metadata
license: mit
tags:
- generated_from_trainer
metrics:
- accuracy
- precision
- recall
- f1
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: 0.9312
- Accuracy: 0.8163
- Precision: 0.8090
- Recall: 0.8163
- F1: 0.8108
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 |
|---|---|---|---|---|---|---|---|
| 2.2472 | 1.0 | 104 | 1.4263 | 0.7364 | 0.6666 | 0.7364 | 0.6921 |
| 1.2677 | 2.0 | 208 | 1.0547 | 0.7888 | 0.7581 | 0.7888 | 0.7638 |
| 0.8676 | 3.0 | 312 | 0.9315 | 0.7963 | 0.7775 | 0.7963 | 0.7791 |
| 0.6407 | 4.0 | 416 | 0.9022 | 0.8102 | 0.8012 | 0.8102 | 0.7995 |
| 0.4926 | 5.0 | 520 | 0.8994 | 0.8120 | 0.8080 | 0.8120 | 0.8016 |
| 0.3754 | 6.0 | 624 | 0.9018 | 0.8069 | 0.7999 | 0.8069 | 0.8002 |
| 0.3037 | 7.0 | 728 | 0.9048 | 0.8131 | 0.8055 | 0.8131 | 0.8060 |
| 0.2499 | 8.0 | 832 | 0.9030 | 0.8161 | 0.8119 | 0.8161 | 0.8117 |
| 0.2155 | 9.0 | 936 | 0.9279 | 0.8160 | 0.8088 | 0.8160 | 0.8106 |
| 0.2062 | 10.0 | 1040 | 0.9312 | 0.8163 | 0.8090 | 0.8163 | 0.8108 |
Framework versions
- Transformers 4.26.1
- Pytorch 1.13.1+cu116
- Datasets 2.10.1
- Tokenizers 0.13.2