kfahn's picture
update model card README.md
d466811
---
license: bsd-3-clause
base_model: MIT/ast-finetuned-audioset-10-10-0.4593
tags:
- generated_from_trainer
datasets:
- marsyas/gtzan
metrics:
- accuracy
model-index:
- name: ast-finetuned-audioset-10-10-0.4593-MIT/ast-finetuned-audioset-v1
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: 0.91
---
<!-- 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-audioset-10-10-0.4593-MIT/ast-finetuned-audioset-v1
This model is a fine-tuned version of [MIT/ast-finetuned-audioset-10-10-0.4593](https://huggingface.co/MIT/ast-finetuned-audioset-10-10-0.4593) on the GTZAN dataset.
It achieves the following results on the evaluation set:
- Loss: 0.4979
- 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: 5e-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: linear
- lr_scheduler_warmup_ratio: 0.1
- num_epochs: 10
### Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|:-------------:|:-----:|:----:|:---------------:|:--------:|
| 0.8293 | 1.0 | 225 | 0.5020 | 0.85 |
| 1.4048 | 2.0 | 450 | 0.5068 | 0.84 |
| 0.8456 | 3.0 | 675 | 0.9684 | 0.82 |
| 0.004 | 4.0 | 900 | 0.5937 | 0.86 |
| 0.0981 | 5.0 | 1125 | 0.5353 | 0.87 |
| 0.0001 | 6.0 | 1350 | 0.6000 | 0.89 |
| 0.4493 | 7.0 | 1575 | 0.6168 | 0.9 |
| 0.0001 | 8.0 | 1800 | 0.5155 | 0.91 |
| 0.0001 | 9.0 | 2025 | 0.5043 | 0.91 |
| 0.0 | 10.0 | 2250 | 0.4979 | 0.91 |
### Framework versions
- Transformers 4.31.0.dev0
- Pytorch 2.0.1+cu118
- Datasets 2.13.1
- Tokenizers 0.13.3