|
--- |
|
license: apache-2.0 |
|
base_model: facebook/wav2vec2-base |
|
tags: |
|
- generated_from_trainer |
|
metrics: |
|
- accuracy |
|
model-index: |
|
- name: wav2vec2-base-finetuned-organ |
|
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-finetuned-organ |
|
|
|
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: 1.2973 |
|
- Accuracy: 0.8182 |
|
|
|
## 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: 5e-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: 50 |
|
- mixed_precision_training: Native AMP |
|
|
|
### Training results |
|
|
|
| Training Loss | Epoch | Step | Validation Loss | Accuracy | |
|
|:-------------:|:-----:|:----:|:---------------:|:--------:| |
|
| 0.0652 | 1.0 | 6 | 0.0202 | 1.0 | |
|
| 0.0226 | 2.0 | 12 | 0.0171 | 1.0 | |
|
| 0.1719 | 3.0 | 18 | 0.5006 | 0.9091 | |
|
| 0.1115 | 4.0 | 24 | 1.4275 | 0.7273 | |
|
| 0.191 | 5.0 | 30 | 0.3866 | 0.9091 | |
|
| 0.4063 | 6.0 | 36 | 1.6167 | 0.7273 | |
|
| 0.6557 | 7.0 | 42 | 2.5850 | 0.5455 | |
|
| 0.7413 | 8.0 | 48 | 1.7765 | 0.5455 | |
|
| 0.8188 | 9.0 | 54 | 2.1469 | 0.5455 | |
|
| 1.168 | 10.0 | 60 | 1.0001 | 0.8182 | |
|
| 0.9951 | 11.0 | 66 | 1.0984 | 0.8182 | |
|
| 0.7365 | 12.0 | 72 | 1.6653 | 0.5455 | |
|
| 0.5536 | 13.0 | 78 | 1.2873 | 0.7273 | |
|
| 0.8315 | 14.0 | 84 | 0.2661 | 0.9091 | |
|
| 0.3605 | 15.0 | 90 | 0.2670 | 0.9091 | |
|
| 0.6238 | 16.0 | 96 | 0.5140 | 0.8182 | |
|
| 0.3698 | 17.0 | 102 | 0.5254 | 0.8182 | |
|
| 0.2818 | 18.0 | 108 | 1.1506 | 0.6364 | |
|
| 0.4245 | 19.0 | 114 | 1.2583 | 0.6364 | |
|
| 0.6101 | 20.0 | 120 | 0.9249 | 0.7273 | |
|
| 0.2197 | 21.0 | 126 | 1.1442 | 0.7273 | |
|
| 0.2161 | 22.0 | 132 | 1.6102 | 0.6364 | |
|
| 0.6048 | 23.0 | 138 | 1.3656 | 0.7273 | |
|
| 0.1764 | 24.0 | 144 | 1.4459 | 0.7273 | |
|
| 0.1602 | 25.0 | 150 | 1.4824 | 0.7273 | |
|
| 0.185 | 26.0 | 156 | 1.5401 | 0.7273 | |
|
| 0.0679 | 27.0 | 162 | 1.6073 | 0.7273 | |
|
| 0.1278 | 28.0 | 168 | 1.0710 | 0.8182 | |
|
| 0.1546 | 29.0 | 174 | 0.5503 | 0.9091 | |
|
| 0.2121 | 30.0 | 180 | 0.5570 | 0.9091 | |
|
| 0.0087 | 31.0 | 186 | 0.5756 | 0.9091 | |
|
| 0.2233 | 32.0 | 192 | 1.1581 | 0.8182 | |
|
| 0.0088 | 33.0 | 198 | 1.1720 | 0.8182 | |
|
| 0.1851 | 34.0 | 204 | 1.5192 | 0.6364 | |
|
| 0.0098 | 35.0 | 210 | 1.7753 | 0.7273 | |
|
| 0.008 | 36.0 | 216 | 1.8136 | 0.7273 | |
|
| 0.0648 | 37.0 | 222 | 1.8277 | 0.7273 | |
|
| 0.1351 | 38.0 | 228 | 1.8239 | 0.7273 | |
|
| 0.1287 | 39.0 | 234 | 1.7748 | 0.7273 | |
|
| 0.0712 | 40.0 | 240 | 1.6251 | 0.7273 | |
|
| 0.0503 | 41.0 | 246 | 1.2516 | 0.8182 | |
|
| 0.1273 | 42.0 | 252 | 1.2622 | 0.8182 | |
|
| 0.0859 | 43.0 | 258 | 1.2601 | 0.8182 | |
|
| 0.073 | 44.0 | 264 | 1.2624 | 0.8182 | |
|
| 0.2027 | 45.0 | 270 | 1.2639 | 0.8182 | |
|
| 0.0477 | 46.0 | 276 | 1.2667 | 0.8182 | |
|
| 0.1111 | 47.0 | 282 | 1.2688 | 0.8182 | |
|
| 0.072 | 48.0 | 288 | 1.2689 | 0.8182 | |
|
| 0.0615 | 49.0 | 294 | 1.2726 | 0.8182 | |
|
| 0.0049 | 50.0 | 300 | 1.2973 | 0.8182 | |
|
|
|
|
|
### Framework versions |
|
|
|
- Transformers 4.42.3 |
|
- Pytorch 2.3.1+cu121 |
|
- Datasets 2.19.1 |
|
- Tokenizers 0.19.1 |
|
|
