Modelpublic

rkrstacic/bpmn-task-extractor

sourceHugging Facemitupdated 4y agoView on Hugging Face

1likes18downloads

Model Card

bpmn-task-extractor

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

—Loss: 0.0970
—Precision: 0.95
—Recall: 0.95
—F1: 0.9500
—Accuracy: 0.9888

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: 5e-05
—trainbatchsize: 16
—evalbatchsize: 16
—seed: 42
—optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
—lrschedulertype: linear
—num_epochs: 10

Training results

Training Loss	Epoch	Step	Validation Loss	Precision	Recall	F1	Accuracy
No log	1.0	1	1.0813	0.3077	0.2	0.2424	0.6404
No log	2.0	2	0.7296	0.4783	0.55	0.5116	0.7191
No log	3.0	3	0.5097	0.6111	0.55	0.5789	0.8090
No log	4.0	4	0.3683	0.7059	0.6	0.6486	0.8652
No log	5.0	5	0.2926	0.75	0.6	0.6667	0.8539
No log	6.0	6	0.2268	0.7647	0.65	0.7027	0.8764
No log	7.0	7	0.1699	0.7778	0.7	0.7368	0.9101
No log	8.0	8	0.1273	0.8	0.8	0.8000	0.9438
No log	9.0	9	0.1061	0.95	0.95	0.9500	0.9888
No log	10.0	10	0.0970	0.95	0.95	0.9500	0.9888

Framework versions

—Transformers 4.21.3
—Pytorch 1.12.1+cu113
—Datasets 2.4.0
—Tokenizers 0.12.1