flan-t5-small-destination-inference

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

• Loss: 0.1533
• Rouge1: 93.7111
• Rouge2: 0.0
• Rougel: 93.7462
• Rougelsum: 93.7462

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
1.5338	1.0	5701	0.2460	89.4132	0.0	89.4395	89.4483
1.2443	2.0	11402	0.2024	90.8692	0.0	90.8868	90.8955
1.1477	3.0	17103	0.1810	91.8779	0.0	91.8954	91.8954
1.0878	4.0	22804	0.1693	92.5445	0.0	92.5621	92.5621
1.0495	5.0	28505	0.1609	93.3164	0.0	93.3427	93.3339
1.0178	6.0	34206	0.1556	93.4041	0.0	93.4216	93.4304
0.9981	7.0	39907	0.1542	93.6935	0.0	93.7286	93.7286
0.9848	8.0	45608	0.1533	93.7111	0.0	93.7462	93.7462

Framework versions

• Transformers 4.33.3
• Pytorch 2.0.1+cu117
• Datasets 2.14.5
• Tokenizers 0.13.3