resultsfinalgerman
This model is a fine-tuned version of padmalcom/wav2vec2-large-emotion-detection-german on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.6302
- Accuracy: 0.6429
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: 1e-05
- train_batch_size: 4
- eval_batch_size: 4
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 50
Training results
Training Loss | Epoch | Step | Validation Loss | Accuracy |
---|---|---|---|---|
0.7053 | 1.0 | 13 | 0.6971 | 0.3571 |
0.6994 | 2.0 | 26 | 0.6930 | 0.5714 |
0.686 | 3.0 | 39 | 0.6891 | 0.5714 |
0.6759 | 4.0 | 52 | 0.6889 | 0.5714 |
0.6865 | 5.0 | 65 | 0.6870 | 0.5714 |
0.6916 | 6.0 | 78 | 0.6847 | 0.5714 |
0.6764 | 7.0 | 91 | 0.6854 | 0.5714 |
0.6768 | 8.0 | 104 | 0.6869 | 0.5714 |
0.6546 | 9.0 | 117 | 0.6882 | 0.5714 |
0.6806 | 10.0 | 130 | 0.6875 | 0.5714 |
0.6742 | 11.0 | 143 | 0.6893 | 0.5714 |
0.6675 | 12.0 | 156 | 0.6897 | 0.5714 |
0.6762 | 13.0 | 169 | 0.6903 | 0.5714 |
0.6451 | 14.0 | 182 | 0.6920 | 0.5714 |
0.6641 | 15.0 | 195 | 0.6928 | 0.5714 |
0.634 | 16.0 | 208 | 0.6974 | 0.5714 |
0.6342 | 17.0 | 221 | 0.6983 | 0.5714 |
0.6526 | 18.0 | 234 | 0.6992 | 0.5714 |
0.6498 | 19.0 | 247 | 0.6926 | 0.5714 |
0.6293 | 20.0 | 260 | 0.6842 | 0.5714 |
0.5946 | 21.0 | 273 | 0.6833 | 0.5714 |
0.6281 | 22.0 | 286 | 0.6761 | 0.5 |
0.6084 | 23.0 | 299 | 0.6748 | 0.5 |
0.6055 | 24.0 | 312 | 0.6655 | 0.5 |
0.5806 | 25.0 | 325 | 0.6670 | 0.7143 |
0.62 | 26.0 | 338 | 0.6550 | 0.5714 |
0.5741 | 27.0 | 351 | 0.6578 | 0.7143 |
0.6261 | 28.0 | 364 | 0.6675 | 0.6429 |
0.5069 | 29.0 | 377 | 0.6661 | 0.6429 |
0.5526 | 30.0 | 390 | 0.6602 | 0.6429 |
0.5145 | 31.0 | 403 | 0.6545 | 0.6429 |
0.5634 | 32.0 | 416 | 0.6553 | 0.6429 |
0.4619 | 33.0 | 429 | 0.6493 | 0.6429 |
0.5694 | 34.0 | 442 | 0.6487 | 0.6429 |
0.5045 | 35.0 | 455 | 0.6436 | 0.6429 |
0.4623 | 36.0 | 468 | 0.6448 | 0.6429 |
0.5001 | 37.0 | 481 | 0.6465 | 0.6429 |
0.4779 | 38.0 | 494 | 0.6439 | 0.6429 |
0.4751 | 39.0 | 507 | 0.6329 | 0.6429 |
0.4426 | 40.0 | 520 | 0.6294 | 0.6429 |
0.4341 | 41.0 | 533 | 0.6270 | 0.6429 |
0.4282 | 42.0 | 546 | 0.6265 | 0.6429 |
0.4908 | 43.0 | 559 | 0.6269 | 0.6429 |
0.4073 | 44.0 | 572 | 0.6251 | 0.6429 |
0.4207 | 45.0 | 585 | 0.6261 | 0.6429 |
0.4757 | 46.0 | 598 | 0.6277 | 0.6429 |
0.4357 | 47.0 | 611 | 0.6294 | 0.6429 |
0.4473 | 48.0 | 624 | 0.6302 | 0.6429 |
0.4047 | 49.0 | 637 | 0.6302 | 0.6429 |
0.4881 | 50.0 | 650 | 0.6302 | 0.6429 |
Framework versions
- Transformers 4.30.2
- Pytorch 2.0.1+cu118
- Datasets 2.13.1
- Tokenizers 0.13.3
- Downloads last month
- 4
This model does not have enough activity to be deployed to Inference API (serverless) yet. Increase its social
visibility and check back later, or deploy to Inference Endpoints (dedicated)
instead.