|
--- |
|
base_model: microsoft/wavlm-base |
|
tags: |
|
- audio-classification |
|
- generated_from_trainer |
|
metrics: |
|
- accuracy |
|
model-index: |
|
- name: wavlm-base_5 |
|
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. --> |
|
|
|
# wavlm-base_5 |
|
|
|
This model is a fine-tuned version of [microsoft/wavlm-base](https://huggingface.co/microsoft/wavlm-base) on an unknown dataset. |
|
It achieves the following results on the evaluation set: |
|
- Loss: 0.4151 |
|
- Accuracy: 0.8974 |
|
|
|
## 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: 2 |
|
- seed: 0 |
|
- gradient_accumulation_steps: 4 |
|
- total_train_batch_size: 64 |
|
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 |
|
- lr_scheduler_type: linear |
|
- lr_scheduler_warmup_ratio: 0.1 |
|
- num_epochs: 10.0 |
|
|
|
### Training results |
|
|
|
| Training Loss | Epoch | Step | Validation Loss | Accuracy | |
|
|:-------------:|:-----:|:----:|:---------------:|:--------:| |
|
| 0.3764 | 0.25 | 100 | 0.0277 | 0.9948 | |
|
| 0.1211 | 0.5 | 200 | 0.0297 | 0.9981 | |
|
| 0.2525 | 0.76 | 300 | 1.2840 | 0.9168 | |
|
| 0.784 | 1.01 | 400 | 0.3443 | 0.8974 | |
|
| 0.6053 | 1.26 | 500 | 0.3958 | 0.8974 | |
|
| 0.6038 | 1.51 | 600 | 0.4848 | 0.8974 | |
|
| 0.5996 | 1.76 | 700 | 0.3954 | 0.8974 | |
|
| 0.5914 | 2.02 | 800 | 0.3970 | 0.8974 | |
|
| 0.6077 | 2.27 | 900 | 0.4722 | 0.8974 | |
|
| 0.5991 | 2.52 | 1000 | 0.4362 | 0.8974 | |
|
| 0.5813 | 2.77 | 1100 | 0.3871 | 0.8974 | |
|
| 0.5953 | 3.02 | 1200 | 0.4013 | 0.8974 | |
|
| 0.5957 | 3.28 | 1300 | 0.4693 | 0.8974 | |
|
| 0.5852 | 3.53 | 1400 | 0.3879 | 0.8974 | |
|
| 0.6066 | 3.78 | 1500 | 0.4280 | 0.8974 | |
|
| 0.6085 | 4.03 | 1600 | 0.4359 | 0.8974 | |
|
| 0.5944 | 4.28 | 1700 | 0.4167 | 0.8974 | |
|
| 0.5994 | 4.54 | 1800 | 0.4139 | 0.8974 | |
|
| 0.5953 | 4.79 | 1900 | 0.4256 | 0.8974 | |
|
| 0.5929 | 5.04 | 2000 | 0.4371 | 0.8974 | |
|
| 0.6067 | 5.29 | 2100 | 0.4255 | 0.8974 | |
|
| 0.5944 | 5.55 | 2200 | 0.4121 | 0.8974 | |
|
| 0.5926 | 5.8 | 2300 | 0.4210 | 0.8974 | |
|
| 0.594 | 6.05 | 2400 | 0.4057 | 0.8974 | |
|
| 0.6042 | 6.3 | 2500 | 0.4252 | 0.8974 | |
|
| 0.5971 | 6.55 | 2600 | 0.3958 | 0.8974 | |
|
| 0.597 | 6.81 | 2700 | 0.4124 | 0.8974 | |
|
| 0.5816 | 7.06 | 2800 | 0.4101 | 0.8974 | |
|
| 0.5944 | 7.31 | 2900 | 0.4258 | 0.8974 | |
|
| 0.6053 | 7.56 | 3000 | 0.4415 | 0.8974 | |
|
| 0.5894 | 7.81 | 3100 | 0.4067 | 0.8974 | |
|
| 0.5987 | 8.07 | 3200 | 0.4109 | 0.8974 | |
|
| 0.5846 | 8.32 | 3300 | 0.4095 | 0.8974 | |
|
| 0.5982 | 8.57 | 3400 | 0.4187 | 0.8974 | |
|
| 0.5932 | 8.82 | 3500 | 0.4124 | 0.8974 | |
|
| 0.6007 | 9.07 | 3600 | 0.4212 | 0.8974 | |
|
| 0.6041 | 9.33 | 3700 | 0.4257 | 0.8974 | |
|
| 0.5859 | 9.58 | 3800 | 0.4176 | 0.8974 | |
|
| 0.5842 | 9.83 | 3900 | 0.4151 | 0.8974 | |
|
|
|
|
|
### Framework versions |
|
|
|
- Transformers 4.34.0.dev0 |
|
- Pytorch 2.0.0.post302 |
|
- Datasets 2.14.5 |
|
- Tokenizers 0.13.3 |
|
|
