|
--- |
|
license: mit |
|
tags: |
|
- generated_from_trainer |
|
datasets: |
|
- snli |
|
model-index: |
|
- name: DeBERTa-finetuned-SNLI2 |
|
results: [] |
|
metrics: |
|
- accuracy |
|
library_name: transformers |
|
--- |
|
|
|
<!-- This model card has been generated automatically according to the information the Trainer had access to. You |
|
should probably proofread and complete it, then remove this comment. --> |
|
|
|
# DeBERTa-finetuned-SNLI2 |
|
|
|
This model is a fine-tuned version of [gyeoldere/test_trainer](https://huggingface.co/gyeoldere/test_trainer) on the snli dataset. |
|
|
|
Test_trainer model is a fine-tuned version of [microsoft/deberta-base](https://huggingface.co/microsoft/deberta-base) on the snli dataset. |
|
|
|
This model achieves the following results on the evaluation set: |
|
- NLI accuracy : 0.86 |
|
- MLM accuracy : 0.68 |
|
|
|
|
|
## Model description |
|
|
|
This model fine-tuned to perform 2 tasks simultaneously; NLI task and MLM task. |
|
|
|
Output vector of DeBERTa processed through two different fc layer to predict. |
|
I used layer structure introduced in BERT paper, which is implemented on huggingface transformers; DebertaForTokenClassification and DebertaForMaskedLM. |
|
[https://huggingface.co/docs/transformers/index] |
|
|
|
BinaryCrossEntrophyLoss are used for each class, and two losses are added to obtain final loss |
|
final_loss = MLM_loss + NLI_loss |
|
|
|
## Intended uses & limitations |
|
|
|
More information needed |
|
|
|
## Training and evaluation data |
|
|
|
More information needed |
|
|
|
## Training procedure |
|
|
|
### Training hyperparameters |
|
|
|
The following hyperparameters were used during training: |
|
- learning_rate: 2e-05 |
|
- train_batch_size: 128 |
|
- eval_batch_size: 128 |
|
- seed: 42 |
|
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 |
|
- lr_scheduler_type: linear |
|
- num_epochs: 3 |
|
|
|
### Training results |
|
|
|
|
|
|
|
### Framework versions |
|
|
|
- Transformers 4.26.0 |
|
- Pytorch 1.13.1+cu116 |
|
- Datasets 2.9.0 |
|
- Tokenizers 0.13.2 |