|
--- |
|
license: apache-2.0 |
|
base_model: google/byt5-small |
|
tags: |
|
- generated_from_trainer |
|
metrics: |
|
- wer |
|
model-index: |
|
- name: bn2ipa2braincells-byt5-small |
|
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. --> |
|
|
|
# bn2ipa2braincells-byt5-small |
|
|
|
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: 0.0193 |
|
- Wer: 0.0176 |
|
|
|
## 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: 0.0003 |
|
- train_batch_size: 4 |
|
- eval_batch_size: 16 |
|
- seed: 42 |
|
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 |
|
- lr_scheduler_type: linear |
|
- lr_scheduler_warmup_steps: 2000 |
|
- num_epochs: 10 |
|
|
|
### Training results |
|
|
|
| Training Loss | Epoch | Step | Validation Loss | Wer | |
|
|:-------------:|:-----:|:-----:|:---------------:|:------:| |
|
| 0.473 | 0.7 | 4000 | 0.0418 | 0.1341 | |
|
| 0.0394 | 1.39 | 8000 | 0.0281 | 0.0623 | |
|
| 0.03 | 2.09 | 12000 | 0.0258 | 0.0607 | |
|
| 0.0236 | 2.78 | 16000 | 0.0196 | 0.0476 | |
|
| 0.0195 | 3.48 | 20000 | 0.0189 | 0.0395 | |
|
| 0.0168 | 4.17 | 24000 | 0.0201 | 0.0352 | |
|
| 0.0139 | 4.87 | 28000 | 0.0174 | 0.0278 | |
|
| 0.0113 | 5.57 | 32000 | 0.0165 | 0.0271 | |
|
| 0.0093 | 6.26 | 36000 | 0.0165 | 0.0229 | |
|
| 0.008 | 6.96 | 40000 | 0.0159 | 0.0213 | |
|
| 0.0055 | 7.65 | 44000 | 0.0166 | 0.0203 | |
|
| 0.0049 | 8.35 | 48000 | 0.0178 | 0.0191 | |
|
| 0.0036 | 9.05 | 52000 | 0.0179 | 0.0183 | |
|
| 0.0023 | 9.74 | 56000 | 0.0193 | 0.0176 | |
|
|
|
|
|
### Framework versions |
|
|
|
- Transformers 4.37.0 |
|
- Pytorch 2.1.2 |
|
- Datasets 2.1.0 |
|
- Tokenizers 0.15.1 |
|
|
