README.md

metadata

license: apache-2.0
tags:
  - generated_from_trainer
metrics:
  - accuracy
  - f1
  - precision
  - recall
base_model: salohnana2018/CAMEL-BERT-MSA-domianAdaption-Single-ABSA-HARD
model-index:
  - name: ABSA-SentencePair-DAPT-HARDARABS-bert-base-Camel-MSA-ru1
    results: []

ABSA-SentencePair-DAPT-HARDARABS-bert-base-Camel-MSA-ru1

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: 1.6590
• Accuracy: 0.8965
• F1: 0.8965
• Precision: 0.8965
• Recall: 0.8965

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: 25
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• num_epochs: 30

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy	F1	Precision	Recall
0.5505	1.0	265	0.4846	0.7703	0.7703	0.7703	0.7703
0.354	2.0	530	0.3727	0.8852	0.8852	0.8852	0.8852
0.2455	3.0	795	0.4606	0.8582	0.8582	0.8582	0.8582
0.179	4.0	1060	0.5599	0.8771	0.8771	0.8771	0.8771
0.1452	5.0	1325	0.8984	0.8795	0.8795	0.8795	0.8795
0.1076	6.0	1590	0.8935	0.8960	0.8960	0.8960	0.8960
0.093	7.0	1855	0.6251	0.8757	0.8757	0.8757	0.8757
0.0779	8.0	2120	0.9415	0.8899	0.8899	0.8899	0.8899
0.0653	9.0	2385	0.9360	0.8965	0.8965	0.8965	0.8965
0.0514	10.0	2650	1.0234	0.8889	0.8889	0.8889	0.8889
0.0367	11.0	2915	1.3198	0.8951	0.8951	0.8951	0.8951
0.0414	12.0	3180	1.1830	0.8833	0.8833	0.8833	0.8833
0.0396	13.0	3445	1.1262	0.8885	0.8885	0.8885	0.8885
0.0338	14.0	3710	1.3073	0.8970	0.8970	0.8970	0.8970
0.0204	15.0	3975	1.2894	0.8946	0.8946	0.8946	0.8946
0.0232	16.0	4240	1.3265	0.8960	0.8960	0.8960	0.8960
0.0203	17.0	4505	1.2467	0.8974	0.8974	0.8974	0.8974
0.012	18.0	4770	1.5870	0.8960	0.8960	0.8960	0.8960
0.0155	19.0	5035	1.5296	0.8974	0.8974	0.8974	0.8974
0.0112	20.0	5300	1.6052	0.9026	0.9026	0.9026	0.9026
0.0109	21.0	5565	1.5280	0.8974	0.8974	0.8974	0.8974
0.012	22.0	5830	1.5513	0.8941	0.8941	0.8941	0.8941
0.0103	23.0	6095	1.6142	0.8984	0.8984	0.8984	0.8984
0.0116	24.0	6360	1.5363	0.8965	0.8965	0.8965	0.8965
0.0104	25.0	6625	1.6729	0.8984	0.8984	0.8984	0.8984
0.0079	26.0	6890	1.7198	0.8993	0.8993	0.8993	0.8993
0.0093	27.0	7155	1.5210	0.8941	0.8941	0.8941	0.8941
0.0077	28.0	7420	1.6023	0.8960	0.8960	0.8960	0.8960
0.0077	29.0	7685	1.6430	0.8960	0.8960	0.8960	0.8960
0.0073	30.0	7950	1.6590	0.8965	0.8965	0.8965	0.8965

Framework versions

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