---
library_name: transformers
license: mit
base_model: FiveC/BartTay
tags:
- generated_from_trainer
metrics:
- sacrebleu
model-index:
- name: ViTay-SwitchOut
  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. -->

# ViTay-SwitchOut

This model is a fine-tuned version of [FiveC/BartTay](https://huggingface.co/FiveC/BartTay) on an unknown dataset.
It achieves the following results on the evaluation set:
- Loss: 0.1335
- Sacrebleu: 22.1613

## 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: Use OptimizerNames.ADAMW_TORCH_FUSED with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
- lr_scheduler_type: linear
- num_epochs: 3
- mixed_precision_training: Native AMP

### Training results

| Training Loss | Epoch | Step  | Validation Loss | Sacrebleu |
|:-------------:|:-----:|:-----:|:---------------:|:---------:|
| 0.2165        | 1.0   | 4905  | 0.1527          | 17.1994   |
| 0.1949        | 2.0   | 9810  | 0.1373          | 20.6914   |
| 0.1822        | 3.0   | 14715 | 0.1335          | 22.1613   |


### Framework versions

- Transformers 4.57.3
- Pytorch 2.9.0+cu126
- Datasets 4.0.0
- Tokenizers 0.22.1