Bert-Sentiment-Fa

This model is a fine-tuned version of HooshvareLab/bert-fa-base-uncased on the None dataset. It achieves the following results on the evaluation set:

• Loss: 1.0154
• Accuracy: 0.8333
• F1: 0.8456

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-06
• train_batch_size: 32
• eval_batch_size: 64
• seed: 42
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• num_epochs: 15

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy	F1
No log	1.0	68	0.5588	0.8333	0.8419
No log	2.0	136	0.5678	0.8417	0.8557
No log	3.0	204	0.6083	0.8208	0.8311
No log	4.0	272	0.6749	0.8167	0.8285
No log	5.0	340	0.7690	0.8292	0.8424
No log	6.0	408	0.8706	0.8208	0.8328
No log	7.0	476	0.8554	0.8292	0.8424
0.0725	8.0	544	0.8950	0.825	0.8390
0.0725	9.0	612	0.9200	0.825	0.8390
0.0725	10.0	680	0.9511	0.8292	0.8455
0.0725	11.0	748	0.9698	0.8375	0.8490
0.0725	12.0	816	0.9829	0.8333	0.8456
0.0725	13.0	884	1.0022	0.8333	0.8456
0.0725	14.0	952	1.0130	0.8333	0.8456
0.0167	15.0	1020	1.0154	0.8333	0.8456

Framework versions

• Transformers 4.44.2
• Pytorch 2.4.0+cu121
• Datasets 2.21.0
• Tokenizers 0.19.1