{
  "best_global_step": null,
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.010691103474608629,
  "eval_steps": 5,
  "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": 0.059311224489795866,
      "completions/max_length": 2048.0,
      "completions/max_terminated_length": 2043.0,
      "completions/mean_length": 712.6721801757812,
      "completions/mean_terminated_length": 628.4786376953125,
      "completions/min_length": 2.0,
      "completions/min_terminated_length": 2.0,
      "epoch": 0.010691103474608629,
      "grad_norm": 0.09828040965548591,
      "learning_rate": 0.0,
      "loss": -0.0013,
      "num_tokens": 1599382.0,
      "reward": 0.09311224520206451,
      "reward_std": 0.1442481130361557,
      "rewards/accuracy_reward/mean": 0.09311224520206451,
      "rewards/accuracy_reward/std": 0.2906823754310608,
      "rewards/format_reward/mean": 0.0,
      "rewards/format_reward/std": 0.0,
      "step": 1
    },
    {
      "epoch": 0.010691103474608629,
      "step": 1,
      "total_flos": 0.0,
      "train_loss": -0.0012948065996170044,
      "train_runtime": 601.6348,
      "train_samples_per_second": 2.606,
      "train_steps_per_second": 0.002
    }
  ],
  "logging_steps": 5,
  "max_steps": 1,
  "num_input_tokens_seen": 1599382,
  "num_train_epochs": 1,
  "save_steps": 1,
  "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
}