metadata
license: apache-2.0
tags:
- generated_from_trainer
datasets:
- minds14
metrics:
- accuracy
model-index:
- name: audio_classification
results: []
audio_classification
This model is a fine-tuned version of facebook/wav2vec2-base on the minds14 dataset. It achieves the following results on the evaluation set:
- Loss: 2.6385
- Accuracy: 0.0708
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: 32
- eval_batch_size: 32
- seed: 42
- gradient_accumulation_steps: 4
- total_train_batch_size: 128
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_ratio: 0.1
- num_epochs: 10
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|---|---|---|---|---|
| No log | 0.8 | 3 | 2.6440 | 0.0442 |
| No log | 1.87 | 7 | 2.6566 | 0.0531 |
| 2.6406 | 2.93 | 11 | 2.6527 | 0.0354 |
| 2.6406 | 4.0 | 15 | 2.6533 | 0.0619 |
| 2.6406 | 4.8 | 18 | 2.6503 | 0.0796 |
| 2.6412 | 5.87 | 22 | 2.6402 | 0.0885 |
| 2.6412 | 6.93 | 26 | 2.6394 | 0.0619 |
| 2.6389 | 8.0 | 30 | 2.6385 | 0.0708 |
Framework versions
- Transformers 4.27.4
- Pytorch 2.0.0
- Datasets 2.11.0
- Tokenizers 0.13.3