t5-base-samsum

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

• Loss: 0.6172
• Rouge1: 48.9131
• Rouge2: 25.4942
• Rougel: 41.2363
• Rougelsum: 45.3434

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: 5

Training results

Training Loss	Epoch	Step	Validation Loss	Rouge1	Rouge2	Rougel	Rougelsum
0.7606	1.0	3683	0.6254	46.9778	23.8245	39.8294	43.4639
0.6273	2.0	7366	0.6119	48.2515	24.7534	40.4415	44.5567
0.5769	3.0	11049	0.6116	48.228	24.7865	40.7537	44.4026
0.5412	4.0	14732	0.6145	48.8563	25.356	41.1913	45.186
0.5199	5.0	18415	0.6172	48.9131	25.4942	41.2363	45.3434

Framework versions

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