bert-finetuned-gesture-prediction-5-classes
This model is a fine-tuned version of bert-base-cased on the None dataset. It achieves the following results on the validation set:
- Loss: 0.4958
- Accuracy: 0.8636
- Precision: 0.8662
- Recall: 0.8636
- F1: 0.8625
It achieves the following results on the test set:
- Loss: 0.4599
- Accuracy: 0.8561
- Precision: 0.8578
- Recall: 0.8561
- F1: 0.8533
Model description
More information needed
Intended uses & limitations
More information needed
Training and evaluation data
The model has been trained with the qfrodicio/gesture-prediction-5-classes dataset
Training procedure
Training hyperparameters
The following hyperparameters were used during training:
- learning_rate: 2e-05
- weight_decay: 0.01
- train_batch_size: 16
- eval_batch_size: 16
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 10
Training results
Training Loss | Epoch | Step | Validation Loss | Accuracy | Precision | Recall | F1 |
---|---|---|---|---|---|---|---|
1.3816 | 1.0 | 71 | 0.6929 | 0.7820 | 0.7518 | 0.7820 | 0.7510 |
0.546 | 2.0 | 142 | 0.5128 | 0.8591 | 0.8614 | 0.8591 | 0.8579 |
0.3026 | 3.0 | 213 | 0.4958 | 0.8636 | 0.8662 | 0.8636 | 0.8625 |
0.1689 | 4.0 | 284 | 0.5090 | 0.8688 | 0.8694 | 0.8688 | 0.8678 |
0.1085 | 5.0 | 355 | 0.5306 | 0.8794 | 0.8813 | 0.8794 | 0.8786 |
0.0684 | 6.0 | 426 | 0.5516 | 0.8776 | 0.8774 | 0.8776 | 0.8765 |
0.0485 | 7.0 | 497 | 0.6051 | 0.8779 | 0.8794 | 0.8779 | 0.8770 |
0.0341 | 8.0 | 568 | 0.6224 | 0.8781 | 0.8780 | 0.8781 | 0.8776 |
0.0251 | 9.0 | 639 | 0.6429 | 0.8812 | 0.8817 | 0.8812 | 0.8805 |
0.021 | 10.0 | 710 | 0.6456 | 0.8807 | 0.8811 | 0.8807 | 0.8798 |
Framework versions
- Transformers 4.26.1
- Pytorch 1.13.1+cu116
- Datasets 2.10.1
- Tokenizers 0.13.2
- Downloads last month
- 21
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.