Modelpublic

SharonTudi/DIALOGUE_two

sourceHugging Faceapache-2.0updated 3y agoView on Hugging Face

0likes4downloads

Model Card

DIALOGUE_two

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

—Loss: 0.3804
—Precision: 0.9762
—Recall: 0.9737
—F1: 0.9736
—Accuracy: 0.9737

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: 1e-05
—trainbatchsize: 8
—evalbatchsize: 8
—seed: 42
—optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
—lrschedulertype: linear
—num_epochs: 3

Training results

Training Loss	Epoch	Step	Validation Loss	Precision	Recall	F1	Accuracy
1.3711	0.31	15	1.3213	0.5848	0.5132	0.4588	0.5132
1.2829	0.62	30	1.1830	0.7679	0.7237	0.7027	0.7237
1.1039	0.94	45	0.9695	0.8939	0.8158	0.8094	0.8158
0.9122	1.25	60	0.7720	0.9499	0.9474	0.9473	0.9474
0.7581	1.56	75	0.6220	0.9762	0.9737	0.9736	0.9737
0.6483	1.88	90	0.5096	0.9762	0.9737	0.9736	0.9737
0.5277	2.19	105	0.4330	0.9762	0.9737	0.9736	0.9737
0.4708	2.5	120	0.4003	0.9762	0.9737	0.9736	0.9737
0.4622	2.81	135	0.3804	0.9762	0.9737	0.9736	0.9737

Framework versions

—Transformers 4.37.1
—Pytorch 2.1.0+cu121
—Datasets 2.16.1
—Tokenizers 0.15.1