{
  "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": 0.1125,
      "completions/max_length": 461.2,
      "completions/max_terminated_length": 447.5,
      "completions/mean_length": 376.325,
      "completions/mean_terminated_length": 362.7201232910156,
      "completions/min_length": 279.3,
      "completions/min_terminated_length": 279.3,
      "entropy": 0.2633976127021015,
      "epoch": 0.06666666666666667,
      "frac_reward_zero_std": 0.15,
      "grad_norm": 2.515625,
      "kl": 0.06368143780127866,
      "learning_rate": 9.4375e-06,
      "loss": 0.013505807518959046,
      "num_tokens": 42974.0,
      "reward": 0.83304443359375,
      "reward_std": 0.4131676867604256,
      "rewards/JointRewardFunction/mean": 0.83304443359375,
      "rewards/JointRewardFunction/std": 0.4131676971912384,
      "step": 10,
      "step_time": 20.514270653799578
    },
    {
      "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": 409.6,
      "completions/max_terminated_length": 384.0,
      "completions/mean_length": 317.925,
      "completions/mean_terminated_length": 308.6857147216797,
      "completions/min_length": 249.7,
      "completions/min_terminated_length": 249.7,
      "entropy": 0.18158590691164136,
      "epoch": 0.13333333333333333,
      "frac_reward_zero_std": 0.25,
      "grad_norm": 3.421875,
      "kl": 0.1635891743004322,
      "learning_rate": 8.8125e-06,
      "loss": 0.009117365628480912,
      "num_tokens": 82168.0,
      "reward": 1.0664794921875,
      "reward_std": 0.29466880708932874,
      "rewards/JointRewardFunction/mean": 1.0664794921875,
      "rewards/JointRewardFunction/std": 0.29466880932450296,
      "step": 20,
      "step_time": 19.10480176490073
    },
    {
      "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": 406.0,
      "completions/max_terminated_length": 389.9,
      "completions/mean_length": 295.1375,
      "completions/mean_terminated_length": 285.5047637939453,
      "completions/min_length": 206.6,
      "completions/min_terminated_length": 206.6,
      "entropy": 0.21663210522383453,
      "epoch": 0.2,
      "frac_reward_zero_std": 0.25,
      "grad_norm": 2.5625,
      "kl": 0.18388604540377856,
      "learning_rate": 8.1875e-06,
      "loss": -0.01458892971277237,
      "num_tokens": 117195.0,
      "reward": 1.017388916015625,
      "reward_std": 0.4210638031363487,
      "rewards/JointRewardFunction/mean": 1.017388916015625,
      "rewards/JointRewardFunction/std": 0.4210638180375099,
      "step": 30,
      "step_time": 19.004520852699535
    },
    {
      "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": 453.9,
      "completions/max_terminated_length": 431.6,
      "completions/mean_length": 362.6625,
      "completions/mean_terminated_length": 344.75762634277345,
      "completions/min_length": 264.3,
      "completions/min_terminated_length": 264.3,
      "entropy": 0.2015760915353894,
      "epoch": 0.26666666666666666,
      "frac_reward_zero_std": 0.15,
      "grad_norm": 2.484375,
      "kl": 0.17142300652340053,
      "learning_rate": 7.5625e-06,
      "loss": 0.021102146804332735,
      "num_tokens": 159520.0,
      "reward": 1.040948486328125,
      "reward_std": 0.31338895484805107,
      "rewards/JointRewardFunction/mean": 1.040948486328125,
      "rewards/JointRewardFunction/std": 0.31338896676898004,
      "step": 40,
      "step_time": 20.873488509700472
    },
    {
      "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": 410.2,
      "completions/max_terminated_length": 389.0,
      "completions/mean_length": 307.825,
      "completions/mean_terminated_length": 303.1875030517578,
      "completions/min_length": 237.3,
      "completions/min_terminated_length": 237.3,
      "entropy": 0.22014566687867046,
      "epoch": 0.3333333333333333,
      "frac_reward_zero_std": 0.35,
      "grad_norm": 0.014892578125,
      "kl": 0.22832224890589714,
      "learning_rate": 6.9375e-06,
      "loss": 0.039792636036872865,
      "num_tokens": 196862.0,
      "reward": 1.0728515625,
      "reward_std": 0.32390306144952774,
      "rewards/JointRewardFunction/mean": 1.0728515625,
      "rewards/JointRewardFunction/std": 0.3239030599594116,
      "step": 50,
      "step_time": 19.236986151600284
    },
    {
      "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": 397.9,
      "completions/max_terminated_length": 383.6,
      "completions/mean_length": 315.625,
      "completions/mean_terminated_length": 310.5375,
      "completions/min_length": 221.9,
      "completions/min_terminated_length": 221.9,
      "entropy": 0.19608328267931938,
      "epoch": 0.4,
      "frac_reward_zero_std": 0.35,
      "grad_norm": 1.8203125,
      "kl": 0.2169005206786096,
      "learning_rate": 6.3125e-06,
      "loss": 0.017893573641777037,
      "num_tokens": 235512.0,
      "reward": 1.103521728515625,
      "reward_std": 0.26875718161463735,
      "rewards/JointRewardFunction/mean": 1.103521728515625,
      "rewards/JointRewardFunction/std": 0.26875719204545023,
      "step": 60,
      "step_time": 18.723443715600297
    },
    {
      "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": 0.075,
      "completions/max_length": 438.1,
      "completions/max_terminated_length": 423.8,
      "completions/mean_length": 340.4875,
      "completions/mean_terminated_length": 326.67738342285156,
      "completions/min_length": 246.7,
      "completions/min_terminated_length": 246.7,
      "entropy": 0.17470104116946458,
      "epoch": 0.4666666666666667,
      "frac_reward_zero_std": 0.45,
      "grad_norm": 1.90625,
      "kl": 0.17606046590954066,
      "learning_rate": 5.6875e-06,
      "loss": 0.012082196772098541,
      "num_tokens": 276547.0,
      "reward": 1.0309814453125,
      "reward_std": 0.3187349811196327,
      "rewards/JointRewardFunction/mean": 1.0309814453125,
      "rewards/JointRewardFunction/std": 0.31873499751091006,
      "step": 70,
      "step_time": 20.5276982866013
    },
    {
      "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": 441.0,
      "completions/max_terminated_length": 439.9,
      "completions/mean_length": 336.4,
      "completions/mean_terminated_length": 334.3732147216797,
      "completions/min_length": 238.0,
      "completions/min_terminated_length": 238.0,
      "entropy": 0.18340560160577296,
      "epoch": 0.5333333333333333,
      "frac_reward_zero_std": 0.7,
      "grad_norm": 0.04248046875,
      "kl": 0.1858743063174188,
      "learning_rate": 5.0625e-06,
      "loss": -0.010596746206283569,
      "num_tokens": 317131.0,
      "reward": 1.1973876953125,
      "reward_std": 0.14741100370883942,
      "rewards/JointRewardFunction/mean": 1.1973876953125,
      "rewards/JointRewardFunction/std": 0.1474110044538975,
      "step": 80,
      "step_time": 20.424764195699574
    },
    {
      "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": 422.6,
      "completions/max_terminated_length": 411.2,
      "completions/mean_length": 319.8375,
      "completions/mean_terminated_length": 309.8089294433594,
      "completions/min_length": 222.4,
      "completions/min_terminated_length": 222.4,
      "entropy": 0.17013722923584282,
      "epoch": 0.6,
      "frac_reward_zero_std": 0.45,
      "grad_norm": 1.75,
      "kl": 0.22596123907715082,
      "learning_rate": 4.4375e-06,
      "loss": 0.0059959739446640015,
      "num_tokens": 356866.0,
      "reward": 1.0788330078125,
      "reward_std": 0.2970864400267601,
      "rewards/JointRewardFunction/mean": 1.0788330078125,
      "rewards/JointRewardFunction/std": 0.29708646088838575,
      "step": 90,
      "step_time": 19.734197501099334
    },
    {
      "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": 397.6,
      "completions/max_terminated_length": 372.7,
      "completions/mean_length": 300.6,
      "completions/mean_terminated_length": 287.1,
      "completions/min_length": 220.5,
      "completions/min_terminated_length": 220.5,
      "entropy": 0.18155792271718382,
      "epoch": 0.6666666666666666,
      "frac_reward_zero_std": 0.95,
      "grad_norm": 0.0279541015625,
      "kl": 0.23375053312629462,
      "learning_rate": 3.8125e-06,
      "loss": 8.478660020045936e-05,
      "num_tokens": 395798.0,
      "reward": 1.1875,
      "reward_std": 0.08880758583545685,
      "rewards/JointRewardFunction/mean": 1.1875,
      "rewards/JointRewardFunction/std": 0.08880758583545685,
      "step": 100,
      "step_time": 18.690151827099545
    },
    {
      "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": 459.3,
      "completions/max_terminated_length": 430.1,
      "completions/mean_length": 335.3875,
      "completions/mean_terminated_length": 328.3857177734375,
      "completions/min_length": 243.9,
      "completions/min_terminated_length": 243.9,
      "entropy": 0.1711413566954434,
      "epoch": 0.7333333333333333,
      "frac_reward_zero_std": 0.65,
      "grad_norm": 1.4140625,
      "kl": 0.18389353882521392,
      "learning_rate": 3.1875e-06,
      "loss": 0.0026162829250097274,
      "num_tokens": 435577.0,
      "reward": 1.116802978515625,
      "reward_std": 0.22371026836335658,
      "rewards/JointRewardFunction/mean": 1.116802978515625,
      "rewards/JointRewardFunction/std": 0.2237102746963501,
      "step": 110,
      "step_time": 21.052574327701223
    },
    {
      "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": 380.6,
      "completions/max_terminated_length": 371.3,
      "completions/mean_length": 303.3,
      "completions/mean_terminated_length": 292.425,
      "completions/min_length": 222.7,
      "completions/min_terminated_length": 222.7,
      "entropy": 0.19935499429702758,
      "epoch": 0.8,
      "frac_reward_zero_std": 0.55,
      "grad_norm": 1.59375,
      "kl": 0.19222176214680076,
      "learning_rate": 2.5625e-06,
      "loss": 0.01612665057182312,
      "num_tokens": 472105.0,
      "reward": 1.0654541015625,
      "reward_std": 0.28345242142677307,
      "rewards/JointRewardFunction/mean": 1.0654541015625,
      "rewards/JointRewardFunction/std": 0.28345243632793427,
      "step": 120,
      "step_time": 18.070694422099404
    },
    {
      "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": 451.0,
      "completions/max_terminated_length": 385.2,
      "completions/mean_length": 331.925,
      "completions/mean_terminated_length": 312.57203063964846,
      "completions/min_length": 237.9,
      "completions/min_terminated_length": 237.9,
      "entropy": 0.1600348782725632,
      "epoch": 0.8666666666666667,
      "frac_reward_zero_std": 0.45,
      "grad_norm": 2.390625,
      "kl": 0.18412442253902556,
      "learning_rate": 1.9375e-06,
      "loss": 0.01880526840686798,
      "num_tokens": 512911.0,
      "reward": 1.0941162109375,
      "reward_std": 0.313115157186985,
      "rewards/JointRewardFunction/mean": 1.0941162109375,
      "rewards/JointRewardFunction/std": 0.31311516016721724,
      "step": 130,
      "step_time": 20.829227783899295
    },
    {
      "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": 361.2,
      "completions/max_terminated_length": 361.2,
      "completions/mean_length": 285.1,
      "completions/mean_terminated_length": 285.1,
      "completions/min_length": 226.3,
      "completions/min_terminated_length": 226.3,
      "entropy": 0.18776001809164883,
      "epoch": 0.9333333333333333,
      "frac_reward_zero_std": 0.75,
      "grad_norm": 0.038818359375,
      "kl": 0.2174981951713562,
      "learning_rate": 1.3125000000000001e-06,
      "loss": 0.00478580966591835,
      "num_tokens": 548351.0,
      "reward": 1.18388671875,
      "reward_std": 0.18575088679790497,
      "rewards/JointRewardFunction/mean": 1.18388671875,
      "rewards/JointRewardFunction/std": 0.1857508897781372,
      "step": 140,
      "step_time": 17.17216874960086
    },
    {
      "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": 431.1,
      "completions/max_terminated_length": 389.6,
      "completions/mean_length": 295.625,
      "completions/mean_terminated_length": 285.92440643310545,
      "completions/min_length": 217.1,
      "completions/min_terminated_length": 217.1,
      "entropy": 0.19556321045383812,
      "epoch": 1.0,
      "frac_reward_zero_std": 0.6,
      "grad_norm": 1.984375,
      "kl": 0.22088080924004316,
      "learning_rate": 6.875000000000001e-07,
      "loss": 0.03738939166069031,
      "num_tokens": 584313.0,
      "reward": 1.14267578125,
      "reward_std": 0.25464810580015185,
      "rewards/JointRewardFunction/mean": 1.14267578125,
      "rewards/JointRewardFunction/std": 0.2546481089666486,
      "step": 150,
      "step_time": 20.206593494599836
    },
    {
      "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": 372.0,
      "completions/max_terminated_length": 365.0,
      "completions/mean_length": 278.375,
      "completions/mean_terminated_length": 276.0125,
      "completions/min_length": 212.7,
      "completions/min_terminated_length": 212.7,
      "entropy": 0.19452018961310386,
      "epoch": 1.0666666666666667,
      "frac_reward_zero_std": 0.55,
      "grad_norm": 2.03125,
      "kl": 0.2295491287484765,
      "learning_rate": 6.250000000000001e-08,
      "loss": -0.003883980959653854,
      "num_tokens": 618499.0,
      "reward": 1.161102294921875,
      "reward_std": 0.1998678043484688,
      "rewards/JointRewardFunction/mean": 1.161102294921875,
      "rewards/JointRewardFunction/std": 0.19986780881881713,
      "step": 160,
      "step_time": 17.52442454840075
    }
  ],
  "logging_steps": 10,
  "max_steps": 160,
  "num_input_tokens_seen": 618499,
  "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
}