my_legal_summarization_model

This model is a fine-tuned version of t5-small on the eur-lex-sum dataset. It achieves the following results on the evaluation set:

• Loss: 2.1064
• Rouge1: 0.2166
• Rouge2: 0.1493
• Rougel: 0.1992
• Rougelsum: 0.1991
• Gen Len: 19.0

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: 2e-05
• 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: 4
• mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	Rouge1	Rouge2	Rougel	Rougelsum	Gen Len
No log	1.0	71	2.3019	0.2114	0.1485	0.1934	0.1937	19.0
No log	2.0	142	2.1766	0.2156	0.1508	0.1987	0.1988	19.0
No log	3.0	213	2.1215	0.2161	0.1499	0.1988	0.1987	19.0
No log	4.0	284	2.1064	0.2166	0.1493	0.1992	0.1991	19.0

Framework versions

• Transformers 4.35.2
• Pytorch 2.1.1+cu121
• Datasets 2.15.0
• Tokenizers 0.15.0