t5-base-tag-generation-recipes

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

• Loss: 0.6106
• Rouge1: 76.7317
• Rouge2: 59.2273
• Rougel: 74.3318
• Rougelsum: 74.2181
• Gen Len: 15.93

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: 2e-05
• train_batch_size: 2
• eval_batch_size: 2
• seed: 42
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• num_epochs: 4
• mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	Rouge1	Rouge2	Rougel	Rougelsum	Gen Len
1.2596	1.0	950	0.7129	75.4613	57.2255	70.7783	70.8028	15.56
0.7531	2.0	1900	0.6407	75.7627	58.0085	72.5222	72.4208	15.71
0.673	3.0	2850	0.6158	76.7922	59.4197	73.5378	73.4624	15.71
0.6064	4.0	3800	0.6106	76.7317	59.2273	74.3318	74.2181	15.93

Framework versions

• Transformers 4.26.1
• Pytorch 1.13.1+cu116
• Datasets 2.10.1
• Tokenizers 0.13.2