---
library_name: transformers
license: apache-2.0
base_model: google/mt5-small
tags:
- generated_from_trainer
metrics:
- rouge
- bleu
model-index:
- name: mt5-small-qa_v1
  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-qa_v1

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: 1.6111
- Rouge1: 0.5618
- Rouge2: 0.3184
- Rougel: 0.5619
- Rougelsum: 0.5615
- Bleu: 0.3653
- Exact Match: 0.3573

## 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: 0.0003
- train_batch_size: 8
- eval_batch_size: 8
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 5

### Training results

| Training Loss | Epoch | Step  | Validation Loss | Rouge1 | Rouge2 | Rougel | Rougelsum | Bleu   | Exact Match |
|:-------------:|:-----:|:-----:|:---------------:|:------:|:------:|:------:|:---------:|:------:|:-----------:|
| 1.1338        | 1.0   | 2000  | 1.3124          | 0.4546 | 0.2541 | 0.4547 | 0.4545    | 0.2867 | 0.273       |
| 0.5454        | 2.0   | 4000  | 1.3752          | 0.5488 | 0.3100 | 0.5483 | 0.5481    | 0.3488 | 0.3362      |
| 0.3365        | 3.0   | 6000  | 1.4375          | 0.5533 | 0.3113 | 0.5535 | 0.5530    | 0.3482 | 0.3478      |
| 0.1999        | 4.0   | 8000  | 1.5008          | 0.5533 | 0.3111 | 0.5530 | 0.5528    | 0.3529 | 0.3367      |
| 0.1432        | 5.0   | 10000 | 1.6111          | 0.5618 | 0.3184 | 0.5619 | 0.5615    | 0.3653 | 0.3573      |


### Framework versions

- Transformers 4.45.1
- Pytorch 2.4.0
- Datasets 3.0.1
- Tokenizers 0.20.0