Update README.md

README.md

@@ -65,6 +65,7 @@ Rather than training one model, we trained multiple models, each on a different
 
 # Results
 
-| Dataset | Tokens | Final Val Loss ↓ | ARC-Easy ↑ | ARC-Challenge ↑ | HellaSwag ↑ | PIQA ↑ | SWAG ↑ | BLiMP ↑ | Avg ↑ |
-|:-----------------|-------:|-----------:|-----------:|----------------:|------------:|-------:|-------:|--------:|-------:|
-| [FineWeb](https://huggingface.co/HuggingFaceFW/fineweb) | 500,000,000 | 3.344866 | 27.82% | 22.01% | 26.89% | 52.83% | 30.34% | 65.21% | 37.52% |
+| Dataset | ARC-Easy ↑ | ARC-Challenge ↑ | HellaSwag ↑ | PIQA ↑ | SWAG ↑ | BLiMP ↑ | Avg ↑ |
+|:-----------------|-----------:|----------------:|------------:|-------:|-------:|--------:|-------:|
+| [FineWeb](https://huggingface.co/HuggingFaceFW/fineweb) | 27.82% | 22.01% | 26.89% | 52.83% | 30.34% | 65.21% | 37.52% |
+| [DCLM-1.0-Baseline]() | 29.08% | 22.41% | 27.06% | 52.23% | 31.00% | 66.16% | 37.99% |