flan-t5-large-clara-med

This model is a fine-tuned version of google/flan-t5-large on the CLARA-MeD dataset. It achieves the following results on the evaluation set:

• Loss: 1.0898
• Rouge1: 28.9888
• Rouge2: 16.3801
• Rougel: 27.4186
• Rougelsum: 27.4043
• sari: 39.1731

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: 5

Training results

Training Loss	Epoch	Step	Validation Loss	Rouge1	Rouge2	Rougel	Rougelsum
No log	1.0	380	1.1948	28.2861	15.6461	26.7126	26.7389
No log	2.0	760	1.1361	28.3528	15.8519	26.8151	26.8069
1.3561	3.0	1140	1.1051	29.6216	16.8227	28.0662	28.0613
1.3561	4.0	1520	1.0915	29.3603	16.5008	27.7915	27.7761
1.0939	5.0	1900	1.0898	28.9888	16.3801	27.4186	27.4043

Framework versions

• Transformers 4.25.1
• Pytorch 1.13.0
• Datasets 2.8.0
• Tokenizers 0.12.1