carlfeynman's picture
End of training
b80472f verified
|
raw
history blame
2 kB
---
license: apache-2.0
base_model: ntu-spml/distilhubert
tags:
- generated_from_trainer
datasets:
- marsyas/gtzan
metrics:
- accuracy
model-index:
- name: carl-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: 0.81
---
<!-- 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. -->
# carl-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: 0.7695
- Accuracy: 0.81
## 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: 5
- mixed_precision_training: Native AMP
### Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|:-------------:|:-----:|:----:|:---------------:|:--------:|
| 1.7944 | 1.0 | 113 | 1.7209 | 0.52 |
| 1.2247 | 2.0 | 226 | 1.1857 | 0.75 |
| 1.0477 | 3.0 | 339 | 0.9697 | 0.74 |
| 0.7418 | 4.0 | 452 | 0.8605 | 0.78 |
| 0.6595 | 5.0 | 565 | 0.7695 | 0.81 |
### Framework versions
- Transformers 4.38.2
- Pytorch 1.12.1+cu116
- Datasets 2.4.0
- Tokenizers 0.15.2