metadata
license: apache-2.0
base_model: google/byt5-small
tags:
- generated_from_trainer
metrics:
- wer
model-index:
- name: bn2ipa2braincells-byt5-small
results: []
bn2ipa2braincells-byt5-small
This model is a fine-tuned version of 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