{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 1.0,
  "eval_steps": 500,
  "global_step": 69,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "clip_ratio": 0.0,
      "completion_length": 131.1875,
      "epoch": 0.014492753623188406,
      "grad_norm": 0.6139106154441833,
      "kl": 0.0,
      "learning_rate": 9.855072463768118e-06,
      "loss": 0.0,
      "reward": 2.4375,
      "reward_std": 0.5868084877729416,
      "rewards/format_reward_custom": 1.0,
      "rewards/high_level_action_reward": 0.625,
      "rewards/low_level_action_reward": 0.8125,
      "step": 1
    },
    {
      "clip_ratio": 0.0,
      "completion_length": 127.5625,
      "epoch": 0.028985507246376812,
      "grad_norm": 0.5722443461418152,
      "kl": 0.00024318695068359375,
      "learning_rate": 9.710144927536233e-06,
      "loss": 0.0,
      "reward": 2.5,
      "reward_std": 0.5239592343568802,
      "rewards/format_reward_custom": 1.0,
      "rewards/high_level_action_reward": 0.6875,
      "rewards/low_level_action_reward": 0.8125,
      "step": 2
    },
    {
      "clip_ratio": 0.0,
      "completion_length": 131.4375,
      "epoch": 0.043478260869565216,
      "grad_norm": 0.5824880003929138,
      "kl": 0.00020122528076171875,
      "learning_rate": 9.565217391304349e-06,
      "loss": 0.0,
      "reward": 2.65625,
      "reward_std": 0.2651650384068489,
      "rewards/format_reward_custom": 1.0,
      "rewards/high_level_action_reward": 0.71875,
      "rewards/low_level_action_reward": 0.9375,
      "step": 3
    },
    {
      "clip_ratio": 0.0,
      "completion_length": 118.6875,
      "epoch": 0.057971014492753624,
      "grad_norm": 0.36597952246665955,
      "kl": 0.00018024444580078125,
      "learning_rate": 9.420289855072464e-06,
      "loss": 0.0,
      "reward": 2.9375,
      "reward_std": 0.1157275140285492,
      "rewards/format_reward_custom": 1.0,
      "rewards/high_level_action_reward": 0.9375,
      "rewards/low_level_action_reward": 1.0,
      "step": 4
    },
    {
      "clip_ratio": 0.0,
      "completion_length": 152.5625,
      "epoch": 0.07246376811594203,
      "grad_norm": 0.6035860180854797,
      "kl": 0.0002532005310058594,
      "learning_rate": 9.275362318840581e-06,
      "loss": 0.0,
      "reward": 2.5625,
      "reward_std": 0.5609941333532333,
      "rewards/format_reward_custom": 1.0,
      "rewards/high_level_action_reward": 0.8125,
      "rewards/low_level_action_reward": 0.75,
      "step": 5
    },
    {
      "clip_ratio": 0.0,
      "completion_length": 127.4375,
      "epoch": 0.08695652173913043,
      "grad_norm": 0.6012734174728394,
      "kl": 0.00024127960205078125,
      "learning_rate": 9.130434782608697e-06,
      "loss": 0.0,
      "reward": 2.53125,
      "reward_std": 0.619232714176178,
      "rewards/format_reward_custom": 1.0,
      "rewards/high_level_action_reward": 0.84375,
      "rewards/low_level_action_reward": 0.6875,
      "step": 6
    },
    {
      "clip_ratio": 0.0,
      "completion_length": 144.125,
      "epoch": 0.10144927536231885,
      "grad_norm": 0.5445747375488281,
      "kl": 0.000244140625,
      "learning_rate": 8.985507246376812e-06,
      "loss": 0.0,
      "reward": 2.59375,
      "reward_std": 0.38138842582702637,
      "rewards/format_reward_custom": 1.0,
      "rewards/high_level_action_reward": 0.84375,
      "rewards/low_level_action_reward": 0.75,
      "step": 7
    },
    {
      "clip_ratio": 0.0,
      "completion_length": 129.375,
      "epoch": 0.11594202898550725,
      "grad_norm": 0.5511504411697388,
      "kl": 0.0002574920654296875,
      "learning_rate": 8.840579710144929e-06,
      "loss": 0.0,
      "reward": 2.5625,
      "reward_std": 0.4802234023809433,
      "rewards/format_reward_custom": 1.0,
      "rewards/high_level_action_reward": 0.75,
      "rewards/low_level_action_reward": 0.8125,
      "step": 8
    },
    {
      "clip_ratio": 0.0,
      "completion_length": 146.3125,
      "epoch": 0.13043478260869565,
      "grad_norm": 0.39530378580093384,
      "kl": 0.000354766845703125,
      "learning_rate": 8.695652173913044e-06,
      "loss": 0.0,
      "reward": 2.65625,
      "reward_std": 0.35197147727012634,
      "rewards/format_reward_custom": 1.0,
      "rewards/high_level_action_reward": 0.84375,
      "rewards/low_level_action_reward": 0.8125,
      "step": 9
    },
    {
      "clip_ratio": 0.0,
      "completion_length": 140.375,
      "epoch": 0.14492753623188406,
      "grad_norm": 0.6552218794822693,
      "kl": 0.0005092620849609375,
      "learning_rate": 8.55072463768116e-06,
      "loss": 0.0,
      "reward": 2.4375,
      "reward_std": 0.5546489059925079,
      "rewards/format_reward_custom": 1.0,
      "rewards/high_level_action_reward": 0.75,
      "rewards/low_level_action_reward": 0.6875,
      "step": 10
    },
    {
      "clip_ratio": 0.0,
      "completion_length": 133.8125,
      "epoch": 0.15942028985507245,
      "grad_norm": 0.5951517224311829,
      "kl": 0.00035858154296875,
      "learning_rate": 8.405797101449275e-06,
      "loss": 0.0,
      "reward": 2.78125,
      "reward_std": 0.3061639815568924,
      "rewards/format_reward_custom": 1.0,
      "rewards/high_level_action_reward": 0.84375,
      "rewards/low_level_action_reward": 0.9375,
      "step": 11
    },
    {
      "clip_ratio": 0.0,
      "completion_length": 135.3125,
      "epoch": 0.17391304347826086,
      "grad_norm": 0.5633934140205383,
      "kl": 0.0006542205810546875,
      "learning_rate": 8.260869565217392e-06,
      "loss": 0.0,
      "reward": 2.625,
      "reward_std": 0.2925042062997818,
      "rewards/format_reward_custom": 1.0,
      "rewards/high_level_action_reward": 0.8125,
      "rewards/low_level_action_reward": 0.8125,
      "step": 12
    },
    {
      "clip_ratio": 0.0,
      "completion_length": 123.5625,
      "epoch": 0.18840579710144928,
      "grad_norm": 0.6226204037666321,
      "kl": 0.0006656646728515625,
      "learning_rate": 8.115942028985508e-06,
      "loss": 0.0,
      "reward": 2.59375,
      "reward_std": 0.35564958304166794,
      "rewards/format_reward_custom": 1.0,
      "rewards/high_level_action_reward": 0.78125,
      "rewards/low_level_action_reward": 0.8125,
      "step": 13
    },
    {
      "clip_ratio": 0.0,
      "completion_length": 105.625,
      "epoch": 0.2028985507246377,
      "grad_norm": 0.6195806264877319,
      "kl": 0.000820159912109375,
      "learning_rate": 7.971014492753623e-06,
      "loss": 0.0,
      "reward": 2.0,
      "reward_std": 0.26726123690605164,
      "rewards/format_reward_custom": 1.0,
      "rewards/high_level_action_reward": 0.5,
      "rewards/low_level_action_reward": 0.5,
      "step": 14
    },
    {
      "clip_ratio": 0.0,
      "completion_length": 125.1875,
      "epoch": 0.21739130434782608,
      "grad_norm": 0.6649656891822815,
      "kl": 0.000728607177734375,
      "learning_rate": 7.82608695652174e-06,
      "loss": 0.0,
      "reward": 2.625,
      "reward_std": 0.5720614045858383,
      "rewards/format_reward_custom": 1.0,
      "rewards/high_level_action_reward": 0.8125,
      "rewards/low_level_action_reward": 0.8125,
      "step": 15
    },
    {
      "clip_ratio": 0.0,
      "completion_length": 133.9375,
      "epoch": 0.2318840579710145,
      "grad_norm": 0.5864853262901306,
      "kl": 0.000736236572265625,
      "learning_rate": 7.681159420289856e-06,
      "loss": 0.0,
      "reward": 2.4375,
      "reward_std": 0.5585024058818817,
      "rewards/format_reward_custom": 1.0,
      "rewards/high_level_action_reward": 0.8125,
      "rewards/low_level_action_reward": 0.625,
      "step": 16
    },
    {
      "clip_ratio": 0.0,
      "completion_length": 134.5,
      "epoch": 0.2463768115942029,
      "grad_norm": 0.6138740181922913,
      "kl": 0.0010128021240234375,
      "learning_rate": 7.536231884057972e-06,
      "loss": 0.0,
      "reward": 2.5,
      "reward_std": 0.5500157475471497,
      "rewards/format_reward_custom": 1.0,
      "rewards/high_level_action_reward": 0.6875,
      "rewards/low_level_action_reward": 0.8125,
      "step": 17
    },
    {
      "clip_ratio": 0.0,
      "completion_length": 121.875,
      "epoch": 0.2608695652173913,
      "grad_norm": 0.5959410667419434,
      "kl": 0.001262664794921875,
      "learning_rate": 7.391304347826087e-06,
      "loss": 0.0001,
      "reward": 2.8125,
      "reward_std": 0.31539323925971985,
      "rewards/format_reward_custom": 1.0,
      "rewards/high_level_action_reward": 0.875,
      "rewards/low_level_action_reward": 0.9375,
      "step": 18
    },
    {
      "clip_ratio": 0.0,
      "completion_length": 141.375,
      "epoch": 0.2753623188405797,
      "grad_norm": 0.5705474615097046,
      "kl": 0.001049041748046875,
      "learning_rate": 7.246376811594203e-06,
      "loss": 0.0,
      "reward": 2.28125,
      "reward_std": 0.6677263081073761,
      "rewards/format_reward_custom": 1.0,
      "rewards/high_level_action_reward": 0.84375,
      "rewards/low_level_action_reward": 0.4375,
      "step": 19
    },
    {
      "clip_ratio": 0.0,
      "completion_length": 135.5625,
      "epoch": 0.2898550724637681,
      "grad_norm": 0.43123292922973633,
      "kl": 0.001407623291015625,
      "learning_rate": 7.10144927536232e-06,
      "loss": 0.0001,
      "reward": 2.90625,
      "reward_std": 0.18600594997406006,
      "rewards/format_reward_custom": 1.0,
      "rewards/high_level_action_reward": 0.96875,
      "rewards/low_level_action_reward": 0.9375,
      "step": 20
    },
    {
      "clip_ratio": 0.0,
      "completion_length": 122.0,
      "epoch": 0.30434782608695654,
      "grad_norm": 0.6939437985420227,
      "kl": 0.001312255859375,
      "learning_rate": 6.956521739130435e-06,
      "loss": 0.0001,
      "reward": 2.625,
      "reward_std": 0.39837799966335297,
      "rewards/format_reward_custom": 1.0,
      "rewards/high_level_action_reward": 0.8125,
      "rewards/low_level_action_reward": 0.8125,
      "step": 21
    },
    {
      "clip_ratio": 0.0,
      "completion_length": 118.3125,
      "epoch": 0.3188405797101449,
      "grad_norm": 0.6187354326248169,
      "kl": 0.00099945068359375,
      "learning_rate": 6.811594202898551e-06,
      "loss": 0.0,
      "reward": 2.90625,
      "reward_std": 0.2651650384068489,
      "rewards/format_reward_custom": 1.0,
      "rewards/high_level_action_reward": 0.96875,
      "rewards/low_level_action_reward": 0.9375,
      "step": 22
    },
    {
      "clip_ratio": 0.0,
      "completion_length": 137.125,
      "epoch": 0.3333333333333333,
      "grad_norm": 0.619391143321991,
      "kl": 0.00128173828125,
      "learning_rate": 6.666666666666667e-06,
      "loss": 0.0001,
      "reward": 2.53125,
      "reward_std": 0.3966485261917114,
      "rewards/format_reward_custom": 1.0,
      "rewards/high_level_action_reward": 0.65625,
      "rewards/low_level_action_reward": 0.875,
      "step": 23
    },
    {
      "clip_ratio": 0.0,
      "completion_length": 113.375,
      "epoch": 0.34782608695652173,
      "grad_norm": 0.6596890687942505,
      "kl": 0.001399993896484375,
      "learning_rate": 6.521739130434783e-06,
      "loss": 0.0001,
      "reward": 2.75,
      "reward_std": 0.32261285185813904,
      "rewards/format_reward_custom": 1.0,
      "rewards/high_level_action_reward": 0.75,
      "rewards/low_level_action_reward": 1.0,
      "step": 24
    },
    {
      "clip_ratio": 0.0,
      "completion_length": 132.6875,
      "epoch": 0.36231884057971014,
      "grad_norm": 0.6133448481559753,
      "kl": 0.0009860992431640625,
      "learning_rate": 6.376811594202898e-06,
      "loss": 0.0,
      "reward": 2.8125,
      "reward_std": 0.45117098093032837,
      "rewards/format_reward_custom": 1.0,
      "rewards/high_level_action_reward": 0.9375,
      "rewards/low_level_action_reward": 0.875,
      "step": 25
    },
    {
      "clip_ratio": 0.0,
      "completion_length": 149.1875,
      "epoch": 0.37681159420289856,
      "grad_norm": 0.6592795848846436,
      "kl": 0.00177764892578125,
      "learning_rate": 6.2318840579710145e-06,
      "loss": 0.0001,
      "reward": 2.59375,
      "reward_std": 0.6028470396995544,
      "rewards/format_reward_custom": 0.9375,
      "rewards/high_level_action_reward": 0.84375,
      "rewards/low_level_action_reward": 0.8125,
      "step": 26
    },
    {
      "clip_ratio": 0.0,
      "completion_length": 129.6875,
      "epoch": 0.391304347826087,
      "grad_norm": 0.5780444145202637,
      "kl": 0.00179290771484375,
      "learning_rate": 6.086956521739132e-06,
      "loss": 0.0001,
      "reward": 2.75,
      "reward_std": 0.35841864347457886,
      "rewards/format_reward_custom": 1.0,
      "rewards/high_level_action_reward": 0.875,
      "rewards/low_level_action_reward": 0.875,
      "step": 27
    },
    {
      "clip_ratio": 0.0,
      "completion_length": 122.4375,
      "epoch": 0.4057971014492754,
      "grad_norm": 0.004627756774425507,
      "kl": 0.00113677978515625,
      "learning_rate": 5.942028985507247e-06,
      "loss": 0.0,
      "reward": 3.0,
      "reward_std": 0.0,
      "rewards/format_reward_custom": 1.0,
      "rewards/high_level_action_reward": 1.0,
      "rewards/low_level_action_reward": 1.0,
      "step": 28
    },
    {
      "clip_ratio": 0.0,
      "completion_length": 141.0625,
      "epoch": 0.42028985507246375,
      "grad_norm": 0.5492585301399231,
      "kl": 0.001590728759765625,
      "learning_rate": 5.797101449275363e-06,
      "loss": 0.0001,
      "reward": 2.78125,
      "reward_std": 0.2630179077386856,
      "rewards/format_reward_custom": 1.0,
      "rewards/high_level_action_reward": 0.78125,
      "rewards/low_level_action_reward": 1.0,
      "step": 29
    },
    {
      "clip_ratio": 0.0,
      "completion_length": 141.0,
      "epoch": 0.43478260869565216,
      "grad_norm": 0.5583959221839905,
      "kl": 0.002197265625,
      "learning_rate": 5.652173913043479e-06,
      "loss": 0.0001,
      "reward": 2.34375,
      "reward_std": 0.38138842582702637,
      "rewards/format_reward_custom": 1.0,
      "rewards/high_level_action_reward": 0.65625,
      "rewards/low_level_action_reward": 0.6875,
      "step": 30
    },
    {
      "clip_ratio": 0.0,
      "completion_length": 132.8125,
      "epoch": 0.4492753623188406,
      "grad_norm": 0.5492476224899292,
      "kl": 0.002262115478515625,
      "learning_rate": 5.507246376811595e-06,
      "loss": 0.0001,
      "reward": 2.4375,
      "reward_std": 0.5260358154773712,
      "rewards/format_reward_custom": 1.0,
      "rewards/high_level_action_reward": 0.875,
      "rewards/low_level_action_reward": 0.5625,
      "step": 31
    },
    {
      "clip_ratio": 0.0,
      "completion_length": 138.875,
      "epoch": 0.463768115942029,
      "grad_norm": 0.5487068891525269,
      "kl": 0.00237274169921875,
      "learning_rate": 5.362318840579711e-06,
      "loss": 0.0001,
      "reward": 2.59375,
      "reward_std": 0.34475886821746826,
      "rewards/format_reward_custom": 1.0,
      "rewards/high_level_action_reward": 0.78125,
      "rewards/low_level_action_reward": 0.8125,
      "step": 32
    },
    {
      "clip_ratio": 0.0,
      "completion_length": 142.875,
      "epoch": 0.4782608695652174,
      "grad_norm": 0.5532354712486267,
      "kl": 0.001415252685546875,
      "learning_rate": 5.2173913043478265e-06,
      "loss": 0.0001,
      "reward": 2.65625,
      "reward_std": 0.35098859667778015,
      "rewards/format_reward_custom": 1.0,
      "rewards/high_level_action_reward": 0.71875,
      "rewards/low_level_action_reward": 0.9375,
      "step": 33
    },
    {
      "clip_ratio": 0.0,
      "completion_length": 124.75,
      "epoch": 0.4927536231884058,
      "grad_norm": 0.5815756916999817,
      "kl": 0.00170135498046875,
      "learning_rate": 5.072463768115943e-06,
      "loss": 0.0001,
      "reward": 2.75,
      "reward_std": 0.39837799966335297,
      "rewards/format_reward_custom": 1.0,
      "rewards/high_level_action_reward": 0.9375,
      "rewards/low_level_action_reward": 0.8125,
      "step": 34
    },
    {
      "clip_ratio": 0.0,
      "completion_length": 114.4375,
      "epoch": 0.5072463768115942,
      "grad_norm": 0.6308125257492065,
      "kl": 0.0013580322265625,
      "learning_rate": 4.927536231884059e-06,
      "loss": 0.0001,
      "reward": 2.625,
      "reward_std": 0.3535533770918846,
      "rewards/format_reward_custom": 1.0,
      "rewards/high_level_action_reward": 0.875,
      "rewards/low_level_action_reward": 0.75,
      "step": 35
    },
    {
      "clip_ratio": 0.0,
      "completion_length": 148.625,
      "epoch": 0.5217391304347826,
      "grad_norm": 0.5474228858947754,
      "kl": 0.00164031982421875,
      "learning_rate": 4.782608695652174e-06,
      "loss": 0.0001,
      "reward": 2.625,
      "reward_std": 0.4355512708425522,
      "rewards/format_reward_custom": 1.0,
      "rewards/high_level_action_reward": 0.875,
      "rewards/low_level_action_reward": 0.75,
      "step": 36
    },
    {
      "clip_ratio": 0.0,
      "completion_length": 124.75,
      "epoch": 0.5362318840579711,
      "grad_norm": 0.46679696440696716,
      "kl": 0.002105712890625,
      "learning_rate": 4.637681159420291e-06,
      "loss": 0.0001,
      "reward": 2.78125,
      "reward_std": 0.33905068039894104,
      "rewards/format_reward_custom": 1.0,
      "rewards/high_level_action_reward": 0.90625,
      "rewards/low_level_action_reward": 0.875,
      "step": 37
    },
    {
      "clip_ratio": 0.0,
      "completion_length": 131.125,
      "epoch": 0.5507246376811594,
      "grad_norm": 0.6113550662994385,
      "kl": 0.002593994140625,
      "learning_rate": 4.492753623188406e-06,
      "loss": 0.0001,
      "reward": 2.78125,
      "reward_std": 0.3749881833791733,
      "rewards/format_reward_custom": 1.0,
      "rewards/high_level_action_reward": 0.90625,
      "rewards/low_level_action_reward": 0.875,
      "step": 38
    },
    {
      "clip_ratio": 0.0,
      "completion_length": 132.25,
      "epoch": 0.5652173913043478,
      "grad_norm": 0.6611613035202026,
      "kl": 0.00252532958984375,
      "learning_rate": 4.347826086956522e-06,
      "loss": 0.0001,
      "reward": 2.625,
      "reward_std": 0.5487885922193527,
      "rewards/format_reward_custom": 1.0,
      "rewards/high_level_action_reward": 0.75,
      "rewards/low_level_action_reward": 0.875,
      "step": 39
    },
    {
      "clip_ratio": 0.0,
      "completion_length": 115.5,
      "epoch": 0.5797101449275363,
      "grad_norm": 0.6072784662246704,
      "kl": 0.002056121826171875,
      "learning_rate": 4.202898550724638e-06,
      "loss": 0.0001,
      "reward": 2.84375,
      "reward_std": 0.3808925449848175,
      "rewards/format_reward_custom": 1.0,
      "rewards/high_level_action_reward": 0.90625,
      "rewards/low_level_action_reward": 0.9375,
      "step": 40
    },
    {
      "clip_ratio": 0.0,
      "completion_length": 129.875,
      "epoch": 0.5942028985507246,
      "grad_norm": 0.5880132913589478,
      "kl": 0.0030670166015625,
      "learning_rate": 4.057971014492754e-06,
      "loss": 0.0001,
      "reward": 2.65625,
      "reward_std": 0.3966485261917114,
      "rewards/format_reward_custom": 1.0,
      "rewards/high_level_action_reward": 0.78125,
      "rewards/low_level_action_reward": 0.875,
      "step": 41
    },
    {
      "clip_ratio": 0.0,
      "completion_length": 120.75,
      "epoch": 0.6086956521739131,
      "grad_norm": 0.6412323117256165,
      "kl": 0.0033416748046875,
      "learning_rate": 3.91304347826087e-06,
      "loss": 0.0001,
      "reward": 2.21875,
      "reward_std": 0.3818188011646271,
      "rewards/format_reward_custom": 1.0,
      "rewards/high_level_action_reward": 0.59375,
      "rewards/low_level_action_reward": 0.625,
      "step": 42
    },
    {
      "clip_ratio": 0.0,
      "completion_length": 131.3125,
      "epoch": 0.6231884057971014,
      "grad_norm": 0.6180394887924194,
      "kl": 0.00208282470703125,
      "learning_rate": 3.768115942028986e-06,
      "loss": 0.0001,
      "reward": 2.65625,
      "reward_std": 0.5133327841758728,
      "rewards/format_reward_custom": 1.0,
      "rewards/high_level_action_reward": 0.84375,
      "rewards/low_level_action_reward": 0.8125,
      "step": 43
    },
    {
      "clip_ratio": 0.0,
      "completion_length": 128.5625,
      "epoch": 0.6376811594202898,
      "grad_norm": 0.6940774917602539,
      "kl": 0.002685546875,
      "learning_rate": 3.6231884057971017e-06,
      "loss": 0.0001,
      "reward": 2.625,
      "reward_std": 0.44099316000938416,
      "rewards/format_reward_custom": 0.9375,
      "rewards/high_level_action_reward": 0.875,
      "rewards/low_level_action_reward": 0.8125,
      "step": 44
    },
    {
      "clip_ratio": 0.0,
      "completion_length": 126.6875,
      "epoch": 0.6521739130434783,
      "grad_norm": 0.6032717227935791,
      "kl": 0.00244140625,
      "learning_rate": 3.4782608695652175e-06,
      "loss": 0.0001,
      "reward": 2.65625,
      "reward_std": 0.5762138962745667,
      "rewards/format_reward_custom": 1.0,
      "rewards/high_level_action_reward": 0.84375,
      "rewards/low_level_action_reward": 0.8125,
      "step": 45
    },
    {
      "clip_ratio": 0.0,
      "completion_length": 137.25,
      "epoch": 0.6666666666666666,
      "grad_norm": 0.3984113335609436,
      "kl": 0.001659393310546875,
      "learning_rate": 3.3333333333333333e-06,
      "loss": 0.0001,
      "reward": 2.84375,
      "reward_std": 0.2651650309562683,
      "rewards/format_reward_custom": 1.0,
      "rewards/high_level_action_reward": 0.90625,
      "rewards/low_level_action_reward": 0.9375,
      "step": 46
    },
    {
      "clip_ratio": 0.0,
      "completion_length": 134.3125,
      "epoch": 0.6811594202898551,
      "grad_norm": 0.37174344062805176,
      "kl": 0.003200531005859375,
      "learning_rate": 3.188405797101449e-06,
      "loss": 0.0001,
      "reward": 2.875,
      "reward_std": 0.13363061845302582,
      "rewards/format_reward_custom": 1.0,
      "rewards/high_level_action_reward": 0.875,
      "rewards/low_level_action_reward": 1.0,
      "step": 47
    },
    {
      "clip_ratio": 0.0,
      "completion_length": 113.625,
      "epoch": 0.6956521739130435,
      "grad_norm": 0.6417880654335022,
      "kl": 0.0034027099609375,
      "learning_rate": 3.043478260869566e-06,
      "loss": 0.0001,
      "reward": 2.125,
      "reward_std": 0.5175491571426392,
      "rewards/format_reward_custom": 1.0,
      "rewards/high_level_action_reward": 0.5,
      "rewards/low_level_action_reward": 0.625,
      "step": 48
    },
    {
      "clip_ratio": 0.0,
      "completion_length": 120.875,
      "epoch": 0.7101449275362319,
      "grad_norm": 0.3155536353588104,
      "kl": 0.003082275390625,
      "learning_rate": 2.8985507246376816e-06,
      "loss": 0.0001,
      "reward": 2.84375,
      "reward_std": 0.18600594997406006,
      "rewards/format_reward_custom": 1.0,
      "rewards/high_level_action_reward": 0.90625,
      "rewards/low_level_action_reward": 0.9375,
      "step": 49
    },
    {
      "clip_ratio": 0.0,
      "completion_length": 133.3125,
      "epoch": 0.7246376811594203,
      "grad_norm": 0.6605053544044495,
      "kl": 0.00164031982421875,
      "learning_rate": 2.7536231884057974e-06,
      "loss": 0.0001,
      "reward": 2.65625,
      "reward_std": 0.36348532140254974,
      "rewards/format_reward_custom": 1.0,
      "rewards/high_level_action_reward": 0.78125,
      "rewards/low_level_action_reward": 0.875,
      "step": 50
    },
    {
      "clip_ratio": 0.0,
      "completion_length": 141.9375,
      "epoch": 0.7391304347826086,
      "grad_norm": 0.5570524334907532,
      "kl": 0.002655029296875,
      "learning_rate": 2.6086956521739132e-06,
      "loss": 0.0001,
      "reward": 2.59375,
      "reward_std": 0.7191916108131409,
      "rewards/format_reward_custom": 1.0,
      "rewards/high_level_action_reward": 0.78125,
      "rewards/low_level_action_reward": 0.8125,
      "step": 51
    },
    {
      "clip_ratio": 0.0,
      "completion_length": 141.1875,
      "epoch": 0.7536231884057971,
      "grad_norm": 0.4170561730861664,
      "kl": 0.001430511474609375,
      "learning_rate": 2.4637681159420295e-06,
      "loss": 0.0001,
      "reward": 2.90625,
      "reward_std": 0.1293872892856598,
      "rewards/format_reward_custom": 1.0,
      "rewards/high_level_action_reward": 0.90625,
      "rewards/low_level_action_reward": 1.0,
      "step": 52
    },
    {
      "clip_ratio": 0.0,
      "completion_length": 121.5625,
      "epoch": 0.7681159420289855,
      "grad_norm": 0.6030449867248535,
      "kl": 0.0033111572265625,
      "learning_rate": 2.3188405797101453e-06,
      "loss": 0.0001,
      "reward": 2.212499976158142,
      "reward_std": 0.46406444907188416,
      "rewards/format_reward_custom": 1.0,
      "rewards/high_level_action_reward": 0.5250000059604645,
      "rewards/low_level_action_reward": 0.6875,
      "step": 53
    },
    {
      "clip_ratio": 0.0,
      "completion_length": 130.0625,
      "epoch": 0.782608695652174,
      "grad_norm": 0.40535715222358704,
      "kl": 0.001888275146484375,
      "learning_rate": 2.173913043478261e-06,
      "loss": 0.0001,
      "reward": 2.90625,
      "reward_std": 0.1293872892856598,
      "rewards/format_reward_custom": 1.0,
      "rewards/high_level_action_reward": 0.90625,
      "rewards/low_level_action_reward": 1.0,
      "step": 54
    },
    {
      "clip_ratio": 0.0,
      "completion_length": 133.25,
      "epoch": 0.7971014492753623,
      "grad_norm": 0.5601004958152771,
      "kl": 0.00250244140625,
      "learning_rate": 2.028985507246377e-06,
      "loss": 0.0001,
      "reward": 2.5,
      "reward_std": 0.5945880711078644,
      "rewards/format_reward_custom": 1.0,
      "rewards/high_level_action_reward": 0.8125,
      "rewards/low_level_action_reward": 0.6875,
      "step": 55
    },
    {
      "clip_ratio": 0.0,
      "completion_length": 123.3125,
      "epoch": 0.8115942028985508,
      "grad_norm": 0.6125327348709106,
      "kl": 0.00266265869140625,
      "learning_rate": 1.884057971014493e-06,
      "loss": 0.0001,
      "reward": 2.625,
      "reward_std": 0.3380180299282074,
      "rewards/format_reward_custom": 1.0,
      "rewards/high_level_action_reward": 0.75,
      "rewards/low_level_action_reward": 0.875,
      "step": 56
    },
    {
      "clip_ratio": 0.0,
      "completion_length": 139.875,
      "epoch": 0.8260869565217391,
      "grad_norm": 0.525627613067627,
      "kl": 0.002033233642578125,
      "learning_rate": 1.7391304347826088e-06,
      "loss": 0.0001,
      "reward": 2.65625,
      "reward_std": 0.5649385899305344,
      "rewards/format_reward_custom": 0.9375,
      "rewards/high_level_action_reward": 0.84375,
      "rewards/low_level_action_reward": 0.875,
      "step": 57
    },
    {
      "clip_ratio": 0.0,
      "completion_length": 121.0,
      "epoch": 0.8405797101449275,
      "grad_norm": 0.6244301795959473,
      "kl": 0.0027923583984375,
      "learning_rate": 1.5942028985507246e-06,
      "loss": 0.0001,
      "reward": 2.875,
      "reward_std": 0.27439429610967636,
      "rewards/format_reward_custom": 1.0,
      "rewards/high_level_action_reward": 0.9375,
      "rewards/low_level_action_reward": 0.9375,
      "step": 58
    },
    {
      "clip_ratio": 0.0,
      "completion_length": 134.6875,
      "epoch": 0.855072463768116,
      "grad_norm": 0.6077686548233032,
      "kl": 0.0023651123046875,
      "learning_rate": 1.4492753623188408e-06,
      "loss": 0.0001,
      "reward": 2.5,
      "reward_std": 0.42632102966308594,
      "rewards/format_reward_custom": 1.0,
      "rewards/high_level_action_reward": 0.8125,
      "rewards/low_level_action_reward": 0.6875,
      "step": 59
    },
    {
      "clip_ratio": 0.0,
      "completion_length": 129.125,
      "epoch": 0.8695652173913043,
      "grad_norm": 0.549598217010498,
      "kl": 0.001483917236328125,
      "learning_rate": 1.3043478260869566e-06,
      "loss": 0.0001,
      "reward": 2.6875,
      "reward_std": 0.4150373041629791,
      "rewards/format_reward_custom": 1.0,
      "rewards/high_level_action_reward": 0.875,
      "rewards/low_level_action_reward": 0.8125,
      "step": 60
    },
    {
      "clip_ratio": 0.0,
      "completion_length": 132.0625,
      "epoch": 0.8840579710144928,
      "grad_norm": 0.3656002879142761,
      "kl": 0.00152587890625,
      "learning_rate": 1.1594202898550726e-06,
      "loss": 0.0001,
      "reward": 2.837499976158142,
      "reward_std": 0.18077217042446136,
      "rewards/format_reward_custom": 1.0,
      "rewards/high_level_action_reward": 0.9000000059604645,
      "rewards/low_level_action_reward": 0.9375,
      "step": 61
    },
    {
      "clip_ratio": 0.0,
      "completion_length": 150.25,
      "epoch": 0.8985507246376812,
      "grad_norm": 0.5994426012039185,
      "kl": 0.0025482177734375,
      "learning_rate": 1.0144927536231885e-06,
      "loss": 0.0001,
      "reward": 2.71875,
      "reward_std": 0.36348532140254974,
      "rewards/format_reward_custom": 1.0,
      "rewards/high_level_action_reward": 0.84375,
      "rewards/low_level_action_reward": 0.875,
      "step": 62
    },
    {
      "clip_ratio": 0.0,
      "completion_length": 121.3125,
      "epoch": 0.9130434782608695,
      "grad_norm": 0.6515089273452759,
      "kl": 0.0019683837890625,
      "learning_rate": 8.695652173913044e-07,
      "loss": 0.0001,
      "reward": 2.21875,
      "reward_std": 0.4966200590133667,
      "rewards/format_reward_custom": 1.0,
      "rewards/high_level_action_reward": 0.65625,
      "rewards/low_level_action_reward": 0.5625,
      "step": 63
    },
    {
      "clip_ratio": 0.0,
      "completion_length": 124.625,
      "epoch": 0.927536231884058,
      "grad_norm": 0.6351967453956604,
      "kl": 0.002838134765625,
      "learning_rate": 7.246376811594204e-07,
      "loss": 0.0001,
      "reward": 2.78125,
      "reward_std": 0.3808925449848175,
      "rewards/format_reward_custom": 1.0,
      "rewards/high_level_action_reward": 0.84375,
      "rewards/low_level_action_reward": 0.9375,
      "step": 64
    },
    {
      "clip_ratio": 0.0,
      "completion_length": 121.6875,
      "epoch": 0.9420289855072463,
      "grad_norm": 0.6020182967185974,
      "kl": 0.001895904541015625,
      "learning_rate": 5.797101449275363e-07,
      "loss": 0.0001,
      "reward": 2.8125,
      "reward_std": 0.3535533770918846,
      "rewards/format_reward_custom": 0.9375,
      "rewards/high_level_action_reward": 0.875,
      "rewards/low_level_action_reward": 1.0,
      "step": 65
    },
    {
      "clip_ratio": 0.0,
      "completion_length": 125.0,
      "epoch": 0.9565217391304348,
      "grad_norm": 0.6860438585281372,
      "kl": 0.00278472900390625,
      "learning_rate": 4.347826086956522e-07,
      "loss": 0.0001,
      "reward": 2.65625,
      "reward_std": 0.2651650384068489,
      "rewards/format_reward_custom": 1.0,
      "rewards/high_level_action_reward": 0.71875,
      "rewards/low_level_action_reward": 0.9375,
      "step": 66
    },
    {
      "clip_ratio": 0.0,
      "completion_length": 123.875,
      "epoch": 0.9710144927536232,
      "grad_norm": 0.587708592414856,
      "kl": 0.003173828125,
      "learning_rate": 2.8985507246376816e-07,
      "loss": 0.0001,
      "reward": 2.625,
      "reward_std": 0.2925042062997818,
      "rewards/format_reward_custom": 1.0,
      "rewards/high_level_action_reward": 0.8125,
      "rewards/low_level_action_reward": 0.8125,
      "step": 67
    },
    {
      "clip_ratio": 0.0,
      "completion_length": 131.125,
      "epoch": 0.9855072463768116,
      "grad_norm": 0.5342994928359985,
      "kl": 0.002532958984375,
      "learning_rate": 1.4492753623188408e-07,
      "loss": 0.0001,
      "reward": 2.71875,
      "reward_std": 0.4419417232275009,
      "rewards/format_reward_custom": 1.0,
      "rewards/high_level_action_reward": 0.84375,
      "rewards/low_level_action_reward": 0.875,
      "step": 68
    },
    {
      "clip_ratio": 0.0,
      "completion_length": 122.875,
      "epoch": 1.0,
      "grad_norm": 0.43572136759757996,
      "kl": 0.00244140625,
      "learning_rate": 0.0,
      "loss": 0.0001,
      "reward": 2.875,
      "reward_std": 0.13363061845302582,
      "rewards/format_reward_custom": 1.0,
      "rewards/high_level_action_reward": 0.875,
      "rewards/low_level_action_reward": 1.0,
      "step": 69
    }
  ],
  "logging_steps": 1.0,
  "max_steps": 69,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 2,
  "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
}