araT5-Base-with-DoRA

This model is a fine-tuned version of UBC-NLP/AraT5v2-base-1024 on an unknown dataset. It achieves the following results on the evaluation set:

• Loss: 2.0824
• Bleu: 13.0059
• Rouge: 0.5123
• Gen Len: 14.0744

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: 0.0002
• train_batch_size: 2
• eval_batch_size: 2
• seed: 42
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• num_epochs: 5
• mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	Bleu	Rouge	Gen Len
4.2609	1.0	7500	2.6129	9.8191	0.4309	14.0316
3.2235	2.0	15000	2.3141	11.3505	0.4801	13.944
2.9623	3.0	22500	2.1885	12.2927	0.4951	14.0504
2.7918	4.0	30000	2.1044	12.7617	0.5053	14.0332
2.7009	5.0	37500	2.0824	13.0059	0.5123	14.0744

Framework versions

• PEFT 0.12.0
• Transformers 4.44.0
• Pytorch 2.4.0
• Datasets 2.21.0
• Tokenizers 0.19.1