flan-t5-small-asap_t4_f4_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: 0.0597
• Rouge1: 83.822
• Rouge2: 79.5644
• Rougel: 83.8414
• Rougelsum: 83.8601
• Gen Len: 12.1384

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	266	0.0783	82.3137	77.2617	82.3362	82.3581	12.1836
0.4094	2.0	532	0.0676	82.9368	78.4362	82.962	82.9633	12.1356
0.4094	3.0	798	0.0571	84.7957	80.9486	84.8665	84.8224	12.1963
0.0756	4.0	1064	0.0577	84.5562	80.4996	84.5733	84.5457	12.1667
0.0756	5.0	1330	0.0597	83.822	79.5644	83.8414	83.8601	12.1384

Framework versions

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