ABSA-SentencePair-DAPT-HARDAR-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: 0.1140
• Accuracy: 0.8956
• F1: 0.8956
• Precision: 0.8956
• Recall: 0.8956

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
• train_batch_size: 32
• eval_batch_size: 32
• seed: 42
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• num_epochs: 20

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy	F1	Precision	Recall
0.0556	1.0	265	0.0421	0.8842	0.8842	0.8842	0.8842
0.0372	2.0	530	0.0368	0.8828	0.8828	0.8828	0.8828
0.0231	3.0	795	0.0426	0.8828	0.8828	0.8828	0.8828
0.0145	4.0	1060	0.0601	0.8809	0.8809	0.8809	0.8809
0.0101	5.0	1325	0.0573	0.8842	0.8842	0.8842	0.8842
0.0076	6.0	1590	0.0621	0.8856	0.8856	0.8856	0.8856
0.0051	7.0	1855	0.0621	0.8866	0.8866	0.8866	0.8866
0.0044	8.0	2120	0.0709	0.8899	0.8899	0.8899	0.8899
0.0035	9.0	2385	0.0827	0.8899	0.8899	0.8899	0.8899
0.0028	10.0	2650	0.0895	0.8946	0.8946	0.8946	0.8946
0.0024	11.0	2915	0.0859	0.8908	0.8908	0.8908	0.8908
0.0021	12.0	3180	0.0897	0.8847	0.8847	0.8847	0.8847
0.0017	13.0	3445	0.0994	0.8989	0.8989	0.8989	0.8989
0.0014	14.0	3710	0.1056	0.8937	0.8937	0.8937	0.8937
0.0014	15.0	3975	0.1044	0.8941	0.8941	0.8941	0.8941
0.0012	16.0	4240	0.1105	0.8951	0.8951	0.8951	0.8951
0.0012	17.0	4505	0.1119	0.8956	0.8956	0.8956	0.8956
0.0011	18.0	4770	0.1088	0.8965	0.8965	0.8965	0.8965
0.001	19.0	5035	0.1132	0.8979	0.8979	0.8979	0.8979
0.001	20.0	5300	0.1140	0.8956	0.8956	0.8956	0.8956

Framework versions

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