{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.002488722974023954,
  "eval_steps": 500,
  "global_step": 2,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "completion_length": 389.40849685668945,
      "epoch": 0.002488722974023954,
      "grad_norm": 0.11305962966298544,
      "kl": 0.0,
      "learning_rate": 0.0,
      "loss": -0.0,
      "reward": 0.5111607313156128,
      "reward_std": 0.5251041390001774,
      "rewards/correctness": 0.04464285960420966,
      "rewards/format": 0.466517873108387,
      "step": 2
    },
    {
      "epoch": 0.002488722974023954,
      "step": 2,
      "total_flos": 0.0,
      "train_loss": -2.6609217051998257e-09,
      "train_runtime": 213.9149,
      "train_samples_per_second": 0.262,
      "train_steps_per_second": 0.005
    }
  ],
  "logging_steps": 2,
  "max_steps": 1,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 25,
  "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": 1,
  "trial_name": null,
  "trial_params": null
}