{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.96,
  "eval_steps": 100,
  "global_step": 12,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "clip_ratio": 0.0018349495546544858,
      "completion_length": 2632.3706385294595,
      "epoch": 0.8,
      "grad_norm": 0.05368517549287073,
      "kl": 0.006453031301498413,
      "learning_rate": 1.9098300562505266e-06,
      "loss": 0.0144,
      "reward": 0.11235119577031583,
      "reward_std": 0.18164984920683006,
      "rewards/cot_length_penalty_reward": 0.0,
      "rewards/math_latex_accuracy_reward": 0.11235119577031583,
      "step": 10
    },
    {
      "clip_ratio": 0.0014721900843142066,
      "epoch": 0.96,
      "kl": 0.008948326110839844,
      "step": 12,
      "total_flos": 0.0,
      "train_loss": 0.02955327307184537,
      "train_runtime": 3696.0854,
      "train_samples_per_second": 0.108,
      "train_steps_per_second": 0.003
    }
  ],
  "logging_steps": 10,
  "max_steps": 12,
  "num_input_tokens_seen": 0,
  "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": 8,
  "trial_name": null,
  "trial_params": null
}