idt5-base-ae_adapter

This model is a fine-tuned version of muchad/idt5-base on the None dataset. It achieves the following results on the evaluation set:

• Loss: 1.1132
• Rouge1: 0.3358
• Rouge2: 0.1831
• Rougel: 0.3088
• Rougelsum: 0.3109
• Bleu: 0.1408

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: 4
• eval_batch_size: 4
• 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	Bleu
1.35	1.0	3390	1.2546	0.2972	0.1424	0.2697	0.2722	0.1256
1.1749	2.0	6780	1.1832	0.3197	0.1655	0.2940	0.2961	0.1313
1.1447	3.0	10170	1.1313	0.3279	0.1742	0.3024	0.3043	0.1372
1.1106	4.0	13560	1.1294	0.3308	0.1790	0.3045	0.3065	0.1386
1.0842	5.0	16950	1.1132	0.3358	0.1831	0.3088	0.3109	0.1408

Framework versions

• PEFT 0.13.2
• Transformers 4.45.1
• Pytorch 2.4.0
• Datasets 3.0.1
• Tokenizers 0.20.0