{
  "best_global_step": null,
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 2.0,
  "eval_steps": 500,
  "global_step": 500,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "clip_ratio": 0.0,
      "completion_length": 240.75,
      "epoch": 0.004,
      "grad_norm": 3.483977794647217,
      "kl": 0.0011882781982421875,
      "learning_rate": 9.996e-07,
      "loss": 0.0,
      "reward": 0.0625,
      "reward_std": 0.1767766922712326,
      "rewards/format_reward": 0.0,
      "rewards/score_reward": 0.0625,
      "step": 1
    },
    {
      "clip_ratio": 0.0,
      "completion_length": 244.59375,
      "epoch": 0.008,
      "grad_norm": 0.001067359815351665,
      "kl": 0.001041412353515625,
      "learning_rate": 9.992e-07,
      "loss": 0.0,
      "reward": 0.0,
      "reward_std": 0.0,
      "rewards/format_reward": 0.0,
      "rewards/score_reward": 0.0,
      "step": 2
    },
    {
      "clip_ratio": 0.0,
      "completion_length": 246.375,
      "epoch": 0.012,
      "grad_norm": 0.003222062485292554,
      "kl": 0.001255035400390625,
      "learning_rate": 9.988e-07,
      "loss": 0.0,
      "reward": 0.0,
      "reward_std": 0.0,
      "rewards/format_reward": 0.0,
      "rewards/score_reward": 0.0,
      "step": 3
    },
    {
      "clip_ratio": 0.0,
      "completion_length": 231.40625,
      "epoch": 0.016,
      "grad_norm": 4.284538745880127,
      "kl": 0.00179290771484375,
      "learning_rate": 9.983999999999998e-07,
      "loss": 0.0,
      "reward": 0.125,
      "reward_std": 0.2925042062997818,
      "rewards/format_reward": 0.0,
      "rewards/score_reward": 0.125,
      "step": 4
    },
    {
      "clip_ratio": 0.0,
      "completion_length": 226.90625,
      "epoch": 0.02,
      "grad_norm": 5.088000774383545,
      "kl": 0.00188446044921875,
      "learning_rate": 9.98e-07,
      "loss": 0.0,
      "reward": 0.125,
      "reward_std": 0.2925042062997818,
      "rewards/format_reward": 0.0,
      "rewards/score_reward": 0.125,
      "step": 5
    },
    {
      "clip_ratio": 0.0,
      "completion_length": 220.71875,
      "epoch": 0.024,
      "grad_norm": 6.958590507507324,
      "kl": 0.002094268798828125,
      "learning_rate": 9.976e-07,
      "loss": 0.0,
      "reward": 0.0625,
      "reward_std": 0.1767766922712326,
      "rewards/format_reward": 0.0,
      "rewards/score_reward": 0.0625,
      "step": 6
    },
    {
      "clip_ratio": 0.0,
      "completion_length": 212.875,
      "epoch": 0.028,
      "grad_norm": 2.5518085956573486,
      "kl": 0.003185272216796875,
      "learning_rate": 9.972e-07,
      "loss": 0.0,
      "reward": 0.125,
      "reward_std": 0.13363061845302582,
      "rewards/format_reward": 0.0,
      "rewards/score_reward": 0.125,
      "step": 7
    },
    {
      "clip_ratio": 0.0,
      "completion_length": 208.375,
      "epoch": 0.032,
      "grad_norm": 0.003275999566540122,
      "kl": 0.0058441162109375,
      "learning_rate": 9.968e-07,
      "loss": 0.0,
      "reward": 0.0,
      "reward_std": 0.0,
      "rewards/format_reward": 0.0,
      "rewards/score_reward": 0.0,
      "step": 8
    },
    {
      "clip_ratio": 0.0,
      "completion_length": 204.65625,
      "epoch": 0.036,
      "grad_norm": 3.262775182723999,
      "kl": 0.007598876953125,
      "learning_rate": 9.964e-07,
      "loss": 0.0,
      "reward": 0.0625,
      "reward_std": 0.1767766922712326,
      "rewards/format_reward": 0.0,
      "rewards/score_reward": 0.0625,
      "step": 9
    },
    {
      "clip_ratio": 0.0,
      "completion_length": 198.375,
      "epoch": 0.04,
      "grad_norm": 0.004171893931925297,
      "kl": 0.0090484619140625,
      "learning_rate": 9.959999999999999e-07,
      "loss": 0.0,
      "reward": 0.0,
      "reward_std": 0.0,
      "rewards/format_reward": 0.0,
      "rewards/score_reward": 0.0,
      "step": 10
    },
    {
      "clip_ratio": 0.0,
      "completion_length": 185.71875,
      "epoch": 0.044,
      "grad_norm": 11.263163566589355,
      "kl": 0.0082550048828125,
      "learning_rate": 9.956e-07,
      "loss": 0.0,
      "reward": 0.40625,
      "reward_std": 0.3061639815568924,
      "rewards/format_reward": 0.0,
      "rewards/score_reward": 0.40625,
      "step": 11
    },
    {
      "clip_ratio": 0.0,
      "completion_length": 221.5,
      "epoch": 0.048,
      "grad_norm": 2.615539312362671,
      "kl": 0.0104522705078125,
      "learning_rate": 9.952e-07,
      "loss": 0.0,
      "reward": 0.09375,
      "reward_std": 0.1293872892856598,
      "rewards/format_reward": 0.0,
      "rewards/score_reward": 0.09375,
      "step": 12
    },
    {
      "clip_ratio": 0.0,
      "completion_length": 182.0,
      "epoch": 0.052,
      "grad_norm": 4.1748127937316895,
      "kl": 0.0160369873046875,
      "learning_rate": 9.948e-07,
      "loss": 0.0,
      "reward": 0.21875,
      "reward_std": 0.3377464786171913,
      "rewards/format_reward": 0.0,
      "rewards/score_reward": 0.21875,
      "step": 13
    },
    {
      "clip_ratio": 0.0,
      "completion_length": 200.09375,
      "epoch": 0.056,
      "grad_norm": 4.833225727081299,
      "kl": 0.018402099609375,
      "learning_rate": 9.944e-07,
      "loss": 0.0,
      "reward": 0.15625,
      "reward_std": 0.24511480331420898,
      "rewards/format_reward": 0.0,
      "rewards/score_reward": 0.15625,
      "step": 14
    },
    {
      "clip_ratio": 0.0,
      "completion_length": 161.21875,
      "epoch": 0.06,
      "grad_norm": 6.787618637084961,
      "kl": 0.03887939453125,
      "learning_rate": 9.94e-07,
      "loss": 0.0,
      "reward": 0.125,
      "reward_std": 0.2314550280570984,
      "rewards/format_reward": 0.0,
      "rewards/score_reward": 0.125,
      "step": 15
    },
    {
      "clip_ratio": 0.0,
      "completion_length": 179.53125,
      "epoch": 0.064,
      "grad_norm": 4.547823905944824,
      "kl": 0.03192138671875,
      "learning_rate": 9.936e-07,
      "loss": 0.0,
      "reward": 0.15625,
      "reward_std": 0.3198433741927147,
      "rewards/format_reward": 0.0,
      "rewards/score_reward": 0.15625,
      "step": 16
    },
    {
      "clip_ratio": 0.0,
      "completion_length": 171.78125,
      "epoch": 0.068,
      "grad_norm": 3.955144166946411,
      "kl": 0.030029296875,
      "learning_rate": 9.931999999999999e-07,
      "loss": 0.0,
      "reward": 0.28125,
      "reward_std": 0.2041158601641655,
      "rewards/format_reward": 0.0,
      "rewards/score_reward": 0.28125,
      "step": 17
    },
    {
      "clip_ratio": 0.0,
      "completion_length": 184.0,
      "epoch": 0.072,
      "grad_norm": 3.1369616985321045,
      "kl": 0.0242919921875,
      "learning_rate": 9.928e-07,
      "loss": 0.0,
      "reward": 0.03125,
      "reward_std": 0.0883883461356163,
      "rewards/format_reward": 0.0,
      "rewards/score_reward": 0.03125,
      "step": 18
    },
    {
      "clip_ratio": 0.0,
      "completion_length": 165.71875,
      "epoch": 0.076,
      "grad_norm": 3.3629579544067383,
      "kl": 0.03326416015625,
      "learning_rate": 9.923999999999998e-07,
      "loss": 0.0,
      "reward": 0.125,
      "reward_std": 0.2314550280570984,
      "rewards/format_reward": 0.0,
      "rewards/score_reward": 0.125,
      "step": 19
    },
    {
      "clip_ratio": 0.0,
      "completion_length": 173.09375,
      "epoch": 0.08,
      "grad_norm": 1.9398032426834106,
      "kl": 0.032012939453125,
      "learning_rate": 9.92e-07,
      "loss": 0.0,
      "reward": 0.03125,
      "reward_std": 0.0883883461356163,
      "rewards/format_reward": 0.0,
      "rewards/score_reward": 0.03125,
      "step": 20
    },
    {
      "clip_ratio": 0.0,
      "completion_length": 165.28125,
      "epoch": 0.084,
      "grad_norm": 3.363475799560547,
      "kl": 0.03326416015625,
      "learning_rate": 9.916e-07,
      "loss": 0.0,
      "reward": 0.03125,
      "reward_std": 0.0883883461356163,
      "rewards/format_reward": 0.0,
      "rewards/score_reward": 0.03125,
      "step": 21
    },
    {
      "clip_ratio": 0.0,
      "completion_length": 178.875,
      "epoch": 0.088,
      "grad_norm": 24.74161720275879,
      "kl": 0.02996826171875,
      "learning_rate": 9.912e-07,
      "loss": 0.0,
      "reward": 0.1875,
      "reward_std": 0.3335031494498253,
      "rewards/format_reward": 0.0,
      "rewards/score_reward": 0.1875,
      "step": 22
    },
    {
      "clip_ratio": 0.0,
      "completion_length": 143.53125,
      "epoch": 0.092,
      "grad_norm": 5.056652069091797,
      "kl": 0.035888671875,
      "learning_rate": 9.908e-07,
      "loss": 0.0,
      "reward": 0.09375,
      "reward_std": 0.2041158601641655,
      "rewards/format_reward": 0.0,
      "rewards/score_reward": 0.09375,
      "step": 23
    },
    {
      "clip_ratio": 0.0,
      "completion_length": 149.125,
      "epoch": 0.096,
      "grad_norm": 2.984828233718872,
      "kl": 0.036224365234375,
      "learning_rate": 9.903999999999999e-07,
      "loss": 0.0,
      "reward": 0.34375,
      "reward_std": 0.24511480331420898,
      "rewards/format_reward": 0.0,
      "rewards/score_reward": 0.34375,
      "step": 24
    },
    {
      "clip_ratio": 0.0,
      "completion_length": 140.375,
      "epoch": 0.1,
      "grad_norm": 11.72681713104248,
      "kl": 0.042724609375,
      "learning_rate": 9.9e-07,
      "loss": 0.0,
      "reward": 0.15625,
      "reward_std": 0.3808925524353981,
      "rewards/format_reward": 0.0,
      "rewards/score_reward": 0.15625,
      "step": 25
    },
    {
      "clip_ratio": 0.0,
      "completion_length": 156.3125,
      "epoch": 0.104,
      "grad_norm": 9.360048294067383,
      "kl": 0.0421142578125,
      "learning_rate": 9.896e-07,
      "loss": 0.0,
      "reward": 0.25,
      "reward_std": 0.4492306634783745,
      "rewards/format_reward": 0.0,
      "rewards/score_reward": 0.25,
      "step": 26
    },
    {
      "clip_ratio": 0.0,
      "completion_length": 156.8125,
      "epoch": 0.108,
      "grad_norm": 5.80740213394165,
      "kl": 0.04278564453125,
      "learning_rate": 9.892e-07,
      "loss": 0.0,
      "reward": 0.15625,
      "reward_std": 0.3198433741927147,
      "rewards/format_reward": 0.0,
      "rewards/score_reward": 0.15625,
      "step": 27
    },
    {
      "clip_ratio": 0.0,
      "completion_length": 152.4375,
      "epoch": 0.112,
      "grad_norm": 5.797030448913574,
      "kl": 0.04522705078125,
      "learning_rate": 9.888e-07,
      "loss": 0.0,
      "reward": 0.1875,
      "reward_std": 0.249358132481575,
      "rewards/format_reward": 0.0,
      "rewards/score_reward": 0.1875,
      "step": 28
    },
    {
      "clip_ratio": 0.0,
      "completion_length": 160.8125,
      "epoch": 0.116,
      "grad_norm": 15.973736763000488,
      "kl": 0.0457763671875,
      "learning_rate": 9.884e-07,
      "loss": 0.0,
      "reward": 0.125,
      "reward_std": 0.2925042062997818,
      "rewards/format_reward": 0.0,
      "rewards/score_reward": 0.125,
      "step": 29
    },
    {
      "clip_ratio": 0.0,
      "completion_length": 144.46875,
      "epoch": 0.12,
      "grad_norm": 52.75318908691406,
      "kl": 0.05126953125,
      "learning_rate": 9.88e-07,
      "loss": 0.0001,
      "reward": 0.25,
      "reward_std": 0.4492306634783745,
      "rewards/format_reward": 0.0,
      "rewards/score_reward": 0.25,
      "step": 30
    },
    {
      "clip_ratio": 0.0,
      "completion_length": 142.625,
      "epoch": 0.124,
      "grad_norm": 19.736919403076172,
      "kl": 0.05572509765625,
      "learning_rate": 9.876e-07,
      "loss": 0.0001,
      "reward": 0.15625,
      "reward_std": 0.3061639815568924,
      "rewards/format_reward": 0.0,
      "rewards/score_reward": 0.15625,
      "step": 31
    },
    {
      "clip_ratio": 0.0,
      "completion_length": 159.875,
      "epoch": 0.128,
      "grad_norm": 5.151854515075684,
      "kl": 0.05242919921875,
      "learning_rate": 9.871999999999998e-07,
      "loss": 0.0001,
      "reward": 0.125,
      "reward_std": 0.2177756354212761,
      "rewards/format_reward": 0.0,
      "rewards/score_reward": 0.125,
      "step": 32
    },
    {
      "clip_ratio": 0.0,
      "completion_length": 163.5,
      "epoch": 0.132,
      "grad_norm": 4.104671001434326,
      "kl": 0.04571533203125,
      "learning_rate": 9.868e-07,
      "loss": 0.0,
      "reward": 0.125,
      "reward_std": 0.2314550280570984,
      "rewards/format_reward": 0.0,
      "rewards/score_reward": 0.125,
      "step": 33
    },
    {
      "clip_ratio": 0.0,
      "completion_length": 151.46875,
      "epoch": 0.136,
      "grad_norm": 11.92469310760498,
      "kl": 0.05950927734375,
      "learning_rate": 9.864e-07,
      "loss": 0.0001,
      "reward": 0.25,
      "reward_std": 0.3514062538743019,
      "rewards/format_reward": 0.0,
      "rewards/score_reward": 0.25,
      "step": 34
    },
    {
      "clip_ratio": 0.0,
      "completion_length": 136.3125,
      "epoch": 0.14,
      "grad_norm": 6.980234622955322,
      "kl": 0.05780029296875,
      "learning_rate": 9.86e-07,
      "loss": 0.0001,
      "reward": 0.375,
      "reward_std": 0.3924051970243454,
      "rewards/format_reward": 0.0,
      "rewards/score_reward": 0.375,
      "step": 35
    },
    {
      "clip_ratio": 0.0,
      "completion_length": 146.34375,
      "epoch": 0.144,
      "grad_norm": 2.9053189754486084,
      "kl": 0.06768798828125,
      "learning_rate": 9.856e-07,
      "loss": 0.0001,
      "reward": 0.03125,
      "reward_std": 0.0883883461356163,
      "rewards/format_reward": 0.0,
      "rewards/score_reward": 0.03125,
      "step": 36
    },
    {
      "clip_ratio": 0.0,
      "completion_length": 132.1875,
      "epoch": 0.148,
      "grad_norm": 10.398985862731934,
      "kl": 0.06573486328125,
      "learning_rate": 9.852e-07,
      "loss": 0.0001,
      "reward": 0.125,
      "reward_std": 0.2314550280570984,
      "rewards/format_reward": 0.0,
      "rewards/score_reward": 0.125,
      "step": 37
    },
    {
      "clip_ratio": 0.0,
      "completion_length": 134.4375,
      "epoch": 0.152,
      "grad_norm": 12.788537979125977,
      "kl": 0.07025146484375,
      "learning_rate": 9.847999999999999e-07,
      "loss": 0.0001,
      "reward": 0.09375,
      "reward_std": 0.2041158601641655,
      "rewards/format_reward": 0.0,
      "rewards/score_reward": 0.09375,
      "step": 38
    },
    {
      "clip_ratio": 0.0,
      "completion_length": 125.6875,
      "epoch": 0.156,
      "grad_norm": 3.894649028778076,
      "kl": 0.068603515625,
      "learning_rate": 9.844e-07,
      "loss": 0.0001,
      "reward": 0.375,
      "reward_std": 0.2314550280570984,
      "rewards/format_reward": 0.0,
      "rewards/score_reward": 0.375,
      "step": 39
    },
    {
      "clip_ratio": 0.0,
      "completion_length": 128.875,
      "epoch": 0.16,
      "grad_norm": 4.223596096038818,
      "kl": 0.07427978515625,
      "learning_rate": 9.84e-07,
      "loss": 0.0001,
      "reward": 0.09375,
      "reward_std": 0.2041158601641655,
      "rewards/format_reward": 0.0,
      "rewards/score_reward": 0.09375,
      "step": 40
    },
    {
      "clip_ratio": 0.0,
      "completion_length": 135.375,
      "epoch": 0.164,
      "grad_norm": 3.229766845703125,
      "kl": 0.08056640625,
      "learning_rate": 9.836e-07,
      "loss": 0.0001,
      "reward": 0.28125,
      "reward_std": 0.2630179077386856,
      "rewards/format_reward": 0.0,
      "rewards/score_reward": 0.28125,
      "step": 41
    },
    {
      "clip_ratio": 0.0,
      "completion_length": 126.0625,
      "epoch": 0.168,
      "grad_norm": 5.142240047454834,
      "kl": 0.076904296875,
      "learning_rate": 9.832e-07,
      "loss": 0.0001,
      "reward": 0.15625,
      "reward_std": 0.3061639815568924,
      "rewards/format_reward": 0.0,
      "rewards/score_reward": 0.15625,
      "step": 42
    },
    {
      "clip_ratio": 0.0,
      "completion_length": 137.46875,
      "epoch": 0.172,
      "grad_norm": 6.515385627746582,
      "kl": 0.08544921875,
      "learning_rate": 9.828e-07,
      "loss": 0.0001,
      "reward": 0.34375,
      "reward_std": 0.4218914955854416,
      "rewards/format_reward": 0.0,
      "rewards/score_reward": 0.34375,
      "step": 43
    },
    {
      "clip_ratio": 0.0,
      "completion_length": 163.40625,
      "epoch": 0.176,
      "grad_norm": 6.223419666290283,
      "kl": 0.06097412109375,
      "learning_rate": 9.824e-07,
      "loss": 0.0001,
      "reward": 0.28125,
      "reward_std": 0.3787454217672348,
      "rewards/format_reward": 0.0,
      "rewards/score_reward": 0.28125,
      "step": 44
    },
    {
      "clip_ratio": 0.0,
      "completion_length": 131.65625,
      "epoch": 0.18,
      "grad_norm": 4.957655429840088,
      "kl": 0.0849609375,
      "learning_rate": 9.819999999999999e-07,
      "loss": 0.0001,
      "reward": 0.34375,
      "reward_std": 0.3198433741927147,
      "rewards/format_reward": 0.0,
      "rewards/score_reward": 0.34375,
      "step": 45
    },
    {
      "clip_ratio": 0.0,
      "completion_length": 132.1875,
      "epoch": 0.184,
      "grad_norm": 2.228003978729248,
      "kl": 0.0794677734375,
      "learning_rate": 9.816e-07,
      "loss": 0.0001,
      "reward": 0.0625,
      "reward_std": 0.1157275140285492,
      "rewards/format_reward": 0.0,
      "rewards/score_reward": 0.0625,
      "step": 46
    },
    {
      "clip_ratio": 0.0,
      "completion_length": 143.875,
      "epoch": 0.188,
      "grad_norm": 11.523205757141113,
      "kl": 0.0767822265625,
      "learning_rate": 9.811999999999998e-07,
      "loss": 0.0001,
      "reward": 0.125,
      "reward_std": 0.2177756354212761,
      "rewards/format_reward": 0.0,
      "rewards/score_reward": 0.125,
      "step": 47
    },
    {
      "clip_ratio": 0.0,
      "completion_length": 156.6875,
      "epoch": 0.192,
      "grad_norm": 7.209992408752441,
      "kl": 0.073486328125,
      "learning_rate": 9.808e-07,
      "loss": 0.0001,
      "reward": 0.25,
      "reward_std": 0.3514062538743019,
      "rewards/format_reward": 0.0,
      "rewards/score_reward": 0.25,
      "step": 48
    },
    {
      "clip_ratio": 0.0,
      "completion_length": 155.40625,
      "epoch": 0.196,
      "grad_norm": 5.14667272567749,
      "kl": 0.1248779296875,
      "learning_rate": 9.804e-07,
      "loss": 0.0001,
      "reward": 0.25,
      "reward_std": 0.4492306634783745,
      "rewards/format_reward": 0.0,
      "rewards/score_reward": 0.25,
      "step": 49
    },
    {
      "clip_ratio": 0.0,
      "completion_length": 146.96875,
      "epoch": 0.2,
      "grad_norm": 4.949409008026123,
      "kl": 0.0828857421875,
      "learning_rate": 9.8e-07,
      "loss": 0.0001,
      "reward": 0.28125,
      "reward_std": 0.4628904387354851,
      "rewards/format_reward": 0.0,
      "rewards/score_reward": 0.28125,
      "step": 50
    },
    {
      "clip_ratio": 0.0,
      "completion_length": 122.375,
      "epoch": 0.204,
      "grad_norm": 13.097493171691895,
      "kl": 0.0899658203125,
      "learning_rate": 9.796e-07,
      "loss": 0.0001,
      "reward": 0.15625,
      "reward_std": 0.3808925524353981,
      "rewards/format_reward": 0.0,
      "rewards/score_reward": 0.15625,
      "step": 51
    },
    {
      "clip_ratio": 0.0,
      "completion_length": 135.15625,
      "epoch": 0.208,
      "grad_norm": 12.397465705871582,
      "kl": 0.08447265625,
      "learning_rate": 9.791999999999999e-07,
      "loss": 0.0001,
      "reward": 0.1875,
      "reward_std": 0.3335031494498253,
      "rewards/format_reward": 0.0,
      "rewards/score_reward": 0.1875,
      "step": 52
    },
    {
      "clip_ratio": 0.0,
      "completion_length": 125.75,
      "epoch": 0.212,
      "grad_norm": 6.712313175201416,
      "kl": 0.0906982421875,
      "learning_rate": 9.788e-07,
      "loss": 0.0001,
      "reward": 0.375,
      "reward_std": 0.408231720328331,
      "rewards/format_reward": 0.0,
      "rewards/score_reward": 0.375,
      "step": 53
    },
    {
      "clip_ratio": 0.0,
      "completion_length": 141.625,
      "epoch": 0.216,
      "grad_norm": 5.286505222320557,
      "kl": 0.0909423828125,
      "learning_rate": 9.784e-07,
      "loss": 0.0001,
      "reward": 0.3125,
      "reward_std": 0.3745020925998688,
      "rewards/format_reward": 0.0,
      "rewards/score_reward": 0.3125,
      "step": 54
    },
    {
      "clip_ratio": 0.0,
      "completion_length": 152.25,
      "epoch": 0.22,
      "grad_norm": 4.269443511962891,
      "kl": 0.08026123046875,
      "learning_rate": 9.78e-07,
      "loss": 0.0001,
      "reward": 0.0625,
      "reward_std": 0.1767766922712326,
      "rewards/format_reward": 0.0,
      "rewards/score_reward": 0.0625,
      "step": 55
    },
    {
      "clip_ratio": 0.0,
      "completion_length": 138.09375,
      "epoch": 0.224,
      "grad_norm": 4.18522310256958,
      "kl": 0.0966796875,
      "learning_rate": 9.776e-07,
      "loss": 0.0001,
      "reward": 0.25,
      "reward_std": 0.2925042062997818,
      "rewards/format_reward": 0.0,
      "rewards/score_reward": 0.25,
      "step": 56
    },
    {
      "clip_ratio": 0.0,
      "completion_length": 140.3125,
      "epoch": 0.228,
      "grad_norm": 7.846221446990967,
      "kl": 0.1097412109375,
      "learning_rate": 9.772e-07,
      "loss": 0.0001,
      "reward": 0.4375,
      "reward_std": 0.2925042062997818,
      "rewards/format_reward": 0.0,
      "rewards/score_reward": 0.4375,
      "step": 57
    },
    {
      "clip_ratio": 0.0,
      "completion_length": 141.59375,
      "epoch": 0.232,
      "grad_norm": 2.465056896209717,
      "kl": 0.0821533203125,
      "learning_rate": 9.768e-07,
      "loss": 0.0001,
      "reward": 0.09375,
      "reward_std": 0.1293872892856598,
      "rewards/format_reward": 0.0,
      "rewards/score_reward": 0.09375,
      "step": 58
    },
    {
      "clip_ratio": 0.0,
      "completion_length": 142.6875,
      "epoch": 0.236,
      "grad_norm": 34.07876968383789,
      "kl": 0.07476806640625,
      "learning_rate": 9.764e-07,
      "loss": 0.0001,
      "reward": 0.3125,
      "reward_std": 0.3745020925998688,
      "rewards/format_reward": 0.0,
      "rewards/score_reward": 0.3125,
      "step": 59
    },
    {
      "clip_ratio": 0.0,
      "completion_length": 136.40625,
      "epoch": 0.24,
      "grad_norm": 4.285093784332275,
      "kl": 0.07568359375,
      "learning_rate": 9.759999999999998e-07,
      "loss": 0.0001,
      "reward": 0.1875,
      "reward_std": 0.3104073107242584,
      "rewards/format_reward": 0.0,
      "rewards/score_reward": 0.1875,
      "step": 60
    },
    {
      "clip_ratio": 0.0,
      "completion_length": 156.5,
      "epoch": 0.244,
      "grad_norm": 4.140926837921143,
      "kl": 0.08203125,
      "learning_rate": 9.756e-07,
      "loss": 0.0001,
      "reward": 0.15625,
      "reward_std": 0.22201896458864212,
      "rewards/format_reward": 0.0,
      "rewards/score_reward": 0.15625,
      "step": 61
    },
    {
      "clip_ratio": 0.0,
      "completion_length": 154.0625,
      "epoch": 0.248,
      "grad_norm": 5.816662311553955,
      "kl": 0.0833740234375,
      "learning_rate": 9.752e-07,
      "loss": 0.0001,
      "reward": 0.125,
      "reward_std": 0.2177756354212761,
      "rewards/format_reward": 0.0,
      "rewards/score_reward": 0.125,
      "step": 62
    },
    {
      "clip_ratio": 0.0,
      "completion_length": 144.75,
      "epoch": 0.252,
      "grad_norm": 5.923285961151123,
      "kl": 0.079345703125,
      "learning_rate": 9.748e-07,
      "loss": 0.0001,
      "reward": 0.5,
      "reward_std": 0.4355512708425522,
      "rewards/format_reward": 0.0,
      "rewards/score_reward": 0.5,
      "step": 63
    },
    {
      "clip_ratio": 0.0,
      "completion_length": 143.6875,
      "epoch": 0.256,
      "grad_norm": 3.0318973064422607,
      "kl": 0.1051025390625,
      "learning_rate": 9.744e-07,
      "loss": 0.0001,
      "reward": 0.0625,
      "reward_std": 0.1157275140285492,
      "rewards/format_reward": 0.0,
      "rewards/score_reward": 0.0625,
      "step": 64
    },
    {
      "clip_ratio": 0.0,
      "completion_length": 137.15625,
      "epoch": 0.26,
      "grad_norm": 9.24459171295166,
      "kl": 0.081298828125,
      "learning_rate": 9.74e-07,
      "loss": 0.0001,
      "reward": 0.34375,
      "reward_std": 0.3608423173427582,
      "rewards/format_reward": 0.0,
      "rewards/score_reward": 0.34375,
      "step": 65
    },
    {
      "clip_ratio": 0.0,
      "completion_length": 139.09375,
      "epoch": 0.264,
      "grad_norm": 2.5574748516082764,
      "kl": 0.0794677734375,
      "learning_rate": 9.735999999999999e-07,
      "loss": 0.0001,
      "reward": 0.21875,
      "reward_std": 0.0883883461356163,
      "rewards/format_reward": 0.0,
      "rewards/score_reward": 0.21875,
      "step": 66
    },
    {
      "clip_ratio": 0.0,
      "completion_length": 147.875,
      "epoch": 0.268,
      "grad_norm": 3.8737809658050537,
      "kl": 0.8548583984375,
      "learning_rate": 9.731999999999998e-07,
      "loss": 0.0009,
      "reward": 0.25,
      "reward_std": 0.1767766922712326,
      "rewards/format_reward": 0.0,
      "rewards/score_reward": 0.25,
      "step": 67
    },
    {
      "clip_ratio": 0.0,
      "completion_length": 133.0,
      "epoch": 0.272,
      "grad_norm": 18.663503646850586,
      "kl": 0.1005859375,
      "learning_rate": 9.728e-07,
      "loss": 0.0001,
      "reward": 0.3125,
      "reward_std": 0.3924051970243454,
      "rewards/format_reward": 0.0,
      "rewards/score_reward": 0.3125,
      "step": 68
    },
    {
      "clip_ratio": 0.0,
      "completion_length": 145.0,
      "epoch": 0.276,
      "grad_norm": 3.6664018630981445,
      "kl": 0.0904541015625,
      "learning_rate": 9.724e-07,
      "loss": 0.0001,
      "reward": 0.21875,
      "reward_std": 0.2041158601641655,
      "rewards/format_reward": 0.0,
      "rewards/score_reward": 0.21875,
      "step": 69
    },
    {
      "clip_ratio": 0.0,
      "completion_length": 134.03125,
      "epoch": 0.28,
      "grad_norm": 4.882191181182861,
      "kl": 0.0919189453125,
      "learning_rate": 9.72e-07,
      "loss": 0.0001,
      "reward": 0.375,
      "reward_std": 0.3745020925998688,
      "rewards/format_reward": 0.0,
      "rewards/score_reward": 0.375,
      "step": 70
    },
    {
      "clip_ratio": 0.0,
      "completion_length": 159.375,
      "epoch": 0.284,
      "grad_norm": 3.3950247764587402,
      "kl": 0.11431884765625,
      "learning_rate": 9.716e-07,
      "loss": 0.0001,
      "reward": 0.21875,
      "reward_std": 0.2041158601641655,
      "rewards/format_reward": 0.0,
      "rewards/score_reward": 0.21875,
      "step": 71
    },
    {
      "clip_ratio": 0.0,
      "completion_length": 128.4375,
      "epoch": 0.288,
      "grad_norm": 3.155332326889038,
      "kl": 0.0821533203125,
      "learning_rate": 9.712e-07,
      "loss": 0.0001,
      "reward": 0.5625,
      "reward_std": 0.1157275140285492,
      "rewards/format_reward": 0.0,
      "rewards/score_reward": 0.5625,
      "step": 72
    },
    {
      "clip_ratio": 0.0,
      "completion_length": 137.1875,
      "epoch": 0.292,
      "grad_norm": 5.511759281158447,
      "kl": 0.095458984375,
      "learning_rate": 9.707999999999999e-07,
      "loss": 0.0001,
      "reward": 0.34375,
      "reward_std": 0.2041158601641655,
      "rewards/format_reward": 0.0,
      "rewards/score_reward": 0.34375,
      "step": 73
    },
    {
      "clip_ratio": 0.0,
      "completion_length": 145.21875,
      "epoch": 0.296,
      "grad_norm": 3.31162428855896,
      "kl": 0.8125,
      "learning_rate": 9.704e-07,
      "loss": 0.0008,
      "reward": 0.28125,
      "reward_std": 0.0883883461356163,
      "rewards/format_reward": 0.0,
      "rewards/score_reward": 0.28125,
      "step": 74
    },
    {
      "clip_ratio": 0.0,
      "completion_length": 145.5625,
      "epoch": 0.3,
      "grad_norm": 3.7722182273864746,
      "kl": 0.0821533203125,
      "learning_rate": 9.7e-07,
      "loss": 0.0001,
      "reward": 0.59375,
      "reward_std": 0.22201896458864212,
      "rewards/format_reward": 0.0,
      "rewards/score_reward": 0.59375,
      "step": 75
    },
    {
      "clip_ratio": 0.0,
      "completion_length": 143.4375,
      "epoch": 0.304,
      "grad_norm": 10.5135498046875,
      "kl": 0.0877685546875,
      "learning_rate": 9.696e-07,
      "loss": 0.0001,
      "reward": 0.28125,
      "reward_std": 0.2041158601641655,
      "rewards/format_reward": 0.0,
      "rewards/score_reward": 0.28125,
      "step": 76
    },
    {
      "clip_ratio": 0.0,
      "completion_length": 139.25,
      "epoch": 0.308,
      "grad_norm": 5.515931606292725,
      "kl": 0.125732421875,
      "learning_rate": 9.692e-07,
      "loss": 0.0001,
      "reward": 0.34375,
      "reward_std": 0.3966485261917114,
      "rewards/format_reward": 0.0,
      "rewards/score_reward": 0.34375,
      "step": 77
    },
    {
      "clip_ratio": 0.0,
      "completion_length": 170.375,
      "epoch": 0.312,
      "grad_norm": 3.9698073863983154,
      "kl": 0.0877685546875,
      "learning_rate": 9.688e-07,
      "loss": 0.0001,
      "reward": 0.03125,
      "reward_std": 0.0883883461356163,
      "rewards/format_reward": 0.0,
      "rewards/score_reward": 0.03125,
      "step": 78
    },
    {
      "clip_ratio": 0.0,
      "completion_length": 165.96875,
      "epoch": 0.316,
      "grad_norm": 0.01992066204547882,
      "kl": 0.1063232421875,
      "learning_rate": 9.684e-07,
      "loss": 0.0001,
      "reward": 0.0,
      "reward_std": 0.0,
      "rewards/format_reward": 0.0,
      "rewards/score_reward": 0.0,
      "step": 79
    },
    {
      "clip_ratio": 0.0,
      "completion_length": 146.0,
      "epoch": 0.32,
      "grad_norm": 2.0439631938934326,
      "kl": 0.08642578125,
      "learning_rate": 9.679999999999999e-07,
      "loss": 0.0001,
      "reward": 0.46875,
      "reward_std": 0.0883883461356163,
      "rewards/format_reward": 0.0,
      "rewards/score_reward": 0.46875,
      "step": 80
    },
    {
      "clip_ratio": 0.0,
      "completion_length": 146.0625,
      "epoch": 0.324,
      "grad_norm": 5.627711772918701,
      "kl": 0.2181396484375,
      "learning_rate": 9.676e-07,
      "loss": 0.0002,
      "reward": 0.0625,
      "reward_std": 0.1767766922712326,
      "rewards/format_reward": 0.0,
      "rewards/score_reward": 0.0625,
      "step": 81
    },
    {
      "clip_ratio": 0.0,
      "completion_length": 149.03125,
      "epoch": 0.328,
      "grad_norm": 3.953463077545166,
      "kl": 0.1114501953125,
      "learning_rate": 9.671999999999998e-07,
      "loss": 0.0001,
      "reward": 0.53125,
      "reward_std": 0.2041158601641655,
      "rewards/format_reward": 0.0,
      "rewards/score_reward": 0.53125,
      "step": 82
    },
    {
      "clip_ratio": 0.0,
      "completion_length": 136.28125,
      "epoch": 0.332,
      "grad_norm": 4.612481117248535,
      "kl": 0.1048583984375,
      "learning_rate": 9.668e-07,
      "loss": 0.0001,
      "reward": 0.40625,
      "reward_std": 0.2041158601641655,
      "rewards/format_reward": 0.0,
      "rewards/score_reward": 0.40625,
      "step": 83
    },
    {
      "clip_ratio": 0.0,
      "completion_length": 137.59375,
      "epoch": 0.336,
      "grad_norm": 6.570859909057617,
      "kl": 0.2337646484375,
      "learning_rate": 9.664e-07,
      "loss": 0.0002,
      "reward": 0.3125,
      "reward_std": 0.3335031494498253,
      "rewards/format_reward": 0.0,
      "rewards/score_reward": 0.3125,
      "step": 84
    },
    {
      "clip_ratio": 0.0,
      "completion_length": 152.6875,
      "epoch": 0.34,
      "grad_norm": 8.282193183898926,
      "kl": 0.0938720703125,
      "learning_rate": 9.66e-07,
      "loss": 0.0001,
      "reward": 0.3125,
      "reward_std": 0.4355512708425522,
      "rewards/format_reward": 0.0,
      "rewards/score_reward": 0.3125,
      "step": 85
    },
    {
      "clip_ratio": 0.0,
      "completion_length": 135.28125,
      "epoch": 0.344,
      "grad_norm": 3.57267165184021,
      "kl": 0.1107177734375,
      "learning_rate": 9.656e-07,
      "loss": 0.0001,
      "reward": 0.28125,
      "reward_std": 0.2041158601641655,
      "rewards/format_reward": 0.0,
      "rewards/score_reward": 0.28125,
      "step": 86
    },
    {
      "clip_ratio": 0.0,
      "completion_length": 153.8125,
      "epoch": 0.348,
      "grad_norm": 9.419325828552246,
      "kl": 0.0953369140625,
      "learning_rate": 9.651999999999999e-07,
      "loss": 0.0001,
      "reward": 0.34375,
      "reward_std": 0.1293872892856598,
      "rewards/format_reward": 0.0,
      "rewards/score_reward": 0.34375,
      "step": 87
    },
    {
      "clip_ratio": 0.0,
      "completion_length": 143.5625,
      "epoch": 0.352,
      "grad_norm": 11.560566902160645,
      "kl": 0.1787109375,
      "learning_rate": 9.647999999999999e-07,
      "loss": 0.0002,
      "reward": 0.34375,
      "reward_std": 0.2041158601641655,
      "rewards/format_reward": 0.0,
      "rewards/score_reward": 0.34375,
      "step": 88
    },
    {
      "clip_ratio": 0.0,
      "completion_length": 145.1875,
      "epoch": 0.356,
      "grad_norm": 8.131706237792969,
      "kl": 0.12060546875,
      "learning_rate": 9.644e-07,
      "loss": 0.0001,
      "reward": 0.03125,
      "reward_std": 0.0883883461356163,
      "rewards/format_reward": 0.0,
      "rewards/score_reward": 0.03125,
      "step": 89
    },
    {
      "clip_ratio": 0.0,
      "completion_length": 139.21875,
      "epoch": 0.36,
      "grad_norm": 11.170744895935059,
      "kl": 0.1241455078125,
      "learning_rate": 9.64e-07,
      "loss": 0.0001,
      "reward": 0.34375,
      "reward_std": 0.3377464786171913,
      "rewards/format_reward": 0.0,
      "rewards/score_reward": 0.34375,
      "step": 90
    },
    {
      "clip_ratio": 0.0,
      "completion_length": 155.6875,
      "epoch": 0.364,
      "grad_norm": 27.866975784301758,
      "kl": 0.1082763671875,
      "learning_rate": 9.636e-07,
      "loss": 0.0001,
      "reward": 0.125,
      "reward_std": 0.2177756354212761,
      "rewards/format_reward": 0.0,
      "rewards/score_reward": 0.125,
      "step": 91
    },
    {
      "clip_ratio": 0.0,
      "completion_length": 151.75,
      "epoch": 0.368,
      "grad_norm": 5.540046215057373,
      "kl": 0.1146240234375,
      "learning_rate": 9.632e-07,
      "loss": 0.0001,
      "reward": 0.21875,
      "reward_std": 0.0883883461356163,
      "rewards/format_reward": 0.0,
      "rewards/score_reward": 0.21875,
      "step": 92
    },
    {
      "clip_ratio": 0.0,
      "completion_length": 136.96875,
      "epoch": 0.372,
      "grad_norm": 4.550509929656982,
      "kl": 0.1181640625,
      "learning_rate": 9.628e-07,
      "loss": 0.0001,
      "reward": 0.625,
      "reward_std": 0.3745020925998688,
      "rewards/format_reward": 0.0,
      "rewards/score_reward": 0.625,
      "step": 93
    },
    {
      "clip_ratio": 0.0,
      "completion_length": 151.28125,
      "epoch": 0.376,
      "grad_norm": 6.27862548828125,
      "kl": 0.1434326171875,
      "learning_rate": 9.624e-07,
      "loss": 0.0001,
      "reward": 0.0625,
      "reward_std": 0.1767766922712326,
      "rewards/format_reward": 0.0,
      "rewards/score_reward": 0.0625,
      "step": 94
    },
    {
      "clip_ratio": 0.0,
      "completion_length": 135.4375,
      "epoch": 0.38,
      "grad_norm": 14.521442413330078,
      "kl": 0.1177978515625,
      "learning_rate": 9.619999999999999e-07,
      "loss": 0.0001,
      "reward": 0.1875,
      "reward_std": 0.2177756354212761,
      "rewards/format_reward": 0.0,
      "rewards/score_reward": 0.1875,
      "step": 95
    },
    {
      "clip_ratio": 0.0,
      "completion_length": 160.3125,
      "epoch": 0.384,
      "grad_norm": 5.92653751373291,
      "kl": 0.1239013671875,
      "learning_rate": 9.616e-07,
      "loss": 0.0001,
      "reward": 0.3125,
      "reward_std": 0.2925042062997818,
      "rewards/format_reward": 0.0,
      "rewards/score_reward": 0.3125,
      "step": 96
    },
    {
      "clip_ratio": 0.0,
      "completion_length": 137.625,
      "epoch": 0.388,
      "grad_norm": 8.451234817504883,
      "kl": 0.134521484375,
      "learning_rate": 9.612e-07,
      "loss": 0.0001,
      "reward": 0.625,
      "reward_std": 0.3650856465101242,
      "rewards/format_reward": 0.0,
      "rewards/score_reward": 0.625,
      "step": 97
    },
    {
      "clip_ratio": 0.0,
      "completion_length": 142.65625,
      "epoch": 0.392,
      "grad_norm": 0.014137900434434414,
      "kl": 0.146728515625,
      "learning_rate": 9.608e-07,
      "loss": 0.0001,
      "reward": 0.5,
      "reward_std": 0.0,
      "rewards/format_reward": 0.0,
      "rewards/score_reward": 0.5,
      "step": 98
    },
    {
      "clip_ratio": 0.0,
      "completion_length": 137.15625,
      "epoch": 0.396,
      "grad_norm": 5.509148120880127,
      "kl": 0.1878662109375,
      "learning_rate": 9.604e-07,
      "loss": 0.0002,
      "reward": 0.25,
      "reward_std": 0.2587745785713196,
      "rewards/format_reward": 0.0,
      "rewards/score_reward": 0.25,
      "step": 99
    },
    {
      "clip_ratio": 0.0,
      "completion_length": 146.71875,
      "epoch": 0.4,
      "grad_norm": 9.132729530334473,
      "kl": 0.1285400390625,
      "learning_rate": 9.6e-07,
      "loss": 0.0001,
      "reward": 0.0625,
      "reward_std": 0.1767766922712326,
      "rewards/format_reward": 0.0,
      "rewards/score_reward": 0.0625,
      "step": 100
    },
    {
      "clip_ratio": 0.0,
      "completion_length": 135.40625,
      "epoch": 0.404,
      "grad_norm": 4.046815872192383,
      "kl": 0.152587890625,
      "learning_rate": 9.595999999999999e-07,
      "loss": 0.0002,
      "reward": 0.125,
      "reward_std": 0.13363061845302582,
      "rewards/format_reward": 0.0,
      "rewards/score_reward": 0.125,
      "step": 101
    },
    {
      "clip_ratio": 0.0,
      "completion_length": 143.25,
      "epoch": 0.408,
      "grad_norm": 4.168700218200684,
      "kl": 0.1993408203125,
      "learning_rate": 9.592e-07,
      "loss": 0.0002,
      "reward": 0.28125,
      "reward_std": 0.0883883461356163,
      "rewards/format_reward": 0.0,
      "rewards/score_reward": 0.28125,
      "step": 102
    },
    {
      "clip_ratio": 0.0,
      "completion_length": 131.03125,
      "epoch": 0.412,
      "grad_norm": 0.014560648240149021,
      "kl": 0.1416015625,
      "learning_rate": 9.588e-07,
      "loss": 0.0001,
      "reward": 0.5,
      "reward_std": 0.0,
      "rewards/format_reward": 0.0,
      "rewards/score_reward": 0.5,
      "step": 103
    },
    {
      "clip_ratio": 0.0,
      "completion_length": 140.71875,
      "epoch": 0.416,
      "grad_norm": 2.6636085510253906,
      "kl": 0.1611328125,
      "learning_rate": 9.584e-07,
      "loss": 0.0002,
      "reward": 0.46875,
      "reward_std": 0.0883883461356163,
      "rewards/format_reward": 0.0,
      "rewards/score_reward": 0.46875,
      "step": 104
    },
    {
      "clip_ratio": 0.0,
      "completion_length": 138.375,
      "epoch": 0.42,
      "grad_norm": 7.546946048736572,
      "kl": 0.1434326171875,
      "learning_rate": 9.58e-07,
      "loss": 0.0001,
      "reward": 0.28125,
      "reward_std": 0.24511480331420898,
      "rewards/format_reward": 0.0,
      "rewards/score_reward": 0.28125,
      "step": 105
    },
    {
      "clip_ratio": 0.0,
      "completion_length": 148.96875,
      "epoch": 0.424,
      "grad_norm": 5.07991361618042,
      "kl": 0.1376953125,
      "learning_rate": 9.576e-07,
      "loss": 0.0001,
      "reward": 0.03125,
      "reward_std": 0.0883883461356163,
      "rewards/format_reward": 0.0,
      "rewards/score_reward": 0.03125,
      "step": 106
    },
    {
      "clip_ratio": 0.0,
      "completion_length": 157.375,
      "epoch": 0.428,
      "grad_norm": 2.303396463394165,
      "kl": 0.1376953125,
      "learning_rate": 9.572e-07,
      "loss": 0.0001,
      "reward": 0.3125,
      "reward_std": 0.1157275140285492,
      "rewards/format_reward": 0.0,
      "rewards/score_reward": 0.3125,
      "step": 107
    },
    {
      "clip_ratio": 0.0,
      "completion_length": 152.40625,
      "epoch": 0.432,
      "grad_norm": 10.513725280761719,
      "kl": 0.217529296875,
      "learning_rate": 9.567999999999999e-07,
      "loss": 0.0002,
      "reward": 0.71875,
      "reward_std": 0.2651650384068489,
      "rewards/format_reward": 0.0,
      "rewards/score_reward": 0.71875,
      "step": 108
    },
    {
      "clip_ratio": 0.0,
      "completion_length": 148.21875,
      "epoch": 0.436,
      "grad_norm": 2.932323932647705,
      "kl": 0.213623046875,
      "learning_rate": 9.564e-07,
      "loss": 0.0002,
      "reward": 0.46875,
      "reward_std": 0.0883883461356163,
      "rewards/format_reward": 0.0,
      "rewards/score_reward": 0.46875,
      "step": 109
    },
    {
      "clip_ratio": 0.0,
      "completion_length": 144.3125,
      "epoch": 0.44,
      "grad_norm": 2.535456895828247,
      "kl": 0.150634765625,
      "learning_rate": 9.559999999999998e-07,
      "loss": 0.0002,
      "reward": 0.21875,
      "reward_std": 0.0883883461356163,
      "rewards/format_reward": 0.0,
      "rewards/score_reward": 0.21875,
      "step": 110
    },
    {
      "clip_ratio": 0.0,
      "completion_length": 151.46875,
      "epoch": 0.444,
      "grad_norm": 14.733839988708496,
      "kl": 0.1661376953125,
      "learning_rate": 9.556e-07,
      "loss": 0.0002,
      "reward": 0.0625,
      "reward_std": 0.1767766922712326,
      "rewards/format_reward": 0.0,
      "rewards/score_reward": 0.0625,
      "step": 111
    },
    {
      "clip_ratio": 0.0,
      "completion_length": 142.34375,
      "epoch": 0.448,
      "grad_norm": 0.015656903386116028,
      "kl": 0.1395263671875,
      "learning_rate": 9.552e-07,
      "loss": 0.0001,
      "reward": 0.25,
      "reward_std": 0.0,
      "rewards/format_reward": 0.0,
      "rewards/score_reward": 0.25,
      "step": 112
    },
    {
      "clip_ratio": 0.0,
      "completion_length": 153.34375,
      "epoch": 0.452,
      "grad_norm": 0.022109676152467728,
      "kl": 0.1488037109375,
      "learning_rate": 9.548e-07,
      "loss": 0.0001,
      "reward": 0.75,
      "reward_std": 0.0,
      "rewards/format_reward": 0.0,
      "rewards/score_reward": 0.75,
      "step": 113
    },
    {
      "clip_ratio": 0.0,
      "completion_length": 156.15625,
      "epoch": 0.456,
      "grad_norm": 2.3757565021514893,
      "kl": 0.2210693359375,
      "learning_rate": 9.544e-07,
      "loss": 0.0002,
      "reward": 0.28125,
      "reward_std": 0.0883883461356163,
      "rewards/format_reward": 0.0,
      "rewards/score_reward": 0.28125,
      "step": 114
    },
    {
      "clip_ratio": 0.0,
      "completion_length": 167.625,
      "epoch": 0.46,
      "grad_norm": 4.812951564788818,
      "kl": 0.1298828125,
      "learning_rate": 9.539999999999999e-07,
      "loss": 0.0001,
      "reward": 0.5625,
      "reward_std": 0.1157275140285492,
      "rewards/format_reward": 0.0,
      "rewards/score_reward": 0.5625,
      "step": 115
    },
    {
      "clip_ratio": 0.0,
      "completion_length": 154.96875,
      "epoch": 0.464,
      "grad_norm": 2.8628149032592773,
      "kl": 0.183349609375,
      "learning_rate": 9.536e-07,
      "loss": 0.0002,
      "reward": 0.0625,
      "reward_std": 0.1767766922712326,
      "rewards/format_reward": 0.0,
      "rewards/score_reward": 0.0625,
      "step": 116
    },
    {
      "clip_ratio": 0.0,
      "completion_length": 168.78125,
      "epoch": 0.468,
      "grad_norm": 0.01167032215744257,
      "kl": 0.123046875,
      "learning_rate": 9.532e-07,
      "loss": 0.0001,
      "reward": 0.5,
      "reward_std": 0.0,
      "rewards/format_reward": 0.0,
      "rewards/score_reward": 0.5,
      "step": 117
    },
    {
      "clip_ratio": 0.0,
      "completion_length": 164.46875,
      "epoch": 0.472,
      "grad_norm": 8.528116226196289,
      "kl": 0.150390625,
      "learning_rate": 9.527999999999999e-07,
      "loss": 0.0002,
      "reward": 0.09375,
      "reward_std": 0.2041158601641655,
      "rewards/format_reward": 0.0,
      "rewards/score_reward": 0.09375,
      "step": 118
    },
    {
      "clip_ratio": 0.0,
      "completion_length": 173.25,
      "epoch": 0.476,
      "grad_norm": 3.113943338394165,
      "kl": 0.1400146484375,
      "learning_rate": 9.524e-07,
      "loss": 0.0001,
      "reward": 0.28125,
      "reward_std": 0.0883883461356163,
      "rewards/format_reward": 0.0,
      "rewards/score_reward": 0.28125,
      "step": 119
    },
    {
      "clip_ratio": 0.0,
      "completion_length": 166.0,
      "epoch": 0.48,
      "grad_norm": 1.5100096464157104,
      "kl": 0.139404296875,
      "learning_rate": 9.52e-07,
      "loss": 0.0001,
      "reward": 0.21875,
      "reward_std": 0.0883883461356163,
      "rewards/format_reward": 0.0,
      "rewards/score_reward": 0.21875,
      "step": 120
    },
    {
      "clip_ratio": 0.0,
      "completion_length": 157.34375,
      "epoch": 0.484,
      "grad_norm": 2.4216766357421875,
      "kl": 0.1324462890625,
      "learning_rate": 9.515999999999999e-07,
      "loss": 0.0001,
      "reward": 0.71875,
      "reward_std": 0.0883883461356163,
      "rewards/format_reward": 0.0,
      "rewards/score_reward": 0.71875,
      "step": 121
    },
    {
      "clip_ratio": 0.0,
      "completion_length": 164.25,
      "epoch": 0.488,
      "grad_norm": 8.379853248596191,
      "kl": 0.146728515625,
      "learning_rate": 9.512e-07,
      "loss": 0.0001,
      "reward": 0.375,
      "reward_std": 0.3650856465101242,
      "rewards/format_reward": 0.0,
      "rewards/score_reward": 0.375,
      "step": 122
    },
    {
      "clip_ratio": 0.0,
      "completion_length": 176.40625,
      "epoch": 0.492,
      "grad_norm": 21.827362060546875,
      "kl": 0.1123046875,
      "learning_rate": 9.508e-07,
      "loss": 0.0001,
      "reward": 0.5,
      "reward_std": 0.1767766922712326,
      "rewards/format_reward": 0.0,
      "rewards/score_reward": 0.5,
      "step": 123
    },
    {
      "clip_ratio": 0.0,
      "completion_length": 165.84375,
      "epoch": 0.496,
      "grad_norm": 3.238415479660034,
      "kl": 0.10888671875,
      "learning_rate": 9.503999999999999e-07,
      "loss": 0.0001,
      "reward": 0.09375,
      "reward_std": 0.1293872892856598,
      "rewards/format_reward": 0.0,
      "rewards/score_reward": 0.09375,
      "step": 124
    },
    {
      "clip_ratio": 0.0,
      "completion_length": 176.3125,
      "epoch": 0.5,
      "grad_norm": 2.2066924571990967,
      "kl": 0.12939453125,
      "learning_rate": 9.499999999999999e-07,
      "loss": 0.0001,
      "reward": 0.1875,
      "reward_std": 0.1157275140285492,
      "rewards/format_reward": 0.0,
      "rewards/score_reward": 0.1875,
      "step": 125
    },
    {
      "clip_ratio": 0.0,
      "completion_length": 163.25,
      "epoch": 0.504,
      "grad_norm": 7.6757307052612305,
      "kl": 0.176025390625,
      "learning_rate": 9.496e-07,
      "loss": 0.0002,
      "reward": 0.15625,
      "reward_std": 0.1293872892856598,
      "rewards/format_reward": 0.0,
      "rewards/score_reward": 0.15625,
      "step": 126
    },
    {
      "clip_ratio": 0.0,
      "completion_length": 170.125,
      "epoch": 0.508,
      "grad_norm": 3.0611886978149414,
      "kl": 0.1181640625,
      "learning_rate": 9.492e-07,
      "loss": 0.0001,
      "reward": 0.375,
      "reward_std": 0.2177756354212761,
      "rewards/format_reward": 0.0,
      "rewards/score_reward": 0.375,
      "step": 127
    },
    {
      "clip_ratio": 0.0,
      "completion_length": 160.15625,
      "epoch": 0.512,
      "grad_norm": 0.009313968941569328,
      "kl": 0.11865234375,
      "learning_rate": 9.487999999999999e-07,
      "loss": 0.0001,
      "reward": 0.25,
      "reward_std": 0.0,
      "rewards/format_reward": 0.0,
      "rewards/score_reward": 0.25,
      "step": 128
    },
    {
      "clip_ratio": 0.0,
      "completion_length": 159.03125,
      "epoch": 0.516,
      "grad_norm": 1.8127228021621704,
      "kl": 0.1759033203125,
      "learning_rate": 9.484e-07,
      "loss": 0.0002,
      "reward": 0.71875,
      "reward_std": 0.0883883461356163,
      "rewards/format_reward": 0.0,
      "rewards/score_reward": 0.71875,
      "step": 129
    },
    {
      "clip_ratio": 0.0,
      "completion_length": 132.25,
      "epoch": 0.52,
      "grad_norm": 2.159052610397339,
      "kl": 0.1309814453125,
      "learning_rate": 9.479999999999999e-07,
      "loss": 0.0001,
      "reward": 0.28125,
      "reward_std": 0.0883883461356163,
      "rewards/format_reward": 0.0,
      "rewards/score_reward": 0.28125,
      "step": 130
    },
    {
      "clip_ratio": 0.0,
      "completion_length": 149.84375,
      "epoch": 0.524,
      "grad_norm": 5.0523552894592285,
      "kl": 0.15087890625,
      "learning_rate": 9.475999999999999e-07,
      "loss": 0.0002,
      "reward": 0.21875,
      "reward_std": 0.24511480331420898,
      "rewards/format_reward": 0.0,
      "rewards/score_reward": 0.21875,
      "step": 131
    },
    {
      "clip_ratio": 0.0,
      "completion_length": 146.65625,
      "epoch": 0.528,
      "grad_norm": 3.5751190185546875,
      "kl": 0.1422119140625,
      "learning_rate": 9.472e-07,
      "loss": 0.0001,
      "reward": 0.03125,
      "reward_std": 0.0883883461356163,
      "rewards/format_reward": 0.0,
      "rewards/score_reward": 0.03125,
      "step": 132
    },
    {
      "clip_ratio": 0.0,
      "completion_length": 138.75,
      "epoch": 0.532,
      "grad_norm": 7.118408203125,
      "kl": 0.1361083984375,
      "learning_rate": 9.468e-07,
      "loss": 0.0001,
      "reward": 0.46875,
      "reward_std": 0.2041158601641655,
      "rewards/format_reward": 0.0,
      "rewards/score_reward": 0.46875,
      "step": 133
    },
    {
      "clip_ratio": 0.0,
      "completion_length": 142.90625,
      "epoch": 0.536,
      "grad_norm": 7.05600118637085,
      "kl": 0.1453857421875,
      "learning_rate": 9.464e-07,
      "loss": 0.0001,
      "reward": 0.03125,
      "reward_std": 0.0883883461356163,
      "rewards/format_reward": 0.0,
      "rewards/score_reward": 0.03125,
      "step": 134
    },
    {
      "clip_ratio": 0.0,
      "completion_length": 146.53125,
      "epoch": 0.54,
      "grad_norm": 14.140984535217285,
      "kl": 0.24853515625,
      "learning_rate": 9.459999999999999e-07,
      "loss": 0.0002,
      "reward": 0.28125,
      "reward_std": 0.24511480331420898,
      "rewards/format_reward": 0.0,
      "rewards/score_reward": 0.28125,
      "step": 135
    },
    {
      "clip_ratio": 0.0,
      "completion_length": 140.25,
      "epoch": 0.544,
      "grad_norm": 10.306221961975098,
      "kl": 0.1552734375,
      "learning_rate": 9.456e-07,
      "loss": 0.0002,
      "reward": 0.25,
      "reward_std": 0.1767766922712326,
      "rewards/format_reward": 0.0,
      "rewards/score_reward": 0.25,
      "step": 136
    },
    {
      "clip_ratio": 0.0,
      "completion_length": 149.5,
      "epoch": 0.548,
      "grad_norm": 10.985379219055176,
      "kl": 0.150634765625,
      "learning_rate": 9.452e-07,
      "loss": 0.0002,
      "reward": 0.25,
      "reward_std": 0.3514062538743019,
      "rewards/format_reward": 0.0,
      "rewards/score_reward": 0.25,
      "step": 137
    },
    {
      "clip_ratio": 0.0,
      "completion_length": 143.25,
      "epoch": 0.552,
      "grad_norm": 5.7292022705078125,
      "kl": 0.164306640625,
      "learning_rate": 9.447999999999999e-07,
      "loss": 0.0002,
      "reward": 0.15625,
      "reward_std": 0.3061639815568924,
      "rewards/format_reward": 0.0,
      "rewards/score_reward": 0.15625,
      "step": 138
    },
    {
      "clip_ratio": 0.0,
      "completion_length": 152.625,
      "epoch": 0.556,
      "grad_norm": 8.641803741455078,
      "kl": 0.117431640625,
      "learning_rate": 9.444e-07,
      "loss": 0.0001,
      "reward": 0.28125,
      "reward_std": 0.24511480331420898,
      "rewards/format_reward": 0.0,
      "rewards/score_reward": 0.28125,
      "step": 139
    },
    {
      "clip_ratio": 0.0,
      "completion_length": 140.40625,
      "epoch": 0.56,
      "grad_norm": 3.8259010314941406,
      "kl": 0.18310546875,
      "learning_rate": 9.439999999999999e-07,
      "loss": 0.0002,
      "reward": 0.34375,
      "reward_std": 0.2041158601641655,
      "rewards/format_reward": 0.0,
      "rewards/score_reward": 0.34375,
      "step": 140
    },
    {
      "clip_ratio": 0.0,
      "completion_length": 142.0,
      "epoch": 0.564,
      "grad_norm": 0.026461126282811165,
      "kl": 0.150634765625,
      "learning_rate": 9.436e-07,
      "loss": 0.0002,
      "reward": 0.25,
      "reward_std": 0.0,
      "rewards/format_reward": 0.0,
      "rewards/score_reward": 0.25,
      "step": 141
    },
    {
      "clip_ratio": 0.0,
      "completion_length": 130.40625,
      "epoch": 0.568,
      "grad_norm": 20.714466094970703,
      "kl": 0.164306640625,
      "learning_rate": 9.432e-07,
      "loss": 0.0002,
      "reward": 0.75,
      "reward_std": 0.3335031494498253,
      "rewards/format_reward": 0.0,
      "rewards/score_reward": 0.75,
      "step": 142
    },
    {
      "clip_ratio": 0.0,
      "completion_length": 146.25,
      "epoch": 0.572,
      "grad_norm": 2.2029976844787598,
      "kl": 0.2403564453125,
      "learning_rate": 9.427999999999999e-07,
      "loss": 0.0002,
      "reward": 0.03125,
      "reward_std": 0.0883883461356163,
      "rewards/format_reward": 0.0,
      "rewards/score_reward": 0.03125,
      "step": 143
    },
    {
      "clip_ratio": 0.0,
      "completion_length": 157.15625,
      "epoch": 0.576,
      "grad_norm": 4.797538757324219,
      "kl": 0.125,
      "learning_rate": 9.424e-07,
      "loss": 0.0001,
      "reward": 0.03125,
      "reward_std": 0.0883883461356163,
      "rewards/format_reward": 0.0,
      "rewards/score_reward": 0.03125,
      "step": 144
    },
    {
      "clip_ratio": 0.0,
      "completion_length": 141.0625,
      "epoch": 0.58,
      "grad_norm": 4.411031723022461,
      "kl": 0.14599609375,
      "learning_rate": 9.419999999999999e-07,
      "loss": 0.0001,
      "reward": 0.21875,
      "reward_std": 0.0883883461356163,
      "rewards/format_reward": 0.0,
      "rewards/score_reward": 0.21875,
      "step": 145
    },
    {
      "clip_ratio": 0.0,
      "completion_length": 149.6875,
      "epoch": 0.584,
      "grad_norm": 13.82177448272705,
      "kl": 0.1361083984375,
      "learning_rate": 9.415999999999999e-07,
      "loss": 0.0001,
      "reward": 0.46875,
      "reward_std": 0.2041158601641655,
      "rewards/format_reward": 0.0,
      "rewards/score_reward": 0.46875,
      "step": 146
    },
    {
      "clip_ratio": 0.0,
      "completion_length": 143.125,
      "epoch": 0.588,
      "grad_norm": 3.6890528202056885,
      "kl": 0.1322021484375,
      "learning_rate": 9.412e-07,
      "loss": 0.0001,
      "reward": 0.0625,
      "reward_std": 0.1157275140285492,
      "rewards/format_reward": 0.0,
      "rewards/score_reward": 0.0625,
      "step": 147
    },
    {
      "clip_ratio": 0.0,
      "completion_length": 156.0,
      "epoch": 0.592,
      "grad_norm": 7.011545181274414,
      "kl": 0.153564453125,
      "learning_rate": 9.408e-07,
      "loss": 0.0002,
      "reward": 0.5,
      "reward_std": 0.26726123690605164,
      "rewards/format_reward": 0.0,
      "rewards/score_reward": 0.5,
      "step": 148
    },
    {
      "clip_ratio": 0.0,
      "completion_length": 153.5625,
      "epoch": 0.596,
      "grad_norm": 7.351828098297119,
      "kl": 0.1778564453125,
      "learning_rate": 9.403999999999999e-07,
      "loss": 0.0002,
      "reward": 0.34375,
      "reward_std": 0.22201896458864212,
      "rewards/format_reward": 0.0,
      "rewards/score_reward": 0.34375,
      "step": 149
    },
    {
      "clip_ratio": 0.0,
      "completion_length": 142.5625,
      "epoch": 0.6,
      "grad_norm": 3.5653135776519775,
      "kl": 0.1507568359375,
      "learning_rate": 9.399999999999999e-07,
      "loss": 0.0002,
      "reward": 0.5,
      "reward_std": 0.1767766922712326,
      "rewards/format_reward": 0.0,
      "rewards/score_reward": 0.5,
      "step": 150
    },
    {
      "clip_ratio": 0.0,
      "completion_length": 135.15625,
      "epoch": 0.604,
      "grad_norm": 2.1044363975524902,
      "kl": 0.168701171875,
      "learning_rate": 9.396e-07,
      "loss": 0.0002,
      "reward": 0.46875,
      "reward_std": 0.0883883461356163,
      "rewards/format_reward": 0.0,
      "rewards/score_reward": 0.46875,
      "step": 151
    },
    {
      "clip_ratio": 0.0,
      "completion_length": 153.0,
      "epoch": 0.608,
      "grad_norm": 5.389544486999512,
      "kl": 0.1319580078125,
      "learning_rate": 9.391999999999999e-07,
      "loss": 0.0001,
      "reward": 0.25,
      "reward_std": 0.2587745785713196,
      "rewards/format_reward": 0.0,
      "rewards/score_reward": 0.25,
      "step": 152
    },
    {
      "clip_ratio": 0.0,
      "completion_length": 143.625,
      "epoch": 0.612,
      "grad_norm": 7.576977729797363,
      "kl": 0.154541015625,
      "learning_rate": 9.387999999999999e-07,
      "loss": 0.0002,
      "reward": 0.21875,
      "reward_std": 0.24511480331420898,
      "rewards/format_reward": 0.0,
      "rewards/score_reward": 0.21875,
      "step": 153
    },
    {
      "clip_ratio": 0.0,
      "completion_length": 154.96875,
      "epoch": 0.616,
      "grad_norm": 17.224998474121094,
      "kl": 0.1458740234375,
      "learning_rate": 9.384e-07,
      "loss": 0.0001,
      "reward": 0.4375,
      "reward_std": 0.1767766922712326,
      "rewards/format_reward": 0.0,
      "rewards/score_reward": 0.4375,
      "step": 154
    },
    {
      "clip_ratio": 0.0,
      "completion_length": 130.90625,
      "epoch": 0.62,
      "grad_norm": 6.7807297706604,
      "kl": 0.1806640625,
      "learning_rate": 9.379999999999998e-07,
      "loss": 0.0002,
      "reward": 0.28125,
      "reward_std": 0.0883883461356163,
      "rewards/format_reward": 0.0,
      "rewards/score_reward": 0.28125,
      "step": 155
    },
    {
      "clip_ratio": 0.0,
      "completion_length": 138.875,
      "epoch": 0.624,
      "grad_norm": 24.668161392211914,
      "kl": 0.158935546875,
      "learning_rate": 9.375999999999999e-07,
      "loss": 0.0002,
      "reward": 0.25,
      "reward_std": 0.3650856465101242,
      "rewards/format_reward": 0.0,
      "rewards/score_reward": 0.25,
      "step": 156
    },
    {
      "clip_ratio": 0.0,
      "completion_length": 154.71875,
      "epoch": 0.628,
      "grad_norm": 3.2327768802642822,
      "kl": 0.153076171875,
      "learning_rate": 9.372e-07,
      "loss": 0.0002,
      "reward": 0.0625,
      "reward_std": 0.1157275140285492,
      "rewards/format_reward": 0.0,
      "rewards/score_reward": 0.0625,
      "step": 157
    },
    {
      "clip_ratio": 0.0,
      "completion_length": 150.53125,
      "epoch": 0.632,
      "grad_norm": 4.513970851898193,
      "kl": 0.17236328125,
      "learning_rate": 9.368e-07,
      "loss": 0.0002,
      "reward": 0.3125,
      "reward_std": 0.1767766922712326,
      "rewards/format_reward": 0.0,
      "rewards/score_reward": 0.3125,
      "step": 158
    },
    {
      "clip_ratio": 0.0,
      "completion_length": 125.9375,
      "epoch": 0.636,
      "grad_norm": 0.025679027661681175,
      "kl": 0.18505859375,
      "learning_rate": 9.363999999999999e-07,
      "loss": 0.0002,
      "reward": 0.25,
      "reward_std": 0.0,
      "rewards/format_reward": 0.0,
      "rewards/score_reward": 0.25,
      "step": 159
    },
    {
      "clip_ratio": 0.0,
      "completion_length": 130.125,
      "epoch": 0.64,
      "grad_norm": 2.8930089473724365,
      "kl": 0.193359375,
      "learning_rate": 9.36e-07,
      "loss": 0.0002,
      "reward": 0.3125,
      "reward_std": 0.1157275140285492,
      "rewards/format_reward": 0.0,
      "rewards/score_reward": 0.3125,
      "step": 160
    },
    {
      "clip_ratio": 0.0,
      "completion_length": 156.65625,
      "epoch": 0.644,
      "grad_norm": 4.403336048126221,
      "kl": 0.16552734375,
      "learning_rate": 9.356e-07,
      "loss": 0.0002,
      "reward": 0.28125,
      "reward_std": 0.2041158601641655,
      "rewards/format_reward": 0.0,
      "rewards/score_reward": 0.28125,
      "step": 161
    },
    {
      "clip_ratio": 0.0,
      "completion_length": 151.75,
      "epoch": 0.648,
      "grad_norm": 9.439102172851562,
      "kl": 0.152587890625,
      "learning_rate": 9.352e-07,
      "loss": 0.0002,
      "reward": 0.4375,
      "reward_std": 0.2925042062997818,
      "rewards/format_reward": 0.0,
      "rewards/score_reward": 0.4375,
      "step": 162
    },
    {
      "clip_ratio": 0.0,
      "completion_length": 128.6875,
      "epoch": 0.652,
      "grad_norm": 0.018322864547371864,
      "kl": 0.18701171875,
      "learning_rate": 9.347999999999999e-07,
      "loss": 0.0002,
      "reward": 0.5,
      "reward_std": 0.0,
      "rewards/format_reward": 0.0,
      "rewards/score_reward": 0.5,
      "step": 163
    },
    {
      "clip_ratio": 0.0,
      "completion_length": 144.375,
      "epoch": 0.656,
      "grad_norm": 3.9991912841796875,
      "kl": 0.1630859375,
      "learning_rate": 9.344e-07,
      "loss": 0.0002,
      "reward": 0.21875,
      "reward_std": 0.2041158601641655,
      "rewards/format_reward": 0.0,
      "rewards/score_reward": 0.21875,
      "step": 164
    },
    {
      "clip_ratio": 0.0,
      "completion_length": 140.125,
      "epoch": 0.66,
      "grad_norm": 9.71346378326416,
      "kl": 0.188720703125,
      "learning_rate": 9.34e-07,
      "loss": 0.0002,
      "reward": 0.5625,
      "reward_std": 0.2177756354212761,
      "rewards/format_reward": 0.0,
      "rewards/score_reward": 0.5625,
      "step": 165
    },
    {
      "clip_ratio": 0.0,
      "completion_length": 158.96875,
      "epoch": 0.664,
      "grad_norm": 4.799767971038818,
      "kl": 0.1461181640625,
      "learning_rate": 9.335999999999999e-07,
      "loss": 0.0001,
      "reward": 0.34375,
      "reward_std": 0.1293872892856598,
      "rewards/format_reward": 0.0,
      "rewards/score_reward": 0.34375,
      "step": 166
    },
    {
      "clip_ratio": 0.0,
      "completion_length": 160.78125,
      "epoch": 0.668,
      "grad_norm": 2.5199387073516846,
      "kl": 0.1396484375,
      "learning_rate": 9.332e-07,
      "loss": 0.0001,
      "reward": 0.46875,
      "reward_std": 0.0883883461356163,
      "rewards/format_reward": 0.0,
      "rewards/score_reward": 0.46875,
      "step": 167
    },
    {
      "clip_ratio": 0.0,
      "completion_length": 158.875,
      "epoch": 0.672,
      "grad_norm": 6.527361869812012,
      "kl": 0.192138671875,
      "learning_rate": 9.327999999999999e-07,
      "loss": 0.0002,
      "reward": 0.125,
      "reward_std": 0.2177756354212761,
      "rewards/format_reward": 0.0,
      "rewards/score_reward": 0.125,
      "step": 168
    },
    {
      "clip_ratio": 0.0,
      "completion_length": 149.96875,
      "epoch": 0.676,
      "grad_norm": 2.801525592803955,
      "kl": 0.2891845703125,
      "learning_rate": 9.324e-07,
      "loss": 0.0003,
      "reward": 0.46875,
      "reward_std": 0.0883883461356163,
      "rewards/format_reward": 0.0,
      "rewards/score_reward": 0.46875,
      "step": 169
    },
    {
      "clip_ratio": 0.0,
      "completion_length": 149.53125,
      "epoch": 0.68,
      "grad_norm": 8.147767066955566,
      "kl": 0.18017578125,
      "learning_rate": 9.32e-07,
      "loss": 0.0002,
      "reward": 0.3125,
      "reward_std": 0.2177756354212761,
      "rewards/format_reward": 0.0,
      "rewards/score_reward": 0.3125,
      "step": 170
    },
    {
      "clip_ratio": 0.0,
      "completion_length": 165.625,
      "epoch": 0.684,
      "grad_norm": 4.073009967803955,
      "kl": 0.20751953125,
      "learning_rate": 9.315999999999999e-07,
      "loss": 0.0002,
      "reward": 0.25,
      "reward_std": 0.3335031494498253,
      "rewards/format_reward": 0.0,
      "rewards/score_reward": 0.25,
      "step": 171
    },
    {
      "clip_ratio": 0.0,
      "completion_length": 165.25,
      "epoch": 0.688,
      "grad_norm": 6.553722858428955,
      "kl": 0.1534423828125,
      "learning_rate": 9.312e-07,
      "loss": 0.0002,
      "reward": 0.3125,
      "reward_std": 0.2177756354212761,
      "rewards/format_reward": 0.0,
      "rewards/score_reward": 0.3125,
      "step": 172
    },
    {
      "clip_ratio": 0.0,
      "completion_length": 174.40625,
      "epoch": 0.692,
      "grad_norm": 4.628172874450684,
      "kl": 0.14404296875,
      "learning_rate": 9.307999999999999e-07,
      "loss": 0.0001,
      "reward": 0.03125,
      "reward_std": 0.0883883461356163,
      "rewards/format_reward": 0.0,
      "rewards/score_reward": 0.03125,
      "step": 173
    },
    {
      "clip_ratio": 0.0,
      "completion_length": 173.96875,
      "epoch": 0.696,
      "grad_norm": 0.014567671343684196,
      "kl": 0.133544921875,
      "learning_rate": 9.303999999999999e-07,
      "loss": 0.0001,
      "reward": 0.0,
      "reward_std": 0.0,
      "rewards/format_reward": 0.0,
      "rewards/score_reward": 0.0,
      "step": 174
    },
    {
      "clip_ratio": 0.0,
      "completion_length": 144.1875,
      "epoch": 0.7,
      "grad_norm": 0.012290208600461483,
      "kl": 0.155517578125,
      "learning_rate": 9.3e-07,
      "loss": 0.0002,
      "reward": 0.75,
      "reward_std": 0.0,
      "rewards/format_reward": 0.0,
      "rewards/score_reward": 0.75,
      "step": 175
    },
    {
      "clip_ratio": 0.0,
      "completion_length": 152.25,
      "epoch": 0.704,
      "grad_norm": 4.443714141845703,
      "kl": 0.1324462890625,
      "learning_rate": 9.296e-07,
      "loss": 0.0001,
      "reward": 0.46875,
      "reward_std": 0.2041158601641655,
      "rewards/format_reward": 0.0,
      "rewards/score_reward": 0.46875,
      "step": 176
    },
    {
      "clip_ratio": 0.0,
      "completion_length": 155.40625,
      "epoch": 0.708,
      "grad_norm": 0.017265308648347855,
      "kl": 0.1400146484375,
      "learning_rate": 9.292e-07,
      "loss": 0.0001,
      "reward": 0.0,
      "reward_std": 0.0,
      "rewards/format_reward": 0.0,
      "rewards/score_reward": 0.0,
      "step": 177
    },
    {
      "clip_ratio": 0.0,
      "completion_length": 150.0625,
      "epoch": 0.712,
      "grad_norm": 2.628682851791382,
      "kl": 0.1719970703125,
      "learning_rate": 9.287999999999999e-07,
      "loss": 0.0002,
      "reward": 0.3125,
      "reward_std": 0.1157275140285492,
      "rewards/format_reward": 0.0,
      "rewards/score_reward": 0.3125,
      "step": 178
    },
    {
      "clip_ratio": 0.0,
      "completion_length": 162.46875,
      "epoch": 0.716,
      "grad_norm": 6.353070259094238,
      "kl": 0.14990234375,
      "learning_rate": 9.284e-07,
      "loss": 0.0001,
      "reward": 0.84375,
      "reward_std": 0.3061639815568924,
      "rewards/format_reward": 0.0,
      "rewards/score_reward": 0.84375,
      "step": 179
    },
    {
      "clip_ratio": 0.0,
      "completion_length": 133.40625,
      "epoch": 0.72,
      "grad_norm": 8.15472412109375,
      "kl": 0.16064453125,
      "learning_rate": 9.28e-07,
      "loss": 0.0002,
      "reward": 0.46875,
      "reward_std": 0.0883883461356163,
      "rewards/format_reward": 0.0,
      "rewards/score_reward": 0.46875,
      "step": 180
    },
    {
      "clip_ratio": 0.0,
      "completion_length": 138.71875,
      "epoch": 0.724,
      "grad_norm": 5.264553070068359,
      "kl": 0.15869140625,
      "learning_rate": 9.275999999999999e-07,
      "loss": 0.0002,
      "reward": 0.1875,
      "reward_std": 0.2177756354212761,
      "rewards/format_reward": 0.0,
      "rewards/score_reward": 0.1875,
      "step": 181
    },
    {
      "clip_ratio": 0.0,
      "completion_length": 150.8125,
      "epoch": 0.728,
      "grad_norm": 7.217442989349365,
      "kl": 0.15283203125,
      "learning_rate": 9.272e-07,
      "loss": 0.0002,
      "reward": 0.0625,
      "reward_std": 0.1157275140285492,
      "rewards/format_reward": 0.0,
      "rewards/score_reward": 0.0625,
      "step": 182
    },
    {
      "clip_ratio": 0.0,
      "completion_length": 157.875,
      "epoch": 0.732,
      "grad_norm": 3.5819404125213623,
      "kl": 0.167236328125,
      "learning_rate": 9.268e-07,
      "loss": 0.0002,
      "reward": 0.53125,
      "reward_std": 0.2041158601641655,
      "rewards/format_reward": 0.0,
      "rewards/score_reward": 0.53125,
      "step": 183
    },
    {
      "clip_ratio": 0.0,
      "completion_length": 152.53125,
      "epoch": 0.736,
      "grad_norm": 20.323453903198242,
      "kl": 0.172119140625,
      "learning_rate": 9.263999999999999e-07,
      "loss": 0.0002,
      "reward": 0.21875,
      "reward_std": 0.0883883461356163,
      "rewards/format_reward": 0.0,
      "rewards/score_reward": 0.21875,
      "step": 184
    },
    {
      "clip_ratio": 0.0,
      "completion_length": 144.90625,
      "epoch": 0.74,
      "grad_norm": 0.01625896245241165,
      "kl": 0.1708984375,
      "learning_rate": 9.26e-07,
      "loss": 0.0002,
      "reward": 0.25,
      "reward_std": 0.0,
      "rewards/format_reward": 0.0,
      "rewards/score_reward": 0.25,
      "step": 185
    },
    {
      "clip_ratio": 0.0,
      "completion_length": 142.6875,
      "epoch": 0.744,
      "grad_norm": 7.118624687194824,
      "kl": 0.15478515625,
      "learning_rate": 9.256e-07,
      "loss": 0.0002,
      "reward": 0.53125,
      "reward_std": 0.0883883461356163,
      "rewards/format_reward": 0.0,
      "rewards/score_reward": 0.53125,
      "step": 186
    },
    {
      "clip_ratio": 0.0,
      "completion_length": 150.0,
      "epoch": 0.748,
      "grad_norm": 0.018267452716827393,
      "kl": 0.157470703125,
      "learning_rate": 9.251999999999999e-07,
      "loss": 0.0002,
      "reward": 0.75,
      "reward_std": 0.0,
      "rewards/format_reward": 0.0,
      "rewards/score_reward": 0.75,
      "step": 187
    },
    {
      "clip_ratio": 0.0,
      "completion_length": 156.25,
      "epoch": 0.752,
      "grad_norm": 4.424862861633301,
      "kl": 0.1611328125,
      "learning_rate": 9.247999999999999e-07,
      "loss": 0.0002,
      "reward": 0.53125,
      "reward_std": 0.0883883461356163,
      "rewards/format_reward": 0.0,
      "rewards/score_reward": 0.53125,
      "step": 188
    },
    {
      "clip_ratio": 0.0,
      "completion_length": 145.34375,
      "epoch": 0.756,
      "grad_norm": 5.989232063293457,
      "kl": 0.29541015625,
      "learning_rate": 9.244e-07,
      "loss": 0.0003,
      "reward": 0.53125,
      "reward_std": 0.2630179077386856,
      "rewards/format_reward": 0.0,
      "rewards/score_reward": 0.53125,
      "step": 189
    },
    {
      "clip_ratio": 0.0,
      "completion_length": 147.0625,
      "epoch": 0.76,
      "grad_norm": 5.551213264465332,
      "kl": 0.17138671875,
      "learning_rate": 9.24e-07,
      "loss": 0.0002,
      "reward": 0.5625,
      "reward_std": 0.2177756354212761,
      "rewards/format_reward": 0.0,
      "rewards/score_reward": 0.5625,
      "step": 190
    },
    {
      "clip_ratio": 0.0,
      "completion_length": 139.84375,
      "epoch": 0.764,
      "grad_norm": 3.024784803390503,
      "kl": 0.162841796875,
      "learning_rate": 9.235999999999999e-07,
      "loss": 0.0002,
      "reward": 0.4375,
      "reward_std": 0.1157275140285492,
      "rewards/format_reward": 0.0,
      "rewards/score_reward": 0.4375,
      "step": 191
    },
    {
      "clip_ratio": 0.0,
      "completion_length": 164.21875,
      "epoch": 0.768,
      "grad_norm": 2.841665744781494,
      "kl": 0.18115234375,
      "learning_rate": 9.232e-07,
      "loss": 0.0002,
      "reward": 0.21875,
      "reward_std": 0.0883883461356163,
      "rewards/format_reward": 0.0,
      "rewards/score_reward": 0.21875,
      "step": 192
    },
    {
      "clip_ratio": 0.0,
      "completion_length": 144.15625,
      "epoch": 0.772,
      "grad_norm": 0.2720145285129547,
      "kl": 0.3896484375,
      "learning_rate": 9.227999999999999e-07,
      "loss": 0.0004,
      "reward": 0.25,
      "reward_std": 0.0,
      "rewards/format_reward": 0.0,
      "rewards/score_reward": 0.25,
      "step": 193
    },
    {
      "clip_ratio": 0.0,
      "completion_length": 134.84375,
      "epoch": 0.776,
      "grad_norm": 13.293619155883789,
      "kl": 0.171630859375,
      "learning_rate": 9.224e-07,
      "loss": 0.0002,
      "reward": 0.375,
      "reward_std": 0.2177756354212761,
      "rewards/format_reward": 0.0,
      "rewards/score_reward": 0.375,
      "step": 194
    },
    {
      "clip_ratio": 0.0,
      "completion_length": 146.0,
      "epoch": 0.78,
      "grad_norm": 4.161295413970947,
      "kl": 0.1806640625,
      "learning_rate": 9.22e-07,
      "loss": 0.0002,
      "reward": 0.0625,
      "reward_std": 0.1767766922712326,
      "rewards/format_reward": 0.0,
      "rewards/score_reward": 0.0625,
      "step": 195
    },
    {
      "clip_ratio": 0.0,
      "completion_length": 126.53125,
      "epoch": 0.784,
      "grad_norm": 2.5194199085235596,
      "kl": 0.1943359375,
      "learning_rate": 9.215999999999999e-07,
      "loss": 0.0002,
      "reward": 0.09375,
      "reward_std": 0.1293872892856598,
      "rewards/format_reward": 0.0,
      "rewards/score_reward": 0.09375,
      "step": 196
    },
    {
      "clip_ratio": 0.0,
      "completion_length": 155.9375,
      "epoch": 0.788,
      "grad_norm": 0.013363498263061047,
      "kl": 0.154052734375,
      "learning_rate": 9.212e-07,
      "loss": 0.0002,
      "reward": 0.0,
      "reward_std": 0.0,
      "rewards/format_reward": 0.0,
      "rewards/score_reward": 0.0,
      "step": 197
    },
    {
      "clip_ratio": 0.0,
      "completion_length": 148.5,
      "epoch": 0.792,
      "grad_norm": 0.011504505760967731,
      "kl": 0.169921875,
      "learning_rate": 9.207999999999999e-07,
      "loss": 0.0002,
      "reward": 0.0,
      "reward_std": 0.0,
      "rewards/format_reward": 0.0,
      "rewards/score_reward": 0.0,
      "step": 198
    },
    {
      "clip_ratio": 0.0,
      "completion_length": 148.34375,
      "epoch": 0.796,
      "grad_norm": 3.968836545944214,
      "kl": 0.1748046875,
      "learning_rate": 9.203999999999999e-07,
      "loss": 0.0002,
      "reward": 0.1875,
      "reward_std": 0.1157275140285492,
      "rewards/format_reward": 0.0,
      "rewards/score_reward": 0.1875,
      "step": 199
    },
    {
      "clip_ratio": 0.0,
      "completion_length": 148.65625,
      "epoch": 0.8,
      "grad_norm": 0.018608927726745605,
      "kl": 0.1884765625,
      "learning_rate": 9.2e-07,
      "loss": 0.0002,
      "reward": 0.0,
      "reward_std": 0.0,
      "rewards/format_reward": 0.0,
      "rewards/score_reward": 0.0,
      "step": 200
    },
    {
      "clip_ratio": 0.0,
      "completion_length": 148.78125,
      "epoch": 0.804,
      "grad_norm": 7.09287166595459,
      "kl": 0.186767578125,
      "learning_rate": 9.196e-07,
      "loss": 0.0002,
      "reward": 0.0625,
      "reward_std": 0.1767766922712326,
      "rewards/format_reward": 0.0,
      "rewards/score_reward": 0.0625,
      "step": 201
    },
    {
      "clip_ratio": 0.0,
      "completion_length": 127.8125,
      "epoch": 0.808,
      "grad_norm": 0.012347673065960407,
      "kl": 0.1826171875,
      "learning_rate": 9.192e-07,
      "loss": 0.0002,
      "reward": 0.0,
      "reward_std": 0.0,
      "rewards/format_reward": 0.0,
      "rewards/score_reward": 0.0,
      "step": 202
    },
    {
      "clip_ratio": 0.0,
      "completion_length": 134.8125,
      "epoch": 0.812,
      "grad_norm": 5.15930700302124,
      "kl": 0.170654296875,
      "learning_rate": 9.187999999999999e-07,
      "loss": 0.0002,
      "reward": 0.1875,
      "reward_std": 0.2177756354212761,
      "rewards/format_reward": 0.0,
      "rewards/score_reward": 0.1875,
      "step": 203
    },
    {
      "clip_ratio": 0.0,
      "completion_length": 131.0,
      "epoch": 0.816,
      "grad_norm": 6.69101619720459,
      "kl": 0.175048828125,
      "learning_rate": 9.184e-07,
      "loss": 0.0002,
      "reward": 0.1875,
      "reward_std": 0.2177756354212761,
      "rewards/format_reward": 0.0,
      "rewards/score_reward": 0.1875,
      "step": 204
    },
    {
      "clip_ratio": 0.0,
      "completion_length": 143.4375,
      "epoch": 0.82,
      "grad_norm": 11.913467407226562,
      "kl": 0.16259765625,
      "learning_rate": 9.18e-07,
      "loss": 0.0002,
      "reward": 0.53125,
      "reward_std": 0.2651650384068489,
      "rewards/format_reward": 0.0,
      "rewards/score_reward": 0.53125,
      "step": 205
    },
    {
      "clip_ratio": 0.0,
      "completion_length": 140.6875,
      "epoch": 0.824,
      "grad_norm": 0.013337607495486736,
      "kl": 0.1787109375,
      "learning_rate": 9.175999999999999e-07,
      "loss": 0.0002,
      "reward": 0.25,
      "reward_std": 0.0,
      "rewards/format_reward": 0.0,
      "rewards/score_reward": 0.25,
      "step": 206
    },
    {
      "clip_ratio": 0.0,
      "completion_length": 138.875,
      "epoch": 0.828,
      "grad_norm": 3.1044652462005615,
      "kl": 0.192138671875,
      "learning_rate": 9.172e-07,
      "loss": 0.0002,
      "reward": 0.03125,
      "reward_std": 0.0883883461356163,
      "rewards/format_reward": 0.0,
      "rewards/score_reward": 0.03125,
      "step": 207
    },
    {
      "clip_ratio": 0.0,
      "completion_length": 136.90625,
      "epoch": 0.832,
      "grad_norm": 4.334849834442139,
      "kl": 0.159912109375,
      "learning_rate": 9.168e-07,
      "loss": 0.0002,
      "reward": 0.5,
      "reward_std": 0.1767766922712326,
      "rewards/format_reward": 0.0,
      "rewards/score_reward": 0.5,
      "step": 208
    },
    {
      "clip_ratio": 0.0,
      "completion_length": 138.84375,
      "epoch": 0.836,
      "grad_norm": 0.02636542171239853,
      "kl": 0.161865234375,
      "learning_rate": 9.163999999999999e-07,
      "loss": 0.0002,
      "reward": 0.25,
      "reward_std": 0.0,
      "rewards/format_reward": 0.0,
      "rewards/score_reward": 0.25,
      "step": 209
    },
    {
      "clip_ratio": 0.0,
      "completion_length": 125.65625,
      "epoch": 0.84,
      "grad_norm": 22.57999038696289,
      "kl": 0.178466796875,
      "learning_rate": 9.16e-07,
      "loss": 0.0002,
      "reward": 0.4375,
      "reward_std": 0.2177756354212761,
      "rewards/format_reward": 0.0,
      "rewards/score_reward": 0.4375,
      "step": 210
    },
    {
      "clip_ratio": 0.0,
      "completion_length": 138.4375,
      "epoch": 0.844,
      "grad_norm": 13.246150016784668,
      "kl": 0.298583984375,
      "learning_rate": 9.156e-07,
      "loss": 0.0003,
      "reward": 0.15625,
      "reward_std": 0.22201896458864212,
      "rewards/format_reward": 0.0,
      "rewards/score_reward": 0.15625,
      "step": 211
    },
    {
      "clip_ratio": 0.0,
      "completion_length": 151.25,
      "epoch": 0.848,
      "grad_norm": 6.394719123840332,
      "kl": 0.1474609375,
      "learning_rate": 9.151999999999999e-07,
      "loss": 0.0001,
      "reward": 0.0625,
      "reward_std": 0.1767766922712326,
      "rewards/format_reward": 0.0,
      "rewards/score_reward": 0.0625,
      "step": 212
    },
    {
      "clip_ratio": 0.0,
      "completion_length": 135.9375,
      "epoch": 0.852,
      "grad_norm": 4.514334201812744,
      "kl": 0.180419921875,
      "learning_rate": 9.147999999999999e-07,
      "loss": 0.0002,
      "reward": 0.5,
      "reward_std": 0.3335031494498253,
      "rewards/format_reward": 0.0,
      "rewards/score_reward": 0.5,
      "step": 213
    },
    {
      "clip_ratio": 0.0,
      "completion_length": 158.84375,
      "epoch": 0.856,
      "grad_norm": 4.87898588180542,
      "kl": 0.2811279296875,
      "learning_rate": 9.144e-07,
      "loss": 0.0003,
      "reward": 0.09375,
      "reward_std": 0.1293872892856598,
      "rewards/format_reward": 0.0,
      "rewards/score_reward": 0.09375,
      "step": 214
    },
    {
      "clip_ratio": 0.0,
      "completion_length": 161.3125,
      "epoch": 0.86,
      "grad_norm": 4.790887355804443,
      "kl": 0.15283203125,
      "learning_rate": 9.14e-07,
      "loss": 0.0002,
      "reward": 0.40625,
      "reward_std": 0.3198433741927147,
      "rewards/format_reward": 0.0,
      "rewards/score_reward": 0.40625,
      "step": 215
    },
    {
      "clip_ratio": 0.0,
      "completion_length": 148.53125,
      "epoch": 0.864,
      "grad_norm": 9.748350143432617,
      "kl": 0.176025390625,
      "learning_rate": 9.135999999999999e-07,
      "loss": 0.0002,
      "reward": 0.40625,
      "reward_std": 0.3198433741927147,
      "rewards/format_reward": 0.0,
      "rewards/score_reward": 0.40625,
      "step": 216
    },
    {
      "clip_ratio": 0.0,
      "completion_length": 148.21875,
      "epoch": 0.868,
      "grad_norm": 3.753589391708374,
      "kl": 0.16259765625,
      "learning_rate": 9.132e-07,
      "loss": 0.0002,
      "reward": 0.28125,
      "reward_std": 0.2630179077386856,
      "rewards/format_reward": 0.0,
      "rewards/score_reward": 0.28125,
      "step": 217
    },
    {
      "clip_ratio": 0.0,
      "completion_length": 132.125,
      "epoch": 0.872,
      "grad_norm": 5.923015594482422,
      "kl": 0.17041015625,
      "learning_rate": 9.127999999999999e-07,
      "loss": 0.0002,
      "reward": 0.375,
      "reward_std": 0.3650856465101242,
      "rewards/format_reward": 0.0,
      "rewards/score_reward": 0.375,
      "step": 218
    },
    {
      "clip_ratio": 0.0,
      "completion_length": 133.28125,
      "epoch": 0.876,
      "grad_norm": 5.67153787612915,
      "kl": 0.1689453125,
      "learning_rate": 9.123999999999999e-07,
      "loss": 0.0002,
      "reward": 0.03125,
      "reward_std": 0.0883883461356163,
      "rewards/format_reward": 0.0,
      "rewards/score_reward": 0.03125,
      "step": 219
    },
    {
      "clip_ratio": 0.0,
      "completion_length": 140.90625,
      "epoch": 0.88,
      "grad_norm": 2.6040894985198975,
      "kl": 0.15185546875,
      "learning_rate": 9.12e-07,
      "loss": 0.0002,
      "reward": 0.1875,
      "reward_std": 0.1157275140285492,
      "rewards/format_reward": 0.0,
      "rewards/score_reward": 0.1875,
      "step": 220
    },
    {
      "clip_ratio": 0.0,
      "completion_length": 134.71875,
      "epoch": 0.884,
      "grad_norm": 4.3682379722595215,
      "kl": 0.16845703125,
      "learning_rate": 9.115999999999999e-07,
      "loss": 0.0002,
      "reward": 0.40625,
      "reward_std": 0.22201896458864212,
      "rewards/format_reward": 0.0,
      "rewards/score_reward": 0.40625,
      "step": 221
    },
    {
      "clip_ratio": 0.0,
      "completion_length": 149.0,
      "epoch": 0.888,
      "grad_norm": 7.323733806610107,
      "kl": 0.158203125,
      "learning_rate": 9.112e-07,
      "loss": 0.0002,
      "reward": 0.5625,
      "reward_std": 0.4355512708425522,
      "rewards/format_reward": 0.0,
      "rewards/score_reward": 0.5625,
      "step": 222
    },
    {
      "clip_ratio": 0.0,
      "completion_length": 133.3125,
      "epoch": 0.892,
      "grad_norm": 8.492609977722168,
      "kl": 0.1689453125,
      "learning_rate": 9.108e-07,
      "loss": 0.0002,
      "reward": 0.5,
      "reward_std": 0.3745020925998688,
      "rewards/format_reward": 0.0,
      "rewards/score_reward": 0.5,
      "step": 223
    },
    {
      "clip_ratio": 0.0,
      "completion_length": 124.625,
      "epoch": 0.896,
      "grad_norm": 4.2470622062683105,
      "kl": 0.300537109375,
      "learning_rate": 9.103999999999999e-07,
      "loss": 0.0003,
      "reward": 0.3125,
      "reward_std": 0.1157275140285492,
      "rewards/format_reward": 0.0,
      "rewards/score_reward": 0.3125,
      "step": 224
    },
    {
      "clip_ratio": 0.0,
      "completion_length": 117.75,
      "epoch": 0.9,
      "grad_norm": 2.365232467651367,
      "kl": 0.175048828125,
      "learning_rate": 9.1e-07,
      "loss": 0.0002,
      "reward": 0.3125,
      "reward_std": 0.1157275140285492,
      "rewards/format_reward": 0.0,
      "rewards/score_reward": 0.3125,
      "step": 225
    },
    {
      "clip_ratio": 0.0,
      "completion_length": 126.9375,
      "epoch": 0.904,
      "grad_norm": 5.005716323852539,
      "kl": 0.184814453125,
      "learning_rate": 9.095999999999999e-07,
      "loss": 0.0002,
      "reward": 0.15625,
      "reward_std": 0.22201896458864212,
      "rewards/format_reward": 0.0,
      "rewards/score_reward": 0.15625,
      "step": 226
    },
    {
      "clip_ratio": 0.0,
      "completion_length": 145.34375,
      "epoch": 0.908,
      "grad_norm": 3.4398090839385986,
      "kl": 0.403076171875,
      "learning_rate": 9.092e-07,
      "loss": 0.0004,
      "reward": 0.28125,
      "reward_std": 0.0883883461356163,
      "rewards/format_reward": 0.0,
      "rewards/score_reward": 0.28125,
      "step": 227
    },
    {
      "clip_ratio": 0.0,
      "completion_length": 126.3125,
      "epoch": 0.912,
      "grad_norm": 5.781132698059082,
      "kl": 0.185546875,
      "learning_rate": 9.088e-07,
      "loss": 0.0002,
      "reward": 0.1875,
      "reward_std": 0.3335031494498253,
      "rewards/format_reward": 0.0,
      "rewards/score_reward": 0.1875,
      "step": 228
    },
    {
      "clip_ratio": 0.0,
      "completion_length": 121.375,
      "epoch": 0.916,
      "grad_norm": 8.078886032104492,
      "kl": 0.184326171875,
      "learning_rate": 9.084e-07,
      "loss": 0.0002,
      "reward": 0.53125,
      "reward_std": 0.3471629247069359,
      "rewards/format_reward": 0.0,
      "rewards/score_reward": 0.53125,
      "step": 229
    },
    {
      "clip_ratio": 0.0,
      "completion_length": 112.1875,
      "epoch": 0.92,
      "grad_norm": 17.53875732421875,
      "kl": 0.181640625,
      "learning_rate": 9.08e-07,
      "loss": 0.0002,
      "reward": 0.5,
      "reward_std": 0.2925042062997818,
      "rewards/format_reward": 0.0,
      "rewards/score_reward": 0.5,
      "step": 230
    },
    {
      "clip_ratio": 0.0,
      "completion_length": 145.3125,
      "epoch": 0.924,
      "grad_norm": 6.732425212860107,
      "kl": 0.180419921875,
      "learning_rate": 9.075999999999999e-07,
      "loss": 0.0002,
      "reward": 0.21875,
      "reward_std": 0.3377464786171913,
      "rewards/format_reward": 0.0,
      "rewards/score_reward": 0.21875,
      "step": 231
    },
    {
      "clip_ratio": 0.0,
      "completion_length": 131.15625,
      "epoch": 0.928,
      "grad_norm": 5.378574371337891,
      "kl": 0.183349609375,
      "learning_rate": 9.072e-07,
      "loss": 0.0002,
      "reward": 0.40625,
      "reward_std": 0.22201896458864212,
      "rewards/format_reward": 0.0,
      "rewards/score_reward": 0.40625,
      "step": 232
    },
    {
      "clip_ratio": 0.0,
      "completion_length": 126.34375,
      "epoch": 0.932,
      "grad_norm": 8.546733856201172,
      "kl": 0.246337890625,
      "learning_rate": 9.068e-07,
      "loss": 0.0002,
      "reward": 0.40625,
      "reward_std": 0.5217924863100052,
      "rewards/format_reward": 0.0,
      "rewards/score_reward": 0.40625,
      "step": 233
    },
    {
      "clip_ratio": 0.0,
      "completion_length": 119.28125,
      "epoch": 0.936,
      "grad_norm": 4.824804782867432,
      "kl": 0.21923828125,
      "learning_rate": 9.063999999999999e-07,
      "loss": 0.0002,
      "reward": 0.375,
      "reward_std": 0.2177756354212761,
      "rewards/format_reward": 0.0,
      "rewards/score_reward": 0.375,
      "step": 234
    },
    {
      "clip_ratio": 0.0,
      "completion_length": 129.71875,
      "epoch": 0.94,
      "grad_norm": 4.122939109802246,
      "kl": 0.18359375,
      "learning_rate": 9.06e-07,
      "loss": 0.0002,
      "reward": 0.09375,
      "reward_std": 0.2041158601641655,
      "rewards/format_reward": 0.0,
      "rewards/score_reward": 0.09375,
      "step": 235
    },
    {
      "clip_ratio": 0.0,
      "completion_length": 135.875,
      "epoch": 0.944,
      "grad_norm": 2.8131566047668457,
      "kl": 0.26416015625,
      "learning_rate": 9.056e-07,
      "loss": 0.0003,
      "reward": 0.03125,
      "reward_std": 0.0883883461356163,
      "rewards/format_reward": 0.0,
      "rewards/score_reward": 0.03125,
      "step": 236
    },
    {
      "clip_ratio": 0.0,
      "completion_length": 139.0,
      "epoch": 0.948,
      "grad_norm": 2.190013885498047,
      "kl": 0.18359375,
      "learning_rate": 9.051999999999999e-07,
      "loss": 0.0002,
      "reward": 0.46875,
      "reward_std": 0.0883883461356163,
      "rewards/format_reward": 0.0,
      "rewards/score_reward": 0.46875,
      "step": 237
    },
    {
      "clip_ratio": 0.0,
      "completion_length": 157.4375,
      "epoch": 0.952,
      "grad_norm": 3.7834203243255615,
      "kl": 0.1572265625,
      "learning_rate": 9.048e-07,
      "loss": 0.0002,
      "reward": 0.0625,
      "reward_std": 0.1157275140285492,
      "rewards/format_reward": 0.0,
      "rewards/score_reward": 0.0625,
      "step": 238
    },
    {
      "clip_ratio": 0.0,
      "completion_length": 133.78125,
      "epoch": 0.956,
      "grad_norm": 32.57776641845703,
      "kl": 0.179443359375,
      "learning_rate": 9.044e-07,
      "loss": 0.0002,
      "reward": 0.40625,
      "reward_std": 0.5123760402202606,
      "rewards/format_reward": 0.0,
      "rewards/score_reward": 0.40625,
      "step": 239
    },
    {
      "clip_ratio": 0.0,
      "completion_length": 119.53125,
      "epoch": 0.96,
      "grad_norm": 3.308706045150757,
      "kl": 0.210693359375,
      "learning_rate": 9.039999999999999e-07,
      "loss": 0.0002,
      "reward": 0.09375,
      "reward_std": 0.1293872892856598,
      "rewards/format_reward": 0.0,
      "rewards/score_reward": 0.09375,
      "step": 240
    },
    {
      "clip_ratio": 0.0,
      "completion_length": 120.59375,
      "epoch": 0.964,
      "grad_norm": 6.456974506378174,
      "kl": 0.187255859375,
      "learning_rate": 9.035999999999999e-07,
      "loss": 0.0002,
      "reward": 0.40625,
      "reward_std": 0.3377464786171913,
      "rewards/format_reward": 0.0,
      "rewards/score_reward": 0.40625,
      "step": 241
    },
    {
      "clip_ratio": 0.0,
      "completion_length": 140.21875,
      "epoch": 0.968,
      "grad_norm": 13.71239185333252,
      "kl": 0.162353515625,
      "learning_rate": 9.032e-07,
      "loss": 0.0002,
      "reward": 0.1875,
      "reward_std": 0.3104073107242584,
      "rewards/format_reward": 0.0,
      "rewards/score_reward": 0.1875,
      "step": 242
    },
    {
      "clip_ratio": 0.0,
      "completion_length": 154.0625,
      "epoch": 0.972,
      "grad_norm": 10.391451835632324,
      "kl": 0.160888671875,
      "learning_rate": 9.028e-07,
      "loss": 0.0002,
      "reward": 0.0625,
      "reward_std": 0.1767766922712326,
      "rewards/format_reward": 0.0,
      "rewards/score_reward": 0.0625,
      "step": 243
    },
    {
      "clip_ratio": 0.0,
      "completion_length": 133.5,
      "epoch": 0.976,
      "grad_norm": 5.7491044998168945,
      "kl": 0.192138671875,
      "learning_rate": 9.023999999999999e-07,
      "loss": 0.0002,
      "reward": 0.28125,
      "reward_std": 0.2651650384068489,
      "rewards/format_reward": 0.0,
      "rewards/score_reward": 0.28125,
      "step": 244
    },
    {
      "clip_ratio": 0.0,
      "completion_length": 144.59375,
      "epoch": 0.98,
      "grad_norm": 6.993992328643799,
      "kl": 0.16796875,
      "learning_rate": 9.02e-07,
      "loss": 0.0002,
      "reward": 0.03125,
      "reward_std": 0.0883883461356163,
      "rewards/format_reward": 0.0,
      "rewards/score_reward": 0.03125,
      "step": 245
    },
    {
      "clip_ratio": 0.0,
      "completion_length": 140.78125,
      "epoch": 0.984,
      "grad_norm": 11.08362102508545,
      "kl": 0.192626953125,
      "learning_rate": 9.015999999999999e-07,
      "loss": 0.0002,
      "reward": 0.40625,
      "reward_std": 0.22201896458864212,
      "rewards/format_reward": 0.0,
      "rewards/score_reward": 0.40625,
      "step": 246
    },
    {
      "clip_ratio": 0.0,
      "completion_length": 149.75,
      "epoch": 0.988,
      "grad_norm": 35.28593826293945,
      "kl": 0.166015625,
      "learning_rate": 9.011999999999999e-07,
      "loss": 0.0002,
      "reward": 0.375,
      "reward_std": 0.4492306634783745,
      "rewards/format_reward": 0.0,
      "rewards/score_reward": 0.375,
      "step": 247
    },
    {
      "clip_ratio": 0.0,
      "completion_length": 142.125,
      "epoch": 0.992,
      "grad_norm": 8.120216369628906,
      "kl": 0.1826171875,
      "learning_rate": 9.008e-07,
      "loss": 0.0002,
      "reward": 0.21875,
      "reward_std": 0.24511480331420898,
      "rewards/format_reward": 0.0,
      "rewards/score_reward": 0.21875,
      "step": 248
    },
    {
      "clip_ratio": 0.0,
      "completion_length": 129.09375,
      "epoch": 0.996,
      "grad_norm": 7.45528507232666,
      "kl": 0.2109375,
      "learning_rate": 9.004e-07,
      "loss": 0.0002,
      "reward": 0.03125,
      "reward_std": 0.0883883461356163,
      "rewards/format_reward": 0.0,
      "rewards/score_reward": 0.03125,
      "step": 249
    },
    {
      "clip_ratio": 0.0,
      "completion_length": 150.21875,
      "epoch": 1.0,
      "grad_norm": 12.991154670715332,
      "kl": 0.177978515625,
      "learning_rate": 9e-07,
      "loss": 0.0002,
      "reward": 0.125,
      "reward_std": 0.2925042062997818,
      "rewards/format_reward": 0.0,
      "rewards/score_reward": 0.125,
      "step": 250
    },
    {
      "clip_ratio": 0.0,
      "completion_length": 135.71875,
      "epoch": 1.004,
      "grad_norm": 10.966651916503906,
      "kl": 0.2197265625,
      "learning_rate": 8.995999999999999e-07,
      "loss": 0.0002,
      "reward": 0.125,
      "reward_std": 0.2925042062997818,
      "rewards/format_reward": 0.0,
      "rewards/score_reward": 0.125,
      "step": 251
    },
    {
      "clip_ratio": 0.0,
      "completion_length": 141.90625,
      "epoch": 1.008,
      "grad_norm": 6.208240509033203,
      "kl": 0.205078125,
      "learning_rate": 8.992e-07,
      "loss": 0.0002,
      "reward": 0.3125,
      "reward_std": 0.3514062538743019,
      "rewards/format_reward": 0.0,
      "rewards/score_reward": 0.3125,
      "step": 252
    },
    {
      "clip_ratio": 0.0,
      "completion_length": 151.46875,
      "epoch": 1.012,
      "grad_norm": 6.70610237121582,
      "kl": 1.283935546875,
      "learning_rate": 8.988e-07,
      "loss": 0.0013,
      "reward": 0.40625,
      "reward_std": 0.3608423173427582,
      "rewards/format_reward": 0.0,
      "rewards/score_reward": 0.40625,
      "step": 253
    },
    {
      "clip_ratio": 0.0,
      "completion_length": 130.21875,
      "epoch": 1.016,
      "grad_norm": 3.005783796310425,
      "kl": 0.173095703125,
      "learning_rate": 8.983999999999999e-07,
      "loss": 0.0002,
      "reward": 0.53125,
      "reward_std": 0.0883883461356163,
      "rewards/format_reward": 0.0,
      "rewards/score_reward": 0.53125,
      "step": 254
    },
    {
      "clip_ratio": 0.0,
      "completion_length": 146.21875,
      "epoch": 1.02,
      "grad_norm": 5.299511432647705,
      "kl": 0.185302734375,
      "learning_rate": 8.98e-07,
      "loss": 0.0002,
      "reward": 0.34375,
      "reward_std": 0.3061639815568924,
      "rewards/format_reward": 0.0,
      "rewards/score_reward": 0.34375,
      "step": 255
    },
    {
      "clip_ratio": 0.0,
      "completion_length": 145.0625,
      "epoch": 1.024,
      "grad_norm": 7.629411220550537,
      "kl": 0.26318359375,
      "learning_rate": 8.975999999999999e-07,
      "loss": 0.0003,
      "reward": 0.46875,
      "reward_std": 0.3471629247069359,
      "rewards/format_reward": 0.0,
      "rewards/score_reward": 0.46875,
      "step": 256
    },
    {
      "clip_ratio": 0.0,
      "completion_length": 135.5625,
      "epoch": 1.028,
      "grad_norm": 15.968307495117188,
      "kl": 0.17822265625,
      "learning_rate": 8.972e-07,
      "loss": 0.0002,
      "reward": 0.5625,
      "reward_std": 0.2587745785713196,
      "rewards/format_reward": 0.0,
      "rewards/score_reward": 0.5625,
      "step": 257
    },
    {
      "clip_ratio": 0.0,
      "completion_length": 140.8125,
      "epoch": 1.032,
      "grad_norm": 9.633905410766602,
      "kl": 0.265380859375,
      "learning_rate": 8.968e-07,
      "loss": 0.0003,
      "reward": 0.3125,
      "reward_std": 0.3514062538743019,
      "rewards/format_reward": 0.0,
      "rewards/score_reward": 0.3125,
      "step": 258
    },
    {
      "clip_ratio": 0.0,
      "completion_length": 167.53125,
      "epoch": 1.036,
      "grad_norm": 5.413832187652588,
      "kl": 0.187255859375,
      "learning_rate": 8.963999999999999e-07,
      "loss": 0.0002,
      "reward": 0.15625,
      "reward_std": 0.24511480331420898,
      "rewards/format_reward": 0.0,
      "rewards/score_reward": 0.15625,
      "step": 259
    },
    {
      "clip_ratio": 0.0,
      "completion_length": 145.28125,
      "epoch": 1.04,
      "grad_norm": 42.84470748901367,
      "kl": 0.178466796875,
      "learning_rate": 8.96e-07,
      "loss": 0.0002,
      "reward": 0.40625,
      "reward_std": 0.4218914955854416,
      "rewards/format_reward": 0.0,
      "rewards/score_reward": 0.40625,
      "step": 260
    },
    {
      "clip_ratio": 0.0,
      "completion_length": 139.1875,
      "epoch": 1.044,
      "grad_norm": 5.803390979766846,
      "kl": 0.201904296875,
      "learning_rate": 8.955999999999999e-07,
      "loss": 0.0002,
      "reward": 0.34375,
      "reward_std": 0.4807935431599617,
      "rewards/format_reward": 0.0,
      "rewards/score_reward": 0.34375,
      "step": 261
    },
    {
      "clip_ratio": 0.0,
      "completion_length": 157.59375,
      "epoch": 1.048,
      "grad_norm": 9.147906303405762,
      "kl": 0.20263671875,
      "learning_rate": 8.951999999999999e-07,
      "loss": 0.0002,
      "reward": 0.21875,
      "reward_std": 0.3987956568598747,
      "rewards/format_reward": 0.0,
      "rewards/score_reward": 0.21875,
      "step": 262
    },
    {
      "clip_ratio": 0.0,
      "completion_length": 153.8125,
      "epoch": 1.052,
      "grad_norm": 3.2289392948150635,
      "kl": 0.22314453125,
      "learning_rate": 8.948e-07,
      "loss": 0.0002,
      "reward": 0.625,
      "reward_std": 0.2314550280570984,
      "rewards/format_reward": 0.0,
      "rewards/score_reward": 0.625,
      "step": 263
    },
    {
      "clip_ratio": 0.0,
      "completion_length": 145.0,
      "epoch": 1.056,
      "grad_norm": 16.819181442260742,
      "kl": 0.2177734375,
      "learning_rate": 8.944e-07,
      "loss": 0.0002,
      "reward": 0.21875,
      "reward_std": 0.3061639815568924,
      "rewards/format_reward": 0.0,
      "rewards/score_reward": 0.21875,
      "step": 264
    },
    {
      "clip_ratio": 0.0,
      "completion_length": 149.71875,
      "epoch": 1.06,
      "grad_norm": 14.53752326965332,
      "kl": 0.1953125,
      "learning_rate": 8.939999999999999e-07,
      "loss": 0.0002,
      "reward": 0.5,
      "reward_std": 0.2587745785713196,
      "rewards/format_reward": 0.0,
      "rewards/score_reward": 0.5,
      "step": 265
    },
    {
      "clip_ratio": 0.0,
      "completion_length": 142.96875,
      "epoch": 1.064,
      "grad_norm": 3.053736925125122,
      "kl": 0.21142578125,
      "learning_rate": 8.935999999999999e-07,
      "loss": 0.0002,
      "reward": 0.34375,
      "reward_std": 0.1293872892856598,
      "rewards/format_reward": 0.0,
      "rewards/score_reward": 0.34375,
      "step": 266
    },
    {
      "clip_ratio": 0.0,
      "completion_length": 158.25,
      "epoch": 1.068,
      "grad_norm": 4.489502906799316,
      "kl": 0.180908203125,
      "learning_rate": 8.932e-07,
      "loss": 0.0002,
      "reward": 0.5,
      "reward_std": 0.2925042062997818,
      "rewards/format_reward": 0.0,
      "rewards/score_reward": 0.5,
      "step": 267
    },
    {
      "clip_ratio": 0.0,
      "completion_length": 140.0625,
      "epoch": 1.072,
      "grad_norm": 7.516378402709961,
      "kl": 0.201416015625,
      "learning_rate": 8.928e-07,
      "loss": 0.0002,
      "reward": 0.28125,
      "reward_std": 0.0883883461356163,
      "rewards/format_reward": 0.0,
      "rewards/score_reward": 0.28125,
      "step": 268
    },
    {
      "clip_ratio": 0.0,
      "completion_length": 143.28125,
      "epoch": 1.076,
      "grad_norm": 7.0981645584106445,
      "kl": 0.21875,
      "learning_rate": 8.923999999999999e-07,
      "loss": 0.0002,
      "reward": 0.1875,
      "reward_std": 0.3335031494498253,
      "rewards/format_reward": 0.0,
      "rewards/score_reward": 0.1875,
      "step": 269
    },
    {
      "clip_ratio": 0.0,
      "completion_length": 133.59375,
      "epoch": 1.08,
      "grad_norm": 5.433140754699707,
      "kl": 0.222900390625,
      "learning_rate": 8.92e-07,
      "loss": 0.0002,
      "reward": 0.3125,
      "reward_std": 0.1767766922712326,
      "rewards/format_reward": 0.0,
      "rewards/score_reward": 0.3125,
      "step": 270
    },
    {
      "clip_ratio": 0.0,
      "completion_length": 141.125,
      "epoch": 1.084,
      "grad_norm": 11.345158576965332,
      "kl": 0.216552734375,
      "learning_rate": 8.915999999999999e-07,
      "loss": 0.0002,
      "reward": 0.4375,
      "reward_std": 0.4492306634783745,
      "rewards/format_reward": 0.0,
      "rewards/score_reward": 0.4375,
      "step": 271
    },
    {
      "clip_ratio": 0.0,
      "completion_length": 146.71875,
      "epoch": 1.088,
      "grad_norm": 7.191331386566162,
      "kl": 0.253173828125,
      "learning_rate": 8.911999999999999e-07,
      "loss": 0.0003,
      "reward": 0.53125,
      "reward_std": 0.3787454217672348,
      "rewards/format_reward": 0.0,
      "rewards/score_reward": 0.53125,
      "step": 272
    },
    {
      "clip_ratio": 0.0,
      "completion_length": 122.96875,
      "epoch": 1.092,
      "grad_norm": 5.7541985511779785,
      "kl": 0.203125,
      "learning_rate": 8.908e-07,
      "loss": 0.0002,
      "reward": 0.34375,
      "reward_std": 0.2041158601641655,
      "rewards/format_reward": 0.0,
      "rewards/score_reward": 0.34375,
      "step": 273
    },
    {
      "clip_ratio": 0.0,
      "completion_length": 144.6875,
      "epoch": 1.096,
      "grad_norm": 6.448830604553223,
      "kl": 0.213623046875,
      "learning_rate": 8.904e-07,
      "loss": 0.0002,
      "reward": 0.34375,
      "reward_std": 0.3808925524353981,
      "rewards/format_reward": 0.0,
      "rewards/score_reward": 0.34375,
      "step": 274
    },
    {
      "clip_ratio": 0.0,
      "completion_length": 142.125,
      "epoch": 1.1,
      "grad_norm": 3.787655830383301,
      "kl": 0.217529296875,
      "learning_rate": 8.9e-07,
      "loss": 0.0002,
      "reward": 0.1875,
      "reward_std": 0.2177756354212761,
      "rewards/format_reward": 0.0,
      "rewards/score_reward": 0.1875,
      "step": 275
    },
    {
      "clip_ratio": 0.0,
      "completion_length": 145.21875,
      "epoch": 1.104,
      "grad_norm": 3.446657180786133,
      "kl": 0.217529296875,
      "learning_rate": 8.895999999999999e-07,
      "loss": 0.0002,
      "reward": 0.6875,
      "reward_std": 0.249358132481575,
      "rewards/format_reward": 0.0,
      "rewards/score_reward": 0.6875,
      "step": 276
    },
    {
      "clip_ratio": 0.0,
      "completion_length": 129.0625,
      "epoch": 1.108,
      "grad_norm": 54.69266128540039,
      "kl": 0.211669921875,
      "learning_rate": 8.892e-07,
      "loss": 0.0002,
      "reward": 0.34375,
      "reward_std": 0.3377464786171913,
      "rewards/format_reward": 0.0,
      "rewards/score_reward": 0.34375,
      "step": 277
    },
    {
      "clip_ratio": 0.0,
      "completion_length": 126.71875,
      "epoch": 1.112,
      "grad_norm": 32.58818817138672,
      "kl": 0.248779296875,
      "learning_rate": 8.888e-07,
      "loss": 0.0002,
      "reward": 0.28125,
      "reward_std": 0.2630179077386856,
      "rewards/format_reward": 0.0,
      "rewards/score_reward": 0.28125,
      "step": 278
    },
    {
      "clip_ratio": 0.0,
      "completion_length": 127.875,
      "epoch": 1.116,
      "grad_norm": 0.0929594337940216,
      "kl": 0.3173828125,
      "learning_rate": 8.883999999999999e-07,
      "loss": 0.0003,
      "reward": 0.75,
      "reward_std": 0.0,
      "rewards/format_reward": 0.0,
      "rewards/score_reward": 0.75,
      "step": 279
    },
    {
      "clip_ratio": 0.0,
      "completion_length": 121.375,
      "epoch": 1.12,
      "grad_norm": 3.5213842391967773,
      "kl": 0.2275390625,
      "learning_rate": 8.88e-07,
      "loss": 0.0002,
      "reward": 0.3125,
      "reward_std": 0.1157275140285492,
      "rewards/format_reward": 0.0,
      "rewards/score_reward": 0.3125,
      "step": 280
    },
    {
      "clip_ratio": 0.0,
      "completion_length": 132.9375,
      "epoch": 1.124,
      "grad_norm": 5.264272212982178,
      "kl": 0.28369140625,
      "learning_rate": 8.875999999999999e-07,
      "loss": 0.0003,
      "reward": 0.375,
      "reward_std": 0.3104073107242584,
      "rewards/format_reward": 0.0,
      "rewards/score_reward": 0.375,
      "step": 281
    },
    {
      "clip_ratio": 0.0,
      "completion_length": 116.53125,
      "epoch": 1.1280000000000001,
      "grad_norm": 4.806576728820801,
      "kl": 0.26025390625,
      "learning_rate": 8.872e-07,
      "loss": 0.0003,
      "reward": 0.34375,
      "reward_std": 0.22201896458864212,
      "rewards/format_reward": 0.0,
      "rewards/score_reward": 0.34375,
      "step": 282
    },
    {
      "clip_ratio": 0.0,
      "completion_length": 144.34375,
      "epoch": 1.1320000000000001,
      "grad_norm": 16.849353790283203,
      "kl": 0.2763671875,
      "learning_rate": 8.868e-07,
      "loss": 0.0003,
      "reward": 0.5625,
      "reward_std": 0.1157275140285492,
      "rewards/format_reward": 0.0,
      "rewards/score_reward": 0.5625,
      "step": 283
    },
    {
      "clip_ratio": 0.0,
      "completion_length": 119.5,
      "epoch": 1.1360000000000001,
      "grad_norm": 0.024166446179151535,
      "kl": 0.277587890625,
      "learning_rate": 8.863999999999999e-07,
      "loss": 0.0003,
      "reward": 0.25,
      "reward_std": 0.0,
      "rewards/format_reward": 0.0,
      "rewards/score_reward": 0.25,
      "step": 284
    },
    {
      "clip_ratio": 0.0,
      "completion_length": 125.375,
      "epoch": 1.1400000000000001,
      "grad_norm": 3.680453300476074,
      "kl": 0.27392578125,
      "learning_rate": 8.86e-07,
      "loss": 0.0003,
      "reward": 0.53125,
      "reward_std": 0.2041158601641655,
      "rewards/format_reward": 0.0,
      "rewards/score_reward": 0.53125,
      "step": 285
    },
    {
      "clip_ratio": 0.0,
      "completion_length": 115.375,
      "epoch": 1.144,
      "grad_norm": 3.488722562789917,
      "kl": 0.292724609375,
      "learning_rate": 8.856e-07,
      "loss": 0.0003,
      "reward": 0.3125,
      "reward_std": 0.1157275140285492,
      "rewards/format_reward": 0.0,
      "rewards/score_reward": 0.3125,
      "step": 286
    },
    {
      "clip_ratio": 0.0,
      "completion_length": 125.96875,
      "epoch": 1.148,
      "grad_norm": 4.979753494262695,
      "kl": 0.269287109375,
      "learning_rate": 8.851999999999999e-07,
      "loss": 0.0003,
      "reward": 0.4375,
      "reward_std": 0.3514062538743019,
      "rewards/format_reward": 0.0,
      "rewards/score_reward": 0.4375,
      "step": 287
    },
    {
      "clip_ratio": 0.0,
      "completion_length": 138.21875,
      "epoch": 1.152,
      "grad_norm": 6.298620223999023,
      "kl": 0.27734375,
      "learning_rate": 8.848e-07,
      "loss": 0.0003,
      "reward": 0.1875,
      "reward_std": 0.2587745785713196,
      "rewards/format_reward": 0.0,
      "rewards/score_reward": 0.1875,
      "step": 288
    },
    {
      "clip_ratio": 0.0,
      "completion_length": 127.78125,
      "epoch": 1.156,
      "grad_norm": 5.3922882080078125,
      "kl": 0.296875,
      "learning_rate": 8.844e-07,
      "loss": 0.0003,
      "reward": 0.1875,
      "reward_std": 0.249358132481575,
      "rewards/format_reward": 0.0,
      "rewards/score_reward": 0.1875,
      "step": 289
    },
    {
      "clip_ratio": 0.0,
      "completion_length": 136.90625,
      "epoch": 1.16,
      "grad_norm": 5.702232360839844,
      "kl": 0.27685546875,
      "learning_rate": 8.839999999999999e-07,
      "loss": 0.0003,
      "reward": 0.4375,
      "reward_std": 0.2177756354212761,
      "rewards/format_reward": 0.0,
      "rewards/score_reward": 0.4375,
      "step": 290
    },
    {
      "clip_ratio": 0.0,
      "completion_length": 131.28125,
      "epoch": 1.164,
      "grad_norm": 0.024661913514137268,
      "kl": 0.2802734375,
      "learning_rate": 8.836e-07,
      "loss": 0.0003,
      "reward": 0.25,
      "reward_std": 0.0,
      "rewards/format_reward": 0.0,
      "rewards/score_reward": 0.25,
      "step": 291
    },
    {
      "clip_ratio": 0.0,
      "completion_length": 137.59375,
      "epoch": 1.168,
      "grad_norm": 32.11168670654297,
      "kl": 0.240966796875,
      "learning_rate": 8.832e-07,
      "loss": 0.0002,
      "reward": 0.46875,
      "reward_std": 0.24511480331420898,
      "rewards/format_reward": 0.0,
      "rewards/score_reward": 0.46875,
      "step": 292
    },
    {
      "clip_ratio": 0.0,
      "completion_length": 149.03125,
      "epoch": 1.172,
      "grad_norm": 36.96295166015625,
      "kl": 0.34814453125,
      "learning_rate": 8.827999999999999e-07,
      "loss": 0.0003,
      "reward": 0.09375,
      "reward_std": 0.2041158601641655,
      "rewards/format_reward": 0.0,
      "rewards/score_reward": 0.09375,
      "step": 293
    },
    {
      "clip_ratio": 0.0,
      "completion_length": 122.3125,
      "epoch": 1.176,
      "grad_norm": 3.696056604385376,
      "kl": 0.2783203125,
      "learning_rate": 8.823999999999999e-07,
      "loss": 0.0003,
      "reward": 0.28125,
      "reward_std": 0.0883883461356163,
      "rewards/format_reward": 0.0,
      "rewards/score_reward": 0.28125,
      "step": 294
    },
    {
      "clip_ratio": 0.0,
      "completion_length": 138.875,
      "epoch": 1.18,
      "grad_norm": 2.5873639583587646,
      "kl": 0.35009765625,
      "learning_rate": 8.82e-07,
      "loss": 0.0003,
      "reward": 0.71875,
      "reward_std": 0.0883883461356163,
      "rewards/format_reward": 0.0,
      "rewards/score_reward": 0.71875,
      "step": 295
    },
    {
      "clip_ratio": 0.0,
      "completion_length": 133.125,
      "epoch": 1.184,
      "grad_norm": 5.720484733581543,
      "kl": 0.4599609375,
      "learning_rate": 8.816000000000001e-07,
      "loss": 0.0005,
      "reward": 0.375,
      "reward_std": 0.3650856465101242,
      "rewards/format_reward": 0.0,
      "rewards/score_reward": 0.375,
      "step": 296
    },
    {
      "clip_ratio": 0.0,
      "completion_length": 133.3125,
      "epoch": 1.188,
      "grad_norm": 10.18944263458252,
      "kl": 0.31298828125,
      "learning_rate": 8.811999999999999e-07,
      "loss": 0.0003,
      "reward": 0.46875,
      "reward_std": 0.4765698313713074,
      "rewards/format_reward": 0.0,
      "rewards/score_reward": 0.46875,
      "step": 297
    },
    {
      "clip_ratio": 0.0,
      "completion_length": 152.625,
      "epoch": 1.192,
      "grad_norm": 5.152041435241699,
      "kl": 0.27001953125,
      "learning_rate": 8.808e-07,
      "loss": 0.0003,
      "reward": 0.03125,
      "reward_std": 0.0883883461356163,
      "rewards/format_reward": 0.0,
      "rewards/score_reward": 0.03125,
      "step": 298
    },
    {
      "clip_ratio": 0.0,
      "completion_length": 151.46875,
      "epoch": 1.196,
      "grad_norm": 4.417140007019043,
      "kl": 0.5234375,
      "learning_rate": 8.804e-07,
      "loss": 0.0005,
      "reward": 0.125,
      "reward_std": 0.2925042062997818,
      "rewards/format_reward": 0.0,
      "rewards/score_reward": 0.125,
      "step": 299
    },
    {
      "clip_ratio": 0.0,
      "completion_length": 146.8125,
      "epoch": 1.2,
      "grad_norm": 6.4717230796813965,
      "kl": 0.294677734375,
      "learning_rate": 8.799999999999999e-07,
      "loss": 0.0003,
      "reward": 0.375,
      "reward_std": 0.3945523276925087,
      "rewards/format_reward": 0.0,
      "rewards/score_reward": 0.375,
      "step": 300
    },
    {
      "clip_ratio": 0.0,
      "completion_length": 142.75,
      "epoch": 1.204,
      "grad_norm": 5.155836582183838,
      "kl": 0.26806640625,
      "learning_rate": 8.796e-07,
      "loss": 0.0003,
      "reward": 0.6875,
      "reward_std": 0.3335031494498253,
      "rewards/format_reward": 0.0,
      "rewards/score_reward": 0.6875,
      "step": 301
    },
    {
      "clip_ratio": 0.0,
      "completion_length": 130.65625,
      "epoch": 1.208,
      "grad_norm": 3.839174270629883,
      "kl": 0.27783203125,
      "learning_rate": 8.792e-07,
      "loss": 0.0003,
      "reward": 0.53125,
      "reward_std": 0.2651650384068489,
      "rewards/format_reward": 0.0,
      "rewards/score_reward": 0.53125,
      "step": 302
    },
    {
      "clip_ratio": 0.0,
      "completion_length": 141.34375,
      "epoch": 1.212,
      "grad_norm": 4.404873371124268,
      "kl": 0.29296875,
      "learning_rate": 8.788e-07,
      "loss": 0.0003,
      "reward": 0.28125,
      "reward_std": 0.2630179077386856,
      "rewards/format_reward": 0.0,
      "rewards/score_reward": 0.28125,
      "step": 303
    },
    {
      "clip_ratio": 0.0,
      "completion_length": 140.65625,
      "epoch": 1.216,
      "grad_norm": 9.610031127929688,
      "kl": 0.310546875,
      "learning_rate": 8.783999999999999e-07,
      "loss": 0.0003,
      "reward": 0.65625,
      "reward_std": 0.2041158601641655,
      "rewards/format_reward": 0.0,
      "rewards/score_reward": 0.65625,
      "step": 304
    },
    {
      "clip_ratio": 0.0,
      "completion_length": 146.75,
      "epoch": 1.22,
      "grad_norm": 5.232041835784912,
      "kl": 0.3271484375,
      "learning_rate": 8.78e-07,
      "loss": 0.0003,
      "reward": 0.65625,
      "reward_std": 0.2041158601641655,
      "rewards/format_reward": 0.0,
      "rewards/score_reward": 0.65625,
      "step": 305
    },
    {
      "clip_ratio": 0.0,
      "completion_length": 155.65625,
      "epoch": 1.224,
      "grad_norm": 5.603926181793213,
      "kl": 0.4677734375,
      "learning_rate": 8.776e-07,
      "loss": 0.0005,
      "reward": 0.59375,
      "reward_std": 0.4218914955854416,
      "rewards/format_reward": 0.0,
      "rewards/score_reward": 0.59375,
      "step": 306
    },
    {
      "clip_ratio": 0.0,
      "completion_length": 145.84375,
      "epoch": 1.228,
      "grad_norm": 6.439726829528809,
      "kl": 0.31396484375,
      "learning_rate": 8.771999999999999e-07,
      "loss": 0.0003,
      "reward": 0.40625,
      "reward_std": 0.3198433741927147,
      "rewards/format_reward": 0.0,
      "rewards/score_reward": 0.40625,
      "step": 307
    },
    {
      "clip_ratio": 0.0,
      "completion_length": 163.09375,
      "epoch": 1.232,
      "grad_norm": 4.445047855377197,
      "kl": 0.32958984375,
      "learning_rate": 8.768e-07,
      "loss": 0.0003,
      "reward": 0.25,
      "reward_std": 0.1767766922712326,
      "rewards/format_reward": 0.0,
      "rewards/score_reward": 0.25,
      "step": 308
    },
    {
      "clip_ratio": 0.0,
      "completion_length": 151.9375,
      "epoch": 1.236,
      "grad_norm": 9.926246643066406,
      "kl": 0.313720703125,
      "learning_rate": 8.763999999999999e-07,
      "loss": 0.0003,
      "reward": 0.4375,
      "reward_std": 0.3945523276925087,
      "rewards/format_reward": 0.0,
      "rewards/score_reward": 0.4375,
      "step": 309
    },
    {
      "clip_ratio": 0.0,
      "completion_length": 160.65625,
      "epoch": 1.24,
      "grad_norm": 4.820209503173828,
      "kl": 0.3916015625,
      "learning_rate": 8.76e-07,
      "loss": 0.0004,
      "reward": 0.3125,
      "reward_std": 0.2177756354212761,
      "rewards/format_reward": 0.0,
      "rewards/score_reward": 0.3125,
      "step": 310
    },
    {
      "clip_ratio": 0.0,
      "completion_length": 160.875,
      "epoch": 1.244,
      "grad_norm": 4.64197301864624,
      "kl": 0.28564453125,
      "learning_rate": 8.756e-07,
      "loss": 0.0003,
      "reward": 0.40625,
      "reward_std": 0.24511480331420898,
      "rewards/format_reward": 0.0,
      "rewards/score_reward": 0.40625,
      "step": 311
    },
    {
      "clip_ratio": 0.0,
      "completion_length": 171.34375,
      "epoch": 1.248,
      "grad_norm": 6.238957405090332,
      "kl": 0.269775390625,
      "learning_rate": 8.751999999999999e-07,
      "loss": 0.0003,
      "reward": 0.46875,
      "reward_std": 0.2041158601641655,
      "rewards/format_reward": 0.0,
      "rewards/score_reward": 0.46875,
      "step": 312
    },
    {
      "clip_ratio": 0.0,
      "completion_length": 163.0625,
      "epoch": 1.252,
      "grad_norm": 16.75998878479004,
      "kl": 0.29443359375,
      "learning_rate": 8.748e-07,
      "loss": 0.0003,
      "reward": 0.21875,
      "reward_std": 0.4355708882212639,
      "rewards/format_reward": 0.0,
      "rewards/score_reward": 0.21875,
      "step": 313
    },
    {
      "clip_ratio": 0.0,
      "completion_length": 180.09375,
      "epoch": 1.256,
      "grad_norm": 1.9939095973968506,
      "kl": 0.248291015625,
      "learning_rate": 8.743999999999999e-07,
      "loss": 0.0002,
      "reward": 0.03125,
      "reward_std": 0.0883883461356163,
      "rewards/format_reward": 0.0,
      "rewards/score_reward": 0.03125,
      "step": 314
    },
    {
      "clip_ratio": 0.0,
      "completion_length": 174.625,
      "epoch": 1.26,
      "grad_norm": 11.04178524017334,
      "kl": 0.2802734375,
      "learning_rate": 8.739999999999999e-07,
      "loss": 0.0003,
      "reward": 0.53125,
      "reward_std": 0.3061639815568924,
      "rewards/format_reward": 0.0,
      "rewards/score_reward": 0.53125,
      "step": 315
    },
    {
      "clip_ratio": 0.0,
      "completion_length": 172.40625,
      "epoch": 1.264,
      "grad_norm": 4.063099384307861,
      "kl": 0.29736328125,
      "learning_rate": 8.736e-07,
      "loss": 0.0003,
      "reward": 0.6875,
      "reward_std": 0.2925042062997818,
      "rewards/format_reward": 0.0,
      "rewards/score_reward": 0.6875,
      "step": 316
    },
    {
      "clip_ratio": 0.0,
      "completion_length": 149.1875,
      "epoch": 1.268,
      "grad_norm": 3.432239055633545,
      "kl": 0.260009765625,
      "learning_rate": 8.732e-07,
      "loss": 0.0003,
      "reward": 0.3125,
      "reward_std": 0.1157275140285492,
      "rewards/format_reward": 0.0,
      "rewards/score_reward": 0.3125,
      "step": 317
    },
    {
      "clip_ratio": 0.0,
      "completion_length": 169.625,
      "epoch": 1.272,
      "grad_norm": 1.9211883544921875,
      "kl": 0.4375,
      "learning_rate": 8.728e-07,
      "loss": 0.0004,
      "reward": 0.21875,
      "reward_std": 0.0883883461356163,
      "rewards/format_reward": 0.0,
      "rewards/score_reward": 0.21875,
      "step": 318
    },
    {
      "clip_ratio": 0.0,
      "completion_length": 160.90625,
      "epoch": 1.276,
      "grad_norm": 2.502659559249878,
      "kl": 0.31591796875,
      "learning_rate": 8.723999999999999e-07,
      "loss": 0.0003,
      "reward": 0.28125,
      "reward_std": 0.0883883461356163,
      "rewards/format_reward": 0.0,
      "rewards/score_reward": 0.28125,
      "step": 319
    },
    {
      "clip_ratio": 0.0,
      "completion_length": 148.875,
      "epoch": 1.28,
      "grad_norm": 3.1834092140197754,
      "kl": 0.2861328125,
      "learning_rate": 8.72e-07,
      "loss": 0.0003,
      "reward": 0.3125,
      "reward_std": 0.1157275140285492,
      "rewards/format_reward": 0.0,
      "rewards/score_reward": 0.3125,
      "step": 320
    },
    {
      "clip_ratio": 0.0,
      "completion_length": 166.03125,
      "epoch": 1.284,
      "grad_norm": 37.28458786010742,
      "kl": 0.27490234375,
      "learning_rate": 8.716e-07,
      "loss": 0.0003,
      "reward": 0.28125,
      "reward_std": 0.0883883461356163,
      "rewards/format_reward": 0.0,
      "rewards/score_reward": 0.28125,
      "step": 321
    },
    {
      "clip_ratio": 0.0,
      "completion_length": 175.5625,
      "epoch": 1.288,
      "grad_norm": 3.5250649452209473,
      "kl": 0.42919921875,
      "learning_rate": 8.711999999999999e-07,
      "loss": 0.0004,
      "reward": 0.28125,
      "reward_std": 0.2041158601641655,
      "rewards/format_reward": 0.0,
      "rewards/score_reward": 0.28125,
      "step": 322
    },
    {
      "clip_ratio": 0.0,
      "completion_length": 168.46875,
      "epoch": 1.292,
      "grad_norm": 6.868240833282471,
      "kl": 0.3134765625,
      "learning_rate": 8.708e-07,
      "loss": 0.0003,
      "reward": 0.15625,
      "reward_std": 0.22201896458864212,
      "rewards/format_reward": 0.0,
      "rewards/score_reward": 0.15625,
      "step": 323
    },
    {
      "clip_ratio": 0.0,
      "completion_length": 159.75,
      "epoch": 1.296,
      "grad_norm": 6.121273040771484,
      "kl": 0.34033203125,
      "learning_rate": 8.704e-07,
      "loss": 0.0003,
      "reward": 0.40625,
      "reward_std": 0.3377464786171913,
      "rewards/format_reward": 0.0,
      "rewards/score_reward": 0.40625,
      "step": 324
    },
    {
      "clip_ratio": 0.0,
      "completion_length": 157.71875,
      "epoch": 1.3,
      "grad_norm": 3.7920565605163574,
      "kl": 0.298828125,
      "learning_rate": 8.699999999999999e-07,
      "loss": 0.0003,
      "reward": 0.46875,
      "reward_std": 0.0883883461356163,
      "rewards/format_reward": 0.0,
      "rewards/score_reward": 0.46875,
      "step": 325
    },
    {
      "clip_ratio": 0.0,
      "completion_length": 159.71875,
      "epoch": 1.304,
      "grad_norm": 3.7230024337768555,
      "kl": 0.3349609375,
      "learning_rate": 8.696e-07,
      "loss": 0.0003,
      "reward": 0.0625,
      "reward_std": 0.1157275140285492,
      "rewards/format_reward": 0.0,
      "rewards/score_reward": 0.0625,
      "step": 326
    },
    {
      "clip_ratio": 0.0,
      "completion_length": 162.6875,
      "epoch": 1.308,
      "grad_norm": 3.6794321537017822,
      "kl": 0.302978515625,
      "learning_rate": 8.692e-07,
      "loss": 0.0003,
      "reward": 0.34375,
      "reward_std": 0.1293872892856598,
      "rewards/format_reward": 0.0,
      "rewards/score_reward": 0.34375,
      "step": 327
    },
    {
      "clip_ratio": 0.0,
      "completion_length": 160.8125,
      "epoch": 1.312,
      "grad_norm": 2.1902525424957275,
      "kl": 0.279052734375,
      "learning_rate": 8.687999999999999e-07,
      "loss": 0.0003,
      "reward": 0.4375,
      "reward_std": 0.1157275140285492,
      "rewards/format_reward": 0.0,
      "rewards/score_reward": 0.4375,
      "step": 328
    },
    {
      "clip_ratio": 0.0,
      "completion_length": 165.96875,
      "epoch": 1.316,
      "grad_norm": 3.8480546474456787,
      "kl": 0.38330078125,
      "learning_rate": 8.683999999999999e-07,
      "loss": 0.0004,
      "reward": 0.71875,
      "reward_std": 0.2630179077386856,
      "rewards/format_reward": 0.0,
      "rewards/score_reward": 0.71875,
      "step": 329
    },
    {
      "clip_ratio": 0.0,
      "completion_length": 170.0625,
      "epoch": 1.32,
      "grad_norm": 3.8732831478118896,
      "kl": 0.333984375,
      "learning_rate": 8.68e-07,
      "loss": 0.0003,
      "reward": 0.28125,
      "reward_std": 0.0883883461356163,
      "rewards/format_reward": 0.0,
      "rewards/score_reward": 0.28125,
      "step": 330
    },
    {
      "clip_ratio": 0.0,
      "completion_length": 168.4375,
      "epoch": 1.324,
      "grad_norm": 6.415884971618652,
      "kl": 0.28662109375,
      "learning_rate": 8.676e-07,
      "loss": 0.0003,
      "reward": 0.1875,
      "reward_std": 0.249358132481575,
      "rewards/format_reward": 0.0,
      "rewards/score_reward": 0.1875,
      "step": 331
    },
    {
      "clip_ratio": 0.0,
      "completion_length": 180.34375,
      "epoch": 1.328,
      "grad_norm": 2.7691843509674072,
      "kl": 0.59912109375,
      "learning_rate": 8.671999999999999e-07,
      "loss": 0.0006,
      "reward": 0.15625,
      "reward_std": 0.1293872892856598,
      "rewards/format_reward": 0.0,
      "rewards/score_reward": 0.15625,
      "step": 332
    },
    {
      "clip_ratio": 0.0,
      "completion_length": 182.03125,
      "epoch": 1.332,
      "grad_norm": 8.122827529907227,
      "kl": 0.31787109375,
      "learning_rate": 8.668e-07,
      "loss": 0.0003,
      "reward": 0.6875,
      "reward_std": 0.1767766922712326,
      "rewards/format_reward": 0.0,
      "rewards/score_reward": 0.6875,
      "step": 333
    },
    {
      "clip_ratio": 0.0,
      "completion_length": 163.28125,
      "epoch": 1.336,
      "grad_norm": 11.689245223999023,
      "kl": 0.43017578125,
      "learning_rate": 8.663999999999999e-07,
      "loss": 0.0004,
      "reward": 0.53125,
      "reward_std": 0.35564958304166794,
      "rewards/format_reward": 0.0,
      "rewards/score_reward": 0.53125,
      "step": 334
    },
    {
      "clip_ratio": 0.0,
      "completion_length": 163.5625,
      "epoch": 1.34,
      "grad_norm": 0.040142327547073364,
      "kl": 0.3466796875,
      "learning_rate": 8.659999999999999e-07,
      "loss": 0.0003,
      "reward": 0.0,
      "reward_std": 0.0,
      "rewards/format_reward": 0.0,
      "rewards/score_reward": 0.0,
      "step": 335
    },
    {
      "clip_ratio": 0.0,
      "completion_length": 168.15625,
      "epoch": 1.3439999999999999,
      "grad_norm": 7.134670257568359,
      "kl": 0.31787109375,
      "learning_rate": 8.656e-07,
      "loss": 0.0003,
      "reward": 0.625,
      "reward_std": 0.2177756354212761,
      "rewards/format_reward": 0.0,
      "rewards/score_reward": 0.625,
      "step": 336
    },
    {
      "clip_ratio": 0.0,
      "completion_length": 160.8125,
      "epoch": 1.3479999999999999,
      "grad_norm": 6.3668599128723145,
      "kl": 0.35205078125,
      "learning_rate": 8.651999999999999e-07,
      "loss": 0.0004,
      "reward": 0.3125,
      "reward_std": 0.1157275140285492,
      "rewards/format_reward": 0.0,
      "rewards/score_reward": 0.3125,
      "step": 337
    },
    {
      "clip_ratio": 0.0,
      "completion_length": 174.4375,
      "epoch": 1.3519999999999999,
      "grad_norm": 3.3299219608306885,
      "kl": 0.37939453125,
      "learning_rate": 8.648e-07,
      "loss": 0.0004,
      "reward": 0.46875,
      "reward_std": 0.0883883461356163,
      "rewards/format_reward": 0.0,
      "rewards/score_reward": 0.46875,
      "step": 338
    },
    {
      "clip_ratio": 0.0,
      "completion_length": 172.84375,
      "epoch": 1.3559999999999999,
      "grad_norm": 3.8048033714294434,
      "kl": 0.35791015625,
      "learning_rate": 8.643999999999999e-07,
      "loss": 0.0004,
      "reward": 0.21875,
      "reward_std": 0.0883883461356163,
      "rewards/format_reward": 0.0,
      "rewards/score_reward": 0.21875,
      "step": 339
    },
    {
      "clip_ratio": 0.0,
      "completion_length": 175.4375,
      "epoch": 1.3599999999999999,
      "grad_norm": 0.019212258979678154,
      "kl": 0.3486328125,
      "learning_rate": 8.639999999999999e-07,
      "loss": 0.0003,
      "reward": 0.25,
      "reward_std": 0.0,
      "rewards/format_reward": 0.0,
      "rewards/score_reward": 0.25,
      "step": 340
    },
    {
      "clip_ratio": 0.0,
      "completion_length": 172.0625,
      "epoch": 1.3639999999999999,
      "grad_norm": 4.146425724029541,
      "kl": 0.365234375,
      "learning_rate": 8.636e-07,
      "loss": 0.0004,
      "reward": 0.1875,
      "reward_std": 0.1157275140285492,
      "rewards/format_reward": 0.0,
      "rewards/score_reward": 0.1875,
      "step": 341
    },
    {
      "clip_ratio": 0.0,
      "completion_length": 163.9375,
      "epoch": 1.3679999999999999,
      "grad_norm": 5.75056266784668,
      "kl": 0.36328125,
      "learning_rate": 8.632e-07,
      "loss": 0.0004,
      "reward": 0.25,
      "reward_std": 0.2925042062997818,
      "rewards/format_reward": 0.0,
      "rewards/score_reward": 0.25,
      "step": 342
    },
    {
      "clip_ratio": 0.0,
      "completion_length": 160.375,
      "epoch": 1.3719999999999999,
      "grad_norm": 5.63866662979126,
      "kl": 0.330078125,
      "learning_rate": 8.628e-07,
      "loss": 0.0003,
      "reward": 0.4375,
      "reward_std": 0.3335031494498253,
      "rewards/format_reward": 0.0,
      "rewards/score_reward": 0.4375,
      "step": 343
    },
    {
      "clip_ratio": 0.0,
      "completion_length": 149.59375,
      "epoch": 1.376,
      "grad_norm": 2.1933727264404297,
      "kl": 0.52587890625,
      "learning_rate": 8.624e-07,
      "loss": 0.0005,
      "reward": 0.5625,
      "reward_std": 0.1157275140285492,
      "rewards/format_reward": 0.0,
      "rewards/score_reward": 0.5625,
      "step": 344
    },
    {
      "clip_ratio": 0.0,
      "completion_length": 148.125,
      "epoch": 1.38,
      "grad_norm": 3.293926954269409,
      "kl": 0.51171875,
      "learning_rate": 8.62e-07,
      "loss": 0.0005,
      "reward": 0.28125,
      "reward_std": 0.0883883461356163,
      "rewards/format_reward": 0.0,
      "rewards/score_reward": 0.28125,
      "step": 345
    },
    {
      "clip_ratio": 0.0,
      "completion_length": 145.4375,
      "epoch": 1.384,
      "grad_norm": 27.214008331298828,
      "kl": 0.3837890625,
      "learning_rate": 8.616e-07,
      "loss": 0.0004,
      "reward": 0.3125,
      "reward_std": 0.1767766922712326,
      "rewards/format_reward": 0.0,
      "rewards/score_reward": 0.3125,
      "step": 346
    },
    {
      "clip_ratio": 0.0,
      "completion_length": 155.65625,
      "epoch": 1.388,
      "grad_norm": 8.472949981689453,
      "kl": 0.4326171875,
      "learning_rate": 8.611999999999999e-07,
      "loss": 0.0004,
      "reward": 0.4375,
      "reward_std": 0.249358132481575,
      "rewards/format_reward": 0.0,
      "rewards/score_reward": 0.4375,
      "step": 347
    },
    {
      "clip_ratio": 0.0,
      "completion_length": 147.125,
      "epoch": 1.392,
      "grad_norm": 2.3920438289642334,
      "kl": 0.369140625,
      "learning_rate": 8.608e-07,
      "loss": 0.0004,
      "reward": 0.09375,
      "reward_std": 0.1293872892856598,
      "rewards/format_reward": 0.0,
      "rewards/score_reward": 0.09375,
      "step": 348
    },
    {
      "clip_ratio": 0.0,
      "completion_length": 140.3125,
      "epoch": 1.396,
      "grad_norm": 4.007767677307129,
      "kl": 0.5234375,
      "learning_rate": 8.604000000000001e-07,
      "loss": 0.0005,
      "reward": 0.46875,
      "reward_std": 0.24511480331420898,
      "rewards/format_reward": 0.0,
      "rewards/score_reward": 0.46875,
      "step": 349
    },
    {
      "clip_ratio": 0.0,
      "completion_length": 153.3125,
      "epoch": 1.4,
      "grad_norm": 4.542917728424072,
      "kl": 0.4287109375,
      "learning_rate": 8.599999999999999e-07,
      "loss": 0.0004,
      "reward": 0.4375,
      "reward_std": 0.3335031494498253,
      "rewards/format_reward": 0.0,
      "rewards/score_reward": 0.4375,
      "step": 350
    },
    {
      "clip_ratio": 0.0,
      "completion_length": 146.375,
      "epoch": 1.404,
      "grad_norm": 5.640623092651367,
      "kl": 0.365234375,
      "learning_rate": 8.596e-07,
      "loss": 0.0004,
      "reward": 0.15625,
      "reward_std": 0.24511480331420898,
      "rewards/format_reward": 0.0,
      "rewards/score_reward": 0.15625,
      "step": 351
    },
    {
      "clip_ratio": 0.0,
      "completion_length": 149.40625,
      "epoch": 1.408,
      "grad_norm": 2.198486328125,
      "kl": 0.419921875,
      "learning_rate": 8.592e-07,
      "loss": 0.0004,
      "reward": 0.03125,
      "reward_std": 0.0883883461356163,
      "rewards/format_reward": 0.0,
      "rewards/score_reward": 0.03125,
      "step": 352
    },
    {
      "clip_ratio": 0.0,
      "completion_length": 152.3125,
      "epoch": 1.412,
      "grad_norm": 5.3141984939575195,
      "kl": 0.44580078125,
      "learning_rate": 8.587999999999999e-07,
      "loss": 0.0004,
      "reward": 0.125,
      "reward_std": 0.2314550280570984,
      "rewards/format_reward": 0.0,
      "rewards/score_reward": 0.125,
      "step": 353
    },
    {
      "clip_ratio": 0.0,
      "completion_length": 144.875,
      "epoch": 1.416,
      "grad_norm": 5.0913777351379395,
      "kl": 0.3828125,
      "learning_rate": 8.584e-07,
      "loss": 0.0004,
      "reward": 0.625,
      "reward_std": 0.2314550280570984,
      "rewards/format_reward": 0.0,
      "rewards/score_reward": 0.625,
      "step": 354
    },
    {
      "clip_ratio": 0.0,
      "completion_length": 145.65625,
      "epoch": 1.42,
      "grad_norm": 6.999328136444092,
      "kl": 0.3427734375,
      "learning_rate": 8.58e-07,
      "loss": 0.0003,
      "reward": 0.65625,
      "reward_std": 0.3377464786171913,
      "rewards/format_reward": 0.0,
      "rewards/score_reward": 0.65625,
      "step": 355
    },
    {
      "clip_ratio": 0.0,
      "completion_length": 158.3125,
      "epoch": 1.424,
      "grad_norm": 4.412006855010986,
      "kl": 0.35302734375,
      "learning_rate": 8.576e-07,
      "loss": 0.0004,
      "reward": 0.15625,
      "reward_std": 0.3061639815568924,
      "rewards/format_reward": 0.0,
      "rewards/score_reward": 0.15625,
      "step": 356
    },
    {
      "clip_ratio": 0.0,
      "completion_length": 156.96875,
      "epoch": 1.428,
      "grad_norm": 6.386446952819824,
      "kl": 0.380859375,
      "learning_rate": 8.571999999999999e-07,
      "loss": 0.0004,
      "reward": 0.28125,
      "reward_std": 0.24511480331420898,
      "rewards/format_reward": 0.0,
      "rewards/score_reward": 0.28125,
      "step": 357
    },
    {
      "clip_ratio": 0.0,
      "completion_length": 155.8125,
      "epoch": 1.432,
      "grad_norm": 0.12800700962543488,
      "kl": 0.380859375,
      "learning_rate": 8.568e-07,
      "loss": 0.0004,
      "reward": 0.0,
      "reward_std": 0.0,
      "rewards/format_reward": 0.0,
      "rewards/score_reward": 0.0,
      "step": 358
    },
    {
      "clip_ratio": 0.0,
      "completion_length": 145.75,
      "epoch": 1.436,
      "grad_norm": 3.816267490386963,
      "kl": 0.63037109375,
      "learning_rate": 8.564e-07,
      "loss": 0.0006,
      "reward": 0.6875,
      "reward_std": 0.1767766922712326,
      "rewards/format_reward": 0.0,
      "rewards/score_reward": 0.6875,
      "step": 359
    },
    {
      "clip_ratio": 0.0,
      "completion_length": 153.46875,
      "epoch": 1.44,
      "grad_norm": 3.641408681869507,
      "kl": 0.49169921875,
      "learning_rate": 8.559999999999999e-07,
      "loss": 0.0005,
      "reward": 0.40625,
      "reward_std": 0.1293872892856598,
      "rewards/format_reward": 0.0,
      "rewards/score_reward": 0.40625,
      "step": 360
    },
    {
      "clip_ratio": 0.0,
      "completion_length": 152.78125,
      "epoch": 1.444,
      "grad_norm": 6.496709823608398,
      "kl": 0.43115234375,
      "learning_rate": 8.556e-07,
      "loss": 0.0004,
      "reward": 0.28125,
      "reward_std": 0.4218914955854416,
      "rewards/format_reward": 0.0,
      "rewards/score_reward": 0.28125,
      "step": 361
    },
    {
      "clip_ratio": 0.0,
      "completion_length": 158.8125,
      "epoch": 1.448,
      "grad_norm": 6.215940952301025,
      "kl": 0.40771484375,
      "learning_rate": 8.551999999999999e-07,
      "loss": 0.0004,
      "reward": 0.375,
      "reward_std": 0.3945523276925087,
      "rewards/format_reward": 0.0,
      "rewards/score_reward": 0.375,
      "step": 362
    },
    {
      "clip_ratio": 0.0,
      "completion_length": 161.875,
      "epoch": 1.452,
      "grad_norm": 3.668593645095825,
      "kl": 0.5849609375,
      "learning_rate": 8.548e-07,
      "loss": 0.0006,
      "reward": 0.46875,
      "reward_std": 0.0883883461356163,
      "rewards/format_reward": 0.0,
      "rewards/score_reward": 0.46875,
      "step": 363
    },
    {
      "clip_ratio": 0.0,
      "completion_length": 150.78125,
      "epoch": 1.456,
      "grad_norm": 4.504969120025635,
      "kl": 0.37060546875,
      "learning_rate": 8.544e-07,
      "loss": 0.0004,
      "reward": 0.65625,
      "reward_std": 0.1293872892856598,
      "rewards/format_reward": 0.0,
      "rewards/score_reward": 0.65625,
      "step": 364
    },
    {
      "clip_ratio": 0.0,
      "completion_length": 162.0,
      "epoch": 1.46,
      "grad_norm": 2.0712342262268066,
      "kl": 0.3798828125,
      "learning_rate": 8.539999999999999e-07,
      "loss": 0.0004,
      "reward": 0.53125,
      "reward_std": 0.0883883461356163,
      "rewards/format_reward": 0.0,
      "rewards/score_reward": 0.53125,
      "step": 365
    },
    {
      "clip_ratio": 0.0,
      "completion_length": 162.0625,
      "epoch": 1.464,
      "grad_norm": 6.902523994445801,
      "kl": 0.7861328125,
      "learning_rate": 8.536e-07,
      "loss": 0.0008,
      "reward": 0.1875,
      "reward_std": 0.3104073107242584,
      "rewards/format_reward": 0.0,
      "rewards/score_reward": 0.1875,
      "step": 366
    },
    {
      "clip_ratio": 0.0,
      "completion_length": 157.09375,
      "epoch": 1.468,
      "grad_norm": 2.4611382484436035,
      "kl": 0.37109375,
      "learning_rate": 8.531999999999999e-07,
      "loss": 0.0004,
      "reward": 0.375,
      "reward_std": 0.13363061845302582,
      "rewards/format_reward": 0.0,
      "rewards/score_reward": 0.375,
      "step": 367
    },
    {
      "clip_ratio": 0.0,
      "completion_length": 149.59375,
      "epoch": 1.472,
      "grad_norm": 3.2094199657440186,
      "kl": 0.40185546875,
      "learning_rate": 8.528e-07,
      "loss": 0.0004,
      "reward": 0.4375,
      "reward_std": 0.1157275140285492,
      "rewards/format_reward": 0.0,
      "rewards/score_reward": 0.4375,
      "step": 368
    },
    {
      "clip_ratio": 0.0,
      "completion_length": 158.90625,
      "epoch": 1.476,
      "grad_norm": 2.43998122215271,
      "kl": 0.380859375,
      "learning_rate": 8.524e-07,
      "loss": 0.0004,
      "reward": 0.0625,
      "reward_std": 0.1157275140285492,
      "rewards/format_reward": 0.0,
      "rewards/score_reward": 0.0625,
      "step": 369
    },
    {
      "clip_ratio": 0.0,
      "completion_length": 166.625,
      "epoch": 1.48,
      "grad_norm": 4.880451202392578,
      "kl": 0.4033203125,
      "learning_rate": 8.52e-07,
      "loss": 0.0004,
      "reward": 0.5625,
      "reward_std": 0.1767766922712326,
      "rewards/format_reward": 0.0,
      "rewards/score_reward": 0.5625,
      "step": 370
    },
    {
      "clip_ratio": 0.0,
      "completion_length": 163.125,
      "epoch": 1.484,
      "grad_norm": 2.5401484966278076,
      "kl": 0.4384765625,
      "learning_rate": 8.516e-07,
      "loss": 0.0004,
      "reward": 0.4375,
      "reward_std": 0.1157275140285492,
      "rewards/format_reward": 0.0,
      "rewards/score_reward": 0.4375,
      "step": 371
    },
    {
      "clip_ratio": 0.0,
      "completion_length": 169.3125,
      "epoch": 1.488,
      "grad_norm": 3.9937148094177246,
      "kl": 0.41357421875,
      "learning_rate": 8.511999999999999e-07,
      "loss": 0.0004,
      "reward": 0.46875,
      "reward_std": 0.2041158601641655,
      "rewards/format_reward": 0.0,
      "rewards/score_reward": 0.46875,
      "step": 372
    },
    {
      "clip_ratio": 0.0,
      "completion_length": 166.71875,
      "epoch": 1.492,
      "grad_norm": 19.11022186279297,
      "kl": 0.39599609375,
      "learning_rate": 8.508e-07,
      "loss": 0.0004,
      "reward": 0.28125,
      "reward_std": 0.0883883461356163,
      "rewards/format_reward": 0.0,
      "rewards/score_reward": 0.28125,
      "step": 373
    },
    {
      "clip_ratio": 0.0,
      "completion_length": 165.375,
      "epoch": 1.496,
      "grad_norm": 6.305721759796143,
      "kl": 0.36376953125,
      "learning_rate": 8.504e-07,
      "loss": 0.0004,
      "reward": 0.34375,
      "reward_std": 0.3377464786171913,
      "rewards/format_reward": 0.0,
      "rewards/score_reward": 0.34375,
      "step": 374
    },
    {
      "clip_ratio": 0.0,
      "completion_length": 159.75,
      "epoch": 1.5,
      "grad_norm": 4.335789203643799,
      "kl": 0.404296875,
      "learning_rate": 8.499999999999999e-07,
      "loss": 0.0004,
      "reward": 0.25,
      "reward_std": 0.1767766922712326,
      "rewards/format_reward": 0.0,
      "rewards/score_reward": 0.25,
      "step": 375
    },
    {
      "clip_ratio": 0.0,
      "completion_length": 163.6875,
      "epoch": 1.504,
      "grad_norm": 0.017256610095500946,
      "kl": 0.39697265625,
      "learning_rate": 8.496e-07,
      "loss": 0.0004,
      "reward": 0.25,
      "reward_std": 0.0,
      "rewards/format_reward": 0.0,
      "rewards/score_reward": 0.25,
      "step": 376
    },
    {
      "clip_ratio": 0.0,
      "completion_length": 161.96875,
      "epoch": 1.508,
      "grad_norm": 5.186189651489258,
      "kl": 0.40478515625,
      "learning_rate": 8.492e-07,
      "loss": 0.0004,
      "reward": 0.125,
      "reward_std": 0.2177756354212761,
      "rewards/format_reward": 0.0,
      "rewards/score_reward": 0.125,
      "step": 377
    },
    {
      "clip_ratio": 0.0,
      "completion_length": 174.40625,
      "epoch": 1.512,
      "grad_norm": 8.06170654296875,
      "kl": 0.39599609375,
      "learning_rate": 8.487999999999999e-07,
      "loss": 0.0004,
      "reward": 0.125,
      "reward_std": 0.2177756354212761,
      "rewards/format_reward": 0.0,
      "rewards/score_reward": 0.125,
      "step": 378
    },
    {
      "clip_ratio": 0.0,
      "completion_length": 173.75,
      "epoch": 1.516,
      "grad_norm": 4.342880725860596,
      "kl": 0.33984375,
      "learning_rate": 8.484e-07,
      "loss": 0.0003,
      "reward": 0.25,
      "reward_std": 0.1767766922712326,
      "rewards/format_reward": 0.0,
      "rewards/score_reward": 0.25,
      "step": 379
    },
    {
      "clip_ratio": 0.0,
      "completion_length": 175.375,
      "epoch": 1.52,
      "grad_norm": 2.14447021484375,
      "kl": 0.37890625,
      "learning_rate": 8.48e-07,
      "loss": 0.0004,
      "reward": 0.34375,
      "reward_std": 0.1293872892856598,
      "rewards/format_reward": 0.0,
      "rewards/score_reward": 0.34375,
      "step": 380
    },
    {
      "clip_ratio": 0.0,
      "completion_length": 166.96875,
      "epoch": 1.524,
      "grad_norm": 3.2591371536254883,
      "kl": 0.44140625,
      "learning_rate": 8.475999999999999e-07,
      "loss": 0.0004,
      "reward": 0.59375,
      "reward_std": 0.24511480331420898,
      "rewards/format_reward": 0.0,
      "rewards/score_reward": 0.59375,
      "step": 381
    },
    {
      "clip_ratio": 0.0,
      "completion_length": 172.21875,
      "epoch": 1.528,
      "grad_norm": 7.309144020080566,
      "kl": 0.32958984375,
      "learning_rate": 8.471999999999999e-07,
      "loss": 0.0003,
      "reward": 0.53125,
      "reward_std": 0.24511480331420898,
      "rewards/format_reward": 0.0,
      "rewards/score_reward": 0.53125,
      "step": 382
    },
    {
      "clip_ratio": 0.0,
      "completion_length": 178.9375,
      "epoch": 1.532,
      "grad_norm": 5.914097309112549,
      "kl": 0.33544921875,
      "learning_rate": 8.468e-07,
      "loss": 0.0003,
      "reward": 0.4375,
      "reward_std": 0.3745020925998688,
      "rewards/format_reward": 0.0,
      "rewards/score_reward": 0.4375,
      "step": 383
    },
    {
      "clip_ratio": 0.0,
      "completion_length": 174.03125,
      "epoch": 1.536,
      "grad_norm": 5.55394172668457,
      "kl": 0.3583984375,
      "learning_rate": 8.464e-07,
      "loss": 0.0004,
      "reward": 0.53125,
      "reward_std": 0.2041158601641655,
      "rewards/format_reward": 0.0,
      "rewards/score_reward": 0.53125,
      "step": 384
    },
    {
      "clip_ratio": 0.0,
      "completion_length": 182.0,
      "epoch": 1.54,
      "grad_norm": 4.632668972015381,
      "kl": 0.35986328125,
      "learning_rate": 8.459999999999999e-07,
      "loss": 0.0004,
      "reward": 0.46875,
      "reward_std": 0.0883883461356163,
      "rewards/format_reward": 0.0,
      "rewards/score_reward": 0.46875,
      "step": 385
    },
    {
      "clip_ratio": 0.0,
      "completion_length": 173.8125,
      "epoch": 1.544,
      "grad_norm": 6.332529067993164,
      "kl": 0.3095703125,
      "learning_rate": 8.456e-07,
      "loss": 0.0003,
      "reward": 0.5625,
      "reward_std": 0.2177756354212761,
      "rewards/format_reward": 0.0,
      "rewards/score_reward": 0.5625,
      "step": 386
    },
    {
      "clip_ratio": 0.0,
      "completion_length": 183.71875,
      "epoch": 1.548,
      "grad_norm": 5.1340012550354,
      "kl": 0.41455078125,
      "learning_rate": 8.451999999999999e-07,
      "loss": 0.0004,
      "reward": 0.3125,
      "reward_std": 0.2587745785713196,
      "rewards/format_reward": 0.0,
      "rewards/score_reward": 0.3125,
      "step": 387
    },
    {
      "clip_ratio": 0.0,
      "completion_length": 181.65625,
      "epoch": 1.552,
      "grad_norm": 1.8199496269226074,
      "kl": 0.4033203125,
      "learning_rate": 8.447999999999999e-07,
      "loss": 0.0004,
      "reward": 0.46875,
      "reward_std": 0.0883883461356163,
      "rewards/format_reward": 0.0,
      "rewards/score_reward": 0.46875,
      "step": 388
    },
    {
      "clip_ratio": 0.0,
      "completion_length": 180.21875,
      "epoch": 1.556,
      "grad_norm": 3.395925760269165,
      "kl": 0.37939453125,
      "learning_rate": 8.444e-07,
      "loss": 0.0004,
      "reward": 0.40625,
      "reward_std": 0.1293872892856598,
      "rewards/format_reward": 0.0,
      "rewards/score_reward": 0.40625,
      "step": 389
    },
    {
      "clip_ratio": 0.0,
      "completion_length": 184.15625,
      "epoch": 1.56,
      "grad_norm": 2.5946571826934814,
      "kl": 0.38134765625,
      "learning_rate": 8.439999999999999e-07,
      "loss": 0.0004,
      "reward": 0.03125,
      "reward_std": 0.0883883461356163,
      "rewards/format_reward": 0.0,
      "rewards/score_reward": 0.03125,
      "step": 390
    },
    {
      "clip_ratio": 0.0,
      "completion_length": 172.375,
      "epoch": 1.564,
      "grad_norm": 3.0371081829071045,
      "kl": 0.40673828125,
      "learning_rate": 8.436e-07,
      "loss": 0.0004,
      "reward": 0.59375,
      "reward_std": 0.1293872892856598,
      "rewards/format_reward": 0.0,
      "rewards/score_reward": 0.59375,
      "step": 391
    },
    {
      "clip_ratio": 0.0,
      "completion_length": 182.78125,
      "epoch": 1.568,
      "grad_norm": 0.05896129459142685,
      "kl": 0.36083984375,
      "learning_rate": 8.431999999999999e-07,
      "loss": 0.0004,
      "reward": 0.25,
      "reward_std": 0.0,
      "rewards/format_reward": 0.0,
      "rewards/score_reward": 0.25,
      "step": 392
    },
    {
      "clip_ratio": 0.0,
      "completion_length": 160.625,
      "epoch": 1.572,
      "grad_norm": 0.7617104649543762,
      "kl": 0.40087890625,
      "learning_rate": 8.428e-07,
      "loss": 0.0004,
      "reward": 0.75,
      "reward_std": 0.0,
      "rewards/format_reward": 0.0,
      "rewards/score_reward": 0.75,
      "step": 393
    },
    {
      "clip_ratio": 0.0,
      "completion_length": 176.0625,
      "epoch": 1.576,
      "grad_norm": 11.398433685302734,
      "kl": 0.34228515625,
      "learning_rate": 8.424e-07,
      "loss": 0.0003,
      "reward": 0.6875,
      "reward_std": 0.1767766922712326,
      "rewards/format_reward": 0.0,
      "rewards/score_reward": 0.6875,
      "step": 394
    },
    {
      "clip_ratio": 0.0,
      "completion_length": 167.125,
      "epoch": 1.58,
      "grad_norm": 0.6610611081123352,
      "kl": 0.62158203125,
      "learning_rate": 8.419999999999999e-07,
      "loss": 0.0006,
      "reward": 0.75,
      "reward_std": 0.0,
      "rewards/format_reward": 0.0,
      "rewards/score_reward": 0.75,
      "step": 395
    },
    {
      "clip_ratio": 0.0,
      "completion_length": 171.0625,
      "epoch": 1.584,
      "grad_norm": 1.8818594217300415,
      "kl": 0.39404296875,
      "learning_rate": 8.416e-07,
      "loss": 0.0004,
      "reward": 0.53125,
      "reward_std": 0.0883883461356163,
      "rewards/format_reward": 0.0,
      "rewards/score_reward": 0.53125,
      "step": 396
    },
    {
      "clip_ratio": 0.0,
      "completion_length": 181.1875,
      "epoch": 1.588,
      "grad_norm": 2.491208791732788,
      "kl": 0.3828125,
      "learning_rate": 8.411999999999999e-07,
      "loss": 0.0004,
      "reward": 0.46875,
      "reward_std": 0.0883883461356163,
      "rewards/format_reward": 0.0,
      "rewards/score_reward": 0.46875,
      "step": 397
    },
    {
      "clip_ratio": 0.0,
      "completion_length": 173.8125,
      "epoch": 1.592,
      "grad_norm": 0.01651681773364544,
      "kl": 0.34423828125,
      "learning_rate": 8.408e-07,
      "loss": 0.0003,
      "reward": 0.75,
      "reward_std": 0.0,
      "rewards/format_reward": 0.0,
      "rewards/score_reward": 0.75,
      "step": 398
    },
    {
      "clip_ratio": 0.0,
      "completion_length": 170.90625,
      "epoch": 1.596,
      "grad_norm": 12.821555137634277,
      "kl": 0.37255859375,
      "learning_rate": 8.404e-07,
      "loss": 0.0004,
      "reward": 0.28125,
      "reward_std": 0.0883883461356163,
      "rewards/format_reward": 0.0,
      "rewards/score_reward": 0.28125,
      "step": 399
    },
    {
      "clip_ratio": 0.0,
      "completion_length": 173.46875,
      "epoch": 1.6,
      "grad_norm": 2.659421920776367,
      "kl": 0.4072265625,
      "learning_rate": 8.399999999999999e-07,
      "loss": 0.0004,
      "reward": 0.28125,
      "reward_std": 0.0883883461356163,
      "rewards/format_reward": 0.0,
      "rewards/score_reward": 0.28125,
      "step": 400
    },
    {
      "clip_ratio": 0.0,
      "completion_length": 171.875,
      "epoch": 1.604,
      "grad_norm": 3.0120511054992676,
      "kl": 0.3759765625,
      "learning_rate": 8.396e-07,
      "loss": 0.0004,
      "reward": 0.65625,
      "reward_std": 0.1293872892856598,
      "rewards/format_reward": 0.0,
      "rewards/score_reward": 0.65625,
      "step": 401
    },
    {
      "clip_ratio": 0.0,
      "completion_length": 170.09375,
      "epoch": 1.608,
      "grad_norm": 0.057813845574855804,
      "kl": 0.474609375,
      "learning_rate": 8.391999999999999e-07,
      "loss": 0.0005,
      "reward": 0.5,
      "reward_std": 0.0,
      "rewards/format_reward": 0.0,
      "rewards/score_reward": 0.5,
      "step": 402
    },
    {
      "clip_ratio": 0.0,
      "completion_length": 168.46875,
      "epoch": 1.612,
      "grad_norm": 0.05991186574101448,
      "kl": 0.474609375,
      "learning_rate": 8.387999999999999e-07,
      "loss": 0.0005,
      "reward": 0.25,
      "reward_std": 0.0,
      "rewards/format_reward": 0.0,
      "rewards/score_reward": 0.25,
      "step": 403
    },
    {
      "clip_ratio": 0.0,
      "completion_length": 163.09375,
      "epoch": 1.616,
      "grad_norm": 12.902780532836914,
      "kl": 0.3994140625,
      "learning_rate": 8.384e-07,
      "loss": 0.0004,
      "reward": 0.65625,
      "reward_std": 0.3061639815568924,
      "rewards/format_reward": 0.0,
      "rewards/score_reward": 0.65625,
      "step": 404
    },
    {
      "clip_ratio": 0.0,
      "completion_length": 173.46875,
      "epoch": 1.62,
      "grad_norm": 0.03287380188703537,
      "kl": 0.39794921875,
      "learning_rate": 8.38e-07,
      "loss": 0.0004,
      "reward": 0.25,
      "reward_std": 0.0,
      "rewards/format_reward": 0.0,
      "rewards/score_reward": 0.25,
      "step": 405
    },
    {
      "clip_ratio": 0.0,
      "completion_length": 173.625,
      "epoch": 1.624,
      "grad_norm": 0.035295650362968445,
      "kl": 0.408203125,
      "learning_rate": 8.375999999999999e-07,
      "loss": 0.0004,
      "reward": 0.0,
      "reward_std": 0.0,
      "rewards/format_reward": 0.0,
      "rewards/score_reward": 0.0,
      "step": 406
    },
    {
      "clip_ratio": 0.0,
      "completion_length": 173.4375,
      "epoch": 1.6280000000000001,
      "grad_norm": 6.105829238891602,
      "kl": 0.3671875,
      "learning_rate": 8.372e-07,
      "loss": 0.0004,
      "reward": 0.84375,
      "reward_std": 0.1293872892856598,
      "rewards/format_reward": 0.0,
      "rewards/score_reward": 0.84375,
      "step": 407
    },
    {
      "clip_ratio": 0.0,
      "completion_length": 155.75,
      "epoch": 1.6320000000000001,
      "grad_norm": 0.024823768064379692,
      "kl": 0.4033203125,
      "learning_rate": 8.368e-07,
      "loss": 0.0004,
      "reward": 0.5,
      "reward_std": 0.0,
      "rewards/format_reward": 0.0,
      "rewards/score_reward": 0.5,
      "step": 408
    },
    {
      "clip_ratio": 0.0,
      "completion_length": 180.59375,
      "epoch": 1.6360000000000001,
      "grad_norm": 3.6022651195526123,
      "kl": 0.423828125,
      "learning_rate": 8.363999999999999e-07,
      "loss": 0.0004,
      "reward": 0.625,
      "reward_std": 0.2314550280570984,
      "rewards/format_reward": 0.0,
      "rewards/score_reward": 0.625,
      "step": 409
    },
    {
      "clip_ratio": 0.0,
      "completion_length": 168.5625,
      "epoch": 1.6400000000000001,
      "grad_norm": 34.663330078125,
      "kl": 0.4638671875,
      "learning_rate": 8.359999999999999e-07,
      "loss": 0.0005,
      "reward": 0.65625,
      "reward_std": 0.1293872892856598,
      "rewards/format_reward": 0.0,
      "rewards/score_reward": 0.65625,
      "step": 410
    },
    {
      "clip_ratio": 0.0,
      "completion_length": 174.6875,
      "epoch": 1.6440000000000001,
      "grad_norm": 0.057538438588380814,
      "kl": 0.41748046875,
      "learning_rate": 8.356e-07,
      "loss": 0.0004,
      "reward": 0.25,
      "reward_std": 0.0,
      "rewards/format_reward": 0.0,
      "rewards/score_reward": 0.25,
      "step": 411
    },
    {
      "clip_ratio": 0.0,
      "completion_length": 165.0,
      "epoch": 1.6480000000000001,
      "grad_norm": 4.462127208709717,
      "kl": 0.4384765625,
      "learning_rate": 8.352000000000001e-07,
      "loss": 0.0004,
      "reward": 0.0625,
      "reward_std": 0.1157275140285492,
      "rewards/format_reward": 0.0,
      "rewards/score_reward": 0.0625,
      "step": 412
    },
    {
      "clip_ratio": 0.0,
      "completion_length": 157.65625,
      "epoch": 1.6520000000000001,
      "grad_norm": 5.903091907501221,
      "kl": 0.44580078125,
      "learning_rate": 8.347999999999999e-07,
      "loss": 0.0004,
      "reward": 0.5625,
      "reward_std": 0.1157275140285492,
      "rewards/format_reward": 0.0,
      "rewards/score_reward": 0.5625,
      "step": 413
    },
    {
      "clip_ratio": 0.0,
      "completion_length": 164.71875,
      "epoch": 1.6560000000000001,
      "grad_norm": 3.8491811752319336,
      "kl": 0.4384765625,
      "learning_rate": 8.344e-07,
      "loss": 0.0004,
      "reward": 0.59375,
      "reward_std": 0.22201896458864212,
      "rewards/format_reward": 0.0,
      "rewards/score_reward": 0.59375,
      "step": 414
    },
    {
      "clip_ratio": 0.0,
      "completion_length": 167.71875,
      "epoch": 1.6600000000000001,
      "grad_norm": 3.3095595836639404,
      "kl": 0.54345703125,
      "learning_rate": 8.34e-07,
      "loss": 0.0005,
      "reward": 0.09375,
      "reward_std": 0.1293872892856598,
      "rewards/format_reward": 0.0,
      "rewards/score_reward": 0.09375,
      "step": 415
    },
    {
      "clip_ratio": 0.0,
      "completion_length": 164.65625,
      "epoch": 1.6640000000000001,
      "grad_norm": 0.035175856202840805,
      "kl": 0.41015625,
      "learning_rate": 8.335999999999999e-07,
      "loss": 0.0004,
      "reward": 0.75,
      "reward_std": 0.0,
      "rewards/format_reward": 0.0,
      "rewards/score_reward": 0.75,
      "step": 416
    },
    {
      "clip_ratio": 0.0,
      "completion_length": 165.71875,
      "epoch": 1.6680000000000001,
      "grad_norm": 0.03981241583824158,
      "kl": 0.40087890625,
      "learning_rate": 8.332e-07,
      "loss": 0.0004,
      "reward": 0.75,
      "reward_std": 0.0,
      "rewards/format_reward": 0.0,
      "rewards/score_reward": 0.75,
      "step": 417
    },
    {
      "clip_ratio": 0.0,
      "completion_length": 169.75,
      "epoch": 1.6720000000000002,
      "grad_norm": 2.5092711448669434,
      "kl": 0.42333984375,
      "learning_rate": 8.328e-07,
      "loss": 0.0004,
      "reward": 0.375,
      "reward_std": 0.13363061845302582,
      "rewards/format_reward": 0.0,
      "rewards/score_reward": 0.375,
      "step": 418
    },
    {
      "clip_ratio": 0.0,
      "completion_length": 163.78125,
      "epoch": 1.6760000000000002,
      "grad_norm": 5.321307182312012,
      "kl": 0.45068359375,
      "learning_rate": 8.324e-07,
      "loss": 0.0005,
      "reward": 0.5625,
      "reward_std": 0.2177756354212761,
      "rewards/format_reward": 0.0,
      "rewards/score_reward": 0.5625,
      "step": 419
    },
    {
      "clip_ratio": 0.0,
      "completion_length": 163.4375,
      "epoch": 1.6800000000000002,
      "grad_norm": 0.02313672937452793,
      "kl": 0.42529296875,
      "learning_rate": 8.319999999999999e-07,
      "loss": 0.0004,
      "reward": 1.0,
      "reward_std": 0.0,
      "rewards/format_reward": 0.0,
      "rewards/score_reward": 1.0,
      "step": 420
    },
    {
      "clip_ratio": 0.0,
      "completion_length": 170.375,
      "epoch": 1.6840000000000002,
      "grad_norm": 4.892299175262451,
      "kl": 0.38623046875,
      "learning_rate": 8.316e-07,
      "loss": 0.0004,
      "reward": 0.5625,
      "reward_std": 0.2177756354212761,
      "rewards/format_reward": 0.0,
      "rewards/score_reward": 0.5625,
      "step": 421
    },
    {
      "clip_ratio": 0.0,
      "completion_length": 171.0,
      "epoch": 1.688,
      "grad_norm": 4.429207801818848,
      "kl": 0.3623046875,
      "learning_rate": 8.312e-07,
      "loss": 0.0004,
      "reward": 0.65625,
      "reward_std": 0.22201896458864212,
      "rewards/format_reward": 0.0,
      "rewards/score_reward": 0.65625,
      "step": 422
    },
    {
      "clip_ratio": 0.0,
      "completion_length": 163.34375,
      "epoch": 1.692,
      "grad_norm": 5.539219379425049,
      "kl": 0.41748046875,
      "learning_rate": 8.308e-07,
      "loss": 0.0004,
      "reward": 0.5,
      "reward_std": 0.1767766922712326,
      "rewards/format_reward": 0.0,
      "rewards/score_reward": 0.5,
      "step": 423
    },
    {
      "clip_ratio": 0.0,
      "completion_length": 164.5625,
      "epoch": 1.696,
      "grad_norm": 15.078441619873047,
      "kl": 0.41650390625,
      "learning_rate": 8.304e-07,
      "loss": 0.0004,
      "reward": 0.21875,
      "reward_std": 0.0883883461356163,
      "rewards/format_reward": 0.0,
      "rewards/score_reward": 0.21875,
      "step": 424
    },
    {
      "clip_ratio": 0.0,
      "completion_length": 160.84375,
      "epoch": 1.7,
      "grad_norm": 2.2660272121429443,
      "kl": 0.375,
      "learning_rate": 8.299999999999999e-07,
      "loss": 0.0004,
      "reward": 0.125,
      "reward_std": 0.13363061845302582,
      "rewards/format_reward": 0.0,
      "rewards/score_reward": 0.125,
      "step": 425
    },
    {
      "clip_ratio": 0.0,
      "completion_length": 158.46875,
      "epoch": 1.704,
      "grad_norm": 2.217654228210449,
      "kl": 0.3955078125,
      "learning_rate": 8.296e-07,
      "loss": 0.0004,
      "reward": 0.78125,
      "reward_std": 0.0883883461356163,
      "rewards/format_reward": 0.0,
      "rewards/score_reward": 0.78125,
      "step": 426
    },
    {
      "clip_ratio": 0.0,
      "completion_length": 161.90625,
      "epoch": 1.708,
      "grad_norm": 16.062503814697266,
      "kl": 0.49462890625,
      "learning_rate": 8.292e-07,
      "loss": 0.0005,
      "reward": 0.15625,
      "reward_std": 0.22201896458864212,
      "rewards/format_reward": 0.0,
      "rewards/score_reward": 0.15625,
      "step": 427
    },
    {
      "clip_ratio": 0.0,
      "completion_length": 155.15625,
      "epoch": 1.712,
      "grad_norm": 2.677586317062378,
      "kl": 0.43212890625,
      "learning_rate": 8.287999999999999e-07,
      "loss": 0.0004,
      "reward": 0.28125,
      "reward_std": 0.0883883461356163,
      "rewards/format_reward": 0.0,
      "rewards/score_reward": 0.28125,
      "step": 428
    },
    {
      "clip_ratio": 0.0,
      "completion_length": 167.125,
      "epoch": 1.716,
      "grad_norm": 14.95690631866455,
      "kl": 0.42626953125,
      "learning_rate": 8.284e-07,
      "loss": 0.0004,
      "reward": 0.5,
      "reward_std": 0.1767766922712326,
      "rewards/format_reward": 0.0,
      "rewards/score_reward": 0.5,
      "step": 429
    },
    {
      "clip_ratio": 0.0,
      "completion_length": 162.0,
      "epoch": 1.72,
      "grad_norm": 0.026368090882897377,
      "kl": 0.42333984375,
      "learning_rate": 8.28e-07,
      "loss": 0.0004,
      "reward": 0.5,
      "reward_std": 0.0,
      "rewards/format_reward": 0.0,
      "rewards/score_reward": 0.5,
      "step": 430
    },
    {
      "clip_ratio": 0.0,
      "completion_length": 163.75,
      "epoch": 1.724,
      "grad_norm": 2.9461612701416016,
      "kl": 0.45849609375,
      "learning_rate": 8.275999999999999e-07,
      "loss": 0.0005,
      "reward": 0.28125,
      "reward_std": 0.0883883461356163,
      "rewards/format_reward": 0.0,
      "rewards/score_reward": 0.28125,
      "step": 431
    },
    {
      "clip_ratio": 0.0,
      "completion_length": 167.15625,
      "epoch": 1.728,
      "grad_norm": 0.02435384877026081,
      "kl": 0.41357421875,
      "learning_rate": 8.272e-07,
      "loss": 0.0004,
      "reward": 0.25,
      "reward_std": 0.0,
      "rewards/format_reward": 0.0,
      "rewards/score_reward": 0.25,
      "step": 432
    },
    {
      "clip_ratio": 0.0,
      "completion_length": 160.8125,
      "epoch": 1.732,
      "grad_norm": 0.02652944251894951,
      "kl": 0.41015625,
      "learning_rate": 8.268e-07,
      "loss": 0.0004,
      "reward": 0.25,
      "reward_std": 0.0,
      "rewards/format_reward": 0.0,
      "rewards/score_reward": 0.25,
      "step": 433
    },
    {
      "clip_ratio": 0.0,
      "completion_length": 154.90625,
      "epoch": 1.736,
      "grad_norm": 6.1886115074157715,
      "kl": 0.4853515625,
      "learning_rate": 8.263999999999999e-07,
      "loss": 0.0005,
      "reward": 0.21875,
      "reward_std": 0.0883883461356163,
      "rewards/format_reward": 0.0,
      "rewards/score_reward": 0.21875,
      "step": 434
    },
    {
      "clip_ratio": 0.0,
      "completion_length": 157.875,
      "epoch": 1.74,
      "grad_norm": 13.261157989501953,
      "kl": 0.45166015625,
      "learning_rate": 8.259999999999999e-07,
      "loss": 0.0005,
      "reward": 0.3125,
      "reward_std": 0.3514062538743019,
      "rewards/format_reward": 0.0,
      "rewards/score_reward": 0.3125,
      "step": 435
    },
    {
      "clip_ratio": 0.0,
      "completion_length": 160.25,
      "epoch": 1.744,
      "grad_norm": 1.860460877418518,
      "kl": 0.40966796875,
      "learning_rate": 8.256e-07,
      "loss": 0.0004,
      "reward": 0.15625,
      "reward_std": 0.1293872892856598,
      "rewards/format_reward": 0.0,
      "rewards/score_reward": 0.15625,
      "step": 436
    },
    {
      "clip_ratio": 0.0,
      "completion_length": 158.125,
      "epoch": 1.748,
      "grad_norm": 0.02234129048883915,
      "kl": 0.4365234375,
      "learning_rate": 8.252000000000001e-07,
      "loss": 0.0004,
      "reward": 0.25,
      "reward_std": 0.0,
      "rewards/format_reward": 0.0,
      "rewards/score_reward": 0.25,
      "step": 437
    },
    {
      "clip_ratio": 0.0,
      "completion_length": 150.09375,
      "epoch": 1.752,
      "grad_norm": 0.08076012879610062,
      "kl": 0.4140625,
      "learning_rate": 8.247999999999999e-07,
      "loss": 0.0004,
      "reward": 0.0,
      "reward_std": 0.0,
      "rewards/format_reward": 0.0,
      "rewards/score_reward": 0.0,
      "step": 438
    },
    {
      "clip_ratio": 0.0,
      "completion_length": 167.28125,
      "epoch": 1.756,
      "grad_norm": 2.5461416244506836,
      "kl": 0.35107421875,
      "learning_rate": 8.244e-07,
      "loss": 0.0004,
      "reward": 0.3125,
      "reward_std": 0.1157275140285492,
      "rewards/format_reward": 0.0,
      "rewards/score_reward": 0.3125,
      "step": 439
    },
    {
      "clip_ratio": 0.0,
      "completion_length": 162.25,
      "epoch": 1.76,
      "grad_norm": 4.5673346519470215,
      "kl": 0.41455078125,
      "learning_rate": 8.24e-07,
      "loss": 0.0004,
      "reward": 0.46875,
      "reward_std": 0.0883883461356163,
      "rewards/format_reward": 0.0,
      "rewards/score_reward": 0.46875,
      "step": 440
    },
    {
      "clip_ratio": 0.0,
      "completion_length": 164.71875,
      "epoch": 1.764,
      "grad_norm": 10.48403549194336,
      "kl": 0.37548828125,
      "learning_rate": 8.235999999999999e-07,
      "loss": 0.0004,
      "reward": 0.40625,
      "reward_std": 0.1293872892856598,
      "rewards/format_reward": 0.0,
      "rewards/score_reward": 0.40625,
      "step": 441
    },
    {
      "clip_ratio": 0.0,
      "completion_length": 170.4375,
      "epoch": 1.768,
      "grad_norm": 0.018004318699240685,
      "kl": 0.376953125,
      "learning_rate": 8.232e-07,
      "loss": 0.0004,
      "reward": 0.25,
      "reward_std": 0.0,
      "rewards/format_reward": 0.0,
      "rewards/score_reward": 0.25,
      "step": 442
    },
    {
      "clip_ratio": 0.0,
      "completion_length": 163.53125,
      "epoch": 1.772,
      "grad_norm": 0.020243454724550247,
      "kl": 0.4091796875,
      "learning_rate": 8.228e-07,
      "loss": 0.0004,
      "reward": 0.5,
      "reward_std": 0.0,
      "rewards/format_reward": 0.0,
      "rewards/score_reward": 0.5,
      "step": 443
    },
    {
      "clip_ratio": 0.0,
      "completion_length": 163.1875,
      "epoch": 1.776,
      "grad_norm": 0.02688312903046608,
      "kl": 0.42138671875,
      "learning_rate": 8.224e-07,
      "loss": 0.0004,
      "reward": 0.75,
      "reward_std": 0.0,
      "rewards/format_reward": 0.0,
      "rewards/score_reward": 0.75,
      "step": 444
    },
    {
      "clip_ratio": 0.0,
      "completion_length": 170.4375,
      "epoch": 1.78,
      "grad_norm": 8.352977752685547,
      "kl": 0.396484375,
      "learning_rate": 8.219999999999999e-07,
      "loss": 0.0004,
      "reward": 0.34375,
      "reward_std": 0.1293872892856598,
      "rewards/format_reward": 0.0,
      "rewards/score_reward": 0.34375,
      "step": 445
    },
    {
      "clip_ratio": 0.0,
      "completion_length": 164.84375,
      "epoch": 1.784,
      "grad_norm": 0.057273704558610916,
      "kl": 0.40283203125,
      "learning_rate": 8.216e-07,
      "loss": 0.0004,
      "reward": 1.0,
      "reward_std": 0.0,
      "rewards/format_reward": 0.0,
      "rewards/score_reward": 1.0,
      "step": 446
    },
    {
      "clip_ratio": 0.0,
      "completion_length": 166.84375,
      "epoch": 1.788,
      "grad_norm": 1.9381979703903198,
      "kl": 0.3701171875,
      "learning_rate": 8.212e-07,
      "loss": 0.0004,
      "reward": 0.4375,
      "reward_std": 0.1157275140285492,
      "rewards/format_reward": 0.0,
      "rewards/score_reward": 0.4375,
      "step": 447
    },
    {
      "clip_ratio": 0.0,
      "completion_length": 159.6875,
      "epoch": 1.792,
      "grad_norm": 7.398300647735596,
      "kl": 0.37939453125,
      "learning_rate": 8.207999999999999e-07,
      "loss": 0.0004,
      "reward": 0.34375,
      "reward_std": 0.24511480331420898,
      "rewards/format_reward": 0.0,
      "rewards/score_reward": 0.34375,
      "step": 448
    },
    {
      "clip_ratio": 0.0,
      "completion_length": 170.59375,
      "epoch": 1.796,
      "grad_norm": 5.741900444030762,
      "kl": 0.4267578125,
      "learning_rate": 8.204e-07,
      "loss": 0.0004,
      "reward": 0.46875,
      "reward_std": 0.2041158601641655,
      "rewards/format_reward": 0.0,
      "rewards/score_reward": 0.46875,
      "step": 449
    },
    {
      "clip_ratio": 0.0,
      "completion_length": 178.9375,
      "epoch": 1.8,
      "grad_norm": 0.04533645510673523,
      "kl": 0.3720703125,
      "learning_rate": 8.199999999999999e-07,
      "loss": 0.0004,
      "reward": 0.5,
      "reward_std": 0.0,
      "rewards/format_reward": 0.0,
      "rewards/score_reward": 0.5,
      "step": 450
    },
    {
      "clip_ratio": 0.0,
      "completion_length": 183.4375,
      "epoch": 1.804,
      "grad_norm": 2.4087061882019043,
      "kl": 0.58642578125,
      "learning_rate": 8.196e-07,
      "loss": 0.0006,
      "reward": 0.03125,
      "reward_std": 0.0883883461356163,
      "rewards/format_reward": 0.0,
      "rewards/score_reward": 0.03125,
      "step": 451
    },
    {
      "clip_ratio": 0.0,
      "completion_length": 176.4375,
      "epoch": 1.808,
      "grad_norm": 5.901292324066162,
      "kl": 0.3544921875,
      "learning_rate": 8.192e-07,
      "loss": 0.0004,
      "reward": 0.96875,
      "reward_std": 0.0883883461356163,
      "rewards/format_reward": 0.0,
      "rewards/score_reward": 0.96875,
      "step": 452
    },
    {
      "clip_ratio": 0.0,
      "completion_length": 172.03125,
      "epoch": 1.812,
      "grad_norm": 0.013622630387544632,
      "kl": 0.3583984375,
      "learning_rate": 8.187999999999999e-07,
      "loss": 0.0004,
      "reward": 0.5,
      "reward_std": 0.0,
      "rewards/format_reward": 0.0,
      "rewards/score_reward": 0.5,
      "step": 453
    },
    {
      "clip_ratio": 0.0,
      "completion_length": 185.15625,
      "epoch": 1.8159999999999998,
      "grad_norm": 13.24351692199707,
      "kl": 0.35791015625,
      "learning_rate": 8.184e-07,
      "loss": 0.0004,
      "reward": 0.46875,
      "reward_std": 0.3198433741927147,
      "rewards/format_reward": 0.0,
      "rewards/score_reward": 0.46875,
      "step": 454
    },
    {
      "clip_ratio": 0.0,
      "completion_length": 180.03125,
      "epoch": 1.8199999999999998,
      "grad_norm": 9.442585945129395,
      "kl": 0.3681640625,
      "learning_rate": 8.179999999999999e-07,
      "loss": 0.0004,
      "reward": 0.6875,
      "reward_std": 0.2925042062997818,
      "rewards/format_reward": 0.0,
      "rewards/score_reward": 0.6875,
      "step": 455
    },
    {
      "clip_ratio": 0.0,
      "completion_length": 182.25,
      "epoch": 1.8239999999999998,
      "grad_norm": 19.553857803344727,
      "kl": 0.32421875,
      "learning_rate": 8.175999999999999e-07,
      "loss": 0.0003,
      "reward": 0.375,
      "reward_std": 0.2177756354212761,
      "rewards/format_reward": 0.0,
      "rewards/score_reward": 0.375,
      "step": 456
    },
    {
      "clip_ratio": 0.0,
      "completion_length": 165.625,
      "epoch": 1.8279999999999998,
      "grad_norm": 3.0148234367370605,
      "kl": 0.3466796875,
      "learning_rate": 8.172e-07,
      "loss": 0.0003,
      "reward": 0.3125,
      "reward_std": 0.2177756354212761,
      "rewards/format_reward": 0.0,
      "rewards/score_reward": 0.3125,
      "step": 457
    },
    {
      "clip_ratio": 0.0,
      "completion_length": 169.5,
      "epoch": 1.8319999999999999,
      "grad_norm": 3.1484971046447754,
      "kl": 0.36279296875,
      "learning_rate": 8.168e-07,
      "loss": 0.0004,
      "reward": 0.625,
      "reward_std": 0.13363061845302582,
      "rewards/format_reward": 0.0,
      "rewards/score_reward": 0.625,
      "step": 458
    },
    {
      "clip_ratio": 0.0,
      "completion_length": 190.34375,
      "epoch": 1.8359999999999999,
      "grad_norm": 2.9252376556396484,
      "kl": 0.37353515625,
      "learning_rate": 8.163999999999999e-07,
      "loss": 0.0004,
      "reward": 0.65625,
      "reward_std": 0.2041158601641655,
      "rewards/format_reward": 0.0,
      "rewards/score_reward": 0.65625,
      "step": 459
    },
    {
      "clip_ratio": 0.0,
      "completion_length": 191.3125,
      "epoch": 1.8399999999999999,
      "grad_norm": 4.039405345916748,
      "kl": 0.30712890625,
      "learning_rate": 8.159999999999999e-07,
      "loss": 0.0003,
      "reward": 0.40625,
      "reward_std": 0.1293872892856598,
      "rewards/format_reward": 0.0,
      "rewards/score_reward": 0.40625,
      "step": 460
    },
    {
      "clip_ratio": 0.0,
      "completion_length": 182.84375,
      "epoch": 1.8439999999999999,
      "grad_norm": 3.5302557945251465,
      "kl": 0.34228515625,
      "learning_rate": 8.156e-07,
      "loss": 0.0003,
      "reward": 0.5625,
      "reward_std": 0.2177756354212761,
      "rewards/format_reward": 0.0,
      "rewards/score_reward": 0.5625,
      "step": 461
    },
    {
      "clip_ratio": 0.0,
      "completion_length": 178.625,
      "epoch": 1.8479999999999999,
      "grad_norm": 2.647287607192993,
      "kl": 0.38916015625,
      "learning_rate": 8.152e-07,
      "loss": 0.0004,
      "reward": 0.40625,
      "reward_std": 0.1293872892856598,
      "rewards/format_reward": 0.0,
      "rewards/score_reward": 0.40625,
      "step": 462
    },
    {
      "clip_ratio": 0.0,
      "completion_length": 177.34375,
      "epoch": 1.8519999999999999,
      "grad_norm": 3.616725206375122,
      "kl": 0.41162109375,
      "learning_rate": 8.147999999999999e-07,
      "loss": 0.0004,
      "reward": 0.71875,
      "reward_std": 0.0883883461356163,
      "rewards/format_reward": 0.0,
      "rewards/score_reward": 0.71875,
      "step": 463
    },
    {
      "clip_ratio": 0.0,
      "completion_length": 191.34375,
      "epoch": 1.8559999999999999,
      "grad_norm": 26.745315551757812,
      "kl": 0.359375,
      "learning_rate": 8.144e-07,
      "loss": 0.0004,
      "reward": 0.46875,
      "reward_std": 0.2041158601641655,
      "rewards/format_reward": 0.0,
      "rewards/score_reward": 0.46875,
      "step": 464
    },
    {
      "clip_ratio": 0.0,
      "completion_length": 180.84375,
      "epoch": 1.8599999999999999,
      "grad_norm": 7.421332359313965,
      "kl": 0.3837890625,
      "learning_rate": 8.14e-07,
      "loss": 0.0004,
      "reward": 0.375,
      "reward_std": 0.2177756354212761,
      "rewards/format_reward": 0.0,
      "rewards/score_reward": 0.375,
      "step": 465
    },
    {
      "clip_ratio": 0.0,
      "completion_length": 170.96875,
      "epoch": 1.8639999999999999,
      "grad_norm": 5.073638439178467,
      "kl": 0.365234375,
      "learning_rate": 8.135999999999999e-07,
      "loss": 0.0004,
      "reward": 0.59375,
      "reward_std": 0.3061639815568924,
      "rewards/format_reward": 0.0,
      "rewards/score_reward": 0.59375,
      "step": 466
    },
    {
      "clip_ratio": 0.0,
      "completion_length": 174.09375,
      "epoch": 1.8679999999999999,
      "grad_norm": 4.215259552001953,
      "kl": 0.341796875,
      "learning_rate": 8.132e-07,
      "loss": 0.0003,
      "reward": 0.59375,
      "reward_std": 0.22201896458864212,
      "rewards/format_reward": 0.0,
      "rewards/score_reward": 0.59375,
      "step": 467
    },
    {
      "clip_ratio": 0.0,
      "completion_length": 183.46875,
      "epoch": 1.8719999999999999,
      "grad_norm": 30.839479446411133,
      "kl": 0.345703125,
      "learning_rate": 8.128e-07,
      "loss": 0.0003,
      "reward": 0.21875,
      "reward_std": 0.0883883461356163,
      "rewards/format_reward": 0.0,
      "rewards/score_reward": 0.21875,
      "step": 468
    },
    {
      "clip_ratio": 0.0,
      "completion_length": 163.125,
      "epoch": 1.876,
      "grad_norm": 3.3285722732543945,
      "kl": 0.38720703125,
      "learning_rate": 8.123999999999999e-07,
      "loss": 0.0004,
      "reward": 0.65625,
      "reward_std": 0.1293872892856598,
      "rewards/format_reward": 0.0,
      "rewards/score_reward": 0.65625,
      "step": 469
    },
    {
      "clip_ratio": 0.0,
      "completion_length": 158.03125,
      "epoch": 1.88,
      "grad_norm": 0.04166668653488159,
      "kl": 0.458984375,
      "learning_rate": 8.12e-07,
      "loss": 0.0005,
      "reward": 0.25,
      "reward_std": 0.0,
      "rewards/format_reward": 0.0,
      "rewards/score_reward": 0.25,
      "step": 470
    },
    {
      "clip_ratio": 0.0,
      "completion_length": 164.84375,
      "epoch": 1.884,
      "grad_norm": 6.062572479248047,
      "kl": 0.40771484375,
      "learning_rate": 8.116e-07,
      "loss": 0.0004,
      "reward": 0.09375,
      "reward_std": 0.2041158601641655,
      "rewards/format_reward": 0.0,
      "rewards/score_reward": 0.09375,
      "step": 471
    },
    {
      "clip_ratio": 0.0,
      "completion_length": 156.3125,
      "epoch": 1.888,
      "grad_norm": 9.836076736450195,
      "kl": 0.36474609375,
      "learning_rate": 8.112e-07,
      "loss": 0.0004,
      "reward": 0.6875,
      "reward_std": 0.1767766922712326,
      "rewards/format_reward": 0.0,
      "rewards/score_reward": 0.6875,
      "step": 472
    },
    {
      "clip_ratio": 0.0,
      "completion_length": 165.4375,
      "epoch": 1.892,
      "grad_norm": 2.3117265701293945,
      "kl": 0.38330078125,
      "learning_rate": 8.107999999999999e-07,
      "loss": 0.0004,
      "reward": 0.34375,
      "reward_std": 0.1293872892856598,
      "rewards/format_reward": 0.0,
      "rewards/score_reward": 0.34375,
      "step": 473
    },
    {
      "clip_ratio": 0.0,
      "completion_length": 165.1875,
      "epoch": 1.896,
      "grad_norm": 0.01977263018488884,
      "kl": 0.39892578125,
      "learning_rate": 8.104e-07,
      "loss": 0.0004,
      "reward": 0.25,
      "reward_std": 0.0,
      "rewards/format_reward": 0.0,
      "rewards/score_reward": 0.25,
      "step": 474
    },
    {
      "clip_ratio": 0.0,
      "completion_length": 150.375,
      "epoch": 1.9,
      "grad_norm": 7.866539001464844,
      "kl": 0.48486328125,
      "learning_rate": 8.1e-07,
      "loss": 0.0005,
      "reward": 0.46875,
      "reward_std": 0.0883883461356163,
      "rewards/format_reward": 0.0,
      "rewards/score_reward": 0.46875,
      "step": 475
    },
    {
      "clip_ratio": 0.0,
      "completion_length": 164.0625,
      "epoch": 1.904,
      "grad_norm": 3.914083242416382,
      "kl": 0.3837890625,
      "learning_rate": 8.095999999999999e-07,
      "loss": 0.0004,
      "reward": 0.28125,
      "reward_std": 0.2041158601641655,
      "rewards/format_reward": 0.0,
      "rewards/score_reward": 0.28125,
      "step": 476
    },
    {
      "clip_ratio": 0.0,
      "completion_length": 151.4375,
      "epoch": 1.908,
      "grad_norm": 3.30718994140625,
      "kl": 0.537109375,
      "learning_rate": 8.092e-07,
      "loss": 0.0005,
      "reward": 0.28125,
      "reward_std": 0.0883883461356163,
      "rewards/format_reward": 0.0,
      "rewards/score_reward": 0.28125,
      "step": 477
    },
    {
      "clip_ratio": 0.0,
      "completion_length": 165.25,
      "epoch": 1.912,
      "grad_norm": 1.9141907691955566,
      "kl": 0.37841796875,
      "learning_rate": 8.087999999999999e-07,
      "loss": 0.0004,
      "reward": 0.71875,
      "reward_std": 0.0883883461356163,
      "rewards/format_reward": 0.0,
      "rewards/score_reward": 0.71875,
      "step": 478
    },
    {
      "clip_ratio": 0.0,
      "completion_length": 152.0625,
      "epoch": 1.916,
      "grad_norm": 3.471940279006958,
      "kl": 0.42333984375,
      "learning_rate": 8.084e-07,
      "loss": 0.0004,
      "reward": 0.53125,
      "reward_std": 0.0883883461356163,
      "rewards/format_reward": 0.0,
      "rewards/score_reward": 0.53125,
      "step": 479
    },
    {
      "clip_ratio": 0.0,
      "completion_length": 166.78125,
      "epoch": 1.92,
      "grad_norm": 0.02734890766441822,
      "kl": 0.3984375,
      "learning_rate": 8.08e-07,
      "loss": 0.0004,
      "reward": 0.25,
      "reward_std": 0.0,
      "rewards/format_reward": 0.0,
      "rewards/score_reward": 0.25,
      "step": 480
    },
    {
      "clip_ratio": 0.0,
      "completion_length": 155.5625,
      "epoch": 1.924,
      "grad_norm": 2.8940510749816895,
      "kl": 0.408203125,
      "learning_rate": 8.075999999999999e-07,
      "loss": 0.0004,
      "reward": 0.28125,
      "reward_std": 0.0883883461356163,
      "rewards/format_reward": 0.0,
      "rewards/score_reward": 0.28125,
      "step": 481
    },
    {
      "clip_ratio": 0.0,
      "completion_length": 152.875,
      "epoch": 1.928,
      "grad_norm": 6.591331481933594,
      "kl": 0.36474609375,
      "learning_rate": 8.072e-07,
      "loss": 0.0004,
      "reward": 0.34375,
      "reward_std": 0.2041158601641655,
      "rewards/format_reward": 0.0,
      "rewards/score_reward": 0.34375,
      "step": 482
    },
    {
      "clip_ratio": 0.0,
      "completion_length": 163.28125,
      "epoch": 1.932,
      "grad_norm": 0.044952016323804855,
      "kl": 0.36328125,
      "learning_rate": 8.067999999999999e-07,
      "loss": 0.0004,
      "reward": 0.25,
      "reward_std": 0.0,
      "rewards/format_reward": 0.0,
      "rewards/score_reward": 0.25,
      "step": 483
    },
    {
      "clip_ratio": 0.0,
      "completion_length": 160.0,
      "epoch": 1.936,
      "grad_norm": 2.8192989826202393,
      "kl": 0.423828125,
      "learning_rate": 8.064e-07,
      "loss": 0.0004,
      "reward": 0.96875,
      "reward_std": 0.0883883461356163,
      "rewards/format_reward": 0.0,
      "rewards/score_reward": 0.96875,
      "step": 484
    },
    {
      "clip_ratio": 0.0,
      "completion_length": 145.90625,
      "epoch": 1.94,
      "grad_norm": 0.05787898600101471,
      "kl": 0.421875,
      "learning_rate": 8.06e-07,
      "loss": 0.0004,
      "reward": 0.25,
      "reward_std": 0.0,
      "rewards/format_reward": 0.0,
      "rewards/score_reward": 0.25,
      "step": 485
    },
    {
      "clip_ratio": 0.0,
      "completion_length": 149.84375,
      "epoch": 1.944,
      "grad_norm": 6.145750045776367,
      "kl": 0.50146484375,
      "learning_rate": 8.056e-07,
      "loss": 0.0005,
      "reward": 0.4375,
      "reward_std": 0.2177756354212761,
      "rewards/format_reward": 0.0,
      "rewards/score_reward": 0.4375,
      "step": 486
    },
    {
      "clip_ratio": 0.0,
      "completion_length": 154.90625,
      "epoch": 1.948,
      "grad_norm": 2.458923578262329,
      "kl": 0.37451171875,
      "learning_rate": 8.052e-07,
      "loss": 0.0004,
      "reward": 0.34375,
      "reward_std": 0.1293872892856598,
      "rewards/format_reward": 0.0,
      "rewards/score_reward": 0.34375,
      "step": 487
    },
    {
      "clip_ratio": 0.0,
      "completion_length": 165.46875,
      "epoch": 1.952,
      "grad_norm": 2.168976306915283,
      "kl": 0.390625,
      "learning_rate": 8.047999999999999e-07,
      "loss": 0.0004,
      "reward": 0.40625,
      "reward_std": 0.1293872892856598,
      "rewards/format_reward": 0.0,
      "rewards/score_reward": 0.40625,
      "step": 488
    },
    {
      "clip_ratio": 0.0,
      "completion_length": 167.3125,
      "epoch": 1.956,
      "grad_norm": 5.698536396026611,
      "kl": 0.408203125,
      "learning_rate": 8.044e-07,
      "loss": 0.0004,
      "reward": 0.65625,
      "reward_std": 0.2041158601641655,
      "rewards/format_reward": 0.0,
      "rewards/score_reward": 0.65625,
      "step": 489
    },
    {
      "clip_ratio": 0.0,
      "completion_length": 161.0,
      "epoch": 1.96,
      "grad_norm": 0.03852026164531708,
      "kl": 0.44873046875,
      "learning_rate": 8.04e-07,
      "loss": 0.0004,
      "reward": 0.5,
      "reward_std": 0.0,
      "rewards/format_reward": 0.0,
      "rewards/score_reward": 0.5,
      "step": 490
    },
    {
      "clip_ratio": 0.0,
      "completion_length": 158.40625,
      "epoch": 1.964,
      "grad_norm": 0.02888845093548298,
      "kl": 0.4013671875,
      "learning_rate": 8.035999999999999e-07,
      "loss": 0.0004,
      "reward": 0.0,
      "reward_std": 0.0,
      "rewards/format_reward": 0.0,
      "rewards/score_reward": 0.0,
      "step": 491
    },
    {
      "clip_ratio": 0.0,
      "completion_length": 180.625,
      "epoch": 1.968,
      "grad_norm": 2.9419054985046387,
      "kl": 0.53662109375,
      "learning_rate": 8.032e-07,
      "loss": 0.0005,
      "reward": 0.4375,
      "reward_std": 0.1157275140285492,
      "rewards/format_reward": 0.0,
      "rewards/score_reward": 0.4375,
      "step": 492
    },
    {
      "clip_ratio": 0.0,
      "completion_length": 161.75,
      "epoch": 1.972,
      "grad_norm": 2.9988346099853516,
      "kl": 0.3994140625,
      "learning_rate": 8.028e-07,
      "loss": 0.0004,
      "reward": 0.46875,
      "reward_std": 0.0883883461356163,
      "rewards/format_reward": 0.0,
      "rewards/score_reward": 0.46875,
      "step": 493
    },
    {
      "clip_ratio": 0.0,
      "completion_length": 171.875,
      "epoch": 1.976,
      "grad_norm": 0.023221736773848534,
      "kl": 0.4091796875,
      "learning_rate": 8.023999999999999e-07,
      "loss": 0.0004,
      "reward": 0.0,
      "reward_std": 0.0,
      "rewards/format_reward": 0.0,
      "rewards/score_reward": 0.0,
      "step": 494
    },
    {
      "clip_ratio": 0.0,
      "completion_length": 175.125,
      "epoch": 1.98,
      "grad_norm": 0.026831550523638725,
      "kl": 0.3896484375,
      "learning_rate": 8.02e-07,
      "loss": 0.0004,
      "reward": 0.25,
      "reward_std": 0.0,
      "rewards/format_reward": 0.0,
      "rewards/score_reward": 0.25,
      "step": 495
    },
    {
      "clip_ratio": 0.0,
      "completion_length": 176.75,
      "epoch": 1.984,
      "grad_norm": 1.9323009252548218,
      "kl": 0.39208984375,
      "learning_rate": 8.016e-07,
      "loss": 0.0004,
      "reward": 0.46875,
      "reward_std": 0.0883883461356163,
      "rewards/format_reward": 0.0,
      "rewards/score_reward": 0.46875,
      "step": 496
    },
    {
      "clip_ratio": 0.0,
      "completion_length": 179.9375,
      "epoch": 1.988,
      "grad_norm": 2.6626555919647217,
      "kl": 0.37744140625,
      "learning_rate": 8.012e-07,
      "loss": 0.0004,
      "reward": 0.4375,
      "reward_std": 0.1157275140285492,
      "rewards/format_reward": 0.0,
      "rewards/score_reward": 0.4375,
      "step": 497
    },
    {
      "clip_ratio": 0.0,
      "completion_length": 168.875,
      "epoch": 1.992,
      "grad_norm": 5.306944847106934,
      "kl": 0.34814453125,
      "learning_rate": 8.007999999999999e-07,
      "loss": 0.0003,
      "reward": 0.59375,
      "reward_std": 0.1293872892856598,
      "rewards/format_reward": 0.0,
      "rewards/score_reward": 0.59375,
      "step": 498
    },
    {
      "clip_ratio": 0.0,
      "completion_length": 183.96875,
      "epoch": 1.996,
      "grad_norm": 0.02336149290204048,
      "kl": 0.41064453125,
      "learning_rate": 8.004e-07,
      "loss": 0.0004,
      "reward": 0.25,
      "reward_std": 0.0,
      "rewards/format_reward": 0.0,
      "rewards/score_reward": 0.25,
      "step": 499
    },
    {
      "clip_ratio": 0.0,
      "completion_length": 175.15625,
      "epoch": 2.0,
      "grad_norm": 5.964815616607666,
      "kl": 0.4072265625,
      "learning_rate": 8e-07,
      "loss": 0.0004,
      "reward": 0.4375,
      "reward_std": 0.1767766922712326,
      "rewards/format_reward": 0.0,
      "rewards/score_reward": 0.4375,
      "step": 500
    }
  ],
  "logging_steps": 1.0,
  "max_steps": 2500,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 10,
  "save_steps": 500,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 0.0,
  "train_batch_size": 1,
  "trial_name": null,
  "trial_params": null
}