yuval6967's picture
update model card README.md
053a372
|
raw
history blame
2.54 kB
---
license: apache-2.0
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: 0.84
---
<!-- 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: 0.6273
- Accuracy: 0.84
## 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: 3e-05
- train_batch_size: 16
- eval_batch_size: 16
- 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: 15
### Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|:-------------:|:-----:|:----:|:---------------:|:--------:|
| 2.253 | 1.0 | 57 | 2.2124 | 0.43 |
| 1.8499 | 2.0 | 114 | 1.7776 | 0.56 |
| 1.4569 | 3.0 | 171 | 1.4535 | 0.69 |
| 1.3715 | 4.0 | 228 | 1.2296 | 0.74 |
| 1.097 | 5.0 | 285 | 1.0841 | 0.73 |
| 0.9876 | 6.0 | 342 | 0.9591 | 0.76 |
| 0.8501 | 7.0 | 399 | 0.8912 | 0.75 |
| 0.8233 | 8.0 | 456 | 0.8314 | 0.75 |
| 0.7055 | 9.0 | 513 | 0.7713 | 0.77 |
| 0.5709 | 10.0 | 570 | 0.7053 | 0.81 |
| 0.4924 | 11.0 | 627 | 0.7325 | 0.79 |
| 0.4679 | 12.0 | 684 | 0.6562 | 0.8 |
| 0.496 | 13.0 | 741 | 0.6376 | 0.85 |
| 0.3827 | 14.0 | 798 | 0.6331 | 0.84 |
| 0.4118 | 15.0 | 855 | 0.6273 | 0.84 |
### Framework versions
- Transformers 4.31.0.dev0
- Pytorch 1.13.0
- Datasets 2.1.0
- Tokenizers 0.13.3