Add NLP evaluation metrics (#8)

Co-authored-by: Zhiyu Wu <zhiyuwu@ampere01.eecs.umich.edu>

data/2023-06-17/score.csv

@@ -1,21 +1,21 @@
-model,lmsys_elo
-lmsys/vicuna-7B,1007
-lmsys/vicuna-13B,1054
-tatsu-lab/alpaca-7B,NaN
-metaai/llama-7B,NaN
-metaai/llama-13B,854
-camel-ai/CAMEL-13B-Combined-Data,NaN
-BlinkDL/RWKV-4-Raven-7B-v12-Eng98%-Other2%-20230521-ctx8192.pth,NaN
-databricks/dolly-v2-12b,866
-FreedomIntelligence/phoenix-inst-chat-7b,NaN
-h2oai/h2ogpt-gm-oasst1-en-2048-open-llama-7b-preview-300bt-v2,NaN
-lmsys/fastchat-t5-3b-v1.0,941
-Neutralzz/BiLLa-7B-SFT,NaN
-nomic-ai/gpt4all-13b-snoozy,NaN
-openaccess-ai-collective/manticore-13b-chat-pyg,NaN
-OpenAssistant/oasst-sft-1-pythia-12b,921
-project-baize/baize-v2-7B,NaN
-BAIR/koala-7b,NaN
-BAIR/koala-13b,980
-StabilityAI/stablelm-tuned-alpha-7b,882
-togethercomputer/RedPajama-INCITE-7B-Chat,NaN
+model,average,ARC (25-s),HellaSwag (10-s),TruthfulQA (MC) (0-s)
+lmsys/vicuna-7B,60.0,53.5,77.5,49.0
+lmsys/vicuna-13B,61.6,52.9,80.1,51.8
+tatsu-lab/alpaca-7B,56.4,52.6,76.9,39.6
+metaai/llama-7B,54.3,51.1,77.7,34.1
+metaai/llama-13B,59.0,56.3,80.9,39.9
+camel-ai/CAMEL-13B-Combined-Data,60.7,55.5,79.3,47.3
+BlinkDL/RWKV-4-Raven-7B-v12-Eng98%-Other2%-20230521-ctx8192.pth,NaN,NaN,NaN,NaN
+databricks/dolly-v2-12b,49.1,42.2,71.8,33.4
+FreedomIntelligence/phoenix-inst-chat-7b,51.8,45.0,63.2,47.1
+h2oai/h2ogpt-gm-oasst1-en-2048-open-llama-7b-preview-300bt-v2,45.5,36.9,61.6,37.9
+lmsys/fastchat-t5-3b-v1.0,43.7,35.9,46.4,48.8
+Neutralzz/BiLLa-7B-SFT,34.2,27.7,26.0,49.0
+nomic-ai/gpt4all-13b-snoozy,61.1,56.1,78.7,48.4
+openaccess-ai-collective/manticore-13b-chat-pyg,63.2,58.7,82.0,48.9
+OpenAssistant/oasst-sft-1-pythia-12b,51.6,45.6,69.9,39.2
+project-baize/baize-v2-7B,55.1,48.5,75.0,41.7
+BAIR/koala-7b,55.6,47.1,73.7,46.0
+BAIR/koala-13b,60.2,52.9,77.5,50.1
+StabilityAI/stablelm-tuned-alpha-7b,41.9,31.9,53.6,40.2
+togethercomputer/RedPajama-INCITE-7B-Chat,49.7,42.2,70.8,36.1