evaluation_val/mwsc/what-think/results.json

{
  "dataset_name": "mwsc",
  "dataset_config_name": null,
  "template_name": "what-think",
  "evaluation": {
    "accuracy": 0.6951219512195121
  },
  "arguments": "Namespace(config_name=None, dataset_config_name=None, dataset_name='mwsc', debug=False, dtype='float16', max_length=2048, model_name_or_path='/gpfsscratch/rech/six/commun/experiments/muennighoff/bloomckpt/6b3t0/tr13f-6b3-ml-t0-lmtoks341b-t0toks4b2-xp3capmixnewcodelonglossseq', output_dir='/gpfsscratch/rech/six/commun/experiments/muennighoff/bloomckpt/6b3t0/tr13f-6b3-ml-t0-lmtoks341b-t0toks4b2-xp3capmixnewcodelonglossseq/evaluation', pad_to_max_length=False, per_device_eval_batch_size=8, prefixlm=False, split='validation', target_max_length=256, template_config_name=None, template_name='what-think', tokenizer_name=None, use_slow_tokenizer=False)"
}