{
  "best_global_step": null,
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 1.0,
  "eval_steps": 500,
  "global_step": 27,
  "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,
      "completion_length": 22.6125,
      "completions/clipped_ratio": 0.0,
      "completions/max_length": 34.5,
      "completions/max_terminated_length": 34.5,
      "completions/mean_length": 22.6125,
      "completions/mean_terminated_length": 22.6125,
      "completions/min_length": 20.0,
      "completions/min_terminated_length": 20.0,
      "epoch": 0.37037037037037035,
      "frac_reward_zero_std": 1.0,
      "grad_norm": 0.0015931904781609774,
      "kl": 7.081240113127052e-06,
      "learning_rate": 3.7500000000000005e-06,
      "loss": 0.0,
      "num_tokens": 17129.0,
      "reward": 0.07599999867379666,
      "reward_std": 0.0,
      "rewards/reward_fn/mean": 0.07599999867379666,
      "rewards/reward_fn/std": 0.05559033881872892,
      "step": 10
    },
    {
      "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,
      "completion_length": 21.9875,
      "completions/clipped_ratio": 0.0,
      "completions/max_length": 29.1,
      "completions/max_terminated_length": 29.1,
      "completions/mean_length": 21.9875,
      "completions/mean_terminated_length": 21.9875,
      "completions/min_length": 19.6,
      "completions/min_terminated_length": 19.6,
      "epoch": 0.7407407407407407,
      "frac_reward_zero_std": 1.0,
      "grad_norm": 0.0021628099493682384,
      "kl": 3.2263426703593723e-06,
      "learning_rate": 1.6666666666666667e-06,
      "loss": 0.0,
      "num_tokens": 34236.0,
      "reward": 0.17839999608695506,
      "reward_std": 0.0,
      "rewards/reward_fn/mean": 0.17839999608695506,
      "rewards/reward_fn/std": 0.10690449737012386,
      "step": 20
    }
  ],
  "logging_steps": 10,
  "max_steps": 27,
  "num_input_tokens_seen": 46206,
  "num_train_epochs": 1,
  "save_steps": 50,
  "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": 2,
  "trial_name": null,
  "trial_params": null
}