text_shortening_model_v18

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

• Loss: 1.7863
• Rouge1: 0.6984
• Rouge2: 0.3313
• Rougel: 0.4652
• Rougelsum: 0.6832
• Bert precision: 0.8799
• Bert recall: 0.8838
• Average word count: 1610.0
• Max word count: 1610
• Min word count: 1610
• Average token count: 16.8143
• % shortened texts with length > 12: 100.0

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: 0.0001
• 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: 1

Training results

Training Loss	Epoch	Step	Validation Loss	Rouge1	Rouge2	Rougel	Rougelsum	Bert precision	Bert recall	Average word count	Max word count	Min word count	Average token count	% shortened texts with length > 12
1.195	1.0	62	1.7863	0.6984	0.3313	0.4652	0.6832	0.8799	0.8838	1610.0	1610	1610	16.8143	100.0

Framework versions

• Transformers 4.33.1
• Pytorch 2.0.1+cu118
• Datasets 2.14.5
• Tokenizers 0.13.3