jjsprockel's picture
End of training
eeaedc2
---
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: 0.89
---
<!-- 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. -->
# distil-ast-audioset-finetuned-gtzan
This model is a fine-tuned version of [bookbot/distil-ast-audioset](https://huggingface.co/bookbot/distil-ast-audioset) on the GTZAN dataset.
It achieves the following results on the evaluation set:
- Loss: 0.3897
- Accuracy: 0.89
## 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: 4e-05
- train_batch_size: 8
- eval_batch_size: 8
- seed: 42
- gradient_accumulation_steps: 4
- total_train_batch_size: 32
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_ratio: 0.1
- num_epochs: 6
### Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|:-------------:|:-----:|:----:|:---------------:|:--------:|
| 1.321 | 0.99 | 28 | 0.6668 | 0.82 |
| 0.4901 | 1.98 | 56 | 0.5119 | 0.85 |
| 0.2659 | 2.97 | 84 | 0.4564 | 0.87 |
| 0.1518 | 4.0 | 113 | 0.3853 | 0.88 |
| 0.0626 | 4.99 | 141 | 0.3862 | 0.89 |
| 0.0309 | 5.95 | 168 | 0.3897 | 0.89 |
### Framework versions
- Transformers 4.32.0.dev0
- Pytorch 2.0.1+cu118
- Datasets 2.14.4
- Tokenizers 0.13.3