flan-t5-large-qa

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

• Loss: 0.1278
• Rouge1: 78.0023
• Rouge2: 66.617
• Rougel: 77.19
• Rougelsum: 77.2401
• Gen Len: 19.0

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	306	0.1278	78.0023	66.617	77.19	77.2401	19.0
0.1993	2.0	612	0.1297	78.1082	66.8695	77.3786	77.3804	19.0
0.1993	3.0	918	0.1325	77.9622	66.9415	77.4017	77.4172	19.0
0.1013	4.0	1224	0.1322	78.0245	66.925	77.3878	77.4057	19.0
0.0694	5.0	1530	0.1396	78.0487	67.1825	77.4944	77.5247	19.0

Framework versions

• Transformers 4.28.0
• Pytorch 2.0.1+cu118
• Datasets 2.12.0
• Tokenizers 0.13.3