|
--- |
|
tags: |
|
- generated_from_keras_callback |
|
model-index: |
|
- name: xtremedistil-l6-h256-uncased-nli |
|
results: [] |
|
datasets: |
|
- scitail |
|
- multi_nli |
|
- anli |
|
- snli |
|
- bias-amplified-splits/wanli |
|
--- |
|
|
|
<!-- 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. --> |
|
|
|
# xtremedistil-l6-h256-uncased-nli |
|
|
|
The model base is [xtremedistil-l6-h256-uncased](https://huggingface.co/microsoft/xtremedistil-l6-h256-uncased). |
|
It has been fine-tuned on: [snli](https://huggingface.co/datasets/snli), [wanli](https://huggingface.co/datasets/alisawuffles/WANLI), |
|
[mnli](https://huggingface.co/datasets/multi_nli), [anli](https://huggingface.co/datasets/anli), |
|
[scitail](https://huggingface.co/datasets/scitail) |
|
|
|
## 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 (on validation sets): |
|
SNLI: 87.90% |
|
MNLI: 82.27% |
|
ANLI_r3: 44.83% |
|
scitail: 91.02% |
|
|
|
### Framework versions |
|
|
|
- Transformers 4.31.0 |
|
- TensorFlow 2.12.0 |
|
- Datasets 2.14.4 |
|
- Tokenizers 0.13.3 |
