{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.7619047619047619,
  "eval_steps": 500,
  "global_step": 2,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "clip_ratio": 0.0,
      "completion_length": 999.6105346679688,
      "epoch": 0.38095238095238093,
      "grad_norm": 154.43353271484375,
      "kl": 0.0,
      "learning_rate": 3e-06,
      "loss": -0.019,
      "reward": 0.7500000298023224,
      "reward_std": 0.3680399917066097,
      "rewards/accuracy_reward": 0.031250001629814506,
      "rewards/format_reward": 0.7187500298023224,
      "step": 1
    },
    {
      "clip_ratio": 0.0,
      "completion_length": 1004.9062957763672,
      "epoch": 0.7619047619047619,
      "kl": 0.0,
      "reward": 0.7745536118745804,
      "reward_std": 0.36208853125572205,
      "rewards/accuracy_reward": 0.039062502793967724,
      "rewards/format_reward": 0.7354911044239998,
      "step": 2,
      "total_flos": 0.0,
      "train_loss": -0.017851791344583035,
      "train_runtime": 640.8452,
      "train_samples_per_second": 0.524,
      "train_steps_per_second": 0.003
    }
  ],
  "logging_steps": 5,
  "max_steps": 2,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 500,
  "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": 16,
  "trial_name": null,
  "trial_params": null
}