{
  "best_global_step": null,
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 1.0666666666666667,
  "eval_steps": 500,
  "global_step": 160,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "clip_ratio/high_max": 0.0,
      "clip_ratio/high_mean": 0.0,
      "clip_ratio/low_mean": 0.0,
      "clip_ratio/low_min": 0.0,
      "clip_ratio/region_mean": 0.0,
      "completions/clipped_ratio": 0.0625,
      "completions/max_length": 419.8,
      "completions/max_terminated_length": 406.8,
      "completions/mean_length": 314.8625,
      "completions/mean_terminated_length": 307.5414337158203,
      "completions/min_length": 206.3,
      "completions/min_terminated_length": 206.3,
      "entropy": 0.44715926721692084,
      "epoch": 0.06666666666666667,
      "frac_reward_zero_std": 0.15,
      "grad_norm": 4.625,
      "kl": 0.09871633112052222,
      "learning_rate": 9.4375e-06,
      "loss": -0.010261553525924682,
      "num_tokens": 38057.0,
      "reward": 0.9905517578125,
      "reward_std": 0.6565703094005585,
      "rewards/JointRewardFunction/mean": 0.9905517578125,
      "rewards/JointRewardFunction/std": 0.6565703094005585,
      "step": 10,
      "step_time": 19.035294922399043
    },
    {
      "clip_ratio/high_max": 0.0,
      "clip_ratio/high_mean": 0.0,
      "clip_ratio/low_mean": 0.0,
      "clip_ratio/low_min": 0.0,
      "clip_ratio/region_mean": 0.0,
      "completions/clipped_ratio": 0.2,
      "completions/max_length": 458.4,
      "completions/max_terminated_length": 426.1,
      "completions/mean_length": 343.8,
      "completions/mean_terminated_length": 313.08583984375,
      "completions/min_length": 211.7,
      "completions/min_terminated_length": 211.7,
      "entropy": 0.31359912948682905,
      "epoch": 0.13333333333333333,
      "frac_reward_zero_std": 0.1,
      "grad_norm": 3.125,
      "kl": 0.14868967132642866,
      "learning_rate": 8.8125e-06,
      "loss": -0.023439544439315795,
      "num_tokens": 79321.0,
      "reward": 1.072357177734375,
      "reward_std": 0.5760923266410828,
      "rewards/JointRewardFunction/mean": 1.072357177734375,
      "rewards/JointRewardFunction/std": 0.5760923385620117,
      "step": 20,
      "step_time": 21.0788949906022
    },
    {
      "clip_ratio/high_max": 0.0,
      "clip_ratio/high_mean": 0.0,
      "clip_ratio/low_mean": 0.0,
      "clip_ratio/low_min": 0.0,
      "clip_ratio/region_mean": 0.0,
      "completions/clipped_ratio": 0.0,
      "completions/max_length": 351.8,
      "completions/max_terminated_length": 351.8,
      "completions/mean_length": 260.625,
      "completions/mean_terminated_length": 260.625,
      "completions/min_length": 174.2,
      "completions/min_terminated_length": 174.2,
      "entropy": 0.3843053654767573,
      "epoch": 0.2,
      "frac_reward_zero_std": 0.1,
      "grad_norm": 4.5625,
      "kl": 0.18629266200587152,
      "learning_rate": 8.1875e-06,
      "loss": 0.004870641976594925,
      "num_tokens": 111587.0,
      "reward": 1.3501953125,
      "reward_std": 0.6562108278274537,
      "rewards/JointRewardFunction/mean": 1.3501953125,
      "rewards/JointRewardFunction/std": 0.6562108367681503,
      "step": 30,
      "step_time": 16.898221987598664
    },
    {
      "clip_ratio/high_max": 0.0,
      "clip_ratio/high_mean": 0.0,
      "clip_ratio/low_mean": 0.0,
      "clip_ratio/low_min": 0.0,
      "clip_ratio/region_mean": 0.0,
      "completions/clipped_ratio": 0.0375,
      "completions/max_length": 429.1,
      "completions/max_terminated_length": 425.2,
      "completions/mean_length": 327.5125,
      "completions/mean_terminated_length": 321.53809814453126,
      "completions/min_length": 227.9,
      "completions/min_terminated_length": 227.9,
      "entropy": 0.44414809048175813,
      "epoch": 0.26666666666666666,
      "frac_reward_zero_std": 0.35,
      "grad_norm": 6.34375,
      "kl": 0.14110819818452,
      "learning_rate": 7.5625e-06,
      "loss": -0.03268973827362061,
      "num_tokens": 151100.0,
      "reward": 1.493701171875,
      "reward_std": 0.3899420065339655,
      "rewards/JointRewardFunction/mean": 1.493701171875,
      "rewards/JointRewardFunction/std": 0.38994201249442995,
      "step": 40,
      "step_time": 20.12026042639991
    },
    {
      "clip_ratio/high_max": 0.0,
      "clip_ratio/high_mean": 0.0,
      "clip_ratio/low_mean": 0.0,
      "clip_ratio/low_min": 0.0,
      "clip_ratio/region_mean": 0.0,
      "completions/clipped_ratio": 0.225,
      "completions/max_length": 472.2,
      "completions/max_terminated_length": 427.6,
      "completions/mean_length": 352.75,
      "completions/mean_terminated_length": 313.9489349365234,
      "completions/min_length": 201.0,
      "completions/min_terminated_length": 201.0,
      "entropy": 0.5324544316157699,
      "epoch": 0.3333333333333333,
      "frac_reward_zero_std": 0.25,
      "grad_norm": 5.3125,
      "kl": 0.13007921809330583,
      "learning_rate": 6.9375e-06,
      "loss": -0.03016577959060669,
      "num_tokens": 192036.0,
      "reward": 1.0732177734375,
      "reward_std": 0.5164182722568512,
      "rewards/JointRewardFunction/mean": 1.0732177734375,
      "rewards/JointRewardFunction/std": 0.5164182841777801,
      "step": 50,
      "step_time": 21.588160099001833
    },
    {
      "clip_ratio/high_max": 0.0,
      "clip_ratio/high_mean": 0.0,
      "clip_ratio/low_mean": 0.0,
      "clip_ratio/low_min": 0.0,
      "clip_ratio/region_mean": 0.0,
      "completions/clipped_ratio": 0.225,
      "completions/max_length": 495.4,
      "completions/max_terminated_length": 461.4,
      "completions/mean_length": 396.95,
      "completions/mean_terminated_length": 363.4666687011719,
      "completions/min_length": 224.4,
      "completions/min_terminated_length": 224.4,
      "entropy": 0.47121726758778093,
      "epoch": 0.4,
      "frac_reward_zero_std": 0.05,
      "grad_norm": 2.46875,
      "kl": 0.10462474231608213,
      "learning_rate": 6.3125e-06,
      "loss": -0.031146174669265746,
      "num_tokens": 237192.0,
      "reward": 1.193585205078125,
      "reward_std": 0.5929911494255066,
      "rewards/JointRewardFunction/mean": 1.193585205078125,
      "rewards/JointRewardFunction/std": 0.592991155385971,
      "step": 60,
      "step_time": 22.437090325800817
    },
    {
      "clip_ratio/high_max": 0.0,
      "clip_ratio/high_mean": 0.0,
      "clip_ratio/low_mean": 0.0,
      "clip_ratio/low_min": 0.0,
      "clip_ratio/region_mean": 0.0,
      "completions/clipped_ratio": 0.275,
      "completions/max_length": 497.6,
      "completions/max_terminated_length": 455.6,
      "completions/mean_length": 392.0375,
      "completions/mean_terminated_length": 351.8452484130859,
      "completions/min_length": 243.3,
      "completions/min_terminated_length": 243.3,
      "entropy": 0.4913482774049044,
      "epoch": 0.4666666666666667,
      "frac_reward_zero_std": 0.2,
      "grad_norm": 4.21875,
      "kl": 0.11023280541412532,
      "learning_rate": 5.6875e-06,
      "loss": -0.02786441147327423,
      "num_tokens": 282351.0,
      "reward": 1.166510009765625,
      "reward_std": 0.5283917605876922,
      "rewards/JointRewardFunction/mean": 1.166510009765625,
      "rewards/JointRewardFunction/std": 0.528391769528389,
      "step": 70,
      "step_time": 22.72093682029881
    },
    {
      "clip_ratio/high_max": 0.0,
      "clip_ratio/high_mean": 0.0,
      "clip_ratio/low_mean": 0.0,
      "clip_ratio/low_min": 0.0,
      "clip_ratio/region_mean": 0.0,
      "completions/clipped_ratio": 0.3125,
      "completions/max_length": 507.2,
      "completions/max_terminated_length": 447.3,
      "completions/mean_length": 409.9125,
      "completions/mean_terminated_length": 365.60191040039064,
      "completions/min_length": 248.5,
      "completions/min_terminated_length": 248.5,
      "entropy": 0.43941801562905314,
      "epoch": 0.5333333333333333,
      "frac_reward_zero_std": 0.2,
      "grad_norm": 1.640625,
      "kl": 0.12287256089039147,
      "learning_rate": 5.0625e-06,
      "loss": -0.024439637362957,
      "num_tokens": 328816.0,
      "reward": 1.467431640625,
      "reward_std": 0.4256438536103815,
      "rewards/JointRewardFunction/mean": 1.467431640625,
      "rewards/JointRewardFunction/std": 0.42564386553131045,
      "step": 80,
      "step_time": 23.137156244499057
    },
    {
      "clip_ratio/high_max": 0.0,
      "clip_ratio/high_mean": 0.0,
      "clip_ratio/low_mean": 0.0,
      "clip_ratio/low_min": 0.0,
      "clip_ratio/region_mean": 0.0,
      "completions/clipped_ratio": 0.1875,
      "completions/max_length": 486.2,
      "completions/max_terminated_length": 463.3,
      "completions/mean_length": 379.0625,
      "completions/mean_terminated_length": 360.1238128662109,
      "completions/min_length": 241.6,
      "completions/min_terminated_length": 241.6,
      "entropy": 0.3873957570642233,
      "epoch": 0.6,
      "frac_reward_zero_std": 0.35,
      "grad_norm": 2.15625,
      "kl": 0.12395602646283806,
      "learning_rate": 4.4375e-06,
      "loss": 0.0433960497379303,
      "num_tokens": 373289.0,
      "reward": 1.3514892578125,
      "reward_std": 0.43082923418842256,
      "rewards/JointRewardFunction/mean": 1.3514892578125,
      "rewards/JointRewardFunction/std": 0.4308292371686548,
      "step": 90,
      "step_time": 22.175798371599377
    },
    {
      "clip_ratio/high_max": 0.0,
      "clip_ratio/high_mean": 0.0,
      "clip_ratio/low_mean": 0.0,
      "clip_ratio/low_min": 0.0,
      "clip_ratio/region_mean": 0.0,
      "completions/clipped_ratio": 0.1375,
      "completions/max_length": 475.4,
      "completions/max_terminated_length": 439.4,
      "completions/mean_length": 344.5625,
      "completions/mean_terminated_length": 319.0309600830078,
      "completions/min_length": 209.0,
      "completions/min_terminated_length": 209.0,
      "entropy": 0.3818320112302899,
      "epoch": 0.6666666666666666,
      "frac_reward_zero_std": 0.15,
      "grad_norm": 1.7265625,
      "kl": 0.1494429545942694,
      "learning_rate": 3.8125e-06,
      "loss": -0.00486765056848526,
      "num_tokens": 415738.0,
      "reward": 1.4651611328125,
      "reward_std": 0.453005512803793,
      "rewards/JointRewardFunction/mean": 1.4651611328125,
      "rewards/JointRewardFunction/std": 0.45300552546977996,
      "step": 100,
      "step_time": 21.99789129000128
    },
    {
      "clip_ratio/high_max": 0.0,
      "clip_ratio/high_mean": 0.0,
      "clip_ratio/low_mean": 0.0,
      "clip_ratio/low_min": 0.0,
      "clip_ratio/region_mean": 0.0,
      "completions/clipped_ratio": 0.125,
      "completions/max_length": 500.8,
      "completions/max_terminated_length": 454.0,
      "completions/mean_length": 348.225,
      "completions/mean_terminated_length": 326.1460815429688,
      "completions/min_length": 184.0,
      "completions/min_terminated_length": 184.0,
      "entropy": 0.38654828127473595,
      "epoch": 0.7333333333333333,
      "frac_reward_zero_std": 0.25,
      "grad_norm": 4.25,
      "kl": 0.19588984637521206,
      "learning_rate": 3.1875e-06,
      "loss": -0.04184774756431579,
      "num_tokens": 456544.0,
      "reward": 1.449822998046875,
      "reward_std": 0.40167671740055083,
      "rewards/JointRewardFunction/mean": 1.449822998046875,
      "rewards/JointRewardFunction/std": 0.40167671740055083,
      "step": 110,
      "step_time": 22.696052773901464
    },
    {
      "clip_ratio/high_max": 0.0,
      "clip_ratio/high_mean": 0.0,
      "clip_ratio/low_mean": 0.0,
      "clip_ratio/low_min": 0.0,
      "clip_ratio/region_mean": 0.0,
      "completions/clipped_ratio": 0.1875,
      "completions/max_length": 474.8,
      "completions/max_terminated_length": 426.7,
      "completions/mean_length": 338.5375,
      "completions/mean_terminated_length": 308.2898864746094,
      "completions/min_length": 179.5,
      "completions/min_terminated_length": 179.5,
      "entropy": 0.42813673401251434,
      "epoch": 0.8,
      "frac_reward_zero_std": 0.15,
      "grad_norm": 3.625,
      "kl": 0.188834874285385,
      "learning_rate": 2.5625e-06,
      "loss": -0.022572511434555055,
      "num_tokens": 495891.0,
      "reward": 1.37578125,
      "reward_std": 0.485464009642601,
      "rewards/JointRewardFunction/mean": 1.37578125,
      "rewards/JointRewardFunction/std": 0.4854640245437622,
      "step": 120,
      "step_time": 21.932242763400062
    },
    {
      "clip_ratio/high_max": 0.0,
      "clip_ratio/high_mean": 0.0,
      "clip_ratio/low_mean": 0.0,
      "clip_ratio/low_min": 0.0,
      "clip_ratio/region_mean": 0.0,
      "completions/clipped_ratio": 0.225,
      "completions/max_length": 480.4,
      "completions/max_terminated_length": 457.0,
      "completions/mean_length": 353.0375,
      "completions/mean_terminated_length": 309.4391723632813,
      "completions/min_length": 93.9,
      "completions/min_terminated_length": 93.9,
      "entropy": 0.4207899322733283,
      "epoch": 0.8666666666666667,
      "frac_reward_zero_std": 0.15,
      "grad_norm": 3.140625,
      "kl": 0.19314469541423024,
      "learning_rate": 1.9375e-06,
      "loss": -0.10344405174255371,
      "num_tokens": 538386.0,
      "reward": 1.3167236328125,
      "reward_std": 0.5021238774061203,
      "rewards/JointRewardFunction/mean": 1.3167236328125,
      "rewards/JointRewardFunction/std": 0.5021239161491394,
      "step": 130,
      "step_time": 22.154275490202053
    },
    {
      "clip_ratio/high_max": 0.0,
      "clip_ratio/high_mean": 0.0,
      "clip_ratio/low_mean": 0.0,
      "clip_ratio/low_min": 0.0,
      "clip_ratio/region_mean": 0.0,
      "completions/clipped_ratio": 0.1375,
      "completions/max_length": 468.1,
      "completions/max_terminated_length": 443.4,
      "completions/mean_length": 351.3625,
      "completions/mean_terminated_length": 333.25274353027345,
      "completions/min_length": 215.1,
      "completions/min_terminated_length": 215.1,
      "entropy": 0.3897366087883711,
      "epoch": 0.9333333333333333,
      "frac_reward_zero_std": 0.4,
      "grad_norm": 1.8828125,
      "kl": 0.1783840640448034,
      "learning_rate": 1.3125000000000001e-06,
      "loss": -0.012397536635398864,
      "num_tokens": 579127.0,
      "reward": 1.5228759765625,
      "reward_std": 0.3425671649631113,
      "rewards/JointRewardFunction/mean": 1.5228759765625,
      "rewards/JointRewardFunction/std": 0.3425671679433435,
      "step": 140,
      "step_time": 21.521125249801845
    },
    {
      "clip_ratio/high_max": 0.0,
      "clip_ratio/high_mean": 0.0,
      "clip_ratio/low_mean": 0.0,
      "clip_ratio/low_min": 0.0,
      "clip_ratio/region_mean": 0.0,
      "completions/clipped_ratio": 0.15,
      "completions/max_length": 482.1,
      "completions/max_terminated_length": 444.4,
      "completions/mean_length": 354.5375,
      "completions/mean_terminated_length": 328.6072692871094,
      "completions/min_length": 207.4,
      "completions/min_terminated_length": 207.4,
      "entropy": 0.4106031972914934,
      "epoch": 1.0,
      "frac_reward_zero_std": 0.2,
      "grad_norm": 1.703125,
      "kl": 0.16290537370368838,
      "learning_rate": 6.875000000000001e-07,
      "loss": 0.014532069861888885,
      "num_tokens": 619802.0,
      "reward": 1.502001953125,
      "reward_std": 0.44335485696792604,
      "rewards/JointRewardFunction/mean": 1.502001953125,
      "rewards/JointRewardFunction/std": 0.443354868888855,
      "step": 150,
      "step_time": 22.203639667498646
    },
    {
      "clip_ratio/high_max": 0.0,
      "clip_ratio/high_mean": 0.0,
      "clip_ratio/low_mean": 0.0,
      "clip_ratio/low_min": 0.0,
      "clip_ratio/region_mean": 0.0,
      "completions/clipped_ratio": 0.125,
      "completions/max_length": 432.7,
      "completions/max_terminated_length": 389.6,
      "completions/mean_length": 310.0125,
      "completions/mean_terminated_length": 283.19702911376953,
      "completions/min_length": 129.3,
      "completions/min_terminated_length": 129.3,
      "entropy": 0.43815543316304684,
      "epoch": 1.0666666666666667,
      "frac_reward_zero_std": 0.2,
      "grad_norm": 3.484375,
      "kl": 0.21010836036875843,
      "learning_rate": 6.250000000000001e-08,
      "loss": -0.05822192430496216,
      "num_tokens": 656519.0,
      "reward": 1.34354248046875,
      "reward_std": 0.5034710764884949,
      "rewards/JointRewardFunction/mean": 1.34354248046875,
      "rewards/JointRewardFunction/std": 0.503471103310585,
      "step": 160,
      "step_time": 20.17411774720167
    }
  ],
  "logging_steps": 10,
  "max_steps": 160,
  "num_input_tokens_seen": 656519,
  "num_train_epochs": 2,
  "save_steps": 10,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 0.0,
  "train_batch_size": 1,
  "trial_name": null,
  "trial_params": null
}