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: 1.0350
- Precision: 0.8324
- Recall: 0.8324
- F1: 0.8324
- Accuracy: 0.8230
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 | 1.1258 | 0.7513 | 0.7513 | 0.7513 | 0.7258 |
| 0.8843 | 2.0 | 208 | 0.9338 | 0.7765 | 0.7765 | 0.7765 | 0.7578 |
| 0.5881 | 3.0 | 312 | 0.8124 | 0.8173 | 0.8173 | 0.8173 | 0.8011 |
| 0.4017 | 4.0 | 416 | 0.8831 | 0.7973 | 0.7973 | 0.7973 | 0.7848 |
| 0.2652 | 5.0 | 520 | 0.9254 | 0.8300 | 0.8300 | 0.8300 | 0.8172 |
| 0.1776 | 6.0 | 624 | 0.9221 | 0.8310 | 0.8310 | 0.8310 | 0.8180 |
| 0.1234 | 7.0 | 728 | 1.0063 | 0.8211 | 0.8211 | 0.8211 | 0.8112 |
| 0.0829 | 8.0 | 832 | 1.0132 | 0.8298 | 0.8298 | 0.8298 | 0.8201 |
| 0.0552 | 9.0 | 936 | 1.0408 | 0.8290 | 0.8290 | 0.8290 | 0.8189 |
| 0.0409 | 10.0 | 1040 | 1.0350 | 0.8324 | 0.8324 | 0.8324 | 0.8230 |
Framework versions
- Transformers 4.40.1
- Pytorch 2.2.1+cu121
- Datasets 2.19.1
- Tokenizers 0.19.1