binary_persian_sentiment_analysis

This model is a fine-tuned version of sentence-transformers/LaBSE on the None dataset. It achieves the following results on the evaluation set:

• Loss: 0.5060
• Accuracy: 0.8805
• F1 Score: 0.8805

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: 2e-05
• train_batch_size: 2
• eval_batch_size: 2
• 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 Score
0.5045	1.0	8359	0.5295	0.8816	0.8814
0.4211	2.0	16718	0.6029	0.8837	0.8837
0.3501	3.0	25077	0.5060	0.8805	0.8805
0.2541	4.0	33436	0.7740	0.8762	0.8762
0.2065	5.0	41795	0.8071	0.8746	0.8745
0.1915	6.0	50154	0.8341	0.8805	0.8805
0.137	7.0	58513	0.9235	0.8644	0.8644
0.0605	8.0	66872	0.9695	0.8584	0.8584
0.0405	9.0	75231	1.0090	0.8751	0.8751
0.0712	10.0	83590	1.0134	0.8767	0.8767
0.0295	11.0	91949	1.0266	0.8708	0.8709
0.0704	12.0	100308	0.9940	0.8767	0.8767
0.0233	13.0	108667	1.0747	0.8762	0.8762
0.0153	14.0	117026	1.0747	0.8741	0.8741
0.0245	15.0	125385	1.0027	0.8837	0.8837
0.0618	16.0	133744	0.9939	0.8778	0.8778
0.0087	17.0	142103	1.0448	0.8854	0.8853
0.0174	18.0	150462	1.0339	0.8837	0.8838
0.0185	19.0	158821	1.1171	0.8778	0.8778
0.0075	20.0	167180	1.1022	0.8827	0.8827

Framework versions

• Transformers 4.35.2
• Pytorch 2.1.0+cu121
• Datasets 2.16.1
• Tokenizers 0.15.0