bert-base-uncased-sst2

This model is exactly the same as textattack/bert-base-uncased-SST-2 but is also converted to OpenVINO IR format. It achieves the following results on the evaluation set:

  • torch loss: 0.2819
  • torch accuracy: 0.9243
  • OpenVINO IR accuracy: 0.9243

Framework versions

  • Transformers 4.26.0
  • Pytorch 1.13.1+cu116
  • Datasets 2.8.0
  • Tokenizers 0.13.2
Downloads last month
8
Inference Providers NEW
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support

Dataset used to train yujiepan/bert-base-uncased-sst2