Finished training.

README.md

@@ -23,7 +23,7 @@ model-index:
       args: irony
     metrics:
     - type: accuracy
-      value: 0.6638743455497382
+      value: 0.6659685863874345
       name: accuracy
 ---
 
@@ -34,7 +34,7 @@ should probably proofread and complete it, then remove this comment. -->
 
 This model is a fine-tuned version of [bert-base-uncased](https://huggingface.co/bert-base-uncased) on the tweet_eval dataset.
 It achieves the following results on the evaluation set:
-- accuracy: 0.6639
+- accuracy: 0.6660
 
 ## Model description
 
@@ -65,15 +65,15 @@ The following hyperparameters were used during training:
 
 | accuracy | train_loss | epoch |
 |:--------:|:----------:|:-----:|
-| 0.4827   | None       | 0     |
-| 0.5686   | 0.6998     | 0     |
-| 0.5801   | 0.6597     | 1     |
-| 0.6220   | 0.6154     | 2     |
-| 0.6524   | 0.5970     | 3     |
-| 0.6346   | 0.5721     | 4     |
-| 0.6471   | 0.5588     | 5     |
-| 0.6545   | 0.5436     | 6     |
-| 0.6639   | 0.5430     | 7     |
+| 0.4775   | None       | 0     |
+| 0.5654   | 0.6976     | 0     |
+| 0.6115   | 0.6567     | 1     |
+| 0.6241   | 0.6117     | 2     |
+| 0.6649   | 0.5838     | 3     |
+| 0.6471   | 0.5611     | 4     |
+| 0.6440   | 0.5594     | 5     |
+| 0.6576   | 0.5457     | 6     |
+| 0.6660   | 0.5372     | 7     |
 
 
 ### 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 sha256:93a4f4678799d11e39b37d6448dee494321e9ceed5b660433cc76d1511ab7d11
+oid sha256:338b7d04650791ad0a1bc6208fe8ac5f5312c68e4195023d57518e33bf3d0333
 size 160400