t5-small-ufloodKP

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

• Loss: 1.2340
• Rouge1: 51.1957
• Rouge2: 38.6274
• Rougel: 51.029
• Rougelsum: 50.9936
• Gen Len: 7.2789

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: 8

Training results

Training Loss	Epoch	Step	Validation Loss	Rouge1	Rouge2	Rougel	Rougelsum	Gen Len
1.1747	1.0	6058	1.2542	52.1875	40.2309	51.9801	51.9847	8.1324
1.0245	2.0	12116	1.2340	51.1957	38.6274	51.029	50.9936	7.2789
0.9058	3.0	18174	1.2498	51.6649	38.9989	51.5003	51.5001	7.6738
0.8717	4.0	24232	1.2799	51.6254	38.7551	51.5113	51.5324	7.9947
0.7923	5.0	30290	1.2744	52.241	39.1567	52.0777	52.0785	8.0851
0.7674	6.0	36348	1.2981	52.1724	39.1874	51.9824	51.9644	7.7757
0.727	7.0	42406	1.3060	52.0124	39.0293	51.8309	51.8109	7.8134
0.7335	8.0	48464	1.3128	52.1094	39.048	51.9469	51.97	7.9159

Framework versions

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