Finished training.

README.md

@@ -22,7 +22,7 @@ model-index:
       args: default
     metrics:
     - type: accuracy
-      value: 0.9284210526315789
+      value: 0.9301315789473684
       name: accuracy
 ---
 
@@ -33,7 +33,7 @@ should probably proofread and complete it, then remove this comment. -->
 
 This model is a fine-tuned version of [connectivity/bert_ft_qqp-7](https://huggingface.co/connectivity/bert_ft_qqp-7) on the ag_news dataset.
 It achieves the following results on the evaluation set:
-- accuracy: 0.9284
+- accuracy: 0.9301
 
 ## Model description
 
@@ -64,11 +64,11 @@ The following hyperparameters were used during training:
 
 | accuracy | train_loss | epoch |
 |:--------:|:----------:|:-----:|
-| 0.2729   | None       | 0     |
-| 0.9166   | 0.3328     | 0     |
-| 0.9220   | 0.2335     | 1     |
-| 0.9263   | 0.2118     | 2     |
-| 0.9284   | 0.2012     | 3     |
+| 0.2486   | None       | 0     |
+| 0.9176   | 0.3278     | 0     |
+| 0.9228   | 0.2313     | 1     |
+| 0.9297   | 0.2097     | 2     |
+| 0.9301   | 0.1984     | 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:e5da83e24bc94f096d24fec4dc8e1fb6815bd643bf17f6eba8dc5a88e1bc99d0
+oid sha256:d551cda07bf9d79e7f08ef47720138d0826c797359274f9fedee8411e7d41697
 size 166552