Modelpublic

LovenOO/BERT_with_preprocessing_grid_search

sourceHugging Faceapache-2.0updated 3y agoView on Hugging Face

0likes12downloads

Model Card

BERTwithpreprocessinggridsearch

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

—Loss: 0.8836
—Precision: 0.8262
—Recall: 0.8258
—F1: 0.8249
—Accuracy: 0.8724

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: 3e-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
1.047	1.0	510	0.6171	0.7493	0.8057	0.7716	0.8336
0.4348	2.0	1020	0.4954	0.8056	0.8646	0.8296	0.8714
0.2818	3.0	1530	0.6252	0.8181	0.8323	0.8212	0.8660
0.1793	4.0	2040	0.7381	0.8216	0.8258	0.8227	0.8733
0.1356	5.0	2550	0.8601	0.8161	0.8219	0.8165	0.8660
0.1023	6.0	3060	0.8526	0.8363	0.8299	0.8307	0.8758
0.0944	7.0	3570	0.8459	0.8234	0.8298	0.8251	0.8729
0.0631	8.0	4080	0.8519	0.8212	0.8325	0.8252	0.8714
0.0602	9.0	4590	0.8756	0.8200	0.8267	0.8226	0.8719
0.0532	10.0	5100	0.8836	0.8262	0.8258	0.8249	0.8724

Framework versions

—Transformers 4.31.0
—Pytorch 2.0.1+cu118
—Datasets 2.14.4
—Tokenizers 0.13.3