metadata
license: apache-2.0
base_model: bert-base-cased
tags:
- generated_from_trainer
metrics:
- precision
- recall
- f1
- accuracy
model-index:
- name: bert-finetuned-gesture-prediction-21-classes
results: []
bert-finetuned-gesture-prediction-21-classes
This model is a fine-tuned version of bert-base-cased on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.9626
- Precision: 0.8178
- Recall: 0.8178
- F1: 0.8178
- Accuracy: 0.8075
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: 6.042200829392303e-05
- train_batch_size: 64
- eval_batch_size: 64
- 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 | Precision | Recall | F1 | Accuracy |
|---|---|---|---|---|---|---|---|
| 2.3221 | 1.0 | 26 | 1.4762 | 0.6969 | 0.6969 | 0.6969 | 0.6192 |
| 1.2093 | 2.0 | 52 | 0.9843 | 0.7634 | 0.7634 | 0.7634 | 0.7469 |
| 0.7309 | 3.0 | 78 | 0.8908 | 0.7878 | 0.7878 | 0.7878 | 0.7690 |
| 0.4596 | 4.0 | 104 | 0.8613 | 0.7894 | 0.7894 | 0.7894 | 0.7763 |
| 0.2947 | 5.0 | 130 | 0.8971 | 0.8075 | 0.8075 | 0.8075 | 0.7962 |
| 0.1921 | 6.0 | 156 | 0.8838 | 0.8063 | 0.8063 | 0.8063 | 0.7956 |
| 0.1348 | 7.0 | 182 | 0.9271 | 0.8166 | 0.8166 | 0.8166 | 0.8057 |
| 0.0986 | 8.0 | 208 | 0.9548 | 0.8137 | 0.8137 | 0.8137 | 0.8035 |
| 0.073 | 9.0 | 234 | 0.9553 | 0.8174 | 0.8174 | 0.8174 | 0.8063 |
| 0.0619 | 10.0 | 260 | 0.9626 | 0.8178 | 0.8178 | 0.8178 | 0.8075 |
Framework versions
- Transformers 4.40.1
- Pytorch 2.2.1+cu121
- Datasets 2.19.0
- Tokenizers 0.19.1