arabart_wiki

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

• Loss: 0.0001
• Rouge1: 0.1109
• Rouge2: 0.009
• Rougel: 0.1109
• Rougelsum: 0.1105
• Gen Len: 19.9251

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: 4
• eval_batch_size: 4
• seed: 42
• gradient_accumulation_steps: 8
• total_train_batch_size: 32
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• lr_scheduler_warmup_steps: 250
• num_epochs: 10
• mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	Rouge1	Rouge2	Rougel	Rougelsum	Gen Len
0.0048	7.35	500	0.0001	0.1109	0.009	0.1109	0.1105	19.9251

Framework versions

• Transformers 4.40.0.dev0
• Pytorch 2.2.1+cu121
• Datasets 2.18.0
• Tokenizers 0.15.2