flan-t5-base-juraqanda

This model is a fine-tuned version of google/flan-t5-base on the None dataset. It achieves the following results on the evaluation set:

• Loss: 3.0784
• Rouge1: 9.5491
• Rouge2: 1.4927
• Rougel: 8.828
• Rougelsum: 9.2708
• Gen Len: 18.5260

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: 5e-05
• 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
4.0303	1.0	712	3.3466	9.4455	1.2684	8.8558	9.1832	18.7577
3.6049	2.0	1424	3.1931	10.0714	1.4116	9.4163	9.8024	18.6461
3.3464	3.0	2136	3.1246	9.6542	1.4317	8.9441	9.36	18.5485
3.2831	4.0	2848	3.0910	9.6676	1.4584	8.9533	9.3876	18.6706
3.2176	5.0	3560	3.0784	9.5491	1.4927	8.828	9.2708	18.5260

Framework versions

• Transformers 4.26.1
• Pytorch 1.13.1+cu116
• Datasets 2.9.0
• Tokenizers 0.13.2