text_shortening_model_v64

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

• Loss: 2.3622
• Bert precision: 0.7381
• Bert recall: 0.7763
• Bert f1-score: 0.7541
• Average word count: 9.0345
• Max word count: 14
• Min word count: 2
• Average token count: 15.5862
• % shortened texts with length > 12: 20.6897

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: 16
• eval_batch_size: 16
• 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	Bert precision	Bert recall	Bert f1-score	Average word count	Max word count	Min word count	Average token count	% shortened texts with length > 12
3.1461	1.0	5	2.3622	0.7381	0.7763	0.7541	9.0345	14	2	15.5862	20.6897

Framework versions

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