distilhubert-finetuned-ravdess
This model is a fine-tuned version of ntu-spml/distilhubert on the RAVDESS dataset. It achieves the following results on the evaluation set:
- Loss: 0.2810
- Accuracy: 0.9236
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: 5e-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
Training results
Training Loss | Epoch | Step | Validation Loss | Accuracy |
---|---|---|---|---|
1.7599 | 1.0 | 162 | 1.7350 | 0.3264 |
1.3271 | 2.0 | 324 | 1.1987 | 0.5972 |
0.8845 | 3.0 | 486 | 0.8824 | 0.7639 |
0.6083 | 4.0 | 648 | 0.5919 | 0.8403 |
0.4952 | 5.0 | 810 | 0.4469 | 0.8611 |
0.1386 | 6.0 | 972 | 0.3736 | 0.8681 |
0.1028 | 7.0 | 1134 | 0.3645 | 0.8819 |
0.053 | 8.0 | 1296 | 0.3079 | 0.9028 |
0.0149 | 9.0 | 1458 | 0.2723 | 0.9236 |
0.0154 | 10.0 | 1620 | 0.2810 | 0.9236 |
Framework versions
- Transformers 4.30.2
- Pytorch 2.0.0
- Datasets 2.13.0
- Tokenizers 0.13.3
- Downloads last month
- 77
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.