Update README.md
Browse files
README.md
CHANGED
|
@@ -51,4 +51,20 @@ hf-causal-experimental (pretrained=winglian/basilisk-4b,use_accelerate=True,trus
|
|
| 51 |
|bigbench_tracking_shuffled_objects_five_objects | 0|multiple_choice_grade|0.1904|_ |0.0111|
|
| 52 |
|bigbench_tracking_shuffled_objects_seven_objects| 0|multiple_choice_grade|0.1394|_ |0.0083|
|
| 53 |
|bigbench_tracking_shuffled_objects_three_objects| 0|multiple_choice_grade|0.3800|_ |0.0281|
|
| 54 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 51 |
|bigbench_tracking_shuffled_objects_five_objects | 0|multiple_choice_grade|0.1904|_ |0.0111|
|
| 52 |
|bigbench_tracking_shuffled_objects_seven_objects| 0|multiple_choice_grade|0.1394|_ |0.0083|
|
| 53 |
|bigbench_tracking_shuffled_objects_three_objects| 0|multiple_choice_grade|0.3800|_ |0.0281|
|
| 54 |
+
|
| 55 |
+
hf-causal-experimental (pretrained=winglian/basilisk-4b,use_accelerate=True,trust_remote_code=True), limit: None, provide_description: False, num_fewshot: 0, batch_size: 12
|
| 56 |
+
| Task |Version| Metric |Value | |Stderr|
|
| 57 |
+
|-------------|------:|--------|-----:|---|-----:|
|
| 58 |
+
|arc_challenge| 0|acc |0.3285|_ |0.0137|
|
| 59 |
+
| | |acc_norm|0.3532|_ |0.0140|
|
| 60 |
+
|arc_easy | 0|acc |0.6364|_ |0.0099|
|
| 61 |
+
| | |acc_norm|0.6035|_ |0.0100|
|
| 62 |
+
|boolq | 1|acc |0.7196|_ |0.0079|
|
| 63 |
+
|hellaswag | 0|acc |0.4239|_ |0.0049|
|
| 64 |
+
| | |acc_norm|0.5473|_ |0.0050|
|
| 65 |
+
|openbookqa | 0|acc |0.2220|_ |0.0186|
|
| 66 |
+
| | |acc_norm|0.3320|_ |0.0211|
|
| 67 |
+
|piqa | 0|acc |0.6937|_ |0.0108|
|
| 68 |
+
| | |acc_norm|0.6921|_ |0.0108|
|
| 69 |
+
|winogrande | 0|acc |0.5399|_ |0.0140|
|
| 70 |
+
```
|