Update README.md

README.md

@@ -124,10 +124,10 @@ model-index:
     metrics:
     - type: cosine_accuracy
       value: 0.9089999794960022
-      name: Cosine Accuracy
+      name: Cosine Accuracy on Dev
     - type: cosine_accuracy
       value: 0.9210000038146973
-      name: Cosine Accuracy
+      name: Cosine Accuracy on Test
 ---
 
 # SentenceTransformer based on DeepMount00/Italian-ModernBERT-base
@@ -233,7 +233,7 @@ You can finetune this model on your own dataset.
 
 #### Triplet
 
-* Dataset: `mmarco_dev`
+* Dataset: `mmarco_test`
 * Evaluated with [<code>TripletEvaluator</code>](https://sbert.net/docs/package_reference/sentence_transformer/evaluation.html#sentence_transformers.evaluation.TripletEvaluator)
 
 | Metric              | Value     |
@@ -259,7 +259,8 @@ You can finetune this model on your own dataset.
 #### mmarco
 
 * Dataset: mmarco
-* Size: 39,780,811 training samples
+* Total Size: 39,780,811
+* Size: 50,000 training samples
 * Columns: <code>query</code>, <code>positive</code>, and <code>negative</code>
 * Approximate statistics based on the first 1000 samples:
   |         | query                                                                             | positive                                                                            | negative                                                                            |
@@ -285,7 +286,7 @@ You can finetune this model on your own dataset.
 #### mmarco
 
 * Dataset: mmarco
-* Size: 39,780,811 evaluation samples
+* Size: 2,000 evaluation samples
 * Columns: <code>query</code>, <code>positive</code>, and <code>negative</code>
 * Approximate statistics based on the first 1000 samples:
   |         | query                                                                             | positive                                                                            | negative                                                                            |
@@ -450,6 +451,10 @@ You can finetune this model on your own dataset.
 | 0.24    | 750      | 1.4301        | 1.3971          | 0.8930                     |
 | 0.32    | 1000     | 1.3361        | 1.2686          | 0.8955                     |
 | **0.4** | **1250** | **1.237**     | **1.2151**      | **0.909**                  |
+
+## Test Logs
+| Epoch   | Step     | Training Loss | Validation Loss | mmarco_dev_cosine_accuracy |
+|:-------:|:--------:|:-------------:|:---------------:|:--------------------------:|
 | -1      | -1       | -             | -               | 0.9210                     |
 
 * The bold row denotes the saved checkpoint.