metadata
license: mit
tags:
- generated_from_trainer
metrics:
- accuracy
- precision
- recall
- f1
model-index:
- name: roberta-finetuned-gesture-prediction-9-classes
results: []
roberta-finetuned-gesture-prediction-9-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: 0.7459
- Accuracy: 0.8536
- Precision: 0.8561
- Recall: 0.8536
- F1: 0.8520
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 |
|---|---|---|---|---|---|---|---|
| 1.707 | 1.0 | 87 | 1.1502 | 0.6656 | 0.6124 | 0.6656 | 0.6133 |
| 0.8587 | 2.0 | 174 | 0.7766 | 0.7866 | 0.7738 | 0.7866 | 0.7675 |
| 0.5593 | 3.0 | 261 | 0.7240 | 0.8114 | 0.8063 | 0.8114 | 0.8017 |
| 0.4122 | 4.0 | 348 | 0.6559 | 0.8248 | 0.8266 | 0.8248 | 0.8217 |
| 0.3081 | 5.0 | 435 | 0.7089 | 0.8373 | 0.8431 | 0.8373 | 0.8326 |
| 0.2322 | 6.0 | 522 | 0.7230 | 0.8234 | 0.8312 | 0.8234 | 0.8237 |
| 0.1848 | 7.0 | 609 | 0.7016 | 0.8457 | 0.8491 | 0.8457 | 0.8434 |
| 0.141 | 8.0 | 696 | 0.7443 | 0.8489 | 0.8540 | 0.8489 | 0.8451 |
| 0.1181 | 9.0 | 783 | 0.7478 | 0.8534 | 0.8567 | 0.8534 | 0.8509 |
| 0.1008 | 10.0 | 870 | 0.7459 | 0.8536 | 0.8561 | 0.8536 | 0.8520 |
Framework versions
- Transformers 4.26.1
- Pytorch 1.13.1+cu116
- Datasets 2.10.1
- Tokenizers 0.13.2