|
--- |
|
tags: |
|
- generated_from_trainer |
|
model-index: |
|
- name: '' |
|
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. --> |
|
|
|
# |
|
|
|
This model was trained from scratch on the None dataset. |
|
It achieves the following results on the evaluation set: |
|
- Loss: 0.5575 |
|
- Wer: 0.5219 |
|
|
|
## 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: 8 |
|
- eval_batch_size: 8 |
|
- seed: 42 |
|
- gradient_accumulation_steps: 8 |
|
- total_train_batch_size: 64 |
|
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 |
|
- lr_scheduler_type: linear |
|
- lr_scheduler_warmup_steps: 400 |
|
- num_epochs: 5.0 |
|
- mixed_precision_training: Native AMP |
|
|
|
### Training results |
|
|
|
| Training Loss | Epoch | Step | Validation Loss | Wer | |
|
|:-------------:|:-----:|:----:|:---------------:|:------:| |
|
| 2.3036 | 0.51 | 400 | 4.2199 | 0.9500 | |
|
| 2.836 | 1.02 | 800 | 2.7748 | 1.2758 | |
|
| 2.7021 | 1.53 | 1200 | 2.6211 | 1.1725 | |
|
| 2.2322 | 2.04 | 1600 | 2.5714 | 1.1042 | |
|
| 2.1435 | 2.55 | 2000 | 2.4205 | 1.0093 | |
|
| 1.1205 | 3.06 | 2400 | 2.7612 | 0.9098 | |
|
| 0.7821 | 3.57 | 2800 | 2.2900 | 0.8478 | |
|
| 1.0018 | 4.08 | 3200 | 0.7970 | 0.6275 | |
|
| 0.6312 | 4.59 | 3600 | 0.5575 | 0.5219 | |
|
|
|
|
|
### Framework versions |
|
|
|
- Transformers 4.17.0.dev0 |
|
- Pytorch 1.10.0+cu113 |
|
- Datasets 1.18.1 |
|
- Tokenizers 0.11.0 |
|
|