024,
      "reward": 2.106156349182129,
      "reward_std": 0.01716047339141369,
      "rewards/accuracy_reward": 0.9061562418937683,
      "rewards/format_reward": 1.0,
      "step": 916
    },
    {
      "all_correct": 0.75,
      "all_wrong": 0.0,
      "completion_length": 374.5625,
      "epoch": 0.012648101405497856,
      "grad_norm": 3.051945071161466,
      "kl": 0.06298828125,
      "learning_rate": 9.996053307509735e-07,
      "loss": 0.0025,
      "reward": 2.127500057220459,
      "reward_std": 0.02436526119709015,
      "rewards/accuracy_reward": 0.9337500333786011,
      "rewards/format_reward": 1.0,
      "step": 917
    },
    {
      "all_correct": 1.0,
      "all_wrong": 0.0,
      "completion_length": 375.1875,
      "epoch": 0.012661894318699053,
      "grad_norm": 4.27526689440216,
      "kl": 0.068359375,
      "learning_rate": 9.996044696116634e-07,
      "loss": 0.0027,
      "reward": 2.120593786239624,
      "reward_std": 0.027109824120998383,
      "rewards/accuracy_reward": 0.9205936789512634,
      "rewards/format_reward": 1.0,
      "step": 918
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.0,
      "completion_length": 372.09375,
      "epoch": 0.01267568723190025,
      "grad_norm": 4.5924682802658205,
      "kl": 0.06884765625,
      "learning_rate": 9.99603607534277e-07,
      "loss": 0.0028,
      "reward": 2.04296875,
      "reward_std": 0.016068341210484505,
      "rewards/accuracy_reward": 0.8429688215255737,
      "rewards/format_reward": 1.0,
      "step": 919
    },
    {
      "all_correct": 0.75,
      "all_wrong": 0.0,
      "completion_length": 376.5,
      "epoch": 0.012689480145101448,
      "grad_norm": 2.3765006752269,
      "kl": 0.06787109375,
      "learning_rate": 9.996027445188163e-07,
      "loss": 0.0027,
      "reward": 2.05831241607666,
      "reward_std": 0.01175000797957182,
      "rewards/accuracy_reward": 0.8583124876022339,
      "rewards/format_reward": 1.0,
      "step": 920
    },
    {
      "all_correct": 0.75,
      "all_wrong": 0.0,
      "completion_length": 375.53125,
      "epoch": 0.012703273058302643,
      "grad_norm": 2.593287870405021,
      "kl": 0.05712890625,
      "learning_rate": 9.996018805652824e-07,
      "loss": 0.0023,
      "reward": 2.1519062519073486,
      "reward_std": 0.02840704470872879,
      "rewards/accuracy_reward": 0.9581562876701355,
      "rewards/format_reward": 1.0,
      "step": 921
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.0,
      "completion_length": 377.53125,
      "epoch": 0.01271706597150384,
      "grad_norm": 6.771963326537981,
      "kl": 0.06884765625,
      "learning_rate": 9.996010156736776e-07,
      "loss": 0.0028,
      "reward": 2.0836563110351562,
      "reward_std": 0.02402690052986145,
      "rewards/accuracy_reward": 0.8899062275886536,
      "rewards/format_reward": 1.0,
      "step": 922
    },
    {
      "all_correct": 0.75,
      "all_wrong": 0.0,
      "completion_length": 384.0625,
      "epoch": 0.012730858884705038,
      "grad_norm": 2.3159900000790787,
      "kl": 0.055908203125,
      "learning_rate": 9.996001498440033e-07,
      "loss": 0.0022,
      "reward": 2.0596563816070557,
      "reward_std": 0.007038048934191465,
      "rewards/accuracy_reward": 0.8596562147140503,
      "rewards/format_reward": 1.0,
      "step": 923
    },
    {
      "all_correct": 0.75,
      "all_wrong": 0.0,
      "completion_length": 370.75,
      "epoch": 0.012744651797906235,
      "grad_norm": 5.794802010367455,
      "kl": 0.06640625,
      "learning_rate": 9.995992830762607e-07,
      "loss": 0.0027,
      "reward": 2.088062286376953,
      "reward_std": 0.01949411630630493,
      "rewards/accuracy_reward": 0.8880625367164612,
      "rewards/format_reward": 1.0,
      "step": 924
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.0,
      "completion_length": 361.0625,
      "epoch": 0.012758444711107432,
      "grad_norm": 3.8378583917643847,
      "kl": 0.06884765625,
      "learning_rate": 9.995984153704518e-07,
      "loss": 0.0028,
      "reward": 2.0709376335144043,
      "reward_std": 0.03367071971297264,
      "rewards/accuracy_reward": 0.8834375143051147,
      "rewards/format_reward": 1.0,
      "step": 925
    },
    {
      "all_correct": 0.25,
      "all_wrong": 0.0,
      "completion_length": 364.53125,
      "epoch": 0.01277223762430863,
      "grad_norm": 2.4266878297545444,
      "kl": 0.06982421875,
      "learning_rate": 9.995975467265782e-07,
      "loss": 0.0028,
      "reward": 2.0297813415527344,
      "reward_std": 0.0686185285449028,
      "rewards/accuracy_reward": 0.8610312342643738,
      "rewards/format_reward": 1.0,
      "step": 926
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.0,
      "completion_length": 374.78125,
      "epoch": 0.012786030537509827,
      "grad_norm": 3.76553231019906,
      "kl": 0.06396484375,
      "learning_rate": 9.995966771446417e-07,
      "loss": 0.0026,
      "reward": 2.0322186946868896,
      "reward_std": 0.03391903638839722,
      "rewards/accuracy_reward": 0.8322186470031738,
      "rewards/format_reward": 1.0,
      "step": 927
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.0,
      "completion_length": 394.84375,
      "epoch": 0.012799823450711024,
      "grad_norm": 2.620665321086029,
      "kl": 0.060791015625,
      "learning_rate": 9.995958066246436e-07,
      "loss": 0.0024,
      "reward": 2.043375015258789,
      "reward_std": 0.026476388797163963,
      "rewards/accuracy_reward": 0.843375027179718,
      "rewards/format_reward": 1.0,
      "step": 928
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.0,
      "completion_length": 379.53125,
      "epoch": 0.012813616363912221,
      "grad_norm": 3.013001107323946,
      "kl": 0.0673828125,
      "learning_rate": 9.995949351665856e-07,
      "loss": 0.0027,
      "reward": 2.1157186031341553,
      "reward_std": 0.03292486071586609,
      "rewards/accuracy_reward": 0.9219688177108765,
      "rewards/format_reward": 1.0,
      "step": 929
    },
    {
      "all_correct": 1.0,
      "all_wrong": 0.0,
      "completion_length": 389.375,
      "epoch": 0.012827409277113419,
      "grad_norm": 2.0995687056642676,
      "kl": 0.0595703125,
      "learning_rate": 9.995940627704696e-07,
      "loss": 0.0024,
      "reward": 2.1374998092651367,
      "reward_std": 0.009665516205132008,
      "rewards/accuracy_reward": 0.9375000596046448,
      "rewards/format_reward": 1.0,
      "step": 930
    },
    {
      "all_correct": 0.75,
      "all_wrong": 0.0,
      "completion_length": 390.3125,
      "epoch": 0.012841202190314616,
      "grad_norm": 1.895892621246368,
      "kl": 0.061767578125,
      "learning_rate": 9.995931894362968e-07,
      "loss": 0.0024,
      "reward": 2.1489062309265137,
      "reward_std": 0.021223776042461395,
      "rewards/accuracy_reward": 0.9551562666893005,
      "rewards/format_reward": 1.0,
      "step": 931
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.0,
      "completion_length": 372.09375,
      "epoch": 0.012854995103515813,
      "grad_norm": 1.7104553026834026,
      "kl": 0.060791015625,
      "learning_rate": 9.995923151640693e-07,
      "loss": 0.0024,
      "reward": 2.0697498321533203,
      "reward_std": 0.03370888903737068,
      "rewards/accuracy_reward": 0.8822500705718994,
      "rewards/format_reward": 1.0,
      "step": 932
    },
    {
      "all_correct": 1.0,
      "all_wrong": 0.0,
      "completion_length": 399.0625,
      "epoch": 0.01286878801671701,
      "grad_norm": 3.360395721276478,
      "kl": 0.06494140625,
      "learning_rate": 9.995914399537884e-07,
      "loss": 0.0026,
      "reward": 2.080531120300293,
      "reward_std": 0.010477394796907902,
      "rewards/accuracy_reward": 0.8805312514305115,
      "rewards/format_reward": 1.0,
      "step": 933
    },
    {
      "all_correct": 0.75,
      "all_wrong": 0.0,
      "completion_length": 394.15625,
      "epoch": 0.012882580929918208,
      "grad_norm": 2.143762023639265,
      "kl": 0.061279296875,
      "learning_rate": 9.99590563805456e-07,
      "loss": 0.0024,
      "reward": 2.110562324523926,
      "reward_std": 0.019955508410930634,
      "rewards/accuracy_reward": 0.9105625152587891,
      "rewards/format_reward": 1.0,
      "step": 934
    },
    {
      "all_correct": 0.75,
      "all_wrong": 0.0,
      "completion_length": 384.53125,
      "epoch": 0.012896373843119405,
      "grad_norm": 3.3071350463292495,
      "kl": 0.064453125,
      "learning_rate": 9.995896867190736e-07,
      "loss": 0.0026,
      "reward": 2.1410000324249268,
      "reward_std": 0.033771172165870667,
      "rewards/accuracy_reward": 0.9472500085830688,
      "rewards/format_reward": 1.0,
      "step": 935
    },
    {
      "all_correct": 1.0,
      "all_wrong": 0.0,
      "completion_length": 409.6875,
      "epoch": 0.012910166756320602,
      "grad_norm": 2.0141665161157936,
      "kl": 0.061767578125,
      "learning_rate": 9.995888086946428e-07,
      "loss": 0.0025,
      "reward": 2.0889999866485596,
      "reward_std": 0.0042914170771837234,
      "rewards/accuracy_reward": 0.8889999389648438,
      "rewards/format_reward": 1.0,
      "step": 936
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.0,
      "completion_length": 408.125,
      "epoch": 0.0129239596695218,
      "grad_norm": 1.6337262572752422,
      "kl": 0.056396484375,
      "learning_rate": 9.995879297321654e-07,
      "loss": 0.0023,
      "reward": 2.0865938663482666,
      "reward_std": 0.04895639047026634,
      "rewards/accuracy_reward": 0.8865936994552612,
      "rewards/format_reward": 1.0,
      "step": 937
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.0,
      "completion_length": 387.09375,
      "epoch": 0.012937752582722997,
      "grad_norm": 2.0620506370125975,
      "kl": 0.05810546875,
      "learning_rate": 9.995870498316428e-07,
      "loss": 0.0023,
      "reward": 1.9742813110351562,
      "reward_std": 0.00941779650747776,
      "rewards/accuracy_reward": 0.7742812037467957,
      "rewards/format_reward": 1.0,
      "step": 938
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.0,
      "completion_length": 397.28125,
      "epoch": 0.012951545495924194,
      "grad_norm": 2.5984474504990605,
      "kl": 0.054443359375,
      "learning_rate": 9.995861689930768e-07,
      "loss": 0.0022,
      "reward": 2.011218786239624,
      "reward_std": 0.026280401274561882,
      "rewards/accuracy_reward": 0.8112187385559082,
      "rewards/format_reward": 1.0,
      "step": 939
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.0,
      "completion_length": 402.5625,
      "epoch": 0.012965338409125391,
      "grad_norm": 3.409584811066543,
      "kl": 0.06396484375,
      "learning_rate": 9.995852872164695e-07,
      "loss": 0.0026,
      "reward": 2.0370311737060547,
      "reward_std": 0.014715050347149372,
      "rewards/accuracy_reward": 0.8370311856269836,
      "rewards/format_reward": 1.0,
      "step": 940
    },
    {
      "all_correct": 1.0,
      "all_wrong": 0.0,
      "completion_length": 418.125,
      "epoch": 0.012979131322326589,
      "grad_norm": 3.5886430068693205,
      "kl": 0.060791015625,
      "learning_rate": 9.995844045018216e-07,
      "loss": 0.0024,
      "reward": 2.1205625534057617,
      "reward_std": 0.019434409216046333,
      "rewards/accuracy_reward": 0.9205625057220459,
      "rewards/format_reward": 1.0,
      "step": 941
    },
    {
      "all_correct": 0.75,
      "all_wrong": 0.0,
      "completion_length": 397.4375,
      "epoch": 0.012992924235527786,
      "grad_norm": 2.2954037921104824,
      "kl": 0.0654296875,
      "learning_rate": 9.995835208491356e-07,
      "loss": 0.0026,
      "reward": 2.111875057220459,
      "reward_std": 0.018479883670806885,
      "rewards/accuracy_reward": 0.9118750095367432,
      "rewards/format_reward": 1.0,
      "step": 942
    },
    {
      "all_correct": 0.75,
      "all_wrong": 0.0,
      "completion_length": 404.3125,
      "epoch": 0.013006717148728983,
      "grad_norm": 2.167334040093991,
      "kl": 0.05712890625,
      "learning_rate": 9.995826362584129e-07,
      "loss": 0.0023,
      "reward": 1.9730000495910645,
      "reward_std": 0.006898774299770594,
      "rewards/accuracy_reward": 0.7730000019073486,
      "rewards/format_reward": 1.0,
      "step": 943
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.0,
      "completion_length": 412.34375,
      "epoch": 0.01302051006193018,
      "grad_norm": 4.434470495093593,
      "kl": 0.0625,
      "learning_rate": 9.99581750729655e-07,
      "loss": 0.0025,
      "reward": 2.065218925476074,
      "reward_std": 0.040436986833810806,
      "rewards/accuracy_reward": 0.871468722820282,
      "rewards/format_reward": 1.0,
      "step": 944
    },
    {
      "all_correct": 0.75,
      "all_wrong": 0.0,
      "completion_length": 425.34375,
      "epoch": 0.013034302975131378,
      "grad_norm": 2.6563888076754436,
      "kl": 0.0576171875,
      "learning_rate": 9.995808642628633e-07,
      "loss": 0.0023,
      "reward": 2.063312530517578,
      "reward_std": 0.030278170481324196,
      "rewards/accuracy_reward": 0.8695625066757202,
      "rewards/format_reward": 1.0,
      "step": 945
    },
    {
      "all_correct": 0.75,
      "all_wrong": 0.0,
      "completion_length": 404.5,
      "epoch": 0.013048095888332575,
      "grad_norm": 4.080358092003208,
      "kl": 0.06005859375,
      "learning_rate": 9.995799768580403e-07,
      "loss": 0.0024,
      "reward": 2.103250026702881,
      "reward_std": 0.02897321805357933,
      "rewards/accuracy_reward": 0.9032500386238098,
      "rewards/format_reward": 1.0,
      "step": 946
    },
    {
      "all_correct": 1.0,
      "all_wrong": 0.0,
      "completion_length": 413.3125,
      "epoch": 0.013061888801533772,
      "grad_norm": 0.96206234899221,
      "kl": 0.0517578125,
      "learning_rate": 9.995790885151871e-07,
      "loss": 0.0021,
      "reward": 2.141031265258789,
      "reward_std": 0.0031408481299877167,
      "rewards/accuracy_reward": 0.9410312175750732,
      "rewards/format_reward": 1.0,
      "step": 947
    },
    {
      "all_correct": 0.75,
      "all_wrong": 0.0,
      "completion_length": 397.0,
      "epoch": 0.01307568171473497,
      "grad_norm": 1.9783221294050166,
      "kl": 0.05224609375,
      "learning_rate": 9.995781992343053e-07,
      "loss": 0.0021,
      "reward": 2.1516873836517334,
      "reward_std": 0.025221746414899826,
      "rewards/accuracy_reward": 0.957937479019165,
      "rewards/format_reward": 1.0,
      "step": 948
    },
    {
      "all_correct": 0.75,
      "all_wrong": 0.0,
      "completion_length": 387.90625,
      "epoch": 0.013089474627936167,
      "grad_norm": 1.603459321759574,
      "kl": 0.05908203125,
      "learning_rate": 9.99577309015397e-07,
      "loss": 0.0024,
      "reward": 2.1642186641693115,
      "reward_std": 0.01903594098985195,
      "rewards/accuracy_reward": 0.9704688191413879,
      "rewards/format_reward": 1.0,
      "step": 949
    },
    {
      "all_correct": 0.75,
      "all_wrong": 0.0,
      "completion_length": 401.53125,
      "epoch": 0.013103267541137364,
      "grad_norm": 1.891060649459561,
      "kl": 0.06494140625,
      "learning_rate": 9.995764178584633e-07,
      "loss": 0.0026,
      "reward": 2.1019062995910645,
      "reward_std": 0.01263848040252924,
      "rewards/accuracy_reward": 0.9019061923027039,
      "rewards/format_reward": 1.0,
      "step": 950
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.0,
      "completion_length": 410.375,
      "epoch": 0.013117060454338561,
      "grad_norm": 4.133796988321448,
      "kl": 0.060546875,
      "learning_rate": 9.995755257635064e-07,
      "loss": 0.0024,
      "reward": 2.0258126258850098,
      "reward_std": 0.031173421069979668,
      "rewards/accuracy_reward": 0.8258125185966492,
      "rewards/format_reward": 1.0,
      "step": 951
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.0,
      "completion_length": 375.21875,
      "epoch": 0.013130853367539759,
      "grad_norm": 2.0682174174411756,
      "kl": 0.068359375,
      "learning_rate": 9.995746327305276e-07,
      "loss": 0.0027,
      "reward": 2.1248438358306885,
      "reward_std": 0.03573830798268318,
      "rewards/accuracy_reward": 0.9373438358306885,
      "rewards/format_reward": 1.0,
      "step": 952
    },
    {
      "all_correct": 0.75,
      "all_wrong": 0.0,
      "completion_length": 399.21875,
      "epoch": 0.013144646280740956,
      "grad_norm": 2.3116031717973557,
      "kl": 0.05419921875,
      "learning_rate": 9.99573738759529e-07,
      "loss": 0.0022,
      "reward": 2.05078125,
      "reward_std": 0.02314024046063423,
      "rewards/accuracy_reward": 0.8507813215255737,
      "rewards/format_reward": 1.0,
      "step": 953
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.0,
      "completion_length": 383.53125,
      "epoch": 0.013158439193942153,
      "grad_norm": 1.9536978347300982,
      "kl": 0.05224609375,
      "learning_rate": 9.995728438505117e-07,
      "loss": 0.0021,
      "reward": 2.040968894958496,
      "reward_std": 0.02620755508542061,
      "rewards/accuracy_reward": 0.8409687280654907,
      "rewards/format_reward": 1.0,
      "step": 954
    },
    {
      "all_correct": 0.75,
      "all_wrong": 0.0,
      "completion_length": 381.59375,
      "epoch": 0.01317223210714335,
      "grad_norm": 3.4775180665448615,
      "kl": 0.06591796875,
      "learning_rate": 9.99571948003478e-07,
      "loss": 0.0026,
      "reward": 2.121000051498413,
      "reward_std": 0.0229371078312397,
      "rewards/accuracy_reward": 0.921000063419342,
      "rewards/format_reward": 1.0,
      "step": 955
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.0,
      "completion_length": 383.34375,
      "epoch": 0.013186025020344548,
      "grad_norm": 2.230545767425793,
      "kl": 0.058837890625,
      "learning_rate": 9.99571051218429e-07,
      "loss": 0.0023,
      "reward": 2.120968818664551,
      "reward_std": 0.04076975956559181,
      "rewards/accuracy_reward": 0.9272187352180481,
      "rewards/format_reward": 1.0,
      "step": 956
    },
    {
      "all_correct": 0.75,
      "all_wrong": 0.0,
      "completion_length": 378.9375,
      "epoch": 0.013199817933545745,
      "grad_norm": 12.187507277584867,
      "kl": 0.058349609375,
      "learning_rate": 9.995701534953669e-07,
      "loss": 0.0023,
      "reward": 2.124687433242798,
      "reward_std": 0.03506990894675255,
      "rewards/accuracy_reward": 0.9246875047683716,
      "rewards/format_reward": 1.0,
      "step": 957
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.0,
      "completion_length": 372.6875,
      "epoch": 0.01321361084674694,
      "grad_norm": 2.225453856215837,
      "kl": 0.060791015625,
      "learning_rate": 9.99569254834293e-07,
      "loss": 0.0024,
      "reward": 2.1204376220703125,
      "reward_std": 0.05662054196000099,
      "rewards/accuracy_reward": 0.9391874670982361,
      "rewards/format_reward": 1.0,
      "step": 958
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.0,
      "completion_length": 365.375,
      "epoch": 0.013227403759948138,
      "grad_norm": 3.1531469343554335,
      "kl": 0.059326171875,
      "learning_rate": 9.995683552352092e-07,
      "loss": 0.0024,
      "reward": 2.123000144958496,
      "reward_std": 0.04171569645404816,
      "rewards/accuracy_reward": 0.9354999661445618,
      "rewards/format_reward": 1.0,
      "step": 959
    },
    {
      "all_correct": 0.75,
      "all_wrong": 0.0,
      "completion_length": 366.6875,
      "epoch": 0.013241196673149335,
      "grad_norm": 2.510283560853735,
      "kl": 0.0546875,
      "learning_rate": 9.99567454698117e-07,
      "loss": 0.0022,
      "reward": 2.0232813358306885,
      "reward_std": 0.04163326323032379,
      "rewards/accuracy_reward": 0.8420312404632568,
      "rewards/format_reward": 1.0,
      "step": 960
    },
    {
      "all_correct": 0.75,
      "all_wrong": 0.0,
      "completion_length": 397.0625,
      "epoch": 0.013254989586350532,
      "grad_norm": 2.8777407417439105,
      "kl": 0.0654296875,
      "learning_rate": 9.99566553223018e-07,
      "loss": 0.0026,
      "reward": 2.1313750743865967,
      "reward_std": 0.022761916741728783,
      "rewards/accuracy_reward": 0.9313749074935913,
      "rewards/format_reward": 1.0,
      "step": 961
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.0,
      "completion_length": 380.4375,
      "epoch": 0.01326878249955173,
      "grad_norm": 2.4662369354427947,
      "kl": 0.06005859375,
      "learning_rate": 9.995656508099145e-07,
      "loss": 0.0024,
      "reward": 2.074718952178955,
      "reward_std": 0.05522676557302475,
      "rewards/accuracy_reward": 0.8934687376022339,
      "rewards/format_reward": 1.0,
      "step": 962
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.0,
      "completion_length": 371.4375,
      "epoch": 0.013282575412752927,
      "grad_norm": 2.316676704282207,
      "kl": 0.0576171875,
      "learning_rate": 9.995647474588077e-07,
      "loss": 0.0023,
      "reward": 2.069406270980835,
      "reward_std": 0.040666162967681885,
      "rewards/accuracy_reward": 0.881906270980835,
      "rewards/format_reward": 1.0,
      "step": 963
    },
    {
      "all_correct": 0.75,
      "all_wrong": 0.0,
      "completion_length": 386.0625,
      "epoch": 0.013296368325954124,
      "grad_norm": 6.451994796671183,
      "kl": 0.059814453125,
      "learning_rate": 9.995638431696994e-07,
      "loss": 0.0024,
      "reward": 2.08021879196167,
      "reward_std": 0.036402128636837006,
      "rewards/accuracy_reward": 0.8802187442779541,
      "rewards/format_reward": 1.0,
      "step": 964
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.0,
      "completion_length": 396.0625,
      "epoch": 0.013310161239155321,
      "grad_norm": 2.1422472664307532,
      "kl": 0.0625,
      "learning_rate": 9.995629379425912e-07,
      "loss": 0.0025,
      "reward": 2.0102813243865967,
      "reward_std": 0.026051711291074753,
      "rewards/accuracy_reward": 0.816531240940094,
      "rewards/format_reward": 1.0,
      "step": 965
    },
    {
      "all_correct": 0.25,
      "all_wrong": 0.0,
      "completion_length": 385.90625,
      "epoch": 0.013323954152356519,
      "grad_norm": 2.067149110197044,
      "kl": 0.0615234375,
      "learning_rate": 9.995620317774851e-07,
      "loss": 0.0025,
      "reward": 1.9296250343322754,
      "reward_std": 0.019551243633031845,
      "rewards/accuracy_reward": 0.7296250462532043,
      "rewards/format_reward": 1.0,
      "step": 966
    },
    {
      "all_correct": 1.0,
      "all_wrong": 0.0,
      "completion_length": 396.75,
      "epoch": 0.013337747065557716,
      "grad_norm": 6.251715887985888,
      "kl": 0.059326171875,
      "learning_rate": 9.995611246743824e-07,
      "loss": 0.0024,
      "reward": 2.152656316757202,
      "reward_std": 0.01397896371781826,
      "rewards/accuracy_reward": 0.9526562690734863,
      "rewards/format_reward": 1.0,
      "step": 967
    },
    {
      "all_correct": 0.75,
      "all_wrong": 0.0,
      "completion_length": 392.0,
      "epoch": 0.013351539978758913,
      "grad_norm": 2.5837081521457193,
      "kl": 0.0634765625,
      "learning_rate": 9.99560216633285e-07,
      "loss": 0.0025,
      "reward": 2.1388750076293945,
      "reward_std": 0.01405518501996994,
      "rewards/accuracy_reward": 0.9388750791549683,
      "rewards/format_reward": 1.0,
      "step": 968
    },
    {
      "all_correct": 0.75,
      "all_wrong": 0.0,
      "completion_length": 401.8125,
      "epoch": 0.01336533289196011,
      "grad_norm": 3.4240178637681313,
      "kl": 0.0625,
      "learning_rate": 9.995593076541947e-07,
      "loss": 0.0025,
      "reward": 2.0802500247955322,
      "reward_std": 0.017234977334737778,
      "rewards/accuracy_reward": 0.8802499771118164,
      "rewards/format_reward": 1.0,
      "step": 969
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.0,
      "completion_length": 408.75,
      "epoch": 0.013379125805161308,
      "grad_norm": 2.0050233770833965,
      "kl": 0.060546875,
      "learning_rate": 9.99558397737113e-07,
      "loss": 0.0024,
      "reward": 2.050093650817871,
      "reward_std": 0.020653944462537766,
      "rewards/accuracy_reward": 0.8500937819480896,
      "rewards/format_reward": 1.0,
      "step": 970
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.0,
      "completion_length": 404.4375,
      "epoch": 0.013392918718362505,
      "grad_norm": 1.100530179238951,
      "kl": 0.06298828125,
      "learning_rate": 9.995574868820417e-07,
      "loss": 0.0025,
      "reward": 1.9181562662124634,
      "reward_std": 0.010097677819430828,
      "rewards/accuracy_reward": 0.7181562185287476,
      "rewards/format_reward": 1.0,
      "step": 971
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.0,
      "completion_length": 394.96875,
      "epoch": 0.013406711631563702,
      "grad_norm": 2.3083452865416407,
      "kl": 0.06298828125,
      "learning_rate": 9.995565750889826e-07,
      "loss": 0.0025,
      "reward": 1.9631249904632568,
      "reward_std": 0.03356027603149414,
      "rewards/accuracy_reward": 0.7631250619888306,
      "rewards/format_reward": 1.0,
      "step": 972
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.0,
      "completion_length": 396.8125,
      "epoch": 0.0134205045447649,
      "grad_norm": 1.975854283008749,
      "kl": 0.05517578125,
      "learning_rate": 9.995556623579373e-07,
      "loss": 0.0022,
      "reward": 2.106187343597412,
      "reward_std": 0.03825730085372925,
      "rewards/accuracy_reward": 0.9124375581741333,
      "rewards/format_reward": 1.0,
      "step": 973
    },
    {
      "all_correct": 0.75,
      "all_wrong": 0.0,
      "completion_length": 392.0625,
      "epoch": 0.013434297457966097,
      "grad_norm": 2.530695759744838,
      "kl": 0.068359375,
      "learning_rate": 9.995547486889077e-07,
      "loss": 0.0027,
      "reward": 2.073500156402588,
      "reward_std": 0.033998943865299225,
      "rewards/accuracy_reward": 0.8735000491142273,
      "rewards/format_reward": 1.0,
      "step": 974
    },
    {
      "all_correct": 1.0,
      "all_wrong": 0.0,
      "completion_length": 414.09375,
      "epoch": 0.013448090371167294,
      "grad_norm": 1.6458334499336997,
      "kl": 0.06396484375,
      "learning_rate": 9.995538340818951e-07,
      "loss": 0.0026,
      "reward": 2.151218891143799,
      "reward_std": 0.010997899807989597,
      "rewards/accuracy_reward": 0.9512187242507935,
      "rewards/format_reward": 1.0,
      "step": 975
    },
    {
      "all_correct": 0.75,
      "all_wrong": 0.0,
      "completion_length": 392.375,
      "epoch": 0.013461883284368491,
      "grad_norm": 0.2477452730346337,
      "kl": 0.053955078125,
      "learning_rate": 9.995529185369018e-07,
      "loss": 0.0022,
      "reward": 1.9482500553131104,
      "reward_std": 0.0,
      "rewards/accuracy_reward": 0.7482500672340393,
      "rewards/format_reward": 1.0,
      "step": 976
    },
    {
      "all_correct": 1.0,
      "all_wrong": 0.0,
      "completion_length": 398.40625,
      "epoch": 0.013475676197569689,
      "grad_norm": 3.0131001294551965,
      "kl": 0.052978515625,
      "learning_rate": 9.99552002053929e-07,
      "loss": 0.0021,
      "reward": 2.1441564559936523,
      "reward_std": 0.02559378556907177,
      "rewards/accuracy_reward": 0.9441561698913574,
      "rewards/format_reward": 1.0,
      "step": 977
    },
    {
      "all_correct": 1.0,
      "all_wrong": 0.0,
      "completion_length": 418.0,
      "epoch": 0.013489469110770886,
      "grad_norm": 2.539167597786399,
      "kl": 0.056640625,
      "learning_rate": 9.995510846329788e-07,
      "loss": 0.0023,
      "reward": 2.0927810668945312,
      "reward_std": 0.029973864555358887,
      "rewards/accuracy_reward": 0.8927812576293945,
      "rewards/format_reward": 1.0,
      "step": 978
    },
    {
      "all_correct": 0.75,
      "all_wrong": 0.0,
      "completion_length": 401.84375,
      "epoch": 0.013503262023972083,
      "grad_norm": 1.659274302788287,
      "kl": 0.0654296875,
      "learning_rate": 9.995501662740524e-07,
      "loss": 0.0026,
      "reward": 2.063000202178955,
      "reward_std": 0.006210608873516321,
      "rewards/accuracy_reward": 0.8630000352859497,
      "rewards/format_reward": 1.0,
      "step": 979
    },
    {
      "all_correct": 0.75,
      "all_wrong": 0.0,
      "completion_length": 376.6875,
      "epoch": 0.01351705493717328,
      "grad_norm": 1.9213398583182117,
      "kl": 0.064453125,
      "learning_rate": 9.99549246977152e-07,
      "loss": 0.0026,
      "reward": 2.143531322479248,
      "reward_std": 0.07075823098421097,
      "rewards/accuracy_reward": 0.9497812986373901,
      "rewards/format_reward": 1.0,
      "step": 980
    },
    {
      "all_correct": 0.75,
      "all_wrong": 0.0,
      "completion_length": 387.8125,
      "epoch": 0.013530847850374478,
      "grad_norm": 3.125976968410198,
      "kl": 0.0625,
      "learning_rate": 9.995483267422792e-07,
      "loss": 0.0025,
      "reward": 2.0835938453674316,
      "reward_std": 0.0372149720788002,
      "rewards/accuracy_reward": 0.8898437023162842,
      "rewards/format_reward": 1.0,
      "step": 981
    },
    {
      "all_correct": 0.75,
      "all_wrong": 0.0,
      "completion_length": 395.96875,
      "epoch": 0.013544640763575675,
      "grad_norm": 2.500428329828002,
      "kl": 0.05859375,
      "learning_rate": 9.99547405569436e-07,
      "loss": 0.0023,
      "reward": 2.0518126487731934,
      "reward_std": 0.020919105038046837,
      "rewards/accuracy_reward": 0.8518125414848328,
      "rewards/format_reward": 1.0,
      "step": 982
    },
    {
      "all_correct": 0.0,
      "all_wrong": 0.0,
      "completion_length": 387.71875,
      "epoch": 0.013558433676776872,
      "grad_norm": 2.1681708674973326,
      "kl": 0.061279296875,
      "learning_rate": 9.995464834586235e-07,
      "loss": 0.0025,
      "reward": 1.9480624198913574,
      "reward_std": 0.03235013037919998,
      "rewards/accuracy_reward": 0.7543125152587891,
      "rewards/format_reward": 1.0,
      "step": 983
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.0,
      "completion_length": 405.5,
      "epoch": 0.01357222658997807,
      "grad_norm": 1.7307679603834816,
      "kl": 0.0673828125,
      "learning_rate": 9.99545560409844e-07,
      "loss": 0.0027,
      "reward": 2.0042500495910645,
      "reward_std": 0.012961498461663723,
      "rewards/accuracy_reward": 0.8042500019073486,
      "rewards/format_reward": 1.0,
      "step": 984
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.0,
      "completion_length": 395.46875,
      "epoch": 0.013586019503179267,
      "grad_norm": 1.8536788783270453,
      "kl": 0.06396484375,
      "learning_rate": 9.995446364230991e-07,
      "loss": 0.0026,
      "reward": 2.066718816757202,
      "reward_std": 0.03827047348022461,
      "rewards/accuracy_reward": 0.8667187690734863,
      "rewards/format_reward": 1.0,
      "step": 985
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.0,
      "completion_length": 398.59375,
      "epoch": 0.013599812416380464,
      "grad_norm": 2.6835941275324284,
      "kl": 0.06298828125,
      "learning_rate": 9.995437114983901e-07,
      "loss": 0.0025,
      "reward": 1.9026875495910645,
      "reward_std": 0.014580855146050453,
      "rewards/accuracy_reward": 0.7026875019073486,
      "rewards/format_reward": 1.0,
      "step": 986
    },
    {
      "all_correct": 0.75,
      "all_wrong": 0.0,
      "completion_length": 416.5,
      "epoch": 0.013613605329581661,
      "grad_norm": 22.492767801161104,
      "kl": 0.057861328125,
      "learning_rate": 9.995427856357194e-07,
      "loss": 0.0023,
      "reward": 2.0933125019073486,
      "reward_std": 0.02505647763609886,
      "rewards/accuracy_reward": 0.8933125734329224,
      "rewards/format_reward": 1.0,
      "step": 987
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.0,
      "completion_length": 397.65625,
      "epoch": 0.013627398242782859,
      "grad_norm": 4.966099600360118,
      "kl": 0.06494140625,
      "learning_rate": 9.995418588350884e-07,
      "loss": 0.0026,
      "reward": 1.888718843460083,
      "reward_std": 0.02759726345539093,
      "rewards/accuracy_reward": 0.688718855381012,
      "rewards/format_reward": 1.0,
      "step": 988
    },
    {
      "all_correct": 0.75,
      "all_wrong": 0.0,
      "completion_length": 417.125,
      "epoch": 0.013641191155984056,
      "grad_norm": 2.1799339139432448,
      "kl": 0.06494140625,
      "learning_rate": 9.99540931096499e-07,
      "loss": 0.0026,
      "reward": 2.0843124389648438,
      "reward_std": 0.012447066605091095,
      "rewards/accuracy_reward": 0.8843125104904175,
      "rewards/format_reward": 1.0,
      "step": 989
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.0,
      "completion_length": 399.8125,
      "epoch": 0.013654984069185253,
      "grad_norm": 3.6513041943975875,
      "kl": 0.0634765625,
      "learning_rate": 9.995400024199523e-07,
      "loss": 0.0025,
      "reward": 2.0113439559936523,
      "reward_std": 0.032104697078466415,
      "rewards/accuracy_reward": 0.8175938129425049,
      "rewards/format_reward": 1.0,
      "step": 990
    },
    {
      "all_correct": 0.75,
      "all_wrong": 0.0,
      "completion_length": 391.5625,
      "epoch": 0.01366877698238645,
      "grad_norm": 1.3049986212995772,
      "kl": 0.06201171875,
      "learning_rate": 9.995390728054508e-07,
      "loss": 0.0025,
      "reward": 2.0866565704345703,
      "reward_std": 0.012286011129617691,
      "rewards/accuracy_reward": 0.8866562247276306,
      "rewards/format_reward": 1.0,
      "step": 991
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.0,
      "completion_length": 420.46875,
      "epoch": 0.013682569895587648,
      "grad_norm": 2.130959311738575,
      "kl": 0.05908203125,
      "learning_rate": 9.995381422529962e-07,
      "loss": 0.0024,
      "reward": 1.9981250762939453,
      "reward_std": 0.05305713415145874,
      "rewards/accuracy_reward": 0.8043749928474426,
      "rewards/format_reward": 1.0,
      "step": 992
    },
    {
      "all_correct": 0.75,
      "all_wrong": 0.0,
      "completion_length": 409.3125,
      "epoch": 0.013696362808788845,
      "grad_norm": 1.4435491083063408,
      "kl": 0.06640625,
      "learning_rate": 9.9953721076259e-07,
      "loss": 0.0027,
      "reward": 2.083531379699707,
      "reward_std": 0.009409750811755657,
      "rewards/accuracy_reward": 0.8835312128067017,
      "rewards/format_reward": 1.0,
      "step": 993
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.0,
      "completion_length": 398.25,
      "epoch": 0.013710155721990042,
      "grad_norm": 2.35799571419742,
      "kl": 0.056884765625,
      "learning_rate": 9.99536278334234e-07,
      "loss": 0.0023,
      "reward": 2.058781147003174,
      "reward_std": 0.038040243089199066,
      "rewards/accuracy_reward": 0.8587812185287476,
      "rewards/format_reward": 1.0,
      "step": 994
    },
    {
      "all_correct": 0.75,
      "all_wrong": 0.0,
      "completion_length": 412.46875,
      "epoch": 0.01372394863519124,
      "grad_norm": 3.1647969678637637,
      "kl": 0.05615234375,
      "learning_rate": 9.995353449679298e-07,
      "loss": 0.0022,
      "reward": 2.0491561889648438,
      "reward_std": 0.018156027421355247,
      "rewards/accuracy_reward": 0.8491562604904175,
      "rewards/format_reward": 1.0,
      "step": 995
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.0,
      "completion_length": 410.875,
      "epoch": 0.013737741548392435,
      "grad_norm": 1.4698220414974874,
      "kl": 0.06689453125,
      "learning_rate": 9.995344106636793e-07,
      "loss": 0.0027,
      "reward": 1.8772813081741333,
      "reward_std": 0.014451442286372185,
      "rewards/accuracy_reward": 0.6772812604904175,
      "rewards/format_reward": 1.0,
      "step": 996
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.0,
      "completion_length": 409.34375,
      "epoch": 0.013751534461593632,
      "grad_norm": 2.9435540764919885,
      "kl": 0.06494140625,
      "learning_rate": 9.995334754214843e-07,
      "loss": 0.0026,
      "reward": 2.0444061756134033,
      "reward_std": 0.041618090122938156,
      "rewards/accuracy_reward": 0.844406247138977,
      "rewards/format_reward": 1.0,
      "step": 997
    },
    {
      "all_correct": 1.0,
      "all_wrong": 0.0,
      "completion_length": 422.84375,
      "epoch": 0.01376532737479483,
      "grad_norm": 2.3773181609999594,
      "kl": 0.058837890625,
      "learning_rate": 9.995325392413467e-07,
      "loss": 0.0024,
      "reward": 2.1249687671661377,
      "reward_std": 0.022040609270334244,
      "rewards/accuracy_reward": 0.9249687790870667,
      "rewards/format_reward": 1.0,
      "step": 998
    },
    {
      "all_correct": 0.75,
      "all_wrong": 0.0,
      "completion_length": 406.25,
      "epoch": 0.013779120287996027,
      "grad_norm": 1.9611305368502028,
      "kl": 0.0634765625,
      "learning_rate": 9.995316021232678e-07,
      "loss": 0.0025,
      "reward": 2.076812505722046,
      "reward_std": 0.016642915084958076,
      "rewards/accuracy_reward": 0.8768124580383301,
      "rewards/format_reward": 1.0,
      "step": 999
    },
    {
      "all_correct": 0.75,
      "all_wrong": 0.0,
      "completion_length": 416.71875,
      "epoch": 0.013792913201197224,
      "grad_norm": 2.2665532696317245,
      "kl": 0.064453125,
      "learning_rate": 9.995306640672497e-07,
      "loss": 0.0026,
      "reward": 2.14662504196167,
      "reward_std": 0.03353721648454666,
      "rewards/accuracy_reward": 0.9466249942779541,
      "rewards/format_reward": 1.0,
      "step": 1000
    },
    {
      "all_correct": 0.25,
      "all_wrong": 0.0,
      "completion_length": 402.65625,
      "epoch": 0.013806706114398421,
      "grad_norm": 2.6841593636591816,
      "kl": 0.0615234375,
      "learning_rate": 9.99529725073294e-07,
      "loss": 0.0025,
      "reward": 1.918468713760376,
      "reward_std": 0.01867750473320484,
      "rewards/accuracy_reward": 0.7184686660766602,
      "rewards/format_reward": 1.0,
      "step": 1001
    },
    {
      "all_correct": 1.0,
      "all_wrong": 0.0,
      "completion_length": 418.34375,
      "epoch": 0.013820499027599619,
      "grad_norm": 2.340833035537331,
      "kl": 0.058349609375,
      "learning_rate": 9.995287851414029e-07,
      "loss": 0.0023,
      "reward": 2.130500078201294,
      "reward_std": 0.035647280514240265,
      "rewards/accuracy_reward": 0.9305000305175781,
      "rewards/format_reward": 1.0,
      "step": 1002
    },
    {
      "all_correct": 0.75,
      "all_wrong": 0.0,
      "completion_length": 395.21875,
      "epoch": 0.013834291940800816,
      "grad_norm": 2.382335624842158,
      "kl": 0.06298828125,
      "learning_rate": 9.995278442715775e-07,
      "loss": 0.0025,
      "reward": 2.090749979019165,
      "reward_std": 0.01863645389676094,
      "rewards/accuracy_reward": 0.890749990940094,
      "rewards/format_reward": 1.0,
      "step": 1003
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.0,
      "completion_length": 402.0625,
      "epoch": 0.013848084854002013,
      "grad_norm": 3.1549631514710854,
      "kl": 0.0703125,
      "learning_rate": 9.9952690246382e-07,
      "loss": 0.0028,
      "reward": 2.057000160217285,
      "reward_std": 0.02115192636847496,
      "rewards/accuracy_reward": 0.8569999933242798,
      "rewards/format_reward": 1.0,
      "step": 1004
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.0,
      "completion_length": 402.5625,
      "epoch": 0.01386187776720321,
      "grad_norm": 1.6145694170610638,
      "kl": 0.06689453125,
      "learning_rate": 9.99525959718132e-07,
      "loss": 0.0027,
      "reward": 2.0301876068115234,
      "reward_std": 0.014465948566794395,
      "rewards/accuracy_reward": 0.8301874995231628,
      "rewards/format_reward": 1.0,
      "step": 1005
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.0,
      "completion_length": 393.53125,
      "epoch": 0.013875670680404408,
      "grad_norm": 1.7246037242703653,
      "kl": 0.0615234375,
      "learning_rate": 9.995250160345154e-07,
      "loss": 0.0025,
      "reward": 2.065687417984009,
      "reward_std": 0.053799569606781006,
      "rewards/accuracy_reward": 0.8656875491142273,
      "rewards/format_reward": 1.0,
      "step": 1006
    },
    {
      "all_correct": 0.75,
      "all_wrong": 0.0,
      "completion_length": 392.03125,
      "epoch": 0.013889463593605605,
      "grad_norm": 2.274902733978332,
      "kl": 0.06982421875,
      "learning_rate": 9.995240714129719e-07,
      "loss": 0.0028,
      "reward": 2.0545313358306885,
      "reward_std": 0.020327426493167877,
      "rewards/accuracy_reward": 0.8545312285423279,
      "rewards/format_reward": 1.0,
      "step": 1007
    },
    {
      "all_correct": 0.75,
      "all_wrong": 0.0,
      "completion_length": 390.375,
      "epoch": 0.013903256506806802,
      "grad_norm": 2.0253955247856483,
      "kl": 0.0654296875,
      "learning_rate": 9.995231258535033e-07,
      "loss": 0.0026,
      "reward": 2.073718786239624,
      "reward_std": 0.015995020046830177,
      "rewards/accuracy_reward": 0.8737187385559082,
      "rewards/format_reward": 1.0,
      "step": 1008
    },
    {
      "all_correct": 0.25,
      "all_wrong": 0.0,
      "completion_length": 384.25,
      "epoch": 0.013917049420008,
      "grad_norm": 4.036634684637275,
      "kl": 0.06591796875,
      "learning_rate": 9.995221793561113e-07,
      "loss": 0.0026,
      "reward": 1.9777500629425049,
      "reward_std": 0.07585783302783966,
      "rewards/accuracy_reward": 0.7902500033378601,
      "rewards/format_reward": 1.0,
      "step": 1009
    },
    {
      "all_correct": 0.75,
      "all_wrong": 0.0,
      "completion_length": 395.15625,
      "epoch": 0.013930842333209197,
      "grad_norm": 5.6564302480286575,
      "kl": 0.059814453125,
      "learning_rate": 9.995212319207976e-07,
      "loss": 0.0024,
      "reward": 2.071031332015991,
      "reward_std": 0.041754066944122314,
      "rewards/accuracy_reward": 0.8710312843322754,
      "rewards/format_reward": 1.0,
      "step": 1010
    },
    {
      "all_correct": 0.75,
      "all_wrong": 0.0,
      "completion_length": 399.03125,
      "epoch": 0.013944635246410394,
      "grad_norm": 5.06472738897145,
      "kl": 0.06298828125,
      "learning_rate": 9.995202835475641e-07,
      "loss": 0.0025,
      "reward": 2.0567188262939453,
      "reward_std": 0.031211989000439644,
      "rewards/accuracy_reward": 0.8567187786102295,
      "rewards/format_reward": 1.0,
      "step": 1011
    },
    {
      "all_correct": 0.25,
      "all_wrong": 0.0,
      "completion_length": 400.4375,
      "epoch": 0.013958428159611591,
      "grad_norm": 2.7941958010217474,
      "kl": 0.060546875,
      "learning_rate": 9.995193342364128e-07,
      "loss": 0.0024,
      "reward": 1.8352186679840088,
      "reward_std": 0.005374276079237461,
      "rewards/accuracy_reward": 0.6352187395095825,
      "rewards/format_reward": 1.0,
      "step": 1012
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.0,
      "completion_length": 374.53125,
      "epoch": 0.013972221072812789,
      "grad_norm": 2.473876327437781,
      "kl": 0.0654296875,
      "learning_rate": 9.99518383987345e-07,
      "loss": 0.0026,
      "reward": 2.0870938301086426,
      "reward_std": 0.03920717164874077,
      "rewards/accuracy_reward": 0.8933437466621399,
      "rewards/format_reward": 1.0,
      "step": 1013
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.0,
      "completion_length": 381.625,
      "epoch": 0.013986013986013986,
      "grad_norm": 1.925270923405343,
      "kl": 0.061767578125,
      "learning_rate": 9.99517432800363e-07,
      "loss": 0.0025,
      "reward": 2.0156874656677246,
      "reward_std": 0.027778197079896927,
      "rewards/accuracy_reward": 0.8219375014305115,
      "rewards/format_reward": 1.0,
      "step": 1014
    },
    {
      "all_correct": 0.0,
      "all_wrong": 0.0,
      "completion_length": 394.9375,
      "epoch": 0.013999806899215183,
      "grad_norm": 1.862736498607258,
      "kl": 0.0576171875,
      "learning_rate": 9.99516480675468e-07,
      "loss": 0.0023,
      "reward": 1.8773751258850098,
      "reward_std": 0.008180994540452957,
      "rewards/accuracy_reward": 0.6773749589920044,
      "rewards/format_reward": 1.0,
      "step": 1015
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.0,
      "completion_length": 388.5625,
      "epoch": 0.01401359981241638,
      "grad_norm": 2.3267801183908836,
      "kl": 0.05419921875,
      "learning_rate": 9.995155276126626e-07,
      "loss": 0.0022,
      "reward": 1.9841251373291016,
      "reward_std": 0.04302642494440079,
      "rewards/accuracy_reward": 0.784125030040741,
      "rewards/format_reward": 1.0,
      "step": 1016
    },
    {
      "all_correct": 0.25,
      "all_wrong": 0.0,
      "completion_length": 379.53125,
      "epoch": 0.014027392725617578,
      "grad_norm": 2.4198964527178086,
      "kl": 0.057373046875,
      "learning_rate": 9.995145736119476e-07,
      "loss": 0.0023,
      "reward": 2.078843832015991,
      "reward_std": 0.04709043726325035,
      "rewards/accuracy_reward": 0.8850936889648438,
      "rewards/format_reward": 1.0,
      "step": 1017
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.0,
      "completion_length": 393.71875,
      "epoch": 0.014041185638818775,
      "grad_norm": 2.7753958744593783,
      "kl": 0.057861328125,
      "learning_rate": 9.995136186733257e-07,
      "loss": 0.0023,
      "reward": 2.0915000438690186,
      "reward_std": 0.07932135462760925,
      "rewards/accuracy_reward": 0.8914999961853027,
      "rewards/format_reward": 1.0,
      "step": 1018
    },
    {
      "all_correct": 0.75,
      "all_wrong": 0.0,
      "completion_length": 392.40625,
      "epoch": 0.014054978552019972,
      "grad_norm": 1.8747227301003553,
      "kl": 0.050537109375,
      "learning_rate": 9.99512662796798e-07,
      "loss": 0.002,
      "reward": 2.111187696456909,
      "reward_std": 0.030793720856308937,
      "rewards/accuracy_reward": 0.9174375534057617,
      "rewards/format_reward": 1.0,
      "step": 1019
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.0,
      "completion_length": 384.4375,
      "epoch": 0.01406877146522117,
      "grad_norm": 3.018782971982781,
      "kl": 0.057373046875,
      "learning_rate": 9.995117059823667e-07,
      "loss": 0.0023,
      "reward": 2.0834999084472656,
      "reward_std": 0.025418316945433617,
      "rewards/accuracy_reward": 0.8834999799728394,
      "rewards/format_reward": 1.0,
      "step": 1020
    },
    {
      "all_correct": 0.75,
      "all_wrong": 0.0,
      "completion_length": 381.375,
      "epoch": 0.014082564378422367,
      "grad_norm": 2.2283906563593,
      "kl": 0.061279296875,
      "learning_rate": 9.995107482300335e-07,
      "loss": 0.0025,
      "reward": 2.0917813777923584,
      "reward_std": 0.030742540955543518,
      "rewards/accuracy_reward": 0.8917812705039978,
      "rewards/format_reward": 1.0,
      "step": 1021
    },
    {
      "all_correct": 0.75,
      "all_wrong": 0.0,
      "completion_length": 392.0,
      "epoch": 0.014096357291623564,
      "grad_norm": 3.7469031261924775,
      "kl": 0.0625,
      "learning_rate": 9.995097895398003e-07,
      "loss": 0.0025,
      "reward": 2.0813751220703125,
      "reward_std": 0.019066594541072845,
      "rewards/accuracy_reward": 0.8813750147819519,
      "rewards/format_reward": 1.0,
      "step": 1022
    },
    {
      "all_correct": 0.75,
      "all_wrong": 0.0,
      "completion_length": 377.9375,
      "epoch": 0.014110150204824761,
      "grad_norm": 2.1316071164421024,
      "kl": 0.05615234375,
      "learning_rate": 9.995088299116688e-07,
      "loss": 0.0022,
      "reward": 2.1322813034057617,
      "reward_std": 0.03719237446784973,
      "rewards/accuracy_reward": 0.938531219959259,
      "rewards/format_reward": 1.0,
      "step": 1023
    },
    {
      "all_correct": 0.75,
      "all_wrong": 0.0,
      "completion_length": 367.09375,
      "epoch": 0.014123943118025959,
      "grad_norm": 3.4566052885942553,
      "kl": 0.0615234375,
      "learning_rate": 9.995078693456407e-07,
      "loss": 0.0025,
      "reward": 2.0728750228881836,
      "reward_std": 0.04213777929544449,
      "rewards/accuracy_reward": 0.8791249990463257,
      "rewards/format_reward": 1.0,
      "step": 1024
    },
    {
      "all_correct": 0.75,
      "all_wrong": 0.0,
      "completion_length": 378.625,
      "epoch": 0.014137736031227156,
      "grad_norm": 2.262560830772727,
      "kl": 0.060302734375,
      "learning_rate": 9.995069078417177e-07,
      "loss": 0.0024,
      "reward": 2.020249843597412,
      "reward_std": 0.013918399810791016,
      "rewards/accuracy_reward": 0.8202500343322754,
      "rewards/format_reward": 1.0,
      "step": 1025
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.0,
      "completion_length": 387.25,
      "epoch": 0.014151528944428353,
      "grad_norm": 2.556370021374263,
      "kl": 0.056640625,
      "learning_rate": 9.99505945399902e-07,
      "loss": 0.0023,
      "reward": 2.003406047821045,
      "reward_std": 0.08778459578752518,
      "rewards/accuracy_reward": 0.8096562623977661,
      "rewards/format_reward": 1.0,
      "step": 1026
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.0,
      "completion_length": 383.25,
      "epoch": 0.01416532185762955,
      "grad_norm": 2.747186719581895,
      "kl": 0.0615234375,
      "learning_rate": 9.995049820201952e-07,
      "loss": 0.0025,
      "reward": 2.0791561603546143,
      "reward_std": 0.02769346907734871,
      "rewards/accuracy_reward": 0.879156231880188,
      "rewards/format_reward": 1.0,
      "step": 1027
    },
    {
      "all_correct": 0.75,
      "all_wrong": 0.0,
      "completion_length": 403.84375,
      "epoch": 0.014179114770830748,
      "grad_norm": 2.2228034115777238,
      "kl": 0.05517578125,
      "learning_rate": 9.99504017702599e-07,
      "loss": 0.0022,
      "reward": 2.146437644958496,
      "reward_std": 0.031086117029190063,
      "rewards/accuracy_reward": 0.9464374780654907,
      "rewards/format_reward": 1.0,
      "step": 1028
    },
    {
      "all_correct": 1.0,
      "all_wrong": 0.0,
      "completion_length": 382.875,
      "epoch": 0.014192907684031945,
      "grad_norm": 2.4237383420672143,
      "kl": 0.0634765625,
      "learning_rate": 9.995030524471154e-07,
      "loss": 0.0025,
      "reward": 2.0984373092651367,
      "reward_std": 0.02709505707025528,
      "rewards/accuracy_reward": 0.8984375,
      "rewards/format_reward": 1.0,
      "step": 1029
    },
    {
      "all_correct": 0.25,
      "all_wrong": 0.0,
      "completion_length": 383.125,
      "epoch": 0.014206700597233142,
      "grad_norm": 9.992156867116375,
      "kl": 0.0595703125,
      "learning_rate": 9.995020862537462e-07,
      "loss": 0.0024,
      "reward": 2.0556561946868896,
      "reward_std": 0.039962634444236755,
      "rewards/accuracy_reward": 0.8619062304496765,
      "rewards/format_reward": 1.0,
      "step": 1030
    },
    {
      "all_correct": 1.0,
      "all_wrong": 0.0,
      "completion_length": 377.21875,
      "epoch": 0.01422049351043434,
      "grad_norm": 3.749501724210966,
      "kl": 0.06396484375,
      "learning_rate": 9.99501119122493e-07,
      "loss": 0.0026,
      "reward": 2.136625051498413,
      "reward_std": 0.028208408504724503,
      "rewards/accuracy_reward": 0.9366250038146973,
      "rewards/format_reward": 1.0,
      "step": 1031
    },
    {
      "all_correct": 0.75,
      "all_wrong": 0.0,
      "completion_length": 382.6875,
      "epoch": 0.014234286423635537,
      "grad_norm": 2.5634091107812917,
      "kl": 0.06591796875,
      "learning_rate": 9.99500151053358e-07,
      "loss": 0.0026,
      "reward": 2.0800938606262207,
      "reward_std": 0.03827814757823944,
      "rewards/accuracy_reward": 0.8863437175750732,
      "rewards/format_reward": 1.0,
      "step": 1032
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.0,
      "completion_length": 382.375,
      "epoch": 0.014248079336836734,
      "grad_norm": 2.2669041007151476,
      "kl": 0.0634765625,
      "learning_rate": 9.994991820463426e-07,
      "loss": 0.0025,
      "reward": 2.1167502403259277,
      "reward_std": 0.06366574764251709,
      "rewards/accuracy_reward": 0.9167500138282776,
      "rewards/format_reward": 1.0,
      "step": 1033
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.0,
      "completion_length": 389.8125,
      "epoch": 0.01426187225003793,
      "grad_norm": 2.4915107432135724,
      "kl": 0.0576171875,
      "learning_rate": 9.994982121014487e-07,
      "loss": 0.0023,
      "reward": 1.968656301498413,
      "reward_std": 0.035532400012016296,
      "rewards/accuracy_reward": 0.7686562538146973,
      "rewards/format_reward": 1.0,
      "step": 1034
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.0,
      "completion_length": 380.5,
      "epoch": 0.014275665163239127,
      "grad_norm": 2.1809811971570356,
      "kl": 0.0634765625,
      "learning_rate": 9.994972412186785e-07,
      "loss": 0.0025,
      "reward": 2.0294063091278076,
      "reward_std": 0.03878871724009514,
      "rewards/accuracy_reward": 0.8356562852859497,
      "rewards/format_reward": 1.0,
      "step": 1035
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.0,
      "completion_length": 379.09375,
      "epoch": 0.014289458076440324,
      "grad_norm": 2.260253775706708,
      "kl": 0.056640625,
      "learning_rate": 9.994962693980333e-07,
      "loss": 0.0023,
      "reward": 1.9719061851501465,
      "reward_std": 0.04054107144474983,
      "rewards/accuracy_reward": 0.7844062447547913,
      "rewards/format_reward": 1.0,
      "step": 1036
    },
    {
      "all_correct": 1.0,
      "all_wrong": 0.0,
      "completion_length": 381.15625,
      "epoch": 0.014303250989641522,
      "grad_norm": 6.934004361380599,
      "kl": 0.0546875,
      "learning_rate": 9.994952966395152e-07,
      "loss": 0.0022,
      "reward": 2.1446876525878906,
      "reward_std": 0.009687417186796665,
      "rewards/accuracy_reward": 0.9446874856948853,
      "rewards/format_reward": 1.0,
      "step": 1037
    },
    {
      "all_correct": 0.25,
      "all_wrong": 0.0,
      "completion_length": 390.40625,
      "epoch": 0.014317043902842719,
      "grad_norm": 2.871732371385341,
      "kl": 0.05810546875,
      "learning_rate": 9.994943229431262e-07,
      "loss": 0.0023,
      "reward": 2.009031295776367,
      "reward_std": 0.06822541356086731,
      "rewards/accuracy_reward": 0.8152812719345093,
      "rewards/format_reward": 1.0,
      "step": 1038
    },
    {
      "all_correct": 0.75,
      "all_wrong": 0.0,
      "completion_length": 374.625,
      "epoch": 0.014330836816043916,
      "grad_norm": 2.090810930347843,
      "kl": 0.06591796875,
      "learning_rate": 9.994933483088677e-07,
      "loss": 0.0026,
      "reward": 2.0885000228881836,
      "reward_std": 0.03708851337432861,
      "rewards/accuracy_reward": 0.8947499990463257,
      "rewards/format_reward": 1.0,
      "step": 1039
    },
    {
      "all_correct": 0.75,
      "all_wrong": 0.0,
      "completion_length": 377.6875,
      "epoch": 0.014344629729245113,
      "grad_norm": 1.6883198717499386,
      "kl": 0.06298828125,
      "learning_rate": 9.994923727367418e-07,
      "loss": 0.0025,
      "reward": 2.1227500438690186,
      "reward_std": 0.025841422379016876,
      "rewards/accuracy_reward": 0.9352499842643738,
      "rewards/format_reward": 1.0,
      "step": 1040
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.0,
      "completion_length": 377.90625,
      "epoch": 0.01435842264244631,
      "grad_norm": 3.2253503668773083,
      "kl": 0.0654296875,
      "learning_rate": 9.994913962267503e-07,
      "loss": 0.0026,
      "reward": 2.0452499389648438,
      "reward_std": 0.03652583062648773,
      "rewards/accuracy_reward": 0.8452500104904175,
      "rewards/format_reward": 1.0,
      "step": 1041
    },
    {
      "all_correct": 0.75,
      "all_wrong": 0.0,
      "completion_length": 389.25,
      "epoch": 0.014372215555647508,
      "grad_norm": 1.0793983996727927,
      "kl": 0.051513671875,
      "learning_rate": 9.99490418778895e-07,
      "loss": 0.0021,
      "reward": 2.110781192779541,
      "reward_std": 0.009393594227731228,
      "rewards/accuracy_reward": 0.9107812643051147,
      "rewards/format_reward": 1.0,
      "step": 1042
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.0,
      "completion_length": 399.34375,
      "epoch": 0.014386008468848705,
      "grad_norm": 3.567533867559961,
      "kl": 0.06298828125,
      "learning_rate": 9.994894403931778e-07,
      "loss": 0.0025,
      "reward": 2.071499824523926,
      "reward_std": 0.01883268915116787,
      "rewards/accuracy_reward": 0.8715000748634338,
      "rewards/format_reward": 1.0,
      "step": 1043
    },
    {
      "all_correct": 0.75,
      "all_wrong": 0.0,
      "completion_length": 408.3125,
      "epoch": 0.014399801382049902,
      "grad_norm": 1.9767863781483073,
      "kl": 0.056396484375,
      "learning_rate": 9.994884610696006e-07,
      "loss": 0.0023,
      "reward": 2.0631563663482666,
      "reward_std": 0.023641955107450485,
      "rewards/accuracy_reward": 0.863156259059906,
      "rewards/format_reward": 1.0,
      "step": 1044
    },
    {
      "all_correct": 1.0,
      "all_wrong": 0.0,
      "completion_length": 401.21875,
      "epoch": 0.0144135942952511,
      "grad_norm": 2.3432420394467752,
      "kl": 0.059326171875,
      "learning_rate": 9.99487480808165e-07,
      "loss": 0.0024,
      "reward": 2.1525936126708984,
      "reward_std": 0.018496576696634293,
      "rewards/accuracy_reward": 0.9525937438011169,
      "rewards/format_reward": 1.0,
      "step": 1045
    },
    {
      "all_correct": 0.75,
      "all_wrong": 0.0,
      "completion_length": 390.875,
      "epoch": 0.014427387208452297,
      "grad_norm": 2.11665813366599,
      "kl": 0.05712890625,
      "learning_rate": 9.99486499608873e-07,
      "loss": 0.0023,
      "reward": 2.023750066757202,
      "reward_std": 0.03328660875558853,
      "rewards/accuracy_reward": 0.8299999833106995,
      "rewards/format_reward": 1.0,
      "step": 1046
    },
    {
      "all_correct": 0.75,
      "all_wrong": 0.0,
      "completion_length": 390.90625,
      "epoch": 0.014441180121653494,
      "grad_norm": 2.308078835490882,
      "kl": 0.06591796875,
      "learning_rate": 9.994855174717264e-07,
      "loss": 0.0026,
      "reward": 2.0730624198913574,
      "reward_std": 0.008193084970116615,
      "rewards/accuracy_reward": 0.8730625510215759,
      "rewards/format_reward": 1.0,
      "step": 1047
    },
    {
      "all_correct": 0.75,
      "all_wrong": 0.0,
      "completion_length": 398.84375,
      "epoch": 0.014454973034854691,
      "grad_norm": 2.525293100444316,
      "kl": 0.05615234375,
      "learning_rate": 9.99484534396727e-07,
      "loss": 0.0023,
      "reward": 2.126281261444092,
      "reward_std": 0.0399869903922081,
      "rewards/accuracy_reward": 0.9450312256813049,
      "rewards/format_reward": 1.0,
      "step": 1048
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.0,
      "completion_length": 406.0625,
      "epoch": 0.014468765948055889,
      "grad_norm": 2.313492910387635,
      "kl": 0.060791015625,
      "learning_rate": 9.994835503838768e-07,
      "loss": 0.0024,
      "reward": 1.9915001392364502,
      "reward_std": 0.01579016074538231,
      "rewards/accuracy_reward": 0.7915000915527344,
      "rewards/format_reward": 1.0,
      "step": 1049
    },
    {
      "all_correct": 0.75,
      "all_wrong": 0.0,
      "completion_length": 403.78125,
      "epoch": 0.014482558861257086,
      "grad_norm": 4.643788930351187,
      "kl": 0.05859375,
      "learning_rate": 9.994825654331776e-07,
      "loss": 0.0023,
      "reward": 2.049499988555908,
      "reward_std": 0.01867077127099037,
      "rewards/accuracy_reward": 0.8495000600814819,
      "rewards/format_reward": 1.0,
      "step": 1050
    },
    {
      "all_correct": 0.75,
      "all_wrong": 0.0,
      "completion_length": 402.40625,
      "epoch": 0.014496351774458283,
      "grad_norm": 2.647180271597688,
      "kl": 0.05859375,
      "learning_rate": 9.99481579544631e-07,
      "loss": 0.0023,
      "reward": 2.068312644958496,
      "reward_std": 0.029035402461886406,
      "rewards/accuracy_reward": 0.8683124780654907,
      "rewards/format_reward": 1.0,
      "step": 1051
    },
    {
      "all_correct": 0.75,
      "all_wrong": 0.0,
      "completion_length": 407.9375,
      "epoch": 0.01451014468765948,
      "grad_norm": 2.6491884664332597,
      "kl": 0.062255859375,
      "learning_rate": 9.994805927182393e-07,
      "loss": 0.0025,
      "reward": 2.0622501373291016,
      "reward_std": 0.04071832075715065,
      "rewards/accuracy_reward": 0.862250030040741,
      "rewards/format_reward": 1.0,
      "step": 1052
    },
    {
      "all_correct": 0.75,
      "all_wrong": 0.0,
      "completion_length": 397.4375,
      "epoch": 0.014523937600860678,
      "grad_norm": 2.3423580431266395,
      "kl": 0.06640625,
      "learning_rate": 9.99479604954004e-07,
      "loss": 0.0026,
      "reward": 2.0285000801086426,
      "reward_std": 0.019985763356089592,
      "rewards/accuracy_reward": 0.8284999132156372,
      "rewards/format_reward": 1.0,
      "step": 1053
    },
    {
      "all_correct": 0.75,
      "all_wrong": 0.0,
      "completion_length": 410.6875,
      "epoch": 0.014537730514061875,
      "grad_norm": 1.6756725204796774,
      "kl": 0.0546875,
      "learning_rate": 9.994786162519271e-07,
      "loss": 0.0022,
      "reward": 2.100437641143799,
      "reward_std": 0.021006863564252853,
      "rewards/accuracy_reward": 0.9004374146461487,
      "rewards/format_reward": 1.0,
      "step": 1054
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.0,
      "completion_length": 410.84375,
      "epoch": 0.014551523427263072,
      "grad_norm": 3.8194351990252198,
      "kl": 0.072265625,
      "learning_rate": 9.994776266120104e-07,
      "loss": 0.0029,
      "reward": 2.0522189140319824,
      "reward_std": 0.023851297795772552,
      "rewards/accuracy_reward": 0.852218747138977,
      "rewards/format_reward": 1.0,
      "step": 1055
    },
    {
      "all_correct": 1.0,
      "all_wrong": 0.0,
      "completion_length": 412.03125,
      "epoch": 0.01456531634046427,
      "grad_norm": 2.6374030353977003,
      "kl": 0.0595703125,
      "learning_rate": 9.994766360342558e-07,
      "loss": 0.0024,
      "reward": 2.118593692779541,
      "reward_std": 0.02647656947374344,
      "rewards/accuracy_reward": 0.9185937643051147,
      "rewards/format_reward": 1.0,
      "step": 1056
    },
    {
      "all_correct": 0.75,
      "all_wrong": 0.0,
      "completion_length": 397.75,
      "epoch": 0.014579109253665467,
      "grad_norm": 2.6238147638786815,
      "kl": 0.056884765625,
      "learning_rate": 9.99475644518665e-07,
      "loss": 0.0023,
      "reward": 2.1460001468658447,
      "reward_std": 0.03200087323784828,
      "rewards/accuracy_reward": 0.9459999799728394,
      "rewards/format_reward": 1.0,
      "step": 1057
    },
    {
      "all_correct": 0.75,
      "all_wrong": 0.0,
      "completion_length": 410.5625,
      "epoch": 0.014592902166866664,
      "grad_norm": 2.082613684206703,
      "kl": 0.0654296875,
      "learning_rate": 9.9947465206524e-07,
      "loss": 0.0026,
      "reward": 2.0904998779296875,
      "reward_std": 0.020687583833932877,
      "rewards/accuracy_reward": 0.8904999494552612,
      "rewards/format_reward": 1.0,
      "step": 1058
    },
    {
      "all_correct": 1.0,
      "all_wrong": 0.0,
      "completion_length": 421.375,
      "epoch": 0.014606695080067861,
      "grad_norm": 3.450562654773857,
      "kl": 0.064453125,
      "learning_rate": 9.994736586739827e-07,
      "loss": 0.0026,
      "reward": 2.1506876945495605,
      "reward_std": 0.015783367678523064,
      "rewards/accuracy_reward": 0.9506875276565552,
      "rewards/format_reward": 1.0,
      "step": 1059
    },
    {
      "all_correct": 1.0,
      "all_wrong": 0.0,
      "completion_length": 420.25,
      "epoch": 0.014620487993269059,
      "grad_norm": 1.9472301918914765,
      "kl": 0.06787109375,
      "learning_rate": 9.99472664344895e-07,
      "loss": 0.0027,
      "reward": 2.1585001945495605,
      "reward_std": 0.021822787821292877,
      "rewards/accuracy_reward": 0.9584999084472656,
      "rewards/format_reward": 1.0,
      "step": 1060
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.0,
      "completion_length": 414.59375,
      "epoch": 0.014634280906470256,
      "grad_norm": 1.8273523890431835,
      "kl": 0.06640625,
      "learning_rate": 9.994716690779787e-07,
      "loss": 0.0027,
      "reward": 2.0393123626708984,
      "reward_std": 0.018948350101709366,
      "rewards/accuracy_reward": 0.8393124938011169,
      "rewards/format_reward": 1.0,
      "step": 1061
    },
    {
      "all_correct": 1.0,
      "all_wrong": 0.0,
      "completion_length": 399.0625,
      "epoch": 0.014648073819671453,
      "grad_norm": 2.6782014668207665,
      "kl": 0.06298828125,
      "learning_rate": 9.994706728732355e-07,
      "loss": 0.0025,
      "reward": 2.1312811374664307,
      "reward_std": 0.031693197786808014,
      "rewards/accuracy_reward": 0.9312812089920044,
      "rewards/format_reward": 1.0,
      "step": 1062
    },
    {
      "all_correct": 0.75,
      "all_wrong": 0.0,
      "completion_length": 403.625,
      "epoch": 0.01466186673287265,
      "grad_norm": 2.324852894599851,
      "kl": 0.06396484375,
      "learning_rate": 9.994696757306675e-07,
      "loss": 0.0026,
      "reward": 2.057000160217285,
      "reward_std": 0.06525996327400208,
      "rewards/accuracy_reward": 0.856999933719635,
      "rewards/format_reward": 1.0,
      "step": 1063
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.0,
      "completion_length": 404.0,
      "epoch": 0.014675659646073848,
      "grad_norm": 3.29667561854513,
      "kl": 0.064453125,
      "learning_rate": 9.994686776502766e-07,
      "loss": 0.0026,
      "reward": 1.9528436660766602,
      "reward_std": 0.029975606128573418,
      "rewards/accuracy_reward": 0.7528437376022339,
      "rewards/format_reward": 1.0,
      "step": 1064
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.0,
      "completion_length": 403.25,
      "epoch": 0.014689452559275045,
      "grad_norm": 1.7500356482894373,
      "kl": 0.0712890625,
      "learning_rate": 9.994676786320647e-07,
      "loss": 0.0028,
      "reward": 2.054281234741211,
      "reward_std": 0.028028924018144608,
      "rewards/accuracy_reward": 0.8605312705039978,
      "rewards/format_reward": 1.0,
      "step": 1065
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.0,
      "completion_length": 432.28125,
      "epoch": 0.014703245472476242,
      "grad_norm": 9.309616225727984,
      "kl": 0.06396484375,
      "learning_rate": 9.994666786760333e-07,
      "loss": 0.0026,
      "reward": 2.1013126373291016,
      "reward_std": 0.03515523672103882,
      "rewards/accuracy_reward": 0.9075624942779541,
      "rewards/format_reward": 1.0,
      "step": 1066
    },
    {
      "all_correct": 0.75,
      "all_wrong": 0.0,
      "completion_length": 429.375,
      "epoch": 0.01471703838567744,
      "grad_norm": 2.035352915275198,
      "kl": 0.06396484375,
      "learning_rate": 9.994656777821846e-07,
      "loss": 0.0026,
      "reward": 2.156437397003174,
      "reward_std": 0.025794094428420067,
      "rewards/accuracy_reward": 0.9626874923706055,
      "rewards/format_reward": 1.0,
      "step": 1067
    },
    {
      "all_correct": 0.75,
      "all_wrong": 0.0,
      "completion_length": 411.75,
      "epoch": 0.014730831298878637,
      "grad_norm": 2.187782467298346,
      "kl": 0.059814453125,
      "learning_rate": 9.994646759505203e-07,
      "loss": 0.0024,
      "reward": 2.1257810592651367,
      "reward_std": 0.040661588311195374,
      "rewards/accuracy_reward": 0.92578125,
      "rewards/format_reward": 1.0,
      "step": 1068
    },
    {
      "all_correct": 0.25,
      "all_wrong": 0.0,
      "completion_length": 420.28125,
      "epoch": 0.014744624212079834,
      "grad_norm": 2.5026453390955274,
      "kl": 0.06640625,
      "learning_rate": 9.994636731810427e-07,
      "loss": 0.0027,
      "reward": 1.9868437051773071,
      "reward_std": 0.023193754255771637,
      "rewards/accuracy_reward": 0.7868437767028809,
      "rewards/format_reward": 1.0,
      "step": 1069
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.0,
      "completion_length": 429.1875,
      "epoch": 0.014758417125281031,
      "grad_norm": 2.288931551258801,
      "kl": 0.057861328125,
      "learning_rate": 9.99462669473753e-07,
      "loss": 0.0023,
      "reward": 2.1106252670288086,
      "reward_std": 0.050059713423252106,
      "rewards/accuracy_reward": 0.9168750047683716,
      "rewards/format_reward": 1.0,
      "step": 1070
    },
    {
      "all_correct": 0.75,
      "all_wrong": 0.0,
      "completion_length": 437.3125,
      "epoch": 0.014772210038482227,
      "grad_norm": 2.057354487026471,
      "kl": 0.0673828125,
      "learning_rate": 9.994616648286536e-07,
      "loss": 0.0027,
      "reward": 2.0542187690734863,
      "reward_std": 0.04256404936313629,
      "rewards/accuracy_reward": 0.8604687452316284,
      "rewards/format_reward": 1.0,
      "step": 1071
    },
    {
      "all_correct": 0.75,
      "all_wrong": 0.0,
      "completion_length": 425.09375,
      "epoch": 0.014786002951683424,
      "grad_norm": 2.0371520809223878,
      "kl": 0.060546875,
      "learning_rate": 9.994606592457463e-07,
      "loss": 0.0024,
      "reward": 2.103062629699707,
      "reward_std": 0.04283753037452698,
      "rewards/accuracy_reward": 0.9093124866485596,
      "rewards/format_reward": 1.0,
      "step": 1072
    },
    {
      "all_correct": 0.75,
      "all_wrong": 0.0,
      "completion_length": 417.03125,
      "epoch": 0.014799795864884622,
      "grad_norm": 1.9452010049327786,
      "kl": 0.059814453125,
      "learning_rate": 9.99459652725033e-07,
      "loss": 0.0024,
      "reward": 2.104968786239624,
      "reward_std": 0.03442716225981712,
      "rewards/accuracy_reward": 0.9112187027931213,
      "rewards/format_reward": 1.0,
      "step": 1073
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.0,
      "completion_length": 421.75,
      "epoch": 0.014813588778085819,
      "grad_norm": 1.2523213041177887,
      "kl": 0.0693359375,
      "learning_rate": 9.994586452665155e-07,
      "loss": 0.0028,
      "reward": 2.129312515258789,
      "reward_std": 0.033046651631593704,
      "rewards/accuracy_reward": 0.9418123960494995,
      "rewards/format_reward": 1.0,
      "step": 1074
    },
    {
      "all_correct": 0.75,
      "all_wrong": 0.0,
      "completion_length": 429.65625,
      "epoch": 0.014827381691287016,
      "grad_norm": 2.8727954950597177,
      "kl": 0.060302734375,
      "learning_rate": 9.994576368701957e-07,
      "loss": 0.0024,
      "reward": 2.141531229019165,
      "reward_std": 0.04028373956680298,
      "rewards/accuracy_reward": 0.9477812647819519,
      "rewards/format_reward": 1.0,
      "step": 1075
    },
    {
      "all_correct": 0.75,
      "all_wrong": 0.0,
      "completion_length": 411.59375,
      "epoch": 0.014841174604488213,
      "grad_norm": 1.5956311726419976,
      "kl": 0.06591796875,
      "learning_rate": 9.994566275360753e-07,
      "loss": 0.0026,
      "reward": 2.121875047683716,
      "reward_std": 0.009881383739411831,
      "rewards/accuracy_reward": 0.921875,
      "rewards/format_reward": 1.0,
      "step": 1076
    },
    {
      "all_correct": 0.75,
      "all_wrong": 0.0,
      "completion_length": 425.15625,
      "epoch": 0.01485496751768941,
      "grad_norm": 2.218568019552992,
      "kl": 0.0556640625,
      "learning_rate": 9.994556172641567e-07,
      "loss": 0.0022,
      "reward": 2.1162188053131104,
      "reward_std": 0.011133064515888691,
      "rewards/accuracy_reward": 0.9162187576293945,
      "rewards/format_reward": 1.0,
      "step": 1077
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.0,
      "completion_length": 411.96875,
      "epoch": 0.014868760430890608,
      "grad_norm": 1.424588244485191,
      "kl": 0.07080078125,
      "learning_rate": 9.994546060544413e-07,
      "loss": 0.0028,
      "reward": 2.0124688148498535,
      "reward_std": 0.004626516252756119,
      "rewards/accuracy_reward": 0.8124687671661377,
      "rewards/format_reward": 1.0,
      "step": 1078
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.0,
      "completion_length": 409.40625,
      "epoch": 0.014882553344091805,
      "grad_norm": 2.9556073070322904,
      "kl": 0.06201171875,
      "learning_rate": 9.994535939069313e-07,
      "loss": 0.0025,
      "reward": 2.0877811908721924,
      "reward_std": 0.01757834479212761,
      "rewards/accuracy_reward": 0.8877811431884766,
      "rewards/format_reward": 1.0,
      "step": 1079
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.0,
      "completion_length": 405.4375,
      "epoch": 0.014896346257293002,
      "grad_norm": 2.400652816341641,
      "kl": 0.0625,
      "learning_rate": 9.994525808216286e-07,
      "loss": 0.0025,
      "reward": 2.096937417984009,
      "reward_std": 0.02723454311490059,
      "rewards/accuracy_reward": 0.8969374895095825,
      "rewards/format_reward": 1.0,
      "step": 1080
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.0,
      "completion_length": 422.1875,
      "epoch": 0.0149101391704942,
      "grad_norm": 2.6900558056393655,
      "kl": 0.06640625,
      "learning_rate": 9.994515667985348e-07,
      "loss": 0.0027,
      "reward": 2.0487499237060547,
      "reward_std": 0.052178263664245605,
      "rewards/accuracy_reward": 0.8550000190734863,
      "rewards/format_reward": 1.0,
      "step": 1081
    },
    {
      "all_correct": 1.0,
      "all_wrong": 0.0,
      "completion_length": 413.59375,
      "epoch": 0.014923932083695397,
      "grad_norm": 1.333579928012792,
      "kl": 0.0517578125,
      "learning_rate": 9.99450551837652e-07,
      "loss": 0.0021,
      "reward": 2.1450939178466797,
      "reward_std": 0.002078552497550845,
      "rewards/accuracy_reward": 0.9450937509536743,
      "rewards/format_reward": 1.0,
      "step": 1082
    },
    {
      "all_correct": 0.75,
      "all_wrong": 0.0,
      "completion_length": 409.28125,
      "epoch": 0.014937724996896594,
      "grad_norm": 5.372646244504243,
      "kl": 0.0712890625,
      "learning_rate": 9.994495359389823e-07,
      "loss": 0.0028,
      "reward": 2.0963125228881836,
      "reward_std": 0.010374093428254128,
      "rewards/accuracy_reward": 0.8963124752044678,
      "rewards/format_reward": 1.0,
      "step": 1083
    },
    {
      "all_correct": 0.75,
      "all_wrong": 0.0,
      "completion_length": 412.375,
      "epoch": 0.014951517910097792,
      "grad_norm": 2.4921541387065727,
      "kl": 0.06787109375,
      "learning_rate": 9.994485191025272e-07,
      "loss": 0.0027,
      "reward": 2.087218761444092,
      "reward_std": 0.024709578603506088,
      "rewards/accuracy_reward": 0.887218713760376,
      "rewards/format_reward": 1.0,
      "step": 1084
    },
    {
      "all_correct": 1.0,
      "all_wrong": 0.0,
      "completion_length": 398.375,
      "epoch": 0.014965310823298989,
      "grad_norm": 1.48399931650834,
      "kl": 0.052490234375,
      "learning_rate": 9.99447501328289e-07,
      "loss": 0.0021,
      "reward": 2.174562454223633,
      "reward_std": 0.010739422403275967,
      "rewards/accuracy_reward": 0.9745625257492065,
      "rewards/format_reward": 1.0,
      "step": 1085
    },
    {
      "all_correct": 0.75,
      "all_wrong": 0.0,
      "completion_length": 397.0625,
      "epoch": 0.014979103736500186,
      "grad_norm": 4.842247127748281,
      "kl": 0.0634765625,
      "learning_rate": 9.994464826162694e-07,
      "loss": 0.0025,
      "reward": 2.086437463760376,
      "reward_std": 0.03863893449306488,
      "rewards/accuracy_reward": 0.8926874399185181,
      "rewards/format_reward": 1.0,
      "step": 1086
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.0,
      "completion_length": 403.75,
      "epoch": 0.014992896649701383,
      "grad_norm": 2.1795682781704797,
      "kl": 0.056884765625,
      "learning_rate": 9.994454629664704e-07,
      "loss": 0.0023,
      "reward": 2.114375114440918,
      "reward_std": 0.03267224133014679,
      "rewards/accuracy_reward": 0.9206250309944153,
      "rewards/format_reward": 1.0,
      "step": 1087
    },
    {
      "all_correct": 1.0,
      "all_wrong": 0.0,
      "completion_length": 406.84375,
      "epoch": 0.01500668956290258,
      "grad_norm": 1.926170602872597,
      "kl": 0.06787109375,
      "learning_rate": 9.994444423788937e-07,
      "loss": 0.0027,
      "reward": 2.121062755584717,
      "reward_std": 0.017179129645228386,
      "rewards/accuracy_reward": 0.9210624098777771,
      "rewards/format_reward": 1.0,
      "step": 1088
    },
    {
      "all_correct": 1.0,
      "all_wrong": 0.0,
      "completion_length": 385.71875,
      "epoch": 0.015020482476103778,
      "grad_norm": 1.3725523750611817,
      "kl": 0.057373046875,
      "learning_rate": 9.994434208535414e-07,
      "loss": 0.0023,
      "reward": 2.1212501525878906,
      "reward_std": 0.004670638125389814,
      "rewards/accuracy_reward": 0.9212501049041748,
      "rewards/format_reward": 1.0,
      "step": 1089
    },
    {
      "all_correct": 0.75,
      "all_wrong": 0.0,
      "completion_length": 401.5,
      "epoch": 0.015034275389304975,
      "grad_norm": 1.8777286157731157,
      "kl": 0.0634765625,
      "learning_rate": 9.994423983904157e-07,
      "loss": 0.0025,
      "reward": 2.0565624237060547,
      "reward_std": 0.015134502202272415,
      "rewards/accuracy_reward": 0.8565624952316284,
      "rewards/format_reward": 1.0,
      "step": 1090
    },
    {
      "all_correct": 0.75,
      "all_wrong": 0.0,
      "completion_length": 409.09375,
      "epoch": 0.015048068302506172,
      "grad_norm": 42.66234406750561,
      "kl": 0.0654296875,
      "learning_rate": 9.99441374989518e-07,
      "loss": 0.0026,
      "reward": 2.0629687309265137,
      "reward_std": 0.026116151362657547,
      "rewards/accuracy_reward": 0.8629687428474426,
      "rewards/format_reward": 1.0,
      "step": 1091
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.0,
      "completion_length": 410.5,
      "epoch": 0.01506186121570737,
      "grad_norm": 10.41268494868566,
      "kl": 0.06494140625,
      "learning_rate": 9.994403506508503e-07,
      "loss": 0.0026,
      "reward": 2.0698747634887695,
      "reward_std": 0.03441910073161125,
      "rewards/accuracy_reward": 0.8698750138282776,
      "rewards/format_reward": 1.0,
      "step": 1092
    },
    {
      "all_correct": 0.75,
      "all_wrong": 0.0,
      "completion_length": 403.03125,
      "epoch": 0.015075654128908567,
      "grad_norm": 2.4362879999026066,
      "kl": 0.06689453125,
      "learning_rate": 9.99439325374415e-07,
      "loss": 0.0027,
      "reward": 2.067187547683716,
      "reward_std": 0.024930741637945175,
      "rewards/accuracy_reward": 0.8671875596046448,
      "rewards/format_reward": 1.0,
      "step": 1093
    },
    {
      "all_correct": 1.0,
      "all_wrong": 0.0,
      "completion_length": 413.34375,
      "epoch": 0.015089447042109764,
      "grad_norm": 2.1130370523876048,
      "kl": 0.0673828125,
      "learning_rate": 9.994382991602133e-07,
      "loss": 0.0027,
      "reward": 2.142124891281128,
      "reward_std": 0.01581864058971405,
      "rewards/accuracy_reward": 0.9421250224113464,
      "rewards/format_reward": 1.0,
      "step": 1094
    },
    {
      "all_correct": 0.75,
      "all_wrong": 0.0,
      "completion_length": 405.9375,
      "epoch": 0.015103239955310961,
      "grad_norm": 3.1864484621376525,
      "kl": 0.0634765625,
      "learning_rate": 9.994372720082478e-07,
      "loss": 0.0025,
      "reward": 2.1130313873291016,
      "reward_std": 0.02044382505118847,
      "rewards/accuracy_reward": 0.9130312204360962,
      "rewards/format_reward": 1.0,
      "step": 1095
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.0,
      "completion_length": 414.25,
      "epoch": 0.015117032868512159,
      "grad_norm": 2.1388219698734723,
      "kl": 0.05419921875,
      "learning_rate": 9.9943624391852e-07,
      "loss": 0.0022,
      "reward": 2.107875108718872,
      "reward_std": 0.05932911857962608,
      "rewards/accuracy_reward": 0.9203750491142273,
      "rewards/format_reward": 1.0,
      "step": 1096
    },
    {
      "all_correct": 0.75,
      "all_wrong": 0.0,
      "completion_length": 410.21875,
      "epoch": 0.015130825781713356,
      "grad_norm": 2.3839989599174833,
      "kl": 0.0625,
      "learning_rate": 9.99435214891032e-07,
      "loss": 0.0025,
      "reward": 2.0528125762939453,
      "reward_std": 0.019413847476243973,
      "rewards/accuracy_reward": 0.8528125286102295,
      "rewards/format_reward": 1.0,
      "step": 1097
    },
    {
      "all_correct": 0.25,
      "all_wrong": 0.0,
      "completion_length": 407.09375,
      "epoch": 0.015144618694914553,
      "grad_norm": 2.033735055120275,
      "kl": 0.0703125,
      "learning_rate": 9.994341849257859e-07,
      "loss": 0.0028,
      "reward": 1.9528439044952393,
      "reward_std": 0.025748802348971367,
      "rewards/accuracy_reward": 0.7528437972068787,
      "rewards/format_reward": 1.0,
      "step": 1098
    },
    {
      "all_correct": 0.75,
      "all_wrong": 0.0,
      "completion_length": 428.6875,
      "epoch": 0.01515841160811575,
      "grad_norm": 2.245073830736851,
      "kl": 0.064453125,
      "learning_rate": 9.994331540227832e-07,
      "loss": 0.0026,
      "reward": 2.001093864440918,
      "reward_std": 0.03333578258752823,
      "rewards/accuracy_reward": 0.8010937571525574,
      "rewards/format_reward": 1.0,
      "step": 1099
    },
    {
      "all_correct": 0.75,
      "all_wrong": 0.0,
      "completion_length": 402.375,
      "epoch": 0.015172204521316948,
      "grad_norm": 2.496701802389481,
      "kl": 0.07373046875,
      "learning_rate": 9.994321221820263e-07,
      "loss": 0.003,
      "reward": 2.0866875648498535,
      "reward_std": 0.023032210767269135,
      "rewards/accuracy_reward": 0.8866875171661377,
      "rewards/format_reward": 1.0,
      "step": 1100
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.0,
      "completion_length": 419.21875,
      "epoch": 0.015185997434518145,
      "grad_norm": 5.006268716123861,
      "kl": 0.0654296875,
      "learning_rate": 9.994310894035167e-07,
      "loss": 0.0026,
      "reward": 2.0892810821533203,
      "reward_std": 0.029601451009511948,
      "rewards/accuracy_reward": 0.895531177520752,
      "rewards/format_reward": 1.0,
      "step": 1101
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.0,
      "completion_length": 414.40625,
      "epoch": 0.015199790347719342,
      "grad_norm": 1.865276240188177,
      "kl": 0.064453125,
      "learning_rate": 9.994300556872567e-07,
      "loss": 0.0026,
      "reward": 2.017937660217285,
      "reward_std": 0.03594556450843811,
      "rewards/accuracy_reward": 0.8241875171661377,
      "rewards/format_reward": 1.0,
      "step": 1102
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.0,
      "completion_length": 412.25,
      "epoch": 0.01521358326092054,
      "grad_norm": 3.0769919361254736,
      "kl": 0.06787109375,
      "learning_rate": 9.994290210332478e-07,
      "loss": 0.0027,
      "reward": 2.0431251525878906,
      "reward_std": 0.05550801753997803,
      "rewards/accuracy_reward": 0.8493750095367432,
      "rewards/format_reward": 1.0,
      "step": 1103
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.0,
      "completion_length": 428.21875,
      "epoch": 0.015227376174121737,
      "grad_norm": 1.1934991898044662,
      "kl": 0.0615234375,
      "learning_rate": 9.994279854414927e-07,
      "loss": 0.0025,
      "reward": 2.0102500915527344,
      "reward_std": 0.00590096740052104,
      "rewards/accuracy_reward": 0.8102500438690186,
      "rewards/format_reward": 1.0,
      "step": 1104
    },
    {
      "all_correct": 0.75,
      "all_wrong": 0.0,
      "completion_length": 413.28125,
      "epoch": 0.015241169087322934,
      "grad_norm": 2.783297836932153,
      "kl": 0.0712890625,
      "learning_rate": 9.994269489119926e-07,
      "loss": 0.0029,
      "reward": 2.067812442779541,
      "reward_std": 0.018586885184049606,
      "rewards/accuracy_reward": 0.8678125143051147,
      "rewards/format_reward": 1.0,
      "step": 1105
    },
    {
      "all_correct": 0.75,
      "all_wrong": 0.0,
      "completion_length": 412.59375,
      "epoch": 0.015254962000524131,
      "grad_norm": 3.6209274001933975,
      "kl": 0.072265625,
      "learning_rate": 9.994259114447499e-07,
      "loss": 0.0029,
      "reward": 2.080812454223633,
      "reward_std": 0.019839555025100708,
      "rewards/accuracy_reward": 0.8808125257492065,
      "rewards/format_reward": 1.0,
      "step": 1106
    },
    {
      "all_correct": 0.25,
      "all_wrong": 0.0,
      "completion_length": 411.5,
      "epoch": 0.015268754913725329,
      "grad_norm": 1.483393149084059,
      "kl": 0.06201171875,
      "learning_rate": 9.994248730397661e-07,
      "loss": 0.0025,
      "reward": 2.0144686698913574,
      "reward_std": 0.010401781648397446,
      "rewards/accuracy_reward": 0.8144687414169312,
      "rewards/format_reward": 1.0,
      "step": 1107
    },
    {
      "all_correct": 0.75,
      "all_wrong": 0.0,
      "completion_length": 412.84375,
      "epoch": 0.015282547826926526,
      "grad_norm": 2.72084521752612,
      "kl": 0.060791015625,
      "learning_rate": 9.994238336970436e-07,
      "loss": 0.0024,
      "reward": 2.1058125495910645,
      "reward_std": 0.02686990797519684,
      "rewards/accuracy_reward": 0.9058125615119934,
      "rewards/format_reward": 1.0,
      "step": 1108
    },
    {
      "all_correct": 0.25,
      "all_wrong": 0.0,
      "completion_length": 403.8125,
      "epoch": 0.015296340740127722,
      "grad_norm": 1.823953342188384,
      "kl": 0.0703125,
      "learning_rate": 9.994227934165843e-07,
      "loss": 0.0028,
      "reward": 1.9065937995910645,
      "reward_std": 0.014940287917852402,
      "rewards/accuracy_reward": 0.7065937519073486,
      "rewards/format_reward": 1.0,
      "step": 1109
    },
    {
      "all_correct": 0.75,
      "all_wrong": 0.0,
      "completion_length": 405.9375,
      "epoch": 0.015310133653328919,
      "grad_norm": 2.114621453977902,
      "kl": 0.06494140625,
      "learning_rate": 9.994217521983898e-07,
      "loss": 0.0026,
      "reward": 2.06278133392334,
      "reward_std": 0.02265346422791481,
      "rewards/accuracy_reward": 0.862781286239624,
      "rewards/format_reward": 1.0,
      "step": 1110
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.0,
      "completion_length": 415.09375,
      "epoch": 0.015323926566530116,
      "grad_norm": 2.8239795437789477,
      "kl": 0.060546875,
      "learning_rate": 9.994207100424625e-07,
      "loss": 0.0024,
      "reward": 2.0698437690734863,
      "reward_std": 0.03149894252419472,
      "rewards/accuracy_reward": 0.8698437213897705,
      "rewards/format_reward": 1.0,
      "step": 1111
    },
    {
      "all_correct": 0.75,
      "all_wrong": 0.0,
      "completion_length": 402.40625,
      "epoch": 0.015337719479731313,
      "grad_norm": 1.7070307350029286,
      "kl": 0.06396484375,
      "learning_rate": 9.99419666948804e-07,
      "loss": 0.0025,
      "reward": 2.1032185554504395,
      "reward_std": 0.011139210313558578,
      "rewards/accuracy_reward": 0.9032188057899475,
      "rewards/format_reward": 1.0,
      "step": 1112
    },
    {
      "all_correct": 0.75,
      "all_wrong": 0.0,
      "completion_length": 411.46875,
      "epoch": 0.01535151239293251,
      "grad_norm": 19.24588487725623,
      "kl": 0.06640625,
      "learning_rate": 9.994186229174164e-07,
      "loss": 0.0027,
      "reward": 2.032562494277954,
      "reward_std": 0.023525450378656387,
      "rewards/accuracy_reward": 0.8325625061988831,
      "rewards/format_reward": 1.0,
      "step": 1113
    },
    {
      "all_correct": 0.75,
      "all_wrong": 0.0,
      "completion_length": 406.84375,
      "epoch": 0.015365305306133708,
      "grad_norm": 2.79638005343388,
      "kl": 0.06640625,
      "learning_rate": 9.994175779483017e-07,
      "loss": 0.0027,
      "reward": 2.038062572479248,
      "reward_std": 0.0161270871758461,
      "rewards/accuracy_reward": 0.8380624651908875,
      "rewards/format_reward": 1.0,
      "step": 1114
    },
    {
      "all_correct": 0.75,
      "all_wrong": 0.0,
      "completion_length": 393.375,
      "epoch": 0.015379098219334905,
      "grad_norm": 2.8525139000897015,
      "kl": 0.0615234375,
      "learning_rate": 9.994165320414618e-07,
      "loss": 0.0025,
      "reward": 2.1016249656677246,
      "reward_std": 0.015592718496918678,
      "rewards/accuracy_reward": 0.9016249775886536,
      "rewards/format_reward": 1.0,
      "step": 1115
    },
    {
      "all_correct": 0.75,
      "all_wrong": 0.0,
      "completion_length": 411.53125,
      "epoch": 0.015392891132536102,
      "grad_norm": 2.2731562507807763,
      "kl": 0.0654296875,
      "learning_rate": 9.994154851968988e-07,
      "loss": 0.0026,
      "reward": 2.048281192779541,
      "reward_std": 0.012053274549543858,
      "rewards/accuracy_reward": 0.8482812643051147,
      "rewards/format_reward": 1.0,
      "step": 1116
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.0,
      "completion_length": 392.375,
      "epoch": 0.0154066840457373,
      "grad_norm": 6.008809417243853,
      "kl": 0.068359375,
      "learning_rate": 9.994144374146145e-07,
      "loss": 0.0027,
      "reward": 1.990875005722046,
      "reward_std": 0.03312664106488228,
      "rewards/accuracy_reward": 0.7908750176429749,
      "rewards/format_reward": 1.0,
      "step": 1117
    },
    {
      "all_correct": 0.75,
      "all_wrong": 0.0,
      "completion_length": 402.21875,
      "epoch": 0.015420476958938497,
      "grad_norm": 2.406566575373047,
      "kl": 0.06298828125,
      "learning_rate": 9.994133886946108e-07,
      "loss": 0.0025,
      "reward": 2.0693750381469727,
      "reward_std": 0.029706541448831558,
      "rewards/accuracy_reward": 0.8693749904632568,
      "rewards/format_reward": 1.0,
      "step": 1118
    },
    {
      "all_correct": 0.25,
      "all_wrong": 0.0,
      "completion_length": 411.875,
      "epoch": 0.015434269872139694,
      "grad_norm": 2.0678949573014638,
      "kl": 0.06591796875,
      "learning_rate": 9.994123390368899e-07,
      "loss": 0.0026,
      "reward": 2.019843578338623,
      "reward_std": 0.046620793640613556,
      "rewards/accuracy_reward": 0.8323436975479126,
      "rewards/format_reward": 1.0,
      "step": 1119
    },
    {
      "all_correct": 0.75,
      "all_wrong": 0.0,
      "completion_length": 395.5,
      "epoch": 0.015448062785340892,
      "grad_norm": 1.73815244240117,
      "kl": 0.0556640625,
      "learning_rate": 9.994112884414537e-07,
      "loss": 0.0022,
      "reward": 2.124875068664551,
      "reward_std": 0.04046914353966713,
      "rewards/accuracy_reward": 0.937375009059906,
      "rewards/format_reward": 1.0,
      "step": 1120
    },
    {
      "all_correct": 0.75,
      "all_wrong": 0.0,
      "completion_length": 395.03125,
      "epoch": 0.015461855698542089,
      "grad_norm": 6.3524144726152825,
      "kl": 0.06787109375,
      "learning_rate": 9.99410236908304e-07,
      "loss": 0.0027,
      "reward": 2.114734411239624,
      "reward_std": 0.041595689952373505,
      "rewards/accuracy_reward": 0.9209843277931213,
      "rewards/format_reward": 1.0,
      "step": 1121
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.0,
      "completion_length": 394.59375,
      "epoch": 0.015475648611743286,
      "grad_norm": 1.9924175510208753,
      "kl": 0.06591796875,
      "learning_rate": 9.99409184437443e-07,
      "loss": 0.0026,
      "reward": 2.0250000953674316,
      "reward_std": 0.014884786680340767,
      "rewards/accuracy_reward": 0.8250000476837158,
      "rewards/format_reward": 1.0,
      "step": 1122
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.0,
      "completion_length": 400.375,
      "epoch": 0.015489441524944483,
      "grad_norm": 1.826142853300095,
      "kl": 0.060791015625,
      "learning_rate": 9.994081310288725e-07,
      "loss": 0.0024,
      "reward": 2.028390645980835,
      "reward_std": 0.012495080009102821,
      "rewards/accuracy_reward": 0.8283905982971191,
      "rewards/format_reward": 1.0,
      "step": 1123
    },
    {
      "all_correct": 0.75,
      "all_wrong": 0.0,
      "completion_length": 395.4375,
      "epoch": 0.01550323443814568,
      "grad_norm": 1.7060229216807339,
      "kl": 0.0712890625,
      "learning_rate": 9.994070766825946e-07,
      "loss": 0.0029,
      "reward": 2.027437448501587,
      "reward_std": 0.012202245183289051,
      "rewards/accuracy_reward": 0.8274375200271606,
      "rewards/format_reward": 1.0,
      "step": 1124
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.0,
      "completion_length": 397.625,
      "epoch": 0.015517027351346878,
      "grad_norm": 2.2619932484529777,
      "kl": 0.0634765625,
      "learning_rate": 9.994060213986112e-07,
      "loss": 0.0025,
      "reward": 2.034468650817871,
      "reward_std": 0.025152001529932022,
      "rewards/accuracy_reward": 0.8344687223434448,
      "rewards/format_reward": 1.0,
      "step": 1125
    },
    {
      "all_correct": 0.75,
      "all_wrong": 0.0,
      "completion_length": 390.71875,
      "epoch": 0.015530820264548075,
      "grad_norm": 3.162495559122797,
      "kl": 0.07470703125,
      "learning_rate": 9.994049651769245e-07,
      "loss": 0.003,
      "reward": 2.1051249504089355,
      "reward_std": 0.035846106708049774,
      "rewards/accuracy_reward": 0.9113749861717224,
      "rewards/format_reward": 1.0,
      "step": 1126
    },
    {
      "all_correct": 0.25,
      "all_wrong": 0.0,
      "completion_length": 413.59375,
      "epoch": 0.015544613177749272,
      "grad_norm": 2.514282537535975,
      "kl": 0.06494140625,
      "learning_rate": 9.994039080175362e-07,
      "loss": 0.0026,
      "reward": 2.037234306335449,
      "reward_std": 0.0439925417304039,
      "rewards/accuracy_reward": 0.8434844017028809,
      "rewards/format_reward": 1.0,
      "step": 1127
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.0,
      "completion_length": 387.65625,
      "epoch": 0.01555840609095047,
      "grad_norm": 2.797905476969195,
      "kl": 0.06494140625,
      "learning_rate": 9.994028499204482e-07,
      "loss": 0.0026,
      "reward": 1.9822499752044678,
      "reward_std": 0.01832308992743492,
      "rewards/accuracy_reward": 0.7822500467300415,
      "rewards/format_reward": 1.0,
      "step": 1128
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.0,
      "completion_length": 397.3125,
      "epoch": 0.015572199004151667,
      "grad_norm": 2.265747457683481,
      "kl": 0.06884765625,
      "learning_rate": 9.994017908856632e-07,
      "loss": 0.0027,
      "reward": 2.004718780517578,
      "reward_std": 0.02151535265147686,
      "rewards/accuracy_reward": 0.8047187924385071,
      "rewards/format_reward": 1.0,
      "step": 1129
    },
    {
      "all_correct": 0.75,
      "all_wrong": 0.0,
      "completion_length": 390.6875,
      "epoch": 0.015585991917352864,
      "grad_norm": 2.6598770148788073,
      "kl": 0.0732421875,
      "learning_rate": 9.994007309131822e-07,
      "loss": 0.0029,
      "reward": 2.0670626163482666,
      "reward_std": 0.034036919474601746,
      "rewards/accuracy_reward": 0.8733125925064087,
      "rewards/format_reward": 1.0,
      "step": 1130
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.0,
      "completion_length": 407.59375,
      "epoch": 0.015599784830554062,
      "grad_norm": 2.296487548390693,
      "kl": 0.061767578125,
      "learning_rate": 9.993996700030078e-07,
      "loss": 0.0025,
      "reward": 2.053187370300293,
      "reward_std": 0.025254828855395317,
      "rewards/accuracy_reward": 0.8531875610351562,
      "rewards/format_reward": 1.0,
      "step": 1131
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.0,
      "completion_length": 403.5625,
      "epoch": 0.015613577743755259,
      "grad_norm": 2.202847231501686,
      "kl": 0.064453125,
      "learning_rate": 9.993986081551419e-07,
      "loss": 0.0026,
      "reward": 1.945968747138977,
      "reward_std": 0.012108190916478634,
      "rewards/accuracy_reward": 0.745968759059906,
      "rewards/format_reward": 1.0,
      "step": 1132
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.0,
      "completion_length": 407.0,
      "epoch": 0.015627370656956456,
      "grad_norm": 2.1923861337441486,
      "kl": 0.056396484375,
      "learning_rate": 9.993975453695863e-07,
      "loss": 0.0023,
      "reward": 2.101968765258789,
      "reward_std": 0.03147018700838089,
      "rewards/accuracy_reward": 0.9082187414169312,
      "rewards/format_reward": 1.0,
      "step": 1133
    },
    {
      "all_correct": 0.75,
      "all_wrong": 0.0,
      "completion_length": 402.84375,
      "epoch": 0.015641163570157653,
      "grad_norm": 2.876764104519325,
      "kl": 0.072265625,
      "learning_rate": 9.993964816463433e-07,
      "loss": 0.0029,
      "reward": 2.119874954223633,
      "reward_std": 0.029321841895580292,
      "rewards/accuracy_reward": 0.9198750257492065,
      "rewards/format_reward": 1.0,
      "step": 1134
    },
    {
      "all_correct": 0.25,
      "all_wrong": 0.0,
      "completion_length": 406.875,
      "epoch": 0.01565495648335885,
      "grad_norm": 2.588124826073845,
      "kl": 0.06787109375,
      "learning_rate": 9.993954169854146e-07,
      "loss": 0.0027,
      "reward": 1.9973751306533813,
      "reward_std": 0.019354483112692833,
      "rewards/accuracy_reward": 0.797374963760376,
      "rewards/format_reward": 1.0,
      "step": 1135
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.0,
      "completion_length": 405.6875,
      "epoch": 0.015668749396560048,
      "grad_norm": 2.365653484663119,
      "kl": 0.0703125,
      "learning_rate": 9.993943513868023e-07,
      "loss": 0.0028,
      "reward": 1.9656875133514404,
      "reward_std": 0.025600366294384003,
      "rewards/accuracy_reward": 0.7656875252723694,
      "rewards/format_reward": 1.0,
      "step": 1136
    },
    {
      "all_correct": 1.0,
      "all_wrong": 0.0,
      "completion_length": 409.71875,
      "epoch": 0.015682542309761245,
      "grad_norm": 2.76342915524858,
      "kl": 0.07421875,
      "learning_rate": 9.993932848505086e-07,
      "loss": 0.003,
      "reward": 2.1200313568115234,
      "reward_std": 0.021025152876973152,
      "rewards/accuracy_reward": 0.9200311899185181,
      "rewards/format_reward": 1.0,
      "step": 1137
    },
    {
      "all_correct": 0.75,
      "all_wrong": 0.0,
      "completion_length": 393.5,
      "epoch": 0.015696335222962442,
      "grad_norm": 3.4983245109927177,
      "kl": 0.06982421875,
      "learning_rate": 9.993922173765353e-07,
      "loss": 0.0028,
      "reward": 2.0953750610351562,
      "reward_std": 0.01202378235757351,
      "rewards/accuracy_reward": 0.8953750729560852,
      "rewards/format_reward": 1.0,
      "step": 1138
    },
    {
      "all_correct": 0.75,
      "all_wrong": 0.0,
      "completion_length": 410.125,
      "epoch": 0.01571012813616364,
      "grad_norm": 2.6349678223295143,
      "kl": 0.06884765625,
      "learning_rate": 9.993911489648844e-07,
      "loss": 0.0028,
      "reward": 2.112593650817871,
      "reward_std": 0.03881729394197464,
      "rewards/accuracy_reward": 0.9188437461853027,
      "rewards/format_reward": 1.0,
      "step": 1139
    },
    {
      "all_correct": 0.25,
      "all_wrong": 0.0,
      "completion_length": 392.0,
      "epoch": 0.015723921049364837,
      "grad_norm": 5.279422495562205,
      "kl": 0.0673828125,
      "learning_rate": 9.99390079615558e-07,
      "loss": 0.0027,
      "reward": 1.995750069618225,
      "reward_std": 0.036774467676877975,
      "rewards/accuracy_reward": 0.7957500219345093,
      "rewards/format_reward": 1.0,
      "step": 1140
    },
    {
      "all_correct": 1.0,
      "all_wrong": 0.0,
      "completion_length": 396.5625,
      "epoch": 0.015737713962566034,
      "grad_norm": 55.02813971989049,
      "kl": 0.05615234375,
      "learning_rate": 9.99389009328558e-07,
      "loss": 0.0022,
      "reward": 2.1155624389648438,
      "reward_std": 0.014095155522227287,
      "rewards/accuracy_reward": 0.9155624508857727,
      "rewards/format_reward": 1.0,
      "step": 1141
    },
    {
      "all_correct": 0.75,
      "all_wrong": 0.0,
      "completion_length": 418.8125,
      "epoch": 0.01575150687576723,
      "grad_norm": 5.8619625184261075,
      "kl": 0.06201171875,
      "learning_rate": 9.993879381038865e-07,
      "loss": 0.0025,
      "reward": 2.0765938758850098,
      "reward_std": 0.04129648208618164,
      "rewards/accuracy_reward": 0.8765937089920044,
      "rewards/format_reward": 1.0,
      "step": 1142
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.0,
      "completion_length": 387.8125,
      "epoch": 0.01576529978896843,
      "grad_norm": 2.0790611137040105,
      "kl": 0.0625,
      "learning_rate": 9.993868659415453e-07,
      "loss": 0.0025,
      "reward": 2.0629687309265137,
      "reward_std": 0.08024712651968002,
      "rewards/accuracy_reward": 0.8629688024520874,
      "rewards/format_reward": 1.0,
      "step": 1143
    },
    {
      "all_correct": 0.25,
      "all_wrong": 0.0,
      "completion_length": 409.90625,
      "epoch": 0.015779092702169626,
      "grad_norm": 4.885438570305793,
      "kl": 0.060546875,
      "learning_rate": 9.993857928415368e-07,
      "loss": 0.0024,
      "reward": 2.044875144958496,
      "reward_std": 0.028586652129888535,
      "rewards/accuracy_reward": 0.8448749780654907,
      "rewards/format_reward": 1.0,
      "step": 1144
    },
    {
      "all_correct": 0.75,
      "all_wrong": 0.0,
      "completion_length": 405.4375,
      "epoch": 0.015792885615370823,
      "grad_norm": 2.698557986663061,
      "kl": 0.064453125,
      "learning_rate": 9.993847188038628e-07,
      "loss": 0.0026,
      "reward": 2.0670313835144043,
      "reward_std": 0.027227405458688736,
      "rewards/accuracy_reward": 0.8670312166213989,
      "rewards/format_reward": 1.0,
      "step": 1145
    },
    {
      "all_correct": 0.25,
      "all_wrong": 0.0,
      "completion_length": 392.71875,
      "epoch": 0.01580667852857202,
      "grad_norm": 2.430768731897271,
      "kl": 0.060302734375,
      "learning_rate": 9.993836438285255e-07,
      "loss": 0.0024,
      "reward": 2.037937641143799,
      "reward_std": 0.041231196373701096,
      "rewards/accuracy_reward": 0.8441874384880066,
      "rewards/format_reward": 1.0,
      "step": 1146
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.0,
      "completion_length": 417.0625,
      "epoch": 0.015820471441773218,
      "grad_norm": 2.982746654651911,
      "kl": 0.05859375,
      "learning_rate": 9.993825679155262e-07,
      "loss": 0.0023,
      "reward": 2.077031373977661,
      "reward_std": 0.061495304107666016,
      "rewards/accuracy_reward": 0.8770313262939453,
      "rewards/format_reward": 1.0,
      "step": 1147
    },
    {
      "all_correct": 0.0,
      "all_wrong": 0.0,
      "completion_length": 410.3125,
      "epoch": 0.015834264354974415,
      "grad_norm": 1.8186873686715441,
      "kl": 0.0576171875,
      "learning_rate": 9.99381491064868e-07,
      "loss": 0.0023,
      "reward": 1.9345937967300415,
      "reward_std": 0.020978011190891266,
      "rewards/accuracy_reward": 0.7345937490463257,
      "rewards/format_reward": 1.0,
      "step": 1148
    },
    {
      "all_correct": 0.75,
      "all_wrong": 0.0,
      "completion_length": 407.96875,
      "epoch": 0.015848057268175612,
      "grad_norm": 2.3525540442997595,
      "kl": 0.06494140625,
      "learning_rate": 9.993804132765521e-07,
      "loss": 0.0026,
      "reward": 2.0937187671661377,
      "reward_std": 0.020365837961435318,
      "rewards/accuracy_reward": 0.8937187790870667,
      "rewards/format_reward": 1.0,
      "step": 1149
    },
    {
      "all_correct": 0.75,
      "all_wrong": 0.0,
      "completion_length": 421.78125,
      "epoch": 0.01586185018137681,
      "grad_norm": 14.01362629528508,
      "kl": 0.06640625,
      "learning_rate": 9.993793345505809e-07,
      "loss": 0.0026,
      "reward": 2.0889062881469727,
      "reward_std": 0.019671235233545303,
      "rewards/accuracy_reward": 0.8889062404632568,
      "rewards/format_reward": 1.0,
      "step": 1150
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.0,
      "completion_length": 417.09375,
      "epoch": 0.015875643094578007,
      "grad_norm": 2.3662879399109267,
      "kl": 0.05810546875,
      "learning_rate": 9.993782548869562e-07,
      "loss": 0.0023,
      "reward": 1.9958750009536743,
      "reward_std": 0.03132371976971626,
      "rewards/accuracy_reward": 0.7958749532699585,
      "rewards/format_reward": 1.0,
      "step": 1151
    },
    {
      "all_correct": 0.25,
      "all_wrong": 0.0,
      "completion_length": 410.21875,
      "epoch": 0.015889436007779204,
      "grad_norm": 2.399341917265444,
      "kl": 0.062255859375,
      "learning_rate": 9.993771742856804e-07,
      "loss": 0.0025,
      "reward": 1.9700312614440918,
      "reward_std": 0.040816061198711395,
      "rewards/accuracy_reward": 0.7700312733650208,
      "rewards/format_reward": 1.0,
      "step": 1152
    },
    {
      "all_correct": 0.75,
      "all_wrong": 0.0,
      "completion_length": 394.46875,
      "epoch": 0.0159032289209804,
      "grad_norm": 2.3654804095394653,
      "kl": 0.06201171875,
      "learning_rate": 9.993760927467553e-07,
      "loss": 0.0025,
      "reward": 2.0527501106262207,
      "reward_std": 0.03276272863149643,
      "rewards/accuracy_reward": 0.8527500033378601,
      "rewards/format_reward": 1.0,
      "step": 1153
    },
    {
      "all_correct": 0.25,
      "all_wrong": 0.0,
      "completion_length": 416.0625,
      "epoch": 0.0159170218341816,
      "grad_norm": 1.8090014575254691,
      "kl": 0.060791015625,
      "learning_rate": 9.993750102701826e-07,
      "loss": 0.0024,
      "reward": 2.009671926498413,
      "reward_std": 0.026841901242733,
      "rewards/accuracy_reward": 0.8159218430519104,
      "rewards/format_reward": 1.0,
      "step": 1154
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.0,
      "completion_length": 407.5,
      "epoch": 0.015930814747382796,
      "grad_norm": 4.245357779411806,
      "kl": 0.06201171875,
      "learning_rate": 9.993739268559647e-07,
      "loss": 0.0025,
      "reward": 2.044343948364258,
      "reward_std": 0.027243871241807938,
      "rewards/accuracy_reward": 0.8443437218666077,
      "rewards/format_reward": 1.0,
      "step": 1155
    },
    {
      "all_correct": 0.25,
      "all_wrong": 0.0,
      "completion_length": 423.03125,
      "epoch": 0.015944607660583993,
      "grad_norm": 2.4299734333140215,
      "kl": 0.06591796875,
      "learning_rate": 9.99372842504104e-07,
      "loss": 0.0026,
      "reward": 1.964296817779541,
      "reward_std": 0.045913681387901306,
      "rewards/accuracy_reward": 0.7705468535423279,
      "rewards/format_reward": 1.0,
      "step": 1156
    },
    {
      "all_correct": 0.75,
      "all_wrong": 0.0,
      "completion_length": 399.75,
      "epoch": 0.01595840057378519,
      "grad_norm": 2.4141429541700226,
      "kl": 0.0634765625,
      "learning_rate": 9.993717572146016e-07,
      "loss": 0.0025,
      "reward": 2.0583748817443848,
      "reward_std": 0.013394411653280258,
      "rewards/accuracy_reward": 0.8583750128746033,
      "rewards/format_reward": 1.0,
      "step": 1157
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.0,
      "completion_length": 401.875,
      "epoch": 0.015972193486986388,
      "grad_norm": 2.7514518993397274,
      "kl": 0.06640625,
      "learning_rate": 9.993706709874602e-07,
      "loss": 0.0026,
      "reward": 1.9363125562667847,
      "reward_std": 0.032857369631528854,
      "rewards/accuracy_reward": 0.7425625324249268,
      "rewards/format_reward": 1.0,
      "step": 1158
    },
    {
      "all_correct": 0.75,
      "all_wrong": 0.0,
      "completion_length": 410.78125,
      "epoch": 0.015985986400187585,
      "grad_norm": 1.3329847645543602,
      "kl": 0.055908203125,
      "learning_rate": 9.993695838226818e-07,
      "loss": 0.0022,
      "reward": 2.0935001373291016,
      "reward_std": 0.009721132926642895,
      "rewards/accuracy_reward": 0.893500030040741,
      "rewards/format_reward": 1.0,
      "step": 1159
    },
    {
      "all_correct": 0.75,
      "all_wrong": 0.0,
      "completion_length": 413.09375,
      "epoch": 0.015999779313388782,
      "grad_norm": 5.65610004433882,
      "kl": 0.05908203125,
      "learning_rate": 9.993684957202684e-07,
      "loss": 0.0024,
      "reward": 2.0814061164855957,
      "reward_std": 0.03583874925971031,
      "rewards/accuracy_reward": 0.8876563310623169,
      "rewards/format_reward": 1.0,
      "step": 1160
    },
    {
      "all_correct": 0.75,
      "all_wrong": 0.0,
      "completion_length": 427.625,
      "epoch": 0.01601357222658998,
      "grad_norm": 1.5261686316222318,
      "kl": 0.0595703125,
      "learning_rate": 9.99367406680222e-07,
      "loss": 0.0024,
      "reward": 2.120187282562256,
      "reward_std": 0.010566852986812592,
      "rewards/accuracy_reward": 0.9201875329017639,
      "rewards/format_reward": 1.0,
      "step": 1161
    },
    {
      "all_correct": 0.0,
      "all_wrong": 0.0,
      "completion_length": 444.46875,
      "epoch": 0.016027365139791177,
      "grad_norm": 1.709002106042905,
      "kl": 0.058837890625,
      "learning_rate": 9.993663167025445e-07,
      "loss": 0.0024,
      "reward": 1.9316562414169312,
      "reward_std": 0.03195605427026749,
      "rewards/accuracy_reward": 0.737906277179718,
      "rewards/format_reward": 1.0,
      "step": 1162
    },
    {
      "all_correct": 0.75,
      "all_wrong": 0.0,
      "completion_length": 410.15625,
      "epoch": 0.016041158052992374,
      "grad_norm": 1.8828778686583867,
      "kl": 0.06689453125,
      "learning_rate": 9.99365225787238e-07,
      "loss": 0.0027,
      "reward": 2.0196564197540283,
      "reward_std": 0.016404660418629646,
      "rewards/accuracy_reward": 0.8196563124656677,
      "rewards/format_reward": 1.0,
      "step": 1163
    },
    {
      "all_correct": 0.25,
      "all_wrong": 0.0,
      "completion_length": 418.6875,
      "epoch": 0.01605495096619357,
      "grad_norm": 2.6157308153332623,
      "kl": 0.0673828125,
      "learning_rate": 9.993641339343048e-07,
      "loss": 0.0027,
      "reward": 1.8850313425064087,
      "reward_std": 0.02486385405063629,
      "rewards/accuracy_reward": 0.6850312948226929,
      "rewards/format_reward": 1.0,
      "step": 1164
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.0,
      "completion_length": 417.25,
      "epoch": 0.016068743879394765,
      "grad_norm": 3.282839511851077,
      "kl": 0.06298828125,
      "learning_rate": 9.993630411437468e-07,
      "loss": 0.0025,
      "reward": 2.0717499256134033,
      "reward_std": 0.05713348463177681,
      "rewards/accuracy_reward": 0.878000020980835,
      "rewards/format_reward": 1.0,
      "step": 1165
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.0,
      "completion_length": 424.375,
      "epoch": 0.016082536792595963,
      "grad_norm": 1.6727532247128405,
      "kl": 0.06494140625,
      "learning_rate": 9.993619474155658e-07,
      "loss": 0.0026,
      "reward": 1.9839375019073486,
      "reward_std": 0.012156892567873001,
      "rewards/accuracy_reward": 0.7839374542236328,
      "rewards/format_reward": 1.0,
      "step": 1166
    },
    {
      "all_correct": 0.75,
      "all_wrong": 0.0,
      "completion_length": 413.78125,
      "epoch": 0.01609632970579716,
      "grad_norm": 1.7988053296143596,
      "kl": 0.0595703125,
      "learning_rate": 9.993608527497643e-07,
      "loss": 0.0024,
      "reward": 2.0970938205718994,
      "reward_std": 0.01126367598772049,
      "rewards/accuracy_reward": 0.8970937728881836,
      "rewards/format_reward": 1.0,
      "step": 1167
    },
    {
      "all_correct": 0.75,
      "all_wrong": 0.0,
      "completion_length": 415.34375,
      "epoch": 0.016110122618998357,
      "grad_norm": 2.5477468422602287,
      "kl": 0.05615234375,
      "learning_rate": 9.99359757146344e-07,
      "loss": 0.0022,
      "reward": 2.0705623626708984,
      "reward_std": 0.02816617116332054,
      "rewards/accuracy_reward": 0.8705624938011169,
      "rewards/format_reward": 1.0,
      "step": 1168
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.0,
      "completion_length": 414.71875,
      "epoch": 0.016123915532199554,
      "grad_norm": 5.685719393648389,
      "kl": 0.05712890625,
      "learning_rate": 9.99358660605307e-07,
      "loss": 0.0023,
      "reward": 2.0773439407348633,
      "reward_std": 0.036236897110939026,
      "rewards/accuracy_reward": 0.8773437738418579,
      "rewards/format_reward": 1.0,
      "step": 1169
    },
    {
      "all_correct": 0.75,
      "all_wrong": 0.0,
      "completion_length": 416.0,
      "epoch": 0.01613770844540075,
      "grad_norm": 1.729303054238063,
      "kl": 0.05517578125,
      "learning_rate": 9.993575631266558e-07,
      "loss": 0.0022,
      "reward": 2.0693438053131104,
      "reward_std": 0.017319152131676674,
      "rewards/accuracy_reward": 0.8693437576293945,
      "rewards/format_reward": 1.0,
      "step": 1170
    },
    {
      "all_correct": 0.25,
      "all_wrong": 0.0,
      "completion_length": 424.1875,
      "epoch": 0.01615150135860195,
      "grad_norm": 2.243796428548856,
      "kl": 0.062255859375,
      "learning_rate": 9.993564647103919e-07,
      "loss": 0.0025,
      "reward": 2.0122811794281006,
      "reward_std": 0.04178939759731293,
      "rewards/accuracy_reward": 0.8185312747955322,
      "rewards/format_reward": 1.0,
      "step": 1171
    },
    {
      "all_correct": 1.0,
      "all_wrong": 0.0,
      "completion_length": 397.4375,
      "epoch": 0.016165294271803146,
      "grad_norm": 1.3220641681103404,
      "kl": 0.056396484375,
      "learning_rate": 9.993553653565175e-07,
      "loss": 0.0022,
      "reward": 2.1764373779296875,
      "reward_std": 0.0063827005214989185,
      "rewards/accuracy_reward": 0.9764374494552612,
      "rewards/format_reward": 1.0,
      "step": 1172
    },
    {
      "all_correct": 0.75,
      "all_wrong": 0.0,
      "completion_length": 410.5625,
      "epoch": 0.016179087185004343,
      "grad_norm": 3.0231804717365582,
      "kl": 0.06005859375,
      "learning_rate": 9.99354265065035e-07,
      "loss": 0.0024,
      "reward": 2.061187744140625,
      "reward_std": 0.026546740904450417,
      "rewards/accuracy_reward": 0.8611875176429749,
      "rewards/format_reward": 1.0,
      "step": 1173
    },
    {
      "all_correct": 0.75,
      "all_wrong": 0.0,
      "completion_length": 415.46875,
      "epoch": 0.01619288009820554,
      "grad_norm": 4.597139166488826,
      "kl": 0.0654296875,
      "learning_rate": 9.993531638359459e-07,
      "loss": 0.0026,
      "reward": 2.1100001335144043,
      "reward_std": 0.026963971555233,
      "rewards/accuracy_reward": 0.9100000262260437,
      "rewards/format_reward": 1.0,
      "step": 1174
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.0,
      "completion_length": 423.3125,
      "epoch": 0.016206673011406738,
      "grad_norm": 6.21985943125025,
      "kl": 0.0537109375,
      "learning_rate": 9.993520616692526e-07,
      "loss": 0.0021,
      "reward": 2.04325008392334,
      "reward_std": 0.037057772278785706,
      "rewards/accuracy_reward": 0.8494999408721924,
      "rewards/format_reward": 1.0,
      "step": 1175
    },
    {
      "all_correct": 0.25,
      "all_wrong": 0.0,
      "completion_length": 416.25,
      "epoch": 0.016220465924607935,
      "grad_norm": 2.414668465904221,
      "kl": 0.056640625,
      "learning_rate": 9.99350958564957e-07,
      "loss": 0.0023,
      "reward": 1.9773750305175781,
      "reward_std": 0.02781280316412449,
      "rewards/accuracy_reward": 0.7773749828338623,
      "rewards/format_reward": 1.0,
      "step": 1176
    },
    {
      "all_correct": 0.75,
      "all_wrong": 0.0,
      "completion_length": 412.5,
      "epoch": 0.016234258837809133,
      "grad_norm": 2.31868472194358,
      "kl": 0.0537109375,
      "learning_rate": 9.993498545230616e-07,
      "loss": 0.0021,
      "reward": 2.1153438091278076,
      "reward_std": 0.015813734382390976,
      "rewards/accuracy_reward": 0.9153437614440918,
      "rewards/format_reward": 1.0,
      "step": 1177
    },
    {
      "all_correct": 0.75,
      "all_wrong": 0.0,
      "completion_length": 407.25,
      "epoch": 0.01624805175101033,
      "grad_norm": 2.948206045648212,
      "kl": 0.06396484375,
      "learning_rate": 9.993487495435682e-07,
      "loss": 0.0026,
      "reward": 2.121500015258789,
      "reward_std": 0.026033833622932434,
      "rewards/accuracy_reward": 0.9214999675750732,
      "rewards/format_reward": 1.0,
      "step": 1178
    },
    {
      "all_correct": 1.0,
      "all_wrong": 0.0,
      "completion_length": 411.4375,
      "epoch": 0.016261844664211527,
      "grad_norm": 2.127673203166328,
      "kl": 0.0654296875,
      "learning_rate": 9.993476436264787e-07,
      "loss": 0.0026,
      "reward": 2.1236250400543213,
      "reward_std": 0.024130120873451233,
      "rewards/accuracy_reward": 0.9236249923706055,
      "rewards/format_reward": 1.0,
      "step": 1179
    },
    {
      "all_correct": 0.25,
      "all_wrong": 0.0,
      "completion_length": 438.96875,
      "epoch": 0.016275637577412724,
      "grad_norm": 2.5536922089990703,
      "kl": 0.060302734375,
      "learning_rate": 9.993465367717954e-07,
      "loss": 0.0024,
      "reward": 1.9992188215255737,
      "reward_std": 0.0426429882645607,
      "rewards/accuracy_reward": 0.8117187023162842,
      "rewards/format_reward": 1.0,
      "step": 1180
    },
    {
      "all_correct": 0.75,
      "all_wrong": 0.0,
      "completion_length": 417.625,
      "epoch": 0.01628943049061392,
      "grad_norm": 6.645836548127712,
      "kl": 0.05517578125,
      "learning_rate": 9.993454289795205e-07,
      "loss": 0.0022,
      "reward": 2.098656177520752,
      "reward_std": 0.024374019354581833,
      "rewards/accuracy_reward": 0.8986561894416809,
      "rewards/format_reward": 1.0,
      "step": 1181
    },
    {
      "all_correct": 0.75,
      "all_wrong": 0.0,
      "completion_length": 404.3125,
      "epoch": 0.01630322340381512,
      "grad_norm": 1.5768737030021052,
      "kl": 0.06005859375,
      "learning_rate": 9.993443202496557e-07,
      "loss": 0.0024,
      "reward": 2.083124876022339,
      "reward_std": 0.054747484624385834,
      "rewards/accuracy_reward": 0.8831250071525574,
      "rewards/format_reward": 1.0,
      "step": 1182
    },
    {
      "all_correct": 1.0,
      "all_wrong": 0.0,
      "completion_length": 425.9375,
      "epoch": 0.016317016317016316,
      "grad_norm": 2.722133619504414,
      "kl": 0.06982421875,
      "learning_rate": 9.993432105822034e-07,
      "loss": 0.0028,
      "reward": 2.1630001068115234,
      "reward_std": 0.02354966662824154,
      "rewards/accuracy_reward": 0.969249963760376,
      "rewards/format_reward": 1.0,
      "step": 1183
    },
    {
      "all_correct": 0.75,
      "all_wrong": 0.0,
      "completion_length": 412.40625,
      "epoch": 0.016330809230217513,
      "grad_norm": 2.656927516556769,
      "kl": 0.059326171875,
      "learning_rate": 9.993420999771654e-07,
      "loss": 0.0024,
      "reward": 2.0958125591278076,
      "reward_std": 0.021701566874980927,
      "rewards/accuracy_reward": 0.9020625352859497,
      "rewards/format_reward": 1.0,
      "step": 1184
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.0,
      "completion_length": 420.28125,
      "epoch": 0.01634460214341871,
      "grad_norm": 2.4785063990663834,
      "kl": 0.06689453125,
      "learning_rate": 9.99340988434544e-07,
      "loss": 0.0027,
      "reward": 2.084343910217285,
      "reward_std": 0.0472121424973011,
      "rewards/accuracy_reward": 0.8905937671661377,
      "rewards/format_reward": 1.0,
      "step": 1185
    },
    {
      "all_correct": 0.75,
      "all_wrong": 0.0,
      "completion_length": 419.0625,
      "epoch": 0.016358395056619908,
      "grad_norm": 3.2443550863611654,
      "kl": 0.0595703125,
      "learning_rate": 9.99339875954341e-07,
      "loss": 0.0024,
      "reward": 2.087296962738037,
      "reward_std": 0.019508250057697296,
      "rewards/accuracy_reward": 0.8872967958450317,
      "rewards/format_reward": 1.0,
      "step": 1186
    },
    {
      "all_correct": 0.75,
      "all_wrong": 0.0,
      "completion_length": 413.21875,
      "epoch": 0.016372187969821105,
      "grad_norm": 2.005623501282883,
      "kl": 0.06640625,
      "learning_rate": 9.99338762536559e-07,
      "loss": 0.0026,
      "reward": 2.1083436012268066,
      "reward_std": 0.032916728407144547,
      "rewards/accuracy_reward": 0.9145937561988831,
      "rewards/format_reward": 1.0,
      "step": 1187
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.0,
      "completion_length": 394.65625,
      "epoch": 0.016385980883022302,
      "grad_norm": 2.44556714816464,
      "kl": 0.056396484375,
      "learning_rate": 9.993376481812e-07,
      "loss": 0.0023,
      "reward": 2.055093765258789,
      "reward_std": 0.018108908087015152,
      "rewards/accuracy_reward": 0.8550937175750732,
      "rewards/format_reward": 1.0,
      "step": 1188
    },
    {
      "all_correct": 1.0,
      "all_wrong": 0.0,
      "completion_length": 406.625,
      "epoch": 0.0163997737962235,
      "grad_norm": 5.325937417213604,
      "kl": 0.062255859375,
      "learning_rate": 9.993365328882655e-07,
      "loss": 0.0024,
      "reward": 2.1734375953674316,
      "reward_std": 0.012735157273709774,
      "rewards/accuracy_reward": 0.973437488079071,
      "rewards/format_reward": 1.0,
      "step": 1189
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.0,
      "completion_length": 409.09375,
      "epoch": 0.016413566709424697,
      "grad_norm": 2.1502562404801715,
      "kl": 0.060791015625,
      "learning_rate": 9.993354166577582e-07,
      "loss": 0.0024,
      "reward": 2.113156318664551,
      "reward_std": 0.027573805302381516,
      "rewards/accuracy_reward": 0.9194062352180481,
      "rewards/format_reward": 1.0,
      "step": 1190
    },
    {
      "all_correct": 1.0,
      "all_wrong": 0.0,
      "completion_length": 395.96875,
      "epoch": 0.016427359622625894,
      "grad_norm": 2.1803974872619025,
      "kl": 0.06787109375,
      "learning_rate": 9.9933429948968e-07,
      "loss": 0.0027,
      "reward": 2.0982186794281006,
      "reward_std": 0.018505975604057312,
      "rewards/accuracy_reward": 0.8982187509536743,
      "rewards/format_reward": 1.0,
      "step": 1191
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.0,
      "completion_length": 392.5625,
      "epoch": 0.01644115253582709,
      "grad_norm": 2.707978402526472,
      "kl": 0.057861328125,
      "learning_rate": 9.99333181384033e-07,
      "loss": 0.0023,
      "reward": 2.0052812099456787,
      "reward_std": 0.011651430279016495,
      "rewards/accuracy_reward": 0.8052812814712524,
      "rewards/format_reward": 1.0,
      "step": 1192
    },
    {
      "all_correct": 0.75,
      "all_wrong": 0.0,
      "completion_length": 383.0,
      "epoch": 0.01645494544902829,
      "grad_norm": 4.624640841441573,
      "kl": 0.0673828125,
      "learning_rate": 9.993320623408191e-07,
      "loss": 0.0027,
      "reward": 2.119000196456909,
      "reward_std": 0.030218057334423065,
      "rewards/accuracy_reward": 0.918999969959259,
      "rewards/format_reward": 1.0,
      "step": 1193
    },
    {
      "all_correct": 1.0,
      "all_wrong": 0.0,
      "completion_length": 394.125,
      "epoch": 0.016468738362229486,
      "grad_norm": 1.9728416662091435,
      "kl": 0.060546875,
      "learning_rate": 9.993309423600406e-07,
      "loss": 0.0024,
      "reward": 2.122812509536743,
      "reward_std": 0.013722698204219341,
      "rewards/accuracy_reward": 0.9228125810623169,
      "rewards/format_reward": 1.0,
      "step": 1194
    },
    {
      "all_correct": 0.75,
      "all_wrong": 0.0,
      "completion_length": 393.0,
      "epoch": 0.016482531275430683,
      "grad_norm": 5.512863984092441,
      "kl": 0.06396484375,
      "learning_rate": 9.993298214417e-07,
      "loss": 0.0026,
      "reward": 2.096468687057495,
      "reward_std": 0.018410982564091682,
      "rewards/accuracy_reward": 0.8964687585830688,
      "rewards/format_reward": 1.0,
      "step": 1195
    },
    {
      "all_correct": 1.0,
      "all_wrong": 0.0,
      "completion_length": 394.21875,
      "epoch": 0.01649632418863188,
      "grad_norm": 2.3584568620794193,
      "kl": 0.06787109375,
      "learning_rate": 9.993286995857986e-07,
      "loss": 0.0027,
      "reward": 2.144625186920166,
      "reward_std": 0.019434140995144844,
      "rewards/accuracy_reward": 0.9446250200271606,
      "rewards/format_reward": 1.0,
      "step": 1196
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.0,
      "completion_length": 381.5625,
      "epoch": 0.016510117101833078,
      "grad_norm": 3.0144953213459136,
      "kl": 0.06884765625,
      "learning_rate": 9.99327576792339e-07,
      "loss": 0.0028,
      "reward": 2.052968740463257,
      "reward_std": 0.053260281682014465,
      "rewards/accuracy_reward": 0.8592187762260437,
      "rewards/format_reward": 1.0,
      "step": 1197
    },
    {
      "all_correct": 1.0,
      "all_wrong": 0.0,
      "completion_length": 381.75,
      "epoch": 0.016523910015034275,
      "grad_norm": 4.148022864199572,
      "kl": 0.05810546875,
      "learning_rate": 9.993264530613233e-07,
      "loss": 0.0023,
      "reward": 2.125500202178955,
      "reward_std": 0.042740464210510254,
      "rewards/accuracy_reward": 0.9255000352859497,
      "rewards/format_reward": 1.0,
      "step": 1198
    },
    {
      "all_correct": 0.25,
      "all_wrong": 0.0,
      "completion_length": 381.25,
      "epoch": 0.016537702928235472,
      "grad_norm": 5.691347690396019,
      "kl": 0.05712890625,
      "learning_rate": 9.993253283927534e-07,
      "loss": 0.0023,
      "reward": 1.9095938205718994,
      "reward_std": 0.0367857925593853,
      "rewards/accuracy_reward": 0.7158437967300415,
      "rewards/format_reward": 1.0,
      "step": 1199
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.0,
      "completion_length": 394.09375,
      "epoch": 0.01655149584143667,
      "grad_norm": 2.4616430536119296,
      "kl": 0.06005859375,
      "learning_rate": 9.993242027866317e-07,
      "loss": 0.0024,
      "reward": 2.0504064559936523,
      "reward_std": 0.021390054374933243,
      "rewards/accuracy_reward": 0.850406289100647,
      "rewards/format_reward": 1.0,
      "step": 1200
    },
    {
      "all_correct": 0.75,
      "all_wrong": 0.0,
      "completion_length": 376.78125,
      "epoch": 0.016565288754637867,
      "grad_norm": 1.4475569873349592,
      "kl": 0.061767578125,
      "learning_rate": 9.993230762429601e-07,
      "loss": 0.0025,
      "reward": 2.050187587738037,
      "reward_std": 0.01267438754439354,
      "rewards/accuracy_reward": 0.8501875400543213,
      "rewards/format_reward": 1.0,
      "step": 1201
    },
    {
      "all_correct": 1.0,
      "all_wrong": 0.0,
      "completion_length": 386.40625,
      "epoch": 0.016579081667839064,
      "grad_norm": 6.089982266676443,
      "kl": 0.05078125,
      "learning_rate": 9.993219487617407e-07,
      "loss": 0.002,
      "reward": 2.1338748931884766,
      "reward_std": 0.007224694825708866,
      "rewards/accuracy_reward": 0.9338750243186951,
      "rewards/format_reward": 1.0,
      "step": 1202
    },
    {
      "all_correct": 0.75,
      "all_wrong": 0.0,
      "completion_length": 388.40625,
      "epoch": 0.01659287458104026,
      "grad_norm": 2.3111265386563793,
      "kl": 0.061767578125,
      "learning_rate": 9.993208203429758e-07,
      "loss": 0.0025,
      "reward": 2.145124912261963,
      "reward_std": 0.026629649102687836,
      "rewards/accuracy_reward": 0.951374888420105,
      "rewards/format_reward": 1.0,
      "step": 1203
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.0,
      "completion_length": 378.125,
      "epoch": 0.01660666749424146,
      "grad_norm": 2.4251314351268163,
      "kl": 0.060791015625,
      "learning_rate": 9.993196909866671e-07,
      "loss": 0.0024,
      "reward": 2.0392813682556152,
      "reward_std": 0.018102699890732765,
      "rewards/accuracy_reward": 0.8392812609672546,
      "rewards/format_reward": 1.0,
      "step": 1204
    },
    {
      "all_correct": 0.75,
      "all_wrong": 0.0,
      "completion_length": 386.71875,
      "epoch": 0.016620460407442656,
      "grad_norm": 2.3906094135948113,
      "kl": 0.0625,
      "learning_rate": 9.993185606928174e-07,
      "loss": 0.0025,
      "reward": 2.053281307220459,
      "reward_std": 0.028174404054880142,
      "rewards/accuracy_reward": 0.8532812595367432,
      "rewards/format_reward": 1.0,
      "step": 1205
    },
    {
      "all_correct": 0.75,
      "all_wrong": 0.0,
      "completion_length": 398.1875,
      "epoch": 0.016634253320643853,
      "grad_norm": 2.043617698128752,
      "kl": 0.0634765625,
      "learning_rate": 9.99317429461428e-07,
      "loss": 0.0025,
      "reward": 2.0999374389648438,
      "reward_std": 0.019859399646520615,
      "rewards/accuracy_reward": 0.8999375104904175,
      "rewards/format_reward": 1.0,
      "step": 1206
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.0,
      "completion_length": 385.625,
      "epoch": 0.01664804623384505,
      "grad_norm": 2.915775622168035,
      "kl": 0.060791015625,
      "learning_rate": 9.99316297292502e-07,
      "loss": 0.0024,
      "reward": 2.0141875743865967,
      "reward_std": 0.03311220556497574,
      "rewards/accuracy_reward": 0.8204374313354492,
      "rewards/format_reward": 1.0,
      "step": 1207
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.0,
      "completion_length": 404.15625,
      "epoch": 0.016661839147046248,
      "grad_norm": 2.765239327061956,
      "kl": 0.06494140625,
      "learning_rate": 9.993151641860407e-07,
      "loss": 0.0026,
      "reward": 2.010312557220459,
      "reward_std": 0.023398401215672493,
      "rewards/accuracy_reward": 0.8103125691413879,
      "rewards/format_reward": 1.0,
      "step": 1208
    },
    {
      "all_correct": 0.75,
      "all_wrong": 0.0,
      "completion_length": 390.75,
      "epoch": 0.016675632060247445,
      "grad_norm": 2.174605024045954,
      "kl": 0.0615234375,
      "learning_rate": 9.993140301420463e-07,
      "loss": 0.0025,
      "reward": 2.128781318664551,
      "reward_std": 0.023918021470308304,
      "rewards/accuracy_reward": 0.9350312948226929,
      "rewards/format_reward": 1.0,
      "step": 1209
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.0,
      "completion_length": 403.21875,
      "epoch": 0.016689424973448642,
      "grad_norm": 2.5509507489870007,
      "kl": 0.06103515625,
      "learning_rate": 9.993128951605216e-07,
      "loss": 0.0024,
      "reward": 2.036937713623047,
      "reward_std": 0.016708016395568848,
      "rewards/accuracy_reward": 0.836937427520752,
      "rewards/format_reward": 1.0,
      "step": 1210
    },
    {
      "all_correct": 0.75,
      "all_wrong": 0.0,
      "completion_length": 408.21875,
      "epoch": 0.01670321788664984,
      "grad_norm": 2.014689075082376,
      "kl": 0.052734375,
      "learning_rate": 9.99311759241468e-07,
      "loss": 0.0021,
      "reward": 2.140749931335449,
      "reward_std": 0.01507203932851553,
      "rewards/accuracy_reward": 0.9407499432563782,
      "rewards/format_reward": 1.0,
      "step": 1211
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.0,
      "completion_length": 399.5625,
      "epoch": 0.016717010799851037,
      "grad_norm": 2.4945905041703442,
      "kl": 0.05712890625,
      "learning_rate": 9.993106223848879e-07,
      "loss": 0.0023,
      "reward": 2.0440311431884766,
      "reward_std": 0.029954148456454277,
      "rewards/accuracy_reward": 0.8440312743186951,
      "rewards/format_reward": 1.0,
      "step": 1212
    },
    {
      "all_correct": 0.75,
      "all_wrong": 0.0,
      "completion_length": 402.6875,
      "epoch": 0.016730803713052234,
      "grad_norm": 3.1110711525459727,
      "kl": 0.0654296875,
      "learning_rate": 9.993094845907837e-07,
      "loss": 0.0026,
      "reward": 2.109499931335449,
      "reward_std": 0.01622195914387703,
      "rewards/accuracy_reward": 0.9094999432563782,
      "rewards/format_reward": 1.0,
      "step": 1213
    },
    {
      "all_correct": 0.75,
      "all_wrong": 0.0,
      "completion_length": 397.40625,
      "epoch": 0.01674459662625343,
      "grad_norm": 2.1942249532110263,
      "kl": 0.064453125,
      "learning_rate": 9.993083458591572e-07,
      "loss": 0.0026,
      "reward": 2.1093125343322754,
      "reward_std": 0.04177458956837654,
      "rewards/accuracy_reward": 0.9155624508857727,
      "rewards/format_reward": 1.0,
      "step": 1214
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.0,
      "completion_length": 397.71875,
      "epoch": 0.01675838953945463,
      "grad_norm": 2.645894489171604,
      "kl": 0.062255859375,
      "learning_rate": 9.993072061900104e-07,
      "loss": 0.0025,
      "reward": 2.1039376258850098,
      "reward_std": 0.02338177151978016,
      "rewards/accuracy_reward": 0.9101874828338623,
      "rewards/format_reward": 1.0,
      "step": 1215
    },
    {
      "all_correct": 0.75,
      "all_wrong": 0.0,
      "completion_length": 384.84375,
      "epoch": 0.016772182452655826,
      "grad_norm": 2.111482114360971,
      "kl": 0.061279296875,
      "learning_rate": 9.993060655833459e-07,
      "loss": 0.0024,
      "reward": 2.0365939140319824,
      "reward_std": 0.01635849103331566,
      "rewards/accuracy_reward": 0.836593747138977,
      "rewards/format_reward": 1.0,
      "step": 1216
    },
    {
      "all_correct": 0.25,
      "all_wrong": 0.0,
      "completion_length": 393.59375,
      "epoch": 0.016785975365857023,
      "grad_norm": 2.0913840288475183,
      "kl": 0.06640625,
      "learning_rate": 9.993049240391655e-07,
      "loss": 0.0027,
      "reward": 1.9040000438690186,
      "reward_std": 0.02014370635151863,
      "rewards/accuracy_reward": 0.7039999961853027,
      "rewards/format_reward": 1.0,
      "step": 1217
    },
    {
      "all_correct": 0.75,
      "all_wrong": 0.0,
      "completion_length": 388.8125,
      "epoch": 0.01679976827905822,
      "grad_norm": 4.775042448556552,
      "kl": 0.058837890625,
      "learning_rate": 9.993037815574715e-07,
      "loss": 0.0024,
      "reward": 2.0795626640319824,
      "reward_std": 0.01768878847360611,
      "rewards/accuracy_reward": 0.879562497138977,
      "rewards/format_reward": 1.0,
      "step": 1218
    },
    {
      "all_correct": 0.75,
      "all_wrong": 0.0,
      "completion_length": 407.84375,
      "epoch": 0.016813561192259418,
      "grad_norm": 2.2529042531407866,
      "kl": 0.0673828125,
      "learning_rate": 9.993026381382658e-07,
      "loss": 0.0027,
      "reward": 2.085343837738037,
      "reward_std": 0.020005101338028908,
      "rewards/accuracy_reward": 0.8853437900543213,
      "rewards/format_reward": 1.0,
      "step": 1219
    },
    {
      "all_correct": 0.75,
      "all_wrong": 0.0,
      "completion_length": 391.125,
      "epoch": 0.016827354105460615,
      "grad_norm": 1.5735816650556906,
      "kl": 0.059326171875,
      "learning_rate": 9.993014937815509e-07,
      "loss": 0.0024,
      "reward": 2.1101250648498535,
      "reward_std": 0.009071951732039452,
      "rewards/accuracy_reward": 0.9101250171661377,
      "rewards/format_reward": 1.0,
      "step": 1220
    },
    {
      "all_correct": 0.75,
      "all_wrong": 0.0,
      "completion_length": 391.84375,
      "epoch": 0.016841147018661812,
      "grad_norm": 3.4382738639985724,
      "kl": 0.061767578125,
      "learning_rate": 9.993003484873289e-07,
      "loss": 0.0025,
      "reward": 1.9953436851501465,
      "reward_std": 0.017380014061927795,
      "rewards/accuracy_reward": 0.7953437566757202,
      "rewards/format_reward": 1.0,
      "step": 1221
    },
    {
      "all_correct": 0.75,
      "all_wrong": 0.0,
      "completion_length": 392.4375,
      "epoch": 0.01685493993186301,
      "grad_norm": 2.39306610291031,
      "kl": 0.0703125,
      "learning_rate": 9.992992022556017e-07,
      "loss": 0.0028,
      "reward": 2.045187473297119,
      "reward_std": 0.04146747663617134,
      "rewards/accuracy_reward": 0.863937497138977,
      "rewards/format_reward": 1.0,
      "step": 1222
    },
    {
      "all_correct": 0.25,
      "all_wrong": 0.0,
      "completion_length": 404.65625,
      "epoch": 0.016868732845064207,
      "grad_norm": 2.9482258680987243,
      "kl": 0.06982421875,
      "learning_rate": 9.992980550863715e-07,
      "loss": 0.0028,
      "reward": 1.9826874732971191,
      "reward_std": 0.022615507245063782,
      "rewards/accuracy_reward": 0.7826874852180481,
      "rewards/format_reward": 1.0,
      "step": 1223
    },
    {
      "all_correct": 1.0,
      "all_wrong": 0.0,
      "completion_length": 384.0,
      "epoch": 0.016882525758265404,
      "grad_norm": 1.8206569873960117,
      "kl": 0.0546875,
      "learning_rate": 9.992969069796407e-07,
      "loss": 0.0022,
      "reward": 2.1243438720703125,
      "reward_std": 0.012220284901559353,
      "rewards/accuracy_reward": 0.9243437647819519,
      "rewards/format_reward": 1.0,
      "step": 1224
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.0,
      "completion_length": 403.09375,
      "epoch": 0.0168963186714666,
      "grad_norm": 4.18120246830379,
      "kl": 0.06396484375,
      "learning_rate": 9.992957579354114e-07,
      "loss": 0.0026,
      "reward": 1.9914062023162842,
      "reward_std": 0.02773621864616871,
      "rewards/accuracy_reward": 0.7914062738418579,
      "rewards/format_reward": 1.0,
      "step": 1225
    },
    {
      "all_correct": 0.75,
      "all_wrong": 0.0,
      "completion_length": 401.75,
      "epoch": 0.0169101115846678,
      "grad_norm": 3.0317885713682604,
      "kl": 0.06298828125,
      "learning_rate": 9.992946079536855e-07,
      "loss": 0.0025,
      "reward": 2.1069374084472656,
      "reward_std": 0.04304736107587814,
      "rewards/accuracy_reward": 0.9131874442100525,
      "rewards/format_reward": 1.0,
      "step": 1226
    },
    {
      "all_correct": 0.75,
      "all_wrong": 0.0,
      "completion_length": 398.96875,
      "epoch": 0.016923904497868996,
      "grad_norm": 2.044266394699229,
      "kl": 0.0634765625,
      "learning_rate": 9.992934570344651e-07,
      "loss": 0.0026,
      "reward": 2.1077187061309814,
      "reward_std": 0.0352020189166069,
      "rewards/accuracy_reward": 0.9139687418937683,
      "rewards/format_reward": 1.0,
      "step": 1227
    },
    {
      "all_correct": 0.75,
      "all_wrong": 0.0,
      "completion_length": 396.78125,
      "epoch": 0.016937697411070193,
      "grad_norm": 1.1515796291464742,
      "kl": 0.0556640625,
      "learning_rate": 9.992923051777529e-07,
      "loss": 0.0022,
      "reward": 2.0836875438690186,
      "reward_std": 0.010349041782319546,
      "rewards/accuracy_reward": 0.8836874961853027,
      "rewards/format_reward": 1.0,
      "step": 1228
    },
    {
      "all_correct": 0.75,
      "all_wrong": 0.0,
      "completion_length": 412.28125,
      "epoch": 0.01695149032427139,
      "grad_norm": 3.4006158712178918,
      "kl": 0.06298828125,
      "learning_rate": 9.992911523835507e-07,
      "loss": 0.0025,
      "reward": 2.1156251430511475,
      "reward_std": 0.03228399157524109,
      "rewards/accuracy_reward": 0.921875,
      "rewards/format_reward": 1.0,
      "step": 1229
    },
    {
      "all_correct": 1.0,
      "all_wrong": 0.0,
      "completion_length": 389.0,
      "epoch": 0.016965283237472588,
      "grad_norm": 4.325247590107978,
      "kl": 0.064453125,
      "learning_rate": 9.992899986518605e-07,
      "loss": 0.0026,
      "reward": 2.1386563777923584,
      "reward_std": 0.020227182656526566,
      "rewards/accuracy_reward": 0.938656210899353,
      "rewards/format_reward": 1.0,
      "step": 1230
    },
    {
      "all_correct": 0.75,
      "all_wrong": 0.0,
      "completion_length": 397.28125,
      "epoch": 0.016979076150673785,
      "grad_norm": 3.0243130824383457,
      "kl": 0.06396484375,
      "learning_rate": 9.99288843982685e-07,
      "loss": 0.0026,
      "reward": 2.0880000591278076,
      "reward_std": 0.03455888852477074,
      "rewards/accuracy_reward": 0.8942500352859497,
      "rewards/format_reward": 1.0,
      "step": 1231
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.0,
      "completion_length": 376.09375,
      "epoch": 0.016992869063874982,
      "grad_norm": 2.6438696477737285,
      "kl": 0.06298828125,
      "learning_rate": 9.992876883760258e-07,
      "loss": 0.0025,
      "reward": 2.0804061889648438,
      "reward_std": 0.030565757304430008,
      "rewards/accuracy_reward": 0.8804062604904175,
      "rewards/format_reward": 1.0,
      "step": 1232
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.0,
      "completion_length": 387.90625,
      "epoch": 0.01700666197707618,
      "grad_norm": 3.950742918219173,
      "kl": 0.05712890625,
      "learning_rate": 9.992865318318855e-07,
      "loss": 0.0023,
      "reward": 2.0841875076293945,
      "reward_std": 0.03223949298262596,
      "rewards/accuracy_reward": 0.8904374837875366,
      "rewards/format_reward": 1.0,
      "step": 1233
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.0,
      "completion_length": 403.84375,
      "epoch": 0.017020454890277377,
      "grad_norm": 1.8229161674693881,
      "kl": 0.06982421875,
      "learning_rate": 9.99285374350266e-07,
      "loss": 0.0028,
      "reward": 1.9882187843322754,
      "reward_std": 0.015215826220810413,
      "rewards/accuracy_reward": 0.7882187366485596,
      "rewards/format_reward": 1.0,
      "step": 1234
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.0,
      "completion_length": 377.03125,
      "epoch": 0.017034247803478574,
      "grad_norm": 2.2471449640736925,
      "kl": 0.06640625,
      "learning_rate": 9.992842159311695e-07,
      "loss": 0.0027,
      "reward": 2.0631251335144043,
      "reward_std": 0.030933350324630737,
      "rewards/accuracy_reward": 0.8693749904632568,
      "rewards/format_reward": 1.0,
      "step": 1235
    },
    {
      "all_correct": 1.0,
      "all_wrong": 0.0,
      "completion_length": 383.09375,
      "epoch": 0.01704804071667977,
      "grad_norm": 4.386590279249822,
      "kl": 0.057861328125,
      "learning_rate": 9.992830565745982e-07,
      "loss": 0.0023,
      "reward": 2.1308436393737793,
      "reward_std": 0.061652712523937225,
      "rewards/accuracy_reward": 0.9495937824249268,
      "rewards/format_reward": 1.0,
      "step": 1236
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.0,
      "completion_length": 391.53125,
      "epoch": 0.01706183362988097,
      "grad_norm": 2.391687245043779,
      "kl": 0.06201171875,
      "learning_rate": 9.992818962805543e-07,
      "loss": 0.0025,
      "reward": 2.048156261444092,
      "reward_std": 0.0197436586022377,
      "rewards/accuracy_reward": 0.848156213760376,
      "rewards/format_reward": 1.0,
      "step": 1237
    },
    {
      "all_correct": 0.75,
      "all_wrong": 0.0,
      "completion_length": 394.0,
      "epoch": 0.017075626543082166,
      "grad_norm": 2.3230121239614365,
      "kl": 0.06689453125,
      "learning_rate": 9.9928073504904e-07,
      "loss": 0.0027,
      "reward": 2.084437370300293,
      "reward_std": 0.028027672320604324,
      "rewards/accuracy_reward": 0.8844375014305115,
      "rewards/format_reward": 1.0,
      "step": 1238
    },
    {
      "all_correct": 0.25,
      "all_wrong": 0.0,
      "completion_length": 379.46875,
      "epoch": 0.017089419456283363,
      "grad_norm": 2.3082662250803563,
      "kl": 0.06884765625,
      "learning_rate": 9.992795728800576e-07,
      "loss": 0.0028,
      "reward": 2.079218864440918,
      "reward_std": 0.06573303788900375,
      "rewards/accuracy_reward": 0.8979687690734863,
      "rewards/format_reward": 1.0,
      "step": 1239
    },
    {
      "all_correct": 1.0,
      "all_wrong": 0.0,
      "completion_length": 384.0625,
      "epoch": 0.017103212369484557,
      "grad_norm": 1.9339256322698573,
      "kl": 0.06591796875,
      "learning_rate": 9.992784097736092e-07,
      "loss": 0.0026,
      "reward": 2.145437479019165,
      "reward_std": 0.01848694123327732,
      "rewards/accuracy_reward": 0.9454375505447388,
      "rewards/format_reward": 1.0,
      "step": 1240
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.0,
      "completion_length": 378.875,
      "epoch": 0.017117005282685754,
      "grad_norm": 4.37828493008526,
      "kl": 0.057861328125,
      "learning_rate": 9.992772457296967e-07,
      "loss": 0.0023,
      "reward": 1.9357500076293945,
      "reward_std": 0.04101315140724182,
      "rewards/accuracy_reward": 0.7419999837875366,
      "rewards/format_reward": 1.0,
      "step": 1241
    },
    {
      "all_correct": 0.75,
      "all_wrong": 0.0,
      "completion_length": 386.9375,
      "epoch": 0.01713079819588695,
      "grad_norm": 2.5668631345595863,
      "kl": 0.061279296875,
      "learning_rate": 9.992760807483224e-07,
      "loss": 0.0025,
      "reward": 2.135531425476074,
      "reward_std": 0.0379534550011158,
      "rewards/accuracy_reward": 0.941781222820282,
      "rewards/format_reward": 1.0,
      "step": 1242
    },
    {
      "all_correct": 0.25,
      "all_wrong": 0.0,
      "completion_length": 402.21875,
      "epoch": 0.01714459110908815,
      "grad_norm": 2.736856062421682,
      "kl": 0.0654296875,
      "learning_rate": 9.99274914829489e-07,
      "loss": 0.0026,
      "reward": 2.0041563510894775,
      "reward_std": 0.07743582129478455,
      "rewards/accuracy_reward": 0.8041561841964722,
      "rewards/format_reward": 1.0,
      "step": 1243
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.0,
      "completion_length": 391.1875,
      "epoch": 0.017158384022289346,
      "grad_norm": 2.3318474891083314,
      "kl": 0.06640625,
      "learning_rate": 9.992737479731981e-07,
      "loss": 0.0027,
      "reward": 2.040781259536743,
      "reward_std": 0.029941465705633163,
      "rewards/accuracy_reward": 0.8407812118530273,
      "rewards/format_reward": 1.0,
      "step": 1244
    },
    {
      "all_correct": 0.25,
      "all_wrong": 0.0,
      "completion_length": 410.125,
      "epoch": 0.017172176935490543,
      "grad_norm": 4.220386624098627,
      "kl": 0.0703125,
      "learning_rate": 9.99272580179452e-07,
      "loss": 0.0028,
      "reward": 2.015531301498413,
      "reward_std": 0.03705378621816635,
      "rewards/accuracy_reward": 0.8155312538146973,
      "rewards/format_reward": 1.0,
      "step": 1245
    },
    {
      "all_correct": 0.25,
      "all_wrong": 0.0,
      "completion_length": 411.3125,
      "epoch": 0.01718596984869174,
      "grad_norm": 5.128074107949049,
      "kl": 0.07373046875,
      "learning_rate": 9.99271411448253e-07,
      "loss": 0.003,
      "reward": 2.011625051498413,
      "reward_std": 0.037562109529972076,
      "rewards/accuracy_reward": 0.8116250038146973,
      "rewards/format_reward": 1.0,
      "step": 1246
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.0,
      "completion_length": 405.6875,
      "epoch": 0.017199762761892938,
      "grad_norm": 2.9667012211965473,
      "kl": 0.07080078125,
      "learning_rate": 9.992702417796035e-07,
      "loss": 0.0028,
      "reward": 2.0946874618530273,
      "reward_std": 0.028073575347661972,
      "rewards/accuracy_reward": 0.8946874141693115,
      "rewards/format_reward": 1.0,
      "step": 1247
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.0,
      "completion_length": 409.3125,
      "epoch": 0.017213555675094135,
      "grad_norm": 2.2899867197105386,
      "kl": 0.0654296875,
      "learning_rate": 9.992690711735052e-07,
      "loss": 0.0026,
      "reward": 2.0166563987731934,
      "reward_std": 0.02354704961180687,
      "rewards/accuracy_reward": 0.816656231880188,
      "rewards/format_reward": 1.0,
      "step": 1248
    },
    {
      "all_correct": 1.0,
      "all_wrong": 0.0,
      "completion_length": 394.0625,
      "epoch": 0.017227348588295333,
      "grad_norm": 2.291531281338938,
      "kl": 0.07080078125,
      "learning_rate": 9.992678996299607e-07,
      "loss": 0.0028,
      "reward": 2.161375045776367,
      "reward_std": 0.011862218379974365,
      "rewards/accuracy_reward": 0.9613750576972961,
      "rewards/format_reward": 1.0,
      "step": 1249
    },
    {
      "all_correct": 1.0,
      "all_wrong": 0.0,
      "completion_length": 413.4375,
      "epoch": 0.01724114150149653,
      "grad_norm": 2.1500935424260628,
      "kl": 0.06494140625,
      "learning_rate": 9.992667271489721e-07,
      "loss": 0.0026,
      "reward": 2.1350626945495605,
      "reward_std": 0.016322283074259758,
      "rewards/accuracy_reward": 0.9350624680519104,
      "rewards/format_reward": 1.0,
      "step": 1250
    },
    {
      "all_correct": 0.75,
      "all_wrong": 0.0,
      "completion_length": 406.59375,
      "epoch": 0.017254934414697727,
      "grad_norm": 18.72490411726987,
      "kl": 0.07275390625,
      "learning_rate": 9.992655537305413e-07,
      "loss": 0.0029,
      "reward": 2.1120312213897705,
      "reward_std": 0.037210579961538315,
      "rewards/accuracy_reward": 0.9245312213897705,
      "rewards/format_reward": 1.0,
      "step": 1251
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.0,
      "completion_length": 398.03125,
      "epoch": 0.017268727327898924,
      "grad_norm": 4.6832979827118635,
      "kl": 0.06591796875,
      "learning_rate": 9.99264379374671e-07,
      "loss": 0.0026,
      "reward": 2.071312427520752,
      "reward_std": 0.04111713543534279,
      "rewards/accuracy_reward": 0.8775625228881836,
      "rewards/format_reward": 1.0,
      "step": 1252
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.0,
      "completion_length": 413.21875,
      "epoch": 0.01728252024110012,
      "grad_norm": 2.067493687168406,
      "kl": 0.0693359375,
      "learning_rate": 9.992632040813633e-07,
      "loss": 0.0028,
      "reward": 2.0321874618530273,
      "reward_std": 0.01625334843993187,
      "rewards/accuracy_reward": 0.8321874737739563,
      "rewards/format_reward": 1.0,
      "step": 1253
    },
    {
      "all_correct": 0.75,
      "all_wrong": 0.0,
      "completion_length": 416.1875,
      "epoch": 0.01729631315430132,
      "grad_norm": 2.2615432777418345,
      "kl": 0.06884765625,
      "learning_rate": 9.992620278506202e-07,
      "loss": 0.0028,
      "reward": 2.069031238555908,
      "reward_std": 0.027360178530216217,
      "rewards/accuracy_reward": 0.8690312504768372,
      "rewards/format_reward": 1.0,
      "step": 1254
    },
    {
      "all_correct": 0.75,
      "all_wrong": 0.0,
      "completion_length": 426.0625,
      "epoch": 0.017310106067502516,
      "grad_norm": 2.098946377415223,
      "kl": 0.06396484375,
      "learning_rate": 9.992608506824438e-07,
      "loss": 0.0026,
      "reward": 2.0982813835144043,
      "reward_std": 0.049889855086803436,
      "rewards/accuracy_reward": 0.9107812643051147,
      "rewards/format_reward": 1.0,
      "step": 1255
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.0,
      "completion_length": 396.09375,
      "epoch": 0.017323898980703713,
      "grad_norm": 1.9941983951998314,
      "kl": 0.06884765625,
      "learning_rate": 9.992596725768368e-07,
      "loss": 0.0028,
      "reward": 2.056062698364258,
      "reward_std": 0.03154001384973526,
      "rewards/accuracy_reward": 0.8623125553131104,
      "rewards/format_reward": 1.0,
      "step": 1256
    },
    {
      "all_correct": 0.25,
      "all_wrong": 0.0,
      "completion_length": 413.65625,
      "epoch": 0.01733769189390491,
      "grad_norm": 1.7972413129910345,
      "kl": 0.072265625,
      "learning_rate": 9.992584935338008e-07,
      "loss": 0.0029,
      "reward": 2.067187547683716,
      "reward_std": 0.06780581921339035,
      "rewards/accuracy_reward": 0.8859375715255737,
      "rewards/format_reward": 1.0,
      "step": 1257
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.0,
      "completion_length": 408.0625,
      "epoch": 0.017351484807106108,
      "grad_norm": 2.294427937116036,
      "kl": 0.0693359375,
      "learning_rate": 9.992573135533386e-07,
      "loss": 0.0028,
      "reward": 2.022125244140625,
      "reward_std": 0.026630530133843422,
      "rewards/accuracy_reward": 0.8283750414848328,
      "rewards/format_reward": 1.0,
      "step": 1258
    },
    {
      "all_correct": 0.75,
      "all_wrong": 0.0,
      "completion_length": 404.96875,
      "epoch": 0.017365277720307305,
      "grad_norm": 4.086316547559066,
      "kl": 0.0673828125,
      "learning_rate": 9.99256132635452e-07,
      "loss": 0.0027,
      "reward": 2.0937812328338623,
      "reward_std": 0.02037150040268898,
      "rewards/accuracy_reward": 0.8937812447547913,
      "rewards/format_reward": 1.0,
      "step": 1259
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.0,
      "completion_length": 400.09375,
      "epoch": 0.017379070633508503,
      "grad_norm": 7.153747393999852,
      "kl": 0.0712890625,
      "learning_rate": 9.992549507801434e-07,
      "loss": 0.0029,
      "reward": 1.9926562309265137,
      "reward_std": 0.03664803132414818,
      "rewards/accuracy_reward": 0.7926562428474426,
      "rewards/format_reward": 1.0,
      "step": 1260
    },
    {
      "all_correct": 0.75,
      "all_wrong": 0.0,
      "completion_length": 392.8125,
      "epoch": 0.0173928635467097,
      "grad_norm": 2.5004406991188373,
      "kl": 0.072265625,
      "learning_rate": 9.99253767987415e-07,
      "loss": 0.0029,
      "reward": 2.1089377403259277,
      "reward_std": 0.03793904557824135,
      "rewards/accuracy_reward": 0.915187418460846,
      "rewards/format_reward": 1.0,
      "step": 1261
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.0,
      "completion_length": 394.125,
      "epoch": 0.017406656459910897,
      "grad_norm": 15.38594194501659,
      "kl": 0.05859375,
      "learning_rate": 9.992525842572687e-07,
      "loss": 0.0023,
      "reward": 2.091468572616577,
      "reward_std": 0.045612677931785583,
      "rewards/accuracy_reward": 0.8977187275886536,
      "rewards/format_reward": 1.0,
      "step": 1262
    },
    {
      "all_correct": 0.75,
      "all_wrong": 0.0,
      "completion_length": 391.75,
      "epoch": 0.017420449373112094,
      "grad_norm": 2.394367939462294,
      "kl": 0.0673828125,
      "learning_rate": 9.992513995897074e-07,
      "loss": 0.0027,
      "reward": 2.168375015258789,
      "reward_std": 0.030526449903845787,
      "rewards/accuracy_reward": 0.9746249914169312,
      "rewards/format_reward": 1.0,
      "step": 1263
    },
    {
      "all_correct": 1.0,
      "all_wrong": 0.0,
      "completion_length": 390.59375,
      "epoch": 0.01743424228631329,
      "grad_norm": 7.5266991147920255,
      "kl": 0.06396484375,
      "learning_rate": 9.992502139847328e-07,
      "loss": 0.0026,
      "reward": 2.1299376487731934,
      "reward_std": 0.008113998919725418,
      "rewards/accuracy_reward": 0.9299376010894775,
      "rewards/format_reward": 1.0,
      "step": 1264
    },
    {
      "all_correct": 0.75,
      "all_wrong": 0.0,
      "completion_length": 398.78125,
      "epoch": 0.01744803519951449,
      "grad_norm": 3.688791552019758,
      "kl": 0.0654296875,
      "learning_rate": 9.992490274423473e-07,
      "loss": 0.0026,
      "reward": 2.126187562942505,
      "reward_std": 0.04226308688521385,
      "rewards/accuracy_reward": 0.932437539100647,
      "rewards/format_reward": 1.0,
      "step": 1265
    },
    {
      "all_correct": 1.0,
      "all_wrong": 0.0,
      "completion_length": 402.03125,
      "epoch": 0.017461828112715686,
      "grad_norm": 3.41515412758276,
      "kl": 0.06201171875,
      "learning_rate": 9.99247839962553e-07,
      "loss": 0.0025,
      "reward": 2.087437629699707,
      "reward_std": 0.01846667006611824,
      "rewards/accuracy_reward": 0.8874375820159912,
      "rewards/format_reward": 1.0,
      "step": 1266
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.0,
      "completion_length": 382.75,
      "epoch": 0.017475621025916883,
      "grad_norm": 2.3076574682755697,
      "kl": 0.060302734375,
      "learning_rate": 9.992466515453525e-07,
      "loss": 0.0024,
      "reward": 2.0504374504089355,
      "reward_std": 0.034033939242362976,
      "rewards/accuracy_reward": 0.8566875457763672,
      "rewards/format_reward": 1.0,
      "step": 1267
    },
    {
      "all_correct": 0.75,
      "all_wrong": 0.0,
      "completion_length": 409.34375,
      "epoch": 0.01748941393911808,
      "grad_norm": 2.2446307400242516,
      "kl": 0.0634765625,
      "learning_rate": 9.992454621907476e-07,
      "loss": 0.0025,
      "reward": 2.049093723297119,
      "reward_std": 0.04463730752468109,
      "rewards/accuracy_reward": 0.8490937948226929,
      "rewards/format_reward": 1.0,
      "step": 1268
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.0,
      "completion_length": 392.03125,
      "epoch": 0.017503206852319278,
      "grad_norm": 2.5302112575013838,
      "kl": 0.0673828125,
      "learning_rate": 9.992442718987406e-07,
      "loss": 0.0027,
      "reward": 2.0161561965942383,
      "reward_std": 0.022656098008155823,
      "rewards/accuracy_reward": 0.816156268119812,
      "rewards/format_reward": 1.0,
      "step": 1269
    },
    {
      "all_correct": 1.0,
      "all_wrong": 0.0,
      "completion_length": 395.5,
      "epoch": 0.017516999765520475,
      "grad_norm": 1.9859406652389073,
      "kl": 0.060546875,
      "learning_rate": 9.99243080669334e-07,
      "loss": 0.0024,
      "reward": 2.0910000801086426,
      "reward_std": 0.01576429232954979,
      "rewards/accuracy_reward": 0.8910000324249268,
      "rewards/format_reward": 1.0,
      "step": 1270
    },
    {
      "all_correct": 1.0,
      "all_wrong": 0.0,
      "completion_length": 404.40625,
      "epoch": 0.017530792678721673,
      "grad_norm": 2.3011352442817077,
      "kl": 0.061279296875,
      "learning_rate": 9.992418885025298e-07,
      "loss": 0.0024,
      "reward": 2.1239686012268066,
      "reward_std": 0.015013029798865318,
      "rewards/accuracy_reward": 0.9239687323570251,
      "rewards/format_reward": 1.0,
      "step": 1271
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.0,
      "completion_length": 384.53125,
      "epoch": 0.01754458559192287,
      "grad_norm": 2.4305872580025167,
      "kl": 0.06689453125,
      "learning_rate": 9.992406953983304e-07,
      "loss": 0.0027,
      "reward": 2.020437479019165,
      "reward_std": 0.025568563491106033,
      "rewards/accuracy_reward": 0.820437490940094,
      "rewards/format_reward": 1.0,
      "step": 1272
    },
    {
      "all_correct": 0.25,
      "all_wrong": 0.0,
      "completion_length": 386.3125,
      "epoch": 0.017558378505124067,
      "grad_norm": 7.294911341535325,
      "kl": 0.0693359375,
      "learning_rate": 9.992395013567378e-07,
      "loss": 0.0028,
      "reward": 2.0815625190734863,
      "reward_std": 0.04772401601076126,
      "rewards/accuracy_reward": 0.8940625190734863,
      "rewards/format_reward": 1.0,
      "step": 1273
    },
    {
      "all_correct": 0.75,
      "all_wrong": 0.0,
      "completion_length": 389.15625,
      "epoch": 0.017572171418325264,
      "grad_norm": 2.517702522351415,
      "kl": 0.06494140625,
      "learning_rate": 9.992383063777544e-07,
      "loss": 0.0026,
      "reward": 2.0726563930511475,
      "reward_std": 0.029531696811318398,
      "rewards/accuracy_reward": 0.8789063096046448,
      "rewards/format_reward": 1.0,
      "step": 1274
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.0,
      "completion_length": 381.96875,
      "epoch": 0.01758596433152646,
      "grad_norm": 2.0161750867487,
      "kl": 0.0703125,
      "learning_rate": 9.992371104613823e-07,
      "loss": 0.0028,
      "reward": 2.066718816757202,
      "reward_std": 0.025595100596547127,
      "rewards/accuracy_reward": 0.8729687333106995,
      "rewards/format_reward": 1.0,
      "step": 1275
    },
    {
      "all_correct": 0.75,
      "all_wrong": 0.0,
      "completion_length": 402.375,
      "epoch": 0.01759975724472766,
      "grad_norm": 2.971561624868294,
      "kl": 0.06787109375,
      "learning_rate": 9.99235913607624e-07,
      "loss": 0.0027,
      "reward": 2.0804686546325684,
      "reward_std": 0.03435364365577698,
      "rewards/accuracy_reward": 0.88671875,
      "rewards/format_reward": 1.0,
      "step": 1276
    },
    {
      "all_correct": 0.75,
      "all_wrong": 0.0,
      "completion_length": 383.53125,
      "epoch": 0.017613550157928856,
      "grad_norm": 2.4949421162610768,
      "kl": 0.06396484375,
      "learning_rate": 9.992347158164817e-07,
      "loss": 0.0025,
      "reward": 2.132312297821045,
      "reward_std": 0.020098654553294182,
      "rewards/accuracy_reward": 0.932312548160553,
      "rewards/format_reward": 1.0,
      "step": 1277
    },
    {
      "all_correct": 0.75,
      "all_wrong": 0.0,
      "completion_length": 399.0,
      "epoch": 0.017627343071130053,
      "grad_norm": 12.34088454702304,
      "kl": 0.06640625,
      "learning_rate": 9.992335170879576e-07,
      "loss": 0.0027,
      "reward": 2.1072187423706055,
      "reward_std": 0.021995626389980316,
      "rewards/accuracy_reward": 0.9072187542915344,
      "rewards/format_reward": 1.0,
      "step": 1278
    },
    {
      "all_correct": 1.0,
      "all_wrong": 0.0,
      "completion_length": 393.15625,
      "epoch": 0.01764113598433125,
      "grad_norm": 3.1788434701871644,
      "kl": 0.0703125,
      "learning_rate": 9.992323174220538e-07,
      "loss": 0.0028,
      "reward": 2.1569061279296875,
      "reward_std": 0.025308357551693916,
      "rewards/accuracy_reward": 0.9569063186645508,
      "rewards/format_reward": 1.0,
      "step": 1279
    },
    {
      "all_correct": 0.75,
      "all_wrong": 0.0,
      "completion_length": 387.15625,
      "epoch": 0.017654928897532448,
      "grad_norm": 1.9921322556515215,
      "kl": 0.0693359375,
      "learning_rate": 9.992311168187729e-07,
      "loss": 0.0028,
      "reward": 2.13671875,
      "reward_std": 0.034134991466999054,
      "rewards/accuracy_reward": 0.9429687261581421,
      "rewards/format_reward": 1.0,
      "step": 1280
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.0,
      "completion_length": 387.90625,
      "epoch": 0.017668721810733645,
      "grad_norm": 1.7297271163764978,
      "kl": 0.0693359375,
      "learning_rate": 9.992299152781168e-07,
      "loss": 0.0028,
      "reward": 1.9619061946868896,
      "reward_std": 0.007677676156163216,
      "rewards/accuracy_reward": 0.7619062662124634,
      "rewards/format_reward": 1.0,
      "step": 1281
    },
    {
      "all_correct": 1.0,
      "all_wrong": 0.0,
      "completion_length": 385.875,
      "epoch": 0.017682514723934842,
      "grad_norm": 2.503294213866577,
      "kl": 0.0634765625,
      "learning_rate": 9.992287128000877e-07,
      "loss": 0.0025,
      "reward": 2.106656312942505,
      "reward_std": 0.021199192851781845,
      "rewards/accuracy_reward": 0.9066562652587891,
      "rewards/format_reward": 1.0,
      "step": 1282
    },
    {
      "all_correct": 1.0,
      "all_wrong": 0.0,
      "completion_length": 381.71875,
      "epoch": 0.01769630763713604,
      "grad_norm": 5.174851418183943,
      "kl": 0.06396484375,
      "learning_rate": 9.992275093846883e-07,
      "loss": 0.0025,
      "reward": 2.1569998264312744,
      "reward_std": 0.004118942655622959,
      "rewards/accuracy_reward": 0.9570000171661377,
      "rewards/format_reward": 1.0,
      "step": 1283
    },
    {
      "all_correct": 0.75,
      "all_wrong": 0.0,
      "completion_length": 380.625,
      "epoch": 0.017710100550337237,
      "grad_norm": 3.1384155069768327,
      "kl": 0.0673828125,
      "learning_rate": 9.992263050319204e-07,
      "loss": 0.0027,
      "reward": 2.1176562309265137,
      "reward_std": 0.03260079398751259,
      "rewards/accuracy_reward": 0.9301563501358032,
      "rewards/format_reward": 1.0,
      "step": 1284
    },
    {
      "all_correct": 0.75,
      "all_wrong": 0.0,
      "completion_length": 389.75,
      "epoch": 0.017723893463538434,
      "grad_norm": 6.765583590133097,
      "kl": 0.06396484375,
      "learning_rate": 9.992250997417866e-07,
      "loss": 0.0026,
      "reward": 2.0833749771118164,
      "reward_std": 0.01692761667072773,
      "rewards/accuracy_reward": 0.8833749890327454,
      "rewards/format_reward": 1.0,
      "step": 1285
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.0,
      "completion_length": 404.09375,
      "epoch": 0.01773768637673963,
      "grad_norm": 2.1526087802081744,
      "kl": 0.0654296875,
      "learning_rate": 9.99223893514289e-07,
      "loss": 0.0026,
      "reward": 1.9795937538146973,
      "reward_std": 0.019519304856657982,
      "rewards/accuracy_reward": 0.7795937061309814,
      "rewards/format_reward": 1.0,
      "step": 1286
    },
    {
      "all_correct": 0.75,
      "all_wrong": 0.0,
      "completion_length": 390.5,
      "epoch": 0.01775147928994083,
      "grad_norm": 1.741793970155477,
      "kl": 0.07275390625,
      "learning_rate": 9.9922268634943e-07,
      "loss": 0.0029,
      "reward": 2.1280312538146973,
      "reward_std": 0.024315692484378815,
      "rewards/accuracy_reward": 0.9342812299728394,
      "rewards/format_reward": 1.0,
      "step": 1287
    },
    {
      "all_correct": 0.75,
      "all_wrong": 0.0,
      "completion_length": 381.59375,
      "epoch": 0.017765272203142026,
      "grad_norm": 2.9334320217091086,
      "kl": 0.06787109375,
      "learning_rate": 9.992214782472115e-07,
      "loss": 0.0027,
      "reward": 2.08203125,
      "reward_std": 0.019113700836896896,
      "rewards/accuracy_reward": 0.882031261920929,
      "rewards/format_reward": 1.0,
      "step": 1288
    },
    {
      "all_correct": 0.25,
      "all_wrong": 0.0,
      "completion_length": 397.53125,
      "epoch": 0.017779065116343223,
      "grad_norm": 3.756170197221209,
      "kl": 0.0712890625,
      "learning_rate": 9.992202692076362e-07,
      "loss": 0.0029,
      "reward": 2.029968738555908,
      "reward_std": 0.02976238541305065,
      "rewards/accuracy_reward": 0.8299686908721924,
      "rewards/format_reward": 1.0,
      "step": 1289
    },
    {
      "all_correct": 0.75,
      "all_wrong": 0.0,
      "completion_length": 384.71875,
      "epoch": 0.01779285802954442,
      "grad_norm": 2.3122942448900816,
      "kl": 0.068359375,
      "learning_rate": 9.992190592307063e-07,
      "loss": 0.0027,
      "reward": 2.0606250762939453,
      "reward_std": 0.012134727090597153,
      "rewards/accuracy_reward": 0.8606250286102295,
      "rewards/format_reward": 1.0,
      "step": 1290
    },
    {
      "all_correct": 0.0,
      "all_wrong": 0.0,
      "completion_length": 398.53125,
      "epoch": 0.017806650942745618,
      "grad_norm": 12.674295098780371,
      "kl": 0.0712890625,
      "learning_rate": 9.992178483164238e-07,
      "loss": 0.0029,
      "reward": 2.0131874084472656,
      "reward_std": 0.02567855641245842,
      "rewards/accuracy_reward": 0.8131875991821289,
      "rewards/format_reward": 1.0,
      "step": 1291
    },
    {
      "all_correct": 0.75,
      "all_wrong": 0.0,
      "completion_length": 409.4375,
      "epoch": 0.017820443855946815,
      "grad_norm": 2.4979549954721403,
      "kl": 0.056884765625,
      "learning_rate": 9.992166364647912e-07,
      "loss": 0.0023,
      "reward": 2.1094374656677246,
      "reward_std": 0.022530939429998398,
      "rewards/accuracy_reward": 0.9094374775886536,
      "rewards/format_reward": 1.0,
      "step": 1292
    },
    {
      "all_correct": 0.75,
      "all_wrong": 0.0,
      "completion_length": 400.1875,
      "epoch": 0.017834236769148012,
      "grad_norm": 2.2102403550860052,
      "kl": 0.0830078125,
      "learning_rate": 9.992154236758106e-07,
      "loss": 0.0033,
      "reward": 2.0909063816070557,
      "reward_std": 0.03599603846669197,
      "rewards/accuracy_reward": 0.8971562385559082,
      "rewards/format_reward": 1.0,
      "step": 1293
    },
    {
      "all_correct": 0.75,
      "all_wrong": 0.0,
      "completion_length": 415.53125,
      "epoch": 0.01784802968234921,
      "grad_norm": 9.756326973723638,
      "kl": 0.0625,
      "learning_rate": 9.992142099494844e-07,
      "loss": 0.0025,
      "reward": 2.0747499465942383,
      "reward_std": 0.026643654331564903,
      "rewards/accuracy_reward": 0.874750018119812,
      "rewards/format_reward": 1.0,
      "step": 1294
    },
    {
      "all_correct": 1.0,
      "all_wrong": 0.0,
      "completion_length": 390.9375,
      "epoch": 0.017861822595550407,
      "grad_norm": 1.861029523922298,
      "kl": 0.07373046875,
      "learning_rate": 9.99212995285815e-07,
      "loss": 0.003,
      "reward": 2.1524689197540283,
      "reward_std": 0.013114258646965027,
      "rewards/accuracy_reward": 0.952468752861023,
      "rewards/format_reward": 1.0,
      "step": 1295
    },
    {
      "all_correct": 0.75,
      "all_wrong": 0.0,
      "completion_length": 389.6875,
      "epoch": 0.017875615508751604,
      "grad_norm": 2.3700312688285896,
      "kl": 0.068359375,
      "learning_rate": 9.992117796848047e-07,
      "loss": 0.0027,
      "reward": 2.1459686756134033,
      "reward_std": 0.036623407155275345,
      "rewards/accuracy_reward": 0.952218770980835,
      "rewards/format_reward": 1.0,
      "step": 1296
    },
    {
      "all_correct": 1.0,
      "all_wrong": 0.0,
      "completion_length": 391.375,
      "epoch": 0.0178894084219528,
      "grad_norm": 2.4866139710005686,
      "kl": 0.07373046875,
      "learning_rate": 9.992105631464554e-07,
      "loss": 0.003,
      "reward": 2.1166563034057617,
      "reward_std": 0.015610732138156891,
      "rewards/accuracy_reward": 0.9166562557220459,
      "rewards/format_reward": 1.0,
      "step": 1297
    },
    {
      "all_correct": 0.25,
      "all_wrong": 0.0,
      "completion_length": 393.90625,
      "epoch": 0.017903201335154,
      "grad_norm": 2.402165425162664,
      "kl": 0.0673828125,
      "learning_rate": 9.992093456707699e-07,
      "loss": 0.0027,
      "reward": 1.894124984741211,
      "reward_std": 0.03596854582428932,
      "rewards/accuracy_reward": 0.700374960899353,
      "rewards/format_reward": 1.0,
      "step": 1298
    },
    {
      "all_correct": 0.75,
      "all_wrong": 0.0,
      "completion_length": 388.03125,
      "epoch": 0.017916994248355196,
      "grad_norm": 2.568921693645958,
      "kl": 0.0634765625,
      "learning_rate": 9.992081272577498e-07,
      "loss": 0.0025,
      "reward": 2.083437442779541,
      "reward_std": 0.025990627706050873,
      "rewards/accuracy_reward": 0.8834375143051147,
      "rewards/format_reward": 1.0,
      "step": 1299
    },
    {
      "all_correct": 0.75,
      "all_wrong": 0.0,
      "completion_length": 384.6875,
      "epoch": 0.017930787161556393,
      "grad_norm": 2.7557299826414683,
      "kl": 0.064453125,
      "learning_rate": 9.99206907907398e-07,
      "loss": 0.0026,
      "reward": 2.1140940189361572,
      "reward_std": 0.021752499043941498,
      "rewards/accuracy_reward": 0.9140937328338623,
      "rewards/format_reward": 1.0,
      "step": 1300
    },
    {
      "all_correct": 0.25,
      "all_wrong": 0.0,
      "completion_length": 406.4375,
      "epoch": 0.01794458007475759,
      "grad_norm": 3.385968019076272,
      "kl": 0.0703125,
      "learning_rate": 9.992056876197167e-07,
      "loss": 0.0028,
      "reward": 2.092531204223633,
      "reward_std": 0.05235935375094414,
      "rewards/accuracy_reward": 0.8987812399864197,
      "rewards/format_reward": 1.0,
      "step": 1301
    },
    {
      "all_correct": 1.0,
      "all_wrong": 0.0,
      "completion_length": 400.40625,
      "epoch": 0.017958372987958788,
      "grad_norm": 3.629825429706229,
      "kl": 0.07080078125,
      "learning_rate": 9.992044663947078e-07,
      "loss": 0.0028,
      "reward": 2.1239686012268066,
      "reward_std": 0.020227909088134766,
      "rewards/accuracy_reward": 0.9239687919616699,
      "rewards/format_reward": 1.0,
      "step": 1302
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.0,
      "completion_length": 383.5,
      "epoch": 0.017972165901159985,
      "grad_norm": 2.4798689201534225,
      "kl": 0.064453125,
      "learning_rate": 9.992032442323742e-07,
      "loss": 0.0026,
      "reward": 2.0557188987731934,
      "reward_std": 0.035645052790641785,
      "rewards/accuracy_reward": 0.8619687557220459,
      "rewards/format_reward": 1.0,
      "step": 1303
    },
    {
      "all_correct": 0.75,
      "all_wrong": 0.0,
      "completion_length": 385.34375,
      "epoch": 0.017985958814361182,
      "grad_norm": 2.3368143161431996,
      "kl": 0.06396484375,
      "learning_rate": 9.992020211327177e-07,
      "loss": 0.0026,
      "reward": 2.0753438472747803,
      "reward_std": 0.013957293704152107,
      "rewards/accuracy_reward": 0.8753437995910645,
      "rewards/format_reward": 1.0,
      "step": 1304
    },
    {
      "all_correct": 0.75,
      "all_wrong": 0.0,
      "completion_length": 394.5625,
      "epoch": 0.01799975172756238,
      "grad_norm": 2.295421557869091,
      "kl": 0.076171875,
      "learning_rate": 9.992007970957407e-07,
      "loss": 0.003,
      "reward": 2.040374994277954,
      "reward_std": 0.014951921999454498,
      "rewards/accuracy_reward": 0.8403750658035278,
      "rewards/format_reward": 1.0,
      "step": 1305
    },
    {
      "all_correct": 0.25,
      "all_wrong": 0.0,
      "completion_length": 394.625,
      "epoch": 0.018013544640763577,
      "grad_norm": 2.0980857236969874,
      "kl": 0.0751953125,
      "learning_rate": 9.991995721214457e-07,
      "loss": 0.003,
      "reward": 2.080031394958496,
      "reward_std": 0.049908656626939774,
      "rewards/accuracy_reward": 0.8925312757492065,
      "rewards/format_reward": 1.0,
      "step": 1306
    },
    {
      "all_correct": 0.25,
      "all_wrong": 0.0,
      "completion_length": 389.3125,
      "epoch": 0.018027337553964774,
      "grad_norm": 2.3412007801443706,
      "kl": 0.0791015625,
      "learning_rate": 9.991983462098349e-07,
      "loss": 0.0032,
      "reward": 1.9791876077651978,
      "reward_std": 0.03083454817533493,
      "rewards/accuracy_reward": 0.7854374647140503,
      "rewards/format_reward": 1.0,
      "step": 1307
    },
    {
      "all_correct": 0.75,
      "all_wrong": 0.0,
      "completion_length": 404.8125,
      "epoch": 0.01804113046716597,
      "grad_norm": 1.9545182965726413,
      "kl": 0.061279296875,
      "learning_rate": 9.991971193609103e-07,
      "loss": 0.0024,
      "reward": 2.115281343460083,
      "reward_std": 0.03376578539609909,
      "rewards/accuracy_reward": 0.9215313196182251,
      "rewards/format_reward": 1.0,
      "step": 1308
    },
    {
      "all_correct": 0.75,
      "all_wrong": 0.0,
      "completion_length": 390.21875,
      "epoch": 0.01805492338036717,
      "grad_norm": 4.991290932912927,
      "kl": 0.07275390625,
      "learning_rate": 9.991958915746747e-07,
      "loss": 0.0029,
      "reward": 2.1332499980926514,
      "reward_std": 0.041369445621967316,
      "rewards/accuracy_reward": 0.9394999742507935,
      "rewards/format_reward": 1.0,
      "step": 1309
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.0,
      "completion_length": 391.25,
      "epoch": 0.018068716293568366,
      "grad_norm": 4.0592490101908565,
      "kl": 0.0673828125,
      "learning_rate": 9.9919466285113e-07,
      "loss": 0.0027,
      "reward": 2.0373125076293945,
      "reward_std": 0.03273964300751686,
      "rewards/accuracy_reward": 0.8435624837875366,
      "rewards/format_reward": 1.0,
      "step": 1310
    },
    {
      "all_correct": 0.25,
      "all_wrong": 0.0,
      "completion_length": 380.625,
      "epoch": 0.018082509206769563,
      "grad_norm": 2.655849268189705,
      "kl": 0.06494140625,
      "learning_rate": 9.991934331902789e-07,
      "loss": 0.0026,
      "reward": 1.9785312414169312,
      "reward_std": 0.06187181547284126,
      "rewards/accuracy_reward": 0.7910313010215759,
      "rewards/format_reward": 1.0,
      "step": 1311
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.0,
      "completion_length": 381.40625,
      "epoch": 0.01809630211997076,
      "grad_norm": 9.965632179626775,
      "kl": 0.06591796875,
      "learning_rate": 9.991922025921232e-07,
      "loss": 0.0026,
      "reward": 2.13253116607666,
      "reward_std": 0.02880311757326126,
      "rewards/accuracy_reward": 0.9387812614440918,
      "rewards/format_reward": 1.0,
      "step": 1312
    },
    {
      "all_correct": 0.75,
      "all_wrong": 0.0,
      "completion_length": 391.09375,
      "epoch": 0.018110095033171958,
      "grad_norm": 3.5182005503082574,
      "kl": 0.0673828125,
      "learning_rate": 9.991909710566657e-07,
      "loss": 0.0027,
      "reward": 2.069031238555908,
      "reward_std": 0.027374345809221268,
      "rewards/accuracy_reward": 0.8690313100814819,
      "rewards/format_reward": 1.0,
      "step": 1313
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.0,
      "completion_length": 395.9375,
      "epoch": 0.018123887946373155,
      "grad_norm": 2.5440027565075933,
      "kl": 0.062255859375,
      "learning_rate": 9.991897385839085e-07,
      "loss": 0.0025,
      "reward": 2.0666251182556152,
      "reward_std": 0.02783946879208088,
      "rewards/accuracy_reward": 0.8666249513626099,
      "rewards/format_reward": 1.0,
      "step": 1314
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.0,
      "completion_length": 387.8125,
      "epoch": 0.01813768085957435,
      "grad_norm": 2.8868659514781947,
      "kl": 0.06982421875,
      "learning_rate": 9.99188505173854e-07,
      "loss": 0.0028,
      "reward": 2.0211873054504395,
      "reward_std": 0.018854837864637375,
      "rewards/accuracy_reward": 0.8211874961853027,
      "rewards/format_reward": 1.0,
      "step": 1315
    },
    {
      "all_correct": 1.0,
      "all_wrong": 0.0,
      "completion_length": 392.875,
      "epoch": 0.018151473772775546,
      "grad_norm": 2.1503997331165827,
      "kl": 0.0693359375,
      "learning_rate": 9.991872708265041e-07,
      "loss": 0.0028,
      "reward": 2.095343828201294,
      "reward_std": 0.01398918591439724,
      "rewards/accuracy_reward": 0.8953437805175781,
      "rewards/format_reward": 1.0,
      "step": 1316
    },
    {
      "all_correct": 0.75,
      "all_wrong": 0.0,
      "completion_length": 396.875,
      "epoch": 0.018165266685976744,
      "grad_norm": 2.0452298782375737,
      "kl": 0.06640625,
      "learning_rate": 9.991860355418618e-07,
      "loss": 0.0027,
      "reward": 2.054500102996826,
      "reward_std": 0.02902274951338768,
      "rewards/accuracy_reward": 0.8544999957084656,
      "rewards/format_reward": 1.0,
      "step": 1317
    },
    {
      "all_correct": 1.0,
      "all_wrong": 0.0,
      "completion_length": 387.9375,
      "epoch": 0.01817905959917794,
      "grad_norm": 1.9163852138598063,
      "kl": 0.06396484375,
      "learning_rate": 9.99184799319929e-07,
      "loss": 0.0026,
      "reward": 2.1368439197540283,
      "reward_std": 0.012028755620121956,
      "rewards/accuracy_reward": 0.936843752861023,
      "rewards/format_reward": 1.0,
      "step": 1318
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.0,
      "completion_length": 391.65625,
      "epoch": 0.018192852512379138,
      "grad_norm": 4.133464636525462,
      "kl": 0.06640625,
      "learning_rate": 9.991835621607082e-07,
      "loss": 0.0027,
      "reward": 2.1093125343322754,
      "reward_std": 0.03394792228937149,
      "rewards/accuracy_reward": 0.9155625104904175,
      "rewards/format_reward": 1.0,
      "step": 1319
    },
    {
      "all_correct": 1.0,
      "all_wrong": 0.0,
      "completion_length": 383.09375,
      "epoch": 0.018206645425580335,
      "grad_norm": 1.7634421982488198,
      "kl": 0.06640625,
      "learning_rate": 9.991823240642014e-07,
      "loss": 0.0027,
      "reward": 2.129093885421753,
      "reward_std": 0.00860103964805603,
      "rewards/accuracy_reward": 0.9290937185287476,
      "rewards/format_reward": 1.0,
      "step": 1320
    },
    {
      "all_correct": 0.75,
      "all_wrong": 0.0,
      "completion_length": 408.34375,
      "epoch": 0.018220438338781533,
      "grad_norm": 3.8155978824687433,
      "kl": 0.06396484375,
      "learning_rate": 9.991810850304112e-07,
      "loss": 0.0026,
      "reward": 2.1029064655303955,
      "reward_std": 0.018995974212884903,
      "rewards/accuracy_reward": 0.9029062390327454,
      "rewards/format_reward": 1.0,
      "step": 1321
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.0,
      "completion_length": 399.6875,
      "epoch": 0.01823423125198273,
      "grad_norm": 1.7862235299039864,
      "kl": 0.06494140625,
      "learning_rate": 9.9917984505934e-07,
      "loss": 0.0026,
      "reward": 2.0381875038146973,
      "reward_std": 0.022393614053726196,
      "rewards/accuracy_reward": 0.8444375395774841,
      "rewards/format_reward": 1.0,
      "step": 1322
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.0,
      "completion_length": 379.875,
      "epoch": 0.018248024165183927,
      "grad_norm": 5.701456101301914,
      "kl": 0.0703125,
      "learning_rate": 9.991786041509898e-07,
      "loss": 0.0028,
      "reward": 1.9686561822891235,
      "reward_std": 0.01742098480463028,
      "rewards/accuracy_reward": 0.7686562538146973,
      "rewards/format_reward": 1.0,
      "step": 1323
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.0,
      "completion_length": 396.6875,
      "epoch": 0.018261817078385124,
      "grad_norm": 2.3585676788738743,
      "kl": 0.06494140625,
      "learning_rate": 9.991773623053632e-07,
      "loss": 0.0026,
      "reward": 2.10546875,
      "reward_std": 0.03171078488230705,
      "rewards/accuracy_reward": 0.9117187857627869,
      "rewards/format_reward": 1.0,
      "step": 1324
    },
    {
      "all_correct": 0.25,
      "all_wrong": 0.0,
      "completion_length": 414.59375,
      "epoch": 0.01827560999158632,
      "grad_norm": 2.3819125062119038,
      "kl": 0.07275390625,
      "learning_rate": 9.991761195224626e-07,
      "loss": 0.0029,
      "reward": 2.0290937423706055,
      "reward_std": 0.03605687618255615,
      "rewards/accuracy_reward": 0.8353437781333923,
      "rewards/format_reward": 1.0,
      "step": 1325
    },
    {
      "all_correct": 0.75,
      "all_wrong": 0.0,
      "completion_length": 404.40625,
      "epoch": 0.01828940290478752,
      "grad_norm": 1.9423954827040824,
      "kl": 0.06396484375,
      "learning_rate": 9.9917487580229e-07,
      "loss": 0.0026,
      "reward": 2.1045312881469727,
      "reward_std": 0.015334662050008774,
      "rewards/accuracy_reward": 0.9045312404632568,
      "rewards/format_reward": 1.0,
      "step": 1326
    },
    {
      "all_correct": 0.75,
      "all_wrong": 0.0,
      "completion_length": 419.46875,
      "epoch": 0.018303195817988716,
      "grad_norm": 1.6208200237901333,
      "kl": 0.0703125,
      "learning_rate": 9.99173631144848e-07,
      "loss": 0.0028,
      "reward": 2.075000047683716,
      "reward_std": 0.01023872010409832,
      "rewards/accuracy_reward": 0.8749999403953552,
      "rewards/format_reward": 1.0,
      "step": 1327
    },
    {
      "all_correct": 0.75,
      "all_wrong": 0.0,
      "completion_length": 432.375,
      "epoch": 0.018316988731189913,
      "grad_norm": 4.704455231200037,
      "kl": 0.0703125,
      "learning_rate": 9.99172385550139e-07,
      "loss": 0.0028,
      "reward": 2.101656436920166,
      "reward_std": 0.03354896605014801,
      "rewards/accuracy_reward": 0.9079062342643738,
      "rewards/format_reward": 1.0,
      "step": 1328
    },
    {
      "all_correct": 0.75,
      "all_wrong": 0.0,
      "completion_length": 389.4375,
      "epoch": 0.01833078164439111,
      "grad_norm": 2.1562555900686378,
      "kl": 0.07177734375,
      "learning_rate": 9.991711390181652e-07,
      "loss": 0.0029,
      "reward": 2.119500160217285,
      "reward_std": 0.008087344467639923,
      "rewards/accuracy_reward": 0.9194999933242798,
      "rewards/format_reward": 1.0,
      "step": 1329
    },
    {
      "all_correct": 0.75,
      "all_wrong": 0.0,
      "completion_length": 403.75,
      "epoch": 0.018344574557592308,
      "grad_norm": 2.360134470971612,
      "kl": 0.07275390625,
      "learning_rate": 9.991698915489286e-07,
      "loss": 0.0029,
      "reward": 2.034749984741211,
      "reward_std": 0.01637093722820282,
      "rewards/accuracy_reward": 0.8347499966621399,
      "rewards/format_reward": 1.0,
      "step": 1330
    },
    {
      "all_correct": 0.0,
      "all_wrong": 0.0,
      "completion_length": 406.65625,
      "epoch": 0.018358367470793505,
      "grad_norm": 4.985515018094128,
      "kl": 0.07470703125,
      "learning_rate": 9.991686431424322e-07,
      "loss": 0.003,
      "reward": 1.9120937585830688,
      "reward_std": 0.051356006413698196,
      "rewards/accuracy_reward": 0.7120937705039978,
      "rewards/format_reward": 1.0,
      "step": 1331
    },
    {
      "all_correct": 0.25,
      "all_wrong": 0.0,
      "completion_length": 395.09375,
      "epoch": 0.018372160383994703,
      "grad_norm": 2.2119426010538534,
      "kl": 0.078125,
      "learning_rate": 9.99167393798678e-07,
      "loss": 0.0031,
      "reward": 2.093062400817871,
      "reward_std": 0.05680582672357559,
      "rewards/accuracy_reward": 0.911812424659729,
      "rewards/format_reward": 1.0,
      "step": 1332
    },
    {
      "all_correct": 1.0,
      "all_wrong": 0.0,
      "completion_length": 405.9375,
      "epoch": 0.0183859532971959,
      "grad_norm": 2.287375733459683,
      "kl": 0.0791015625,
      "learning_rate": 9.991661435176684e-07,
      "loss": 0.0032,
      "reward": 2.141812324523926,
      "reward_std": 0.012004390358924866,
      "rewards/accuracy_reward": 0.9418124556541443,
      "rewards/format_reward": 1.0,
      "step": 1333
    },
    {
      "all_correct": 0.75,
      "all_wrong": 0.0,
      "completion_length": 416.78125,
      "epoch": 0.018399746210397097,
      "grad_norm": 2.7929312945513716,
      "kl": 0.0673828125,
      "learning_rate": 9.991648922994056e-07,
      "loss": 0.0027,
      "reward": 2.064000129699707,
      "reward_std": 0.0319165475666523,
      "rewards/accuracy_reward": 0.8639999628067017,
      "rewards/format_reward": 1.0,
      "step": 1334
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.0,
      "completion_length": 409.5625,
      "epoch": 0.018413539123598294,
      "grad_norm": 4.101596251767827,
      "kl": 0.07861328125,
      "learning_rate": 9.991636401438922e-07,
      "loss": 0.0032,
      "reward": 2.099343776702881,
      "reward_std": 0.028483789414167404,
      "rewards/accuracy_reward": 0.905593752861023,
      "rewards/format_reward": 1.0,
      "step": 1335
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.0,
      "completion_length": 407.625,
      "epoch": 0.01842733203679949,
      "grad_norm": 3.101866598957218,
      "kl": 0.0703125,
      "learning_rate": 9.991623870511302e-07,
      "loss": 0.0028,
      "reward": 2.05078125,
      "reward_std": 0.01934993639588356,
      "rewards/accuracy_reward": 0.8507813215255737,
      "rewards/format_reward": 1.0,
      "step": 1336
    },
    {
      "all_correct": 1.0,
      "all_wrong": 0.0,
      "completion_length": 413.875,
      "epoch": 0.01844112495000069,
      "grad_norm": 2.2444862501305423,
      "kl": 0.06396484375,
      "learning_rate": 9.991611330211225e-07,
      "loss": 0.0026,
      "reward": 2.1689376831054688,
      "reward_std": 0.021803725510835648,
      "rewards/accuracy_reward": 0.9689374566078186,
      "rewards/format_reward": 1.0,
      "step": 1337
    },
    {
      "all_correct": 0.75,
      "all_wrong": 0.0,
      "completion_length": 393.4375,
      "epoch": 0.018454917863201886,
      "grad_norm": 2.272289361291398,
      "kl": 0.07373046875,
      "learning_rate": 9.991598780538711e-07,
      "loss": 0.0029,
      "reward": 2.101375102996826,
      "reward_std": 0.00968160480260849,
      "rewards/accuracy_reward": 0.9013750553131104,
      "rewards/format_reward": 1.0,
      "step": 1338
    },
    {
      "all_correct": 1.0,
      "all_wrong": 0.0,
      "completion_length": 421.6875,
      "epoch": 0.018468710776403083,
      "grad_norm": 3.22700265443963,
      "kl": 0.07666015625,
      "learning_rate": 9.991586221493782e-07,
      "loss": 0.0031,
      "reward": 2.1269688606262207,
      "reward_std": 0.016268674284219742,
      "rewards/accuracy_reward": 0.9269687533378601,
      "rewards/format_reward": 1.0,
      "step": 1339
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.0,
      "completion_length": 421.09375,
      "epoch": 0.01848250368960428,
      "grad_norm": 2.8701778210012976,
      "kl": 0.0712890625,
      "learning_rate": 9.991573653076465e-07,
      "loss": 0.0029,
      "reward": 2.0544373989105225,
      "reward_std": 0.0317423939704895,
      "rewards/accuracy_reward": 0.8606875538825989,
      "rewards/format_reward": 1.0,
      "step": 1340
    },
    {
      "all_correct": 0.75,
      "all_wrong": 0.0,
      "completion_length": 413.28125,
      "epoch": 0.018496296602805478,
      "grad_norm": 1.4197183012210006,
      "kl": 0.06689453125,
      "learning_rate": 9.991561075286782e-07,
      "loss": 0.0027,
      "reward": 2.1239686012268066,
      "reward_std": 0.007951047271490097,
      "rewards/accuracy_reward": 0.9239687323570251,
      "rewards/format_reward": 1.0,
      "step": 1341
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.0,
      "completion_length": 409.3125,
      "epoch": 0.018510089516006675,
      "grad_norm": 2.0709104617009144,
      "kl": 0.07958984375,
      "learning_rate": 9.991548488124755e-07,
      "loss": 0.0032,
      "reward": 2.149718761444092,
      "reward_std": 0.04433050751686096,
      "rewards/accuracy_reward": 0.9622187614440918,
      "rewards/format_reward": 1.0,
      "step": 1342
    },
    {
      "all_correct": 1.0,
      "all_wrong": 0.0,
      "completion_length": 407.875,
      "epoch": 0.018523882429207873,
      "grad_norm": 2.8063581849325834,
      "kl": 0.07421875,
      "learning_rate": 9.99153589159041e-07,
      "loss": 0.003,
      "reward": 2.1442501544952393,
      "reward_std": 0.008503405377268791,
      "rewards/accuracy_reward": 0.9442500472068787,
      "rewards/format_reward": 1.0,
      "step": 1343
    },
    {
      "all_correct": 0.75,
      "all_wrong": 0.0,
      "completion_length": 396.90625,
      "epoch": 0.01853767534240907,
      "grad_norm": 5.452082990163365,
      "kl": 0.07861328125,
      "learning_rate": 9.99152328568377e-07,
      "loss": 0.0031,
      "reward": 2.1150002479553223,
      "reward_std": 0.030775217339396477,
      "rewards/accuracy_reward": 0.92125004529953,
      "rewards/format_reward": 1.0,
      "step": 1344
    },
    {
      "all_correct": 0.75,
      "all_wrong": 0.0,
      "completion_length": 415.59375,
      "epoch": 0.018551468255610267,
      "grad_norm": 5.582527642050675,
      "kl": 0.078125,
      "learning_rate": 9.991510670404862e-07,
      "loss": 0.0031,
      "reward": 2.087531089782715,
      "reward_std": 0.021545231342315674,
      "rewards/accuracy_reward": 0.8875312805175781,
      "rewards/format_reward": 1.0,
      "step": 1345
    },
    {
      "all_correct": 0.75,
      "all_wrong": 0.0,
      "completion_length": 426.125,
      "epoch": 0.018565261168811464,
      "grad_norm": 3.134959983375769,
      "kl": 0.0673828125,
      "learning_rate": 9.991498045753701e-07,
      "loss": 0.0027,
      "reward": 2.0568125247955322,
      "reward_std": 0.02381068468093872,
      "rewards/accuracy_reward": 0.8568124771118164,
      "rewards/format_reward": 1.0,
      "step": 1346
    },
    {
      "all_correct": 0.75,
      "all_wrong": 0.0,
      "completion_length": 412.4375,
      "epoch": 0.01857905408201266,
      "grad_norm": 5.408913193256637,
      "kl": 0.07275390625,
      "learning_rate": 9.99148541173032e-07,
      "loss": 0.0029,
      "reward": 2.082937479019165,
      "reward_std": 0.02531331591308117,
      "rewards/accuracy_reward": 0.882937490940094,
      "rewards/format_reward": 1.0,
      "step": 1347
    },
    {
      "all_correct": 0.75,
      "all_wrong": 0.0,
      "completion_length": 413.4375,
      "epoch": 0.01859284699521386,
      "grad_norm": 2.8505764854003974,
      "kl": 0.06982421875,
      "learning_rate": 9.991472768334737e-07,
      "loss": 0.0028,
      "reward": 2.1494998931884766,
      "reward_std": 0.028745274990797043,
      "rewards/accuracy_reward": 0.9557499885559082,
      "rewards/format_reward": 1.0,
      "step": 1348
    },
    {
      "all_correct": 0.75,
      "all_wrong": 0.0,
      "completion_length": 407.15625,
      "epoch": 0.018606639908415056,
      "grad_norm": 2.376338226753753,
      "kl": 0.0751953125,
      "learning_rate": 9.991460115566978e-07,
      "loss": 0.003,
      "reward": 2.035562515258789,
      "reward_std": 0.023025721311569214,
      "rewards/accuracy_reward": 0.835562527179718,
      "rewards/format_reward": 1.0,
      "step": 1349
    },
    {
      "all_correct": 0.75,
      "all_wrong": 0.0,
      "completion_length": 415.28125,
      "epoch": 0.018620432821616253,
      "grad_norm": 3.263741667221038,
      "kl": 0.07763671875,
      "learning_rate": 9.991447453427067e-07,
      "loss": 0.0031,
      "reward": 2.0255937576293945,
      "reward_std": 0.017825044691562653,
      "rewards/accuracy_reward": 0.8255937695503235,
      "rewards/format_reward": 1.0,
      "step": 1350
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.0,
      "completion_length": 414.9375,
      "epoch": 0.01863422573481745,
      "grad_norm": 1.983969538051493,
      "kl": 0.0751953125,
      "learning_rate": 9.991434781915026e-07,
      "loss": 0.003,
      "reward": 2.09012508392334,
      "reward_std": 0.01619267836213112,
      "rewards/accuracy_reward": 0.8901249766349792,
      "rewards/format_reward": 1.0,
      "step": 1351
    },
    {
      "all_correct": 1.0,
      "all_wrong": 0.0,
      "completion_length": 409.28125,
      "epoch": 0.018648018648018648,
      "grad_norm": 2.1924901131100327,
      "kl": 0.0595703125,
      "learning_rate": 9.99142210103088e-07,
      "loss": 0.0024,
      "reward": 2.1401562690734863,
      "reward_std": 0.013448791578412056,
      "rewards/accuracy_reward": 0.9401562213897705,
      "rewards/format_reward": 1.0,
      "step": 1352
    },
    {
      "all_correct": 1.0,
      "all_wrong": 0.0,
      "completion_length": 407.65625,
      "epoch": 0.018661811561219845,
      "grad_norm": 1.9370415001797936,
      "kl": 0.0693359375,
      "learning_rate": 9.991409410774653e-07,
      "loss": 0.0028,
      "reward": 2.129624843597412,
      "reward_std": 0.011086581274867058,
      "rewards/accuracy_reward": 0.9296250343322754,
      "rewards/format_reward": 1.0,
      "step": 1353
    },
    {
      "all_correct": 0.75,
      "all_wrong": 0.0,
      "completion_length": 419.03125,
      "epoch": 0.018675604474421043,
      "grad_norm": 1.8252733188785442,
      "kl": 0.07421875,
      "learning_rate": 9.99139671114637e-07,
      "loss": 0.003,
      "reward": 2.087343692779541,
      "reward_std": 0.025723453611135483,
      "rewards/accuracy_reward": 0.8935937285423279,
      "rewards/format_reward": 1.0,
      "step": 1354
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.0,
      "completion_length": 401.8125,
      "epoch": 0.01868939738762224,
      "grad_norm": 2.235551051279889,
      "kl": 0.06982421875,
      "learning_rate": 9.99138400214605e-07,
      "loss": 0.0028,
      "reward": 1.9066250324249268,
      "reward_std": 0.047897472977638245,
      "rewards/accuracy_reward": 0.719124972820282,
      "rewards/format_reward": 1.0,
      "step": 1355
    },
    {
      "all_correct": 0.75,
      "all_wrong": 0.0,
      "completion_length": 417.9375,
      "epoch": 0.018703190300823437,
      "grad_norm": 2.0475582245280046,
      "kl": 0.068359375,
      "learning_rate": 9.991371283773721e-07,
      "loss": 0.0027,
      "reward": 2.0213751792907715,
      "reward_std": 0.030648333951830864,
      "rewards/accuracy_reward": 0.8276249766349792,
      "rewards/format_reward": 1.0,
      "step": 1356
    },
    {
      "all_correct": 0.75,
      "all_wrong": 0.0,
      "completion_length": 411.8125,
      "epoch": 0.018716983214024634,
      "grad_norm": 3.0947143794301732,
      "kl": 0.07763671875,
      "learning_rate": 9.991358556029407e-07,
      "loss": 0.0031,
      "reward": 2.089531421661377,
      "reward_std": 0.021671392023563385,
      "rewards/accuracy_reward": 0.8895312547683716,
      "rewards/format_reward": 1.0,
      "step": 1357
    },
    {
      "all_correct": 0.75,
      "all_wrong": 0.0,
      "completion_length": 402.625,
      "epoch": 0.01873077612722583,
      "grad_norm": 3.345173621844925,
      "kl": 0.07177734375,
      "learning_rate": 9.991345818913132e-07,
      "loss": 0.0029,
      "reward": 2.121281147003174,
      "reward_std": 0.03856559470295906,
      "rewards/accuracy_reward": 0.9275312423706055,
      "rewards/format_reward": 1.0,
      "step": 1358
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.0,
      "completion_length": 428.0625,
      "epoch": 0.01874456904042703,
      "grad_norm": 2.419742359947703,
      "kl": 0.06494140625,
      "learning_rate": 9.991333072424917e-07,
      "loss": 0.0026,
      "reward": 2.026718854904175,
      "reward_std": 0.02642715349793434,
      "rewards/accuracy_reward": 0.8329687714576721,
      "rewards/format_reward": 1.0,
      "step": 1359
    },
    {
      "all_correct": 0.75,
      "all_wrong": 0.0,
      "completion_length": 406.5,
      "epoch": 0.018758361953628226,
      "grad_norm": 3.4849116417821504,
      "kl": 0.06689453125,
      "learning_rate": 9.991320316564788e-07,
      "loss": 0.0027,
      "reward": 2.0764377117156982,
      "reward_std": 0.026358962059020996,
      "rewards/accuracy_reward": 0.8764375448226929,
      "rewards/format_reward": 1.0,
      "step": 1360
    },
    {
      "all_correct": 0.75,
      "all_wrong": 0.0,
      "completion_length": 399.15625,
      "epoch": 0.018772154866829423,
      "grad_norm": 2.423372390081931,
      "kl": 0.0693359375,
      "learning_rate": 9.99130755133277e-07,
      "loss": 0.0028,
      "reward": 2.048156261444092,
      "reward_std": 0.023086393252015114,
      "rewards/accuracy_reward": 0.848156213760376,
      "rewards/format_reward": 1.0,
      "step": 1361
    },
    {
      "all_correct": 1.0,
      "all_wrong": 0.0,
      "completion_length": 398.6875,
      "epoch": 0.01878594778003062,
      "grad_norm": 5.165924481832018,
      "kl": 0.06884765625,
      "learning_rate": 9.991294776728885e-07,
      "loss": 0.0028,
      "reward": 2.1153438091278076,
      "reward_std": 0.01083328202366829,
      "rewards/accuracy_reward": 0.9153437614440918,
      "rewards/format_reward": 1.0,
      "step": 1362
    },
    {
      "all_correct": 1.0,
      "all_wrong": 0.0,
      "completion_length": 393.75,
      "epoch": 0.018799740693231818,
      "grad_norm": 2.5854302494235477,
      "kl": 0.080078125,
      "learning_rate": 9.991281992753158e-07,
      "loss": 0.0032,
      "reward": 2.1729061603546143,
      "reward_std": 0.015167968347668648,
      "rewards/accuracy_reward": 0.972906231880188,
      "rewards/format_reward": 1.0,
      "step": 1363
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.0,
      "completion_length": 390.46875,
      "epoch": 0.018813533606433015,
      "grad_norm": 2.965826203940543,
      "kl": 0.0673828125,
      "learning_rate": 9.991269199405613e-07,
      "loss": 0.0027,
      "reward": 2.1620311737060547,
      "reward_std": 0.04841157793998718,
      "rewards/accuracy_reward": 0.9745312929153442,
      "rewards/format_reward": 1.0,
      "step": 1364
    },
    {
      "all_correct": 0.0,
      "all_wrong": 0.0,
      "completion_length": 396.125,
      "epoch": 0.018827326519634213,
      "grad_norm": 2.9106077063294644,
      "kl": 0.07373046875,
      "learning_rate": 9.99125639668627e-07,
      "loss": 0.003,
      "reward": 1.9558436870574951,
      "reward_std": 0.020240500569343567,
      "rewards/accuracy_reward": 0.7558437585830688,
      "rewards/format_reward": 1.0,
      "step": 1365
    },
    {
      "all_correct": 1.0,
      "all_wrong": 0.0,
      "completion_length": 409.21875,
      "epoch": 0.01884111943283541,
      "grad_norm": 1.9745329265337146,
      "kl": 0.07275390625,
      "learning_rate": 9.991243584595162e-07,
      "loss": 0.0029,
      "reward": 2.157531261444092,
      "reward_std": 0.016875505447387695,
      "rewards/accuracy_reward": 0.957531213760376,
      "rewards/format_reward": 1.0,
      "step": 1366
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.0,
      "completion_length": 393.46875,
      "epoch": 0.018854912346036607,
      "grad_norm": 2.434004969758939,
      "kl": 0.06787109375,
      "learning_rate": 9.991230763132306e-07,
      "loss": 0.0027,
      "reward": 1.9667187929153442,
      "reward_std": 0.013308387249708176,
      "rewards/accuracy_reward": 0.7667186856269836,
      "rewards/format_reward": 1.0,
      "step": 1367
    },
    {
      "all_correct": 0.75,
      "all_wrong": 0.0,
      "completion_length": 408.625,
      "epoch": 0.018868705259237804,
      "grad_norm": 2.5329570641590244,
      "kl": 0.06298828125,
      "learning_rate": 9.991217932297728e-07,
      "loss": 0.0025,
      "reward": 2.0630311965942383,
      "reward_std": 0.01589939184486866,
      "rewards/accuracy_reward": 0.863031268119812,
      "rewards/format_reward": 1.0,
      "step": 1368
    },
    {
      "all_correct": 0.75,
      "all_wrong": 0.0,
      "completion_length": 409.21875,
      "epoch": 0.018882498172439,
      "grad_norm": 2.670051852264782,
      "kl": 0.06591796875,
      "learning_rate": 9.991205092091452e-07,
      "loss": 0.0026,
      "reward": 2.0581564903259277,
      "reward_std": 0.019017966464161873,
      "rewards/accuracy_reward": 0.8581562638282776,
      "rewards/format_reward": 1.0,
      "step": 1369
    },
    {
      "all_correct": 0.75,
      "all_wrong": 0.0,
      "completion_length": 405.15625,
      "epoch": 0.0188962910856402,
      "grad_norm": 2.52800273343408,
      "kl": 0.06689453125,
      "learning_rate": 9.991192242513502e-07,
      "loss": 0.0027,
      "reward": 2.0528125762939453,
      "reward_std": 0.014065331779420376,
      "rewards/accuracy_reward": 0.8528125286102295,
      "rewards/format_reward": 1.0,
      "step": 1370
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.0,
      "completion_length": 405.9375,
      "epoch": 0.018910083998841396,
      "grad_norm": 2.59207789965161,
      "kl": 0.072265625,
      "learning_rate": 9.991179383563901e-07,
      "loss": 0.0029,
      "reward": 2.0565781593322754,
      "reward_std": 0.016641080379486084,
      "rewards/accuracy_reward": 0.8565781116485596,
      "rewards/format_reward": 1.0,
      "step": 1371
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.0,
      "completion_length": 394.9375,
      "epoch": 0.018923876912042593,
      "grad_norm": 4.633462528320491,
      "kl": 0.06640625,
      "learning_rate": 9.991166515242677e-07,
      "loss": 0.0027,
      "reward": 2.0631561279296875,
      "reward_std": 0.032800182700157166,
      "rewards/accuracy_reward": 0.875656247138977,
      "rewards/format_reward": 1.0,
      "step": 1372
    },
    {
      "all_correct": 1.0,
      "all_wrong": 0.0,
      "completion_length": 403.4375,
      "epoch": 0.01893766982524379,
      "grad_norm": 2.8645025271161555,
      "kl": 0.06640625,
      "learning_rate": 9.991153637549848e-07,
      "loss": 0.0027,
      "reward": 2.172656297683716,
      "reward_std": 0.030428048223257065,
      "rewards/accuracy_reward": 0.9789062142372131,
      "rewards/format_reward": 1.0,
      "step": 1373
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.0,
      "completion_length": 381.78125,
      "epoch": 0.018951462738444988,
      "grad_norm": 3.001483966449212,
      "kl": 0.07177734375,
      "learning_rate": 9.991140750485445e-07,
      "loss": 0.0029,
      "reward": 2.0498437881469727,
      "reward_std": 0.018360059708356857,
      "rewards/accuracy_reward": 0.8498437404632568,
      "rewards/format_reward": 1.0,
      "step": 1374
    },
    {
      "all_correct": 0.75,
      "all_wrong": 0.0,
      "completion_length": 396.96875,
      "epoch": 0.018965255651646185,
      "grad_norm": 6.86166035745758,
      "kl": 0.068359375,
      "learning_rate": 9.991127854049489e-07,
      "loss": 0.0027,
      "reward": 2.0992345809936523,
      "reward_std": 0.021194960922002792,
      "rewards/accuracy_reward": 0.899234414100647,
      "rewards/format_reward": 1.0,
      "step": 1375
    },
    {
      "all_correct": 0.75,
      "all_wrong": 0.0,
      "completion_length": 402.28125,
      "epoch": 0.018979048564847383,
      "grad_norm": 4.352203720350787,
      "kl": 0.0712890625,
      "learning_rate": 9.991114948242002e-07,
      "loss": 0.0029,
      "reward": 2.065281391143799,
      "reward_std": 0.0284421369433403,
      "rewards/accuracy_reward": 0.8652812242507935,
      "rewards/format_reward": 1.0,
      "step": 1376
    },
    {
      "all_correct": 0.75,
      "all_wrong": 0.0,
      "completion_length": 415.875,
      "epoch": 0.01899284147804858,
      "grad_norm": 21.245959448261683,
      "kl": 0.06884765625,
      "learning_rate": 9.99110203306301e-07,
      "loss": 0.0027,
      "reward": 2.0699687004089355,
      "reward_std": 0.016931701451539993,
      "rewards/accuracy_reward": 0.8699687719345093,
      "rewards/format_reward": 1.0,
      "step": 1377
    },
    {
      "all_correct": 0.75,
      "all_wrong": 0.0,
      "completion_length": 413.4375,
      "epoch": 0.019006634391249777,
      "grad_norm": 2.9893530560991017,
      "kl": 0.06787109375,
      "learning_rate": 9.99108910851254e-07,
      "loss": 0.0027,
      "reward": 2.089968681335449,
      "reward_std": 0.03087923862040043,
      "rewards/accuracy_reward": 0.8962187170982361,
      "rewards/format_reward": 1.0,
      "step": 1378
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.0,
      "completion_length": 416.75,
      "epoch": 0.019020427304450974,
      "grad_norm": 2.2613369735417144,
      "kl": 0.06787109375,
      "learning_rate": 9.991076174590612e-07,
      "loss": 0.0027,
      "reward": 2.0407814979553223,
      "reward_std": 0.023062093183398247,
      "rewards/accuracy_reward": 0.8407812118530273,
      "rewards/format_reward": 1.0,
      "step": 1379
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.0,
      "completion_length": 413.9375,
      "epoch": 0.01903422021765217,
      "grad_norm": 6.256814808683799,
      "kl": 0.06787109375,
      "learning_rate": 9.991063231297255e-07,
      "loss": 0.0027,
      "reward": 2.0450000762939453,
      "reward_std": 0.019958723336458206,
      "rewards/accuracy_reward": 0.8449999690055847,
      "rewards/format_reward": 1.0,
      "step": 1380
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.0,
      "completion_length": 385.1875,
      "epoch": 0.01904801313085337,
      "grad_norm": 3.0508079933981547,
      "kl": 0.068359375,
      "learning_rate": 9.991050278632488e-07,
      "loss": 0.0027,
      "reward": 2.047468662261963,
      "reward_std": 0.04885120317339897,
      "rewards/accuracy_reward": 0.8599687814712524,
      "rewards/format_reward": 1.0,
      "step": 1381
    },
    {
      "all_correct": 1.0,
      "all_wrong": 0.0,
      "completion_length": 405.375,
      "epoch": 0.019061806044054566,
      "grad_norm": 2.560188593035059,
      "kl": 0.06396484375,
      "learning_rate": 9.991037316596339e-07,
      "loss": 0.0025,
      "reward": 2.1327810287475586,
      "reward_std": 0.030704261735081673,
      "rewards/accuracy_reward": 0.9327812194824219,
      "rewards/format_reward": 1.0,
      "step": 1382
    },
    {
      "all_correct": 0.75,
      "all_wrong": 0.0,
      "completion_length": 404.1875,
      "epoch": 0.019075598957255763,
      "grad_norm": 2.4127431924900837,
      "kl": 0.076171875,
      "learning_rate": 9.991024345188829e-07,
      "loss": 0.0031,
      "reward": 2.0745625495910645,
      "reward_std": 0.02189439721405506,
      "rewards/accuracy_reward": 0.8745625019073486,
      "rewards/format_reward": 1.0,
      "step": 1383
    },
    {
      "all_correct": 1.0,
      "all_wrong": 0.0,
      "completion_length": 411.15625,
      "epoch": 0.01908939187045696,
      "grad_norm": 15.322939180686419,
      "kl": 0.06689453125,
      "learning_rate": 9.991011364409986e-07,
      "loss": 0.0027,
      "reward": 2.118593692779541,
      "reward_std": 0.006792397703975439,
      "rewards/accuracy_reward": 0.9185937643051147,
      "rewards/format_reward": 1.0,
      "step": 1384
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.0,
      "completion_length": 407.0,
      "epoch": 0.019103184783658158,
      "grad_norm": 2.3089285319316883,
      "kl": 0.07421875,
      "learning_rate": 9.990998374259833e-07,
      "loss": 0.003,
      "reward": 2.094531297683716,
      "reward_std": 0.015446671284735203,
      "rewards/accuracy_reward": 0.89453125,
      "rewards/format_reward": 1.0,
      "step": 1385
    },
    {
      "all_correct": 1.0,
      "all_wrong": 0.0,
      "completion_length": 420.8125,
      "epoch": 0.019116977696859355,
      "grad_norm": 2.24937093486185,
      "kl": 0.0615234375,
      "learning_rate": 9.990985374738395e-07,
      "loss": 0.0025,
      "reward": 2.1020936965942383,
      "reward_std": 0.01481853611767292,
      "rewards/accuracy_reward": 0.902093768119812,
      "rewards/format_reward": 1.0,
      "step": 1386
    },
    {
      "all_correct": 0.25,
      "all_wrong": 0.0,
      "completion_length": 401.5,
      "epoch": 0.019130770610060552,
      "grad_norm": 4.4409468423841,
      "kl": 0.0625,
      "learning_rate": 9.990972365845694e-07,
      "loss": 0.0025,
      "reward": 2.0081875324249268,
      "reward_std": 0.018969684839248657,
      "rewards/accuracy_reward": 0.8081874251365662,
      "rewards/format_reward": 1.0,
      "step": 1387
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.0,
      "completion_length": 406.875,
      "epoch": 0.01914456352326175,
      "grad_norm": 2.8495613782729103,
      "kl": 0.0654296875,
      "learning_rate": 9.990959347581756e-07,
      "loss": 0.0026,
      "reward": 2.044562339782715,
      "reward_std": 0.015596939250826836,
      "rewards/accuracy_reward": 0.8445624709129333,
      "rewards/format_reward": 1.0,
      "step": 1388
    },
    {
      "all_correct": 0.75,
      "all_wrong": 0.0,
      "completion_length": 393.21875,
      "epoch": 0.019158356436462947,
      "grad_norm": 2.4038115640660442,
      "kl": 0.061767578125,
      "learning_rate": 9.990946319946606e-07,
      "loss": 0.0025,
      "reward": 2.0484752655029297,
      "reward_std": 0.009697951376438141,
      "rewards/accuracy_reward": 0.8484753370285034,
      "rewards/format_reward": 1.0,
      "step": 1389
    },
    {
      "all_correct": 0.75,
      "all_wrong": 0.0,
      "completion_length": 407.75,
      "epoch": 0.01917214934966414,
      "grad_norm": 2.365709593829244,
      "kl": 0.06201171875,
      "learning_rate": 9.990933282940268e-07,
      "loss": 0.0025,
      "reward": 2.118499755859375,
      "reward_std": 0.028025349602103233,
      "rewards/accuracy_reward": 0.924750030040741,
      "rewards/format_reward": 1.0,
      "step": 1390
    },
    {
      "all_correct": 0.75,
      "all_wrong": 0.0,
      "completion_length": 405.375,
      "epoch": 0.019185942262865338,
      "grad_norm": 2.760345800837128,
      "kl": 0.06640625,
      "learning_rate": 9.990920236562767e-07,
      "loss": 0.0026,
      "reward": 2.115687370300293,
      "reward_std": 0.02271743305027485,
      "rewards/accuracy_reward": 0.9219374656677246,
      "rewards/format_reward": 1.0,
      "step": 1391
    },
    {
      "all_correct": 1.0,
      "all_wrong": 0.0,
      "completion_length": 396.90625,
      "epoch": 0.019199735176066535,
      "grad_norm": 2.4719968506959566,
      "kl": 0.06640625,
      "learning_rate": 9.990907180814127e-07,
      "loss": 0.0026,
      "reward": 2.14662504196167,
      "reward_std": 0.005435137078166008,
      "rewards/accuracy_reward": 0.9466249942779541,
      "rewards/format_reward": 1.0,
      "step": 1392
    },
    {
      "all_correct": 1.0,
      "all_wrong": 0.0,
      "completion_length": 400.4375,
      "epoch": 0.019213528089267733,
      "grad_norm": 2.921653276635333,
      "kl": 0.06640625,
      "learning_rate": 9.990894115694373e-07,
      "loss": 0.0027,
      "reward": 2.1763126850128174,
      "reward_std": 0.024860410019755363,
      "rewards/accuracy_reward": 0.9825624823570251,
      "rewards/format_reward": 1.0,
      "step": 1393
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.0,
      "completion_length": 405.84375,
      "epoch": 0.01922732100246893,
      "grad_norm": 4.695182684585688,
      "kl": 0.06982421875,
      "learning_rate": 9.990881041203527e-07,
      "loss": 0.0028,
      "reward": 2.120640754699707,
      "reward_std": 0.02664576843380928,
      "rewards/accuracy_reward": 0.9268906116485596,
      "rewards/format_reward": 1.0,
      "step": 1394
    },
    {
      "all_correct": 0.25,
      "all_wrong": 0.0,
      "completion_length": 394.375,
      "epoch": 0.019241113915670127,
      "grad_norm": 2.948055774747822,
      "kl": 0.078125,
      "learning_rate": 9.990867957341617e-07,
      "loss": 0.0031,
      "reward": 2.053187370300293,
      "reward_std": 0.04791552573442459,
      "rewards/accuracy_reward": 0.8656874895095825,
      "rewards/format_reward": 1.0,
      "step": 1395
    },
    {
      "all_correct": 0.75,
      "all_wrong": 0.0,
      "completion_length": 399.5625,
      "epoch": 0.019254906828871324,
      "grad_norm": 2.670385126230036,
      "kl": 0.07177734375,
      "learning_rate": 9.990854864108666e-07,
      "loss": 0.0029,
      "reward": 2.129499912261963,
      "reward_std": 0.025492768734693527,
      "rewards/accuracy_reward": 0.9357499480247498,
      "rewards/format_reward": 1.0,
      "step": 1396
    },
    {
      "all_correct": 0.75,
      "all_wrong": 0.0,
      "completion_length": 387.40625,
      "epoch": 0.01926869974207252,
      "grad_norm": 2.258663069326255,
      "kl": 0.06298828125,
      "learning_rate": 9.9908417615047e-07,
      "loss": 0.0025,
      "reward": 2.064406394958496,
      "reward_std": 0.02151062712073326,
      "rewards/accuracy_reward": 0.8644062280654907,
      "rewards/format_reward": 1.0,
      "step": 1397
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.0,
      "completion_length": 388.9375,
      "epoch": 0.01928249265527372,
      "grad_norm": 2.297977100366778,
      "kl": 0.06494140625,
      "learning_rate": 9.99082864952974e-07,
      "loss": 0.0026,
      "reward": 2.064687490463257,
      "reward_std": 0.028131868690252304,
      "rewards/accuracy_reward": 0.8709375262260437,
      "rewards/format_reward": 1.0,
      "step": 1398
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.0,
      "completion_length": 399.09375,
      "epoch": 0.019296285568474916,
      "grad_norm": 3.004945067939647,
      "kl": 0.064453125,
      "learning_rate": 9.990815528183815e-07,
      "loss": 0.0026,
      "reward": 2.0157811641693115,
      "reward_std": 0.02041110396385193,
      "rewards/accuracy_reward": 0.8157812356948853,
      "rewards/format_reward": 1.0,
      "step": 1399
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.0,
      "completion_length": 385.21875,
      "epoch": 0.019310078481676114,
      "grad_norm": 4.566409895909664,
      "kl": 0.072265625,
      "learning_rate": 9.990802397466946e-07,
      "loss": 0.0029,
      "reward": 2.031540632247925,
      "reward_std": 0.03331389278173447,
      "rewards/accuracy_reward": 0.8377906084060669,
      "rewards/format_reward": 1.0,
      "step": 1400
    },
    {
      "all_correct": 0.25,
      "all_wrong": 0.0,
      "completion_length": 388.40625,
      "epoch": 0.01932387139487731,
      "grad_norm": 2.816010107802226,
      "kl": 0.06591796875,
      "learning_rate": 9.99078925737916e-07,
      "loss": 0.0026,
      "reward": 2.0303125381469727,
      "reward_std": 0.03370671719312668,
      "rewards/accuracy_reward": 0.8365625739097595,
      "rewards/format_reward": 1.0,
      "step": 1401
    },
    {
      "all_correct": 1.0,
      "all_wrong": 0.0,
      "completion_length": 387.46875,
      "epoch": 0.019337664308078508,
      "grad_norm": 2.0093763034820484,
      "kl": 0.0634765625,
      "learning_rate": 9.99077610792048e-07,
      "loss": 0.0026,
      "reward": 2.117500066757202,
      "reward_std": 0.010711370036005974,
      "rewards/accuracy_reward": 0.9174999594688416,
      "rewards/format_reward": 1.0,
      "step": 1402
    },
    {
      "all_correct": 0.0,
      "all_wrong": 0.0,
      "completion_length": 385.0625,
      "epoch": 0.019351457221279705,
      "grad_norm": 1.964705004863095,
      "kl": 0.06787109375,
      "learning_rate": 9.990762949090932e-07,
      "loss": 0.0027,
      "reward": 2.012312650680542,
      "reward_std": 0.026217876002192497,
      "rewards/accuracy_reward": 0.8185625076293945,
      "rewards/format_reward": 1.0,
      "step": 1403
    },
    {
      "all_correct": 0.25,
      "all_wrong": 0.0,
      "completion_length": 384.53125,
      "epoch": 0.019365250134480903,
      "grad_norm": 3.8917036634762305,
      "kl": 0.06591796875,
      "learning_rate": 9.990749780890543e-07,
      "loss": 0.0026,
      "reward": 1.9648125171661377,
      "reward_std": 0.037845950573682785,
      "rewards/accuracy_reward": 0.7648124694824219,
      "rewards/format_reward": 1.0,
      "step": 1404
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.0,
      "completion_length": 388.15625,
      "epoch": 0.0193790430476821,
      "grad_norm": 3.7791355827027897,
      "kl": 0.06396484375,
      "learning_rate": 9.990736603319332e-07,
      "loss": 0.0026,
      "reward": 2.101375102996826,
      "reward_std": 0.04703740030527115,
      "rewards/accuracy_reward": 0.9013749361038208,
      "rewards/format_reward": 1.0,
      "step": 1405
    },
    {
      "all_correct": 0.25,
      "all_wrong": 0.0,
      "completion_length": 390.8125,
      "epoch": 0.019392835960883297,
      "grad_norm": 3.4782599406137877,
      "kl": 0.06298828125,
      "learning_rate": 9.990723416377326e-07,
      "loss": 0.0025,
      "reward": 1.9942188262939453,
      "reward_std": 0.010157547891139984,
      "rewards/accuracy_reward": 0.7942187786102295,
      "rewards/format_reward": 1.0,
      "step": 1406
    },
    {
      "all_correct": 0.75,
      "all_wrong": 0.0,
      "completion_length": 389.0,
      "epoch": 0.019406628874084494,
      "grad_norm": 1.9183813775975525,
      "kl": 0.0654296875,
      "learning_rate": 9.990710220064553e-07,
      "loss": 0.0026,
      "reward": 2.082937717437744,
      "reward_std": 0.010085434652864933,
      "rewards/accuracy_reward": 0.8829374313354492,
      "rewards/format_reward": 1.0,
      "step": 1407
    },
    {
      "all_correct": 0.25,
      "all_wrong": 0.0,
      "completion_length": 390.125,
      "epoch": 0.01942042178728569,
      "grad_norm": 2.841260601384254,
      "kl": 0.0673828125,
      "learning_rate": 9.990697014381034e-07,
      "loss": 0.0027,
      "reward": 2.0561251640319824,
      "reward_std": 0.030994638800621033,
      "rewards/accuracy_reward": 0.862375020980835,
      "rewards/format_reward": 1.0,
      "step": 1408
    },
    {
      "all_correct": 0.75,
      "all_wrong": 0.0,
      "completion_length": 388.875,
      "epoch": 0.01943421470048689,
      "grad_norm": 7.877301682722908,
      "kl": 0.068359375,
      "learning_rate": 9.990683799326795e-07,
      "loss": 0.0027,
      "reward": 2.0743751525878906,
      "reward_std": 0.015688057988882065,
      "rewards/accuracy_reward": 0.8743749856948853,
      "rewards/format_reward": 1.0,
      "step": 1409
    },
    {
      "all_correct": 0.75,
      "all_wrong": 0.0,
      "completion_length": 398.25,
      "epoch": 0.019448007613688086,
      "grad_norm": 2.6976833786107357,
      "kl": 0.0654296875,
      "learning_rate": 9.990670574901861e-07,
      "loss": 0.0026,
      "reward": 2.1114063262939453,
      "reward_std": 0.019553350284695625,
      "rewards/accuracy_reward": 0.9114062786102295,
      "rewards/format_reward": 1.0,
      "step": 1410
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.0,
      "completion_length": 395.5,
      "epoch": 0.019461800526889284,
      "grad_norm": 3.851158144377856,
      "kl": 0.0703125,
      "learning_rate": 9.990657341106258e-07,
      "loss": 0.0028,
      "reward": 2.0808498859405518,
      "reward_std": 0.04106046259403229,
      "rewards/accuracy_reward": 0.8933500647544861,
      "rewards/format_reward": 1.0,
      "step": 1411
    },
    {
      "all_correct": 0.75,
      "all_wrong": 0.0,
      "completion_length": 393.03125,
      "epoch": 0.01947559344009048,
      "grad_norm": 2.9251545264930496,
      "kl": 0.07275390625,
      "learning_rate": 9.99064409794001e-07,
      "loss": 0.0029,
      "reward": 2.12137508392334,
      "reward_std": 0.028615232557058334,
      "rewards/accuracy_reward": 0.9276250004768372,
      "rewards/format_reward": 1.0,
      "step": 1412
    },
    {
      "all_correct": 1.0,
      "all_wrong": 0.0,
      "completion_length": 399.09375,
      "epoch": 0.019489386353291678,
      "grad_norm": 2.9823938749513297,
      "kl": 0.0693359375,
      "learning_rate": 9.990630845403139e-07,
      "loss": 0.0028,
      "reward": 2.1189374923706055,
      "reward_std": 0.015463745221495628,
      "rewards/accuracy_reward": 0.9189374446868896,
      "rewards/format_reward": 1.0,
      "step": 1413
    },
    {
      "all_correct": 1.0,
      "all_wrong": 0.0,
      "completion_length": 406.40625,
      "epoch": 0.019503179266492875,
      "grad_norm": 3.2499441215325957,
      "kl": 0.0673828125,
      "learning_rate": 9.990617583495674e-07,
      "loss": 0.0027,
      "reward": 2.1347813606262207,
      "reward_std": 0.014841862954199314,
      "rewards/accuracy_reward": 0.9347811937332153,
      "rewards/format_reward": 1.0,
      "step": 1414
    },
    {
      "all_correct": 1.0,
      "all_wrong": 0.0,
      "completion_length": 399.0625,
      "epoch": 0.019516972179694073,
      "grad_norm": 7.3485830510949395,
      "kl": 0.06689453125,
      "learning_rate": 9.990604312217636e-07,
      "loss": 0.0027,
      "reward": 2.137343645095825,
      "reward_std": 0.01708845980465412,
      "rewards/accuracy_reward": 0.9373437762260437,
      "rewards/format_reward": 1.0,
      "step": 1415
    },
    {
      "all_correct": 0.75,
      "all_wrong": 0.0,
      "completion_length": 407.9375,
      "epoch": 0.01953076509289527,
      "grad_norm": 2.3316750023619908,
      "kl": 0.0693359375,
      "learning_rate": 9.990591031569055e-07,
      "loss": 0.0028,
      "reward": 2.0688748359680176,
      "reward_std": 0.014043771661818027,
      "rewards/accuracy_reward": 0.8688750267028809,
      "rewards/format_reward": 1.0,
      "step": 1416
    },
    {
      "all_correct": 0.75,
      "all_wrong": 0.0,
      "completion_length": 429.90625,
      "epoch": 0.019544558006096467,
      "grad_norm": 5.388408852254975,
      "kl": 0.0673828125,
      "learning_rate": 9.990577741549952e-07,
      "loss": 0.0027,
      "reward": 2.095968723297119,
      "reward_std": 0.01867583580315113,
      "rewards/accuracy_reward": 0.8959687948226929,
      "rewards/format_reward": 1.0,
      "step": 1417
    },
    {
      "all_correct": 0.75,
      "all_wrong": 0.0,
      "completion_length": 414.5,
      "epoch": 0.019558350919297664,
      "grad_norm": 2.0788566359784935,
      "kl": 0.06640625,
      "learning_rate": 9.990564442160352e-07,
      "loss": 0.0026,
      "reward": 2.0601251125335693,
      "reward_std": 0.01963699422776699,
      "rewards/accuracy_reward": 0.8601250648498535,
      "rewards/format_reward": 1.0,
      "step": 1418
    },
    {
      "all_correct": 0.25,
      "all_wrong": 0.0,
      "completion_length": 410.71875,
      "epoch": 0.01957214383249886,
      "grad_norm": 2.800607541032042,
      "kl": 0.0712890625,
      "learning_rate": 9.990551133400283e-07,
      "loss": 0.0028,
      "reward": 2.000093936920166,
      "reward_std": 0.021569915115833282,
      "rewards/accuracy_reward": 0.8000937104225159,
      "rewards/format_reward": 1.0,
      "step": 1419
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.0,
      "completion_length": 409.03125,
      "epoch": 0.01958593674570006,
      "grad_norm": 2.3001075444508965,
      "kl": 0.07275390625,
      "learning_rate": 9.990537815269765e-07,
      "loss": 0.0029,
      "reward": 2.0057811737060547,
      "reward_std": 0.010040796361863613,
      "rewards/accuracy_reward": 0.8057812452316284,
      "rewards/format_reward": 1.0,
      "step": 1420
    },
    {
      "all_correct": 0.0,
      "all_wrong": 0.0,
      "completion_length": 401.5625,
      "epoch": 0.019599729658901256,
      "grad_norm": 2.520649600787214,
      "kl": 0.07568359375,
      "learning_rate": 9.99052448776883e-07,
      "loss": 0.003,
      "reward": 2.0252814292907715,
      "reward_std": 0.03313218802213669,
      "rewards/accuracy_reward": 0.831531286239624,
      "rewards/format_reward": 1.0,
      "step": 1421
    },
    {
      "all_correct": 0.75,
      "all_wrong": 0.0,
      "completion_length": 404.71875,
      "epoch": 0.019613522572102454,
      "grad_norm": 3.0774828302666695,
      "kl": 0.07373046875,
      "learning_rate": 9.990511150897496e-07,
      "loss": 0.003,
      "reward": 2.1285157203674316,
      "reward_std": 0.01692095398902893,
      "rewards/accuracy_reward": 0.928515613079071,
      "rewards/format_reward": 1.0,
      "step": 1422
    },
    {
      "all_correct": 1.0,
      "all_wrong": 0.0,
      "completion_length": 417.75,
      "epoch": 0.01962731548530365,
      "grad_norm": 2.367879250724881,
      "kl": 0.0712890625,
      "learning_rate": 9.990497804655793e-07,
      "loss": 0.0028,
      "reward": 2.1272499561309814,
      "reward_std": 0.02027575671672821,
      "rewards/accuracy_reward": 0.9272499680519104,
      "rewards/format_reward": 1.0,
      "step": 1423
    },
    {
      "all_correct": 0.75,
      "all_wrong": 0.0,
      "completion_length": 427.1875,
      "epoch": 0.019641108398504848,
      "grad_norm": 2.406134215714481,
      "kl": 0.0654296875,
      "learning_rate": 9.990484449043744e-07,
      "loss": 0.0026,
      "reward": 2.0484063625335693,
      "reward_std": 0.02412530779838562,
      "rewards/accuracy_reward": 0.8484062552452087,
      "rewards/format_reward": 1.0,
      "step": 1424
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.0,
      "completion_length": 426.0,
      "epoch": 0.019654901311706045,
      "grad_norm": 2.5933129417946357,
      "kl": 0.0732421875,
      "learning_rate": 9.990471084061373e-07,
      "loss": 0.0029,
      "reward": 2.052187442779541,
      "reward_std": 0.035337500274181366,
      "rewards/accuracy_reward": 0.8584374785423279,
      "rewards/format_reward": 1.0,
      "step": 1425
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.0,
      "completion_length": 413.71875,
      "epoch": 0.019668694224907243,
      "grad_norm": 10.806961798226759,
      "kl": 0.0673828125,
      "learning_rate": 9.990457709708705e-07,
      "loss": 0.0027,
      "reward": 2.0996875762939453,
      "reward_std": 0.026638073846697807,
      "rewards/accuracy_reward": 0.9059374928474426,
      "rewards/format_reward": 1.0,
      "step": 1426
    },
    {
      "all_correct": 1.0,
      "all_wrong": 0.0,
      "completion_length": 416.625,
      "epoch": 0.01968248713810844,
      "grad_norm": 3.427685274050611,
      "kl": 0.0703125,
      "learning_rate": 9.99044432598577e-07,
      "loss": 0.0028,
      "reward": 2.133406162261963,
      "reward_std": 0.02070443332195282,
      "rewards/accuracy_reward": 0.9334062337875366,
      "rewards/format_reward": 1.0,
      "step": 1427
    },
    {
      "all_correct": 1.0,
      "all_wrong": 0.0,
      "completion_length": 412.1875,
      "epoch": 0.019696280051309637,
      "grad_norm": 2.544944003080472,
      "kl": 0.07177734375,
      "learning_rate": 9.990430932892588e-07,
      "loss": 0.0029,
      "reward": 2.085624933242798,
      "reward_std": 0.01857692375779152,
      "rewards/accuracy_reward": 0.8856250047683716,
      "rewards/format_reward": 1.0,
      "step": 1428
    },
    {
      "all_correct": 0.75,
      "all_wrong": 0.0,
      "completion_length": 427.625,
      "epoch": 0.019710072964510834,
      "grad_norm": 2.8662737447680335,
      "kl": 0.07666015625,
      "learning_rate": 9.990417530429186e-07,
      "loss": 0.0031,
      "reward": 2.067312717437744,
      "reward_std": 0.021073510870337486,
      "rewards/accuracy_reward": 0.867312490940094,
      "rewards/format_reward": 1.0,
      "step": 1429
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.0,
      "completion_length": 417.28125,
      "epoch": 0.01972386587771203,
      "grad_norm": 2.2717837997473125,
      "kl": 0.07470703125,
      "learning_rate": 9.990404118595587e-07,
      "loss": 0.003,
      "reward": 2.1215624809265137,
      "reward_std": 0.028076861053705215,
      "rewards/accuracy_reward": 0.9278125166893005,
      "rewards/format_reward": 1.0,
      "step": 1430
    },
    {
      "all_correct": 0.75,
      "all_wrong": 0.0,
      "completion_length": 425.40625,
      "epoch": 0.01973765879091323,
      "grad_norm": 2.499405558427648,
      "kl": 0.07177734375,
      "learning_rate": 9.99039069739182e-07,
      "loss": 0.0029,
      "reward": 2.05049991607666,
      "reward_std": 0.014963004738092422,
      "rewards/accuracy_reward": 0.8504999876022339,
      "rewards/format_reward": 1.0,
      "step": 1431
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.0,
      "completion_length": 417.625,
      "epoch": 0.019751451704114426,
      "grad_norm": 2.414492798561618,
      "kl": 0.080078125,
      "learning_rate": 9.99037726681791e-07,
      "loss": 0.0032,
      "reward": 1.9780938625335693,
      "reward_std": 0.03298702836036682,
      "rewards/accuracy_reward": 0.778093695640564,
      "rewards/format_reward": 1.0,
      "step": 1432
    },
    {
      "all_correct": 0.75,
      "all_wrong": 0.0,
      "completion_length": 415.46875,
      "epoch": 0.019765244617315623,
      "grad_norm": 3.5838160270555,
      "kl": 0.072265625,
      "learning_rate": 9.990363826873877e-07,
      "loss": 0.0029,
      "reward": 2.1017813682556152,
      "reward_std": 0.02714308351278305,
      "rewards/accuracy_reward": 0.9017812609672546,
      "rewards/format_reward": 1.0,
      "step": 1433
    },
    {
      "all_correct": 0.75,
      "all_wrong": 0.0,
      "completion_length": 404.75,
      "epoch": 0.01977903753051682,
      "grad_norm": 8.212660605744995,
      "kl": 0.078125,
      "learning_rate": 9.99035037755975e-07,
      "loss": 0.0031,
      "reward": 2.116875171661377,
      "reward_std": 0.030858095735311508,
      "rewards/accuracy_reward": 0.9231250286102295,
      "rewards/format_reward": 1.0,
      "step": 1434
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.0,
      "completion_length": 415.21875,
      "epoch": 0.019792830443718018,
      "grad_norm": 2.530384796034006,
      "kl": 0.072265625,
      "learning_rate": 9.990336918875557e-07,
      "loss": 0.0029,
      "reward": 2.073406219482422,
      "reward_std": 0.033087823539972305,
      "rewards/accuracy_reward": 0.8796562552452087,
      "rewards/format_reward": 1.0,
      "step": 1435
    },
    {
      "all_correct": 1.0,
      "all_wrong": 0.0,
      "completion_length": 408.40625,
      "epoch": 0.019806623356919215,
      "grad_norm": 5.862788582254299,
      "kl": 0.0830078125,
      "learning_rate": 9.990323450821317e-07,
      "loss": 0.0033,
      "reward": 2.1296873092651367,
      "reward_std": 0.017731118947267532,
      "rewards/accuracy_reward": 0.9296875,
      "rewards/format_reward": 1.0,
      "step": 1436
    },
    {
      "all_correct": 0.75,
      "all_wrong": 0.0,
      "completion_length": 402.5,
      "epoch": 0.019820416270120413,
      "grad_norm": 2.553000715757157,
      "kl": 0.07958984375,
      "learning_rate": 9.99030997339706e-07,
      "loss": 0.0032,
      "reward": 2.11447811126709,
      "reward_std": 0.02133796736598015,
      "rewards/accuracy_reward": 0.9144781231880188,
      "rewards/format_reward": 1.0,
      "step": 1437
    },
    {
      "all_correct": 1.0,
      "all_wrong": 0.0,
      "completion_length": 411.0625,
      "epoch": 0.01983420918332161,
      "grad_norm": 7.537701671431813,
      "kl": 0.07275390625,
      "learning_rate": 9.990296486602809e-07,
      "loss": 0.0029,
      "reward": 2.1310312747955322,
      "reward_std": 0.04073544591665268,
      "rewards/accuracy_reward": 0.9310312271118164,
      "rewards/format_reward": 1.0,
      "step": 1438
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.0,
      "completion_length": 419.59375,
      "epoch": 0.019848002096522807,
      "grad_norm": 3.0150078328275876,
      "kl": 0.0693359375,
      "learning_rate": 9.99028299043859e-07,
      "loss": 0.0028,
      "reward": 2.076406240463257,
      "reward_std": 0.03086410090327263,
      "rewards/accuracy_reward": 0.8826562166213989,
      "rewards/format_reward": 1.0,
      "step": 1439
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.0,
      "completion_length": 397.09375,
      "epoch": 0.019861795009724004,
      "grad_norm": 2.7278265141157676,
      "kl": 0.07666015625,
      "learning_rate": 9.99026948490443e-07,
      "loss": 0.0031,
      "reward": 2.0022811889648438,
      "reward_std": 0.01818978041410446,
      "rewards/accuracy_reward": 0.8022812604904175,
      "rewards/format_reward": 1.0,
      "step": 1440
    },
    {
      "all_correct": 0.75,
      "all_wrong": 0.0,
      "completion_length": 388.9375,
      "epoch": 0.0198755879229252,
      "grad_norm": 3.0086712372134716,
      "kl": 0.0751953125,
      "learning_rate": 9.990255970000352e-07,
      "loss": 0.003,
      "reward": 2.0996251106262207,
      "reward_std": 0.0259021557867527,
      "rewards/accuracy_reward": 0.8996249437332153,
      "rewards/format_reward": 1.0,
      "step": 1441
    },
    {
      "all_correct": 0.75,
      "all_wrong": 0.0,
      "completion_length": 394.34375,
      "epoch": 0.0198893808361264,
      "grad_norm": 2.1449807743936984,
      "kl": 0.0712890625,
      "learning_rate": 9.990242445726383e-07,
      "loss": 0.0028,
      "reward": 2.1070938110351562,
      "reward_std": 0.013833701610565186,
      "rewards/accuracy_reward": 0.9070937037467957,
      "rewards/format_reward": 1.0,
      "step": 1442
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.0,
      "completion_length": 393.78125,
      "epoch": 0.019903173749327596,
      "grad_norm": 2.2030681132618417,
      "kl": 0.078125,
      "learning_rate": 9.990228912082545e-07,
      "loss": 0.0031,
      "reward": 2.099375009536743,
      "reward_std": 0.029069416224956512,
      "rewards/accuracy_reward": 0.9056249856948853,
      "rewards/format_reward": 1.0,
      "step": 1443
    },
    {
      "all_correct": 1.0,
      "all_wrong": 0.0,
      "completion_length": 375.5625,
      "epoch": 0.019916966662528793,
      "grad_norm": 3.09720987760733,
      "kl": 0.078125,
      "learning_rate": 9.99021536906887e-07,
      "loss": 0.0031,
      "reward": 2.0868749618530273,
      "reward_std": 0.01801455393433571,
      "rewards/accuracy_reward": 0.8868749737739563,
      "rewards/format_reward": 1.0,
      "step": 1444
    },
    {
      "all_correct": 0.75,
      "all_wrong": 0.0,
      "completion_length": 398.90625,
      "epoch": 0.01993075957572999,
      "grad_norm": 2.3280074806987727,
      "kl": 0.080078125,
      "learning_rate": 9.990201816685378e-07,
      "loss": 0.0032,
      "reward": 2.083343982696533,
      "reward_std": 0.015879862010478973,
      "rewards/accuracy_reward": 0.8833437561988831,
      "rewards/format_reward": 1.0,
      "step": 1445
    },
    {
      "all_correct": 1.0,
      "all_wrong": 0.0,
      "completion_length": 387.1875,
      "epoch": 0.019944552488931188,
      "grad_norm": 2.1722469200182997,
      "kl": 0.0732421875,
      "learning_rate": 9.990188254932096e-07,
      "loss": 0.0029,
      "reward": 2.1130001544952393,
      "reward_std": 0.01783987134695053,
      "rewards/accuracy_reward": 0.9129999876022339,
      "rewards/format_reward": 1.0,
      "step": 1446
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.0,
      "completion_length": 389.59375,
      "epoch": 0.019958345402132385,
      "grad_norm": 3.113658086628346,
      "kl": 0.072265625,
      "learning_rate": 9.990174683809047e-07,
      "loss": 0.0029,
      "reward": 2.028031349182129,
      "reward_std": 0.03220091015100479,
      "rewards/accuracy_reward": 0.8280312418937683,
      "rewards/format_reward": 1.0,
      "step": 1447
    },
    {
      "all_correct": 0.75,
      "all_wrong": 0.0,
      "completion_length": 382.375,
      "epoch": 0.019972138315333583,
      "grad_norm": 2.7258957173500913,
      "kl": 0.0693359375,
      "learning_rate": 9.99016110331626e-07,
      "loss": 0.0028,
      "reward": 2.075906276702881,
      "reward_std": 0.030843686312437057,
      "rewards/accuracy_reward": 0.8821563124656677,
      "rewards/format_reward": 1.0,
      "step": 1448
    },
    {
      "all_correct": 0.75,
      "all_wrong": 0.0,
      "completion_length": 374.59375,
      "epoch": 0.01998593122853478,
      "grad_norm": 2.1182130106951536,
      "kl": 0.0732421875,
      "learning_rate": 9.99014751345376e-07,
      "loss": 0.0029,
      "reward": 2.140812397003174,
      "reward_std": 0.03086215630173683,
      "rewards/accuracy_reward": 0.9470625519752502,
      "rewards/format_reward": 1.0,
      "step": 1449
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.0,
      "completion_length": 399.46875,
      "epoch": 0.019999724141735977,
      "grad_norm": 4.51714947154425,
      "kl": 0.076171875,
      "learning_rate": 9.990133914221573e-07,
      "loss": 0.003,
      "reward": 2.0561561584472656,
      "reward_std": 0.025271710008382797,
      "rewards/accuracy_reward": 0.8561562895774841,
      "rewards/format_reward": 1.0,
      "step": 1450
    },
    {
      "all_correct": 0.75,
      "all_wrong": 0.0,
      "completion_length": 383.6875,
      "epoch": 0.020013517054937174,
      "grad_norm": 5.747795951529524,
      "kl": 0.08203125,
      "learning_rate": 9.99012030561972e-07,
      "loss": 0.0033,
      "reward": 2.028437614440918,
      "reward_std": 0.022412512451410294,
      "rewards/accuracy_reward": 0.8284375071525574,
      "rewards/format_reward": 1.0,
      "step": 1451
    },
    {
      "all_correct": 0.25,
      "all_wrong": 0.0,
      "completion_length": 382.65625,
      "epoch": 0.02002730996813837,
      "grad_norm": 2.3702601381037773,
      "kl": 0.080078125,
      "learning_rate": 9.990106687648234e-07,
      "loss": 0.0032,
      "reward": 2.0584373474121094,
      "reward_std": 0.050187185406684875,
      "rewards/accuracy_reward": 0.8709375262260437,
      "rewards/format_reward": 1.0,
      "step": 1452
    },
    {
      "all_correct": 0.75,
      "all_wrong": 0.0,
      "completion_length": 381.96875,
      "epoch": 0.02004110288133957,
      "grad_norm": 2.870280503999781,
      "kl": 0.0771484375,
      "learning_rate": 9.990093060307134e-07,
      "loss": 0.0031,
      "reward": 2.102193832397461,
      "reward_std": 0.037157513201236725,
      "rewards/accuracy_reward": 0.9084437489509583,
      "rewards/format_reward": 1.0,
      "step": 1453
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.0,
      "completion_length": 374.96875,
      "epoch": 0.020054895794540766,
      "grad_norm": 2.2391834679139433,
      "kl": 0.07373046875,
      "learning_rate": 9.99007942359645e-07,
      "loss": 0.003,
      "reward": 1.9770625829696655,
      "reward_std": 0.03263351693749428,
      "rewards/accuracy_reward": 0.789562463760376,
      "rewards/format_reward": 1.0,
      "step": 1454
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.0,
      "completion_length": 379.875,
      "epoch": 0.020068688707741963,
      "grad_norm": 2.805966438635942,
      "kl": 0.07958984375,
      "learning_rate": 9.990065777516203e-07,
      "loss": 0.0032,
      "reward": 2.0721874237060547,
      "reward_std": 0.03986940532922745,
      "rewards/accuracy_reward": 0.8784375786781311,
      "rewards/format_reward": 1.0,
      "step": 1455
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.0,
      "completion_length": 376.78125,
      "epoch": 0.02008248162094316,
      "grad_norm": 4.513762339417655,
      "kl": 0.0751953125,
      "learning_rate": 9.990052122066423e-07,
      "loss": 0.003,
      "reward": 2.035062313079834,
      "reward_std": 0.028803803026676178,
      "rewards/accuracy_reward": 0.8413124680519104,
      "rewards/format_reward": 1.0,
      "step": 1456
    },
    {
      "all_correct": 0.25,
      "all_wrong": 0.0,
      "completion_length": 382.71875,
      "epoch": 0.020096274534144358,
      "grad_norm": 2.209519098465575,
      "kl": 0.0751953125,
      "learning_rate": 9.990038457247135e-07,
      "loss": 0.003,
      "reward": 2.059093952178955,
      "reward_std": 0.02936217002570629,
      "rewards/accuracy_reward": 0.8653438091278076,
      "rewards/format_reward": 1.0,
      "step": 1457
    },
    {
      "all_correct": 1.0,
      "all_wrong": 0.0,
      "completion_length": 382.15625,
      "epoch": 0.020110067447345555,
      "grad_norm": 5.275383632147241,
      "kl": 0.0712890625,
      "learning_rate": 9.99002478305836e-07,
      "loss": 0.0029,
      "reward": 2.136593818664551,
      "reward_std": 0.029701193794608116,
      "rewards/accuracy_reward": 0.9428437948226929,
      "rewards/format_reward": 1.0,
      "step": 1458
    },
    {
      "all_correct": 0.75,
      "all_wrong": 0.0,
      "completion_length": 388.1875,
      "epoch": 0.020123860360546753,
      "grad_norm": 2.569242678900793,
      "kl": 0.078125,
      "learning_rate": 9.99001109950013e-07,
      "loss": 0.0031,
      "reward": 2.114187479019165,
      "reward_std": 0.018061114475131035,
      "rewards/accuracy_reward": 0.9141875505447388,
      "rewards/format_reward": 1.0,
      "step": 1459
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.0,
      "completion_length": 397.03125,
      "epoch": 0.02013765327374795,
      "grad_norm": 5.731445674137346,
      "kl": 0.06640625,
      "learning_rate": 9.989997406572467e-07,
      "loss": 0.0027,
      "reward": 2.0840625762939453,
      "reward_std": 0.02083110623061657,
      "rewards/accuracy_reward": 0.8840625286102295,
      "rewards/format_reward": 1.0,
      "step": 1460
    },
    {
      "all_correct": 0.0,
      "all_wrong": 0.0,
      "completion_length": 405.25,
      "epoch": 0.020151446186949147,
      "grad_norm": 2.3202474142012237,
      "kl": 0.08349609375,
      "learning_rate": 9.9899837042754e-07,
      "loss": 0.0033,
      "reward": 1.8969063758850098,
      "reward_std": 0.049554333090782166,
      "rewards/accuracy_reward": 0.7156562209129333,
      "rewards/format_reward": 1.0,
      "step": 1461
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.0,
      "completion_length": 417.75,
      "epoch": 0.020165239100150344,
      "grad_norm": 2.653689168150688,
      "kl": 0.072265625,
      "learning_rate": 9.989969992608952e-07,
      "loss": 0.0029,
      "reward": 2.0672812461853027,
      "reward_std": 0.0335346944630146,
      "rewards/accuracy_reward": 0.8735312819480896,
      "rewards/format_reward": 1.0,
      "step": 1462
    },
    {
      "all_correct": 0.25,
      "all_wrong": 0.0,
      "completion_length": 395.71875,
      "epoch": 0.02017903201335154,
      "grad_norm": 2.8829537302895,
      "kl": 0.0830078125,
      "learning_rate": 9.989956271573146e-07,
      "loss": 0.0033,
      "reward": 2.0203750133514404,
      "reward_std": 0.031481314450502396,
      "rewards/accuracy_reward": 0.8266249895095825,
      "rewards/format_reward": 1.0,
      "step": 1463
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.0,
      "completion_length": 402.71875,
      "epoch": 0.02019282492655274,
      "grad_norm": 2.298391993201629,
      "kl": 0.0703125,
      "learning_rate": 9.989942541168014e-07,
      "loss": 0.0028,
      "reward": 2.0488126277923584,
      "reward_std": 0.030729303136467934,
      "rewards/accuracy_reward": 0.8550624847412109,
      "rewards/format_reward": 1.0,
      "step": 1464
    },
    {
      "all_correct": 0.75,
      "all_wrong": 0.0,
      "completion_length": 420.5,
      "epoch": 0.020206617839753936,
      "grad_norm": 2.2312097748787223,
      "kl": 0.072265625,
      "learning_rate": 9.989928801393578e-07,
      "loss": 0.0029,
      "reward": 2.0637500286102295,
      "reward_std": 0.008092949166893959,
      "rewards/accuracy_reward": 0.8637499213218689,
      "rewards/format_reward": 1.0,
      "step": 1465
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.0,
      "completion_length": 404.90625,
      "epoch": 0.02022041075295513,
      "grad_norm": 4.023196168787191,
      "kl": 0.0791015625,
      "learning_rate": 9.989915052249864e-07,
      "loss": 0.0032,
      "reward": 2.017031192779541,
      "reward_std": 0.034903790801763535,
      "rewards/accuracy_reward": 0.8170312643051147,
      "rewards/format_reward": 1.0,
      "step": 1466
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.0,
      "completion_length": 404.34375,
      "epoch": 0.020234203666156327,
      "grad_norm": 3.2540815736474786,
      "kl": 0.076171875,
      "learning_rate": 9.989901293736897e-07,
      "loss": 0.0031,
      "reward": 2.05400013923645,
      "reward_std": 0.026853162795305252,
      "rewards/accuracy_reward": 0.8539999723434448,
      "rewards/format_reward": 1.0,
      "step": 1467
    },
    {
      "all_correct": 0.75,
      "all_wrong": 0.0,
      "completion_length": 435.65625,
      "epoch": 0.020247996579357525,
      "grad_norm": 2.234032815486629,
      "kl": 0.076171875,
      "learning_rate": 9.989887525854708e-07,
      "loss": 0.003,
      "reward": 2.110374927520752,
      "reward_std": 0.018385866656899452,
      "rewards/accuracy_reward": 0.9103749990463257,
      "rewards/format_reward": 1.0,
      "step": 1468
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.0,
      "completion_length": 413.0625,
      "epoch": 0.020261789492558722,
      "grad_norm": 4.841013135337845,
      "kl": 0.07080078125,
      "learning_rate": 9.989873748603316e-07,
      "loss": 0.0028,
      "reward": 2.0072813034057617,
      "reward_std": 0.011211058124899864,
      "rewards/accuracy_reward": 0.8072812557220459,
      "rewards/format_reward": 1.0,
      "step": 1469
    },
    {
      "all_correct": 0.75,
      "all_wrong": 0.0,
      "completion_length": 406.15625,
      "epoch": 0.02027558240575992,
      "grad_norm": 25.240793802416594,
      "kl": 0.0771484375,
      "learning_rate": 9.98985996198275e-07,
      "loss": 0.0031,
      "reward": 2.063593864440918,
      "reward_std": 0.023534409701824188,
      "rewards/accuracy_reward": 0.8635937571525574,
      "rewards/format_reward": 1.0,
      "step": 1470
    },
    {
      "all_correct": 0.75,
      "all_wrong": 0.0,
      "completion_length": 411.84375,
      "epoch": 0.020289375318961116,
      "grad_norm": 7.417145160218178,
      "kl": 0.0751953125,
      "learning_rate": 9.989846165993037e-07,
      "loss": 0.003,
      "reward": 2.0546875,
      "reward_std": 0.017199421301484108,
      "rewards/accuracy_reward": 0.8546874523162842,
      "rewards/format_reward": 1.0,
      "step": 1471
    },
    {
      "all_correct": 1.0,
      "all_wrong": 0.0,
      "completion_length": 412.03125,
      "epoch": 0.020303168232162314,
      "grad_norm": 2.3842360275911845,
      "kl": 0.0732421875,
      "learning_rate": 9.9898323606342e-07,
      "loss": 0.0029,
      "reward": 2.137937545776367,
      "reward_std": 0.012007412500679493,
      "rewards/accuracy_reward": 0.9379374980926514,
      "rewards/format_reward": 1.0,
      "step": 1472
    },
    {
      "all_correct": 0.75,
      "all_wrong": 0.0,
      "completion_length": 419.0625,
      "epoch": 0.02031696114536351,
      "grad_norm": 2.649914949442856,
      "kl": 0.0791015625,
      "learning_rate": 9.989818545906269e-07,
      "loss": 0.0032,
      "reward": 2.088156223297119,
      "reward_std": 0.008715685456991196,
      "rewards/accuracy_reward": 0.8881562948226929,
      "rewards/format_reward": 1.0,
      "step": 1473
    },
    {
      "all_correct": 0.75,
      "all_wrong": 0.0,
      "completion_length": 423.96875,
      "epoch": 0.020330754058564708,
      "grad_norm": 2.4476070083864347,
      "kl": 0.0771484375,
      "learning_rate": 9.989804721809266e-07,
      "loss": 0.0031,
      "reward": 2.1330626010894775,
      "reward_std": 0.029888728633522987,
      "rewards/accuracy_reward": 0.9393125176429749,
      "rewards/format_reward": 1.0,
      "step": 1474
    },
    {
      "all_correct": 0.25,
      "all_wrong": 0.0,
      "completion_length": 413.0625,
      "epoch": 0.020344546971765905,
      "grad_norm": 2.932398650127671,
      "kl": 0.07177734375,
      "learning_rate": 9.98979088834322e-07,
      "loss": 0.0029,
      "reward": 2.014343738555908,
      "reward_std": 0.022120721638202667,
      "rewards/accuracy_reward": 0.8143437504768372,
      "rewards/format_reward": 1.0,
      "step": 1475
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.0,
      "completion_length": 414.15625,
      "epoch": 0.020358339884967103,
      "grad_norm": 2.650293900427481,
      "kl": 0.08203125,
      "learning_rate": 9.989777045508155e-07,
      "loss": 0.0033,
      "reward": 1.9688124656677246,
      "reward_std": 0.022652767598628998,
      "rewards/accuracy_reward": 0.7688125371932983,
      "rewards/format_reward": 1.0,
      "step": 1476
    },
    {
      "all_correct": 0.75,
      "all_wrong": 0.0,
      "completion_length": 422.53125,
      "epoch": 0.0203721327981683,
      "grad_norm": 2.5421774639434624,
      "kl": 0.07763671875,
      "learning_rate": 9.989763193304094e-07,
      "loss": 0.0031,
      "reward": 2.1029999256134033,
      "reward_std": 0.017032857984304428,
      "rewards/accuracy_reward": 0.902999997138977,
      "rewards/format_reward": 1.0,
      "step": 1477
    },
    {
      "all_correct": 1.0,
      "all_wrong": 0.0,
      "completion_length": 413.75,
      "epoch": 0.020385925711369497,
      "grad_norm": 2.0188034380453805,
      "kl": 0.0830078125,
      "learning_rate": 9.989749331731072e-07,
      "loss": 0.0033,
      "reward": 2.1459999084472656,
      "reward_std": 0.010570304468274117,
      "rewards/accuracy_reward": 0.9459999799728394,
      "rewards/format_reward": 1.0,
      "step": 1478
    },
    {
      "all_correct": 0.25,
      "all_wrong": 0.0,
      "completion_length": 414.375,
      "epoch": 0.020399718624570694,
      "grad_norm": 2.4112312451120874,
      "kl": 0.07861328125,
      "learning_rate": 9.989735460789107e-07,
      "loss": 0.0031,
      "reward": 1.961625099182129,
      "reward_std": 0.020201044157147408,
      "rewards/accuracy_reward": 0.7616250514984131,
      "rewards/format_reward": 1.0,
      "step": 1479
    },
    {
      "all_correct": 0.25,
      "all_wrong": 0.0,
      "completion_length": 402.375,
      "epoch": 0.020413511537771892,
      "grad_norm": 2.512817512563664,
      "kl": 0.08056640625,
      "learning_rate": 9.989721580478227e-07,
      "loss": 0.0032,
      "reward": 2.020843982696533,
      "reward_std": 0.021659670397639275,
      "rewards/accuracy_reward": 0.8208437561988831,
      "rewards/format_reward": 1.0,
      "step": 1480
    },
    {
      "all_correct": 0.75,
      "all_wrong": 0.0,
      "completion_length": 421.5,
      "epoch": 0.02042730445097309,
      "grad_norm": 2.7077147134968245,
      "kl": 0.07861328125,
      "learning_rate": 9.989707690798458e-07,
      "loss": 0.0032,
      "reward": 2.1095938682556152,
      "reward_std": 0.013318461365997791,
      "rewards/accuracy_reward": 0.9095937013626099,
      "rewards/format_reward": 1.0,
      "step": 1481
    },
    {
      "all_correct": 0.25,
      "all_wrong": 0.0,
      "completion_length": 411.3125,
      "epoch": 0.020441097364174286,
      "grad_norm": 6.392652014844335,
      "kl": 0.07958984375,
      "learning_rate": 9.98969379174983e-07,
      "loss": 0.0032,
      "reward": 1.992343783378601,
      "reward_std": 0.027757490053772926,
      "rewards/accuracy_reward": 0.79234379529953,
      "rewards/format_reward": 1.0,
      "step": 1482
    },
    {
      "all_correct": 0.25,
      "all_wrong": 0.0,
      "completion_length": 416.03125,
      "epoch": 0.020454890277375484,
      "grad_norm": 2.46023771878258,
      "kl": 0.08544921875,
      "learning_rate": 9.989679883332361e-07,
      "loss": 0.0034,
      "reward": 1.988187551498413,
      "reward_std": 0.03203430399298668,
      "rewards/accuracy_reward": 0.7881875038146973,
      "rewards/format_reward": 1.0,
      "step": 1483
    },
    {
      "all_correct": 0.75,
      "all_wrong": 0.0,
      "completion_length": 411.5,
      "epoch": 0.02046868319057668,
      "grad_norm": 2.1221391079412673,
      "kl": 0.0771484375,
      "learning_rate": 9.989665965546084e-07,
      "loss": 0.0031,
      "reward": 2.05078125,
      "reward_std": 0.03196130692958832,
      "rewards/accuracy_reward": 0.850781261920929,
      "rewards/format_reward": 1.0,
      "step": 1484
    },
    {
      "all_correct": 1.0,
      "all_wrong": 0.0,
      "completion_length": 425.40625,
      "epoch": 0.020482476103777878,
      "grad_norm": 2.1026395380688934,
      "kl": 0.076171875,
      "learning_rate": 9.989652038391024e-07,
      "loss": 0.0031,
      "reward": 2.1292812824249268,
      "reward_std": 0.019329454749822617,
      "rewards/accuracy_reward": 0.9292811751365662,
      "rewards/format_reward": 1.0,
      "step": 1485
    },
    {
      "all_correct": 1.0,
      "all_wrong": 0.0,
      "completion_length": 403.3125,
      "epoch": 0.020496269016979075,
      "grad_norm": 3.115015061843392,
      "kl": 0.0849609375,
      "learning_rate": 9.989638101867207e-07,
      "loss": 0.0034,
      "reward": 2.128218650817871,
      "reward_std": 0.018721235916018486,
      "rewards/accuracy_reward": 0.9282187223434448,
      "rewards/format_reward": 1.0,
      "step": 1486
    },
    {
      "all_correct": 0.75,
      "all_wrong": 0.0,
      "completion_length": 405.8125,
      "epoch": 0.020510061930180273,
      "grad_norm": 2.5414559938831056,
      "kl": 0.0791015625,
      "learning_rate": 9.989624155974657e-07,
      "loss": 0.0032,
      "reward": 2.1322813034057617,
      "reward_std": 0.041062213480472565,
      "rewards/accuracy_reward": 0.938531219959259,
      "rewards/format_reward": 1.0,
      "step": 1487
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.0,
      "completion_length": 413.09375,
      "epoch": 0.02052385484338147,
      "grad_norm": 2.369762796274225,
      "kl": 0.076171875,
      "learning_rate": 9.9896102007134e-07,
      "loss": 0.0031,
      "reward": 2.0397188663482666,
      "reward_std": 0.025427144020795822,
      "rewards/accuracy_reward": 0.839718759059906,
      "rewards/format_reward": 1.0,
      "step": 1488
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.0,
      "completion_length": 410.71875,
      "epoch": 0.020537647756582667,
      "grad_norm": 2.7831538407754732,
      "kl": 0.08056640625,
      "learning_rate": 9.989596236083465e-07,
      "loss": 0.0032,
      "reward": 1.9581562280654907,
      "reward_std": 0.01716439239680767,
      "rewards/accuracy_reward": 0.7581562995910645,
      "rewards/format_reward": 1.0,
      "step": 1489
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.0,
      "completion_length": 408.875,
      "epoch": 0.020551440669783864,
      "grad_norm": 3.1473385913761014,
      "kl": 0.07958984375,
      "learning_rate": 9.989582262084878e-07,
      "loss": 0.0032,
      "reward": 2.0429999828338623,
      "reward_std": 0.022510571405291557,
      "rewards/accuracy_reward": 0.8429999947547913,
      "rewards/format_reward": 1.0,
      "step": 1490
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.0,
      "completion_length": 407.96875,
      "epoch": 0.020565233582985062,
      "grad_norm": 2.552389909118091,
      "kl": 0.08984375,
      "learning_rate": 9.989568278717664e-07,
      "loss": 0.0036,
      "reward": 2.063718795776367,
      "reward_std": 0.02434457838535309,
      "rewards/accuracy_reward": 0.8637188076972961,
      "rewards/format_reward": 1.0,
      "step": 1491
    },
    {
      "all_correct": 1.0,
      "all_wrong": 0.0,
      "completion_length": 410.53125,
      "epoch": 0.02057902649618626,
      "grad_norm": 2.2657698955735497,
      "kl": 0.0830078125,
      "learning_rate": 9.989554285981848e-07,
      "loss": 0.0033,
      "reward": 2.131812334060669,
      "reward_std": 0.01354505680501461,
      "rewards/accuracy_reward": 0.9318125247955322,
      "rewards/format_reward": 1.0,
      "step": 1492
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.0,
      "completion_length": 396.5,
      "epoch": 0.020592819409387456,
      "grad_norm": 2.3538273729945547,
      "kl": 0.07861328125,
      "learning_rate": 9.989540283877458e-07,
      "loss": 0.0031,
      "reward": 2.0350937843322754,
      "reward_std": 0.02350785583257675,
      "rewards/accuracy_reward": 0.8350937366485596,
      "rewards/format_reward": 1.0,
      "step": 1493
    },
    {
      "all_correct": 1.0,
      "all_wrong": 0.0,
      "completion_length": 410.71875,
      "epoch": 0.020606612322588654,
      "grad_norm": 2.6456278831917905,
      "kl": 0.08837890625,
      "learning_rate": 9.989526272404522e-07,
      "loss": 0.0035,
      "reward": 2.113781213760376,
      "reward_std": 0.01741741970181465,
      "rewards/accuracy_reward": 0.9137811660766602,
      "rewards/format_reward": 1.0,
      "step": 1494
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.0,
      "completion_length": 413.9375,
      "epoch": 0.02062040523578985,
      "grad_norm": 3.48187233900594,
      "kl": 0.07275390625,
      "learning_rate": 9.989512251563063e-07,
      "loss": 0.0029,
      "reward": 2.0299062728881836,
      "reward_std": 0.02307567186653614,
      "rewards/accuracy_reward": 0.8299062252044678,
      "rewards/format_reward": 1.0,
      "step": 1495
    },
    {
      "all_correct": 1.0,
      "all_wrong": 0.0,
      "completion_length": 397.59375,
      "epoch": 0.020634198148991048,
      "grad_norm": 2.009689987046221,
      "kl": 0.080078125,
      "learning_rate": 9.989498221353107e-07,
      "loss": 0.0032,
      "reward": 2.165250062942505,
      "reward_std": 0.011667201295495033,
      "rewards/accuracy_reward": 0.9652500152587891,
      "rewards/format_reward": 1.0,
      "step": 1496
    },
    {
      "all_correct": 0.75,
      "all_wrong": 0.0,
      "completion_length": 400.21875,
      "epoch": 0.020647991062192245,
      "grad_norm": 3.7574275713972907,
      "kl": 0.08447265625,
      "learning_rate": 9.989484181774686e-07,
      "loss": 0.0034,
      "reward": 2.0981874465942383,
      "reward_std": 0.03144136816263199,
      "rewards/accuracy_reward": 0.898187518119812,
      "rewards/format_reward": 1.0,
      "step": 1497
    },
    {
      "all_correct": 0.75,
      "all_wrong": 0.0,
      "completion_length": 394.90625,
      "epoch": 0.020661783975393443,
      "grad_norm": 3.0936045961612746,
      "kl": 0.080078125,
      "learning_rate": 9.98947013282782e-07,
      "loss": 0.0032,
      "reward": 2.120594024658203,
      "reward_std": 0.019680829718708992,
      "rewards/accuracy_reward": 0.9205937385559082,
      "rewards/format_reward": 1.0,
      "step": 1498
    },
    {
      "all_correct": 0.75,
      "all_wrong": 0.0,
      "completion_length": 395.3125,
      "epoch": 0.02067557688859464,
      "grad_norm": 2.6038141207174923,
      "kl": 0.0830078125,
      "learning_rate": 9.989456074512537e-07,
      "loss": 0.0033,
      "reward": 2.0644373893737793,
      "reward_std": 0.021542729809880257,
      "rewards/accuracy_reward": 0.8644375205039978,
      "rewards/format_reward": 1.0,
      "step": 1499
    },
    {
      "all_correct": 1.0,
      "all_wrong": 0.0,
      "completion_length": 395.25,
      "epoch": 0.020689369801795837,
      "grad_norm": 2.446497263212654,
      "kl": 0.09130859375,
      "learning_rate": 9.989442006828866e-07,
      "loss": 0.0037,
      "reward": 2.1802499294281006,
      "reward_std": 0.01756836473941803,
      "rewards/accuracy_reward": 0.9802500009536743,
      "rewards/format_reward": 1.0,
      "step": 1500
    },
    {
      "all_correct": 0.75,
      "all_wrong": 0.0,
      "completion_length": 386.6875,
      "epoch": 0.020703162714997034,
      "grad_norm": 2.4412589030156613,
      "kl": 0.0771484375,
      "learning_rate": 9.98942792977683e-07,
      "loss": 0.0031,
      "reward": 2.081312656402588,
      "reward_std": 0.028154775500297546,
      "rewards/accuracy_reward": 0.8813124895095825,
      "rewards/format_reward": 1.0,
      "step": 1501
    },
    {
      "all_correct": 0.25,
      "all_wrong": 0.0,
      "completion_length": 381.875,
      "epoch": 0.02071695562819823,
      "grad_norm": 1.9974109852631787,
      "kl": 0.07763671875,
      "learning_rate": 9.989413843356458e-07,
      "loss": 0.0031,
      "reward": 2.037781238555908,
      "reward_std": 0.0330815352499485,
      "rewards/accuracy_reward": 0.8440312743186951,
      "rewards/format_reward": 1.0,
      "step": 1502
    },
    {
      "all_correct": 0.75,
      "all_wrong": 0.0,
      "completion_length": 398.875,
      "epoch": 0.02073074854139943,
      "grad_norm": 2.819648442168812,
      "kl": 0.0908203125,
      "learning_rate": 9.989399747567774e-07,
      "loss": 0.0036,
      "reward": 2.1148123741149902,
      "reward_std": 0.018034860491752625,
      "rewards/accuracy_reward": 0.9148125052452087,
      "rewards/format_reward": 1.0,
      "step": 1503
    },
    {
      "all_correct": 0.75,
      "all_wrong": 0.0,
      "completion_length": 386.375,
      "epoch": 0.020744541454600626,
      "grad_norm": 17.664696052578673,
      "kl": 0.0771484375,
      "learning_rate": 9.989385642410806e-07,
      "loss": 0.0031,
      "reward": 2.1179685592651367,
      "reward_std": 0.038253627717494965,
      "rewards/accuracy_reward": 0.9242187738418579,
      "rewards/format_reward": 1.0,
      "step": 1504
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.0,
      "completion_length": 386.25,
      "epoch": 0.020758334367801824,
      "grad_norm": 2.413352219735155,
      "kl": 0.080078125,
      "learning_rate": 9.989371527885582e-07,
      "loss": 0.0032,
      "reward": 2.0059375762939453,
      "reward_std": 0.0405728742480278,
      "rewards/accuracy_reward": 0.8059374690055847,
      "rewards/format_reward": 1.0,
      "step": 1505
    },
    {
      "all_correct": 0.25,
      "all_wrong": 0.0,
      "completion_length": 376.375,
      "epoch": 0.02077212728100302,
      "grad_norm": 2.514804664128141,
      "kl": 0.07958984375,
      "learning_rate": 9.989357403992125e-07,
      "loss": 0.0032,
      "reward": 2.021353244781494,
      "reward_std": 0.04269827902317047,
      "rewards/accuracy_reward": 0.8276031017303467,
      "rewards/format_reward": 1.0,
      "step": 1506
    },
    {
      "all_correct": 0.25,
      "all_wrong": 0.0,
      "completion_length": 382.84375,
      "epoch": 0.020785920194204218,
      "grad_norm": 2.4134918426041096,
      "kl": 0.08203125,
      "learning_rate": 9.989343270730466e-07,
      "loss": 0.0033,
      "reward": 1.898343801498413,
      "reward_std": 0.044561997056007385,
      "rewards/accuracy_reward": 0.7108438014984131,
      "rewards/format_reward": 1.0,
      "step": 1507
    },
    {
      "all_correct": 0.75,
      "all_wrong": 0.0,
      "completion_length": 381.28125,
      "epoch": 0.020799713107405415,
      "grad_norm": 2.429433601102753,
      "kl": 0.07568359375,
      "learning_rate": 9.989329128100628e-07,
      "loss": 0.003,
      "reward": 2.0971250534057617,
      "reward_std": 0.030733685940504074,
      "rewards/accuracy_reward": 0.9033750295639038,
      "rewards/format_reward": 1.0,
      "step": 1508
    },
    {
      "all_correct": 0.75,
      "all_wrong": 0.0,
      "completion_length": 401.34375,
      "epoch": 0.020813506020606613,
      "grad_norm": 2.4642712682123737,
      "kl": 0.0810546875,
      "learning_rate": 9.989314976102636e-07,
      "loss": 0.0032,
      "reward": 2.064687490463257,
      "reward_std": 0.021355709061026573,
      "rewards/accuracy_reward": 0.864687442779541,
      "rewards/format_reward": 1.0,
      "step": 1509
    },
    {
      "all_correct": 0.75,
      "all_wrong": 0.0,
      "completion_length": 391.8125,
      "epoch": 0.02082729893380781,
      "grad_norm": 3.723201861583115,
      "kl": 0.0712890625,
      "learning_rate": 9.989300814736522e-07,
      "loss": 0.0028,
      "reward": 2.123906135559082,
      "reward_std": 0.037387050688266754,
      "rewards/accuracy_reward": 0.9301562905311584,
      "rewards/format_reward": 1.0,
      "step": 1510
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.0,
      "completion_length": 396.78125,
      "epoch": 0.020841091847009007,
      "grad_norm": 2.779478770399653,
      "kl": 0.0869140625,
      "learning_rate": 9.989286644002308e-07,
      "loss": 0.0035,
      "reward": 2.054593801498413,
      "reward_std": 0.03944680094718933,
      "rewards/accuracy_reward": 0.8608437180519104,
      "rewards/format_reward": 1.0,
      "step": 1511
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.0,
      "completion_length": 371.03125,
      "epoch": 0.020854884760210204,
      "grad_norm": 3.104423079866213,
      "kl": 0.08251953125,
      "learning_rate": 9.989272463900024e-07,
      "loss": 0.0033,
      "reward": 2.1294689178466797,
      "reward_std": 0.0512034147977829,
      "rewards/accuracy_reward": 0.9419687986373901,
      "rewards/format_reward": 1.0,
      "step": 1512
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.0,
      "completion_length": 395.71875,
      "epoch": 0.0208686776734114,
      "grad_norm": 3.0961399732755903,
      "kl": 0.083984375,
      "learning_rate": 9.989258274429693e-07,
      "loss": 0.0034,
      "reward": 1.995156168937683,
      "reward_std": 0.028719495981931686,
      "rewards/accuracy_reward": 0.7951561808586121,
      "rewards/format_reward": 1.0,
      "step": 1513
    },
    {
      "all_correct": 0.75,
      "all_wrong": 0.0,
      "completion_length": 396.0625,
      "epoch": 0.0208824705866126,
      "grad_norm": 2.6640897284332556,
      "kl": 0.0810546875,
      "learning_rate": 9.989244075591345e-07,
      "loss": 0.0032,
      "reward": 2.100781202316284,
      "reward_std": 0.028524093329906464,
      "rewards/accuracy_reward": 0.9007812738418579,
      "rewards/format_reward": 1.0,
      "step": 1514
    },
    {
      "all_correct": 1.0,
      "all_wrong": 0.0,
      "completion_length": 405.46875,
      "epoch": 0.020896263499813796,
      "grad_norm": 2.3801262206580476,
      "kl": 0.08154296875,
      "learning_rate": 9.989229867385003e-07,
      "loss": 0.0033,
      "reward": 2.1276001930236816,
      "reward_std": 0.020540155470371246,
      "rewards/accuracy_reward": 0.9276003241539001,
      "rewards/format_reward": 1.0,
      "step": 1515
    },
    {
      "all_correct": 0.75,
      "all_wrong": 0.0,
      "completion_length": 399.90625,
      "epoch": 0.020910056413014994,
      "grad_norm": 5.495826883711522,
      "kl": 0.0830078125,
      "learning_rate": 9.989215649810697e-07,
      "loss": 0.0033,
      "reward": 2.0838751792907715,
      "reward_std": 0.03532567620277405,
      "rewards/accuracy_reward": 0.8838750123977661,
      "rewards/format_reward": 1.0,
      "step": 1516
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.0,
      "completion_length": 403.0625,
      "epoch": 0.02092384932621619,
      "grad_norm": 2.9439855102347985,
      "kl": 0.0859375,
      "learning_rate": 9.989201422868455e-07,
      "loss": 0.0034,
      "reward": 2.0687501430511475,
      "reward_std": 0.020984133705496788,
      "rewards/accuracy_reward": 0.8687499165534973,
      "rewards/format_reward": 1.0,
      "step": 1517
    },
    {
      "all_correct": 0.75,
      "all_wrong": 0.0,
      "completion_length": 402.3125,
      "epoch": 0.020937642239417388,
      "grad_norm": 2.8606934434411713,
      "kl": 0.0859375,
      "learning_rate": 9.989187186558299e-07,
      "loss": 0.0034,
      "reward": 2.0810000896453857,
      "reward_std": 0.03569136932492256,
      "rewards/accuracy_reward": 0.8810000419616699,
      "rewards/format_reward": 1.0,
      "step": 1518
    },
    {
      "all_correct": 1.0,
      "all_wrong": 0.0,
      "completion_length": 406.03125,
      "epoch": 0.020951435152618585,
      "grad_norm": 2.8669744553649497,
      "kl": 0.09033203125,
      "learning_rate": 9.98917294088026e-07,
      "loss": 0.0036,
      "reward": 2.1474685668945312,
      "reward_std": 0.0178835391998291,
      "rewards/accuracy_reward": 0.9474687576293945,
      "rewards/format_reward": 1.0,
      "step": 1519
    },
    {
      "all_correct": 0.75,
      "all_wrong": 0.0,
      "completion_length": 416.84375,
      "epoch": 0.020965228065819783,
      "grad_norm": 2.068133609218328,
      "kl": 0.08056640625,
      "learning_rate": 9.98915868583436e-07,
      "loss": 0.0032,
      "reward": 2.1226563453674316,
      "reward_std": 0.031642794609069824,
      "rewards/accuracy_reward": 0.928906261920929,
      "rewards/format_reward": 1.0,
      "step": 1520
    },
    {
      "all_correct": 1.0,
      "all_wrong": 0.0,
      "completion_length": 387.9375,
      "epoch": 0.02097902097902098,
      "grad_norm": 2.226008061728883,
      "kl": 0.08447265625,
      "learning_rate": 9.989144421420628e-07,
      "loss": 0.0034,
      "reward": 2.137218713760376,
      "reward_std": 0.03068123385310173,
      "rewards/accuracy_reward": 0.9372187256813049,
      "rewards/format_reward": 1.0,
      "step": 1521
    },
    {
      "all_correct": 0.75,
      "all_wrong": 0.0,
      "completion_length": 404.09375,
      "epoch": 0.020992813892222177,
      "grad_norm": 2.7235869240468302,
      "kl": 0.09619140625,
      "learning_rate": 9.989130147639092e-07,
      "loss": 0.0038,
      "reward": 2.0676562786102295,
      "reward_std": 0.024769969284534454,
      "rewards/accuracy_reward": 0.8676562309265137,
      "rewards/format_reward": 1.0,
      "step": 1522
    },
    {
      "all_correct": 1.0,
      "all_wrong": 0.0,
      "completion_length": 398.5,
      "epoch": 0.021006606805423374,
      "grad_norm": 3.138919834922565,
      "kl": 0.083984375,
      "learning_rate": 9.98911586448978e-07,
      "loss": 0.0034,
      "reward": 2.1533126831054688,
      "reward_std": 0.019278643652796745,
      "rewards/accuracy_reward": 0.9533125162124634,
      "rewards/format_reward": 1.0,
      "step": 1523
    },
    {
      "all_correct": 0.75,
      "all_wrong": 0.0,
      "completion_length": 407.5625,
      "epoch": 0.02102039971862457,
      "grad_norm": 3.0647395558481585,
      "kl": 0.091796875,
      "learning_rate": 9.989101571972716e-07,
      "loss": 0.0037,
      "reward": 2.104031562805176,
      "reward_std": 0.022861778736114502,
      "rewards/accuracy_reward": 0.9040312767028809,
      "rewards/format_reward": 1.0,
      "step": 1524
    },
    {
      "all_correct": 0.75,
      "all_wrong": 0.0,
      "completion_length": 406.78125,
      "epoch": 0.02103419263182577,
      "grad_norm": 7.746727793069399,
      "kl": 0.09375,
      "learning_rate": 9.989087270087927e-07,
      "loss": 0.0038,
      "reward": 2.1284284591674805,
      "reward_std": 0.05125795304775238,
      "rewards/accuracy_reward": 0.9346784949302673,
      "rewards/format_reward": 1.0,
      "step": 1525
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.0,
      "completion_length": 415.09375,
      "epoch": 0.021047985545026966,
      "grad_norm": 3.1206768926172566,
      "kl": 0.083984375,
      "learning_rate": 9.989072958835443e-07,
      "loss": 0.0034,
      "reward": 2.05078125,
      "reward_std": 0.026583846658468246,
      "rewards/accuracy_reward": 0.8507813215255737,
      "rewards/format_reward": 1.0,
      "step": 1526
    },
    {
      "all_correct": 0.75,
      "all_wrong": 0.0,
      "completion_length": 406.125,
      "epoch": 0.021061778458228163,
      "grad_norm": 1.9482717232649231,
      "kl": 0.08251953125,
      "learning_rate": 9.989058638215286e-07,
      "loss": 0.0033,
      "reward": 2.0946874618530273,
      "reward_std": 0.02435433492064476,
      "rewards/accuracy_reward": 0.8946874141693115,
      "rewards/format_reward": 1.0,
      "step": 1527
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.0,
      "completion_length": 392.9375,
      "epoch": 0.02107557137142936,
      "grad_norm": 1.8887445866403607,
      "kl": 0.09033203125,
      "learning_rate": 9.989044308227488e-07,
      "loss": 0.0036,
      "reward": 2.0756876468658447,
      "reward_std": 0.023495055735111237,
      "rewards/accuracy_reward": 0.8756874799728394,
      "rewards/format_reward": 1.0,
      "step": 1528
    },
    {
      "all_correct": 0.75,
      "all_wrong": 0.0,
      "completion_length": 415.90625,
      "epoch": 0.021089364284630558,
      "grad_norm": 2.2610234204933506,
      "kl": 0.08203125,
      "learning_rate": 9.989029968872072e-07,
      "loss": 0.0033,
      "reward": 2.085343599319458,
      "reward_std": 0.036933641880750656,
      "rewards/accuracy_reward": 0.8915936946868896,
      "rewards/format_reward": 1.0,
      "step": 1529
    },
    {
      "all_correct": 0.75,
      "all_wrong": 0.0,
      "completion_length": 414.34375,
      "epoch": 0.021103157197831755,
      "grad_norm": 2.8545865759476317,
      "kl": 0.0869140625,
      "learning_rate": 9.989015620149063e-07,
      "loss": 0.0035,
      "reward": 2.0868594646453857,
      "reward_std": 0.024989519268274307,
      "rewards/accuracy_reward": 0.8868594169616699,
      "rewards/format_reward": 1.0,
      "step": 1530
    },
    {
      "all_correct": 1.0,
      "all_wrong": 0.0,
      "completion_length": 407.8125,
      "epoch": 0.021116950111032953,
      "grad_norm": 2.1157264923864005,
      "kl": 0.09375,
      "learning_rate": 9.989001262058495e-07,
      "loss": 0.0037,
      "reward": 2.1402812004089355,
      "reward_std": 0.012138539925217628,
      "rewards/accuracy_reward": 0.9402812719345093,
      "rewards/format_reward": 1.0,
      "step": 1531
    },
    {
      "all_correct": 1.0,
      "all_wrong": 0.0,
      "completion_length": 412.59375,
      "epoch": 0.02113074302423415,
      "grad_norm": 2.017778594316767,
      "kl": 0.0869140625,
      "learning_rate": 9.988986894600391e-07,
      "loss": 0.0035,
      "reward": 2.113093852996826,
      "reward_std": 0.01661318726837635,
      "rewards/accuracy_reward": 0.9130936861038208,
      "rewards/format_reward": 1.0,
      "step": 1532
    },
    {
      "all_correct": 0.75,
      "all_wrong": 0.0,
      "completion_length": 416.28125,
      "epoch": 0.021144535937435347,
      "grad_norm": 5.056252296759649,
      "kl": 0.087890625,
      "learning_rate": 9.988972517774777e-07,
      "loss": 0.0035,
      "reward": 2.0796875953674316,
      "reward_std": 0.023273160681128502,
      "rewards/accuracy_reward": 0.879687488079071,
      "rewards/format_reward": 1.0,
      "step": 1533
    },
    {
      "all_correct": 1.0,
      "all_wrong": 0.0,
      "completion_length": 410.03125,
      "epoch": 0.021158328850636544,
      "grad_norm": 2.817885965012272,
      "kl": 0.0869140625,
      "learning_rate": 9.98895813158168e-07,
      "loss": 0.0035,
      "reward": 2.162374973297119,
      "reward_std": 0.01492896769195795,
      "rewards/accuracy_reward": 0.9623750448226929,
      "rewards/format_reward": 1.0,
      "step": 1534
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.0,
      "completion_length": 409.9375,
      "epoch": 0.02117212176383774,
      "grad_norm": 2.6637289325898323,
      "kl": 0.08740234375,
      "learning_rate": 9.988943736021128e-07,
      "loss": 0.0035,
      "reward": 1.9640939235687256,
      "reward_std": 0.020299989730119705,
      "rewards/accuracy_reward": 0.764093816280365,
      "rewards/format_reward": 1.0,
      "step": 1535
    },
    {
      "all_correct": 1.0,
      "all_wrong": 0.0,
      "completion_length": 402.21875,
      "epoch": 0.02118591467703894,
      "grad_norm": 2.21331201887261,
      "kl": 0.08642578125,
      "learning_rate": 9.98892933109315e-07,
      "loss": 0.0035,
      "reward": 2.1415627002716064,
      "reward_std": 0.015297467820346355,
      "rewards/accuracy_reward": 0.9415625333786011,
      "rewards/format_reward": 1.0,
      "step": 1536
    },
    {
      "all_correct": 1.0,
      "all_wrong": 0.0,
      "completion_length": 416.09375,
      "epoch": 0.021199707590240136,
      "grad_norm": 2.1446447253991785,
      "kl": 0.0810546875,
      "learning_rate": 9.988914916797772e-07,
      "loss": 0.0032,
      "reward": 2.1563124656677246,
      "reward_std": 0.016780951991677284,
      "rewards/accuracy_reward": 0.9563124775886536,
      "rewards/format_reward": 1.0,
      "step": 1537
    },
    {
      "all_correct": 0.75,
      "all_wrong": 0.0,
      "completion_length": 393.5,
      "epoch": 0.021213500503441333,
      "grad_norm": 2.17152487773185,
      "kl": 0.080078125,
      "learning_rate": 9.988900493135018e-07,
      "loss": 0.0032,
      "reward": 2.1330623626708984,
      "reward_std": 0.014645039103925228,
      "rewards/accuracy_reward": 0.9330624938011169,
      "rewards/format_reward": 1.0,
      "step": 1538
    },
    {
      "all_correct": 1.0,
      "all_wrong": 0.0,
      "completion_length": 406.25,
      "epoch": 0.02122729341664253,
      "grad_norm": 2.53137971321452,
      "kl": 0.08544921875,
      "learning_rate": 9.988886060104918e-07,
      "loss": 0.0034,
      "reward": 2.1524999141693115,
      "reward_std": 0.016380976885557175,
      "rewards/accuracy_reward": 0.9524999856948853,
      "rewards/format_reward": 1.0,
      "step": 1539
    },
    {
      "all_correct": 1.0,
      "all_wrong": 0.0,
      "completion_length": 413.4375,
      "epoch": 0.021241086329843728,
      "grad_norm": 3.2972521540024307,
      "kl": 0.0849609375,
      "learning_rate": 9.9888716177075e-07,
      "loss": 0.0034,
      "reward": 2.0991876125335693,
      "reward_std": 0.02933315560221672,
      "rewards/accuracy_reward": 0.899187445640564,
      "rewards/format_reward": 1.0,
      "step": 1540
    },
    {
      "all_correct": 1.0,
      "all_wrong": 0.0,
      "completion_length": 405.5,
      "epoch": 0.021254879243044922,
      "grad_norm": 2.972382706822661,
      "kl": 0.0888671875,
      "learning_rate": 9.988857165942787e-07,
      "loss": 0.0036,
      "reward": 2.091531276702881,
      "reward_std": 0.022795991972088814,
      "rewards/accuracy_reward": 0.891531229019165,
      "rewards/format_reward": 1.0,
      "step": 1541
    },
    {
      "all_correct": 1.0,
      "all_wrong": 0.0,
      "completion_length": 413.28125,
      "epoch": 0.02126867215624612,
      "grad_norm": 6.029279464258887,
      "kl": 0.09326171875,
      "learning_rate": 9.98884270481081e-07,
      "loss": 0.0037,
      "reward": 2.1213126182556152,
      "reward_std": 0.021050382405519485,
      "rewards/accuracy_reward": 0.9213125109672546,
      "rewards/format_reward": 1.0,
      "step": 1542
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.0,
      "completion_length": 413.71875,
      "epoch": 0.021282465069447316,
      "grad_norm": 4.856696953148061,
      "kl": 0.08203125,
      "learning_rate": 9.988828234311594e-07,
      "loss": 0.0033,
      "reward": 2.066850423812866,
      "reward_std": 0.024274926632642746,
      "rewards/accuracy_reward": 0.8668503165245056,
      "rewards/format_reward": 1.0,
      "step": 1543
    },
    {
      "all_correct": 1.0,
      "all_wrong": 0.0,
      "completion_length": 399.125,
      "epoch": 0.021296257982648514,
      "grad_norm": 2.227717914949612,
      "kl": 0.083984375,
      "learning_rate": 9.98881375444517e-07,
      "loss": 0.0034,
      "reward": 2.162781238555908,
      "reward_std": 0.010355159640312195,
      "rewards/accuracy_reward": 0.9627813100814819,
      "rewards/format_reward": 1.0,
      "step": 1544
    },
    {
      "all_correct": 0.75,
      "all_wrong": 0.0,
      "completion_length": 388.125,
      "epoch": 0.02131005089584971,
      "grad_norm": 3.5728001949392896,
      "kl": 0.07861328125,
      "learning_rate": 9.988799265211558e-07,
      "loss": 0.0031,
      "reward": 2.086062431335449,
      "reward_std": 0.027896970510482788,
      "rewards/accuracy_reward": 0.8860624432563782,
      "rewards/format_reward": 1.0,
      "step": 1545
    },
    {
      "all_correct": 0.75,
      "all_wrong": 0.0,
      "completion_length": 395.1875,
      "epoch": 0.021323843809050908,
      "grad_norm": 2.10505269153072,
      "kl": 0.076171875,
      "learning_rate": 9.98878476661079e-07,
      "loss": 0.003,
      "reward": 2.0056562423706055,
      "reward_std": 0.01300123892724514,
      "rewards/accuracy_reward": 0.8056562542915344,
      "rewards/format_reward": 1.0,
      "step": 1546
    },
    {
      "all_correct": 0.75,
      "all_wrong": 0.0,
      "completion_length": 415.4375,
      "epoch": 0.021337636722252105,
      "grad_norm": 3.313191567121275,
      "kl": 0.08056640625,
      "learning_rate": 9.988770258642896e-07,
      "loss": 0.0032,
      "reward": 2.024656295776367,
      "reward_std": 0.02149621583521366,
      "rewards/accuracy_reward": 0.8246562480926514,
      "rewards/format_reward": 1.0,
      "step": 1547
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.0,
      "completion_length": 399.25,
      "epoch": 0.021351429635453303,
      "grad_norm": 2.7253332346190526,
      "kl": 0.0810546875,
      "learning_rate": 9.988755741307897e-07,
      "loss": 0.0032,
      "reward": 2.019312620162964,
      "reward_std": 0.02338443323969841,
      "rewards/accuracy_reward": 0.8193125128746033,
      "rewards/format_reward": 1.0,
      "step": 1548
    },
    {
      "all_correct": 1.0,
      "all_wrong": 0.0,
      "completion_length": 415.75,
      "epoch": 0.0213652225486545,
      "grad_norm": 2.2993868047678974,
      "kl": 0.07763671875,
      "learning_rate": 9.988741214605823e-07,
      "loss": 0.0031,
      "reward": 2.093874931335449,
      "reward_std": 0.013927859254181385,
      "rewards/accuracy_reward": 0.893875002861023,
      "rewards/format_reward": 1.0,
      "step": 1549
    },
    {
      "all_correct": 1.0,
      "all_wrong": 0.0,
      "completion_length": 420.78125,
      "epoch": 0.021379015461855697,
      "grad_norm": 3.218688257551977,
      "kl": 0.08447265625,
      "learning_rate": 9.988726678536702e-07,
      "loss": 0.0034,
      "reward": 2.112874984741211,
      "reward_std": 0.033188559114933014,
      "rewards/accuracy_reward": 0.9128749966621399,
      "rewards/format_reward": 1.0,
      "step": 1550
    },
    {
      "all_correct": 0.25,
      "all_wrong": 0.0,
      "completion_length": 413.28125,
      "epoch": 0.021392808375056895,
      "grad_norm": 5.225160932145518,
      "kl": 0.080078125,
      "learning_rate": 9.988712133100561e-07,
      "loss": 0.0032,
      "reward": 2.025177001953125,
      "reward_std": 0.04278388246893883,
      "rewards/accuracy_reward": 0.8251770734786987,
      "rewards/format_reward": 1.0,
      "step": 1551
    },
    {
      "all_correct": 0.25,
      "all_wrong": 0.0,
      "completion_length": 408.03125,
      "epoch": 0.021406601288258092,
      "grad_norm": 7.388750952996294,
      "kl": 0.078125,
      "learning_rate": 9.988697578297426e-07,
      "loss": 0.0031,
      "reward": 1.8918238878250122,
      "reward_std": 0.07013053447008133,
      "rewards/accuracy_reward": 0.6918237805366516,
      "rewards/format_reward": 1.0,
      "step": 1552
    },
    {
      "all_correct": 0.75,
      "all_wrong": 0.0,
      "completion_length": 421.9375,
      "epoch": 0.02142039420145929,
      "grad_norm": 2.0482494336792745,
      "kl": 0.08203125,
      "learning_rate": 9.988683014127327e-07,
      "loss": 0.0033,
      "reward": 2.0768749713897705,
      "reward_std": 0.012193598784506321,
      "rewards/accuracy_reward": 0.8768750429153442,
      "rewards/format_reward": 1.0,
      "step": 1553
    },
    {
      "all_correct": 0.25,
      "all_wrong": 0.0,
      "completion_length": 414.53125,
      "epoch": 0.021434187114660486,
      "grad_norm": 1.9585988460520216,
      "kl": 0.0712890625,
      "learning_rate": 9.98866844059029e-07,
      "loss": 0.0029,
      "reward": 2.1084063053131104,
      "reward_std": 0.0719788521528244,
      "rewards/accuracy_reward": 0.9146562218666077,
      "rewards/format_reward": 1.0,
      "step": 1554
    },
    {
      "all_correct": 1.0,
      "all_wrong": 0.0,
      "completion_length": 421.59375,
      "epoch": 0.021447980027861684,
      "grad_norm": 2.3520659607253167,
      "kl": 0.0751953125,
      "learning_rate": 9.988653857686339e-07,
      "loss": 0.003,
      "reward": 2.144406318664551,
      "reward_std": 0.014882270246744156,
      "rewards/accuracy_reward": 0.944406270980835,
      "rewards/format_reward": 1.0,
      "step": 1555
    },
    {
      "all_correct": 0.75,
      "all_wrong": 0.0,
      "completion_length": 426.75,
      "epoch": 0.02146177294106288,
      "grad_norm": 2.06146643698252,
      "kl": 0.08251953125,
      "learning_rate": 9.988639265415508e-07,
      "loss": 0.0033,
      "reward": 2.0045623779296875,
      "reward_std": 0.014828743413090706,
      "rewards/accuracy_reward": 0.8045624494552612,
      "rewards/format_reward": 1.0,
      "step": 1556
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.0,
      "completion_length": 424.375,
      "epoch": 0.021475565854264078,
      "grad_norm": 2.8216345989635174,
      "kl": 0.076171875,
      "learning_rate": 9.988624663777819e-07,
      "loss": 0.003,
      "reward": 2.0919063091278076,
      "reward_std": 0.047057442367076874,
      "rewards/accuracy_reward": 0.8919062614440918,
      "rewards/format_reward": 1.0,
      "step": 1557
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.0,
      "completion_length": 433.15625,
      "epoch": 0.021489358767465275,
      "grad_norm": 4.570568080456706,
      "kl": 0.07958984375,
      "learning_rate": 9.9886100527733e-07,
      "loss": 0.0032,
      "reward": 2.027937412261963,
      "reward_std": 0.020956214517354965,
      "rewards/accuracy_reward": 0.8279374837875366,
      "rewards/format_reward": 1.0,
      "step": 1558
    },
    {
      "all_correct": 1.0,
      "all_wrong": 0.0,
      "completion_length": 412.4375,
      "epoch": 0.021503151680666473,
      "grad_norm": 2.8117561792439165,
      "kl": 0.0810546875,
      "learning_rate": 9.988595432401982e-07,
      "loss": 0.0032,
      "reward": 2.113687515258789,
      "reward_std": 0.027239935472607613,
      "rewards/accuracy_reward": 0.9136874675750732,
      "rewards/format_reward": 1.0,
      "step": 1559
    },
    {
      "all_correct": 0.75,
      "all_wrong": 0.0,
      "completion_length": 420.1875,
      "epoch": 0.02151694459386767,
      "grad_norm": 4.251963555947831,
      "kl": 0.07470703125,
      "learning_rate": 9.988580802663887e-07,
      "loss": 0.003,
      "reward": 2.114562511444092,
      "reward_std": 0.036585815250873566,
      "rewards/accuracy_reward": 0.9208124876022339,
      "rewards/format_reward": 1.0,
      "step": 1560
    },
    {
      "all_correct": 0.75,
      "all_wrong": 0.0,
      "completion_length": 428.6875,
      "epoch": 0.021530737507068867,
      "grad_norm": 2.5219995177527545,
      "kl": 0.078125,
      "learning_rate": 9.988566163559049e-07,
      "loss": 0.0031,
      "reward": 2.0700626373291016,
      "reward_std": 0.02543047070503235,
      "rewards/accuracy_reward": 0.8700624704360962,
      "rewards/format_reward": 1.0,
      "step": 1561
    },
    {
      "all_correct": 0.75,
      "all_wrong": 0.0,
      "completion_length": 412.90625,
      "epoch": 0.021544530420270065,
      "grad_norm": 5.526570331675459,
      "kl": 0.08154296875,
      "learning_rate": 9.98855151508749e-07,
      "loss": 0.0033,
      "reward": 2.047656297683716,
      "reward_std": 0.028637949377298355,
      "rewards/accuracy_reward": 0.84765625,
      "rewards/format_reward": 1.0,
      "step": 1562
    },
    {
      "all_correct": 0.75,
      "all_wrong": 0.0,
      "completion_length": 418.4375,
      "epoch": 0.021558323333471262,
      "grad_norm": 3.0031201897300126,
      "kl": 0.07470703125,
      "learning_rate": 9.988536857249241e-07,
      "loss": 0.003,
      "reward": 2.0929062366485596,
      "reward_std": 0.03276754170656204,
      "rewards/accuracy_reward": 0.8991562128067017,
      "rewards/format_reward": 1.0,
      "step": 1563
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.0,
      "completion_length": 411.84375,
      "epoch": 0.02157211624667246,
      "grad_norm": 1.983178904618438,
      "kl": 0.0859375,
      "learning_rate": 9.988522190044328e-07,
      "loss": 0.0034,
      "reward": 1.9270312786102295,
      "reward_std": 0.009660182520747185,
      "rewards/accuracy_reward": 0.7270312309265137,
      "rewards/format_reward": 1.0,
      "step": 1564
    },
    {
      "all_correct": 1.0,
      "all_wrong": 0.0,
      "completion_length": 404.09375,
      "epoch": 0.021585909159873656,
      "grad_norm": 2.5858870856831278,
      "kl": 0.080078125,
      "learning_rate": 9.988507513472776e-07,
      "loss": 0.0032,
      "reward": 2.140899658203125,
      "reward_std": 0.012261909432709217,
      "rewards/accuracy_reward": 0.940899670124054,
      "rewards/format_reward": 1.0,
      "step": 1565
    },
    {
      "all_correct": 1.0,
      "all_wrong": 0.0,
      "completion_length": 410.0625,
      "epoch": 0.021599702073074854,
      "grad_norm": 2.906625090866049,
      "kl": 0.0810546875,
      "learning_rate": 9.988492827534618e-07,
      "loss": 0.0033,
      "reward": 2.147156238555908,
      "reward_std": 0.014906302094459534,
      "rewards/accuracy_reward": 0.9471562504768372,
      "rewards/format_reward": 1.0,
      "step": 1566
    },
    {
      "all_correct": 0.75,
      "all_wrong": 0.0,
      "completion_length": 408.8125,
      "epoch": 0.02161349498627605,
      "grad_norm": 2.5150170362313267,
      "kl": 0.07861328125,
      "learning_rate": 9.988478132229878e-07,
      "loss": 0.0031,
      "reward": 2.144124984741211,
      "reward_std": 0.03592435270547867,
      "rewards/accuracy_reward": 0.950374960899353,
      "rewards/format_reward": 1.0,
      "step": 1567
    },
    {
      "all_correct": 0.75,
      "all_wrong": 0.0,
      "completion_length": 413.34375,
      "epoch": 0.021627287899477248,
      "grad_norm": 3.3654542970723167,
      "kl": 0.07421875,
      "learning_rate": 9.988463427558584e-07,
      "loss": 0.003,
      "reward": 2.060187339782715,
      "reward_std": 0.024146951735019684,
      "rewards/accuracy_reward": 0.8601875305175781,
      "rewards/format_reward": 1.0,
      "step": 1568
    },
    {
      "all_correct": 1.0,
      "all_wrong": 0.0,
      "completion_length": 391.71875,
      "epoch": 0.021641080812678445,
      "grad_norm": 3.6140742161554145,
      "kl": 0.07666015625,
      "learning_rate": 9.988448713520766e-07,
      "loss": 0.0031,
      "reward": 2.1519999504089355,
      "reward_std": 0.014973675832152367,
      "rewards/accuracy_reward": 0.9519999623298645,
      "rewards/format_reward": 1.0,
      "step": 1569
    },
    {
      "all_correct": 0.75,
      "all_wrong": 0.0,
      "completion_length": 391.90625,
      "epoch": 0.021654873725879643,
      "grad_norm": 2.930493235792114,
      "kl": 0.080078125,
      "learning_rate": 9.988433990116446e-07,
      "loss": 0.0032,
      "reward": 2.0972187519073486,
      "reward_std": 0.01555462833493948,
      "rewards/accuracy_reward": 0.8972187638282776,
      "rewards/format_reward": 1.0,
      "step": 1570
    },
    {
      "all_correct": 0.75,
      "all_wrong": 0.0,
      "completion_length": 388.90625,
      "epoch": 0.02166866663908084,
      "grad_norm": 3.499323046108649,
      "kl": 0.078125,
      "learning_rate": 9.98841925734566e-07,
      "loss": 0.0031,
      "reward": 2.034343719482422,
      "reward_std": 0.023150470107793808,
      "rewards/accuracy_reward": 0.8405937552452087,
      "rewards/format_reward": 1.0,
      "step": 1571
    },
    {
      "all_correct": 0.75,
      "all_wrong": 0.0,
      "completion_length": 395.75,
      "epoch": 0.021682459552282037,
      "grad_norm": 2.2536647657995457,
      "kl": 0.0751953125,
      "learning_rate": 9.988404515208426e-07,
      "loss": 0.003,
      "reward": 2.067218780517578,
      "reward_std": 0.012301644310355186,
      "rewards/accuracy_reward": 0.8672187328338623,
      "rewards/format_reward": 1.0,
      "step": 1572
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.0,
      "completion_length": 394.34375,
      "epoch": 0.021696252465483234,
      "grad_norm": 2.362339253643306,
      "kl": 0.078125,
      "learning_rate": 9.988389763704778e-07,
      "loss": 0.0031,
      "reward": 2.066531181335449,
      "reward_std": 0.016664590686559677,
      "rewards/accuracy_reward": 0.8665311932563782,
      "rewards/format_reward": 1.0,
      "step": 1573
    },
    {
      "all_correct": 1.0,
      "all_wrong": 0.0,
      "completion_length": 387.0,
      "epoch": 0.021710045378684432,
      "grad_norm": 17.325235804524315,
      "kl": 0.07958984375,
      "learning_rate": 9.988375002834743e-07,
      "loss": 0.0032,
      "reward": 2.134531259536743,
      "reward_std": 0.01741349697113037,
      "rewards/accuracy_reward": 0.9345313310623169,
      "rewards/format_reward": 1.0,
      "step": 1574
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.0,
      "completion_length": 399.125,
      "epoch": 0.02172383829188563,
      "grad_norm": 2.196936629027982,
      "kl": 0.08251953125,
      "learning_rate": 9.98836023259835e-07,
      "loss": 0.0033,
      "reward": 1.9609061479568481,
      "reward_std": 0.029735153540968895,
      "rewards/accuracy_reward": 0.7671563029289246,
      "rewards/format_reward": 1.0,
      "step": 1575
    },
    {
      "all_correct": 1.0,
      "all_wrong": 0.0,
      "completion_length": 397.96875,
      "epoch": 0.021737631205086826,
      "grad_norm": 3.9764373039242655,
      "kl": 0.08251953125,
      "learning_rate": 9.988345452995622e-07,
      "loss": 0.0033,
      "reward": 2.1524062156677246,
      "reward_std": 0.015514640137553215,
      "rewards/accuracy_reward": 0.9524062871932983,
      "rewards/format_reward": 1.0,
      "step": 1576
    },
    {
      "all_correct": 0.75,
      "all_wrong": 0.0,
      "completion_length": 405.3125,
      "epoch": 0.021751424118288024,
      "grad_norm": 5.140630134968848,
      "kl": 0.08837890625,
      "learning_rate": 9.988330664026589e-07,
      "loss": 0.0035,
      "reward": 2.1183438301086426,
      "reward_std": 0.024402325972914696,
      "rewards/accuracy_reward": 0.9183437824249268,
      "rewards/format_reward": 1.0,
      "step": 1577
    },
    {
      "all_correct": 1.0,
      "all_wrong": 0.0,
      "completion_length": 392.40625,
      "epoch": 0.02176521703148922,
      "grad_norm": 3.699035372462222,
      "kl": 0.0771484375,
      "learning_rate": 9.98831586569128e-07,
      "loss": 0.0031,
      "reward": 2.1333439350128174,
      "reward_std": 0.018361661583185196,
      "rewards/accuracy_reward": 0.933343768119812,
      "rewards/format_reward": 1.0,
      "step": 1578
    },
    {
      "all_correct": 1.0,
      "all_wrong": 0.0,
      "completion_length": 391.59375,
      "epoch": 0.021779009944690418,
      "grad_norm": 2.6309835563391295,
      "kl": 0.0869140625,
      "learning_rate": 9.988301057989724e-07,
      "loss": 0.0035,
      "reward": 2.1221251487731934,
      "reward_std": 0.021491248160600662,
      "rewards/accuracy_reward": 0.922124981880188,
      "rewards/format_reward": 1.0,
      "step": 1579
    },
    {
      "all_correct": 1.0,
      "all_wrong": 0.0,
      "completion_length": 398.90625,
      "epoch": 0.021792802857891615,
      "grad_norm": 2.161715625365343,
      "kl": 0.0693359375,
      "learning_rate": 9.988286240921946e-07,
      "loss": 0.0028,
      "reward": 2.1294686794281006,
      "reward_std": 0.012171508744359016,
      "rewards/accuracy_reward": 0.9294688105583191,
      "rewards/format_reward": 1.0,
      "step": 1580
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.0,
      "completion_length": 387.8125,
      "epoch": 0.021806595771092813,
      "grad_norm": 2.5330929905394544,
      "kl": 0.0703125,
      "learning_rate": 9.988271414487974e-07,
      "loss": 0.0028,
      "reward": 2.0659375190734863,
      "reward_std": 0.015786802396178246,
      "rewards/accuracy_reward": 0.8659375309944153,
      "rewards/format_reward": 1.0,
      "step": 1581
    },
    {
      "all_correct": 0.75,
      "all_wrong": 0.0,
      "completion_length": 380.5625,
      "epoch": 0.02182038868429401,
      "grad_norm": 5.226057624433558,
      "kl": 0.072265625,
      "learning_rate": 9.988256578687836e-07,
      "loss": 0.0029,
      "reward": 2.094562530517578,
      "reward_std": 0.01329224556684494,
      "rewards/accuracy_reward": 0.8945624828338623,
      "rewards/format_reward": 1.0,
      "step": 1582
    },
    {
      "all_correct": 0.75,
      "all_wrong": 0.0,
      "completion_length": 394.28125,
      "epoch": 0.021834181597495207,
      "grad_norm": 2.0700563854025273,
      "kl": 0.07275390625,
      "learning_rate": 9.98824173352156e-07,
      "loss": 0.0029,
      "reward": 2.0830626487731934,
      "reward_std": 0.014956730417907238,
      "rewards/accuracy_reward": 0.883062481880188,
      "rewards/format_reward": 1.0,
      "step": 1583
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.0,
      "completion_length": 415.15625,
      "epoch": 0.021847974510696404,
      "grad_norm": 1.7649587756278515,
      "kl": 0.076171875,
      "learning_rate": 9.988226878989176e-07,
      "loss": 0.003,
      "reward": 2.0845937728881836,
      "reward_std": 0.021020015701651573,
      "rewards/accuracy_reward": 0.8908436298370361,
      "rewards/format_reward": 1.0,
      "step": 1584
    },
    {
      "all_correct": 0.75,
      "all_wrong": 0.0,
      "completion_length": 374.75,
      "epoch": 0.021861767423897602,
      "grad_norm": 1.5217863214531302,
      "kl": 0.07666015625,
      "learning_rate": 9.988212015090708e-07,
      "loss": 0.0031,
      "reward": 2.0310001373291016,
      "reward_std": 0.00146384141407907,
      "rewards/accuracy_reward": 0.831000030040741,
      "rewards/format_reward": 1.0,
      "step": 1585
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.0,
      "completion_length": 387.46875,
      "epoch": 0.0218755603370988,
      "grad_norm": 8.103618418543745,
      "kl": 0.0703125,
      "learning_rate": 9.988197141826188e-07,
      "loss": 0.0028,
      "reward": 2.0257811546325684,
      "reward_std": 0.025264011695981026,
      "rewards/accuracy_reward": 0.8257813453674316,
      "rewards/format_reward": 1.0,
      "step": 1586
    },
    {
      "all_correct": 0.75,
      "all_wrong": 0.0,
      "completion_length": 374.0,
      "epoch": 0.021889353250299996,
      "grad_norm": 2.332754055152769,
      "kl": 0.078125,
      "learning_rate": 9.988182259195642e-07,
      "loss": 0.0031,
      "reward": 2.0961251258850098,
      "reward_std": 0.03362717479467392,
      "rewards/accuracy_reward": 0.9086250066757202,
      "rewards/format_reward": 1.0,
      "step": 1587
    },
    {
      "all_correct": 0.75,
      "all_wrong": 0.0,
      "completion_length": 388.65625,
      "epoch": 0.021903146163501194,
      "grad_norm": 2.6874105036521465,
      "kl": 0.07421875,
      "learning_rate": 9.988167367199096e-07,
      "loss": 0.003,
      "reward": 2.0760626792907715,
      "reward_std": 0.025703947991132736,
      "rewards/accuracy_reward": 0.8760625123977661,
      "rewards/format_reward": 1.0,
      "step": 1588
    },
    {
      "all_correct": 1.0,
      "all_wrong": 0.0,
      "completion_length": 389.5625,
      "epoch": 0.02191693907670239,
      "grad_norm": 2.218049496575101,
      "kl": 0.0771484375,
      "learning_rate": 9.988152465836581e-07,
      "loss": 0.0031,
      "reward": 2.1312499046325684,
      "reward_std": 0.016386108472943306,
      "rewards/accuracy_reward": 0.9312500357627869,
      "rewards/format_reward": 1.0,
      "step": 1589
    },
    {
      "all_correct": 0.75,
      "all_wrong": 0.0,
      "completion_length": 376.5,
      "epoch": 0.021930731989903588,
      "grad_norm": 3.282572888837597,
      "kl": 0.0751953125,
      "learning_rate": 9.988137555108124e-07,
      "loss": 0.003,
      "reward": 2.1472811698913574,
      "reward_std": 0.03093050792813301,
      "rewards/accuracy_reward": 0.9535312056541443,
      "rewards/format_reward": 1.0,
      "step": 1590
    },
    {
      "all_correct": 0.75,
      "all_wrong": 0.0,
      "completion_length": 396.9375,
      "epoch": 0.021944524903104785,
      "grad_norm": 3.647449859136758,
      "kl": 0.07421875,
      "learning_rate": 9.988122635013753e-07,
      "loss": 0.003,
      "reward": 2.021718978881836,
      "reward_std": 0.03832070156931877,
      "rewards/accuracy_reward": 0.8279687762260437,
      "rewards/format_reward": 1.0,
      "step": 1591
    },
    {
      "all_correct": 0.25,
      "all_wrong": 0.0,
      "completion_length": 391.5,
      "epoch": 0.021958317816305983,
      "grad_norm": 3.4390033611755206,
      "kl": 0.07373046875,
      "learning_rate": 9.988107705553495e-07,
      "loss": 0.0029,
      "reward": 1.9759063720703125,
      "reward_std": 0.027544600889086723,
      "rewards/accuracy_reward": 0.7759063243865967,
      "rewards/format_reward": 1.0,
      "step": 1592
    },
    {
      "all_correct": 1.0,
      "all_wrong": 0.0,
      "completion_length": 397.125,
      "epoch": 0.02197211072950718,
      "grad_norm": 2.5797418416835933,
      "kl": 0.07373046875,
      "learning_rate": 9.98809276672738e-07,
      "loss": 0.003,
      "reward": 2.110781192779541,
      "reward_std": 0.018572986125946045,
      "rewards/accuracy_reward": 0.9107812643051147,
      "rewards/format_reward": 1.0,
      "step": 1593
    },
    {
      "all_correct": 0.25,
      "all_wrong": 0.0,
      "completion_length": 413.8125,
      "epoch": 0.021985903642708377,
      "grad_norm": 2.1827013296789115,
      "kl": 0.08056640625,
      "learning_rate": 9.988077818535435e-07,
      "loss": 0.0032,
      "reward": 2.045562505722046,
      "reward_std": 0.031129637733101845,
      "rewards/accuracy_reward": 0.851812481880188,
      "rewards/format_reward": 1.0,
      "step": 1594
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.0,
      "completion_length": 404.15625,
      "epoch": 0.021999696555909574,
      "grad_norm": 2.766342776421939,
      "kl": 0.07861328125,
      "learning_rate": 9.988062860977686e-07,
      "loss": 0.0031,
      "reward": 2.0461249351501465,
      "reward_std": 0.011592695489525795,
      "rewards/accuracy_reward": 0.8461249470710754,
      "rewards/format_reward": 1.0,
      "step": 1595
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.0,
      "completion_length": 407.53125,
      "epoch": 0.02201348946911077,
      "grad_norm": 4.1656036893810775,
      "kl": 0.0712890625,
      "learning_rate": 9.988047894054164e-07,
      "loss": 0.0028,
      "reward": 2.0014686584472656,
      "reward_std": 0.006300115957856178,
      "rewards/accuracy_reward": 0.8014687299728394,
      "rewards/format_reward": 1.0,
      "step": 1596
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.0,
      "completion_length": 394.21875,
      "epoch": 0.02202728238231197,
      "grad_norm": 1.9583783115355127,
      "kl": 0.08154296875,
      "learning_rate": 9.988032917764898e-07,
      "loss": 0.0033,
      "reward": 1.9821875095367432,
      "reward_std": 0.012056650593876839,
      "rewards/accuracy_reward": 0.7821875214576721,
      "rewards/format_reward": 1.0,
      "step": 1597
    },
    {
      "all_correct": 0.75,
      "all_wrong": 0.0,
      "completion_length": 407.25,
      "epoch": 0.022041075295513166,
      "grad_norm": 3.5399851121544472,
      "kl": 0.07763671875,
      "learning_rate": 9.988017932109912e-07,
      "loss": 0.0031,
      "reward": 2.054874897003174,
      "reward_std": 0.020652741193771362,
      "rewards/accuracy_reward": 0.8548749685287476,
      "rewards/format_reward": 1.0,
      "step": 1598
    },
    {
      "all_correct": 0.75,
      "all_wrong": 0.0,
      "completion_length": 394.03125,
      "epoch": 0.022054868208714364,
      "grad_norm": 4.678225616923067,
      "kl": 0.08544921875,
      "learning_rate": 9.988002937089238e-07,
      "loss": 0.0034,
      "reward": 2.0822813510894775,
      "reward_std": 0.015072397887706757,
      "rewards/accuracy_reward": 0.8822813034057617,
      "rewards/format_reward": 1.0,
      "step": 1599
    },
    {
      "all_correct": 0.75,
      "all_wrong": 0.0,
      "completion_length": 392.71875,
      "epoch": 0.02206866112191556,
      "grad_norm": 2.5234663984438237,
      "kl": 0.07421875,
      "learning_rate": 9.987987932702902e-07,
      "loss": 0.003,
      "reward": 2.1270313262939453,
      "reward_std": 0.010079530067741871,
      "rewards/accuracy_reward": 0.9270312190055847,
      "rewards/format_reward": 1.0,
      "step": 1600
    },
    {
      "all_correct": 0.75,
      "all_wrong": 0.0,
      "completion_length": 401.25,
      "epoch": 0.022082454035116758,
      "grad_norm": 2.0218743350459096,
      "kl": 0.06787109375,
      "learning_rate": 9.987972918950933e-07,
      "loss": 0.0027,
      "reward": 2.1231563091278076,
      "reward_std": 0.021622788161039352,
      "rewards/accuracy_reward": 0.9294062256813049,
      "rewards/format_reward": 1.0,
      "step": 1601
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.0,
      "completion_length": 393.46875,
      "epoch": 0.022096246948317955,
      "grad_norm": 2.9313096507871768,
      "kl": 0.08203125,
      "learning_rate": 9.987957895833359e-07,
      "loss": 0.0033,
      "reward": 2.0399062633514404,
      "reward_std": 0.029750332236289978,
      "rewards/accuracy_reward": 0.8399062156677246,
      "rewards/format_reward": 1.0,
      "step": 1602
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.0,
      "completion_length": 385.5625,
      "epoch": 0.022110039861519153,
      "grad_norm": 2.27480467227018,
      "kl": 0.07763671875,
      "learning_rate": 9.987942863350207e-07,
      "loss": 0.0031,
      "reward": 2.05009388923645,
      "reward_std": 0.016288653016090393,
      "rewards/accuracy_reward": 0.8500937819480896,
      "rewards/format_reward": 1.0,
      "step": 1603
    },
    {
      "all_correct": 1.0,
      "all_wrong": 0.0,
      "completion_length": 392.125,
      "epoch": 0.02212383277472035,
      "grad_norm": 4.096795289350605,
      "kl": 0.0712890625,
      "learning_rate": 9.987927821501507e-07,
      "loss": 0.0028,
      "reward": 2.1626875400543213,
      "reward_std": 0.024405695497989655,
      "rewards/accuracy_reward": 0.9689375162124634,
      "rewards/format_reward": 1.0,
      "step": 1604
    },
    {
      "all_correct": 1.0,
      "all_wrong": 0.0,
      "completion_length": 382.28125,
      "epoch": 0.022137625687921547,
      "grad_norm": 2.545853388278239,
      "kl": 0.0751953125,
      "learning_rate": 9.987912770287287e-07,
      "loss": 0.003,
      "reward": 2.1858439445495605,
      "reward_std": 0.02256779372692108,
      "rewards/accuracy_reward": 0.9920937418937683,
      "rewards/format_reward": 1.0,
      "step": 1605
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.0,
      "completion_length": 395.21875,
      "epoch": 0.022151418601122744,
      "grad_norm": 5.533992855812773,
      "kl": 0.0712890625,
      "learning_rate": 9.987897709707576e-07,
      "loss": 0.0029,
      "reward": 2.010499954223633,
      "reward_std": 0.019612543284893036,
      "rewards/accuracy_reward": 0.8104999661445618,
      "rewards/format_reward": 1.0,
      "step": 1606
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.0,
      "completion_length": 400.71875,
      "epoch": 0.02216521151432394,
      "grad_norm": 2.4654377695399012,
      "kl": 0.087890625,
      "learning_rate": 9.9878826397624e-07,
      "loss": 0.0035,
      "reward": 2.079312562942505,
      "reward_std": 0.01909957453608513,
      "rewards/accuracy_reward": 0.8793125152587891,
      "rewards/format_reward": 1.0,
      "step": 1607
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.0,
      "completion_length": 391.09375,
      "epoch": 0.02217900442752514,
      "grad_norm": 3.64585957663724,
      "kl": 0.0771484375,
      "learning_rate": 9.987867560451787e-07,
      "loss": 0.0031,
      "reward": 2.0647499561309814,
      "reward_std": 0.023414820432662964,
      "rewards/accuracy_reward": 0.8710000514984131,
      "rewards/format_reward": 1.0,
      "step": 1608
    },
    {
      "all_correct": 0.75,
      "all_wrong": 0.0,
      "completion_length": 394.46875,
      "epoch": 0.022192797340726336,
      "grad_norm": 2.8894580950626625,
      "kl": 0.0771484375,
      "learning_rate": 9.987852471775769e-07,
      "loss": 0.0031,
      "reward": 2.12850022315979,
      "reward_std": 0.038125794380903244,
      "rewards/accuracy_reward": 0.934749960899353,
      "rewards/format_reward": 1.0,
      "step": 1609
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.0,
      "completion_length": 396.46875,
      "epoch": 0.022206590253927534,
      "grad_norm": 3.596958897335824,
      "kl": 0.080078125,
      "learning_rate": 9.987837373734372e-07,
      "loss": 0.0032,
      "reward": 2.0559375286102295,
      "reward_std": 0.01801699586212635,
      "rewards/accuracy_reward": 0.8559374809265137,
      "rewards/format_reward": 1.0,
      "step": 1610
    },
    {
      "all_correct": 0.75,
      "all_wrong": 0.0,
      "completion_length": 395.4375,
      "epoch": 0.02222038316712873,
      "grad_norm": 3.916782219349192,
      "kl": 0.0771484375,
      "learning_rate": 9.987822266327624e-07,
      "loss": 0.0031,
      "reward": 2.0479373931884766,
      "reward_std": 0.017862647771835327,
      "rewards/accuracy_reward": 0.8479374647140503,
      "rewards/format_reward": 1.0,
      "step": 1611
    },
    {
      "all_correct": 0.75,
      "all_wrong": 0.0,
      "completion_length": 394.0,
      "epoch": 0.022234176080329928,
      "grad_norm": 2.0505635447726283,
      "kl": 0.06982421875,
      "learning_rate": 9.987807149555554e-07,
      "loss": 0.0028,
      "reward": 2.1303749084472656,
      "reward_std": 0.023144150152802467,
      "rewards/accuracy_reward": 0.9303749203681946,
      "rewards/format_reward": 1.0,
      "step": 1612
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.0,
      "completion_length": 384.0,
      "epoch": 0.022247968993531125,
      "grad_norm": 3.2604147332214755,
      "kl": 0.068359375,
      "learning_rate": 9.987792023418189e-07,
      "loss": 0.0027,
      "reward": 2.0581562519073486,
      "reward_std": 0.017807789146900177,
      "rewards/accuracy_reward": 0.8581562638282776,
      "rewards/format_reward": 1.0,
      "step": 1613
    },
    {
      "all_correct": 0.75,
      "all_wrong": 0.0,
      "completion_length": 380.78125,
      "epoch": 0.022261761906732323,
      "grad_norm": 2.3481618660544084,
      "kl": 0.07177734375,
      "learning_rate": 9.98777688791556e-07,
      "loss": 0.0029,
      "reward": 2.0974998474121094,
      "reward_std": 0.02573578618466854,
      "rewards/accuracy_reward": 0.903749942779541,
      "rewards/format_reward": 1.0,
      "step": 1614
    },
    {
      "all_correct": 0.75,
      "all_wrong": 0.0,
      "completion_length": 393.6875,
      "epoch": 0.02227555481993352,
      "grad_norm": 2.456537182121554,
      "kl": 0.0673828125,
      "learning_rate": 9.987761743047693e-07,
      "loss": 0.0027,
      "reward": 2.080843925476074,
      "reward_std": 0.012926635332405567,
      "rewards/accuracy_reward": 0.8808437585830688,
      "rewards/format_reward": 1.0,
      "step": 1615
    },
    {
      "all_correct": 0.75,
      "all_wrong": 0.0,
      "completion_length": 382.0,
      "epoch": 0.022289347733134714,
      "grad_norm": 1.9540094434596145,
      "kl": 0.06494140625,
      "learning_rate": 9.98774658881462e-07,
      "loss": 0.0026,
      "reward": 2.0770626068115234,
      "reward_std": 0.011614246293902397,
      "rewards/accuracy_reward": 0.8770624995231628,
      "rewards/format_reward": 1.0,
      "step": 1616
    },
    {
      "all_correct": 0.75,
      "all_wrong": 0.0,
      "completion_length": 396.21875,
      "epoch": 0.02230314064633591,
      "grad_norm": 3.468532753757021,
      "kl": 0.0703125,
      "learning_rate": 9.987731425216364e-07,
      "loss": 0.0028,
      "reward": 2.042187452316284,
      "reward_std": 0.02053939737379551,
      "rewards/accuracy_reward": 0.8421874046325684,
      "rewards/format_reward": 1.0,
      "step": 1617
    },
    {
      "all_correct": 0.75,
      "all_wrong": 0.0,
      "completion_length": 395.625,
      "epoch": 0.022316933559537108,
      "grad_norm": 2.2356802284425163,
      "kl": 0.068359375,
      "learning_rate": 9.987716252252957e-07,
      "loss": 0.0027,
      "reward": 2.0247654914855957,
      "reward_std": 0.025083305314183235,
      "rewards/accuracy_reward": 0.8310155868530273,
      "rewards/format_reward": 1.0,
      "step": 1618
    },
    {
      "all_correct": 0.75,
      "all_wrong": 0.0,
      "completion_length": 375.625,
      "epoch": 0.022330726472738305,
      "grad_norm": 2.40069343630425,
      "kl": 0.06787109375,
      "learning_rate": 9.987701069924427e-07,
      "loss": 0.0027,
      "reward": 2.1070001125335693,
      "reward_std": 0.014938032254576683,
      "rewards/accuracy_reward": 0.906999945640564,
      "rewards/format_reward": 1.0,
      "step": 1619
    },
    {
      "all_correct": 0.25,
      "all_wrong": 0.0,
      "completion_length": 382.0625,
      "epoch": 0.022344519385939503,
      "grad_norm": 3.195540825530226,
      "kl": 0.0771484375,
      "learning_rate": 9.987685878230803e-07,
      "loss": 0.0031,
      "reward": 2.016718864440918,
      "reward_std": 0.02631540596485138,
      "rewards/accuracy_reward": 0.8229687213897705,
      "rewards/format_reward": 1.0,
      "step": 1620
    },
    {
      "all_correct": 0.75,
      "all_wrong": 0.0,
      "completion_length": 376.4375,
      "epoch": 0.0223583122991407,
      "grad_norm": 3.6386246575180516,
      "kl": 0.068359375,
      "learning_rate": 9.987670677172113e-07,
      "loss": 0.0027,
      "reward": 2.091437339782715,
      "reward_std": 0.033959440886974335,
      "rewards/accuracy_reward": 0.8914374709129333,
      "rewards/format_reward": 1.0,
      "step": 1621
    },
    {
      "all_correct": 0.75,
      "all_wrong": 0.0,
      "completion_length": 387.78125,
      "epoch": 0.022372105212341897,
      "grad_norm": 2.6455846219595873,
      "kl": 0.078125,
      "learning_rate": 9.987655466748384e-07,
      "loss": 0.0031,
      "reward": 2.0830626487731934,
      "reward_std": 0.032215796411037445,
      "rewards/accuracy_reward": 0.8893125057220459,
      "rewards/format_reward": 1.0,
      "step": 1622
    },
    {
      "all_correct": 0.75,
      "all_wrong": 0.0,
      "completion_length": 380.75,
      "epoch": 0.022385898125543095,
      "grad_norm": 1.7424033586725158,
      "kl": 0.0751953125,
      "learning_rate": 9.987640246959648e-07,
      "loss": 0.003,
      "reward": 2.024531364440918,
      "reward_std": 0.021746691316366196,
      "rewards/accuracy_reward": 0.8307812213897705,
      "rewards/format_reward": 1.0,
      "step": 1623
    },
    {
      "all_correct": 1.0,
      "all_wrong": 0.0,
      "completion_length": 385.03125,
      "epoch": 0.022399691038744292,
      "grad_norm": 2.4642272376215315,
      "kl": 0.0693359375,
      "learning_rate": 9.987625017805933e-07,
      "loss": 0.0028,
      "reward": 2.1683435440063477,
      "reward_std": 0.009530635550618172,
      "rewards/accuracy_reward": 0.9683437347412109,
      "rewards/format_reward": 1.0,
      "step": 1624
    },
    {
      "all_correct": 1.0,
      "all_wrong": 0.0,
      "completion_length": 382.65625,
      "epoch": 0.02241348395194549,
      "grad_norm": 2.7652539374980445,
      "kl": 0.06640625,
      "learning_rate": 9.987609779287262e-07,
      "loss": 0.0027,
      "reward": 2.096062660217285,
      "reward_std": 0.016550809144973755,
      "rewards/accuracy_reward": 0.8960625529289246,
      "rewards/format_reward": 1.0,
      "step": 1625
    },
    {
      "all_correct": 0.75,
      "all_wrong": 0.0,
      "completion_length": 378.0625,
      "epoch": 0.022427276865146686,
      "grad_norm": 4.588052411991899,
      "kl": 0.07861328125,
      "learning_rate": 9.98759453140367e-07,
      "loss": 0.0031,
      "reward": 2.0502500534057617,
      "reward_std": 0.011521900072693825,
      "rewards/accuracy_reward": 0.8502499461174011,
      "rewards/format_reward": 1.0,
      "step": 1626
    },
    {
      "all_correct": 1.0,
      "all_wrong": 0.0,
      "completion_length": 392.84375,
      "epoch": 0.022441069778347884,
      "grad_norm": 4.2124360996096115,
      "kl": 0.0693359375,
      "learning_rate": 9.987579274155182e-07,
      "loss": 0.0028,
      "reward": 2.1075310707092285,
      "reward_std": 0.013847069814801216,
      "rewards/accuracy_reward": 0.9075312614440918,
      "rewards/format_reward": 1.0,
      "step": 1627
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.0,
      "completion_length": 379.6875,
      "epoch": 0.02245486269154908,
      "grad_norm": 5.426314357669005,
      "kl": 0.0791015625,
      "learning_rate": 9.987564007541832e-07,
      "loss": 0.0032,
      "reward": 1.97475004196167,
      "reward_std": 0.03231143206357956,
      "rewards/accuracy_reward": 0.7810000777244568,
      "rewards/format_reward": 1.0,
      "step": 1628
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.0,
      "completion_length": 399.0,
      "epoch": 0.022468655604750278,
      "grad_norm": 3.5415681066205216,
      "kl": 0.078125,
      "learning_rate": 9.98754873156364e-07,
      "loss": 0.0031,
      "reward": 2.0370936393737793,
      "reward_std": 0.03552011772990227,
      "rewards/accuracy_reward": 0.8433436751365662,
      "rewards/format_reward": 1.0,
      "step": 1629
    },
    {
      "all_correct": 0.75,
      "all_wrong": 0.0,
      "completion_length": 386.34375,
      "epoch": 0.022482448517951475,
      "grad_norm": 4.3135285231021445,
      "kl": 0.06787109375,
      "learning_rate": 9.987533446220642e-07,
      "loss": 0.0027,
      "reward": 2.1143438816070557,
      "reward_std": 0.010626059956848621,
      "rewards/accuracy_reward": 0.9143437147140503,
      "rewards/format_reward": 1.0,
      "step": 1630
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.0,
      "completion_length": 390.1875,
      "epoch": 0.022496241431152673,
      "grad_norm": 2.161792505344043,
      "kl": 0.07763671875,
      "learning_rate": 9.987518151512863e-07,
      "loss": 0.0031,
      "reward": 1.8996875286102295,
      "reward_std": 0.011843464337289333,
      "rewards/accuracy_reward": 0.6996874809265137,
      "rewards/format_reward": 1.0,
      "step": 1631
    },
    {
      "all_correct": 0.75,
      "all_wrong": 0.0,
      "completion_length": 396.09375,
      "epoch": 0.02251003434435387,
      "grad_norm": 2.639045801220504,
      "kl": 0.072265625,
      "learning_rate": 9.987502847440335e-07,
      "loss": 0.0029,
      "reward": 2.098968982696533,
      "reward_std": 0.013721741735935211,
      "rewards/accuracy_reward": 0.8989687561988831,
      "rewards/format_reward": 1.0,
      "step": 1632
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.0,
      "completion_length": 383.71875,
      "epoch": 0.022523827257555067,
      "grad_norm": 8.081977097473715,
      "kl": 0.0712890625,
      "learning_rate": 9.987487534003082e-07,
      "loss": 0.0028,
      "reward": 1.9724375009536743,
      "reward_std": 0.01910484954714775,
      "rewards/accuracy_reward": 0.7724375128746033,
      "rewards/format_reward": 1.0,
      "step": 1633
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.0,
      "completion_length": 387.71875,
      "epoch": 0.022537620170756265,
      "grad_norm": 3.5172905275188038,
      "kl": 0.0791015625,
      "learning_rate": 9.987472211201139e-07,
      "loss": 0.0032,
      "reward": 2.007406234741211,
      "reward_std": 0.016517942771315575,
      "rewards/accuracy_reward": 0.8074062466621399,
      "rewards/format_reward": 1.0,
      "step": 1634
    },
    {
      "all_correct": 0.75,
      "all_wrong": 0.0,
      "completion_length": 391.875,
      "epoch": 0.022551413083957462,
      "grad_norm": 26.11986204609202,
      "kl": 0.0751953125,
      "learning_rate": 9.987456879034526e-07,
      "loss": 0.003,
      "reward": 2.1055314540863037,
      "reward_std": 0.024459335952997208,
      "rewards/accuracy_reward": 0.9055312871932983,
      "rewards/format_reward": 1.0,
      "step": 1635
    },
    {
      "all_correct": 0.75,
      "all_wrong": 0.0,
      "completion_length": 374.1875,
      "epoch": 0.02256520599715866,
      "grad_norm": 4.090719347099288,
      "kl": 0.07373046875,
      "learning_rate": 9.98744153750328e-07,
      "loss": 0.003,
      "reward": 2.1271252632141113,
      "reward_std": 0.03258293867111206,
      "rewards/accuracy_reward": 0.9333750009536743,
      "rewards/format_reward": 1.0,
      "step": 1636
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.0,
      "completion_length": 390.34375,
      "epoch": 0.022578998910359856,
      "grad_norm": 2.976081529762625,
      "kl": 0.07958984375,
      "learning_rate": 9.987426186607425e-07,
      "loss": 0.0032,
      "reward": 2.054281234741211,
      "reward_std": 0.025163572281599045,
      "rewards/accuracy_reward": 0.8542812466621399,
      "rewards/format_reward": 1.0,
      "step": 1637
    },
    {
      "all_correct": 1.0,
      "all_wrong": 0.0,
      "completion_length": 377.46875,
      "epoch": 0.022592791823561054,
      "grad_norm": 3.759704003109648,
      "kl": 0.07080078125,
      "learning_rate": 9.987410826346994e-07,
      "loss": 0.0028,
      "reward": 2.0804061889648438,
      "reward_std": 0.01303371973335743,
      "rewards/accuracy_reward": 0.8804062604904175,
      "rewards/format_reward": 1.0,
      "step": 1638
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.0,
      "completion_length": 381.1875,
      "epoch": 0.02260658473676225,
      "grad_norm": 4.429015151705762,
      "kl": 0.07568359375,
      "learning_rate": 9.987395456722012e-07,
      "loss": 0.003,
      "reward": 1.9929375648498535,
      "reward_std": 0.011019095778465271,
      "rewards/accuracy_reward": 0.7929374575614929,
      "rewards/format_reward": 1.0,
      "step": 1639
    },
    {
      "all_correct": 1.0,
      "all_wrong": 0.0,
      "completion_length": 381.28125,
      "epoch": 0.022620377649963448,
      "grad_norm": 2.672817395978639,
      "kl": 0.06982421875,
      "learning_rate": 9.98738007773251e-07,
      "loss": 0.0028,
      "reward": 2.138406276702881,
      "reward_std": 0.035480089485645294,
      "rewards/accuracy_reward": 0.9571563005447388,
      "rewards/format_reward": 1.0,
      "step": 1640
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.0,
      "completion_length": 380.78125,
      "epoch": 0.022634170563164645,
      "grad_norm": 2.4441750624262193,
      "kl": 0.06640625,
      "learning_rate": 9.987364689378514e-07,
      "loss": 0.0027,
      "reward": 2.139937400817871,
      "reward_std": 0.04453915357589722,
      "rewards/accuracy_reward": 0.9524375200271606,
      "rewards/format_reward": 1.0,
      "step": 1641
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.0,
      "completion_length": 382.5625,
      "epoch": 0.022647963476365843,
      "grad_norm": 5.124465866373513,
      "kl": 0.07080078125,
      "learning_rate": 9.987349291660058e-07,
      "loss": 0.0028,
      "reward": 2.0469062328338623,
      "reward_std": 0.0361442007124424,
      "rewards/accuracy_reward": 0.8531562089920044,
      "rewards/format_reward": 1.0,
      "step": 1642
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.0,
      "completion_length": 383.46875,
      "epoch": 0.02266175638956704,
      "grad_norm": 2.353584137383195,
      "kl": 0.0712890625,
      "learning_rate": 9.987333884577165e-07,
      "loss": 0.0028,
      "reward": 1.9849374294281006,
      "reward_std": 0.009978788904845715,
      "rewards/accuracy_reward": 0.7849375605583191,
      "rewards/format_reward": 1.0,
      "step": 1643
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.0,
      "completion_length": 395.0625,
      "epoch": 0.022675549302768237,
      "grad_norm": 2.1660351809070515,
      "kl": 0.06494140625,
      "learning_rate": 9.987318468129869e-07,
      "loss": 0.0026,
      "reward": 2.0594310760498047,
      "reward_std": 0.02263607829809189,
      "rewards/accuracy_reward": 0.865680992603302,
      "rewards/format_reward": 1.0,
      "step": 1644
    },
    {
      "all_correct": 0.75,
      "all_wrong": 0.0,
      "completion_length": 407.78125,
      "epoch": 0.022689342215969435,
      "grad_norm": 5.839559912600374,
      "kl": 0.07763671875,
      "learning_rate": 9.987303042318197e-07,
      "loss": 0.0031,
      "reward": 2.0973124504089355,
      "reward_std": 0.015562057495117188,
      "rewards/accuracy_reward": 0.8973124623298645,
      "rewards/format_reward": 1.0,
      "step": 1645
    },
    {
      "all_correct": 0.75,
      "all_wrong": 0.0,
      "completion_length": 392.21875,
      "epoch": 0.022703135129170632,
      "grad_norm": 3.1852166384659486,
      "kl": 0.068359375,
      "learning_rate": 9.987287607142175e-07,
      "loss": 0.0027,
      "reward": 2.091437339782715,
      "reward_std": 0.011914307251572609,
      "rewards/accuracy_reward": 0.8914375305175781,
      "rewards/format_reward": 1.0,
      "step": 1646
    },
    {
      "all_correct": 1.0,
      "all_wrong": 0.0,
      "completion_length": 387.4375,
      "epoch": 0.02271692804237183,
      "grad_norm": 3.2110001823347436,
      "kl": 0.0673828125,
      "learning_rate": 9.987272162601836e-07,
      "loss": 0.0027,
      "reward": 2.0966248512268066,
      "reward_std": 0.02088780142366886,
      "rewards/accuracy_reward": 0.8966249227523804,
      "rewards/format_reward": 1.0,
      "step": 1647
    },
    {
      "all_correct": 1.0,
      "all_wrong": 0.0,
      "completion_length": 411.03125,
      "epoch": 0.022730720955573026,
      "grad_norm": 2.0785619253009116,
      "kl": 0.0703125,
      "learning_rate": 9.98725670869721e-07,
      "loss": 0.0028,
      "reward": 2.1183531284332275,
      "reward_std": 0.015527507290244102,
      "rewards/accuracy_reward": 0.9183530807495117,
      "rewards/format_reward": 1.0,
      "step": 1648
    },
    {
      "all_correct": 0.25,
      "all_wrong": 0.0,
      "completion_length": 396.34375,
      "epoch": 0.022744513868774224,
      "grad_norm": 2.7673417700482394,
      "kl": 0.07080078125,
      "learning_rate": 9.987241245428322e-07,
      "loss": 0.0028,
      "reward": 1.9821875095367432,
      "reward_std": 0.012552608735859394,
      "rewards/accuracy_reward": 0.7821875214576721,
      "rewards/format_reward": 1.0,
      "step": 1649
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.0,
      "completion_length": 409.875,
      "epoch": 0.02275830678197542,
      "grad_norm": 33.221404162866214,
      "kl": 0.07080078125,
      "learning_rate": 9.987225772795201e-07,
      "loss": 0.0028,
      "reward": 2.113093614578247,
      "reward_std": 0.026470482349395752,
      "rewards/accuracy_reward": 0.9193437099456787,
      "rewards/format_reward": 1.0,
      "step": 1650
    },
    {
      "all_correct": 1.0,
      "all_wrong": 0.0,
      "completion_length": 402.4375,
      "epoch": 0.022772099695176618,
      "grad_norm": 2.7226735814247207,
      "kl": 0.06494140625,
      "learning_rate": 9.98721029079788e-07,
      "loss": 0.0026,
      "reward": 2.0960001945495605,
      "reward_std": 0.013849593698978424,
      "rewards/accuracy_reward": 0.8959999680519104,
      "rewards/format_reward": 1.0,
      "step": 1651
    },
    {
      "all_correct": 0.75,
      "all_wrong": 0.0,
      "completion_length": 410.03125,
      "epoch": 0.022785892608377815,
      "grad_norm": 2.0815498159063437,
      "kl": 0.072265625,
      "learning_rate": 9.987194799436386e-07,
      "loss": 0.0029,
      "reward": 2.0556564331054688,
      "reward_std": 0.01970680058002472,
      "rewards/accuracy_reward": 0.8556562662124634,
      "rewards/format_reward": 1.0,
      "step": 1652
    },
    {
      "all_correct": 1.0,
      "all_wrong": 0.0,
      "completion_length": 407.90625,
      "epoch": 0.022799685521579013,
      "grad_norm": 1.9594509009400654,
      "kl": 0.07373046875,
      "learning_rate": 9.98717929871075e-07,
      "loss": 0.0029,
      "reward": 2.1013436317443848,
      "reward_std": 0.01352996937930584,
      "rewards/accuracy_reward": 0.9013437032699585,
      "rewards/format_reward": 1.0,
      "step": 1653
    },
    {
      "all_correct": 1.0,
      "all_wrong": 0.0,
      "completion_length": 401.5,
      "epoch": 0.02281347843478021,
      "grad_norm": 2.070654489749832,
      "kl": 0.06640625,
      "learning_rate": 9.987163788620995e-07,
      "loss": 0.0027,
      "reward": 2.1234688758850098,
      "reward_std": 0.011304449290037155,
      "rewards/accuracy_reward": 0.923468828201294,
      "rewards/format_reward": 1.0,
      "step": 1654
    },
    {
      "all_correct": 1.0,
      "all_wrong": 0.0,
      "completion_length": 398.90625,
      "epoch": 0.022827271347981407,
      "grad_norm": 3.2764125669868234,
      "kl": 0.0693359375,
      "learning_rate": 9.987148269167157e-07,
      "loss": 0.0028,
      "reward": 2.1664376258850098,
      "reward_std": 0.015318438410758972,
      "rewards/accuracy_reward": 0.9664375185966492,
      "rewards/format_reward": 1.0,
      "step": 1655
    },
    {
      "all_correct": 1.0,
      "all_wrong": 0.0,
      "completion_length": 397.40625,
      "epoch": 0.022841064261182605,
      "grad_norm": 1.8631941140950767,
      "kl": 0.0634765625,
      "learning_rate": 9.98713274034926e-07,
      "loss": 0.0025,
      "reward": 2.152937650680542,
      "reward_std": 0.012151816859841347,
      "rewards/accuracy_reward": 0.9529374837875366,
      "rewards/format_reward": 1.0,
      "step": 1656
    },
    {
      "all_correct": 1.0,
      "all_wrong": 0.0,
      "completion_length": 418.84375,
      "epoch": 0.022854857174383802,
      "grad_norm": 11.236525264633915,
      "kl": 0.06298828125,
      "learning_rate": 9.987117202167337e-07,
      "loss": 0.0025,
      "reward": 2.1085000038146973,
      "reward_std": 0.010128715075552464,
      "rewards/accuracy_reward": 0.908500075340271,
      "rewards/format_reward": 1.0,
      "step": 1657
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.0,
      "completion_length": 404.28125,
      "epoch": 0.022868650087585,
      "grad_norm": 2.313797345428018,
      "kl": 0.0712890625,
      "learning_rate": 9.987101654621416e-07,
      "loss": 0.0028,
      "reward": 2.087156295776367,
      "reward_std": 0.031427495181560516,
      "rewards/accuracy_reward": 0.8934062719345093,
      "rewards/format_reward": 1.0,
      "step": 1658
    },
    {
      "all_correct": 0.0,
      "all_wrong": 0.0,
      "completion_length": 422.6875,
      "epoch": 0.022882443000786196,
      "grad_norm": 2.132083557201774,
      "kl": 0.07177734375,
      "learning_rate": 9.987086097711524e-07,
      "loss": 0.0029,
      "reward": 1.9529376029968262,
      "reward_std": 0.03312106430530548,
      "rewards/accuracy_reward": 0.7591875195503235,
      "rewards/format_reward": 1.0,
      "step": 1659
    },
    {
      "all_correct": 0.25,
      "all_wrong": 0.0,
      "completion_length": 424.40625,
      "epoch": 0.022896235913987394,
      "grad_norm": 2.8942070323549114,
      "kl": 0.0654296875,
      "learning_rate": 9.987070531437694e-07,
      "loss": 0.0026,
      "reward": 1.9530937671661377,
      "reward_std": 0.018820933997631073,
      "rewards/accuracy_reward": 0.7530937194824219,
      "rewards/format_reward": 1.0,
      "step": 1660
    },
    {
      "all_correct": 0.75,
      "all_wrong": 0.0,
      "completion_length": 418.40625,
      "epoch": 0.02291002882718859,
      "grad_norm": 2.655399528869471,
      "kl": 0.0732421875,
      "learning_rate": 9.987054955799952e-07,
      "loss": 0.0029,
      "reward": 2.097249984741211,
      "reward_std": 0.01258598268032074,
      "rewards/accuracy_reward": 0.8972499370574951,
      "rewards/format_reward": 1.0,
      "step": 1661
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.0,
      "completion_length": 400.125,
      "epoch": 0.022923821740389788,
      "grad_norm": 4.205156707019659,
      "kl": 0.07421875,
      "learning_rate": 9.987039370798331e-07,
      "loss": 0.003,
      "reward": 2.1006250381469727,
      "reward_std": 0.01906784437596798,
      "rewards/accuracy_reward": 0.9006250500679016,
      "rewards/format_reward": 1.0,
      "step": 1662
    },
    {
      "all_correct": 0.75,
      "all_wrong": 0.0,
      "completion_length": 410.875,
      "epoch": 0.022937614653590985,
      "grad_norm": 3.02287594681577,
      "kl": 0.07177734375,
      "learning_rate": 9.987023776432854e-07,
      "loss": 0.0029,
      "reward": 2.1303436756134033,
      "reward_std": 0.029743749648332596,
      "rewards/accuracy_reward": 0.9365937113761902,
      "rewards/format_reward": 1.0,
      "step": 1663
    },
    {
      "all_correct": 0.75,
      "all_wrong": 0.0,
      "completion_length": 407.21875,
      "epoch": 0.022951407566792183,
      "grad_norm": 1.8434933484424019,
      "kl": 0.072265625,
      "learning_rate": 9.987008172703557e-07,
      "loss": 0.0029,
      "reward": 2.145343780517578,
      "reward_std": 0.0064971670508384705,
      "rewards/accuracy_reward": 0.9453437924385071,
      "rewards/format_reward": 1.0,
      "step": 1664
    },
    {
      "all_correct": 0.75,
      "all_wrong": 0.0,
      "completion_length": 404.78125,
      "epoch": 0.02296520047999338,
      "grad_norm": 3.322838632058154,
      "kl": 0.0693359375,
      "learning_rate": 9.986992559610466e-07,
      "loss": 0.0028,
      "reward": 2.0964531898498535,
      "reward_std": 0.028336143121123314,
      "rewards/accuracy_reward": 0.9027031064033508,
      "rewards/format_reward": 1.0,
      "step": 1665
    },
    {
      "all_correct": 0.75,
      "all_wrong": 0.0,
      "completion_length": 414.75,
      "epoch": 0.022978993393194577,
      "grad_norm": 2.218958646524337,
      "kl": 0.076171875,
      "learning_rate": 9.98697693715361e-07,
      "loss": 0.0031,
      "reward": 2.1302499771118164,
      "reward_std": 0.024848777800798416,
      "rewards/accuracy_reward": 0.9365000128746033,
      "rewards/format_reward": 1.0,
      "step": 1666
    },
    {
      "all_correct": 0.75,
      "all_wrong": 0.0,
      "completion_length": 417.875,
      "epoch": 0.022992786306395775,
      "grad_norm": 2.373010030560566,
      "kl": 0.0673828125,
      "learning_rate": 9.98696130533302e-07,
      "loss": 0.0027,
      "reward": 2.1166560649871826,
      "reward_std": 0.00951197650283575,
      "rewards/accuracy_reward": 0.9166562557220459,
      "rewards/format_reward": 1.0,
      "step": 1667
    },
    {
      "all_correct": 0.75,
      "all_wrong": 0.0,
      "completion_length": 429.4375,
      "epoch": 0.023006579219596972,
      "grad_norm": 2.108639863049619,
      "kl": 0.06640625,
      "learning_rate": 9.986945664148723e-07,
      "loss": 0.0027,
      "reward": 2.121509552001953,
      "reward_std": 0.03110520914196968,
      "rewards/accuracy_reward": 0.9277593493461609,
      "rewards/format_reward": 1.0,
      "step": 1668
    },
    {
      "all_correct": 0.75,
      "all_wrong": 0.0,
      "completion_length": 440.53125,
      "epoch": 0.02302037213279817,
      "grad_norm": 5.028493232761288,
      "kl": 0.06494140625,
      "learning_rate": 9.986930013600752e-07,
      "loss": 0.0026,
      "reward": 2.084437370300293,
      "reward_std": 0.029759516939520836,
      "rewards/accuracy_reward": 0.8906875252723694,
      "rewards/format_reward": 1.0,
      "step": 1669
    },
    {
      "all_correct": 1.0,
      "all_wrong": 0.0,
      "completion_length": 422.03125,
      "epoch": 0.023034165045999366,
      "grad_norm": 1.9456311677734903,
      "kl": 0.07763671875,
      "learning_rate": 9.986914353689134e-07,
      "loss": 0.0031,
      "reward": 2.120187759399414,
      "reward_std": 0.008283843286335468,
      "rewards/accuracy_reward": 0.9201874732971191,
      "rewards/format_reward": 1.0,
      "step": 1670
    },
    {
      "all_correct": 1.0,
      "all_wrong": 0.0,
      "completion_length": 417.34375,
      "epoch": 0.023047957959200564,
      "grad_norm": 2.8738681609739443,
      "kl": 0.068359375,
      "learning_rate": 9.986898684413897e-07,
      "loss": 0.0027,
      "reward": 2.071624994277954,
      "reward_std": 0.018431399017572403,
      "rewards/accuracy_reward": 0.8716249465942383,
      "rewards/format_reward": 1.0,
      "step": 1671
    },
    {
      "all_correct": 1.0,
      "all_wrong": 0.0,
      "completion_length": 410.25,
      "epoch": 0.02306175087240176,
      "grad_norm": 3.3355956777241453,
      "kl": 0.0673828125,
      "learning_rate": 9.98688300577507e-07,
      "loss": 0.0027,
      "reward": 2.13685941696167,
      "reward_std": 0.011823462322354317,
      "rewards/accuracy_reward": 0.9368594288825989,
      "rewards/format_reward": 1.0,
      "step": 1672
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.0,
      "completion_length": 421.8125,
      "epoch": 0.023075543785602958,
      "grad_norm": 2.2224807510423186,
      "kl": 0.0693359375,
      "learning_rate": 9.986867317772689e-07,
      "loss": 0.0028,
      "reward": 2.0652291774749756,
      "reward_std": 0.01932460255920887,
      "rewards/accuracy_reward": 0.8652291893959045,
      "rewards/format_reward": 1.0,
      "step": 1673
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.0,
      "completion_length": 411.0625,
      "epoch": 0.023089336698804155,
      "grad_norm": 2.85276188427479,
      "kl": 0.06591796875,
      "learning_rate": 9.986851620406775e-07,
      "loss": 0.0026,
      "reward": 2.0309062004089355,
      "reward_std": 0.012519195675849915,
      "rewards/accuracy_reward": 0.8309062719345093,
      "rewards/format_reward": 1.0,
      "step": 1674
    },
    {
      "all_correct": 0.75,
      "all_wrong": 0.0,
      "completion_length": 422.21875,
      "epoch": 0.023103129612005353,
      "grad_norm": 3.1535972543580346,
      "kl": 0.0703125,
      "learning_rate": 9.986835913677363e-07,
      "loss": 0.0028,
      "reward": 2.0654375553131104,
      "reward_std": 0.016368605196475983,
      "rewards/accuracy_reward": 0.8654374480247498,
      "rewards/format_reward": 1.0,
      "step": 1675
    },
    {
      "all_correct": 0.75,
      "all_wrong": 0.0,
      "completion_length": 420.84375,
      "epoch": 0.02311692252520655,
      "grad_norm": 1.4633776138349617,
      "kl": 0.07373046875,
      "learning_rate": 9.986820197584483e-07,
      "loss": 0.003,
      "reward": 2.0888750553131104,
      "reward_std": 0.004317393526434898,
      "rewards/accuracy_reward": 0.8888750076293945,
      "rewards/format_reward": 1.0,
      "step": 1676
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.0,
      "completion_length": 424.0,
      "epoch": 0.023130715438407747,
      "grad_norm": 3.20145105519077,
      "kl": 0.0712890625,
      "learning_rate": 9.98680447212816e-07,
      "loss": 0.0028,
      "reward": 2.0140624046325684,
      "reward_std": 0.022028621286153793,
      "rewards/accuracy_reward": 0.8140624761581421,
      "rewards/format_reward": 1.0,
      "step": 1677
    },
    {
      "all_correct": 0.75,
      "all_wrong": 0.0,
      "completion_length": 421.59375,
      "epoch": 0.023144508351608944,
      "grad_norm": 8.767472568874263,
      "kl": 0.072265625,
      "learning_rate": 9.986788737308425e-07,
      "loss": 0.0029,
      "reward": 2.1104063987731934,
      "reward_std": 0.013903023675084114,
      "rewards/accuracy_reward": 0.910406231880188,
      "rewards/format_reward": 1.0,
      "step": 1678
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.0,
      "completion_length": 418.15625,
      "epoch": 0.023158301264810142,
      "grad_norm": 6.064668822241957,
      "kl": 0.07470703125,
      "learning_rate": 9.98677299312531e-07,
      "loss": 0.003,
      "reward": 2.0306248664855957,
      "reward_std": 0.016842491924762726,
      "rewards/accuracy_reward": 0.8306249976158142,
      "rewards/format_reward": 1.0,
      "step": 1679
    },
    {
      "all_correct": 0.75,
      "all_wrong": 0.0,
      "completion_length": 427.3125,
      "epoch": 0.02317209417801134,
      "grad_norm": 5.605289672548259,
      "kl": 0.07861328125,
      "learning_rate": 9.986757239578841e-07,
      "loss": 0.0031,
      "reward": 2.0912375450134277,
      "reward_std": 0.009705105796456337,
      "rewards/accuracy_reward": 0.8912374973297119,
      "rewards/format_reward": 1.0,
      "step": 1680
    },
    {
      "all_correct": 0.75,
      "all_wrong": 0.0,
      "completion_length": 405.5625,
      "epoch": 0.023185887091212536,
      "grad_norm": 6.283973648744672,
      "kl": 0.0634765625,
      "learning_rate": 9.986741476669052e-07,
      "loss": 0.0026,
      "reward": 2.162749767303467,
      "reward_std": 0.04761098325252533,
      "rewards/accuracy_reward": 0.9752500057220459,
      "rewards/format_reward": 1.0,
      "step": 1681
    },
    {
      "all_correct": 0.75,
      "all_wrong": 0.0,
      "completion_length": 412.0,
      "epoch": 0.023199680004413734,
      "grad_norm": 7.43221628672166,
      "kl": 0.06982421875,
      "learning_rate": 9.98672570439597e-07,
      "loss": 0.0028,
      "reward": 2.0488126277923584,
      "reward_std": 0.01502240914851427,
      "rewards/accuracy_reward": 0.8488125801086426,
      "rewards/format_reward": 1.0,
      "step": 1682
    },
    {
      "all_correct": 1.0,
      "all_wrong": 0.0,
      "completion_length": 411.875,
      "epoch": 0.02321347291761493,
      "grad_norm": 2.6111387040900205,
      "kl": 0.07421875,
      "learning_rate": 9.986709922759624e-07,
      "loss": 0.003,
      "reward": 2.1423094272613525,
      "reward_std": 0.00808392558246851,
      "rewards/accuracy_reward": 0.9423093199729919,
      "rewards/format_reward": 1.0,
      "step": 1683
    },
    {
      "all_correct": 1.0,
      "all_wrong": 0.0,
      "completion_length": 426.28125,
      "epoch": 0.023227265830816128,
      "grad_norm": 2.7536377421888663,
      "kl": 0.072265625,
      "learning_rate": 9.986694131760045e-07,
      "loss": 0.0029,
      "reward": 2.117374897003174,
      "reward_std": 0.013065105304121971,
      "rewards/accuracy_reward": 0.9173749685287476,
      "rewards/format_reward": 1.0,
      "step": 1684
    },
    {
      "all_correct": 1.0,
      "all_wrong": 0.0,
      "completion_length": 428.5,
      "epoch": 0.023241058744017325,
      "grad_norm": 1.5389553475223623,
      "kl": 0.0703125,
      "learning_rate": 9.98667833139726e-07,
      "loss": 0.0028,
      "reward": 2.1069374084472656,
      "reward_std": 0.004994590766727924,
      "rewards/accuracy_reward": 0.9069375395774841,
      "rewards/format_reward": 1.0,
      "step": 1685
    },
    {
      "all_correct": 1.0,
      "all_wrong": 0.0,
      "completion_length": 413.1875,
      "epoch": 0.023254851657218523,
      "grad_norm": 4.479515165985387,
      "kl": 0.080078125,
      "learning_rate": 9.986662521671302e-07,
      "loss": 0.0032,
      "reward": 2.1265311241149902,
      "reward_std": 0.013859818689525127,
      "rewards/accuracy_reward": 0.9265313148498535,
      "rewards/format_reward": 1.0,
      "step": 1686
    },
    {
      "all_correct": 0.75,
      "all_wrong": 0.0,
      "completion_length": 411.4375,
      "epoch": 0.02326864457041972,
      "grad_norm": 2.503294160586001,
      "kl": 0.076171875,
      "learning_rate": 9.986646702582201e-07,
      "loss": 0.003,
      "reward": 2.153937339782715,
      "reward_std": 0.028295788913965225,
      "rewards/accuracy_reward": 0.960187554359436,
      "rewards/format_reward": 1.0,
      "step": 1687
    },
    {
      "all_correct": 1.0,
      "all_wrong": 0.0,
      "completion_length": 412.5625,
      "epoch": 0.023282437483620917,
      "grad_norm": 4.441688203165198,
      "kl": 0.07373046875,
      "learning_rate": 9.986630874129983e-07,
      "loss": 0.0029,
      "reward": 2.115884304046631,
      "reward_std": 0.017986608669161797,
      "rewards/accuracy_reward": 0.9158843755722046,
      "rewards/format_reward": 1.0,
      "step": 1688
    },
    {
      "all_correct": 0.75,
      "all_wrong": 0.0,
      "completion_length": 416.875,
      "epoch": 0.023296230396822114,
      "grad_norm": 2.807887076029559,
      "kl": 0.0673828125,
      "learning_rate": 9.986615036314682e-07,
      "loss": 0.0027,
      "reward": 2.0740625858306885,
      "reward_std": 0.008702855557203293,
      "rewards/accuracy_reward": 0.8740624785423279,
      "rewards/format_reward": 1.0,
      "step": 1689
    },
    {
      "all_correct": 1.0,
      "all_wrong": 0.0,
      "completion_length": 403.65625,
      "epoch": 0.023310023310023312,
      "grad_norm": 2.3830464551744925,
      "kl": 0.07568359375,
      "learning_rate": 9.986599189136323e-07,
      "loss": 0.003,
      "reward": 2.084843635559082,
      "reward_std": 0.013038131408393383,
      "rewards/accuracy_reward": 0.8848437666893005,
      "rewards/format_reward": 1.0,
      "step": 1690
    },
    {
      "all_correct": 1.0,
      "all_wrong": 0.0,
      "completion_length": 403.375,
      "epoch": 0.023323816223224506,
      "grad_norm": 1.9070433118527552,
      "kl": 0.0712890625,
      "learning_rate": 9.98658333259494e-07,
      "loss": 0.0029,
      "reward": 2.1456093788146973,
      "reward_std": 0.004530326928943396,
      "rewards/accuracy_reward": 0.9456093311309814,
      "rewards/format_reward": 1.0,
      "step": 1691
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.0,
      "completion_length": 433.28125,
      "epoch": 0.023337609136425703,
      "grad_norm": 1.5934918988257967,
      "kl": 0.072265625,
      "learning_rate": 9.986567466690562e-07,
      "loss": 0.0029,
      "reward": 2.1080312728881836,
      "reward_std": 0.022230740636587143,
      "rewards/accuracy_reward": 0.9142812490463257,
      "rewards/format_reward": 1.0,
      "step": 1692
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.0,
      "completion_length": 420.03125,
      "epoch": 0.0233514020496269,
      "grad_norm": 3.5332894745457737,
      "kl": 0.068359375,
      "learning_rate": 9.986551591423216e-07,
      "loss": 0.0027,
      "reward": 1.9298124313354492,
      "reward_std": 0.007952363230288029,
      "rewards/accuracy_reward": 0.729812502861023,
      "rewards/format_reward": 1.0,
      "step": 1693
    },
    {
      "all_correct": 1.0,
      "all_wrong": 0.0,
      "completion_length": 405.5625,
      "epoch": 0.023365194962828097,
      "grad_norm": 2.6340685227274636,
      "kl": 0.078125,
      "learning_rate": 9.986535706792935e-07,
      "loss": 0.0031,
      "reward": 2.132171869277954,
      "reward_std": 0.008069278672337532,
      "rewards/accuracy_reward": 0.9321718215942383,
      "rewards/format_reward": 1.0,
      "step": 1694
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.0,
      "completion_length": 406.65625,
      "epoch": 0.023378987876029295,
      "grad_norm": 2.8492318261380065,
      "kl": 0.0791015625,
      "learning_rate": 9.986519812799747e-07,
      "loss": 0.0032,
      "reward": 1.9759130477905273,
      "reward_std": 0.009217929095029831,
      "rewards/accuracy_reward": 0.7759132385253906,
      "rewards/format_reward": 1.0,
      "step": 1695
    },
    {
      "all_correct": 1.0,
      "all_wrong": 0.0,
      "completion_length": 412.25,
      "epoch": 0.023392780789230492,
      "grad_norm": 5.846606065456442,
      "kl": 0.0751953125,
      "learning_rate": 9.986503909443681e-07,
      "loss": 0.003,
      "reward": 2.1065688133239746,
      "reward_std": 0.01671210117638111,
      "rewards/accuracy_reward": 0.9065687656402588,
      "rewards/format_reward": 1.0,
      "step": 1696
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.0,
      "completion_length": 408.78125,
      "epoch": 0.02340657370243169,
      "grad_norm": 2.4142969651961774,
      "kl": 0.072265625,
      "learning_rate": 9.98648799672477e-07,
      "loss": 0.0029,
      "reward": 1.979062557220459,
      "reward_std": 0.005396238062530756,
      "rewards/accuracy_reward": 0.7790625095367432,
      "rewards/format_reward": 1.0,
      "step": 1697
    },
    {
      "all_correct": 0.75,
      "all_wrong": 0.0,
      "completion_length": 414.15625,
      "epoch": 0.023420366615632886,
      "grad_norm": 2.5854546446988143,
      "kl": 0.068359375,
      "learning_rate": 9.986472074643042e-07,
      "loss": 0.0027,
      "reward": 2.093031167984009,
      "reward_std": 0.007706265430897474,
      "rewards/accuracy_reward": 0.8930312395095825,
      "rewards/format_reward": 1.0,
      "step": 1698
    },
    {
      "all_correct": 0.75,
      "all_wrong": 0.0,
      "completion_length": 401.21875,
      "epoch": 0.023434159528834084,
      "grad_norm": 1.886258510438861,
      "kl": 0.068359375,
      "learning_rate": 9.986456143198527e-07,
      "loss": 0.0027,
      "reward": 2.100281238555908,
      "reward_std": 0.004760038107633591,
      "rewards/accuracy_reward": 0.9002811908721924,
      "rewards/format_reward": 1.0,
      "step": 1699
    },
    {
      "all_correct": 1.0,
      "all_wrong": 0.0,
      "completion_length": 406.28125,
      "epoch": 0.02344795244203528,
      "grad_norm": 2.822688158817216,
      "kl": 0.08056640625,
      "learning_rate": 9.986440202391255e-07,
      "loss": 0.0032,
      "reward": 2.13421893119812,
      "reward_std": 0.010491998866200447,
      "rewards/accuracy_reward": 0.9342187643051147,
      "rewards/format_reward": 1.0,
      "step": 1700
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.0,
      "completion_length": 411.875,
      "epoch": 0.023461745355236478,
      "grad_norm": 2.729248283060408,
      "kl": 0.076171875,
      "learning_rate": 9.986424252221254e-07,
      "loss": 0.003,
      "reward": 2.0096664428710938,
      "reward_std": 0.012444496154785156,
      "rewards/accuracy_reward": 0.8096666932106018,
      "rewards/format_reward": 1.0,
      "step": 1701
    },
    {
      "all_correct": 1.0,
      "all_wrong": 0.0,
      "completion_length": 407.96875,
      "epoch": 0.023475538268437676,
      "grad_norm": 3.1092368401185713,
      "kl": 0.07861328125,
      "learning_rate": 9.98640829268856e-07,
      "loss": 0.0031,
      "reward": 2.069103240966797,
      "reward_std": 0.009965509176254272,
      "rewards/accuracy_reward": 0.8691031336784363,
      "rewards/format_reward": 1.0,
      "step": 1702
    },
    {
      "all_correct": 1.0,
      "all_wrong": 0.0,
      "completion_length": 400.71875,
      "epoch": 0.023489331181638873,
      "grad_norm": 6.463143728540664,
      "kl": 0.0830078125,
      "learning_rate": 9.986392323793194e-07,
      "loss": 0.0033,
      "reward": 2.108466625213623,
      "reward_std": 0.014811607077717781,
      "rewards/accuracy_reward": 0.9084665775299072,
      "rewards/format_reward": 1.0,
      "step": 1703
    },
    {
      "all_correct": 0.75,
      "all_wrong": 0.0,
      "completion_length": 402.21875,
      "epoch": 0.02350312409484007,
      "grad_norm": 4.436697105443859,
      "kl": 0.0693359375,
      "learning_rate": 9.986376345535193e-07,
      "loss": 0.0028,
      "reward": 2.0995874404907227,
      "reward_std": 0.01052086241543293,
      "rewards/accuracy_reward": 0.8995875120162964,
      "rewards/format_reward": 1.0,
      "step": 1704
    },
    {
      "all_correct": 1.0,
      "all_wrong": 0.0,
      "completion_length": 412.34375,
      "epoch": 0.023516917008041267,
      "grad_norm": 4.539649593034272,
      "kl": 0.078125,
      "learning_rate": 9.986360357914585e-07,
      "loss": 0.0031,
      "reward": 2.1238560676574707,
      "reward_std": 0.009398294612765312,
      "rewards/accuracy_reward": 0.923856258392334,
      "rewards/format_reward": 1.0,
      "step": 1705
    },
    {
      "all_correct": 1.0,
      "all_wrong": 0.0,
      "completion_length": 382.5625,
      "epoch": 0.023530709921242465,
      "grad_norm": 7.069869664039515,
      "kl": 0.0673828125,
      "learning_rate": 9.986344360931398e-07,
      "loss": 0.0027,
      "reward": 2.180812358856201,
      "reward_std": 0.00308728264644742,
      "rewards/accuracy_reward": 0.9808125495910645,
      "rewards/format_reward": 1.0,
      "step": 1706
    },
    {
      "all_correct": 1.0,
      "all_wrong": 0.0,
      "completion_length": 402.25,
      "epoch": 0.023544502834443662,
      "grad_norm": 3.9522791206040804,
      "kl": 0.06787109375,
      "learning_rate": 9.986328354585665e-07,
      "loss": 0.0027,
      "reward": 2.066878080368042,
      "reward_std": 0.010748587548732758,
      "rewards/accuracy_reward": 0.8668781518936157,
      "rewards/format_reward": 1.0,
      "step": 1707
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.0,
      "completion_length": 408.96875,
      "epoch": 0.02355829574764486,
      "grad_norm": 3.7781428036422646,
      "kl": 0.07958984375,
      "learning_rate": 9.986312338877415e-07,
      "loss": 0.0032,
      "reward": 2.0023488998413086,
      "reward_std": 0.011203627102077007,
      "rewards/accuracy_reward": 0.802348792552948,
      "rewards/format_reward": 1.0,
      "step": 1708
    },
    {
      "all_correct": 0.75,
      "all_wrong": 0.0,
      "completion_length": 399.625,
      "epoch": 0.023572088660846056,
      "grad_norm": 3.4957114407424514,
      "kl": 0.072265625,
      "learning_rate": 9.98629631380668e-07,
      "loss": 0.0029,
      "reward": 2.0955874919891357,
      "reward_std": 0.010107596404850483,
      "rewards/accuracy_reward": 0.8955875039100647,
      "rewards/format_reward": 1.0,
      "step": 1709
    },
    {
      "all_correct": 0.75,
      "all_wrong": 0.0,
      "completion_length": 401.1875,
      "epoch": 0.023585881574047254,
      "grad_norm": 1.9033069682896537,
      "kl": 0.0732421875,
      "learning_rate": 9.986280279373484e-07,
      "loss": 0.0029,
      "reward": 2.0947813987731934,
      "reward_std": 0.004276146646589041,
      "rewards/accuracy_reward": 0.894781231880188,
      "rewards/format_reward": 1.0,
      "step": 1710
    },
    {
      "all_correct": 0.0,
      "all_wrong": 0.0,
      "completion_length": 379.3125,
      "epoch": 0.02359967448724845,
      "grad_norm": 5.867222020775312,
      "kl": 0.07421875,
      "learning_rate": 9.986264235577863e-07,
      "loss": 0.003,
      "reward": 1.8767969608306885,
      "reward_std": 0.028966933488845825,
      "rewards/accuracy_reward": 0.6830468773841858,
      "rewards/format_reward": 1.0,
      "step": 1711
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.0,
      "completion_length": 392.53125,
      "epoch": 0.023613467400449648,
      "grad_norm": 2.731920737907278,
      "kl": 0.0673828125,
      "learning_rate": 9.986248182419845e-07,
      "loss": 0.0027,
      "reward": 2.0266876220703125,
      "reward_std": 0.006303221918642521,
      "rewards/accuracy_reward": 0.8266874551773071,
      "rewards/format_reward": 1.0,
      "step": 1712
    },
    {
      "all_correct": 1.0,
      "all_wrong": 0.0,
      "completion_length": 405.3125,
      "epoch": 0.023627260313650846,
      "grad_norm": 2.626970184207237,
      "kl": 0.0771484375,
      "learning_rate": 9.986232119899461e-07,
      "loss": 0.0031,
      "reward": 2.134718894958496,
      "reward_std": 0.011585233733057976,
      "rewards/accuracy_reward": 0.9347187280654907,
      "rewards/format_reward": 1.0,
      "step": 1713
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.0,
      "completion_length": 385.375,
      "epoch": 0.023641053226852043,
      "grad_norm": 2.552727687959991,
      "kl": 0.0732421875,
      "learning_rate": 9.986216048016742e-07,
      "loss": 0.0029,
      "reward": 1.9184062480926514,
      "reward_std": 0.021414421498775482,
      "rewards/accuracy_reward": 0.7184062004089355,
      "rewards/format_reward": 1.0,
      "step": 1714
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.0,
      "completion_length": 412.28125,
      "epoch": 0.02365484614005324,
      "grad_norm": 13.777134298484489,
      "kl": 0.07177734375,
      "learning_rate": 9.986199966771713e-07,
      "loss": 0.0029,
      "reward": 2.0880000591278076,
      "reward_std": 0.01766117289662361,
      "rewards/accuracy_reward": 0.8880000114440918,
      "rewards/format_reward": 1.0,
      "step": 1715
    },
    {
      "all_correct": 0.75,
      "all_wrong": 0.0,
      "completion_length": 397.25,
      "epoch": 0.023668639053254437,
      "grad_norm": 4.4655075172256655,
      "kl": 0.0693359375,
      "learning_rate": 9.98618387616441e-07,
      "loss": 0.0028,
      "reward": 2.0521562099456787,
      "reward_std": 0.006293314974755049,
      "rewards/accuracy_reward": 0.8521562814712524,
      "rewards/format_reward": 1.0,
      "step": 1716
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.0,
      "completion_length": 401.03125,
      "epoch": 0.023682431966455635,
      "grad_norm": 2.6718997760957324,
      "kl": 0.08251953125,
      "learning_rate": 9.986167776194863e-07,
      "loss": 0.0033,
      "reward": 1.9139530658721924,
      "reward_std": 0.020417839288711548,
      "rewards/accuracy_reward": 0.7139531373977661,
      "rewards/format_reward": 1.0,
      "step": 1717
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.0,
      "completion_length": 399.21875,
      "epoch": 0.023696224879656832,
      "grad_norm": 2.4677430153934004,
      "kl": 0.0703125,
      "learning_rate": 9.986151666863097e-07,
      "loss": 0.0028,
      "reward": 2.0550622940063477,
      "reward_std": 0.007356978952884674,
      "rewards/accuracy_reward": 0.8550626039505005,
      "rewards/format_reward": 1.0,
      "step": 1718
    },
    {
      "all_correct": 1.0,
      "all_wrong": 0.0,
      "completion_length": 398.875,
      "epoch": 0.02371001779285803,
      "grad_norm": 2.1939899815669426,
      "kl": 0.068359375,
      "learning_rate": 9.986135548169149e-07,
      "loss": 0.0027,
      "reward": 2.0898125171661377,
      "reward_std": 0.007136219646781683,
      "rewards/accuracy_reward": 0.8898124694824219,
      "rewards/format_reward": 1.0,
      "step": 1719
    },
    {
      "all_correct": 1.0,
      "all_wrong": 0.0,
      "completion_length": 387.40625,
      "epoch": 0.023723810706059226,
      "grad_norm": 2.515741061054989,
      "kl": 0.0771484375,
      "learning_rate": 9.986119420113043e-07,
      "loss": 0.0031,
      "reward": 2.101253032684326,
      "reward_std": 0.017434094101190567,
      "rewards/accuracy_reward": 0.9012531638145447,
      "rewards/format_reward": 1.0,
      "step": 1720
    },
    {
      "all_correct": 1.0,
      "all_wrong": 0.0,
      "completion_length": 400.46875,
      "epoch": 0.023737603619260424,
      "grad_norm": 1.600265154399046,
      "kl": 0.060791015625,
      "learning_rate": 9.986103282694812e-07,
      "loss": 0.0024,
      "reward": 2.181375026702881,
      "reward_std": 0.00671817222610116,
      "rewards/accuracy_reward": 0.9813750386238098,
      "rewards/format_reward": 1.0,
      "step": 1721
    },
    {
      "all_correct": 1.0,
      "all_wrong": 0.0,
      "completion_length": 402.9375,
      "epoch": 0.02375139653246162,
      "grad_norm": 3.0599808020254464,
      "kl": 0.076171875,
      "learning_rate": 9.986087135914488e-07,
      "loss": 0.003,
      "reward": 2.093647003173828,
      "reward_std": 0.017799291759729385,
      "rewards/accuracy_reward": 0.8936468362808228,
      "rewards/format_reward": 1.0,
      "step": 1722
    },
    {
      "all_correct": 0.75,
      "all_wrong": 0.0,
      "completion_length": 409.125,
      "epoch": 0.023765189445662818,
      "grad_norm": 3.319295020392552,
      "kl": 0.0712890625,
      "learning_rate": 9.9860709797721e-07,
      "loss": 0.0029,
      "reward": 2.127687692642212,
      "reward_std": 0.02012709528207779,
      "rewards/accuracy_reward": 0.9276874661445618,
      "rewards/format_reward": 1.0,
      "step": 1723
    },
    {
      "all_correct": 0.75,
      "all_wrong": 0.0,
      "completion_length": 395.78125,
      "epoch": 0.023778982358864015,
      "grad_norm": 2.7782832942336793,
      "kl": 0.07470703125,
      "learning_rate": 9.986054814267677e-07,
      "loss": 0.003,
      "reward": 2.1031250953674316,
      "reward_std": 0.02038407325744629,
      "rewards/accuracy_reward": 0.9031249284744263,
      "rewards/format_reward": 1.0,
      "step": 1724
    },
    {
      "all_correct": 1.0,
      "all_wrong": 0.0,
      "completion_length": 395.5,
      "epoch": 0.023792775272065213,
      "grad_norm": 12.38354490808643,
      "kl": 0.0712890625,
      "learning_rate": 9.98603863940125e-07,
      "loss": 0.0029,
      "reward": 2.1373751163482666,
      "reward_std": 0.015513171441853046,
      "rewards/accuracy_reward": 0.937375009059906,
      "rewards/format_reward": 1.0,
      "step": 1725
    },
    {
      "all_correct": 1.0,
      "all_wrong": 0.0,
      "completion_length": 398.90625,
      "epoch": 0.02380656818526641,
      "grad_norm": 4.456827369299883,
      "kl": 0.078125,
      "learning_rate": 9.986022455172852e-07,
      "loss": 0.0031,
      "reward": 2.1432812213897705,
      "reward_std": 0.015676815062761307,
      "rewards/accuracy_reward": 0.9432812333106995,
      "rewards/format_reward": 1.0,
      "step": 1726
    },
    {
      "all_correct": 0.75,
      "all_wrong": 0.0,
      "completion_length": 388.4375,
      "epoch": 0.023820361098467607,
      "grad_norm": 16.67054442452413,
      "kl": 0.0712890625,
      "learning_rate": 9.98600626158251e-07,
      "loss": 0.0029,
      "reward": 2.1101250648498535,
      "reward_std": 0.04009168967604637,
      "rewards/accuracy_reward": 0.9163749814033508,
      "rewards/format_reward": 1.0,
      "step": 1727
    },
    {
      "all_correct": 1.0,
      "all_wrong": 0.0,
      "completion_length": 398.3125,
      "epoch": 0.023834154011668805,
      "grad_norm": 3.969631658516179,
      "kl": 0.0703125,
      "learning_rate": 9.985990058630255e-07,
      "loss": 0.0028,
      "reward": 2.138625144958496,
      "reward_std": 0.009320787154138088,
      "rewards/accuracy_reward": 0.9386250376701355,
      "rewards/format_reward": 1.0,
      "step": 1728
    },
    {
      "all_correct": 0.75,
      "all_wrong": 0.0,
      "completion_length": 401.53125,
      "epoch": 0.023847946924870002,
      "grad_norm": 1.8686466282663734,
      "kl": 0.0732421875,
      "learning_rate": 9.985973846316118e-07,
      "loss": 0.0028,
      "reward": 2.099249839782715,
      "reward_std": 0.0196660328656435,
      "rewards/accuracy_reward": 0.9054999351501465,
      "rewards/format_reward": 1.0,
      "step": 1729
    },
    {
      "all_correct": 0.0,
      "all_wrong": 0.0,
      "completion_length": 399.0,
      "epoch": 0.0238617398380712,
      "grad_norm": 4.4299319900147305,
      "kl": 0.07080078125,
      "learning_rate": 9.98595762464013e-07,
      "loss": 0.0028,
      "reward": 1.9225938320159912,
      "reward_std": 0.01270025409758091,
      "rewards/accuracy_reward": 0.7225937843322754,
      "rewards/format_reward": 1.0,
      "step": 1730
    },
    {
      "all_correct": 0.75,
      "all_wrong": 0.0,
      "completion_length": 399.71875,
      "epoch": 0.023875532751272396,
      "grad_norm": 2.2146126289941153,
      "kl": 0.06982421875,
      "learning_rate": 9.985941393602324e-07,
      "loss": 0.0028,
      "reward": 2.0733437538146973,
      "reward_std": 0.016932286322116852,
      "rewards/accuracy_reward": 0.8733437657356262,
      "rewards/format_reward": 1.0,
      "step": 1731
    },
    {
      "all_correct": 1.0,
      "all_wrong": 0.0,
      "completion_length": 400.1875,
      "epoch": 0.023889325664473594,
      "grad_norm": 1.861701969324973,
      "kl": 0.06884765625,
      "learning_rate": 9.985925153202724e-07,
      "loss": 0.0028,
      "reward": 2.149656295776367,
      "reward_std": 0.008015827275812626,
      "rewards/accuracy_reward": 0.9496562480926514,
      "rewards/format_reward": 1.0,
      "step": 1732
    },
    {
      "all_correct": 0.75,
      "all_wrong": 0.0,
      "completion_length": 409.4375,
      "epoch": 0.02390311857767479,
      "grad_norm": 1.4679235471717649,
      "kl": 0.0732421875,
      "learning_rate": 9.985908903441364e-07,
      "loss": 0.0029,
      "reward": 2.163968563079834,
      "reward_std": 0.019429108127951622,
      "rewards/accuracy_reward": 0.9702187180519104,
      "rewards/format_reward": 1.0,
      "step": 1733
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.0,
      "completion_length": 425.46875,
      "epoch": 0.023916911490875988,
      "grad_norm": 5.2470395522560604,
      "kl": 0.07177734375,
      "learning_rate": 9.985892644318274e-07,
      "loss": 0.0029,
      "reward": 2.0458436012268066,
      "reward_std": 0.0353349968791008,
      "rewards/accuracy_reward": 0.8520936965942383,
      "rewards/format_reward": 1.0,
      "step": 1734
    },
    {
      "all_correct": 1.0,
      "all_wrong": 0.0,
      "completion_length": 411.46875,
      "epoch": 0.023930704404077185,
      "grad_norm": 2.3126466981488973,
      "kl": 0.0732421875,
      "learning_rate": 9.985876375833486e-07,
      "loss": 0.0029,
      "reward": 2.09793758392334,
      "reward_std": 0.013394429348409176,
      "rewards/accuracy_reward": 0.8979374766349792,
      "rewards/format_reward": 1.0,
      "step": 1735
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.0,
      "completion_length": 417.78125,
      "epoch": 0.023944497317278383,
      "grad_norm": 4.51834999228688,
      "kl": 0.06494140625,
      "learning_rate": 9.985860097987032e-07,
      "loss": 0.0026,
      "reward": 2.112375020980835,
      "reward_std": 0.03277178108692169,
      "rewards/accuracy_reward": 0.918624997138977,
      "rewards/format_reward": 1.0,
      "step": 1736
    },
    {
      "all_correct": 0.75,
      "all_wrong": 0.0,
      "completion_length": 390.75,
      "epoch": 0.02395829023047958,
      "grad_norm": 2.5137681586952474,
      "kl": 0.0771484375,
      "learning_rate": 9.985843810778936e-07,
      "loss": 0.0031,
      "reward": 2.096968650817871,
      "reward_std": 0.016660798341035843,
      "rewards/accuracy_reward": 0.8969687223434448,
      "rewards/format_reward": 1.0,
      "step": 1737
    },
    {
      "all_correct": 0.75,
      "all_wrong": 0.0,
      "completion_length": 410.53125,
      "epoch": 0.023972083143680777,
      "grad_norm": 4.453886849240466,
      "kl": 0.06640625,
      "learning_rate": 9.985827514209236e-07,
      "loss": 0.0026,
      "reward": 2.0604376792907715,
      "reward_std": 0.007918298244476318,
      "rewards/accuracy_reward": 0.8604375123977661,
      "rewards/format_reward": 1.0,
      "step": 1738
    },
    {
      "all_correct": 0.75,
      "all_wrong": 0.0,
      "completion_length": 411.03125,
      "epoch": 0.023985876056881975,
      "grad_norm": 2.4819342067203856,
      "kl": 0.07666015625,
      "learning_rate": 9.985811208277957e-07,
      "loss": 0.0031,
      "reward": 1.9915937185287476,
      "reward_std": 0.00937240943312645,
      "rewards/accuracy_reward": 0.7915937900543213,
      "rewards/format_reward": 1.0,
      "step": 1739
    },
    {
      "all_correct": 1.0,
      "all_wrong": 0.0,
      "completion_length": 408.03125,
      "epoch": 0.023999668970083172,
      "grad_norm": 3.6585757122772673,
      "kl": 0.068359375,
      "learning_rate": 9.985794892985131e-07,
      "loss": 0.0027,
      "reward": 2.1114063262939453,
      "reward_std": 0.031646594405174255,
      "rewards/accuracy_reward": 0.9114062786102295,
      "rewards/format_reward": 1.0,
      "step": 1740
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.0,
      "completion_length": 419.0,
      "epoch": 0.02401346188328437,
      "grad_norm": 2.5450651610331296,
      "kl": 0.08447265625,
      "learning_rate": 9.985778568330791e-07,
      "loss": 0.0034,
      "reward": 2.0655624866485596,
      "reward_std": 0.04809194430708885,
      "rewards/accuracy_reward": 0.8780624866485596,
      "rewards/format_reward": 1.0,
      "step": 1741
    },
    {
      "all_correct": 0.25,
      "all_wrong": 0.0,
      "completion_length": 425.09375,
      "epoch": 0.024027254796485566,
      "grad_norm": 2.530902592900987,
      "kl": 0.07275390625,
      "learning_rate": 9.985762234314967e-07,
      "loss": 0.0029,
      "reward": 1.9913125038146973,
      "reward_std": 0.011736673302948475,
      "rewards/accuracy_reward": 0.7913125157356262,
      "rewards/format_reward": 1.0,
      "step": 1742
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.0,
      "completion_length": 392.4375,
      "epoch": 0.024041047709686764,
      "grad_norm": 2.6140164331444797,
      "kl": 0.0810546875,
      "learning_rate": 9.985745890937688e-07,
      "loss": 0.0033,
      "reward": 2.037656307220459,
      "reward_std": 0.0340898334980011,
      "rewards/accuracy_reward": 0.8501562476158142,
      "rewards/format_reward": 1.0,
      "step": 1743
    },
    {
      "all_correct": 0.75,
      "all_wrong": 0.0,
      "completion_length": 395.65625,
      "epoch": 0.02405484062288796,
      "grad_norm": 1.7897864659100733,
      "kl": 0.07373046875,
      "learning_rate": 9.985729538198986e-07,
      "loss": 0.003,
      "reward": 2.1214065551757812,
      "reward_std": 0.02272145263850689,
      "rewards/accuracy_reward": 0.9276562333106995,
      "rewards/format_reward": 1.0,
      "step": 1744
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.0,
      "completion_length": 385.90625,
      "epoch": 0.024068633536089158,
      "grad_norm": 2.446121041993616,
      "kl": 0.076171875,
      "learning_rate": 9.985713176098888e-07,
      "loss": 0.0031,
      "reward": 2.0507724285125732,
      "reward_std": 0.007350444328039885,
      "rewards/accuracy_reward": 0.8507723212242126,
      "rewards/format_reward": 1.0,
      "step": 1745
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.0,
      "completion_length": 413.0625,
      "epoch": 0.024082426449290355,
      "grad_norm": 2.7705725535301227,
      "kl": 0.0673828125,
      "learning_rate": 9.98569680463743e-07,
      "loss": 0.0027,
      "reward": 2.0127811431884766,
      "reward_std": 0.03422151133418083,
      "rewards/accuracy_reward": 0.8190312385559082,
      "rewards/format_reward": 1.0,
      "step": 1746
    },
    {
      "all_correct": 1.0,
      "all_wrong": 0.0,
      "completion_length": 405.0,
      "epoch": 0.024096219362491553,
      "grad_norm": 2.3872010424482477,
      "kl": 0.07470703125,
      "learning_rate": 9.985680423814642e-07,
      "loss": 0.003,
      "reward": 2.1339688301086426,
      "reward_std": 0.02170136198401451,
      "rewards/accuracy_reward": 0.9339687824249268,
      "rewards/format_reward": 1.0,
      "step": 1747
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.0,
      "completion_length": 398.28125,
      "epoch": 0.02411001227569275,
      "grad_norm": 2.6316361218681465,
      "kl": 0.072265625,
      "learning_rate": 9.985664033630553e-07,
      "loss": 0.0029,
      "reward": 2.074937582015991,
      "reward_std": 0.029040640220046043,
      "rewards/accuracy_reward": 0.8811874985694885,
      "rewards/format_reward": 1.0,
      "step": 1748
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.0,
      "completion_length": 403.90625,
      "epoch": 0.024123805188893947,
      "grad_norm": 3.405750619703905,
      "kl": 0.0712890625,
      "learning_rate": 9.985647634085194e-07,
      "loss": 0.0029,
      "reward": 2.0605313777923584,
      "reward_std": 0.03339112550020218,
      "rewards/accuracy_reward": 0.8667812943458557,
      "rewards/format_reward": 1.0,
      "step": 1749
    },
    {
      "all_correct": 0.75,
      "all_wrong": 0.0,
      "completion_length": 385.03125,
      "epoch": 0.024137598102095145,
      "grad_norm": 2.91977031272727,
      "kl": 0.0751953125,
      "learning_rate": 9.985631225178598e-07,
      "loss": 0.003,
      "reward": 2.0946874618530273,
      "reward_std": 0.019197026267647743,
      "rewards/accuracy_reward": 0.8946875333786011,
      "rewards/format_reward": 1.0,
      "step": 1750
    },
    {
      "all_correct": 0.75,
      "all_wrong": 0.0,
      "completion_length": 397.75,
      "epoch": 0.024151391015296342,
      "grad_norm": 3.604232767070265,
      "kl": 0.0810546875,
      "learning_rate": 9.985614806910792e-07,
      "loss": 0.0032,
      "reward": 2.076906204223633,
      "reward_std": 0.019419647753238678,
      "rewards/accuracy_reward": 0.8769062757492065,
      "rewards/format_reward": 1.0,
      "step": 1751
    },
    {
      "all_correct": 0.75,
      "all_wrong": 0.0,
      "completion_length": 410.78125,
      "epoch": 0.02416518392849754,
      "grad_norm": 2.376437580329351,
      "kl": 0.0751953125,
      "learning_rate": 9.985598379281808e-07,
      "loss": 0.003,
      "reward": 2.0655312538146973,
      "reward_std": 0.01601465232670307,
      "rewards/accuracy_reward": 0.8655312061309814,
      "rewards/format_reward": 1.0,
      "step": 1752
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.0,
      "completion_length": 384.28125,
      "epoch": 0.024178976841698736,
      "grad_norm": 4.116061292435113,
      "kl": 0.08251953125,
      "learning_rate": 9.985581942291675e-07,
      "loss": 0.0033,
      "reward": 2.052500009536743,
      "reward_std": 0.016271580010652542,
      "rewards/accuracy_reward": 0.8524999618530273,
      "rewards/format_reward": 1.0,
      "step": 1753
    },
    {
      "all_correct": 0.75,
      "all_wrong": 0.0,
      "completion_length": 416.28125,
      "epoch": 0.024192769754899934,
      "grad_norm": 2.8459132192306806,
      "kl": 0.0888671875,
      "learning_rate": 9.985565495940431e-07,
      "loss": 0.0035,
      "reward": 2.0820937156677246,
      "reward_std": 0.025291379541158676,
      "rewards/accuracy_reward": 0.8820937275886536,
      "rewards/format_reward": 1.0,
      "step": 1754
    },
    {
      "all_correct": 0.75,
      "all_wrong": 0.0,
      "completion_length": 401.375,
      "epoch": 0.02420656266810113,
      "grad_norm": 1.4439906845419863,
      "kl": 0.0693359375,
      "learning_rate": 9.985549040228101e-07,
      "loss": 0.0028,
      "reward": 2.022624969482422,
      "reward_std": 0.0030057914555072784,
      "rewards/accuracy_reward": 0.8226249814033508,
      "rewards/format_reward": 1.0,
      "step": 1755
    },
    {
      "all_correct": 1.0,
      "all_wrong": 0.0,
      "completion_length": 413.46875,
      "epoch": 0.024220355581302328,
      "grad_norm": 2.435579747925683,
      "kl": 0.0849609375,
      "learning_rate": 9.985532575154717e-07,
      "loss": 0.0034,
      "reward": 2.1383438110351562,
      "reward_std": 0.018488572910428047,
      "rewards/accuracy_reward": 0.9383437633514404,
      "rewards/format_reward": 1.0,
      "step": 1756
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.0,
      "completion_length": 399.125,
      "epoch": 0.024234148494503525,
      "grad_norm": 3.0120026475764483,
      "kl": 0.0771484375,
      "learning_rate": 9.98551610072031e-07,
      "loss": 0.0031,
      "reward": 2.035656213760376,
      "reward_std": 0.009117106907069683,
      "rewards/accuracy_reward": 0.8356562852859497,
      "rewards/format_reward": 1.0,
      "step": 1757
    },
    {
      "all_correct": 1.0,
      "all_wrong": 0.0,
      "completion_length": 399.53125,
      "epoch": 0.024247941407704723,
      "grad_norm": 2.5538727615336247,
      "kl": 0.08203125,
      "learning_rate": 9.98549961692491e-07,
      "loss": 0.0033,
      "reward": 2.126584529876709,
      "reward_std": 0.0063272942788898945,
      "rewards/accuracy_reward": 0.9265843629837036,
      "rewards/format_reward": 1.0,
      "step": 1758
    },
    {
      "all_correct": 1.0,
      "all_wrong": 0.0,
      "completion_length": 398.875,
      "epoch": 0.02426173432090592,
      "grad_norm": 8.37522776549557,
      "kl": 0.07177734375,
      "learning_rate": 9.98548312376855e-07,
      "loss": 0.0029,
      "reward": 2.1524062156677246,
      "reward_std": 0.010602997615933418,
      "rewards/accuracy_reward": 0.9524062275886536,
      "rewards/format_reward": 1.0,
      "step": 1759
    },
    {
      "all_correct": 0.75,
      "all_wrong": 0.0,
      "completion_length": 405.125,
      "epoch": 0.024275527234107117,
      "grad_norm": 3.507332854838465,
      "kl": 0.08349609375,
      "learning_rate": 9.98546662125126e-07,
      "loss": 0.0033,
      "reward": 2.0226876735687256,
      "reward_std": 0.01573045551776886,
      "rewards/accuracy_reward": 0.8226875066757202,
      "rewards/format_reward": 1.0,
      "step": 1760
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.0,
      "completion_length": 410.34375,
      "epoch": 0.024289320147308315,
      "grad_norm": 5.809003785345363,
      "kl": 0.08447265625,
      "learning_rate": 9.98545010937307e-07,
      "loss": 0.0034,
      "reward": 2.03515625,
      "reward_std": 0.019804697483778,
      "rewards/accuracy_reward": 0.835156261920929,
      "rewards/format_reward": 1.0,
      "step": 1761
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.0,
      "completion_length": 413.78125,
      "epoch": 0.024303113060509512,
      "grad_norm": 3.0305832348923687,
      "kl": 0.0859375,
      "learning_rate": 9.98543358813401e-07,
      "loss": 0.0034,
      "reward": 2.052062511444092,
      "reward_std": 0.03612096980214119,
      "rewards/accuracy_reward": 0.8583125472068787,
      "rewards/format_reward": 1.0,
      "step": 1762
    },
    {
      "all_correct": 0.75,
      "all_wrong": 0.0,
      "completion_length": 393.78125,
      "epoch": 0.02431690597371071,
      "grad_norm": 3.5563079913533424,
      "kl": 0.08740234375,
      "learning_rate": 9.985417057534117e-07,
      "loss": 0.0035,
      "reward": 2.1191563606262207,
      "reward_std": 0.016575699672102928,
      "rewards/accuracy_reward": 0.9191562533378601,
      "rewards/format_reward": 1.0,
      "step": 1763
    },
    {
      "all_correct": 0.25,
      "all_wrong": 0.0,
      "completion_length": 412.78125,
      "epoch": 0.024330698886911906,
      "grad_norm": 3.0645052581267507,
      "kl": 0.0888671875,
      "learning_rate": 9.985400517573417e-07,
      "loss": 0.0036,
      "reward": 2.044740676879883,
      "reward_std": 0.028551694005727768,
      "rewards/accuracy_reward": 0.8509905934333801,
      "rewards/format_reward": 1.0,
      "step": 1764
    },
    {
      "all_correct": 0.75,
      "all_wrong": 0.0,
      "completion_length": 403.09375,
      "epoch": 0.024344491800113104,
      "grad_norm": 2.765856515806997,
      "kl": 0.08740234375,
      "learning_rate": 9.985383968251941e-07,
      "loss": 0.0035,
      "reward": 2.066312789916992,
      "reward_std": 0.01751692220568657,
      "rewards/accuracy_reward": 0.8663125038146973,
      "rewards/format_reward": 1.0,
      "step": 1765
    },
    {
      "all_correct": 0.75,
      "all_wrong": 0.0,
      "completion_length": 387.375,
      "epoch": 0.024358284713314297,
      "grad_norm": 2.015853784114689,
      "kl": 0.08447265625,
      "learning_rate": 9.98536740956972e-07,
      "loss": 0.0034,
      "reward": 2.103749990463257,
      "reward_std": 0.013015479780733585,
      "rewards/accuracy_reward": 0.9037500023841858,
      "rewards/format_reward": 1.0,
      "step": 1766
    },
    {
      "all_correct": 1.0,
      "all_wrong": 0.0,
      "completion_length": 409.0625,
      "epoch": 0.024372077626515495,
      "grad_norm": 3.3477428713056567,
      "kl": 0.087890625,
      "learning_rate": 9.985350841526788e-07,
      "loss": 0.0035,
      "reward": 2.0847811698913574,
      "reward_std": 0.023640643805265427,
      "rewards/accuracy_reward": 0.8847812414169312,
      "rewards/format_reward": 1.0,
      "step": 1767
    },
    {
      "all_correct": 0.75,
      "all_wrong": 0.0,
      "completion_length": 416.75,
      "epoch": 0.024385870539716692,
      "grad_norm": 6.017892808909625,
      "kl": 0.08935546875,
      "learning_rate": 9.985334264123174e-07,
      "loss": 0.0036,
      "reward": 2.047187328338623,
      "reward_std": 0.014335026033222675,
      "rewards/accuracy_reward": 0.8471875190734863,
      "rewards/format_reward": 1.0,
      "step": 1768
    },
    {
      "all_correct": 0.75,
      "all_wrong": 0.0,
      "completion_length": 397.8125,
      "epoch": 0.02439966345291789,
      "grad_norm": 2.698199071657015,
      "kl": 0.08349609375,
      "learning_rate": 9.985317677358908e-07,
      "loss": 0.0033,
      "reward": 2.010718822479248,
      "reward_std": 0.014230258762836456,
      "rewards/accuracy_reward": 0.8107187151908875,
      "rewards/format_reward": 1.0,
      "step": 1769
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.0,
      "completion_length": 400.75,
      "epoch": 0.024413456366119086,
      "grad_norm": 2.304985842183476,
      "kl": 0.0751953125,
      "learning_rate": 9.985301081234025e-07,
      "loss": 0.003,
      "reward": 2.0739998817443848,
      "reward_std": 0.009021366946399212,
      "rewards/accuracy_reward": 0.8739999532699585,
      "rewards/format_reward": 1.0,
      "step": 1770
    },
    {
      "all_correct": 1.0,
      "all_wrong": 0.0,
      "completion_length": 410.75,
      "epoch": 0.024427249279320284,
      "grad_norm": 2.616584686497504,
      "kl": 0.08056640625,
      "learning_rate": 9.985284475748552e-07,
      "loss": 0.0033,
      "reward": 2.149031162261963,
      "reward_std": 0.017312081530690193,
      "rewards/accuracy_reward": 0.9490312337875366,
      "rewards/format_reward": 1.0,
      "step": 1771
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.0,
      "completion_length": 406.46875,
      "epoch": 0.02444104219252148,
      "grad_norm": 3.7454364850367723,
      "kl": 0.0791015625,
      "learning_rate": 9.985267860902522e-07,
      "loss": 0.0032,
      "reward": 2.0531249046325684,
      "reward_std": 0.012606385163962841,
      "rewards/accuracy_reward": 0.8531250357627869,
      "rewards/format_reward": 1.0,
      "step": 1772
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.0,
      "completion_length": 400.21875,
      "epoch": 0.02445483510572268,
      "grad_norm": 2.1842734408082483,
      "kl": 0.08203125,
      "learning_rate": 9.985251236695967e-07,
      "loss": 0.0033,
      "reward": 2.0401875972747803,
      "reward_std": 0.02127690799534321,
      "rewards/accuracy_reward": 0.8464374542236328,
      "rewards/format_reward": 1.0,
      "step": 1773
    },
    {
      "all_correct": 0.75,
      "all_wrong": 0.0,
      "completion_length": 414.34375,
      "epoch": 0.024468628018923876,
      "grad_norm": 6.173423938420589,
      "kl": 0.0791015625,
      "learning_rate": 9.985234603128917e-07,
      "loss": 0.0032,
      "reward": 2.0656564235687256,
      "reward_std": 0.018526801839470863,
      "rewards/accuracy_reward": 0.8656562566757202,
      "rewards/format_reward": 1.0,
      "step": 1774
    },
    {
      "all_correct": 0.75,
      "all_wrong": 0.0,
      "completion_length": 401.4375,
      "epoch": 0.024482420932125073,
      "grad_norm": 2.7349810771321166,
      "kl": 0.08056640625,
      "learning_rate": 9.985217960201402e-07,
      "loss": 0.0032,
      "reward": 2.1108124256134033,
      "reward_std": 0.018724944442510605,
      "rewards/accuracy_reward": 0.910812497138977,
      "rewards/format_reward": 1.0,
      "step": 1775
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.0,
      "completion_length": 410.5,
      "epoch": 0.02449621384532627,
      "grad_norm": 9.06553580363702,
      "kl": 0.0791015625,
      "learning_rate": 9.985201307913456e-07,
      "loss": 0.0031,
      "reward": 2.0666468143463135,
      "reward_std": 0.03265304118394852,
      "rewards/accuracy_reward": 0.8666468858718872,
      "rewards/format_reward": 1.0,
      "step": 1776
    },
    {
      "all_correct": 0.75,
      "all_wrong": 0.0,
      "completion_length": 421.40625,
      "epoch": 0.024510006758527467,
      "grad_norm": 4.331300934590727,
      "kl": 0.07666015625,
      "learning_rate": 9.98518464626511e-07,
      "loss": 0.0031,
      "reward": 2.1221561431884766,
      "reward_std": 0.0323910228908062,
      "rewards/accuracy_reward": 0.9284062385559082,
      "rewards/format_reward": 1.0,
      "step": 1777
    },
    {
      "all_correct": 1.0,
      "all_wrong": 0.0,
      "completion_length": 406.625,
      "epoch": 0.024523799671728665,
      "grad_norm": 2.4672398380474148,
      "kl": 0.078125,
      "learning_rate": 9.985167975256393e-07,
      "loss": 0.0031,
      "reward": 2.141625165939331,
      "reward_std": 0.014096378348767757,
      "rewards/accuracy_reward": 0.9416250586509705,
      "rewards/format_reward": 1.0,
      "step": 1778
    },
    {
      "all_correct": 0.75,
      "all_wrong": 0.0,
      "completion_length": 407.6875,
      "epoch": 0.024537592584929862,
      "grad_norm": 34.324223710054575,
      "kl": 0.09765625,
      "learning_rate": 9.985151294887338e-07,
      "loss": 0.0039,
      "reward": 2.0224688053131104,
      "reward_std": 0.025731824338436127,
      "rewards/accuracy_reward": 0.8224687576293945,
      "rewards/format_reward": 1.0,
      "step": 1779
    },
    {
      "all_correct": 0.75,
      "all_wrong": 0.0,
      "completion_length": 402.53125,
      "epoch": 0.02455138549813106,
      "grad_norm": 2.70846013690555,
      "kl": 0.083984375,
      "learning_rate": 9.985134605157975e-07,
      "loss": 0.0033,
      "reward": 2.0834689140319824,
      "reward_std": 0.016936348751187325,
      "rewards/accuracy_reward": 0.883468747138977,
      "rewards/format_reward": 1.0,
      "step": 1780
    },
    {
      "all_correct": 1.0,
      "all_wrong": 0.0,
      "completion_length": 397.03125,
      "epoch": 0.024565178411332256,
      "grad_norm": 2.653429903702211,
      "kl": 0.080078125,
      "learning_rate": 9.985117906068337e-07,
      "loss": 0.0032,
      "reward": 2.087218761444092,
      "reward_std": 0.026929259300231934,
      "rewards/accuracy_reward": 0.8872188329696655,
      "rewards/format_reward": 1.0,
      "step": 1781
    },
    {
      "all_correct": 0.75,
      "all_wrong": 0.0,
      "completion_length": 402.8125,
      "epoch": 0.024578971324533454,
      "grad_norm": 2.402392929045198,
      "kl": 0.08203125,
      "learning_rate": 9.985101197618456e-07,
      "loss": 0.0033,
      "reward": 1.9732187986373901,
      "reward_std": 0.02099413424730301,
      "rewards/accuracy_reward": 0.7732187509536743,
      "rewards/format_reward": 1.0,
      "step": 1782
    },
    {
      "all_correct": 0.75,
      "all_wrong": 0.0,
      "completion_length": 402.25,
      "epoch": 0.02459276423773465,
      "grad_norm": 3.2217360796310057,
      "kl": 0.0771484375,
      "learning_rate": 9.98508447980836e-07,
      "loss": 0.0031,
      "reward": 2.0893125534057617,
      "reward_std": 0.01791352406144142,
      "rewards/accuracy_reward": 0.8893125057220459,
      "rewards/format_reward": 1.0,
      "step": 1783
    },
    {
      "all_correct": 0.75,
      "all_wrong": 0.0,
      "completion_length": 408.0625,
      "epoch": 0.02460655715093585,
      "grad_norm": 2.683709335052171,
      "kl": 0.078125,
      "learning_rate": 9.985067752638084e-07,
      "loss": 0.0031,
      "reward": 2.1088438034057617,
      "reward_std": 0.021613825112581253,
      "rewards/accuracy_reward": 0.9088437557220459,
      "rewards/format_reward": 1.0,
      "step": 1784
    },
    {
      "all_correct": 1.0,
      "all_wrong": 0.0,
      "completion_length": 400.75,
      "epoch": 0.024620350064137046,
      "grad_norm": 2.769526538229454,
      "kl": 0.08837890625,
      "learning_rate": 9.985051016107656e-07,
      "loss": 0.0035,
      "reward": 2.144731283187866,
      "reward_std": 0.007910585030913353,
      "rewards/accuracy_reward": 0.9447312355041504,
      "rewards/format_reward": 1.0,
      "step": 1785
    },
    {
      "all_correct": 1.0,
      "all_wrong": 0.0,
      "completion_length": 419.46875,
      "epoch": 0.024634142977338243,
      "grad_norm": 1.985566695953307,
      "kl": 0.0830078125,
      "learning_rate": 9.985034270217112e-07,
      "loss": 0.0033,
      "reward": 2.150343656539917,
      "reward_std": 0.017256196588277817,
      "rewards/accuracy_reward": 0.9503437280654907,
      "rewards/format_reward": 1.0,
      "step": 1786
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.0,
      "completion_length": 414.25,
      "epoch": 0.02464793589053944,
      "grad_norm": 2.725957722445619,
      "kl": 0.0849609375,
      "learning_rate": 9.985017514966478e-07,
      "loss": 0.0034,
      "reward": 2.0619373321533203,
      "reward_std": 0.022585805505514145,
      "rewards/accuracy_reward": 0.8619375228881836,
      "rewards/format_reward": 1.0,
      "step": 1787
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.0,
      "completion_length": 406.34375,
      "epoch": 0.024661728803740637,
      "grad_norm": 2.725238061648846,
      "kl": 0.078125,
      "learning_rate": 9.98500075035579e-07,
      "loss": 0.0031,
      "reward": 2.0465939044952393,
      "reward_std": 0.026005594059824944,
      "rewards/accuracy_reward": 0.8528437614440918,
      "rewards/format_reward": 1.0,
      "step": 1788
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.0,
      "completion_length": 393.78125,
      "epoch": 0.024675521716941835,
      "grad_norm": 4.823457412712981,
      "kl": 0.0830078125,
      "learning_rate": 9.984983976385077e-07,
      "loss": 0.0033,
      "reward": 2.0460939407348633,
      "reward_std": 0.08084728568792343,
      "rewards/accuracy_reward": 0.8460937738418579,
      "rewards/format_reward": 1.0,
      "step": 1789
    },
    {
      "all_correct": 0.75,
      "all_wrong": 0.0,
      "completion_length": 403.09375,
      "epoch": 0.024689314630143032,
      "grad_norm": 4.581116446149254,
      "kl": 0.07470703125,
      "learning_rate": 9.98496719305437e-07,
      "loss": 0.003,
      "reward": 2.1031155586242676,
      "reward_std": 0.03143152594566345,
      "rewards/accuracy_reward": 0.9093655943870544,
      "rewards/format_reward": 1.0,
      "step": 1790
    },
    {
      "all_correct": 1.0,
      "all_wrong": 0.0,
      "completion_length": 406.96875,
      "epoch": 0.02470310754334423,
      "grad_norm": 2.876962599508138,
      "kl": 0.087890625,
      "learning_rate": 9.984950400363704e-07,
      "loss": 0.0035,
      "reward": 2.1196563243865967,
      "reward_std": 0.012997458688914776,
      "rewards/accuracy_reward": 0.9196562767028809,
      "rewards/format_reward": 1.0,
      "step": 1791
    },
    {
      "all_correct": 0.75,
      "all_wrong": 0.0,
      "completion_length": 398.84375,
      "epoch": 0.024716900456545426,
      "grad_norm": 2.2778762938618273,
      "kl": 0.0751953125,
      "learning_rate": 9.984933598313105e-07,
      "loss": 0.003,
      "reward": 2.1229686737060547,
      "reward_std": 0.013324317522346973,
      "rewards/accuracy_reward": 0.9229687452316284,
      "rewards/format_reward": 1.0,
      "step": 1792
    },
    {
      "all_correct": 0.75,
      "all_wrong": 0.0,
      "completion_length": 403.15625,
      "epoch": 0.024730693369746624,
      "grad_norm": 4.2082699145935,
      "kl": 0.078125,
      "learning_rate": 9.98491678690261e-07,
      "loss": 0.0031,
      "reward": 2.080031394958496,
      "reward_std": 0.01834378018975258,
      "rewards/accuracy_reward": 0.8800312876701355,
      "rewards/format_reward": 1.0,
      "step": 1793
    },
    {
      "all_correct": 0.25,
      "all_wrong": 0.0,
      "completion_length": 396.34375,
      "epoch": 0.02474448628294782,
      "grad_norm": 2.2298200484881514,
      "kl": 0.08837890625,
      "learning_rate": 9.984899966132247e-07,
      "loss": 0.0035,
      "reward": 2.0351874828338623,
      "reward_std": 0.03237765282392502,
      "rewards/accuracy_reward": 0.8414374589920044,
      "rewards/format_reward": 1.0,
      "step": 1794
    },
    {
      "all_correct": 1.0,
      "all_wrong": 0.0,
      "completion_length": 402.09375,
      "epoch": 0.024758279196149018,
      "grad_norm": 4.421820727567943,
      "kl": 0.07421875,
      "learning_rate": 9.984883136002051e-07,
      "loss": 0.003,
      "reward": 2.133000135421753,
      "reward_std": 0.01489143818616867,
      "rewards/accuracy_reward": 0.9329999685287476,
      "rewards/format_reward": 1.0,
      "step": 1795
    },
    {
      "all_correct": 1.0,
      "all_wrong": 0.0,
      "completion_length": 393.46875,
      "epoch": 0.024772072109350216,
      "grad_norm": 3.0742689286485527,
      "kl": 0.080078125,
      "learning_rate": 9.98486629651205e-07,
      "loss": 0.0032,
      "reward": 2.125718832015991,
      "reward_std": 0.014771716669201851,
      "rewards/accuracy_reward": 0.9257187247276306,
      "rewards/format_reward": 1.0,
      "step": 1796
    },
    {
      "all_correct": 0.75,
      "all_wrong": 0.0,
      "completion_length": 389.09375,
      "epoch": 0.024785865022551413,
      "grad_norm": 4.08258152216409,
      "kl": 0.0693359375,
      "learning_rate": 9.984849447662278e-07,
      "loss": 0.0028,
      "reward": 2.0645313262939453,
      "reward_std": 0.029033970087766647,
      "rewards/accuracy_reward": 0.8645312786102295,
      "rewards/format_reward": 1.0,
      "step": 1797
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.0,
      "completion_length": 390.53125,
      "epoch": 0.02479965793575261,
      "grad_norm": 2.077638826240048,
      "kl": 0.080078125,
      "learning_rate": 9.984832589452764e-07,
      "loss": 0.0032,
      "reward": 2.0334062576293945,
      "reward_std": 0.009484776295721531,
      "rewards/accuracy_reward": 0.8334062695503235,
      "rewards/format_reward": 1.0,
      "step": 1798
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.0,
      "completion_length": 396.375,
      "epoch": 0.024813450848953807,
      "grad_norm": 3.024384104108754,
      "kl": 0.0771484375,
      "learning_rate": 9.984815721883542e-07,
      "loss": 0.0031,
      "reward": 2.0014376640319824,
      "reward_std": 0.022771289572119713,
      "rewards/accuracy_reward": 0.801437497138977,
      "rewards/format_reward": 1.0,
      "step": 1799
    },
    {
      "all_correct": 0.75,
      "all_wrong": 0.0,
      "completion_length": 400.8125,
      "epoch": 0.024827243762155005,
      "grad_norm": 2.840072468474782,
      "kl": 0.0703125,
      "learning_rate": 9.984798844954642e-07,
      "loss": 0.0028,
      "reward": 2.10756254196167,
      "reward_std": 0.01857057586312294,
      "rewards/accuracy_reward": 0.9075624942779541,
      "rewards/format_reward": 1.0,
      "step": 1800
    },
    {
      "all_correct": 0.75,
      "all_wrong": 0.0,
      "completion_length": 381.5625,
      "epoch": 0.024841036675356202,
      "grad_norm": 2.419564851903318,
      "kl": 0.080078125,
      "learning_rate": 9.9847819586661e-07,
      "loss": 0.0032,
      "reward": 2.0813751220703125,
      "reward_std": 0.02807619608938694,
      "rewards/accuracy_reward": 0.887624979019165,
      "rewards/format_reward": 1.0,
      "step": 1801
    },
    {
      "all_correct": 0.75,
      "all_wrong": 0.0,
      "completion_length": 398.34375,
      "epoch": 0.0248548295885574,
      "grad_norm": 5.265284200214633,
      "kl": 0.072265625,
      "learning_rate": 9.984765063017942e-07,
      "loss": 0.0029,
      "reward": 2.071125030517578,
      "reward_std": 0.008159724995493889,
      "rewards/accuracy_reward": 0.8711249828338623,
      "rewards/format_reward": 1.0,
      "step": 1802
    },
    {
      "all_correct": 0.25,
      "all_wrong": 0.0,
      "completion_length": 375.78125,
      "epoch": 0.024868622501758596,
      "grad_norm": 2.417742803497985,
      "kl": 0.078125,
      "learning_rate": 9.984748158010203e-07,
      "loss": 0.0031,
      "reward": 2.0822811126708984,
      "reward_std": 0.0606490820646286,
      "rewards/accuracy_reward": 0.9072812795639038,
      "rewards/format_reward": 1.0,
      "step": 1803
    },
    {
      "all_correct": 1.0,
      "all_wrong": 0.0,
      "completion_length": 378.9375,
      "epoch": 0.024882415414959794,
      "grad_norm": 3.2660153386483612,
      "kl": 0.07470703125,
      "learning_rate": 9.984731243642913e-07,
      "loss": 0.003,
      "reward": 2.145656108856201,
      "reward_std": 0.0271601602435112,
      "rewards/accuracy_reward": 0.9456561803817749,
      "rewards/format_reward": 1.0,
      "step": 1804
    },
    {
      "all_correct": 0.75,
      "all_wrong": 0.0,
      "completion_length": 383.75,
      "epoch": 0.02489620832816099,
      "grad_norm": 2.3149288294115666,
      "kl": 0.0751953125,
      "learning_rate": 9.984714319916105e-07,
      "loss": 0.003,
      "reward": 2.1265313625335693,
      "reward_std": 0.03469683229923248,
      "rewards/accuracy_reward": 0.9390312433242798,
      "rewards/format_reward": 1.0,
      "step": 1805
    },
    {
      "all_correct": 0.75,
      "all_wrong": 0.0,
      "completion_length": 379.21875,
      "epoch": 0.024910001241362188,
      "grad_norm": 1.958748649606308,
      "kl": 0.072265625,
      "learning_rate": 9.98469738682981e-07,
      "loss": 0.0029,
      "reward": 2.1150312423706055,
      "reward_std": 0.019574537873268127,
      "rewards/accuracy_reward": 0.9212811589241028,
      "rewards/format_reward": 1.0,
      "step": 1806
    },
    {
      "all_correct": 0.25,
      "all_wrong": 0.0,
      "completion_length": 391.40625,
      "epoch": 0.024923794154563386,
      "grad_norm": 3.432904245801903,
      "kl": 0.08203125,
      "learning_rate": 9.984680444384062e-07,
      "loss": 0.0033,
      "reward": 1.9821562767028809,
      "reward_std": 0.0369049608707428,
      "rewards/accuracy_reward": 0.788406252861023,
      "rewards/format_reward": 1.0,
      "step": 1807
    },
    {
      "all_correct": 0.75,
      "all_wrong": 0.0,
      "completion_length": 395.71875,
      "epoch": 0.024937587067764583,
      "grad_norm": 2.953627641991977,
      "kl": 0.07421875,
      "learning_rate": 9.984663492578888e-07,
      "loss": 0.003,
      "reward": 2.057468891143799,
      "reward_std": 0.03296763077378273,
      "rewards/accuracy_reward": 0.8637187480926514,
      "rewards/format_reward": 1.0,
      "step": 1808
    },
    {
      "all_correct": 0.75,
      "all_wrong": 0.0,
      "completion_length": 391.75,
      "epoch": 0.02495137998096578,
      "grad_norm": 2.482057072855879,
      "kl": 0.0732421875,
      "learning_rate": 9.984646531414325e-07,
      "loss": 0.0029,
      "reward": 1.9731563329696655,
      "reward_std": 0.00761070940643549,
      "rewards/accuracy_reward": 0.7731561660766602,
      "rewards/format_reward": 1.0,
      "step": 1809
    },
    {
      "all_correct": 0.75,
      "all_wrong": 0.0,
      "completion_length": 396.4375,
      "epoch": 0.024965172894166977,
      "grad_norm": 2.1106669311753485,
      "kl": 0.07470703125,
      "learning_rate": 9.984629560890402e-07,
      "loss": 0.003,
      "reward": 2.0951249599456787,
      "reward_std": 0.013353114016354084,
      "rewards/accuracy_reward": 0.8951249718666077,
      "rewards/format_reward": 1.0,
      "step": 1810
    },
    {
      "all_correct": 0.75,
      "all_wrong": 0.0,
      "completion_length": 408.0,
      "epoch": 0.024978965807368175,
      "grad_norm": 4.368961204311242,
      "kl": 0.07568359375,
      "learning_rate": 9.984612581007153e-07,
      "loss": 0.003,
      "reward": 2.0777499675750732,
      "reward_std": 0.02158227562904358,
      "rewards/accuracy_reward": 0.877750039100647,
      "rewards/format_reward": 1.0,
      "step": 1811
    },
    {
      "all_correct": 0.25,
      "all_wrong": 0.0,
      "completion_length": 390.28125,
      "epoch": 0.024992758720569372,
      "grad_norm": 6.697641658711596,
      "kl": 0.0712890625,
      "learning_rate": 9.984595591764609e-07,
      "loss": 0.0029,
      "reward": 2.004000186920166,
      "reward_std": 0.03239420801401138,
      "rewards/accuracy_reward": 0.8164999485015869,
      "rewards/format_reward": 1.0,
      "step": 1812
    },
    {
      "all_correct": 0.75,
      "all_wrong": 0.0,
      "completion_length": 400.9375,
      "epoch": 0.02500655163377057,
      "grad_norm": 4.610901858061098,
      "kl": 0.076171875,
      "learning_rate": 9.9845785931628e-07,
      "loss": 0.003,
      "reward": 2.079906463623047,
      "reward_std": 0.029418643563985825,
      "rewards/accuracy_reward": 0.8861563205718994,
      "rewards/format_reward": 1.0,
      "step": 1813
    },
    {
      "all_correct": 1.0,
      "all_wrong": 0.0,
      "completion_length": 404.6875,
      "epoch": 0.025020344546971766,
      "grad_norm": 2.0085333775317196,
      "kl": 0.076171875,
      "learning_rate": 9.98456158520176e-07,
      "loss": 0.003,
      "reward": 2.151156425476074,
      "reward_std": 0.01612015813589096,
      "rewards/accuracy_reward": 0.9511562585830688,
      "rewards/format_reward": 1.0,
      "step": 1814
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.0,
      "completion_length": 401.3125,
      "epoch": 0.025034137460172964,
      "grad_norm": 3.0711199374550273,
      "kl": 0.06982421875,
      "learning_rate": 9.984544567881517e-07,
      "loss": 0.0028,
      "reward": 2.0467188358306885,
      "reward_std": 0.028811011463403702,
      "rewards/accuracy_reward": 0.8467187881469727,
      "rewards/format_reward": 1.0,
      "step": 1815
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.0,
      "completion_length": 410.34375,
      "epoch": 0.02504793037337416,
      "grad_norm": 2.169521221953622,
      "kl": 0.06787109375,
      "learning_rate": 9.98452754120211e-07,
      "loss": 0.0027,
      "reward": 1.9512187242507935,
      "reward_std": 0.014672722667455673,
      "rewards/accuracy_reward": 0.7512187957763672,
      "rewards/format_reward": 1.0,
      "step": 1816
    },
    {
      "all_correct": 0.75,
      "all_wrong": 0.0,
      "completion_length": 424.34375,
      "epoch": 0.025061723286575358,
      "grad_norm": 3.755524547901593,
      "kl": 0.0751953125,
      "learning_rate": 9.984510505163565e-07,
      "loss": 0.003,
      "reward": 2.1437501907348633,
      "reward_std": 0.03614560514688492,
      "rewards/accuracy_reward": 0.9499999284744263,
      "rewards/format_reward": 1.0,
      "step": 1817
    },
    {
      "all_correct": 1.0,
      "all_wrong": 0.0,
      "completion_length": 419.28125,
      "epoch": 0.025075516199776555,
      "grad_norm": 2.49891605222498,
      "kl": 0.08203125,
      "learning_rate": 9.984493459765917e-07,
      "loss": 0.0033,
      "reward": 2.1090939044952393,
      "reward_std": 0.01739683374762535,
      "rewards/accuracy_reward": 0.9090937376022339,
      "rewards/format_reward": 1.0,
      "step": 1818
    },
    {
      "all_correct": 0.75,
      "all_wrong": 0.0,
      "completion_length": 405.59375,
      "epoch": 0.025089309112977753,
      "grad_norm": 2.5722757983522992,
      "kl": 0.068359375,
      "learning_rate": 9.984476405009197e-07,
      "loss": 0.0027,
      "reward": 2.1441564559936523,
      "reward_std": 0.03765767812728882,
      "rewards/accuracy_reward": 0.9504061937332153,
      "rewards/format_reward": 1.0,
      "step": 1819
    },
    {
      "all_correct": 1.0,
      "all_wrong": 0.0,
      "completion_length": 396.46875,
      "epoch": 0.02510310202617895,
      "grad_norm": 1.66823560737798,
      "kl": 0.0712890625,
      "learning_rate": 9.984459340893436e-07,
      "loss": 0.0028,
      "reward": 2.1195626258850098,
      "reward_std": 0.022312071174383163,
      "rewards/accuracy_reward": 0.9258124828338623,
      "rewards/format_reward": 1.0,
      "step": 1820
    },
    {
      "all_correct": 1.0,
      "all_wrong": 0.0,
      "completion_length": 404.65625,
      "epoch": 0.025116894939380147,
      "grad_norm": 2.2308678770960317,
      "kl": 0.0732421875,
      "learning_rate": 9.98444226741867e-07,
      "loss": 0.0029,
      "reward": 2.158874988555908,
      "reward_std": 0.015427597798407078,
      "rewards/accuracy_reward": 0.9588750004768372,
      "rewards/format_reward": 1.0,
      "step": 1821
    },
    {
      "all_correct": 1.0,
      "all_wrong": 0.0,
      "completion_length": 406.5,
      "epoch": 0.025130687852581345,
      "grad_norm": 2.703205300148182,
      "kl": 0.07470703125,
      "learning_rate": 9.984425184584925e-07,
      "loss": 0.003,
      "reward": 2.1072187423706055,
      "reward_std": 0.014376457780599594,
      "rewards/accuracy_reward": 0.9072187542915344,
      "rewards/format_reward": 1.0,
      "step": 1822
    },
    {
      "all_correct": 1.0,
      "all_wrong": 0.0,
      "completion_length": 398.21875,
      "epoch": 0.025144480765782542,
      "grad_norm": 3.481870794078983,
      "kl": 0.06884765625,
      "learning_rate": 9.984408092392239e-07,
      "loss": 0.0028,
      "reward": 2.1358749866485596,
      "reward_std": 0.0331958569586277,
      "rewards/accuracy_reward": 0.9358750581741333,
      "rewards/format_reward": 1.0,
      "step": 1823
    },
    {
      "all_correct": 1.0,
      "all_wrong": 0.0,
      "completion_length": 404.8125,
      "epoch": 0.02515827367898374,
      "grad_norm": 2.5048217724213244,
      "kl": 0.0830078125,
      "learning_rate": 9.984390990840639e-07,
      "loss": 0.0033,
      "reward": 2.1587812900543213,
      "reward_std": 0.01900339126586914,
      "rewards/accuracy_reward": 0.9587812423706055,
      "rewards/format_reward": 1.0,
      "step": 1824
    },
    {
      "all_correct": 1.0,
      "all_wrong": 0.0,
      "completion_length": 401.84375,
      "epoch": 0.025172066592184936,
      "grad_norm": 1.9915057057346952,
      "kl": 0.06982421875,
      "learning_rate": 9.984373879930161e-07,
      "loss": 0.0028,
      "reward": 2.1549999713897705,
      "reward_std": 0.015268120914697647,
      "rewards/accuracy_reward": 0.9550000429153442,
      "rewards/format_reward": 1.0,
      "step": 1825
    },
    {
      "all_correct": 0.75,
      "all_wrong": 0.0,
      "completion_length": 410.03125,
      "epoch": 0.025185859505386134,
      "grad_norm": 3.2488064080797687,
      "kl": 0.0703125,
      "learning_rate": 9.984356759660836e-07,
      "loss": 0.0028,
      "reward": 2.0687813758850098,
      "reward_std": 0.016980387270450592,
      "rewards/accuracy_reward": 0.8687812685966492,
      "rewards/format_reward": 1.0,
      "step": 1826
    },
    {
      "all_correct": 0.75,
      "all_wrong": 0.0,
      "completion_length": 402.53125,
      "epoch": 0.02519965241858733,
      "grad_norm": 4.68460593788176,
      "kl": 0.08349609375,
      "learning_rate": 9.984339630032694e-07,
      "loss": 0.0033,
      "reward": 2.090968608856201,
      "reward_std": 0.0176951065659523,
      "rewards/accuracy_reward": 0.8909687399864197,
      "rewards/format_reward": 1.0,
      "step": 1827
    },
    {
      "all_correct": 0.25,
      "all_wrong": 0.0,
      "completion_length": 416.0,
      "epoch": 0.025213445331788528,
      "grad_norm": 2.2079619534532227,
      "kl": 0.076171875,
      "learning_rate": 9.98432249104577e-07,
      "loss": 0.003,
      "reward": 1.9787812232971191,
      "reward_std": 0.01229407824575901,
      "rewards/accuracy_reward": 0.7787812948226929,
      "rewards/format_reward": 1.0,
      "step": 1828
    },
    {
      "all_correct": 0.75,
      "all_wrong": 0.0,
      "completion_length": 404.15625,
      "epoch": 0.025227238244989725,
      "grad_norm": 2.062163834178871,
      "kl": 0.06640625,
      "learning_rate": 9.984305342700096e-07,
      "loss": 0.0027,
      "reward": 2.051875114440918,
      "reward_std": 0.006034111138433218,
      "rewards/accuracy_reward": 0.8518750071525574,
      "rewards/format_reward": 1.0,
      "step": 1829
    },
    {
      "all_correct": 0.75,
      "all_wrong": 0.0,
      "completion_length": 400.4375,
      "epoch": 0.025241031158190923,
      "grad_norm": 2.5534888133413096,
      "kl": 0.0751953125,
      "learning_rate": 9.984288184995705e-07,
      "loss": 0.003,
      "reward": 2.0749688148498535,
      "reward_std": 0.011115302331745625,
      "rewards/accuracy_reward": 0.8749687671661377,
      "rewards/format_reward": 1.0,
      "step": 1830
    },
    {
      "all_correct": 0.75,
      "all_wrong": 0.0,
      "completion_length": 386.59375,
      "epoch": 0.02525482407139212,
      "grad_norm": 2.0625345609854295,
      "kl": 0.0849609375,
      "learning_rate": 9.984271017932624e-07,
      "loss": 0.0034,
      "reward": 2.1003124713897705,
      "reward_std": 0.010857428424060345,
      "rewards/accuracy_reward": 0.9003124833106995,
      "rewards/format_reward": 1.0,
      "step": 1831
    },
    {
      "all_correct": 1.0,
      "all_wrong": 0.0,
      "completion_length": 396.625,
      "epoch": 0.025268616984593317,
      "grad_norm": 2.1961172659527617,
      "kl": 0.0810546875,
      "learning_rate": 9.98425384151089e-07,
      "loss": 0.0032,
      "reward": 2.1265311241149902,
      "reward_std": 0.01104404404759407,
      "rewards/accuracy_reward": 0.9265313148498535,
      "rewards/format_reward": 1.0,
      "step": 1832
    },
    {
      "all_correct": 0.75,
      "all_wrong": 0.0,
      "completion_length": 410.4375,
      "epoch": 0.025282409897794515,
      "grad_norm": 2.757163489840819,
      "kl": 0.076171875,
      "learning_rate": 9.984236655730534e-07,
      "loss": 0.003,
      "reward": 2.0827717781066895,
      "reward_std": 0.021459490060806274,
      "rewards/accuracy_reward": 0.882771909236908,
      "rewards/format_reward": 1.0,
      "step": 1833
    },
    {
      "all_correct": 0.75,
      "all_wrong": 0.0,
      "completion_length": 401.40625,
      "epoch": 0.025296202810995712,
      "grad_norm": 2.4049703952157393,
      "kl": 0.06884765625,
      "learning_rate": 9.98421946059159e-07,
      "loss": 0.0027,
      "reward": 2.0678749084472656,
      "reward_std": 0.023924771696329117,
      "rewards/accuracy_reward": 0.8678749799728394,
      "rewards/format_reward": 1.0,
      "step": 1834
    },
    {
      "all_correct": 1.0,
      "all_wrong": 0.0,
      "completion_length": 399.875,
      "epoch": 0.02530999572419691,
      "grad_norm": 3.1736190750633786,
      "kl": 0.07275390625,
      "learning_rate": 9.984202256094085e-07,
      "loss": 0.0029,
      "reward": 2.141343832015991,
      "reward_std": 0.013485681265592575,
      "rewards/accuracy_reward": 0.9413437247276306,
      "rewards/format_reward": 1.0,
      "step": 1835
    },
    {
      "all_correct": 0.75,
      "all_wrong": 0.0,
      "completion_length": 389.0,
      "epoch": 0.025323788637398106,
      "grad_norm": 2.889002064771838,
      "kl": 0.07470703125,
      "learning_rate": 9.984185042238058e-07,
      "loss": 0.003,
      "reward": 2.0661563873291016,
      "reward_std": 0.02142975851893425,
      "rewards/accuracy_reward": 0.8661562204360962,
      "rewards/format_reward": 1.0,
      "step": 1836
    },
    {
      "all_correct": 0.75,
      "all_wrong": 0.0,
      "completion_length": 399.375,
      "epoch": 0.025337581550599304,
      "grad_norm": 2.4645181419460362,
      "kl": 0.0791015625,
      "learning_rate": 9.984167819023538e-07,
      "loss": 0.0032,
      "reward": 2.08774995803833,
      "reward_std": 0.011205369606614113,
      "rewards/accuracy_reward": 0.8877500295639038,
      "rewards/format_reward": 1.0,
      "step": 1837
    },
    {
      "all_correct": 1.0,
      "all_wrong": 0.0,
      "completion_length": 398.0,
      "epoch": 0.0253513744638005,
      "grad_norm": 2.8926009107047204,
      "kl": 0.0703125,
      "learning_rate": 9.984150586450556e-07,
      "loss": 0.0028,
      "reward": 2.1521248817443848,
      "reward_std": 0.014543944038450718,
      "rewards/accuracy_reward": 0.952125072479248,
      "rewards/format_reward": 1.0,
      "step": 1838
    },
    {
      "all_correct": 0.75,
      "all_wrong": 0.0,
      "completion_length": 396.9375,
      "epoch": 0.025365167377001698,
      "grad_norm": 3.813652772408831,
      "kl": 0.07763671875,
      "learning_rate": 9.984133344519147e-07,
      "loss": 0.0031,
      "reward": 2.0731563568115234,
      "reward_std": 0.017619047313928604,
      "rewards/accuracy_reward": 0.8731563091278076,
      "rewards/format_reward": 1.0,
      "step": 1839
    },
    {
      "all_correct": 1.0,
      "all_wrong": 0.0,
      "completion_length": 393.5,
      "epoch": 0.025378960290202895,
      "grad_norm": 2.7147271815300904,
      "kl": 0.076171875,
      "learning_rate": 9.984116093229342e-07,
      "loss": 0.003,
      "reward": 2.1460626125335693,
      "reward_std": 0.021524153649806976,
      "rewards/accuracy_reward": 0.946062445640564,
      "rewards/format_reward": 1.0,
      "step": 1840
    },
    {
      "all_correct": 0.75,
      "all_wrong": 0.0,
      "completion_length": 393.40625,
      "epoch": 0.02539275320340409,
      "grad_norm": 3.174118113098078,
      "kl": 0.0732421875,
      "learning_rate": 9.984098832581174e-07,
      "loss": 0.0029,
      "reward": 2.0907187461853027,
      "reward_std": 0.015461665578186512,
      "rewards/accuracy_reward": 0.8907187581062317,
      "rewards/format_reward": 1.0,
      "step": 1841
    },
    {
      "all_correct": 0.75,
      "all_wrong": 0.0,
      "completion_length": 388.125,
      "epoch": 0.025406546116605287,
      "grad_norm": 3.598866702367068,
      "kl": 0.07861328125,
      "learning_rate": 9.984081562574673e-07,
      "loss": 0.0031,
      "reward": 2.096062660217285,
      "reward_std": 0.023558679968118668,
      "rewards/accuracy_reward": 0.8960624933242798,
      "rewards/format_reward": 1.0,
      "step": 1842
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.0,
      "completion_length": 388.125,
      "epoch": 0.025420339029806484,
      "grad_norm": 2.0147814308743754,
      "kl": 0.07080078125,
      "learning_rate": 9.984064283209877e-07,
      "loss": 0.0028,
      "reward": 2.0739998817443848,
      "reward_std": 0.029729995876550674,
      "rewards/accuracy_reward": 0.8802499771118164,
      "rewards/format_reward": 1.0,
      "step": 1843
    },
    {
      "all_correct": 1.0,
      "all_wrong": 0.0,
      "completion_length": 377.53125,
      "epoch": 0.02543413194300768,
      "grad_norm": 8.453329596243213,
      "kl": 0.0732421875,
      "learning_rate": 9.984046994486812e-07,
      "loss": 0.0029,
      "reward": 2.1384687423706055,
      "reward_std": 0.014828226529061794,
      "rewards/accuracy_reward": 0.9384686946868896,
      "rewards/format_reward": 1.0,
      "step": 1844
    },
    {
      "all_correct": 1.0,
      "all_wrong": 0.0,
      "completion_length": 371.0625,
      "epoch": 0.02544792485620888,
      "grad_norm": 2.7529798438141717,
      "kl": 0.080078125,
      "learning_rate": 9.984029696405516e-07,
      "loss": 0.0032,
      "reward": 2.1325626373291016,
      "reward_std": 0.012229455634951591,
      "rewards/accuracy_reward": 0.932562530040741,
      "rewards/format_reward": 1.0,
      "step": 1845
    },
    {
      "all_correct": 0.75,
      "all_wrong": 0.0,
      "completion_length": 390.65625,
      "epoch": 0.025461717769410076,
      "grad_norm": 2.1643419439161296,
      "kl": 0.07421875,
      "learning_rate": 9.984012388966016e-07,
      "loss": 0.003,
      "reward": 2.0810937881469727,
      "reward_std": 0.026225507259368896,
      "rewards/accuracy_reward": 0.8873437643051147,
      "rewards/format_reward": 1.0,
      "step": 1846
    },
    {
      "all_correct": 1.0,
      "all_wrong": 0.0,
      "completion_length": 383.125,
      "epoch": 0.025475510682611273,
      "grad_norm": 3.835810762659808,
      "kl": 0.07763671875,
      "learning_rate": 9.98399507216835e-07,
      "loss": 0.0031,
      "reward": 2.127687454223633,
      "reward_std": 0.0294649638235569,
      "rewards/accuracy_reward": 0.9339374899864197,
      "rewards/format_reward": 1.0,
      "step": 1847
    },
    {
      "all_correct": 0.75,
      "all_wrong": 0.0,
      "completion_length": 382.75,
      "epoch": 0.02548930359581247,
      "grad_norm": 3.8238763539846787,
      "kl": 0.08154296875,
      "learning_rate": 9.983977746012547e-07,
      "loss": 0.0033,
      "reward": 2.159843683242798,
      "reward_std": 0.03189468756318092,
      "rewards/accuracy_reward": 0.9660937786102295,
      "rewards/format_reward": 1.0,
      "step": 1848
    },
    {
      "all_correct": 0.75,
      "all_wrong": 0.0,
      "completion_length": 380.84375,
      "epoch": 0.025503096509013667,
      "grad_norm": 2.6918177909269687,
      "kl": 0.0791015625,
      "learning_rate": 9.98396041049864e-07,
      "loss": 0.0032,
      "reward": 2.1157188415527344,
      "reward_std": 0.027348648756742477,
      "rewards/accuracy_reward": 0.9219688177108765,
      "rewards/format_reward": 1.0,
      "step": 1849
    },
    {
      "all_correct": 0.75,
      "all_wrong": 0.0,
      "completion_length": 371.3125,
      "epoch": 0.025516889422214865,
      "grad_norm": 5.603041859939737,
      "kl": 0.07275390625,
      "learning_rate": 9.983943065626663e-07,
      "loss": 0.0029,
      "reward": 2.0533437728881836,
      "reward_std": 0.02138070948421955,
      "rewards/accuracy_reward": 0.8533437252044678,
      "rewards/format_reward": 1.0,
      "step": 1850
    },
    {
      "all_correct": 0.75,
      "all_wrong": 0.0,
      "completion_length": 387.25,
      "epoch": 0.025530682335416062,
      "grad_norm": 1.9700967287976536,
      "kl": 0.07421875,
      "learning_rate": 9.983925711396646e-07,
      "loss": 0.003,
      "reward": 2.1324687004089355,
      "reward_std": 0.024304986000061035,
      "rewards/accuracy_reward": 0.9387187361717224,
      "rewards/format_reward": 1.0,
      "step": 1851
    },
    {
      "all_correct": 0.75,
      "all_wrong": 0.0,
      "completion_length": 382.78125,
      "epoch": 0.02554447524861726,
      "grad_norm": 2.3963907426435225,
      "kl": 0.0849609375,
      "learning_rate": 9.983908347808626e-07,
      "loss": 0.0034,
      "reward": 2.0945937633514404,
      "reward_std": 0.02313227578997612,
      "rewards/accuracy_reward": 0.9008437395095825,
      "rewards/format_reward": 1.0,
      "step": 1852
    },
    {
      "all_correct": 0.75,
      "all_wrong": 0.0,
      "completion_length": 379.25,
      "epoch": 0.025558268161818457,
      "grad_norm": 2.853813057104101,
      "kl": 0.0869140625,
      "learning_rate": 9.98389097486263e-07,
      "loss": 0.0035,
      "reward": 2.1250624656677246,
      "reward_std": 0.03674417734146118,
      "rewards/accuracy_reward": 0.9313124418258667,
      "rewards/format_reward": 1.0,
      "step": 1853
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.0,
      "completion_length": 392.65625,
      "epoch": 0.025572061075019654,
      "grad_norm": 2.794679757154359,
      "kl": 0.076171875,
      "learning_rate": 9.983873592558694e-07,
      "loss": 0.0031,
      "reward": 2.022125244140625,
      "reward_std": 0.029511287808418274,
      "rewards/accuracy_reward": 0.828374981880188,
      "rewards/format_reward": 1.0,
      "step": 1854
    },
    {
      "all_correct": 1.0,
      "all_wrong": 0.0,
      "completion_length": 390.46875,
      "epoch": 0.02558585398822085,
      "grad_norm": 2.1646527246673357,
      "kl": 0.07861328125,
      "learning_rate": 9.98385620089685e-07,
      "loss": 0.0031,
      "reward": 2.1636252403259277,
      "reward_std": 0.027691997587680817,
      "rewards/accuracy_reward": 0.9698750376701355,
      "rewards/format_reward": 1.0,
      "step": 1855
    },
    {
      "all_correct": 1.0,
      "all_wrong": 0.0,
      "completion_length": 395.9375,
      "epoch": 0.02559964690142205,
      "grad_norm": 4.328330009642746,
      "kl": 0.0810546875,
      "learning_rate": 9.983838799877132e-07,
      "loss": 0.0032,
      "reward": 2.1452813148498535,
      "reward_std": 0.009981352835893631,
      "rewards/accuracy_reward": 0.9452812671661377,
      "rewards/format_reward": 1.0,
      "step": 1856
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.0,
      "completion_length": 390.96875,
      "epoch": 0.025613439814623246,
      "grad_norm": 2.807801471900933,
      "kl": 0.08056640625,
      "learning_rate": 9.98382138949957e-07,
      "loss": 0.0032,
      "reward": 2.044468879699707,
      "reward_std": 0.030625659972429276,
      "rewards/accuracy_reward": 0.8507187366485596,
      "rewards/format_reward": 1.0,
      "step": 1857
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.0,
      "completion_length": 389.03125,
      "epoch": 0.025627232727824443,
      "grad_norm": 2.664027744076353,
      "kl": 0.0849609375,
      "learning_rate": 9.983803969764199e-07,
      "loss": 0.0034,
      "reward": 2.067687511444092,
      "reward_std": 0.01151359174400568,
      "rewards/accuracy_reward": 0.8676875233650208,
      "rewards/format_reward": 1.0,
      "step": 1858
    },
    {
      "all_correct": 0.75,
      "all_wrong": 0.0,
      "completion_length": 402.71875,
      "epoch": 0.02564102564102564,
      "grad_norm": 2.185237919929018,
      "kl": 0.080078125,
      "learning_rate": 9.98378654067105e-07,
      "loss": 0.0032,
      "reward": 2.0583438873291016,
      "reward_std": 0.01906484179198742,
      "rewards/accuracy_reward": 0.8583437204360962,
      "rewards/format_reward": 1.0,
      "step": 1859
    },
    {
      "all_correct": 1.0,
      "all_wrong": 0.0,
      "completion_length": 399.96875,
      "epoch": 0.025654818554226837,
      "grad_norm": 2.8348823693676866,
      "kl": 0.0751953125,
      "learning_rate": 9.983769102220157e-07,
      "loss": 0.003,
      "reward": 2.122781276702881,
      "reward_std": 0.013881700113415718,
      "rewards/accuracy_reward": 0.9227812886238098,
      "rewards/format_reward": 1.0,
      "step": 1860
    },
    {
      "all_correct": 1.0,
      "all_wrong": 0.0,
      "completion_length": 400.875,
      "epoch": 0.025668611467428035,
      "grad_norm": 1.9281698057615821,
      "kl": 0.076171875,
      "learning_rate": 9.983751654411551e-07,
      "loss": 0.003,
      "reward": 2.167750120162964,
      "reward_std": 0.010406461544334888,
      "rewards/accuracy_reward": 0.9677499532699585,
      "rewards/format_reward": 1.0,
      "step": 1861
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.0,
      "completion_length": 377.4375,
      "epoch": 0.025682404380629232,
      "grad_norm": 1.8748098234731816,
      "kl": 0.07861328125,
      "learning_rate": 9.983734197245267e-07,
      "loss": 0.0031,
      "reward": 2.0851564407348633,
      "reward_std": 0.029073134064674377,
      "rewards/accuracy_reward": 0.891406238079071,
      "rewards/format_reward": 1.0,
      "step": 1862
    },
    {
      "all_correct": 0.25,
      "all_wrong": 0.0,
      "completion_length": 397.96875,
      "epoch": 0.02569619729383043,
      "grad_norm": 2.001995155868636,
      "kl": 0.07421875,
      "learning_rate": 9.983716730721336e-07,
      "loss": 0.003,
      "reward": 1.9856562614440918,
      "reward_std": 0.010835351422429085,
      "rewards/accuracy_reward": 0.7856562733650208,
      "rewards/format_reward": 1.0,
      "step": 1863
    },
    {
      "all_correct": 1.0,
      "all_wrong": 0.0,
      "completion_length": 402.71875,
      "epoch": 0.025709990207031626,
      "grad_norm": 6.9295445810275185,
      "kl": 0.07861328125,
      "learning_rate": 9.983699254839793e-07,
      "loss": 0.0031,
      "reward": 2.1544060707092285,
      "reward_std": 0.012011079117655754,
      "rewards/accuracy_reward": 0.9544063210487366,
      "rewards/format_reward": 1.0,
      "step": 1864
    },
    {
      "all_correct": 1.0,
      "all_wrong": 0.0,
      "completion_length": 408.9375,
      "epoch": 0.025723783120232824,
      "grad_norm": 2.0486517003466322,
      "kl": 0.078125,
      "learning_rate": 9.983681769600668e-07,
      "loss": 0.0031,
      "reward": 2.121312379837036,
      "reward_std": 0.008215043693780899,
      "rewards/accuracy_reward": 0.9213125109672546,
      "rewards/format_reward": 1.0,
      "step": 1865
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.0,
      "completion_length": 409.59375,
      "epoch": 0.02573757603343402,
      "grad_norm": 2.794561678802557,
      "kl": 0.08447265625,
      "learning_rate": 9.983664275003997e-07,
      "loss": 0.0034,
      "reward": 2.0582499504089355,
      "reward_std": 0.016837604343891144,
      "rewards/accuracy_reward": 0.8582500219345093,
      "rewards/format_reward": 1.0,
      "step": 1866
    },
    {
      "all_correct": 0.75,
      "all_wrong": 0.0,
      "completion_length": 407.65625,
      "epoch": 0.02575136894663522,
      "grad_norm": 3.0965585637611284,
      "kl": 0.078125,
      "learning_rate": 9.983646771049808e-07,
      "loss": 0.0031,
      "reward": 2.0903749465942383,
      "reward_std": 0.02898436412215233,
      "rewards/accuracy_reward": 0.8966250419616699,
      "rewards/format_reward": 1.0,
      "step": 1867
    },
    {
      "all_correct": 1.0,
      "all_wrong": 0.0,
      "completion_length": 425.5,
      "epoch": 0.025765161859836416,
      "grad_norm": 2.431143881446561,
      "kl": 0.07958984375,
      "learning_rate": 9.983629257738139e-07,
      "loss": 0.0032,
      "reward": 2.1497812271118164,
      "reward_std": 0.008799711242318153,
      "rewards/accuracy_reward": 0.9497812390327454,
      "rewards/format_reward": 1.0,
      "step": 1868
    },
    {
      "all_correct": 0.75,
      "all_wrong": 0.0,
      "completion_length": 412.375,
      "epoch": 0.025778954773037613,
      "grad_norm": 2.361456574092,
      "kl": 0.0869140625,
      "learning_rate": 9.98361173506902e-07,
      "loss": 0.0035,
      "reward": 2.0873751640319824,
      "reward_std": 0.013711605221033096,
      "rewards/accuracy_reward": 0.8873750567436218,
      "rewards/format_reward": 1.0,
      "step": 1869
    },
    {
      "all_correct": 1.0,
      "all_wrong": 0.0,
      "completion_length": 410.34375,
      "epoch": 0.02579274768623881,
      "grad_norm": 12.117904620459306,
      "kl": 0.08935546875,
      "learning_rate": 9.983594203042485e-07,
      "loss": 0.0036,
      "reward": 2.124593734741211,
      "reward_std": 0.017907653003931046,
      "rewards/accuracy_reward": 0.9245937466621399,
      "rewards/format_reward": 1.0,
      "step": 1870
    },
    {
      "all_correct": 1.0,
      "all_wrong": 0.0,
      "completion_length": 416.9375,
      "epoch": 0.025806540599440007,
      "grad_norm": 2.406914301836135,
      "kl": 0.072265625,
      "learning_rate": 9.983576661658567e-07,
      "loss": 0.0029,
      "reward": 2.1099376678466797,
      "reward_std": 0.016399363055825233,
      "rewards/accuracy_reward": 0.9099375009536743,
      "rewards/format_reward": 1.0,
      "step": 1871
    },
    {
      "all_correct": 0.75,
      "all_wrong": 0.0,
      "completion_length": 408.21875,
      "epoch": 0.025820333512641205,
      "grad_norm": 2.542509352827263,
      "kl": 0.0771484375,
      "learning_rate": 9.983559110917297e-07,
      "loss": 0.0031,
      "reward": 2.1330313682556152,
      "reward_std": 0.026605045422911644,
      "rewards/accuracy_reward": 0.9392812252044678,
      "rewards/format_reward": 1.0,
      "step": 1872
    },
    {
      "all_correct": 0.75,
      "all_wrong": 0.0,
      "completion_length": 401.375,
      "epoch": 0.025834126425842402,
      "grad_norm": 2.4547970890687894,
      "kl": 0.07958984375,
      "learning_rate": 9.983541550818711e-07,
      "loss": 0.0032,
      "reward": 2.084718704223633,
      "reward_std": 0.013663766905665398,
      "rewards/accuracy_reward": 0.8847187757492065,
      "rewards/format_reward": 1.0,
      "step": 1873
    },
    {
      "all_correct": 1.0,
      "all_wrong": 0.0,
      "completion_length": 414.28125,
      "epoch": 0.0258479193390436,
      "grad_norm": 4.6467052152682635,
      "kl": 0.0810546875,
      "learning_rate": 9.98352398136284e-07,
      "loss": 0.0032,
      "reward": 2.175062656402588,
      "reward_std": 0.012637021951377392,
      "rewards/accuracy_reward": 0.9750624895095825,
      "rewards/format_reward": 1.0,
      "step": 1874
    },
    {
      "all_correct": 0.75,
      "all_wrong": 0.0,
      "completion_length": 417.96875,
      "epoch": 0.025861712252244796,
      "grad_norm": 2.1704201810849226,
      "kl": 0.07177734375,
      "learning_rate": 9.983506402549719e-07,
      "loss": 0.0029,
      "reward": 2.114656448364258,
      "reward_std": 0.12084515392780304,
      "rewards/accuracy_reward": 0.9521563053131104,
      "rewards/format_reward": 0.96875,
      "step": 1875
    },
    {
      "all_correct": 0.75,
      "all_wrong": 0.0,
      "completion_length": 404.40625,
      "epoch": 0.025875505165445994,
      "grad_norm": 3.0880592887395615,
      "kl": 0.076171875,
      "learning_rate": 9.983488814379376e-07,
      "loss": 0.0031,
      "reward": 2.118281364440918,
      "reward_std": 0.1004912480711937,
      "rewards/accuracy_reward": 0.9495313167572021,
      "rewards/format_reward": 0.96875,
      "step": 1876
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.0,
      "completion_length": 408.65625,
      "epoch": 0.02588929807864719,
      "grad_norm": 2.2737975895682254,
      "kl": 0.0751953125,
      "learning_rate": 9.98347121685185e-07,
      "loss": 0.003,
      "reward": 2.0881876945495605,
      "reward_std": 0.0455729179084301,
      "rewards/accuracy_reward": 0.9006874561309814,
      "rewards/format_reward": 1.0,
      "step": 1877
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.0,
      "completion_length": 398.0625,
      "epoch": 0.02590309099184839,
      "grad_norm": 2.3691075317193566,
      "kl": 0.083984375,
      "learning_rate": 9.983453609967173e-07,
      "loss": 0.0034,
      "reward": 2.094531297683716,
      "reward_std": 0.023566478863358498,
      "rewards/accuracy_reward": 0.9007812142372131,
      "rewards/format_reward": 1.0,
      "step": 1878
    },
    {
      "all_correct": 0.25,
      "all_wrong": 0.0,
      "completion_length": 405.40625,
      "epoch": 0.025916883905049586,
      "grad_norm": 2.9056453960642004,
      "kl": 0.083984375,
      "learning_rate": 9.983435993725375e-07,
      "loss": 0.0034,
      "reward": 2.015625,
      "reward_std": 0.018177349120378494,
      "rewards/accuracy_reward": 0.8156250715255737,
      "rewards/format_reward": 1.0,
      "step": 1879
    },
    {
      "all_correct": 0.25,
      "all_wrong": 0.0,
      "completion_length": 392.25,
      "epoch": 0.025930676818250783,
      "grad_norm": 6.836704224544842,
      "kl": 0.091796875,
      "learning_rate": 9.983418368126489e-07,
      "loss": 0.0037,
      "reward": 2.003187417984009,
      "reward_std": 0.1331649273633957,
      "rewards/accuracy_reward": 0.8469374179840088,
      "rewards/format_reward": 0.96875,
      "step": 1880
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.0,
      "completion_length": 397.40625,
      "epoch": 0.02594446973145198,
      "grad_norm": 13.759491626563882,
      "kl": 0.07958984375,
      "learning_rate": 9.983400733170553e-07,
      "loss": 0.0032,
      "reward": 2.0055625438690186,
      "reward_std": 0.01725863665342331,
      "rewards/accuracy_reward": 0.8055624961853027,
      "rewards/format_reward": 1.0,
      "step": 1881
    },
    {
      "all_correct": 0.75,
      "all_wrong": 0.0,
      "completion_length": 391.59375,
      "epoch": 0.025958262644653177,
      "grad_norm": 3.0019805753970417,
      "kl": 0.0810546875,
      "learning_rate": 9.983383088857594e-07,
      "loss": 0.0032,
      "reward": 2.1140313148498535,
      "reward_std": 0.017071839421987534,
      "rewards/accuracy_reward": 0.9140312671661377,
      "rewards/format_reward": 1.0,
      "step": 1882
    },
    {
      "all_correct": 1.0,
      "all_wrong": 0.0,
      "completion_length": 395.125,
      "epoch": 0.025972055557854375,
      "grad_norm": 1.8277776417879426,
      "kl": 0.07421875,
      "learning_rate": 9.98336543518765e-07,
      "loss": 0.003,
      "reward": 2.1651248931884766,
      "reward_std": 0.009313899092376232,
      "rewards/accuracy_reward": 0.9651249647140503,
      "rewards/format_reward": 1.0,
      "step": 1883
    },
    {
      "all_correct": 0.75,
      "all_wrong": 0.0,
      "completion_length": 395.375,
      "epoch": 0.025985848471055572,
      "grad_norm": 3.354512363534502,
      "kl": 0.08447265625,
      "learning_rate": 9.98334777216075e-07,
      "loss": 0.0034,
      "reward": 2.0831875801086426,
      "reward_std": 0.02759060077369213,
      "rewards/accuracy_reward": 0.8831875324249268,
      "rewards/format_reward": 1.0,
      "step": 1884
    },
    {
      "all_correct": 0.75,
      "all_wrong": 0.0,
      "completion_length": 389.65625,
      "epoch": 0.02599964138425677,
      "grad_norm": 2.4912088620046022,
      "kl": 0.06396484375,
      "learning_rate": 9.983330099776929e-07,
      "loss": 0.0026,
      "reward": 2.1124062538146973,
      "reward_std": 0.02426830306649208,
      "rewards/accuracy_reward": 0.9124062657356262,
      "rewards/format_reward": 1.0,
      "step": 1885
    },
    {
      "all_correct": 1.0,
      "all_wrong": 0.0,
      "completion_length": 401.875,
      "epoch": 0.026013434297457966,
      "grad_norm": 2.0002994483792147,
      "kl": 0.06787109375,
      "learning_rate": 9.983312418036225e-07,
      "loss": 0.0027,
      "reward": 2.1269376277923584,
      "reward_std": 0.008103366941213608,
      "rewards/accuracy_reward": 0.9269375801086426,
      "rewards/format_reward": 1.0,
      "step": 1886
    },
    {
      "all_correct": 0.75,
      "all_wrong": 0.0,
      "completion_length": 405.375,
      "epoch": 0.026027227210659164,
      "grad_norm": 2.81766079112827,
      "kl": 0.0693359375,
      "learning_rate": 9.983294726938663e-07,
      "loss": 0.0028,
      "reward": 2.081249952316284,
      "reward_std": 0.012763720005750656,
      "rewards/accuracy_reward": 0.8812500238418579,
      "rewards/format_reward": 1.0,
      "step": 1887
    },
    {
      "all_correct": 0.75,
      "all_wrong": 0.0,
      "completion_length": 395.25,
      "epoch": 0.02604102012386036,
      "grad_norm": 7.288633040377808,
      "kl": 0.08251953125,
      "learning_rate": 9.98327702648428e-07,
      "loss": 0.0033,
      "reward": 2.0316247940063477,
      "reward_std": 0.015839356929063797,
      "rewards/accuracy_reward": 0.8316250443458557,
      "rewards/format_reward": 1.0,
      "step": 1888
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.0,
      "completion_length": 389.46875,
      "epoch": 0.02605481303706156,
      "grad_norm": 2.916198006875666,
      "kl": 0.06982421875,
      "learning_rate": 9.98325931667311e-07,
      "loss": 0.0028,
      "reward": 2.0199687480926514,
      "reward_std": 0.04930349811911583,
      "rewards/accuracy_reward": 0.8199687004089355,
      "rewards/format_reward": 1.0,
      "step": 1889
    },
    {
      "all_correct": 0.75,
      "all_wrong": 0.0,
      "completion_length": 397.625,
      "epoch": 0.026068605950262756,
      "grad_norm": 3.220923308357919,
      "kl": 0.068359375,
      "learning_rate": 9.983241597505185e-07,
      "loss": 0.0027,
      "reward": 2.0854063034057617,
      "reward_std": 0.019993368536233902,
      "rewards/accuracy_reward": 0.8854062557220459,
      "rewards/format_reward": 1.0,
      "step": 1890
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.0,
      "completion_length": 391.5,
      "epoch": 0.026082398863463953,
      "grad_norm": 2.0730445013968595,
      "kl": 0.06640625,
      "learning_rate": 9.98322386898054e-07,
      "loss": 0.0026,
      "reward": 2.062187671661377,
      "reward_std": 0.014803411439061165,
      "rewards/accuracy_reward": 0.8621875047683716,
      "rewards/format_reward": 1.0,
      "step": 1891
    },
    {
      "all_correct": 0.75,
      "all_wrong": 0.0,
      "completion_length": 399.34375,
      "epoch": 0.02609619177666515,
      "grad_norm": 3.1754931276567464,
      "kl": 0.07568359375,
      "learning_rate": 9.983206131099205e-07,
      "loss": 0.003,
      "reward": 2.063093662261963,
      "reward_std": 0.015045160427689552,
      "rewards/accuracy_reward": 0.8630937933921814,
      "rewards/format_reward": 1.0,
      "step": 1892
    },
    {
      "all_correct": 1.0,
      "all_wrong": 0.0,
      "completion_length": 395.1875,
      "epoch": 0.026109984689866347,
      "grad_norm": 3.3021426965852068,
      "kl": 0.0732421875,
      "learning_rate": 9.983188383861216e-07,
      "loss": 0.0029,
      "reward": 2.1875312328338623,
      "reward_std": 0.008857827633619308,
      "rewards/accuracy_reward": 0.987531304359436,
      "rewards/format_reward": 1.0,
      "step": 1893
    },
    {
      "all_correct": 1.0,
      "all_wrong": 0.0,
      "completion_length": 393.1875,
      "epoch": 0.026123777603067545,
      "grad_norm": 4.970401986276893,
      "kl": 0.072265625,
      "learning_rate": 9.983170627266606e-07,
      "loss": 0.0029,
      "reward": 2.133812427520752,
      "reward_std": 0.004189165309071541,
      "rewards/accuracy_reward": 0.9338124990463257,
      "rewards/format_reward": 1.0,
      "step": 1894
    },
    {
      "all_correct": 1.0,
      "all_wrong": 0.0,
      "completion_length": 382.5625,
      "epoch": 0.026137570516268742,
      "grad_norm": 3.3709887680311126,
      "kl": 0.07763671875,
      "learning_rate": 9.983152861315406e-07,
      "loss": 0.0031,
      "reward": 2.084937572479248,
      "reward_std": 0.021619021892547607,
      "rewards/accuracy_reward": 0.8849375247955322,
      "rewards/format_reward": 1.0,
      "step": 1895
    },
    {
      "all_correct": 1.0,
      "all_wrong": 0.0,
      "completion_length": 386.875,
      "epoch": 0.02615136342946994,
      "grad_norm": 13.081294697888739,
      "kl": 0.0888671875,
      "learning_rate": 9.983135086007654e-07,
      "loss": 0.0035,
      "reward": 2.1125311851501465,
      "reward_std": 0.015462963841855526,
      "rewards/accuracy_reward": 0.9125312566757202,
      "rewards/format_reward": 1.0,
      "step": 1896
    },
    {
      "all_correct": 0.75,
      "all_wrong": 0.0,
      "completion_length": 382.5625,
      "epoch": 0.026165156342671136,
      "grad_norm": 2.3875891853307722,
      "kl": 0.08154296875,
      "learning_rate": 9.98311730134338e-07,
      "loss": 0.0033,
      "reward": 2.1114063262939453,
      "reward_std": 0.0249087605625391,
      "rewards/accuracy_reward": 0.9176562428474426,
      "rewards/format_reward": 1.0,
      "step": 1897
    },
    {
      "all_correct": 0.0,
      "all_wrong": 0.0,
      "completion_length": 370.0625,
      "epoch": 0.026178949255872334,
      "grad_norm": 2.028916751845437,
      "kl": 0.0732421875,
      "learning_rate": 9.983099507322618e-07,
      "loss": 0.0029,
      "reward": 2.0262811183929443,
      "reward_std": 0.054959043860435486,
      "rewards/accuracy_reward": 0.8450313210487366,
      "rewards/format_reward": 1.0,
      "step": 1898
    },
    {
      "all_correct": 0.75,
      "all_wrong": 0.0,
      "completion_length": 376.46875,
      "epoch": 0.02619274216907353,
      "grad_norm": 3.6983934539591714,
      "kl": 0.07666015625,
      "learning_rate": 9.983081703945401e-07,
      "loss": 0.0031,
      "reward": 2.0888125896453857,
      "reward_std": 0.030467383563518524,
      "rewards/accuracy_reward": 0.8950624465942383,
      "rewards/format_reward": 1.0,
      "step": 1899
    },
    {
      "all_correct": 0.75,
      "all_wrong": 0.0,
      "completion_length": 384.46875,
      "epoch": 0.026206535082274728,
      "grad_norm": 4.976831643531543,
      "kl": 0.07470703125,
      "learning_rate": 9.983063891211763e-07,
      "loss": 0.003,
      "reward": 2.088843822479248,
      "reward_std": 0.027769802138209343,
      "rewards/accuracy_reward": 0.8888437747955322,
      "rewards/format_reward": 1.0,
      "step": 1900
    },
    {
      "all_correct": 1.0,
      "all_wrong": 0.0,
      "completion_length": 387.40625,
      "epoch": 0.026220327995475926,
      "grad_norm": 2.5997812010653827,
      "kl": 0.072265625,
      "learning_rate": 9.983046069121736e-07,
      "loss": 0.0029,
      "reward": 2.1284375190734863,
      "reward_std": 0.01613606885075569,
      "rewards/accuracy_reward": 0.9284374713897705,
      "rewards/format_reward": 1.0,
      "step": 1901
    },
    {
      "all_correct": 0.75,
      "all_wrong": 0.0,
      "completion_length": 381.46875,
      "epoch": 0.026234120908677123,
      "grad_norm": 2.578028884006925,
      "kl": 0.07763671875,
      "learning_rate": 9.983028237675357e-07,
      "loss": 0.0031,
      "reward": 2.085906505584717,
      "reward_std": 0.03340889513492584,
      "rewards/accuracy_reward": 0.8921562433242798,
      "rewards/format_reward": 1.0,
      "step": 1902
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.0,
      "completion_length": 384.65625,
      "epoch": 0.02624791382187832,
      "grad_norm": 4.561895732932041,
      "kl": 0.07666015625,
      "learning_rate": 9.983010396872657e-07,
      "loss": 0.0031,
      "reward": 2.1163125038146973,
      "reward_std": 0.04884226620197296,
      "rewards/accuracy_reward": 0.9288125038146973,
      "rewards/format_reward": 1.0,
      "step": 1903
    },
    {
      "all_correct": 1.0,
      "all_wrong": 0.0,
      "completion_length": 394.28125,
      "epoch": 0.026261706735079517,
      "grad_norm": 4.270186995823431,
      "kl": 0.06494140625,
      "learning_rate": 9.982992546713669e-07,
      "loss": 0.0026,
      "reward": 2.1293437480926514,
      "reward_std": 0.022905055433511734,
      "rewards/accuracy_reward": 0.9293437600135803,
      "rewards/format_reward": 1.0,
      "step": 1904
    },
    {
      "all_correct": 0.75,
      "all_wrong": 0.0,
      "completion_length": 377.59375,
      "epoch": 0.026275499648280715,
      "grad_norm": 5.4301956029983405,
      "kl": 0.06982421875,
      "learning_rate": 9.982974687198427e-07,
      "loss": 0.0028,
      "reward": 2.1040940284729004,
      "reward_std": 0.03425617143511772,
      "rewards/accuracy_reward": 0.9103437662124634,
      "rewards/format_reward": 1.0,
      "step": 1905
    },
    {
      "all_correct": 1.0,
      "all_wrong": 0.0,
      "completion_length": 386.5625,
      "epoch": 0.026289292561481912,
      "grad_norm": 2.1826665071563474,
      "kl": 0.0732421875,
      "learning_rate": 9.982956818326966e-07,
      "loss": 0.0029,
      "reward": 2.1343750953674316,
      "reward_std": 0.013854065909981728,
      "rewards/accuracy_reward": 0.9343750476837158,
      "rewards/format_reward": 1.0,
      "step": 1906
    },
    {
      "all_correct": 0.75,
      "all_wrong": 0.0,
      "completion_length": 379.75,
      "epoch": 0.02630308547468311,
      "grad_norm": 5.045341331330085,
      "kl": 0.0888671875,
      "learning_rate": 9.982938940099318e-07,
      "loss": 0.0036,
      "reward": 2.1560935974121094,
      "reward_std": 0.03527868166565895,
      "rewards/accuracy_reward": 0.962343692779541,
      "rewards/format_reward": 1.0,
      "step": 1907
    },
    {
      "all_correct": 0.75,
      "all_wrong": 0.0,
      "completion_length": 392.03125,
      "epoch": 0.026316878387884306,
      "grad_norm": 2.585764075662836,
      "kl": 0.07763671875,
      "learning_rate": 9.982921052515515e-07,
      "loss": 0.0031,
      "reward": 2.1163125038146973,
      "reward_std": 0.01224626787006855,
      "rewards/accuracy_reward": 0.9163124561309814,
      "rewards/format_reward": 1.0,
      "step": 1908
    },
    {
      "all_correct": 1.0,
      "all_wrong": 0.0,
      "completion_length": 384.5625,
      "epoch": 0.026330671301085504,
      "grad_norm": 4.009492226902157,
      "kl": 0.08203125,
      "learning_rate": 9.982903155575594e-07,
      "loss": 0.0033,
      "reward": 2.149656295776367,
      "reward_std": 0.02167775109410286,
      "rewards/accuracy_reward": 0.9496561884880066,
      "rewards/format_reward": 1.0,
      "step": 1909
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.0,
      "completion_length": 389.8125,
      "epoch": 0.0263444642142867,
      "grad_norm": 4.192897607652903,
      "kl": 0.08251953125,
      "learning_rate": 9.982885249279588e-07,
      "loss": 0.0033,
      "reward": 2.1063437461853027,
      "reward_std": 0.038686685264110565,
      "rewards/accuracy_reward": 0.9125937819480896,
      "rewards/format_reward": 1.0,
      "step": 1910
    },
    {
      "all_correct": 0.75,
      "all_wrong": 0.0,
      "completion_length": 388.4375,
      "epoch": 0.026358257127487898,
      "grad_norm": 1.8673974522114576,
      "kl": 0.0791015625,
      "learning_rate": 9.98286733362753e-07,
      "loss": 0.0032,
      "reward": 2.0999999046325684,
      "reward_std": 0.010693451389670372,
      "rewards/accuracy_reward": 0.9000000357627869,
      "rewards/format_reward": 1.0,
      "step": 1911
    },
    {
      "all_correct": 1.0,
      "all_wrong": 0.0,
      "completion_length": 394.375,
      "epoch": 0.026372050040689096,
      "grad_norm": 1.6680172997767577,
      "kl": 0.076171875,
      "learning_rate": 9.982849408619452e-07,
      "loss": 0.0031,
      "reward": 2.171968936920166,
      "reward_std": 0.008573643863201141,
      "rewards/accuracy_reward": 0.9719687700271606,
      "rewards/format_reward": 1.0,
      "step": 1912
    },
    {
      "all_correct": 0.25,
      "all_wrong": 0.0,
      "completion_length": 387.6875,
      "epoch": 0.026385842953890293,
      "grad_norm": 3.2316097982894387,
      "kl": 0.0908203125,
      "learning_rate": 9.982831474255392e-07,
      "loss": 0.0036,
      "reward": 2.0645623207092285,
      "reward_std": 0.04534504562616348,
      "rewards/accuracy_reward": 0.8770625591278076,
      "rewards/format_reward": 1.0,
      "step": 1913
    },
    {
      "all_correct": 0.75,
      "all_wrong": 0.0,
      "completion_length": 387.4375,
      "epoch": 0.02639963586709149,
      "grad_norm": 3.4795134207215033,
      "kl": 0.08544921875,
      "learning_rate": 9.982813530535376e-07,
      "loss": 0.0034,
      "reward": 2.0827813148498535,
      "reward_std": 0.027300989255309105,
      "rewards/accuracy_reward": 0.8827812671661377,
      "rewards/format_reward": 1.0,
      "step": 1914
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.0,
      "completion_length": 392.8125,
      "epoch": 0.026413428780292687,
      "grad_norm": 2.646759466219593,
      "kl": 0.087890625,
      "learning_rate": 9.982795577459445e-07,
      "loss": 0.0035,
      "reward": 2.0375313758850098,
      "reward_std": 0.014005608856678009,
      "rewards/accuracy_reward": 0.8375312685966492,
      "rewards/format_reward": 1.0,
      "step": 1915
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.0,
      "completion_length": 400.375,
      "epoch": 0.02642722169349388,
      "grad_norm": 4.12686725948492,
      "kl": 0.08056640625,
      "learning_rate": 9.982777615027631e-07,
      "loss": 0.0032,
      "reward": 2.066093921661377,
      "reward_std": 0.020965585485100746,
      "rewards/accuracy_reward": 0.8660937547683716,
      "rewards/format_reward": 1.0,
      "step": 1916
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.0,
      "completion_length": 391.375,
      "epoch": 0.02644101460669508,
      "grad_norm": 2.2022983580988065,
      "kl": 0.0693359375,
      "learning_rate": 9.982759643239965e-07,
      "loss": 0.0028,
      "reward": 2.045781135559082,
      "reward_std": 0.04319870471954346,
      "rewards/accuracy_reward": 0.8582812547683716,
      "rewards/format_reward": 1.0,
      "step": 1917
    },
    {
      "all_correct": 0.25,
      "all_wrong": 0.0,
      "completion_length": 398.59375,
      "epoch": 0.026454807519896276,
      "grad_norm": 3.089738262417307,
      "kl": 0.078125,
      "learning_rate": 9.982741662096484e-07,
      "loss": 0.0031,
      "reward": 2.0027499198913574,
      "reward_std": 0.03057563677430153,
      "rewards/accuracy_reward": 0.8090000152587891,
      "rewards/format_reward": 1.0,
      "step": 1918
    },
    {
      "all_correct": 1.0,
      "all_wrong": 0.0,
      "completion_length": 409.625,
      "epoch": 0.026468600433097473,
      "grad_norm": 1.5438678519468854,
      "kl": 0.0703125,
      "learning_rate": 9.98272367159722e-07,
      "loss": 0.0028,
      "reward": 2.1192188262939453,
      "reward_std": 0.005279357545077801,
      "rewards/accuracy_reward": 0.9192187786102295,
      "rewards/format_reward": 1.0,
      "step": 1919
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.0,
      "completion_length": 404.0,
      "epoch": 0.02648239334629867,
      "grad_norm": 7.949626451142351,
      "kl": 0.0693359375,
      "learning_rate": 9.982705671742206e-07,
      "loss": 0.0028,
      "reward": 1.9359376430511475,
      "reward_std": 0.022330183535814285,
      "rewards/accuracy_reward": 0.7359374761581421,
      "rewards/format_reward": 1.0,
      "step": 1920
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.0,
      "completion_length": 433.40625,
      "epoch": 0.026496186259499867,
      "grad_norm": 6.705376621560179,
      "kl": 0.07568359375,
      "learning_rate": 9.98268766253148e-07,
      "loss": 0.003,
      "reward": 2.0542500019073486,
      "reward_std": 0.04051809012889862,
      "rewards/accuracy_reward": 0.8667500615119934,
      "rewards/format_reward": 1.0,
      "step": 1921
    },
    {
      "all_correct": 0.75,
      "all_wrong": 0.0,
      "completion_length": 413.71875,
      "epoch": 0.026509979172701065,
      "grad_norm": 2.781573787713504,
      "kl": 0.080078125,
      "learning_rate": 9.98266964396507e-07,
      "loss": 0.0032,
      "reward": 2.080312490463257,
      "reward_std": 0.020189763978123665,
      "rewards/accuracy_reward": 0.880312442779541,
      "rewards/format_reward": 1.0,
      "step": 1922
    },
    {
      "all_correct": 0.75,
      "all_wrong": 0.0,
      "completion_length": 420.875,
      "epoch": 0.026523772085902262,
      "grad_norm": 3.9693455782903384,
      "kl": 0.07421875,
      "learning_rate": 9.982651616043012e-07,
      "loss": 0.003,
      "reward": 2.1007189750671387,
      "reward_std": 0.019428091123700142,
      "rewards/accuracy_reward": 0.9007187485694885,
      "rewards/format_reward": 1.0,
      "step": 1923
    },
    {
      "all_correct": 0.75,
      "all_wrong": 0.0,
      "completion_length": 410.1875,
      "epoch": 0.02653756499910346,
      "grad_norm": 6.0958947140648325,
      "kl": 0.06982421875,
      "learning_rate": 9.982633578765343e-07,
      "loss": 0.0028,
      "reward": 2.0754687786102295,
      "reward_std": 0.02279149740934372,
      "rewards/accuracy_reward": 0.8754688501358032,
      "rewards/format_reward": 1.0,
      "step": 1924
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.0,
      "completion_length": 412.9375,
      "epoch": 0.026551357912304657,
      "grad_norm": 2.7130420140475895,
      "kl": 0.07666015625,
      "learning_rate": 9.982615532132092e-07,
      "loss": 0.0031,
      "reward": 2.0829687118530273,
      "reward_std": 0.03561375290155411,
      "rewards/accuracy_reward": 0.889218807220459,
      "rewards/format_reward": 1.0,
      "step": 1925
    },
    {
      "all_correct": 0.75,
      "all_wrong": 0.0,
      "completion_length": 413.8125,
      "epoch": 0.026565150825505854,
      "grad_norm": 2.733139048458819,
      "kl": 0.09228515625,
      "learning_rate": 9.982597476143297e-07,
      "loss": 0.0037,
      "reward": 2.0730624198913574,
      "reward_std": 0.013417109847068787,
      "rewards/accuracy_reward": 0.8730624318122864,
      "rewards/format_reward": 1.0,
      "step": 1926
    },
    {
      "all_correct": 1.0,
      "all_wrong": 0.0,
      "completion_length": 410.34375,
      "epoch": 0.02657894373870705,
      "grad_norm": 5.9815436825189465,
      "kl": 0.078125,
      "learning_rate": 9.98257941079899e-07,
      "loss": 0.0031,
      "reward": 2.1597185134887695,
      "reward_std": 0.01997998356819153,
      "rewards/accuracy_reward": 0.9597187042236328,
      "rewards/format_reward": 1.0,
      "step": 1927
    },
    {
      "all_correct": 0.75,
      "all_wrong": 0.0,
      "completion_length": 402.375,
      "epoch": 0.02659273665190825,
      "grad_norm": 3.226744660428045,
      "kl": 0.08251953125,
      "learning_rate": 9.982561336099203e-07,
      "loss": 0.0033,
      "reward": 2.098749876022339,
      "reward_std": 0.009890900924801826,
      "rewards/accuracy_reward": 0.8987500667572021,
      "rewards/format_reward": 1.0,
      "step": 1928
    },
    {
      "all_correct": 0.75,
      "all_wrong": 0.0,
      "completion_length": 417.59375,
      "epoch": 0.026606529565109446,
      "grad_norm": 5.241779991096966,
      "kl": 0.08740234375,
      "learning_rate": 9.982543252043974e-07,
      "loss": 0.0035,
      "reward": 2.103968858718872,
      "reward_std": 0.016507325693964958,
      "rewards/accuracy_reward": 0.9039686918258667,
      "rewards/format_reward": 1.0,
      "step": 1929
    },
    {
      "all_correct": 1.0,
      "all_wrong": 0.0,
      "completion_length": 405.03125,
      "epoch": 0.026620322478310643,
      "grad_norm": 1.595461150707015,
      "kl": 0.07421875,
      "learning_rate": 9.982525158633333e-07,
      "loss": 0.003,
      "reward": 2.1637187004089355,
      "reward_std": 0.008594900369644165,
      "rewards/accuracy_reward": 0.9637187719345093,
      "rewards/format_reward": 1.0,
      "step": 1930
    },
    {
      "all_correct": 0.75,
      "all_wrong": 0.0,
      "completion_length": 416.34375,
      "epoch": 0.02663411539151184,
      "grad_norm": 3.701514816567279,
      "kl": 0.0791015625,
      "learning_rate": 9.982507055867317e-07,
      "loss": 0.0032,
      "reward": 2.0741562843322754,
      "reward_std": 0.021511593833565712,
      "rewards/accuracy_reward": 0.8741562366485596,
      "rewards/format_reward": 1.0,
      "step": 1931
    },
    {
      "all_correct": 0.75,
      "all_wrong": 0.0,
      "completion_length": 406.625,
      "epoch": 0.026647908304713037,
      "grad_norm": 4.059367068286267,
      "kl": 0.08203125,
      "learning_rate": 9.98248894374596e-07,
      "loss": 0.0033,
      "reward": 2.122468948364258,
      "reward_std": 0.020731305703520775,
      "rewards/accuracy_reward": 0.9224687218666077,
      "rewards/format_reward": 1.0,
      "step": 1932
    },
    {
      "all_correct": 1.0,
      "all_wrong": 0.0,
      "completion_length": 402.4375,
      "epoch": 0.026661701217914235,
      "grad_norm": 3.5167449646235784,
      "kl": 0.08251953125,
      "learning_rate": 9.982470822269294e-07,
      "loss": 0.0033,
      "reward": 2.0926249027252197,
      "reward_std": 0.01040612906217575,
      "rewards/accuracy_reward": 0.8926249742507935,
      "rewards/format_reward": 1.0,
      "step": 1933
    },
    {
      "all_correct": 1.0,
      "all_wrong": 0.0,
      "completion_length": 398.4375,
      "epoch": 0.026675494131115432,
      "grad_norm": 5.159893282997334,
      "kl": 0.0732421875,
      "learning_rate": 9.982452691437354e-07,
      "loss": 0.0029,
      "reward": 2.0933749675750732,
      "reward_std": 0.01213439553976059,
      "rewards/accuracy_reward": 0.893375039100647,
      "rewards/format_reward": 1.0,
      "step": 1934
    },
    {
      "all_correct": 1.0,
      "all_wrong": 0.0,
      "completion_length": 399.78125,
      "epoch": 0.02668928704431663,
      "grad_norm": 2.798177561141299,
      "kl": 0.07958984375,
      "learning_rate": 9.982434551250174e-07,
      "loss": 0.0032,
      "reward": 2.117500066757202,
      "reward_std": 0.016086172312498093,
      "rewards/accuracy_reward": 0.9175000190734863,
      "rewards/format_reward": 1.0,
      "step": 1935
    },
    {
      "all_correct": 0.75,
      "all_wrong": 0.0,
      "completion_length": 410.15625,
      "epoch": 0.026703079957517827,
      "grad_norm": 5.82826113507385,
      "kl": 0.0810546875,
      "learning_rate": 9.982416401707787e-07,
      "loss": 0.0032,
      "reward": 2.0697813034057617,
      "reward_std": 0.016002286225557327,
      "rewards/accuracy_reward": 0.8697812557220459,
      "rewards/format_reward": 1.0,
      "step": 1936
    },
    {
      "all_correct": 1.0,
      "all_wrong": 0.0,
      "completion_length": 398.90625,
      "epoch": 0.026716872870719024,
      "grad_norm": 4.606238427406338,
      "kl": 0.0869140625,
      "learning_rate": 9.98239824281023e-07,
      "loss": 0.0035,
      "reward": 2.12250018119812,
      "reward_std": 0.023778196424245834,
      "rewards/accuracy_reward": 0.9225000143051147,
      "rewards/format_reward": 1.0,
      "step": 1937
    },
    {
      "all_correct": 0.75,
      "all_wrong": 0.0,
      "completion_length": 399.03125,
      "epoch": 0.02673066578392022,
      "grad_norm": 3.3284601819839286,
      "kl": 0.07666015625,
      "learning_rate": 9.982380074557532e-07,
      "loss": 0.0031,
      "reward": 2.1208436489105225,
      "reward_std": 0.016521064564585686,
      "rewards/accuracy_reward": 0.9208437204360962,
      "rewards/format_reward": 1.0,
      "step": 1938
    },
    {
      "all_correct": 1.0,
      "all_wrong": 0.0,
      "completion_length": 389.21875,
      "epoch": 0.02674445869712142,
      "grad_norm": 2.516936344554583,
      "kl": 0.07177734375,
      "learning_rate": 9.982361896949733e-07,
      "loss": 0.0029,
      "reward": 2.1640625,
      "reward_std": 0.02064230851829052,
      "rewards/accuracy_reward": 0.964062511920929,
      "rewards/format_reward": 1.0,
      "step": 1939
    },
    {
      "all_correct": 0.75,
      "all_wrong": 0.0,
      "completion_length": 388.59375,
      "epoch": 0.026758251610322616,
      "grad_norm": 4.057452587358344,
      "kl": 0.08642578125,
      "learning_rate": 9.982343709986866e-07,
      "loss": 0.0035,
      "reward": 2.10728120803833,
      "reward_std": 0.016745882108807564,
      "rewards/accuracy_reward": 0.9072812795639038,
      "rewards/format_reward": 1.0,
      "step": 1940
    },
    {
      "all_correct": 1.0,
      "all_wrong": 0.0,
      "completion_length": 398.09375,
      "epoch": 0.026772044523523813,
      "grad_norm": 4.760308136592588,
      "kl": 0.08349609375,
      "learning_rate": 9.98232551366896e-07,
      "loss": 0.0033,
      "reward": 2.116062641143799,
      "reward_std": 0.016728738322854042,
      "rewards/accuracy_reward": 0.9160624742507935,
      "rewards/format_reward": 1.0,
      "step": 1941
    },
    {
      "all_correct": 1.0,
      "all_wrong": 0.0,
      "completion_length": 399.1875,
      "epoch": 0.02678583743672501,
      "grad_norm": 2.2878912312656414,
      "kl": 0.07275390625,
      "learning_rate": 9.982307307996054e-07,
      "loss": 0.0029,
      "reward": 2.1108436584472656,
      "reward_std": 0.012023009359836578,
      "rewards/accuracy_reward": 0.9108437895774841,
      "rewards/format_reward": 1.0,
      "step": 1942
    },
    {
      "all_correct": 0.75,
      "all_wrong": 0.0,
      "completion_length": 396.8125,
      "epoch": 0.026799630349926207,
      "grad_norm": 2.37695671372471,
      "kl": 0.08740234375,
      "learning_rate": 9.98228909296818e-07,
      "loss": 0.0035,
      "reward": 2.096062660217285,
      "reward_std": 0.02040119841694832,
      "rewards/accuracy_reward": 0.8960624933242798,
      "rewards/format_reward": 1.0,
      "step": 1943
    },
    {
      "all_correct": 0.75,
      "all_wrong": 0.0,
      "completion_length": 387.59375,
      "epoch": 0.026813423263127405,
      "grad_norm": 2.9096358192113403,
      "kl": 0.08154296875,
      "learning_rate": 9.982270868585376e-07,
      "loss": 0.0033,
      "reward": 2.075531244277954,
      "reward_std": 0.030106842517852783,
      "rewards/accuracy_reward": 0.881781280040741,
      "rewards/format_reward": 1.0,
      "step": 1944
    },
    {
      "all_correct": 1.0,
      "all_wrong": 0.0,
      "completion_length": 399.625,
      "epoch": 0.026827216176328602,
      "grad_norm": 18.07686300226145,
      "kl": 0.0712890625,
      "learning_rate": 9.98225263484767e-07,
      "loss": 0.0028,
      "reward": 2.146228313446045,
      "reward_std": 0.011443981900811195,
      "rewards/accuracy_reward": 0.9462281465530396,
      "rewards/format_reward": 1.0,
      "step": 1945
    },
    {
      "all_correct": 1.0,
      "all_wrong": 0.0,
      "completion_length": 386.78125,
      "epoch": 0.0268410090895298,
      "grad_norm": 4.711936782595007,
      "kl": 0.08154296875,
      "learning_rate": 9.982234391755101e-07,
      "loss": 0.0033,
      "reward": 2.153125047683716,
      "reward_std": 0.021105458959937096,
      "rewards/accuracy_reward": 0.9531249403953552,
      "rewards/format_reward": 1.0,
      "step": 1946
    },
    {
      "all_correct": 0.75,
      "all_wrong": 0.0,
      "completion_length": 386.1875,
      "epoch": 0.026854802002730997,
      "grad_norm": 2.269853761924988,
      "kl": 0.08203125,
      "learning_rate": 9.982216139307704e-07,
      "loss": 0.0033,
      "reward": 2.098656177520752,
      "reward_std": 0.015547218732535839,
      "rewards/accuracy_reward": 0.8986562490463257,
      "rewards/format_reward": 1.0,
      "step": 1947
    },
    {
      "all_correct": 0.25,
      "all_wrong": 0.0,
      "completion_length": 398.625,
      "epoch": 0.026868594915932194,
      "grad_norm": 4.844174160012034,
      "kl": 0.072265625,
      "learning_rate": 9.982197877505507e-07,
      "loss": 0.0029,
      "reward": 1.9913437366485596,
      "reward_std": 0.027762141078710556,
      "rewards/accuracy_reward": 0.7913437485694885,
      "rewards/format_reward": 1.0,
      "step": 1948
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.0,
      "completion_length": 386.875,
      "epoch": 0.02688238782913339,
      "grad_norm": 3.9429491554399276,
      "kl": 0.0791015625,
      "learning_rate": 9.982179606348552e-07,
      "loss": 0.0031,
      "reward": 2.0159687995910645,
      "reward_std": 0.016044585034251213,
      "rewards/accuracy_reward": 0.8159687519073486,
      "rewards/format_reward": 1.0,
      "step": 1949
    },
    {
      "all_correct": 1.0,
      "all_wrong": 0.0,
      "completion_length": 387.875,
      "epoch": 0.02689618074233459,
      "grad_norm": 2.5314859747253577,
      "kl": 0.083984375,
      "learning_rate": 9.982161325836867e-07,
      "loss": 0.0034,
      "reward": 2.1345314979553223,
      "reward_std": 0.013676775619387627,
      "rewards/accuracy_reward": 0.9345312118530273,
      "rewards/format_reward": 1.0,
      "step": 1950
    },
    {
      "all_correct": 1.0,
      "all_wrong": 0.0,
      "completion_length": 384.34375,
      "epoch": 0.026909973655535786,
      "grad_norm": 3.7754952187315673,
      "kl": 0.0751953125,
      "learning_rate": 9.98214303597049e-07,
      "loss": 0.003,
      "reward": 2.1527812480926514,
      "reward_std": 0.009778826497495174,
      "rewards/accuracy_reward": 0.9527812004089355,
      "rewards/format_reward": 1.0,
      "step": 1951
    },
    {
      "all_correct": 1.0,
      "all_wrong": 0.0,
      "completion_length": 377.6875,
      "epoch": 0.026923766568736983,
      "grad_norm": 3.894202600297443,
      "kl": 0.0703125,
      "learning_rate": 9.982124736749456e-07,
      "loss": 0.0028,
      "reward": 2.1665310859680176,
      "reward_std": 0.028231702744960785,
      "rewards/accuracy_reward": 0.972781240940094,
      "rewards/format_reward": 1.0,
      "step": 1952
    },
    {
      "all_correct": 1.0,
      "all_wrong": 0.0,
      "completion_length": 385.21875,
      "epoch": 0.02693755948193818,
      "grad_norm": 3.0224362183706552,
      "kl": 0.07177734375,
      "learning_rate": 9.982106428173795e-07,
      "loss": 0.0029,
      "reward": 2.1128437519073486,
      "reward_std": 0.022281402722001076,
      "rewards/accuracy_reward": 0.9128437042236328,
      "rewards/format_reward": 1.0,
      "step": 1953
    },
    {
      "all_correct": 1.0,
      "all_wrong": 0.0,
      "completion_length": 380.25,
      "epoch": 0.026951352395139377,
      "grad_norm": 2.7560229497486577,
      "kl": 0.080078125,
      "learning_rate": 9.982088110243547e-07,
      "loss": 0.0032,
      "reward": 2.126312494277954,
      "reward_std": 0.01885402575135231,
      "rewards/accuracy_reward": 0.9263124465942383,
      "rewards/format_reward": 1.0,
      "step": 1954
    },
    {
      "all_correct": 0.75,
      "all_wrong": 0.0,
      "completion_length": 396.0625,
      "epoch": 0.026965145308340575,
      "grad_norm": 2.2702322374515997,
      "kl": 0.0712890625,
      "learning_rate": 9.982069782958743e-07,
      "loss": 0.0029,
      "reward": 2.132093906402588,
      "reward_std": 0.01684606447815895,
      "rewards/accuracy_reward": 0.9320937395095825,
      "rewards/format_reward": 1.0,
      "step": 1955
    },
    {
      "all_correct": 0.25,
      "all_wrong": 0.0,
      "completion_length": 383.3125,
      "epoch": 0.026978938221541772,
      "grad_norm": 2.7368210978615095,
      "kl": 0.076171875,
      "learning_rate": 9.982051446319415e-07,
      "loss": 0.0031,
      "reward": 2.015718936920166,
      "reward_std": 0.03476415574550629,
      "rewards/accuracy_reward": 0.8219687938690186,
      "rewards/format_reward": 1.0,
      "step": 1956
    },
    {
      "all_correct": 1.0,
      "all_wrong": 0.0,
      "completion_length": 384.9375,
      "epoch": 0.02699273113474297,
      "grad_norm": 12.12168128461032,
      "kl": 0.08984375,
      "learning_rate": 9.982033100325601e-07,
      "loss": 0.0036,
      "reward": 2.1455624103546143,
      "reward_std": 0.01730254851281643,
      "rewards/accuracy_reward": 0.945562481880188,
      "rewards/format_reward": 1.0,
      "step": 1957
    },
    {
      "all_correct": 1.0,
      "all_wrong": 0.0,
      "completion_length": 377.875,
      "epoch": 0.027006524047944167,
      "grad_norm": 2.6107115616525496,
      "kl": 0.0791015625,
      "learning_rate": 9.982014744977338e-07,
      "loss": 0.0032,
      "reward": 2.1704063415527344,
      "reward_std": 0.013156077824532986,
      "rewards/accuracy_reward": 0.9704062938690186,
      "rewards/format_reward": 1.0,
      "step": 1958
    },
    {
      "all_correct": 0.75,
      "all_wrong": 0.0,
      "completion_length": 385.9375,
      "epoch": 0.027020316961145364,
      "grad_norm": 1.9175153963905764,
      "kl": 0.07373046875,
      "learning_rate": 9.981996380274655e-07,
      "loss": 0.0029,
      "reward": 2.139937400817871,
      "reward_std": 0.029868323355913162,
      "rewards/accuracy_reward": 0.9399374723434448,
      "rewards/format_reward": 1.0,
      "step": 1959
    },
    {
      "all_correct": 0.75,
      "all_wrong": 0.0,
      "completion_length": 389.3125,
      "epoch": 0.02703410987434656,
      "grad_norm": 4.01039788479685,
      "kl": 0.080078125,
      "learning_rate": 9.98197800621759e-07,
      "loss": 0.0032,
      "reward": 2.151249885559082,
      "reward_std": 0.02801770344376564,
      "rewards/accuracy_reward": 0.9574999809265137,
      "rewards/format_reward": 1.0,
      "step": 1960
    },
    {
      "all_correct": 1.0,
      "all_wrong": 0.0,
      "completion_length": 385.03125,
      "epoch": 0.02704790278754776,
      "grad_norm": 1.8568752414585066,
      "kl": 0.07275390625,
      "learning_rate": 9.981959622806174e-07,
      "loss": 0.0029,
      "reward": 2.1570000648498535,
      "reward_std": 0.013699093833565712,
      "rewards/accuracy_reward": 0.9569999575614929,
      "rewards/format_reward": 1.0,
      "step": 1961
    },
    {
      "all_correct": 1.0,
      "all_wrong": 0.0,
      "completion_length": 370.28125,
      "epoch": 0.027061695700748956,
      "grad_norm": 2.023916101610666,
      "kl": 0.08056640625,
      "learning_rate": 9.981941230040446e-07,
      "loss": 0.0032,
      "reward": 2.1745312213897705,
      "reward_std": 0.02012145332992077,
      "rewards/accuracy_reward": 0.9807811975479126,
      "rewards/format_reward": 1.0,
      "step": 1962
    },
    {
      "all_correct": 1.0,
      "all_wrong": 0.0,
      "completion_length": 385.09375,
      "epoch": 0.027075488613950153,
      "grad_norm": 5.848948952517147,
      "kl": 0.08935546875,
      "learning_rate": 9.981922827920438e-07,
      "loss": 0.0036,
      "reward": 2.152250051498413,
      "reward_std": 0.01440475881099701,
      "rewards/accuracy_reward": 0.9522500038146973,
      "rewards/format_reward": 1.0,
      "step": 1963
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.0,
      "completion_length": 388.8125,
      "epoch": 0.02708928152715135,
      "grad_norm": 5.063419446627412,
      "kl": 0.0849609375,
      "learning_rate": 9.981904416446183e-07,
      "loss": 0.0034,
      "reward": 2.0025312900543213,
      "reward_std": 0.03082101047039032,
      "rewards/accuracy_reward": 0.8025312423706055,
      "rewards/format_reward": 1.0,
      "step": 1964
    },
    {
      "all_correct": 1.0,
      "all_wrong": 0.0,
      "completion_length": 403.5625,
      "epoch": 0.027103074440352547,
      "grad_norm": 2.479213858347537,
      "kl": 0.078125,
      "learning_rate": 9.981885995617718e-07,
      "loss": 0.0031,
      "reward": 2.1049375534057617,
      "reward_std": 0.022446513175964355,
      "rewards/accuracy_reward": 0.9049373865127563,
      "rewards/format_reward": 1.0,
      "step": 1965
    },
    {
      "all_correct": 0.0,
      "all_wrong": 0.0,
      "completion_length": 387.59375,
      "epoch": 0.027116867353553745,
      "grad_norm": 2.600204433737937,
      "kl": 0.08349609375,
      "learning_rate": 9.981867565435079e-07,
      "loss": 0.0033,
      "reward": 2.0359063148498535,
      "reward_std": 0.07090350240468979,
      "rewards/accuracy_reward": 0.8609062433242798,
      "rewards/format_reward": 1.0,
      "step": 1966
    },
    {
      "all_correct": 0.75,
      "all_wrong": 0.0,
      "completion_length": 408.3125,
      "epoch": 0.027130660266754942,
      "grad_norm": 3.9609062881331445,
      "kl": 0.0751953125,
      "learning_rate": 9.981849125898296e-07,
      "loss": 0.003,
      "reward": 2.112093925476074,
      "reward_std": 0.015172101557254791,
      "rewards/accuracy_reward": 0.9120937585830688,
      "rewards/format_reward": 1.0,
      "step": 1967
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.0,
      "completion_length": 405.71875,
      "epoch": 0.02714445317995614,
      "grad_norm": 3.9779621494863298,
      "kl": 0.072265625,
      "learning_rate": 9.981830677007407e-07,
      "loss": 0.0029,
      "reward": 1.975968837738037,
      "reward_std": 0.009230835363268852,
      "rewards/accuracy_reward": 0.7759687900543213,
      "rewards/format_reward": 1.0,
      "step": 1968
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.0,
      "completion_length": 391.84375,
      "epoch": 0.027158246093157336,
      "grad_norm": 8.56251786215719,
      "kl": 0.07763671875,
      "learning_rate": 9.981812218762446e-07,
      "loss": 0.0031,
      "reward": 2.0310938358306885,
      "reward_std": 0.017720166593790054,
      "rewards/accuracy_reward": 0.8310937881469727,
      "rewards/format_reward": 1.0,
      "step": 1969
    },
    {
      "all_correct": 0.25,
      "all_wrong": 0.0,
      "completion_length": 401.59375,
      "epoch": 0.027172039006358534,
      "grad_norm": 2.492009152427361,
      "kl": 0.0791015625,
      "learning_rate": 9.98179375116345e-07,
      "loss": 0.0032,
      "reward": 1.9724063873291016,
      "reward_std": 0.03215337544679642,
      "rewards/accuracy_reward": 0.7786562442779541,
      "rewards/format_reward": 1.0,
      "step": 1970
    },
    {
      "all_correct": 0.75,
      "all_wrong": 0.0,
      "completion_length": 411.6875,
      "epoch": 0.02718583191955973,
      "grad_norm": 2.122142069281791,
      "kl": 0.07470703125,
      "learning_rate": 9.981775274210448e-07,
      "loss": 0.003,
      "reward": 2.152937412261963,
      "reward_std": 0.023467950522899628,
      "rewards/accuracy_reward": 0.9591875076293945,
      "rewards/format_reward": 1.0,
      "step": 1971
    },
    {
      "all_correct": 0.75,
      "all_wrong": 0.0,
      "completion_length": 399.78125,
      "epoch": 0.02719962483276093,
      "grad_norm": 5.255352051053777,
      "kl": 0.0771484375,
      "learning_rate": 9.98175678790348e-07,
      "loss": 0.0031,
      "reward": 2.074718713760376,
      "reward_std": 0.023217612877488136,
      "rewards/accuracy_reward": 0.8747187256813049,
      "rewards/format_reward": 1.0,
      "step": 1972
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.0,
      "completion_length": 410.40625,
      "epoch": 0.027213417745962126,
      "grad_norm": 3.306688164824961,
      "kl": 0.080078125,
      "learning_rate": 9.981738292242575e-07,
      "loss": 0.0032,
      "reward": 2.100562572479248,
      "reward_std": 0.03188871964812279,
      "rewards/accuracy_reward": 0.9068125486373901,
      "rewards/format_reward": 1.0,
      "step": 1973
    },
    {
      "all_correct": 0.75,
      "all_wrong": 0.0,
      "completion_length": 413.28125,
      "epoch": 0.027227210659163323,
      "grad_norm": 3.200523432744986,
      "kl": 0.076171875,
      "learning_rate": 9.981719787227777e-07,
      "loss": 0.003,
      "reward": 2.0820624828338623,
      "reward_std": 0.029341604560613632,
      "rewards/accuracy_reward": 0.882062554359436,
      "rewards/format_reward": 1.0,
      "step": 1974
    },
    {
      "all_correct": 0.75,
      "all_wrong": 0.0,
      "completion_length": 414.90625,
      "epoch": 0.02724100357236452,
      "grad_norm": 2.942676915792152,
      "kl": 0.07470703125,
      "learning_rate": 9.98170127285911e-07,
      "loss": 0.003,
      "reward": 2.1136250495910645,
      "reward_std": 0.03603549301624298,
      "rewards/accuracy_reward": 0.9261250495910645,
      "rewards/format_reward": 1.0,
      "step": 1975
    },
    {
      "all_correct": 0.75,
      "all_wrong": 0.0,
      "completion_length": 416.1875,
      "epoch": 0.027254796485565717,
      "grad_norm": 2.672573354475276,
      "kl": 0.08447265625,
      "learning_rate": 9.981682749136615e-07,
      "loss": 0.0034,
      "reward": 2.0636250972747803,
      "reward_std": 0.015592987649142742,
      "rewards/accuracy_reward": 0.8636249303817749,
      "rewards/format_reward": 1.0,
      "step": 1976
    },
    {
      "all_correct": 1.0,
      "all_wrong": 0.0,
      "completion_length": 419.21875,
      "epoch": 0.027268589398766915,
      "grad_norm": 2.124067155647725,
      "kl": 0.08447265625,
      "learning_rate": 9.98166421606033e-07,
      "loss": 0.0034,
      "reward": 2.160562515258789,
      "reward_std": 0.00924752838909626,
      "rewards/accuracy_reward": 0.9605624675750732,
      "rewards/format_reward": 1.0,
      "step": 1977
    },
    {
      "all_correct": 0.0,
      "all_wrong": 0.0,
      "completion_length": 407.4375,
      "epoch": 0.027282382311968112,
      "grad_norm": 3.582608939553046,
      "kl": 0.0771484375,
      "learning_rate": 9.981645673630279e-07,
      "loss": 0.0031,
      "reward": 2.0482499599456787,
      "reward_std": 0.0560419037938118,
      "rewards/accuracy_reward": 0.8607499599456787,
      "rewards/format_reward": 1.0,
      "step": 1978
    },
    {
      "all_correct": 1.0,
      "all_wrong": 0.0,
      "completion_length": 395.1875,
      "epoch": 0.02729617522516931,
      "grad_norm": 3.909923980094944,
      "kl": 0.068359375,
      "learning_rate": 9.981627121846507e-07,
      "loss": 0.0027,
      "reward": 2.1547813415527344,
      "reward_std": 0.008173666894435883,
      "rewards/accuracy_reward": 0.9547812938690186,
      "rewards/format_reward": 1.0,
      "step": 1979
    },
    {
      "all_correct": 0.75,
      "all_wrong": 0.0,
      "completion_length": 418.28125,
      "epoch": 0.027309968138370506,
      "grad_norm": 2.298319390584412,
      "kl": 0.0703125,
      "learning_rate": 9.981608560709044e-07,
      "loss": 0.0028,
      "reward": 2.1258749961853027,
      "reward_std": 0.012761179357767105,
      "rewards/accuracy_reward": 0.9258750081062317,
      "rewards/format_reward": 1.0,
      "step": 1980
    },
    {
      "all_correct": 1.0,
      "all_wrong": 0.0,
      "completion_length": 421.25,
      "epoch": 0.027323761051571704,
      "grad_norm": 3.62657996977868,
      "kl": 0.0830078125,
      "learning_rate": 9.981589990217927e-07,
      "loss": 0.0033,
      "reward": 2.145718574523926,
      "reward_std": 0.01764613762497902,
      "rewards/accuracy_reward": 0.9457187652587891,
      "rewards/format_reward": 1.0,
      "step": 1981
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.0,
      "completion_length": 424.3125,
      "epoch": 0.0273375539647729,
      "grad_norm": 4.885730841161599,
      "kl": 0.08251953125,
      "learning_rate": 9.981571410373189e-07,
      "loss": 0.0033,
      "reward": 2.03696870803833,
      "reward_std": 0.02655961364507675,
      "rewards/accuracy_reward": 0.836968719959259,
      "rewards/format_reward": 1.0,
      "step": 1982
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.0,
      "completion_length": 433.6875,
      "epoch": 0.0273513468779741,
      "grad_norm": 2.1726128678289283,
      "kl": 0.08203125,
      "learning_rate": 9.981552821174865e-07,
      "loss": 0.0033,
      "reward": 2.051968574523926,
      "reward_std": 0.043825335800647736,
      "rewards/accuracy_reward": 0.8707187175750732,
      "rewards/format_reward": 1.0,
      "step": 1983
    },
    {
      "all_correct": 0.75,
      "all_wrong": 0.0,
      "completion_length": 410.125,
      "epoch": 0.027365139791175296,
      "grad_norm": 2.3507363545677222,
      "kl": 0.0791015625,
      "learning_rate": 9.98153422262299e-07,
      "loss": 0.0032,
      "reward": 1.9909999370574951,
      "reward_std": 0.01418959628790617,
      "rewards/accuracy_reward": 0.7910000085830688,
      "rewards/format_reward": 1.0,
      "step": 1984
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.0,
      "completion_length": 431.90625,
      "epoch": 0.027378932704376493,
      "grad_norm": 2.3753046950223196,
      "kl": 0.07177734375,
      "learning_rate": 9.981515614717603e-07,
      "loss": 0.0029,
      "reward": 2.053093910217285,
      "reward_std": 0.01402326300740242,
      "rewards/accuracy_reward": 0.8530938029289246,
      "rewards/format_reward": 1.0,
      "step": 1985
    },
    {
      "all_correct": 0.25,
      "all_wrong": 0.0,
      "completion_length": 409.90625,
      "epoch": 0.02739272561757769,
      "grad_norm": 3.391280828791311,
      "kl": 0.08203125,
      "learning_rate": 9.98149699745873e-07,
      "loss": 0.0033,
      "reward": 1.9285000562667847,
      "reward_std": 0.023256802931427956,
      "rewards/accuracy_reward": 0.7285000085830688,
      "rewards/format_reward": 1.0,
      "step": 1986
    },
    {
      "all_correct": 0.75,
      "all_wrong": 0.0,
      "completion_length": 414.3125,
      "epoch": 0.027406518530778887,
      "grad_norm": 2.6992841528426923,
      "kl": 0.076171875,
      "learning_rate": 9.981478370846417e-07,
      "loss": 0.003,
      "reward": 2.1123123168945312,
      "reward_std": 0.016241051256656647,
      "rewards/accuracy_reward": 0.9123125076293945,
      "rewards/format_reward": 1.0,
      "step": 1987
    },
    {
      "all_correct": 0.75,
      "all_wrong": 0.0,
      "completion_length": 417.6875,
      "epoch": 0.027420311443980085,
      "grad_norm": 3.2972260704656615,
      "kl": 0.08984375,
      "learning_rate": 9.98145973488069e-07,
      "loss": 0.0036,
      "reward": 2.121500015258789,
      "reward_std": 0.03570738807320595,
      "rewards/accuracy_reward": 0.9277500510215759,
      "rewards/format_reward": 1.0,
      "step": 1988
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.0,
      "completion_length": 423.125,
      "epoch": 0.027434104357181282,
      "grad_norm": 1.9603578758219324,
      "kl": 0.0888671875,
      "learning_rate": 9.981441089561589e-07,
      "loss": 0.0036,
      "reward": 2.102656364440918,
      "reward_std": 0.025772742927074432,
      "rewards/accuracy_reward": 0.9089062213897705,
      "rewards/format_reward": 1.0,
      "step": 1989
    },
    {
      "all_correct": 0.75,
      "all_wrong": 0.0,
      "completion_length": 411.25,
      "epoch": 0.02744789727038248,
      "grad_norm": 3.9682732469748,
      "kl": 0.076171875,
      "learning_rate": 9.981422434889147e-07,
      "loss": 0.0031,
      "reward": 2.013406276702881,
      "reward_std": 0.012101572938263416,
      "rewards/accuracy_reward": 0.813406229019165,
      "rewards/format_reward": 1.0,
      "step": 1990
    },
    {
      "all_correct": 0.75,
      "all_wrong": 0.0,
      "completion_length": 412.21875,
      "epoch": 0.027461690183583673,
      "grad_norm": 3.5203845609518853,
      "kl": 0.07666015625,
      "learning_rate": 9.981403770863398e-07,
      "loss": 0.0031,
      "reward": 2.106062412261963,
      "reward_std": 0.015214774757623672,
      "rewards/accuracy_reward": 0.9060624837875366,
      "rewards/format_reward": 1.0,
      "step": 1991
    },
    {
      "all_correct": 1.0,
      "all_wrong": 0.0,
      "completion_length": 405.65625,
      "epoch": 0.02747548309678487,
      "grad_norm": 4.103945117895234,
      "kl": 0.0771484375,
      "learning_rate": 9.98138509748438e-07,
      "loss": 0.0031,
      "reward": 2.1064374446868896,
      "reward_std": 0.008362555876374245,
      "rewards/accuracy_reward": 0.9064374566078186,
      "rewards/format_reward": 1.0,
      "step": 1992
    },
    {
      "all_correct": 0.25,
      "all_wrong": 0.0,
      "completion_length": 412.96875,
      "epoch": 0.027489276009986068,
      "grad_norm": 1.8409485463186182,
      "kl": 0.07373046875,
      "learning_rate": 9.981366414752126e-07,
      "loss": 0.003,
      "reward": 1.9903438091278076,
      "reward_std": 0.02833339013159275,
      "rewards/accuracy_reward": 0.7965936660766602,
      "rewards/format_reward": 1.0,
      "step": 1993
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.0,
      "completion_length": 416.78125,
      "epoch": 0.027503068923187265,
      "grad_norm": 1.507191170318596,
      "kl": 0.06787109375,
      "learning_rate": 9.98134772266667e-07,
      "loss": 0.0027,
      "reward": 2.097062587738037,
      "reward_std": 0.008244003169238567,
      "rewards/accuracy_reward": 0.8970625400543213,
      "rewards/format_reward": 1.0,
      "step": 1994
    },
    {
      "all_correct": 1.0,
      "all_wrong": 0.0,
      "completion_length": 414.875,
      "epoch": 0.027516861836388462,
      "grad_norm": 6.4563752978414355,
      "kl": 0.08154296875,
      "learning_rate": 9.981329021228051e-07,
      "loss": 0.0033,
      "reward": 2.1385626792907715,
      "reward_std": 0.017914045602083206,
      "rewards/accuracy_reward": 0.9385625123977661,
      "rewards/format_reward": 1.0,
      "step": 1995
    },
    {
      "all_correct": 1.0,
      "all_wrong": 0.0,
      "completion_length": 412.65625,
      "epoch": 0.02753065474958966,
      "grad_norm": 2.9601656070699685,
      "kl": 0.0771484375,
      "learning_rate": 9.9813103104363e-07,
      "loss": 0.0031,
      "reward": 2.1109063625335693,
      "reward_std": 0.02493947744369507,
      "rewards/accuracy_reward": 0.910906195640564,
      "rewards/format_reward": 1.0,
      "step": 1996
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.0,
      "completion_length": 406.96875,
      "epoch": 0.027544447662790857,
      "grad_norm": 1.950536689661912,
      "kl": 0.076171875,
      "learning_rate": 9.981291590291456e-07,
      "loss": 0.003,
      "reward": 2.0784687995910645,
      "reward_std": 0.09255323559045792,
      "rewards/accuracy_reward": 0.9097187519073486,
      "rewards/format_reward": 0.96875,
      "step": 1997
    },
    {
      "all_correct": 1.0,
      "all_wrong": 0.0,
      "completion_length": 415.6875,
      "epoch": 0.027558240575992054,
      "grad_norm": 2.8686894224680453,
      "kl": 0.08984375,
      "learning_rate": 9.981272860793552e-07,
      "loss": 0.0036,
      "reward": 2.078218936920166,
      "reward_std": 0.015872638672590256,
      "rewards/accuracy_reward": 0.8782187104225159,
      "rewards/format_reward": 1.0,
      "step": 1998
    },
    {
      "all_correct": 0.75,
      "all_wrong": 0.0,
      "completion_length": 414.46875,
      "epoch": 0.02757203348919325,
      "grad_norm": 2.5342368902223744,
      "kl": 0.07421875,
      "learning_rate": 9.981254121942622e-07,
      "loss": 0.003,
      "reward": 2.1020312309265137,
      "reward_std": 0.010027805343270302,
      "rewards/accuracy_reward": 0.9020313024520874,
      "rewards/format_reward": 1.0,
      "step": 1999
    },
    {
      "all_correct": 1.0,
      "all_wrong": 0.0,
      "completion_length": 398.0,
      "epoch": 0.02758582640239445,
      "grad_norm": 2.610870944141539,
      "kl": 0.08056640625,
      "learning_rate": 9.981235373738703e-07,
      "loss": 0.0032,
      "reward": 2.119406223297119,
      "reward_std": 0.014805818907916546,
      "rewards/accuracy_reward": 0.9194062352180481,
      "rewards/format_reward": 1.0,
      "step": 2000
    },
    {
      "all_correct": 0.75,
      "all_wrong": 0.0,
      "completion_length": 401.4375,
      "epoch": 0.027599619315595646,
      "grad_norm": 2.8084775351197404,
      "kl": 0.076171875,
      "learning_rate": 9.98121661618183e-07,
      "loss": 0.003,
      "reward": 2.1069064140319824,
      "reward_std": 0.019730646163225174,
      "rewards/accuracy_reward": 0.906906247138977,
      "rewards/format_reward": 1.0,
      "step": 2001
    },
    {
      "all_correct": 0.75,
      "all_wrong": 0.0,
      "completion_length": 385.65625,
      "epoch": 0.027613412228796843,
      "grad_norm": 2.7114356860055113,
      "kl": 0.083984375,
      "learning_rate": 9.981197849272038e-07,
      "loss": 0.0034,
      "reward": 2.0946874618530273,
      "reward_std": 0.0399150587618351,
      "rewards/accuracy_reward": 0.9009374976158142,
      "rewards/format_reward": 1.0,
      "step": 2002
    },
    {
      "all_correct": 0.75,
      "all_wrong": 0.0,
      "completion_length": 405.6875,
      "epoch": 0.02762720514199804,
      "grad_norm": 2.3881314964794735,
      "kl": 0.07861328125,
      "learning_rate": 9.98117907300936e-07,
      "loss": 0.0032,
      "reward": 2.1321563720703125,
      "reward_std": 0.021678175777196884,
      "rewards/accuracy_reward": 0.9321562647819519,
      "rewards/format_reward": 1.0,
      "step": 2003
    },
    {
      "all_correct": 1.0,
      "all_wrong": 0.0,
      "completion_length": 395.6875,
      "epoch": 0.027640998055199237,
      "grad_norm": 2.9228114885434158,
      "kl": 0.078125,
      "learning_rate": 9.981160287393835e-07,
      "loss": 0.0031,
      "reward": 2.160749912261963,
      "reward_std": 0.011518163606524467,
      "rewards/accuracy_reward": 0.9607499837875366,
      "rewards/format_reward": 1.0,
      "step": 2004
    },
    {
      "all_correct": 1.0,
      "all_wrong": 0.0,
      "completion_length": 384.625,
      "epoch": 0.027654790968400435,
      "grad_norm": 2.3171069852133326,
      "kl": 0.072265625,
      "learning_rate": 9.981141492425496e-07,
      "loss": 0.0029,
      "reward": 2.1293439865112305,
      "reward_std": 0.017616232857108116,
      "rewards/accuracy_reward": 0.9293437004089355,
      "rewards/format_reward": 1.0,
      "step": 2005
    },
    {
      "all_correct": 1.0,
      "all_wrong": 0.0,
      "completion_length": 393.09375,
      "epoch": 0.027668583881601632,
      "grad_norm": 2.69804513497294,
      "kl": 0.08203125,
      "learning_rate": 9.98112268810438e-07,
      "loss": 0.0033,
      "reward": 2.1133437156677246,
      "reward_std": 0.011599687859416008,
      "rewards/accuracy_reward": 0.9133437871932983,
      "rewards/format_reward": 1.0,
      "step": 2006
    },
    {
      "all_correct": 0.75,
      "all_wrong": 0.0,
      "completion_length": 390.9375,
      "epoch": 0.02768237679480283,
      "grad_norm": 2.7925807919908587,
      "kl": 0.076171875,
      "learning_rate": 9.981103874430521e-07,
      "loss": 0.0031,
      "reward": 2.0713436603546143,
      "reward_std": 0.028428178280591965,
      "rewards/accuracy_reward": 0.8775937557220459,
      "rewards/format_reward": 1.0,
      "step": 2007
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.0,
      "completion_length": 381.6875,
      "epoch": 0.027696169708004027,
      "grad_norm": 6.916744212955163,
      "kl": 0.08447265625,
      "learning_rate": 9.981085051403954e-07,
      "loss": 0.0034,
      "reward": 2.0361876487731934,
      "reward_std": 0.03168478608131409,
      "rewards/accuracy_reward": 0.8424375057220459,
      "rewards/format_reward": 1.0,
      "step": 2008
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.0,
      "completion_length": 375.21875,
      "epoch": 0.027709962621205224,
      "grad_norm": 3.8174792734655085,
      "kl": 0.07568359375,
      "learning_rate": 9.981066219024715e-07,
      "loss": 0.003,
      "reward": 2.084437370300293,
      "reward_std": 0.008145329542458057,
      "rewards/accuracy_reward": 0.8844374418258667,
      "rewards/format_reward": 1.0,
      "step": 2009
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.0,
      "completion_length": 393.0,
      "epoch": 0.02772375553440642,
      "grad_norm": 2.672495920194106,
      "kl": 0.08154296875,
      "learning_rate": 9.981047377292839e-07,
      "loss": 0.0033,
      "reward": 2.0176563262939453,
      "reward_std": 0.01224865484982729,
      "rewards/accuracy_reward": 0.8176562786102295,
      "rewards/format_reward": 1.0,
      "step": 2010
    },
    {
      "all_correct": 1.0,
      "all_wrong": 0.0,
      "completion_length": 386.78125,
      "epoch": 0.02773754844760762,
      "grad_norm": 2.4021085534516007,
      "kl": 0.0869140625,
      "learning_rate": 9.981028526208362e-07,
      "loss": 0.0035,
      "reward": 2.1004064083099365,
      "reward_std": 0.029316674917936325,
      "rewards/accuracy_reward": 0.9066562652587891,
      "rewards/format_reward": 1.0,
      "step": 2011
    },
    {
      "all_correct": 0.75,
      "all_wrong": 0.0,
      "completion_length": 384.6875,
      "epoch": 0.027751341360808816,
      "grad_norm": 2.8153433546616915,
      "kl": 0.07958984375,
      "learning_rate": 9.981009665771318e-07,
      "loss": 0.0032,
      "reward": 2.1179685592651367,
      "reward_std": 0.011852141469717026,
      "rewards/accuracy_reward": 0.9179688096046448,
      "rewards/format_reward": 1.0,
      "step": 2012
    },
    {
      "all_correct": 0.75,
      "all_wrong": 0.0,
      "completion_length": 384.5,
      "epoch": 0.027765134274010013,
      "grad_norm": 3.044222433287558,
      "kl": 0.0869140625,
      "learning_rate": 9.980990795981744e-07,
      "loss": 0.0035,
      "reward": 2.079031467437744,
      "reward_std": 0.014792138710618019,
      "rewards/accuracy_reward": 0.879031240940094,
      "rewards/format_reward": 1.0,
      "step": 2013
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.0,
      "completion_length": 372.15625,
      "epoch": 0.02777892718721121,
      "grad_norm": 2.981786770186084,
      "kl": 0.0751953125,
      "learning_rate": 9.980971916839676e-07,
      "loss": 0.003,
      "reward": 1.968656301498413,
      "reward_std": 0.027573253959417343,
      "rewards/accuracy_reward": 0.7811562418937683,
      "rewards/format_reward": 1.0,
      "step": 2014
    },
    {
      "all_correct": 0.75,
      "all_wrong": 0.0,
      "completion_length": 386.0,
      "epoch": 0.027792720100412407,
      "grad_norm": 5.659418526181548,
      "kl": 0.08837890625,
      "learning_rate": 9.980953028345148e-07,
      "loss": 0.0035,
      "reward": 2.138031244277954,
      "reward_std": 0.03208222612738609,
      "rewards/accuracy_reward": 0.944281280040741,
      "rewards/format_reward": 1.0,
      "step": 2015
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.0,
      "completion_length": 397.0625,
      "epoch": 0.027806513013613605,
      "grad_norm": 2.414807506931623,
      "kl": 0.07373046875,
      "learning_rate": 9.980934130498195e-07,
      "loss": 0.003,
      "reward": 2.043093681335449,
      "reward_std": 0.010804702527821064,
      "rewards/accuracy_reward": 0.843093752861023,
      "rewards/format_reward": 1.0,
      "step": 2016
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.0,
      "completion_length": 399.625,
      "epoch": 0.027820305926814802,
      "grad_norm": 30.444039451052753,
      "kl": 0.0830078125,
      "learning_rate": 9.980915223298854e-07,
      "loss": 0.0033,
      "reward": 2.060999870300293,
      "reward_std": 0.02490059658885002,
      "rewards/accuracy_reward": 0.8610000014305115,
      "rewards/format_reward": 1.0,
      "step": 2017
    },
    {
      "all_correct": 1.0,
      "all_wrong": 0.0,
      "completion_length": 400.25,
      "epoch": 0.027834098840016,
      "grad_norm": 3.5985905327780716,
      "kl": 0.09033203125,
      "learning_rate": 9.980896306747158e-07,
      "loss": 0.0036,
      "reward": 2.0984063148498535,
      "reward_std": 0.019991839304566383,
      "rewards/accuracy_reward": 0.8984062671661377,
      "rewards/format_reward": 1.0,
      "step": 2018
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.0,
      "completion_length": 383.03125,
      "epoch": 0.027847891753217197,
      "grad_norm": 4.476733650490753,
      "kl": 0.1015625,
      "learning_rate": 9.980877380843145e-07,
      "loss": 0.0041,
      "reward": 1.99609375,
      "reward_std": 0.02948116697371006,
      "rewards/accuracy_reward": 0.8023437261581421,
      "rewards/format_reward": 1.0,
      "step": 2019
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.0,
      "completion_length": 380.84375,
      "epoch": 0.027861684666418394,
      "grad_norm": 2.568336154292667,
      "kl": 0.08740234375,
      "learning_rate": 9.98085844558685e-07,
      "loss": 0.0035,
      "reward": 2.0034687519073486,
      "reward_std": 0.011369307525455952,
      "rewards/accuracy_reward": 0.8034687638282776,
      "rewards/format_reward": 1.0,
      "step": 2020
    },
    {
      "all_correct": 0.25,
      "all_wrong": 0.0,
      "completion_length": 383.9375,
      "epoch": 0.02787547757961959,
      "grad_norm": 2.5557683115881105,
      "kl": 0.0732421875,
      "learning_rate": 9.98083950097831e-07,
      "loss": 0.0029,
      "reward": 2.0200624465942383,
      "reward_std": 0.04915841668844223,
      "rewards/accuracy_reward": 0.8325625061988831,
      "rewards/format_reward": 1.0,
      "step": 2021
    },
    {
      "all_correct": 0.75,
      "all_wrong": 0.0,
      "completion_length": 388.40625,
      "epoch": 0.02788927049282079,
      "grad_norm": 15.391262802454044,
      "kl": 0.1025390625,
      "learning_rate": 9.980820547017557e-07,
      "loss": 0.0041,
      "reward": 2.0832810401916504,
      "reward_std": 0.014530522748827934,
      "rewards/accuracy_reward": 0.8832812309265137,
      "rewards/format_reward": 1.0,
      "step": 2022
    },
    {
      "all_correct": 0.75,
      "all_wrong": 0.0,
      "completion_length": 410.40625,
      "epoch": 0.027903063406021986,
      "grad_norm": 3.5155203681260545,
      "kl": 0.09326171875,
      "learning_rate": 9.98080158370463e-07,
      "loss": 0.0037,
      "reward": 2.1206250190734863,
      "reward_std": 0.033267080783843994,
      "rewards/accuracy_reward": 0.9268750548362732,
      "rewards/format_reward": 1.0,
      "step": 2023
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.0,
      "completion_length": 386.1875,
      "epoch": 0.027916856319223183,
      "grad_norm": 2.002417237529394,
      "kl": 0.09375,
      "learning_rate": 9.980782611039562e-07,
      "loss": 0.0038,
      "reward": 1.9477499723434448,
      "reward_std": 0.009035258553922176,
      "rewards/accuracy_reward": 0.7477500438690186,
      "rewards/format_reward": 1.0,
      "step": 2024
    },
    {
      "all_correct": 0.75,
      "all_wrong": 0.0,
      "completion_length": 402.84375,
      "epoch": 0.02793064923242438,
      "grad_norm": 2.283592767109554,
      "kl": 0.0849609375,
      "learning_rate": 9.98076362902239e-07,
      "loss": 0.0034,
      "reward": 2.0442469120025635,
      "reward_std": 0.004505848977714777,
      "rewards/accuracy_reward": 0.8442468047142029,
      "rewards/format_reward": 1.0,
      "step": 2025
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.0,
      "completion_length": 396.78125,
      "epoch": 0.027944442145625577,
      "grad_norm": 2.9378510321527544,
      "kl": 0.08984375,
      "learning_rate": 9.980744637653148e-07,
      "loss": 0.0036,
      "reward": 2.0288126468658447,
      "reward_std": 0.018277857452630997,
      "rewards/accuracy_reward": 0.8288124799728394,
      "rewards/format_reward": 1.0,
      "step": 2026
    },
    {
      "all_correct": 0.75,
      "all_wrong": 0.0,
      "completion_length": 419.25,
      "epoch": 0.027958235058826775,
      "grad_norm": 2.3118866496318957,
      "kl": 0.08251953125,
      "learning_rate": 9.980725636931875e-07,
      "loss": 0.0033,
      "reward": 2.118375062942505,
      "reward_std": 0.027417782694101334,
      "rewards/accuracy_reward": 0.924625039100647,
      "rewards/format_reward": 1.0,
      "step": 2027
    },
    {
      "all_correct": 0.75,
      "all_wrong": 0.0,
      "completion_length": 414.8125,
      "epoch": 0.027972027972027972,
      "grad_norm": 2.0557021536390807,
      "kl": 0.0869140625,
      "learning_rate": 9.980706626858607e-07,
      "loss": 0.0035,
      "reward": 2.1043436527252197,
      "reward_std": 0.0201911348849535,
      "rewards/accuracy_reward": 0.9105937480926514,
      "rewards/format_reward": 1.0,
      "step": 2028
    },
    {
      "all_correct": 0.75,
      "all_wrong": 0.0,
      "completion_length": 411.84375,
      "epoch": 0.02798582088522917,
      "grad_norm": 2.411652807128667,
      "kl": 0.09033203125,
      "learning_rate": 9.980687607433373e-07,
      "loss": 0.0036,
      "reward": 2.1010470390319824,
      "reward_std": 0.03239306062459946,
      "rewards/accuracy_reward": 0.9072968363761902,
      "rewards/format_reward": 1.0,
      "step": 2029
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.0,
      "completion_length": 408.25,
      "epoch": 0.027999613798430367,
      "grad_norm": 3.368887657065975,
      "kl": 0.0830078125,
      "learning_rate": 9.980668578656215e-07,
      "loss": 0.0033,
      "reward": 2.017500162124634,
      "reward_std": 0.01959807053208351,
      "rewards/accuracy_reward": 0.8174999952316284,
      "rewards/format_reward": 1.0,
      "step": 2030
    },
    {
      "all_correct": 0.75,
      "all_wrong": 0.0,
      "completion_length": 412.28125,
      "epoch": 0.028013406711631564,
      "grad_norm": 2.336123805715452,
      "kl": 0.08203125,
      "learning_rate": 9.980649540527165e-07,
      "loss": 0.0033,
      "reward": 2.129593849182129,
      "reward_std": 0.015878131613135338,
      "rewards/accuracy_reward": 0.9295936822891235,
      "rewards/format_reward": 1.0,
      "step": 2031
    },
    {
      "all_correct": 0.75,
      "all_wrong": 0.0,
      "completion_length": 405.6875,
      "epoch": 0.02802719962483276,
      "grad_norm": 3.1886311497815454,
      "kl": 0.0908203125,
      "learning_rate": 9.980630493046264e-07,
      "loss": 0.0036,
      "reward": 2.1080312728881836,
      "reward_std": 0.017673006281256676,
      "rewards/accuracy_reward": 0.9080312252044678,
      "rewards/format_reward": 1.0,
      "step": 2032
    },
    {
      "all_correct": 0.75,
      "all_wrong": 0.0,
      "completion_length": 405.4375,
      "epoch": 0.02804099253803396,
      "grad_norm": 2.9214863905656006,
      "kl": 0.0830078125,
      "learning_rate": 9.980611436213544e-07,
      "loss": 0.0033,
      "reward": 2.0946249961853027,
      "reward_std": 0.018046777695417404,
      "rewards/accuracy_reward": 0.8946249485015869,
      "rewards/format_reward": 1.0,
      "step": 2033
    },
    {
      "all_correct": 1.0,
      "all_wrong": 0.0,
      "completion_length": 404.25,
      "epoch": 0.028054785451235156,
      "grad_norm": 5.238866070088939,
      "kl": 0.08349609375,
      "learning_rate": 9.98059237002904e-07,
      "loss": 0.0033,
      "reward": 2.138718843460083,
      "reward_std": 0.017147937789559364,
      "rewards/accuracy_reward": 0.9387186765670776,
      "rewards/format_reward": 1.0,
      "step": 2034
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.0,
      "completion_length": 412.53125,
      "epoch": 0.028068578364436353,
      "grad_norm": 3.306845612252958,
      "kl": 0.0908203125,
      "learning_rate": 9.980573294492787e-07,
      "loss": 0.0036,
      "reward": 1.9710625410079956,
      "reward_std": 0.03476882725954056,
      "rewards/accuracy_reward": 0.7773123979568481,
      "rewards/format_reward": 1.0,
      "step": 2035
    },
    {
      "all_correct": 0.75,
      "all_wrong": 0.0,
      "completion_length": 410.9375,
      "epoch": 0.02808237127763755,
      "grad_norm": 2.9547635161751504,
      "kl": 0.08837890625,
      "learning_rate": 9.980554209604825e-07,
      "loss": 0.0035,
      "reward": 2.027468681335449,
      "reward_std": 0.012101997621357441,
      "rewards/accuracy_reward": 0.8274686932563782,
      "rewards/format_reward": 1.0,
      "step": 2036
    },
    {
      "all_correct": 0.75,
      "all_wrong": 0.0,
      "completion_length": 414.0625,
      "epoch": 0.028096164190838747,
      "grad_norm": 7.854176775858453,
      "kl": 0.0859375,
      "learning_rate": 9.980535115365188e-07,
      "loss": 0.0034,
      "reward": 2.114281177520752,
      "reward_std": 0.009043807163834572,
      "rewards/accuracy_reward": 0.9142812490463257,
      "rewards/format_reward": 1.0,
      "step": 2037
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.0,
      "completion_length": 406.6875,
      "epoch": 0.028109957104039945,
      "grad_norm": 2.904379586832252,
      "kl": 0.1025390625,
      "learning_rate": 9.98051601177391e-07,
      "loss": 0.0041,
      "reward": 2.0442187786102295,
      "reward_std": 0.020171722397208214,
      "rewards/accuracy_reward": 0.8442187309265137,
      "rewards/format_reward": 1.0,
      "step": 2038
    },
    {
      "all_correct": 0.75,
      "all_wrong": 0.0,
      "completion_length": 409.21875,
      "epoch": 0.028123750017241142,
      "grad_norm": 2.8714500229049826,
      "kl": 0.09375,
      "learning_rate": 9.98049689883103e-07,
      "loss": 0.0037,
      "reward": 2.097871780395508,
      "reward_std": 0.02635156363248825,
      "rewards/accuracy_reward": 0.8978718519210815,
      "rewards/format_reward": 1.0,
      "step": 2039
    },
    {
      "all_correct": 1.0,
      "all_wrong": 0.0,
      "completion_length": 407.625,
      "epoch": 0.02813754293044234,
      "grad_norm": 2.2630764513596566,
      "kl": 0.08740234375,
      "learning_rate": 9.98047777653658e-07,
      "loss": 0.0035,
      "reward": 2.1635000705718994,
      "reward_std": 0.01236058585345745,
      "rewards/accuracy_reward": 0.9635000228881836,
      "rewards/format_reward": 1.0,
      "step": 2040
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.0,
      "completion_length": 403.96875,
      "epoch": 0.028151335843643537,
      "grad_norm": 3.0834774585446327,
      "kl": 0.0791015625,
      "learning_rate": 9.980458644890598e-07,
      "loss": 0.0032,
      "reward": 2.052968978881836,
      "reward_std": 0.008962081745266914,
      "rewards/accuracy_reward": 0.8529687523841858,
      "rewards/format_reward": 1.0,
      "step": 2041
    },
    {
      "all_correct": 0.75,
      "all_wrong": 0.0,
      "completion_length": 391.25,
      "epoch": 0.028165128756844734,
      "grad_norm": 2.5839638634275297,
      "kl": 0.08935546875,
      "learning_rate": 9.980439503893124e-07,
      "loss": 0.0036,
      "reward": 2.104062557220459,
      "reward_std": 0.017595740035176277,
      "rewards/accuracy_reward": 0.9040625691413879,
      "rewards/format_reward": 1.0,
      "step": 2042
    },
    {
      "all_correct": 1.0,
      "all_wrong": 0.0,
      "completion_length": 398.84375,
      "epoch": 0.02817892167004593,
      "grad_norm": 2.783328861502429,
      "kl": 0.08984375,
      "learning_rate": 9.980420353544186e-07,
      "loss": 0.0036,
      "reward": 2.1425342559814453,
      "reward_std": 0.011194610968232155,
      "rewards/accuracy_reward": 0.942534327507019,
      "rewards/format_reward": 1.0,
      "step": 2043
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.0,
      "completion_length": 400.90625,
      "epoch": 0.02819271458324713,
      "grad_norm": 2.971659369320894,
      "kl": 0.0859375,
      "learning_rate": 9.980401193843827e-07,
      "loss": 0.0034,
      "reward": 2.002406120300293,
      "reward_std": 0.03162484988570213,
      "rewards/accuracy_reward": 0.8024062514305115,
      "rewards/format_reward": 1.0,
      "step": 2044
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.0,
      "completion_length": 396.5,
      "epoch": 0.028206507496448326,
      "grad_norm": 12.679050087466655,
      "kl": 0.0791015625,
      "learning_rate": 9.980382024792077e-07,
      "loss": 0.0032,
      "reward": 2.062312602996826,
      "reward_std": 0.020395871251821518,
      "rewards/accuracy_reward": 0.8623125553131104,
      "rewards/format_reward": 1.0,
      "step": 2045
    },
    {
      "all_correct": 0.25,
      "all_wrong": 0.0,
      "completion_length": 375.34375,
      "epoch": 0.028220300409649523,
      "grad_norm": 2.196318607577958,
      "kl": 0.080078125,
      "learning_rate": 9.980362846388976e-07,
      "loss": 0.0032,
      "reward": 1.978562593460083,
      "reward_std": 0.02489536441862583,
      "rewards/accuracy_reward": 0.7848124504089355,
      "rewards/format_reward": 1.0,
      "step": 2046
    },
    {
      "all_correct": 0.75,
      "all_wrong": 0.0,
      "completion_length": 392.1875,
      "epoch": 0.02823409332285072,
      "grad_norm": 1.9361530369501339,
      "kl": 0.0859375,
      "learning_rate": 9.98034365863456e-07,
      "loss": 0.0034,
      "reward": 2.115906238555908,
      "reward_std": 0.01409249659627676,
      "rewards/accuracy_reward": 0.9159062504768372,
      "rewards/format_reward": 1.0,
      "step": 2047
    },
    {
      "all_correct": 0.75,
      "all_wrong": 0.0,
      "completion_length": 388.0625,
      "epoch": 0.028247886236051917,
      "grad_norm": 2.6855138861331804,
      "kl": 0.08642578125,
      "learning_rate": 9.980324461528865e-07,
      "loss": 0.0035,
      "reward": 2.106250047683716,
      "reward_std": 0.014943841844797134,
      "rewards/accuracy_reward": 0.9062499403953552,
      "rewards/format_reward": 1.0,
      "step": 2048
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.0,
      "completion_length": 394.6875,
      "epoch": 0.028261679149253115,
      "grad_norm": 6.594156869797373,
      "kl": 0.083984375,
      "learning_rate": 9.980305255071922e-07,
      "loss": 0.0034,
      "reward": 2.0450313091278076,
      "reward_std": 0.020993392914533615,
      "rewards/accuracy_reward": 0.845031201839447,
      "rewards/format_reward": 1.0,
      "step": 2049
    },
    {
      "all_correct": 0.0,
      "all_wrong": 0.0,
      "completion_length": 388.65625,
      "epoch": 0.028275472062454312,
      "grad_norm": 2.654019550042582,
      "kl": 0.08984375,
      "learning_rate": 9.980286039263774e-07,
      "loss": 0.0036,
      "reward": 2.011906147003174,
      "reward_std": 0.028995629400014877,
      "rewards/accuracy_reward": 0.8181562423706055,
      "rewards/format_reward": 1.0,
      "step": 2050
    },
    {
      "all_correct": 1.0,
      "all_wrong": 0.0,
      "completion_length": 394.34375,
      "epoch": 0.02828926497565551,
      "grad_norm": 2.5163281369855546,
      "kl": 0.0712890625,
      "learning_rate": 9.980266814104454e-07,
      "loss": 0.0028,
      "reward": 2.113687515258789,
      "reward_std": 0.009443430230021477,
      "rewards/accuracy_reward": 0.9136874675750732,
      "rewards/format_reward": 1.0,
      "step": 2051
    },
    {
      "all_correct": 1.0,
      "all_wrong": 0.0,
      "completion_length": 386.75,
      "epoch": 0.028303057888856707,
      "grad_norm": 2.9121186143889,
      "kl": 0.0810546875,
      "learning_rate": 9.980247579593996e-07,
      "loss": 0.0032,
      "reward": 2.0890936851501465,
      "reward_std": 0.015981599688529968,
      "rewards/accuracy_reward": 0.8890937566757202,
      "rewards/format_reward": 1.0,
      "step": 2052
    },
    {
      "all_correct": 1.0,
      "all_wrong": 0.0,
      "completion_length": 390.03125,
      "epoch": 0.028316850802057904,
      "grad_norm": 2.1455831615776297,
      "kl": 0.080078125,
      "learning_rate": 9.98022833573244e-07,
      "loss": 0.0032,
      "reward": 2.1273436546325684,
      "reward_std": 0.013971472159028053,
      "rewards/accuracy_reward": 0.9273437261581421,
      "rewards/format_reward": 1.0,
      "step": 2053
    },
    {
      "all_correct": 0.75,
      "all_wrong": 0.0,
      "completion_length": 382.90625,
      "epoch": 0.0283306437152591,
      "grad_norm": 2.1309348958758783,
      "kl": 0.076171875,
      "learning_rate": 9.980209082519822e-07,
      "loss": 0.003,
      "reward": 2.1307501792907715,
      "reward_std": 0.02510671317577362,
      "rewards/accuracy_reward": 0.9369999170303345,
      "rewards/format_reward": 1.0,
      "step": 2054
    },
    {
      "all_correct": 1.0,
      "all_wrong": 0.0,
      "completion_length": 403.875,
      "epoch": 0.0283444366284603,
      "grad_norm": 2.789125978101275,
      "kl": 0.076171875,
      "learning_rate": 9.980189819956175e-07,
      "loss": 0.003,
      "reward": 2.135593891143799,
      "reward_std": 0.008521700277924538,
      "rewards/accuracy_reward": 0.9355937242507935,
      "rewards/format_reward": 1.0,
      "step": 2055
    },
    {
      "all_correct": 0.75,
      "all_wrong": 0.0,
      "completion_length": 402.1875,
      "epoch": 0.028358229541661496,
      "grad_norm": 2.4557818433047824,
      "kl": 0.0771484375,
      "learning_rate": 9.980170548041536e-07,
      "loss": 0.0031,
      "reward": 2.1533126831054688,
      "reward_std": 0.029019678011536598,
      "rewards/accuracy_reward": 0.9595625400543213,
      "rewards/format_reward": 1.0,
      "step": 2056
    },
    {
      "all_correct": 1.0,
      "all_wrong": 0.0,
      "completion_length": 385.375,
      "epoch": 0.028372022454862693,
      "grad_norm": 5.458354526153296,
      "kl": 0.078125,
      "learning_rate": 9.980151266775942e-07,
      "loss": 0.0031,
      "reward": 2.0703749656677246,
      "reward_std": 0.020792512223124504,
      "rewards/accuracy_reward": 0.8703750371932983,
      "rewards/format_reward": 1.0,
      "step": 2057
    },
    {
      "all_correct": 1.0,
      "all_wrong": 0.0,
      "completion_length": 413.5625,
      "epoch": 0.02838581536806389,
      "grad_norm": 2.1994200102764365,
      "kl": 0.083984375,
      "learning_rate": 9.980131976159432e-07,
      "loss": 0.0034,
      "reward": 2.159250259399414,
      "reward_std": 0.009845316410064697,
      "rewards/accuracy_reward": 0.9592499732971191,
      "rewards/format_reward": 1.0,
      "step": 2058
    },
    {
      "all_correct": 0.75,
      "all_wrong": 0.0,
      "completion_length": 388.03125,
      "epoch": 0.028399608281265087,
      "grad_norm": 6.677962248902495,
      "kl": 0.0791015625,
      "learning_rate": 9.980112676192037e-07,
      "loss": 0.0032,
      "reward": 1.9943437576293945,
      "reward_std": 0.018568377941846848,
      "rewards/accuracy_reward": 0.7943437695503235,
      "rewards/format_reward": 1.0,
      "step": 2059
    },
    {
      "all_correct": 0.75,
      "all_wrong": 0.0,
      "completion_length": 391.75,
      "epoch": 0.028413401194466285,
      "grad_norm": 3.6875644046326532,
      "kl": 0.083984375,
      "learning_rate": 9.980093366873797e-07,
      "loss": 0.0034,
      "reward": 2.0176563262939453,
      "reward_std": 0.018136974424123764,
      "rewards/accuracy_reward": 0.8176563382148743,
      "rewards/format_reward": 1.0,
      "step": 2060
    },
    {
      "all_correct": 0.75,
      "all_wrong": 0.0,
      "completion_length": 407.6875,
      "epoch": 0.028427194107667482,
      "grad_norm": 2.7034239656725623,
      "kl": 0.07861328125,
      "learning_rate": 9.980074048204744e-07,
      "loss": 0.0031,
      "reward": 2.0900626182556152,
      "reward_std": 0.009769640862941742,
      "rewards/accuracy_reward": 0.8900624513626099,
      "rewards/format_reward": 1.0,
      "step": 2061
    },
    {
      "all_correct": 1.0,
      "all_wrong": 0.0,
      "completion_length": 410.6875,
      "epoch": 0.02844098702086868,
      "grad_norm": 3.2053751316199164,
      "kl": 0.076171875,
      "learning_rate": 9.98005472018492e-07,
      "loss": 0.0031,
      "reward": 2.142218589782715,
      "reward_std": 0.01818351447582245,
      "rewards/accuracy_reward": 0.9422187805175781,
      "rewards/format_reward": 1.0,
      "step": 2062
    },
    {
      "all_correct": 0.75,
      "all_wrong": 0.0,
      "completion_length": 402.15625,
      "epoch": 0.028454779934069876,
      "grad_norm": 12.744656982507609,
      "kl": 0.08203125,
      "learning_rate": 9.980035382814357e-07,
      "loss": 0.0033,
      "reward": 2.081843852996826,
      "reward_std": 0.01705320179462433,
      "rewards/accuracy_reward": 0.8818437457084656,
      "rewards/format_reward": 1.0,
      "step": 2063
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.0,
      "completion_length": 405.46875,
      "epoch": 0.028468572847271074,
      "grad_norm": 2.4460673091208354,
      "kl": 0.06982421875,
      "learning_rate": 9.980016036093093e-07,
      "loss": 0.0028,
      "reward": 2.0595312118530273,
      "reward_std": 0.012723948806524277,
      "rewards/accuracy_reward": 0.8595312237739563,
      "rewards/format_reward": 1.0,
      "step": 2064
    },
    {
      "all_correct": 1.0,
      "all_wrong": 0.0,
      "completion_length": 413.5,
      "epoch": 0.02848236576047227,
      "grad_norm": 10.690303999779175,
      "kl": 0.08203125,
      "learning_rate": 9.979996680021166e-07,
      "loss": 0.0033,
      "reward": 2.1090002059936523,
      "reward_std": 0.02731136605143547,
      "rewards/accuracy_reward": 0.909000039100647,
      "rewards/format_reward": 1.0,
      "step": 2065
    },
    {
      "all_correct": 0.75,
      "all_wrong": 0.0,
      "completion_length": 415.5,
      "epoch": 0.02849615867367347,
      "grad_norm": 2.263414737450947,
      "kl": 0.07470703125,
      "learning_rate": 9.97997731459861e-07,
      "loss": 0.003,
      "reward": 2.0491220951080322,
      "reward_std": 0.011150998994708061,
      "rewards/accuracy_reward": 0.8491218090057373,
      "rewards/format_reward": 1.0,
      "step": 2066
    },
    {
      "all_correct": 0.75,
      "all_wrong": 0.0,
      "completion_length": 410.65625,
      "epoch": 0.028509951586874662,
      "grad_norm": 2.108701215577669,
      "kl": 0.072265625,
      "learning_rate": 9.97995793982546e-07,
      "loss": 0.0029,
      "reward": 2.09770131111145,
      "reward_std": 0.008197976276278496,
      "rewards/accuracy_reward": 0.8977012634277344,
      "rewards/format_reward": 1.0,
      "step": 2067
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.0,
      "completion_length": 418.25,
      "epoch": 0.02852374450007586,
      "grad_norm": 3.4433795464372032,
      "kl": 0.0751953125,
      "learning_rate": 9.979938555701754e-07,
      "loss": 0.003,
      "reward": 2.0000624656677246,
      "reward_std": 0.013488207012414932,
      "rewards/accuracy_reward": 0.8000625371932983,
      "rewards/format_reward": 1.0,
      "step": 2068
    },
    {
      "all_correct": 1.0,
      "all_wrong": 0.0,
      "completion_length": 406.375,
      "epoch": 0.028537537413277057,
      "grad_norm": 5.161791238612761,
      "kl": 0.08203125,
      "learning_rate": 9.97991916222753e-07,
      "loss": 0.0033,
      "reward": 2.088531255722046,
      "reward_std": 0.013438455760478973,
      "rewards/accuracy_reward": 0.8885312080383301,
      "rewards/format_reward": 1.0,
      "step": 2069
    },
    {
      "all_correct": 1.0,
      "all_wrong": 0.0,
      "completion_length": 408.0625,
      "epoch": 0.028551330326478254,
      "grad_norm": 3.4610384000208443,
      "kl": 0.0751953125,
      "learning_rate": 9.979899759402823e-07,
      "loss": 0.003,
      "reward": 2.1161248683929443,
      "reward_std": 0.033605195581912994,
      "rewards/accuracy_reward": 0.9161250591278076,
      "rewards/format_reward": 1.0,
      "step": 2070
    },
    {
      "all_correct": 1.0,
      "all_wrong": 0.0,
      "completion_length": 412.1875,
      "epoch": 0.02856512323967945,
      "grad_norm": 4.921646812201996,
      "kl": 0.080078125,
      "learning_rate": 9.979880347227669e-07,
      "loss": 0.0032,
      "reward": 2.1761562824249268,
      "reward_std": 0.011000405065715313,
      "rewards/accuracy_reward": 0.9761562943458557,
      "rewards/format_reward": 1.0,
      "step": 2071
    },
    {
      "all_correct": 0.75,
      "all_wrong": 0.0,
      "completion_length": 408.9375,
      "epoch": 0.02857891615288065,
      "grad_norm": 7.141057473858071,
      "kl": 0.0771484375,
      "learning_rate": 9.979860925702105e-07,
      "loss": 0.0031,
      "reward": 2.113156318664551,
      "reward_std": 0.010698425583541393,
      "rewards/accuracy_reward": 0.913156270980835,
      "rewards/format_reward": 1.0,
      "step": 2072
    },
    {
      "all_correct": 0.75,
      "all_wrong": 0.0,
      "completion_length": 405.15625,
      "epoch": 0.028592709066081846,
      "grad_norm": 2.7903819001852237,
      "kl": 0.087890625,
      "learning_rate": 9.979841494826167e-07,
      "loss": 0.0035,
      "reward": 2.1317501068115234,
      "reward_std": 0.0135076018050313,
      "rewards/accuracy_reward": 0.9317499995231628,
      "rewards/format_reward": 1.0,
      "step": 2073
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.0,
      "completion_length": 409.40625,
      "epoch": 0.028606501979283043,
      "grad_norm": 2.0915499397023014,
      "kl": 0.080078125,
      "learning_rate": 9.979822054599894e-07,
      "loss": 0.0032,
      "reward": 2.0935935974121094,
      "reward_std": 0.024439077824354172,
      "rewards/accuracy_reward": 0.8998437523841858,
      "rewards/format_reward": 1.0,
      "step": 2074
    },
    {
      "all_correct": 1.0,
      "all_wrong": 0.0,
      "completion_length": 415.84375,
      "epoch": 0.02862029489248424,
      "grad_norm": 4.254950816370984,
      "kl": 0.08203125,
      "learning_rate": 9.979802605023318e-07,
      "loss": 0.0033,
      "reward": 2.1291561126708984,
      "reward_std": 0.01947108283638954,
      "rewards/accuracy_reward": 0.9291563034057617,
      "rewards/format_reward": 1.0,
      "step": 2075
    },
    {
      "all_correct": 0.25,
      "all_wrong": 0.0,
      "completion_length": 403.125,
      "epoch": 0.028634087805685438,
      "grad_norm": 3.9531415207398846,
      "kl": 0.08056640625,
      "learning_rate": 9.979783146096479e-07,
      "loss": 0.0032,
      "reward": 1.9294064044952393,
      "reward_std": 0.017338544130325317,
      "rewards/accuracy_reward": 0.7294062972068787,
      "rewards/format_reward": 1.0,
      "step": 2076
    },
    {
      "all_correct": 0.75,
      "all_wrong": 0.0,
      "completion_length": 402.90625,
      "epoch": 0.028647880718886635,
      "grad_norm": 6.919585654920173,
      "kl": 0.07421875,
      "learning_rate": 9.97976367781941e-07,
      "loss": 0.003,
      "reward": 2.1209375858306885,
      "reward_std": 0.024540863931179047,
      "rewards/accuracy_reward": 0.9209375381469727,
      "rewards/format_reward": 1.0,
      "step": 2077
    },
    {
      "all_correct": 0.75,
      "all_wrong": 0.0,
      "completion_length": 407.34375,
      "epoch": 0.028661673632087832,
      "grad_norm": 5.765836660587872,
      "kl": 0.07568359375,
      "learning_rate": 9.979744200192153e-07,
      "loss": 0.003,
      "reward": 2.125645875930786,
      "reward_std": 0.029877355322241783,
      "rewards/accuracy_reward": 0.9318958520889282,
      "rewards/format_reward": 1.0,
      "step": 2078
    },
    {
      "all_correct": 0.75,
      "all_wrong": 0.0,
      "completion_length": 406.78125,
      "epoch": 0.02867546654528903,
      "grad_norm": 4.29473995907193,
      "kl": 0.07861328125,
      "learning_rate": 9.97972471321474e-07,
      "loss": 0.0031,
      "reward": 2.1382498741149902,
      "reward_std": 0.028349842876195908,
      "rewards/accuracy_reward": 0.9444999694824219,
      "rewards/format_reward": 1.0,
      "step": 2079
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.0,
      "completion_length": 400.75,
      "epoch": 0.028689259458490227,
      "grad_norm": 13.77050613624554,
      "kl": 0.0791015625,
      "learning_rate": 9.97970521688721e-07,
      "loss": 0.0032,
      "reward": 2.0674374103546143,
      "reward_std": 0.04495127499103546,
      "rewards/accuracy_reward": 0.8736875057220459,
      "rewards/format_reward": 1.0,
      "step": 2080
    },
    {
      "all_correct": 0.75,
      "all_wrong": 0.0,
      "completion_length": 418.21875,
      "epoch": 0.028703052371691424,
      "grad_norm": 1.9361973581944902,
      "kl": 0.083984375,
      "learning_rate": 9.979685711209597e-07,
      "loss": 0.0034,
      "reward": 2.1226563453674316,
      "reward_std": 0.024589134380221367,
      "rewards/accuracy_reward": 0.9289063215255737,
      "rewards/format_reward": 1.0,
      "step": 2081
    },
    {
      "all_correct": 1.0,
      "all_wrong": 0.0,
      "completion_length": 415.96875,
      "epoch": 0.02871684528489262,
      "grad_norm": 2.599464014084937,
      "kl": 0.0693359375,
      "learning_rate": 9.97966619618194e-07,
      "loss": 0.0028,
      "reward": 2.1723437309265137,
      "reward_std": 0.02695685625076294,
      "rewards/accuracy_reward": 0.9785937070846558,
      "rewards/format_reward": 1.0,
      "step": 2082
    },
    {
      "all_correct": 1.0,
      "all_wrong": 0.0,
      "completion_length": 414.0,
      "epoch": 0.02873063819809382,
      "grad_norm": 1.569643836200425,
      "kl": 0.07958984375,
      "learning_rate": 9.979646671804276e-07,
      "loss": 0.0032,
      "reward": 2.1110312938690186,
      "reward_std": 0.007149267941713333,
      "rewards/accuracy_reward": 0.9110312461853027,
      "rewards/format_reward": 1.0,
      "step": 2083
    },
    {
      "all_correct": 1.0,
      "all_wrong": 0.0,
      "completion_length": 388.65625,
      "epoch": 0.028744431111295016,
      "grad_norm": 3.190030648318923,
      "kl": 0.08154296875,
      "learning_rate": 9.979627138076639e-07,
      "loss": 0.0033,
      "reward": 2.174093723297119,
      "reward_std": 0.007472606375813484,
      "rewards/accuracy_reward": 0.9740937948226929,
      "rewards/format_reward": 1.0,
      "step": 2084
    },
    {
      "all_correct": 1.0,
      "all_wrong": 0.0,
      "completion_length": 404.875,
      "epoch": 0.028758224024496213,
      "grad_norm": 3.07316520867738,
      "kl": 0.07421875,
      "learning_rate": 9.979607594999069e-07,
      "loss": 0.003,
      "reward": 2.1448750495910645,
      "reward_std": 0.018620474264025688,
      "rewards/accuracy_reward": 0.9448750019073486,
      "rewards/format_reward": 1.0,
      "step": 2085
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.0,
      "completion_length": 386.5625,
      "epoch": 0.02877201693769741,
      "grad_norm": 4.426303001381219,
      "kl": 0.07666015625,
      "learning_rate": 9.979588042571601e-07,
      "loss": 0.0031,
      "reward": 2.0162813663482666,
      "reward_std": 0.02568703331053257,
      "rewards/accuracy_reward": 0.8162811994552612,
      "rewards/format_reward": 1.0,
      "step": 2086
    },
    {
      "all_correct": 1.0,
      "all_wrong": 0.0,
      "completion_length": 401.625,
      "epoch": 0.028785809850898608,
      "grad_norm": 2.108257890474877,
      "kl": 0.0810546875,
      "learning_rate": 9.97956848079427e-07,
      "loss": 0.0032,
      "reward": 2.1298437118530273,
      "reward_std": 0.008606940507888794,
      "rewards/accuracy_reward": 0.9298437833786011,
      "rewards/format_reward": 1.0,
      "step": 2087
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.0,
      "completion_length": 375.6875,
      "epoch": 0.028799602764099805,
      "grad_norm": 3.807179077400949,
      "kl": 0.080078125,
      "learning_rate": 9.979548909667116e-07,
      "loss": 0.0032,
      "reward": 1.9619063138961792,
      "reward_std": 0.03733261674642563,
      "rewards/accuracy_reward": 0.7744062542915344,
      "rewards/format_reward": 1.0,
      "step": 2088
    },
    {
      "all_correct": 0.75,
      "all_wrong": 0.0,
      "completion_length": 391.40625,
      "epoch": 0.028813395677301002,
      "grad_norm": 2.79635918152035,
      "kl": 0.08447265625,
      "learning_rate": 9.979529329190174e-07,
      "loss": 0.0034,
      "reward": 1.9932187795639038,
      "reward_std": 0.09017042815685272,
      "rewards/accuracy_reward": 0.824468731880188,
      "rewards/format_reward": 0.96875,
      "step": 2089
    },
    {
      "all_correct": 1.0,
      "all_wrong": 0.0,
      "completion_length": 385.375,
      "epoch": 0.0288271885905022,
      "grad_norm": 3.1102944415937914,
      "kl": 0.0888671875,
      "learning_rate": 9.97950973936348e-07,
      "loss": 0.0036,
      "reward": 2.118000030517578,
      "reward_std": 0.03228549659252167,
      "rewards/accuracy_reward": 0.924250066280365,
      "rewards/format_reward": 1.0,
      "step": 2090
    },
    {
      "all_correct": 1.0,
      "all_wrong": 0.0,
      "completion_length": 399.9375,
      "epoch": 0.028840981503703397,
      "grad_norm": 4.213120767290845,
      "kl": 0.07470703125,
      "learning_rate": 9.979490140187073e-07,
      "loss": 0.003,
      "reward": 2.147218704223633,
      "reward_std": 0.02015913464128971,
      "rewards/accuracy_reward": 0.9472187161445618,
      "rewards/format_reward": 1.0,
      "step": 2091
    },
    {
      "all_correct": 1.0,
      "all_wrong": 0.0,
      "completion_length": 397.90625,
      "epoch": 0.028854774416904594,
      "grad_norm": 2.640892061219349,
      "kl": 0.0771484375,
      "learning_rate": 9.979470531660986e-07,
      "loss": 0.0031,
      "reward": 2.114687442779541,
      "reward_std": 0.017453260719776154,
      "rewards/accuracy_reward": 0.9146875143051147,
      "rewards/format_reward": 1.0,
      "step": 2092
    },
    {
      "all_correct": 0.75,
      "all_wrong": 0.0,
      "completion_length": 401.25,
      "epoch": 0.02886856733010579,
      "grad_norm": 4.1515280983760485,
      "kl": 0.0771484375,
      "learning_rate": 9.979450913785263e-07,
      "loss": 0.0031,
      "reward": 2.0978751182556152,
      "reward_std": 0.019949279725551605,
      "rewards/accuracy_reward": 0.8978749513626099,
      "rewards/format_reward": 1.0,
      "step": 2093
    },
    {
      "all_correct": 0.25,
      "all_wrong": 0.0,
      "completion_length": 400.5625,
      "epoch": 0.02888236024330699,
      "grad_norm": 4.597083957292824,
      "kl": 0.07568359375,
      "learning_rate": 9.979431286559933e-07,
      "loss": 0.003,
      "reward": 2.062375068664551,
      "reward_std": 0.029642976820468903,
      "rewards/accuracy_reward": 0.8686250448226929,
      "rewards/format_reward": 1.0,
      "step": 2094
    },
    {
      "all_correct": 1.0,
      "all_wrong": 0.0,
      "completion_length": 400.03125,
      "epoch": 0.028896153156508186,
      "grad_norm": 2.832273985170308,
      "kl": 0.09033203125,
      "learning_rate": 9.979411649985037e-07,
      "loss": 0.0036,
      "reward": 2.10518741607666,
      "reward_std": 0.013895487412810326,
      "rewards/accuracy_reward": 0.9051874279975891,
      "rewards/format_reward": 1.0,
      "step": 2095
    },
    {
      "all_correct": 0.75,
      "all_wrong": 0.0,
      "completion_length": 402.6875,
      "epoch": 0.028909946069709383,
      "grad_norm": 3.199596924447709,
      "kl": 0.07958984375,
      "learning_rate": 9.97939200406061e-07,
      "loss": 0.0032,
      "reward": 2.0587189197540283,
      "reward_std": 0.014315973967313766,
      "rewards/accuracy_reward": 0.8587186932563782,
      "rewards/format_reward": 1.0,
      "step": 2096
    },
    {
      "all_correct": 0.75,
      "all_wrong": 0.0,
      "completion_length": 405.375,
      "epoch": 0.02892373898291058,
      "grad_norm": 4.775581630970847,
      "kl": 0.08935546875,
      "learning_rate": 9.97937234878669e-07,
      "loss": 0.0036,
      "reward": 2.070718765258789,
      "reward_std": 0.02618570253252983,
      "rewards/accuracy_reward": 0.8769687414169312,
      "rewards/format_reward": 1.0,
      "step": 2097
    },
    {
      "all_correct": 1.0,
      "all_wrong": 0.0,
      "completion_length": 395.6875,
      "epoch": 0.028937531896111778,
      "grad_norm": 2.747497169736035,
      "kl": 0.0830078125,
      "learning_rate": 9.979352684163316e-07,
      "loss": 0.0033,
      "reward": 2.1251564025878906,
      "reward_std": 0.010395649820566177,
      "rewards/accuracy_reward": 0.9251562356948853,
      "rewards/format_reward": 1.0,
      "step": 2098
    },
    {
      "all_correct": 1.0,
      "all_wrong": 0.0,
      "completion_length": 393.125,
      "epoch": 0.028951324809312975,
      "grad_norm": 3.3409368244468824,
      "kl": 0.0771484375,
      "learning_rate": 9.979333010190519e-07,
      "loss": 0.0031,
      "reward": 2.117968797683716,
      "reward_std": 0.018976405262947083,
      "rewards/accuracy_reward": 0.9179686903953552,
      "rewards/format_reward": 1.0,
      "step": 2099
    },
    {
      "all_correct": 0.75,
      "all_wrong": 0.0,
      "completion_length": 389.8125,
      "epoch": 0.028965117722514172,
      "grad_norm": 2.444924369555416,
      "kl": 0.0771484375,
      "learning_rate": 9.979313326868342e-07,
      "loss": 0.0031,
      "reward": 2.0849688053131104,
      "reward_std": 0.012484787032008171,
      "rewards/accuracy_reward": 0.8849687576293945,
      "rewards/format_reward": 1.0,
      "step": 2100
    },
    {
      "all_correct": 1.0,
      "all_wrong": 0.0,
      "completion_length": 410.96875,
      "epoch": 0.02897891063571537,
      "grad_norm": 8.54544128521888,
      "kl": 0.087890625,
      "learning_rate": 9.979293634196819e-07,
      "loss": 0.0035,
      "reward": 2.1270313262939453,
      "reward_std": 0.017910931259393692,
      "rewards/accuracy_reward": 0.9270312786102295,
      "rewards/format_reward": 1.0,
      "step": 2101
    },
    {
      "all_correct": 0.25,
      "all_wrong": 0.0,
      "completion_length": 397.03125,
      "epoch": 0.028992703548916567,
      "grad_norm": 2.783408219036573,
      "kl": 0.0751953125,
      "learning_rate": 9.979273932175987e-07,
      "loss": 0.003,
      "reward": 2.011593818664551,
      "reward_std": 0.017483575269579887,
      "rewards/accuracy_reward": 0.811593770980835,
      "rewards/format_reward": 1.0,
      "step": 2102
    },
    {
      "all_correct": 0.75,
      "all_wrong": 0.0,
      "completion_length": 394.03125,
      "epoch": 0.029006496462117764,
      "grad_norm": 3.2457868839194166,
      "kl": 0.09521484375,
      "learning_rate": 9.979254220805883e-07,
      "loss": 0.0038,
      "reward": 2.0436248779296875,
      "reward_std": 0.019684679806232452,
      "rewards/accuracy_reward": 0.843625009059906,
      "rewards/format_reward": 1.0,
      "step": 2103
    },
    {
      "all_correct": 0.75,
      "all_wrong": 0.0,
      "completion_length": 399.25,
      "epoch": 0.02902028937531896,
      "grad_norm": 3.340308167709199,
      "kl": 0.076171875,
      "learning_rate": 9.979234500086547e-07,
      "loss": 0.0031,
      "reward": 2.118781328201294,
      "reward_std": 0.023527873679995537,
      "rewards/accuracy_reward": 0.9187812805175781,
      "rewards/format_reward": 1.0,
      "step": 2104
    },
    {
      "all_correct": 0.75,
      "all_wrong": 0.0,
      "completion_length": 393.78125,
      "epoch": 0.02903408228852016,
      "grad_norm": 3.1616015013518313,
      "kl": 0.08251953125,
      "learning_rate": 9.97921477001801e-07,
      "loss": 0.0033,
      "reward": 2.0796875953674316,
      "reward_std": 0.01122305728495121,
      "rewards/accuracy_reward": 0.879687488079071,
      "rewards/format_reward": 1.0,
      "step": 2105
    },
    {
      "all_correct": 1.0,
      "all_wrong": 0.0,
      "completion_length": 385.6875,
      "epoch": 0.029047875201721356,
      "grad_norm": 9.430061753508822,
      "kl": 0.08056640625,
      "learning_rate": 9.979195030600317e-07,
      "loss": 0.0032,
      "reward": 2.1826562881469727,
      "reward_std": 0.006362080108374357,
      "rewards/accuracy_reward": 0.9826562404632568,
      "rewards/format_reward": 1.0,
      "step": 2106
    },
    {
      "all_correct": 1.0,
      "all_wrong": 0.0,
      "completion_length": 393.15625,
      "epoch": 0.029061668114922553,
      "grad_norm": 2.241999609078686,
      "kl": 0.09228515625,
      "learning_rate": 9.979175281833499e-07,
      "loss": 0.0037,
      "reward": 2.097156286239624,
      "reward_std": 0.014765438623726368,
      "rewards/accuracy_reward": 0.8971562385559082,
      "rewards/format_reward": 1.0,
      "step": 2107
    },
    {
      "all_correct": 1.0,
      "all_wrong": 0.0,
      "completion_length": 390.03125,
      "epoch": 0.02907546102812375,
      "grad_norm": 4.23771388158449,
      "kl": 0.09033203125,
      "learning_rate": 9.979155523717593e-07,
      "loss": 0.0036,
      "reward": 2.1519999504089355,
      "reward_std": 0.03193982318043709,
      "rewards/accuracy_reward": 0.9582499861717224,
      "rewards/format_reward": 1.0,
      "step": 2108
    },
    {
      "all_correct": 1.0,
      "all_wrong": 0.0,
      "completion_length": 397.90625,
      "epoch": 0.029089253941324947,
      "grad_norm": 2.6605842998706204,
      "kl": 0.0849609375,
      "learning_rate": 9.979135756252639e-07,
      "loss": 0.0034,
      "reward": 2.1091251373291016,
      "reward_std": 0.008270704187452793,
      "rewards/accuracy_reward": 0.9091250896453857,
      "rewards/format_reward": 1.0,
      "step": 2109
    },
    {
      "all_correct": 1.0,
      "all_wrong": 0.0,
      "completion_length": 393.40625,
      "epoch": 0.029103046854526145,
      "grad_norm": 3.0487255267527202,
      "kl": 0.07275390625,
      "learning_rate": 9.979115979438673e-07,
      "loss": 0.0029,
      "reward": 2.1705470085144043,
      "reward_std": 0.016734443604946136,
      "rewards/accuracy_reward": 0.9705468416213989,
      "rewards/format_reward": 1.0,
      "step": 2110
    },
    {
      "all_correct": 0.75,
      "all_wrong": 0.0,
      "completion_length": 390.84375,
      "epoch": 0.029116839767727342,
      "grad_norm": 3.710469228403074,
      "kl": 0.0849609375,
      "learning_rate": 9.979096193275731e-07,
      "loss": 0.0034,
      "reward": 2.0710625648498535,
      "reward_std": 0.009986454620957375,
      "rewards/accuracy_reward": 0.8710625171661377,
      "rewards/format_reward": 1.0,
      "step": 2111
    },
    {
      "all_correct": 0.75,
      "all_wrong": 0.0,
      "completion_length": 386.96875,
      "epoch": 0.02913063268092854,
      "grad_norm": 3.9013126120312625,
      "kl": 0.080078125,
      "learning_rate": 9.979076397763852e-07,
      "loss": 0.0032,
      "reward": 2.0230000019073486,
      "reward_std": 0.03693739324808121,
      "rewards/accuracy_reward": 0.8292499780654907,
      "rewards/format_reward": 1.0,
      "step": 2112
    },
    {
      "all_correct": 1.0,
      "all_wrong": 0.0,
      "completion_length": 408.34375,
      "epoch": 0.029144425594129737,
      "grad_norm": 2.3009510655209615,
      "kl": 0.08642578125,
      "learning_rate": 9.979056592903073e-07,
      "loss": 0.0035,
      "reward": 2.1267499923706055,
      "reward_std": 0.011796379461884499,
      "rewards/accuracy_reward": 0.9267499446868896,
      "rewards/format_reward": 1.0,
      "step": 2113
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.0,
      "completion_length": 386.90625,
      "epoch": 0.029158218507330934,
      "grad_norm": 4.427301020722693,
      "kl": 0.080078125,
      "learning_rate": 9.97903677869343e-07,
      "loss": 0.0032,
      "reward": 2.052968740463257,
      "reward_std": 0.016182444989681244,
      "rewards/accuracy_reward": 0.8529687523841858,
      "rewards/format_reward": 1.0,
      "step": 2114
    },
    {
      "all_correct": 1.0,
      "all_wrong": 0.0,
      "completion_length": 398.96875,
      "epoch": 0.02917201142053213,
      "grad_norm": 5.067117029900634,
      "kl": 0.09130859375,
      "learning_rate": 9.97901695513496e-07,
      "loss": 0.0037,
      "reward": 2.1168127059936523,
      "reward_std": 0.012572855688631535,
      "rewards/accuracy_reward": 0.916812539100647,
      "rewards/format_reward": 1.0,
      "step": 2115
    },
    {
      "all_correct": 1.0,
      "all_wrong": 0.0,
      "completion_length": 400.09375,
      "epoch": 0.02918580433373333,
      "grad_norm": 2.4802782428883154,
      "kl": 0.0869140625,
      "learning_rate": 9.978997122227703e-07,
      "loss": 0.0035,
      "reward": 2.1394500732421875,
      "reward_std": 0.015019536018371582,
      "rewards/accuracy_reward": 0.9394500255584717,
      "rewards/format_reward": 1.0,
      "step": 2116
    },
    {
      "all_correct": 1.0,
      "all_wrong": 0.0,
      "completion_length": 395.71875,
      "epoch": 0.029199597246934526,
      "grad_norm": 2.027608526349447,
      "kl": 0.08203125,
      "learning_rate": 9.978977279971692e-07,
      "loss": 0.0033,
      "reward": 2.159343719482422,
      "reward_std": 0.0072292909026145935,
      "rewards/accuracy_reward": 0.9593437314033508,
      "rewards/format_reward": 1.0,
      "step": 2117
    },
    {
      "all_correct": 0.75,
      "all_wrong": 0.0,
      "completion_length": 389.4375,
      "epoch": 0.029213390160135723,
      "grad_norm": 4.56286517312335,
      "kl": 0.09033203125,
      "learning_rate": 9.97895742836697e-07,
      "loss": 0.0036,
      "reward": 2.1171875,
      "reward_std": 0.02136104926466942,
      "rewards/accuracy_reward": 0.9234374761581421,
      "rewards/format_reward": 1.0,
      "step": 2118
    },
    {
      "all_correct": 0.75,
      "all_wrong": 0.0,
      "completion_length": 394.5,
      "epoch": 0.02922718307333692,
      "grad_norm": 3.189917825822055,
      "kl": 0.09326171875,
      "learning_rate": 9.978937567413567e-07,
      "loss": 0.0037,
      "reward": 2.085218667984009,
      "reward_std": 0.014136429876089096,
      "rewards/accuracy_reward": 0.8852187395095825,
      "rewards/format_reward": 1.0,
      "step": 2119
    },
    {
      "all_correct": 0.75,
      "all_wrong": 0.0,
      "completion_length": 416.625,
      "epoch": 0.029240975986538117,
      "grad_norm": 2.415233532918492,
      "kl": 0.08349609375,
      "learning_rate": 9.978917697111527e-07,
      "loss": 0.0033,
      "reward": 2.05078125,
      "reward_std": 0.005621230695396662,
      "rewards/accuracy_reward": 0.8507812023162842,
      "rewards/format_reward": 1.0,
      "step": 2120
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.0,
      "completion_length": 408.4375,
      "epoch": 0.029254768899739315,
      "grad_norm": 4.9699034633081665,
      "kl": 0.08837890625,
      "learning_rate": 9.978897817460883e-07,
      "loss": 0.0035,
      "reward": 1.9973125457763672,
      "reward_std": 0.022114025428891182,
      "rewards/accuracy_reward": 0.7973124980926514,
      "rewards/format_reward": 1.0,
      "step": 2121
    },
    {
      "all_correct": 0.75,
      "all_wrong": 0.0,
      "completion_length": 402.625,
      "epoch": 0.029268561812940512,
      "grad_norm": 4.562417920530549,
      "kl": 0.07958984375,
      "learning_rate": 9.978877928461673e-07,
      "loss": 0.0032,
      "reward": 2.0763437747955322,
      "reward_std": 0.014324802905321121,
      "rewards/accuracy_reward": 0.8763437271118164,
      "rewards/format_reward": 1.0,
      "step": 2122
    },
    {
      "all_correct": 1.0,
      "all_wrong": 0.0,
      "completion_length": 401.78125,
      "epoch": 0.02928235472614171,
      "grad_norm": 7.44604681003263,
      "kl": 0.0859375,
      "learning_rate": 9.978858030113935e-07,
      "loss": 0.0035,
      "reward": 2.1031250953674316,
      "reward_std": 0.017918944358825684,
      "rewards/accuracy_reward": 0.9031249284744263,
      "rewards/format_reward": 1.0,
      "step": 2123
    },
    {
      "all_correct": 0.75,
      "all_wrong": 0.0,
      "completion_length": 411.8125,
      "epoch": 0.029296147639342907,
      "grad_norm": 3.179200665688222,
      "kl": 0.0888671875,
      "learning_rate": 9.978838122417707e-07,
      "loss": 0.0035,
      "reward": 2.1171250343322754,
      "reward_std": 0.008016312494874,
      "rewards/accuracy_reward": 0.9171249866485596,
      "rewards/format_reward": 1.0,
      "step": 2124
    },
    {
      "all_correct": 1.0,
      "all_wrong": 0.0,
      "completion_length": 406.625,
      "epoch": 0.029309940552544104,
      "grad_norm": 3.784362134306023,
      "kl": 0.09033203125,
      "learning_rate": 9.978818205373028e-07,
      "loss": 0.0036,
      "reward": 2.0875000953674316,
      "reward_std": 0.015809625387191772,
      "rewards/accuracy_reward": 0.8875000476837158,
      "rewards/format_reward": 1.0,
      "step": 2125
    },
    {
      "all_correct": 1.0,
      "all_wrong": 0.0,
      "completion_length": 415.28125,
      "epoch": 0.0293237334657453,
      "grad_norm": 2.538941098063826,
      "kl": 0.08642578125,
      "learning_rate": 9.97879827897993e-07,
      "loss": 0.0034,
      "reward": 2.1544687747955322,
      "reward_std": 0.01447913609445095,
      "rewards/accuracy_reward": 0.9544687867164612,
      "rewards/format_reward": 1.0,
      "step": 2126
    },
    {
      "all_correct": 1.0,
      "all_wrong": 0.0,
      "completion_length": 405.1875,
      "epoch": 0.0293375263789465,
      "grad_norm": 5.166172666915555,
      "kl": 0.0830078125,
      "learning_rate": 9.978778343238455e-07,
      "loss": 0.0033,
      "reward": 2.1079373359680176,
      "reward_std": 0.01183334831148386,
      "rewards/accuracy_reward": 0.9079375267028809,
      "rewards/format_reward": 1.0,
      "step": 2127
    },
    {
      "all_correct": 0.75,
      "all_wrong": 0.0,
      "completion_length": 419.09375,
      "epoch": 0.029351319292147696,
      "grad_norm": 2.3351985525684027,
      "kl": 0.09326171875,
      "learning_rate": 9.978758398148638e-07,
      "loss": 0.0037,
      "reward": 2.1147186756134033,
      "reward_std": 0.019157445058226585,
      "rewards/accuracy_reward": 0.914718747138977,
      "rewards/format_reward": 1.0,
      "step": 2128
    },
    {
      "all_correct": 0.75,
      "all_wrong": 0.0,
      "completion_length": 420.125,
      "epoch": 0.029365112205348893,
      "grad_norm": 4.768021132238271,
      "kl": 0.0810546875,
      "learning_rate": 9.978738443710519e-07,
      "loss": 0.0033,
      "reward": 1.9914376735687256,
      "reward_std": 0.01594974473118782,
      "rewards/accuracy_reward": 0.7914375066757202,
      "rewards/format_reward": 1.0,
      "step": 2129
    },
    {
      "all_correct": 0.75,
      "all_wrong": 0.0,
      "completion_length": 429.0,
      "epoch": 0.02937890511855009,
      "grad_norm": 3.117995350718515,
      "kl": 0.0888671875,
      "learning_rate": 9.978718479924135e-07,
      "loss": 0.0036,
      "reward": 2.059812545776367,
      "reward_std": 0.01983087696135044,
      "rewards/accuracy_reward": 0.8598124980926514,
      "rewards/format_reward": 1.0,
      "step": 2130
    },
    {
      "all_correct": 0.75,
      "all_wrong": 0.0,
      "completion_length": 418.71875,
      "epoch": 0.029392698031751287,
      "grad_norm": 2.079176625623688,
      "kl": 0.0888671875,
      "learning_rate": 9.97869850678952e-07,
      "loss": 0.0036,
      "reward": 2.139343738555908,
      "reward_std": 0.03310300037264824,
      "rewards/accuracy_reward": 0.9518437385559082,
      "rewards/format_reward": 1.0,
      "step": 2131
    },
    {
      "all_correct": 1.0,
      "all_wrong": 0.0,
      "completion_length": 422.03125,
      "epoch": 0.029406490944952485,
      "grad_norm": 2.882148557990783,
      "kl": 0.087890625,
      "learning_rate": 9.978678524306714e-07,
      "loss": 0.0035,
      "reward": 2.168375015258789,
      "reward_std": 0.028139302507042885,
      "rewards/accuracy_reward": 0.9683749675750732,
      "rewards/format_reward": 1.0,
      "step": 2132
    },
    {
      "all_correct": 0.75,
      "all_wrong": 0.0,
      "completion_length": 408.84375,
      "epoch": 0.029420283858153682,
      "grad_norm": 2.9787532178845675,
      "kl": 0.087890625,
      "learning_rate": 9.978658532475756e-07,
      "loss": 0.0035,
      "reward": 2.125,
      "reward_std": 0.009319850243628025,
      "rewards/accuracy_reward": 0.9249999523162842,
      "rewards/format_reward": 1.0,
      "step": 2133
    },
    {
      "all_correct": 0.75,
      "all_wrong": 0.0,
      "completion_length": 406.625,
      "epoch": 0.02943407677135488,
      "grad_norm": 2.905957153049684,
      "kl": 0.0869140625,
      "learning_rate": 9.978638531296681e-07,
      "loss": 0.0035,
      "reward": 2.0711874961853027,
      "reward_std": 0.011048303917050362,
      "rewards/accuracy_reward": 0.8711875081062317,
      "rewards/format_reward": 1.0,
      "step": 2134
    },
    {
      "all_correct": 0.75,
      "all_wrong": 0.0,
      "completion_length": 399.3125,
      "epoch": 0.029447869684556077,
      "grad_norm": 2.1774469309483626,
      "kl": 0.08984375,
      "learning_rate": 9.978618520769528e-07,
      "loss": 0.0036,
      "reward": 2.070906162261963,
      "reward_std": 0.016848890110850334,
      "rewards/accuracy_reward": 0.8709062337875366,
      "rewards/format_reward": 1.0,
      "step": 2135
    },
    {
      "all_correct": 0.75,
      "all_wrong": 0.0,
      "completion_length": 400.96875,
      "epoch": 0.029461662597757274,
      "grad_norm": 2.2377773396502945,
      "kl": 0.08056640625,
      "learning_rate": 9.978598500894334e-07,
      "loss": 0.0032,
      "reward": 2.088437557220459,
      "reward_std": 0.013646058738231659,
      "rewards/accuracy_reward": 0.8884374499320984,
      "rewards/format_reward": 1.0,
      "step": 2136
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.0,
      "completion_length": 412.90625,
      "epoch": 0.02947545551095847,
      "grad_norm": 2.5584010881481705,
      "kl": 0.07958984375,
      "learning_rate": 9.978578471671138e-07,
      "loss": 0.0032,
      "reward": 2.0523438453674316,
      "reward_std": 0.011382254771888256,
      "rewards/accuracy_reward": 0.852343738079071,
      "rewards/format_reward": 1.0,
      "step": 2137
    },
    {
      "all_correct": 1.0,
      "all_wrong": 0.0,
      "completion_length": 399.75,
      "epoch": 0.02948924842415967,
      "grad_norm": 2.875528615926683,
      "kl": 0.08544921875,
      "learning_rate": 9.978558433099974e-07,
      "loss": 0.0034,
      "reward": 2.112468719482422,
      "reward_std": 0.01609628088772297,
      "rewards/accuracy_reward": 0.9124687910079956,
      "rewards/format_reward": 1.0,
      "step": 2138
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.0,
      "completion_length": 404.125,
      "epoch": 0.029503041337360866,
      "grad_norm": 2.877970166120491,
      "kl": 0.0849609375,
      "learning_rate": 9.978538385180884e-07,
      "loss": 0.0034,
      "reward": 2.0692501068115234,
      "reward_std": 0.012559600174427032,
      "rewards/accuracy_reward": 0.8692499399185181,
      "rewards/format_reward": 1.0,
      "step": 2139
    },
    {
      "all_correct": 0.75,
      "all_wrong": 0.0,
      "completion_length": 392.59375,
      "epoch": 0.029516834250562063,
      "grad_norm": 3.1316881587225014,
      "kl": 0.08935546875,
      "learning_rate": 9.9785183279139e-07,
      "loss": 0.0036,
      "reward": 2.07450008392334,
      "reward_std": 0.031652599573135376,
      "rewards/accuracy_reward": 0.8807499408721924,
      "rewards/format_reward": 1.0,
      "step": 2140
    },
    {
      "all_correct": 1.0,
      "all_wrong": 0.0,
      "completion_length": 394.59375,
      "epoch": 0.02953062716376326,
      "grad_norm": 2.8788656058468023,
      "kl": 0.08203125,
      "learning_rate": 9.978498261299066e-07,
      "loss": 0.0033,
      "reward": 2.1280312538146973,
      "reward_std": 0.02024359628558159,
      "rewards/accuracy_reward": 0.9280312061309814,
      "rewards/format_reward": 1.0,
      "step": 2141
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.0,
      "completion_length": 402.59375,
      "epoch": 0.029544420076964454,
      "grad_norm": 5.9812467053196805,
      "kl": 0.07666015625,
      "learning_rate": 9.978478185336418e-07,
      "loss": 0.0031,
      "reward": 2.067593812942505,
      "reward_std": 0.029555248096585274,
      "rewards/accuracy_reward": 0.8738437294960022,
      "rewards/format_reward": 1.0,
      "step": 2142
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.0,
      "completion_length": 409.1875,
      "epoch": 0.02955821299016565,
      "grad_norm": 2.1376543878891288,
      "kl": 0.087890625,
      "learning_rate": 9.97845810002599e-07,
      "loss": 0.0035,
      "reward": 2.0815000534057617,
      "reward_std": 0.02134629152715206,
      "rewards/accuracy_reward": 0.8814999461174011,
      "rewards/format_reward": 1.0,
      "step": 2143
    },
    {
      "all_correct": 0.75,
      "all_wrong": 0.0,
      "completion_length": 398.90625,
      "epoch": 0.02957200590336685,
      "grad_norm": 2.6101996283004336,
      "kl": 0.0888671875,
      "learning_rate": 9.978438005367824e-07,
      "loss": 0.0036,
      "reward": 2.0667812824249268,
      "reward_std": 0.012508269399404526,
      "rewards/accuracy_reward": 0.8667812347412109,
      "rewards/format_reward": 1.0,
      "step": 2144
    },
    {
      "all_correct": 0.75,
      "all_wrong": 0.0,
      "completion_length": 398.46875,
      "epoch": 0.029585798816568046,
      "grad_norm": 2.3873864045505893,
      "kl": 0.0859375,
      "learning_rate": 9.978417901361957e-07,
      "loss": 0.0034,
      "reward": 2.0777812004089355,
      "reward_std": 0.0191669762134552,
      "rewards/accuracy_reward": 0.8777812123298645,
      "rewards/format_reward": 1.0,
      "step": 2145
    },
    {
      "all_correct": 0.75,
      "all_wrong": 0.0,
      "completion_length": 402.40625,
      "epoch": 0.029599591729769243,
      "grad_norm": 2.8541186010689317,
      "kl": 0.08251953125,
      "learning_rate": 9.978397788008424e-07,
      "loss": 0.0033,
      "reward": 2.085031032562256,
      "reward_std": 0.019557081162929535,
      "rewards/accuracy_reward": 0.8850312232971191,
      "rewards/format_reward": 1.0,
      "step": 2146
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.0,
      "completion_length": 415.09375,
      "epoch": 0.02961338464297044,
      "grad_norm": 2.604685832409183,
      "kl": 0.072265625,
      "learning_rate": 9.978377665307267e-07,
      "loss": 0.0029,
      "reward": 2.024156093597412,
      "reward_std": 0.010080362670123577,
      "rewards/accuracy_reward": 0.8241562843322754,
      "rewards/format_reward": 1.0,
      "step": 2147
    },
    {
      "all_correct": 1.0,
      "all_wrong": 0.0,
      "completion_length": 404.4375,
      "epoch": 0.029627177556171638,
      "grad_norm": 2.54893984392409,
      "kl": 0.07958984375,
      "learning_rate": 9.978357533258519e-07,
      "loss": 0.0032,
      "reward": 2.1401875019073486,
      "reward_std": 0.014890208840370178,
      "rewards/accuracy_reward": 0.9401875734329224,
      "rewards/format_reward": 1.0,
      "step": 2148
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.0,
      "completion_length": 415.875,
      "epoch": 0.029640970469372835,
      "grad_norm": 3.840579320662775,
      "kl": 0.0849609375,
      "learning_rate": 9.978337391862222e-07,
      "loss": 0.0034,
      "reward": 2.01631236076355,
      "reward_std": 0.01764514110982418,
      "rewards/accuracy_reward": 0.8163124322891235,
      "rewards/format_reward": 1.0,
      "step": 2149
    },
    {
      "all_correct": 0.75,
      "all_wrong": 0.0,
      "completion_length": 405.90625,
      "epoch": 0.029654763382574032,
      "grad_norm": 2.975806862608416,
      "kl": 0.0830078125,
      "learning_rate": 9.97831724111841e-07,
      "loss": 0.0033,
      "reward": 2.0737500190734863,
      "reward_std": 0.015361923724412918,
      "rewards/accuracy_reward": 0.8737500309944153,
      "rewards/format_reward": 1.0,
      "step": 2150
    },
    {
      "all_correct": 1.0,
      "all_wrong": 0.0,
      "completion_length": 406.71875,
      "epoch": 0.02966855629577523,
      "grad_norm": 2.92006622831087,
      "kl": 0.08251953125,
      "learning_rate": 9.978297081027123e-07,
      "loss": 0.0033,
      "reward": 2.120093584060669,
      "reward_std": 0.018047591671347618,
      "rewards/accuracy_reward": 0.9200937747955322,
      "rewards/format_reward": 1.0,
      "step": 2151
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.0,
      "completion_length": 408.1875,
      "epoch": 0.029682349208976427,
      "grad_norm": 5.266211221576084,
      "kl": 0.072265625,
      "learning_rate": 9.978276911588398e-07,
      "loss": 0.0029,
      "reward": 2.0843749046325684,
      "reward_std": 0.022663431242108345,
      "rewards/accuracy_reward": 0.8843749761581421,
      "rewards/format_reward": 1.0,
      "step": 2152
    },
    {
      "all_correct": 1.0,
      "all_wrong": 0.0,
      "completion_length": 409.53125,
      "epoch": 0.029696142122177624,
      "grad_norm": 2.89893569138178,
      "kl": 0.0830078125,
      "learning_rate": 9.978256732802278e-07,
      "loss": 0.0033,
      "reward": 2.107375144958496,
      "reward_std": 0.024955984205007553,
      "rewards/accuracy_reward": 0.9073749780654907,
      "rewards/format_reward": 1.0,
      "step": 2153
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.0,
      "completion_length": 413.875,
      "epoch": 0.02970993503537882,
      "grad_norm": 3.238170161374507,
      "kl": 0.08056640625,
      "learning_rate": 9.978236544668793e-07,
      "loss": 0.0032,
      "reward": 2.016906261444092,
      "reward_std": 0.028309836983680725,
      "rewards/accuracy_reward": 0.8231562376022339,
      "rewards/format_reward": 1.0,
      "step": 2154
    },
    {
      "all_correct": 0.75,
      "all_wrong": 0.0,
      "completion_length": 410.09375,
      "epoch": 0.02972372794858002,
      "grad_norm": 2.935671648303275,
      "kl": 0.083984375,
      "learning_rate": 9.978216347187984e-07,
      "loss": 0.0034,
      "reward": 2.0879688262939453,
      "reward_std": 0.02018401399254799,
      "rewards/accuracy_reward": 0.8879687190055847,
      "rewards/format_reward": 1.0,
      "step": 2155
    },
    {
      "all_correct": 0.75,
      "all_wrong": 0.0,
      "completion_length": 399.9375,
      "epoch": 0.029737520861781216,
      "grad_norm": 8.163255279087053,
      "kl": 0.08984375,
      "learning_rate": 9.97819614035989e-07,
      "loss": 0.0036,
      "reward": 2.0929064750671387,
      "reward_std": 0.017653988674283028,
      "rewards/accuracy_reward": 0.8929062485694885,
      "rewards/format_reward": 1.0,
      "step": 2156
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.0,
      "completion_length": 409.84375,
      "epoch": 0.029751313774982413,
      "grad_norm": 2.48398554660599,
      "kl": 0.0810546875,
      "learning_rate": 9.978175924184549e-07,
      "loss": 0.0032,
      "reward": 2.1097497940063477,
      "reward_std": 0.03194742649793625,
      "rewards/accuracy_reward": 0.9159999489784241,
      "rewards/format_reward": 1.0,
      "step": 2157
    },
    {
      "all_correct": 0.75,
      "all_wrong": 0.0,
      "completion_length": 414.5,
      "epoch": 0.02976510668818361,
      "grad_norm": 6.499278903251688,
      "kl": 0.080078125,
      "learning_rate": 9.978155698661997e-07,
      "loss": 0.0032,
      "reward": 2.1356563568115234,
      "reward_std": 0.03120109811425209,
      "rewards/accuracy_reward": 0.9419062733650208,
      "rewards/format_reward": 1.0,
      "step": 2158
    },
    {
      "all_correct": 1.0,
      "all_wrong": 0.0,
      "completion_length": 406.53125,
      "epoch": 0.029778899601384808,
      "grad_norm": 6.924626612390532,
      "kl": 0.07958984375,
      "learning_rate": 9.978135463792272e-07,
      "loss": 0.0032,
      "reward": 2.1131250858306885,
      "reward_std": 0.028056159615516663,
      "rewards/accuracy_reward": 0.9131249189376831,
      "rewards/format_reward": 1.0,
      "step": 2159
    },
    {
      "all_correct": 1.0,
      "all_wrong": 0.0,
      "completion_length": 403.3125,
      "epoch": 0.029792692514586005,
      "grad_norm": 2.768071757995682,
      "kl": 0.0810546875,
      "learning_rate": 9.978115219575415e-07,
      "loss": 0.0032,
      "reward": 2.124875068664551,
      "reward_std": 0.015134197659790516,
      "rewards/accuracy_reward": 0.924875020980835,
      "rewards/format_reward": 1.0,
      "step": 2160
    },
    {
      "all_correct": 0.75,
      "all_wrong": 0.0,
      "completion_length": 401.15625,
      "epoch": 0.029806485427787202,
      "grad_norm": 2.2597427352509896,
      "kl": 0.095703125,
      "learning_rate": 9.978094966011462e-07,
      "loss": 0.0038,
      "reward": 2.1288750171661377,
      "reward_std": 0.014218784868717194,
      "rewards/accuracy_reward": 0.9288750290870667,
      "rewards/format_reward": 1.0,
      "step": 2161
    },
    {
      "all_correct": 1.0,
      "all_wrong": 0.0,
      "completion_length": 402.65625,
      "epoch": 0.0298202783409884,
      "grad_norm": 2.995593591894307,
      "kl": 0.080078125,
      "learning_rate": 9.978074703100452e-07,
      "loss": 0.0032,
      "reward": 2.1445937156677246,
      "reward_std": 0.0158880315721035,
      "rewards/accuracy_reward": 0.9445937275886536,
      "rewards/format_reward": 1.0,
      "step": 2162
    },
    {
      "all_correct": 1.0,
      "all_wrong": 0.0,
      "completion_length": 389.21875,
      "epoch": 0.029834071254189597,
      "grad_norm": 3.1360165301793668,
      "kl": 0.08544921875,
      "learning_rate": 9.97805443084242e-07,
      "loss": 0.0034,
      "reward": 2.1525938510894775,
      "reward_std": 0.008373921737074852,
      "rewards/accuracy_reward": 0.9525937438011169,
      "rewards/format_reward": 1.0,
      "step": 2163
    },
    {
      "all_correct": 1.0,
      "all_wrong": 0.0,
      "completion_length": 399.9375,
      "epoch": 0.029847864167390794,
      "grad_norm": 2.6505661273803542,
      "kl": 0.078125,
      "learning_rate": 9.978034149237408e-07,
      "loss": 0.0031,
      "reward": 2.113468647003174,
      "reward_std": 0.023791436105966568,
      "rewards/accuracy_reward": 0.9134687781333923,
      "rewards/format_reward": 1.0,
      "step": 2164
    },
    {
      "all_correct": 1.0,
      "all_wrong": 0.0,
      "completion_length": 386.0,
      "epoch": 0.02986165708059199,
      "grad_norm": 2.8453187362795505,
      "kl": 0.08642578125,
      "learning_rate": 9.978013858285452e-07,
      "loss": 0.0035,
      "reward": 2.1449062824249268,
      "reward_std": 0.011698558926582336,
      "rewards/accuracy_reward": 0.9449062347412109,
      "rewards/format_reward": 1.0,
      "step": 2165
    },
    {
      "all_correct": 1.0,
      "all_wrong": 0.0,
      "completion_length": 402.65625,
      "epoch": 0.02987544999379319,
      "grad_norm": 2.364622446033586,
      "kl": 0.07080078125,
      "learning_rate": 9.97799355798659e-07,
      "loss": 0.0028,
      "reward": 2.143531322479248,
      "reward_std": 0.013602443970739841,
      "rewards/accuracy_reward": 0.9435312747955322,
      "rewards/format_reward": 1.0,
      "step": 2166
    },
    {
      "all_correct": 0.75,
      "all_wrong": 0.0,
      "completion_length": 395.21875,
      "epoch": 0.029889242906994386,
      "grad_norm": 2.0285015682756806,
      "kl": 0.07568359375,
      "learning_rate": 9.97797324834086e-07,
      "loss": 0.003,
      "reward": 2.140531063079834,
      "reward_std": 0.01572326198220253,
      "rewards/accuracy_reward": 0.9405312538146973,
      "rewards/format_reward": 1.0,
      "step": 2167
    },
    {
      "all_correct": 0.75,
      "all_wrong": 0.0,
      "completion_length": 404.75,
      "epoch": 0.029903035820195583,
      "grad_norm": 2.509314338215299,
      "kl": 0.07568359375,
      "learning_rate": 9.977952929348303e-07,
      "loss": 0.003,
      "reward": 2.0768749713897705,
      "reward_std": 0.01655711978673935,
      "rewards/accuracy_reward": 0.8768749833106995,
      "rewards/format_reward": 1.0,
      "step": 2168
    },
    {
      "all_correct": 0.75,
      "all_wrong": 0.0,
      "completion_length": 396.71875,
      "epoch": 0.02991682873339678,
      "grad_norm": 36.05552545242765,
      "kl": 0.07763671875,
      "learning_rate": 9.977932601008953e-07,
      "loss": 0.0031,
      "reward": 2.018249988555908,
      "reward_std": 0.028770923614501953,
      "rewards/accuracy_reward": 0.8182500004768372,
      "rewards/format_reward": 1.0,
      "step": 2169
    },
    {
      "all_correct": 1.0,
      "all_wrong": 0.0,
      "completion_length": 398.65625,
      "epoch": 0.029930621646597978,
      "grad_norm": 1.9503543557451053,
      "kl": 0.078125,
      "learning_rate": 9.977912263322852e-07,
      "loss": 0.0031,
      "reward": 2.177093744277954,
      "reward_std": 0.025064757093787193,
      "rewards/accuracy_reward": 0.9833437204360962,
      "rewards/format_reward": 1.0,
      "step": 2170
    },
    {
      "all_correct": 0.75,
      "all_wrong": 0.0,
      "completion_length": 380.96875,
      "epoch": 0.029944414559799175,
      "grad_norm": 2.1052868046048054,
      "kl": 0.080078125,
      "learning_rate": 9.977891916290034e-07,
      "loss": 0.0032,
      "reward": 2.100062847137451,
      "reward_std": 0.018956970423460007,
      "rewards/accuracy_reward": 0.9000625014305115,
      "rewards/format_reward": 1.0,
      "step": 2171
    },
    {
      "all_correct": 0.75,
      "all_wrong": 0.0,
      "completion_length": 382.96875,
      "epoch": 0.029958207473000372,
      "grad_norm": 3.766676976135831,
      "kl": 0.080078125,
      "learning_rate": 9.97787155991054e-07,
      "loss": 0.0032,
      "reward": 2.112468719482422,
      "reward_std": 0.013913454487919807,
      "rewards/accuracy_reward": 0.9124687910079956,
      "rewards/format_reward": 1.0,
      "step": 2172
    },
    {
      "all_correct": 0.75,
      "all_wrong": 0.0,
      "completion_length": 380.1875,
      "epoch": 0.02997200038620157,
      "grad_norm": 2.2995707450873875,
      "kl": 0.07275390625,
      "learning_rate": 9.977851194184408e-07,
      "loss": 0.0029,
      "reward": 2.087625026702881,
      "reward_std": 0.016663692891597748,
      "rewards/accuracy_reward": 0.8876249194145203,
      "rewards/format_reward": 1.0,
      "step": 2173
    },
    {
      "all_correct": 1.0,
      "all_wrong": 0.0,
      "completion_length": 393.59375,
      "epoch": 0.029985793299402767,
      "grad_norm": 1.6701813818269653,
      "kl": 0.06591796875,
      "learning_rate": 9.977830819111677e-07,
      "loss": 0.0026,
      "reward": 2.17396879196167,
      "reward_std": 0.0061285244300961494,
      "rewards/accuracy_reward": 0.9739687442779541,
      "rewards/format_reward": 1.0,
      "step": 2174
    },
    {
      "all_correct": 0.75,
      "all_wrong": 0.0,
      "completion_length": 390.96875,
      "epoch": 0.029999586212603964,
      "grad_norm": 4.620354032250096,
      "kl": 0.078125,
      "learning_rate": 9.977810434692382e-07,
      "loss": 0.0031,
      "reward": 2.079531192779541,
      "reward_std": 0.025339238345623016,
      "rewards/accuracy_reward": 0.8795312643051147,
      "rewards/format_reward": 1.0,
      "step": 2175
    },
    {
      "all_correct": 0.25,
      "all_wrong": 0.0,
      "completion_length": 376.0,
      "epoch": 0.03001337912580516,
      "grad_norm": 3.038742812191827,
      "kl": 0.078125,
      "learning_rate": 9.977790040926564e-07,
      "loss": 0.0031,
      "reward": 1.9677188396453857,
      "reward_std": 0.01996118575334549,
      "rewards/accuracy_reward": 0.7677187323570251,
      "rewards/format_reward": 1.0,
      "step": 2176
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.0,
      "completion_length": 384.59375,
      "epoch": 0.03002717203900636,
      "grad_norm": 5.010668778086776,
      "kl": 0.0791015625,
      "learning_rate": 9.977769637814262e-07,
      "loss": 0.0032,
      "reward": 1.9748749732971191,
      "reward_std": 0.01638328656554222,
      "rewards/accuracy_reward": 0.7748749256134033,
      "rewards/format_reward": 1.0,
      "step": 2177
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.0,
      "completion_length": 376.25,
      "epoch": 0.030040964952207556,
      "grad_norm": 2.4600798300088615,
      "kl": 0.08056640625,
      "learning_rate": 9.977749225355513e-07,
      "loss": 0.0032,
      "reward": 2.120687484741211,
      "reward_std": 0.03754265978932381,
      "rewards/accuracy_reward": 0.9331875443458557,
      "rewards/format_reward": 1.0,
      "step": 2178
    },
    {
      "all_correct": 1.0,
      "all_wrong": 0.0,
      "completion_length": 386.46875,
      "epoch": 0.030054757865408753,
      "grad_norm": 2.3294518004206477,
      "kl": 0.0673828125,
      "learning_rate": 9.977728803550354e-07,
      "loss": 0.0027,
      "reward": 2.146749973297119,
      "reward_std": 0.012294841930270195,
      "rewards/accuracy_reward": 0.9467499256134033,
      "rewards/format_reward": 1.0,
      "step": 2179
    },
    {
      "all_correct": 1.0,
      "all_wrong": 0.0,
      "completion_length": 384.84375,
      "epoch": 0.03006855077860995,
      "grad_norm": 5.291889903710729,
      "kl": 0.076171875,
      "learning_rate": 9.977708372398825e-07,
      "loss": 0.003,
      "reward": 2.122593641281128,
      "reward_std": 0.043387528508901596,
      "rewards/accuracy_reward": 0.9225937724113464,
      "rewards/format_reward": 1.0,
      "step": 2180
    },
    {
      "all_correct": 0.25,
      "all_wrong": 0.0,
      "completion_length": 386.09375,
      "epoch": 0.030082343691811148,
      "grad_norm": 2.3011057917786815,
      "kl": 0.0771484375,
      "learning_rate": 9.977687931900964e-07,
      "loss": 0.0031,
      "reward": 1.9800312519073486,
      "reward_std": 0.027691654860973358,
      "rewards/accuracy_reward": 0.7800313234329224,
      "rewards/format_reward": 1.0,
      "step": 2181
    },
    {
      "all_correct": 0.75,
      "all_wrong": 0.0,
      "completion_length": 390.0625,
      "epoch": 0.030096136605012345,
      "grad_norm": 2.168541525310985,
      "kl": 0.083984375,
      "learning_rate": 9.97766748205681e-07,
      "loss": 0.0034,
      "reward": 2.115968704223633,
      "reward_std": 0.009785845875740051,
      "rewards/accuracy_reward": 0.9159688353538513,
      "rewards/format_reward": 1.0,
      "step": 2182
    },
    {
      "all_correct": 1.0,
      "all_wrong": 0.0,
      "completion_length": 379.375,
      "epoch": 0.030109929518213542,
      "grad_norm": 2.4607620918111768,
      "kl": 0.0673828125,
      "learning_rate": 9.9776470228664e-07,
      "loss": 0.0027,
      "reward": 2.1579999923706055,
      "reward_std": 0.017274891957640648,
      "rewards/accuracy_reward": 0.9580000638961792,
      "rewards/format_reward": 1.0,
      "step": 2183
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.0,
      "completion_length": 383.4375,
      "epoch": 0.03012372243141474,
      "grad_norm": 2.9249667299728586,
      "kl": 0.08349609375,
      "learning_rate": 9.977626554329774e-07,
      "loss": 0.0033,
      "reward": 2.0839061737060547,
      "reward_std": 0.032355956733226776,
      "rewards/accuracy_reward": 0.8901562690734863,
      "rewards/format_reward": 1.0,
      "step": 2184
    },
    {
      "all_correct": 1.0,
      "all_wrong": 0.0,
      "completion_length": 388.0625,
      "epoch": 0.030137515344615937,
      "grad_norm": 3.122571621572205,
      "kl": 0.07275390625,
      "learning_rate": 9.97760607644697e-07,
      "loss": 0.0029,
      "reward": 2.141843795776367,
      "reward_std": 0.013540457934141159,
      "rewards/accuracy_reward": 0.9418437480926514,
      "rewards/format_reward": 1.0,
      "step": 2185
    },
    {
      "all_correct": 1.0,
      "all_wrong": 0.0,
      "completion_length": 385.96875,
      "epoch": 0.030151308257817134,
      "grad_norm": 3.076471409176197,
      "kl": 0.08203125,
      "learning_rate": 9.977585589218027e-07,
      "loss": 0.0033,
      "reward": 2.1568126678466797,
      "reward_std": 0.011049201712012291,
      "rewards/accuracy_reward": 0.9568124413490295,
      "rewards/format_reward": 1.0,
      "step": 2186
    },
    {
      "all_correct": 0.25,
      "all_wrong": 0.0,
      "completion_length": 375.0,
      "epoch": 0.03016510117101833,
      "grad_norm": 2.97496284292612,
      "kl": 0.087890625,
      "learning_rate": 9.97756509264298e-07,
      "loss": 0.0035,
      "reward": 2.0447187423706055,
      "reward_std": 0.04658292233943939,
      "rewards/accuracy_reward": 0.8572187423706055,
      "rewards/format_reward": 1.0,
      "step": 2187
    },
    {
      "all_correct": 0.25,
      "all_wrong": 0.0,
      "completion_length": 370.84375,
      "epoch": 0.03017889408421953,
      "grad_norm": 2.719218977129783,
      "kl": 0.07861328125,
      "learning_rate": 9.97754458672187e-07,
      "loss": 0.0031,
      "reward": 1.9946563243865967,
      "reward_std": 0.01253945380449295,
      "rewards/accuracy_reward": 0.7946561574935913,
      "rewards/format_reward": 1.0,
      "step": 2188
    },
    {
      "all_correct": 1.0,
      "all_wrong": 0.0,
      "completion_length": 399.0625,
      "epoch": 0.030192686997420726,
      "grad_norm": 2.3528926497907947,
      "kl": 0.07470703125,
      "learning_rate": 9.97752407145474e-07,
      "loss": 0.003,
      "reward": 2.14736270904541,
      "reward_std": 0.01700129732489586,
      "rewards/accuracy_reward": 0.9473625421524048,
      "rewards/format_reward": 1.0,
      "step": 2189
    },
    {
      "all_correct": 1.0,
      "all_wrong": 0.0,
      "completion_length": 402.6875,
      "epoch": 0.030206479910621923,
      "grad_norm": 2.2119627206977417,
      "kl": 0.08056640625,
      "learning_rate": 9.97750354684162e-07,
      "loss": 0.0032,
      "reward": 2.154531240463257,
      "reward_std": 0.014431731775403023,
      "rewards/accuracy_reward": 0.9545312523841858,
      "rewards/format_reward": 1.0,
      "step": 2190
    },
    {
      "all_correct": 1.0,
      "all_wrong": 0.0,
      "completion_length": 398.28125,
      "epoch": 0.03022027282382312,
      "grad_norm": 2.2972766701343414,
      "kl": 0.078125,
      "learning_rate": 9.977483012882555e-07,
      "loss": 0.0031,
      "reward": 2.142343759536743,
      "reward_std": 0.013355524279177189,
      "rewards/accuracy_reward": 0.9423437714576721,
      "rewards/format_reward": 1.0,
      "step": 2191
    },
    {
      "all_correct": 0.75,
      "all_wrong": 0.0,
      "completion_length": 398.90625,
      "epoch": 0.030234065737024318,
      "grad_norm": 3.0812410672646973,
      "kl": 0.07763671875,
      "learning_rate": 9.97746246957758e-07,
      "loss": 0.0031,
      "reward": 2.0666563510894775,
      "reward_std": 0.025859542191028595,
      "rewards/accuracy_reward": 0.8666562438011169,
      "rewards/format_reward": 1.0,
      "step": 2192
    },
    {
      "all_correct": 0.75,
      "all_wrong": 0.0,
      "completion_length": 400.6875,
      "epoch": 0.030247858650225515,
      "grad_norm": 3.2406973025286776,
      "kl": 0.06884765625,
      "learning_rate": 9.977441916926734e-07,
      "loss": 0.0028,
      "reward": 2.0384063720703125,
      "reward_std": 0.034345947206020355,
      "rewards/accuracy_reward": 0.8384062051773071,
      "rewards/format_reward": 1.0,
      "step": 2193
    },
    {
      "all_correct": 0.75,
      "all_wrong": 0.0,
      "completion_length": 401.875,
      "epoch": 0.030261651563426712,
      "grad_norm": 2.4193024626897324,
      "kl": 0.08056640625,
      "learning_rate": 9.977421354930056e-07,
      "loss": 0.0032,
      "reward": 2.0469374656677246,
      "reward_std": 0.01872834376990795,
      "rewards/accuracy_reward": 0.8469375371932983,
      "rewards/format_reward": 1.0,
      "step": 2194
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.0,
      "completion_length": 398.28125,
      "epoch": 0.03027544447662791,
      "grad_norm": 2.515117819770639,
      "kl": 0.0751953125,
      "learning_rate": 9.977400783587586e-07,
      "loss": 0.003,
      "reward": 2.010406255722046,
      "reward_std": 0.020029190927743912,
      "rewards/accuracy_reward": 0.8104062676429749,
      "rewards/format_reward": 1.0,
      "step": 2195
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.0,
      "completion_length": 392.0,
      "epoch": 0.030289237389829107,
      "grad_norm": 2.9456626807740247,
      "kl": 0.083984375,
      "learning_rate": 9.977380202899363e-07,
      "loss": 0.0034,
      "reward": 2.017125129699707,
      "reward_std": 0.01958318054676056,
      "rewards/accuracy_reward": 0.8171249628067017,
      "rewards/format_reward": 1.0,
      "step": 2196
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.0,
      "completion_length": 392.4375,
      "epoch": 0.030303030303030304,
      "grad_norm": 3.5454949638624145,
      "kl": 0.07275390625,
      "learning_rate": 9.977359612865422e-07,
      "loss": 0.0029,
      "reward": 2.106968879699707,
      "reward_std": 0.03425057232379913,
      "rewards/accuracy_reward": 0.9132187366485596,
      "rewards/format_reward": 1.0,
      "step": 2197
    },
    {
      "all_correct": 0.75,
      "all_wrong": 0.0,
      "completion_length": 394.65625,
      "epoch": 0.0303168232162315,
      "grad_norm": 3.4955659730397866,
      "kl": 0.08056640625,
      "learning_rate": 9.977339013485806e-07,
      "loss": 0.0032,
      "reward": 2.0889062881469727,
      "reward_std": 0.02780120261013508,
      "rewards/accuracy_reward": 0.8889062404632568,
      "rewards/format_reward": 1.0,
      "step": 2198
    },
    {
      "all_correct": 0.25,
      "all_wrong": 0.0,
      "completion_length": 402.75,
      "epoch": 0.0303306161294327,
      "grad_norm": 1.976163071320007,
      "kl": 0.06689453125,
      "learning_rate": 9.97731840476055e-07,
      "loss": 0.0027,
      "reward": 2.068906307220459,
      "reward_std": 0.026243673637509346,
      "rewards/accuracy_reward": 0.8751562237739563,
      "rewards/format_reward": 1.0,
      "step": 2199
    },
    {
      "all_correct": 1.0,
      "all_wrong": 0.0,
      "completion_length": 412.21875,
      "epoch": 0.030344409042633896,
      "grad_norm": 2.642038761372087,
      "kl": 0.0703125,
      "learning_rate": 9.977297786689695e-07,
      "loss": 0.0028,
      "reward": 2.145718574523926,
      "reward_std": 0.017455019056797028,
      "rewards/accuracy_reward": 0.9457187652587891,
      "rewards/format_reward": 1.0,
      "step": 2200
    },
    {
      "all_correct": 1.0,
      "all_wrong": 0.0,
      "completion_length": 406.875,
      "epoch": 0.030358201955835093,
      "grad_norm": 2.138230163872008,
      "kl": 0.07861328125,
      "learning_rate": 9.97727715927328e-07,
      "loss": 0.0031,
      "reward": 2.1140313148498535,
      "reward_std": 0.02577412873506546,
      "rewards/accuracy_reward": 0.9140312075614929,
      "rewards/format_reward": 1.0,
      "step": 2201
    },
    {
      "all_correct": 0.75,
      "all_wrong": 0.0,
      "completion_length": 405.71875,
      "epoch": 0.03037199486903629,
      "grad_norm": 2.8655290879303426,
      "kl": 0.07177734375,
      "learning_rate": 9.977256522511341e-07,
      "loss": 0.0029,
      "reward": 2.101468563079834,
      "reward_std": 0.016969265416264534,
      "rewards/accuracy_reward": 0.9014687538146973,
      "rewards/format_reward": 1.0,
      "step": 2202
    },
    {
      "all_correct": 1.0,
      "all_wrong": 0.0,
      "completion_length": 400.75,
      "epoch": 0.030385787782237487,
      "grad_norm": 2.926329849080525,
      "kl": 0.07275390625,
      "learning_rate": 9.977235876403917e-07,
      "loss": 0.0029,
      "reward": 2.1384999752044678,
      "reward_std": 0.015922226011753082,
      "rewards/accuracy_reward": 0.9385000467300415,
      "rewards/format_reward": 1.0,
      "step": 2203
    },
    {
      "all_correct": 0.75,
      "all_wrong": 0.0,
      "completion_length": 414.5625,
      "epoch": 0.030399580695438685,
      "grad_norm": 4.554514910715986,
      "kl": 0.078125,
      "learning_rate": 9.977215220951052e-07,
      "loss": 0.0031,
      "reward": 2.1174373626708984,
      "reward_std": 0.015788527205586433,
      "rewards/accuracy_reward": 0.9174374341964722,
      "rewards/format_reward": 1.0,
      "step": 2204
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.0,
      "completion_length": 422.28125,
      "epoch": 0.030413373608639882,
      "grad_norm": 2.5669971551511543,
      "kl": 0.07275390625,
      "learning_rate": 9.97719455615278e-07,
      "loss": 0.0029,
      "reward": 1.9704687595367432,
      "reward_std": 0.02118171565234661,
      "rewards/accuracy_reward": 0.7704687714576721,
      "rewards/format_reward": 1.0,
      "step": 2205
    },
    {
      "all_correct": 1.0,
      "all_wrong": 0.0,
      "completion_length": 408.46875,
      "epoch": 0.03042716652184108,
      "grad_norm": 1.8949751480227206,
      "kl": 0.072265625,
      "learning_rate": 9.977173882009139e-07,
      "loss": 0.0029,
      "reward": 2.1453280448913574,
      "reward_std": 0.008334027603268623,
      "rewards/accuracy_reward": 0.9453281164169312,
      "rewards/format_reward": 1.0,
      "step": 2206
    },
    {
      "all_correct": 0.75,
      "all_wrong": 0.0,
      "completion_length": 421.3125,
      "epoch": 0.030440959435042277,
      "grad_norm": 7.686394691849239,
      "kl": 0.07568359375,
      "learning_rate": 9.977153198520169e-07,
      "loss": 0.003,
      "reward": 2.11928129196167,
      "reward_std": 0.02656150609254837,
      "rewards/accuracy_reward": 0.9192812442779541,
      "rewards/format_reward": 1.0,
      "step": 2207
    },
    {
      "all_correct": 0.25,
      "all_wrong": 0.0,
      "completion_length": 421.9375,
      "epoch": 0.030454752348243474,
      "grad_norm": 2.459156397192004,
      "kl": 0.08154296875,
      "learning_rate": 9.977132505685912e-07,
      "loss": 0.0033,
      "reward": 2.0004687309265137,
      "reward_std": 0.033843837678432465,
      "rewards/accuracy_reward": 0.8067187666893005,
      "rewards/format_reward": 1.0,
      "step": 2208
    },
    {
      "all_correct": 0.75,
      "all_wrong": 0.0,
      "completion_length": 410.71875,
      "epoch": 0.03046854526144467,
      "grad_norm": 8.18672049184234,
      "kl": 0.07470703125,
      "learning_rate": 9.977111803506404e-07,
      "loss": 0.003,
      "reward": 2.125718832015991,
      "reward_std": 0.01143190823495388,
      "rewards/accuracy_reward": 0.9257187843322754,
      "rewards/format_reward": 1.0,
      "step": 2209
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.0,
      "completion_length": 419.3125,
      "epoch": 0.03048233817464587,
      "grad_norm": 3.1399075653630626,
      "kl": 0.072265625,
      "learning_rate": 9.977091091981683e-07,
      "loss": 0.0029,
      "reward": 2.0902187824249268,
      "reward_std": 0.0364406518638134,
      "rewards/accuracy_reward": 0.8964687585830688,
      "rewards/format_reward": 1.0,
      "step": 2210
    },
    {
      "all_correct": 0.75,
      "all_wrong": 0.0,
      "completion_length": 416.6875,
      "epoch": 0.030496131087847066,
      "grad_norm": 2.179556823229944,
      "kl": 0.08203125,
      "learning_rate": 9.97707037111179e-07,
      "loss": 0.0033,
      "reward": 2.0192811489105225,
      "reward_std": 0.011065879836678505,
      "rewards/accuracy_reward": 0.819281280040741,
      "rewards/format_reward": 1.0,
      "step": 2211
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.0,
      "completion_length": 409.59375,
      "epoch": 0.030509924001048263,
      "grad_norm": 2.733655606703832,
      "kl": 0.0771484375,
      "learning_rate": 9.977049640896764e-07,
      "loss": 0.0031,
      "reward": 2.0240938663482666,
      "reward_std": 0.024245424196124077,
      "rewards/accuracy_reward": 0.8240938186645508,
      "rewards/format_reward": 1.0,
      "step": 2212
    },
    {
      "all_correct": 1.0,
      "all_wrong": 0.0,
      "completion_length": 422.0,
      "epoch": 0.03052371691424946,
      "grad_norm": 2.6686014150167217,
      "kl": 0.076171875,
      "learning_rate": 9.977028901336642e-07,
      "loss": 0.0031,
      "reward": 2.1514062881469727,
      "reward_std": 0.016458529978990555,
      "rewards/accuracy_reward": 0.9514062404632568,
      "rewards/format_reward": 1.0,
      "step": 2213
    },
    {
      "all_correct": 1.0,
      "all_wrong": 0.0,
      "completion_length": 414.1875,
      "epoch": 0.030537509827450657,
      "grad_norm": 2.513533602492548,
      "kl": 0.07666015625,
      "learning_rate": 9.977008152431464e-07,
      "loss": 0.0031,
      "reward": 2.1211252212524414,
      "reward_std": 0.020682761445641518,
      "rewards/accuracy_reward": 0.9211249947547913,
      "rewards/format_reward": 1.0,
      "step": 2214
    },
    {
      "all_correct": 0.75,
      "all_wrong": 0.0,
      "completion_length": 410.5,
      "epoch": 0.030551302740651855,
      "grad_norm": 2.4577089806894867,
      "kl": 0.0830078125,
      "learning_rate": 9.976987394181268e-07,
      "loss": 0.0033,
      "reward": 2.0757501125335693,
      "reward_std": 0.02439242973923683,
      "rewards/accuracy_reward": 0.8757500052452087,
      "rewards/format_reward": 1.0,
      "step": 2215
    },
    {
      "all_correct": 1.0,
      "all_wrong": 0.0,
      "completion_length": 418.96875,
      "epoch": 0.030565095653853052,
      "grad_norm": 2.0341885480550297,
      "kl": 0.07958984375,
      "learning_rate": 9.976966626586094e-07,
      "loss": 0.0032,
      "reward": 2.132687568664551,
      "reward_std": 0.010410184971988201,
      "rewards/accuracy_reward": 0.932687520980835,
      "rewards/format_reward": 1.0,
      "step": 2216
    },
    {
      "all_correct": 0.75,
      "all_wrong": 0.0,
      "completion_length": 416.125,
      "epoch": 0.030578888567054246,
      "grad_norm": 2.528840489794019,
      "kl": 0.08251953125,
      "learning_rate": 9.976945849645982e-07,
      "loss": 0.0033,
      "reward": 2.0746562480926514,
      "reward_std": 0.021503344178199768,
      "rewards/accuracy_reward": 0.8746562600135803,
      "rewards/format_reward": 1.0,
      "step": 2217
    },
    {
      "all_correct": 0.75,
      "all_wrong": 0.0,
      "completion_length": 406.46875,
      "epoch": 0.030592681480255443,
      "grad_norm": 2.1720790927046707,
      "kl": 0.08349609375,
      "learning_rate": 9.976925063360969e-07,
      "loss": 0.0033,
      "reward": 1.958031177520752,
      "reward_std": 0.01428062841296196,
      "rewards/accuracy_reward": 0.7580313086509705,
      "rewards/format_reward": 1.0,
      "step": 2218
    },
    {
      "all_correct": 0.75,
      "all_wrong": 0.0,
      "completion_length": 404.875,
      "epoch": 0.03060647439345664,
      "grad_norm": 2.3651510960369455,
      "kl": 0.08740234375,
      "learning_rate": 9.976904267731094e-07,
      "loss": 0.0035,
      "reward": 2.058499813079834,
      "reward_std": 0.018771033734083176,
      "rewards/accuracy_reward": 0.8585000038146973,
      "rewards/format_reward": 1.0,
      "step": 2219
    },
    {
      "all_correct": 1.0,
      "all_wrong": 0.0,
      "completion_length": 429.625,
      "epoch": 0.030620267306657838,
      "grad_norm": 1.7941257717792825,
      "kl": 0.08203125,
      "learning_rate": 9.976883462756396e-07,
      "loss": 0.0033,
      "reward": 2.1697187423706055,
      "reward_std": 0.013782726600766182,
      "rewards/accuracy_reward": 0.9697187542915344,
      "rewards/format_reward": 1.0,
      "step": 2220
    },
    {
      "all_correct": 0.75,
      "all_wrong": 0.0,
      "completion_length": 406.53125,
      "epoch": 0.030634060219859035,
      "grad_norm": 2.368408251382291,
      "kl": 0.078125,
      "learning_rate": 9.976862648436918e-07,
      "loss": 0.0031,
      "reward": 2.051968812942505,
      "reward_std": 0.007895168848335743,
      "rewards/accuracy_reward": 0.8519687056541443,
      "rewards/format_reward": 1.0,
      "step": 2221
    },
    {
      "all_correct": 1.0,
      "all_wrong": 0.0,
      "completion_length": 398.46875,
      "epoch": 0.030647853133060232,
      "grad_norm": 2.4682423594997713,
      "kl": 0.0791015625,
      "learning_rate": 9.976841824772694e-07,
      "loss": 0.0032,
      "reward": 2.1348438262939453,
      "reward_std": 0.00763288140296936,
      "rewards/accuracy_reward": 0.9348437786102295,
      "rewards/format_reward": 1.0,
      "step": 2222
    },
    {
      "all_correct": 0.75,
      "all_wrong": 0.0,
      "completion_length": 404.0625,
      "epoch": 0.03066164604626143,
      "grad_norm": 3.1077677241072155,
      "kl": 0.068359375,
      "learning_rate": 9.976820991763766e-07,
      "loss": 0.0027,
      "reward": 2.095749855041504,
      "reward_std": 0.026015982031822205,
      "rewards/accuracy_reward": 0.8957499861717224,
      "rewards/format_reward": 1.0,
      "step": 2223
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.0,
      "completion_length": 408.21875,
      "epoch": 0.030675438959462627,
      "grad_norm": 2.4017392972771825,
      "kl": 0.06884765625,
      "learning_rate": 9.97680014941017e-07,
      "loss": 0.0028,
      "reward": 2.0806875228881836,
      "reward_std": 0.011542889289557934,
      "rewards/accuracy_reward": 0.8806875348091125,
      "rewards/format_reward": 1.0,
      "step": 2224
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.0,
      "completion_length": 392.375,
      "epoch": 0.030689231872663824,
      "grad_norm": 2.5235671917056672,
      "kl": 0.07568359375,
      "learning_rate": 9.97677929771195e-07,
      "loss": 0.003,
      "reward": 2.0131564140319824,
      "reward_std": 0.03558385372161865,
      "rewards/accuracy_reward": 0.819406270980835,
      "rewards/format_reward": 1.0,
      "step": 2225
    },
    {
      "all_correct": 1.0,
      "all_wrong": 0.0,
      "completion_length": 392.125,
      "epoch": 0.03070302478586502,
      "grad_norm": 2.93808277386678,
      "kl": 0.0771484375,
      "learning_rate": 9.976758436669143e-07,
      "loss": 0.0031,
      "reward": 2.1344687938690186,
      "reward_std": 0.024807695299386978,
      "rewards/accuracy_reward": 0.9344688057899475,
      "rewards/format_reward": 1.0,
      "step": 2226
    },
    {
      "all_correct": 1.0,
      "all_wrong": 0.0,
      "completion_length": 379.4375,
      "epoch": 0.03071681769906622,
      "grad_norm": 2.971829394095093,
      "kl": 0.07568359375,
      "learning_rate": 9.976737566281786e-07,
      "loss": 0.003,
      "reward": 2.14634370803833,
      "reward_std": 0.019381701946258545,
      "rewards/accuracy_reward": 0.9463437795639038,
      "rewards/format_reward": 1.0,
      "step": 2227
    },
    {
      "all_correct": 0.75,
      "all_wrong": 0.0,
      "completion_length": 372.09375,
      "epoch": 0.030730610612267416,
      "grad_norm": 1.827691353414307,
      "kl": 0.08349609375,
      "learning_rate": 9.97671668654992e-07,
      "loss": 0.0033,
      "reward": 2.1275625228881836,
      "reward_std": 0.029285648837685585,
      "rewards/accuracy_reward": 0.9338124990463257,
      "rewards/format_reward": 1.0,
      "step": 2228
    },
    {
      "all_correct": 1.0,
      "all_wrong": 0.0,
      "completion_length": 388.3125,
      "epoch": 0.030744403525468613,
      "grad_norm": 5.5095614586256465,
      "kl": 0.07666015625,
      "learning_rate": 9.976695797473586e-07,
      "loss": 0.0031,
      "reward": 2.1415624618530273,
      "reward_std": 0.02668778970837593,
      "rewards/accuracy_reward": 0.9415625333786011,
      "rewards/format_reward": 1.0,
      "step": 2229
    },
    {
      "all_correct": 0.75,
      "all_wrong": 0.0,
      "completion_length": 389.1875,
      "epoch": 0.03075819643866981,
      "grad_norm": 3.7832720213875586,
      "kl": 0.0693359375,
      "learning_rate": 9.97667489905282e-07,
      "loss": 0.0028,
      "reward": 2.133625030517578,
      "reward_std": 0.025699052959680557,
      "rewards/accuracy_reward": 0.9336249828338623,
      "rewards/format_reward": 1.0,
      "step": 2230
    },
    {
      "all_correct": 0.75,
      "all_wrong": 0.0,
      "completion_length": 384.21875,
      "epoch": 0.030771989351871008,
      "grad_norm": 8.392595456984209,
      "kl": 0.0830078125,
      "learning_rate": 9.976653991287663e-07,
      "loss": 0.0033,
      "reward": 2.135312557220459,
      "reward_std": 0.015526149421930313,
      "rewards/accuracy_reward": 0.9353125095367432,
      "rewards/format_reward": 1.0,
      "step": 2231
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.0,
      "completion_length": 375.34375,
      "epoch": 0.030785782265072205,
      "grad_norm": 2.6724588859096636,
      "kl": 0.08544921875,
      "learning_rate": 9.97663307417815e-07,
      "loss": 0.0034,
      "reward": 2.0517501831054688,
      "reward_std": 0.024781785905361176,
      "rewards/accuracy_reward": 0.8579999804496765,
      "rewards/format_reward": 1.0,
      "step": 2232
    },
    {
      "all_correct": 0.75,
      "all_wrong": 0.0,
      "completion_length": 375.1875,
      "epoch": 0.030799575178273402,
      "grad_norm": 11.327668111461566,
      "kl": 0.08251953125,
      "learning_rate": 9.97661214772433e-07,
      "loss": 0.0033,
      "reward": 2.1013126373291016,
      "reward_std": 0.01635340228676796,
      "rewards/accuracy_reward": 0.901312530040741,
      "rewards/format_reward": 1.0,
      "step": 2233
    },
    {
      "all_correct": 0.75,
      "all_wrong": 0.0,
      "completion_length": 365.90625,
      "epoch": 0.0308133680914746,
      "grad_norm": 2.1384325780673823,
      "kl": 0.0830078125,
      "learning_rate": 9.976591211926234e-07,
      "loss": 0.0033,
      "reward": 2.0364062786102295,
      "reward_std": 0.009607749991118908,
      "rewards/accuracy_reward": 0.8364062309265137,
      "rewards/format_reward": 1.0,
      "step": 2234
    },
    {
      "all_correct": 0.75,
      "all_wrong": 0.0,
      "completion_length": 383.46875,
      "epoch": 0.030827161004675797,
      "grad_norm": 2.204461990673804,
      "kl": 0.07275390625,
      "learning_rate": 9.976570266783903e-07,
      "loss": 0.0029,
      "reward": 2.124406337738037,
      "reward_std": 0.022497011348605156,
      "rewards/accuracy_reward": 0.9244062304496765,
      "rewards/format_reward": 1.0,
      "step": 2235
    },
    {
      "all_correct": 1.0,
      "all_wrong": 0.0,
      "completion_length": 367.84375,
      "epoch": 0.030840953917876994,
      "grad_norm": 2.7644044618056487,
      "kl": 0.07763671875,
      "learning_rate": 9.976549312297377e-07,
      "loss": 0.0031,
      "reward": 2.158937454223633,
      "reward_std": 0.014448843896389008,
      "rewards/accuracy_reward": 0.9589375257492065,
      "rewards/format_reward": 1.0,
      "step": 2236
    },
    {
      "all_correct": 0.75,
      "all_wrong": 0.0,
      "completion_length": 379.28125,
      "epoch": 0.03085474683107819,
      "grad_norm": 3.145633406695606,
      "kl": 0.0849609375,
      "learning_rate": 9.976528348466696e-07,
      "loss": 0.0034,
      "reward": 2.080718755722046,
      "reward_std": 0.013893071562051773,
      "rewards/accuracy_reward": 0.8807187080383301,
      "rewards/format_reward": 1.0,
      "step": 2237
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.0,
      "completion_length": 361.96875,
      "epoch": 0.03086853974427939,
      "grad_norm": 2.4205322345880638,
      "kl": 0.07958984375,
      "learning_rate": 9.976507375291899e-07,
      "loss": 0.0032,
      "reward": 2.1183125972747803,
      "reward_std": 0.04246281832456589,
      "rewards/accuracy_reward": 0.9308124780654907,
      "rewards/format_reward": 1.0,
      "step": 2238
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.0,
      "completion_length": 360.90625,
      "epoch": 0.030882332657480586,
      "grad_norm": 2.844281725485797,
      "kl": 0.08154296875,
      "learning_rate": 9.976486392773024e-07,
      "loss": 0.0032,
      "reward": 2.0728437900543213,
      "reward_std": 0.016438495367765427,
      "rewards/accuracy_reward": 0.8728438019752502,
      "rewards/format_reward": 1.0,
      "step": 2239
    },
    {
      "all_correct": 0.75,
      "all_wrong": 0.0,
      "completion_length": 367.5625,
      "epoch": 0.030896125570681783,
      "grad_norm": 4.621018941936662,
      "kl": 0.06982421875,
      "learning_rate": 9.976465400910112e-07,
      "loss": 0.0028,
      "reward": 2.077125072479248,
      "reward_std": 0.01715395227074623,
      "rewards/accuracy_reward": 0.877125084400177,
      "rewards/format_reward": 1.0,
      "step": 2240
    },
    {
      "all_correct": 0.75,
      "all_wrong": 0.0,
      "completion_length": 366.59375,
      "epoch": 0.03090991848388298,
      "grad_norm": 2.0577509061327426,
      "kl": 0.08056640625,
      "learning_rate": 9.9764443997032e-07,
      "loss": 0.0032,
      "reward": 2.1116561889648438,
      "reward_std": 0.02548736147582531,
      "rewards/accuracy_reward": 0.9241563081741333,
      "rewards/format_reward": 1.0,
      "step": 2241
    },
    {
      "all_correct": 0.75,
      "all_wrong": 0.0,
      "completion_length": 357.84375,
      "epoch": 0.030923711397084178,
      "grad_norm": 22.744508980270847,
      "kl": 0.0810546875,
      "learning_rate": 9.976423389152333e-07,
      "loss": 0.0033,
      "reward": 2.129218816757202,
      "reward_std": 0.04335203766822815,
      "rewards/accuracy_reward": 0.9479687213897705,
      "rewards/format_reward": 1.0,
      "step": 2242
    },
    {
      "all_correct": 0.75,
      "all_wrong": 0.0,
      "completion_length": 381.0,
      "epoch": 0.030937504310285375,
      "grad_norm": 2.963337044240746,
      "kl": 0.0712890625,
      "learning_rate": 9.976402369257545e-07,
      "loss": 0.0028,
      "reward": 2.128093719482422,
      "reward_std": 0.03770013526082039,
      "rewards/accuracy_reward": 0.9405937194824219,
      "rewards/format_reward": 1.0,
      "step": 2243
    },
    {
      "all_correct": 0.75,
      "all_wrong": 0.0,
      "completion_length": 359.25,
      "epoch": 0.030951297223486572,
      "grad_norm": 2.6960204318314487,
      "kl": 0.08251953125,
      "learning_rate": 9.976381340018879e-07,
      "loss": 0.0033,
      "reward": 2.1100311279296875,
      "reward_std": 0.04551228880882263,
      "rewards/accuracy_reward": 0.928781270980835,
      "rewards/format_reward": 1.0,
      "step": 2244
    },
    {
      "all_correct": 0.75,
      "all_wrong": 0.0,
      "completion_length": 370.625,
      "epoch": 0.03096509013668777,
      "grad_norm": 8.652480811834844,
      "kl": 0.08056640625,
      "learning_rate": 9.976360301436371e-07,
      "loss": 0.0032,
      "reward": 2.0601563453674316,
      "reward_std": 0.03214862942695618,
      "rewards/accuracy_reward": 0.860156238079071,
      "rewards/format_reward": 1.0,
      "step": 2245
    },
    {
      "all_correct": 0.75,
      "all_wrong": 0.0,
      "completion_length": 375.9375,
      "epoch": 0.030978883049888967,
      "grad_norm": 5.692512028898535,
      "kl": 0.0791015625,
      "learning_rate": 9.976339253510061e-07,
      "loss": 0.0032,
      "reward": 2.0611562728881836,
      "reward_std": 0.018124910071492195,
      "rewards/accuracy_reward": 0.8611562252044678,
      "rewards/format_reward": 1.0,
      "step": 2246
    },
    {
      "all_correct": 1.0,
      "all_wrong": 0.0,
      "completion_length": 382.8125,
      "epoch": 0.030992675963090164,
      "grad_norm": 2.8356484923369267,
      "kl": 0.0712890625,
      "learning_rate": 9.976318196239993e-07,
      "loss": 0.0029,
      "reward": 2.118000030517578,
      "reward_std": 0.021000022068619728,
      "rewards/accuracy_reward": 0.9180000424385071,
      "rewards/format_reward": 1.0,
      "step": 2247
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.0,
      "completion_length": 394.5,
      "epoch": 0.03100646887629136,
      "grad_norm": 1.9789276552945052,
      "kl": 0.07666015625,
      "learning_rate": 9.976297129626199e-07,
      "loss": 0.0031,
      "reward": 2.0753750801086426,
      "reward_std": 0.02469100058078766,
      "rewards/accuracy_reward": 0.8816250562667847,
      "rewards/format_reward": 1.0,
      "step": 2248
    },
    {
      "all_correct": 0.75,
      "all_wrong": 0.0,
      "completion_length": 385.5,
      "epoch": 0.03102026178949256,
      "grad_norm": 2.752123285315237,
      "kl": 0.07763671875,
      "learning_rate": 9.976276053668727e-07,
      "loss": 0.0031,
      "reward": 2.0533127784729004,
      "reward_std": 0.02811865136027336,
      "rewards/accuracy_reward": 0.8595624566078186,
      "rewards/format_reward": 1.0,
      "step": 2249
    },
    {
      "all_correct": 0.75,
      "all_wrong": 0.0,
      "completion_length": 386.0625,
      "epoch": 0.031034054702693756,
      "grad_norm": 1.968964903946242,
      "kl": 0.08154296875,
      "learning_rate": 9.97625496836761e-07,
      "loss": 0.0033,
      "reward": 2.125124931335449,
      "reward_std": 0.02524317428469658,
      "rewards/accuracy_reward": 0.9313750267028809,
      "rewards/format_reward": 1.0,
      "step": 2250
    },
    {
      "all_correct": 0.75,
      "all_wrong": 0.0,
      "completion_length": 395.9375,
      "epoch": 0.031047847615894953,
      "grad_norm": 1.8646218285651153,
      "kl": 0.076171875,
      "learning_rate": 9.976233873722892e-07,
      "loss": 0.003,
      "reward": 2.0802500247955322,
      "reward_std": 0.00986083596944809,
      "rewards/accuracy_reward": 0.8802499771118164,
      "rewards/format_reward": 1.0,
      "step": 2251
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.0,
      "completion_length": 393.78125,
      "epoch": 0.03106164052909615,
      "grad_norm": 9.948187608748917,
      "kl": 0.07080078125,
      "learning_rate": 9.97621276973461e-07,
      "loss": 0.0028,
      "reward": 2.0847811698913574,
      "reward_std": 0.027061868458986282,
      "rewards/accuracy_reward": 0.8910312056541443,
      "rewards/format_reward": 1.0,
      "step": 2252
    },
    {
      "all_correct": 1.0,
      "all_wrong": 0.0,
      "completion_length": 387.1875,
      "epoch": 0.031075433442297348,
      "grad_norm": 3.724281014273633,
      "kl": 0.072265625,
      "learning_rate": 9.976191656402802e-07,
      "loss": 0.0029,
      "reward": 2.12918758392334,
      "reward_std": 0.017832955345511436,
      "rewards/accuracy_reward": 0.9291874766349792,
      "rewards/format_reward": 1.0,
      "step": 2253
    },
    {
      "all_correct": 1.0,
      "all_wrong": 0.0,
      "completion_length": 400.28125,
      "epoch": 0.031089226355498545,
      "grad_norm": 6.9227067913396585,
      "kl": 0.0771484375,
      "learning_rate": 9.976170533727514e-07,
      "loss": 0.0031,
      "reward": 2.1320314407348633,
      "reward_std": 0.01620614528656006,
      "rewards/accuracy_reward": 0.9320312142372131,
      "rewards/format_reward": 1.0,
      "step": 2254
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.0,
      "completion_length": 405.34375,
      "epoch": 0.031103019268699742,
      "grad_norm": 2.7375972952163607,
      "kl": 0.072265625,
      "learning_rate": 9.976149401708779e-07,
      "loss": 0.0029,
      "reward": 1.988968849182129,
      "reward_std": 0.103922039270401,
      "rewards/accuracy_reward": 0.8202187418937683,
      "rewards/format_reward": 0.96875,
      "step": 2255
    },
    {
      "all_correct": 0.75,
      "all_wrong": 0.0,
      "completion_length": 403.71875,
      "epoch": 0.03111681218190094,
      "grad_norm": 2.5645238861618904,
      "kl": 0.07421875,
      "learning_rate": 9.976128260346637e-07,
      "loss": 0.003,
      "reward": 2.0241875648498535,
      "reward_std": 0.020421762019395828,
      "rewards/accuracy_reward": 0.8241874575614929,
      "rewards/format_reward": 1.0,
      "step": 2256
    },
    {
      "all_correct": 1.0,
      "all_wrong": 0.0,
      "completion_length": 412.8125,
      "epoch": 0.031130605095102137,
      "grad_norm": 1.7731716261583952,
      "kl": 0.080078125,
      "learning_rate": 9.976107109641133e-07,
      "loss": 0.0032,
      "reward": 2.1723437309265137,
      "reward_std": 0.015186430886387825,
      "rewards/accuracy_reward": 0.9723437428474426,
      "rewards/format_reward": 1.0,
      "step": 2257
    },
    {
      "all_correct": 1.0,
      "all_wrong": 0.0,
      "completion_length": 393.8125,
      "epoch": 0.031144398008303334,
      "grad_norm": 7.339239918515213,
      "kl": 0.083984375,
      "learning_rate": 9.976085949592303e-07,
      "loss": 0.0034,
      "reward": 2.1562812328338623,
      "reward_std": 0.01189088262617588,
      "rewards/accuracy_reward": 0.956281304359436,
      "rewards/format_reward": 1.0,
      "step": 2258
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.0,
      "completion_length": 411.46875,
      "epoch": 0.03115819092150453,
      "grad_norm": 4.072541252752485,
      "kl": 0.07177734375,
      "learning_rate": 9.976064780200188e-07,
      "loss": 0.0029,
      "reward": 2.0021250247955322,
      "reward_std": 0.024898849427700043,
      "rewards/accuracy_reward": 0.8021249771118164,
      "rewards/format_reward": 1.0,
      "step": 2259
    },
    {
      "all_correct": 1.0,
      "all_wrong": 0.0,
      "completion_length": 398.1875,
      "epoch": 0.03117198383470573,
      "grad_norm": 2.2569326885036785,
      "kl": 0.0771484375,
      "learning_rate": 9.976043601464826e-07,
      "loss": 0.0031,
      "reward": 2.13462495803833,
      "reward_std": 0.020481616258621216,
      "rewards/accuracy_reward": 0.9346249103546143,
      "rewards/format_reward": 1.0,
      "step": 2260
    },
    {
      "all_correct": 0.75,
      "all_wrong": 0.0,
      "completion_length": 398.15625,
      "epoch": 0.031185776747906926,
      "grad_norm": 3.0491014954147397,
      "kl": 0.0810546875,
      "learning_rate": 9.97602241338626e-07,
      "loss": 0.0032,
      "reward": 2.0787811279296875,
      "reward_std": 0.01796579174697399,
      "rewards/accuracy_reward": 0.878781259059906,
      "rewards/format_reward": 1.0,
      "step": 2261
    },
    {
      "all_correct": 1.0,
      "all_wrong": 0.0,
      "completion_length": 403.25,
      "epoch": 0.031199569661108123,
      "grad_norm": 3.7707670295178732,
      "kl": 0.080078125,
      "learning_rate": 9.976001215964525e-07,
      "loss": 0.0032,
      "reward": 2.0914063453674316,
      "reward_std": 0.014145651832222939,
      "rewards/accuracy_reward": 0.891406238079071,
      "rewards/format_reward": 1.0,
      "step": 2262
    },
    {
      "all_correct": 1.0,
      "all_wrong": 0.0,
      "completion_length": 423.84375,
      "epoch": 0.03121336257430932,
      "grad_norm": 2.9659502647996336,
      "kl": 0.078125,
      "learning_rate": 9.975980009199664e-07,
      "loss": 0.0031,
      "reward": 2.1424999237060547,
      "reward_std": 0.02005607634782791,
      "rewards/accuracy_reward": 0.9424999356269836,
      "rewards/format_reward": 1.0,
      "step": 2263
    },
    {
      "all_correct": 1.0,
      "all_wrong": 0.0,
      "completion_length": 423.3125,
      "epoch": 0.031227155487510518,
      "grad_norm": 2.9546681724599595,
      "kl": 0.0908203125,
      "learning_rate": 9.975958793091719e-07,
      "loss": 0.0036,
      "reward": 2.0823750495910645,
      "reward_std": 0.014879917725920677,
      "rewards/accuracy_reward": 0.8823750019073486,
      "rewards/format_reward": 1.0,
      "step": 2264
    },
    {
      "all_correct": 1.0,
      "all_wrong": 0.0,
      "completion_length": 413.25,
      "epoch": 0.031240948400711715,
      "grad_norm": 12.737518251876528,
      "kl": 0.076171875,
      "learning_rate": 9.975937567640724e-07,
      "loss": 0.003,
      "reward": 2.1417813301086426,
      "reward_std": 0.019783347845077515,
      "rewards/accuracy_reward": 0.941781222820282,
      "rewards/format_reward": 1.0,
      "step": 2265
    },
    {
      "all_correct": 1.0,
      "all_wrong": 0.0,
      "completion_length": 414.6875,
      "epoch": 0.03125474131391291,
      "grad_norm": 5.537585660967187,
      "kl": 0.08251953125,
      "learning_rate": 9.975916332846723e-07,
      "loss": 0.0033,
      "reward": 2.128593683242798,
      "reward_std": 0.020362388342618942,
      "rewards/accuracy_reward": 0.9285937547683716,
      "rewards/format_reward": 1.0,
      "step": 2266
    },
    {
      "all_correct": 1.0,
      "all_wrong": 0.0,
      "completion_length": 411.15625,
      "epoch": 0.031268534227114106,
      "grad_norm": 1.8428683071500345,
      "kl": 0.08203125,
      "learning_rate": 9.975895088709756e-07,
      "loss": 0.0033,
      "reward": 2.1715002059936523,
      "reward_std": 0.011392639949917793,
      "rewards/accuracy_reward": 0.9714999794960022,
      "rewards/format_reward": 1.0,
      "step": 2267
    },
    {
      "all_correct": 0.75,
      "all_wrong": 0.0,
      "completion_length": 402.40625,
      "epoch": 0.03128232714031531,
      "grad_norm": 4.211057476053346,
      "kl": 0.0791015625,
      "learning_rate": 9.97587383522986e-07,
      "loss": 0.0032,
      "reward": 2.09556245803833,
      "reward_std": 0.02641196735203266,
      "rewards/accuracy_reward": 0.9018125534057617,
      "rewards/format_reward": 1.0,
      "step": 2268
    },
    {
      "all_correct": 0.75,
      "all_wrong": 0.0,
      "completion_length": 406.09375,
      "epoch": 0.0312961200535165,
      "grad_norm": 2.799815983078908,
      "kl": 0.0849609375,
      "learning_rate": 9.975852572407077e-07,
      "loss": 0.0034,
      "reward": 2.1171562671661377,
      "reward_std": 0.01794649288058281,
      "rewards/accuracy_reward": 0.9171561598777771,
      "rewards/format_reward": 1.0,
      "step": 2269
    },
    {
      "all_correct": 0.75,
      "all_wrong": 0.0,
      "completion_length": 414.59375,
      "epoch": 0.0313099129667177,
      "grad_norm": 2.665871421606478,
      "kl": 0.0869140625,
      "learning_rate": 9.975831300241447e-07,
      "loss": 0.0035,
      "reward": 2.097909450531006,
      "reward_std": 0.01113520935177803,
      "rewards/accuracy_reward": 0.89790940284729,
      "rewards/format_reward": 1.0,
      "step": 2270
    },
    {
      "all_correct": 0.75,
      "all_wrong": 0.0,
      "completion_length": 393.40625,
      "epoch": 0.031323705879918895,
      "grad_norm": 2.5675211108799796,
      "kl": 0.0810546875,
      "learning_rate": 9.975810018733011e-07,
      "loss": 0.0032,
      "reward": 2.088624954223633,
      "reward_std": 0.02920497953891754,
      "rewards/accuracy_reward": 0.8948750495910645,
      "rewards/format_reward": 1.0,
      "step": 2271
    },
    {
      "all_correct": 1.0,
      "all_wrong": 0.0,
      "completion_length": 401.65625,
      "epoch": 0.031337498793120096,
      "grad_norm": 3.8790258981998296,
      "kl": 0.0849609375,
      "learning_rate": 9.975788727881805e-07,
      "loss": 0.0034,
      "reward": 2.1497812271118164,
      "reward_std": 0.024576518684625626,
      "rewards/accuracy_reward": 0.9497812390327454,
      "rewards/format_reward": 1.0,
      "step": 2272
    },
    {
      "all_correct": 0.75,
      "all_wrong": 0.0,
      "completion_length": 393.25,
      "epoch": 0.03135129170632129,
      "grad_norm": 5.337841975385978,
      "kl": 0.08349609375,
      "learning_rate": 9.975767427687873e-07,
      "loss": 0.0033,
      "reward": 2.0717501640319824,
      "reward_std": 0.007796011865139008,
      "rewards/accuracy_reward": 0.8717499375343323,
      "rewards/format_reward": 1.0,
      "step": 2273
    },
    {
      "all_correct": 1.0,
      "all_wrong": 0.0,
      "completion_length": 391.125,
      "epoch": 0.03136508461952249,
      "grad_norm": 4.468961239105371,
      "kl": 0.07568359375,
      "learning_rate": 9.975746118151253e-07,
      "loss": 0.003,
      "reward": 2.0844998359680176,
      "reward_std": 0.007305807434022427,
      "rewards/accuracy_reward": 0.8844999670982361,
      "rewards/format_reward": 1.0,
      "step": 2274
    },
    {
      "all_correct": 1.0,
      "all_wrong": 0.0,
      "completion_length": 386.46875,
      "epoch": 0.031378877532723684,
      "grad_norm": 3.9144826966411412,
      "kl": 0.08154296875,
      "learning_rate": 9.975724799271985e-07,
      "loss": 0.0033,
      "reward": 2.139531135559082,
      "reward_std": 0.012412281706929207,
      "rewards/accuracy_reward": 0.9395312666893005,
      "rewards/format_reward": 1.0,
      "step": 2275
    },
    {
      "all_correct": 1.0,
      "all_wrong": 0.0,
      "completion_length": 395.9375,
      "epoch": 0.031392670445924885,
      "grad_norm": 2.247217390979363,
      "kl": 0.0849609375,
      "learning_rate": 9.97570347105011e-07,
      "loss": 0.0034,
      "reward": 2.1615939140319824,
      "reward_std": 0.020095108076930046,
      "rewards/accuracy_reward": 0.961593747138977,
      "rewards/format_reward": 1.0,
      "step": 2276
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.0,
      "completion_length": 394.15625,
      "epoch": 0.03140646335912608,
      "grad_norm": 6.598113178381127,
      "kl": 0.08984375,
      "learning_rate": 9.975682133485667e-07,
      "loss": 0.0036,
      "reward": 2.0371875762939453,
      "reward_std": 0.0338313914835453,
      "rewards/accuracy_reward": 0.8371874690055847,
      "rewards/format_reward": 1.0,
      "step": 2277
    },
    {
      "all_correct": 1.0,
      "all_wrong": 0.0,
      "completion_length": 387.3125,
      "epoch": 0.03142025627232728,
      "grad_norm": 2.0167431145717507,
      "kl": 0.083984375,
      "learning_rate": 9.975660786578697e-07,
      "loss": 0.0034,
      "reward": 2.1931562423706055,
      "reward_std": 0.016381051391363144,
      "rewards/accuracy_reward": 0.9931561946868896,
      "rewards/format_reward": 1.0,
      "step": 2278
    },
    {
      "all_correct": 1.0,
      "all_wrong": 0.0,
      "completion_length": 398.5625,
      "epoch": 0.03143404918552847,
      "grad_norm": 2.705724921182165,
      "kl": 0.0830078125,
      "learning_rate": 9.975639430329241e-07,
      "loss": 0.0033,
      "reward": 2.1126561164855957,
      "reward_std": 0.011554856784641743,
      "rewards/accuracy_reward": 0.912656307220459,
      "rewards/format_reward": 1.0,
      "step": 2279
    },
    {
      "all_correct": 1.0,
      "all_wrong": 0.0,
      "completion_length": 391.28125,
      "epoch": 0.031447842098729674,
      "grad_norm": 2.268176490866149,
      "kl": 0.08740234375,
      "learning_rate": 9.975618064737336e-07,
      "loss": 0.0035,
      "reward": 2.15596866607666,
      "reward_std": 0.02884788066148758,
      "rewards/accuracy_reward": 0.9559687376022339,
      "rewards/format_reward": 1.0,
      "step": 2280
    },
    {
      "all_correct": 0.75,
      "all_wrong": 0.0,
      "completion_length": 376.875,
      "epoch": 0.03146163501193087,
      "grad_norm": 4.933171101868903,
      "kl": 0.07177734375,
      "learning_rate": 9.975596689803024e-07,
      "loss": 0.0029,
      "reward": 2.1358752250671387,
      "reward_std": 0.026951689273118973,
      "rewards/accuracy_reward": 0.9421250224113464,
      "rewards/format_reward": 1.0,
      "step": 2281
    },
    {
      "all_correct": 1.0,
      "all_wrong": 0.0,
      "completion_length": 387.6875,
      "epoch": 0.03147542792513207,
      "grad_norm": 3.983475689175812,
      "kl": 0.08251953125,
      "learning_rate": 9.975575305526347e-07,
      "loss": 0.0033,
      "reward": 2.136812448501587,
      "reward_std": 0.020964784547686577,
      "rewards/accuracy_reward": 0.9368124604225159,
      "rewards/format_reward": 1.0,
      "step": 2282
    },
    {
      "all_correct": 0.75,
      "all_wrong": 0.0,
      "completion_length": 377.96875,
      "epoch": 0.03148922083833326,
      "grad_norm": 2.3215301439483107,
      "kl": 0.0966796875,
      "learning_rate": 9.975553911907339e-07,
      "loss": 0.0039,
      "reward": 2.1399688720703125,
      "reward_std": 0.02450164407491684,
      "rewards/accuracy_reward": 0.9462187886238098,
      "rewards/format_reward": 1.0,
      "step": 2283
    },
    {
      "all_correct": 0.75,
      "all_wrong": 0.0,
      "completion_length": 394.78125,
      "epoch": 0.03150301375153446,
      "grad_norm": 2.3094136694587806,
      "kl": 0.083984375,
      "learning_rate": 9.975532508946049e-07,
      "loss": 0.0034,
      "reward": 2.033656358718872,
      "reward_std": 0.0077733565121889114,
      "rewards/accuracy_reward": 0.8336561918258667,
      "rewards/format_reward": 1.0,
      "step": 2284
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.0,
      "completion_length": 385.34375,
      "epoch": 0.03151680666473566,
      "grad_norm": 3.0665324707304458,
      "kl": 0.087890625,
      "learning_rate": 9.97551109664251e-07,
      "loss": 0.0035,
      "reward": 2.1108436584472656,
      "reward_std": 0.028609005734324455,
      "rewards/accuracy_reward": 0.9170937538146973,
      "rewards/format_reward": 1.0,
      "step": 2285
    },
    {
      "all_correct": 0.75,
      "all_wrong": 0.0,
      "completion_length": 393.75,
      "epoch": 0.03153059957793686,
      "grad_norm": 2.2930623873016764,
      "kl": 0.08154296875,
      "learning_rate": 9.975489674996766e-07,
      "loss": 0.0033,
      "reward": 2.0263748168945312,
      "reward_std": 0.03337153419852257,
      "rewards/accuracy_reward": 0.8263750076293945,
      "rewards/format_reward": 1.0,
      "step": 2286
    },
    {
      "all_correct": 1.0,
      "all_wrong": 0.0,
      "completion_length": 394.0,
      "epoch": 0.03154439249113805,
      "grad_norm": 2.9391900907343995,
      "kl": 0.07763671875,
      "learning_rate": 9.975468244008854e-07,
      "loss": 0.0031,
      "reward": 2.142878293991089,
      "reward_std": 0.011515817604959011,
      "rewards/accuracy_reward": 0.9428781270980835,
      "rewards/format_reward": 1.0,
      "step": 2287
    },
    {
      "all_correct": 0.25,
      "all_wrong": 0.0,
      "completion_length": 393.9375,
      "epoch": 0.03155818540433925,
      "grad_norm": 3.6925777305986007,
      "kl": 0.08984375,
      "learning_rate": 9.975446803678817e-07,
      "loss": 0.0036,
      "reward": 2.0121874809265137,
      "reward_std": 0.019458185881376266,
      "rewards/accuracy_reward": 0.8121875524520874,
      "rewards/format_reward": 1.0,
      "step": 2288
    },
    {
      "all_correct": 1.0,
      "all_wrong": 0.0,
      "completion_length": 385.25,
      "epoch": 0.031571978317540446,
      "grad_norm": 2.4090613635973765,
      "kl": 0.08447265625,
      "learning_rate": 9.975425354006697e-07,
      "loss": 0.0034,
      "reward": 2.1460626125335693,
      "reward_std": 0.008709149435162544,
      "rewards/accuracy_reward": 0.9460625648498535,
      "rewards/format_reward": 1.0,
      "step": 2289
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.0,
      "completion_length": 375.46875,
      "epoch": 0.03158577123074165,
      "grad_norm": 2.1557699965981576,
      "kl": 0.1025390625,
      "learning_rate": 9.97540389499253e-07,
      "loss": 0.0041,
      "reward": 2.096531391143799,
      "reward_std": 0.04128604754805565,
      "rewards/accuracy_reward": 0.9090312719345093,
      "rewards/format_reward": 1.0,
      "step": 2290
    },
    {
      "all_correct": 0.75,
      "all_wrong": 0.0,
      "completion_length": 388.875,
      "epoch": 0.03159956414394284,
      "grad_norm": 2.2462730791901215,
      "kl": 0.09130859375,
      "learning_rate": 9.975382426636357e-07,
      "loss": 0.0036,
      "reward": 2.17396879196167,
      "reward_std": 0.03342505171895027,
      "rewards/accuracy_reward": 0.9802187085151672,
      "rewards/format_reward": 1.0,
      "step": 2291
    },
    {
      "all_correct": 0.75,
      "all_wrong": 0.0,
      "completion_length": 391.15625,
      "epoch": 0.03161335705714404,
      "grad_norm": 3.416497516962503,
      "kl": 0.08984375,
      "learning_rate": 9.97536094893822e-07,
      "loss": 0.0036,
      "reward": 2.104281187057495,
      "reward_std": 0.013790383003652096,
      "rewards/accuracy_reward": 0.9042812585830688,
      "rewards/format_reward": 1.0,
      "step": 2292
    },
    {
      "all_correct": 0.75,
      "all_wrong": 0.0,
      "completion_length": 375.5,
      "epoch": 0.031627149970345235,
      "grad_norm": 1.1200499903122947,
      "kl": 0.08203125,
      "learning_rate": 9.97533946189816e-07,
      "loss": 0.0033,
      "reward": 2.054093837738037,
      "reward_std": 0.0027220644988119602,
      "rewards/accuracy_reward": 0.8540937900543213,
      "rewards/format_reward": 1.0,
      "step": 2293
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.0,
      "completion_length": 385.96875,
      "epoch": 0.031640942883546436,
      "grad_norm": 3.1924813112400607,
      "kl": 0.08984375,
      "learning_rate": 9.975317965516214e-07,
      "loss": 0.0036,
      "reward": 2.1097187995910645,
      "reward_std": 0.02264920435845852,
      "rewards/accuracy_reward": 0.9097187519073486,
      "rewards/format_reward": 1.0,
      "step": 2294
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.0,
      "completion_length": 377.3125,
      "epoch": 0.03165473579674763,
      "grad_norm": 10.921711478924543,
      "kl": 0.0830078125,
      "learning_rate": 9.975296459792426e-07,
      "loss": 0.0033,
      "reward": 2.0443124771118164,
      "reward_std": 0.038417719304561615,
      "rewards/accuracy_reward": 0.8505625128746033,
      "rewards/format_reward": 1.0,
      "step": 2295
    },
    {
      "all_correct": 0.75,
      "all_wrong": 0.0,
      "completion_length": 393.03125,
      "epoch": 0.03166852870994883,
      "grad_norm": 3.3469008903065585,
      "kl": 0.09326171875,
      "learning_rate": 9.975274944726833e-07,
      "loss": 0.0037,
      "reward": 2.1206250190734863,
      "reward_std": 0.03464517369866371,
      "rewards/accuracy_reward": 0.9268749952316284,
      "rewards/format_reward": 1.0,
      "step": 2296
    },
    {
      "all_correct": 1.0,
      "all_wrong": 0.0,
      "completion_length": 386.40625,
      "epoch": 0.031682321623150024,
      "grad_norm": 2.8791720241301464,
      "kl": 0.0869140625,
      "learning_rate": 9.975253420319478e-07,
      "loss": 0.0035,
      "reward": 2.121906280517578,
      "reward_std": 0.030730130150914192,
      "rewards/accuracy_reward": 0.9281561970710754,
      "rewards/format_reward": 1.0,
      "step": 2297
    },
    {
      "all_correct": 1.0,
      "all_wrong": 0.0,
      "completion_length": 388.75,
      "epoch": 0.031696114536351225,
      "grad_norm": 2.625697759684863,
      "kl": 0.083984375,
      "learning_rate": 9.9752318865704e-07,
      "loss": 0.0033,
      "reward": 2.1727187633514404,
      "reward_std": 0.008489701896905899,
      "rewards/accuracy_reward": 0.9727187156677246,
      "rewards/format_reward": 1.0,
      "step": 2298
    },
    {
      "all_correct": 1.0,
      "all_wrong": 0.0,
      "completion_length": 397.1875,
      "epoch": 0.03170990744955242,
      "grad_norm": 1.9962552325377538,
      "kl": 0.0703125,
      "learning_rate": 9.975210343479641e-07,
      "loss": 0.0028,
      "reward": 2.1116561889648438,
      "reward_std": 0.012254114262759686,
      "rewards/accuracy_reward": 0.9116562008857727,
      "rewards/format_reward": 1.0,
      "step": 2299
    },
    {
      "all_correct": 0.75,
      "all_wrong": 0.0,
      "completion_length": 389.71875,
      "epoch": 0.03172370036275362,
      "grad_norm": 3.357955183820964,
      "kl": 0.07568359375,
      "learning_rate": 9.975188791047241e-07,
      "loss": 0.003,
      "reward": 2.112656354904175,
      "reward_std": 0.0253610797226429,
      "rewards/accuracy_reward": 0.9126561880111694,
      "rewards/format_reward": 1.0,
      "step": 2300
    },
    {
      "all_correct": 0.75,
      "all_wrong": 0.0,
      "completion_length": 387.1875,
      "epoch": 0.03173749327595481,
      "grad_norm": 3.1984752760470614,
      "kl": 0.08984375,
      "learning_rate": 9.97516722927324e-07,
      "loss": 0.0036,
      "reward": 2.0823750495910645,
      "reward_std": 0.023001380264759064,
      "rewards/accuracy_reward": 0.8823750019073486,
      "rewards/format_reward": 1.0,
      "step": 2301
    },
    {
      "all_correct": 1.0,
      "all_wrong": 0.0,
      "completion_length": 381.15625,
      "epoch": 0.031751286189156014,
      "grad_norm": 9.980481463749479,
      "kl": 0.07958984375,
      "learning_rate": 9.975145658157677e-07,
      "loss": 0.0032,
      "reward": 2.1624999046325684,
      "reward_std": 0.00814671441912651,
      "rewards/accuracy_reward": 0.9624999761581421,
      "rewards/format_reward": 1.0,
      "step": 2302
    },
    {
      "all_correct": 1.0,
      "all_wrong": 0.0,
      "completion_length": 388.875,
      "epoch": 0.03176507910235721,
      "grad_norm": 2.4775649729432954,
      "kl": 0.08837890625,
      "learning_rate": 9.975124077700594e-07,
      "loss": 0.0035,
      "reward": 2.1408438682556152,
      "reward_std": 0.026987893506884575,
      "rewards/accuracy_reward": 0.9470937848091125,
      "rewards/format_reward": 1.0,
      "step": 2303
    },
    {
      "all_correct": 1.0,
      "all_wrong": 0.0,
      "completion_length": 391.84375,
      "epoch": 0.03177887201555841,
      "grad_norm": 2.6106013584134726,
      "kl": 0.078125,
      "learning_rate": 9.975102487902033e-07,
      "loss": 0.0031,
      "reward": 2.103562355041504,
      "reward_std": 0.010480975732207298,
      "rewards/accuracy_reward": 0.9035625457763672,
      "rewards/format_reward": 1.0,
      "step": 2304
    },
    {
      "all_correct": 1.0,
      "all_wrong": 0.0,
      "completion_length": 397.28125,
      "epoch": 0.0317926649287596,
      "grad_norm": 2.739984500849049,
      "kl": 0.068359375,
      "learning_rate": 9.975080888762032e-07,
      "loss": 0.0028,
      "reward": 2.146937608718872,
      "reward_std": 0.009717043489217758,
      "rewards/accuracy_reward": 0.9469375014305115,
      "rewards/format_reward": 1.0,
      "step": 2305
    },
    {
      "all_correct": 0.75,
      "all_wrong": 0.0,
      "completion_length": 392.90625,
      "epoch": 0.0318064578419608,
      "grad_norm": 2.6073931429806425,
      "kl": 0.0751953125,
      "learning_rate": 9.975059280280631e-07,
      "loss": 0.003,
      "reward": 2.1352500915527344,
      "reward_std": 0.024324417114257812,
      "rewards/accuracy_reward": 0.9415000677108765,
      "rewards/format_reward": 1.0,
      "step": 2306
    },
    {
      "all_correct": 1.0,
      "all_wrong": 0.0,
      "completion_length": 394.90625,
      "epoch": 0.031820250755162,
      "grad_norm": 2.8339642457462753,
      "kl": 0.08740234375,
      "learning_rate": 9.975037662457874e-07,
      "loss": 0.0035,
      "reward": 2.108250141143799,
      "reward_std": 0.016800247132778168,
      "rewards/accuracy_reward": 0.9082499742507935,
      "rewards/format_reward": 1.0,
      "step": 2307
    },
    {
      "all_correct": 0.75,
      "all_wrong": 0.0,
      "completion_length": 394.0625,
      "epoch": 0.0318340436683632,
      "grad_norm": 2.544390784965393,
      "kl": 0.08251953125,
      "learning_rate": 9.975016035293799e-07,
      "loss": 0.0033,
      "reward": 2.1215624809265137,
      "reward_std": 0.029493363574147224,
      "rewards/accuracy_reward": 0.9215625524520874,
      "rewards/format_reward": 1.0,
      "step": 2308
    },
    {
      "all_correct": 0.75,
      "all_wrong": 0.0,
      "completion_length": 389.96875,
      "epoch": 0.03184783658156439,
      "grad_norm": 2.2567491718429893,
      "kl": 0.078125,
      "learning_rate": 9.974994398788447e-07,
      "loss": 0.0031,
      "reward": 2.0270938873291016,
      "reward_std": 0.009944726713001728,
      "rewards/accuracy_reward": 0.827093780040741,
      "rewards/format_reward": 1.0,
      "step": 2309
    },
    {
      "all_correct": 0.75,
      "all_wrong": 0.0,
      "completion_length": 389.03125,
      "epoch": 0.03186162949476559,
      "grad_norm": 2.154549945332516,
      "kl": 0.078125,
      "learning_rate": 9.97497275294186e-07,
      "loss": 0.0031,
      "reward": 2.0022501945495605,
      "reward_std": 0.017113225534558296,
      "rewards/accuracy_reward": 0.8022500872612,
      "rewards/format_reward": 1.0,
      "step": 2310
    },
    {
      "all_correct": 0.75,
      "all_wrong": 0.0,
      "completion_length": 397.84375,
      "epoch": 0.031875422407966786,
      "grad_norm": 2.058418541848099,
      "kl": 0.080078125,
      "learning_rate": 9.974951097754075e-07,
      "loss": 0.0032,
      "reward": 2.1064376831054688,
      "reward_std": 0.004897836595773697,
      "rewards/accuracy_reward": 0.9064375162124634,
      "rewards/format_reward": 1.0,
      "step": 2311
    },
    {
      "all_correct": 0.75,
      "all_wrong": 0.0,
      "completion_length": 407.25,
      "epoch": 0.03188921532116799,
      "grad_norm": 9.32905612836491,
      "kl": 0.0751953125,
      "learning_rate": 9.974929433225138e-07,
      "loss": 0.0029,
      "reward": 2.0581769943237305,
      "reward_std": 0.013685942627489567,
      "rewards/accuracy_reward": 0.858177125453949,
      "rewards/format_reward": 1.0,
      "step": 2312
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.0,
      "completion_length": 405.40625,
      "epoch": 0.03190300823436918,
      "grad_norm": 2.8502713062155256,
      "kl": 0.0771484375,
      "learning_rate": 9.974907759355086e-07,
      "loss": 0.0031,
      "reward": 1.98046875,
      "reward_std": 0.015279257670044899,
      "rewards/accuracy_reward": 0.780468761920929,
      "rewards/format_reward": 1.0,
      "step": 2313
    },
    {
      "all_correct": 0.75,
      "all_wrong": 0.0,
      "completion_length": 407.34375,
      "epoch": 0.03191680114757038,
      "grad_norm": 3.855142522539016,
      "kl": 0.0869140625,
      "learning_rate": 9.974886076143962e-07,
      "loss": 0.0035,
      "reward": 2.1050000190734863,
      "reward_std": 0.019919203594326973,
      "rewards/accuracy_reward": 0.9049999713897705,
      "rewards/format_reward": 1.0,
      "step": 2314
    },
    {
      "all_correct": 1.0,
      "all_wrong": 0.0,
      "completion_length": 396.3125,
      "epoch": 0.031930594060771575,
      "grad_norm": 2.362971603615965,
      "kl": 0.0732421875,
      "learning_rate": 9.974864383591804e-07,
      "loss": 0.0029,
      "reward": 2.1367406845092773,
      "reward_std": 0.009053431451320648,
      "rewards/accuracy_reward": 0.936740517616272,
      "rewards/format_reward": 1.0,
      "step": 2315
    },
    {
      "all_correct": 0.75,
      "all_wrong": 0.0,
      "completion_length": 402.625,
      "epoch": 0.031944386973972776,
      "grad_norm": 2.5169657865996067,
      "kl": 0.0859375,
      "learning_rate": 9.974842681698653e-07,
      "loss": 0.0034,
      "reward": 2.120513677597046,
      "reward_std": 0.011337135918438435,
      "rewards/accuracy_reward": 0.9205137491226196,
      "rewards/format_reward": 1.0,
      "step": 2316
    },
    {
      "all_correct": 1.0,
      "all_wrong": 0.0,
      "completion_length": 410.375,
      "epoch": 0.03195817988717397,
      "grad_norm": 1.4191570126918736,
      "kl": 0.07373046875,
      "learning_rate": 9.974820970464552e-07,
      "loss": 0.003,
      "reward": 2.1772499084472656,
      "reward_std": 0.008732639253139496,
      "rewards/accuracy_reward": 0.9772499799728394,
      "rewards/format_reward": 1.0,
      "step": 2317
    },
    {
      "all_correct": 0.75,
      "all_wrong": 0.0,
      "completion_length": 413.53125,
      "epoch": 0.03197197280037517,
      "grad_norm": 4.580004600703628,
      "kl": 0.07275390625,
      "learning_rate": 9.974799249889542e-07,
      "loss": 0.0029,
      "reward": 2.0073437690734863,
      "reward_std": 0.027227478101849556,
      "rewards/accuracy_reward": 0.8073437809944153,
      "rewards/format_reward": 1.0,
      "step": 2318
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.0,
      "completion_length": 409.9375,
      "epoch": 0.031985765713576364,
      "grad_norm": 4.324348257257624,
      "kl": 0.0810546875,
      "learning_rate": 9.97477751997366e-07,
      "loss": 0.0032,
      "reward": 2.0601563453674316,
      "reward_std": 0.012123478576540947,
      "rewards/accuracy_reward": 0.860156238079071,
      "rewards/format_reward": 1.0,
      "step": 2319
    },
    {
      "all_correct": 0.75,
      "all_wrong": 0.0,
      "completion_length": 406.9375,
      "epoch": 0.031999558626777565,
      "grad_norm": 2.4815305147866518,
      "kl": 0.0771484375,
      "learning_rate": 9.97475578071695e-07,
      "loss": 0.0031,
      "reward": 2.128218650817871,
      "reward_std": 0.007847452536225319,
      "rewards/accuracy_reward": 0.9282187223434448,
      "rewards/format_reward": 1.0,
      "step": 2320
    },
    {
      "all_correct": 0.75,
      "all_wrong": 0.0,
      "completion_length": 412.53125,
      "epoch": 0.03201335153997876,
      "grad_norm": 2.0412791670306305,
      "kl": 0.08203125,
      "learning_rate": 9.974734032119452e-07,
      "loss": 0.0033,
      "reward": 2.1193437576293945,
      "reward_std": 0.01069062203168869,
      "rewards/accuracy_reward": 0.9193437099456787,
      "rewards/format_reward": 1.0,
      "step": 2321
    },
    {
      "all_correct": 0.75,
      "all_wrong": 0.0,
      "completion_length": 410.21875,
      "epoch": 0.03202714445317996,
      "grad_norm": 2.6274071169258737,
      "kl": 0.08349609375,
      "learning_rate": 9.974712274181208e-07,
      "loss": 0.0033,
      "reward": 2.089062452316284,
      "reward_std": 0.01782357506453991,
      "rewards/accuracy_reward": 0.8890624642372131,
      "rewards/format_reward": 1.0,
      "step": 2322
    },
    {
      "all_correct": 1.0,
      "all_wrong": 0.0,
      "completion_length": 410.84375,
      "epoch": 0.03204093736638115,
      "grad_norm": 2.3248122663803006,
      "kl": 0.080078125,
      "learning_rate": 9.974690506902255e-07,
      "loss": 0.0032,
      "reward": 2.1310312747955322,
      "reward_std": 0.016628500074148178,
      "rewards/accuracy_reward": 0.9310312271118164,
      "rewards/format_reward": 1.0,
      "step": 2323
    },
    {
      "all_correct": 0.75,
      "all_wrong": 0.0,
      "completion_length": 402.8125,
      "epoch": 0.032054730279582354,
      "grad_norm": 1.6996090600110827,
      "kl": 0.08251953125,
      "learning_rate": 9.974668730282638e-07,
      "loss": 0.0033,
      "reward": 2.033937454223633,
      "reward_std": 0.006229642312973738,
      "rewards/accuracy_reward": 0.8339375257492065,
      "rewards/format_reward": 1.0,
      "step": 2324
    },
    {
      "all_correct": 0.75,
      "all_wrong": 0.0,
      "completion_length": 409.40625,
      "epoch": 0.03206852319278355,
      "grad_norm": 2.947229159632449,
      "kl": 0.08935546875,
      "learning_rate": 9.974646944322397e-07,
      "loss": 0.0036,
      "reward": 2.0913751125335693,
      "reward_std": 0.015313539654016495,
      "rewards/accuracy_reward": 0.8913750052452087,
      "rewards/format_reward": 1.0,
      "step": 2325
    },
    {
      "all_correct": 0.75,
      "all_wrong": 0.0,
      "completion_length": 402.15625,
      "epoch": 0.03208231610598475,
      "grad_norm": 2.2098465689425444,
      "kl": 0.076171875,
      "learning_rate": 9.974625149021572e-07,
      "loss": 0.003,
      "reward": 2.11928129196167,
      "reward_std": 0.022272884845733643,
      "rewards/accuracy_reward": 0.9192811846733093,
      "rewards/format_reward": 1.0,
      "step": 2326
    },
    {
      "all_correct": 0.75,
      "all_wrong": 0.0,
      "completion_length": 405.78125,
      "epoch": 0.03209610901918594,
      "grad_norm": 25.78150202858481,
      "kl": 0.08642578125,
      "learning_rate": 9.974603344380203e-07,
      "loss": 0.0035,
      "reward": 2.0751874446868896,
      "reward_std": 0.02650390937924385,
      "rewards/accuracy_reward": 0.8751873970031738,
      "rewards/format_reward": 1.0,
      "step": 2327
    },
    {
      "all_correct": 1.0,
      "all_wrong": 0.0,
      "completion_length": 401.78125,
      "epoch": 0.03210990193238714,
      "grad_norm": 8.955326727526062,
      "kl": 0.0810546875,
      "learning_rate": 9.974581530398333e-07,
      "loss": 0.0033,
      "reward": 2.1094064712524414,
      "reward_std": 0.021358944475650787,
      "rewards/accuracy_reward": 0.909406304359436,
      "rewards/format_reward": 1.0,
      "step": 2328
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.0,
      "completion_length": 394.03125,
      "epoch": 0.03212369484558834,
      "grad_norm": 2.9534450307683566,
      "kl": 0.08251953125,
      "learning_rate": 9.974559707076002e-07,
      "loss": 0.0033,
      "reward": 2.0166876316070557,
      "reward_std": 0.026313763111829758,
      "rewards/accuracy_reward": 0.8166874647140503,
      "rewards/format_reward": 1.0,
      "step": 2329
    },
    {
      "all_correct": 0.75,
      "all_wrong": 0.0,
      "completion_length": 392.5625,
      "epoch": 0.03213748775878953,
      "grad_norm": 2.6769641930782786,
      "kl": 0.083984375,
      "learning_rate": 9.97453787441325e-07,
      "loss": 0.0034,
      "reward": 2.131093978881836,
      "reward_std": 0.013185089454054832,
      "rewards/accuracy_reward": 0.9310937523841858,
      "rewards/format_reward": 1.0,
      "step": 2330
    },
    {
      "all_correct": 0.75,
      "all_wrong": 0.0,
      "completion_length": 389.0625,
      "epoch": 0.03215128067199073,
      "grad_norm": 5.887994643950803,
      "kl": 0.08203125,
      "learning_rate": 9.974516032410123e-07,
      "loss": 0.0033,
      "reward": 2.076218605041504,
      "reward_std": 0.017778923735022545,
      "rewards/accuracy_reward": 0.8762187957763672,
      "rewards/format_reward": 1.0,
      "step": 2331
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.0,
      "completion_length": 396.96875,
      "epoch": 0.032165073585191925,
      "grad_norm": 3.930450991478668,
      "kl": 0.08251953125,
      "learning_rate": 9.974494181066655e-07,
      "loss": 0.0033,
      "reward": 2.0151877403259277,
      "reward_std": 0.0163571834564209,
      "rewards/accuracy_reward": 0.8151874542236328,
      "rewards/format_reward": 1.0,
      "step": 2332
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.0,
      "completion_length": 397.0625,
      "epoch": 0.032178866498393126,
      "grad_norm": 3.4216881399245533,
      "kl": 0.091796875,
      "learning_rate": 9.97447232038289e-07,
      "loss": 0.0037,
      "reward": 2.0705313682556152,
      "reward_std": 0.02359245903789997,
      "rewards/accuracy_reward": 0.8705312013626099,
      "rewards/format_reward": 1.0,
      "step": 2333
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.0,
      "completion_length": 388.125,
      "epoch": 0.03219265941159432,
      "grad_norm": 3.060793416795109,
      "kl": 0.076171875,
      "learning_rate": 9.97445045035887e-07,
      "loss": 0.0031,
      "reward": 2.0478124618530273,
      "reward_std": 0.021338466554880142,
      "rewards/accuracy_reward": 0.8478125333786011,
      "rewards/format_reward": 1.0,
      "step": 2334
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.0,
      "completion_length": 403.875,
      "epoch": 0.03220645232479552,
      "grad_norm": 4.834611104144321,
      "kl": 0.08984375,
      "learning_rate": 9.974428570994636e-07,
      "loss": 0.0036,
      "reward": 2.109715461730957,
      "reward_std": 0.029342088848352432,
      "rewards/accuracy_reward": 0.9159656167030334,
      "rewards/format_reward": 1.0,
      "step": 2335
    },
    {
      "all_correct": 0.75,
      "all_wrong": 0.0,
      "completion_length": 401.75,
      "epoch": 0.032220245237996714,
      "grad_norm": 3.8493422859776874,
      "kl": 0.07666015625,
      "learning_rate": 9.974406682290226e-07,
      "loss": 0.0031,
      "reward": 2.0732502937316895,
      "reward_std": 0.016811514273285866,
      "rewards/accuracy_reward": 0.8732500076293945,
      "rewards/format_reward": 1.0,
      "step": 2336
    },
    {
      "all_correct": 0.75,
      "all_wrong": 0.0,
      "completion_length": 396.0625,
      "epoch": 0.032234038151197915,
      "grad_norm": 2.8234388747705745,
      "kl": 0.0849609375,
      "learning_rate": 9.974384784245687e-07,
      "loss": 0.0034,
      "reward": 1.93959379196167,
      "reward_std": 0.014548176899552345,
      "rewards/accuracy_reward": 0.7395937442779541,
      "rewards/format_reward": 1.0,
      "step": 2337
    },
    {
      "all_correct": 0.75,
      "all_wrong": 0.0,
      "completion_length": 419.3125,
      "epoch": 0.03224783106439911,
      "grad_norm": 4.529598366145159,
      "kl": 0.083984375,
      "learning_rate": 9.974362876861054e-07,
      "loss": 0.0033,
      "reward": 2.0817813873291016,
      "reward_std": 0.01818380132317543,
      "rewards/accuracy_reward": 0.881781280040741,
      "rewards/format_reward": 1.0,
      "step": 2338
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.0,
      "completion_length": 406.1875,
      "epoch": 0.03226162397760031,
      "grad_norm": 3.1938708582024438,
      "kl": 0.0869140625,
      "learning_rate": 9.97434096013637e-07,
      "loss": 0.0035,
      "reward": 2.0459351539611816,
      "reward_std": 0.015249264426529408,
      "rewards/accuracy_reward": 0.8459351062774658,
      "rewards/format_reward": 1.0,
      "step": 2339
    },
    {
      "all_correct": 0.75,
      "all_wrong": 0.0,
      "completion_length": 398.8125,
      "epoch": 0.0322754168908015,
      "grad_norm": 2.126501769507135,
      "kl": 0.08349609375,
      "learning_rate": 9.974319034071679e-07,
      "loss": 0.0033,
      "reward": 2.0508615970611572,
      "reward_std": 0.01695430465042591,
      "rewards/accuracy_reward": 0.8508615493774414,
      "rewards/format_reward": 1.0,
      "step": 2340
    },
    {
      "all_correct": 1.0,
      "all_wrong": 0.0,
      "completion_length": 407.9375,
      "epoch": 0.032289209804002704,
      "grad_norm": 3.851130384146306,
      "kl": 0.08837890625,
      "learning_rate": 9.974297098667017e-07,
      "loss": 0.0035,
      "reward": 2.1062188148498535,
      "reward_std": 0.01266256533563137,
      "rewards/accuracy_reward": 0.9062187075614929,
      "rewards/format_reward": 1.0,
      "step": 2341
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.0,
      "completion_length": 412.03125,
      "epoch": 0.0323030027172039,
      "grad_norm": 2.9705387640655623,
      "kl": 0.0810546875,
      "learning_rate": 9.974275153922431e-07,
      "loss": 0.0032,
      "reward": 1.997593879699707,
      "reward_std": 0.011554213240742683,
      "rewards/accuracy_reward": 0.7975937724113464,
      "rewards/format_reward": 1.0,
      "step": 2342
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.0,
      "completion_length": 414.65625,
      "epoch": 0.0323167956304051,
      "grad_norm": 1.668882262052337,
      "kl": 0.080078125,
      "learning_rate": 9.97425319983796e-07,
      "loss": 0.0032,
      "reward": 1.9397811889648438,
      "reward_std": 0.0055802930146455765,
      "rewards/accuracy_reward": 0.7397812604904175,
      "rewards/format_reward": 1.0,
      "step": 2343
    },
    {
      "all_correct": 1.0,
      "all_wrong": 0.0,
      "completion_length": 409.28125,
      "epoch": 0.03233058854360629,
      "grad_norm": 2.6109228493523076,
      "kl": 0.087890625,
      "learning_rate": 9.974231236413643e-07,
      "loss": 0.0035,
      "reward": 2.106843948364258,
      "reward_std": 0.011872983537614346,
      "rewards/accuracy_reward": 0.9068437218666077,
      "rewards/format_reward": 1.0,
      "step": 2344
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.0,
      "completion_length": 417.40625,
      "epoch": 0.03234438145680749,
      "grad_norm": 3.216842831639977,
      "kl": 0.08251953125,
      "learning_rate": 9.974209263649523e-07,
      "loss": 0.0033,
      "reward": 1.9984999895095825,
      "reward_std": 0.03902565687894821,
      "rewards/accuracy_reward": 0.8047500252723694,
      "rewards/format_reward": 1.0,
      "step": 2345
    },
    {
      "all_correct": 0.25,
      "all_wrong": 0.0,
      "completion_length": 406.5,
      "epoch": 0.03235817437000869,
      "grad_norm": 2.215271794334236,
      "kl": 0.08251953125,
      "learning_rate": 9.974187281545642e-07,
      "loss": 0.0033,
      "reward": 2.013031482696533,
      "reward_std": 0.0055474755354225636,
      "rewards/accuracy_reward": 0.8130311965942383,
      "rewards/format_reward": 1.0,
      "step": 2346
    },
    {
      "all_correct": 1.0,
      "all_wrong": 0.0,
      "completion_length": 404.5,
      "epoch": 0.03237196728320989,
      "grad_norm": 3.0852133313992103,
      "kl": 0.08740234375,
      "learning_rate": 9.974165290102039e-07,
      "loss": 0.0035,
      "reward": 2.111062526702881,
      "reward_std": 0.010986735112965107,
      "rewards/accuracy_reward": 0.911062479019165,
      "rewards/format_reward": 1.0,
      "step": 2347
    },
    {
      "all_correct": 0.25,
      "all_wrong": 0.0,
      "completion_length": 406.3125,
      "epoch": 0.03238576019641108,
      "grad_norm": 2.507537334365763,
      "kl": 0.0849609375,
      "learning_rate": 9.974143289318756e-07,
      "loss": 0.0034,
      "reward": 2.009500026702881,
      "reward_std": 0.029866669327020645,
      "rewards/accuracy_reward": 0.8157499432563782,
      "rewards/format_reward": 1.0,
      "step": 2348
    },
    {
      "all_correct": 1.0,
      "all_wrong": 0.0,
      "completion_length": 408.84375,
      "epoch": 0.03239955310961228,
      "grad_norm": 1.9951901921263475,
      "kl": 0.08984375,
      "learning_rate": 9.974121279195837e-07,
      "loss": 0.0036,
      "reward": 2.1469688415527344,
      "reward_std": 0.00911218486726284,
      "rewards/accuracy_reward": 0.9469687938690186,
      "rewards/format_reward": 1.0,
      "step": 2349
    },
    {
      "all_correct": 0.75,
      "all_wrong": 0.0,
      "completion_length": 403.0,
      "epoch": 0.032413346022813476,
      "grad_norm": 1.4985005935974436,
      "kl": 0.08203125,
      "learning_rate": 9.974099259733322e-07,
      "loss": 0.0033,
      "reward": 2.085031509399414,
      "reward_std": 0.005332938861101866,
      "rewards/accuracy_reward": 0.8850312232971191,
      "rewards/format_reward": 1.0,
      "step": 2350
    },
    {
      "all_correct": 1.0,
      "all_wrong": 0.0,
      "completion_length": 402.9375,
      "epoch": 0.03242713893601468,
      "grad_norm": 3.103144542429257,
      "kl": 0.083984375,
      "learning_rate": 9.97407723093125e-07,
      "loss": 0.0034,
      "reward": 2.149343967437744,
      "reward_std": 0.019839826971292496,
      "rewards/accuracy_reward": 0.9493438005447388,
      "rewards/format_reward": 1.0,
      "step": 2351
    },
    {
      "all_correct": 0.75,
      "all_wrong": 0.0,
      "completion_length": 406.4375,
      "epoch": 0.03244093184921587,
      "grad_norm": 3.386565044206934,
      "kl": 0.0927734375,
      "learning_rate": 9.974055192789665e-07,
      "loss": 0.0037,
      "reward": 2.063624858856201,
      "reward_std": 0.017994562163949013,
      "rewards/accuracy_reward": 0.8636250495910645,
      "rewards/format_reward": 1.0,
      "step": 2352
    },
    {
      "all_correct": 1.0,
      "all_wrong": 0.0,
      "completion_length": 401.40625,
      "epoch": 0.03245472476241707,
      "grad_norm": 2.2761309494338295,
      "kl": 0.08349609375,
      "learning_rate": 9.974033145308607e-07,
      "loss": 0.0033,
      "reward": 2.1413750648498535,
      "reward_std": 0.01586213707923889,
      "rewards/accuracy_reward": 0.9413750171661377,
      "rewards/format_reward": 1.0,
      "step": 2353
    },
    {
      "all_correct": 1.0,
      "all_wrong": 0.0,
      "completion_length": 389.78125,
      "epoch": 0.032468517675618265,
      "grad_norm": 1.8432715728651696,
      "kl": 0.08642578125,
      "learning_rate": 9.974011088488117e-07,
      "loss": 0.0035,
      "reward": 2.132718801498413,
      "reward_std": 0.005831220652908087,
      "rewards/accuracy_reward": 0.9327187538146973,
      "rewards/format_reward": 1.0,
      "step": 2354
    },
    {
      "all_correct": 0.75,
      "all_wrong": 0.0,
      "completion_length": 386.03125,
      "epoch": 0.032482310588819466,
      "grad_norm": 2.477588129396509,
      "kl": 0.08935546875,
      "learning_rate": 9.973989022328237e-07,
      "loss": 0.0036,
      "reward": 2.0822811126708984,
      "reward_std": 0.012081412598490715,
      "rewards/accuracy_reward": 0.8822813034057617,
      "rewards/format_reward": 1.0,
      "step": 2355
    },
    {
      "all_correct": 1.0,
      "all_wrong": 0.0,
      "completion_length": 389.21875,
      "epoch": 0.03249610350202066,
      "grad_norm": 3.3365285601954326,
      "kl": 0.0869140625,
      "learning_rate": 9.97396694682901e-07,
      "loss": 0.0035,
      "reward": 2.106156349182129,
      "reward_std": 0.013339381664991379,
      "rewards/accuracy_reward": 0.9061561822891235,
      "rewards/format_reward": 1.0,
      "step": 2356
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.0,
      "completion_length": 392.75,
      "epoch": 0.03250989641522186,
      "grad_norm": 11.849880391347611,
      "kl": 0.087890625,
      "learning_rate": 9.973944861990475e-07,
      "loss": 0.0035,
      "reward": 2.0523126125335693,
      "reward_std": 0.0322912335395813,
      "rewards/accuracy_reward": 0.8585624694824219,
      "rewards/format_reward": 1.0,
      "step": 2357
    },
    {
      "all_correct": 1.0,
      "all_wrong": 0.0,
      "completion_length": 387.3125,
      "epoch": 0.032523689328423054,
      "grad_norm": 8.392127570633706,
      "kl": 0.08544921875,
      "learning_rate": 9.973922767812675e-07,
      "loss": 0.0034,
      "reward": 2.12681245803833,
      "reward_std": 0.018162531778216362,
      "rewards/accuracy_reward": 0.9268125295639038,
      "rewards/format_reward": 1.0,
      "step": 2358
    },
    {
      "all_correct": 1.0,
      "all_wrong": 0.0,
      "completion_length": 387.96875,
      "epoch": 0.032537482241624255,
      "grad_norm": 2.943888458050703,
      "kl": 0.0908203125,
      "learning_rate": 9.97390066429565e-07,
      "loss": 0.0036,
      "reward": 2.1219375133514404,
      "reward_std": 0.016423191875219345,
      "rewards/accuracy_reward": 0.9219375848770142,
      "rewards/format_reward": 1.0,
      "step": 2359
    },
    {
      "all_correct": 0.75,
      "all_wrong": 0.0,
      "completion_length": 398.21875,
      "epoch": 0.03255127515482545,
      "grad_norm": 14.287235924336045,
      "kl": 0.09521484375,
      "learning_rate": 9.973878551439444e-07,
      "loss": 0.0038,
      "reward": 2.0561251640319824,
      "reward_std": 0.015381023287773132,
      "rewards/accuracy_reward": 0.856124997138977,
      "rewards/format_reward": 1.0,
      "step": 2360
    },
    {
      "all_correct": 0.75,
      "all_wrong": 0.0,
      "completion_length": 379.15625,
      "epoch": 0.03256506806802665,
      "grad_norm": 2.339159417704558,
      "kl": 0.0830078125,
      "learning_rate": 9.973856429244098e-07,
      "loss": 0.0033,
      "reward": 2.0890345573425293,
      "reward_std": 0.029502497985959053,
      "rewards/accuracy_reward": 0.8952842950820923,
      "rewards/format_reward": 1.0,
      "step": 2361
    },
    {
      "all_correct": 0.75,
      "all_wrong": 0.0,
      "completion_length": 382.46875,
      "epoch": 0.03257886098122784,
      "grad_norm": 2.9886503479010162,
      "kl": 0.0830078125,
      "learning_rate": 9.973834297709653e-07,
      "loss": 0.0033,
      "reward": 2.120687484741211,
      "reward_std": 0.027790088206529617,
      "rewards/accuracy_reward": 0.9269375205039978,
      "rewards/format_reward": 1.0,
      "step": 2362
    },
    {
      "all_correct": 0.75,
      "all_wrong": 0.0,
      "completion_length": 382.3125,
      "epoch": 0.032592653894429044,
      "grad_norm": 2.6831080041579374,
      "kl": 0.0869140625,
      "learning_rate": 9.973812156836148e-07,
      "loss": 0.0035,
      "reward": 2.1221563816070557,
      "reward_std": 0.0333104133605957,
      "rewards/accuracy_reward": 0.9284062385559082,
      "rewards/format_reward": 1.0,
      "step": 2363
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.0,
      "completion_length": 389.0,
      "epoch": 0.03260644680763024,
      "grad_norm": 5.902226917081986,
      "kl": 0.0927734375,
      "learning_rate": 9.973790006623629e-07,
      "loss": 0.0037,
      "reward": 1.9923124313354492,
      "reward_std": 0.05784345418214798,
      "rewards/accuracy_reward": 0.804812490940094,
      "rewards/format_reward": 1.0,
      "step": 2364
    },
    {
      "all_correct": 1.0,
      "all_wrong": 0.0,
      "completion_length": 384.09375,
      "epoch": 0.03262023972083144,
      "grad_norm": 2.927095845204925,
      "kl": 0.08935546875,
      "learning_rate": 9.973767847072133e-07,
      "loss": 0.0035,
      "reward": 2.138051986694336,
      "reward_std": 0.007921425625681877,
      "rewards/accuracy_reward": 0.9380520582199097,
      "rewards/format_reward": 1.0,
      "step": 2365
    },
    {
      "all_correct": 0.75,
      "all_wrong": 0.0,
      "completion_length": 384.0,
      "epoch": 0.03263403263403263,
      "grad_norm": 3.079658610465056,
      "kl": 0.08642578125,
      "learning_rate": 9.973745678181704e-07,
      "loss": 0.0035,
      "reward": 2.058718681335449,
      "reward_std": 0.021353382617235184,
      "rewards/accuracy_reward": 0.8587188124656677,
      "rewards/format_reward": 1.0,
      "step": 2366
    },
    {
      "all_correct": 1.0,
      "all_wrong": 0.0,
      "completion_length": 391.25,
      "epoch": 0.03264782554723383,
      "grad_norm": 1.9730684993662486,
      "kl": 0.08984375,
      "learning_rate": 9.973723499952384e-07,
      "loss": 0.0036,
      "reward": 2.1182498931884766,
      "reward_std": 0.0077733239158988,
      "rewards/accuracy_reward": 0.9182500243186951,
      "rewards/format_reward": 1.0,
      "step": 2367
    },
    {
      "all_correct": 0.75,
      "all_wrong": 0.0,
      "completion_length": 384.875,
      "epoch": 0.03266161846043503,
      "grad_norm": 2.0341904079955055,
      "kl": 0.08056640625,
      "learning_rate": 9.973701312384215e-07,
      "loss": 0.0032,
      "reward": 2.124500036239624,
      "reward_std": 0.026494383811950684,
      "rewards/accuracy_reward": 0.937000036239624,
      "rewards/format_reward": 1.0,
      "step": 2368
    },
    {
      "all_correct": 0.75,
      "all_wrong": 0.0,
      "completion_length": 384.0,
      "epoch": 0.03267541137363623,
      "grad_norm": 4.8726830959665435,
      "kl": 0.07470703125,
      "learning_rate": 9.973679115477238e-07,
      "loss": 0.003,
      "reward": 2.1194376945495605,
      "reward_std": 0.011935602873563766,
      "rewards/accuracy_reward": 0.9194374680519104,
      "rewards/format_reward": 1.0,
      "step": 2369
    },
    {
      "all_correct": 0.75,
      "all_wrong": 0.0,
      "completion_length": 385.59375,
      "epoch": 0.03268920428683742,
      "grad_norm": 2.6967009035499054,
      "kl": 0.07568359375,
      "learning_rate": 9.973656909231495e-07,
      "loss": 0.003,
      "reward": 2.101531505584717,
      "reward_std": 0.010418438352644444,
      "rewards/accuracy_reward": 0.9015312194824219,
      "rewards/format_reward": 1.0,
      "step": 2370
    },
    {
      "all_correct": 0.25,
      "all_wrong": 0.0,
      "completion_length": 375.25,
      "epoch": 0.03270299720003862,
      "grad_norm": 3.165494353344299,
      "kl": 0.08154296875,
      "learning_rate": 9.973634693647024e-07,
      "loss": 0.0033,
      "reward": 2.08134388923645,
      "reward_std": 0.050670918077230453,
      "rewards/accuracy_reward": 0.8938437700271606,
      "rewards/format_reward": 1.0,
      "step": 2371
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.0,
      "completion_length": 382.1875,
      "epoch": 0.032716790113239816,
      "grad_norm": 1.8671773146818746,
      "kl": 0.08251953125,
      "learning_rate": 9.973612468723874e-07,
      "loss": 0.0033,
      "reward": 2.0793747901916504,
      "reward_std": 0.008107316680252552,
      "rewards/accuracy_reward": 0.8793749809265137,
      "rewards/format_reward": 1.0,
      "step": 2372
    },
    {
      "all_correct": 0.75,
      "all_wrong": 0.0,
      "completion_length": 398.6875,
      "epoch": 0.03273058302644102,
      "grad_norm": 3.116751694895294,
      "kl": 0.08203125,
      "learning_rate": 9.97359023446208e-07,
      "loss": 0.0033,
      "reward": 2.0723750591278076,
      "reward_std": 0.011620712466537952,
      "rewards/accuracy_reward": 0.8723750114440918,
      "rewards/format_reward": 1.0,
      "step": 2373
    },
    {
      "all_correct": 0.75,
      "all_wrong": 0.0,
      "completion_length": 377.78125,
      "epoch": 0.03274437593964221,
      "grad_norm": 2.672323119923527,
      "kl": 0.08447265625,
      "learning_rate": 9.973567990861687e-07,
      "loss": 0.0034,
      "reward": 2.1391220092773438,
      "reward_std": 0.027407145127654076,
      "rewards/accuracy_reward": 0.9453719258308411,
      "rewards/format_reward": 1.0,
      "step": 2374
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.0,
      "completion_length": 384.59375,
      "epoch": 0.03275816885284341,
      "grad_norm": 3.8358348492990153,
      "kl": 0.0771484375,
      "learning_rate": 9.973545737922736e-07,
      "loss": 0.0031,
      "reward": 2.1338748931884766,
      "reward_std": 0.04213307797908783,
      "rewards/accuracy_reward": 0.9463750123977661,
      "rewards/format_reward": 1.0,
      "step": 2375
    },
    {
      "all_correct": 0.75,
      "all_wrong": 0.0,
      "completion_length": 374.53125,
      "epoch": 0.032771961766044605,
      "grad_norm": 2.3489391410091094,
      "kl": 0.07421875,
      "learning_rate": 9.97352347564527e-07,
      "loss": 0.003,
      "reward": 2.1101250648498535,
      "reward_std": 0.022552819922566414,
      "rewards/accuracy_reward": 0.9163750410079956,
      "rewards/format_reward": 1.0,
      "step": 2376
    },
    {
      "all_correct": 0.75,
      "all_wrong": 0.0,
      "completion_length": 386.8125,
      "epoch": 0.032785754679245806,
      "grad_norm": 5.4585844652772435,
      "kl": 0.0888671875,
      "learning_rate": 9.973501204029328e-07,
      "loss": 0.0036,
      "reward": 2.076124906539917,
      "reward_std": 0.02718494087457657,
      "rewards/accuracy_reward": 0.8761250376701355,
      "rewards/format_reward": 1.0,
      "step": 2377
    },
    {
      "all_correct": 1.0,
      "all_wrong": 0.0,
      "completion_length": 390.875,
      "epoch": 0.032799547592447,
      "grad_norm": 4.143807061511893,
      "kl": 0.0869140625,
      "learning_rate": 9.973478923074957e-07,
      "loss": 0.0035,
      "reward": 2.1364998817443848,
      "reward_std": 0.031032584607601166,
      "rewards/accuracy_reward": 0.9427499175071716,
      "rewards/format_reward": 1.0,
      "step": 2378
    },
    {
      "all_correct": 1.0,
      "all_wrong": 0.0,
      "completion_length": 414.90625,
      "epoch": 0.0328133405056482,
      "grad_norm": 2.6955632757511294,
      "kl": 0.06689453125,
      "learning_rate": 9.973456632782193e-07,
      "loss": 0.0027,
      "reward": 2.142406463623047,
      "reward_std": 0.025756757706403732,
      "rewards/accuracy_reward": 0.9486562013626099,
      "rewards/format_reward": 1.0,
      "step": 2379
    },
    {
      "all_correct": 1.0,
      "all_wrong": 0.0,
      "completion_length": 409.9375,
      "epoch": 0.032827133418849394,
      "grad_norm": 2.047918124942534,
      "kl": 0.078125,
      "learning_rate": 9.97343433315108e-07,
      "loss": 0.0031,
      "reward": 2.1542186737060547,
      "reward_std": 0.004356837831437588,
      "rewards/accuracy_reward": 0.9542187452316284,
      "rewards/format_reward": 1.0,
      "step": 2380
    },
    {
      "all_correct": 0.25,
      "all_wrong": 0.0,
      "completion_length": 405.9375,
      "epoch": 0.032840926332050595,
      "grad_norm": 4.510018267524575,
      "kl": 0.0791015625,
      "learning_rate": 9.97341202418166e-07,
      "loss": 0.0032,
      "reward": 2.045593738555908,
      "reward_std": 0.03318803757429123,
      "rewards/accuracy_reward": 0.8518437743186951,
      "rewards/format_reward": 1.0,
      "step": 2381
    },
    {
      "all_correct": 0.75,
      "all_wrong": 0.0,
      "completion_length": 403.53125,
      "epoch": 0.03285471924525179,
      "grad_norm": 3.117937202605605,
      "kl": 0.080078125,
      "learning_rate": 9.973389705873975e-07,
      "loss": 0.0032,
      "reward": 2.1275312900543213,
      "reward_std": 0.021019957959651947,
      "rewards/accuracy_reward": 0.9337812662124634,
      "rewards/format_reward": 1.0,
      "step": 2382
    },
    {
      "all_correct": 0.75,
      "all_wrong": 0.0,
      "completion_length": 407.4375,
      "epoch": 0.03286851215845299,
      "grad_norm": 3.7193578446461775,
      "kl": 0.07763671875,
      "learning_rate": 9.973367378228069e-07,
      "loss": 0.0031,
      "reward": 2.1307811737060547,
      "reward_std": 0.012470152229070663,
      "rewards/accuracy_reward": 0.9307812452316284,
      "rewards/format_reward": 1.0,
      "step": 2383
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.0,
      "completion_length": 392.5625,
      "epoch": 0.03288230507165418,
      "grad_norm": 2.5658145371196333,
      "kl": 0.083984375,
      "learning_rate": 9.973345041243982e-07,
      "loss": 0.0034,
      "reward": 2.008593797683716,
      "reward_std": 0.032400086522102356,
      "rewards/accuracy_reward": 0.8148437738418579,
      "rewards/format_reward": 1.0,
      "step": 2384
    },
    {
      "all_correct": 1.0,
      "all_wrong": 0.0,
      "completion_length": 410.0,
      "epoch": 0.032896097984855384,
      "grad_norm": 2.0921653834263645,
      "kl": 0.08349609375,
      "learning_rate": 9.973322694921753e-07,
      "loss": 0.0033,
      "reward": 2.1388437747955322,
      "reward_std": 0.005781481973826885,
      "rewards/accuracy_reward": 0.9388437271118164,
      "rewards/format_reward": 1.0,
      "step": 2385
    },
    {
      "all_correct": 0.75,
      "all_wrong": 0.0,
      "completion_length": 401.875,
      "epoch": 0.03290989089805658,
      "grad_norm": 1.6942686118466461,
      "kl": 0.08837890625,
      "learning_rate": 9.973300339261428e-07,
      "loss": 0.0035,
      "reward": 2.186375141143799,
      "reward_std": 0.022686326876282692,
      "rewards/accuracy_reward": 0.9926249980926514,
      "rewards/format_reward": 1.0,
      "step": 2386
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.0,
      "completion_length": 398.90625,
      "epoch": 0.03292368381125778,
      "grad_norm": 4.2585733558131125,
      "kl": 0.0927734375,
      "learning_rate": 9.973277974263048e-07,
      "loss": 0.0037,
      "reward": 2.040875196456909,
      "reward_std": 0.024384882301092148,
      "rewards/accuracy_reward": 0.840874969959259,
      "rewards/format_reward": 1.0,
      "step": 2387
    },
    {
      "all_correct": 1.0,
      "all_wrong": 0.0,
      "completion_length": 422.6875,
      "epoch": 0.03293747672445897,
      "grad_norm": 2.1267470233836314,
      "kl": 0.08056640625,
      "learning_rate": 9.973255599926655e-07,
      "loss": 0.0032,
      "reward": 2.133406400680542,
      "reward_std": 0.02618633769452572,
      "rewards/accuracy_reward": 0.9396562576293945,
      "rewards/format_reward": 1.0,
      "step": 2388
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.0,
      "completion_length": 404.59375,
      "epoch": 0.03295126963766017,
      "grad_norm": 5.008861536587949,
      "kl": 0.0927734375,
      "learning_rate": 9.97323321625229e-07,
      "loss": 0.0037,
      "reward": 2.045687675476074,
      "reward_std": 0.018814748153090477,
      "rewards/accuracy_reward": 0.8456875085830688,
      "rewards/format_reward": 1.0,
      "step": 2389
    },
    {
      "all_correct": 1.0,
      "all_wrong": 0.0,
      "completion_length": 402.84375,
      "epoch": 0.03296506255086137,
      "grad_norm": 5.329722737658765,
      "kl": 0.083984375,
      "learning_rate": 9.973210823239996e-07,
      "loss": 0.0034,
      "reward": 2.143843650817871,
      "reward_std": 0.012380078434944153,
      "rewards/accuracy_reward": 0.9438437223434448,
      "rewards/format_reward": 1.0,
      "step": 2390
    },
    {
      "all_correct": 0.25,
      "all_wrong": 0.0,
      "completion_length": 411.0625,
      "epoch": 0.03297885546406257,
      "grad_norm": 2.664733009476507,
      "kl": 0.0869140625,
      "learning_rate": 9.973188420889816e-07,
      "loss": 0.0035,
      "reward": 1.826812505722046,
      "reward_std": 0.014422931708395481,
      "rewards/accuracy_reward": 0.6268125176429749,
      "rewards/format_reward": 1.0,
      "step": 2391
    },
    {
      "all_correct": 0.75,
      "all_wrong": 0.0,
      "completion_length": 391.6875,
      "epoch": 0.03299264837726376,
      "grad_norm": 2.8494405564210035,
      "kl": 0.07958984375,
      "learning_rate": 9.97316600920179e-07,
      "loss": 0.0032,
      "reward": 2.0310938358306885,
      "reward_std": 0.018070163205266,
      "rewards/accuracy_reward": 0.8310937285423279,
      "rewards/format_reward": 1.0,
      "step": 2392
    },
    {
      "all_correct": 0.75,
      "all_wrong": 0.0,
      "completion_length": 387.3125,
      "epoch": 0.03300644129046496,
      "grad_norm": 2.216269019927954,
      "kl": 0.0869140625,
      "learning_rate": 9.97314358817596e-07,
      "loss": 0.0035,
      "reward": 2.1406564712524414,
      "reward_std": 0.03640886768698692,
      "rewards/accuracy_reward": 0.9531562924385071,
      "rewards/format_reward": 1.0,
      "step": 2393
    },
    {
      "all_correct": 1.0,
      "all_wrong": 0.0,
      "completion_length": 387.25,
      "epoch": 0.033020234203666156,
      "grad_norm": 2.296214209825985,
      "kl": 0.0927734375,
      "learning_rate": 9.97312115781237e-07,
      "loss": 0.0037,
      "reward": 2.113687515258789,
      "reward_std": 0.014185428619384766,
      "rewards/accuracy_reward": 0.9136874675750732,
      "rewards/format_reward": 1.0,
      "step": 2394
    },
    {
      "all_correct": 1.0,
      "all_wrong": 0.0,
      "completion_length": 380.59375,
      "epoch": 0.03303402711686736,
      "grad_norm": 3.9799257974870685,
      "kl": 0.1005859375,
      "learning_rate": 9.973098718111061e-07,
      "loss": 0.004,
      "reward": 2.1571249961853027,
      "reward_std": 0.016814254224300385,
      "rewards/accuracy_reward": 0.9571249485015869,
      "rewards/format_reward": 1.0,
      "step": 2395
    },
    {
      "all_correct": 0.75,
      "all_wrong": 0.0,
      "completion_length": 396.9375,
      "epoch": 0.03304782003006855,
      "grad_norm": 2.3743539775718414,
      "kl": 0.08642578125,
      "learning_rate": 9.973076269072075e-07,
      "loss": 0.0035,
      "reward": 2.107343912124634,
      "reward_std": 0.017473481595516205,
      "rewards/accuracy_reward": 0.9073437452316284,
      "rewards/format_reward": 1.0,
      "step": 2396
    },
    {
      "all_correct": 0.75,
      "all_wrong": 0.0,
      "completion_length": 382.625,
      "epoch": 0.03306161294326975,
      "grad_norm": 2.8013854200604658,
      "kl": 0.07958984375,
      "learning_rate": 9.973053810695457e-07,
      "loss": 0.0032,
      "reward": 2.112562417984009,
      "reward_std": 0.011191128753125668,
      "rewards/accuracy_reward": 0.9125624895095825,
      "rewards/format_reward": 1.0,
      "step": 2397
    },
    {
      "all_correct": 1.0,
      "all_wrong": 0.0,
      "completion_length": 393.78125,
      "epoch": 0.033075405856470945,
      "grad_norm": 5.330557156468669,
      "kl": 0.0771484375,
      "learning_rate": 9.973031342981244e-07,
      "loss": 0.0031,
      "reward": 2.1572813987731934,
      "reward_std": 0.012861261144280434,
      "rewards/accuracy_reward": 0.957281231880188,
      "rewards/format_reward": 1.0,
      "step": 2398
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.0,
      "completion_length": 386.28125,
      "epoch": 0.033089198769672146,
      "grad_norm": 3.984579946953634,
      "kl": 0.08544921875,
      "learning_rate": 9.973008865929483e-07,
      "loss": 0.0034,
      "reward": 2.0656251907348633,
      "reward_std": 0.013595905154943466,
      "rewards/accuracy_reward": 0.8656249642372131,
      "rewards/format_reward": 1.0,
      "step": 2399
    },
    {
      "all_correct": 0.75,
      "all_wrong": 0.0,
      "completion_length": 378.03125,
      "epoch": 0.03310299168287334,
      "grad_norm": 6.216136210817981,
      "kl": 0.08203125,
      "learning_rate": 9.97298637954021e-07,
      "loss": 0.0033,
      "reward": 2.07240629196167,
      "reward_std": 0.009323226287961006,
      "rewards/accuracy_reward": 0.8724062442779541,
      "rewards/format_reward": 1.0,
      "step": 2400
    },
    {
      "all_correct": 0.75,
      "all_wrong": 0.0,
      "completion_length": 377.5625,
      "epoch": 0.03311678459607454,
      "grad_norm": 8.221543568756736,
      "kl": 0.07763671875,
      "learning_rate": 9.972963883813476e-07,
      "loss": 0.0031,
      "reward": 2.127593755722046,
      "reward_std": 0.008764777332544327,
      "rewards/accuracy_reward": 0.9275937676429749,
      "rewards/format_reward": 1.0,
      "step": 2401
    },
    {
      "all_correct": 1.0,
      "all_wrong": 0.0,
      "completion_length": 384.40625,
      "epoch": 0.033130577509275734,
      "grad_norm": 2.8362306643516173,
      "kl": 0.09033203125,
      "learning_rate": 9.972941378749316e-07,
      "loss": 0.0036,
      "reward": 2.139437437057495,
      "reward_std": 0.015877075493335724,
      "rewards/accuracy_reward": 0.9394374489784241,
      "rewards/format_reward": 1.0,
      "step": 2402
    },
    {
      "all_correct": 0.75,
      "all_wrong": 0.0,
      "completion_length": 376.40625,
      "epoch": 0.033144370422476935,
      "grad_norm": 2.3639772550253957,
      "kl": 0.08740234375,
      "learning_rate": 9.972918864347775e-07,
      "loss": 0.0035,
      "reward": 2.129312515258789,
      "reward_std": 0.02568642422556877,
      "rewards/accuracy_reward": 0.9355624914169312,
      "rewards/format_reward": 1.0,
      "step": 2403
    },
    {
      "all_correct": 1.0,
      "all_wrong": 0.0,
      "completion_length": 385.28125,
      "epoch": 0.03315816333567813,
      "grad_norm": 2.6715838347248866,
      "kl": 0.087890625,
      "learning_rate": 9.972896340608894e-07,
      "loss": 0.0035,
      "reward": 2.1388437747955322,
      "reward_std": 0.01290091685950756,
      "rewards/accuracy_reward": 0.9388437271118164,
      "rewards/format_reward": 1.0,
      "step": 2404
    },
    {
      "all_correct": 0.75,
      "all_wrong": 0.0,
      "completion_length": 373.53125,
      "epoch": 0.03317195624887932,
      "grad_norm": 1.8561072825430347,
      "kl": 0.08447265625,
      "learning_rate": 9.972873807532718e-07,
      "loss": 0.0034,
      "reward": 2.007625102996826,
      "reward_std": 0.026237372308969498,
      "rewards/accuracy_reward": 0.8076249957084656,
      "rewards/format_reward": 1.0,
      "step": 2405
    },
    {
      "all_correct": 0.25,
      "all_wrong": 0.0,
      "completion_length": 363.75,
      "epoch": 0.03318574916208052,
      "grad_norm": 2.336971683307296,
      "kl": 0.09228515625,
      "learning_rate": 9.972851265119287e-07,
      "loss": 0.0037,
      "reward": 2.081125020980835,
      "reward_std": 0.052818939089775085,
      "rewards/accuracy_reward": 0.8998750448226929,
      "rewards/format_reward": 1.0,
      "step": 2406
    },
    {
      "all_correct": 0.75,
      "all_wrong": 0.0,
      "completion_length": 378.59375,
      "epoch": 0.03319954207528172,
      "grad_norm": 1.9259696652231992,
      "kl": 0.0771484375,
      "learning_rate": 9.972828713368643e-07,
      "loss": 0.0031,
      "reward": 2.056999921798706,
      "reward_std": 0.005443733185529709,
      "rewards/accuracy_reward": 0.8569999933242798,
      "rewards/format_reward": 1.0,
      "step": 2407
    },
    {
      "all_correct": 1.0,
      "all_wrong": 0.0,
      "completion_length": 389.75,
      "epoch": 0.03321333498848292,
      "grad_norm": 1.8827932239322343,
      "kl": 0.0732421875,
      "learning_rate": 9.972806152280834e-07,
      "loss": 0.0029,
      "reward": 2.170875072479248,
      "reward_std": 0.014248276129364967,
      "rewards/accuracy_reward": 0.9708750247955322,
      "rewards/format_reward": 1.0,
      "step": 2408
    },
    {
      "all_correct": 0.75,
      "all_wrong": 0.0,
      "completion_length": 381.0625,
      "epoch": 0.03322712790168411,
      "grad_norm": 18.377650887285704,
      "kl": 0.0771484375,
      "learning_rate": 9.972783581855892e-07,
      "loss": 0.0031,
      "reward": 2.1256561279296875,
      "reward_std": 0.01474706269800663,
      "rewards/accuracy_reward": 0.9256561994552612,
      "rewards/format_reward": 1.0,
      "step": 2409
    },
    {
      "all_correct": 0.75,
      "all_wrong": 0.0,
      "completion_length": 383.4375,
      "epoch": 0.03324092081488531,
      "grad_norm": 2.4538553611388956,
      "kl": 0.087890625,
      "learning_rate": 9.972761002093866e-07,
      "loss": 0.0035,
      "reward": 2.1155314445495605,
      "reward_std": 0.010522525757551193,
      "rewards/accuracy_reward": 0.9155312776565552,
      "rewards/format_reward": 1.0,
      "step": 2410
    },
    {
      "all_correct": 1.0,
      "all_wrong": 0.0,
      "completion_length": 373.09375,
      "epoch": 0.033254713728086506,
      "grad_norm": 3.5926245855456234,
      "kl": 0.08203125,
      "learning_rate": 9.9727384129948e-07,
      "loss": 0.0033,
      "reward": 2.1695938110351562,
      "reward_std": 0.024917827919125557,
      "rewards/accuracy_reward": 0.9758437871932983,
      "rewards/format_reward": 1.0,
      "step": 2411
    },
    {
      "all_correct": 0.75,
      "all_wrong": 0.0,
      "completion_length": 378.78125,
      "epoch": 0.03326850664128771,
      "grad_norm": 2.4851963418716174,
      "kl": 0.0947265625,
      "learning_rate": 9.972715814558732e-07,
      "loss": 0.0038,
      "reward": 2.1246564388275146,
      "reward_std": 0.011552146635949612,
      "rewards/accuracy_reward": 0.9246562719345093,
      "rewards/format_reward": 1.0,
      "step": 2412
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.0,
      "completion_length": 370.90625,
      "epoch": 0.0332822995544889,
      "grad_norm": 4.107681301273479,
      "kl": 0.0966796875,
      "learning_rate": 9.972693206785706e-07,
      "loss": 0.0039,
      "reward": 2.0489375591278076,
      "reward_std": 0.022118523716926575,
      "rewards/accuracy_reward": 0.848937451839447,
      "rewards/format_reward": 1.0,
      "step": 2413
    },
    {
      "all_correct": 1.0,
      "all_wrong": 0.0,
      "completion_length": 380.5625,
      "epoch": 0.0332960924676901,
      "grad_norm": 2.9656141275351806,
      "kl": 0.08935546875,
      "learning_rate": 9.972670589675766e-07,
      "loss": 0.0036,
      "reward": 2.144718885421753,
      "reward_std": 0.020112890750169754,
      "rewards/accuracy_reward": 0.9447187781333923,
      "rewards/format_reward": 1.0,
      "step": 2414
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.0,
      "completion_length": 374.0625,
      "epoch": 0.033309885380891295,
      "grad_norm": 2.543859750446778,
      "kl": 0.08251953125,
      "learning_rate": 9.972647963228953e-07,
      "loss": 0.0033,
      "reward": 2.0807814598083496,
      "reward_std": 0.041097287088632584,
      "rewards/accuracy_reward": 0.8932812213897705,
      "rewards/format_reward": 1.0,
      "step": 2415
    },
    {
      "all_correct": 0.75,
      "all_wrong": 0.0,
      "completion_length": 382.03125,
      "epoch": 0.033323678294092496,
      "grad_norm": 2.51712493253632,
      "kl": 0.08203125,
      "learning_rate": 9.972625327445307e-07,
      "loss": 0.0033,
      "reward": 2.1582188606262207,
      "reward_std": 0.02050146833062172,
      "rewards/accuracy_reward": 0.9644687175750732,
      "rewards/format_reward": 1.0,
      "step": 2416
    },
    {
      "all_correct": 0.75,
      "all_wrong": 0.0,
      "completion_length": 370.59375,
      "epoch": 0.03333747120729369,
      "grad_norm": 2.722630365394544,
      "kl": 0.08154296875,
      "learning_rate": 9.972602682324877e-07,
      "loss": 0.0033,
      "reward": 2.1474685668945312,
      "reward_std": 0.02480340749025345,
      "rewards/accuracy_reward": 0.9537187218666077,
      "rewards/format_reward": 1.0,
      "step": 2417
    },
    {
      "all_correct": 0.75,
      "all_wrong": 0.0,
      "completion_length": 371.125,
      "epoch": 0.03335126412049489,
      "grad_norm": 2.4782277425164527,
      "kl": 0.08251953125,
      "learning_rate": 9.9725800278677e-07,
      "loss": 0.0033,
      "reward": 2.103687286376953,
      "reward_std": 0.026489539071917534,
      "rewards/accuracy_reward": 0.9099375009536743,
      "rewards/format_reward": 1.0,
      "step": 2418
    },
    {
      "all_correct": 0.75,
      "all_wrong": 0.0,
      "completion_length": 378.25,
      "epoch": 0.033365057033696084,
      "grad_norm": 3.1856597450066575,
      "kl": 0.095703125,
      "learning_rate": 9.972557364073819e-07,
      "loss": 0.0038,
      "reward": 2.0617189407348633,
      "reward_std": 0.018151069059967995,
      "rewards/accuracy_reward": 0.8617187738418579,
      "rewards/format_reward": 1.0,
      "step": 2419
    },
    {
      "all_correct": 0.75,
      "all_wrong": 0.0,
      "completion_length": 381.875,
      "epoch": 0.033378849946897285,
      "grad_norm": 1.1518360391563398,
      "kl": 0.0732421875,
      "learning_rate": 9.97253469094328e-07,
      "loss": 0.0029,
      "reward": 2.1312499046325684,
      "reward_std": 0.017677675932645798,
      "rewards/accuracy_reward": 0.9375,
      "rewards/format_reward": 1.0,
      "step": 2420
    },
    {
      "all_correct": 0.75,
      "all_wrong": 0.0,
      "completion_length": 380.625,
      "epoch": 0.03339264286009848,
      "grad_norm": 13.350230308940366,
      "kl": 0.0927734375,
      "learning_rate": 9.972512008476123e-07,
      "loss": 0.0037,
      "reward": 2.1233749389648438,
      "reward_std": 0.012214983813464642,
      "rewards/accuracy_reward": 0.9233750104904175,
      "rewards/format_reward": 1.0,
      "step": 2421
    },
    {
      "all_correct": 0.75,
      "all_wrong": 0.0,
      "completion_length": 382.5625,
      "epoch": 0.03340643577329968,
      "grad_norm": 2.328168748796646,
      "kl": 0.0869140625,
      "learning_rate": 9.97248931667239e-07,
      "loss": 0.0035,
      "reward": 2.128406524658203,
      "reward_std": 0.025792112573981285,
      "rewards/accuracy_reward": 0.9346562623977661,
      "rewards/format_reward": 1.0,
      "step": 2422
    },
    {
      "all_correct": 0.25,
      "all_wrong": 0.0,
      "completion_length": 382.9375,
      "epoch": 0.03342022868650087,
      "grad_norm": 2.6963226717099187,
      "kl": 0.087890625,
      "learning_rate": 9.972466615532124e-07,
      "loss": 0.0035,
      "reward": 2.050940752029419,
      "reward_std": 0.029490116983652115,
      "rewards/accuracy_reward": 0.8571906089782715,
      "rewards/format_reward": 1.0,
      "step": 2423
    },
    {
      "all_correct": 0.75,
      "all_wrong": 0.0,
      "completion_length": 380.65625,
      "epoch": 0.033434021599702074,
      "grad_norm": 3.863580668796059,
      "kl": 0.08349609375,
      "learning_rate": 9.97244390505537e-07,
      "loss": 0.0033,
      "reward": 2.0817813873291016,
      "reward_std": 0.013757359236478806,
      "rewards/accuracy_reward": 0.8817812204360962,
      "rewards/format_reward": 1.0,
      "step": 2424
    },
    {
      "all_correct": 0.25,
      "all_wrong": 0.0,
      "completion_length": 376.65625,
      "epoch": 0.03344781451290327,
      "grad_norm": 3.054151597245667,
      "kl": 0.0888671875,
      "learning_rate": 9.972421185242169e-07,
      "loss": 0.0036,
      "reward": 2.098656177520752,
      "reward_std": 0.048749424517154694,
      "rewards/accuracy_reward": 0.9111562967300415,
      "rewards/format_reward": 1.0,
      "step": 2425
    },
    {
      "all_correct": 1.0,
      "all_wrong": 0.0,
      "completion_length": 379.4375,
      "epoch": 0.03346160742610447,
      "grad_norm": 2.577269652225504,
      "kl": 0.0830078125,
      "learning_rate": 9.972398456092562e-07,
      "loss": 0.0033,
      "reward": 2.1077189445495605,
      "reward_std": 0.01511446014046669,
      "rewards/accuracy_reward": 0.9077187180519104,
      "rewards/format_reward": 1.0,
      "step": 2426
    },
    {
      "all_correct": 1.0,
      "all_wrong": 0.0,
      "completion_length": 384.375,
      "epoch": 0.03347540033930566,
      "grad_norm": 3.8511200990567733,
      "kl": 0.0810546875,
      "learning_rate": 9.972375717606593e-07,
      "loss": 0.0033,
      "reward": 2.142937660217285,
      "reward_std": 0.010026934556663036,
      "rewards/accuracy_reward": 0.9429374933242798,
      "rewards/format_reward": 1.0,
      "step": 2427
    },
    {
      "all_correct": 0.75,
      "all_wrong": 0.0,
      "completion_length": 384.875,
      "epoch": 0.03348919325250686,
      "grad_norm": 2.088545057038509,
      "kl": 0.08447265625,
      "learning_rate": 9.972352969784305e-07,
      "loss": 0.0034,
      "reward": 2.131333351135254,
      "reward_std": 0.0233272984623909,
      "rewards/accuracy_reward": 0.937583327293396,
      "rewards/format_reward": 1.0,
      "step": 2428
    },
    {
      "all_correct": 0.75,
      "all_wrong": 0.0,
      "completion_length": 389.34375,
      "epoch": 0.03350298616570806,
      "grad_norm": 2.3506554559714754,
      "kl": 0.0859375,
      "learning_rate": 9.97233021262574e-07,
      "loss": 0.0035,
      "reward": 2.0661563873291016,
      "reward_std": 0.02349940314888954,
      "rewards/accuracy_reward": 0.8724062442779541,
      "rewards/format_reward": 1.0,
      "step": 2429
    },
    {
      "all_correct": 1.0,
      "all_wrong": 0.0,
      "completion_length": 398.375,
      "epoch": 0.03351677907890926,
      "grad_norm": 3.617462970624219,
      "kl": 0.087890625,
      "learning_rate": 9.972307446130944e-07,
      "loss": 0.0035,
      "reward": 2.082750082015991,
      "reward_std": 0.01732909306883812,
      "rewards/accuracy_reward": 0.8827500343322754,
      "rewards/format_reward": 1.0,
      "step": 2430
    },
    {
      "all_correct": 0.25,
      "all_wrong": 0.0,
      "completion_length": 387.0625,
      "epoch": 0.03353057199211045,
      "grad_norm": 7.24485562526061,
      "kl": 0.08642578125,
      "learning_rate": 9.972284670299955e-07,
      "loss": 0.0034,
      "reward": 1.9272499084472656,
      "reward_std": 0.010798781178891659,
      "rewards/accuracy_reward": 0.7272499799728394,
      "rewards/format_reward": 1.0,
      "step": 2431
    },
    {
      "all_correct": 1.0,
      "all_wrong": 0.0,
      "completion_length": 407.34375,
      "epoch": 0.03354436490531165,
      "grad_norm": 2.4207804705077756,
      "kl": 0.08203125,
      "learning_rate": 9.97226188513282e-07,
      "loss": 0.0033,
      "reward": 2.1395626068115234,
      "reward_std": 0.009129272773861885,
      "rewards/accuracy_reward": 0.9395624399185181,
      "rewards/format_reward": 1.0,
      "step": 2432
    },
    {
      "all_correct": 1.0,
      "all_wrong": 0.0,
      "completion_length": 413.25,
      "epoch": 0.033558157818512846,
      "grad_norm": 2.4855238197036686,
      "kl": 0.08154296875,
      "learning_rate": 9.972239090629578e-07,
      "loss": 0.0033,
      "reward": 2.10868763923645,
      "reward_std": 0.0074102627113461494,
      "rewards/accuracy_reward": 0.9086875319480896,
      "rewards/format_reward": 1.0,
      "step": 2433
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.0,
      "completion_length": 399.9375,
      "epoch": 0.03357195073171405,
      "grad_norm": 2.664360697631489,
      "kl": 0.08837890625,
      "learning_rate": 9.972216286790272e-07,
      "loss": 0.0035,
      "reward": 2.0164687633514404,
      "reward_std": 0.012277012690901756,
      "rewards/accuracy_reward": 0.8164688348770142,
      "rewards/format_reward": 1.0,
      "step": 2434
    },
    {
      "all_correct": 0.75,
      "all_wrong": 0.0,
      "completion_length": 400.75,
      "epoch": 0.03358574364491524,
      "grad_norm": 3.51656537641986,
      "kl": 0.0869140625,
      "learning_rate": 9.972193473614948e-07,
      "loss": 0.0035,
      "reward": 2.0055625438690186,
      "reward_std": 0.0083012655377388,
      "rewards/accuracy_reward": 0.8055624961853027,
      "rewards/format_reward": 1.0,
      "step": 2435
    },
    {
      "all_correct": 0.75,
      "all_wrong": 0.0,
      "completion_length": 403.625,
      "epoch": 0.03359953655811644,
      "grad_norm": 4.083725203407614,
      "kl": 0.08642578125,
      "learning_rate": 9.972170651103647e-07,
      "loss": 0.0035,
      "reward": 2.0890936851501465,
      "reward_std": 0.03324972838163376,
      "rewards/accuracy_reward": 0.8890937566757202,
      "rewards/format_reward": 1.0,
      "step": 2436
    },
    {
      "all_correct": 0.25,
      "all_wrong": 0.0,
      "completion_length": 406.6875,
      "epoch": 0.033613329471317635,
      "grad_norm": 4.47755386213965,
      "kl": 0.0966796875,
      "learning_rate": 9.97214781925641e-07,
      "loss": 0.0039,
      "reward": 1.9827501773834229,
      "reward_std": 0.01662595197558403,
      "rewards/accuracy_reward": 0.7827500104904175,
      "rewards/format_reward": 1.0,
      "step": 2437
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.0,
      "completion_length": 388.09375,
      "epoch": 0.033627122384518836,
      "grad_norm": 1.897925868444686,
      "kl": 0.0830078125,
      "learning_rate": 9.972124978073284e-07,
      "loss": 0.0033,
      "reward": 2.0619375705718994,
      "reward_std": 0.006030885502696037,
      "rewards/accuracy_reward": 0.8619375824928284,
      "rewards/format_reward": 1.0,
      "step": 2438
    },
    {
      "all_correct": 0.75,
      "all_wrong": 0.0,
      "completion_length": 393.53125,
      "epoch": 0.03364091529772003,
      "grad_norm": 2.385725610135012,
      "kl": 0.0810546875,
      "learning_rate": 9.972102127554307e-07,
      "loss": 0.0032,
      "reward": 2.0602188110351562,
      "reward_std": 0.007102045696228743,
      "rewards/accuracy_reward": 0.8602187633514404,
      "rewards/format_reward": 1.0,
      "step": 2439
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.0,
      "completion_length": 400.90625,
      "epoch": 0.03365470821092123,
      "grad_norm": 5.65282098650959,
      "kl": 0.0830078125,
      "learning_rate": 9.972079267699526e-07,
      "loss": 0.0033,
      "reward": 2.0046563148498535,
      "reward_std": 0.019091207534074783,
      "rewards/accuracy_reward": 0.8046562671661377,
      "rewards/format_reward": 1.0,
      "step": 2440
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.0,
      "completion_length": 405.53125,
      "epoch": 0.033668501124122424,
      "grad_norm": 4.669345736260731,
      "kl": 0.0849609375,
      "learning_rate": 9.972056398508984e-07,
      "loss": 0.0034,
      "reward": 2.0408437252044678,
      "reward_std": 0.012706535868346691,
      "rewards/accuracy_reward": 0.8408437371253967,
      "rewards/format_reward": 1.0,
      "step": 2441
    },
    {
      "all_correct": 1.0,
      "all_wrong": 0.0,
      "completion_length": 404.0625,
      "epoch": 0.033682294037323625,
      "grad_norm": 3.0949382951462696,
      "kl": 0.08251953125,
      "learning_rate": 9.97203351998272e-07,
      "loss": 0.0033,
      "reward": 2.168656349182129,
      "reward_std": 0.01767483353614807,
      "rewards/accuracy_reward": 0.9686563014984131,
      "rewards/format_reward": 1.0,
      "step": 2442
    },
    {
      "all_correct": 1.0,
      "all_wrong": 0.0,
      "completion_length": 403.1875,
      "epoch": 0.03369608695052482,
      "grad_norm": 2.7724112619274925,
      "kl": 0.07666015625,
      "learning_rate": 9.97201063212078e-07,
      "loss": 0.0031,
      "reward": 2.1036248207092285,
      "reward_std": 0.01158314198255539,
      "rewards/accuracy_reward": 0.9036250114440918,
      "rewards/format_reward": 1.0,
      "step": 2443
    },
    {
      "all_correct": 0.75,
      "all_wrong": 0.0,
      "completion_length": 401.875,
      "epoch": 0.03370987986372602,
      "grad_norm": 2.6676294727136107,
      "kl": 0.083984375,
      "learning_rate": 9.97198773492321e-07,
      "loss": 0.0034,
      "reward": 2.1239376068115234,
      "reward_std": 0.025089092552661896,
      "rewards/accuracy_reward": 0.9239374995231628,
      "rewards/format_reward": 1.0,
      "step": 2444
    },
    {
      "all_correct": 0.75,
      "all_wrong": 0.0,
      "completion_length": 386.34375,
      "epoch": 0.03372367277692721,
      "grad_norm": 2.642678056326857,
      "kl": 0.08984375,
      "learning_rate": 9.971964828390047e-07,
      "loss": 0.0036,
      "reward": 2.026249885559082,
      "reward_std": 0.011902209371328354,
      "rewards/accuracy_reward": 0.8262499570846558,
      "rewards/format_reward": 1.0,
      "step": 2445
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.0,
      "completion_length": 393.3125,
      "epoch": 0.033737465690128414,
      "grad_norm": 4.595366298878818,
      "kl": 0.07958984375,
      "learning_rate": 9.971941912521335e-07,
      "loss": 0.0032,
      "reward": 2.0620625019073486,
      "reward_std": 0.012353375554084778,
      "rewards/accuracy_reward": 0.8620625138282776,
      "rewards/format_reward": 1.0,
      "step": 2446
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.0,
      "completion_length": 396.875,
      "epoch": 0.03375125860332961,
      "grad_norm": 3.0458713282711183,
      "kl": 0.0830078125,
      "learning_rate": 9.971918987317117e-07,
      "loss": 0.0033,
      "reward": 2.0361876487731934,
      "reward_std": 0.021022191271185875,
      "rewards/accuracy_reward": 0.8361876010894775,
      "rewards/format_reward": 1.0,
      "step": 2447
    },
    {
      "all_correct": 1.0,
      "all_wrong": 0.0,
      "completion_length": 399.1875,
      "epoch": 0.03376505151653081,
      "grad_norm": 3.6574162160207377,
      "kl": 0.08984375,
      "learning_rate": 9.97189605277744e-07,
      "loss": 0.0036,
      "reward": 2.151750087738037,
      "reward_std": 0.011491785757243633,
      "rewards/accuracy_reward": 0.9517499804496765,
      "rewards/format_reward": 1.0,
      "step": 2448
    },
    {
      "all_correct": 1.0,
      "all_wrong": 0.0,
      "completion_length": 392.0,
      "epoch": 0.033778844429732,
      "grad_norm": 2.63140295141255,
      "kl": 0.08056640625,
      "learning_rate": 9.971873108902345e-07,
      "loss": 0.0032,
      "reward": 2.1619999408721924,
      "reward_std": 0.007781158667057753,
      "rewards/accuracy_reward": 0.9620000123977661,
      "rewards/format_reward": 1.0,
      "step": 2449
    },
    {
      "all_correct": 0.75,
      "all_wrong": 0.0,
      "completion_length": 390.40625,
      "epoch": 0.0337926373429332,
      "grad_norm": 3.093291900477158,
      "kl": 0.078125,
      "learning_rate": 9.971850155691874e-07,
      "loss": 0.0031,
      "reward": 2.122781276702881,
      "reward_std": 0.044731613248586655,
      "rewards/accuracy_reward": 0.922781229019165,
      "rewards/format_reward": 1.0,
      "step": 2450
    },
    {
      "all_correct": 1.0,
      "all_wrong": 0.0,
      "completion_length": 386.9375,
      "epoch": 0.0338064302561344,
      "grad_norm": 6.463156689368654,
      "kl": 0.0703125,
      "learning_rate": 9.97182719314607e-07,
      "loss": 0.0028,
      "reward": 2.1404688358306885,
      "reward_std": 0.010282193310558796,
      "rewards/accuracy_reward": 0.9404687881469727,
      "rewards/format_reward": 1.0,
      "step": 2451
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.0,
      "completion_length": 385.84375,
      "epoch": 0.0338202231693356,
      "grad_norm": 2.896773754705013,
      "kl": 0.0830078125,
      "learning_rate": 9.971804221264977e-07,
      "loss": 0.0033,
      "reward": 2.1138124465942383,
      "reward_std": 0.03136708587408066,
      "rewards/accuracy_reward": 0.9263125061988831,
      "rewards/format_reward": 1.0,
      "step": 2452
    },
    {
      "all_correct": 1.0,
      "all_wrong": 0.0,
      "completion_length": 373.3125,
      "epoch": 0.03383401608253679,
      "grad_norm": 3.3747246201428163,
      "kl": 0.0869140625,
      "learning_rate": 9.971781240048639e-07,
      "loss": 0.0035,
      "reward": 2.1637189388275146,
      "reward_std": 0.0077643669210374355,
      "rewards/accuracy_reward": 0.9637187719345093,
      "rewards/format_reward": 1.0,
      "step": 2453
    },
    {
      "all_correct": 0.25,
      "all_wrong": 0.0,
      "completion_length": 370.875,
      "epoch": 0.03384780899573799,
      "grad_norm": 3.9642644702356495,
      "kl": 0.0908203125,
      "learning_rate": 9.971758249497096e-07,
      "loss": 0.0036,
      "reward": 2.0025625228881836,
      "reward_std": 0.037515923380851746,
      "rewards/accuracy_reward": 0.8150624632835388,
      "rewards/format_reward": 1.0,
      "step": 2454
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.0,
      "completion_length": 374.46875,
      "epoch": 0.033861601908939186,
      "grad_norm": 3.3502580157771495,
      "kl": 0.0830078125,
      "learning_rate": 9.971735249610394e-07,
      "loss": 0.0033,
      "reward": 2.0908751487731934,
      "reward_std": 0.024314774200320244,
      "rewards/accuracy_reward": 0.8971249461174011,
      "rewards/format_reward": 1.0,
      "step": 2455
    },
    {
      "all_correct": 1.0,
      "all_wrong": 0.0,
      "completion_length": 380.375,
      "epoch": 0.03387539482214039,
      "grad_norm": 5.394240688036444,
      "kl": 0.0859375,
      "learning_rate": 9.971712240388576e-07,
      "loss": 0.0035,
      "reward": 2.1338438987731934,
      "reward_std": 0.017250115051865578,
      "rewards/accuracy_reward": 0.933843731880188,
      "rewards/format_reward": 1.0,
      "step": 2456
    },
    {
      "all_correct": 0.75,
      "all_wrong": 0.0,
      "completion_length": 375.15625,
      "epoch": 0.03388918773534158,
      "grad_norm": 4.685872872380482,
      "kl": 0.08984375,
      "learning_rate": 9.971689221831684e-07,
      "loss": 0.0036,
      "reward": 2.1126251220703125,
      "reward_std": 0.02720843441784382,
      "rewards/accuracy_reward": 0.918874979019165,
      "rewards/format_reward": 1.0,
      "step": 2457
    },
    {
      "all_correct": 0.75,
      "all_wrong": 0.0,
      "completion_length": 381.90625,
      "epoch": 0.03390298064854278,
      "grad_norm": 2.160279344611698,
      "kl": 0.07958984375,
      "learning_rate": 9.971666193939763e-07,
      "loss": 0.0032,
      "reward": 2.159656286239624,
      "reward_std": 0.0219342689961195,
      "rewards/accuracy_reward": 0.9659062623977661,
      "rewards/format_reward": 1.0,
      "step": 2458
    },
    {
      "all_correct": 1.0,
      "all_wrong": 0.0,
      "completion_length": 379.6875,
      "epoch": 0.033916773561743975,
      "grad_norm": 2.057524035915639,
      "kl": 0.08447265625,
      "learning_rate": 9.971643156712855e-07,
      "loss": 0.0034,
      "reward": 2.165253162384033,
      "reward_std": 0.009145085699856281,
      "rewards/accuracy_reward": 0.9652531147003174,
      "rewards/format_reward": 1.0,
      "step": 2459
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.0,
      "completion_length": 378.03125,
      "epoch": 0.033930566474945176,
      "grad_norm": 6.565121450329172,
      "kl": 0.0810546875,
      "learning_rate": 9.971620110151002e-07,
      "loss": 0.0033,
      "reward": 2.0455312728881836,
      "reward_std": 0.03897400200366974,
      "rewards/accuracy_reward": 0.8580312132835388,
      "rewards/format_reward": 1.0,
      "step": 2460
    },
    {
      "all_correct": 1.0,
      "all_wrong": 0.0,
      "completion_length": 387.78125,
      "epoch": 0.03394435938814637,
      "grad_norm": 3.2723399725121682,
      "kl": 0.07080078125,
      "learning_rate": 9.971597054254248e-07,
      "loss": 0.0028,
      "reward": 2.092750072479248,
      "reward_std": 0.006710412912070751,
      "rewards/accuracy_reward": 0.8927499651908875,
      "rewards/format_reward": 1.0,
      "step": 2461
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.0,
      "completion_length": 393.59375,
      "epoch": 0.03395815230134757,
      "grad_norm": 2.3234776316756336,
      "kl": 0.07275390625,
      "learning_rate": 9.97157398902264e-07,
      "loss": 0.0029,
      "reward": 2.103781223297119,
      "reward_std": 0.02257383055984974,
      "rewards/accuracy_reward": 0.9100311994552612,
      "rewards/format_reward": 1.0,
      "step": 2462
    },
    {
      "all_correct": 1.0,
      "all_wrong": 0.0,
      "completion_length": 397.0,
      "epoch": 0.033971945214548764,
      "grad_norm": 2.3517598987425403,
      "kl": 0.0859375,
      "learning_rate": 9.971550914456217e-07,
      "loss": 0.0034,
      "reward": 2.134031295776367,
      "reward_std": 0.010852044448256493,
      "rewards/accuracy_reward": 0.9340312480926514,
      "rewards/format_reward": 1.0,
      "step": 2463
    },
    {
      "all_correct": 0.75,
      "all_wrong": 0.0,
      "completion_length": 380.6875,
      "epoch": 0.033985738127749965,
      "grad_norm": 4.7973722135779475,
      "kl": 0.09033203125,
      "learning_rate": 9.971527830555021e-07,
      "loss": 0.0036,
      "reward": 2.040468692779541,
      "reward_std": 0.010141235776245594,
      "rewards/accuracy_reward": 0.84046870470047,
      "rewards/format_reward": 1.0,
      "step": 2464
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.0,
      "completion_length": 384.15625,
      "epoch": 0.03399953104095116,
      "grad_norm": 3.0173789702295157,
      "kl": 0.08154296875,
      "learning_rate": 9.971504737319101e-07,
      "loss": 0.0033,
      "reward": 2.0005626678466797,
      "reward_std": 0.07080061733722687,
      "rewards/accuracy_reward": 0.8005625009536743,
      "rewards/format_reward": 1.0,
      "step": 2465
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.0,
      "completion_length": 387.59375,
      "epoch": 0.03401332395415236,
      "grad_norm": 2.6133684855381283,
      "kl": 0.09521484375,
      "learning_rate": 9.971481634748495e-07,
      "loss": 0.0038,
      "reward": 2.0197813510894775,
      "reward_std": 0.03206191211938858,
      "rewards/accuracy_reward": 0.8260312676429749,
      "rewards/format_reward": 1.0,
      "step": 2466
    },
    {
      "all_correct": 1.0,
      "all_wrong": 0.0,
      "completion_length": 398.625,
      "epoch": 0.03402711686735355,
      "grad_norm": 5.866873540986668,
      "kl": 0.08349609375,
      "learning_rate": 9.97145852284325e-07,
      "loss": 0.0033,
      "reward": 2.117906332015991,
      "reward_std": 0.007888181135058403,
      "rewards/accuracy_reward": 0.9179062843322754,
      "rewards/format_reward": 1.0,
      "step": 2467
    },
    {
      "all_correct": 0.75,
      "all_wrong": 0.0,
      "completion_length": 384.78125,
      "epoch": 0.034040909780554754,
      "grad_norm": 5.0572905549114076,
      "kl": 0.08935546875,
      "learning_rate": 9.971435401603407e-07,
      "loss": 0.0036,
      "reward": 2.0903749465942383,
      "reward_std": 0.027681348845362663,
      "rewards/accuracy_reward": 0.8966250419616699,
      "rewards/format_reward": 1.0,
      "step": 2468
    },
    {
      "all_correct": 0.75,
      "all_wrong": 0.0,
      "completion_length": 382.59375,
      "epoch": 0.03405470269375595,
      "grad_norm": 1.3156902998176172,
      "kl": 0.0810546875,
      "learning_rate": 9.971412271029013e-07,
      "loss": 0.0032,
      "reward": 2.1235625743865967,
      "reward_std": 0.023817671462893486,
      "rewards/accuracy_reward": 0.9360624551773071,
      "rewards/format_reward": 1.0,
      "step": 2469
    },
    {
      "all_correct": 0.25,
      "all_wrong": 0.0,
      "completion_length": 411.9375,
      "epoch": 0.03406849560695715,
      "grad_norm": 3.7195421296306668,
      "kl": 0.08642578125,
      "learning_rate": 9.971389131120108e-07,
      "loss": 0.0035,
      "reward": 1.964093804359436,
      "reward_std": 0.06583546102046967,
      "rewards/accuracy_reward": 0.7640937566757202,
      "rewards/format_reward": 1.0,
      "step": 2470
    },
    {
      "all_correct": 0.75,
      "all_wrong": 0.0,
      "completion_length": 402.15625,
      "epoch": 0.03408228852015834,
      "grad_norm": 3.0295248489458633,
      "kl": 0.08837890625,
      "learning_rate": 9.971365981876734e-07,
      "loss": 0.0035,
      "reward": 2.101830005645752,
      "reward_std": 0.02001786045730114,
      "rewards/accuracy_reward": 0.9018298387527466,
      "rewards/format_reward": 1.0,
      "step": 2471
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.0,
      "completion_length": 389.5625,
      "epoch": 0.03409608143335954,
      "grad_norm": 7.1150072581499995,
      "kl": 0.08447265625,
      "learning_rate": 9.97134282329894e-07,
      "loss": 0.0034,
      "reward": 2.0817813873291016,
      "reward_std": 0.026779845356941223,
      "rewards/accuracy_reward": 0.881781280040741,
      "rewards/format_reward": 1.0,
      "step": 2472
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.0,
      "completion_length": 400.71875,
      "epoch": 0.03410987434656074,
      "grad_norm": 4.195636147756919,
      "kl": 0.0869140625,
      "learning_rate": 9.971319655386763e-07,
      "loss": 0.0035,
      "reward": 2.0225937366485596,
      "reward_std": 0.029494451358914375,
      "rewards/accuracy_reward": 0.8288437128067017,
      "rewards/format_reward": 1.0,
      "step": 2473
    },
    {
      "all_correct": 1.0,
      "all_wrong": 0.0,
      "completion_length": 416.46875,
      "epoch": 0.03412366725976194,
      "grad_norm": 2.3419742955447007,
      "kl": 0.09033203125,
      "learning_rate": 9.97129647814025e-07,
      "loss": 0.0036,
      "reward": 2.1741561889648438,
      "reward_std": 0.006099590100347996,
      "rewards/accuracy_reward": 0.9741562604904175,
      "rewards/format_reward": 1.0,
      "step": 2474
    },
    {
      "all_correct": 0.75,
      "all_wrong": 0.0,
      "completion_length": 412.0625,
      "epoch": 0.03413746017296313,
      "grad_norm": 2.772833498800288,
      "kl": 0.08642578125,
      "learning_rate": 9.971273291559446e-07,
      "loss": 0.0035,
      "reward": 2.1161561012268066,
      "reward_std": 0.0149550661444664,
      "rewards/accuracy_reward": 0.9161562323570251,
      "rewards/format_reward": 1.0,
      "step": 2475
    },
    {
      "all_correct": 1.0,
      "all_wrong": 0.0,
      "completion_length": 407.34375,
      "epoch": 0.03415125308616433,
      "grad_norm": 3.898858564895746,
      "kl": 0.09326171875,
      "learning_rate": 9.971250095644392e-07,
      "loss": 0.0037,
      "reward": 2.1189374923706055,
      "reward_std": 0.017431240528821945,
      "rewards/accuracy_reward": 0.9189375042915344,
      "rewards/format_reward": 1.0,
      "step": 2476
    },
    {
      "all_correct": 0.75,
      "all_wrong": 0.0,
      "completion_length": 413.34375,
      "epoch": 0.034165045999365526,
      "grad_norm": 2.9555917020149574,
      "kl": 0.09228515625,
      "learning_rate": 9.971226890395132e-07,
      "loss": 0.0037,
      "reward": 2.019031286239624,
      "reward_std": 0.013402904383838177,
      "rewards/accuracy_reward": 0.8190311789512634,
      "rewards/format_reward": 1.0,
      "step": 2477
    },
    {
      "all_correct": 0.25,
      "all_wrong": 0.0,
      "completion_length": 412.75,
      "epoch": 0.03417883891256673,
      "grad_norm": 3.0685472343498463,
      "kl": 0.0791015625,
      "learning_rate": 9.97120367581171e-07,
      "loss": 0.0032,
      "reward": 1.9044687747955322,
      "reward_std": 0.04219035804271698,
      "rewards/accuracy_reward": 0.7107187509536743,
      "rewards/format_reward": 1.0,
      "step": 2478
    },
    {
      "all_correct": 0.25,
      "all_wrong": 0.0,
      "completion_length": 406.71875,
      "epoch": 0.03419263182576792,
      "grad_norm": 3.2418424809581268,
      "kl": 0.0859375,
      "learning_rate": 9.971180451894172e-07,
      "loss": 0.0035,
      "reward": 1.980125069618225,
      "reward_std": 0.014232121407985687,
      "rewards/accuracy_reward": 0.7801250219345093,
      "rewards/format_reward": 1.0,
      "step": 2479
    },
    {
      "all_correct": 0.75,
      "all_wrong": 0.0,
      "completion_length": 402.90625,
      "epoch": 0.034206424738969114,
      "grad_norm": 2.6745811352136974,
      "kl": 0.08447265625,
      "learning_rate": 9.971157218642556e-07,
      "loss": 0.0034,
      "reward": 1.9965624809265137,
      "reward_std": 0.010226715356111526,
      "rewards/accuracy_reward": 0.7965624332427979,
      "rewards/format_reward": 1.0,
      "step": 2480
    },
    {
      "all_correct": 0.75,
      "all_wrong": 0.0,
      "completion_length": 416.84375,
      "epoch": 0.034220217652170315,
      "grad_norm": 4.930951633392177,
      "kl": 0.083984375,
      "learning_rate": 9.97113397605691e-07,
      "loss": 0.0034,
      "reward": 2.0781562328338623,
      "reward_std": 0.015688687562942505,
      "rewards/accuracy_reward": 0.8781561851501465,
      "rewards/format_reward": 1.0,
      "step": 2481
    },
    {
      "all_correct": 1.0,
      "all_wrong": 0.0,
      "completion_length": 410.09375,
      "epoch": 0.03423401056537151,
      "grad_norm": 3.437921211682119,
      "kl": 0.07568359375,
      "learning_rate": 9.971110724137276e-07,
      "loss": 0.003,
      "reward": 2.119374990463257,
      "reward_std": 0.01475725881755352,
      "rewards/accuracy_reward": 0.9193750023841858,
      "rewards/format_reward": 1.0,
      "step": 2482
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.0,
      "completion_length": 427.875,
      "epoch": 0.03424780347857271,
      "grad_norm": 3.3107338780351347,
      "kl": 0.078125,
      "learning_rate": 9.971087462883697e-07,
      "loss": 0.0031,
      "reward": 2.0736875534057617,
      "reward_std": 0.008253393694758415,
      "rewards/accuracy_reward": 0.8736873865127563,
      "rewards/format_reward": 1.0,
      "step": 2483
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.0,
      "completion_length": 416.6875,
      "epoch": 0.0342615963917739,
      "grad_norm": 4.475249844210883,
      "kl": 0.08447265625,
      "learning_rate": 9.971064192296222e-07,
      "loss": 0.0034,
      "reward": 1.9825000762939453,
      "reward_std": 0.028541497886180878,
      "rewards/accuracy_reward": 0.7887499332427979,
      "rewards/format_reward": 1.0,
      "step": 2484
    },
    {
      "all_correct": 0.75,
      "all_wrong": 0.0,
      "completion_length": 406.40625,
      "epoch": 0.034275389304975104,
      "grad_norm": 2.879428313194441,
      "kl": 0.087890625,
      "learning_rate": 9.971040912374886e-07,
      "loss": 0.0035,
      "reward": 2.1397812366485596,
      "reward_std": 0.013590086251497269,
      "rewards/accuracy_reward": 0.9397812485694885,
      "rewards/format_reward": 1.0,
      "step": 2485
    },
    {
      "all_correct": 0.75,
      "all_wrong": 0.0,
      "completion_length": 420.59375,
      "epoch": 0.0342891822181763,
      "grad_norm": 6.317778461168252,
      "kl": 0.0810546875,
      "learning_rate": 9.971017623119739e-07,
      "loss": 0.0032,
      "reward": 2.13853120803833,
      "reward_std": 0.013636965304613113,
      "rewards/accuracy_reward": 0.9385312795639038,
      "rewards/format_reward": 1.0,
      "step": 2486
    },
    {
      "all_correct": 1.0,
      "all_wrong": 0.0,
      "completion_length": 407.0,
      "epoch": 0.0343029751313775,
      "grad_norm": 2.5873515223000747,
      "kl": 0.08349609375,
      "learning_rate": 9.970994324530824e-07,
      "loss": 0.0033,
      "reward": 2.1447501182556152,
      "reward_std": 0.012977300211787224,
      "rewards/accuracy_reward": 0.9447499513626099,
      "rewards/format_reward": 1.0,
      "step": 2487
    },
    {
      "all_correct": 1.0,
      "all_wrong": 0.0,
      "completion_length": 415.5625,
      "epoch": 0.03431676804457869,
      "grad_norm": 2.9246081118692167,
      "kl": 0.0869140625,
      "learning_rate": 9.97097101660818e-07,
      "loss": 0.0035,
      "reward": 2.1542186737060547,
      "reward_std": 0.015418612398207188,
      "rewards/accuracy_reward": 0.9542188048362732,
      "rewards/format_reward": 1.0,
      "step": 2488
    },
    {
      "all_correct": 0.25,
      "all_wrong": 0.0,
      "completion_length": 427.5625,
      "epoch": 0.03433056095777989,
      "grad_norm": 2.0930674403234195,
      "kl": 0.08154296875,
      "learning_rate": 9.970947699351857e-07,
      "loss": 0.0033,
      "reward": 2.055093765258789,
      "reward_std": 0.030023913830518723,
      "rewards/accuracy_reward": 0.8613437414169312,
      "rewards/format_reward": 1.0,
      "step": 2489
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.0,
      "completion_length": 414.4375,
      "epoch": 0.03434435387098109,
      "grad_norm": 3.9937996142284558,
      "kl": 0.0791015625,
      "learning_rate": 9.970924372761896e-07,
      "loss": 0.0032,
      "reward": 2.0469062328338623,
      "reward_std": 0.03693939745426178,
      "rewards/accuracy_reward": 0.8531562089920044,
      "rewards/format_reward": 1.0,
      "step": 2490
    },
    {
      "all_correct": 1.0,
      "all_wrong": 0.0,
      "completion_length": 421.96875,
      "epoch": 0.03435814678418229,
      "grad_norm": 2.8254197294337,
      "kl": 0.07421875,
      "learning_rate": 9.970901036838342e-07,
      "loss": 0.003,
      "reward": 2.131687641143799,
      "reward_std": 0.010842893272638321,
      "rewards/accuracy_reward": 0.9316875338554382,
      "rewards/format_reward": 1.0,
      "step": 2491
    },
    {
      "all_correct": 0.25,
      "all_wrong": 0.0,
      "completion_length": 417.15625,
      "epoch": 0.03437193969738348,
      "grad_norm": 1.9596384483936762,
      "kl": 0.08837890625,
      "learning_rate": 9.970877691581236e-07,
      "loss": 0.0035,
      "reward": 2.0266876220703125,
      "reward_std": 0.0414372943341732,
      "rewards/accuracy_reward": 0.839187502861023,
      "rewards/format_reward": 1.0,
      "step": 2492
    },
    {
      "all_correct": 1.0,
      "all_wrong": 0.0,
      "completion_length": 407.28125,
      "epoch": 0.03438573261058468,
      "grad_norm": 2.2381669334726952,
      "kl": 0.07421875,
      "learning_rate": 9.970854336990624e-07,
      "loss": 0.003,
      "reward": 2.1756250858306885,
      "reward_std": 0.009924383834004402,
      "rewards/accuracy_reward": 0.9756249785423279,
      "rewards/format_reward": 1.0,
      "step": 2493
    },
    {
      "all_correct": 1.0,
      "all_wrong": 0.0,
      "completion_length": 422.15625,
      "epoch": 0.034399525523785876,
      "grad_norm": 2.5692768372546446,
      "kl": 0.0830078125,
      "learning_rate": 9.970830973066549e-07,
      "loss": 0.0033,
      "reward": 2.101468801498413,
      "reward_std": 0.01245273556560278,
      "rewards/accuracy_reward": 0.9014687538146973,
      "rewards/format_reward": 1.0,
      "step": 2494
    },
    {
      "all_correct": 0.75,
      "all_wrong": 0.0,
      "completion_length": 411.1875,
      "epoch": 0.03441331843698708,
      "grad_norm": 7.57162041956244,
      "kl": 0.07470703125,
      "learning_rate": 9.970807599809056e-07,
      "loss": 0.003,
      "reward": 2.079625129699707,
      "reward_std": 0.008041145280003548,
      "rewards/accuracy_reward": 0.8796249628067017,
      "rewards/format_reward": 1.0,
      "step": 2495
    },
    {
      "all_correct": 1.0,
      "all_wrong": 0.0,
      "completion_length": 412.125,
      "epoch": 0.03442711135018827,
      "grad_norm": 2.3123518034331125,
      "kl": 0.083984375,
      "learning_rate": 9.97078421721819e-07,
      "loss": 0.0034,
      "reward": 2.1514687538146973,
      "reward_std": 0.009307511150836945,
      "rewards/accuracy_reward": 0.9514687657356262,
      "rewards/format_reward": 1.0,
      "step": 2496
    },
    {
      "all_correct": 1.0,
      "all_wrong": 0.0,
      "completion_length": 411.03125,
      "epoch": 0.03444090426338947,
      "grad_norm": 4.411916140559651,
      "kl": 0.083984375,
      "learning_rate": 9.97076082529399e-07,
      "loss": 0.0034,
      "reward": 2.152156352996826,
      "reward_std": 0.010378116741776466,
      "rewards/accuracy_reward": 0.9521562457084656,
      "rewards/format_reward": 1.0,
      "step": 2497
    },
    {
      "all_correct": 0.75,
      "all_wrong": 0.0,
      "completion_length": 399.65625,
      "epoch": 0.034454697176590665,
      "grad_norm": 2.4775239786426533,
      "kl": 0.0771484375,
      "learning_rate": 9.970737424036504e-07,
      "loss": 0.0031,
      "reward": 2.0715625286102295,
      "reward_std": 0.013272336684167385,
      "rewards/accuracy_reward": 0.8715626001358032,
      "rewards/format_reward": 1.0,
      "step": 2498
    },
    {
      "all_correct": 0.25,
      "all_wrong": 0.0,
      "completion_length": 390.78125,
      "epoch": 0.034468490089791866,
      "grad_norm": 2.04170119441449,
      "kl": 0.08642578125,
      "learning_rate": 9.970714013445775e-07,
      "loss": 0.0035,
      "reward": 1.9000937938690186,
      "reward_std": 0.006583128124475479,
      "rewards/accuracy_reward": 0.7000937461853027,
      "rewards/format_reward": 1.0,
      "step": 2499
    },
    {
      "all_correct": 1.0,
      "all_wrong": 0.0,
      "completion_length": 381.15625,
      "epoch": 0.03448228300299306,
      "grad_norm": 4.124821929364961,
      "kl": 0.0859375,
      "learning_rate": 9.970690593521847e-07,
      "loss": 0.0034,
      "reward": 2.112281322479248,
      "reward_std": 0.03347647190093994,
      "rewards/accuracy_reward": 0.9185312390327454,
      "rewards/format_reward": 1.0,
      "step": 2500
    }
  ],
  "logging_steps": 1.0,
  "max_steps": 72501,
  "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": false
      },
      "attributes": {}
    }
  },
  "total_flos": 0.0,
  "train_batch_size": 1,
  "trial_name": null,
  "trial_params": null
}