Finished training.

README.md

@@ -22,7 +22,7 @@ model-index:
       args: default
     metrics:
     - type: accuracy
-      value: 0.9297368421052632
+      value: 0.9256578947368421
       name: accuracy
 ---
 
@@ -33,7 +33,7 @@ should probably proofread and complete it, then remove this comment. -->
 
 This model is a fine-tuned version of [Jeevesh8/bert_ft_qqp-68](https://huggingface.co/Jeevesh8/bert_ft_qqp-68) on the ag_news dataset.
 It achieves the following results on the evaluation set:
-- accuracy: 0.9297
+- accuracy: 0.9257
 
 ## Model description
 
@@ -64,11 +64,11 @@ The following hyperparameters were used during training:
 
 | accuracy | train_loss | epoch |
 |:--------:|:----------:|:-----:|
-| 0.2599   | None       | 0     |
-| 0.9167   | 0.3214     | 0     |
-| 0.9238   | 0.2279     | 1     |
-| 0.9283   | 0.2080     | 2     |
-| 0.9297   | 0.1969     | 3     |
+| 0.2493   | None       | 0     |
+| 0.9143   | 0.3284     | 0     |
+| 0.9214   | 0.2317     | 1     |
+| 0.9255   | 0.2102     | 2     |
+| 0.9257   | 0.1990     | 3     |
 
 
 ### Framework versions

adapter_config.json

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

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:06a41dbb93d4de5de3888f2b3630cc7f0f3dd57b784d1c578e11f66d845b8767
+oid sha256:41e8ff6c77be7c1e297ca43644726e23986374e2a0eb38ce992929e3c8b5cfce
 size 166552