{
  "best_global_step": null,
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.96,
  "eval_steps": 50,
  "global_step": 6,
  "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": 232.0,
      "completions/max_terminated_length": 232.0,
      "completions/mean_length": 101.86875,
      "completions/mean_terminated_length": 101.86875,
      "completions/min_length": 48.6,
      "completions/min_terminated_length": 48.6,
      "epoch": 0.8,
      "grad_norm": 0.1953125,
      "learning_rate": 1e-06,
      "loss": -0.001,
      "num_tokens": 202916.0,
      "reward": 0.5779708623886108,
      "reward_std": 0.12342077642679214,
      "rewards/accuracy_reward": 0.0,
      "rewards/brier_reward": 0.17625187635421752,
      "rewards/confidence_one_or_zero": 0.278125,
      "rewards/format_reward": 0.9796875,
      "rewards/mean_confidence_reward": 0.8856875181198121,
      "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": 247.0,
      "completions/max_terminated_length": 247.0,
      "completions/mean_length": 100.83999633789062,
      "completions/mean_terminated_length": 100.83999633789062,
      "completions/min_length": 53.0,
      "completions/min_terminated_length": 53.0,
      "epoch": 0.96,
      "num_tokens": 243139.0,
      "reward": 0.577644944190979,
      "reward_std": 0.11149925738573074,
      "rewards/accuracy_reward": 0.0,
      "rewards/brier_reward": 0.17091251909732819,
      "rewards/confidence_one_or_zero": 0.2734375,
      "rewards/format_reward": 0.984375,
      "rewards/mean_confidence_reward": 0.8831242322921753,
      "step": 6,
      "total_flos": 0.0,
      "train_loss": -0.0013609611584494512,
      "train_runtime": 209.0392,
      "train_samples_per_second": 0.478,
      "train_steps_per_second": 0.029
    }
  ],
  "logging_steps": 5,
  "max_steps": 6,
  "num_input_tokens_seen": 243139,
  "num_train_epochs": 1,
  "save_steps": 60,
  "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
}