uncased-clf-persiannews_v2-finetuned-bmd-20241027_125058-LOSO-section-out1

This model is a fine-tuned version of soltaniali/uncased-clf-persiannews_v2 on an unknown dataset. It achieves the following results on the evaluation set:

• Loss: 1.0781
• Accuracy: 0.5172
• F1: 0.5143

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: 16
• eval_batch_size: 16
• seed: 42
• gradient_accumulation_steps: 4
• total_train_batch_size: 64
• optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
• lr_scheduler_type: linear
• lr_scheduler_warmup_ratio: 0.1
• num_epochs: 20

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy	F1
No log	0.5714	1	1.1232	0.3103	0.2074
No log	1.7143	3	1.1024	0.3103	0.2431
No log	2.8571	5	1.0925	0.3448	0.2995
No log	4.0	7	1.0876	0.4138	0.4185
No log	4.5714	8	1.0853	0.4828	0.4860
4.3532	5.7143	10	1.0819	0.5517	0.5479
4.3532	6.8571	12	1.0806	0.5172	0.5143
4.3532	8.0	14	1.0793	0.5172	0.5143
4.3532	8.5714	15	1.0787	0.5172	0.5143
4.3532	9.7143	17	1.0786	0.5172	0.5143
4.3532	10.8571	19	1.0782	0.5172	0.5143
4.1191	11.4286	20	1.0781	0.5172	0.5143

Framework versions

• Transformers 4.46.0
• Pytorch 2.5.0+cu121
• Datasets 3.0.2
• Tokenizers 0.20.1