metadata
license: apache-2.0
base_model: bookbot/distil-ast-audioset
tags:
- generated_from_trainer
datasets:
- marsyas/gtzan
metrics:
- accuracy
model-index:
- name: distil-ast-audioset-finetuned-gtzan
results:
- task:
name: Audio Classification
type: audio-classification
dataset:
name: GTZAN
type: marsyas/gtzan
config: all
split: train
args: all
metrics:
- name: Accuracy
type: accuracy
value: 0.9
distil-ast-audioset-finetuned-gtzan
This model is a fine-tuned version of bookbot/distil-ast-audioset on the GTZAN dataset. It achieves the following results on the evaluation set:
- Loss: 0.5918
- Accuracy: 0.9
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
- lr_scheduler_warmup_ratio: 0.1
- num_epochs: 20
Training results
Training Loss | Epoch | Step | Validation Loss | Accuracy |
---|---|---|---|---|
0.9796 | 1.0 | 113 | 0.6252 | 0.85 |
0.7554 | 2.0 | 226 | 0.4882 | 0.86 |
0.5652 | 3.0 | 339 | 0.6223 | 0.77 |
0.193 | 4.0 | 452 | 0.6506 | 0.84 |
0.0392 | 5.0 | 565 | 0.7147 | 0.86 |
0.2759 | 6.0 | 678 | 0.8537 | 0.81 |
0.2412 | 7.0 | 791 | 0.6172 | 0.87 |
0.0648 | 8.0 | 904 | 0.6085 | 0.86 |
0.308 | 9.0 | 1017 | 0.7734 | 0.86 |
0.0002 | 10.0 | 1130 | 0.6427 | 0.88 |
0.0001 | 11.0 | 1243 | 0.6242 | 0.89 |
0.0 | 12.0 | 1356 | 0.5868 | 0.9 |
0.0001 | 13.0 | 1469 | 0.6369 | 0.9 |
0.0001 | 14.0 | 1582 | 0.6108 | 0.9 |
0.0001 | 15.0 | 1695 | 0.6002 | 0.9 |
0.0 | 16.0 | 1808 | 0.5925 | 0.9 |
0.0 | 17.0 | 1921 | 0.5898 | 0.9 |
0.0 | 18.0 | 2034 | 0.5877 | 0.9 |
0.0 | 19.0 | 2147 | 0.5926 | 0.9 |
0.0001 | 20.0 | 2260 | 0.5918 | 0.9 |
Framework versions
- Transformers 4.31.0
- Pytorch 2.0.1+cu118
- Datasets 2.14.4
- Tokenizers 0.13.3