fam/nanochat-omni
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

Merge pull request #639 from mathieu-lacage/master

Browse Source 
Verified: both paths return identical data (99,842 rows), and all splits under subset='all' load cleanly.
This commit is contained in:
Andrej
2026-03-25 14:29:30 -07:00
committed by GitHub
parent 47e983eea7 a641b6ca96
commit 7b70f6b411
3 changed files with 5 additions and 10 deletions
Download Patch File Download Diff File Expand all files Collapse all files
scripts/chat_sft.py
+1 -1
View File
@@ -166,7 +166,7 @@ train_tasks = [
SmolTalk(split="train"), # 460K rows of general conversations
CustomJSON(filepath=identity_conversations_filepath), # 1000 rows of synthetic identity conversations
CustomJSON(filepath=identity_conversations_filepath), # 2 epochs of these
*[MMLU(subset="auxiliary_train", split="train") for _ in range(args.mmlu_epochs)], # 100K rows per epoch
*[MMLU(subset="all", split="auxiliary_train") for _ in range(args.mmlu_epochs)], # 100K rows per epoch
*[GSM8K(subset="main", split="train") for _ in range(args.gsm8k_epochs)], # 8K rows per epoch
SimpleSpelling(size=200000, split="train"), # 200K rows of Simple Spelling (e.g. spell the word 'apple')
SpellingBee(size=80000, split="train"), # 80K rows of Spelling Bee (e.g. how many 'r' are in 'strawberry'?)