Fix typos (#1143)

Found via `codespell -S .mypy_cache,yarn.lock,*.json,*.ipynb -L
rouge,nam,vie`

model/reward/instructor/TODO.md

@@ -1,6 +1,6 @@
 Some other reward features we can use
 
-0. Finish classifcation feature
+0. Finish classification feature
 
 1. Summaries from human feedback
 

model/reward/instructor/rank_datasets.py

@@ -14,7 +14,7 @@
     [] support additional negative samples generated from other models.
 
         For example we can use galactica-125m to generate a TLDR and assume it was
-        inferior than the human perference one
+        inferior than the human preference one
 
 
 """

model/supervised_finetuning/custom_datasets/README.md

@@ -23,5 +23,5 @@ Issues and TODO:
 - ideally we can update the config yaml and new dataset will be download from
   hub
 
-  - one possible idea is we upload the trasform format of these dataset to the
+  - one possible idea is we upload the transform format of these dataset to the
     OA hub

model/supervised_finetuning/custom_datasets/qa_datasets.py

@@ -314,7 +314,7 @@ class JokeExplaination(Dataset):
             for line in f:
                 data = json.loads(line)
                 joke = data["joke"]
-                explanation = data["explaination"]
+                explanation = data["explanation"]
                 self.pairs.append((joke, explanation))
 
         if len(question) > 0 and len(answer) > 0: