{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.05333333333333334,
  "eval_steps": 500,
  "global_step": 150,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "completion_length": 961.2890625,
      "epoch": 0.0007111111111111111,
      "grad_norm": 0.07362582076051967,
      "kl": 0.0,
      "learning_rate": 2e-07,
      "loss": -0.0,
      "reward": 0.09375000186264515,
      "reward_std": 0.15193375945091248,
      "rewards/format_compliance_reward": 0.0,
      "rewards/math_reasoning_reward": 0.0,
      "rewards/solution_quality_reward": 0.09375000186264515,
      "step": 2
    },
    {
      "completion_length": 939.3046875,
      "epoch": 0.0014222222222222223,
      "grad_norm": 0.0907152492976058,
      "kl": 0.0003669261932373047,
      "learning_rate": 4e-07,
      "loss": 0.0,
      "reward": 0.0875000013038516,
      "reward_std": 0.14330127369612455,
      "rewards/format_compliance_reward": 0.0,
      "rewards/math_reasoning_reward": 0.0,
      "rewards/solution_quality_reward": 0.0875000013038516,
      "step": 4
    },
    {
      "completion_length": 966.875,
      "epoch": 0.0021333333333333334,
      "grad_norm": 0.07758448496582468,
      "kl": 0.00034809112548828125,
      "learning_rate": 4.99941324504621e-07,
      "loss": 0.0,
      "reward": 0.08750000176951289,
      "reward_std": 0.12500000186264515,
      "rewards/format_compliance_reward": 0.0,
      "rewards/math_reasoning_reward": 0.0,
      "rewards/solution_quality_reward": 0.08750000176951289,
      "step": 6
    },
    {
      "completion_length": 974.5625,
      "epoch": 0.0028444444444444446,
      "grad_norm": 0.04999161599871498,
      "kl": 0.00039124488830566406,
      "learning_rate": 4.99472085783721e-07,
      "loss": 0.0,
      "reward": 0.031250000931322575,
      "reward_std": 0.037500000558793545,
      "rewards/format_compliance_reward": 0.0,
      "rewards/math_reasoning_reward": 0.0,
      "rewards/solution_quality_reward": 0.031250000931322575,
      "step": 8
    },
    {
      "completion_length": 988.71875,
      "epoch": 0.0035555555555555557,
      "grad_norm": 0.05986623117422814,
      "kl": 0.00038301944732666016,
      "learning_rate": 4.985344892885899e-07,
      "loss": 0.0,
      "reward": 0.06250000093132257,
      "reward_std": 0.0933012729510665,
      "rewards/format_compliance_reward": 0.0,
      "rewards/math_reasoning_reward": 0.0,
      "rewards/solution_quality_reward": 0.06250000093132257,
      "step": 10
    },
    {
      "completion_length": 951.15625,
      "epoch": 0.004266666666666667,
      "grad_norm": 0.0799364307268448,
      "kl": 0.00038933753967285156,
      "learning_rate": 4.971302952586796e-07,
      "loss": 0.0,
      "reward": 0.07500000158324838,
      "reward_std": 0.12886751629412174,
      "rewards/format_compliance_reward": 0.0,
      "rewards/math_reasoning_reward": 0.0,
      "rewards/solution_quality_reward": 0.07500000158324838,
      "step": 12
    },
    {
      "completion_length": 960.3046875,
      "epoch": 0.004977777777777778,
      "grad_norm": 0.03830275509956425,
      "kl": 0.0003789663314819336,
      "learning_rate": 4.952621399215597e-07,
      "loss": 0.0,
      "reward": 0.05000000074505806,
      "reward_std": 0.0894337585195899,
      "rewards/format_compliance_reward": 0.0,
      "rewards/math_reasoning_reward": 0.0,
      "rewards/solution_quality_reward": 0.05000000074505806,
      "step": 14
    },
    {
      "completion_length": 943.65625,
      "epoch": 0.005688888888888889,
      "grad_norm": 0.09243726858362067,
      "kl": 0.00037360191345214844,
      "learning_rate": 4.929335305436764e-07,
      "loss": 0.0,
      "reward": 0.12500000279396772,
      "reward_std": 0.15773503109812737,
      "rewards/format_compliance_reward": 0.0,
      "rewards/math_reasoning_reward": 0.0,
      "rewards/solution_quality_reward": 0.12500000279396772,
      "step": 16
    },
    {
      "completion_length": 991.3359375,
      "epoch": 0.0064,
      "grad_norm": 0.02502555687332951,
      "kl": 0.0003898143768310547,
      "learning_rate": 4.901488388458247e-07,
      "loss": 0.0,
      "reward": 0.0437500006519258,
      "reward_std": 0.06636751536279917,
      "rewards/format_compliance_reward": 0.0,
      "rewards/math_reasoning_reward": 0.0,
      "rewards/solution_quality_reward": 0.0437500006519258,
      "step": 18
    },
    {
      "completion_length": 946.1328125,
      "epoch": 0.0071111111111111115,
      "grad_norm": 0.09101166665795608,
      "kl": 0.0004526376724243164,
      "learning_rate": 4.869132927957006e-07,
      "loss": 0.0,
      "reward": 0.1171875037252903,
      "reward_std": 0.1776762753725052,
      "rewards/format_compliance_reward": 0.0,
      "rewards/math_reasoning_reward": 0.0,
      "rewards/solution_quality_reward": 0.1171875037252903,
      "step": 20
    },
    {
      "completion_length": 935.46875,
      "epoch": 0.007822222222222222,
      "grad_norm": 0.07270975069713734,
      "kl": 0.0004680156707763672,
      "learning_rate": 4.832329667929376e-07,
      "loss": 0.0,
      "reward": 0.08750000223517418,
      "reward_std": 0.11443375889211893,
      "rewards/format_compliance_reward": 0.0,
      "rewards/math_reasoning_reward": 0.0,
      "rewards/solution_quality_reward": 0.08750000223517418,
      "step": 22
    },
    {
      "completion_length": 949.0859375,
      "epoch": 0.008533333333333334,
      "grad_norm": 0.08038949844442059,
      "kl": 0.0006613731384277344,
      "learning_rate": 4.791147702650565e-07,
      "loss": 0.0,
      "reward": 0.11250000260770321,
      "reward_std": 0.12886751629412174,
      "rewards/format_compliance_reward": 0.0,
      "rewards/math_reasoning_reward": 0.0,
      "rewards/solution_quality_reward": 0.11250000260770321,
      "step": 24
    },
    {
      "completion_length": 956.25,
      "epoch": 0.009244444444444444,
      "grad_norm": 0.08202117227401906,
      "kl": 0.0005040168762207031,
      "learning_rate": 4.745664346957361e-07,
      "loss": 0.0,
      "reward": 0.09375000186264515,
      "reward_std": 0.13466878794133663,
      "rewards/format_compliance_reward": 0.0,
      "rewards/math_reasoning_reward": 0.0,
      "rewards/solution_quality_reward": 0.09375000186264515,
      "step": 26
    },
    {
      "completion_length": 975.703125,
      "epoch": 0.009955555555555556,
      "grad_norm": 0.052563124629516914,
      "kl": 0.0009806156158447266,
      "learning_rate": 4.695964991097616e-07,
      "loss": 0.0,
      "reward": 0.056250001303851604,
      "reward_std": 0.07693375833332539,
      "rewards/format_compliance_reward": 0.0,
      "rewards/math_reasoning_reward": 0.0,
      "rewards/solution_quality_reward": 0.056250001303851604,
      "step": 28
    },
    {
      "completion_length": 950.8515625,
      "epoch": 0.010666666666666666,
      "grad_norm": 0.07832441677596065,
      "kl": 0.0008480548858642578,
      "learning_rate": 4.642142940418973e-07,
      "loss": 0.0,
      "reward": 0.15000000316649675,
      "reward_std": 0.20773503184318542,
      "rewards/format_compliance_reward": 0.0,
      "rewards/math_reasoning_reward": 0.0,
      "rewards/solution_quality_reward": 0.15000000316649675,
      "step": 30
    },
    {
      "completion_length": 974.40625,
      "epoch": 0.011377777777777778,
      "grad_norm": 0.07055076490510688,
      "kl": 0.0010929107666015625,
      "learning_rate": 4.5842992401978256e-07,
      "loss": 0.0,
      "reward": 0.11250000167638063,
      "reward_std": 0.15773503109812737,
      "rewards/format_compliance_reward": 0.0,
      "rewards/math_reasoning_reward": 0.0,
      "rewards/solution_quality_reward": 0.11250000167638063,
      "step": 32
    },
    {
      "completion_length": 931.6015625,
      "epoch": 0.012088888888888889,
      "grad_norm": 0.11840439438100717,
      "kl": 0.0014081001281738281,
      "learning_rate": 4.5225424859373684e-07,
      "loss": 0.0001,
      "reward": 0.17812500521540642,
      "reward_std": 0.22999473847448826,
      "rewards/format_compliance_reward": 0.0,
      "rewards/math_reasoning_reward": 0.0,
      "rewards/solution_quality_reward": 0.17812500521540642,
      "step": 34
    },
    {
      "completion_length": 913.5078125,
      "epoch": 0.0128,
      "grad_norm": 0.09388094812115422,
      "kl": 0.0025322437286376953,
      "learning_rate": 4.456988619490889e-07,
      "loss": 0.0001,
      "reward": 0.218750003259629,
      "reward_std": 0.19240381754934788,
      "rewards/format_compliance_reward": 0.0,
      "rewards/math_reasoning_reward": 0.0,
      "rewards/solution_quality_reward": 0.218750003259629,
      "step": 36
    },
    {
      "completion_length": 942.7890625,
      "epoch": 0.013511111111111111,
      "grad_norm": 0.1071443097365241,
      "kl": 0.0012729167938232422,
      "learning_rate": 4.3877607113930516e-07,
      "loss": 0.0001,
      "reward": 0.1937500024214387,
      "reward_std": 0.24523503240197897,
      "rewards/format_compliance_reward": 0.0,
      "rewards/math_reasoning_reward": 0.0,
      "rewards/solution_quality_reward": 0.1937500024214387,
      "step": 38
    },
    {
      "completion_length": 932.3125,
      "epoch": 0.014222222222222223,
      "grad_norm": 0.09884048766059533,
      "kl": 0.0025246143341064453,
      "learning_rate": 4.314988729807827e-07,
      "loss": 0.0001,
      "reward": 0.2312500043772161,
      "reward_std": 0.20966878905892372,
      "rewards/format_compliance_reward": 0.0,
      "rewards/math_reasoning_reward": 0.0,
      "rewards/solution_quality_reward": 0.2312500043772161,
      "step": 40
    },
    {
      "completion_length": 983.9375,
      "epoch": 0.014933333333333333,
      "grad_norm": 0.06377692673539463,
      "kl": 0.0017533302307128906,
      "learning_rate": 4.238809296526846e-07,
      "loss": 0.0001,
      "reward": 0.15000000223517418,
      "reward_std": 0.1933012744411826,
      "rewards/format_compliance_reward": 0.0,
      "rewards/math_reasoning_reward": 0.0,
      "rewards/solution_quality_reward": 0.15000000223517418,
      "step": 42
    },
    {
      "completion_length": 934.265625,
      "epoch": 0.015644444444444443,
      "grad_norm": 0.10797227603988564,
      "kl": 0.0016703605651855469,
      "learning_rate": 4.159365430476261e-07,
      "loss": 0.0001,
      "reward": 0.26250000577419996,
      "reward_std": 0.21830127481371164,
      "rewards/format_compliance_reward": 0.0,
      "rewards/math_reasoning_reward": 0.0,
      "rewards/solution_quality_reward": 0.26250000204890966,
      "step": 44
    },
    {
      "completion_length": 888.1484375,
      "epoch": 0.016355555555555557,
      "grad_norm": 0.11888486637171698,
      "kl": 0.0021381378173828125,
      "learning_rate": 4.076806279213655e-07,
      "loss": 0.0001,
      "reward": 0.3250000048428774,
      "reward_std": 0.2577350325882435,
      "rewards/format_compliance_reward": 0.0,
      "rewards/math_reasoning_reward": 0.0,
      "rewards/solution_quality_reward": 0.3250000048428774,
      "step": 46
    },
    {
      "completion_length": 844.6484375,
      "epoch": 0.017066666666666667,
      "grad_norm": 0.10144889612555925,
      "kl": 0.002949237823486328,
      "learning_rate": 3.991286838919086e-07,
      "loss": 0.0001,
      "reward": 0.3921875115483999,
      "reward_std": 0.2589998487383127,
      "rewards/format_compliance_reward": 0.0,
      "rewards/math_reasoning_reward": 0.0,
      "rewards/solution_quality_reward": 0.3921875115483999,
      "step": 48
    },
    {
      "completion_length": 862.4296875,
      "epoch": 0.017777777777777778,
      "grad_norm": 0.09453500886940876,
      "kl": 0.0031652450561523438,
      "learning_rate": 3.902967663405956e-07,
      "loss": 0.0001,
      "reward": 0.36250000912696123,
      "reward_std": 0.24047006107866764,
      "rewards/format_compliance_reward": 0.0,
      "rewards/math_reasoning_reward": 0.0,
      "rewards/solution_quality_reward": 0.36250000912696123,
      "step": 50
    },
    {
      "completion_length": 905.5,
      "epoch": 0.018488888888888888,
      "grad_norm": 0.10133881191260517,
      "kl": 0.0029811859130859375,
      "learning_rate": 3.8120145626980015e-07,
      "loss": 0.0001,
      "reward": 0.32031250838190317,
      "reward_std": 0.22642100881785154,
      "rewards/format_compliance_reward": 0.0,
      "rewards/math_reasoning_reward": 0.0,
      "rewards/solution_quality_reward": 0.3203125046566129,
      "step": 52
    },
    {
      "completion_length": 920.1953125,
      "epoch": 0.0192,
      "grad_norm": 0.10154509040958454,
      "kl": 0.0032434463500976562,
      "learning_rate": 3.718598291738298e-07,
      "loss": 0.0001,
      "reward": 0.30781250540167093,
      "reward_std": 0.2779353503137827,
      "rewards/format_compliance_reward": 0.0,
      "rewards/math_reasoning_reward": 0.0,
      "rewards/solution_quality_reward": 0.30781250540167093,
      "step": 54
    },
    {
      "completion_length": 893.3515625,
      "epoch": 0.019911111111111112,
      "grad_norm": 0.10046839615716938,
      "kl": 0.0037431716918945312,
      "learning_rate": 3.622894229814698e-07,
      "loss": 0.0001,
      "reward": 0.3812500098720193,
      "reward_std": 0.2846687901765108,
      "rewards/format_compliance_reward": 0.0,
      "rewards/math_reasoning_reward": 0.0,
      "rewards/solution_quality_reward": 0.3812500098720193,
      "step": 56
    },
    {
      "completion_length": 905.0546875,
      "epoch": 0.020622222222222222,
      "grad_norm": 0.0961680067295368,
      "kl": 0.004122734069824219,
      "learning_rate": 3.52508205130354e-07,
      "loss": 0.0002,
      "reward": 0.3875000085681677,
      "reward_std": 0.2616025470197201,
      "rewards/format_compliance_reward": 0.0,
      "rewards/math_reasoning_reward": 0.0,
      "rewards/solution_quality_reward": 0.3875000048428774,
      "step": 58
    },
    {
      "completion_length": 871.7890625,
      "epoch": 0.021333333333333333,
      "grad_norm": 0.08426575372485079,
      "kl": 0.0044574737548828125,
      "learning_rate": 3.4253453883497864e-07,
      "loss": 0.0002,
      "reward": 0.4125000177882612,
      "reward_std": 0.25103630404919386,
      "rewards/format_compliance_reward": 0.0,
      "rewards/math_reasoning_reward": 0.0,
      "rewards/solution_quality_reward": 0.4125000028871,
      "step": 60
    },
    {
      "completion_length": 901.296875,
      "epoch": 0.022044444444444443,
      "grad_norm": 0.09601873424860208,
      "kl": 0.004614830017089844,
      "learning_rate": 3.323871486116851e-07,
      "loss": 0.0002,
      "reward": 0.3750000107102096,
      "reward_std": 0.2943375762552023,
      "rewards/format_compliance_reward": 0.0,
      "rewards/math_reasoning_reward": 0.0,
      "rewards/solution_quality_reward": 0.3750000107102096,
      "step": 62
    },
    {
      "completion_length": 876.109375,
      "epoch": 0.022755555555555557,
      "grad_norm": 0.07468416170263495,
      "kl": 0.004523277282714844,
      "learning_rate": 3.220850851253377e-07,
      "loss": 0.0002,
      "reward": 0.37187500670552254,
      "reward_std": 0.20931097934953868,
      "rewards/format_compliance_reward": 0.0,
      "rewards/math_reasoning_reward": 0.0,
      "rewards/solution_quality_reward": 0.37187500670552254,
      "step": 64
    },
    {
      "completion_length": 876.34375,
      "epoch": 0.023466666666666667,
      "grad_norm": 0.10975736428011727,
      "kl": 0.005245208740234375,
      "learning_rate": 3.1164768942369053e-07,
      "loss": 0.0002,
      "reward": 0.42343751108273864,
      "reward_std": 0.2873450629413128,
      "rewards/format_compliance_reward": 0.0,
      "rewards/math_reasoning_reward": 0.0,
      "rewards/solution_quality_reward": 0.42343750735744834,
      "step": 66
    },
    {
      "completion_length": 846.3671875,
      "epoch": 0.024177777777777777,
      "grad_norm": 0.10665048077601928,
      "kl": 0.0054931640625,
      "learning_rate": 3.010945566265912e-07,
      "loss": 0.0002,
      "reward": 0.4234375124797225,
      "reward_std": 0.2752937898039818,
      "rewards/format_compliance_reward": 0.0,
      "rewards/math_reasoning_reward": 0.0,
      "rewards/solution_quality_reward": 0.42343750689178705,
      "step": 68
    },
    {
      "completion_length": 829.9609375,
      "epoch": 0.024888888888888887,
      "grad_norm": 0.08361928294620831,
      "kl": 0.005539894104003906,
      "learning_rate": 2.9044549913819124e-07,
      "loss": 0.0002,
      "reward": 0.48750001983717084,
      "reward_std": 0.2154700607061386,
      "rewards/format_compliance_reward": 0.0,
      "rewards/math_reasoning_reward": 0.0,
      "rewards/solution_quality_reward": 0.48750000493600965,
      "step": 70
    },
    {
      "completion_length": 858.71875,
      "epoch": 0.0256,
      "grad_norm": 0.07638495432759437,
      "kl": 0.005488395690917969,
      "learning_rate": 2.797205094512266e-07,
      "loss": 0.0002,
      "reward": 0.45000001741573215,
      "reward_std": 0.21160254627466202,
      "rewards/format_compliance_reward": 0.0,
      "rewards/math_reasoning_reward": 0.0,
      "rewards/solution_quality_reward": 0.45000000623986125,
      "step": 72
    },
    {
      "completion_length": 864.84375,
      "epoch": 0.02631111111111111,
      "grad_norm": 0.10096698237334256,
      "kl": 0.0058040618896484375,
      "learning_rate": 2.6893972261320264e-07,
      "loss": 0.0002,
      "reward": 0.4000000124797225,
      "reward_std": 0.2827350329607725,
      "rewards/format_compliance_reward": 0.0,
      "rewards/math_reasoning_reward": 0.0,
      "rewards/solution_quality_reward": 0.4000000087544322,
      "step": 74
    },
    {
      "completion_length": 907.4296875,
      "epoch": 0.027022222222222222,
      "grad_norm": 0.08728011123913502,
      "kl": 0.005370140075683594,
      "learning_rate": 2.5812337842494516e-07,
      "loss": 0.0002,
      "reward": 0.42500000866129994,
      "reward_std": 0.24433757551014423,
      "rewards/format_compliance_reward": 0.0,
      "rewards/math_reasoning_reward": 0.0,
      "rewards/solution_quality_reward": 0.42500000493600965,
      "step": 76
    },
    {
      "completion_length": 817.8828125,
      "epoch": 0.027733333333333332,
      "grad_norm": 0.09172512669808838,
      "kl": 0.0060749053955078125,
      "learning_rate": 2.4729178344249006e-07,
      "loss": 0.0002,
      "reward": 0.487500018440187,
      "reward_std": 0.22603630367666483,
      "rewards/format_compliance_reward": 0.0,
      "rewards/math_reasoning_reward": 0.0,
      "rewards/solution_quality_reward": 0.4875000109896064,
      "step": 78
    },
    {
      "completion_length": 811.90625,
      "epoch": 0.028444444444444446,
      "grad_norm": 0.087230141698115,
      "kl": 0.0064601898193359375,
      "learning_rate": 2.3646527285364563e-07,
      "loss": 0.0003,
      "reward": 0.5500000175088644,
      "reward_std": 0.22216878924518824,
      "rewards/format_compliance_reward": 0.0,
      "rewards/math_reasoning_reward": 0.0,
      "rewards/solution_quality_reward": 0.5500000100582838,
      "step": 80
    },
    {
      "completion_length": 820.3125,
      "epoch": 0.029155555555555556,
      "grad_norm": 0.0917309701218231,
      "kl": 0.0067539215087890625,
      "learning_rate": 2.256641723008026e-07,
      "loss": 0.0003,
      "reward": 0.4890625160187483,
      "reward_std": 0.23515222850255668,
      "rewards/format_compliance_reward": 0.0,
      "rewards/math_reasoning_reward": 0.0,
      "rewards/solution_quality_reward": 0.489062512293458,
      "step": 82
    },
    {
      "completion_length": 875.1953125,
      "epoch": 0.029866666666666666,
      "grad_norm": 0.05629416236953807,
      "kl": 0.005397796630859375,
      "learning_rate": 2.1490875972166393e-07,
      "loss": 0.0002,
      "reward": 0.5187500147148967,
      "reward_std": 0.1991025460883975,
      "rewards/format_compliance_reward": 0.0,
      "rewards/math_reasoning_reward": 0.0,
      "rewards/solution_quality_reward": 0.5187500072643161,
      "step": 84
    },
    {
      "completion_length": 853.609375,
      "epoch": 0.030577777777777777,
      "grad_norm": 0.08222448453561998,
      "kl": 0.0061321258544921875,
      "learning_rate": 2.0421922727953595e-07,
      "loss": 0.0002,
      "reward": 0.49843751173466444,
      "reward_std": 0.24561973754316568,
      "rewards/format_compliance_reward": 0.0,
      "rewards/math_reasoning_reward": 0.0,
      "rewards/solution_quality_reward": 0.498437506146729,
      "step": 86
    },
    {
      "completion_length": 848.15625,
      "epoch": 0.03128888888888889,
      "grad_norm": 0.0924588566987047,
      "kl": 0.0057964324951171875,
      "learning_rate": 1.9361564345465145e-07,
      "loss": 0.0002,
      "reward": 0.49375001480802894,
      "reward_std": 0.2741025472059846,
      "rewards/format_compliance_reward": 0.0,
      "rewards/math_reasoning_reward": 0.0,
      "rewards/solution_quality_reward": 0.49375001108273864,
      "step": 88
    },
    {
      "completion_length": 850.2109375,
      "epoch": 0.032,
      "grad_norm": 0.09370433522264131,
      "kl": 0.005938529968261719,
      "learning_rate": 1.8311791536769483e-07,
      "loss": 0.0002,
      "reward": 0.4875000179745257,
      "reward_std": 0.25490381848067045,
      "rewards/format_compliance_reward": 0.0,
      "rewards/math_reasoning_reward": 0.0,
      "rewards/solution_quality_reward": 0.4875000105239451,
      "step": 90
    },
    {
      "completion_length": 823.2890625,
      "epoch": 0.032711111111111114,
      "grad_norm": 0.10865632851826816,
      "kl": 0.0072078704833984375,
      "learning_rate": 1.7274575140626315e-07,
      "loss": 0.0003,
      "reward": 0.47968751238659024,
      "reward_std": 0.2377937890123576,
      "rewards/format_compliance_reward": 0.0,
      "rewards/math_reasoning_reward": 0.0,
      "rewards/solution_quality_reward": 0.47968750866129994,
      "step": 92
    },
    {
      "completion_length": 817.4140625,
      "epoch": 0.03342222222222222,
      "grad_norm": 0.08418982535916476,
      "kl": 0.0056285858154296875,
      "learning_rate": 1.6251862422442788e-07,
      "loss": 0.0002,
      "reward": 0.5242187650874257,
      "reward_std": 0.25055886153131723,
      "rewards/format_compliance_reward": 0.0,
      "rewards/math_reasoning_reward": 0.0054687499068677425,
      "rewards/solution_quality_reward": 0.5187500091269612,
      "step": 94
    },
    {
      "completion_length": 832.8984375,
      "epoch": 0.034133333333333335,
      "grad_norm": 0.08609457505525932,
      "kl": 0.0064220428466796875,
      "learning_rate": 1.5245573418486135e-07,
      "loss": 0.0003,
      "reward": 0.498437509406358,
      "reward_std": 0.19642627402208745,
      "rewards/format_compliance_reward": 0.0,
      "rewards/math_reasoning_reward": 0.0,
      "rewards/solution_quality_reward": 0.498437509406358,
      "step": 96
    },
    {
      "completion_length": 834.265625,
      "epoch": 0.03484444444444444,
      "grad_norm": 0.11364212512648743,
      "kl": 0.0072803497314453125,
      "learning_rate": 1.4257597331216208e-07,
      "loss": 0.0003,
      "reward": 0.4625000134110451,
      "reward_std": 0.25401466409675777,
      "rewards/format_compliance_reward": 0.0,
      "rewards/math_reasoning_reward": 0.0,
      "rewards/solution_quality_reward": 0.4625000096857548,
      "step": 98
    },
    {
      "completion_length": 857.9921875,
      "epoch": 0.035555555555555556,
      "grad_norm": 0.07970778178862901,
      "kl": 0.005957603454589844,
      "learning_rate": 1.328978898250525e-07,
      "loss": 0.0002,
      "reward": 0.49140626657754183,
      "reward_std": 0.256591965444386,
      "rewards/format_compliance_reward": 0.00390625,
      "rewards/math_reasoning_reward": 0.0,
      "rewards/solution_quality_reward": 0.48750000540167093,
      "step": 100
    },
    {
      "completion_length": 850.5234375,
      "epoch": 0.03626666666666667,
      "grad_norm": 0.0806380302022146,
      "kl": 0.0061206817626953125,
      "learning_rate": 1.234396533140365e-07,
      "loss": 0.0002,
      "reward": 0.5625000167638063,
      "reward_std": 0.22216878924518824,
      "rewards/format_compliance_reward": 0.0,
      "rewards/math_reasoning_reward": 0.0,
      "rewards/solution_quality_reward": 0.5625000093132257,
      "step": 102
    },
    {
      "completion_length": 873.421875,
      "epoch": 0.036977777777777776,
      "grad_norm": 0.08485517408265005,
      "kl": 0.00583648681640625,
      "learning_rate": 1.1421902062989178e-07,
      "loss": 0.0002,
      "reward": 0.5046875160187483,
      "reward_std": 0.22255349438637495,
      "rewards/format_compliance_reward": 0.0,
      "rewards/math_reasoning_reward": 0.0,
      "rewards/solution_quality_reward": 0.5046875067055225,
      "step": 104
    },
    {
      "completion_length": 868.8515625,
      "epoch": 0.03768888888888889,
      "grad_norm": 0.08212512079305459,
      "kl": 0.005665779113769531,
      "learning_rate": 1.0525330254703788e-07,
      "loss": 0.0002,
      "reward": 0.4375000107102096,
      "reward_std": 0.22603630367666483,
      "rewards/format_compliance_reward": 0.0,
      "rewards/math_reasoning_reward": 0.0,
      "rewards/solution_quality_reward": 0.4375000107102096,
      "step": 106
    },
    {
      "completion_length": 853.9140625,
      "epoch": 0.0384,
      "grad_norm": 0.08994900430130048,
      "kl": 0.00644683837890625,
      "learning_rate": 9.655933126436563e-08,
      "loss": 0.0003,
      "reward": 0.4796875203028321,
      "reward_std": 0.21711003221571445,
      "rewards/format_compliance_reward": 0.0,
      "rewards/math_reasoning_reward": 0.0,
      "rewards/solution_quality_reward": 0.4796875109896064,
      "step": 108
    },
    {
      "completion_length": 825.1328125,
      "epoch": 0.03911111111111111,
      "grad_norm": 0.07289579376020662,
      "kl": 0.006561279296875,
      "learning_rate": 8.81534288045431e-08,
      "loss": 0.0003,
      "reward": 0.5171875199303031,
      "reward_std": 0.20899984799325466,
      "rewards/format_compliance_reward": 0.0,
      "rewards/math_reasoning_reward": 0.0,
      "rewards/solution_quality_reward": 0.5171875124797225,
      "step": 110
    },
    {
      "completion_length": 841.34375,
      "epoch": 0.039822222222222224,
      "grad_norm": 0.09488084966315946,
      "kl": 0.006694793701171875,
      "learning_rate": 8.005137637112302e-08,
      "loss": 0.0003,
      "reward": 0.5093750152736902,
      "reward_std": 0.28519109170883894,
      "rewards/format_compliance_reward": 0.0,
      "rewards/math_reasoning_reward": 0.0,
      "rewards/solution_quality_reward": 0.5093750134110451,
      "step": 112
    },
    {
      "completion_length": 872.6796875,
      "epoch": 0.04053333333333333,
      "grad_norm": 0.09567296035443791,
      "kl": 0.0057201385498046875,
      "learning_rate": 7.226838472098237e-08,
      "loss": 0.0002,
      "reward": 0.47968751238659024,
      "reward_std": 0.2666613038163632,
      "rewards/format_compliance_reward": 0.0,
      "rewards/math_reasoning_reward": 0.0,
      "rewards/solution_quality_reward": 0.47968750493600965,
      "step": 114
    },
    {
      "completion_length": 813.8828125,
      "epoch": 0.041244444444444445,
      "grad_norm": 0.10820746157768055,
      "kl": 0.007022857666015625,
      "learning_rate": 6.481906560771524e-08,
      "loss": 0.0003,
      "reward": 0.5648437645286322,
      "reward_std": 0.24614199809730053,
      "rewards/format_compliance_reward": 0.0,
      "rewards/math_reasoning_reward": 0.01015624962747097,
      "rewards/solution_quality_reward": 0.5546875093132257,
      "step": 116
    },
    {
      "completion_length": 767.515625,
      "epoch": 0.04195555555555556,
      "grad_norm": 0.08997306133980622,
      "kl": 0.0065708160400390625,
      "learning_rate": 5.771740434959277e-08,
      "loss": 0.0003,
      "reward": 0.6203125147148967,
      "reward_std": 0.21331608993932605,
      "rewards/format_compliance_reward": 0.0,
      "rewards/math_reasoning_reward": 0.0,
      "rewards/solution_quality_reward": 0.6203125072643161,
      "step": 118
    },
    {
      "completion_length": 873.734375,
      "epoch": 0.042666666666666665,
      "grad_norm": 0.08100641846157194,
      "kl": 0.006244659423828125,
      "learning_rate": 5.097673357358906e-08,
      "loss": 0.0002,
      "reward": 0.40000000363215804,
      "reward_std": 0.2500735791400075,
      "rewards/format_compliance_reward": 0.0,
      "rewards/math_reasoning_reward": 0.0,
      "rewards/solution_quality_reward": 0.40000000363215804,
      "step": 120
    },
    {
      "completion_length": 792.8515625,
      "epoch": 0.04337777777777778,
      "grad_norm": 0.09791409622965977,
      "kl": 0.0066165924072265625,
      "learning_rate": 4.460970818476717e-08,
      "loss": 0.0003,
      "reward": 0.5750000160187483,
      "reward_std": 0.23660254664719105,
      "rewards/format_compliance_reward": 0.0,
      "rewards/math_reasoning_reward": 0.0,
      "rewards/solution_quality_reward": 0.5750000085681677,
      "step": 122
    },
    {
      "completion_length": 801.453125,
      "epoch": 0.044088888888888886,
      "grad_norm": 0.08071603466853912,
      "kl": 0.005702972412109375,
      "learning_rate": 3.8628281608017065e-08,
      "loss": 0.0002,
      "reward": 0.5296875154599547,
      "reward_std": 0.16949251643382013,
      "rewards/format_compliance_reward": 0.0,
      "rewards/math_reasoning_reward": 0.0,
      "rewards/solution_quality_reward": 0.5296875117346644,
      "step": 124
    },
    {
      "completion_length": 837.828125,
      "epoch": 0.0448,
      "grad_norm": 0.08788137824409525,
      "kl": 0.0059604644775390625,
      "learning_rate": 3.304368334674965e-08,
      "loss": 0.0002,
      "reward": 0.481250012293458,
      "reward_std": 0.24910254683345556,
      "rewards/format_compliance_reward": 0.0,
      "rewards/math_reasoning_reward": 0.0,
      "rewards/solution_quality_reward": 0.4812500048428774,
      "step": 126
    },
    {
      "completion_length": 821.6015625,
      "epoch": 0.04551111111111111,
      "grad_norm": 0.09054496411632566,
      "kl": 0.006633758544921875,
      "learning_rate": 2.7866397900677185e-08,
      "loss": 0.0003,
      "reward": 0.5437500169500709,
      "reward_std": 0.22410254646092653,
      "rewards/format_compliance_reward": 0.0,
      "rewards/math_reasoning_reward": 0.0,
      "rewards/solution_quality_reward": 0.5437500094994903,
      "step": 128
    },
    {
      "completion_length": 853.3046875,
      "epoch": 0.04622222222222222,
      "grad_norm": 0.08754779746234931,
      "kl": 0.006439208984375,
      "learning_rate": 2.3106145082260774e-08,
      "loss": 0.0003,
      "reward": 0.48125001415610313,
      "reward_std": 0.23466878943145275,
      "rewards/format_compliance_reward": 0.0,
      "rewards/math_reasoning_reward": 0.0,
      "rewards/solution_quality_reward": 0.48125000670552254,
      "step": 130
    },
    {
      "completion_length": 828.0703125,
      "epoch": 0.046933333333333334,
      "grad_norm": 0.09068860656569837,
      "kl": 0.005916595458984375,
      "learning_rate": 1.877186176877779e-08,
      "loss": 0.0002,
      "reward": 0.4781250171363354,
      "reward_std": 0.15580127481371164,
      "rewards/format_compliance_reward": 0.0,
      "rewards/math_reasoning_reward": 0.0,
      "rewards/solution_quality_reward": 0.4781250134110451,
      "step": 132
    },
    {
      "completion_length": 807.2109375,
      "epoch": 0.04764444444444445,
      "grad_norm": 0.0940658478261923,
      "kl": 0.006163597106933594,
      "learning_rate": 1.4871685124269007e-08,
      "loss": 0.0002,
      "reward": 0.48593751387670636,
      "reward_std": 0.23586003202944994,
      "rewards/format_compliance_reward": 0.0,
      "rewards/math_reasoning_reward": 0.0,
      "rewards/solution_quality_reward": 0.48593751015141606,
      "step": 134
    },
    {
      "completion_length": 850.7578125,
      "epoch": 0.048355555555555554,
      "grad_norm": 0.09234689786610698,
      "kl": 0.006160736083984375,
      "learning_rate": 1.141293732286297e-08,
      "loss": 0.0002,
      "reward": 0.4687500139698386,
      "reward_std": 0.2885363046079874,
      "rewards/format_compliance_reward": 0.0,
      "rewards/math_reasoning_reward": 0.0,
      "rewards/solution_quality_reward": 0.4687500102445483,
      "step": 136
    },
    {
      "completion_length": 836.015625,
      "epoch": 0.04906666666666667,
      "grad_norm": 0.08756107592003563,
      "kl": 0.0068187713623046875,
      "learning_rate": 8.402111802159412e-09,
      "loss": 0.0003,
      "reward": 0.526562511920929,
      "reward_std": 0.23564936965703964,
      "rewards/format_compliance_reward": 0.0,
      "rewards/math_reasoning_reward": 0.0,
      "rewards/solution_quality_reward": 0.5265625081956387,
      "step": 138
    },
    {
      "completion_length": 815.0625,
      "epoch": 0.049777777777777775,
      "grad_norm": 0.07921211552971878,
      "kl": 0.0070705413818359375,
      "learning_rate": 5.844861072478335e-09,
      "loss": 0.0003,
      "reward": 0.5671875206753612,
      "reward_std": 0.24085476621985435,
      "rewards/format_compliance_reward": 0.0,
      "rewards/math_reasoning_reward": 0.0,
      "rewards/solution_quality_reward": 0.5671875076368451,
      "step": 140
    },
    {
      "completion_length": 817.890625,
      "epoch": 0.05048888888888889,
      "grad_norm": 0.08609005306539234,
      "kl": 0.006622314453125,
      "learning_rate": 3.745986104862903e-09,
      "loss": 0.0003,
      "reward": 0.5875000208616257,
      "reward_std": 0.2721687899902463,
      "rewards/format_compliance_reward": 0.0,
      "rewards/math_reasoning_reward": 0.0,
      "rewards/solution_quality_reward": 0.5875000134110451,
      "step": 142
    },
    {
      "completion_length": 818.9375,
      "epoch": 0.0512,
      "grad_norm": 0.06621426959758697,
      "kl": 0.0066070556640625,
      "learning_rate": 2.1094273177576505e-09,
      "loss": 0.0003,
      "reward": 0.4500000085681677,
      "reward_std": 0.1933012744411826,
      "rewards/format_compliance_reward": 0.0,
      "rewards/math_reasoning_reward": 0.0,
      "rewards/solution_quality_reward": 0.4500000085681677,
      "step": 144
    },
    {
      "completion_length": 841.125,
      "epoch": 0.05191111111111111,
      "grad_norm": 0.10016409872935261,
      "kl": 0.0057544708251953125,
      "learning_rate": 9.38257179284696e-10,
      "loss": 0.0002,
      "reward": 0.5109375165775418,
      "reward_std": 0.2147275460883975,
      "rewards/format_compliance_reward": 0.0,
      "rewards/math_reasoning_reward": 0.0,
      "rewards/solution_quality_reward": 0.5109375016763806,
      "step": 146
    },
    {
      "completion_length": 822.9921875,
      "epoch": 0.05262222222222222,
      "grad_norm": 0.08984285169471264,
      "kl": 0.0066013336181640625,
      "learning_rate": 2.3467443900582197e-10,
      "loss": 0.0003,
      "reward": 0.517187518067658,
      "reward_std": 0.2522275464143604,
      "rewards/format_compliance_reward": 0.0,
      "rewards/math_reasoning_reward": 0.0,
      "rewards/solution_quality_reward": 0.517187506891787,
      "step": 148
    },
    {
      "completion_length": 772.4453125,
      "epoch": 0.05333333333333334,
      "grad_norm": 0.09806696754810183,
      "kl": 0.007259368896484375,
      "learning_rate": 0.0,
      "loss": 0.0003,
      "reward": 0.5906250197440386,
      "reward_std": 0.23228630423545837,
      "rewards/format_compliance_reward": 0.00390625,
      "rewards/math_reasoning_reward": 0.0054687499068677425,
      "rewards/solution_quality_reward": 0.5812500100582838,
      "step": 150
    },
    {
      "epoch": 0.05333333333333334,
      "step": 150,
      "total_flos": 0.0,
      "train_loss": 0.00017194549279035223,
      "train_runtime": 4065.9132,
      "train_samples_per_second": 0.59,
      "train_steps_per_second": 0.037
    }
  ],
  "logging_steps": 2,
  "max_steps": 150,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 25,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 0.0,
  "train_batch_size": 1,
  "trial_name": null,
  "trial_params": null
}