| --- |
| base_model: microsoft/wavlm-base |
| tags: |
| - audio-classification |
| - generated_from_trainer |
| metrics: |
| - f1 |
| model-index: |
| - name: wavlm-base_4 |
| 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_4 |
| |
| 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: 0.3325 |
| - F1: 0.9459 |
| |
| ## 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 | F1 | |
| |:-------------:|:-----:|:----:|:---------------:|:------:| |
| | 0.3784 | 0.25 | 100 | 0.0784 | 0.9906 | |
| | 0.1125 | 0.5 | 200 | 0.0638 | 0.9925 | |
| | 0.1158 | 0.76 | 300 | 0.1716 | 0.9773 | |
| | 0.327 | 1.01 | 400 | 0.3308 | 0.9459 | |
| | 0.3346 | 1.26 | 500 | 0.3449 | 0.9459 | |
| | 0.3345 | 1.51 | 600 | 0.3316 | 0.9459 | |
| | 0.3313 | 1.76 | 700 | 0.3320 | 0.9459 | |
| | 0.3249 | 2.02 | 800 | 0.3327 | 0.9459 | |
| | 0.3403 | 2.27 | 900 | 0.3315 | 0.9459 | |
| | 0.3345 | 2.52 | 1000 | 0.3382 | 0.9459 | |
| | 0.3174 | 2.77 | 1100 | 0.3376 | 0.9459 | |
| | 0.3274 | 3.02 | 1200 | 0.3354 | 0.9459 | |
| | 0.3296 | 3.28 | 1300 | 0.3307 | 0.9459 | |
| | 0.3175 | 3.53 | 1400 | 0.3341 | 0.9459 | |
| | 0.3416 | 3.78 | 1500 | 0.3344 | 0.9459 | |
| | 0.3412 | 4.03 | 1600 | 0.3308 | 0.9459 | |
| | 0.3293 | 4.28 | 1700 | 0.3314 | 0.9459 | |
| | 0.3346 | 4.54 | 1800 | 0.3308 | 0.9459 | |
| | 0.3279 | 4.79 | 1900 | 0.3317 | 0.9459 | |
| | 0.3246 | 5.04 | 2000 | 0.3318 | 0.9459 | |
| | 0.3373 | 5.29 | 2100 | 0.3311 | 0.9459 | |
| | 0.3262 | 5.55 | 2200 | 0.3335 | 0.9459 | |
| | 0.3279 | 5.8 | 2300 | 0.3326 | 0.9459 | |
| | 0.3298 | 6.05 | 2400 | 0.3323 | 0.9459 | |
| | 0.3397 | 6.3 | 2500 | 0.3311 | 0.9459 | |
| | 0.3312 | 6.55 | 2600 | 0.3386 | 0.9459 | |
| | 0.3291 | 6.81 | 2700 | 0.3317 | 0.9459 | |
| | 0.3146 | 7.06 | 2800 | 0.3323 | 0.9459 | |
| | 0.3296 | 7.31 | 2900 | 0.3313 | 0.9459 | |
| | 0.3367 | 7.56 | 3000 | 0.3317 | 0.9459 | |
| | 0.3232 | 7.81 | 3100 | 0.3318 | 0.9459 | |
| | 0.3314 | 8.07 | 3200 | 0.3325 | 0.9459 | |
| | 0.3201 | 8.32 | 3300 | 0.3323 | 0.9459 | |
| | 0.3301 | 8.57 | 3400 | 0.3347 | 0.9459 | |
| | 0.3268 | 8.82 | 3500 | 0.3325 | 0.9459 | |
| | 0.3361 | 9.07 | 3600 | 0.3321 | 0.9459 | |
| | 0.3395 | 9.33 | 3700 | 0.3313 | 0.9459 | |
| | 0.3231 | 9.58 | 3800 | 0.3319 | 0.9459 | |
| | 0.3197 | 9.83 | 3900 | 0.3326 | 0.9459 | |
| |
| |
| ### Framework versions |
| |
| - Transformers 4.34.0.dev0 |
| - Pytorch 2.0.0.post302 |
| - Datasets 2.14.5 |
| - Tokenizers 0.13.3 |
| |
