wav2vec2-base-F1-New
This model is a fine-tuned version of facebook/wav2vec2-base on the None dataset. It achieves the following results on the evaluation set:
- Loss: 1.3003
- Accuracy: 0.7943
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: 4
- eval_batch_size: 4
- seed: 42
- gradient_accumulation_steps: 2
- total_train_batch_size: 8
- optimizer: Use OptimizerNames.ADAMW_TORCH_FUSED with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
- lr_scheduler_type: linear
- num_epochs: 9
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|---|---|---|---|---|
| 0.7564 | 0.5714 | 400 | 0.9340 | 0.6421 |
| 1.1544 | 1.1429 | 800 | 0.8919 | 0.7036 |
| 1.2419 | 1.7143 | 1200 | 0.9550 | 0.7043 |
| 0.8845 | 2.2857 | 1600 | 0.9173 | 0.7421 |
| 0.768 | 2.8571 | 2000 | 1.0055 | 0.7143 |
| 0.7651 | 3.4286 | 2400 | 1.0335 | 0.7493 |
| 0.0727 | 4.0 | 2800 | 1.0752 | 0.7657 |
| 0.4221 | 4.5714 | 3200 | 1.1511 | 0.7714 |
| 0.0223 | 5.1429 | 3600 | 1.1912 | 0.7786 |
| 0.0197 | 5.7143 | 4000 | 1.2445 | 0.7793 |
| 0.0155 | 6.2857 | 4400 | 1.3507 | 0.7671 |
| 0.0098 | 6.8571 | 4800 | 1.3745 | 0.7743 |
| 0.0196 | 7.4286 | 5200 | 1.3180 | 0.7864 |
| 0.012 | 8.0 | 5600 | 1.3457 | 0.7886 |
| 0.0113 | 8.5714 | 6000 | 1.3003 | 0.7943 |
Framework versions
- Transformers 4.57.0
- Pytorch 2.8.0+cu126
- Datasets 4.0.0
- Tokenizers 0.22.1