• 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 3,012 files with 51,606 lines of code.
• 4 very long files (5,525 lines of code)
• 2 long files (1,676 lines of code)
• 20 medium size files (6,861 lines of codeclsfd_ftr_w_mp_ins)
• 45 small files (6,132 lines of code)
• 2,941 very small files (31,412 lines of code)

There are 176 files with lines longer than 120 characters. In total, there are 284 long lines.

File	# lines	# units	# long lines
flan_held_in.yaml in lm_eval/tasks/benchmarks/flan	345	-	42
huggingface.py in lm_eval/models	1037	35	9
evaluation_tracker.py in lm_eval/loggers	397	8	8
__main__.py in lm_eval	401	6	7
utils.py in lm_eval/tasks/minerva_math	229	13	7
utils.py in lm_eval/tasks/leaderboard/math	95	6	7
task.py in lm_eval/api	1218	79	5
nemo_lm.py in lm_eval/models	423	25	5
__init__.py in lm_eval/tasks	471	34	5
zeno_visualize.py in scripts	174	5	3
regression.py in scripts	155	6	3
evaluator.py in lm_eval	466	4	3
evaluator_utils.py in lm_eval	384	14	3
boolean_expressions.yaml in lm_eval/tasks/bbh/cot_fewshot	21	-	3
registry.py in lm_eval/api	140	12	2
samplers.py in lm_eval/api	117	8	2
model.py in lm_eval/api	183	26	2
tracking_shuffled_objects_five_objects.yaml in lm_eval/tasks/bbh/cot_zeroshot	19	-	2
tracking_shuffled_objects_seven_objects.yaml in lm_eval/tasks/bbh/cot_zeroshot	19	-	2
navigate.yaml in lm_eval/tasks/bbh/cot_zeroshot	17	-	2
snarks.yaml in lm_eval/tasks/bbh/cot_zeroshot	19	-	2
tracking_shuffled_objects_three_objects.yaml in lm_eval/tasks/bbh/cot_zeroshot	19	-	2
french_bench_fquadv2_genq.yaml in lm_eval/tasks/french_bench	26	-	2
metric.py in lm_eval/tasks/realtoxicityprompts	67	1	2
polemo2_in.yaml in lm_eval/tasks/polemo2	46	-	2
t5_utils.py in lm_eval/tasks/super_glue/wsc	76	4	2
cost_estimate.py in scripts	72	6	1
write_out.py in scripts	78	2	1
model_comparator.py in scripts	123	4	1
group.py in lm_eval/api	81	13	1
openai_completions.py in lm_eval/models	342	24	1
vllm_causallms.py in lm_eval/models	412	18	1
neuron_optimum.py in lm_eval/models	497	23	1
selection.py in lm_eval/filters	28	6	1
boolean_expressions.yaml in lm_eval/tasks/bbh/cot_zeroshot	17	-	1
causal_judgement.yaml in lm_eval/tasks/bbh/cot_zeroshot	17	-	1
logical_deduction_seven_objects.yaml in lm_eval/tasks/bbh/cot_zeroshot	19	-	1
word_sorting.yaml in lm_eval/tasks/bbh/cot_zeroshot	15	-	1
penguins_in_a_table.yaml in lm_eval/tasks/bbh/cot_zeroshot	19	-	1
formal_fallacies.yaml in lm_eval/tasks/bbh/cot_zeroshot	17	-	1
ruin_names.yaml in lm_eval/tasks/bbh/cot_zeroshot	19	-	1
temporal_sequences.yaml in lm_eval/tasks/bbh/cot_zeroshot	19	-	1
web_of_lies.yaml in lm_eval/tasks/bbh/cot_zeroshot	20	-	1
logical_deduction_five_objects.yaml in lm_eval/tasks/bbh/cot_zeroshot	19	-	1
dyck_languages.yaml in lm_eval/tasks/bbh/cot_zeroshot	17	-	1
hyperbaton.yaml in lm_eval/tasks/bbh/cot_zeroshot	19	-	1
logical_deduction_three_objects.yaml in lm_eval/tasks/bbh/cot_zeroshot	19	-	1
geometric_shapes.yaml in lm_eval/tasks/bbh/cot_zeroshot	19	-	1
salient_translation_error_detection.yaml in lm_eval/tasks/bbh/cot_zeroshot	19	-	1
reasoning_about_colored_objects.yaml in lm_eval/tasks/bbh/cot_zeroshot	19	-	1