Add Model Evals
Browse files
README.md
CHANGED
|
@@ -1 +1,15 @@
|
|
| 1 |
-
wandb run: https://wandb.ai/eleutherai/pythia-rlhf/runs/0c0pmvz8
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
wandb run: https://wandb.ai/eleutherai/pythia-rlhf/runs/0c0pmvz8
|
| 2 |
+
|
| 3 |
+
| Task |Version|Filter| Metric |Value | |Stderr|
|
| 4 |
+
|-------------|-------|------|--------|-----:|---|-----:|
|
| 5 |
+
|arc_challenge|Yaml |none |acc |0.2961|± |0.0133|
|
| 6 |
+
| | |none |acc_norm|0.3285|± |0.0137|
|
| 7 |
+
|arc_easy |Yaml |none |acc |0.6452|± |0.0098|
|
| 8 |
+
| | |none |acc_norm|0.5678|± |0.0102|
|
| 9 |
+
|logiqa |Yaml |none |acc |0.2151|± |0.0161|
|
| 10 |
+
| | |none |acc_norm|0.2857|± |0.0177|
|
| 11 |
+
|piqa |Yaml |none |acc |0.7508|± |0.0101|
|
| 12 |
+
| | |none |acc_norm|0.7503|± |0.0101|
|
| 13 |
+
|sciq |Yaml |none |acc |0.8820|± |0.0102|
|
| 14 |
+
| | |none |acc_norm|0.8140|± |0.0123|
|
| 15 |
+
|winogrande |Yaml |none |acc |0.6038|± |0.0137|
|