metadata
license: mit
base_model: roberta-base
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 an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 1.0301
- Precision: 0.8177
- Recall: 0.8177
- F1: 0.8177
- Accuracy: 0.8089
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: 4.9033776462709114e-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 | Precision | Recall | F1 | Accuracy |
|---|---|---|---|---|---|---|---|
| 1.8808 | 1.0 | 104 | 1.0755 | 0.7554 | 0.7554 | 0.7554 | 0.7327 |
| 0.8843 | 2.0 | 208 | 0.8376 | 0.7637 | 0.7637 | 0.7637 | 0.7465 |
| 0.5881 | 3.0 | 312 | 0.7300 | 0.8152 | 0.8152 | 0.8152 | 0.8014 |
| 0.4017 | 4.0 | 416 | 0.8043 | 0.7985 | 0.7985 | 0.7985 | 0.7881 |
| 0.2652 | 5.0 | 520 | 0.8595 | 0.8118 | 0.8118 | 0.8118 | 0.8018 |
| 0.1776 | 6.0 | 624 | 0.9623 | 0.8133 | 0.8133 | 0.8133 | 0.8041 |
| 0.1234 | 7.0 | 728 | 0.9631 | 0.8068 | 0.8068 | 0.8068 | 0.7989 |
| 0.0829 | 8.0 | 832 | 1.0190 | 0.8256 | 0.8256 | 0.8256 | 0.8168 |
| 0.0552 | 9.0 | 936 | 1.0117 | 0.8222 | 0.8222 | 0.8222 | 0.8139 |
| 0.0409 | 10.0 | 1040 | 1.0301 | 0.8177 | 0.8177 | 0.8177 | 0.8089 |
Framework versions
- Transformers 4.40.1
- Pytorch 2.2.1+cu121
- Datasets 2.19.0
- Tokenizers 0.19.1