Improve model card

README.md

@@ -57,13 +57,13 @@ similarity over normalized embeddings.
 
 ## Training
 
-The base revision is `d4aa6901d3a41ba39fb536a557fa166f842b0e09`. We used
-40 reviews sampled from the training split to select the epoch count. Recall@20
-is the primary metric, with Recall@100 and Recall@200 used as tie-breakers. The
-released checkpoint was retrained for one epoch using the full training split
-with Multiple Negatives Ranking Loss, batch size 64, learning rate 2e-5,
-maximum sequence length 512, and seed 718. After excluding articles linked to
-a test review, 334 of the 336 training reviews contribute positive pairs.
+We used 40 reviews sampled from the training split to select the epoch count.
+Recall@20 is the primary metric, with Recall@100 and Recall@200 used as
+tie-breakers. The released checkpoint was retrained for one epoch using the
+full training split with Multiple Negatives Ranking Loss, batch size 64,
+learning rate 2e-5, maximum sequence length 512, and seed 718. After excluding
+articles linked to a test review, 334 of the 336 training reviews contribute
+positive pairs.
 
 There are 5,585 constructed training pairs. The sentence-transformers training
 loader used 5,568 examples in complete batches during the epoch; this accounts
@@ -74,14 +74,10 @@ for the smaller sample count shown by automatically generated trainer metadata.
 All metrics are macro-averaged over the 86 held-out reviews after removing the
 source review itself from each ranking.
 
-| K | Recall@K | Precision@K |
-|---:|---:|---:|
-| 5 | 24.0% | 47.9% |
-| 10 | 38.8% | 42.0% |
-| 20 | 53.5% | 34.0% |
-| 50 | 75.3% | 22.6% |
-| 100 | 84.2% | 14.0% |
-| 200 | 91.7% | 8.4% |
+| Metric | K=5 | K=10 | K=20 | K=50 | K=100 | K=200 |
+|:--|--:|--:|--:|--:|--:|--:|
+| Recall@K | 24.0% | 38.8% | 53.5% | 75.3% | 84.2% | 91.7% |
+| Precision@K | 47.9% | 42.0% | 34.0% | 22.6% | 14.0% | 8.4% |
 
 The source-review split is disjoint, and every article linked to a test review
 is excluded as a positive retriever-training example.