README.md

metadata

license: mit
tags:
  - generated_from_trainer
datasets: qfrodicio/gesture-prediction-21-classes
metrics:
  - accuracy
  - precision
  - recall
  - f1
base_model: roberta-base
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: 0.7782
• Accuracy: 0.8185
• Precision: 0.8116
• Recall: 0.8185
• F1: 0.8072

It achieves the following results on the evaluation set:

• Loss: 0.8142
• Accuracy: 0.8154
• Precision: 0.8189
• Recall: 0.8154
• F1: 0.8125

Model description

More information needed

Intended uses & limitations

More information needed

Training and evaluation data

The model has been trained with the qfrodicio/gesture-prediction-21-classes dataset

Training procedure

Training hyperparameters

The following hyperparameters were used during training:

• learning_rate: 2e-05
• weight_decay: 0.01
• 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
2.2147	1.0	104	1.3857	0.7406	0.6887	0.7406	0.7013
1.2291	2.0	208	0.9750	0.7907	0.7597	0.7907	0.7618
0.836	3.0	312	0.8609	0.8028	0.7813	0.8028	0.7829
0.6129	4.0	416	0.8059	0.8078	0.8030	0.8078	0.7973
0.4747	5.0	520	0.7782	0.8185	0.8116	0.8185	0.8072
0.3639	6.0	624	0.7825	0.8175	0.8170	0.8175	0.8108
0.295	7.0	728	0.7913	0.8365	0.8283	0.8365	0.8280
0.236	8.0	832	0.7619	0.8273	0.8230	0.8273	0.8229
0.1989	9.0	936	0.7880	0.8309	0.8258	0.8309	0.8261
0.1879	10.0	1040	0.7915	0.8314	0.8247	0.8314	0.8264

Framework versions

• Transformers 4.26.1
• Pytorch 1.13.1+cu116
• Datasets 2.10.1
• Tokenizers 0.13.2