README.md

metadata

language: nl
widget:
  - text: In het jaar 2030 zullen we
  - text: Toen ik gisteren volledig in de ban was van
  - text: >-
      Studenten en leraren van de Bogazici Universiteit in de Turkse stad
      Istanbul
  - text: In Israël was een strenge lockdown
tags:
  - gpt2-medium
  - gpt2
pipeline_tag: text-generation
datasets:
  - yhavinga/mc4_nl_cleaned

GPT2-Medium pre-trained on cleaned Dutch mC4 🇳🇱

Dataset:

• mC4 NL Cleaned
• dataset split: full (33B tokens)

Tokenizer:

• New tokenizer trained on mC4 with the scripts from the Huggingface Transformers Flax examples

Training details:

• Trained for 240k steps (29 dec 2021)
• Block size: 512
• Optimizer: adam, lr 8e-4, beta1 0.9, beta2 0.98
• Warmup steps: 5000
• Weight decay: 0.01

Work in progress. Dec 2021.

• Many thanks to the Google TPU Research Cloud for providing access to a TPU cluster!
• Thanks to @gsarti for creating the t5-flax-gcp repository.
• Also thanks to the creators of gpt2-medium-persian and gpt2-medium-indonesian for sharing their training scripts!