metadata
license: apache-2.0
base_model: facebook/wav2vec2-base
tags:
- generated_from_trainer
metrics:
- accuracy
model-index:
- name: mydata-sentence
results: []
mydata-sentence
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: 0.7519
- Accuracy: 0.4615
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: 16
- eval_batch_size: 16
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_ratio: 0.1
- num_epochs: 15
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|---|---|---|---|---|
| 0.7048 | 1.0 | 4 | 0.7079 | 0.3846 |
| 0.6478 | 2.0 | 8 | 0.7239 | 0.3846 |
| 0.7242 | 3.0 | 12 | 0.7464 | 0.3846 |
| 0.5978 | 4.0 | 16 | 0.7460 | 0.4615 |
| 0.7061 | 5.0 | 20 | 0.7460 | 0.4615 |
| 0.7089 | 6.0 | 24 | 0.7377 | 0.4615 |
| 0.5751 | 7.0 | 28 | 0.7324 | 0.4615 |
| 0.5799 | 8.0 | 32 | 0.7365 | 0.4615 |
| 0.563 | 9.0 | 36 | 0.7477 | 0.4615 |
| 0.555 | 10.0 | 40 | 0.7562 | 0.4615 |
| 0.5227 | 11.0 | 44 | 0.7632 | 0.4615 |
| 0.6701 | 12.0 | 48 | 0.7590 | 0.4615 |
| 0.5219 | 13.0 | 52 | 0.7540 | 0.4615 |
| 0.5003 | 14.0 | 56 | 0.7526 | 0.4615 |
| 0.488 | 15.0 | 60 | 0.7519 | 0.4615 |
Framework versions
- Transformers 4.37.2
- Pytorch 2.2.0
- Datasets 2.12.0
- Tokenizers 0.15.1