uncased-clf-persiannews_v1

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

• Loss: 1.4385
• Accuracy: 0.6459
• F1: 0.6461
• Precision: 0.6470

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
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• num_epochs: 10

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy	F1	Precision
No log	1.0	221	1.0855	0.6277	0.6263	0.6472
No log	2.0	442	1.0924	0.6549	0.6545	0.6598
0.4554	3.0	663	1.1278	0.6583	0.6570	0.6609
0.4554	4.0	884	1.2085	0.6481	0.6488	0.6559
0.2653	5.0	1105	1.2614	0.6481	0.6487	0.6498
0.2653	6.0	1326	1.3392	0.6402	0.6371	0.6433
0.1817	7.0	1547	1.3692	0.6549	0.6543	0.6572
0.1817	8.0	1768	1.4216	0.6425	0.6419	0.6424
0.1817	9.0	1989	1.4325	0.6549	0.6551	0.6555
0.1334	10.0	2210	1.4385	0.6459	0.6461	0.6470

Framework versions

• Transformers 4.38.2
• Pytorch 2.1.0+cu121
• Datasets 2.18.0
• Tokenizers 0.15.2