|
--- |
|
tags: |
|
- generated_from_keras_callback |
|
model-index: |
|
- name: electra-nli_finetuned |
|
results: [] |
|
datasets: |
|
- snli |
|
- scitail |
|
- multi_nli |
|
- alisawuffles/WANLI |
|
- pietrolesci/nli_fever |
|
- anli |
|
--- |
|
|
|
<!-- This model card has been generated automatically according to the information Keras had access to. You should |
|
probably proofread and complete it, then remove this comment. --> |
|
|
|
# electra-nli_finetuned |
|
|
|
The model base is [electra-small](google/electra-small-discriminator). |
|
It has been fine-tuned on: [snli](https://huggingface.co./datasets/snli), [scitail](https://huggingface.co./datasets/scitail), |
|
[wanli](https://huggingface.co./datasets/alisawuffles/WANLI), [mnli](https://huggingface.co./datasets/multi_nli), |
|
[fever_nli](https://huggingface.co./datasets/pietrolesci/nli_fever), [anli](https://huggingface.co./datasets/anli). |
|
|
|
|
|
|
|
## Model description |
|
|
|
More information needed |
|
|
|
## Intended uses & limitations |
|
|
|
More information needed |
|
|
|
## Training and evaluation data |
|
|
|
More information needed |
|
|
|
## Training procedure |
|
|
|
### Training hyperparameters |
|
|
|
|
|
### Training results |
|
It achieved the following accuracy during training: |
|
snli: 89.15 |
|
scitail: 90.08% |
|
wanli: 67.84% |
|
mnli: 81.95% |
|
nli_fever: 74.14% |
|
anli-r1_test: 46.60% |
|
anli-r2_test: 42.50% |
|
anli-r3_test: 43.08% |
|
|
|
|
|
### Framework versions |
|
|
|
- Transformers 4.31.0 |
|
- TensorFlow 2.12.0 |
|
- Tokenizers 0.13.3 |
