|
|
--- |
|
|
license: apache-2.0 |
|
|
tags: |
|
|
- generated_from_trainer |
|
|
datasets: |
|
|
- common_voice |
|
|
model-index: |
|
|
- name: test-model-lg-data |
|
|
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. --> |
|
|
|
|
|
# test-model-lg-data |
|
|
|
|
|
This model is a fine-tuned version of [Monsia/test-model-lg-data](https://huggingface.co/Monsia/test-model-lg-data) on the common_voice dataset. |
|
|
It achieves the following results on the evaluation set: |
|
|
- Loss: 0.2894 |
|
|
- Wer: 0.4059 |
|
|
|
|
|
## 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: 16 |
|
|
- eval_batch_size: 8 |
|
|
- seed: 42 |
|
|
- gradient_accumulation_steps: 2 |
|
|
- total_train_batch_size: 32 |
|
|
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 |
|
|
- lr_scheduler_type: linear |
|
|
- lr_scheduler_warmup_steps: 200 |
|
|
- num_epochs: 5 |
|
|
- mixed_precision_training: Native AMP |
|
|
|
|
|
### Training results |
|
|
|
|
|
| Training Loss | Epoch | Step | Validation Loss | Wer | |
|
|
|:-------------:|:-----:|:----:|:---------------:|:------:| |
|
|
| 0.0992 | 0.67 | 100 | 0.3152 | 0.4505 | |
|
|
| 0.1249 | 1.35 | 200 | 0.4314 | 0.5483 | |
|
|
| 0.1551 | 2.03 | 300 | 0.3639 | 0.5119 | |
|
|
| 0.1153 | 2.7 | 400 | 0.3347 | 0.4718 | |
|
|
| 0.0969 | 3.38 | 500 | 0.3219 | 0.4320 | |
|
|
| 0.084 | 4.05 | 600 | 0.2899 | 0.4171 | |
|
|
| 0.077 | 4.73 | 700 | 0.2894 | 0.4059 | |
|
|
|
|
|
|
|
|
### Framework versions |
|
|
|
|
|
- Transformers 4.11.3 |
|
|
- Pytorch 1.10.0+cu113 |
|
|
- Datasets 1.13.3 |
|
|
- Tokenizers 0.10.3 |
|
|
|
