metadata
license: mit
tags:
- generated_from_trainer
metrics:
- precision
- recall
- f1
- accuracy
model-index:
- name: roberta-finetuned-gesture-prediction-5-classes
results: []
roberta-finetuned-gesture-prediction-5-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: 0.4016
- Precision: 0.6731
- Recall: 0.7778
- F1: 0.7216
- Accuracy: 0.8912
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: 8.933445816612466e-05
- train_batch_size: 32
- eval_batch_size: 32
- 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 |
|---|---|---|---|---|---|---|---|
| 1.2011 | 1.0 | 36 | 0.7200 | 0.4537 | 0.5636 | 0.5027 | 0.7552 |
| 0.473 | 2.0 | 72 | 0.5067 | 0.6552 | 0.7333 | 0.6921 | 0.8627 |
| 0.2919 | 3.0 | 108 | 0.4244 | 0.6267 | 0.7394 | 0.6784 | 0.8721 |
| 0.1748 | 4.0 | 144 | 0.4016 | 0.6731 | 0.7778 | 0.7216 | 0.8912 |
Framework versions
- Transformers 4.26.1
- Pytorch 1.13.1+cu116
- Datasets 2.10.1
- Tokenizers 0.13.2