{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.07602481449945263,
  "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": 0.375,
      "all_wrong": 0.0,
      "completion_length": 385.515625,
      "epoch": 3.040992579978105e-05,
      "grad_norm": 1.46462129102653,
      "kl": 0.0,
      "learning_rate": 9.999999977182372e-07,
      "loss": -0.0,
      "reward": 1.6200919151306152,
      "reward_std": 0.3473181128501892,
      "rewards/accuracy_reward": 0.5732167959213257,
      "rewards/format_reward": 0.984375,
      "step": 1,
      "temperature": 1.0
    },
    {
      "all_correct": 0.375,
      "all_wrong": 0.125,
      "completion_length": 349.140625,
      "epoch": 6.08198515995621e-05,
      "grad_norm": 1.5765784532645386,
      "kl": 0.0006866455078125,
      "learning_rate": 9.999999908729493e-07,
      "loss": 0.0,
      "reward": 1.6871967315673828,
      "reward_std": 0.15995854139328003,
      "rewards/accuracy_reward": 0.6090717315673828,
      "rewards/format_reward": 1.0,
      "step": 2,
      "temperature": 1.0
    },
    {
      "all_correct": 0.375,
      "all_wrong": 0.0,
      "completion_length": 382.171875,
      "epoch": 9.122977739934314e-05,
      "grad_norm": 1.4479568746080858,
      "kl": 0.000553131103515625,
      "learning_rate": 9.99999979464136e-07,
      "loss": 0.0,
      "reward": 1.800853967666626,
      "reward_std": 0.3275423049926758,
      "rewards/accuracy_reward": 0.7696040868759155,
      "rewards/format_reward": 0.953125,
      "step": 3,
      "temperature": 1.0
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.0,
      "completion_length": 301.59375,
      "epoch": 0.0001216397031991242,
      "grad_norm": 1.8873157921194488,
      "kl": 0.000637054443359375,
      "learning_rate": 9.999999634917972e-07,
      "loss": 0.0,
      "reward": 1.7625000476837158,
      "reward_std": 0.2836723327636719,
      "rewards/accuracy_reward": 0.71875,
      "rewards/format_reward": 1.0,
      "step": 4,
      "temperature": 1.0
    },
    {
      "all_correct": 0.375,
      "all_wrong": 0.125,
      "completion_length": 340.03125,
      "epoch": 0.00015204962899890526,
      "grad_norm": 1.8722689099433998,
      "kl": 0.000545501708984375,
      "learning_rate": 9.999999429559338e-07,
      "loss": 0.0,
      "reward": 1.6502331495285034,
      "reward_std": 0.2827591896057129,
      "rewards/accuracy_reward": 0.6189831495285034,
      "rewards/format_reward": 0.984375,
      "step": 5,
      "temperature": 1.0
    },
    {
      "all_correct": 0.25,
      "all_wrong": 0.0,
      "completion_length": 335.21875,
      "epoch": 0.0001824595547986863,
      "grad_norm": 1.562897442755551,
      "kl": 0.000797271728515625,
      "learning_rate": 9.999999178565453e-07,
      "loss": 0.0,
      "reward": 1.743882179260254,
      "reward_std": 0.3677159547805786,
      "rewards/accuracy_reward": 0.6720072031021118,
      "rewards/format_reward": 1.0,
      "step": 6,
      "temperature": 1.0
    },
    {
      "all_correct": 0.25,
      "all_wrong": 0.125,
      "completion_length": 290.828125,
      "epoch": 0.00021286948059846735,
      "grad_norm": 1.7767724234648412,
      "kl": 0.000823974609375,
      "learning_rate": 9.999998881936323e-07,
      "loss": 0.0,
      "reward": 1.5342857837677002,
      "reward_std": 0.2276882380247116,
      "rewards/accuracy_reward": 0.5092858076095581,
      "rewards/format_reward": 1.0,
      "step": 7,
      "temperature": 1.0
    },
    {
      "all_correct": 0.25,
      "all_wrong": 0.125,
      "completion_length": 431.515625,
      "epoch": 0.0002432794063982484,
      "grad_norm": 2.418736542031397,
      "kl": 0.0012359619140625,
      "learning_rate": 9.999998539671947e-07,
      "loss": 0.0,
      "reward": 1.4342398643493652,
      "reward_std": 0.3719263970851898,
      "rewards/accuracy_reward": 0.49986493587493896,
      "rewards/format_reward": 0.890625,
      "step": 8,
      "temperature": 1.0
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.0,
      "completion_length": 370.890625,
      "epoch": 0.0002736893321980294,
      "grad_norm": 1.3838072184589625,
      "kl": 0.0007476806640625,
      "learning_rate": 9.999998151772334e-07,
      "loss": 0.0,
      "reward": 1.756640076637268,
      "reward_std": 0.20073392987251282,
      "rewards/accuracy_reward": 0.6941401362419128,
      "rewards/format_reward": 0.984375,
      "step": 9,
      "temperature": 1.0
    },
    {
      "all_correct": 0.625,
      "all_wrong": 0.0,
      "completion_length": 361.09375,
      "epoch": 0.0003040992579978105,
      "grad_norm": 1.5727200865129225,
      "kl": 0.000728607177734375,
      "learning_rate": 9.99999771823748e-07,
      "loss": 0.0,
      "reward": 1.75,
      "reward_std": 0.22021089494228363,
      "rewards/accuracy_reward": 0.6875,
      "rewards/format_reward": 1.0,
      "step": 10,
      "temperature": 1.0
    },
    {
      "all_correct": 0.75,
      "all_wrong": 0.0,
      "completion_length": 325.59375,
      "epoch": 0.00033450918379759155,
      "grad_norm": 2.688424452559186,
      "kl": 0.00084686279296875,
      "learning_rate": 9.999997239067396e-07,
      "loss": 0.0,
      "reward": 1.917578101158142,
      "reward_std": 0.17126643657684326,
      "rewards/accuracy_reward": 0.861328125,
      "rewards/format_reward": 1.0,
      "step": 11,
      "temperature": 1.0
    },
    {
      "all_correct": 0.75,
      "all_wrong": 0.0,
      "completion_length": 333.3125,
      "epoch": 0.0003649191095973726,
      "grad_norm": 1.2016068474261656,
      "kl": 0.000919342041015625,
      "learning_rate": 9.999996714262083e-07,
      "loss": 0.0,
      "reward": 1.890625,
      "reward_std": 0.16929560899734497,
      "rewards/accuracy_reward": 0.828125,
      "rewards/format_reward": 1.0,
      "step": 12,
      "temperature": 1.0
    },
    {
      "all_correct": 0.375,
      "all_wrong": 0.0,
      "completion_length": 335.25,
      "epoch": 0.0003953290353971536,
      "grad_norm": 1.501756467523148,
      "kl": 0.00115203857421875,
      "learning_rate": 9.999996143821546e-07,
      "loss": 0.0,
      "reward": 1.7435684204101562,
      "reward_std": 0.2695395350456238,
      "rewards/accuracy_reward": 0.7029433846473694,
      "rewards/format_reward": 1.0,
      "step": 13,
      "temperature": 1.0
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.0,
      "completion_length": 386.421875,
      "epoch": 0.0004257389611969347,
      "grad_norm": 1.7218942478249426,
      "kl": 0.00122833251953125,
      "learning_rate": 9.999995527745788e-07,
      "loss": 0.0,
      "reward": 1.8532562255859375,
      "reward_std": 0.2433551549911499,
      "rewards/accuracy_reward": 0.7657562494277954,
      "rewards/format_reward": 1.0,
      "step": 14,
      "temperature": 1.0
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.125,
      "completion_length": 392.9375,
      "epoch": 0.00045614888699671574,
      "grad_norm": 1.4130863054579237,
      "kl": 0.00146484375,
      "learning_rate": 9.99999486603482e-07,
      "loss": 0.0001,
      "reward": 1.7096762657165527,
      "reward_std": 0.1203475296497345,
      "rewards/accuracy_reward": 0.6503013372421265,
      "rewards/format_reward": 1.0,
      "step": 15,
      "temperature": 1.0
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.125,
      "completion_length": 352.703125,
      "epoch": 0.0004865588127964968,
      "grad_norm": 2.2745796643908838,
      "kl": 0.00124359130859375,
      "learning_rate": 9.999994158688644e-07,
      "loss": 0.0,
      "reward": 1.6993539333343506,
      "reward_std": 0.15594330430030823,
      "rewards/accuracy_reward": 0.6274789571762085,
      "rewards/format_reward": 1.0,
      "step": 16,
      "temperature": 1.0
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.125,
      "completion_length": 325.890625,
      "epoch": 0.0005169687385962778,
      "grad_norm": 1.3784606032507907,
      "kl": 0.00185394287109375,
      "learning_rate": 9.999993405707267e-07,
      "loss": 0.0001,
      "reward": 1.789963722229004,
      "reward_std": 0.16524848341941833,
      "rewards/accuracy_reward": 0.7243385910987854,
      "rewards/format_reward": 1.0,
      "step": 17,
      "temperature": 1.0
    },
    {
      "all_correct": 0.25,
      "all_wrong": 0.0,
      "completion_length": 333.515625,
      "epoch": 0.0005473786643960588,
      "grad_norm": 1.8108028298378926,
      "kl": 0.001678466796875,
      "learning_rate": 9.999992607090697e-07,
      "loss": 0.0001,
      "reward": 1.6446179151535034,
      "reward_std": 0.3519408702850342,
      "rewards/accuracy_reward": 0.5883679389953613,
      "rewards/format_reward": 1.0,
      "step": 18,
      "temperature": 1.0
    },
    {
      "all_correct": 0.25,
      "all_wrong": 0.125,
      "completion_length": 347.828125,
      "epoch": 0.0005777885901958399,
      "grad_norm": 1.8002379603895076,
      "kl": 0.0018463134765625,
      "learning_rate": 9.999991762838942e-07,
      "loss": 0.0001,
      "reward": 1.800812005996704,
      "reward_std": 0.2275523990392685,
      "rewards/accuracy_reward": 0.6851869821548462,
      "rewards/format_reward": 1.0,
      "step": 19,
      "temperature": 1.0
    },
    {
      "all_correct": 0.25,
      "all_wrong": 0.0,
      "completion_length": 440.3125,
      "epoch": 0.000608198515995621,
      "grad_norm": 1.7096354165169774,
      "kl": 0.001556396484375,
      "learning_rate": 9.999990872952006e-07,
      "loss": 0.0001,
      "reward": 1.7975349426269531,
      "reward_std": 0.342560738325119,
      "rewards/accuracy_reward": 0.716284990310669,
      "rewards/format_reward": 1.0,
      "step": 20,
      "temperature": 1.0
    },
    {
      "all_correct": 0.25,
      "all_wrong": 0.125,
      "completion_length": 378.140625,
      "epoch": 0.0006386084417954021,
      "grad_norm": 2.48989439056807,
      "kl": 0.001953125,
      "learning_rate": 9.999989937429902e-07,
      "loss": 0.0001,
      "reward": 1.5938849449157715,
      "reward_std": 0.24751313030719757,
      "rewards/accuracy_reward": 0.5095100402832031,
      "rewards/format_reward": 1.0,
      "step": 21,
      "temperature": 1.0
    },
    {
      "all_correct": 0.25,
      "all_wrong": 0.125,
      "completion_length": 347.703125,
      "epoch": 0.0006690183675951831,
      "grad_norm": 1.5987316397281808,
      "kl": 0.0026397705078125,
      "learning_rate": 9.999988956272633e-07,
      "loss": 0.0001,
      "reward": 1.5236949920654297,
      "reward_std": 0.24698606133460999,
      "rewards/accuracy_reward": 0.4674449861049652,
      "rewards/format_reward": 1.0,
      "step": 22,
      "temperature": 1.0
    },
    {
      "all_correct": 0.625,
      "all_wrong": 0.0,
      "completion_length": 316.28125,
      "epoch": 0.0006994282933949641,
      "grad_norm": 1.6727439953130954,
      "kl": 0.0034027099609375,
      "learning_rate": 9.999987929480213e-07,
      "loss": 0.0001,
      "reward": 1.9693775177001953,
      "reward_std": 0.21827057003974915,
      "rewards/accuracy_reward": 0.8818774223327637,
      "rewards/format_reward": 1.0,
      "step": 23,
      "temperature": 1.0
    },
    {
      "all_correct": 0.625,
      "all_wrong": 0.0,
      "completion_length": 392.59375,
      "epoch": 0.0007298382191947452,
      "grad_norm": 1.5077457194830788,
      "kl": 0.003173828125,
      "learning_rate": 9.99998685705265e-07,
      "loss": 0.0001,
      "reward": 1.9068952798843384,
      "reward_std": 0.16635803878307343,
      "rewards/accuracy_reward": 0.8318951725959778,
      "rewards/format_reward": 0.96875,
      "step": 24,
      "temperature": 1.0
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.0,
      "completion_length": 436.640625,
      "epoch": 0.0007602481449945262,
      "grad_norm": 1.9822459834217656,
      "kl": 0.00299072265625,
      "learning_rate": 9.999985738989952e-07,
      "loss": 0.0001,
      "reward": 1.6628453731536865,
      "reward_std": 0.1725778877735138,
      "rewards/accuracy_reward": 0.6472203135490417,
      "rewards/format_reward": 0.96875,
      "step": 25,
      "temperature": 1.0
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.0,
      "completion_length": 335.65625,
      "epoch": 0.0007906580707943072,
      "grad_norm": 1.8945284918235032,
      "kl": 0.003997802734375,
      "learning_rate": 9.99998457529213e-07,
      "loss": 0.0002,
      "reward": 1.953125,
      "reward_std": 0.2697862684726715,
      "rewards/accuracy_reward": 0.859375,
      "rewards/format_reward": 1.0,
      "step": 26,
      "temperature": 1.0
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.125,
      "completion_length": 313.484375,
      "epoch": 0.0008210679965940883,
      "grad_norm": 2.2296562874480825,
      "kl": 0.00518798828125,
      "learning_rate": 9.999983365959195e-07,
      "loss": 0.0002,
      "reward": 1.853124976158142,
      "reward_std": 0.21263141930103302,
      "rewards/accuracy_reward": 0.796875,
      "rewards/format_reward": 1.0,
      "step": 27,
      "temperature": 1.0
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.375,
      "completion_length": 356.921875,
      "epoch": 0.0008514779223938694,
      "grad_norm": 1.374397718368643,
      "kl": 0.004486083984375,
      "learning_rate": 9.99998211099116e-07,
      "loss": 0.0002,
      "reward": 1.5906494855880737,
      "reward_std": 0.09352891147136688,
      "rewards/accuracy_reward": 0.5406495332717896,
      "rewards/format_reward": 0.984375,
      "step": 28,
      "temperature": 1.0
    },
    {
      "all_correct": 0.25,
      "all_wrong": 0.25,
      "completion_length": 377.09375,
      "epoch": 0.0008818878481936504,
      "grad_norm": 2.1876852440717003,
      "kl": 0.004486083984375,
      "learning_rate": 9.99998081038803e-07,
      "loss": 0.0002,
      "reward": 1.6968750953674316,
      "reward_std": 0.24924103915691376,
      "rewards/accuracy_reward": 0.609375,
      "rewards/format_reward": 1.0,
      "step": 29,
      "temperature": 1.0
    },
    {
      "all_correct": 0.25,
      "all_wrong": 0.125,
      "completion_length": 389.6875,
      "epoch": 0.0009122977739934315,
      "grad_norm": 1.3752351130491731,
      "kl": 0.00482177734375,
      "learning_rate": 9.999979464149825e-07,
      "loss": 0.0002,
      "reward": 1.596991777420044,
      "reward_std": 0.26820871233940125,
      "rewards/accuracy_reward": 0.5251166820526123,
      "rewards/format_reward": 1.0,
      "step": 30,
      "temperature": 1.0
    },
    {
      "all_correct": 0.375,
      "all_wrong": 0.0,
      "completion_length": 386.921875,
      "epoch": 0.0009427076997932125,
      "grad_norm": 1.508165110944859,
      "kl": 0.00579833984375,
      "learning_rate": 9.999978072276553e-07,
      "loss": 0.0002,
      "reward": 1.718550443649292,
      "reward_std": 0.35128822922706604,
      "rewards/accuracy_reward": 0.6154255270957947,
      "rewards/format_reward": 1.0,
      "step": 31,
      "temperature": 1.0
    },
    {
      "all_correct": 0.25,
      "all_wrong": 0.0,
      "completion_length": 377.65625,
      "epoch": 0.0009731176255929935,
      "grad_norm": 1.2888692440946512,
      "kl": 0.00555419921875,
      "learning_rate": 9.999976634768226e-07,
      "loss": 0.0002,
      "reward": 1.8919233083724976,
      "reward_std": 0.345920205116272,
      "rewards/accuracy_reward": 0.7700482606887817,
      "rewards/format_reward": 1.0,
      "step": 32,
      "temperature": 1.0
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.125,
      "completion_length": 364.703125,
      "epoch": 0.0010035275513927747,
      "grad_norm": 1.232348639633421,
      "kl": 0.005157470703125,
      "learning_rate": 9.99997515162486e-07,
      "loss": 0.0002,
      "reward": 1.8963067531585693,
      "reward_std": 0.19907650351524353,
      "rewards/accuracy_reward": 0.7713068723678589,
      "rewards/format_reward": 1.0,
      "step": 33,
      "temperature": 1.0
    },
    {
      "all_correct": 0.25,
      "all_wrong": 0.125,
      "completion_length": 438.5625,
      "epoch": 0.0010339374771925556,
      "grad_norm": 1.3578169430467355,
      "kl": 0.005340576171875,
      "learning_rate": 9.999973622846466e-07,
      "loss": 0.0002,
      "reward": 1.593675136566162,
      "reward_std": 0.2628445625305176,
      "rewards/accuracy_reward": 0.5311751365661621,
      "rewards/format_reward": 0.96875,
      "step": 34,
      "temperature": 1.0
    },
    {
      "all_correct": 0.25,
      "all_wrong": 0.0,
      "completion_length": 384.328125,
      "epoch": 0.0010643474029923368,
      "grad_norm": 1.5866826727618084,
      "kl": 0.00689697265625,
      "learning_rate": 9.99997204843306e-07,
      "loss": 0.0003,
      "reward": 1.8410686254501343,
      "reward_std": 0.33037933707237244,
      "rewards/accuracy_reward": 0.7223186492919922,
      "rewards/format_reward": 1.0,
      "step": 35,
      "temperature": 1.0
    },
    {
      "all_correct": 0.625,
      "all_wrong": 0.0,
      "completion_length": 367.734375,
      "epoch": 0.0010947573287921177,
      "grad_norm": 1.3910018979925194,
      "kl": 0.009521484375,
      "learning_rate": 9.999970428384654e-07,
      "loss": 0.0004,
      "reward": 1.7983285188674927,
      "reward_std": 0.2062988579273224,
      "rewards/accuracy_reward": 0.7202036380767822,
      "rewards/format_reward": 0.984375,
      "step": 36,
      "temperature": 1.0
    },
    {
      "all_correct": 0.25,
      "all_wrong": 0.125,
      "completion_length": 416.1875,
      "epoch": 0.0011251672545918988,
      "grad_norm": 3.4750962646915196,
      "kl": 0.00799560546875,
      "learning_rate": 9.999968762701265e-07,
      "loss": 0.0003,
      "reward": 1.5581188201904297,
      "reward_std": 0.23245224356651306,
      "rewards/accuracy_reward": 0.47686874866485596,
      "rewards/format_reward": 1.0,
      "step": 37,
      "temperature": 1.0
    },
    {
      "all_correct": 0.375,
      "all_wrong": 0.125,
      "completion_length": 408.4375,
      "epoch": 0.0011555771803916798,
      "grad_norm": 1.4937905037107568,
      "kl": 0.00823974609375,
      "learning_rate": 9.999967051382908e-07,
      "loss": 0.0003,
      "reward": 1.7101589441299438,
      "reward_std": 0.21186581254005432,
      "rewards/accuracy_reward": 0.6289088726043701,
      "rewards/format_reward": 1.0,
      "step": 38,
      "temperature": 1.0
    },
    {
      "all_correct": 0.25,
      "all_wrong": 0.125,
      "completion_length": 369.0625,
      "epoch": 0.001185987106191461,
      "grad_norm": 1.5830653150849738,
      "kl": 0.01007080078125,
      "learning_rate": 9.999965294429597e-07,
      "loss": 0.0004,
      "reward": 1.6895959377288818,
      "reward_std": 0.1790069043636322,
      "rewards/accuracy_reward": 0.5833459496498108,
      "rewards/format_reward": 1.0,
      "step": 39,
      "temperature": 1.0
    },
    {
      "all_correct": 0.375,
      "all_wrong": 0.25,
      "completion_length": 406.390625,
      "epoch": 0.001216397031991242,
      "grad_norm": 1.4961036906202025,
      "kl": 0.007720947265625,
      "learning_rate": 9.99996349184135e-07,
      "loss": 0.0003,
      "reward": 1.6968750953674316,
      "reward_std": 0.21975873410701752,
      "rewards/accuracy_reward": 0.625,
      "rewards/format_reward": 0.96875,
      "step": 40,
      "temperature": 1.0
    },
    {
      "all_correct": 0.125,
      "all_wrong": 0.375,
      "completion_length": 396.578125,
      "epoch": 0.001246806957791023,
      "grad_norm": 1.8720107464553335,
      "kl": 0.00830078125,
      "learning_rate": 9.99996164361818e-07,
      "loss": 0.0003,
      "reward": 1.3554950952529907,
      "reward_std": 0.10378493368625641,
      "rewards/accuracy_reward": 0.305495023727417,
      "rewards/format_reward": 1.0,
      "step": 41,
      "temperature": 1.0
    },
    {
      "all_correct": 0.25,
      "all_wrong": 0.0,
      "completion_length": 405.359375,
      "epoch": 0.0012772168835908041,
      "grad_norm": 1.9376029926340375,
      "kl": 0.0111083984375,
      "learning_rate": 9.999959749760108e-07,
      "loss": 0.0004,
      "reward": 1.6944656372070312,
      "reward_std": 0.2876342236995697,
      "rewards/accuracy_reward": 0.5757156610488892,
      "rewards/format_reward": 1.0,
      "step": 42,
      "temperature": 1.0
    },
    {
      "all_correct": 0.75,
      "all_wrong": 0.0,
      "completion_length": 352.34375,
      "epoch": 0.001307626809390585,
      "grad_norm": 1.247138658977461,
      "kl": 0.01123046875,
      "learning_rate": 9.99995781026715e-07,
      "loss": 0.0004,
      "reward": 2.0968751907348633,
      "reward_std": 0.15718582272529602,
      "rewards/accuracy_reward": 0.953125,
      "rewards/format_reward": 1.0,
      "step": 43,
      "temperature": 1.0
    },
    {
      "all_correct": 0.375,
      "all_wrong": 0.125,
      "completion_length": 395.4375,
      "epoch": 0.0013380367351903662,
      "grad_norm": 1.1259095782576038,
      "kl": 0.01202392578125,
      "learning_rate": 9.999955825139322e-07,
      "loss": 0.0005,
      "reward": 1.735487699508667,
      "reward_std": 0.1868601143360138,
      "rewards/accuracy_reward": 0.6354876756668091,
      "rewards/format_reward": 0.984375,
      "step": 44,
      "temperature": 1.0
    },
    {
      "all_correct": 0.125,
      "all_wrong": 0.0,
      "completion_length": 435.25,
      "epoch": 0.001368446660990147,
      "grad_norm": 1.4793116261961232,
      "kl": 0.00897216796875,
      "learning_rate": 9.999953794376643e-07,
      "loss": 0.0004,
      "reward": 1.7550036907196045,
      "reward_std": 0.37853968143463135,
      "rewards/accuracy_reward": 0.6425036191940308,
      "rewards/format_reward": 0.984375,
      "step": 45,
      "temperature": 1.0
    },
    {
      "all_correct": 0.375,
      "all_wrong": 0.0,
      "completion_length": 413.34375,
      "epoch": 0.0013988565867899283,
      "grad_norm": 1.441985044139194,
      "kl": 0.01287841796875,
      "learning_rate": 9.999951717979134e-07,
      "loss": 0.0005,
      "reward": 1.7012786865234375,
      "reward_std": 0.22611986100673676,
      "rewards/accuracy_reward": 0.5919036269187927,
      "rewards/format_reward": 1.0,
      "step": 46,
      "temperature": 1.0
    },
    {
      "all_correct": 0.25,
      "all_wrong": 0.0,
      "completion_length": 437.171875,
      "epoch": 0.0014292665125897092,
      "grad_norm": 2.566395975798807,
      "kl": 0.0111083984375,
      "learning_rate": 9.99994959594681e-07,
      "loss": 0.0004,
      "reward": 1.748474359512329,
      "reward_std": 0.3263983130455017,
      "rewards/accuracy_reward": 0.6359742879867554,
      "rewards/format_reward": 1.0,
      "step": 47,
      "temperature": 1.0
    },
    {
      "all_correct": 0.125,
      "all_wrong": 0.125,
      "completion_length": 469.3125,
      "epoch": 0.0014596764383894903,
      "grad_norm": 1.2051169690229298,
      "kl": 0.0089111328125,
      "learning_rate": 9.999947428279694e-07,
      "loss": 0.0004,
      "reward": 1.3944621086120605,
      "reward_std": 0.32815349102020264,
      "rewards/accuracy_reward": 0.38508710265159607,
      "rewards/format_reward": 0.921875,
      "step": 48,
      "temperature": 1.0
    },
    {
      "all_correct": 0.375,
      "all_wrong": 0.125,
      "completion_length": 420.796875,
      "epoch": 0.0014900863641892715,
      "grad_norm": 1.2857179475078493,
      "kl": 0.01416015625,
      "learning_rate": 9.999945214977802e-07,
      "loss": 0.0006,
      "reward": 1.730210304260254,
      "reward_std": 0.15597693622112274,
      "rewards/accuracy_reward": 0.633335292339325,
      "rewards/format_reward": 1.0,
      "step": 49,
      "temperature": 1.0
    },
    {
      "all_correct": 0.25,
      "all_wrong": 0.25,
      "completion_length": 341.71875,
      "epoch": 0.0015204962899890524,
      "grad_norm": 1.6077028970954936,
      "kl": 0.0172119140625,
      "learning_rate": 9.999942956041157e-07,
      "loss": 0.0007,
      "reward": 1.4790146350860596,
      "reward_std": 0.20343194901943207,
      "rewards/accuracy_reward": 0.41338956356048584,
      "rewards/format_reward": 1.0,
      "step": 50,
      "temperature": 1.0
    },
    {
      "all_correct": 0.375,
      "all_wrong": 0.25,
      "completion_length": 427.390625,
      "epoch": 0.0015509062157888335,
      "grad_norm": 1.2833602919748015,
      "kl": 0.0155029296875,
      "learning_rate": 9.999940651469777e-07,
      "loss": 0.0006,
      "reward": 1.6171908378601074,
      "reward_std": 0.16841214895248413,
      "rewards/accuracy_reward": 0.5328157544136047,
      "rewards/format_reward": 0.984375,
      "step": 51,
      "temperature": 1.0
    },
    {
      "all_correct": 0.125,
      "all_wrong": 0.0,
      "completion_length": 473.90625,
      "epoch": 0.0015813161415886145,
      "grad_norm": 1.5347386121422006,
      "kl": 0.010498046875,
      "learning_rate": 9.999938301263689e-07,
      "loss": 0.0004,
      "reward": 1.446211576461792,
      "reward_std": 0.3887838125228882,
      "rewards/accuracy_reward": 0.45246145129203796,
      "rewards/format_reward": 0.90625,
      "step": 52,
      "temperature": 1.0
    },
    {
      "all_correct": 0.75,
      "all_wrong": 0.0,
      "completion_length": 377.109375,
      "epoch": 0.0016117260673883956,
      "grad_norm": 1.3010726103581274,
      "kl": 0.017333984375,
      "learning_rate": 9.999935905422906e-07,
      "loss": 0.0007,
      "reward": 2.03125,
      "reward_std": 0.19370707869529724,
      "rewards/accuracy_reward": 0.875,
      "rewards/format_reward": 1.0,
      "step": 53,
      "temperature": 1.0
    },
    {
      "all_correct": 0.375,
      "all_wrong": 0.0,
      "completion_length": 375.0,
      "epoch": 0.0016421359931881765,
      "grad_norm": 1.8165008374461562,
      "kl": 0.01531982421875,
      "learning_rate": 9.999933463947457e-07,
      "loss": 0.0006,
      "reward": 1.7314881086349487,
      "reward_std": 0.254728227853775,
      "rewards/accuracy_reward": 0.6252381205558777,
      "rewards/format_reward": 1.0,
      "step": 54,
      "temperature": 1.0
    },
    {
      "all_correct": 0.375,
      "all_wrong": 0.25,
      "completion_length": 448.5625,
      "epoch": 0.0016725459189879577,
      "grad_norm": 1.1805774442651564,
      "kl": 0.011962890625,
      "learning_rate": 9.99993097683736e-07,
      "loss": 0.0005,
      "reward": 1.5063714981079102,
      "reward_std": 0.17219069600105286,
      "rewards/accuracy_reward": 0.4501214325428009,
      "rewards/format_reward": 0.96875,
      "step": 55,
      "temperature": 1.0
    },
    {
      "all_correct": 0.625,
      "all_wrong": 0.125,
      "completion_length": 419.53125,
      "epoch": 0.0017029558447877388,
      "grad_norm": 0.6537447709750156,
      "kl": 0.01507568359375,
      "learning_rate": 9.99992844409264e-07,
      "loss": 0.0006,
      "reward": 1.8656249046325684,
      "reward_std": 0.16710473597049713,
      "rewards/accuracy_reward": 0.75,
      "rewards/format_reward": 0.984375,
      "step": 56,
      "temperature": 1.0
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.0,
      "completion_length": 421.296875,
      "epoch": 0.0017333657705875197,
      "grad_norm": 1.0263463835692015,
      "kl": 0.010986328125,
      "learning_rate": 9.99992586571332e-07,
      "loss": 0.0004,
      "reward": 1.945468783378601,
      "reward_std": 0.2802686393260956,
      "rewards/accuracy_reward": 0.7985937595367432,
      "rewards/format_reward": 1.0,
      "step": 57,
      "temperature": 1.0
    },
    {
      "all_correct": 0.25,
      "all_wrong": 0.25,
      "completion_length": 437.375,
      "epoch": 0.0017637756963873009,
      "grad_norm": 1.076073320456093,
      "kl": 0.0130615234375,
      "learning_rate": 9.999923241699422e-07,
      "loss": 0.0005,
      "reward": 1.686951994895935,
      "reward_std": 0.19162070751190186,
      "rewards/accuracy_reward": 0.5869519114494324,
      "rewards/format_reward": 1.0,
      "step": 58,
      "temperature": 1.0
    },
    {
      "all_correct": 0.375,
      "all_wrong": 0.125,
      "completion_length": 445.4375,
      "epoch": 0.0017941856221870818,
      "grad_norm": 0.9960617743408544,
      "kl": 0.0123291015625,
      "learning_rate": 9.99992057205097e-07,
      "loss": 0.0005,
      "reward": 1.6391254663467407,
      "reward_std": 0.24785034358501434,
      "rewards/accuracy_reward": 0.573500394821167,
      "rewards/format_reward": 0.9375,
      "step": 59,
      "temperature": 1.0
    },
    {
      "all_correct": 0.25,
      "all_wrong": 0.125,
      "completion_length": 420.875,
      "epoch": 0.001824595547986863,
      "grad_norm": 6.483373705035169,
      "kl": 0.01336669921875,
      "learning_rate": 9.99991785676799e-07,
      "loss": 0.0005,
      "reward": 1.6313416957855225,
      "reward_std": 0.20466020703315735,
      "rewards/accuracy_reward": 0.5407165884971619,
      "rewards/format_reward": 1.0,
      "step": 60,
      "temperature": 1.0
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.125,
      "completion_length": 375.78125,
      "epoch": 0.0018550054737866439,
      "grad_norm": 2.093180961005048,
      "kl": 0.015625,
      "learning_rate": 9.999915095850507e-07,
      "loss": 0.0006,
      "reward": 1.7097656726837158,
      "reward_std": 0.19712693989276886,
      "rewards/accuracy_reward": 0.603515625,
      "rewards/format_reward": 1.0,
      "step": 61,
      "temperature": 1.0
    },
    {
      "all_correct": 0.375,
      "all_wrong": 0.25,
      "completion_length": 382.09375,
      "epoch": 0.001885415399586425,
      "grad_norm": 0.9596082118279999,
      "kl": 0.01544189453125,
      "learning_rate": 9.999912289298542e-07,
      "loss": 0.0006,
      "reward": 1.7470896244049072,
      "reward_std": 0.13650238513946533,
      "rewards/accuracy_reward": 0.6252144575119019,
      "rewards/format_reward": 1.0,
      "step": 62,
      "temperature": 1.0
    },
    {
      "all_correct": 0.75,
      "all_wrong": 0.0,
      "completion_length": 381.953125,
      "epoch": 0.001915825325386206,
      "grad_norm": 0.9498841030661145,
      "kl": 0.015625,
      "learning_rate": 9.999909437112127e-07,
      "loss": 0.0006,
      "reward": 2.0062499046325684,
      "reward_std": 0.15554746985435486,
      "rewards/accuracy_reward": 0.84375,
      "rewards/format_reward": 1.0,
      "step": 63,
      "temperature": 1.0
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.0,
      "completion_length": 368.390625,
      "epoch": 0.001946235251185987,
      "grad_norm": 1.4807535326882024,
      "kl": 0.01416015625,
      "learning_rate": 9.999906539291283e-07,
      "loss": 0.0006,
      "reward": 1.8768644332885742,
      "reward_std": 0.21333277225494385,
      "rewards/accuracy_reward": 0.7331144213676453,
      "rewards/format_reward": 1.0,
      "step": 64,
      "temperature": 1.0
    },
    {
      "all_correct": 0.25,
      "all_wrong": 0.0,
      "completion_length": 427.296875,
      "epoch": 0.001976645176985768,
      "grad_norm": 1.214398911591177,
      "kl": 0.0101318359375,
      "learning_rate": 9.999903595836038e-07,
      "loss": 0.0004,
      "reward": 1.7070368528366089,
      "reward_std": 0.34790247678756714,
      "rewards/accuracy_reward": 0.6070367693901062,
      "rewards/format_reward": 1.0,
      "step": 65,
      "temperature": 1.0
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.125,
      "completion_length": 461.140625,
      "epoch": 0.0020070551027855494,
      "grad_norm": 1.4959046818170132,
      "kl": 0.01165771484375,
      "learning_rate": 9.99990060674642e-07,
      "loss": 0.0005,
      "reward": 1.6366686820983887,
      "reward_std": 0.1298898160457611,
      "rewards/accuracy_reward": 0.5710436105728149,
      "rewards/format_reward": 0.953125,
      "step": 66,
      "temperature": 1.0
    },
    {
      "all_correct": 0.125,
      "all_wrong": 0.375,
      "completion_length": 438.390625,
      "epoch": 0.0020374650285853303,
      "grad_norm": 4.538453262127269,
      "kl": 0.00933837890625,
      "learning_rate": 9.999897572022456e-07,
      "loss": 0.0004,
      "reward": 1.4098670482635498,
      "reward_std": 0.1763109415769577,
      "rewards/accuracy_reward": 0.34111708402633667,
      "rewards/format_reward": 0.984375,
      "step": 67,
      "temperature": 1.0
    },
    {
      "all_correct": 0.375,
      "all_wrong": 0.0,
      "completion_length": 435.34375,
      "epoch": 0.0020678749543851112,
      "grad_norm": 2.0874902548005756,
      "kl": 0.0096435546875,
      "learning_rate": 9.99989449166417e-07,
      "loss": 0.0004,
      "reward": 1.7215529680252075,
      "reward_std": 0.21077515184879303,
      "rewards/accuracy_reward": 0.6215529441833496,
      "rewards/format_reward": 1.0,
      "step": 68,
      "temperature": 1.0
    },
    {
      "all_correct": 0.25,
      "all_wrong": 0.0,
      "completion_length": 436.984375,
      "epoch": 0.002098284880184892,
      "grad_norm": 1.7146351828596011,
      "kl": 0.0113525390625,
      "learning_rate": 9.999891365671596e-07,
      "loss": 0.0005,
      "reward": 1.6222567558288574,
      "reward_std": 0.27506405115127563,
      "rewards/accuracy_reward": 0.5222567915916443,
      "rewards/format_reward": 1.0,
      "step": 69,
      "temperature": 1.0
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.0,
      "completion_length": 410.46875,
      "epoch": 0.0021286948059846735,
      "grad_norm": 2.197154462353113,
      "kl": 0.0166015625,
      "learning_rate": 9.99988819404476e-07,
      "loss": 0.0007,
      "reward": 1.8892011642456055,
      "reward_std": 0.23192350566387177,
      "rewards/accuracy_reward": 0.7548261284828186,
      "rewards/format_reward": 1.0,
      "step": 70,
      "temperature": 1.0
    },
    {
      "all_correct": 0.25,
      "all_wrong": 0.25,
      "completion_length": 394.96875,
      "epoch": 0.0021591047317844544,
      "grad_norm": 1.1189918218015957,
      "kl": 0.013671875,
      "learning_rate": 9.999884976783688e-07,
      "loss": 0.0005,
      "reward": 1.357374668121338,
      "reward_std": 0.22493042051792145,
      "rewards/accuracy_reward": 0.332374632358551,
      "rewards/format_reward": 0.96875,
      "step": 71,
      "temperature": 1.0
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.0,
      "completion_length": 395.453125,
      "epoch": 0.0021895146575842354,
      "grad_norm": 1.451347471947504,
      "kl": 0.015869140625,
      "learning_rate": 9.999881713888414e-07,
      "loss": 0.0006,
      "reward": 1.8340792655944824,
      "reward_std": 0.17378279566764832,
      "rewards/accuracy_reward": 0.6965792179107666,
      "rewards/format_reward": 1.0,
      "step": 72,
      "temperature": 1.0
    },
    {
      "all_correct": 0.125,
      "all_wrong": 0.125,
      "completion_length": 388.84375,
      "epoch": 0.0022199245833840167,
      "grad_norm": 1.685924842797364,
      "kl": 0.01220703125,
      "learning_rate": 9.999878405358967e-07,
      "loss": 0.0005,
      "reward": 1.6226558685302734,
      "reward_std": 0.18531137704849243,
      "rewards/accuracy_reward": 0.5382808446884155,
      "rewards/format_reward": 1.0,
      "step": 73,
      "temperature": 1.0
    },
    {
      "all_correct": 0.25,
      "all_wrong": 0.0,
      "completion_length": 463.265625,
      "epoch": 0.0022503345091837977,
      "grad_norm": 1.6190723344090046,
      "kl": 0.01031494140625,
      "learning_rate": 9.999875051195372e-07,
      "loss": 0.0004,
      "reward": 1.6120021343231201,
      "reward_std": 0.3168191909790039,
      "rewards/accuracy_reward": 0.524502158164978,
      "rewards/format_reward": 1.0,
      "step": 74,
      "temperature": 1.0
    },
    {
      "all_correct": 0.375,
      "all_wrong": 0.25,
      "completion_length": 451.765625,
      "epoch": 0.0022807444349835786,
      "grad_norm": 3.5254170467954453,
      "kl": 0.01220703125,
      "learning_rate": 9.999871651397667e-07,
      "loss": 0.0005,
      "reward": 1.6127300262451172,
      "reward_std": 0.15051430463790894,
      "rewards/accuracy_reward": 0.5596050024032593,
      "rewards/format_reward": 0.984375,
      "step": 75,
      "temperature": 1.0
    },
    {
      "all_correct": 0.375,
      "all_wrong": 0.25,
      "completion_length": 383.015625,
      "epoch": 0.0023111543607833595,
      "grad_norm": 0.8987896270440928,
      "kl": 0.016357421875,
      "learning_rate": 9.999868205965878e-07,
      "loss": 0.0007,
      "reward": 1.6875,
      "reward_std": 0.21905139088630676,
      "rewards/accuracy_reward": 0.578125,
      "rewards/format_reward": 1.0,
      "step": 76,
      "temperature": 1.0
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.125,
      "completion_length": 385.859375,
      "epoch": 0.002341564286583141,
      "grad_norm": 1.2105123411895744,
      "kl": 0.0140380859375,
      "learning_rate": 9.99986471490004e-07,
      "loss": 0.0006,
      "reward": 1.7625000476837158,
      "reward_std": 0.20695412158966064,
      "rewards/accuracy_reward": 0.65625,
      "rewards/format_reward": 1.0,
      "step": 77,
      "temperature": 1.0
    },
    {
      "all_correct": 0.375,
      "all_wrong": 0.0,
      "completion_length": 391.59375,
      "epoch": 0.002371974212382922,
      "grad_norm": 1.6022385015193465,
      "kl": 0.01318359375,
      "learning_rate": 9.99986117820018e-07,
      "loss": 0.0005,
      "reward": 1.801504373550415,
      "reward_std": 0.24511218070983887,
      "rewards/accuracy_reward": 0.6733792424201965,
      "rewards/format_reward": 1.0,
      "step": 78,
      "temperature": 1.0
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.125,
      "completion_length": 427.078125,
      "epoch": 0.0024023841381827027,
      "grad_norm": 1.2043719522172864,
      "kl": 0.01116943359375,
      "learning_rate": 9.999857595866335e-07,
      "loss": 0.0004,
      "reward": 1.7467107772827148,
      "reward_std": 0.17070460319519043,
      "rewards/accuracy_reward": 0.6467106938362122,
      "rewards/format_reward": 1.0,
      "step": 79,
      "temperature": 1.0
    },
    {
      "all_correct": 0.125,
      "all_wrong": 0.25,
      "completion_length": 431.390625,
      "epoch": 0.002432794063982484,
      "grad_norm": 2.108227862622634,
      "kl": 0.01446533203125,
      "learning_rate": 9.999853967898537e-07,
      "loss": 0.0006,
      "reward": 1.3918615579605103,
      "reward_std": 0.11718933284282684,
      "rewards/accuracy_reward": 0.32623645663261414,
      "rewards/format_reward": 1.0,
      "step": 80,
      "temperature": 1.0
    },
    {
      "all_correct": 0.625,
      "all_wrong": 0.125,
      "completion_length": 404.5,
      "epoch": 0.002463203989782265,
      "grad_norm": 0.9692539817597077,
      "kl": 0.01318359375,
      "learning_rate": 9.999850294296816e-07,
      "loss": 0.0005,
      "reward": 1.8312500715255737,
      "reward_std": 0.16712023317813873,
      "rewards/accuracy_reward": 0.71875,
      "rewards/format_reward": 1.0,
      "step": 81,
      "temperature": 1.0
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.125,
      "completion_length": 402.109375,
      "epoch": 0.002493613915582046,
      "grad_norm": 0.8761166873709011,
      "kl": 0.01409912109375,
      "learning_rate": 9.99984657506121e-07,
      "loss": 0.0006,
      "reward": 1.6949537992477417,
      "reward_std": 0.12685883045196533,
      "rewards/accuracy_reward": 0.6105788350105286,
      "rewards/format_reward": 1.0,
      "step": 82,
      "temperature": 1.0
    },
    {
      "all_correct": 0.375,
      "all_wrong": 0.125,
      "completion_length": 435.03125,
      "epoch": 0.002524023841381827,
      "grad_norm": 2.2100798784549505,
      "kl": 0.01092529296875,
      "learning_rate": 9.999842810191747e-07,
      "loss": 0.0004,
      "reward": 1.64670991897583,
      "reward_std": 0.2460305094718933,
      "rewards/accuracy_reward": 0.540459930896759,
      "rewards/format_reward": 1.0,
      "step": 83,
      "temperature": 1.0
    },
    {
      "all_correct": 0.625,
      "all_wrong": 0.125,
      "completion_length": 395.890625,
      "epoch": 0.0025544337671816082,
      "grad_norm": 1.3487257761624414,
      "kl": 0.01507568359375,
      "learning_rate": 9.999838999688465e-07,
      "loss": 0.0006,
      "reward": 1.8760416507720947,
      "reward_std": 0.13139429688453674,
      "rewards/accuracy_reward": 0.7635416984558105,
      "rewards/format_reward": 1.0,
      "step": 84,
      "temperature": 1.0
    },
    {
      "all_correct": 0.375,
      "all_wrong": 0.125,
      "completion_length": 425.90625,
      "epoch": 0.002584843692981389,
      "grad_norm": 1.4077493051045469,
      "kl": 0.012451171875,
      "learning_rate": 9.999835143551402e-07,
      "loss": 0.0005,
      "reward": 1.8503814935684204,
      "reward_std": 0.19670003652572632,
      "rewards/accuracy_reward": 0.7191314101219177,
      "rewards/format_reward": 1.0,
      "step": 85,
      "temperature": 1.0
    },
    {
      "all_correct": 0.625,
      "all_wrong": 0.0,
      "completion_length": 409.921875,
      "epoch": 0.00261525361878117,
      "grad_norm": 1.326853347999934,
      "kl": 0.01263427734375,
      "learning_rate": 9.999831241780588e-07,
      "loss": 0.0005,
      "reward": 1.9051461219787598,
      "reward_std": 0.13108865916728973,
      "rewards/accuracy_reward": 0.7707711458206177,
      "rewards/format_reward": 1.0,
      "step": 86,
      "temperature": 1.0
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.125,
      "completion_length": 408.6875,
      "epoch": 0.0026456635445809514,
      "grad_norm": 1.5100265978927194,
      "kl": 0.01513671875,
      "learning_rate": 9.99982729437606e-07,
      "loss": 0.0006,
      "reward": 1.7437500953674316,
      "reward_std": 0.31241440773010254,
      "rewards/accuracy_reward": 0.6875,
      "rewards/format_reward": 0.9375,
      "step": 87,
      "temperature": 1.0
    },
    {
      "all_correct": 0.625,
      "all_wrong": 0.125,
      "completion_length": 389.625,
      "epoch": 0.0026760734703807324,
      "grad_norm": 1.3926909394883846,
      "kl": 0.01434326171875,
      "learning_rate": 9.999823301337855e-07,
      "loss": 0.0006,
      "reward": 1.8625000715255737,
      "reward_std": 0.14150118827819824,
      "rewards/accuracy_reward": 0.734375,
      "rewards/format_reward": 1.0,
      "step": 88,
      "temperature": 1.0
    },
    {
      "all_correct": 0.375,
      "all_wrong": 0.125,
      "completion_length": 431.109375,
      "epoch": 0.0027064833961805133,
      "grad_norm": 1.859221024826941,
      "kl": 0.0111083984375,
      "learning_rate": 9.99981926266601e-07,
      "loss": 0.0004,
      "reward": 1.78244948387146,
      "reward_std": 0.28553903102874756,
      "rewards/accuracy_reward": 0.666824460029602,
      "rewards/format_reward": 0.984375,
      "step": 89,
      "temperature": 1.0
    },
    {
      "all_correct": 0.625,
      "all_wrong": 0.0,
      "completion_length": 412.21875,
      "epoch": 0.002736893321980294,
      "grad_norm": 1.620012331539679,
      "kl": 0.01214599609375,
      "learning_rate": 9.99981517836056e-07,
      "loss": 0.0005,
      "reward": 1.9375,
      "reward_std": 0.20358122885227203,
      "rewards/accuracy_reward": 0.796875,
      "rewards/format_reward": 1.0,
      "step": 90,
      "temperature": 1.0
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.375,
      "completion_length": 399.875,
      "epoch": 0.0027673032477800756,
      "grad_norm": 1.0283293281513692,
      "kl": 0.01190185546875,
      "learning_rate": 9.999811048421543e-07,
      "loss": 0.0005,
      "reward": 1.671875,
      "reward_std": 0.08074887096881866,
      "rewards/accuracy_reward": 0.578125,
      "rewards/format_reward": 1.0,
      "step": 91,
      "temperature": 1.0
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.125,
      "completion_length": 434.25,
      "epoch": 0.0027977131735798565,
      "grad_norm": 1.2589396013442424,
      "kl": 0.01177978515625,
      "learning_rate": 9.999806872848996e-07,
      "loss": 0.0005,
      "reward": 1.740625023841858,
      "reward_std": 0.20894074440002441,
      "rewards/accuracy_reward": 0.625,
      "rewards/format_reward": 1.0,
      "step": 92,
      "temperature": 1.0
    },
    {
      "all_correct": 0.75,
      "all_wrong": 0.0,
      "completion_length": 406.765625,
      "epoch": 0.0028281230993796374,
      "grad_norm": 1.2290289686000981,
      "kl": 0.01214599609375,
      "learning_rate": 9.999802651642959e-07,
      "loss": 0.0005,
      "reward": 1.870416522026062,
      "reward_std": 0.19986608624458313,
      "rewards/accuracy_reward": 0.8079164624214172,
      "rewards/format_reward": 0.953125,
      "step": 93,
      "temperature": 1.0
    },
    {
      "all_correct": 0.25,
      "all_wrong": 0.0,
      "completion_length": 421.109375,
      "epoch": 0.0028585330251794184,
      "grad_norm": 1.6494777381764956,
      "kl": 0.012939453125,
      "learning_rate": 9.999798384803468e-07,
      "loss": 0.0005,
      "reward": 1.7553774118423462,
      "reward_std": 0.3744775652885437,
      "rewards/accuracy_reward": 0.6335023045539856,
      "rewards/format_reward": 1.0,
      "step": 94,
      "temperature": 1.0
    },
    {
      "all_correct": 0.375,
      "all_wrong": 0.0,
      "completion_length": 390.984375,
      "epoch": 0.0028889429509791997,
      "grad_norm": 1.2261005372553526,
      "kl": 0.0135498046875,
      "learning_rate": 9.999794072330564e-07,
      "loss": 0.0005,
      "reward": 1.821874976158142,
      "reward_std": 0.3170676827430725,
      "rewards/accuracy_reward": 0.71875,
      "rewards/format_reward": 0.984375,
      "step": 95,
      "temperature": 1.0
    },
    {
      "all_correct": 0.25,
      "all_wrong": 0.0,
      "completion_length": 397.6875,
      "epoch": 0.0029193528767789806,
      "grad_norm": 1.320081343511887,
      "kl": 0.0120849609375,
      "learning_rate": 9.999789714224287e-07,
      "loss": 0.0005,
      "reward": 1.955208420753479,
      "reward_std": 0.2944028377532959,
      "rewards/accuracy_reward": 0.8020833134651184,
      "rewards/format_reward": 1.0,
      "step": 96,
      "temperature": 1.0
    },
    {
      "all_correct": 0.75,
      "all_wrong": 0.0,
      "completion_length": 389.765625,
      "epoch": 0.0029497628025787616,
      "grad_norm": 1.7815217711393854,
      "kl": 0.015869140625,
      "learning_rate": 9.999785310484673e-07,
      "loss": 0.0006,
      "reward": 2.0625,
      "reward_std": 0.16938352584838867,
      "rewards/accuracy_reward": 0.890625,
      "rewards/format_reward": 1.0,
      "step": 97,
      "temperature": 1.0
    },
    {
      "all_correct": 0.375,
      "all_wrong": 0.0,
      "completion_length": 400.140625,
      "epoch": 0.002980172728378543,
      "grad_norm": 1.8925236124886895,
      "kl": 0.01336669921875,
      "learning_rate": 9.999780861111765e-07,
      "loss": 0.0005,
      "reward": 1.8936694860458374,
      "reward_std": 0.21802827715873718,
      "rewards/accuracy_reward": 0.7467944622039795,
      "rewards/format_reward": 1.0,
      "step": 98,
      "temperature": 1.0
    },
    {
      "all_correct": 0.25,
      "all_wrong": 0.0,
      "completion_length": 425.28125,
      "epoch": 0.003010582654178324,
      "grad_norm": 1.3099964918558389,
      "kl": 0.0133056640625,
      "learning_rate": 9.999776366105606e-07,
      "loss": 0.0005,
      "reward": 1.855330467224121,
      "reward_std": 0.3692500591278076,
      "rewards/accuracy_reward": 0.7553303837776184,
      "rewards/format_reward": 0.96875,
      "step": 99,
      "temperature": 1.0
    },
    {
      "all_correct": 0.375,
      "all_wrong": 0.0,
      "completion_length": 371.8125,
      "epoch": 0.0030409925799781048,
      "grad_norm": 1.6107059297561335,
      "kl": 0.01300048828125,
      "learning_rate": 9.999771825466232e-07,
      "loss": 0.0005,
      "reward": 1.9406250715255737,
      "reward_std": 0.2936359941959381,
      "rewards/accuracy_reward": 0.796875,
      "rewards/format_reward": 1.0,
      "step": 100,
      "temperature": 1.0
    },
    {
      "all_correct": 0.375,
      "all_wrong": 0.25,
      "completion_length": 381.0,
      "epoch": 0.0030714025057778857,
      "grad_norm": 1.1435506156259134,
      "kl": 0.01336669921875,
      "learning_rate": 9.999767239193688e-07,
      "loss": 0.0005,
      "reward": 1.6163592338562012,
      "reward_std": 0.10960143804550171,
      "rewards/accuracy_reward": 0.5069841742515564,
      "rewards/format_reward": 1.0,
      "step": 101,
      "temperature": 1.0
    },
    {
      "all_correct": 0.75,
      "all_wrong": 0.0,
      "completion_length": 375.046875,
      "epoch": 0.003101812431577667,
      "grad_norm": 1.191072112005555,
      "kl": 0.012939453125,
      "learning_rate": 9.999762607288014e-07,
      "loss": 0.0005,
      "reward": 2.0187501907348633,
      "reward_std": 0.18259362876415253,
      "rewards/accuracy_reward": 0.875,
      "rewards/format_reward": 1.0,
      "step": 102,
      "temperature": 1.0
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.125,
      "completion_length": 360.6875,
      "epoch": 0.003132222357377448,
      "grad_norm": 1.2120608878998178,
      "kl": 0.0130615234375,
      "learning_rate": 9.999757929749252e-07,
      "loss": 0.0005,
      "reward": 1.8628289699554443,
      "reward_std": 0.11512254178524017,
      "rewards/accuracy_reward": 0.7128288745880127,
      "rewards/format_reward": 1.0,
      "step": 103,
      "temperature": 1.0
    },
    {
      "all_correct": 0.625,
      "all_wrong": 0.0,
      "completion_length": 365.703125,
      "epoch": 0.003162632283177229,
      "grad_norm": 1.5119521598542058,
      "kl": 0.0135498046875,
      "learning_rate": 9.999753206577448e-07,
      "loss": 0.0005,
      "reward": 1.9562499523162842,
      "reward_std": 0.2622116506099701,
      "rewards/accuracy_reward": 0.828125,
      "rewards/format_reward": 1.0,
      "step": 104,
      "temperature": 1.0
    },
    {
      "all_correct": 0.125,
      "all_wrong": 0.125,
      "completion_length": 454.21875,
      "epoch": 0.0031930422089770103,
      "grad_norm": 1.4115809218417046,
      "kl": 0.0108642578125,
      "learning_rate": 9.99974843777264e-07,
      "loss": 0.0004,
      "reward": 1.4562711715698242,
      "reward_std": 0.34898149967193604,
      "rewards/accuracy_reward": 0.40627118945121765,
      "rewards/format_reward": 0.96875,
      "step": 105,
      "temperature": 1.0
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.125,
      "completion_length": 375.03125,
      "epoch": 0.003223452134776791,
      "grad_norm": 1.1943710506900078,
      "kl": 0.01202392578125,
      "learning_rate": 9.999743623334876e-07,
      "loss": 0.0005,
      "reward": 1.7741870880126953,
      "reward_std": 0.17306214570999146,
      "rewards/accuracy_reward": 0.6648120880126953,
      "rewards/format_reward": 1.0,
      "step": 106,
      "temperature": 1.0
    },
    {
      "all_correct": 0.375,
      "all_wrong": 0.0,
      "completion_length": 378.46875,
      "epoch": 0.003253862060576572,
      "grad_norm": 1.4729281075548473,
      "kl": 0.0103759765625,
      "learning_rate": 9.999738763264197e-07,
      "loss": 0.0004,
      "reward": 1.9126482009887695,
      "reward_std": 0.32268238067626953,
      "rewards/accuracy_reward": 0.7657730579376221,
      "rewards/format_reward": 0.984375,
      "step": 107,
      "temperature": 1.0
    },
    {
      "all_correct": 0.375,
      "all_wrong": 0.125,
      "completion_length": 446.046875,
      "epoch": 0.003284271986376353,
      "grad_norm": 1.705785582140939,
      "kl": 0.00927734375,
      "learning_rate": 9.999733857560649e-07,
      "loss": 0.0004,
      "reward": 1.613050103187561,
      "reward_std": 0.27703195810317993,
      "rewards/accuracy_reward": 0.5661750435829163,
      "rewards/format_reward": 0.953125,
      "step": 108,
      "temperature": 1.0
    },
    {
      "all_correct": 0.125,
      "all_wrong": 0.5,
      "completion_length": 499.96875,
      "epoch": 0.0033146819121761344,
      "grad_norm": 0.9622434953213093,
      "kl": 0.00909423828125,
      "learning_rate": 9.999728906224276e-07,
      "loss": 0.0004,
      "reward": 1.2282872200012207,
      "reward_std": 0.09929470717906952,
      "rewards/accuracy_reward": 0.23766222596168518,
      "rewards/format_reward": 0.96875,
      "step": 109,
      "temperature": 1.0
    },
    {
      "all_correct": 0.375,
      "all_wrong": 0.25,
      "completion_length": 438.3125,
      "epoch": 0.0033450918379759153,
      "grad_norm": 1.697222097259729,
      "kl": 0.010498046875,
      "learning_rate": 9.999723909255124e-07,
      "loss": 0.0004,
      "reward": 1.6912615299224854,
      "reward_std": 0.24412010610103607,
      "rewards/accuracy_reward": 0.6318864822387695,
      "rewards/format_reward": 0.953125,
      "step": 110,
      "temperature": 1.0
    },
    {
      "all_correct": 0.375,
      "all_wrong": 0.125,
      "completion_length": 412.703125,
      "epoch": 0.0033755017637756963,
      "grad_norm": 1.2369543491609039,
      "kl": 0.01123046875,
      "learning_rate": 9.999718866653237e-07,
      "loss": 0.0005,
      "reward": 1.7088282108306885,
      "reward_std": 0.3435198664665222,
      "rewards/accuracy_reward": 0.624453067779541,
      "rewards/format_reward": 0.96875,
      "step": 111,
      "temperature": 1.0
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.0,
      "completion_length": 422.1875,
      "epoch": 0.0034059116895754776,
      "grad_norm": 1.8507689567213426,
      "kl": 0.01190185546875,
      "learning_rate": 9.999713778418665e-07,
      "loss": 0.0005,
      "reward": 1.9233193397521973,
      "reward_std": 0.22450970113277435,
      "rewards/accuracy_reward": 0.8108192682266235,
      "rewards/format_reward": 0.984375,
      "step": 112,
      "temperature": 1.0
    },
    {
      "all_correct": 0.25,
      "all_wrong": 0.375,
      "completion_length": 404.984375,
      "epoch": 0.0034363216153752586,
      "grad_norm": 1.399880525066186,
      "kl": 0.0133056640625,
      "learning_rate": 9.999708644551448e-07,
      "loss": 0.0005,
      "reward": 1.4375,
      "reward_std": 0.17550253868103027,
      "rewards/accuracy_reward": 0.375,
      "rewards/format_reward": 1.0,
      "step": 113,
      "temperature": 1.0
    },
    {
      "all_correct": 0.375,
      "all_wrong": 0.125,
      "completion_length": 384.15625,
      "epoch": 0.0034667315411750395,
      "grad_norm": 1.8157402050726867,
      "kl": 0.01275634765625,
      "learning_rate": 9.999703465051638e-07,
      "loss": 0.0005,
      "reward": 1.6812500953674316,
      "reward_std": 0.27547648549079895,
      "rewards/accuracy_reward": 0.59375,
      "rewards/format_reward": 1.0,
      "step": 114,
      "temperature": 1.0
    },
    {
      "all_correct": 0.25,
      "all_wrong": 0.25,
      "completion_length": 374.140625,
      "epoch": 0.0034971414669748204,
      "grad_norm": 1.3256303335408497,
      "kl": 0.01416015625,
      "learning_rate": 9.999698239919282e-07,
      "loss": 0.0006,
      "reward": 1.5202667713165283,
      "reward_std": 0.23908200860023499,
      "rewards/accuracy_reward": 0.44214165210723877,
      "rewards/format_reward": 1.0,
      "step": 115,
      "temperature": 1.0
    },
    {
      "all_correct": 0.25,
      "all_wrong": 0.0,
      "completion_length": 399.421875,
      "epoch": 0.0035275513927746018,
      "grad_norm": 1.2711021744130893,
      "kl": 0.01104736328125,
      "learning_rate": 9.999692969154423e-07,
      "loss": 0.0004,
      "reward": 1.7680635452270508,
      "reward_std": 0.337743878364563,
      "rewards/accuracy_reward": 0.6586884260177612,
      "rewards/format_reward": 1.0,
      "step": 116,
      "temperature": 1.0
    },
    {
      "all_correct": 0.375,
      "all_wrong": 0.375,
      "completion_length": 433.625,
      "epoch": 0.0035579613185743827,
      "grad_norm": 0.9873440205784932,
      "kl": 0.00787353515625,
      "learning_rate": 9.999687652757116e-07,
      "loss": 0.0003,
      "reward": 1.649999976158142,
      "reward_std": 0.15633204579353333,
      "rewards/accuracy_reward": 0.5625,
      "rewards/format_reward": 1.0,
      "step": 117,
      "temperature": 1.0
    },
    {
      "all_correct": 0.375,
      "all_wrong": 0.25,
      "completion_length": 384.71875,
      "epoch": 0.0035883712443741636,
      "grad_norm": 1.1390425401656346,
      "kl": 0.01513671875,
      "learning_rate": 9.999682290727402e-07,
      "loss": 0.0006,
      "reward": 1.738194465637207,
      "reward_std": 0.1970047652721405,
      "rewards/accuracy_reward": 0.6163194179534912,
      "rewards/format_reward": 1.0,
      "step": 118,
      "temperature": 1.0
    },
    {
      "all_correct": 0.25,
      "all_wrong": 0.0,
      "completion_length": 379.828125,
      "epoch": 0.003618781170173945,
      "grad_norm": 1.5954146720231357,
      "kl": 0.010986328125,
      "learning_rate": 9.999676883065339e-07,
      "loss": 0.0004,
      "reward": 1.8111308813095093,
      "reward_std": 0.20661289989948273,
      "rewards/accuracy_reward": 0.6767559051513672,
      "rewards/format_reward": 1.0,
      "step": 119,
      "temperature": 1.0
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.25,
      "completion_length": 395.625,
      "epoch": 0.003649191095973726,
      "grad_norm": 1.0695744299357113,
      "kl": 0.014892578125,
      "learning_rate": 9.999671429770967e-07,
      "loss": 0.0006,
      "reward": 1.6961580514907837,
      "reward_std": 0.14148113131523132,
      "rewards/accuracy_reward": 0.6180330514907837,
      "rewards/format_reward": 0.96875,
      "step": 120,
      "temperature": 1.0
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.0,
      "completion_length": 414.875,
      "epoch": 0.003679601021773507,
      "grad_norm": 1.945354071536962,
      "kl": 0.0123291015625,
      "learning_rate": 9.999665930844342e-07,
      "loss": 0.0005,
      "reward": 1.8152601718902588,
      "reward_std": 0.23605464398860931,
      "rewards/accuracy_reward": 0.7152600288391113,
      "rewards/format_reward": 0.96875,
      "step": 121,
      "temperature": 1.0
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.0,
      "completion_length": 436.671875,
      "epoch": 0.0037100109475732878,
      "grad_norm": 1.0968894228795836,
      "kl": 0.01275634765625,
      "learning_rate": 9.999660386285512e-07,
      "loss": 0.0005,
      "reward": 1.753679871559143,
      "reward_std": 0.25608769059181213,
      "rewards/accuracy_reward": 0.6568049192428589,
      "rewards/format_reward": 0.984375,
      "step": 122,
      "temperature": 1.0
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.0,
      "completion_length": 437.671875,
      "epoch": 0.003740420873373069,
      "grad_norm": 1.4673063371872073,
      "kl": 0.01275634765625,
      "learning_rate": 9.999654796094527e-07,
      "loss": 0.0005,
      "reward": 1.9900388717651367,
      "reward_std": 0.1983608454465866,
      "rewards/accuracy_reward": 0.8587887287139893,
      "rewards/format_reward": 1.0,
      "step": 123,
      "temperature": 1.0
    },
    {
      "all_correct": 0.625,
      "all_wrong": 0.0,
      "completion_length": 381.640625,
      "epoch": 0.00377083079917285,
      "grad_norm": 1.6416560271510383,
      "kl": 0.012939453125,
      "learning_rate": 9.99964916027144e-07,
      "loss": 0.0005,
      "reward": 1.9000000953674316,
      "reward_std": 0.17067179083824158,
      "rewards/accuracy_reward": 0.765625,
      "rewards/format_reward": 1.0,
      "step": 124,
      "temperature": 1.0
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.0,
      "completion_length": 457.40625,
      "epoch": 0.003801240724972631,
      "grad_norm": 1.0225803997486793,
      "kl": 0.012451171875,
      "learning_rate": 9.999643478816301e-07,
      "loss": 0.0005,
      "reward": 1.763511061668396,
      "reward_std": 0.2219434380531311,
      "rewards/accuracy_reward": 0.7291359901428223,
      "rewards/format_reward": 0.921875,
      "step": 125,
      "temperature": 1.0
    },
    {
      "all_correct": 0.25,
      "all_wrong": 0.125,
      "completion_length": 448.859375,
      "epoch": 0.003831650650772412,
      "grad_norm": 8.352785593061897,
      "kl": 0.01104736328125,
      "learning_rate": 9.999637751729162e-07,
      "loss": 0.0004,
      "reward": 1.6567270755767822,
      "reward_std": 0.14242099225521088,
      "rewards/accuracy_reward": 0.5473519563674927,
      "rewards/format_reward": 1.0,
      "step": 126,
      "temperature": 1.0
    },
    {
      "all_correct": 0.375,
      "all_wrong": 0.0,
      "completion_length": 438.0,
      "epoch": 0.0038620605765721933,
      "grad_norm": 1.0799127843001628,
      "kl": 0.00970458984375,
      "learning_rate": 9.999631979010075e-07,
      "loss": 0.0004,
      "reward": 1.755429744720459,
      "reward_std": 0.33935219049453735,
      "rewards/accuracy_reward": 0.6710547208786011,
      "rewards/format_reward": 0.96875,
      "step": 127,
      "temperature": 1.0
    },
    {
      "all_correct": 0.375,
      "all_wrong": 0.125,
      "completion_length": 441.359375,
      "epoch": 0.003892470502371974,
      "grad_norm": 1.0661924261754825,
      "kl": 0.01324462890625,
      "learning_rate": 9.999626160659094e-07,
      "loss": 0.0005,
      "reward": 1.5311402082443237,
      "reward_std": 0.22228728234767914,
      "rewards/accuracy_reward": 0.49051526188850403,
      "rewards/format_reward": 0.96875,
      "step": 128,
      "temperature": 1.0
    },
    {
      "all_correct": 0.25,
      "all_wrong": 0.25,
      "completion_length": 400.703125,
      "epoch": 0.003922880428171755,
      "grad_norm": 1.3569775529091876,
      "kl": 0.01318359375,
      "learning_rate": 9.999620296676273e-07,
      "loss": 0.0005,
      "reward": 1.6112319231033325,
      "reward_std": 0.16228729486465454,
      "rewards/accuracy_reward": 0.5049818754196167,
      "rewards/format_reward": 1.0,
      "step": 129,
      "temperature": 1.0
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.0,
      "completion_length": 424.71875,
      "epoch": 0.003953290353971536,
      "grad_norm": 1.3836269306579518,
      "kl": 0.01495361328125,
      "learning_rate": 9.99961438706166e-07,
      "loss": 0.0006,
      "reward": 1.8607784509658813,
      "reward_std": 0.11711832135915756,
      "rewards/accuracy_reward": 0.7232784628868103,
      "rewards/format_reward": 1.0,
      "step": 130,
      "temperature": 1.0
    },
    {
      "all_correct": 0.625,
      "all_wrong": 0.125,
      "completion_length": 394.15625,
      "epoch": 0.003983700279771317,
      "grad_norm": 1.4107358207677978,
      "kl": 0.015625,
      "learning_rate": 9.999608431815313e-07,
      "loss": 0.0006,
      "reward": 1.8250000476837158,
      "reward_std": 0.18652412295341492,
      "rewards/accuracy_reward": 0.703125,
      "rewards/format_reward": 1.0,
      "step": 131,
      "temperature": 1.0
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.125,
      "completion_length": 367.390625,
      "epoch": 0.004014110205571099,
      "grad_norm": 1.1726251380447597,
      "kl": 0.0177001953125,
      "learning_rate": 9.99960243093729e-07,
      "loss": 0.0007,
      "reward": 1.8555676937103271,
      "reward_std": 0.1450468897819519,
      "rewards/accuracy_reward": 0.7180677056312561,
      "rewards/format_reward": 1.0,
      "step": 132,
      "temperature": 1.0
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.0,
      "completion_length": 387.953125,
      "epoch": 0.00404452013137088,
      "grad_norm": 1.3575715734166978,
      "kl": 0.015380859375,
      "learning_rate": 9.999596384427637e-07,
      "loss": 0.0006,
      "reward": 1.835242748260498,
      "reward_std": 0.2508818805217743,
      "rewards/accuracy_reward": 0.7227427363395691,
      "rewards/format_reward": 1.0,
      "step": 133,
      "temperature": 1.0
    },
    {
      "all_correct": 0.25,
      "all_wrong": 0.25,
      "completion_length": 377.84375,
      "epoch": 0.004074930057170661,
      "grad_norm": 1.139747620935481,
      "kl": 0.014404296875,
      "learning_rate": 9.999590292286418e-07,
      "loss": 0.0006,
      "reward": 1.6535420417785645,
      "reward_std": 0.2498963177204132,
      "rewards/accuracy_reward": 0.5535419583320618,
      "rewards/format_reward": 1.0,
      "step": 134,
      "temperature": 1.0
    },
    {
      "all_correct": 0.75,
      "all_wrong": 0.0,
      "completion_length": 415.859375,
      "epoch": 0.0041053399829704415,
      "grad_norm": 1.402961959420838,
      "kl": 0.01483154296875,
      "learning_rate": 9.999584154513682e-07,
      "loss": 0.0006,
      "reward": 1.9603800773620605,
      "reward_std": 0.050045616924762726,
      "rewards/accuracy_reward": 0.8135050535202026,
      "rewards/format_reward": 1.0,
      "step": 135,
      "temperature": 1.0
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.25,
      "completion_length": 388.9375,
      "epoch": 0.0041357499087702225,
      "grad_norm": 2.2987765574575882,
      "kl": 0.01361083984375,
      "learning_rate": 9.999577971109489e-07,
      "loss": 0.0005,
      "reward": 1.7411651611328125,
      "reward_std": 0.11923021078109741,
      "rewards/accuracy_reward": 0.6224152445793152,
      "rewards/format_reward": 1.0,
      "step": 136,
      "temperature": 1.0
    },
    {
      "all_correct": 0.25,
      "all_wrong": 0.25,
      "completion_length": 422.671875,
      "epoch": 0.004166159834570003,
      "grad_norm": 1.1635082350786998,
      "kl": 0.01416015625,
      "learning_rate": 9.999571742073893e-07,
      "loss": 0.0006,
      "reward": 1.6062500476837158,
      "reward_std": 0.2297685146331787,
      "rewards/accuracy_reward": 0.53125,
      "rewards/format_reward": 1.0,
      "step": 137,
      "temperature": 1.0
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.0,
      "completion_length": 462.015625,
      "epoch": 0.004196569760369784,
      "grad_norm": 1.639453929022012,
      "kl": 0.01263427734375,
      "learning_rate": 9.999565467406952e-07,
      "loss": 0.0005,
      "reward": 1.8578273057937622,
      "reward_std": 0.09192578494548798,
      "rewards/accuracy_reward": 0.7234523296356201,
      "rewards/format_reward": 1.0,
      "step": 138,
      "temperature": 1.0
    },
    {
      "all_correct": 0.25,
      "all_wrong": 0.0,
      "completion_length": 499.546875,
      "epoch": 0.004226979686169566,
      "grad_norm": 1.7563537775719584,
      "kl": 0.00970458984375,
      "learning_rate": 9.999559147108725e-07,
      "loss": 0.0004,
      "reward": 1.5782231092453003,
      "reward_std": 0.18151439726352692,
      "rewards/accuracy_reward": 0.5344730615615845,
      "rewards/format_reward": 0.9375,
      "step": 139,
      "temperature": 1.0
    },
    {
      "all_correct": 0.375,
      "all_wrong": 0.125,
      "completion_length": 392.390625,
      "epoch": 0.004257389611969347,
      "grad_norm": 1.1406199565944355,
      "kl": 0.01708984375,
      "learning_rate": 9.999552781179266e-07,
      "loss": 0.0007,
      "reward": 1.5926470756530762,
      "reward_std": 0.18690401315689087,
      "rewards/accuracy_reward": 0.49264708161354065,
      "rewards/format_reward": 1.0,
      "step": 140,
      "temperature": 1.0
    },
    {
      "all_correct": 0.625,
      "all_wrong": 0.0,
      "completion_length": 375.65625,
      "epoch": 0.004287799537769128,
      "grad_norm": 1.3605958847837936,
      "kl": 0.0224609375,
      "learning_rate": 9.999546369618637e-07,
      "loss": 0.0009,
      "reward": 1.915426254272461,
      "reward_std": 0.11051365733146667,
      "rewards/accuracy_reward": 0.7591762542724609,
      "rewards/format_reward": 1.0,
      "step": 141,
      "temperature": 1.0
    },
    {
      "all_correct": 0.25,
      "all_wrong": 0.25,
      "completion_length": 472.109375,
      "epoch": 0.004318209463568909,
      "grad_norm": 0.9698083088398921,
      "kl": 0.01263427734375,
      "learning_rate": 9.999539912426892e-07,
      "loss": 0.0005,
      "reward": 1.4461592435836792,
      "reward_std": 0.0903548151254654,
      "rewards/accuracy_reward": 0.3805343210697174,
      "rewards/format_reward": 1.0,
      "step": 142,
      "temperature": 1.0
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.25,
      "completion_length": 389.484375,
      "epoch": 0.00434861938936869,
      "grad_norm": 1.040035997424916,
      "kl": 0.014404296875,
      "learning_rate": 9.999533409604093e-07,
      "loss": 0.0006,
      "reward": 1.631250023841858,
      "reward_std": 0.11976678669452667,
      "rewards/accuracy_reward": 0.546875,
      "rewards/format_reward": 1.0,
      "step": 143,
      "temperature": 1.0
    },
    {
      "all_correct": 0.375,
      "all_wrong": 0.125,
      "completion_length": 450.484375,
      "epoch": 0.004379029315168471,
      "grad_norm": 1.1421509953959035,
      "kl": 0.0157470703125,
      "learning_rate": 9.9995268611503e-07,
      "loss": 0.0006,
      "reward": 1.6714529991149902,
      "reward_std": 0.12337745726108551,
      "rewards/accuracy_reward": 0.5558279156684875,
      "rewards/format_reward": 1.0,
      "step": 144,
      "temperature": 1.0
    },
    {
      "all_correct": 0.625,
      "all_wrong": 0.0,
      "completion_length": 423.390625,
      "epoch": 0.004409439240968252,
      "grad_norm": 1.0759991753626605,
      "kl": 0.0196533203125,
      "learning_rate": 9.999520267065572e-07,
      "loss": 0.0008,
      "reward": 1.9781577587127686,
      "reward_std": 0.1568175107240677,
      "rewards/accuracy_reward": 0.8344077467918396,
      "rewards/format_reward": 1.0,
      "step": 145,
      "temperature": 1.0
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.125,
      "completion_length": 452.640625,
      "epoch": 0.0044398491667680335,
      "grad_norm": 0.8519314536708666,
      "kl": 0.018798828125,
      "learning_rate": 9.999513627349967e-07,
      "loss": 0.0008,
      "reward": 1.6944670677185059,
      "reward_std": 0.12818582355976105,
      "rewards/accuracy_reward": 0.63509202003479,
      "rewards/format_reward": 0.9375,
      "step": 146,
      "temperature": 1.0
    },
    {
      "all_correct": 0.375,
      "all_wrong": 0.25,
      "completion_length": 451.046875,
      "epoch": 0.004470259092567814,
      "grad_norm": 0.90631585986892,
      "kl": 0.01171875,
      "learning_rate": 9.999506942003547e-07,
      "loss": 0.0005,
      "reward": 1.667960524559021,
      "reward_std": 0.19165682792663574,
      "rewards/accuracy_reward": 0.5523355007171631,
      "rewards/format_reward": 1.0,
      "step": 147,
      "temperature": 1.0
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.0,
      "completion_length": 424.140625,
      "epoch": 0.004500669018367595,
      "grad_norm": 1.132809510162569,
      "kl": 0.0189208984375,
      "learning_rate": 9.999500211026376e-07,
      "loss": 0.0008,
      "reward": 1.8894298076629639,
      "reward_std": 0.1842423528432846,
      "rewards/accuracy_reward": 0.7863047122955322,
      "rewards/format_reward": 0.953125,
      "step": 148,
      "temperature": 1.0
    },
    {
      "all_correct": 0.625,
      "all_wrong": 0.0,
      "completion_length": 409.46875,
      "epoch": 0.004531078944167376,
      "grad_norm": 1.0125047844435144,
      "kl": 0.0203857421875,
      "learning_rate": 9.999493434418508e-07,
      "loss": 0.0008,
      "reward": 1.9479596614837646,
      "reward_std": 0.1112360879778862,
      "rewards/accuracy_reward": 0.7948344945907593,
      "rewards/format_reward": 1.0,
      "step": 149,
      "temperature": 1.0
    },
    {
      "all_correct": 0.375,
      "all_wrong": 0.0,
      "completion_length": 492.828125,
      "epoch": 0.004561488869967157,
      "grad_norm": 1.3245815716926614,
      "kl": 0.00982666015625,
      "learning_rate": 9.999486612180015e-07,
      "loss": 0.0004,
      "reward": 1.860871434211731,
      "reward_std": 0.26773563027381897,
      "rewards/accuracy_reward": 0.7546213865280151,
      "rewards/format_reward": 0.984375,
      "step": 150,
      "temperature": 1.0
    },
    {
      "all_correct": 0.125,
      "all_wrong": 0.25,
      "completion_length": 427.171875,
      "epoch": 0.004591898795766938,
      "grad_norm": 1.2321894970714469,
      "kl": 0.01611328125,
      "learning_rate": 9.99947974431095e-07,
      "loss": 0.0006,
      "reward": 1.4892878532409668,
      "reward_std": 0.16884982585906982,
      "rewards/accuracy_reward": 0.4111628234386444,
      "rewards/format_reward": 1.0,
      "step": 151,
      "temperature": 1.0
    },
    {
      "all_correct": 0.625,
      "all_wrong": 0.0,
      "completion_length": 428.9375,
      "epoch": 0.004622308721566719,
      "grad_norm": 1.1213278922266443,
      "kl": 0.01519775390625,
      "learning_rate": 9.999472830811382e-07,
      "loss": 0.0006,
      "reward": 1.8488322496414185,
      "reward_std": 0.09654758870601654,
      "rewards/accuracy_reward": 0.7113322615623474,
      "rewards/format_reward": 1.0,
      "step": 152,
      "temperature": 1.0
    },
    {
      "all_correct": 0.75,
      "all_wrong": 0.125,
      "completion_length": 391.171875,
      "epoch": 0.004652718647366501,
      "grad_norm": 0.8304602358235011,
      "kl": 0.0218505859375,
      "learning_rate": 9.99946587168137e-07,
      "loss": 0.0009,
      "reward": 1.941306710243225,
      "reward_std": 0.029227139428257942,
      "rewards/accuracy_reward": 0.775681734085083,
      "rewards/format_reward": 1.0,
      "step": 153,
      "temperature": 1.0
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.125,
      "completion_length": 418.453125,
      "epoch": 0.004683128573166282,
      "grad_norm": 1.2554274834074644,
      "kl": 0.01446533203125,
      "learning_rate": 9.99945886692098e-07,
      "loss": 0.0006,
      "reward": 1.9105966091156006,
      "reward_std": 0.14083711802959442,
      "rewards/accuracy_reward": 0.7605965733528137,
      "rewards/format_reward": 1.0,
      "step": 154,
      "temperature": 1.0
    },
    {
      "all_correct": 0.25,
      "all_wrong": 0.0,
      "completion_length": 417.09375,
      "epoch": 0.004713538498966063,
      "grad_norm": 1.405928031553138,
      "kl": 0.0135498046875,
      "learning_rate": 9.999451816530275e-07,
      "loss": 0.0005,
      "reward": 1.6618525981903076,
      "reward_std": 0.21694952249526978,
      "rewards/accuracy_reward": 0.5556026101112366,
      "rewards/format_reward": 0.984375,
      "step": 155,
      "temperature": 1.0
    },
    {
      "all_correct": 0.625,
      "all_wrong": 0.125,
      "completion_length": 373.140625,
      "epoch": 0.004743948424765844,
      "grad_norm": 1.0697919086566865,
      "kl": 0.0196533203125,
      "learning_rate": 9.99944472050932e-07,
      "loss": 0.0008,
      "reward": 1.821874976158142,
      "reward_std": 0.147711843252182,
      "rewards/accuracy_reward": 0.6875,
      "rewards/format_reward": 1.0,
      "step": 156,
      "temperature": 1.0
    },
    {
      "all_correct": 0.375,
      "all_wrong": 0.125,
      "completion_length": 382.296875,
      "epoch": 0.0047743583505656245,
      "grad_norm": 1.3137637121377133,
      "kl": 0.0184326171875,
      "learning_rate": 9.99943757885818e-07,
      "loss": 0.0007,
      "reward": 1.8315324783325195,
      "reward_std": 0.17180569469928741,
      "rewards/accuracy_reward": 0.6971573829650879,
      "rewards/format_reward": 1.0,
      "step": 157,
      "temperature": 1.0
    },
    {
      "all_correct": 0.25,
      "all_wrong": 0.125,
      "completion_length": 450.078125,
      "epoch": 0.0048047682763654054,
      "grad_norm": 1.0325763822116654,
      "kl": 0.014404296875,
      "learning_rate": 9.999430391576918e-07,
      "loss": 0.0006,
      "reward": 1.594119668006897,
      "reward_std": 0.18696415424346924,
      "rewards/accuracy_reward": 0.515994668006897,
      "rewards/format_reward": 1.0,
      "step": 158,
      "temperature": 1.0
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.25,
      "completion_length": 376.640625,
      "epoch": 0.004835178202165186,
      "grad_norm": 0.996193873185499,
      "kl": 0.019287109375,
      "learning_rate": 9.9994231586656e-07,
      "loss": 0.0008,
      "reward": 1.7409956455230713,
      "reward_std": 0.12510690093040466,
      "rewards/accuracy_reward": 0.6159957647323608,
      "rewards/format_reward": 1.0,
      "step": 159,
      "temperature": 1.0
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.0,
      "completion_length": 394.015625,
      "epoch": 0.004865588127964968,
      "grad_norm": 1.1598439380998047,
      "kl": 0.019775390625,
      "learning_rate": 9.999415880124296e-07,
      "loss": 0.0008,
      "reward": 1.9418286085128784,
      "reward_std": 0.2405511885881424,
      "rewards/accuracy_reward": 0.7762036323547363,
      "rewards/format_reward": 1.0,
      "step": 160,
      "temperature": 1.0
    },
    {
      "all_correct": 0.625,
      "all_wrong": 0.0,
      "completion_length": 397.25,
      "epoch": 0.004895998053764749,
      "grad_norm": 1.2265609150598025,
      "kl": 0.017822265625,
      "learning_rate": 9.999408555953066e-07,
      "loss": 0.0007,
      "reward": 1.9905532598495483,
      "reward_std": 0.05020171031355858,
      "rewards/accuracy_reward": 0.8124282360076904,
      "rewards/format_reward": 1.0,
      "step": 161,
      "temperature": 1.0
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.25,
      "completion_length": 405.765625,
      "epoch": 0.00492640797956453,
      "grad_norm": 0.5407968570662303,
      "kl": 0.014892578125,
      "learning_rate": 9.999401186151983e-07,
      "loss": 0.0006,
      "reward": 1.7437500953674316,
      "reward_std": 0.09669842571020126,
      "rewards/accuracy_reward": 0.625,
      "rewards/format_reward": 1.0,
      "step": 162,
      "temperature": 1.0
    },
    {
      "all_correct": 0.25,
      "all_wrong": 0.125,
      "completion_length": 412.28125,
      "epoch": 0.004956817905364311,
      "grad_norm": 0.9864724322545501,
      "kl": 0.01495361328125,
      "learning_rate": 9.99939377072111e-07,
      "loss": 0.0006,
      "reward": 1.6354146003723145,
      "reward_std": 0.28268858790397644,
      "rewards/accuracy_reward": 0.5416646003723145,
      "rewards/format_reward": 0.984375,
      "step": 163,
      "temperature": 1.0
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.0,
      "completion_length": 394.84375,
      "epoch": 0.004987227831164092,
      "grad_norm": 1.0647402377184647,
      "kl": 0.0205078125,
      "learning_rate": 9.999386309660518e-07,
      "loss": 0.0008,
      "reward": 1.8802317380905151,
      "reward_std": 0.18236258625984192,
      "rewards/accuracy_reward": 0.7396067976951599,
      "rewards/format_reward": 0.984375,
      "step": 164,
      "temperature": 1.0
    },
    {
      "all_correct": 0.25,
      "all_wrong": 0.0,
      "completion_length": 403.796875,
      "epoch": 0.005017637756963873,
      "grad_norm": 1.3360443785792222,
      "kl": 0.017822265625,
      "learning_rate": 9.999378802970273e-07,
      "loss": 0.0007,
      "reward": 1.7311592102050781,
      "reward_std": 0.37493041157722473,
      "rewards/accuracy_reward": 0.6342841386795044,
      "rewards/format_reward": 0.984375,
      "step": 165,
      "temperature": 1.0
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.125,
      "completion_length": 414.21875,
      "epoch": 0.005048047682763654,
      "grad_norm": 1.227267912895048,
      "kl": 0.015625,
      "learning_rate": 9.999371250650443e-07,
      "loss": 0.0006,
      "reward": 1.7867743968963623,
      "reward_std": 0.10373984277248383,
      "rewards/accuracy_reward": 0.6555243730545044,
      "rewards/format_reward": 1.0,
      "step": 166,
      "temperature": 1.0
    },
    {
      "all_correct": 0.625,
      "all_wrong": 0.125,
      "completion_length": 381.265625,
      "epoch": 0.0050784576085634355,
      "grad_norm": 5.573274860294901,
      "kl": 0.0186767578125,
      "learning_rate": 9.999363652701097e-07,
      "loss": 0.0007,
      "reward": 1.8781249523162842,
      "reward_std": 0.189039409160614,
      "rewards/accuracy_reward": 0.75,
      "rewards/format_reward": 1.0,
      "step": 167,
      "temperature": 1.0
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.0,
      "completion_length": 381.1875,
      "epoch": 0.0051088675343632164,
      "grad_norm": 1.5245968420451688,
      "kl": 0.015869140625,
      "learning_rate": 9.999356009122307e-07,
      "loss": 0.0006,
      "reward": 1.8024578094482422,
      "reward_std": 0.19867169857025146,
      "rewards/accuracy_reward": 0.6774578094482422,
      "rewards/format_reward": 1.0,
      "step": 168,
      "temperature": 1.0
    },
    {
      "all_correct": 0.0,
      "all_wrong": 0.125,
      "completion_length": 438.484375,
      "epoch": 0.005139277460162997,
      "grad_norm": 1.5126479755429134,
      "kl": 0.0174560546875,
      "learning_rate": 9.999348319914141e-07,
      "loss": 0.0007,
      "reward": 1.550065279006958,
      "reward_std": 0.353948712348938,
      "rewards/accuracy_reward": 0.4906902611255646,
      "rewards/format_reward": 0.984375,
      "step": 169,
      "temperature": 1.0
    },
    {
      "all_correct": 0.125,
      "all_wrong": 0.125,
      "completion_length": 449.078125,
      "epoch": 0.005169687385962778,
      "grad_norm": 1.621401769931139,
      "kl": 0.01019287109375,
      "learning_rate": 9.999340585076667e-07,
      "loss": 0.0004,
      "reward": 1.446197271347046,
      "reward_std": 0.22781604528427124,
      "rewards/accuracy_reward": 0.3868221938610077,
      "rewards/format_reward": 1.0,
      "step": 170,
      "temperature": 1.0
    },
    {
      "all_correct": 0.625,
      "all_wrong": 0.0,
      "completion_length": 400.5,
      "epoch": 0.005200097311762559,
      "grad_norm": 1.008489149973811,
      "kl": 0.0159912109375,
      "learning_rate": 9.99933280460996e-07,
      "loss": 0.0006,
      "reward": 1.9821999073028564,
      "reward_std": 0.17775297164916992,
      "rewards/accuracy_reward": 0.8384499549865723,
      "rewards/format_reward": 0.96875,
      "step": 171,
      "temperature": 1.0
    },
    {
      "all_correct": 0.75,
      "all_wrong": 0.0,
      "completion_length": 398.265625,
      "epoch": 0.00523050723756234,
      "grad_norm": 1.2521057745061377,
      "kl": 0.01446533203125,
      "learning_rate": 9.999324978514087e-07,
      "loss": 0.0006,
      "reward": 2.0507450103759766,
      "reward_std": 0.08263193815946579,
      "rewards/accuracy_reward": 0.8913698196411133,
      "rewards/format_reward": 1.0,
      "step": 172,
      "temperature": 1.0
    },
    {
      "all_correct": 0.625,
      "all_wrong": 0.125,
      "completion_length": 362.390625,
      "epoch": 0.005260917163362121,
      "grad_norm": 0.9522233747661588,
      "kl": 0.0205078125,
      "learning_rate": 9.999317106789121e-07,
      "loss": 0.0008,
      "reward": 1.8781249523162842,
      "reward_std": 0.10790814459323883,
      "rewards/accuracy_reward": 0.75,
      "rewards/format_reward": 1.0,
      "step": 173,
      "temperature": 1.0
    },
    {
      "all_correct": 0.0,
      "all_wrong": 0.125,
      "completion_length": 463.890625,
      "epoch": 0.005291327089161903,
      "grad_norm": 1.562755596088275,
      "kl": 0.017333984375,
      "learning_rate": 9.999309189435137e-07,
      "loss": 0.0007,
      "reward": 1.5901439189910889,
      "reward_std": 0.32178163528442383,
      "rewards/accuracy_reward": 0.5495189428329468,
      "rewards/format_reward": 0.953125,
      "step": 174,
      "temperature": 1.0
    },
    {
      "all_correct": 0.375,
      "all_wrong": 0.0,
      "completion_length": 430.8125,
      "epoch": 0.005321737014961684,
      "grad_norm": 1.3739334321952938,
      "kl": 0.0133056640625,
      "learning_rate": 9.9993012264522e-07,
      "loss": 0.0005,
      "reward": 1.6702098846435547,
      "reward_std": 0.2349352240562439,
      "rewards/accuracy_reward": 0.5733348727226257,
      "rewards/format_reward": 0.984375,
      "step": 175,
      "temperature": 1.0
    },
    {
      "all_correct": 0.375,
      "all_wrong": 0.125,
      "completion_length": 416.921875,
      "epoch": 0.005352146940761465,
      "grad_norm": 1.1652981075424256,
      "kl": 0.0115966796875,
      "learning_rate": 9.99929321784039e-07,
      "loss": 0.0005,
      "reward": 1.8125,
      "reward_std": 0.29565125703811646,
      "rewards/accuracy_reward": 0.6968750357627869,
      "rewards/format_reward": 1.0,
      "step": 176,
      "temperature": 1.0
    },
    {
      "all_correct": 0.0,
      "all_wrong": 0.375,
      "completion_length": 404.59375,
      "epoch": 0.005382556866561246,
      "grad_norm": 1.3406466440273301,
      "kl": 0.01239013671875,
      "learning_rate": 9.999285163599776e-07,
      "loss": 0.0005,
      "reward": 1.3471534252166748,
      "reward_std": 0.15532881021499634,
      "rewards/accuracy_reward": 0.2877783477306366,
      "rewards/format_reward": 1.0,
      "step": 177,
      "temperature": 1.0
    },
    {
      "all_correct": 0.375,
      "all_wrong": 0.25,
      "completion_length": 430.625,
      "epoch": 0.005412966792361027,
      "grad_norm": 1.3887344535264228,
      "kl": 0.01336669921875,
      "learning_rate": 9.999277063730433e-07,
      "loss": 0.0005,
      "reward": 1.6237156391143799,
      "reward_std": 0.21755698323249817,
      "rewards/accuracy_reward": 0.570590615272522,
      "rewards/format_reward": 0.953125,
      "step": 178,
      "temperature": 1.0
    },
    {
      "all_correct": 0.375,
      "all_wrong": 0.0,
      "completion_length": 409.625,
      "epoch": 0.0054433767181608075,
      "grad_norm": 2.0743859063561723,
      "kl": 0.01324462890625,
      "learning_rate": 9.999268918232434e-07,
      "loss": 0.0005,
      "reward": 1.8434568643569946,
      "reward_std": 0.10064193606376648,
      "rewards/accuracy_reward": 0.6872068643569946,
      "rewards/format_reward": 1.0,
      "step": 179,
      "temperature": 1.0
    },
    {
      "all_correct": 0.625,
      "all_wrong": 0.25,
      "completion_length": 379.015625,
      "epoch": 0.005473786643960588,
      "grad_norm": 0.7532915053197624,
      "kl": 0.01214599609375,
      "learning_rate": 9.999260727105853e-07,
      "loss": 0.0005,
      "reward": 1.8430216312408447,
      "reward_std": 0.05529624968767166,
      "rewards/accuracy_reward": 0.7055215239524841,
      "rewards/format_reward": 1.0,
      "step": 180,
      "temperature": 1.0
    },
    {
      "all_correct": 0.375,
      "all_wrong": 0.125,
      "completion_length": 356.453125,
      "epoch": 0.005504196569760369,
      "grad_norm": 1.7075214346164662,
      "kl": 0.0218505859375,
      "learning_rate": 9.999252490350766e-07,
      "loss": 0.0009,
      "reward": 1.6724622249603271,
      "reward_std": 0.25920727849006653,
      "rewards/accuracy_reward": 0.5787121057510376,
      "rewards/format_reward": 1.0,
      "step": 181,
      "temperature": 1.0
    },
    {
      "all_correct": 0.625,
      "all_wrong": 0.0,
      "completion_length": 358.28125,
      "epoch": 0.005534606495560151,
      "grad_norm": 2.042184463125017,
      "kl": 0.0133056640625,
      "learning_rate": 9.99924420796725e-07,
      "loss": 0.0005,
      "reward": 1.8975837230682373,
      "reward_std": 0.09810338169336319,
      "rewards/accuracy_reward": 0.7507086992263794,
      "rewards/format_reward": 1.0,
      "step": 182,
      "temperature": 1.0
    },
    {
      "all_correct": 0.0,
      "all_wrong": 0.25,
      "completion_length": 423.890625,
      "epoch": 0.005565016421359932,
      "grad_norm": 1.3303510784474357,
      "kl": 0.013916015625,
      "learning_rate": 9.999235879955376e-07,
      "loss": 0.0006,
      "reward": 1.4585750102996826,
      "reward_std": 0.36167454719543457,
      "rewards/accuracy_reward": 0.3898250460624695,
      "rewards/format_reward": 1.0,
      "step": 183,
      "temperature": 1.0
    },
    {
      "all_correct": 0.375,
      "all_wrong": 0.0,
      "completion_length": 400.59375,
      "epoch": 0.005595426347159713,
      "grad_norm": 1.557466390721163,
      "kl": 0.01129150390625,
      "learning_rate": 9.999227506315222e-07,
      "loss": 0.0005,
      "reward": 1.8849766254425049,
      "reward_std": 0.25979411602020264,
      "rewards/accuracy_reward": 0.7599766254425049,
      "rewards/format_reward": 1.0,
      "step": 184,
      "temperature": 1.0
    },
    {
      "all_correct": 0.375,
      "all_wrong": 0.25,
      "completion_length": 430.90625,
      "epoch": 0.005625836272959494,
      "grad_norm": 1.2477656111925082,
      "kl": 0.01007080078125,
      "learning_rate": 9.999219087046865e-07,
      "loss": 0.0004,
      "reward": 1.7110908031463623,
      "reward_std": 0.164617657661438,
      "rewards/accuracy_reward": 0.582965612411499,
      "rewards/format_reward": 1.0,
      "step": 185,
      "temperature": 1.0
    },
    {
      "all_correct": 0.25,
      "all_wrong": 0.125,
      "completion_length": 382.5625,
      "epoch": 0.005656246198759275,
      "grad_norm": 1.3597665407127855,
      "kl": 0.0146484375,
      "learning_rate": 9.999210622150383e-07,
      "loss": 0.0006,
      "reward": 1.634385347366333,
      "reward_std": 0.28478699922561646,
      "rewards/accuracy_reward": 0.540635347366333,
      "rewards/format_reward": 1.0,
      "step": 186,
      "temperature": 1.0
    },
    {
      "all_correct": 0.25,
      "all_wrong": 0.125,
      "completion_length": 437.296875,
      "epoch": 0.005686656124559056,
      "grad_norm": 8.877258215680504,
      "kl": 0.0115966796875,
      "learning_rate": 9.999202111625851e-07,
      "loss": 0.0005,
      "reward": 1.5340607166290283,
      "reward_std": 0.2130703628063202,
      "rewards/accuracy_reward": 0.4715607166290283,
      "rewards/format_reward": 0.9375,
      "step": 187,
      "temperature": 1.0
    },
    {
      "all_correct": 0.625,
      "all_wrong": 0.125,
      "completion_length": 369.34375,
      "epoch": 0.005717066050358837,
      "grad_norm": 1.0737367954086672,
      "kl": 0.013916015625,
      "learning_rate": 9.999193555473349e-07,
      "loss": 0.0006,
      "reward": 1.984375,
      "reward_std": 0.13876724243164062,
      "rewards/accuracy_reward": 0.828125,
      "rewards/format_reward": 1.0,
      "step": 188,
      "temperature": 1.0
    },
    {
      "all_correct": 0.125,
      "all_wrong": 0.25,
      "completion_length": 406.46875,
      "epoch": 0.0057474759761586185,
      "grad_norm": 1.1086347245193864,
      "kl": 0.01226806640625,
      "learning_rate": 9.999184953692952e-07,
      "loss": 0.0005,
      "reward": 1.414463758468628,
      "reward_std": 0.28794142603874207,
      "rewards/accuracy_reward": 0.33633872866630554,
      "rewards/format_reward": 1.0,
      "step": 189,
      "temperature": 1.0
    },
    {
      "all_correct": 0.25,
      "all_wrong": 0.375,
      "completion_length": 360.484375,
      "epoch": 0.005777885901958399,
      "grad_norm": 1.101609083427379,
      "kl": 0.0162353515625,
      "learning_rate": 9.99917630628474e-07,
      "loss": 0.0007,
      "reward": 1.4500000476837158,
      "reward_std": 0.20526908338069916,
      "rewards/accuracy_reward": 0.390625,
      "rewards/format_reward": 1.0,
      "step": 190,
      "temperature": 1.0
    },
    {
      "all_correct": 0.25,
      "all_wrong": 0.125,
      "completion_length": 411.03125,
      "epoch": 0.00580829582775818,
      "grad_norm": 1.7051722738234822,
      "kl": 0.013916015625,
      "learning_rate": 9.999167613248794e-07,
      "loss": 0.0006,
      "reward": 1.6270763874053955,
      "reward_std": 0.2157573401927948,
      "rewards/accuracy_reward": 0.5395764112472534,
      "rewards/format_reward": 1.0,
      "step": 191,
      "temperature": 1.0
    },
    {
      "all_correct": 0.25,
      "all_wrong": 0.125,
      "completion_length": 386.984375,
      "epoch": 0.005838705753557961,
      "grad_norm": 1.302695433524478,
      "kl": 0.01422119140625,
      "learning_rate": 9.99915887458519e-07,
      "loss": 0.0006,
      "reward": 1.5817657709121704,
      "reward_std": 0.28352606296539307,
      "rewards/accuracy_reward": 0.5036407709121704,
      "rewards/format_reward": 1.0,
      "step": 192,
      "temperature": 1.0
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.0,
      "completion_length": 386.28125,
      "epoch": 0.005869115679357742,
      "grad_norm": 1.7590269488643204,
      "kl": 0.0137939453125,
      "learning_rate": 9.999150090294008e-07,
      "loss": 0.0006,
      "reward": 1.7564142942428589,
      "reward_std": 0.1505160629749298,
      "rewards/accuracy_reward": 0.6282892227172852,
      "rewards/format_reward": 0.984375,
      "step": 193,
      "temperature": 1.0
    },
    {
      "all_correct": 0.375,
      "all_wrong": 0.0,
      "completion_length": 363.796875,
      "epoch": 0.005899525605157523,
      "grad_norm": 1.920205592023229,
      "kl": 0.018310546875,
      "learning_rate": 9.99914126037533e-07,
      "loss": 0.0007,
      "reward": 1.7245876789093018,
      "reward_std": 0.2171836495399475,
      "rewards/accuracy_reward": 0.5933376550674438,
      "rewards/format_reward": 1.0,
      "step": 194,
      "temperature": 1.0
    },
    {
      "all_correct": 0.125,
      "all_wrong": 0.0,
      "completion_length": 402.03125,
      "epoch": 0.005929935530957304,
      "grad_norm": 2.708794554667455,
      "kl": 0.0142822265625,
      "learning_rate": 9.999132384829237e-07,
      "loss": 0.0006,
      "reward": 1.6385501623153687,
      "reward_std": 0.34167760610580444,
      "rewards/accuracy_reward": 0.5385500192642212,
      "rewards/format_reward": 1.0,
      "step": 195,
      "temperature": 1.0
    },
    {
      "all_correct": 0.625,
      "all_wrong": 0.125,
      "completion_length": 387.15625,
      "epoch": 0.005960345456757086,
      "grad_norm": 0.7565696081840521,
      "kl": 0.0157470703125,
      "learning_rate": 9.99912346365581e-07,
      "loss": 0.0006,
      "reward": 1.8814079761505127,
      "reward_std": 0.1055237203836441,
      "rewards/accuracy_reward": 0.7220330238342285,
      "rewards/format_reward": 1.0,
      "step": 196,
      "temperature": 1.0
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.25,
      "completion_length": 415.578125,
      "epoch": 0.005990755382556867,
      "grad_norm": 1.3716921990656596,
      "kl": 0.0145263671875,
      "learning_rate": 9.999114496855125e-07,
      "loss": 0.0006,
      "reward": 1.6889476776123047,
      "reward_std": 0.06109042093157768,
      "rewards/accuracy_reward": 0.5764476656913757,
      "rewards/format_reward": 1.0,
      "step": 197,
      "temperature": 1.0
    },
    {
      "all_correct": 0.375,
      "all_wrong": 0.125,
      "completion_length": 408.953125,
      "epoch": 0.006021165308356648,
      "grad_norm": 1.2696577001009746,
      "kl": 0.0157470703125,
      "learning_rate": 9.999105484427273e-07,
      "loss": 0.0006,
      "reward": 1.703125,
      "reward_std": 0.3058618903160095,
      "rewards/accuracy_reward": 0.625,
      "rewards/format_reward": 0.984375,
      "step": 198,
      "temperature": 1.0
    },
    {
      "all_correct": 0.75,
      "all_wrong": 0.0,
      "completion_length": 378.25,
      "epoch": 0.006051575234156429,
      "grad_norm": 1.2521705961099014,
      "kl": 0.0169677734375,
      "learning_rate": 9.999096426372328e-07,
      "loss": 0.0007,
      "reward": 1.9564234018325806,
      "reward_std": 0.029600605368614197,
      "rewards/accuracy_reward": 0.7939233183860779,
      "rewards/format_reward": 1.0,
      "step": 199,
      "temperature": 1.0
    },
    {
      "all_correct": 0.375,
      "all_wrong": 0.0,
      "completion_length": 385.28125,
      "epoch": 0.0060819851599562096,
      "grad_norm": 1.4527944675901368,
      "kl": 0.0147705078125,
      "learning_rate": 9.999087322690379e-07,
      "loss": 0.0006,
      "reward": 1.8885259628295898,
      "reward_std": 0.12971588969230652,
      "rewards/accuracy_reward": 0.7322760224342346,
      "rewards/format_reward": 1.0,
      "step": 200,
      "temperature": 1.0
    },
    {
      "all_correct": 0.25,
      "all_wrong": 0.0,
      "completion_length": 438.09375,
      "epoch": 0.0061123950857559905,
      "grad_norm": 1.3893010615237968,
      "kl": 0.0123291015625,
      "learning_rate": 9.999078173381504e-07,
      "loss": 0.0005,
      "reward": 1.719128131866455,
      "reward_std": 0.270042359828949,
      "rewards/accuracy_reward": 0.6066280603408813,
      "rewards/format_reward": 1.0,
      "step": 201,
      "temperature": 1.0
    },
    {
      "all_correct": 0.625,
      "all_wrong": 0.0,
      "completion_length": 374.125,
      "epoch": 0.006142805011555771,
      "grad_norm": 1.2857928784234862,
      "kl": 0.0186767578125,
      "learning_rate": 9.99906897844579e-07,
      "loss": 0.0007,
      "reward": 1.8464598655700684,
      "reward_std": 0.22821247577667236,
      "rewards/accuracy_reward": 0.7464597821235657,
      "rewards/format_reward": 0.96875,
      "step": 202,
      "temperature": 1.0
    },
    {
      "all_correct": 0.125,
      "all_wrong": 0.0,
      "completion_length": 484.828125,
      "epoch": 0.006173214937355553,
      "grad_norm": 1.161916327769571,
      "kl": 0.0106201171875,
      "learning_rate": 9.99905973788332e-07,
      "loss": 0.0004,
      "reward": 1.7661173343658447,
      "reward_std": 0.3755035996437073,
      "rewards/accuracy_reward": 0.6723674535751343,
      "rewards/format_reward": 0.984375,
      "step": 203,
      "temperature": 1.0
    },
    {
      "all_correct": 0.875,
      "all_wrong": 0.0,
      "completion_length": 383.40625,
      "epoch": 0.006203624863155334,
      "grad_norm": 0.8321996024052432,
      "kl": 0.018310546875,
      "learning_rate": 9.999050451694177e-07,
      "loss": 0.0007,
      "reward": 2.125,
      "reward_std": 0.09940993785858154,
      "rewards/accuracy_reward": 0.953125,
      "rewards/format_reward": 1.0,
      "step": 204,
      "temperature": 1.0
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.125,
      "completion_length": 401.453125,
      "epoch": 0.006234034788955115,
      "grad_norm": 0.9804543956579949,
      "kl": 0.018310546875,
      "learning_rate": 9.999041119878447e-07,
      "loss": 0.0007,
      "reward": 1.7361085414886475,
      "reward_std": 0.17073804140090942,
      "rewards/accuracy_reward": 0.6204833984375,
      "rewards/format_reward": 1.0,
      "step": 205,
      "temperature": 1.0
    },
    {
      "all_correct": 0.75,
      "all_wrong": 0.0,
      "completion_length": 391.109375,
      "epoch": 0.006264444714754896,
      "grad_norm": 1.2028693885976411,
      "kl": 0.0213623046875,
      "learning_rate": 9.999031742436215e-07,
      "loss": 0.0009,
      "reward": 1.984070062637329,
      "reward_std": 0.11129516363143921,
      "rewards/accuracy_reward": 0.837195098400116,
      "rewards/format_reward": 1.0,
      "step": 206,
      "temperature": 1.0
    },
    {
      "all_correct": 0.125,
      "all_wrong": 0.0,
      "completion_length": 437.390625,
      "epoch": 0.006294854640554677,
      "grad_norm": 1.5376020965816457,
      "kl": 0.0137939453125,
      "learning_rate": 9.999022319367567e-07,
      "loss": 0.0006,
      "reward": 1.6291178464889526,
      "reward_std": 0.2104966640472412,
      "rewards/accuracy_reward": 0.5009927749633789,
      "rewards/format_reward": 0.984375,
      "step": 207,
      "temperature": 1.0
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.125,
      "completion_length": 410.703125,
      "epoch": 0.006325264566354458,
      "grad_norm": 2.099640306710403,
      "kl": 0.017578125,
      "learning_rate": 9.999012850672587e-07,
      "loss": 0.0007,
      "reward": 1.7741410732269287,
      "reward_std": 0.16794037818908691,
      "rewards/accuracy_reward": 0.6491410136222839,
      "rewards/format_reward": 1.0,
      "step": 208,
      "temperature": 1.0
    },
    {
      "all_correct": 0.375,
      "all_wrong": 0.125,
      "completion_length": 448.515625,
      "epoch": 0.006355674492154239,
      "grad_norm": 1.3803918216890592,
      "kl": 0.017578125,
      "learning_rate": 9.999003336351364e-07,
      "loss": 0.0007,
      "reward": 1.7693995237350464,
      "reward_std": 0.1516171246767044,
      "rewards/accuracy_reward": 0.6381495594978333,
      "rewards/format_reward": 1.0,
      "step": 209,
      "temperature": 1.0
    },
    {
      "all_correct": 0.375,
      "all_wrong": 0.125,
      "completion_length": 432.078125,
      "epoch": 0.0063860844179540206,
      "grad_norm": 2.0535011409234167,
      "kl": 0.020263671875,
      "learning_rate": 9.998993776403983e-07,
      "loss": 0.0008,
      "reward": 1.74228835105896,
      "reward_std": 0.21149301528930664,
      "rewards/accuracy_reward": 0.6422882676124573,
      "rewards/format_reward": 1.0,
      "step": 210,
      "temperature": 1.0
    },
    {
      "all_correct": 0.375,
      "all_wrong": 0.25,
      "completion_length": 395.046875,
      "epoch": 0.0064164943437538015,
      "grad_norm": 1.7156220404120721,
      "kl": 0.0220947265625,
      "learning_rate": 9.998984170830533e-07,
      "loss": 0.0009,
      "reward": 1.7945313453674316,
      "reward_std": 0.146955668926239,
      "rewards/accuracy_reward": 0.66015625,
      "rewards/format_reward": 1.0,
      "step": 211,
      "temperature": 1.0
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.25,
      "completion_length": 396.703125,
      "epoch": 0.006446904269553582,
      "grad_norm": 1.0191415850799448,
      "kl": 0.020263671875,
      "learning_rate": 9.998974519631103e-07,
      "loss": 0.0008,
      "reward": 1.734459400177002,
      "reward_std": 0.10649251192808151,
      "rewards/accuracy_reward": 0.6063344478607178,
      "rewards/format_reward": 1.0,
      "step": 212,
      "temperature": 1.0
    },
    {
      "all_correct": 0.625,
      "all_wrong": 0.125,
      "completion_length": 426.109375,
      "epoch": 0.006477314195353363,
      "grad_norm": 1.1212553986619302,
      "kl": 0.0216064453125,
      "learning_rate": 9.998964822805774e-07,
      "loss": 0.0009,
      "reward": 1.6878325939178467,
      "reward_std": 0.1365116685628891,
      "rewards/accuracy_reward": 0.6440826058387756,
      "rewards/format_reward": 0.9375,
      "step": 213,
      "temperature": 1.0
    },
    {
      "all_correct": 0.375,
      "all_wrong": 0.125,
      "completion_length": 422.859375,
      "epoch": 0.006507724121153144,
      "grad_norm": 6.258472389668914,
      "kl": 0.021728515625,
      "learning_rate": 9.998955080354644e-07,
      "loss": 0.0009,
      "reward": 1.714188575744629,
      "reward_std": 0.14747735857963562,
      "rewards/accuracy_reward": 0.5891884565353394,
      "rewards/format_reward": 1.0,
      "step": 214,
      "temperature": 1.0
    },
    {
      "all_correct": 0.375,
      "all_wrong": 0.0,
      "completion_length": 438.265625,
      "epoch": 0.006538134046952925,
      "grad_norm": 1.7274532008253825,
      "kl": 0.017822265625,
      "learning_rate": 9.998945292277793e-07,
      "loss": 0.0007,
      "reward": 1.6116645336151123,
      "reward_std": 0.1820090264081955,
      "rewards/accuracy_reward": 0.5491644740104675,
      "rewards/format_reward": 0.921875,
      "step": 215,
      "temperature": 1.0
    },
    {
      "all_correct": 0.25,
      "all_wrong": 0.0,
      "completion_length": 389.0,
      "epoch": 0.006568543972752706,
      "grad_norm": 1.35340326061819,
      "kl": 0.020751953125,
      "learning_rate": 9.998935458575316e-07,
      "loss": 0.0008,
      "reward": 1.7151023149490356,
      "reward_std": 0.26303189992904663,
      "rewards/accuracy_reward": 0.5651022791862488,
      "rewards/format_reward": 1.0,
      "step": 216,
      "temperature": 1.0
    },
    {
      "all_correct": 0.75,
      "all_wrong": 0.125,
      "completion_length": 382.65625,
      "epoch": 0.006598953898552488,
      "grad_norm": 0.9891291843789567,
      "kl": 0.02490234375,
      "learning_rate": 9.998925579247302e-07,
      "loss": 0.001,
      "reward": 2.028125047683716,
      "reward_std": 0.06187184900045395,
      "rewards/accuracy_reward": 0.859375,
      "rewards/format_reward": 1.0,
      "step": 217,
      "temperature": 1.0
    },
    {
      "all_correct": 0.625,
      "all_wrong": 0.125,
      "completion_length": 415.53125,
      "epoch": 0.006629363824352269,
      "grad_norm": 0.6999098048725213,
      "kl": 0.017578125,
      "learning_rate": 9.99891565429384e-07,
      "loss": 0.0007,
      "reward": 1.8948068618774414,
      "reward_std": 0.0846766009926796,
      "rewards/accuracy_reward": 0.751056969165802,
      "rewards/format_reward": 1.0,
      "step": 218,
      "temperature": 1.0
    },
    {
      "all_correct": 0.25,
      "all_wrong": 0.125,
      "completion_length": 421.96875,
      "epoch": 0.00665977375015205,
      "grad_norm": 4.3048021553854285,
      "kl": 0.0167236328125,
      "learning_rate": 9.998905683715021e-07,
      "loss": 0.0007,
      "reward": 1.7319144010543823,
      "reward_std": 0.10828442871570587,
      "rewards/accuracy_reward": 0.6100394129753113,
      "rewards/format_reward": 1.0,
      "step": 219,
      "temperature": 1.0
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.25,
      "completion_length": 378.0625,
      "epoch": 0.006690183675951831,
      "grad_norm": 0.8868201339092495,
      "kl": 0.020751953125,
      "learning_rate": 9.998895667510938e-07,
      "loss": 0.0008,
      "reward": 1.78125,
      "reward_std": 0.1530359536409378,
      "rewards/accuracy_reward": 0.671875,
      "rewards/format_reward": 1.0,
      "step": 220,
      "temperature": 1.0
    },
    {
      "all_correct": 0.625,
      "all_wrong": 0.125,
      "completion_length": 411.09375,
      "epoch": 0.006720593601751612,
      "grad_norm": 1.1557171687279029,
      "kl": 0.020751953125,
      "learning_rate": 9.998885605681676e-07,
      "loss": 0.0008,
      "reward": 1.7820312976837158,
      "reward_std": 0.08407025039196014,
      "rewards/accuracy_reward": 0.66015625,
      "rewards/format_reward": 1.0,
      "step": 221,
      "temperature": 1.0
    },
    {
      "all_correct": 0.375,
      "all_wrong": 0.125,
      "completion_length": 449.71875,
      "epoch": 0.0067510035275513925,
      "grad_norm": 1.0569183354789908,
      "kl": 0.012939453125,
      "learning_rate": 9.998875498227337e-07,
      "loss": 0.0005,
      "reward": 1.6942498683929443,
      "reward_std": 0.22362014651298523,
      "rewards/accuracy_reward": 0.5879997611045837,
      "rewards/format_reward": 1.0,
      "step": 222,
      "temperature": 1.0
    },
    {
      "all_correct": 0.625,
      "all_wrong": 0.0,
      "completion_length": 410.625,
      "epoch": 0.0067814134533511735,
      "grad_norm": 7.906802442704991,
      "kl": 0.01708984375,
      "learning_rate": 9.998865345148004e-07,
      "loss": 0.0007,
      "reward": 1.969193458557129,
      "reward_std": 0.15727870166301727,
      "rewards/accuracy_reward": 0.7973184585571289,
      "rewards/format_reward": 1.0,
      "step": 223,
      "temperature": 1.0
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.0,
      "completion_length": 432.359375,
      "epoch": 0.006811823379150955,
      "grad_norm": 2.96437483469161,
      "kl": 0.0146484375,
      "learning_rate": 9.998855146443775e-07,
      "loss": 0.0006,
      "reward": 1.7564566135406494,
      "reward_std": 0.11943941563367844,
      "rewards/accuracy_reward": 0.6283315420150757,
      "rewards/format_reward": 1.0,
      "step": 224,
      "temperature": 1.0
    },
    {
      "all_correct": 0.625,
      "all_wrong": 0.0,
      "completion_length": 413.984375,
      "epoch": 0.006842233304950736,
      "grad_norm": 1.266059182595279,
      "kl": 0.0191650390625,
      "learning_rate": 9.998844902114739e-07,
      "loss": 0.0008,
      "reward": 1.9190821647644043,
      "reward_std": 0.20085208117961884,
      "rewards/accuracy_reward": 0.7784572243690491,
      "rewards/format_reward": 0.984375,
      "step": 225,
      "temperature": 1.0
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.125,
      "completion_length": 397.484375,
      "epoch": 0.006872643230750517,
      "grad_norm": 1.5112630298156946,
      "kl": 0.0220947265625,
      "learning_rate": 9.998834612160993e-07,
      "loss": 0.0009,
      "reward": 1.7913932800292969,
      "reward_std": 0.15194737911224365,
      "rewards/accuracy_reward": 0.669518232345581,
      "rewards/format_reward": 1.0,
      "step": 226,
      "temperature": 1.0
    },
    {
      "all_correct": 0.75,
      "all_wrong": 0.0,
      "completion_length": 389.40625,
      "epoch": 0.006903053156550298,
      "grad_norm": 1.0268766912676646,
      "kl": 0.0213623046875,
      "learning_rate": 9.99882427658263e-07,
      "loss": 0.0009,
      "reward": 2.030564785003662,
      "reward_std": 0.09639369696378708,
      "rewards/accuracy_reward": 0.8493149280548096,
      "rewards/format_reward": 1.0,
      "step": 227,
      "temperature": 1.0
    },
    {
      "all_correct": 0.125,
      "all_wrong": 0.125,
      "completion_length": 431.8125,
      "epoch": 0.006933463082350079,
      "grad_norm": 1.679679765943165,
      "kl": 0.01544189453125,
      "learning_rate": 9.998813895379742e-07,
      "loss": 0.0006,
      "reward": 1.6168794631958008,
      "reward_std": 0.29984116554260254,
      "rewards/accuracy_reward": 0.526254415512085,
      "rewards/format_reward": 1.0,
      "step": 228,
      "temperature": 1.0
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.0,
      "completion_length": 405.375,
      "epoch": 0.00696387300814986,
      "grad_norm": 1.7846381547403725,
      "kl": 0.0181884765625,
      "learning_rate": 9.998803468552428e-07,
      "loss": 0.0007,
      "reward": 1.8887107372283936,
      "reward_std": 0.12382345646619797,
      "rewards/accuracy_reward": 0.7418356537818909,
      "rewards/format_reward": 1.0,
      "step": 229,
      "temperature": 1.0
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.125,
      "completion_length": 374.84375,
      "epoch": 0.006994282933949641,
      "grad_norm": 1.1428493463383278,
      "kl": 0.0179443359375,
      "learning_rate": 9.998792996100782e-07,
      "loss": 0.0007,
      "reward": 1.7624480724334717,
      "reward_std": 0.12163154035806656,
      "rewards/accuracy_reward": 0.6468230485916138,
      "rewards/format_reward": 1.0,
      "step": 230,
      "temperature": 1.0
    },
    {
      "all_correct": 0.25,
      "all_wrong": 0.125,
      "completion_length": 431.71875,
      "epoch": 0.007024692859749423,
      "grad_norm": 1.166922419567413,
      "kl": 0.0172119140625,
      "learning_rate": 9.998782478024897e-07,
      "loss": 0.0007,
      "reward": 1.7511425018310547,
      "reward_std": 0.22296537458896637,
      "rewards/accuracy_reward": 0.6386424899101257,
      "rewards/format_reward": 1.0,
      "step": 231,
      "temperature": 1.0
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.125,
      "completion_length": 380.34375,
      "epoch": 0.0070551027855492035,
      "grad_norm": 0.9734376500868925,
      "kl": 0.018310546875,
      "learning_rate": 9.99877191432487e-07,
      "loss": 0.0007,
      "reward": 1.859375,
      "reward_std": 0.1939256191253662,
      "rewards/accuracy_reward": 0.734375,
      "rewards/format_reward": 0.984375,
      "step": 232,
      "temperature": 1.0
    },
    {
      "all_correct": 0.25,
      "all_wrong": 0.125,
      "completion_length": 373.015625,
      "epoch": 0.0070855127113489845,
      "grad_norm": 3.1585609162562522,
      "kl": 0.0177001953125,
      "learning_rate": 9.9987613050008e-07,
      "loss": 0.0007,
      "reward": 1.720524549484253,
      "reward_std": 0.24647434055805206,
      "rewards/accuracy_reward": 0.5986495614051819,
      "rewards/format_reward": 1.0,
      "step": 233,
      "temperature": 1.0
    },
    {
      "all_correct": 0.375,
      "all_wrong": 0.375,
      "completion_length": 415.484375,
      "epoch": 0.007115922637148765,
      "grad_norm": 1.1413550607333405,
      "kl": 0.0159912109375,
      "learning_rate": 9.99875065005278e-07,
      "loss": 0.0006,
      "reward": 1.5806015729904175,
      "reward_std": 0.10819113254547119,
      "rewards/accuracy_reward": 0.4931015968322754,
      "rewards/format_reward": 1.0,
      "step": 234,
      "temperature": 1.0
    },
    {
      "all_correct": 0.125,
      "all_wrong": 0.125,
      "completion_length": 415.046875,
      "epoch": 0.007146332562948546,
      "grad_norm": 1.263984754486529,
      "kl": 0.01336669921875,
      "learning_rate": 9.99873994948091e-07,
      "loss": 0.0005,
      "reward": 1.5381163358688354,
      "reward_std": 0.27806341648101807,
      "rewards/accuracy_reward": 0.4349912703037262,
      "rewards/format_reward": 1.0,
      "step": 235,
      "temperature": 1.0
    },
    {
      "all_correct": 0.375,
      "all_wrong": 0.25,
      "completion_length": 387.78125,
      "epoch": 0.007176742488748327,
      "grad_norm": 1.168037503685382,
      "kl": 0.017333984375,
      "learning_rate": 9.998729203285287e-07,
      "loss": 0.0007,
      "reward": 1.6493332386016846,
      "reward_std": 0.11238259077072144,
      "rewards/accuracy_reward": 0.5399582386016846,
      "rewards/format_reward": 1.0,
      "step": 236,
      "temperature": 1.0
    },
    {
      "all_correct": 0.625,
      "all_wrong": 0.0,
      "completion_length": 373.359375,
      "epoch": 0.007207152414548108,
      "grad_norm": 1.268387927184248,
      "kl": 0.0177001953125,
      "learning_rate": 9.998718411466008e-07,
      "loss": 0.0007,
      "reward": 1.8947432041168213,
      "reward_std": 0.10737168788909912,
      "rewards/accuracy_reward": 0.7384930849075317,
      "rewards/format_reward": 1.0,
      "step": 237,
      "temperature": 1.0
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.0,
      "completion_length": 419.59375,
      "epoch": 0.00723756234034789,
      "grad_norm": 1.5050301211427486,
      "kl": 0.0155029296875,
      "learning_rate": 9.998707574023172e-07,
      "loss": 0.0006,
      "reward": 1.7658064365386963,
      "reward_std": 0.09879247844219208,
      "rewards/accuracy_reward": 0.6376813650131226,
      "rewards/format_reward": 1.0,
      "step": 238,
      "temperature": 1.0
    },
    {
      "all_correct": 0.375,
      "all_wrong": 0.125,
      "completion_length": 369.6875,
      "epoch": 0.007267972266147671,
      "grad_norm": 2.6382105945747507,
      "kl": 0.0179443359375,
      "learning_rate": 9.99869669095688e-07,
      "loss": 0.0007,
      "reward": 1.6472656726837158,
      "reward_std": 0.17413204908370972,
      "rewards/accuracy_reward": 0.556640625,
      "rewards/format_reward": 1.0,
      "step": 239,
      "temperature": 1.0
    },
    {
      "all_correct": 0.25,
      "all_wrong": 0.0,
      "completion_length": 408.78125,
      "epoch": 0.007298382191947452,
      "grad_norm": 1.3865649348822708,
      "kl": 0.014892578125,
      "learning_rate": 9.998685762267229e-07,
      "loss": 0.0006,
      "reward": 1.8254108428955078,
      "reward_std": 0.2866128385066986,
      "rewards/accuracy_reward": 0.6879106760025024,
      "rewards/format_reward": 1.0,
      "step": 240,
      "temperature": 1.0
    },
    {
      "all_correct": 0.25,
      "all_wrong": 0.125,
      "completion_length": 425.6875,
      "epoch": 0.007328792117747233,
      "grad_norm": 1.4692098400653377,
      "kl": 0.0135498046875,
      "learning_rate": 9.998674787954318e-07,
      "loss": 0.0005,
      "reward": 1.6054425239562988,
      "reward_std": 0.21674001216888428,
      "rewards/accuracy_reward": 0.5054423809051514,
      "rewards/format_reward": 0.984375,
      "step": 241,
      "temperature": 1.0
    },
    {
      "all_correct": 0.625,
      "all_wrong": 0.125,
      "completion_length": 370.109375,
      "epoch": 0.007359202043547014,
      "grad_norm": 1.8934079492849498,
      "kl": 0.01806640625,
      "learning_rate": 9.99866376801825e-07,
      "loss": 0.0007,
      "reward": 1.8729619979858398,
      "reward_std": 0.08135965466499329,
      "rewards/accuracy_reward": 0.7323369383811951,
      "rewards/format_reward": 1.0,
      "step": 242,
      "temperature": 1.0
    },
    {
      "all_correct": 0.375,
      "all_wrong": 0.0,
      "completion_length": 412.734375,
      "epoch": 0.007389611969346795,
      "grad_norm": 1.304983648567823,
      "kl": 0.01519775390625,
      "learning_rate": 9.998652702459123e-07,
      "loss": 0.0006,
      "reward": 1.7894978523254395,
      "reward_std": 0.23549628257751465,
      "rewards/accuracy_reward": 0.6394978761672974,
      "rewards/format_reward": 1.0,
      "step": 243,
      "temperature": 1.0
    },
    {
      "all_correct": 0.75,
      "all_wrong": 0.0,
      "completion_length": 377.515625,
      "epoch": 0.0074200218951465755,
      "grad_norm": 1.1114601985571375,
      "kl": 0.01513671875,
      "learning_rate": 9.998641591277038e-07,
      "loss": 0.0006,
      "reward": 2.0155651569366455,
      "reward_std": 0.04978543519973755,
      "rewards/accuracy_reward": 0.8624401688575745,
      "rewards/format_reward": 1.0,
      "step": 244,
      "temperature": 1.0
    },
    {
      "all_correct": 0.625,
      "all_wrong": 0.0,
      "completion_length": 383.65625,
      "epoch": 0.007450431820946357,
      "grad_norm": 1.4515246684859342,
      "kl": 0.0196533203125,
      "learning_rate": 9.9986304344721e-07,
      "loss": 0.0008,
      "reward": 2.065331220626831,
      "reward_std": 0.19604066014289856,
      "rewards/accuracy_reward": 0.9028311967849731,
      "rewards/format_reward": 1.0,
      "step": 245,
      "temperature": 1.0
    },
    {
      "all_correct": 0.375,
      "all_wrong": 0.125,
      "completion_length": 424.9375,
      "epoch": 0.007480841746746138,
      "grad_norm": 1.0988957051601167,
      "kl": 0.0159912109375,
      "learning_rate": 9.998619232044405e-07,
      "loss": 0.0006,
      "reward": 1.6412570476531982,
      "reward_std": 0.19408860802650452,
      "rewards/accuracy_reward": 0.5475069284439087,
      "rewards/format_reward": 0.96875,
      "step": 246,
      "temperature": 1.0
    },
    {
      "all_correct": 0.625,
      "all_wrong": 0.0,
      "completion_length": 416.75,
      "epoch": 0.007511251672545919,
      "grad_norm": 1.435719151402882,
      "kl": 0.0185546875,
      "learning_rate": 9.998607983994061e-07,
      "loss": 0.0007,
      "reward": 1.9047449827194214,
      "reward_std": 0.10657308995723724,
      "rewards/accuracy_reward": 0.7391198873519897,
      "rewards/format_reward": 1.0,
      "step": 247,
      "temperature": 1.0
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.0,
      "completion_length": 378.890625,
      "epoch": 0.0075416615983457,
      "grad_norm": 1.3455637978204695,
      "kl": 0.0211181640625,
      "learning_rate": 9.998596690321168e-07,
      "loss": 0.0008,
      "reward": 1.9215421676635742,
      "reward_std": 0.24901898205280304,
      "rewards/accuracy_reward": 0.7809171676635742,
      "rewards/format_reward": 1.0,
      "step": 248,
      "temperature": 1.0
    },
    {
      "all_correct": 0.375,
      "all_wrong": 0.25,
      "completion_length": 397.828125,
      "epoch": 0.007572071524145481,
      "grad_norm": 1.167171903141408,
      "kl": 0.0205078125,
      "learning_rate": 9.998585351025829e-07,
      "loss": 0.0008,
      "reward": 1.6909074783325195,
      "reward_std": 0.17762073874473572,
      "rewards/accuracy_reward": 0.5877823829650879,
      "rewards/format_reward": 1.0,
      "step": 249,
      "temperature": 1.0
    },
    {
      "all_correct": 0.25,
      "all_wrong": 0.0,
      "completion_length": 382.71875,
      "epoch": 0.007602481449945262,
      "grad_norm": 2.0764422873513295,
      "kl": 0.0191650390625,
      "learning_rate": 9.998573966108147e-07,
      "loss": 0.0008,
      "reward": 1.6750352382659912,
      "reward_std": 0.30122262239456177,
      "rewards/accuracy_reward": 0.5500352382659912,
      "rewards/format_reward": 1.0,
      "step": 250,
      "temperature": 1.0
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.0,
      "completion_length": 399.703125,
      "epoch": 0.007632891375745043,
      "grad_norm": 0.8997983074065692,
      "kl": 0.018798828125,
      "learning_rate": 9.998562535568227e-07,
      "loss": 0.0007,
      "reward": 1.9275240898132324,
      "reward_std": 0.17176565527915955,
      "rewards/accuracy_reward": 0.7806490659713745,
      "rewards/format_reward": 1.0,
      "step": 251,
      "temperature": 1.0
    },
    {
      "all_correct": 0.375,
      "all_wrong": 0.125,
      "completion_length": 413.671875,
      "epoch": 0.007663301301544824,
      "grad_norm": 1.5932879533627549,
      "kl": 0.0186767578125,
      "learning_rate": 9.998551059406174e-07,
      "loss": 0.0007,
      "reward": 1.5218663215637207,
      "reward_std": 0.1883080154657364,
      "rewards/accuracy_reward": 0.45311635732650757,
      "rewards/format_reward": 0.984375,
      "step": 252,
      "temperature": 1.0
    },
    {
      "all_correct": 0.375,
      "all_wrong": 0.0,
      "completion_length": 434.140625,
      "epoch": 0.007693711227344606,
      "grad_norm": 1.742823374375136,
      "kl": 0.017822265625,
      "learning_rate": 9.998539537622093e-07,
      "loss": 0.0007,
      "reward": 1.7532962560653687,
      "reward_std": 0.14785994589328766,
      "rewards/accuracy_reward": 0.6095462441444397,
      "rewards/format_reward": 1.0,
      "step": 253,
      "temperature": 1.0
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.125,
      "completion_length": 394.921875,
      "epoch": 0.0077241211531443865,
      "grad_norm": 1.2722874219875149,
      "kl": 0.0191650390625,
      "learning_rate": 9.998527970216084e-07,
      "loss": 0.0008,
      "reward": 1.9215774536132812,
      "reward_std": 0.1415565460920334,
      "rewards/accuracy_reward": 0.7715773582458496,
      "rewards/format_reward": 1.0,
      "step": 254,
      "temperature": 1.0
    },
    {
      "all_correct": 0.875,
      "all_wrong": 0.125,
      "completion_length": 377.578125,
      "epoch": 0.0077545310789441674,
      "grad_norm": 0.6936276319667944,
      "kl": 0.022705078125,
      "learning_rate": 9.998516357188258e-07,
      "loss": 0.0009,
      "reward": 2.043750047683716,
      "reward_std": 0.017677675932645798,
      "rewards/accuracy_reward": 0.875,
      "rewards/format_reward": 1.0,
      "step": 255,
      "temperature": 1.0
    },
    {
      "all_correct": 0.75,
      "all_wrong": 0.0,
      "completion_length": 406.96875,
      "epoch": 0.007784941004743948,
      "grad_norm": 1.2276230997416127,
      "kl": 0.0177001953125,
      "learning_rate": 9.99850469853872e-07,
      "loss": 0.0007,
      "reward": 2.046505928039551,
      "reward_std": 0.07997314631938934,
      "rewards/accuracy_reward": 0.8777557611465454,
      "rewards/format_reward": 1.0,
      "step": 256,
      "temperature": 1.0
    },
    {
      "all_correct": 0.625,
      "all_wrong": 0.125,
      "completion_length": 379.4375,
      "epoch": 0.00781535093054373,
      "grad_norm": 0.8746516396380941,
      "kl": 0.0164794921875,
      "learning_rate": 9.998492994267576e-07,
      "loss": 0.0007,
      "reward": 1.9320472478866577,
      "reward_std": 0.1163143664598465,
      "rewards/accuracy_reward": 0.7757972478866577,
      "rewards/format_reward": 1.0,
      "step": 257,
      "temperature": 1.0
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.125,
      "completion_length": 392.140625,
      "epoch": 0.00784576085634351,
      "grad_norm": 1.6968203059364477,
      "kl": 0.0185546875,
      "learning_rate": 9.998481244374932e-07,
      "loss": 0.0007,
      "reward": 1.6855379343032837,
      "reward_std": 0.15177245438098907,
      "rewards/accuracy_reward": 0.5824129581451416,
      "rewards/format_reward": 1.0,
      "step": 258,
      "temperature": 1.0
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.0,
      "completion_length": 376.46875,
      "epoch": 0.007876170782143291,
      "grad_norm": 4.023832821261256,
      "kl": 0.021240234375,
      "learning_rate": 9.998469448860898e-07,
      "loss": 0.0008,
      "reward": 1.9996700286865234,
      "reward_std": 0.23446165025234222,
      "rewards/accuracy_reward": 0.8340448141098022,
      "rewards/format_reward": 1.0,
      "step": 259,
      "temperature": 1.0
    },
    {
      "all_correct": 0.125,
      "all_wrong": 0.125,
      "completion_length": 395.90625,
      "epoch": 0.007906580707943072,
      "grad_norm": 1.468067958819823,
      "kl": 0.0174560546875,
      "learning_rate": 9.998457607725577e-07,
      "loss": 0.0007,
      "reward": 1.5739922523498535,
      "reward_std": 0.3005222678184509,
      "rewards/accuracy_reward": 0.4864921271800995,
      "rewards/format_reward": 0.984375,
      "step": 260,
      "temperature": 1.0
    },
    {
      "all_correct": 0.625,
      "all_wrong": 0.125,
      "completion_length": 407.109375,
      "epoch": 0.007936990633742853,
      "grad_norm": 1.4478560274594938,
      "kl": 0.0172119140625,
      "learning_rate": 9.998445720969082e-07,
      "loss": 0.0007,
      "reward": 1.7547173500061035,
      "reward_std": 0.0737149715423584,
      "rewards/accuracy_reward": 0.6390923857688904,
      "rewards/format_reward": 1.0,
      "step": 261,
      "temperature": 1.0
    },
    {
      "all_correct": 0.75,
      "all_wrong": 0.0,
      "completion_length": 386.046875,
      "epoch": 0.007967400559542634,
      "grad_norm": 1.2995545752815922,
      "kl": 0.016845703125,
      "learning_rate": 9.998433788591516e-07,
      "loss": 0.0007,
      "reward": 2.0538532733917236,
      "reward_std": 0.07212623953819275,
      "rewards/accuracy_reward": 0.8757283091545105,
      "rewards/format_reward": 1.0,
      "step": 262,
      "temperature": 1.0
    },
    {
      "all_correct": 0.625,
      "all_wrong": 0.125,
      "completion_length": 392.75,
      "epoch": 0.007997810485342417,
      "grad_norm": 1.0039865621466422,
      "kl": 0.0198974609375,
      "learning_rate": 9.998421810592995e-07,
      "loss": 0.0008,
      "reward": 1.850000023841858,
      "reward_std": 0.13277359306812286,
      "rewards/accuracy_reward": 0.7125000357627869,
      "rewards/format_reward": 1.0,
      "step": 263,
      "temperature": 1.0
    },
    {
      "all_correct": 0.375,
      "all_wrong": 0.125,
      "completion_length": 387.984375,
      "epoch": 0.008028220411142198,
      "grad_norm": 1.6787583724136423,
      "kl": 0.0201416015625,
      "learning_rate": 9.998409786973622e-07,
      "loss": 0.0008,
      "reward": 1.7388439178466797,
      "reward_std": 0.14969630539417267,
      "rewards/accuracy_reward": 0.5950939655303955,
      "rewards/format_reward": 1.0,
      "step": 264,
      "temperature": 1.0
    },
    {
      "all_correct": 0.25,
      "all_wrong": 0.0,
      "completion_length": 406.359375,
      "epoch": 0.008058630336941978,
      "grad_norm": 3.58921592621572,
      "kl": 0.0162353515625,
      "learning_rate": 9.99839771773351e-07,
      "loss": 0.0006,
      "reward": 1.7742525339126587,
      "reward_std": 0.21629348397254944,
      "rewards/accuracy_reward": 0.6117525696754456,
      "rewards/format_reward": 1.0,
      "step": 265,
      "temperature": 1.0
    },
    {
      "all_correct": 0.375,
      "all_wrong": 0.125,
      "completion_length": 430.421875,
      "epoch": 0.00808904026274176,
      "grad_norm": 9.729282074480514,
      "kl": 0.0166015625,
      "learning_rate": 9.998385602872768e-07,
      "loss": 0.0007,
      "reward": 1.6444361209869385,
      "reward_std": 0.16006812453269958,
      "rewards/accuracy_reward": 0.5475611090660095,
      "rewards/format_reward": 1.0,
      "step": 266,
      "temperature": 1.0
    },
    {
      "all_correct": 0.375,
      "all_wrong": 0.125,
      "completion_length": 454.734375,
      "epoch": 0.00811945018854154,
      "grad_norm": 1.2696450990003763,
      "kl": 0.0162353515625,
      "learning_rate": 9.998373442391505e-07,
      "loss": 0.0007,
      "reward": 1.5544025897979736,
      "reward_std": 0.2473534494638443,
      "rewards/accuracy_reward": 0.5262776613235474,
      "rewards/format_reward": 0.921875,
      "step": 267,
      "temperature": 1.0
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.0,
      "completion_length": 400.625,
      "epoch": 0.008149860114341321,
      "grad_norm": 1.0757583736109715,
      "kl": 0.021240234375,
      "learning_rate": 9.998361236289836e-07,
      "loss": 0.0009,
      "reward": 1.7983217239379883,
      "reward_std": 0.17950627207756042,
      "rewards/accuracy_reward": 0.6826967000961304,
      "rewards/format_reward": 1.0,
      "step": 268,
      "temperature": 1.0
    },
    {
      "all_correct": 0.375,
      "all_wrong": 0.125,
      "completion_length": 385.765625,
      "epoch": 0.008180270040141102,
      "grad_norm": 88.34558035216274,
      "kl": 0.017333984375,
      "learning_rate": 9.99834898456787e-07,
      "loss": 0.0007,
      "reward": 1.6330974102020264,
      "reward_std": 0.10395858436822891,
      "rewards/accuracy_reward": 0.5080972909927368,
      "rewards/format_reward": 1.0,
      "step": 269,
      "temperature": 1.0
    },
    {
      "all_correct": 0.875,
      "all_wrong": 0.0,
      "completion_length": 355.359375,
      "epoch": 0.008210679965940883,
      "grad_norm": 0.9639375732062316,
      "kl": 0.025146484375,
      "learning_rate": 9.99833668722572e-07,
      "loss": 0.001,
      "reward": 2.1500000953674316,
      "reward_std": 0.09121407568454742,
      "rewards/accuracy_reward": 0.96875,
      "rewards/format_reward": 1.0,
      "step": 270,
      "temperature": 1.0
    },
    {
      "all_correct": 0.375,
      "all_wrong": 0.0,
      "completion_length": 430.390625,
      "epoch": 0.008241089891740664,
      "grad_norm": 1.3672529823270474,
      "kl": 0.0169677734375,
      "learning_rate": 9.998324344263497e-07,
      "loss": 0.0007,
      "reward": 1.742522954940796,
      "reward_std": 0.1812654584646225,
      "rewards/accuracy_reward": 0.6175230741500854,
      "rewards/format_reward": 1.0,
      "step": 271,
      "temperature": 1.0
    },
    {
      "all_correct": 0.375,
      "all_wrong": 0.125,
      "completion_length": 441.78125,
      "epoch": 0.008271499817540445,
      "grad_norm": 6.506897812501092,
      "kl": 0.015625,
      "learning_rate": 9.998311955681312e-07,
      "loss": 0.0006,
      "reward": 1.6561243534088135,
      "reward_std": 0.13107216358184814,
      "rewards/accuracy_reward": 0.5498743057250977,
      "rewards/format_reward": 1.0,
      "step": 272,
      "temperature": 1.0
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.125,
      "completion_length": 410.734375,
      "epoch": 0.008301909743340226,
      "grad_norm": 2.049900258813113,
      "kl": 0.01806640625,
      "learning_rate": 9.998299521479281e-07,
      "loss": 0.0007,
      "reward": 1.8084383010864258,
      "reward_std": 0.1195424497127533,
      "rewards/accuracy_reward": 0.6771881580352783,
      "rewards/format_reward": 1.0,
      "step": 273,
      "temperature": 1.0
    },
    {
      "all_correct": 0.75,
      "all_wrong": 0.0,
      "completion_length": 370.09375,
      "epoch": 0.008332319669140007,
      "grad_norm": 1.1151104799809013,
      "kl": 0.0213623046875,
      "learning_rate": 9.998287041657515e-07,
      "loss": 0.0009,
      "reward": 2.0338916778564453,
      "reward_std": 0.10179020464420319,
      "rewards/accuracy_reward": 0.8495166897773743,
      "rewards/format_reward": 1.0,
      "step": 274,
      "temperature": 1.0
    },
    {
      "all_correct": 0.75,
      "all_wrong": 0.25,
      "completion_length": 381.390625,
      "epoch": 0.008362729594939788,
      "grad_norm": 0.633587659886379,
      "kl": 0.01806640625,
      "learning_rate": 9.998274516216132e-07,
      "loss": 0.0007,
      "reward": 1.8968749046325684,
      "reward_std": 0.008838837966322899,
      "rewards/accuracy_reward": 0.75,
      "rewards/format_reward": 1.0,
      "step": 275,
      "temperature": 1.0
    },
    {
      "all_correct": 0.25,
      "all_wrong": 0.25,
      "completion_length": 364.25,
      "epoch": 0.008393139520739569,
      "grad_norm": 1.2549106407714368,
      "kl": 0.0169677734375,
      "learning_rate": 9.998261945155245e-07,
      "loss": 0.0007,
      "reward": 1.7268636226654053,
      "reward_std": 0.20624911785125732,
      "rewards/accuracy_reward": 0.6081135272979736,
      "rewards/format_reward": 1.0,
      "step": 276,
      "temperature": 1.0
    },
    {
      "all_correct": 0.25,
      "all_wrong": 0.375,
      "completion_length": 369.34375,
      "epoch": 0.008423549446539351,
      "grad_norm": 1.3437726173468763,
      "kl": 0.02294921875,
      "learning_rate": 9.998249328474964e-07,
      "loss": 0.0009,
      "reward": 1.5311367511749268,
      "reward_std": 0.2296334058046341,
      "rewards/accuracy_reward": 0.449886679649353,
      "rewards/format_reward": 0.984375,
      "step": 277,
      "temperature": 1.0
    },
    {
      "all_correct": 0.75,
      "all_wrong": 0.125,
      "completion_length": 373.078125,
      "epoch": 0.008453959372339132,
      "grad_norm": 0.9114216670248432,
      "kl": 0.02197265625,
      "learning_rate": 9.99823666617541e-07,
      "loss": 0.0009,
      "reward": 2.0062501430511475,
      "reward_std": 0.08711418509483337,
      "rewards/accuracy_reward": 0.84375,
      "rewards/format_reward": 1.0,
      "step": 278,
      "temperature": 1.0
    },
    {
      "all_correct": 0.375,
      "all_wrong": 0.0,
      "completion_length": 374.671875,
      "epoch": 0.008484369298138913,
      "grad_norm": 1.1859561845566342,
      "kl": 0.0196533203125,
      "learning_rate": 9.998223958256695e-07,
      "loss": 0.0008,
      "reward": 1.903586745262146,
      "reward_std": 0.22309716045856476,
      "rewards/accuracy_reward": 0.731711745262146,
      "rewards/format_reward": 1.0,
      "step": 279,
      "temperature": 1.0
    },
    {
      "all_correct": 0.625,
      "all_wrong": 0.0,
      "completion_length": 364.375,
      "epoch": 0.008514779223938694,
      "grad_norm": 1.6769116808674795,
      "kl": 0.021240234375,
      "learning_rate": 9.998211204718936e-07,
      "loss": 0.0009,
      "reward": 2.087890625,
      "reward_std": 0.188189297914505,
      "rewards/accuracy_reward": 0.916015625,
      "rewards/format_reward": 1.0,
      "step": 280,
      "temperature": 1.0
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.25,
      "completion_length": 398.609375,
      "epoch": 0.008545189149738475,
      "grad_norm": 0.6488468337757527,
      "kl": 0.019287109375,
      "learning_rate": 9.99819840556225e-07,
      "loss": 0.0008,
      "reward": 1.7400803565979004,
      "reward_std": 0.12728886306285858,
      "rewards/accuracy_reward": 0.6182053089141846,
      "rewards/format_reward": 0.984375,
      "step": 281,
      "temperature": 1.0
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.0,
      "completion_length": 365.734375,
      "epoch": 0.008575599075538256,
      "grad_norm": 1.179660191289629,
      "kl": 0.02001953125,
      "learning_rate": 9.998185560786753e-07,
      "loss": 0.0008,
      "reward": 1.8793513774871826,
      "reward_std": 0.2097109854221344,
      "rewards/accuracy_reward": 0.7324762344360352,
      "rewards/format_reward": 1.0,
      "step": 282,
      "temperature": 1.0
    },
    {
      "all_correct": 0.75,
      "all_wrong": 0.0,
      "completion_length": 380.921875,
      "epoch": 0.008606009001338037,
      "grad_norm": 0.9254812804034066,
      "kl": 0.02001953125,
      "learning_rate": 9.998172670392566e-07,
      "loss": 0.0008,
      "reward": 2.0477325916290283,
      "reward_std": 0.06443040072917938,
      "rewards/accuracy_reward": 0.8664825558662415,
      "rewards/format_reward": 1.0,
      "step": 283,
      "temperature": 1.0
    },
    {
      "all_correct": 0.25,
      "all_wrong": 0.125,
      "completion_length": 389.8125,
      "epoch": 0.008636418927137818,
      "grad_norm": 2.637937194392917,
      "kl": 0.0203857421875,
      "learning_rate": 9.9981597343798e-07,
      "loss": 0.0008,
      "reward": 1.5260801315307617,
      "reward_std": 0.2240482121706009,
      "rewards/accuracy_reward": 0.43233007192611694,
      "rewards/format_reward": 1.0,
      "step": 284,
      "temperature": 1.0
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.0,
      "completion_length": 389.890625,
      "epoch": 0.008666828852937599,
      "grad_norm": 1.1072693246546153,
      "kl": 0.016845703125,
      "learning_rate": 9.998146752748577e-07,
      "loss": 0.0007,
      "reward": 1.9428386688232422,
      "reward_std": 0.24031490087509155,
      "rewards/accuracy_reward": 0.7897135019302368,
      "rewards/format_reward": 1.0,
      "step": 285,
      "temperature": 1.0
    },
    {
      "all_correct": 0.75,
      "all_wrong": 0.0,
      "completion_length": 399.96875,
      "epoch": 0.00869723877873738,
      "grad_norm": 0.8546295331496868,
      "kl": 0.01806640625,
      "learning_rate": 9.998133725499014e-07,
      "loss": 0.0007,
      "reward": 2.0550358295440674,
      "reward_std": 0.1342320740222931,
      "rewards/accuracy_reward": 0.9050357341766357,
      "rewards/format_reward": 1.0,
      "step": 286,
      "temperature": 1.0
    },
    {
      "all_correct": 0.625,
      "all_wrong": 0.25,
      "completion_length": 369.359375,
      "epoch": 0.00872764870453716,
      "grad_norm": 0.42319947894545923,
      "kl": 0.018798828125,
      "learning_rate": 9.998120652631231e-07,
      "loss": 0.0008,
      "reward": 1.875,
      "reward_std": 0.051754921674728394,
      "rewards/accuracy_reward": 0.734375,
      "rewards/format_reward": 1.0,
      "step": 287,
      "temperature": 1.0
    },
    {
      "all_correct": 0.75,
      "all_wrong": 0.0,
      "completion_length": 408.703125,
      "epoch": 0.008758058630336941,
      "grad_norm": 0.5448274786954306,
      "kl": 0.0205078125,
      "learning_rate": 9.998107534145348e-07,
      "loss": 0.0008,
      "reward": 2.077310800552368,
      "reward_std": 0.09646253287792206,
      "rewards/accuracy_reward": 0.8991856575012207,
      "rewards/format_reward": 1.0,
      "step": 288,
      "temperature": 1.0
    },
    {
      "all_correct": 0.625,
      "all_wrong": 0.0,
      "completion_length": 394.796875,
      "epoch": 0.008788468556136722,
      "grad_norm": 1.263692114643898,
      "kl": 0.0177001953125,
      "learning_rate": 9.998094370041485e-07,
      "loss": 0.0007,
      "reward": 1.9167423248291016,
      "reward_std": 0.07768350094556808,
      "rewards/accuracy_reward": 0.7511173486709595,
      "rewards/format_reward": 1.0,
      "step": 289,
      "temperature": 1.0
    },
    {
      "all_correct": 0.625,
      "all_wrong": 0.0,
      "completion_length": 413.4375,
      "epoch": 0.008818878481936503,
      "grad_norm": 1.4574613980867532,
      "kl": 0.0206298828125,
      "learning_rate": 9.998081160319759e-07,
      "loss": 0.0008,
      "reward": 1.9200654029846191,
      "reward_std": 0.1518048793077469,
      "rewards/accuracy_reward": 0.7919403910636902,
      "rewards/format_reward": 0.984375,
      "step": 290,
      "temperature": 1.0
    },
    {
      "all_correct": 0.625,
      "all_wrong": 0.0,
      "completion_length": 361.375,
      "epoch": 0.008849288407736284,
      "grad_norm": 1.6967769004986903,
      "kl": 0.0238037109375,
      "learning_rate": 9.998067904980293e-07,
      "loss": 0.001,
      "reward": 1.9124999046325684,
      "reward_std": 0.23418307304382324,
      "rewards/accuracy_reward": 0.765625,
      "rewards/format_reward": 1.0,
      "step": 291,
      "temperature": 1.0
    },
    {
      "all_correct": 0.125,
      "all_wrong": 0.25,
      "completion_length": 386.203125,
      "epoch": 0.008879698333536067,
      "grad_norm": 1.5270866574207245,
      "kl": 0.01708984375,
      "learning_rate": 9.998054604023208e-07,
      "loss": 0.0007,
      "reward": 1.6708673238754272,
      "reward_std": 0.22572845220565796,
      "rewards/accuracy_reward": 0.5583672523498535,
      "rewards/format_reward": 1.0,
      "step": 292,
      "temperature": 1.0
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.0,
      "completion_length": 423.6875,
      "epoch": 0.008910108259335848,
      "grad_norm": 1.2254023006663615,
      "kl": 0.019287109375,
      "learning_rate": 9.998041257448623e-07,
      "loss": 0.0008,
      "reward": 1.7597155570983887,
      "reward_std": 0.26602789759635925,
      "rewards/accuracy_reward": 0.6597157120704651,
      "rewards/format_reward": 0.984375,
      "step": 293,
      "temperature": 1.0
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.0,
      "completion_length": 380.9375,
      "epoch": 0.008940518185135629,
      "grad_norm": 1.5121729070637349,
      "kl": 0.0225830078125,
      "learning_rate": 9.998027865256664e-07,
      "loss": 0.0009,
      "reward": 1.9640789031982422,
      "reward_std": 0.2045850157737732,
      "rewards/accuracy_reward": 0.8047038912773132,
      "rewards/format_reward": 1.0,
      "step": 294,
      "temperature": 1.0
    },
    {
      "all_correct": 0.25,
      "all_wrong": 0.0,
      "completion_length": 443.25,
      "epoch": 0.00897092811093541,
      "grad_norm": 2.6542982099965604,
      "kl": 0.020751953125,
      "learning_rate": 9.99801442744745e-07,
      "loss": 0.0008,
      "reward": 1.6407462358474731,
      "reward_std": 0.30159279704093933,
      "rewards/accuracy_reward": 0.5438711643218994,
      "rewards/format_reward": 1.0,
      "step": 295,
      "temperature": 1.0
    },
    {
      "all_correct": 1.0,
      "all_wrong": 0.0,
      "completion_length": 376.734375,
      "epoch": 0.00900133803673519,
      "grad_norm": 1.0356791095074909,
      "kl": 0.0234375,
      "learning_rate": 9.998000944021105e-07,
      "loss": 0.0009,
      "reward": 2.190624952316284,
      "reward_std": 0.026516513898968697,
      "rewards/accuracy_reward": 1.0,
      "rewards/format_reward": 1.0,
      "step": 296,
      "temperature": 1.0
    },
    {
      "all_correct": 0.75,
      "all_wrong": 0.0,
      "completion_length": 398.59375,
      "epoch": 0.009031747962534972,
      "grad_norm": 1.0930553306787711,
      "kl": 0.0203857421875,
      "learning_rate": 9.997987414977751e-07,
      "loss": 0.0008,
      "reward": 2.0114102363586426,
      "reward_std": 0.03505685180425644,
      "rewards/accuracy_reward": 0.8270350694656372,
      "rewards/format_reward": 1.0,
      "step": 297,
      "temperature": 1.0
    },
    {
      "all_correct": 0.625,
      "all_wrong": 0.0,
      "completion_length": 383.453125,
      "epoch": 0.009062157888334752,
      "grad_norm": 1.4956913686960942,
      "kl": 0.02587890625,
      "learning_rate": 9.997973840317512e-07,
      "loss": 0.001,
      "reward": 1.884374976158142,
      "reward_std": 0.2237825095653534,
      "rewards/accuracy_reward": 0.75,
      "rewards/format_reward": 1.0,
      "step": 298,
      "temperature": 1.0
    },
    {
      "all_correct": 0.625,
      "all_wrong": 0.125,
      "completion_length": 403.875,
      "epoch": 0.009092567814134533,
      "grad_norm": 2.1483223023180926,
      "kl": 0.0233154296875,
      "learning_rate": 9.997960220040513e-07,
      "loss": 0.0009,
      "reward": 1.805154800415039,
      "reward_std": 0.06720379739999771,
      "rewards/accuracy_reward": 0.6739048957824707,
      "rewards/format_reward": 1.0,
      "step": 299,
      "temperature": 1.0
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.0,
      "completion_length": 408.75,
      "epoch": 0.009122977739934314,
      "grad_norm": 1.0463953955814098,
      "kl": 0.021728515625,
      "learning_rate": 9.99794655414688e-07,
      "loss": 0.0009,
      "reward": 1.9292975664138794,
      "reward_std": 0.20763559639453888,
      "rewards/accuracy_reward": 0.7730474472045898,
      "rewards/format_reward": 1.0,
      "step": 300,
      "temperature": 1.0
    },
    {
      "all_correct": 0.25,
      "all_wrong": 0.375,
      "completion_length": 394.484375,
      "epoch": 0.009153387665734095,
      "grad_norm": 3.1512766598196396,
      "kl": 0.0267333984375,
      "learning_rate": 9.99793284263673e-07,
      "loss": 0.0011,
      "reward": 1.430694580078125,
      "reward_std": 0.14200130105018616,
      "rewards/accuracy_reward": 0.36819449067115784,
      "rewards/format_reward": 1.0,
      "step": 301,
      "temperature": 1.0
    },
    {
      "all_correct": 0.375,
      "all_wrong": 0.25,
      "completion_length": 406.609375,
      "epoch": 0.009183797591533876,
      "grad_norm": 1.0791137430105968,
      "kl": 0.02587890625,
      "learning_rate": 9.997919085510195e-07,
      "loss": 0.001,
      "reward": 1.6759614944458008,
      "reward_std": 0.17698103189468384,
      "rewards/accuracy_reward": 0.5697115063667297,
      "rewards/format_reward": 1.0,
      "step": 302,
      "temperature": 1.0
    },
    {
      "all_correct": 0.125,
      "all_wrong": 0.125,
      "completion_length": 444.8125,
      "epoch": 0.009214207517333657,
      "grad_norm": 1.4418307326155777,
      "kl": 0.016357421875,
      "learning_rate": 9.9979052827674e-07,
      "loss": 0.0007,
      "reward": 1.655404806137085,
      "reward_std": 0.1988653838634491,
      "rewards/accuracy_reward": 0.524154782295227,
      "rewards/format_reward": 1.0,
      "step": 303,
      "temperature": 1.0
    },
    {
      "all_correct": 0.375,
      "all_wrong": 0.125,
      "completion_length": 447.109375,
      "epoch": 0.009244617443133438,
      "grad_norm": 1.248057559674378,
      "kl": 0.025390625,
      "learning_rate": 9.997891434408468e-07,
      "loss": 0.001,
      "reward": 1.6764607429504395,
      "reward_std": 0.25445371866226196,
      "rewards/accuracy_reward": 0.5983356833457947,
      "rewards/format_reward": 0.984375,
      "step": 304,
      "temperature": 1.0
    },
    {
      "all_correct": 0.25,
      "all_wrong": 0.375,
      "completion_length": 397.0625,
      "epoch": 0.009275027368933219,
      "grad_norm": 1.2817247996072059,
      "kl": 0.03125,
      "learning_rate": 9.997877540433528e-07,
      "loss": 0.0012,
      "reward": 1.4456782341003418,
      "reward_std": 0.11583495885133743,
      "rewards/accuracy_reward": 0.37380316853523254,
      "rewards/format_reward": 1.0,
      "step": 305,
      "temperature": 1.0
    },
    {
      "all_correct": 0.375,
      "all_wrong": 0.0,
      "completion_length": 408.078125,
      "epoch": 0.009305437294733002,
      "grad_norm": 1.2715245243088085,
      "kl": 0.0279541015625,
      "learning_rate": 9.997863600842707e-07,
      "loss": 0.0011,
      "reward": 1.8627594709396362,
      "reward_std": 0.307189404964447,
      "rewards/accuracy_reward": 0.7315094470977783,
      "rewards/format_reward": 1.0,
      "step": 306,
      "temperature": 1.0
    },
    {
      "all_correct": 0.375,
      "all_wrong": 0.125,
      "completion_length": 387.203125,
      "epoch": 0.009335847220532783,
      "grad_norm": 1.2061878735481548,
      "kl": 0.0250244140625,
      "learning_rate": 9.99784961563613e-07,
      "loss": 0.001,
      "reward": 1.8187501430511475,
      "reward_std": 0.2811111509799957,
      "rewards/accuracy_reward": 0.6875,
      "rewards/format_reward": 1.0,
      "step": 307,
      "temperature": 1.0
    },
    {
      "all_correct": 0.625,
      "all_wrong": 0.25,
      "completion_length": 383.828125,
      "epoch": 0.009366257146332563,
      "grad_norm": 0.5985537422618991,
      "kl": 0.03125,
      "learning_rate": 9.997835584813926e-07,
      "loss": 0.0013,
      "reward": 1.84726881980896,
      "reward_std": 0.004020115826278925,
      "rewards/accuracy_reward": 0.6972686648368835,
      "rewards/format_reward": 1.0,
      "step": 308,
      "temperature": 1.0
    },
    {
      "all_correct": 0.25,
      "all_wrong": 0.25,
      "completion_length": 411.046875,
      "epoch": 0.009396667072132344,
      "grad_norm": 1.0704198498017132,
      "kl": 0.020751953125,
      "learning_rate": 9.997821508376224e-07,
      "loss": 0.0008,
      "reward": 1.5381271839141846,
      "reward_std": 0.06827206909656525,
      "rewards/accuracy_reward": 0.4193771779537201,
      "rewards/format_reward": 1.0,
      "step": 309,
      "temperature": 1.0
    },
    {
      "all_correct": 0.625,
      "all_wrong": 0.0,
      "completion_length": 421.84375,
      "epoch": 0.009427076997932125,
      "grad_norm": 0.6895041807599859,
      "kl": 0.025634765625,
      "learning_rate": 9.99780738632315e-07,
      "loss": 0.001,
      "reward": 1.9787968397140503,
      "reward_std": 0.1919824779033661,
      "rewards/accuracy_reward": 0.8475468158721924,
      "rewards/format_reward": 0.96875,
      "step": 310,
      "temperature": 1.0
    },
    {
      "all_correct": 0.625,
      "all_wrong": 0.0,
      "completion_length": 373.671875,
      "epoch": 0.009457486923731906,
      "grad_norm": 1.3122637558664003,
      "kl": 0.0247802734375,
      "learning_rate": 9.997793218654834e-07,
      "loss": 0.001,
      "reward": 1.9734376668930054,
      "reward_std": 0.19686976075172424,
      "rewards/accuracy_reward": 0.8140624761581421,
      "rewards/format_reward": 1.0,
      "step": 311,
      "temperature": 1.0
    },
    {
      "all_correct": 0.625,
      "all_wrong": 0.125,
      "completion_length": 416.859375,
      "epoch": 0.009487896849531687,
      "grad_norm": 4.109287020477817,
      "kl": 0.0233154296875,
      "learning_rate": 9.997779005371407e-07,
      "loss": 0.0009,
      "reward": 1.9256929159164429,
      "reward_std": 0.06598345935344696,
      "rewards/accuracy_reward": 0.7819429039955139,
      "rewards/format_reward": 1.0,
      "step": 312,
      "temperature": 1.0
    },
    {
      "all_correct": 0.25,
      "all_wrong": 0.0,
      "completion_length": 424.21875,
      "epoch": 0.009518306775331468,
      "grad_norm": 1.8737314780510137,
      "kl": 0.0205078125,
      "learning_rate": 9.997764746472996e-07,
      "loss": 0.0008,
      "reward": 1.8117625713348389,
      "reward_std": 0.3156144320964813,
      "rewards/accuracy_reward": 0.664887547492981,
      "rewards/format_reward": 1.0,
      "step": 313,
      "temperature": 1.0
    },
    {
      "all_correct": 0.625,
      "all_wrong": 0.0,
      "completion_length": 399.59375,
      "epoch": 0.009548716701131249,
      "grad_norm": 1.7064761384703606,
      "kl": 0.0250244140625,
      "learning_rate": 9.997750441959734e-07,
      "loss": 0.001,
      "reward": 1.916944980621338,
      "reward_std": 0.14504948258399963,
      "rewards/accuracy_reward": 0.7700700163841248,
      "rewards/format_reward": 1.0,
      "step": 314,
      "temperature": 1.0
    },
    {
      "all_correct": 0.25,
      "all_wrong": 0.25,
      "completion_length": 375.734375,
      "epoch": 0.00957912662693103,
      "grad_norm": 1.1583862872424482,
      "kl": 0.0242919921875,
      "learning_rate": 9.99773609183175e-07,
      "loss": 0.001,
      "reward": 1.4302083253860474,
      "reward_std": 0.17158865928649902,
      "rewards/accuracy_reward": 0.3645833432674408,
      "rewards/format_reward": 1.0,
      "step": 315,
      "temperature": 1.0
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.0,
      "completion_length": 392.671875,
      "epoch": 0.009609536552730811,
      "grad_norm": 1.043983484483266,
      "kl": 0.0185546875,
      "learning_rate": 9.997721696089173e-07,
      "loss": 0.0007,
      "reward": 1.8526010513305664,
      "reward_std": 0.25343698263168335,
      "rewards/accuracy_reward": 0.7088510394096375,
      "rewards/format_reward": 1.0,
      "step": 316,
      "temperature": 1.0
    },
    {
      "all_correct": 0.75,
      "all_wrong": 0.0,
      "completion_length": 379.34375,
      "epoch": 0.009639946478530592,
      "grad_norm": 1.2435685205190956,
      "kl": 0.024169921875,
      "learning_rate": 9.997707254732137e-07,
      "loss": 0.001,
      "reward": 2.0125956535339355,
      "reward_std": 0.08711028099060059,
      "rewards/accuracy_reward": 0.8625956177711487,
      "rewards/format_reward": 1.0,
      "step": 317,
      "temperature": 1.0
    },
    {
      "all_correct": 0.25,
      "all_wrong": 0.0,
      "completion_length": 420.453125,
      "epoch": 0.009670356404330373,
      "grad_norm": 1.2073808849375935,
      "kl": 0.0191650390625,
      "learning_rate": 9.997692767760773e-07,
      "loss": 0.0008,
      "reward": 1.483243465423584,
      "reward_std": 0.22430793941020966,
      "rewards/accuracy_reward": 0.38949358463287354,
      "rewards/format_reward": 1.0,
      "step": 318,
      "temperature": 1.0
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.0,
      "completion_length": 414.921875,
      "epoch": 0.009700766330130154,
      "grad_norm": 1.7543338198623577,
      "kl": 0.01458740234375,
      "learning_rate": 9.997678235175215e-07,
      "loss": 0.0006,
      "reward": 2.0304794311523438,
      "reward_std": 0.15252670645713806,
      "rewards/accuracy_reward": 0.8648544549942017,
      "rewards/format_reward": 1.0,
      "step": 319,
      "temperature": 1.0
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.25,
      "completion_length": 394.359375,
      "epoch": 0.009731176255929936,
      "grad_norm": 1.1622687202292914,
      "kl": 0.0203857421875,
      "learning_rate": 9.997663656975592e-07,
      "loss": 0.0008,
      "reward": 1.6910561323165894,
      "reward_std": 0.03899677097797394,
      "rewards/accuracy_reward": 0.5723061561584473,
      "rewards/format_reward": 1.0,
      "step": 320,
      "temperature": 1.0
    },
    {
      "all_correct": 0.75,
      "all_wrong": 0.125,
      "completion_length": 398.734375,
      "epoch": 0.009761586181729717,
      "grad_norm": 0.978334555688099,
      "kl": 0.01904296875,
      "learning_rate": 9.997649033162042e-07,
      "loss": 0.0008,
      "reward": 1.9593749046325684,
      "reward_std": 0.11948156356811523,
      "rewards/accuracy_reward": 0.828125,
      "rewards/format_reward": 1.0,
      "step": 321,
      "temperature": 1.0
    },
    {
      "all_correct": 0.375,
      "all_wrong": 0.25,
      "completion_length": 370.0625,
      "epoch": 0.009791996107529498,
      "grad_norm": 1.3129654251741718,
      "kl": 0.021484375,
      "learning_rate": 9.997634363734692e-07,
      "loss": 0.0009,
      "reward": 1.6187500953674316,
      "reward_std": 0.21988226473331451,
      "rewards/accuracy_reward": 0.53125,
      "rewards/format_reward": 1.0,
      "step": 322,
      "temperature": 1.0
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.125,
      "completion_length": 395.53125,
      "epoch": 0.009822406033329279,
      "grad_norm": 2.10137825726634,
      "kl": 0.0247802734375,
      "learning_rate": 9.997619648693682e-07,
      "loss": 0.001,
      "reward": 1.8324732780456543,
      "reward_std": 0.17295102775096893,
      "rewards/accuracy_reward": 0.6949732303619385,
      "rewards/format_reward": 1.0,
      "step": 323,
      "temperature": 1.0
    },
    {
      "all_correct": 0.625,
      "all_wrong": 0.0,
      "completion_length": 424.796875,
      "epoch": 0.00985281595912906,
      "grad_norm": 1.2091792124021508,
      "kl": 0.0169677734375,
      "learning_rate": 9.997604888039145e-07,
      "loss": 0.0007,
      "reward": 1.9597744941711426,
      "reward_std": 0.07805581390857697,
      "rewards/accuracy_reward": 0.8097744584083557,
      "rewards/format_reward": 1.0,
      "step": 324,
      "temperature": 1.0
    },
    {
      "all_correct": 0.25,
      "all_wrong": 0.0,
      "completion_length": 468.359375,
      "epoch": 0.009883225884928841,
      "grad_norm": 1.470298354998882,
      "kl": 0.01531982421875,
      "learning_rate": 9.99759008177121e-07,
      "loss": 0.0006,
      "reward": 1.7124056816101074,
      "reward_std": 0.17168018221855164,
      "rewards/accuracy_reward": 0.5780308246612549,
      "rewards/format_reward": 0.984375,
      "step": 325,
      "temperature": 1.0
    },
    {
      "all_correct": 0.625,
      "all_wrong": 0.125,
      "completion_length": 359.046875,
      "epoch": 0.009913635810728622,
      "grad_norm": 1.4401498106282375,
      "kl": 0.0263671875,
      "learning_rate": 9.99757522989002e-07,
      "loss": 0.0011,
      "reward": 1.896331548690796,
      "reward_std": 0.16039817035198212,
      "rewards/accuracy_reward": 0.7588316202163696,
      "rewards/format_reward": 1.0,
      "step": 326,
      "temperature": 1.0
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.0,
      "completion_length": 369.09375,
      "epoch": 0.009944045736528403,
      "grad_norm": 1.4028236008621378,
      "kl": 0.0242919921875,
      "learning_rate": 9.997560332395708e-07,
      "loss": 0.001,
      "reward": 1.8496155738830566,
      "reward_std": 0.17857444286346436,
      "rewards/accuracy_reward": 0.7121155858039856,
      "rewards/format_reward": 1.0,
      "step": 327,
      "temperature": 1.0
    },
    {
      "all_correct": 0.375,
      "all_wrong": 0.125,
      "completion_length": 413.84375,
      "epoch": 0.009974455662328184,
      "grad_norm": 1.5576510603963416,
      "kl": 0.019775390625,
      "learning_rate": 9.997545389288406e-07,
      "loss": 0.0008,
      "reward": 1.7248263359069824,
      "reward_std": 0.1685350239276886,
      "rewards/accuracy_reward": 0.5998262166976929,
      "rewards/format_reward": 1.0,
      "step": 328,
      "temperature": 1.0
    },
    {
      "all_correct": 0.375,
      "all_wrong": 0.25,
      "completion_length": 390.234375,
      "epoch": 0.010004865588127965,
      "grad_norm": 0.9574485456894085,
      "kl": 0.0191650390625,
      "learning_rate": 9.997530400568254e-07,
      "loss": 0.0008,
      "reward": 1.6866984367370605,
      "reward_std": 0.12370496988296509,
      "rewards/accuracy_reward": 0.5523233413696289,
      "rewards/format_reward": 1.0,
      "step": 329,
      "temperature": 1.0
    },
    {
      "all_correct": 0.875,
      "all_wrong": 0.0,
      "completion_length": 385.109375,
      "epoch": 0.010035275513927746,
      "grad_norm": 0.9200797909039734,
      "kl": 0.0262451171875,
      "learning_rate": 9.99751536623539e-07,
      "loss": 0.0011,
      "reward": 2.0815439224243164,
      "reward_std": 0.03328409790992737,
      "rewards/accuracy_reward": 0.9034188389778137,
      "rewards/format_reward": 1.0,
      "step": 330,
      "temperature": 1.0
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.375,
      "completion_length": 359.296875,
      "epoch": 0.010065685439727527,
      "grad_norm": 0.5969029669857804,
      "kl": 0.027099609375,
      "learning_rate": 9.99750028628995e-07,
      "loss": 0.0011,
      "reward": 1.6343750953674316,
      "reward_std": 0.07827534526586533,
      "rewards/accuracy_reward": 0.53125,
      "rewards/format_reward": 1.0,
      "step": 331,
      "temperature": 1.0
    },
    {
      "all_correct": 0.125,
      "all_wrong": 0.125,
      "completion_length": 434.65625,
      "epoch": 0.010096095365527307,
      "grad_norm": 1.3629394053333748,
      "kl": 0.018310546875,
      "learning_rate": 9.997485160732069e-07,
      "loss": 0.0007,
      "reward": 1.4190571308135986,
      "reward_std": 0.19542253017425537,
      "rewards/accuracy_reward": 0.32218223810195923,
      "rewards/format_reward": 1.0,
      "step": 332,
      "temperature": 1.0
    },
    {
      "all_correct": 0.75,
      "all_wrong": 0.0,
      "completion_length": 366.75,
      "epoch": 0.010126505291327088,
      "grad_norm": 1.5797602130890627,
      "kl": 0.0220947265625,
      "learning_rate": 9.997469989561888e-07,
      "loss": 0.0009,
      "reward": 2.048142910003662,
      "reward_std": 0.0324062705039978,
      "rewards/accuracy_reward": 0.8512676954269409,
      "rewards/format_reward": 1.0,
      "step": 333,
      "temperature": 1.0
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.0,
      "completion_length": 382.375,
      "epoch": 0.010156915217126871,
      "grad_norm": 1.0092773286353647,
      "kl": 0.0205078125,
      "learning_rate": 9.997454772779548e-07,
      "loss": 0.0008,
      "reward": 1.8166532516479492,
      "reward_std": 0.23889750242233276,
      "rewards/accuracy_reward": 0.6729031801223755,
      "rewards/format_reward": 1.0,
      "step": 334,
      "temperature": 1.0
    },
    {
      "all_correct": 0.25,
      "all_wrong": 0.0,
      "completion_length": 399.84375,
      "epoch": 0.010187325142926652,
      "grad_norm": 2.470337565938291,
      "kl": 0.0179443359375,
      "learning_rate": 9.99743951038518e-07,
      "loss": 0.0007,
      "reward": 1.7218533754348755,
      "reward_std": 0.32006701827049255,
      "rewards/accuracy_reward": 0.5968533754348755,
      "rewards/format_reward": 1.0,
      "step": 335,
      "temperature": 1.0
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.125,
      "completion_length": 389.3125,
      "epoch": 0.010217735068726433,
      "grad_norm": 3.1610778618689848,
      "kl": 0.0260009765625,
      "learning_rate": 9.99742420237893e-07,
      "loss": 0.001,
      "reward": 1.7296210527420044,
      "reward_std": 0.15104272961616516,
      "rewards/accuracy_reward": 0.6108710169792175,
      "rewards/format_reward": 1.0,
      "step": 336,
      "temperature": 1.0
    },
    {
      "all_correct": 0.25,
      "all_wrong": 0.0,
      "completion_length": 391.421875,
      "epoch": 0.010248144994526214,
      "grad_norm": 1.6150632585954299,
      "kl": 0.0244140625,
      "learning_rate": 9.997408848760936e-07,
      "loss": 0.001,
      "reward": 1.8327126502990723,
      "reward_std": 0.30116862058639526,
      "rewards/accuracy_reward": 0.6858375072479248,
      "rewards/format_reward": 1.0,
      "step": 337,
      "temperature": 1.0
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.0,
      "completion_length": 386.25,
      "epoch": 0.010278554920325995,
      "grad_norm": 1.3024991197748887,
      "kl": 0.0281982421875,
      "learning_rate": 9.997393449531337e-07,
      "loss": 0.0011,
      "reward": 1.9110532999038696,
      "reward_std": 0.15766188502311707,
      "rewards/accuracy_reward": 0.7516781687736511,
      "rewards/format_reward": 1.0,
      "step": 338,
      "temperature": 1.0
    },
    {
      "all_correct": 0.625,
      "all_wrong": 0.0,
      "completion_length": 431.671875,
      "epoch": 0.010308964846125776,
      "grad_norm": 0.8607159669595827,
      "kl": 0.0218505859375,
      "learning_rate": 9.997378004690274e-07,
      "loss": 0.0009,
      "reward": 2.0114333629608154,
      "reward_std": 0.15601055324077606,
      "rewards/accuracy_reward": 0.8676832318305969,
      "rewards/format_reward": 1.0,
      "step": 339,
      "temperature": 1.0
    },
    {
      "all_correct": 0.75,
      "all_wrong": 0.0,
      "completion_length": 376.3125,
      "epoch": 0.010339374771925557,
      "grad_norm": 2.3863769002162916,
      "kl": 0.027099609375,
      "learning_rate": 9.997362514237888e-07,
      "loss": 0.0011,
      "reward": 2.0123977661132812,
      "reward_std": 0.0494222529232502,
      "rewards/accuracy_reward": 0.8405227661132812,
      "rewards/format_reward": 1.0,
      "step": 340,
      "temperature": 1.0
    },
    {
      "all_correct": 0.625,
      "all_wrong": 0.25,
      "completion_length": 375.75,
      "epoch": 0.010369784697725338,
      "grad_norm": 1.8138844938133896,
      "kl": 0.0284423828125,
      "learning_rate": 9.997346978174322e-07,
      "loss": 0.0011,
      "reward": 1.8250000476837158,
      "reward_std": 0.08017837256193161,
      "rewards/accuracy_reward": 0.6875,
      "rewards/format_reward": 1.0,
      "step": 341,
      "temperature": 1.0
    },
    {
      "all_correct": 0.125,
      "all_wrong": 0.0,
      "completion_length": 417.328125,
      "epoch": 0.010400194623525118,
      "grad_norm": 1.4936494375604366,
      "kl": 0.02099609375,
      "learning_rate": 9.997331396499716e-07,
      "loss": 0.0008,
      "reward": 1.6359374523162842,
      "reward_std": 0.24820901453495026,
      "rewards/accuracy_reward": 0.48281240463256836,
      "rewards/format_reward": 1.0,
      "step": 342,
      "temperature": 1.0
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.0,
      "completion_length": 382.6875,
      "epoch": 0.0104306045493249,
      "grad_norm": 1.656477444273406,
      "kl": 0.022216796875,
      "learning_rate": 9.997315769214212e-07,
      "loss": 0.0009,
      "reward": 1.8265624046325684,
      "reward_std": 0.24232600629329681,
      "rewards/accuracy_reward": 0.6796874403953552,
      "rewards/format_reward": 1.0,
      "step": 343,
      "temperature": 1.0
    },
    {
      "all_correct": 0.625,
      "all_wrong": 0.125,
      "completion_length": 376.859375,
      "epoch": 0.01046101447512468,
      "grad_norm": 1.6049510398086544,
      "kl": 0.0281982421875,
      "learning_rate": 9.997300096317954e-07,
      "loss": 0.0011,
      "reward": 1.8283483982086182,
      "reward_std": 0.08479934930801392,
      "rewards/accuracy_reward": 0.6908482313156128,
      "rewards/format_reward": 1.0,
      "step": 344,
      "temperature": 1.0
    },
    {
      "all_correct": 0.75,
      "all_wrong": 0.0,
      "completion_length": 379.4375,
      "epoch": 0.010491424400924461,
      "grad_norm": 1.4004504887545426,
      "kl": 0.0240478515625,
      "learning_rate": 9.997284377811084e-07,
      "loss": 0.001,
      "reward": 2.0796875953674316,
      "reward_std": 0.1020514965057373,
      "rewards/accuracy_reward": 0.8984375,
      "rewards/format_reward": 1.0,
      "step": 345,
      "temperature": 1.0
    },
    {
      "all_correct": 0.375,
      "all_wrong": 0.25,
      "completion_length": 377.40625,
      "epoch": 0.010521834326724242,
      "grad_norm": 0.7153849752855842,
      "kl": 0.0191650390625,
      "learning_rate": 9.997268613693746e-07,
      "loss": 0.0008,
      "reward": 1.6875001192092896,
      "reward_std": 0.17433080077171326,
      "rewards/accuracy_reward": 0.578125,
      "rewards/format_reward": 1.0,
      "step": 346,
      "temperature": 1.0
    },
    {
      "all_correct": 0.625,
      "all_wrong": 0.0,
      "completion_length": 389.78125,
      "epoch": 0.010552244252524023,
      "grad_norm": 0.9256000342917721,
      "kl": 0.023681640625,
      "learning_rate": 9.997252803966083e-07,
      "loss": 0.0009,
      "reward": 1.892232060432434,
      "reward_std": 0.13832026720046997,
      "rewards/accuracy_reward": 0.7422319650650024,
      "rewards/format_reward": 1.0,
      "step": 347,
      "temperature": 1.0
    },
    {
      "all_correct": 0.625,
      "all_wrong": 0.0,
      "completion_length": 399.59375,
      "epoch": 0.010582654178323806,
      "grad_norm": 0.8294889522002576,
      "kl": 0.021240234375,
      "learning_rate": 9.99723694862824e-07,
      "loss": 0.0009,
      "reward": 1.9756220579147339,
      "reward_std": 0.11665228009223938,
      "rewards/accuracy_reward": 0.7974969744682312,
      "rewards/format_reward": 1.0,
      "step": 348,
      "temperature": 1.0
    },
    {
      "all_correct": 0.75,
      "all_wrong": 0.0,
      "completion_length": 382.859375,
      "epoch": 0.010613064104123587,
      "grad_norm": 0.9378216077644611,
      "kl": 0.02734375,
      "learning_rate": 9.997221047680362e-07,
      "loss": 0.0011,
      "reward": 2.0281248092651367,
      "reward_std": 0.1600036919116974,
      "rewards/accuracy_reward": 0.875,
      "rewards/format_reward": 1.0,
      "step": 349,
      "temperature": 1.0
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.125,
      "completion_length": 417.171875,
      "epoch": 0.010643474029923368,
      "grad_norm": 0.6503517655191055,
      "kl": 0.0208740234375,
      "learning_rate": 9.997205101122594e-07,
      "loss": 0.0008,
      "reward": 1.8544048070907593,
      "reward_std": 0.14091598987579346,
      "rewards/accuracy_reward": 0.7169046401977539,
      "rewards/format_reward": 1.0,
      "step": 350,
      "temperature": 1.0
    },
    {
      "all_correct": 0.375,
      "all_wrong": 0.0,
      "completion_length": 421.921875,
      "epoch": 0.010673883955723149,
      "grad_norm": 1.050949439707556,
      "kl": 0.02001953125,
      "learning_rate": 9.997189108955081e-07,
      "loss": 0.0008,
      "reward": 1.70163893699646,
      "reward_std": 0.29886701703071594,
      "rewards/accuracy_reward": 0.6078888773918152,
      "rewards/format_reward": 0.984375,
      "step": 351,
      "temperature": 1.0
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.125,
      "completion_length": 391.34375,
      "epoch": 0.01070429388152293,
      "grad_norm": 1.3003666008893664,
      "kl": 0.025390625,
      "learning_rate": 9.99717307117797e-07,
      "loss": 0.001,
      "reward": 1.7807180881500244,
      "reward_std": 0.12660560011863708,
      "rewards/accuracy_reward": 0.649468183517456,
      "rewards/format_reward": 1.0,
      "step": 352,
      "temperature": 1.0
    },
    {
      "all_correct": 0.375,
      "all_wrong": 0.0,
      "completion_length": 385.890625,
      "epoch": 0.01073470380732271,
      "grad_norm": 1.5194493284569137,
      "kl": 0.02783203125,
      "learning_rate": 9.997156987791406e-07,
      "loss": 0.0011,
      "reward": 1.8250924348831177,
      "reward_std": 0.23386509716510773,
      "rewards/accuracy_reward": 0.693842351436615,
      "rewards/format_reward": 1.0,
      "step": 353,
      "temperature": 1.0
    },
    {
      "all_correct": 0.375,
      "all_wrong": 0.25,
      "completion_length": 404.515625,
      "epoch": 0.010765113733122491,
      "grad_norm": 0.9493138487580918,
      "kl": 0.020751953125,
      "learning_rate": 9.997140858795538e-07,
      "loss": 0.0008,
      "reward": 1.6468260288238525,
      "reward_std": 0.08402933180332184,
      "rewards/accuracy_reward": 0.5187010765075684,
      "rewards/format_reward": 1.0,
      "step": 354,
      "temperature": 1.0
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.25,
      "completion_length": 368.328125,
      "epoch": 0.010795523658922272,
      "grad_norm": 3.903013956535791,
      "kl": 0.02783203125,
      "learning_rate": 9.997124684190512e-07,
      "loss": 0.0011,
      "reward": 1.6581554412841797,
      "reward_std": 0.08747033774852753,
      "rewards/accuracy_reward": 0.5550304055213928,
      "rewards/format_reward": 1.0,
      "step": 355,
      "temperature": 1.0
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.0,
      "completion_length": 389.890625,
      "epoch": 0.010825933584722053,
      "grad_norm": 1.2268900661624917,
      "kl": 0.0213623046875,
      "learning_rate": 9.997108463976473e-07,
      "loss": 0.0009,
      "reward": 1.7474215030670166,
      "reward_std": 0.1925657093524933,
      "rewards/accuracy_reward": 0.6192964315414429,
      "rewards/format_reward": 1.0,
      "step": 356,
      "temperature": 1.0
    },
    {
      "all_correct": 0.625,
      "all_wrong": 0.0,
      "completion_length": 384.9375,
      "epoch": 0.010856343510521834,
      "grad_norm": 0.9530083357359483,
      "kl": 0.0189208984375,
      "learning_rate": 9.997092198153571e-07,
      "loss": 0.0008,
      "reward": 1.9738308191299438,
      "reward_std": 0.08408787846565247,
      "rewards/accuracy_reward": 0.7988307476043701,
      "rewards/format_reward": 1.0,
      "step": 357,
      "temperature": 1.0
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.0,
      "completion_length": 397.875,
      "epoch": 0.010886753436321615,
      "grad_norm": 1.58182358242398,
      "kl": 0.023193359375,
      "learning_rate": 9.997075886721957e-07,
      "loss": 0.0009,
      "reward": 1.8325740098953247,
      "reward_std": 0.15860262513160706,
      "rewards/accuracy_reward": 0.6856989860534668,
      "rewards/format_reward": 1.0,
      "step": 358,
      "temperature": 1.0
    },
    {
      "all_correct": 0.625,
      "all_wrong": 0.125,
      "completion_length": 376.96875,
      "epoch": 0.010917163362121396,
      "grad_norm": 1.2671627397589489,
      "kl": 0.0224609375,
      "learning_rate": 9.997059529681776e-07,
      "loss": 0.0009,
      "reward": 1.828125,
      "reward_std": 0.11202043294906616,
      "rewards/accuracy_reward": 0.684374988079071,
      "rewards/format_reward": 1.0,
      "step": 359,
      "temperature": 1.0
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.0,
      "completion_length": 412.859375,
      "epoch": 0.010947573287921177,
      "grad_norm": 1.0842802704398273,
      "kl": 0.018310546875,
      "learning_rate": 9.99704312703318e-07,
      "loss": 0.0007,
      "reward": 1.8854668140411377,
      "reward_std": 0.08531834185123444,
      "rewards/accuracy_reward": 0.7167167663574219,
      "rewards/format_reward": 1.0,
      "step": 360,
      "temperature": 1.0
    },
    {
      "all_correct": 0.75,
      "all_wrong": 0.125,
      "completion_length": 366.734375,
      "epoch": 0.010977983213720958,
      "grad_norm": 1.1785682686143464,
      "kl": 0.0242919921875,
      "learning_rate": 9.99702667877632e-07,
      "loss": 0.001,
      "reward": 2.0142135620117188,
      "reward_std": 0.07085821777582169,
      "rewards/accuracy_reward": 0.8548387289047241,
      "rewards/format_reward": 1.0,
      "step": 361,
      "temperature": 1.0
    },
    {
      "all_correct": 0.625,
      "all_wrong": 0.0,
      "completion_length": 443.515625,
      "epoch": 0.011008393139520739,
      "grad_norm": 0.7952036734766956,
      "kl": 0.017578125,
      "learning_rate": 9.99701018491134e-07,
      "loss": 0.0007,
      "reward": 1.9316582679748535,
      "reward_std": 0.09770317375659943,
      "rewards/accuracy_reward": 0.7660331130027771,
      "rewards/format_reward": 1.0,
      "step": 362,
      "temperature": 1.0
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.125,
      "completion_length": 384.125,
      "epoch": 0.011038803065320521,
      "grad_norm": 1.0050400149275307,
      "kl": 0.0218505859375,
      "learning_rate": 9.996993645438396e-07,
      "loss": 0.0009,
      "reward": 1.9343750476837158,
      "reward_std": 0.19957314431667328,
      "rewards/accuracy_reward": 0.78125,
      "rewards/format_reward": 1.0,
      "step": 363,
      "temperature": 1.0
    },
    {
      "all_correct": 0.625,
      "all_wrong": 0.125,
      "completion_length": 423.703125,
      "epoch": 0.011069212991120302,
      "grad_norm": 0.7840730194261892,
      "kl": 0.0181884765625,
      "learning_rate": 9.996977060357637e-07,
      "loss": 0.0007,
      "reward": 1.7778847217559814,
      "reward_std": 0.17245075106620789,
      "rewards/accuracy_reward": 0.677884578704834,
      "rewards/format_reward": 0.96875,
      "step": 364,
      "temperature": 1.0
    },
    {
      "all_correct": 0.625,
      "all_wrong": 0.0,
      "completion_length": 367.078125,
      "epoch": 0.011099622916920083,
      "grad_norm": 1.4423948934019022,
      "kl": 0.0242919921875,
      "learning_rate": 9.996960429669215e-07,
      "loss": 0.001,
      "reward": 2.010911464691162,
      "reward_std": 0.10332072526216507,
      "rewards/accuracy_reward": 0.8296614289283752,
      "rewards/format_reward": 1.0,
      "step": 365,
      "temperature": 1.0
    },
    {
      "all_correct": 0.25,
      "all_wrong": 0.0,
      "completion_length": 410.140625,
      "epoch": 0.011130032842719864,
      "grad_norm": 1.3013899508472213,
      "kl": 0.0185546875,
      "learning_rate": 9.99694375337328e-07,
      "loss": 0.0007,
      "reward": 1.6582443714141846,
      "reward_std": 0.1563914716243744,
      "rewards/accuracy_reward": 0.5051193833351135,
      "rewards/format_reward": 1.0,
      "step": 366,
      "temperature": 1.0
    },
    {
      "all_correct": 0.375,
      "all_wrong": 0.125,
      "completion_length": 397.0,
      "epoch": 0.011160442768519645,
      "grad_norm": 3.4850421876109796,
      "kl": 0.024169921875,
      "learning_rate": 9.996927031469988e-07,
      "loss": 0.001,
      "reward": 1.6948763132095337,
      "reward_std": 0.13153031468391418,
      "rewards/accuracy_reward": 0.55112624168396,
      "rewards/format_reward": 1.0,
      "step": 367,
      "temperature": 1.0
    },
    {
      "all_correct": 0.375,
      "all_wrong": 0.125,
      "completion_length": 404.53125,
      "epoch": 0.011190852694319426,
      "grad_norm": 1.3760804113238818,
      "kl": 0.02099609375,
      "learning_rate": 9.99691026395949e-07,
      "loss": 0.0008,
      "reward": 1.8155430555343628,
      "reward_std": 0.1822381168603897,
      "rewards/accuracy_reward": 0.6624179482460022,
      "rewards/format_reward": 1.0,
      "step": 368,
      "temperature": 1.0
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.0,
      "completion_length": 405.78125,
      "epoch": 0.011221262620119207,
      "grad_norm": 1.4806080781566082,
      "kl": 0.025634765625,
      "learning_rate": 9.996893450841937e-07,
      "loss": 0.001,
      "reward": 1.8327884674072266,
      "reward_std": 0.13730138540267944,
      "rewards/accuracy_reward": 0.6827883124351501,
      "rewards/format_reward": 1.0,
      "step": 369,
      "temperature": 1.0
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.0,
      "completion_length": 398.5,
      "epoch": 0.011251672545918988,
      "grad_norm": 1.2268312466231384,
      "kl": 0.020751953125,
      "learning_rate": 9.996876592117482e-07,
      "loss": 0.0008,
      "reward": 1.7721421718597412,
      "reward_std": 0.09305316209793091,
      "rewards/accuracy_reward": 0.6252670288085938,
      "rewards/format_reward": 1.0,
      "step": 370,
      "temperature": 1.0
    },
    {
      "all_correct": 0.375,
      "all_wrong": 0.125,
      "completion_length": 391.734375,
      "epoch": 0.011282082471718769,
      "grad_norm": 1.1203238277974892,
      "kl": 0.0260009765625,
      "learning_rate": 9.996859687786283e-07,
      "loss": 0.001,
      "reward": 1.7975209951400757,
      "reward_std": 0.07121521234512329,
      "rewards/accuracy_reward": 0.6443960070610046,
      "rewards/format_reward": 1.0,
      "step": 371,
      "temperature": 1.0
    },
    {
      "all_correct": 0.375,
      "all_wrong": 0.25,
      "completion_length": 456.015625,
      "epoch": 0.01131249239751855,
      "grad_norm": 0.7459272316525624,
      "kl": 0.0194091796875,
      "learning_rate": 9.996842737848492e-07,
      "loss": 0.0008,
      "reward": 1.6215076446533203,
      "reward_std": 0.15464895963668823,
      "rewards/accuracy_reward": 0.5621325969696045,
      "rewards/format_reward": 0.953125,
      "step": 372,
      "temperature": 1.0
    },
    {
      "all_correct": 0.625,
      "all_wrong": 0.125,
      "completion_length": 398.9375,
      "epoch": 0.01134290232331833,
      "grad_norm": 0.7493862450152716,
      "kl": 0.0242919921875,
      "learning_rate": 9.996825742304262e-07,
      "loss": 0.001,
      "reward": 1.8313472270965576,
      "reward_std": 0.05798782408237457,
      "rewards/accuracy_reward": 0.6969722509384155,
      "rewards/format_reward": 1.0,
      "step": 373,
      "temperature": 1.0
    },
    {
      "all_correct": 0.625,
      "all_wrong": 0.0,
      "completion_length": 396.140625,
      "epoch": 0.011373312249118112,
      "grad_norm": 0.9609906093811658,
      "kl": 0.02392578125,
      "learning_rate": 9.996808701153752e-07,
      "loss": 0.001,
      "reward": 1.934267282485962,
      "reward_std": 0.17643608152866364,
      "rewards/accuracy_reward": 0.7717671990394592,
      "rewards/format_reward": 1.0,
      "step": 374,
      "temperature": 1.0
    },
    {
      "all_correct": 0.0,
      "all_wrong": 0.375,
      "completion_length": 399.515625,
      "epoch": 0.011403722174917892,
      "grad_norm": 1.2941091441374422,
      "kl": 0.0234375,
      "learning_rate": 9.996791614397114e-07,
      "loss": 0.0009,
      "reward": 1.3692656755447388,
      "reward_std": 0.20688988268375397,
      "rewards/accuracy_reward": 0.3130156397819519,
      "rewards/format_reward": 1.0,
      "step": 375,
      "temperature": 1.0
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.0,
      "completion_length": 394.078125,
      "epoch": 0.011434132100717673,
      "grad_norm": 1.2065358317355055,
      "kl": 0.0252685546875,
      "learning_rate": 9.996774482034504e-07,
      "loss": 0.001,
      "reward": 1.7968661785125732,
      "reward_std": 0.19386743009090424,
      "rewards/accuracy_reward": 0.6562411785125732,
      "rewards/format_reward": 1.0,
      "step": 376,
      "temperature": 1.0
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.125,
      "completion_length": 398.765625,
      "epoch": 0.011464542026517456,
      "grad_norm": 0.7803615770999071,
      "kl": 0.02099609375,
      "learning_rate": 9.996757304066082e-07,
      "loss": 0.0008,
      "reward": 1.9000000953674316,
      "reward_std": 0.1769564002752304,
      "rewards/accuracy_reward": 0.765625,
      "rewards/format_reward": 1.0,
      "step": 377,
      "temperature": 1.0
    },
    {
      "all_correct": 0.625,
      "all_wrong": 0.125,
      "completion_length": 368.890625,
      "epoch": 0.011494951952317237,
      "grad_norm": 1.0723777077267151,
      "kl": 0.03173828125,
      "learning_rate": 9.996740080492e-07,
      "loss": 0.0013,
      "reward": 1.9687501192092896,
      "reward_std": 0.13897547125816345,
      "rewards/accuracy_reward": 0.8125,
      "rewards/format_reward": 1.0,
      "step": 378,
      "temperature": 1.0
    },
    {
      "all_correct": 0.625,
      "all_wrong": 0.0,
      "completion_length": 377.515625,
      "epoch": 0.011525361878117018,
      "grad_norm": 1.3345379575740723,
      "kl": 0.0255126953125,
      "learning_rate": 9.996722811312421e-07,
      "loss": 0.001,
      "reward": 1.8573659658432007,
      "reward_std": 0.13177335262298584,
      "rewards/accuracy_reward": 0.7073659300804138,
      "rewards/format_reward": 1.0,
      "step": 379,
      "temperature": 1.0
    },
    {
      "all_correct": 0.625,
      "all_wrong": 0.125,
      "completion_length": 392.296875,
      "epoch": 0.011555771803916799,
      "grad_norm": 0.9948255629135296,
      "kl": 0.0247802734375,
      "learning_rate": 9.996705496527498e-07,
      "loss": 0.001,
      "reward": 1.844771385192871,
      "reward_std": 0.11077163368463516,
      "rewards/accuracy_reward": 0.7041463851928711,
      "rewards/format_reward": 1.0,
      "step": 380,
      "temperature": 1.0
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.0,
      "completion_length": 397.171875,
      "epoch": 0.01158618172971658,
      "grad_norm": 1.529416177804708,
      "kl": 0.026123046875,
      "learning_rate": 9.996688136137389e-07,
      "loss": 0.001,
      "reward": 1.8979039192199707,
      "reward_std": 0.11607788503170013,
      "rewards/accuracy_reward": 0.7166540026664734,
      "rewards/format_reward": 1.0,
      "step": 381,
      "temperature": 1.0
    },
    {
      "all_correct": 0.625,
      "all_wrong": 0.125,
      "completion_length": 379.0,
      "epoch": 0.01161659165551636,
      "grad_norm": 1.0169282213750153,
      "kl": 0.021240234375,
      "learning_rate": 9.996670730142253e-07,
      "loss": 0.0008,
      "reward": 1.9374959468841553,
      "reward_std": 0.08553895354270935,
      "rewards/accuracy_reward": 0.7718709707260132,
      "rewards/format_reward": 1.0,
      "step": 382,
      "temperature": 1.0
    },
    {
      "all_correct": 0.625,
      "all_wrong": 0.0,
      "completion_length": 393.03125,
      "epoch": 0.011647001581316142,
      "grad_norm": 3.0262990016823834,
      "kl": 0.0169677734375,
      "learning_rate": 9.996653278542252e-07,
      "loss": 0.0007,
      "reward": 1.9877909421920776,
      "reward_std": 0.17407485842704773,
      "rewards/accuracy_reward": 0.8284158706665039,
      "rewards/format_reward": 1.0,
      "step": 383,
      "temperature": 1.0
    },
    {
      "all_correct": 0.625,
      "all_wrong": 0.125,
      "completion_length": 367.140625,
      "epoch": 0.011677411507115923,
      "grad_norm": 0.8052365679051469,
      "kl": 0.0234375,
      "learning_rate": 9.99663578133754e-07,
      "loss": 0.0009,
      "reward": 1.8718750476837158,
      "reward_std": 0.13130834698677063,
      "rewards/accuracy_reward": 0.734375,
      "rewards/format_reward": 1.0,
      "step": 384,
      "temperature": 1.0
    },
    {
      "all_correct": 0.375,
      "all_wrong": 0.125,
      "completion_length": 392.59375,
      "epoch": 0.011707821432915703,
      "grad_norm": 2.0517034069494704,
      "kl": 0.0184326171875,
      "learning_rate": 9.996618238528282e-07,
      "loss": 0.0007,
      "reward": 1.7625436782836914,
      "reward_std": 0.14881935715675354,
      "rewards/accuracy_reward": 0.6156686544418335,
      "rewards/format_reward": 1.0,
      "step": 385,
      "temperature": 1.0
    },
    {
      "all_correct": 0.625,
      "all_wrong": 0.25,
      "completion_length": 382.296875,
      "epoch": 0.011738231358715484,
      "grad_norm": 0.7977540648656763,
      "kl": 0.0255126953125,
      "learning_rate": 9.996600650114638e-07,
      "loss": 0.001,
      "reward": 1.8375000953674316,
      "reward_std": 0.08920513093471527,
      "rewards/accuracy_reward": 0.703125,
      "rewards/format_reward": 1.0,
      "step": 386,
      "temperature": 1.0
    },
    {
      "all_correct": 0.375,
      "all_wrong": 0.25,
      "completion_length": 396.5,
      "epoch": 0.011768641284515265,
      "grad_norm": 0.7601343344208239,
      "kl": 0.022216796875,
      "learning_rate": 9.996583016096763e-07,
      "loss": 0.0009,
      "reward": 1.6375000476837158,
      "reward_std": 0.20795778930187225,
      "rewards/accuracy_reward": 0.546875,
      "rewards/format_reward": 1.0,
      "step": 387,
      "temperature": 1.0
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.25,
      "completion_length": 398.609375,
      "epoch": 0.011799051210315046,
      "grad_norm": 1.1953722749572813,
      "kl": 0.025146484375,
      "learning_rate": 9.99656533647482e-07,
      "loss": 0.001,
      "reward": 1.6994366645812988,
      "reward_std": 0.07241673022508621,
      "rewards/accuracy_reward": 0.5744366645812988,
      "rewards/format_reward": 1.0,
      "step": 388,
      "temperature": 1.0
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.125,
      "completion_length": 401.328125,
      "epoch": 0.011829461136114827,
      "grad_norm": 0.8176248441056455,
      "kl": 0.0205078125,
      "learning_rate": 9.996547611248974e-07,
      "loss": 0.0008,
      "reward": 1.8029773235321045,
      "reward_std": 0.04074126109480858,
      "rewards/accuracy_reward": 0.6404772996902466,
      "rewards/format_reward": 1.0,
      "step": 389,
      "temperature": 1.0
    },
    {
      "all_correct": 0.25,
      "all_wrong": 0.125,
      "completion_length": 437.15625,
      "epoch": 0.011859871061914608,
      "grad_norm": 1.384536645365741,
      "kl": 0.0224609375,
      "learning_rate": 9.996529840419384e-07,
      "loss": 0.0009,
      "reward": 1.684781551361084,
      "reward_std": 0.14926466345787048,
      "rewards/accuracy_reward": 0.5441564321517944,
      "rewards/format_reward": 1.0,
      "step": 390,
      "temperature": 1.0
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.125,
      "completion_length": 349.1875,
      "epoch": 0.01189028098771439,
      "grad_norm": 1.6887365664547622,
      "kl": 0.02880859375,
      "learning_rate": 9.99651202398621e-07,
      "loss": 0.0012,
      "reward": 1.8038419485092163,
      "reward_std": 0.04790571331977844,
      "rewards/accuracy_reward": 0.6413419842720032,
      "rewards/format_reward": 1.0,
      "step": 391,
      "temperature": 1.0
    },
    {
      "all_correct": 0.625,
      "all_wrong": 0.125,
      "completion_length": 382.53125,
      "epoch": 0.011920690913514172,
      "grad_norm": 0.9981259372501113,
      "kl": 0.02978515625,
      "learning_rate": 9.99649416194962e-07,
      "loss": 0.0012,
      "reward": 1.868749976158142,
      "reward_std": 0.16536714136600494,
      "rewards/accuracy_reward": 0.734375,
      "rewards/format_reward": 1.0,
      "step": 392,
      "temperature": 1.0
    },
    {
      "all_correct": 0.625,
      "all_wrong": 0.0,
      "completion_length": 353.765625,
      "epoch": 0.011951100839313953,
      "grad_norm": 1.8448058299490133,
      "kl": 0.0260009765625,
      "learning_rate": 9.996476254309773e-07,
      "loss": 0.001,
      "reward": 2.0181920528411865,
      "reward_std": 0.11770347505807877,
      "rewards/accuracy_reward": 0.8588169813156128,
      "rewards/format_reward": 1.0,
      "step": 393,
      "temperature": 1.0
    },
    {
      "all_correct": 0.375,
      "all_wrong": 0.125,
      "completion_length": 400.84375,
      "epoch": 0.011981510765113734,
      "grad_norm": 1.4341111466534822,
      "kl": 0.0225830078125,
      "learning_rate": 9.996458301066835e-07,
      "loss": 0.0009,
      "reward": 1.7502045631408691,
      "reward_std": 0.2051336169242859,
      "rewards/accuracy_reward": 0.6220794916152954,
      "rewards/format_reward": 1.0,
      "step": 394,
      "temperature": 1.0
    },
    {
      "all_correct": 0.375,
      "all_wrong": 0.125,
      "completion_length": 371.28125,
      "epoch": 0.012011920690913514,
      "grad_norm": 2.315779754381853,
      "kl": 0.0264892578125,
      "learning_rate": 9.996440302220967e-07,
      "loss": 0.0011,
      "reward": 1.6628079414367676,
      "reward_std": 0.1338011622428894,
      "rewards/accuracy_reward": 0.5503078699111938,
      "rewards/format_reward": 1.0,
      "step": 395,
      "temperature": 1.0
    },
    {
      "all_correct": 0.625,
      "all_wrong": 0.25,
      "completion_length": 385.75,
      "epoch": 0.012042330616713295,
      "grad_norm": 0.49131978481123745,
      "kl": 0.0240478515625,
      "learning_rate": 9.996422257772335e-07,
      "loss": 0.001,
      "reward": 1.8250000476837158,
      "reward_std": 0.08017837256193161,
      "rewards/accuracy_reward": 0.6875,
      "rewards/format_reward": 1.0,
      "step": 396,
      "temperature": 1.0
    },
    {
      "all_correct": 0.375,
      "all_wrong": 0.0,
      "completion_length": 394.03125,
      "epoch": 0.012072740542513076,
      "grad_norm": 3.388649828030671,
      "kl": 0.0218505859375,
      "learning_rate": 9.996404167721101e-07,
      "loss": 0.0009,
      "reward": 1.9327692985534668,
      "reward_std": 0.1615990549325943,
      "rewards/accuracy_reward": 0.7577692270278931,
      "rewards/format_reward": 1.0,
      "step": 397,
      "temperature": 1.0
    },
    {
      "all_correct": 0.625,
      "all_wrong": 0.125,
      "completion_length": 361.90625,
      "epoch": 0.012103150468312857,
      "grad_norm": 9.815904613753887,
      "kl": 0.029296875,
      "learning_rate": 9.996386032067437e-07,
      "loss": 0.0012,
      "reward": 1.9656250476837158,
      "reward_std": 0.12840762734413147,
      "rewards/accuracy_reward": 0.8125,
      "rewards/format_reward": 1.0,
      "step": 398,
      "temperature": 1.0
    },
    {
      "all_correct": 0.625,
      "all_wrong": 0.25,
      "completion_length": 371.828125,
      "epoch": 0.012133560394112638,
      "grad_norm": 1.2110059490884901,
      "kl": 0.0242919921875,
      "learning_rate": 9.996367850811503e-07,
      "loss": 0.001,
      "reward": 1.875,
      "reward_std": 0.06460576504468918,
      "rewards/accuracy_reward": 0.734375,
      "rewards/format_reward": 1.0,
      "step": 399,
      "temperature": 1.0
    },
    {
      "all_correct": 0.75,
      "all_wrong": 0.0,
      "completion_length": 382.921875,
      "epoch": 0.012163970319912419,
      "grad_norm": 5.484870431099293,
      "kl": 0.028564453125,
      "learning_rate": 9.996349623953464e-07,
      "loss": 0.0011,
      "reward": 2.0436489582061768,
      "reward_std": 0.08788136392831802,
      "rewards/accuracy_reward": 0.8686488270759583,
      "rewards/format_reward": 1.0,
      "step": 400,
      "temperature": 1.0
    },
    {
      "all_correct": 0.75,
      "all_wrong": 0.0,
      "completion_length": 378.5,
      "epoch": 0.0121943802457122,
      "grad_norm": 0.9080088211059828,
      "kl": 0.0296630859375,
      "learning_rate": 9.996331351493488e-07,
      "loss": 0.0012,
      "reward": 2.0423500537872314,
      "reward_std": 0.11549904942512512,
      "rewards/accuracy_reward": 0.8673499822616577,
      "rewards/format_reward": 1.0,
      "step": 401,
      "temperature": 1.0
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.0,
      "completion_length": 402.15625,
      "epoch": 0.012224790171511981,
      "grad_norm": 1.1423769537719999,
      "kl": 0.02099609375,
      "learning_rate": 9.996313033431744e-07,
      "loss": 0.0008,
      "reward": 1.8997764587402344,
      "reward_std": 0.1524738222360611,
      "rewards/accuracy_reward": 0.7310263514518738,
      "rewards/format_reward": 1.0,
      "step": 402,
      "temperature": 1.0
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.0,
      "completion_length": 376.59375,
      "epoch": 0.012255200097311762,
      "grad_norm": 2.2975493526546202,
      "kl": 0.0294189453125,
      "learning_rate": 9.996294669768398e-07,
      "loss": 0.0012,
      "reward": 1.864615559577942,
      "reward_std": 0.08533743023872375,
      "rewards/accuracy_reward": 0.6833655834197998,
      "rewards/format_reward": 1.0,
      "step": 403,
      "temperature": 1.0
    },
    {
      "all_correct": 0.625,
      "all_wrong": 0.125,
      "completion_length": 361.84375,
      "epoch": 0.012285610023111543,
      "grad_norm": 1.6653609743276963,
      "kl": 0.0286865234375,
      "learning_rate": 9.996276260503616e-07,
      "loss": 0.0011,
      "reward": 1.8635417222976685,
      "reward_std": 0.20986217260360718,
      "rewards/accuracy_reward": 0.7447916865348816,
      "rewards/format_reward": 0.984375,
      "step": 404,
      "temperature": 1.0
    },
    {
      "all_correct": 0.375,
      "all_wrong": 0.0,
      "completion_length": 440.765625,
      "epoch": 0.012316019948911325,
      "grad_norm": 1.2945540418279038,
      "kl": 0.0211181640625,
      "learning_rate": 9.996257805637564e-07,
      "loss": 0.0008,
      "reward": 1.7538068294525146,
      "reward_std": 0.16644743084907532,
      "rewards/accuracy_reward": 0.622556746006012,
      "rewards/format_reward": 1.0,
      "step": 405,
      "temperature": 1.0
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.125,
      "completion_length": 373.296875,
      "epoch": 0.012346429874711106,
      "grad_norm": 0.9565332068062118,
      "kl": 0.029541015625,
      "learning_rate": 9.996239305170417e-07,
      "loss": 0.0012,
      "reward": 1.7602752447128296,
      "reward_std": 0.1293303519487381,
      "rewards/accuracy_reward": 0.6227751970291138,
      "rewards/format_reward": 1.0,
      "step": 406,
      "temperature": 1.0
    },
    {
      "all_correct": 0.625,
      "all_wrong": 0.125,
      "completion_length": 380.984375,
      "epoch": 0.012376839800510887,
      "grad_norm": 1.1816180748076128,
      "kl": 0.023193359375,
      "learning_rate": 9.99622075910234e-07,
      "loss": 0.0009,
      "reward": 1.972031831741333,
      "reward_std": 0.08351900428533554,
      "rewards/accuracy_reward": 0.8157817125320435,
      "rewards/format_reward": 1.0,
      "step": 407,
      "temperature": 1.0
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.0,
      "completion_length": 368.609375,
      "epoch": 0.012407249726310668,
      "grad_norm": 1.5642399928788158,
      "kl": 0.0262451171875,
      "learning_rate": 9.9962021674335e-07,
      "loss": 0.0011,
      "reward": 1.9522716999053955,
      "reward_std": 0.1168014332652092,
      "rewards/accuracy_reward": 0.7835216522216797,
      "rewards/format_reward": 1.0,
      "step": 408,
      "temperature": 1.0
    },
    {
      "all_correct": 0.625,
      "all_wrong": 0.0,
      "completion_length": 360.59375,
      "epoch": 0.01243765965211045,
      "grad_norm": 3.2963069861183865,
      "kl": 0.02294921875,
      "learning_rate": 9.996183530164074e-07,
      "loss": 0.0009,
      "reward": 1.9045774936676025,
      "reward_std": 0.10382448881864548,
      "rewards/accuracy_reward": 0.7483274936676025,
      "rewards/format_reward": 1.0,
      "step": 409,
      "temperature": 1.0
    },
    {
      "all_correct": 0.75,
      "all_wrong": 0.0,
      "completion_length": 370.078125,
      "epoch": 0.01246806957791023,
      "grad_norm": 1.677188381525764,
      "kl": 0.0264892578125,
      "learning_rate": 9.996164847294222e-07,
      "loss": 0.0011,
      "reward": 2.065524101257324,
      "reward_std": 0.07782972604036331,
      "rewards/accuracy_reward": 0.8811489939689636,
      "rewards/format_reward": 1.0,
      "step": 410,
      "temperature": 1.0
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.0,
      "completion_length": 412.625,
      "epoch": 0.012498479503710011,
      "grad_norm": 2.1613245758812982,
      "kl": 0.0244140625,
      "learning_rate": 9.996146118824123e-07,
      "loss": 0.001,
      "reward": 1.9531219005584717,
      "reward_std": 0.22167542576789856,
      "rewards/accuracy_reward": 0.8156219720840454,
      "rewards/format_reward": 1.0,
      "step": 411,
      "temperature": 1.0
    },
    {
      "all_correct": 0.75,
      "all_wrong": 0.0,
      "completion_length": 376.921875,
      "epoch": 0.012528889429509792,
      "grad_norm": 1.4698928795060002,
      "kl": 0.02001953125,
      "learning_rate": 9.996127344753944e-07,
      "loss": 0.0008,
      "reward": 2.070927858352661,
      "reward_std": 0.08682312071323395,
      "rewards/accuracy_reward": 0.8865528702735901,
      "rewards/format_reward": 1.0,
      "step": 412,
      "temperature": 1.0
    },
    {
      "all_correct": 0.75,
      "all_wrong": 0.0,
      "completion_length": 382.28125,
      "epoch": 0.012559299355309573,
      "grad_norm": 0.9000164852037478,
      "kl": 0.02734375,
      "learning_rate": 9.996108525083857e-07,
      "loss": 0.0011,
      "reward": 2.0280327796936035,
      "reward_std": 0.07457979023456573,
      "rewards/accuracy_reward": 0.859282910823822,
      "rewards/format_reward": 1.0,
      "step": 413,
      "temperature": 1.0
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.25,
      "completion_length": 368.4375,
      "epoch": 0.012589709281109354,
      "grad_norm": 0.9333505076634158,
      "kl": 0.0252685546875,
      "learning_rate": 9.996089659814032e-07,
      "loss": 0.001,
      "reward": 1.778926134109497,
      "reward_std": 0.10284383594989777,
      "rewards/accuracy_reward": 0.6445510387420654,
      "rewards/format_reward": 1.0,
      "step": 414,
      "temperature": 1.0
    },
    {
      "all_correct": 0.625,
      "all_wrong": 0.25,
      "completion_length": 368.453125,
      "epoch": 0.012620119206909135,
      "grad_norm": 1.1109114673997336,
      "kl": 0.0250244140625,
      "learning_rate": 9.996070748944646e-07,
      "loss": 0.001,
      "reward": 1.7941220998764038,
      "reward_std": 0.03619522601366043,
      "rewards/accuracy_reward": 0.6503720283508301,
      "rewards/format_reward": 1.0,
      "step": 415,
      "temperature": 1.0
    },
    {
      "all_correct": 0.625,
      "all_wrong": 0.0,
      "completion_length": 374.171875,
      "epoch": 0.012650529132708916,
      "grad_norm": 4.067140537038911,
      "kl": 0.0242919921875,
      "learning_rate": 9.996051792475869e-07,
      "loss": 0.001,
      "reward": 2.0318899154663086,
      "reward_std": 0.13213837146759033,
      "rewards/accuracy_reward": 0.850639820098877,
      "rewards/format_reward": 1.0,
      "step": 416,
      "temperature": 1.0
    },
    {
      "all_correct": 0.375,
      "all_wrong": 0.125,
      "completion_length": 394.578125,
      "epoch": 0.012680939058508697,
      "grad_norm": 1.0856540189127113,
      "kl": 0.0196533203125,
      "learning_rate": 9.99603279040787e-07,
      "loss": 0.0008,
      "reward": 1.801923394203186,
      "reward_std": 0.1127195805311203,
      "rewards/accuracy_reward": 0.6362982988357544,
      "rewards/format_reward": 1.0,
      "step": 417,
      "temperature": 1.0
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.125,
      "completion_length": 401.921875,
      "epoch": 0.012711348984308478,
      "grad_norm": 0.9105330854135775,
      "kl": 0.022216796875,
      "learning_rate": 9.99601374274083e-07,
      "loss": 0.0009,
      "reward": 1.8045833110809326,
      "reward_std": 0.12587976455688477,
      "rewards/accuracy_reward": 0.6670833230018616,
      "rewards/format_reward": 1.0,
      "step": 418,
      "temperature": 1.0
    },
    {
      "all_correct": 0.625,
      "all_wrong": 0.125,
      "completion_length": 431.546875,
      "epoch": 0.01274175891010826,
      "grad_norm": 1.1347127894406621,
      "kl": 0.0179443359375,
      "learning_rate": 9.995994649474918e-07,
      "loss": 0.0007,
      "reward": 1.8670748472213745,
      "reward_std": 0.0404692068696022,
      "rewards/accuracy_reward": 0.7170748114585876,
      "rewards/format_reward": 1.0,
      "step": 419,
      "temperature": 1.0
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.125,
      "completion_length": 394.5,
      "epoch": 0.012772168835908041,
      "grad_norm": 0.9449873289506605,
      "kl": 0.025634765625,
      "learning_rate": 9.995975510610307e-07,
      "loss": 0.001,
      "reward": 1.836775302886963,
      "reward_std": 0.1473839282989502,
      "rewards/accuracy_reward": 0.6992752552032471,
      "rewards/format_reward": 0.984375,
      "step": 420,
      "temperature": 1.0
    },
    {
      "all_correct": 0.625,
      "all_wrong": 0.25,
      "completion_length": 375.265625,
      "epoch": 0.012802578761707822,
      "grad_norm": 1.0516091777259904,
      "kl": 0.0244140625,
      "learning_rate": 9.995956326147176e-07,
      "loss": 0.001,
      "reward": 1.7887868881225586,
      "reward_std": 0.07155824452638626,
      "rewards/accuracy_reward": 0.663786768913269,
      "rewards/format_reward": 1.0,
      "step": 421,
      "temperature": 1.0
    },
    {
      "all_correct": 0.625,
      "all_wrong": 0.375,
      "completion_length": 377.953125,
      "epoch": 0.012832988687507603,
      "grad_norm": 0.5694380019233464,
      "kl": 0.024169921875,
      "learning_rate": 9.995937096085697e-07,
      "loss": 0.001,
      "reward": 1.7468750476837158,
      "reward_std": 0.008838837966322899,
      "rewards/accuracy_reward": 0.625,
      "rewards/format_reward": 1.0,
      "step": 422,
      "temperature": 1.0
    },
    {
      "all_correct": 0.375,
      "all_wrong": 0.0,
      "completion_length": 424.359375,
      "epoch": 0.012863398613307384,
      "grad_norm": 1.127248002853664,
      "kl": 0.015869140625,
      "learning_rate": 9.995917820426047e-07,
      "loss": 0.0006,
      "reward": 1.7372026443481445,
      "reward_std": 0.17061707377433777,
      "rewards/accuracy_reward": 0.5997025966644287,
      "rewards/format_reward": 1.0,
      "step": 423,
      "temperature": 1.0
    },
    {
      "all_correct": 0.375,
      "all_wrong": 0.125,
      "completion_length": 413.609375,
      "epoch": 0.012893808539107165,
      "grad_norm": 3.974309207935761,
      "kl": 0.0201416015625,
      "learning_rate": 9.995898499168402e-07,
      "loss": 0.0008,
      "reward": 1.7879559993743896,
      "reward_std": 0.194219708442688,
      "rewards/accuracy_reward": 0.6504560708999634,
      "rewards/format_reward": 1.0,
      "step": 424,
      "temperature": 1.0
    },
    {
      "all_correct": 0.75,
      "all_wrong": 0.125,
      "completion_length": 376.859375,
      "epoch": 0.012924218464906946,
      "grad_norm": 0.622142736111521,
      "kl": 0.027099609375,
      "learning_rate": 9.995879132312936e-07,
      "loss": 0.0011,
      "reward": 1.9343750476837158,
      "reward_std": 0.07827534526586533,
      "rewards/accuracy_reward": 0.78125,
      "rewards/format_reward": 1.0,
      "step": 425,
      "temperature": 1.0
    },
    {
      "all_correct": 0.375,
      "all_wrong": 0.125,
      "completion_length": 375.203125,
      "epoch": 0.012954628390706727,
      "grad_norm": 1.5903279331050733,
      "kl": 0.026123046875,
      "learning_rate": 9.99585971985983e-07,
      "loss": 0.001,
      "reward": 1.6797423362731934,
      "reward_std": 0.150284543633461,
      "rewards/accuracy_reward": 0.5516172647476196,
      "rewards/format_reward": 1.0,
      "step": 426,
      "temperature": 1.0
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.125,
      "completion_length": 380.953125,
      "epoch": 0.012985038316506508,
      "grad_norm": 1.062176531375013,
      "kl": 0.0216064453125,
      "learning_rate": 9.995840261809256e-07,
      "loss": 0.0009,
      "reward": 1.8180136680603027,
      "reward_std": 0.08744699507951736,
      "rewards/accuracy_reward": 0.6523886919021606,
      "rewards/format_reward": 1.0,
      "step": 427,
      "temperature": 1.0
    },
    {
      "all_correct": 0.625,
      "all_wrong": 0.0,
      "completion_length": 369.65625,
      "epoch": 0.013015448242306289,
      "grad_norm": 0.8337367026433918,
      "kl": 0.0274658203125,
      "learning_rate": 9.995820758161396e-07,
      "loss": 0.0011,
      "reward": 1.8878841400146484,
      "reward_std": 0.1377033144235611,
      "rewards/accuracy_reward": 0.7347592115402222,
      "rewards/format_reward": 1.0,
      "step": 428,
      "temperature": 1.0
    },
    {
      "all_correct": 0.625,
      "all_wrong": 0.125,
      "completion_length": 384.75,
      "epoch": 0.01304585816810607,
      "grad_norm": 0.6084481475037314,
      "kl": 0.0211181640625,
      "learning_rate": 9.995801208916426e-07,
      "loss": 0.0008,
      "reward": 1.8877935409545898,
      "reward_std": 0.09616396576166153,
      "rewards/accuracy_reward": 0.7315435409545898,
      "rewards/format_reward": 1.0,
      "step": 429,
      "temperature": 1.0
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.25,
      "completion_length": 377.203125,
      "epoch": 0.01307626809390585,
      "grad_norm": 1.098252325031774,
      "kl": 0.02490234375,
      "learning_rate": 9.995781614074525e-07,
      "loss": 0.001,
      "reward": 1.779937505722046,
      "reward_std": 0.08466672152280807,
      "rewards/accuracy_reward": 0.6393124461174011,
      "rewards/format_reward": 1.0,
      "step": 430,
      "temperature": 1.0
    },
    {
      "all_correct": 0.375,
      "all_wrong": 0.125,
      "completion_length": 407.640625,
      "epoch": 0.013106678019705631,
      "grad_norm": 1.8846486597481995,
      "kl": 0.0233154296875,
      "learning_rate": 9.995761973635873e-07,
      "loss": 0.0009,
      "reward": 1.7590913772583008,
      "reward_std": 0.23392775654792786,
      "rewards/accuracy_reward": 0.6340913772583008,
      "rewards/format_reward": 1.0,
      "step": 431,
      "temperature": 1.0
    },
    {
      "all_correct": 0.625,
      "all_wrong": 0.125,
      "completion_length": 372.203125,
      "epoch": 0.013137087945505412,
      "grad_norm": 1.2557707122278616,
      "kl": 0.0308837890625,
      "learning_rate": 9.995742287600645e-07,
      "loss": 0.0012,
      "reward": 1.8699300289154053,
      "reward_std": 0.10238337516784668,
      "rewards/accuracy_reward": 0.7168049812316895,
      "rewards/format_reward": 1.0,
      "step": 432,
      "temperature": 1.0
    },
    {
      "all_correct": 0.375,
      "all_wrong": 0.0,
      "completion_length": 371.921875,
      "epoch": 0.013167497871305193,
      "grad_norm": 1.5699627776590146,
      "kl": 0.0301513671875,
      "learning_rate": 9.995722555969026e-07,
      "loss": 0.0012,
      "reward": 1.8518974781036377,
      "reward_std": 0.2162868082523346,
      "rewards/accuracy_reward": 0.6925222277641296,
      "rewards/format_reward": 1.0,
      "step": 433,
      "temperature": 1.0
    },
    {
      "all_correct": 0.375,
      "all_wrong": 0.25,
      "completion_length": 380.046875,
      "epoch": 0.013197907797104976,
      "grad_norm": 0.9288802923072665,
      "kl": 0.0225830078125,
      "learning_rate": 9.995702778741192e-07,
      "loss": 0.0009,
      "reward": 1.7594242095947266,
      "reward_std": 0.07744473218917847,
      "rewards/accuracy_reward": 0.6219242215156555,
      "rewards/format_reward": 1.0,
      "step": 434,
      "temperature": 1.0
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.0,
      "completion_length": 402.71875,
      "epoch": 0.013228317722904757,
      "grad_norm": 1.3675505091144904,
      "kl": 0.0220947265625,
      "learning_rate": 9.995682955917326e-07,
      "loss": 0.0009,
      "reward": 1.9266667366027832,
      "reward_std": 0.09359733015298843,
      "rewards/accuracy_reward": 0.7422915697097778,
      "rewards/format_reward": 1.0,
      "step": 435,
      "temperature": 1.0
    },
    {
      "all_correct": 0.625,
      "all_wrong": 0.125,
      "completion_length": 385.484375,
      "epoch": 0.013258727648704538,
      "grad_norm": 2.23819519846205,
      "kl": 0.0238037109375,
      "learning_rate": 9.995663087497608e-07,
      "loss": 0.001,
      "reward": 1.9015331268310547,
      "reward_std": 0.03403928130865097,
      "rewards/accuracy_reward": 0.7484080791473389,
      "rewards/format_reward": 1.0,
      "step": 436,
      "temperature": 1.0
    },
    {
      "all_correct": 0.375,
      "all_wrong": 0.375,
      "completion_length": 375.9375,
      "epoch": 0.013289137574504319,
      "grad_norm": 4.706405211413954,
      "kl": 0.025390625,
      "learning_rate": 9.995643173482218e-07,
      "loss": 0.001,
      "reward": 1.5572465658187866,
      "reward_std": 0.03346993029117584,
      "rewards/accuracy_reward": 0.4416215419769287,
      "rewards/format_reward": 1.0,
      "step": 437,
      "temperature": 1.0
    },
    {
      "all_correct": 0.375,
      "all_wrong": 0.375,
      "completion_length": 404.921875,
      "epoch": 0.0133195475003041,
      "grad_norm": 0.7703207420764284,
      "kl": 0.01953125,
      "learning_rate": 9.99562321387134e-07,
      "loss": 0.0008,
      "reward": 1.5982862710952759,
      "reward_std": 0.06301999092102051,
      "rewards/accuracy_reward": 0.48578622937202454,
      "rewards/format_reward": 1.0,
      "step": 438,
      "temperature": 1.0
    },
    {
      "all_correct": 0.375,
      "all_wrong": 0.125,
      "completion_length": 384.0625,
      "epoch": 0.01334995742610388,
      "grad_norm": 1.468654125223099,
      "kl": 0.0218505859375,
      "learning_rate": 9.995603208665157e-07,
      "loss": 0.0009,
      "reward": 1.6567028760910034,
      "reward_std": 0.11169316619634628,
      "rewards/accuracy_reward": 0.5223277807235718,
      "rewards/format_reward": 1.0,
      "step": 439,
      "temperature": 1.0
    },
    {
      "all_correct": 0.625,
      "all_wrong": 0.125,
      "completion_length": 360.3125,
      "epoch": 0.013380367351903661,
      "grad_norm": 1.126958068422436,
      "kl": 0.022216796875,
      "learning_rate": 9.995583157863848e-07,
      "loss": 0.0009,
      "reward": 1.9796874523162842,
      "reward_std": 0.08926186710596085,
      "rewards/accuracy_reward": 0.8203125,
      "rewards/format_reward": 1.0,
      "step": 440,
      "temperature": 1.0
    },
    {
      "all_correct": 0.375,
      "all_wrong": 0.0,
      "completion_length": 397.078125,
      "epoch": 0.013410777277703442,
      "grad_norm": 2.989665454494861,
      "kl": 0.0213623046875,
      "learning_rate": 9.995563061467597e-07,
      "loss": 0.0009,
      "reward": 1.781590461730957,
      "reward_std": 0.08468598127365112,
      "rewards/accuracy_reward": 0.6190904378890991,
      "rewards/format_reward": 1.0,
      "step": 441,
      "temperature": 1.0
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.25,
      "completion_length": 369.140625,
      "epoch": 0.013441187203503223,
      "grad_norm": 1.0396161274260947,
      "kl": 0.023681640625,
      "learning_rate": 9.995542919476592e-07,
      "loss": 0.0009,
      "reward": 1.790672779083252,
      "reward_std": 0.08840832859277725,
      "rewards/accuracy_reward": 0.6500478386878967,
      "rewards/format_reward": 1.0,
      "step": 442,
      "temperature": 1.0
    },
    {
      "all_correct": 0.625,
      "all_wrong": 0.0,
      "completion_length": 390.53125,
      "epoch": 0.013471597129303004,
      "grad_norm": 1.4791970001769736,
      "kl": 0.0238037109375,
      "learning_rate": 9.99552273189101e-07,
      "loss": 0.001,
      "reward": 1.8770506381988525,
      "reward_std": 0.06989116966724396,
      "rewards/accuracy_reward": 0.7114256024360657,
      "rewards/format_reward": 1.0,
      "step": 443,
      "temperature": 1.0
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.125,
      "completion_length": 360.296875,
      "epoch": 0.013502007055102785,
      "grad_norm": 1.1384169772377273,
      "kl": 0.02294921875,
      "learning_rate": 9.99550249871104e-07,
      "loss": 0.0009,
      "reward": 1.9211235046386719,
      "reward_std": 0.20084112882614136,
      "rewards/accuracy_reward": 0.7679983973503113,
      "rewards/format_reward": 1.0,
      "step": 444,
      "temperature": 1.0
    },
    {
      "all_correct": 0.875,
      "all_wrong": 0.0,
      "completion_length": 395.890625,
      "epoch": 0.013532416980902566,
      "grad_norm": 0.6153453961417708,
      "kl": 0.02001953125,
      "learning_rate": 9.995482219936864e-07,
      "loss": 0.0008,
      "reward": 2.0562500953674316,
      "reward_std": 0.09121407568454742,
      "rewards/accuracy_reward": 0.90625,
      "rewards/format_reward": 1.0,
      "step": 445,
      "temperature": 1.0
    },
    {
      "all_correct": 0.625,
      "all_wrong": 0.125,
      "completion_length": 398.984375,
      "epoch": 0.013562826906702347,
      "grad_norm": 0.8618215192613391,
      "kl": 0.0218505859375,
      "learning_rate": 9.995461895568668e-07,
      "loss": 0.0009,
      "reward": 1.9375,
      "reward_std": 0.15492431819438934,
      "rewards/accuracy_reward": 0.796875,
      "rewards/format_reward": 1.0,
      "step": 446,
      "temperature": 1.0
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.125,
      "completion_length": 399.984375,
      "epoch": 0.013593236832502128,
      "grad_norm": 1.5945336232652259,
      "kl": 0.0235595703125,
      "learning_rate": 9.99544152560664e-07,
      "loss": 0.0009,
      "reward": 1.7949377298355103,
      "reward_std": 0.05537300929427147,
      "rewards/accuracy_reward": 0.6355627775192261,
      "rewards/format_reward": 1.0,
      "step": 447,
      "temperature": 1.0
    },
    {
      "all_correct": 0.625,
      "all_wrong": 0.25,
      "completion_length": 396.71875,
      "epoch": 0.01362364675830191,
      "grad_norm": 0.8008103675423062,
      "kl": 0.0216064453125,
      "learning_rate": 9.99542111005096e-07,
      "loss": 0.0009,
      "reward": 1.7746574878692627,
      "reward_std": 0.07270940393209457,
      "rewards/accuracy_reward": 0.6527825593948364,
      "rewards/format_reward": 1.0,
      "step": 448,
      "temperature": 1.0
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.125,
      "completion_length": 395.5625,
      "epoch": 0.013654056684101691,
      "grad_norm": 1.105572543787844,
      "kl": 0.0233154296875,
      "learning_rate": 9.995400648901823e-07,
      "loss": 0.0009,
      "reward": 1.7727954387664795,
      "reward_std": 0.08363926410675049,
      "rewards/accuracy_reward": 0.6415454149246216,
      "rewards/format_reward": 1.0,
      "step": 449,
      "temperature": 1.0
    },
    {
      "all_correct": 0.75,
      "all_wrong": 0.25,
      "completion_length": 373.46875,
      "epoch": 0.013684466609901472,
      "grad_norm": 0.6018386909568895,
      "kl": 0.027099609375,
      "learning_rate": 9.995380142159406e-07,
      "loss": 0.0011,
      "reward": 1.896875023841858,
      "reward_std": 0.008838837966322899,
      "rewards/accuracy_reward": 0.75,
      "rewards/format_reward": 1.0,
      "step": 450,
      "temperature": 1.0
    },
    {
      "all_correct": 0.75,
      "all_wrong": 0.125,
      "completion_length": 368.0625,
      "epoch": 0.013714876535701253,
      "grad_norm": 0.8380762449116346,
      "kl": 0.0277099609375,
      "learning_rate": 9.995359589823904e-07,
      "loss": 0.0011,
      "reward": 1.9687501192092896,
      "reward_std": 0.0978560596704483,
      "rewards/accuracy_reward": 0.8125,
      "rewards/format_reward": 1.0,
      "step": 451,
      "temperature": 1.0
    },
    {
      "all_correct": 0.375,
      "all_wrong": 0.0,
      "completion_length": 401.296875,
      "epoch": 0.013745286461501034,
      "grad_norm": 2.0286423199653627,
      "kl": 0.0225830078125,
      "learning_rate": 9.995338991895498e-07,
      "loss": 0.0009,
      "reward": 1.6641693115234375,
      "reward_std": 0.165618896484375,
      "rewards/accuracy_reward": 0.5485442876815796,
      "rewards/format_reward": 1.0,
      "step": 452,
      "temperature": 1.0
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.125,
      "completion_length": 402.984375,
      "epoch": 0.013775696387300815,
      "grad_norm": 1.1305742453533707,
      "kl": 0.0228271484375,
      "learning_rate": 9.995318348374384e-07,
      "loss": 0.0009,
      "reward": 1.8092817068099976,
      "reward_std": 0.11414626240730286,
      "rewards/accuracy_reward": 0.6780316233634949,
      "rewards/format_reward": 1.0,
      "step": 453,
      "temperature": 1.0
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.0,
      "completion_length": 368.90625,
      "epoch": 0.013806106313100596,
      "grad_norm": 1.1221976435534433,
      "kl": 0.0244140625,
      "learning_rate": 9.995297659260742e-07,
      "loss": 0.001,
      "reward": 1.8606196641921997,
      "reward_std": 0.1809464693069458,
      "rewards/accuracy_reward": 0.7231194972991943,
      "rewards/format_reward": 1.0,
      "step": 454,
      "temperature": 1.0
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.0,
      "completion_length": 374.34375,
      "epoch": 0.013836516238900377,
      "grad_norm": 1.314333836821333,
      "kl": 0.0263671875,
      "learning_rate": 9.995276924554767e-07,
      "loss": 0.0011,
      "reward": 1.8475112915039062,
      "reward_std": 0.23364703357219696,
      "rewards/accuracy_reward": 0.7006362676620483,
      "rewards/format_reward": 1.0,
      "step": 455,
      "temperature": 1.0
    },
    {
      "all_correct": 0.625,
      "all_wrong": 0.125,
      "completion_length": 390.71875,
      "epoch": 0.013866926164700158,
      "grad_norm": 0.7309687189504123,
      "kl": 0.0257568359375,
      "learning_rate": 9.995256144256644e-07,
      "loss": 0.001,
      "reward": 1.9031249284744263,
      "reward_std": 0.14942099153995514,
      "rewards/accuracy_reward": 0.7593749761581421,
      "rewards/format_reward": 1.0,
      "step": 456,
      "temperature": 1.0
    },
    {
      "all_correct": 0.625,
      "all_wrong": 0.25,
      "completion_length": 390.5,
      "epoch": 0.013897336090499939,
      "grad_norm": 0.9400969584701695,
      "kl": 0.0262451171875,
      "learning_rate": 9.995235318366566e-07,
      "loss": 0.0011,
      "reward": 1.8725000619888306,
      "reward_std": 0.07008225470781326,
      "rewards/accuracy_reward": 0.7318750023841858,
      "rewards/format_reward": 1.0,
      "step": 457,
      "temperature": 1.0
    },
    {
      "all_correct": 0.875,
      "all_wrong": 0.0,
      "completion_length": 371.84375,
      "epoch": 0.01392774601629972,
      "grad_norm": 1.0806275889339196,
      "kl": 0.0289306640625,
      "learning_rate": 9.995214446884722e-07,
      "loss": 0.0012,
      "reward": 2.171875,
      "reward_std": 0.07344460487365723,
      "rewards/accuracy_reward": 0.984375,
      "rewards/format_reward": 1.0,
      "step": 458,
      "temperature": 1.0
    },
    {
      "all_correct": 0.75,
      "all_wrong": 0.125,
      "completion_length": 385.015625,
      "epoch": 0.0139581559420995,
      "grad_norm": 0.8312789204091494,
      "kl": 0.03173828125,
      "learning_rate": 9.995193529811301e-07,
      "loss": 0.0013,
      "reward": 1.9650859832763672,
      "reward_std": 0.018264738842844963,
      "rewards/accuracy_reward": 0.7963359355926514,
      "rewards/format_reward": 1.0,
      "step": 459,
      "temperature": 1.0
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.125,
      "completion_length": 400.46875,
      "epoch": 0.013988565867899282,
      "grad_norm": 1.5996490673044275,
      "kl": 0.02294921875,
      "learning_rate": 9.995172567146496e-07,
      "loss": 0.0009,
      "reward": 1.7979313135147095,
      "reward_std": 0.09172330796718597,
      "rewards/accuracy_reward": 0.6416813135147095,
      "rewards/format_reward": 1.0,
      "step": 460,
      "temperature": 1.0
    },
    {
      "all_correct": 0.375,
      "all_wrong": 0.125,
      "completion_length": 383.796875,
      "epoch": 0.014018975793699063,
      "grad_norm": 1.2351942913074625,
      "kl": 0.0281982421875,
      "learning_rate": 9.995151558890495e-07,
      "loss": 0.0011,
      "reward": 1.851953148841858,
      "reward_std": 0.18310530483722687,
      "rewards/accuracy_reward": 0.705078125,
      "rewards/format_reward": 1.0,
      "step": 461,
      "temperature": 1.0
    },
    {
      "all_correct": 0.0,
      "all_wrong": 0.25,
      "completion_length": 443.703125,
      "epoch": 0.014049385719498845,
      "grad_norm": 1.7411484741607874,
      "kl": 0.02490234375,
      "learning_rate": 9.995130505043495e-07,
      "loss": 0.001,
      "reward": 1.2498527765274048,
      "reward_std": 0.13263455033302307,
      "rewards/accuracy_reward": 0.20610277354717255,
      "rewards/format_reward": 1.0,
      "step": 462,
      "temperature": 1.0
    },
    {
      "all_correct": 0.375,
      "all_wrong": 0.375,
      "completion_length": 380.859375,
      "epoch": 0.014079795645298626,
      "grad_norm": 1.2495323644891858,
      "kl": 0.0302734375,
      "learning_rate": 9.995109405605683e-07,
      "loss": 0.0012,
      "reward": 1.4718749523162842,
      "reward_std": 0.101327084004879,
      "rewards/accuracy_reward": 0.40625,
      "rewards/format_reward": 1.0,
      "step": 463,
      "temperature": 1.0
    },
    {
      "all_correct": 0.75,
      "all_wrong": 0.125,
      "completion_length": 403.015625,
      "epoch": 0.014110205571098407,
      "grad_norm": 0.4181846124701794,
      "kl": 0.0247802734375,
      "learning_rate": 9.995088260577257e-07,
      "loss": 0.001,
      "reward": 1.9343749284744263,
      "reward_std": 0.07827534526586533,
      "rewards/accuracy_reward": 0.78125,
      "rewards/format_reward": 1.0,
      "step": 464,
      "temperature": 1.0
    },
    {
      "all_correct": 0.625,
      "all_wrong": 0.25,
      "completion_length": 387.28125,
      "epoch": 0.014140615496898188,
      "grad_norm": 0.7953206755988361,
      "kl": 0.029052734375,
      "learning_rate": 9.995067069958404e-07,
      "loss": 0.0012,
      "reward": 1.8015625476837158,
      "reward_std": 0.08693268150091171,
      "rewards/accuracy_reward": 0.6703125238418579,
      "rewards/format_reward": 1.0,
      "step": 465,
      "temperature": 1.0
    },
    {
      "all_correct": 1.0,
      "all_wrong": 0.0,
      "completion_length": 377.359375,
      "epoch": 0.014171025422697969,
      "grad_norm": 0.9408394023777019,
      "kl": 0.025634765625,
      "learning_rate": 9.995045833749323e-07,
      "loss": 0.001,
      "reward": 2.1937499046325684,
      "reward_std": 0.017677675932645798,
      "rewards/accuracy_reward": 1.0,
      "rewards/format_reward": 1.0,
      "step": 466,
      "temperature": 1.0
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.125,
      "completion_length": 404.890625,
      "epoch": 0.01420143534849775,
      "grad_norm": 1.0781516326422151,
      "kl": 0.026611328125,
      "learning_rate": 9.995024551950203e-07,
      "loss": 0.0011,
      "reward": 1.794966220855713,
      "reward_std": 0.14499084651470184,
      "rewards/accuracy_reward": 0.6574661731719971,
      "rewards/format_reward": 1.0,
      "step": 467,
      "temperature": 1.0
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.0,
      "completion_length": 411.578125,
      "epoch": 0.01423184527429753,
      "grad_norm": 1.8664424004576747,
      "kl": 0.0252685546875,
      "learning_rate": 9.99500322456124e-07,
      "loss": 0.001,
      "reward": 1.8546946048736572,
      "reward_std": 0.10674580186605453,
      "rewards/accuracy_reward": 0.6796945929527283,
      "rewards/format_reward": 1.0,
      "step": 468,
      "temperature": 1.0
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.125,
      "completion_length": 402.0,
      "epoch": 0.014262255200097312,
      "grad_norm": 8.499584285454972,
      "kl": 0.0262451171875,
      "learning_rate": 9.99498185158263e-07,
      "loss": 0.001,
      "reward": 1.8758907318115234,
      "reward_std": 0.13766837120056152,
      "rewards/accuracy_reward": 0.7321406602859497,
      "rewards/format_reward": 1.0,
      "step": 469,
      "temperature": 1.0
    },
    {
      "all_correct": 0.25,
      "all_wrong": 0.125,
      "completion_length": 403.109375,
      "epoch": 0.014292665125897093,
      "grad_norm": 1.8972264783382558,
      "kl": 0.024169921875,
      "learning_rate": 9.994960433014568e-07,
      "loss": 0.001,
      "reward": 1.4283539056777954,
      "reward_std": 0.15578557550907135,
      "rewards/accuracy_reward": 0.3627288341522217,
      "rewards/format_reward": 1.0,
      "step": 470,
      "temperature": 1.0
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.125,
      "completion_length": 395.09375,
      "epoch": 0.014323075051696874,
      "grad_norm": 0.9301703657198602,
      "kl": 0.024658203125,
      "learning_rate": 9.994938968857248e-07,
      "loss": 0.001,
      "reward": 1.8406250476837158,
      "reward_std": 0.183067187666893,
      "rewards/accuracy_reward": 0.703125,
      "rewards/format_reward": 1.0,
      "step": 471,
      "temperature": 1.0
    },
    {
      "all_correct": 0.25,
      "all_wrong": 0.0,
      "completion_length": 432.453125,
      "epoch": 0.014353484977496654,
      "grad_norm": 1.2812077327499334,
      "kl": 0.0206298828125,
      "learning_rate": 9.994917459110866e-07,
      "loss": 0.0008,
      "reward": 1.6236194372177124,
      "reward_std": 0.25698375701904297,
      "rewards/accuracy_reward": 0.5392444729804993,
      "rewards/format_reward": 0.96875,
      "step": 472,
      "temperature": 1.0
    },
    {
      "all_correct": 0.625,
      "all_wrong": 0.0,
      "completion_length": 397.03125,
      "epoch": 0.014383894903296435,
      "grad_norm": 1.476101342228793,
      "kl": 0.018798828125,
      "learning_rate": 9.994895903775618e-07,
      "loss": 0.0008,
      "reward": 1.9296013116836548,
      "reward_std": 0.165361687541008,
      "rewards/accuracy_reward": 0.7671012878417969,
      "rewards/format_reward": 1.0,
      "step": 473,
      "temperature": 1.0
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.25,
      "completion_length": 374.5625,
      "epoch": 0.014414304829096216,
      "grad_norm": 1.2054324526869955,
      "kl": 0.030517578125,
      "learning_rate": 9.994874302851704e-07,
      "loss": 0.0012,
      "reward": 1.8375000953674316,
      "reward_std": 0.12992841005325317,
      "rewards/accuracy_reward": 0.703125,
      "rewards/format_reward": 1.0,
      "step": 474,
      "temperature": 1.0
    },
    {
      "all_correct": 0.375,
      "all_wrong": 0.125,
      "completion_length": 382.21875,
      "epoch": 0.014444714754895997,
      "grad_norm": 0.9605522805925136,
      "kl": 0.022216796875,
      "learning_rate": 9.994852656339317e-07,
      "loss": 0.0009,
      "reward": 1.8764104843139648,
      "reward_std": 0.08165568858385086,
      "rewards/accuracy_reward": 0.7107853889465332,
      "rewards/format_reward": 1.0,
      "step": 475,
      "temperature": 1.0
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.0,
      "completion_length": 408.3125,
      "epoch": 0.01447512468069578,
      "grad_norm": 1.5557925777476829,
      "kl": 0.0234375,
      "learning_rate": 9.994830964238655e-07,
      "loss": 0.0009,
      "reward": 1.9632638692855835,
      "reward_std": 0.13806749880313873,
      "rewards/accuracy_reward": 0.8070138096809387,
      "rewards/format_reward": 1.0,
      "step": 476,
      "temperature": 1.0
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.0,
      "completion_length": 407.546875,
      "epoch": 0.01450553460649556,
      "grad_norm": 1.594750723693762,
      "kl": 0.023193359375,
      "learning_rate": 9.99480922654992e-07,
      "loss": 0.0009,
      "reward": 1.8550639152526855,
      "reward_std": 0.18018555641174316,
      "rewards/accuracy_reward": 0.7019388675689697,
      "rewards/format_reward": 1.0,
      "step": 477,
      "temperature": 1.0
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.0,
      "completion_length": 382.125,
      "epoch": 0.014535944532295342,
      "grad_norm": 1.1981462114456876,
      "kl": 0.0203857421875,
      "learning_rate": 9.994787443273305e-07,
      "loss": 0.0008,
      "reward": 1.9415209293365479,
      "reward_std": 0.15329420566558838,
      "rewards/accuracy_reward": 0.7727709412574768,
      "rewards/format_reward": 1.0,
      "step": 478,
      "temperature": 1.0
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.125,
      "completion_length": 366.703125,
      "epoch": 0.014566354458095123,
      "grad_norm": 1.0124550289266019,
      "kl": 0.0235595703125,
      "learning_rate": 9.994765614409013e-07,
      "loss": 0.0009,
      "reward": 1.772862434387207,
      "reward_std": 0.05820607393980026,
      "rewards/accuracy_reward": 0.6228625178337097,
      "rewards/format_reward": 1.0,
      "step": 479,
      "temperature": 1.0
    },
    {
      "all_correct": 0.75,
      "all_wrong": 0.125,
      "completion_length": 364.421875,
      "epoch": 0.014596764383894904,
      "grad_norm": 1.73310972399627,
      "kl": 0.026611328125,
      "learning_rate": 9.99474373995724e-07,
      "loss": 0.0011,
      "reward": 1.9468750953674316,
      "reward_std": 0.15362296998500824,
      "rewards/accuracy_reward": 0.8125,
      "rewards/format_reward": 0.984375,
      "step": 480,
      "temperature": 1.0
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.125,
      "completion_length": 367.984375,
      "epoch": 0.014627174309694685,
      "grad_norm": 1.278776072064968,
      "kl": 0.0240478515625,
      "learning_rate": 9.99472181991819e-07,
      "loss": 0.001,
      "reward": 1.6767091751098633,
      "reward_std": 0.08327358961105347,
      "rewards/accuracy_reward": 0.5485841631889343,
      "rewards/format_reward": 1.0,
      "step": 481,
      "temperature": 1.0
    },
    {
      "all_correct": 0.875,
      "all_wrong": 0.125,
      "completion_length": 361.75,
      "epoch": 0.014657584235494465,
      "grad_norm": 1.1354116964573329,
      "kl": 0.0301513671875,
      "learning_rate": 9.99469985429206e-07,
      "loss": 0.0012,
      "reward": 2.0374999046325684,
      "reward_std": 0.029250435531139374,
      "rewards/accuracy_reward": 0.875,
      "rewards/format_reward": 1.0,
      "step": 482,
      "temperature": 1.0
    },
    {
      "all_correct": 0.625,
      "all_wrong": 0.0,
      "completion_length": 368.296875,
      "epoch": 0.014687994161294246,
      "grad_norm": 0.9816022633769056,
      "kl": 0.022705078125,
      "learning_rate": 9.994677843079049e-07,
      "loss": 0.0009,
      "reward": 1.9828240871429443,
      "reward_std": 0.14439547061920166,
      "rewards/accuracy_reward": 0.7984490394592285,
      "rewards/format_reward": 1.0,
      "step": 483,
      "temperature": 1.0
    },
    {
      "all_correct": 0.375,
      "all_wrong": 0.125,
      "completion_length": 357.4375,
      "epoch": 0.014718404087094027,
      "grad_norm": 1.3762233724222692,
      "kl": 0.0238037109375,
      "learning_rate": 9.99465578627936e-07,
      "loss": 0.001,
      "reward": 1.73703932762146,
      "reward_std": 0.22470009326934814,
      "rewards/accuracy_reward": 0.6151642799377441,
      "rewards/format_reward": 1.0,
      "step": 484,
      "temperature": 1.0
    },
    {
      "all_correct": 0.75,
      "all_wrong": 0.25,
      "completion_length": 341.515625,
      "epoch": 0.014748814012893808,
      "grad_norm": 21.483624729352442,
      "kl": 0.0299072265625,
      "learning_rate": 9.994633683893194e-07,
      "loss": 0.0012,
      "reward": 1.890625,
      "reward_std": 0.020411595702171326,
      "rewards/accuracy_reward": 0.75,
      "rewards/format_reward": 1.0,
      "step": 485,
      "temperature": 1.0
    },
    {
      "all_correct": 0.625,
      "all_wrong": 0.125,
      "completion_length": 350.671875,
      "epoch": 0.01477922393869359,
      "grad_norm": 4.750600359663863,
      "kl": 0.030517578125,
      "learning_rate": 9.994611535920755e-07,
      "loss": 0.0012,
      "reward": 1.8562500476837158,
      "reward_std": 0.1672925502061844,
      "rewards/accuracy_reward": 0.71875,
      "rewards/format_reward": 1.0,
      "step": 486,
      "temperature": 1.0
    },
    {
      "all_correct": 0.75,
      "all_wrong": 0.25,
      "completion_length": 345.40625,
      "epoch": 0.01480963386449337,
      "grad_norm": 0.4490329278190297,
      "kl": 0.032470703125,
      "learning_rate": 9.994589342362242e-07,
      "loss": 0.0013,
      "reward": 1.8968751430511475,
      "reward_std": 0.008838837966322899,
      "rewards/accuracy_reward": 0.75,
      "rewards/format_reward": 1.0,
      "step": 487,
      "temperature": 1.0
    },
    {
      "all_correct": 0.75,
      "all_wrong": 0.0,
      "completion_length": 374.328125,
      "epoch": 0.014840043790293151,
      "grad_norm": 0.8811612692288447,
      "kl": 0.025146484375,
      "learning_rate": 9.994567103217857e-07,
      "loss": 0.001,
      "reward": 2.1192474365234375,
      "reward_std": 0.02281036786735058,
      "rewards/accuracy_reward": 0.9192472696304321,
      "rewards/format_reward": 1.0,
      "step": 488,
      "temperature": 1.0
    },
    {
      "all_correct": 0.25,
      "all_wrong": 0.5,
      "completion_length": 409.390625,
      "epoch": 0.014870453716092932,
      "grad_norm": 1.449497617084126,
      "kl": 0.0244140625,
      "learning_rate": 9.994544818487807e-07,
      "loss": 0.001,
      "reward": 1.4860035181045532,
      "reward_std": 0.030808432027697563,
      "rewards/accuracy_reward": 0.40787848830223083,
      "rewards/format_reward": 1.0,
      "step": 489,
      "temperature": 1.0
    },
    {
      "all_correct": 0.625,
      "all_wrong": 0.0,
      "completion_length": 369.1875,
      "epoch": 0.014900863641892715,
      "grad_norm": 1.197418595850855,
      "kl": 0.026123046875,
      "learning_rate": 9.994522488172292e-07,
      "loss": 0.001,
      "reward": 1.9457591772079468,
      "reward_std": 0.13133002817630768,
      "rewards/accuracy_reward": 0.7832591533660889,
      "rewards/format_reward": 1.0,
      "step": 490,
      "temperature": 1.0
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.0,
      "completion_length": 434.578125,
      "epoch": 0.014931273567692496,
      "grad_norm": 3.8766259808301777,
      "kl": 0.0167236328125,
      "learning_rate": 9.994500112271515e-07,
      "loss": 0.0007,
      "reward": 1.9357054233551025,
      "reward_std": 0.2655298113822937,
      "rewards/accuracy_reward": 0.8013304471969604,
      "rewards/format_reward": 0.984375,
      "step": 491,
      "temperature": 1.0
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.0,
      "completion_length": 356.578125,
      "epoch": 0.014961683493492276,
      "grad_norm": 2.0308594187354307,
      "kl": 0.0277099609375,
      "learning_rate": 9.994477690785683e-07,
      "loss": 0.0011,
      "reward": 1.9444613456726074,
      "reward_std": 0.13510005176067352,
      "rewards/accuracy_reward": 0.7725862264633179,
      "rewards/format_reward": 1.0,
      "step": 492,
      "temperature": 1.0
    },
    {
      "all_correct": 0.625,
      "all_wrong": 0.125,
      "completion_length": 380.0625,
      "epoch": 0.014992093419292057,
      "grad_norm": 0.7251449247281695,
      "kl": 0.0322265625,
      "learning_rate": 9.994455223715e-07,
      "loss": 0.0013,
      "reward": 1.8531250953674316,
      "reward_std": 0.15011084079742432,
      "rewards/accuracy_reward": 0.71875,
      "rewards/format_reward": 1.0,
      "step": 493,
      "temperature": 1.0
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.125,
      "completion_length": 366.515625,
      "epoch": 0.015022503345091838,
      "grad_norm": 1.3961813675517114,
      "kl": 0.0228271484375,
      "learning_rate": 9.99443271105967e-07,
      "loss": 0.0009,
      "reward": 1.7663193941116333,
      "reward_std": 0.2004338800907135,
      "rewards/accuracy_reward": 0.647569477558136,
      "rewards/format_reward": 1.0,
      "step": 494,
      "temperature": 1.0
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.375,
      "completion_length": 398.46875,
      "epoch": 0.01505291327089162,
      "grad_norm": 0.43603587661087234,
      "kl": 0.0238037109375,
      "learning_rate": 9.994410152819901e-07,
      "loss": 0.001,
      "reward": 1.6700551509857178,
      "reward_std": 0.011016301810741425,
      "rewards/accuracy_reward": 0.5513050556182861,
      "rewards/format_reward": 1.0,
      "step": 495,
      "temperature": 1.0
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.25,
      "completion_length": 391.078125,
      "epoch": 0.0150833231966914,
      "grad_norm": 6.528817867688138,
      "kl": 0.0238037109375,
      "learning_rate": 9.994387548995895e-07,
      "loss": 0.001,
      "reward": 1.7028368711471558,
      "reward_std": 0.0879361554980278,
      "rewards/accuracy_reward": 0.5903368592262268,
      "rewards/format_reward": 1.0,
      "step": 496,
      "temperature": 1.0
    },
    {
      "all_correct": 0.375,
      "all_wrong": 0.125,
      "completion_length": 383.515625,
      "epoch": 0.015113733122491181,
      "grad_norm": 1.1438669635370577,
      "kl": 0.0283203125,
      "learning_rate": 9.99436489958786e-07,
      "loss": 0.0011,
      "reward": 1.7709039449691772,
      "reward_std": 0.08125047385692596,
      "rewards/accuracy_reward": 0.6240289211273193,
      "rewards/format_reward": 1.0,
      "step": 497,
      "temperature": 1.0
    },
    {
      "all_correct": 0.875,
      "all_wrong": 0.0,
      "completion_length": 373.375,
      "epoch": 0.015144143048290962,
      "grad_norm": 0.7407721238302988,
      "kl": 0.02587890625,
      "learning_rate": 9.994342204596005e-07,
      "loss": 0.001,
      "reward": 2.113842248916626,
      "reward_std": 0.012486360967159271,
      "rewards/accuracy_reward": 0.9169672131538391,
      "rewards/format_reward": 1.0,
      "step": 498,
      "temperature": 1.0
    },
    {
      "all_correct": 0.25,
      "all_wrong": 0.125,
      "completion_length": 391.59375,
      "epoch": 0.015174552974090743,
      "grad_norm": 1.7547240765527865,
      "kl": 0.023193359375,
      "learning_rate": 9.994319464020535e-07,
      "loss": 0.0009,
      "reward": 1.6313037872314453,
      "reward_std": 0.10591939091682434,
      "rewards/accuracy_reward": 0.47817879915237427,
      "rewards/format_reward": 1.0,
      "step": 499,
      "temperature": 1.0
    },
    {
      "all_correct": 0.125,
      "all_wrong": 0.125,
      "completion_length": 417.078125,
      "epoch": 0.015204962899890524,
      "grad_norm": 1.7671884927395058,
      "kl": 0.0224609375,
      "learning_rate": 9.994296677861656e-07,
      "loss": 0.0009,
      "reward": 1.5905811786651611,
      "reward_std": 0.28221431374549866,
      "rewards/accuracy_reward": 0.49995630979537964,
      "rewards/format_reward": 1.0,
      "step": 500,
      "temperature": 1.0
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.0,
      "completion_length": 386.390625,
      "epoch": 0.015235372825690305,
      "grad_norm": 1.0579745722302552,
      "kl": 0.02099609375,
      "learning_rate": 9.99427384611958e-07,
      "loss": 0.0008,
      "reward": 1.6781747341156006,
      "reward_std": 0.16024881601333618,
      "rewards/accuracy_reward": 0.5719246864318848,
      "rewards/format_reward": 1.0,
      "step": 501,
      "temperature": 1.0
    },
    {
      "all_correct": 0.375,
      "all_wrong": 0.25,
      "completion_length": 410.296875,
      "epoch": 0.015265782751490086,
      "grad_norm": 0.9557962176132624,
      "kl": 0.026611328125,
      "learning_rate": 9.99425096879451e-07,
      "loss": 0.0011,
      "reward": 1.6614211797714233,
      "reward_std": 0.08476591855287552,
      "rewards/accuracy_reward": 0.5457960367202759,
      "rewards/format_reward": 1.0,
      "step": 502,
      "temperature": 1.0
    },
    {
      "all_correct": 0.25,
      "all_wrong": 0.375,
      "completion_length": 414.578125,
      "epoch": 0.015296192677289867,
      "grad_norm": 2.5270387407852226,
      "kl": 0.0174560546875,
      "learning_rate": 9.99422804588666e-07,
      "loss": 0.0007,
      "reward": 1.5413379669189453,
      "reward_std": 0.1443595290184021,
      "rewards/accuracy_reward": 0.4319629669189453,
      "rewards/format_reward": 1.0,
      "step": 503,
      "temperature": 1.0
    },
    {
      "all_correct": 0.375,
      "all_wrong": 0.25,
      "completion_length": 388.6875,
      "epoch": 0.015326602603089648,
      "grad_norm": 3.212793562040323,
      "kl": 0.0262451171875,
      "learning_rate": 9.994205077396235e-07,
      "loss": 0.001,
      "reward": 1.7812501192092896,
      "reward_std": 0.2039220929145813,
      "rewards/accuracy_reward": 0.65625,
      "rewards/format_reward": 1.0,
      "step": 504,
      "temperature": 1.0
    },
    {
      "all_correct": 0.625,
      "all_wrong": 0.0,
      "completion_length": 382.34375,
      "epoch": 0.01535701252888943,
      "grad_norm": 0.8830435979823414,
      "kl": 0.02197265625,
      "learning_rate": 9.99418206332345e-07,
      "loss": 0.0009,
      "reward": 2.081249952316284,
      "reward_std": 0.1801677793264389,
      "rewards/accuracy_reward": 0.90625,
      "rewards/format_reward": 1.0,
      "step": 505,
      "temperature": 1.0
    },
    {
      "all_correct": 0.375,
      "all_wrong": 0.125,
      "completion_length": 408.140625,
      "epoch": 0.015387422454689211,
      "grad_norm": 1.7651640875101753,
      "kl": 0.025146484375,
      "learning_rate": 9.99415900366851e-07,
      "loss": 0.001,
      "reward": 1.701768159866333,
      "reward_std": 0.10204082727432251,
      "rewards/accuracy_reward": 0.561143159866333,
      "rewards/format_reward": 1.0,
      "step": 506,
      "temperature": 1.0
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.125,
      "completion_length": 387.796875,
      "epoch": 0.015417832380488992,
      "grad_norm": 1.2433370198476819,
      "kl": 0.0286865234375,
      "learning_rate": 9.994135898431626e-07,
      "loss": 0.0011,
      "reward": 1.8230243921279907,
      "reward_std": 0.030501363798975945,
      "rewards/accuracy_reward": 0.6698993444442749,
      "rewards/format_reward": 1.0,
      "step": 507,
      "temperature": 1.0
    },
    {
      "all_correct": 0.375,
      "all_wrong": 0.125,
      "completion_length": 400.53125,
      "epoch": 0.015448242306288773,
      "grad_norm": 1.601411041562304,
      "kl": 0.0244140625,
      "learning_rate": 9.994112747613013e-07,
      "loss": 0.001,
      "reward": 1.6756925582885742,
      "reward_std": 0.19744716584682465,
      "rewards/accuracy_reward": 0.5475676655769348,
      "rewards/format_reward": 1.0,
      "step": 508,
      "temperature": 1.0
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.125,
      "completion_length": 364.765625,
      "epoch": 0.015478652232088554,
      "grad_norm": 1.334225481217231,
      "kl": 0.033447265625,
      "learning_rate": 9.994089551212878e-07,
      "loss": 0.0013,
      "reward": 1.836044192314148,
      "reward_std": 0.20293495059013367,
      "rewards/accuracy_reward": 0.7047942280769348,
      "rewards/format_reward": 1.0,
      "step": 509,
      "temperature": 1.0
    },
    {
      "all_correct": 0.25,
      "all_wrong": 0.125,
      "completion_length": 421.140625,
      "epoch": 0.015509062157888335,
      "grad_norm": 2.2315658848306748,
      "kl": 0.0224609375,
      "learning_rate": 9.994066309231433e-07,
      "loss": 0.0009,
      "reward": 1.5848779678344727,
      "reward_std": 0.1835135668516159,
      "rewards/accuracy_reward": 0.4786280393600464,
      "rewards/format_reward": 1.0,
      "step": 510,
      "temperature": 1.0
    },
    {
      "all_correct": 0.625,
      "all_wrong": 0.0,
      "completion_length": 414.875,
      "epoch": 0.015539472083688116,
      "grad_norm": 1.0259196284542582,
      "kl": 0.02587890625,
      "learning_rate": 9.994043021668893e-07,
      "loss": 0.001,
      "reward": 1.8112499713897705,
      "reward_std": 0.10919193923473358,
      "rewards/accuracy_reward": 0.6893749237060547,
      "rewards/format_reward": 1.0,
      "step": 511,
      "temperature": 1.0
    },
    {
      "all_correct": 0.25,
      "all_wrong": 0.125,
      "completion_length": 386.5,
      "epoch": 0.015569882009487897,
      "grad_norm": 4.604892286988543,
      "kl": 0.0244140625,
      "learning_rate": 9.994019688525468e-07,
      "loss": 0.001,
      "reward": 1.8986676931381226,
      "reward_std": 0.18019667267799377,
      "rewards/accuracy_reward": 0.7330426573753357,
      "rewards/format_reward": 1.0,
      "step": 512,
      "temperature": 1.0
    },
    {
      "all_correct": 0.375,
      "all_wrong": 0.25,
      "completion_length": 412.03125,
      "epoch": 0.015600291935287678,
      "grad_norm": 0.7396815554950271,
      "kl": 0.01806640625,
      "learning_rate": 9.993996309801372e-07,
      "loss": 0.0007,
      "reward": 1.6681134700775146,
      "reward_std": 0.08704882115125656,
      "rewards/accuracy_reward": 0.5431134700775146,
      "rewards/format_reward": 1.0,
      "step": 513,
      "temperature": 1.0
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.0,
      "completion_length": 360.265625,
      "epoch": 0.01563070186108746,
      "grad_norm": 1.6690888405541142,
      "kl": 0.02978515625,
      "learning_rate": 9.993972885496818e-07,
      "loss": 0.0012,
      "reward": 1.791684627532959,
      "reward_std": 0.09275756776332855,
      "rewards/accuracy_reward": 0.6291844844818115,
      "rewards/format_reward": 1.0,
      "step": 514,
      "temperature": 1.0
    },
    {
      "all_correct": 0.375,
      "all_wrong": 0.0,
      "completion_length": 379.96875,
      "epoch": 0.01566111178688724,
      "grad_norm": 0.9714671847747159,
      "kl": 0.0245361328125,
      "learning_rate": 9.99394941561202e-07,
      "loss": 0.001,
      "reward": 1.7595596313476562,
      "reward_std": 0.26944100856781006,
      "rewards/accuracy_reward": 0.6251845359802246,
      "rewards/format_reward": 1.0,
      "step": 515,
      "temperature": 1.0
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.0,
      "completion_length": 404.109375,
      "epoch": 0.01569152171268702,
      "grad_norm": 0.9952776018834041,
      "kl": 0.02294921875,
      "learning_rate": 9.993925900147192e-07,
      "loss": 0.0009,
      "reward": 1.7211538553237915,
      "reward_std": 0.19977575540542603,
      "rewards/accuracy_reward": 0.611778974533081,
      "rewards/format_reward": 0.984375,
      "step": 516,
      "temperature": 1.0
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.0,
      "completion_length": 366.453125,
      "epoch": 0.015721931638486803,
      "grad_norm": 1.1271872799825466,
      "kl": 0.02392578125,
      "learning_rate": 9.99390233910255e-07,
      "loss": 0.001,
      "reward": 1.9171892404556274,
      "reward_std": 0.23139682412147522,
      "rewards/accuracy_reward": 0.7515642642974854,
      "rewards/format_reward": 1.0,
      "step": 517,
      "temperature": 1.0
    },
    {
      "all_correct": 0.25,
      "all_wrong": 0.0,
      "completion_length": 407.421875,
      "epoch": 0.015752341564286582,
      "grad_norm": 1.4148442953292637,
      "kl": 0.02197265625,
      "learning_rate": 9.993878732478307e-07,
      "loss": 0.0009,
      "reward": 1.814260482788086,
      "reward_std": 0.2154199779033661,
      "rewards/accuracy_reward": 0.6330103874206543,
      "rewards/format_reward": 1.0,
      "step": 518,
      "temperature": 1.0
    },
    {
      "all_correct": 0.625,
      "all_wrong": 0.125,
      "completion_length": 379.9375,
      "epoch": 0.015782751490086365,
      "grad_norm": 0.9117037230310154,
      "kl": 0.025390625,
      "learning_rate": 9.99385508027468e-07,
      "loss": 0.001,
      "reward": 1.9541666507720947,
      "reward_std": 0.09727580100297928,
      "rewards/accuracy_reward": 0.7979166507720947,
      "rewards/format_reward": 1.0,
      "step": 519,
      "temperature": 1.0
    },
    {
      "all_correct": 0.625,
      "all_wrong": 0.0,
      "completion_length": 392.796875,
      "epoch": 0.015813161415886144,
      "grad_norm": 1.8840561359969978,
      "kl": 0.027099609375,
      "learning_rate": 9.993831382491884e-07,
      "loss": 0.0011,
      "reward": 1.9901095628738403,
      "reward_std": 0.21440814435482025,
      "rewards/accuracy_reward": 0.8244844675064087,
      "rewards/format_reward": 1.0,
      "step": 520,
      "temperature": 1.0
    },
    {
      "all_correct": 0.75,
      "all_wrong": 0.0,
      "completion_length": 381.15625,
      "epoch": 0.015843571341685927,
      "grad_norm": 1.0692597127521983,
      "kl": 0.02587890625,
      "learning_rate": 9.993807639130133e-07,
      "loss": 0.001,
      "reward": 2.0625,
      "reward_std": 0.16474656760692596,
      "rewards/accuracy_reward": 0.890625,
      "rewards/format_reward": 1.0,
      "step": 521,
      "temperature": 1.0
    },
    {
      "all_correct": 0.375,
      "all_wrong": 0.0,
      "completion_length": 402.5,
      "epoch": 0.015873981267485706,
      "grad_norm": 1.7035038134937677,
      "kl": 0.022705078125,
      "learning_rate": 9.99378385018965e-07,
      "loss": 0.0009,
      "reward": 1.8963849544525146,
      "reward_std": 0.3370119035243988,
      "rewards/accuracy_reward": 0.7557598352432251,
      "rewards/format_reward": 0.984375,
      "step": 522,
      "temperature": 1.0
    },
    {
      "all_correct": 0.375,
      "all_wrong": 0.125,
      "completion_length": 387.078125,
      "epoch": 0.01590439119328549,
      "grad_norm": 0.780901457286748,
      "kl": 0.0177001953125,
      "learning_rate": 9.993760015670644e-07,
      "loss": 0.0007,
      "reward": 1.6112170219421387,
      "reward_std": 0.23193469643592834,
      "rewards/accuracy_reward": 0.5112169981002808,
      "rewards/format_reward": 0.984375,
      "step": 523,
      "temperature": 1.0
    },
    {
      "all_correct": 0.375,
      "all_wrong": 0.25,
      "completion_length": 389.984375,
      "epoch": 0.015934801119085268,
      "grad_norm": 0.9625130944234312,
      "kl": 0.02392578125,
      "learning_rate": 9.993736135573341e-07,
      "loss": 0.001,
      "reward": 1.765625,
      "reward_std": 0.21148672699928284,
      "rewards/accuracy_reward": 0.640625,
      "rewards/format_reward": 1.0,
      "step": 524,
      "temperature": 1.0
    },
    {
      "all_correct": 0.625,
      "all_wrong": 0.125,
      "completion_length": 383.953125,
      "epoch": 0.01596521104488505,
      "grad_norm": 1.1593850326921535,
      "kl": 0.0274658203125,
      "learning_rate": 9.993712209897954e-07,
      "loss": 0.0011,
      "reward": 1.8734374046325684,
      "reward_std": 0.1397111713886261,
      "rewards/accuracy_reward": 0.7296875715255737,
      "rewards/format_reward": 1.0,
      "step": 525,
      "temperature": 1.0
    },
    {
      "all_correct": 0.75,
      "all_wrong": 0.125,
      "completion_length": 382.8125,
      "epoch": 0.015995620970684833,
      "grad_norm": 0.3328221255135476,
      "kl": 0.02490234375,
      "learning_rate": 9.9936882386447e-07,
      "loss": 0.001,
      "reward": 2.0218751430511475,
      "reward_std": 0.05077523738145828,
      "rewards/accuracy_reward": 0.859375,
      "rewards/format_reward": 1.0,
      "step": 526,
      "temperature": 1.0
    },
    {
      "all_correct": 0.625,
      "all_wrong": 0.125,
      "completion_length": 366.40625,
      "epoch": 0.016026030896484612,
      "grad_norm": 0.7461185627324085,
      "kl": 0.03369140625,
      "learning_rate": 9.993664221813801e-07,
      "loss": 0.0014,
      "reward": 1.8531250953674316,
      "reward_std": 0.11738668382167816,
      "rewards/accuracy_reward": 0.71875,
      "rewards/format_reward": 1.0,
      "step": 527,
      "temperature": 1.0
    },
    {
      "all_correct": 0.375,
      "all_wrong": 0.125,
      "completion_length": 408.703125,
      "epoch": 0.016056440822284395,
      "grad_norm": 1.085743044665237,
      "kl": 0.02197265625,
      "learning_rate": 9.993640159405476e-07,
      "loss": 0.0009,
      "reward": 1.609356164932251,
      "reward_std": 0.16089139878749847,
      "rewards/accuracy_reward": 0.49685609340667725,
      "rewards/format_reward": 1.0,
      "step": 528,
      "temperature": 1.0
    },
    {
      "all_correct": 0.625,
      "all_wrong": 0.0,
      "completion_length": 372.40625,
      "epoch": 0.016086850748084174,
      "grad_norm": 7.074046320438292,
      "kl": 0.0244140625,
      "learning_rate": 9.993616051419943e-07,
      "loss": 0.001,
      "reward": 2.0406250953674316,
      "reward_std": 0.2205134928226471,
      "rewards/accuracy_reward": 0.875,
      "rewards/format_reward": 1.0,
      "step": 529,
      "temperature": 1.0
    },
    {
      "all_correct": 0.625,
      "all_wrong": 0.125,
      "completion_length": 367.9375,
      "epoch": 0.016117260673883957,
      "grad_norm": 0.9390608563156165,
      "kl": 0.029052734375,
      "learning_rate": 9.993591897857423e-07,
      "loss": 0.0012,
      "reward": 1.84375,
      "reward_std": 0.14706888794898987,
      "rewards/accuracy_reward": 0.703125,
      "rewards/format_reward": 1.0,
      "step": 530,
      "temperature": 1.0
    },
    {
      "all_correct": 0.625,
      "all_wrong": 0.125,
      "completion_length": 375.03125,
      "epoch": 0.016147670599683736,
      "grad_norm": 1.3584662554495432,
      "kl": 0.0238037109375,
      "learning_rate": 9.993567698718136e-07,
      "loss": 0.001,
      "reward": 1.8705666065216064,
      "reward_std": 0.03462255001068115,
      "rewards/accuracy_reward": 0.7111915946006775,
      "rewards/format_reward": 1.0,
      "step": 531,
      "temperature": 1.0
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.25,
      "completion_length": 382.0625,
      "epoch": 0.01617808052548352,
      "grad_norm": 1.6917243155579849,
      "kl": 0.02587890625,
      "learning_rate": 9.993543454002303e-07,
      "loss": 0.001,
      "reward": 1.7641172409057617,
      "reward_std": 0.09114737808704376,
      "rewards/accuracy_reward": 0.635992169380188,
      "rewards/format_reward": 1.0,
      "step": 532,
      "temperature": 1.0
    },
    {
      "all_correct": 0.625,
      "all_wrong": 0.0,
      "completion_length": 372.84375,
      "epoch": 0.016208490451283298,
      "grad_norm": 1.1409825426174645,
      "kl": 0.0242919921875,
      "learning_rate": 9.993519163710146e-07,
      "loss": 0.001,
      "reward": 1.9512312412261963,
      "reward_std": 0.1779123693704605,
      "rewards/accuracy_reward": 0.7918561697006226,
      "rewards/format_reward": 1.0,
      "step": 533,
      "temperature": 1.0
    },
    {
      "all_correct": 0.625,
      "all_wrong": 0.125,
      "completion_length": 363.59375,
      "epoch": 0.01623890037708308,
      "grad_norm": 2.974921497398216,
      "kl": 0.021484375,
      "learning_rate": 9.993494827841886e-07,
      "loss": 0.0009,
      "reward": 1.935035228729248,
      "reward_std": 0.08776319026947021,
      "rewards/accuracy_reward": 0.769410252571106,
      "rewards/format_reward": 1.0,
      "step": 534,
      "temperature": 1.0
    },
    {
      "all_correct": 0.875,
      "all_wrong": 0.0,
      "completion_length": 353.0625,
      "epoch": 0.01626931030288286,
      "grad_norm": 5.620758565555608,
      "kl": 0.0279541015625,
      "learning_rate": 9.993470446397744e-07,
      "loss": 0.0011,
      "reward": 2.1281251907348633,
      "reward_std": 0.11572164297103882,
      "rewards/accuracy_reward": 0.953125,
      "rewards/format_reward": 1.0,
      "step": 535,
      "temperature": 1.0
    },
    {
      "all_correct": 0.625,
      "all_wrong": 0.125,
      "completion_length": 378.5,
      "epoch": 0.016299720228682642,
      "grad_norm": 1.0278039332585507,
      "kl": 0.0244140625,
      "learning_rate": 9.993446019377947e-07,
      "loss": 0.001,
      "reward": 1.8778808116912842,
      "reward_std": 0.016999786719679832,
      "rewards/accuracy_reward": 0.7060058116912842,
      "rewards/format_reward": 1.0,
      "step": 536,
      "temperature": 1.0
    },
    {
      "all_correct": 0.375,
      "all_wrong": 0.125,
      "completion_length": 444.421875,
      "epoch": 0.01633013015448242,
      "grad_norm": 6.56766491234196,
      "kl": 0.0167236328125,
      "learning_rate": 9.99342154678271e-07,
      "loss": 0.0007,
      "reward": 1.6468727588653564,
      "reward_std": 0.2497006356716156,
      "rewards/accuracy_reward": 0.5624977350234985,
      "rewards/format_reward": 0.96875,
      "step": 537,
      "temperature": 1.0
    },
    {
      "all_correct": 0.625,
      "all_wrong": 0.125,
      "completion_length": 359.765625,
      "epoch": 0.016360540080282204,
      "grad_norm": 0.9944108109794813,
      "kl": 0.0277099609375,
      "learning_rate": 9.993397028612264e-07,
      "loss": 0.0011,
      "reward": 1.8656251430511475,
      "reward_std": 0.17158037424087524,
      "rewards/accuracy_reward": 0.734375,
      "rewards/format_reward": 1.0,
      "step": 538,
      "temperature": 1.0
    },
    {
      "all_correct": 0.625,
      "all_wrong": 0.0,
      "completion_length": 390.5,
      "epoch": 0.016390950006081983,
      "grad_norm": 1.1496669474447838,
      "kl": 0.021240234375,
      "learning_rate": 9.99337246486683e-07,
      "loss": 0.0009,
      "reward": 1.96875,
      "reward_std": 0.12482766062021255,
      "rewards/accuracy_reward": 0.7999999523162842,
      "rewards/format_reward": 1.0,
      "step": 539,
      "temperature": 1.0
    },
    {
      "all_correct": 0.625,
      "all_wrong": 0.0,
      "completion_length": 396.203125,
      "epoch": 0.016421359931881766,
      "grad_norm": 1.8325948958130853,
      "kl": 0.0211181640625,
      "learning_rate": 9.993347855546632e-07,
      "loss": 0.0008,
      "reward": 1.988114833831787,
      "reward_std": 0.1748911738395691,
      "rewards/accuracy_reward": 0.8256146907806396,
      "rewards/format_reward": 1.0,
      "step": 540,
      "temperature": 1.0
    },
    {
      "all_correct": 0.375,
      "all_wrong": 0.375,
      "completion_length": 411.5,
      "epoch": 0.01645176985768155,
      "grad_norm": 4.3836195932159026,
      "kl": 0.0201416015625,
      "learning_rate": 9.993323200651894e-07,
      "loss": 0.0008,
      "reward": 1.5890107154846191,
      "reward_std": 0.01648581773042679,
      "rewards/accuracy_reward": 0.46401065587997437,
      "rewards/format_reward": 1.0,
      "step": 541,
      "temperature": 1.0
    },
    {
      "all_correct": 0.625,
      "all_wrong": 0.125,
      "completion_length": 367.15625,
      "epoch": 0.016482179783481328,
      "grad_norm": 2.2965032825537826,
      "kl": 0.0296630859375,
      "learning_rate": 9.99329850018284e-07,
      "loss": 0.0012,
      "reward": 1.887526512145996,
      "reward_std": 0.13017582893371582,
      "rewards/accuracy_reward": 0.7406514883041382,
      "rewards/format_reward": 1.0,
      "step": 542,
      "temperature": 1.0
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.0,
      "completion_length": 372.734375,
      "epoch": 0.01651258970928111,
      "grad_norm": 1.3938738879017516,
      "kl": 0.0255126953125,
      "learning_rate": 9.9932737541397e-07,
      "loss": 0.001,
      "reward": 1.8326916694641113,
      "reward_std": 0.1102554127573967,
      "rewards/accuracy_reward": 0.6639417409896851,
      "rewards/format_reward": 1.0,
      "step": 543,
      "temperature": 1.0
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.0,
      "completion_length": 423.0625,
      "epoch": 0.01654299963508089,
      "grad_norm": 1.3633646897373013,
      "kl": 0.0174560546875,
      "learning_rate": 9.993248962522695e-07,
      "loss": 0.0007,
      "reward": 1.8517284393310547,
      "reward_std": 0.11528775095939636,
      "rewards/accuracy_reward": 0.7017285227775574,
      "rewards/format_reward": 1.0,
      "step": 544,
      "temperature": 1.0
    },
    {
      "all_correct": 0.75,
      "all_wrong": 0.0,
      "completion_length": 367.125,
      "epoch": 0.016573409560880673,
      "grad_norm": 1.032095326324485,
      "kl": 0.023681640625,
      "learning_rate": 9.993224125332056e-07,
      "loss": 0.0009,
      "reward": 1.9763847589492798,
      "reward_std": 0.10624010860919952,
      "rewards/accuracy_reward": 0.8107597827911377,
      "rewards/format_reward": 1.0,
      "step": 545,
      "temperature": 1.0
    },
    {
      "all_correct": 0.625,
      "all_wrong": 0.125,
      "completion_length": 380.0625,
      "epoch": 0.01660381948668045,
      "grad_norm": 1.2163105023389043,
      "kl": 0.02734375,
      "learning_rate": 9.993199242568005e-07,
      "loss": 0.0011,
      "reward": 1.9005695581436157,
      "reward_std": 0.09277185052633286,
      "rewards/accuracy_reward": 0.7474446296691895,
      "rewards/format_reward": 1.0,
      "step": 546,
      "temperature": 1.0
    },
    {
      "all_correct": 0.625,
      "all_wrong": 0.0,
      "completion_length": 362.328125,
      "epoch": 0.016634229412480234,
      "grad_norm": 1.5977639445846574,
      "kl": 0.0299072265625,
      "learning_rate": 9.99317431423077e-07,
      "loss": 0.0012,
      "reward": 1.9183369874954224,
      "reward_std": 0.1112891435623169,
      "rewards/accuracy_reward": 0.7464619278907776,
      "rewards/format_reward": 1.0,
      "step": 547,
      "temperature": 1.0
    },
    {
      "all_correct": 0.375,
      "all_wrong": 0.125,
      "completion_length": 401.28125,
      "epoch": 0.016664639338280014,
      "grad_norm": 0.8467991021030187,
      "kl": 0.0218505859375,
      "learning_rate": 9.993149340320582e-07,
      "loss": 0.0009,
      "reward": 1.6057817935943604,
      "reward_std": 0.09839224815368652,
      "rewards/accuracy_reward": 0.4807818531990051,
      "rewards/format_reward": 1.0,
      "step": 548,
      "temperature": 1.0
    },
    {
      "all_correct": 0.625,
      "all_wrong": 0.25,
      "completion_length": 372.84375,
      "epoch": 0.016695049264079796,
      "grad_norm": 0.8357612606352839,
      "kl": 0.0255126953125,
      "learning_rate": 9.993124320837664e-07,
      "loss": 0.001,
      "reward": 1.8343751430511475,
      "reward_std": 0.09804397076368332,
      "rewards/accuracy_reward": 0.703125,
      "rewards/format_reward": 1.0,
      "step": 549,
      "temperature": 1.0
    },
    {
      "all_correct": 0.75,
      "all_wrong": 0.0,
      "completion_length": 375.5625,
      "epoch": 0.016725459189879575,
      "grad_norm": 1.407874959884774,
      "kl": 0.0201416015625,
      "learning_rate": 9.993099255782247e-07,
      "loss": 0.0008,
      "reward": 1.9874300956726074,
      "reward_std": 0.053691502660512924,
      "rewards/accuracy_reward": 0.8155549764633179,
      "rewards/format_reward": 1.0,
      "step": 550,
      "temperature": 1.0
    },
    {
      "all_correct": 0.375,
      "all_wrong": 0.125,
      "completion_length": 413.171875,
      "epoch": 0.016755869115679358,
      "grad_norm": 1.2613798808352086,
      "kl": 0.0186767578125,
      "learning_rate": 9.993074145154563e-07,
      "loss": 0.0007,
      "reward": 1.7065178155899048,
      "reward_std": 0.10608058422803879,
      "rewards/accuracy_reward": 0.5658928155899048,
      "rewards/format_reward": 1.0,
      "step": 551,
      "temperature": 1.0
    },
    {
      "all_correct": 0.75,
      "all_wrong": 0.125,
      "completion_length": 385.9375,
      "epoch": 0.016786279041479137,
      "grad_norm": 1.323970138211582,
      "kl": 0.0272216796875,
      "learning_rate": 9.993048988954833e-07,
      "loss": 0.0011,
      "reward": 2.006477117538452,
      "reward_std": 0.043110501021146774,
      "rewards/accuracy_reward": 0.8533520698547363,
      "rewards/format_reward": 1.0,
      "step": 552,
      "temperature": 1.0
    },
    {
      "all_correct": 0.625,
      "all_wrong": 0.125,
      "completion_length": 395.234375,
      "epoch": 0.01681668896727892,
      "grad_norm": 1.1793579264954002,
      "kl": 0.02783203125,
      "learning_rate": 9.993023787183295e-07,
      "loss": 0.0011,
      "reward": 1.9462419748306274,
      "reward_std": 0.07720139622688293,
      "rewards/accuracy_reward": 0.7837419509887695,
      "rewards/format_reward": 1.0,
      "step": 553,
      "temperature": 1.0
    },
    {
      "all_correct": 0.375,
      "all_wrong": 0.25,
      "completion_length": 365.03125,
      "epoch": 0.016847098893078703,
      "grad_norm": 0.8565651825875189,
      "kl": 0.027099609375,
      "learning_rate": 9.992998539840173e-07,
      "loss": 0.0011,
      "reward": 1.7223215103149414,
      "reward_std": 0.185908704996109,
      "rewards/accuracy_reward": 0.6004464626312256,
      "rewards/format_reward": 1.0,
      "step": 554,
      "temperature": 1.0
    },
    {
      "all_correct": 0.25,
      "all_wrong": 0.0,
      "completion_length": 393.5625,
      "epoch": 0.016877508818878482,
      "grad_norm": 1.3027761956048955,
      "kl": 0.0196533203125,
      "learning_rate": 9.992973246925703e-07,
      "loss": 0.0008,
      "reward": 1.6851897239685059,
      "reward_std": 0.28823140263557434,
      "rewards/accuracy_reward": 0.54768967628479,
      "rewards/format_reward": 1.0,
      "step": 555,
      "temperature": 1.0
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.25,
      "completion_length": 365.421875,
      "epoch": 0.016907918744678264,
      "grad_norm": 1.3601459447578725,
      "kl": 0.026611328125,
      "learning_rate": 9.99294790844011e-07,
      "loss": 0.0011,
      "reward": 1.6862847805023193,
      "reward_std": 0.08702725172042847,
      "rewards/accuracy_reward": 0.5581597089767456,
      "rewards/format_reward": 1.0,
      "step": 556,
      "temperature": 1.0
    },
    {
      "all_correct": 0.125,
      "all_wrong": 0.25,
      "completion_length": 400.640625,
      "epoch": 0.016938328670478044,
      "grad_norm": 1.2224024179890598,
      "kl": 0.022705078125,
      "learning_rate": 9.992922524383628e-07,
      "loss": 0.0009,
      "reward": 1.5042027235031128,
      "reward_std": 0.2732207775115967,
      "rewards/accuracy_reward": 0.41045260429382324,
      "rewards/format_reward": 1.0,
      "step": 557,
      "temperature": 1.0
    },
    {
      "all_correct": 0.625,
      "all_wrong": 0.0,
      "completion_length": 392.28125,
      "epoch": 0.016968738596277826,
      "grad_norm": 0.7617721605575297,
      "kl": 0.0205078125,
      "learning_rate": 9.992897094756492e-07,
      "loss": 0.0008,
      "reward": 1.9370760917663574,
      "reward_std": 0.15735886991024017,
      "rewards/accuracy_reward": 0.7745760679244995,
      "rewards/format_reward": 1.0,
      "step": 558,
      "temperature": 1.0
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.0,
      "completion_length": 369.78125,
      "epoch": 0.016999148522077605,
      "grad_norm": 1.3418875652939304,
      "kl": 0.023681640625,
      "learning_rate": 9.992871619558926e-07,
      "loss": 0.0009,
      "reward": 2.1012680530548096,
      "reward_std": 0.10392493009567261,
      "rewards/accuracy_reward": 0.9168931245803833,
      "rewards/format_reward": 1.0,
      "step": 559,
      "temperature": 1.0
    },
    {
      "all_correct": 0.375,
      "all_wrong": 0.0,
      "completion_length": 347.984375,
      "epoch": 0.017029558447877388,
      "grad_norm": 1.847504137402203,
      "kl": 0.029296875,
      "learning_rate": 9.992846098791172e-07,
      "loss": 0.0012,
      "reward": 1.8774423599243164,
      "reward_std": 0.2313249707221985,
      "rewards/accuracy_reward": 0.7211923599243164,
      "rewards/format_reward": 1.0,
      "step": 560,
      "temperature": 1.0
    },
    {
      "all_correct": 0.625,
      "all_wrong": 0.125,
      "completion_length": 384.15625,
      "epoch": 0.017059968373677167,
      "grad_norm": 5.146573220678828,
      "kl": 0.02490234375,
      "learning_rate": 9.992820532453453e-07,
      "loss": 0.001,
      "reward": 1.8488876819610596,
      "reward_std": 0.13339930772781372,
      "rewards/accuracy_reward": 0.7145127058029175,
      "rewards/format_reward": 1.0,
      "step": 561,
      "temperature": 1.0
    },
    {
      "all_correct": 0.625,
      "all_wrong": 0.125,
      "completion_length": 358.203125,
      "epoch": 0.01709037829947695,
      "grad_norm": 1.2601285290402524,
      "kl": 0.0250244140625,
      "learning_rate": 9.992794920546013e-07,
      "loss": 0.001,
      "reward": 1.9891787767410278,
      "reward_std": 0.0844581127166748,
      "rewards/accuracy_reward": 0.8298037052154541,
      "rewards/format_reward": 1.0,
      "step": 562,
      "temperature": 1.0
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.375,
      "completion_length": 361.28125,
      "epoch": 0.01712078822527673,
      "grad_norm": 1.297508343100705,
      "kl": 0.0255126953125,
      "learning_rate": 9.992769263069076e-07,
      "loss": 0.001,
      "reward": 1.6500000953674316,
      "reward_std": 0.09531005471944809,
      "rewards/accuracy_reward": 0.546875,
      "rewards/format_reward": 1.0,
      "step": 563,
      "temperature": 1.0
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.0,
      "completion_length": 418.65625,
      "epoch": 0.017151198151076512,
      "grad_norm": 1.13360117142651,
      "kl": 0.024658203125,
      "learning_rate": 9.992743560022883e-07,
      "loss": 0.001,
      "reward": 1.8644129037857056,
      "reward_std": 0.17236268520355225,
      "rewards/accuracy_reward": 0.7237879037857056,
      "rewards/format_reward": 1.0,
      "step": 564,
      "temperature": 1.0
    },
    {
      "all_correct": 0.625,
      "all_wrong": 0.125,
      "completion_length": 398.34375,
      "epoch": 0.01718160807687629,
      "grad_norm": 0.7635775165151959,
      "kl": 0.0267333984375,
      "learning_rate": 9.992717811407664e-07,
      "loss": 0.0011,
      "reward": 1.8516591787338257,
      "reward_std": 0.012908020056784153,
      "rewards/accuracy_reward": 0.6985341310501099,
      "rewards/format_reward": 1.0,
      "step": 565,
      "temperature": 1.0
    },
    {
      "all_correct": 0.625,
      "all_wrong": 0.25,
      "completion_length": 365.53125,
      "epoch": 0.017212018002676074,
      "grad_norm": 0.6447127086817688,
      "kl": 0.0244140625,
      "learning_rate": 9.992692017223659e-07,
      "loss": 0.001,
      "reward": 1.8047688007354736,
      "reward_std": 0.017000392079353333,
      "rewards/accuracy_reward": 0.657893717288971,
      "rewards/format_reward": 1.0,
      "step": 566,
      "temperature": 1.0
    },
    {
      "all_correct": 0.375,
      "all_wrong": 0.125,
      "completion_length": 401.953125,
      "epoch": 0.017242427928475853,
      "grad_norm": 1.5188734796293817,
      "kl": 0.0228271484375,
      "learning_rate": 9.992666177471098e-07,
      "loss": 0.0009,
      "reward": 1.7812390327453613,
      "reward_std": 0.1712251752614975,
      "rewards/accuracy_reward": 0.6343639492988586,
      "rewards/format_reward": 1.0,
      "step": 567,
      "temperature": 1.0
    },
    {
      "all_correct": 0.625,
      "all_wrong": 0.125,
      "completion_length": 369.734375,
      "epoch": 0.017272837854275636,
      "grad_norm": 1.201776688689362,
      "kl": 0.028076171875,
      "learning_rate": 9.99264029215022e-07,
      "loss": 0.0011,
      "reward": 1.91015625,
      "reward_std": 0.08285161852836609,
      "rewards/accuracy_reward": 0.757031261920929,
      "rewards/format_reward": 1.0,
      "step": 568,
      "temperature": 1.0
    },
    {
      "all_correct": 0.625,
      "all_wrong": 0.125,
      "completion_length": 388.75,
      "epoch": 0.017303247780075418,
      "grad_norm": 3.863676781286814,
      "kl": 0.0269775390625,
      "learning_rate": 9.992614361261262e-07,
      "loss": 0.0011,
      "reward": 1.845820426940918,
      "reward_std": 0.10071505606174469,
      "rewards/accuracy_reward": 0.7083203792572021,
      "rewards/format_reward": 1.0,
      "step": 569,
      "temperature": 1.0
    },
    {
      "all_correct": 0.75,
      "all_wrong": 0.0,
      "completion_length": 377.28125,
      "epoch": 0.017333657705875197,
      "grad_norm": 1.9407281459184562,
      "kl": 0.0302734375,
      "learning_rate": 9.992588384804456e-07,
      "loss": 0.0012,
      "reward": 2.1265625953674316,
      "reward_std": 0.12014105916023254,
      "rewards/accuracy_reward": 0.9390624761581421,
      "rewards/format_reward": 1.0,
      "step": 570,
      "temperature": 1.0
    },
    {
      "all_correct": 0.375,
      "all_wrong": 0.125,
      "completion_length": 403.953125,
      "epoch": 0.01736406763167498,
      "grad_norm": 1.2471813411969082,
      "kl": 0.0289306640625,
      "learning_rate": 9.992562362780047e-07,
      "loss": 0.0012,
      "reward": 1.7252793312072754,
      "reward_std": 0.12868757545948029,
      "rewards/accuracy_reward": 0.6065292358398438,
      "rewards/format_reward": 1.0,
      "step": 571,
      "temperature": 1.0
    },
    {
      "all_correct": 0.375,
      "all_wrong": 0.125,
      "completion_length": 387.25,
      "epoch": 0.01739447755747476,
      "grad_norm": 1.044655844615009,
      "kl": 0.0274658203125,
      "learning_rate": 9.992536295188265e-07,
      "loss": 0.0011,
      "reward": 1.7438277006149292,
      "reward_std": 0.22789573669433594,
      "rewards/accuracy_reward": 0.6188276410102844,
      "rewards/format_reward": 1.0,
      "step": 572,
      "temperature": 1.0
    },
    {
      "all_correct": 0.25,
      "all_wrong": 0.0,
      "completion_length": 410.4375,
      "epoch": 0.017424887483274542,
      "grad_norm": 1.7835064565347276,
      "kl": 0.0228271484375,
      "learning_rate": 9.99251018202935e-07,
      "loss": 0.0009,
      "reward": 1.7491974830627441,
      "reward_std": 0.1960187554359436,
      "rewards/accuracy_reward": 0.6085724234580994,
      "rewards/format_reward": 1.0,
      "step": 573,
      "temperature": 1.0
    },
    {
      "all_correct": 0.375,
      "all_wrong": 0.125,
      "completion_length": 402.25,
      "epoch": 0.01745529740907432,
      "grad_norm": 0.6861679592366509,
      "kl": 0.020751953125,
      "learning_rate": 9.992484023303542e-07,
      "loss": 0.0008,
      "reward": 1.6845179796218872,
      "reward_std": 0.15099084377288818,
      "rewards/accuracy_reward": 0.5626429319381714,
      "rewards/format_reward": 1.0,
      "step": 574,
      "temperature": 1.0
    },
    {
      "all_correct": 0.625,
      "all_wrong": 0.125,
      "completion_length": 404.5,
      "epoch": 0.017485707334874104,
      "grad_norm": 0.8191226747115254,
      "kl": 0.026123046875,
      "learning_rate": 9.99245781901108e-07,
      "loss": 0.001,
      "reward": 1.9397214651107788,
      "reward_std": 0.07836076617240906,
      "rewards/accuracy_reward": 0.7803462743759155,
      "rewards/format_reward": 1.0,
      "step": 575,
      "temperature": 1.0
    },
    {
      "all_correct": 0.375,
      "all_wrong": 0.125,
      "completion_length": 383.8125,
      "epoch": 0.017516117260673883,
      "grad_norm": 1.2632142879600834,
      "kl": 0.02587890625,
      "learning_rate": 9.992431569152201e-07,
      "loss": 0.001,
      "reward": 1.7038289308547974,
      "reward_std": 0.13528932631015778,
      "rewards/accuracy_reward": 0.5725789666175842,
      "rewards/format_reward": 1.0,
      "step": 576,
      "temperature": 1.0
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.125,
      "completion_length": 368.359375,
      "epoch": 0.017546527186473666,
      "grad_norm": 1.320968696932847,
      "kl": 0.02978515625,
      "learning_rate": 9.992405273727147e-07,
      "loss": 0.0012,
      "reward": 1.8704546689987183,
      "reward_std": 0.16585060954093933,
      "rewards/accuracy_reward": 0.7329545617103577,
      "rewards/format_reward": 1.0,
      "step": 577,
      "temperature": 1.0
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.25,
      "completion_length": 392.234375,
      "epoch": 0.017576937112273445,
      "grad_norm": 1.0909852075508653,
      "kl": 0.022705078125,
      "learning_rate": 9.992378932736154e-07,
      "loss": 0.0009,
      "reward": 1.6427083015441895,
      "reward_std": 0.11842279136180878,
      "rewards/accuracy_reward": 0.5364583730697632,
      "rewards/format_reward": 1.0,
      "step": 578,
      "temperature": 1.0
    },
    {
      "all_correct": 0.875,
      "all_wrong": 0.125,
      "completion_length": 358.265625,
      "epoch": 0.017607347038073227,
      "grad_norm": 0.6798318982385767,
      "kl": 0.031982421875,
      "learning_rate": 9.992352546179466e-07,
      "loss": 0.0013,
      "reward": 2.043750047683716,
      "reward_std": 0.017677675932645798,
      "rewards/accuracy_reward": 0.875,
      "rewards/format_reward": 1.0,
      "step": 579,
      "temperature": 1.0
    },
    {
      "all_correct": 0.75,
      "all_wrong": 0.0,
      "completion_length": 381.609375,
      "epoch": 0.017637756963873007,
      "grad_norm": 0.9814548381346477,
      "kl": 0.025634765625,
      "learning_rate": 9.992326114057325e-07,
      "loss": 0.001,
      "reward": 2.1030664443969727,
      "reward_std": 0.06711506098508835,
      "rewards/accuracy_reward": 0.9093164801597595,
      "rewards/format_reward": 1.0,
      "step": 580,
      "temperature": 1.0
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.0,
      "completion_length": 353.421875,
      "epoch": 0.01766816688967279,
      "grad_norm": 1.7524928879387054,
      "kl": 0.030517578125,
      "learning_rate": 9.992299636369968e-07,
      "loss": 0.0012,
      "reward": 1.9520833492279053,
      "reward_std": 0.22887161374092102,
      "rewards/accuracy_reward": 0.7864583730697632,
      "rewards/format_reward": 1.0,
      "step": 581,
      "temperature": 1.0
    },
    {
      "all_correct": 0.625,
      "all_wrong": 0.125,
      "completion_length": 397.109375,
      "epoch": 0.01769857681547257,
      "grad_norm": 1.8441756014952742,
      "kl": 0.0238037109375,
      "learning_rate": 9.99227311311764e-07,
      "loss": 0.001,
      "reward": 1.8849236965179443,
      "reward_std": 0.09047336131334305,
      "rewards/accuracy_reward": 0.7286736965179443,
      "rewards/format_reward": 1.0,
      "step": 582,
      "temperature": 1.0
    },
    {
      "all_correct": 0.625,
      "all_wrong": 0.25,
      "completion_length": 357.21875,
      "epoch": 0.01772898674127235,
      "grad_norm": 0.7585881955602598,
      "kl": 0.033203125,
      "learning_rate": 9.99224654430058e-07,
      "loss": 0.0013,
      "reward": 1.8382327556610107,
      "reward_std": 0.03417164087295532,
      "rewards/accuracy_reward": 0.6913577318191528,
      "rewards/format_reward": 1.0,
      "step": 583,
      "temperature": 1.0
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.125,
      "completion_length": 390.90625,
      "epoch": 0.017759396667072134,
      "grad_norm": 1.4220417144545328,
      "kl": 0.028564453125,
      "learning_rate": 9.992219929919034e-07,
      "loss": 0.0011,
      "reward": 1.718446135520935,
      "reward_std": 0.09436649829149246,
      "rewards/accuracy_reward": 0.5903211832046509,
      "rewards/format_reward": 1.0,
      "step": 584,
      "temperature": 1.0
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.0,
      "completion_length": 385.328125,
      "epoch": 0.017789806592871913,
      "grad_norm": 1.1784537671132156,
      "kl": 0.028564453125,
      "learning_rate": 9.992193269973245e-07,
      "loss": 0.0011,
      "reward": 1.747064471244812,
      "reward_std": 0.17472191154956818,
      "rewards/accuracy_reward": 0.6251895427703857,
      "rewards/format_reward": 1.0,
      "step": 585,
      "temperature": 1.0
    },
    {
      "all_correct": 0.375,
      "all_wrong": 0.0,
      "completion_length": 365.203125,
      "epoch": 0.017820216518671696,
      "grad_norm": 1.2275023818182955,
      "kl": 0.036865234375,
      "learning_rate": 9.99216656446345e-07,
      "loss": 0.0015,
      "reward": 1.877621054649353,
      "reward_std": 0.23138678073883057,
      "rewards/accuracy_reward": 0.7182459831237793,
      "rewards/format_reward": 1.0,
      "step": 586,
      "temperature": 1.0
    },
    {
      "all_correct": 0.625,
      "all_wrong": 0.125,
      "completion_length": 366.140625,
      "epoch": 0.017850626444471475,
      "grad_norm": 0.8485411730675455,
      "kl": 0.043212890625,
      "learning_rate": 9.9921398133899e-07,
      "loss": 0.0017,
      "reward": 1.920138955116272,
      "reward_std": 0.10352161526679993,
      "rewards/accuracy_reward": 0.7638888955116272,
      "rewards/format_reward": 1.0,
      "step": 587,
      "temperature": 1.0
    },
    {
      "all_correct": 0.75,
      "all_wrong": 0.0,
      "completion_length": 376.171875,
      "epoch": 0.017881036370271258,
      "grad_norm": 0.9688169079096972,
      "kl": 0.0419921875,
      "learning_rate": 9.992113016752836e-07,
      "loss": 0.0017,
      "reward": 2.0319104194641113,
      "reward_std": 0.10207494348287582,
      "rewards/accuracy_reward": 0.8475353717803955,
      "rewards/format_reward": 1.0,
      "step": 588,
      "temperature": 1.0
    },
    {
      "all_correct": 0.625,
      "all_wrong": 0.0,
      "completion_length": 380.109375,
      "epoch": 0.017911446296071037,
      "grad_norm": 2.049074380961269,
      "kl": 0.044921875,
      "learning_rate": 9.992086174552505e-07,
      "loss": 0.0018,
      "reward": 1.8737730979919434,
      "reward_std": 0.12766709923744202,
      "rewards/accuracy_reward": 0.7175230383872986,
      "rewards/format_reward": 1.0,
      "step": 589,
      "temperature": 1.0
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.0,
      "completion_length": 413.609375,
      "epoch": 0.01794185622187082,
      "grad_norm": 1.079514699091543,
      "kl": 0.044921875,
      "learning_rate": 9.992059286789147e-07,
      "loss": 0.0018,
      "reward": 1.8300812244415283,
      "reward_std": 0.1272916942834854,
      "rewards/accuracy_reward": 0.7175811529159546,
      "rewards/format_reward": 0.9375,
      "step": 590,
      "temperature": 1.0
    },
    {
      "all_correct": 0.75,
      "all_wrong": 0.0,
      "completion_length": 362.0625,
      "epoch": 0.0179722661476706,
      "grad_norm": 1.184987882050577,
      "kl": 0.05029296875,
      "learning_rate": 9.992032353463013e-07,
      "loss": 0.002,
      "reward": 2.0025362968444824,
      "reward_std": 0.09839466959238052,
      "rewards/accuracy_reward": 0.8306612372398376,
      "rewards/format_reward": 1.0,
      "step": 591,
      "temperature": 1.0
    },
    {
      "all_correct": 0.25,
      "all_wrong": 0.0,
      "completion_length": 363.546875,
      "epoch": 0.01800267607347038,
      "grad_norm": 1.4697981828305116,
      "kl": 0.041015625,
      "learning_rate": 9.992005374574345e-07,
      "loss": 0.0016,
      "reward": 1.752118468284607,
      "reward_std": 0.23267632722854614,
      "rewards/accuracy_reward": 0.6052433252334595,
      "rewards/format_reward": 1.0,
      "step": 592,
      "temperature": 1.0
    },
    {
      "all_correct": 0.75,
      "all_wrong": 0.0,
      "completion_length": 350.546875,
      "epoch": 0.01803308599927016,
      "grad_norm": 1.127629496102784,
      "kl": 0.049560546875,
      "learning_rate": 9.991978350123391e-07,
      "loss": 0.002,
      "reward": 2.040572166442871,
      "reward_std": 0.09483858942985535,
      "rewards/accuracy_reward": 0.871821939945221,
      "rewards/format_reward": 1.0,
      "step": 593,
      "temperature": 1.0
    },
    {
      "all_correct": 0.25,
      "all_wrong": 0.375,
      "completion_length": 375.453125,
      "epoch": 0.018063495925069943,
      "grad_norm": 1.0819872217855888,
      "kl": 0.043701171875,
      "learning_rate": 9.991951280110396e-07,
      "loss": 0.0018,
      "reward": 1.5016298294067383,
      "reward_std": 0.09979674220085144,
      "rewards/accuracy_reward": 0.40787991881370544,
      "rewards/format_reward": 1.0,
      "step": 594,
      "temperature": 1.0
    },
    {
      "all_correct": 0.75,
      "all_wrong": 0.0,
      "completion_length": 361.296875,
      "epoch": 0.018093905850869722,
      "grad_norm": 2.299313232393947,
      "kl": 0.048095703125,
      "learning_rate": 9.99192416453561e-07,
      "loss": 0.0019,
      "reward": 2.0348854064941406,
      "reward_std": 0.04809385538101196,
      "rewards/accuracy_reward": 0.8536352515220642,
      "rewards/format_reward": 1.0,
      "step": 595,
      "temperature": 1.0
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.0,
      "completion_length": 396.90625,
      "epoch": 0.018124315776669505,
      "grad_norm": 1.7685658559941535,
      "kl": 0.046142578125,
      "learning_rate": 9.991897003399279e-07,
      "loss": 0.0018,
      "reward": 1.8747129440307617,
      "reward_std": 0.2227209508419037,
      "rewards/accuracy_reward": 0.7215878963470459,
      "rewards/format_reward": 1.0,
      "step": 596,
      "temperature": 1.0
    },
    {
      "all_correct": 0.625,
      "all_wrong": 0.125,
      "completion_length": 367.125,
      "epoch": 0.018154725702469288,
      "grad_norm": 2.0385906210110503,
      "kl": 0.051513671875,
      "learning_rate": 9.991869796701648e-07,
      "loss": 0.0021,
      "reward": 1.8681142330169678,
      "reward_std": 0.04913956671953201,
      "rewards/accuracy_reward": 0.708739161491394,
      "rewards/format_reward": 1.0,
      "step": 597,
      "temperature": 1.0
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.125,
      "completion_length": 402.71875,
      "epoch": 0.018185135628269067,
      "grad_norm": 1.042504465270702,
      "kl": 0.0419921875,
      "learning_rate": 9.99184254444297e-07,
      "loss": 0.0017,
      "reward": 1.8252263069152832,
      "reward_std": 0.15027400851249695,
      "rewards/accuracy_reward": 0.6783512830734253,
      "rewards/format_reward": 1.0,
      "step": 598,
      "temperature": 1.0
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.125,
      "completion_length": 364.859375,
      "epoch": 0.01821554555406885,
      "grad_norm": 1.290359576104531,
      "kl": 0.048095703125,
      "learning_rate": 9.991815246623493e-07,
      "loss": 0.0019,
      "reward": 1.8686763048171997,
      "reward_std": 0.13960713148117065,
      "rewards/accuracy_reward": 0.706176221370697,
      "rewards/format_reward": 1.0,
      "step": 599,
      "temperature": 1.0
    },
    {
      "all_correct": 0.375,
      "all_wrong": 0.375,
      "completion_length": 413.21875,
      "epoch": 0.01824595547986863,
      "grad_norm": 0.9688752544396189,
      "kl": 0.038330078125,
      "learning_rate": 9.991787903243463e-07,
      "loss": 0.0015,
      "reward": 1.536142349243164,
      "reward_std": 0.01596335880458355,
      "rewards/accuracy_reward": 0.4236423671245575,
      "rewards/format_reward": 1.0,
      "step": 600,
      "temperature": 1.0
    },
    {
      "all_correct": 0.25,
      "all_wrong": 0.125,
      "completion_length": 370.296875,
      "epoch": 0.01827636540566841,
      "grad_norm": 1.3873465516859986,
      "kl": 0.04443359375,
      "learning_rate": 9.991760514303132e-07,
      "loss": 0.0018,
      "reward": 1.8008612394332886,
      "reward_std": 0.2821829617023468,
      "rewards/accuracy_reward": 0.660236120223999,
      "rewards/format_reward": 1.0,
      "step": 601,
      "temperature": 1.0
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.125,
      "completion_length": 404.25,
      "epoch": 0.01830677533146819,
      "grad_norm": 0.9322885161877308,
      "kl": 0.0294189453125,
      "learning_rate": 9.991733079802748e-07,
      "loss": 0.0012,
      "reward": 1.9062501192092896,
      "reward_std": 0.2160109579563141,
      "rewards/accuracy_reward": 0.765625,
      "rewards/format_reward": 1.0,
      "step": 602,
      "temperature": 1.0
    },
    {
      "all_correct": 0.125,
      "all_wrong": 0.375,
      "completion_length": 396.359375,
      "epoch": 0.018337185257267973,
      "grad_norm": 1.2546804699904273,
      "kl": 0.0308837890625,
      "learning_rate": 9.991705599742564e-07,
      "loss": 0.0012,
      "reward": 1.4027683734893799,
      "reward_std": 0.24704982340335846,
      "rewards/accuracy_reward": 0.3371432423591614,
      "rewards/format_reward": 0.984375,
      "step": 603,
      "temperature": 1.0
    },
    {
      "all_correct": 0.75,
      "all_wrong": 0.0,
      "completion_length": 403.15625,
      "epoch": 0.018367595183067752,
      "grad_norm": 0.959492014454973,
      "kl": 0.033203125,
      "learning_rate": 9.991678074122828e-07,
      "loss": 0.0013,
      "reward": 2.008178234100342,
      "reward_std": 0.027123089879751205,
      "rewards/accuracy_reward": 0.8269281387329102,
      "rewards/format_reward": 1.0,
      "step": 604,
      "temperature": 1.0
    },
    {
      "all_correct": 0.625,
      "all_wrong": 0.0,
      "completion_length": 387.0625,
      "epoch": 0.018398005108867535,
      "grad_norm": 1.1539315805318402,
      "kl": 0.0240478515625,
      "learning_rate": 9.991650502943795e-07,
      "loss": 0.001,
      "reward": 1.9461710453033447,
      "reward_std": 0.07115110754966736,
      "rewards/accuracy_reward": 0.7680459022521973,
      "rewards/format_reward": 1.0,
      "step": 605,
      "temperature": 1.0
    },
    {
      "all_correct": 0.625,
      "all_wrong": 0.125,
      "completion_length": 395.578125,
      "epoch": 0.018428415034667314,
      "grad_norm": 0.6221506136131344,
      "kl": 0.0252685546875,
      "learning_rate": 9.991622886205714e-07,
      "loss": 0.001,
      "reward": 1.8969091176986694,
      "reward_std": 0.08935505896806717,
      "rewards/accuracy_reward": 0.7344090938568115,
      "rewards/format_reward": 1.0,
      "step": 606,
      "temperature": 1.0
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.125,
      "completion_length": 387.0,
      "epoch": 0.018458824960467097,
      "grad_norm": 1.4029656502284182,
      "kl": 0.029541015625,
      "learning_rate": 9.991595223908837e-07,
      "loss": 0.0012,
      "reward": 1.8726065158843994,
      "reward_std": 0.13873696327209473,
      "rewards/accuracy_reward": 0.7132315635681152,
      "rewards/format_reward": 1.0,
      "step": 607,
      "temperature": 1.0
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.25,
      "completion_length": 381.609375,
      "epoch": 0.018489234886266876,
      "grad_norm": 0.946494106311795,
      "kl": 0.03466796875,
      "learning_rate": 9.991567516053417e-07,
      "loss": 0.0014,
      "reward": 1.7780226469039917,
      "reward_std": 0.042960405349731445,
      "rewards/accuracy_reward": 0.6342726349830627,
      "rewards/format_reward": 1.0,
      "step": 608,
      "temperature": 1.0
    },
    {
      "all_correct": 0.25,
      "all_wrong": 0.375,
      "completion_length": 390.015625,
      "epoch": 0.01851964481206666,
      "grad_norm": 1.037715430840855,
      "kl": 0.031982421875,
      "learning_rate": 9.991539762639706e-07,
      "loss": 0.0013,
      "reward": 1.4132628440856934,
      "reward_std": 0.11848343908786774,
      "rewards/accuracy_reward": 0.34138786792755127,
      "rewards/format_reward": 1.0,
      "step": 609,
      "temperature": 1.0
    },
    {
      "all_correct": 0.625,
      "all_wrong": 0.25,
      "completion_length": 369.578125,
      "epoch": 0.018550054737866438,
      "grad_norm": 0.7840780869029643,
      "kl": 0.0283203125,
      "learning_rate": 9.99151196366796e-07,
      "loss": 0.0011,
      "reward": 1.8250000476837158,
      "reward_std": 0.08017837256193161,
      "rewards/accuracy_reward": 0.6875,
      "rewards/format_reward": 1.0,
      "step": 610,
      "temperature": 1.0
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.125,
      "completion_length": 387.046875,
      "epoch": 0.01858046466366622,
      "grad_norm": 1.0261828832554214,
      "kl": 0.03173828125,
      "learning_rate": 9.991484119138432e-07,
      "loss": 0.0013,
      "reward": 1.7433415651321411,
      "reward_std": 0.1010158360004425,
      "rewards/accuracy_reward": 0.5995915532112122,
      "rewards/format_reward": 1.0,
      "step": 611,
      "temperature": 1.0
    },
    {
      "all_correct": 0.875,
      "all_wrong": 0.0,
      "completion_length": 379.671875,
      "epoch": 0.018610874589466003,
      "grad_norm": 0.9730297737043242,
      "kl": 0.035400390625,
      "learning_rate": 9.99145622905137e-07,
      "loss": 0.0014,
      "reward": 2.0426056385040283,
      "reward_std": 0.024341296404600143,
      "rewards/accuracy_reward": 0.8769806623458862,
      "rewards/format_reward": 1.0,
      "step": 612,
      "temperature": 1.0
    },
    {
      "all_correct": 0.25,
      "all_wrong": 0.25,
      "completion_length": 408.453125,
      "epoch": 0.018641284515265782,
      "grad_norm": 1.9103427318156068,
      "kl": 0.0233154296875,
      "learning_rate": 9.991428293407039e-07,
      "loss": 0.0009,
      "reward": 1.6917380094528198,
      "reward_std": 0.13564084470272064,
      "rewards/accuracy_reward": 0.5792379379272461,
      "rewards/format_reward": 1.0,
      "step": 613,
      "temperature": 1.0
    },
    {
      "all_correct": 0.625,
      "all_wrong": 0.125,
      "completion_length": 388.0625,
      "epoch": 0.018671694441065565,
      "grad_norm": 0.9620525986388728,
      "kl": 0.032470703125,
      "learning_rate": 9.991400312205686e-07,
      "loss": 0.0013,
      "reward": 1.8695738315582275,
      "reward_std": 0.030544929206371307,
      "rewards/accuracy_reward": 0.7101988196372986,
      "rewards/format_reward": 1.0,
      "step": 614,
      "temperature": 1.0
    },
    {
      "all_correct": 0.25,
      "all_wrong": 0.25,
      "completion_length": 397.671875,
      "epoch": 0.018702104366865344,
      "grad_norm": 1.2947269515086028,
      "kl": 0.0289306640625,
      "learning_rate": 9.99137228544757e-07,
      "loss": 0.0012,
      "reward": 1.5723220109939575,
      "reward_std": 0.14814886450767517,
      "rewards/accuracy_reward": 0.4660719037055969,
      "rewards/format_reward": 1.0,
      "step": 615,
      "temperature": 1.0
    },
    {
      "all_correct": 0.375,
      "all_wrong": 0.25,
      "completion_length": 397.28125,
      "epoch": 0.018732514292665127,
      "grad_norm": 1.0433791479046082,
      "kl": 0.0279541015625,
      "learning_rate": 9.991344213132945e-07,
      "loss": 0.0011,
      "reward": 1.583266258239746,
      "reward_std": 0.03504175692796707,
      "rewards/accuracy_reward": 0.47701627016067505,
      "rewards/format_reward": 1.0,
      "step": 616,
      "temperature": 1.0
    },
    {
      "all_correct": 0.375,
      "all_wrong": 0.25,
      "completion_length": 365.15625,
      "epoch": 0.018762924218464906,
      "grad_norm": 2.5383366534843463,
      "kl": 0.02587890625,
      "learning_rate": 9.991316095262068e-07,
      "loss": 0.001,
      "reward": 1.7088302373886108,
      "reward_std": 0.076881043612957,
      "rewards/accuracy_reward": 0.5650802850723267,
      "rewards/format_reward": 1.0,
      "step": 617,
      "temperature": 1.0
    },
    {
      "all_correct": 0.125,
      "all_wrong": 0.125,
      "completion_length": 395.234375,
      "epoch": 0.01879333414426469,
      "grad_norm": 1.3724658192691543,
      "kl": 0.0240478515625,
      "learning_rate": 9.991287931835197e-07,
      "loss": 0.001,
      "reward": 1.4778103828430176,
      "reward_std": 0.25440776348114014,
      "rewards/accuracy_reward": 0.36218535900115967,
      "rewards/format_reward": 1.0,
      "step": 618,
      "temperature": 1.0
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.25,
      "completion_length": 388.8125,
      "epoch": 0.018823744070064468,
      "grad_norm": 0.7453644057197045,
      "kl": 0.0244140625,
      "learning_rate": 9.991259722852585e-07,
      "loss": 0.001,
      "reward": 1.6281249523162842,
      "reward_std": 0.09722718596458435,
      "rewards/accuracy_reward": 0.53125,
      "rewards/format_reward": 1.0,
      "step": 619,
      "temperature": 1.0
    },
    {
      "all_correct": 0.625,
      "all_wrong": 0.0,
      "completion_length": 406.125,
      "epoch": 0.01885415399586425,
      "grad_norm": 1.2339587864139192,
      "kl": 0.02294921875,
      "learning_rate": 9.991231468314494e-07,
      "loss": 0.0009,
      "reward": 2.0086283683776855,
      "reward_std": 0.12564092874526978,
      "rewards/accuracy_reward": 0.836753249168396,
      "rewards/format_reward": 1.0,
      "step": 620,
      "temperature": 1.0
    },
    {
      "all_correct": 0.125,
      "all_wrong": 0.375,
      "completion_length": 364.390625,
      "epoch": 0.01888456392166403,
      "grad_norm": 0.95049834766344,
      "kl": 0.022216796875,
      "learning_rate": 9.99120316822118e-07,
      "loss": 0.0009,
      "reward": 1.5004464387893677,
      "reward_std": 0.2071518450975418,
      "rewards/accuracy_reward": 0.4129464626312256,
      "rewards/format_reward": 1.0,
      "step": 621,
      "temperature": 1.0
    },
    {
      "all_correct": 0.625,
      "all_wrong": 0.0,
      "completion_length": 362.734375,
      "epoch": 0.018914973847463813,
      "grad_norm": 1.2009901201034807,
      "kl": 0.0311279296875,
      "learning_rate": 9.9911748225729e-07,
      "loss": 0.0012,
      "reward": 1.916428804397583,
      "reward_std": 0.11666810512542725,
      "rewards/accuracy_reward": 0.750803530216217,
      "rewards/format_reward": 1.0,
      "step": 622,
      "temperature": 1.0
    },
    {
      "all_correct": 0.625,
      "all_wrong": 0.125,
      "completion_length": 398.90625,
      "epoch": 0.01894538377326359,
      "grad_norm": 1.3025178576870173,
      "kl": 0.0240478515625,
      "learning_rate": 9.991146431369917e-07,
      "loss": 0.001,
      "reward": 1.8494185209274292,
      "reward_std": 0.09329584240913391,
      "rewards/accuracy_reward": 0.6994185447692871,
      "rewards/format_reward": 1.0,
      "step": 623,
      "temperature": 1.0
    },
    {
      "all_correct": 0.625,
      "all_wrong": 0.375,
      "completion_length": 359.1875,
      "epoch": 0.018975793699063374,
      "grad_norm": 1.0312548818320586,
      "kl": 0.02587890625,
      "learning_rate": 9.991117994612484e-07,
      "loss": 0.001,
      "reward": 1.743749976158142,
      "reward_std": 0.017677675932645798,
      "rewards/accuracy_reward": 0.625,
      "rewards/format_reward": 1.0,
      "step": 624,
      "temperature": 1.0
    },
    {
      "all_correct": 0.125,
      "all_wrong": 0.25,
      "completion_length": 355.953125,
      "epoch": 0.019006203624863157,
      "grad_norm": 1.586765348164984,
      "kl": 0.0274658203125,
      "learning_rate": 9.991089512300866e-07,
      "loss": 0.0011,
      "reward": 1.4598374366760254,
      "reward_std": 0.21847301721572876,
      "rewards/accuracy_reward": 0.387962281703949,
      "rewards/format_reward": 1.0,
      "step": 625,
      "temperature": 1.0
    },
    {
      "all_correct": 0.375,
      "all_wrong": 0.25,
      "completion_length": 363.765625,
      "epoch": 0.019036613550662936,
      "grad_norm": 1.6605294163803124,
      "kl": 0.02587890625,
      "learning_rate": 9.991060984435318e-07,
      "loss": 0.001,
      "reward": 1.5627896785736084,
      "reward_std": 0.03303666040301323,
      "rewards/accuracy_reward": 0.46591466665267944,
      "rewards/format_reward": 1.0,
      "step": 626,
      "temperature": 1.0
    },
    {
      "all_correct": 0.75,
      "all_wrong": 0.25,
      "completion_length": 363.453125,
      "epoch": 0.01906702347646272,
      "grad_norm": 0.6995419795539591,
      "kl": 0.02587890625,
      "learning_rate": 9.991032411016104e-07,
      "loss": 0.001,
      "reward": 1.896875023841858,
      "reward_std": 0.008838837966322899,
      "rewards/accuracy_reward": 0.75,
      "rewards/format_reward": 1.0,
      "step": 627,
      "temperature": 1.0
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.0,
      "completion_length": 380.828125,
      "epoch": 0.019097433402262498,
      "grad_norm": 1.4560804773452942,
      "kl": 0.02490234375,
      "learning_rate": 9.991003792043487e-07,
      "loss": 0.001,
      "reward": 1.8818953037261963,
      "reward_std": 0.11065559089183807,
      "rewards/accuracy_reward": 0.700645387172699,
      "rewards/format_reward": 1.0,
      "step": 628,
      "temperature": 1.0
    },
    {
      "all_correct": 0.25,
      "all_wrong": 0.25,
      "completion_length": 398.65625,
      "epoch": 0.01912784332806228,
      "grad_norm": 1.208267871406542,
      "kl": 0.0213623046875,
      "learning_rate": 9.990975127517722e-07,
      "loss": 0.0009,
      "reward": 1.6488420963287354,
      "reward_std": 0.22068798542022705,
      "rewards/accuracy_reward": 0.5269670486450195,
      "rewards/format_reward": 1.0,
      "step": 629,
      "temperature": 1.0
    },
    {
      "all_correct": 0.25,
      "all_wrong": 0.25,
      "completion_length": 387.65625,
      "epoch": 0.01915825325386206,
      "grad_norm": 1.5769873858782995,
      "kl": 0.0223388671875,
      "learning_rate": 9.990946417439074e-07,
      "loss": 0.0009,
      "reward": 1.6526292562484741,
      "reward_std": 0.17980273067951202,
      "rewards/accuracy_reward": 0.5338792204856873,
      "rewards/format_reward": 1.0,
      "step": 630,
      "temperature": 1.0
    },
    {
      "all_correct": 0.375,
      "all_wrong": 0.0,
      "completion_length": 372.796875,
      "epoch": 0.019188663179661843,
      "grad_norm": 2.0264850387179063,
      "kl": 0.025146484375,
      "learning_rate": 9.990917661807804e-07,
      "loss": 0.001,
      "reward": 1.82393217086792,
      "reward_std": 0.2524424195289612,
      "rewards/accuracy_reward": 0.6833070516586304,
      "rewards/format_reward": 1.0,
      "step": 631,
      "temperature": 1.0
    },
    {
      "all_correct": 0.625,
      "all_wrong": 0.125,
      "completion_length": 390.421875,
      "epoch": 0.019219073105461622,
      "grad_norm": 1.258693282315969,
      "kl": 0.02294921875,
      "learning_rate": 9.990888860624177e-07,
      "loss": 0.0009,
      "reward": 1.90625,
      "reward_std": 0.15655069053173065,
      "rewards/accuracy_reward": 0.765625,
      "rewards/format_reward": 1.0,
      "step": 632,
      "temperature": 1.0
    },
    {
      "all_correct": 0.375,
      "all_wrong": 0.0,
      "completion_length": 362.28125,
      "epoch": 0.019249483031261404,
      "grad_norm": 1.5277042477361833,
      "kl": 0.0281982421875,
      "learning_rate": 9.990860013888451e-07,
      "loss": 0.0011,
      "reward": 1.8355580568313599,
      "reward_std": 0.27930980920791626,
      "rewards/accuracy_reward": 0.6980580687522888,
      "rewards/format_reward": 1.0,
      "step": 633,
      "temperature": 1.0
    },
    {
      "all_correct": 0.625,
      "all_wrong": 0.0,
      "completion_length": 384.796875,
      "epoch": 0.019279892957061184,
      "grad_norm": 2.950728724003849,
      "kl": 0.02685546875,
      "learning_rate": 9.990831121600895e-07,
      "loss": 0.0011,
      "reward": 1.9457731246948242,
      "reward_std": 0.11338792741298676,
      "rewards/accuracy_reward": 0.7707730531692505,
      "rewards/format_reward": 1.0,
      "step": 634,
      "temperature": 1.0
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.125,
      "completion_length": 358.8125,
      "epoch": 0.019310302882860966,
      "grad_norm": 1.5388133363613137,
      "kl": 0.0283203125,
      "learning_rate": 9.99080218376177e-07,
      "loss": 0.0011,
      "reward": 1.7218749523162842,
      "reward_std": 0.17485956847667694,
      "rewards/accuracy_reward": 0.609375,
      "rewards/format_reward": 1.0,
      "step": 635,
      "temperature": 1.0
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.0,
      "completion_length": 386.390625,
      "epoch": 0.019340712808660745,
      "grad_norm": 2.165420667802019,
      "kl": 0.025146484375,
      "learning_rate": 9.99077320037134e-07,
      "loss": 0.001,
      "reward": 1.8524532318115234,
      "reward_std": 0.13530555367469788,
      "rewards/accuracy_reward": 0.6774532198905945,
      "rewards/format_reward": 1.0,
      "step": 636,
      "temperature": 1.0
    },
    {
      "all_correct": 0.625,
      "all_wrong": 0.0,
      "completion_length": 362.015625,
      "epoch": 0.019371122734460528,
      "grad_norm": 1.24873374676275,
      "kl": 0.0250244140625,
      "learning_rate": 9.990744171429867e-07,
      "loss": 0.001,
      "reward": 2.0134856700897217,
      "reward_std": 0.19197435677051544,
      "rewards/accuracy_reward": 0.8416104912757874,
      "rewards/format_reward": 1.0,
      "step": 637,
      "temperature": 1.0
    },
    {
      "all_correct": 0.375,
      "all_wrong": 0.0,
      "completion_length": 376.625,
      "epoch": 0.019401532660260307,
      "grad_norm": 1.5195214629791318,
      "kl": 0.02685546875,
      "learning_rate": 9.99071509693762e-07,
      "loss": 0.0011,
      "reward": 1.7479314804077148,
      "reward_std": 0.19491618871688843,
      "rewards/accuracy_reward": 0.6041814088821411,
      "rewards/format_reward": 1.0,
      "step": 638,
      "temperature": 1.0
    },
    {
      "all_correct": 0.25,
      "all_wrong": 0.125,
      "completion_length": 413.71875,
      "epoch": 0.01943194258606009,
      "grad_norm": 1.4126931807642382,
      "kl": 0.019287109375,
      "learning_rate": 9.990685976894865e-07,
      "loss": 0.0008,
      "reward": 1.5989735126495361,
      "reward_std": 0.208685964345932,
      "rewards/accuracy_reward": 0.4958483576774597,
      "rewards/format_reward": 1.0,
      "step": 639,
      "temperature": 1.0
    },
    {
      "all_correct": 0.375,
      "all_wrong": 0.125,
      "completion_length": 399.015625,
      "epoch": 0.019462352511859873,
      "grad_norm": 2.458838051486715,
      "kl": 0.0260009765625,
      "learning_rate": 9.990656811301864e-07,
      "loss": 0.001,
      "reward": 1.6153169870376587,
      "reward_std": 0.19008949398994446,
      "rewards/accuracy_reward": 0.5059419870376587,
      "rewards/format_reward": 1.0,
      "step": 640,
      "temperature": 1.0
    },
    {
      "all_correct": 0.625,
      "all_wrong": 0.25,
      "completion_length": 383.3125,
      "epoch": 0.019492762437659652,
      "grad_norm": 0.5127573351760508,
      "kl": 0.028076171875,
      "learning_rate": 9.990627600158885e-07,
      "loss": 0.0011,
      "reward": 1.8062500953674316,
      "reward_std": 0.077632375061512,
      "rewards/accuracy_reward": 0.671875,
      "rewards/format_reward": 1.0,
      "step": 641,
      "temperature": 1.0
    },
    {
      "all_correct": 0.625,
      "all_wrong": 0.0,
      "completion_length": 379.890625,
      "epoch": 0.019523172363459435,
      "grad_norm": 3.630182420875963,
      "kl": 0.0302734375,
      "learning_rate": 9.990598343466197e-07,
      "loss": 0.0012,
      "reward": 2.026771306991577,
      "reward_std": 0.1488124430179596,
      "rewards/accuracy_reward": 0.8392711877822876,
      "rewards/format_reward": 1.0,
      "step": 642,
      "temperature": 1.0
    },
    {
      "all_correct": 0.875,
      "all_wrong": 0.0,
      "completion_length": 375.140625,
      "epoch": 0.019553582289259214,
      "grad_norm": 0.829760302162651,
      "kl": 0.0291748046875,
      "learning_rate": 9.990569041224063e-07,
      "loss": 0.0012,
      "reward": 2.075000047683716,
      "reward_std": 0.02314549870789051,
      "rewards/accuracy_reward": 0.8937500715255737,
      "rewards/format_reward": 1.0,
      "step": 643,
      "temperature": 1.0
    },
    {
      "all_correct": 0.25,
      "all_wrong": 0.25,
      "completion_length": 410.203125,
      "epoch": 0.019583992215058996,
      "grad_norm": 0.8511825180955228,
      "kl": 0.02294921875,
      "learning_rate": 9.990539693432748e-07,
      "loss": 0.0009,
      "reward": 1.6409912109375,
      "reward_std": 0.15731123089790344,
      "rewards/accuracy_reward": 0.5284910202026367,
      "rewards/format_reward": 1.0,
      "step": 644,
      "temperature": 1.0
    },
    {
      "all_correct": 0.75,
      "all_wrong": 0.125,
      "completion_length": 363.265625,
      "epoch": 0.019614402140858776,
      "grad_norm": 1.3223514324793195,
      "kl": 0.036376953125,
      "learning_rate": 9.99051030009253e-07,
      "loss": 0.0015,
      "reward": 1.950523018836975,
      "reward_std": 0.03516820818185806,
      "rewards/accuracy_reward": 0.7880231142044067,
      "rewards/format_reward": 1.0,
      "step": 645,
      "temperature": 1.0
    },
    {
      "all_correct": 0.75,
      "all_wrong": 0.0,
      "completion_length": 398.78125,
      "epoch": 0.019644812066658558,
      "grad_norm": 2.099031418276086,
      "kl": 0.0252685546875,
      "learning_rate": 9.990480861203668e-07,
      "loss": 0.001,
      "reward": 2.1360092163085938,
      "reward_std": 0.06928229331970215,
      "rewards/accuracy_reward": 0.9516341090202332,
      "rewards/format_reward": 1.0,
      "step": 646,
      "temperature": 1.0
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.125,
      "completion_length": 407.46875,
      "epoch": 0.019675221992458337,
      "grad_norm": 4.173178054074948,
      "kl": 0.0281982421875,
      "learning_rate": 9.990451376766434e-07,
      "loss": 0.0011,
      "reward": 1.7876081466674805,
      "reward_std": 0.08835624903440475,
      "rewards/accuracy_reward": 0.6407331824302673,
      "rewards/format_reward": 1.0,
      "step": 647,
      "temperature": 1.0
    },
    {
      "all_correct": 0.75,
      "all_wrong": 0.25,
      "completion_length": 402.890625,
      "epoch": 0.01970563191825812,
      "grad_norm": 0.8465399637980721,
      "kl": 0.0281982421875,
      "learning_rate": 9.990421846781098e-07,
      "loss": 0.0011,
      "reward": 1.890625,
      "reward_std": 0.026516513898968697,
      "rewards/accuracy_reward": 0.75,
      "rewards/format_reward": 1.0,
      "step": 648,
      "temperature": 1.0
    },
    {
      "all_correct": 0.625,
      "all_wrong": 0.0,
      "completion_length": 395.78125,
      "epoch": 0.0197360418440579,
      "grad_norm": 0.8197573744592871,
      "kl": 0.03271484375,
      "learning_rate": 9.990392271247927e-07,
      "loss": 0.0013,
      "reward": 1.964296817779541,
      "reward_std": 0.08782364428043365,
      "rewards/accuracy_reward": 0.7799217104911804,
      "rewards/format_reward": 1.0,
      "step": 649,
      "temperature": 1.0
    },
    {
      "all_correct": 0.875,
      "all_wrong": 0.0,
      "completion_length": 389.84375,
      "epoch": 0.019766451769857682,
      "grad_norm": 0.5187919632812292,
      "kl": 0.02978515625,
      "learning_rate": 9.990362650167194e-07,
      "loss": 0.0012,
      "reward": 2.106008291244507,
      "reward_std": 0.006497703958302736,
      "rewards/accuracy_reward": 0.906008243560791,
      "rewards/format_reward": 1.0,
      "step": 650,
      "temperature": 1.0
    },
    {
      "all_correct": 0.625,
      "all_wrong": 0.25,
      "completion_length": 404.734375,
      "epoch": 0.01979686169565746,
      "grad_norm": 0.556164541443606,
      "kl": 0.036376953125,
      "learning_rate": 9.990332983539168e-07,
      "loss": 0.0015,
      "reward": 1.8004518747329712,
      "reward_std": 0.012578457593917847,
      "rewards/accuracy_reward": 0.6660767793655396,
      "rewards/format_reward": 1.0,
      "step": 651,
      "temperature": 1.0
    },
    {
      "all_correct": 0.375,
      "all_wrong": 0.0,
      "completion_length": 451.1875,
      "epoch": 0.019827271621457244,
      "grad_norm": 1.5232993585917596,
      "kl": 0.0174560546875,
      "learning_rate": 9.990303271364116e-07,
      "loss": 0.0007,
      "reward": 1.9128844738006592,
      "reward_std": 0.1640322506427765,
      "rewards/accuracy_reward": 0.7691343426704407,
      "rewards/format_reward": 1.0,
      "step": 652,
      "temperature": 1.0
    },
    {
      "all_correct": 0.75,
      "all_wrong": 0.125,
      "completion_length": 382.109375,
      "epoch": 0.019857681547257023,
      "grad_norm": 1.0257064360469872,
      "kl": 0.0283203125,
      "learning_rate": 9.990273513642315e-07,
      "loss": 0.0011,
      "reward": 1.9710252285003662,
      "reward_std": 0.026936471462249756,
      "rewards/accuracy_reward": 0.7991501688957214,
      "rewards/format_reward": 1.0,
      "step": 653,
      "temperature": 1.0
    },
    {
      "all_correct": 0.375,
      "all_wrong": 0.25,
      "completion_length": 408.796875,
      "epoch": 0.019888091473056806,
      "grad_norm": 1.03674946322046,
      "kl": 0.0269775390625,
      "learning_rate": 9.990243710374036e-07,
      "loss": 0.0011,
      "reward": 1.6634440422058105,
      "reward_std": 0.19483540952205658,
      "rewards/accuracy_reward": 0.5540690422058105,
      "rewards/format_reward": 1.0,
      "step": 654,
      "temperature": 1.0
    },
    {
      "all_correct": 0.375,
      "all_wrong": 0.375,
      "completion_length": 400.4375,
      "epoch": 0.01991850139885659,
      "grad_norm": 0.7579534517188027,
      "kl": 0.034423828125,
      "learning_rate": 9.990213861559548e-07,
      "loss": 0.0014,
      "reward": 1.5534179210662842,
      "reward_std": 0.07709024846553802,
      "rewards/accuracy_reward": 0.44716793298721313,
      "rewards/format_reward": 1.0,
      "step": 655,
      "temperature": 1.0
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.125,
      "completion_length": 391.015625,
      "epoch": 0.019948911324656367,
      "grad_norm": 0.9517862587511295,
      "kl": 0.03515625,
      "learning_rate": 9.990183967199125e-07,
      "loss": 0.0014,
      "reward": 1.9356319904327393,
      "reward_std": 0.1179971694946289,
      "rewards/accuracy_reward": 0.7731318473815918,
      "rewards/format_reward": 1.0,
      "step": 656,
      "temperature": 1.0
    },
    {
      "all_correct": 0.375,
      "all_wrong": 0.0,
      "completion_length": 419.609375,
      "epoch": 0.01997932125045615,
      "grad_norm": 1.0037908166550191,
      "kl": 0.027099609375,
      "learning_rate": 9.99015402729304e-07,
      "loss": 0.0011,
      "reward": 1.7795934677124023,
      "reward_std": 0.28604164719581604,
      "rewards/accuracy_reward": 0.6514685153961182,
      "rewards/format_reward": 1.0,
      "step": 657,
      "temperature": 1.0
    },
    {
      "all_correct": 0.375,
      "all_wrong": 0.125,
      "completion_length": 416.734375,
      "epoch": 0.02000973117625593,
      "grad_norm": 1.1948288809149632,
      "kl": 0.03173828125,
      "learning_rate": 9.990124041841564e-07,
      "loss": 0.0013,
      "reward": 1.727430820465088,
      "reward_std": 0.14140310883522034,
      "rewards/accuracy_reward": 0.5868057608604431,
      "rewards/format_reward": 1.0,
      "step": 658,
      "temperature": 1.0
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.125,
      "completion_length": 409.234375,
      "epoch": 0.020040141102055712,
      "grad_norm": 12.87615769115042,
      "kl": 0.027099609375,
      "learning_rate": 9.990094010844975e-07,
      "loss": 0.0011,
      "reward": 1.7602542638778687,
      "reward_std": 0.083908312022686,
      "rewards/accuracy_reward": 0.610254168510437,
      "rewards/format_reward": 1.0,
      "step": 659,
      "temperature": 1.0
    },
    {
      "all_correct": 0.25,
      "all_wrong": 0.0,
      "completion_length": 416.15625,
      "epoch": 0.02007055102785549,
      "grad_norm": 1.4571503638723753,
      "kl": 0.031005859375,
      "learning_rate": 9.990063934303542e-07,
      "loss": 0.0012,
      "reward": 1.7599095106124878,
      "reward_std": 0.2226928323507309,
      "rewards/accuracy_reward": 0.6067845225334167,
      "rewards/format_reward": 0.984375,
      "step": 660,
      "temperature": 1.0
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.125,
      "completion_length": 426.453125,
      "epoch": 0.020100960953655274,
      "grad_norm": 1.1290797322221129,
      "kl": 0.0262451171875,
      "learning_rate": 9.990033812217543e-07,
      "loss": 0.001,
      "reward": 1.7170798778533936,
      "reward_std": 0.12519504129886627,
      "rewards/accuracy_reward": 0.5920798778533936,
      "rewards/format_reward": 1.0,
      "step": 661,
      "temperature": 1.0
    },
    {
      "all_correct": 0.75,
      "all_wrong": 0.0,
      "completion_length": 393.84375,
      "epoch": 0.020131370879455053,
      "grad_norm": 0.6663544267287709,
      "kl": 0.0235595703125,
      "learning_rate": 9.990003644587252e-07,
      "loss": 0.0009,
      "reward": 2.0290255546569824,
      "reward_std": 0.06814910471439362,
      "rewards/accuracy_reward": 0.8540254235267639,
      "rewards/format_reward": 1.0,
      "step": 662,
      "temperature": 1.0
    },
    {
      "all_correct": 0.625,
      "all_wrong": 0.0,
      "completion_length": 402.265625,
      "epoch": 0.020161780805254836,
      "grad_norm": 1.0553800931832154,
      "kl": 0.0284423828125,
      "learning_rate": 9.989973431412945e-07,
      "loss": 0.0011,
      "reward": 2.031787872314453,
      "reward_std": 0.06939591467380524,
      "rewards/accuracy_reward": 0.8411630392074585,
      "rewards/format_reward": 1.0,
      "step": 663,
      "temperature": 1.0
    },
    {
      "all_correct": 0.375,
      "all_wrong": 0.125,
      "completion_length": 404.59375,
      "epoch": 0.020192190731054615,
      "grad_norm": 0.962805620934257,
      "kl": 0.02490234375,
      "learning_rate": 9.9899431726949e-07,
      "loss": 0.001,
      "reward": 1.6338539123535156,
      "reward_std": 0.1546269953250885,
      "rewards/accuracy_reward": 0.5119788646697998,
      "rewards/format_reward": 1.0,
      "step": 664,
      "temperature": 1.0
    },
    {
      "all_correct": 0.25,
      "all_wrong": 0.375,
      "completion_length": 399.890625,
      "epoch": 0.020222600656854398,
      "grad_norm": 1.3139052096558272,
      "kl": 0.0245361328125,
      "learning_rate": 9.989912868433386e-07,
      "loss": 0.001,
      "reward": 1.5590829849243164,
      "reward_std": 0.10083663463592529,
      "rewards/accuracy_reward": 0.44658297300338745,
      "rewards/format_reward": 1.0,
      "step": 665,
      "temperature": 1.0
    },
    {
      "all_correct": 0.875,
      "all_wrong": 0.0,
      "completion_length": 366.609375,
      "epoch": 0.020253010582654177,
      "grad_norm": 0.5207536826700402,
      "kl": 0.033203125,
      "learning_rate": 9.989882518628686e-07,
      "loss": 0.0013,
      "reward": 2.0875000953674316,
      "reward_std": 0.06943650543689728,
      "rewards/accuracy_reward": 0.90625,
      "rewards/format_reward": 1.0,
      "step": 666,
      "temperature": 1.0
    },
    {
      "all_correct": 0.375,
      "all_wrong": 0.0,
      "completion_length": 402.3125,
      "epoch": 0.02028342050845396,
      "grad_norm": 1.0881756933706128,
      "kl": 0.0225830078125,
      "learning_rate": 9.989852123281073e-07,
      "loss": 0.0009,
      "reward": 1.759714961051941,
      "reward_std": 0.1360561102628708,
      "rewards/accuracy_reward": 0.6034649610519409,
      "rewards/format_reward": 1.0,
      "step": 667,
      "temperature": 1.0
    },
    {
      "all_correct": 0.375,
      "all_wrong": 0.125,
      "completion_length": 389.125,
      "epoch": 0.020313830434253742,
      "grad_norm": 3.0831469477607323,
      "kl": 0.026123046875,
      "learning_rate": 9.989821682390829e-07,
      "loss": 0.001,
      "reward": 1.7557421922683716,
      "reward_std": 0.17218458652496338,
      "rewards/accuracy_reward": 0.6057420969009399,
      "rewards/format_reward": 1.0,
      "step": 668,
      "temperature": 1.0
    },
    {
      "all_correct": 0.875,
      "all_wrong": 0.0,
      "completion_length": 362.265625,
      "epoch": 0.02034424036005352,
      "grad_norm": 1.060380386817024,
      "kl": 0.024658203125,
      "learning_rate": 9.989791195958227e-07,
      "loss": 0.001,
      "reward": 2.1773133277893066,
      "reward_std": 0.02901316061615944,
      "rewards/accuracy_reward": 0.9835633039474487,
      "rewards/format_reward": 1.0,
      "step": 669,
      "temperature": 1.0
    },
    {
      "all_correct": 0.25,
      "all_wrong": 0.25,
      "completion_length": 379.546875,
      "epoch": 0.020374650285853304,
      "grad_norm": 1.0791148780455193,
      "kl": 0.029052734375,
      "learning_rate": 9.98976066398355e-07,
      "loss": 0.0012,
      "reward": 1.5806500911712646,
      "reward_std": 0.19715918600559235,
      "rewards/accuracy_reward": 0.4744000732898712,
      "rewards/format_reward": 1.0,
      "step": 670,
      "temperature": 1.0
    },
    {
      "all_correct": 0.75,
      "all_wrong": 0.0,
      "completion_length": 381.125,
      "epoch": 0.020405060211653083,
      "grad_norm": 1.64637513725008,
      "kl": 0.024169921875,
      "learning_rate": 9.989730086467071e-07,
      "loss": 0.001,
      "reward": 1.9743870496749878,
      "reward_std": 0.04748433828353882,
      "rewards/accuracy_reward": 0.790012001991272,
      "rewards/format_reward": 1.0,
      "step": 671,
      "temperature": 1.0
    },
    {
      "all_correct": 0.75,
      "all_wrong": 0.0,
      "completion_length": 373.71875,
      "epoch": 0.020435470137452866,
      "grad_norm": 2.473573119854195,
      "kl": 0.0245361328125,
      "learning_rate": 9.989699463409074e-07,
      "loss": 0.001,
      "reward": 2.0678670406341553,
      "reward_std": 0.09563078731298447,
      "rewards/accuracy_reward": 0.8897418975830078,
      "rewards/format_reward": 1.0,
      "step": 672,
      "temperature": 1.0
    },
    {
      "all_correct": 0.875,
      "all_wrong": 0.125,
      "completion_length": 356.8125,
      "epoch": 0.020465880063252645,
      "grad_norm": 1.2070813582027315,
      "kl": 0.02490234375,
      "learning_rate": 9.989668794809838e-07,
      "loss": 0.001,
      "reward": 2.0343751907348633,
      "reward_std": 0.03808927163481712,
      "rewards/accuracy_reward": 0.875,
      "rewards/format_reward": 1.0,
      "step": 673,
      "temperature": 1.0
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.0,
      "completion_length": 356.3125,
      "epoch": 0.020496289989052428,
      "grad_norm": 1.2888948442110533,
      "kl": 0.0322265625,
      "learning_rate": 9.98963808066964e-07,
      "loss": 0.0013,
      "reward": 1.9281251430511475,
      "reward_std": 0.33044448494911194,
      "rewards/accuracy_reward": 0.796875,
      "rewards/format_reward": 1.0,
      "step": 674,
      "temperature": 1.0
    },
    {
      "all_correct": 0.375,
      "all_wrong": 0.0,
      "completion_length": 415.765625,
      "epoch": 0.020526699914852207,
      "grad_norm": 1.3479555356873087,
      "kl": 0.0238037109375,
      "learning_rate": 9.989607320988762e-07,
      "loss": 0.001,
      "reward": 1.6207882165908813,
      "reward_std": 0.1512431800365448,
      "rewards/accuracy_reward": 0.5020381808280945,
      "rewards/format_reward": 1.0,
      "step": 675,
      "temperature": 1.0
    },
    {
      "all_correct": 0.625,
      "all_wrong": 0.25,
      "completion_length": 360.890625,
      "epoch": 0.02055710984065199,
      "grad_norm": 0.9397730997851568,
      "kl": 0.0279541015625,
      "learning_rate": 9.989576515767484e-07,
      "loss": 0.0011,
      "reward": 1.7625000476837158,
      "reward_std": 0.0530330091714859,
      "rewards/accuracy_reward": 0.640625,
      "rewards/format_reward": 1.0,
      "step": 676,
      "temperature": 1.0
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.125,
      "completion_length": 389.078125,
      "epoch": 0.02058751976645177,
      "grad_norm": 3.9149500611579713,
      "kl": 0.0272216796875,
      "learning_rate": 9.98954566500609e-07,
      "loss": 0.0011,
      "reward": 1.7727192640304565,
      "reward_std": 0.12443836778402328,
      "rewards/accuracy_reward": 0.6477192044258118,
      "rewards/format_reward": 1.0,
      "step": 677,
      "temperature": 1.0
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.0,
      "completion_length": 367.609375,
      "epoch": 0.02061792969225155,
      "grad_norm": 1.5797261197006918,
      "kl": 0.0267333984375,
      "learning_rate": 9.989514768704858e-07,
      "loss": 0.0011,
      "reward": 1.9609650373458862,
      "reward_std": 0.20830951631069183,
      "rewards/accuracy_reward": 0.7922148704528809,
      "rewards/format_reward": 1.0,
      "step": 678,
      "temperature": 1.0
    },
    {
      "all_correct": 0.625,
      "all_wrong": 0.25,
      "completion_length": 383.640625,
      "epoch": 0.02064833961805133,
      "grad_norm": 1.004336027718628,
      "kl": 0.028564453125,
      "learning_rate": 9.989483826864072e-07,
      "loss": 0.0011,
      "reward": 1.7489676475524902,
      "reward_std": 0.01990433782339096,
      "rewards/accuracy_reward": 0.6270925998687744,
      "rewards/format_reward": 1.0,
      "step": 679,
      "temperature": 1.0
    },
    {
      "all_correct": 0.625,
      "all_wrong": 0.125,
      "completion_length": 381.453125,
      "epoch": 0.020678749543851113,
      "grad_norm": 0.8176627402165275,
      "kl": 0.02490234375,
      "learning_rate": 9.989452839484013e-07,
      "loss": 0.001,
      "reward": 1.8937500715255737,
      "reward_std": 0.12730026245117188,
      "rewards/accuracy_reward": 0.75,
      "rewards/format_reward": 1.0,
      "step": 680,
      "temperature": 1.0
    },
    {
      "all_correct": 0.625,
      "all_wrong": 0.0,
      "completion_length": 368.1875,
      "epoch": 0.020709159469650892,
      "grad_norm": 1.2394771992348648,
      "kl": 0.0286865234375,
      "learning_rate": 9.989421806564965e-07,
      "loss": 0.0012,
      "reward": 1.9444711208343506,
      "reward_std": 0.18188361823558807,
      "rewards/accuracy_reward": 0.7788462042808533,
      "rewards/format_reward": 1.0,
      "step": 681,
      "temperature": 1.0
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.0,
      "completion_length": 408.765625,
      "epoch": 0.020739569395450675,
      "grad_norm": 0.7868972656018047,
      "kl": 0.021484375,
      "learning_rate": 9.98939072810721e-07,
      "loss": 0.0009,
      "reward": 1.8661730289459229,
      "reward_std": 0.14778602123260498,
      "rewards/accuracy_reward": 0.7067980766296387,
      "rewards/format_reward": 1.0,
      "step": 682,
      "temperature": 1.0
    },
    {
      "all_correct": 0.625,
      "all_wrong": 0.125,
      "completion_length": 357.390625,
      "epoch": 0.020769979321250458,
      "grad_norm": 1.0699316632670048,
      "kl": 0.0299072265625,
      "learning_rate": 9.989359604111033e-07,
      "loss": 0.0012,
      "reward": 1.7626953125,
      "reward_std": 0.0924317017197609,
      "rewards/accuracy_reward": 0.6376953125,
      "rewards/format_reward": 1.0,
      "step": 683,
      "temperature": 1.0
    },
    {
      "all_correct": 0.625,
      "all_wrong": 0.0,
      "completion_length": 417.78125,
      "epoch": 0.020800389247050237,
      "grad_norm": 0.7743100420567133,
      "kl": 0.0228271484375,
      "learning_rate": 9.98932843457672e-07,
      "loss": 0.0009,
      "reward": 1.8919696807861328,
      "reward_std": 0.1535273790359497,
      "rewards/accuracy_reward": 0.7482196688652039,
      "rewards/format_reward": 1.0,
      "step": 684,
      "temperature": 1.0
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.125,
      "completion_length": 371.671875,
      "epoch": 0.02083079917285002,
      "grad_norm": 1.348400187622915,
      "kl": 0.0299072265625,
      "learning_rate": 9.98929721950455e-07,
      "loss": 0.0012,
      "reward": 1.7625000476837158,
      "reward_std": 0.1414213478565216,
      "rewards/accuracy_reward": 0.640625,
      "rewards/format_reward": 1.0,
      "step": 685,
      "temperature": 1.0
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.0,
      "completion_length": 374.234375,
      "epoch": 0.0208612090986498,
      "grad_norm": 1.076024899431847,
      "kl": 0.0245361328125,
      "learning_rate": 9.989265958894813e-07,
      "loss": 0.001,
      "reward": 1.8858520984649658,
      "reward_std": 0.1646895855665207,
      "rewards/accuracy_reward": 0.7233520150184631,
      "rewards/format_reward": 1.0,
      "step": 686,
      "temperature": 1.0
    },
    {
      "all_correct": 0.375,
      "all_wrong": 0.0,
      "completion_length": 410.859375,
      "epoch": 0.02089161902444958,
      "grad_norm": 1.8198815639881512,
      "kl": 0.02880859375,
      "learning_rate": 9.989234652747792e-07,
      "loss": 0.0012,
      "reward": 1.7496097087860107,
      "reward_std": 0.1555100828409195,
      "rewards/accuracy_reward": 0.5871097445487976,
      "rewards/format_reward": 1.0,
      "step": 687,
      "temperature": 1.0
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.125,
      "completion_length": 384.375,
      "epoch": 0.02092202895024936,
      "grad_norm": 0.9495578796368424,
      "kl": 0.027587890625,
      "learning_rate": 9.98920330106377e-07,
      "loss": 0.0011,
      "reward": 1.796875,
      "reward_std": 0.19501903653144836,
      "rewards/accuracy_reward": 0.671875,
      "rewards/format_reward": 1.0,
      "step": 688,
      "temperature": 1.0
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.0,
      "completion_length": 410.46875,
      "epoch": 0.020952438876049143,
      "grad_norm": 1.3903452606585855,
      "kl": 0.028076171875,
      "learning_rate": 9.989171903843041e-07,
      "loss": 0.0011,
      "reward": 1.9002516269683838,
      "reward_std": 0.03786957263946533,
      "rewards/accuracy_reward": 0.7033764123916626,
      "rewards/format_reward": 1.0,
      "step": 689,
      "temperature": 1.0
    },
    {
      "all_correct": 0.625,
      "all_wrong": 0.125,
      "completion_length": 385.265625,
      "epoch": 0.020982848801848922,
      "grad_norm": 0.9129695414268254,
      "kl": 0.02978515625,
      "learning_rate": 9.989140461085884e-07,
      "loss": 0.0012,
      "reward": 1.9258019924163818,
      "reward_std": 0.06725609302520752,
      "rewards/accuracy_reward": 0.7601770162582397,
      "rewards/format_reward": 1.0,
      "step": 690,
      "temperature": 1.0
    },
    {
      "all_correct": 0.875,
      "all_wrong": 0.0,
      "completion_length": 370.09375,
      "epoch": 0.021013258727648705,
      "grad_norm": 1.5291332037197616,
      "kl": 0.0302734375,
      "learning_rate": 9.989108972792588e-07,
      "loss": 0.0012,
      "reward": 2.1048214435577393,
      "reward_std": 0.018811214715242386,
      "rewards/accuracy_reward": 0.9110714197158813,
      "rewards/format_reward": 1.0,
      "step": 691,
      "temperature": 1.0
    },
    {
      "all_correct": 0.625,
      "all_wrong": 0.0,
      "completion_length": 385.78125,
      "epoch": 0.021043668653448484,
      "grad_norm": 1.4911174892484735,
      "kl": 0.0250244140625,
      "learning_rate": 9.989077438963446e-07,
      "loss": 0.001,
      "reward": 1.972328543663025,
      "reward_std": 0.1256667971611023,
      "rewards/accuracy_reward": 0.7942036390304565,
      "rewards/format_reward": 1.0,
      "step": 692,
      "temperature": 1.0
    },
    {
      "all_correct": 0.25,
      "all_wrong": 0.125,
      "completion_length": 364.59375,
      "epoch": 0.021074078579248267,
      "grad_norm": 4.0742315991079225,
      "kl": 0.035400390625,
      "learning_rate": 9.989045859598735e-07,
      "loss": 0.0014,
      "reward": 1.6659669876098633,
      "reward_std": 0.2535577714443207,
      "rewards/accuracy_reward": 0.5378419160842896,
      "rewards/format_reward": 1.0,
      "step": 693,
      "temperature": 1.0
    },
    {
      "all_correct": 0.75,
      "all_wrong": 0.0,
      "completion_length": 396.109375,
      "epoch": 0.021104488505048046,
      "grad_norm": 0.6510446015733851,
      "kl": 0.023681640625,
      "learning_rate": 9.98901423469875e-07,
      "loss": 0.0009,
      "reward": 1.9562500715255737,
      "reward_std": 0.13476528227329254,
      "rewards/accuracy_reward": 0.8125,
      "rewards/format_reward": 1.0,
      "step": 694,
      "temperature": 1.0
    },
    {
      "all_correct": 0.75,
      "all_wrong": 0.125,
      "completion_length": 379.6875,
      "epoch": 0.02113489843084783,
      "grad_norm": 1.284707243433621,
      "kl": 0.0341796875,
      "learning_rate": 9.988982564263783e-07,
      "loss": 0.0014,
      "reward": 1.9819912910461426,
      "reward_std": 0.02816206030547619,
      "rewards/accuracy_reward": 0.810116171836853,
      "rewards/format_reward": 1.0,
      "step": 695,
      "temperature": 1.0
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.0,
      "completion_length": 420.765625,
      "epoch": 0.02116530835664761,
      "grad_norm": 1.0228858927903428,
      "kl": 0.025634765625,
      "learning_rate": 9.988950848294115e-07,
      "loss": 0.001,
      "reward": 1.956160068511963,
      "reward_std": 0.1683378666639328,
      "rewards/accuracy_reward": 0.7905351519584656,
      "rewards/format_reward": 1.0,
      "step": 696,
      "temperature": 1.0
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.125,
      "completion_length": 364.140625,
      "epoch": 0.02119571828244739,
      "grad_norm": 6.953942738895297,
      "kl": 0.0306396484375,
      "learning_rate": 9.988919086790042e-07,
      "loss": 0.0012,
      "reward": 1.9083714485168457,
      "reward_std": 0.14154362678527832,
      "rewards/accuracy_reward": 0.7552464008331299,
      "rewards/format_reward": 1.0,
      "step": 697,
      "temperature": 1.0
    },
    {
      "all_correct": 0.25,
      "all_wrong": 0.0,
      "completion_length": 413.65625,
      "epoch": 0.021226128208247173,
      "grad_norm": 2.0502753068091013,
      "kl": 0.02685546875,
      "learning_rate": 9.98888727975185e-07,
      "loss": 0.0011,
      "reward": 1.7411872148513794,
      "reward_std": 0.1346178948879242,
      "rewards/accuracy_reward": 0.5818121433258057,
      "rewards/format_reward": 1.0,
      "step": 698,
      "temperature": 1.0
    },
    {
      "all_correct": 0.375,
      "all_wrong": 0.125,
      "completion_length": 398.671875,
      "epoch": 0.021256538134046953,
      "grad_norm": 1.1108207427788948,
      "kl": 0.0286865234375,
      "learning_rate": 9.98885542717983e-07,
      "loss": 0.0011,
      "reward": 1.6812796592712402,
      "reward_std": 0.19948555529117584,
      "rewards/accuracy_reward": 0.5594046711921692,
      "rewards/format_reward": 1.0,
      "step": 699,
      "temperature": 1.0
    },
    {
      "all_correct": 0.625,
      "all_wrong": 0.0,
      "completion_length": 370.796875,
      "epoch": 0.021286948059846735,
      "grad_norm": 1.1051913229462709,
      "kl": 0.037841796875,
      "learning_rate": 9.988823529074273e-07,
      "loss": 0.0015,
      "reward": 1.8820419311523438,
      "reward_std": 0.028230367228388786,
      "rewards/accuracy_reward": 0.7007919549942017,
      "rewards/format_reward": 1.0,
      "step": 700,
      "temperature": 1.0
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.0,
      "completion_length": 388.8125,
      "epoch": 0.021317357985646514,
      "grad_norm": 1.3189130744438085,
      "kl": 0.0286865234375,
      "learning_rate": 9.988791585435473e-07,
      "loss": 0.0011,
      "reward": 1.8846724033355713,
      "reward_std": 0.15534169971942902,
      "rewards/accuracy_reward": 0.7252973318099976,
      "rewards/format_reward": 1.0,
      "step": 701,
      "temperature": 1.0
    },
    {
      "all_correct": 0.625,
      "all_wrong": 0.0,
      "completion_length": 361.015625,
      "epoch": 0.021347767911446297,
      "grad_norm": 1.2850311736204318,
      "kl": 0.0281982421875,
      "learning_rate": 9.988759596263716e-07,
      "loss": 0.0011,
      "reward": 1.9652068614959717,
      "reward_std": 0.14845925569534302,
      "rewards/accuracy_reward": 0.7995818257331848,
      "rewards/format_reward": 1.0,
      "step": 702,
      "temperature": 1.0
    },
    {
      "all_correct": 0.625,
      "all_wrong": 0.25,
      "completion_length": 366.5,
      "epoch": 0.021378177837246076,
      "grad_norm": 0.7473492927736173,
      "kl": 0.0277099609375,
      "learning_rate": 9.988727561559298e-07,
      "loss": 0.0011,
      "reward": 1.8022041320800781,
      "reward_std": 0.012764747254550457,
      "rewards/accuracy_reward": 0.6522042155265808,
      "rewards/format_reward": 1.0,
      "step": 703,
      "temperature": 1.0
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.0,
      "completion_length": 401.625,
      "epoch": 0.02140858776304586,
      "grad_norm": 3.5135745491854133,
      "kl": 0.0277099609375,
      "learning_rate": 9.98869548132251e-07,
      "loss": 0.0011,
      "reward": 2.0574450492858887,
      "reward_std": 0.18382766842842102,
      "rewards/accuracy_reward": 0.8824450373649597,
      "rewards/format_reward": 1.0,
      "step": 704,
      "temperature": 1.0
    },
    {
      "all_correct": 0.625,
      "all_wrong": 0.0,
      "completion_length": 374.953125,
      "epoch": 0.021438997688845638,
      "grad_norm": 0.8270584942057014,
      "kl": 0.031982421875,
      "learning_rate": 9.988663355553646e-07,
      "loss": 0.0013,
      "reward": 2.015568733215332,
      "reward_std": 0.07329375296831131,
      "rewards/accuracy_reward": 0.8311936259269714,
      "rewards/format_reward": 1.0,
      "step": 705,
      "temperature": 1.0
    },
    {
      "all_correct": 0.375,
      "all_wrong": 0.0,
      "completion_length": 422.6875,
      "epoch": 0.02146940761464542,
      "grad_norm": 1.2004283484774476,
      "kl": 0.0255126953125,
      "learning_rate": 9.988631184252998e-07,
      "loss": 0.001,
      "reward": 1.7782607078552246,
      "reward_std": 0.23250901699066162,
      "rewards/accuracy_reward": 0.6470108032226562,
      "rewards/format_reward": 1.0,
      "step": 706,
      "temperature": 1.0
    },
    {
      "all_correct": 0.625,
      "all_wrong": 0.0,
      "completion_length": 402.140625,
      "epoch": 0.0214998175404452,
      "grad_norm": 0.7550582140447133,
      "kl": 0.0291748046875,
      "learning_rate": 9.988598967420859e-07,
      "loss": 0.0012,
      "reward": 1.8572123050689697,
      "reward_std": 0.09363141655921936,
      "rewards/accuracy_reward": 0.7072123885154724,
      "rewards/format_reward": 1.0,
      "step": 707,
      "temperature": 1.0
    },
    {
      "all_correct": 0.375,
      "all_wrong": 0.25,
      "completion_length": 355.953125,
      "epoch": 0.021530227466244983,
      "grad_norm": 1.354910754421629,
      "kl": 0.029296875,
      "learning_rate": 9.988566705057524e-07,
      "loss": 0.0012,
      "reward": 1.6400147676467896,
      "reward_std": 0.10470054298639297,
      "rewards/accuracy_reward": 0.5243897438049316,
      "rewards/format_reward": 1.0,
      "step": 708,
      "temperature": 1.0
    },
    {
      "all_correct": 0.375,
      "all_wrong": 0.125,
      "completion_length": 403.5625,
      "epoch": 0.021560637392044762,
      "grad_norm": 1.7470952393041894,
      "kl": 0.0247802734375,
      "learning_rate": 9.988534397163288e-07,
      "loss": 0.001,
      "reward": 1.6837437152862549,
      "reward_std": 0.11966129392385483,
      "rewards/accuracy_reward": 0.5649937391281128,
      "rewards/format_reward": 1.0,
      "step": 709,
      "temperature": 1.0
    },
    {
      "all_correct": 0.625,
      "all_wrong": 0.0,
      "completion_length": 368.421875,
      "epoch": 0.021591047317844544,
      "grad_norm": 0.9576535290302793,
      "kl": 0.034912109375,
      "learning_rate": 9.988502043738446e-07,
      "loss": 0.0014,
      "reward": 1.9031682014465332,
      "reward_std": 0.1091449111700058,
      "rewards/accuracy_reward": 0.7312930822372437,
      "rewards/format_reward": 1.0,
      "step": 710,
      "temperature": 1.0
    },
    {
      "all_correct": 0.125,
      "all_wrong": 0.25,
      "completion_length": 360.046875,
      "epoch": 0.021621457243644327,
      "grad_norm": 1.9683335088547544,
      "kl": 0.0284423828125,
      "learning_rate": 9.988469644783292e-07,
      "loss": 0.0011,
      "reward": 1.421875,
      "reward_std": 0.3600984215736389,
      "rewards/accuracy_reward": 0.359375,
      "rewards/format_reward": 1.0,
      "step": 711,
      "temperature": 1.0
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.125,
      "completion_length": 378.453125,
      "epoch": 0.021651867169444106,
      "grad_norm": 1.1191351287384375,
      "kl": 0.03271484375,
      "learning_rate": 9.988437200298122e-07,
      "loss": 0.0013,
      "reward": 1.8150949478149414,
      "reward_std": 0.0747203379869461,
      "rewards/accuracy_reward": 0.6494698524475098,
      "rewards/format_reward": 1.0,
      "step": 712,
      "temperature": 1.0
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.125,
      "completion_length": 396.359375,
      "epoch": 0.02168227709524389,
      "grad_norm": 1.5410124151734454,
      "kl": 0.027587890625,
      "learning_rate": 9.988404710283233e-07,
      "loss": 0.0011,
      "reward": 1.8281421661376953,
      "reward_std": 0.1140567883849144,
      "rewards/accuracy_reward": 0.6875171661376953,
      "rewards/format_reward": 1.0,
      "step": 713,
      "temperature": 1.0
    },
    {
      "all_correct": 0.625,
      "all_wrong": 0.125,
      "completion_length": 376.640625,
      "epoch": 0.021712687021043668,
      "grad_norm": 1.0159516208860988,
      "kl": 0.034423828125,
      "learning_rate": 9.988372174738921e-07,
      "loss": 0.0014,
      "reward": 1.9187500476837158,
      "reward_std": 0.14878928661346436,
      "rewards/accuracy_reward": 0.78125,
      "rewards/format_reward": 1.0,
      "step": 714,
      "temperature": 1.0
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.0,
      "completion_length": 383.875,
      "epoch": 0.02174309694684345,
      "grad_norm": 1.3544330017464423,
      "kl": 0.028564453125,
      "learning_rate": 9.988339593665483e-07,
      "loss": 0.0011,
      "reward": 1.9659550189971924,
      "reward_std": 0.18172678351402283,
      "rewards/accuracy_reward": 0.8034549355506897,
      "rewards/format_reward": 1.0,
      "step": 715,
      "temperature": 1.0
    },
    {
      "all_correct": 0.625,
      "all_wrong": 0.125,
      "completion_length": 391.9375,
      "epoch": 0.02177350687264323,
      "grad_norm": 2.0999879748810115,
      "kl": 0.032958984375,
      "learning_rate": 9.988306967063215e-07,
      "loss": 0.0013,
      "reward": 1.8330107927322388,
      "reward_std": 0.05549243837594986,
      "rewards/accuracy_reward": 0.689260721206665,
      "rewards/format_reward": 1.0,
      "step": 716,
      "temperature": 1.0
    },
    {
      "all_correct": 0.625,
      "all_wrong": 0.0,
      "completion_length": 361.828125,
      "epoch": 0.021803916798443013,
      "grad_norm": 2.892890202982373,
      "kl": 0.03125,
      "learning_rate": 9.988274294932418e-07,
      "loss": 0.0013,
      "reward": 1.875,
      "reward_std": 0.1660207211971283,
      "rewards/accuracy_reward": 0.734375,
      "rewards/format_reward": 1.0,
      "step": 717,
      "temperature": 1.0
    },
    {
      "all_correct": 0.625,
      "all_wrong": 0.0,
      "completion_length": 387.078125,
      "epoch": 0.021834326724242792,
      "grad_norm": 1.2159550958942147,
      "kl": 0.033447265625,
      "learning_rate": 9.988241577273387e-07,
      "loss": 0.0013,
      "reward": 1.9819549322128296,
      "reward_std": 0.11317240446805954,
      "rewards/accuracy_reward": 0.8007049560546875,
      "rewards/format_reward": 1.0,
      "step": 718,
      "temperature": 1.0
    },
    {
      "all_correct": 0.75,
      "all_wrong": 0.125,
      "completion_length": 367.78125,
      "epoch": 0.021864736650042575,
      "grad_norm": 1.6662803638531312,
      "kl": 0.0302734375,
      "learning_rate": 9.988208814086423e-07,
      "loss": 0.0012,
      "reward": 2.0187501907348633,
      "reward_std": 0.07902076840400696,
      "rewards/accuracy_reward": 0.859375,
      "rewards/format_reward": 1.0,
      "step": 719,
      "temperature": 1.0
    },
    {
      "all_correct": 0.375,
      "all_wrong": 0.125,
      "completion_length": 367.5625,
      "epoch": 0.021895146575842354,
      "grad_norm": 1.3977024575206578,
      "kl": 0.03564453125,
      "learning_rate": 9.988176005371823e-07,
      "loss": 0.0014,
      "reward": 1.7965492010116577,
      "reward_std": 0.1774827092885971,
      "rewards/accuracy_reward": 0.6621740460395813,
      "rewards/format_reward": 1.0,
      "step": 720,
      "temperature": 1.0
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.0,
      "completion_length": 393.78125,
      "epoch": 0.021925556501642136,
      "grad_norm": 1.8056817244750996,
      "kl": 0.031494140625,
      "learning_rate": 9.98814315112989e-07,
      "loss": 0.0013,
      "reward": 1.934206485748291,
      "reward_std": 0.09965212643146515,
      "rewards/accuracy_reward": 0.7592064142227173,
      "rewards/format_reward": 1.0,
      "step": 721,
      "temperature": 1.0
    },
    {
      "all_correct": 1.0,
      "all_wrong": 0.0,
      "completion_length": 356.09375,
      "epoch": 0.021955966427441916,
      "grad_norm": 0.9567560347553676,
      "kl": 0.035400390625,
      "learning_rate": 9.988110251360917e-07,
      "loss": 0.0014,
      "reward": 2.190624952316284,
      "reward_std": 0.026516513898968697,
      "rewards/accuracy_reward": 1.0,
      "rewards/format_reward": 1.0,
      "step": 722,
      "temperature": 1.0
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.25,
      "completion_length": 361.21875,
      "epoch": 0.021986376353241698,
      "grad_norm": 0.8158320054946443,
      "kl": 0.035400390625,
      "learning_rate": 9.98807730606521e-07,
      "loss": 0.0014,
      "reward": 1.723860740661621,
      "reward_std": 0.040238410234451294,
      "rewards/accuracy_reward": 0.58636075258255,
      "rewards/format_reward": 1.0,
      "step": 723,
      "temperature": 1.0
    },
    {
      "all_correct": 0.125,
      "all_wrong": 0.375,
      "completion_length": 398.65625,
      "epoch": 0.022016786279041477,
      "grad_norm": 1.1098093094231731,
      "kl": 0.0289306640625,
      "learning_rate": 9.98804431524307e-07,
      "loss": 0.0012,
      "reward": 1.4754552841186523,
      "reward_std": 0.1270744353532791,
      "rewards/accuracy_reward": 0.3785802721977234,
      "rewards/format_reward": 1.0,
      "step": 724,
      "temperature": 1.0
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.25,
      "completion_length": 373.25,
      "epoch": 0.02204719620484126,
      "grad_norm": 1.2183616601207778,
      "kl": 0.0380859375,
      "learning_rate": 9.988011278894795e-07,
      "loss": 0.0015,
      "reward": 1.7102231979370117,
      "reward_std": 0.08546829968690872,
      "rewards/accuracy_reward": 0.5852231383323669,
      "rewards/format_reward": 1.0,
      "step": 725,
      "temperature": 1.0
    },
    {
      "all_correct": 0.25,
      "all_wrong": 0.125,
      "completion_length": 399.03125,
      "epoch": 0.022077606130641043,
      "grad_norm": 1.1681630281894226,
      "kl": 0.0283203125,
      "learning_rate": 9.987978197020687e-07,
      "loss": 0.0011,
      "reward": 1.501389741897583,
      "reward_std": 0.1450280249118805,
      "rewards/accuracy_reward": 0.4013897180557251,
      "rewards/format_reward": 1.0,
      "step": 726,
      "temperature": 1.0
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.0,
      "completion_length": 400.1875,
      "epoch": 0.022108016056440822,
      "grad_norm": 1.1411547253118972,
      "kl": 0.0299072265625,
      "learning_rate": 9.98794506962105e-07,
      "loss": 0.0012,
      "reward": 2.012653350830078,
      "reward_std": 0.1220325455069542,
      "rewards/accuracy_reward": 0.8220282793045044,
      "rewards/format_reward": 1.0,
      "step": 727,
      "temperature": 1.0
    },
    {
      "all_correct": 0.75,
      "all_wrong": 0.125,
      "completion_length": 377.0,
      "epoch": 0.022138425982240605,
      "grad_norm": 1.3514340209932092,
      "kl": 0.034423828125,
      "learning_rate": 9.987911896696185e-07,
      "loss": 0.0014,
      "reward": 2.0093750953674316,
      "reward_std": 0.07827534526586533,
      "rewards/accuracy_reward": 0.84375,
      "rewards/format_reward": 1.0,
      "step": 728,
      "temperature": 1.0
    },
    {
      "all_correct": 0.375,
      "all_wrong": 0.25,
      "completion_length": 412.1875,
      "epoch": 0.022168835908040384,
      "grad_norm": 1.1702099934196326,
      "kl": 0.033203125,
      "learning_rate": 9.987878678246393e-07,
      "loss": 0.0013,
      "reward": 1.6856060028076172,
      "reward_std": 0.15356150269508362,
      "rewards/accuracy_reward": 0.5699810981750488,
      "rewards/format_reward": 1.0,
      "step": 729,
      "temperature": 1.0
    },
    {
      "all_correct": 0.875,
      "all_wrong": 0.0,
      "completion_length": 383.234375,
      "epoch": 0.022199245833840166,
      "grad_norm": 0.7273505110212117,
      "kl": 0.031494140625,
      "learning_rate": 9.987845414271981e-07,
      "loss": 0.0013,
      "reward": 2.106250047683716,
      "reward_std": 0.077632375061512,
      "rewards/accuracy_reward": 0.921875,
      "rewards/format_reward": 1.0,
      "step": 730,
      "temperature": 1.0
    },
    {
      "all_correct": 0.375,
      "all_wrong": 0.125,
      "completion_length": 379.8125,
      "epoch": 0.022229655759639946,
      "grad_norm": 1.4263464375075543,
      "kl": 0.03515625,
      "learning_rate": 9.987812104773252e-07,
      "loss": 0.0014,
      "reward": 1.7749428749084473,
      "reward_std": 0.1686939001083374,
      "rewards/accuracy_reward": 0.6218177080154419,
      "rewards/format_reward": 1.0,
      "step": 731,
      "temperature": 1.0
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.125,
      "completion_length": 402.015625,
      "epoch": 0.02226006568543973,
      "grad_norm": 0.8913883866530306,
      "kl": 0.0380859375,
      "learning_rate": 9.987778749750506e-07,
      "loss": 0.0015,
      "reward": 1.7426148653030396,
      "reward_std": 0.007226511836051941,
      "rewards/accuracy_reward": 0.5957398414611816,
      "rewards/format_reward": 1.0,
      "step": 732,
      "temperature": 1.0
    },
    {
      "all_correct": 0.25,
      "all_wrong": 0.125,
      "completion_length": 394.3125,
      "epoch": 0.022290475611239507,
      "grad_norm": 1.8338488816478984,
      "kl": 0.0361328125,
      "learning_rate": 9.987745349204053e-07,
      "loss": 0.0014,
      "reward": 1.711248517036438,
      "reward_std": 0.1885174810886383,
      "rewards/accuracy_reward": 0.5737485289573669,
      "rewards/format_reward": 1.0,
      "step": 733,
      "temperature": 1.0
    },
    {
      "all_correct": 0.625,
      "all_wrong": 0.125,
      "completion_length": 372.140625,
      "epoch": 0.02232088553703929,
      "grad_norm": 0.9094313823446758,
      "kl": 0.0361328125,
      "learning_rate": 9.987711903134193e-07,
      "loss": 0.0014,
      "reward": 1.84375,
      "reward_std": 0.14706888794898987,
      "rewards/accuracy_reward": 0.703125,
      "rewards/format_reward": 1.0,
      "step": 734,
      "temperature": 1.0
    },
    {
      "all_correct": 0.25,
      "all_wrong": 0.25,
      "completion_length": 381.296875,
      "epoch": 0.02235129546283907,
      "grad_norm": 1.1464659738770122,
      "kl": 0.03515625,
      "learning_rate": 9.987678411541234e-07,
      "loss": 0.0014,
      "reward": 1.6514378786087036,
      "reward_std": 0.18804897367954254,
      "rewards/accuracy_reward": 0.5201878547668457,
      "rewards/format_reward": 1.0,
      "step": 735,
      "temperature": 1.0
    },
    {
      "all_correct": 0.375,
      "all_wrong": 0.125,
      "completion_length": 384.984375,
      "epoch": 0.022381705388638852,
      "grad_norm": 1.291010346276496,
      "kl": 0.0302734375,
      "learning_rate": 9.98764487442548e-07,
      "loss": 0.0012,
      "reward": 1.6768947839736938,
      "reward_std": 0.08444131910800934,
      "rewards/accuracy_reward": 0.555019736289978,
      "rewards/format_reward": 1.0,
      "step": 736,
      "temperature": 1.0
    },
    {
      "all_correct": 0.625,
      "all_wrong": 0.125,
      "completion_length": 391.421875,
      "epoch": 0.02241211531443863,
      "grad_norm": 0.823421836041912,
      "kl": 0.036865234375,
      "learning_rate": 9.98761129178724e-07,
      "loss": 0.0015,
      "reward": 1.7976568937301636,
      "reward_std": 0.06957726180553436,
      "rewards/accuracy_reward": 0.6601568460464478,
      "rewards/format_reward": 1.0,
      "step": 737,
      "temperature": 1.0
    },
    {
      "all_correct": 0.375,
      "all_wrong": 0.125,
      "completion_length": 384.328125,
      "epoch": 0.022442525240238414,
      "grad_norm": 2.2622801393055396,
      "kl": 0.0322265625,
      "learning_rate": 9.987577663626817e-07,
      "loss": 0.0013,
      "reward": 1.716848611831665,
      "reward_std": 0.21006464958190918,
      "rewards/accuracy_reward": 0.6074735522270203,
      "rewards/format_reward": 1.0,
      "step": 738,
      "temperature": 1.0
    },
    {
      "all_correct": 0.625,
      "all_wrong": 0.125,
      "completion_length": 365.921875,
      "epoch": 0.022472935166038197,
      "grad_norm": 3.015272825477005,
      "kl": 0.031494140625,
      "learning_rate": 9.987543989944519e-07,
      "loss": 0.0013,
      "reward": 1.9758110046386719,
      "reward_std": 0.0849425345659256,
      "rewards/accuracy_reward": 0.807060956954956,
      "rewards/format_reward": 1.0,
      "step": 739,
      "temperature": 1.0
    },
    {
      "all_correct": 0.625,
      "all_wrong": 0.125,
      "completion_length": 389.578125,
      "epoch": 0.022503345091837976,
      "grad_norm": 1.0688015856224915,
      "kl": 0.0264892578125,
      "learning_rate": 9.987510270740654e-07,
      "loss": 0.0011,
      "reward": 1.8392271995544434,
      "reward_std": 0.07759998738765717,
      "rewards/accuracy_reward": 0.6861021518707275,
      "rewards/format_reward": 1.0,
      "step": 740,
      "temperature": 1.0
    },
    {
      "all_correct": 0.375,
      "all_wrong": 0.125,
      "completion_length": 372.515625,
      "epoch": 0.02253375501763776,
      "grad_norm": 1.1500346694003214,
      "kl": 0.034912109375,
      "learning_rate": 9.98747650601553e-07,
      "loss": 0.0014,
      "reward": 1.7619264125823975,
      "reward_std": 0.19373206794261932,
      "rewards/accuracy_reward": 0.63067626953125,
      "rewards/format_reward": 1.0,
      "step": 741,
      "temperature": 1.0
    },
    {
      "all_correct": 0.375,
      "all_wrong": 0.125,
      "completion_length": 375.953125,
      "epoch": 0.022564164943437538,
      "grad_norm": 1.1035879546104315,
      "kl": 0.03369140625,
      "learning_rate": 9.987442695769455e-07,
      "loss": 0.0013,
      "reward": 1.7696813344955444,
      "reward_std": 0.19338145852088928,
      "rewards/accuracy_reward": 0.6321812868118286,
      "rewards/format_reward": 1.0,
      "step": 742,
      "temperature": 1.0
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.25,
      "completion_length": 363.71875,
      "epoch": 0.02259457486923732,
      "grad_norm": 1.2437793328857525,
      "kl": 0.030517578125,
      "learning_rate": 9.987408840002737e-07,
      "loss": 0.0012,
      "reward": 1.8453125953674316,
      "reward_std": 0.042508676648139954,
      "rewards/accuracy_reward": 0.7015625834465027,
      "rewards/format_reward": 1.0,
      "step": 743,
      "temperature": 1.0
    },
    {
      "all_correct": 0.375,
      "all_wrong": 0.25,
      "completion_length": 370.59375,
      "epoch": 0.0226249847950371,
      "grad_norm": 1.8445164487446828,
      "kl": 0.02587890625,
      "learning_rate": 9.987374938715685e-07,
      "loss": 0.001,
      "reward": 1.6270833015441895,
      "reward_std": 0.18902161717414856,
      "rewards/accuracy_reward": 0.5208333134651184,
      "rewards/format_reward": 1.0,
      "step": 744,
      "temperature": 1.0
    },
    {
      "all_correct": 0.375,
      "all_wrong": 0.25,
      "completion_length": 393.625,
      "epoch": 0.022655394720836882,
      "grad_norm": 3.890205553589082,
      "kl": 0.025390625,
      "learning_rate": 9.98734099190861e-07,
      "loss": 0.001,
      "reward": 1.6375000476837158,
      "reward_std": 0.19854024052619934,
      "rewards/accuracy_reward": 0.5625,
      "rewards/format_reward": 0.984375,
      "step": 745,
      "temperature": 1.0
    },
    {
      "all_correct": 0.625,
      "all_wrong": 0.125,
      "completion_length": 340.171875,
      "epoch": 0.02268580464663666,
      "grad_norm": 1.8007790811440603,
      "kl": 0.0291748046875,
      "learning_rate": 9.98730699958182e-07,
      "loss": 0.0012,
      "reward": 1.8573578596115112,
      "reward_std": 0.12742909789085388,
      "rewards/accuracy_reward": 0.7167328000068665,
      "rewards/format_reward": 1.0,
      "step": 746,
      "temperature": 1.0
    },
    {
      "all_correct": 0.375,
      "all_wrong": 0.125,
      "completion_length": 402.375,
      "epoch": 0.022716214572436444,
      "grad_norm": 4.872981637051921,
      "kl": 0.0211181640625,
      "learning_rate": 9.987272961735625e-07,
      "loss": 0.0008,
      "reward": 1.6657042503356934,
      "reward_std": 0.2179035246372223,
      "rewards/accuracy_reward": 0.5719541311264038,
      "rewards/format_reward": 1.0,
      "step": 747,
      "temperature": 1.0
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.125,
      "completion_length": 349.0625,
      "epoch": 0.022746624498236223,
      "grad_norm": 1.3989106953302732,
      "kl": 0.027587890625,
      "learning_rate": 9.987238878370337e-07,
      "loss": 0.0011,
      "reward": 1.798216462135315,
      "reward_std": 0.18179690837860107,
      "rewards/accuracy_reward": 0.6794663667678833,
      "rewards/format_reward": 1.0,
      "step": 748,
      "temperature": 1.0
    },
    {
      "all_correct": 0.625,
      "all_wrong": 0.0,
      "completion_length": 357.046875,
      "epoch": 0.022777034424036006,
      "grad_norm": 1.9984254089382694,
      "kl": 0.025146484375,
      "learning_rate": 9.987204749486267e-07,
      "loss": 0.001,
      "reward": 1.9562500715255737,
      "reward_std": 0.22807425260543823,
      "rewards/accuracy_reward": 0.8125,
      "rewards/format_reward": 1.0,
      "step": 749,
      "temperature": 1.0
    },
    {
      "all_correct": 0.125,
      "all_wrong": 0.125,
      "completion_length": 372.6875,
      "epoch": 0.022807444349835785,
      "grad_norm": 1.9903949992535945,
      "kl": 0.0255126953125,
      "learning_rate": 9.987170575083727e-07,
      "loss": 0.001,
      "reward": 1.6590054035186768,
      "reward_std": 0.16362865269184113,
      "rewards/accuracy_reward": 0.5183802843093872,
      "rewards/format_reward": 1.0,
      "step": 750,
      "temperature": 1.0
    },
    {
      "all_correct": 0.375,
      "all_wrong": 0.0,
      "completion_length": 385.125,
      "epoch": 0.022837854275635568,
      "grad_norm": 1.1454249383111754,
      "kl": 0.0252685546875,
      "learning_rate": 9.987136355163027e-07,
      "loss": 0.001,
      "reward": 1.9045586585998535,
      "reward_std": 0.21874359250068665,
      "rewards/accuracy_reward": 0.7358086705207825,
      "rewards/format_reward": 1.0,
      "step": 751,
      "temperature": 1.0
    },
    {
      "all_correct": 1.0,
      "all_wrong": 0.0,
      "completion_length": 361.296875,
      "epoch": 0.022868264201435347,
      "grad_norm": 0.8814794824068796,
      "kl": 0.0274658203125,
      "learning_rate": 9.987102089724479e-07,
      "loss": 0.0011,
      "reward": 2.184375047683716,
      "reward_std": 0.030616413801908493,
      "rewards/accuracy_reward": 1.0,
      "rewards/format_reward": 1.0,
      "step": 752,
      "temperature": 1.0
    },
    {
      "all_correct": 0.375,
      "all_wrong": 0.25,
      "completion_length": 404.015625,
      "epoch": 0.02289867412723513,
      "grad_norm": 0.8128564540040495,
      "kl": 0.022216796875,
      "learning_rate": 9.987067778768398e-07,
      "loss": 0.0009,
      "reward": 1.7192349433898926,
      "reward_std": 0.1248355358839035,
      "rewards/accuracy_reward": 0.6004849076271057,
      "rewards/format_reward": 1.0,
      "step": 753,
      "temperature": 1.0
    },
    {
      "all_correct": 0.625,
      "all_wrong": 0.25,
      "completion_length": 363.25,
      "epoch": 0.022929084053034912,
      "grad_norm": 1.892492029894602,
      "kl": 0.030029296875,
      "learning_rate": 9.987033422295096e-07,
      "loss": 0.0012,
      "reward": 1.783818006515503,
      "reward_std": 0.09978213906288147,
      "rewards/accuracy_reward": 0.6619428396224976,
      "rewards/format_reward": 1.0,
      "step": 754,
      "temperature": 1.0
    },
    {
      "all_correct": 0.625,
      "all_wrong": 0.0,
      "completion_length": 372.921875,
      "epoch": 0.02295949397883469,
      "grad_norm": 1.3484429636558195,
      "kl": 0.026611328125,
      "learning_rate": 9.986999020304889e-07,
      "loss": 0.0011,
      "reward": 1.9940892457962036,
      "reward_std": 0.11476308107376099,
      "rewards/accuracy_reward": 0.8128392100334167,
      "rewards/format_reward": 1.0,
      "step": 755,
      "temperature": 1.0
    },
    {
      "all_correct": 0.25,
      "all_wrong": 0.125,
      "completion_length": 395.40625,
      "epoch": 0.022989903904634474,
      "grad_norm": 1.1782680560420162,
      "kl": 0.0257568359375,
      "learning_rate": 9.986964572798087e-07,
      "loss": 0.001,
      "reward": 1.671875,
      "reward_std": 0.3408779203891754,
      "rewards/accuracy_reward": 0.5625,
      "rewards/format_reward": 1.0,
      "step": 756,
      "temperature": 1.0
    },
    {
      "all_correct": 0.25,
      "all_wrong": 0.0,
      "completion_length": 397.046875,
      "epoch": 0.023020313830434253,
      "grad_norm": 3.9010688571281094,
      "kl": 0.029052734375,
      "learning_rate": 9.986930079775006e-07,
      "loss": 0.0012,
      "reward": 1.7876451015472412,
      "reward_std": 0.3001384735107422,
      "rewards/accuracy_reward": 0.6532700061798096,
      "rewards/format_reward": 1.0,
      "step": 757,
      "temperature": 1.0
    },
    {
      "all_correct": 0.75,
      "all_wrong": 0.0,
      "completion_length": 394.734375,
      "epoch": 0.023050723756234036,
      "grad_norm": 0.8314108017978707,
      "kl": 0.0250244140625,
      "learning_rate": 9.986895541235962e-07,
      "loss": 0.001,
      "reward": 1.9951221942901611,
      "reward_std": 0.0914997085928917,
      "rewards/accuracy_reward": 0.8263722062110901,
      "rewards/format_reward": 1.0,
      "step": 758,
      "temperature": 1.0
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.0,
      "completion_length": 378.125,
      "epoch": 0.023081133682033815,
      "grad_norm": 1.8539042371917176,
      "kl": 0.032470703125,
      "learning_rate": 9.98686095718127e-07,
      "loss": 0.0013,
      "reward": 1.8104023933410645,
      "reward_std": 0.2301657497882843,
      "rewards/accuracy_reward": 0.6791523694992065,
      "rewards/format_reward": 1.0,
      "step": 759,
      "temperature": 1.0
    },
    {
      "all_correct": 0.375,
      "all_wrong": 0.0,
      "completion_length": 399.890625,
      "epoch": 0.023111543607833598,
      "grad_norm": 0.8654292889895803,
      "kl": 0.0224609375,
      "learning_rate": 9.986826327611243e-07,
      "loss": 0.0009,
      "reward": 1.9511767625808716,
      "reward_std": 0.25309449434280396,
      "rewards/accuracy_reward": 0.7886766791343689,
      "rewards/format_reward": 1.0,
      "step": 760,
      "temperature": 1.0
    },
    {
      "all_correct": 0.625,
      "all_wrong": 0.0,
      "completion_length": 395.953125,
      "epoch": 0.023141953533633377,
      "grad_norm": 1.0741326810940508,
      "kl": 0.0264892578125,
      "learning_rate": 9.9867916525262e-07,
      "loss": 0.0011,
      "reward": 1.8732432126998901,
      "reward_std": 0.09512462466955185,
      "rewards/accuracy_reward": 0.710743248462677,
      "rewards/format_reward": 1.0,
      "step": 761,
      "temperature": 1.0
    },
    {
      "all_correct": 0.375,
      "all_wrong": 0.125,
      "completion_length": 378.4375,
      "epoch": 0.02317236345943316,
      "grad_norm": 1.3741871806333228,
      "kl": 0.0279541015625,
      "learning_rate": 9.986756931926455e-07,
      "loss": 0.0011,
      "reward": 1.613971471786499,
      "reward_std": 0.17764733731746674,
      "rewards/accuracy_reward": 0.48897144198417664,
      "rewards/format_reward": 1.0,
      "step": 762,
      "temperature": 1.0
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.25,
      "completion_length": 381.3125,
      "epoch": 0.02320277338523294,
      "grad_norm": 0.7373601609617522,
      "kl": 0.028564453125,
      "learning_rate": 9.986722165812326e-07,
      "loss": 0.0011,
      "reward": 1.734375,
      "reward_std": 0.08797704428434372,
      "rewards/accuracy_reward": 0.609375,
      "rewards/format_reward": 1.0,
      "step": 763,
      "temperature": 1.0
    },
    {
      "all_correct": 0.25,
      "all_wrong": 0.0,
      "completion_length": 393.34375,
      "epoch": 0.02323318331103272,
      "grad_norm": 1.7867541502119688,
      "kl": 0.0260009765625,
      "learning_rate": 9.986687354184132e-07,
      "loss": 0.001,
      "reward": 1.7962843179702759,
      "reward_std": 0.246465265750885,
      "rewards/accuracy_reward": 0.6619092226028442,
      "rewards/format_reward": 1.0,
      "step": 764,
      "temperature": 1.0
    },
    {
      "all_correct": 0.875,
      "all_wrong": 0.0,
      "completion_length": 365.578125,
      "epoch": 0.0232635932368325,
      "grad_norm": 0.5880294556167397,
      "kl": 0.0286865234375,
      "learning_rate": 9.986652497042189e-07,
      "loss": 0.0011,
      "reward": 2.1031250953674316,
      "reward_std": 0.07372426986694336,
      "rewards/accuracy_reward": 0.921875,
      "rewards/format_reward": 1.0,
      "step": 765,
      "temperature": 1.0
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.0,
      "completion_length": 379.609375,
      "epoch": 0.023294003162632283,
      "grad_norm": 1.4468293109569579,
      "kl": 0.0267333984375,
      "learning_rate": 9.986617594386817e-07,
      "loss": 0.0011,
      "reward": 1.8983525037765503,
      "reward_std": 0.18144752085208893,
      "rewards/accuracy_reward": 0.7264774441719055,
      "rewards/format_reward": 1.0,
      "step": 766,
      "temperature": 1.0
    },
    {
      "all_correct": 0.625,
      "all_wrong": 0.25,
      "completion_length": 363.8125,
      "epoch": 0.023324413088432066,
      "grad_norm": 0.4200898096974516,
      "kl": 0.0283203125,
      "learning_rate": 9.98658264621833e-07,
      "loss": 0.0011,
      "reward": 1.8593751192092896,
      "reward_std": 0.06805657595396042,
      "rewards/accuracy_reward": 0.71875,
      "rewards/format_reward": 1.0,
      "step": 767,
      "temperature": 1.0
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.25,
      "completion_length": 378.609375,
      "epoch": 0.023354823014231845,
      "grad_norm": 1.149190483234591,
      "kl": 0.0281982421875,
      "learning_rate": 9.986547652537052e-07,
      "loss": 0.0011,
      "reward": 1.7759602069854736,
      "reward_std": 0.07735943049192429,
      "rewards/accuracy_reward": 0.6478351354598999,
      "rewards/format_reward": 1.0,
      "step": 768,
      "temperature": 1.0
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.0,
      "completion_length": 386.78125,
      "epoch": 0.023385232940031628,
      "grad_norm": 1.9985330531319843,
      "kl": 0.0264892578125,
      "learning_rate": 9.9865126133433e-07,
      "loss": 0.0011,
      "reward": 1.7804362773895264,
      "reward_std": 0.13158154487609863,
      "rewards/accuracy_reward": 0.6398111581802368,
      "rewards/format_reward": 1.0,
      "step": 769,
      "temperature": 1.0
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.0,
      "completion_length": 369.75,
      "epoch": 0.023415642865831407,
      "grad_norm": 1.7796850612062007,
      "kl": 0.0286865234375,
      "learning_rate": 9.986477528637397e-07,
      "loss": 0.0011,
      "reward": 1.851261854171753,
      "reward_std": 0.25341296195983887,
      "rewards/accuracy_reward": 0.7137618064880371,
      "rewards/format_reward": 1.0,
      "step": 770,
      "temperature": 1.0
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.25,
      "completion_length": 389.3125,
      "epoch": 0.02344605279163119,
      "grad_norm": 1.6343019910511987,
      "kl": 0.0272216796875,
      "learning_rate": 9.986442398419657e-07,
      "loss": 0.0011,
      "reward": 1.7222223281860352,
      "reward_std": 0.07617852836847305,
      "rewards/accuracy_reward": 0.6128472089767456,
      "rewards/format_reward": 1.0,
      "step": 771,
      "temperature": 1.0
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.25,
      "completion_length": 416.90625,
      "epoch": 0.02347646271743097,
      "grad_norm": 0.8128435781265602,
      "kl": 0.02099609375,
      "learning_rate": 9.986407222690405e-07,
      "loss": 0.0008,
      "reward": 1.7283798456192017,
      "reward_std": 0.03378346562385559,
      "rewards/accuracy_reward": 0.5877547860145569,
      "rewards/format_reward": 1.0,
      "step": 772,
      "temperature": 1.0
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.0,
      "completion_length": 380.53125,
      "epoch": 0.02350687264323075,
      "grad_norm": 1.5830758083146865,
      "kl": 0.027099609375,
      "learning_rate": 9.98637200144996e-07,
      "loss": 0.0011,
      "reward": 1.847960352897644,
      "reward_std": 0.17717812955379486,
      "rewards/accuracy_reward": 0.6885852813720703,
      "rewards/format_reward": 1.0,
      "step": 773,
      "temperature": 1.0
    },
    {
      "all_correct": 0.625,
      "all_wrong": 0.125,
      "completion_length": 391.578125,
      "epoch": 0.02353728256903053,
      "grad_norm": 0.9616305243958918,
      "kl": 0.023681640625,
      "learning_rate": 9.986336734698648e-07,
      "loss": 0.0009,
      "reward": 1.908273696899414,
      "reward_std": 0.11014175415039062,
      "rewards/accuracy_reward": 0.7551485896110535,
      "rewards/format_reward": 1.0,
      "step": 774,
      "temperature": 1.0
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.0,
      "completion_length": 437.609375,
      "epoch": 0.023567692494830313,
      "grad_norm": 2.3915666241249225,
      "kl": 0.0235595703125,
      "learning_rate": 9.986301422436784e-07,
      "loss": 0.0009,
      "reward": 1.853381633758545,
      "reward_std": 0.11915645748376846,
      "rewards/accuracy_reward": 0.7002565860748291,
      "rewards/format_reward": 1.0,
      "step": 775,
      "temperature": 1.0
    },
    {
      "all_correct": 0.625,
      "all_wrong": 0.0,
      "completion_length": 376.5,
      "epoch": 0.023598102420630093,
      "grad_norm": 1.2744706011582818,
      "kl": 0.0269775390625,
      "learning_rate": 9.986266064664697e-07,
      "loss": 0.0011,
      "reward": 2.0259487628936768,
      "reward_std": 0.08181364834308624,
      "rewards/accuracy_reward": 0.8384487628936768,
      "rewards/format_reward": 1.0,
      "step": 776,
      "temperature": 1.0
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.125,
      "completion_length": 399.578125,
      "epoch": 0.023628512346429875,
      "grad_norm": 0.7514170902259528,
      "kl": 0.023193359375,
      "learning_rate": 9.986230661382704e-07,
      "loss": 0.0009,
      "reward": 1.8625000715255737,
      "reward_std": 0.22470125555992126,
      "rewards/accuracy_reward": 0.71875,
      "rewards/format_reward": 1.0,
      "step": 777,
      "temperature": 1.0
    },
    {
      "all_correct": 0.25,
      "all_wrong": 0.25,
      "completion_length": 397.03125,
      "epoch": 0.023658922272229654,
      "grad_norm": 1.0399599372562451,
      "kl": 0.021240234375,
      "learning_rate": 9.986195212591131e-07,
      "loss": 0.0008,
      "reward": 1.4069530963897705,
      "reward_std": 0.1705554723739624,
      "rewards/accuracy_reward": 0.3444531261920929,
      "rewards/format_reward": 1.0,
      "step": 778,
      "temperature": 1.0
    },
    {
      "all_correct": 0.375,
      "all_wrong": 0.0,
      "completion_length": 387.21875,
      "epoch": 0.023689332198029437,
      "grad_norm": 1.4523965467122186,
      "kl": 0.0306396484375,
      "learning_rate": 9.986159718290302e-07,
      "loss": 0.0012,
      "reward": 1.8218750953674316,
      "reward_std": 0.34781375527381897,
      "rewards/accuracy_reward": 0.6875,
      "rewards/format_reward": 1.0,
      "step": 779,
      "temperature": 1.0
    },
    {
      "all_correct": 0.625,
      "all_wrong": 0.0,
      "completion_length": 374.125,
      "epoch": 0.023719742123829216,
      "grad_norm": 1.1810049410022392,
      "kl": 0.03466796875,
      "learning_rate": 9.98612417848054e-07,
      "loss": 0.0014,
      "reward": 2.0662689208984375,
      "reward_std": 0.10660039633512497,
      "rewards/accuracy_reward": 0.875643789768219,
      "rewards/format_reward": 1.0,
      "step": 780,
      "temperature": 1.0
    },
    {
      "all_correct": 0.75,
      "all_wrong": 0.125,
      "completion_length": 362.90625,
      "epoch": 0.023750152049629,
      "grad_norm": 0.1340575940459647,
      "kl": 0.03271484375,
      "learning_rate": 9.98608859316217e-07,
      "loss": 0.0013,
      "reward": 2.008333206176758,
      "reward_std": 0.0,
      "rewards/accuracy_reward": 0.8333333730697632,
      "rewards/format_reward": 1.0,
      "step": 781,
      "temperature": 1.0
    },
    {
      "all_correct": 0.25,
      "all_wrong": 0.125,
      "completion_length": 404.109375,
      "epoch": 0.02378056197542878,
      "grad_norm": 1.2327608833746468,
      "kl": 0.0284423828125,
      "learning_rate": 9.986052962335516e-07,
      "loss": 0.0011,
      "reward": 1.5544676780700684,
      "reward_std": 0.14577242732048035,
      "rewards/accuracy_reward": 0.42946767807006836,
      "rewards/format_reward": 1.0,
      "step": 782,
      "temperature": 1.0
    },
    {
      "all_correct": 0.375,
      "all_wrong": 0.125,
      "completion_length": 436.4375,
      "epoch": 0.02381097190122856,
      "grad_norm": 1.1078770998810665,
      "kl": 0.026123046875,
      "learning_rate": 9.986017286000902e-07,
      "loss": 0.001,
      "reward": 1.6280699968338013,
      "reward_std": 0.2018967717885971,
      "rewards/accuracy_reward": 0.5530700087547302,
      "rewards/format_reward": 0.96875,
      "step": 783,
      "temperature": 1.0
    },
    {
      "all_correct": 0.75,
      "all_wrong": 0.125,
      "completion_length": 358.9375,
      "epoch": 0.023841381827028343,
      "grad_norm": 0.7931463344084059,
      "kl": 0.03369140625,
      "learning_rate": 9.985981564158656e-07,
      "loss": 0.0014,
      "reward": 1.9065475463867188,
      "reward_std": 0.0530330091714859,
      "rewards/accuracy_reward": 0.7596726417541504,
      "rewards/format_reward": 1.0,
      "step": 784,
      "temperature": 1.0
    },
    {
      "all_correct": 0.75,
      "all_wrong": 0.125,
      "completion_length": 376.359375,
      "epoch": 0.023871791752828123,
      "grad_norm": 0.5884591963971636,
      "kl": 0.0263671875,
      "learning_rate": 9.985945796809103e-07,
      "loss": 0.0011,
      "reward": 1.931249976158142,
      "reward_std": 0.07283870130777359,
      "rewards/accuracy_reward": 0.78125,
      "rewards/format_reward": 1.0,
      "step": 785,
      "temperature": 1.0
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.0,
      "completion_length": 358.28125,
      "epoch": 0.023902201678627905,
      "grad_norm": 1.4184127451505397,
      "kl": 0.0277099609375,
      "learning_rate": 9.98590998395257e-07,
      "loss": 0.0011,
      "reward": 1.9197499752044678,
      "reward_std": 0.17344173789024353,
      "rewards/accuracy_reward": 0.7572498917579651,
      "rewards/format_reward": 1.0,
      "step": 786,
      "temperature": 1.0
    },
    {
      "all_correct": 0.75,
      "all_wrong": 0.0,
      "completion_length": 361.28125,
      "epoch": 0.023932611604427684,
      "grad_norm": 1.011397119800329,
      "kl": 0.0277099609375,
      "learning_rate": 9.985874125589383e-07,
      "loss": 0.0011,
      "reward": 1.9830851554870605,
      "reward_std": 0.08638297021389008,
      "rewards/accuracy_reward": 0.8112100958824158,
      "rewards/format_reward": 1.0,
      "step": 787,
      "temperature": 1.0
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.125,
      "completion_length": 388.375,
      "epoch": 0.023963021530227467,
      "grad_norm": 1.5502893031665737,
      "kl": 0.0244140625,
      "learning_rate": 9.985838221719871e-07,
      "loss": 0.001,
      "reward": 1.7328448295593262,
      "reward_std": 0.19366195797920227,
      "rewards/accuracy_reward": 0.6390948295593262,
      "rewards/format_reward": 0.96875,
      "step": 788,
      "temperature": 1.0
    },
    {
      "all_correct": 0.25,
      "all_wrong": 0.25,
      "completion_length": 406.6875,
      "epoch": 0.023993431456027246,
      "grad_norm": 1.1517971177658946,
      "kl": 0.027099609375,
      "learning_rate": 9.985802272344359e-07,
      "loss": 0.0011,
      "reward": 1.4072890281677246,
      "reward_std": 0.17669269442558289,
      "rewards/accuracy_reward": 0.35728907585144043,
      "rewards/format_reward": 0.984375,
      "step": 789,
      "temperature": 1.0
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.125,
      "completion_length": 363.40625,
      "epoch": 0.02402384138182703,
      "grad_norm": 2.1427116200520406,
      "kl": 0.02685546875,
      "learning_rate": 9.985766277463179e-07,
      "loss": 0.0011,
      "reward": 1.7281250953674316,
      "reward_std": 0.22230380773544312,
      "rewards/accuracy_reward": 0.625,
      "rewards/format_reward": 1.0,
      "step": 790,
      "temperature": 1.0
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.125,
      "completion_length": 378.140625,
      "epoch": 0.024054251307626808,
      "grad_norm": 2.4593138913151082,
      "kl": 0.0279541015625,
      "learning_rate": 9.985730237076655e-07,
      "loss": 0.0011,
      "reward": 1.7292461395263672,
      "reward_std": 0.11161977797746658,
      "rewards/accuracy_reward": 0.6104961037635803,
      "rewards/format_reward": 1.0,
      "step": 791,
      "temperature": 1.0
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.125,
      "completion_length": 363.015625,
      "epoch": 0.02408466123342659,
      "grad_norm": 1.5380651608787437,
      "kl": 0.031005859375,
      "learning_rate": 9.985694151185117e-07,
      "loss": 0.0012,
      "reward": 1.8104652166366577,
      "reward_std": 0.17807050049304962,
      "rewards/accuracy_reward": 0.6635902523994446,
      "rewards/format_reward": 1.0,
      "step": 792,
      "temperature": 1.0
    },
    {
      "all_correct": 0.125,
      "all_wrong": 0.25,
      "completion_length": 355.859375,
      "epoch": 0.02411507115922637,
      "grad_norm": 2.905784489643889,
      "kl": 0.0257568359375,
      "learning_rate": 9.985658019788897e-07,
      "loss": 0.001,
      "reward": 1.4597008228302002,
      "reward_std": 0.27356308698654175,
      "rewards/accuracy_reward": 0.3722008168697357,
      "rewards/format_reward": 1.0,
      "step": 793,
      "temperature": 1.0
    },
    {
      "all_correct": 0.75,
      "all_wrong": 0.125,
      "completion_length": 345.1875,
      "epoch": 0.024145481085026153,
      "grad_norm": 0.8647291599259485,
      "kl": 0.0252685546875,
      "learning_rate": 9.985621842888324e-07,
      "loss": 0.001,
      "reward": 1.9494946002960205,
      "reward_std": 0.03824981302022934,
      "rewards/accuracy_reward": 0.7869945168495178,
      "rewards/format_reward": 1.0,
      "step": 794,
      "temperature": 1.0
    },
    {
      "all_correct": 0.0,
      "all_wrong": 0.0,
      "completion_length": 395.875,
      "epoch": 0.024175891010825932,
      "grad_norm": 1.3702880013868752,
      "kl": 0.027099609375,
      "learning_rate": 9.985585620483725e-07,
      "loss": 0.0011,
      "reward": 1.6429288387298584,
      "reward_std": 0.32906872034072876,
      "rewards/accuracy_reward": 0.5116787552833557,
      "rewards/format_reward": 1.0,
      "step": 795,
      "temperature": 1.0
    },
    {
      "all_correct": 0.625,
      "all_wrong": 0.125,
      "completion_length": 392.03125,
      "epoch": 0.024206300936625715,
      "grad_norm": 1.3157251153830898,
      "kl": 0.023193359375,
      "learning_rate": 9.985549352575435e-07,
      "loss": 0.0009,
      "reward": 1.9093750715255737,
      "reward_std": 0.16394595801830292,
      "rewards/accuracy_reward": 0.796875,
      "rewards/format_reward": 1.0,
      "step": 796,
      "temperature": 1.0
    },
    {
      "all_correct": 0.375,
      "all_wrong": 0.125,
      "completion_length": 377.890625,
      "epoch": 0.024236710862425497,
      "grad_norm": 1.3937358038483803,
      "kl": 0.0262451171875,
      "learning_rate": 9.985513039163782e-07,
      "loss": 0.001,
      "reward": 1.801854133605957,
      "reward_std": 0.15722987055778503,
      "rewards/accuracy_reward": 0.6674790382385254,
      "rewards/format_reward": 1.0,
      "step": 797,
      "temperature": 1.0
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.125,
      "completion_length": 361.40625,
      "epoch": 0.024267120788225276,
      "grad_norm": 1.7339451275938458,
      "kl": 0.02490234375,
      "learning_rate": 9.9854766802491e-07,
      "loss": 0.001,
      "reward": 1.799006700515747,
      "reward_std": 0.1200207993388176,
      "rewards/accuracy_reward": 0.6490066647529602,
      "rewards/format_reward": 1.0,
      "step": 798,
      "temperature": 1.0
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.125,
      "completion_length": 367.296875,
      "epoch": 0.02429753071402506,
      "grad_norm": 1.401229118477146,
      "kl": 0.031494140625,
      "learning_rate": 9.985440275831716e-07,
      "loss": 0.0013,
      "reward": 1.8512508869171143,
      "reward_std": 0.08396824449300766,
      "rewards/accuracy_reward": 0.6825007796287537,
      "rewards/format_reward": 1.0,
      "step": 799,
      "temperature": 1.0
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.0,
      "completion_length": 389.5,
      "epoch": 0.024327940639824838,
      "grad_norm": 1.2778062111740731,
      "kl": 0.0294189453125,
      "learning_rate": 9.985403825911968e-07,
      "loss": 0.0012,
      "reward": 1.7474007606506348,
      "reward_std": 0.13472574949264526,
      "rewards/accuracy_reward": 0.5974007248878479,
      "rewards/format_reward": 1.0,
      "step": 800,
      "temperature": 1.0
    },
    {
      "all_correct": 0.875,
      "all_wrong": 0.0,
      "completion_length": 360.15625,
      "epoch": 0.02435835056562462,
      "grad_norm": 0.8422667755068607,
      "kl": 0.0380859375,
      "learning_rate": 9.985367330490184e-07,
      "loss": 0.0015,
      "reward": 2.1187500953674316,
      "reward_std": 0.09175113588571548,
      "rewards/accuracy_reward": 0.9375,
      "rewards/format_reward": 1.0,
      "step": 801,
      "temperature": 1.0
    },
    {
      "all_correct": 0.125,
      "all_wrong": 0.0,
      "completion_length": 469.96875,
      "epoch": 0.0243887604914244,
      "grad_norm": 2.044532105927981,
      "kl": 0.0194091796875,
      "learning_rate": 9.985330789566701e-07,
      "loss": 0.0008,
      "reward": 1.5624651908874512,
      "reward_std": 0.30480289459228516,
      "rewards/accuracy_reward": 0.4562152624130249,
      "rewards/format_reward": 1.0,
      "step": 802,
      "temperature": 1.0
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.125,
      "completion_length": 437.9375,
      "epoch": 0.024419170417224183,
      "grad_norm": 0.936276620147263,
      "kl": 0.024658203125,
      "learning_rate": 9.985294203141851e-07,
      "loss": 0.001,
      "reward": 1.817041039466858,
      "reward_std": 0.09996174275875092,
      "rewards/accuracy_reward": 0.6670409440994263,
      "rewards/format_reward": 1.0,
      "step": 803,
      "temperature": 1.0
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.125,
      "completion_length": 371.578125,
      "epoch": 0.024449580343023962,
      "grad_norm": 2.7390871030767387,
      "kl": 0.03564453125,
      "learning_rate": 9.985257571215969e-07,
      "loss": 0.0014,
      "reward": 1.8532803058624268,
      "reward_std": 0.16679328680038452,
      "rewards/accuracy_reward": 0.7001551389694214,
      "rewards/format_reward": 1.0,
      "step": 804,
      "temperature": 1.0
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.0,
      "completion_length": 396.421875,
      "epoch": 0.024479990268823745,
      "grad_norm": 1.1350548686394575,
      "kl": 0.0281982421875,
      "learning_rate": 9.985220893789386e-07,
      "loss": 0.0011,
      "reward": 1.8072664737701416,
      "reward_std": 0.08884067088365555,
      "rewards/accuracy_reward": 0.6416415572166443,
      "rewards/format_reward": 1.0,
      "step": 805,
      "temperature": 1.0
    },
    {
      "all_correct": 0.625,
      "all_wrong": 0.0,
      "completion_length": 381.078125,
      "epoch": 0.024510400194623524,
      "grad_norm": 1.1838546809098474,
      "kl": 0.0341796875,
      "learning_rate": 9.985184170862439e-07,
      "loss": 0.0014,
      "reward": 1.8751509189605713,
      "reward_std": 0.12401609122753143,
      "rewards/accuracy_reward": 0.7189009189605713,
      "rewards/format_reward": 1.0,
      "step": 806,
      "temperature": 1.0
    },
    {
      "all_correct": 0.625,
      "all_wrong": 0.125,
      "completion_length": 416.984375,
      "epoch": 0.024540810120423306,
      "grad_norm": 0.7113854330107958,
      "kl": 0.025390625,
      "learning_rate": 9.985147402435465e-07,
      "loss": 0.001,
      "reward": 1.860893964767456,
      "reward_std": 0.10788382589817047,
      "rewards/accuracy_reward": 0.7171440124511719,
      "rewards/format_reward": 1.0,
      "step": 807,
      "temperature": 1.0
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.25,
      "completion_length": 379.625,
      "epoch": 0.024571220046223086,
      "grad_norm": 0.8621736558472874,
      "kl": 0.0291748046875,
      "learning_rate": 9.985110588508795e-07,
      "loss": 0.0012,
      "reward": 1.6844508647918701,
      "reward_std": 0.022079434245824814,
      "rewards/accuracy_reward": 0.5594507455825806,
      "rewards/format_reward": 1.0,
      "step": 808,
      "temperature": 1.0
    },
    {
      "all_correct": 0.625,
      "all_wrong": 0.125,
      "completion_length": 374.359375,
      "epoch": 0.02460162997202287,
      "grad_norm": 0.7071942765346917,
      "kl": 0.0286865234375,
      "learning_rate": 9.98507372908277e-07,
      "loss": 0.0011,
      "reward": 1.803125023841858,
      "reward_std": 0.11363068222999573,
      "rewards/accuracy_reward": 0.671875,
      "rewards/format_reward": 1.0,
      "step": 809,
      "temperature": 1.0
    },
    {
      "all_correct": 0.75,
      "all_wrong": 0.125,
      "completion_length": 378.078125,
      "epoch": 0.02463203989782265,
      "grad_norm": 0.753317685037029,
      "kl": 0.031494140625,
      "learning_rate": 9.985036824157721e-07,
      "loss": 0.0013,
      "reward": 1.9469069242477417,
      "reward_std": 0.0033762247767299414,
      "rewards/accuracy_reward": 0.771906852722168,
      "rewards/format_reward": 1.0,
      "step": 810,
      "temperature": 1.0
    },
    {
      "all_correct": 0.125,
      "all_wrong": 0.375,
      "completion_length": 408.3125,
      "epoch": 0.02466244982362243,
      "grad_norm": 1.3133526037882994,
      "kl": 0.025390625,
      "learning_rate": 9.98499987373399e-07,
      "loss": 0.001,
      "reward": 1.4260823726654053,
      "reward_std": 0.2575654983520508,
      "rewards/accuracy_reward": 0.357332319021225,
      "rewards/format_reward": 1.0,
      "step": 811,
      "temperature": 1.0
    },
    {
      "all_correct": 0.625,
      "all_wrong": 0.125,
      "completion_length": 383.046875,
      "epoch": 0.024692859749422213,
      "grad_norm": 0.9405671198543698,
      "kl": 0.026611328125,
      "learning_rate": 9.984962877811912e-07,
      "loss": 0.0011,
      "reward": 1.973444938659668,
      "reward_std": 0.0744757130742073,
      "rewards/accuracy_reward": 0.8078199028968811,
      "rewards/format_reward": 1.0,
      "step": 812,
      "temperature": 1.0
    },
    {
      "all_correct": 0.375,
      "all_wrong": 0.375,
      "completion_length": 362.8125,
      "epoch": 0.024723269675221992,
      "grad_norm": 1.3366797214305564,
      "kl": 0.034912109375,
      "learning_rate": 9.984925836391824e-07,
      "loss": 0.0014,
      "reward": 1.5078840255737305,
      "reward_std": 0.09823894500732422,
      "rewards/accuracy_reward": 0.42350900173187256,
      "rewards/format_reward": 1.0,
      "step": 813,
      "temperature": 1.0
    },
    {
      "all_correct": 0.375,
      "all_wrong": 0.125,
      "completion_length": 385.515625,
      "epoch": 0.024753679601021775,
      "grad_norm": 11.787372693678307,
      "kl": 0.032470703125,
      "learning_rate": 9.984888749474065e-07,
      "loss": 0.0013,
      "reward": 1.6988606452941895,
      "reward_std": 0.07482944428920746,
      "rewards/accuracy_reward": 0.5332356095314026,
      "rewards/format_reward": 1.0,
      "step": 814,
      "temperature": 1.0
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.125,
      "completion_length": 391.84375,
      "epoch": 0.024784089526821554,
      "grad_norm": 1.6503160923401785,
      "kl": 0.0301513671875,
      "learning_rate": 9.984851617058973e-07,
      "loss": 0.0012,
      "reward": 1.8883610963821411,
      "reward_std": 0.14864513278007507,
      "rewards/accuracy_reward": 0.7321109771728516,
      "rewards/format_reward": 1.0,
      "step": 815,
      "temperature": 1.0
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.125,
      "completion_length": 380.890625,
      "epoch": 0.024814499452621337,
      "grad_norm": 1.6862114208862402,
      "kl": 0.0234375,
      "learning_rate": 9.984814439146888e-07,
      "loss": 0.0009,
      "reward": 1.6855181455612183,
      "reward_std": 0.06899987906217575,
      "rewards/accuracy_reward": 0.5636430978775024,
      "rewards/format_reward": 1.0,
      "step": 816,
      "temperature": 1.0
    },
    {
      "all_correct": 0.625,
      "all_wrong": 0.0,
      "completion_length": 357.9375,
      "epoch": 0.024844909378421116,
      "grad_norm": 1.2532849972569562,
      "kl": 0.027587890625,
      "learning_rate": 9.984777215738149e-07,
      "loss": 0.0011,
      "reward": 1.9966022968292236,
      "reward_std": 0.17398184537887573,
      "rewards/accuracy_reward": 0.8216022253036499,
      "rewards/format_reward": 1.0,
      "step": 817,
      "temperature": 1.0
    },
    {
      "all_correct": 0.375,
      "all_wrong": 0.125,
      "completion_length": 369.25,
      "epoch": 0.0248753193042209,
      "grad_norm": 1.242709080230352,
      "kl": 0.0281982421875,
      "learning_rate": 9.984739946833095e-07,
      "loss": 0.0011,
      "reward": 1.7294418811798096,
      "reward_std": 0.10268831253051758,
      "rewards/accuracy_reward": 0.57319176197052,
      "rewards/format_reward": 1.0,
      "step": 818,
      "temperature": 1.0
    },
    {
      "all_correct": 0.125,
      "all_wrong": 0.25,
      "completion_length": 404.46875,
      "epoch": 0.024905729230020678,
      "grad_norm": 4.666140804016954,
      "kl": 0.0252685546875,
      "learning_rate": 9.984702632432065e-07,
      "loss": 0.001,
      "reward": 1.5115324258804321,
      "reward_std": 0.18961066007614136,
      "rewards/accuracy_reward": 0.42715737223625183,
      "rewards/format_reward": 1.0,
      "step": 819,
      "temperature": 1.0
    },
    {
      "all_correct": 0.375,
      "all_wrong": 0.25,
      "completion_length": 354.65625,
      "epoch": 0.02493613915582046,
      "grad_norm": 1.20173530491368,
      "kl": 0.03369140625,
      "learning_rate": 9.984665272535401e-07,
      "loss": 0.0013,
      "reward": 1.7843750715255737,
      "reward_std": 0.20894074440002441,
      "rewards/accuracy_reward": 0.65625,
      "rewards/format_reward": 1.0,
      "step": 820,
      "temperature": 1.0
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.25,
      "completion_length": 373.640625,
      "epoch": 0.02496654908162024,
      "grad_norm": 2.175721887242528,
      "kl": 0.030517578125,
      "learning_rate": 9.984627867143448e-07,
      "loss": 0.0012,
      "reward": 1.6507654190063477,
      "reward_std": 0.006912535987794399,
      "rewards/accuracy_reward": 0.5257654190063477,
      "rewards/format_reward": 1.0,
      "step": 821,
      "temperature": 1.0
    },
    {
      "all_correct": 0.375,
      "all_wrong": 0.375,
      "completion_length": 378.921875,
      "epoch": 0.024996959007420022,
      "grad_norm": 1.1819830292655331,
      "kl": 0.029052734375,
      "learning_rate": 9.98459041625654e-07,
      "loss": 0.0012,
      "reward": 1.6184587478637695,
      "reward_std": 0.07483232021331787,
      "rewards/accuracy_reward": 0.4997085928916931,
      "rewards/format_reward": 1.0,
      "step": 822,
      "temperature": 1.0
    },
    {
      "all_correct": 0.25,
      "all_wrong": 0.625,
      "completion_length": 385.234375,
      "epoch": 0.0250273689332198,
      "grad_norm": 0.5890580778114546,
      "kl": 0.0257568359375,
      "learning_rate": 9.984552919875023e-07,
      "loss": 0.001,
      "reward": 1.350223183631897,
      "reward_std": 0.0022408082149922848,
      "rewards/accuracy_reward": 0.2752231955528259,
      "rewards/format_reward": 1.0,
      "step": 823,
      "temperature": 1.0
    },
    {
      "all_correct": 0.375,
      "all_wrong": 0.125,
      "completion_length": 384.3125,
      "epoch": 0.025057778859019584,
      "grad_norm": 1.0626272463859665,
      "kl": 0.03173828125,
      "learning_rate": 9.984515377999238e-07,
      "loss": 0.0013,
      "reward": 1.7680878639221191,
      "reward_std": 0.21717840433120728,
      "rewards/accuracy_reward": 0.6399627923965454,
      "rewards/format_reward": 1.0,
      "step": 824,
      "temperature": 1.0
    },
    {
      "all_correct": 0.75,
      "all_wrong": 0.0,
      "completion_length": 372.359375,
      "epoch": 0.025088188784819367,
      "grad_norm": 0.860881227803636,
      "kl": 0.034423828125,
      "learning_rate": 9.984477790629528e-07,
      "loss": 0.0014,
      "reward": 2.045442581176758,
      "reward_std": 0.0174080953001976,
      "rewards/accuracy_reward": 0.848567545413971,
      "rewards/format_reward": 1.0,
      "step": 825,
      "temperature": 1.0
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.0,
      "completion_length": 357.078125,
      "epoch": 0.025118598710619146,
      "grad_norm": 1.027399425939752,
      "kl": 0.0281982421875,
      "learning_rate": 9.984440157766237e-07,
      "loss": 0.0011,
      "reward": 1.892415165901184,
      "reward_std": 0.16436290740966797,
      "rewards/accuracy_reward": 0.742415189743042,
      "rewards/format_reward": 1.0,
      "step": 826,
      "temperature": 1.0
    },
    {
      "all_correct": 0.75,
      "all_wrong": 0.125,
      "completion_length": 371.8125,
      "epoch": 0.02514900863641893,
      "grad_norm": 0.6642525007865296,
      "kl": 0.0284423828125,
      "learning_rate": 9.984402479409706e-07,
      "loss": 0.0011,
      "reward": 1.9496476650238037,
      "reward_std": 0.008385919965803623,
      "rewards/accuracy_reward": 0.7808976173400879,
      "rewards/format_reward": 1.0,
      "step": 827,
      "temperature": 1.0
    },
    {
      "all_correct": 0.375,
      "all_wrong": 0.25,
      "completion_length": 418.21875,
      "epoch": 0.025179418562218708,
      "grad_norm": 0.7685288268290463,
      "kl": 0.021728515625,
      "learning_rate": 9.984364755560283e-07,
      "loss": 0.0009,
      "reward": 1.576933741569519,
      "reward_std": 0.05900060757994652,
      "rewards/accuracy_reward": 0.4644337594509125,
      "rewards/format_reward": 1.0,
      "step": 828,
      "temperature": 1.0
    },
    {
      "all_correct": 0.625,
      "all_wrong": 0.125,
      "completion_length": 376.546875,
      "epoch": 0.02520982848801849,
      "grad_norm": 0.8542773475084886,
      "kl": 0.0291748046875,
      "learning_rate": 9.984326986218307e-07,
      "loss": 0.0012,
      "reward": 1.8766294717788696,
      "reward_std": 0.11274223029613495,
      "rewards/accuracy_reward": 0.7297544479370117,
      "rewards/format_reward": 1.0,
      "step": 829,
      "temperature": 1.0
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.25,
      "completion_length": 382.609375,
      "epoch": 0.02524023841381827,
      "grad_norm": 0.6556835507549637,
      "kl": 0.0284423828125,
      "learning_rate": 9.984289171384128e-07,
      "loss": 0.0011,
      "reward": 1.78634512424469,
      "reward_std": 0.10739859938621521,
      "rewards/accuracy_reward": 0.6582200527191162,
      "rewards/format_reward": 0.984375,
      "step": 830,
      "temperature": 1.0
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.125,
      "completion_length": 376.015625,
      "epoch": 0.025270648339618052,
      "grad_norm": 2.0655646454483185,
      "kl": 0.023681640625,
      "learning_rate": 9.984251311058089e-07,
      "loss": 0.0009,
      "reward": 1.7772659063339233,
      "reward_std": 0.08064363896846771,
      "rewards/accuracy_reward": 0.6335158348083496,
      "rewards/format_reward": 1.0,
      "step": 831,
      "temperature": 1.0
    },
    {
      "all_correct": 0.625,
      "all_wrong": 0.125,
      "completion_length": 365.46875,
      "epoch": 0.02530105826541783,
      "grad_norm": 2.027330325770631,
      "kl": 0.028564453125,
      "learning_rate": 9.984213405240533e-07,
      "loss": 0.0011,
      "reward": 1.849196434020996,
      "reward_std": 0.08454695343971252,
      "rewards/accuracy_reward": 0.699196457862854,
      "rewards/format_reward": 1.0,
      "step": 832,
      "temperature": 1.0
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.0,
      "completion_length": 365.21875,
      "epoch": 0.025331468191217614,
      "grad_norm": 1.4262445633930974,
      "kl": 0.0281982421875,
      "learning_rate": 9.98417545393181e-07,
      "loss": 0.0011,
      "reward": 1.7781119346618652,
      "reward_std": 0.17312592267990112,
      "rewards/accuracy_reward": 0.6374868750572205,
      "rewards/format_reward": 1.0,
      "step": 833,
      "temperature": 1.0
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.0,
      "completion_length": 364.625,
      "epoch": 0.025361878117017393,
      "grad_norm": 3.5321082833203796,
      "kl": 0.0269775390625,
      "learning_rate": 9.984137457132266e-07,
      "loss": 0.0011,
      "reward": 1.9796721935272217,
      "reward_std": 0.27583861351013184,
      "rewards/accuracy_reward": 0.8171721696853638,
      "rewards/format_reward": 1.0,
      "step": 834,
      "temperature": 1.0
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.0,
      "completion_length": 394.375,
      "epoch": 0.025392288042817176,
      "grad_norm": 3.262304699600032,
      "kl": 0.031494140625,
      "learning_rate": 9.984099414842244e-07,
      "loss": 0.0013,
      "reward": 1.8777580261230469,
      "reward_std": 0.0923653244972229,
      "rewards/accuracy_reward": 0.693382978439331,
      "rewards/format_reward": 1.0,
      "step": 835,
      "temperature": 1.0
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.25,
      "completion_length": 371.15625,
      "epoch": 0.025422697968616955,
      "grad_norm": 0.8056051442761981,
      "kl": 0.02587890625,
      "learning_rate": 9.984061327062093e-07,
      "loss": 0.001,
      "reward": 1.77370023727417,
      "reward_std": 0.01660957932472229,
      "rewards/accuracy_reward": 0.6299501657485962,
      "rewards/format_reward": 1.0,
      "step": 836,
      "temperature": 1.0
    },
    {
      "all_correct": 0.625,
      "all_wrong": 0.0,
      "completion_length": 406.03125,
      "epoch": 0.025453107894416738,
      "grad_norm": 1.111456845465687,
      "kl": 0.0250244140625,
      "learning_rate": 9.984023193792163e-07,
      "loss": 0.001,
      "reward": 1.9238277673721313,
      "reward_std": 0.1628345102071762,
      "rewards/accuracy_reward": 0.7613277435302734,
      "rewards/format_reward": 1.0,
      "step": 837,
      "temperature": 1.0
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.125,
      "completion_length": 398.84375,
      "epoch": 0.02548351782021652,
      "grad_norm": 1.367743610546074,
      "kl": 0.023193359375,
      "learning_rate": 9.983985015032799e-07,
      "loss": 0.0009,
      "reward": 1.8928800821304321,
      "reward_std": 0.12182924151420593,
      "rewards/accuracy_reward": 0.7366300821304321,
      "rewards/format_reward": 1.0,
      "step": 838,
      "temperature": 1.0
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.125,
      "completion_length": 361.71875,
      "epoch": 0.0255139277460163,
      "grad_norm": 1.0246144840746412,
      "kl": 0.0322265625,
      "learning_rate": 9.983946790784352e-07,
      "loss": 0.0013,
      "reward": 1.9377695322036743,
      "reward_std": 0.15529388189315796,
      "rewards/accuracy_reward": 0.7721444964408875,
      "rewards/format_reward": 1.0,
      "step": 839,
      "temperature": 1.0
    },
    {
      "all_correct": 0.375,
      "all_wrong": 0.25,
      "completion_length": 394.296875,
      "epoch": 0.025544337671816082,
      "grad_norm": 1.2972349728565007,
      "kl": 0.026123046875,
      "learning_rate": 9.983908521047169e-07,
      "loss": 0.001,
      "reward": 1.5154740810394287,
      "reward_std": 0.1842728555202484,
      "rewards/accuracy_reward": 0.45297402143478394,
      "rewards/format_reward": 0.984375,
      "step": 840,
      "temperature": 1.0
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.125,
      "completion_length": 360.140625,
      "epoch": 0.02557474759761586,
      "grad_norm": 1.4475498402613012,
      "kl": 0.028564453125,
      "learning_rate": 9.9838702058216e-07,
      "loss": 0.0011,
      "reward": 1.7000000476837158,
      "reward_std": 0.21167466044425964,
      "rewards/accuracy_reward": 0.59375,
      "rewards/format_reward": 1.0,
      "step": 841,
      "temperature": 1.0
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.0,
      "completion_length": 391.125,
      "epoch": 0.025605157523415644,
      "grad_norm": 0.8377675227701067,
      "kl": 0.02490234375,
      "learning_rate": 9.983831845107994e-07,
      "loss": 0.001,
      "reward": 1.9406315088272095,
      "reward_std": 0.14284569025039673,
      "rewards/accuracy_reward": 0.7625064849853516,
      "rewards/format_reward": 1.0,
      "step": 842,
      "temperature": 1.0
    },
    {
      "all_correct": 0.25,
      "all_wrong": 0.125,
      "completion_length": 409.328125,
      "epoch": 0.025635567449215423,
      "grad_norm": 1.265027170882157,
      "kl": 0.02587890625,
      "learning_rate": 9.983793438906701e-07,
      "loss": 0.001,
      "reward": 1.6790452003479004,
      "reward_std": 0.12033594399690628,
      "rewards/accuracy_reward": 0.5352951884269714,
      "rewards/format_reward": 1.0,
      "step": 843,
      "temperature": 1.0
    },
    {
      "all_correct": 0.375,
      "all_wrong": 0.125,
      "completion_length": 365.953125,
      "epoch": 0.025665977375015206,
      "grad_norm": 1.3220933558296946,
      "kl": 0.0306396484375,
      "learning_rate": 9.983754987218077e-07,
      "loss": 0.0012,
      "reward": 1.543589472770691,
      "reward_std": 0.13156212866306305,
      "rewards/accuracy_reward": 0.45608940720558167,
      "rewards/format_reward": 1.0,
      "step": 844,
      "temperature": 1.0
    },
    {
      "all_correct": 0.25,
      "all_wrong": 0.0,
      "completion_length": 384.328125,
      "epoch": 0.025696387300814985,
      "grad_norm": 1.298653333589377,
      "kl": 0.027099609375,
      "learning_rate": 9.983716490042464e-07,
      "loss": 0.0011,
      "reward": 1.7942698001861572,
      "reward_std": 0.08681254088878632,
      "rewards/accuracy_reward": 0.6036449074745178,
      "rewards/format_reward": 1.0,
      "step": 845,
      "temperature": 1.0
    },
    {
      "all_correct": 0.75,
      "all_wrong": 0.125,
      "completion_length": 385.90625,
      "epoch": 0.025726797226614768,
      "grad_norm": 0.41777919201746394,
      "kl": 0.0230712890625,
      "learning_rate": 9.983677947380218e-07,
      "loss": 0.0009,
      "reward": 1.9500000476837158,
      "reward_std": 0.08920513093471527,
      "rewards/accuracy_reward": 0.796875,
      "rewards/format_reward": 1.0,
      "step": 846,
      "temperature": 1.0
    },
    {
      "all_correct": 0.125,
      "all_wrong": 0.125,
      "completion_length": 409.40625,
      "epoch": 0.025757207152414547,
      "grad_norm": 1.7224468249949592,
      "kl": 0.024169921875,
      "learning_rate": 9.983639359231691e-07,
      "loss": 0.001,
      "reward": 1.5336899757385254,
      "reward_std": 0.32330387830734253,
      "rewards/accuracy_reward": 0.45243996381759644,
      "rewards/format_reward": 0.984375,
      "step": 847,
      "temperature": 1.0
    },
    {
      "all_correct": 0.375,
      "all_wrong": 0.0,
      "completion_length": 382.78125,
      "epoch": 0.02578761707821433,
      "grad_norm": 2.0676796538377635,
      "kl": 0.0216064453125,
      "learning_rate": 9.983600725597234e-07,
      "loss": 0.0009,
      "reward": 1.8787537813186646,
      "reward_std": 0.216922789812088,
      "rewards/accuracy_reward": 0.7131287455558777,
      "rewards/format_reward": 1.0,
      "step": 848,
      "temperature": 1.0
    },
    {
      "all_correct": 0.75,
      "all_wrong": 0.0,
      "completion_length": 369.625,
      "epoch": 0.02581802700401411,
      "grad_norm": 1.5231400523181586,
      "kl": 0.02734375,
      "learning_rate": 9.983562046477202e-07,
      "loss": 0.0011,
      "reward": 1.9757616519927979,
      "reward_std": 0.02236121892929077,
      "rewards/accuracy_reward": 0.8070114850997925,
      "rewards/format_reward": 1.0,
      "step": 849,
      "temperature": 1.0
    },
    {
      "all_correct": 0.625,
      "all_wrong": 0.125,
      "completion_length": 353.671875,
      "epoch": 0.02584843692981389,
      "grad_norm": 1.1869500179620096,
      "kl": 0.03125,
      "learning_rate": 9.983523321871944e-07,
      "loss": 0.0013,
      "reward": 1.8624999523162842,
      "reward_std": 0.14150117337703705,
      "rewards/accuracy_reward": 0.734375,
      "rewards/format_reward": 1.0,
      "step": 850,
      "temperature": 1.0
    },
    {
      "all_correct": 0.375,
      "all_wrong": 0.0,
      "completion_length": 390.125,
      "epoch": 0.02587884685561367,
      "grad_norm": 1.929123493203054,
      "kl": 0.030029296875,
      "learning_rate": 9.983484551781818e-07,
      "loss": 0.0012,
      "reward": 1.647362470626831,
      "reward_std": 0.17034035921096802,
      "rewards/accuracy_reward": 0.5286123752593994,
      "rewards/format_reward": 1.0,
      "step": 851,
      "temperature": 1.0
    },
    {
      "all_correct": 0.125,
      "all_wrong": 0.375,
      "completion_length": 380.640625,
      "epoch": 0.025909256781413453,
      "grad_norm": 7.419320574363224,
      "kl": 0.02099609375,
      "learning_rate": 9.983445736207172e-07,
      "loss": 0.0008,
      "reward": 1.5718750953674316,
      "reward_std": 0.24147427082061768,
      "rewards/accuracy_reward": 0.484375,
      "rewards/format_reward": 1.0,
      "step": 852,
      "temperature": 1.0
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.125,
      "completion_length": 373.59375,
      "epoch": 0.025939666707213236,
      "grad_norm": 1.1592747817606803,
      "kl": 0.0294189453125,
      "learning_rate": 9.983406875148367e-07,
      "loss": 0.0012,
      "reward": 1.7848021984100342,
      "reward_std": 0.10883790254592896,
      "rewards/accuracy_reward": 0.6348022222518921,
      "rewards/format_reward": 1.0,
      "step": 853,
      "temperature": 1.0
    },
    {
      "all_correct": 0.25,
      "all_wrong": 0.0,
      "completion_length": 406.015625,
      "epoch": 0.025970076633013015,
      "grad_norm": 1.5065848739738974,
      "kl": 0.0279541015625,
      "learning_rate": 9.983367968605754e-07,
      "loss": 0.0011,
      "reward": 1.7275400161743164,
      "reward_std": 0.2939084470272064,
      "rewards/accuracy_reward": 0.6025399565696716,
      "rewards/format_reward": 1.0,
      "step": 854,
      "temperature": 1.0
    },
    {
      "all_correct": 0.625,
      "all_wrong": 0.0,
      "completion_length": 360.625,
      "epoch": 0.026000486558812798,
      "grad_norm": 2.5496701802517463,
      "kl": 0.026611328125,
      "learning_rate": 9.983329016579687e-07,
      "loss": 0.0011,
      "reward": 1.9937500953674316,
      "reward_std": 0.23289713263511658,
      "rewards/accuracy_reward": 0.828125,
      "rewards/format_reward": 1.0,
      "step": 855,
      "temperature": 1.0
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.125,
      "completion_length": 364.359375,
      "epoch": 0.026030896484612577,
      "grad_norm": 2.2007921262656795,
      "kl": 0.0257568359375,
      "learning_rate": 9.983290019070525e-07,
      "loss": 0.001,
      "reward": 1.7394740581512451,
      "reward_std": 0.1827305555343628,
      "rewards/accuracy_reward": 0.6144740581512451,
      "rewards/format_reward": 1.0,
      "step": 856,
      "temperature": 1.0
    },
    {
      "all_correct": 0.75,
      "all_wrong": 0.0,
      "completion_length": 366.59375,
      "epoch": 0.02606130641041236,
      "grad_norm": 1.4893904361420967,
      "kl": 0.0274658203125,
      "learning_rate": 9.98325097607862e-07,
      "loss": 0.0011,
      "reward": 2.02575945854187,
      "reward_std": 0.09400910139083862,
      "rewards/accuracy_reward": 0.8507594466209412,
      "rewards/format_reward": 1.0,
      "step": 857,
      "temperature": 1.0
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.125,
      "completion_length": 361.21875,
      "epoch": 0.02609171633621214,
      "grad_norm": 1.1138096367871577,
      "kl": 0.0281982421875,
      "learning_rate": 9.983211887604332e-07,
      "loss": 0.0011,
      "reward": 1.7625000476837158,
      "reward_std": 0.2082977592945099,
      "rewards/accuracy_reward": 0.640625,
      "rewards/format_reward": 1.0,
      "step": 858,
      "temperature": 1.0
    },
    {
      "all_correct": 0.375,
      "all_wrong": 0.125,
      "completion_length": 368.703125,
      "epoch": 0.02612212626201192,
      "grad_norm": 1.3294540815621967,
      "kl": 0.0294189453125,
      "learning_rate": 9.983172753648018e-07,
      "loss": 0.0012,
      "reward": 1.6704678535461426,
      "reward_std": 0.18212249875068665,
      "rewards/accuracy_reward": 0.5579677820205688,
      "rewards/format_reward": 1.0,
      "step": 859,
      "temperature": 1.0
    },
    {
      "all_correct": 0.25,
      "all_wrong": 0.125,
      "completion_length": 379.03125,
      "epoch": 0.0261525361878117,
      "grad_norm": 1.2317845208704672,
      "kl": 0.029052734375,
      "learning_rate": 9.98313357421003e-07,
      "loss": 0.0012,
      "reward": 1.6934876441955566,
      "reward_std": 0.2625080347061157,
      "rewards/accuracy_reward": 0.5559875965118408,
      "rewards/format_reward": 1.0,
      "step": 860,
      "temperature": 1.0
    },
    {
      "all_correct": 0.75,
      "all_wrong": 0.125,
      "completion_length": 360.75,
      "epoch": 0.026182946113611483,
      "grad_norm": 0.7743985481564009,
      "kl": 0.031982421875,
      "learning_rate": 9.98309434929073e-07,
      "loss": 0.0013,
      "reward": 1.999851107597351,
      "reward_std": 0.017677675932645798,
      "rewards/accuracy_reward": 0.8311011791229248,
      "rewards/format_reward": 1.0,
      "step": 861,
      "temperature": 1.0
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.0,
      "completion_length": 364.125,
      "epoch": 0.026213356039411263,
      "grad_norm": 2.4909999872254844,
      "kl": 0.034423828125,
      "learning_rate": 9.983055078890475e-07,
      "loss": 0.0014,
      "reward": 1.85933518409729,
      "reward_std": 0.12884247303009033,
      "rewards/accuracy_reward": 0.7093351483345032,
      "rewards/format_reward": 1.0,
      "step": 862,
      "temperature": 1.0
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.125,
      "completion_length": 437.5625,
      "epoch": 0.026243765965211045,
      "grad_norm": 0.8997173943274382,
      "kl": 0.0277099609375,
      "learning_rate": 9.983015763009623e-07,
      "loss": 0.0011,
      "reward": 1.7145646810531616,
      "reward_std": 0.20130015909671783,
      "rewards/accuracy_reward": 0.6583147048950195,
      "rewards/format_reward": 0.9375,
      "step": 863,
      "temperature": 1.0
    },
    {
      "all_correct": 0.625,
      "all_wrong": 0.125,
      "completion_length": 365.71875,
      "epoch": 0.026274175891010824,
      "grad_norm": 1.2334851397104887,
      "kl": 0.02978515625,
      "learning_rate": 9.982976401648533e-07,
      "loss": 0.0012,
      "reward": 1.8901915550231934,
      "reward_std": 0.037181075662374496,
      "rewards/accuracy_reward": 0.7276915311813354,
      "rewards/format_reward": 1.0,
      "step": 864,
      "temperature": 1.0
    },
    {
      "all_correct": 0.625,
      "all_wrong": 0.0,
      "completion_length": 342.625,
      "epoch": 0.026304585816810607,
      "grad_norm": 1.9919030755272673,
      "kl": 0.027587890625,
      "learning_rate": 9.982936994807566e-07,
      "loss": 0.0011,
      "reward": 1.853270411491394,
      "reward_std": 0.08195285499095917,
      "rewards/accuracy_reward": 0.6907703876495361,
      "rewards/format_reward": 1.0,
      "step": 865,
      "temperature": 1.0
    },
    {
      "all_correct": 0.625,
      "all_wrong": 0.0,
      "completion_length": 374.171875,
      "epoch": 0.026334995742610386,
      "grad_norm": 1.2138233272698584,
      "kl": 0.02392578125,
      "learning_rate": 9.982897542487079e-07,
      "loss": 0.001,
      "reward": 2.02734375,
      "reward_std": 0.19783607125282288,
      "rewards/accuracy_reward": 0.8648437261581421,
      "rewards/format_reward": 1.0,
      "step": 866,
      "temperature": 1.0
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.0,
      "completion_length": 372.25,
      "epoch": 0.02636540566841017,
      "grad_norm": 1.5505146892100785,
      "kl": 0.0322265625,
      "learning_rate": 9.982858044687432e-07,
      "loss": 0.0013,
      "reward": 2.0061817169189453,
      "reward_std": 0.15434777736663818,
      "rewards/accuracy_reward": 0.821806788444519,
      "rewards/format_reward": 1.0,
      "step": 867,
      "temperature": 1.0
    },
    {
      "all_correct": 0.625,
      "all_wrong": 0.0,
      "completion_length": 372.171875,
      "epoch": 0.02639581559420995,
      "grad_norm": 0.9624729377131497,
      "kl": 0.025390625,
      "learning_rate": 9.982818501408987e-07,
      "loss": 0.001,
      "reward": 2.0065112113952637,
      "reward_std": 0.14402265846729279,
      "rewards/accuracy_reward": 0.8283862471580505,
      "rewards/format_reward": 1.0,
      "step": 868,
      "temperature": 1.0
    },
    {
      "all_correct": 0.625,
      "all_wrong": 0.125,
      "completion_length": 356.4375,
      "epoch": 0.02642622552000973,
      "grad_norm": 1.0769681146869727,
      "kl": 0.03125,
      "learning_rate": 9.982778912652107e-07,
      "loss": 0.0013,
      "reward": 1.9249999523162842,
      "reward_std": 0.09531004726886749,
      "rewards/accuracy_reward": 0.7718750238418579,
      "rewards/format_reward": 1.0,
      "step": 869,
      "temperature": 1.0
    },
    {
      "all_correct": 0.375,
      "all_wrong": 0.0,
      "completion_length": 397.53125,
      "epoch": 0.026456635445809513,
      "grad_norm": 4.884932430551105,
      "kl": 0.0263671875,
      "learning_rate": 9.982739278417146e-07,
      "loss": 0.0011,
      "reward": 1.9031250476837158,
      "reward_std": 0.3369966745376587,
      "rewards/accuracy_reward": 0.765625,
      "rewards/format_reward": 1.0,
      "step": 870,
      "temperature": 1.0
    },
    {
      "all_correct": 0.625,
      "all_wrong": 0.25,
      "completion_length": 362.359375,
      "epoch": 0.026487045371609293,
      "grad_norm": 0.8320703244626642,
      "kl": 0.0263671875,
      "learning_rate": 9.982699598704475e-07,
      "loss": 0.0011,
      "reward": 1.873399019241333,
      "reward_std": 0.00807617325335741,
      "rewards/accuracy_reward": 0.7265239357948303,
      "rewards/format_reward": 1.0,
      "step": 871,
      "temperature": 1.0
    },
    {
      "all_correct": 0.125,
      "all_wrong": 0.375,
      "completion_length": 396.78125,
      "epoch": 0.026517455297409075,
      "grad_norm": 1.085670421688828,
      "kl": 0.02099609375,
      "learning_rate": 9.982659873514452e-07,
      "loss": 0.0008,
      "reward": 1.5830128192901611,
      "reward_std": 0.08244168758392334,
      "rewards/accuracy_reward": 0.48926281929016113,
      "rewards/format_reward": 1.0,
      "step": 872,
      "temperature": 1.0
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.375,
      "completion_length": 382.4375,
      "epoch": 0.026547865223208855,
      "grad_norm": 0.6720713691095094,
      "kl": 0.0272216796875,
      "learning_rate": 9.982620102847438e-07,
      "loss": 0.0011,
      "reward": 1.709375023841858,
      "reward_std": 0.07827534526586533,
      "rewards/accuracy_reward": 0.59375,
      "rewards/format_reward": 1.0,
      "step": 873,
      "temperature": 1.0
    },
    {
      "all_correct": 0.25,
      "all_wrong": 0.125,
      "completion_length": 350.609375,
      "epoch": 0.026578275149008637,
      "grad_norm": 3.2857768722209326,
      "kl": 0.036865234375,
      "learning_rate": 9.982580286703796e-07,
      "loss": 0.0015,
      "reward": 1.75,
      "reward_std": 0.28431224822998047,
      "rewards/accuracy_reward": 0.640625,
      "rewards/format_reward": 1.0,
      "step": 874,
      "temperature": 1.0
    },
    {
      "all_correct": 0.625,
      "all_wrong": 0.125,
      "completion_length": 356.8125,
      "epoch": 0.026608685074808416,
      "grad_norm": 1.2195104293218655,
      "kl": 0.028564453125,
      "learning_rate": 9.982540425083894e-07,
      "loss": 0.0011,
      "reward": 1.9500000476837158,
      "reward_std": 0.1508890688419342,
      "rewards/accuracy_reward": 0.796875,
      "rewards/format_reward": 1.0,
      "step": 875,
      "temperature": 1.0
    },
    {
      "all_correct": 0.25,
      "all_wrong": 0.125,
      "completion_length": 380.5,
      "epoch": 0.0266390950006082,
      "grad_norm": 1.8105289352966827,
      "kl": 0.02587890625,
      "learning_rate": 9.98250051798809e-07,
      "loss": 0.001,
      "reward": 1.6753591299057007,
      "reward_std": 0.257985383272171,
      "rewards/accuracy_reward": 0.5441091060638428,
      "rewards/format_reward": 1.0,
      "step": 876,
      "temperature": 1.0
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.25,
      "completion_length": 360.953125,
      "epoch": 0.026669504926407978,
      "grad_norm": 0.6975135252933212,
      "kl": 0.030029296875,
      "learning_rate": 9.982460565416753e-07,
      "loss": 0.0012,
      "reward": 1.725000023841858,
      "reward_std": 0.11225074529647827,
      "rewards/accuracy_reward": 0.609375,
      "rewards/format_reward": 1.0,
      "step": 877,
      "temperature": 1.0
    },
    {
      "all_correct": 0.625,
      "all_wrong": 0.0,
      "completion_length": 343.71875,
      "epoch": 0.02669991485220776,
      "grad_norm": 1.0205203035006727,
      "kl": 0.02978515625,
      "learning_rate": 9.982420567370245e-07,
      "loss": 0.0012,
      "reward": 2.0251989364624023,
      "reward_std": 0.12982305884361267,
      "rewards/accuracy_reward": 0.8564489483833313,
      "rewards/format_reward": 1.0,
      "step": 878,
      "temperature": 1.0
    },
    {
      "all_correct": 0.375,
      "all_wrong": 0.125,
      "completion_length": 354.265625,
      "epoch": 0.02673032477800754,
      "grad_norm": 1.2860595347360626,
      "kl": 0.02783203125,
      "learning_rate": 9.98238052384893e-07,
      "loss": 0.0011,
      "reward": 1.7984168529510498,
      "reward_std": 0.24946370720863342,
      "rewards/accuracy_reward": 0.6609169244766235,
      "rewards/format_reward": 1.0,
      "step": 879,
      "temperature": 1.0
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.0,
      "completion_length": 379.765625,
      "epoch": 0.026760734703807323,
      "grad_norm": 0.9075033343656573,
      "kl": 0.021728515625,
      "learning_rate": 9.982340434853177e-07,
      "loss": 0.0009,
      "reward": 2.022137403488159,
      "reward_std": 0.1549217402935028,
      "rewards/accuracy_reward": 0.8315123319625854,
      "rewards/format_reward": 1.0,
      "step": 880,
      "temperature": 1.0
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.125,
      "completion_length": 360.59375,
      "epoch": 0.026791144629607105,
      "grad_norm": 3.393599770983227,
      "kl": 0.0264892578125,
      "learning_rate": 9.982300300383347e-07,
      "loss": 0.0011,
      "reward": 1.8451385498046875,
      "reward_std": 0.09243814647197723,
      "rewards/accuracy_reward": 0.688888430595398,
      "rewards/format_reward": 1.0,
      "step": 881,
      "temperature": 1.0
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.125,
      "completion_length": 352.015625,
      "epoch": 0.026821554555406885,
      "grad_norm": 1.2437494482901101,
      "kl": 0.027099609375,
      "learning_rate": 9.98226012043981e-07,
      "loss": 0.0011,
      "reward": 1.821874976158142,
      "reward_std": 0.22308871150016785,
      "rewards/accuracy_reward": 0.703125,
      "rewards/format_reward": 1.0,
      "step": 882,
      "temperature": 1.0
    },
    {
      "all_correct": 0.25,
      "all_wrong": 0.125,
      "completion_length": 354.296875,
      "epoch": 0.026851964481206667,
      "grad_norm": 3.117784740205964,
      "kl": 0.0262451171875,
      "learning_rate": 9.982219895022934e-07,
      "loss": 0.001,
      "reward": 1.6497461795806885,
      "reward_std": 0.2257424294948578,
      "rewards/accuracy_reward": 0.5341210961341858,
      "rewards/format_reward": 1.0,
      "step": 883,
      "temperature": 1.0
    },
    {
      "all_correct": 0.625,
      "all_wrong": 0.125,
      "completion_length": 370.96875,
      "epoch": 0.026882374407006446,
      "grad_norm": 0.9489396380701225,
      "kl": 0.021484375,
      "learning_rate": 9.982179624133084e-07,
      "loss": 0.0009,
      "reward": 1.8611946105957031,
      "reward_std": 0.037532929331064224,
      "rewards/accuracy_reward": 0.6924446821212769,
      "rewards/format_reward": 1.0,
      "step": 884,
      "temperature": 1.0
    },
    {
      "all_correct": 0.375,
      "all_wrong": 0.125,
      "completion_length": 382.046875,
      "epoch": 0.02691278433280623,
      "grad_norm": 1.3298126166294117,
      "kl": 0.030029296875,
      "learning_rate": 9.982139307770627e-07,
      "loss": 0.0012,
      "reward": 1.7973594665527344,
      "reward_std": 0.14469589293003082,
      "rewards/accuracy_reward": 0.6536096334457397,
      "rewards/format_reward": 1.0,
      "step": 885,
      "temperature": 1.0
    },
    {
      "all_correct": 0.375,
      "all_wrong": 0.375,
      "completion_length": 375.515625,
      "epoch": 0.02694319425860601,
      "grad_norm": 0.926950321876323,
      "kl": 0.0277099609375,
      "learning_rate": 9.98209894593593e-07,
      "loss": 0.0011,
      "reward": 1.623437523841858,
      "reward_std": 0.0865686684846878,
      "rewards/accuracy_reward": 0.5359374284744263,
      "rewards/format_reward": 1.0,
      "step": 886,
      "temperature": 1.0
    },
    {
      "all_correct": 0.375,
      "all_wrong": 0.375,
      "completion_length": 373.75,
      "epoch": 0.02697360418440579,
      "grad_norm": 1.4128885644530433,
      "kl": 0.0286865234375,
      "learning_rate": 9.982058538629366e-07,
      "loss": 0.0011,
      "reward": 1.5056250095367432,
      "reward_std": 0.10134813189506531,
      "rewards/accuracy_reward": 0.4274999797344208,
      "rewards/format_reward": 1.0,
      "step": 887,
      "temperature": 1.0
    },
    {
      "all_correct": 0.25,
      "all_wrong": 0.25,
      "completion_length": 363.640625,
      "epoch": 0.02700401411020557,
      "grad_norm": 1.7655377487403774,
      "kl": 0.034423828125,
      "learning_rate": 9.982018085851297e-07,
      "loss": 0.0014,
      "reward": 1.578125,
      "reward_std": 0.2865731120109558,
      "rewards/accuracy_reward": 0.484375,
      "rewards/format_reward": 1.0,
      "step": 888,
      "temperature": 1.0
    },
    {
      "all_correct": 0.875,
      "all_wrong": 0.0,
      "completion_length": 372.578125,
      "epoch": 0.027034424036005353,
      "grad_norm": 2.6417907518264063,
      "kl": 0.027587890625,
      "learning_rate": 9.9819775876021e-07,
      "loss": 0.0011,
      "reward": 2.0992777347564697,
      "reward_std": 0.012263868935406208,
      "rewards/accuracy_reward": 0.9024028182029724,
      "rewards/format_reward": 1.0,
      "step": 889,
      "temperature": 1.0
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.125,
      "completion_length": 389.53125,
      "epoch": 0.027064833961805132,
      "grad_norm": 4.688509124322886,
      "kl": 0.0264892578125,
      "learning_rate": 9.98193704388214e-07,
      "loss": 0.0011,
      "reward": 1.7051362991333008,
      "reward_std": 0.14113397896289825,
      "rewards/accuracy_reward": 0.5863862037658691,
      "rewards/format_reward": 1.0,
      "step": 890,
      "temperature": 1.0
    },
    {
      "all_correct": 0.625,
      "all_wrong": 0.125,
      "completion_length": 375.671875,
      "epoch": 0.027095243887604915,
      "grad_norm": 0.6634671932252996,
      "kl": 0.03076171875,
      "learning_rate": 9.981896454691786e-07,
      "loss": 0.0012,
      "reward": 1.8781250715255737,
      "reward_std": 0.14495554566383362,
      "rewards/accuracy_reward": 0.734375,
      "rewards/format_reward": 1.0,
      "step": 891,
      "temperature": 1.0
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.25,
      "completion_length": 381.1875,
      "epoch": 0.027125653813404694,
      "grad_norm": 0.6385036944999951,
      "kl": 0.03173828125,
      "learning_rate": 9.98185582003141e-07,
      "loss": 0.0013,
      "reward": 1.7580617666244507,
      "reward_std": 0.07697310298681259,
      "rewards/accuracy_reward": 0.623686671257019,
      "rewards/format_reward": 1.0,
      "step": 892,
      "temperature": 1.0
    },
    {
      "all_correct": 0.375,
      "all_wrong": 0.375,
      "completion_length": 390.84375,
      "epoch": 0.027156063739204477,
      "grad_norm": 0.5334310474622267,
      "kl": 0.0302734375,
      "learning_rate": 9.981815139901383e-07,
      "loss": 0.0012,
      "reward": 1.5406250953674316,
      "reward_std": 0.14316077530384064,
      "rewards/accuracy_reward": 0.453125,
      "rewards/format_reward": 1.0,
      "step": 893,
      "temperature": 1.0
    },
    {
      "all_correct": 0.625,
      "all_wrong": 0.25,
      "completion_length": 380.484375,
      "epoch": 0.027186473665004256,
      "grad_norm": 0.8584856914674049,
      "kl": 0.030517578125,
      "learning_rate": 9.981774414302079e-07,
      "loss": 0.0012,
      "reward": 1.8052207231521606,
      "reward_std": 0.0214085653424263,
      "rewards/accuracy_reward": 0.6677207946777344,
      "rewards/format_reward": 1.0,
      "step": 894,
      "temperature": 1.0
    },
    {
      "all_correct": 0.375,
      "all_wrong": 0.125,
      "completion_length": 373.8125,
      "epoch": 0.02721688359080404,
      "grad_norm": 1.2925027242072804,
      "kl": 0.0272216796875,
      "learning_rate": 9.981733643233866e-07,
      "loss": 0.0011,
      "reward": 1.7487808465957642,
      "reward_std": 0.16004620492458344,
      "rewards/accuracy_reward": 0.6081558465957642,
      "rewards/format_reward": 1.0,
      "step": 895,
      "temperature": 1.0
    },
    {
      "all_correct": 0.125,
      "all_wrong": 0.0,
      "completion_length": 398.40625,
      "epoch": 0.02724729351660382,
      "grad_norm": 2.043120244435532,
      "kl": 0.028564453125,
      "learning_rate": 9.981692826697115e-07,
      "loss": 0.0011,
      "reward": 1.5589139461517334,
      "reward_std": 0.3679611384868622,
      "rewards/accuracy_reward": 0.4651640057563782,
      "rewards/format_reward": 0.984375,
      "step": 896,
      "temperature": 1.0
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.0,
      "completion_length": 366.71875,
      "epoch": 0.0272777034424036,
      "grad_norm": 1.1291064780764344,
      "kl": 0.03173828125,
      "learning_rate": 9.981651964692202e-07,
      "loss": 0.0013,
      "reward": 1.9500001668930054,
      "reward_std": 0.24376732110977173,
      "rewards/accuracy_reward": 0.796875,
      "rewards/format_reward": 1.0,
      "step": 897,
      "temperature": 1.0
    },
    {
      "all_correct": 0.625,
      "all_wrong": 0.0,
      "completion_length": 388.765625,
      "epoch": 0.027308113368203383,
      "grad_norm": 1.3750506665939297,
      "kl": 0.0291748046875,
      "learning_rate": 9.9816110572195e-07,
      "loss": 0.0012,
      "reward": 1.89055335521698,
      "reward_std": 0.1391996592283249,
      "rewards/accuracy_reward": 0.7436783909797668,
      "rewards/format_reward": 1.0,
      "step": 898,
      "temperature": 1.0
    },
    {
      "all_correct": 0.375,
      "all_wrong": 0.25,
      "completion_length": 377.65625,
      "epoch": 0.027338523294003162,
      "grad_norm": 1.1864955791058833,
      "kl": 0.031494140625,
      "learning_rate": 9.98157010427938e-07,
      "loss": 0.0013,
      "reward": 1.6825969219207764,
      "reward_std": 0.10635487735271454,
      "rewards/accuracy_reward": 0.5513469576835632,
      "rewards/format_reward": 1.0,
      "step": 899,
      "temperature": 1.0
    },
    {
      "all_correct": 0.375,
      "all_wrong": 0.375,
      "completion_length": 388.859375,
      "epoch": 0.027368933219802945,
      "grad_norm": 0.922919824150924,
      "kl": 0.029052734375,
      "learning_rate": 9.981529105872216e-07,
      "loss": 0.0012,
      "reward": 1.6239583492279053,
      "reward_std": 0.10447327792644501,
      "rewards/accuracy_reward": 0.5177083015441895,
      "rewards/format_reward": 1.0,
      "step": 900,
      "temperature": 1.0
    },
    {
      "all_correct": 0.25,
      "all_wrong": 0.25,
      "completion_length": 358.328125,
      "epoch": 0.027399343145602724,
      "grad_norm": 1.654188308627461,
      "kl": 0.0306396484375,
      "learning_rate": 9.981488061998382e-07,
      "loss": 0.0012,
      "reward": 1.4632987976074219,
      "reward_std": 0.19796308875083923,
      "rewards/accuracy_reward": 0.3914237916469574,
      "rewards/format_reward": 1.0,
      "step": 901,
      "temperature": 1.0
    },
    {
      "all_correct": 0.375,
      "all_wrong": 0.375,
      "completion_length": 376.703125,
      "epoch": 0.027429753071402507,
      "grad_norm": 1.0854570867395315,
      "kl": 0.0311279296875,
      "learning_rate": 9.981446972658257e-07,
      "loss": 0.0012,
      "reward": 1.6490330696105957,
      "reward_std": 0.055693116039037704,
      "rewards/accuracy_reward": 0.5271580219268799,
      "rewards/format_reward": 1.0,
      "step": 902,
      "temperature": 1.0
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.25,
      "completion_length": 370.296875,
      "epoch": 0.027460162997202286,
      "grad_norm": 1.127809195168914,
      "kl": 0.0301513671875,
      "learning_rate": 9.981405837852209e-07,
      "loss": 0.0012,
      "reward": 1.7267836332321167,
      "reward_std": 0.04569198936223984,
      "rewards/accuracy_reward": 0.5924085974693298,
      "rewards/format_reward": 1.0,
      "step": 903,
      "temperature": 1.0
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.25,
      "completion_length": 376.296875,
      "epoch": 0.02749057292300207,
      "grad_norm": 0.9358964274327413,
      "kl": 0.034423828125,
      "learning_rate": 9.98136465758062e-07,
      "loss": 0.0014,
      "reward": 1.7383935451507568,
      "reward_std": 0.06318999826908112,
      "rewards/accuracy_reward": 0.6133936047554016,
      "rewards/format_reward": 1.0,
      "step": 904,
      "temperature": 1.0
    },
    {
      "all_correct": 0.75,
      "all_wrong": 0.125,
      "completion_length": 354.96875,
      "epoch": 0.027520982848801848,
      "grad_norm": 0.8511361597802979,
      "kl": 0.0341796875,
      "learning_rate": 9.98132343184386e-07,
      "loss": 0.0014,
      "reward": 2.0176825523376465,
      "reward_std": 0.02414887025952339,
      "rewards/accuracy_reward": 0.8489325046539307,
      "rewards/format_reward": 1.0,
      "step": 905,
      "temperature": 1.0
    },
    {
      "all_correct": 0.625,
      "all_wrong": 0.125,
      "completion_length": 383.109375,
      "epoch": 0.02755139277460163,
      "grad_norm": 0.9745485135989337,
      "kl": 0.0308837890625,
      "learning_rate": 9.98128216064231e-07,
      "loss": 0.0012,
      "reward": 1.8669123649597168,
      "reward_std": 0.10205531865358353,
      "rewards/accuracy_reward": 0.7106623649597168,
      "rewards/format_reward": 1.0,
      "step": 906,
      "temperature": 1.0
    },
    {
      "all_correct": 0.625,
      "all_wrong": 0.0,
      "completion_length": 370.25,
      "epoch": 0.02758180270040141,
      "grad_norm": 1.895851937140255,
      "kl": 0.030517578125,
      "learning_rate": 9.981240843976345e-07,
      "loss": 0.0012,
      "reward": 1.9984097480773926,
      "reward_std": 0.1495390683412552,
      "rewards/accuracy_reward": 0.8171596527099609,
      "rewards/format_reward": 1.0,
      "step": 907,
      "temperature": 1.0
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.0,
      "completion_length": 358.015625,
      "epoch": 0.027612212626201192,
      "grad_norm": 1.6098516042847661,
      "kl": 0.0267333984375,
      "learning_rate": 9.98119948184634e-07,
      "loss": 0.0011,
      "reward": 1.914100170135498,
      "reward_std": 0.23505143821239471,
      "rewards/accuracy_reward": 0.7641000747680664,
      "rewards/format_reward": 1.0,
      "step": 908,
      "temperature": 1.0
    },
    {
      "all_correct": 0.75,
      "all_wrong": 0.0,
      "completion_length": 375.796875,
      "epoch": 0.027642622552000975,
      "grad_norm": 1.033574192365843,
      "kl": 0.0281982421875,
      "learning_rate": 9.981158074252678e-07,
      "loss": 0.0011,
      "reward": 1.990525245666504,
      "reward_std": 0.06795720010995865,
      "rewards/accuracy_reward": 0.8217751979827881,
      "rewards/format_reward": 1.0,
      "step": 909,
      "temperature": 1.0
    },
    {
      "all_correct": 0.625,
      "all_wrong": 0.0,
      "completion_length": 416.203125,
      "epoch": 0.027673032477800754,
      "grad_norm": 0.9914155496887159,
      "kl": 0.023193359375,
      "learning_rate": 9.98111662119573e-07,
      "loss": 0.0009,
      "reward": 1.9707400798797607,
      "reward_std": 0.09584079682826996,
      "rewards/accuracy_reward": 0.8019900918006897,
      "rewards/format_reward": 1.0,
      "step": 910,
      "temperature": 1.0
    },
    {
      "all_correct": 0.375,
      "all_wrong": 0.125,
      "completion_length": 377.703125,
      "epoch": 0.027703442403600537,
      "grad_norm": 1.5349799012658385,
      "kl": 0.025390625,
      "learning_rate": 9.98107512267588e-07,
      "loss": 0.001,
      "reward": 1.6978265047073364,
      "reward_std": 0.1508125364780426,
      "rewards/accuracy_reward": 0.5665765404701233,
      "rewards/format_reward": 1.0,
      "step": 911,
      "temperature": 1.0
    },
    {
      "all_correct": 0.75,
      "all_wrong": 0.0,
      "completion_length": 365.4375,
      "epoch": 0.027733852329400316,
      "grad_norm": 1.2936510644957224,
      "kl": 0.0308837890625,
      "learning_rate": 9.981033578693504e-07,
      "loss": 0.0012,
      "reward": 2.0045530796051025,
      "reward_std": 0.09096268564462662,
      "rewards/accuracy_reward": 0.8264280557632446,
      "rewards/format_reward": 1.0,
      "step": 912,
      "temperature": 1.0
    },
    {
      "all_correct": 0.375,
      "all_wrong": 0.125,
      "completion_length": 356.234375,
      "epoch": 0.0277642622552001,
      "grad_norm": 1.3718693769008454,
      "kl": 0.03466796875,
      "learning_rate": 9.980991989248982e-07,
      "loss": 0.0014,
      "reward": 1.7949542999267578,
      "reward_std": 0.16163060069084167,
      "rewards/accuracy_reward": 0.6387042999267578,
      "rewards/format_reward": 1.0,
      "step": 913,
      "temperature": 1.0
    },
    {
      "all_correct": 0.625,
      "all_wrong": 0.125,
      "completion_length": 370.359375,
      "epoch": 0.027794672180999878,
      "grad_norm": 3.6198798411398494,
      "kl": 0.02978515625,
      "learning_rate": 9.980950354342693e-07,
      "loss": 0.0012,
      "reward": 1.7999999523162842,
      "reward_std": 0.12246951460838318,
      "rewards/accuracy_reward": 0.671875,
      "rewards/format_reward": 1.0,
      "step": 914,
      "temperature": 1.0
    },
    {
      "all_correct": 0.625,
      "all_wrong": 0.125,
      "completion_length": 367.59375,
      "epoch": 0.02782508210679966,
      "grad_norm": 0.6991926328229966,
      "kl": 0.029541015625,
      "learning_rate": 9.980908673975016e-07,
      "loss": 0.0012,
      "reward": 1.882638931274414,
      "reward_std": 0.08100926131010056,
      "rewards/accuracy_reward": 0.7326388955116272,
      "rewards/format_reward": 1.0,
      "step": 915,
      "temperature": 1.0
    },
    {
      "all_correct": 0.375,
      "all_wrong": 0.375,
      "completion_length": 363.53125,
      "epoch": 0.02785549203259944,
      "grad_norm": 0.8133604325907676,
      "kl": 0.0291748046875,
      "learning_rate": 9.980866948146333e-07,
      "loss": 0.0012,
      "reward": 1.521875023841858,
      "reward_std": 0.12182654440402985,
      "rewards/accuracy_reward": 0.4375,
      "rewards/format_reward": 1.0,
      "step": 916,
      "temperature": 1.0
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.125,
      "completion_length": 371.671875,
      "epoch": 0.027885901958399222,
      "grad_norm": 1.7215792826521052,
      "kl": 0.0277099609375,
      "learning_rate": 9.980825176857026e-07,
      "loss": 0.0011,
      "reward": 1.8953166007995605,
      "reward_std": 0.1273740828037262,
      "rewards/accuracy_reward": 0.7296916842460632,
      "rewards/format_reward": 1.0,
      "step": 917,
      "temperature": 1.0
    },
    {
      "all_correct": 0.375,
      "all_wrong": 0.125,
      "completion_length": 379.578125,
      "epoch": 0.027916311884199,
      "grad_norm": 0.9323764979423356,
      "kl": 0.030517578125,
      "learning_rate": 9.980783360107474e-07,
      "loss": 0.0012,
      "reward": 1.6779088973999023,
      "reward_std": 0.21271350979804993,
      "rewards/accuracy_reward": 0.5685338377952576,
      "rewards/format_reward": 1.0,
      "step": 918,
      "temperature": 1.0
    },
    {
      "all_correct": 0.875,
      "all_wrong": 0.125,
      "completion_length": 363.5,
      "epoch": 0.027946721809998784,
      "grad_norm": 0.5036526044285736,
      "kl": 0.037109375,
      "learning_rate": 9.980741497898059e-07,
      "loss": 0.0015,
      "reward": 2.0406250953674316,
      "reward_std": 0.012938733212649822,
      "rewards/accuracy_reward": 0.875,
      "rewards/format_reward": 1.0,
      "step": 919,
      "temperature": 1.0
    },
    {
      "all_correct": 0.375,
      "all_wrong": 0.0,
      "completion_length": 449.09375,
      "epoch": 0.027977131735798563,
      "grad_norm": 1.1181503590706576,
      "kl": 0.02685546875,
      "learning_rate": 9.980699590229163e-07,
      "loss": 0.0011,
      "reward": 1.7752344608306885,
      "reward_std": 0.30081695318222046,
      "rewards/accuracy_reward": 0.6533594727516174,
      "rewards/format_reward": 1.0,
      "step": 920,
      "temperature": 1.0
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.0,
      "completion_length": 396.703125,
      "epoch": 0.028007541661598346,
      "grad_norm": 2.2400200286490155,
      "kl": 0.0291748046875,
      "learning_rate": 9.98065763710117e-07,
      "loss": 0.0012,
      "reward": 1.8694725036621094,
      "reward_std": 0.10489445924758911,
      "rewards/accuracy_reward": 0.6975974440574646,
      "rewards/format_reward": 1.0,
      "step": 921,
      "temperature": 1.0
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.125,
      "completion_length": 383.90625,
      "epoch": 0.028037951587398125,
      "grad_norm": 1.449539652320286,
      "kl": 0.03173828125,
      "learning_rate": 9.980615638514462e-07,
      "loss": 0.0013,
      "reward": 1.7131584882736206,
      "reward_std": 0.07114633917808533,
      "rewards/accuracy_reward": 0.5694084167480469,
      "rewards/format_reward": 1.0,
      "step": 922,
      "temperature": 1.0
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.25,
      "completion_length": 358.46875,
      "epoch": 0.028068361513197908,
      "grad_norm": 1.0254694345337798,
      "kl": 0.033447265625,
      "learning_rate": 9.98057359446942e-07,
      "loss": 0.0013,
      "reward": 1.725000023841858,
      "reward_std": 0.12246951460838318,
      "rewards/accuracy_reward": 0.609375,
      "rewards/format_reward": 1.0,
      "step": 923,
      "temperature": 1.0
    },
    {
      "all_correct": 0.625,
      "all_wrong": 0.25,
      "completion_length": 375.5,
      "epoch": 0.02809877143899769,
      "grad_norm": 0.9636333571347802,
      "kl": 0.038330078125,
      "learning_rate": 9.980531504966435e-07,
      "loss": 0.0015,
      "reward": 1.806096076965332,
      "reward_std": 0.026446864008903503,
      "rewards/accuracy_reward": 0.6685960292816162,
      "rewards/format_reward": 1.0,
      "step": 924,
      "temperature": 1.0
    },
    {
      "all_correct": 0.375,
      "all_wrong": 0.25,
      "completion_length": 387.703125,
      "epoch": 0.02812918136479747,
      "grad_norm": 1.2327195958197117,
      "kl": 0.02978515625,
      "learning_rate": 9.980489370005882e-07,
      "loss": 0.0012,
      "reward": 1.584425449371338,
      "reward_std": 0.12056782841682434,
      "rewards/accuracy_reward": 0.4906753897666931,
      "rewards/format_reward": 1.0,
      "step": 925,
      "temperature": 1.0
    },
    {
      "all_correct": 0.625,
      "all_wrong": 0.0,
      "completion_length": 420.625,
      "epoch": 0.028159591290597252,
      "grad_norm": 1.7836051233030696,
      "kl": 0.034912109375,
      "learning_rate": 9.98044718958815e-07,
      "loss": 0.0014,
      "reward": 1.9043868780136108,
      "reward_std": 0.09988686442375183,
      "rewards/accuracy_reward": 0.7637618780136108,
      "rewards/format_reward": 1.0,
      "step": 926,
      "temperature": 1.0
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.25,
      "completion_length": 398.046875,
      "epoch": 0.02819000121639703,
      "grad_norm": 2.0495932481021004,
      "kl": 0.031494140625,
      "learning_rate": 9.980404963713625e-07,
      "loss": 0.0013,
      "reward": 1.7250001430511475,
      "reward_std": 0.16474655270576477,
      "rewards/accuracy_reward": 0.609375,
      "rewards/format_reward": 1.0,
      "step": 927,
      "temperature": 1.0
    },
    {
      "all_correct": 0.375,
      "all_wrong": 0.25,
      "completion_length": 416.359375,
      "epoch": 0.028220411142196814,
      "grad_norm": 0.6958913598805665,
      "kl": 0.0277099609375,
      "learning_rate": 9.98036269238269e-07,
      "loss": 0.0011,
      "reward": 1.612518310546875,
      "reward_std": 0.15618416666984558,
      "rewards/accuracy_reward": 0.518768310546875,
      "rewards/format_reward": 0.984375,
      "step": 928,
      "temperature": 1.0
    },
    {
      "all_correct": 0.75,
      "all_wrong": 0.0,
      "completion_length": 393.359375,
      "epoch": 0.028250821067996593,
      "grad_norm": 1.8605528943159149,
      "kl": 0.029541015625,
      "learning_rate": 9.980320375595733e-07,
      "loss": 0.0012,
      "reward": 2.0207390785217285,
      "reward_std": 0.040223851799964905,
      "rewards/accuracy_reward": 0.8394889831542969,
      "rewards/format_reward": 1.0,
      "step": 929,
      "temperature": 1.0
    },
    {
      "all_correct": 0.625,
      "all_wrong": 0.0,
      "completion_length": 411.875,
      "epoch": 0.028281230993796376,
      "grad_norm": 1.4510236521538862,
      "kl": 0.0308837890625,
      "learning_rate": 9.980278013353138e-07,
      "loss": 0.0012,
      "reward": 1.917789101600647,
      "reward_std": 0.14712709188461304,
      "rewards/accuracy_reward": 0.7896640300750732,
      "rewards/format_reward": 1.0,
      "step": 930,
      "temperature": 1.0
    },
    {
      "all_correct": 0.75,
      "all_wrong": 0.0,
      "completion_length": 364.546875,
      "epoch": 0.028311640919596155,
      "grad_norm": 0.9839097008232094,
      "kl": 0.0380859375,
      "learning_rate": 9.980235605655293e-07,
      "loss": 0.0015,
      "reward": 2.121875047683716,
      "reward_std": 0.13950422406196594,
      "rewards/accuracy_reward": 0.9375,
      "rewards/format_reward": 1.0,
      "step": 931,
      "temperature": 1.0
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.25,
      "completion_length": 398.515625,
      "epoch": 0.028342050845395938,
      "grad_norm": 0.6689879422126677,
      "kl": 0.029052734375,
      "learning_rate": 9.980193152502587e-07,
      "loss": 0.0012,
      "reward": 1.7489992380142212,
      "reward_std": 0.055807724595069885,
      "rewards/accuracy_reward": 0.6271241903305054,
      "rewards/format_reward": 1.0,
      "step": 932,
      "temperature": 1.0
    },
    {
      "all_correct": 0.75,
      "all_wrong": 0.0,
      "completion_length": 370.703125,
      "epoch": 0.028372460771195717,
      "grad_norm": 0.8188485686718167,
      "kl": 0.0299072265625,
      "learning_rate": 9.980150653895402e-07,
      "loss": 0.0012,
      "reward": 2.054932117462158,
      "reward_std": 0.08002617210149765,
      "rewards/accuracy_reward": 0.8705570697784424,
      "rewards/format_reward": 1.0,
      "step": 933,
      "temperature": 1.0
    },
    {
      "all_correct": 0.75,
      "all_wrong": 0.0,
      "completion_length": 371.21875,
      "epoch": 0.0284028706969955,
      "grad_norm": 1.2216375959528853,
      "kl": 0.0419921875,
      "learning_rate": 9.980108109834131e-07,
      "loss": 0.0017,
      "reward": 2.077817440032959,
      "reward_std": 0.10074599087238312,
      "rewards/accuracy_reward": 0.8934422731399536,
      "rewards/format_reward": 1.0,
      "step": 934,
      "temperature": 1.0
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.25,
      "completion_length": 392.28125,
      "epoch": 0.02843328062279528,
      "grad_norm": 0.7211319772695124,
      "kl": 0.0311279296875,
      "learning_rate": 9.98006552031916e-07,
      "loss": 0.0012,
      "reward": 1.7468750476837158,
      "reward_std": 0.147711843252182,
      "rewards/accuracy_reward": 0.625,
      "rewards/format_reward": 1.0,
      "step": 935,
      "temperature": 1.0
    },
    {
      "all_correct": 0.375,
      "all_wrong": 0.125,
      "completion_length": 399.125,
      "epoch": 0.02846369054859506,
      "grad_norm": 1.3210966850576604,
      "kl": 0.03369140625,
      "learning_rate": 9.98002288535088e-07,
      "loss": 0.0013,
      "reward": 1.5802547931671143,
      "reward_std": 0.1403290033340454,
      "rewards/accuracy_reward": 0.46462976932525635,
      "rewards/format_reward": 1.0,
      "step": 936,
      "temperature": 1.0
    },
    {
      "all_correct": 0.125,
      "all_wrong": 0.25,
      "completion_length": 401.671875,
      "epoch": 0.02849410047439484,
      "grad_norm": 1.01077858694633,
      "kl": 0.0255126953125,
      "learning_rate": 9.979980204929675e-07,
      "loss": 0.001,
      "reward": 1.5889317989349365,
      "reward_std": 0.22281545400619507,
      "rewards/accuracy_reward": 0.4608067274093628,
      "rewards/format_reward": 1.0,
      "step": 937,
      "temperature": 1.0
    },
    {
      "all_correct": 0.625,
      "all_wrong": 0.125,
      "completion_length": 378.515625,
      "epoch": 0.028524510400194623,
      "grad_norm": 0.8103053302764397,
      "kl": 0.0322265625,
      "learning_rate": 9.97993747905594e-07,
      "loss": 0.0013,
      "reward": 1.9020813703536987,
      "reward_std": 0.011060738936066628,
      "rewards/accuracy_reward": 0.7270812392234802,
      "rewards/format_reward": 1.0,
      "step": 938,
      "temperature": 1.0
    },
    {
      "all_correct": 0.75,
      "all_wrong": 0.0,
      "completion_length": 394.21875,
      "epoch": 0.028554920325994406,
      "grad_norm": 0.6608990672443955,
      "kl": 0.03125,
      "learning_rate": 9.979894707730062e-07,
      "loss": 0.0012,
      "reward": 2.038043737411499,
      "reward_std": 0.0746963694691658,
      "rewards/accuracy_reward": 0.8599188327789307,
      "rewards/format_reward": 1.0,
      "step": 939,
      "temperature": 1.0
    },
    {
      "all_correct": 0.25,
      "all_wrong": 0.25,
      "completion_length": 390.734375,
      "epoch": 0.028585330251794185,
      "grad_norm": 1.912762350397319,
      "kl": 0.0279541015625,
      "learning_rate": 9.979851890952433e-07,
      "loss": 0.0011,
      "reward": 1.6827574968338013,
      "reward_std": 0.199858158826828,
      "rewards/accuracy_reward": 0.5546325445175171,
      "rewards/format_reward": 1.0,
      "step": 940,
      "temperature": 1.0
    },
    {
      "all_correct": 0.75,
      "all_wrong": 0.125,
      "completion_length": 372.421875,
      "epoch": 0.028615740177593968,
      "grad_norm": 0.48009103444448936,
      "kl": 0.0400390625,
      "learning_rate": 9.979809028723442e-07,
      "loss": 0.0016,
      "reward": 1.9156250953674316,
      "reward_std": 0.04419417306780815,
      "rewards/accuracy_reward": 0.765625,
      "rewards/format_reward": 1.0,
      "step": 941,
      "temperature": 1.0
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.25,
      "completion_length": 408.71875,
      "epoch": 0.028646150103393747,
      "grad_norm": 0.7777220778370562,
      "kl": 0.034912109375,
      "learning_rate": 9.979766121043482e-07,
      "loss": 0.0014,
      "reward": 1.7216309309005737,
      "reward_std": 0.027476558461785316,
      "rewards/accuracy_reward": 0.596630871295929,
      "rewards/format_reward": 1.0,
      "step": 942,
      "temperature": 1.0
    },
    {
      "all_correct": 0.625,
      "all_wrong": 0.125,
      "completion_length": 404.71875,
      "epoch": 0.02867656002919353,
      "grad_norm": 0.9198329151539716,
      "kl": 0.0294189453125,
      "learning_rate": 9.979723167912943e-07,
      "loss": 0.0012,
      "reward": 1.9346178770065308,
      "reward_std": 0.07425513863563538,
      "rewards/accuracy_reward": 0.7752428650856018,
      "rewards/format_reward": 1.0,
      "step": 943,
      "temperature": 1.0
    },
    {
      "all_correct": 0.25,
      "all_wrong": 0.0,
      "completion_length": 398.96875,
      "epoch": 0.02870696995499331,
      "grad_norm": 1.2492067383093468,
      "kl": 0.023681640625,
      "learning_rate": 9.979680169332218e-07,
      "loss": 0.0009,
      "reward": 1.7629592418670654,
      "reward_std": 0.2209610491991043,
      "rewards/accuracy_reward": 0.6317091584205627,
      "rewards/format_reward": 1.0,
      "step": 944,
      "temperature": 1.0
    },
    {
      "all_correct": 0.625,
      "all_wrong": 0.125,
      "completion_length": 375.53125,
      "epoch": 0.02873737988079309,
      "grad_norm": 1.0021986293836167,
      "kl": 0.034423828125,
      "learning_rate": 9.9796371253017e-07,
      "loss": 0.0014,
      "reward": 1.9547169208526611,
      "reward_std": 0.10674916207790375,
      "rewards/accuracy_reward": 0.7890918850898743,
      "rewards/format_reward": 1.0,
      "step": 945,
      "temperature": 1.0
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.375,
      "completion_length": 392.765625,
      "epoch": 0.02876778980659287,
      "grad_norm": 0.42457408637622385,
      "kl": 0.03076171875,
      "learning_rate": 9.97959403582178e-07,
      "loss": 0.0012,
      "reward": 1.7281250953674316,
      "reward_std": 0.05250425264239311,
      "rewards/accuracy_reward": 0.609375,
      "rewards/format_reward": 1.0,
      "step": 946,
      "temperature": 1.0
    },
    {
      "all_correct": 0.375,
      "all_wrong": 0.125,
      "completion_length": 439.171875,
      "epoch": 0.028798199732392653,
      "grad_norm": 0.721668805203199,
      "kl": 0.0250244140625,
      "learning_rate": 9.979550900892855e-07,
      "loss": 0.001,
      "reward": 1.771875023841858,
      "reward_std": 0.23347899317741394,
      "rewards/accuracy_reward": 0.65625,
      "rewards/format_reward": 1.0,
      "step": 947,
      "temperature": 1.0
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.125,
      "completion_length": 405.15625,
      "epoch": 0.028828609658192433,
      "grad_norm": 1.2583794360604859,
      "kl": 0.03173828125,
      "learning_rate": 9.979507720515315e-07,
      "loss": 0.0013,
      "reward": 1.8047316074371338,
      "reward_std": 0.047892432659864426,
      "rewards/accuracy_reward": 0.6453566551208496,
      "rewards/format_reward": 1.0,
      "step": 948,
      "temperature": 1.0
    },
    {
      "all_correct": 0.625,
      "all_wrong": 0.0,
      "completion_length": 392.703125,
      "epoch": 0.028859019583992215,
      "grad_norm": 1.0734142744654365,
      "kl": 0.0257568359375,
      "learning_rate": 9.979464494689554e-07,
      "loss": 0.001,
      "reward": 1.8413039445877075,
      "reward_std": 0.09166154265403748,
      "rewards/accuracy_reward": 0.6913039088249207,
      "rewards/format_reward": 1.0,
      "step": 949,
      "temperature": 1.0
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.125,
      "completion_length": 393.8125,
      "epoch": 0.028889429509791995,
      "grad_norm": 1.083258443809071,
      "kl": 0.02587890625,
      "learning_rate": 9.979421223415969e-07,
      "loss": 0.001,
      "reward": 1.851592779159546,
      "reward_std": 0.13468001782894135,
      "rewards/accuracy_reward": 0.6953428387641907,
      "rewards/format_reward": 1.0,
      "step": 950,
      "temperature": 1.0
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.25,
      "completion_length": 388.65625,
      "epoch": 0.028919839435591777,
      "grad_norm": 3.9233771180464427,
      "kl": 0.0291748046875,
      "learning_rate": 9.979377906694951e-07,
      "loss": 0.0012,
      "reward": 1.6732618808746338,
      "reward_std": 0.037542469799518585,
      "rewards/accuracy_reward": 0.5420119762420654,
      "rewards/format_reward": 1.0,
      "step": 951,
      "temperature": 1.0
    },
    {
      "all_correct": 0.375,
      "all_wrong": 0.125,
      "completion_length": 404.671875,
      "epoch": 0.02895024936139156,
      "grad_norm": 0.9794857387291974,
      "kl": 0.0267333984375,
      "learning_rate": 9.979334544526902e-07,
      "loss": 0.0011,
      "reward": 1.6966025829315186,
      "reward_std": 0.20698893070220947,
      "rewards/accuracy_reward": 0.5684775114059448,
      "rewards/format_reward": 1.0,
      "step": 952,
      "temperature": 1.0
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.0,
      "completion_length": 392.59375,
      "epoch": 0.02898065928719134,
      "grad_norm": 1.668871628374678,
      "kl": 0.0294189453125,
      "learning_rate": 9.979291136912213e-07,
      "loss": 0.0012,
      "reward": 1.8008915185928345,
      "reward_std": 0.04139992594718933,
      "rewards/accuracy_reward": 0.610266387462616,
      "rewards/format_reward": 1.0,
      "step": 953,
      "temperature": 1.0
    },
    {
      "all_correct": 0.375,
      "all_wrong": 0.0,
      "completion_length": 437.78125,
      "epoch": 0.02901106921299112,
      "grad_norm": 1.38145164616484,
      "kl": 0.02880859375,
      "learning_rate": 9.97924768385128e-07,
      "loss": 0.0011,
      "reward": 1.749072551727295,
      "reward_std": 0.14466246962547302,
      "rewards/accuracy_reward": 0.6178224682807922,
      "rewards/format_reward": 1.0,
      "step": 954,
      "temperature": 1.0
    },
    {
      "all_correct": 0.625,
      "all_wrong": 0.125,
      "completion_length": 379.484375,
      "epoch": 0.0290414791387909,
      "grad_norm": 23.099239772447394,
      "kl": 0.02783203125,
      "learning_rate": 9.9792041853445e-07,
      "loss": 0.0011,
      "reward": 1.8895816802978516,
      "reward_std": 0.08888044953346252,
      "rewards/accuracy_reward": 0.7302066683769226,
      "rewards/format_reward": 1.0,
      "step": 955,
      "temperature": 1.0
    },
    {
      "all_correct": 0.375,
      "all_wrong": 0.125,
      "completion_length": 386.34375,
      "epoch": 0.029071889064590684,
      "grad_norm": 1.9618639377814826,
      "kl": 0.033447265625,
      "learning_rate": 9.979160641392273e-07,
      "loss": 0.0013,
      "reward": 1.6772538423538208,
      "reward_std": 0.12570199370384216,
      "rewards/accuracy_reward": 0.5491288900375366,
      "rewards/format_reward": 1.0,
      "step": 956,
      "temperature": 1.0
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.0,
      "completion_length": 375.234375,
      "epoch": 0.029102298990390463,
      "grad_norm": 1.1989404253767613,
      "kl": 0.03369140625,
      "learning_rate": 9.979117051994991e-07,
      "loss": 0.0013,
      "reward": 1.9542853832244873,
      "reward_std": 0.12954586744308472,
      "rewards/accuracy_reward": 0.7730352878570557,
      "rewards/format_reward": 1.0,
      "step": 957,
      "temperature": 1.0
    },
    {
      "all_correct": 0.625,
      "all_wrong": 0.0,
      "completion_length": 376.234375,
      "epoch": 0.029132708916190245,
      "grad_norm": 0.6999490027694096,
      "kl": 0.0240478515625,
      "learning_rate": 9.979073417153056e-07,
      "loss": 0.001,
      "reward": 1.915624976158142,
      "reward_std": 0.19945894181728363,
      "rewards/accuracy_reward": 0.765625,
      "rewards/format_reward": 1.0,
      "step": 958,
      "temperature": 1.0
    },
    {
      "all_correct": 0.875,
      "all_wrong": 0.0,
      "completion_length": 362.265625,
      "epoch": 0.029163118841990025,
      "grad_norm": 0.7369000499348929,
      "kl": 0.0267333984375,
      "learning_rate": 9.979029736866865e-07,
      "loss": 0.0011,
      "reward": 2.10657000541687,
      "reward_std": 0.017150744795799255,
      "rewards/accuracy_reward": 0.909695029258728,
      "rewards/format_reward": 1.0,
      "step": 959,
      "temperature": 1.0
    },
    {
      "all_correct": 0.375,
      "all_wrong": 0.125,
      "completion_length": 427.71875,
      "epoch": 0.029193528767789807,
      "grad_norm": 1.2702683362614735,
      "kl": 0.0203857421875,
      "learning_rate": 9.97898601113682e-07,
      "loss": 0.0008,
      "reward": 1.6314494609832764,
      "reward_std": 0.2217612862586975,
      "rewards/accuracy_reward": 0.5814494490623474,
      "rewards/format_reward": 0.96875,
      "step": 960,
      "temperature": 1.0
    },
    {
      "all_correct": 0.75,
      "all_wrong": 0.0,
      "completion_length": 362.421875,
      "epoch": 0.029223938693589586,
      "grad_norm": 1.3454688418066623,
      "kl": 0.031005859375,
      "learning_rate": 9.978942239963313e-07,
      "loss": 0.0012,
      "reward": 1.9503661394119263,
      "reward_std": 0.0223162192851305,
      "rewards/accuracy_reward": 0.7909910678863525,
      "rewards/format_reward": 1.0,
      "step": 961,
      "temperature": 1.0
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.125,
      "completion_length": 371.46875,
      "epoch": 0.02925434861938937,
      "grad_norm": 1.1394228365817627,
      "kl": 0.025390625,
      "learning_rate": 9.97889842334675e-07,
      "loss": 0.001,
      "reward": 1.8466341495513916,
      "reward_std": 0.14077790081501007,
      "rewards/accuracy_reward": 0.6997590065002441,
      "rewards/format_reward": 1.0,
      "step": 962,
      "temperature": 1.0
    },
    {
      "all_correct": 0.625,
      "all_wrong": 0.0,
      "completion_length": 365.21875,
      "epoch": 0.02928475854518915,
      "grad_norm": 1.1849044273331357,
      "kl": 0.0279541015625,
      "learning_rate": 9.978854561287526e-07,
      "loss": 0.0011,
      "reward": 1.8964686393737793,
      "reward_std": 0.09825307875871658,
      "rewards/accuracy_reward": 0.7308435440063477,
      "rewards/format_reward": 1.0,
      "step": 963,
      "temperature": 1.0
    },
    {
      "all_correct": 0.75,
      "all_wrong": 0.0,
      "completion_length": 372.234375,
      "epoch": 0.02931516847098893,
      "grad_norm": 1.4882034685366563,
      "kl": 0.0264892578125,
      "learning_rate": 9.978810653786047e-07,
      "loss": 0.0011,
      "reward": 2.1031250953674316,
      "reward_std": 0.1590200662612915,
      "rewards/accuracy_reward": 0.9375,
      "rewards/format_reward": 1.0,
      "step": 964,
      "temperature": 1.0
    },
    {
      "all_correct": 0.75,
      "all_wrong": 0.125,
      "completion_length": 353.125,
      "epoch": 0.02934557839678871,
      "grad_norm": 1.1399864272692561,
      "kl": 0.02880859375,
      "learning_rate": 9.978766700842708e-07,
      "loss": 0.0012,
      "reward": 1.975847840309143,
      "reward_std": 0.022725991904735565,
      "rewards/accuracy_reward": 0.8164727687835693,
      "rewards/format_reward": 1.0,
      "step": 965,
      "temperature": 1.0
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.125,
      "completion_length": 361.5,
      "epoch": 0.029375988322588493,
      "grad_norm": 1.3343373972984818,
      "kl": 0.02685546875,
      "learning_rate": 9.978722702457912e-07,
      "loss": 0.0011,
      "reward": 1.9047565460205078,
      "reward_std": 0.14533251523971558,
      "rewards/accuracy_reward": 0.7453814744949341,
      "rewards/format_reward": 1.0,
      "step": 966,
      "temperature": 1.0
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.125,
      "completion_length": 378.734375,
      "epoch": 0.029406398248388275,
      "grad_norm": 0.8460601083173706,
      "kl": 0.0203857421875,
      "learning_rate": 9.978678658632062e-07,
      "loss": 0.0008,
      "reward": 1.8355995416641235,
      "reward_std": 0.128595232963562,
      "rewards/accuracy_reward": 0.6824743747711182,
      "rewards/format_reward": 1.0,
      "step": 967,
      "temperature": 1.0
    },
    {
      "all_correct": 0.375,
      "all_wrong": 0.0,
      "completion_length": 372.421875,
      "epoch": 0.029436808174188055,
      "grad_norm": 1.475867147831558,
      "kl": 0.02783203125,
      "learning_rate": 9.978634569365559e-07,
      "loss": 0.0011,
      "reward": 1.8253848552703857,
      "reward_std": 0.24557790160179138,
      "rewards/accuracy_reward": 0.6691348552703857,
      "rewards/format_reward": 1.0,
      "step": 968,
      "temperature": 1.0
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.0,
      "completion_length": 375.796875,
      "epoch": 0.029467218099987837,
      "grad_norm": 2.169297660446578,
      "kl": 0.027587890625,
      "learning_rate": 9.978590434658806e-07,
      "loss": 0.0011,
      "reward": 1.9281532764434814,
      "reward_std": 0.18303149938583374,
      "rewards/accuracy_reward": 0.7594032883644104,
      "rewards/format_reward": 1.0,
      "step": 969,
      "temperature": 1.0
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.375,
      "completion_length": 345.953125,
      "epoch": 0.029497628025787617,
      "grad_norm": 0.7151006176558011,
      "kl": 0.035888671875,
      "learning_rate": 9.978546254512206e-07,
      "loss": 0.0014,
      "reward": 1.6122395992279053,
      "reward_std": 0.017303230240941048,
      "rewards/accuracy_reward": 0.5091145634651184,
      "rewards/format_reward": 1.0,
      "step": 970,
      "temperature": 1.0
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.0,
      "completion_length": 392.96875,
      "epoch": 0.0295280379515874,
      "grad_norm": 1.156622711966878,
      "kl": 0.023193359375,
      "learning_rate": 9.97850202892616e-07,
      "loss": 0.0009,
      "reward": 1.827118158340454,
      "reward_std": 0.15230073034763336,
      "rewards/accuracy_reward": 0.6614930629730225,
      "rewards/format_reward": 1.0,
      "step": 971,
      "temperature": 1.0
    },
    {
      "all_correct": 0.625,
      "all_wrong": 0.0,
      "completion_length": 359.0,
      "epoch": 0.02955844787738718,
      "grad_norm": 1.2567777112654557,
      "kl": 0.025146484375,
      "learning_rate": 9.978457757901074e-07,
      "loss": 0.001,
      "reward": 1.953125,
      "reward_std": 0.2253442257642746,
      "rewards/accuracy_reward": 0.796875,
      "rewards/format_reward": 1.0,
      "step": 972,
      "temperature": 1.0
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.0,
      "completion_length": 391.3125,
      "epoch": 0.02958885780318696,
      "grad_norm": 5.286549021007393,
      "kl": 0.03271484375,
      "learning_rate": 9.978413441437352e-07,
      "loss": 0.0013,
      "reward": 1.8352673053741455,
      "reward_std": 0.06420054286718369,
      "rewards/accuracy_reward": 0.6790173053741455,
      "rewards/format_reward": 1.0,
      "step": 973,
      "temperature": 1.0
    },
    {
      "all_correct": 0.625,
      "all_wrong": 0.125,
      "completion_length": 366.203125,
      "epoch": 0.02961926772898674,
      "grad_norm": 0.7401289635294794,
      "kl": 0.02880859375,
      "learning_rate": 9.978369079535397e-07,
      "loss": 0.0012,
      "reward": 1.9489858150482178,
      "reward_std": 0.07714703679084778,
      "rewards/accuracy_reward": 0.789610743522644,
      "rewards/format_reward": 1.0,
      "step": 974,
      "temperature": 1.0
    },
    {
      "all_correct": 0.625,
      "all_wrong": 0.0,
      "completion_length": 364.09375,
      "epoch": 0.029649677654786523,
      "grad_norm": 1.1255922200526791,
      "kl": 0.0267333984375,
      "learning_rate": 9.978324672195615e-07,
      "loss": 0.0011,
      "reward": 2.1031250953674316,
      "reward_std": 0.190526083111763,
      "rewards/accuracy_reward": 0.921875,
      "rewards/format_reward": 1.0,
      "step": 975,
      "temperature": 1.0
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.125,
      "completion_length": 376.484375,
      "epoch": 0.029680087580586302,
      "grad_norm": 1.1122777567497524,
      "kl": 0.03173828125,
      "learning_rate": 9.97828021941841e-07,
      "loss": 0.0013,
      "reward": 1.7939478158950806,
      "reward_std": 0.17696912586688995,
      "rewards/accuracy_reward": 0.653322696685791,
      "rewards/format_reward": 1.0,
      "step": 976,
      "temperature": 1.0
    },
    {
      "all_correct": 0.75,
      "all_wrong": 0.125,
      "completion_length": 356.796875,
      "epoch": 0.029710497506386085,
      "grad_norm": 0.7538102238125617,
      "kl": 0.0296630859375,
      "learning_rate": 9.97823572120419e-07,
      "loss": 0.0012,
      "reward": 1.975000023841858,
      "reward_std": 0.08017838001251221,
      "rewards/accuracy_reward": 0.8125,
      "rewards/format_reward": 1.0,
      "step": 977,
      "temperature": 1.0
    },
    {
      "all_correct": 0.625,
      "all_wrong": 0.125,
      "completion_length": 359.34375,
      "epoch": 0.029740907432185864,
      "grad_norm": 1.1599605620501257,
      "kl": 0.03173828125,
      "learning_rate": 9.97819117755336e-07,
      "loss": 0.0013,
      "reward": 1.9171385765075684,
      "reward_std": 0.09751737117767334,
      "rewards/accuracy_reward": 0.7640135288238525,
      "rewards/format_reward": 1.0,
      "step": 978,
      "temperature": 1.0
    },
    {
      "all_correct": 0.25,
      "all_wrong": 0.25,
      "completion_length": 379.75,
      "epoch": 0.029771317357985647,
      "grad_norm": 4.503875807685217,
      "kl": 0.0294189453125,
      "learning_rate": 9.978146588466325e-07,
      "loss": 0.0012,
      "reward": 1.6928553581237793,
      "reward_std": 0.09279040992259979,
      "rewards/accuracy_reward": 0.549105167388916,
      "rewards/format_reward": 1.0,
      "step": 979,
      "temperature": 1.0
    },
    {
      "all_correct": 0.375,
      "all_wrong": 0.25,
      "completion_length": 393.25,
      "epoch": 0.02980172728378543,
      "grad_norm": 1.8302686911428612,
      "kl": 0.030029296875,
      "learning_rate": 9.978101953943493e-07,
      "loss": 0.0012,
      "reward": 1.5455598831176758,
      "reward_std": 0.0946376621723175,
      "rewards/accuracy_reward": 0.46118488907814026,
      "rewards/format_reward": 1.0,
      "step": 980,
      "temperature": 1.0
    },
    {
      "all_correct": 0.375,
      "all_wrong": 0.125,
      "completion_length": 414.140625,
      "epoch": 0.02983213720958521,
      "grad_norm": 1.6506077815154478,
      "kl": 0.028564453125,
      "learning_rate": 9.978057273985274e-07,
      "loss": 0.0011,
      "reward": 1.7312986850738525,
      "reward_std": 0.1738753467798233,
      "rewards/accuracy_reward": 0.5969235897064209,
      "rewards/format_reward": 1.0,
      "step": 981,
      "temperature": 1.0
    },
    {
      "all_correct": 0.25,
      "all_wrong": 0.125,
      "completion_length": 408.578125,
      "epoch": 0.02986254713538499,
      "grad_norm": 1.833667770887371,
      "kl": 0.028076171875,
      "learning_rate": 9.978012548592072e-07,
      "loss": 0.0011,
      "reward": 1.5394816398620605,
      "reward_std": 0.18644912540912628,
      "rewards/accuracy_reward": 0.4238566756248474,
      "rewards/format_reward": 1.0,
      "step": 982,
      "temperature": 1.0
    },
    {
      "all_correct": 0.375,
      "all_wrong": 0.125,
      "completion_length": 364.96875,
      "epoch": 0.02989295706118477,
      "grad_norm": 1.5160733703126137,
      "kl": 0.031982421875,
      "learning_rate": 9.977967777764298e-07,
      "loss": 0.0013,
      "reward": 1.6664032936096191,
      "reward_std": 0.08078866451978683,
      "rewards/accuracy_reward": 0.5101531744003296,
      "rewards/format_reward": 1.0,
      "step": 983,
      "temperature": 1.0
    },
    {
      "all_correct": 0.75,
      "all_wrong": 0.125,
      "completion_length": 360.359375,
      "epoch": 0.029923366986984553,
      "grad_norm": 0.44449218073993657,
      "kl": 0.033203125,
      "learning_rate": 9.97792296150236e-07,
      "loss": 0.0013,
      "reward": 1.9976552724838257,
      "reward_std": 0.005704321898519993,
      "rewards/accuracy_reward": 0.822655200958252,
      "rewards/format_reward": 1.0,
      "step": 984,
      "temperature": 1.0
    },
    {
      "all_correct": 0.375,
      "all_wrong": 0.125,
      "completion_length": 414.625,
      "epoch": 0.029953776912784332,
      "grad_norm": 1.1091560585910236,
      "kl": 0.0264892578125,
      "learning_rate": 9.977878099806665e-07,
      "loss": 0.0011,
      "reward": 1.70172917842865,
      "reward_std": 0.1716819703578949,
      "rewards/accuracy_reward": 0.5673540830612183,
      "rewards/format_reward": 1.0,
      "step": 985,
      "temperature": 1.0
    },
    {
      "all_correct": 0.75,
      "all_wrong": 0.125,
      "completion_length": 358.9375,
      "epoch": 0.029984186838584115,
      "grad_norm": 0.3466471642938768,
      "kl": 0.027587890625,
      "learning_rate": 9.977833192677623e-07,
      "loss": 0.0011,
      "reward": 1.9562499523162842,
      "reward_std": 0.077632375061512,
      "rewards/accuracy_reward": 0.796875,
      "rewards/format_reward": 1.0,
      "step": 986,
      "temperature": 1.0
    },
    {
      "all_correct": 0.375,
      "all_wrong": 0.125,
      "completion_length": 369.8125,
      "epoch": 0.030014596764383894,
      "grad_norm": 1.5107527162047532,
      "kl": 0.0230712890625,
      "learning_rate": 9.977788240115646e-07,
      "loss": 0.0009,
      "reward": 1.8345935344696045,
      "reward_std": 0.18656717240810394,
      "rewards/accuracy_reward": 0.6877186298370361,
      "rewards/format_reward": 1.0,
      "step": 987,
      "temperature": 1.0
    },
    {
      "all_correct": 0.875,
      "all_wrong": 0.0,
      "completion_length": 369.1875,
      "epoch": 0.030045006690183677,
      "grad_norm": 0.29539111343017155,
      "kl": 0.0311279296875,
      "learning_rate": 9.977743242121142e-07,
      "loss": 0.0012,
      "reward": 2.1437501907348633,
      "reward_std": 0.077632375061512,
      "rewards/accuracy_reward": 0.953125,
      "rewards/format_reward": 1.0,
      "step": 988,
      "temperature": 1.0
    },
    {
      "all_correct": 0.375,
      "all_wrong": 0.125,
      "completion_length": 400.765625,
      "epoch": 0.030075416615983456,
      "grad_norm": 1.1081499466093632,
      "kl": 0.0269775390625,
      "learning_rate": 9.977698198694523e-07,
      "loss": 0.0011,
      "reward": 1.6687896251678467,
      "reward_std": 0.04964016377925873,
      "rewards/accuracy_reward": 0.5156646370887756,
      "rewards/format_reward": 1.0,
      "step": 989,
      "temperature": 1.0
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.25,
      "completion_length": 365.296875,
      "epoch": 0.03010582654178324,
      "grad_norm": 0.6733295323828469,
      "kl": 0.02978515625,
      "learning_rate": 9.977653109836201e-07,
      "loss": 0.0012,
      "reward": 1.8562500476837158,
      "reward_std": 0.11763877421617508,
      "rewards/accuracy_reward": 0.71875,
      "rewards/format_reward": 1.0,
      "step": 990,
      "temperature": 1.0
    },
    {
      "all_correct": 0.625,
      "all_wrong": 0.0,
      "completion_length": 390.515625,
      "epoch": 0.030136236467583018,
      "grad_norm": 0.6981963351715742,
      "kl": 0.026123046875,
      "learning_rate": 9.977607975546588e-07,
      "loss": 0.001,
      "reward": 2.081507682800293,
      "reward_std": 0.12283474206924438,
      "rewards/accuracy_reward": 0.9002578258514404,
      "rewards/format_reward": 1.0,
      "step": 991,
      "temperature": 1.0
    },
    {
      "all_correct": 0.625,
      "all_wrong": 0.125,
      "completion_length": 369.796875,
      "epoch": 0.0301666463933828,
      "grad_norm": 1.1929917405349333,
      "kl": 0.033447265625,
      "learning_rate": 9.97756279582609e-07,
      "loss": 0.0013,
      "reward": 1.9112459421157837,
      "reward_std": 0.10382983088493347,
      "rewards/accuracy_reward": 0.75187087059021,
      "rewards/format_reward": 1.0,
      "step": 992,
      "temperature": 1.0
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.125,
      "completion_length": 371.6875,
      "epoch": 0.03019705631918258,
      "grad_norm": 7.433376278489804,
      "kl": 0.0380859375,
      "learning_rate": 9.977517570675128e-07,
      "loss": 0.0015,
      "reward": 1.873798131942749,
      "reward_std": 0.1491905152797699,
      "rewards/accuracy_reward": 0.7331730723381042,
      "rewards/format_reward": 1.0,
      "step": 993,
      "temperature": 1.0
    },
    {
      "all_correct": 0.875,
      "all_wrong": 0.0,
      "completion_length": 399.46875,
      "epoch": 0.030227466244982362,
      "grad_norm": 0.7285474661582106,
      "kl": 0.02685546875,
      "learning_rate": 9.977472300094108e-07,
      "loss": 0.0011,
      "reward": 2.1031250953674316,
      "reward_std": 0.08647121489048004,
      "rewards/accuracy_reward": 0.921875,
      "rewards/format_reward": 1.0,
      "step": 994,
      "temperature": 1.0
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.25,
      "completion_length": 368.421875,
      "epoch": 0.030257876170782145,
      "grad_norm": 0.6211543500311653,
      "kl": 0.03662109375,
      "learning_rate": 9.977426984083445e-07,
      "loss": 0.0015,
      "reward": 1.7468750476837158,
      "reward_std": 0.15315142273902893,
      "rewards/accuracy_reward": 0.625,
      "rewards/format_reward": 1.0,
      "step": 995,
      "temperature": 1.0
    },
    {
      "all_correct": 0.25,
      "all_wrong": 0.25,
      "completion_length": 374.15625,
      "epoch": 0.030288286096581924,
      "grad_norm": 3.3128506331826095,
      "kl": 0.034423828125,
      "learning_rate": 9.977381622643555e-07,
      "loss": 0.0014,
      "reward": 1.5265625715255737,
      "reward_std": 0.18119041621685028,
      "rewards/accuracy_reward": 0.4453125,
      "rewards/format_reward": 1.0,
      "step": 996,
      "temperature": 1.0
    },
    {
      "all_correct": 0.625,
      "all_wrong": 0.0,
      "completion_length": 394.265625,
      "epoch": 0.030318696022381707,
      "grad_norm": 0.8180593751576957,
      "kl": 0.02783203125,
      "learning_rate": 9.97733621577485e-07,
      "loss": 0.0011,
      "reward": 2.05006742477417,
      "reward_std": 0.09958094358444214,
      "rewards/accuracy_reward": 0.8656922578811646,
      "rewards/format_reward": 1.0,
      "step": 997,
      "temperature": 1.0
    },
    {
      "all_correct": 0.375,
      "all_wrong": 0.125,
      "completion_length": 385.703125,
      "epoch": 0.030349105948181486,
      "grad_norm": 1.7214226749397117,
      "kl": 0.033447265625,
      "learning_rate": 9.977290763477744e-07,
      "loss": 0.0013,
      "reward": 1.66288423538208,
      "reward_std": 0.23061969876289368,
      "rewards/accuracy_reward": 0.5597591400146484,
      "rewards/format_reward": 0.953125,
      "step": 998,
      "temperature": 1.0
    },
    {
      "all_correct": 0.875,
      "all_wrong": 0.0,
      "completion_length": 375.15625,
      "epoch": 0.03037951587398127,
      "grad_norm": 1.5463239044841857,
      "kl": 0.0289306640625,
      "learning_rate": 9.977245265752652e-07,
      "loss": 0.0012,
      "reward": 2.054236888885498,
      "reward_std": 0.013707850128412247,
      "rewards/accuracy_reward": 0.8823617696762085,
      "rewards/format_reward": 1.0,
      "step": 999,
      "temperature": 1.0
    },
    {
      "all_correct": 0.75,
      "all_wrong": 0.0,
      "completion_length": 357.15625,
      "epoch": 0.030409925799781048,
      "grad_norm": 0.782399850106308,
      "kl": 0.02880859375,
      "learning_rate": 9.977199722599991e-07,
      "loss": 0.0012,
      "reward": 2.106250047683716,
      "reward_std": 0.1332113891839981,
      "rewards/accuracy_reward": 0.921875,
      "rewards/format_reward": 1.0,
      "step": 1000,
      "temperature": 1.0
    },
    {
      "all_correct": 0.625,
      "all_wrong": 0.125,
      "completion_length": 385.15625,
      "epoch": 0.03044033572558083,
      "grad_norm": 2.5352426202895546,
      "kl": 0.0284423828125,
      "learning_rate": 9.977154134020174e-07,
      "loss": 0.0011,
      "reward": 1.8904694318771362,
      "reward_std": 0.07783059775829315,
      "rewards/accuracy_reward": 0.7342193722724915,
      "rewards/format_reward": 1.0,
      "step": 1001,
      "temperature": 1.0
    },
    {
      "all_correct": 0.625,
      "all_wrong": 0.125,
      "completion_length": 351.65625,
      "epoch": 0.03047074565138061,
      "grad_norm": 1.1322854843580028,
      "kl": 0.03125,
      "learning_rate": 9.97710850001362e-07,
      "loss": 0.0012,
      "reward": 1.9802082777023315,
      "reward_std": 0.07344460487365723,
      "rewards/accuracy_reward": 0.8177083730697632,
      "rewards/format_reward": 1.0,
      "step": 1002,
      "temperature": 1.0
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.25,
      "completion_length": 390.6875,
      "epoch": 0.030501155577180392,
      "grad_norm": 1.2207954424876948,
      "kl": 0.028564453125,
      "learning_rate": 9.977062820580744e-07,
      "loss": 0.0011,
      "reward": 1.7218749523162842,
      "reward_std": 0.10816285014152527,
      "rewards/accuracy_reward": 0.625,
      "rewards/format_reward": 1.0,
      "step": 1003,
      "temperature": 1.0
    },
    {
      "all_correct": 0.75,
      "all_wrong": 0.0,
      "completion_length": 363.734375,
      "epoch": 0.03053156550298017,
      "grad_norm": 0.8529650625732379,
      "kl": 0.034912109375,
      "learning_rate": 9.977017095721963e-07,
      "loss": 0.0014,
      "reward": 2.074571132659912,
      "reward_std": 0.08991102874279022,
      "rewards/accuracy_reward": 0.8933210968971252,
      "rewards/format_reward": 1.0,
      "step": 1004,
      "temperature": 1.0
    },
    {
      "all_correct": 0.75,
      "all_wrong": 0.0,
      "completion_length": 355.828125,
      "epoch": 0.030561975428779954,
      "grad_norm": 1.389363713669344,
      "kl": 0.0306396484375,
      "learning_rate": 9.976971325437693e-07,
      "loss": 0.0012,
      "reward": 2.0461008548736572,
      "reward_std": 0.045329876244068146,
      "rewards/accuracy_reward": 0.8586008548736572,
      "rewards/format_reward": 1.0,
      "step": 1005,
      "temperature": 1.0
    },
    {
      "all_correct": 0.625,
      "all_wrong": 0.0,
      "completion_length": 393.6875,
      "epoch": 0.030592385354579733,
      "grad_norm": 1.4876171469465767,
      "kl": 0.028076171875,
      "learning_rate": 9.976925509728354e-07,
      "loss": 0.0011,
      "reward": 1.9939799308776855,
      "reward_std": 0.15717732906341553,
      "rewards/accuracy_reward": 0.847105085849762,
      "rewards/format_reward": 1.0,
      "step": 1006,
      "temperature": 1.0
    },
    {
      "all_correct": 0.625,
      "all_wrong": 0.125,
      "completion_length": 374.765625,
      "epoch": 0.030622795280379516,
      "grad_norm": 1.0638612113186632,
      "kl": 0.0308837890625,
      "learning_rate": 9.976879648594362e-07,
      "loss": 0.0012,
      "reward": 1.9098339080810547,
      "reward_std": 0.04801425337791443,
      "rewards/accuracy_reward": 0.7473338842391968,
      "rewards/format_reward": 1.0,
      "step": 1007,
      "temperature": 1.0
    },
    {
      "all_correct": 0.625,
      "all_wrong": 0.0,
      "completion_length": 387.8125,
      "epoch": 0.030653205206179295,
      "grad_norm": 1.1338305280574497,
      "kl": 0.03369140625,
      "learning_rate": 9.976833742036138e-07,
      "loss": 0.0014,
      "reward": 2.0214643478393555,
      "reward_std": 0.05749175697565079,
      "rewards/accuracy_reward": 0.8245891332626343,
      "rewards/format_reward": 1.0,
      "step": 1008,
      "temperature": 1.0
    },
    {
      "all_correct": 0.375,
      "all_wrong": 0.25,
      "completion_length": 371.34375,
      "epoch": 0.030683615131979078,
      "grad_norm": 0.8910110238535314,
      "kl": 0.0301513671875,
      "learning_rate": 9.976787790054102e-07,
      "loss": 0.0012,
      "reward": 1.709375023841858,
      "reward_std": 0.16666369140148163,
      "rewards/accuracy_reward": 0.59375,
      "rewards/format_reward": 1.0,
      "step": 1009,
      "temperature": 1.0
    },
    {
      "all_correct": 0.125,
      "all_wrong": 0.125,
      "completion_length": 390.28125,
      "epoch": 0.03071402505777886,
      "grad_norm": 1.4706095789329003,
      "kl": 0.0281982421875,
      "learning_rate": 9.976741792648668e-07,
      "loss": 0.0011,
      "reward": 1.5338377952575684,
      "reward_std": 0.23000706732273102,
      "rewards/accuracy_reward": 0.4275878369808197,
      "rewards/format_reward": 1.0,
      "step": 1010,
      "temperature": 1.0
    },
    {
      "all_correct": 0.375,
      "all_wrong": 0.25,
      "completion_length": 375.359375,
      "epoch": 0.03074443498357864,
      "grad_norm": 1.0386717397737988,
      "kl": 0.032470703125,
      "learning_rate": 9.97669574982026e-07,
      "loss": 0.0013,
      "reward": 1.5888352394104004,
      "reward_std": 0.06130202114582062,
      "rewards/accuracy_reward": 0.4669603705406189,
      "rewards/format_reward": 1.0,
      "step": 1011,
      "temperature": 1.0
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.0,
      "completion_length": 400.390625,
      "epoch": 0.030774844909378422,
      "grad_norm": 1.7763034198469754,
      "kl": 0.03271484375,
      "learning_rate": 9.976649661569298e-07,
      "loss": 0.0013,
      "reward": 1.8490240573883057,
      "reward_std": 0.11306708306074142,
      "rewards/accuracy_reward": 0.6896489858627319,
      "rewards/format_reward": 1.0,
      "step": 1012,
      "temperature": 1.0
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.125,
      "completion_length": 382.34375,
      "epoch": 0.0308052548351782,
      "grad_norm": 1.1689508955512573,
      "kl": 0.033447265625,
      "learning_rate": 9.976603527896202e-07,
      "loss": 0.0013,
      "reward": 1.7343809604644775,
      "reward_std": 0.12506583333015442,
      "rewards/accuracy_reward": 0.6125059723854065,
      "rewards/format_reward": 1.0,
      "step": 1013,
      "temperature": 1.0
    },
    {
      "all_correct": 0.625,
      "all_wrong": 0.0,
      "completion_length": 366.4375,
      "epoch": 0.030835664760977984,
      "grad_norm": 0.941164418094868,
      "kl": 0.04150390625,
      "learning_rate": 9.976557348801392e-07,
      "loss": 0.0017,
      "reward": 2.0537610054016113,
      "reward_std": 0.09884816408157349,
      "rewards/accuracy_reward": 0.8631359338760376,
      "rewards/format_reward": 1.0,
      "step": 1014,
      "temperature": 1.0
    },
    {
      "all_correct": 0.625,
      "all_wrong": 0.0,
      "completion_length": 381.390625,
      "epoch": 0.030866074686777763,
      "grad_norm": 0.831857428020724,
      "kl": 0.026123046875,
      "learning_rate": 9.97651112428529e-07,
      "loss": 0.001,
      "reward": 1.8866114616394043,
      "reward_std": 0.10539491474628448,
      "rewards/accuracy_reward": 0.7209863662719727,
      "rewards/format_reward": 1.0,
      "step": 1015,
      "temperature": 1.0
    },
    {
      "all_correct": 0.25,
      "all_wrong": 0.125,
      "completion_length": 393.8125,
      "epoch": 0.030896484612577546,
      "grad_norm": 1.253263403381405,
      "kl": 0.0322265625,
      "learning_rate": 9.97646485434832e-07,
      "loss": 0.0013,
      "reward": 1.6774048805236816,
      "reward_std": 0.20186689496040344,
      "rewards/accuracy_reward": 0.5336548089981079,
      "rewards/format_reward": 1.0,
      "step": 1016,
      "temperature": 1.0
    },
    {
      "all_correct": 0.75,
      "all_wrong": 0.0,
      "completion_length": 382.890625,
      "epoch": 0.030926894538377325,
      "grad_norm": 0.8894819683205699,
      "kl": 0.0306396484375,
      "learning_rate": 9.9764185389909e-07,
      "loss": 0.0012,
      "reward": 1.9500000476837158,
      "reward_std": 0.12246951460838318,
      "rewards/accuracy_reward": 0.796875,
      "rewards/format_reward": 1.0,
      "step": 1017,
      "temperature": 1.0
    },
    {
      "all_correct": 0.625,
      "all_wrong": 0.125,
      "completion_length": 379.53125,
      "epoch": 0.030957304464177108,
      "grad_norm": 1.2104989301853364,
      "kl": 0.03515625,
      "learning_rate": 9.976372178213456e-07,
      "loss": 0.0014,
      "reward": 1.8262748718261719,
      "reward_std": 0.08429563790559769,
      "rewards/accuracy_reward": 0.679399847984314,
      "rewards/format_reward": 1.0,
      "step": 1018,
      "temperature": 1.0
    },
    {
      "all_correct": 0.625,
      "all_wrong": 0.125,
      "completion_length": 385.03125,
      "epoch": 0.030987714389976887,
      "grad_norm": 1.1865058840825473,
      "kl": 0.031494140625,
      "learning_rate": 9.976325772016414e-07,
      "loss": 0.0013,
      "reward": 1.8211631774902344,
      "reward_std": 0.1438705325126648,
      "rewards/accuracy_reward": 0.686788022518158,
      "rewards/format_reward": 1.0,
      "step": 1019,
      "temperature": 1.0
    },
    {
      "all_correct": 0.75,
      "all_wrong": 0.0,
      "completion_length": 366.15625,
      "epoch": 0.03101812431577667,
      "grad_norm": 0.4914112043612559,
      "kl": 0.031494140625,
      "learning_rate": 9.976279320400192e-07,
      "loss": 0.0013,
      "reward": 2.1187500953674316,
      "reward_std": 0.0530330091714859,
      "rewards/accuracy_reward": 0.921875,
      "rewards/format_reward": 1.0,
      "step": 1020,
      "temperature": 1.0
    },
    {
      "all_correct": 0.75,
      "all_wrong": 0.0,
      "completion_length": 376.625,
      "epoch": 0.03104853424157645,
      "grad_norm": 1.0128239611337386,
      "kl": 0.03369140625,
      "learning_rate": 9.976232823365215e-07,
      "loss": 0.0014,
      "reward": 2.06553316116333,
      "reward_std": 0.04186427593231201,
      "rewards/accuracy_reward": 0.8749080300331116,
      "rewards/format_reward": 1.0,
      "step": 1021,
      "temperature": 1.0
    },
    {
      "all_correct": 0.625,
      "all_wrong": 0.0,
      "completion_length": 386.9375,
      "epoch": 0.03107894416737623,
      "grad_norm": 1.0307083875752883,
      "kl": 0.027587890625,
      "learning_rate": 9.97618628091191e-07,
      "loss": 0.0011,
      "reward": 1.8793494701385498,
      "reward_std": 0.15918007493019104,
      "rewards/accuracy_reward": 0.7230994701385498,
      "rewards/format_reward": 1.0,
      "step": 1022,
      "temperature": 1.0
    },
    {
      "all_correct": 0.625,
      "all_wrong": 0.25,
      "completion_length": 385.75,
      "epoch": 0.031109354093176014,
      "grad_norm": 1.4294363581755307,
      "kl": 0.033203125,
      "learning_rate": 9.976139693040697e-07,
      "loss": 0.0013,
      "reward": 1.8375000953674316,
      "reward_std": 0.09531005471944809,
      "rewards/accuracy_reward": 0.703125,
      "rewards/format_reward": 1.0,
      "step": 1023,
      "temperature": 1.0
    },
    {
      "all_correct": 0.375,
      "all_wrong": 0.25,
      "completion_length": 392.5625,
      "epoch": 0.031139764018975793,
      "grad_norm": 1.2074880237842038,
      "kl": 0.02783203125,
      "learning_rate": 9.976093059752009e-07,
      "loss": 0.0011,
      "reward": 1.7406575679779053,
      "reward_std": 0.12536031007766724,
      "rewards/accuracy_reward": 0.6000326871871948,
      "rewards/format_reward": 1.0,
      "step": 1024,
      "temperature": 1.0
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.125,
      "completion_length": 360.625,
      "epoch": 0.031170173944775576,
      "grad_norm": 1.0327862152264016,
      "kl": 0.03564453125,
      "learning_rate": 9.976046381046264e-07,
      "loss": 0.0014,
      "reward": 1.8537046909332275,
      "reward_std": 0.13305805623531342,
      "rewards/accuracy_reward": 0.713079571723938,
      "rewards/format_reward": 1.0,
      "step": 1025,
      "temperature": 1.0
    },
    {
      "all_correct": 0.375,
      "all_wrong": 0.0,
      "completion_length": 388.375,
      "epoch": 0.031200583870575355,
      "grad_norm": 3.101474064043986,
      "kl": 0.033203125,
      "learning_rate": 9.97599965692389e-07,
      "loss": 0.0013,
      "reward": 1.8433763980865479,
      "reward_std": 0.11379536986351013,
      "rewards/accuracy_reward": 0.6715012788772583,
      "rewards/format_reward": 1.0,
      "step": 1026,
      "temperature": 1.0
    },
    {
      "all_correct": 0.625,
      "all_wrong": 0.0,
      "completion_length": 381.5,
      "epoch": 0.031230993796375138,
      "grad_norm": 0.7608621621800262,
      "kl": 0.02685546875,
      "learning_rate": 9.975952887385317e-07,
      "loss": 0.0011,
      "reward": 1.8340480327606201,
      "reward_std": 0.1912408322095871,
      "rewards/accuracy_reward": 0.7059230804443359,
      "rewards/format_reward": 0.984375,
      "step": 1027,
      "temperature": 1.0
    },
    {
      "all_correct": 0.75,
      "all_wrong": 0.0,
      "completion_length": 348.328125,
      "epoch": 0.03126140372217492,
      "grad_norm": 1.1145174861487677,
      "kl": 0.033935546875,
      "learning_rate": 9.975906072430969e-07,
      "loss": 0.0014,
      "reward": 2.02040433883667,
      "reward_std": 0.0999375432729721,
      "rewards/accuracy_reward": 0.8391544222831726,
      "rewards/format_reward": 1.0,
      "step": 1028,
      "temperature": 1.0
    },
    {
      "all_correct": 0.75,
      "all_wrong": 0.0,
      "completion_length": 393.625,
      "epoch": 0.031291813647974696,
      "grad_norm": 1.430521498035193,
      "kl": 0.02734375,
      "learning_rate": 9.975859212061274e-07,
      "loss": 0.0011,
      "reward": 2.1035537719726562,
      "reward_std": 0.07151352614164352,
      "rewards/accuracy_reward": 0.9129289388656616,
      "rewards/format_reward": 1.0,
      "step": 1029,
      "temperature": 1.0
    },
    {
      "all_correct": 0.875,
      "all_wrong": 0.0,
      "completion_length": 366.09375,
      "epoch": 0.03132222357377448,
      "grad_norm": 0.9725369091114492,
      "kl": 0.0291748046875,
      "learning_rate": 9.97581230627666e-07,
      "loss": 0.0012,
      "reward": 2.0565624237060547,
      "reward_std": 0.05702798068523407,
      "rewards/accuracy_reward": 0.8846875429153442,
      "rewards/format_reward": 1.0,
      "step": 1030,
      "temperature": 1.0
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.0,
      "completion_length": 379.5625,
      "epoch": 0.03135263349957426,
      "grad_norm": 1.3794703306002054,
      "kl": 0.035888671875,
      "learning_rate": 9.975765355077553e-07,
      "loss": 0.0014,
      "reward": 1.93522047996521,
      "reward_std": 0.13645440340042114,
      "rewards/accuracy_reward": 0.7633453607559204,
      "rewards/format_reward": 1.0,
      "step": 1031,
      "temperature": 1.0
    },
    {
      "all_correct": 0.375,
      "all_wrong": 0.0,
      "completion_length": 373.09375,
      "epoch": 0.03138304342537404,
      "grad_norm": 1.5917229873345842,
      "kl": 0.031005859375,
      "learning_rate": 9.975718358464383e-07,
      "loss": 0.0012,
      "reward": 1.8549714088439941,
      "reward_std": 0.19620639085769653,
      "rewards/accuracy_reward": 0.6862212419509888,
      "rewards/format_reward": 1.0,
      "step": 1032,
      "temperature": 1.0
    },
    {
      "all_correct": 0.625,
      "all_wrong": 0.0,
      "completion_length": 379.421875,
      "epoch": 0.03141345335117382,
      "grad_norm": 1.4726606412692054,
      "kl": 0.031494140625,
      "learning_rate": 9.97567131643758e-07,
      "loss": 0.0013,
      "reward": 1.9913734197616577,
      "reward_std": 0.1471506804227829,
      "rewards/accuracy_reward": 0.8507484197616577,
      "rewards/format_reward": 1.0,
      "step": 1033,
      "temperature": 1.0
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.0,
      "completion_length": 387.484375,
      "epoch": 0.031443863276973606,
      "grad_norm": 1.259856833652236,
      "kl": 0.026123046875,
      "learning_rate": 9.97562422899757e-07,
      "loss": 0.001,
      "reward": 1.8706974983215332,
      "reward_std": 0.1301310956478119,
      "rewards/accuracy_reward": 0.6988223791122437,
      "rewards/format_reward": 1.0,
      "step": 1034,
      "temperature": 1.0
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.0,
      "completion_length": 404.84375,
      "epoch": 0.031474273202773385,
      "grad_norm": 2.2608351361129797,
      "kl": 0.0260009765625,
      "learning_rate": 9.975577096144788e-07,
      "loss": 0.001,
      "reward": 1.7881382703781128,
      "reward_std": 0.15508222579956055,
      "rewards/accuracy_reward": 0.6725132465362549,
      "rewards/format_reward": 1.0,
      "step": 1035,
      "temperature": 1.0
    },
    {
      "all_correct": 0.875,
      "all_wrong": 0.0,
      "completion_length": 371.265625,
      "epoch": 0.031504683128573165,
      "grad_norm": 0.48728254589879094,
      "kl": 0.0322265625,
      "learning_rate": 9.97552991787966e-07,
      "loss": 0.0013,
      "reward": 2.1239399909973145,
      "reward_std": 0.007922534830868244,
      "rewards/accuracy_reward": 0.9239398837089539,
      "rewards/format_reward": 1.0,
      "step": 1036,
      "temperature": 1.0
    },
    {
      "all_correct": 0.125,
      "all_wrong": 0.375,
      "completion_length": 374.421875,
      "epoch": 0.03153509305437295,
      "grad_norm": 1.3629466911378965,
      "kl": 0.02734375,
      "learning_rate": 9.975482694202618e-07,
      "loss": 0.0011,
      "reward": 1.2980787754058838,
      "reward_std": 0.11241129040718079,
      "rewards/accuracy_reward": 0.2137036919593811,
      "rewards/format_reward": 1.0,
      "step": 1037,
      "temperature": 1.0
    },
    {
      "all_correct": 0.25,
      "all_wrong": 0.375,
      "completion_length": 406.625,
      "epoch": 0.03156550298017273,
      "grad_norm": 1.461056211536323,
      "kl": 0.0283203125,
      "learning_rate": 9.975435425114092e-07,
      "loss": 0.0011,
      "reward": 1.4827834367752075,
      "reward_std": 0.10858327895402908,
      "rewards/accuracy_reward": 0.4015333950519562,
      "rewards/format_reward": 1.0,
      "step": 1038,
      "temperature": 1.0
    },
    {
      "all_correct": 0.75,
      "all_wrong": 0.125,
      "completion_length": 397.109375,
      "epoch": 0.03159591290597251,
      "grad_norm": 0.66771279792573,
      "kl": 0.0247802734375,
      "learning_rate": 9.975388110614514e-07,
      "loss": 0.001,
      "reward": 1.9582293033599854,
      "reward_std": 0.004301874432712793,
      "rewards/accuracy_reward": 0.7832292318344116,
      "rewards/format_reward": 1.0,
      "step": 1039,
      "temperature": 1.0
    },
    {
      "all_correct": 0.625,
      "all_wrong": 0.0,
      "completion_length": 389.328125,
      "epoch": 0.03162632283177229,
      "grad_norm": 0.9623246814350269,
      "kl": 0.027587890625,
      "learning_rate": 9.975340750704317e-07,
      "loss": 0.0011,
      "reward": 1.9350848197937012,
      "reward_std": 0.15852871537208557,
      "rewards/accuracy_reward": 0.7663347721099854,
      "rewards/format_reward": 1.0,
      "step": 1040,
      "temperature": 1.0
    },
    {
      "all_correct": 0.625,
      "all_wrong": 0.25,
      "completion_length": 388.734375,
      "epoch": 0.031656732757572074,
      "grad_norm": 0.29921358495941097,
      "kl": 0.032958984375,
      "learning_rate": 9.975293345383933e-07,
      "loss": 0.0013,
      "reward": 1.765625,
      "reward_std": 0.04419417306780815,
      "rewards/accuracy_reward": 0.640625,
      "rewards/format_reward": 1.0,
      "step": 1041,
      "temperature": 1.0
    },
    {
      "all_correct": 0.875,
      "all_wrong": 0.0,
      "completion_length": 383.53125,
      "epoch": 0.031687142683371854,
      "grad_norm": 6.553914097257682,
      "kl": 0.04052734375,
      "learning_rate": 9.975245894653795e-07,
      "loss": 0.0016,
      "reward": 2.112783432006836,
      "reward_std": 0.006405085325241089,
      "rewards/accuracy_reward": 0.912783145904541,
      "rewards/format_reward": 1.0,
      "step": 1042,
      "temperature": 1.0
    },
    {
      "all_correct": 0.625,
      "all_wrong": 0.125,
      "completion_length": 421.921875,
      "epoch": 0.03171755260917163,
      "grad_norm": 0.8658028152057612,
      "kl": 0.029296875,
      "learning_rate": 9.975198398514333e-07,
      "loss": 0.0012,
      "reward": 1.869927167892456,
      "reward_std": 0.12430602312088013,
      "rewards/accuracy_reward": 0.7261770963668823,
      "rewards/format_reward": 0.984375,
      "step": 1043,
      "temperature": 1.0
    },
    {
      "all_correct": 0.75,
      "all_wrong": 0.125,
      "completion_length": 374.65625,
      "epoch": 0.03174796253497141,
      "grad_norm": 1.5865512189991238,
      "kl": 0.0419921875,
      "learning_rate": 9.975150856965984e-07,
      "loss": 0.0017,
      "reward": 1.9823377132415771,
      "reward_std": 0.007232592906802893,
      "rewards/accuracy_reward": 0.8073376417160034,
      "rewards/format_reward": 1.0,
      "step": 1044,
      "temperature": 1.0
    },
    {
      "all_correct": 0.375,
      "all_wrong": 0.125,
      "completion_length": 404.84375,
      "epoch": 0.0317783724607712,
      "grad_norm": 1.33193976633155,
      "kl": 0.029052734375,
      "learning_rate": 9.97510327000918e-07,
      "loss": 0.0012,
      "reward": 1.6656694412231445,
      "reward_std": 0.10279634594917297,
      "rewards/accuracy_reward": 0.5187945365905762,
      "rewards/format_reward": 1.0,
      "step": 1045,
      "temperature": 1.0
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.0,
      "completion_length": 395.328125,
      "epoch": 0.03180878238657098,
      "grad_norm": 1.3035393755697025,
      "kl": 0.0390625,
      "learning_rate": 9.975055637644355e-07,
      "loss": 0.0016,
      "reward": 1.786503791809082,
      "reward_std": 0.111859530210495,
      "rewards/accuracy_reward": 0.6458787322044373,
      "rewards/format_reward": 1.0,
      "step": 1046,
      "temperature": 1.0
    },
    {
      "all_correct": 0.375,
      "all_wrong": 0.125,
      "completion_length": 397.125,
      "epoch": 0.03183919231237076,
      "grad_norm": 1.0076990893591982,
      "kl": 0.033935546875,
      "learning_rate": 9.975007959871947e-07,
      "loss": 0.0014,
      "reward": 1.810640811920166,
      "reward_std": 0.21970966458320618,
      "rewards/accuracy_reward": 0.6637657284736633,
      "rewards/format_reward": 1.0,
      "step": 1047,
      "temperature": 1.0
    },
    {
      "all_correct": 0.375,
      "all_wrong": 0.25,
      "completion_length": 405.453125,
      "epoch": 0.031869602238170536,
      "grad_norm": 1.1632123679178106,
      "kl": 0.03369140625,
      "learning_rate": 9.974960236692387e-07,
      "loss": 0.0013,
      "reward": 1.686184287071228,
      "reward_std": 0.051657333970069885,
      "rewards/accuracy_reward": 0.5424342155456543,
      "rewards/format_reward": 1.0,
      "step": 1048,
      "temperature": 1.0
    },
    {
      "all_correct": 0.625,
      "all_wrong": 0.0,
      "completion_length": 401.875,
      "epoch": 0.03190001216397032,
      "grad_norm": 0.7782241410854358,
      "kl": 0.03857421875,
      "learning_rate": 9.974912468106112e-07,
      "loss": 0.0015,
      "reward": 1.9845863580703735,
      "reward_std": 0.08298208564519882,
      "rewards/accuracy_reward": 0.7939612865447998,
      "rewards/format_reward": 1.0,
      "step": 1049,
      "temperature": 1.0
    },
    {
      "all_correct": 0.875,
      "all_wrong": 0.125,
      "completion_length": 401.765625,
      "epoch": 0.0319304220897701,
      "grad_norm": 0.2278528084097704,
      "kl": 0.04052734375,
      "learning_rate": 9.97486465411356e-07,
      "loss": 0.0016,
      "reward": 2.0031251907348633,
      "reward_std": 0.0646936446428299,
      "rewards/accuracy_reward": 0.875,
      "rewards/format_reward": 0.953125,
      "step": 1050,
      "temperature": 1.0
    },
    {
      "all_correct": 0.625,
      "all_wrong": 0.0,
      "completion_length": 385.921875,
      "epoch": 0.03196083201556988,
      "grad_norm": 1.0086817191493935,
      "kl": 0.03955078125,
      "learning_rate": 9.974816794715165e-07,
      "loss": 0.0016,
      "reward": 2.0194334983825684,
      "reward_std": 0.06533440947532654,
      "rewards/accuracy_reward": 0.8256836533546448,
      "rewards/format_reward": 1.0,
      "step": 1051,
      "temperature": 1.0
    },
    {
      "all_correct": 0.75,
      "all_wrong": 0.0,
      "completion_length": 386.625,
      "epoch": 0.031991241941369666,
      "grad_norm": 0.5998748827167423,
      "kl": 0.03466796875,
      "learning_rate": 9.974768889911365e-07,
      "loss": 0.0014,
      "reward": 2.1642045974731445,
      "reward_std": 0.061623118817806244,
      "rewards/accuracy_reward": 0.9673295021057129,
      "rewards/format_reward": 1.0,
      "step": 1052,
      "temperature": 1.0
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.0,
      "completion_length": 381.234375,
      "epoch": 0.032021651867169446,
      "grad_norm": 1.1801284648311607,
      "kl": 0.04052734375,
      "learning_rate": 9.974720939702596e-07,
      "loss": 0.0016,
      "reward": 1.8989980220794678,
      "reward_std": 0.12210077047348022,
      "rewards/accuracy_reward": 0.7208729982376099,
      "rewards/format_reward": 1.0,
      "step": 1053,
      "temperature": 1.0
    },
    {
      "all_correct": 0.375,
      "all_wrong": 0.125,
      "completion_length": 375.828125,
      "epoch": 0.032052061792969225,
      "grad_norm": 3.0655197929301248,
      "kl": 0.0361328125,
      "learning_rate": 9.974672944089296e-07,
      "loss": 0.0014,
      "reward": 1.7496037483215332,
      "reward_std": 0.16746900975704193,
      "rewards/accuracy_reward": 0.6214788556098938,
      "rewards/format_reward": 1.0,
      "step": 1054,
      "temperature": 1.0
    },
    {
      "all_correct": 0.625,
      "all_wrong": 0.25,
      "completion_length": 365.484375,
      "epoch": 0.032082471718769004,
      "grad_norm": 0.7612209929918888,
      "kl": 0.034423828125,
      "learning_rate": 9.974624903071903e-07,
      "loss": 0.0014,
      "reward": 1.8343307971954346,
      "reward_std": 0.013469927944242954,
      "rewards/accuracy_reward": 0.6843306422233582,
      "rewards/format_reward": 1.0,
      "step": 1055,
      "temperature": 1.0
    },
    {
      "all_correct": 0.25,
      "all_wrong": 0.125,
      "completion_length": 399.65625,
      "epoch": 0.03211288164456879,
      "grad_norm": 1.6204578480917131,
      "kl": 0.03271484375,
      "learning_rate": 9.97457681665086e-07,
      "loss": 0.0013,
      "reward": 1.718801736831665,
      "reward_std": 0.21143373847007751,
      "rewards/accuracy_reward": 0.6063016653060913,
      "rewards/format_reward": 1.0,
      "step": 1056,
      "temperature": 1.0
    },
    {
      "all_correct": 0.375,
      "all_wrong": 0.0,
      "completion_length": 392.265625,
      "epoch": 0.03214329157036857,
      "grad_norm": 1.722078742051551,
      "kl": 0.031494140625,
      "learning_rate": 9.974528684826598e-07,
      "loss": 0.0013,
      "reward": 1.7573037147521973,
      "reward_std": 0.18160060048103333,
      "rewards/accuracy_reward": 0.6073037385940552,
      "rewards/format_reward": 0.984375,
      "step": 1057,
      "temperature": 1.0
    },
    {
      "all_correct": 0.625,
      "all_wrong": 0.125,
      "completion_length": 375.984375,
      "epoch": 0.03217370149616835,
      "grad_norm": 1.2005784098615955,
      "kl": 0.031494140625,
      "learning_rate": 9.97448050759956e-07,
      "loss": 0.0013,
      "reward": 1.8566406965255737,
      "reward_std": 0.08184340596199036,
      "rewards/accuracy_reward": 0.7035156488418579,
      "rewards/format_reward": 1.0,
      "step": 1058,
      "temperature": 1.0
    },
    {
      "all_correct": 0.75,
      "all_wrong": 0.0,
      "completion_length": 348.078125,
      "epoch": 0.03220411142196813,
      "grad_norm": 1.1694386500197025,
      "kl": 0.034423828125,
      "learning_rate": 9.97443228497019e-07,
      "loss": 0.0014,
      "reward": 2.0843751430511475,
      "reward_std": 0.1595131754875183,
      "rewards/accuracy_reward": 0.921875,
      "rewards/format_reward": 1.0,
      "step": 1059,
      "temperature": 1.0
    },
    {
      "all_correct": 0.625,
      "all_wrong": 0.25,
      "completion_length": 367.21875,
      "epoch": 0.032234521347767914,
      "grad_norm": 1.5085682650996186,
      "kl": 0.0341796875,
      "learning_rate": 9.97438401693892e-07,
      "loss": 0.0014,
      "reward": 1.805967926979065,
      "reward_std": 0.043219514191150665,
      "rewards/accuracy_reward": 0.6715928912162781,
      "rewards/format_reward": 1.0,
      "step": 1060,
      "temperature": 1.0
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.0,
      "completion_length": 391.4375,
      "epoch": 0.03226493127356769,
      "grad_norm": 1.2843785197775819,
      "kl": 0.0296630859375,
      "learning_rate": 9.974335703506195e-07,
      "loss": 0.0012,
      "reward": 1.9324777126312256,
      "reward_std": 0.1777973622083664,
      "rewards/accuracy_reward": 0.7762277126312256,
      "rewards/format_reward": 1.0,
      "step": 1061,
      "temperature": 1.0
    },
    {
      "all_correct": 0.875,
      "all_wrong": 0.125,
      "completion_length": 353.578125,
      "epoch": 0.03229534119936747,
      "grad_norm": 0.9274474149210893,
      "kl": 0.0286865234375,
      "learning_rate": 9.974287344672458e-07,
      "loss": 0.0011,
      "reward": 2.0343751907348633,
      "reward_std": 0.030616413801908493,
      "rewards/accuracy_reward": 0.875,
      "rewards/format_reward": 1.0,
      "step": 1062,
      "temperature": 1.0
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.0,
      "completion_length": 358.453125,
      "epoch": 0.03232575112516725,
      "grad_norm": 4.099988383137438,
      "kl": 0.031494140625,
      "learning_rate": 9.974238940438145e-07,
      "loss": 0.0013,
      "reward": 1.8780081272125244,
      "reward_std": 0.2630694806575775,
      "rewards/accuracy_reward": 0.7248830795288086,
      "rewards/format_reward": 1.0,
      "step": 1063,
      "temperature": 1.0
    },
    {
      "all_correct": 0.625,
      "all_wrong": 0.125,
      "completion_length": 348.640625,
      "epoch": 0.03235616105096704,
      "grad_norm": 2.4818476415134567,
      "kl": 0.03662109375,
      "learning_rate": 9.974190490803702e-07,
      "loss": 0.0015,
      "reward": 1.8492457866668701,
      "reward_std": 0.11250324547290802,
      "rewards/accuracy_reward": 0.7117456793785095,
      "rewards/format_reward": 1.0,
      "step": 1064,
      "temperature": 1.0
    },
    {
      "all_correct": 0.375,
      "all_wrong": 0.25,
      "completion_length": 365.6875,
      "epoch": 0.03238657097676682,
      "grad_norm": 0.8569010092934155,
      "kl": 0.03271484375,
      "learning_rate": 9.97414199576957e-07,
      "loss": 0.0013,
      "reward": 1.609375,
      "reward_std": 0.14089259505271912,
      "rewards/accuracy_reward": 0.515625,
      "rewards/format_reward": 1.0,
      "step": 1065,
      "temperature": 1.0
    },
    {
      "all_correct": 0.25,
      "all_wrong": 0.125,
      "completion_length": 383.125,
      "epoch": 0.032416980902566596,
      "grad_norm": 2.2040386956667173,
      "kl": 0.03515625,
      "learning_rate": 9.974093455336192e-07,
      "loss": 0.0014,
      "reward": 1.6146278381347656,
      "reward_std": 0.19844332337379456,
      "rewards/accuracy_reward": 0.48650285601615906,
      "rewards/format_reward": 1.0,
      "step": 1066,
      "temperature": 1.0
    },
    {
      "all_correct": 0.75,
      "all_wrong": 0.125,
      "completion_length": 361.375,
      "epoch": 0.03244739082836638,
      "grad_norm": 0.7779248216512246,
      "kl": 0.036376953125,
      "learning_rate": 9.97404486950401e-07,
      "loss": 0.0015,
      "reward": 1.9718750715255737,
      "reward_std": 0.08901721239089966,
      "rewards/accuracy_reward": 0.8125,
      "rewards/format_reward": 1.0,
      "step": 1067,
      "temperature": 1.0
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.0,
      "completion_length": 419.234375,
      "epoch": 0.03247780075416616,
      "grad_norm": 1.3818472136952866,
      "kl": 0.026123046875,
      "learning_rate": 9.973996238273468e-07,
      "loss": 0.001,
      "reward": 1.8044815063476562,
      "reward_std": 0.11264000087976456,
      "rewards/accuracy_reward": 0.6576066017150879,
      "rewards/format_reward": 1.0,
      "step": 1068,
      "temperature": 1.0
    },
    {
      "all_correct": 0.375,
      "all_wrong": 0.125,
      "completion_length": 374.734375,
      "epoch": 0.03250821067996594,
      "grad_norm": 1.4298278780276268,
      "kl": 0.0341796875,
      "learning_rate": 9.973947561645008e-07,
      "loss": 0.0014,
      "reward": 1.896875023841858,
      "reward_std": 0.2362026572227478,
      "rewards/accuracy_reward": 0.75,
      "rewards/format_reward": 1.0,
      "step": 1069,
      "temperature": 1.0
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.25,
      "completion_length": 396.3125,
      "epoch": 0.03253862060576572,
      "grad_norm": 0.6803816360331187,
      "kl": 0.0281982421875,
      "learning_rate": 9.97389883961908e-07,
      "loss": 0.0011,
      "reward": 1.7533247470855713,
      "reward_std": 0.08520626276731491,
      "rewards/accuracy_reward": 0.6158246994018555,
      "rewards/format_reward": 1.0,
      "step": 1070,
      "temperature": 1.0
    },
    {
      "all_correct": 0.875,
      "all_wrong": 0.0,
      "completion_length": 391.5,
      "epoch": 0.032569030531565506,
      "grad_norm": 1.050297100744761,
      "kl": 0.033447265625,
      "learning_rate": 9.973850072196122e-07,
      "loss": 0.0013,
      "reward": 2.0400681495666504,
      "reward_std": 0.013605024665594101,
      "rewards/accuracy_reward": 0.8838181495666504,
      "rewards/format_reward": 1.0,
      "step": 1071,
      "temperature": 1.0
    },
    {
      "all_correct": 0.625,
      "all_wrong": 0.125,
      "completion_length": 378.859375,
      "epoch": 0.032599440457365285,
      "grad_norm": 0.8194215031196004,
      "kl": 0.037841796875,
      "learning_rate": 9.973801259376583e-07,
      "loss": 0.0015,
      "reward": 1.8406963348388672,
      "reward_std": 0.05681546777486801,
      "rewards/accuracy_reward": 0.696946382522583,
      "rewards/format_reward": 1.0,
      "step": 1072,
      "temperature": 1.0
    },
    {
      "all_correct": 0.625,
      "all_wrong": 0.125,
      "completion_length": 407.265625,
      "epoch": 0.032629850383165064,
      "grad_norm": 0.5931019624130202,
      "kl": 0.037109375,
      "learning_rate": 9.973752401160905e-07,
      "loss": 0.0015,
      "reward": 1.8343359231948853,
      "reward_std": 0.052666086703538895,
      "rewards/accuracy_reward": 0.6874608993530273,
      "rewards/format_reward": 1.0,
      "step": 1073,
      "temperature": 1.0
    },
    {
      "all_correct": 0.75,
      "all_wrong": 0.125,
      "completion_length": 371.75,
      "epoch": 0.03266026030896484,
      "grad_norm": 0.5850531213485309,
      "kl": 0.037353515625,
      "learning_rate": 9.97370349754954e-07,
      "loss": 0.0015,
      "reward": 1.970604419708252,
      "reward_std": 0.006674332078546286,
      "rewards/accuracy_reward": 0.7956044673919678,
      "rewards/format_reward": 1.0,
      "step": 1074,
      "temperature": 1.0
    },
    {
      "all_correct": 0.375,
      "all_wrong": 0.0,
      "completion_length": 400.5,
      "epoch": 0.03269067023476463,
      "grad_norm": 1.110155660909042,
      "kl": 0.0247802734375,
      "learning_rate": 9.973654548542927e-07,
      "loss": 0.001,
      "reward": 1.8497488498687744,
      "reward_std": 0.19115684926509857,
      "rewards/accuracy_reward": 0.6747488379478455,
      "rewards/format_reward": 1.0,
      "step": 1075,
      "temperature": 1.0
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.125,
      "completion_length": 365.15625,
      "epoch": 0.03272108016056441,
      "grad_norm": 1.0284487521612546,
      "kl": 0.031494140625,
      "learning_rate": 9.97360555414152e-07,
      "loss": 0.0013,
      "reward": 1.8062500953674316,
      "reward_std": 0.19190602004528046,
      "rewards/accuracy_reward": 0.671875,
      "rewards/format_reward": 1.0,
      "step": 1076,
      "temperature": 1.0
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.0,
      "completion_length": 369.734375,
      "epoch": 0.03275149008636419,
      "grad_norm": 1.9472521362140927,
      "kl": 0.03759765625,
      "learning_rate": 9.973556514345761e-07,
      "loss": 0.0015,
      "reward": 1.9555892944335938,
      "reward_std": 0.07708688080310822,
      "rewards/accuracy_reward": 0.7587141990661621,
      "rewards/format_reward": 1.0,
      "step": 1077,
      "temperature": 1.0
    },
    {
      "all_correct": 0.25,
      "all_wrong": 0.125,
      "completion_length": 387.1875,
      "epoch": 0.03278190001216397,
      "grad_norm": 1.3884403244974035,
      "kl": 0.0274658203125,
      "learning_rate": 9.973507429156098e-07,
      "loss": 0.0011,
      "reward": 1.819960355758667,
      "reward_std": 0.21372120082378387,
      "rewards/accuracy_reward": 0.663710355758667,
      "rewards/format_reward": 1.0,
      "step": 1078,
      "temperature": 1.0
    },
    {
      "all_correct": 0.375,
      "all_wrong": 0.375,
      "completion_length": 390.0625,
      "epoch": 0.03281230993796375,
      "grad_norm": 0.8200422254215559,
      "kl": 0.03173828125,
      "learning_rate": 9.973458298572982e-07,
      "loss": 0.0013,
      "reward": 1.631159782409668,
      "reward_std": 0.08605692535638809,
      "rewards/accuracy_reward": 0.5155346393585205,
      "rewards/format_reward": 1.0,
      "step": 1079,
      "temperature": 1.0
    },
    {
      "all_correct": 0.75,
      "all_wrong": 0.125,
      "completion_length": 365.890625,
      "epoch": 0.03284271986376353,
      "grad_norm": 0.8075935578414538,
      "kl": 0.0341796875,
      "learning_rate": 9.973409122596858e-07,
      "loss": 0.0014,
      "reward": 2.0218749046325684,
      "reward_std": 0.07018192857503891,
      "rewards/accuracy_reward": 0.859375,
      "rewards/format_reward": 1.0,
      "step": 1080,
      "temperature": 1.0
    },
    {
      "all_correct": 0.25,
      "all_wrong": 0.25,
      "completion_length": 414.28125,
      "epoch": 0.03287312978956331,
      "grad_norm": 2.164588831509964,
      "kl": 0.0264892578125,
      "learning_rate": 9.97335990122818e-07,
      "loss": 0.0011,
      "reward": 1.4646395444869995,
      "reward_std": 0.1339268684387207,
      "rewards/accuracy_reward": 0.38338956236839294,
      "rewards/format_reward": 0.984375,
      "step": 1081,
      "temperature": 1.0
    },
    {
      "all_correct": 0.625,
      "all_wrong": 0.125,
      "completion_length": 370.96875,
      "epoch": 0.0329035397153631,
      "grad_norm": 0.5506757118454917,
      "kl": 0.03369140625,
      "learning_rate": 9.97331063446739e-07,
      "loss": 0.0013,
      "reward": 1.9762752056121826,
      "reward_std": 0.024736447259783745,
      "rewards/accuracy_reward": 0.8012750148773193,
      "rewards/format_reward": 1.0,
      "step": 1082,
      "temperature": 1.0
    },
    {
      "all_correct": 0.375,
      "all_wrong": 0.125,
      "completion_length": 385.546875,
      "epoch": 0.03293394964116288,
      "grad_norm": 1.4689588116782917,
      "kl": 0.0308837890625,
      "learning_rate": 9.973261322314942e-07,
      "loss": 0.0012,
      "reward": 1.714081048965454,
      "reward_std": 0.05578683689236641,
      "rewards/accuracy_reward": 0.5484559535980225,
      "rewards/format_reward": 1.0,
      "step": 1083,
      "temperature": 1.0
    },
    {
      "all_correct": 0.375,
      "all_wrong": 0.375,
      "completion_length": 386.59375,
      "epoch": 0.032964359566962656,
      "grad_norm": 0.7729783315586961,
      "kl": 0.0301513671875,
      "learning_rate": 9.973211964771286e-07,
      "loss": 0.0012,
      "reward": 1.6049872636795044,
      "reward_std": 0.07922689616680145,
      "rewards/accuracy_reward": 0.495612233877182,
      "rewards/format_reward": 1.0,
      "step": 1084,
      "temperature": 1.0
    },
    {
      "all_correct": 0.75,
      "all_wrong": 0.25,
      "completion_length": 364.09375,
      "epoch": 0.032994769492762435,
      "grad_norm": 0.08579283258951795,
      "kl": 0.03271484375,
      "learning_rate": 9.973162561836872e-07,
      "loss": 0.0013,
      "reward": 1.9000000953674316,
      "reward_std": 0.0,
      "rewards/accuracy_reward": 0.75,
      "rewards/format_reward": 1.0,
      "step": 1085,
      "temperature": 1.0
    },
    {
      "all_correct": 0.75,
      "all_wrong": 0.25,
      "completion_length": 360.4375,
      "epoch": 0.03302517941856222,
      "grad_norm": 0.46954585572884366,
      "kl": 0.0341796875,
      "learning_rate": 9.973113113512152e-07,
      "loss": 0.0014,
      "reward": 1.896875023841858,
      "reward_std": 0.008838837966322899,
      "rewards/accuracy_reward": 0.75,
      "rewards/format_reward": 1.0,
      "step": 1086,
      "temperature": 1.0
    },
    {
      "all_correct": 0.25,
      "all_wrong": 0.25,
      "completion_length": 389.40625,
      "epoch": 0.033055589344362,
      "grad_norm": 1.7091455195897645,
      "kl": 0.0267333984375,
      "learning_rate": 9.973063619797576e-07,
      "loss": 0.0011,
      "reward": 1.5719795227050781,
      "reward_std": 0.13767774403095245,
      "rewards/accuracy_reward": 0.4501045346260071,
      "rewards/format_reward": 1.0,
      "step": 1087,
      "temperature": 1.0
    },
    {
      "all_correct": 0.375,
      "all_wrong": 0.125,
      "completion_length": 398.09375,
      "epoch": 0.03308599927016178,
      "grad_norm": 1.0289699015560325,
      "kl": 0.025390625,
      "learning_rate": 9.973014080693593e-07,
      "loss": 0.001,
      "reward": 1.8027890920639038,
      "reward_std": 0.12817265093326569,
      "rewards/accuracy_reward": 0.6559140086174011,
      "rewards/format_reward": 1.0,
      "step": 1088,
      "temperature": 1.0
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.0,
      "completion_length": 395.015625,
      "epoch": 0.03311640919596156,
      "grad_norm": 1.5449118187480184,
      "kl": 0.032470703125,
      "learning_rate": 9.972964496200661e-07,
      "loss": 0.0013,
      "reward": 1.8438479900360107,
      "reward_std": 0.09966101497411728,
      "rewards/accuracy_reward": 0.6594729423522949,
      "rewards/format_reward": 1.0,
      "step": 1089,
      "temperature": 1.0
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.375,
      "completion_length": 363.921875,
      "epoch": 0.033146819121761345,
      "grad_norm": 0.7394582997275666,
      "kl": 0.032470703125,
      "learning_rate": 9.972914866319228e-07,
      "loss": 0.0013,
      "reward": 1.6560384035110474,
      "reward_std": 0.013002442196011543,
      "rewards/accuracy_reward": 0.5341634750366211,
      "rewards/format_reward": 1.0,
      "step": 1090,
      "temperature": 1.0
    },
    {
      "all_correct": 0.125,
      "all_wrong": 0.375,
      "completion_length": 387.796875,
      "epoch": 0.033177229047561124,
      "grad_norm": 5.706732301032811,
      "kl": 0.0361328125,
      "learning_rate": 9.97286519104975e-07,
      "loss": 0.0014,
      "reward": 1.5088940858840942,
      "reward_std": 0.16414456069469452,
      "rewards/accuracy_reward": 0.40264415740966797,
      "rewards/format_reward": 1.0,
      "step": 1091,
      "temperature": 1.0
    },
    {
      "all_correct": 0.625,
      "all_wrong": 0.125,
      "completion_length": 389.453125,
      "epoch": 0.0332076389733609,
      "grad_norm": 0.7165977625533464,
      "kl": 0.0301513671875,
      "learning_rate": 9.972815470392679e-07,
      "loss": 0.0012,
      "reward": 1.870192289352417,
      "reward_std": 0.08161399513483047,
      "rewards/accuracy_reward": 0.729567289352417,
      "rewards/format_reward": 1.0,
      "step": 1092,
      "temperature": 1.0
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.0,
      "completion_length": 391.5625,
      "epoch": 0.03323804889916068,
      "grad_norm": 0.9248391407503694,
      "kl": 0.03076171875,
      "learning_rate": 9.972765704348467e-07,
      "loss": 0.0012,
      "reward": 1.8346686363220215,
      "reward_std": 0.16912472248077393,
      "rewards/accuracy_reward": 0.6784186363220215,
      "rewards/format_reward": 1.0,
      "step": 1093,
      "temperature": 1.0
    },
    {
      "all_correct": 0.375,
      "all_wrong": 0.25,
      "completion_length": 364.015625,
      "epoch": 0.03326845882496047,
      "grad_norm": 0.974307748350617,
      "kl": 0.03466796875,
      "learning_rate": 9.972715892917572e-07,
      "loss": 0.0014,
      "reward": 1.7006316184997559,
      "reward_std": 0.13532617688179016,
      "rewards/accuracy_reward": 0.5662564635276794,
      "rewards/format_reward": 1.0,
      "step": 1094,
      "temperature": 1.0
    },
    {
      "all_correct": 0.625,
      "all_wrong": 0.25,
      "completion_length": 349.9375,
      "epoch": 0.03329886875076025,
      "grad_norm": 0.8915227577354273,
      "kl": 0.03271484375,
      "learning_rate": 9.972666036100444e-07,
      "loss": 0.0013,
      "reward": 1.7798829078674316,
      "reward_std": 0.02489185519516468,
      "rewards/accuracy_reward": 0.6455078125,
      "rewards/format_reward": 1.0,
      "step": 1095,
      "temperature": 1.0
    },
    {
      "all_correct": 0.625,
      "all_wrong": 0.25,
      "completion_length": 379.859375,
      "epoch": 0.03332927867656003,
      "grad_norm": 0.48060170225431265,
      "kl": 0.0262451171875,
      "learning_rate": 9.972616133897543e-07,
      "loss": 0.0011,
      "reward": 1.8218750953674316,
      "reward_std": 0.08901721239089966,
      "rewards/accuracy_reward": 0.6875,
      "rewards/format_reward": 1.0,
      "step": 1096,
      "temperature": 1.0
    },
    {
      "all_correct": 0.375,
      "all_wrong": 0.25,
      "completion_length": 395.0,
      "epoch": 0.03335968860235981,
      "grad_norm": 1.2592743953890917,
      "kl": 0.030517578125,
      "learning_rate": 9.972566186309321e-07,
      "loss": 0.0012,
      "reward": 1.6198643445968628,
      "reward_std": 0.10171298682689667,
      "rewards/accuracy_reward": 0.494864284992218,
      "rewards/format_reward": 1.0,
      "step": 1097,
      "temperature": 1.0
    },
    {
      "all_correct": 0.625,
      "all_wrong": 0.125,
      "completion_length": 388.71875,
      "epoch": 0.03339009852815959,
      "grad_norm": 0.6234882876885078,
      "kl": 0.0301513671875,
      "learning_rate": 9.972516193336235e-07,
      "loss": 0.0012,
      "reward": 1.9183714389801025,
      "reward_std": 0.08268841356039047,
      "rewards/accuracy_reward": 0.7683714628219604,
      "rewards/format_reward": 1.0,
      "step": 1098,
      "temperature": 1.0
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.125,
      "completion_length": 378.6875,
      "epoch": 0.03342050845395937,
      "grad_norm": 1.1879629268265015,
      "kl": 0.0308837890625,
      "learning_rate": 9.972466154978743e-07,
      "loss": 0.0012,
      "reward": 1.8996248245239258,
      "reward_std": 0.1979600489139557,
      "rewards/accuracy_reward": 0.758999764919281,
      "rewards/format_reward": 1.0,
      "step": 1099,
      "temperature": 1.0
    },
    {
      "all_correct": 0.75,
      "all_wrong": 0.0,
      "completion_length": 372.125,
      "epoch": 0.03345091837975915,
      "grad_norm": 0.6969750381163629,
      "kl": 0.030517578125,
      "learning_rate": 9.972416071237297e-07,
      "loss": 0.0012,
      "reward": 1.9986071586608887,
      "reward_std": 0.05326046049594879,
      "rewards/accuracy_reward": 0.8111070394515991,
      "rewards/format_reward": 1.0,
      "step": 1100,
      "temperature": 1.0
    },
    {
      "all_correct": 0.75,
      "all_wrong": 0.125,
      "completion_length": 355.21875,
      "epoch": 0.03348132830555894,
      "grad_norm": 1.1670169454417925,
      "kl": 0.036376953125,
      "learning_rate": 9.97236594211236e-07,
      "loss": 0.0015,
      "reward": 1.9805370569229126,
      "reward_std": 0.047131411731243134,
      "rewards/accuracy_reward": 0.8117871284484863,
      "rewards/format_reward": 1.0,
      "step": 1101,
      "temperature": 1.0
    },
    {
      "all_correct": 0.25,
      "all_wrong": 0.25,
      "completion_length": 393.71875,
      "epoch": 0.033511738231358716,
      "grad_norm": 1.1557842585686968,
      "kl": 0.029296875,
      "learning_rate": 9.972315767604384e-07,
      "loss": 0.0012,
      "reward": 1.475762963294983,
      "reward_std": 0.18541356921195984,
      "rewards/accuracy_reward": 0.391387939453125,
      "rewards/format_reward": 1.0,
      "step": 1102,
      "temperature": 1.0
    },
    {
      "all_correct": 0.375,
      "all_wrong": 0.125,
      "completion_length": 398.5625,
      "epoch": 0.033542148157158495,
      "grad_norm": 1.6982091192995499,
      "kl": 0.028564453125,
      "learning_rate": 9.97226554771383e-07,
      "loss": 0.0011,
      "reward": 1.6949204206466675,
      "reward_std": 0.1318046748638153,
      "rewards/accuracy_reward": 0.5542953610420227,
      "rewards/format_reward": 1.0,
      "step": 1103,
      "temperature": 1.0
    },
    {
      "all_correct": 0.625,
      "all_wrong": 0.25,
      "completion_length": 387.984375,
      "epoch": 0.033572558082958275,
      "grad_norm": 0.712282533668454,
      "kl": 0.03173828125,
      "learning_rate": 9.972215282441159e-07,
      "loss": 0.0013,
      "reward": 1.7991609573364258,
      "reward_std": 0.016065146774053574,
      "rewards/accuracy_reward": 0.6522858738899231,
      "rewards/format_reward": 1.0,
      "step": 1104,
      "temperature": 1.0
    },
    {
      "all_correct": 0.375,
      "all_wrong": 0.25,
      "completion_length": 394.421875,
      "epoch": 0.03360296800875806,
      "grad_norm": 1.136228153510139,
      "kl": 0.0303955078125,
      "learning_rate": 9.972164971786824e-07,
      "loss": 0.0012,
      "reward": 1.6297039985656738,
      "reward_std": 0.01870308443903923,
      "rewards/accuracy_reward": 0.5047040581703186,
      "rewards/format_reward": 1.0,
      "step": 1105,
      "temperature": 1.0
    },
    {
      "all_correct": 0.375,
      "all_wrong": 0.25,
      "completion_length": 409.9375,
      "epoch": 0.03363337793455784,
      "grad_norm": 0.7446650634925455,
      "kl": 0.0255126953125,
      "learning_rate": 9.972114615751287e-07,
      "loss": 0.001,
      "reward": 1.7607765197753906,
      "reward_std": 0.1566496044397354,
      "rewards/accuracy_reward": 0.6357765197753906,
      "rewards/format_reward": 0.984375,
      "step": 1106,
      "temperature": 1.0
    },
    {
      "all_correct": 0.625,
      "all_wrong": 0.125,
      "completion_length": 380.375,
      "epoch": 0.03366378786035762,
      "grad_norm": 0.9641752956345843,
      "kl": 0.031494140625,
      "learning_rate": 9.97206421433501e-07,
      "loss": 0.0013,
      "reward": 1.8046131134033203,
      "reward_std": 0.08519918471574783,
      "rewards/accuracy_reward": 0.6733629703521729,
      "rewards/format_reward": 0.984375,
      "step": 1107,
      "temperature": 1.0
    },
    {
      "all_correct": 0.625,
      "all_wrong": 0.125,
      "completion_length": 378.15625,
      "epoch": 0.033694197786157405,
      "grad_norm": 0.7673943013304966,
      "kl": 0.02978515625,
      "learning_rate": 9.972013767538448e-07,
      "loss": 0.0012,
      "reward": 1.8758015632629395,
      "reward_std": 0.08757517486810684,
      "rewards/accuracy_reward": 0.7226765155792236,
      "rewards/format_reward": 1.0,
      "step": 1108,
      "temperature": 1.0
    },
    {
      "all_correct": 0.375,
      "all_wrong": 0.125,
      "completion_length": 376.984375,
      "epoch": 0.033724607711957184,
      "grad_norm": 0.963322040028811,
      "kl": 0.0286865234375,
      "learning_rate": 9.971963275362062e-07,
      "loss": 0.0011,
      "reward": 1.5670509338378906,
      "reward_std": 0.13995975255966187,
      "rewards/accuracy_reward": 0.4545508623123169,
      "rewards/format_reward": 1.0,
      "step": 1109,
      "temperature": 1.0
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.0,
      "completion_length": 385.453125,
      "epoch": 0.033755017637756964,
      "grad_norm": 2.672311078318137,
      "kl": 0.0306396484375,
      "learning_rate": 9.971912737806319e-07,
      "loss": 0.0012,
      "reward": 1.9038267135620117,
      "reward_std": 0.1121816486120224,
      "rewards/accuracy_reward": 0.7350767850875854,
      "rewards/format_reward": 1.0,
      "step": 1110,
      "temperature": 1.0
    },
    {
      "all_correct": 0.375,
      "all_wrong": 0.25,
      "completion_length": 363.453125,
      "epoch": 0.03378542756355674,
      "grad_norm": 1.2558479431204714,
      "kl": 0.03271484375,
      "learning_rate": 9.971862154871674e-07,
      "loss": 0.0013,
      "reward": 1.658834457397461,
      "reward_std": 0.060252152383327484,
      "rewards/accuracy_reward": 0.527584433555603,
      "rewards/format_reward": 1.0,
      "step": 1111,
      "temperature": 1.0
    },
    {
      "all_correct": 0.25,
      "all_wrong": 0.125,
      "completion_length": 378.34375,
      "epoch": 0.03381583748935653,
      "grad_norm": 1.1270021494138065,
      "kl": 0.026611328125,
      "learning_rate": 9.97181152655859e-07,
      "loss": 0.0011,
      "reward": 1.5101438760757446,
      "reward_std": 0.25951337814331055,
      "rewards/accuracy_reward": 0.4351438581943512,
      "rewards/format_reward": 0.984375,
      "step": 1112,
      "temperature": 1.0
    },
    {
      "all_correct": 0.25,
      "all_wrong": 0.125,
      "completion_length": 387.75,
      "epoch": 0.03384624741515631,
      "grad_norm": 1.2117361639038522,
      "kl": 0.0291748046875,
      "learning_rate": 9.971760852867532e-07,
      "loss": 0.0012,
      "reward": 1.5003330707550049,
      "reward_std": 0.20664426684379578,
      "rewards/accuracy_reward": 0.412833034992218,
      "rewards/format_reward": 1.0,
      "step": 1113,
      "temperature": 1.0
    },
    {
      "all_correct": 0.375,
      "all_wrong": 0.125,
      "completion_length": 396.265625,
      "epoch": 0.03387665734095609,
      "grad_norm": 1.1755606365907483,
      "kl": 0.02392578125,
      "learning_rate": 9.97171013379896e-07,
      "loss": 0.001,
      "reward": 1.7332415580749512,
      "reward_std": 0.08857608586549759,
      "rewards/accuracy_reward": 0.5894915461540222,
      "rewards/format_reward": 1.0,
      "step": 1114,
      "temperature": 1.0
    },
    {
      "all_correct": 0.375,
      "all_wrong": 0.375,
      "completion_length": 374.640625,
      "epoch": 0.033907067266755866,
      "grad_norm": 0.9210505530670403,
      "kl": 0.0296630859375,
      "learning_rate": 9.971659369353336e-07,
      "loss": 0.0012,
      "reward": 1.5143427848815918,
      "reward_std": 0.05233721062541008,
      "rewards/accuracy_reward": 0.4205928146839142,
      "rewards/format_reward": 1.0,
      "step": 1115,
      "temperature": 1.0
    },
    {
      "all_correct": 0.25,
      "all_wrong": 0.625,
      "completion_length": 354.625,
      "epoch": 0.03393747719255565,
      "grad_norm": 0.611951872528932,
      "kl": 0.030517578125,
      "learning_rate": 9.971608559531125e-07,
      "loss": 0.0012,
      "reward": 1.375,
      "reward_std": 0.08017838001251221,
      "rewards/accuracy_reward": 0.3125,
      "rewards/format_reward": 1.0,
      "step": 1116,
      "temperature": 1.0
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.125,
      "completion_length": 371.171875,
      "epoch": 0.03396788711835543,
      "grad_norm": 1.3663988661679252,
      "kl": 0.033203125,
      "learning_rate": 9.97155770433279e-07,
      "loss": 0.0013,
      "reward": 1.788399338722229,
      "reward_std": 0.15740957856178284,
      "rewards/accuracy_reward": 0.6602743268013,
      "rewards/format_reward": 1.0,
      "step": 1117,
      "temperature": 1.0
    },
    {
      "all_correct": 0.625,
      "all_wrong": 0.25,
      "completion_length": 417.25,
      "epoch": 0.03399829704415521,
      "grad_norm": 2.9571042805531276,
      "kl": 0.029296875,
      "learning_rate": 9.971506803758795e-07,
      "loss": 0.0012,
      "reward": 1.8625000715255737,
      "reward_std": 0.08448860794305801,
      "rewards/accuracy_reward": 0.734375,
      "rewards/format_reward": 1.0,
      "step": 1118,
      "temperature": 1.0
    },
    {
      "all_correct": 0.75,
      "all_wrong": 0.125,
      "completion_length": 375.453125,
      "epoch": 0.03402870696995499,
      "grad_norm": 1.6445221111201525,
      "kl": 0.02783203125,
      "learning_rate": 9.971455857809606e-07,
      "loss": 0.0011,
      "reward": 1.9543342590332031,
      "reward_std": 0.05220496654510498,
      "rewards/accuracy_reward": 0.8043341040611267,
      "rewards/format_reward": 1.0,
      "step": 1119,
      "temperature": 1.0
    },
    {
      "all_correct": 0.125,
      "all_wrong": 0.125,
      "completion_length": 395.453125,
      "epoch": 0.034059116895754776,
      "grad_norm": 1.4751750111053377,
      "kl": 0.0257568359375,
      "learning_rate": 9.971404866485687e-07,
      "loss": 0.001,
      "reward": 1.582068920135498,
      "reward_std": 0.29019424319267273,
      "rewards/accuracy_reward": 0.4851939082145691,
      "rewards/format_reward": 1.0,
      "step": 1120,
      "temperature": 1.0
    },
    {
      "all_correct": 0.75,
      "all_wrong": 0.125,
      "completion_length": 358.0625,
      "epoch": 0.034089526821554555,
      "grad_norm": 1.0335957607718362,
      "kl": 0.0272216796875,
      "learning_rate": 9.971353829787504e-07,
      "loss": 0.0011,
      "reward": 1.9825429916381836,
      "reward_std": 0.015851331874728203,
      "rewards/accuracy_reward": 0.810667872428894,
      "rewards/format_reward": 1.0,
      "step": 1121,
      "temperature": 1.0
    },
    {
      "all_correct": 0.375,
      "all_wrong": 0.25,
      "completion_length": 375.09375,
      "epoch": 0.034119936747354335,
      "grad_norm": 1.0574268139005814,
      "kl": 0.0322265625,
      "learning_rate": 9.97130274771552e-07,
      "loss": 0.0013,
      "reward": 1.6531250476837158,
      "reward_std": 0.2007448673248291,
      "rewards/accuracy_reward": 0.546875,
      "rewards/format_reward": 1.0,
      "step": 1122,
      "temperature": 1.0
    },
    {
      "all_correct": 1.0,
      "all_wrong": 0.0,
      "completion_length": 357.59375,
      "epoch": 0.03415034667315412,
      "grad_norm": 1.0290707698268704,
      "kl": 0.02783203125,
      "learning_rate": 9.971251620270205e-07,
      "loss": 0.0011,
      "reward": 2.1875,
      "reward_std": 0.029250433668494225,
      "rewards/accuracy_reward": 1.0,
      "rewards/format_reward": 1.0,
      "step": 1123,
      "temperature": 1.0
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.375,
      "completion_length": 365.671875,
      "epoch": 0.0341807565989539,
      "grad_norm": 0.9078286142575763,
      "kl": 0.031494140625,
      "learning_rate": 9.971200447452025e-07,
      "loss": 0.0013,
      "reward": 1.725000023841858,
      "reward_std": 0.06134308874607086,
      "rewards/accuracy_reward": 0.609375,
      "rewards/format_reward": 1.0,
      "step": 1124,
      "temperature": 1.0
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.125,
      "completion_length": 371.59375,
      "epoch": 0.03421116652475368,
      "grad_norm": 2.0567512180567147,
      "kl": 0.0247802734375,
      "learning_rate": 9.971149229261444e-07,
      "loss": 0.001,
      "reward": 1.7211308479309082,
      "reward_std": 0.13100098073482513,
      "rewards/accuracy_reward": 0.5898808240890503,
      "rewards/format_reward": 1.0,
      "step": 1125,
      "temperature": 1.0
    },
    {
      "all_correct": 0.875,
      "all_wrong": 0.0,
      "completion_length": 351.0625,
      "epoch": 0.03424157645055346,
      "grad_norm": 1.1963595173639654,
      "kl": 0.0322265625,
      "learning_rate": 9.971097965698934e-07,
      "loss": 0.0013,
      "reward": 2.094332218170166,
      "reward_std": 0.04028134047985077,
      "rewards/accuracy_reward": 0.9068320989608765,
      "rewards/format_reward": 1.0,
      "step": 1126,
      "temperature": 1.0
    },
    {
      "all_correct": 0.375,
      "all_wrong": 0.0,
      "completion_length": 373.25,
      "epoch": 0.034271986376353245,
      "grad_norm": 1.7077131554355405,
      "kl": 0.0322265625,
      "learning_rate": 9.971046656764958e-07,
      "loss": 0.0013,
      "reward": 1.8754020929336548,
      "reward_std": 0.17054632306098938,
      "rewards/accuracy_reward": 0.7129021883010864,
      "rewards/format_reward": 1.0,
      "step": 1127,
      "temperature": 1.0
    },
    {
      "all_correct": 0.75,
      "all_wrong": 0.125,
      "completion_length": 364.296875,
      "epoch": 0.034302396302153024,
      "grad_norm": 0.7235772236845203,
      "kl": 0.0283203125,
      "learning_rate": 9.97099530245999e-07,
      "loss": 0.0011,
      "reward": 1.96875,
      "reward_std": 0.08611097186803818,
      "rewards/accuracy_reward": 0.8125,
      "rewards/format_reward": 1.0,
      "step": 1128,
      "temperature": 1.0
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.0,
      "completion_length": 375.515625,
      "epoch": 0.0343328062279528,
      "grad_norm": 3.449172454198428,
      "kl": 0.0224609375,
      "learning_rate": 9.970943902784493e-07,
      "loss": 0.0009,
      "reward": 1.8469563722610474,
      "reward_std": 0.1868019700050354,
      "rewards/accuracy_reward": 0.6875813603401184,
      "rewards/format_reward": 1.0,
      "step": 1129,
      "temperature": 1.0
    },
    {
      "all_correct": 0.125,
      "all_wrong": 0.125,
      "completion_length": 400.796875,
      "epoch": 0.03436321615375258,
      "grad_norm": 1.2091136047387152,
      "kl": 0.033203125,
      "learning_rate": 9.97089245773894e-07,
      "loss": 0.0013,
      "reward": 1.7847669124603271,
      "reward_std": 0.209543377161026,
      "rewards/accuracy_reward": 0.6410167813301086,
      "rewards/format_reward": 1.0,
      "step": 1130,
      "temperature": 1.0
    },
    {
      "all_correct": 0.75,
      "all_wrong": 0.125,
      "completion_length": 364.5,
      "epoch": 0.03439362607955237,
      "grad_norm": 0.9410007787577985,
      "kl": 0.032470703125,
      "learning_rate": 9.9708409673238e-07,
      "loss": 0.0013,
      "reward": 1.9010366201400757,
      "reward_std": 0.017607901245355606,
      "rewards/accuracy_reward": 0.751036524772644,
      "rewards/format_reward": 1.0,
      "step": 1131,
      "temperature": 1.0
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.125,
      "completion_length": 406.734375,
      "epoch": 0.03442403600535215,
      "grad_norm": 0.908586090698521,
      "kl": 0.029296875,
      "learning_rate": 9.970789431539539e-07,
      "loss": 0.0012,
      "reward": 1.8408238887786865,
      "reward_std": 0.09544786810874939,
      "rewards/accuracy_reward": 0.6908238530158997,
      "rewards/format_reward": 1.0,
      "step": 1132,
      "temperature": 1.0
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.375,
      "completion_length": 380.125,
      "epoch": 0.03445444593115193,
      "grad_norm": 0.49611828600933333,
      "kl": 0.0294189453125,
      "learning_rate": 9.970737850386633e-07,
      "loss": 0.0012,
      "reward": 1.6937501430511475,
      "reward_std": 0.077632375061512,
      "rewards/accuracy_reward": 0.578125,
      "rewards/format_reward": 1.0,
      "step": 1133,
      "temperature": 1.0
    },
    {
      "all_correct": 0.625,
      "all_wrong": 0.25,
      "completion_length": 379.28125,
      "epoch": 0.034484855856951706,
      "grad_norm": 0.5520796247701365,
      "kl": 0.033935546875,
      "learning_rate": 9.97068622386555e-07,
      "loss": 0.0014,
      "reward": 1.823991298675537,
      "reward_std": 0.012359250336885452,
      "rewards/accuracy_reward": 0.6802411675453186,
      "rewards/format_reward": 1.0,
      "step": 1134,
      "temperature": 1.0
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.125,
      "completion_length": 371.96875,
      "epoch": 0.03451526578275149,
      "grad_norm": 0.971961980451252,
      "kl": 0.0296630859375,
      "learning_rate": 9.97063455197676e-07,
      "loss": 0.0012,
      "reward": 1.8294472694396973,
      "reward_std": 0.0805341899394989,
      "rewards/accuracy_reward": 0.6575722694396973,
      "rewards/format_reward": 1.0,
      "step": 1135,
      "temperature": 1.0
    },
    {
      "all_correct": 0.75,
      "all_wrong": 0.0,
      "completion_length": 365.390625,
      "epoch": 0.03454567570855127,
      "grad_norm": 1.0852322847656206,
      "kl": 0.0322265625,
      "learning_rate": 9.970582834720736e-07,
      "loss": 0.0013,
      "reward": 2.0802955627441406,
      "reward_std": 0.07524856925010681,
      "rewards/accuracy_reward": 0.8896706104278564,
      "rewards/format_reward": 1.0,
      "step": 1136,
      "temperature": 1.0
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.125,
      "completion_length": 380.234375,
      "epoch": 0.03457608563435105,
      "grad_norm": 1.3975940309707076,
      "kl": 0.034912109375,
      "learning_rate": 9.970531072097952e-07,
      "loss": 0.0014,
      "reward": 1.7180752754211426,
      "reward_std": 0.033700451254844666,
      "rewards/accuracy_reward": 0.561825156211853,
      "rewards/format_reward": 1.0,
      "step": 1137,
      "temperature": 1.0
    },
    {
      "all_correct": 0.25,
      "all_wrong": 0.5,
      "completion_length": 411.203125,
      "epoch": 0.034606495560150836,
      "grad_norm": 0.3978940051681478,
      "kl": 0.0283203125,
      "learning_rate": 9.970479264108878e-07,
      "loss": 0.0011,
      "reward": 1.415454626083374,
      "reward_std": 0.13413015007972717,
      "rewards/accuracy_reward": 0.3810797333717346,
      "rewards/format_reward": 0.953125,
      "step": 1138,
      "temperature": 1.0
    },
    {
      "all_correct": 0.625,
      "all_wrong": 0.0,
      "completion_length": 371.5,
      "epoch": 0.034636905485950616,
      "grad_norm": 1.1529001480369871,
      "kl": 0.032958984375,
      "learning_rate": 9.970427410753987e-07,
      "loss": 0.0013,
      "reward": 1.921875,
      "reward_std": 0.15858273208141327,
      "rewards/accuracy_reward": 0.765625,
      "rewards/format_reward": 1.0,
      "step": 1139,
      "temperature": 1.0
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.125,
      "completion_length": 378.0,
      "epoch": 0.034667315411750395,
      "grad_norm": 9.181256947299897,
      "kl": 0.034423828125,
      "learning_rate": 9.970375512033753e-07,
      "loss": 0.0014,
      "reward": 1.745079755783081,
      "reward_std": 0.110328808426857,
      "rewards/accuracy_reward": 0.6013297438621521,
      "rewards/format_reward": 1.0,
      "step": 1140,
      "temperature": 1.0
    },
    {
      "all_correct": 0.75,
      "all_wrong": 0.0,
      "completion_length": 374.84375,
      "epoch": 0.034697725337550174,
      "grad_norm": 1.0932684617786967,
      "kl": 0.0264892578125,
      "learning_rate": 9.97032356794865e-07,
      "loss": 0.0011,
      "reward": 2.0882415771484375,
      "reward_std": 0.0599309504032135,
      "rewards/accuracy_reward": 0.8913666605949402,
      "rewards/format_reward": 1.0,
      "step": 1141,
      "temperature": 1.0
    },
    {
      "all_correct": 0.875,
      "all_wrong": 0.125,
      "completion_length": 359.53125,
      "epoch": 0.03472813526334996,
      "grad_norm": 0.48494704730474314,
      "kl": 0.031494140625,
      "learning_rate": 9.97027157849915e-07,
      "loss": 0.0013,
      "reward": 2.046875,
      "reward_std": 0.008838837966322899,
      "rewards/accuracy_reward": 0.875,
      "rewards/format_reward": 1.0,
      "step": 1142,
      "temperature": 1.0
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.125,
      "completion_length": 372.671875,
      "epoch": 0.03475854518914974,
      "grad_norm": 1.5052958700844847,
      "kl": 0.036865234375,
      "learning_rate": 9.97021954368573e-07,
      "loss": 0.0015,
      "reward": 1.7848329544067383,
      "reward_std": 0.17025971412658691,
      "rewards/accuracy_reward": 0.6410830020904541,
      "rewards/format_reward": 1.0,
      "step": 1143,
      "temperature": 1.0
    },
    {
      "all_correct": 0.625,
      "all_wrong": 0.25,
      "completion_length": 368.25,
      "epoch": 0.03478895511494952,
      "grad_norm": 1.633993810720194,
      "kl": 0.02978515625,
      "learning_rate": 9.970167463508865e-07,
      "loss": 0.0012,
      "reward": 1.8181629180908203,
      "reward_std": 0.024760911241173744,
      "rewards/accuracy_reward": 0.6712878942489624,
      "rewards/format_reward": 1.0,
      "step": 1144,
      "temperature": 1.0
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.25,
      "completion_length": 365.796875,
      "epoch": 0.0348193650407493,
      "grad_norm": 0.8787459677537164,
      "kl": 0.030517578125,
      "learning_rate": 9.970115337969027e-07,
      "loss": 0.0012,
      "reward": 1.7283766269683838,
      "reward_std": 0.09927521646022797,
      "rewards/accuracy_reward": 0.5971266031265259,
      "rewards/format_reward": 1.0,
      "step": 1145,
      "temperature": 1.0
    },
    {
      "all_correct": 0.625,
      "all_wrong": 0.125,
      "completion_length": 376.140625,
      "epoch": 0.034849774966549084,
      "grad_norm": 2.1798777171219155,
      "kl": 0.0286865234375,
      "learning_rate": 9.970063167066696e-07,
      "loss": 0.0011,
      "reward": 1.9034209251403809,
      "reward_std": 0.02453031577169895,
      "rewards/accuracy_reward": 0.7315459251403809,
      "rewards/format_reward": 1.0,
      "step": 1146,
      "temperature": 1.0
    },
    {
      "all_correct": 0.75,
      "all_wrong": 0.125,
      "completion_length": 388.3125,
      "epoch": 0.03488018489234886,
      "grad_norm": 0.6235675806737009,
      "kl": 0.0277099609375,
      "learning_rate": 9.970010950802346e-07,
      "loss": 0.0011,
      "reward": 1.9968749284744263,
      "reward_std": 0.07151715457439423,
      "rewards/accuracy_reward": 0.84375,
      "rewards/format_reward": 1.0,
      "step": 1147,
      "temperature": 1.0
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.125,
      "completion_length": 385.984375,
      "epoch": 0.03491059481814864,
      "grad_norm": 0.8614620498175211,
      "kl": 0.032958984375,
      "learning_rate": 9.969958689176452e-07,
      "loss": 0.0013,
      "reward": 1.7910230159759521,
      "reward_std": 0.06380719691514969,
      "rewards/accuracy_reward": 0.6503980159759521,
      "rewards/format_reward": 1.0,
      "step": 1148,
      "temperature": 1.0
    },
    {
      "all_correct": 0.625,
      "all_wrong": 0.125,
      "completion_length": 360.96875,
      "epoch": 0.03494100474394842,
      "grad_norm": 6.9891784666690615,
      "kl": 0.03564453125,
      "learning_rate": 9.969906382189494e-07,
      "loss": 0.0014,
      "reward": 1.7764062881469727,
      "reward_std": 0.04640388488769531,
      "rewards/accuracy_reward": 0.6514062285423279,
      "rewards/format_reward": 1.0,
      "step": 1149,
      "temperature": 1.0
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.125,
      "completion_length": 395.40625,
      "epoch": 0.03497141466974821,
      "grad_norm": 1.1492934451768142,
      "kl": 0.03173828125,
      "learning_rate": 9.969854029841948e-07,
      "loss": 0.0013,
      "reward": 1.7899036407470703,
      "reward_std": 0.11600731313228607,
      "rewards/accuracy_reward": 0.6399034857749939,
      "rewards/format_reward": 1.0,
      "step": 1150,
      "temperature": 1.0
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.125,
      "completion_length": 370.140625,
      "epoch": 0.03500182459554799,
      "grad_norm": 1.1792462099638712,
      "kl": 0.034912109375,
      "learning_rate": 9.96980163213429e-07,
      "loss": 0.0014,
      "reward": 1.8117589950561523,
      "reward_std": 0.15627166628837585,
      "rewards/accuracy_reward": 0.6680090427398682,
      "rewards/format_reward": 1.0,
      "step": 1151,
      "temperature": 1.0
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.125,
      "completion_length": 386.421875,
      "epoch": 0.035032234521347766,
      "grad_norm": 0.8516265507210926,
      "kl": 0.027099609375,
      "learning_rate": 9.969749189067005e-07,
      "loss": 0.0011,
      "reward": 1.8625000715255737,
      "reward_std": 0.2108437716960907,
      "rewards/accuracy_reward": 0.71875,
      "rewards/format_reward": 1.0,
      "step": 1152,
      "temperature": 1.0
    },
    {
      "all_correct": 0.625,
      "all_wrong": 0.0,
      "completion_length": 372.0,
      "epoch": 0.03506264444714755,
      "grad_norm": 1.2170402308144335,
      "kl": 0.0301513671875,
      "learning_rate": 9.969696700640565e-07,
      "loss": 0.0012,
      "reward": 1.8844451904296875,
      "reward_std": 0.029813367873430252,
      "rewards/accuracy_reward": 0.7250702381134033,
      "rewards/format_reward": 1.0,
      "step": 1153,
      "temperature": 1.0
    },
    {
      "all_correct": 0.25,
      "all_wrong": 0.25,
      "completion_length": 415.671875,
      "epoch": 0.03509305437294733,
      "grad_norm": 0.7148363338812642,
      "kl": 0.035400390625,
      "learning_rate": 9.969644166855449e-07,
      "loss": 0.0014,
      "reward": 1.4465069770812988,
      "reward_std": 0.11390846967697144,
      "rewards/accuracy_reward": 0.37150701880455017,
      "rewards/format_reward": 0.984375,
      "step": 1154,
      "temperature": 1.0
    },
    {
      "all_correct": 0.375,
      "all_wrong": 0.375,
      "completion_length": 376.125,
      "epoch": 0.03512346429874711,
      "grad_norm": 0.8814426695820301,
      "kl": 0.03076171875,
      "learning_rate": 9.969591587712138e-07,
      "loss": 0.0012,
      "reward": 1.5531249046325684,
      "reward_std": 0.11738666892051697,
      "rewards/accuracy_reward": 0.46875,
      "rewards/format_reward": 1.0,
      "step": 1155,
      "temperature": 1.0
    },
    {
      "all_correct": 0.25,
      "all_wrong": 0.125,
      "completion_length": 377.4375,
      "epoch": 0.03515387422454689,
      "grad_norm": 2.503417425861633,
      "kl": 0.038330078125,
      "learning_rate": 9.969538963211114e-07,
      "loss": 0.0015,
      "reward": 1.6409857273101807,
      "reward_std": 0.21098706126213074,
      "rewards/accuracy_reward": 0.5128607153892517,
      "rewards/format_reward": 1.0,
      "step": 1156,
      "temperature": 1.0
    },
    {
      "all_correct": 0.25,
      "all_wrong": 0.25,
      "completion_length": 376.625,
      "epoch": 0.035184284150346676,
      "grad_norm": 1.6032154488382135,
      "kl": 0.04248046875,
      "learning_rate": 9.969486293352855e-07,
      "loss": 0.0017,
      "reward": 1.4589827060699463,
      "reward_std": 0.08787427842617035,
      "rewards/accuracy_reward": 0.34648269414901733,
      "rewards/format_reward": 1.0,
      "step": 1157,
      "temperature": 1.0
    },
    {
      "all_correct": 0.375,
      "all_wrong": 0.375,
      "completion_length": 386.4375,
      "epoch": 0.035214694076146455,
      "grad_norm": 1.00080809949175,
      "kl": 0.032958984375,
      "learning_rate": 9.969433578137843e-07,
      "loss": 0.0013,
      "reward": 1.6479413509368896,
      "reward_std": 0.026308942586183548,
      "rewards/accuracy_reward": 0.5385662913322449,
      "rewards/format_reward": 1.0,
      "step": 1158,
      "temperature": 1.0
    },
    {
      "all_correct": 0.75,
      "all_wrong": 0.0,
      "completion_length": 355.734375,
      "epoch": 0.035245104001946234,
      "grad_norm": 1.1514138514700039,
      "kl": 0.040283203125,
      "learning_rate": 9.96938081756656e-07,
      "loss": 0.0016,
      "reward": 2.0572447776794434,
      "reward_std": 0.11053717881441116,
      "rewards/accuracy_reward": 0.8759948015213013,
      "rewards/format_reward": 1.0,
      "step": 1159,
      "temperature": 1.0
    },
    {
      "all_correct": 0.25,
      "all_wrong": 0.25,
      "completion_length": 450.25,
      "epoch": 0.03527551392774601,
      "grad_norm": 0.6436159700997038,
      "kl": 0.027099609375,
      "learning_rate": 9.969328011639483e-07,
      "loss": 0.0011,
      "reward": 1.5360925197601318,
      "reward_std": 0.21513505280017853,
      "rewards/accuracy_reward": 0.4704675078392029,
      "rewards/format_reward": 0.984375,
      "step": 1160,
      "temperature": 1.0
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.375,
      "completion_length": 383.40625,
      "epoch": 0.0353059238535458,
      "grad_norm": 0.7721102492301887,
      "kl": 0.025390625,
      "learning_rate": 9.969275160357099e-07,
      "loss": 0.001,
      "reward": 1.6437499523162842,
      "reward_std": 0.0909954383969307,
      "rewards/accuracy_reward": 0.546875,
      "rewards/format_reward": 1.0,
      "step": 1161,
      "temperature": 1.0
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.375,
      "completion_length": 370.734375,
      "epoch": 0.03533633377934558,
      "grad_norm": 0.6252239478250365,
      "kl": 0.03271484375,
      "learning_rate": 9.969222263719888e-07,
      "loss": 0.0013,
      "reward": 1.7224416732788086,
      "reward_std": 0.012419304810464382,
      "rewards/accuracy_reward": 0.5974416732788086,
      "rewards/format_reward": 1.0,
      "step": 1162,
      "temperature": 1.0
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.25,
      "completion_length": 396.109375,
      "epoch": 0.03536674370514536,
      "grad_norm": 0.7509517056107452,
      "kl": 0.0289306640625,
      "learning_rate": 9.969169321728332e-07,
      "loss": 0.0012,
      "reward": 1.6746838092803955,
      "reward_std": 0.058494821190834045,
      "rewards/accuracy_reward": 0.5590587258338928,
      "rewards/format_reward": 1.0,
      "step": 1163,
      "temperature": 1.0
    },
    {
      "all_correct": 0.375,
      "all_wrong": 0.125,
      "completion_length": 399.5,
      "epoch": 0.03539715363094514,
      "grad_norm": 1.0944056297816556,
      "kl": 0.03125,
      "learning_rate": 9.969116334382916e-07,
      "loss": 0.0012,
      "reward": 1.7903258800506592,
      "reward_std": 0.10033317655324936,
      "rewards/accuracy_reward": 0.6309508085250854,
      "rewards/format_reward": 1.0,
      "step": 1164,
      "temperature": 1.0
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.125,
      "completion_length": 381.828125,
      "epoch": 0.03542756355674492,
      "grad_norm": 1.4459090095298563,
      "kl": 0.03173828125,
      "learning_rate": 9.969063301684122e-07,
      "loss": 0.0013,
      "reward": 1.8457082509994507,
      "reward_std": 0.17786380648612976,
      "rewards/accuracy_reward": 0.701958179473877,
      "rewards/format_reward": 1.0,
      "step": 1165,
      "temperature": 1.0
    },
    {
      "all_correct": 0.625,
      "all_wrong": 0.25,
      "completion_length": 364.171875,
      "epoch": 0.0354579734825447,
      "grad_norm": 0.6495847827642469,
      "kl": 0.033203125,
      "learning_rate": 9.969010223632438e-07,
      "loss": 0.0013,
      "reward": 1.8812499046325684,
      "reward_std": 0.0530330091714859,
      "rewards/accuracy_reward": 0.734375,
      "rewards/format_reward": 1.0,
      "step": 1166,
      "temperature": 1.0
    },
    {
      "all_correct": 0.375,
      "all_wrong": 0.125,
      "completion_length": 374.609375,
      "epoch": 0.03548838340834448,
      "grad_norm": 0.9979204737646302,
      "kl": 0.03662109375,
      "learning_rate": 9.968957100228341e-07,
      "loss": 0.0015,
      "reward": 1.7093751430511475,
      "reward_std": 0.2606995701789856,
      "rewards/accuracy_reward": 0.59375,
      "rewards/format_reward": 1.0,
      "step": 1167,
      "temperature": 1.0
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.25,
      "completion_length": 381.640625,
      "epoch": 0.03551879333414427,
      "grad_norm": 0.9898733601082234,
      "kl": 0.0301513671875,
      "learning_rate": 9.968903931472322e-07,
      "loss": 0.0012,
      "reward": 1.8159818649291992,
      "reward_std": 0.1083039790391922,
      "rewards/accuracy_reward": 0.6847319006919861,
      "rewards/format_reward": 0.984375,
      "step": 1168,
      "temperature": 1.0
    },
    {
      "all_correct": 0.25,
      "all_wrong": 0.25,
      "completion_length": 375.484375,
      "epoch": 0.03554920325994405,
      "grad_norm": 1.3182098032840643,
      "kl": 0.0294189453125,
      "learning_rate": 9.968850717364868e-07,
      "loss": 0.0012,
      "reward": 1.5841600894927979,
      "reward_std": 0.07941659539937973,
      "rewards/accuracy_reward": 0.4622851014137268,
      "rewards/format_reward": 1.0,
      "step": 1169,
      "temperature": 1.0
    },
    {
      "all_correct": 0.625,
      "all_wrong": 0.25,
      "completion_length": 363.328125,
      "epoch": 0.035579613185743826,
      "grad_norm": 0.380305527813375,
      "kl": 0.03662109375,
      "learning_rate": 9.968797457906458e-07,
      "loss": 0.0015,
      "reward": 1.8250000476837158,
      "reward_std": 0.08017837256193161,
      "rewards/accuracy_reward": 0.6875,
      "rewards/format_reward": 1.0,
      "step": 1170,
      "temperature": 1.0
    },
    {
      "all_correct": 0.75,
      "all_wrong": 0.125,
      "completion_length": 372.5625,
      "epoch": 0.035610023111543605,
      "grad_norm": 0.8590394745775125,
      "kl": 0.035888671875,
      "learning_rate": 9.968744153097582e-07,
      "loss": 0.0014,
      "reward": 1.941326379776001,
      "reward_std": 0.025385325774550438,
      "rewards/accuracy_reward": 0.7757013440132141,
      "rewards/format_reward": 1.0,
      "step": 1171,
      "temperature": 1.0
    },
    {
      "all_correct": 0.375,
      "all_wrong": 0.0,
      "completion_length": 406.84375,
      "epoch": 0.03564043303734339,
      "grad_norm": 11.466341526099667,
      "kl": 0.03271484375,
      "learning_rate": 9.968690802938726e-07,
      "loss": 0.0013,
      "reward": 1.7135803699493408,
      "reward_std": 0.15738029778003693,
      "rewards/accuracy_reward": 0.5635802745819092,
      "rewards/format_reward": 1.0,
      "step": 1172,
      "temperature": 1.0
    },
    {
      "all_correct": 0.875,
      "all_wrong": 0.0,
      "completion_length": 371.078125,
      "epoch": 0.03567084296314317,
      "grad_norm": 0.8272982077412819,
      "kl": 0.0301513671875,
      "learning_rate": 9.968637407430375e-07,
      "loss": 0.0012,
      "reward": 2.1204514503479004,
      "reward_std": 0.015612217597663403,
      "rewards/accuracy_reward": 0.9267013669013977,
      "rewards/format_reward": 1.0,
      "step": 1173,
      "temperature": 1.0
    },
    {
      "all_correct": 0.625,
      "all_wrong": 0.25,
      "completion_length": 387.96875,
      "epoch": 0.03570125288894295,
      "grad_norm": 0.6965215441219149,
      "kl": 0.02978515625,
      "learning_rate": 9.96858396657302e-07,
      "loss": 0.0012,
      "reward": 1.8656251430511475,
      "reward_std": 0.07523491233587265,
      "rewards/accuracy_reward": 0.734375,
      "rewards/format_reward": 1.0,
      "step": 1174,
      "temperature": 1.0
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.0,
      "completion_length": 384.625,
      "epoch": 0.03573166281474273,
      "grad_norm": 1.068305855827611,
      "kl": 0.0303955078125,
      "learning_rate": 9.968530480367147e-07,
      "loss": 0.0012,
      "reward": 1.9180628061294556,
      "reward_std": 0.16402453184127808,
      "rewards/accuracy_reward": 0.7430627346038818,
      "rewards/format_reward": 1.0,
      "step": 1175,
      "temperature": 1.0
    },
    {
      "all_correct": 0.625,
      "all_wrong": 0.0,
      "completion_length": 380.34375,
      "epoch": 0.035762072740542515,
      "grad_norm": 1.4461056573254005,
      "kl": 0.028564453125,
      "learning_rate": 9.968476948813244e-07,
      "loss": 0.0011,
      "reward": 1.9896197319030762,
      "reward_std": 0.10615414381027222,
      "rewards/accuracy_reward": 0.8083697557449341,
      "rewards/format_reward": 1.0,
      "step": 1176,
      "temperature": 1.0
    },
    {
      "all_correct": 0.25,
      "all_wrong": 0.25,
      "completion_length": 398.0625,
      "epoch": 0.035792482666342294,
      "grad_norm": 1.099603268497178,
      "kl": 0.0284423828125,
      "learning_rate": 9.9684233719118e-07,
      "loss": 0.0011,
      "reward": 1.6466586589813232,
      "reward_std": 0.2337760478258133,
      "rewards/accuracy_reward": 0.5279086232185364,
      "rewards/format_reward": 1.0,
      "step": 1177,
      "temperature": 1.0
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.125,
      "completion_length": 411.828125,
      "epoch": 0.035822892592142073,
      "grad_norm": 1.0809137541164098,
      "kl": 0.029052734375,
      "learning_rate": 9.968369749663303e-07,
      "loss": 0.0012,
      "reward": 1.6710968017578125,
      "reward_std": 0.07263951003551483,
      "rewards/accuracy_reward": 0.561721682548523,
      "rewards/format_reward": 0.984375,
      "step": 1178,
      "temperature": 1.0
    },
    {
      "all_correct": 0.625,
      "all_wrong": 0.125,
      "completion_length": 358.453125,
      "epoch": 0.03585330251794186,
      "grad_norm": 1.2441350221369591,
      "kl": 0.03759765625,
      "learning_rate": 9.968316082068245e-07,
      "loss": 0.0015,
      "reward": 1.8768274784088135,
      "reward_std": 0.09971503168344498,
      "rewards/accuracy_reward": 0.7268275618553162,
      "rewards/format_reward": 1.0,
      "step": 1179,
      "temperature": 1.0
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.125,
      "completion_length": 369.203125,
      "epoch": 0.03588371244374164,
      "grad_norm": 1.4171047280074038,
      "kl": 0.030029296875,
      "learning_rate": 9.968262369127113e-07,
      "loss": 0.0012,
      "reward": 1.7928521633148193,
      "reward_std": 0.1550390124320984,
      "rewards/accuracy_reward": 0.6553521156311035,
      "rewards/format_reward": 1.0,
      "step": 1180,
      "temperature": 1.0
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.125,
      "completion_length": 406.171875,
      "epoch": 0.03591412236954142,
      "grad_norm": 1.8007463661266467,
      "kl": 0.029052734375,
      "learning_rate": 9.968208610840395e-07,
      "loss": 0.0012,
      "reward": 1.8497192859649658,
      "reward_std": 0.157828226685524,
      "rewards/accuracy_reward": 0.7122193574905396,
      "rewards/format_reward": 1.0,
      "step": 1181,
      "temperature": 1.0
    },
    {
      "all_correct": 0.25,
      "all_wrong": 0.125,
      "completion_length": 410.765625,
      "epoch": 0.0359445322953412,
      "grad_norm": 1.142855906925365,
      "kl": 0.029296875,
      "learning_rate": 9.968154807208587e-07,
      "loss": 0.0012,
      "reward": 1.6572691202163696,
      "reward_std": 0.22080466151237488,
      "rewards/accuracy_reward": 0.5447690486907959,
      "rewards/format_reward": 0.984375,
      "step": 1182,
      "temperature": 1.0
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.25,
      "completion_length": 359.046875,
      "epoch": 0.03597494222114098,
      "grad_norm": 1.1347860660889892,
      "kl": 0.03173828125,
      "learning_rate": 9.968100958232178e-07,
      "loss": 0.0013,
      "reward": 1.7593750953674316,
      "reward_std": 0.13471055030822754,
      "rewards/accuracy_reward": 0.640625,
      "rewards/format_reward": 1.0,
      "step": 1183,
      "temperature": 1.0
    },
    {
      "all_correct": 0.625,
      "all_wrong": 0.25,
      "completion_length": 376.703125,
      "epoch": 0.03600535214694076,
      "grad_norm": 0.7133977275239562,
      "kl": 0.023681640625,
      "learning_rate": 9.96804706391166e-07,
      "loss": 0.0009,
      "reward": 1.8214243650436401,
      "reward_std": 0.09029192477464676,
      "rewards/accuracy_reward": 0.6870493292808533,
      "rewards/format_reward": 1.0,
      "step": 1184,
      "temperature": 1.0
    },
    {
      "all_correct": 0.75,
      "all_wrong": 0.25,
      "completion_length": 345.71875,
      "epoch": 0.03603576207274054,
      "grad_norm": 0.6967976294770689,
      "kl": 0.03515625,
      "learning_rate": 9.967993124247523e-07,
      "loss": 0.0014,
      "reward": 1.8968751430511475,
      "reward_std": 0.008838837966322899,
      "rewards/accuracy_reward": 0.75,
      "rewards/format_reward": 1.0,
      "step": 1185,
      "temperature": 1.0
    },
    {
      "all_correct": 0.875,
      "all_wrong": 0.0,
      "completion_length": 359.015625,
      "epoch": 0.03606617199854032,
      "grad_norm": 1.1186051043445568,
      "kl": 0.0306396484375,
      "learning_rate": 9.967939139240263e-07,
      "loss": 0.0012,
      "reward": 2.089137554168701,
      "reward_std": 0.017244329676032066,
      "rewards/accuracy_reward": 0.8953874111175537,
      "rewards/format_reward": 1.0,
      "step": 1186,
      "temperature": 1.0
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.125,
      "completion_length": 378.796875,
      "epoch": 0.03609658192434011,
      "grad_norm": 1.3285576154380563,
      "kl": 0.02978515625,
      "learning_rate": 9.967885108890366e-07,
      "loss": 0.0012,
      "reward": 1.7848801612854004,
      "reward_std": 0.1768539845943451,
      "rewards/accuracy_reward": 0.6536300778388977,
      "rewards/format_reward": 1.0,
      "step": 1187,
      "temperature": 1.0
    },
    {
      "all_correct": 0.375,
      "all_wrong": 0.25,
      "completion_length": 356.5,
      "epoch": 0.036126991850139886,
      "grad_norm": 1.4087343721938757,
      "kl": 0.035888671875,
      "learning_rate": 9.967831033198332e-07,
      "loss": 0.0014,
      "reward": 1.6132287979125977,
      "reward_std": 0.14344462752342224,
      "rewards/accuracy_reward": 0.5101038217544556,
      "rewards/format_reward": 1.0,
      "step": 1188,
      "temperature": 1.0
    },
    {
      "all_correct": 0.375,
      "all_wrong": 0.125,
      "completion_length": 398.171875,
      "epoch": 0.036157401775939665,
      "grad_norm": 1.6305690544642972,
      "kl": 0.0299072265625,
      "learning_rate": 9.967776912164654e-07,
      "loss": 0.0012,
      "reward": 1.664294719696045,
      "reward_std": 0.22947821021080017,
      "rewards/accuracy_reward": 0.5486696362495422,
      "rewards/format_reward": 1.0,
      "step": 1189,
      "temperature": 1.0
    },
    {
      "all_correct": 0.75,
      "all_wrong": 0.0,
      "completion_length": 388.359375,
      "epoch": 0.036187811701739445,
      "grad_norm": 0.9320953940462177,
      "kl": 0.029541015625,
      "learning_rate": 9.967722745789821e-07,
      "loss": 0.0012,
      "reward": 2.0042881965637207,
      "reward_std": 0.026993395760655403,
      "rewards/accuracy_reward": 0.8324130773544312,
      "rewards/format_reward": 1.0,
      "step": 1190,
      "temperature": 1.0
    },
    {
      "all_correct": 0.875,
      "all_wrong": 0.0,
      "completion_length": 370.34375,
      "epoch": 0.03621822162753923,
      "grad_norm": 0.5975919574030307,
      "kl": 0.031982421875,
      "learning_rate": 9.96766853407433e-07,
      "loss": 0.0013,
      "reward": 2.144791603088379,
      "reward_std": 0.03830162435770035,
      "rewards/accuracy_reward": 0.9479167461395264,
      "rewards/format_reward": 1.0,
      "step": 1191,
      "temperature": 1.0
    },
    {
      "all_correct": 0.625,
      "all_wrong": 0.0,
      "completion_length": 399.90625,
      "epoch": 0.03624863155333901,
      "grad_norm": 1.0764676435999878,
      "kl": 0.0322265625,
      "learning_rate": 9.967614277018679e-07,
      "loss": 0.0013,
      "reward": 1.988457441329956,
      "reward_std": 0.08253973722457886,
      "rewards/accuracy_reward": 0.8353323936462402,
      "rewards/format_reward": 1.0,
      "step": 1192,
      "temperature": 1.0
    },
    {
      "all_correct": 0.375,
      "all_wrong": 0.125,
      "completion_length": 382.40625,
      "epoch": 0.03627904147913879,
      "grad_norm": 1.2341022368480987,
      "kl": 0.033935546875,
      "learning_rate": 9.967559974623359e-07,
      "loss": 0.0014,
      "reward": 1.8015625476837158,
      "reward_std": 0.2570255696773529,
      "rewards/accuracy_reward": 0.6703125238418579,
      "rewards/format_reward": 1.0,
      "step": 1193,
      "temperature": 1.0
    },
    {
      "all_correct": 0.875,
      "all_wrong": 0.0,
      "completion_length": 362.078125,
      "epoch": 0.036309451404938575,
      "grad_norm": 0.5645158834454872,
      "kl": 0.041015625,
      "learning_rate": 9.967505626888866e-07,
      "loss": 0.0016,
      "reward": 2.153818130493164,
      "reward_std": 0.00623175036162138,
      "rewards/accuracy_reward": 0.9538180828094482,
      "rewards/format_reward": 1.0,
      "step": 1194,
      "temperature": 1.0
    },
    {
      "all_correct": 0.75,
      "all_wrong": 0.0,
      "completion_length": 369.671875,
      "epoch": 0.036339861330738354,
      "grad_norm": 0.7895940874474386,
      "kl": 0.0286865234375,
      "learning_rate": 9.967451233815697e-07,
      "loss": 0.0011,
      "reward": 2.038499355316162,
      "reward_std": 0.056512411683797836,
      "rewards/accuracy_reward": 0.8634991645812988,
      "rewards/format_reward": 1.0,
      "step": 1195,
      "temperature": 1.0
    },
    {
      "all_correct": 0.625,
      "all_wrong": 0.0,
      "completion_length": 379.25,
      "epoch": 0.036370271256538134,
      "grad_norm": 1.3076750391527348,
      "kl": 0.03515625,
      "learning_rate": 9.96739679540435e-07,
      "loss": 0.0014,
      "reward": 1.9959135055541992,
      "reward_std": 0.09294147789478302,
      "rewards/accuracy_reward": 0.8177883625030518,
      "rewards/format_reward": 1.0,
      "step": 1196,
      "temperature": 1.0
    },
    {
      "all_correct": 0.625,
      "all_wrong": 0.25,
      "completion_length": 375.75,
      "epoch": 0.03640068118233791,
      "grad_norm": 0.32484330199761985,
      "kl": 0.03515625,
      "learning_rate": 9.967342311655317e-07,
      "loss": 0.0014,
      "reward": 1.859375,
      "reward_std": 0.06805656850337982,
      "rewards/accuracy_reward": 0.71875,
      "rewards/format_reward": 1.0,
      "step": 1197,
      "temperature": 1.0
    },
    {
      "all_correct": 0.625,
      "all_wrong": 0.125,
      "completion_length": 401.5,
      "epoch": 0.0364310911081377,
      "grad_norm": 0.9620007160341915,
      "kl": 0.0361328125,
      "learning_rate": 9.967287782569103e-07,
      "loss": 0.0014,
      "reward": 1.834375023841858,
      "reward_std": 0.1532049924135208,
      "rewards/accuracy_reward": 0.703125,
      "rewards/format_reward": 1.0,
      "step": 1198,
      "temperature": 1.0
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.25,
      "completion_length": 386.4375,
      "epoch": 0.03646150103393748,
      "grad_norm": 0.8673758016973084,
      "kl": 0.03271484375,
      "learning_rate": 9.967233208146198e-07,
      "loss": 0.0013,
      "reward": 1.709754228591919,
      "reward_std": 0.08199620991945267,
      "rewards/accuracy_reward": 0.5785042643547058,
      "rewards/format_reward": 1.0,
      "step": 1199,
      "temperature": 1.0
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.0,
      "completion_length": 408.84375,
      "epoch": 0.03649191095973726,
      "grad_norm": 1.1171750789337782,
      "kl": 0.035400390625,
      "learning_rate": 9.967178588387105e-07,
      "loss": 0.0014,
      "reward": 1.7569730281829834,
      "reward_std": 0.1504843682050705,
      "rewards/accuracy_reward": 0.6382229328155518,
      "rewards/format_reward": 1.0,
      "step": 1200,
      "temperature": 1.0
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.25,
      "completion_length": 378.9375,
      "epoch": 0.03652232088553704,
      "grad_norm": 1.3634616646782756,
      "kl": 0.0322265625,
      "learning_rate": 9.96712392329232e-07,
      "loss": 0.0013,
      "reward": 1.7582263946533203,
      "reward_std": 0.14932964742183685,
      "rewards/accuracy_reward": 0.6301013231277466,
      "rewards/format_reward": 1.0,
      "step": 1201,
      "temperature": 1.0
    },
    {
      "all_correct": 0.25,
      "all_wrong": 0.375,
      "completion_length": 407.421875,
      "epoch": 0.03655273081133682,
      "grad_norm": 0.8687880973062533,
      "kl": 0.022705078125,
      "learning_rate": 9.967069212862344e-07,
      "loss": 0.0009,
      "reward": 1.4812500476837158,
      "reward_std": 0.18988311290740967,
      "rewards/accuracy_reward": 0.40625,
      "rewards/format_reward": 1.0,
      "step": 1202,
      "temperature": 1.0
    },
    {
      "all_correct": 0.25,
      "all_wrong": 0.5,
      "completion_length": 417.859375,
      "epoch": 0.0365831407371366,
      "grad_norm": 0.7836273469848917,
      "kl": 0.031005859375,
      "learning_rate": 9.967014457097674e-07,
      "loss": 0.0012,
      "reward": 1.3569281101226807,
      "reward_std": 0.14372044801712036,
      "rewards/accuracy_reward": 0.3131781220436096,
      "rewards/format_reward": 0.96875,
      "step": 1203,
      "temperature": 1.0
    },
    {
      "all_correct": 0.625,
      "all_wrong": 0.125,
      "completion_length": 385.984375,
      "epoch": 0.03661355066293638,
      "grad_norm": 0.8026837070655322,
      "kl": 0.035888671875,
      "learning_rate": 9.96695965599881e-07,
      "loss": 0.0014,
      "reward": 1.8945523500442505,
      "reward_std": 0.08972810953855515,
      "rewards/accuracy_reward": 0.7383023500442505,
      "rewards/format_reward": 1.0,
      "step": 1204,
      "temperature": 1.0
    },
    {
      "all_correct": 0.75,
      "all_wrong": 0.125,
      "completion_length": 382.125,
      "epoch": 0.03664396058873616,
      "grad_norm": 4.463699689997463,
      "kl": 0.03369140625,
      "learning_rate": 9.966904809566254e-07,
      "loss": 0.0013,
      "reward": 1.925453543663025,
      "reward_std": 0.027894020080566406,
      "rewards/accuracy_reward": 0.7567035555839539,
      "rewards/format_reward": 1.0,
      "step": 1205,
      "temperature": 1.0
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.125,
      "completion_length": 433.03125,
      "epoch": 0.036674370514535946,
      "grad_norm": 0.9793168422046096,
      "kl": 0.0262451171875,
      "learning_rate": 9.966849917800506e-07,
      "loss": 0.001,
      "reward": 1.7894985675811768,
      "reward_std": 0.11389000713825226,
      "rewards/accuracy_reward": 0.7519985437393188,
      "rewards/format_reward": 0.875,
      "step": 1206,
      "temperature": 1.0
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.25,
      "completion_length": 374.265625,
      "epoch": 0.036704780440335726,
      "grad_norm": 2.0818830897901486,
      "kl": 0.033935546875,
      "learning_rate": 9.966794980702068e-07,
      "loss": 0.0014,
      "reward": 1.6943612098693848,
      "reward_std": 0.035793375223875046,
      "rewards/accuracy_reward": 0.581861138343811,
      "rewards/format_reward": 1.0,
      "step": 1207,
      "temperature": 1.0
    },
    {
      "all_correct": 0.625,
      "all_wrong": 0.125,
      "completion_length": 376.84375,
      "epoch": 0.036735190366135505,
      "grad_norm": 1.178900126330261,
      "kl": 0.029541015625,
      "learning_rate": 9.96673999827144e-07,
      "loss": 0.0012,
      "reward": 1.8115098476409912,
      "reward_std": 0.05396632105112076,
      "rewards/accuracy_reward": 0.6771348714828491,
      "rewards/format_reward": 1.0,
      "step": 1208,
      "temperature": 1.0
    },
    {
      "all_correct": 0.625,
      "all_wrong": 0.125,
      "completion_length": 352.1875,
      "epoch": 0.03676560029193529,
      "grad_norm": 1.4387193720931983,
      "kl": 0.03173828125,
      "learning_rate": 9.96668497050912e-07,
      "loss": 0.0013,
      "reward": 1.8645833730697632,
      "reward_std": 0.10012082010507584,
      "rewards/accuracy_reward": 0.7239583730697632,
      "rewards/format_reward": 1.0,
      "step": 1209,
      "temperature": 1.0
    },
    {
      "all_correct": 0.375,
      "all_wrong": 0.375,
      "completion_length": 365.390625,
      "epoch": 0.03679601021773507,
      "grad_norm": 1.1363495127150767,
      "kl": 0.0284423828125,
      "learning_rate": 9.966629897415617e-07,
      "loss": 0.0011,
      "reward": 1.5947306156158447,
      "reward_std": 0.07874157279729843,
      "rewards/accuracy_reward": 0.4853556156158447,
      "rewards/format_reward": 1.0,
      "step": 1210,
      "temperature": 1.0
    },
    {
      "all_correct": 0.75,
      "all_wrong": 0.0,
      "completion_length": 387.78125,
      "epoch": 0.03682642014353485,
      "grad_norm": 1.208442634663853,
      "kl": 0.0302734375,
      "learning_rate": 9.966574778991432e-07,
      "loss": 0.0012,
      "reward": 2.0115935802459717,
      "reward_std": 0.03436083719134331,
      "rewards/accuracy_reward": 0.8334685564041138,
      "rewards/format_reward": 1.0,
      "step": 1211,
      "temperature": 1.0
    },
    {
      "all_correct": 0.625,
      "all_wrong": 0.25,
      "completion_length": 362.875,
      "epoch": 0.03685683006933463,
      "grad_norm": 2.8758779767557012,
      "kl": 0.038330078125,
      "learning_rate": 9.966519615237065e-07,
      "loss": 0.0015,
      "reward": 1.7900360822677612,
      "reward_std": 0.04290841519832611,
      "rewards/accuracy_reward": 0.6556610465049744,
      "rewards/format_reward": 1.0,
      "step": 1212,
      "temperature": 1.0
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.0,
      "completion_length": 390.9375,
      "epoch": 0.036887239995134415,
      "grad_norm": 1.5541432406253806,
      "kl": 0.035400390625,
      "learning_rate": 9.966464406153021e-07,
      "loss": 0.0014,
      "reward": 1.955958366394043,
      "reward_std": 0.14124098420143127,
      "rewards/accuracy_reward": 0.8215833902359009,
      "rewards/format_reward": 0.96875,
      "step": 1213,
      "temperature": 1.0
    },
    {
      "all_correct": 0.625,
      "all_wrong": 0.125,
      "completion_length": 369.375,
      "epoch": 0.036917649920934194,
      "grad_norm": 1.0424339826756504,
      "kl": 0.03173828125,
      "learning_rate": 9.966409151739806e-07,
      "loss": 0.0013,
      "reward": 1.946874976158142,
      "reward_std": 0.16336661577224731,
      "rewards/accuracy_reward": 0.796875,
      "rewards/format_reward": 1.0,
      "step": 1214,
      "temperature": 1.0
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.125,
      "completion_length": 361.359375,
      "epoch": 0.03694805984673397,
      "grad_norm": 1.58038302498911,
      "kl": 0.03125,
      "learning_rate": 9.966353851997923e-07,
      "loss": 0.0012,
      "reward": 1.8651032447814941,
      "reward_std": 0.1377798616886139,
      "rewards/accuracy_reward": 0.7057281732559204,
      "rewards/format_reward": 1.0,
      "step": 1215,
      "temperature": 1.0
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.0,
      "completion_length": 419.5625,
      "epoch": 0.03697846977253375,
      "grad_norm": 1.0880074538339308,
      "kl": 0.02392578125,
      "learning_rate": 9.966298506927872e-07,
      "loss": 0.001,
      "reward": 1.787438154220581,
      "reward_std": 0.21425844728946686,
      "rewards/accuracy_reward": 0.6655632257461548,
      "rewards/format_reward": 1.0,
      "step": 1216,
      "temperature": 1.0
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.125,
      "completion_length": 374.015625,
      "epoch": 0.03700887969833354,
      "grad_norm": 3.861972156329695,
      "kl": 0.02685546875,
      "learning_rate": 9.966243116530166e-07,
      "loss": 0.0011,
      "reward": 1.7696444988250732,
      "reward_std": 0.15385319292545319,
      "rewards/accuracy_reward": 0.6352695226669312,
      "rewards/format_reward": 1.0,
      "step": 1217,
      "temperature": 1.0
    },
    {
      "all_correct": 0.375,
      "all_wrong": 0.25,
      "completion_length": 413.0625,
      "epoch": 0.03703928962413332,
      "grad_norm": 0.906261229520691,
      "kl": 0.028564453125,
      "learning_rate": 9.966187680805306e-07,
      "loss": 0.0011,
      "reward": 1.5482540130615234,
      "reward_std": 0.15232303738594055,
      "rewards/accuracy_reward": 0.45762890577316284,
      "rewards/format_reward": 1.0,
      "step": 1218,
      "temperature": 1.0
    },
    {
      "all_correct": 0.75,
      "all_wrong": 0.0,
      "completion_length": 360.515625,
      "epoch": 0.0370696995499331,
      "grad_norm": 1.7421324539687955,
      "kl": 0.036376953125,
      "learning_rate": 9.966132199753801e-07,
      "loss": 0.0015,
      "reward": 2.078726053237915,
      "reward_std": 0.10794822126626968,
      "rewards/accuracy_reward": 0.8943510055541992,
      "rewards/format_reward": 1.0,
      "step": 1219,
      "temperature": 1.0
    },
    {
      "all_correct": 0.75,
      "all_wrong": 0.0,
      "completion_length": 370.953125,
      "epoch": 0.037100109475732876,
      "grad_norm": 0.5037320591843865,
      "kl": 0.0284423828125,
      "learning_rate": 9.966076673376154e-07,
      "loss": 0.0011,
      "reward": 2.046875,
      "reward_std": 0.09722718596458435,
      "rewards/accuracy_reward": 0.875,
      "rewards/format_reward": 1.0,
      "step": 1220,
      "temperature": 1.0
    },
    {
      "all_correct": 0.375,
      "all_wrong": 0.125,
      "completion_length": 373.28125,
      "epoch": 0.03713051940153266,
      "grad_norm": 2.1830184615082286,
      "kl": 0.03076171875,
      "learning_rate": 9.96602110167287e-07,
      "loss": 0.0012,
      "reward": 1.8402504920959473,
      "reward_std": 0.11787135899066925,
      "rewards/accuracy_reward": 0.6715005040168762,
      "rewards/format_reward": 1.0,
      "step": 1221,
      "temperature": 1.0
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.25,
      "completion_length": 364.8125,
      "epoch": 0.03716092932733244,
      "grad_norm": 0.6624015563055085,
      "kl": 0.032470703125,
      "learning_rate": 9.965965484644463e-07,
      "loss": 0.0013,
      "reward": 1.6531250476837158,
      "reward_std": 0.11363068222999573,
      "rewards/accuracy_reward": 0.546875,
      "rewards/format_reward": 1.0,
      "step": 1222,
      "temperature": 1.0
    },
    {
      "all_correct": 0.75,
      "all_wrong": 0.0,
      "completion_length": 374.296875,
      "epoch": 0.03719133925313222,
      "grad_norm": 0.6628709858215975,
      "kl": 0.0301513671875,
      "learning_rate": 9.965909822291436e-07,
      "loss": 0.0012,
      "reward": 2.046875,
      "reward_std": 0.1374930739402771,
      "rewards/accuracy_reward": 0.875,
      "rewards/format_reward": 1.0,
      "step": 1223,
      "temperature": 1.0
    },
    {
      "all_correct": 0.625,
      "all_wrong": 0.125,
      "completion_length": 376.328125,
      "epoch": 0.037221749178932007,
      "grad_norm": 0.7873412826967261,
      "kl": 0.0244140625,
      "learning_rate": 9.9658541146143e-07,
      "loss": 0.001,
      "reward": 1.96875,
      "reward_std": 0.1293872892856598,
      "rewards/accuracy_reward": 0.8125,
      "rewards/format_reward": 1.0,
      "step": 1224,
      "temperature": 1.0
    },
    {
      "all_correct": 0.75,
      "all_wrong": 0.0,
      "completion_length": 393.671875,
      "epoch": 0.037252159104731786,
      "grad_norm": 0.7330801616056122,
      "kl": 0.036865234375,
      "learning_rate": 9.965798361613558e-07,
      "loss": 0.0015,
      "reward": 2.0437426567077637,
      "reward_std": 0.01713588461279869,
      "rewards/accuracy_reward": 0.8499925136566162,
      "rewards/format_reward": 1.0,
      "step": 1225,
      "temperature": 1.0
    },
    {
      "all_correct": 0.625,
      "all_wrong": 0.25,
      "completion_length": 373.765625,
      "epoch": 0.037282569030531565,
      "grad_norm": 0.29470607435970175,
      "kl": 0.03173828125,
      "learning_rate": 9.965742563289723e-07,
      "loss": 0.0013,
      "reward": 1.8593751192092896,
      "reward_std": 0.06805657595396042,
      "rewards/accuracy_reward": 0.71875,
      "rewards/format_reward": 1.0,
      "step": 1226,
      "temperature": 1.0
    },
    {
      "all_correct": 0.375,
      "all_wrong": 0.25,
      "completion_length": 373.765625,
      "epoch": 0.037312978956331344,
      "grad_norm": 0.7671066076076499,
      "kl": 0.0284423828125,
      "learning_rate": 9.965686719643306e-07,
      "loss": 0.0011,
      "reward": 1.6811611652374268,
      "reward_std": 0.13532957434654236,
      "rewards/accuracy_reward": 0.5530362129211426,
      "rewards/format_reward": 1.0,
      "step": 1227,
      "temperature": 1.0
    },
    {
      "all_correct": 0.75,
      "all_wrong": 0.0,
      "completion_length": 413.875,
      "epoch": 0.03734338888213113,
      "grad_norm": 0.5839433990046675,
      "kl": 0.0269775390625,
      "learning_rate": 9.965630830674811e-07,
      "loss": 0.0011,
      "reward": 2.007234811782837,
      "reward_std": 0.059669144451618195,
      "rewards/accuracy_reward": 0.8322348594665527,
      "rewards/format_reward": 1.0,
      "step": 1228,
      "temperature": 1.0
    },
    {
      "all_correct": 0.625,
      "all_wrong": 0.125,
      "completion_length": 398.296875,
      "epoch": 0.03737379880793091,
      "grad_norm": 1.04504483458555,
      "kl": 0.0302734375,
      "learning_rate": 9.965574896384752e-07,
      "loss": 0.0012,
      "reward": 1.8041876554489136,
      "reward_std": 0.07023001462221146,
      "rewards/accuracy_reward": 0.6635626554489136,
      "rewards/format_reward": 1.0,
      "step": 1229,
      "temperature": 1.0
    },
    {
      "all_correct": 0.75,
      "all_wrong": 0.125,
      "completion_length": 379.96875,
      "epoch": 0.03740420873373069,
      "grad_norm": 0.9801820992728698,
      "kl": 0.027587890625,
      "learning_rate": 9.96551891677364e-07,
      "loss": 0.0011,
      "reward": 1.927573561668396,
      "reward_std": 0.08493957668542862,
      "rewards/accuracy_reward": 0.7775735259056091,
      "rewards/format_reward": 1.0,
      "step": 1230,
      "temperature": 1.0
    },
    {
      "all_correct": 0.625,
      "all_wrong": 0.125,
      "completion_length": 361.53125,
      "epoch": 0.03743461865953047,
      "grad_norm": 0.9744591801053886,
      "kl": 0.034423828125,
      "learning_rate": 9.965462891841985e-07,
      "loss": 0.0014,
      "reward": 1.8536531925201416,
      "reward_std": 0.07960119098424911,
      "rewards/accuracy_reward": 0.6974031925201416,
      "rewards/format_reward": 1.0,
      "step": 1231,
      "temperature": 1.0
    },
    {
      "all_correct": 0.375,
      "all_wrong": 0.125,
      "completion_length": 401.890625,
      "epoch": 0.037465028585330254,
      "grad_norm": 1.190577939491672,
      "kl": 0.0299072265625,
      "learning_rate": 9.965406821590297e-07,
      "loss": 0.0012,
      "reward": 1.827261209487915,
      "reward_std": 0.1324939727783203,
      "rewards/accuracy_reward": 0.6678860783576965,
      "rewards/format_reward": 1.0,
      "step": 1232,
      "temperature": 1.0
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.25,
      "completion_length": 352.140625,
      "epoch": 0.03749543851113003,
      "grad_norm": 1.0470058319377902,
      "kl": 0.032470703125,
      "learning_rate": 9.965350706019089e-07,
      "loss": 0.0013,
      "reward": 1.8218339681625366,
      "reward_std": 0.03220607712864876,
      "rewards/accuracy_reward": 0.6749589443206787,
      "rewards/format_reward": 1.0,
      "step": 1233,
      "temperature": 1.0
    },
    {
      "all_correct": 0.625,
      "all_wrong": 0.0,
      "completion_length": 390.578125,
      "epoch": 0.03752584843692981,
      "grad_norm": 1.035546006376402,
      "kl": 0.0296630859375,
      "learning_rate": 9.965294545128874e-07,
      "loss": 0.0012,
      "reward": 1.9316580295562744,
      "reward_std": 0.10213324427604675,
      "rewards/accuracy_reward": 0.7566580176353455,
      "rewards/format_reward": 1.0,
      "step": 1234,
      "temperature": 1.0
    },
    {
      "all_correct": 0.375,
      "all_wrong": 0.125,
      "completion_length": 371.578125,
      "epoch": 0.03755625836272959,
      "grad_norm": 1.4642897719935828,
      "kl": 0.03076171875,
      "learning_rate": 9.965238338920164e-07,
      "loss": 0.0012,
      "reward": 1.7755050659179688,
      "reward_std": 0.22341889142990112,
      "rewards/accuracy_reward": 0.6692550778388977,
      "rewards/format_reward": 0.984375,
      "step": 1235,
      "temperature": 1.0
    },
    {
      "all_correct": 0.125,
      "all_wrong": 0.0,
      "completion_length": 383.484375,
      "epoch": 0.03758666828852938,
      "grad_norm": 7.040237983053658,
      "kl": 0.030029296875,
      "learning_rate": 9.96518208739347e-07,
      "loss": 0.0012,
      "reward": 1.5384817123413086,
      "reward_std": 0.315449059009552,
      "rewards/accuracy_reward": 0.41973167657852173,
      "rewards/format_reward": 1.0,
      "step": 1236,
      "temperature": 1.0
    },
    {
      "all_correct": 0.75,
      "all_wrong": 0.25,
      "completion_length": 353.296875,
      "epoch": 0.03761707821432916,
      "grad_norm": 0.530121268428862,
      "kl": 0.031982421875,
      "learning_rate": 9.965125790549306e-07,
      "loss": 0.0013,
      "reward": 1.8968749046325684,
      "reward_std": 0.008838837966322899,
      "rewards/accuracy_reward": 0.75,
      "rewards/format_reward": 1.0,
      "step": 1237,
      "temperature": 1.0
    },
    {
      "all_correct": 0.25,
      "all_wrong": 0.125,
      "completion_length": 366.078125,
      "epoch": 0.037647488140128936,
      "grad_norm": 2.641844831376638,
      "kl": 0.03466796875,
      "learning_rate": 9.96506944838819e-07,
      "loss": 0.0014,
      "reward": 1.5409669876098633,
      "reward_std": 0.17587411403656006,
      "rewards/accuracy_reward": 0.43471699953079224,
      "rewards/format_reward": 1.0,
      "step": 1238,
      "temperature": 1.0
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.125,
      "completion_length": 368.984375,
      "epoch": 0.03767789806592872,
      "grad_norm": 10.781444891274246,
      "kl": 0.0267333984375,
      "learning_rate": 9.965013060910632e-07,
      "loss": 0.0011,
      "reward": 1.7990696430206299,
      "reward_std": 0.12815704941749573,
      "rewards/accuracy_reward": 0.667819619178772,
      "rewards/format_reward": 1.0,
      "step": 1239,
      "temperature": 1.0
    },
    {
      "all_correct": 0.25,
      "all_wrong": 0.125,
      "completion_length": 369.921875,
      "epoch": 0.0377083079917285,
      "grad_norm": 1.3664953017098478,
      "kl": 0.031982421875,
      "learning_rate": 9.964956628117147e-07,
      "loss": 0.0013,
      "reward": 1.7144029140472412,
      "reward_std": 0.16515496373176575,
      "rewards/accuracy_reward": 0.570652961730957,
      "rewards/format_reward": 1.0,
      "step": 1240,
      "temperature": 1.0
    },
    {
      "all_correct": 0.625,
      "all_wrong": 0.125,
      "completion_length": 336.6875,
      "epoch": 0.03773871791752828,
      "grad_norm": 1.6518992062464046,
      "kl": 0.034912109375,
      "learning_rate": 9.96490015000825e-07,
      "loss": 0.0014,
      "reward": 1.9328126907348633,
      "reward_std": 0.1499861478805542,
      "rewards/accuracy_reward": 0.8046875,
      "rewards/format_reward": 1.0,
      "step": 1241,
      "temperature": 1.0
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.125,
      "completion_length": 360.453125,
      "epoch": 0.03776912784332806,
      "grad_norm": 1.8315896123879818,
      "kl": 0.0322265625,
      "learning_rate": 9.964843626584459e-07,
      "loss": 0.0013,
      "reward": 1.7527251243591309,
      "reward_std": 0.056719888001680374,
      "rewards/accuracy_reward": 0.6089749932289124,
      "rewards/format_reward": 1.0,
      "step": 1242,
      "temperature": 1.0
    },
    {
      "all_correct": 0.625,
      "all_wrong": 0.25,
      "completion_length": 360.40625,
      "epoch": 0.037799537769127846,
      "grad_norm": 0.9440690682440332,
      "kl": 0.0284423828125,
      "learning_rate": 9.96478705784629e-07,
      "loss": 0.0011,
      "reward": 1.820537805557251,
      "reward_std": 0.014862941578030586,
      "rewards/accuracy_reward": 0.6736628413200378,
      "rewards/format_reward": 1.0,
      "step": 1243,
      "temperature": 1.0
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.0,
      "completion_length": 365.609375,
      "epoch": 0.037829947694927625,
      "grad_norm": 4.170969734855603,
      "kl": 0.0308837890625,
      "learning_rate": 9.964730443794254e-07,
      "loss": 0.0012,
      "reward": 1.7946250438690186,
      "reward_std": 0.059131920337677,
      "rewards/accuracy_reward": 0.6446249485015869,
      "rewards/format_reward": 1.0,
      "step": 1244,
      "temperature": 1.0
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.125,
      "completion_length": 367.609375,
      "epoch": 0.037860357620727404,
      "grad_norm": 0.8027578930664081,
      "kl": 0.0216064453125,
      "learning_rate": 9.964673784428872e-07,
      "loss": 0.0009,
      "reward": 1.7999999523162842,
      "reward_std": 0.20830951631069183,
      "rewards/accuracy_reward": 0.671875,
      "rewards/format_reward": 1.0,
      "step": 1245,
      "temperature": 1.0
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.0,
      "completion_length": 368.359375,
      "epoch": 0.03789076754652718,
      "grad_norm": 1.4802423240245264,
      "kl": 0.0269775390625,
      "learning_rate": 9.964617079750662e-07,
      "loss": 0.0011,
      "reward": 1.9007866382598877,
      "reward_std": 0.10542438179254532,
      "rewards/accuracy_reward": 0.7382866144180298,
      "rewards/format_reward": 1.0,
      "step": 1246,
      "temperature": 1.0
    },
    {
      "all_correct": 0.625,
      "all_wrong": 0.125,
      "completion_length": 359.71875,
      "epoch": 0.03792117747232697,
      "grad_norm": 1.2888714387797215,
      "kl": 0.034423828125,
      "learning_rate": 9.964560329760137e-07,
      "loss": 0.0014,
      "reward": 1.8350915908813477,
      "reward_std": 0.0758938416838646,
      "rewards/accuracy_reward": 0.6975915431976318,
      "rewards/format_reward": 1.0,
      "step": 1247,
      "temperature": 1.0
    },
    {
      "all_correct": 0.625,
      "all_wrong": 0.0,
      "completion_length": 387.078125,
      "epoch": 0.03795158739812675,
      "grad_norm": 1.3056266517770545,
      "kl": 0.033447265625,
      "learning_rate": 9.96450353445782e-07,
      "loss": 0.0013,
      "reward": 2.0613996982574463,
      "reward_std": 0.1021379679441452,
      "rewards/accuracy_reward": 0.8801496028900146,
      "rewards/format_reward": 1.0,
      "step": 1248,
      "temperature": 1.0
    },
    {
      "all_correct": 0.75,
      "all_wrong": 0.0,
      "completion_length": 356.828125,
      "epoch": 0.03798199732392653,
      "grad_norm": 0.6565394948757017,
      "kl": 0.03369140625,
      "learning_rate": 9.964446693844226e-07,
      "loss": 0.0013,
      "reward": 2.049384355545044,
      "reward_std": 0.08088602870702744,
      "rewards/accuracy_reward": 0.8587594032287598,
      "rewards/format_reward": 1.0,
      "step": 1249,
      "temperature": 1.0
    },
    {
      "all_correct": 0.375,
      "all_wrong": 0.25,
      "completion_length": 391.390625,
      "epoch": 0.038012407249726314,
      "grad_norm": 0.6279364459235974,
      "kl": 0.0224609375,
      "learning_rate": 9.964389807919877e-07,
      "loss": 0.0009,
      "reward": 1.7124006748199463,
      "reward_std": 0.15352453291416168,
      "rewards/accuracy_reward": 0.5967757701873779,
      "rewards/format_reward": 1.0,
      "step": 1250,
      "temperature": 1.0
    },
    {
      "all_correct": 0.75,
      "all_wrong": 0.125,
      "completion_length": 360.734375,
      "epoch": 0.03804281717552609,
      "grad_norm": 0.571488166215603,
      "kl": 0.028564453125,
      "learning_rate": 9.964332876685288e-07,
      "loss": 0.0011,
      "reward": 1.9156250953674316,
      "reward_std": 0.04419417306780815,
      "rewards/accuracy_reward": 0.765625,
      "rewards/format_reward": 1.0,
      "step": 1251,
      "temperature": 1.0
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.125,
      "completion_length": 384.484375,
      "epoch": 0.03807322710132587,
      "grad_norm": 0.86930372825186,
      "kl": 0.026123046875,
      "learning_rate": 9.964275900140983e-07,
      "loss": 0.001,
      "reward": 1.76670241355896,
      "reward_std": 0.13029633462429047,
      "rewards/accuracy_reward": 0.6323273777961731,
      "rewards/format_reward": 1.0,
      "step": 1252,
      "temperature": 1.0
    },
    {
      "all_correct": 0.625,
      "all_wrong": 0.0,
      "completion_length": 386.03125,
      "epoch": 0.03810363702712565,
      "grad_norm": 1.0540194890672043,
      "kl": 0.0322265625,
      "learning_rate": 9.964218878287478e-07,
      "loss": 0.0013,
      "reward": 2.004464864730835,
      "reward_std": 0.05205019190907478,
      "rewards/accuracy_reward": 0.8044646978378296,
      "rewards/format_reward": 1.0,
      "step": 1253,
      "temperature": 1.0
    },
    {
      "all_correct": 0.75,
      "all_wrong": 0.125,
      "completion_length": 362.53125,
      "epoch": 0.03813404695292544,
      "grad_norm": 0.32555587211172576,
      "kl": 0.0302734375,
      "learning_rate": 9.964161811125296e-07,
      "loss": 0.0012,
      "reward": 2.012500047683716,
      "reward_std": 0.06943650543689728,
      "rewards/accuracy_reward": 0.84375,
      "rewards/format_reward": 1.0,
      "step": 1254,
      "temperature": 1.0
    },
    {
      "all_correct": 0.75,
      "all_wrong": 0.125,
      "completion_length": 386.015625,
      "epoch": 0.03816445687872522,
      "grad_norm": 0.9538431294251063,
      "kl": 0.02587890625,
      "learning_rate": 9.964104698654958e-07,
      "loss": 0.001,
      "reward": 1.943750023841858,
      "reward_std": 0.07353248447179794,
      "rewards/accuracy_reward": 0.796875,
      "rewards/format_reward": 1.0,
      "step": 1255,
      "temperature": 1.0
    },
    {
      "all_correct": 0.75,
      "all_wrong": 0.125,
      "completion_length": 362.703125,
      "epoch": 0.038194866804524996,
      "grad_norm": 0.5389047522384508,
      "kl": 0.031982421875,
      "learning_rate": 9.964047540876984e-07,
      "loss": 0.0013,
      "reward": 1.9156250953674316,
      "reward_std": 0.04419417306780815,
      "rewards/accuracy_reward": 0.765625,
      "rewards/format_reward": 1.0,
      "step": 1256,
      "temperature": 1.0
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.125,
      "completion_length": 363.453125,
      "epoch": 0.038225276730324775,
      "grad_norm": 1.1029472720095477,
      "kl": 0.0390625,
      "learning_rate": 9.963990337791895e-07,
      "loss": 0.0016,
      "reward": 1.788149118423462,
      "reward_std": 0.11239831149578094,
      "rewards/accuracy_reward": 0.6381491422653198,
      "rewards/format_reward": 1.0,
      "step": 1257,
      "temperature": 1.0
    },
    {
      "all_correct": 0.375,
      "all_wrong": 0.375,
      "completion_length": 412.859375,
      "epoch": 0.03825568665612456,
      "grad_norm": 0.38396649116414483,
      "kl": 0.0257568359375,
      "learning_rate": 9.963933089400215e-07,
      "loss": 0.001,
      "reward": 1.59375,
      "reward_std": 0.12730026245117188,
      "rewards/accuracy_reward": 0.5,
      "rewards/format_reward": 1.0,
      "step": 1258,
      "temperature": 1.0
    },
    {
      "all_correct": 0.75,
      "all_wrong": 0.125,
      "completion_length": 351.375,
      "epoch": 0.03828609658192434,
      "grad_norm": 0.732037344403108,
      "kl": 0.033935546875,
      "learning_rate": 9.963875795702466e-07,
      "loss": 0.0014,
      "reward": 2.0218751430511475,
      "reward_std": 0.0659717470407486,
      "rewards/accuracy_reward": 0.859375,
      "rewards/format_reward": 1.0,
      "step": 1259,
      "temperature": 1.0
    },
    {
      "all_correct": 0.625,
      "all_wrong": 0.0,
      "completion_length": 380.03125,
      "epoch": 0.03831650650772412,
      "grad_norm": 1.2927377093265666,
      "kl": 0.02880859375,
      "learning_rate": 9.963818456699169e-07,
      "loss": 0.0012,
      "reward": 2.0321199893951416,
      "reward_std": 0.054939642548561096,
      "rewards/accuracy_reward": 0.8414947986602783,
      "rewards/format_reward": 1.0,
      "step": 1260,
      "temperature": 1.0
    },
    {
      "all_correct": 0.25,
      "all_wrong": 0.25,
      "completion_length": 385.734375,
      "epoch": 0.0383469164335239,
      "grad_norm": 2.7591561724178435,
      "kl": 0.03369140625,
      "learning_rate": 9.963761072390852e-07,
      "loss": 0.0013,
      "reward": 1.5007102489471436,
      "reward_std": 0.1544691026210785,
      "rewards/accuracy_reward": 0.4007102847099304,
      "rewards/format_reward": 1.0,
      "step": 1261,
      "temperature": 1.0
    },
    {
      "all_correct": 0.25,
      "all_wrong": 0.25,
      "completion_length": 378.71875,
      "epoch": 0.038377326359323685,
      "grad_norm": 1.444546466930967,
      "kl": 0.0322265625,
      "learning_rate": 9.963703642778033e-07,
      "loss": 0.0013,
      "reward": 1.5905085802078247,
      "reward_std": 0.15695898234844208,
      "rewards/accuracy_reward": 0.46550852060317993,
      "rewards/format_reward": 1.0,
      "step": 1262,
      "temperature": 1.0
    },
    {
      "all_correct": 0.625,
      "all_wrong": 0.375,
      "completion_length": 368.1875,
      "epoch": 0.038407736285123464,
      "grad_norm": 0.5595674624429317,
      "kl": 0.0281982421875,
      "learning_rate": 9.96364616786124e-07,
      "loss": 0.0011,
      "reward": 1.7468750476837158,
      "reward_std": 0.008838837966322899,
      "rewards/accuracy_reward": 0.625,
      "rewards/format_reward": 1.0,
      "step": 1263,
      "temperature": 1.0
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.0,
      "completion_length": 357.390625,
      "epoch": 0.038438146210923244,
      "grad_norm": 1.1833190077655955,
      "kl": 0.033447265625,
      "learning_rate": 9.963588647640995e-07,
      "loss": 0.0013,
      "reward": 1.7588131427764893,
      "reward_std": 0.17466342449188232,
      "rewards/accuracy_reward": 0.6119380593299866,
      "rewards/format_reward": 1.0,
      "step": 1264,
      "temperature": 1.0
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.0,
      "completion_length": 348.375,
      "epoch": 0.03846855613672303,
      "grad_norm": 1.602818390916467,
      "kl": 0.0322265625,
      "learning_rate": 9.963531082117826e-07,
      "loss": 0.0013,
      "reward": 1.8966145515441895,
      "reward_std": 0.18168765306472778,
      "rewards/accuracy_reward": 0.7528645992279053,
      "rewards/format_reward": 1.0,
      "step": 1265,
      "temperature": 1.0
    },
    {
      "all_correct": 0.625,
      "all_wrong": 0.125,
      "completion_length": 353.859375,
      "epoch": 0.03849896606252281,
      "grad_norm": 0.6380081656374837,
      "kl": 0.0306396484375,
      "learning_rate": 9.963473471292257e-07,
      "loss": 0.0012,
      "reward": 1.9627233743667603,
      "reward_std": 0.008838835172355175,
      "rewards/accuracy_reward": 0.7908483743667603,
      "rewards/format_reward": 1.0,
      "step": 1266,
      "temperature": 1.0
    },
    {
      "all_correct": 0.25,
      "all_wrong": 0.125,
      "completion_length": 378.15625,
      "epoch": 0.03852937598832259,
      "grad_norm": 2.10252359125003,
      "kl": 0.037109375,
      "learning_rate": 9.963415815164814e-07,
      "loss": 0.0015,
      "reward": 1.583824634552002,
      "reward_std": 0.2249050736427307,
      "rewards/accuracy_reward": 0.46819961071014404,
      "rewards/format_reward": 1.0,
      "step": 1267,
      "temperature": 1.0
    },
    {
      "all_correct": 0.25,
      "all_wrong": 0.5,
      "completion_length": 359.90625,
      "epoch": 0.03855978591412237,
      "grad_norm": 1.0805066568184425,
      "kl": 0.03369140625,
      "learning_rate": 9.963358113736022e-07,
      "loss": 0.0014,
      "reward": 1.4713525772094727,
      "reward_std": 0.08763913810253143,
      "rewards/accuracy_reward": 0.38697749376296997,
      "rewards/format_reward": 1.0,
      "step": 1268,
      "temperature": 1.0
    },
    {
      "all_correct": 0.25,
      "all_wrong": 0.25,
      "completion_length": 356.0,
      "epoch": 0.03859019583992215,
      "grad_norm": 0.9904265559039437,
      "kl": 0.0303955078125,
      "learning_rate": 9.963300367006409e-07,
      "loss": 0.0012,
      "reward": 1.5116394758224487,
      "reward_std": 0.11188942193984985,
      "rewards/accuracy_reward": 0.41163942217826843,
      "rewards/format_reward": 1.0,
      "step": 1269,
      "temperature": 1.0
    },
    {
      "all_correct": 0.75,
      "all_wrong": 0.0,
      "completion_length": 352.703125,
      "epoch": 0.03862060576572193,
      "grad_norm": 1.166406805130573,
      "kl": 0.03271484375,
      "learning_rate": 9.9632425749765e-07,
      "loss": 0.0013,
      "reward": 1.9444780349731445,
      "reward_std": 0.1057472825050354,
      "rewards/accuracy_reward": 0.7788530588150024,
      "rewards/format_reward": 1.0,
      "step": 1270,
      "temperature": 1.0
    },
    {
      "all_correct": 0.625,
      "all_wrong": 0.375,
      "completion_length": 356.265625,
      "epoch": 0.03865101569152171,
      "grad_norm": 0.057644823582353386,
      "kl": 0.027099609375,
      "learning_rate": 9.963184737646826e-07,
      "loss": 0.0011,
      "reward": 1.75,
      "reward_std": 0.0,
      "rewards/accuracy_reward": 0.625,
      "rewards/format_reward": 1.0,
      "step": 1271,
      "temperature": 1.0
    },
    {
      "all_correct": 0.75,
      "all_wrong": 0.0,
      "completion_length": 348.875,
      "epoch": 0.03868142561732149,
      "grad_norm": 1.1198136967958012,
      "kl": 0.033203125,
      "learning_rate": 9.96312685501791e-07,
      "loss": 0.0013,
      "reward": 1.9925200939178467,
      "reward_std": 0.040434785187244415,
      "rewards/accuracy_reward": 0.8175201416015625,
      "rewards/format_reward": 1.0,
      "step": 1272,
      "temperature": 1.0
    },
    {
      "all_correct": 0.75,
      "all_wrong": 0.125,
      "completion_length": 389.703125,
      "epoch": 0.03871183554312128,
      "grad_norm": 0.7362419005442138,
      "kl": 0.032470703125,
      "learning_rate": 9.963068927090287e-07,
      "loss": 0.0013,
      "reward": 1.8125,
      "reward_std": 0.11499667167663574,
      "rewards/accuracy_reward": 0.765625,
      "rewards/format_reward": 0.90625,
      "step": 1273,
      "temperature": 1.0
    },
    {
      "all_correct": 0.375,
      "all_wrong": 0.125,
      "completion_length": 406.375,
      "epoch": 0.038742245468921056,
      "grad_norm": 0.865928850864484,
      "kl": 0.02685546875,
      "learning_rate": 9.963010953864481e-07,
      "loss": 0.0011,
      "reward": 1.7434850931167603,
      "reward_std": 0.08635497093200684,
      "rewards/accuracy_reward": 0.5997350811958313,
      "rewards/format_reward": 1.0,
      "step": 1274,
      "temperature": 1.0
    },
    {
      "all_correct": 0.625,
      "all_wrong": 0.125,
      "completion_length": 358.078125,
      "epoch": 0.038772655394720835,
      "grad_norm": 1.0034849049090346,
      "kl": 0.0302734375,
      "learning_rate": 9.962952935341022e-07,
      "loss": 0.0012,
      "reward": 1.953125,
      "reward_std": 0.14205020666122437,
      "rewards/accuracy_reward": 0.796875,
      "rewards/format_reward": 1.0,
      "step": 1275,
      "temperature": 1.0
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.25,
      "completion_length": 374.65625,
      "epoch": 0.038803065320520615,
      "grad_norm": 2.2836808464223552,
      "kl": 0.03466796875,
      "learning_rate": 9.962894871520439e-07,
      "loss": 0.0014,
      "reward": 1.7178198099136353,
      "reward_std": 0.023216933012008667,
      "rewards/accuracy_reward": 0.5740697979927063,
      "rewards/format_reward": 1.0,
      "step": 1276,
      "temperature": 1.0
    },
    {
      "all_correct": 0.25,
      "all_wrong": 0.375,
      "completion_length": 423.96875,
      "epoch": 0.0388334752463204,
      "grad_norm": 0.8396630741137664,
      "kl": 0.0238037109375,
      "learning_rate": 9.962836762403263e-07,
      "loss": 0.001,
      "reward": 1.4961453676223755,
      "reward_std": 0.1826830357313156,
      "rewards/accuracy_reward": 0.41489535570144653,
      "rewards/format_reward": 0.984375,
      "step": 1277,
      "temperature": 1.0
    },
    {
      "all_correct": 0.875,
      "all_wrong": 0.0,
      "completion_length": 361.734375,
      "epoch": 0.03886388517212018,
      "grad_norm": 0.6423896831532357,
      "kl": 0.039794921875,
      "learning_rate": 9.962778607990024e-07,
      "loss": 0.0016,
      "reward": 2.1280763149261475,
      "reward_std": 0.015616388991475105,
      "rewards/accuracy_reward": 0.9312012791633606,
      "rewards/format_reward": 1.0,
      "step": 1278,
      "temperature": 1.0
    },
    {
      "all_correct": 0.25,
      "all_wrong": 0.375,
      "completion_length": 353.90625,
      "epoch": 0.03889429509791996,
      "grad_norm": 2.1235720959667717,
      "kl": 0.03515625,
      "learning_rate": 9.962720408281252e-07,
      "loss": 0.0014,
      "reward": 1.3937880992889404,
      "reward_std": 0.12773333489894867,
      "rewards/accuracy_reward": 0.3156631588935852,
      "rewards/format_reward": 1.0,
      "step": 1279,
      "temperature": 1.0
    },
    {
      "all_correct": 0.625,
      "all_wrong": 0.0,
      "completion_length": 362.453125,
      "epoch": 0.038924705023719745,
      "grad_norm": 1.0389428900399809,
      "kl": 0.036376953125,
      "learning_rate": 9.96266216327748e-07,
      "loss": 0.0015,
      "reward": 1.963141679763794,
      "reward_std": 0.029613522812724113,
      "rewards/accuracy_reward": 0.7631416320800781,
      "rewards/format_reward": 1.0,
      "step": 1280,
      "temperature": 1.0
    },
    {
      "all_correct": 0.375,
      "all_wrong": 0.125,
      "completion_length": 390.140625,
      "epoch": 0.038955114949519525,
      "grad_norm": 1.1055251004611069,
      "kl": 0.030517578125,
      "learning_rate": 9.962603872979238e-07,
      "loss": 0.0012,
      "reward": 1.6734874248504639,
      "reward_std": 0.16549795866012573,
      "rewards/accuracy_reward": 0.5328624248504639,
      "rewards/format_reward": 1.0,
      "step": 1281,
      "temperature": 1.0
    },
    {
      "all_correct": 0.75,
      "all_wrong": 0.125,
      "completion_length": 362.390625,
      "epoch": 0.038985524875319304,
      "grad_norm": 0.4316540582810598,
      "kl": 0.034423828125,
      "learning_rate": 9.962545537387058e-07,
      "loss": 0.0014,
      "reward": 1.9568827152252197,
      "reward_std": 0.0059239245019853115,
      "rewards/accuracy_reward": 0.7818825840950012,
      "rewards/format_reward": 1.0,
      "step": 1282,
      "temperature": 1.0
    },
    {
      "all_correct": 0.75,
      "all_wrong": 0.125,
      "completion_length": 353.484375,
      "epoch": 0.03901593480111908,
      "grad_norm": 0.9183092673750451,
      "kl": 0.039306640625,
      "learning_rate": 9.962487156501474e-07,
      "loss": 0.0016,
      "reward": 1.9093750715255737,
      "reward_std": 0.06187184900045395,
      "rewards/accuracy_reward": 0.765625,
      "rewards/format_reward": 1.0,
      "step": 1283,
      "temperature": 1.0
    },
    {
      "all_correct": 0.375,
      "all_wrong": 0.25,
      "completion_length": 398.046875,
      "epoch": 0.03904634472691887,
      "grad_norm": 1.7521040314494982,
      "kl": 0.031005859375,
      "learning_rate": 9.962428730323017e-07,
      "loss": 0.0012,
      "reward": 1.639801025390625,
      "reward_std": 0.11338851600885391,
      "rewards/accuracy_reward": 0.533551037311554,
      "rewards/format_reward": 0.984375,
      "step": 1284,
      "temperature": 1.0
    },
    {
      "all_correct": 0.75,
      "all_wrong": 0.125,
      "completion_length": 388.296875,
      "epoch": 0.03907675465271865,
      "grad_norm": 0.7235301366831329,
      "kl": 0.039794921875,
      "learning_rate": 9.96237025885222e-07,
      "loss": 0.0016,
      "reward": 1.8937499523162842,
      "reward_std": 0.0530330054461956,
      "rewards/accuracy_reward": 0.765625,
      "rewards/format_reward": 1.0,
      "step": 1285,
      "temperature": 1.0
    },
    {
      "all_correct": 0.75,
      "all_wrong": 0.125,
      "completion_length": 373.40625,
      "epoch": 0.03910716457851843,
      "grad_norm": 0.5115175019287024,
      "kl": 0.041015625,
      "learning_rate": 9.96231174208962e-07,
      "loss": 0.0016,
      "reward": 2.003525733947754,
      "reward_std": 0.005139642860740423,
      "rewards/accuracy_reward": 0.8285256624221802,
      "rewards/format_reward": 1.0,
      "step": 1286,
      "temperature": 1.0
    },
    {
      "all_correct": 0.75,
      "all_wrong": 0.0,
      "completion_length": 366.234375,
      "epoch": 0.03913757450431821,
      "grad_norm": 0.50161282244396,
      "kl": 0.03857421875,
      "learning_rate": 9.962253180035747e-07,
      "loss": 0.0015,
      "reward": 2.0642921924591064,
      "reward_std": 0.0130257373675704,
      "rewards/accuracy_reward": 0.8642921447753906,
      "rewards/format_reward": 1.0,
      "step": 1287,
      "temperature": 1.0
    },
    {
      "all_correct": 0.25,
      "all_wrong": 0.125,
      "completion_length": 412.0625,
      "epoch": 0.03916798443011799,
      "grad_norm": 0.607991605189762,
      "kl": 0.03173828125,
      "learning_rate": 9.962194572691139e-07,
      "loss": 0.0013,
      "reward": 1.7259693145751953,
      "reward_std": 0.1509249210357666,
      "rewards/accuracy_reward": 0.5853441953659058,
      "rewards/format_reward": 1.0,
      "step": 1288,
      "temperature": 1.0
    },
    {
      "all_correct": 0.625,
      "all_wrong": 0.125,
      "completion_length": 400.796875,
      "epoch": 0.03919839435591777,
      "grad_norm": 0.7244747857353911,
      "kl": 0.0274658203125,
      "learning_rate": 9.962135920056328e-07,
      "loss": 0.0011,
      "reward": 1.9484374523162842,
      "reward_std": 0.147711843252182,
      "rewards/accuracy_reward": 0.7890625,
      "rewards/format_reward": 1.0,
      "step": 1289,
      "temperature": 1.0
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.25,
      "completion_length": 406.5625,
      "epoch": 0.03922880428171755,
      "grad_norm": 0.7626932135649339,
      "kl": 0.030517578125,
      "learning_rate": 9.962077222131852e-07,
      "loss": 0.0012,
      "reward": 1.8417868614196777,
      "reward_std": 0.06385098397731781,
      "rewards/accuracy_reward": 0.7136617302894592,
      "rewards/format_reward": 1.0,
      "step": 1290,
      "temperature": 1.0
    },
    {
      "all_correct": 0.875,
      "all_wrong": 0.0,
      "completion_length": 356.875,
      "epoch": 0.03925921420751733,
      "grad_norm": 0.7256042486802683,
      "kl": 0.04931640625,
      "learning_rate": 9.962018478918244e-07,
      "loss": 0.002,
      "reward": 2.1593751907348633,
      "reward_std": 0.07827534526586533,
      "rewards/accuracy_reward": 0.96875,
      "rewards/format_reward": 1.0,
      "step": 1291,
      "temperature": 1.0
    },
    {
      "all_correct": 0.375,
      "all_wrong": 0.375,
      "completion_length": 365.59375,
      "epoch": 0.039289624133317116,
      "grad_norm": 0.8201631840296107,
      "kl": 0.0341796875,
      "learning_rate": 9.961959690416041e-07,
      "loss": 0.0014,
      "reward": 1.6178460121154785,
      "reward_std": 0.06796128302812576,
      "rewards/accuracy_reward": 0.5115960836410522,
      "rewards/format_reward": 1.0,
      "step": 1292,
      "temperature": 1.0
    },
    {
      "all_correct": 0.875,
      "all_wrong": 0.125,
      "completion_length": 362.625,
      "epoch": 0.039320034059116896,
      "grad_norm": 0.08207798670455557,
      "kl": 0.03759765625,
      "learning_rate": 9.961900856625782e-07,
      "loss": 0.0015,
      "reward": 2.0500001907348633,
      "reward_std": 0.0,
      "rewards/accuracy_reward": 0.875,
      "rewards/format_reward": 1.0,
      "step": 1293,
      "temperature": 1.0
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.25,
      "completion_length": 365.921875,
      "epoch": 0.039350443984916675,
      "grad_norm": 1.3529287547770732,
      "kl": 0.0419921875,
      "learning_rate": 9.961841977548e-07,
      "loss": 0.0017,
      "reward": 1.6968610286712646,
      "reward_std": 0.07324168086051941,
      "rewards/accuracy_reward": 0.5687360763549805,
      "rewards/format_reward": 1.0,
      "step": 1294,
      "temperature": 1.0
    },
    {
      "all_correct": 0.75,
      "all_wrong": 0.125,
      "completion_length": 379.375,
      "epoch": 0.03938085391071646,
      "grad_norm": 0.7799968902292901,
      "kl": 0.028564453125,
      "learning_rate": 9.961783053183235e-07,
      "loss": 0.0011,
      "reward": 1.9093749523162842,
      "reward_std": 0.06187184900045395,
      "rewards/accuracy_reward": 0.765625,
      "rewards/format_reward": 1.0,
      "step": 1295,
      "temperature": 1.0
    },
    {
      "all_correct": 0.75,
      "all_wrong": 0.125,
      "completion_length": 346.4375,
      "epoch": 0.03941126383651624,
      "grad_norm": 0.8301073063285291,
      "kl": 0.0361328125,
      "learning_rate": 9.961724083532025e-07,
      "loss": 0.0014,
      "reward": 2.0250000953674316,
      "reward_std": 0.06134308874607086,
      "rewards/accuracy_reward": 0.859375,
      "rewards/format_reward": 1.0,
      "step": 1296,
      "temperature": 1.0
    },
    {
      "all_correct": 0.75,
      "all_wrong": 0.0,
      "completion_length": 352.890625,
      "epoch": 0.03944167376231602,
      "grad_norm": 5.88803715755647,
      "kl": 0.03369140625,
      "learning_rate": 9.961665068594906e-07,
      "loss": 0.0013,
      "reward": 2.1190028190612793,
      "reward_std": 0.09822721779346466,
      "rewards/accuracy_reward": 0.9283777475357056,
      "rewards/format_reward": 1.0,
      "step": 1297,
      "temperature": 1.0
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.125,
      "completion_length": 361.203125,
      "epoch": 0.0394720836881158,
      "grad_norm": 1.2677164076099372,
      "kl": 0.036376953125,
      "learning_rate": 9.96160600837242e-07,
      "loss": 0.0015,
      "reward": 1.8633277416229248,
      "reward_std": 0.13791996240615845,
      "rewards/accuracy_reward": 0.7133276462554932,
      "rewards/format_reward": 1.0,
      "step": 1298,
      "temperature": 1.0
    },
    {
      "all_correct": 0.625,
      "all_wrong": 0.125,
      "completion_length": 374.28125,
      "epoch": 0.039502493613915585,
      "grad_norm": 1.3311327494857392,
      "kl": 0.0289306640625,
      "learning_rate": 9.961546902865102e-07,
      "loss": 0.0012,
      "reward": 1.8705925941467285,
      "reward_std": 0.06272601336240768,
      "rewards/accuracy_reward": 0.7268426418304443,
      "rewards/format_reward": 1.0,
      "step": 1299,
      "temperature": 1.0
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.25,
      "completion_length": 372.796875,
      "epoch": 0.039532903539715364,
      "grad_norm": 0.5729202564215646,
      "kl": 0.033935546875,
      "learning_rate": 9.961487752073493e-07,
      "loss": 0.0014,
      "reward": 1.8011949062347412,
      "reward_std": 0.09193049371242523,
      "rewards/accuracy_reward": 0.6668198704719543,
      "rewards/format_reward": 1.0,
      "step": 1300,
      "temperature": 1.0
    },
    {
      "all_correct": 0.625,
      "all_wrong": 0.0,
      "completion_length": 349.125,
      "epoch": 0.03956331346551514,
      "grad_norm": 2.240176080055285,
      "kl": 0.033447265625,
      "learning_rate": 9.961428555998137e-07,
      "loss": 0.0013,
      "reward": 2.001201868057251,
      "reward_std": 0.1575872302055359,
      "rewards/accuracy_reward": 0.8293269276618958,
      "rewards/format_reward": 1.0,
      "step": 1301,
      "temperature": 1.0
    },
    {
      "all_correct": 0.75,
      "all_wrong": 0.0,
      "completion_length": 345.484375,
      "epoch": 0.03959372339131492,
      "grad_norm": 0.95299612843412,
      "kl": 0.0322265625,
      "learning_rate": 9.96136931463957e-07,
      "loss": 0.0013,
      "reward": 2.0250000953674316,
      "reward_std": 0.12246952205896378,
      "rewards/accuracy_reward": 0.859375,
      "rewards/format_reward": 1.0,
      "step": 1302,
      "temperature": 1.0
    },
    {
      "all_correct": 0.25,
      "all_wrong": 0.125,
      "completion_length": 421.78125,
      "epoch": 0.03962413331711471,
      "grad_norm": 1.1609403597347412,
      "kl": 0.02490234375,
      "learning_rate": 9.96131002799833e-07,
      "loss": 0.001,
      "reward": 1.5474251508712769,
      "reward_std": 0.1381864994764328,
      "rewards/accuracy_reward": 0.43180012702941895,
      "rewards/format_reward": 1.0,
      "step": 1303,
      "temperature": 1.0
    },
    {
      "all_correct": 0.375,
      "all_wrong": 0.25,
      "completion_length": 363.171875,
      "epoch": 0.03965454324291449,
      "grad_norm": 1.501789258861905,
      "kl": 0.029541015625,
      "learning_rate": 9.961250696074963e-07,
      "loss": 0.0012,
      "reward": 1.6882401704788208,
      "reward_std": 0.16457030177116394,
      "rewards/accuracy_reward": 0.5694901347160339,
      "rewards/format_reward": 1.0,
      "step": 1304,
      "temperature": 1.0
    },
    {
      "all_correct": 0.375,
      "all_wrong": 0.5,
      "completion_length": 365.1875,
      "epoch": 0.03968495316871427,
      "grad_norm": 1.4016039121676045,
      "kl": 0.028076171875,
      "learning_rate": 9.96119131887001e-07,
      "loss": 0.0011,
      "reward": 1.5366151332855225,
      "reward_std": 0.01780317723751068,
      "rewards/accuracy_reward": 0.4397400915622711,
      "rewards/format_reward": 1.0,
      "step": 1305,
      "temperature": 1.0
    },
    {
      "all_correct": 0.625,
      "all_wrong": 0.125,
      "completion_length": 362.796875,
      "epoch": 0.039715363094514046,
      "grad_norm": 1.2074679919637177,
      "kl": 0.032958984375,
      "learning_rate": 9.961131896384013e-07,
      "loss": 0.0013,
      "reward": 1.9812500476837158,
      "reward_std": 0.13402831554412842,
      "rewards/accuracy_reward": 0.828125,
      "rewards/format_reward": 1.0,
      "step": 1306,
      "temperature": 1.0
    },
    {
      "all_correct": 0.75,
      "all_wrong": 0.125,
      "completion_length": 355.328125,
      "epoch": 0.03974577302031383,
      "grad_norm": 0.563225816831639,
      "kl": 0.0289306640625,
      "learning_rate": 9.96107242861751e-07,
      "loss": 0.0012,
      "reward": 1.9375,
      "reward_std": 0.06943650543689728,
      "rewards/accuracy_reward": 0.78125,
      "rewards/format_reward": 1.0,
      "step": 1307,
      "temperature": 1.0
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.0,
      "completion_length": 368.6875,
      "epoch": 0.03977618294611361,
      "grad_norm": 2.038779470571373,
      "kl": 0.037109375,
      "learning_rate": 9.96101291557105e-07,
      "loss": 0.0015,
      "reward": 1.816410779953003,
      "reward_std": 0.054240547120571136,
      "rewards/accuracy_reward": 0.6539105772972107,
      "rewards/format_reward": 1.0,
      "step": 1308,
      "temperature": 1.0
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.375,
      "completion_length": 338.421875,
      "epoch": 0.03980659287191339,
      "grad_norm": 0.9253009394332102,
      "kl": 0.03466796875,
      "learning_rate": 9.960953357245173e-07,
      "loss": 0.0014,
      "reward": 1.6031250953674316,
      "reward_std": 0.067339688539505,
      "rewards/accuracy_reward": 0.515625,
      "rewards/format_reward": 1.0,
      "step": 1309,
      "temperature": 1.0
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.0,
      "completion_length": 389.59375,
      "epoch": 0.03983700279771318,
      "grad_norm": 1.4771398119031744,
      "kl": 0.031494140625,
      "learning_rate": 9.960893753640422e-07,
      "loss": 0.0013,
      "reward": 1.8139492273330688,
      "reward_std": 0.14914552867412567,
      "rewards/accuracy_reward": 0.6576991677284241,
      "rewards/format_reward": 1.0,
      "step": 1310,
      "temperature": 1.0
    },
    {
      "all_correct": 0.25,
      "all_wrong": 0.0,
      "completion_length": 387.3125,
      "epoch": 0.039867412723512956,
      "grad_norm": 1.2975032790808658,
      "kl": 0.035888671875,
      "learning_rate": 9.960834104757342e-07,
      "loss": 0.0014,
      "reward": 1.7364957332611084,
      "reward_std": 0.18749645352363586,
      "rewards/accuracy_reward": 0.5802457332611084,
      "rewards/format_reward": 1.0,
      "step": 1311,
      "temperature": 1.0
    },
    {
      "all_correct": 0.375,
      "all_wrong": 0.125,
      "completion_length": 399.15625,
      "epoch": 0.039897822649312735,
      "grad_norm": 2.7914229876516967,
      "kl": 0.032958984375,
      "learning_rate": 9.960774410596477e-07,
      "loss": 0.0013,
      "reward": 1.7136642932891846,
      "reward_std": 0.15386910736560822,
      "rewards/accuracy_reward": 0.6511642932891846,
      "rewards/format_reward": 0.921875,
      "step": 1312,
      "temperature": 1.0
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.125,
      "completion_length": 397.765625,
      "epoch": 0.039928232575112514,
      "grad_norm": 2.2107138683935825,
      "kl": 0.028564453125,
      "learning_rate": 9.960714671158373e-07,
      "loss": 0.0011,
      "reward": 1.7863473892211914,
      "reward_std": 0.11173753440380096,
      "rewards/accuracy_reward": 0.6519724130630493,
      "rewards/format_reward": 1.0,
      "step": 1313,
      "temperature": 1.0
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.0,
      "completion_length": 396.28125,
      "epoch": 0.0399586425009123,
      "grad_norm": 1.0169353253453348,
      "kl": 0.02783203125,
      "learning_rate": 9.960654886443573e-07,
      "loss": 0.0011,
      "reward": 1.8392975330352783,
      "reward_std": 0.19117602705955505,
      "rewards/accuracy_reward": 0.7080473899841309,
      "rewards/format_reward": 1.0,
      "step": 1314,
      "temperature": 1.0
    },
    {
      "all_correct": 0.625,
      "all_wrong": 0.125,
      "completion_length": 357.375,
      "epoch": 0.03998905242671208,
      "grad_norm": 1.1942419532258988,
      "kl": 0.0400390625,
      "learning_rate": 9.960595056452625e-07,
      "loss": 0.0016,
      "reward": 1.8291510343551636,
      "reward_std": 0.072826087474823,
      "rewards/accuracy_reward": 0.6854010820388794,
      "rewards/format_reward": 1.0,
      "step": 1315,
      "temperature": 1.0
    },
    {
      "all_correct": 0.375,
      "all_wrong": 0.125,
      "completion_length": 396.953125,
      "epoch": 0.04001946235251186,
      "grad_norm": 1.0337391045249644,
      "kl": 0.0244140625,
      "learning_rate": 9.960535181186075e-07,
      "loss": 0.001,
      "reward": 1.7338731288909912,
      "reward_std": 0.1774049699306488,
      "rewards/accuracy_reward": 0.6088730096817017,
      "rewards/format_reward": 1.0,
      "step": 1316,
      "temperature": 1.0
    },
    {
      "all_correct": 0.75,
      "all_wrong": 0.125,
      "completion_length": 381.46875,
      "epoch": 0.04004987227831164,
      "grad_norm": 0.9211275913192079,
      "kl": 0.032470703125,
      "learning_rate": 9.960475260644468e-07,
      "loss": 0.0013,
      "reward": 1.9375,
      "reward_std": 0.10867312550544739,
      "rewards/accuracy_reward": 0.796875,
      "rewards/format_reward": 1.0,
      "step": 1317,
      "temperature": 1.0
    },
    {
      "all_correct": 0.75,
      "all_wrong": 0.0,
      "completion_length": 360.84375,
      "epoch": 0.040080282204111424,
      "grad_norm": 3.445572032114775,
      "kl": 0.0299072265625,
      "learning_rate": 9.96041529482835e-07,
      "loss": 0.0012,
      "reward": 2.0757908821105957,
      "reward_std": 0.0918976366519928,
      "rewards/accuracy_reward": 0.885165810585022,
      "rewards/format_reward": 1.0,
      "step": 1318,
      "temperature": 1.0
    },
    {
      "all_correct": 0.625,
      "all_wrong": 0.125,
      "completion_length": 366.125,
      "epoch": 0.0401106921299112,
      "grad_norm": 3.3390643076864177,
      "kl": 0.0283203125,
      "learning_rate": 9.960355283738272e-07,
      "loss": 0.0011,
      "reward": 1.9224340915679932,
      "reward_std": 0.0858631283044815,
      "rewards/accuracy_reward": 0.7536839842796326,
      "rewards/format_reward": 1.0,
      "step": 1319,
      "temperature": 1.0
    },
    {
      "all_correct": 0.625,
      "all_wrong": 0.125,
      "completion_length": 358.265625,
      "epoch": 0.04014110205571098,
      "grad_norm": 0.9561689460043742,
      "kl": 0.0341796875,
      "learning_rate": 9.96029522737478e-07,
      "loss": 0.0014,
      "reward": 1.9840564727783203,
      "reward_std": 0.10123483836650848,
      "rewards/accuracy_reward": 0.8153064250946045,
      "rewards/format_reward": 1.0,
      "step": 1320,
      "temperature": 1.0
    },
    {
      "all_correct": 0.625,
      "all_wrong": 0.25,
      "completion_length": 371.5,
      "epoch": 0.04017151198151077,
      "grad_norm": 1.1189274987324662,
      "kl": 0.033935546875,
      "learning_rate": 9.960235125738418e-07,
      "loss": 0.0014,
      "reward": 1.816159963607788,
      "reward_std": 0.003463847329840064,
      "rewards/accuracy_reward": 0.666159987449646,
      "rewards/format_reward": 1.0,
      "step": 1321,
      "temperature": 1.0
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.0,
      "completion_length": 406.96875,
      "epoch": 0.04020192190731055,
      "grad_norm": 0.9504857076018339,
      "kl": 0.037109375,
      "learning_rate": 9.960174978829742e-07,
      "loss": 0.0015,
      "reward": 1.8848531246185303,
      "reward_std": 0.03111434541642666,
      "rewards/accuracy_reward": 0.7004780769348145,
      "rewards/format_reward": 1.0,
      "step": 1322,
      "temperature": 1.0
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.0,
      "completion_length": 398.03125,
      "epoch": 0.04023233183311033,
      "grad_norm": 2.36202888937614,
      "kl": 0.033447265625,
      "learning_rate": 9.960114786649293e-07,
      "loss": 0.0013,
      "reward": 1.8598071336746216,
      "reward_std": 0.15658432245254517,
      "rewards/accuracy_reward": 0.703557014465332,
      "rewards/format_reward": 1.0,
      "step": 1323,
      "temperature": 1.0
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.0,
      "completion_length": 375.015625,
      "epoch": 0.040262741758910106,
      "grad_norm": 1.2317196139737694,
      "kl": 0.037353515625,
      "learning_rate": 9.960054549197628e-07,
      "loss": 0.0015,
      "reward": 1.915244460105896,
      "reward_std": 0.13039034605026245,
      "rewards/accuracy_reward": 0.7371194362640381,
      "rewards/format_reward": 1.0,
      "step": 1324,
      "temperature": 1.0
    },
    {
      "all_correct": 0.625,
      "all_wrong": 0.0,
      "completion_length": 349.078125,
      "epoch": 0.04029315168470989,
      "grad_norm": 1.6130517078895361,
      "kl": 0.03125,
      "learning_rate": 9.959994266475293e-07,
      "loss": 0.0013,
      "reward": 1.9375,
      "reward_std": 0.22470125555992126,
      "rewards/accuracy_reward": 0.78125,
      "rewards/format_reward": 1.0,
      "step": 1325,
      "temperature": 1.0
    },
    {
      "all_correct": 0.625,
      "all_wrong": 0.125,
      "completion_length": 369.953125,
      "epoch": 0.04032356161050967,
      "grad_norm": 0.8290163003969956,
      "kl": 0.030517578125,
      "learning_rate": 9.95993393848284e-07,
      "loss": 0.0012,
      "reward": 1.8490631580352783,
      "reward_std": 0.05882937088608742,
      "rewards/accuracy_reward": 0.6896881461143494,
      "rewards/format_reward": 1.0,
      "step": 1326,
      "temperature": 1.0
    },
    {
      "all_correct": 0.625,
      "all_wrong": 0.25,
      "completion_length": 358.921875,
      "epoch": 0.04035397153630945,
      "grad_norm": 0.7771225119765722,
      "kl": 0.0341796875,
      "learning_rate": 9.959873565220814e-07,
      "loss": 0.0014,
      "reward": 1.7544031143188477,
      "reward_std": 0.0530330091714859,
      "rewards/accuracy_reward": 0.6325280666351318,
      "rewards/format_reward": 1.0,
      "step": 1327,
      "temperature": 1.0
    },
    {
      "all_correct": 0.625,
      "all_wrong": 0.0,
      "completion_length": 370.1875,
      "epoch": 0.04038438146210923,
      "grad_norm": 1.2361075223311364,
      "kl": 0.03271484375,
      "learning_rate": 9.959813146689774e-07,
      "loss": 0.0013,
      "reward": 1.999735713005066,
      "reward_std": 0.10615263879299164,
      "rewards/accuracy_reward": 0.8122357130050659,
      "rewards/format_reward": 1.0,
      "step": 1328,
      "temperature": 1.0
    },
    {
      "all_correct": 0.625,
      "all_wrong": 0.0,
      "completion_length": 363.140625,
      "epoch": 0.040414791387909016,
      "grad_norm": 1.1421687131580691,
      "kl": 0.035888671875,
      "learning_rate": 9.959752682890264e-07,
      "loss": 0.0014,
      "reward": 2.098296642303467,
      "reward_std": 0.10883867740631104,
      "rewards/accuracy_reward": 0.9076717495918274,
      "rewards/format_reward": 1.0,
      "step": 1329,
      "temperature": 1.0
    },
    {
      "all_correct": 0.875,
      "all_wrong": 0.125,
      "completion_length": 349.765625,
      "epoch": 0.040445201313708795,
      "grad_norm": 0.08169214426988264,
      "kl": 0.037353515625,
      "learning_rate": 9.959692173822843e-07,
      "loss": 0.0015,
      "reward": 2.0500001907348633,
      "reward_std": 0.0,
      "rewards/accuracy_reward": 0.875,
      "rewards/format_reward": 1.0,
      "step": 1330,
      "temperature": 1.0
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.125,
      "completion_length": 359.84375,
      "epoch": 0.040475611239508574,
      "grad_norm": 2.5703292667113584,
      "kl": 0.035888671875,
      "learning_rate": 9.959631619488056e-07,
      "loss": 0.0014,
      "reward": 1.8603743314743042,
      "reward_std": 0.07285212725400925,
      "rewards/accuracy_reward": 0.6947493553161621,
      "rewards/format_reward": 1.0,
      "step": 1331,
      "temperature": 1.0
    },
    {
      "all_correct": 0.625,
      "all_wrong": 0.125,
      "completion_length": 377.84375,
      "epoch": 0.040506021165308354,
      "grad_norm": 0.7104214303797572,
      "kl": 0.0263671875,
      "learning_rate": 9.959571019886463e-07,
      "loss": 0.0011,
      "reward": 1.8565657138824463,
      "reward_std": 0.07906949520111084,
      "rewards/accuracy_reward": 0.7034406661987305,
      "rewards/format_reward": 1.0,
      "step": 1332,
      "temperature": 1.0
    },
    {
      "all_correct": 0.25,
      "all_wrong": 0.25,
      "completion_length": 395.671875,
      "epoch": 0.04053643109110814,
      "grad_norm": 1.1342694561075992,
      "kl": 0.0289306640625,
      "learning_rate": 9.959510375018611e-07,
      "loss": 0.0012,
      "reward": 1.6762497425079346,
      "reward_std": 0.09515200555324554,
      "rewards/accuracy_reward": 0.5543747544288635,
      "rewards/format_reward": 1.0,
      "step": 1333,
      "temperature": 1.0
    },
    {
      "all_correct": 0.625,
      "all_wrong": 0.0,
      "completion_length": 351.390625,
      "epoch": 0.04056684101690792,
      "grad_norm": 2.9223507356928864,
      "kl": 0.033203125,
      "learning_rate": 9.959449684885056e-07,
      "loss": 0.0013,
      "reward": 1.9155181646347046,
      "reward_std": 0.12182654440402985,
      "rewards/accuracy_reward": 0.7561431527137756,
      "rewards/format_reward": 1.0,
      "step": 1334,
      "temperature": 1.0
    },
    {
      "all_correct": 0.25,
      "all_wrong": 0.0,
      "completion_length": 414.28125,
      "epoch": 0.0405972509427077,
      "grad_norm": 2.0226103270529796,
      "kl": 0.025634765625,
      "learning_rate": 9.959388949486355e-07,
      "loss": 0.001,
      "reward": 1.719913125038147,
      "reward_std": 0.17510588467121124,
      "rewards/accuracy_reward": 0.5480380058288574,
      "rewards/format_reward": 1.0,
      "step": 1335,
      "temperature": 1.0
    },
    {
      "all_correct": 0.75,
      "all_wrong": 0.125,
      "completion_length": 346.375,
      "epoch": 0.040627660868507484,
      "grad_norm": 0.9813379076880263,
      "kl": 0.03515625,
      "learning_rate": 9.959328168823058e-07,
      "loss": 0.0014,
      "reward": 1.8983631134033203,
      "reward_std": 0.013047808781266212,
      "rewards/accuracy_reward": 0.7514880895614624,
      "rewards/format_reward": 1.0,
      "step": 1336,
      "temperature": 1.0
    },
    {
      "all_correct": 0.75,
      "all_wrong": 0.0,
      "completion_length": 378.515625,
      "epoch": 0.04065807079430726,
      "grad_norm": 0.6908030927388166,
      "kl": 0.0263671875,
      "learning_rate": 9.95926734289572e-07,
      "loss": 0.0011,
      "reward": 2.0971951484680176,
      "reward_std": 0.029635250568389893,
      "rewards/accuracy_reward": 0.8971948623657227,
      "rewards/format_reward": 1.0,
      "step": 1337,
      "temperature": 1.0
    },
    {
      "all_correct": 0.25,
      "all_wrong": 0.125,
      "completion_length": 397.09375,
      "epoch": 0.04068848072010704,
      "grad_norm": 1.5392314568723093,
      "kl": 0.033203125,
      "learning_rate": 9.959206471704898e-07,
      "loss": 0.0013,
      "reward": 1.6306530237197876,
      "reward_std": 0.0899733230471611,
      "rewards/accuracy_reward": 0.47440293431282043,
      "rewards/format_reward": 1.0,
      "step": 1338,
      "temperature": 1.0
    },
    {
      "all_correct": 0.75,
      "all_wrong": 0.0,
      "completion_length": 362.109375,
      "epoch": 0.04071889064590682,
      "grad_norm": 1.5594762859452738,
      "kl": 0.03173828125,
      "learning_rate": 9.959145555251147e-07,
      "loss": 0.0013,
      "reward": 1.9375,
      "reward_std": 0.14424708485603333,
      "rewards/accuracy_reward": 0.796875,
      "rewards/format_reward": 1.0,
      "step": 1339,
      "temperature": 1.0
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.125,
      "completion_length": 358.546875,
      "epoch": 0.04074930057170661,
      "grad_norm": 1.1133703627868659,
      "kl": 0.034423828125,
      "learning_rate": 9.959084593535022e-07,
      "loss": 0.0014,
      "reward": 1.8486685752868652,
      "reward_std": 0.07270568609237671,
      "rewards/accuracy_reward": 0.6861684322357178,
      "rewards/format_reward": 1.0,
      "step": 1340,
      "temperature": 1.0
    },
    {
      "all_correct": 0.75,
      "all_wrong": 0.125,
      "completion_length": 361.25,
      "epoch": 0.04077971049750639,
      "grad_norm": 1.4476454114524349,
      "kl": 0.033203125,
      "learning_rate": 9.95902358655708e-07,
      "loss": 0.0013,
      "reward": 1.9710166454315186,
      "reward_std": 0.02923586405813694,
      "rewards/accuracy_reward": 0.8085166215896606,
      "rewards/format_reward": 1.0,
      "step": 1341,
      "temperature": 1.0
    },
    {
      "all_correct": 0.625,
      "all_wrong": 0.25,
      "completion_length": 353.6875,
      "epoch": 0.040810120423306166,
      "grad_norm": 0.37439872223183535,
      "kl": 0.0299072265625,
      "learning_rate": 9.958962534317879e-07,
      "loss": 0.0012,
      "reward": 1.881250023841858,
      "reward_std": 0.0530330091714859,
      "rewards/accuracy_reward": 0.734375,
      "rewards/format_reward": 1.0,
      "step": 1342,
      "temperature": 1.0
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.125,
      "completion_length": 368.59375,
      "epoch": 0.040840530349105945,
      "grad_norm": 1.2093084754691545,
      "kl": 0.03369140625,
      "learning_rate": 9.958901436817976e-07,
      "loss": 0.0013,
      "reward": 1.6858181953430176,
      "reward_std": 0.09985166788101196,
      "rewards/accuracy_reward": 0.5639432668685913,
      "rewards/format_reward": 1.0,
      "step": 1343,
      "temperature": 1.0
    },
    {
      "all_correct": 0.375,
      "all_wrong": 0.125,
      "completion_length": 347.921875,
      "epoch": 0.04087094027490573,
      "grad_norm": 1.335591765419783,
      "kl": 0.041015625,
      "learning_rate": 9.958840294057926e-07,
      "loss": 0.0016,
      "reward": 1.785186767578125,
      "reward_std": 0.25591838359832764,
      "rewards/accuracy_reward": 0.6539367437362671,
      "rewards/format_reward": 1.0,
      "step": 1344,
      "temperature": 1.0
    },
    {
      "all_correct": 0.75,
      "all_wrong": 0.0,
      "completion_length": 364.015625,
      "epoch": 0.04090135020070551,
      "grad_norm": 0.7149604691909549,
      "kl": 0.031494140625,
      "learning_rate": 9.958779106038288e-07,
      "loss": 0.0013,
      "reward": 2.0577006340026855,
      "reward_std": 0.08434312045574188,
      "rewards/accuracy_reward": 0.8670756816864014,
      "rewards/format_reward": 1.0,
      "step": 1345,
      "temperature": 1.0
    },
    {
      "all_correct": 0.375,
      "all_wrong": 0.0,
      "completion_length": 378.6875,
      "epoch": 0.04093176012650529,
      "grad_norm": 2.7239104313696214,
      "kl": 0.03369140625,
      "learning_rate": 9.958717872759624e-07,
      "loss": 0.0013,
      "reward": 1.8692957162857056,
      "reward_std": 0.1602056920528412,
      "rewards/accuracy_reward": 0.7067955732345581,
      "rewards/format_reward": 1.0,
      "step": 1346,
      "temperature": 1.0
    },
    {
      "all_correct": 0.25,
      "all_wrong": 0.25,
      "completion_length": 386.421875,
      "epoch": 0.04096217005230507,
      "grad_norm": 4.060058364152238,
      "kl": 0.0267333984375,
      "learning_rate": 9.95865659422249e-07,
      "loss": 0.0011,
      "reward": 1.7184205055236816,
      "reward_std": 0.1956622451543808,
      "rewards/accuracy_reward": 0.5840454697608948,
      "rewards/format_reward": 1.0,
      "step": 1347,
      "temperature": 1.0
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.0,
      "completion_length": 365.296875,
      "epoch": 0.040992579978104855,
      "grad_norm": 1.084755669443812,
      "kl": 0.031982421875,
      "learning_rate": 9.958595270427444e-07,
      "loss": 0.0013,
      "reward": 1.909855842590332,
      "reward_std": 0.2032507061958313,
      "rewards/accuracy_reward": 0.7536057829856873,
      "rewards/format_reward": 1.0,
      "step": 1348,
      "temperature": 1.0
    },
    {
      "all_correct": 0.625,
      "all_wrong": 0.125,
      "completion_length": 375.765625,
      "epoch": 0.041022989903904634,
      "grad_norm": 1.023990420386371,
      "kl": 0.036865234375,
      "learning_rate": 9.958533901375048e-07,
      "loss": 0.0015,
      "reward": 1.8748741149902344,
      "reward_std": 0.01003176998347044,
      "rewards/accuracy_reward": 0.6998740434646606,
      "rewards/format_reward": 1.0,
      "step": 1349,
      "temperature": 1.0
    },
    {
      "all_correct": 0.625,
      "all_wrong": 0.0,
      "completion_length": 382.15625,
      "epoch": 0.041053399829704414,
      "grad_norm": 0.7862832436070752,
      "kl": 0.031494140625,
      "learning_rate": 9.958472487065861e-07,
      "loss": 0.0013,
      "reward": 2.0239477157592773,
      "reward_std": 0.13823741674423218,
      "rewards/accuracy_reward": 0.8395727276802063,
      "rewards/format_reward": 1.0,
      "step": 1350,
      "temperature": 1.0
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.0,
      "completion_length": 368.25,
      "epoch": 0.0410838097555042,
      "grad_norm": 0.9568973862143455,
      "kl": 0.036865234375,
      "learning_rate": 9.958411027500444e-07,
      "loss": 0.0015,
      "reward": 1.834375023841858,
      "reward_std": 0.25955602526664734,
      "rewards/accuracy_reward": 0.6875,
      "rewards/format_reward": 1.0,
      "step": 1351,
      "temperature": 1.0
    },
    {
      "all_correct": 0.75,
      "all_wrong": 0.125,
      "completion_length": 375.234375,
      "epoch": 0.04111421968130398,
      "grad_norm": 0.5052447963655162,
      "kl": 0.04052734375,
      "learning_rate": 9.958349522679358e-07,
      "loss": 0.0016,
      "reward": 1.9608256816864014,
      "reward_std": 0.005701042246073484,
      "rewards/accuracy_reward": 0.7858256697654724,
      "rewards/format_reward": 1.0,
      "step": 1352,
      "temperature": 1.0
    },
    {
      "all_correct": 0.625,
      "all_wrong": 0.375,
      "completion_length": 357.6875,
      "epoch": 0.04114462960710376,
      "grad_norm": 0.09187506500515366,
      "kl": 0.03759765625,
      "learning_rate": 9.958287972603165e-07,
      "loss": 0.0015,
      "reward": 1.75,
      "reward_std": 0.0,
      "rewards/accuracy_reward": 0.625,
      "rewards/format_reward": 1.0,
      "step": 1353,
      "temperature": 1.0
    },
    {
      "all_correct": 0.375,
      "all_wrong": 0.25,
      "completion_length": 374.265625,
      "epoch": 0.04117503953290354,
      "grad_norm": 1.358335769314926,
      "kl": 0.0294189453125,
      "learning_rate": 9.958226377272425e-07,
      "loss": 0.0012,
      "reward": 1.6300781965255737,
      "reward_std": 0.11866331845521927,
      "rewards/accuracy_reward": 0.517578125,
      "rewards/format_reward": 1.0,
      "step": 1354,
      "temperature": 1.0
    },
    {
      "all_correct": 0.75,
      "all_wrong": 0.25,
      "completion_length": 357.21875,
      "epoch": 0.041205449458703323,
      "grad_norm": 0.0747002453531493,
      "kl": 0.036865234375,
      "learning_rate": 9.958164736687702e-07,
      "loss": 0.0015,
      "reward": 1.9000000953674316,
      "reward_std": 0.0,
      "rewards/accuracy_reward": 0.75,
      "rewards/format_reward": 1.0,
      "step": 1355,
      "temperature": 1.0
    },
    {
      "all_correct": 0.375,
      "all_wrong": 0.25,
      "completion_length": 412.09375,
      "epoch": 0.0412358593845031,
      "grad_norm": 0.912485963733874,
      "kl": 0.025634765625,
      "learning_rate": 9.958103050849556e-07,
      "loss": 0.001,
      "reward": 1.639655351638794,
      "reward_std": 0.09232194721698761,
      "rewards/accuracy_reward": 0.527155339717865,
      "rewards/format_reward": 1.0,
      "step": 1356,
      "temperature": 1.0
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.0,
      "completion_length": 394.125,
      "epoch": 0.04126626931030288,
      "grad_norm": 0.8962499470123171,
      "kl": 0.033203125,
      "learning_rate": 9.958041319758553e-07,
      "loss": 0.0013,
      "reward": 1.8270025253295898,
      "reward_std": 0.1693069189786911,
      "rewards/accuracy_reward": 0.6707525253295898,
      "rewards/format_reward": 1.0,
      "step": 1357,
      "temperature": 1.0
    },
    {
      "all_correct": 0.75,
      "all_wrong": 0.0,
      "completion_length": 363.890625,
      "epoch": 0.04129667923610266,
      "grad_norm": 1.1640764569792519,
      "kl": 0.0289306640625,
      "learning_rate": 9.957979543415256e-07,
      "loss": 0.0012,
      "reward": 2.0755209922790527,
      "reward_std": 0.15776163339614868,
      "rewards/accuracy_reward": 0.9036458730697632,
      "rewards/format_reward": 1.0,
      "step": 1358,
      "temperature": 1.0
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.125,
      "completion_length": 400.578125,
      "epoch": 0.04132708916190245,
      "grad_norm": 0.8224545222029924,
      "kl": 0.03125,
      "learning_rate": 9.957917721820228e-07,
      "loss": 0.0013,
      "reward": 1.8485685586929321,
      "reward_std": 0.07196305692195892,
      "rewards/accuracy_reward": 0.686068594455719,
      "rewards/format_reward": 1.0,
      "step": 1359,
      "temperature": 1.0
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.125,
      "completion_length": 381.46875,
      "epoch": 0.041357499087702226,
      "grad_norm": 1.0215253339886545,
      "kl": 0.03173828125,
      "learning_rate": 9.957855854974031e-07,
      "loss": 0.0013,
      "reward": 1.8232738971710205,
      "reward_std": 0.16958290338516235,
      "rewards/accuracy_reward": 0.6732739210128784,
      "rewards/format_reward": 1.0,
      "step": 1360,
      "temperature": 1.0
    },
    {
      "all_correct": 0.625,
      "all_wrong": 0.0,
      "completion_length": 366.703125,
      "epoch": 0.041387909013502006,
      "grad_norm": 1.1505760209014952,
      "kl": 0.036376953125,
      "learning_rate": 9.957793942877234e-07,
      "loss": 0.0015,
      "reward": 1.9686541557312012,
      "reward_std": 0.1127479076385498,
      "rewards/accuracy_reward": 0.8030290603637695,
      "rewards/format_reward": 1.0,
      "step": 1361,
      "temperature": 1.0
    },
    {
      "all_correct": 0.625,
      "all_wrong": 0.25,
      "completion_length": 358.078125,
      "epoch": 0.041418318939301785,
      "grad_norm": 0.9797118931668743,
      "kl": 0.046142578125,
      "learning_rate": 9.9577319855304e-07,
      "loss": 0.0018,
      "reward": 1.8024139404296875,
      "reward_std": 0.03240561857819557,
      "rewards/accuracy_reward": 0.6711639165878296,
      "rewards/format_reward": 1.0,
      "step": 1362,
      "temperature": 1.0
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.125,
      "completion_length": 382.59375,
      "epoch": 0.04144872886510157,
      "grad_norm": 1.1800745232733343,
      "kl": 0.031494140625,
      "learning_rate": 9.957669982934095e-07,
      "loss": 0.0013,
      "reward": 1.8131953477859497,
      "reward_std": 0.10240954160690308,
      "rewards/accuracy_reward": 0.6569451689720154,
      "rewards/format_reward": 1.0,
      "step": 1363,
      "temperature": 1.0
    },
    {
      "all_correct": 0.75,
      "all_wrong": 0.0,
      "completion_length": 366.296875,
      "epoch": 0.04147913879090135,
      "grad_norm": 1.579373767967266,
      "kl": 0.0283203125,
      "learning_rate": 9.957607935088881e-07,
      "loss": 0.0011,
      "reward": 2.082505702972412,
      "reward_std": 0.08248256146907806,
      "rewards/accuracy_reward": 0.8950057029724121,
      "rewards/format_reward": 1.0,
      "step": 1364,
      "temperature": 1.0
    },
    {
      "all_correct": 0.625,
      "all_wrong": 0.0,
      "completion_length": 359.875,
      "epoch": 0.04150954871670113,
      "grad_norm": 1.0994258225115032,
      "kl": 0.03271484375,
      "learning_rate": 9.95754584199533e-07,
      "loss": 0.0013,
      "reward": 1.946874976158142,
      "reward_std": 0.20484475791454315,
      "rewards/accuracy_reward": 0.796875,
      "rewards/format_reward": 1.0,
      "step": 1365,
      "temperature": 1.0
    },
    {
      "all_correct": 0.625,
      "all_wrong": 0.125,
      "completion_length": 380.625,
      "epoch": 0.041539958642500915,
      "grad_norm": 2.142313473407584,
      "kl": 0.03466796875,
      "learning_rate": 9.957483703654007e-07,
      "loss": 0.0014,
      "reward": 1.8287945985794067,
      "reward_std": 0.09270096570253372,
      "rewards/accuracy_reward": 0.681919515132904,
      "rewards/format_reward": 1.0,
      "step": 1366,
      "temperature": 1.0
    },
    {
      "all_correct": 0.25,
      "all_wrong": 0.125,
      "completion_length": 404.796875,
      "epoch": 0.041570368568300695,
      "grad_norm": 4.070596419153116,
      "kl": 0.030517578125,
      "learning_rate": 9.957421520065478e-07,
      "loss": 0.0012,
      "reward": 1.7388451099395752,
      "reward_std": 0.2863381505012512,
      "rewards/accuracy_reward": 0.6232200860977173,
      "rewards/format_reward": 0.984375,
      "step": 1367,
      "temperature": 1.0
    },
    {
      "all_correct": 0.75,
      "all_wrong": 0.0,
      "completion_length": 364.5,
      "epoch": 0.041600778494100474,
      "grad_norm": 0.6985405625163128,
      "kl": 0.03564453125,
      "learning_rate": 9.957359291230312e-07,
      "loss": 0.0014,
      "reward": 2.117159605026245,
      "reward_std": 0.06562963873147964,
      "rewards/accuracy_reward": 0.9202845096588135,
      "rewards/format_reward": 1.0,
      "step": 1368,
      "temperature": 1.0
    },
    {
      "all_correct": 0.75,
      "all_wrong": 0.0,
      "completion_length": 353.5,
      "epoch": 0.04163118841990025,
      "grad_norm": 0.8939929837988022,
      "kl": 0.044921875,
      "learning_rate": 9.957297017149074e-07,
      "loss": 0.0018,
      "reward": 2.1624999046325684,
      "reward_std": 0.1060660183429718,
      "rewards/accuracy_reward": 0.96875,
      "rewards/format_reward": 1.0,
      "step": 1369,
      "temperature": 1.0
    },
    {
      "all_correct": 0.625,
      "all_wrong": 0.125,
      "completion_length": 376.640625,
      "epoch": 0.04166159834570004,
      "grad_norm": 0.7851483279213706,
      "kl": 0.03369140625,
      "learning_rate": 9.957234697822336e-07,
      "loss": 0.0014,
      "reward": 1.9848215579986572,
      "reward_std": 0.12246951460838318,
      "rewards/accuracy_reward": 0.8191964626312256,
      "rewards/format_reward": 1.0,
      "step": 1370,
      "temperature": 1.0
    },
    {
      "all_correct": 0.375,
      "all_wrong": 0.25,
      "completion_length": 380.890625,
      "epoch": 0.04169200827149982,
      "grad_norm": 0.9947247043089857,
      "kl": 0.038818359375,
      "learning_rate": 9.957172333250665e-07,
      "loss": 0.0016,
      "reward": 1.597571611404419,
      "reward_std": 0.019277328625321388,
      "rewards/accuracy_reward": 0.47882160544395447,
      "rewards/format_reward": 1.0,
      "step": 1371,
      "temperature": 1.0
    },
    {
      "all_correct": 0.25,
      "all_wrong": 0.125,
      "completion_length": 390.3125,
      "epoch": 0.0417224181972996,
      "grad_norm": 1.784295128440716,
      "kl": 0.0380859375,
      "learning_rate": 9.95710992343463e-07,
      "loss": 0.0015,
      "reward": 1.5076708793640137,
      "reward_std": 0.26120397448539734,
      "rewards/accuracy_reward": 0.41392096877098083,
      "rewards/format_reward": 0.984375,
      "step": 1372,
      "temperature": 1.0
    },
    {
      "all_correct": 0.75,
      "all_wrong": 0.125,
      "completion_length": 349.171875,
      "epoch": 0.04175282812309938,
      "grad_norm": 0.689767236641378,
      "kl": 0.038818359375,
      "learning_rate": 9.957047468374802e-07,
      "loss": 0.0016,
      "reward": 2.0194854736328125,
      "reward_std": 0.059365928173065186,
      "rewards/accuracy_reward": 0.8538603186607361,
      "rewards/format_reward": 1.0,
      "step": 1373,
      "temperature": 1.0
    },
    {
      "all_correct": 0.625,
      "all_wrong": 0.0,
      "completion_length": 359.484375,
      "epoch": 0.04178323804889916,
      "grad_norm": 0.8476792433817267,
      "kl": 0.035400390625,
      "learning_rate": 9.95698496807175e-07,
      "loss": 0.0014,
      "reward": 1.9301159381866455,
      "reward_std": 0.21660631895065308,
      "rewards/accuracy_reward": 0.7801159620285034,
      "rewards/format_reward": 1.0,
      "step": 1374,
      "temperature": 1.0
    },
    {
      "all_correct": 0.625,
      "all_wrong": 0.125,
      "completion_length": 361.75,
      "epoch": 0.04181364797469894,
      "grad_norm": 1.918046473143597,
      "kl": 0.038330078125,
      "learning_rate": 9.956922422526044e-07,
      "loss": 0.0015,
      "reward": 1.8562500476837158,
      "reward_std": 0.1306653916835785,
      "rewards/accuracy_reward": 0.71875,
      "rewards/format_reward": 1.0,
      "step": 1375,
      "temperature": 1.0
    },
    {
      "all_correct": 0.625,
      "all_wrong": 0.0,
      "completion_length": 355.578125,
      "epoch": 0.04184405790049872,
      "grad_norm": 0.9779042951842699,
      "kl": 0.037353515625,
      "learning_rate": 9.956859831738255e-07,
      "loss": 0.0015,
      "reward": 2.104365110397339,
      "reward_std": 0.12784358859062195,
      "rewards/accuracy_reward": 0.9231151342391968,
      "rewards/format_reward": 1.0,
      "step": 1376,
      "temperature": 1.0
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.0,
      "completion_length": 362.0625,
      "epoch": 0.0418744678262985,
      "grad_norm": 1.2036717444706044,
      "kl": 0.0302734375,
      "learning_rate": 9.956797195708956e-07,
      "loss": 0.0012,
      "reward": 2.0006837844848633,
      "reward_std": 0.22426101565361023,
      "rewards/accuracy_reward": 0.8381837606430054,
      "rewards/format_reward": 1.0,
      "step": 1377,
      "temperature": 1.0
    },
    {
      "all_correct": 0.625,
      "all_wrong": 0.0,
      "completion_length": 375.03125,
      "epoch": 0.041904877752098287,
      "grad_norm": 1.1425535973095085,
      "kl": 0.031494140625,
      "learning_rate": 9.956734514438717e-07,
      "loss": 0.0013,
      "reward": 1.9820313453674316,
      "reward_std": 0.23114120960235596,
      "rewards/accuracy_reward": 0.828906238079071,
      "rewards/format_reward": 1.0,
      "step": 1378,
      "temperature": 1.0
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.125,
      "completion_length": 346.921875,
      "epoch": 0.041935287677898066,
      "grad_norm": 1.4992635776053853,
      "kl": 0.041015625,
      "learning_rate": 9.95667178792811e-07,
      "loss": 0.0016,
      "reward": 1.8628125190734863,
      "reward_std": 0.15551820397377014,
      "rewards/accuracy_reward": 0.7190625071525574,
      "rewards/format_reward": 1.0,
      "step": 1379,
      "temperature": 1.0
    },
    {
      "all_correct": 0.625,
      "all_wrong": 0.125,
      "completion_length": 368.296875,
      "epoch": 0.041965697603697845,
      "grad_norm": 1.5928241173498965,
      "kl": 0.032470703125,
      "learning_rate": 9.956609016177708e-07,
      "loss": 0.0013,
      "reward": 1.941906452178955,
      "reward_std": 0.08737563341856003,
      "rewards/accuracy_reward": 0.8012814521789551,
      "rewards/format_reward": 1.0,
      "step": 1380,
      "temperature": 1.0
    },
    {
      "all_correct": 0.75,
      "all_wrong": 0.0,
      "completion_length": 353.84375,
      "epoch": 0.04199610752949763,
      "grad_norm": 1.0913982525005104,
      "kl": 0.03271484375,
      "learning_rate": 9.956546199188085e-07,
      "loss": 0.0013,
      "reward": 2.0999999046325684,
      "reward_std": 0.1508890688419342,
      "rewards/accuracy_reward": 0.921875,
      "rewards/format_reward": 1.0,
      "step": 1381,
      "temperature": 1.0
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.125,
      "completion_length": 369.953125,
      "epoch": 0.04202651745529741,
      "grad_norm": 1.0337523453864121,
      "kl": 0.03173828125,
      "learning_rate": 9.956483336959813e-07,
      "loss": 0.0013,
      "reward": 1.7231431007385254,
      "reward_std": 0.13377638161182404,
      "rewards/accuracy_reward": 0.6043931245803833,
      "rewards/format_reward": 1.0,
      "step": 1382,
      "temperature": 1.0
    },
    {
      "all_correct": 0.375,
      "all_wrong": 0.25,
      "completion_length": 360.609375,
      "epoch": 0.04205692738109719,
      "grad_norm": 0.8907339087513076,
      "kl": 0.031494140625,
      "learning_rate": 9.956420429493464e-07,
      "loss": 0.0013,
      "reward": 1.7444961071014404,
      "reward_std": 0.10254321247339249,
      "rewards/accuracy_reward": 0.6038711071014404,
      "rewards/format_reward": 1.0,
      "step": 1383,
      "temperature": 1.0
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.25,
      "completion_length": 341.296875,
      "epoch": 0.04208733730689697,
      "grad_norm": 1.1065106945712984,
      "kl": 0.03759765625,
      "learning_rate": 9.956357476789617e-07,
      "loss": 0.0015,
      "reward": 1.6664738655090332,
      "reward_std": 0.05185055360198021,
      "rewards/accuracy_reward": 0.5414737462997437,
      "rewards/format_reward": 1.0,
      "step": 1384,
      "temperature": 1.0
    },
    {
      "all_correct": 0.625,
      "all_wrong": 0.0,
      "completion_length": 359.84375,
      "epoch": 0.042117747232696755,
      "grad_norm": 1.2391149565154294,
      "kl": 0.043212890625,
      "learning_rate": 9.956294478848841e-07,
      "loss": 0.0017,
      "reward": 1.938907504081726,
      "reward_std": 0.14079871773719788,
      "rewards/accuracy_reward": 0.7795325517654419,
      "rewards/format_reward": 1.0,
      "step": 1385,
      "temperature": 1.0
    },
    {
      "all_correct": 0.375,
      "all_wrong": 0.125,
      "completion_length": 382.3125,
      "epoch": 0.042148157158496534,
      "grad_norm": 1.2384501016988423,
      "kl": 0.0341796875,
      "learning_rate": 9.956231435671714e-07,
      "loss": 0.0014,
      "reward": 1.827519416809082,
      "reward_std": 0.19984927773475647,
      "rewards/accuracy_reward": 0.6743943691253662,
      "rewards/format_reward": 1.0,
      "step": 1386,
      "temperature": 1.0
    },
    {
      "all_correct": 0.375,
      "all_wrong": 0.25,
      "completion_length": 354.828125,
      "epoch": 0.04217856708429631,
      "grad_norm": 0.7968053280738694,
      "kl": 0.032470703125,
      "learning_rate": 9.956168347258813e-07,
      "loss": 0.0013,
      "reward": 1.7843750715255737,
      "reward_std": 0.18571564555168152,
      "rewards/accuracy_reward": 0.65625,
      "rewards/format_reward": 1.0,
      "step": 1387,
      "temperature": 1.0
    },
    {
      "all_correct": 0.75,
      "all_wrong": 0.0,
      "completion_length": 371.734375,
      "epoch": 0.04220897701009609,
      "grad_norm": 0.6675766688700255,
      "kl": 0.03515625,
      "learning_rate": 9.95610521361071e-07,
      "loss": 0.0014,
      "reward": 2.075000047683716,
      "reward_std": 0.12449951469898224,
      "rewards/accuracy_reward": 0.90625,
      "rewards/format_reward": 1.0,
      "step": 1388,
      "temperature": 1.0
    },
    {
      "all_correct": 0.75,
      "all_wrong": 0.0,
      "completion_length": 379.265625,
      "epoch": 0.04223938693589588,
      "grad_norm": 0.7818800502448621,
      "kl": 0.0341796875,
      "learning_rate": 9.956042034727985e-07,
      "loss": 0.0014,
      "reward": 2.066763401031494,
      "reward_std": 0.07203345000743866,
      "rewards/accuracy_reward": 0.8855133056640625,
      "rewards/format_reward": 1.0,
      "step": 1389,
      "temperature": 1.0
    },
    {
      "all_correct": 0.75,
      "all_wrong": 0.125,
      "completion_length": 356.90625,
      "epoch": 0.04226979686169566,
      "grad_norm": 0.0724866816835963,
      "kl": 0.029541015625,
      "learning_rate": 9.955978810611211e-07,
      "loss": 0.0012,
      "reward": 2.0140368938446045,
      "reward_std": 0.0,
      "rewards/accuracy_reward": 0.8390368819236755,
      "rewards/format_reward": 1.0,
      "step": 1390,
      "temperature": 1.0
    },
    {
      "all_correct": 0.625,
      "all_wrong": 0.125,
      "completion_length": 345.578125,
      "epoch": 0.04230020678749544,
      "grad_norm": 1.7992814818664191,
      "kl": 0.038330078125,
      "learning_rate": 9.955915541260969e-07,
      "loss": 0.0015,
      "reward": 1.8659237623214722,
      "reward_std": 0.0924883484840393,
      "rewards/accuracy_reward": 0.7127987742424011,
      "rewards/format_reward": 1.0,
      "step": 1391,
      "temperature": 1.0
    },
    {
      "all_correct": 0.375,
      "all_wrong": 0.375,
      "completion_length": 373.734375,
      "epoch": 0.04233061671329522,
      "grad_norm": 0.4208736047719149,
      "kl": 0.03515625,
      "learning_rate": 9.955852226677832e-07,
      "loss": 0.0014,
      "reward": 1.59375,
      "reward_std": 0.09669842571020126,
      "rewards/accuracy_reward": 0.5,
      "rewards/format_reward": 1.0,
      "step": 1392,
      "temperature": 1.0
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.125,
      "completion_length": 350.5,
      "epoch": 0.042361026639095,
      "grad_norm": 1.0526480713520352,
      "kl": 0.03369140625,
      "learning_rate": 9.95578886686238e-07,
      "loss": 0.0014,
      "reward": 1.7999999523162842,
      "reward_std": 0.19530820846557617,
      "rewards/accuracy_reward": 0.671875,
      "rewards/format_reward": 1.0,
      "step": 1393,
      "temperature": 1.0
    },
    {
      "all_correct": 0.625,
      "all_wrong": 0.0,
      "completion_length": 378.640625,
      "epoch": 0.04239143656489478,
      "grad_norm": 2.990754731618439,
      "kl": 0.035888671875,
      "learning_rate": 9.955725461815194e-07,
      "loss": 0.0014,
      "reward": 1.8154511451721191,
      "reward_std": 0.08033843338489532,
      "rewards/accuracy_reward": 0.6873260736465454,
      "rewards/format_reward": 1.0,
      "step": 1394,
      "temperature": 1.0
    },
    {
      "all_correct": 0.625,
      "all_wrong": 0.375,
      "completion_length": 376.953125,
      "epoch": 0.04242184649069456,
      "grad_norm": 0.5710888968463236,
      "kl": 0.0281982421875,
      "learning_rate": 9.955662011536848e-07,
      "loss": 0.0011,
      "reward": 1.7468750476837158,
      "reward_std": 0.008838837966322899,
      "rewards/accuracy_reward": 0.625,
      "rewards/format_reward": 1.0,
      "step": 1395,
      "temperature": 1.0
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.125,
      "completion_length": 358.75,
      "epoch": 0.04245225641649435,
      "grad_norm": 1.8230811471045338,
      "kl": 0.0308837890625,
      "learning_rate": 9.955598516027923e-07,
      "loss": 0.0012,
      "reward": 1.7721840143203735,
      "reward_std": 0.09068720787763596,
      "rewards/accuracy_reward": 0.631558895111084,
      "rewards/format_reward": 1.0,
      "step": 1396,
      "temperature": 1.0
    },
    {
      "all_correct": 0.625,
      "all_wrong": 0.0,
      "completion_length": 351.359375,
      "epoch": 0.042482666342294126,
      "grad_norm": 1.0493647396721761,
      "kl": 0.034912109375,
      "learning_rate": 9.955534975289e-07,
      "loss": 0.0014,
      "reward": 1.920665979385376,
      "reward_std": 0.07833994925022125,
      "rewards/accuracy_reward": 0.764415979385376,
      "rewards/format_reward": 1.0,
      "step": 1397,
      "temperature": 1.0
    },
    {
      "all_correct": 0.375,
      "all_wrong": 0.0,
      "completion_length": 383.234375,
      "epoch": 0.042513076268093905,
      "grad_norm": 1.4743487872088243,
      "kl": 0.040283203125,
      "learning_rate": 9.955471389320657e-07,
      "loss": 0.0016,
      "reward": 1.8181214332580566,
      "reward_std": 0.15854354202747345,
      "rewards/accuracy_reward": 0.639996349811554,
      "rewards/format_reward": 1.0,
      "step": 1398,
      "temperature": 1.0
    },
    {
      "all_correct": 0.75,
      "all_wrong": 0.0,
      "completion_length": 367.09375,
      "epoch": 0.042543486193893684,
      "grad_norm": 1.001258748020277,
      "kl": 0.035888671875,
      "learning_rate": 9.955407758123476e-07,
      "loss": 0.0014,
      "reward": 1.9713821411132812,
      "reward_std": 0.0642324835062027,
      "rewards/accuracy_reward": 0.802632212638855,
      "rewards/format_reward": 1.0,
      "step": 1399,
      "temperature": 1.0
    },
    {
      "all_correct": 0.625,
      "all_wrong": 0.0,
      "completion_length": 356.15625,
      "epoch": 0.04257389611969347,
      "grad_norm": 1.4115221072547501,
      "kl": 0.04052734375,
      "learning_rate": 9.955344081698036e-07,
      "loss": 0.0016,
      "reward": 1.909414291381836,
      "reward_std": 0.16459053754806519,
      "rewards/accuracy_reward": 0.7531642913818359,
      "rewards/format_reward": 1.0,
      "step": 1400,
      "temperature": 1.0
    },
    {
      "all_correct": 0.625,
      "all_wrong": 0.0,
      "completion_length": 377.953125,
      "epoch": 0.04260430604549325,
      "grad_norm": 0.905302787419834,
      "kl": 0.03271484375,
      "learning_rate": 9.95528036004492e-07,
      "loss": 0.0013,
      "reward": 1.9376168251037598,
      "reward_std": 0.0854758620262146,
      "rewards/accuracy_reward": 0.7532418966293335,
      "rewards/format_reward": 1.0,
      "step": 1401,
      "temperature": 1.0
    },
    {
      "all_correct": 0.75,
      "all_wrong": 0.0,
      "completion_length": 351.796875,
      "epoch": 0.04263471597129303,
      "grad_norm": 1.1842627419073168,
      "kl": 0.0380859375,
      "learning_rate": 9.955216593164707e-07,
      "loss": 0.0015,
      "reward": 2.0881142616271973,
      "reward_std": 0.09037096053361893,
      "rewards/accuracy_reward": 0.8974892497062683,
      "rewards/format_reward": 1.0,
      "step": 1402,
      "temperature": 1.0
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.0,
      "completion_length": 353.078125,
      "epoch": 0.04266512589709281,
      "grad_norm": 1.0831424984539992,
      "kl": 0.036376953125,
      "learning_rate": 9.955152781057982e-07,
      "loss": 0.0015,
      "reward": 2.078812599182129,
      "reward_std": 0.18137730658054352,
      "rewards/accuracy_reward": 0.8881875872612,
      "rewards/format_reward": 1.0,
      "step": 1403,
      "temperature": 1.0
    },
    {
      "all_correct": 0.625,
      "all_wrong": 0.0,
      "completion_length": 394.328125,
      "epoch": 0.042695535822892594,
      "grad_norm": 1.0464001971870835,
      "kl": 0.032958984375,
      "learning_rate": 9.955088923725326e-07,
      "loss": 0.0013,
      "reward": 1.8705427646636963,
      "reward_std": 0.08714998513460159,
      "rewards/accuracy_reward": 0.71741783618927,
      "rewards/format_reward": 1.0,
      "step": 1404,
      "temperature": 1.0
    },
    {
      "all_correct": 0.375,
      "all_wrong": 0.375,
      "completion_length": 393.8125,
      "epoch": 0.04272594574869237,
      "grad_norm": 0.6390348862019546,
      "kl": 0.0274658203125,
      "learning_rate": 9.955025021167322e-07,
      "loss": 0.0011,
      "reward": 1.6036441326141357,
      "reward_std": 0.0829862654209137,
      "rewards/accuracy_reward": 0.491144061088562,
      "rewards/format_reward": 1.0,
      "step": 1405,
      "temperature": 1.0
    },
    {
      "all_correct": 0.625,
      "all_wrong": 0.25,
      "completion_length": 357.421875,
      "epoch": 0.04275635567449215,
      "grad_norm": 0.7531338243810934,
      "kl": 0.03125,
      "learning_rate": 9.95496107338455e-07,
      "loss": 0.0013,
      "reward": 1.859375,
      "reward_std": 0.07827534526586533,
      "rewards/accuracy_reward": 0.71875,
      "rewards/format_reward": 1.0,
      "step": 1406,
      "temperature": 1.0
    },
    {
      "all_correct": 0.625,
      "all_wrong": 0.125,
      "completion_length": 372.625,
      "epoch": 0.04278676560029194,
      "grad_norm": 12.204370174330474,
      "kl": 0.03125,
      "learning_rate": 9.9548970803776e-07,
      "loss": 0.0012,
      "reward": 1.9285497665405273,
      "reward_std": 0.061849795281887054,
      "rewards/accuracy_reward": 0.7597997784614563,
      "rewards/format_reward": 1.0,
      "step": 1407,
      "temperature": 1.0
    },
    {
      "all_correct": 0.375,
      "all_wrong": 0.25,
      "completion_length": 367.921875,
      "epoch": 0.04281717552609172,
      "grad_norm": 1.0758398476025555,
      "kl": 0.03662109375,
      "learning_rate": 9.954833042147053e-07,
      "loss": 0.0015,
      "reward": 1.641932725906372,
      "reward_std": 0.04902216047048569,
      "rewards/accuracy_reward": 0.4981827735900879,
      "rewards/format_reward": 1.0,
      "step": 1408,
      "temperature": 1.0
    },
    {
      "all_correct": 0.625,
      "all_wrong": 0.125,
      "completion_length": 380.125,
      "epoch": 0.0428475854518915,
      "grad_norm": 0.8605003205951494,
      "kl": 0.030029296875,
      "learning_rate": 9.954768958693493e-07,
      "loss": 0.0012,
      "reward": 1.8602197170257568,
      "reward_std": 0.09333300590515137,
      "rewards/accuracy_reward": 0.7070946097373962,
      "rewards/format_reward": 1.0,
      "step": 1409,
      "temperature": 1.0
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.125,
      "completion_length": 383.28125,
      "epoch": 0.042877995377691276,
      "grad_norm": 1.0673170244771828,
      "kl": 0.03564453125,
      "learning_rate": 9.954704830017504e-07,
      "loss": 0.0014,
      "reward": 1.8254494667053223,
      "reward_std": 0.040953077375888824,
      "rewards/accuracy_reward": 0.6598243713378906,
      "rewards/format_reward": 1.0,
      "step": 1410,
      "temperature": 1.0
    },
    {
      "all_correct": 0.375,
      "all_wrong": 0.0,
      "completion_length": 395.1875,
      "epoch": 0.04290840530349106,
      "grad_norm": 1.8896723220098544,
      "kl": 0.038330078125,
      "learning_rate": 9.954640656119674e-07,
      "loss": 0.0015,
      "reward": 1.643940806388855,
      "reward_std": 0.1714984029531479,
      "rewards/accuracy_reward": 0.5251908302307129,
      "rewards/format_reward": 1.0,
      "step": 1411,
      "temperature": 1.0
    },
    {
      "all_correct": 0.625,
      "all_wrong": 0.125,
      "completion_length": 376.640625,
      "epoch": 0.04293881522929084,
      "grad_norm": 0.627655840559016,
      "kl": 0.0301513671875,
      "learning_rate": 9.954576437000586e-07,
      "loss": 0.0012,
      "reward": 1.85562264919281,
      "reward_std": 0.07370621711015701,
      "rewards/accuracy_reward": 0.6993725895881653,
      "rewards/format_reward": 1.0,
      "step": 1412,
      "temperature": 1.0
    },
    {
      "all_correct": 0.625,
      "all_wrong": 0.125,
      "completion_length": 360.984375,
      "epoch": 0.04296922515509062,
      "grad_norm": 0.8558489581272183,
      "kl": 0.029052734375,
      "learning_rate": 9.954512172660827e-07,
      "loss": 0.0012,
      "reward": 1.881404161453247,
      "reward_std": 0.021881647408008575,
      "rewards/accuracy_reward": 0.7126542329788208,
      "rewards/format_reward": 1.0,
      "step": 1413,
      "temperature": 1.0
    },
    {
      "all_correct": 0.625,
      "all_wrong": 0.125,
      "completion_length": 352.890625,
      "epoch": 0.0429996350808904,
      "grad_norm": 1.2511134402312547,
      "kl": 0.033935546875,
      "learning_rate": 9.954447863100986e-07,
      "loss": 0.0014,
      "reward": 1.7999999523162842,
      "reward_std": 0.10819403827190399,
      "rewards/accuracy_reward": 0.671875,
      "rewards/format_reward": 1.0,
      "step": 1414,
      "temperature": 1.0
    },
    {
      "all_correct": 0.625,
      "all_wrong": 0.25,
      "completion_length": 371.1875,
      "epoch": 0.043030045006690186,
      "grad_norm": 0.5241430332937208,
      "kl": 0.03271484375,
      "learning_rate": 9.954383508321646e-07,
      "loss": 0.0013,
      "reward": 1.765625,
      "reward_std": 0.04419417306780815,
      "rewards/accuracy_reward": 0.640625,
      "rewards/format_reward": 1.0,
      "step": 1415,
      "temperature": 1.0
    },
    {
      "all_correct": 0.75,
      "all_wrong": 0.125,
      "completion_length": 362.203125,
      "epoch": 0.043060454932489965,
      "grad_norm": 0.8918081103657807,
      "kl": 0.0294189453125,
      "learning_rate": 9.954319108323396e-07,
      "loss": 0.0012,
      "reward": 2.0093750953674316,
      "reward_std": 0.07827534526586533,
      "rewards/accuracy_reward": 0.84375,
      "rewards/format_reward": 1.0,
      "step": 1416,
      "temperature": 1.0
    },
    {
      "all_correct": 0.375,
      "all_wrong": 0.0,
      "completion_length": 396.5,
      "epoch": 0.043090864858289744,
      "grad_norm": 1.2253805508398652,
      "kl": 0.032958984375,
      "learning_rate": 9.954254663106825e-07,
      "loss": 0.0013,
      "reward": 1.8449311256408691,
      "reward_std": 0.23291127383708954,
      "rewards/accuracy_reward": 0.6793060302734375,
      "rewards/format_reward": 1.0,
      "step": 1417,
      "temperature": 1.0
    },
    {
      "all_correct": 0.375,
      "all_wrong": 0.0,
      "completion_length": 366.78125,
      "epoch": 0.043121274784089524,
      "grad_norm": 1.9654714484621454,
      "kl": 0.039306640625,
      "learning_rate": 9.95419017267252e-07,
      "loss": 0.0016,
      "reward": 1.7403266429901123,
      "reward_std": 0.23603031039237976,
      "rewards/accuracy_reward": 0.5934516191482544,
      "rewards/format_reward": 1.0,
      "step": 1418,
      "temperature": 1.0
    },
    {
      "all_correct": 0.75,
      "all_wrong": 0.25,
      "completion_length": 374.828125,
      "epoch": 0.04315168470988931,
      "grad_norm": 0.7252879064139763,
      "kl": 0.03173828125,
      "learning_rate": 9.954125637021069e-07,
      "loss": 0.0013,
      "reward": 1.8968749046325684,
      "reward_std": 0.008838837966322899,
      "rewards/accuracy_reward": 0.75,
      "rewards/format_reward": 1.0,
      "step": 1419,
      "temperature": 1.0
    },
    {
      "all_correct": 0.375,
      "all_wrong": 0.0,
      "completion_length": 379.5625,
      "epoch": 0.04318209463568909,
      "grad_norm": 1.291367281172599,
      "kl": 0.0263671875,
      "learning_rate": 9.954061056153062e-07,
      "loss": 0.0011,
      "reward": 1.8468750715255737,
      "reward_std": 0.3137286603450775,
      "rewards/accuracy_reward": 0.71875,
      "rewards/format_reward": 1.0,
      "step": 1420,
      "temperature": 1.0
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.375,
      "completion_length": 367.1875,
      "epoch": 0.04321250456148887,
      "grad_norm": 0.7431683708603904,
      "kl": 0.036376953125,
      "learning_rate": 9.95399643006909e-07,
      "loss": 0.0015,
      "reward": 1.6340558528900146,
      "reward_std": 0.020328953862190247,
      "rewards/accuracy_reward": 0.5184307098388672,
      "rewards/format_reward": 1.0,
      "step": 1421,
      "temperature": 1.0
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.125,
      "completion_length": 395.65625,
      "epoch": 0.043242914487288654,
      "grad_norm": 3.2642062472615523,
      "kl": 0.030517578125,
      "learning_rate": 9.95393175876974e-07,
      "loss": 0.0012,
      "reward": 1.7997121810913086,
      "reward_std": 0.15055255591869354,
      "rewards/accuracy_reward": 0.6622122526168823,
      "rewards/format_reward": 1.0,
      "step": 1422,
      "temperature": 1.0
    },
    {
      "all_correct": 0.375,
      "all_wrong": 0.0,
      "completion_length": 381.828125,
      "epoch": 0.04327332441308843,
      "grad_norm": 1.3301865353911098,
      "kl": 0.036865234375,
      "learning_rate": 9.953867042255603e-07,
      "loss": 0.0015,
      "reward": 1.807694673538208,
      "reward_std": 0.10424507409334183,
      "rewards/accuracy_reward": 0.6264446973800659,
      "rewards/format_reward": 1.0,
      "step": 1423,
      "temperature": 1.0
    },
    {
      "all_correct": 0.625,
      "all_wrong": 0.0,
      "completion_length": 363.78125,
      "epoch": 0.04330373433888821,
      "grad_norm": 1.1818196479726868,
      "kl": 0.032958984375,
      "learning_rate": 9.95380228052727e-07,
      "loss": 0.0013,
      "reward": 2.0754377841949463,
      "reward_std": 0.19192728400230408,
      "rewards/accuracy_reward": 0.8910626173019409,
      "rewards/format_reward": 1.0,
      "step": 1424,
      "temperature": 1.0
    },
    {
      "all_correct": 0.625,
      "all_wrong": 0.0,
      "completion_length": 367.25,
      "epoch": 0.04333414426468799,
      "grad_norm": 1.6843413045092313,
      "kl": 0.029052734375,
      "learning_rate": 9.953737473585334e-07,
      "loss": 0.0012,
      "reward": 1.8454101085662842,
      "reward_std": 0.14871634542942047,
      "rewards/accuracy_reward": 0.70166015625,
      "rewards/format_reward": 1.0,
      "step": 1425,
      "temperature": 1.0
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.25,
      "completion_length": 372.234375,
      "epoch": 0.04336455419048778,
      "grad_norm": 1.276331012003874,
      "kl": 0.0341796875,
      "learning_rate": 9.95367262143038e-07,
      "loss": 0.0014,
      "reward": 1.659361481666565,
      "reward_std": 0.031196530908346176,
      "rewards/accuracy_reward": 0.5374864339828491,
      "rewards/format_reward": 1.0,
      "step": 1426,
      "temperature": 1.0
    },
    {
      "all_correct": 0.75,
      "all_wrong": 0.0,
      "completion_length": 361.34375,
      "epoch": 0.04339496411628756,
      "grad_norm": 0.8055627452554797,
      "kl": 0.0322265625,
      "learning_rate": 9.95360772406301e-07,
      "loss": 0.0013,
      "reward": 2.0843749046325684,
      "reward_std": 0.15845370292663574,
      "rewards/accuracy_reward": 0.90625,
      "rewards/format_reward": 1.0,
      "step": 1427,
      "temperature": 1.0
    },
    {
      "all_correct": 0.625,
      "all_wrong": 0.125,
      "completion_length": 385.609375,
      "epoch": 0.043425374042087336,
      "grad_norm": 0.8059394819486126,
      "kl": 0.03173828125,
      "learning_rate": 9.953542781483807e-07,
      "loss": 0.0013,
      "reward": 1.8274681568145752,
      "reward_std": 0.0897180512547493,
      "rewards/accuracy_reward": 0.6837181448936462,
      "rewards/format_reward": 1.0,
      "step": 1428,
      "temperature": 1.0
    },
    {
      "all_correct": 0.375,
      "all_wrong": 0.25,
      "completion_length": 377.84375,
      "epoch": 0.043455783967887116,
      "grad_norm": 0.9276925565644119,
      "kl": 0.028564453125,
      "learning_rate": 9.953477793693369e-07,
      "loss": 0.0011,
      "reward": 1.7710769176483154,
      "reward_std": 0.1064361035823822,
      "rewards/accuracy_reward": 0.627327024936676,
      "rewards/format_reward": 1.0,
      "step": 1429,
      "temperature": 1.0
    },
    {
      "all_correct": 0.75,
      "all_wrong": 0.25,
      "completion_length": 388.109375,
      "epoch": 0.0434861938936869,
      "grad_norm": 3.2544571345879536,
      "kl": 0.0291748046875,
      "learning_rate": 9.953412760692289e-07,
      "loss": 0.0012,
      "reward": 1.865625023841858,
      "reward_std": 0.06670259684324265,
      "rewards/accuracy_reward": 0.75,
      "rewards/format_reward": 0.96875,
      "step": 1430,
      "temperature": 1.0
    },
    {
      "all_correct": 0.375,
      "all_wrong": 0.25,
      "completion_length": 366.265625,
      "epoch": 0.04351660381948668,
      "grad_norm": 1.3343617979110485,
      "kl": 0.03173828125,
      "learning_rate": 9.953347682481156e-07,
      "loss": 0.0013,
      "reward": 1.7437500953674316,
      "reward_std": 0.20756080746650696,
      "rewards/accuracy_reward": 0.625,
      "rewards/format_reward": 1.0,
      "step": 1431,
      "temperature": 1.0
    },
    {
      "all_correct": 0.375,
      "all_wrong": 0.0,
      "completion_length": 394.453125,
      "epoch": 0.04354701374528646,
      "grad_norm": 1.450442021026999,
      "kl": 0.035888671875,
      "learning_rate": 9.953282559060569e-07,
      "loss": 0.0014,
      "reward": 1.8605952262878418,
      "reward_std": 0.1639946699142456,
      "rewards/accuracy_reward": 0.6887201070785522,
      "rewards/format_reward": 1.0,
      "step": 1432,
      "temperature": 1.0
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.0,
      "completion_length": 366.234375,
      "epoch": 0.04357742367108624,
      "grad_norm": 0.987437961895171,
      "kl": 0.0277099609375,
      "learning_rate": 9.95321739043112e-07,
      "loss": 0.0011,
      "reward": 1.969940423965454,
      "reward_std": 0.17938214540481567,
      "rewards/accuracy_reward": 0.804315447807312,
      "rewards/format_reward": 1.0,
      "step": 1433,
      "temperature": 1.0
    },
    {
      "all_correct": 0.75,
      "all_wrong": 0.0,
      "completion_length": 358.984375,
      "epoch": 0.043607833596886025,
      "grad_norm": 2.2142698310124245,
      "kl": 0.031494140625,
      "learning_rate": 9.953152176593407e-07,
      "loss": 0.0013,
      "reward": 2.014552116394043,
      "reward_std": 0.0031000934541225433,
      "rewards/accuracy_reward": 0.8145519495010376,
      "rewards/format_reward": 1.0,
      "step": 1434,
      "temperature": 1.0
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.25,
      "completion_length": 363.3125,
      "epoch": 0.043638243522685805,
      "grad_norm": 0.9724225933249551,
      "kl": 0.0283203125,
      "learning_rate": 9.953086917548022e-07,
      "loss": 0.0011,
      "reward": 1.7427167892456055,
      "reward_std": 0.1048978716135025,
      "rewards/accuracy_reward": 0.6114667654037476,
      "rewards/format_reward": 1.0,
      "step": 1435,
      "temperature": 1.0
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.0,
      "completion_length": 373.875,
      "epoch": 0.043668653448485584,
      "grad_norm": 4.108701607153318,
      "kl": 0.035400390625,
      "learning_rate": 9.953021613295559e-07,
      "loss": 0.0014,
      "reward": 1.7902079820632935,
      "reward_std": 0.11418286710977554,
      "rewards/accuracy_reward": 0.6402080059051514,
      "rewards/format_reward": 1.0,
      "step": 1436,
      "temperature": 1.0
    },
    {
      "all_correct": 0.25,
      "all_wrong": 0.25,
      "completion_length": 363.46875,
      "epoch": 0.04369906337428537,
      "grad_norm": 1.1077681661337027,
      "kl": 0.033203125,
      "learning_rate": 9.952956263836617e-07,
      "loss": 0.0013,
      "reward": 1.600822925567627,
      "reward_std": 0.10736281424760818,
      "rewards/accuracy_reward": 0.4664478302001953,
      "rewards/format_reward": 1.0,
      "step": 1437,
      "temperature": 1.0
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.125,
      "completion_length": 367.890625,
      "epoch": 0.04372947330008515,
      "grad_norm": 1.1097933376317737,
      "kl": 0.03173828125,
      "learning_rate": 9.952890869171794e-07,
      "loss": 0.0013,
      "reward": 1.7584264278411865,
      "reward_std": 0.07671654224395752,
      "rewards/accuracy_reward": 0.6115514636039734,
      "rewards/format_reward": 1.0,
      "step": 1438,
      "temperature": 1.0
    },
    {
      "all_correct": 0.625,
      "all_wrong": 0.375,
      "completion_length": 346.234375,
      "epoch": 0.04375988322588493,
      "grad_norm": 0.6745761165047038,
      "kl": 0.0299072265625,
      "learning_rate": 9.952825429301682e-07,
      "loss": 0.0012,
      "reward": 1.7468750476837158,
      "reward_std": 0.008838837966322899,
      "rewards/accuracy_reward": 0.625,
      "rewards/format_reward": 1.0,
      "step": 1439,
      "temperature": 1.0
    },
    {
      "all_correct": 0.625,
      "all_wrong": 0.25,
      "completion_length": 351.6875,
      "epoch": 0.04379029315168471,
      "grad_norm": 0.9534164564023454,
      "kl": 0.0380859375,
      "learning_rate": 9.95275994422688e-07,
      "loss": 0.0015,
      "reward": 1.8374111652374268,
      "reward_std": 0.02175387367606163,
      "rewards/accuracy_reward": 0.6999111771583557,
      "rewards/format_reward": 1.0,
      "step": 1440,
      "temperature": 1.0
    },
    {
      "all_correct": 0.375,
      "all_wrong": 0.25,
      "completion_length": 347.359375,
      "epoch": 0.043820703077484494,
      "grad_norm": 2.998131961463864,
      "kl": 0.031982421875,
      "learning_rate": 9.95269441394799e-07,
      "loss": 0.0013,
      "reward": 1.722355842590332,
      "reward_std": 0.14863130450248718,
      "rewards/accuracy_reward": 0.5973557233810425,
      "rewards/format_reward": 1.0,
      "step": 1441,
      "temperature": 1.0
    },
    {
      "all_correct": 0.375,
      "all_wrong": 0.125,
      "completion_length": 370.671875,
      "epoch": 0.04385111300328427,
      "grad_norm": 1.1586711093082385,
      "kl": 0.03173828125,
      "learning_rate": 9.952628838465605e-07,
      "loss": 0.0013,
      "reward": 1.5950384140014648,
      "reward_std": 0.1618431806564331,
      "rewards/accuracy_reward": 0.4950385093688965,
      "rewards/format_reward": 1.0,
      "step": 1442,
      "temperature": 1.0
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.125,
      "completion_length": 367.703125,
      "epoch": 0.04388152292908405,
      "grad_norm": 1.26135537462759,
      "kl": 0.03173828125,
      "learning_rate": 9.952563217780325e-07,
      "loss": 0.0013,
      "reward": 1.8301081657409668,
      "reward_std": 0.045346699655056,
      "rewards/accuracy_reward": 0.6676081418991089,
      "rewards/format_reward": 1.0,
      "step": 1443,
      "temperature": 1.0
    },
    {
      "all_correct": 0.375,
      "all_wrong": 0.125,
      "completion_length": 390.59375,
      "epoch": 0.04391193285488383,
      "grad_norm": 2.282157513676405,
      "kl": 0.0311279296875,
      "learning_rate": 9.95249755189275e-07,
      "loss": 0.0012,
      "reward": 1.777186632156372,
      "reward_std": 0.1454283595085144,
      "rewards/accuracy_reward": 0.6365616321563721,
      "rewards/format_reward": 1.0,
      "step": 1444,
      "temperature": 1.0
    },
    {
      "all_correct": 0.25,
      "all_wrong": 0.25,
      "completion_length": 389.0,
      "epoch": 0.04394234278068362,
      "grad_norm": 0.8608242583449095,
      "kl": 0.031982421875,
      "learning_rate": 9.952431840803476e-07,
      "loss": 0.0013,
      "reward": 1.6358062028884888,
      "reward_std": 0.1612795889377594,
      "rewards/accuracy_reward": 0.5014311075210571,
      "rewards/format_reward": 1.0,
      "step": 1445,
      "temperature": 1.0
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.25,
      "completion_length": 359.421875,
      "epoch": 0.043972752706483396,
      "grad_norm": 0.910701737075201,
      "kl": 0.03662109375,
      "learning_rate": 9.952366084513108e-07,
      "loss": 0.0015,
      "reward": 1.6645950078964233,
      "reward_std": 0.06247019022703171,
      "rewards/accuracy_reward": 0.5458450317382812,
      "rewards/format_reward": 1.0,
      "step": 1446,
      "temperature": 1.0
    },
    {
      "all_correct": 0.625,
      "all_wrong": 0.0,
      "completion_length": 358.8125,
      "epoch": 0.044003162632283176,
      "grad_norm": 0.9767069762444006,
      "kl": 0.0341796875,
      "learning_rate": 9.952300283022242e-07,
      "loss": 0.0014,
      "reward": 1.949601411819458,
      "reward_std": 0.079706110060215,
      "rewards/accuracy_reward": 0.7621012926101685,
      "rewards/format_reward": 1.0,
      "step": 1447,
      "temperature": 1.0
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.125,
      "completion_length": 381.4375,
      "epoch": 0.044033572558082955,
      "grad_norm": 1.9448086284847381,
      "kl": 0.0390625,
      "learning_rate": 9.952234436331478e-07,
      "loss": 0.0016,
      "reward": 1.7736895084381104,
      "reward_std": 0.09731435775756836,
      "rewards/accuracy_reward": 0.6424395442008972,
      "rewards/format_reward": 1.0,
      "step": 1448,
      "temperature": 1.0
    },
    {
      "all_correct": 0.375,
      "all_wrong": 0.25,
      "completion_length": 362.296875,
      "epoch": 0.04406398248388274,
      "grad_norm": 1.808786301810168,
      "kl": 0.033935546875,
      "learning_rate": 9.952168544441423e-07,
      "loss": 0.0014,
      "reward": 1.677612543106079,
      "reward_std": 0.07382393628358841,
      "rewards/accuracy_reward": 0.5588625073432922,
      "rewards/format_reward": 1.0,
      "step": 1449,
      "temperature": 1.0
    },
    {
      "all_correct": 0.625,
      "all_wrong": 0.0,
      "completion_length": 372.84375,
      "epoch": 0.04409439240968252,
      "grad_norm": 1.4327497868631311,
      "kl": 0.03369140625,
      "learning_rate": 9.952102607352673e-07,
      "loss": 0.0014,
      "reward": 1.9167944192886353,
      "reward_std": 0.09248004108667374,
      "rewards/accuracy_reward": 0.7386693954467773,
      "rewards/format_reward": 1.0,
      "step": 1450,
      "temperature": 1.0
    },
    {
      "all_correct": 0.375,
      "all_wrong": 0.25,
      "completion_length": 395.109375,
      "epoch": 0.0441248023354823,
      "grad_norm": 0.7832087926653342,
      "kl": 0.0281982421875,
      "learning_rate": 9.952036625065828e-07,
      "loss": 0.0011,
      "reward": 1.6026294231414795,
      "reward_std": 0.1323229968547821,
      "rewards/accuracy_reward": 0.4932544231414795,
      "rewards/format_reward": 1.0,
      "step": 1451,
      "temperature": 1.0
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.125,
      "completion_length": 373.171875,
      "epoch": 0.044155212261282085,
      "grad_norm": 1.6010255559511783,
      "kl": 0.029541015625,
      "learning_rate": 9.951970597581498e-07,
      "loss": 0.0012,
      "reward": 1.840694546699524,
      "reward_std": 0.09693321585655212,
      "rewards/accuracy_reward": 0.6844445466995239,
      "rewards/format_reward": 1.0,
      "step": 1452,
      "temperature": 1.0
    },
    {
      "all_correct": 0.75,
      "all_wrong": 0.25,
      "completion_length": 355.8125,
      "epoch": 0.044185622187081865,
      "grad_norm": 0.5271208169338722,
      "kl": 0.034912109375,
      "learning_rate": 9.95190452490028e-07,
      "loss": 0.0014,
      "reward": 1.8937500715255737,
      "reward_std": 0.011572758667171001,
      "rewards/accuracy_reward": 0.75,
      "rewards/format_reward": 1.0,
      "step": 1453,
      "temperature": 1.0
    },
    {
      "all_correct": 0.875,
      "all_wrong": 0.0,
      "completion_length": 345.859375,
      "epoch": 0.044216032112881644,
      "grad_norm": 0.44727881987488494,
      "kl": 0.038818359375,
      "learning_rate": 9.951838407022776e-07,
      "loss": 0.0016,
      "reward": 2.1750001907348633,
      "reward_std": 0.051754921674728394,
      "rewards/accuracy_reward": 0.984375,
      "rewards/format_reward": 1.0,
      "step": 1454,
      "temperature": 1.0
    },
    {
      "all_correct": 0.875,
      "all_wrong": 0.125,
      "completion_length": 348.4375,
      "epoch": 0.04424644203868142,
      "grad_norm": 0.10081682621202316,
      "kl": 0.03955078125,
      "learning_rate": 9.951772243949592e-07,
      "loss": 0.0016,
      "reward": 2.0500001907348633,
      "reward_std": 0.0,
      "rewards/accuracy_reward": 0.875,
      "rewards/format_reward": 1.0,
      "step": 1455,
      "temperature": 1.0
    },
    {
      "all_correct": 0.75,
      "all_wrong": 0.0,
      "completion_length": 364.03125,
      "epoch": 0.04427685196448121,
      "grad_norm": 0.9522053523432532,
      "kl": 0.04248046875,
      "learning_rate": 9.951706035681332e-07,
      "loss": 0.0017,
      "reward": 2.031747817993164,
      "reward_std": 0.015882009640336037,
      "rewards/accuracy_reward": 0.8348726034164429,
      "rewards/format_reward": 1.0,
      "step": 1456,
      "temperature": 1.0
    },
    {
      "all_correct": 0.75,
      "all_wrong": 0.0,
      "completion_length": 368.296875,
      "epoch": 0.04430726189028099,
      "grad_norm": 1.0419885343848692,
      "kl": 0.02783203125,
      "learning_rate": 9.9516397822186e-07,
      "loss": 0.0011,
      "reward": 2.1232306957244873,
      "reward_std": 0.09801394492387772,
      "rewards/accuracy_reward": 0.935730516910553,
      "rewards/format_reward": 1.0,
      "step": 1457,
      "temperature": 1.0
    },
    {
      "all_correct": 0.625,
      "all_wrong": 0.0,
      "completion_length": 392.578125,
      "epoch": 0.04433767181608077,
      "grad_norm": 1.8517418142135063,
      "kl": 0.029296875,
      "learning_rate": 9.951573483561999e-07,
      "loss": 0.0012,
      "reward": 1.9896379709243774,
      "reward_std": 0.07773250341415405,
      "rewards/accuracy_reward": 0.7990127801895142,
      "rewards/format_reward": 1.0,
      "step": 1458,
      "temperature": 1.0
    },
    {
      "all_correct": 0.375,
      "all_wrong": 0.0,
      "completion_length": 365.453125,
      "epoch": 0.04436808174188055,
      "grad_norm": 1.2500016498987283,
      "kl": 0.0361328125,
      "learning_rate": 9.951507139712135e-07,
      "loss": 0.0014,
      "reward": 1.8249154090881348,
      "reward_std": 0.1567482054233551,
      "rewards/accuracy_reward": 0.6592903137207031,
      "rewards/format_reward": 1.0,
      "step": 1459,
      "temperature": 1.0
    },
    {
      "all_correct": 0.375,
      "all_wrong": 0.25,
      "completion_length": 352.515625,
      "epoch": 0.04439849166768033,
      "grad_norm": 1.0363516727280049,
      "kl": 0.041748046875,
      "learning_rate": 9.951440750669617e-07,
      "loss": 0.0017,
      "reward": 1.7068523168563843,
      "reward_std": 0.13696826994419098,
      "rewards/accuracy_reward": 0.5724773406982422,
      "rewards/format_reward": 1.0,
      "step": 1460,
      "temperature": 1.0
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.125,
      "completion_length": 375.46875,
      "epoch": 0.04442890159348011,
      "grad_norm": 1.1356562122457683,
      "kl": 0.0299072265625,
      "learning_rate": 9.951374316435044e-07,
      "loss": 0.0012,
      "reward": 1.8911783695220947,
      "reward_std": 0.15338963270187378,
      "rewards/accuracy_reward": 0.7349283695220947,
      "rewards/format_reward": 1.0,
      "step": 1461,
      "temperature": 1.0
    },
    {
      "all_correct": 0.875,
      "all_wrong": 0.0,
      "completion_length": 357.140625,
      "epoch": 0.04445931151927989,
      "grad_norm": 0.7839827207417605,
      "kl": 0.031005859375,
      "learning_rate": 9.95130783700903e-07,
      "loss": 0.0012,
      "reward": 2.117067337036133,
      "reward_std": 0.08855694532394409,
      "rewards/accuracy_reward": 0.932692289352417,
      "rewards/format_reward": 1.0,
      "step": 1462,
      "temperature": 1.0
    },
    {
      "all_correct": 0.625,
      "all_wrong": 0.125,
      "completion_length": 370.453125,
      "epoch": 0.04448972144507968,
      "grad_norm": 1.5040226846370996,
      "kl": 0.0322265625,
      "learning_rate": 9.951241312392175e-07,
      "loss": 0.0013,
      "reward": 1.926222801208496,
      "reward_std": 0.11093716323375702,
      "rewards/accuracy_reward": 0.7730978727340698,
      "rewards/format_reward": 1.0,
      "step": 1463,
      "temperature": 1.0
    },
    {
      "all_correct": 0.625,
      "all_wrong": 0.0,
      "completion_length": 376.34375,
      "epoch": 0.04452013137087946,
      "grad_norm": 1.1288581066217378,
      "kl": 0.031982421875,
      "learning_rate": 9.95117474258509e-07,
      "loss": 0.0013,
      "reward": 1.8765690326690674,
      "reward_std": 0.16353511810302734,
      "rewards/accuracy_reward": 0.7328190803527832,
      "rewards/format_reward": 1.0,
      "step": 1464,
      "temperature": 1.0
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.125,
      "completion_length": 371.1875,
      "epoch": 0.044550541296679236,
      "grad_norm": 1.0099541617495906,
      "kl": 0.041015625,
      "learning_rate": 9.951108127588384e-07,
      "loss": 0.0016,
      "reward": 1.8732120990753174,
      "reward_std": 0.03758494183421135,
      "rewards/accuracy_reward": 0.7075871229171753,
      "rewards/format_reward": 1.0,
      "step": 1465,
      "temperature": 1.0
    },
    {
      "all_correct": 0.25,
      "all_wrong": 0.25,
      "completion_length": 357.671875,
      "epoch": 0.044580951222479015,
      "grad_norm": 1.07112950703109,
      "kl": 0.039794921875,
      "learning_rate": 9.951041467402662e-07,
      "loss": 0.0016,
      "reward": 1.6632583141326904,
      "reward_std": 0.14806610345840454,
      "rewards/accuracy_reward": 0.5288832187652588,
      "rewards/format_reward": 1.0,
      "step": 1466,
      "temperature": 1.0
    },
    {
      "all_correct": 0.375,
      "all_wrong": 0.0,
      "completion_length": 399.53125,
      "epoch": 0.0446113611482788,
      "grad_norm": 1.0910665962681687,
      "kl": 0.03662109375,
      "learning_rate": 9.950974762028531e-07,
      "loss": 0.0015,
      "reward": 1.8939828872680664,
      "reward_std": 0.1992325782775879,
      "rewards/accuracy_reward": 0.7221077680587769,
      "rewards/format_reward": 1.0,
      "step": 1467,
      "temperature": 1.0
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.125,
      "completion_length": 390.03125,
      "epoch": 0.04464177107407858,
      "grad_norm": 0.9213723719201844,
      "kl": 0.027099609375,
      "learning_rate": 9.950908011466604e-07,
      "loss": 0.0011,
      "reward": 1.8288965225219727,
      "reward_std": 0.10781900584697723,
      "rewards/accuracy_reward": 0.6820214986801147,
      "rewards/format_reward": 0.984375,
      "step": 1468,
      "temperature": 1.0
    },
    {
      "all_correct": 0.25,
      "all_wrong": 0.0,
      "completion_length": 425.453125,
      "epoch": 0.04467218099987836,
      "grad_norm": 1.6946295284192618,
      "kl": 0.03564453125,
      "learning_rate": 9.950841215717486e-07,
      "loss": 0.0014,
      "reward": 1.7433699369430542,
      "reward_std": 0.15014700591564178,
      "rewards/accuracy_reward": 0.5839948654174805,
      "rewards/format_reward": 1.0,
      "step": 1469,
      "temperature": 1.0
    },
    {
      "all_correct": 0.75,
      "all_wrong": 0.125,
      "completion_length": 366.265625,
      "epoch": 0.04470259092567814,
      "grad_norm": 0.6684982927040791,
      "kl": 0.028564453125,
      "learning_rate": 9.950774374781791e-07,
      "loss": 0.0011,
      "reward": 2.000401020050049,
      "reward_std": 0.017368635162711143,
      "rewards/accuracy_reward": 0.8285259008407593,
      "rewards/format_reward": 1.0,
      "step": 1470,
      "temperature": 1.0
    },
    {
      "all_correct": 0.875,
      "all_wrong": 0.0,
      "completion_length": 357.140625,
      "epoch": 0.044733000851477925,
      "grad_norm": 0.4506155515392534,
      "kl": 0.0308837890625,
      "learning_rate": 9.950707488660128e-07,
      "loss": 0.0012,
      "reward": 2.065624952316284,
      "reward_std": 0.04419417306780815,
      "rewards/accuracy_reward": 0.890625,
      "rewards/format_reward": 1.0,
      "step": 1471,
      "temperature": 1.0
    },
    {
      "all_correct": 0.625,
      "all_wrong": 0.0,
      "completion_length": 358.453125,
      "epoch": 0.044763410777277704,
      "grad_norm": 1.2973050479991999,
      "kl": 0.03466796875,
      "learning_rate": 9.950640557353105e-07,
      "loss": 0.0014,
      "reward": 1.909334421157837,
      "reward_std": 0.12173619866371155,
      "rewards/accuracy_reward": 0.7593344449996948,
      "rewards/format_reward": 1.0,
      "step": 1472,
      "temperature": 1.0
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.0,
      "completion_length": 406.8125,
      "epoch": 0.04479382070307748,
      "grad_norm": 0.9705975908672091,
      "kl": 0.0301513671875,
      "learning_rate": 9.950573580861334e-07,
      "loss": 0.0012,
      "reward": 1.8421473503112793,
      "reward_std": 0.15772631764411926,
      "rewards/accuracy_reward": 0.7108972668647766,
      "rewards/format_reward": 0.96875,
      "step": 1473,
      "temperature": 1.0
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.125,
      "completion_length": 365.234375,
      "epoch": 0.04482423062887726,
      "grad_norm": 1.7751361517240847,
      "kl": 0.03759765625,
      "learning_rate": 9.950506559185427e-07,
      "loss": 0.0015,
      "reward": 1.8007440567016602,
      "reward_std": 0.13253821432590485,
      "rewards/accuracy_reward": 0.6601190567016602,
      "rewards/format_reward": 1.0,
      "step": 1474,
      "temperature": 1.0
    },
    {
      "all_correct": 0.75,
      "all_wrong": 0.0,
      "completion_length": 351.75,
      "epoch": 0.04485464055467705,
      "grad_norm": 1.0231435562934674,
      "kl": 0.032470703125,
      "learning_rate": 9.950439492325996e-07,
      "loss": 0.0013,
      "reward": 1.9802191257476807,
      "reward_std": 0.04725078493356705,
      "rewards/accuracy_reward": 0.8052189350128174,
      "rewards/format_reward": 1.0,
      "step": 1475,
      "temperature": 1.0
    },
    {
      "all_correct": 0.375,
      "all_wrong": 0.125,
      "completion_length": 385.609375,
      "epoch": 0.04488505048047683,
      "grad_norm": 6.207218521375364,
      "kl": 0.03515625,
      "learning_rate": 9.950372380283652e-07,
      "loss": 0.0014,
      "reward": 1.627403736114502,
      "reward_std": 0.19693249464035034,
      "rewards/accuracy_reward": 0.5055287480354309,
      "rewards/format_reward": 1.0,
      "step": 1476,
      "temperature": 1.0
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.0,
      "completion_length": 376.953125,
      "epoch": 0.04491546040627661,
      "grad_norm": 2.93981818317281,
      "kl": 0.0361328125,
      "learning_rate": 9.950305223059006e-07,
      "loss": 0.0014,
      "reward": 1.8260126113891602,
      "reward_std": 0.14023137092590332,
      "rewards/accuracy_reward": 0.6760127544403076,
      "rewards/format_reward": 1.0,
      "step": 1477,
      "temperature": 1.0
    },
    {
      "all_correct": 0.0,
      "all_wrong": 0.125,
      "completion_length": 400.578125,
      "epoch": 0.04494587033207639,
      "grad_norm": 1.439020652240854,
      "kl": 0.02880859375,
      "learning_rate": 9.950238020652674e-07,
      "loss": 0.0012,
      "reward": 1.4315876960754395,
      "reward_std": 0.2973781228065491,
      "rewards/accuracy_reward": 0.3378376364707947,
      "rewards/format_reward": 1.0,
      "step": 1478,
      "temperature": 1.0
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.375,
      "completion_length": 349.578125,
      "epoch": 0.04497628025787617,
      "grad_norm": 1.1143370649172963,
      "kl": 0.036376953125,
      "learning_rate": 9.95017077306527e-07,
      "loss": 0.0015,
      "reward": 1.6362563371658325,
      "reward_std": 0.02975967898964882,
      "rewards/accuracy_reward": 0.5206311941146851,
      "rewards/format_reward": 1.0,
      "step": 1479,
      "temperature": 1.0
    },
    {
      "all_correct": 0.375,
      "all_wrong": 0.25,
      "completion_length": 348.265625,
      "epoch": 0.04500669018367595,
      "grad_norm": 52.814293823995925,
      "kl": 0.03173828125,
      "learning_rate": 9.950103480297404e-07,
      "loss": 0.0013,
      "reward": 1.6327314376831055,
      "reward_std": 0.14577078819274902,
      "rewards/accuracy_reward": 0.5171064138412476,
      "rewards/format_reward": 1.0,
      "step": 1480,
      "temperature": 1.0
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.0,
      "completion_length": 359.15625,
      "epoch": 0.04503710010947573,
      "grad_norm": 1.4963436162267556,
      "kl": 0.030517578125,
      "learning_rate": 9.950036142349695e-07,
      "loss": 0.0012,
      "reward": 1.9544835090637207,
      "reward_std": 0.14945869147777557,
      "rewards/accuracy_reward": 0.7951084971427917,
      "rewards/format_reward": 1.0,
      "step": 1481,
      "temperature": 1.0
    },
    {
      "all_correct": 0.875,
      "all_wrong": 0.0,
      "completion_length": 356.234375,
      "epoch": 0.04506751003527552,
      "grad_norm": 0.879946397617088,
      "kl": 0.0301513671875,
      "learning_rate": 9.949968759222753e-07,
      "loss": 0.0012,
      "reward": 2.13305926322937,
      "reward_std": 0.07978584617376328,
      "rewards/accuracy_reward": 0.9424341917037964,
      "rewards/format_reward": 1.0,
      "step": 1482,
      "temperature": 1.0
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.125,
      "completion_length": 378.078125,
      "epoch": 0.045097919961075296,
      "grad_norm": 1.0536098493703574,
      "kl": 0.029052734375,
      "learning_rate": 9.949901330917194e-07,
      "loss": 0.0012,
      "reward": 1.7526874542236328,
      "reward_std": 0.18059033155441284,
      "rewards/accuracy_reward": 0.6308124661445618,
      "rewards/format_reward": 1.0,
      "step": 1483,
      "temperature": 1.0
    },
    {
      "all_correct": 0.625,
      "all_wrong": 0.0,
      "completion_length": 346.390625,
      "epoch": 0.045128329886875075,
      "grad_norm": 1.2153050194043369,
      "kl": 0.0390625,
      "learning_rate": 9.949833857433635e-07,
      "loss": 0.0016,
      "reward": 2.0583395957946777,
      "reward_std": 0.12933349609375,
      "rewards/accuracy_reward": 0.870839536190033,
      "rewards/format_reward": 1.0,
      "step": 1484,
      "temperature": 1.0
    },
    {
      "all_correct": 0.375,
      "all_wrong": 0.25,
      "completion_length": 393.375,
      "epoch": 0.045158739812674854,
      "grad_norm": 3.9483433435626623,
      "kl": 0.0230712890625,
      "learning_rate": 9.949766338772691e-07,
      "loss": 0.0009,
      "reward": 1.6679595708847046,
      "reward_std": 0.17675693333148956,
      "rewards/accuracy_reward": 0.5617096424102783,
      "rewards/format_reward": 1.0,
      "step": 1485,
      "temperature": 1.0
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.125,
      "completion_length": 353.265625,
      "epoch": 0.04518914973847464,
      "grad_norm": 2.083860712177062,
      "kl": 0.032470703125,
      "learning_rate": 9.94969877493498e-07,
      "loss": 0.0013,
      "reward": 1.760359287261963,
      "reward_std": 0.13927516341209412,
      "rewards/accuracy_reward": 0.6353593468666077,
      "rewards/format_reward": 1.0,
      "step": 1486,
      "temperature": 1.0
    },
    {
      "all_correct": 0.625,
      "all_wrong": 0.0,
      "completion_length": 377.203125,
      "epoch": 0.04521955966427442,
      "grad_norm": 0.8942759642987876,
      "kl": 0.026611328125,
      "learning_rate": 9.949631165921114e-07,
      "loss": 0.0011,
      "reward": 1.9829045534133911,
      "reward_std": 0.07493706792593002,
      "rewards/accuracy_reward": 0.8235296010971069,
      "rewards/format_reward": 1.0,
      "step": 1487,
      "temperature": 1.0
    },
    {
      "all_correct": 0.625,
      "all_wrong": 0.0,
      "completion_length": 360.578125,
      "epoch": 0.0452499695900742,
      "grad_norm": 6.610008308402162,
      "kl": 0.0380859375,
      "learning_rate": 9.949563511731716e-07,
      "loss": 0.0015,
      "reward": 1.9175341129302979,
      "reward_std": 0.09986317157745361,
      "rewards/accuracy_reward": 0.7550340294837952,
      "rewards/format_reward": 1.0,
      "step": 1488,
      "temperature": 1.0
    },
    {
      "all_correct": 0.625,
      "all_wrong": 0.25,
      "completion_length": 347.21875,
      "epoch": 0.04528037951587398,
      "grad_norm": 0.8990897090069695,
      "kl": 0.036865234375,
      "learning_rate": 9.9494958123674e-07,
      "loss": 0.0015,
      "reward": 1.7609374523162842,
      "reward_std": 0.05287374183535576,
      "rewards/accuracy_reward": 0.6390625238418579,
      "rewards/format_reward": 1.0,
      "step": 1489,
      "temperature": 1.0
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.0,
      "completion_length": 376.6875,
      "epoch": 0.045310789441673764,
      "grad_norm": 0.9662755782125431,
      "kl": 0.037841796875,
      "learning_rate": 9.949428067828783e-07,
      "loss": 0.0015,
      "reward": 1.7970421314239502,
      "reward_std": 0.15590900182724,
      "rewards/accuracy_reward": 0.6407921314239502,
      "rewards/format_reward": 1.0,
      "step": 1490,
      "temperature": 1.0
    },
    {
      "all_correct": 0.375,
      "all_wrong": 0.125,
      "completion_length": 385.21875,
      "epoch": 0.04534119936747354,
      "grad_norm": 2.9788792687465406,
      "kl": 0.032958984375,
      "learning_rate": 9.949360278116485e-07,
      "loss": 0.0013,
      "reward": 1.8427278995513916,
      "reward_std": 0.07297234237194061,
      "rewards/accuracy_reward": 0.6771028637886047,
      "rewards/format_reward": 1.0,
      "step": 1491,
      "temperature": 1.0
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.0,
      "completion_length": 382.65625,
      "epoch": 0.04537160929327332,
      "grad_norm": 1.1218463639658613,
      "kl": 0.038330078125,
      "learning_rate": 9.949292443231126e-07,
      "loss": 0.0015,
      "reward": 1.8783656358718872,
      "reward_std": 0.15227922797203064,
      "rewards/accuracy_reward": 0.7064905762672424,
      "rewards/format_reward": 1.0,
      "step": 1492,
      "temperature": 1.0
    },
    {
      "all_correct": 0.375,
      "all_wrong": 0.0,
      "completion_length": 357.1875,
      "epoch": 0.04540201921907311,
      "grad_norm": 1.131043023543099,
      "kl": 0.036376953125,
      "learning_rate": 9.949224563173324e-07,
      "loss": 0.0015,
      "reward": 1.9406839609146118,
      "reward_std": 0.13163180649280548,
      "rewards/accuracy_reward": 0.7469338774681091,
      "rewards/format_reward": 1.0,
      "step": 1493,
      "temperature": 1.0
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.0,
      "completion_length": 350.875,
      "epoch": 0.04543242914487289,
      "grad_norm": 1.3116104831704865,
      "kl": 0.0458984375,
      "learning_rate": 9.949156637943697e-07,
      "loss": 0.0018,
      "reward": 1.8398926258087158,
      "reward_std": 0.17847460508346558,
      "rewards/accuracy_reward": 0.6836427450180054,
      "rewards/format_reward": 1.0,
      "step": 1494,
      "temperature": 1.0
    },
    {
      "all_correct": 0.625,
      "all_wrong": 0.0,
      "completion_length": 366.609375,
      "epoch": 0.04546283907067267,
      "grad_norm": 1.1352401894710695,
      "kl": 0.030029296875,
      "learning_rate": 9.949088667542864e-07,
      "loss": 0.0012,
      "reward": 1.9238330125808716,
      "reward_std": 0.13391874730587006,
      "rewards/accuracy_reward": 0.7582079768180847,
      "rewards/format_reward": 1.0,
      "step": 1495,
      "temperature": 1.0
    },
    {
      "all_correct": 0.75,
      "all_wrong": 0.0,
      "completion_length": 373.78125,
      "epoch": 0.045493248996472446,
      "grad_norm": 1.0897315557312168,
      "kl": 0.0322265625,
      "learning_rate": 9.949020651971452e-07,
      "loss": 0.0013,
      "reward": 2.01607084274292,
      "reward_std": 0.016686681658029556,
      "rewards/accuracy_reward": 0.8191959857940674,
      "rewards/format_reward": 1.0,
      "step": 1496,
      "temperature": 1.0
    },
    {
      "all_correct": 0.875,
      "all_wrong": 0.0,
      "completion_length": 369.578125,
      "epoch": 0.04552365892227223,
      "grad_norm": 0.6101103446317552,
      "kl": 0.0277099609375,
      "learning_rate": 9.948952591230072e-07,
      "loss": 0.0011,
      "reward": 2.178379535675049,
      "reward_std": 0.058348141610622406,
      "rewards/accuracy_reward": 0.981504499912262,
      "rewards/format_reward": 1.0,
      "step": 1497,
      "temperature": 1.0
    },
    {
      "all_correct": 0.375,
      "all_wrong": 0.0,
      "completion_length": 376.125,
      "epoch": 0.04555406884807201,
      "grad_norm": 1.1957024426430471,
      "kl": 0.03759765625,
      "learning_rate": 9.948884485319354e-07,
      "loss": 0.0015,
      "reward": 1.9359761476516724,
      "reward_std": 0.23552243411540985,
      "rewards/accuracy_reward": 0.7703511118888855,
      "rewards/format_reward": 1.0,
      "step": 1498,
      "temperature": 1.0
    },
    {
      "all_correct": 0.375,
      "all_wrong": 0.0,
      "completion_length": 382.140625,
      "epoch": 0.04558447877387179,
      "grad_norm": 2.422783128951826,
      "kl": 0.041748046875,
      "learning_rate": 9.948816334239916e-07,
      "loss": 0.0017,
      "reward": 1.7369554042816162,
      "reward_std": 0.17986533045768738,
      "rewards/accuracy_reward": 0.5869553089141846,
      "rewards/format_reward": 1.0,
      "step": 1499,
      "temperature": 1.0
    },
    {
      "all_correct": 0.75,
      "all_wrong": 0.125,
      "completion_length": 344.9375,
      "epoch": 0.04561488869967157,
      "grad_norm": 0.573565526773741,
      "kl": 0.03466796875,
      "learning_rate": 9.94874813799238e-07,
      "loss": 0.0014,
      "reward": 2.0133042335510254,
      "reward_std": 0.015123185701668262,
      "rewards/accuracy_reward": 0.8383040428161621,
      "rewards/format_reward": 1.0,
      "step": 1500,
      "temperature": 1.0
    },
    {
      "all_correct": 0.375,
      "all_wrong": 0.0,
      "completion_length": 385.609375,
      "epoch": 0.045645298625471356,
      "grad_norm": 1.6344611968450313,
      "kl": 0.0244140625,
      "learning_rate": 9.948679896577368e-07,
      "loss": 0.001,
      "reward": 1.7537634372711182,
      "reward_std": 0.20297253131866455,
      "rewards/accuracy_reward": 0.6100134253501892,
      "rewards/format_reward": 1.0,
      "step": 1501,
      "temperature": 1.0
    },
    {
      "all_correct": 0.625,
      "all_wrong": 0.125,
      "completion_length": 339.75,
      "epoch": 0.045675708551271135,
      "grad_norm": 1.1897831822289011,
      "kl": 0.03564453125,
      "learning_rate": 9.948611609995503e-07,
      "loss": 0.0014,
      "reward": 1.9249999523162842,
      "reward_std": 0.15665315091609955,
      "rewards/accuracy_reward": 0.78125,
      "rewards/format_reward": 1.0,
      "step": 1502,
      "temperature": 1.0
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.125,
      "completion_length": 384.671875,
      "epoch": 0.045706118477070914,
      "grad_norm": 1.458419400798581,
      "kl": 0.031494140625,
      "learning_rate": 9.94854327824741e-07,
      "loss": 0.0013,
      "reward": 1.8189011812210083,
      "reward_std": 0.15998052060604095,
      "rewards/accuracy_reward": 0.6845262050628662,
      "rewards/format_reward": 1.0,
      "step": 1503,
      "temperature": 1.0
    },
    {
      "all_correct": 0.75,
      "all_wrong": 0.0,
      "completion_length": 359.59375,
      "epoch": 0.045736528402870694,
      "grad_norm": 1.258710233209215,
      "kl": 0.03955078125,
      "learning_rate": 9.94847490133371e-07,
      "loss": 0.0016,
      "reward": 1.9312500953674316,
      "reward_std": 0.1571877896785736,
      "rewards/accuracy_reward": 0.796875,
      "rewards/format_reward": 1.0,
      "step": 1504,
      "temperature": 1.0
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.375,
      "completion_length": 345.5,
      "epoch": 0.04576693832867048,
      "grad_norm": 4.849787897971567,
      "kl": 0.03857421875,
      "learning_rate": 9.948406479255029e-07,
      "loss": 0.0015,
      "reward": 1.6372532844543457,
      "reward_std": 0.03142615407705307,
      "rewards/accuracy_reward": 0.524753212928772,
      "rewards/format_reward": 1.0,
      "step": 1505,
      "temperature": 1.0
    },
    {
      "all_correct": 0.375,
      "all_wrong": 0.0,
      "completion_length": 384.265625,
      "epoch": 0.04579734825447026,
      "grad_norm": 2.482537746801645,
      "kl": 0.0400390625,
      "learning_rate": 9.94833801201199e-07,
      "loss": 0.0016,
      "reward": 1.8902778625488281,
      "reward_std": 0.2431999146938324,
      "rewards/accuracy_reward": 0.7621527910232544,
      "rewards/format_reward": 1.0,
      "step": 1506,
      "temperature": 1.0
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.0,
      "completion_length": 347.328125,
      "epoch": 0.04582775818027004,
      "grad_norm": 1.562474174681093,
      "kl": 0.038818359375,
      "learning_rate": 9.94826949960522e-07,
      "loss": 0.0015,
      "reward": 1.8534408807754517,
      "reward_std": 0.2663414180278778,
      "rewards/accuracy_reward": 0.706565797328949,
      "rewards/format_reward": 1.0,
      "step": 1507,
      "temperature": 1.0
    },
    {
      "all_correct": 0.375,
      "all_wrong": 0.125,
      "completion_length": 360.4375,
      "epoch": 0.045858168106069824,
      "grad_norm": 1.0211026200244981,
      "kl": 0.03564453125,
      "learning_rate": 9.948200942035342e-07,
      "loss": 0.0014,
      "reward": 1.84375,
      "reward_std": 0.25313490629196167,
      "rewards/accuracy_reward": 0.703125,
      "rewards/format_reward": 1.0,
      "step": 1508,
      "temperature": 1.0
    },
    {
      "all_correct": 0.375,
      "all_wrong": 0.125,
      "completion_length": 381.546875,
      "epoch": 0.045888578031869603,
      "grad_norm": 1.2173857017865652,
      "kl": 0.03515625,
      "learning_rate": 9.948132339302984e-07,
      "loss": 0.0014,
      "reward": 1.7156915664672852,
      "reward_std": 0.24871021509170532,
      "rewards/accuracy_reward": 0.5969415903091431,
      "rewards/format_reward": 1.0,
      "step": 1509,
      "temperature": 1.0
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.25,
      "completion_length": 360.828125,
      "epoch": 0.04591898795766938,
      "grad_norm": 1.1388940868021875,
      "kl": 0.039306640625,
      "learning_rate": 9.94806369140877e-07,
      "loss": 0.0016,
      "reward": 1.704660177230835,
      "reward_std": 0.08171486854553223,
      "rewards/accuracy_reward": 0.5859100818634033,
      "rewards/format_reward": 1.0,
      "step": 1510,
      "temperature": 1.0
    },
    {
      "all_correct": 0.75,
      "all_wrong": 0.0,
      "completion_length": 356.828125,
      "epoch": 0.04594939788346916,
      "grad_norm": 0.8114983621048736,
      "kl": 0.03369140625,
      "learning_rate": 9.947994998353326e-07,
      "loss": 0.0013,
      "reward": 2.020199775695801,
      "reward_std": 0.07879830151796341,
      "rewards/accuracy_reward": 0.8389497995376587,
      "rewards/format_reward": 1.0,
      "step": 1511,
      "temperature": 1.0
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.125,
      "completion_length": 379.921875,
      "epoch": 0.04597980780926895,
      "grad_norm": 0.7829033317428011,
      "kl": 0.037109375,
      "learning_rate": 9.947926260137284e-07,
      "loss": 0.0015,
      "reward": 1.8514877557754517,
      "reward_std": 0.08532886207103729,
      "rewards/accuracy_reward": 0.6889877319335938,
      "rewards/format_reward": 1.0,
      "step": 1512,
      "temperature": 1.0
    },
    {
      "all_correct": 0.625,
      "all_wrong": 0.125,
      "completion_length": 384.515625,
      "epoch": 0.04601021773506873,
      "grad_norm": 1.1191746145809083,
      "kl": 0.04052734375,
      "learning_rate": 9.947857476761265e-07,
      "loss": 0.0016,
      "reward": 1.9793094396591187,
      "reward_std": 0.11250028759241104,
      "rewards/accuracy_reward": 0.8293095231056213,
      "rewards/format_reward": 1.0,
      "step": 1513,
      "temperature": 1.0
    },
    {
      "all_correct": 0.25,
      "all_wrong": 0.25,
      "completion_length": 420.625,
      "epoch": 0.046040627660868506,
      "grad_norm": 0.7137288567475439,
      "kl": 0.0322265625,
      "learning_rate": 9.9477886482259e-07,
      "loss": 0.0013,
      "reward": 1.4401919841766357,
      "reward_std": 0.19135333597660065,
      "rewards/accuracy_reward": 0.3714420199394226,
      "rewards/format_reward": 1.0,
      "step": 1514,
      "temperature": 1.0
    },
    {
      "all_correct": 0.125,
      "all_wrong": 0.25,
      "completion_length": 375.765625,
      "epoch": 0.046071037586668286,
      "grad_norm": 1.0300857628555844,
      "kl": 0.035400390625,
      "learning_rate": 9.94771977453182e-07,
      "loss": 0.0014,
      "reward": 1.5888595581054688,
      "reward_std": 0.17372721433639526,
      "rewards/accuracy_reward": 0.45448437333106995,
      "rewards/format_reward": 1.0,
      "step": 1515,
      "temperature": 1.0
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.125,
      "completion_length": 391.171875,
      "epoch": 0.04610144751246807,
      "grad_norm": 2.5347021875005296,
      "kl": 0.03466796875,
      "learning_rate": 9.947650855679649e-07,
      "loss": 0.0014,
      "reward": 1.8931080102920532,
      "reward_std": 0.141493558883667,
      "rewards/accuracy_reward": 0.7368580102920532,
      "rewards/format_reward": 1.0,
      "step": 1516,
      "temperature": 1.0
    },
    {
      "all_correct": 0.625,
      "all_wrong": 0.25,
      "completion_length": 366.484375,
      "epoch": 0.04613185743826785,
      "grad_norm": 0.41198028832444783,
      "kl": 0.038330078125,
      "learning_rate": 9.947581891670015e-07,
      "loss": 0.0015,
      "reward": 1.8006374835968018,
      "reward_std": 0.008857602253556252,
      "rewards/accuracy_reward": 0.6537624597549438,
      "rewards/format_reward": 1.0,
      "step": 1517,
      "temperature": 1.0
    },
    {
      "all_correct": 0.625,
      "all_wrong": 0.0,
      "completion_length": 416.1875,
      "epoch": 0.04616226736406763,
      "grad_norm": 1.2508945703684131,
      "kl": 0.03515625,
      "learning_rate": 9.94751288250355e-07,
      "loss": 0.0014,
      "reward": 1.9455528259277344,
      "reward_std": 0.14354023337364197,
      "rewards/accuracy_reward": 0.7799278497695923,
      "rewards/format_reward": 1.0,
      "step": 1518,
      "temperature": 1.0
    },
    {
      "all_correct": 0.625,
      "all_wrong": 0.125,
      "completion_length": 368.546875,
      "epoch": 0.04619267728986741,
      "grad_norm": 0.8131875773706615,
      "kl": 0.030517578125,
      "learning_rate": 9.947443828180886e-07,
      "loss": 0.0012,
      "reward": 1.8515865802764893,
      "reward_std": 0.059592120349407196,
      "rewards/accuracy_reward": 0.7015864849090576,
      "rewards/format_reward": 1.0,
      "step": 1519,
      "temperature": 1.0
    },
    {
      "all_correct": 0.375,
      "all_wrong": 0.0,
      "completion_length": 425.578125,
      "epoch": 0.046223087215667195,
      "grad_norm": 1.220134639430691,
      "kl": 0.035888671875,
      "learning_rate": 9.947374728702651e-07,
      "loss": 0.0014,
      "reward": 1.7307689189910889,
      "reward_std": 0.05556311830878258,
      "rewards/accuracy_reward": 0.5870188474655151,
      "rewards/format_reward": 1.0,
      "step": 1520,
      "temperature": 1.0
    },
    {
      "all_correct": 0.875,
      "all_wrong": 0.0,
      "completion_length": 344.8125,
      "epoch": 0.046253497141466975,
      "grad_norm": 0.56030815958017,
      "kl": 0.032958984375,
      "learning_rate": 9.947305584069473e-07,
      "loss": 0.0013,
      "reward": 2.065624952316284,
      "reward_std": 0.04419417306780815,
      "rewards/accuracy_reward": 0.890625,
      "rewards/format_reward": 1.0,
      "step": 1521,
      "temperature": 1.0
    },
    {
      "all_correct": 0.25,
      "all_wrong": 0.125,
      "completion_length": 377.0,
      "epoch": 0.046283907067266754,
      "grad_norm": 1.5560728709672904,
      "kl": 0.035888671875,
      "learning_rate": 9.94723639428199e-07,
      "loss": 0.0014,
      "reward": 1.624798059463501,
      "reward_std": 0.1477717161178589,
      "rewards/accuracy_reward": 0.47479814291000366,
      "rewards/format_reward": 1.0,
      "step": 1522,
      "temperature": 1.0
    },
    {
      "all_correct": 0.75,
      "all_wrong": 0.0,
      "completion_length": 372.859375,
      "epoch": 0.04631431699306654,
      "grad_norm": 0.902267021153162,
      "kl": 0.03466796875,
      "learning_rate": 9.947167159340825e-07,
      "loss": 0.0014,
      "reward": 2.014842987060547,
      "reward_std": 0.009716305881738663,
      "rewards/accuracy_reward": 0.8148430585861206,
      "rewards/format_reward": 1.0,
      "step": 1523,
      "temperature": 1.0
    },
    {
      "all_correct": 0.75,
      "all_wrong": 0.0,
      "completion_length": 383.265625,
      "epoch": 0.04634472691886632,
      "grad_norm": 0.7320523541022059,
      "kl": 0.034423828125,
      "learning_rate": 9.947097879246618e-07,
      "loss": 0.0014,
      "reward": 2.110445499420166,
      "reward_std": 0.05745057016611099,
      "rewards/accuracy_reward": 0.9135704040527344,
      "rewards/format_reward": 1.0,
      "step": 1524,
      "temperature": 1.0
    },
    {
      "all_correct": 0.375,
      "all_wrong": 0.375,
      "completion_length": 402.890625,
      "epoch": 0.0463751368446661,
      "grad_norm": 3.5547059022242555,
      "kl": 0.0311279296875,
      "learning_rate": 9.947028553999995e-07,
      "loss": 0.0012,
      "reward": 1.5954759120941162,
      "reward_std": 0.0381922647356987,
      "rewards/accuracy_reward": 0.49235087633132935,
      "rewards/format_reward": 1.0,
      "step": 1525,
      "temperature": 1.0
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.0,
      "completion_length": 367.828125,
      "epoch": 0.04640554677046588,
      "grad_norm": 1.7253306447220629,
      "kl": 0.0322265625,
      "learning_rate": 9.946959183601593e-07,
      "loss": 0.0013,
      "reward": 2.029130458831787,
      "reward_std": 0.13583141565322876,
      "rewards/accuracy_reward": 0.8541305065155029,
      "rewards/format_reward": 0.984375,
      "step": 1526,
      "temperature": 1.0
    },
    {
      "all_correct": 0.25,
      "all_wrong": 0.0,
      "completion_length": 376.109375,
      "epoch": 0.046435956696265664,
      "grad_norm": 1.5534313564861473,
      "kl": 0.03466796875,
      "learning_rate": 9.946889768052041e-07,
      "loss": 0.0014,
      "reward": 1.6638532876968384,
      "reward_std": 0.1377621740102768,
      "rewards/accuracy_reward": 0.4857282042503357,
      "rewards/format_reward": 1.0,
      "step": 1527,
      "temperature": 1.0
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.125,
      "completion_length": 361.140625,
      "epoch": 0.04646636662206544,
      "grad_norm": 0.9531581665984314,
      "kl": 0.03125,
      "learning_rate": 9.946820307351977e-07,
      "loss": 0.0013,
      "reward": 1.7577677965164185,
      "reward_std": 0.09089983999729156,
      "rewards/accuracy_reward": 0.6202678084373474,
      "rewards/format_reward": 1.0,
      "step": 1528,
      "temperature": 1.0
    },
    {
      "all_correct": 0.375,
      "all_wrong": 0.25,
      "completion_length": 363.625,
      "epoch": 0.04649677654786522,
      "grad_norm": 1.089614049147969,
      "kl": 0.035888671875,
      "learning_rate": 9.946750801502033e-07,
      "loss": 0.0014,
      "reward": 1.7125000953674316,
      "reward_std": 0.21213886141777039,
      "rewards/accuracy_reward": 0.59375,
      "rewards/format_reward": 1.0,
      "step": 1529,
      "temperature": 1.0
    },
    {
      "all_correct": 0.625,
      "all_wrong": 0.0,
      "completion_length": 357.640625,
      "epoch": 0.046527186473665,
      "grad_norm": 1.0914333916999122,
      "kl": 0.03369140625,
      "learning_rate": 9.946681250502842e-07,
      "loss": 0.0013,
      "reward": 1.9557760953903198,
      "reward_std": 0.16583147644996643,
      "rewards/accuracy_reward": 0.790151059627533,
      "rewards/format_reward": 1.0,
      "step": 1530,
      "temperature": 1.0
    },
    {
      "all_correct": 0.375,
      "all_wrong": 0.25,
      "completion_length": 381.140625,
      "epoch": 0.04655759639946479,
      "grad_norm": 2.191393194528012,
      "kl": 0.031494140625,
      "learning_rate": 9.946611654355041e-07,
      "loss": 0.0013,
      "reward": 1.735191822052002,
      "reward_std": 0.07497971504926682,
      "rewards/accuracy_reward": 0.5914418697357178,
      "rewards/format_reward": 1.0,
      "step": 1531,
      "temperature": 1.0
    },
    {
      "all_correct": 0.625,
      "all_wrong": 0.0,
      "completion_length": 360.40625,
      "epoch": 0.04658800632526457,
      "grad_norm": 1.1549654360251704,
      "kl": 0.0380859375,
      "learning_rate": 9.946542013059265e-07,
      "loss": 0.0015,
      "reward": 1.988822102546692,
      "reward_std": 0.17995887994766235,
      "rewards/accuracy_reward": 0.826322078704834,
      "rewards/format_reward": 1.0,
      "step": 1532,
      "temperature": 1.0
    },
    {
      "all_correct": 0.625,
      "all_wrong": 0.0,
      "completion_length": 357.125,
      "epoch": 0.046618416251064346,
      "grad_norm": 0.6888523543826557,
      "kl": 0.0322265625,
      "learning_rate": 9.946472326616147e-07,
      "loss": 0.0013,
      "reward": 2.0143518447875977,
      "reward_std": 0.06943650543689728,
      "rewards/accuracy_reward": 0.8206018805503845,
      "rewards/format_reward": 1.0,
      "step": 1533,
      "temperature": 1.0
    },
    {
      "all_correct": 0.625,
      "all_wrong": 0.0,
      "completion_length": 367.03125,
      "epoch": 0.04664882617686413,
      "grad_norm": 1.1025587349348267,
      "kl": 0.03662109375,
      "learning_rate": 9.946402595026327e-07,
      "loss": 0.0015,
      "reward": 1.8937666416168213,
      "reward_std": 0.021150335669517517,
      "rewards/accuracy_reward": 0.7187666296958923,
      "rewards/format_reward": 1.0,
      "step": 1534,
      "temperature": 1.0
    },
    {
      "all_correct": 0.625,
      "all_wrong": 0.0,
      "completion_length": 359.421875,
      "epoch": 0.04667923610266391,
      "grad_norm": 1.2546239586102172,
      "kl": 0.05224609375,
      "learning_rate": 9.946332818290438e-07,
      "loss": 0.0021,
      "reward": 1.9164773225784302,
      "reward_std": 0.16829003393650055,
      "rewards/accuracy_reward": 0.7602272033691406,
      "rewards/format_reward": 1.0,
      "step": 1535,
      "temperature": 1.0
    },
    {
      "all_correct": 0.25,
      "all_wrong": 0.375,
      "completion_length": 382.390625,
      "epoch": 0.04670964602846369,
      "grad_norm": 1.0558509420492939,
      "kl": 0.032470703125,
      "learning_rate": 9.94626299640912e-07,
      "loss": 0.0013,
      "reward": 1.4431209564208984,
      "reward_std": 0.08103935420513153,
      "rewards/accuracy_reward": 0.33999598026275635,
      "rewards/format_reward": 1.0,
      "step": 1536,
      "temperature": 1.0
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.125,
      "completion_length": 347.703125,
      "epoch": 0.04674005595426347,
      "grad_norm": 1.162069068539975,
      "kl": 0.036376953125,
      "learning_rate": 9.946193129383007e-07,
      "loss": 0.0015,
      "reward": 1.872774362564087,
      "reward_std": 0.14167305827140808,
      "rewards/accuracy_reward": 0.7165243625640869,
      "rewards/format_reward": 1.0,
      "step": 1537,
      "temperature": 1.0
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.125,
      "completion_length": 363.0625,
      "epoch": 0.046770465880063256,
      "grad_norm": 1.559317282402883,
      "kl": 0.034423828125,
      "learning_rate": 9.946123217212738e-07,
      "loss": 0.0014,
      "reward": 1.8008460998535156,
      "reward_std": 0.1059165969491005,
      "rewards/accuracy_reward": 0.6477210521697998,
      "rewards/format_reward": 1.0,
      "step": 1538,
      "temperature": 1.0
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.0,
      "completion_length": 355.5,
      "epoch": 0.046800875805863035,
      "grad_norm": 2.384803006452768,
      "kl": 0.04443359375,
      "learning_rate": 9.946053259898951e-07,
      "loss": 0.0018,
      "reward": 1.8696527481079102,
      "reward_std": 0.19570326805114746,
      "rewards/accuracy_reward": 0.7071527242660522,
      "rewards/format_reward": 1.0,
      "step": 1539,
      "temperature": 1.0
    },
    {
      "all_correct": 0.75,
      "all_wrong": 0.125,
      "completion_length": 355.65625,
      "epoch": 0.046831285731662814,
      "grad_norm": 0.9068824518139893,
      "kl": 0.03564453125,
      "learning_rate": 9.945983257442287e-07,
      "loss": 0.0014,
      "reward": 1.9635319709777832,
      "reward_std": 0.02752988040447235,
      "rewards/accuracy_reward": 0.7979068756103516,
      "rewards/format_reward": 1.0,
      "step": 1540,
      "temperature": 1.0
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.0,
      "completion_length": 363.890625,
      "epoch": 0.04686169565746259,
      "grad_norm": 1.6378855985034637,
      "kl": 0.03662109375,
      "learning_rate": 9.94591320984338e-07,
      "loss": 0.0015,
      "reward": 1.8875000476837158,
      "reward_std": 0.26964086294174194,
      "rewards/accuracy_reward": 0.75,
      "rewards/format_reward": 1.0,
      "step": 1541,
      "temperature": 1.0
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.0,
      "completion_length": 363.375,
      "epoch": 0.04689210558326238,
      "grad_norm": 1.5233192189089795,
      "kl": 0.033203125,
      "learning_rate": 9.945843117102874e-07,
      "loss": 0.0013,
      "reward": 1.8291280269622803,
      "reward_std": 0.25905275344848633,
      "rewards/accuracy_reward": 0.6947530508041382,
      "rewards/format_reward": 1.0,
      "step": 1542,
      "temperature": 1.0
    },
    {
      "all_correct": 0.75,
      "all_wrong": 0.0,
      "completion_length": 352.125,
      "epoch": 0.04692251550906216,
      "grad_norm": 0.9741589064791435,
      "kl": 0.03173828125,
      "learning_rate": 9.945772979221407e-07,
      "loss": 0.0013,
      "reward": 2.1334705352783203,
      "reward_std": 0.128914937376976,
      "rewards/accuracy_reward": 0.9428454637527466,
      "rewards/format_reward": 1.0,
      "step": 1543,
      "temperature": 1.0
    },
    {
      "all_correct": 0.375,
      "all_wrong": 0.125,
      "completion_length": 390.453125,
      "epoch": 0.04695292543486194,
      "grad_norm": 1.6243864728538238,
      "kl": 0.031982421875,
      "learning_rate": 9.945702796199617e-07,
      "loss": 0.0013,
      "reward": 1.7554842233657837,
      "reward_std": 0.183892622590065,
      "rewards/accuracy_reward": 0.6086091995239258,
      "rewards/format_reward": 1.0,
      "step": 1544,
      "temperature": 1.0
    },
    {
      "all_correct": 0.375,
      "all_wrong": 0.125,
      "completion_length": 357.234375,
      "epoch": 0.04698333536066172,
      "grad_norm": 1.2922284262832764,
      "kl": 0.032958984375,
      "learning_rate": 9.945632568038149e-07,
      "loss": 0.0013,
      "reward": 1.774712085723877,
      "reward_std": 0.18133237957954407,
      "rewards/accuracy_reward": 0.6372120380401611,
      "rewards/format_reward": 1.0,
      "step": 1545,
      "temperature": 1.0
    },
    {
      "all_correct": 0.625,
      "all_wrong": 0.0,
      "completion_length": 386.40625,
      "epoch": 0.0470137452864615,
      "grad_norm": 0.9967112339669894,
      "kl": 0.03466796875,
      "learning_rate": 9.945562294737639e-07,
      "loss": 0.0014,
      "reward": 1.9337646961212158,
      "reward_std": 0.013676613569259644,
      "rewards/accuracy_reward": 0.7368895411491394,
      "rewards/format_reward": 1.0,
      "step": 1546,
      "temperature": 1.0
    },
    {
      "all_correct": 0.625,
      "all_wrong": 0.25,
      "completion_length": 358.0,
      "epoch": 0.04704415521226128,
      "grad_norm": 1.312940533018157,
      "kl": 0.037353515625,
      "learning_rate": 9.945491976298734e-07,
      "loss": 0.0015,
      "reward": 1.8718750476837158,
      "reward_std": 0.07344460487365723,
      "rewards/accuracy_reward": 0.734375,
      "rewards/format_reward": 1.0,
      "step": 1547,
      "temperature": 1.0
    },
    {
      "all_correct": 0.375,
      "all_wrong": 0.25,
      "completion_length": 355.8125,
      "epoch": 0.04707456513806106,
      "grad_norm": 1.5552138544455676,
      "kl": 0.035400390625,
      "learning_rate": 9.945421612722069e-07,
      "loss": 0.0014,
      "reward": 1.6254463195800781,
      "reward_std": 0.22079315781593323,
      "rewards/accuracy_reward": 0.5223214626312256,
      "rewards/format_reward": 1.0,
      "step": 1548,
      "temperature": 1.0
    },
    {
      "all_correct": 0.375,
      "all_wrong": 0.0,
      "completion_length": 386.578125,
      "epoch": 0.04710497506386085,
      "grad_norm": 0.8717021672417284,
      "kl": 0.03564453125,
      "learning_rate": 9.945351204008292e-07,
      "loss": 0.0014,
      "reward": 1.8744988441467285,
      "reward_std": 0.13295477628707886,
      "rewards/accuracy_reward": 0.7088736891746521,
      "rewards/format_reward": 1.0,
      "step": 1549,
      "temperature": 1.0
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.0,
      "completion_length": 369.796875,
      "epoch": 0.04713538498966063,
      "grad_norm": 1.2833396405627877,
      "kl": 0.033447265625,
      "learning_rate": 9.945280750158044e-07,
      "loss": 0.0013,
      "reward": 1.9808827638626099,
      "reward_std": 0.17337007820606232,
      "rewards/accuracy_reward": 0.8027576804161072,
      "rewards/format_reward": 1.0,
      "step": 1550,
      "temperature": 1.0
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.125,
      "completion_length": 362.796875,
      "epoch": 0.047165794915460406,
      "grad_norm": 1.8074974147216338,
      "kl": 0.03515625,
      "learning_rate": 9.945210251171966e-07,
      "loss": 0.0014,
      "reward": 1.885331392288208,
      "reward_std": 0.15647625923156738,
      "rewards/accuracy_reward": 0.729081392288208,
      "rewards/format_reward": 1.0,
      "step": 1551,
      "temperature": 1.0
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.125,
      "completion_length": 357.0625,
      "epoch": 0.047196204841260185,
      "grad_norm": 1.244653719852763,
      "kl": 0.035400390625,
      "learning_rate": 9.945139707050705e-07,
      "loss": 0.0014,
      "reward": 1.7670929431915283,
      "reward_std": 0.0673820897936821,
      "rewards/accuracy_reward": 0.623342752456665,
      "rewards/format_reward": 1.0,
      "step": 1552,
      "temperature": 1.0
    },
    {
      "all_correct": 0.75,
      "all_wrong": 0.0,
      "completion_length": 351.09375,
      "epoch": 0.04722661476705997,
      "grad_norm": 0.8202775806155235,
      "kl": 0.037109375,
      "learning_rate": 9.945069117794903e-07,
      "loss": 0.0015,
      "reward": 2.1208202838897705,
      "reward_std": 0.09091229736804962,
      "rewards/accuracy_reward": 0.930195152759552,
      "rewards/format_reward": 1.0,
      "step": 1553,
      "temperature": 1.0
    },
    {
      "all_correct": 0.375,
      "all_wrong": 0.375,
      "completion_length": 356.046875,
      "epoch": 0.04725702469285975,
      "grad_norm": 3.1772189255974483,
      "kl": 0.033935546875,
      "learning_rate": 9.9449984834052e-07,
      "loss": 0.0014,
      "reward": 1.6708016395568848,
      "reward_std": 0.08724631369113922,
      "rewards/accuracy_reward": 0.5551766157150269,
      "rewards/format_reward": 1.0,
      "step": 1554,
      "temperature": 1.0
    },
    {
      "all_correct": 0.875,
      "all_wrong": 0.0,
      "completion_length": 371.71875,
      "epoch": 0.04728743461865953,
      "grad_norm": 0.28866260078484823,
      "kl": 0.034423828125,
      "learning_rate": 9.944927803882249e-07,
      "loss": 0.0014,
      "reward": 2.1422150135040283,
      "reward_std": 0.011572758667171001,
      "rewards/accuracy_reward": 0.9484648704528809,
      "rewards/format_reward": 1.0,
      "step": 1555,
      "temperature": 1.0
    },
    {
      "all_correct": 0.75,
      "all_wrong": 0.0,
      "completion_length": 362.328125,
      "epoch": 0.04731784454445931,
      "grad_norm": 1.3497709191765361,
      "kl": 0.037841796875,
      "learning_rate": 9.944857079226689e-07,
      "loss": 0.0015,
      "reward": 2.0602612495422363,
      "reward_std": 0.07537347078323364,
      "rewards/accuracy_reward": 0.8665112853050232,
      "rewards/format_reward": 1.0,
      "step": 1556,
      "temperature": 1.0
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.375,
      "completion_length": 390.21875,
      "epoch": 0.047348254470259095,
      "grad_norm": 1.067983478909884,
      "kl": 0.03076171875,
      "learning_rate": 9.944786309439167e-07,
      "loss": 0.0012,
      "reward": 1.662770390510559,
      "reward_std": 0.07826808094978333,
      "rewards/accuracy_reward": 0.5565203428268433,
      "rewards/format_reward": 1.0,
      "step": 1557,
      "temperature": 1.0
    },
    {
      "all_correct": 0.75,
      "all_wrong": 0.125,
      "completion_length": 353.625,
      "epoch": 0.047378664396058874,
      "grad_norm": 0.8628796162250926,
      "kl": 0.03662109375,
      "learning_rate": 9.94471549452033e-07,
      "loss": 0.0015,
      "reward": 1.9475369453430176,
      "reward_std": 0.04816683754324913,
      "rewards/accuracy_reward": 0.7819119095802307,
      "rewards/format_reward": 1.0,
      "step": 1558,
      "temperature": 1.0
    },
    {
      "all_correct": 0.375,
      "all_wrong": 0.0,
      "completion_length": 411.703125,
      "epoch": 0.04740907432185865,
      "grad_norm": 1.912954806317993,
      "kl": 0.035888671875,
      "learning_rate": 9.944644634470825e-07,
      "loss": 0.0014,
      "reward": 1.7232180833816528,
      "reward_std": 0.1536242961883545,
      "rewards/accuracy_reward": 0.5950931310653687,
      "rewards/format_reward": 0.984375,
      "step": 1559,
      "temperature": 1.0
    },
    {
      "all_correct": 0.25,
      "all_wrong": 0.25,
      "completion_length": 393.0625,
      "epoch": 0.04743948424765843,
      "grad_norm": 1.5214355237572437,
      "kl": 0.034423828125,
      "learning_rate": 9.944573729291296e-07,
      "loss": 0.0014,
      "reward": 1.5150384902954102,
      "reward_std": 0.1093657910823822,
      "rewards/accuracy_reward": 0.4025384485721588,
      "rewards/format_reward": 1.0,
      "step": 1560,
      "temperature": 1.0
    },
    {
      "all_correct": 0.75,
      "all_wrong": 0.125,
      "completion_length": 358.21875,
      "epoch": 0.04746989417345822,
      "grad_norm": 0.7276105776498598,
      "kl": 0.03369140625,
      "learning_rate": 9.944502778982394e-07,
      "loss": 0.0013,
      "reward": 1.952887773513794,
      "reward_std": 0.012567606754601002,
      "rewards/accuracy_reward": 0.7810126543045044,
      "rewards/format_reward": 1.0,
      "step": 1561,
      "temperature": 1.0
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.125,
      "completion_length": 361.578125,
      "epoch": 0.047500304099258,
      "grad_norm": 0.9841566008588063,
      "kl": 0.0341796875,
      "learning_rate": 9.944431783544762e-07,
      "loss": 0.0014,
      "reward": 1.8032851219177246,
      "reward_std": 0.10920310020446777,
      "rewards/accuracy_reward": 0.6657851934432983,
      "rewards/format_reward": 1.0,
      "step": 1562,
      "temperature": 1.0
    },
    {
      "all_correct": 0.375,
      "all_wrong": 0.125,
      "completion_length": 364.21875,
      "epoch": 0.04753071402505778,
      "grad_norm": 1.1366244187951449,
      "kl": 0.035888671875,
      "learning_rate": 9.94436074297905e-07,
      "loss": 0.0014,
      "reward": 1.8437501192092896,
      "reward_std": 0.23605698347091675,
      "rewards/accuracy_reward": 0.703125,
      "rewards/format_reward": 1.0,
      "step": 1563,
      "temperature": 1.0
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.25,
      "completion_length": 346.796875,
      "epoch": 0.04756112395085756,
      "grad_norm": 2.506955296941956,
      "kl": 0.035888671875,
      "learning_rate": 9.944289657285905e-07,
      "loss": 0.0014,
      "reward": 1.674835205078125,
      "reward_std": 0.06749535351991653,
      "rewards/accuracy_reward": 0.5529600977897644,
      "rewards/format_reward": 1.0,
      "step": 1564,
      "temperature": 1.0
    },
    {
      "all_correct": 0.625,
      "all_wrong": 0.25,
      "completion_length": 375.78125,
      "epoch": 0.04759153387665734,
      "grad_norm": 1.023928068461891,
      "kl": 0.0380859375,
      "learning_rate": 9.944218526465979e-07,
      "loss": 0.0015,
      "reward": 1.7856860160827637,
      "reward_std": 0.06369657814502716,
      "rewards/accuracy_reward": 0.6575610637664795,
      "rewards/format_reward": 0.984375,
      "step": 1565,
      "temperature": 1.0
    },
    {
      "all_correct": 0.25,
      "all_wrong": 0.125,
      "completion_length": 378.359375,
      "epoch": 0.04762194380245712,
      "grad_norm": 1.1274449806554883,
      "kl": 0.0341796875,
      "learning_rate": 9.94414735051992e-07,
      "loss": 0.0014,
      "reward": 1.6358880996704102,
      "reward_std": 0.09547819942235947,
      "rewards/accuracy_reward": 0.4921380281448364,
      "rewards/format_reward": 1.0,
      "step": 1566,
      "temperature": 1.0
    },
    {
      "all_correct": 0.375,
      "all_wrong": 0.375,
      "completion_length": 341.65625,
      "epoch": 0.0476523537282569,
      "grad_norm": 0.9240323697666751,
      "kl": 0.0361328125,
      "learning_rate": 9.944076129448378e-07,
      "loss": 0.0014,
      "reward": 1.618647575378418,
      "reward_std": 0.10974804311990738,
      "rewards/accuracy_reward": 0.5155225992202759,
      "rewards/format_reward": 1.0,
      "step": 1567,
      "temperature": 1.0
    },
    {
      "all_correct": 0.375,
      "all_wrong": 0.125,
      "completion_length": 371.734375,
      "epoch": 0.04768276365405669,
      "grad_norm": 0.9265472677305572,
      "kl": 0.0341796875,
      "learning_rate": 9.944004863252001e-07,
      "loss": 0.0014,
      "reward": 1.7358182668685913,
      "reward_std": 0.09713871031999588,
      "rewards/accuracy_reward": 0.5795682668685913,
      "rewards/format_reward": 1.0,
      "step": 1568,
      "temperature": 1.0
    },
    {
      "all_correct": 0.25,
      "all_wrong": 0.375,
      "completion_length": 381.9375,
      "epoch": 0.047713173579856466,
      "grad_norm": 1.7176708853116256,
      "kl": 0.037353515625,
      "learning_rate": 9.94393355193144e-07,
      "loss": 0.0015,
      "reward": 1.582282304763794,
      "reward_std": 0.08384598791599274,
      "rewards/accuracy_reward": 0.4791572093963623,
      "rewards/format_reward": 1.0,
      "step": 1569,
      "temperature": 1.0
    },
    {
      "all_correct": 0.625,
      "all_wrong": 0.0,
      "completion_length": 371.984375,
      "epoch": 0.047743583505656245,
      "grad_norm": 2.4280290319859237,
      "kl": 0.042724609375,
      "learning_rate": 9.943862195487347e-07,
      "loss": 0.0017,
      "reward": 1.8999028205871582,
      "reward_std": 0.05048826336860657,
      "rewards/accuracy_reward": 0.7186528444290161,
      "rewards/format_reward": 1.0,
      "step": 1570,
      "temperature": 1.0
    },
    {
      "all_correct": 0.75,
      "all_wrong": 0.125,
      "completion_length": 357.796875,
      "epoch": 0.047773993431456024,
      "grad_norm": 1.240472439429232,
      "kl": 0.039306640625,
      "learning_rate": 9.943790793920373e-07,
      "loss": 0.0016,
      "reward": 1.9381531476974487,
      "reward_std": 0.04622669890522957,
      "rewards/accuracy_reward": 0.794403076171875,
      "rewards/format_reward": 1.0,
      "step": 1571,
      "temperature": 1.0
    },
    {
      "all_correct": 0.375,
      "all_wrong": 0.25,
      "completion_length": 392.9375,
      "epoch": 0.04780440335725581,
      "grad_norm": 1.096641580971876,
      "kl": 0.0322265625,
      "learning_rate": 9.94371934723117e-07,
      "loss": 0.0013,
      "reward": 1.6043202877044678,
      "reward_std": 0.08812005817890167,
      "rewards/accuracy_reward": 0.473070353269577,
      "rewards/format_reward": 1.0,
      "step": 1572,
      "temperature": 1.0
    },
    {
      "all_correct": 0.75,
      "all_wrong": 0.25,
      "completion_length": 350.0,
      "epoch": 0.04783481328305559,
      "grad_norm": 0.06746722896096136,
      "kl": 0.036865234375,
      "learning_rate": 9.943647855420388e-07,
      "loss": 0.0015,
      "reward": 1.9000000953674316,
      "reward_std": 0.0,
      "rewards/accuracy_reward": 0.75,
      "rewards/format_reward": 1.0,
      "step": 1573,
      "temperature": 1.0
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.0,
      "completion_length": 382.609375,
      "epoch": 0.04786522320885537,
      "grad_norm": 0.8781529264859942,
      "kl": 0.033935546875,
      "learning_rate": 9.943576318488682e-07,
      "loss": 0.0014,
      "reward": 2.0207979679107666,
      "reward_std": 0.12056371569633484,
      "rewards/accuracy_reward": 0.8364229798316956,
      "rewards/format_reward": 1.0,
      "step": 1574,
      "temperature": 1.0
    },
    {
      "all_correct": 0.75,
      "all_wrong": 0.0,
      "completion_length": 343.171875,
      "epoch": 0.04789563313465515,
      "grad_norm": 0.7497062115884768,
      "kl": 0.0361328125,
      "learning_rate": 9.943504736436705e-07,
      "loss": 0.0014,
      "reward": 2.133333206176758,
      "reward_std": 0.06134308874607086,
      "rewards/accuracy_reward": 0.9427083730697632,
      "rewards/format_reward": 1.0,
      "step": 1575,
      "temperature": 1.0
    },
    {
      "all_correct": 0.625,
      "all_wrong": 0.125,
      "completion_length": 361.265625,
      "epoch": 0.047926043060454934,
      "grad_norm": 1.7256290312998543,
      "kl": 0.037109375,
      "learning_rate": 9.943433109265106e-07,
      "loss": 0.0015,
      "reward": 1.874631643295288,
      "reward_std": 0.025582769885659218,
      "rewards/accuracy_reward": 0.6996316313743591,
      "rewards/format_reward": 1.0,
      "step": 1576,
      "temperature": 1.0
    },
    {
      "all_correct": 0.375,
      "all_wrong": 0.0,
      "completion_length": 380.953125,
      "epoch": 0.04795645298625471,
      "grad_norm": 1.1265997050732721,
      "kl": 0.032470703125,
      "learning_rate": 9.943361436974546e-07,
      "loss": 0.0013,
      "reward": 1.8008129596710205,
      "reward_std": 0.18737894296646118,
      "rewards/accuracy_reward": 0.6414377689361572,
      "rewards/format_reward": 1.0,
      "step": 1577,
      "temperature": 1.0
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.375,
      "completion_length": 368.765625,
      "epoch": 0.04798686291205449,
      "grad_norm": 0.6464948738567164,
      "kl": 0.046875,
      "learning_rate": 9.943289719565673e-07,
      "loss": 0.0019,
      "reward": 1.6754918098449707,
      "reward_std": 0.00784970447421074,
      "rewards/accuracy_reward": 0.5504918694496155,
      "rewards/format_reward": 1.0,
      "step": 1578,
      "temperature": 1.0
    },
    {
      "all_correct": 0.625,
      "all_wrong": 0.25,
      "completion_length": 353.84375,
      "epoch": 0.04801727283785428,
      "grad_norm": 0.5136057368711837,
      "kl": 0.034423828125,
      "learning_rate": 9.943217957039146e-07,
      "loss": 0.0014,
      "reward": 1.765625,
      "reward_std": 0.04419417306780815,
      "rewards/accuracy_reward": 0.640625,
      "rewards/format_reward": 1.0,
      "step": 1579,
      "temperature": 1.0
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.0,
      "completion_length": 376.171875,
      "epoch": 0.04804768276365406,
      "grad_norm": 2.5784092896690325,
      "kl": 0.034423828125,
      "learning_rate": 9.943146149395616e-07,
      "loss": 0.0014,
      "reward": 2.0359914302825928,
      "reward_std": 0.14440687000751495,
      "rewards/accuracy_reward": 0.8484913110733032,
      "rewards/format_reward": 1.0,
      "step": 1580,
      "temperature": 1.0
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.125,
      "completion_length": 404.9375,
      "epoch": 0.04807809268945384,
      "grad_norm": 0.6828462339522391,
      "kl": 0.0306396484375,
      "learning_rate": 9.943074296635738e-07,
      "loss": 0.0012,
      "reward": 1.7997803688049316,
      "reward_std": 0.15681302547454834,
      "rewards/accuracy_reward": 0.6560302972793579,
      "rewards/format_reward": 1.0,
      "step": 1581,
      "temperature": 1.0
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.25,
      "completion_length": 354.921875,
      "epoch": 0.048108502615253616,
      "grad_norm": 1.4667237569274554,
      "kl": 0.039794921875,
      "learning_rate": 9.943002398760174e-07,
      "loss": 0.0016,
      "reward": 1.7875001430511475,
      "reward_std": 0.14961488544940948,
      "rewards/accuracy_reward": 0.65625,
      "rewards/format_reward": 1.0,
      "step": 1582,
      "temperature": 1.0
    },
    {
      "all_correct": 0.875,
      "all_wrong": 0.125,
      "completion_length": 371.515625,
      "epoch": 0.0481389125410534,
      "grad_norm": 0.6238793384298421,
      "kl": 0.0380859375,
      "learning_rate": 9.942930455769574e-07,
      "loss": 0.0015,
      "reward": 2.0402345657348633,
      "reward_std": 0.008086705580353737,
      "rewards/accuracy_reward": 0.865234375,
      "rewards/format_reward": 1.0,
      "step": 1583,
      "temperature": 1.0
    },
    {
      "all_correct": 0.625,
      "all_wrong": 0.125,
      "completion_length": 347.96875,
      "epoch": 0.04816932246685318,
      "grad_norm": 0.6221197383175237,
      "kl": 0.04150390625,
      "learning_rate": 9.942858467664596e-07,
      "loss": 0.0017,
      "reward": 1.806249976158142,
      "reward_std": 0.10079033672809601,
      "rewards/accuracy_reward": 0.671875,
      "rewards/format_reward": 1.0,
      "step": 1584,
      "temperature": 1.0
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.125,
      "completion_length": 405.640625,
      "epoch": 0.04819973239265296,
      "grad_norm": 1.031585548205416,
      "kl": 0.038330078125,
      "learning_rate": 9.9427864344459e-07,
      "loss": 0.0015,
      "reward": 1.6910154819488525,
      "reward_std": 0.14263184368610382,
      "rewards/accuracy_reward": 0.5910155177116394,
      "rewards/format_reward": 0.96875,
      "step": 1585,
      "temperature": 1.0
    },
    {
      "all_correct": 0.25,
      "all_wrong": 0.25,
      "completion_length": 366.890625,
      "epoch": 0.04823014231845274,
      "grad_norm": 1.223275608439595,
      "kl": 0.037109375,
      "learning_rate": 9.942714356114142e-07,
      "loss": 0.0015,
      "reward": 1.6380391120910645,
      "reward_std": 0.17795586585998535,
      "rewards/accuracy_reward": 0.5099140405654907,
      "rewards/format_reward": 1.0,
      "step": 1586,
      "temperature": 1.0
    },
    {
      "all_correct": 0.75,
      "all_wrong": 0.0,
      "completion_length": 368.328125,
      "epoch": 0.048260552244252526,
      "grad_norm": 0.6520116864443368,
      "kl": 0.0322265625,
      "learning_rate": 9.942642232669976e-07,
      "loss": 0.0013,
      "reward": 2.113842248916626,
      "reward_std": 0.07689541578292847,
      "rewards/accuracy_reward": 0.926342248916626,
      "rewards/format_reward": 1.0,
      "step": 1587,
      "temperature": 1.0
    },
    {
      "all_correct": 0.625,
      "all_wrong": 0.125,
      "completion_length": 357.46875,
      "epoch": 0.048290962170052305,
      "grad_norm": 1.1704457966371444,
      "kl": 0.034912109375,
      "learning_rate": 9.942570064114065e-07,
      "loss": 0.0014,
      "reward": 1.9099608659744263,
      "reward_std": 0.08057739585638046,
      "rewards/accuracy_reward": 0.7568359375,
      "rewards/format_reward": 1.0,
      "step": 1588,
      "temperature": 1.0
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.125,
      "completion_length": 363.390625,
      "epoch": 0.048321372095852085,
      "grad_norm": 0.8072791272124485,
      "kl": 0.033447265625,
      "learning_rate": 9.942497850447066e-07,
      "loss": 0.0013,
      "reward": 1.8170771598815918,
      "reward_std": 0.11260746419429779,
      "rewards/accuracy_reward": 0.6733270883560181,
      "rewards/format_reward": 1.0,
      "step": 1589,
      "temperature": 1.0
    },
    {
      "all_correct": 0.75,
      "all_wrong": 0.0,
      "completion_length": 363.109375,
      "epoch": 0.048351782021651864,
      "grad_norm": 0.880259150837379,
      "kl": 0.033447265625,
      "learning_rate": 9.942425591669638e-07,
      "loss": 0.0013,
      "reward": 1.975000023841858,
      "reward_std": 0.13887301087379456,
      "rewards/accuracy_reward": 0.8125,
      "rewards/format_reward": 1.0,
      "step": 1590,
      "temperature": 1.0
    },
    {
      "all_correct": 0.375,
      "all_wrong": 0.25,
      "completion_length": 388.078125,
      "epoch": 0.04838219194745165,
      "grad_norm": 1.5455032945479896,
      "kl": 0.0322265625,
      "learning_rate": 9.942353287782443e-07,
      "loss": 0.0013,
      "reward": 1.6080572605133057,
      "reward_std": 0.10116233676671982,
      "rewards/accuracy_reward": 0.4893072843551636,
      "rewards/format_reward": 1.0,
      "step": 1591,
      "temperature": 1.0
    },
    {
      "all_correct": 0.625,
      "all_wrong": 0.125,
      "completion_length": 372.796875,
      "epoch": 0.04841260187325143,
      "grad_norm": 1.5330375534733567,
      "kl": 0.041015625,
      "learning_rate": 9.942280938786136e-07,
      "loss": 0.0016,
      "reward": 1.827918529510498,
      "reward_std": 0.075978122651577,
      "rewards/accuracy_reward": 0.693543553352356,
      "rewards/format_reward": 1.0,
      "step": 1592,
      "temperature": 1.0
    },
    {
      "all_correct": 0.625,
      "all_wrong": 0.125,
      "completion_length": 351.0,
      "epoch": 0.04844301179905121,
      "grad_norm": 1.873313210746184,
      "kl": 0.0390625,
      "learning_rate": 9.942208544681382e-07,
      "loss": 0.0016,
      "reward": 1.9183484315872192,
      "reward_std": 0.03680071234703064,
      "rewards/accuracy_reward": 0.7558484077453613,
      "rewards/format_reward": 1.0,
      "step": 1593,
      "temperature": 1.0
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.125,
      "completion_length": 378.40625,
      "epoch": 0.048473421724850994,
      "grad_norm": 1.2466522950877232,
      "kl": 0.03173828125,
      "learning_rate": 9.942136105468836e-07,
      "loss": 0.0013,
      "reward": 1.8782905340194702,
      "reward_std": 0.06371896713972092,
      "rewards/accuracy_reward": 0.7095404863357544,
      "rewards/format_reward": 1.0,
      "step": 1594,
      "temperature": 1.0
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.375,
      "completion_length": 345.734375,
      "epoch": 0.048503831650650774,
      "grad_norm": 1.0127522486589493,
      "kl": 0.032958984375,
      "learning_rate": 9.942063621149167e-07,
      "loss": 0.0013,
      "reward": 1.6687500476837158,
      "reward_std": 0.09785604476928711,
      "rewards/accuracy_reward": 0.5625,
      "rewards/format_reward": 1.0,
      "step": 1595,
      "temperature": 1.0
    },
    {
      "all_correct": 0.75,
      "all_wrong": 0.25,
      "completion_length": 352.703125,
      "epoch": 0.04853424157645055,
      "grad_norm": 0.5239190601959732,
      "kl": 0.029541015625,
      "learning_rate": 9.94199109172303e-07,
      "loss": 0.0012,
      "reward": 1.8967673778533936,
      "reward_std": 0.0019953041337430477,
      "rewards/accuracy_reward": 0.7467672228813171,
      "rewards/format_reward": 1.0,
      "step": 1596,
      "temperature": 1.0
    },
    {
      "all_correct": 0.625,
      "all_wrong": 0.25,
      "completion_length": 353.78125,
      "epoch": 0.04856465150225033,
      "grad_norm": 0.5223022458695523,
      "kl": 0.03271484375,
      "learning_rate": 9.94191851719109e-07,
      "loss": 0.0013,
      "reward": 1.8195064067840576,
      "reward_std": 0.003923232667148113,
      "rewards/accuracy_reward": 0.669506311416626,
      "rewards/format_reward": 1.0,
      "step": 1597,
      "temperature": 1.0
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.125,
      "completion_length": 407.46875,
      "epoch": 0.04859506142805012,
      "grad_norm": 1.0477238042492734,
      "kl": 0.0311279296875,
      "learning_rate": 9.94184589755401e-07,
      "loss": 0.0012,
      "reward": 1.7822928428649902,
      "reward_std": 0.20271551609039307,
      "rewards/accuracy_reward": 0.6729178428649902,
      "rewards/format_reward": 0.984375,
      "step": 1598,
      "temperature": 1.0
    },
    {
      "all_correct": 0.625,
      "all_wrong": 0.0,
      "completion_length": 355.203125,
      "epoch": 0.0486254713538499,
      "grad_norm": 3.0963659139314945,
      "kl": 0.033203125,
      "learning_rate": 9.94177323281245e-07,
      "loss": 0.0013,
      "reward": 2.0595688819885254,
      "reward_std": 0.0841984823346138,
      "rewards/accuracy_reward": 0.8720687627792358,
      "rewards/format_reward": 1.0,
      "step": 1599,
      "temperature": 1.0
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.125,
      "completion_length": 353.640625,
      "epoch": 0.048655881279649676,
      "grad_norm": 2.478039505589137,
      "kl": 0.030029296875,
      "learning_rate": 9.941700522967075e-07,
      "loss": 0.0012,
      "reward": 1.7853107452392578,
      "reward_std": 0.07803639024496078,
      "rewards/accuracy_reward": 0.6415607929229736,
      "rewards/format_reward": 1.0,
      "step": 1600,
      "temperature": 1.0
    },
    {
      "all_correct": 0.75,
      "all_wrong": 0.0,
      "completion_length": 355.859375,
      "epoch": 0.048686291205449456,
      "grad_norm": 1.3484416111241089,
      "kl": 0.03955078125,
      "learning_rate": 9.94162776801855e-07,
      "loss": 0.0016,
      "reward": 2.017160415649414,
      "reward_std": 0.03981923684477806,
      "rewards/accuracy_reward": 0.829660177230835,
      "rewards/format_reward": 1.0,
      "step": 1601,
      "temperature": 1.0
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.0,
      "completion_length": 353.4375,
      "epoch": 0.04871670113124924,
      "grad_norm": 3.7241698901285076,
      "kl": 0.03955078125,
      "learning_rate": 9.941554967967536e-07,
      "loss": 0.0016,
      "reward": 1.8958606719970703,
      "reward_std": 0.16589069366455078,
      "rewards/accuracy_reward": 0.7396107316017151,
      "rewards/format_reward": 1.0,
      "step": 1602,
      "temperature": 1.0
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.125,
      "completion_length": 391.5625,
      "epoch": 0.04874711105704902,
      "grad_norm": 1.002616647619633,
      "kl": 0.0302734375,
      "learning_rate": 9.9414821228147e-07,
      "loss": 0.0012,
      "reward": 1.8509879112243652,
      "reward_std": 0.06839513778686523,
      "rewards/accuracy_reward": 0.697862982749939,
      "rewards/format_reward": 1.0,
      "step": 1603,
      "temperature": 1.0
    },
    {
      "all_correct": 0.75,
      "all_wrong": 0.0,
      "completion_length": 360.0625,
      "epoch": 0.0487775209828488,
      "grad_norm": 5.538458759235147,
      "kl": 0.0303955078125,
      "learning_rate": 9.941409232560706e-07,
      "loss": 0.0012,
      "reward": 2.104374885559082,
      "reward_std": 0.10199768841266632,
      "rewards/accuracy_reward": 0.9168750047683716,
      "rewards/format_reward": 1.0,
      "step": 1604,
      "temperature": 1.0
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.25,
      "completion_length": 389.875,
      "epoch": 0.048807930908648586,
      "grad_norm": 4.299657580781597,
      "kl": 0.032958984375,
      "learning_rate": 9.941336297206218e-07,
      "loss": 0.0013,
      "reward": 1.7654898166656494,
      "reward_std": 0.035659000277519226,
      "rewards/accuracy_reward": 0.6248648166656494,
      "rewards/format_reward": 1.0,
      "step": 1605,
      "temperature": 1.0
    },
    {
      "all_correct": 0.25,
      "all_wrong": 0.25,
      "completion_length": 421.078125,
      "epoch": 0.048838340834448365,
      "grad_norm": 1.3709310345231727,
      "kl": 0.028564453125,
      "learning_rate": 9.941263316751903e-07,
      "loss": 0.0011,
      "reward": 1.5403196811676025,
      "reward_std": 0.16956695914268494,
      "rewards/accuracy_reward": 0.4246945381164551,
      "rewards/format_reward": 1.0,
      "step": 1606,
      "temperature": 1.0
    },
    {
      "all_correct": 0.25,
      "all_wrong": 0.25,
      "completion_length": 377.8125,
      "epoch": 0.048868750760248145,
      "grad_norm": 1.2575989970300037,
      "kl": 0.0439453125,
      "learning_rate": 9.941190291198427e-07,
      "loss": 0.0018,
      "reward": 1.6765680313110352,
      "reward_std": 0.1317962110042572,
      "rewards/accuracy_reward": 0.5546929836273193,
      "rewards/format_reward": 1.0,
      "step": 1607,
      "temperature": 1.0
    },
    {
      "all_correct": 0.875,
      "all_wrong": 0.0,
      "completion_length": 356.9375,
      "epoch": 0.048899160686047924,
      "grad_norm": 0.5253648932133926,
      "kl": 0.036376953125,
      "learning_rate": 9.941117220546456e-07,
      "loss": 0.0015,
      "reward": 2.0561275482177734,
      "reward_std": 0.00507401255890727,
      "rewards/accuracy_reward": 0.8811274766921997,
      "rewards/format_reward": 1.0,
      "step": 1608,
      "temperature": 1.0
    },
    {
      "all_correct": 0.375,
      "all_wrong": 0.125,
      "completion_length": 381.171875,
      "epoch": 0.04892957061184771,
      "grad_norm": 1.2907963887867246,
      "kl": 0.028076171875,
      "learning_rate": 9.94104410479666e-07,
      "loss": 0.0011,
      "reward": 1.7683851718902588,
      "reward_std": 0.1850762516260147,
      "rewards/accuracy_reward": 0.6340101957321167,
      "rewards/format_reward": 1.0,
      "step": 1609,
      "temperature": 1.0
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.125,
      "completion_length": 390.25,
      "epoch": 0.04895998053764749,
      "grad_norm": 1.048965739826735,
      "kl": 0.035888671875,
      "learning_rate": 9.9409709439497e-07,
      "loss": 0.0014,
      "reward": 1.8398423194885254,
      "reward_std": 0.06410342454910278,
      "rewards/accuracy_reward": 0.6710922122001648,
      "rewards/format_reward": 1.0,
      "step": 1610,
      "temperature": 1.0
    },
    {
      "all_correct": 0.75,
      "all_wrong": 0.0,
      "completion_length": 376.390625,
      "epoch": 0.04899039046344727,
      "grad_norm": 1.4907542786223664,
      "kl": 0.03271484375,
      "learning_rate": 9.940897738006249e-07,
      "loss": 0.0013,
      "reward": 2.0062501430511475,
      "reward_std": 0.1197132021188736,
      "rewards/accuracy_reward": 0.84375,
      "rewards/format_reward": 1.0,
      "step": 1611,
      "temperature": 1.0
    },
    {
      "all_correct": 0.625,
      "all_wrong": 0.125,
      "completion_length": 364.640625,
      "epoch": 0.04902080038924705,
      "grad_norm": 1.1426833643894796,
      "kl": 0.04150390625,
      "learning_rate": 9.940824486966973e-07,
      "loss": 0.0017,
      "reward": 1.9526190757751465,
      "reward_std": 0.01772783324122429,
      "rewards/accuracy_reward": 0.7807440161705017,
      "rewards/format_reward": 1.0,
      "step": 1612,
      "temperature": 1.0
    },
    {
      "all_correct": 0.25,
      "all_wrong": 0.25,
      "completion_length": 382.125,
      "epoch": 0.049051210315046834,
      "grad_norm": 1.06352829898061,
      "kl": 0.03662109375,
      "learning_rate": 9.940751190832542e-07,
      "loss": 0.0015,
      "reward": 1.483259916305542,
      "reward_std": 0.04168295860290527,
      "rewards/accuracy_reward": 0.36763477325439453,
      "rewards/format_reward": 1.0,
      "step": 1613,
      "temperature": 1.0
    },
    {
      "all_correct": 0.75,
      "all_wrong": 0.0,
      "completion_length": 369.609375,
      "epoch": 0.04908162024084661,
      "grad_norm": 0.8671115988600048,
      "kl": 0.0361328125,
      "learning_rate": 9.940677849603623e-07,
      "loss": 0.0014,
      "reward": 2.078125,
      "reward_std": 0.1436041295528412,
      "rewards/accuracy_reward": 0.90625,
      "rewards/format_reward": 1.0,
      "step": 1614,
      "temperature": 1.0
    },
    {
      "all_correct": 0.625,
      "all_wrong": 0.0,
      "completion_length": 366.0625,
      "epoch": 0.04911203016664639,
      "grad_norm": 1.4189014494137373,
      "kl": 0.03759765625,
      "learning_rate": 9.940604463280887e-07,
      "loss": 0.0015,
      "reward": 2.071859359741211,
      "reward_std": 0.17294278740882874,
      "rewards/accuracy_reward": 0.893734335899353,
      "rewards/format_reward": 1.0,
      "step": 1615,
      "temperature": 1.0
    },
    {
      "all_correct": 0.125,
      "all_wrong": 0.25,
      "completion_length": 385.375,
      "epoch": 0.04914244009244617,
      "grad_norm": 1.4834780542250774,
      "kl": 0.0419921875,
      "learning_rate": 9.940531031865003e-07,
      "loss": 0.0017,
      "reward": 1.362673282623291,
      "reward_std": 0.05739261955022812,
      "rewards/accuracy_reward": 0.2564231753349304,
      "rewards/format_reward": 1.0,
      "step": 1616,
      "temperature": 1.0
    },
    {
      "all_correct": 0.875,
      "all_wrong": 0.0,
      "completion_length": 363.296875,
      "epoch": 0.04917285001824596,
      "grad_norm": 0.4688582738854757,
      "kl": 0.033447265625,
      "learning_rate": 9.940457555356643e-07,
      "loss": 0.0013,
      "reward": 2.110405445098877,
      "reward_std": 0.008229927159845829,
      "rewards/accuracy_reward": 0.9104055166244507,
      "rewards/format_reward": 1.0,
      "step": 1617,
      "temperature": 1.0
    },
    {
      "all_correct": 0.625,
      "all_wrong": 0.0,
      "completion_length": 361.5625,
      "epoch": 0.04920325994404574,
      "grad_norm": 1.7435215978858059,
      "kl": 0.048828125,
      "learning_rate": 9.940384033756475e-07,
      "loss": 0.002,
      "reward": 2.054636001586914,
      "reward_std": 0.1404547244310379,
      "rewards/accuracy_reward": 0.8671360611915588,
      "rewards/format_reward": 1.0,
      "step": 1618,
      "temperature": 1.0
    },
    {
      "all_correct": 0.625,
      "all_wrong": 0.125,
      "completion_length": 359.546875,
      "epoch": 0.049233669869845516,
      "grad_norm": 0.7308266162859263,
      "kl": 0.03515625,
      "learning_rate": 9.940310467065168e-07,
      "loss": 0.0014,
      "reward": 1.9130616188049316,
      "reward_std": 0.08688535541296005,
      "rewards/accuracy_reward": 0.7568116188049316,
      "rewards/format_reward": 1.0,
      "step": 1619,
      "temperature": 1.0
    },
    {
      "all_correct": 0.625,
      "all_wrong": 0.0,
      "completion_length": 372.0,
      "epoch": 0.0492640797956453,
      "grad_norm": 0.8249601837489324,
      "kl": 0.0284423828125,
      "learning_rate": 9.940236855283402e-07,
      "loss": 0.0011,
      "reward": 2.0044503211975098,
      "reward_std": 0.09639055281877518,
      "rewards/accuracy_reward": 0.8138253092765808,
      "rewards/format_reward": 1.0,
      "step": 1620,
      "temperature": 1.0
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.375,
      "completion_length": 426.625,
      "epoch": 0.04929448972144508,
      "grad_norm": 0.48947654096508736,
      "kl": 0.0286865234375,
      "learning_rate": 9.940163198411841e-07,
      "loss": 0.0011,
      "reward": 1.6551868915557861,
      "reward_std": 0.009914111346006393,
      "rewards/accuracy_reward": 0.5333119034767151,
      "rewards/format_reward": 1.0,
      "step": 1621,
      "temperature": 1.0
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.125,
      "completion_length": 380.21875,
      "epoch": 0.04932489964724486,
      "grad_norm": 1.0236904942326734,
      "kl": 0.030517578125,
      "learning_rate": 9.940089496451158e-07,
      "loss": 0.0012,
      "reward": 1.7944661378860474,
      "reward_std": 0.1585567742586136,
      "rewards/accuracy_reward": 0.6444660425186157,
      "rewards/format_reward": 1.0,
      "step": 1622,
      "temperature": 1.0
    },
    {
      "all_correct": 0.375,
      "all_wrong": 0.125,
      "completion_length": 393.09375,
      "epoch": 0.04935530957304464,
      "grad_norm": 1.3957201955326277,
      "kl": 0.044189453125,
      "learning_rate": 9.94001574940203e-07,
      "loss": 0.0018,
      "reward": 1.7461063861846924,
      "reward_std": 0.03529345989227295,
      "rewards/accuracy_reward": 0.5773564577102661,
      "rewards/format_reward": 1.0,
      "step": 1623,
      "temperature": 1.0
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.0,
      "completion_length": 365.65625,
      "epoch": 0.049385719498844426,
      "grad_norm": 1.6625290436694786,
      "kl": 0.040771484375,
      "learning_rate": 9.939941957265126e-07,
      "loss": 0.0016,
      "reward": 1.807074785232544,
      "reward_std": 0.1034763753414154,
      "rewards/accuracy_reward": 0.6383247971534729,
      "rewards/format_reward": 1.0,
      "step": 1624,
      "temperature": 1.0
    },
    {
      "all_correct": 0.625,
      "all_wrong": 0.0,
      "completion_length": 369.71875,
      "epoch": 0.049416129424644205,
      "grad_norm": 4.565557020090409,
      "kl": 0.03564453125,
      "learning_rate": 9.93986812004112e-07,
      "loss": 0.0014,
      "reward": 1.9766405820846558,
      "reward_std": 0.08576418459415436,
      "rewards/accuracy_reward": 0.8016405701637268,
      "rewards/format_reward": 1.0,
      "step": 1625,
      "temperature": 1.0
    },
    {
      "all_correct": 0.75,
      "all_wrong": 0.125,
      "completion_length": 350.890625,
      "epoch": 0.049446539350443984,
      "grad_norm": 0.7262923651673935,
      "kl": 0.037109375,
      "learning_rate": 9.939794237730691e-07,
      "loss": 0.0015,
      "reward": 1.9906251430511475,
      "reward_std": 0.08647121489048004,
      "rewards/accuracy_reward": 0.828125,
      "rewards/format_reward": 1.0,
      "step": 1626,
      "temperature": 1.0
    },
    {
      "all_correct": 0.875,
      "all_wrong": 0.0,
      "completion_length": 366.59375,
      "epoch": 0.04947694927624376,
      "grad_norm": 0.8330422454538527,
      "kl": 0.0308837890625,
      "learning_rate": 9.939720310334508e-07,
      "loss": 0.0012,
      "reward": 2.1593751907348633,
      "reward_std": 0.07827534526586533,
      "rewards/accuracy_reward": 0.96875,
      "rewards/format_reward": 1.0,
      "step": 1627,
      "temperature": 1.0
    },
    {
      "all_correct": 0.625,
      "all_wrong": 0.125,
      "completion_length": 381.984375,
      "epoch": 0.04950735920204355,
      "grad_norm": 1.1228799183154856,
      "kl": 0.03564453125,
      "learning_rate": 9.939646337853245e-07,
      "loss": 0.0014,
      "reward": 1.8919830322265625,
      "reward_std": 0.025667762383818626,
      "rewards/accuracy_reward": 0.72635817527771,
      "rewards/format_reward": 1.0,
      "step": 1628,
      "temperature": 1.0
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.0,
      "completion_length": 375.453125,
      "epoch": 0.04953776912784333,
      "grad_norm": 1.131050375483854,
      "kl": 0.03564453125,
      "learning_rate": 9.939572320287578e-07,
      "loss": 0.0014,
      "reward": 1.849438190460205,
      "reward_std": 0.05381552875041962,
      "rewards/accuracy_reward": 0.680688202381134,
      "rewards/format_reward": 1.0,
      "step": 1629,
      "temperature": 1.0
    },
    {
      "all_correct": 0.625,
      "all_wrong": 0.125,
      "completion_length": 351.296875,
      "epoch": 0.04956817905364311,
      "grad_norm": 0.8007424778596781,
      "kl": 0.035888671875,
      "learning_rate": 9.939498257638187e-07,
      "loss": 0.0014,
      "reward": 1.8370535373687744,
      "reward_std": 0.09386977553367615,
      "rewards/accuracy_reward": 0.6964285969734192,
      "rewards/format_reward": 1.0,
      "step": 1630,
      "temperature": 1.0
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.125,
      "completion_length": 357.984375,
      "epoch": 0.04959858897944289,
      "grad_norm": 1.298788173921301,
      "kl": 0.0322265625,
      "learning_rate": 9.939424149905742e-07,
      "loss": 0.0013,
      "reward": 1.822864055633545,
      "reward_std": 0.15720722079277039,
      "rewards/accuracy_reward": 0.6791141033172607,
      "rewards/format_reward": 1.0,
      "step": 1631,
      "temperature": 1.0
    },
    {
      "all_correct": 0.75,
      "all_wrong": 0.125,
      "completion_length": 347.5625,
      "epoch": 0.04962899890524267,
      "grad_norm": 0.5766538041005346,
      "kl": 0.0380859375,
      "learning_rate": 9.939349997090925e-07,
      "loss": 0.0015,
      "reward": 1.9670263528823853,
      "reward_std": 0.009457984007894993,
      "rewards/accuracy_reward": 0.7920262813568115,
      "rewards/format_reward": 1.0,
      "step": 1632,
      "temperature": 1.0
    },
    {
      "all_correct": 0.75,
      "all_wrong": 0.0,
      "completion_length": 346.890625,
      "epoch": 0.04965940883104245,
      "grad_norm": 0.9738371822219221,
      "kl": 0.041259765625,
      "learning_rate": 9.939275799194406e-07,
      "loss": 0.0017,
      "reward": 1.9765625,
      "reward_std": 0.060398709028959274,
      "rewards/accuracy_reward": 0.8046875,
      "rewards/format_reward": 1.0,
      "step": 1633,
      "temperature": 1.0
    },
    {
      "all_correct": 0.375,
      "all_wrong": 0.0,
      "completion_length": 383.84375,
      "epoch": 0.04968981875684223,
      "grad_norm": 2.8621775161227014,
      "kl": 0.032958984375,
      "learning_rate": 9.93920155621687e-07,
      "loss": 0.0013,
      "reward": 1.8008538484573364,
      "reward_std": 0.05842326208949089,
      "rewards/accuracy_reward": 0.6102288365364075,
      "rewards/format_reward": 1.0,
      "step": 1634,
      "temperature": 1.0
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.125,
      "completion_length": 332.28125,
      "epoch": 0.04972022868264202,
      "grad_norm": 1.5371610531744304,
      "kl": 0.04443359375,
      "learning_rate": 9.939127268158987e-07,
      "loss": 0.0018,
      "reward": 1.8770833015441895,
      "reward_std": 0.17122013866901398,
      "rewards/accuracy_reward": 0.7395833730697632,
      "rewards/format_reward": 1.0,
      "step": 1635,
      "temperature": 1.0
    },
    {
      "all_correct": 0.625,
      "all_wrong": 0.0,
      "completion_length": 342.03125,
      "epoch": 0.0497506386084418,
      "grad_norm": 1.5899053902015894,
      "kl": 0.033935546875,
      "learning_rate": 9.939052935021442e-07,
      "loss": 0.0014,
      "reward": 2.01462459564209,
      "reward_std": 0.10628823935985565,
      "rewards/accuracy_reward": 0.8396245241165161,
      "rewards/format_reward": 1.0,
      "step": 1636,
      "temperature": 1.0
    },
    {
      "all_correct": 0.75,
      "all_wrong": 0.125,
      "completion_length": 379.453125,
      "epoch": 0.049781048534241576,
      "grad_norm": 1.1009704959983944,
      "kl": 0.031494140625,
      "learning_rate": 9.938978556804907e-07,
      "loss": 0.0013,
      "reward": 1.9638290405273438,
      "reward_std": 0.03070160374045372,
      "rewards/accuracy_reward": 0.7950790524482727,
      "rewards/format_reward": 1.0,
      "step": 1637,
      "temperature": 1.0
    },
    {
      "all_correct": 0.75,
      "all_wrong": 0.125,
      "completion_length": 355.875,
      "epoch": 0.049811458460041355,
      "grad_norm": 0.30376802399305636,
      "kl": 0.03369140625,
      "learning_rate": 9.938904133510066e-07,
      "loss": 0.0014,
      "reward": 1.9375,
      "reward_std": 0.06943650543689728,
      "rewards/accuracy_reward": 0.78125,
      "rewards/format_reward": 1.0,
      "step": 1638,
      "temperature": 1.0
    },
    {
      "all_correct": 0.75,
      "all_wrong": 0.0,
      "completion_length": 365.359375,
      "epoch": 0.04984186838584114,
      "grad_norm": 1.1232362296676783,
      "kl": 0.029541015625,
      "learning_rate": 9.938829665137595e-07,
      "loss": 0.0012,
      "reward": 2.049867868423462,
      "reward_std": 0.1196543425321579,
      "rewards/accuracy_reward": 0.8686177730560303,
      "rewards/format_reward": 1.0,
      "step": 1639,
      "temperature": 1.0
    },
    {
      "all_correct": 0.375,
      "all_wrong": 0.25,
      "completion_length": 393.546875,
      "epoch": 0.04987227831164092,
      "grad_norm": 0.6126305221586202,
      "kl": 0.033447265625,
      "learning_rate": 9.938755151688176e-07,
      "loss": 0.0013,
      "reward": 1.6714158058166504,
      "reward_std": 0.14979159832000732,
      "rewards/accuracy_reward": 0.5526658296585083,
      "rewards/format_reward": 1.0,
      "step": 1640,
      "temperature": 1.0
    },
    {
      "all_correct": 0.625,
      "all_wrong": 0.0,
      "completion_length": 384.921875,
      "epoch": 0.0499026882374407,
      "grad_norm": 0.6966865177064817,
      "kl": 0.03564453125,
      "learning_rate": 9.938680593162488e-07,
      "loss": 0.0014,
      "reward": 1.8735941648483276,
      "reward_std": 0.13001015782356262,
      "rewards/accuracy_reward": 0.7267191410064697,
      "rewards/format_reward": 1.0,
      "step": 1641,
      "temperature": 1.0
    },
    {
      "all_correct": 0.625,
      "all_wrong": 0.25,
      "completion_length": 351.640625,
      "epoch": 0.04993309816324048,
      "grad_norm": 0.8710328699575767,
      "kl": 0.04150390625,
      "learning_rate": 9.938605989561212e-07,
      "loss": 0.0017,
      "reward": 1.839176893234253,
      "reward_std": 0.07993703335523605,
      "rewards/accuracy_reward": 0.6985518336296082,
      "rewards/format_reward": 1.0,
      "step": 1642,
      "temperature": 1.0
    },
    {
      "all_correct": 0.625,
      "all_wrong": 0.125,
      "completion_length": 354.046875,
      "epoch": 0.049963508089040265,
      "grad_norm": 0.3330535540502741,
      "kl": 0.0301513671875,
      "learning_rate": 9.938531340885028e-07,
      "loss": 0.0012,
      "reward": 1.8765519857406616,
      "reward_std": 0.077632375061512,
      "rewards/accuracy_reward": 0.7109269499778748,
      "rewards/format_reward": 1.0,
      "step": 1643,
      "temperature": 1.0
    },
    {
      "all_correct": 0.375,
      "all_wrong": 0.0,
      "completion_length": 355.640625,
      "epoch": 0.049993918014840044,
      "grad_norm": 4.889179501029402,
      "kl": 0.033935546875,
      "learning_rate": 9.938456647134617e-07,
      "loss": 0.0014,
      "reward": 1.636674165725708,
      "reward_std": 0.2371462881565094,
      "rewards/accuracy_reward": 0.5179240703582764,
      "rewards/format_reward": 1.0,
      "step": 1644,
      "temperature": 1.0
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.125,
      "completion_length": 371.5625,
      "epoch": 0.05002432794063982,
      "grad_norm": 4.442556743116582,
      "kl": 0.036376953125,
      "learning_rate": 9.938381908310663e-07,
      "loss": 0.0015,
      "reward": 1.79168701171875,
      "reward_std": 0.0852556899189949,
      "rewards/accuracy_reward": 0.632311999797821,
      "rewards/format_reward": 1.0,
      "step": 1645,
      "temperature": 1.0
    },
    {
      "all_correct": 0.625,
      "all_wrong": 0.125,
      "completion_length": 381.265625,
      "epoch": 0.0500547378664396,
      "grad_norm": 1.340102870247926,
      "kl": 0.038818359375,
      "learning_rate": 9.938307124413846e-07,
      "loss": 0.0016,
      "reward": 1.8142801523208618,
      "reward_std": 0.06440731137990952,
      "rewards/accuracy_reward": 0.673655092716217,
      "rewards/format_reward": 1.0,
      "step": 1646,
      "temperature": 1.0
    },
    {
      "all_correct": 0.125,
      "all_wrong": 0.125,
      "completion_length": 406.9375,
      "epoch": 0.05008514779223939,
      "grad_norm": 1.039049590517804,
      "kl": 0.032958984375,
      "learning_rate": 9.938232295444849e-07,
      "loss": 0.0013,
      "reward": 1.477534532546997,
      "reward_std": 0.23548895120620728,
      "rewards/accuracy_reward": 0.3775344491004944,
      "rewards/format_reward": 1.0,
      "step": 1647,
      "temperature": 1.0
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.25,
      "completion_length": 379.625,
      "epoch": 0.05011555771803917,
      "grad_norm": 0.8045936546376954,
      "kl": 0.0294189453125,
      "learning_rate": 9.938157421404354e-07,
      "loss": 0.0012,
      "reward": 1.8295786380767822,
      "reward_std": 0.09341376274824142,
      "rewards/accuracy_reward": 0.6889535188674927,
      "rewards/format_reward": 1.0,
      "step": 1648,
      "temperature": 1.0
    },
    {
      "all_correct": 0.875,
      "all_wrong": 0.125,
      "completion_length": 373.171875,
      "epoch": 0.05014596764383895,
      "grad_norm": 0.24953388076486008,
      "kl": 0.031494140625,
      "learning_rate": 9.938082502293045e-07,
      "loss": 0.0013,
      "reward": 2.046875,
      "reward_std": 0.008838837966322899,
      "rewards/accuracy_reward": 0.875,
      "rewards/format_reward": 1.0,
      "step": 1649,
      "temperature": 1.0
    },
    {
      "all_correct": 0.75,
      "all_wrong": 0.125,
      "completion_length": 354.15625,
      "epoch": 0.05017637756963873,
      "grad_norm": 0.4183402418758457,
      "kl": 0.03515625,
      "learning_rate": 9.93800753811161e-07,
      "loss": 0.0014,
      "reward": 1.9156250953674316,
      "reward_std": 0.04419417306780815,
      "rewards/accuracy_reward": 0.765625,
      "rewards/format_reward": 1.0,
      "step": 1650,
      "temperature": 1.0
    },
    {
      "all_correct": 0.625,
      "all_wrong": 0.125,
      "completion_length": 371.375,
      "epoch": 0.05020678749543851,
      "grad_norm": 0.6121153856507449,
      "kl": 0.037353515625,
      "learning_rate": 9.937932528860727e-07,
      "loss": 0.0015,
      "reward": 1.9039881229400635,
      "reward_std": 0.0864611566066742,
      "rewards/accuracy_reward": 0.741487979888916,
      "rewards/format_reward": 1.0,
      "step": 1651,
      "temperature": 1.0
    },
    {
      "all_correct": 0.375,
      "all_wrong": 0.25,
      "completion_length": 365.515625,
      "epoch": 0.05023719742123829,
      "grad_norm": 1.6587345494518946,
      "kl": 0.042236328125,
      "learning_rate": 9.937857474541083e-07,
      "loss": 0.0017,
      "reward": 1.5650074481964111,
      "reward_std": 0.0547744557261467,
      "rewards/accuracy_reward": 0.4431324601173401,
      "rewards/format_reward": 1.0,
      "step": 1652,
      "temperature": 1.0
    },
    {
      "all_correct": 0.625,
      "all_wrong": 0.125,
      "completion_length": 361.40625,
      "epoch": 0.05026760734703807,
      "grad_norm": 1.0617490451283724,
      "kl": 0.036376953125,
      "learning_rate": 9.937782375153364e-07,
      "loss": 0.0015,
      "reward": 1.8342570066452026,
      "reward_std": 0.07604838907718658,
      "rewards/accuracy_reward": 0.6811319589614868,
      "rewards/format_reward": 1.0,
      "step": 1653,
      "temperature": 1.0
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.125,
      "completion_length": 353.375,
      "epoch": 0.05029801727283786,
      "grad_norm": 0.8310994657658896,
      "kl": 0.043212890625,
      "learning_rate": 9.937707230698255e-07,
      "loss": 0.0017,
      "reward": 1.8482410907745361,
      "reward_std": 0.15723612904548645,
      "rewards/accuracy_reward": 0.701366126537323,
      "rewards/format_reward": 1.0,
      "step": 1654,
      "temperature": 1.0
    },
    {
      "all_correct": 0.375,
      "all_wrong": 0.25,
      "completion_length": 373.09375,
      "epoch": 0.050328427198637636,
      "grad_norm": 3.6399266148591574,
      "kl": 0.037841796875,
      "learning_rate": 9.93763204117644e-07,
      "loss": 0.0015,
      "reward": 1.7966499328613281,
      "reward_std": 0.0966249331831932,
      "rewards/accuracy_reward": 0.6560249328613281,
      "rewards/format_reward": 1.0,
      "step": 1655,
      "temperature": 1.0
    },
    {
      "all_correct": 0.375,
      "all_wrong": 0.25,
      "completion_length": 361.0,
      "epoch": 0.050358837124437415,
      "grad_norm": 1.178986597138529,
      "kl": 0.042236328125,
      "learning_rate": 9.937556806588606e-07,
      "loss": 0.0017,
      "reward": 1.697963833808899,
      "reward_std": 0.17579889297485352,
      "rewards/accuracy_reward": 0.5729637145996094,
      "rewards/format_reward": 1.0,
      "step": 1656,
      "temperature": 1.0
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.125,
      "completion_length": 390.15625,
      "epoch": 0.050389247050237194,
      "grad_norm": 2.9622499482698816,
      "kl": 0.0380859375,
      "learning_rate": 9.937481526935443e-07,
      "loss": 0.0015,
      "reward": 1.8066219091415405,
      "reward_std": 0.09898646175861359,
      "rewards/accuracy_reward": 0.6566218733787537,
      "rewards/format_reward": 1.0,
      "step": 1657,
      "temperature": 1.0
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.125,
      "completion_length": 374.109375,
      "epoch": 0.05041965697603698,
      "grad_norm": 1.473096996494932,
      "kl": 0.045166015625,
      "learning_rate": 9.937406202217635e-07,
      "loss": 0.0018,
      "reward": 1.7280230522155762,
      "reward_std": 0.1014149859547615,
      "rewards/accuracy_reward": 0.5936480760574341,
      "rewards/format_reward": 1.0,
      "step": 1658,
      "temperature": 1.0
    },
    {
      "all_correct": 0.25,
      "all_wrong": 0.375,
      "completion_length": 365.328125,
      "epoch": 0.05045006690183676,
      "grad_norm": 0.9597011332437813,
      "kl": 0.0322265625,
      "learning_rate": 9.93733083243587e-07,
      "loss": 0.0013,
      "reward": 1.4885691404342651,
      "reward_std": 0.10112345963716507,
      "rewards/accuracy_reward": 0.37919408082962036,
      "rewards/format_reward": 1.0,
      "step": 1659,
      "temperature": 1.0
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.25,
      "completion_length": 354.9375,
      "epoch": 0.05048047682763654,
      "grad_norm": 0.6986928189945019,
      "kl": 0.03515625,
      "learning_rate": 9.937255417590835e-07,
      "loss": 0.0014,
      "reward": 1.766253113746643,
      "reward_std": 0.01196515467017889,
      "rewards/accuracy_reward": 0.6193780899047852,
      "rewards/format_reward": 1.0,
      "step": 1660,
      "temperature": 1.0
    },
    {
      "all_correct": 0.25,
      "all_wrong": 0.125,
      "completion_length": 390.90625,
      "epoch": 0.05051088675343632,
      "grad_norm": 3.511848636702321,
      "kl": 0.039794921875,
      "learning_rate": 9.937179957683218e-07,
      "loss": 0.0016,
      "reward": 1.614233136177063,
      "reward_std": 0.12450411170721054,
      "rewards/accuracy_reward": 0.4704830050468445,
      "rewards/format_reward": 1.0,
      "step": 1661,
      "temperature": 1.0
    },
    {
      "all_correct": 0.375,
      "all_wrong": 0.125,
      "completion_length": 377.59375,
      "epoch": 0.050541296679236104,
      "grad_norm": 1.6828295610164712,
      "kl": 0.033935546875,
      "learning_rate": 9.937104452713711e-07,
      "loss": 0.0014,
      "reward": 1.6807746887207031,
      "reward_std": 0.20051831007003784,
      "rewards/accuracy_reward": 0.562024712562561,
      "rewards/format_reward": 1.0,
      "step": 1662,
      "temperature": 1.0
    },
    {
      "all_correct": 0.75,
      "all_wrong": 0.0,
      "completion_length": 354.203125,
      "epoch": 0.050571706605035883,
      "grad_norm": 1.1319360294225356,
      "kl": 0.03759765625,
      "learning_rate": 9.937028902683e-07,
      "loss": 0.0015,
      "reward": 2.0091750621795654,
      "reward_std": 0.07335405051708221,
      "rewards/accuracy_reward": 0.8466750383377075,
      "rewards/format_reward": 1.0,
      "step": 1663,
      "temperature": 1.0
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.125,
      "completion_length": 340.390625,
      "epoch": 0.05060211653083566,
      "grad_norm": 1.828628224142654,
      "kl": 0.039794921875,
      "learning_rate": 9.936953307591777e-07,
      "loss": 0.0016,
      "reward": 1.8635308742523193,
      "reward_std": 0.12882153689861298,
      "rewards/accuracy_reward": 0.7197808027267456,
      "rewards/format_reward": 1.0,
      "step": 1664,
      "temperature": 1.0
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.25,
      "completion_length": 356.53125,
      "epoch": 0.05063252645663545,
      "grad_norm": 1.1458638914066333,
      "kl": 0.043212890625,
      "learning_rate": 9.93687766744073e-07,
      "loss": 0.0017,
      "reward": 1.7048448324203491,
      "reward_std": 0.11007291078567505,
      "rewards/accuracy_reward": 0.5798447132110596,
      "rewards/format_reward": 1.0,
      "step": 1665,
      "temperature": 1.0
    },
    {
      "all_correct": 0.625,
      "all_wrong": 0.125,
      "completion_length": 352.078125,
      "epoch": 0.05066293638243523,
      "grad_norm": 1.4288198379279586,
      "kl": 0.03369140625,
      "learning_rate": 9.936801982230548e-07,
      "loss": 0.0013,
      "reward": 1.9037678241729736,
      "reward_std": 0.018663080409169197,
      "rewards/accuracy_reward": 0.7287677526473999,
      "rewards/format_reward": 1.0,
      "step": 1666,
      "temperature": 1.0
    },
    {
      "all_correct": 0.75,
      "all_wrong": 0.0,
      "completion_length": 356.21875,
      "epoch": 0.05069334630823501,
      "grad_norm": 0.7863880348225815,
      "kl": 0.038330078125,
      "learning_rate": 9.936726251961925e-07,
      "loss": 0.0015,
      "reward": 2.039496660232544,
      "reward_std": 0.07071912288665771,
      "rewards/accuracy_reward": 0.8644964694976807,
      "rewards/format_reward": 1.0,
      "step": 1667,
      "temperature": 1.0
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.125,
      "completion_length": 365.390625,
      "epoch": 0.050723756234034786,
      "grad_norm": 3.966981127952393,
      "kl": 0.038330078125,
      "learning_rate": 9.93665047663555e-07,
      "loss": 0.0015,
      "reward": 1.8164305686950684,
      "reward_std": 0.020390480756759644,
      "rewards/accuracy_reward": 0.6414304375648499,
      "rewards/format_reward": 1.0,
      "step": 1668,
      "temperature": 1.0
    },
    {
      "all_correct": 0.75,
      "all_wrong": 0.0,
      "completion_length": 379.453125,
      "epoch": 0.05075416615983457,
      "grad_norm": 1.1533730851878448,
      "kl": 0.0269775390625,
      "learning_rate": 9.936574656252116e-07,
      "loss": 0.0011,
      "reward": 2.027372360229492,
      "reward_std": 0.09050028771162033,
      "rewards/accuracy_reward": 0.8429971933364868,
      "rewards/format_reward": 1.0,
      "step": 1669,
      "temperature": 1.0
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.25,
      "completion_length": 342.671875,
      "epoch": 0.05078457608563435,
      "grad_norm": 2.2878501541360743,
      "kl": 0.037841796875,
      "learning_rate": 9.936498790812316e-07,
      "loss": 0.0015,
      "reward": 1.8312500715255737,
      "reward_std": 0.09080372750759125,
      "rewards/accuracy_reward": 0.6875,
      "rewards/format_reward": 1.0,
      "step": 1670,
      "temperature": 1.0
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.0,
      "completion_length": 385.671875,
      "epoch": 0.05081498601143413,
      "grad_norm": 1.1168035576399926,
      "kl": 0.034912109375,
      "learning_rate": 9.93642288031684e-07,
      "loss": 0.0014,
      "reward": 1.9249169826507568,
      "reward_std": 0.21349960565567017,
      "rewards/accuracy_reward": 0.7686669826507568,
      "rewards/format_reward": 1.0,
      "step": 1671,
      "temperature": 1.0
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.125,
      "completion_length": 383.953125,
      "epoch": 0.05084539593723391,
      "grad_norm": 0.5943885498576946,
      "kl": 0.03515625,
      "learning_rate": 9.936346924766383e-07,
      "loss": 0.0014,
      "reward": 1.8754420280456543,
      "reward_std": 0.07013367861509323,
      "rewards/accuracy_reward": 0.709817111492157,
      "rewards/format_reward": 1.0,
      "step": 1672,
      "temperature": 1.0
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.0,
      "completion_length": 391.984375,
      "epoch": 0.050875805863033696,
      "grad_norm": 1.0790132512070234,
      "kl": 0.03759765625,
      "learning_rate": 9.936270924161635e-07,
      "loss": 0.0015,
      "reward": 1.8200020790100098,
      "reward_std": 0.1979990005493164,
      "rewards/accuracy_reward": 0.7012521624565125,
      "rewards/format_reward": 0.984375,
      "step": 1673,
      "temperature": 1.0
    },
    {
      "all_correct": 0.25,
      "all_wrong": 0.375,
      "completion_length": 370.265625,
      "epoch": 0.050906215788833475,
      "grad_norm": 0.9482184940203908,
      "kl": 0.040283203125,
      "learning_rate": 9.936194878503291e-07,
      "loss": 0.0016,
      "reward": 1.6085577011108398,
      "reward_std": 0.1292867809534073,
      "rewards/accuracy_reward": 0.49293267726898193,
      "rewards/format_reward": 1.0,
      "step": 1674,
      "temperature": 1.0
    },
    {
      "all_correct": 0.75,
      "all_wrong": 0.125,
      "completion_length": 362.265625,
      "epoch": 0.050936625714633255,
      "grad_norm": 0.7133985073444051,
      "kl": 0.03271484375,
      "learning_rate": 9.936118787792049e-07,
      "loss": 0.0013,
      "reward": 1.9343750476837158,
      "reward_std": 0.07827534526586533,
      "rewards/accuracy_reward": 0.78125,
      "rewards/format_reward": 1.0,
      "step": 1675,
      "temperature": 1.0
    },
    {
      "all_correct": 0.625,
      "all_wrong": 0.125,
      "completion_length": 362.71875,
      "epoch": 0.05096703564043304,
      "grad_norm": 0.3971615580548201,
      "kl": 0.03955078125,
      "learning_rate": 9.936042652028597e-07,
      "loss": 0.0016,
      "reward": 1.9452810287475586,
      "reward_std": 0.011235001496970654,
      "rewards/accuracy_reward": 0.7734060287475586,
      "rewards/format_reward": 1.0,
      "step": 1676,
      "temperature": 1.0
    },
    {
      "all_correct": 0.75,
      "all_wrong": 0.125,
      "completion_length": 371.09375,
      "epoch": 0.05099744556623282,
      "grad_norm": 2.816785325438691,
      "kl": 0.0380859375,
      "learning_rate": 9.935966471213634e-07,
      "loss": 0.0015,
      "reward": 2.0082387924194336,
      "reward_std": 0.07206667214632034,
      "rewards/accuracy_reward": 0.8394886255264282,
      "rewards/format_reward": 1.0,
      "step": 1677,
      "temperature": 1.0
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.125,
      "completion_length": 351.546875,
      "epoch": 0.0510278554920326,
      "grad_norm": 0.9377350789267656,
      "kl": 0.03662109375,
      "learning_rate": 9.935890245347856e-07,
      "loss": 0.0015,
      "reward": 1.9370989799499512,
      "reward_std": 0.08515331894159317,
      "rewards/accuracy_reward": 0.765224039554596,
      "rewards/format_reward": 1.0,
      "step": 1678,
      "temperature": 1.0
    },
    {
      "all_correct": 0.375,
      "all_wrong": 0.0,
      "completion_length": 391.8125,
      "epoch": 0.05105826541783238,
      "grad_norm": 1.4591388121684274,
      "kl": 0.037841796875,
      "learning_rate": 9.935813974431957e-07,
      "loss": 0.0015,
      "reward": 1.8176357746124268,
      "reward_std": 0.18189215660095215,
      "rewards/accuracy_reward": 0.6832607388496399,
      "rewards/format_reward": 0.96875,
      "step": 1679,
      "temperature": 1.0
    },
    {
      "all_correct": 0.375,
      "all_wrong": 0.375,
      "completion_length": 374.4375,
      "epoch": 0.051088675343632164,
      "grad_norm": 0.6936870528033658,
      "kl": 0.04345703125,
      "learning_rate": 9.935737658466631e-07,
      "loss": 0.0017,
      "reward": 1.5233813524246216,
      "reward_std": 0.05789122357964516,
      "rewards/accuracy_reward": 0.43900638818740845,
      "rewards/format_reward": 1.0,
      "step": 1680,
      "temperature": 1.0
    },
    {
      "all_correct": 0.75,
      "all_wrong": 0.0,
      "completion_length": 352.65625,
      "epoch": 0.051119085269431944,
      "grad_norm": 0.9509372394399741,
      "kl": 0.0361328125,
      "learning_rate": 9.93566129745258e-07,
      "loss": 0.0014,
      "reward": 2.036555051803589,
      "reward_std": 0.01791897602379322,
      "rewards/accuracy_reward": 0.836555004119873,
      "rewards/format_reward": 1.0,
      "step": 1681,
      "temperature": 1.0
    },
    {
      "all_correct": 0.625,
      "all_wrong": 0.25,
      "completion_length": 371.078125,
      "epoch": 0.05114949519523172,
      "grad_norm": 0.3951769342742871,
      "kl": 0.042724609375,
      "learning_rate": 9.935584891390495e-07,
      "loss": 0.0017,
      "reward": 1.791914463043213,
      "reward_std": 0.009663645178079605,
      "rewards/accuracy_reward": 0.660664439201355,
      "rewards/format_reward": 1.0,
      "step": 1682,
      "temperature": 1.0
    },
    {
      "all_correct": 0.25,
      "all_wrong": 0.25,
      "completion_length": 385.203125,
      "epoch": 0.0511799051210315,
      "grad_norm": 1.3605734298930652,
      "kl": 0.04931640625,
      "learning_rate": 9.935508440281078e-07,
      "loss": 0.002,
      "reward": 1.6233460903167725,
      "reward_std": 0.11581914871931076,
      "rewards/accuracy_reward": 0.49834609031677246,
      "rewards/format_reward": 1.0,
      "step": 1683,
      "temperature": 1.0
    },
    {
      "all_correct": 0.375,
      "all_wrong": 0.125,
      "completion_length": 364.796875,
      "epoch": 0.05121031504683129,
      "grad_norm": 2.890698984590165,
      "kl": 0.0294189453125,
      "learning_rate": 9.935431944125024e-07,
      "loss": 0.0012,
      "reward": 1.9088068008422852,
      "reward_std": 0.19097597897052765,
      "rewards/accuracy_reward": 0.7556818127632141,
      "rewards/format_reward": 1.0,
      "step": 1684,
      "temperature": 1.0
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.25,
      "completion_length": 389.828125,
      "epoch": 0.05124072497263107,
      "grad_norm": 1.7211652321826534,
      "kl": 0.03955078125,
      "learning_rate": 9.935355402923033e-07,
      "loss": 0.0016,
      "reward": 1.7310891151428223,
      "reward_std": 0.1575307846069336,
      "rewards/accuracy_reward": 0.6373391151428223,
      "rewards/format_reward": 0.96875,
      "step": 1685,
      "temperature": 1.0
    },
    {
      "all_correct": 0.75,
      "all_wrong": 0.0,
      "completion_length": 359.40625,
      "epoch": 0.05127113489843085,
      "grad_norm": 4.429784977710128,
      "kl": 0.0390625,
      "learning_rate": 9.935278816675802e-07,
      "loss": 0.0016,
      "reward": 2.050593852996826,
      "reward_std": 0.02281137928366661,
      "rewards/accuracy_reward": 0.8537189364433289,
      "rewards/format_reward": 1.0,
      "step": 1686,
      "temperature": 1.0
    },
    {
      "all_correct": 0.375,
      "all_wrong": 0.25,
      "completion_length": 363.8125,
      "epoch": 0.051301544824230626,
      "grad_norm": 7.602922751970457,
      "kl": 0.03759765625,
      "learning_rate": 9.935202185384031e-07,
      "loss": 0.0015,
      "reward": 1.6680340766906738,
      "reward_std": 0.08603070676326752,
      "rewards/accuracy_reward": 0.533659040927887,
      "rewards/format_reward": 1.0,
      "step": 1687,
      "temperature": 1.0
    },
    {
      "all_correct": 0.75,
      "all_wrong": 0.0,
      "completion_length": 353.09375,
      "epoch": 0.05133195475003041,
      "grad_norm": 1.5179480810969561,
      "kl": 0.036376953125,
      "learning_rate": 9.935125509048418e-07,
      "loss": 0.0015,
      "reward": 2.0531249046325684,
      "reward_std": 0.18494783341884613,
      "rewards/accuracy_reward": 0.890625,
      "rewards/format_reward": 1.0,
      "step": 1688,
      "temperature": 1.0
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.25,
      "completion_length": 349.890625,
      "epoch": 0.05136236467583019,
      "grad_norm": 0.9065629458172986,
      "kl": 0.038330078125,
      "learning_rate": 9.935048787669665e-07,
      "loss": 0.0015,
      "reward": 1.7286990880966187,
      "reward_std": 0.09804330766201019,
      "rewards/accuracy_reward": 0.6036989688873291,
      "rewards/format_reward": 1.0,
      "step": 1689,
      "temperature": 1.0
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.125,
      "completion_length": 354.921875,
      "epoch": 0.05139277460162997,
      "grad_norm": 1.52422660389779,
      "kl": 0.045654296875,
      "learning_rate": 9.93497202124847e-07,
      "loss": 0.0018,
      "reward": 1.7389616966247559,
      "reward_std": 0.05179315805435181,
      "rewards/accuracy_reward": 0.5827116966247559,
      "rewards/format_reward": 1.0,
      "step": 1690,
      "temperature": 1.0
    },
    {
      "all_correct": 0.625,
      "all_wrong": 0.0,
      "completion_length": 345.796875,
      "epoch": 0.051423184527429756,
      "grad_norm": 1.070619639271041,
      "kl": 0.0361328125,
      "learning_rate": 9.934895209785536e-07,
      "loss": 0.0014,
      "reward": 2.0241079330444336,
      "reward_std": 0.07567884773015976,
      "rewards/accuracy_reward": 0.8366081118583679,
      "rewards/format_reward": 1.0,
      "step": 1691,
      "temperature": 1.0
    },
    {
      "all_correct": 0.875,
      "all_wrong": 0.0,
      "completion_length": 354.640625,
      "epoch": 0.051453594453229536,
      "grad_norm": 1.5113803828379757,
      "kl": 0.03955078125,
      "learning_rate": 9.934818353281564e-07,
      "loss": 0.0016,
      "reward": 2.0800211429595947,
      "reward_std": 0.031228920444846153,
      "rewards/accuracy_reward": 0.8893961310386658,
      "rewards/format_reward": 1.0,
      "step": 1692,
      "temperature": 1.0
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.125,
      "completion_length": 395.0,
      "epoch": 0.051484004379029315,
      "grad_norm": 1.5163073362737587,
      "kl": 0.032470703125,
      "learning_rate": 9.934741451737254e-07,
      "loss": 0.0013,
      "reward": 1.7957069873809814,
      "reward_std": 0.08248253166675568,
      "rewards/accuracy_reward": 0.6394569277763367,
      "rewards/format_reward": 1.0,
      "step": 1693,
      "temperature": 1.0
    },
    {
      "all_correct": 0.75,
      "all_wrong": 0.0,
      "completion_length": 351.546875,
      "epoch": 0.051514414304829094,
      "grad_norm": 0.8653184565169834,
      "kl": 0.03466796875,
      "learning_rate": 9.934664505153308e-07,
      "loss": 0.0014,
      "reward": 2.0211806297302246,
      "reward_std": 0.03529752790927887,
      "rewards/accuracy_reward": 0.8430556058883667,
      "rewards/format_reward": 1.0,
      "step": 1694,
      "temperature": 1.0
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.125,
      "completion_length": 400.484375,
      "epoch": 0.05154482423062888,
      "grad_norm": 0.7886583539947964,
      "kl": 0.036865234375,
      "learning_rate": 9.934587513530428e-07,
      "loss": 0.0015,
      "reward": 1.811471939086914,
      "reward_std": 0.09145061671733856,
      "rewards/accuracy_reward": 0.6614718437194824,
      "rewards/format_reward": 1.0,
      "step": 1695,
      "temperature": 1.0
    },
    {
      "all_correct": 0.75,
      "all_wrong": 0.125,
      "completion_length": 338.28125,
      "epoch": 0.05157523415642866,
      "grad_norm": 0.9356359876134492,
      "kl": 0.0390625,
      "learning_rate": 9.934510476869315e-07,
      "loss": 0.0016,
      "reward": 1.938044548034668,
      "reward_std": 0.036843061447143555,
      "rewards/accuracy_reward": 0.7755445241928101,
      "rewards/format_reward": 1.0,
      "step": 1696,
      "temperature": 1.0
    },
    {
      "all_correct": 0.375,
      "all_wrong": 0.125,
      "completion_length": 384.765625,
      "epoch": 0.05160564408222844,
      "grad_norm": 1.1611883627854689,
      "kl": 0.037841796875,
      "learning_rate": 9.934433395170677e-07,
      "loss": 0.0015,
      "reward": 1.7988560199737549,
      "reward_std": 0.18911992013454437,
      "rewards/accuracy_reward": 0.6551059484481812,
      "rewards/format_reward": 1.0,
      "step": 1697,
      "temperature": 1.0
    },
    {
      "all_correct": 0.625,
      "all_wrong": 0.125,
      "completion_length": 367.921875,
      "epoch": 0.05163605400802822,
      "grad_norm": 0.9630382646793093,
      "kl": 0.0341796875,
      "learning_rate": 9.934356268435215e-07,
      "loss": 0.0014,
      "reward": 1.9741320610046387,
      "reward_std": 0.13312062621116638,
      "rewards/accuracy_reward": 0.8116319179534912,
      "rewards/format_reward": 1.0,
      "step": 1698,
      "temperature": 1.0
    },
    {
      "all_correct": 0.75,
      "all_wrong": 0.125,
      "completion_length": 358.984375,
      "epoch": 0.051666463933828004,
      "grad_norm": 0.503210643045451,
      "kl": 0.034423828125,
      "learning_rate": 9.934279096663634e-07,
      "loss": 0.0014,
      "reward": 1.970725178718567,
      "reward_std": 0.004311002790927887,
      "rewards/accuracy_reward": 0.7957251667976379,
      "rewards/format_reward": 1.0,
      "step": 1699,
      "temperature": 1.0
    },
    {
      "all_correct": 0.875,
      "all_wrong": 0.0,
      "completion_length": 368.15625,
      "epoch": 0.05169687385962778,
      "grad_norm": 0.8565713178714169,
      "kl": 0.04052734375,
      "learning_rate": 9.934201879856634e-07,
      "loss": 0.0016,
      "reward": 2.0955491065979004,
      "reward_std": 0.029428184032440186,
      "rewards/accuracy_reward": 0.9111740589141846,
      "rewards/format_reward": 1.0,
      "step": 1700,
      "temperature": 1.0
    },
    {
      "all_correct": 0.25,
      "all_wrong": 0.5,
      "completion_length": 369.921875,
      "epoch": 0.05172728378542756,
      "grad_norm": 0.8591133475865472,
      "kl": 0.03662109375,
      "learning_rate": 9.934124618014925e-07,
      "loss": 0.0015,
      "reward": 1.446874976158142,
      "reward_std": 0.09722718596458435,
      "rewards/accuracy_reward": 0.375,
      "rewards/format_reward": 1.0,
      "step": 1701,
      "temperature": 1.0
    },
    {
      "all_correct": 0.75,
      "all_wrong": 0.0,
      "completion_length": 359.921875,
      "epoch": 0.05175769371122734,
      "grad_norm": 1.5590615335120794,
      "kl": 0.0400390625,
      "learning_rate": 9.93404731113921e-07,
      "loss": 0.0016,
      "reward": 2.0147361755371094,
      "reward_std": 0.038761723786592484,
      "rewards/accuracy_reward": 0.827235996723175,
      "rewards/format_reward": 1.0,
      "step": 1702,
      "temperature": 1.0
    },
    {
      "all_correct": 0.375,
      "all_wrong": 0.125,
      "completion_length": 364.390625,
      "epoch": 0.05178810363702713,
      "grad_norm": 0.9501324925560295,
      "kl": 0.042236328125,
      "learning_rate": 9.933969959230195e-07,
      "loss": 0.0017,
      "reward": 1.7727097272872925,
      "reward_std": 0.215582937002182,
      "rewards/accuracy_reward": 0.6477096080780029,
      "rewards/format_reward": 1.0,
      "step": 1703,
      "temperature": 1.0
    },
    {
      "all_correct": 0.625,
      "all_wrong": 0.0,
      "completion_length": 376.328125,
      "epoch": 0.05181851356282691,
      "grad_norm": 0.5988409479043928,
      "kl": 0.03857421875,
      "learning_rate": 9.933892562288584e-07,
      "loss": 0.0015,
      "reward": 1.9458026885986328,
      "reward_std": 0.1047879308462143,
      "rewards/accuracy_reward": 0.7833025455474854,
      "rewards/format_reward": 1.0,
      "step": 1704,
      "temperature": 1.0
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.0,
      "completion_length": 356.203125,
      "epoch": 0.051848923488626686,
      "grad_norm": 1.265448084548528,
      "kl": 0.037109375,
      "learning_rate": 9.933815120315087e-07,
      "loss": 0.0015,
      "reward": 1.775796890258789,
      "reward_std": 0.1951175034046173,
      "rewards/accuracy_reward": 0.6351718306541443,
      "rewards/format_reward": 1.0,
      "step": 1705,
      "temperature": 1.0
    },
    {
      "all_correct": 0.375,
      "all_wrong": 0.25,
      "completion_length": 346.34375,
      "epoch": 0.05187933341442647,
      "grad_norm": 1.0977140443811335,
      "kl": 0.04345703125,
      "learning_rate": 9.93373763331041e-07,
      "loss": 0.0017,
      "reward": 1.5187499523162842,
      "reward_std": 0.15782485902309418,
      "rewards/accuracy_reward": 0.4375,
      "rewards/format_reward": 1.0,
      "step": 1706,
      "temperature": 1.0
    },
    {
      "all_correct": 0.375,
      "all_wrong": 0.5,
      "completion_length": 390.578125,
      "epoch": 0.05190974334022625,
      "grad_norm": 0.4317568777250948,
      "kl": 0.03662109375,
      "learning_rate": 9.933660101275257e-07,
      "loss": 0.0015,
      "reward": 1.497149109840393,
      "reward_std": 0.00949166901409626,
      "rewards/accuracy_reward": 0.40339910984039307,
      "rewards/format_reward": 1.0,
      "step": 1707,
      "temperature": 1.0
    },
    {
      "all_correct": 0.25,
      "all_wrong": 0.0,
      "completion_length": 398.65625,
      "epoch": 0.05194015326602603,
      "grad_norm": 1.479935862634438,
      "kl": 0.039794921875,
      "learning_rate": 9.933582524210337e-07,
      "loss": 0.0016,
      "reward": 1.7873013019561768,
      "reward_std": 0.16633044183254242,
      "rewards/accuracy_reward": 0.6185513138771057,
      "rewards/format_reward": 1.0,
      "step": 1708,
      "temperature": 1.0
    },
    {
      "all_correct": 0.625,
      "all_wrong": 0.125,
      "completion_length": 374.828125,
      "epoch": 0.05197056319182581,
      "grad_norm": 0.8580855559527292,
      "kl": 0.040771484375,
      "learning_rate": 9.933504902116361e-07,
      "loss": 0.0016,
      "reward": 1.97991144657135,
      "reward_std": 0.044846419245004654,
      "rewards/accuracy_reward": 0.8049113750457764,
      "rewards/format_reward": 1.0,
      "step": 1709,
      "temperature": 1.0
    },
    {
      "all_correct": 0.625,
      "all_wrong": 0.125,
      "completion_length": 383.703125,
      "epoch": 0.052000973117625596,
      "grad_norm": 1.1836716505058824,
      "kl": 0.043212890625,
      "learning_rate": 9.933427234994034e-07,
      "loss": 0.0017,
      "reward": 1.8689963817596436,
      "reward_std": 0.08528483659029007,
      "rewards/accuracy_reward": 0.7221212387084961,
      "rewards/format_reward": 1.0,
      "step": 1710,
      "temperature": 1.0
    },
    {
      "all_correct": 0.375,
      "all_wrong": 0.0,
      "completion_length": 398.21875,
      "epoch": 0.052031383043425375,
      "grad_norm": 1.3660456902660463,
      "kl": 0.041748046875,
      "learning_rate": 9.933349522844066e-07,
      "loss": 0.0017,
      "reward": 1.752043604850769,
      "reward_std": 0.1173986941576004,
      "rewards/accuracy_reward": 0.5895435810089111,
      "rewards/format_reward": 1.0,
      "step": 1711,
      "temperature": 1.0
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.0,
      "completion_length": 365.984375,
      "epoch": 0.052061792969225154,
      "grad_norm": 1.9349183026458403,
      "kl": 0.0390625,
      "learning_rate": 9.933271765667167e-07,
      "loss": 0.0016,
      "reward": 1.799690842628479,
      "reward_std": 0.11679378896951675,
      "rewards/accuracy_reward": 0.643440842628479,
      "rewards/format_reward": 1.0,
      "step": 1712,
      "temperature": 1.0
    },
    {
      "all_correct": 0.375,
      "all_wrong": 0.125,
      "completion_length": 362.28125,
      "epoch": 0.05209220289502493,
      "grad_norm": 1.0192001306401566,
      "kl": 0.0400390625,
      "learning_rate": 9.933193963464046e-07,
      "loss": 0.0016,
      "reward": 1.844870686531067,
      "reward_std": 0.19211235642433167,
      "rewards/accuracy_reward": 0.6917456388473511,
      "rewards/format_reward": 1.0,
      "step": 1713,
      "temperature": 1.0
    },
    {
      "all_correct": 0.625,
      "all_wrong": 0.0,
      "completion_length": 383.21875,
      "epoch": 0.05212261282082472,
      "grad_norm": 0.9398283249237044,
      "kl": 0.040283203125,
      "learning_rate": 9.933116116235414e-07,
      "loss": 0.0016,
      "reward": 2.019998550415039,
      "reward_std": 0.06577799469232559,
      "rewards/accuracy_reward": 0.8293734192848206,
      "rewards/format_reward": 1.0,
      "step": 1714,
      "temperature": 1.0
    },
    {
      "all_correct": 0.75,
      "all_wrong": 0.0,
      "completion_length": 368.15625,
      "epoch": 0.0521530227466245,
      "grad_norm": 0.929083364351505,
      "kl": 0.04052734375,
      "learning_rate": 9.93303822398198e-07,
      "loss": 0.0016,
      "reward": 2.0230250358581543,
      "reward_std": 0.028195075690746307,
      "rewards/accuracy_reward": 0.8292750716209412,
      "rewards/format_reward": 1.0,
      "step": 1715,
      "temperature": 1.0
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.25,
      "completion_length": 396.75,
      "epoch": 0.05218343267242428,
      "grad_norm": 1.33212459144287,
      "kl": 0.04150390625,
      "learning_rate": 9.932960286704457e-07,
      "loss": 0.0017,
      "reward": 1.7906250953674316,
      "reward_std": 0.20484083890914917,
      "rewards/accuracy_reward": 0.703125,
      "rewards/format_reward": 0.953125,
      "step": 1716,
      "temperature": 1.0
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.0,
      "completion_length": 340.9375,
      "epoch": 0.05221384259822406,
      "grad_norm": 1.4571616004143157,
      "kl": 0.0478515625,
      "learning_rate": 9.932882304403554e-07,
      "loss": 0.0019,
      "reward": 1.9562500715255737,
      "reward_std": 0.17180021107196808,
      "rewards/accuracy_reward": 0.7874999642372131,
      "rewards/format_reward": 1.0,
      "step": 1717,
      "temperature": 1.0
    },
    {
      "all_correct": 0.625,
      "all_wrong": 0.0,
      "completion_length": 385.203125,
      "epoch": 0.05224425252402384,
      "grad_norm": 1.5984187397557628,
      "kl": 0.0380859375,
      "learning_rate": 9.932804277079983e-07,
      "loss": 0.0015,
      "reward": 1.8924496173858643,
      "reward_std": 0.16073644161224365,
      "rewards/accuracy_reward": 0.7486996650695801,
      "rewards/format_reward": 1.0,
      "step": 1718,
      "temperature": 1.0
    },
    {
      "all_correct": 0.875,
      "all_wrong": 0.125,
      "completion_length": 351.421875,
      "epoch": 0.05227466244982362,
      "grad_norm": 0.5998310364904058,
      "kl": 0.042724609375,
      "learning_rate": 9.932726204734458e-07,
      "loss": 0.0017,
      "reward": 2.046875,
      "reward_std": 0.008838837966322899,
      "rewards/accuracy_reward": 0.875,
      "rewards/format_reward": 1.0,
      "step": 1719,
      "temperature": 1.0
    },
    {
      "all_correct": 0.625,
      "all_wrong": 0.0,
      "completion_length": 359.890625,
      "epoch": 0.0523050723756234,
      "grad_norm": 1.777480766828006,
      "kl": 0.056396484375,
      "learning_rate": 9.93264808736769e-07,
      "loss": 0.0023,
      "reward": 2.00716495513916,
      "reward_std": 0.0291978120803833,
      "rewards/accuracy_reward": 0.8102896809577942,
      "rewards/format_reward": 1.0,
      "step": 1720,
      "temperature": 1.0
    },
    {
      "all_correct": 0.375,
      "all_wrong": 0.25,
      "completion_length": 377.984375,
      "epoch": 0.05233548230142319,
      "grad_norm": 1.0364725589308517,
      "kl": 0.040771484375,
      "learning_rate": 9.932569924980394e-07,
      "loss": 0.0016,
      "reward": 1.6118416786193848,
      "reward_std": 0.09988240897655487,
      "rewards/accuracy_reward": 0.4930917024612427,
      "rewards/format_reward": 1.0,
      "step": 1721,
      "temperature": 1.0
    },
    {
      "all_correct": 0.375,
      "all_wrong": 0.0,
      "completion_length": 393.9375,
      "epoch": 0.05236589222722297,
      "grad_norm": 3.5388999185689984,
      "kl": 0.04931640625,
      "learning_rate": 9.932491717573282e-07,
      "loss": 0.002,
      "reward": 1.7885299921035767,
      "reward_std": 0.06719963997602463,
      "rewards/accuracy_reward": 0.6041549444198608,
      "rewards/format_reward": 1.0,
      "step": 1722,
      "temperature": 1.0
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.25,
      "completion_length": 397.109375,
      "epoch": 0.052396302153022746,
      "grad_norm": 0.8395984169324521,
      "kl": 0.04052734375,
      "learning_rate": 9.932413465147065e-07,
      "loss": 0.0016,
      "reward": 1.7591776847839355,
      "reward_std": 0.07111681252717972,
      "rewards/accuracy_reward": 0.6310526728630066,
      "rewards/format_reward": 1.0,
      "step": 1723,
      "temperature": 1.0
    },
    {
      "all_correct": 0.25,
      "all_wrong": 0.375,
      "completion_length": 367.203125,
      "epoch": 0.052426712078822525,
      "grad_norm": 0.728277070326255,
      "kl": 0.045654296875,
      "learning_rate": 9.932335167702461e-07,
      "loss": 0.0018,
      "reward": 1.5781887769699097,
      "reward_std": 0.15444427728652954,
      "rewards/accuracy_reward": 0.4688137471675873,
      "rewards/format_reward": 1.0,
      "step": 1724,
      "temperature": 1.0
    },
    {
      "all_correct": 0.625,
      "all_wrong": 0.0,
      "completion_length": 377.8125,
      "epoch": 0.05245712200462231,
      "grad_norm": 0.81287027871598,
      "kl": 0.040283203125,
      "learning_rate": 9.932256825240185e-07,
      "loss": 0.0016,
      "reward": 1.8304009437561035,
      "reward_std": 0.059511780738830566,
      "rewards/accuracy_reward": 0.6866510510444641,
      "rewards/format_reward": 1.0,
      "step": 1725,
      "temperature": 1.0
    },
    {
      "all_correct": 0.625,
      "all_wrong": 0.125,
      "completion_length": 363.75,
      "epoch": 0.05248753193042209,
      "grad_norm": 0.7594044705066947,
      "kl": 0.045654296875,
      "learning_rate": 9.93217843776095e-07,
      "loss": 0.0018,
      "reward": 1.8916666507720947,
      "reward_std": 0.0824957937002182,
      "rewards/accuracy_reward": 0.7447916865348816,
      "rewards/format_reward": 1.0,
      "step": 1726,
      "temperature": 1.0
    },
    {
      "all_correct": 0.375,
      "all_wrong": 0.125,
      "completion_length": 362.140625,
      "epoch": 0.05251794185622187,
      "grad_norm": 1.1798908039225517,
      "kl": 0.04345703125,
      "learning_rate": 9.932100005265472e-07,
      "loss": 0.0017,
      "reward": 1.8173259496688843,
      "reward_std": 0.09162682294845581,
      "rewards/accuracy_reward": 0.6517008543014526,
      "rewards/format_reward": 1.0,
      "step": 1727,
      "temperature": 1.0
    },
    {
      "all_correct": 0.75,
      "all_wrong": 0.125,
      "completion_length": 364.515625,
      "epoch": 0.05254835178202165,
      "grad_norm": 0.8548169847406715,
      "kl": 0.04736328125,
      "learning_rate": 9.932021527754466e-07,
      "loss": 0.0019,
      "reward": 1.9537043571472168,
      "reward_std": 0.010699999518692493,
      "rewards/accuracy_reward": 0.781829297542572,
      "rewards/format_reward": 1.0,
      "step": 1728,
      "temperature": 1.0
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.375,
      "completion_length": 371.15625,
      "epoch": 0.052578761707821435,
      "grad_norm": 0.6180866662946092,
      "kl": 0.051025390625,
      "learning_rate": 9.93194300522865e-07,
      "loss": 0.002,
      "reward": 1.6797244548797607,
      "reward_std": 0.019820820540189743,
      "rewards/accuracy_reward": 0.5609744191169739,
      "rewards/format_reward": 1.0,
      "step": 1729,
      "temperature": 1.0
    },
    {
      "all_correct": 0.75,
      "all_wrong": 0.0,
      "completion_length": 374.078125,
      "epoch": 0.052609171633621214,
      "grad_norm": 0.6542545233984774,
      "kl": 0.04736328125,
      "learning_rate": 9.931864437688738e-07,
      "loss": 0.0019,
      "reward": 1.9587702751159668,
      "reward_std": 0.05685633420944214,
      "rewards/accuracy_reward": 0.7868952751159668,
      "rewards/format_reward": 1.0,
      "step": 1730,
      "temperature": 1.0
    },
    {
      "all_correct": 0.375,
      "all_wrong": 0.125,
      "completion_length": 382.140625,
      "epoch": 0.05263958155942099,
      "grad_norm": 1.4650487754531858,
      "kl": 0.044189453125,
      "learning_rate": 9.93178582513545e-07,
      "loss": 0.0018,
      "reward": 1.7392561435699463,
      "reward_std": 0.11198993027210236,
      "rewards/accuracy_reward": 0.5861310958862305,
      "rewards/format_reward": 1.0,
      "step": 1731,
      "temperature": 1.0
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.125,
      "completion_length": 370.34375,
      "epoch": 0.05266999148522077,
      "grad_norm": 1.058491516946553,
      "kl": 0.047607421875,
      "learning_rate": 9.931707167569503e-07,
      "loss": 0.0019,
      "reward": 1.8322917222976685,
      "reward_std": 0.16913866996765137,
      "rewards/accuracy_reward": 0.6822916269302368,
      "rewards/format_reward": 1.0,
      "step": 1732,
      "temperature": 1.0
    },
    {
      "all_correct": 0.625,
      "all_wrong": 0.0,
      "completion_length": 357.015625,
      "epoch": 0.05270040141102056,
      "grad_norm": 3.739528004352349,
      "kl": 0.04345703125,
      "learning_rate": 9.931628464991616e-07,
      "loss": 0.0017,
      "reward": 1.9121160507202148,
      "reward_std": 0.028857268393039703,
      "rewards/accuracy_reward": 0.7246160507202148,
      "rewards/format_reward": 1.0,
      "step": 1733,
      "temperature": 1.0
    },
    {
      "all_correct": 0.25,
      "all_wrong": 0.25,
      "completion_length": 398.828125,
      "epoch": 0.05273081133682034,
      "grad_norm": 1.1230772315853261,
      "kl": 0.043212890625,
      "learning_rate": 9.931549717402504e-07,
      "loss": 0.0017,
      "reward": 1.6522834300994873,
      "reward_std": 0.15697012841701508,
      "rewards/accuracy_reward": 0.5179083347320557,
      "rewards/format_reward": 1.0,
      "step": 1734,
      "temperature": 1.0
    },
    {
      "all_correct": 0.625,
      "all_wrong": 0.125,
      "completion_length": 399.8125,
      "epoch": 0.05276122126262012,
      "grad_norm": 0.7357951914998079,
      "kl": 0.03271484375,
      "learning_rate": 9.931470924802887e-07,
      "loss": 0.0013,
      "reward": 1.8989508152008057,
      "reward_std": 0.09077323228120804,
      "rewards/accuracy_reward": 0.7364507913589478,
      "rewards/format_reward": 1.0,
      "step": 1735,
      "temperature": 1.0
    },
    {
      "all_correct": 0.625,
      "all_wrong": 0.25,
      "completion_length": 354.890625,
      "epoch": 0.0527916311884199,
      "grad_norm": 0.5080282171341534,
      "kl": 0.037841796875,
      "learning_rate": 9.931392087193484e-07,
      "loss": 0.0015,
      "reward": 1.8555550575256348,
      "reward_std": 0.025247374549508095,
      "rewards/accuracy_reward": 0.7055552005767822,
      "rewards/format_reward": 1.0,
      "step": 1736,
      "temperature": 1.0
    },
    {
      "all_correct": 0.625,
      "all_wrong": 0.25,
      "completion_length": 357.140625,
      "epoch": 0.05282204111421968,
      "grad_norm": 0.3716966480196633,
      "kl": 0.03515625,
      "learning_rate": 9.931313204575015e-07,
      "loss": 0.0014,
      "reward": 1.881250023841858,
      "reward_std": 0.0530330091714859,
      "rewards/accuracy_reward": 0.734375,
      "rewards/format_reward": 1.0,
      "step": 1737,
      "temperature": 1.0
    },
    {
      "all_correct": 0.625,
      "all_wrong": 0.0,
      "completion_length": 393.71875,
      "epoch": 0.05285245104001946,
      "grad_norm": 2.6006393805487193,
      "kl": 0.034423828125,
      "learning_rate": 9.9312342769482e-07,
      "loss": 0.0014,
      "reward": 1.902111291885376,
      "reward_std": 0.1417084038257599,
      "rewards/accuracy_reward": 0.7396112680435181,
      "rewards/format_reward": 1.0,
      "step": 1738,
      "temperature": 1.0
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.125,
      "completion_length": 411.484375,
      "epoch": 0.05288286096581924,
      "grad_norm": 0.6575456730527551,
      "kl": 0.0303955078125,
      "learning_rate": 9.931155304313762e-07,
      "loss": 0.0012,
      "reward": 1.7260732650756836,
      "reward_std": 0.22020688652992249,
      "rewards/accuracy_reward": 0.638573169708252,
      "rewards/format_reward": 0.96875,
      "step": 1739,
      "temperature": 1.0
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.125,
      "completion_length": 389.78125,
      "epoch": 0.05291327089161903,
      "grad_norm": 1.1017322765261257,
      "kl": 0.037841796875,
      "learning_rate": 9.931076286672417e-07,
      "loss": 0.0015,
      "reward": 1.7297368049621582,
      "reward_std": 0.01664542779326439,
      "rewards/accuracy_reward": 0.5734866857528687,
      "rewards/format_reward": 1.0,
      "step": 1740,
      "temperature": 1.0
    },
    {
      "all_correct": 0.625,
      "all_wrong": 0.25,
      "completion_length": 376.078125,
      "epoch": 0.052943680817418806,
      "grad_norm": 0.9491881887325085,
      "kl": 0.026611328125,
      "learning_rate": 9.930997224024888e-07,
      "loss": 0.0011,
      "reward": 1.8082174062728882,
      "reward_std": 0.011353096924722195,
      "rewards/accuracy_reward": 0.6613423228263855,
      "rewards/format_reward": 1.0,
      "step": 1741,
      "temperature": 1.0
    },
    {
      "all_correct": 0.375,
      "all_wrong": 0.125,
      "completion_length": 358.078125,
      "epoch": 0.052974090743218585,
      "grad_norm": 0.8417268891664833,
      "kl": 0.036865234375,
      "learning_rate": 9.9309181163719e-07,
      "loss": 0.0015,
      "reward": 1.6787805557250977,
      "reward_std": 0.19126306474208832,
      "rewards/accuracy_reward": 0.5631555914878845,
      "rewards/format_reward": 1.0,
      "step": 1742,
      "temperature": 1.0
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.125,
      "completion_length": 380.546875,
      "epoch": 0.053004500669018365,
      "grad_norm": 1.7648883421342274,
      "kl": 0.037841796875,
      "learning_rate": 9.93083896371417e-07,
      "loss": 0.0015,
      "reward": 1.7168731689453125,
      "reward_std": 0.104706771671772,
      "rewards/accuracy_reward": 0.576248049736023,
      "rewards/format_reward": 1.0,
      "step": 1743,
      "temperature": 1.0
    },
    {
      "all_correct": 0.75,
      "all_wrong": 0.125,
      "completion_length": 393.578125,
      "epoch": 0.05303491059481815,
      "grad_norm": 0.9970850148866124,
      "kl": 0.0284423828125,
      "learning_rate": 9.93075976605242e-07,
      "loss": 0.0011,
      "reward": 1.9124999046325684,
      "reward_std": 0.0530330091714859,
      "rewards/accuracy_reward": 0.765625,
      "rewards/format_reward": 1.0,
      "step": 1744,
      "temperature": 1.0
    },
    {
      "all_correct": 0.25,
      "all_wrong": 0.125,
      "completion_length": 374.96875,
      "epoch": 0.05306532052061793,
      "grad_norm": 2.140672869454024,
      "kl": 0.033203125,
      "learning_rate": 9.93068052338738e-07,
      "loss": 0.0013,
      "reward": 1.739622712135315,
      "reward_std": 0.1683429777622223,
      "rewards/accuracy_reward": 0.5864977240562439,
      "rewards/format_reward": 1.0,
      "step": 1745,
      "temperature": 1.0
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.375,
      "completion_length": 347.609375,
      "epoch": 0.05309573044641771,
      "grad_norm": 0.4239443399894489,
      "kl": 0.0361328125,
      "learning_rate": 9.930601235719765e-07,
      "loss": 0.0014,
      "reward": 1.65625,
      "reward_std": 0.077632375061512,
      "rewards/accuracy_reward": 0.546875,
      "rewards/format_reward": 1.0,
      "step": 1746,
      "temperature": 1.0
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.125,
      "completion_length": 417.78125,
      "epoch": 0.053126140372217495,
      "grad_norm": 0.8991270107431673,
      "kl": 0.0264892578125,
      "learning_rate": 9.930521903050304e-07,
      "loss": 0.0011,
      "reward": 1.7762322425842285,
      "reward_std": 0.08783479034900665,
      "rewards/accuracy_reward": 0.6231071949005127,
      "rewards/format_reward": 1.0,
      "step": 1747,
      "temperature": 1.0
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.125,
      "completion_length": 400.71875,
      "epoch": 0.053156550298017274,
      "grad_norm": 1.016355773539133,
      "kl": 0.03515625,
      "learning_rate": 9.930442525379719e-07,
      "loss": 0.0014,
      "reward": 1.7676626443862915,
      "reward_std": 0.17786872386932373,
      "rewards/accuracy_reward": 0.6426626443862915,
      "rewards/format_reward": 1.0,
      "step": 1748,
      "temperature": 1.0
    },
    {
      "all_correct": 0.875,
      "all_wrong": 0.125,
      "completion_length": 365.765625,
      "epoch": 0.053186960223817054,
      "grad_norm": 0.5349088688643145,
      "kl": 0.03466796875,
      "learning_rate": 9.930363102708734e-07,
      "loss": 0.0014,
      "reward": 2.046875,
      "reward_std": 0.008838837966322899,
      "rewards/accuracy_reward": 0.875,
      "rewards/format_reward": 1.0,
      "step": 1749,
      "temperature": 1.0
    },
    {
      "all_correct": 0.875,
      "all_wrong": 0.0,
      "completion_length": 354.484375,
      "epoch": 0.05321737014961683,
      "grad_norm": 1.1797717237448997,
      "kl": 0.0322265625,
      "learning_rate": 9.930283635038077e-07,
      "loss": 0.0013,
      "reward": 2.163480043411255,
      "reward_std": 0.04172266274690628,
      "rewards/accuracy_reward": 0.9759801030158997,
      "rewards/format_reward": 1.0,
      "step": 1750,
      "temperature": 1.0
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.125,
      "completion_length": 370.171875,
      "epoch": 0.05324778007541662,
      "grad_norm": 0.7196814619998144,
      "kl": 0.032958984375,
      "learning_rate": 9.93020412236847e-07,
      "loss": 0.0013,
      "reward": 1.7657501697540283,
      "reward_std": 0.1526947170495987,
      "rewards/accuracy_reward": 0.6345000267028809,
      "rewards/format_reward": 1.0,
      "step": 1751,
      "temperature": 1.0
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.125,
      "completion_length": 396.078125,
      "epoch": 0.0532781900012164,
      "grad_norm": 1.865299134301001,
      "kl": 0.03369140625,
      "learning_rate": 9.930124564700636e-07,
      "loss": 0.0014,
      "reward": 1.6824376583099365,
      "reward_std": 0.09923285245895386,
      "rewards/accuracy_reward": 0.5574377179145813,
      "rewards/format_reward": 1.0,
      "step": 1752,
      "temperature": 1.0
    },
    {
      "all_correct": 0.75,
      "all_wrong": 0.125,
      "completion_length": 357.234375,
      "epoch": 0.05330859992701618,
      "grad_norm": 0.5525320267292863,
      "kl": 0.036865234375,
      "learning_rate": 9.930044962035309e-07,
      "loss": 0.0015,
      "reward": 2.03125,
      "reward_std": 0.0530330091714859,
      "rewards/accuracy_reward": 0.859375,
      "rewards/format_reward": 1.0,
      "step": 1753,
      "temperature": 1.0
    },
    {
      "all_correct": 0.375,
      "all_wrong": 0.125,
      "completion_length": 392.734375,
      "epoch": 0.053339009852815956,
      "grad_norm": 1.5410236252655487,
      "kl": 0.03955078125,
      "learning_rate": 9.92996531437321e-07,
      "loss": 0.0016,
      "reward": 1.6641496419906616,
      "reward_std": 0.03943108394742012,
      "rewards/accuracy_reward": 0.5047745704650879,
      "rewards/format_reward": 1.0,
      "step": 1754,
      "temperature": 1.0
    },
    {
      "all_correct": 0.75,
      "all_wrong": 0.0,
      "completion_length": 348.640625,
      "epoch": 0.05336941977861574,
      "grad_norm": 0.8023339347746173,
      "kl": 0.0361328125,
      "learning_rate": 9.929885621715069e-07,
      "loss": 0.0015,
      "reward": 2.085416793823242,
      "reward_std": 0.10849304497241974,
      "rewards/accuracy_reward": 0.8947916626930237,
      "rewards/format_reward": 1.0,
      "step": 1755,
      "temperature": 1.0
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.125,
      "completion_length": 384.78125,
      "epoch": 0.05339982970441552,
      "grad_norm": 2.8337067074041045,
      "kl": 0.038330078125,
      "learning_rate": 9.929805884061611e-07,
      "loss": 0.0015,
      "reward": 1.8345284461975098,
      "reward_std": 0.0697808712720871,
      "rewards/accuracy_reward": 0.675153374671936,
      "rewards/format_reward": 1.0,
      "step": 1756,
      "temperature": 1.0
    },
    {
      "all_correct": 0.375,
      "all_wrong": 0.25,
      "completion_length": 362.265625,
      "epoch": 0.0534302396302153,
      "grad_norm": 0.8957468575906574,
      "kl": 0.036376953125,
      "learning_rate": 9.929726101413563e-07,
      "loss": 0.0015,
      "reward": 1.7416856288909912,
      "reward_std": 0.10728268325328827,
      "rewards/accuracy_reward": 0.6041855812072754,
      "rewards/format_reward": 1.0,
      "step": 1757,
      "temperature": 1.0
    },
    {
      "all_correct": 0.875,
      "all_wrong": 0.0,
      "completion_length": 364.59375,
      "epoch": 0.05346064955601508,
      "grad_norm": 0.5772351467096913,
      "kl": 0.040283203125,
      "learning_rate": 9.929646273771655e-07,
      "loss": 0.0016,
      "reward": 2.1126341819763184,
      "reward_std": 0.0031856982968747616,
      "rewards/accuracy_reward": 0.9126341342926025,
      "rewards/format_reward": 1.0,
      "step": 1758,
      "temperature": 1.0
    },
    {
      "all_correct": 0.375,
      "all_wrong": 0.125,
      "completion_length": 384.203125,
      "epoch": 0.053491059481814866,
      "grad_norm": 1.0483151816965295,
      "kl": 0.034423828125,
      "learning_rate": 9.929566401136616e-07,
      "loss": 0.0014,
      "reward": 1.7578452825546265,
      "reward_std": 0.10913911461830139,
      "rewards/accuracy_reward": 0.6109702587127686,
      "rewards/format_reward": 1.0,
      "step": 1759,
      "temperature": 1.0
    },
    {
      "all_correct": 0.25,
      "all_wrong": 0.25,
      "completion_length": 365.8125,
      "epoch": 0.053521469407614645,
      "grad_norm": 1.0780376133259406,
      "kl": 0.04638671875,
      "learning_rate": 9.929486483509172e-07,
      "loss": 0.0019,
      "reward": 1.592857837677002,
      "reward_std": 0.12637543678283691,
      "rewards/accuracy_reward": 0.47098276019096375,
      "rewards/format_reward": 1.0,
      "step": 1760,
      "temperature": 1.0
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.25,
      "completion_length": 363.703125,
      "epoch": 0.053551879333414425,
      "grad_norm": 1.1411611807689201,
      "kl": 0.03955078125,
      "learning_rate": 9.929406520890057e-07,
      "loss": 0.0016,
      "reward": 1.7194530963897705,
      "reward_std": 0.09455876052379608,
      "rewards/accuracy_reward": 0.5850780010223389,
      "rewards/format_reward": 1.0,
      "step": 1761,
      "temperature": 1.0
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.25,
      "completion_length": 376.59375,
      "epoch": 0.05358228925921421,
      "grad_norm": 1.0990709893710588,
      "kl": 0.03857421875,
      "learning_rate": 9.929326513279998e-07,
      "loss": 0.0015,
      "reward": 1.7798888683319092,
      "reward_std": 0.030979227274656296,
      "rewards/accuracy_reward": 0.6392639875411987,
      "rewards/format_reward": 1.0,
      "step": 1762,
      "temperature": 1.0
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.125,
      "completion_length": 370.375,
      "epoch": 0.05361269918501399,
      "grad_norm": 1.5619074600195828,
      "kl": 0.0458984375,
      "learning_rate": 9.929246460679726e-07,
      "loss": 0.0018,
      "reward": 1.8410710096359253,
      "reward_std": 0.13639596104621887,
      "rewards/accuracy_reward": 0.7004460096359253,
      "rewards/format_reward": 1.0,
      "step": 1763,
      "temperature": 1.0
    },
    {
      "all_correct": 0.375,
      "all_wrong": 0.25,
      "completion_length": 369.890625,
      "epoch": 0.05364310911081377,
      "grad_norm": 1.267018239322046,
      "kl": 0.04931640625,
      "learning_rate": 9.92916636308997e-07,
      "loss": 0.002,
      "reward": 1.548771858215332,
      "reward_std": 0.10878238081932068,
      "rewards/accuracy_reward": 0.4550217390060425,
      "rewards/format_reward": 1.0,
      "step": 1764,
      "temperature": 1.0
    },
    {
      "all_correct": 0.375,
      "all_wrong": 0.25,
      "completion_length": 357.5625,
      "epoch": 0.05367351903661355,
      "grad_norm": 1.10040002668136,
      "kl": 0.04052734375,
      "learning_rate": 9.929086220511464e-07,
      "loss": 0.0016,
      "reward": 1.6640499830245972,
      "reward_std": 0.04192690551280975,
      "rewards/accuracy_reward": 0.5140500068664551,
      "rewards/format_reward": 1.0,
      "step": 1765,
      "temperature": 1.0
    },
    {
      "all_correct": 0.25,
      "all_wrong": 0.125,
      "completion_length": 393.9375,
      "epoch": 0.053703928962413335,
      "grad_norm": 1.258009812354391,
      "kl": 0.039306640625,
      "learning_rate": 9.929006032944937e-07,
      "loss": 0.0016,
      "reward": 1.750711441040039,
      "reward_std": 0.19465500116348267,
      "rewards/accuracy_reward": 0.6069614291191101,
      "rewards/format_reward": 1.0,
      "step": 1766,
      "temperature": 1.0
    },
    {
      "all_correct": 0.75,
      "all_wrong": 0.0,
      "completion_length": 358.140625,
      "epoch": 0.053734338888213114,
      "grad_norm": 0.979811231693195,
      "kl": 0.032958984375,
      "learning_rate": 9.928925800391122e-07,
      "loss": 0.0013,
      "reward": 1.9893229007720947,
      "reward_std": 0.1280553936958313,
      "rewards/accuracy_reward": 0.8268229365348816,
      "rewards/format_reward": 1.0,
      "step": 1767,
      "temperature": 1.0
    },
    {
      "all_correct": 0.75,
      "all_wrong": 0.125,
      "completion_length": 368.734375,
      "epoch": 0.05376474881401289,
      "grad_norm": 1.245326969352413,
      "kl": 0.03857421875,
      "learning_rate": 9.92884552285075e-07,
      "loss": 0.0015,
      "reward": 1.9602339267730713,
      "reward_std": 0.020391281694173813,
      "rewards/accuracy_reward": 0.7977339029312134,
      "rewards/format_reward": 1.0,
      "step": 1768,
      "temperature": 1.0
    },
    {
      "all_correct": 0.125,
      "all_wrong": 0.5,
      "completion_length": 355.5,
      "epoch": 0.05379515873981267,
      "grad_norm": 1.4377474901201928,
      "kl": 0.046875,
      "learning_rate": 9.928765200324556e-07,
      "loss": 0.0019,
      "reward": 1.336641550064087,
      "reward_std": 0.12639351189136505,
      "rewards/accuracy_reward": 0.2585165798664093,
      "rewards/format_reward": 1.0,
      "step": 1769,
      "temperature": 1.0
    },
    {
      "all_correct": 0.125,
      "all_wrong": 0.5,
      "completion_length": 379.125,
      "epoch": 0.05382556866561246,
      "grad_norm": 1.131896108581665,
      "kl": 0.041259765625,
      "learning_rate": 9.928684832813271e-07,
      "loss": 0.0016,
      "reward": 1.3194055557250977,
      "reward_std": 0.12246951460838318,
      "rewards/accuracy_reward": 0.2662805914878845,
      "rewards/format_reward": 1.0,
      "step": 1770,
      "temperature": 1.0
    },
    {
      "all_correct": 0.375,
      "all_wrong": 0.125,
      "completion_length": 393.765625,
      "epoch": 0.05385597859141224,
      "grad_norm": 1.3392822171928767,
      "kl": 0.037841796875,
      "learning_rate": 9.92860442031763e-07,
      "loss": 0.0015,
      "reward": 1.6653803586959839,
      "reward_std": 0.09766694158315659,
      "rewards/accuracy_reward": 0.5153802633285522,
      "rewards/format_reward": 1.0,
      "step": 1771,
      "temperature": 1.0
    },
    {
      "all_correct": 0.625,
      "all_wrong": 0.0,
      "completion_length": 386.703125,
      "epoch": 0.05388638851721202,
      "grad_norm": 0.9429016451987904,
      "kl": 0.0361328125,
      "learning_rate": 9.928523962838367e-07,
      "loss": 0.0014,
      "reward": 1.9241161346435547,
      "reward_std": 0.0734207034111023,
      "rewards/accuracy_reward": 0.7584910988807678,
      "rewards/format_reward": 1.0,
      "step": 1772,
      "temperature": 1.0
    },
    {
      "all_correct": 0.25,
      "all_wrong": 0.5,
      "completion_length": 377.84375,
      "epoch": 0.053916798443011796,
      "grad_norm": 0.6449840137534874,
      "kl": 0.043701171875,
      "learning_rate": 9.928443460376214e-07,
      "loss": 0.0018,
      "reward": 1.4719064235687256,
      "reward_std": 0.02093832567334175,
      "rewards/accuracy_reward": 0.39378130435943604,
      "rewards/format_reward": 1.0,
      "step": 1773,
      "temperature": 1.0
    },
    {
      "all_correct": 0.375,
      "all_wrong": 0.25,
      "completion_length": 359.5,
      "epoch": 0.05394720836881158,
      "grad_norm": 0.8619882894784859,
      "kl": 0.03515625,
      "learning_rate": 9.928362912931908e-07,
      "loss": 0.0014,
      "reward": 1.666562557220459,
      "reward_std": 0.1892632246017456,
      "rewards/accuracy_reward": 0.5478125214576721,
      "rewards/format_reward": 1.0,
      "step": 1774,
      "temperature": 1.0
    },
    {
      "all_correct": 0.375,
      "all_wrong": 0.25,
      "completion_length": 363.609375,
      "epoch": 0.05397761829461136,
      "grad_norm": 0.7894507492899807,
      "kl": 0.032470703125,
      "learning_rate": 9.928282320506184e-07,
      "loss": 0.0013,
      "reward": 1.5625,
      "reward_std": 0.20830951631069183,
      "rewards/accuracy_reward": 0.46875,
      "rewards/format_reward": 1.0,
      "step": 1775,
      "temperature": 1.0
    },
    {
      "all_correct": 0.75,
      "all_wrong": 0.0,
      "completion_length": 360.0,
      "epoch": 0.05400802822041114,
      "grad_norm": 0.6439435545284175,
      "kl": 0.04638671875,
      "learning_rate": 9.928201683099776e-07,
      "loss": 0.0019,
      "reward": 2.0901756286621094,
      "reward_std": 0.08176927268505096,
      "rewards/accuracy_reward": 0.8995506763458252,
      "rewards/format_reward": 1.0,
      "step": 1776,
      "temperature": 1.0
    },
    {
      "all_correct": 0.625,
      "all_wrong": 0.0,
      "completion_length": 375.0625,
      "epoch": 0.054038438146210926,
      "grad_norm": 1.0162005352654053,
      "kl": 0.038330078125,
      "learning_rate": 9.92812100071342e-07,
      "loss": 0.0015,
      "reward": 1.9773123264312744,
      "reward_std": 0.1322588324546814,
      "rewards/accuracy_reward": 0.8085622191429138,
      "rewards/format_reward": 1.0,
      "step": 1777,
      "temperature": 1.0
    },
    {
      "all_correct": 0.625,
      "all_wrong": 0.0,
      "completion_length": 378.78125,
      "epoch": 0.054068848072010706,
      "grad_norm": 1.018356078030503,
      "kl": 0.03369140625,
      "learning_rate": 9.928040273347857e-07,
      "loss": 0.0013,
      "reward": 2.0540552139282227,
      "reward_std": 0.07261952757835388,
      "rewards/accuracy_reward": 0.8603051900863647,
      "rewards/format_reward": 1.0,
      "step": 1778,
      "temperature": 1.0
    },
    {
      "all_correct": 0.625,
      "all_wrong": 0.125,
      "completion_length": 372.765625,
      "epoch": 0.054099257997810485,
      "grad_norm": 10.306130800978577,
      "kl": 0.0498046875,
      "learning_rate": 9.927959501003818e-07,
      "loss": 0.002,
      "reward": 1.8654594421386719,
      "reward_std": 0.024972496554255486,
      "rewards/accuracy_reward": 0.6967092752456665,
      "rewards/format_reward": 1.0,
      "step": 1779,
      "temperature": 1.0
    },
    {
      "all_correct": 0.625,
      "all_wrong": 0.25,
      "completion_length": 370.5,
      "epoch": 0.054129667923610264,
      "grad_norm": 0.5380322217986514,
      "kl": 0.033447265625,
      "learning_rate": 9.927878683682042e-07,
      "loss": 0.0013,
      "reward": 1.8211686611175537,
      "reward_std": 0.014143557287752628,
      "rewards/accuracy_reward": 0.6742936372756958,
      "rewards/format_reward": 1.0,
      "step": 1780,
      "temperature": 1.0
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.125,
      "completion_length": 415.828125,
      "epoch": 0.05416007784941005,
      "grad_norm": 0.8417510469660456,
      "kl": 0.03271484375,
      "learning_rate": 9.927797821383268e-07,
      "loss": 0.0013,
      "reward": 1.7898240089416504,
      "reward_std": 0.1088612824678421,
      "rewards/accuracy_reward": 0.6585740447044373,
      "rewards/format_reward": 1.0,
      "step": 1781,
      "temperature": 1.0
    },
    {
      "all_correct": 0.625,
      "all_wrong": 0.0,
      "completion_length": 369.21875,
      "epoch": 0.05419048777520983,
      "grad_norm": 2.5172960805917612,
      "kl": 0.041015625,
      "learning_rate": 9.927716914108234e-07,
      "loss": 0.0016,
      "reward": 1.954413652420044,
      "reward_std": 0.17351588606834412,
      "rewards/accuracy_reward": 0.782538652420044,
      "rewards/format_reward": 1.0,
      "step": 1782,
      "temperature": 1.0
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.125,
      "completion_length": 343.0625,
      "epoch": 0.05422089770100961,
      "grad_norm": 1.786912565328946,
      "kl": 0.04345703125,
      "learning_rate": 9.927635961857676e-07,
      "loss": 0.0017,
      "reward": 1.84542977809906,
      "reward_std": 0.13848485052585602,
      "rewards/accuracy_reward": 0.7110546827316284,
      "rewards/format_reward": 0.984375,
      "step": 1783,
      "temperature": 1.0
    },
    {
      "all_correct": 0.625,
      "all_wrong": 0.0,
      "completion_length": 360.34375,
      "epoch": 0.05425130762680939,
      "grad_norm": 1.0705404911157932,
      "kl": 0.031982421875,
      "learning_rate": 9.927554964632336e-07,
      "loss": 0.0013,
      "reward": 1.9792534112930298,
      "reward_std": 0.14146408438682556,
      "rewards/accuracy_reward": 0.8042534589767456,
      "rewards/format_reward": 1.0,
      "step": 1784,
      "temperature": 1.0
    },
    {
      "all_correct": 0.625,
      "all_wrong": 0.125,
      "completion_length": 375.1875,
      "epoch": 0.054281717552609174,
      "grad_norm": 0.8772968620722489,
      "kl": 0.035400390625,
      "learning_rate": 9.92747392243295e-07,
      "loss": 0.0014,
      "reward": 1.7880208492279053,
      "reward_std": 0.15328487753868103,
      "rewards/accuracy_reward": 0.6661458015441895,
      "rewards/format_reward": 1.0,
      "step": 1785,
      "temperature": 1.0
    },
    {
      "all_correct": 0.75,
      "all_wrong": 0.125,
      "completion_length": 360.0,
      "epoch": 0.05431212747840895,
      "grad_norm": 0.26052674188374403,
      "kl": 0.032958984375,
      "learning_rate": 9.92739283526026e-07,
      "loss": 0.0013,
      "reward": 1.9937500953674316,
      "reward_std": 0.077632375061512,
      "rewards/accuracy_reward": 0.828125,
      "rewards/format_reward": 1.0,
      "step": 1786,
      "temperature": 1.0
    },
    {
      "all_correct": 0.375,
      "all_wrong": 0.25,
      "completion_length": 379.234375,
      "epoch": 0.05434253740420873,
      "grad_norm": 2.4959708676620846,
      "kl": 0.04345703125,
      "learning_rate": 9.927311703115006e-07,
      "loss": 0.0017,
      "reward": 1.6713738441467285,
      "reward_std": 0.024273546412587166,
      "rewards/accuracy_reward": 0.5276238918304443,
      "rewards/format_reward": 1.0,
      "step": 1787,
      "temperature": 1.0
    },
    {
      "all_correct": 0.375,
      "all_wrong": 0.375,
      "completion_length": 381.65625,
      "epoch": 0.05437294733000851,
      "grad_norm": 1.3009136153894694,
      "kl": 0.03369140625,
      "learning_rate": 9.927230525997927e-07,
      "loss": 0.0013,
      "reward": 1.5975360870361328,
      "reward_std": 0.07986532151699066,
      "rewards/accuracy_reward": 0.5037860870361328,
      "rewards/format_reward": 1.0,
      "step": 1788,
      "temperature": 1.0
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.125,
      "completion_length": 375.25,
      "epoch": 0.0544033572558083,
      "grad_norm": 0.9331215541727185,
      "kl": 0.04052734375,
      "learning_rate": 9.927149303909766e-07,
      "loss": 0.0016,
      "reward": 1.784458041191101,
      "reward_std": 0.1636240929365158,
      "rewards/accuracy_reward": 0.650083065032959,
      "rewards/format_reward": 1.0,
      "step": 1789,
      "temperature": 1.0
    },
    {
      "all_correct": 0.375,
      "all_wrong": 0.125,
      "completion_length": 359.828125,
      "epoch": 0.05443376718160808,
      "grad_norm": 1.3705318478471595,
      "kl": 0.039306640625,
      "learning_rate": 9.927068036851262e-07,
      "loss": 0.0016,
      "reward": 1.7698920965194702,
      "reward_std": 0.20690850913524628,
      "rewards/accuracy_reward": 0.6292670369148254,
      "rewards/format_reward": 1.0,
      "step": 1790,
      "temperature": 1.0
    },
    {
      "all_correct": 0.375,
      "all_wrong": 0.125,
      "completion_length": 376.1875,
      "epoch": 0.054464177107407856,
      "grad_norm": 1.4125366598956606,
      "kl": 0.041259765625,
      "learning_rate": 9.92698672482316e-07,
      "loss": 0.0017,
      "reward": 1.678125023841858,
      "reward_std": 0.24642017483711243,
      "rewards/accuracy_reward": 0.578125,
      "rewards/format_reward": 1.0,
      "step": 1791,
      "temperature": 1.0
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.125,
      "completion_length": 361.390625,
      "epoch": 0.05449458703320764,
      "grad_norm": 2.480509526962815,
      "kl": 0.03955078125,
      "learning_rate": 9.9269053678262e-07,
      "loss": 0.0016,
      "reward": 1.7759034633636475,
      "reward_std": 0.08361143618822098,
      "rewards/accuracy_reward": 0.6352784037590027,
      "rewards/format_reward": 1.0,
      "step": 1792,
      "temperature": 1.0
    },
    {
      "all_correct": 0.375,
      "all_wrong": 0.0,
      "completion_length": 356.890625,
      "epoch": 0.05452499695900742,
      "grad_norm": 1.5671263197704786,
      "kl": 0.049560546875,
      "learning_rate": 9.926823965861122e-07,
      "loss": 0.002,
      "reward": 1.751999020576477,
      "reward_std": 0.17759668827056885,
      "rewards/accuracy_reward": 0.5894989371299744,
      "rewards/format_reward": 1.0,
      "step": 1793,
      "temperature": 1.0
    },
    {
      "all_correct": 0.25,
      "all_wrong": 0.25,
      "completion_length": 357.828125,
      "epoch": 0.0545554068848072,
      "grad_norm": 1.5383738378679102,
      "kl": 0.054931640625,
      "learning_rate": 9.926742518928673e-07,
      "loss": 0.0022,
      "reward": 1.701249599456787,
      "reward_std": 0.14524880051612854,
      "rewards/accuracy_reward": 0.5699995756149292,
      "rewards/format_reward": 1.0,
      "step": 1794,
      "temperature": 1.0
    },
    {
      "all_correct": 0.25,
      "all_wrong": 0.125,
      "completion_length": 356.953125,
      "epoch": 0.05458581681060698,
      "grad_norm": 2.012750203932684,
      "kl": 0.046142578125,
      "learning_rate": 9.926661027029595e-07,
      "loss": 0.0018,
      "reward": 1.6020137071609497,
      "reward_std": 0.18549156188964844,
      "rewards/accuracy_reward": 0.4957636594772339,
      "rewards/format_reward": 1.0,
      "step": 1795,
      "temperature": 1.0
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.125,
      "completion_length": 364.015625,
      "epoch": 0.054616226736406766,
      "grad_norm": 1.3396600748411733,
      "kl": 0.0380859375,
      "learning_rate": 9.92657949016463e-07,
      "loss": 0.0015,
      "reward": 1.900700330734253,
      "reward_std": 0.04315320774912834,
      "rewards/accuracy_reward": 0.7319502234458923,
      "rewards/format_reward": 1.0,
      "step": 1796,
      "temperature": 1.0
    },
    {
      "all_correct": 0.75,
      "all_wrong": 0.0,
      "completion_length": 358.984375,
      "epoch": 0.054646636662206545,
      "grad_norm": 0.8127969025071565,
      "kl": 0.04296875,
      "learning_rate": 9.926497908334525e-07,
      "loss": 0.0017,
      "reward": 2.0303053855895996,
      "reward_std": 0.006462138146162033,
      "rewards/accuracy_reward": 0.8303053379058838,
      "rewards/format_reward": 1.0,
      "step": 1797,
      "temperature": 1.0
    },
    {
      "all_correct": 0.875,
      "all_wrong": 0.125,
      "completion_length": 341.328125,
      "epoch": 0.054677046588006324,
      "grad_norm": 0.9717605064989127,
      "kl": 0.0439453125,
      "learning_rate": 9.926416281540025e-07,
      "loss": 0.0018,
      "reward": 2.0343751907348633,
      "reward_std": 0.030616411939263344,
      "rewards/accuracy_reward": 0.875,
      "rewards/format_reward": 1.0,
      "step": 1798,
      "temperature": 1.0
    },
    {
      "all_correct": 0.75,
      "all_wrong": 0.125,
      "completion_length": 352.578125,
      "epoch": 0.0547074565138061,
      "grad_norm": 0.8735632889812265,
      "kl": 0.039794921875,
      "learning_rate": 9.926334609781872e-07,
      "loss": 0.0016,
      "reward": 1.994710922241211,
      "reward_std": 0.020471710711717606,
      "rewards/accuracy_reward": 0.8197108507156372,
      "rewards/format_reward": 1.0,
      "step": 1799,
      "temperature": 1.0
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.125,
      "completion_length": 374.953125,
      "epoch": 0.05473786643960589,
      "grad_norm": 0.7983037343834086,
      "kl": 0.03662109375,
      "learning_rate": 9.926252893060813e-07,
      "loss": 0.0015,
      "reward": 1.7769169807434082,
      "reward_std": 0.1593465358018875,
      "rewards/accuracy_reward": 0.6394169330596924,
      "rewards/format_reward": 1.0,
      "step": 1800,
      "temperature": 1.0
    },
    {
      "all_correct": 0.25,
      "all_wrong": 0.25,
      "completion_length": 355.328125,
      "epoch": 0.05476827636540567,
      "grad_norm": 1.5435004475522043,
      "kl": 0.042236328125,
      "learning_rate": 9.926171131377595e-07,
      "loss": 0.0017,
      "reward": 1.6208317279815674,
      "reward_std": 0.07936879992485046,
      "rewards/accuracy_reward": 0.47395679354667664,
      "rewards/format_reward": 1.0,
      "step": 1801,
      "temperature": 1.0
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.125,
      "completion_length": 361.15625,
      "epoch": 0.05479868629120545,
      "grad_norm": 1.048033469920985,
      "kl": 0.0380859375,
      "learning_rate": 9.926089324732962e-07,
      "loss": 0.0015,
      "reward": 1.7613670825958252,
      "reward_std": 0.10836216807365417,
      "rewards/accuracy_reward": 0.6238670349121094,
      "rewards/format_reward": 1.0,
      "step": 1802,
      "temperature": 1.0
    },
    {
      "all_correct": 0.375,
      "all_wrong": 0.125,
      "completion_length": 353.015625,
      "epoch": 0.05482909621700523,
      "grad_norm": 1.3398989619898078,
      "kl": 0.0380859375,
      "learning_rate": 9.926007473127662e-07,
      "loss": 0.0015,
      "reward": 1.7222988605499268,
      "reward_std": 0.22579775750637054,
      "rewards/accuracy_reward": 0.6035487055778503,
      "rewards/format_reward": 1.0,
      "step": 1803,
      "temperature": 1.0
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.0,
      "completion_length": 368.296875,
      "epoch": 0.05485950614280501,
      "grad_norm": 1.456614292818029,
      "kl": 0.04443359375,
      "learning_rate": 9.92592557656244e-07,
      "loss": 0.0018,
      "reward": 1.8075824975967407,
      "reward_std": 0.12256352603435516,
      "rewards/accuracy_reward": 0.6419574618339539,
      "rewards/format_reward": 1.0,
      "step": 1804,
      "temperature": 1.0
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.0,
      "completion_length": 375.8125,
      "epoch": 0.05488991606860479,
      "grad_norm": 1.2932988406157064,
      "kl": 0.032470703125,
      "learning_rate": 9.925843635038048e-07,
      "loss": 0.0013,
      "reward": 1.895079255104065,
      "reward_std": 0.17520296573638916,
      "rewards/accuracy_reward": 0.7263292670249939,
      "rewards/format_reward": 1.0,
      "step": 1805,
      "temperature": 1.0
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.0,
      "completion_length": 376.140625,
      "epoch": 0.05492032599440457,
      "grad_norm": 1.4258968783611523,
      "kl": 0.041748046875,
      "learning_rate": 9.92576164855523e-07,
      "loss": 0.0017,
      "reward": 1.9859092235565186,
      "reward_std": 0.14932841062545776,
      "rewards/accuracy_reward": 0.8015341758728027,
      "rewards/format_reward": 1.0,
      "step": 1806,
      "temperature": 1.0
    },
    {
      "all_correct": 0.625,
      "all_wrong": 0.0,
      "completion_length": 352.53125,
      "epoch": 0.05495073592020436,
      "grad_norm": 1.1249191140109915,
      "kl": 0.041015625,
      "learning_rate": 9.925679617114735e-07,
      "loss": 0.0016,
      "reward": 1.961499810218811,
      "reward_std": 0.1550062596797943,
      "rewards/accuracy_reward": 0.8021246790885925,
      "rewards/format_reward": 1.0,
      "step": 1807,
      "temperature": 1.0
    },
    {
      "all_correct": 0.625,
      "all_wrong": 0.0,
      "completion_length": 348.25,
      "epoch": 0.05498114584600414,
      "grad_norm": 1.640943635415484,
      "kl": 0.040771484375,
      "learning_rate": 9.925597540717311e-07,
      "loss": 0.0016,
      "reward": 2.075655698776245,
      "reward_std": 0.13321137428283691,
      "rewards/accuracy_reward": 0.8912806510925293,
      "rewards/format_reward": 1.0,
      "step": 1808,
      "temperature": 1.0
    },
    {
      "all_correct": 0.375,
      "all_wrong": 0.25,
      "completion_length": 390.140625,
      "epoch": 0.055011555771803916,
      "grad_norm": 0.8769442291243054,
      "kl": 0.041259765625,
      "learning_rate": 9.925515419363711e-07,
      "loss": 0.0016,
      "reward": 1.645674705505371,
      "reward_std": 0.016574416309595108,
      "rewards/accuracy_reward": 0.4956746995449066,
      "rewards/format_reward": 1.0,
      "step": 1809,
      "temperature": 1.0
    },
    {
      "all_correct": 0.375,
      "all_wrong": 0.375,
      "completion_length": 378.21875,
      "epoch": 0.055041965697603695,
      "grad_norm": 0.7106836727263328,
      "kl": 0.03662109375,
      "learning_rate": 9.92543325305468e-07,
      "loss": 0.0015,
      "reward": 1.5473958253860474,
      "reward_std": 0.09293131530284882,
      "rewards/accuracy_reward": 0.4598958194255829,
      "rewards/format_reward": 1.0,
      "step": 1810,
      "temperature": 1.0
    },
    {
      "all_correct": 0.625,
      "all_wrong": 0.125,
      "completion_length": 382.25,
      "epoch": 0.05507237562340348,
      "grad_norm": 0.54736202046218,
      "kl": 0.031982421875,
      "learning_rate": 9.92535104179097e-07,
      "loss": 0.0013,
      "reward": 1.9531251192092896,
      "reward_std": 0.17300525307655334,
      "rewards/accuracy_reward": 0.8125,
      "rewards/format_reward": 0.984375,
      "step": 1811,
      "temperature": 1.0
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.125,
      "completion_length": 350.6875,
      "epoch": 0.05510278554920326,
      "grad_norm": 0.977392856100019,
      "kl": 0.03662109375,
      "learning_rate": 9.925268785573332e-07,
      "loss": 0.0015,
      "reward": 1.919791579246521,
      "reward_std": 0.16896700859069824,
      "rewards/accuracy_reward": 0.7604167461395264,
      "rewards/format_reward": 1.0,
      "step": 1812,
      "temperature": 1.0
    },
    {
      "all_correct": 0.625,
      "all_wrong": 0.125,
      "completion_length": 365.46875,
      "epoch": 0.05513319547500304,
      "grad_norm": 0.8476268963499787,
      "kl": 0.0400390625,
      "learning_rate": 9.925186484402512e-07,
      "loss": 0.0016,
      "reward": 1.9810937643051147,
      "reward_std": 0.02394336462020874,
      "rewards/accuracy_reward": 0.8092187643051147,
      "rewards/format_reward": 1.0,
      "step": 1813,
      "temperature": 1.0
    },
    {
      "all_correct": 0.625,
      "all_wrong": 0.25,
      "completion_length": 369.5625,
      "epoch": 0.05516360540080282,
      "grad_norm": 0.3222451085297914,
      "kl": 0.03515625,
      "learning_rate": 9.925104138279268e-07,
      "loss": 0.0014,
      "reward": 1.8624999523162842,
      "reward_std": 0.06943650543689728,
      "rewards/accuracy_reward": 0.71875,
      "rewards/format_reward": 1.0,
      "step": 1814,
      "temperature": 1.0
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.25,
      "completion_length": 366.484375,
      "epoch": 0.055194015326602605,
      "grad_norm": 1.4283901752006507,
      "kl": 0.043701171875,
      "learning_rate": 9.92502174720435e-07,
      "loss": 0.0018,
      "reward": 1.6837177276611328,
      "reward_std": 0.05716827139258385,
      "rewards/accuracy_reward": 0.5587177872657776,
      "rewards/format_reward": 1.0,
      "step": 1815,
      "temperature": 1.0
    },
    {
      "all_correct": 0.625,
      "all_wrong": 0.125,
      "completion_length": 353.109375,
      "epoch": 0.055224425252402384,
      "grad_norm": 1.007097999743465,
      "kl": 0.043212890625,
      "learning_rate": 9.924939311178506e-07,
      "loss": 0.0017,
      "reward": 1.838458776473999,
      "reward_std": 0.04184095561504364,
      "rewards/accuracy_reward": 0.6759586930274963,
      "rewards/format_reward": 1.0,
      "step": 1816,
      "temperature": 1.0
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.0,
      "completion_length": 397.796875,
      "epoch": 0.055254835178202164,
      "grad_norm": 2.4294998715474314,
      "kl": 0.0294189453125,
      "learning_rate": 9.92485683020249e-07,
      "loss": 0.0012,
      "reward": 1.9912397861480713,
      "reward_std": 0.10232331603765488,
      "rewards/accuracy_reward": 0.8037397861480713,
      "rewards/format_reward": 1.0,
      "step": 1817,
      "temperature": 1.0
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.125,
      "completion_length": 376.046875,
      "epoch": 0.05528524510400195,
      "grad_norm": 1.6600904990874867,
      "kl": 0.033203125,
      "learning_rate": 9.92477430427706e-07,
      "loss": 0.0013,
      "reward": 1.7595914602279663,
      "reward_std": 0.052386827766895294,
      "rewards/accuracy_reward": 0.6095914244651794,
      "rewards/format_reward": 1.0,
      "step": 1818,
      "temperature": 1.0
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.125,
      "completion_length": 377.296875,
      "epoch": 0.05531565502980173,
      "grad_norm": 1.6004028763061766,
      "kl": 0.041748046875,
      "learning_rate": 9.92469173340296e-07,
      "loss": 0.0017,
      "reward": 1.6154446601867676,
      "reward_std": 0.08654943853616714,
      "rewards/accuracy_reward": 0.5279447436332703,
      "rewards/format_reward": 1.0,
      "step": 1819,
      "temperature": 1.0
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.125,
      "completion_length": 356.75,
      "epoch": 0.05534606495560151,
      "grad_norm": 1.377380782239242,
      "kl": 0.04541015625,
      "learning_rate": 9.924609117580951e-07,
      "loss": 0.0018,
      "reward": 1.8948674201965332,
      "reward_std": 0.07723085582256317,
      "rewards/accuracy_reward": 0.7261173725128174,
      "rewards/format_reward": 1.0,
      "step": 1820,
      "temperature": 1.0
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.0,
      "completion_length": 391.0625,
      "epoch": 0.05537647488140129,
      "grad_norm": 0.8839340175894997,
      "kl": 0.041259765625,
      "learning_rate": 9.924526456811785e-07,
      "loss": 0.0017,
      "reward": 2.0152053833007812,
      "reward_std": 0.12524709105491638,
      "rewards/accuracy_reward": 0.8308305144309998,
      "rewards/format_reward": 1.0,
      "step": 1821,
      "temperature": 1.0
    },
    {
      "all_correct": 0.625,
      "all_wrong": 0.0,
      "completion_length": 347.734375,
      "epoch": 0.05540688480720107,
      "grad_norm": 1.8549139139246353,
      "kl": 0.038818359375,
      "learning_rate": 9.924443751096215e-07,
      "loss": 0.0015,
      "reward": 1.9861880540847778,
      "reward_std": 0.11136253923177719,
      "rewards/accuracy_reward": 0.8174380660057068,
      "rewards/format_reward": 1.0,
      "step": 1822,
      "temperature": 1.0
    },
    {
      "all_correct": 0.75,
      "all_wrong": 0.0,
      "completion_length": 354.71875,
      "epoch": 0.05543729473300085,
      "grad_norm": 2.3093435679670873,
      "kl": 0.036865234375,
      "learning_rate": 9.924361000434997e-07,
      "loss": 0.0015,
      "reward": 2.072706699371338,
      "reward_std": 0.08866246789693832,
      "rewards/accuracy_reward": 0.8883317708969116,
      "rewards/format_reward": 1.0,
      "step": 1823,
      "temperature": 1.0
    },
    {
      "all_correct": 0.375,
      "all_wrong": 0.125,
      "completion_length": 373.4375,
      "epoch": 0.05546770465880063,
      "grad_norm": 1.2994203906027615,
      "kl": 0.03662109375,
      "learning_rate": 9.924278204828885e-07,
      "loss": 0.0015,
      "reward": 1.8100841045379639,
      "reward_std": 0.11531638354063034,
      "rewards/accuracy_reward": 0.6600841283798218,
      "rewards/format_reward": 1.0,
      "step": 1824,
      "temperature": 1.0
    },
    {
      "all_correct": 0.25,
      "all_wrong": 0.25,
      "completion_length": 379.328125,
      "epoch": 0.05549811458460041,
      "grad_norm": 2.927134591359527,
      "kl": 0.0439453125,
      "learning_rate": 9.92419536427864e-07,
      "loss": 0.0018,
      "reward": 1.6755608320236206,
      "reward_std": 0.04908619821071625,
      "rewards/accuracy_reward": 0.5255608558654785,
      "rewards/format_reward": 1.0,
      "step": 1825,
      "temperature": 1.0
    },
    {
      "all_correct": 0.75,
      "all_wrong": 0.0,
      "completion_length": 381.40625,
      "epoch": 0.0555285245104002,
      "grad_norm": 0.8268663404142803,
      "kl": 0.033203125,
      "learning_rate": 9.924112478785011e-07,
      "loss": 0.0013,
      "reward": 1.9913171529769897,
      "reward_std": 0.01231265440583229,
      "rewards/accuracy_reward": 0.8100671172142029,
      "rewards/format_reward": 1.0,
      "step": 1826,
      "temperature": 1.0
    },
    {
      "all_correct": 0.375,
      "all_wrong": 0.0,
      "completion_length": 419.484375,
      "epoch": 0.055558934436199976,
      "grad_norm": 1.9931406517003176,
      "kl": 0.04345703125,
      "learning_rate": 9.924029548348758e-07,
      "loss": 0.0017,
      "reward": 1.6861860752105713,
      "reward_std": 0.06438237428665161,
      "rewards/accuracy_reward": 0.5236860513687134,
      "rewards/format_reward": 1.0,
      "step": 1827,
      "temperature": 1.0
    },
    {
      "all_correct": 0.625,
      "all_wrong": 0.0,
      "completion_length": 348.390625,
      "epoch": 0.055589344361999755,
      "grad_norm": 1.230808951654158,
      "kl": 0.035888671875,
      "learning_rate": 9.923946572970636e-07,
      "loss": 0.0014,
      "reward": 2.0843749046325684,
      "reward_std": 0.19508321583271027,
      "rewards/accuracy_reward": 0.90625,
      "rewards/format_reward": 1.0,
      "step": 1828,
      "temperature": 1.0
    },
    {
      "all_correct": 0.625,
      "all_wrong": 0.125,
      "completion_length": 346.609375,
      "epoch": 0.055619754287799535,
      "grad_norm": 1.0487314531643683,
      "kl": 0.0380859375,
      "learning_rate": 9.923863552651405e-07,
      "loss": 0.0015,
      "reward": 1.7979985475540161,
      "reward_std": 0.06891971826553345,
      "rewards/accuracy_reward": 0.6636235117912292,
      "rewards/format_reward": 1.0,
      "step": 1829,
      "temperature": 1.0
    },
    {
      "all_correct": 0.375,
      "all_wrong": 0.125,
      "completion_length": 355.984375,
      "epoch": 0.05565016421359932,
      "grad_norm": 1.1607839160185394,
      "kl": 0.03857421875,
      "learning_rate": 9.923780487391822e-07,
      "loss": 0.0015,
      "reward": 1.7312500476837158,
      "reward_std": 0.30233362317085266,
      "rewards/accuracy_reward": 0.609375,
      "rewards/format_reward": 1.0,
      "step": 1830,
      "temperature": 1.0
    },
    {
      "all_correct": 0.625,
      "all_wrong": 0.0,
      "completion_length": 353.828125,
      "epoch": 0.0556805741393991,
      "grad_norm": 1.0089524585810061,
      "kl": 0.0478515625,
      "learning_rate": 9.923697377192644e-07,
      "loss": 0.0019,
      "reward": 2.0357604026794434,
      "reward_std": 0.09623770415782928,
      "rewards/accuracy_reward": 0.8513851165771484,
      "rewards/format_reward": 1.0,
      "step": 1831,
      "temperature": 1.0
    },
    {
      "all_correct": 0.75,
      "all_wrong": 0.125,
      "completion_length": 343.390625,
      "epoch": 0.05571098406519888,
      "grad_norm": 0.9049065601240881,
      "kl": 0.033203125,
      "learning_rate": 9.92361422205463e-07,
      "loss": 0.0013,
      "reward": 1.953125,
      "reward_std": 0.08647121489048004,
      "rewards/accuracy_reward": 0.796875,
      "rewards/format_reward": 1.0,
      "step": 1832,
      "temperature": 1.0
    },
    {
      "all_correct": 0.875,
      "all_wrong": 0.125,
      "completion_length": 342.703125,
      "epoch": 0.055741393990998665,
      "grad_norm": 0.5486600557676367,
      "kl": 0.054443359375,
      "learning_rate": 9.923531021978537e-07,
      "loss": 0.0022,
      "reward": 2.044959545135498,
      "reward_std": 0.0018665710231289268,
      "rewards/accuracy_reward": 0.8699596524238586,
      "rewards/format_reward": 1.0,
      "step": 1833,
      "temperature": 1.0
    },
    {
      "all_correct": 0.625,
      "all_wrong": 0.125,
      "completion_length": 353.171875,
      "epoch": 0.055771803916798444,
      "grad_norm": 1.2334516884932032,
      "kl": 0.03955078125,
      "learning_rate": 9.92344777696513e-07,
      "loss": 0.0016,
      "reward": 1.823790192604065,
      "reward_std": 0.029252495616674423,
      "rewards/accuracy_reward": 0.6706651449203491,
      "rewards/format_reward": 1.0,
      "step": 1834,
      "temperature": 1.0
    },
    {
      "all_correct": 0.625,
      "all_wrong": 0.125,
      "completion_length": 347.0,
      "epoch": 0.055802213842598224,
      "grad_norm": 0.48596692961575844,
      "kl": 0.03466796875,
      "learning_rate": 9.923364487015162e-07,
      "loss": 0.0014,
      "reward": 1.9562500715255737,
      "reward_std": 0.14706888794898987,
      "rewards/accuracy_reward": 0.796875,
      "rewards/format_reward": 1.0,
      "step": 1835,
      "temperature": 1.0
    },
    {
      "all_correct": 0.75,
      "all_wrong": 0.0,
      "completion_length": 354.8125,
      "epoch": 0.055832623768398,
      "grad_norm": 0.7778282609104304,
      "kl": 0.037841796875,
      "learning_rate": 9.923281152129399e-07,
      "loss": 0.0015,
      "reward": 2.06136155128479,
      "reward_std": 0.028856799006462097,
      "rewards/accuracy_reward": 0.8644865155220032,
      "rewards/format_reward": 1.0,
      "step": 1836,
      "temperature": 1.0
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.125,
      "completion_length": 359.828125,
      "epoch": 0.05586303369419779,
      "grad_norm": 1.04456295719975,
      "kl": 0.041259765625,
      "learning_rate": 9.923197772308597e-07,
      "loss": 0.0017,
      "reward": 1.8501803874969482,
      "reward_std": 0.1517704427242279,
      "rewards/accuracy_reward": 0.7095552682876587,
      "rewards/format_reward": 1.0,
      "step": 1837,
      "temperature": 1.0
    },
    {
      "all_correct": 0.375,
      "all_wrong": 0.25,
      "completion_length": 410.828125,
      "epoch": 0.05589344361999757,
      "grad_norm": 3.336341985898304,
      "kl": 0.03173828125,
      "learning_rate": 9.92311434755352e-07,
      "loss": 0.0013,
      "reward": 1.5871260166168213,
      "reward_std": 0.08487197756767273,
      "rewards/accuracy_reward": 0.46525105834007263,
      "rewards/format_reward": 1.0,
      "step": 1838,
      "temperature": 1.0
    },
    {
      "all_correct": 0.625,
      "all_wrong": 0.125,
      "completion_length": 363.28125,
      "epoch": 0.05592385354579735,
      "grad_norm": 1.4883900247881565,
      "kl": 0.04638671875,
      "learning_rate": 9.923030877864928e-07,
      "loss": 0.0019,
      "reward": 1.895857334136963,
      "reward_std": 0.06589207798242569,
      "rewards/accuracy_reward": 0.7333572506904602,
      "rewards/format_reward": 1.0,
      "step": 1839,
      "temperature": 1.0
    },
    {
      "all_correct": 0.25,
      "all_wrong": 0.125,
      "completion_length": 412.71875,
      "epoch": 0.05595426347159713,
      "grad_norm": 3.0778497463352097,
      "kl": 0.031982421875,
      "learning_rate": 9.922947363243585e-07,
      "loss": 0.0013,
      "reward": 1.6286427974700928,
      "reward_std": 0.11927562206983566,
      "rewards/accuracy_reward": 0.4755178689956665,
      "rewards/format_reward": 1.0,
      "step": 1840,
      "temperature": 1.0
    },
    {
      "all_correct": 0.25,
      "all_wrong": 0.125,
      "completion_length": 407.546875,
      "epoch": 0.05598467339739691,
      "grad_norm": 0.9575660204521547,
      "kl": 0.0289306640625,
      "learning_rate": 9.922863803690249e-07,
      "loss": 0.0012,
      "reward": 1.580139398574829,
      "reward_std": 0.28412267565727234,
      "rewards/accuracy_reward": 0.5051394104957581,
      "rewards/format_reward": 0.953125,
      "step": 1841,
      "temperature": 1.0
    },
    {
      "all_correct": 0.375,
      "all_wrong": 0.125,
      "completion_length": 354.9375,
      "epoch": 0.05601508332319669,
      "grad_norm": 1.0755044015423803,
      "kl": 0.0322265625,
      "learning_rate": 9.922780199205688e-07,
      "loss": 0.0013,
      "reward": 1.7700700759887695,
      "reward_std": 0.2082536518573761,
      "rewards/accuracy_reward": 0.6325700283050537,
      "rewards/format_reward": 1.0,
      "step": 1842,
      "temperature": 1.0
    },
    {
      "all_correct": 0.625,
      "all_wrong": 0.0,
      "completion_length": 349.125,
      "epoch": 0.05604549324899647,
      "grad_norm": 1.8343532000513065,
      "kl": 0.0380859375,
      "learning_rate": 9.92269654979066e-07,
      "loss": 0.0015,
      "reward": 2.0218751430511475,
      "reward_std": 0.21231761574745178,
      "rewards/accuracy_reward": 0.859375,
      "rewards/format_reward": 1.0,
      "step": 1843,
      "temperature": 1.0
    },
    {
      "all_correct": 0.625,
      "all_wrong": 0.0,
      "completion_length": 349.515625,
      "epoch": 0.05607590317479625,
      "grad_norm": 1.2330015511660366,
      "kl": 0.03515625,
      "learning_rate": 9.922612855445931e-07,
      "loss": 0.0014,
      "reward": 1.953125,
      "reward_std": 0.2253442406654358,
      "rewards/accuracy_reward": 0.796875,
      "rewards/format_reward": 1.0,
      "step": 1844,
      "temperature": 1.0
    },
    {
      "all_correct": 0.375,
      "all_wrong": 0.125,
      "completion_length": 358.171875,
      "epoch": 0.056106313100596036,
      "grad_norm": 1.5973750873190569,
      "kl": 0.039794921875,
      "learning_rate": 9.922529116172265e-07,
      "loss": 0.0016,
      "reward": 1.7458016872406006,
      "reward_std": 0.22305285930633545,
      "rewards/accuracy_reward": 0.6083016395568848,
      "rewards/format_reward": 1.0,
      "step": 1845,
      "temperature": 1.0
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.0,
      "completion_length": 373.3125,
      "epoch": 0.056136723026395816,
      "grad_norm": 2.6075486990186185,
      "kl": 0.039794921875,
      "learning_rate": 9.922445331970426e-07,
      "loss": 0.0016,
      "reward": 1.8482511043548584,
      "reward_std": 0.11192609369754791,
      "rewards/accuracy_reward": 0.6763760447502136,
      "rewards/format_reward": 1.0,
      "step": 1846,
      "temperature": 1.0
    },
    {
      "all_correct": 0.375,
      "all_wrong": 0.125,
      "completion_length": 366.078125,
      "epoch": 0.056167132952195595,
      "grad_norm": 0.9001168650455822,
      "kl": 0.043701171875,
      "learning_rate": 9.922361502841178e-07,
      "loss": 0.0018,
      "reward": 1.7739583253860474,
      "reward_std": 0.22493413090705872,
      "rewards/accuracy_reward": 0.6458333134651184,
      "rewards/format_reward": 1.0,
      "step": 1847,
      "temperature": 1.0
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.125,
      "completion_length": 372.953125,
      "epoch": 0.05619754287799538,
      "grad_norm": 1.0874942647285268,
      "kl": 0.0380859375,
      "learning_rate": 9.922277628785287e-07,
      "loss": 0.0015,
      "reward": 1.8757933378219604,
      "reward_std": 0.17411655187606812,
      "rewards/accuracy_reward": 0.7195432782173157,
      "rewards/format_reward": 1.0,
      "step": 1848,
      "temperature": 1.0
    },
    {
      "all_correct": 0.75,
      "all_wrong": 0.125,
      "completion_length": 359.15625,
      "epoch": 0.05622795280379516,
      "grad_norm": 1.1551137955046786,
      "kl": 0.03466796875,
      "learning_rate": 9.922193709803519e-07,
      "loss": 0.0014,
      "reward": 1.875568151473999,
      "reward_std": 0.10124483704566956,
      "rewards/accuracy_reward": 0.7443181872367859,
      "rewards/format_reward": 0.984375,
      "step": 1849,
      "temperature": 1.0
    },
    {
      "all_correct": 0.375,
      "all_wrong": 0.375,
      "completion_length": 357.1875,
      "epoch": 0.05625836272959494,
      "grad_norm": 0.6220895176656418,
      "kl": 0.042236328125,
      "learning_rate": 9.922109745896637e-07,
      "loss": 0.0017,
      "reward": 1.5498721599578857,
      "reward_std": 0.048731740564107895,
      "rewards/accuracy_reward": 0.4498721957206726,
      "rewards/format_reward": 1.0,
      "step": 1850,
      "temperature": 1.0
    },
    {
      "all_correct": 0.625,
      "all_wrong": 0.0,
      "completion_length": 343.671875,
      "epoch": 0.05628877265539472,
      "grad_norm": 25.13358638185564,
      "kl": 0.040771484375,
      "learning_rate": 9.922025737065412e-07,
      "loss": 0.0016,
      "reward": 2.0662150382995605,
      "reward_std": 0.15824121236801147,
      "rewards/accuracy_reward": 0.8880901336669922,
      "rewards/format_reward": 1.0,
      "step": 1851,
      "temperature": 1.0
    },
    {
      "all_correct": 0.375,
      "all_wrong": 0.125,
      "completion_length": 379.984375,
      "epoch": 0.056319182581194505,
      "grad_norm": 0.9934314366436088,
      "kl": 0.03662109375,
      "learning_rate": 9.921941683310605e-07,
      "loss": 0.0015,
      "reward": 1.7997488975524902,
      "reward_std": 0.18747317790985107,
      "rewards/accuracy_reward": 0.6778739094734192,
      "rewards/format_reward": 0.984375,
      "step": 1852,
      "temperature": 1.0
    },
    {
      "all_correct": 0.25,
      "all_wrong": 0.125,
      "completion_length": 362.765625,
      "epoch": 0.056349592506994284,
      "grad_norm": 1.5625271495605662,
      "kl": 0.05712890625,
      "learning_rate": 9.92185758463299e-07,
      "loss": 0.0023,
      "reward": 1.7489309310913086,
      "reward_std": 0.23080140352249146,
      "rewards/accuracy_reward": 0.6020558476448059,
      "rewards/format_reward": 1.0,
      "step": 1853,
      "temperature": 1.0
    },
    {
      "all_correct": 0.75,
      "all_wrong": 0.0,
      "completion_length": 353.203125,
      "epoch": 0.05638000243279406,
      "grad_norm": 0.8748453337552218,
      "kl": 0.040283203125,
      "learning_rate": 9.92177344103333e-07,
      "loss": 0.0016,
      "reward": 2.0786030292510986,
      "reward_std": 0.08555250614881516,
      "rewards/accuracy_reward": 0.8911029100418091,
      "rewards/format_reward": 1.0,
      "step": 1854,
      "temperature": 1.0
    },
    {
      "all_correct": 0.625,
      "all_wrong": 0.25,
      "completion_length": 365.6875,
      "epoch": 0.05641041235859384,
      "grad_norm": 0.4326961918771979,
      "kl": 0.04248046875,
      "learning_rate": 9.921689252512393e-07,
      "loss": 0.0017,
      "reward": 1.8231035470962524,
      "reward_std": 0.009484430775046349,
      "rewards/accuracy_reward": 0.6762285828590393,
      "rewards/format_reward": 1.0,
      "step": 1855,
      "temperature": 1.0
    },
    {
      "all_correct": 0.625,
      "all_wrong": 0.0,
      "completion_length": 380.6875,
      "epoch": 0.05644082228439363,
      "grad_norm": 1.8029994511917542,
      "kl": 0.0400390625,
      "learning_rate": 9.92160501907095e-07,
      "loss": 0.0016,
      "reward": 1.9482872486114502,
      "reward_std": 0.05767810717225075,
      "rewards/accuracy_reward": 0.7701621651649475,
      "rewards/format_reward": 1.0,
      "step": 1856,
      "temperature": 1.0
    },
    {
      "all_correct": 0.625,
      "all_wrong": 0.125,
      "completion_length": 384.25,
      "epoch": 0.05647123221019341,
      "grad_norm": 1.2766406489627038,
      "kl": 0.04541015625,
      "learning_rate": 9.921520740709765e-07,
      "loss": 0.0018,
      "reward": 1.8384604454040527,
      "reward_std": 0.07768689841032028,
      "rewards/accuracy_reward": 0.6853355169296265,
      "rewards/format_reward": 1.0,
      "step": 1857,
      "temperature": 1.0
    },
    {
      "all_correct": 0.75,
      "all_wrong": 0.0,
      "completion_length": 363.953125,
      "epoch": 0.05650164213599319,
      "grad_norm": 1.5418241194115512,
      "kl": 0.04052734375,
      "learning_rate": 9.921436417429612e-07,
      "loss": 0.0016,
      "reward": 1.9332107305526733,
      "reward_std": 0.06883864849805832,
      "rewards/accuracy_reward": 0.7769607305526733,
      "rewards/format_reward": 1.0,
      "step": 1858,
      "temperature": 1.0
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.0,
      "completion_length": 363.796875,
      "epoch": 0.056532052061792966,
      "grad_norm": 1.2806297958598352,
      "kl": 0.041259765625,
      "learning_rate": 9.92135204923126e-07,
      "loss": 0.0017,
      "reward": 1.867650032043457,
      "reward_std": 0.17836429178714752,
      "rewards/accuracy_reward": 0.7051499485969543,
      "rewards/format_reward": 1.0,
      "step": 1859,
      "temperature": 1.0
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.0,
      "completion_length": 344.65625,
      "epoch": 0.05656246198759275,
      "grad_norm": 1.4074167664440507,
      "kl": 0.039794921875,
      "learning_rate": 9.921267636115478e-07,
      "loss": 0.0016,
      "reward": 1.9787335395812988,
      "reward_std": 0.20133064687252045,
      "rewards/accuracy_reward": 0.8006083965301514,
      "rewards/format_reward": 1.0,
      "step": 1860,
      "temperature": 1.0
    },
    {
      "all_correct": 0.375,
      "all_wrong": 0.0,
      "completion_length": 370.765625,
      "epoch": 0.05659287191339253,
      "grad_norm": 1.3488314866156224,
      "kl": 0.048095703125,
      "learning_rate": 9.921183178083035e-07,
      "loss": 0.0019,
      "reward": 1.932004451751709,
      "reward_std": 0.09696999192237854,
      "rewards/accuracy_reward": 0.7413793802261353,
      "rewards/format_reward": 1.0,
      "step": 1861,
      "temperature": 1.0
    },
    {
      "all_correct": 0.625,
      "all_wrong": 0.0,
      "completion_length": 362.203125,
      "epoch": 0.05662328183919231,
      "grad_norm": 0.9534472962813201,
      "kl": 0.04443359375,
      "learning_rate": 9.921098675134704e-07,
      "loss": 0.0018,
      "reward": 2.071725368499756,
      "reward_std": 0.037764161825180054,
      "rewards/accuracy_reward": 0.877975344657898,
      "rewards/format_reward": 1.0,
      "step": 1862,
      "temperature": 1.0
    },
    {
      "all_correct": 0.625,
      "all_wrong": 0.375,
      "completion_length": 347.03125,
      "epoch": 0.056653691764992097,
      "grad_norm": 0.4915780859728136,
      "kl": 0.03515625,
      "learning_rate": 9.921014127271257e-07,
      "loss": 0.0014,
      "reward": 1.7437500953674316,
      "reward_std": 0.011572758667171001,
      "rewards/accuracy_reward": 0.625,
      "rewards/format_reward": 1.0,
      "step": 1863,
      "temperature": 1.0
    },
    {
      "all_correct": 0.75,
      "all_wrong": 0.125,
      "completion_length": 336.765625,
      "epoch": 0.056684101690791876,
      "grad_norm": 0.9366182842437619,
      "kl": 0.052490234375,
      "learning_rate": 9.920929534493463e-07,
      "loss": 0.0021,
      "reward": 1.96875,
      "reward_std": 0.0978560596704483,
      "rewards/accuracy_reward": 0.8125,
      "rewards/format_reward": 1.0,
      "step": 1864,
      "temperature": 1.0
    },
    {
      "all_correct": 0.875,
      "all_wrong": 0.125,
      "completion_length": 341.40625,
      "epoch": 0.056714511616591655,
      "grad_norm": 1.1694495623434176,
      "kl": 0.044189453125,
      "learning_rate": 9.920844896802093e-07,
      "loss": 0.0018,
      "reward": 2.043750047683716,
      "reward_std": 0.017677675932645798,
      "rewards/accuracy_reward": 0.875,
      "rewards/format_reward": 1.0,
      "step": 1865,
      "temperature": 1.0
    },
    {
      "all_correct": 0.375,
      "all_wrong": 0.25,
      "completion_length": 364.09375,
      "epoch": 0.056744921542391434,
      "grad_norm": 1.11981809197019,
      "kl": 0.04150390625,
      "learning_rate": 9.920760214197924e-07,
      "loss": 0.0017,
      "reward": 1.7781250476837158,
      "reward_std": 0.1972883939743042,
      "rewards/accuracy_reward": 0.65625,
      "rewards/format_reward": 1.0,
      "step": 1866,
      "temperature": 1.0
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.125,
      "completion_length": 377.28125,
      "epoch": 0.05677533146819122,
      "grad_norm": 0.8966699107727735,
      "kl": 0.0478515625,
      "learning_rate": 9.920675486681728e-07,
      "loss": 0.0019,
      "reward": 1.7971857786178589,
      "reward_std": 0.017440611496567726,
      "rewards/accuracy_reward": 0.6253107786178589,
      "rewards/format_reward": 1.0,
      "step": 1867,
      "temperature": 1.0
    },
    {
      "all_correct": 0.625,
      "all_wrong": 0.0,
      "completion_length": 341.78125,
      "epoch": 0.056805741393991,
      "grad_norm": 1.70372319647996,
      "kl": 0.034912109375,
      "learning_rate": 9.920590714254275e-07,
      "loss": 0.0014,
      "reward": 2.125,
      "reward_std": 0.17550252377986908,
      "rewards/accuracy_reward": 0.9375,
      "rewards/format_reward": 1.0,
      "step": 1868,
      "temperature": 1.0
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.125,
      "completion_length": 353.296875,
      "epoch": 0.05683615131979078,
      "grad_norm": 1.0618694031823293,
      "kl": 0.04052734375,
      "learning_rate": 9.920505896916342e-07,
      "loss": 0.0016,
      "reward": 1.8476537466049194,
      "reward_std": 0.14259874820709229,
      "rewards/accuracy_reward": 0.7007787227630615,
      "rewards/format_reward": 1.0,
      "step": 1869,
      "temperature": 1.0
    },
    {
      "all_correct": 0.625,
      "all_wrong": 0.0,
      "completion_length": 351.078125,
      "epoch": 0.05686656124559056,
      "grad_norm": 1.12369152246337,
      "kl": 0.033935546875,
      "learning_rate": 9.920421034668703e-07,
      "loss": 0.0014,
      "reward": 1.9709336757659912,
      "reward_std": 0.17443126440048218,
      "rewards/accuracy_reward": 0.7959335446357727,
      "rewards/format_reward": 1.0,
      "step": 1870,
      "temperature": 1.0
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.25,
      "completion_length": 361.09375,
      "epoch": 0.056896971171390344,
      "grad_norm": 0.6805041296573715,
      "kl": 0.035888671875,
      "learning_rate": 9.92033612751213e-07,
      "loss": 0.0014,
      "reward": 1.6889848709106445,
      "reward_std": 0.04650196060538292,
      "rewards/accuracy_reward": 0.5639848113059998,
      "rewards/format_reward": 1.0,
      "step": 1871,
      "temperature": 1.0
    },
    {
      "all_correct": 0.375,
      "all_wrong": 0.125,
      "completion_length": 375.015625,
      "epoch": 0.05692738109719012,
      "grad_norm": 1.3111713081537106,
      "kl": 0.02734375,
      "learning_rate": 9.920251175447397e-07,
      "loss": 0.0011,
      "reward": 1.8788461685180664,
      "reward_std": 0.22712530195713043,
      "rewards/accuracy_reward": 0.7319711446762085,
      "rewards/format_reward": 1.0,
      "step": 1872,
      "temperature": 1.0
    },
    {
      "all_correct": 0.625,
      "all_wrong": 0.125,
      "completion_length": 380.59375,
      "epoch": 0.0569577910229899,
      "grad_norm": 0.7721329306152038,
      "kl": 0.03271484375,
      "learning_rate": 9.920166178475287e-07,
      "loss": 0.0013,
      "reward": 1.8742027282714844,
      "reward_std": 0.09498561173677444,
      "rewards/accuracy_reward": 0.7273277640342712,
      "rewards/format_reward": 1.0,
      "step": 1873,
      "temperature": 1.0
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.0,
      "completion_length": 376.03125,
      "epoch": 0.05698820094878968,
      "grad_norm": 0.9944406872404637,
      "kl": 0.03173828125,
      "learning_rate": 9.920081136596569e-07,
      "loss": 0.0013,
      "reward": 1.798855185508728,
      "reward_std": 0.1442265510559082,
      "rewards/accuracy_reward": 0.6394801139831543,
      "rewards/format_reward": 1.0,
      "step": 1874,
      "temperature": 1.0
    },
    {
      "all_correct": 0.875,
      "all_wrong": 0.0,
      "completion_length": 344.484375,
      "epoch": 0.05701861087458947,
      "grad_norm": 0.6691698710531648,
      "kl": 0.040283203125,
      "learning_rate": 9.919996049812017e-07,
      "loss": 0.0016,
      "reward": 2.105757236480713,
      "reward_std": 0.009038932621479034,
      "rewards/accuracy_reward": 0.905756950378418,
      "rewards/format_reward": 1.0,
      "step": 1875,
      "temperature": 1.0
    },
    {
      "all_correct": 0.625,
      "all_wrong": 0.25,
      "completion_length": 390.296875,
      "epoch": 0.05704902080038925,
      "grad_norm": 0.647064639184316,
      "kl": 0.0294189453125,
      "learning_rate": 9.919910918122415e-07,
      "loss": 0.0012,
      "reward": 1.8351638317108154,
      "reward_std": 0.025424057617783546,
      "rewards/accuracy_reward": 0.7070387601852417,
      "rewards/format_reward": 1.0,
      "step": 1876,
      "temperature": 1.0
    },
    {
      "all_correct": 0.75,
      "all_wrong": 0.0,
      "completion_length": 376.515625,
      "epoch": 0.057079430726189026,
      "grad_norm": 0.8856239279835408,
      "kl": 0.0303955078125,
      "learning_rate": 9.919825741528533e-07,
      "loss": 0.0012,
      "reward": 2.016319513320923,
      "reward_std": 0.008788714185357094,
      "rewards/accuracy_reward": 0.8163194060325623,
      "rewards/format_reward": 1.0,
      "step": 1877,
      "temperature": 1.0
    },
    {
      "all_correct": 0.625,
      "all_wrong": 0.0,
      "completion_length": 384.46875,
      "epoch": 0.05710984065198881,
      "grad_norm": 1.0406720879063511,
      "kl": 0.036376953125,
      "learning_rate": 9.919740520031155e-07,
      "loss": 0.0015,
      "reward": 1.980074405670166,
      "reward_std": 0.09344036132097244,
      "rewards/accuracy_reward": 0.7925743460655212,
      "rewards/format_reward": 1.0,
      "step": 1878,
      "temperature": 1.0
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.125,
      "completion_length": 383.203125,
      "epoch": 0.05714025057778859,
      "grad_norm": 0.7667431274639929,
      "kl": 0.034423828125,
      "learning_rate": 9.919655253631054e-07,
      "loss": 0.0014,
      "reward": 1.8458385467529297,
      "reward_std": 0.15162408351898193,
      "rewards/accuracy_reward": 0.6927134990692139,
      "rewards/format_reward": 1.0,
      "step": 1879,
      "temperature": 1.0
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.125,
      "completion_length": 376.25,
      "epoch": 0.05717066050358837,
      "grad_norm": 1.14080870389853,
      "kl": 0.048095703125,
      "learning_rate": 9.919569942329009e-07,
      "loss": 0.0019,
      "reward": 1.7443220615386963,
      "reward_std": 0.06011394411325455,
      "rewards/accuracy_reward": 0.6005719900131226,
      "rewards/format_reward": 1.0,
      "step": 1880,
      "temperature": 1.0
    },
    {
      "all_correct": 0.375,
      "all_wrong": 0.125,
      "completion_length": 375.75,
      "epoch": 0.05720107042938815,
      "grad_norm": 2.637647472482071,
      "kl": 0.0390625,
      "learning_rate": 9.919484586125802e-07,
      "loss": 0.0016,
      "reward": 1.7118557691574097,
      "reward_std": 0.13622045516967773,
      "rewards/accuracy_reward": 0.5774807929992676,
      "rewards/format_reward": 1.0,
      "step": 1881,
      "temperature": 1.0
    },
    {
      "all_correct": 0.625,
      "all_wrong": 0.125,
      "completion_length": 372.71875,
      "epoch": 0.057231480355187936,
      "grad_norm": 0.5519170912122575,
      "kl": 0.033203125,
      "learning_rate": 9.919399185022206e-07,
      "loss": 0.0013,
      "reward": 1.9000000953674316,
      "reward_std": 0.13887301087379456,
      "rewards/accuracy_reward": 0.75,
      "rewards/format_reward": 1.0,
      "step": 1882,
      "temperature": 1.0
    },
    {
      "all_correct": 0.625,
      "all_wrong": 0.375,
      "completion_length": 364.078125,
      "epoch": 0.057261890280987715,
      "grad_norm": 0.07778799895529925,
      "kl": 0.034423828125,
      "learning_rate": 9.919313739019005e-07,
      "loss": 0.0014,
      "reward": 1.75,
      "reward_std": 0.0,
      "rewards/accuracy_reward": 0.625,
      "rewards/format_reward": 1.0,
      "step": 1883,
      "temperature": 1.0
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.375,
      "completion_length": 356.5625,
      "epoch": 0.057292300206787494,
      "grad_norm": 0.4071381724904059,
      "kl": 0.033447265625,
      "learning_rate": 9.919228248116979e-07,
      "loss": 0.0013,
      "reward": 1.6375000476837158,
      "reward_std": 0.06943650543689728,
      "rewards/accuracy_reward": 0.53125,
      "rewards/format_reward": 1.0,
      "step": 1884,
      "temperature": 1.0
    },
    {
      "all_correct": 0.625,
      "all_wrong": 0.0,
      "completion_length": 359.625,
      "epoch": 0.05732271013258727,
      "grad_norm": 1.3221228163380951,
      "kl": 0.03271484375,
      "learning_rate": 9.919142712316908e-07,
      "loss": 0.0013,
      "reward": 1.8824599981307983,
      "reward_std": 0.10024935007095337,
      "rewards/accuracy_reward": 0.7137100100517273,
      "rewards/format_reward": 1.0,
      "step": 1885,
      "temperature": 1.0
    },
    {
      "all_correct": 0.875,
      "all_wrong": 0.0,
      "completion_length": 360.84375,
      "epoch": 0.05735312005838706,
      "grad_norm": 0.3438298259669171,
      "kl": 0.0302734375,
      "learning_rate": 9.91905713161957e-07,
      "loss": 0.0012,
      "reward": 2.1812500953674316,
      "reward_std": 0.0530330091714859,
      "rewards/accuracy_reward": 0.984375,
      "rewards/format_reward": 1.0,
      "step": 1886,
      "temperature": 1.0
    },
    {
      "all_correct": 0.625,
      "all_wrong": 0.125,
      "completion_length": 364.703125,
      "epoch": 0.05738352998418684,
      "grad_norm": 0.697426835202751,
      "kl": 0.03759765625,
      "learning_rate": 9.918971506025748e-07,
      "loss": 0.0015,
      "reward": 1.9042613506317139,
      "reward_std": 0.0547148659825325,
      "rewards/accuracy_reward": 0.7542614340782166,
      "rewards/format_reward": 1.0,
      "step": 1887,
      "temperature": 1.0
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.25,
      "completion_length": 391.25,
      "epoch": 0.05741393990998662,
      "grad_norm": 0.7603068597705075,
      "kl": 0.032470703125,
      "learning_rate": 9.918885835536224e-07,
      "loss": 0.0013,
      "reward": 1.788675308227539,
      "reward_std": 0.06308997422456741,
      "rewards/accuracy_reward": 0.6574252247810364,
      "rewards/format_reward": 1.0,
      "step": 1888,
      "temperature": 1.0
    },
    {
      "all_correct": 0.75,
      "all_wrong": 0.0,
      "completion_length": 384.96875,
      "epoch": 0.057444349835786404,
      "grad_norm": 1.2720786266932729,
      "kl": 0.034423828125,
      "learning_rate": 9.91880012015178e-07,
      "loss": 0.0014,
      "reward": 2.0269055366516113,
      "reward_std": 0.032083842903375626,
      "rewards/accuracy_reward": 0.8362805247306824,
      "rewards/format_reward": 1.0,
      "step": 1889,
      "temperature": 1.0
    },
    {
      "all_correct": 0.25,
      "all_wrong": 0.125,
      "completion_length": 376.46875,
      "epoch": 0.05747475976158618,
      "grad_norm": 1.1097446528975026,
      "kl": 0.0311279296875,
      "learning_rate": 9.918714359873196e-07,
      "loss": 0.0012,
      "reward": 1.5291284322738647,
      "reward_std": 0.21159903705120087,
      "rewards/accuracy_reward": 0.4385033845901489,
      "rewards/format_reward": 1.0,
      "step": 1890,
      "temperature": 1.0
    },
    {
      "all_correct": 0.75,
      "all_wrong": 0.125,
      "completion_length": 348.8125,
      "epoch": 0.05750516968738596,
      "grad_norm": 0.742983427881877,
      "kl": 0.03125,
      "learning_rate": 9.918628554701255e-07,
      "loss": 0.0013,
      "reward": 1.912500023841858,
      "reward_std": 0.0530330091714859,
      "rewards/accuracy_reward": 0.765625,
      "rewards/format_reward": 1.0,
      "step": 1891,
      "temperature": 1.0
    },
    {
      "all_correct": 0.75,
      "all_wrong": 0.0,
      "completion_length": 348.375,
      "epoch": 0.05753557961318574,
      "grad_norm": 0.8924434227276397,
      "kl": 0.0400390625,
      "learning_rate": 9.918542704636746e-07,
      "loss": 0.0016,
      "reward": 2.1175732612609863,
      "reward_std": 0.0632951632142067,
      "rewards/accuracy_reward": 0.9206979870796204,
      "rewards/format_reward": 1.0,
      "step": 1892,
      "temperature": 1.0
    },
    {
      "all_correct": 0.75,
      "all_wrong": 0.125,
      "completion_length": 358.796875,
      "epoch": 0.05756598953898553,
      "grad_norm": 0.3597485326232882,
      "kl": 0.034423828125,
      "learning_rate": 9.918456809680444e-07,
      "loss": 0.0014,
      "reward": 1.953125,
      "reward_std": 0.07372426986694336,
      "rewards/accuracy_reward": 0.796875,
      "rewards/format_reward": 1.0,
      "step": 1893,
      "temperature": 1.0
    },
    {
      "all_correct": 0.625,
      "all_wrong": 0.0,
      "completion_length": 384.390625,
      "epoch": 0.05759639946478531,
      "grad_norm": 1.4960860461058496,
      "kl": 0.029052734375,
      "learning_rate": 9.91837086983314e-07,
      "loss": 0.0012,
      "reward": 1.9725404977798462,
      "reward_std": 0.1434636116027832,
      "rewards/accuracy_reward": 0.8100404143333435,
      "rewards/format_reward": 1.0,
      "step": 1894,
      "temperature": 1.0
    },
    {
      "all_correct": 0.375,
      "all_wrong": 0.25,
      "completion_length": 366.21875,
      "epoch": 0.057626809390585086,
      "grad_norm": 0.9198639198174171,
      "kl": 0.02783203125,
      "learning_rate": 9.918284885095614e-07,
      "loss": 0.0011,
      "reward": 1.578125,
      "reward_std": 0.19380906224250793,
      "rewards/accuracy_reward": 0.484375,
      "rewards/format_reward": 1.0,
      "step": 1895,
      "temperature": 1.0
    },
    {
      "all_correct": 0.25,
      "all_wrong": 0.375,
      "completion_length": 372.015625,
      "epoch": 0.057657219316384865,
      "grad_norm": 1.7578506511545606,
      "kl": 0.0289306640625,
      "learning_rate": 9.918198855468652e-07,
      "loss": 0.0012,
      "reward": 1.428168773651123,
      "reward_std": 0.06693951785564423,
      "rewards/accuracy_reward": 0.35316866636276245,
      "rewards/format_reward": 1.0,
      "step": 1896,
      "temperature": 1.0
    },
    {
      "all_correct": 0.75,
      "all_wrong": 0.125,
      "completion_length": 346.125,
      "epoch": 0.05768762924218465,
      "grad_norm": 0.8962215786927146,
      "kl": 0.03173828125,
      "learning_rate": 9.91811278095304e-07,
      "loss": 0.0013,
      "reward": 2.0250000953674316,
      "reward_std": 0.070710688829422,
      "rewards/accuracy_reward": 0.859375,
      "rewards/format_reward": 1.0,
      "step": 1897,
      "temperature": 1.0
    },
    {
      "all_correct": 0.625,
      "all_wrong": 0.0,
      "completion_length": 343.890625,
      "epoch": 0.05771803916798443,
      "grad_norm": 1.8427826830397054,
      "kl": 0.03662109375,
      "learning_rate": 9.918026661549561e-07,
      "loss": 0.0015,
      "reward": 2.0277183055877686,
      "reward_std": 0.10206834971904755,
      "rewards/accuracy_reward": 0.8339681625366211,
      "rewards/format_reward": 1.0,
      "step": 1898,
      "temperature": 1.0
    },
    {
      "all_correct": 0.375,
      "all_wrong": 0.375,
      "completion_length": 358.40625,
      "epoch": 0.05774844909378421,
      "grad_norm": 1.0199748147036032,
      "kl": 0.027587890625,
      "learning_rate": 9.917940497259003e-07,
      "loss": 0.0011,
      "reward": 1.5790156126022339,
      "reward_std": 0.07046148926019669,
      "rewards/accuracy_reward": 0.4821406900882721,
      "rewards/format_reward": 1.0,
      "step": 1899,
      "temperature": 1.0
    },
    {
      "all_correct": 0.875,
      "all_wrong": 0.0,
      "completion_length": 345.109375,
      "epoch": 0.05777885901958399,
      "grad_norm": 0.7844493641141327,
      "kl": 0.0380859375,
      "learning_rate": 9.917854288082154e-07,
      "loss": 0.0015,
      "reward": 2.105393886566162,
      "reward_std": 0.021596401929855347,
      "rewards/accuracy_reward": 0.9116440415382385,
      "rewards/format_reward": 1.0,
      "step": 1900,
      "temperature": 1.0
    },
    {
      "all_correct": 0.75,
      "all_wrong": 0.0,
      "completion_length": 348.125,
      "epoch": 0.057809268945383775,
      "grad_norm": 0.8513497946067383,
      "kl": 0.0306396484375,
      "learning_rate": 9.9177680340198e-07,
      "loss": 0.0012,
      "reward": 2.09395170211792,
      "reward_std": 0.021317126229405403,
      "rewards/accuracy_reward": 0.8939515948295593,
      "rewards/format_reward": 1.0,
      "step": 1901,
      "temperature": 1.0
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.0,
      "completion_length": 365.34375,
      "epoch": 0.057839678871183554,
      "grad_norm": 1.2822183774256382,
      "kl": 0.031494140625,
      "learning_rate": 9.917681735072726e-07,
      "loss": 0.0013,
      "reward": 1.9283008575439453,
      "reward_std": 0.12729044258594513,
      "rewards/accuracy_reward": 0.7501758337020874,
      "rewards/format_reward": 1.0,
      "step": 1902,
      "temperature": 1.0
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.0,
      "completion_length": 376.265625,
      "epoch": 0.057870088796983334,
      "grad_norm": 1.1855024797954445,
      "kl": 0.036376953125,
      "learning_rate": 9.917595391241721e-07,
      "loss": 0.0015,
      "reward": 1.8624359369277954,
      "reward_std": 0.04997137933969498,
      "rewards/accuracy_reward": 0.67806077003479,
      "rewards/format_reward": 1.0,
      "step": 1903,
      "temperature": 1.0
    },
    {
      "all_correct": 0.75,
      "all_wrong": 0.0,
      "completion_length": 356.828125,
      "epoch": 0.05790049872278312,
      "grad_norm": 1.6942335084396216,
      "kl": 0.0361328125,
      "learning_rate": 9.917509002527575e-07,
      "loss": 0.0014,
      "reward": 2.035306930541992,
      "reward_std": 0.12590652704238892,
      "rewards/accuracy_reward": 0.8603069186210632,
      "rewards/format_reward": 1.0,
      "step": 1904,
      "temperature": 1.0
    },
    {
      "all_correct": 0.625,
      "all_wrong": 0.0,
      "completion_length": 362.34375,
      "epoch": 0.0579309086485829,
      "grad_norm": 0.8028863580163638,
      "kl": 0.026123046875,
      "learning_rate": 9.917422568931075e-07,
      "loss": 0.001,
      "reward": 1.9750001430511475,
      "reward_std": 0.235443115234375,
      "rewards/accuracy_reward": 0.8125,
      "rewards/format_reward": 1.0,
      "step": 1905,
      "temperature": 1.0
    },
    {
      "all_correct": 0.375,
      "all_wrong": 0.25,
      "completion_length": 373.171875,
      "epoch": 0.05796131857438268,
      "grad_norm": 0.6193118223896407,
      "kl": 0.02978515625,
      "learning_rate": 9.917336090453008e-07,
      "loss": 0.0012,
      "reward": 1.600000023841858,
      "reward_std": 0.2220800668001175,
      "rewards/accuracy_reward": 0.515625,
      "rewards/format_reward": 0.984375,
      "step": 1906,
      "temperature": 1.0
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.125,
      "completion_length": 379.078125,
      "epoch": 0.05799172850018246,
      "grad_norm": 1.1171733928028575,
      "kl": 0.03076171875,
      "learning_rate": 9.917249567094164e-07,
      "loss": 0.0012,
      "reward": 1.8750169277191162,
      "reward_std": 0.0764056071639061,
      "rewards/accuracy_reward": 0.7093918919563293,
      "rewards/format_reward": 1.0,
      "step": 1907,
      "temperature": 1.0
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.125,
      "completion_length": 350.75,
      "epoch": 0.05802213842598224,
      "grad_norm": 0.972485497035434,
      "kl": 0.03662109375,
      "learning_rate": 9.917162998855335e-07,
      "loss": 0.0015,
      "reward": 1.7945833206176758,
      "reward_std": 0.09081462025642395,
      "rewards/accuracy_reward": 0.6539583206176758,
      "rewards/format_reward": 1.0,
      "step": 1908,
      "temperature": 1.0
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.0,
      "completion_length": 384.546875,
      "epoch": 0.05805254835178202,
      "grad_norm": 2.3575955652391416,
      "kl": 0.0289306640625,
      "learning_rate": 9.917076385737311e-07,
      "loss": 0.0012,
      "reward": 1.9692280292510986,
      "reward_std": 0.14977966248989105,
      "rewards/accuracy_reward": 0.7879780530929565,
      "rewards/format_reward": 1.0,
      "step": 1909,
      "temperature": 1.0
    },
    {
      "all_correct": 0.625,
      "all_wrong": 0.125,
      "completion_length": 374.0,
      "epoch": 0.0580829582775818,
      "grad_norm": 0.9416126752498891,
      "kl": 0.03662109375,
      "learning_rate": 9.916989727740878e-07,
      "loss": 0.0015,
      "reward": 1.8093750476837158,
      "reward_std": 0.18150544166564941,
      "rewards/accuracy_reward": 0.703125,
      "rewards/format_reward": 0.984375,
      "step": 1910,
      "temperature": 1.0
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.25,
      "completion_length": 366.234375,
      "epoch": 0.05811336820338158,
      "grad_norm": 0.6814228686218095,
      "kl": 0.0294189453125,
      "learning_rate": 9.916903024866833e-07,
      "loss": 0.0012,
      "reward": 1.734375,
      "reward_std": 0.06568655371665955,
      "rewards/accuracy_reward": 0.609375,
      "rewards/format_reward": 1.0,
      "step": 1911,
      "temperature": 1.0
    },
    {
      "all_correct": 0.375,
      "all_wrong": 0.0,
      "completion_length": 368.421875,
      "epoch": 0.05814377812918137,
      "grad_norm": 1.3087947491934386,
      "kl": 0.030517578125,
      "learning_rate": 9.916816277115963e-07,
      "loss": 0.0012,
      "reward": 1.7895748615264893,
      "reward_std": 0.23183944821357727,
      "rewards/accuracy_reward": 0.6364498138427734,
      "rewards/format_reward": 1.0,
      "step": 1912,
      "temperature": 1.0
    },
    {
      "all_correct": 0.625,
      "all_wrong": 0.0,
      "completion_length": 359.3125,
      "epoch": 0.058174188054981146,
      "grad_norm": 1.089610792522334,
      "kl": 0.033203125,
      "learning_rate": 9.916729484489062e-07,
      "loss": 0.0013,
      "reward": 1.93362295627594,
      "reward_std": 0.04842543601989746,
      "rewards/accuracy_reward": 0.7648729085922241,
      "rewards/format_reward": 1.0,
      "step": 1913,
      "temperature": 1.0
    },
    {
      "all_correct": 0.75,
      "all_wrong": 0.125,
      "completion_length": 340.359375,
      "epoch": 0.058204597980780926,
      "grad_norm": 1.7154099383940173,
      "kl": 0.03955078125,
      "learning_rate": 9.916642646986922e-07,
      "loss": 0.0016,
      "reward": 2.028125047683716,
      "reward_std": 0.06187184900045395,
      "rewards/accuracy_reward": 0.859375,
      "rewards/format_reward": 1.0,
      "step": 1914,
      "temperature": 1.0
    },
    {
      "all_correct": 0.25,
      "all_wrong": 0.0,
      "completion_length": 380.46875,
      "epoch": 0.058235007906580705,
      "grad_norm": 1.4605282242671804,
      "kl": 0.0263671875,
      "learning_rate": 9.916555764610332e-07,
      "loss": 0.0011,
      "reward": 1.6188099384307861,
      "reward_std": 0.25562745332717896,
      "rewards/accuracy_reward": 0.4875600039958954,
      "rewards/format_reward": 1.0,
      "step": 1915,
      "temperature": 1.0
    },
    {
      "all_correct": 0.375,
      "all_wrong": 0.0,
      "completion_length": 365.953125,
      "epoch": 0.05826541783238049,
      "grad_norm": 1.6940972369812064,
      "kl": 0.03662109375,
      "learning_rate": 9.91646883736009e-07,
      "loss": 0.0015,
      "reward": 1.7356996536254883,
      "reward_std": 0.042403820902109146,
      "rewards/accuracy_reward": 0.5669495463371277,
      "rewards/format_reward": 1.0,
      "step": 1916,
      "temperature": 1.0
    },
    {
      "all_correct": 0.625,
      "all_wrong": 0.25,
      "completion_length": 335.171875,
      "epoch": 0.05829582775818027,
      "grad_norm": 6.254087126604567,
      "kl": 0.048095703125,
      "learning_rate": 9.916381865236989e-07,
      "loss": 0.0019,
      "reward": 1.859375,
      "reward_std": 0.06805657595396042,
      "rewards/accuracy_reward": 0.71875,
      "rewards/format_reward": 1.0,
      "step": 1917,
      "temperature": 1.0
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.25,
      "completion_length": 358.5,
      "epoch": 0.05832623768398005,
      "grad_norm": 0.5788029293989937,
      "kl": 0.02783203125,
      "learning_rate": 9.916294848241819e-07,
      "loss": 0.0011,
      "reward": 1.7988590002059937,
      "reward_std": 0.0588177852332592,
      "rewards/accuracy_reward": 0.6519839763641357,
      "rewards/format_reward": 1.0,
      "step": 1918,
      "temperature": 1.0
    },
    {
      "all_correct": 0.375,
      "all_wrong": 0.25,
      "completion_length": 377.40625,
      "epoch": 0.058356647609779835,
      "grad_norm": 1.5719701391524767,
      "kl": 0.0380859375,
      "learning_rate": 9.916207786375377e-07,
      "loss": 0.0015,
      "reward": 1.7020118236541748,
      "reward_std": 0.03771716356277466,
      "rewards/accuracy_reward": 0.5551367402076721,
      "rewards/format_reward": 1.0,
      "step": 1919,
      "temperature": 1.0
    },
    {
      "all_correct": 0.625,
      "all_wrong": 0.25,
      "completion_length": 360.046875,
      "epoch": 0.058387057535579615,
      "grad_norm": 1.1006374956824891,
      "kl": 0.04052734375,
      "learning_rate": 9.916120679638456e-07,
      "loss": 0.0016,
      "reward": 1.7598072290420532,
      "reward_std": 0.03736592084169388,
      "rewards/accuracy_reward": 0.6348072290420532,
      "rewards/format_reward": 1.0,
      "step": 1920,
      "temperature": 1.0
    },
    {
      "all_correct": 0.375,
      "all_wrong": 0.0,
      "completion_length": 348.328125,
      "epoch": 0.058417467461379394,
      "grad_norm": 1.4631790548379138,
      "kl": 0.03369140625,
      "learning_rate": 9.916033528031853e-07,
      "loss": 0.0013,
      "reward": 1.846264123916626,
      "reward_std": 0.1404450386762619,
      "rewards/accuracy_reward": 0.6806390285491943,
      "rewards/format_reward": 1.0,
      "step": 1921,
      "temperature": 1.0
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.375,
      "completion_length": 377.21875,
      "epoch": 0.05844787738717917,
      "grad_norm": 0.5298400163797515,
      "kl": 0.033935546875,
      "learning_rate": 9.915946331556362e-07,
      "loss": 0.0014,
      "reward": 1.6437499523162842,
      "reward_std": 0.07353248447179794,
      "rewards/accuracy_reward": 0.546875,
      "rewards/format_reward": 1.0,
      "step": 1922,
      "temperature": 1.0
    },
    {
      "all_correct": 1.0,
      "all_wrong": 0.0,
      "completion_length": 349.265625,
      "epoch": 0.05847828731297896,
      "grad_norm": 2.9732511633120375,
      "kl": 0.0439453125,
      "learning_rate": 9.915859090212779e-07,
      "loss": 0.0018,
      "reward": 2.1839284896850586,
      "reward_std": 0.02880534529685974,
      "rewards/accuracy_reward": 0.9933035969734192,
      "rewards/format_reward": 1.0,
      "step": 1923,
      "temperature": 1.0
    },
    {
      "all_correct": 0.75,
      "all_wrong": 0.0,
      "completion_length": 345.828125,
      "epoch": 0.05850869723877874,
      "grad_norm": 0.6937139034444461,
      "kl": 0.041259765625,
      "learning_rate": 9.915771804001902e-07,
      "loss": 0.0017,
      "reward": 2.03125,
      "reward_std": 0.14706888794898987,
      "rewards/accuracy_reward": 0.859375,
      "rewards/format_reward": 1.0,
      "step": 1924,
      "temperature": 1.0
    },
    {
      "all_correct": 0.75,
      "all_wrong": 0.0,
      "completion_length": 334.0625,
      "epoch": 0.05853910716457852,
      "grad_norm": 4.768468154562458,
      "kl": 0.0478515625,
      "learning_rate": 9.915684472924527e-07,
      "loss": 0.0019,
      "reward": 2.1249351501464844,
      "reward_std": 0.11453960835933685,
      "rewards/accuracy_reward": 0.9405601024627686,
      "rewards/format_reward": 1.0,
      "step": 1925,
      "temperature": 1.0
    },
    {
      "all_correct": 0.75,
      "all_wrong": 0.25,
      "completion_length": 353.703125,
      "epoch": 0.0585695170903783,
      "grad_norm": 0.06815154368267241,
      "kl": 0.035888671875,
      "learning_rate": 9.915597096981447e-07,
      "loss": 0.0014,
      "reward": 1.9000000953674316,
      "reward_std": 0.0,
      "rewards/accuracy_reward": 0.75,
      "rewards/format_reward": 1.0,
      "step": 1926,
      "temperature": 1.0
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.125,
      "completion_length": 370.234375,
      "epoch": 0.05859992701617808,
      "grad_norm": 0.6822074231209386,
      "kl": 0.0302734375,
      "learning_rate": 9.915509676173463e-07,
      "loss": 0.0012,
      "reward": 1.8250000476837158,
      "reward_std": 0.2222006767988205,
      "rewards/accuracy_reward": 0.703125,
      "rewards/format_reward": 0.984375,
      "step": 1927,
      "temperature": 1.0
    },
    {
      "all_correct": 0.375,
      "all_wrong": 0.25,
      "completion_length": 340.9375,
      "epoch": 0.05863033694197786,
      "grad_norm": 1.349772442957914,
      "kl": 0.04052734375,
      "learning_rate": 9.915422210501375e-07,
      "loss": 0.0016,
      "reward": 1.6343750953674316,
      "reward_std": 0.21926461160182953,
      "rewards/accuracy_reward": 0.53125,
      "rewards/format_reward": 1.0,
      "step": 1928,
      "temperature": 1.0
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.25,
      "completion_length": 355.421875,
      "epoch": 0.05866074686777764,
      "grad_norm": 0.5661528089209161,
      "kl": 0.0291748046875,
      "learning_rate": 9.91533469996598e-07,
      "loss": 0.0012,
      "reward": 1.8465278148651123,
      "reward_std": 0.0530330091714859,
      "rewards/accuracy_reward": 0.6996527910232544,
      "rewards/format_reward": 1.0,
      "step": 1929,
      "temperature": 1.0
    },
    {
      "all_correct": 0.375,
      "all_wrong": 0.375,
      "completion_length": 399.515625,
      "epoch": 0.05869115679357742,
      "grad_norm": 1.0536658473140443,
      "kl": 0.035400390625,
      "learning_rate": 9.915247144568072e-07,
      "loss": 0.0014,
      "reward": 1.5600395202636719,
      "reward_std": 0.09187215566635132,
      "rewards/accuracy_reward": 0.46316447854042053,
      "rewards/format_reward": 1.0,
      "step": 1930,
      "temperature": 1.0
    },
    {
      "all_correct": 0.625,
      "all_wrong": 0.125,
      "completion_length": 359.984375,
      "epoch": 0.058721566719377206,
      "grad_norm": 1.0803966285212137,
      "kl": 0.039794921875,
      "learning_rate": 9.915159544308457e-07,
      "loss": 0.0016,
      "reward": 1.9145196676254272,
      "reward_std": 0.08712279796600342,
      "rewards/accuracy_reward": 0.7520195245742798,
      "rewards/format_reward": 1.0,
      "step": 1931,
      "temperature": 1.0
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.0,
      "completion_length": 381.453125,
      "epoch": 0.058751976645176986,
      "grad_norm": 1.7890682422940305,
      "kl": 0.03173828125,
      "learning_rate": 9.915071899187928e-07,
      "loss": 0.0013,
      "reward": 1.9411742687225342,
      "reward_std": 0.10596342384815216,
      "rewards/accuracy_reward": 0.7567992210388184,
      "rewards/format_reward": 1.0,
      "step": 1932,
      "temperature": 1.0
    },
    {
      "all_correct": 0.75,
      "all_wrong": 0.0,
      "completion_length": 363.984375,
      "epoch": 0.058782386570976765,
      "grad_norm": 4.275883135800628,
      "kl": 0.045166015625,
      "learning_rate": 9.91498420920729e-07,
      "loss": 0.0018,
      "reward": 2.0919463634490967,
      "reward_std": 0.026878736913204193,
      "rewards/accuracy_reward": 0.8950713276863098,
      "rewards/format_reward": 1.0,
      "step": 1933,
      "temperature": 1.0
    },
    {
      "all_correct": 0.625,
      "all_wrong": 0.0,
      "completion_length": 361.40625,
      "epoch": 0.05881279649677655,
      "grad_norm": 1.5820421822262587,
      "kl": 0.04443359375,
      "learning_rate": 9.914896474367342e-07,
      "loss": 0.0018,
      "reward": 2.0290799140930176,
      "reward_std": 0.14544382691383362,
      "rewards/accuracy_reward": 0.8478297591209412,
      "rewards/format_reward": 1.0,
      "step": 1934,
      "temperature": 1.0
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.125,
      "completion_length": 385.140625,
      "epoch": 0.05884320642257633,
      "grad_norm": 1.1529414658385009,
      "kl": 0.04052734375,
      "learning_rate": 9.914808694668883e-07,
      "loss": 0.0016,
      "reward": 1.892958641052246,
      "reward_std": 0.15377146005630493,
      "rewards/accuracy_reward": 0.7460835576057434,
      "rewards/format_reward": 1.0,
      "step": 1935,
      "temperature": 1.0
    },
    {
      "all_correct": 0.375,
      "all_wrong": 0.25,
      "completion_length": 368.9375,
      "epoch": 0.05887361634837611,
      "grad_norm": 0.9532487787940221,
      "kl": 0.03369140625,
      "learning_rate": 9.914720870112717e-07,
      "loss": 0.0013,
      "reward": 1.615625023841858,
      "reward_std": 0.183067187666893,
      "rewards/accuracy_reward": 0.515625,
      "rewards/format_reward": 1.0,
      "step": 1936,
      "temperature": 1.0
    },
    {
      "all_correct": 0.75,
      "all_wrong": 0.125,
      "completion_length": 348.5625,
      "epoch": 0.05890402627417589,
      "grad_norm": 0.5182027767039996,
      "kl": 0.037109375,
      "learning_rate": 9.914633000699643e-07,
      "loss": 0.0015,
      "reward": 1.9623512029647827,
      "reward_std": 0.017505919560790062,
      "rewards/accuracy_reward": 0.7873511910438538,
      "rewards/format_reward": 1.0,
      "step": 1937,
      "temperature": 1.0
    },
    {
      "all_correct": 0.375,
      "all_wrong": 0.25,
      "completion_length": 363.640625,
      "epoch": 0.058934436199975675,
      "grad_norm": 0.718950047998924,
      "kl": 0.03564453125,
      "learning_rate": 9.914545086430466e-07,
      "loss": 0.0014,
      "reward": 1.804757833480835,
      "reward_std": 0.12973397970199585,
      "rewards/accuracy_reward": 0.6641327142715454,
      "rewards/format_reward": 1.0,
      "step": 1938,
      "temperature": 1.0
    },
    {
      "all_correct": 0.375,
      "all_wrong": 0.25,
      "completion_length": 397.546875,
      "epoch": 0.058964846125775454,
      "grad_norm": 0.8850242151250404,
      "kl": 0.036865234375,
      "learning_rate": 9.914457127305985e-07,
      "loss": 0.0015,
      "reward": 1.7022138833999634,
      "reward_std": 0.08681733906269073,
      "rewards/accuracy_reward": 0.5740888714790344,
      "rewards/format_reward": 1.0,
      "step": 1939,
      "temperature": 1.0
    },
    {
      "all_correct": 0.25,
      "all_wrong": 0.125,
      "completion_length": 389.84375,
      "epoch": 0.05899525605157523,
      "grad_norm": 1.2719879470450386,
      "kl": 0.03271484375,
      "learning_rate": 9.914369123327004e-07,
      "loss": 0.0013,
      "reward": 1.7510440349578857,
      "reward_std": 0.16377565264701843,
      "rewards/accuracy_reward": 0.6041690707206726,
      "rewards/format_reward": 1.0,
      "step": 1940,
      "temperature": 1.0
    },
    {
      "all_correct": 0.875,
      "all_wrong": 0.125,
      "completion_length": 339.953125,
      "epoch": 0.05902566597737501,
      "grad_norm": 0.06809387626321121,
      "kl": 0.04541015625,
      "learning_rate": 9.914281074494329e-07,
      "loss": 0.0018,
      "reward": 2.0500001907348633,
      "reward_std": 0.0,
      "rewards/accuracy_reward": 0.875,
      "rewards/format_reward": 1.0,
      "step": 1941,
      "temperature": 1.0
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.25,
      "completion_length": 367.90625,
      "epoch": 0.0590560759031748,
      "grad_norm": 0.9466723355131045,
      "kl": 0.03466796875,
      "learning_rate": 9.914192980808758e-07,
      "loss": 0.0014,
      "reward": 1.8051339387893677,
      "reward_std": 0.13636811077594757,
      "rewards/accuracy_reward": 0.6707589626312256,
      "rewards/format_reward": 1.0,
      "step": 1942,
      "temperature": 1.0
    },
    {
      "all_correct": 0.375,
      "all_wrong": 0.0,
      "completion_length": 386.453125,
      "epoch": 0.05908648582897458,
      "grad_norm": 1.5251316131290986,
      "kl": 0.040283203125,
      "learning_rate": 9.914104842271101e-07,
      "loss": 0.0016,
      "reward": 1.8705720901489258,
      "reward_std": 0.147018164396286,
      "rewards/accuracy_reward": 0.7143219709396362,
      "rewards/format_reward": 1.0,
      "step": 1943,
      "temperature": 1.0
    },
    {
      "all_correct": 0.375,
      "all_wrong": 0.125,
      "completion_length": 396.15625,
      "epoch": 0.05911689575477436,
      "grad_norm": 1.6906761069258769,
      "kl": 0.041259765625,
      "learning_rate": 9.914016658882158e-07,
      "loss": 0.0017,
      "reward": 1.7677013874053955,
      "reward_std": 0.15818242728710175,
      "rewards/accuracy_reward": 0.6302014589309692,
      "rewards/format_reward": 1.0,
      "step": 1944,
      "temperature": 1.0
    },
    {
      "all_correct": 0.875,
      "all_wrong": 0.0,
      "completion_length": 349.984375,
      "epoch": 0.059147305680574136,
      "grad_norm": 0.46971376991558067,
      "kl": 0.04052734375,
      "learning_rate": 9.913928430642734e-07,
      "loss": 0.0016,
      "reward": 2.13149356842041,
      "reward_std": 0.005983040202409029,
      "rewards/accuracy_reward": 0.9314936399459839,
      "rewards/format_reward": 1.0,
      "step": 1945,
      "temperature": 1.0
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.25,
      "completion_length": 353.53125,
      "epoch": 0.05917771560637392,
      "grad_norm": 1.6114911660061315,
      "kl": 0.042724609375,
      "learning_rate": 9.91384015755364e-07,
      "loss": 0.0017,
      "reward": 1.6861538887023926,
      "reward_std": 0.024565791711211205,
      "rewards/accuracy_reward": 0.5486539006233215,
      "rewards/format_reward": 1.0,
      "step": 1946,
      "temperature": 1.0
    },
    {
      "all_correct": 0.625,
      "all_wrong": 0.0,
      "completion_length": 385.8125,
      "epoch": 0.0592081255321737,
      "grad_norm": 0.7909405850546506,
      "kl": 0.045166015625,
      "learning_rate": 9.913751839615673e-07,
      "loss": 0.0018,
      "reward": 1.8833873271942139,
      "reward_std": 0.07349240034818649,
      "rewards/accuracy_reward": 0.7240123748779297,
      "rewards/format_reward": 0.984375,
      "step": 1947,
      "temperature": 1.0
    },
    {
      "all_correct": 0.625,
      "all_wrong": 0.375,
      "completion_length": 340.578125,
      "epoch": 0.05923853545797348,
      "grad_norm": 0.4588488007189282,
      "kl": 0.041748046875,
      "learning_rate": 9.913663476829645e-07,
      "loss": 0.0017,
      "reward": 1.7468750476837158,
      "reward_std": 0.008838837966322899,
      "rewards/accuracy_reward": 0.625,
      "rewards/format_reward": 1.0,
      "step": 1948,
      "temperature": 1.0
    },
    {
      "all_correct": 0.375,
      "all_wrong": 0.25,
      "completion_length": 361.5625,
      "epoch": 0.05926894538377327,
      "grad_norm": 4.684657630115788,
      "kl": 0.03759765625,
      "learning_rate": 9.913575069196363e-07,
      "loss": 0.0015,
      "reward": 1.7546768188476562,
      "reward_std": 0.035466305911540985,
      "rewards/accuracy_reward": 0.6046769618988037,
      "rewards/format_reward": 1.0,
      "step": 1949,
      "temperature": 1.0
    },
    {
      "all_correct": 0.375,
      "all_wrong": 0.125,
      "completion_length": 365.375,
      "epoch": 0.059299355309573046,
      "grad_norm": 2.1722017627324415,
      "kl": 0.048095703125,
      "learning_rate": 9.91348661671663e-07,
      "loss": 0.0019,
      "reward": 1.660821557044983,
      "reward_std": 0.12771271169185638,
      "rewards/accuracy_reward": 0.5201965570449829,
      "rewards/format_reward": 1.0,
      "step": 1950,
      "temperature": 1.0
    },
    {
      "all_correct": 0.875,
      "all_wrong": 0.125,
      "completion_length": 350.109375,
      "epoch": 0.059329765235372825,
      "grad_norm": 0.06402290048245014,
      "kl": 0.040283203125,
      "learning_rate": 9.913398119391256e-07,
      "loss": 0.0016,
      "reward": 2.0500001907348633,
      "reward_std": 0.0,
      "rewards/accuracy_reward": 0.875,
      "rewards/format_reward": 1.0,
      "step": 1951,
      "temperature": 1.0
    },
    {
      "all_correct": 0.25,
      "all_wrong": 0.0,
      "completion_length": 363.1875,
      "epoch": 0.059360175161172604,
      "grad_norm": 3.8520892959687667,
      "kl": 0.039794921875,
      "learning_rate": 9.913309577221048e-07,
      "loss": 0.0016,
      "reward": 1.764976978302002,
      "reward_std": 0.2561027705669403,
      "rewards/accuracy_reward": 0.6181020140647888,
      "rewards/format_reward": 1.0,
      "step": 1952,
      "temperature": 1.0
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.125,
      "completion_length": 393.09375,
      "epoch": 0.05939058508697239,
      "grad_norm": 0.9379537163565117,
      "kl": 0.0361328125,
      "learning_rate": 9.913220990206813e-07,
      "loss": 0.0014,
      "reward": 1.7286500930786133,
      "reward_std": 0.13317827880382538,
      "rewards/accuracy_reward": 0.6036500334739685,
      "rewards/format_reward": 1.0,
      "step": 1953,
      "temperature": 1.0
    },
    {
      "all_correct": 0.875,
      "all_wrong": 0.0,
      "completion_length": 344.828125,
      "epoch": 0.05942099501277217,
      "grad_norm": 0.6042287195765036,
      "kl": 0.049072265625,
      "learning_rate": 9.91313235834936e-07,
      "loss": 0.002,
      "reward": 2.1427083015441895,
      "reward_std": 0.08057864755392075,
      "rewards/accuracy_reward": 0.9520833492279053,
      "rewards/format_reward": 1.0,
      "step": 1954,
      "temperature": 1.0
    },
    {
      "all_correct": 0.375,
      "all_wrong": 0.125,
      "completion_length": 387.1875,
      "epoch": 0.05945140493857195,
      "grad_norm": 1.603273903753444,
      "kl": 0.037109375,
      "learning_rate": 9.913043681649502e-07,
      "loss": 0.0015,
      "reward": 1.6594336032867432,
      "reward_std": 0.028177479282021523,
      "rewards/accuracy_reward": 0.5125585794448853,
      "rewards/format_reward": 1.0,
      "step": 1955,
      "temperature": 1.0
    },
    {
      "all_correct": 0.25,
      "all_wrong": 0.25,
      "completion_length": 367.84375,
      "epoch": 0.05948181486437173,
      "grad_norm": 0.9216119961149345,
      "kl": 0.04736328125,
      "learning_rate": 9.912954960108042e-07,
      "loss": 0.0019,
      "reward": 1.6091248989105225,
      "reward_std": 0.18067726492881775,
      "rewards/accuracy_reward": 0.4903748333454132,
      "rewards/format_reward": 1.0,
      "step": 1956,
      "temperature": 1.0
    },
    {
      "all_correct": 0.25,
      "all_wrong": 0.25,
      "completion_length": 396.59375,
      "epoch": 0.059512224790171514,
      "grad_norm": 1.8395779007242576,
      "kl": 0.03515625,
      "learning_rate": 9.912866193725795e-07,
      "loss": 0.0014,
      "reward": 1.501940131187439,
      "reward_std": 0.1749444603919983,
      "rewards/accuracy_reward": 0.39569011330604553,
      "rewards/format_reward": 1.0,
      "step": 1957,
      "temperature": 1.0
    },
    {
      "all_correct": 0.25,
      "all_wrong": 0.0,
      "completion_length": 386.671875,
      "epoch": 0.05954263471597129,
      "grad_norm": 1.441771828459778,
      "kl": 0.03857421875,
      "learning_rate": 9.912777382503565e-07,
      "loss": 0.0015,
      "reward": 1.822148084640503,
      "reward_std": 0.1737963706254959,
      "rewards/accuracy_reward": 0.6565229892730713,
      "rewards/format_reward": 1.0,
      "step": 1958,
      "temperature": 1.0
    },
    {
      "all_correct": 0.625,
      "all_wrong": 0.0,
      "completion_length": 362.515625,
      "epoch": 0.05957304464177107,
      "grad_norm": 1.0875873324737508,
      "kl": 0.040771484375,
      "learning_rate": 9.91268852644217e-07,
      "loss": 0.0016,
      "reward": 1.97079598903656,
      "reward_std": 0.11148596554994583,
      "rewards/accuracy_reward": 0.8020459413528442,
      "rewards/format_reward": 1.0,
      "step": 1959,
      "temperature": 1.0
    },
    {
      "all_correct": 0.75,
      "all_wrong": 0.0,
      "completion_length": 359.53125,
      "epoch": 0.05960345456757086,
      "grad_norm": 1.5087855442379052,
      "kl": 0.041015625,
      "learning_rate": 9.912599625542416e-07,
      "loss": 0.0016,
      "reward": 1.9784926176071167,
      "reward_std": 0.06187184900045395,
      "rewards/accuracy_reward": 0.8097426891326904,
      "rewards/format_reward": 1.0,
      "step": 1960,
      "temperature": 1.0
    },
    {
      "all_correct": 0.625,
      "all_wrong": 0.25,
      "completion_length": 350.96875,
      "epoch": 0.05963386449337064,
      "grad_norm": 0.6169738650856209,
      "kl": 0.0439453125,
      "learning_rate": 9.912510679805116e-07,
      "loss": 0.0018,
      "reward": 1.7751202583312988,
      "reward_std": 0.014631202444434166,
      "rewards/accuracy_reward": 0.6376201510429382,
      "rewards/format_reward": 1.0,
      "step": 1961,
      "temperature": 1.0
    },
    {
      "all_correct": 0.375,
      "all_wrong": 0.25,
      "completion_length": 378.796875,
      "epoch": 0.05966427441917042,
      "grad_norm": 1.2295601976912733,
      "kl": 0.0322265625,
      "learning_rate": 9.912421689231082e-07,
      "loss": 0.0013,
      "reward": 1.6150445938110352,
      "reward_std": 0.16728758811950684,
      "rewards/accuracy_reward": 0.518169641494751,
      "rewards/format_reward": 1.0,
      "step": 1962,
      "temperature": 1.0
    },
    {
      "all_correct": 0.75,
      "all_wrong": 0.125,
      "completion_length": 346.09375,
      "epoch": 0.059694684344970196,
      "grad_norm": 0.4205179484664445,
      "kl": 0.037841796875,
      "learning_rate": 9.912332653821124e-07,
      "loss": 0.0015,
      "reward": 1.9937500953674316,
      "reward_std": 0.077632375061512,
      "rewards/accuracy_reward": 0.828125,
      "rewards/format_reward": 1.0,
      "step": 1963,
      "temperature": 1.0
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.125,
      "completion_length": 362.46875,
      "epoch": 0.05972509427076998,
      "grad_norm": 1.0197033484652347,
      "kl": 0.04345703125,
      "learning_rate": 9.91224357357606e-07,
      "loss": 0.0017,
      "reward": 1.9127107858657837,
      "reward_std": 0.12639778852462769,
      "rewards/accuracy_reward": 0.7470858097076416,
      "rewards/format_reward": 1.0,
      "step": 1964,
      "temperature": 1.0
    },
    {
      "all_correct": 0.75,
      "all_wrong": 0.0,
      "completion_length": 349.015625,
      "epoch": 0.05975550419656976,
      "grad_norm": 0.9501448060590215,
      "kl": 0.0537109375,
      "learning_rate": 9.912154448496696e-07,
      "loss": 0.0021,
      "reward": 2.068230390548706,
      "reward_std": 0.07340776920318604,
      "rewards/accuracy_reward": 0.8744803667068481,
      "rewards/format_reward": 1.0,
      "step": 1965,
      "temperature": 1.0
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.125,
      "completion_length": 373.484375,
      "epoch": 0.05978591412236954,
      "grad_norm": 1.1271847528819734,
      "kl": 0.0595703125,
      "learning_rate": 9.912065278583853e-07,
      "loss": 0.0024,
      "reward": 1.7667450904846191,
      "reward_std": 0.024641025811433792,
      "rewards/accuracy_reward": 0.638620138168335,
      "rewards/format_reward": 1.0,
      "step": 1966,
      "temperature": 1.0
    },
    {
      "all_correct": 0.625,
      "all_wrong": 0.125,
      "completion_length": 340.984375,
      "epoch": 0.05981632404816932,
      "grad_norm": 1.2533839993985527,
      "kl": 0.050048828125,
      "learning_rate": 9.911976063838338e-07,
      "loss": 0.002,
      "reward": 1.9451099634170532,
      "reward_std": 0.09429675340652466,
      "rewards/accuracy_reward": 0.7794848680496216,
      "rewards/format_reward": 1.0,
      "step": 1967,
      "temperature": 1.0
    },
    {
      "all_correct": 0.625,
      "all_wrong": 0.125,
      "completion_length": 371.359375,
      "epoch": 0.059846733973969106,
      "grad_norm": 1.0457200137808438,
      "kl": 0.0478515625,
      "learning_rate": 9.91188680426097e-07,
      "loss": 0.0019,
      "reward": 1.8587749004364014,
      "reward_std": 0.018019117414951324,
      "rewards/accuracy_reward": 0.6868999004364014,
      "rewards/format_reward": 1.0,
      "step": 1968,
      "temperature": 1.0
    },
    {
      "all_correct": 0.125,
      "all_wrong": 0.5,
      "completion_length": 386.125,
      "epoch": 0.059877143899768885,
      "grad_norm": 1.0431837283311127,
      "kl": 0.03857421875,
      "learning_rate": 9.911797499852559e-07,
      "loss": 0.0015,
      "reward": 1.321475863456726,
      "reward_std": 0.10865139961242676,
      "rewards/accuracy_reward": 0.2527258098125458,
      "rewards/format_reward": 1.0,
      "step": 1969,
      "temperature": 1.0
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.25,
      "completion_length": 357.671875,
      "epoch": 0.059907553825568664,
      "grad_norm": 1.142398935898857,
      "kl": 0.042236328125,
      "learning_rate": 9.911708150613924e-07,
      "loss": 0.0017,
      "reward": 1.7703170776367188,
      "reward_std": 0.009297682903707027,
      "rewards/accuracy_reward": 0.6203169822692871,
      "rewards/format_reward": 1.0,
      "step": 1970,
      "temperature": 1.0
    },
    {
      "all_correct": 0.625,
      "all_wrong": 0.125,
      "completion_length": 370.84375,
      "epoch": 0.059937963751368444,
      "grad_norm": 0.8206907445941592,
      "kl": 0.031494140625,
      "learning_rate": 9.91161875654588e-07,
      "loss": 0.0013,
      "reward": 1.8650250434875488,
      "reward_std": 0.0807153582572937,
      "rewards/accuracy_reward": 0.7181500196456909,
      "rewards/format_reward": 1.0,
      "step": 1971,
      "temperature": 1.0
    },
    {
      "all_correct": 0.625,
      "all_wrong": 0.125,
      "completion_length": 375.109375,
      "epoch": 0.05996837367716823,
      "grad_norm": 0.6414932018732011,
      "kl": 0.032470703125,
      "learning_rate": 9.91152931764924e-07,
      "loss": 0.0013,
      "reward": 1.8312499523162842,
      "reward_std": 0.15609951317310333,
      "rewards/accuracy_reward": 0.703125,
      "rewards/format_reward": 1.0,
      "step": 1972,
      "temperature": 1.0
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.375,
      "completion_length": 355.671875,
      "epoch": 0.05999878360296801,
      "grad_norm": 0.8738284334042088,
      "kl": 0.045166015625,
      "learning_rate": 9.911439833924826e-07,
      "loss": 0.0018,
      "reward": 1.677626609802246,
      "reward_std": 0.02369932271540165,
      "rewards/accuracy_reward": 0.5588765144348145,
      "rewards/format_reward": 1.0,
      "step": 1973,
      "temperature": 1.0
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.125,
      "completion_length": 368.828125,
      "epoch": 0.06002919352876779,
      "grad_norm": 1.5296967126642902,
      "kl": 0.04443359375,
      "learning_rate": 9.91135030537345e-07,
      "loss": 0.0018,
      "reward": 1.8013516664505005,
      "reward_std": 0.08538375049829483,
      "rewards/accuracy_reward": 0.6419765949249268,
      "rewards/format_reward": 1.0,
      "step": 1974,
      "temperature": 1.0
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.0,
      "completion_length": 370.28125,
      "epoch": 0.060059603454567574,
      "grad_norm": 1.0523610924261948,
      "kl": 0.029541015625,
      "learning_rate": 9.911260731995929e-07,
      "loss": 0.0012,
      "reward": 1.8492486476898193,
      "reward_std": 0.12775130569934845,
      "rewards/accuracy_reward": 0.6804986000061035,
      "rewards/format_reward": 1.0,
      "step": 1975,
      "temperature": 1.0
    },
    {
      "all_correct": 0.625,
      "all_wrong": 0.125,
      "completion_length": 372.046875,
      "epoch": 0.06009001338036735,
      "grad_norm": 0.5109180259835793,
      "kl": 0.03369140625,
      "learning_rate": 9.911171113793084e-07,
      "loss": 0.0013,
      "reward": 1.9937500953674316,
      "reward_std": 0.12246951460838318,
      "rewards/accuracy_reward": 0.828125,
      "rewards/format_reward": 1.0,
      "step": 1976,
      "temperature": 1.0
    },
    {
      "all_correct": 0.625,
      "all_wrong": 0.125,
      "completion_length": 390.40625,
      "epoch": 0.06012042330616713,
      "grad_norm": 1.102908024981143,
      "kl": 0.0341796875,
      "learning_rate": 9.91108145076573e-07,
      "loss": 0.0014,
      "reward": 2.0,
      "reward_std": 0.12268617749214172,
      "rewards/accuracy_reward": 0.84375,
      "rewards/format_reward": 1.0,
      "step": 1977,
      "temperature": 1.0
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.0,
      "completion_length": 372.234375,
      "epoch": 0.06015083323196691,
      "grad_norm": 1.709610783822741,
      "kl": 0.03662109375,
      "learning_rate": 9.910991742914688e-07,
      "loss": 0.0015,
      "reward": 1.8974268436431885,
      "reward_std": 0.08651846647262573,
      "rewards/accuracy_reward": 0.7130517959594727,
      "rewards/format_reward": 1.0,
      "step": 1978,
      "temperature": 1.0
    },
    {
      "all_correct": 0.75,
      "all_wrong": 0.25,
      "completion_length": 347.984375,
      "epoch": 0.0601812431577667,
      "grad_norm": 0.06368488202440593,
      "kl": 0.037841796875,
      "learning_rate": 9.910901990240772e-07,
      "loss": 0.0015,
      "reward": 1.9000000953674316,
      "reward_std": 0.0,
      "rewards/accuracy_reward": 0.75,
      "rewards/format_reward": 1.0,
      "step": 1979,
      "temperature": 1.0
    },
    {
      "all_correct": 0.625,
      "all_wrong": 0.0,
      "completion_length": 383.375,
      "epoch": 0.06021165308356648,
      "grad_norm": 2.3757866306151434,
      "kl": 0.044921875,
      "learning_rate": 9.910812192744807e-07,
      "loss": 0.0018,
      "reward": 1.869271159172058,
      "reward_std": 0.05167567729949951,
      "rewards/accuracy_reward": 0.7098960876464844,
      "rewards/format_reward": 1.0,
      "step": 1980,
      "temperature": 1.0
    },
    {
      "all_correct": 0.375,
      "all_wrong": 0.125,
      "completion_length": 406.703125,
      "epoch": 0.060242063009366256,
      "grad_norm": 1.3654657594927055,
      "kl": 0.0308837890625,
      "learning_rate": 9.910722350427609e-07,
      "loss": 0.0012,
      "reward": 1.6654720306396484,
      "reward_std": 0.22080287337303162,
      "rewards/accuracy_reward": 0.5623469352722168,
      "rewards/format_reward": 1.0,
      "step": 1981,
      "temperature": 1.0
    },
    {
      "all_correct": 0.75,
      "all_wrong": 0.125,
      "completion_length": 372.015625,
      "epoch": 0.060272472935166035,
      "grad_norm": 0.6070560587513565,
      "kl": 0.0400390625,
      "learning_rate": 9.910632463289999e-07,
      "loss": 0.0016,
      "reward": 1.9875001907348633,
      "reward_std": 0.08435788005590439,
      "rewards/accuracy_reward": 0.828125,
      "rewards/format_reward": 1.0,
      "step": 1982,
      "temperature": 1.0
    },
    {
      "all_correct": 0.625,
      "all_wrong": 0.0,
      "completion_length": 347.4375,
      "epoch": 0.06030288286096582,
      "grad_norm": 1.3307857984054687,
      "kl": 0.041259765625,
      "learning_rate": 9.910542531332795e-07,
      "loss": 0.0017,
      "reward": 1.9093294143676758,
      "reward_std": 0.11756882816553116,
      "rewards/accuracy_reward": 0.7437043786048889,
      "rewards/format_reward": 1.0,
      "step": 1983,
      "temperature": 1.0
    },
    {
      "all_correct": 0.625,
      "all_wrong": 0.0,
      "completion_length": 354.453125,
      "epoch": 0.0603332927867656,
      "grad_norm": 17.77065210727443,
      "kl": 0.04150390625,
      "learning_rate": 9.910452554556822e-07,
      "loss": 0.0017,
      "reward": 1.9469906091690063,
      "reward_std": 0.1214180737733841,
      "rewards/accuracy_reward": 0.7876155972480774,
      "rewards/format_reward": 1.0,
      "step": 1984,
      "temperature": 1.0
    },
    {
      "all_correct": 0.25,
      "all_wrong": 0.25,
      "completion_length": 366.703125,
      "epoch": 0.06036370271256538,
      "grad_norm": 0.9472929521263453,
      "kl": 0.0390625,
      "learning_rate": 9.910362532962898e-07,
      "loss": 0.0016,
      "reward": 1.5874080657958984,
      "reward_std": 0.18145638704299927,
      "rewards/accuracy_reward": 0.47803300619125366,
      "rewards/format_reward": 1.0,
      "step": 1985,
      "temperature": 1.0
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.0,
      "completion_length": 413.1875,
      "epoch": 0.06039411263836516,
      "grad_norm": 0.9138971312077004,
      "kl": 0.0303955078125,
      "learning_rate": 9.910272466551847e-07,
      "loss": 0.0012,
      "reward": 1.9122934341430664,
      "reward_std": 0.11233077198266983,
      "rewards/accuracy_reward": 0.7372933030128479,
      "rewards/format_reward": 1.0,
      "step": 1986,
      "temperature": 1.0
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.0,
      "completion_length": 381.421875,
      "epoch": 0.060424522564164945,
      "grad_norm": 0.9864659679933918,
      "kl": 0.04052734375,
      "learning_rate": 9.91018235532449e-07,
      "loss": 0.0016,
      "reward": 1.989978551864624,
      "reward_std": 0.17572543025016785,
      "rewards/accuracy_reward": 0.8337284326553345,
      "rewards/format_reward": 1.0,
      "step": 1987,
      "temperature": 1.0
    },
    {
      "all_correct": 0.375,
      "all_wrong": 0.125,
      "completion_length": 397.953125,
      "epoch": 0.060454932489964724,
      "grad_norm": 2.4991825660598708,
      "kl": 0.040283203125,
      "learning_rate": 9.91009219928165e-07,
      "loss": 0.0016,
      "reward": 1.6769561767578125,
      "reward_std": 0.08373412489891052,
      "rewards/accuracy_reward": 0.5238310694694519,
      "rewards/format_reward": 1.0,
      "step": 1988,
      "temperature": 1.0
    },
    {
      "all_correct": 0.25,
      "all_wrong": 0.0,
      "completion_length": 394.484375,
      "epoch": 0.060485342415764504,
      "grad_norm": 2.0879254561320177,
      "kl": 0.03662109375,
      "learning_rate": 9.910001998424148e-07,
      "loss": 0.0015,
      "reward": 1.6113088130950928,
      "reward_std": 0.2243492603302002,
      "rewards/accuracy_reward": 0.46443384885787964,
      "rewards/format_reward": 1.0,
      "step": 1989,
      "temperature": 1.0
    },
    {
      "all_correct": 0.625,
      "all_wrong": 0.125,
      "completion_length": 373.21875,
      "epoch": 0.06051575234156429,
      "grad_norm": 0.996015561494989,
      "kl": 0.046142578125,
      "learning_rate": 9.90991175275281e-07,
      "loss": 0.0019,
      "reward": 1.8631010055541992,
      "reward_std": 0.041487954556941986,
      "rewards/accuracy_reward": 0.7006008625030518,
      "rewards/format_reward": 1.0,
      "step": 1990,
      "temperature": 1.0
    },
    {
      "all_correct": 0.375,
      "all_wrong": 0.25,
      "completion_length": 383.515625,
      "epoch": 0.06054616226736407,
      "grad_norm": 0.7343137120308841,
      "kl": 0.033203125,
      "learning_rate": 9.909821462268457e-07,
      "loss": 0.0013,
      "reward": 1.7302956581115723,
      "reward_std": 0.1389673501253128,
      "rewards/accuracy_reward": 0.5959206819534302,
      "rewards/format_reward": 1.0,
      "step": 1991,
      "temperature": 1.0
    },
    {
      "all_correct": 0.625,
      "all_wrong": 0.125,
      "completion_length": 355.75,
      "epoch": 0.06057657219316385,
      "grad_norm": 0.776607792500057,
      "kl": 0.03662109375,
      "learning_rate": 9.909731126971913e-07,
      "loss": 0.0015,
      "reward": 1.9947916269302368,
      "reward_std": 0.0681459903717041,
      "rewards/accuracy_reward": 0.8229166269302368,
      "rewards/format_reward": 1.0,
      "step": 1992,
      "temperature": 1.0
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.125,
      "completion_length": 381.515625,
      "epoch": 0.06060698211896363,
      "grad_norm": 0.835727328002826,
      "kl": 0.03564453125,
      "learning_rate": 9.909640746864008e-07,
      "loss": 0.0014,
      "reward": 1.8006861209869385,
      "reward_std": 0.08327779918909073,
      "rewards/accuracy_reward": 0.6538111567497253,
      "rewards/format_reward": 1.0,
      "step": 1993,
      "temperature": 1.0
    },
    {
      "all_correct": 0.375,
      "all_wrong": 0.25,
      "completion_length": 386.125,
      "epoch": 0.060637392044763413,
      "grad_norm": 1.0524091159144835,
      "kl": 0.0308837890625,
      "learning_rate": 9.90955032194556e-07,
      "loss": 0.0012,
      "reward": 1.646376609802246,
      "reward_std": 0.15505598485469818,
      "rewards/accuracy_reward": 0.524501621723175,
      "rewards/format_reward": 1.0,
      "step": 1994,
      "temperature": 1.0
    },
    {
      "all_correct": 0.625,
      "all_wrong": 0.0,
      "completion_length": 389.0,
      "epoch": 0.06066780197056319,
      "grad_norm": 3.573113734574524,
      "kl": 0.04052734375,
      "learning_rate": 9.909459852217396e-07,
      "loss": 0.0016,
      "reward": 1.9151726961135864,
      "reward_std": 0.12631858885288239,
      "rewards/accuracy_reward": 0.7589226961135864,
      "rewards/format_reward": 1.0,
      "step": 1995,
      "temperature": 1.0
    },
    {
      "all_correct": 0.875,
      "all_wrong": 0.0,
      "completion_length": 371.09375,
      "epoch": 0.06069821189636297,
      "grad_norm": 3.962360284402888,
      "kl": 0.035888671875,
      "learning_rate": 9.909369337680344e-07,
      "loss": 0.0014,
      "reward": 2.110389232635498,
      "reward_std": 0.02068474516272545,
      "rewards/accuracy_reward": 0.9197641015052795,
      "rewards/format_reward": 1.0,
      "step": 1996,
      "temperature": 1.0
    },
    {
      "all_correct": 0.375,
      "all_wrong": 0.25,
      "completion_length": 373.46875,
      "epoch": 0.06072862182216275,
      "grad_norm": 0.7652132452324627,
      "kl": 0.03857421875,
      "learning_rate": 9.90927877833523e-07,
      "loss": 0.0015,
      "reward": 1.683347225189209,
      "reward_std": 0.14815086126327515,
      "rewards/accuracy_reward": 0.5708472728729248,
      "rewards/format_reward": 1.0,
      "step": 1997,
      "temperature": 1.0
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.125,
      "completion_length": 358.109375,
      "epoch": 0.06075903174796254,
      "grad_norm": 0.9326094194701183,
      "kl": 0.029296875,
      "learning_rate": 9.909188174182876e-07,
      "loss": 0.0012,
      "reward": 1.8406250476837158,
      "reward_std": 0.17485956847667694,
      "rewards/accuracy_reward": 0.703125,
      "rewards/format_reward": 1.0,
      "step": 1998,
      "temperature": 1.0
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.0,
      "completion_length": 394.703125,
      "epoch": 0.060789441673762316,
      "grad_norm": 1.3427057846942594,
      "kl": 0.03662109375,
      "learning_rate": 9.909097525224113e-07,
      "loss": 0.0015,
      "reward": 1.9200384616851807,
      "reward_std": 0.08428885787725449,
      "rewards/accuracy_reward": 0.7294133901596069,
      "rewards/format_reward": 1.0,
      "step": 1999,
      "temperature": 1.0
    },
    {
      "all_correct": 0.125,
      "all_wrong": 0.125,
      "completion_length": 398.5625,
      "epoch": 0.060819851599562096,
      "grad_norm": 3.0749503768137565,
      "kl": 0.037353515625,
      "learning_rate": 9.90900683145977e-07,
      "loss": 0.0015,
      "reward": 1.6705085039138794,
      "reward_std": 0.11880546808242798,
      "rewards/accuracy_reward": 0.5173835158348083,
      "rewards/format_reward": 1.0,
      "step": 2000,
      "temperature": 1.0
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.25,
      "completion_length": 389.625,
      "epoch": 0.060850261525361875,
      "grad_norm": 2.4584141836633067,
      "kl": 0.0322265625,
      "learning_rate": 9.908916092890672e-07,
      "loss": 0.0013,
      "reward": 1.7610342502593994,
      "reward_std": 0.07611941546201706,
      "rewards/accuracy_reward": 0.6235341429710388,
      "rewards/format_reward": 1.0,
      "step": 2001,
      "temperature": 1.0
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.125,
      "completion_length": 395.984375,
      "epoch": 0.06088067145116166,
      "grad_norm": 0.8096807580529091,
      "kl": 0.03076171875,
      "learning_rate": 9.908825309517646e-07,
      "loss": 0.0012,
      "reward": 1.9089552164077759,
      "reward_std": 0.14473243057727814,
      "rewards/accuracy_reward": 0.7495800256729126,
      "rewards/format_reward": 1.0,
      "step": 2002,
      "temperature": 1.0
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.25,
      "completion_length": 366.078125,
      "epoch": 0.06091108137696144,
      "grad_norm": 1.4661966747165747,
      "kl": 0.034912109375,
      "learning_rate": 9.908734481341524e-07,
      "loss": 0.0014,
      "reward": 1.7146159410476685,
      "reward_std": 0.03164929151535034,
      "rewards/accuracy_reward": 0.5708659291267395,
      "rewards/format_reward": 1.0,
      "step": 2003,
      "temperature": 1.0
    },
    {
      "all_correct": 0.625,
      "all_wrong": 0.0,
      "completion_length": 346.859375,
      "epoch": 0.06094149130276122,
      "grad_norm": 2.0676895372245974,
      "kl": 0.037841796875,
      "learning_rate": 9.908643608363131e-07,
      "loss": 0.0015,
      "reward": 1.975151538848877,
      "reward_std": 0.1236010193824768,
      "rewards/accuracy_reward": 0.8095265030860901,
      "rewards/format_reward": 1.0,
      "step": 2004,
      "temperature": 1.0
    },
    {
      "all_correct": 0.375,
      "all_wrong": 0.125,
      "completion_length": 403.5,
      "epoch": 0.060971901228561005,
      "grad_norm": 1.8778853673451223,
      "kl": 0.03173828125,
      "learning_rate": 9.9085526905833e-07,
      "loss": 0.0013,
      "reward": 1.8376152515411377,
      "reward_std": 0.21920059621334076,
      "rewards/accuracy_reward": 0.6876152157783508,
      "rewards/format_reward": 1.0,
      "step": 2005,
      "temperature": 1.0
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.0,
      "completion_length": 369.328125,
      "epoch": 0.061002311154360785,
      "grad_norm": 1.1192917042278074,
      "kl": 0.036865234375,
      "learning_rate": 9.90846172800286e-07,
      "loss": 0.0015,
      "reward": 1.84938383102417,
      "reward_std": 0.12319977581501007,
      "rewards/accuracy_reward": 0.6837587952613831,
      "rewards/format_reward": 1.0,
      "step": 2006,
      "temperature": 1.0
    },
    {
      "all_correct": 0.375,
      "all_wrong": 0.125,
      "completion_length": 388.84375,
      "epoch": 0.061032721080160564,
      "grad_norm": 6.192662454100659,
      "kl": 0.032470703125,
      "learning_rate": 9.90837072062264e-07,
      "loss": 0.0013,
      "reward": 1.8039448261260986,
      "reward_std": 0.27431347966194153,
      "rewards/accuracy_reward": 0.6914447546005249,
      "rewards/format_reward": 0.984375,
      "step": 2007,
      "temperature": 1.0
    },
    {
      "all_correct": 0.75,
      "all_wrong": 0.0,
      "completion_length": 375.328125,
      "epoch": 0.06106313100596034,
      "grad_norm": 0.6153442989840169,
      "kl": 0.031494140625,
      "learning_rate": 9.908279668443471e-07,
      "loss": 0.0013,
      "reward": 1.9864578247070312,
      "reward_std": 0.047391265630722046,
      "rewards/accuracy_reward": 0.8114577531814575,
      "rewards/format_reward": 1.0,
      "step": 2008,
      "temperature": 1.0
    },
    {
      "all_correct": 0.75,
      "all_wrong": 0.125,
      "completion_length": 345.40625,
      "epoch": 0.06109354093176013,
      "grad_norm": 0.9402845941055297,
      "kl": 0.045166015625,
      "learning_rate": 9.908188571466184e-07,
      "loss": 0.0018,
      "reward": 1.9312500953674316,
      "reward_std": 0.08711418509483337,
      "rewards/accuracy_reward": 0.78125,
      "rewards/format_reward": 1.0,
      "step": 2009,
      "temperature": 1.0
    },
    {
      "all_correct": 0.25,
      "all_wrong": 0.125,
      "completion_length": 345.015625,
      "epoch": 0.06112395085755991,
      "grad_norm": 1.4668053882271297,
      "kl": 0.03564453125,
      "learning_rate": 9.908097429691612e-07,
      "loss": 0.0014,
      "reward": 1.7497222423553467,
      "reward_std": 0.25806403160095215,
      "rewards/accuracy_reward": 0.6122223138809204,
      "rewards/format_reward": 1.0,
      "step": 2010,
      "temperature": 1.0
    },
    {
      "all_correct": 0.625,
      "all_wrong": 0.125,
      "completion_length": 360.15625,
      "epoch": 0.06115436078335969,
      "grad_norm": 1.0136508075622583,
      "kl": 0.037841796875,
      "learning_rate": 9.908006243120586e-07,
      "loss": 0.0015,
      "reward": 1.815248727798462,
      "reward_std": 0.003950612619519234,
      "rewards/accuracy_reward": 0.6652487516403198,
      "rewards/format_reward": 1.0,
      "step": 2011,
      "temperature": 1.0
    },
    {
      "all_correct": 0.375,
      "all_wrong": 0.0,
      "completion_length": 408.921875,
      "epoch": 0.06118477070915947,
      "grad_norm": 2.067966896442725,
      "kl": 0.042724609375,
      "learning_rate": 9.907915011753935e-07,
      "loss": 0.0017,
      "reward": 1.6213836669921875,
      "reward_std": 0.16359512507915497,
      "rewards/accuracy_reward": 0.5620086789131165,
      "rewards/format_reward": 0.90625,
      "step": 2012,
      "temperature": 1.0
    },
    {
      "all_correct": 0.375,
      "all_wrong": 0.25,
      "completion_length": 353.625,
      "epoch": 0.06121518063495925,
      "grad_norm": 0.8826839892327382,
      "kl": 0.028564453125,
      "learning_rate": 9.907823735592497e-07,
      "loss": 0.0011,
      "reward": 1.632556676864624,
      "reward_std": 0.1384935975074768,
      "rewards/accuracy_reward": 0.523181676864624,
      "rewards/format_reward": 1.0,
      "step": 2013,
      "temperature": 1.0
    },
    {
      "all_correct": 0.75,
      "all_wrong": 0.125,
      "completion_length": 346.09375,
      "epoch": 0.06124559056075903,
      "grad_norm": 1.2708261860073458,
      "kl": 0.03857421875,
      "learning_rate": 9.907732414637102e-07,
      "loss": 0.0015,
      "reward": 1.9701991081237793,
      "reward_std": 0.04589265584945679,
      "rewards/accuracy_reward": 0.8014490008354187,
      "rewards/format_reward": 1.0,
      "step": 2014,
      "temperature": 1.0
    },
    {
      "all_correct": 0.625,
      "all_wrong": 0.125,
      "completion_length": 339.9375,
      "epoch": 0.06127600048655881,
      "grad_norm": 0.8143599457597835,
      "kl": 0.033447265625,
      "learning_rate": 9.907641048888585e-07,
      "loss": 0.0013,
      "reward": 1.96875,
      "reward_std": 0.1293872892856598,
      "rewards/accuracy_reward": 0.8125,
      "rewards/format_reward": 1.0,
      "step": 2015,
      "temperature": 1.0
    },
    {
      "all_correct": 0.625,
      "all_wrong": 0.0,
      "completion_length": 356.140625,
      "epoch": 0.06130641041235859,
      "grad_norm": 2.451855780717952,
      "kl": 0.029541015625,
      "learning_rate": 9.907549638347778e-07,
      "loss": 0.0012,
      "reward": 1.9939371347427368,
      "reward_std": 0.1658138632774353,
      "rewards/accuracy_reward": 0.8158120512962341,
      "rewards/format_reward": 1.0,
      "step": 2016,
      "temperature": 1.0
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.0,
      "completion_length": 391.09375,
      "epoch": 0.06133682033815838,
      "grad_norm": 1.2448856001567048,
      "kl": 0.03955078125,
      "learning_rate": 9.907458183015516e-07,
      "loss": 0.0016,
      "reward": 1.7002171277999878,
      "reward_std": 0.14296643435955048,
      "rewards/accuracy_reward": 0.590842068195343,
      "rewards/format_reward": 0.984375,
      "step": 2017,
      "temperature": 1.0
    },
    {
      "all_correct": 0.375,
      "all_wrong": 0.125,
      "completion_length": 364.078125,
      "epoch": 0.061367230263958156,
      "grad_norm": 1.534647785388403,
      "kl": 0.038818359375,
      "learning_rate": 9.907366682892636e-07,
      "loss": 0.0015,
      "reward": 1.750182867050171,
      "reward_std": 0.15653809905052185,
      "rewards/accuracy_reward": 0.6095578670501709,
      "rewards/format_reward": 1.0,
      "step": 2018,
      "temperature": 1.0
    },
    {
      "all_correct": 0.75,
      "all_wrong": 0.0,
      "completion_length": 367.90625,
      "epoch": 0.061397640189757935,
      "grad_norm": 1.178917090393725,
      "kl": 0.03173828125,
      "learning_rate": 9.90727513797997e-07,
      "loss": 0.0013,
      "reward": 2.0434062480926514,
      "reward_std": 0.11369597166776657,
      "rewards/accuracy_reward": 0.8621562719345093,
      "rewards/format_reward": 1.0,
      "step": 2019,
      "temperature": 1.0
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.125,
      "completion_length": 368.9375,
      "epoch": 0.06142805011555772,
      "grad_norm": 1.0157961915253606,
      "kl": 0.03662109375,
      "learning_rate": 9.907183548278353e-07,
      "loss": 0.0015,
      "reward": 1.7323836088180542,
      "reward_std": 0.13221773505210876,
      "rewards/accuracy_reward": 0.6073836088180542,
      "rewards/format_reward": 1.0,
      "step": 2020,
      "temperature": 1.0
    },
    {
      "all_correct": 0.625,
      "all_wrong": 0.0,
      "completion_length": 368.09375,
      "epoch": 0.0614584600413575,
      "grad_norm": 1.6582395335683926,
      "kl": 0.03759765625,
      "learning_rate": 9.907091913788625e-07,
      "loss": 0.0015,
      "reward": 1.8728384971618652,
      "reward_std": 0.12552928924560547,
      "rewards/accuracy_reward": 0.7322134971618652,
      "rewards/format_reward": 1.0,
      "step": 2021,
      "temperature": 1.0
    },
    {
      "all_correct": 0.625,
      "all_wrong": 0.125,
      "completion_length": 393.59375,
      "epoch": 0.06148886996715728,
      "grad_norm": 0.7855824877121248,
      "kl": 0.037109375,
      "learning_rate": 9.907000234511618e-07,
      "loss": 0.0015,
      "reward": 1.8731685876846313,
      "reward_std": 0.12509721517562866,
      "rewards/accuracy_reward": 0.7419184446334839,
      "rewards/format_reward": 0.984375,
      "step": 2022,
      "temperature": 1.0
    },
    {
      "all_correct": 0.75,
      "all_wrong": 0.0,
      "completion_length": 363.328125,
      "epoch": 0.06151927989295706,
      "grad_norm": 34.315817412333004,
      "kl": 0.03515625,
      "learning_rate": 9.906908510448174e-07,
      "loss": 0.0014,
      "reward": 2.013446092605591,
      "reward_std": 0.09947584569454193,
      "rewards/accuracy_reward": 0.8384460210800171,
      "rewards/format_reward": 1.0,
      "step": 2023,
      "temperature": 1.0
    },
    {
      "all_correct": 0.625,
      "all_wrong": 0.125,
      "completion_length": 355.078125,
      "epoch": 0.061549689818756845,
      "grad_norm": 0.9354044754653187,
      "kl": 0.0294189453125,
      "learning_rate": 9.906816741599125e-07,
      "loss": 0.0012,
      "reward": 1.9156250953674316,
      "reward_std": 0.13130834698677063,
      "rewards/accuracy_reward": 0.765625,
      "rewards/format_reward": 1.0,
      "step": 2024,
      "temperature": 1.0
    },
    {
      "all_correct": 0.625,
      "all_wrong": 0.25,
      "completion_length": 342.453125,
      "epoch": 0.061580099744556624,
      "grad_norm": 0.684202130500259,
      "kl": 0.031494140625,
      "learning_rate": 9.906724927965308e-07,
      "loss": 0.0013,
      "reward": 1.829469919204712,
      "reward_std": 0.011335247196257114,
      "rewards/accuracy_reward": 0.6794699430465698,
      "rewards/format_reward": 1.0,
      "step": 2025,
      "temperature": 1.0
    },
    {
      "all_correct": 0.625,
      "all_wrong": 0.125,
      "completion_length": 342.359375,
      "epoch": 0.0616105096703564,
      "grad_norm": 0.7968202961327147,
      "kl": 0.03271484375,
      "learning_rate": 9.906633069547567e-07,
      "loss": 0.0013,
      "reward": 1.8194878101348877,
      "reward_std": 0.09470692276954651,
      "rewards/accuracy_reward": 0.685112714767456,
      "rewards/format_reward": 1.0,
      "step": 2026,
      "temperature": 1.0
    },
    {
      "all_correct": 0.625,
      "all_wrong": 0.0,
      "completion_length": 356.515625,
      "epoch": 0.06164091959615618,
      "grad_norm": 1.0279680363230617,
      "kl": 0.03759765625,
      "learning_rate": 9.906541166346736e-07,
      "loss": 0.0015,
      "reward": 1.9176373481750488,
      "reward_std": 0.07220220565795898,
      "rewards/accuracy_reward": 0.7551373243331909,
      "rewards/format_reward": 1.0,
      "step": 2027,
      "temperature": 1.0
    },
    {
      "all_correct": 0.25,
      "all_wrong": 0.125,
      "completion_length": 374.78125,
      "epoch": 0.06167132952195597,
      "grad_norm": 1.1702449263467285,
      "kl": 0.035888671875,
      "learning_rate": 9.906449218363653e-07,
      "loss": 0.0014,
      "reward": 1.6825354099273682,
      "reward_std": 0.25893667340278625,
      "rewards/accuracy_reward": 0.5481604337692261,
      "rewards/format_reward": 1.0,
      "step": 2028,
      "temperature": 1.0
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.375,
      "completion_length": 350.03125,
      "epoch": 0.06170173944775575,
      "grad_norm": 0.5640948683912339,
      "kl": 0.031982421875,
      "learning_rate": 9.906357225599162e-07,
      "loss": 0.0013,
      "reward": 1.7125000953674316,
      "reward_std": 0.06943650543689728,
      "rewards/accuracy_reward": 0.59375,
      "rewards/format_reward": 1.0,
      "step": 2029,
      "temperature": 1.0
    },
    {
      "all_correct": 0.875,
      "all_wrong": 0.0,
      "completion_length": 350.5625,
      "epoch": 0.06173214937355553,
      "grad_norm": 0.7092419109420526,
      "kl": 0.037841796875,
      "learning_rate": 9.906265188054097e-07,
      "loss": 0.0015,
      "reward": 2.1659364700317383,
      "reward_std": 0.0021651671268045902,
      "rewards/accuracy_reward": 0.965936541557312,
      "rewards/format_reward": 1.0,
      "step": 2030,
      "temperature": 1.0
    },
    {
      "all_correct": 0.75,
      "all_wrong": 0.0,
      "completion_length": 347.015625,
      "epoch": 0.06176255929935531,
      "grad_norm": 0.8401065484932992,
      "kl": 0.041015625,
      "learning_rate": 9.906173105729301e-07,
      "loss": 0.0016,
      "reward": 2.039583206176758,
      "reward_std": 0.11958510428667068,
      "rewards/accuracy_reward": 0.8645833134651184,
      "rewards/format_reward": 1.0,
      "step": 2031,
      "temperature": 1.0
    },
    {
      "all_correct": 0.875,
      "all_wrong": 0.0,
      "completion_length": 367.4375,
      "epoch": 0.06179296922515509,
      "grad_norm": 1.0132838206894346,
      "kl": 0.0341796875,
      "learning_rate": 9.906080978625615e-07,
      "loss": 0.0014,
      "reward": 2.149937629699707,
      "reward_std": 0.004149340093135834,
      "rewards/accuracy_reward": 0.9499375224113464,
      "rewards/format_reward": 1.0,
      "step": 2032,
      "temperature": 1.0
    },
    {
      "all_correct": 0.375,
      "all_wrong": 0.125,
      "completion_length": 381.25,
      "epoch": 0.06182337915095487,
      "grad_norm": 1.2705715676491562,
      "kl": 0.039306640625,
      "learning_rate": 9.90598880674388e-07,
      "loss": 0.0016,
      "reward": 1.6753382682800293,
      "reward_std": 0.14991800487041473,
      "rewards/accuracy_reward": 0.5534632205963135,
      "rewards/format_reward": 1.0,
      "step": 2033,
      "temperature": 1.0
    },
    {
      "all_correct": 0.375,
      "all_wrong": 0.25,
      "completion_length": 385.75,
      "epoch": 0.06185378907675465,
      "grad_norm": 1.075710889191878,
      "kl": 0.038330078125,
      "learning_rate": 9.905896590084934e-07,
      "loss": 0.0015,
      "reward": 1.6953051090240479,
      "reward_std": 0.03766397386789322,
      "rewards/accuracy_reward": 0.5515551567077637,
      "rewards/format_reward": 1.0,
      "step": 2034,
      "temperature": 1.0
    },
    {
      "all_correct": 0.75,
      "all_wrong": 0.125,
      "completion_length": 372.453125,
      "epoch": 0.06188419900255444,
      "grad_norm": 0.7289916645503076,
      "kl": 0.045654296875,
      "learning_rate": 9.905804328649621e-07,
      "loss": 0.0018,
      "reward": 1.9435954093933105,
      "reward_std": 0.008036581799387932,
      "rewards/accuracy_reward": 0.77484530210495,
      "rewards/format_reward": 1.0,
      "step": 2035,
      "temperature": 1.0
    },
    {
      "all_correct": 0.25,
      "all_wrong": 0.375,
      "completion_length": 401.609375,
      "epoch": 0.061914608928354216,
      "grad_norm": 0.9882589464269553,
      "kl": 0.033203125,
      "learning_rate": 9.905712022438782e-07,
      "loss": 0.0013,
      "reward": 1.436063528060913,
      "reward_std": 0.05676914006471634,
      "rewards/accuracy_reward": 0.34231358766555786,
      "rewards/format_reward": 1.0,
      "step": 2036,
      "temperature": 1.0
    },
    {
      "all_correct": 0.375,
      "all_wrong": 0.25,
      "completion_length": 384.59375,
      "epoch": 0.061945018854153995,
      "grad_norm": 0.9299777172077761,
      "kl": 0.033203125,
      "learning_rate": 9.905619671453262e-07,
      "loss": 0.0013,
      "reward": 1.765625,
      "reward_std": 0.21148672699928284,
      "rewards/accuracy_reward": 0.640625,
      "rewards/format_reward": 1.0,
      "step": 2037,
      "temperature": 1.0
    },
    {
      "all_correct": 0.25,
      "all_wrong": 0.0,
      "completion_length": 410.578125,
      "epoch": 0.061975428779953774,
      "grad_norm": 1.3601296207923972,
      "kl": 0.0286865234375,
      "learning_rate": 9.905527275693902e-07,
      "loss": 0.0011,
      "reward": 1.7845923900604248,
      "reward_std": 0.24145135283470154,
      "rewards/accuracy_reward": 0.6189673542976379,
      "rewards/format_reward": 1.0,
      "step": 2038,
      "temperature": 1.0
    },
    {
      "all_correct": 0.25,
      "all_wrong": 0.125,
      "completion_length": 381.25,
      "epoch": 0.06200583870575356,
      "grad_norm": 1.1309604043384553,
      "kl": 0.03369140625,
      "learning_rate": 9.905434835161545e-07,
      "loss": 0.0014,
      "reward": 1.7005425691604614,
      "reward_std": 0.23524481058120728,
      "rewards/accuracy_reward": 0.5692925453186035,
      "rewards/format_reward": 1.0,
      "step": 2039,
      "temperature": 1.0
    },
    {
      "all_correct": 0.375,
      "all_wrong": 0.25,
      "completion_length": 380.453125,
      "epoch": 0.06203624863155334,
      "grad_norm": 0.8838880236497924,
      "kl": 0.03515625,
      "learning_rate": 9.905342349857036e-07,
      "loss": 0.0014,
      "reward": 1.648337483406067,
      "reward_std": 0.025409521535038948,
      "rewards/accuracy_reward": 0.4983374774456024,
      "rewards/format_reward": 1.0,
      "step": 2040,
      "temperature": 1.0
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.125,
      "completion_length": 378.03125,
      "epoch": 0.06206665855735312,
      "grad_norm": 0.8097388042890695,
      "kl": 0.03466796875,
      "learning_rate": 9.905249819781216e-07,
      "loss": 0.0014,
      "reward": 1.9192222356796265,
      "reward_std": 0.1308070570230484,
      "rewards/accuracy_reward": 0.7535971403121948,
      "rewards/format_reward": 1.0,
      "step": 2041,
      "temperature": 1.0
    },
    {
      "all_correct": 0.875,
      "all_wrong": 0.0,
      "completion_length": 352.84375,
      "epoch": 0.0620970684831529,
      "grad_norm": 0.7684804653042219,
      "kl": 0.032958984375,
      "learning_rate": 9.905157244934934e-07,
      "loss": 0.0013,
      "reward": 2.1422853469848633,
      "reward_std": 0.07965405285358429,
      "rewards/accuracy_reward": 0.95166015625,
      "rewards/format_reward": 1.0,
      "step": 2042,
      "temperature": 1.0
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.125,
      "completion_length": 355.515625,
      "epoch": 0.062127478408952684,
      "grad_norm": 0.8021499880881202,
      "kl": 0.035888671875,
      "learning_rate": 9.905064625319035e-07,
      "loss": 0.0014,
      "reward": 1.7461738586425781,
      "reward_std": 0.13696521520614624,
      "rewards/accuracy_reward": 0.6086738705635071,
      "rewards/format_reward": 1.0,
      "step": 2043,
      "temperature": 1.0
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.375,
      "completion_length": 345.953125,
      "epoch": 0.06215788833475246,
      "grad_norm": 0.7005308999840786,
      "kl": 0.03173828125,
      "learning_rate": 9.904971960934359e-07,
      "loss": 0.0013,
      "reward": 1.728124976158142,
      "reward_std": 0.06187184900045395,
      "rewards/accuracy_reward": 0.609375,
      "rewards/format_reward": 1.0,
      "step": 2044,
      "temperature": 1.0
    },
    {
      "all_correct": 0.625,
      "all_wrong": 0.0,
      "completion_length": 374.765625,
      "epoch": 0.06218829826055224,
      "grad_norm": 0.7247497247406496,
      "kl": 0.03515625,
      "learning_rate": 9.904879251781755e-07,
      "loss": 0.0014,
      "reward": 2.00933837890625,
      "reward_std": 0.06618594378232956,
      "rewards/accuracy_reward": 0.8187133073806763,
      "rewards/format_reward": 1.0,
      "step": 2045,
      "temperature": 1.0
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.125,
      "completion_length": 369.046875,
      "epoch": 0.06221870818635203,
      "grad_norm": 0.93673334733384,
      "kl": 0.03466796875,
      "learning_rate": 9.90478649786207e-07,
      "loss": 0.0014,
      "reward": 1.8385248184204102,
      "reward_std": 0.15765385329723358,
      "rewards/accuracy_reward": 0.6853996515274048,
      "rewards/format_reward": 1.0,
      "step": 2046,
      "temperature": 1.0
    },
    {
      "all_correct": 0.625,
      "all_wrong": 0.0,
      "completion_length": 361.8125,
      "epoch": 0.06224911811215181,
      "grad_norm": 0.928052213753772,
      "kl": 0.03369140625,
      "learning_rate": 9.90469369917615e-07,
      "loss": 0.0013,
      "reward": 1.9800981283187866,
      "reward_std": 0.08810873329639435,
      "rewards/accuracy_reward": 0.7925980687141418,
      "rewards/format_reward": 1.0,
      "step": 2047,
      "temperature": 1.0
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.0,
      "completion_length": 362.921875,
      "epoch": 0.06227952803795159,
      "grad_norm": 1.131193053003704,
      "kl": 0.0303955078125,
      "learning_rate": 9.90460085572484e-07,
      "loss": 0.0012,
      "reward": 1.949488878250122,
      "reward_std": 0.13756681978702545,
      "rewards/accuracy_reward": 0.7682388424873352,
      "rewards/format_reward": 1.0,
      "step": 2048,
      "temperature": 1.0
    },
    {
      "all_correct": 0.625,
      "all_wrong": 0.0,
      "completion_length": 390.65625,
      "epoch": 0.062309937963751366,
      "grad_norm": 1.366775535007421,
      "kl": 0.03662109375,
      "learning_rate": 9.90450796750899e-07,
      "loss": 0.0015,
      "reward": 1.9264273643493652,
      "reward_std": 0.0442509651184082,
      "rewards/accuracy_reward": 0.757677435874939,
      "rewards/format_reward": 1.0,
      "step": 2049,
      "temperature": 1.0
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.25,
      "completion_length": 383.40625,
      "epoch": 0.06234034788955115,
      "grad_norm": 0.5207658131457866,
      "kl": 0.026123046875,
      "learning_rate": 9.904415034529447e-07,
      "loss": 0.001,
      "reward": 1.7875001430511475,
      "reward_std": 0.155264750123024,
      "rewards/accuracy_reward": 0.65625,
      "rewards/format_reward": 1.0,
      "step": 2050,
      "temperature": 1.0
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.125,
      "completion_length": 366.875,
      "epoch": 0.06237075781535093,
      "grad_norm": 1.5279307884748905,
      "kl": 0.03369140625,
      "learning_rate": 9.90432205678706e-07,
      "loss": 0.0014,
      "reward": 1.8474767208099365,
      "reward_std": 0.05910363793373108,
      "rewards/accuracy_reward": 0.6974766850471497,
      "rewards/format_reward": 1.0,
      "step": 2051,
      "temperature": 1.0
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.125,
      "completion_length": 370.1875,
      "epoch": 0.06240116774115071,
      "grad_norm": 0.9275379111156308,
      "kl": 0.03271484375,
      "learning_rate": 9.904229034282673e-07,
      "loss": 0.0013,
      "reward": 1.78125,
      "reward_std": 0.1612270474433899,
      "rewards/accuracy_reward": 0.65625,
      "rewards/format_reward": 1.0,
      "step": 2052,
      "temperature": 1.0
    },
    {
      "all_correct": 0.75,
      "all_wrong": 0.125,
      "completion_length": 343.546875,
      "epoch": 0.06243157766695049,
      "grad_norm": 1.291331794933179,
      "kl": 0.045654296875,
      "learning_rate": 9.904135967017143e-07,
      "loss": 0.0018,
      "reward": 1.9118304252624512,
      "reward_std": 0.033199384808540344,
      "rewards/accuracy_reward": 0.7618303894996643,
      "rewards/format_reward": 1.0,
      "step": 2053,
      "temperature": 1.0
    },
    {
      "all_correct": 0.625,
      "all_wrong": 0.125,
      "completion_length": 369.046875,
      "epoch": 0.062461987592750276,
      "grad_norm": 0.718810920160123,
      "kl": 0.0341796875,
      "learning_rate": 9.904042854991312e-07,
      "loss": 0.0014,
      "reward": 1.859375,
      "reward_std": 0.12182654440402985,
      "rewards/accuracy_reward": 0.71875,
      "rewards/format_reward": 1.0,
      "step": 2054,
      "temperature": 1.0
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.125,
      "completion_length": 357.96875,
      "epoch": 0.062492397518550055,
      "grad_norm": 2.311793653923513,
      "kl": 0.037841796875,
      "learning_rate": 9.903949698206035e-07,
      "loss": 0.0015,
      "reward": 1.9187151193618774,
      "reward_std": 0.07667052745819092,
      "rewards/accuracy_reward": 0.7530900239944458,
      "rewards/format_reward": 1.0,
      "step": 2055,
      "temperature": 1.0
    },
    {
      "all_correct": 0.625,
      "all_wrong": 0.125,
      "completion_length": 356.40625,
      "epoch": 0.06252280744434983,
      "grad_norm": 0.759435649454247,
      "kl": 0.032958984375,
      "learning_rate": 9.90385649666216e-07,
      "loss": 0.0013,
      "reward": 1.8229310512542725,
      "reward_std": 0.045942895114421844,
      "rewards/accuracy_reward": 0.6729309558868408,
      "rewards/format_reward": 1.0,
      "step": 2056,
      "temperature": 1.0
    },
    {
      "all_correct": 0.625,
      "all_wrong": 0.125,
      "completion_length": 355.640625,
      "epoch": 0.06255321737014961,
      "grad_norm": 0.7958682915224414,
      "kl": 0.033203125,
      "learning_rate": 9.903763250360538e-07,
      "loss": 0.0013,
      "reward": 1.9847657680511475,
      "reward_std": 0.0980965867638588,
      "rewards/accuracy_reward": 0.822265625,
      "rewards/format_reward": 1.0,
      "step": 2057,
      "temperature": 1.0
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.375,
      "completion_length": 363.265625,
      "epoch": 0.06258362729594939,
      "grad_norm": 0.8520046863322858,
      "kl": 0.04052734375,
      "learning_rate": 9.903669959302017e-07,
      "loss": 0.0016,
      "reward": 1.6726926565170288,
      "reward_std": 0.013306278735399246,
      "rewards/accuracy_reward": 0.550817608833313,
      "rewards/format_reward": 1.0,
      "step": 2058,
      "temperature": 1.0
    },
    {
      "all_correct": 0.75,
      "all_wrong": 0.0,
      "completion_length": 357.6875,
      "epoch": 0.06261403722174919,
      "grad_norm": 0.7023387105896836,
      "kl": 0.03515625,
      "learning_rate": 9.903576623487455e-07,
      "loss": 0.0014,
      "reward": 2.033048629760742,
      "reward_std": 0.010209137573838234,
      "rewards/accuracy_reward": 0.8330484628677368,
      "rewards/format_reward": 1.0,
      "step": 2059,
      "temperature": 1.0
    },
    {
      "all_correct": 0.625,
      "all_wrong": 0.25,
      "completion_length": 356.328125,
      "epoch": 0.06264444714754897,
      "grad_norm": 0.5469953797085015,
      "kl": 0.03369140625,
      "learning_rate": 9.903483242917698e-07,
      "loss": 0.0013,
      "reward": 1.8161206245422363,
      "reward_std": 0.011126866564154625,
      "rewards/accuracy_reward": 0.6692456007003784,
      "rewards/format_reward": 1.0,
      "step": 2060,
      "temperature": 1.0
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.25,
      "completion_length": 360.296875,
      "epoch": 0.06267485707334874,
      "grad_norm": 1.4401091309350895,
      "kl": 0.040771484375,
      "learning_rate": 9.9033898175936e-07,
      "loss": 0.0016,
      "reward": 1.7744289636611938,
      "reward_std": 0.06001918390393257,
      "rewards/accuracy_reward": 0.6306790113449097,
      "rewards/format_reward": 1.0,
      "step": 2061,
      "temperature": 1.0
    },
    {
      "all_correct": 0.375,
      "all_wrong": 0.25,
      "completion_length": 373.421875,
      "epoch": 0.06270526699914852,
      "grad_norm": 0.9827097306894552,
      "kl": 0.037353515625,
      "learning_rate": 9.903296347516018e-07,
      "loss": 0.0015,
      "reward": 1.7161130905151367,
      "reward_std": 0.11669593304395676,
      "rewards/accuracy_reward": 0.5879881381988525,
      "rewards/format_reward": 0.984375,
      "step": 2062,
      "temperature": 1.0
    },
    {
      "all_correct": 0.375,
      "all_wrong": 0.125,
      "completion_length": 384.015625,
      "epoch": 0.0627356769249483,
      "grad_norm": 1.2227015708915272,
      "kl": 0.042236328125,
      "learning_rate": 9.903202832685798e-07,
      "loss": 0.0017,
      "reward": 1.7291587591171265,
      "reward_std": 0.13431653380393982,
      "rewards/accuracy_reward": 0.5947836637496948,
      "rewards/format_reward": 1.0,
      "step": 2063,
      "temperature": 1.0
    },
    {
      "all_correct": 0.375,
      "all_wrong": 0.0,
      "completion_length": 362.5625,
      "epoch": 0.06276608685074808,
      "grad_norm": 2.1060742388772558,
      "kl": 0.042236328125,
      "learning_rate": 9.903109273103798e-07,
      "loss": 0.0017,
      "reward": 1.665625810623169,
      "reward_std": 0.1045437604188919,
      "rewards/accuracy_reward": 0.5500007271766663,
      "rewards/format_reward": 1.0,
      "step": 2064,
      "temperature": 1.0
    },
    {
      "all_correct": 0.25,
      "all_wrong": 0.125,
      "completion_length": 364.3125,
      "epoch": 0.06279649677654786,
      "grad_norm": 1.3639985564743895,
      "kl": 0.0341796875,
      "learning_rate": 9.90301566877087e-07,
      "loss": 0.0014,
      "reward": 1.7351657152175903,
      "reward_std": 0.14109373092651367,
      "rewards/accuracy_reward": 0.5757906436920166,
      "rewards/format_reward": 1.0,
      "step": 2065,
      "temperature": 1.0
    },
    {
      "all_correct": 0.875,
      "all_wrong": 0.125,
      "completion_length": 346.3125,
      "epoch": 0.06282690670234764,
      "grad_norm": 0.06390044476202389,
      "kl": 0.03173828125,
      "learning_rate": 9.90292201968787e-07,
      "loss": 0.0013,
      "reward": 2.0500001907348633,
      "reward_std": 0.0,
      "rewards/accuracy_reward": 0.875,
      "rewards/format_reward": 1.0,
      "step": 2066,
      "temperature": 1.0
    },
    {
      "all_correct": 0.75,
      "all_wrong": 0.125,
      "completion_length": 344.09375,
      "epoch": 0.06285731662814743,
      "grad_norm": 1.342029890330942,
      "kl": 0.037109375,
      "learning_rate": 9.90282832585565e-07,
      "loss": 0.0015,
      "reward": 2.028125047683716,
      "reward_std": 0.06187184900045395,
      "rewards/accuracy_reward": 0.859375,
      "rewards/format_reward": 1.0,
      "step": 2067,
      "temperature": 1.0
    },
    {
      "all_correct": 0.625,
      "all_wrong": 0.0,
      "completion_length": 362.96875,
      "epoch": 0.06288772655394721,
      "grad_norm": 0.9718487235941278,
      "kl": 0.035400390625,
      "learning_rate": 9.902734587275068e-07,
      "loss": 0.0014,
      "reward": 1.9866228103637695,
      "reward_std": 0.01950971409678459,
      "rewards/accuracy_reward": 0.7897477149963379,
      "rewards/format_reward": 1.0,
      "step": 2068,
      "temperature": 1.0
    },
    {
      "all_correct": 0.375,
      "all_wrong": 0.0,
      "completion_length": 398.609375,
      "epoch": 0.06291813647974699,
      "grad_norm": 2.543297548995273,
      "kl": 0.03369140625,
      "learning_rate": 9.902640803946979e-07,
      "loss": 0.0014,
      "reward": 1.7768049240112305,
      "reward_std": 0.10847268998622894,
      "rewards/accuracy_reward": 0.6174298524856567,
      "rewards/format_reward": 1.0,
      "step": 2069,
      "temperature": 1.0
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.0,
      "completion_length": 387.90625,
      "epoch": 0.06294854640554677,
      "grad_norm": 1.6285946401437221,
      "kl": 0.0322265625,
      "learning_rate": 9.90254697587224e-07,
      "loss": 0.0013,
      "reward": 1.8467861413955688,
      "reward_std": 0.1362738013267517,
      "rewards/accuracy_reward": 0.6686611175537109,
      "rewards/format_reward": 1.0,
      "step": 2070,
      "temperature": 1.0
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.25,
      "completion_length": 355.28125,
      "epoch": 0.06297895633134655,
      "grad_norm": 0.6953878849235884,
      "kl": 0.037109375,
      "learning_rate": 9.902453103051702e-07,
      "loss": 0.0015,
      "reward": 1.8449684381484985,
      "reward_std": 0.01673966459929943,
      "rewards/accuracy_reward": 0.6980934143066406,
      "rewards/format_reward": 1.0,
      "step": 2071,
      "temperature": 1.0
    },
    {
      "all_correct": 0.625,
      "all_wrong": 0.0,
      "completion_length": 361.703125,
      "epoch": 0.06300936625714633,
      "grad_norm": 0.7441769832189555,
      "kl": 0.035888671875,
      "learning_rate": 9.90235918548623e-07,
      "loss": 0.0014,
      "reward": 1.853124976158142,
      "reward_std": 0.16566048562526703,
      "rewards/accuracy_reward": 0.71875,
      "rewards/format_reward": 1.0,
      "step": 2072,
      "temperature": 1.0
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.25,
      "completion_length": 393.125,
      "epoch": 0.06303977618294611,
      "grad_norm": 0.8136621660333894,
      "kl": 0.0274658203125,
      "learning_rate": 9.902265223176673e-07,
      "loss": 0.0011,
      "reward": 1.7177050113677979,
      "reward_std": 0.004691427107900381,
      "rewards/accuracy_reward": 0.5677049160003662,
      "rewards/format_reward": 1.0,
      "step": 2073,
      "temperature": 1.0
    },
    {
      "all_correct": 0.875,
      "all_wrong": 0.0,
      "completion_length": 343.140625,
      "epoch": 0.0630701861087459,
      "grad_norm": 0.8260918679094278,
      "kl": 0.04345703125,
      "learning_rate": 9.902171216123894e-07,
      "loss": 0.0017,
      "reward": 2.1187500953674316,
      "reward_std": 0.09175113588571548,
      "rewards/accuracy_reward": 0.9375,
      "rewards/format_reward": 1.0,
      "step": 2074,
      "temperature": 1.0
    },
    {
      "all_correct": 0.625,
      "all_wrong": 0.125,
      "completion_length": 349.4375,
      "epoch": 0.06310059603454568,
      "grad_norm": 8.673867948774213,
      "kl": 0.03857421875,
      "learning_rate": 9.90207716432875e-07,
      "loss": 0.0015,
      "reward": 1.8274343013763428,
      "reward_std": 0.02573998272418976,
      "rewards/accuracy_reward": 0.6711843013763428,
      "rewards/format_reward": 1.0,
      "step": 2075,
      "temperature": 1.0
    },
    {
      "all_correct": 0.375,
      "all_wrong": 0.375,
      "completion_length": 374.765625,
      "epoch": 0.06313100596034546,
      "grad_norm": 0.8607301410124202,
      "kl": 0.0267333984375,
      "learning_rate": 9.901983067792098e-07,
      "loss": 0.0011,
      "reward": 1.5982356071472168,
      "reward_std": 0.08568847179412842,
      "rewards/accuracy_reward": 0.48573556542396545,
      "rewards/format_reward": 1.0,
      "step": 2076,
      "temperature": 1.0
    },
    {
      "all_correct": 0.625,
      "all_wrong": 0.125,
      "completion_length": 356.703125,
      "epoch": 0.06316141588614524,
      "grad_norm": 12.275259101725174,
      "kl": 0.036865234375,
      "learning_rate": 9.9018889265148e-07,
      "loss": 0.0015,
      "reward": 1.9509810209274292,
      "reward_std": 0.058495841920375824,
      "rewards/accuracy_reward": 0.7791059613227844,
      "rewards/format_reward": 1.0,
      "step": 2077,
      "temperature": 1.0
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.125,
      "completion_length": 344.578125,
      "epoch": 0.06319182581194502,
      "grad_norm": 1.1744025894552494,
      "kl": 0.03369140625,
      "learning_rate": 9.90179474049771e-07,
      "loss": 0.0014,
      "reward": 1.7909038066864014,
      "reward_std": 0.054379355162382126,
      "rewards/accuracy_reward": 0.640903890132904,
      "rewards/format_reward": 1.0,
      "step": 2078,
      "temperature": 1.0
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.125,
      "completion_length": 390.140625,
      "epoch": 0.0632222357377448,
      "grad_norm": 1.7583312403110702,
      "kl": 0.03125,
      "learning_rate": 9.901700509741693e-07,
      "loss": 0.0013,
      "reward": 1.8378750085830688,
      "reward_std": 0.12378955632448196,
      "rewards/accuracy_reward": 0.6878749132156372,
      "rewards/format_reward": 1.0,
      "step": 2079,
      "temperature": 1.0
    },
    {
      "all_correct": 0.75,
      "all_wrong": 0.125,
      "completion_length": 345.28125,
      "epoch": 0.06325264566354458,
      "grad_norm": 0.6215106477964852,
      "kl": 0.037841796875,
      "learning_rate": 9.901606234247604e-07,
      "loss": 0.0015,
      "reward": 1.9750001430511475,
      "reward_std": 0.08017837256193161,
      "rewards/accuracy_reward": 0.8125,
      "rewards/format_reward": 1.0,
      "step": 2080,
      "temperature": 1.0
    },
    {
      "all_correct": 0.875,
      "all_wrong": 0.0,
      "completion_length": 335.546875,
      "epoch": 0.06328305558934436,
      "grad_norm": 0.6009034709044881,
      "kl": 0.033935546875,
      "learning_rate": 9.901511914016308e-07,
      "loss": 0.0014,
      "reward": 2.1781249046325684,
      "reward_std": 0.05250425264239311,
      "rewards/accuracy_reward": 0.984375,
      "rewards/format_reward": 1.0,
      "step": 2081,
      "temperature": 1.0
    },
    {
      "all_correct": 0.25,
      "all_wrong": 0.375,
      "completion_length": 349.875,
      "epoch": 0.06331346551514415,
      "grad_norm": 2.2534356564330698,
      "kl": 0.035400390625,
      "learning_rate": 9.901417549048664e-07,
      "loss": 0.0014,
      "reward": 1.4485280513763428,
      "reward_std": 0.07305482029914856,
      "rewards/accuracy_reward": 0.35790300369262695,
      "rewards/format_reward": 1.0,
      "step": 2082,
      "temperature": 1.0
    },
    {
      "all_correct": 0.625,
      "all_wrong": 0.0,
      "completion_length": 344.984375,
      "epoch": 0.06334387544094393,
      "grad_norm": 1.4331067924758507,
      "kl": 0.035400390625,
      "learning_rate": 9.901323139345531e-07,
      "loss": 0.0014,
      "reward": 2.029134511947632,
      "reward_std": 0.15779872238636017,
      "rewards/accuracy_reward": 0.8572593927383423,
      "rewards/format_reward": 1.0,
      "step": 2083,
      "temperature": 1.0
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.125,
      "completion_length": 360.46875,
      "epoch": 0.06337428536674371,
      "grad_norm": 2.205659566841763,
      "kl": 0.03515625,
      "learning_rate": 9.901228684907775e-07,
      "loss": 0.0014,
      "reward": 1.809924602508545,
      "reward_std": 0.030358213931322098,
      "rewards/accuracy_reward": 0.6380495429039001,
      "rewards/format_reward": 1.0,
      "step": 2084,
      "temperature": 1.0
    },
    {
      "all_correct": 0.625,
      "all_wrong": 0.0,
      "completion_length": 354.609375,
      "epoch": 0.06340469529254349,
      "grad_norm": 0.9553728749173171,
      "kl": 0.0341796875,
      "learning_rate": 9.901134185736256e-07,
      "loss": 0.0014,
      "reward": 2.0278735160827637,
      "reward_std": 0.057059720158576965,
      "rewards/accuracy_reward": 0.8278735876083374,
      "rewards/format_reward": 1.0,
      "step": 2085,
      "temperature": 1.0
    },
    {
      "all_correct": 0.75,
      "all_wrong": 0.0,
      "completion_length": 365.46875,
      "epoch": 0.06343510521834327,
      "grad_norm": 1.3824417312938044,
      "kl": 0.03466796875,
      "learning_rate": 9.901039641831836e-07,
      "loss": 0.0014,
      "reward": 2.0466792583465576,
      "reward_std": 0.020899798721075058,
      "rewards/accuracy_reward": 0.8498042821884155,
      "rewards/format_reward": 1.0,
      "step": 2086,
      "temperature": 1.0
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.125,
      "completion_length": 359.5,
      "epoch": 0.06346551514414304,
      "grad_norm": 1.5241662407322047,
      "kl": 0.03369140625,
      "learning_rate": 9.900945053195378e-07,
      "loss": 0.0014,
      "reward": 1.943068265914917,
      "reward_std": 0.11704853177070618,
      "rewards/accuracy_reward": 0.7743180990219116,
      "rewards/format_reward": 1.0,
      "step": 2087,
      "temperature": 1.0
    },
    {
      "all_correct": 0.875,
      "all_wrong": 0.0,
      "completion_length": 355.109375,
      "epoch": 0.06349592506994282,
      "grad_norm": 0.6135670801153557,
      "kl": 0.031005859375,
      "learning_rate": 9.900850419827747e-07,
      "loss": 0.0012,
      "reward": 2.1196517944335938,
      "reward_std": 0.004342858679592609,
      "rewards/accuracy_reward": 0.9196515679359436,
      "rewards/format_reward": 1.0,
      "step": 2088,
      "temperature": 1.0
    },
    {
      "all_correct": 0.75,
      "all_wrong": 0.0,
      "completion_length": 363.171875,
      "epoch": 0.06352633499574262,
      "grad_norm": 0.8937525302381855,
      "kl": 0.03564453125,
      "learning_rate": 9.900755741729804e-07,
      "loss": 0.0014,
      "reward": 2.026134729385376,
      "reward_std": 0.009340699762105942,
      "rewards/accuracy_reward": 0.8261346817016602,
      "rewards/format_reward": 1.0,
      "step": 2089,
      "temperature": 1.0
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.125,
      "completion_length": 346.21875,
      "epoch": 0.0635567449215424,
      "grad_norm": 1.4483716685126036,
      "kl": 0.043212890625,
      "learning_rate": 9.900661018902414e-07,
      "loss": 0.0017,
      "reward": 1.7777183055877686,
      "reward_std": 0.024914588779211044,
      "rewards/accuracy_reward": 0.6120931506156921,
      "rewards/format_reward": 1.0,
      "step": 2090,
      "temperature": 1.0
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.125,
      "completion_length": 382.859375,
      "epoch": 0.06358715484734218,
      "grad_norm": 1.6430604346136035,
      "kl": 0.03173828125,
      "learning_rate": 9.900566251346443e-07,
      "loss": 0.0013,
      "reward": 1.821995735168457,
      "reward_std": 0.10360874980688095,
      "rewards/accuracy_reward": 0.6688706278800964,
      "rewards/format_reward": 1.0,
      "step": 2091,
      "temperature": 1.0
    },
    {
      "all_correct": 0.625,
      "all_wrong": 0.25,
      "completion_length": 348.671875,
      "epoch": 0.06361756477314195,
      "grad_norm": 0.3690318413230103,
      "kl": 0.03369140625,
      "learning_rate": 9.900471439062756e-07,
      "loss": 0.0013,
      "reward": 1.8625000715255737,
      "reward_std": 0.06943650543689728,
      "rewards/accuracy_reward": 0.71875,
      "rewards/format_reward": 1.0,
      "step": 2092,
      "temperature": 1.0
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.375,
      "completion_length": 341.65625,
      "epoch": 0.06364797469894173,
      "grad_norm": 0.8819279449608347,
      "kl": 0.037841796875,
      "learning_rate": 9.900376582052218e-07,
      "loss": 0.0015,
      "reward": 1.6831932067871094,
      "reward_std": 0.01790298894047737,
      "rewards/accuracy_reward": 0.5613182187080383,
      "rewards/format_reward": 1.0,
      "step": 2093,
      "temperature": 1.0
    },
    {
      "all_correct": 0.125,
      "all_wrong": 0.25,
      "completion_length": 394.578125,
      "epoch": 0.06367838462474151,
      "grad_norm": 1.3029635730757725,
      "kl": 0.03466796875,
      "learning_rate": 9.900281680315693e-07,
      "loss": 0.0014,
      "reward": 1.5591199398040771,
      "reward_std": 0.15607582032680511,
      "rewards/accuracy_reward": 0.42474496364593506,
      "rewards/format_reward": 1.0,
      "step": 2094,
      "temperature": 1.0
    },
    {
      "all_correct": 0.75,
      "all_wrong": 0.125,
      "completion_length": 347.5625,
      "epoch": 0.06370879455054129,
      "grad_norm": 0.3845888449514648,
      "kl": 0.034912109375,
      "learning_rate": 9.900186733854048e-07,
      "loss": 0.0014,
      "reward": 1.9156250953674316,
      "reward_std": 0.04419417306780815,
      "rewards/accuracy_reward": 0.765625,
      "rewards/format_reward": 1.0,
      "step": 2095,
      "temperature": 1.0
    },
    {
      "all_correct": 0.125,
      "all_wrong": 0.25,
      "completion_length": 389.78125,
      "epoch": 0.06373920447634107,
      "grad_norm": 1.1474210159127085,
      "kl": 0.03369140625,
      "learning_rate": 9.90009174266815e-07,
      "loss": 0.0013,
      "reward": 1.6258864402770996,
      "reward_std": 0.13403303921222687,
      "rewards/accuracy_reward": 0.49151140451431274,
      "rewards/format_reward": 1.0,
      "step": 2096,
      "temperature": 1.0
    },
    {
      "all_correct": 0.625,
      "all_wrong": 0.25,
      "completion_length": 371.328125,
      "epoch": 0.06376961440214086,
      "grad_norm": 0.38733837417301736,
      "kl": 0.04443359375,
      "learning_rate": 9.899996706758865e-07,
      "loss": 0.0018,
      "reward": 1.8476699590682983,
      "reward_std": 0.021822111681103706,
      "rewards/accuracy_reward": 0.7039200067520142,
      "rewards/format_reward": 1.0,
      "step": 2097,
      "temperature": 1.0
    },
    {
      "all_correct": 0.25,
      "all_wrong": 0.5,
      "completion_length": 358.390625,
      "epoch": 0.06380002432794064,
      "grad_norm": 0.6300871223918846,
      "kl": 0.032470703125,
      "learning_rate": 9.899901626127063e-07,
      "loss": 0.0013,
      "reward": 1.446874976158142,
      "reward_std": 0.09722718596458435,
      "rewards/accuracy_reward": 0.375,
      "rewards/format_reward": 1.0,
      "step": 2098,
      "temperature": 1.0
    },
    {
      "all_correct": 0.625,
      "all_wrong": 0.0,
      "completion_length": 386.59375,
      "epoch": 0.06383043425374042,
      "grad_norm": 1.1097295586857874,
      "kl": 0.03955078125,
      "learning_rate": 9.89980650077361e-07,
      "loss": 0.0016,
      "reward": 1.9942893981933594,
      "reward_std": 0.04625324904918671,
      "rewards/accuracy_reward": 0.8005393743515015,
      "rewards/format_reward": 1.0,
      "step": 2099,
      "temperature": 1.0
    },
    {
      "all_correct": 0.75,
      "all_wrong": 0.0,
      "completion_length": 346.953125,
      "epoch": 0.0638608441795402,
      "grad_norm": 0.843517437587786,
      "kl": 0.04052734375,
      "learning_rate": 9.899711330699374e-07,
      "loss": 0.0016,
      "reward": 2.0448660850524902,
      "reward_std": 0.05009492486715317,
      "rewards/accuracy_reward": 0.8573660254478455,
      "rewards/format_reward": 1.0,
      "step": 2100,
      "temperature": 1.0
    },
    {
      "all_correct": 0.625,
      "all_wrong": 0.125,
      "completion_length": 378.5,
      "epoch": 0.06389125410533998,
      "grad_norm": 1.6616304646340512,
      "kl": 0.0322265625,
      "learning_rate": 9.899616115905222e-07,
      "loss": 0.0013,
      "reward": 1.7805960178375244,
      "reward_std": 0.061432041227817535,
      "rewards/accuracy_reward": 0.6493459343910217,
      "rewards/format_reward": 1.0,
      "step": 2101,
      "temperature": 1.0
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.0,
      "completion_length": 360.796875,
      "epoch": 0.06392166403113976,
      "grad_norm": 1.179245753967449,
      "kl": 0.035888671875,
      "learning_rate": 9.899520856392028e-07,
      "loss": 0.0014,
      "reward": 1.8624999523162842,
      "reward_std": 0.26953840255737305,
      "rewards/accuracy_reward": 0.71875,
      "rewards/format_reward": 1.0,
      "step": 2102,
      "temperature": 1.0
    },
    {
      "all_correct": 0.75,
      "all_wrong": 0.0,
      "completion_length": 381.921875,
      "epoch": 0.06395207395693954,
      "grad_norm": 0.8710482028837138,
      "kl": 0.036376953125,
      "learning_rate": 9.899425552160658e-07,
      "loss": 0.0015,
      "reward": 2.018749952316284,
      "reward_std": 0.16463366150856018,
      "rewards/accuracy_reward": 0.875,
      "rewards/format_reward": 0.984375,
      "step": 2103,
      "temperature": 1.0
    },
    {
      "all_correct": 0.75,
      "all_wrong": 0.125,
      "completion_length": 351.765625,
      "epoch": 0.06398248388273933,
      "grad_norm": 0.7966493759385025,
      "kl": 0.04345703125,
      "learning_rate": 9.89933020321198e-07,
      "loss": 0.0017,
      "reward": 1.963721513748169,
      "reward_std": 0.010661628097295761,
      "rewards/accuracy_reward": 0.78872150182724,
      "rewards/format_reward": 1.0,
      "step": 2104,
      "temperature": 1.0
    },
    {
      "all_correct": 0.75,
      "all_wrong": 0.125,
      "completion_length": 345.625,
      "epoch": 0.06401289380853911,
      "grad_norm": 0.9052513817437199,
      "kl": 0.0341796875,
      "learning_rate": 9.89923480954687e-07,
      "loss": 0.0014,
      "reward": 1.9406579732894897,
      "reward_std": 0.030457256361842155,
      "rewards/accuracy_reward": 0.7750329375267029,
      "rewards/format_reward": 1.0,
      "step": 2105,
      "temperature": 1.0
    },
    {
      "all_correct": 0.625,
      "all_wrong": 0.125,
      "completion_length": 363.0625,
      "epoch": 0.06404330373433889,
      "grad_norm": 1.0707722038346783,
      "kl": 0.03271484375,
      "learning_rate": 9.899139371166192e-07,
      "loss": 0.0013,
      "reward": 1.9431431293487549,
      "reward_std": 0.07140569388866425,
      "rewards/accuracy_reward": 0.7743930220603943,
      "rewards/format_reward": 1.0,
      "step": 2106,
      "temperature": 1.0
    },
    {
      "all_correct": 0.375,
      "all_wrong": 0.125,
      "completion_length": 371.25,
      "epoch": 0.06407371366013867,
      "grad_norm": 2.1538361115591074,
      "kl": 0.0390625,
      "learning_rate": 9.89904388807082e-07,
      "loss": 0.0016,
      "reward": 1.637770175933838,
      "reward_std": 0.15319609642028809,
      "rewards/accuracy_reward": 0.5252702236175537,
      "rewards/format_reward": 1.0,
      "step": 2107,
      "temperature": 1.0
    },
    {
      "all_correct": 0.25,
      "all_wrong": 0.0,
      "completion_length": 391.59375,
      "epoch": 0.06410412358593845,
      "grad_norm": 1.481038484699785,
      "kl": 0.041748046875,
      "learning_rate": 9.898948360261629e-07,
      "loss": 0.0017,
      "reward": 1.7597084045410156,
      "reward_std": 0.14945609867572784,
      "rewards/accuracy_reward": 0.5972083806991577,
      "rewards/format_reward": 1.0,
      "step": 2108,
      "temperature": 1.0
    },
    {
      "all_correct": 0.375,
      "all_wrong": 0.25,
      "completion_length": 375.859375,
      "epoch": 0.06413453351173823,
      "grad_norm": 2.2386871613419284,
      "kl": 0.041015625,
      "learning_rate": 9.898852787739486e-07,
      "loss": 0.0016,
      "reward": 1.6676735877990723,
      "reward_std": 0.16083982586860657,
      "rewards/accuracy_reward": 0.5551736354827881,
      "rewards/format_reward": 1.0,
      "step": 2109,
      "temperature": 1.0
    },
    {
      "all_correct": 0.625,
      "all_wrong": 0.375,
      "completion_length": 354.59375,
      "epoch": 0.06416494343753801,
      "grad_norm": 0.6016372562348676,
      "kl": 0.032958984375,
      "learning_rate": 9.898757170505265e-07,
      "loss": 0.0013,
      "reward": 1.747809886932373,
      "reward_std": 0.004055412020534277,
      "rewards/accuracy_reward": 0.6228098273277283,
      "rewards/format_reward": 1.0,
      "step": 2110,
      "temperature": 1.0
    },
    {
      "all_correct": 0.75,
      "all_wrong": 0.125,
      "completion_length": 349.625,
      "epoch": 0.06419535336333779,
      "grad_norm": 0.49644899713280927,
      "kl": 0.035888671875,
      "learning_rate": 9.898661508559838e-07,
      "loss": 0.0014,
      "reward": 1.9078915119171143,
      "reward_std": 0.00012754539784509689,
      "rewards/accuracy_reward": 0.7578914165496826,
      "rewards/format_reward": 1.0,
      "step": 2111,
      "temperature": 1.0
    },
    {
      "all_correct": 0.625,
      "all_wrong": 0.125,
      "completion_length": 347.359375,
      "epoch": 0.06422576328913758,
      "grad_norm": 1.0031867975779312,
      "kl": 0.03662109375,
      "learning_rate": 9.89856580190408e-07,
      "loss": 0.0015,
      "reward": 1.8902798891067505,
      "reward_std": 0.07828083634376526,
      "rewards/accuracy_reward": 0.7340297698974609,
      "rewards/format_reward": 1.0,
      "step": 2112,
      "temperature": 1.0
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.125,
      "completion_length": 374.109375,
      "epoch": 0.06425617321493736,
      "grad_norm": 4.923614028240135,
      "kl": 0.041015625,
      "learning_rate": 9.89847005053886e-07,
      "loss": 0.0016,
      "reward": 1.8250000476837158,
      "reward_std": 0.15982910990715027,
      "rewards/accuracy_reward": 0.6875,
      "rewards/format_reward": 1.0,
      "step": 2113,
      "temperature": 1.0
    },
    {
      "all_correct": 0.25,
      "all_wrong": 0.375,
      "completion_length": 334.203125,
      "epoch": 0.06428658314073714,
      "grad_norm": 1.8741822864756679,
      "kl": 0.035400390625,
      "learning_rate": 9.89837425446506e-07,
      "loss": 0.0014,
      "reward": 1.44376802444458,
      "reward_std": 0.1725069284439087,
      "rewards/accuracy_reward": 0.36876797676086426,
      "rewards/format_reward": 1.0,
      "step": 2114,
      "temperature": 1.0
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.25,
      "completion_length": 338.421875,
      "epoch": 0.06431699306653692,
      "grad_norm": 1.6241743383818346,
      "kl": 0.033447265625,
      "learning_rate": 9.898278413683546e-07,
      "loss": 0.0013,
      "reward": 1.7639122009277344,
      "reward_std": 0.09392809867858887,
      "rewards/accuracy_reward": 0.6357871294021606,
      "rewards/format_reward": 1.0,
      "step": 2115,
      "temperature": 1.0
    },
    {
      "all_correct": 0.625,
      "all_wrong": 0.125,
      "completion_length": 355.234375,
      "epoch": 0.0643474029923367,
      "grad_norm": 0.9209420410759019,
      "kl": 0.0380859375,
      "learning_rate": 9.898182528195198e-07,
      "loss": 0.0015,
      "reward": 2.0031251907348633,
      "reward_std": 0.11362677067518234,
      "rewards/accuracy_reward": 0.84375,
      "rewards/format_reward": 1.0,
      "step": 2116,
      "temperature": 1.0
    },
    {
      "all_correct": 0.375,
      "all_wrong": 0.0,
      "completion_length": 383.5625,
      "epoch": 0.06437781291813648,
      "grad_norm": 1.16749473761527,
      "kl": 0.033203125,
      "learning_rate": 9.89808659800089e-07,
      "loss": 0.0013,
      "reward": 1.8255112171173096,
      "reward_std": 0.14966201782226562,
      "rewards/accuracy_reward": 0.6473861932754517,
      "rewards/format_reward": 1.0,
      "step": 2117,
      "temperature": 1.0
    },
    {
      "all_correct": 0.625,
      "all_wrong": 0.0,
      "completion_length": 333.34375,
      "epoch": 0.06440822284393626,
      "grad_norm": 1.1352405885948824,
      "kl": 0.04296875,
      "learning_rate": 9.897990623101496e-07,
      "loss": 0.0017,
      "reward": 2.0041370391845703,
      "reward_std": 0.08043959736824036,
      "rewards/accuracy_reward": 0.8322620391845703,
      "rewards/format_reward": 1.0,
      "step": 2118,
      "temperature": 1.0
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.25,
      "completion_length": 365.6875,
      "epoch": 0.06443863276973605,
      "grad_norm": 1.0439086736504721,
      "kl": 0.031494140625,
      "learning_rate": 9.897894603497892e-07,
      "loss": 0.0013,
      "reward": 1.7449532747268677,
      "reward_std": 0.09416370838880539,
      "rewards/accuracy_reward": 0.6230782270431519,
      "rewards/format_reward": 1.0,
      "step": 2119,
      "temperature": 1.0
    },
    {
      "all_correct": 0.75,
      "all_wrong": 0.125,
      "completion_length": 359.734375,
      "epoch": 0.06446904269553583,
      "grad_norm": 0.9559940599663257,
      "kl": 0.032470703125,
      "learning_rate": 9.897798539190957e-07,
      "loss": 0.0013,
      "reward": 1.9458057880401611,
      "reward_std": 0.015595316886901855,
      "rewards/accuracy_reward": 0.7739309072494507,
      "rewards/format_reward": 1.0,
      "step": 2120,
      "temperature": 1.0
    },
    {
      "all_correct": 0.375,
      "all_wrong": 0.125,
      "completion_length": 379.625,
      "epoch": 0.0644994526213356,
      "grad_norm": 1.3634067621699748,
      "kl": 0.041259765625,
      "learning_rate": 9.897702430181566e-07,
      "loss": 0.0017,
      "reward": 1.7735090255737305,
      "reward_std": 0.13696910440921783,
      "rewards/accuracy_reward": 0.6297589540481567,
      "rewards/format_reward": 1.0,
      "step": 2121,
      "temperature": 1.0
    },
    {
      "all_correct": 0.625,
      "all_wrong": 0.125,
      "completion_length": 351.859375,
      "epoch": 0.06452986254713539,
      "grad_norm": 0.9028272330045392,
      "kl": 0.03076171875,
      "learning_rate": 9.897606276470593e-07,
      "loss": 0.0012,
      "reward": 1.8594133853912354,
      "reward_std": 0.08496332168579102,
      "rewards/accuracy_reward": 0.7062882781028748,
      "rewards/format_reward": 1.0,
      "step": 2122,
      "temperature": 1.0
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.0,
      "completion_length": 358.84375,
      "epoch": 0.06456027247293517,
      "grad_norm": 3.2060297209328836,
      "kl": 0.03369140625,
      "learning_rate": 9.897510078058922e-07,
      "loss": 0.0013,
      "reward": 1.8825440406799316,
      "reward_std": 0.08603426069021225,
      "rewards/accuracy_reward": 0.7106691002845764,
      "rewards/format_reward": 1.0,
      "step": 2123,
      "temperature": 1.0
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.0,
      "completion_length": 331.484375,
      "epoch": 0.06459068239873494,
      "grad_norm": 1.8349227523760465,
      "kl": 0.049072265625,
      "learning_rate": 9.897413834947427e-07,
      "loss": 0.002,
      "reward": 1.9387884140014648,
      "reward_std": 0.2935318350791931,
      "rewards/accuracy_reward": 0.7887883186340332,
      "rewards/format_reward": 1.0,
      "step": 2124,
      "temperature": 1.0
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.0,
      "completion_length": 367.578125,
      "epoch": 0.06462109232453472,
      "grad_norm": 1.3528003309215921,
      "kl": 0.04443359375,
      "learning_rate": 9.897317547136988e-07,
      "loss": 0.0018,
      "reward": 1.8656044006347656,
      "reward_std": 0.14573940634727478,
      "rewards/accuracy_reward": 0.7031044363975525,
      "rewards/format_reward": 1.0,
      "step": 2125,
      "temperature": 1.0
    },
    {
      "all_correct": 0.375,
      "all_wrong": 0.25,
      "completion_length": 379.125,
      "epoch": 0.0646515022503345,
      "grad_norm": 0.8343527303239737,
      "kl": 0.044189453125,
      "learning_rate": 9.897221214628484e-07,
      "loss": 0.0018,
      "reward": 1.6528196334838867,
      "reward_std": 0.10057816654443741,
      "rewards/accuracy_reward": 0.5278196334838867,
      "rewards/format_reward": 1.0,
      "step": 2126,
      "temperature": 1.0
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.125,
      "completion_length": 370.9375,
      "epoch": 0.0646819121761343,
      "grad_norm": 9.679084889740105,
      "kl": 0.04443359375,
      "learning_rate": 9.897124837422792e-07,
      "loss": 0.0018,
      "reward": 1.7644470930099487,
      "reward_std": 0.16008460521697998,
      "rewards/accuracy_reward": 0.6394469738006592,
      "rewards/format_reward": 1.0,
      "step": 2127,
      "temperature": 1.0
    },
    {
      "all_correct": 0.375,
      "all_wrong": 0.125,
      "completion_length": 374.8125,
      "epoch": 0.06471232210193407,
      "grad_norm": 0.6768542554282132,
      "kl": 0.04443359375,
      "learning_rate": 9.897028415520792e-07,
      "loss": 0.0018,
      "reward": 1.7843749523162842,
      "reward_std": 0.25249195098876953,
      "rewards/accuracy_reward": 0.65625,
      "rewards/format_reward": 1.0,
      "step": 2128,
      "temperature": 1.0
    },
    {
      "all_correct": 0.25,
      "all_wrong": 0.125,
      "completion_length": 376.859375,
      "epoch": 0.06474273202773385,
      "grad_norm": 2.4895048492459355,
      "kl": 0.046630859375,
      "learning_rate": 9.896931948923366e-07,
      "loss": 0.0019,
      "reward": 1.5706278085708618,
      "reward_std": 0.14404921233654022,
      "rewards/accuracy_reward": 0.43625274300575256,
      "rewards/format_reward": 1.0,
      "step": 2129,
      "temperature": 1.0
    },
    {
      "all_correct": 0.625,
      "all_wrong": 0.0,
      "completion_length": 363.125,
      "epoch": 0.06477314195353363,
      "grad_norm": 1.8097071372255122,
      "kl": 0.042236328125,
      "learning_rate": 9.896835437631394e-07,
      "loss": 0.0017,
      "reward": 2.0391857624053955,
      "reward_std": 0.08121491223573685,
      "rewards/accuracy_reward": 0.8485608100891113,
      "rewards/format_reward": 1.0,
      "step": 2130,
      "temperature": 1.0
    },
    {
      "all_correct": 0.75,
      "all_wrong": 0.125,
      "completion_length": 343.5,
      "epoch": 0.06480355187933341,
      "grad_norm": 0.5344462016106117,
      "kl": 0.042236328125,
      "learning_rate": 9.896738881645757e-07,
      "loss": 0.0017,
      "reward": 1.959800362586975,
      "reward_std": 0.008134474977850914,
      "rewards/accuracy_reward": 0.7848003506660461,
      "rewards/format_reward": 1.0,
      "step": 2131,
      "temperature": 1.0
    },
    {
      "all_correct": 0.375,
      "all_wrong": 0.0,
      "completion_length": 352.421875,
      "epoch": 0.06483396180513319,
      "grad_norm": 1.9622838639713318,
      "kl": 0.05029296875,
      "learning_rate": 9.896642280967334e-07,
      "loss": 0.002,
      "reward": 1.695159912109375,
      "reward_std": 0.12434754520654678,
      "rewards/accuracy_reward": 0.5451599359512329,
      "rewards/format_reward": 1.0,
      "step": 2132,
      "temperature": 1.0
    },
    {
      "all_correct": 0.25,
      "all_wrong": 0.25,
      "completion_length": 390.859375,
      "epoch": 0.06486437173093297,
      "grad_norm": 1.1807476420805225,
      "kl": 0.048095703125,
      "learning_rate": 9.896545635597008e-07,
      "loss": 0.0019,
      "reward": 1.6558191776275635,
      "reward_std": 0.12571552395820618,
      "rewards/accuracy_reward": 0.527694046497345,
      "rewards/format_reward": 1.0,
      "step": 2133,
      "temperature": 1.0
    },
    {
      "all_correct": 0.25,
      "all_wrong": 0.0,
      "completion_length": 389.859375,
      "epoch": 0.06489478165673276,
      "grad_norm": 2.2794949432996567,
      "kl": 0.0439453125,
      "learning_rate": 9.896448945535666e-07,
      "loss": 0.0018,
      "reward": 1.6754416227340698,
      "reward_std": 0.07964123785495758,
      "rewards/accuracy_reward": 0.48481661081314087,
      "rewards/format_reward": 1.0,
      "step": 2134,
      "temperature": 1.0
    },
    {
      "all_correct": 0.75,
      "all_wrong": 0.125,
      "completion_length": 350.546875,
      "epoch": 0.06492519158253254,
      "grad_norm": 0.39648808946114733,
      "kl": 0.0537109375,
      "learning_rate": 9.89635221078418e-07,
      "loss": 0.0022,
      "reward": 1.915624976158142,
      "reward_std": 0.04419417306780815,
      "rewards/accuracy_reward": 0.765625,
      "rewards/format_reward": 1.0,
      "step": 2135,
      "temperature": 1.0
    },
    {
      "all_correct": 0.875,
      "all_wrong": 0.0,
      "completion_length": 347.984375,
      "epoch": 0.06495560150833232,
      "grad_norm": 0.6958096708660882,
      "kl": 0.040283203125,
      "learning_rate": 9.896255431343441e-07,
      "loss": 0.0016,
      "reward": 2.0572917461395264,
      "reward_std": 0.03830162435770035,
      "rewards/accuracy_reward": 0.8854166865348816,
      "rewards/format_reward": 1.0,
      "step": 2136,
      "temperature": 1.0
    },
    {
      "all_correct": 0.625,
      "all_wrong": 0.0,
      "completion_length": 353.234375,
      "epoch": 0.0649860114341321,
      "grad_norm": 1.3734723441313546,
      "kl": 0.04931640625,
      "learning_rate": 9.896158607214332e-07,
      "loss": 0.002,
      "reward": 1.982656717300415,
      "reward_std": 0.1639942079782486,
      "rewards/accuracy_reward": 0.8045315146446228,
      "rewards/format_reward": 1.0,
      "step": 2137,
      "temperature": 1.0
    },
    {
      "all_correct": 0.375,
      "all_wrong": 0.25,
      "completion_length": 361.0,
      "epoch": 0.06501642135993188,
      "grad_norm": 1.0542050232427072,
      "kl": 0.046630859375,
      "learning_rate": 9.89606173839773e-07,
      "loss": 0.0019,
      "reward": 1.6927616596221924,
      "reward_std": 0.04832878336310387,
      "rewards/accuracy_reward": 0.5521366596221924,
      "rewards/format_reward": 1.0,
      "step": 2138,
      "temperature": 1.0
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.125,
      "completion_length": 365.703125,
      "epoch": 0.06504683128573166,
      "grad_norm": 2.208117656458588,
      "kl": 0.04345703125,
      "learning_rate": 9.895964824894529e-07,
      "loss": 0.0017,
      "reward": 1.6826171875,
      "reward_std": 0.1700640767812729,
      "rewards/accuracy_reward": 0.5732421875,
      "rewards/format_reward": 1.0,
      "step": 2139,
      "temperature": 1.0
    },
    {
      "all_correct": 0.625,
      "all_wrong": 0.125,
      "completion_length": 347.71875,
      "epoch": 0.06507724121153144,
      "grad_norm": 1.884391376198748,
      "kl": 0.047607421875,
      "learning_rate": 9.895867866705608e-07,
      "loss": 0.0019,
      "reward": 2.0107929706573486,
      "reward_std": 0.06136559322476387,
      "rewards/accuracy_reward": 0.845167875289917,
      "rewards/format_reward": 1.0,
      "step": 2140,
      "temperature": 1.0
    },
    {
      "all_correct": 0.75,
      "all_wrong": 0.25,
      "completion_length": 345.546875,
      "epoch": 0.06510765113733122,
      "grad_norm": 0.5364680597865498,
      "kl": 0.0537109375,
      "learning_rate": 9.895770863831851e-07,
      "loss": 0.0021,
      "reward": 1.8968751430511475,
      "reward_std": 0.008838837966322899,
      "rewards/accuracy_reward": 0.75,
      "rewards/format_reward": 1.0,
      "step": 2141,
      "temperature": 1.0
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.25,
      "completion_length": 372.046875,
      "epoch": 0.06513806106313101,
      "grad_norm": 1.8535781240385485,
      "kl": 0.047119140625,
      "learning_rate": 9.895673816274144e-07,
      "loss": 0.0019,
      "reward": 1.7141551971435547,
      "reward_std": 0.06155017763376236,
      "rewards/accuracy_reward": 0.5922801494598389,
      "rewards/format_reward": 1.0,
      "step": 2142,
      "temperature": 1.0
    },
    {
      "all_correct": 0.625,
      "all_wrong": 0.25,
      "completion_length": 362.015625,
      "epoch": 0.06516847098893079,
      "grad_norm": 8.912827278175117,
      "kl": 0.040283203125,
      "learning_rate": 9.895576724033376e-07,
      "loss": 0.0016,
      "reward": 1.8562500476837158,
      "reward_std": 0.08100926131010056,
      "rewards/accuracy_reward": 0.71875,
      "rewards/format_reward": 1.0,
      "step": 2143,
      "temperature": 1.0
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.125,
      "completion_length": 388.375,
      "epoch": 0.06519888091473057,
      "grad_norm": 1.0740971487586592,
      "kl": 0.043701171875,
      "learning_rate": 9.89547958711043e-07,
      "loss": 0.0017,
      "reward": 1.686990737915039,
      "reward_std": 0.0771588385105133,
      "rewards/accuracy_reward": 0.568240761756897,
      "rewards/format_reward": 1.0,
      "step": 2144,
      "temperature": 1.0
    },
    {
      "all_correct": 0.375,
      "all_wrong": 0.25,
      "completion_length": 385.015625,
      "epoch": 0.06522929084053035,
      "grad_norm": 0.9200854899031182,
      "kl": 0.042236328125,
      "learning_rate": 9.89538240550619e-07,
      "loss": 0.0017,
      "reward": 1.6555705070495605,
      "reward_std": 0.11085636913776398,
      "rewards/accuracy_reward": 0.5493203997612,
      "rewards/format_reward": 0.984375,
      "step": 2145,
      "temperature": 1.0
    },
    {
      "all_correct": 0.375,
      "all_wrong": 0.125,
      "completion_length": 368.25,
      "epoch": 0.06525970076633013,
      "grad_norm": 0.7352006757712228,
      "kl": 0.033203125,
      "learning_rate": 9.89528517922155e-07,
      "loss": 0.0013,
      "reward": 1.743749976158142,
      "reward_std": 0.28969788551330566,
      "rewards/accuracy_reward": 0.625,
      "rewards/format_reward": 1.0,
      "step": 2146,
      "temperature": 1.0
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.25,
      "completion_length": 368.8125,
      "epoch": 0.06529011069212991,
      "grad_norm": 0.45823322028731206,
      "kl": 0.04736328125,
      "learning_rate": 9.895187908257394e-07,
      "loss": 0.0019,
      "reward": 1.6906250715255737,
      "reward_std": 0.12437255680561066,
      "rewards/accuracy_reward": 0.578125,
      "rewards/format_reward": 1.0,
      "step": 2147,
      "temperature": 1.0
    },
    {
      "all_correct": 0.625,
      "all_wrong": 0.125,
      "completion_length": 342.84375,
      "epoch": 0.06532052061792969,
      "grad_norm": 0.7338883775498909,
      "kl": 0.042724609375,
      "learning_rate": 9.895090592614608e-07,
      "loss": 0.0017,
      "reward": 1.880029559135437,
      "reward_std": 0.0859389528632164,
      "rewards/accuracy_reward": 0.7237794995307922,
      "rewards/format_reward": 1.0,
      "step": 2148,
      "temperature": 1.0
    },
    {
      "all_correct": 0.125,
      "all_wrong": 0.0,
      "completion_length": 363.640625,
      "epoch": 0.06535093054372948,
      "grad_norm": 1.4019951462933893,
      "kl": 0.036865234375,
      "learning_rate": 9.89499323229408e-07,
      "loss": 0.0015,
      "reward": 1.7609286308288574,
      "reward_std": 0.37728893756866455,
      "rewards/accuracy_reward": 0.6203036308288574,
      "rewards/format_reward": 1.0,
      "step": 2149,
      "temperature": 1.0
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.5,
      "completion_length": 336.4375,
      "epoch": 0.06538134046952926,
      "grad_norm": 0.06367687563436776,
      "kl": 0.03515625,
      "learning_rate": 9.894895827296703e-07,
      "loss": 0.0014,
      "reward": 1.600000023841858,
      "reward_std": 0.0,
      "rewards/accuracy_reward": 0.5,
      "rewards/format_reward": 1.0,
      "step": 2150,
      "temperature": 1.0
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.125,
      "completion_length": 351.859375,
      "epoch": 0.06541175039532904,
      "grad_norm": 0.9252965806375493,
      "kl": 0.037109375,
      "learning_rate": 9.89479837762336e-07,
      "loss": 0.0015,
      "reward": 1.7753630876541138,
      "reward_std": 0.12900525331497192,
      "rewards/accuracy_reward": 0.6441130638122559,
      "rewards/format_reward": 1.0,
      "step": 2151,
      "temperature": 1.0
    },
    {
      "all_correct": 0.375,
      "all_wrong": 0.25,
      "completion_length": 358.484375,
      "epoch": 0.06544216032112882,
      "grad_norm": 1.1239139810826408,
      "kl": 0.04052734375,
      "learning_rate": 9.894700883274948e-07,
      "loss": 0.0016,
      "reward": 1.5656399726867676,
      "reward_std": 0.09243050217628479,
      "rewards/accuracy_reward": 0.4562648832798004,
      "rewards/format_reward": 1.0,
      "step": 2152,
      "temperature": 1.0
    },
    {
      "all_correct": 0.625,
      "all_wrong": 0.0,
      "completion_length": 430.609375,
      "epoch": 0.0654725702469286,
      "grad_norm": 0.5322576485153732,
      "kl": 0.027099609375,
      "learning_rate": 9.89460334425235e-07,
      "loss": 0.0011,
      "reward": 1.8913309574127197,
      "reward_std": 0.2120649814605713,
      "rewards/accuracy_reward": 0.8007059097290039,
      "rewards/format_reward": 0.9375,
      "step": 2153,
      "temperature": 1.0
    },
    {
      "all_correct": 0.375,
      "all_wrong": 0.125,
      "completion_length": 376.375,
      "epoch": 0.06550298017272838,
      "grad_norm": 2.0366863215589825,
      "kl": 0.043212890625,
      "learning_rate": 9.89450576055646e-07,
      "loss": 0.0017,
      "reward": 1.8033990859985352,
      "reward_std": 0.17502304911613464,
      "rewards/accuracy_reward": 0.6502741575241089,
      "rewards/format_reward": 1.0,
      "step": 2154,
      "temperature": 1.0
    },
    {
      "all_correct": 0.625,
      "all_wrong": 0.0,
      "completion_length": 389.859375,
      "epoch": 0.06553339009852815,
      "grad_norm": 1.1680208213511205,
      "kl": 0.03125,
      "learning_rate": 9.894408132188167e-07,
      "loss": 0.0013,
      "reward": 1.9641649723052979,
      "reward_std": 0.17212986946105957,
      "rewards/accuracy_reward": 0.798539936542511,
      "rewards/format_reward": 1.0,
      "step": 2155,
      "temperature": 1.0
    },
    {
      "all_correct": 0.625,
      "all_wrong": 0.125,
      "completion_length": 335.453125,
      "epoch": 0.06556380002432793,
      "grad_norm": 1.5757252253835234,
      "kl": 0.044677734375,
      "learning_rate": 9.894310459148363e-07,
      "loss": 0.0018,
      "reward": 1.915624976158142,
      "reward_std": 0.13130834698677063,
      "rewards/accuracy_reward": 0.765625,
      "rewards/format_reward": 1.0,
      "step": 2156,
      "temperature": 1.0
    },
    {
      "all_correct": 0.75,
      "all_wrong": 0.0,
      "completion_length": 356.5,
      "epoch": 0.06559420995012773,
      "grad_norm": 1.092003969800466,
      "kl": 0.03125,
      "learning_rate": 9.894212741437937e-07,
      "loss": 0.0012,
      "reward": 1.9278312921524048,
      "reward_std": 0.07658499479293823,
      "rewards/accuracy_reward": 0.7747061848640442,
      "rewards/format_reward": 1.0,
      "step": 2157,
      "temperature": 1.0
    },
    {
      "all_correct": 0.625,
      "all_wrong": 0.125,
      "completion_length": 366.40625,
      "epoch": 0.0656246198759275,
      "grad_norm": 0.6802086568691329,
      "kl": 0.037353515625,
      "learning_rate": 9.894114979057786e-07,
      "loss": 0.0015,
      "reward": 1.9343750476837158,
      "reward_std": 0.1467086374759674,
      "rewards/accuracy_reward": 0.78125,
      "rewards/format_reward": 1.0,
      "step": 2158,
      "temperature": 1.0
    },
    {
      "all_correct": 0.375,
      "all_wrong": 0.0,
      "completion_length": 342.78125,
      "epoch": 0.06565502980172729,
      "grad_norm": 1.2788573230426565,
      "kl": 0.035400390625,
      "learning_rate": 9.894017172008798e-07,
      "loss": 0.0014,
      "reward": 1.8436254262924194,
      "reward_std": 0.24868270754814148,
      "rewards/accuracy_reward": 0.6873753666877747,
      "rewards/format_reward": 1.0,
      "step": 2159,
      "temperature": 1.0
    },
    {
      "all_correct": 0.75,
      "all_wrong": 0.0,
      "completion_length": 376.671875,
      "epoch": 0.06568543972752706,
      "grad_norm": 2.2527442517709186,
      "kl": 0.03955078125,
      "learning_rate": 9.893919320291864e-07,
      "loss": 0.0016,
      "reward": 1.9951844215393066,
      "reward_std": 0.03023550845682621,
      "rewards/accuracy_reward": 0.8170594573020935,
      "rewards/format_reward": 1.0,
      "step": 2160,
      "temperature": 1.0
    },
    {
      "all_correct": 0.625,
      "all_wrong": 0.0,
      "completion_length": 360.390625,
      "epoch": 0.06571584965332684,
      "grad_norm": 1.077928703248801,
      "kl": 0.040283203125,
      "learning_rate": 9.893821423907884e-07,
      "loss": 0.0016,
      "reward": 2.0173511505126953,
      "reward_std": 0.07441163063049316,
      "rewards/accuracy_reward": 0.8298512697219849,
      "rewards/format_reward": 1.0,
      "step": 2161,
      "temperature": 1.0
    },
    {
      "all_correct": 0.75,
      "all_wrong": 0.125,
      "completion_length": 361.5,
      "epoch": 0.06574625957912662,
      "grad_norm": 1.1783431411999512,
      "kl": 0.04345703125,
      "learning_rate": 9.893723482857746e-07,
      "loss": 0.0017,
      "reward": 1.921875,
      "reward_std": 0.11572164297103882,
      "rewards/accuracy_reward": 0.796875,
      "rewards/format_reward": 1.0,
      "step": 2162,
      "temperature": 1.0
    },
    {
      "all_correct": 0.625,
      "all_wrong": 0.125,
      "completion_length": 351.46875,
      "epoch": 0.0657766695049264,
      "grad_norm": 3.157449754843279,
      "kl": 0.046142578125,
      "learning_rate": 9.893625497142345e-07,
      "loss": 0.0018,
      "reward": 1.8677895069122314,
      "reward_std": 0.0447576679289341,
      "rewards/accuracy_reward": 0.7052894830703735,
      "rewards/format_reward": 1.0,
      "step": 2163,
      "temperature": 1.0
    },
    {
      "all_correct": 0.625,
      "all_wrong": 0.125,
      "completion_length": 343.28125,
      "epoch": 0.0658070794307262,
      "grad_norm": 1.0470054634982928,
      "kl": 0.037841796875,
      "learning_rate": 9.893527466762575e-07,
      "loss": 0.0015,
      "reward": 1.8531250953674316,
      "reward_std": 0.13950422406196594,
      "rewards/accuracy_reward": 0.71875,
      "rewards/format_reward": 1.0,
      "step": 2164,
      "temperature": 1.0
    },
    {
      "all_correct": 0.375,
      "all_wrong": 0.25,
      "completion_length": 379.734375,
      "epoch": 0.06583748935652597,
      "grad_norm": 1.2186945096011434,
      "kl": 0.03857421875,
      "learning_rate": 9.89342939171933e-07,
      "loss": 0.0015,
      "reward": 1.7369017601013184,
      "reward_std": 0.04994848370552063,
      "rewards/accuracy_reward": 0.5994017720222473,
      "rewards/format_reward": 1.0,
      "step": 2165,
      "temperature": 1.0
    },
    {
      "all_correct": 0.625,
      "all_wrong": 0.125,
      "completion_length": 359.578125,
      "epoch": 0.06586789928232575,
      "grad_norm": 0.5178990465717023,
      "kl": 0.0250244140625,
      "learning_rate": 9.89333127201351e-07,
      "loss": 0.001,
      "reward": 1.9000000953674316,
      "reward_std": 0.13887301087379456,
      "rewards/accuracy_reward": 0.75,
      "rewards/format_reward": 1.0,
      "step": 2166,
      "temperature": 1.0
    },
    {
      "all_correct": 0.625,
      "all_wrong": 0.125,
      "completion_length": 359.234375,
      "epoch": 0.06589830920812553,
      "grad_norm": 0.9568610125398591,
      "kl": 0.044921875,
      "learning_rate": 9.893233107646006e-07,
      "loss": 0.0018,
      "reward": 1.8965741395950317,
      "reward_std": 0.11531075835227966,
      "rewards/accuracy_reward": 0.740324079990387,
      "rewards/format_reward": 1.0,
      "step": 2167,
      "temperature": 1.0
    },
    {
      "all_correct": 0.875,
      "all_wrong": 0.0,
      "completion_length": 345.828125,
      "epoch": 0.06592871913392531,
      "grad_norm": 1.0975191212109643,
      "kl": 0.048095703125,
      "learning_rate": 9.893134898617714e-07,
      "loss": 0.0019,
      "reward": 2.094196319580078,
      "reward_std": 0.08892960101366043,
      "rewards/accuracy_reward": 0.9098214507102966,
      "rewards/format_reward": 1.0,
      "step": 2168,
      "temperature": 1.0
    },
    {
      "all_correct": 0.625,
      "all_wrong": 0.0,
      "completion_length": 339.328125,
      "epoch": 0.06595912905972509,
      "grad_norm": 1.4292095285075697,
      "kl": 0.03759765625,
      "learning_rate": 9.893036644929534e-07,
      "loss": 0.0015,
      "reward": 1.9753940105438232,
      "reward_std": 0.15661275386810303,
      "rewards/accuracy_reward": 0.8160189390182495,
      "rewards/format_reward": 1.0,
      "step": 2169,
      "temperature": 1.0
    },
    {
      "all_correct": 0.625,
      "all_wrong": 0.0,
      "completion_length": 355.984375,
      "epoch": 0.06598953898552487,
      "grad_norm": 1.1597201143826492,
      "kl": 0.034423828125,
      "learning_rate": 9.892938346582357e-07,
      "loss": 0.0014,
      "reward": 2.027740001678467,
      "reward_std": 0.10970516502857208,
      "rewards/accuracy_reward": 0.8433650135993958,
      "rewards/format_reward": 1.0,
      "step": 2170,
      "temperature": 1.0
    },
    {
      "all_correct": 0.625,
      "all_wrong": 0.0,
      "completion_length": 381.0,
      "epoch": 0.06601994891132465,
      "grad_norm": 0.8697326730523995,
      "kl": 0.041015625,
      "learning_rate": 9.892840003577083e-07,
      "loss": 0.0016,
      "reward": 1.9620141983032227,
      "reward_std": 0.03178410977125168,
      "rewards/accuracy_reward": 0.7745140790939331,
      "rewards/format_reward": 1.0,
      "step": 2171,
      "temperature": 1.0
    },
    {
      "all_correct": 0.375,
      "all_wrong": 0.25,
      "completion_length": 376.09375,
      "epoch": 0.06605035883712444,
      "grad_norm": 0.8429770118738523,
      "kl": 0.044189453125,
      "learning_rate": 9.892741615914613e-07,
      "loss": 0.0018,
      "reward": 1.7590655088424683,
      "reward_std": 0.06664355099201202,
      "rewards/accuracy_reward": 0.6184403896331787,
      "rewards/format_reward": 1.0,
      "step": 2172,
      "temperature": 1.0
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.125,
      "completion_length": 357.28125,
      "epoch": 0.06608076876292422,
      "grad_norm": 1.308018558209081,
      "kl": 0.04443359375,
      "learning_rate": 9.89264318359584e-07,
      "loss": 0.0018,
      "reward": 1.8214643001556396,
      "reward_std": 0.16325393319129944,
      "rewards/accuracy_reward": 0.6714643836021423,
      "rewards/format_reward": 1.0,
      "step": 2173,
      "temperature": 1.0
    },
    {
      "all_correct": 0.25,
      "all_wrong": 0.25,
      "completion_length": 366.59375,
      "epoch": 0.066111178688724,
      "grad_norm": 1.9116182256325975,
      "kl": 0.03955078125,
      "learning_rate": 9.892544706621665e-07,
      "loss": 0.0016,
      "reward": 1.6888889074325562,
      "reward_std": 0.15620636940002441,
      "rewards/accuracy_reward": 0.5607638955116272,
      "rewards/format_reward": 1.0,
      "step": 2174,
      "temperature": 1.0
    },
    {
      "all_correct": 0.25,
      "all_wrong": 0.25,
      "completion_length": 366.09375,
      "epoch": 0.06614158861452378,
      "grad_norm": 0.9579836230289398,
      "kl": 0.041015625,
      "learning_rate": 9.892446184992987e-07,
      "loss": 0.0016,
      "reward": 1.55078125,
      "reward_std": 0.20485760271549225,
      "rewards/accuracy_reward": 0.45703125,
      "rewards/format_reward": 1.0,
      "step": 2175,
      "temperature": 1.0
    },
    {
      "all_correct": 0.625,
      "all_wrong": 0.0,
      "completion_length": 362.96875,
      "epoch": 0.06617199854032356,
      "grad_norm": 0.9432513111254556,
      "kl": 0.03857421875,
      "learning_rate": 9.8923476187107e-07,
      "loss": 0.0015,
      "reward": 1.9913735389709473,
      "reward_std": 0.07396546006202698,
      "rewards/accuracy_reward": 0.7976235151290894,
      "rewards/format_reward": 1.0,
      "step": 2176,
      "temperature": 1.0
    },
    {
      "all_correct": 0.375,
      "all_wrong": 0.25,
      "completion_length": 345.40625,
      "epoch": 0.06620240846612334,
      "grad_norm": 1.5921816086785212,
      "kl": 0.032470703125,
      "learning_rate": 9.892249007775713e-07,
      "loss": 0.0013,
      "reward": 1.6612179279327393,
      "reward_std": 0.1332113891839981,
      "rewards/accuracy_reward": 0.5518429279327393,
      "rewards/format_reward": 1.0,
      "step": 2177,
      "temperature": 1.0
    },
    {
      "all_correct": 0.125,
      "all_wrong": 0.125,
      "completion_length": 422.984375,
      "epoch": 0.06623281839192312,
      "grad_norm": 1.7138908857733282,
      "kl": 0.0301513671875,
      "learning_rate": 9.89215035218892e-07,
      "loss": 0.0012,
      "reward": 1.5531978607177734,
      "reward_std": 0.2504054009914398,
      "rewards/accuracy_reward": 0.4344477653503418,
      "rewards/format_reward": 1.0,
      "step": 2178,
      "temperature": 1.0
    },
    {
      "all_correct": 0.625,
      "all_wrong": 0.125,
      "completion_length": 350.234375,
      "epoch": 0.06626322831772291,
      "grad_norm": 7.959994559815919,
      "kl": 0.034423828125,
      "learning_rate": 9.89205165195122e-07,
      "loss": 0.0014,
      "reward": 1.8781249523162842,
      "reward_std": 0.15590772032737732,
      "rewards/accuracy_reward": 0.734375,
      "rewards/format_reward": 1.0,
      "step": 2179,
      "temperature": 1.0
    },
    {
      "all_correct": 0.625,
      "all_wrong": 0.0,
      "completion_length": 368.78125,
      "epoch": 0.06629363824352269,
      "grad_norm": 0.9551556346840174,
      "kl": 0.02978515625,
      "learning_rate": 9.891952907063518e-07,
      "loss": 0.0012,
      "reward": 1.8961539268493652,
      "reward_std": 0.10754971206188202,
      "rewards/accuracy_reward": 0.7524038553237915,
      "rewards/format_reward": 1.0,
      "step": 2180,
      "temperature": 1.0
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.25,
      "completion_length": 358.671875,
      "epoch": 0.06632404816932247,
      "grad_norm": 1.2049701553116061,
      "kl": 0.03173828125,
      "learning_rate": 9.891854117526713e-07,
      "loss": 0.0013,
      "reward": 1.6755940914154053,
      "reward_std": 0.09196175634860992,
      "rewards/accuracy_reward": 0.5599690079689026,
      "rewards/format_reward": 1.0,
      "step": 2181,
      "temperature": 1.0
    },
    {
      "all_correct": 0.75,
      "all_wrong": 0.25,
      "completion_length": 341.125,
      "epoch": 0.06635445809512225,
      "grad_norm": 0.5221770240749765,
      "kl": 0.0361328125,
      "learning_rate": 9.891755283341707e-07,
      "loss": 0.0014,
      "reward": 1.8968749046325684,
      "reward_std": 0.008838837966322899,
      "rewards/accuracy_reward": 0.75,
      "rewards/format_reward": 1.0,
      "step": 2182,
      "temperature": 1.0
    },
    {
      "all_correct": 0.75,
      "all_wrong": 0.125,
      "completion_length": 397.859375,
      "epoch": 0.06638486802092203,
      "grad_norm": 0.5736903572413794,
      "kl": 0.033203125,
      "learning_rate": 9.891656404509403e-07,
      "loss": 0.0013,
      "reward": 1.8772469758987427,
      "reward_std": 0.0691828578710556,
      "rewards/accuracy_reward": 0.780371904373169,
      "rewards/format_reward": 0.921875,
      "step": 2183,
      "temperature": 1.0
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.25,
      "completion_length": 347.203125,
      "epoch": 0.0664152779467218,
      "grad_norm": 1.5212429188427288,
      "kl": 0.037841796875,
      "learning_rate": 9.891557481030703e-07,
      "loss": 0.0015,
      "reward": 1.7114999294281006,
      "reward_std": 0.024166982620954514,
      "rewards/accuracy_reward": 0.570874810218811,
      "rewards/format_reward": 1.0,
      "step": 2184,
      "temperature": 1.0
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.125,
      "completion_length": 375.625,
      "epoch": 0.06644568787252159,
      "grad_norm": 1.0463700484591476,
      "kl": 0.037109375,
      "learning_rate": 9.891458512906509e-07,
      "loss": 0.0015,
      "reward": 1.8772956132888794,
      "reward_std": 0.10785648226737976,
      "rewards/accuracy_reward": 0.7241705656051636,
      "rewards/format_reward": 1.0,
      "step": 2185,
      "temperature": 1.0
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.125,
      "completion_length": 371.4375,
      "epoch": 0.06647609779832137,
      "grad_norm": 5.969664624863523,
      "kl": 0.04345703125,
      "learning_rate": 9.891359500137723e-07,
      "loss": 0.0017,
      "reward": 1.7193341255187988,
      "reward_std": 0.0828140452504158,
      "rewards/accuracy_reward": 0.5880841016769409,
      "rewards/format_reward": 1.0,
      "step": 2186,
      "temperature": 1.0
    },
    {
      "all_correct": 0.75,
      "all_wrong": 0.0,
      "completion_length": 352.59375,
      "epoch": 0.06650650772412116,
      "grad_norm": 0.9211553063389013,
      "kl": 0.03271484375,
      "learning_rate": 9.891260442725252e-07,
      "loss": 0.0013,
      "reward": 1.9913378953933716,
      "reward_std": 0.054313041269779205,
      "rewards/accuracy_reward": 0.8163378834724426,
      "rewards/format_reward": 1.0,
      "step": 2187,
      "temperature": 1.0
    },
    {
      "all_correct": 0.375,
      "all_wrong": 0.125,
      "completion_length": 359.734375,
      "epoch": 0.06653691764992094,
      "grad_norm": 1.233020580684019,
      "kl": 0.043212890625,
      "learning_rate": 9.89116134067e-07,
      "loss": 0.0017,
      "reward": 1.7299096584320068,
      "reward_std": 0.1557638943195343,
      "rewards/accuracy_reward": 0.5861595273017883,
      "rewards/format_reward": 1.0,
      "step": 2188,
      "temperature": 1.0
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.25,
      "completion_length": 353.296875,
      "epoch": 0.06656732757572072,
      "grad_norm": 0.8674757407568687,
      "kl": 0.046630859375,
      "learning_rate": 9.891062193972868e-07,
      "loss": 0.0019,
      "reward": 1.7094061374664307,
      "reward_std": 0.01996174082159996,
      "rewards/accuracy_reward": 0.575031042098999,
      "rewards/format_reward": 1.0,
      "step": 2189,
      "temperature": 1.0
    },
    {
      "all_correct": 0.625,
      "all_wrong": 0.125,
      "completion_length": 358.296875,
      "epoch": 0.0665977375015205,
      "grad_norm": 1.006863413214628,
      "kl": 0.032958984375,
      "learning_rate": 9.890963002634765e-07,
      "loss": 0.0013,
      "reward": 1.8406250476837158,
      "reward_std": 0.12437255680561066,
      "rewards/accuracy_reward": 0.703125,
      "rewards/format_reward": 1.0,
      "step": 2190,
      "temperature": 1.0
    },
    {
      "all_correct": 0.625,
      "all_wrong": 0.125,
      "completion_length": 348.453125,
      "epoch": 0.06662814742732028,
      "grad_norm": 0.7694364367798958,
      "kl": 0.034423828125,
      "learning_rate": 9.890863766656594e-07,
      "loss": 0.0014,
      "reward": 1.8406250476837158,
      "reward_std": 0.12437255680561066,
      "rewards/accuracy_reward": 0.703125,
      "rewards/format_reward": 1.0,
      "step": 2191,
      "temperature": 1.0
    },
    {
      "all_correct": 0.75,
      "all_wrong": 0.125,
      "completion_length": 385.03125,
      "epoch": 0.06665855735312005,
      "grad_norm": 0.8216668764442004,
      "kl": 0.036865234375,
      "learning_rate": 9.890764486039261e-07,
      "loss": 0.0015,
      "reward": 1.9977678060531616,
      "reward_std": 0.1139097586274147,
      "rewards/accuracy_reward": 0.8571428656578064,
      "rewards/format_reward": 0.984375,
      "step": 2192,
      "temperature": 1.0
    },
    {
      "all_correct": 0.625,
      "all_wrong": 0.125,
      "completion_length": 351.65625,
      "epoch": 0.06668896727891983,
      "grad_norm": 1.37466984034403,
      "kl": 0.039306640625,
      "learning_rate": 9.890665160783671e-07,
      "loss": 0.0016,
      "reward": 1.9375,
      "reward_std": 0.09785604476928711,
      "rewards/accuracy_reward": 0.78125,
      "rewards/format_reward": 1.0,
      "step": 2193,
      "temperature": 1.0
    },
    {
      "all_correct": 0.625,
      "all_wrong": 0.0,
      "completion_length": 377.875,
      "epoch": 0.06671937720471963,
      "grad_norm": 1.2030926972845888,
      "kl": 0.04150390625,
      "learning_rate": 9.890565790890733e-07,
      "loss": 0.0017,
      "reward": 2.0089097023010254,
      "reward_std": 0.04396862909197807,
      "rewards/accuracy_reward": 0.8307846188545227,
      "rewards/format_reward": 1.0,
      "step": 2194,
      "temperature": 1.0
    },
    {
      "all_correct": 1.0,
      "all_wrong": 0.0,
      "completion_length": 336.3125,
      "epoch": 0.0667497871305194,
      "grad_norm": 0.8532780041171667,
      "kl": 0.046875,
      "learning_rate": 9.890466376361351e-07,
      "loss": 0.0019,
      "reward": 2.1932692527770996,
      "reward_std": 0.015992917120456696,
      "rewards/accuracy_reward": 0.9963942170143127,
      "rewards/format_reward": 1.0,
      "step": 2195,
      "temperature": 1.0
    },
    {
      "all_correct": 0.625,
      "all_wrong": 0.0,
      "completion_length": 358.515625,
      "epoch": 0.06678019705631918,
      "grad_norm": 1.2342594756815422,
      "kl": 0.034912109375,
      "learning_rate": 9.890366917196436e-07,
      "loss": 0.0014,
      "reward": 2.0475234985351562,
      "reward_std": 0.14059799909591675,
      "rewards/accuracy_reward": 0.8631485104560852,
      "rewards/format_reward": 1.0,
      "step": 2196,
      "temperature": 1.0
    },
    {
      "all_correct": 0.625,
      "all_wrong": 0.25,
      "completion_length": 335.703125,
      "epoch": 0.06681060698211896,
      "grad_norm": 2.8716440725062133,
      "kl": 0.03759765625,
      "learning_rate": 9.890267413396893e-07,
      "loss": 0.0015,
      "reward": 1.8114757537841797,
      "reward_std": 0.01881350390613079,
      "rewards/accuracy_reward": 0.6708507537841797,
      "rewards/format_reward": 1.0,
      "step": 2197,
      "temperature": 1.0
    },
    {
      "all_correct": 0.875,
      "all_wrong": 0.0,
      "completion_length": 339.734375,
      "epoch": 0.06684101690791874,
      "grad_norm": 0.7395256291530461,
      "kl": 0.045166015625,
      "learning_rate": 9.890167864963633e-07,
      "loss": 0.0018,
      "reward": 2.153125047683716,
      "reward_std": 0.08237524330615997,
      "rewards/accuracy_reward": 0.96875,
      "rewards/format_reward": 1.0,
      "step": 2198,
      "temperature": 1.0
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.125,
      "completion_length": 357.015625,
      "epoch": 0.06687142683371852,
      "grad_norm": 1.0732227696801029,
      "kl": 0.044921875,
      "learning_rate": 9.89006827189756e-07,
      "loss": 0.0018,
      "reward": 1.86215341091156,
      "reward_std": 0.07089664041996002,
      "rewards/accuracy_reward": 0.7090283632278442,
      "rewards/format_reward": 1.0,
      "step": 2199,
      "temperature": 1.0
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.125,
      "completion_length": 344.578125,
      "epoch": 0.0669018367595183,
      "grad_norm": 2.965122436784346,
      "kl": 0.03271484375,
      "learning_rate": 9.889968634199586e-07,
      "loss": 0.0013,
      "reward": 1.8812501430511475,
      "reward_std": 0.22724726796150208,
      "rewards/accuracy_reward": 0.734375,
      "rewards/format_reward": 1.0,
      "step": 2200,
      "temperature": 1.0
    },
    {
      "all_correct": 0.375,
      "all_wrong": 0.0,
      "completion_length": 353.671875,
      "epoch": 0.0669322466853181,
      "grad_norm": 1.2118531159484083,
      "kl": 0.04736328125,
      "learning_rate": 9.889868951870621e-07,
      "loss": 0.0019,
      "reward": 1.8041009902954102,
      "reward_std": 0.12547039985656738,
      "rewards/accuracy_reward": 0.6478509902954102,
      "rewards/format_reward": 1.0,
      "step": 2201,
      "temperature": 1.0
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.25,
      "completion_length": 369.21875,
      "epoch": 0.06696265661111787,
      "grad_norm": 0.9639575110053586,
      "kl": 0.03369140625,
      "learning_rate": 9.889769224911575e-07,
      "loss": 0.0013,
      "reward": 1.6743358373641968,
      "reward_std": 0.07426143437623978,
      "rewards/accuracy_reward": 0.5430857539176941,
      "rewards/format_reward": 1.0,
      "step": 2202,
      "temperature": 1.0
    },
    {
      "all_correct": 0.625,
      "all_wrong": 0.125,
      "completion_length": 355.1875,
      "epoch": 0.06699306653691765,
      "grad_norm": 0.9287571709700312,
      "kl": 0.041015625,
      "learning_rate": 9.889669453323355e-07,
      "loss": 0.0016,
      "reward": 1.9153801202774048,
      "reward_std": 0.08854761719703674,
      "rewards/accuracy_reward": 0.7528800368309021,
      "rewards/format_reward": 1.0,
      "step": 2203,
      "temperature": 1.0
    },
    {
      "all_correct": 0.875,
      "all_wrong": 0.0,
      "completion_length": 361.984375,
      "epoch": 0.06702347646271743,
      "grad_norm": 0.3649377336082976,
      "kl": 0.038818359375,
      "learning_rate": 9.889569637106874e-07,
      "loss": 0.0016,
      "reward": 2.1271228790283203,
      "reward_std": 0.010082371532917023,
      "rewards/accuracy_reward": 0.9271230697631836,
      "rewards/format_reward": 1.0,
      "step": 2204,
      "temperature": 1.0
    },
    {
      "all_correct": 0.375,
      "all_wrong": 0.25,
      "completion_length": 376.375,
      "epoch": 0.06705388638851721,
      "grad_norm": 1.173058807002147,
      "kl": 0.037353515625,
      "learning_rate": 9.889469776263044e-07,
      "loss": 0.0015,
      "reward": 1.5968750715255737,
      "reward_std": 0.19126304984092712,
      "rewards/accuracy_reward": 0.5,
      "rewards/format_reward": 1.0,
      "step": 2205,
      "temperature": 1.0
    },
    {
      "all_correct": 0.625,
      "all_wrong": 0.25,
      "completion_length": 393.484375,
      "epoch": 0.06708429631431699,
      "grad_norm": 0.43675101533037486,
      "kl": 0.034912109375,
      "learning_rate": 9.889369870792774e-07,
      "loss": 0.0014,
      "reward": 1.8212820291519165,
      "reward_std": 0.009965362027287483,
      "rewards/accuracy_reward": 0.6744069457054138,
      "rewards/format_reward": 1.0,
      "step": 2206,
      "temperature": 1.0
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.125,
      "completion_length": 360.296875,
      "epoch": 0.06711470624011677,
      "grad_norm": 0.9683387610166221,
      "kl": 0.036376953125,
      "learning_rate": 9.889269920696977e-07,
      "loss": 0.0015,
      "reward": 1.911933183670044,
      "reward_std": 0.06308604031801224,
      "rewards/accuracy_reward": 0.7400580644607544,
      "rewards/format_reward": 1.0,
      "step": 2207,
      "temperature": 1.0
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.0,
      "completion_length": 387.453125,
      "epoch": 0.06714511616591655,
      "grad_norm": 1.2543030334557612,
      "kl": 0.03466796875,
      "learning_rate": 9.889169925976567e-07,
      "loss": 0.0014,
      "reward": 1.7569324970245361,
      "reward_std": 0.19314423203468323,
      "rewards/accuracy_reward": 0.6350574493408203,
      "rewards/format_reward": 1.0,
      "step": 2208,
      "temperature": 1.0
    },
    {
      "all_correct": 0.625,
      "all_wrong": 0.125,
      "completion_length": 357.140625,
      "epoch": 0.06717552609171634,
      "grad_norm": 1.5859139862542995,
      "kl": 0.0419921875,
      "learning_rate": 9.889069886632453e-07,
      "loss": 0.0017,
      "reward": 1.8361048698425293,
      "reward_std": 0.006304196082055569,
      "rewards/accuracy_reward": 0.6861048936843872,
      "rewards/format_reward": 1.0,
      "step": 2209,
      "temperature": 1.0
    },
    {
      "all_correct": 0.375,
      "all_wrong": 0.25,
      "completion_length": 380.296875,
      "epoch": 0.06720593601751612,
      "grad_norm": 0.8509601010539325,
      "kl": 0.041748046875,
      "learning_rate": 9.88896980266555e-07,
      "loss": 0.0017,
      "reward": 1.695457935333252,
      "reward_std": 0.08584828674793243,
      "rewards/accuracy_reward": 0.5579578876495361,
      "rewards/format_reward": 1.0,
      "step": 2210,
      "temperature": 1.0
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.25,
      "completion_length": 357.75,
      "epoch": 0.0672363459433159,
      "grad_norm": 0.8604834821913739,
      "kl": 0.03466796875,
      "learning_rate": 9.888869674076772e-07,
      "loss": 0.0014,
      "reward": 1.7046375274658203,
      "reward_std": 0.08134608715772629,
      "rewards/accuracy_reward": 0.5765125751495361,
      "rewards/format_reward": 1.0,
      "step": 2211,
      "temperature": 1.0
    },
    {
      "all_correct": 0.625,
      "all_wrong": 0.0,
      "completion_length": 372.53125,
      "epoch": 0.06726675586911568,
      "grad_norm": 0.9715926231048938,
      "kl": 0.0380859375,
      "learning_rate": 9.888769500867031e-07,
      "loss": 0.0015,
      "reward": 2.097578525543213,
      "reward_std": 0.06918932497501373,
      "rewards/accuracy_reward": 0.9007035493850708,
      "rewards/format_reward": 1.0,
      "step": 2212,
      "temperature": 1.0
    },
    {
      "all_correct": 0.75,
      "all_wrong": 0.0,
      "completion_length": 374.953125,
      "epoch": 0.06729716579491546,
      "grad_norm": 1.2766166004314237,
      "kl": 0.033447265625,
      "learning_rate": 9.888669283037245e-07,
      "loss": 0.0013,
      "reward": 2.029348373413086,
      "reward_std": 0.01156461052596569,
      "rewards/accuracy_reward": 0.8293483257293701,
      "rewards/format_reward": 1.0,
      "step": 2213,
      "temperature": 1.0
    },
    {
      "all_correct": 0.75,
      "all_wrong": 0.0,
      "completion_length": 367.515625,
      "epoch": 0.06732757572071524,
      "grad_norm": 0.9215003525237704,
      "kl": 0.03955078125,
      "learning_rate": 9.888569020588325e-07,
      "loss": 0.0016,
      "reward": 2.0311098098754883,
      "reward_std": 0.09168177098035812,
      "rewards/accuracy_reward": 0.8467345237731934,
      "rewards/format_reward": 1.0,
      "step": 2214,
      "temperature": 1.0
    },
    {
      "all_correct": 0.75,
      "all_wrong": 0.125,
      "completion_length": 374.234375,
      "epoch": 0.06735798564651502,
      "grad_norm": 0.774566980708394,
      "kl": 0.036865234375,
      "learning_rate": 9.888468713521188e-07,
      "loss": 0.0015,
      "reward": 1.965592622756958,
      "reward_std": 0.005947811529040337,
      "rewards/accuracy_reward": 0.7905925512313843,
      "rewards/format_reward": 1.0,
      "step": 2215,
      "temperature": 1.0
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.125,
      "completion_length": 406.90625,
      "epoch": 0.06738839557231481,
      "grad_norm": 1.3057221687884633,
      "kl": 0.033203125,
      "learning_rate": 9.888368361836748e-07,
      "loss": 0.0013,
      "reward": 1.836895227432251,
      "reward_std": 0.0696188285946846,
      "rewards/accuracy_reward": 0.6868952512741089,
      "rewards/format_reward": 1.0,
      "step": 2216,
      "temperature": 1.0
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.25,
      "completion_length": 357.578125,
      "epoch": 0.06741880549811459,
      "grad_norm": 0.7122588737406516,
      "kl": 0.04638671875,
      "learning_rate": 9.888267965535921e-07,
      "loss": 0.0019,
      "reward": 1.7175116539001465,
      "reward_std": 0.08245132863521576,
      "rewards/accuracy_reward": 0.5800116658210754,
      "rewards/format_reward": 1.0,
      "step": 2217,
      "temperature": 1.0
    },
    {
      "all_correct": 0.375,
      "all_wrong": 0.125,
      "completion_length": 377.28125,
      "epoch": 0.06744921542391437,
      "grad_norm": 1.6554297291100282,
      "kl": 0.03564453125,
      "learning_rate": 9.888167524619626e-07,
      "loss": 0.0014,
      "reward": 1.6717925071716309,
      "reward_std": 0.1376330703496933,
      "rewards/accuracy_reward": 0.5342925786972046,
      "rewards/format_reward": 1.0,
      "step": 2218,
      "temperature": 1.0
    },
    {
      "all_correct": 0.75,
      "all_wrong": 0.0,
      "completion_length": 348.296875,
      "epoch": 0.06747962534971415,
      "grad_norm": 1.1253100796109392,
      "kl": 0.0380859375,
      "learning_rate": 9.888067039088776e-07,
      "loss": 0.0015,
      "reward": 2.065624952316284,
      "reward_std": 0.15590772032737732,
      "rewards/accuracy_reward": 0.890625,
      "rewards/format_reward": 1.0,
      "step": 2219,
      "temperature": 1.0
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.125,
      "completion_length": 363.09375,
      "epoch": 0.06751003527551393,
      "grad_norm": 1.0485963127786813,
      "kl": 0.037109375,
      "learning_rate": 9.887966508944292e-07,
      "loss": 0.0015,
      "reward": 1.8107998371124268,
      "reward_std": 0.014005981385707855,
      "rewards/accuracy_reward": 0.6357998847961426,
      "rewards/format_reward": 1.0,
      "step": 2220,
      "temperature": 1.0
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.125,
      "completion_length": 346.234375,
      "epoch": 0.0675404452013137,
      "grad_norm": 1.645339150782058,
      "kl": 0.0439453125,
      "learning_rate": 9.887865934187089e-07,
      "loss": 0.0018,
      "reward": 1.7654517889022827,
      "reward_std": 0.13604041934013367,
      "rewards/accuracy_reward": 0.6404517889022827,
      "rewards/format_reward": 1.0,
      "step": 2221,
      "temperature": 1.0
    },
    {
      "all_correct": 0.75,
      "all_wrong": 0.0,
      "completion_length": 355.828125,
      "epoch": 0.06757085512711349,
      "grad_norm": 2.903908420632924,
      "kl": 0.043701171875,
      "learning_rate": 9.887765314818085e-07,
      "loss": 0.0017,
      "reward": 1.962499976158142,
      "reward_std": 0.14223814010620117,
      "rewards/accuracy_reward": 0.8125,
      "rewards/format_reward": 1.0,
      "step": 2222,
      "temperature": 1.0
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.25,
      "completion_length": 375.9375,
      "epoch": 0.06760126505291326,
      "grad_norm": 1.3954033852374013,
      "kl": 0.04248046875,
      "learning_rate": 9.887664650838198e-07,
      "loss": 0.0017,
      "reward": 1.7894814014434814,
      "reward_std": 0.05271490290760994,
      "rewards/accuracy_reward": 0.6488563418388367,
      "rewards/format_reward": 1.0,
      "step": 2223,
      "temperature": 1.0
    },
    {
      "all_correct": 0.625,
      "all_wrong": 0.25,
      "completion_length": 364.65625,
      "epoch": 0.06763167497871306,
      "grad_norm": 0.8941798708553818,
      "kl": 0.035400390625,
      "learning_rate": 9.88756394224835e-07,
      "loss": 0.0014,
      "reward": 1.834233045578003,
      "reward_std": 0.0618002787232399,
      "rewards/accuracy_reward": 0.6904829144477844,
      "rewards/format_reward": 1.0,
      "step": 2224,
      "temperature": 1.0
    },
    {
      "all_correct": 0.375,
      "all_wrong": 0.5,
      "completion_length": 362.171875,
      "epoch": 0.06766208490451284,
      "grad_norm": 1.312360301298235,
      "kl": 0.033447265625,
      "learning_rate": 9.887463189049457e-07,
      "loss": 0.0013,
      "reward": 1.465134859085083,
      "reward_std": 0.015524456277489662,
      "rewards/accuracy_reward": 0.38388481736183167,
      "rewards/format_reward": 1.0,
      "step": 2225,
      "temperature": 1.0
    },
    {
      "all_correct": 0.625,
      "all_wrong": 0.125,
      "completion_length": 371.1875,
      "epoch": 0.06769249483031262,
      "grad_norm": 0.4693052695392991,
      "kl": 0.03271484375,
      "learning_rate": 9.887362391242437e-07,
      "loss": 0.0013,
      "reward": 1.9920763969421387,
      "reward_std": 0.0659717470407486,
      "rewards/accuracy_reward": 0.8295762538909912,
      "rewards/format_reward": 1.0,
      "step": 2226,
      "temperature": 1.0
    },
    {
      "all_correct": 0.875,
      "all_wrong": 0.0,
      "completion_length": 349.0625,
      "epoch": 0.0677229047561124,
      "grad_norm": 0.6616559652401559,
      "kl": 0.036865234375,
      "learning_rate": 9.887261548828215e-07,
      "loss": 0.0015,
      "reward": 2.179513931274414,
      "reward_std": 0.05624767020344734,
      "rewards/accuracy_reward": 0.9826388955116272,
      "rewards/format_reward": 1.0,
      "step": 2227,
      "temperature": 1.0
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.0,
      "completion_length": 352.4375,
      "epoch": 0.06775331468191217,
      "grad_norm": 1.1631021820362066,
      "kl": 0.0380859375,
      "learning_rate": 9.887160661807708e-07,
      "loss": 0.0015,
      "reward": 1.8558531999588013,
      "reward_std": 0.1292649805545807,
      "rewards/accuracy_reward": 0.7058532238006592,
      "rewards/format_reward": 1.0,
      "step": 2228,
      "temperature": 1.0
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.0,
      "completion_length": 343.984375,
      "epoch": 0.06778372460771195,
      "grad_norm": 1.5298475687083963,
      "kl": 0.0419921875,
      "learning_rate": 9.887059730181838e-07,
      "loss": 0.0017,
      "reward": 1.9083261489868164,
      "reward_std": 0.26008477807044983,
      "rewards/accuracy_reward": 0.7489511370658875,
      "rewards/format_reward": 1.0,
      "step": 2229,
      "temperature": 1.0
    },
    {
      "all_correct": 0.75,
      "all_wrong": 0.125,
      "completion_length": 343.859375,
      "epoch": 0.06781413453351173,
      "grad_norm": 1.116183878692776,
      "kl": 0.043701171875,
      "learning_rate": 9.886958753951524e-07,
      "loss": 0.0017,
      "reward": 1.984375,
      "reward_std": 0.09804397821426392,
      "rewards/accuracy_reward": 0.828125,
      "rewards/format_reward": 1.0,
      "step": 2230,
      "temperature": 1.0
    },
    {
      "all_correct": 0.625,
      "all_wrong": 0.125,
      "completion_length": 355.484375,
      "epoch": 0.06784454445931153,
      "grad_norm": 1.0151983832541056,
      "kl": 0.0400390625,
      "learning_rate": 9.886857733117692e-07,
      "loss": 0.0016,
      "reward": 1.9531069993972778,
      "reward_std": 0.06591516733169556,
      "rewards/accuracy_reward": 0.7843568921089172,
      "rewards/format_reward": 1.0,
      "step": 2231,
      "temperature": 1.0
    },
    {
      "all_correct": 0.75,
      "all_wrong": 0.125,
      "completion_length": 348.15625,
      "epoch": 0.0678749543851113,
      "grad_norm": 0.75267016829093,
      "kl": 0.037353515625,
      "learning_rate": 9.886756667681259e-07,
      "loss": 0.0015,
      "reward": 2.0093750953674316,
      "reward_std": 0.07827534526586533,
      "rewards/accuracy_reward": 0.84375,
      "rewards/format_reward": 1.0,
      "step": 2232,
      "temperature": 1.0
    },
    {
      "all_correct": 0.625,
      "all_wrong": 0.0,
      "completion_length": 356.21875,
      "epoch": 0.06790536431091108,
      "grad_norm": 1.6709839581364976,
      "kl": 0.04638671875,
      "learning_rate": 9.886655557643151e-07,
      "loss": 0.0019,
      "reward": 1.9906619787216187,
      "reward_std": 0.11100949347019196,
      "rewards/accuracy_reward": 0.8125368356704712,
      "rewards/format_reward": 1.0,
      "step": 2233,
      "temperature": 1.0
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.0,
      "completion_length": 368.25,
      "epoch": 0.06793577423671086,
      "grad_norm": 3.6082573841813654,
      "kl": 0.03076171875,
      "learning_rate": 9.88655440300429e-07,
      "loss": 0.0012,
      "reward": 1.8297780752182007,
      "reward_std": 0.15095004439353943,
      "rewards/accuracy_reward": 0.6797781586647034,
      "rewards/format_reward": 1.0,
      "step": 2234,
      "temperature": 1.0
    },
    {
      "all_correct": 0.25,
      "all_wrong": 0.25,
      "completion_length": 386.8125,
      "epoch": 0.06796618416251064,
      "grad_norm": 2.6515970005504057,
      "kl": 0.038818359375,
      "learning_rate": 9.8864532037656e-07,
      "loss": 0.0016,
      "reward": 1.528320550918579,
      "reward_std": 0.05963604524731636,
      "rewards/accuracy_reward": 0.42207059264183044,
      "rewards/format_reward": 1.0,
      "step": 2235,
      "temperature": 1.0
    },
    {
      "all_correct": 0.625,
      "all_wrong": 0.125,
      "completion_length": 367.34375,
      "epoch": 0.06799659408831042,
      "grad_norm": 0.7370335966791741,
      "kl": 0.0400390625,
      "learning_rate": 9.886351959928001e-07,
      "loss": 0.0016,
      "reward": 1.914493441581726,
      "reward_std": 0.011152930557727814,
      "rewards/accuracy_reward": 0.7426183819770813,
      "rewards/format_reward": 1.0,
      "step": 2236,
      "temperature": 1.0
    },
    {
      "all_correct": 0.75,
      "all_wrong": 0.25,
      "completion_length": 367.015625,
      "epoch": 0.0680270040141102,
      "grad_norm": 0.5074762813946876,
      "kl": 0.0400390625,
      "learning_rate": 9.88625067149242e-07,
      "loss": 0.0016,
      "reward": 1.8968749046325684,
      "reward_std": 0.008838837966322899,
      "rewards/accuracy_reward": 0.746874988079071,
      "rewards/format_reward": 1.0,
      "step": 2237,
      "temperature": 1.0
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.125,
      "completion_length": 362.953125,
      "epoch": 0.06805741393990998,
      "grad_norm": 1.9127370249608193,
      "kl": 0.0498046875,
      "learning_rate": 9.886149338459782e-07,
      "loss": 0.002,
      "reward": 1.6760433912277222,
      "reward_std": 0.05108101665973663,
      "rewards/accuracy_reward": 0.5385434031486511,
      "rewards/format_reward": 1.0,
      "step": 2238,
      "temperature": 1.0
    },
    {
      "all_correct": 0.875,
      "all_wrong": 0.0,
      "completion_length": 376.609375,
      "epoch": 0.06808782386570977,
      "grad_norm": 0.4184130412938746,
      "kl": 0.0311279296875,
      "learning_rate": 9.88604796083101e-07,
      "loss": 0.0012,
      "reward": 2.1468749046325684,
      "reward_std": 0.08237523585557938,
      "rewards/accuracy_reward": 0.96875,
      "rewards/format_reward": 1.0,
      "step": 2239,
      "temperature": 1.0
    },
    {
      "all_correct": 0.375,
      "all_wrong": 0.25,
      "completion_length": 401.84375,
      "epoch": 0.06811823379150955,
      "grad_norm": 1.805844491970183,
      "kl": 0.033203125,
      "learning_rate": 9.885946538607031e-07,
      "loss": 0.0013,
      "reward": 1.682572603225708,
      "reward_std": 0.07227236032485962,
      "rewards/accuracy_reward": 0.5513225197792053,
      "rewards/format_reward": 1.0,
      "step": 2240,
      "temperature": 1.0
    },
    {
      "all_correct": 0.875,
      "all_wrong": 0.0,
      "completion_length": 352.859375,
      "epoch": 0.06814864371730933,
      "grad_norm": 0.4046895602290211,
      "kl": 0.046142578125,
      "learning_rate": 9.88584507178877e-07,
      "loss": 0.0018,
      "reward": 2.1315250396728516,
      "reward_std": 0.010544582270085812,
      "rewards/accuracy_reward": 0.934650182723999,
      "rewards/format_reward": 1.0,
      "step": 2241,
      "temperature": 1.0
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.0,
      "completion_length": 375.59375,
      "epoch": 0.06817905364310911,
      "grad_norm": 1.144219701701698,
      "kl": 0.032958984375,
      "learning_rate": 9.885743560377153e-07,
      "loss": 0.0013,
      "reward": 1.8402928113937378,
      "reward_std": 0.15710125863552094,
      "rewards/accuracy_reward": 0.6902925968170166,
      "rewards/format_reward": 0.984375,
      "step": 2242,
      "temperature": 1.0
    },
    {
      "all_correct": 0.875,
      "all_wrong": 0.0,
      "completion_length": 353.734375,
      "epoch": 0.06820946356890889,
      "grad_norm": 0.7724977110124849,
      "kl": 0.040283203125,
      "learning_rate": 9.885642004373107e-07,
      "loss": 0.0016,
      "reward": 2.106642961502075,
      "reward_std": 0.016255296766757965,
      "rewards/accuracy_reward": 0.9097679853439331,
      "rewards/format_reward": 1.0,
      "step": 2243,
      "temperature": 1.0
    },
    {
      "all_correct": 0.75,
      "all_wrong": 0.0,
      "completion_length": 354.53125,
      "epoch": 0.06823987349470867,
      "grad_norm": 1.3876557518155939,
      "kl": 0.045166015625,
      "learning_rate": 9.885540403777556e-07,
      "loss": 0.0018,
      "reward": 2.0749754905700684,
      "reward_std": 0.03171054273843765,
      "rewards/accuracy_reward": 0.8874753713607788,
      "rewards/format_reward": 1.0,
      "step": 2244,
      "temperature": 1.0
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.25,
      "completion_length": 368.171875,
      "epoch": 0.06827028342050845,
      "grad_norm": 1.077688281664119,
      "kl": 0.044921875,
      "learning_rate": 9.885438758591431e-07,
      "loss": 0.0018,
      "reward": 1.725000023841858,
      "reward_std": 0.12246952205896378,
      "rewards/accuracy_reward": 0.609375,
      "rewards/format_reward": 1.0,
      "step": 2245,
      "temperature": 1.0
    },
    {
      "all_correct": 0.75,
      "all_wrong": 0.0,
      "completion_length": 376.53125,
      "epoch": 0.06830069334630824,
      "grad_norm": 0.4644101306656919,
      "kl": 0.04052734375,
      "learning_rate": 9.88533706881566e-07,
      "loss": 0.0016,
      "reward": 2.049999952316284,
      "reward_std": 0.11206510663032532,
      "rewards/accuracy_reward": 0.890625,
      "rewards/format_reward": 1.0,
      "step": 2246,
      "temperature": 1.0
    },
    {
      "all_correct": 0.875,
      "all_wrong": 0.0,
      "completion_length": 384.84375,
      "epoch": 0.06833110327210802,
      "grad_norm": 0.7051081157141439,
      "kl": 0.033447265625,
      "learning_rate": 9.88523533445117e-07,
      "loss": 0.0013,
      "reward": 2.0969135761260986,
      "reward_std": 0.017027081921696663,
      "rewards/accuracy_reward": 0.9094133973121643,
      "rewards/format_reward": 1.0,
      "step": 2247,
      "temperature": 1.0
    },
    {
      "all_correct": 0.75,
      "all_wrong": 0.0,
      "completion_length": 350.390625,
      "epoch": 0.0683615131979078,
      "grad_norm": 0.6781086551716938,
      "kl": 0.03564453125,
      "learning_rate": 9.885133555498887e-07,
      "loss": 0.0014,
      "reward": 2.046875,
      "reward_std": 0.09722718596458435,
      "rewards/accuracy_reward": 0.875,
      "rewards/format_reward": 1.0,
      "step": 2248,
      "temperature": 1.0
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.125,
      "completion_length": 345.75,
      "epoch": 0.06839192312370758,
      "grad_norm": 0.7634153846345358,
      "kl": 0.039794921875,
      "learning_rate": 9.885031731959741e-07,
      "loss": 0.0016,
      "reward": 1.7843749523162842,
      "reward_std": 0.16666369140148163,
      "rewards/accuracy_reward": 0.65625,
      "rewards/format_reward": 1.0,
      "step": 2249,
      "temperature": 1.0
    },
    {
      "all_correct": 0.25,
      "all_wrong": 0.125,
      "completion_length": 393.28125,
      "epoch": 0.06842233304950736,
      "grad_norm": 1.9460064065270672,
      "kl": 0.04345703125,
      "learning_rate": 9.884929863834665e-07,
      "loss": 0.0017,
      "reward": 1.6914310455322266,
      "reward_std": 0.15358980000019073,
      "rewards/accuracy_reward": 0.5601810216903687,
      "rewards/format_reward": 1.0,
      "step": 2250,
      "temperature": 1.0
    },
    {
      "all_correct": 0.25,
      "all_wrong": 0.125,
      "completion_length": 398.421875,
      "epoch": 0.06845274297530714,
      "grad_norm": 1.2804890304173684,
      "kl": 0.03515625,
      "learning_rate": 9.884827951124585e-07,
      "loss": 0.0014,
      "reward": 1.759111762046814,
      "reward_std": 0.21260187029838562,
      "rewards/accuracy_reward": 0.6466116905212402,
      "rewards/format_reward": 1.0,
      "step": 2251,
      "temperature": 1.0
    },
    {
      "all_correct": 0.375,
      "all_wrong": 0.125,
      "completion_length": 378.09375,
      "epoch": 0.06848315290110692,
      "grad_norm": 1.4745686258508393,
      "kl": 0.048095703125,
      "learning_rate": 9.884725993830433e-07,
      "loss": 0.0019,
      "reward": 1.7369842529296875,
      "reward_std": 0.13547685742378235,
      "rewards/accuracy_reward": 0.5869842767715454,
      "rewards/format_reward": 1.0,
      "step": 2252,
      "temperature": 1.0
    },
    {
      "all_correct": 0.625,
      "all_wrong": 0.125,
      "completion_length": 359.75,
      "epoch": 0.0685135628269067,
      "grad_norm": 0.8871923028985719,
      "kl": 0.041748046875,
      "learning_rate": 9.884623991953137e-07,
      "loss": 0.0017,
      "reward": 1.8182101249694824,
      "reward_std": 0.01499113067984581,
      "rewards/accuracy_reward": 0.6744600534439087,
      "rewards/format_reward": 1.0,
      "step": 2253,
      "temperature": 1.0
    },
    {
      "all_correct": 0.25,
      "all_wrong": 0.125,
      "completion_length": 356.0,
      "epoch": 0.06854397275270649,
      "grad_norm": 1.2229444103101907,
      "kl": 0.053955078125,
      "learning_rate": 9.884521945493633e-07,
      "loss": 0.0022,
      "reward": 1.7477614879608154,
      "reward_std": 0.19921521842479706,
      "rewards/accuracy_reward": 0.6102614998817444,
      "rewards/format_reward": 1.0,
      "step": 2254,
      "temperature": 1.0
    },
    {
      "all_correct": 0.75,
      "all_wrong": 0.125,
      "completion_length": 350.296875,
      "epoch": 0.06857438267850627,
      "grad_norm": 0.46578868748278857,
      "kl": 0.03662109375,
      "learning_rate": 9.884419854452849e-07,
      "loss": 0.0015,
      "reward": 2.03125,
      "reward_std": 0.0530330091714859,
      "rewards/accuracy_reward": 0.859375,
      "rewards/format_reward": 1.0,
      "step": 2255,
      "temperature": 1.0
    },
    {
      "all_correct": 0.75,
      "all_wrong": 0.0,
      "completion_length": 362.78125,
      "epoch": 0.06860479260430605,
      "grad_norm": 0.7420801254894409,
      "kl": 0.044189453125,
      "learning_rate": 9.884317718831715e-07,
      "loss": 0.0018,
      "reward": 2.1480114459991455,
      "reward_std": 0.10553726553916931,
      "rewards/accuracy_reward": 0.9573863744735718,
      "rewards/format_reward": 1.0,
      "step": 2256,
      "temperature": 1.0
    },
    {
      "all_correct": 0.25,
      "all_wrong": 0.125,
      "completion_length": 392.0,
      "epoch": 0.06863520253010583,
      "grad_norm": 1.2064680745875855,
      "kl": 0.033447265625,
      "learning_rate": 9.884215538631165e-07,
      "loss": 0.0013,
      "reward": 1.5687499046325684,
      "reward_std": 0.28721606731414795,
      "rewards/accuracy_reward": 0.4781249761581421,
      "rewards/format_reward": 1.0,
      "step": 2257,
      "temperature": 1.0
    },
    {
      "all_correct": 0.625,
      "all_wrong": 0.125,
      "completion_length": 350.703125,
      "epoch": 0.0686656124559056,
      "grad_norm": 0.8532761410665195,
      "kl": 0.037353515625,
      "learning_rate": 9.884113313852133e-07,
      "loss": 0.0015,
      "reward": 1.8167037963867188,
      "reward_std": 0.09854865074157715,
      "rewards/accuracy_reward": 0.6698288917541504,
      "rewards/format_reward": 1.0,
      "step": 2258,
      "temperature": 1.0
    },
    {
      "all_correct": 0.375,
      "all_wrong": 0.125,
      "completion_length": 353.53125,
      "epoch": 0.06869602238170538,
      "grad_norm": 1.6448761973557864,
      "kl": 0.037353515625,
      "learning_rate": 9.88401104449555e-07,
      "loss": 0.0015,
      "reward": 1.7667994499206543,
      "reward_std": 0.15542975068092346,
      "rewards/accuracy_reward": 0.6167994141578674,
      "rewards/format_reward": 1.0,
      "step": 2259,
      "temperature": 1.0
    },
    {
      "all_correct": 0.75,
      "all_wrong": 0.125,
      "completion_length": 350.921875,
      "epoch": 0.06872643230750516,
      "grad_norm": 0.6316409767517929,
      "kl": 0.042236328125,
      "learning_rate": 9.883908730562351e-07,
      "loss": 0.0017,
      "reward": 1.9796427488327026,
      "reward_std": 0.012135233730077744,
      "rewards/accuracy_reward": 0.8108928203582764,
      "rewards/format_reward": 1.0,
      "step": 2260,
      "temperature": 1.0
    },
    {
      "all_correct": 0.625,
      "all_wrong": 0.125,
      "completion_length": 347.84375,
      "epoch": 0.06875684223330496,
      "grad_norm": 0.8056503372911228,
      "kl": 0.045654296875,
      "learning_rate": 9.88380637205347e-07,
      "loss": 0.0018,
      "reward": 1.846882700920105,
      "reward_std": 0.0741848573088646,
      "rewards/accuracy_reward": 0.690632700920105,
      "rewards/format_reward": 1.0,
      "step": 2261,
      "temperature": 1.0
    },
    {
      "all_correct": 0.375,
      "all_wrong": 0.125,
      "completion_length": 367.890625,
      "epoch": 0.06878725215910474,
      "grad_norm": 1.181723048855504,
      "kl": 0.04443359375,
      "learning_rate": 9.883703968969839e-07,
      "loss": 0.0018,
      "reward": 1.7667608261108398,
      "reward_std": 0.022528760135173798,
      "rewards/accuracy_reward": 0.5948858261108398,
      "rewards/format_reward": 1.0,
      "step": 2262,
      "temperature": 1.0
    },
    {
      "all_correct": 0.75,
      "all_wrong": 0.125,
      "completion_length": 336.5625,
      "epoch": 0.06881766208490452,
      "grad_norm": 1.0834613786889569,
      "kl": 0.041015625,
      "learning_rate": 9.883601521312393e-07,
      "loss": 0.0016,
      "reward": 1.9125001430511475,
      "reward_std": 0.0530330091714859,
      "rewards/accuracy_reward": 0.765625,
      "rewards/format_reward": 1.0,
      "step": 2263,
      "temperature": 1.0
    },
    {
      "all_correct": 0.75,
      "all_wrong": 0.0,
      "completion_length": 392.546875,
      "epoch": 0.0688480720107043,
      "grad_norm": 0.34115646537216643,
      "kl": 0.032470703125,
      "learning_rate": 9.88349902908207e-07,
      "loss": 0.0013,
      "reward": 1.9593751430511475,
      "reward_std": 0.184493750333786,
      "rewards/accuracy_reward": 0.84375,
      "rewards/format_reward": 0.953125,
      "step": 2264,
      "temperature": 1.0
    },
    {
      "all_correct": 0.625,
      "all_wrong": 0.125,
      "completion_length": 358.578125,
      "epoch": 0.06887848193650407,
      "grad_norm": 0.8852695569139788,
      "kl": 0.03271484375,
      "learning_rate": 9.883396492279803e-07,
      "loss": 0.0013,
      "reward": 1.9052592515945435,
      "reward_std": 0.0291459821164608,
      "rewards/accuracy_reward": 0.7333841919898987,
      "rewards/format_reward": 1.0,
      "step": 2265,
      "temperature": 1.0
    },
    {
      "all_correct": 0.75,
      "all_wrong": 0.125,
      "completion_length": 343.328125,
      "epoch": 0.06890889186230385,
      "grad_norm": 0.8182329343389032,
      "kl": 0.0294189453125,
      "learning_rate": 9.883293910906528e-07,
      "loss": 0.0012,
      "reward": 1.9375,
      "reward_std": 0.06943650543689728,
      "rewards/accuracy_reward": 0.78125,
      "rewards/format_reward": 1.0,
      "step": 2266,
      "temperature": 1.0
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.125,
      "completion_length": 370.375,
      "epoch": 0.06893930178810363,
      "grad_norm": 1.0205765365184616,
      "kl": 0.03466796875,
      "learning_rate": 9.883191284963182e-07,
      "loss": 0.0014,
      "reward": 1.835097074508667,
      "reward_std": 0.02325272560119629,
      "rewards/accuracy_reward": 0.6632219552993774,
      "rewards/format_reward": 1.0,
      "step": 2267,
      "temperature": 1.0
    },
    {
      "all_correct": 0.625,
      "all_wrong": 0.0,
      "completion_length": 353.703125,
      "epoch": 0.06896971171390341,
      "grad_norm": 0.9226313677957126,
      "kl": 0.035888671875,
      "learning_rate": 9.8830886144507e-07,
      "loss": 0.0014,
      "reward": 1.9139372110366821,
      "reward_std": 0.07032033056020737,
      "rewards/accuracy_reward": 0.738937258720398,
      "rewards/format_reward": 1.0,
      "step": 2268,
      "temperature": 1.0
    },
    {
      "all_correct": 0.875,
      "all_wrong": 0.0,
      "completion_length": 336.21875,
      "epoch": 0.0690001216397032,
      "grad_norm": 0.591537663424875,
      "kl": 0.04248046875,
      "learning_rate": 9.88298589937002e-07,
      "loss": 0.0017,
      "reward": 2.1437501907348633,
      "reward_std": 0.077632375061512,
      "rewards/accuracy_reward": 0.953125,
      "rewards/format_reward": 1.0,
      "step": 2269,
      "temperature": 1.0
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.0,
      "completion_length": 367.34375,
      "epoch": 0.06903053156550298,
      "grad_norm": 1.5404692508277464,
      "kl": 0.038818359375,
      "learning_rate": 9.882883139722083e-07,
      "loss": 0.0016,
      "reward": 1.9613518714904785,
      "reward_std": 0.13811716437339783,
      "rewards/accuracy_reward": 0.7738518118858337,
      "rewards/format_reward": 1.0,
      "step": 2270,
      "temperature": 1.0
    },
    {
      "all_correct": 0.625,
      "all_wrong": 0.125,
      "completion_length": 346.546875,
      "epoch": 0.06906094149130276,
      "grad_norm": 1.8829819033304787,
      "kl": 0.04443359375,
      "learning_rate": 9.88278033550782e-07,
      "loss": 0.0018,
      "reward": 1.876361608505249,
      "reward_std": 0.07933309674263,
      "rewards/accuracy_reward": 0.7419865131378174,
      "rewards/format_reward": 1.0,
      "step": 2271,
      "temperature": 1.0
    },
    {
      "all_correct": 0.375,
      "all_wrong": 0.125,
      "completion_length": 350.6875,
      "epoch": 0.06909135141710254,
      "grad_norm": 1.3919123389713304,
      "kl": 0.034423828125,
      "learning_rate": 9.882677486728176e-07,
      "loss": 0.0014,
      "reward": 1.8618614673614502,
      "reward_std": 0.2066417634487152,
      "rewards/accuracy_reward": 0.705611526966095,
      "rewards/format_reward": 1.0,
      "step": 2272,
      "temperature": 1.0
    },
    {
      "all_correct": 0.75,
      "all_wrong": 0.125,
      "completion_length": 352.125,
      "epoch": 0.06912176134290232,
      "grad_norm": 0.4518602644679097,
      "kl": 0.037109375,
      "learning_rate": 9.882574593384086e-07,
      "loss": 0.0015,
      "reward": 1.9156250953674316,
      "reward_std": 0.04419417306780815,
      "rewards/accuracy_reward": 0.765625,
      "rewards/format_reward": 1.0,
      "step": 2273,
      "temperature": 1.0
    },
    {
      "all_correct": 0.75,
      "all_wrong": 0.125,
      "completion_length": 351.265625,
      "epoch": 0.0691521712687021,
      "grad_norm": 0.7774460175595154,
      "kl": 0.037109375,
      "learning_rate": 9.88247165547649e-07,
      "loss": 0.0015,
      "reward": 1.9488685131072998,
      "reward_std": 0.010748323053121567,
      "rewards/accuracy_reward": 0.776993453502655,
      "rewards/format_reward": 1.0,
      "step": 2274,
      "temperature": 1.0
    },
    {
      "all_correct": 0.375,
      "all_wrong": 0.25,
      "completion_length": 403.359375,
      "epoch": 0.06918258119450188,
      "grad_norm": 0.7830753434879931,
      "kl": 0.041259765625,
      "learning_rate": 9.882368673006325e-07,
      "loss": 0.0017,
      "reward": 1.7278258800506592,
      "reward_std": 0.15781942009925842,
      "rewards/accuracy_reward": 0.6153258085250854,
      "rewards/format_reward": 1.0,
      "step": 2275,
      "temperature": 1.0
    },
    {
      "all_correct": 0.75,
      "all_wrong": 0.125,
      "completion_length": 354.484375,
      "epoch": 0.06921299112030167,
      "grad_norm": 0.6532487036716937,
      "kl": 0.0419921875,
      "learning_rate": 9.882265645974536e-07,
      "loss": 0.0017,
      "reward": 1.9704697132110596,
      "reward_std": 0.002899857936426997,
      "rewards/accuracy_reward": 0.7954696416854858,
      "rewards/format_reward": 1.0,
      "step": 2276,
      "temperature": 1.0
    },
    {
      "all_correct": 0.375,
      "all_wrong": 0.0,
      "completion_length": 372.046875,
      "epoch": 0.06924340104610145,
      "grad_norm": 1.217019881469137,
      "kl": 0.040283203125,
      "learning_rate": 9.882162574382058e-07,
      "loss": 0.0016,
      "reward": 1.7814278602600098,
      "reward_std": 0.12052673101425171,
      "rewards/accuracy_reward": 0.6001777052879333,
      "rewards/format_reward": 1.0,
      "step": 2277,
      "temperature": 1.0
    },
    {
      "all_correct": 0.625,
      "all_wrong": 0.125,
      "completion_length": 357.8125,
      "epoch": 0.06927381097190123,
      "grad_norm": 0.6157950169981056,
      "kl": 0.04248046875,
      "learning_rate": 9.882059458229838e-07,
      "loss": 0.0017,
      "reward": 1.8441228866577148,
      "reward_std": 0.04940905421972275,
      "rewards/accuracy_reward": 0.6941227912902832,
      "rewards/format_reward": 1.0,
      "step": 2278,
      "temperature": 1.0
    },
    {
      "all_correct": 0.625,
      "all_wrong": 0.0,
      "completion_length": 351.078125,
      "epoch": 0.06930422089770101,
      "grad_norm": 1.1635963289211058,
      "kl": 0.04443359375,
      "learning_rate": 9.88195629751881e-07,
      "loss": 0.0018,
      "reward": 1.970986247062683,
      "reward_std": 0.1586020141839981,
      "rewards/accuracy_reward": 0.7959861755371094,
      "rewards/format_reward": 1.0,
      "step": 2279,
      "temperature": 1.0
    },
    {
      "all_correct": 0.375,
      "all_wrong": 0.125,
      "completion_length": 388.84375,
      "epoch": 0.06933463082350079,
      "grad_norm": 1.1869323599480415,
      "kl": 0.04052734375,
      "learning_rate": 9.881853092249922e-07,
      "loss": 0.0016,
      "reward": 1.7687737941741943,
      "reward_std": 0.1427783966064453,
      "rewards/accuracy_reward": 0.6281486749649048,
      "rewards/format_reward": 1.0,
      "step": 2280,
      "temperature": 1.0
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.125,
      "completion_length": 389.5625,
      "epoch": 0.06936504074930057,
      "grad_norm": 0.986237530240388,
      "kl": 0.033935546875,
      "learning_rate": 9.881749842424109e-07,
      "loss": 0.0014,
      "reward": 1.7048877477645874,
      "reward_std": 0.1004287600517273,
      "rewards/accuracy_reward": 0.5798878073692322,
      "rewards/format_reward": 1.0,
      "step": 2281,
      "temperature": 1.0
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.25,
      "completion_length": 360.65625,
      "epoch": 0.06939545067510035,
      "grad_norm": 2.1843880955563932,
      "kl": 0.036865234375,
      "learning_rate": 9.88164654804232e-07,
      "loss": 0.0015,
      "reward": 1.6312499046325684,
      "reward_std": 0.0883883461356163,
      "rewards/accuracy_reward": 0.53125,
      "rewards/format_reward": 1.0,
      "step": 2282,
      "temperature": 1.0
    },
    {
      "all_correct": 0.25,
      "all_wrong": 0.25,
      "completion_length": 382.140625,
      "epoch": 0.06942586060090013,
      "grad_norm": 1.7483121261870007,
      "kl": 0.03564453125,
      "learning_rate": 9.881543209105496e-07,
      "loss": 0.0014,
      "reward": 1.6724202632904053,
      "reward_std": 0.17130136489868164,
      "rewards/accuracy_reward": 0.5380451083183289,
      "rewards/format_reward": 1.0,
      "step": 2283,
      "temperature": 1.0
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.0,
      "completion_length": 384.890625,
      "epoch": 0.06945627052669992,
      "grad_norm": 0.9984343534733315,
      "kl": 0.033447265625,
      "learning_rate": 9.881439825614577e-07,
      "loss": 0.0013,
      "reward": 1.9319651126861572,
      "reward_std": 0.167019322514534,
      "rewards/accuracy_reward": 0.7538400292396545,
      "rewards/format_reward": 1.0,
      "step": 2284,
      "temperature": 1.0
    },
    {
      "all_correct": 0.25,
      "all_wrong": 0.125,
      "completion_length": 366.953125,
      "epoch": 0.0694866804524997,
      "grad_norm": 1.2063902084423044,
      "kl": 0.036376953125,
      "learning_rate": 9.88133639757051e-07,
      "loss": 0.0015,
      "reward": 1.652312994003296,
      "reward_std": 0.14295431971549988,
      "rewards/accuracy_reward": 0.5273130536079407,
      "rewards/format_reward": 1.0,
      "step": 2285,
      "temperature": 1.0
    },
    {
      "all_correct": 0.125,
      "all_wrong": 0.0,
      "completion_length": 394.9375,
      "epoch": 0.06951709037829948,
      "grad_norm": 1.3198663744728758,
      "kl": 0.034912109375,
      "learning_rate": 9.881232924974238e-07,
      "loss": 0.0014,
      "reward": 1.7320127487182617,
      "reward_std": 0.3195357620716095,
      "rewards/accuracy_reward": 0.5820126533508301,
      "rewards/format_reward": 1.0,
      "step": 2286,
      "temperature": 1.0
    },
    {
      "all_correct": 0.375,
      "all_wrong": 0.375,
      "completion_length": 362.015625,
      "epoch": 0.06954750030409926,
      "grad_norm": 1.9331218919662314,
      "kl": 0.0439453125,
      "learning_rate": 9.881129407826708e-07,
      "loss": 0.0018,
      "reward": 1.5314611196517944,
      "reward_std": 0.003886499907821417,
      "rewards/accuracy_reward": 0.4314611554145813,
      "rewards/format_reward": 1.0,
      "step": 2287,
      "temperature": 1.0
    },
    {
      "all_correct": 0.375,
      "all_wrong": 0.0,
      "completion_length": 380.78125,
      "epoch": 0.06957791022989904,
      "grad_norm": 1.4882716048161213,
      "kl": 0.040283203125,
      "learning_rate": 9.88102584612886e-07,
      "loss": 0.0016,
      "reward": 1.8347229957580566,
      "reward_std": 0.12433423101902008,
      "rewards/accuracy_reward": 0.6534730195999146,
      "rewards/format_reward": 1.0,
      "step": 2288,
      "temperature": 1.0
    },
    {
      "all_correct": 0.25,
      "all_wrong": 0.375,
      "completion_length": 374.828125,
      "epoch": 0.06960832015569882,
      "grad_norm": 1.0978709226254382,
      "kl": 0.03271484375,
      "learning_rate": 9.880922239881638e-07,
      "loss": 0.0013,
      "reward": 1.4976376295089722,
      "reward_std": 0.12915125489234924,
      "rewards/accuracy_reward": 0.4163876473903656,
      "rewards/format_reward": 1.0,
      "step": 2289,
      "temperature": 1.0
    },
    {
      "all_correct": 0.75,
      "all_wrong": 0.25,
      "completion_length": 366.796875,
      "epoch": 0.0696387300814986,
      "grad_norm": 0.24775669143239068,
      "kl": 0.03125,
      "learning_rate": 9.880818589085995e-07,
      "loss": 0.0013,
      "reward": 1.8968751430511475,
      "reward_std": 0.008838837966322899,
      "rewards/accuracy_reward": 0.75,
      "rewards/format_reward": 1.0,
      "step": 2290,
      "temperature": 1.0
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.125,
      "completion_length": 340.296875,
      "epoch": 0.06966914000729839,
      "grad_norm": 1.2598423543594697,
      "kl": 0.0400390625,
      "learning_rate": 9.880714893742873e-07,
      "loss": 0.0016,
      "reward": 1.6704634428024292,
      "reward_std": 0.03241485357284546,
      "rewards/accuracy_reward": 0.5392134189605713,
      "rewards/format_reward": 1.0,
      "step": 2291,
      "temperature": 1.0
    },
    {
      "all_correct": 0.75,
      "all_wrong": 0.125,
      "completion_length": 362.609375,
      "epoch": 0.06969954993309817,
      "grad_norm": 0.49159107932310486,
      "kl": 0.03564453125,
      "learning_rate": 9.880611153853216e-07,
      "loss": 0.0014,
      "reward": 1.96297025680542,
      "reward_std": 0.003289412474259734,
      "rewards/accuracy_reward": 0.7879700660705566,
      "rewards/format_reward": 1.0,
      "step": 2292,
      "temperature": 1.0
    },
    {
      "all_correct": 0.75,
      "all_wrong": 0.125,
      "completion_length": 367.453125,
      "epoch": 0.06972995985889795,
      "grad_norm": 0.7469250089504683,
      "kl": 0.035400390625,
      "learning_rate": 9.880507369417974e-07,
      "loss": 0.0014,
      "reward": 1.953125,
      "reward_std": 0.08647121489048004,
      "rewards/accuracy_reward": 0.796875,
      "rewards/format_reward": 1.0,
      "step": 2293,
      "temperature": 1.0
    },
    {
      "all_correct": 0.625,
      "all_wrong": 0.25,
      "completion_length": 357.28125,
      "epoch": 0.06976036978469773,
      "grad_norm": 0.3083134033801743,
      "kl": 0.031494140625,
      "learning_rate": 9.880403540438094e-07,
      "loss": 0.0013,
      "reward": 1.8062500953674316,
      "reward_std": 0.07763238251209259,
      "rewards/accuracy_reward": 0.671875,
      "rewards/format_reward": 1.0,
      "step": 2294,
      "temperature": 1.0
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.25,
      "completion_length": 341.953125,
      "epoch": 0.0697907797104975,
      "grad_norm": 3.291994363812802,
      "kl": 0.046142578125,
      "learning_rate": 9.880299666914522e-07,
      "loss": 0.0018,
      "reward": 1.849205732345581,
      "reward_std": 0.07967593520879745,
      "rewards/accuracy_reward": 0.7054557204246521,
      "rewards/format_reward": 1.0,
      "step": 2295,
      "temperature": 1.0
    },
    {
      "all_correct": 0.625,
      "all_wrong": 0.0,
      "completion_length": 369.625,
      "epoch": 0.06982118963629728,
      "grad_norm": 0.6766648081826101,
      "kl": 0.03662109375,
      "learning_rate": 9.88019574884821e-07,
      "loss": 0.0015,
      "reward": 2.065624952316284,
      "reward_std": 0.20126797258853912,
      "rewards/accuracy_reward": 0.890625,
      "rewards/format_reward": 1.0,
      "step": 2296,
      "temperature": 1.0
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.25,
      "completion_length": 370.390625,
      "epoch": 0.06985159956209706,
      "grad_norm": 0.6515051735410049,
      "kl": 0.036376953125,
      "learning_rate": 9.880091786240102e-07,
      "loss": 0.0015,
      "reward": 1.7697710990905762,
      "reward_std": 0.08235938847064972,
      "rewards/accuracy_reward": 0.6416460275650024,
      "rewards/format_reward": 1.0,
      "step": 2297,
      "temperature": 1.0
    },
    {
      "all_correct": 0.125,
      "all_wrong": 0.25,
      "completion_length": 378.703125,
      "epoch": 0.06988200948789684,
      "grad_norm": 1.080129129026624,
      "kl": 0.03369140625,
      "learning_rate": 9.879987779091148e-07,
      "loss": 0.0014,
      "reward": 1.3913724422454834,
      "reward_std": 0.08132602274417877,
      "rewards/accuracy_reward": 0.2976223826408386,
      "rewards/format_reward": 1.0,
      "step": 2298,
      "temperature": 1.0
    },
    {
      "all_correct": 0.625,
      "all_wrong": 0.375,
      "completion_length": 362.03125,
      "epoch": 0.06991241941369664,
      "grad_norm": 0.09025643559834735,
      "kl": 0.03369140625,
      "learning_rate": 9.879883727402298e-07,
      "loss": 0.0013,
      "reward": 1.75,
      "reward_std": 0.0,
      "rewards/accuracy_reward": 0.625,
      "rewards/format_reward": 1.0,
      "step": 2299,
      "temperature": 1.0
    },
    {
      "all_correct": 0.75,
      "all_wrong": 0.125,
      "completion_length": 354.921875,
      "epoch": 0.06994282933949642,
      "grad_norm": 0.4976207438461873,
      "kl": 0.033935546875,
      "learning_rate": 9.879779631174503e-07,
      "loss": 0.0014,
      "reward": 2.03125,
      "reward_std": 0.0530330091714859,
      "rewards/accuracy_reward": 0.859375,
      "rewards/format_reward": 1.0,
      "step": 2300,
      "temperature": 1.0
    },
    {
      "all_correct": 0.25,
      "all_wrong": 0.25,
      "completion_length": 384.53125,
      "epoch": 0.0699732392652962,
      "grad_norm": 1.1354118354307317,
      "kl": 0.03662109375,
      "learning_rate": 9.87967549040871e-07,
      "loss": 0.0015,
      "reward": 1.648857593536377,
      "reward_std": 0.1248646154999733,
      "rewards/accuracy_reward": 0.5238576531410217,
      "rewards/format_reward": 1.0,
      "step": 2301,
      "temperature": 1.0
    },
    {
      "all_correct": 0.625,
      "all_wrong": 0.125,
      "completion_length": 374.15625,
      "epoch": 0.07000364919109597,
      "grad_norm": 0.750317047560824,
      "kl": 0.03955078125,
      "learning_rate": 9.879571305105873e-07,
      "loss": 0.0016,
      "reward": 1.9010951519012451,
      "reward_std": 0.02355922758579254,
      "rewards/accuracy_reward": 0.7260951399803162,
      "rewards/format_reward": 1.0,
      "step": 2302,
      "temperature": 1.0
    },
    {
      "all_correct": 0.75,
      "all_wrong": 0.125,
      "completion_length": 358.34375,
      "epoch": 0.07003405911689575,
      "grad_norm": 0.6651510985141867,
      "kl": 0.037353515625,
      "learning_rate": 9.879467075266938e-07,
      "loss": 0.0015,
      "reward": 1.9865939617156982,
      "reward_std": 0.0065956078469753265,
      "rewards/accuracy_reward": 0.8147189617156982,
      "rewards/format_reward": 1.0,
      "step": 2303,
      "temperature": 1.0
    },
    {
      "all_correct": 0.625,
      "all_wrong": 0.25,
      "completion_length": 348.90625,
      "epoch": 0.07006446904269553,
      "grad_norm": 0.651526694453003,
      "kl": 0.05126953125,
      "learning_rate": 9.879362800892862e-07,
      "loss": 0.0021,
      "reward": 1.84375,
      "reward_std": 0.077632375061512,
      "rewards/accuracy_reward": 0.703125,
      "rewards/format_reward": 1.0,
      "step": 2304,
      "temperature": 1.0
    },
    {
      "all_correct": 0.375,
      "all_wrong": 0.0,
      "completion_length": 398.6875,
      "epoch": 0.07009487896849531,
      "grad_norm": 3.927001490134674,
      "kl": 0.043212890625,
      "learning_rate": 9.879258481984592e-07,
      "loss": 0.0017,
      "reward": 1.845004677772522,
      "reward_std": 0.09620370715856552,
      "rewards/accuracy_reward": 0.7043795585632324,
      "rewards/format_reward": 1.0,
      "step": 2305,
      "temperature": 1.0
    },
    {
      "all_correct": 0.875,
      "all_wrong": 0.0,
      "completion_length": 367.734375,
      "epoch": 0.0701252888942951,
      "grad_norm": 1.2058228718167345,
      "kl": 0.0439453125,
      "learning_rate": 9.879154118543083e-07,
      "loss": 0.0018,
      "reward": 2.0927352905273438,
      "reward_std": 0.021979494020342827,
      "rewards/accuracy_reward": 0.9021104574203491,
      "rewards/format_reward": 1.0,
      "step": 2306,
      "temperature": 1.0
    },
    {
      "all_correct": 0.375,
      "all_wrong": 0.25,
      "completion_length": 424.46875,
      "epoch": 0.07015569882009488,
      "grad_norm": 1.3795550673046424,
      "kl": 0.031982421875,
      "learning_rate": 9.879049710569287e-07,
      "loss": 0.0013,
      "reward": 1.5257447957992554,
      "reward_std": 0.1564824879169464,
      "rewards/accuracy_reward": 0.5163697600364685,
      "rewards/format_reward": 0.890625,
      "step": 2307,
      "temperature": 1.0
    },
    {
      "all_correct": 0.625,
      "all_wrong": 0.0,
      "completion_length": 380.28125,
      "epoch": 0.07018610874589466,
      "grad_norm": 0.8802635739787507,
      "kl": 0.0341796875,
      "learning_rate": 9.878945258064154e-07,
      "loss": 0.0014,
      "reward": 2.061544418334961,
      "reward_std": 0.08267122507095337,
      "rewards/accuracy_reward": 0.8740445375442505,
      "rewards/format_reward": 1.0,
      "step": 2308,
      "temperature": 1.0
    },
    {
      "all_correct": 0.125,
      "all_wrong": 0.625,
      "completion_length": 352.265625,
      "epoch": 0.07021651867169444,
      "grad_norm": 0.7675436573627277,
      "kl": 0.04345703125,
      "learning_rate": 9.878840761028645e-07,
      "loss": 0.0017,
      "reward": 1.2972195148468018,
      "reward_std": 0.08386655151844025,
      "rewards/accuracy_reward": 0.23471945524215698,
      "rewards/format_reward": 1.0,
      "step": 2309,
      "temperature": 1.0
    },
    {
      "all_correct": 0.75,
      "all_wrong": 0.0,
      "completion_length": 367.328125,
      "epoch": 0.07024692859749422,
      "grad_norm": 3.5503186019566915,
      "kl": 0.0322265625,
      "learning_rate": 9.878736219463705e-07,
      "loss": 0.0013,
      "reward": 2.0423545837402344,
      "reward_std": 0.03579375520348549,
      "rewards/accuracy_reward": 0.8611045479774475,
      "rewards/format_reward": 1.0,
      "step": 2310,
      "temperature": 1.0
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.25,
      "completion_length": 380.46875,
      "epoch": 0.070277338523294,
      "grad_norm": 0.9870104926777629,
      "kl": 0.0341796875,
      "learning_rate": 9.878631633370293e-07,
      "loss": 0.0014,
      "reward": 1.8088619709014893,
      "reward_std": 0.06886190176010132,
      "rewards/accuracy_reward": 0.6682369709014893,
      "rewards/format_reward": 1.0,
      "step": 2311,
      "temperature": 1.0
    },
    {
      "all_correct": 0.75,
      "all_wrong": 0.0,
      "completion_length": 366.796875,
      "epoch": 0.07030774844909378,
      "grad_norm": 0.9453462225409254,
      "kl": 0.046630859375,
      "learning_rate": 9.878527002749361e-07,
      "loss": 0.0019,
      "reward": 2.0369269847869873,
      "reward_std": 0.03608742728829384,
      "rewards/accuracy_reward": 0.8525518774986267,
      "rewards/format_reward": 1.0,
      "step": 2312,
      "temperature": 1.0
    },
    {
      "all_correct": 0.625,
      "all_wrong": 0.125,
      "completion_length": 376.0625,
      "epoch": 0.07033815837489356,
      "grad_norm": 0.7991887605374727,
      "kl": 0.0302734375,
      "learning_rate": 9.878422327601866e-07,
      "loss": 0.0012,
      "reward": 1.8520312309265137,
      "reward_std": 0.08910862356424332,
      "rewards/accuracy_reward": 0.7020313143730164,
      "rewards/format_reward": 1.0,
      "step": 2313,
      "temperature": 1.0
    },
    {
      "all_correct": 0.625,
      "all_wrong": 0.125,
      "completion_length": 369.21875,
      "epoch": 0.07036856830069335,
      "grad_norm": 1.2514406253694041,
      "kl": 0.038330078125,
      "learning_rate": 9.878317607928765e-07,
      "loss": 0.0015,
      "reward": 1.8699041604995728,
      "reward_std": 0.030581310391426086,
      "rewards/accuracy_reward": 0.698029100894928,
      "rewards/format_reward": 1.0,
      "step": 2314,
      "temperature": 1.0
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.125,
      "completion_length": 376.96875,
      "epoch": 0.07039897822649313,
      "grad_norm": 1.1645371452224047,
      "kl": 0.033203125,
      "learning_rate": 9.87821284373101e-07,
      "loss": 0.0013,
      "reward": 1.763006567955017,
      "reward_std": 0.05664077401161194,
      "rewards/accuracy_reward": 0.6130064725875854,
      "rewards/format_reward": 1.0,
      "step": 2315,
      "temperature": 1.0
    },
    {
      "all_correct": 0.25,
      "all_wrong": 0.25,
      "completion_length": 381.875,
      "epoch": 0.07042938815229291,
      "grad_norm": 0.8407366591462966,
      "kl": 0.04638671875,
      "learning_rate": 9.878108035009558e-07,
      "loss": 0.0019,
      "reward": 1.5228604078292847,
      "reward_std": 0.1503661870956421,
      "rewards/accuracy_reward": 0.4197354316711426,
      "rewards/format_reward": 1.0,
      "step": 2316,
      "temperature": 1.0
    },
    {
      "all_correct": 0.625,
      "all_wrong": 0.25,
      "completion_length": 382.609375,
      "epoch": 0.07045979807809269,
      "grad_norm": 0.7703236414610714,
      "kl": 0.0517578125,
      "learning_rate": 9.878003181765369e-07,
      "loss": 0.0021,
      "reward": 1.7848243713378906,
      "reward_std": 0.028871191665530205,
      "rewards/accuracy_reward": 0.6598243117332458,
      "rewards/format_reward": 1.0,
      "step": 2317,
      "temperature": 1.0
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.0,
      "completion_length": 349.234375,
      "epoch": 0.07049020800389247,
      "grad_norm": 0.8097166648062635,
      "kl": 0.034912109375,
      "learning_rate": 9.877898283999394e-07,
      "loss": 0.0014,
      "reward": 1.8730545043945312,
      "reward_std": 0.09398944675922394,
      "rewards/accuracy_reward": 0.7261793613433838,
      "rewards/format_reward": 1.0,
      "step": 2318,
      "temperature": 1.0
    },
    {
      "all_correct": 0.75,
      "all_wrong": 0.125,
      "completion_length": 341.953125,
      "epoch": 0.07052061792969225,
      "grad_norm": 1.3759789838541443,
      "kl": 0.037841796875,
      "learning_rate": 9.877793341712596e-07,
      "loss": 0.0015,
      "reward": 1.929140329360962,
      "reward_std": 0.029561541974544525,
      "rewards/accuracy_reward": 0.7760151624679565,
      "rewards/format_reward": 1.0,
      "step": 2319,
      "temperature": 1.0
    },
    {
      "all_correct": 0.75,
      "all_wrong": 0.0,
      "completion_length": 338.046875,
      "epoch": 0.07055102785549203,
      "grad_norm": 0.763708230796555,
      "kl": 0.042236328125,
      "learning_rate": 9.877688354905928e-07,
      "loss": 0.0017,
      "reward": 2.07489013671875,
      "reward_std": 0.09200280159711838,
      "rewards/accuracy_reward": 0.88739013671875,
      "rewards/format_reward": 1.0,
      "step": 2320,
      "temperature": 1.0
    },
    {
      "all_correct": 0.625,
      "all_wrong": 0.125,
      "completion_length": 343.203125,
      "epoch": 0.07058143778129182,
      "grad_norm": 1.260315895288304,
      "kl": 0.036865234375,
      "learning_rate": 9.877583323580355e-07,
      "loss": 0.0015,
      "reward": 1.9929577112197876,
      "reward_std": 0.08860299736261368,
      "rewards/accuracy_reward": 0.827332615852356,
      "rewards/format_reward": 1.0,
      "step": 2321,
      "temperature": 1.0
    },
    {
      "all_correct": 0.625,
      "all_wrong": 0.0,
      "completion_length": 372.015625,
      "epoch": 0.0706118477070916,
      "grad_norm": 1.071296103423229,
      "kl": 0.040283203125,
      "learning_rate": 9.877478247736828e-07,
      "loss": 0.0016,
      "reward": 1.8927083015441895,
      "reward_std": 0.14467142522335052,
      "rewards/accuracy_reward": 0.7552083134651184,
      "rewards/format_reward": 1.0,
      "step": 2322,
      "temperature": 1.0
    },
    {
      "all_correct": 1.0,
      "all_wrong": 0.0,
      "completion_length": 338.203125,
      "epoch": 0.07064225763289138,
      "grad_norm": 0.07085687593540116,
      "kl": 0.058837890625,
      "learning_rate": 9.87737312737631e-07,
      "loss": 0.0024,
      "reward": 2.200000047683716,
      "reward_std": 0.0,
      "rewards/accuracy_reward": 1.0,
      "rewards/format_reward": 1.0,
      "step": 2323,
      "temperature": 1.0
    },
    {
      "all_correct": 0.375,
      "all_wrong": 0.0,
      "completion_length": 371.125,
      "epoch": 0.07067266755869116,
      "grad_norm": 1.2852428148380417,
      "kl": 0.049072265625,
      "learning_rate": 9.87726796249976e-07,
      "loss": 0.002,
      "reward": 1.7640430927276611,
      "reward_std": 0.04223271459341049,
      "rewards/accuracy_reward": 0.6015430688858032,
      "rewards/format_reward": 1.0,
      "step": 2324,
      "temperature": 1.0
    },
    {
      "all_correct": 0.625,
      "all_wrong": 0.25,
      "completion_length": 387.453125,
      "epoch": 0.07070307748449094,
      "grad_norm": 0.7617805200476044,
      "kl": 0.0308837890625,
      "learning_rate": 9.877162753108138e-07,
      "loss": 0.0012,
      "reward": 1.834062099456787,
      "reward_std": 0.006440363824367523,
      "rewards/accuracy_reward": 0.6840620040893555,
      "rewards/format_reward": 1.0,
      "step": 2325,
      "temperature": 1.0
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.25,
      "completion_length": 366.90625,
      "epoch": 0.07073348741029072,
      "grad_norm": 2.091456419932376,
      "kl": 0.0380859375,
      "learning_rate": 9.877057499202404e-07,
      "loss": 0.0015,
      "reward": 1.7536214590072632,
      "reward_std": 0.08217963576316833,
      "rewards/accuracy_reward": 0.6161214113235474,
      "rewards/format_reward": 1.0,
      "step": 2326,
      "temperature": 1.0
    },
    {
      "all_correct": 0.875,
      "all_wrong": 0.0,
      "completion_length": 345.125,
      "epoch": 0.0707638973360905,
      "grad_norm": 0.6566244678597222,
      "kl": 0.046875,
      "learning_rate": 9.87695220078352e-07,
      "loss": 0.0019,
      "reward": 2.083054542541504,
      "reward_std": 0.013435021974146366,
      "rewards/accuracy_reward": 0.8893045783042908,
      "rewards/format_reward": 1.0,
      "step": 2327,
      "temperature": 1.0
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.25,
      "completion_length": 377.3125,
      "epoch": 0.07079430726189027,
      "grad_norm": 0.9711363118362093,
      "kl": 0.0306396484375,
      "learning_rate": 9.876846857852443e-07,
      "loss": 0.0012,
      "reward": 1.742506742477417,
      "reward_std": 0.08601991832256317,
      "rewards/accuracy_reward": 0.6050066947937012,
      "rewards/format_reward": 1.0,
      "step": 2328,
      "temperature": 1.0
    },
    {
      "all_correct": 0.75,
      "all_wrong": 0.25,
      "completion_length": 344.046875,
      "epoch": 0.07082471718769007,
      "grad_norm": 0.08032897808819615,
      "kl": 0.046875,
      "learning_rate": 9.876741470410138e-07,
      "loss": 0.0019,
      "reward": 1.9000000953674316,
      "reward_std": 0.0,
      "rewards/accuracy_reward": 0.75,
      "rewards/format_reward": 1.0,
      "step": 2329,
      "temperature": 1.0
    },
    {
      "all_correct": 0.625,
      "all_wrong": 0.0,
      "completion_length": 364.28125,
      "epoch": 0.07085512711348985,
      "grad_norm": 1.0768505102580797,
      "kl": 0.0308837890625,
      "learning_rate": 9.876636038457566e-07,
      "loss": 0.0012,
      "reward": 1.8829131126403809,
      "reward_std": 0.17062914371490479,
      "rewards/accuracy_reward": 0.7360380291938782,
      "rewards/format_reward": 1.0,
      "step": 2330,
      "temperature": 1.0
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.0,
      "completion_length": 380.65625,
      "epoch": 0.07088553703928963,
      "grad_norm": 1.2643904268130357,
      "kl": 0.047119140625,
      "learning_rate": 9.87653056199569e-07,
      "loss": 0.0019,
      "reward": 1.9835827350616455,
      "reward_std": 0.10681791603565216,
      "rewards/accuracy_reward": 0.8054577708244324,
      "rewards/format_reward": 1.0,
      "step": 2331,
      "temperature": 1.0
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.25,
      "completion_length": 370.234375,
      "epoch": 0.0709159469650894,
      "grad_norm": 0.9412618504801109,
      "kl": 0.031982421875,
      "learning_rate": 9.876425041025472e-07,
      "loss": 0.0013,
      "reward": 1.82041335105896,
      "reward_std": 0.07400663197040558,
      "rewards/accuracy_reward": 0.676663339138031,
      "rewards/format_reward": 1.0,
      "step": 2332,
      "temperature": 1.0
    },
    {
      "all_correct": 0.875,
      "all_wrong": 0.125,
      "completion_length": 381.46875,
      "epoch": 0.07094635689088918,
      "grad_norm": 0.07042972212435189,
      "kl": 0.0419921875,
      "learning_rate": 9.876319475547876e-07,
      "loss": 0.0017,
      "reward": 2.047159194946289,
      "reward_std": 0.0,
      "rewards/accuracy_reward": 0.8721591234207153,
      "rewards/format_reward": 1.0,
      "step": 2333,
      "temperature": 1.0
    },
    {
      "all_correct": 0.75,
      "all_wrong": 0.0,
      "completion_length": 370.171875,
      "epoch": 0.07097676681668896,
      "grad_norm": 0.7192414015903144,
      "kl": 0.035400390625,
      "learning_rate": 9.876213865563862e-07,
      "loss": 0.0014,
      "reward": 2.0867929458618164,
      "reward_std": 0.055555880069732666,
      "rewards/accuracy_reward": 0.8899179697036743,
      "rewards/format_reward": 1.0,
      "step": 2334,
      "temperature": 1.0
    },
    {
      "all_correct": 0.25,
      "all_wrong": 0.25,
      "completion_length": 382.09375,
      "epoch": 0.07100717674248874,
      "grad_norm": 1.1933814829009333,
      "kl": 0.045166015625,
      "learning_rate": 9.876108211074398e-07,
      "loss": 0.0018,
      "reward": 1.5807031393051147,
      "reward_std": 0.17194490134716034,
      "rewards/accuracy_reward": 0.4588281214237213,
      "rewards/format_reward": 1.0,
      "step": 2335,
      "temperature": 1.0
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.125,
      "completion_length": 429.140625,
      "epoch": 0.07103758666828854,
      "grad_norm": 1.4223185922453216,
      "kl": 0.0341796875,
      "learning_rate": 9.876002512080449e-07,
      "loss": 0.0014,
      "reward": 1.7764413356781006,
      "reward_std": 0.13451741635799408,
      "rewards/accuracy_reward": 0.6420663595199585,
      "rewards/format_reward": 0.984375,
      "step": 2336,
      "temperature": 1.0
    },
    {
      "all_correct": 0.375,
      "all_wrong": 0.375,
      "completion_length": 372.078125,
      "epoch": 0.07106799659408831,
      "grad_norm": 0.6744907246660446,
      "kl": 0.032470703125,
      "learning_rate": 9.875896768582973e-07,
      "loss": 0.0013,
      "reward": 1.5616071224212646,
      "reward_std": 0.0969124287366867,
      "rewards/accuracy_reward": 0.4616071581840515,
      "rewards/format_reward": 1.0,
      "step": 2337,
      "temperature": 1.0
    },
    {
      "all_correct": 0.375,
      "all_wrong": 0.25,
      "completion_length": 367.84375,
      "epoch": 0.0710984065198881,
      "grad_norm": 1.1304911063540322,
      "kl": 0.033203125,
      "learning_rate": 9.875790980582944e-07,
      "loss": 0.0013,
      "reward": 1.7306983470916748,
      "reward_std": 0.15087859332561493,
      "rewards/accuracy_reward": 0.6056983470916748,
      "rewards/format_reward": 1.0,
      "step": 2338,
      "temperature": 1.0
    },
    {
      "all_correct": 0.625,
      "all_wrong": 0.125,
      "completion_length": 388.09375,
      "epoch": 0.07112881644568787,
      "grad_norm": 0.6199517743156713,
      "kl": 0.0294189453125,
      "learning_rate": 9.875685148081321e-07,
      "loss": 0.0012,
      "reward": 1.8539000749588013,
      "reward_std": 0.07059960067272186,
      "rewards/accuracy_reward": 0.7070250511169434,
      "rewards/format_reward": 1.0,
      "step": 2339,
      "temperature": 1.0
    },
    {
      "all_correct": 0.375,
      "all_wrong": 0.125,
      "completion_length": 371.84375,
      "epoch": 0.07115922637148765,
      "grad_norm": 3.0928287263719443,
      "kl": 0.054443359375,
      "learning_rate": 9.875579271079072e-07,
      "loss": 0.0022,
      "reward": 1.7377976179122925,
      "reward_std": 0.09587763249874115,
      "rewards/accuracy_reward": 0.5752975940704346,
      "rewards/format_reward": 1.0,
      "step": 2340,
      "temperature": 1.0
    },
    {
      "all_correct": 0.75,
      "all_wrong": 0.125,
      "completion_length": 352.015625,
      "epoch": 0.07118963629728743,
      "grad_norm": 0.8860976766744139,
      "kl": 0.04443359375,
      "learning_rate": 9.875473349577163e-07,
      "loss": 0.0018,
      "reward": 1.9976170063018799,
      "reward_std": 0.013091685250401497,
      "rewards/accuracy_reward": 0.8257418274879456,
      "rewards/format_reward": 1.0,
      "step": 2341,
      "temperature": 1.0
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.125,
      "completion_length": 368.515625,
      "epoch": 0.07122004622308721,
      "grad_norm": 1.7454497199042656,
      "kl": 0.03271484375,
      "learning_rate": 9.875367383576562e-07,
      "loss": 0.0013,
      "reward": 1.8415366411209106,
      "reward_std": 0.12381254881620407,
      "rewards/accuracy_reward": 0.6884115934371948,
      "rewards/format_reward": 1.0,
      "step": 2342,
      "temperature": 1.0
    },
    {
      "all_correct": 0.375,
      "all_wrong": 0.25,
      "completion_length": 367.171875,
      "epoch": 0.071250456148887,
      "grad_norm": 1.3917214673059821,
      "kl": 0.043701171875,
      "learning_rate": 9.875261373078235e-07,
      "loss": 0.0017,
      "reward": 1.6809732913970947,
      "reward_std": 0.08920764923095703,
      "rewards/accuracy_reward": 0.5559731721878052,
      "rewards/format_reward": 1.0,
      "step": 2343,
      "temperature": 1.0
    },
    {
      "all_correct": 0.375,
      "all_wrong": 0.125,
      "completion_length": 388.09375,
      "epoch": 0.07128086607468678,
      "grad_norm": 1.0896570997166224,
      "kl": 0.0361328125,
      "learning_rate": 9.875155318083153e-07,
      "loss": 0.0014,
      "reward": 1.7034600973129272,
      "reward_std": 0.0824342593550682,
      "rewards/accuracy_reward": 0.5628350973129272,
      "rewards/format_reward": 1.0,
      "step": 2344,
      "temperature": 1.0
    },
    {
      "all_correct": 0.25,
      "all_wrong": 0.125,
      "completion_length": 357.453125,
      "epoch": 0.07131127600048656,
      "grad_norm": 1.4010655658252515,
      "kl": 0.041015625,
      "learning_rate": 9.875049218592277e-07,
      "loss": 0.0016,
      "reward": 1.7863812446594238,
      "reward_std": 0.2668065130710602,
      "rewards/accuracy_reward": 0.6520061492919922,
      "rewards/format_reward": 1.0,
      "step": 2345,
      "temperature": 1.0
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.25,
      "completion_length": 361.921875,
      "epoch": 0.07134168592628634,
      "grad_norm": 0.6438169748067052,
      "kl": 0.037109375,
      "learning_rate": 9.87494307460658e-07,
      "loss": 0.0015,
      "reward": 1.7492815256118774,
      "reward_std": 0.08504504710435867,
      "rewards/accuracy_reward": 0.6149064302444458,
      "rewards/format_reward": 1.0,
      "step": 2346,
      "temperature": 1.0
    },
    {
      "all_correct": 0.75,
      "all_wrong": 0.0,
      "completion_length": 398.5,
      "epoch": 0.07137209585208612,
      "grad_norm": 2.071403256386345,
      "kl": 0.03857421875,
      "learning_rate": 9.874836886127032e-07,
      "loss": 0.0015,
      "reward": 1.9620819091796875,
      "reward_std": 0.04787423089146614,
      "rewards/accuracy_reward": 0.802706778049469,
      "rewards/format_reward": 0.984375,
      "step": 2347,
      "temperature": 1.0
    },
    {
      "all_correct": 0.625,
      "all_wrong": 0.125,
      "completion_length": 348.171875,
      "epoch": 0.0714025057778859,
      "grad_norm": 1.6185414907538251,
      "kl": 0.038818359375,
      "learning_rate": 9.8747306531546e-07,
      "loss": 0.0016,
      "reward": 1.967228651046753,
      "reward_std": 0.06347106397151947,
      "rewards/accuracy_reward": 0.7953536510467529,
      "rewards/format_reward": 1.0,
      "step": 2348,
      "temperature": 1.0
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.375,
      "completion_length": 387.125,
      "epoch": 0.07143291570368568,
      "grad_norm": 0.18744414504786844,
      "kl": 0.033447265625,
      "learning_rate": 9.874624375690252e-07,
      "loss": 0.0013,
      "reward": 1.5758750438690186,
      "reward_std": 0.06229490786790848,
      "rewards/accuracy_reward": 0.5071249008178711,
      "rewards/format_reward": 0.96875,
      "step": 2349,
      "temperature": 1.0
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.0,
      "completion_length": 412.078125,
      "epoch": 0.07146332562948546,
      "grad_norm": 0.9290609344598316,
      "kl": 0.03564453125,
      "learning_rate": 9.87451805373496e-07,
      "loss": 0.0014,
      "reward": 1.8494861125946045,
      "reward_std": 0.17398807406425476,
      "rewards/accuracy_reward": 0.7057360410690308,
      "rewards/format_reward": 1.0,
      "step": 2350,
      "temperature": 1.0
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.0,
      "completion_length": 400.671875,
      "epoch": 0.07149373555528525,
      "grad_norm": 2.0475402304796755,
      "kl": 0.043212890625,
      "learning_rate": 9.874411687289696e-07,
      "loss": 0.0017,
      "reward": 1.849299669265747,
      "reward_std": 0.11398116499185562,
      "rewards/accuracy_reward": 0.6899245977401733,
      "rewards/format_reward": 1.0,
      "step": 2351,
      "temperature": 1.0
    },
    {
      "all_correct": 0.625,
      "all_wrong": 0.25,
      "completion_length": 346.640625,
      "epoch": 0.07152414548108503,
      "grad_norm": 0.7994846754047048,
      "kl": 0.041259765625,
      "learning_rate": 9.87430527635543e-07,
      "loss": 0.0017,
      "reward": 1.8551548719406128,
      "reward_std": 0.014731397852301598,
      "rewards/accuracy_reward": 0.7082799077033997,
      "rewards/format_reward": 1.0,
      "step": 2352,
      "temperature": 1.0
    },
    {
      "all_correct": 0.875,
      "all_wrong": 0.125,
      "completion_length": 368.859375,
      "epoch": 0.07155455540688481,
      "grad_norm": 0.19205016763221117,
      "kl": 0.036376953125,
      "learning_rate": 9.874198820933132e-07,
      "loss": 0.0015,
      "reward": 2.046875,
      "reward_std": 0.008838837966322899,
      "rewards/accuracy_reward": 0.875,
      "rewards/format_reward": 1.0,
      "step": 2353,
      "temperature": 1.0
    },
    {
      "all_correct": 0.875,
      "all_wrong": 0.0,
      "completion_length": 361.78125,
      "epoch": 0.07158496533268459,
      "grad_norm": 0.6406138732344626,
      "kl": 0.04638671875,
      "learning_rate": 9.87409232102377e-07,
      "loss": 0.0019,
      "reward": 2.0625,
      "reward_std": 0.0530330091714859,
      "rewards/accuracy_reward": 0.890625,
      "rewards/format_reward": 1.0,
      "step": 2354,
      "temperature": 1.0
    },
    {
      "all_correct": 0.75,
      "all_wrong": 0.0,
      "completion_length": 392.015625,
      "epoch": 0.07161537525848437,
      "grad_norm": 1.184033148557307,
      "kl": 0.034912109375,
      "learning_rate": 9.873985776628324e-07,
      "loss": 0.0014,
      "reward": 1.9982727766036987,
      "reward_std": 0.10642261058092117,
      "rewards/accuracy_reward": 0.8263977766036987,
      "rewards/format_reward": 1.0,
      "step": 2355,
      "temperature": 1.0
    },
    {
      "all_correct": 0.875,
      "all_wrong": 0.0,
      "completion_length": 363.625,
      "epoch": 0.07164578518428415,
      "grad_norm": 0.3001301702894199,
      "kl": 0.0400390625,
      "learning_rate": 9.87387918774776e-07,
      "loss": 0.0016,
      "reward": 2.1750001907348633,
      "reward_std": 0.051754921674728394,
      "rewards/accuracy_reward": 0.984375,
      "rewards/format_reward": 1.0,
      "step": 2356,
      "temperature": 1.0
    },
    {
      "all_correct": 0.625,
      "all_wrong": 0.125,
      "completion_length": 384.265625,
      "epoch": 0.07167619511008393,
      "grad_norm": 2.241678968184171,
      "kl": 0.0361328125,
      "learning_rate": 9.873772554383055e-07,
      "loss": 0.0014,
      "reward": 1.979071021080017,
      "reward_std": 0.02370750904083252,
      "rewards/accuracy_reward": 0.8103209137916565,
      "rewards/format_reward": 1.0,
      "step": 2357,
      "temperature": 1.0
    },
    {
      "all_correct": 0.75,
      "all_wrong": 0.0,
      "completion_length": 347.78125,
      "epoch": 0.07170660503588372,
      "grad_norm": 1.759500690501111,
      "kl": 0.036376953125,
      "learning_rate": 9.873665876535178e-07,
      "loss": 0.0015,
      "reward": 2.059232711791992,
      "reward_std": 0.0892532616853714,
      "rewards/accuracy_reward": 0.8748578429222107,
      "rewards/format_reward": 1.0,
      "step": 2358,
      "temperature": 1.0
    },
    {
      "all_correct": 0.625,
      "all_wrong": 0.25,
      "completion_length": 333.453125,
      "epoch": 0.0717370149616835,
      "grad_norm": 1.7260963301864547,
      "kl": 0.0361328125,
      "learning_rate": 9.873559154205107e-07,
      "loss": 0.0014,
      "reward": 1.78125,
      "reward_std": 0.08711418509483337,
      "rewards/accuracy_reward": 0.65625,
      "rewards/format_reward": 1.0,
      "step": 2359,
      "temperature": 1.0
    },
    {
      "all_correct": 0.75,
      "all_wrong": 0.125,
      "completion_length": 351.734375,
      "epoch": 0.07176742488748328,
      "grad_norm": 0.3294159860598936,
      "kl": 0.03515625,
      "learning_rate": 9.873452387393815e-07,
      "loss": 0.0014,
      "reward": 2.012500047683716,
      "reward_std": 0.06943650543689728,
      "rewards/accuracy_reward": 0.84375,
      "rewards/format_reward": 1.0,
      "step": 2360,
      "temperature": 1.0
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.0,
      "completion_length": 358.015625,
      "epoch": 0.07179783481328306,
      "grad_norm": 1.2387888396808895,
      "kl": 0.034912109375,
      "learning_rate": 9.873345576102275e-07,
      "loss": 0.0014,
      "reward": 1.760685920715332,
      "reward_std": 0.13407106697559357,
      "rewards/accuracy_reward": 0.6231858730316162,
      "rewards/format_reward": 1.0,
      "step": 2361,
      "temperature": 1.0
    },
    {
      "all_correct": 0.625,
      "all_wrong": 0.125,
      "completion_length": 343.359375,
      "epoch": 0.07182824473908284,
      "grad_norm": 1.243195193673154,
      "kl": 0.037353515625,
      "learning_rate": 9.873238720331461e-07,
      "loss": 0.0015,
      "reward": 2.008072853088379,
      "reward_std": 0.11858770251274109,
      "rewards/accuracy_reward": 0.8424479365348816,
      "rewards/format_reward": 1.0,
      "step": 2362,
      "temperature": 1.0
    },
    {
      "all_correct": 0.375,
      "all_wrong": 0.375,
      "completion_length": 399.328125,
      "epoch": 0.07185865466488262,
      "grad_norm": 0.7347466020250426,
      "kl": 0.036865234375,
      "learning_rate": 9.873131820082353e-07,
      "loss": 0.0015,
      "reward": 1.5863829851150513,
      "reward_std": 0.12548309564590454,
      "rewards/accuracy_reward": 0.4926328659057617,
      "rewards/format_reward": 0.984375,
      "step": 2363,
      "temperature": 1.0
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.125,
      "completion_length": 339.78125,
      "epoch": 0.0718890645906824,
      "grad_norm": 2.430927093095686,
      "kl": 0.04443359375,
      "learning_rate": 9.87302487535592e-07,
      "loss": 0.0018,
      "reward": 1.8776071071624756,
      "reward_std": 0.1703161895275116,
      "rewards/accuracy_reward": 0.7307321429252625,
      "rewards/format_reward": 1.0,
      "step": 2364,
      "temperature": 1.0
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.25,
      "completion_length": 390.328125,
      "epoch": 0.07191947451648217,
      "grad_norm": 0.726168856376468,
      "kl": 0.04052734375,
      "learning_rate": 9.872917886153143e-07,
      "loss": 0.0016,
      "reward": 1.73752760887146,
      "reward_std": 0.013866622932255268,
      "rewards/accuracy_reward": 0.5906525254249573,
      "rewards/format_reward": 1.0,
      "step": 2365,
      "temperature": 1.0
    },
    {
      "all_correct": 0.375,
      "all_wrong": 0.25,
      "completion_length": 348.53125,
      "epoch": 0.07194988444228197,
      "grad_norm": 1.4092102397226216,
      "kl": 0.03857421875,
      "learning_rate": 9.872810852474998e-07,
      "loss": 0.0015,
      "reward": 1.7188366651535034,
      "reward_std": 0.14098027348518372,
      "rewards/accuracy_reward": 0.5907115936279297,
      "rewards/format_reward": 1.0,
      "step": 2366,
      "temperature": 1.0
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.0,
      "completion_length": 375.140625,
      "epoch": 0.07198029436808175,
      "grad_norm": 1.008741601967172,
      "kl": 0.033447265625,
      "learning_rate": 9.872703774322459e-07,
      "loss": 0.0013,
      "reward": 1.8539319038391113,
      "reward_std": 0.1849345564842224,
      "rewards/accuracy_reward": 0.6976817846298218,
      "rewards/format_reward": 1.0,
      "step": 2367,
      "temperature": 1.0
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.0,
      "completion_length": 400.046875,
      "epoch": 0.07201070429388153,
      "grad_norm": 1.1956523031934239,
      "kl": 0.049560546875,
      "learning_rate": 9.872596651696507e-07,
      "loss": 0.002,
      "reward": 1.8618621826171875,
      "reward_std": 0.10856911540031433,
      "rewards/accuracy_reward": 0.6899871230125427,
      "rewards/format_reward": 1.0,
      "step": 2368,
      "temperature": 1.0
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.25,
      "completion_length": 357.359375,
      "epoch": 0.0720411142196813,
      "grad_norm": 0.7288300839194058,
      "kl": 0.04296875,
      "learning_rate": 9.872489484598118e-07,
      "loss": 0.0017,
      "reward": 1.7676124572753906,
      "reward_std": 0.08025988936424255,
      "rewards/accuracy_reward": 0.6269873976707458,
      "rewards/format_reward": 1.0,
      "step": 2369,
      "temperature": 1.0
    },
    {
      "all_correct": 0.875,
      "all_wrong": 0.0,
      "completion_length": 406.53125,
      "epoch": 0.07207152414548108,
      "grad_norm": 0.42346943927514236,
      "kl": 0.027587890625,
      "learning_rate": 9.872382273028271e-07,
      "loss": 0.0011,
      "reward": 2.159374952316284,
      "reward_std": 0.07344459742307663,
      "rewards/accuracy_reward": 0.984375,
      "rewards/format_reward": 1.0,
      "step": 2370,
      "temperature": 1.0
    },
    {
      "all_correct": 0.375,
      "all_wrong": 0.25,
      "completion_length": 386.859375,
      "epoch": 0.07210193407128086,
      "grad_norm": 0.5160970530543679,
      "kl": 0.035888671875,
      "learning_rate": 9.87227501698794e-07,
      "loss": 0.0014,
      "reward": 1.6359111070632935,
      "reward_std": 0.07127352058887482,
      "rewards/accuracy_reward": 0.5046610832214355,
      "rewards/format_reward": 1.0,
      "step": 2371,
      "temperature": 1.0
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.25,
      "completion_length": 371.71875,
      "epoch": 0.07213234399708064,
      "grad_norm": 0.7304731625868155,
      "kl": 0.037353515625,
      "learning_rate": 9.87216771647811e-07,
      "loss": 0.0015,
      "reward": 1.7207286357879639,
      "reward_std": 0.042031966149806976,
      "rewards/accuracy_reward": 0.5832285284996033,
      "rewards/format_reward": 1.0,
      "step": 2372,
      "temperature": 1.0
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.125,
      "completion_length": 372.796875,
      "epoch": 0.07216275392288043,
      "grad_norm": 1.305029130028423,
      "kl": 0.036865234375,
      "learning_rate": 9.87206037149976e-07,
      "loss": 0.0015,
      "reward": 1.7617288827896118,
      "reward_std": 0.13543274998664856,
      "rewards/accuracy_reward": 0.6273539066314697,
      "rewards/format_reward": 1.0,
      "step": 2373,
      "temperature": 1.0
    },
    {
      "all_correct": 0.625,
      "all_wrong": 0.125,
      "completion_length": 349.859375,
      "epoch": 0.07219316384868021,
      "grad_norm": 0.9322076558580428,
      "kl": 0.0400390625,
      "learning_rate": 9.871952982053864e-07,
      "loss": 0.0016,
      "reward": 1.9011987447738647,
      "reward_std": 0.08437976986169815,
      "rewards/accuracy_reward": 0.7386987209320068,
      "rewards/format_reward": 1.0,
      "step": 2374,
      "temperature": 1.0
    },
    {
      "all_correct": 0.625,
      "all_wrong": 0.0,
      "completion_length": 371.5,
      "epoch": 0.07222357377448,
      "grad_norm": 3.781595040304778,
      "kl": 0.048828125,
      "learning_rate": 9.871845548141407e-07,
      "loss": 0.002,
      "reward": 1.8638901710510254,
      "reward_std": 0.09927506744861603,
      "rewards/accuracy_reward": 0.7138901948928833,
      "rewards/format_reward": 1.0,
      "step": 2375,
      "temperature": 1.0
    },
    {
      "all_correct": 0.625,
      "all_wrong": 0.125,
      "completion_length": 352.109375,
      "epoch": 0.07225398370027977,
      "grad_norm": 0.9940906767625175,
      "kl": 0.04736328125,
      "learning_rate": 9.871738069763369e-07,
      "loss": 0.0019,
      "reward": 1.9334869384765625,
      "reward_std": 0.0318918414413929,
      "rewards/accuracy_reward": 0.7678618431091309,
      "rewards/format_reward": 1.0,
      "step": 2376,
      "temperature": 1.0
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.0,
      "completion_length": 396.0,
      "epoch": 0.07228439362607955,
      "grad_norm": 1.9071408267644623,
      "kl": 0.052490234375,
      "learning_rate": 9.87163054692073e-07,
      "loss": 0.0021,
      "reward": 1.8087539672851562,
      "reward_std": 0.14542332291603088,
      "rewards/accuracy_reward": 0.6681289672851562,
      "rewards/format_reward": 0.96875,
      "step": 2377,
      "temperature": 1.0
    },
    {
      "all_correct": 0.875,
      "all_wrong": 0.0,
      "completion_length": 376.890625,
      "epoch": 0.07231480355187933,
      "grad_norm": 0.27206154736830773,
      "kl": 0.037841796875,
      "learning_rate": 9.87152297961447e-07,
      "loss": 0.0015,
      "reward": 2.1061627864837646,
      "reward_std": 0.005692124832421541,
      "rewards/accuracy_reward": 0.9311627149581909,
      "rewards/format_reward": 1.0,
      "step": 2378,
      "temperature": 1.0
    },
    {
      "all_correct": 0.625,
      "all_wrong": 0.125,
      "completion_length": 342.234375,
      "epoch": 0.07234521347767911,
      "grad_norm": 1.3631018169865634,
      "kl": 0.03515625,
      "learning_rate": 9.871415367845576e-07,
      "loss": 0.0014,
      "reward": 1.9156250953674316,
      "reward_std": 0.13130834698677063,
      "rewards/accuracy_reward": 0.765625,
      "rewards/format_reward": 1.0,
      "step": 2379,
      "temperature": 1.0
    },
    {
      "all_correct": 0.375,
      "all_wrong": 0.125,
      "completion_length": 435.15625,
      "epoch": 0.07237562340347889,
      "grad_norm": 2.0533319360748763,
      "kl": 0.03662109375,
      "learning_rate": 9.871307711615025e-07,
      "loss": 0.0015,
      "reward": 1.707545518875122,
      "reward_std": 0.06655619293451309,
      "rewards/accuracy_reward": 0.5606704354286194,
      "rewards/format_reward": 1.0,
      "step": 2380,
      "temperature": 1.0
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.25,
      "completion_length": 345.625,
      "epoch": 0.07240603332927868,
      "grad_norm": 0.9042574155831559,
      "kl": 0.047607421875,
      "learning_rate": 9.871200010923802e-07,
      "loss": 0.0019,
      "reward": 1.7468749284744263,
      "reward_std": 0.09722718596458435,
      "rewards/accuracy_reward": 0.625,
      "rewards/format_reward": 1.0,
      "step": 2381,
      "temperature": 1.0
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.0,
      "completion_length": 372.484375,
      "epoch": 0.07243644325507846,
      "grad_norm": 1.053134833408383,
      "kl": 0.04931640625,
      "learning_rate": 9.871092265772886e-07,
      "loss": 0.002,
      "reward": 1.7778041362762451,
      "reward_std": 0.09956423938274384,
      "rewards/accuracy_reward": 0.6246791481971741,
      "rewards/format_reward": 1.0,
      "step": 2382,
      "temperature": 1.0
    },
    {
      "all_correct": 0.625,
      "all_wrong": 0.125,
      "completion_length": 361.015625,
      "epoch": 0.07246685318087824,
      "grad_norm": 1.411380564106867,
      "kl": 0.04248046875,
      "learning_rate": 9.870984476163266e-07,
      "loss": 0.0017,
      "reward": 1.9268344640731812,
      "reward_std": 0.06711134314537048,
      "rewards/accuracy_reward": 0.7612094879150391,
      "rewards/format_reward": 1.0,
      "step": 2383,
      "temperature": 1.0
    },
    {
      "all_correct": 0.375,
      "all_wrong": 0.125,
      "completion_length": 379.734375,
      "epoch": 0.07249726310667802,
      "grad_norm": 1.7399343535562768,
      "kl": 0.037109375,
      "learning_rate": 9.870876642095924e-07,
      "loss": 0.0015,
      "reward": 1.6735461950302124,
      "reward_std": 0.20593903958797455,
      "rewards/accuracy_reward": 0.5391713380813599,
      "rewards/format_reward": 1.0,
      "step": 2384,
      "temperature": 1.0
    },
    {
      "all_correct": 0.375,
      "all_wrong": 0.125,
      "completion_length": 363.46875,
      "epoch": 0.0725276730324778,
      "grad_norm": 1.2494202082179664,
      "kl": 0.039794921875,
      "learning_rate": 9.870768763571845e-07,
      "loss": 0.0016,
      "reward": 1.6788194179534912,
      "reward_std": 0.2000548392534256,
      "rewards/accuracy_reward": 0.5538194179534912,
      "rewards/format_reward": 1.0,
      "step": 2385,
      "temperature": 1.0
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.25,
      "completion_length": 364.453125,
      "epoch": 0.07255808295827758,
      "grad_norm": 0.7192996518087594,
      "kl": 0.03515625,
      "learning_rate": 9.870660840592009e-07,
      "loss": 0.0014,
      "reward": 1.725977897644043,
      "reward_std": 0.016961591318249702,
      "rewards/accuracy_reward": 0.5791028738021851,
      "rewards/format_reward": 1.0,
      "step": 2386,
      "temperature": 1.0
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.125,
      "completion_length": 409.828125,
      "epoch": 0.07258849288407736,
      "grad_norm": 1.1885091410867556,
      "kl": 0.030029296875,
      "learning_rate": 9.870552873157406e-07,
      "loss": 0.0012,
      "reward": 1.8222078084945679,
      "reward_std": 0.10220152884721756,
      "rewards/accuracy_reward": 0.684707760810852,
      "rewards/format_reward": 1.0,
      "step": 2387,
      "temperature": 1.0
    },
    {
      "all_correct": 0.875,
      "all_wrong": 0.125,
      "completion_length": 341.78125,
      "epoch": 0.07261890280987715,
      "grad_norm": 0.5542245890413094,
      "kl": 0.041259765625,
      "learning_rate": 9.870444861269019e-07,
      "loss": 0.0016,
      "reward": 2.0445313453674316,
      "reward_std": 0.0022097111213952303,
      "rewards/accuracy_reward": 0.8695312142372131,
      "rewards/format_reward": 1.0,
      "step": 2388,
      "temperature": 1.0
    },
    {
      "all_correct": 0.625,
      "all_wrong": 0.125,
      "completion_length": 382.671875,
      "epoch": 0.07264931273567693,
      "grad_norm": 0.789375085898076,
      "kl": 0.03125,
      "learning_rate": 9.870336804927835e-07,
      "loss": 0.0012,
      "reward": 1.931337594985962,
      "reward_std": 0.08027233928442001,
      "rewards/accuracy_reward": 0.768837571144104,
      "rewards/format_reward": 1.0,
      "step": 2389,
      "temperature": 1.0
    },
    {
      "all_correct": 0.375,
      "all_wrong": 0.0,
      "completion_length": 365.34375,
      "epoch": 0.07267972266147671,
      "grad_norm": 1.4420029424731065,
      "kl": 0.03515625,
      "learning_rate": 9.870228704134838e-07,
      "loss": 0.0014,
      "reward": 1.7843749523162842,
      "reward_std": 0.305536687374115,
      "rewards/accuracy_reward": 0.65625,
      "rewards/format_reward": 1.0,
      "step": 2390,
      "temperature": 1.0
    },
    {
      "all_correct": 0.25,
      "all_wrong": 0.125,
      "completion_length": 381.828125,
      "epoch": 0.07271013258727649,
      "grad_norm": 1.3907322998654708,
      "kl": 0.037109375,
      "learning_rate": 9.87012055889102e-07,
      "loss": 0.0015,
      "reward": 1.6607921123504639,
      "reward_std": 0.3719618320465088,
      "rewards/accuracy_reward": 0.576417088508606,
      "rewards/format_reward": 0.984375,
      "step": 2391,
      "temperature": 1.0
    },
    {
      "all_correct": 0.625,
      "all_wrong": 0.25,
      "completion_length": 352.421875,
      "epoch": 0.07274054251307627,
      "grad_norm": 1.0067768056594717,
      "kl": 0.040283203125,
      "learning_rate": 9.87001236919736e-07,
      "loss": 0.0016,
      "reward": 1.801041603088379,
      "reward_std": 0.09032879024744034,
      "rewards/accuracy_reward": 0.6697916984558105,
      "rewards/format_reward": 1.0,
      "step": 2392,
      "temperature": 1.0
    },
    {
      "all_correct": 0.375,
      "all_wrong": 0.125,
      "completion_length": 388.171875,
      "epoch": 0.07277095243887605,
      "grad_norm": 3.321728941018141,
      "kl": 0.03515625,
      "learning_rate": 9.869904135054852e-07,
      "loss": 0.0014,
      "reward": 1.7820522785186768,
      "reward_std": 0.08742889016866684,
      "rewards/accuracy_reward": 0.6164272427558899,
      "rewards/format_reward": 1.0,
      "step": 2393,
      "temperature": 1.0
    },
    {
      "all_correct": 0.625,
      "all_wrong": 0.0,
      "completion_length": 365.0625,
      "epoch": 0.07280136236467583,
      "grad_norm": 1.1074975879512672,
      "kl": 0.03662109375,
      "learning_rate": 9.869795856464483e-07,
      "loss": 0.0015,
      "reward": 2.0538861751556396,
      "reward_std": 0.19253724813461304,
      "rewards/accuracy_reward": 0.8788861036300659,
      "rewards/format_reward": 1.0,
      "step": 2394,
      "temperature": 1.0
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.5,
      "completion_length": 344.9375,
      "epoch": 0.0728317722904756,
      "grad_norm": 0.06032410292837829,
      "kl": 0.038818359375,
      "learning_rate": 9.869687533427238e-07,
      "loss": 0.0015,
      "reward": 1.600000023841858,
      "reward_std": 0.0,
      "rewards/accuracy_reward": 0.5,
      "rewards/format_reward": 1.0,
      "step": 2395,
      "temperature": 1.0
    },
    {
      "all_correct": 0.25,
      "all_wrong": 0.375,
      "completion_length": 373.015625,
      "epoch": 0.0728621822162754,
      "grad_norm": 0.5321502698427486,
      "kl": 0.04296875,
      "learning_rate": 9.86957916594411e-07,
      "loss": 0.0017,
      "reward": 1.5008922815322876,
      "reward_std": 0.04707634076476097,
      "rewards/accuracy_reward": 0.40089231729507446,
      "rewards/format_reward": 1.0,
      "step": 2396,
      "temperature": 1.0
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.125,
      "completion_length": 355.578125,
      "epoch": 0.07289259214207518,
      "grad_norm": 1.8741475856880374,
      "kl": 0.048095703125,
      "learning_rate": 9.869470754016084e-07,
      "loss": 0.0019,
      "reward": 1.8517272472381592,
      "reward_std": 0.09261726588010788,
      "rewards/accuracy_reward": 0.6954772472381592,
      "rewards/format_reward": 1.0,
      "step": 2397,
      "temperature": 1.0
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.25,
      "completion_length": 368.640625,
      "epoch": 0.07292300206787496,
      "grad_norm": 1.2045149246166644,
      "kl": 0.044189453125,
      "learning_rate": 9.86936229764415e-07,
      "loss": 0.0018,
      "reward": 1.7932454347610474,
      "reward_std": 0.06748578697443008,
      "rewards/accuracy_reward": 0.6494954824447632,
      "rewards/format_reward": 1.0,
      "step": 2398,
      "temperature": 1.0
    },
    {
      "all_correct": 0.625,
      "all_wrong": 0.375,
      "completion_length": 356.140625,
      "epoch": 0.07295341199367474,
      "grad_norm": 0.7142624481867306,
      "kl": 0.035888671875,
      "learning_rate": 9.869253796829301e-07,
      "loss": 0.0014,
      "reward": 1.7468750476837158,
      "reward_std": 0.008838837966322899,
      "rewards/accuracy_reward": 0.625,
      "rewards/format_reward": 1.0,
      "step": 2399,
      "temperature": 1.0
    },
    {
      "all_correct": 0.25,
      "all_wrong": 0.375,
      "completion_length": 377.203125,
      "epoch": 0.07298382191947451,
      "grad_norm": 1.181274004680584,
      "kl": 0.0439453125,
      "learning_rate": 9.869145251572526e-07,
      "loss": 0.0018,
      "reward": 1.4649507999420166,
      "reward_std": 0.12162395566701889,
      "rewards/accuracy_reward": 0.3774508237838745,
      "rewards/format_reward": 1.0,
      "step": 2400,
      "temperature": 1.0
    },
    {
      "all_correct": 0.75,
      "all_wrong": 0.125,
      "completion_length": 339.515625,
      "epoch": 0.0730142318452743,
      "grad_norm": 1.0074126329381317,
      "kl": 0.04150390625,
      "learning_rate": 9.869036661874814e-07,
      "loss": 0.0017,
      "reward": 1.9090144634246826,
      "reward_std": 0.03275389224290848,
      "rewards/accuracy_reward": 0.7590144276618958,
      "rewards/format_reward": 1.0,
      "step": 2401,
      "temperature": 1.0
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.0,
      "completion_length": 355.6875,
      "epoch": 0.07304464177107407,
      "grad_norm": 1.4011800320960943,
      "kl": 0.04541015625,
      "learning_rate": 9.868928027737159e-07,
      "loss": 0.0018,
      "reward": 1.8778297901153564,
      "reward_std": 0.14642588794231415,
      "rewards/accuracy_reward": 0.7122048139572144,
      "rewards/format_reward": 1.0,
      "step": 2402,
      "temperature": 1.0
    },
    {
      "all_correct": 0.625,
      "all_wrong": 0.125,
      "completion_length": 376.84375,
      "epoch": 0.07307505169687387,
      "grad_norm": 0.7152743718494116,
      "kl": 0.03564453125,
      "learning_rate": 9.868819349160548e-07,
      "loss": 0.0014,
      "reward": 1.9742333889007568,
      "reward_std": 0.0811690092086792,
      "rewards/accuracy_reward": 0.8117333054542542,
      "rewards/format_reward": 1.0,
      "step": 2403,
      "temperature": 1.0
    },
    {
      "all_correct": 0.375,
      "all_wrong": 0.125,
      "completion_length": 364.9375,
      "epoch": 0.07310546162267365,
      "grad_norm": 2.224080701981514,
      "kl": 0.042236328125,
      "learning_rate": 9.868710626145977e-07,
      "loss": 0.0017,
      "reward": 1.6684293746948242,
      "reward_std": 0.16979125142097473,
      "rewards/accuracy_reward": 0.5434294939041138,
      "rewards/format_reward": 1.0,
      "step": 2404,
      "temperature": 1.0
    },
    {
      "all_correct": 0.625,
      "all_wrong": 0.125,
      "completion_length": 357.734375,
      "epoch": 0.07313587154847342,
      "grad_norm": 0.8129115621368378,
      "kl": 0.043212890625,
      "learning_rate": 9.868601858694437e-07,
      "loss": 0.0017,
      "reward": 1.9687224626541138,
      "reward_std": 0.07925340533256531,
      "rewards/accuracy_reward": 0.796847403049469,
      "rewards/format_reward": 1.0,
      "step": 2405,
      "temperature": 1.0
    },
    {
      "all_correct": 0.75,
      "all_wrong": 0.125,
      "completion_length": 380.4375,
      "epoch": 0.0731662814742732,
      "grad_norm": 0.4888095820681017,
      "kl": 0.04833984375,
      "learning_rate": 9.868493046806921e-07,
      "loss": 0.0019,
      "reward": 1.9721442461013794,
      "reward_std": 0.02054297924041748,
      "rewards/accuracy_reward": 0.8002692461013794,
      "rewards/format_reward": 1.0,
      "step": 2406,
      "temperature": 1.0
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.25,
      "completion_length": 356.046875,
      "epoch": 0.07319669140007298,
      "grad_norm": 0.900442763788821,
      "kl": 0.03955078125,
      "learning_rate": 9.868384190484422e-07,
      "loss": 0.0016,
      "reward": 1.803674578666687,
      "reward_std": 0.05646608769893646,
      "rewards/accuracy_reward": 0.6567996144294739,
      "rewards/format_reward": 1.0,
      "step": 2407,
      "temperature": 1.0
    },
    {
      "all_correct": 0.625,
      "all_wrong": 0.125,
      "completion_length": 379.75,
      "epoch": 0.07322710132587276,
      "grad_norm": 1.04362222171391,
      "kl": 0.035400390625,
      "learning_rate": 9.868275289727931e-07,
      "loss": 0.0014,
      "reward": 1.8784642219543457,
      "reward_std": 0.03106926567852497,
      "rewards/accuracy_reward": 0.7159643173217773,
      "rewards/format_reward": 1.0,
      "step": 2408,
      "temperature": 1.0
    },
    {
      "all_correct": 0.625,
      "all_wrong": 0.0,
      "completion_length": 368.203125,
      "epoch": 0.07325751125167254,
      "grad_norm": 0.9722738501812692,
      "kl": 0.0341796875,
      "learning_rate": 9.868166344538447e-07,
      "loss": 0.0014,
      "reward": 2.010758876800537,
      "reward_std": 0.10203946381807327,
      "rewards/accuracy_reward": 0.8263838887214661,
      "rewards/format_reward": 1.0,
      "step": 2409,
      "temperature": 1.0
    },
    {
      "all_correct": 0.625,
      "all_wrong": 0.125,
      "completion_length": 373.578125,
      "epoch": 0.07328792117747232,
      "grad_norm": 0.848783283002575,
      "kl": 0.03125,
      "learning_rate": 9.86805735491696e-07,
      "loss": 0.0013,
      "reward": 1.890326738357544,
      "reward_std": 0.008600450120866299,
      "rewards/accuracy_reward": 0.7153265476226807,
      "rewards/format_reward": 1.0,
      "step": 2410,
      "temperature": 1.0
    },
    {
      "all_correct": 0.625,
      "all_wrong": 0.25,
      "completion_length": 349.03125,
      "epoch": 0.07331833110327211,
      "grad_norm": 0.44144534797573287,
      "kl": 0.043701171875,
      "learning_rate": 9.867948320864468e-07,
      "loss": 0.0017,
      "reward": 1.8229761123657227,
      "reward_std": 0.010387420654296875,
      "rewards/accuracy_reward": 0.67610102891922,
      "rewards/format_reward": 1.0,
      "step": 2411,
      "temperature": 1.0
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.25,
      "completion_length": 365.3125,
      "epoch": 0.07334874102907189,
      "grad_norm": 1.4943415954741863,
      "kl": 0.03173828125,
      "learning_rate": 9.867839242381964e-07,
      "loss": 0.0013,
      "reward": 1.769737958908081,
      "reward_std": 0.08797435462474823,
      "rewards/accuracy_reward": 0.6384879946708679,
      "rewards/format_reward": 1.0,
      "step": 2412,
      "temperature": 1.0
    },
    {
      "all_correct": 0.75,
      "all_wrong": 0.0,
      "completion_length": 349.90625,
      "epoch": 0.07337915095487167,
      "grad_norm": 0.6053844622722483,
      "kl": 0.038818359375,
      "learning_rate": 9.867730119470443e-07,
      "loss": 0.0016,
      "reward": 2.082291603088379,
      "reward_std": 0.09599603712558746,
      "rewards/accuracy_reward": 0.9010416865348816,
      "rewards/format_reward": 1.0,
      "step": 2413,
      "temperature": 1.0
    },
    {
      "all_correct": 0.75,
      "all_wrong": 0.25,
      "completion_length": 338.9375,
      "epoch": 0.07340956088067145,
      "grad_norm": 0.047609186335330136,
      "kl": 0.041015625,
      "learning_rate": 9.867620952130903e-07,
      "loss": 0.0016,
      "reward": 1.9000000953674316,
      "reward_std": 0.0,
      "rewards/accuracy_reward": 0.75,
      "rewards/format_reward": 1.0,
      "step": 2414,
      "temperature": 1.0
    },
    {
      "all_correct": 0.25,
      "all_wrong": 0.125,
      "completion_length": 365.1875,
      "epoch": 0.07343997080647123,
      "grad_norm": 1.14244099142403,
      "kl": 0.04931640625,
      "learning_rate": 9.86751174036434e-07,
      "loss": 0.002,
      "reward": 1.7373353242874146,
      "reward_std": 0.04766164720058441,
      "rewards/accuracy_reward": 0.5685853958129883,
      "rewards/format_reward": 1.0,
      "step": 2415,
      "temperature": 1.0
    },
    {
      "all_correct": 0.625,
      "all_wrong": 0.0,
      "completion_length": 368.203125,
      "epoch": 0.07347038073227101,
      "grad_norm": 2.6817091003209006,
      "kl": 0.034423828125,
      "learning_rate": 9.86740248417175e-07,
      "loss": 0.0014,
      "reward": 1.9533547163009644,
      "reward_std": 0.01623806357383728,
      "rewards/accuracy_reward": 0.7533547282218933,
      "rewards/format_reward": 1.0,
      "step": 2416,
      "temperature": 1.0
    },
    {
      "all_correct": 0.625,
      "all_wrong": 0.25,
      "completion_length": 357.828125,
      "epoch": 0.07350079065807079,
      "grad_norm": 0.5245537740639242,
      "kl": 0.0390625,
      "learning_rate": 9.867293183554128e-07,
      "loss": 0.0016,
      "reward": 1.827418327331543,
      "reward_std": 0.0031466642394661903,
      "rewards/accuracy_reward": 0.6774182915687561,
      "rewards/format_reward": 1.0,
      "step": 2417,
      "temperature": 1.0
    },
    {
      "all_correct": 0.375,
      "all_wrong": 0.0,
      "completion_length": 374.765625,
      "epoch": 0.07353120058387058,
      "grad_norm": 1.3460949967649667,
      "kl": 0.04638671875,
      "learning_rate": 9.867183838512477e-07,
      "loss": 0.0019,
      "reward": 1.7104425430297852,
      "reward_std": 0.11293171346187592,
      "rewards/accuracy_reward": 0.5573174953460693,
      "rewards/format_reward": 1.0,
      "step": 2418,
      "temperature": 1.0
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.125,
      "completion_length": 372.046875,
      "epoch": 0.07356161050967036,
      "grad_norm": 1.7305739883484743,
      "kl": 0.04150390625,
      "learning_rate": 9.867074449047791e-07,
      "loss": 0.0017,
      "reward": 1.7051334381103516,
      "reward_std": 0.00995232630521059,
      "rewards/accuracy_reward": 0.5551333427429199,
      "rewards/format_reward": 1.0,
      "step": 2419,
      "temperature": 1.0
    },
    {
      "all_correct": 0.375,
      "all_wrong": 0.125,
      "completion_length": 381.609375,
      "epoch": 0.07359202043547014,
      "grad_norm": 1.4617132159168726,
      "kl": 0.035400390625,
      "learning_rate": 9.86696501516107e-07,
      "loss": 0.0014,
      "reward": 1.825235366821289,
      "reward_std": 0.14546802639961243,
      "rewards/accuracy_reward": 0.6721101999282837,
      "rewards/format_reward": 1.0,
      "step": 2420,
      "temperature": 1.0
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.25,
      "completion_length": 351.28125,
      "epoch": 0.07362243036126992,
      "grad_norm": 0.8256672478524869,
      "kl": 0.029541015625,
      "learning_rate": 9.866855536853312e-07,
      "loss": 0.0012,
      "reward": 1.7546409368515015,
      "reward_std": 0.015134266577661037,
      "rewards/accuracy_reward": 0.6077659130096436,
      "rewards/format_reward": 1.0,
      "step": 2421,
      "temperature": 1.0
    },
    {
      "all_correct": 0.375,
      "all_wrong": 0.5,
      "completion_length": 369.0,
      "epoch": 0.0736528402870697,
      "grad_norm": 1.9125822630779419,
      "kl": 0.0322265625,
      "learning_rate": 9.866746014125515e-07,
      "loss": 0.0013,
      "reward": 1.5,
      "reward_std": 0.08256310969591141,
      "rewards/accuracy_reward": 0.421875,
      "rewards/format_reward": 1.0,
      "step": 2422,
      "temperature": 1.0
    },
    {
      "all_correct": 0.625,
      "all_wrong": 0.125,
      "completion_length": 342.96875,
      "epoch": 0.07368325021286948,
      "grad_norm": 0.4376545276079412,
      "kl": 0.042236328125,
      "learning_rate": 9.866636446978682e-07,
      "loss": 0.0017,
      "reward": 2.0044641494750977,
      "reward_std": 0.0530330091714859,
      "rewards/accuracy_reward": 0.8325892686843872,
      "rewards/format_reward": 1.0,
      "step": 2423,
      "temperature": 1.0
    },
    {
      "all_correct": 0.375,
      "all_wrong": 0.25,
      "completion_length": 366.078125,
      "epoch": 0.07371366013866926,
      "grad_norm": 2.040210001686647,
      "kl": 0.04052734375,
      "learning_rate": 9.866526835413811e-07,
      "loss": 0.0016,
      "reward": 1.6171314716339111,
      "reward_std": 0.02809916064143181,
      "rewards/accuracy_reward": 0.473381370306015,
      "rewards/format_reward": 1.0,
      "step": 2424,
      "temperature": 1.0
    },
    {
      "all_correct": 0.375,
      "all_wrong": 0.25,
      "completion_length": 388.421875,
      "epoch": 0.07374407006446904,
      "grad_norm": 1.4886639303523426,
      "kl": 0.04248046875,
      "learning_rate": 9.866417179431903e-07,
      "loss": 0.0017,
      "reward": 1.590973138809204,
      "reward_std": 0.18717995285987854,
      "rewards/accuracy_reward": 0.5534729957580566,
      "rewards/format_reward": 0.9375,
      "step": 2425,
      "temperature": 1.0
    },
    {
      "all_correct": 0.75,
      "all_wrong": 0.125,
      "completion_length": 338.46875,
      "epoch": 0.07377447999026883,
      "grad_norm": 2.464349857867224,
      "kl": 0.03955078125,
      "learning_rate": 9.866307479033954e-07,
      "loss": 0.0016,
      "reward": 1.96875,
      "reward_std": 0.08611097186803818,
      "rewards/accuracy_reward": 0.8125,
      "rewards/format_reward": 1.0,
      "step": 2426,
      "temperature": 1.0
    },
    {
      "all_correct": 0.75,
      "all_wrong": 0.125,
      "completion_length": 340.3125,
      "epoch": 0.07380488991606861,
      "grad_norm": 4.064602911142833,
      "kl": 0.034912109375,
      "learning_rate": 9.866197734220975e-07,
      "loss": 0.0014,
      "reward": 2.0093750953674316,
      "reward_std": 0.07827534526586533,
      "rewards/accuracy_reward": 0.84375,
      "rewards/format_reward": 1.0,
      "step": 2427,
      "temperature": 1.0
    },
    {
      "all_correct": 0.125,
      "all_wrong": 0.375,
      "completion_length": 387.375,
      "epoch": 0.07383529984186839,
      "grad_norm": 0.901584615767375,
      "kl": 0.038330078125,
      "learning_rate": 9.86608794499396e-07,
      "loss": 0.0015,
      "reward": 1.4975647926330566,
      "reward_std": 0.2287033200263977,
      "rewards/accuracy_reward": 0.406939834356308,
      "rewards/format_reward": 1.0,
      "step": 2428,
      "temperature": 1.0
    },
    {
      "all_correct": 0.875,
      "all_wrong": 0.125,
      "completion_length": 356.453125,
      "epoch": 0.07386570976766817,
      "grad_norm": 0.6777475619072667,
      "kl": 0.03759765625,
      "learning_rate": 9.865978111353914e-07,
      "loss": 0.0015,
      "reward": 2.0374999046325684,
      "reward_std": 0.029250433668494225,
      "rewards/accuracy_reward": 0.875,
      "rewards/format_reward": 1.0,
      "step": 2429,
      "temperature": 1.0
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.125,
      "completion_length": 389.0,
      "epoch": 0.07389611969346795,
      "grad_norm": 1.550111489281346,
      "kl": 0.0458984375,
      "learning_rate": 9.865868233301838e-07,
      "loss": 0.0018,
      "reward": 1.83012056350708,
      "reward_std": 0.10616391152143478,
      "rewards/accuracy_reward": 0.6832455396652222,
      "rewards/format_reward": 1.0,
      "step": 2430,
      "temperature": 1.0
    },
    {
      "all_correct": 0.625,
      "all_wrong": 0.0,
      "completion_length": 378.25,
      "epoch": 0.07392652961926773,
      "grad_norm": 0.9195488957637191,
      "kl": 0.035888671875,
      "learning_rate": 9.865758310838737e-07,
      "loss": 0.0014,
      "reward": 2.0080654621124268,
      "reward_std": 0.06260258704423904,
      "rewards/accuracy_reward": 0.8111904263496399,
      "rewards/format_reward": 1.0,
      "step": 2431,
      "temperature": 1.0
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.25,
      "completion_length": 383.390625,
      "epoch": 0.0739569395450675,
      "grad_norm": 1.2083513160361266,
      "kl": 0.0390625,
      "learning_rate": 9.86564834396561e-07,
      "loss": 0.0016,
      "reward": 1.6922341585159302,
      "reward_std": 0.09212476760149002,
      "rewards/accuracy_reward": 0.5734841227531433,
      "rewards/format_reward": 1.0,
      "step": 2432,
      "temperature": 1.0
    },
    {
      "all_correct": 0.375,
      "all_wrong": 0.125,
      "completion_length": 356.515625,
      "epoch": 0.0739873494708673,
      "grad_norm": 2.318027168455351,
      "kl": 0.04296875,
      "learning_rate": 9.865538332683465e-07,
      "loss": 0.0017,
      "reward": 1.7383453845977783,
      "reward_std": 0.230462446808815,
      "rewards/accuracy_reward": 0.6102203726768494,
      "rewards/format_reward": 1.0,
      "step": 2433,
      "temperature": 1.0
    },
    {
      "all_correct": 0.375,
      "all_wrong": 0.125,
      "completion_length": 357.015625,
      "epoch": 0.07401775939666708,
      "grad_norm": 1.3237742822388896,
      "kl": 0.03515625,
      "learning_rate": 9.865428276993305e-07,
      "loss": 0.0014,
      "reward": 1.816334843635559,
      "reward_std": 0.1322784125804901,
      "rewards/accuracy_reward": 0.6600847244262695,
      "rewards/format_reward": 1.0,
      "step": 2434,
      "temperature": 1.0
    },
    {
      "all_correct": 0.625,
      "all_wrong": 0.0,
      "completion_length": 369.84375,
      "epoch": 0.07404816932246686,
      "grad_norm": 1.0224552754149703,
      "kl": 0.03271484375,
      "learning_rate": 9.865318176896137e-07,
      "loss": 0.0013,
      "reward": 2.000845432281494,
      "reward_std": 0.088492751121521,
      "rewards/accuracy_reward": 0.8102203607559204,
      "rewards/format_reward": 1.0,
      "step": 2435,
      "temperature": 1.0
    },
    {
      "all_correct": 0.25,
      "all_wrong": 0.125,
      "completion_length": 413.859375,
      "epoch": 0.07407857924826663,
      "grad_norm": 1.1050400285244213,
      "kl": 0.050537109375,
      "learning_rate": 9.865208032392959e-07,
      "loss": 0.002,
      "reward": 1.7133132219314575,
      "reward_std": 0.12883175909519196,
      "rewards/accuracy_reward": 0.5695631504058838,
      "rewards/format_reward": 1.0,
      "step": 2436,
      "temperature": 1.0
    },
    {
      "all_correct": 0.625,
      "all_wrong": 0.125,
      "completion_length": 367.203125,
      "epoch": 0.07410898917406641,
      "grad_norm": 0.6038902397687032,
      "kl": 0.050048828125,
      "learning_rate": 9.865097843484782e-07,
      "loss": 0.002,
      "reward": 1.8265496492385864,
      "reward_std": 0.060750119388103485,
      "rewards/accuracy_reward": 0.6859246492385864,
      "rewards/format_reward": 1.0,
      "step": 2437,
      "temperature": 1.0
    },
    {
      "all_correct": 0.25,
      "all_wrong": 0.0,
      "completion_length": 398.625,
      "epoch": 0.0741393990998662,
      "grad_norm": 1.2487994778651919,
      "kl": 0.041748046875,
      "learning_rate": 9.86498761017261e-07,
      "loss": 0.0017,
      "reward": 1.7737808227539062,
      "reward_std": 0.1029369905591011,
      "rewards/accuracy_reward": 0.633155882358551,
      "rewards/format_reward": 1.0,
      "step": 2438,
      "temperature": 1.0
    },
    {
      "all_correct": 0.625,
      "all_wrong": 0.25,
      "completion_length": 364.953125,
      "epoch": 0.07416980902566597,
      "grad_norm": 3.0184637238313567,
      "kl": 0.042724609375,
      "learning_rate": 9.864877332457447e-07,
      "loss": 0.0017,
      "reward": 1.7953405380249023,
      "reward_std": 0.013075281865894794,
      "rewards/accuracy_reward": 0.6547154188156128,
      "rewards/format_reward": 1.0,
      "step": 2439,
      "temperature": 1.0
    },
    {
      "all_correct": 0.375,
      "all_wrong": 0.5,
      "completion_length": 378.515625,
      "epoch": 0.07420021895146575,
      "grad_norm": 0.6273756324300105,
      "kl": 0.033935546875,
      "learning_rate": 9.864767010340303e-07,
      "loss": 0.0014,
      "reward": 1.5625,
      "reward_std": 0.06943650543689728,
      "rewards/accuracy_reward": 0.46875,
      "rewards/format_reward": 1.0,
      "step": 2440,
      "temperature": 1.0
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.25,
      "completion_length": 371.625,
      "epoch": 0.07423062887726554,
      "grad_norm": 0.7182830683150857,
      "kl": 0.043701171875,
      "learning_rate": 9.864656643822185e-07,
      "loss": 0.0017,
      "reward": 1.7364407777786255,
      "reward_std": 0.012584841810166836,
      "rewards/accuracy_reward": 0.5864406228065491,
      "rewards/format_reward": 1.0,
      "step": 2441,
      "temperature": 1.0
    },
    {
      "all_correct": 0.75,
      "all_wrong": 0.25,
      "completion_length": 354.6875,
      "epoch": 0.07426103880306532,
      "grad_norm": 0.064951927096182,
      "kl": 0.03515625,
      "learning_rate": 9.864546232904097e-07,
      "loss": 0.0014,
      "reward": 1.9000000953674316,
      "reward_std": 0.0,
      "rewards/accuracy_reward": 0.75,
      "rewards/format_reward": 1.0,
      "step": 2442,
      "temperature": 1.0
    },
    {
      "all_correct": 0.75,
      "all_wrong": 0.125,
      "completion_length": 377.109375,
      "epoch": 0.0742914487288651,
      "grad_norm": 0.289331297116656,
      "kl": 0.033447265625,
      "learning_rate": 9.86443577758705e-07,
      "loss": 0.0013,
      "reward": 1.975000023841858,
      "reward_std": 0.08017838001251221,
      "rewards/accuracy_reward": 0.8125,
      "rewards/format_reward": 1.0,
      "step": 2443,
      "temperature": 1.0
    },
    {
      "all_correct": 0.25,
      "all_wrong": 0.25,
      "completion_length": 380.3125,
      "epoch": 0.07432185865466488,
      "grad_norm": 0.8101507871600769,
      "kl": 0.03466796875,
      "learning_rate": 9.86432527787205e-07,
      "loss": 0.0014,
      "reward": 1.5771369934082031,
      "reward_std": 0.17012745141983032,
      "rewards/accuracy_reward": 0.4615119695663452,
      "rewards/format_reward": 1.0,
      "step": 2444,
      "temperature": 1.0
    },
    {
      "all_correct": 0.75,
      "all_wrong": 0.0,
      "completion_length": 362.15625,
      "epoch": 0.07435226858046466,
      "grad_norm": 1.4048447865835865,
      "kl": 0.037353515625,
      "learning_rate": 9.864214733760105e-07,
      "loss": 0.0015,
      "reward": 1.9670672416687012,
      "reward_std": 0.05414704233407974,
      "rewards/accuracy_reward": 0.792067289352417,
      "rewards/format_reward": 1.0,
      "step": 2445,
      "temperature": 1.0
    },
    {
      "all_correct": 0.375,
      "all_wrong": 0.125,
      "completion_length": 377.296875,
      "epoch": 0.07438267850626444,
      "grad_norm": 1.5141240510946599,
      "kl": 0.03662109375,
      "learning_rate": 9.864104145252228e-07,
      "loss": 0.0015,
      "reward": 1.74039626121521,
      "reward_std": 0.14393679797649384,
      "rewards/accuracy_reward": 0.6060212254524231,
      "rewards/format_reward": 1.0,
      "step": 2446,
      "temperature": 1.0
    },
    {
      "all_correct": 0.375,
      "all_wrong": 0.125,
      "completion_length": 382.96875,
      "epoch": 0.07441308843206422,
      "grad_norm": 1.1626758733908558,
      "kl": 0.0419921875,
      "learning_rate": 9.863993512349422e-07,
      "loss": 0.0017,
      "reward": 1.73267662525177,
      "reward_std": 0.18755152821540833,
      "rewards/accuracy_reward": 0.5983015298843384,
      "rewards/format_reward": 1.0,
      "step": 2447,
      "temperature": 1.0
    },
    {
      "all_correct": 0.625,
      "all_wrong": 0.375,
      "completion_length": 375.3125,
      "epoch": 0.07444349835786401,
      "grad_norm": 0.3516838495711569,
      "kl": 0.030517578125,
      "learning_rate": 9.863882835052703e-07,
      "loss": 0.0012,
      "reward": 1.7468750476837158,
      "reward_std": 0.008838837966322899,
      "rewards/accuracy_reward": 0.625,
      "rewards/format_reward": 1.0,
      "step": 2448,
      "temperature": 1.0
    },
    {
      "all_correct": 0.25,
      "all_wrong": 0.125,
      "completion_length": 372.09375,
      "epoch": 0.07447390828366379,
      "grad_norm": 1.8457732712207748,
      "kl": 0.047119140625,
      "learning_rate": 9.863772113363079e-07,
      "loss": 0.0019,
      "reward": 1.8109742403030396,
      "reward_std": 0.09137019515037537,
      "rewards/accuracy_reward": 0.657849133014679,
      "rewards/format_reward": 1.0,
      "step": 2449,
      "temperature": 1.0
    },
    {
      "all_correct": 0.625,
      "all_wrong": 0.25,
      "completion_length": 375.5,
      "epoch": 0.07450431820946357,
      "grad_norm": 0.9893721340588104,
      "kl": 0.04150390625,
      "learning_rate": 9.863661347281559e-07,
      "loss": 0.0017,
      "reward": 1.7946966886520386,
      "reward_std": 0.012107347138226032,
      "rewards/accuracy_reward": 0.6540716886520386,
      "rewards/format_reward": 1.0,
      "step": 2450,
      "temperature": 1.0
    },
    {
      "all_correct": 0.375,
      "all_wrong": 0.125,
      "completion_length": 355.96875,
      "epoch": 0.07453472813526335,
      "grad_norm": 1.1707529776595416,
      "kl": 0.03271484375,
      "learning_rate": 9.863550536809155e-07,
      "loss": 0.0013,
      "reward": 1.6749060153961182,
      "reward_std": 0.15124866366386414,
      "rewards/accuracy_reward": 0.5530309081077576,
      "rewards/format_reward": 1.0,
      "step": 2451,
      "temperature": 1.0
    },
    {
      "all_correct": 0.75,
      "all_wrong": 0.125,
      "completion_length": 346.421875,
      "epoch": 0.07456513806106313,
      "grad_norm": 0.3316130915493195,
      "kl": 0.039794921875,
      "learning_rate": 9.863439681946876e-07,
      "loss": 0.0016,
      "reward": 2.012500047683716,
      "reward_std": 0.06943650543689728,
      "rewards/accuracy_reward": 0.84375,
      "rewards/format_reward": 1.0,
      "step": 2452,
      "temperature": 1.0
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.125,
      "completion_length": 359.015625,
      "epoch": 0.07459554798686291,
      "grad_norm": 1.1169364165201192,
      "kl": 0.0361328125,
      "learning_rate": 9.86332878269574e-07,
      "loss": 0.0014,
      "reward": 1.777503490447998,
      "reward_std": 0.09107542037963867,
      "rewards/accuracy_reward": 0.6275034546852112,
      "rewards/format_reward": 1.0,
      "step": 2453,
      "temperature": 1.0
    },
    {
      "all_correct": 0.375,
      "all_wrong": 0.125,
      "completion_length": 368.265625,
      "epoch": 0.07462595791266269,
      "grad_norm": 2.2794141345578227,
      "kl": 0.057861328125,
      "learning_rate": 9.863217839056753e-07,
      "loss": 0.0023,
      "reward": 1.635258674621582,
      "reward_std": 0.17192363739013672,
      "rewards/accuracy_reward": 0.5321337580680847,
      "rewards/format_reward": 1.0,
      "step": 2454,
      "temperature": 1.0
    },
    {
      "all_correct": 0.75,
      "all_wrong": 0.125,
      "completion_length": 349.484375,
      "epoch": 0.07465636783846247,
      "grad_norm": 1.0567344106151233,
      "kl": 0.05029296875,
      "learning_rate": 9.863106851030931e-07,
      "loss": 0.002,
      "reward": 1.9281251430511475,
      "reward_std": 0.11234867572784424,
      "rewards/accuracy_reward": 0.796875,
      "rewards/format_reward": 1.0,
      "step": 2455,
      "temperature": 1.0
    },
    {
      "all_correct": 0.625,
      "all_wrong": 0.25,
      "completion_length": 336.734375,
      "epoch": 0.07468677776426226,
      "grad_norm": 2.044713339948245,
      "kl": 0.043701171875,
      "learning_rate": 9.862995818619285e-07,
      "loss": 0.0017,
      "reward": 1.8125,
      "reward_std": 0.10942880809307098,
      "rewards/accuracy_reward": 0.6875,
      "rewards/format_reward": 1.0,
      "step": 2456,
      "temperature": 1.0
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.25,
      "completion_length": 348.9375,
      "epoch": 0.07471718769006204,
      "grad_norm": 1.154382217205233,
      "kl": 0.037353515625,
      "learning_rate": 9.86288474182283e-07,
      "loss": 0.0015,
      "reward": 1.718045711517334,
      "reward_std": 0.06686752289533615,
      "rewards/accuracy_reward": 0.5805457830429077,
      "rewards/format_reward": 1.0,
      "step": 2457,
      "temperature": 1.0
    },
    {
      "all_correct": 0.75,
      "all_wrong": 0.125,
      "completion_length": 359.765625,
      "epoch": 0.07474759761586182,
      "grad_norm": 0.7270482487687907,
      "kl": 0.047119140625,
      "learning_rate": 9.862773620642579e-07,
      "loss": 0.0019,
      "reward": 1.9517834186553955,
      "reward_std": 0.024797961115837097,
      "rewards/accuracy_reward": 0.7924084663391113,
      "rewards/format_reward": 1.0,
      "step": 2458,
      "temperature": 1.0
    },
    {
      "all_correct": 0.375,
      "all_wrong": 0.25,
      "completion_length": 372.609375,
      "epoch": 0.0747780075416616,
      "grad_norm": 0.5208613711512166,
      "kl": 0.0341796875,
      "learning_rate": 9.862662455079547e-07,
      "loss": 0.0014,
      "reward": 1.615625023841858,
      "reward_std": 0.21106873452663422,
      "rewards/accuracy_reward": 0.515625,
      "rewards/format_reward": 1.0,
      "step": 2459,
      "temperature": 1.0
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.125,
      "completion_length": 375.34375,
      "epoch": 0.07480841746746138,
      "grad_norm": 1.0840508866033822,
      "kl": 0.054443359375,
      "learning_rate": 9.862551245134748e-07,
      "loss": 0.0022,
      "reward": 1.8168368339538574,
      "reward_std": 0.13141664862632751,
      "rewards/accuracy_reward": 0.6699618697166443,
      "rewards/format_reward": 1.0,
      "step": 2460,
      "temperature": 1.0
    },
    {
      "all_correct": 0.375,
      "all_wrong": 0.25,
      "completion_length": 372.359375,
      "epoch": 0.07483882739326116,
      "grad_norm": 1.7590025770012876,
      "kl": 0.040283203125,
      "learning_rate": 9.862439990809194e-07,
      "loss": 0.0016,
      "reward": 1.701322078704834,
      "reward_std": 0.14187799394130707,
      "rewards/accuracy_reward": 0.5700720548629761,
      "rewards/format_reward": 1.0,
      "step": 2461,
      "temperature": 1.0
    },
    {
      "all_correct": 0.375,
      "all_wrong": 0.25,
      "completion_length": 387.109375,
      "epoch": 0.07486923731906094,
      "grad_norm": 0.7714404109126028,
      "kl": 0.031982421875,
      "learning_rate": 9.862328692103906e-07,
      "loss": 0.0013,
      "reward": 1.7373809814453125,
      "reward_std": 0.10618994385004044,
      "rewards/accuracy_reward": 0.6030058860778809,
      "rewards/format_reward": 1.0,
      "step": 2462,
      "temperature": 1.0
    },
    {
      "all_correct": 0.75,
      "all_wrong": 0.125,
      "completion_length": 359.921875,
      "epoch": 0.07489964724486073,
      "grad_norm": 0.4179774930762378,
      "kl": 0.04052734375,
      "learning_rate": 9.862217349019898e-07,
      "loss": 0.0016,
      "reward": 1.9695611000061035,
      "reward_std": 0.007892224006354809,
      "rewards/accuracy_reward": 0.7945610284805298,
      "rewards/format_reward": 1.0,
      "step": 2463,
      "temperature": 1.0
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.125,
      "completion_length": 360.765625,
      "epoch": 0.07493005717066051,
      "grad_norm": 0.8514652690839146,
      "kl": 0.04443359375,
      "learning_rate": 9.862105961558181e-07,
      "loss": 0.0018,
      "reward": 1.8496713638305664,
      "reward_std": 0.08928145468235016,
      "rewards/accuracy_reward": 0.6871712803840637,
      "rewards/format_reward": 1.0,
      "step": 2464,
      "temperature": 1.0
    },
    {
      "all_correct": 0.625,
      "all_wrong": 0.0,
      "completion_length": 360.171875,
      "epoch": 0.07496046709646029,
      "grad_norm": 1.8925500168398144,
      "kl": 0.049560546875,
      "learning_rate": 9.861994529719782e-07,
      "loss": 0.002,
      "reward": 1.9960846900939941,
      "reward_std": 0.08680392801761627,
      "rewards/accuracy_reward": 0.80545973777771,
      "rewards/format_reward": 1.0,
      "step": 2465,
      "temperature": 1.0
    },
    {
      "all_correct": 0.375,
      "all_wrong": 0.25,
      "completion_length": 367.109375,
      "epoch": 0.07499087702226007,
      "grad_norm": 2.2419958708900634,
      "kl": 0.044677734375,
      "learning_rate": 9.861883053505709e-07,
      "loss": 0.0018,
      "reward": 1.7002004384994507,
      "reward_std": 0.09157991409301758,
      "rewards/accuracy_reward": 0.5689502954483032,
      "rewards/format_reward": 1.0,
      "step": 2466,
      "temperature": 1.0
    },
    {
      "all_correct": 0.625,
      "all_wrong": 0.0,
      "completion_length": 355.40625,
      "epoch": 0.07502128694805985,
      "grad_norm": 1.5234000671636032,
      "kl": 0.05419921875,
      "learning_rate": 9.861771532916982e-07,
      "loss": 0.0022,
      "reward": 2.0240349769592285,
      "reward_std": 0.15204796195030212,
      "rewards/accuracy_reward": 0.8490350246429443,
      "rewards/format_reward": 1.0,
      "step": 2467,
      "temperature": 1.0
    },
    {
      "all_correct": 0.625,
      "all_wrong": 0.125,
      "completion_length": 364.140625,
      "epoch": 0.07505169687385962,
      "grad_norm": 1.3566997573333124,
      "kl": 0.0537109375,
      "learning_rate": 9.86165996795462e-07,
      "loss": 0.0022,
      "reward": 1.8291666507720947,
      "reward_std": 0.08725392818450928,
      "rewards/accuracy_reward": 0.6760416626930237,
      "rewards/format_reward": 1.0,
      "step": 2468,
      "temperature": 1.0
    },
    {
      "all_correct": 0.75,
      "all_wrong": 0.0,
      "completion_length": 360.84375,
      "epoch": 0.0750821067996594,
      "grad_norm": 1.6983741691325775,
      "kl": 0.04736328125,
      "learning_rate": 9.861548358619642e-07,
      "loss": 0.0019,
      "reward": 2.0466551780700684,
      "reward_std": 0.026137743145227432,
      "rewards/accuracy_reward": 0.846655011177063,
      "rewards/format_reward": 1.0,
      "step": 2469,
      "temperature": 1.0
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.0,
      "completion_length": 369.9375,
      "epoch": 0.07511251672545918,
      "grad_norm": 1.489412317472571,
      "kl": 0.0478515625,
      "learning_rate": 9.861436704913064e-07,
      "loss": 0.0019,
      "reward": 1.935652494430542,
      "reward_std": 0.1458202600479126,
      "rewards/accuracy_reward": 0.7512774467468262,
      "rewards/format_reward": 1.0,
      "step": 2470,
      "temperature": 1.0
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.0,
      "completion_length": 351.859375,
      "epoch": 0.07514292665125898,
      "grad_norm": 5.077931611877617,
      "kl": 0.05712890625,
      "learning_rate": 9.861325006835907e-07,
      "loss": 0.0023,
      "reward": 1.911177635192871,
      "reward_std": 0.154936283826828,
      "rewards/accuracy_reward": 0.7393025159835815,
      "rewards/format_reward": 0.984375,
      "step": 2471,
      "temperature": 1.0
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.25,
      "completion_length": 378.515625,
      "epoch": 0.07517333657705876,
      "grad_norm": 0.7860913426598098,
      "kl": 0.045654296875,
      "learning_rate": 9.86121326438919e-07,
      "loss": 0.0018,
      "reward": 1.776305079460144,
      "reward_std": 0.07419613003730774,
      "rewards/accuracy_reward": 0.641930103302002,
      "rewards/format_reward": 1.0,
      "step": 2472,
      "temperature": 1.0
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.125,
      "completion_length": 376.953125,
      "epoch": 0.07520374650285853,
      "grad_norm": 8.485478521573564,
      "kl": 0.041748046875,
      "learning_rate": 9.861101477573932e-07,
      "loss": 0.0017,
      "reward": 1.8207122087478638,
      "reward_std": 0.13071081042289734,
      "rewards/accuracy_reward": 0.680087149143219,
      "rewards/format_reward": 1.0,
      "step": 2473,
      "temperature": 1.0
    },
    {
      "all_correct": 0.625,
      "all_wrong": 0.375,
      "completion_length": 352.03125,
      "epoch": 0.07523415642865831,
      "grad_norm": 0.07271371098965215,
      "kl": 0.046875,
      "learning_rate": 9.860989646391154e-07,
      "loss": 0.0019,
      "reward": 1.75,
      "reward_std": 0.0,
      "rewards/accuracy_reward": 0.625,
      "rewards/format_reward": 1.0,
      "step": 2474,
      "temperature": 1.0
    },
    {
      "all_correct": 0.75,
      "all_wrong": 0.125,
      "completion_length": 365.1875,
      "epoch": 0.07526456635445809,
      "grad_norm": 0.5426966961277859,
      "kl": 0.04833984375,
      "learning_rate": 9.860877770841877e-07,
      "loss": 0.0019,
      "reward": 1.9754856824874878,
      "reward_std": 0.0027033109217882156,
      "rewards/accuracy_reward": 0.8004856109619141,
      "rewards/format_reward": 1.0,
      "step": 2475,
      "temperature": 1.0
    },
    {
      "all_correct": 0.875,
      "all_wrong": 0.125,
      "completion_length": 344.0,
      "epoch": 0.07529497628025787,
      "grad_norm": 0.05713668037224509,
      "kl": 0.038330078125,
      "learning_rate": 9.860765850927123e-07,
      "loss": 0.0015,
      "reward": 2.0500001907348633,
      "reward_std": 0.0,
      "rewards/accuracy_reward": 0.875,
      "rewards/format_reward": 1.0,
      "step": 2476,
      "temperature": 1.0
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.125,
      "completion_length": 359.046875,
      "epoch": 0.07532538620605765,
      "grad_norm": 1.1855176625270283,
      "kl": 0.0625,
      "learning_rate": 9.86065388664791e-07,
      "loss": 0.0025,
      "reward": 1.717117428779602,
      "reward_std": 0.07998567819595337,
      "rewards/accuracy_reward": 0.5858674049377441,
      "rewards/format_reward": 1.0,
      "step": 2477,
      "temperature": 1.0
    },
    {
      "all_correct": 0.625,
      "all_wrong": 0.25,
      "completion_length": 358.015625,
      "epoch": 0.07535579613185744,
      "grad_norm": 0.6243011914501678,
      "kl": 0.035400390625,
      "learning_rate": 9.860541878005265e-07,
      "loss": 0.0014,
      "reward": 1.7988369464874268,
      "reward_std": 0.005458469968289137,
      "rewards/accuracy_reward": 0.6488368511199951,
      "rewards/format_reward": 1.0,
      "step": 2478,
      "temperature": 1.0
    },
    {
      "all_correct": 0.875,
      "all_wrong": 0.0,
      "completion_length": 372.171875,
      "epoch": 0.07538620605765722,
      "grad_norm": 0.5188317705038367,
      "kl": 0.034423828125,
      "learning_rate": 9.860429825000205e-07,
      "loss": 0.0014,
      "reward": 2.106250047683716,
      "reward_std": 0.077632375061512,
      "rewards/accuracy_reward": 0.921875,
      "rewards/format_reward": 1.0,
      "step": 2479,
      "temperature": 1.0
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.0,
      "completion_length": 377.078125,
      "epoch": 0.075416615983457,
      "grad_norm": 1.4250837798306268,
      "kl": 0.045654296875,
      "learning_rate": 9.860317727633755e-07,
      "loss": 0.0018,
      "reward": 1.8872348070144653,
      "reward_std": 0.1437542587518692,
      "rewards/accuracy_reward": 0.7372347712516785,
      "rewards/format_reward": 1.0,
      "step": 2480,
      "temperature": 1.0
    },
    {
      "all_correct": 0.25,
      "all_wrong": 0.25,
      "completion_length": 386.703125,
      "epoch": 0.07544702590925678,
      "grad_norm": 0.9946974212222288,
      "kl": 0.0390625,
      "learning_rate": 9.86020558590694e-07,
      "loss": 0.0016,
      "reward": 1.620572566986084,
      "reward_std": 0.16380320489406586,
      "rewards/accuracy_reward": 0.5018225908279419,
      "rewards/format_reward": 1.0,
      "step": 2481,
      "temperature": 1.0
    },
    {
      "all_correct": 0.625,
      "all_wrong": 0.125,
      "completion_length": 370.84375,
      "epoch": 0.07547743583505656,
      "grad_norm": 0.953768195585671,
      "kl": 0.040283203125,
      "learning_rate": 9.860093399820782e-07,
      "loss": 0.0016,
      "reward": 1.8818761110305786,
      "reward_std": 0.025369292125105858,
      "rewards/accuracy_reward": 0.713126003742218,
      "rewards/format_reward": 1.0,
      "step": 2482,
      "temperature": 1.0
    },
    {
      "all_correct": 0.625,
      "all_wrong": 0.0,
      "completion_length": 355.5,
      "epoch": 0.07550784576085634,
      "grad_norm": 1.0774331163796875,
      "kl": 0.04052734375,
      "learning_rate": 9.859981169376306e-07,
      "loss": 0.0016,
      "reward": 2.023257255554199,
      "reward_std": 0.15300512313842773,
      "rewards/accuracy_reward": 0.8357572555541992,
      "rewards/format_reward": 1.0,
      "step": 2483,
      "temperature": 1.0
    },
    {
      "all_correct": 0.75,
      "all_wrong": 0.0,
      "completion_length": 359.609375,
      "epoch": 0.07553825568665612,
      "grad_norm": 0.5521875415032471,
      "kl": 0.041259765625,
      "learning_rate": 9.859868894574532e-07,
      "loss": 0.0016,
      "reward": 1.975000023841858,
      "reward_std": 0.13887301087379456,
      "rewards/accuracy_reward": 0.8125,
      "rewards/format_reward": 1.0,
      "step": 2484,
      "temperature": 1.0
    },
    {
      "all_correct": 0.75,
      "all_wrong": 0.0,
      "completion_length": 353.015625,
      "epoch": 0.07556866561245591,
      "grad_norm": 1.070579889736262,
      "kl": 0.049072265625,
      "learning_rate": 9.85975657541649e-07,
      "loss": 0.002,
      "reward": 2.1401352882385254,
      "reward_std": 0.09388431906700134,
      "rewards/accuracy_reward": 0.9526352882385254,
      "rewards/format_reward": 1.0,
      "step": 2485,
      "temperature": 1.0
    },
    {
      "all_correct": 0.375,
      "all_wrong": 0.0,
      "completion_length": 372.015625,
      "epoch": 0.07559907553825569,
      "grad_norm": 1.1370533121142035,
      "kl": 0.051025390625,
      "learning_rate": 9.859644211903202e-07,
      "loss": 0.002,
      "reward": 1.786617636680603,
      "reward_std": 0.15352703630924225,
      "rewards/accuracy_reward": 0.6147426962852478,
      "rewards/format_reward": 1.0,
      "step": 2486,
      "temperature": 1.0
    },
    {
      "all_correct": 0.625,
      "all_wrong": 0.125,
      "completion_length": 354.890625,
      "epoch": 0.07562948546405547,
      "grad_norm": 1.1693893115212104,
      "kl": 0.051513671875,
      "learning_rate": 9.859531804035696e-07,
      "loss": 0.0021,
      "reward": 1.9025732278823853,
      "reward_std": 0.035607125610113144,
      "rewards/accuracy_reward": 0.7338231205940247,
      "rewards/format_reward": 1.0,
      "step": 2487,
      "temperature": 1.0
    },
    {
      "all_correct": 0.625,
      "all_wrong": 0.25,
      "completion_length": 362.65625,
      "epoch": 0.07565989538985525,
      "grad_norm": 0.5970097315123322,
      "kl": 0.04931640625,
      "learning_rate": 9.859419351814996e-07,
      "loss": 0.002,
      "reward": 1.8781249523162842,
      "reward_std": 0.06187184900045395,
      "rewards/accuracy_reward": 0.734375,
      "rewards/format_reward": 1.0,
      "step": 2488,
      "temperature": 1.0
    },
    {
      "all_correct": 0.5,
      "all_wrong": 0.5,
      "completion_length": 360.265625,
      "epoch": 0.07569030531565503,
      "grad_norm": 0.5531070588891508,
      "kl": 0.033203125,
      "learning_rate": 9.859306855242128e-07,
      "loss": 0.0013,
      "reward": 1.5968749523162842,
      "reward_std": 0.008838837966322899,
      "rewards/accuracy_reward": 0.5,
      "rewards/format_reward": 1.0,
      "step": 2489,
      "temperature": 1.0
    },
    {
      "all_correct": 0.625,
      "all_wrong": 0.0,
      "completion_length": 344.3125,
      "epoch": 0.07572071524145481,
      "grad_norm": 1.1684490824231821,
      "kl": 0.041259765625,
      "learning_rate": 9.85919431431812e-07,
      "loss": 0.0016,
      "reward": 1.991852879524231,
      "reward_std": 0.1611950695514679,
      "rewards/accuracy_reward": 0.8168528079986572,
      "rewards/format_reward": 1.0,
      "step": 2490,
      "temperature": 1.0
    },
    {
      "all_correct": 0.625,
      "all_wrong": 0.0,
      "completion_length": 347.984375,
      "epoch": 0.07575112516725459,
      "grad_norm": 1.6776006745663348,
      "kl": 0.0439453125,
      "learning_rate": 9.859081729044e-07,
      "loss": 0.0018,
      "reward": 1.9742608070373535,
      "reward_std": 0.0359986275434494,
      "rewards/accuracy_reward": 0.7773858904838562,
      "rewards/format_reward": 1.0,
      "step": 2491,
      "temperature": 1.0
    },
    {
      "all_correct": 0.875,
      "all_wrong": 0.0,
      "completion_length": 355.46875,
      "epoch": 0.07578153509305437,
      "grad_norm": 0.7869383393780497,
      "kl": 0.032958984375,
      "learning_rate": 9.858969099420792e-07,
      "loss": 0.0013,
      "reward": 2.1308512687683105,
      "reward_std": 0.016522862017154694,
      "rewards/accuracy_reward": 0.9339761137962341,
      "rewards/format_reward": 1.0,
      "step": 2492,
      "temperature": 1.0
    },
    {
      "all_correct": 0.375,
      "all_wrong": 0.125,
      "completion_length": 383.90625,
      "epoch": 0.07581194501885416,
      "grad_norm": 1.2402048641405226,
      "kl": 0.048583984375,
      "learning_rate": 9.858856425449528e-07,
      "loss": 0.0019,
      "reward": 1.7456811666488647,
      "reward_std": 0.10677331686019897,
      "rewards/accuracy_reward": 0.5863059759140015,
      "rewards/format_reward": 1.0,
      "step": 2493,
      "temperature": 1.0
    },
    {
      "all_correct": 0.625,
      "all_wrong": 0.25,
      "completion_length": 370.21875,
      "epoch": 0.07584235494465394,
      "grad_norm": 1.1866071006884658,
      "kl": 0.04443359375,
      "learning_rate": 9.858743707131235e-07,
      "loss": 0.0018,
      "reward": 1.8085421323776245,
      "reward_std": 0.0016743600135669112,
      "rewards/accuracy_reward": 0.6585420966148376,
      "rewards/format_reward": 1.0,
      "step": 2494,
      "temperature": 1.0
    },
    {
      "all_correct": 0.625,
      "all_wrong": 0.0,
      "completion_length": 400.640625,
      "epoch": 0.07587276487045372,
      "grad_norm": 1.9023615267742355,
      "kl": 0.034423828125,
      "learning_rate": 9.858630944466942e-07,
      "loss": 0.0014,
      "reward": 1.9092881679534912,
      "reward_std": 0.1398414969444275,
      "rewards/accuracy_reward": 0.7561631202697754,
      "rewards/format_reward": 1.0,
      "step": 2495,
      "temperature": 1.0
    },
    {
      "all_correct": 0.625,
      "all_wrong": 0.25,
      "completion_length": 346.015625,
      "epoch": 0.0759031747962535,
      "grad_norm": 0.7567730238111163,
      "kl": 0.035400390625,
      "learning_rate": 9.858518137457676e-07,
      "loss": 0.0014,
      "reward": 1.859375,
      "reward_std": 0.07827534526586533,
      "rewards/accuracy_reward": 0.71875,
      "rewards/format_reward": 1.0,
      "step": 2496,
      "temperature": 1.0
    },
    {
      "all_correct": 0.875,
      "all_wrong": 0.0,
      "completion_length": 370.28125,
      "epoch": 0.07593358472205328,
      "grad_norm": 3.4977687100284096,
      "kl": 0.04052734375,
      "learning_rate": 9.85840528610447e-07,
      "loss": 0.0016,
      "reward": 2.1546006202697754,
      "reward_std": 0.08007238060235977,
      "rewards/accuracy_reward": 0.963975727558136,
      "rewards/format_reward": 1.0,
      "step": 2497,
      "temperature": 1.0
    },
    {
      "all_correct": 0.375,
      "all_wrong": 0.25,
      "completion_length": 367.046875,
      "epoch": 0.07596399464785306,
      "grad_norm": 1.1870415818959628,
      "kl": 0.05224609375,
      "learning_rate": 9.85829239040835e-07,
      "loss": 0.0021,
      "reward": 1.6631851196289062,
      "reward_std": 0.028778309002518654,
      "rewards/accuracy_reward": 0.5194350481033325,
      "rewards/format_reward": 1.0,
      "step": 2498,
      "temperature": 1.0
    },
    {
      "all_correct": 0.25,
      "all_wrong": 0.375,
      "completion_length": 380.140625,
      "epoch": 0.07599440457365284,
      "grad_norm": 4.9208788569425765,
      "kl": 0.041015625,
      "learning_rate": 9.858179450370352e-07,
      "loss": 0.0016,
      "reward": 1.4496848583221436,
      "reward_std": 0.12111330777406693,
      "rewards/accuracy_reward": 0.36530983448028564,
      "rewards/format_reward": 0.984375,
      "step": 2499,
      "temperature": 1.0
    },
    {
      "all_correct": 0.875,
      "all_wrong": 0.125,
      "completion_length": 372.3125,
      "epoch": 0.07602481449945263,
      "grad_norm": 0.09674058622159516,
      "kl": 0.03857421875,
      "learning_rate": 9.858066465991502e-07,
      "loss": 0.0015,
      "reward": 2.0500001907348633,
      "reward_std": 0.0,
      "rewards/accuracy_reward": 0.875,
      "rewards/format_reward": 1.0,
      "step": 2500,
      "temperature": 1.0
    }
  ],
  "logging_steps": 1.0,
  "max_steps": 32884,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 500,
  "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
}