{
  "best_global_step": null,
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.07935314027830011,
  "eval_steps": 500,
  "global_step": 422,
  "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": 0.625,
      "completions/max_length": 256.0,
      "completions/max_terminated_length": 96.0,
      "completions/mean_length": 181.75,
      "completions/mean_terminated_length": 58.0,
      "completions/min_length": 32.0,
      "completions/min_terminated_length": 32.0,
      "entropy": 2.7904417514801025,
      "epoch": 0.000188040616773223,
      "frac_reward_zero_std": 0.0,
      "grad_norm": 1.449855089187622,
      "kl": 0.0,
      "learning_rate": 0.0,
      "loss": 0.0,
      "num_tokens": 3318.0,
      "reward": -0.5996060967445374,
      "reward_std": 0.5187338590621948,
      "rewards/reward_low_difficult_words_percentage/mean": -0.29142773151397705,
      "rewards/reward_low_difficult_words_percentage/std": 0.12733609974384308,
      "rewards/reward_reasoning_keywords/mean": 0.25,
      "rewards/reward_reasoning_keywords/std": 0.4629100561141968,
      "step": 1
    }
  ],
  "logging_steps": 500,
  "max_steps": 422,
  "num_input_tokens_seen": 475851,
  "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": 4,
  "trial_name": null,
  "trial_params": null
}