--- 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: 0.82 --- # 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: 0.5914 - 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: 0.0001 - 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: 10 ### Training results | Training Loss | Epoch | Step | Validation Loss | Accuracy | |:-------------:|:-----:|:----:|:---------------:|:--------:| | 1.9157 | 1.0 | 57 | 1.7318 | 0.45 | | 1.2425 | 2.0 | 114 | 1.1454 | 0.7 | | 0.8878 | 3.0 | 171 | 0.8611 | 0.76 | | 0.6978 | 4.0 | 228 | 0.7691 | 0.77 | | 0.4136 | 5.0 | 285 | 0.6523 | 0.82 | | 0.2548 | 6.0 | 342 | 0.5780 | 0.84 | | 0.183 | 7.0 | 399 | 0.6210 | 0.81 | | 0.0801 | 8.0 | 456 | 0.6295 | 0.82 | | 0.0709 | 9.0 | 513 | 0.6664 | 0.82 | | 0.0423 | 10.0 | 570 | 0.5914 | 0.82 | ### Framework versions - Transformers 4.31.0 - Pytorch 1.13.1 - Datasets 2.13.1 - Tokenizers 0.13.3