File size: 160 Bytes
31dc8dc | 1 2 3 4 5 6 7 8 | train: openwebtext
valid: wikitext103
tokenizer_name_or_path: gpt2
cache_dir: /tmp/data
wrap: True
streaming: True
insert_train_eos: True
insert_valid_eos: True |
31dc8dc | 1 2 3 4 5 6 7 8 | train: openwebtext
valid: wikitext103
tokenizer_name_or_path: gpt2
cache_dir: /tmp/data
wrap: True
streaming: True
insert_train_eos: True
insert_valid_eos: True |