---
library_name: transformers
tags:
- generated_from_trainer
model-index:
- name: SwinV2_Syllable
  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. -->

# SwinV2_Syllable

This model is a fine-tuned version of [](https://huggingface.co/) on an unknown dataset.
It achieves the following results on the evaluation set:
- Loss: 1.1881
- Bleu-4: 0.2121

## 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: 5e-05
- train_batch_size: 64
- eval_batch_size: 64
- seed: 42
- gradient_accumulation_steps: 2
- total_train_batch_size: 128
- optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
- lr_scheduler_type: linear
- lr_scheduler_warmup_steps: 300
- num_epochs: 100
- mixed_precision_training: Native AMP

### Training results

| Training Loss | Epoch | Step | Validation Loss | Bleu-4 |
|:-------------:|:-----:|:----:|:---------------:|:------:|
| No log        | 1.0   | 118  | 1.4441          | 0.1228 |
| No log        | 2.0   | 236  | 1.3026          | 0.1406 |
| 2.0335        | 3.0   | 354  | 1.2238          | 0.1685 |
| 2.0335        | 4.0   | 472  | 1.1742          | 0.1841 |
| 2.0335        | 5.0   | 590  | 1.1522          | 0.1944 |
| 1.0795        | 6.0   | 708  | 1.1471          | 0.2103 |
| 1.0795        | 7.0   | 826  | 1.1434          | 0.2125 |
| 0.8075        | 8.0   | 944  | 1.1574          | 0.2108 |
| 0.8075        | 9.0   | 1062 | 1.1881          | 0.2121 |


### Framework versions

- Transformers 4.46.2
- Pytorch 2.5.1+cu121
- Datasets 3.1.0
- Tokenizers 0.20.3