{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.019843238416509576,
  "eval_steps": 500,
  "global_step": 100,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "completion_length": 673.5,
      "epoch": 0.00019843238416509574,
      "grad_norm": 0.0,
      "kl": 0.0,
      "learning_rate": 1e-05,
      "loss": 0.0,
      "reward": 0.0,
      "reward_std": 0.0,
      "rewards/correctness_reward_func": 0.0,
      "step": 1
    },
    {
      "completion_length": 589.625,
      "epoch": 0.0003968647683301915,
      "grad_norm": 0.2197265625,
      "kl": 0.0,
      "learning_rate": 1e-05,
      "loss": -0.0,
      "reward": 1.375,
      "reward_std": 0.39433756470680237,
      "rewards/correctness_reward_func": 1.375,
      "step": 2
    },
    {
      "completion_length": 408.28125,
      "epoch": 0.0005952971524952872,
      "grad_norm": 0.1533203125,
      "kl": 0.00010921969078481197,
      "learning_rate": 1e-05,
      "loss": 0.0,
      "reward": 1.4375,
      "reward_std": 0.125,
      "rewards/correctness_reward_func": 1.4375,
      "step": 3
    },
    {
      "completion_length": 606.40625,
      "epoch": 0.000793729536660383,
      "grad_norm": 0.193359375,
      "kl": 0.0011470153476693667,
      "learning_rate": 1e-05,
      "loss": 0.0,
      "reward": 0.625,
      "reward_std": 0.25,
      "rewards/correctness_reward_func": 0.625,
      "step": 4
    },
    {
      "completion_length": 382.59375,
      "epoch": 0.0009921619208254787,
      "grad_norm": 0.18359375,
      "kl": 0.0041184365400113165,
      "learning_rate": 1e-05,
      "loss": 0.0,
      "reward": 1.3125,
      "reward_std": 0.26933756470680237,
      "rewards/correctness_reward_func": 1.3125,
      "step": 5
    },
    {
      "completion_length": 528.28125,
      "epoch": 0.0011905943049905744,
      "grad_norm": 0.002655029296875,
      "kl": 0.0031762155922478996,
      "learning_rate": 1e-05,
      "loss": 0.0,
      "reward": 1.5,
      "reward_std": 0.0,
      "rewards/correctness_reward_func": 1.5,
      "step": 6
    },
    {
      "completion_length": 486.625,
      "epoch": 0.0013890266891556703,
      "grad_norm": 0.22265625,
      "kl": 0.006348274531774223,
      "learning_rate": 1e-05,
      "loss": 0.0,
      "reward": 1.625,
      "reward_std": 0.14433756470680237,
      "rewards/correctness_reward_func": 1.625,
      "step": 7
    },
    {
      "completion_length": 295.09375,
      "epoch": 0.001587459073320766,
      "grad_norm": 0.1318359375,
      "kl": 0.00916035019326955,
      "learning_rate": 1e-05,
      "loss": 0.0,
      "reward": 1.6875,
      "reward_std": 0.125,
      "rewards/correctness_reward_func": 1.6875,
      "step": 8
    },
    {
      "completion_length": 305.9375,
      "epoch": 0.0017858914574858616,
      "grad_norm": 0.003814697265625,
      "kl": 0.01111468207091093,
      "learning_rate": 1e-05,
      "loss": 0.0001,
      "reward": 2.0,
      "reward_std": 0.0,
      "rewards/correctness_reward_func": 2.0,
      "step": 9
    },
    {
      "completion_length": 262.59375,
      "epoch": 0.0019843238416509573,
      "grad_norm": 0.006805419921875,
      "kl": 0.01166562782600522,
      "learning_rate": 1e-05,
      "loss": 0.0001,
      "reward": 2.0,
      "reward_std": 0.0,
      "rewards/correctness_reward_func": 2.0,
      "step": 10
    },
    {
      "completion_length": 427.28125,
      "epoch": 0.002182756225816053,
      "grad_norm": 0.134765625,
      "kl": 0.0021403132705017924,
      "learning_rate": 1e-05,
      "loss": 0.0,
      "reward": 1.4375,
      "reward_std": 0.125,
      "rewards/correctness_reward_func": 1.4375,
      "step": 11
    },
    {
      "completion_length": 454.96875,
      "epoch": 0.0023811886099811487,
      "grad_norm": 0.15625,
      "kl": 0.009784933528862894,
      "learning_rate": 1e-05,
      "loss": 0.0,
      "reward": 1.1875,
      "reward_std": 0.125,
      "rewards/correctness_reward_func": 1.1875,
      "step": 12
    },
    {
      "completion_length": 520.0625,
      "epoch": 0.002579620994146245,
      "grad_norm": 0.208984375,
      "kl": 0.0027196165174245834,
      "learning_rate": 1e-05,
      "loss": 0.0,
      "reward": 0.8125,
      "reward_std": 0.375,
      "rewards/correctness_reward_func": 0.8125,
      "step": 13
    },
    {
      "completion_length": 270.5625,
      "epoch": 0.0027780533783113405,
      "grad_norm": 0.1396484375,
      "kl": 0.00326572876656428,
      "learning_rate": 1e-05,
      "loss": 0.0,
      "reward": 1.1875,
      "reward_std": 0.125,
      "rewards/correctness_reward_func": 1.1875,
      "step": 14
    },
    {
      "completion_length": 302.71875,
      "epoch": 0.0029764857624764362,
      "grad_norm": 0.09130859375,
      "kl": 0.0021118283621035516,
      "learning_rate": 1e-05,
      "loss": 0.0,
      "reward": 1.9375,
      "reward_std": 0.125,
      "rewards/correctness_reward_func": 1.9375,
      "step": 15
    },
    {
      "completion_length": 289.03125,
      "epoch": 0.003174918146641532,
      "grad_norm": 0.123046875,
      "kl": 0.006330179603537545,
      "learning_rate": 1e-05,
      "loss": 0.0,
      "reward": 1.9375,
      "reward_std": 0.125,
      "rewards/correctness_reward_func": 1.9375,
      "step": 16
    },
    {
      "completion_length": 377.28125,
      "epoch": 0.0033733505308066276,
      "grad_norm": 0.0027923583984375,
      "kl": 0.008314917489769869,
      "learning_rate": 1e-05,
      "loss": 0.0,
      "reward": 1.5,
      "reward_std": 0.0,
      "rewards/correctness_reward_func": 1.5,
      "step": 17
    },
    {
      "completion_length": 366.1875,
      "epoch": 0.0035717829149717233,
      "grad_norm": 0.0023956298828125,
      "kl": 0.006974527728743851,
      "learning_rate": 1e-05,
      "loss": 0.0,
      "reward": 1.25,
      "reward_std": 0.0,
      "rewards/correctness_reward_func": 1.25,
      "step": 18
    },
    {
      "completion_length": 455.53125,
      "epoch": 0.003770215299136819,
      "grad_norm": 0.1455078125,
      "kl": 0.0025141297810478136,
      "learning_rate": 1e-05,
      "loss": 0.0,
      "reward": 1.25,
      "reward_std": 0.39433756470680237,
      "rewards/correctness_reward_func": 1.25,
      "step": 19
    },
    {
      "completion_length": 512.03125,
      "epoch": 0.003968647683301915,
      "grad_norm": 0.1826171875,
      "kl": 0.0014448043148149736,
      "learning_rate": 1e-05,
      "loss": 0.0,
      "reward": 1.1875,
      "reward_std": 0.26933756470680237,
      "rewards/correctness_reward_func": 1.1875,
      "step": 20
    },
    {
      "completion_length": 539.78125,
      "epoch": 0.00416708006746701,
      "grad_norm": 0.1328125,
      "kl": 0.0007829267560737208,
      "learning_rate": 1e-05,
      "loss": 0.0,
      "reward": 1.375,
      "reward_std": 0.25,
      "rewards/correctness_reward_func": 1.375,
      "step": 21
    },
    {
      "completion_length": 524.8125,
      "epoch": 0.004365512451632106,
      "grad_norm": 0.1962890625,
      "kl": 0.0011430769227445126,
      "learning_rate": 1e-05,
      "loss": 0.0,
      "reward": 1.125,
      "reward_std": 0.25,
      "rewards/correctness_reward_func": 1.125,
      "step": 22
    },
    {
      "completion_length": 354.46875,
      "epoch": 0.004563944835797202,
      "grad_norm": 0.12890625,
      "kl": 0.0008475587819702923,
      "learning_rate": 1e-05,
      "loss": 0.0,
      "reward": 1.8125,
      "reward_std": 0.125,
      "rewards/correctness_reward_func": 1.8125,
      "step": 23
    },
    {
      "completion_length": 358.15625,
      "epoch": 0.0047623772199622974,
      "grad_norm": 0.00142669677734375,
      "kl": 0.0014332281207316555,
      "learning_rate": 1e-05,
      "loss": 0.0,
      "reward": 2.0,
      "reward_std": 0.0,
      "rewards/correctness_reward_func": 2.0,
      "step": 24
    },
    {
      "completion_length": 458.84375,
      "epoch": 0.004960809604127394,
      "grad_norm": 0.1318359375,
      "kl": 0.0006973636773182079,
      "learning_rate": 1e-05,
      "loss": 0.0,
      "reward": 1.5625,
      "reward_std": 0.26933756470680237,
      "rewards/correctness_reward_func": 1.5625,
      "step": 25
    },
    {
      "completion_length": 391.46875,
      "epoch": 0.00515924198829249,
      "grad_norm": 0.189453125,
      "kl": 0.0014636927953688428,
      "learning_rate": 1e-05,
      "loss": 0.0,
      "reward": 1.625,
      "reward_std": 0.25,
      "rewards/correctness_reward_func": 1.625,
      "step": 26
    },
    {
      "completion_length": 258.3125,
      "epoch": 0.005357674372457585,
      "grad_norm": 0.1484375,
      "kl": 0.004023743560537696,
      "learning_rate": 1e-05,
      "loss": 0.0,
      "reward": 1.9375,
      "reward_std": 0.125,
      "rewards/correctness_reward_func": 1.9375,
      "step": 27
    },
    {
      "completion_length": 271.75,
      "epoch": 0.005556106756622681,
      "grad_norm": 0.12109375,
      "kl": 0.0016350722071365453,
      "learning_rate": 1e-05,
      "loss": 0.0,
      "reward": 1.9375,
      "reward_std": 0.125,
      "rewards/correctness_reward_func": 1.9375,
      "step": 28
    },
    {
      "completion_length": 308.96875,
      "epoch": 0.005754539140787777,
      "grad_norm": 0.001739501953125,
      "kl": 0.003819223667960614,
      "learning_rate": 1e-05,
      "loss": 0.0,
      "reward": 1.5,
      "reward_std": 0.0,
      "rewards/correctness_reward_func": 1.5,
      "step": 29
    },
    {
      "completion_length": 515.9375,
      "epoch": 0.0059529715249528724,
      "grad_norm": 0.2451171875,
      "kl": 0.0021796236469526775,
      "learning_rate": 1e-05,
      "loss": 0.0,
      "reward": 0.75,
      "reward_std": 0.39433756470680237,
      "rewards/correctness_reward_func": 0.75,
      "step": 30
    },
    {
      "completion_length": 403.65625,
      "epoch": 0.006151403909117968,
      "grad_norm": 0.140625,
      "kl": 0.0013396024442045018,
      "learning_rate": 1e-05,
      "loss": 0.0,
      "reward": 1.5,
      "reward_std": 0.25,
      "rewards/correctness_reward_func": 1.5,
      "step": 31
    },
    {
      "completion_length": 469.875,
      "epoch": 0.006349836293283064,
      "grad_norm": 0.1455078125,
      "kl": 0.001866564794909209,
      "learning_rate": 1e-05,
      "loss": 0.0,
      "reward": 1.5,
      "reward_std": 0.25,
      "rewards/correctness_reward_func": 1.5,
      "step": 32
    },
    {
      "completion_length": 472.1875,
      "epoch": 0.0065482686774481595,
      "grad_norm": 0.1103515625,
      "kl": 0.0019174512126483023,
      "learning_rate": 1e-05,
      "loss": 0.0,
      "reward": 1.0625,
      "reward_std": 0.125,
      "rewards/correctness_reward_func": 1.0625,
      "step": 33
    },
    {
      "completion_length": 278.5625,
      "epoch": 0.006746701061613255,
      "grad_norm": 0.0005950927734375,
      "kl": 0.0010064128291560337,
      "learning_rate": 1e-05,
      "loss": 0.0,
      "reward": 1.75,
      "reward_std": 0.0,
      "rewards/correctness_reward_func": 1.75,
      "step": 34
    },
    {
      "completion_length": 391.03125,
      "epoch": 0.006945133445778351,
      "grad_norm": 0.09375,
      "kl": 0.0012205626408103853,
      "learning_rate": 1e-05,
      "loss": 0.0,
      "reward": 1.4375,
      "reward_std": 0.125,
      "rewards/correctness_reward_func": 1.4375,
      "step": 35
    },
    {
      "completion_length": 433.625,
      "epoch": 0.007143565829943447,
      "grad_norm": 0.189453125,
      "kl": 0.0007209242321550846,
      "learning_rate": 1e-05,
      "loss": 0.0,
      "reward": 1.8125,
      "reward_std": 0.375,
      "rewards/correctness_reward_func": 1.8125,
      "step": 36
    },
    {
      "completion_length": 362.71875,
      "epoch": 0.007341998214108542,
      "grad_norm": 0.11474609375,
      "kl": 0.0012260141083970666,
      "learning_rate": 1e-05,
      "loss": 0.0,
      "reward": 1.875,
      "reward_std": 0.14433756470680237,
      "rewards/correctness_reward_func": 1.875,
      "step": 37
    },
    {
      "completion_length": 339.875,
      "epoch": 0.007540430598273638,
      "grad_norm": 0.0027618408203125,
      "kl": 0.009935397887602448,
      "learning_rate": 1e-05,
      "loss": 0.0,
      "reward": 1.75,
      "reward_std": 0.0,
      "rewards/correctness_reward_func": 1.75,
      "step": 38
    },
    {
      "completion_length": 379.5,
      "epoch": 0.007738862982438734,
      "grad_norm": 0.185546875,
      "kl": 0.0012411218194756657,
      "learning_rate": 1e-05,
      "loss": 0.0,
      "reward": 0.9375,
      "reward_std": 0.26933756470680237,
      "rewards/correctness_reward_func": 0.9375,
      "step": 39
    },
    {
      "completion_length": 555.34375,
      "epoch": 0.00793729536660383,
      "grad_norm": 0.1201171875,
      "kl": 0.007853956165490672,
      "learning_rate": 1e-05,
      "loss": 0.0,
      "reward": 1.0625,
      "reward_std": 0.125,
      "rewards/correctness_reward_func": 1.0625,
      "step": 40
    },
    {
      "completion_length": 624.5,
      "epoch": 0.008135727750768925,
      "grad_norm": 0.279296875,
      "kl": 0.0027262063522357494,
      "learning_rate": 1e-05,
      "loss": 0.0,
      "reward": 0.8125,
      "reward_std": 0.5193375647068024,
      "rewards/correctness_reward_func": 0.8125,
      "step": 41
    },
    {
      "completion_length": 525.125,
      "epoch": 0.00833416013493402,
      "grad_norm": 0.166015625,
      "kl": 0.0035142535489285365,
      "learning_rate": 1e-05,
      "loss": 0.0,
      "reward": 1.375,
      "reward_std": 0.39433756470680237,
      "rewards/correctness_reward_func": 1.375,
      "step": 42
    },
    {
      "completion_length": 456.65625,
      "epoch": 0.008532592519099116,
      "grad_norm": 0.000522613525390625,
      "kl": 0.0011033852133550681,
      "learning_rate": 1e-05,
      "loss": 0.0,
      "reward": 0.75,
      "reward_std": 0.0,
      "rewards/correctness_reward_func": 0.75,
      "step": 43
    },
    {
      "completion_length": 252.8125,
      "epoch": 0.008731024903264212,
      "grad_norm": 0.126953125,
      "kl": 0.0013557878410210833,
      "learning_rate": 1e-05,
      "loss": 0.0,
      "reward": 1.875,
      "reward_std": 0.14433756470680237,
      "rewards/correctness_reward_func": 1.875,
      "step": 44
    },
    {
      "completion_length": 283.5625,
      "epoch": 0.008929457287429308,
      "grad_norm": 0.00055694580078125,
      "kl": 0.0010409851965960115,
      "learning_rate": 1e-05,
      "loss": 0.0,
      "reward": 1.0,
      "reward_std": 0.0,
      "rewards/correctness_reward_func": 1.0,
      "step": 45
    },
    {
      "completion_length": 452.6875,
      "epoch": 0.009127889671594403,
      "grad_norm": 0.0810546875,
      "kl": 0.0016598845832049847,
      "learning_rate": 1e-05,
      "loss": 0.0,
      "reward": 1.8125,
      "reward_std": 0.125,
      "rewards/correctness_reward_func": 1.8125,
      "step": 46
    },
    {
      "completion_length": 504.59375,
      "epoch": 0.0093263220557595,
      "grad_norm": 0.1064453125,
      "kl": 0.001195055043353932,
      "learning_rate": 1e-05,
      "loss": 0.0,
      "reward": 1.6875,
      "reward_std": 0.125,
      "rewards/correctness_reward_func": 1.6875,
      "step": 47
    },
    {
      "completion_length": 350.375,
      "epoch": 0.009524754439924595,
      "grad_norm": 0.06591796875,
      "kl": 0.0007179172534961253,
      "learning_rate": 1e-05,
      "loss": 0.0,
      "reward": 1.9375,
      "reward_std": 0.125,
      "rewards/correctness_reward_func": 1.9375,
      "step": 48
    },
    {
      "completion_length": 356.75,
      "epoch": 0.009723186824089692,
      "grad_norm": 0.06640625,
      "kl": 0.004019862040877342,
      "learning_rate": 1e-05,
      "loss": 0.0,
      "reward": 1.9375,
      "reward_std": 0.125,
      "rewards/correctness_reward_func": 1.9375,
      "step": 49
    },
    {
      "completion_length": 343.9375,
      "epoch": 0.009921619208254788,
      "grad_norm": 0.00055694580078125,
      "kl": 0.0014488446759060025,
      "learning_rate": 1e-05,
      "loss": 0.0,
      "reward": 2.0,
      "reward_std": 0.0,
      "rewards/correctness_reward_func": 2.0,
      "step": 50
    },
    {
      "completion_length": 456.4375,
      "epoch": 0.010120051592419884,
      "grad_norm": 0.169921875,
      "kl": 0.001344717078609392,
      "learning_rate": 1e-05,
      "loss": 0.0,
      "reward": 1.5625,
      "reward_std": 0.375,
      "rewards/correctness_reward_func": 1.5625,
      "step": 51
    },
    {
      "completion_length": 489.3125,
      "epoch": 0.01031848397658498,
      "grad_norm": 0.1845703125,
      "kl": 0.0024816631339490414,
      "learning_rate": 1e-05,
      "loss": 0.0,
      "reward": 1.1875,
      "reward_std": 0.375,
      "rewards/correctness_reward_func": 1.1875,
      "step": 52
    },
    {
      "completion_length": 489.5625,
      "epoch": 0.010516916360750075,
      "grad_norm": 0.12451171875,
      "kl": 0.016249713487923145,
      "learning_rate": 1e-05,
      "loss": 0.0001,
      "reward": 0.5625,
      "reward_std": 0.125,
      "rewards/correctness_reward_func": 0.5625,
      "step": 53
    },
    {
      "completion_length": 556.8125,
      "epoch": 0.01071534874491517,
      "grad_norm": 0.2490234375,
      "kl": 0.0019329865172039717,
      "learning_rate": 1e-05,
      "loss": 0.0,
      "reward": 1.375,
      "reward_std": 0.6443375647068024,
      "rewards/correctness_reward_func": 1.375,
      "step": 54
    },
    {
      "completion_length": 514.0,
      "epoch": 0.010913781129080266,
      "grad_norm": 0.6796875,
      "kl": 0.005961886083241552,
      "learning_rate": 1e-05,
      "loss": 0.0,
      "reward": 0.6875,
      "reward_std": 0.41367512941360474,
      "rewards/correctness_reward_func": 0.6875,
      "step": 55
    },
    {
      "completion_length": 432.84375,
      "epoch": 0.011112213513245362,
      "grad_norm": 0.19140625,
      "kl": 0.0009212676668539643,
      "learning_rate": 1e-05,
      "loss": 0.0,
      "reward": 1.1875,
      "reward_std": 0.41367512941360474,
      "rewards/correctness_reward_func": 1.1875,
      "step": 56
    },
    {
      "completion_length": 434.0625,
      "epoch": 0.011310645897410458,
      "grad_norm": 0.318359375,
      "kl": 0.0013161345414118841,
      "learning_rate": 1e-05,
      "loss": 0.0,
      "reward": 1.0625,
      "reward_std": 0.6636751294136047,
      "rewards/correctness_reward_func": 1.0625,
      "step": 57
    },
    {
      "completion_length": 503.9375,
      "epoch": 0.011509078281575554,
      "grad_norm": 0.10791015625,
      "kl": 0.0013501367502612993,
      "learning_rate": 1e-05,
      "loss": 0.0,
      "reward": 0.6875,
      "reward_std": 0.125,
      "rewards/correctness_reward_func": 0.6875,
      "step": 58
    },
    {
      "completion_length": 577.25,
      "epoch": 0.01170751066574065,
      "grad_norm": 0.06298828125,
      "kl": 0.0004623739223461598,
      "learning_rate": 1e-05,
      "loss": 0.0,
      "reward": 0.1875,
      "reward_std": 0.125,
      "rewards/correctness_reward_func": 0.1875,
      "step": 59
    },
    {
      "completion_length": 639.375,
      "epoch": 0.011905943049905745,
      "grad_norm": 0.0908203125,
      "kl": 0.0009281258899136446,
      "learning_rate": 1e-05,
      "loss": 0.0,
      "reward": 0.6875,
      "reward_std": 0.125,
      "rewards/correctness_reward_func": 0.6875,
      "step": 60
    },
    {
      "completion_length": 631.3125,
      "epoch": 0.01210437543407084,
      "grad_norm": 0.000553131103515625,
      "kl": 0.0021498738351510838,
      "learning_rate": 1e-05,
      "loss": 0.0,
      "reward": 0.75,
      "reward_std": 0.0,
      "rewards/correctness_reward_func": 0.75,
      "step": 61
    },
    {
      "completion_length": 328.8125,
      "epoch": 0.012302807818235936,
      "grad_norm": 0.000690460205078125,
      "kl": 0.0010117258789250627,
      "learning_rate": 1e-05,
      "loss": 0.0,
      "reward": 0.75,
      "reward_std": 0.0,
      "rewards/correctness_reward_func": 0.75,
      "step": 62
    },
    {
      "completion_length": 273.8125,
      "epoch": 0.012501240202401032,
      "grad_norm": 0.103515625,
      "kl": 0.000650071247946471,
      "learning_rate": 1e-05,
      "loss": 0.0,
      "reward": 1.4375,
      "reward_std": 0.125,
      "rewards/correctness_reward_func": 1.4375,
      "step": 63
    },
    {
      "completion_length": 450.03125,
      "epoch": 0.012699672586566128,
      "grad_norm": 0.1552734375,
      "kl": 0.0009097288202610798,
      "learning_rate": 1e-05,
      "loss": 0.0,
      "reward": 1.8125,
      "reward_std": 0.26933756470680237,
      "rewards/correctness_reward_func": 1.8125,
      "step": 64
    },
    {
      "completion_length": 415.96875,
      "epoch": 0.012898104970731223,
      "grad_norm": 0.0830078125,
      "kl": 0.0014095778460614383,
      "learning_rate": 1e-05,
      "loss": 0.0,
      "reward": 1.875,
      "reward_std": 0.14433756470680237,
      "rewards/correctness_reward_func": 1.875,
      "step": 65
    },
    {
      "completion_length": 421.8125,
      "epoch": 0.013096537354896319,
      "grad_norm": 0.09130859375,
      "kl": 0.0017693252448225394,
      "learning_rate": 1e-05,
      "loss": 0.0,
      "reward": 1.9375,
      "reward_std": 0.125,
      "rewards/correctness_reward_func": 1.9375,
      "step": 66
    },
    {
      "completion_length": 322.65625,
      "epoch": 0.013294969739061415,
      "grad_norm": 0.1484375,
      "kl": 0.007693824853049591,
      "learning_rate": 1e-05,
      "loss": 0.0,
      "reward": 1.875,
      "reward_std": 0.14433756470680237,
      "rewards/correctness_reward_func": 1.875,
      "step": 67
    },
    {
      "completion_length": 273.0625,
      "epoch": 0.01349340212322651,
      "grad_norm": 0.1787109375,
      "kl": 0.0014752715069334954,
      "learning_rate": 1e-05,
      "loss": 0.0,
      "reward": 1.875,
      "reward_std": 0.14433756470680237,
      "rewards/correctness_reward_func": 1.875,
      "step": 68
    },
    {
      "completion_length": 252.09375,
      "epoch": 0.013691834507391606,
      "grad_norm": 0.11083984375,
      "kl": 0.0045530187780968845,
      "learning_rate": 1e-05,
      "loss": 0.0,
      "reward": 1.6875,
      "reward_std": 0.125,
      "rewards/correctness_reward_func": 1.6875,
      "step": 69
    },
    {
      "completion_length": 430.96875,
      "epoch": 0.013890266891556702,
      "grad_norm": 0.1953125,
      "kl": 0.0021810558391734958,
      "learning_rate": 1e-05,
      "loss": 0.0,
      "reward": 1.75,
      "reward_std": 0.39433756470680237,
      "rewards/correctness_reward_func": 1.75,
      "step": 70
    },
    {
      "completion_length": 539.40625,
      "epoch": 0.014088699275721797,
      "grad_norm": 0.10498046875,
      "kl": 0.003831994123174809,
      "learning_rate": 1e-05,
      "loss": 0.0,
      "reward": 0.6875,
      "reward_std": 0.125,
      "rewards/correctness_reward_func": 0.6875,
      "step": 71
    },
    {
      "completion_length": 557.53125,
      "epoch": 0.014287131659886893,
      "grad_norm": 0.002471923828125,
      "kl": 0.006553357859957032,
      "learning_rate": 1e-05,
      "loss": 0.0,
      "reward": 1.0,
      "reward_std": 0.0,
      "rewards/correctness_reward_func": 1.0,
      "step": 72
    },
    {
      "completion_length": 587.78125,
      "epoch": 0.014485564044051989,
      "grad_norm": 0.27734375,
      "kl": 0.0071588484570384026,
      "learning_rate": 1e-05,
      "loss": 0.0,
      "reward": 1.0,
      "reward_std": 0.5386751294136047,
      "rewards/correctness_reward_func": 1.0,
      "step": 73
    },
    {
      "completion_length": 496.125,
      "epoch": 0.014683996428217085,
      "grad_norm": 0.28125,
      "kl": 0.005753638513851911,
      "learning_rate": 1e-05,
      "loss": 0.0,
      "reward": 1.0625,
      "reward_std": 0.375,
      "rewards/correctness_reward_func": 1.0625,
      "step": 74
    },
    {
      "completion_length": 400.90625,
      "epoch": 0.01488242881238218,
      "grad_norm": 0.234375,
      "kl": 0.002603573986561969,
      "learning_rate": 1e-05,
      "loss": 0.0,
      "reward": 1.5,
      "reward_std": 0.39433756470680237,
      "rewards/correctness_reward_func": 1.5,
      "step": 75
    },
    {
      "completion_length": 499.75,
      "epoch": 0.015080861196547276,
      "grad_norm": 0.162109375,
      "kl": 0.003349974052980542,
      "learning_rate": 1e-05,
      "loss": 0.0,
      "reward": 1.3125,
      "reward_std": 0.375,
      "rewards/correctness_reward_func": 1.3125,
      "step": 76
    },
    {
      "completion_length": 421.53125,
      "epoch": 0.015279293580712372,
      "grad_norm": 0.359375,
      "kl": 0.003231665992643684,
      "learning_rate": 1e-05,
      "loss": 0.0,
      "reward": 1.375,
      "reward_std": 0.5386751294136047,
      "rewards/correctness_reward_func": 1.375,
      "step": 77
    },
    {
      "completion_length": 324.59375,
      "epoch": 0.015477725964877467,
      "grad_norm": 0.345703125,
      "kl": 0.0044938469072803855,
      "learning_rate": 1e-05,
      "loss": 0.0,
      "reward": 0.75,
      "reward_std": 0.25,
      "rewards/correctness_reward_func": 0.75,
      "step": 78
    },
    {
      "completion_length": 584.875,
      "epoch": 0.015676158349042565,
      "grad_norm": 0.0007781982421875,
      "kl": 0.0039344872056972235,
      "learning_rate": 1e-05,
      "loss": 0.0,
      "reward": 0.25,
      "reward_std": 0.0,
      "rewards/correctness_reward_func": 0.25,
      "step": 79
    },
    {
      "completion_length": 568.84375,
      "epoch": 0.01587459073320766,
      "grad_norm": 0.000675201416015625,
      "kl": 0.0011096175148850307,
      "learning_rate": 1e-05,
      "loss": 0.0,
      "reward": 1.0,
      "reward_std": 0.0,
      "rewards/correctness_reward_func": 1.0,
      "step": 80
    },
    {
      "completion_length": 402.15625,
      "epoch": 0.016073023117372756,
      "grad_norm": 0.0005645751953125,
      "kl": 0.002124628212186508,
      "learning_rate": 1e-05,
      "loss": 0.0,
      "reward": 1.75,
      "reward_std": 0.0,
      "rewards/correctness_reward_func": 1.75,
      "step": 81
    },
    {
      "completion_length": 303.84375,
      "epoch": 0.01627145550153785,
      "grad_norm": 0.000911712646484375,
      "kl": 0.001547299834783189,
      "learning_rate": 1e-05,
      "loss": 0.0,
      "reward": 1.5,
      "reward_std": 0.0,
      "rewards/correctness_reward_func": 1.5,
      "step": 82
    },
    {
      "completion_length": 442.40625,
      "epoch": 0.016469887885702948,
      "grad_norm": 0.22265625,
      "kl": 0.0019549240387277678,
      "learning_rate": 1e-05,
      "loss": 0.0,
      "reward": 1.6875,
      "reward_std": 0.41367512941360474,
      "rewards/correctness_reward_func": 1.6875,
      "step": 83
    },
    {
      "completion_length": 363.5625,
      "epoch": 0.01666832026986804,
      "grad_norm": 0.1005859375,
      "kl": 0.0021169226529309526,
      "learning_rate": 1e-05,
      "loss": 0.0,
      "reward": 1.4375,
      "reward_std": 0.125,
      "rewards/correctness_reward_func": 1.4375,
      "step": 84
    },
    {
      "completion_length": 333.5,
      "epoch": 0.01686675265403314,
      "grad_norm": 0.00101470947265625,
      "kl": 0.0020763709326274693,
      "learning_rate": 1e-05,
      "loss": 0.0,
      "reward": 2.0,
      "reward_std": 0.0,
      "rewards/correctness_reward_func": 2.0,
      "step": 85
    },
    {
      "completion_length": 260.6875,
      "epoch": 0.017065185038198233,
      "grad_norm": 0.2578125,
      "kl": 0.0023609662894159555,
      "learning_rate": 1e-05,
      "loss": 0.0,
      "reward": 1.9375,
      "reward_std": 0.125,
      "rewards/correctness_reward_func": 1.9375,
      "step": 86
    },
    {
      "completion_length": 317.78125,
      "epoch": 0.01726361742236333,
      "grad_norm": 0.1416015625,
      "kl": 0.0023049223236739635,
      "learning_rate": 1e-05,
      "loss": 0.0,
      "reward": 1.8125,
      "reward_std": 0.125,
      "rewards/correctness_reward_func": 1.8125,
      "step": 87
    },
    {
      "completion_length": 374.5625,
      "epoch": 0.017462049806528424,
      "grad_norm": 0.002838134765625,
      "kl": 0.003084336465690285,
      "learning_rate": 1e-05,
      "loss": 0.0,
      "reward": 2.0,
      "reward_std": 0.0,
      "rewards/correctness_reward_func": 2.0,
      "step": 88
    },
    {
      "completion_length": 400.75,
      "epoch": 0.01766048219069352,
      "grad_norm": 0.265625,
      "kl": 0.004105731437448412,
      "learning_rate": 1e-05,
      "loss": 0.0,
      "reward": 1.25,
      "reward_std": 0.25,
      "rewards/correctness_reward_func": 1.25,
      "step": 89
    },
    {
      "completion_length": 481.28125,
      "epoch": 0.017858914574858616,
      "grad_norm": 0.00104522705078125,
      "kl": 0.004729912034235895,
      "learning_rate": 1e-05,
      "loss": 0.0,
      "reward": 0.5,
      "reward_std": 0.0,
      "rewards/correctness_reward_func": 0.5,
      "step": 90
    },
    {
      "completion_length": 660.34375,
      "epoch": 0.018057346959023713,
      "grad_norm": 0.2421875,
      "kl": 0.005954354302957654,
      "learning_rate": 1e-05,
      "loss": 0.0,
      "reward": 1.0,
      "reward_std": 0.6830126941204071,
      "rewards/correctness_reward_func": 1.0,
      "step": 91
    },
    {
      "completion_length": 547.09375,
      "epoch": 0.018255779343188807,
      "grad_norm": 0.248046875,
      "kl": 0.004669041052693501,
      "learning_rate": 1e-05,
      "loss": 0.0,
      "reward": 0.625,
      "reward_std": 0.6443375647068024,
      "rewards/correctness_reward_func": 0.625,
      "step": 92
    },
    {
      "completion_length": 467.71875,
      "epoch": 0.018454211727353904,
      "grad_norm": 0.189453125,
      "kl": 0.0035645719908643514,
      "learning_rate": 1e-05,
      "loss": 0.0,
      "reward": 1.3125,
      "reward_std": 0.375,
      "rewards/correctness_reward_func": 1.3125,
      "step": 93
    },
    {
      "completion_length": 442.84375,
      "epoch": 0.018652644111519,
      "grad_norm": 0.146484375,
      "kl": 0.0033500409917905927,
      "learning_rate": 1e-05,
      "loss": 0.0,
      "reward": 1.3125,
      "reward_std": 0.375,
      "rewards/correctness_reward_func": 1.3125,
      "step": 94
    },
    {
      "completion_length": 457.875,
      "epoch": 0.018851076495684096,
      "grad_norm": 0.06787109375,
      "kl": 0.0038696340925525874,
      "learning_rate": 1e-05,
      "loss": 0.0,
      "reward": 1.8125,
      "reward_std": 0.125,
      "rewards/correctness_reward_func": 1.8125,
      "step": 95
    },
    {
      "completion_length": 522.15625,
      "epoch": 0.01904950887984919,
      "grad_norm": 0.1328125,
      "kl": 0.005176389531698078,
      "learning_rate": 1e-05,
      "loss": 0.0,
      "reward": 0.875,
      "reward_std": 0.25,
      "rewards/correctness_reward_func": 0.875,
      "step": 96
    },
    {
      "completion_length": 682.34375,
      "epoch": 0.019247941264014287,
      "grad_norm": 0.000698089599609375,
      "kl": 0.003805596032179892,
      "learning_rate": 1e-05,
      "loss": 0.0,
      "reward": 0.0,
      "reward_std": 0.0,
      "rewards/correctness_reward_func": 0.0,
      "step": 97
    },
    {
      "completion_length": 561.03125,
      "epoch": 0.019446373648179385,
      "grad_norm": 0.078125,
      "kl": 0.003582520061172545,
      "learning_rate": 1e-05,
      "loss": 0.0,
      "reward": 0.6875,
      "reward_std": 0.125,
      "rewards/correctness_reward_func": 0.6875,
      "step": 98
    },
    {
      "completion_length": 517.96875,
      "epoch": 0.01964480603234448,
      "grad_norm": 0.16796875,
      "kl": 0.005401681060902774,
      "learning_rate": 1e-05,
      "loss": 0.0,
      "reward": 0.0625,
      "reward_std": 0.125,
      "rewards/correctness_reward_func": 0.0625,
      "step": 99
    },
    {
      "completion_length": 377.4375,
      "epoch": 0.019843238416509576,
      "grad_norm": 0.12255859375,
      "kl": 0.0034658076183404773,
      "learning_rate": 1e-05,
      "loss": 0.0,
      "reward": 1.1875,
      "reward_std": 0.125,
      "rewards/correctness_reward_func": 1.1875,
      "step": 100
    }
  ],
  "logging_steps": 1,
  "max_steps": 1007800,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 200,
  "save_steps": 10,
  "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": 2,
  "trial_name": null,
  "trial_params": null
}