Modelpublic

salohnana2018/ABSA-SentencePair-DAPT-HARDARABS-bert-base-Camel-MSA-ru2

sourceHugging Faceapache-2.0updated 3y agoView on Hugging Face

0likes10downloads

Model Card

ABSA-SentencePair-DAPT-HARDARABS-bert-base-Camel-MSA-ru2

This model is a fine-tuned version of salohnana2018/CAMEL-BERT-MSA-domianAdaption-Single-ABSA-HARD on the None dataset. It achieves the following results on the evaluation set:

—Loss: 1.7587
—Accuracy: 0.8941
—F1: 0.8941
—Precision: 0.8941
—Recall: 0.8941

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: 32
—evalbatchsize: 32
—seed: 42
—optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
—lrschedulertype: linear
—num_epochs: 30

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy	F1	Precision	Recall
0.5254	1.0	265	0.4268	0.8483	0.8483	0.8483	0.8483
0.3572	2.0	530	0.3457	0.8563	0.8563	0.8563	0.8563
0.2477	3.0	795	0.5427	0.8795	0.8795	0.8795	0.8795
0.1905	4.0	1060	0.8314	0.8899	0.8899	0.8899	0.8899
0.1353	5.0	1325	1.0504	0.8852	0.8852	0.8852	0.8852
0.12	6.0	1590	0.7891	0.8842	0.8842	0.8842	0.8842
0.0749	7.0	1855	1.3696	0.8894	0.8894	0.8894	0.8894
0.097	8.0	2120	0.9817	0.8904	0.8904	0.8904	0.8904
0.0624	9.0	2385	1.0450	0.8847	0.8847	0.8847	0.8847
0.0582	10.0	2650	1.3148	0.8970	0.8970	0.8970	0.8970
0.0599	11.0	2915	1.4069	0.8946	0.8946	0.8946	0.8946
0.0451	12.0	3180	1.0183	0.8889	0.8889	0.8889	0.8889
0.0309	13.0	3445	1.3034	0.8932	0.8932	0.8932	0.8932
0.0251	14.0	3710	1.5148	0.8946	0.8946	0.8946	0.8946
0.0245	15.0	3975	1.5136	0.8946	0.8946	0.8946	0.8946
0.0153	16.0	4240	1.3876	0.8927	0.8927	0.8927	0.8927
0.0161	17.0	4505	1.6176	0.8885	0.8885	0.8885	0.8885
0.0166	18.0	4770	1.6110	0.8937	0.8937	0.8937	0.8937
0.0137	19.0	5035	1.7113	0.8960	0.8960	0.8960	0.8960
0.0111	20.0	5300	1.7241	0.8946	0.8946	0.8946	0.8946
0.0101	21.0	5565	1.6722	0.8970	0.8970	0.8970	0.8970
0.0142	22.0	5830	1.6423	0.8904	0.8904	0.8904	0.8904
0.0118	23.0	6095	1.6384	0.8904	0.8904	0.8904	0.8904
0.0083	24.0	6360	1.6616	0.8922	0.8922	0.8922	0.8922
0.0124	25.0	6625	1.9046	0.8951	0.8951	0.8951	0.8951
0.0154	26.0	6890	1.6547	0.8974	0.8974	0.8974	0.8974
0.0086	27.0	7155	1.6440	0.8932	0.8932	0.8932	0.8932
0.0077	28.0	7420	1.7566	0.8941	0.8941	0.8941	0.8941
0.0076	29.0	7685	1.7419	0.8937	0.8937	0.8937	0.8937
0.0078	30.0	7950	1.7587	0.8941	0.8941	0.8941	0.8941

Framework versions

—Transformers 4.38.1
—Pytorch 2.1.0+cu121
—Datasets 2.18.0
—Tokenizers 0.15.2