my_language_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: 4.4688
- Accuracy: 0.0
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: 1e-05
- train_batch_size: 2
- eval_batch_size: 2
- seed: 42
- 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: 10
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|---|---|---|---|---|
| 4.4844 | 1.0 | 35 | 4.4688 | 0.0 |
| 4.4691 | 2.0 | 70 | 4.4883 | 0.0 |
| 4.4355 | 3.0 | 105 | 4.5020 | 0.0 |
| 4.4457 | 4.0 | 140 | 4.5200 | 0.0 |
| 4.4246 | 5.0 | 175 | 4.5312 | 0.0 |
| 4.4492 | 6.0 | 210 | 4.5454 | 0.0 |
| 4.4066 | 7.0 | 245 | 4.5562 | 0.0 |
| 4.4094 | 8.0 | 280 | 4.5645 | 0.0 |
| 4.3883 | 9.0 | 315 | 4.5710 | 0.0 |
| 4.3910 | 10.0 | 350 | 4.5734 | 0.0 |
Framework versions
- Transformers 5.15.0
- Pytorch 2.11.0+cu128
- Datasets 4.0.0
- Tokenizers 0.22.2
- Downloads last month
- 12
Model tree for Ritesh-kumar-07/my_language_model
Base model
facebook/wav2vec2-base