{
  "best_global_step": null,
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.07142857142857142,
  "eval_steps": 500,
  "global_step": 25,
  "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": 16.1,
      "completions/max_terminated_length": 16.1,
      "completions/mean_length": 15.43125,
      "completions/mean_terminated_length": 15.43125,
      "completions/min_length": 12.8,
      "completions/min_terminated_length": 12.8,
      "entropy": 0.11648641154170036,
      "epoch": 0.02857142857142857,
      "frac_reward_zero_std": 0.0,
      "grad_norm": 3.766094207763672,
      "learning_rate": 1.955e-06,
      "loss": -0.03027614951133728,
      "num_tokens": 117861.0,
      "reward": 0.42463125213980674,
      "reward_std": 0.4041272960603237,
      "rewards/<lambda>/mean": 0.42463125213980674,
      "rewards/<lambda>/std": 0.4041273109614849,
      "step": 10,
      "step_time": 8.86154415559722
    },
    {
      "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": 39.1,
      "completions/max_terminated_length": 39.1,
      "completions/mean_length": 15.76875,
      "completions/mean_terminated_length": 15.76875,
      "completions/min_length": 12.0,
      "completions/min_terminated_length": 12.0,
      "entropy": 0.14287759065628053,
      "epoch": 0.05714285714285714,
      "frac_reward_zero_std": 0.3,
      "grad_norm": 4.652894020080566,
      "learning_rate": 1.905e-06,
      "loss": -0.007219273597002029,
      "num_tokens": 211120.0,
      "reward": 0.16723437011241912,
      "reward_std": 0.23346474170684814,
      "rewards/<lambda>/mean": 0.16723437011241912,
      "rewards/<lambda>/std": 0.233464752137661,
      "step": 20,
      "step_time": 8.861151697207243
    }
  ],
  "logging_steps": 10,
  "max_steps": 400,
  "num_input_tokens_seen": 264439,
  "num_train_epochs": 2,
  "save_steps": 25,
  "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": 16,
  "trial_name": null,
  "trial_params": null
}