---
license: apache-2.0
tags:
- generated_from_trainer
datasets:
- glue
metrics:
- accuracy
model-index:
- name: glue-mnli
  results:
  - task:
      name: Text Classification
      type: text-classification
    dataset:
      name: glue
      type: glue
      config: mnli
      split: train
      args: mnli
    metrics:
    - name: Accuracy
      type: accuracy
      value: 0.6772287315333673
---

<!-- 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. -->

# glue-mnli

This model is a fine-tuned version of [distilbert-base-uncased](https://huggingface.co/distilbert-base-uncased) on the glue dataset.
It achieves the following results on the evaluation set:
- Loss: 0.8003
- Accuracy: 0.6772

## 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: 16
- eval_batch_size: 16
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 3

### Training results

| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|:-------------:|:-----:|:----:|:---------------:|:--------:|
| 0.9378        | 1.0   | 625  | 0.7896          | 0.6585   |
| 0.7086        | 2.0   | 1250 | 0.7850          | 0.6712   |
| 0.5758        | 3.0   | 1875 | 0.8003          | 0.6772   |


### Framework versions

- Transformers 4.21.2
- Pytorch 1.12.1+cu113
- Datasets 2.4.0
- Tokenizers 0.12.1