---
license: mit
base_model: VietAI/vit5-base
tags:
- generated_from_trainer
metrics:
- rouge
model-index:
- name: mymodel_base_10k_sample_2e5_batchsize32
  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_2e5_batchsize32

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: 1.8017
- Rouge1: 0.5626
- Rouge2: 0.2589
- Rougel: 0.3631
- Rougelsum: 0.3633
- Gen Len: 38.8535

## 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: 2e-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: 3
- mixed_precision_training: Native AMP

### Training results

| Training Loss | Epoch | Step | Validation Loss | Rouge1 | Rouge2 | Rougel | Rougelsum | Gen Len |
|:-------------:|:-----:|:----:|:---------------:|:------:|:------:|:------:|:---------:|:-------:|
| 2.0869        | 1.0   | 500  | 1.8225          | 0.5506 | 0.2479 | 0.3552 | 0.3553    | 40.6745 |
| 1.8071        | 2.0   | 1000 | 1.8038          | 0.5589 | 0.2523 | 0.3585 | 0.3586    | 39.335  |
| 1.6991        | 3.0   | 1500 | 1.8017          | 0.5626 | 0.2589 | 0.3631 | 0.3633    | 38.8535 |


### Framework versions

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