{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 2.032,
  "eval_steps": 500,
  "global_step": 126,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "completion_length": 142.08333587646484,
      "epoch": 0.016,
      "grad_norm": 0.9348842823066913,
      "kl": 0.0,
      "learning_rate": 1.25e-07,
      "loss": -0.0,
      "reward": 0.6988552212715149,
      "reward_std": 0.5108021795749664,
      "rewards/correct_code_reward_func": 0.4583333432674408,
      "rewards/len_reward_func": 0.24052191525697708,
      "step": 1
    },
    {
      "completion_length": 126.56250762939453,
      "epoch": 0.032,
      "grad_norm": 0.8243337506143691,
      "kl": 0.0,
      "learning_rate": 2.5e-07,
      "loss": -0.0,
      "reward": 0.6203328222036362,
      "reward_std": 0.45215627551078796,
      "rewards/correct_code_reward_func": 0.3541666865348816,
      "rewards/len_reward_func": 0.26616617292165756,
      "step": 2
    },
    {
      "completion_length": 108.79166793823242,
      "epoch": 0.048,
      "grad_norm": 0.9128499702856003,
      "kl": 7.30752944946289e-05,
      "learning_rate": 3.75e-07,
      "loss": 0.0,
      "reward": 0.6249927878379822,
      "reward_std": 0.5788741409778595,
      "rewards/correct_code_reward_func": 0.3958333432674408,
      "rewards/len_reward_func": 0.22915946692228317,
      "step": 3
    },
    {
      "completion_length": 142.2291717529297,
      "epoch": 0.064,
      "grad_norm": 0.9975440173663436,
      "kl": 0.00012683868408203125,
      "learning_rate": 5e-07,
      "loss": 0.0,
      "reward": 0.4923219382762909,
      "reward_std": 0.5618958175182343,
      "rewards/correct_code_reward_func": 0.2708333358168602,
      "rewards/len_reward_func": 0.2214886099100113,
      "step": 4
    },
    {
      "completion_length": 167.9166717529297,
      "epoch": 0.08,
      "grad_norm": 0.6875029348712502,
      "kl": 7.176399230957031e-05,
      "learning_rate": 4.999157413258781e-07,
      "loss": 0.0,
      "reward": 0.3392188400030136,
      "reward_std": 0.3500474542379379,
      "rewards/correct_code_reward_func": 0.0833333358168602,
      "rewards/len_reward_func": 0.255885511636734,
      "step": 5
    },
    {
      "completion_length": 132.9166717529297,
      "epoch": 0.096,
      "grad_norm": 0.7328221161754551,
      "kl": 0.0001456737518310547,
      "learning_rate": 4.996630220997057e-07,
      "loss": 0.0,
      "reward": 0.7516234815120697,
      "reward_std": 0.5683842748403549,
      "rewards/correct_code_reward_func": 0.4375000298023224,
      "rewards/len_reward_func": 0.3141235262155533,
      "step": 6
    },
    {
      "completion_length": 178.0416717529297,
      "epoch": 0.112,
      "grad_norm": 0.7294488262352424,
      "kl": 0.00011301040649414062,
      "learning_rate": 4.992420126717784e-07,
      "loss": 0.0,
      "reward": 0.4081832021474838,
      "reward_std": 0.4984392523765564,
      "rewards/correct_code_reward_func": 0.1666666716337204,
      "rewards/len_reward_func": 0.24151653796434402,
      "step": 7
    },
    {
      "completion_length": 190.81250762939453,
      "epoch": 0.128,
      "grad_norm": 0.774451422596215,
      "kl": 0.00012731552124023438,
      "learning_rate": 4.986529968316653e-07,
      "loss": 0.0,
      "reward": 0.5889585018157959,
      "reward_std": 0.5029059052467346,
      "rewards/correct_code_reward_func": 0.2500000149011612,
      "rewards/len_reward_func": 0.3389585465192795,
      "step": 8
    },
    {
      "completion_length": 203.1041717529297,
      "epoch": 0.144,
      "grad_norm": 0.7610759960843761,
      "kl": 0.0001308917999267578,
      "learning_rate": 4.978963716169165e-07,
      "loss": 0.0,
      "reward": 0.5821144282817841,
      "reward_std": 0.5114115178585052,
      "rewards/correct_code_reward_func": 0.3333333432674408,
      "rewards/len_reward_func": 0.24878107011318207,
      "step": 9
    },
    {
      "completion_length": 119.56250762939453,
      "epoch": 0.16,
      "grad_norm": 0.9290248509168798,
      "kl": 0.00010132789611816406,
      "learning_rate": 4.969726470454313e-07,
      "loss": 0.0,
      "reward": 0.7238170504570007,
      "reward_std": 0.5344631671905518,
      "rewards/correct_code_reward_func": 0.4166666716337204,
      "rewards/len_reward_func": 0.30715033411979675,
      "step": 10
    },
    {
      "completion_length": 150.9166717529297,
      "epoch": 0.176,
      "grad_norm": 1.3590266587813116,
      "kl": 0.00018453598022460938,
      "learning_rate": 4.958824457716706e-07,
      "loss": 0.0,
      "reward": 0.6649805009365082,
      "reward_std": 0.4508441388607025,
      "rewards/correct_code_reward_func": 0.375,
      "rewards/len_reward_func": 0.289980486035347,
      "step": 11
    },
    {
      "completion_length": 206.8541717529297,
      "epoch": 0.192,
      "grad_norm": 0.6744815448192079,
      "kl": 0.000133514404296875,
      "learning_rate": 4.946265026669454e-07,
      "loss": 0.0,
      "reward": 0.44046473503112793,
      "reward_std": 0.4918256551027298,
      "rewards/correct_code_reward_func": 0.2083333432674408,
      "rewards/len_reward_func": 0.23213139921426773,
      "step": 12
    },
    {
      "completion_length": 100.33333587646484,
      "epoch": 0.208,
      "grad_norm": 1.1473694035346043,
      "kl": 0.00011897087097167969,
      "learning_rate": 4.932056643240618e-07,
      "loss": 0.0,
      "reward": 0.8099721968173981,
      "reward_std": 0.5177792608737946,
      "rewards/correct_code_reward_func": 0.4791666716337204,
      "rewards/len_reward_func": 0.3308054953813553,
      "step": 13
    },
    {
      "completion_length": 174.52084350585938,
      "epoch": 0.224,
      "grad_norm": 0.7173952224852224,
      "kl": 0.00014257431030273438,
      "learning_rate": 4.916208884866592e-07,
      "loss": 0.0,
      "reward": 0.5219025313854218,
      "reward_std": 0.43796107172966003,
      "rewards/correct_code_reward_func": 0.229166679084301,
      "rewards/len_reward_func": 0.29273584485054016,
      "step": 14
    },
    {
      "completion_length": 118.60417175292969,
      "epoch": 0.24,
      "grad_norm": 1.2540281005004774,
      "kl": 0.00018072128295898438,
      "learning_rate": 4.898732434036243e-07,
      "loss": 0.0,
      "reward": 0.7924503684043884,
      "reward_std": 0.506152406334877,
      "rewards/correct_code_reward_func": 0.4375000149011612,
      "rewards/len_reward_func": 0.3549504280090332,
      "step": 15
    },
    {
      "completion_length": 105.31250381469727,
      "epoch": 0.256,
      "grad_norm": 0.9431489918373908,
      "kl": 0.00018644332885742188,
      "learning_rate": 4.879639071090173e-07,
      "loss": 0.0,
      "reward": 0.5001727938652039,
      "reward_std": 0.45510660111904144,
      "rewards/correct_code_reward_func": 0.2291666716337204,
      "rewards/len_reward_func": 0.27100610733032227,
      "step": 16
    },
    {
      "completion_length": 130.85416793823242,
      "epoch": 0.272,
      "grad_norm": 0.7237713131170656,
      "kl": 0.00011801719665527344,
      "learning_rate": 4.858941666279955e-07,
      "loss": 0.0,
      "reward": 0.7888750731945038,
      "reward_std": 0.5659129619598389,
      "rewards/correct_code_reward_func": 0.5208333432674408,
      "rewards/len_reward_func": 0.2680417224764824,
      "step": 17
    },
    {
      "completion_length": 134.89583587646484,
      "epoch": 0.288,
      "grad_norm": 0.8717728732040717,
      "kl": 0.000164031982421875,
      "learning_rate": 4.836654171092682e-07,
      "loss": 0.0,
      "reward": 0.5576134622097015,
      "reward_std": 0.5418040752410889,
      "rewards/correct_code_reward_func": 0.3125000149011612,
      "rewards/len_reward_func": 0.24511344730854034,
      "step": 18
    },
    {
      "completion_length": 116.54167175292969,
      "epoch": 0.304,
      "grad_norm": 0.9377250817808462,
      "kl": 0.0002789497375488281,
      "learning_rate": 4.812791608846709e-07,
      "loss": 0.0,
      "reward": 0.7832874357700348,
      "reward_std": 0.5703642070293427,
      "rewards/correct_code_reward_func": 0.4583333432674408,
      "rewards/len_reward_func": 0.3249540776014328,
      "step": 19
    },
    {
      "completion_length": 186.06250762939453,
      "epoch": 0.32,
      "grad_norm": 0.9812718853662215,
      "kl": 0.00038433074951171875,
      "learning_rate": 4.787370064564882e-07,
      "loss": 0.0,
      "reward": 0.5579635202884674,
      "reward_std": 0.519572913646698,
      "rewards/correct_code_reward_func": 0.3125,
      "rewards/len_reward_func": 0.2454635202884674,
      "step": 20
    },
    {
      "completion_length": 110.75,
      "epoch": 0.336,
      "grad_norm": 1.0782358974361461,
      "kl": 0.00030231475830078125,
      "learning_rate": 4.7604066741321253e-07,
      "loss": 0.0,
      "reward": 0.9209870100021362,
      "reward_std": 0.5739021599292755,
      "rewards/correct_code_reward_func": 0.6458333432674408,
      "rewards/len_reward_func": 0.2751536965370178,
      "step": 21
    },
    {
      "completion_length": 162.08334350585938,
      "epoch": 0.352,
      "grad_norm": 0.874006092063079,
      "kl": 0.00022363662719726562,
      "learning_rate": 4.731919612744659e-07,
      "loss": 0.0,
      "reward": 0.7241076529026031,
      "reward_std": 0.5581964254379272,
      "rewards/correct_code_reward_func": 0.4791666865348816,
      "rewards/len_reward_func": 0.24494098126888275,
      "step": 22
    },
    {
      "completion_length": 204.14584350585938,
      "epoch": 0.368,
      "grad_norm": 0.82204687952658,
      "kl": 0.00034046173095703125,
      "learning_rate": 4.7019280826586604e-07,
      "loss": 0.0,
      "reward": 0.532179206609726,
      "reward_std": 0.34643039107322693,
      "rewards/correct_code_reward_func": 0.1666666716337204,
      "rewards/len_reward_func": 0.36551257967948914,
      "step": 23
    },
    {
      "completion_length": 151.0208396911621,
      "epoch": 0.384,
      "grad_norm": 0.9960569412421229,
      "kl": 0.00042057037353515625,
      "learning_rate": 4.6704523002466094e-07,
      "loss": 0.0,
      "reward": 0.5193642377853394,
      "reward_std": 0.40249721705913544,
      "rewards/correct_code_reward_func": 0.2083333395421505,
      "rewards/len_reward_func": 0.31103089451789856,
      "step": 24
    },
    {
      "completion_length": 187.20834350585938,
      "epoch": 0.4,
      "grad_norm": 0.6829787161734556,
      "kl": 0.0003147125244140625,
      "learning_rate": 4.6375134823700503e-07,
      "loss": 0.0,
      "reward": 0.43366140127182007,
      "reward_std": 0.4143451601266861,
      "rewards/correct_code_reward_func": 0.1666666716337204,
      "rewards/len_reward_func": 0.2669947147369385,
      "step": 25
    },
    {
      "completion_length": 99.33333587646484,
      "epoch": 0.416,
      "grad_norm": 1.0546549364927,
      "kl": 0.0007066726684570312,
      "learning_rate": 4.603133832077953e-07,
      "loss": 0.0,
      "reward": 0.6213856935501099,
      "reward_std": 0.5858824849128723,
      "rewards/correct_code_reward_func": 0.395833358168602,
      "rewards/len_reward_func": 0.22555235773324966,
      "step": 26
    },
    {
      "completion_length": 119.04167175292969,
      "epoch": 0.432,
      "grad_norm": 1.0435674697004191,
      "kl": 0.000743865966796875,
      "learning_rate": 4.5673365236403216e-07,
      "loss": 0.0,
      "reward": 0.6226212680339813,
      "reward_std": 0.515766441822052,
      "rewards/correct_code_reward_func": 0.4791666865348816,
      "rewards/len_reward_func": 0.14345459267497063,
      "step": 27
    },
    {
      "completion_length": 204.02083587646484,
      "epoch": 0.448,
      "grad_norm": 1.1685217734586066,
      "kl": 0.000659942626953125,
      "learning_rate": 4.530145686927125e-07,
      "loss": 0.0,
      "reward": 0.6347978413105011,
      "reward_std": 0.4856678545475006,
      "rewards/correct_code_reward_func": 0.3333333432674408,
      "rewards/len_reward_func": 0.3014644980430603,
      "step": 28
    },
    {
      "completion_length": 149.87500762939453,
      "epoch": 0.464,
      "grad_norm": 0.7804112511261988,
      "kl": 0.0006847381591796875,
      "learning_rate": 4.4915863911430897e-07,
      "loss": 0.0,
      "reward": 0.4445287883281708,
      "reward_std": 0.4996263086795807,
      "rewards/correct_code_reward_func": 0.1458333358168602,
      "rewards/len_reward_func": 0.29869547486305237,
      "step": 29
    },
    {
      "completion_length": 132.0833396911621,
      "epoch": 0.48,
      "grad_norm": 0.8535635529221804,
      "kl": 0.0006618499755859375,
      "learning_rate": 4.45168462792932e-07,
      "loss": 0.0,
      "reward": 0.6259033381938934,
      "reward_std": 0.4563398212194443,
      "rewards/correct_code_reward_func": 0.3750000149011612,
      "rewards/len_reward_func": 0.2509033679962158,
      "step": 30
    },
    {
      "completion_length": 126.79166793823242,
      "epoch": 0.496,
      "grad_norm": 0.8761490464403178,
      "kl": 0.0010280609130859375,
      "learning_rate": 4.4104672938431223e-07,
      "loss": 0.0,
      "reward": 0.7820720672607422,
      "reward_std": 0.4476567506790161,
      "rewards/correct_code_reward_func": 0.583333358168602,
      "rewards/len_reward_func": 0.1987387351691723,
      "step": 31
    },
    {
      "completion_length": 95.87500381469727,
      "epoch": 0.512,
      "grad_norm": 1.0760263673729638,
      "kl": 0.0013580322265625,
      "learning_rate": 4.367962172227866e-07,
      "loss": 0.0,
      "reward": 0.7095580399036407,
      "reward_std": 0.4921827018260956,
      "rewards/correct_code_reward_func": 0.5000000149011612,
      "rewards/len_reward_func": 0.20955805480480194,
      "step": 32
    },
    {
      "completion_length": 155.02083587646484,
      "epoch": 0.528,
      "grad_norm": 0.9305216291102568,
      "kl": 0.001430511474609375,
      "learning_rate": 4.324197914485075e-07,
      "loss": 0.0,
      "reward": 0.6416721642017365,
      "reward_std": 0.4772767722606659,
      "rewards/correct_code_reward_func": 0.3958333432674408,
      "rewards/len_reward_func": 0.24583880603313446,
      "step": 33
    },
    {
      "completion_length": 215.0416717529297,
      "epoch": 0.544,
      "grad_norm": 0.8211396277152214,
      "kl": 0.0010585784912109375,
      "learning_rate": 4.2792040207614e-07,
      "loss": 0.0,
      "reward": 0.7173371911048889,
      "reward_std": 0.5010073632001877,
      "rewards/correct_code_reward_func": 0.3958333432674408,
      "rewards/len_reward_func": 0.3215038478374481,
      "step": 34
    },
    {
      "completion_length": 128.8958396911621,
      "epoch": 0.56,
      "grad_norm": 0.9266230852523272,
      "kl": 0.001445770263671875,
      "learning_rate": 4.2330108200634723e-07,
      "loss": 0.0,
      "reward": 0.6981382668018341,
      "reward_std": 0.5356450974941254,
      "rewards/correct_code_reward_func": 0.4166666716337204,
      "rewards/len_reward_func": 0.2814715951681137,
      "step": 35
    },
    {
      "completion_length": 174.62500762939453,
      "epoch": 0.576,
      "grad_norm": 0.8774350304368993,
      "kl": 0.00160980224609375,
      "learning_rate": 4.185649449814045e-07,
      "loss": 0.0,
      "reward": 0.819614589214325,
      "reward_std": 0.5062630474567413,
      "rewards/correct_code_reward_func": 0.5000000223517418,
      "rewards/len_reward_func": 0.3196146488189697,
      "step": 36
    },
    {
      "completion_length": 79.29166793823242,
      "epoch": 0.592,
      "grad_norm": 1.1529766368540975,
      "kl": 0.0024871826171875,
      "learning_rate": 4.137151834863213e-07,
      "loss": 0.0,
      "reward": 0.615891844034195,
      "reward_std": 0.6233284175395966,
      "rewards/correct_code_reward_func": 0.4166666716337204,
      "rewards/len_reward_func": 0.19922512769699097,
      "step": 37
    },
    {
      "completion_length": 85.97917175292969,
      "epoch": 0.608,
      "grad_norm": 1.2549480144397245,
      "kl": 0.0028076171875,
      "learning_rate": 4.087550665968846e-07,
      "loss": 0.0,
      "reward": 0.5825270563364029,
      "reward_std": 0.45819054543972015,
      "rewards/correct_code_reward_func": 0.35416667722165585,
      "rewards/len_reward_func": 0.2283603698015213,
      "step": 38
    },
    {
      "completion_length": 85.68750381469727,
      "epoch": 0.624,
      "grad_norm": 1.4005267604268767,
      "kl": 0.003387451171875,
      "learning_rate": 4.036879377760752e-07,
      "loss": 0.0,
      "reward": 0.8216443359851837,
      "reward_std": 0.548437625169754,
      "rewards/correct_code_reward_func": 0.5833333432674408,
      "rewards/len_reward_func": 0.23831100016832352,
      "step": 39
    },
    {
      "completion_length": 113.16667175292969,
      "epoch": 0.64,
      "grad_norm": 1.0341725323218647,
      "kl": 0.003143310546875,
      "learning_rate": 3.9851721262034157e-07,
      "loss": 0.0,
      "reward": 0.520989790558815,
      "reward_std": 0.47860175371170044,
      "rewards/correct_code_reward_func": 0.25,
      "rewards/len_reward_func": 0.270989790558815,
      "step": 40
    },
    {
      "completion_length": 109.70833587646484,
      "epoch": 0.656,
      "grad_norm": 1.0974308815666283,
      "kl": 0.00255584716796875,
      "learning_rate": 3.932463765572505e-07,
      "loss": 0.0,
      "reward": 0.5007437467575073,
      "reward_std": 0.4586540758609772,
      "rewards/correct_code_reward_func": 0.3333333432674408,
      "rewards/len_reward_func": 0.16741041094064713,
      "step": 41
    },
    {
      "completion_length": 113.50000381469727,
      "epoch": 0.672,
      "grad_norm": 0.8007467983812053,
      "kl": 0.00237274169921875,
      "learning_rate": 3.8787898249606767e-07,
      "loss": 0.0,
      "reward": 0.4927902817726135,
      "reward_std": 0.4271247088909149,
      "rewards/correct_code_reward_func": 0.2708333395421505,
      "rewards/len_reward_func": 0.22195692360401154,
      "step": 42
    },
    {
      "completion_length": 79.85416793823242,
      "epoch": 0.688,
      "grad_norm": 1.2179865851315288,
      "kl": 0.00423431396484375,
      "learning_rate": 3.8241864843284964e-07,
      "loss": 0.0,
      "reward": 0.8101656138896942,
      "reward_std": 0.4996851086616516,
      "rewards/correct_code_reward_func": 0.5416666716337204,
      "rewards/len_reward_func": 0.2684989869594574,
      "step": 43
    },
    {
      "completion_length": 91.54167175292969,
      "epoch": 0.704,
      "grad_norm": 1.240439347309207,
      "kl": 0.005615234375,
      "learning_rate": 3.768690550116639e-07,
      "loss": 0.0,
      "reward": 0.7196292579174042,
      "reward_std": 0.5478431880474091,
      "rewards/correct_code_reward_func": 0.4166666865348816,
      "rewards/len_reward_func": 0.3029625713825226,
      "step": 44
    },
    {
      "completion_length": 121.97916793823242,
      "epoch": 0.72,
      "grad_norm": 0.9464336788144472,
      "kl": 0.0048980712890625,
      "learning_rate": 3.712339430435792e-07,
      "loss": 0.0,
      "reward": 0.8251023292541504,
      "reward_std": 0.5142593383789062,
      "rewards/correct_code_reward_func": 0.4791666716337204,
      "rewards/len_reward_func": 0.34593565762043,
      "step": 45
    },
    {
      "completion_length": 88.20833587646484,
      "epoch": 0.736,
      "grad_norm": 0.944700095686709,
      "kl": 0.0039215087890625,
      "learning_rate": 3.65517110985099e-07,
      "loss": 0.0,
      "reward": 0.6876890659332275,
      "reward_std": 0.4308091402053833,
      "rewards/correct_code_reward_func": 0.4166666716337204,
      "rewards/len_reward_func": 0.27102240175008774,
      "step": 46
    },
    {
      "completion_length": 69.75000381469727,
      "epoch": 0.752,
      "grad_norm": 1.2034725464007063,
      "kl": 0.0064544677734375,
      "learning_rate": 3.597224123777389e-07,
      "loss": 0.0,
      "reward": 0.9030305743217468,
      "reward_std": 0.5125944316387177,
      "rewards/correct_code_reward_func": 0.6458333730697632,
      "rewards/len_reward_func": 0.25719721615314484,
      "step": 47
    },
    {
      "completion_length": 84.00000381469727,
      "epoch": 0.768,
      "grad_norm": 1.188785130607309,
      "kl": 0.0072174072265625,
      "learning_rate": 3.5385375325047163e-07,
      "loss": 0.0,
      "reward": 0.6972790956497192,
      "reward_std": 0.6147326231002808,
      "rewards/correct_code_reward_func": 0.3750000149011612,
      "rewards/len_reward_func": 0.32227905094623566,
      "step": 48
    },
    {
      "completion_length": 54.35416793823242,
      "epoch": 0.784,
      "grad_norm": 1.5392691471218216,
      "kl": 0.011932373046875,
      "learning_rate": 3.479150894867926e-07,
      "loss": 0.0,
      "reward": 0.7476979494094849,
      "reward_std": 0.5232938826084137,
      "rewards/correct_code_reward_func": 0.520833358168602,
      "rewards/len_reward_func": 0.22686457633972168,
      "step": 49
    },
    {
      "completion_length": 105.375,
      "epoch": 0.8,
      "grad_norm": 0.9867137272930855,
      "kl": 0.0070037841796875,
      "learning_rate": 3.4191042415818e-07,
      "loss": 0.0,
      "reward": 0.7631438374519348,
      "reward_std": 0.5120529979467392,
      "rewards/correct_code_reward_func": 0.4375,
      "rewards/len_reward_func": 0.3256438076496124,
      "step": 50
    },
    {
      "completion_length": 79.79166793823242,
      "epoch": 0.816,
      "grad_norm": 1.2765736460552886,
      "kl": 0.009490966796875,
      "learning_rate": 3.3584380482574717e-07,
      "loss": 0.0,
      "reward": 0.8190419375896454,
      "reward_std": 0.5837846994400024,
      "rewards/correct_code_reward_func": 0.583333358168602,
      "rewards/len_reward_func": 0.23570860922336578,
      "step": 51
    },
    {
      "completion_length": 66.62500381469727,
      "epoch": 0.832,
      "grad_norm": 1.2357424740774945,
      "kl": 0.012359619140625,
      "learning_rate": 3.297193208119047e-07,
      "loss": 0.0,
      "reward": 0.9992968440055847,
      "reward_std": 0.38213877379894257,
      "rewards/correct_code_reward_func": 0.7500000298023224,
      "rewards/len_reward_func": 0.24929680675268173,
      "step": 52
    },
    {
      "completion_length": 99.83333587646484,
      "epoch": 0.848,
      "grad_norm": 1.1189426445940507,
      "kl": 0.01153564453125,
      "learning_rate": 3.235411004438741e-07,
      "loss": 0.0,
      "reward": 0.8771131932735443,
      "reward_std": 0.5585960447788239,
      "rewards/correct_code_reward_func": 0.520833358168602,
      "rewards/len_reward_func": 0.3562798500061035,
      "step": 53
    },
    {
      "completion_length": 115.89583587646484,
      "epoch": 0.864,
      "grad_norm": 1.3030164084383453,
      "kl": 0.013397216796875,
      "learning_rate": 3.173133082709086e-07,
      "loss": 0.0,
      "reward": 0.9209796786308289,
      "reward_std": 0.5127619951963425,
      "rewards/correct_code_reward_func": 0.5416666865348816,
      "rewards/len_reward_func": 0.37931299209594727,
      "step": 54
    },
    {
      "completion_length": 45.81250190734863,
      "epoch": 0.88,
      "grad_norm": 1.2758138396906251,
      "kl": 0.02093505859375,
      "learning_rate": 3.1104014225709784e-07,
      "loss": 0.0,
      "reward": 1.014316976070404,
      "reward_std": 0.5054647028446198,
      "rewards/correct_code_reward_func": 0.6666666865348816,
      "rewards/len_reward_func": 0.34765030443668365,
      "step": 55
    },
    {
      "completion_length": 177.89584350585938,
      "epoch": 0.896,
      "grad_norm": 0.9790523295873852,
      "kl": 0.0159149169921875,
      "learning_rate": 3.0472583095164873e-07,
      "loss": 0.0,
      "reward": 0.5877984166145325,
      "reward_std": 0.4042231887578964,
      "rewards/correct_code_reward_func": 0.3125000149011612,
      "rewards/len_reward_func": 0.2752983868122101,
      "step": 56
    },
    {
      "completion_length": 46.97916793823242,
      "epoch": 0.912,
      "grad_norm": 2.352715010123481,
      "kl": 0.0218505859375,
      "learning_rate": 2.983746306385499e-07,
      "loss": 0.0,
      "reward": 0.9101540148258209,
      "reward_std": 0.5364184379577637,
      "rewards/correct_code_reward_func": 0.5625,
      "rewards/len_reward_func": 0.3476540297269821,
      "step": 57
    },
    {
      "completion_length": 86.5,
      "epoch": 0.928,
      "grad_norm": 1.3590745378537943,
      "kl": 0.018341064453125,
      "learning_rate": 2.919908224675412e-07,
      "loss": 0.0,
      "reward": 0.7466456890106201,
      "reward_std": 0.4038194566965103,
      "rewards/correct_code_reward_func": 0.458333358168602,
      "rewards/len_reward_func": 0.2883123308420181,
      "step": 58
    },
    {
      "completion_length": 93.35416793823242,
      "epoch": 0.944,
      "grad_norm": 1.0657115005336795,
      "kl": 0.0169677734375,
      "learning_rate": 2.8557870956832133e-07,
      "loss": 0.0,
      "reward": 0.8307068645954132,
      "reward_std": 0.41568903625011444,
      "rewards/correct_code_reward_func": 0.458333358168602,
      "rewards/len_reward_func": 0.37237347662448883,
      "step": 59
    },
    {
      "completion_length": 96.04166793823242,
      "epoch": 0.96,
      "grad_norm": 1.1894982274411716,
      "kl": 0.0167236328125,
      "learning_rate": 2.7914261414993976e-07,
      "loss": 0.0,
      "reward": 0.9781838655471802,
      "reward_std": 0.5707030892372131,
      "rewards/correct_code_reward_func": 0.6458333730697632,
      "rewards/len_reward_func": 0.33235056698322296,
      "step": 60
    },
    {
      "completion_length": 57.041669845581055,
      "epoch": 0.976,
      "grad_norm": 1.6373435351232113,
      "kl": 0.02020263671875,
      "learning_rate": 2.726868745873286e-07,
      "loss": 0.0,
      "reward": 0.7698030173778534,
      "reward_std": 0.5640588998794556,
      "rewards/correct_code_reward_func": 0.5208333432674408,
      "rewards/len_reward_func": 0.2489696592092514,
      "step": 61
    },
    {
      "completion_length": 84.89583587646484,
      "epoch": 0.992,
      "grad_norm": 1.223004703854309,
      "kl": 0.017547607421875,
      "learning_rate": 2.662158424969357e-07,
      "loss": 0.0,
      "reward": 0.8090977072715759,
      "reward_std": 0.6418364942073822,
      "rewards/correct_code_reward_func": 0.4791666716337204,
      "rewards/len_reward_func": 0.32993103563785553,
      "step": 62
    },
    {
      "completion_length": 52.958335876464844,
      "epoch": 1.0,
      "grad_norm": 1.223004703854309,
      "kl": 0.03564453125,
      "learning_rate": 2.597338798034344e-07,
      "loss": 0.0,
      "reward": 0.9149335622787476,
      "reward_std": 0.3469616770744324,
      "rewards/correct_code_reward_func": 0.5416666865348816,
      "rewards/len_reward_func": 0.3732668161392212,
      "step": 63
    },
    {
      "completion_length": 76.31250381469727,
      "epoch": 1.016,
      "grad_norm": 1.234231990060427,
      "kl": 0.0224609375,
      "learning_rate": 2.532453557994827e-07,
      "loss": 0.0,
      "reward": 0.7154572010040283,
      "reward_std": 0.5053917020559311,
      "rewards/correct_code_reward_func": 0.3958333432674408,
      "rewards/len_reward_func": 0.31962384283542633,
      "step": 64
    },
    {
      "completion_length": 116.52083587646484,
      "epoch": 1.032,
      "grad_norm": 1.0750099724368811,
      "kl": 0.01617431640625,
      "learning_rate": 2.467546442005173e-07,
      "loss": 0.0,
      "reward": 0.7226243913173676,
      "reward_std": 0.5376951545476913,
      "rewards/correct_code_reward_func": 0.3750000149011612,
      "rewards/len_reward_func": 0.34762439131736755,
      "step": 65
    },
    {
      "completion_length": 116.10416793823242,
      "epoch": 1.048,
      "grad_norm": 1.0133791335296118,
      "kl": 0.01983642578125,
      "learning_rate": 2.4026612019656556e-07,
      "loss": 0.0,
      "reward": 0.9590997993946075,
      "reward_std": 0.4536292999982834,
      "rewards/correct_code_reward_func": 0.6041666865348816,
      "rewards/len_reward_func": 0.35493315756320953,
      "step": 66
    },
    {
      "completion_length": 66.625,
      "epoch": 1.064,
      "grad_norm": 1.2625208133395418,
      "kl": 0.030517578125,
      "learning_rate": 2.337841575030642e-07,
      "loss": 0.0,
      "reward": 0.9440672397613525,
      "reward_std": 0.42680656909942627,
      "rewards/correct_code_reward_func": 0.583333358168602,
      "rewards/len_reward_func": 0.36073388159275055,
      "step": 67
    },
    {
      "completion_length": 60.458335876464844,
      "epoch": 1.08,
      "grad_norm": 1.174665706452754,
      "kl": 0.02490234375,
      "learning_rate": 2.2731312541267143e-07,
      "loss": 0.0,
      "reward": 0.5735488831996918,
      "reward_std": 0.48749370872974396,
      "rewards/correct_code_reward_func": 0.2500000149011612,
      "rewards/len_reward_func": 0.3235488831996918,
      "step": 68
    },
    {
      "completion_length": 74.10416984558105,
      "epoch": 1.096,
      "grad_norm": 1.5260410634207344,
      "kl": 0.029052734375,
      "learning_rate": 2.2085738585006021e-07,
      "loss": 0.0,
      "reward": 1.0659485459327698,
      "reward_std": 0.3796464204788208,
      "rewards/correct_code_reward_func": 0.6666666865348816,
      "rewards/len_reward_func": 0.3992818146944046,
      "step": 69
    },
    {
      "completion_length": 71.89583396911621,
      "epoch": 1.112,
      "grad_norm": 1.059976697715823,
      "kl": 0.0418701171875,
      "learning_rate": 2.1442129043167873e-07,
      "loss": 0.0,
      "reward": 0.7276312112808228,
      "reward_std": 0.5470257103443146,
      "rewards/correct_code_reward_func": 0.3958333432674408,
      "rewards/len_reward_func": 0.33179786801338196,
      "step": 70
    },
    {
      "completion_length": 96.29166793823242,
      "epoch": 1.1280000000000001,
      "grad_norm": 0.9278761590759935,
      "kl": 0.02056884765625,
      "learning_rate": 2.0800917753245875e-07,
      "loss": 0.0,
      "reward": 0.8413068056106567,
      "reward_std": 0.3271617591381073,
      "rewards/correct_code_reward_func": 0.4375000298023224,
      "rewards/len_reward_func": 0.40380676090717316,
      "step": 71
    },
    {
      "completion_length": 79.33333587646484,
      "epoch": 1.144,
      "grad_norm": 0.9890378359951959,
      "kl": 0.025390625,
      "learning_rate": 2.0162536936145008e-07,
      "loss": 0.0,
      "reward": 0.7865794003009796,
      "reward_std": 0.3915296047925949,
      "rewards/correct_code_reward_func": 0.4166666716337204,
      "rewards/len_reward_func": 0.3699127733707428,
      "step": 72
    },
    {
      "completion_length": 72.95833587646484,
      "epoch": 1.16,
      "grad_norm": 1.3690756427464768,
      "kl": 0.0413818359375,
      "learning_rate": 1.9527416904835132e-07,
      "loss": 0.0,
      "reward": 0.9756404757499695,
      "reward_std": 0.3930533230304718,
      "rewards/correct_code_reward_func": 0.5416666865348816,
      "rewards/len_reward_func": 0.4339737892150879,
      "step": 73
    },
    {
      "completion_length": 79.89583396911621,
      "epoch": 1.176,
      "grad_norm": 1.1734737313856272,
      "kl": 0.02801513671875,
      "learning_rate": 1.889598577429022e-07,
      "loss": 0.0,
      "reward": 0.7878330945968628,
      "reward_std": 0.4340344965457916,
      "rewards/correct_code_reward_func": 0.4166666716337204,
      "rewards/len_reward_func": 0.3711664080619812,
      "step": 74
    },
    {
      "completion_length": 58.270835876464844,
      "epoch": 1.192,
      "grad_norm": 1.2871892634157702,
      "kl": 0.0377197265625,
      "learning_rate": 1.8268669172909136e-07,
      "loss": 0.0,
      "reward": 1.1113883256912231,
      "reward_std": 0.5605219900608063,
      "rewards/correct_code_reward_func": 0.7291666865348816,
      "rewards/len_reward_func": 0.3822215795516968,
      "step": 75
    },
    {
      "completion_length": 97.25,
      "epoch": 1.208,
      "grad_norm": 2.007411904832845,
      "kl": 0.04949951171875,
      "learning_rate": 1.7645889955612592e-07,
      "loss": 0.0,
      "reward": 1.0362713038921356,
      "reward_std": 0.3777136504650116,
      "rewards/correct_code_reward_func": 0.6666666865348816,
      "rewards/len_reward_func": 0.3696046322584152,
      "step": 76
    },
    {
      "completion_length": 42.60416793823242,
      "epoch": 1.224,
      "grad_norm": 1.196008727333628,
      "kl": 0.0433349609375,
      "learning_rate": 1.7028067918809535e-07,
      "loss": 0.0,
      "reward": 0.8968790173530579,
      "reward_std": 0.47050511837005615,
      "rewards/correct_code_reward_func": 0.520833358168602,
      "rewards/len_reward_func": 0.3760456293821335,
      "step": 77
    },
    {
      "completion_length": 44.97916793823242,
      "epoch": 1.24,
      "grad_norm": 1.4303810146633773,
      "kl": 0.0574951171875,
      "learning_rate": 1.6415619517425294e-07,
      "loss": 0.0001,
      "reward": 0.9696877598762512,
      "reward_std": 0.33823370933532715,
      "rewards/correct_code_reward_func": 0.5208333432674408,
      "rewards/len_reward_func": 0.4488544166088104,
      "step": 78
    },
    {
      "completion_length": 66.0625,
      "epoch": 1.256,
      "grad_norm": 1.5543919802377633,
      "kl": 0.03875732421875,
      "learning_rate": 1.5808957584181994e-07,
      "loss": 0.0,
      "reward": 0.9006170630455017,
      "reward_std": 0.37997904419898987,
      "rewards/correct_code_reward_func": 0.4791666716337204,
      "rewards/len_reward_func": 0.4214503914117813,
      "step": 79
    },
    {
      "completion_length": 76.06250381469727,
      "epoch": 1.272,
      "grad_norm": 1.8800678172876588,
      "kl": 0.047607421875,
      "learning_rate": 1.5208491051320744e-07,
      "loss": 0.0,
      "reward": 0.9962214827537537,
      "reward_std": 0.3772743344306946,
      "rewards/correct_code_reward_func": 0.5625000149011612,
      "rewards/len_reward_func": 0.4337214529514313,
      "step": 80
    },
    {
      "completion_length": 43.27083396911621,
      "epoch": 1.288,
      "grad_norm": 1.3749781365688138,
      "kl": 0.055908203125,
      "learning_rate": 1.461462467495284e-07,
      "loss": 0.0001,
      "reward": 1.1482934355735779,
      "reward_std": 0.4654877036809921,
      "rewards/correct_code_reward_func": 0.7291666865348816,
      "rewards/len_reward_func": 0.41912680864334106,
      "step": 81
    },
    {
      "completion_length": 64.25000381469727,
      "epoch": 1.304,
      "grad_norm": 1.2603902864707686,
      "kl": 0.041259765625,
      "learning_rate": 1.4027758762226107e-07,
      "loss": 0.0,
      "reward": 0.8633248507976532,
      "reward_std": 0.44106219708919525,
      "rewards/correct_code_reward_func": 0.4583333432674408,
      "rewards/len_reward_func": 0.40499147772789,
      "step": 82
    },
    {
      "completion_length": 84.87500190734863,
      "epoch": 1.32,
      "grad_norm": 1.3553050400485256,
      "kl": 0.037109375,
      "learning_rate": 1.3448288901490092e-07,
      "loss": 0.0,
      "reward": 0.930885374546051,
      "reward_std": 0.28970160335302353,
      "rewards/correct_code_reward_func": 0.4791666865348816,
      "rewards/len_reward_func": 0.45171867311000824,
      "step": 83
    },
    {
      "completion_length": 44.12500190734863,
      "epoch": 1.336,
      "grad_norm": 1.3471283821112554,
      "kl": 0.05126953125,
      "learning_rate": 1.2876605695642084e-07,
      "loss": 0.0001,
      "reward": 0.8797213435173035,
      "reward_std": 0.4040851444005966,
      "rewards/correct_code_reward_func": 0.4375000149011612,
      "rewards/len_reward_func": 0.44222137331962585,
      "step": 84
    },
    {
      "completion_length": 77.27083587646484,
      "epoch": 1.3519999999999999,
      "grad_norm": 1.3204773489251114,
      "kl": 0.0401611328125,
      "learning_rate": 1.231309449883361e-07,
      "loss": 0.0,
      "reward": 0.9848110675811768,
      "reward_std": 0.5164197236299515,
      "rewards/correct_code_reward_func": 0.5833333432674408,
      "rewards/len_reward_func": 0.40147776901721954,
      "step": 85
    },
    {
      "completion_length": 58.729169845581055,
      "epoch": 1.3679999999999999,
      "grad_norm": 1.6764054808630413,
      "kl": 0.0513916015625,
      "learning_rate": 1.1758135156715041e-07,
      "loss": 0.0001,
      "reward": 1.1368677616119385,
      "reward_std": 0.3856023848056793,
      "rewards/correct_code_reward_func": 0.7708333432674408,
      "rewards/len_reward_func": 0.3660343587398529,
      "step": 86
    },
    {
      "completion_length": 90.02083396911621,
      "epoch": 1.384,
      "grad_norm": 1.1184416966735806,
      "kl": 0.03411865234375,
      "learning_rate": 1.1212101750393235e-07,
      "loss": 0.0,
      "reward": 1.00173819065094,
      "reward_std": 0.49202577769756317,
      "rewards/correct_code_reward_func": 0.5625000298023224,
      "rewards/len_reward_func": 0.43923819065093994,
      "step": 87
    },
    {
      "completion_length": 46.60416793823242,
      "epoch": 1.4,
      "grad_norm": 1.1504631747132115,
      "kl": 0.0496826171875,
      "learning_rate": 1.0675362344274952e-07,
      "loss": 0.0,
      "reward": 0.9823802709579468,
      "reward_std": 0.46341855823993683,
      "rewards/correct_code_reward_func": 0.6041666865348816,
      "rewards/len_reward_func": 0.3782135844230652,
      "step": 88
    },
    {
      "completion_length": 59.937503814697266,
      "epoch": 1.416,
      "grad_norm": 1.3546823329176554,
      "kl": 0.0450439453125,
      "learning_rate": 1.0148278737965844e-07,
      "loss": 0.0,
      "reward": 1.116898536682129,
      "reward_std": 0.3632017821073532,
      "rewards/correct_code_reward_func": 0.6250000298023224,
      "rewards/len_reward_func": 0.4918985068798065,
      "step": 89
    },
    {
      "completion_length": 38.08333396911621,
      "epoch": 1.432,
      "grad_norm": 1.4742606396398155,
      "kl": 0.06396484375,
      "learning_rate": 9.631206222392479e-08,
      "loss": 0.0001,
      "reward": 1.079964131116867,
      "reward_std": 0.47177985310554504,
      "rewards/correct_code_reward_func": 0.6666666865348816,
      "rewards/len_reward_func": 0.4132973849773407,
      "step": 90
    },
    {
      "completion_length": 72.18750190734863,
      "epoch": 1.448,
      "grad_norm": 1.4885040482346985,
      "kl": 0.0491943359375,
      "learning_rate": 9.124493340311537e-08,
      "loss": 0.0,
      "reward": 1.0042789578437805,
      "reward_std": 0.3533863425254822,
      "rewards/correct_code_reward_func": 0.5625000298023224,
      "rewards/len_reward_func": 0.44177892804145813,
      "step": 91
    },
    {
      "completion_length": 69.35416984558105,
      "epoch": 1.464,
      "grad_norm": 1.1925308190836468,
      "kl": 0.0478515625,
      "learning_rate": 8.628481651367875e-08,
      "loss": 0.0,
      "reward": 1.0887993574142456,
      "reward_std": 0.5487662255764008,
      "rewards/correct_code_reward_func": 0.6666666865348816,
      "rewards/len_reward_func": 0.422132670879364,
      "step": 92
    },
    {
      "completion_length": 48.41666793823242,
      "epoch": 1.48,
      "grad_norm": 1.6549689653260358,
      "kl": 0.051025390625,
      "learning_rate": 8.143505501859551e-08,
      "loss": 0.0001,
      "reward": 0.920165479183197,
      "reward_std": 0.415915310382843,
      "rewards/correct_code_reward_func": 0.5208333432674408,
      "rewards/len_reward_func": 0.39933212101459503,
      "step": 93
    },
    {
      "completion_length": 75.87500381469727,
      "epoch": 1.496,
      "grad_norm": 1.586423514577547,
      "kl": 0.053466796875,
      "learning_rate": 7.669891799365282e-08,
      "loss": 0.0001,
      "reward": 0.8828703761100769,
      "reward_std": 0.49832169711589813,
      "rewards/correct_code_reward_func": 0.4375000149011612,
      "rewards/len_reward_func": 0.4453703910112381,
      "step": 94
    },
    {
      "completion_length": 79.06250190734863,
      "epoch": 1.512,
      "grad_norm": 1.7029251090199986,
      "kl": 0.0489501953125,
      "learning_rate": 7.207959792385998e-08,
      "loss": 0.0,
      "reward": 1.0712128281593323,
      "reward_std": 0.39892764389514923,
      "rewards/correct_code_reward_func": 0.6041666865348816,
      "rewards/len_reward_func": 0.4670460820198059,
      "step": 95
    },
    {
      "completion_length": 77.66666984558105,
      "epoch": 1.528,
      "grad_norm": 1.068625601865938,
      "kl": 0.03729248046875,
      "learning_rate": 6.758020855149249e-08,
      "loss": 0.0,
      "reward": 0.839818924665451,
      "reward_std": 0.4449944496154785,
      "rewards/correct_code_reward_func": 0.3958333432674408,
      "rewards/len_reward_func": 0.44398559629917145,
      "step": 96
    },
    {
      "completion_length": 46.00000190734863,
      "epoch": 1.544,
      "grad_norm": 1.6059040022360391,
      "kl": 0.0543212890625,
      "learning_rate": 6.320378277721342e-08,
      "loss": 0.0001,
      "reward": 0.8210516273975372,
      "reward_std": 0.34706588089466095,
      "rewards/correct_code_reward_func": 0.3958333432674408,
      "rewards/len_reward_func": 0.42521825432777405,
      "step": 97
    },
    {
      "completion_length": 47.35416793823242,
      "epoch": 1.56,
      "grad_norm": 1.0536706533475677,
      "kl": 0.06640625,
      "learning_rate": 5.895327061568775e-08,
      "loss": 0.0001,
      "reward": 0.9913617670536041,
      "reward_std": 0.24820256233215332,
      "rewards/correct_code_reward_func": 0.5208333432674408,
      "rewards/len_reward_func": 0.47052840888500214,
      "step": 98
    },
    {
      "completion_length": 34.83333396911621,
      "epoch": 1.576,
      "grad_norm": 1.7119720585841143,
      "kl": 0.0626220703125,
      "learning_rate": 5.483153720706798e-08,
      "loss": 0.0001,
      "reward": 0.8738410770893097,
      "reward_std": 0.5085435211658478,
      "rewards/correct_code_reward_func": 0.4375000149011612,
      "rewards/len_reward_func": 0.4363410472869873,
      "step": 99
    },
    {
      "completion_length": 57.04166793823242,
      "epoch": 1.592,
      "grad_norm": 1.3955252614043234,
      "kl": 0.036865234375,
      "learning_rate": 5.0841360885690996e-08,
      "loss": 0.0,
      "reward": 1.1610032320022583,
      "reward_std": 0.3681405633687973,
      "rewards/correct_code_reward_func": 0.6666666865348816,
      "rewards/len_reward_func": 0.4943365752696991,
      "step": 100
    },
    {
      "completion_length": 71.41666984558105,
      "epoch": 1.608,
      "grad_norm": 0.9360155945219467,
      "kl": 0.055419921875,
      "learning_rate": 4.698543130728755e-08,
      "loss": 0.0001,
      "reward": 1.013959676027298,
      "reward_std": 0.39147183299064636,
      "rewards/correct_code_reward_func": 0.625,
      "rewards/len_reward_func": 0.3889596611261368,
      "step": 101
    },
    {
      "completion_length": 43.5625,
      "epoch": 1.624,
      "grad_norm": 1.620965651402336,
      "kl": 0.054443359375,
      "learning_rate": 4.326634763596784e-08,
      "loss": 0.0001,
      "reward": 0.8748385310173035,
      "reward_std": 0.3259390592575073,
      "rewards/correct_code_reward_func": 0.4166666679084301,
      "rewards/len_reward_func": 0.45817187428474426,
      "step": 102
    },
    {
      "completion_length": 54.125003814697266,
      "epoch": 1.6400000000000001,
      "grad_norm": 2.035180505859693,
      "kl": 0.056640625,
      "learning_rate": 3.968661679220467e-08,
      "loss": 0.0001,
      "reward": 1.2046028971672058,
      "reward_std": 0.4274601340293884,
      "rewards/correct_code_reward_func": 0.7708333730697632,
      "rewards/len_reward_func": 0.433769553899765,
      "step": 103
    },
    {
      "completion_length": 37.72916793823242,
      "epoch": 1.6560000000000001,
      "grad_norm": 1.3110502429273858,
      "kl": 0.07470703125,
      "learning_rate": 3.624865176299499e-08,
      "loss": 0.0001,
      "reward": 1.3125,
      "reward_std": 0.2893980145454407,
      "rewards/correct_code_reward_func": 0.8333333432674408,
      "rewards/len_reward_func": 0.4791666716337204,
      "step": 104
    },
    {
      "completion_length": 85.20833587646484,
      "epoch": 1.6720000000000002,
      "grad_norm": 0.7548512888732658,
      "kl": 0.0379638671875,
      "learning_rate": 3.295476997533905e-08,
      "loss": 0.0,
      "reward": 0.8693651854991913,
      "reward_std": 0.467289537191391,
      "rewards/correct_code_reward_func": 0.4166666865348816,
      "rewards/len_reward_func": 0.4526985138654709,
      "step": 105
    },
    {
      "completion_length": 60.72916793823242,
      "epoch": 1.688,
      "grad_norm": 0.7605372623815415,
      "kl": 0.03662109375,
      "learning_rate": 2.980719173413396e-08,
      "loss": 0.0,
      "reward": 1.058800995349884,
      "reward_std": 0.4301101863384247,
      "rewards/correct_code_reward_func": 0.5625000298023224,
      "rewards/len_reward_func": 0.49630098044872284,
      "step": 106
    },
    {
      "completion_length": 49.08333396911621,
      "epoch": 1.704,
      "grad_norm": 1.0207996418513696,
      "kl": 0.07421875,
      "learning_rate": 2.680803872553408e-08,
      "loss": 0.0001,
      "reward": 0.9703012108802795,
      "reward_std": 0.23036788403987885,
      "rewards/correct_code_reward_func": 0.5208333432674408,
      "rewards/len_reward_func": 0.44946780800819397,
      "step": 107
    },
    {
      "completion_length": 57.62500190734863,
      "epoch": 1.72,
      "grad_norm": 1.5035291383359601,
      "kl": 0.0594482421875,
      "learning_rate": 2.395933258678745e-08,
      "loss": 0.0001,
      "reward": 1.1501469016075134,
      "reward_std": 0.34404293447732925,
      "rewards/correct_code_reward_func": 0.7083333432674408,
      "rewards/len_reward_func": 0.44181351363658905,
      "step": 108
    },
    {
      "completion_length": 31.312501907348633,
      "epoch": 1.736,
      "grad_norm": 1.6167712080198857,
      "kl": 0.0712890625,
      "learning_rate": 2.1262993543511715e-08,
      "loss": 0.0001,
      "reward": 1.3109871745109558,
      "reward_std": 0.3160089999437332,
      "rewards/correct_code_reward_func": 0.875,
      "rewards/len_reward_func": 0.4359871447086334,
      "step": 109
    },
    {
      "completion_length": 87.22916793823242,
      "epoch": 1.752,
      "grad_norm": 1.2313006391246961,
      "kl": 0.0474853515625,
      "learning_rate": 1.872083911532907e-08,
      "loss": 0.0,
      "reward": 0.8871810734272003,
      "reward_std": 0.43447698652744293,
      "rewards/correct_code_reward_func": 0.4166666865348816,
      "rewards/len_reward_func": 0.4705143868923187,
      "step": 110
    },
    {
      "completion_length": 38.52083396911621,
      "epoch": 1.768,
      "grad_norm": 1.1333291307805236,
      "kl": 0.0531005859375,
      "learning_rate": 1.6334582890731697e-08,
      "loss": 0.0001,
      "reward": 1.3089049458503723,
      "reward_std": 0.39449335634708405,
      "rewards/correct_code_reward_func": 0.8541666865348816,
      "rewards/len_reward_func": 0.45473821461200714,
      "step": 111
    },
    {
      "completion_length": 99.85416984558105,
      "epoch": 1.784,
      "grad_norm": 1.1649171723265364,
      "kl": 0.04095458984375,
      "learning_rate": 1.4105833372004523e-08,
      "loss": 0.0,
      "reward": 0.8114411234855652,
      "reward_std": 0.3455437570810318,
      "rewards/correct_code_reward_func": 0.4166666716337204,
      "rewards/len_reward_func": 0.3947744071483612,
      "step": 112
    },
    {
      "completion_length": 62.97916793823242,
      "epoch": 1.8,
      "grad_norm": 1.3270422235967783,
      "kl": 0.042236328125,
      "learning_rate": 1.2036092890982619e-08,
      "loss": 0.0,
      "reward": 0.8704836964607239,
      "reward_std": 0.37642528116703033,
      "rewards/correct_code_reward_func": 0.3958333432674408,
      "rewards/len_reward_func": 0.4746503531932831,
      "step": 113
    },
    {
      "completion_length": 61.854169845581055,
      "epoch": 1.8159999999999998,
      "grad_norm": 1.47111563325612,
      "kl": 0.0511474609375,
      "learning_rate": 1.0126756596375685e-08,
      "loss": 0.0001,
      "reward": 1.0473325848579407,
      "reward_std": 0.5612048506736755,
      "rewards/correct_code_reward_func": 0.5833333730697632,
      "rewards/len_reward_func": 0.4639992117881775,
      "step": 114
    },
    {
      "completion_length": 44.22916793823242,
      "epoch": 1.8319999999999999,
      "grad_norm": 1.3437447624267829,
      "kl": 0.0599365234375,
      "learning_rate": 8.379111513340753e-09,
      "loss": 0.0001,
      "reward": 0.9941486120223999,
      "reward_std": 0.5003164112567902,
      "rewards/correct_code_reward_func": 0.5625000149011612,
      "rewards/len_reward_func": 0.4316485822200775,
      "step": 115
    },
    {
      "completion_length": 51.45833396911621,
      "epoch": 1.8479999999999999,
      "grad_norm": 1.3897204537445644,
      "kl": 0.0416259765625,
      "learning_rate": 6.7943356759381785e-09,
      "loss": 0.0,
      "reward": 1.0625000596046448,
      "reward_std": 0.4191845655441284,
      "rewards/correct_code_reward_func": 0.5833333730697632,
      "rewards/len_reward_func": 0.4791666716337204,
      "step": 116
    },
    {
      "completion_length": 64.45833587646484,
      "epoch": 1.8639999999999999,
      "grad_norm": 2.0280580958010224,
      "kl": 0.07666015625,
      "learning_rate": 5.373497333054616e-09,
      "loss": 0.0001,
      "reward": 0.9957386255264282,
      "reward_std": 0.49953845143318176,
      "rewards/correct_code_reward_func": 0.5,
      "rewards/len_reward_func": 0.4957386255264282,
      "step": 117
    },
    {
      "completion_length": 61.833335876464844,
      "epoch": 1.88,
      "grad_norm": 1.4575505392586763,
      "kl": 0.06689453125,
      "learning_rate": 4.117554228329406e-09,
      "loss": 0.0001,
      "reward": 1.2341400384902954,
      "reward_std": 0.472938671708107,
      "rewards/correct_code_reward_func": 0.8125000298023224,
      "rewards/len_reward_func": 0.421640083193779,
      "step": 118
    },
    {
      "completion_length": 54.43750286102295,
      "epoch": 1.896,
      "grad_norm": 1.6449474004844165,
      "kl": 0.0567626953125,
      "learning_rate": 3.0273529545687125e-09,
      "loss": 0.0001,
      "reward": 1.0164108276367188,
      "reward_std": 0.4117661267518997,
      "rewards/correct_code_reward_func": 0.5208333432674408,
      "rewards/len_reward_func": 0.49557754397392273,
      "step": 119
    },
    {
      "completion_length": 59.8125,
      "epoch": 1.912,
      "grad_norm": 1.2181441627902125,
      "kl": 0.052978515625,
      "learning_rate": 2.1036283830834224e-09,
      "loss": 0.0001,
      "reward": 1.1736499071121216,
      "reward_std": 0.41473129391670227,
      "rewards/correct_code_reward_func": 0.7083333432674408,
      "rewards/len_reward_func": 0.465316578745842,
      "step": 120
    },
    {
      "completion_length": 29.125001907348633,
      "epoch": 1.928,
      "grad_norm": 1.6515660045888947,
      "kl": 0.0712890625,
      "learning_rate": 1.347003168334665e-09,
      "loss": 0.0001,
      "reward": 1.2279411554336548,
      "reward_std": 0.212213896214962,
      "rewards/correct_code_reward_func": 0.7500000298023224,
      "rewards/len_reward_func": 0.477941170334816,
      "step": 121
    },
    {
      "completion_length": 40.29166793823242,
      "epoch": 1.944,
      "grad_norm": 2.3395660695095883,
      "kl": 0.0679931640625,
      "learning_rate": 7.579873282216598e-10,
      "loss": 0.0001,
      "reward": 0.9375000298023224,
      "reward_std": 0.37034808099269867,
      "rewards/correct_code_reward_func": 0.4583333432674408,
      "rewards/len_reward_func": 0.4791666716337204,
      "step": 122
    },
    {
      "completion_length": 70.83333396911621,
      "epoch": 1.96,
      "grad_norm": 1.119825823829922,
      "kl": 0.057861328125,
      "learning_rate": 3.3697790029424413e-10,
      "loss": 0.0001,
      "reward": 1.2083333730697632,
      "reward_std": 0.39485183358192444,
      "rewards/correct_code_reward_func": 0.7083333730697632,
      "rewards/len_reward_func": 0.5,
      "step": 123
    },
    {
      "completion_length": 52.750003814697266,
      "epoch": 1.976,
      "grad_norm": 2.4270573554119026,
      "kl": 0.0513916015625,
      "learning_rate": 8.425867412190091e-11,
      "loss": 0.0001,
      "reward": 1.1584753692150116,
      "reward_std": 0.37459391355514526,
      "rewards/correct_code_reward_func": 0.7083333432674408,
      "rewards/len_reward_func": 0.4501419961452484,
      "step": 124
    },
    {
      "completion_length": 95.9375,
      "epoch": 1.992,
      "grad_norm": 1.1107259696791534,
      "kl": 0.038330078125,
      "learning_rate": 0.0,
      "loss": 0.0,
      "reward": 1.0544261932373047,
      "reward_std": 0.4110799580812454,
      "rewards/correct_code_reward_func": 0.6041666865348816,
      "rewards/len_reward_func": 0.4502594470977783,
      "step": 125
    },
    {
      "completion_length": 70.72916984558105,
      "epoch": 2.032,
      "grad_norm": 0.921072382478298,
      "kl": 0.067626953125,
      "learning_rate": 8.425867412190091e-11,
      "loss": 0.0001,
      "reward": 0.8045242130756378,
      "reward_std": 0.41052111983299255,
      "rewards/correct_code_reward_func": 0.3750000149011612,
      "rewards/len_reward_func": 0.42952418327331543,
      "step": 126
    },
    {
      "epoch": 2.032,
      "step": 126,
      "total_flos": 0.0,
      "train_loss": 5.371543848591428e-07,
      "train_runtime": 142.6302,
      "train_samples_per_second": 5.258,
      "train_steps_per_second": 0.876
    }
  ],
  "logging_steps": 1,
  "max_steps": 125,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 3,
  "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
}