ast_18-finetuned-ICBHI
This model is a fine-tuned version of MIT/ast-finetuned-audioset-10-10-0.4593 on the None dataset. It achieves the following results on the evaluation set:
- Loss: 1.0867
- Accuracy: 0.5757
- Sensitivity: 0.1164
- Specificity: 0.9183
- Score: 0.5173
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: 3e-05
- train_batch_size: 32
- eval_batch_size: 32
- seed: 42
- gradient_accumulation_steps: 4
- total_train_batch_size: 128
- 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 | Sensitivity | Specificity | Score |
---|---|---|---|---|---|---|---|
1.5436 | 0.98 | 32 | 1.4656 | 0.1684 | 0.3127 | 0.0608 | 0.1867 |
1.2922 | 2.0 | 65 | 1.2055 | 0.4530 | 0.1121 | 0.7072 | 0.4097 |
1.2213 | 2.98 | 97 | 1.1364 | 0.5387 | 0.0450 | 0.9068 | 0.4759 |
1.149 | 4.0 | 130 | 1.1176 | 0.5543 | 0.0731 | 0.9132 | 0.4931 |
1.1558 | 4.98 | 162 | 1.1035 | 0.5630 | 0.0705 | 0.9303 | 0.5004 |
1.1363 | 6.0 | 195 | 1.1006 | 0.5655 | 0.1020 | 0.9113 | 0.5066 |
1.1138 | 6.98 | 227 | 1.0938 | 0.5699 | 0.1121 | 0.9113 | 0.5117 |
1.0807 | 8.0 | 260 | 1.0897 | 0.5742 | 0.1147 | 0.9170 | 0.5158 |
1.1071 | 8.98 | 292 | 1.0867 | 0.5757 | 0.1138 | 0.9202 | 0.5170 |
1.1017 | 9.85 | 320 | 1.0867 | 0.5757 | 0.1164 | 0.9183 | 0.5173 |
Framework versions
- Transformers 4.29.2
- Pytorch 2.0.1+cu118
- Datasets 2.12.0
- Tokenizers 0.13.3
- Downloads last month
- 10
This model does not have enough activity to be deployed to Inference API (serverless) yet. Increase its social
visibility and check back later, or deploy to Inference Endpoints (dedicated)
instead.