metadata
license: apache-2.0
base_model: ntu-spml/distilhubert
tags:
- generated_from_trainer
datasets:
- marsyas/gtzan
metrics:
- accuracy
model-index:
- name: distilhubert-finetuned-gtzan-2.5E-5rate
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: 0.82
distilhubert-finetuned-gtzan-2.5E-5rate
This model is a fine-tuned version of ntu-spml/distilhubert on the GTZAN dataset. It achieves the following results on the evaluation set:
- Loss: 0.5939
- Accuracy: 0.82
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: 2.5e-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: 15
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|---|---|---|---|---|
| 2.2487 | 1.0 | 113 | 2.1744 | 0.41 |
| 1.7534 | 2.0 | 226 | 1.6280 | 0.65 |
| 1.4458 | 3.0 | 339 | 1.2993 | 0.7 |
| 1.2271 | 4.0 | 452 | 1.1119 | 0.72 |
| 1.115 | 5.0 | 565 | 1.0119 | 0.75 |
| 0.834 | 6.0 | 678 | 0.8967 | 0.77 |
| 1.0247 | 7.0 | 791 | 0.8154 | 0.78 |
| 0.6211 | 8.0 | 904 | 0.7035 | 0.81 |
| 0.7136 | 9.0 | 1017 | 0.6755 | 0.8 |
| 0.464 | 10.0 | 1130 | 0.6808 | 0.84 |
| 0.2952 | 11.0 | 1243 | 0.6245 | 0.8 |
| 0.3117 | 12.0 | 1356 | 0.6150 | 0.84 |
| 0.24 | 13.0 | 1469 | 0.6000 | 0.82 |
| 0.2554 | 14.0 | 1582 | 0.5952 | 0.83 |
| 0.2452 | 15.0 | 1695 | 0.5939 | 0.82 |
Framework versions
- Transformers 4.31.0
- Pytorch 2.0.1+cu118
- Datasets 2.13.1
- Tokenizers 0.13.3