t5-small-usFloodKP

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

• Loss: 1.2133
• Rouge1: 41.329
• Rouge2: 31.7448
• Rougel: 41.0539
• Rougelsum: 41.0854
• Gen Len: 7.8782

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: 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: 10

Training results

Training Loss	Epoch	Step	Validation Loss	Rouge1	Rouge2	Rougel	Rougelsum	Gen Len
1.1973	1.0	6106	1.2133	41.329	31.7448	41.0539	41.0854	7.8782
1.0408	2.0	12212	1.2598	36.2303	26.3894	35.9474	36.013	7.1096
0.8882	3.0	18318	1.2938	35.7625	25.8543	35.5037	35.5276	7.2957
0.8565	4.0	24424	1.3479	34.8334	24.7897	34.5888	34.6214	7.3202
0.8047	5.0	30530	1.3929	33.5704	23.9038	33.3466	33.342	6.8862
0.741	6.0	36636	1.4090	33.9833	24.1251	33.737	33.7471	7.2181
0.7176	7.0	42742	1.4378	33.416	23.5456	33.1511	33.1855	6.9133
0.6806	8.0	48848	1.4700	32.3628	22.4886	32.1	32.1102	6.8734
0.6731	9.0	54954	1.4713	32.9482	23.1778	32.6983	32.7137	6.9644
0.6456	10.0	61060	1.4765	32.9416	23.1376	32.6633	32.7205	6.9596

Framework versions

• Transformers 4.39.3
• Pytorch 2.2.1+cu121
• Datasets 2.18.0
• Tokenizers 0.15.2