SajjadAyoubi_xlm-roberta-large-fa-qa_finetune_on_hoshfa_18

This model is a fine-tuned version of SajjadAyoubi/xlm-roberta-large-fa-qa on an unknown dataset. It achieves the following results on the evaluation set:

• Loss: 0.7132

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: 10
• eval_batch_size: 10
• seed: 42
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• num_epochs: 18

Training results

Training Loss	Epoch	Step	Validation Loss
No log	1.0	450	1.6760
2.4326	2.0	900	1.2467
1.7149	3.0	1350	1.0080
1.4159	4.0	1800	0.9462
1.1935	5.0	2250	0.8571
1.0304	6.0	2700	0.8423
0.9659	7.0	3150	0.7865
0.8431	8.0	3600	0.7647
0.8279	9.0	4050	0.7421
0.7808	10.0	4500	0.7911
0.7808	11.0	4950	0.7421
0.7409	12.0	5400	0.7146
0.7155	13.0	5850	0.7184
0.6672	14.0	6300	0.7149
0.6637	15.0	6750	0.7134
0.6457	16.0	7200	0.7128
0.6167	17.0	7650	0.7127
0.6256	18.0	8100	0.7132

Framework versions

• Transformers 4.26.1
• Pytorch 1.13.1+cu116
• Datasets 2.9.0
• Tokenizers 0.13.2