Finished training.

README.md

@@ -23,7 +23,7 @@ model-index:
       args: default
     metrics:
     - type: accuracy
-      value: 0.9207894736842105
+      value: 0.9235526315789474
       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/quora-distilroberta-base](https://huggingface.co/cross-encoder/quora-distilroberta-base) on the ag_news dataset.
 It achieves the following results on the evaluation set:
-- accuracy: 0.9208
+- accuracy: 0.9236
 
 ## Model description
 
@@ -65,11 +65,11 @@ The following hyperparameters were used during training:
 
 | accuracy | train_loss | epoch |
 |:--------:|:----------:|:-----:|
-| 0.2799   | None       | 0     |
-| 0.9112   | 0.3489     | 0     |
-| 0.9097   | 0.2580     | 1     |
-| 0.9197   | 0.2347     | 2     |
-| 0.9208   | 0.2188     | 3     |
+| 0.2661   | None       | 0     |
+| 0.9099   | 0.3521     | 0     |
+| 0.9142   | 0.2551     | 1     |
+| 0.9239   | 0.2246     | 2     |
+| 0.9236   | 0.2104     | 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 sha256:9b96c2d66816f9054fd06cfb09098636b1b70655ae05107273f26ddaa3db0df1
+oid sha256:136a793f412055338e2a4bc2da10516a5a017c52a1a188424cf85c8764df9d3c
 size 2452296