t5-small-hagupitKP

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

• Loss: 1.6372
• Rouge1: 48.834
• Rouge2: 33.4205
• Rougel: 48.6607
• Rougelsum: 48.681
• Gen Len: 8.5017

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
1.1542	1.0	6210	1.7110	47.2887	32.082	47.1742	47.2544	9.4784
1.0404	2.0	12420	1.6650	47.6569	32.5934	47.4988	47.5605	9.0240
0.9219	3.0	18630	1.6880	48.2258	32.5305	48.1079	48.1138	9.1102
0.8346	4.0	24840	1.6372	48.834	33.4205	48.6607	48.681	8.5017
0.8004	5.0	31050	1.6453	49.3895	33.5125	49.2774	49.2772	8.5736
0.7556	6.0	37260	1.6455	49.7786	34.0706	49.6065	49.6091	8.3949
0.7383	7.0	43470	1.6682	48.919	33.1249	48.7316	48.7785	8.4641
0.7848	8.0	49680	1.6800	50.1876	34.2436	49.9813	50.0496	8.3799

Framework versions

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