ml-roberta-large-finetuned-gesture-prediction-21-classes

This model is a fine-tuned version of xlm-roberta-large on the None dataset. It achieves the following results on the validation set:

Loss: 0.7506
Accuracy: 0.7927
Precision: 0.7829
Recall: 0.7927
F1: 0.7837

It achieves the following results on the test set:

Loss: 0.8029
Accuracy: 0.7720
Precision: 0.7764
Recall: 0.7720
F1: 0.7636

Model description

More information needed

Intended uses & limitations

More information needed

Training and evaluation data

This model has been trained on 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
2.4441	1.0	104	1.5033	0.5798	0.5071	0.5798	0.5015
1.2049	2.0	208	0.8885	0.7532	0.7434	0.7532	0.7331
0.7329	3.0	312	0.7506	0.7927	0.7829	0.7927	0.7837
0.4949	4.0	416	0.7801	0.7936	0.7946	0.7936	0.7866
0.3221	5.0	520	0.8761	0.7957	0.7889	0.7957	0.7865
0.2112	6.0	624	0.9118	0.8062	0.8085	0.8062	0.8004
0.1458	7.0	728	0.9391	0.8071	0.8057	0.8071	0.8019
0.0988	8.0	832	0.9592	0.8105	0.8073	0.8105	0.8065
0.0685	9.0	936	1.0358	0.8057	0.8043	0.8057	0.8016
0.052	10.0	1040	1.0511	0.8089	0.8080	0.8089	0.8037

Framework versions

Transformers 4.26.1
Pytorch 1.13.1+cu116
Datasets 2.10.1
Tokenizers 0.13.2