update model card README.md
Browse files
README.md
ADDED
|
@@ -0,0 +1,74 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
license: bsd-3-clause
|
| 3 |
+
tags:
|
| 4 |
+
- generated_from_trainer
|
| 5 |
+
metrics:
|
| 6 |
+
- accuracy
|
| 7 |
+
model-index:
|
| 8 |
+
- name: ast_21-finetuned-ICBHI
|
| 9 |
+
results: []
|
| 10 |
+
---
|
| 11 |
+
|
| 12 |
+
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
| 13 |
+
should probably proofread and complete it, then remove this comment. -->
|
| 14 |
+
|
| 15 |
+
# ast_21-finetuned-ICBHI
|
| 16 |
+
|
| 17 |
+
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 None dataset.
|
| 18 |
+
It achieves the following results on the evaluation set:
|
| 19 |
+
- Loss: 2.5318
|
| 20 |
+
- Accuracy: 0.6797
|
| 21 |
+
- Sensitivity: 0.5322
|
| 22 |
+
- Specificity: 0.8118
|
| 23 |
+
- Score: 0.6720
|
| 24 |
+
|
| 25 |
+
## Model description
|
| 26 |
+
|
| 27 |
+
More information needed
|
| 28 |
+
|
| 29 |
+
## Intended uses & limitations
|
| 30 |
+
|
| 31 |
+
More information needed
|
| 32 |
+
|
| 33 |
+
## Training and evaluation data
|
| 34 |
+
|
| 35 |
+
More information needed
|
| 36 |
+
|
| 37 |
+
## Training procedure
|
| 38 |
+
|
| 39 |
+
### Training hyperparameters
|
| 40 |
+
|
| 41 |
+
The following hyperparameters were used during training:
|
| 42 |
+
- learning_rate: 3e-05
|
| 43 |
+
- train_batch_size: 4
|
| 44 |
+
- eval_batch_size: 4
|
| 45 |
+
- seed: 42
|
| 46 |
+
- gradient_accumulation_steps: 4
|
| 47 |
+
- total_train_batch_size: 16
|
| 48 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
| 49 |
+
- lr_scheduler_type: linear
|
| 50 |
+
- lr_scheduler_warmup_ratio: 0.1
|
| 51 |
+
- num_epochs: 10
|
| 52 |
+
|
| 53 |
+
### Training results
|
| 54 |
+
|
| 55 |
+
| Training Loss | Epoch | Step | Validation Loss | Accuracy | Sensitivity | Specificity | Score |
|
| 56 |
+
|:-------------:|:-----:|:----:|:---------------:|:--------:|:-----------:|:-----------:|:------:|
|
| 57 |
+
| 0.8802 | 1.0 | 345 | 0.9189 | 0.6355 | 0.3236 | 0.9148 | 0.6192 |
|
| 58 |
+
| 0.8729 | 2.0 | 690 | 0.8915 | 0.6283 | 0.5138 | 0.7308 | 0.6223 |
|
| 59 |
+
| 0.6646 | 3.0 | 1035 | 0.9005 | 0.6551 | 0.6043 | 0.7005 | 0.6524 |
|
| 60 |
+
| 0.3145 | 4.0 | 1380 | 1.1884 | 0.6572 | 0.4018 | 0.8860 | 0.6439 |
|
| 61 |
+
| 0.2176 | 5.0 | 1725 | 1.4167 | 0.6623 | 0.5828 | 0.7335 | 0.6582 |
|
| 62 |
+
| 0.1556 | 6.0 | 2070 | 1.9695 | 0.6732 | 0.5061 | 0.8228 | 0.6645 |
|
| 63 |
+
| 0.0144 | 7.0 | 2415 | 2.3115 | 0.6761 | 0.5506 | 0.7885 | 0.6695 |
|
| 64 |
+
| 0.0001 | 8.0 | 2760 | 2.4443 | 0.6746 | 0.5291 | 0.8049 | 0.6670 |
|
| 65 |
+
| 0.0001 | 9.0 | 3105 | 2.5163 | 0.6775 | 0.5291 | 0.8104 | 0.6698 |
|
| 66 |
+
| 0.0001 | 10.0 | 3450 | 2.5318 | 0.6797 | 0.5322 | 0.8118 | 0.6720 |
|
| 67 |
+
|
| 68 |
+
|
| 69 |
+
### Framework versions
|
| 70 |
+
|
| 71 |
+
- Transformers 4.29.2
|
| 72 |
+
- Pytorch 2.0.1+cu118
|
| 73 |
+
- Datasets 2.12.0
|
| 74 |
+
- Tokenizers 0.13.3
|