IDAT_red_aug_290_novel_Wav2Vec
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: 0.5251
- Accuracy: 0.7468
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: 4
- total_train_batch_size: 16
- 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 |
---|---|---|---|---|
0.595 | 0.99 | 40 | 0.6560 | 0.6013 |
0.4853 | 1.99 | 80 | 0.5651 | 0.7342 |
0.46 | 2.98 | 120 | 0.5168 | 0.7468 |
0.4401 | 4.0 | 161 | 0.5230 | 0.7848 |
0.3787 | 4.99 | 201 | 0.6051 | 0.7468 |
0.465 | 5.99 | 241 | 0.7267 | 0.6646 |
0.4037 | 6.98 | 281 | 0.4611 | 0.7911 |
0.4508 | 8.0 | 322 | 0.6489 | 0.7468 |
0.4427 | 8.99 | 362 | 0.4774 | 0.7848 |
0.399 | 9.94 | 400 | 0.5251 | 0.7468 |
Framework versions
- Transformers 4.32.1
- Pytorch 2.1.2
- Datasets 2.16.1
- Tokenizers 0.13.3
- Downloads last month
- 2
Model tree for alirzb/IDAT_red_aug_290_novel_Wav2Vec
Base model
facebook/wav2vec2-base