my_awesome_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: 2.6642
- 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: 32
- seed: 42
- gradient_accumulation_steps: 2
- total_train_batch_size: 16
- 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: 3
- num_epochs: 10
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|---|---|---|---|---|
| 5.2885 | 1.0 | 29 | 2.6604 | 0.0354 |
| 5.2598 | 2.0 | 58 | 2.6642 | 0.0619 |
| 5.2311 | 3.0 | 87 | 2.6678 | 0.0265 |
| 5.2295 | 4.0 | 116 | 2.6624 | 0.0265 |
| 5.1979 | 5.0 | 145 | 2.6745 | 0.0354 |
| 5.1715 | 6.0 | 174 | 2.6733 | 0.0265 |
| 5.1656 | 7.0 | 203 | 2.6870 | 0.0442 |
| 5.0972 | 8.0 | 232 | 2.6931 | 0.0354 |
| 5.1156 | 9.0 | 261 | 2.6925 | 0.0265 |
| 4.8175 | 10.0 | 290 | 2.6944 | 0.0265 |
Framework versions
- Transformers 5.16.1
- Pytorch 2.11.0+cu128
- Datasets 4.8.5
- Tokenizers 0.23.1
- Downloads last month
- -
Model tree for sukhun2/my_awesome_mind_model
Base model
facebook/wav2vec2-base