flan-t5-small-asap_t3_f3_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: 0.0646
• Rouge1: 81.612
• Rouge2: 76.5567
• Rougel: 81.6114
• Rougelsum: 81.6406
• Gen Len: 12.0551

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	259	0.0792	80.0007	74.6342	79.9732	79.9587	12.0304
0.4002	2.0	518	0.0635	81.5641	76.5846	81.5448	81.5698	12.0551
0.4002	3.0	777	0.0609	82.0909	77.2267	82.0977	82.1122	12.0551
0.0715	4.0	1036	0.0658	81.5591	76.4851	81.552	81.5761	12.0580
0.0715	5.0	1295	0.0646	81.612	76.5567	81.6114	81.6406	12.0551

Framework versions

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