|
--- |
|
language: |
|
- bn |
|
license: apache-2.0 |
|
base_model: bigscience/mt0-small |
|
tags: |
|
- generated_from_trainer |
|
metrics: |
|
- wer |
|
model-index: |
|
- name: mt0-small-bn-to-ipa-v2 |
|
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. --> |
|
|
|
# mt0-small-bn-to-ipa-v2 |
|
|
|
This model is a fine-tuned version of [bigscience/mt0-small](https://huggingface.co/bigscience/mt0-small) on the None dataset. |
|
It achieves the following results on the evaluation set: |
|
- Loss: 0.0551 |
|
- Wer: 0.0327 |
|
|
|
## 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: 0.001 |
|
- train_batch_size: 16 |
|
- eval_batch_size: 32 |
|
- 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: 20 |
|
|
|
### Training results |
|
|
|
| Training Loss | Epoch | Step | Validation Loss | Wer | |
|
|:-------------:|:-----:|:-----:|:---------------:|:------:| |
|
| 0.079 | 3.64 | 4000 | 0.0600 | 0.0495 | |
|
| 0.0602 | 7.27 | 8000 | 0.0563 | 0.0434 | |
|
| 0.042 | 10.91 | 12000 | 0.0539 | 0.0378 | |
|
| 0.0292 | 14.55 | 16000 | 0.0542 | 0.0346 | |
|
| 0.0212 | 18.18 | 20000 | 0.0551 | 0.0327 | |
|
|
|
|
|
### Framework versions |
|
|
|
- Transformers 4.34.1 |
|
- Pytorch 2.0.0 |
|
- Datasets 2.1.0 |
|
- Tokenizers 0.14.1 |
|
|