---
license: apache-2.0
tags:
- generated_from_trainer
datasets:
- t5_squad
model-index:
- name: t5-simple-qg-eng
  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. -->

# t5-simple-qg-eng

This model is a fine-tuned version of [t5-base](https://huggingface.co/t5-base) on the t5_squad dataset.
It achieves the following results on the evaluation set:
- Loss: 1.5682

## 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: 0.0001
- train_batch_size: 4
- eval_batch_size: 4
- seed: 42
- gradient_accumulation_steps: 16
- total_train_batch_size: 64
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 7

### Training results

| Training Loss | Epoch | Step | Validation Loss |
|:-------------:|:-----:|:----:|:---------------:|
| 2.584         | 0.34  | 100  | 1.9108          |
| 1.9664        | 0.68  | 200  | 1.7275          |
| 1.8466        | 1.02  | 300  | 1.6634          |
| 1.7412        | 1.36  | 400  | 1.6383          |
| 1.7134        | 1.69  | 500  | 1.6202          |
| 1.694         | 2.03  | 600  | 1.6049          |
| 1.6297        | 2.37  | 700  | 1.5975          |
| 1.6261        | 2.71  | 800  | 1.5932          |
| 1.6149        | 3.05  | 900  | 1.5875          |
| 1.569         | 3.39  | 1000 | 1.5893          |
| 1.5683        | 3.73  | 1100 | 1.5740          |
| 1.5569        | 4.07  | 1200 | 1.5785          |
| 1.5331        | 4.41  | 1300 | 1.5733          |
| 1.5216        | 4.75  | 1400 | 1.5705          |
| 1.5226        | 5.08  | 1500 | 1.5735          |
| 1.4933        | 5.42  | 1600 | 1.5703          |
| 1.4845        | 5.76  | 1700 | 1.5683          |
| 1.5077        | 6.1   | 1800 | 1.5684          |
| 1.4749        | 6.44  | 1900 | 1.5727          |
| 1.4757        | 6.78  | 2000 | 1.5682          |


### Framework versions

- Transformers 4.26.1
- Pytorch 1.13.1+cu116
- Datasets 2.10.1
- Tokenizers 0.13.2