{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 1.9230769230769231,
  "eval_steps": 100,
  "global_step": 6,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "clip_ratio": 0.0,
      "completion_length": 390.85,
      "epoch": 1.6153846153846154,
      "grad_norm": 1.6735994815826416,
      "kl": 0.005230331420898437,
      "learning_rate": 1.9098300562505264e-07,
      "loss": -0.0077,
      "reward": 0.3171875,
      "reward_std": 0.17235727477818727,
      "rewards/accuracy_reward": 0.04375,
      "rewards/format_reward": 0.0,
      "rewards/tag_count_reward": 0.2734375,
      "step": 5
    },
    {
      "epoch": 1.9230769230769231,
      "step": 6,
      "total_flos": 0.0,
      "train_loss": 0.0,
      "train_runtime": 1.7279,
      "train_samples_per_second": 115.747,
      "train_steps_per_second": 3.472
    }
  ],
  "logging_steps": 5,
  "max_steps": 6,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 2,
  "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": 2,
  "trial_name": null,
  "trial_params": null
}