wav2vec2-base-finetuned-zindi_techcabal
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: 0.0232
- Accuracy: 0.9963
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: 32
- eval_batch_size: 32
- seed: 42
- gradient_accumulation_steps: 2
- total_train_batch_size: 64
- 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
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|---|---|---|---|---|
| 1.2428 | 1.3333 | 100 | 1.1358 | 0.7566 |
| 0.4838 | 2.6667 | 200 | 0.3009 | 0.9738 |
| 0.1708 | 4.0 | 300 | 0.1599 | 0.9700 |
| 0.1251 | 5.3333 | 400 | 0.0682 | 0.9906 |
| 0.0841 | 6.6667 | 500 | 0.0450 | 0.9888 |
| 0.0692 | 8.0 | 600 | 0.0534 | 0.9888 |
| 0.045 | 9.3333 | 700 | 0.0232 | 0.9963 |
Framework versions
- Transformers 4.44.0
- Pytorch 2.4.0
- Datasets 2.21.0
- Tokenizers 0.19.1
- Downloads last month
- 11
Model tree for DanielTobi0/wav2vec2-base-finetuned-zindi_techcabal
Base model
facebook/wav2vec2-base