Update README.md

README.md

@@ -25,8 +25,8 @@ ProX models are evaluated over 10 language model benchmarks in zero-shot setting
 
 |                       | ARC-C | ARC-E | CSQA  | HellaS | MMLU  | OBQA  | PiQA  | SIQA  | WinoG | SciQ  | AVG  |
 |-----------------------|-------|-------|-------|-----------|-------|-------|-------|-------|-------|-------|------|
-| Original Data | 22.6% | 41.9% | 29.7% | 32.8%     | 26.2% | 26.4% | 62.2% | 39.3% | 51.3% | 63.3% | 39.6 |
-| RedPJ-ProX-0.3B       | 25.9% | 47.5% | 29.2% | 36.7%     | 28.1% | 30.2% | 64.6% | 38.0% | 51.7% | 71.4% | 42.3 |
+| raw | 22.6% | 41.9% | 29.7% | 32.8%     | 26.2% | 26.4% | 62.2% | 39.3% | 51.3% | 63.3% | 39.6 |
+| ours       | 25.9% | 47.5% | 29.2% | 36.7%     | 28.1% | 30.2% | 64.6% | 38.0% | 51.7% | 71.4% | 42.3 |
 
 ### Citation
 ```