Update README.md

README.md

@@ -120,7 +120,7 @@ If you plan to fine-tune this model on some downstream tasks, you can follow the
 
 #### Task-Specific Learning Rates
 
-##### Sequence Classification
+##### Sequence Classification:
 
 | Dataset                              | EuroBERT-210m | EuroBERT-610m | EuroBERT-2.1B |
 |--------------------------------------|----------------|----------------|----------------|
@@ -133,7 +133,7 @@ If you plan to fine-tune this model on some downstream tasks, you can follow the
 | CodeComplexity                       | 3.6e-05        | 3.6e-05        | 1.0e-05        |
 | MathShepherd                         | 7.7e-05        | 2.8e-05        | 1.7e-05        |
 
-##### Sequence Regression
+##### Sequence Regression:
 
 | Dataset                  | EuroBERT-210m | EuroBERT-610m | EuroBERT-2.1B |
 |--------------------------|----------------|----------------|----------------|
@@ -141,8 +141,7 @@ If you plan to fine-tune this model on some downstream tasks, you can follow the
 | SummevalMultilingual     | 3.6e-05        | 2.8e-05        | 3.6e-05        |
 | WMT                      | 2.8e-05        | 2.8e-05        | 1.3e-05        |
 
-##### Retrieval
-
+##### Retrieval:
 | Dataset                                 | EuroBERT-210m | EuroBERT-610m | EuroBERT-2.1B |
 |-----------------------------------------|----------------|----------------|----------------|
 | MIRACL                                  | 4.6e-05        | 3.6e-05        | 2.8e-05        |
@@ -153,8 +152,6 @@ If you plan to fine-tune this model on some downstream tasks, you can follow the
 | CqaDupStackMath                         | 4.6e-05        | 2.8e-05        | 3.6e-05        |
 | MathFormula                             | 1.7e-05        | 3.6e-05        | 3.6e-05        |
 
-**Disclaimer**: These are suggested hyperparameters based on our experiments. We recommend conducting your own grid search for best results on your specific downstream task.
-
 ## License
 
 We release the EuroBERT model architectures, model weights, and training codebase under the Apache 2.0 license.