---
license: mit
base_model: VietAI/vit5-base
tags:
- generated_from_trainer
metrics:
- rouge
model-index:
- name: mymodel_base_10k_sample
  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. -->

# mymodel_base_10k_sample

This model is a fine-tuned version of [VietAI/vit5-base](https://huggingface.co/VietAI/vit5-base) on an unknown dataset.
It achieves the following results on the evaluation set:
- Loss: 2.9184
- Rouge1: 0.5671
- Rouge2: 0.2484
- Rougel: 0.3595
- Rougelsum: 0.3595
- Gen Len: 41.236

## 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: 0.0002
- train_batch_size: 4
- eval_batch_size: 4
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 5
- mixed_precision_training: Native AMP

### Training results

| Training Loss | Epoch | Step  | Validation Loss | Rouge1 | Rouge2 | Rougel | Rougelsum | Gen Len |
|:-------------:|:-----:|:-----:|:---------------:|:------:|:------:|:------:|:---------:|:-------:|
| 2.5062        | 1.0   | 2000  | 2.3325          | 0.5017 | 0.2092 | 0.3239 | 0.3239    | 54.9825 |
| 1.9813        | 2.0   | 4000  | 2.2335          | 0.5247 | 0.225  | 0.3379 | 0.3379    | 48.8705 |
| 1.4287        | 3.0   | 6000  | 2.2989          | 0.5466 | 0.2348 | 0.3492 | 0.3491    | 42.505  |
| 0.9458        | 4.0   | 8000  | 2.5270          | 0.5582 | 0.2476 | 0.3568 | 0.357     | 39.268  |
| 0.5884        | 5.0   | 10000 | 2.9184          | 0.5671 | 0.2484 | 0.3595 | 0.3595    | 41.236  |


### Framework versions

- Transformers 4.36.0.dev0
- Pytorch 2.1.0+cu118
- Datasets 2.15.0
- Tokenizers 0.15.0