emotions_xls53_6_classes
This model is a fine-tuned version of facebook/wav2vec2-large-xlsr-53 on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.8000
- Accuracy: 0.7678
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: 32
- eval_batch_size: 32
- seed: 42
- gradient_accumulation_steps: 4
- total_train_batch_size: 128
- 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
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|---|---|---|---|---|
| 0.6892 | 0.99 | 76 | 0.8018 | 0.7346 |
| 0.6611 | 2.0 | 153 | 0.7451 | 0.7482 |
| 0.6012 | 2.99 | 229 | 0.6767 | 0.7731 |
| 0.4795 | 4.0 | 306 | 0.8686 | 0.7408 |
| 0.5143 | 4.99 | 382 | 0.7684 | 0.7629 |
| 0.4878 | 6.0 | 459 | 0.7513 | 0.7744 |
| 0.4619 | 6.99 | 535 | 0.8314 | 0.7596 |
| 0.458 | 8.0 | 612 | 0.7943 | 0.7670 |
| 0.4383 | 8.99 | 688 | 0.8460 | 0.7596 |
| 0.5196 | 9.93 | 760 | 0.8000 | 0.7678 |
Framework versions
- Transformers 4.31.0
- Pytorch 2.0.1+cu117
- Datasets 2.14.4
- Tokenizers 0.13.3