mirror of
https://github.com/SakanaAI/doc-to-lora.git
synced 2026-07-23 17:01:04 +02:00
context distillation eval + timer
This commit is contained in:
parent
f2efe22cba
commit
7d95db6672
17 changed files with 1840 additions and 51 deletions
5
train.py
5
train.py
|
|
@ -302,6 +302,11 @@ def main():
|
|||
tokenized_ds[split][ds_name] = ds
|
||||
|
||||
train_ds = tokenized_ds["train"]
|
||||
if data_args.max_train_samples_per_ds is not None:
|
||||
for ds_name, ds in train_ds.items():
|
||||
if data_args.max_train_samples_per_ds >= len(ds):
|
||||
continue
|
||||
train_ds[ds_name] = ds.take(data_args.max_train_samples_per_ds)
|
||||
logging.info(f"train_ds: {train_ds}")
|
||||
|
||||
val_ds = dict()
|
||||
|
|
|
|||
Loading…
Add table
Add a link
Reference in a new issue