Upload eval_results/mattshumer/Reflection-Llama-3.1-70B/main/mixeval/results_2024-09-06T22-25-59.json with huggingface_hub
Browse files
eval_results/mattshumer/Reflection-Llama-3.1-70B/main/mixeval/results_2024-09-06T22-25-59.json
ADDED
@@ -0,0 +1,20 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"overall score (final score)": 0.8075,
|
3 |
+
"DROP": 0.936,
|
4 |
+
"BBH": 0.926,
|
5 |
+
"MATH": 0.865,
|
6 |
+
"GSM8k": 0.959,
|
7 |
+
"TriviaQA": 0.888,
|
8 |
+
"AGIEval": 0.634,
|
9 |
+
"MMLU": 0.718,
|
10 |
+
"MBPP": 0.0,
|
11 |
+
"BoolQ": 0.869,
|
12 |
+
"HellaSwag": 0.549,
|
13 |
+
"GPQA": 0.0,
|
14 |
+
"PIQA": 0.844,
|
15 |
+
"ARC": 0.913,
|
16 |
+
"OpenBookQA": 0.75,
|
17 |
+
"SIQA": 0.765,
|
18 |
+
"CommonsenseQA": 0.623,
|
19 |
+
"WinoGrande": 1.0
|
20 |
+
}
|