metadata
license: apache-2.0
tags:
- generated_from_trainer
metrics:
- precision
- recall
- f1
- accuracy
model-index:
- name: bert-finetuned-gesture-prediction-5-classes
results: []
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 evaluation set:
- Loss: 0.4973
- Precision: 0.6620
- Recall: 0.7636
- F1: 0.7092
- Accuracy: 0.8771
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: 6.988334780126428e-05
- 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: 3
Training results
| Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1 | Accuracy |
|---|---|---|---|---|---|---|---|
| 0.9623 | 1.0 | 71 | 0.4925 | 0.5876 | 0.7111 | 0.6435 | 0.8578 |
| 0.3475 | 2.0 | 142 | 0.4570 | 0.6348 | 0.7515 | 0.6883 | 0.8656 |
| 0.1512 | 3.0 | 213 | 0.4973 | 0.6620 | 0.7636 | 0.7092 | 0.8771 |
Framework versions
- Transformers 4.26.1
- Pytorch 1.13.1+cu116
- Datasets 2.10.1
- Tokenizers 0.13.2