W3bsurf/Llawma-sum-2-7b-chat

results

This model is a fine-tuned version of meta-llama/Llama-2-7b-chat-hf on the dreamproit/bill_summary_us dataset. It achieves the following results on the evaluation set:

• Loss: 0.7163

Model description

Model has been fine-tuned from llama 2 7B chat model for legal summarization tasks.

Intended uses & limitations

The model has been fine-tuned with legal summarization text for summarization tasks. Can produce repeating text when creating longer outputs. Tested only with english and the bill_summary_us dataset.

Training procedure

SFTTrainer from Hugging Face's TRL library used for fine-tuning process.

Training hyperparameters

The following hyperparameters were used during training:

• learning_rate: 0.0002
• train_batch_size: 4
• eval_batch_size: 8
• seed: 42
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: constant
• lr_scheduler_warmup_ratio: 0.03
• num_epochs: 1

Training results

Training Loss	Epoch	Step	Validation Loss
0.8263	0.24	70	0.7693
0.6035	0.48	140	0.7467
0.845	0.72	210	0.7347
0.5782	0.96	280	0.7163

Framework versions

• Transformers 4.35.2
• Pytorch 2.1.0+cu118
• Datasets 2.15.0
• Tokenizers 0.15.0

license

Llama 2 is licensed under the LLAMA 2 Community License, Copyright © Meta Platforms, Inc. All Rights Reserved.