{
  "best_global_step": null,
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.4,
  "eval_steps": 500,
  "global_step": 100,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "completion_length": 361.75,
      "epoch": 0.004,
      "grad_norm": 0.0693558007478714,
      "kl": 0.0,
      "learning_rate": 0.0,
      "loss": -0.0,
      "reward": 0.02345000021159649,
      "reward_std": 0.04690000042319298,
      "rewards/pot_combined_reward": 0.02345000021159649,
      "step": 1
    },
    {
      "completion_length": 371.375,
      "epoch": 0.008,
      "grad_norm": 0.08951307833194733,
      "kl": 0.0,
      "learning_rate": 5.000000000000001e-07,
      "loss": -0.0,
      "reward": 0.026133334264159203,
      "reward_std": 0.052266668528318405,
      "rewards/pot_combined_reward": 0.026133334264159203,
      "step": 2
    },
    {
      "completion_length": 374.0,
      "epoch": 0.012,
      "grad_norm": 0.001663331058807671,
      "kl": 0.0005528016190510243,
      "learning_rate": 1.0000000000000002e-06,
      "loss": 0.0001,
      "reward": 0.0,
      "reward_std": 0.0,
      "rewards/pot_combined_reward": 0.0,
      "step": 3
    },
    {
      "completion_length": 374.0,
      "epoch": 0.016,
      "grad_norm": 0.0016158577054738998,
      "kl": 0.0005013404006604105,
      "learning_rate": 1.5e-06,
      "loss": 0.0001,
      "reward": 0.0,
      "reward_std": 0.0,
      "rewards/pot_combined_reward": 0.0,
      "step": 4
    },
    {
      "completion_length": 373.375,
      "epoch": 0.02,
      "grad_norm": 0.0030017346143722534,
      "kl": 0.0005660907772835344,
      "learning_rate": 2.0000000000000003e-06,
      "loss": 0.0001,
      "reward": 0.0,
      "reward_std": 0.0,
      "rewards/pot_combined_reward": 0.0,
      "step": 5
    },
    {
      "completion_length": 373.5625,
      "epoch": 0.024,
      "grad_norm": 0.0015043334569782019,
      "kl": 0.0005426810312201269,
      "learning_rate": 2.5e-06,
      "loss": 0.0001,
      "reward": 0.0,
      "reward_std": 0.0,
      "rewards/pot_combined_reward": 0.0,
      "step": 6
    },
    {
      "completion_length": 364.5,
      "epoch": 0.028,
      "grad_norm": 0.08007726073265076,
      "kl": 0.0005026786457165144,
      "learning_rate": 3e-06,
      "loss": 0.0001,
      "reward": 0.03146666660904884,
      "reward_std": 0.06293333321809769,
      "rewards/pot_combined_reward": 0.03146666660904884,
      "step": 7
    },
    {
      "completion_length": 374.0,
      "epoch": 0.032,
      "grad_norm": 0.0016093035228550434,
      "kl": 0.0005015511706005782,
      "learning_rate": 3.5e-06,
      "loss": 0.0001,
      "reward": 0.0,
      "reward_std": 0.0,
      "rewards/pot_combined_reward": 0.0,
      "step": 8
    },
    {
      "completion_length": 353.0625,
      "epoch": 0.036,
      "grad_norm": 0.001784446300007403,
      "kl": 0.0003549655375536531,
      "learning_rate": 4.000000000000001e-06,
      "loss": 0.0,
      "reward": 0.0,
      "reward_std": 0.0,
      "rewards/pot_combined_reward": 0.0,
      "step": 9
    },
    {
      "completion_length": 374.0,
      "epoch": 0.04,
      "grad_norm": 0.0020515809301286936,
      "kl": 0.0005762250584666617,
      "learning_rate": 4.5e-06,
      "loss": 0.0001,
      "reward": 0.0,
      "reward_std": 0.0,
      "rewards/pot_combined_reward": 0.0,
      "step": 10
    },
    {
      "completion_length": 374.0,
      "epoch": 0.044,
      "grad_norm": 0.06735244393348694,
      "kl": 0.0005008808220736682,
      "learning_rate": 5e-06,
      "loss": 0.0001,
      "reward": 0.01808333396911621,
      "reward_std": 0.03616666793823242,
      "rewards/pot_combined_reward": 0.01808333396911621,
      "step": 11
    },
    {
      "completion_length": 342.5,
      "epoch": 0.048,
      "grad_norm": 0.0024033007211983204,
      "kl": 0.00046441886661341414,
      "learning_rate": 4.99847706754774e-06,
      "loss": 0.0,
      "reward": 0.0,
      "reward_std": 0.0,
      "rewards/pot_combined_reward": 0.0,
      "step": 12
    },
    {
      "completion_length": 374.0,
      "epoch": 0.052,
      "grad_norm": 0.0014815045287832618,
      "kl": 0.0004604290661518462,
      "learning_rate": 4.993910125649561e-06,
      "loss": 0.0,
      "reward": 0.0,
      "reward_std": 0.0,
      "rewards/pot_combined_reward": 0.0,
      "step": 13
    },
    {
      "completion_length": 374.0,
      "epoch": 0.056,
      "grad_norm": 0.001548771746456623,
      "kl": 0.0004989306180505082,
      "learning_rate": 4.986304738420684e-06,
      "loss": 0.0,
      "reward": 0.0,
      "reward_std": 0.0,
      "rewards/pot_combined_reward": 0.0,
      "step": 14
    },
    {
      "completion_length": 360.8125,
      "epoch": 0.06,
      "grad_norm": 0.001822226564399898,
      "kl": 0.00046228048086049967,
      "learning_rate": 4.975670171853926e-06,
      "loss": 0.0,
      "reward": 0.0,
      "reward_std": 0.0,
      "rewards/pot_combined_reward": 0.0,
      "step": 15
    },
    {
      "completion_length": 374.0,
      "epoch": 0.064,
      "grad_norm": 0.09072617441415787,
      "kl": 0.000476861278002616,
      "learning_rate": 4.962019382530521e-06,
      "loss": 0.0,
      "reward": 0.012600000016391277,
      "reward_std": 0.025200000032782555,
      "rewards/pot_combined_reward": 0.012600000016391277,
      "step": 16
    },
    {
      "completion_length": 374.0,
      "epoch": 0.068,
      "grad_norm": 0.0015437575057148933,
      "kl": 0.0005299622716847807,
      "learning_rate": 4.9453690018345144e-06,
      "loss": 0.0001,
      "reward": 0.0,
      "reward_std": 0.0,
      "rewards/pot_combined_reward": 0.0,
      "step": 17
    },
    {
      "completion_length": 374.0,
      "epoch": 0.072,
      "grad_norm": 0.0016528957057744265,
      "kl": 0.0005346549514797516,
      "learning_rate": 4.925739315689991e-06,
      "loss": 0.0001,
      "reward": 0.0,
      "reward_std": 0.0,
      "rewards/pot_combined_reward": 0.0,
      "step": 18
    },
    {
      "completion_length": 374.0,
      "epoch": 0.076,
      "grad_norm": 0.0017183530144393444,
      "kl": 0.0004841076224693097,
      "learning_rate": 4.903154239845798e-06,
      "loss": 0.0,
      "reward": 0.0,
      "reward_std": 0.0,
      "rewards/pot_combined_reward": 0.0,
      "step": 19
    },
    {
      "completion_length": 373.5625,
      "epoch": 0.08,
      "grad_norm": 0.08476348221302032,
      "kl": 0.000539450986252632,
      "learning_rate": 4.8776412907378845e-06,
      "loss": 0.0001,
      "reward": 0.026249999180436134,
      "reward_std": 0.05249999836087227,
      "rewards/pot_combined_reward": 0.026249999180436134,
      "step": 20
    },
    {
      "completion_length": 374.0,
      "epoch": 0.084,
      "grad_norm": 0.07820821553468704,
      "kl": 0.0005957721295999363,
      "learning_rate": 4.849231551964771e-06,
      "loss": 0.0001,
      "reward": 0.07116249948740005,
      "reward_std": 0.1423249989748001,
      "rewards/pot_combined_reward": 0.07116249948740005,
      "step": 21
    },
    {
      "completion_length": 373.5625,
      "epoch": 0.088,
      "grad_norm": 0.0016008545644581318,
      "kl": 0.000533243379322812,
      "learning_rate": 4.817959636416969e-06,
      "loss": 0.0001,
      "reward": 0.0,
      "reward_std": 0.0,
      "rewards/pot_combined_reward": 0.0,
      "step": 22
    },
    {
      "completion_length": 374.0,
      "epoch": 0.092,
      "grad_norm": 0.0018651616992428899,
      "kl": 0.0005620143201667815,
      "learning_rate": 4.783863644106502e-06,
      "loss": 0.0001,
      "reward": 0.0,
      "reward_std": 0.0,
      "rewards/pot_combined_reward": 0.0,
      "step": 23
    },
    {
      "completion_length": 374.0,
      "epoch": 0.096,
      "grad_norm": 0.001895356923341751,
      "kl": 0.00047788477240828797,
      "learning_rate": 4.746985115747918e-06,
      "loss": 0.0,
      "reward": 0.0,
      "reward_std": 0.0,
      "rewards/pot_combined_reward": 0.0,
      "step": 24
    },
    {
      "completion_length": 369.75,
      "epoch": 0.1,
      "grad_norm": 0.11337540298700333,
      "kl": 0.00047047801490407437,
      "learning_rate": 4.707368982147318e-06,
      "loss": 0.0,
      "reward": 0.04736666567623615,
      "reward_std": 0.0947333313524723,
      "rewards/pot_combined_reward": 0.04736666567623615,
      "step": 25
    },
    {
      "completion_length": 368.625,
      "epoch": 0.104,
      "grad_norm": 0.01079186424612999,
      "kl": 0.0006513141634059139,
      "learning_rate": 4.665063509461098e-06,
      "loss": 0.0001,
      "reward": 0.0,
      "reward_std": 0.0,
      "rewards/pot_combined_reward": 0.0,
      "step": 26
    },
    {
      "completion_length": 374.0,
      "epoch": 0.108,
      "grad_norm": 0.0016566955018788576,
      "kl": 0.0005965056043351069,
      "learning_rate": 4.620120240391065e-06,
      "loss": 0.0001,
      "reward": 0.0,
      "reward_std": 0.0,
      "rewards/pot_combined_reward": 0.0,
      "step": 27
    },
    {
      "completion_length": 374.0,
      "epoch": 0.112,
      "grad_norm": 0.001792517607100308,
      "kl": 0.0005393773099058308,
      "learning_rate": 4.572593931387604e-06,
      "loss": 0.0001,
      "reward": 0.0,
      "reward_std": 0.0,
      "rewards/pot_combined_reward": 0.0,
      "step": 28
    },
    {
      "completion_length": 374.0,
      "epoch": 0.116,
      "grad_norm": 0.0017438618233427405,
      "kl": 0.0005095232809253503,
      "learning_rate": 4.522542485937369e-06,
      "loss": 0.0001,
      "reward": 0.0,
      "reward_std": 0.0,
      "rewards/pot_combined_reward": 0.0,
      "step": 29
    },
    {
      "completion_length": 374.0,
      "epoch": 0.12,
      "grad_norm": 0.0015684061218053102,
      "kl": 0.00047055614413693547,
      "learning_rate": 4.470026884016805e-06,
      "loss": 0.0,
      "reward": 0.0,
      "reward_std": 0.0,
      "rewards/pot_combined_reward": 0.0,
      "step": 30
    },
    {
      "completion_length": 374.0,
      "epoch": 0.124,
      "grad_norm": 0.0019608919974416494,
      "kl": 0.0005961552087683231,
      "learning_rate": 4.415111107797445e-06,
      "loss": 0.0001,
      "reward": 0.0,
      "reward_std": 0.0,
      "rewards/pot_combined_reward": 0.0,
      "step": 31
    },
    {
      "completion_length": 372.0625,
      "epoch": 0.128,
      "grad_norm": 0.0015237935585901141,
      "kl": 0.0005326158570824191,
      "learning_rate": 4.357862063693486e-06,
      "loss": 0.0001,
      "reward": 0.0,
      "reward_std": 0.0,
      "rewards/pot_combined_reward": 0.0,
      "step": 32
    },
    {
      "completion_length": 374.0,
      "epoch": 0.132,
      "grad_norm": 0.002203061943873763,
      "kl": 0.0006071907628211193,
      "learning_rate": 4.2983495008466285e-06,
      "loss": 0.0001,
      "reward": 0.0,
      "reward_std": 0.0,
      "rewards/pot_combined_reward": 0.0,
      "step": 33
    },
    {
      "completion_length": 370.5,
      "epoch": 0.136,
      "grad_norm": 0.10126212984323502,
      "kl": 0.0006130525580374524,
      "learning_rate": 4.236645926147493e-06,
      "loss": 0.0001,
      "reward": 0.061249999329447746,
      "reward_std": 0.12249999865889549,
      "rewards/pot_combined_reward": 0.061249999329447746,
      "step": 34
    },
    {
      "completion_length": 374.0,
      "epoch": 0.14,
      "grad_norm": 0.08621055632829666,
      "kl": 0.0004927485424559563,
      "learning_rate": 4.172826515897146e-06,
      "loss": 0.0,
      "reward": 0.024966666474938393,
      "reward_std": 0.049933332949876785,
      "rewards/pot_combined_reward": 0.024966666474938393,
      "step": 35
    },
    {
      "completion_length": 374.0,
      "epoch": 0.144,
      "grad_norm": 0.0017127083847299218,
      "kl": 0.0005035524372942746,
      "learning_rate": 4.106969024216348e-06,
      "loss": 0.0001,
      "reward": 0.0,
      "reward_std": 0.0,
      "rewards/pot_combined_reward": 0.0,
      "step": 36
    },
    {
      "completion_length": 374.0,
      "epoch": 0.148,
      "grad_norm": 0.0018064226023852825,
      "kl": 0.0005530964990612119,
      "learning_rate": 4.039153688314146e-06,
      "loss": 0.0001,
      "reward": 0.0,
      "reward_std": 0.0,
      "rewards/pot_combined_reward": 0.0,
      "step": 37
    },
    {
      "completion_length": 373.8125,
      "epoch": 0.152,
      "grad_norm": 0.0019408023217692971,
      "kl": 0.0006417437689378858,
      "learning_rate": 3.969463130731183e-06,
      "loss": 0.0001,
      "reward": 0.0,
      "reward_std": 0.0,
      "rewards/pot_combined_reward": 0.0,
      "step": 38
    },
    {
      "completion_length": 374.0,
      "epoch": 0.156,
      "grad_norm": 0.08421237021684647,
      "kl": 0.0006241849769139662,
      "learning_rate": 3.897982258676867e-06,
      "loss": 0.0001,
      "reward": 0.07303333282470703,
      "reward_std": 0.057444244623184204,
      "rewards/pot_combined_reward": 0.07303333282470703,
      "step": 39
    },
    {
      "completion_length": 374.0,
      "epoch": 0.16,
      "grad_norm": 0.08112610131502151,
      "kl": 0.0005679467285517603,
      "learning_rate": 3.824798160583012e-06,
      "loss": 0.0001,
      "reward": 0.014233333058655262,
      "reward_std": 0.028466666117310524,
      "rewards/pot_combined_reward": 0.014233333058655262,
      "step": 40
    },
    {
      "completion_length": 374.0,
      "epoch": 0.164,
      "grad_norm": 0.001669050194323063,
      "kl": 0.0005617116403300315,
      "learning_rate": 3.7500000000000005e-06,
      "loss": 0.0001,
      "reward": 0.0,
      "reward_std": 0.0,
      "rewards/pot_combined_reward": 0.0,
      "step": 41
    },
    {
      "completion_length": 374.0,
      "epoch": 0.168,
      "grad_norm": 0.002355287317186594,
      "kl": 0.0006023006426403299,
      "learning_rate": 3.6736789069647273e-06,
      "loss": 0.0001,
      "reward": 0.0,
      "reward_std": 0.0,
      "rewards/pot_combined_reward": 0.0,
      "step": 42
    },
    {
      "completion_length": 328.8125,
      "epoch": 0.172,
      "grad_norm": 0.0023054229095578194,
      "kl": 0.0005200250307098031,
      "learning_rate": 3.595927866972694e-06,
      "loss": 0.0001,
      "reward": 0.0,
      "reward_std": 0.0,
      "rewards/pot_combined_reward": 0.0,
      "step": 43
    },
    {
      "completion_length": 374.0,
      "epoch": 0.176,
      "grad_norm": 0.11641528457403183,
      "kl": 0.0005873750924365595,
      "learning_rate": 3.516841607689501e-06,
      "loss": 0.0001,
      "reward": 0.07468749955296516,
      "reward_std": 0.14937499910593033,
      "rewards/pot_combined_reward": 0.07468749955296516,
      "step": 44
    },
    {
      "completion_length": 374.0,
      "epoch": 0.18,
      "grad_norm": 0.001737726735882461,
      "kl": 0.0005044558856752701,
      "learning_rate": 3.436516483539781e-06,
      "loss": 0.0001,
      "reward": 0.0,
      "reward_std": 0.0,
      "rewards/pot_combined_reward": 0.0,
      "step": 45
    },
    {
      "completion_length": 370.9375,
      "epoch": 0.184,
      "grad_norm": 0.0019563438836485147,
      "kl": 0.000592117925407365,
      "learning_rate": 3.3550503583141726e-06,
      "loss": 0.0001,
      "reward": 0.0,
      "reward_std": 0.0,
      "rewards/pot_combined_reward": 0.0,
      "step": 46
    },
    {
      "completion_length": 372.4375,
      "epoch": 0.188,
      "grad_norm": 0.0026125519070774317,
      "kl": 0.0005959889385849237,
      "learning_rate": 3.272542485937369e-06,
      "loss": 0.0001,
      "reward": 0.0,
      "reward_std": 0.0,
      "rewards/pot_combined_reward": 0.0,
      "step": 47
    },
    {
      "completion_length": 372.75,
      "epoch": 0.192,
      "grad_norm": 0.0820600688457489,
      "kl": 0.0005973696243017912,
      "learning_rate": 3.189093389542498e-06,
      "loss": 0.0001,
      "reward": 0.03968749940395355,
      "reward_std": 0.0793749988079071,
      "rewards/pot_combined_reward": 0.03968749940395355,
      "step": 48
    },
    {
      "completion_length": 374.0,
      "epoch": 0.196,
      "grad_norm": 0.06782057881355286,
      "kl": 0.0007923852826934308,
      "learning_rate": 3.1048047389991693e-06,
      "loss": 0.0001,
      "reward": 0.026249999180436134,
      "reward_std": 0.05249999836087227,
      "rewards/pot_combined_reward": 0.026249999180436134,
      "step": 49
    },
    {
      "completion_length": 374.0,
      "epoch": 0.2,
      "grad_norm": 0.10189752280712128,
      "kl": 0.0004997247888240963,
      "learning_rate": 3.019779227044398e-06,
      "loss": 0.0,
      "reward": 0.06999999843537807,
      "reward_std": 0.13999999687075615,
      "rewards/pot_combined_reward": 0.06999999843537807,
      "step": 50
    },
    {
      "completion_length": 374.0,
      "epoch": 0.204,
      "grad_norm": 0.004633176140487194,
      "kl": 0.0005932025596848689,
      "learning_rate": 2.9341204441673267e-06,
      "loss": 0.0001,
      "reward": 0.0,
      "reward_std": 0.0,
      "rewards/pot_combined_reward": 0.0,
      "step": 51
    },
    {
      "completion_length": 373.3125,
      "epoch": 0.208,
      "grad_norm": 0.0021235239692032337,
      "kl": 0.0006392140567186289,
      "learning_rate": 2.847932752400164e-06,
      "loss": 0.0001,
      "reward": 0.0,
      "reward_std": 0.0,
      "rewards/pot_combined_reward": 0.0,
      "step": 52
    },
    {
      "completion_length": 348.5,
      "epoch": 0.212,
      "grad_norm": 0.001950100064277649,
      "kl": 0.0006046331109246239,
      "learning_rate": 2.761321158169134e-06,
      "loss": 0.0001,
      "reward": 0.0,
      "reward_std": 0.0,
      "rewards/pot_combined_reward": 0.0,
      "step": 53
    },
    {
      "completion_length": 351.875,
      "epoch": 0.216,
      "grad_norm": 0.009500402957201004,
      "kl": 0.0005020819662604481,
      "learning_rate": 2.6743911843603134e-06,
      "loss": 0.0001,
      "reward": 0.0,
      "reward_std": 0.0,
      "rewards/pot_combined_reward": 0.0,
      "step": 54
    },
    {
      "completion_length": 374.0,
      "epoch": 0.22,
      "grad_norm": 0.001888828701339662,
      "kl": 0.0005405374467954971,
      "learning_rate": 2.587248741756253e-06,
      "loss": 0.0001,
      "reward": 0.0,
      "reward_std": 0.0,
      "rewards/pot_combined_reward": 0.0,
      "step": 55
    },
    {
      "completion_length": 371.125,
      "epoch": 0.224,
      "grad_norm": 0.10614389926195145,
      "kl": 0.0007851378031773493,
      "learning_rate": 2.5e-06,
      "loss": 0.0001,
      "reward": 0.18312916532158852,
      "reward_std": 0.27463946491479874,
      "rewards/pot_combined_reward": 0.18312916532158852,
      "step": 56
    },
    {
      "completion_length": 374.0,
      "epoch": 0.228,
      "grad_norm": 0.002482097828760743,
      "kl": 0.0006323368143057451,
      "learning_rate": 2.4127512582437486e-06,
      "loss": 0.0001,
      "reward": 0.0,
      "reward_std": 0.0,
      "rewards/pot_combined_reward": 0.0,
      "step": 57
    },
    {
      "completion_length": 374.0,
      "epoch": 0.232,
      "grad_norm": 0.0019110125722363591,
      "kl": 0.0005738867403124459,
      "learning_rate": 2.325608815639687e-06,
      "loss": 0.0001,
      "reward": 0.0,
      "reward_std": 0.0,
      "rewards/pot_combined_reward": 0.0,
      "step": 58
    },
    {
      "completion_length": 374.0,
      "epoch": 0.236,
      "grad_norm": 0.13201673328876495,
      "kl": 0.0008093079959508032,
      "learning_rate": 2.238678841830867e-06,
      "loss": 0.0001,
      "reward": 0.09951666742563248,
      "reward_std": 0.1495332196354866,
      "rewards/pot_combined_reward": 0.09951666742563248,
      "step": 59
    },
    {
      "completion_length": 373.75,
      "epoch": 0.24,
      "grad_norm": 0.10325703024864197,
      "kl": 0.0007794436533004045,
      "learning_rate": 2.1520672475998374e-06,
      "loss": 0.0001,
      "reward": 0.0652166660875082,
      "reward_std": 0.1304333321750164,
      "rewards/pot_combined_reward": 0.0652166660875082,
      "step": 60
    },
    {
      "completion_length": 374.0,
      "epoch": 0.244,
      "grad_norm": 0.07717566192150116,
      "kl": 0.0006568977987626567,
      "learning_rate": 2.0658795558326745e-06,
      "loss": 0.0001,
      "reward": 0.03968749940395355,
      "reward_std": 0.0793749988079071,
      "rewards/pot_combined_reward": 0.03968749940395355,
      "step": 61
    },
    {
      "completion_length": 373.0625,
      "epoch": 0.248,
      "grad_norm": 0.0719151571393013,
      "kl": 0.0006853110971860588,
      "learning_rate": 1.9802207729556023e-06,
      "loss": 0.0001,
      "reward": 0.026249999180436134,
      "reward_std": 0.05249999836087227,
      "rewards/pot_combined_reward": 0.026249999180436134,
      "step": 62
    },
    {
      "completion_length": 373.625,
      "epoch": 0.252,
      "grad_norm": 0.07498770952224731,
      "kl": 0.0007669057231396437,
      "learning_rate": 1.895195261000831e-06,
      "loss": 0.0001,
      "reward": 0.013883333653211594,
      "reward_std": 0.027766667306423187,
      "rewards/pot_combined_reward": 0.013883333653211594,
      "step": 63
    },
    {
      "completion_length": 372.375,
      "epoch": 0.256,
      "grad_norm": 0.0024490871001034975,
      "kl": 0.0007131954189389944,
      "learning_rate": 1.8109066104575023e-06,
      "loss": 0.0001,
      "reward": 0.0,
      "reward_std": 0.0,
      "rewards/pot_combined_reward": 0.0,
      "step": 64
    },
    {
      "completion_length": 374.0,
      "epoch": 0.26,
      "grad_norm": 0.09898767620325089,
      "kl": 0.0008127802575472742,
      "learning_rate": 1.7274575140626318e-06,
      "loss": 0.0001,
      "reward": 0.06544999964535236,
      "reward_std": 0.09778991341590881,
      "rewards/pot_combined_reward": 0.06544999964535236,
      "step": 65
    },
    {
      "completion_length": 374.0,
      "epoch": 0.264,
      "grad_norm": 0.08986019343137741,
      "kl": 0.000880417152075097,
      "learning_rate": 1.6449496416858285e-06,
      "loss": 0.0001,
      "reward": 0.04374999925494194,
      "reward_std": 0.08749999850988388,
      "rewards/pot_combined_reward": 0.04374999925494194,
      "step": 66
    },
    {
      "completion_length": 374.0,
      "epoch": 0.268,
      "grad_norm": 0.15933048725128174,
      "kl": 0.0012064649199601263,
      "learning_rate": 1.56348351646022e-06,
      "loss": 0.0001,
      "reward": 0.14419999904930592,
      "reward_std": 0.28839999809861183,
      "rewards/pot_combined_reward": 0.14419999904930592,
      "step": 67
    },
    {
      "completion_length": 366.875,
      "epoch": 0.272,
      "grad_norm": 0.0023835976608097553,
      "kl": 0.0007049251580610871,
      "learning_rate": 1.4831583923105e-06,
      "loss": 0.0001,
      "reward": 0.0,
      "reward_std": 0.0,
      "rewards/pot_combined_reward": 0.0,
      "step": 68
    },
    {
      "completion_length": 364.9375,
      "epoch": 0.276,
      "grad_norm": 0.07123439759016037,
      "kl": 0.0006189760897541419,
      "learning_rate": 1.4040721330273063e-06,
      "loss": 0.0001,
      "reward": 0.08187499642372131,
      "reward_std": 0.16374999284744263,
      "rewards/pot_combined_reward": 0.08187499642372131,
      "step": 69
    },
    {
      "completion_length": 371.6875,
      "epoch": 0.28,
      "grad_norm": 0.09466277807950974,
      "kl": 0.0009991034894483164,
      "learning_rate": 1.3263210930352737e-06,
      "loss": 0.0001,
      "reward": 0.1346083376556635,
      "reward_std": 0.2251959629356861,
      "rewards/pot_combined_reward": 0.1346083376556635,
      "step": 70
    },
    {
      "completion_length": 374.0,
      "epoch": 0.284,
      "grad_norm": 0.09791545569896698,
      "kl": 0.001197919569676742,
      "learning_rate": 1.2500000000000007e-06,
      "loss": 0.0001,
      "reward": 0.04223333299160004,
      "reward_std": 0.08446666970849037,
      "rewards/pot_combined_reward": 0.04223333299160004,
      "step": 71
    },
    {
      "completion_length": 373.5,
      "epoch": 0.288,
      "grad_norm": 0.09683706611394882,
      "kl": 0.001184802589705214,
      "learning_rate": 1.1752018394169882e-06,
      "loss": 0.0001,
      "reward": 0.05285000056028366,
      "reward_std": 0.10570000112056732,
      "rewards/pot_combined_reward": 0.05285000056028366,
      "step": 72
    },
    {
      "completion_length": 367.25,
      "epoch": 0.292,
      "grad_norm": 0.0033558327704668045,
      "kl": 0.0008135271054925397,
      "learning_rate": 1.1020177413231334e-06,
      "loss": 0.0001,
      "reward": 0.0,
      "reward_std": 0.0,
      "rewards/pot_combined_reward": 0.0,
      "step": 73
    },
    {
      "completion_length": 374.0,
      "epoch": 0.296,
      "grad_norm": 0.07025693356990814,
      "kl": 0.0007950128638185561,
      "learning_rate": 1.0305368692688175e-06,
      "loss": 0.0001,
      "reward": 0.04374999925494194,
      "reward_std": 0.08749999850988388,
      "rewards/pot_combined_reward": 0.04374999925494194,
      "step": 74
    },
    {
      "completion_length": 374.0,
      "epoch": 0.3,
      "grad_norm": 0.07400605827569962,
      "kl": 0.0009908084612106904,
      "learning_rate": 9.608463116858544e-07,
      "loss": 0.0001,
      "reward": 0.04339999705553055,
      "reward_std": 0.05020662397146225,
      "rewards/pot_combined_reward": 0.04339999705553055,
      "step": 75
    },
    {
      "completion_length": 374.0,
      "epoch": 0.304,
      "grad_norm": 0.09700194746255875,
      "kl": 0.0008199879812309518,
      "learning_rate": 8.930309757836517e-07,
      "loss": 0.0001,
      "reward": 0.061249999329447746,
      "reward_std": 0.12249999865889549,
      "rewards/pot_combined_reward": 0.061249999329447746,
      "step": 76
    },
    {
      "completion_length": 374.0,
      "epoch": 0.308,
      "grad_norm": 0.11501616984605789,
      "kl": 0.001101230038329959,
      "learning_rate": 8.271734841028553e-07,
      "loss": 0.0001,
      "reward": 0.12562499567866325,
      "reward_std": 0.2512499913573265,
      "rewards/pot_combined_reward": 0.12562499567866325,
      "step": 77
    },
    {
      "completion_length": 369.5,
      "epoch": 0.312,
      "grad_norm": 0.07562494277954102,
      "kl": 0.0013928793196100742,
      "learning_rate": 7.633540738525066e-07,
      "loss": 0.0001,
      "reward": 0.021816667169332504,
      "reward_std": 0.04363333433866501,
      "rewards/pot_combined_reward": 0.021816667169332504,
      "step": 78
    },
    {
      "completion_length": 374.0,
      "epoch": 0.316,
      "grad_norm": 0.0032410642597824335,
      "kl": 0.0008720912301214412,
      "learning_rate": 7.016504991533727e-07,
      "loss": 0.0001,
      "reward": 0.0,
      "reward_std": 0.0,
      "rewards/pot_combined_reward": 0.0,
      "step": 79
    },
    {
      "completion_length": 331.1875,
      "epoch": 0.32,
      "grad_norm": 0.004254704806953669,
      "kl": 0.0010208465537289158,
      "learning_rate": 6.421379363065142e-07,
      "loss": 0.0001,
      "reward": 0.0,
      "reward_std": 0.0,
      "rewards/pot_combined_reward": 0.0,
      "step": 80
    },
    {
      "completion_length": 373.75,
      "epoch": 0.324,
      "grad_norm": 0.002906290115788579,
      "kl": 0.0007839756435714662,
      "learning_rate": 5.848888922025553e-07,
      "loss": 0.0001,
      "reward": 0.0,
      "reward_std": 0.0,
      "rewards/pot_combined_reward": 0.0,
      "step": 81
    },
    {
      "completion_length": 374.0,
      "epoch": 0.328,
      "grad_norm": 0.13924577832221985,
      "kl": 0.001414620659488719,
      "learning_rate": 5.299731159831953e-07,
      "loss": 0.0001,
      "reward": 0.15825624577701092,
      "reward_std": 0.31651249155402184,
      "rewards/pot_combined_reward": 0.15825624577701092,
      "step": 82
    },
    {
      "completion_length": 374.0,
      "epoch": 0.332,
      "grad_norm": 0.14953076839447021,
      "kl": 0.0011789420095738024,
      "learning_rate": 4.774575140626317e-07,
      "loss": 0.0001,
      "reward": 0.1184374988079071,
      "reward_std": 0.2368749976158142,
      "rewards/pot_combined_reward": 0.1184374988079071,
      "step": 83
    },
    {
      "completion_length": 374.0,
      "epoch": 0.336,
      "grad_norm": 0.16725599765777588,
      "kl": 0.0009174157894449309,
      "learning_rate": 4.27406068612396e-07,
      "loss": 0.0001,
      "reward": 0.10500000044703484,
      "reward_std": 0.21000000089406967,
      "rewards/pot_combined_reward": 0.10500000044703484,
      "step": 84
    },
    {
      "completion_length": 370.6875,
      "epoch": 0.34,
      "grad_norm": 0.08203138411045074,
      "kl": 0.0009189353149849921,
      "learning_rate": 3.798797596089351e-07,
      "loss": 0.0001,
      "reward": 0.04374999925494194,
      "reward_std": 0.08749999850988388,
      "rewards/pot_combined_reward": 0.04374999925494194,
      "step": 85
    },
    {
      "completion_length": 371.5625,
      "epoch": 0.344,
      "grad_norm": 0.07274218648672104,
      "kl": 0.0008360931678907946,
      "learning_rate": 3.3493649053890325e-07,
      "loss": 0.0001,
      "reward": 0.08656249940395355,
      "reward_std": 0.1731249988079071,
      "rewards/pot_combined_reward": 0.08656249940395355,
      "step": 86
    },
    {
      "completion_length": 374.0,
      "epoch": 0.348,
      "grad_norm": 0.12336569279432297,
      "kl": 0.0012354136852081865,
      "learning_rate": 2.9263101785268253e-07,
      "loss": 0.0001,
      "reward": 0.09249166399240494,
      "reward_std": 0.18498332425951958,
      "rewards/pot_combined_reward": 0.09249166399240494,
      "step": 87
    },
    {
      "completion_length": 367.875,
      "epoch": 0.352,
      "grad_norm": 0.13889098167419434,
      "kl": 0.0017657574207987636,
      "learning_rate": 2.53014884252083e-07,
      "loss": 0.0002,
      "reward": 0.2926562614738941,
      "reward_std": 0.4413819834589958,
      "rewards/pot_combined_reward": 0.2926562614738941,
      "step": 88
    },
    {
      "completion_length": 374.0,
      "epoch": 0.356,
      "grad_norm": 0.06699243932962418,
      "kl": 0.001279524396522902,
      "learning_rate": 2.1613635589349756e-07,
      "loss": 0.0001,
      "reward": 0.08187499642372131,
      "reward_std": 0.16374999284744263,
      "rewards/pot_combined_reward": 0.08187499642372131,
      "step": 89
    },
    {
      "completion_length": 374.0,
      "epoch": 0.36,
      "grad_norm": 0.006427991669625044,
      "kl": 0.0013257948303362355,
      "learning_rate": 1.8204036358303173e-07,
      "loss": 0.0001,
      "reward": 0.0,
      "reward_std": 0.0,
      "rewards/pot_combined_reward": 0.0,
      "step": 90
    },
    {
      "completion_length": 370.9375,
      "epoch": 0.364,
      "grad_norm": 0.1104293167591095,
      "kl": 0.0018631000712048262,
      "learning_rate": 1.507684480352292e-07,
      "loss": 0.0002,
      "reward": 0.058799998834729195,
      "reward_std": 0.11759999766945839,
      "rewards/pot_combined_reward": 0.058799998834729195,
      "step": 91
    },
    {
      "completion_length": 361.9375,
      "epoch": 0.368,
      "grad_norm": 0.07179438322782516,
      "kl": 0.0009191952631226741,
      "learning_rate": 1.223587092621162e-07,
      "loss": 0.0001,
      "reward": 0.08343750238418579,
      "reward_std": 0.09881261736154556,
      "rewards/pot_combined_reward": 0.08343750238418579,
      "step": 92
    },
    {
      "completion_length": 374.0,
      "epoch": 0.372,
      "grad_norm": 0.06493149697780609,
      "kl": 0.0012784109567292035,
      "learning_rate": 9.684576015420277e-08,
      "loss": 0.0001,
      "reward": 0.11232500523328781,
      "reward_std": 0.17172931134700775,
      "rewards/pot_combined_reward": 0.11232500523328781,
      "step": 93
    },
    {
      "completion_length": 374.0,
      "epoch": 0.376,
      "grad_norm": 0.12131404131650925,
      "kl": 0.0012257406779099256,
      "learning_rate": 7.426068431000883e-08,
      "loss": 0.0001,
      "reward": 0.1303124949336052,
      "reward_std": 0.2606249898672104,
      "rewards/pot_combined_reward": 0.1303124949336052,
      "step": 94
    },
    {
      "completion_length": 368.0625,
      "epoch": 0.38,
      "grad_norm": 0.1013365238904953,
      "kl": 0.0013991060986882076,
      "learning_rate": 5.463099816548578e-08,
      "loss": 0.0001,
      "reward": 0.10476666688919067,
      "reward_std": 0.15946697443723679,
      "rewards/pot_combined_reward": 0.10476666688919067,
      "step": 95
    },
    {
      "completion_length": 374.0,
      "epoch": 0.384,
      "grad_norm": 0.06952964514493942,
      "kl": 0.0014077925588935614,
      "learning_rate": 3.798061746947995e-08,
      "loss": 0.0001,
      "reward": 0.11687499284744263,
      "reward_std": 0.1551528126001358,
      "rewards/pot_combined_reward": 0.11687499284744263,
      "step": 96
    },
    {
      "completion_length": 370.25,
      "epoch": 0.388,
      "grad_norm": 0.09735430032014847,
      "kl": 0.0009093381959246472,
      "learning_rate": 2.4329828146074096e-08,
      "loss": 0.0001,
      "reward": 0.026249999180436134,
      "reward_std": 0.05249999836087227,
      "rewards/pot_combined_reward": 0.026249999180436134,
      "step": 97
    },
    {
      "completion_length": 374.0,
      "epoch": 0.392,
      "grad_norm": 0.14300031960010529,
      "kl": 0.0015978575684130192,
      "learning_rate": 1.3695261579316776e-08,
      "loss": 0.0002,
      "reward": 0.23843749426305294,
      "reward_std": 0.33464543148875237,
      "rewards/pot_combined_reward": 0.23843749426305294,
      "step": 98
    },
    {
      "completion_length": 374.0,
      "epoch": 0.396,
      "grad_norm": 0.13475055992603302,
      "kl": 0.0017390053835697472,
      "learning_rate": 6.089874350439507e-09,
      "loss": 0.0002,
      "reward": 0.15921874903142452,
      "reward_std": 0.31843749806284904,
      "rewards/pot_combined_reward": 0.15921874903142452,
      "step": 99
    },
    {
      "completion_length": 374.0,
      "epoch": 0.4,
      "grad_norm": 0.07442972809076309,
      "kl": 0.0010832307452801615,
      "learning_rate": 1.5229324522605949e-09,
      "loss": 0.0001,
      "reward": 0.019833333790302277,
      "reward_std": 0.03966666758060455,
      "rewards/pot_combined_reward": 0.019833333790302277,
      "step": 100
    }
  ],
  "logging_steps": 1,
  "max_steps": 100,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 50,
  "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": 4,
  "trial_name": null,
  "trial_params": null
}