metadata
license: apache-2.0
base_model: facebook/wav2vec2-base
tags:
- generated_from_trainer
metrics:
- accuracy
model-index:
- name: IDAT_red_aug_208_Wav2Vec
results: []
IDAT_red_aug_208_Wav2Vec
This model is a fine-tuned version of facebook/wav2vec2-base on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.0009
- Accuracy: 1.0
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: 3e-05
- train_batch_size: 4
- eval_batch_size: 4
- seed: 42
- gradient_accumulation_steps: 4
- total_train_batch_size: 16
- 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 |
|---|---|---|---|---|
| 0.5328 | 1.0 | 175 | 0.7887 | 0.7025 |
| 0.4456 | 2.0 | 350 | 0.5719 | 0.805 |
| 0.3917 | 3.0 | 525 | 0.3671 | 0.845 |
| 0.2785 | 4.0 | 700 | 0.2427 | 0.915 |
| 0.1368 | 5.0 | 875 | 0.0093 | 1.0 |
| 0.0036 | 6.0 | 1050 | 0.0027 | 1.0 |
| 0.0273 | 7.0 | 1225 | 0.0745 | 0.9875 |
| 0.0019 | 8.0 | 1400 | 0.0012 | 1.0 |
| 0.0015 | 9.0 | 1575 | 0.0010 | 1.0 |
| 0.0013 | 10.0 | 1750 | 0.0009 | 1.0 |
Framework versions
- Transformers 4.32.1
- Pytorch 2.1.2
- Datasets 2.16.1
- Tokenizers 0.13.3