drone-audio-detection-05-17-trial-0
This model is a fine-tuned version of MIT/ast-finetuned-audioset-10-10-0.4593 on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.0131
- Accuracy: 0.996
- Precision: 0.9987
- Recall: 0.9962
- F1: 0.9974
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: 1.1463891217797098e-05
- train_batch_size: 32
- eval_batch_size: 8
- seed: 42
- gradient_accumulation_steps: 4
- total_train_batch_size: 128
- 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: cosine
- lr_scheduler_warmup_ratio: 0.1651375762118582
- num_epochs: 5
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy | Precision | Recall | F1 |
|---|---|---|---|---|---|---|---|
| 0.0441 | 1.0 | 63 | 0.0255 | 0.992 | 0.9987 | 0.9910 | 0.9949 |
| 0.0176 | 2.0 | 126 | 0.0160 | 0.996 | 1.0 | 0.9949 | 0.9974 |
| 0.0027 | 3.0 | 189 | 0.0128 | 0.9955 | 0.9987 | 0.9955 | 0.9971 |
| 0.0003 | 4.0 | 252 | 0.0132 | 0.9955 | 0.9981 | 0.9962 | 0.9971 |
| 0.0002 | 4.928 | 310 | 0.0131 | 0.996 | 0.9987 | 0.9962 | 0.9974 |
Framework versions
- Transformers 4.51.3
- Pytorch 2.6.0+cu124
- Datasets 3.6.0
- Tokenizers 0.21.1