---
language:
- en
base_model: google-t5/t5-base
tags:
- generated_from_trainer
datasets:
- glue
metrics:
- matthews_correlation
model-index:
- name: CoLA
  results:
  - task:
      name: Text Classification
      type: text-classification
    dataset:
      name: GLUE COLA
      type: glue
      args: cola
    metrics:
    - name: Matthews Correlation
      type: matthews_correlation
      value: 0.5835913370480271
---

<!-- 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. -->

# CoLA

This model is a fine-tuned version of [google-t5/t5-base](https://huggingface.co/google-t5/t5-base) on the GLUE COLA dataset.
It achieves the following results on the evaluation set:
- Loss: 0.7745
- Matthews Correlation: 0.5836

## 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: 5e-05
- train_batch_size: 32
- eval_batch_size: 8
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 10.0

### Training results

| Training Loss | Epoch | Step | Validation Loss | Matthews Correlation |
|:-------------:|:-----:|:----:|:---------------:|:--------------------:|
| No log        | 1.0   | 268  | 0.4736          | 0.4885               |
| 0.4668        | 2.0   | 536  | 0.4988          | 0.5416               |
| 0.4668        | 3.0   | 804  | 0.5234          | 0.5495               |
| 0.293         | 4.0   | 1072 | 0.6834          | 0.5435               |
| 0.293         | 5.0   | 1340 | 0.6669          | 0.5656               |
| 0.2049        | 6.0   | 1608 | 0.6631          | 0.5807               |
| 0.2049        | 7.0   | 1876 | 0.7745          | 0.5836               |
| 0.1511        | 8.0   | 2144 | 0.8352          | 0.5781               |
| 0.1511        | 9.0   | 2412 | 0.8336          | 0.5676               |
| 0.128         | 10.0  | 2680 | 0.8593          | 0.5624               |


### Framework versions

- Transformers 4.43.3
- Pytorch 1.11.0+cu113
- Datasets 2.20.0
- Tokenizers 0.19.1