{
  "best_global_step": null,
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.1,
  "eval_steps": 500,
  "global_step": 50,
  "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": 986.8,
      "completions/max_terminated_length": 986.8,
      "completions/mean_length": 859.9,
      "completions/mean_terminated_length": 859.9,
      "completions/min_length": 716.6,
      "completions/min_terminated_length": 716.6,
      "epoch": 0.01,
      "frac_reward_zero_std": 0.0,
      "grad_norm": 0.09593440592288971,
      "learning_rate": 2e-05,
      "loss": 0.0005,
      "num_tokens": 36204.0,
      "reward": 0.5495000004768371,
      "reward_std": 0.17061833292245865,
      "rewards/reward_RULER/mean": 0.5495000004768371,
      "rewards/reward_RULER/std": 0.17061834409832954,
      "rewards/reward_short/mean": 0.0,
      "rewards/reward_short/std": 0.0,
      "step": 5
    },
    {
      "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": 552.0,
      "completions/max_terminated_length": 552.0,
      "completions/mean_length": 464.425,
      "completions/mean_terminated_length": 464.425,
      "completions/min_length": 381.0,
      "completions/min_terminated_length": 381.0,
      "epoch": 0.02,
      "frac_reward_zero_std": 0.0,
      "grad_norm": 0.03579658269882202,
      "learning_rate": 2e-05,
      "loss": -0.013,
      "num_tokens": 57069.0,
      "reward": 0.6187500059604645,
      "reward_std": 0.13032747879624368,
      "rewards/reward_RULER/mean": 0.6187500059604645,
      "rewards/reward_RULER/std": 0.13032748326659202,
      "rewards/reward_short/mean": 0.0,
      "rewards/reward_short/std": 0.0,
      "step": 10
    },
    {
      "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": 1370.8,
      "completions/max_terminated_length": 1370.8,
      "completions/mean_length": 1088.35,
      "completions/mean_terminated_length": 1088.35,
      "completions/min_length": 836.2,
      "completions/min_terminated_length": 836.2,
      "epoch": 0.03,
      "frac_reward_zero_std": 0.0,
      "grad_norm": 0.030775019899010658,
      "learning_rate": 2e-05,
      "loss": -0.0392,
      "num_tokens": 102323.0,
      "reward": 0.503250002861023,
      "reward_std": 0.14202061779797076,
      "rewards/reward_RULER/mean": 0.503250002861023,
      "rewards/reward_RULER/std": 0.1420206159353256,
      "rewards/reward_short/mean": 0.0,
      "rewards/reward_short/std": 0.0,
      "step": 15
    },
    {
      "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": 735.6,
      "completions/max_terminated_length": 735.6,
      "completions/mean_length": 602.4,
      "completions/mean_terminated_length": 602.4,
      "completions/min_length": 494.4,
      "completions/min_terminated_length": 494.4,
      "epoch": 0.04,
      "frac_reward_zero_std": 0.0,
      "grad_norm": 0.11490475386381149,
      "learning_rate": 2e-05,
      "loss": 0.0578,
      "num_tokens": 129907.0,
      "reward": 0.5053500056266784,
      "reward_std": 0.18268517702817916,
      "rewards/reward_RULER/mean": 0.5053500056266784,
      "rewards/reward_RULER/std": 0.1826851785182953,
      "rewards/reward_short/mean": 0.0,
      "rewards/reward_short/std": 0.0,
      "step": 20
    },
    {
      "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": 774.8,
      "completions/max_terminated_length": 774.8,
      "completions/mean_length": 638.225,
      "completions/mean_terminated_length": 638.225,
      "completions/min_length": 552.0,
      "completions/min_terminated_length": 552.0,
      "epoch": 0.05,
      "frac_reward_zero_std": 0.0,
      "grad_norm": 0.0625438317656517,
      "learning_rate": 2e-05,
      "loss": -0.016,
      "num_tokens": 157732.0,
      "reward": 0.521749985218048,
      "reward_std": 0.15968329459428787,
      "rewards/reward_RULER/mean": 0.521749985218048,
      "rewards/reward_RULER/std": 0.15968331769108773,
      "rewards/reward_short/mean": 0.0,
      "rewards/reward_short/std": 0.0,
      "step": 25
    },
    {
      "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": 277.2,
      "completions/max_terminated_length": 277.2,
      "completions/mean_length": 210.925,
      "completions/mean_terminated_length": 210.925,
      "completions/min_length": 150.4,
      "completions/min_terminated_length": 150.4,
      "epoch": 0.06,
      "frac_reward_zero_std": 0.0,
      "grad_norm": 0.12225955724716187,
      "learning_rate": 2e-05,
      "loss": -0.0276,
      "num_tokens": 170273.0,
      "reward": 0.6259999990463256,
      "reward_std": 0.23134377971291542,
      "rewards/reward_RULER/mean": 0.6259999990463256,
      "rewards/reward_RULER/std": 0.2313437804579735,
      "rewards/reward_short/mean": 0.0,
      "rewards/reward_short/std": 0.0,
      "step": 30
    },
    {
      "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": 846.0,
      "completions/max_terminated_length": 846.0,
      "completions/mean_length": 736.775,
      "completions/mean_terminated_length": 736.775,
      "completions/min_length": 618.4,
      "completions/min_terminated_length": 618.4,
      "epoch": 0.07,
      "frac_reward_zero_std": 0.0,
      "grad_norm": 0.03475014120340347,
      "learning_rate": 2e-05,
      "loss": 0.0223,
      "num_tokens": 201488.0,
      "reward": 0.5945000052452087,
      "reward_std": 0.09596815258264542,
      "rewards/reward_RULER/mean": 0.5945000052452087,
      "rewards/reward_RULER/std": 0.09596815742552281,
      "rewards/reward_short/mean": 0.0,
      "rewards/reward_short/std": 0.0,
      "step": 35
    },
    {
      "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": 960.6,
      "completions/max_terminated_length": 960.6,
      "completions/mean_length": 774.175,
      "completions/mean_terminated_length": 774.175,
      "completions/min_length": 655.4,
      "completions/min_terminated_length": 655.4,
      "epoch": 0.08,
      "frac_reward_zero_std": 0.0,
      "grad_norm": 0.10908406227827072,
      "learning_rate": 2e-05,
      "loss": 0.0087,
      "num_tokens": 235343.0,
      "reward": 0.5429999977350235,
      "reward_std": 0.12850210070610046,
      "rewards/reward_RULER/mean": 0.5429999977350235,
      "rewards/reward_RULER/std": 0.12850209772586824,
      "rewards/reward_short/mean": 0.0,
      "rewards/reward_short/std": 0.0,
      "step": 40
    },
    {
      "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": 500.4,
      "completions/max_terminated_length": 500.4,
      "completions/mean_length": 400.825,
      "completions/mean_terminated_length": 400.825,
      "completions/min_length": 327.0,
      "completions/min_terminated_length": 327.0,
      "epoch": 0.09,
      "frac_reward_zero_std": 0.0,
      "grad_norm": 0.1326361447572708,
      "learning_rate": 2e-05,
      "loss": -0.0385,
      "num_tokens": 254880.0,
      "reward": 0.7205000162124634,
      "reward_std": 0.16288756281137468,
      "rewards/reward_RULER/mean": 0.7205000162124634,
      "rewards/reward_RULER/std": 0.1628875747323036,
      "rewards/reward_short/mean": 0.0,
      "rewards/reward_short/std": 0.0,
      "step": 45
    },
    {
      "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": 688.4,
      "completions/max_terminated_length": 688.4,
      "completions/mean_length": 601.575,
      "completions/mean_terminated_length": 601.575,
      "completions/min_length": 520.0,
      "completions/min_terminated_length": 520.0,
      "epoch": 0.1,
      "frac_reward_zero_std": 0.0,
      "grad_norm": 0.029254460707306862,
      "learning_rate": 2e-05,
      "loss": -0.0005,
      "num_tokens": 281871.0,
      "reward": 0.6317500114440918,
      "reward_std": 0.07507448904216289,
      "rewards/reward_RULER/mean": 0.6317500114440918,
      "rewards/reward_RULER/std": 0.0750744953751564,
      "rewards/reward_short/mean": 0.0,
      "rewards/reward_short/std": 0.0,
      "step": 50
    }
  ],
  "logging_steps": 5,
  "max_steps": 500,
  "num_input_tokens_seen": 281871,
  "num_train_epochs": 1,
  "save_steps": 50,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 0.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}