Distilhubert Finetuned Gtzan

--- library_name: transformers 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 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: 0.5659 - 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: 5e-05 - train_batch_size: 2 - eval_batch_size: 2 - seed: 1000 - gradient_accumulation_steps: 4 - total_train_batch_size: 8 - optimizer: Use OptimizerNames.ADAMW_TORCH_FUSED with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments - lr_scheduler_type: linear - lr_scheduler_warmup_steps: 100 - num_epochs: 10 - mixed_precision_training: Native AMP ### Training results | Training Loss | Epoch | Step | Validation Loss | Accuracy | |:-------------:|:-----:|:----:|:---------------:|:--------:| | 1.9742 | 1.0 | 113 | 1.8100 | 0.4 | | 1.0875 | 2.0 | 226 | 1.0744 | 0.71 | | 0.8231 | 3.0 | 339 | 0.7786 | 0.73 | | 0.9411 | 4.0 | 452 | 0.6647 | 0.79 | | 0.5325 | 5.0 | 565 | 0.7246 | 0.81 | | 0.2897 | 6.0 | 678 | 0.5348 | 0.84 | | 0.2653 | 7.0 | 791 | 0.5124 | 0.85 | | 0.1952 | 8.0 | 904 | 0.6130 | 0.83 | | 0.1077 | 9.0 | 1017 | 0.5961 | 0.84 | | 0.0605 | 10.0 | 1130 | 0.5659 | 0.84 | ### Framework versions - Transformers 5.3.0.dev0 - Pytorch 2.10.0+cu128 - Datasets 4.0.0 - Tokenizers 0.22.2

Source context: 6 downloads · 0 likes · Pipeline audio-classification · Library transformers · Repo AlGM93/distilhubert-finetuned-gtzan