metadata

license: mit
tags:
  - generated_from_trainer
datasets: qfrodicio/gesture-prediction-9-classes
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 validation set:

Loss: 0.6668
Accuracy: 0.8289
Precision: 0.8288
Recall: 0.8289
F1: 0.8258

It achieves the following results on the test set:

Loss: 0.6158
Accuracy: 0.83
Precision: 0.8296
Recall: 0.83
F1: 0.8274

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-9-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
1.7138	1.0	87	1.0975	0.6915	0.6290	0.6915	0.6303
0.846	2.0	174	0.7497	0.7948	0.7790	0.7948	0.7772
0.5545	3.0	261	0.7078	0.8020	0.8000	0.8020	0.7927
0.3955	4.0	348	0.6668	0.8289	0.8288	0.8289	0.8258
0.279	5.0	435	0.6922	0.8291	0.8340	0.8291	0.8277
0.2203	6.0	522	0.6955	0.8373	0.8390	0.8373	0.8336
0.1595	7.0	609	0.7149	0.8395	0.8405	0.8395	0.8365
0.1349	8.0	696	0.7065	0.8436	0.8447	0.8436	0.8399
0.1047	9.0	783	0.7408	0.8481	0.8502	0.8481	0.8445
0.0906	10.0	870	0.7439	0.8495	0.8501	0.8495	0.8465

Framework versions

Transformers 4.26.1
Pytorch 1.13.1+cu116
Datasets 2.10.1
Tokenizers 0.13.2