pretrain fixed bigcode/the-stack-smol-xl dataset

scripts/prepare_pretrain_dataset.py

@@ -164,10 +164,12 @@ datasets_configs = [
     #
     [
         # 102 MB, 8,700
-        {'path': 'bigcode/the-stack-smol-xl', 'name': name, 'format': lambda n: n['content']}
+        {'path': 'bigcode/the-stack-smol-xl', 'data_dir': f'data/{name}', 'format': lambda n: n['content']}
         for name in [
+            # 'batchfile' - unsafe
+            # 'powershell' - unsafe
             'ada', 'agda', 'alloy', 'antlr', 'applescript', 'assembly',
-            'augeas', 'awk', 'batchfile', 'bison', 'bluespec', 'c',
+            'augeas', 'awk', 'bison', 'bluespec', 'c',
             'c++', 'c-sharp', 'clojure', 'cmake', 'coffeescript', 'common-lisp',
             'css', 'cuda', 'dart', 'dockerfile', 'elixir',
             'elm', 'emacs-lisp','erlang', 'f-sharp', 'fortran', 'glsl', 'go',
@@ -175,7 +177,7 @@ datasets_configs = [
             'java-server-pages', 'javascript', 'julia', 'kotlin', 'lean',
             'literate-agda', 'literate-coffeescript', 'literate-haskell',
             'lua', 'makefile', 'maple', 'markdown', 'mathematica', 'matlab',
-            'ocaml', 'pascal', 'perl', 'php', 'powershell', 'prolog',
+            'ocaml', 'pascal', 'perl', 'php', 'prolog',
             'protocol-buffer', 'python', 'r', 'racket', 'restructuredtext',
             'rmarkdown', 'ruby', 'rust', 'sas', 'scala', 'scheme',
             'shell', 'smalltalk', 'solidity', 'sparql', 'sql', 'stan',