metadata
license: apache-2.0
base_model: facebook/wav2vec2-base
tags:
- generated_from_trainer
metrics:
- accuracy
model-index:
- name: Audioclasswindows
results: []
Audioclasswindows
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: 2.6744
- Accuracy: 0.0796
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: 16
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|---|---|---|---|---|
| No log | 0.8 | 3 | 2.6364 | 0.1062 |
| No log | 1.87 | 7 | 2.6465 | 0.0442 |
| 2.6363 | 2.93 | 11 | 2.6420 | 0.0973 |
| 2.6363 | 4.0 | 15 | 2.6543 | 0.0796 |
| 2.6363 | 4.8 | 18 | 2.6579 | 0.0885 |
| 2.6244 | 5.87 | 22 | 2.6587 | 0.0885 |
| 2.6244 | 6.93 | 26 | 2.6608 | 0.0885 |
| 2.6103 | 8.0 | 30 | 2.6632 | 0.0796 |
| 2.6103 | 8.8 | 33 | 2.6664 | 0.0796 |
| 2.6103 | 9.87 | 37 | 2.6692 | 0.0796 |
| 2.6019 | 10.93 | 41 | 2.6722 | 0.0796 |
| 2.6019 | 12.0 | 45 | 2.6740 | 0.0796 |
| 2.6019 | 12.8 | 48 | 2.6744 | 0.0796 |
Framework versions
- Transformers 4.35.2
- Pytorch 2.1.0+cu121
- Datasets 2.16.1
- Tokenizers 0.15.0