|
--- |
|
license: apache-2.0 |
|
tags: |
|
- generated_from_trainer |
|
datasets: |
|
- minds14 |
|
metrics: |
|
- accuracy |
|
model-index: |
|
- name: audio_cls_wav2vec2-base_minds14_finetune |
|
results: [] |
|
--- |
|
|
|
<!-- This model card has been generated automatically according to the information the Trainer had access to. You |
|
should probably proofread and complete it, then remove this comment. --> |
|
|
|
# audio_cls_wav2vec2-base_minds14_finetune |
|
|
|
This model is a fine-tuned version of [facebook/wav2vec2-base](https://huggingface.co/facebook/wav2vec2-base) on the minds14 dataset. |
|
It achieves the following results on the evaluation set: |
|
- Loss: 2.6523 |
|
- 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: 64 |
|
- eval_batch_size: 64 |
|
- seed: 42 |
|
- gradient_accumulation_steps: 4 |
|
- total_train_batch_size: 256 |
|
- 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 | 1.0 | 2 | 2.6391 | 0.0708 | |
|
| No log | 2.0 | 4 | 2.6421 | 0.0442 | |
|
| No log | 3.0 | 6 | 2.6465 | 0.0354 | |
|
| No log | 4.0 | 8 | 2.6486 | 0.0442 | |
|
| 2.6349 | 5.0 | 10 | 2.6502 | 0.0442 | |
|
| 2.6349 | 6.0 | 12 | 2.6507 | 0.0531 | |
|
| 2.6349 | 7.0 | 14 | 2.6514 | 0.0619 | |
|
| 2.6349 | 8.0 | 16 | 2.6528 | 0.0619 | |
|
| 2.6349 | 9.0 | 18 | 2.6528 | 0.0619 | |
|
| 2.6278 | 10.0 | 20 | 2.6523 | 0.0619 | |
|
|
|
|
|
### Framework versions |
|
|
|
- Transformers 4.29.2 |
|
- Pytorch 2.0.1+cu117 |
|
- Datasets 2.12.0 |
|
- Tokenizers 0.13.3 |
|
|
