rttl's picture
Update README.md
b62ecbb
---
license: apache-2.0
datasets:
- yelp_polarity
language:
- en
model-index:
- name: rttl-ai/bert-base-uncased-polarity
results:
- task:
type: text classification
name: binary_classification
dataset:
type: yelp_polarity
name: yelp_polarity
config: default
split: test
metrics:
- type: accuracy
value: 0.98
name: Accuracy
---
## Model Details
**Model Description:** This model is a fine-tune checkpoint of [bert-base-uncased](https://huggingface.co/bert-base-uncased), fine-tuned on yelp reviews.
- **Developed by:** rttl-ai
- **Model Type:** Text Classification
- **Language(s):** English
- **License:** Apache-2.0
- **Resources for more information:**
- The model was pre-trained with task-adaptive pre-training [TAPT](https://arxiv.org/pdf/2004.10964.pdf) with an increased masking rate, no corruption strategy, and using WWM, following [this paper](https://aclanthology.org/2023.eacl-main.217.pdf)
- pre-trained on yelp reviews
- fine-tuned on yelp reviews for binary class text classification