|
--- |
|
library_name: transformers |
|
license: apache-2.0 |
|
base_model: facebook/wav2vec2-base |
|
tags: |
|
- generated_from_trainer |
|
metrics: |
|
- accuracy |
|
- f1 |
|
- recall |
|
- precision |
|
model-index: |
|
- name: wav2vec2-base-music_genre_classifier-g4-firstseconds |
|
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. --> |
|
|
|
# wav2vec2-base-music_genre_classifier-g4-firstseconds |
|
|
|
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: 1.0453 |
|
- Accuracy: 0.7794 |
|
- F1: 0.7715 |
|
- Recall: 0.7722 |
|
- Precision: 0.7752 |
|
|
|
## 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: 12 |
|
- eval_batch_size: 12 |
|
- seed: 42 |
|
- optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments |
|
- lr_scheduler_type: linear |
|
- lr_scheduler_warmup_ratio: 0.1 |
|
- num_epochs: 15 |
|
- mixed_precision_training: Native AMP |
|
|
|
### Training results |
|
|
|
| Training Loss | Epoch | Step | Validation Loss | Accuracy | F1 | Recall | Precision | |
|
|:-------------:|:-----:|:----:|:---------------:|:--------:|:------:|:------:|:---------:| |
|
| 2.2104 | 1.0 | 267 | 2.2272 | 0.3755 | 0.3160 | 0.3656 | 0.3611 | |
|
| 1.6919 | 2.0 | 534 | 1.7563 | 0.4622 | 0.3974 | 0.4519 | 0.3981 | |
|
| 1.3183 | 3.0 | 801 | 1.4686 | 0.5366 | 0.4834 | 0.5237 | 0.5364 | |
|
| 1.0196 | 4.0 | 1068 | 1.2824 | 0.6183 | 0.5754 | 0.6094 | 0.5873 | |
|
| 1.0655 | 5.0 | 1335 | 1.2136 | 0.6196 | 0.5822 | 0.6075 | 0.6142 | |
|
| 0.8205 | 6.0 | 1602 | 1.0635 | 0.6778 | 0.6449 | 0.6687 | 0.6611 | |
|
| 0.6309 | 7.0 | 1869 | 1.0256 | 0.7088 | 0.6798 | 0.6975 | 0.7004 | |
|
| 0.4618 | 8.0 | 2136 | 0.9435 | 0.7435 | 0.7330 | 0.7373 | 0.7387 | |
|
| 0.4057 | 9.0 | 2403 | 0.9192 | 0.7534 | 0.7403 | 0.7465 | 0.7507 | |
|
| 0.2491 | 10.0 | 2670 | 0.9099 | 0.7596 | 0.7539 | 0.7510 | 0.7640 | |
|
| 0.2548 | 11.0 | 2937 | 1.0901 | 0.7336 | 0.7305 | 0.7291 | 0.7475 | |
|
| 0.0885 | 12.0 | 3204 | 1.0956 | 0.7447 | 0.7417 | 0.7387 | 0.7519 | |
|
| 0.0988 | 13.0 | 3471 | 1.0585 | 0.7695 | 0.7623 | 0.7634 | 0.7641 | |
|
| 0.1982 | 14.0 | 3738 | 1.0453 | 0.7794 | 0.7715 | 0.7722 | 0.7752 | |
|
| 0.0966 | 15.0 | 4005 | 1.0914 | 0.7732 | 0.7676 | 0.7690 | 0.7706 | |
|
|
|
|
|
### Framework versions |
|
|
|
- Transformers 4.46.2 |
|
- Pytorch 2.5.0+cu121 |
|
- Datasets 3.1.0 |
|
- Tokenizers 0.20.3 |
|
|
