{
  "best_global_step": null,
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.39215686274509803,
  "eval_steps": 500,
  "global_step": 150,
  "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": 0.09375,
      "completions/max_length": 60.3,
      "completions/max_terminated_length": 54.9,
      "completions/mean_length": 29.115625,
      "completions/mean_terminated_length": 25.61234016418457,
      "completions/min_length": 5.0,
      "completions/min_terminated_length": 5.0,
      "entropy": 0.02454666232551972,
      "epoch": 0.026143790849673203,
      "frac_reward_zero_std": 0.91875,
      "grad_norm": 0.0,
      "learning_rate": 9.4e-06,
      "loss": 0.004750595241785049,
      "num_tokens": 97405.0,
      "reward": 0.803125,
      "reward_std": 0.3747939869761467,
      "rewards/reward_execution/mean": 0.803125,
      "rewards/reward_execution/std": 0.3747939869761467,
      "step": 10,
      "step_time": 31.94392708370002
    },
    {
      "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": 0.11875,
      "completions/max_length": 61.5,
      "completions/max_terminated_length": 51.4,
      "completions/mean_length": 29.534375,
      "completions/mean_terminated_length": 24.489348220825196,
      "completions/min_length": 4.5,
      "completions/min_terminated_length": 4.5,
      "entropy": 0.017684313716745236,
      "epoch": 0.05228758169934641,
      "frac_reward_zero_std": 0.90625,
      "grad_norm": 0.21661092340946198,
      "learning_rate": 8.733333333333333e-06,
      "loss": 0.006355612725019455,
      "num_tokens": 190772.0,
      "reward": 0.825,
      "reward_std": 0.3430637501180172,
      "rewards/reward_execution/mean": 0.825,
      "rewards/reward_execution/std": 0.3430637501180172,
      "step": 20,
      "step_time": 22.751771162100045
    },
    {
      "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": 0.10625,
      "completions/max_length": 59.2,
      "completions/max_terminated_length": 55.2,
      "completions/mean_length": 28.6875,
      "completions/mean_terminated_length": 24.416036128997803,
      "completions/min_length": 4.1,
      "completions/min_terminated_length": 4.1,
      "entropy": 0.02558311702705396,
      "epoch": 0.0784313725490196,
      "frac_reward_zero_std": 0.96875,
      "grad_norm": 0.2202943116426468,
      "learning_rate": 8.066666666666667e-06,
      "loss": -5.092360079288483e-05,
      "num_tokens": 284628.0,
      "reward": 0.8109375,
      "reward_std": 0.3315441869199276,
      "rewards/reward_execution/mean": 0.8109375,
      "rewards/reward_execution/std": 0.3315441869199276,
      "step": 30,
      "step_time": 31.906402099300145
    },
    {
      "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": 0.11875,
      "completions/max_length": 61.4,
      "completions/max_terminated_length": 54.5,
      "completions/mean_length": 31.1375,
      "completions/mean_terminated_length": 26.570414543151855,
      "completions/min_length": 7.0,
      "completions/min_terminated_length": 7.0,
      "entropy": 0.01868508225925325,
      "epoch": 0.10457516339869281,
      "frac_reward_zero_std": 0.8875,
      "grad_norm": 0.16491816937923431,
      "learning_rate": 7.4e-06,
      "loss": 0.003377123922109604,
      "num_tokens": 379864.0,
      "reward": 0.7359375,
      "reward_std": 0.4095129996538162,
      "rewards/reward_execution/mean": 0.7359375,
      "rewards/reward_execution/std": 0.4095129996538162,
      "step": 40,
      "step_time": 25.862243815099873
    },
    {
      "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": 0.090625,
      "completions/max_length": 63.5,
      "completions/max_terminated_length": 57.6,
      "completions/mean_length": 30.453125,
      "completions/mean_terminated_length": 26.973687171936035,
      "completions/min_length": 6.2,
      "completions/min_terminated_length": 6.2,
      "entropy": 0.02261894497987669,
      "epoch": 0.13071895424836602,
      "frac_reward_zero_std": 0.95625,
      "grad_norm": 0.0,
      "learning_rate": 6.733333333333334e-06,
      "loss": 0.003694884479045868,
      "num_tokens": 475717.0,
      "reward": 0.815625,
      "reward_std": 0.33494297713041304,
      "rewards/reward_execution/mean": 0.815625,
      "rewards/reward_execution/std": 0.33494297713041304,
      "step": 50,
      "step_time": 31.277315674100077
    },
    {
      "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": 0.165625,
      "completions/max_length": 64.0,
      "completions/max_terminated_length": 57.6,
      "completions/mean_length": 35.090625,
      "completions/mean_terminated_length": 29.284703063964844,
      "completions/min_length": 6.4,
      "completions/min_terminated_length": 6.4,
      "entropy": 0.019299622159451246,
      "epoch": 0.1568627450980392,
      "frac_reward_zero_std": 0.925,
      "grad_norm": 0.0,
      "learning_rate": 6.066666666666667e-06,
      "loss": -0.00391208529472351,
      "num_tokens": 583018.0,
      "reward": 0.7703125,
      "reward_std": 0.38330448120832444,
      "rewards/reward_execution/mean": 0.7703125,
      "rewards/reward_execution/std": 0.38330448120832444,
      "step": 60,
      "step_time": 33.473157937700215
    },
    {
      "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": 0.159375,
      "completions/max_length": 63.6,
      "completions/max_terminated_length": 54.3,
      "completions/mean_length": 30.190625,
      "completions/mean_terminated_length": 23.92726469039917,
      "completions/min_length": 6.9,
      "completions/min_terminated_length": 6.9,
      "entropy": 0.023300658867083258,
      "epoch": 0.1830065359477124,
      "frac_reward_zero_std": 0.975,
      "grad_norm": 0.0,
      "learning_rate": 5.400000000000001e-06,
      "loss": 0.0006014665588736535,
      "num_tokens": 699023.0,
      "reward": 0.79375,
      "reward_std": 0.3528687059879303,
      "rewards/reward_execution/mean": 0.79375,
      "rewards/reward_execution/std": 0.3528687059879303,
      "step": 70,
      "step_time": 51.44500609199972
    },
    {
      "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": 63.5,
      "completions/max_terminated_length": 53.0,
      "completions/mean_length": 34.39375,
      "completions/mean_terminated_length": 27.489916610717774,
      "completions/min_length": 6.4,
      "completions/min_terminated_length": 6.4,
      "entropy": 0.021958425225238897,
      "epoch": 0.20915032679738563,
      "frac_reward_zero_std": 0.94375,
      "grad_norm": 0.23559676110744476,
      "learning_rate": 4.7333333333333335e-06,
      "loss": -0.001726916991174221,
      "num_tokens": 819485.0,
      "reward": 0.721875,
      "reward_std": 0.3789533942937851,
      "rewards/reward_execution/mean": 0.721875,
      "rewards/reward_execution/std": 0.3789533942937851,
      "step": 80,
      "step_time": 43.00004606930047
    },
    {
      "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": 62.0,
      "completions/max_terminated_length": 56.9,
      "completions/mean_length": 31.11875,
      "completions/mean_terminated_length": 25.965628814697265,
      "completions/min_length": 4.4,
      "completions/min_terminated_length": 4.4,
      "entropy": 0.019923989264407284,
      "epoch": 0.23529411764705882,
      "frac_reward_zero_std": 0.96875,
      "grad_norm": 0.0,
      "learning_rate": 4.066666666666667e-06,
      "loss": 0.0018754765391349793,
      "num_tokens": 919863.0,
      "reward": 0.8015625,
      "reward_std": 0.33981852531433104,
      "rewards/reward_execution/mean": 0.8015625,
      "rewards/reward_execution/std": 0.33981852531433104,
      "step": 90,
      "step_time": 33.150223405900036
    },
    {
      "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": 0.065625,
      "completions/max_length": 60.8,
      "completions/max_terminated_length": 59.3,
      "completions/mean_length": 31.55,
      "completions/mean_terminated_length": 29.390228843688966,
      "completions/min_length": 5.8,
      "completions/min_terminated_length": 5.8,
      "entropy": 0.01491436043925205,
      "epoch": 0.26143790849673204,
      "frac_reward_zero_std": 0.9375,
      "grad_norm": 0.0,
      "learning_rate": 3.4000000000000005e-06,
      "loss": -0.002246321178972721,
      "num_tokens": 1009123.0,
      "reward": 0.8390625,
      "reward_std": 0.3023362085223198,
      "rewards/reward_execution/mean": 0.8390625,
      "rewards/reward_execution/std": 0.3023362085223198,
      "step": 100,
      "step_time": 22.67912575240016
    },
    {
      "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": 0.084375,
      "completions/max_length": 57.9,
      "completions/max_terminated_length": 51.4,
      "completions/mean_length": 30.990625,
      "completions/mean_terminated_length": 27.909596824645995,
      "completions/min_length": 10.2,
      "completions/min_terminated_length": 10.2,
      "entropy": 0.020855489475798093,
      "epoch": 0.2875816993464052,
      "frac_reward_zero_std": 0.94375,
      "grad_norm": 0.05379810556769371,
      "learning_rate": 2.7333333333333336e-06,
      "loss": 0.004407734796404839,
      "num_tokens": 1105412.0,
      "reward": 0.834375,
      "reward_std": 0.35761985629796983,
      "rewards/reward_execution/mean": 0.834375,
      "rewards/reward_execution/std": 0.35761985629796983,
      "step": 110,
      "step_time": 24.508954532200278
    },
    {
      "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": 0.10625,
      "completions/max_length": 62.8,
      "completions/max_terminated_length": 59.4,
      "completions/mean_length": 34.053125,
      "completions/mean_terminated_length": 30.486721420288085,
      "completions/min_length": 4.9,
      "completions/min_terminated_length": 4.9,
      "entropy": 0.029882760624423098,
      "epoch": 0.3137254901960784,
      "frac_reward_zero_std": 0.925,
      "grad_norm": 0.0,
      "learning_rate": 2.0666666666666666e-06,
      "loss": -0.000794774666428566,
      "num_tokens": 1210285.0,
      "reward": 0.78125,
      "reward_std": 0.3546693354845047,
      "rewards/reward_execution/mean": 0.78125,
      "rewards/reward_execution/std": 0.3546693354845047,
      "step": 120,
      "step_time": 34.62758466190007
    },
    {
      "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": 0.1,
      "completions/max_length": 62.5,
      "completions/max_terminated_length": 57.9,
      "completions/mean_length": 30.20625,
      "completions/mean_terminated_length": 26.334096908569336,
      "completions/min_length": 7.2,
      "completions/min_terminated_length": 7.2,
      "entropy": 0.025065975469988188,
      "epoch": 0.33986928104575165,
      "frac_reward_zero_std": 0.94375,
      "grad_norm": 0.0,
      "learning_rate": 1.4000000000000001e-06,
      "loss": -0.002230020985007286,
      "num_tokens": 1314099.0,
      "reward": 0.8109375,
      "reward_std": 0.37055897563695905,
      "rewards/reward_execution/mean": 0.8109375,
      "rewards/reward_execution/std": 0.37055897563695905,
      "step": 130,
      "step_time": 33.343724965900584
    },
    {
      "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": 0.059375,
      "completions/max_length": 58.0,
      "completions/max_terminated_length": 53.0,
      "completions/mean_length": 25.6875,
      "completions/mean_terminated_length": 23.403397178649904,
      "completions/min_length": 1.6,
      "completions/min_terminated_length": 1.6,
      "entropy": 0.011309765173427877,
      "epoch": 0.3660130718954248,
      "frac_reward_zero_std": 0.98125,
      "grad_norm": 0.1047602966427803,
      "learning_rate": 7.333333333333334e-07,
      "loss": -0.002726021409034729,
      "num_tokens": 1403035.0,
      "reward": 0.903125,
      "reward_std": 0.23362597078084946,
      "rewards/reward_execution/mean": 0.903125,
      "rewards/reward_execution/std": 0.23362597078084946,
      "step": 140,
      "step_time": 22.193223186700106
    },
    {
      "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": 60.8,
      "completions/max_terminated_length": 48.8,
      "completions/mean_length": 29.640625,
      "completions/mean_terminated_length": 24.425149154663085,
      "completions/min_length": 7.2,
      "completions/min_terminated_length": 7.2,
      "entropy": 0.019182722609548362,
      "epoch": 0.39215686274509803,
      "frac_reward_zero_std": 0.9375,
      "grad_norm": 0.23914681375026703,
      "learning_rate": 6.666666666666668e-08,
      "loss": 0.0005152914673089981,
      "num_tokens": 1492692.0,
      "reward": 0.7953125,
      "reward_std": 0.32230271995067594,
      "rewards/reward_execution/mean": 0.7953125,
      "rewards/reward_execution/std": 0.32230271995067594,
      "step": 150,
      "step_time": 30.48816273099983
    }
  ],
  "logging_steps": 10,
  "max_steps": 150,
  "num_input_tokens_seen": 1492692,
  "num_train_epochs": 1,
  "save_steps": 100,
  "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": 2,
  "trial_name": null,
  "trial_params": null
}