---
language:
- en
license: apache-2.0
datasets:
- glue
metrics:
- accuracy
model-index:
- name: t5-base-finetuned-qnli
  results:
  - task:
      name: Text Classification
      type: text-classification
    dataset:
      name: GLUE QNLI
      type: glue
      args: qnli
    metrics:
    - name: Accuracy
      type: accuracy
      value: 0.9123
---


# T5-base-finetuned-qnli

<!-- Provide a quick summary of what the model is/does. -->

This model is T5 fine-tuned on GLUE QNLI dataset. It acheives the following results on the validation set
- Accuracy: 0.9123


## Model Details
T5 is an encoder-decoder model pre-trained on a multi-task mixture of unsupervised and supervised tasks and for which each task is converted into a text-to-text format. 

## Training procedure

### Tokenization
Since, T5 is a text-to-text model, the labels of the dataset are converted as follows:
For each example, a sentence as been formed as **"qnli question: " + qnli_question + "sentence: " + qnli_sentence** and fed to the tokenizer to get the **input_ids** and **attention_mask**.
For each label, label is choosen as **"equivalent"** if label is 1, else label is **"not_equivalent"** and tokenized to get **input_ids** and **attention_mask** . 
  During training, these inputs_ids having **pad** token are replaced with -100 so that loss is not calculated for them. Then these input ids are given as labels, and above attention_mask of labels
  is given as decoder attention mask.

### Training hyperparameters

The following hyperparameters were used during training:
- learning_rate: 3e-4
- train_batch_size: 8
- eval_batch_size: 8
- seed: 42
- optimizer: epsilon=1e-08
- num_epochs: 3.0

### Training results


|Epoch | Training Loss | Validation Accuracy |
|:----:|:-------------:|:-------------------:|
|   1  |    0.0571     |  0.8973             |
|   2  |    0.0329     |  0.9068              |
|   3  |    0.0133     |  0.9123              |