Upload eval_results.csv with huggingface_hub
Browse files- eval_results.csv +24 -0
eval_results.csv
ADDED
|
@@ -0,0 +1,24 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
Task , Accuracy , Centered
|
| 2 |
+
hellaswag_zeroshot , 0.308903 , 0.078537
|
| 3 |
+
jeopardy , 0.002362 , 0.002362
|
| 4 |
+
bigbench_qa_wikidata , 0.201024 , 0.201024
|
| 5 |
+
arc_easy , 0.360269 , 0.147026
|
| 6 |
+
arc_challenge , 0.231229 , -0.025028
|
| 7 |
+
copa , 0.570000 , 0.140000
|
| 8 |
+
commonsense_qa , 0.315315 , 0.144144
|
| 9 |
+
piqa , 0.564200 , 0.128400
|
| 10 |
+
openbook_qa , 0.264000 , 0.018667
|
| 11 |
+
lambada_openai , 0.298079 , 0.298079
|
| 12 |
+
hellaswag , 0.308604 , 0.078138
|
| 13 |
+
winograd , 0.597070 , 0.194139
|
| 14 |
+
winogrande , 0.489345 , -0.021310
|
| 15 |
+
bigbench_dyck_languages , 0.152000 , 0.152000
|
| 16 |
+
agi_eval_lsat_ar , 0.286957 , 0.108696
|
| 17 |
+
bigbench_cs_algorithms , 0.401515 , 0.401515
|
| 18 |
+
bigbench_operators , 0.109524 , 0.109524
|
| 19 |
+
bigbench_repeat_copy_logic , 0.000000 , 0.000000
|
| 20 |
+
squad , 0.003406 , 0.003406
|
| 21 |
+
coqa , 0.144056 , 0.144056
|
| 22 |
+
boolq , 0.533333 , -0.228070
|
| 23 |
+
bigbench_language_identification , 0.256200 , 0.181738
|
| 24 |
+
CORE , , 0.102593
|