jb_mind_model
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: 2.6530
- Accuracy: 0.0619
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: 8
- eval_batch_size: 8
- seed: 42
- gradient_accumulation_steps: 4
- total_train_batch_size: 32
- 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
- lr_scheduler_warmup_steps: 0.1
- num_epochs: 10
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|---|---|---|---|---|
| 10.5658 | 1.0 | 15 | 2.6464 | 0.0442 |
| 9.7927 | 2.0 | 30 | 2.6471 | 0.0442 |
| 10.5340 | 3.0 | 45 | 2.6574 | 0.0619 |
| 9.7383 | 4.0 | 60 | 2.6564 | 0.0619 |
| 10.5205 | 5.0 | 75 | 2.6577 | 0.0619 |
| 9.7505 | 6.0 | 90 | 2.6541 | 0.0619 |
| 10.5118 | 7.0 | 105 | 2.6518 | 0.0619 |
| 9.6948 | 8.0 | 120 | 2.6514 | 0.0619 |
| 10.5060 | 9.0 | 135 | 2.6533 | 0.0619 |
| 9.7061 | 10.0 | 150 | 2.6530 | 0.0619 |
Framework versions
- Transformers 5.5.4
- Pytorch 2.11.0+cu130
- Datasets 4.8.4
- Tokenizers 0.22.2