metadata
license: bsd-3-clause
base_model: minoosh/ast-finetuned-audioset-10-10-0.4593-finetuned-ie
tags:
- generated_from_trainer
metrics:
- accuracy
model-index:
- name: ASTie-finetuned-on-shEMO_speech
results: []
ASTie-finetuned-on-shEMO_speech
This model is a fine-tuned version of minoosh/ast-finetuned-audioset-10-10-0.4593-finetuned-ie on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 1.1646
- Accuracy: 0.81
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: 8
- eval_batch_size: 8
- seed: 42
- gradient_accumulation_steps: 4
- total_train_batch_size: 32
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_ratio: 0.1
- num_epochs: 15
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|---|---|---|---|---|
| 0.8071 | 1.0 | 75 | 0.7501 | 0.7933 |
| 0.6495 | 2.0 | 150 | 0.6482 | 0.78 |
| 0.2065 | 3.0 | 225 | 0.6468 | 0.82 |
| 0.0629 | 4.0 | 300 | 0.8847 | 0.78 |
| 0.014 | 5.0 | 375 | 0.9425 | 0.81 |
| 0.0086 | 6.0 | 450 | 0.8603 | 0.83 |
| 0.0017 | 7.0 | 525 | 0.9790 | 0.8367 |
| 0.0005 | 8.0 | 600 | 0.9910 | 0.8267 |
| 0.0002 | 9.0 | 675 | 0.9920 | 0.8433 |
| 0.0067 | 10.0 | 750 | 1.0013 | 0.84 |
| 0.0001 | 11.0 | 825 | 1.0186 | 0.8433 |
| 0.0001 | 12.0 | 900 | 1.0189 | 0.8433 |
| 0.0001 | 13.0 | 975 | 1.0227 | 0.8433 |
| 0.0038 | 14.0 | 1050 | 1.0279 | 0.8433 |
| 0.0034 | 15.0 | 1125 | 1.0293 | 0.8433 |
Framework versions
- Transformers 4.34.1
- Pytorch 1.12.0+cu116
- Datasets 2.14.6
- Tokenizers 0.14.1