metadata
tags:
- generated_from_trainer
- pythia
license: apache-2.0
Model description
Sampling-based watermark distilled Pythia 1.4B using the KGW 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: 64 - eval_batch_size: 8 - seed: 42 - distributed_type: multi-GPU - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 - lr_scheduler_type: cosine - lr_scheduler_warmup_steps: 500 - num_epochs: 1.0
Framework versions
- Transformers 4.29.2
- Pytorch 2.0.1+cu117
- Datasets 2.13.1
- Tokenizers 0.13.3