Update README.md
Browse files
README.md
CHANGED
@@ -1,3 +1,4 @@
|
|
|
|
1 |
```
|
2 |
hf-causal-experimental (pretrained=openaccess-ai-collective/mighty-llama-1b,use_accelerate=True,dtype=bfloat16,trust_remote_code=True), limit: None, provide_description: False, num_fewshot: 0, batch_size: 32
|
3 |
| Task |Version| Metric |Value | |Stderr|
|
@@ -14,4 +15,25 @@ hf-causal-experimental (pretrained=openaccess-ai-collective/mighty-llama-1b,use_
|
|
14 |
|piqa | 0|acc |0.6518|_ |0.0111|
|
15 |
| | |acc_norm|0.6464|_ |0.0112|
|
16 |
|winogrande | 0|acc |0.5422|_ |0.0140|
|
17 |
-
```
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
### Single Pass
|
2 |
```
|
3 |
hf-causal-experimental (pretrained=openaccess-ai-collective/mighty-llama-1b,use_accelerate=True,dtype=bfloat16,trust_remote_code=True), limit: None, provide_description: False, num_fewshot: 0, batch_size: 32
|
4 |
| Task |Version| Metric |Value | |Stderr|
|
|
|
15 |
|piqa | 0|acc |0.6518|_ |0.0111|
|
16 |
| | |acc_norm|0.6464|_ |0.0112|
|
17 |
|winogrande | 0|acc |0.5422|_ |0.0140|
|
18 |
+
```
|
19 |
+
|
20 |
+
|
21 |
+
### 16x Passees
|
22 |
+
```
|
23 |
+
hf-causal-experimental (pretrained=openaccess-ai-collective/mighty-llama-1b,use_accelerate=True,dtype=bfloat16,trust_remote_code=True), limit: None, provide_description: False, num_fewshot: 0, batch_size: 32
|
24 |
+
| Task |Version| Metric |Value | |Stderr|
|
25 |
+
|-------------|------:|--------|-----:|---|-----:|
|
26 |
+
|arc_challenge| 0|acc |0.2287|_ |0.0123|
|
27 |
+
| | |acc_norm|0.2654|_ |0.0129|
|
28 |
+
|arc_easy | 0|acc |0.4785|_ |0.0103|
|
29 |
+
| | |acc_norm|0.4390|_ |0.0102|
|
30 |
+
|boolq | 1|acc |0.6076|_ |0.0085|
|
31 |
+
|hellaswag | 0|acc |0.3789|_ |0.0048|
|
32 |
+
| | |acc_norm|0.4877|_ |0.0050|
|
33 |
+
|openbookqa | 0|acc |0.1760|_ |0.0170|
|
34 |
+
| | |acc_norm|0.2800|_ |0.0201|
|
35 |
+
|piqa | 0|acc |0.6572|_ |0.0111|
|
36 |
+
| | |acc_norm|0.6589|_ |0.0111|
|
37 |
+
|winogrande | 0|acc |0.5541|_ |0.0140|
|
38 |
+
```
|
39 |
+
|