{
  "best_global_step": null,
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 2.0,
  "eval_steps": 500,
  "global_step": 300,
  "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": 0.5875,
      "completions/max_length": 512.0,
      "completions/max_terminated_length": 440.4,
      "completions/mean_length": 468.6125,
      "completions/mean_terminated_length": 379.02000122070314,
      "completions/min_length": 369.0,
      "completions/min_terminated_length": 317.8,
      "entropy": 0.2740801006555557,
      "epoch": 0.06666666666666667,
      "frac_reward_zero_std": 0.15,
      "grad_norm": 1.3671875,
      "kl": 0.04017456619621953,
      "learning_rate": 9.7e-06,
      "loss": -0.004630821943283081,
      "num_tokens": 50357.0,
      "reward": 0.803729248046875,
      "reward_std": 0.41876387000083926,
      "rewards/JointRewardFunction/mean": 0.803729248046875,
      "rewards/JointRewardFunction/std": 0.41876387894153594,
      "step": 10,
      "step_time": 23.422285906800244
    },
    {
      "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": 0.75,
      "completions/max_length": 512.0,
      "completions/max_terminated_length": 328.2,
      "completions/mean_length": 493.75,
      "completions/mean_terminated_length": 310.2800018310547,
      "completions/min_length": 446.2,
      "completions/min_terminated_length": 292.6,
      "entropy": 0.1757997965440154,
      "epoch": 0.13333333333333333,
      "frac_reward_zero_std": 0.65,
      "grad_norm": 0.1865234375,
      "kl": 0.064147645724006,
      "learning_rate": 9.366666666666668e-06,
      "loss": -0.00039904499426484107,
      "num_tokens": 103617.0,
      "reward": 0.85,
      "reward_std": 0.3472102493047714,
      "rewards/JointRewardFunction/mean": 0.85,
      "rewards/JointRewardFunction/std": 0.3472102552652359,
      "step": 20,
      "step_time": 23.712279441399733
    },
    {
      "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": 0.6625,
      "completions/max_length": 512.0,
      "completions/max_terminated_length": 376.5,
      "completions/mean_length": 476.5875,
      "completions/mean_terminated_length": 333.94667358398436,
      "completions/min_length": 374.9,
      "completions/min_terminated_length": 272.5,
      "entropy": 0.21253416435793043,
      "epoch": 0.2,
      "frac_reward_zero_std": 0.3,
      "grad_norm": 2.28125,
      "kl": 0.07378085452364758,
      "learning_rate": 9.033333333333334e-06,
      "loss": -0.012095230817794799,
      "num_tokens": 153160.0,
      "reward": 0.95,
      "reward_std": 0.43348987102508546,
      "rewards/JointRewardFunction/mean": 0.95,
      "rewards/JointRewardFunction/std": 0.43348987102508546,
      "step": 30,
      "step_time": 23.327648415401928
    },
    {
      "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": 0.85,
      "completions/max_length": 512.0,
      "completions/max_terminated_length": 284.1,
      "completions/mean_length": 503.7625,
      "completions/mean_terminated_length": 278.8300018310547,
      "completions/min_length": 477.8,
      "completions/min_terminated_length": 273.0,
      "entropy": 0.21520083369687198,
      "epoch": 0.26666666666666666,
      "frac_reward_zero_std": 0.35,
      "grad_norm": 0.255859375,
      "kl": 0.06080276914872229,
      "learning_rate": 8.700000000000001e-06,
      "loss": -0.0005816968623548746,
      "num_tokens": 206773.0,
      "reward": 0.7875,
      "reward_std": 0.4616557478904724,
      "rewards/JointRewardFunction/mean": 0.7875,
      "rewards/JointRewardFunction/std": 0.46165576577186584,
      "step": 40,
      "step_time": 23.59478929130273
    },
    {
      "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": 0.7625,
      "completions/max_length": 512.0,
      "completions/max_terminated_length": 325.7,
      "completions/mean_length": 490.0375,
      "completions/mean_terminated_length": 299.44667053222656,
      "completions/min_length": 433.4,
      "completions/min_terminated_length": 279.8,
      "entropy": 0.25695387944579123,
      "epoch": 0.3333333333333333,
      "frac_reward_zero_std": 0.45,
      "grad_norm": 1.6953125,
      "kl": 0.08556670525576919,
      "learning_rate": 8.366666666666667e-06,
      "loss": -0.004827765375375747,
      "num_tokens": 258692.0,
      "reward": 0.9375,
      "reward_std": 0.3981345325708389,
      "rewards/JointRewardFunction/mean": 0.9375,
      "rewards/JointRewardFunction/std": 0.3981345325708389,
      "step": 50,
      "step_time": 23.633761547702306
    },
    {
      "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": 0.75,
      "completions/max_length": 512.0,
      "completions/max_terminated_length": 332.6,
      "completions/mean_length": 492.95,
      "completions/mean_terminated_length": 307.1166687011719,
      "completions/min_length": 437.8,
      "completions/min_terminated_length": 284.2,
      "entropy": 0.2603289651684463,
      "epoch": 0.4,
      "frac_reward_zero_std": 0.55,
      "grad_norm": 1.671875,
      "kl": 0.060612542228773235,
      "learning_rate": 8.033333333333335e-06,
      "loss": 0.0008684337139129638,
      "num_tokens": 311528.0,
      "reward": 0.925,
      "reward_std": 0.2958350956439972,
      "rewards/JointRewardFunction/mean": 0.925,
      "rewards/JointRewardFunction/std": 0.29583510756492615,
      "step": 60,
      "step_time": 23.58587597120204
    },
    {
      "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": 0.725,
      "completions/max_length": 512.0,
      "completions/max_terminated_length": 339.0,
      "completions/mean_length": 492.8125,
      "completions/mean_terminated_length": 313.85,
      "completions/min_length": 433.5,
      "completions/min_terminated_length": 279.9,
      "entropy": 0.27547385785728695,
      "epoch": 0.4666666666666667,
      "frac_reward_zero_std": 0.6,
      "grad_norm": 0.99609375,
      "kl": 0.0518098235828802,
      "learning_rate": 7.7e-06,
      "loss": -0.0017207100987434386,
      "num_tokens": 364749.0,
      "reward": 0.9125,
      "reward_std": 0.3383516758680344,
      "rewards/JointRewardFunction/mean": 0.9125,
      "rewards/JointRewardFunction/std": 0.3383516877889633,
      "step": 70,
      "step_time": 23.567738218297016
    },
    {
      "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": 0.7375,
      "completions/max_length": 512.0,
      "completions/max_terminated_length": 449.5,
      "completions/mean_length": 487.675,
      "completions/mean_terminated_length": 422.1333343505859,
      "completions/min_length": 393.1,
      "completions/min_terminated_length": 393.1,
      "entropy": 0.2849867718294263,
      "epoch": 0.5333333333333333,
      "frac_reward_zero_std": 0.4,
      "grad_norm": 0.042724609375,
      "kl": 0.054288532945793125,
      "learning_rate": 7.3666666666666676e-06,
      "loss": 0.01214314103126526,
      "num_tokens": 417435.0,
      "reward": 0.9625,
      "reward_std": 0.44988160133361815,
      "rewards/JointRewardFunction/mean": 0.9625,
      "rewards/JointRewardFunction/std": 0.4498816192150116,
      "step": 80,
      "step_time": 23.797617995494512
    },
    {
      "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": 0.7125,
      "completions/max_length": 512.0,
      "completions/max_terminated_length": 330.2,
      "completions/mean_length": 487.5125,
      "completions/mean_terminated_length": 302.90834045410156,
      "completions/min_length": 421.4,
      "completions/min_terminated_length": 267.8,
      "entropy": 0.2951860463246703,
      "epoch": 0.6,
      "frac_reward_zero_std": 0.45,
      "grad_norm": 1.265625,
      "kl": 0.04278905827086419,
      "learning_rate": 7.033333333333334e-06,
      "loss": -0.0006712859496474266,
      "num_tokens": 470584.0,
      "reward": 0.9375,
      "reward_std": 0.31479085683822633,
      "rewards/JointRewardFunction/mean": 0.9375,
      "rewards/JointRewardFunction/std": 0.3147908627986908,
      "step": 90,
      "step_time": 23.514957720592793
    },
    {
      "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": 0.625,
      "completions/max_length": 512.0,
      "completions/max_terminated_length": 459.9,
      "completions/mean_length": 472.3125,
      "completions/mean_terminated_length": 418.8316680908203,
      "completions/min_length": 365.9,
      "completions/min_terminated_length": 365.9,
      "entropy": 0.37076061628758905,
      "epoch": 0.6666666666666666,
      "frac_reward_zero_std": 0.4,
      "grad_norm": 2.15625,
      "kl": 0.05282424986362457,
      "learning_rate": 6.700000000000001e-06,
      "loss": -0.009071560204029083,
      "num_tokens": 523253.0,
      "reward": 0.9815673828125,
      "reward_std": 0.4160596996545792,
      "rewards/JointRewardFunction/mean": 0.9815673828125,
      "rewards/JointRewardFunction/std": 0.41605971157550814,
      "step": 100,
      "step_time": 23.664498128004197
    },
    {
      "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": 0.6125,
      "completions/max_length": 509.7,
      "completions/max_terminated_length": 484.8,
      "completions/mean_length": 475.7,
      "completions/mean_terminated_length": 437.1983367919922,
      "completions/min_length": 383.8,
      "completions/min_terminated_length": 383.8,
      "entropy": 0.4262677112594247,
      "epoch": 0.7333333333333333,
      "frac_reward_zero_std": 0.4,
      "grad_norm": 2.0625,
      "kl": 0.03714689936023206,
      "learning_rate": 6.366666666666668e-06,
      "loss": 0.008247312903404237,
      "num_tokens": 574257.0,
      "reward": 1.037060546875,
      "reward_std": 0.3255626171827316,
      "rewards/JointRewardFunction/mean": 1.037060546875,
      "rewards/JointRewardFunction/std": 0.3255626350641251,
      "step": 110,
      "step_time": 23.18678354880103
    },
    {
      "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": 0.575,
      "completions/max_length": 512.0,
      "completions/max_terminated_length": 388.5,
      "completions/mean_length": 472.7625,
      "completions/mean_terminated_length": 342.3550079345703,
      "completions/min_length": 396.3,
      "completions/min_terminated_length": 293.9,
      "entropy": 0.4861995566636324,
      "epoch": 0.8,
      "frac_reward_zero_std": 0.35,
      "grad_norm": 1.40625,
      "kl": 0.039038634288590404,
      "learning_rate": 6.033333333333335e-06,
      "loss": 0.012050890922546386,
      "num_tokens": 624342.0,
      "reward": 0.925,
      "reward_std": 0.4410230278968811,
      "rewards/JointRewardFunction/mean": 0.925,
      "rewards/JointRewardFunction/std": 0.441023051738739,
      "step": 120,
      "step_time": 23.72601753709896
    },
    {
      "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": 0.5375,
      "completions/max_length": 511.6,
      "completions/max_terminated_length": 476.8,
      "completions/mean_length": 470.0375,
      "completions/mean_terminated_length": 427.0658416748047,
      "completions/min_length": 372.0,
      "completions/min_terminated_length": 372.0,
      "entropy": 0.41965660247951747,
      "epoch": 0.8666666666666667,
      "frac_reward_zero_std": 0.55,
      "grad_norm": 1.4453125,
      "kl": 0.03558391091646627,
      "learning_rate": 5.7e-06,
      "loss": 0.0031338028609752657,
      "num_tokens": 676197.0,
      "reward": 1.029736328125,
      "reward_std": 0.3752464294433594,
      "rewards/JointRewardFunction/mean": 1.029736328125,
      "rewards/JointRewardFunction/std": 0.37524643540382385,
      "step": 130,
      "step_time": 23.592583017596915
    },
    {
      "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": 0.5,
      "completions/max_length": 512.0,
      "completions/max_terminated_length": 470.4,
      "completions/mean_length": 468.3375,
      "completions/mean_terminated_length": 422.97833862304685,
      "completions/min_length": 369.0,
      "completions/min_terminated_length": 369.0,
      "entropy": 0.4238532094284892,
      "epoch": 0.9333333333333333,
      "frac_reward_zero_std": 0.4,
      "grad_norm": 0.048095703125,
      "kl": 0.047195866727270185,
      "learning_rate": 5.366666666666666e-06,
      "loss": 0.011741240322589875,
      "num_tokens": 726296.0,
      "reward": 1.0271484375,
      "reward_std": 0.39577038288116456,
      "rewards/JointRewardFunction/mean": 1.0271484375,
      "rewards/JointRewardFunction/std": 0.39577039480209353,
      "step": 140,
      "step_time": 23.827525900093313
    },
    {
      "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": 0.475,
      "completions/max_length": 507.6,
      "completions/max_terminated_length": 417.3,
      "completions/mean_length": 452.0375,
      "completions/mean_terminated_length": 360.2283416748047,
      "completions/min_length": 351.9,
      "completions/min_terminated_length": 300.7,
      "entropy": 0.405802302993834,
      "epoch": 1.0,
      "frac_reward_zero_std": 0.5,
      "grad_norm": 1.3125,
      "kl": 0.05754059529863298,
      "learning_rate": 5.033333333333333e-06,
      "loss": 0.020150861144065856,
      "num_tokens": 774771.0,
      "reward": 1.0125,
      "reward_std": 0.37200968265533446,
      "rewards/JointRewardFunction/mean": 1.0125,
      "rewards/JointRewardFunction/std": 0.3720097005367279,
      "step": 150,
      "step_time": 23.477148605001275
    },
    {
      "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": 0.35,
      "completions/max_length": 504.7,
      "completions/max_terminated_length": 460.6,
      "completions/mean_length": 418.725,
      "completions/mean_terminated_length": 376.1097686767578,
      "completions/min_length": 290.2,
      "completions/min_terminated_length": 290.2,
      "entropy": 0.4137630261480808,
      "epoch": 1.0666666666666667,
      "frac_reward_zero_std": 0.55,
      "grad_norm": 1.5234375,
      "kl": 0.04866745978360996,
      "learning_rate": 4.7e-06,
      "loss": -0.012348555028438568,
      "num_tokens": 820185.0,
      "reward": 1.1374755859375,
      "reward_std": 0.2693489044904709,
      "rewards/JointRewardFunction/mean": 1.1374755859375,
      "rewards/JointRewardFunction/std": 0.2693489044904709,
      "step": 160,
      "step_time": 23.104779590805993
    },
    {
      "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": 0.45,
      "completions/max_length": 512.0,
      "completions/max_terminated_length": 459.3,
      "completions/mean_length": 452.575,
      "completions/mean_terminated_length": 405.1588165283203,
      "completions/min_length": 342.3,
      "completions/min_terminated_length": 342.3,
      "entropy": 0.3708974776789546,
      "epoch": 1.1333333333333333,
      "frac_reward_zero_std": 0.8,
      "grad_norm": 0.032470703125,
      "kl": 0.05273645754205063,
      "learning_rate": 4.366666666666667e-06,
      "loss": 0.0020671430975198746,
      "num_tokens": 868979.0,
      "reward": 1.2064208984375,
      "reward_std": 0.1077505886554718,
      "rewards/JointRewardFunction/mean": 1.2064208984375,
      "rewards/JointRewardFunction/std": 0.10775059163570404,
      "step": 170,
      "step_time": 23.706487477812335
    },
    {
      "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": 0.3875,
      "completions/max_length": 512.0,
      "completions/max_terminated_length": 481.1,
      "completions/mean_length": 445.025,
      "completions/mean_terminated_length": 411.8959655761719,
      "completions/min_length": 341.8,
      "completions/min_terminated_length": 341.8,
      "entropy": 0.3909618055447936,
      "epoch": 1.2,
      "frac_reward_zero_std": 0.55,
      "grad_norm": 1.7109375,
      "kl": 0.045815252687316385,
      "learning_rate": 4.033333333333333e-06,
      "loss": 0.004306042194366455,
      "num_tokens": 917385.0,
      "reward": 1.075,
      "reward_std": 0.3337466180324554,
      "rewards/JointRewardFunction/mean": 1.075,
      "rewards/JointRewardFunction/std": 0.3337466180324554,
      "step": 180,
      "step_time": 23.554991897323635
    },
    {
      "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": 0.6125,
      "completions/max_length": 512.0,
      "completions/max_terminated_length": 471.2,
      "completions/mean_length": 468.075,
      "completions/mean_terminated_length": 422.6735778808594,
      "completions/min_length": 385.9,
      "completions/min_terminated_length": 385.9,
      "entropy": 0.36821637134999036,
      "epoch": 1.2666666666666666,
      "frac_reward_zero_std": 0.55,
      "grad_norm": 1.8671875,
      "kl": 0.04221574537805282,
      "learning_rate": 3.7e-06,
      "loss": 0.005308620631694794,
      "num_tokens": 968751.0,
      "reward": 0.95,
      "reward_std": 0.3438155859708786,
      "rewards/JointRewardFunction/mean": 0.95,
      "rewards/JointRewardFunction/std": 0.34381560385227206,
      "step": 190,
      "step_time": 23.511522994117694
    },
    {
      "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": 497.9,
      "completions/max_terminated_length": 470.5,
      "completions/mean_length": 431.05,
      "completions/mean_terminated_length": 400.3317901611328,
      "completions/min_length": 318.5,
      "completions/min_terminated_length": 318.5,
      "entropy": 0.41096227150410414,
      "epoch": 1.3333333333333333,
      "frac_reward_zero_std": 0.65,
      "grad_norm": 0.06640625,
      "kl": 0.04462224093731493,
      "learning_rate": 3.366666666666667e-06,
      "loss": 0.0076727248728275296,
      "num_tokens": 1016343.0,
      "reward": 1.125,
      "reward_std": 0.21674493551254273,
      "rewards/JointRewardFunction/mean": 1.125,
      "rewards/JointRewardFunction/std": 0.21674493551254273,
      "step": 200,
      "step_time": 23.060737183006133
    },
    {
      "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": 0.3875,
      "completions/max_length": 512.0,
      "completions/max_terminated_length": 482.7,
      "completions/mean_length": 458.65,
      "completions/mean_terminated_length": 428.9585815429688,
      "completions/min_length": 363.5,
      "completions/min_terminated_length": 363.5,
      "entropy": 0.3947587950155139,
      "epoch": 1.4,
      "frac_reward_zero_std": 0.65,
      "grad_norm": 9.3125,
      "kl": 0.10990666588768364,
      "learning_rate": 3.0333333333333337e-06,
      "loss": 0.010126692801713943,
      "num_tokens": 1066311.0,
      "reward": 1.111083984375,
      "reward_std": 0.28541127145290374,
      "rewards/JointRewardFunction/mean": 1.111083984375,
      "rewards/JointRewardFunction/std": 0.2854112803936005,
      "step": 210,
      "step_time": 23.734341114398557
    },
    {
      "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": 0.375,
      "completions/max_length": 511.2,
      "completions/max_terminated_length": 499.2,
      "completions/mean_length": 448.1,
      "completions/mean_terminated_length": 415.37428894042966,
      "completions/min_length": 327.8,
      "completions/min_terminated_length": 327.8,
      "entropy": 0.4135129824280739,
      "epoch": 1.4666666666666668,
      "frac_reward_zero_std": 0.4,
      "grad_norm": 2.0,
      "kl": 0.04890955399023369,
      "learning_rate": 2.7000000000000004e-06,
      "loss": 0.005412362515926361,
      "num_tokens": 1115131.0,
      "reward": 1.0,
      "reward_std": 0.407365021109581,
      "rewards/JointRewardFunction/mean": 1.0,
      "rewards/JointRewardFunction/std": 0.4073650389909744,
      "step": 220,
      "step_time": 23.674485975824062
    },
    {
      "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": 0.3,
      "completions/max_length": 493.0,
      "completions/max_terminated_length": 468.3,
      "completions/mean_length": 425.175,
      "completions/mean_terminated_length": 400.7392883300781,
      "completions/min_length": 313.4,
      "completions/min_terminated_length": 313.4,
      "entropy": 0.40025499686598776,
      "epoch": 1.5333333333333332,
      "frac_reward_zero_std": 0.6,
      "grad_norm": 0.045166015625,
      "kl": 0.044459241011645646,
      "learning_rate": 2.3666666666666667e-06,
      "loss": 0.0074857622385025024,
      "num_tokens": 1162029.0,
      "reward": 1.0625,
      "reward_std": 0.332049286365509,
      "rewards/JointRewardFunction/mean": 1.0625,
      "rewards/JointRewardFunction/std": 0.3320492923259735,
      "step": 230,
      "step_time": 22.975970137718832
    },
    {
      "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": 0.5125,
      "completions/max_length": 507.5,
      "completions/max_terminated_length": 417.0,
      "completions/mean_length": 443.7875,
      "completions/mean_terminated_length": 338.87250366210935,
      "completions/min_length": 315.1,
      "completions/min_terminated_length": 263.9,
      "entropy": 0.3852341592311859,
      "epoch": 1.6,
      "frac_reward_zero_std": 0.5,
      "grad_norm": 2.109375,
      "kl": 0.039597276959102604,
      "learning_rate": 2.0333333333333335e-06,
      "loss": 0.015155516564846039,
      "num_tokens": 1211952.0,
      "reward": 1.03134765625,
      "reward_std": 0.30796128809452056,
      "rewards/JointRewardFunction/mean": 1.03134765625,
      "rewards/JointRewardFunction/std": 0.30796128809452056,
      "step": 240,
      "step_time": 23.477432061507717
    },
    {
      "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": 0.4125,
      "completions/max_length": 499.5,
      "completions/max_terminated_length": 454.8,
      "completions/mean_length": 440.175,
      "completions/mean_terminated_length": 402.6975067138672,
      "completions/min_length": 342.6,
      "completions/min_terminated_length": 342.6,
      "entropy": 0.4049293929710984,
      "epoch": 1.6666666666666665,
      "frac_reward_zero_std": 0.55,
      "grad_norm": 0.06689453125,
      "kl": 0.057483326562214644,
      "learning_rate": 1.7000000000000002e-06,
      "loss": 0.005497528612613678,
      "num_tokens": 1260194.0,
      "reward": 1.100634765625,
      "reward_std": 0.30466278195381163,
      "rewards/JointRewardFunction/mean": 1.100634765625,
      "rewards/JointRewardFunction/std": 0.30466278940439223,
      "step": 250,
      "step_time": 23.31596095281129
    },
    {
      "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": 0.4125,
      "completions/max_length": 512.0,
      "completions/max_terminated_length": 486.0,
      "completions/mean_length": 455.5875,
      "completions/mean_terminated_length": 423.4404815673828,
      "completions/min_length": 368.3,
      "completions/min_terminated_length": 368.3,
      "entropy": 0.37657185792922976,
      "epoch": 1.7333333333333334,
      "frac_reward_zero_std": 0.55,
      "grad_norm": 1.78125,
      "kl": 0.044227164250332865,
      "learning_rate": 1.3666666666666668e-06,
      "loss": 0.01007101833820343,
      "num_tokens": 1312481.0,
      "reward": 1.0563232421875,
      "reward_std": 0.3230230301618576,
      "rewards/JointRewardFunction/mean": 1.0563232421875,
      "rewards/JointRewardFunction/std": 0.3230230316519737,
      "step": 260,
      "step_time": 23.83616074830352
    },
    {
      "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": 0.25,
      "completions/max_length": 511.2,
      "completions/max_terminated_length": 478.9,
      "completions/mean_length": 419.7,
      "completions/mean_terminated_length": 390.71238708496094,
      "completions/min_length": 292.4,
      "completions/min_terminated_length": 292.4,
      "entropy": 0.3890227179042995,
      "epoch": 1.8,
      "frac_reward_zero_std": 0.85,
      "grad_norm": 0.0517578125,
      "kl": 0.04973521351348609,
      "learning_rate": 1.0333333333333333e-06,
      "loss": 0.00801372081041336,
      "num_tokens": 1358297.0,
      "reward": 1.1375,
      "reward_std": 0.12793734967708587,
      "rewards/JointRewardFunction/mean": 1.1375,
      "rewards/JointRewardFunction/std": 0.12793734967708587,
      "step": 270,
      "step_time": 23.87891690217657
    },
    {
      "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": 0.45,
      "completions/max_length": 512.0,
      "completions/max_terminated_length": 464.2,
      "completions/mean_length": 440.9125,
      "completions/mean_terminated_length": 394.0228607177734,
      "completions/min_length": 329.2,
      "completions/min_terminated_length": 329.2,
      "entropy": 0.3685274325311184,
      "epoch": 1.8666666666666667,
      "frac_reward_zero_std": 0.6,
      "grad_norm": 0.134765625,
      "kl": 0.05201944473665208,
      "learning_rate": 7.000000000000001e-07,
      "loss": 0.013003082573413849,
      "num_tokens": 1406762.0,
      "reward": 1.123974609375,
      "reward_std": 0.25532945692539216,
      "rewards/JointRewardFunction/mean": 1.123974609375,
      "rewards/JointRewardFunction/std": 0.25532945692539216,
      "step": 280,
      "step_time": 23.774091701293948
    },
    {
      "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": 0.4125,
      "completions/max_length": 508.9,
      "completions/max_terminated_length": 447.5,
      "completions/mean_length": 443.3125,
      "completions/mean_terminated_length": 385.1429840087891,
      "completions/min_length": 311.9,
      "completions/min_terminated_length": 311.9,
      "entropy": 0.3619745412841439,
      "epoch": 1.9333333333333333,
      "frac_reward_zero_std": 0.55,
      "grad_norm": 1.296875,
      "kl": 0.04537691879086196,
      "learning_rate": 3.666666666666667e-07,
      "loss": 0.015167883038520813,
      "num_tokens": 1456063.0,
      "reward": 1.1,
      "reward_std": 0.2966939479112625,
      "rewards/JointRewardFunction/mean": 1.1,
      "rewards/JointRewardFunction/std": 0.296693953871727,
      "step": 290,
      "step_time": 23.711561490091846
    },
    {
      "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": 0.3625,
      "completions/max_length": 511.4,
      "completions/max_terminated_length": 471.0,
      "completions/mean_length": 445.95,
      "completions/mean_terminated_length": 418.78345947265626,
      "completions/min_length": 355.0,
      "completions/min_terminated_length": 355.0,
      "entropy": 0.3853150447830558,
      "epoch": 2.0,
      "frac_reward_zero_std": 0.6,
      "grad_norm": 1.8515625,
      "kl": 0.04785980319138616,
      "learning_rate": 3.333333333333334e-08,
      "loss": -0.0016140155494213104,
      "num_tokens": 1504095.0,
      "reward": 1.1375,
      "reward_std": 0.2394672751426697,
      "rewards/JointRewardFunction/mean": 1.1375,
      "rewards/JointRewardFunction/std": 0.23946728110313414,
      "step": 300,
      "step_time": 23.609792864409975
    }
  ],
  "logging_steps": 10,
  "max_steps": 300,
  "num_input_tokens_seen": 1504095,
  "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
}