metadata
license: apache-2.0
base_model: facebook/hubert-base-ls960
tags:
- audio-classification
- hubert
- esc50
- generated_from_trainer
metrics:
- accuracy
model-index:
- name: hubert-esc50-finetuned-v2
results: []
hubert-esc50-finetuned-v2
This model is a fine-tuned version of facebook/hubert-base-ls960 on the ESC-50 dataset. It achieves the following results on the evaluation set:
- Loss: 2.0479
- Accuracy: 0.445
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: 5e-05
- train_batch_size: 8
- eval_batch_size: 8
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 10
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|---|---|---|---|---|
| 3.5088 | 1.0 | 200 | 3.4844 | 0.0825 |
| 3.2062 | 2.0 | 400 | 3.1259 | 0.135 |
| 2.9114 | 3.0 | 600 | 2.9266 | 0.1325 |
| 2.7927 | 4.0 | 800 | 2.7796 | 0.1925 |
| 2.4747 | 5.0 | 1000 | 2.6559 | 0.2175 |
| 2.4665 | 6.0 | 1200 | 2.4073 | 0.3125 |
| 2.1922 | 7.0 | 1400 | 2.3220 | 0.355 |
| 2.0926 | 8.0 | 1600 | 2.1544 | 0.405 |
| 1.8655 | 9.0 | 1800 | 2.0781 | 0.4175 |
| 1.9552 | 10.0 | 2000 | 2.0479 | 0.445 |
Framework versions
- Transformers 4.40.2
- Pytorch 2.3.0+cu121
- Datasets 2.19.1
- Tokenizers 0.19.1