Adding Evaluation Results

README.md

@@ -21,6 +21,9 @@ model-index:
     - type: acc_norm
       value: 60.32
       name: normalized accuracy
+    - type: acc_norm
+      value: 61.09
+      name: normalized accuracy
     source:
       url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=NLUHOPOE/experiment2-cause-non-qLoRa
       name: Open LLM Leaderboard
@@ -37,6 +40,9 @@ model-index:
     - type: acc_norm
       value: 82.92
       name: normalized accuracy
+    - type: acc_norm
+      value: 83.72
+      name: normalized accuracy
     source:
       url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=NLUHOPOE/experiment2-cause-non-qLoRa
       name: Open LLM Leaderboard
@@ -54,6 +60,9 @@ model-index:
     - type: acc
       value: 62.3
       name: accuracy
+    - type: acc
+      value: 64.13
+      name: accuracy
     source:
       url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=NLUHOPOE/experiment2-cause-non-qLoRa
       name: Open LLM Leaderboard
@@ -70,6 +79,8 @@ model-index:
     metrics:
     - type: mc2
       value: 45.47
+    - type: mc2
+      value: 47.34
     source:
       url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=NLUHOPOE/experiment2-cause-non-qLoRa
       name: Open LLM Leaderboard
@@ -87,6 +98,9 @@ model-index:
     - type: acc
       value: 78.06
       name: accuracy
+    - type: acc
+      value: 79.48
+      name: accuracy
     source:
       url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=NLUHOPOE/experiment2-cause-non-qLoRa
       name: Open LLM Leaderboard
@@ -104,6 +118,9 @@ model-index:
     - type: acc
       value: 33.59
       name: accuracy
+    - type: acc
+      value: 40.41
+      name: accuracy
     source:
       url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=NLUHOPOE/experiment2-cause-non-qLoRa
       name: Open LLM Leaderboard
@@ -144,3 +161,17 @@ Detailed results can be found [here](https://huggingface.co/datasets/open-llm-le
 |Winogrande (5-shot)              |78.06|
 |GSM8k (5-shot)                   |33.59|
 
+
+# [Open LLM Leaderboard Evaluation Results](https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard)
+Detailed results can be found [here](https://huggingface.co/datasets/open-llm-leaderboard/details_NLUHOPOE__experiment2-cause-non)
+
+|             Metric              |Value|
+|---------------------------------|----:|
+|Avg.                             |62.69|
+|AI2 Reasoning Challenge (25-Shot)|61.09|
+|HellaSwag (10-Shot)              |83.72|
+|MMLU (5-Shot)                    |64.13|
+|TruthfulQA (0-shot)              |47.34|
+|Winogrande (5-shot)              |79.48|
+|GSM8k (5-shot)                   |40.41|
+