flan-t5-base-veterinaryQA_data-v2

This model is a fine-tuned version of google/flan-t5-base on an unknown dataset. It achieves the following results on the evaluation set:

• Loss: 1.9591
• Rouge1: 36.0626
• Rouge2: 18.4139
• Rougel: 32.828
• Rougelsum: 32.8636
• Gen Len: 16.8267

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
No log	1.0	483	2.2557	32.6699	15.7335	29.8	29.6992	17.54
2.6483	2.0	966	2.1049	35.2991	18.1944	32.1061	32.1271	16.6533
2.2953	3.0	1449	2.0232	36.4245	18.5726	32.9592	33.1281	16.9867
2.1014	4.0	1932	1.9708	36.14	18.3565	32.8218	32.9808	16.9333
2.0122	5.0	2415	1.9591	36.0626	18.4139	32.828	32.8636	16.8267

Framework versions

• Transformers 4.36.0
• Pytorch 2.1.0+cu118
• Datasets 2.15.0
• Tokenizers 0.15.0