Modelpublic

trung061204/absa-restaurants-distilbert

sourceHugging Faceapache-2.0updated 1y agoView on Hugging Face

0likes3downloads

Model Card

absa-restaurants-distilbert

This model is a fine-tuned version of distilbert/distilbert-base-uncased on an unknown dataset. It achieves the following results on the evaluation set:

—Loss: 0.5635
—Accuracy: 0.8159

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: 2e-05
—trainbatchsize: 128
—evalbatchsize: 128
—seed: 42
—optimizer: Use OptimizerNames.ADAMWTORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizerargs=No additional optimizer arguments
—lrschedulertype: linear
—num_epochs: 15

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy
0.9248	1.0	29	0.7330	0.6533
0.6779	2.0	58	0.5587	0.7748
0.5661	3.0	87	0.5331	0.7891
0.4916	4.0	116	0.5064	0.7989
0.4224	5.0	145	0.4861	0.8088
0.3789	6.0	174	0.4965	0.8097
0.3159	7.0	203	0.5085	0.8061
0.29	8.0	232	0.5049	0.8123
0.2548	9.0	261	0.5158	0.8213
0.2228	10.0	290	0.5447	0.8222
0.2145	11.0	319	0.5223	0.8248
0.1785	12.0	348	0.5511	0.8168
0.185	13.0	377	0.5806	0.8105
0.1643	14.0	406	0.5619	0.8114
0.155	15.0	435	0.5635	0.8159

Framework versions

—Transformers 4.53.2
—Pytorch 2.6.0+cu124
—Datasets 3.2.0
—Tokenizers 0.21.2