Update README.md

README.md

@@ -54,10 +54,10 @@ print(tokenizer.decode(sample[0]))
 
 The CLEX-Phi-2-2.7B and CLEX-Mixtral-8x7B are trained on [LongCorpus-2.5B](https://huggingface.co/datasets/DAMO-NLP-SG/LongCorpus-2.5B), where the eval results on test set are listed below.
 
-|                   | Train Length | Eval.(32k) | Eval.(64k) | Eval.(128k) |
-| ----------------- | ------------ | ---------- | ---------- | ----------- |
-| Phi-2        | 2k           | >100       | >100       | >100        |
-| CLEX-Phi-2   | 32k          | 5.96       | 6.07       | 7.46        |
+|                   | Train Length | Eval.(16k) | | Eval.(32k) | Eval.(64k) | Eval.(128k) |
+| ----------------- | ------------ | ---------- | ---------- | ----------- |---------- |
+| Phi-2        | 2k           | >100       | >100       | >100        | >100        |
+| CLEX-Phi-2   | 32k          | 5.21       | 5.11       | 5.17       |6.55       |