Merge branch 'main' into fix-conversion-from-hf

EleutherAI · Oct 31, 2023 · 7c50e77 · 7c50e77
2 parents 71ca6cf + f574f22
commit 7c50e77
Show file tree

Hide file tree

Showing 3 changed files with 3 additions and 3 deletions.
diff --git a/configs/neox_arguments.md b/configs/neox_arguments.md
@@ -111,7 +111,7 @@ Logging Arguments
 
 - **git_hash**: str
 
-    Default = 4579a33
+    Default = 2ff807d
 
     current git hash of repository
 

diff --git a/megatron/neox_arguments/neox_args.py b/megatron/neox_arguments/neox_args.py
@@ -390,7 +390,7 @@ class NeoXArgsOptimizer(NeoXArgsTemplate):
         "adam", "onebitadam", "cpu_adam", "cpu_torch_adam", "sm3", "madgrad_wd", "sgd", "lion"
     ] = "adam"
     """
-    Type of optimizer to use. Choose from ['adam', 'onebitadam', 'cpu_adam', 'cpu_torch_adam', 'sm3', 'madgrad_wd', 'sgd']
+    Type of optimizer to use. Choose from ['adam', 'onebitadam', 'cpu_adam', 'cpu_torch_adam', 'sm3', 'madgrad_wd', 'sgd', 'lion']
     NOTE: sgd will use MuSGD from Mup. Mup must be enabled for this optimizer.
     """
 

diff --git a/tools/datasets/corpora.py b/tools/datasets/corpora.py
@@ -141,7 +141,7 @@ def tokenize(self):
             [os.path.join(parent_folder, os.path.basename(url)) for url in self.urls]
         )
 
-        cmd = f"python tools/preprocess_data.py \
+        cmd = f"python tools/datasets/preprocess_data.py \
             --input {jsonl_filepath} \
             --output-prefix {parent_folder}/{self.name} \
             --vocab {self.vocab_file} \