t5-base-destination-inference

This model is a fine-tuned version of t5-base on the None dataset. It achieves the following results on the evaluation set:

• Loss: 1.4240
• Rouge1: 29.0369
• Rouge2: 0.0
• Rougel: 29.0007
• Rougelsum: 28.9826

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: 5.6e-05
• 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: linear
• num_epochs: 8

Training results

Training Loss	Epoch	Step	Validation Loss	Rouge1	Rouge2	Rougel	Rougelsum
2.1788	1.0	2762	1.6737	21.7686	0.0	21.7958	21.7596
1.7176	2.0	5524	1.5569	24.6017	0.0	24.6017	24.5474
1.556	3.0	8286	1.4978	26.05	0.0	26.05	26.0319
1.4456	4.0	11048	1.4613	26.937	0.0	26.937	26.8827
1.3661	5.0	13810	1.4351	28.2223	0.0	28.2223	28.2042
1.3045	6.0	16572	1.4196	27.9508	0.0	27.9146	27.8965
1.2519	7.0	19334	1.4211	28.8559	0.0	28.8378	28.8197
1.2262	8.0	22096	1.4240	29.0369	0.0	29.0007	28.9826

Framework versions

• Transformers 4.34.0
• Pytorch 2.1.0+cu121
• Datasets 2.14.5
• Tokenizers 0.14.1