kothasuhas/dclm_tokenized_n307888_ctx4096_pg_sp4096_eos

---
dataset_info:
features:
- name: input_ids
sequence: uint16
length: 4096
splits:
- name: train
num_bytes: 2522218496
num_examples: 307888
download_size: 1881565755
dataset_size: 2522218496
configs:
- config_name: default
data_files:
- split: train
path: data/train-*
---