Fix: ensure correct handling of `val_set_size` as `float` or `int` (#1655)
Browse files* Fix: ensure correct handling of val_set_size as float or int
* chore: lint
---------
Co-authored-by: Wing Lian <[email protected]>
src/axolotl/utils/data/sft.py
CHANGED
@@ -494,7 +494,9 @@ def load_prepare_datasets(
|
|
494 |
test_fingerprint = md5(to_hash_test)
|
495 |
|
496 |
dataset = dataset.train_test_split(
|
497 |
-
test_size=cfg.val_set_size
|
|
|
|
|
498 |
shuffle=False,
|
499 |
seed=cfg.seed or 42,
|
500 |
train_new_fingerprint=train_fingerprint,
|
|
|
494 |
test_fingerprint = md5(to_hash_test)
|
495 |
|
496 |
dataset = dataset.train_test_split(
|
497 |
+
test_size=int(cfg.val_set_size)
|
498 |
+
if cfg.val_set_size == int(cfg.val_set_size)
|
499 |
+
else cfg.val_set_size,
|
500 |
shuffle=False,
|
501 |
seed=cfg.seed or 42,
|
502 |
train_new_fingerprint=train_fingerprint,
|