---
library_name: transformers
license: apache-2.0
base_model: google/mt5-base
tags:
- generated_from_trainer
metrics:
- rouge
- bleu
model-index:
- name: mt5-base-qa_v2
  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-qa_v2

This model is a fine-tuned version of [google/mt5-base](https://huggingface.co/google/mt5-base) on the None dataset.
It achieves the following results on the evaluation set:
- Loss: 1.5989
- Rouge1: 0.6780
- Rouge2: 0.3874
- Rougel: 0.6773
- Rougelsum: 0.6775
- Bleu: 0.4518
- Exact Match: 0.4502

## 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: 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 |
|:-------------:|:-----:|:-----:|:---------------:|:------:|:------:|:------:|:---------:|:------:|:-----------:|
| 0.5705        | 1.0   | 2100  | 0.8504          | 0.6538 | 0.3810 | 0.6534 | 0.6539    | 0.4289 | 0.4369      |
| 0.2728        | 2.0   | 4200  | 1.0248          | 0.6644 | 0.3734 | 0.6637 | 0.6646    | 0.4145 | 0.4360      |
| 0.1418        | 3.0   | 6300  | 1.3020          | 0.6664 | 0.3812 | 0.6657 | 0.6661    | 0.4362 | 0.4269      |
| 0.0834        | 4.0   | 8400  | 1.4760          | 0.6739 | 0.3790 | 0.6731 | 0.6737    | 0.4233 | 0.4431      |
| 0.0568        | 5.0   | 10500 | 1.5989          | 0.6780 | 0.3874 | 0.6773 | 0.6775    | 0.4518 | 0.4502      |


### Framework versions

- Transformers 4.45.2
- Pytorch 2.4.0a0+f70bd71a48.nv24.06
- Datasets 3.0.1
- Tokenizers 0.20.1