flan-t5-small-chat

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: 2.4063
• Rouge1: 12.3084
• Rouge2: 4.6455
• Rougel: 12.1876
• Rougelsum: 12.1825
• Gen Len: 16.2885

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: 4

Training results

Training Loss	Epoch	Step	Validation Loss	Rouge1	Rouge2	Rougel	Rougelsum	Gen Len
2.6252	1.0	2000	2.4694	12.2248	4.6103	12.1019	12.0965	15.146
2.5362	2.0	4000	2.4252	12.2682	4.7742	12.136	12.1353	15.9622
2.466	3.0	6000	2.4110	12.0624	4.4491	11.9607	11.954	16.2845
2.459	4.0	8000	2.4063	12.3084	4.6455	12.1876	12.1825	16.2885

Framework versions

• Transformers 4.41.0
• Pytorch 2.3.0+cu121
• Datasets 2.19.1
• Tokenizers 0.19.1