metadata
license: apache-2.0
tags:
- generated_from_trainer
datasets:
- marsyas/gtzan
metrics:
- accuracy
model-index:
- name: distilhubert-finetuned-gtzan
results: []
distilhubert-finetuned-gtzan
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: 0.6995
- Accuracy: 0.87
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: 0.0001
- 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: 0.2
- num_epochs: 10
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|---|---|---|---|---|
| 1.7415 | 1.0 | 113 | 1.8323 | 0.43 |
| 1.2237 | 2.0 | 226 | 1.2223 | 0.65 |
| 0.8856 | 3.0 | 339 | 0.8612 | 0.71 |
| 0.658 | 4.0 | 452 | 0.6679 | 0.8 |
| 0.2701 | 5.0 | 565 | 0.5787 | 0.81 |
| 0.1232 | 6.0 | 678 | 0.7164 | 0.81 |
| 0.0726 | 7.0 | 791 | 0.6973 | 0.84 |
| 0.0253 | 8.0 | 904 | 0.6665 | 0.86 |
| 0.0939 | 9.0 | 1017 | 0.6756 | 0.87 |
| 0.0112 | 10.0 | 1130 | 0.6995 | 0.87 |
Framework versions
- Transformers 4.30.2
- Pytorch 2.0.1+cu117
- Datasets 2.13.1
- Tokenizers 0.13.3