metadata
license: bsd-3-clause
base_model: MIT/ast-finetuned-audioset-10-10-0.4593
tags:
- generated_from_trainer
metrics:
- accuracy
- f1
- recall
- precision
model-index:
- name: ast-finetuned-audioset-10-10-0.4593-finetuned-common_voice
results: []
ast-finetuned-audioset-10-10-0.4593-finetuned-common_voice
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: 0.4652
- Accuracy: 0.905
- F1: 0.9049
- Recall: 0.905
- Precision: 0.9057
- Mcc: 0.8814
- Auc: 0.9874
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
- 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
- mixed_precision_training: Native AMP
Training results
Training Loss | Epoch | Step | Validation Loss | Accuracy | F1 | Recall | Precision | Mcc | Auc |
---|---|---|---|---|---|---|---|---|---|
1.0765 | 1.0 | 200 | 0.9662 | 0.5925 | 0.5411 | 0.5925 | 0.6493 | 0.5098 | 0.9152 |
0.5977 | 2.0 | 400 | 0.5536 | 0.8 | 0.7999 | 0.8 | 0.8146 | 0.7532 | 0.9670 |
0.1826 | 3.0 | 600 | 0.5388 | 0.8375 | 0.8385 | 0.8375 | 0.8491 | 0.7994 | 0.9759 |
0.1125 | 4.0 | 800 | 0.6617 | 0.85 | 0.8486 | 0.85 | 0.8636 | 0.8161 | 0.9798 |
0.0025 | 5.0 | 1000 | 0.5859 | 0.865 | 0.8653 | 0.865 | 0.8733 | 0.8333 | 0.984 |
0.0058 | 6.0 | 1200 | 0.5043 | 0.8975 | 0.8968 | 0.8975 | 0.9001 | 0.8728 | 0.9882 |
0.0 | 7.0 | 1400 | 0.4883 | 0.8925 | 0.8932 | 0.8925 | 0.8957 | 0.8660 | 0.9859 |
0.0 | 8.0 | 1600 | 0.4652 | 0.905 | 0.9050 | 0.905 | 0.9055 | 0.8814 | 0.9871 |
0.0 | 9.0 | 1800 | 0.4655 | 0.905 | 0.9049 | 0.905 | 0.9057 | 0.8814 | 0.9873 |
0.0 | 10.0 | 2000 | 0.4652 | 0.905 | 0.9049 | 0.905 | 0.9057 | 0.8814 | 0.9874 |
Framework versions
- Transformers 4.41.0
- Pytorch 2.3.0+cu121
- Datasets 2.19.1
- Tokenizers 0.19.1