{
  "best_global_step": null,
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.024691358024691357,
  "eval_steps": 1,
  "global_step": 1,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.024691358024691357,
      "grad_norm": 0.0,
      "learning_rate": 0.0,
      "loss": 0.0,
      "step": 1
    },
    {
      "epoch": 0.024691358024691357,
      "eval_clip_ratio/high_max": 0.0,
      "eval_clip_ratio/high_mean": 0.0,
      "eval_clip_ratio/low_mean": 0.0,
      "eval_clip_ratio/low_min": 0.0,
      "eval_clip_ratio/region_mean": 0.0,
      "eval_completions/clipped_ratio": 0.425,
      "eval_completions/max_length": 205.0,
      "eval_completions/max_terminated_length": 138.6,
      "eval_completions/mean_length": 139.95,
      "eval_completions/mean_terminated_length": 78.71333465576171,
      "eval_completions/min_length": 26.8,
      "eval_completions/min_terminated_length": 26.8,
      "eval_kl": 0.0,
      "eval_loss": -0.020106248557567596,
      "eval_num_tokens": 10430.0,
      "eval_reward": 0.38962903022766116,
      "eval_reward_std": 0.4499048709869385,
      "eval_rewards/reward_func_keyword/mean": 0.1,
      "eval_rewards/reward_func_keyword/std": 0.10690449476242066,
      "eval_runtime": 63.1375,
      "eval_samples_per_second": 0.143,
      "eval_steps_per_second": 0.032,
      "step": 1
    }
  ],
  "logging_steps": 1,
  "max_steps": 1,
  "num_input_tokens_seen": 10430,
  "num_train_epochs": 1,
  "save_steps": 61,
  "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": 8,
  "trial_name": null,
  "trial_params": null
}