---
license: apache-2.0
base_model: google/mt5-small
tags:
- generated_from_trainer
metrics:
- accuracy
model-index:
- name: mt5-small-task3-dataset3
  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-task3-dataset3

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: 1.4565
- Accuracy: 0.124
- Mse: 2.0170
- Log-distance: 0.7037
- S Score: 0.4680

## 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: 15

### Training results

| Training Loss | Epoch | Step | Validation Loss | Accuracy | Mse    | Log-distance | S Score |
|:-------------:|:-----:|:----:|:---------------:|:--------:|:------:|:------------:|:-------:|
| 3.3423        | 1.0   | 250  | 1.5914          | 0.074    | 2.3687 | 0.6693       | 0.4992  |
| 2.3267        | 2.0   | 500  | 1.6213          | 0.102    | 2.6627 | 0.7153       | 0.4836  |
| 1.8968        | 3.0   | 750  | 1.4707          | 0.118    | 2.0674 | 0.7576       | 0.4228  |
| 1.7414        | 4.0   | 1000 | 1.4367          | 0.124    | 2.0643 | 0.7534       | 0.4236  |
| 1.6639        | 5.0   | 1250 | 1.4493          | 0.12     | 2.0268 | 0.7079       | 0.4624  |
| 1.6088        | 6.0   | 1500 | 1.4538          | 0.116    | 1.9955 | 0.6762       | 0.4924  |
| 1.5823        | 7.0   | 1750 | 1.4565          | 0.124    | 2.0170 | 0.7037       | 0.4680  |


### Framework versions

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