baileymachihirota commited on
Commit
2fa9867
·
verified ·
1 Parent(s): 7875a96

data-ladder tokenized: refinedweb_smollm2/meta.json

Browse files
data-ladder/refinedweb_smollm2/meta.json ADDED
@@ -0,0 +1,15 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "dataset": "refinedweb",
3
+ "tokenizer": "HuggingFaceTB/SmolLM2-135M",
4
+ "tiktoken_encoding": "HuggingFaceTB/SmolLM2-135M",
5
+ "eot_id": 0,
6
+ "dtype": "uint16",
7
+ "seed": 1234,
8
+ "shuffle_buffer": 0,
9
+ "val_tokens": 5001712,
10
+ "val_bytes": 20404052,
11
+ "val_docs": 6958,
12
+ "train_tokens": 9100001669,
13
+ "train_bytes": 38177323636,
14
+ "train_docs": 14581094
15
+ }