evaluation_bloomz/evaluation_xwinostorycopamt/xcopa/ta/C1_or_C2?_premise_tamt/results.json

{
  "dataset_name": "xcopa",
  "dataset_config_name": "ta",
  "template_name": "C1 or C2? premise_tamt",
  "evaluation": {
    "accuracy": 0.6
  },
  "arguments": "Namespace(config_name=None, dataset_config_name='ta', dataset_name='xcopa', debug=False, dtype='bfloat16', max_length=2048, model_name_or_path='/gpfsscratch/rech/six/commun/experiments/muennighoff/bloomckpt/176bt0/bloomz', output_dir='/gpfsscratch/rech/six/commun/experiments/muennighoff/bloomckpt/176bt0/bloomz/evaluation', pad_to_max_length=False, per_device_eval_batch_size=8, prefixlm=False, split='validation', target_max_length=256, template_config_name='ta', template_name='C1 or C2? premise_tamt', tokenizer_name=None, use_slow_tokenizer=False)"
}