araT5-Base-with-QDoRA

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: 2.0895
• Bleu: 13.0266
• Rouge: 0.51
• Gen Len: 14.0476

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
4.4059	1.0	7500	2.6665	9.3718	0.4205	14.0244
3.2667	2.0	15000	2.3469	11.0187	0.4717	13.966
2.9674	3.0	22500	2.2030	12.2302	0.4942	13.9836
2.8026	4.0	30000	2.1166	12.8104	0.5085	14.022
2.7107	5.0	37500	2.0895	13.0266	0.51	14.0476

Framework versions

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