---
license: apache-2.0
base_model: google/mt5-small
tags:
- generated_from_trainer
metrics:
- accuracy
model-index:
- name: mt5-small-task1-dataset4
  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-small-task1-dataset4

This model is a fine-tuned version of [google/mt5-small](https://huggingface.co/google/mt5-small) on the None dataset.
It achieves the following results on the evaluation set:
- Loss: 1.3594
- Accuracy: 0.086

## 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: 5.6e-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: 12

### Training results

| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|:-------------:|:-----:|:----:|:---------------:|:--------:|
| 7.9758        | 1.0   | 250  | 2.3199          | 0.024    |
| 2.7257        | 2.0   | 500  | 1.9097          | 0.016    |
| 2.2688        | 3.0   | 750  | 1.7108          | 0.044    |
| 1.9809        | 4.0   | 1000 | 1.5786          | 0.062    |
| 1.8098        | 5.0   | 1250 | 1.5045          | 0.064    |
| 1.6944        | 6.0   | 1500 | 1.4686          | 0.066    |
| 1.6063        | 7.0   | 1750 | 1.4260          | 0.08     |
| 1.5417        | 8.0   | 2000 | 1.3970          | 0.086    |
| 1.4947        | 9.0   | 2250 | 1.3749          | 0.086    |
| 1.4704        | 10.0  | 2500 | 1.3714          | 0.086    |
| 1.44          | 11.0  | 2750 | 1.3672          | 0.088    |
| 1.4337        | 12.0  | 3000 | 1.3594          | 0.086    |


### Framework versions

- Transformers 4.35.2
- Pytorch 2.1.0+cu121
- Datasets 2.15.0
- Tokenizers 0.15.0