metadata
license: apache-2.0
tags:
- generated_from_trainer
metrics:
- precision
- recall
- f1
- accuracy
model-index:
- name: distilbert-finetuned-gesture-prediction-5-classes
results: []
distilbert-finetuned-gesture-prediction-5-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: 0.5263
- Precision: 0.6592
- Recall: 0.7697
- F1: 0.7102
- Accuracy: 0.8714
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: 9.294052849737191e-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: 4
Training results
| Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1 | Accuracy |
|---|---|---|---|---|---|---|---|
| 0.9034 | 1.0 | 71 | 0.5358 | 0.5679 | 0.6929 | 0.6242 | 0.8347 |
| 0.3774 | 2.0 | 142 | 0.4307 | 0.6598 | 0.7758 | 0.7131 | 0.8721 |
| 0.1915 | 3.0 | 213 | 0.5510 | 0.6336 | 0.7475 | 0.6858 | 0.8589 |
| 0.09 | 4.0 | 284 | 0.5263 | 0.6592 | 0.7697 | 0.7102 | 0.8714 |
Framework versions
- Transformers 4.26.1
- Pytorch 1.13.1+cu116
- Datasets 2.10.1
- Tokenizers 0.13.2