metadata
license: mit
tags:
- generated_from_trainer
metrics:
- precision
- recall
- f1
- accuracy
model-index:
- name: roberta-finetuned-gesture-prediction-21-classes
results: []
roberta-finetuned-gesture-prediction-21-classes
This model is a fine-tuned version of roberta-base on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.7768
- Precision: 0.5980
- Recall: 0.7114
- F1: 0.6498
- Accuracy: 0.8114
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: 9.453261348481077e-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 |
|---|---|---|---|---|---|---|---|
| 1.7887 | 1.0 | 104 | 1.0084 | 0.4610 | 0.5990 | 0.5210 | 0.7479 |
| 0.8935 | 2.0 | 208 | 0.8393 | 0.5249 | 0.6618 | 0.5855 | 0.7872 |
| 0.5383 | 3.0 | 312 | 0.7661 | 0.5499 | 0.6860 | 0.6104 | 0.7919 |
| 0.3124 | 4.0 | 416 | 0.7768 | 0.5980 | 0.7114 | 0.6498 | 0.8114 |
Framework versions
- Transformers 4.26.1
- Pytorch 1.13.1+cu116
- Datasets 2.10.1
- Tokenizers 0.13.2