{
  "best_global_step": null,
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 3.0,
  "eval_steps": 500,
  "global_step": 18,
  "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": 0.7625,
      "completions/max_length": 512.0,
      "completions/max_terminated_length": 265.2,
      "completions/mean_length": 439.1875,
      "completions/mean_terminated_length": 209.825,
      "completions/min_length": 142.5,
      "completions/min_terminated_length": 142.5,
      "entropy": 3.4775290532037615,
      "epoch": 1.6666666666666665,
      "frac_reward_zero_std": 0.3,
      "grad_norm": 0.02465509995818138,
      "learning_rate": 2.9877258050403214e-06,
      "loss": -0.05790620446205139,
      "num_tokens": 111519.0,
      "reward": 0.02350000003352761,
      "reward_std": 0.036062358692288396,
      "rewards/combined_reward/mean": 0.02350000003352761,
      "rewards/combined_reward/std": 0.036062359996140006,
      "step": 10,
      "step_time": 11.173231775499994
    }
  ],
  "logging_steps": 10,
  "max_steps": 18,
  "num_input_tokens_seen": 201560,
  "num_train_epochs": 3,
  "save_steps": 500,
  "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": 1,
  "trial_name": null,
  "trial_params": null
}