| train: HuggingFaceFW/fineweb-edu | |
| valid: openwebtext-valid #wikitext103 | |
| tokenizer_name_or_path: gpt2 | |
| cache_dir: ./cache | |
| wrap: True | |
| streaming: True | |
| insert_train_eos: True | |
| insert_valid_eos: True |
| train: HuggingFaceFW/fineweb-edu | |
| valid: openwebtext-valid #wikitext103 | |
| tokenizer_name_or_path: gpt2 | |
| cache_dir: ./cache | |
| wrap: True | |
| streaming: True | |
| insert_train_eos: True | |
| insert_valid_eos: True |