{
  "best_global_step": null,
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.5714285714285714,
  "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": -3.0,
      "completions/max_length": 602.0,
      "completions/max_terminated_length": 602.0,
      "completions/mean_length": 419.15625,
      "completions/mean_terminated_length": 419.15625,
      "completions/min_length": 225.0,
      "completions/min_terminated_length": 225.0,
      "epoch": 0.5714285714285714,
      "frac_reward_zero_std": 0.53125,
      "grad_norm": 0.02846240997314453,
      "kl": 0.0002314150333404541,
      "learning_rate": 0.0,
      "loss": 0.0,
      "num_tokens": 59828.0,
      "reward": 2.78125,
      "reward_std": 0.5303300619125366,
      "rewards/format_reward/mean": 0.0,
      "rewards/format_reward/std": 0.0,
      "rewards/unittest_reward/mean": 2.78125,
      "rewards/unittest_reward/std": 2.339914321899414,
      "step": 1
    },
    {
      "epoch": 0.5714285714285714,
      "step": 1,
      "total_flos": 0.0,
      "train_loss": 9.257459169020876e-06,
      "train_runtime": 152.6909,
      "train_samples_per_second": 0.36,
      "train_steps_per_second": 0.013
    }
  ],
  "logging_steps": 1,
  "max_steps": 2,
  "num_input_tokens_seen": 59828,
  "num_train_epochs": 1,
  "save_steps": 50,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": false,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 0.0,
  "train_batch_size": 1,
  "trial_name": null,
  "trial_params": null
}