cygu's picture
Update README.md
bc220b2
metadata
tags:
  - generated_from_trainer
datasets:
  - openwebtext
license: llama2

Model description

Logits-based watermark distilled Llama 2 7B using the KTH s=4s=4 watermarking strategy in the paper On the Learnability of Watermarks for Language Models.

Training hyperparameters

The following hyperparameters were used during training:

  • learning_rate: 1e-05
  • train_batch_size: 32
  • eval_batch_size: 8
  • seed: 42
  • distributed_type: multi-GPU
  • num_devices: 4
  • total_train_batch_size: 128
  • total_eval_batch_size: 32
  • optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
  • lr_scheduler_type: cosine
  • lr_scheduler_warmup_steps: 500
  • training_steps: 5000

Framework versions

  • Transformers 4.29.2
  • Pytorch 2.0.1+cu117
  • Datasets 2.13.1
  • Tokenizers 0.13.3