• File size measurements show the distribution of size of files.
• Files are classified in four categories based on their size (lines of code): 1-100 (very small files), 101-200 (small files), 201-500 (medium size files), 501-1000 (long files), 1001+(very long files).
• It is a good practice to keep files small. Long files may become "bloaters", code that have increased to such gargantuan proportions that they are hard to work with.

• There are 22 files with 2,800 lines of code.
• 0 very long files (0 lines of code)
• 0 long files (0 lines of code)
• 4 medium size files (1,344 lines of codeclsfd_ftr_w_mp_ins)
• 5 small files (707 lines of code)
• 13 very small files (749 lines of code)

There are 10 files with lines longer than 120 characters. In total, there are 26 long lines.

File	# lines	# units	# long lines
train_policy.py in lm_human_preferences	388	15	8
launch.py in root	157	4	6
train_reward.py in lm_human_preferences	239	7	3
launch.py in lm_human_preferences/utils	55	4	2
model.py in lm_human_preferences/language	268	22	2
tldr.py in lm_human_preferences/datasets	21	1	1
books.py in lm_human_preferences/datasets	13	1	1
cnndm.py in lm_human_preferences/datasets	79	7	1
core.py in lm_human_preferences/utils	449	56	1
rewards.py in lm_human_preferences	129	15	1