Llama-3.1-8B-paraphrase-type-generation-etpc-apty-reward

This model is a fine-tuned version of meta-llama/Llama-3.1-8B on the None dataset. It achieves the following results on the evaluation set:

• Loss: 0.7851
• Accuracy: 0.4925

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: 3.0

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy
No log	1.0	34	0.7886	0.4925
No log	2.0	68	0.7860	0.4925
No log	3.0	102	0.7851	0.4925

Framework versions

• PEFT 0.13.2
• Transformers 4.45.1
• Pytorch 2.4.1
• Datasets 3.0.1
• Tokenizers 0.20.0

Citation

Cite this model:

@misc{lübbers2025enhancingparaphrasetypegeneration,
      title={Enhancing Paraphrase Type Generation: The Impact of DPO and RLHF Evaluated with Human-Ranked Data}, 
      author={Christopher Lee Lübbers},
      year={2025},
      eprint={2506.02018},
      archivePrefix={arXiv},
      primaryClass={cs.CL},
      url={https://arxiv.org/abs/2506.02018}, 
}
`