Lamini-fal-prompt-enchance

This model is a fine-tuned version of MBZUAI/LaMini-Flan-T5-248M on an unknown dataset. It achieves the following results on the evaluation set:

• Loss: 1.9041
• Rouge1: 20.9035
• Rouge2: 9.3637
• Rougel: 17.2527
• Rougelsum: 17.2667
• Gen Len: 19.0

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: 64
• 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
2.2667	1.0	1087	2.0387	20.8796	9.0801	17.1295	17.1457	19.0
2.1479	2.0	2174	1.9617	20.9168	9.2939	17.2554	17.2756	19.0
2.0904	3.0	3261	1.9266	20.9394	9.3389	17.2804	17.3005	19.0
2.0609	4.0	4348	1.9096	20.9855	9.3774	17.2773	17.2923	19.0
2.0464	5.0	5435	1.9041	20.9035	9.3637	17.2527	17.2667	19.0

Framework versions

• Transformers 4.42.3
• Pytorch 2.3.0+cu121
• Datasets 2.20.0
• Tokenizers 0.19.1

Citation and attribution

This model release is maintained by Gökay Aydoğan. If you reference this repository in academic work, please cite it as follows and also cite the upstream models, datasets, or projects it builds upon.

@software{aydogan2024lamini_fal_prompt_enchance,
  author = {Aydoğan, Gökay},
  title = {{Lamini-fal-prompt-enchance}},
  year = {2024},
  publisher = {Hugging Face},
  url = {https://huggingface.co/gokaygokay/Lamini-fal-prompt-enchance},
  note = {Model repository; cite the base model and upstream datasets as required.}
}