Finished training.

README.md

@@ -23,7 +23,7 @@ model-index:
       args: default
     metrics:
     - type: accuracy
-      value: 0.8961842105263158
+      value: 0.8952631578947369
       name: accuracy
 ---
 
@@ -34,7 +34,7 @@ should probably proofread and complete it, then remove this comment. -->
 
 This model is a fine-tuned version of [cross-encoder/ms-marco-MiniLM-L-4-v2](https://huggingface.co/cross-encoder/ms-marco-MiniLM-L-4-v2) on the ag_news dataset.
 It achieves the following results on the evaluation set:
-- accuracy: 0.8962
+- accuracy: 0.8953
 
 ## Model description
 
@@ -65,11 +65,11 @@ The following hyperparameters were used during training:
 
 | accuracy | train_loss | epoch |
 |:--------:|:----------:|:-----:|
-| 0.2284   | None       | 0     |
-| 0.8828   | 0.5132     | 0     |
-| 0.8903   | 0.3630     | 1     |
-| 0.8916   | 0.3440     | 2     |
-| 0.8962   | 0.3353     | 3     |
+| 0.2501   | None       | 0     |
+| 0.8776   | 0.5708     | 0     |
+| 0.8908   | 0.3556     | 1     |
+| 0.8939   | 0.3248     | 2     |
+| 0.8953   | 0.3130     | 3     |
 
 
 ### Framework versions

adapter_config.json

@@ -19,8 +19,8 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "query",
-    "value"
+    "value",
+    "query"
   ],
   "task_type": "SEQ_CLS",
   "use_rslora": false

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2a59964b8afb7a1a592361dc2052fd39548d71ec52c553cb07c3e4d6166f6751
+oid sha256:e50ef9a7b3ab9ce41feb3b0003b777e087d04257c56311cce6c003fab225a7d1
 size 33128