flan-t5-small-asap_t4_f0_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: 0.0532
• Rouge1: 84.7093
• Rouge2: 80.7973
• Rougel: 84.7729
• Rougelsum: 84.7122
• Gen Len: 12.1441

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	0.0737	82.0209	76.901	82.1038	82.0496	12.0960
0.403	2.0	532	0.0612	83.1998	78.7278	83.2379	83.2163	12.1582
0.403	3.0	798	0.0588	84.7251	80.7619	84.8122	84.7804	12.1003
0.0755	4.0	1064	0.0540	84.3926	80.3941	84.4621	84.4156	12.1455
0.0755	5.0	1330	0.0532	84.7093	80.7973	84.7729	84.7122	12.1441

Framework versions

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