{
  "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": 0.0,
      "completions/max_length": 697.1,
      "completions/max_terminated_length": 697.1,
      "completions/mean_length": 444.4875,
      "completions/mean_terminated_length": 444.4875,
      "completions/min_length": 229.5,
      "completions/min_terminated_length": 229.5,
      "entropy": 0.7007812947034836,
      "epoch": 0.08,
      "frac_reward_zero_std": 0.275,
      "grad_norm": 2.53125,
      "kl": 0.07940242243275861,
      "learning_rate": 9.4375e-06,
      "loss": 0.008688435703516007,
      "num_tokens": 56203.0,
      "reward": 0.6825366348028183,
      "reward_std": 0.42148933857679366,
      "rewards/JointRewardFunction/mean": 0.6825366348028183,
      "rewards/JointRewardFunction/std": 0.4214893504977226,
      "step": 10,
      "step_time": 29.87573713920101
    },
    {
      "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": 655.1,
      "completions/max_terminated_length": 655.1,
      "completions/mean_length": 424.4125,
      "completions/mean_terminated_length": 424.4125,
      "completions/min_length": 240.3,
      "completions/min_terminated_length": 240.3,
      "entropy": 0.7277415141463279,
      "epoch": 0.16,
      "frac_reward_zero_std": 0.225,
      "grad_norm": 1.765625,
      "kl": 0.09351013670675457,
      "learning_rate": 8.8125e-06,
      "loss": 0.0028222408145666122,
      "num_tokens": 110800.0,
      "reward": 0.7511120676994324,
      "reward_std": 0.4809179216623306,
      "rewards/JointRewardFunction/mean": 0.7511120676994324,
      "rewards/JointRewardFunction/std": 0.4809179395437241,
      "step": 20,
      "step_time": 29.239146613800404
    },
    {
      "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": 681.9,
      "completions/max_terminated_length": 681.9,
      "completions/mean_length": 482.1,
      "completions/mean_terminated_length": 482.1,
      "completions/min_length": 293.0,
      "completions/min_terminated_length": 293.0,
      "entropy": 0.8137854047119617,
      "epoch": 0.24,
      "frac_reward_zero_std": 0.275,
      "grad_norm": 2.34375,
      "kl": 0.08033584761433303,
      "learning_rate": 8.1875e-06,
      "loss": 0.019247914850711822,
      "num_tokens": 169812.0,
      "reward": 0.8227136462926865,
      "reward_std": 0.3767334818840027,
      "rewards/JointRewardFunction/mean": 0.8227136462926865,
      "rewards/JointRewardFunction/std": 0.37673348784446714,
      "step": 30,
      "step_time": 30.690014854901893
    },
    {
      "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": 699.3,
      "completions/max_terminated_length": 699.3,
      "completions/mean_length": 469.3375,
      "completions/mean_terminated_length": 469.3375,
      "completions/min_length": 286.5,
      "completions/min_terminated_length": 286.5,
      "entropy": 0.8683047238737345,
      "epoch": 0.32,
      "frac_reward_zero_std": 0.2,
      "grad_norm": 2.296875,
      "kl": 0.08547290097922086,
      "learning_rate": 7.5625e-06,
      "loss": 0.005851123481988907,
      "num_tokens": 227933.0,
      "reward": 0.8848474144935607,
      "reward_std": 0.4506288319826126,
      "rewards/JointRewardFunction/mean": 0.8848474144935607,
      "rewards/JointRewardFunction/std": 0.4506288468837738,
      "step": 40,
      "step_time": 31.253191193498786
    },
    {
      "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": 713.1,
      "completions/max_terminated_length": 713.1,
      "completions/mean_length": 510.825,
      "completions/mean_terminated_length": 510.825,
      "completions/min_length": 317.9,
      "completions/min_terminated_length": 317.9,
      "entropy": 0.8964162725955248,
      "epoch": 0.4,
      "frac_reward_zero_std": 0.2,
      "grad_norm": 1.71875,
      "kl": 0.07821776089258492,
      "learning_rate": 6.9375e-06,
      "loss": 0.013301727175712586,
      "num_tokens": 289629.0,
      "reward": 1.038847678899765,
      "reward_std": 0.3691652432084084,
      "rewards/JointRewardFunction/mean": 1.038847678899765,
      "rewards/JointRewardFunction/std": 0.36916525810956957,
      "step": 50,
      "step_time": 31.799948546098314
    },
    {
      "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": 746.0,
      "completions/max_terminated_length": 746.0,
      "completions/mean_length": 523.425,
      "completions/mean_terminated_length": 523.425,
      "completions/min_length": 309.1,
      "completions/min_terminated_length": 309.1,
      "entropy": 0.8802642215043306,
      "epoch": 0.48,
      "frac_reward_zero_std": 0.175,
      "grad_norm": 2.0,
      "kl": 0.0804219183512032,
      "learning_rate": 6.3125e-06,
      "loss": 0.03207117319107056,
      "num_tokens": 351843.0,
      "reward": 0.9487841844558715,
      "reward_std": 0.42972691655158995,
      "rewards/JointRewardFunction/mean": 0.9487841844558715,
      "rewards/JointRewardFunction/std": 0.4297269403934479,
      "step": 60,
      "step_time": 32.83071275450202
    },
    {
      "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": 715.3,
      "completions/max_terminated_length": 695.1,
      "completions/mean_length": 510.3,
      "completions/mean_terminated_length": 503.83750305175784,
      "completions/min_length": 295.9,
      "completions/min_terminated_length": 295.9,
      "entropy": 0.9274463646113873,
      "epoch": 0.56,
      "frac_reward_zero_std": 0.3,
      "grad_norm": 2.265625,
      "kl": 0.08897386915050447,
      "learning_rate": 5.6875e-06,
      "loss": 0.07122264504432678,
      "num_tokens": 413123.0,
      "reward": 1.0958777070045471,
      "reward_std": 0.3831350475549698,
      "rewards/JointRewardFunction/mean": 1.0958777070045471,
      "rewards/JointRewardFunction/std": 0.3831350475549698,
      "step": 70,
      "step_time": 31.748691623102424
    },
    {
      "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": 608.4,
      "completions/max_terminated_length": 608.4,
      "completions/mean_length": 440.2875,
      "completions/mean_terminated_length": 440.2875,
      "completions/min_length": 326.3,
      "completions/min_terminated_length": 326.3,
      "entropy": 0.8611678160727024,
      "epoch": 0.64,
      "frac_reward_zero_std": 0.275,
      "grad_norm": 2.8125,
      "kl": 0.0876699925865978,
      "learning_rate": 5.0625e-06,
      "loss": 0.019712889194488527,
      "num_tokens": 468960.0,
      "reward": 1.0908459782600404,
      "reward_std": 0.35941318422555923,
      "rewards/JointRewardFunction/mean": 1.0908459782600404,
      "rewards/JointRewardFunction/std": 0.3594131987541914,
      "step": 80,
      "step_time": 27.2742907967011
    },
    {
      "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": 626.7,
      "completions/max_terminated_length": 626.7,
      "completions/mean_length": 434.05,
      "completions/mean_terminated_length": 434.05,
      "completions/min_length": 263.7,
      "completions/min_terminated_length": 263.7,
      "entropy": 0.8135976739227772,
      "epoch": 0.72,
      "frac_reward_zero_std": 0.375,
      "grad_norm": 1.6953125,
      "kl": 0.09378819759003817,
      "learning_rate": 4.4375e-06,
      "loss": 0.06376264691352844,
      "num_tokens": 524304.0,
      "reward": 1.109246850013733,
      "reward_std": 0.35286828482057897,
      "rewards/JointRewardFunction/mean": 1.109246850013733,
      "rewards/JointRewardFunction/std": 0.3528682907810435,
      "step": 90,
      "step_time": 28.181775099898367
    },
    {
      "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": 627.0,
      "completions/max_terminated_length": 627.0,
      "completions/mean_length": 444.325,
      "completions/mean_terminated_length": 444.325,
      "completions/min_length": 307.4,
      "completions/min_terminated_length": 307.4,
      "entropy": 0.9360679395496845,
      "epoch": 0.8,
      "frac_reward_zero_std": 0.275,
      "grad_norm": 2.3125,
      "kl": 0.08875131588429212,
      "learning_rate": 3.8125e-06,
      "loss": 0.03808712363243103,
      "num_tokens": 580516.0,
      "reward": 1.0944311678409577,
      "reward_std": 0.3305914536118507,
      "rewards/JointRewardFunction/mean": 1.0944311678409577,
      "rewards/JointRewardFunction/std": 0.3305914685130119,
      "step": 100,
      "step_time": 28.45329053500027
    },
    {
      "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": 650.9,
      "completions/max_terminated_length": 650.9,
      "completions/mean_length": 442.6875,
      "completions/mean_terminated_length": 442.6875,
      "completions/min_length": 262.7,
      "completions/min_terminated_length": 262.7,
      "entropy": 0.9691729046404362,
      "epoch": 0.88,
      "frac_reward_zero_std": 0.275,
      "grad_norm": 2.21875,
      "kl": 0.08224498964846134,
      "learning_rate": 3.1875e-06,
      "loss": 0.027349627017974852,
      "num_tokens": 636475.0,
      "reward": 1.031976318359375,
      "reward_std": 0.43738164007663727,
      "rewards/JointRewardFunction/mean": 1.031976318359375,
      "rewards/JointRewardFunction/std": 0.4373816430568695,
      "step": 110,
      "step_time": 29.40713436929982
    },
    {
      "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": 587.8,
      "completions/max_terminated_length": 587.8,
      "completions/mean_length": 423.65,
      "completions/mean_terminated_length": 423.65,
      "completions/min_length": 273.3,
      "completions/min_terminated_length": 273.3,
      "entropy": 0.886437576636672,
      "epoch": 0.96,
      "frac_reward_zero_std": 0.425,
      "grad_norm": 1.96875,
      "kl": 0.08013711464591325,
      "learning_rate": 2.5625e-06,
      "loss": 0.029777994751930235,
      "num_tokens": 690739.0,
      "reward": 1.1266614079475403,
      "reward_std": 0.2993911794852465,
      "rewards/JointRewardFunction/mean": 1.1266614079475403,
      "rewards/JointRewardFunction/std": 0.29939117534086107,
      "step": 120,
      "step_time": 26.532396802499353
    },
    {
      "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": 548.8,
      "completions/max_terminated_length": 548.8,
      "completions/mean_length": 413.5,
      "completions/mean_terminated_length": 413.5,
      "completions/min_length": 296.6,
      "completions/min_terminated_length": 296.6,
      "entropy": 0.8794000033289194,
      "epoch": 1.04,
      "frac_reward_zero_std": 0.475,
      "grad_norm": 1.1875,
      "kl": 0.0789637949783355,
      "learning_rate": 1.9375e-06,
      "loss": -0.010777493566274643,
      "num_tokens": 744437.0,
      "reward": 1.1596606612205504,
      "reward_std": 0.2929948531091213,
      "rewards/JointRewardFunction/mean": 1.1596606612205504,
      "rewards/JointRewardFunction/std": 0.29299486204981806,
      "step": 130,
      "step_time": 25.31505165609851
    },
    {
      "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": 600.5,
      "completions/max_terminated_length": 600.5,
      "completions/mean_length": 419.575,
      "completions/mean_terminated_length": 419.575,
      "completions/min_length": 260.8,
      "completions/min_terminated_length": 260.8,
      "entropy": 0.9347391467541456,
      "epoch": 1.12,
      "frac_reward_zero_std": 0.275,
      "grad_norm": 2.765625,
      "kl": 0.08032974656671285,
      "learning_rate": 1.3125000000000001e-06,
      "loss": 0.02551303505897522,
      "num_tokens": 798651.0,
      "reward": 1.0246130645275116,
      "reward_std": 0.39613366425037383,
      "rewards/JointRewardFunction/mean": 1.0246130645275116,
      "rewards/JointRewardFunction/std": 0.3961336761713028,
      "step": 140,
      "step_time": 27.637355703599678
    },
    {
      "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": 558.5,
      "completions/max_terminated_length": 558.5,
      "completions/mean_length": 394.375,
      "completions/mean_terminated_length": 394.375,
      "completions/min_length": 255.9,
      "completions/min_terminated_length": 255.9,
      "entropy": 0.841333020478487,
      "epoch": 1.2,
      "frac_reward_zero_std": 0.5,
      "grad_norm": 0.11767578125,
      "kl": 0.08763318308629095,
      "learning_rate": 6.875000000000001e-07,
      "loss": 0.025534918904304503,
      "num_tokens": 850777.0,
      "reward": 1.1621960639953612,
      "reward_std": 0.28392985463142395,
      "rewards/JointRewardFunction/mean": 1.1621960639953612,
      "rewards/JointRewardFunction/std": 0.2839298591017723,
      "step": 150,
      "step_time": 25.526650765698285
    },
    {
      "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": 569.3,
      "completions/max_terminated_length": 569.3,
      "completions/mean_length": 417.65,
      "completions/mean_terminated_length": 417.65,
      "completions/min_length": 253.4,
      "completions/min_terminated_length": 253.4,
      "entropy": 0.9602293692529201,
      "epoch": 1.28,
      "frac_reward_zero_std": 0.35,
      "grad_norm": 1.8671875,
      "kl": 0.08848655968904495,
      "learning_rate": 6.250000000000001e-08,
      "loss": 0.002139208652079105,
      "num_tokens": 905091.0,
      "reward": 1.0879150748252868,
      "reward_std": 0.3240631450258661,
      "rewards/JointRewardFunction/mean": 1.0879150748252868,
      "rewards/JointRewardFunction/std": 0.32406314978725276,
      "step": 160,
      "step_time": 26.06666781829881
    }
  ],
  "logging_steps": 10,
  "max_steps": 160,
  "num_input_tokens_seen": 905091,
  "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
}