gsm8k_5shot.json

{
  "results": {
    "gsm8k": {
      "acc": 0.1243366186504928,
      "acc_stderr": 0.00908888096202845
    }
  },
  "versions": {
    "gsm8k": 0
  },
  "config": {
    "model": "hf-causal-experimental",
    "model_args": {
      "pretrained": "/network/alexandre/research/llama2_7b_ultrachat/dense/dense_finetuning/dense_LR1e-4_E1/training",
      "trust_remote_code": true
    },
    "num_fewshot": 5,
    "batch_size": "8",
    "batch_sizes": [],
    "device": "cuda:3",
    "no_cache": true,
    "limit": null,
    "bootstrap_iters": 100000,
    "description_dict": {}
  }
}