{
  "best_global_step": null,
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.004210526315789474,
  "eval_steps": 500,
  "global_step": 1,
  "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": 0.125,
      "completions/max_length": 256.0,
      "completions/max_terminated_length": 128.0,
      "completions/mean_length": 71.8125,
      "completions/mean_terminated_length": 45.500003814697266,
      "completions/min_length": 2.0,
      "completions/min_terminated_length": 2.0,
      "epoch": 0.004210526315789474,
      "frac_reward_zero_std": 0.25,
      "grad_norm": 1.3116257190704346,
      "kl": 0.0,
      "learning_rate": 0.0,
      "loss": -0.1258,
      "num_tokens": 2805.0,
      "reward": 0.565625011920929,
      "reward_std": 0.27519428730010986,
      "rewards/reward_func/mean": 0.565625011920929,
      "rewards/reward_func/std": 0.4510427713394165,
      "step": 1
    }
  ],
  "logging_steps": 1,
  "max_steps": 1,
  "num_input_tokens_seen": 2805,
  "num_train_epochs": 1,
  "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": 4,
  "trial_name": null,
  "trial_params": null
}