|
--- |
|
license: apache-2.0 |
|
base_model: facebook/wav2vec2-base |
|
tags: |
|
- generated_from_trainer |
|
metrics: |
|
- accuracy |
|
model-index: |
|
- name: mydata-sentence |
|
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. --> |
|
|
|
# mydata-sentence |
|
|
|
This model is a fine-tuned version of [facebook/wav2vec2-base](https://huggingface.co/facebook/wav2vec2-base) on an unknown dataset. |
|
It achieves the following results on the evaluation set: |
|
- Loss: 0.7519 |
|
- Accuracy: 0.4615 |
|
|
|
## 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: 3e-05 |
|
- train_batch_size: 16 |
|
- 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_ratio: 0.1 |
|
- num_epochs: 15 |
|
|
|
### Training results |
|
|
|
| Training Loss | Epoch | Step | Validation Loss | Accuracy | |
|
|:-------------:|:-----:|:----:|:---------------:|:--------:| |
|
| 0.7048 | 1.0 | 4 | 0.7079 | 0.3846 | |
|
| 0.6478 | 2.0 | 8 | 0.7239 | 0.3846 | |
|
| 0.7242 | 3.0 | 12 | 0.7464 | 0.3846 | |
|
| 0.5978 | 4.0 | 16 | 0.7460 | 0.4615 | |
|
| 0.7061 | 5.0 | 20 | 0.7460 | 0.4615 | |
|
| 0.7089 | 6.0 | 24 | 0.7377 | 0.4615 | |
|
| 0.5751 | 7.0 | 28 | 0.7324 | 0.4615 | |
|
| 0.5799 | 8.0 | 32 | 0.7365 | 0.4615 | |
|
| 0.563 | 9.0 | 36 | 0.7477 | 0.4615 | |
|
| 0.555 | 10.0 | 40 | 0.7562 | 0.4615 | |
|
| 0.5227 | 11.0 | 44 | 0.7632 | 0.4615 | |
|
| 0.6701 | 12.0 | 48 | 0.7590 | 0.4615 | |
|
| 0.5219 | 13.0 | 52 | 0.7540 | 0.4615 | |
|
| 0.5003 | 14.0 | 56 | 0.7526 | 0.4615 | |
|
| 0.488 | 15.0 | 60 | 0.7519 | 0.4615 | |
|
|
|
|
|
### Framework versions |
|
|
|
- Transformers 4.37.2 |
|
- Pytorch 2.2.0 |
|
- Datasets 2.12.0 |
|
- Tokenizers 0.15.1 |
|
|
