---
tags:
- generated_from_trainer
metrics:
- accuracy
model-index:
- name: cuenb2-mnli-negnli
  results: []
---

<!-- 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. -->

# cuenb2-mnli-negnli

This model is a fine-tuned version of [cuenb](https://huggingface.co/joey234/cuenb) on the GLUE MNLI dataset and the [MNLI subset in NegNLI](https://github.com/mosharafhossain/negation-and-nli/tree/master/data/new_benchmarks/processed_for_run/MNLI).
It achieves the following results on the evaluation set:
- Loss: 0.7677
- Accuracy: 0.8533

## Model description

More information needed

## 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: 8
- eval_batch_size: 8
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 5.0

### Training results



### Framework versions

- Transformers 4.21.0.dev0
- Pytorch 1.8.0
- Datasets 1.18.3
- Tokenizers 0.12.1