metadata
license: apache-2.0
tags:
- generated_from_trainer
metrics:
- accuracy
- precision
- recall
- f1
model-index:
- name: distilbert-finetuned-gesture-prediction-21-classes
results: []
distilbert-finetuned-gesture-prediction-21-classes
This model is a fine-tuned version of distilbert-base-cased on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.9212
- Accuracy: 0.8029
- Precision: 0.7978
- Recall: 0.8029
- F1: 0.7974
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: 2e-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: 10
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy | Precision | Recall | F1 |
|---|---|---|---|---|---|---|---|
| 2.1942 | 1.0 | 104 | 1.3566 | 0.7113 | 0.6581 | 0.7113 | 0.6683 |
| 1.1713 | 2.0 | 208 | 1.0182 | 0.7626 | 0.7445 | 0.7626 | 0.7348 |
| 0.8285 | 3.0 | 312 | 0.9028 | 0.7789 | 0.7626 | 0.7789 | 0.7607 |
| 0.6374 | 4.0 | 416 | 0.8845 | 0.7959 | 0.7950 | 0.7959 | 0.7890 |
| 0.4991 | 5.0 | 520 | 0.8936 | 0.7997 | 0.7949 | 0.7997 | 0.7865 |
| 0.3908 | 6.0 | 624 | 0.8829 | 0.7910 | 0.7879 | 0.7910 | 0.7864 |
| 0.3234 | 7.0 | 728 | 0.9004 | 0.7946 | 0.7898 | 0.7946 | 0.7888 |
| 0.2688 | 8.0 | 832 | 0.8947 | 0.8047 | 0.7993 | 0.8047 | 0.7995 |
| 0.2392 | 9.0 | 936 | 0.9154 | 0.8024 | 0.7980 | 0.8024 | 0.7961 |
| 0.2103 | 10.0 | 1040 | 0.9212 | 0.8029 | 0.7978 | 0.8029 | 0.7974 |
Framework versions
- Transformers 4.26.1
- Pytorch 1.13.1+cu116
- Datasets 2.10.1
- Tokenizers 0.13.2