---
library_name: transformers
license: apache-2.0
base_model: google/byt5-small
tags:
- generated_from_trainer
metrics:
- wer
model-index:
- name: byt5-small-finetuned-yiddish-experiment-9
  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. -->

# byt5-small-finetuned-yiddish-experiment-9

This model is a fine-tuned version of [google/byt5-small](https://huggingface.co/google/byt5-small) on the None dataset.
It achieves the following results on the evaluation set:
- Loss: 0.3473
- Cer: 0.1505
- Wer: 0.4678

## 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: 1e-05
- train_batch_size: 4
- eval_batch_size: 4
- seed: 42
- gradient_accumulation_steps: 2
- total_train_batch_size: 8
- optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
- lr_scheduler_type: cosine
- lr_scheduler_warmup_steps: 600
- num_epochs: 30

### Training results

| Training Loss | Epoch   | Step | Validation Loss | Cer    | Wer    |
|:-------------:|:-------:|:----:|:---------------:|:------:|:------:|
| 10.7996       | 0.4728  | 100  | 10.9325         | 0.2905 | 0.7232 |
| 7.586         | 0.9456  | 200  | 10.5771         | 0.2698 | 0.6850 |
| 8.641         | 1.4161  | 300  | 10.0041         | 0.2570 | 0.6571 |
| 8.2901        | 1.8889  | 400  | 9.1435          | 0.2478 | 0.6396 |
| 8.076         | 2.3593  | 500  | 8.1677          | 0.2394 | 0.6277 |
| 7.8061        | 2.8322  | 600  | 7.0784          | 0.2317 | 0.6142 |
| 5.6829        | 3.3026  | 700  | 6.0549          | 0.2234 | 0.6094 |
| 5.343         | 3.7754  | 800  | 5.0819          | 0.2187 | 0.6038 |
| 4.8853        | 4.2459  | 900  | 4.2224          | 0.2157 | 0.6038 |
| 3.8875        | 4.7187  | 1000 | 3.5281          | 0.2123 | 0.5990 |
| 3.4853        | 5.1891  | 1100 | 2.8204          | 0.2095 | 0.5935 |
| 2.7984        | 5.6619  | 1200 | 2.2737          | 0.2039 | 0.5895 |
| 2.2336        | 6.1324  | 1300 | 1.7448          | 0.2016 | 0.5823 |
| 1.8465        | 6.6052  | 1400 | 1.2905          | 0.1959 | 0.5736 |
| 1.6188        | 7.0757  | 1500 | 1.1662          | 0.1945 | 0.5688 |
| 1.3051        | 7.5485  | 1600 | 1.1433          | 0.1939 | 0.5704 |
| 1.176         | 8.0189  | 1700 | 1.0655          | 0.1910 | 0.5672 |
| 1.0653        | 8.4917  | 1800 | 0.8529          | 0.1863 | 0.5561 |
| 0.8965        | 8.9645  | 1900 | 0.7841          | 0.1686 | 0.4972 |
| 0.7726        | 9.4350  | 2000 | 0.7415          | 0.1649 | 0.4956 |
| 0.7771        | 9.9078  | 2100 | 0.6933          | 0.1629 | 0.4885 |
| 0.7366        | 10.3783 | 2200 | 0.6601          | 0.1616 | 0.4861 |
| 0.6566        | 10.8511 | 2300 | 0.6124          | 0.1593 | 0.4853 |
| 0.6469        | 11.3215 | 2400 | 0.5665          | 0.1604 | 0.4829 |
| 0.6077        | 11.7943 | 2500 | 0.5210          | 0.1576 | 0.4805 |
| 0.5543        | 12.2648 | 2600 | 0.4658          | 0.1576 | 0.4781 |
| 0.5217        | 12.7376 | 2700 | 0.4372          | 0.1559 | 0.4781 |
| 0.5023        | 13.2080 | 2800 | 0.4111          | 0.1570 | 0.4805 |
| 0.4754        | 13.6809 | 2900 | 0.3967          | 0.1554 | 0.4741 |
| 0.4551        | 14.1513 | 3000 | 0.3880          | 0.1545 | 0.4726 |
| 0.4416        | 14.6241 | 3100 | 0.3800          | 0.1538 | 0.4741 |
| 0.4255        | 15.0946 | 3200 | 0.3752          | 0.1542 | 0.4749 |
| 0.4306        | 15.5674 | 3300 | 0.3724          | 0.1544 | 0.4741 |
| 0.4072        | 16.0378 | 3400 | 0.3663          | 0.1538 | 0.4741 |
| 0.4196        | 16.5106 | 3500 | 0.3606          | 0.1528 | 0.4726 |
| 0.3983        | 16.9835 | 3600 | 0.3635          | 0.1530 | 0.4694 |
| 0.3915        | 17.4539 | 3700 | 0.3605          | 0.1524 | 0.4694 |
| 0.4036        | 17.9267 | 3800 | 0.3563          | 0.1517 | 0.4686 |
| 0.3893        | 18.3972 | 3900 | 0.3558          | 0.1524 | 0.4686 |
| 0.3846        | 18.8700 | 4000 | 0.3562          | 0.1525 | 0.4678 |
| 0.3854        | 19.3404 | 4100 | 0.3530          | 0.1516 | 0.4670 |
| 0.3859        | 19.8132 | 4200 | 0.3523          | 0.1521 | 0.4678 |
| 0.3777        | 20.2837 | 4300 | 0.3516          | 0.1519 | 0.4670 |
| 0.3729        | 20.7565 | 4400 | 0.3502          | 0.1516 | 0.4678 |
| 0.3753        | 21.2270 | 4500 | 0.3497          | 0.1517 | 0.4678 |
| 0.3712        | 21.6998 | 4600 | 0.3502          | 0.1514 | 0.4686 |
| 0.3757        | 22.1702 | 4700 | 0.3487          | 0.1508 | 0.4678 |
| 0.3716        | 22.6430 | 4800 | 0.3488          | 0.1510 | 0.4678 |
| 0.369         | 23.1135 | 4900 | 0.3479          | 0.1507 | 0.4678 |
| 0.3808        | 23.5863 | 5000 | 0.3473          | 0.1505 | 0.4678 |
| 0.3696        | 24.0567 | 5100 | 0.3472          | 0.1511 | 0.4686 |
| 0.3718        | 24.5296 | 5200 | 0.3468          | 0.1508 | 0.4678 |
| 0.3651        | 25.0    | 5300 | 0.3466          | 0.1511 | 0.4686 |
| 0.3747        | 25.4728 | 5400 | 0.3467          | 0.1508 | 0.4686 |
| 0.3661        | 25.9456 | 5500 | 0.3468          | 0.1508 | 0.4686 |
| 0.3558        | 26.4161 | 5600 | 0.3472          | 0.1513 | 0.4686 |
| 0.3782        | 26.8889 | 5700 | 0.3469          | 0.1511 | 0.4686 |
| 0.3636        | 27.3593 | 5800 | 0.3467          | 0.1511 | 0.4686 |
| 0.3679        | 27.8322 | 5900 | 0.3466          | 0.1510 | 0.4678 |
| 0.3615        | 28.3026 | 6000 | 0.3465          | 0.1511 | 0.4678 |
| 0.3688        | 28.7754 | 6100 | 0.3466          | 0.1511 | 0.4678 |
| 0.3599        | 29.2459 | 6200 | 0.3466          | 0.1511 | 0.4678 |
| 0.3696        | 29.7187 | 6300 | 0.3465          | 0.1511 | 0.4678 |


### Framework versions

- Transformers 4.47.0
- Pytorch 2.5.1+cu121
- Datasets 2.14.4
- Tokenizers 0.21.0