baileymachihirota commited on
Commit
ee6465f
·
verified ·
1 Parent(s): 40bed7e

data-ladder tokenized: c4_smollm2/meta.json

Browse files
Files changed (1) hide show
  1. data-ladder/c4_smollm2/meta.json +15 -0
data-ladder/c4_smollm2/meta.json ADDED
@@ -0,0 +1,15 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "dataset": "c4",
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": 5000535,
10
+ "val_bytes": 22155480,
11
+ "val_docs": 10248,
12
+ "train_tokens": 9100000657,
13
+ "train_bytes": 40187264015,
14
+ "train_docs": 18540746
15
+ }