KGAQ-2

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: 2.6712
• Rouge1: 9.9002
• Rouge2: 0.817
• Rougel: 9.31
• Rougelsum: 9.8757
• Gen Len: 4.0
• F1: 0.0005
• Recall: 0.0008
• Precision: 0.0003

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: 0.001
• 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: cosine_with_restarts
• num_epochs: 10

Training results

Training Loss	Epoch	Step	Validation Loss	Rouge1	Rouge2	Rougel	Rougelsum	Gen Len	F1	Recall	Precision
3.5701	1.0	598	3.3914	14.1052	1.2078	13.0257	14.1332	3.0	0.0	0.0	0.0
3.0379	2.0	1196	2.7468	12.4379	1.0435	11.3645	12.4814	3.0	0.0005	0.0008	0.0003
2.2773	3.0	1794	2.4962	25.6591	2.6653	16.5422	25.687	6.0	0.0	0.0	0.0
1.8845	4.0	2392	2.4370	8.8131	0.2887	8.1866	8.8014	3.0	0.0005	0.0008	0.0003
1.7721	5.0	2990	2.5342	8.2864	0.5105	7.6569	8.2655	3.0	0.0005	0.0008	0.0003
2.1007	6.0	3588	2.5028	27.8343	3.8693	19.0586	27.8325	6.4795	0.0022	0.0036	0.0015
2.0255	7.0	4186	2.5544	8.2864	0.5105	7.6569	8.2655	3.0	0.0005	0.0008	0.0003
1.9177	8.0	4784	2.5356	22.6347	3.1887	14.2667	22.6751	7.0	0.0005	0.0008	0.0003
1.7165	9.0	5382	2.5492	9.9002	0.817	9.31	9.8757	4.0	0.0005	0.0008	0.0003
1.645	10.0	5980	2.6712	9.9002	0.817	9.31	9.8757	4.0	0.0005	0.0008	0.0003

Framework versions

• Transformers 4.43.3
• Pytorch 2.3.1+cu121
• Datasets 2.20.0
• Tokenizers 0.19.1