fahad1770/bengali_news_article_summarization_BanglaT5

bn_news_article_summarization

This model is a fine-tuned version of csebuetnlp/banglat5 on an unknown dataset. It achieves the following results on the evaluation set:

• Loss: 0.1868

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: 0.001
• train_batch_size: 20
• eval_batch_size: 16
• seed: 42
• gradient_accumulation_steps: 8
• total_train_batch_size: 160
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: cosine_with_restarts
• lr_scheduler_warmup_steps: 100
• num_epochs: 15

Training results

Training Loss	Epoch	Step	Validation Loss
No log	0.99	83	0.5499
No log	2.0	167	0.6308
16.0025	2.99	250	0.4921
16.0025	3.99	334	0.4755
0.5191	5.0	418	0.4795
0.5191	5.99	501	0.4719
0.5191	7.0	585	0.4575
0.4756	8.0	669	0.4345
0.4756	8.99	752	0.3438
0.4157	10.0	836	0.2664
0.4157	10.99	919	0.2263
0.2776	11.99	1003	0.2013
0.2776	13.0	1087	0.1899
0.2776	13.99	1170	0.1872
0.2269	14.89	1245	0.1868

Framework versions

• Transformers 4.39.3
• Pytorch 2.1.2
• Datasets 2.18.0
• Tokenizers 0.15.2