kothasuhas/dclm_tokenized_n124385_ctx1024_pg_sp4096_eos

---
dataset_info:
features:
- name: input_ids
sequence: int32
splits:
- name: train
num_bytes: 505878500
num_examples: 123385
- name: validation
num_bytes: 4100000
num_examples: 1000
download_size: 191285128
dataset_size: 509978500
configs:
- config_name: default
data_files:
- split: train
path: data/train-*
- split: validation
path: data/validation-*
---