WooYoungSeok
/

grpo-llama3.1-8b-0623-final

Model card Files Files and versions

WooYoungSeok commited on Jul 19

Commit

a713a63

·

verified ·

1 Parent(s): f40682c

Update README.md

Files changed (1) hide show

README.md +1 -1

README.md CHANGED Viewed

@@ -38,7 +38,7 @@
 | Split | Source | Rows |
 |---|---|---|
-| Train | `train_subset_90pct.json` (90% stratified by error_type, 5-cluster taxonomy from MathEDU + Stepwise Verification + MathClean + EIC) | 6,105 |
 | Eval (during training) | `train_subset_10pct.json` (in-distribution 10% held-out, stratified, seed=42) | 678 |
 ## Performance

 | Split | Source | Rows |
 |---|---|---|
+| Train | `train_subset_90pct.json` (90% stratified by error_type) | 6,105 |
 | Eval (during training) | `train_subset_10pct.json` (in-distribution 10% held-out, stratified, seed=42) | 678 |
 ## Performance