shimalabaudio-20240425
This model is a fine-tuned version of facebook/wav2vec2-base on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.9754
- Accuracy: 0.3846
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: 10
Training results
Training Loss | Epoch | Step | Validation Loss | Accuracy |
---|---|---|---|---|
0.7094 | 1.0 | 4 | 0.7174 | 0.3846 |
0.7136 | 2.0 | 8 | 0.7253 | 0.3846 |
0.5748 | 3.0 | 12 | 0.7792 | 0.3846 |
0.5697 | 4.0 | 16 | 0.8618 | 0.3846 |
0.6178 | 5.0 | 20 | 0.8132 | 0.3846 |
0.5846 | 6.0 | 24 | 0.7702 | 0.3846 |
0.6907 | 7.0 | 28 | 0.7661 | 0.3846 |
0.641 | 8.0 | 32 | 0.7716 | 0.3846 |
0.8116 | 9.0 | 36 | 1.0015 | 0.3846 |
0.5889 | 10.0 | 40 | 0.9754 | 0.3846 |
Framework versions
- Transformers 4.37.2
- Pytorch 2.2.0
- Datasets 2.12.0
- Tokenizers 0.15.1
- Downloads last month
- 27