t5-small-destination-inference

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

• Loss: 1.6668
• Rouge1: 25.6235
• Rouge2: 0.0
• Rougel: 25.6064
• Rougelsum: 25.6064

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
2.6932	1.0	2927	2.0668	19.9009	0.0	19.9009	19.8838
2.1793	2.0	5854	1.8923	22.2668	0.0	22.2583	22.2412
2.0209	3.0	8781	1.8088	23.1807	0.0	23.1893	23.1978
1.9254	4.0	11708	1.7439	24.5815	0.0	24.5815	24.5815
1.8585	5.0	14635	1.7105	24.7865	0.0	24.7865	24.7865
1.814	6.0	17562	1.6863	25.2989	0.0	25.316	25.2989
1.781	7.0	20489	1.6730	25.3844	0.0	25.3844	25.3502
1.7679	8.0	23416	1.6668	25.6235	0.0	25.6064	25.6064

Framework versions

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