Update README.md
Browse files
README.md
CHANGED
@@ -170,10 +170,10 @@ Average: 61.24%
|
|
170 |
| Tasks |Version| Filter |n-shot| Metric |Value | |Stderr|
|
171 |
|----------------------------------------------------|------:|----------------|-----:|-----------|-----:|---|-----:|
|
172 |
|bbh_zeroshot_tracking_shuffled_objects_three_objects| 2|flexible-extract| 0|exact_match|0.2760|± |0.0283|
|
173 |
-
|bbh_zeroshot_tracking_shuffled_objects_seven_objects| 2
|
174 |
|bbh_zeroshot_tracking_shuffled_objects_five_objects | 2|flexible-extract| 0|exact_match|0.1240|± |0.0209|
|
175 |
|bbh_zeroshot_temporal_sequences | 2|flexible-extract| 0|exact_match|0.4520|± |0.0315|
|
176 |
-
|bbh_zeroshot_sports_understanding | 2
|
177 |
|bbh_zeroshot_snarks | 2|flexible-extract| 0|exact_match|0.5056|± |0.0376|
|
178 |
|bbh_zeroshot_salient_translation_error_detection | 2|flexible-extract| 0|exact_match|0.4480|± |0.0315|
|
179 |
|bbh_zeroshot_ruin_names | 2|flexible-extract| 0|exact_match|0.4520|± |0.0315|
|
|
|
170 |
| Tasks |Version| Filter |n-shot| Metric |Value | |Stderr|
|
171 |
|----------------------------------------------------|------:|----------------|-----:|-----------|-----:|---|-----:|
|
172 |
|bbh_zeroshot_tracking_shuffled_objects_three_objects| 2|flexible-extract| 0|exact_match|0.2760|± |0.0283|
|
173 |
+
|bbh_zeroshot_tracking_shuffled_objects_seven_objects| 2|flexible-extract| 0|exact_match|0.1280|± |0.0212|
|
174 |
|bbh_zeroshot_tracking_shuffled_objects_five_objects | 2|flexible-extract| 0|exact_match|0.1240|± |0.0209|
|
175 |
|bbh_zeroshot_temporal_sequences | 2|flexible-extract| 0|exact_match|0.4520|± |0.0315|
|
176 |
+
|bbh_zeroshot_sports_understanding | 2|flexible-extract| 0|exact_match|0.7120|± |0.0287|
|
177 |
|bbh_zeroshot_snarks | 2|flexible-extract| 0|exact_match|0.5056|± |0.0376|
|
178 |
|bbh_zeroshot_salient_translation_error_detection | 2|flexible-extract| 0|exact_match|0.4480|± |0.0315|
|
179 |
|bbh_zeroshot_ruin_names | 2|flexible-extract| 0|exact_match|0.4520|± |0.0315|
|