flan-t5-small-asap_t5_f2_prompt_adherence

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

• Loss: 0.0615
• Rouge1: 80.7114
• Rouge2: 75.8121
• Rougel: 80.7571
• Rougelsum: 80.7981
• Gen Len: 12.0402

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: 5e-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	Gen Len
No log	1.0	271	0.0966	76.5493	69.7036	76.5316	76.5317	12.0055
0.4737	2.0	542	0.0724	79.7463	74.3566	79.7676	79.7403	12.0319
0.4737	3.0	813	0.0658	80.0516	74.841	80.0495	80.0296	12.0291
0.0868	4.0	1084	0.0615	80.5625	75.5964	80.5884	80.5837	12.0332
0.0868	5.0	1355	0.0615	80.7114	75.8121	80.7571	80.7981	12.0402

Framework versions

• Transformers 4.38.2
• Pytorch 2.1.2
• Datasets 2.18.0
• Tokenizers 0.15.2