metadata

license: apache-2.0
tags:
  - generated_from_trainer
datasets: qfrodicio/gesture-prediction-5-classes
metrics:
  - accuracy
  - precision
  - recall
  - f1
model-index:
  - name: bert-finetuned-gesture-prediction-5-classes
    results: []

bert-finetuned-gesture-prediction-5-classes

This model is a fine-tuned version of bert-base-cased on the None dataset. It achieves the following results on the validation set:

Loss: 0.4958
Accuracy: 0.8636
Precision: 0.8662
Recall: 0.8636
F1: 0.8625

It achieves the following results on the test set:

Loss: 0.4599
Accuracy: 0.8561
Precision: 0.8578
Recall: 0.8561
F1: 0.8533

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-5-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
1.3816	1.0	71	0.6929	0.7820	0.7518	0.7820	0.7510
0.546	2.0	142	0.5128	0.8591	0.8614	0.8591	0.8579
0.3026	3.0	213	0.4958	0.8636	0.8662	0.8636	0.8625
0.1689	4.0	284	0.5090	0.8688	0.8694	0.8688	0.8678
0.1085	5.0	355	0.5306	0.8794	0.8813	0.8794	0.8786
0.0684	6.0	426	0.5516	0.8776	0.8774	0.8776	0.8765
0.0485	7.0	497	0.6051	0.8779	0.8794	0.8779	0.8770
0.0341	8.0	568	0.6224	0.8781	0.8780	0.8781	0.8776
0.0251	9.0	639	0.6429	0.8812	0.8817	0.8812	0.8805
0.021	10.0	710	0.6456	0.8807	0.8811	0.8807	0.8798

Framework versions

Transformers 4.26.1
Pytorch 1.13.1+cu116
Datasets 2.10.1
Tokenizers 0.13.2