metadata

license: llama2
tags:
  - llama-factory
  - legal
base_model: meta-llama/Llama-2-7b-hf
model-index:
  - name: inlegalllama-pt-15-04-2024
    results: []
datasets:
  - sudipto-ducs/InLegalLLaMA-data
language:
  - en
pipeline_tag: text-generation

InLegalLLaMA

This model is a fine-tuned version of meta-llama/Llama-2-7b-hf on the inlegalllama-laws and the inlegalllama-sci datasets.

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: 0.0003
train_batch_size: 2
eval_batch_size: 8
seed: 42
gradient_accumulation_steps: 8
total_train_batch_size: 16
optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
lr_scheduler_type: cosine
lr_scheduler_warmup_steps: 2000
num_epochs: 3.0
mixed_precision_training: Native AMP

Training results

Framework versions

PEFT 0.10.0
Transformers 4.39.0
Pytorch 2.2.1+cu121
Datasets 2.18.0
Tokenizers 0.15.2