Downloads · 30 days
14
27% of all-time downloads
ast-doubly-finetuned-gtzan
dmcartor/ast-doubly-finetuned-gtzan
ast-doubly-finetuned-gtzan is a machine learning model from dmcartor. Use it for the machine learning task on the model card, and read the license before you ship it in a product. The card lists the license as bsd-3-clause.
should probably proofread and complete it, then remove this comment. --
All-time downloads
52
Public
Parameters
86.2M
6.2 GB on disk
Likes
0
Public
Repo makeup
Click a slice to open those files.
.safetensors345 MB · 100%
At a glance
- License
- bsd-3-clause
- Model type
- audio-spectrogram-transformer
- Access
- Public
- Created
- Aug 2, 2024
- Updated
- Aug 8, 2024
- SHA
- cefac853
Base models
Datasets
Model card
From the Hugging Face model README
<!-- 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. -->
ast-finetuned-gtzan-doubly-finetuned-gtzan
This model is a fine-tuned version of ramsri818/ast-finetuned-gtzan on the GTZAN dataset. It achieves the following results on the evaluation set:
- Loss: 0.5406
- Accuracy: 0.91
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: 1e-05
- train_batch_size: 4
- eval_batch_size: 4
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: cosine
- lr_scheduler_warmup_ratio: 0.1
- num_epochs: 10
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|---|---|---|---|---|
| 1.242 | 1.0 | 400 | 1.4400 | 0.78 |
| 0.8054 | 2.0 | 800 | 1.6792 | 0.79 |
| 0.4533 | 3.0 | 1200 | 1.3949 | 0.81 |
| 0.4987 | 4.0 | 1600 | 1.7042 | 0.8 |
| 0.1096 | 5.0 | 2000 | 1.5618 | 0.82 |
| 0.0328 | 6.0 | 2400 | 1.4837 | 0.82 |
| 0.0627 | 7.0 | 2800 | 1.5624 | 0.82 |
| 0.2176 | 8.0 | 3200 | 1.5942 | 0.82 |
| 0.0267 | 9.0 | 3600 | 1.6282 | 0.83 |
| 0.1138 | 10.0 | 4000 | 1.6218 | 0.83 |
Framework versions
- Transformers 4.42.4
- Pytorch 2.3.1+cu121
- Datasets 2.20.0
- Tokenizers 0.19.1
- Type
- audio-spectrogram-transformer
- License
- bsd-3-clause
- Created
- Aug 2, 2024
- Updated
- Aug 8, 2024