Marco-Cheung's picture
update model card README.md
654df5e
---
license: apache-2.0
base_model: ntu-spml/distilhubert
tags:
- generated_from_trainer
datasets:
- marsyas/gtzan
metrics:
- accuracy
model-index:
- name: distilhubert-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: 0.83
---
<!-- 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. -->
# distilhubert-finetuned-gtzan
This model is a fine-tuned version of [ntu-spml/distilhubert](https://huggingface.co/ntu-spml/distilhubert) on the GTZAN dataset.
It achieves the following results on the evaluation set:
- Loss: 0.5933
- Accuracy: 0.83
## 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: 10
### Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|:-------------:|:-----:|:----:|:---------------:|:--------:|
| 1.9825 | 1.0 | 113 | 1.7658 | 0.48 |
| 1.2943 | 2.0 | 226 | 1.2478 | 0.65 |
| 0.9837 | 3.0 | 339 | 0.9757 | 0.71 |
| 0.8201 | 4.0 | 452 | 0.8420 | 0.72 |
| 0.5363 | 5.0 | 565 | 0.6741 | 0.83 |
| 0.3417 | 6.0 | 678 | 0.7083 | 0.76 |
| 0.4129 | 7.0 | 791 | 0.5941 | 0.81 |
| 0.1681 | 8.0 | 904 | 0.5954 | 0.84 |
| 0.2398 | 9.0 | 1017 | 0.5819 | 0.85 |
| 0.1346 | 10.0 | 1130 | 0.5933 | 0.83 |
### Framework versions
- Transformers 4.32.0.dev0
- Pytorch 2.0.0
- Datasets 2.1.0
- Tokenizers 0.13.3