metadata
license: apache-2.0
base_model: facebook/wav2vec2-base
tags:
- generated_from_trainer
metrics:
- accuracy
model-index:
- name: chordektomie-sentence
results: []
chordektomie-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: 0.3963
- Accuracy: 0.8636
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 |
|---|---|---|---|---|
| 0.6931 | 1.0 | 6 | 0.7023 | 0.2273 |
| 0.6659 | 2.0 | 12 | 0.7066 | 0.3182 |
| 0.5839 | 3.0 | 18 | 0.5774 | 0.8636 |
| 0.4567 | 4.0 | 24 | 0.5393 | 0.8182 |
| 0.3303 | 5.0 | 30 | 0.4371 | 0.8182 |
| 0.2379 | 6.0 | 36 | 0.3744 | 0.8182 |
| 0.1511 | 7.0 | 42 | 0.5223 | 0.8182 |
| 0.1061 | 8.0 | 48 | 0.5431 | 0.8182 |
| 0.0781 | 9.0 | 54 | 0.3211 | 0.9091 |
| 0.0623 | 10.0 | 60 | 0.3216 | 0.9091 |
| 0.0681 | 11.0 | 66 | 0.3336 | 0.9091 |
| 0.0475 | 12.0 | 72 | 0.3459 | 0.9091 |
| 0.0441 | 13.0 | 78 | 0.3811 | 0.8636 |
| 0.0419 | 14.0 | 84 | 0.3959 | 0.8636 |
| 0.0409 | 15.0 | 90 | 0.3963 | 0.8636 |
Framework versions
- Transformers 4.37.2
- Pytorch 2.2.0
- Datasets 2.12.0
- Tokenizers 0.15.1