banglat5-headline_WithIp-b8-1e-4 – AI Model by mdosama39 | AlphaNeural AI

You can deploy this model and start earning money today!

mdosama39/
banglat5-headline_WithIp-b8-1e-4

like

0

text2text-generation

generated_from_trainer

csebuetnlp/banglat5

text-generation-inference

endpoints_compatible

Views

No views yet

banglat5-headline_WithIp-b8-1e-4

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

Loss: 2.9335
Rouge1: 0.0
Rouge2: 0.0
Rougel: 0.0
Rougelsum: 0.0
Gen Len: 8.861

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: 0.0001
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	Rouge1	Rouge2	Rougel	Rougelsum	Gen Len
4.5814	1.0	202	3.4611	0.0	0.0	0.0	0.0	11.9231
3.4664	2.0	404	3.0551	0.0	0.0	0.0	0.0	8.335
3.5643	3.0	606	2.9732	0.0	0.0	0.0	0.0	8.871
2.9927	4.0	808	2.9406	0.0	0.0	0.0	0.0	8.6774
3.0685	5.0	1010	2.9335	0.0	0.0	0.0	0.0	8.861

Framework versions

Transformers 4.40.2
Pytorch 2.2.1+cu121
Datasets 2.19.1
Tokenizers 0.19.1