{
  "best_global_step": null,
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 1.28,
  "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": 0.15,
      "completions/max_length": 920.8,
      "completions/max_terminated_length": 815.0,
      "completions/mean_length": 575.9125,
      "completions/mean_terminated_length": 512.0958465576172,
      "completions/min_length": 250.5,
      "completions/min_terminated_length": 250.5,
      "entropy": 1.1609928414225579,
      "epoch": 0.08,
      "frac_reward_zero_std": 0.225,
      "grad_norm": 4.6875,
      "kl": 0.13114853966326337,
      "learning_rate": 9.4375e-06,
      "loss": 0.012817811965942384,
      "num_tokens": 66717.0,
      "reward": 0.730865478515625,
      "reward_std": 0.7215771168470383,
      "rewards/JointRewardFunction/mean": 0.730865478515625,
      "rewards/JointRewardFunction/std": 0.7215771168470383,
      "step": 10,
      "step_time": 38.070080343699374
    },
    {
      "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": 391.7,
      "completions/max_terminated_length": 391.7,
      "completions/mean_length": 177.925,
      "completions/mean_terminated_length": 177.925,
      "completions/min_length": 49.9,
      "completions/min_terminated_length": 49.9,
      "entropy": 2.0190576702356338,
      "epoch": 0.16,
      "frac_reward_zero_std": 0.1,
      "grad_norm": 17.375,
      "kl": 1.693755827844143,
      "learning_rate": 8.8125e-06,
      "loss": 0.07697797417640687,
      "num_tokens": 101595.0,
      "reward": 0.496136474609375,
      "reward_std": 0.7558781564235687,
      "rewards/JointRewardFunction/mean": 0.496136474609375,
      "rewards/JointRewardFunction/std": 0.7558781564235687,
      "step": 20,
      "step_time": 18.131606991801892
    },
    {
      "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": 0.175,
      "completions/max_length": 988.7,
      "completions/max_terminated_length": 802.5,
      "completions/mean_length": 531.1125,
      "completions/mean_terminated_length": 433.47263793945314,
      "completions/min_length": 180.2,
      "completions/min_terminated_length": 180.2,
      "entropy": 1.3736804876476527,
      "epoch": 0.24,
      "frac_reward_zero_std": 0.225,
      "grad_norm": 4.4375,
      "kl": 0.4292584811337292,
      "learning_rate": 8.1875e-06,
      "loss": 0.12034453153610229,
      "num_tokens": 164528.0,
      "reward": 0.727508544921875,
      "reward_std": 0.5448802873492241,
      "rewards/JointRewardFunction/mean": 0.727508544921875,
      "rewards/JointRewardFunction/std": 0.5448802877217531,
      "step": 30,
      "step_time": 42.41746253830024
    },
    {
      "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": 0.1125,
      "completions/max_length": 926.7,
      "completions/max_terminated_length": 754.3,
      "completions/mean_length": 494.75,
      "completions/mean_terminated_length": 441.88750610351565,
      "completions/min_length": 215.1,
      "completions/min_terminated_length": 215.1,
      "entropy": 1.0656868401914834,
      "epoch": 0.32,
      "frac_reward_zero_std": 0.25,
      "grad_norm": 5.125,
      "kl": 0.3164741122163832,
      "learning_rate": 7.5625e-06,
      "loss": 0.0320564866065979,
      "num_tokens": 224682.0,
      "reward": 0.874420166015625,
      "reward_std": 0.6246562719345092,
      "rewards/JointRewardFunction/mean": 0.874420166015625,
      "rewards/JointRewardFunction/std": 0.6246562749147415,
      "step": 40,
      "step_time": 39.87609361880059
    },
    {
      "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": 629.9,
      "completions/max_terminated_length": 629.9,
      "completions/mean_length": 327.525,
      "completions/mean_terminated_length": 327.525,
      "completions/min_length": 114.7,
      "completions/min_terminated_length": 114.7,
      "entropy": 1.2003333028405905,
      "epoch": 0.4,
      "frac_reward_zero_std": 0.2,
      "grad_norm": 7.5,
      "kl": 0.43942997977137566,
      "learning_rate": 6.9375e-06,
      "loss": 0.022251369059085847,
      "num_tokens": 271714.0,
      "reward": 1.063922119140625,
      "reward_std": 0.6383892238140106,
      "rewards/JointRewardFunction/mean": 1.063922119140625,
      "rewards/JointRewardFunction/std": 0.6383892357349396,
      "step": 50,
      "step_time": 27.557733834501413
    },
    {
      "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": 0.0125,
      "completions/max_length": 641.7,
      "completions/max_terminated_length": 590.3,
      "completions/mean_length": 302.5,
      "completions/mean_terminated_length": 293.0178588867187,
      "completions/min_length": 102.5,
      "completions/min_terminated_length": 102.5,
      "entropy": 1.3896781962364912,
      "epoch": 0.48,
      "frac_reward_zero_std": 0.225,
      "grad_norm": 4.375,
      "kl": 0.5564426928758621,
      "learning_rate": 6.3125e-06,
      "loss": -0.0015912272036075592,
      "num_tokens": 316254.0,
      "reward": 0.9928466796875,
      "reward_std": 0.6274125874042511,
      "rewards/JointRewardFunction/mean": 0.9928466796875,
      "rewards/JointRewardFunction/std": 0.6274125933647156,
      "step": 60,
      "step_time": 28.0631938617993
    },
    {
      "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": 586.9,
      "completions/max_terminated_length": 586.9,
      "completions/mean_length": 294.55,
      "completions/mean_terminated_length": 294.55,
      "completions/min_length": 114.6,
      "completions/min_terminated_length": 114.6,
      "entropy": 1.4918637625873088,
      "epoch": 0.56,
      "frac_reward_zero_std": 0.25,
      "grad_norm": 5.15625,
      "kl": 0.5497013371437788,
      "learning_rate": 5.6875e-06,
      "loss": 0.047078275680541994,
      "num_tokens": 360274.0,
      "reward": 1.1190673828125,
      "reward_std": 0.609263214468956,
      "rewards/JointRewardFunction/mean": 1.1190673828125,
      "rewards/JointRewardFunction/std": 0.609263226389885,
      "step": 70,
      "step_time": 26.138083929998174
    },
    {
      "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": 847.5,
      "completions/max_terminated_length": 678.8,
      "completions/mean_length": 365.3375,
      "completions/mean_terminated_length": 321.4898880004883,
      "completions/min_length": 90.4,
      "completions/min_terminated_length": 90.4,
      "entropy": 1.5532763354480266,
      "epoch": 0.64,
      "frac_reward_zero_std": 0.175,
      "grad_norm": 5.78125,
      "kl": 0.4981705164536834,
      "learning_rate": 5.0625e-06,
      "loss": 0.11404727697372437,
      "num_tokens": 410115.0,
      "reward": 0.9597900390625,
      "reward_std": 0.6095708787441254,
      "rewards/JointRewardFunction/mean": 0.9597900390625,
      "rewards/JointRewardFunction/std": 0.6095708817243576,
      "step": 80,
      "step_time": 36.49904953569931
    },
    {
      "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": 0.025,
      "completions/max_length": 732.5,
      "completions/max_terminated_length": 677.8,
      "completions/mean_length": 299.875,
      "completions/mean_terminated_length": 282.1875030517578,
      "completions/min_length": 96.0,
      "completions/min_terminated_length": 96.0,
      "entropy": 1.4728075489401817,
      "epoch": 0.72,
      "frac_reward_zero_std": 0.225,
      "grad_norm": 3.5625,
      "kl": 0.4925263602286577,
      "learning_rate": 4.4375e-06,
      "loss": 0.054662787914276124,
      "num_tokens": 454725.0,
      "reward": 1.019183349609375,
      "reward_std": 0.61219422519207,
      "rewards/JointRewardFunction/mean": 1.019183349609375,
      "rewards/JointRewardFunction/std": 0.6121942341327667,
      "step": 90,
      "step_time": 31.705154634100108
    },
    {
      "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": 760.6,
      "completions/max_terminated_length": 660.6,
      "completions/mean_length": 352.475,
      "completions/mean_terminated_length": 312.0821502685547,
      "completions/min_length": 105.0,
      "completions/min_terminated_length": 105.0,
      "entropy": 1.3954405788332225,
      "epoch": 0.8,
      "frac_reward_zero_std": 0.125,
      "grad_norm": 5.78125,
      "kl": 0.4322750365361571,
      "learning_rate": 3.8125e-06,
      "loss": 0.009273938834667206,
      "num_tokens": 503589.0,
      "reward": 0.9172119140625,
      "reward_std": 0.6775627821683884,
      "rewards/JointRewardFunction/mean": 0.9172119140625,
      "rewards/JointRewardFunction/std": 0.6775627851486206,
      "step": 100,
      "step_time": 33.002576629400934
    },
    {
      "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": 0.0125,
      "completions/max_length": 687.7,
      "completions/max_terminated_length": 653.3,
      "completions/mean_length": 315.025,
      "completions/mean_terminated_length": 306.5357147216797,
      "completions/min_length": 97.6,
      "completions/min_terminated_length": 97.6,
      "entropy": 1.4698836095631123,
      "epoch": 0.88,
      "frac_reward_zero_std": 0.275,
      "grad_norm": 8.125,
      "kl": 0.4709475075826049,
      "learning_rate": 3.1875e-06,
      "loss": 0.09247303009033203,
      "num_tokens": 549335.0,
      "reward": 0.997833251953125,
      "reward_std": 0.6001621454954147,
      "rewards/JointRewardFunction/mean": 0.997833251953125,
      "rewards/JointRewardFunction/std": 0.6001621544361114,
      "step": 110,
      "step_time": 30.22435642040182
    },
    {
      "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": 0.05,
      "completions/max_length": 865.7,
      "completions/max_terminated_length": 724.8,
      "completions/mean_length": 377.4125,
      "completions/mean_terminated_length": 342.6226211547852,
      "completions/min_length": 102.6,
      "completions/min_terminated_length": 102.6,
      "entropy": 1.4377100937068463,
      "epoch": 0.96,
      "frac_reward_zero_std": 0.225,
      "grad_norm": 3.15625,
      "kl": 0.4150696059688926,
      "learning_rate": 2.5625e-06,
      "loss": -0.021556401252746583,
      "num_tokens": 599900.0,
      "reward": 1.0236083984375,
      "reward_std": 0.6392961710691452,
      "rewards/JointRewardFunction/mean": 1.0236083984375,
      "rewards/JointRewardFunction/std": 0.6392962068319321,
      "step": 120,
      "step_time": 37.14680036250138
    },
    {
      "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": 0.05,
      "completions/max_length": 698.9,
      "completions/max_terminated_length": 598.9,
      "completions/mean_length": 299.0125,
      "completions/mean_terminated_length": 260.36726531982424,
      "completions/min_length": 72.3,
      "completions/min_terminated_length": 72.3,
      "entropy": 1.3930659301578998,
      "epoch": 1.04,
      "frac_reward_zero_std": 0.2,
      "grad_norm": 5.71875,
      "kl": 0.48926177779212593,
      "learning_rate": 1.9375e-06,
      "loss": 0.016721364855766297,
      "num_tokens": 644439.0,
      "reward": 0.972833251953125,
      "reward_std": 0.6092687845230103,
      "rewards/JointRewardFunction/mean": 0.972833251953125,
      "rewards/JointRewardFunction/std": 0.6092687904834747,
      "step": 130,
      "step_time": 30.47871646400163
    },
    {
      "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": 623.9,
      "completions/max_terminated_length": 623.9,
      "completions/mean_length": 286.925,
      "completions/mean_terminated_length": 286.925,
      "completions/min_length": 71.1,
      "completions/min_terminated_length": 71.1,
      "entropy": 1.4094880308955908,
      "epoch": 1.12,
      "frac_reward_zero_std": 0.35,
      "grad_norm": 10.8125,
      "kl": 0.4836927611380816,
      "learning_rate": 1.3125000000000001e-06,
      "loss": 0.08277995586395263,
      "num_tokens": 688041.0,
      "reward": 1.046673583984375,
      "reward_std": 0.5450149297714233,
      "rewards/JointRewardFunction/mean": 1.046673583984375,
      "rewards/JointRewardFunction/std": 0.5450149476528168,
      "step": 140,
      "step_time": 27.556023125701177
    },
    {
      "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": 0.05,
      "completions/max_length": 781.7,
      "completions/max_terminated_length": 652.2,
      "completions/mean_length": 349.275,
      "completions/mean_terminated_length": 317.290478515625,
      "completions/min_length": 88.2,
      "completions/min_terminated_length": 88.2,
      "entropy": 1.334358724579215,
      "epoch": 1.2,
      "frac_reward_zero_std": 0.15,
      "grad_norm": 5.9375,
      "kl": 0.44102346180006863,
      "learning_rate": 6.875000000000001e-07,
      "loss": 0.12827397584915162,
      "num_tokens": 736559.0,
      "reward": 0.999505615234375,
      "reward_std": 0.6881234139204025,
      "rewards/JointRewardFunction/mean": 0.999505615234375,
      "rewards/JointRewardFunction/std": 0.6881234139204025,
      "step": 150,
      "step_time": 33.79141057000161
    },
    {
      "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": 0.05,
      "completions/max_length": 678.4,
      "completions/max_terminated_length": 558.1,
      "completions/mean_length": 299.375,
      "completions/mean_terminated_length": 261.2517883300781,
      "completions/min_length": 71.7,
      "completions/min_terminated_length": 71.7,
      "entropy": 1.3799165710806847,
      "epoch": 1.28,
      "frac_reward_zero_std": 0.175,
      "grad_norm": 7.21875,
      "kl": 0.4770205244421959,
      "learning_rate": 6.250000000000001e-08,
      "loss": 0.08484221696853637,
      "num_tokens": 781411.0,
      "reward": 0.87017822265625,
      "reward_std": 0.6314140051603317,
      "rewards/JointRewardFunction/mean": 0.87017822265625,
      "rewards/JointRewardFunction/std": 0.6314140141010285,
      "step": 160,
      "step_time": 30.14368499219854
    }
  ],
  "logging_steps": 10,
  "max_steps": 160,
  "num_input_tokens_seen": 781411,
  "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
}