Ast Finetuned Gtzan

--- library_name: transformers license: bsd-3-clause base_model: MIT/ast-finetuned-audioset-10-10-0.4593 tags: - generated_from_trainer datasets: - marsyas/gtzan model-index: - name: ast-finetuned-gtzan results: [] --- <!-- 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. --> # ast-finetuned-gtzan This model is a fine-tuned version of [MIT/ast-finetuned-audioset-10-10-0.4593](https://huggingface.co/MIT/ast-finetuned-audioset-10-10-0.4593) on the GTZAN dataset. ## 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: 1e-05 - train_batch_size: 16 - eval_batch_size: 16 - seed: 42 - 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 | |:-------------:|:-----:|:----:|:---------------:|:--------:| | 1.3765 | 1.0 | 57 | 1.2784 | 0.74 | | 0.5129 | 2.0 | 114 | 0.5108 | 0.82 | | 0.2895 | 3.0 | 171 | 0.4373 | 0.84 | | 0.1270 | 4.0 | 228 | 0.3689 | 0.86 | | 0.0739 | 5.0 | 285 | 0.2952 | 0.88 | | 0.0660 | 6.0 | 342 | 0.3119 | 0.89 | | 0.0052 | 7.0 | 399 | 0.2709 | 0.88 | | 0.0026 | 8.0 | 456 | 0.2815 | 0.87 | | 0.0024 | 9.0 | 513 | 0.2565 | 0.92 | | 0.0019 | 10.0 | 570 | 0.2623 | 0.91 | ### Framework versions - Transformers 5.4.0 - Pytorch 2.11.0+cu130 - Datasets 4.8.4 - Tokenizers 0.22.2

Source context: 5 downloads · 0 likes · Pipeline audio-classification · Library transformers · Repo kethankrk/ast-finetuned-gtzan