Update README.md
Browse files
README.md
CHANGED
@@ -14,12 +14,15 @@ tags: []
|
|
14 |
Base model (meta-llama/Llama-3.2-1B-Instruct) results:
|
15 |
|
16 |
|
17 |
-
|Tasks
|
18 |
-
|
19 |
-
|
|
20 |
-
|
|
21 |
-
| |
|
22 |
-
|
|
|
|
|
|
|
|
23 |
|
24 |
|
25 |
|
@@ -27,12 +30,12 @@ Fine-tuned model (meta-llama/Llama-3.2-1B-Instruct using [mlabonne/orpo-dpo-mix-
|
|
27 |
|
28 |
|Tasks |Version|Filter|n-shot| Metric | |Value | |Stderr|
|
29 |
|------|------:|------|-----:|-----------------------|---|-----:|---|------|
|
|
|
|
|
30 |
|ifeval| 4|none | 0|inst_level_loose_acc |↑ |0.5132|± | N/A|
|
31 |
| | |none | 0|inst_level_strict_acc |↑ |0.4748|± | N/A|
|
32 |
| | |none | 0|prompt_level_loose_acc |↑ |0.3752|± |0.0208|
|
33 |
| | |none | 0|prompt_level_strict_acc|↑ |0.3327|± |0.0203|
|
34 |
-
|hellaswag| 1|none | 0|acc |↑ |0.4357|± |0.0049|
|
35 |
-
| | |none | 0|acc_norm|↑ |0.5872|± |0.0049|
|
36 |
|
37 |
### Model Description
|
38 |
|
|
|
14 |
Base model (meta-llama/Llama-3.2-1B-Instruct) results:
|
15 |
|
16 |
|
17 |
+
| Tasks |Version|Filter|n-shot| Metric | |Value | |Stderr|
|
18 |
+
|---------|------:|------|-----:|-----------------------|---|-----:|---|------|
|
19 |
+
|hellaswag| 1|none | 0|acc |↑ |0.4514|± |0.0045|
|
20 |
+
| | |none | 0|acc_norm |↑ |0.6071|± |0.0049|
|
21 |
+
|ifeval | 4|none | 0|inst_level_loose_acc |↑ |0.5479|± | N/A|
|
22 |
+
| | |none | 0|inst_level_strict_acc |↑ |0.4940|± | N/A|
|
23 |
+
| | |none | 0|prompt_level_loose_acc |↑ |0.4103|± |0.0212|
|
24 |
+
| | |none | 0|prompt_level_strict_acc|↑ |0.3548|± |0.0206|
|
25 |
+
|
26 |
|
27 |
|
28 |
|
|
|
30 |
|
31 |
|Tasks |Version|Filter|n-shot| Metric | |Value | |Stderr|
|
32 |
|------|------:|------|-----:|-----------------------|---|-----:|---|------|
|
33 |
+
|hellaswag| 1|none | 0|acc |↑ |0.4357|± |0.0049|
|
34 |
+
| | |none | 0|acc_norm|↑ |0.5872|± |0.0049|
|
35 |
|ifeval| 4|none | 0|inst_level_loose_acc |↑ |0.5132|± | N/A|
|
36 |
| | |none | 0|inst_level_strict_acc |↑ |0.4748|± | N/A|
|
37 |
| | |none | 0|prompt_level_loose_acc |↑ |0.3752|± |0.0208|
|
38 |
| | |none | 0|prompt_level_strict_acc|↑ |0.3327|± |0.0203|
|
|
|
|
|
39 |
|
40 |
### Model Description
|
41 |
|