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
  • 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: 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
Downloads last month
17
Safetensors
Model size
109M params
Tensor type
F32
·
Inference Examples
This model does not have enough activity to be deployed to Inference API (serverless) yet. Increase its social visibility and check back later, or deploy to Inference Endpoints (dedicated) instead.

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