evaluation_bloomz/evaluation_l2/xcopa/it/C1_or_C2?_premise/results.json

{
  "dataset_name": "xcopa",
  "dataset_config_name": "it",
  "template_name": "C1 or C2? premise, so/because\u2026",
  "evaluation": {
    "accuracy": 0.57
  },
  "arguments": "Namespace(config_name=None, dataset_config_name='it', dataset_name='xcopa', debug=False, dtype='bfloat16', max_length=2048, model_name_or_path='/gpfsssd/scratch/rech/six/commun/experiments/muennighoff/bloomckpt/176bt0/bloomz', nospace=False, output_dir='/gpfsssd/scratch/rech/six/commun/experiments/muennighoff/bloomckpt/176bt0/bloomz/evaluation', pad_to_max_length=False, per_device_eval_batch_size=8, prefixlm=False, split='so/because\u2026,validation', target_max_length=256, template_config_name='en', template_name='C1 or C2? premise', tokenizer_name=None, use_slow_tokenizer=False)"
}