---
license: apache-2.0
base_model: google/mt5-base
tags:
- generated_from_trainer
datasets:
- tiagoblima/qg_squad_v1_pt
model-index:
- name: mt5_base-qg-ap-nopeft
  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. -->

# mt5_base-qg-ap-nopeft

This model is a fine-tuned version of [google/mt5-base](https://huggingface.co/google/mt5-base) on the tiagoblima/qg_squad_v1_pt dataset.
It achieves the following results on the evaluation set:
- Loss: 1.5832

## 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: 8
- total_train_batch_size: 32
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-06
- lr_scheduler_type: linear
- num_epochs: 5.0

### Training results

| Training Loss | Epoch | Step | Validation Loss |
|:-------------:|:-----:|:----:|:---------------:|
| 1.8875        | 1.0   | 1615 | 1.6600          |
| 1.7353        | 2.0   | 3231 | 1.6089          |
| 1.6382        | 3.0   | 4847 | 1.5926          |
| 1.5789        | 4.0   | 6463 | 1.5868          |
| 1.5343        | 5.0   | 8075 | 1.5832          |


### Framework versions

- Transformers 4.35.2
- Pytorch 2.0.0
- Datasets 2.15.0
- Tokenizers 0.15.0