banglat5-finetuned-headlineBT5_1000_batch8

This model is a fine-tuned version of csebuetnlp/banglat5 on the None dataset. It achieves the following results on the evaluation set:

• Loss: 5.6966

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: 8
• eval_batch_size: 8
• seed: 42
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• num_epochs: 5

Training results

Training Loss	Epoch	Step	Validation Loss
10.9087	1.0	80	7.1863
8.5131	2.0	160	6.5662
8.0331	3.0	240	6.0913
6.9394	4.0	320	5.7946
7.3738	5.0	400	5.6966

Framework versions

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