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

Loss: 0.6414
Accuracy: 0.7252
F1: 0.6988
Precision: 0.7134
Recall: 0.6896

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: 1e-05
train_batch_size: 16
eval_batch_size: 16
seed: 42
optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
lr_scheduler_type: linear
num_epochs: 10

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy	F1	Precision	Recall
0.8163	1.0	705	0.6608	0.7196	0.6929	0.7297	0.6770
0.6332	2.0	1410	0.6414	0.7252	0.6988	0.7134	0.6896
0.4546	3.0	2115	0.6490	0.7212	0.6964	0.7020	0.6921
0.3769	4.0	2820	0.7321	0.7188	0.6934	0.7117	0.6828

Framework versions

Transformers 4.54.0
Pytorch 2.6.0+cu124
Datasets 4.0.0
Tokenizers 0.21.2

Negark/distilbert-fa-merged

distilbert-fa-merged

Model description

Intended uses & limitations

Training and evaluation data

Training procedure

Training hyperparameters

Training results

Framework versions

Negark/
distilbert-fa-merged