Finished training.

README.md

@@ -23,7 +23,7 @@ model-index:
       args: irony
     metrics:
     - type: accuracy
-      value: 0.6722513089005235
+      value: 0.6617801047120419
       name: accuracy
 ---
 
@@ -34,7 +34,7 @@ should probably proofread and complete it, then remove this comment. -->
 
 This model is a fine-tuned version of [michiyasunaga/LinkBERT-base](https://huggingface.co/michiyasunaga/LinkBERT-base) on the tweet_eval dataset.
 It achieves the following results on the evaluation set:
-- accuracy: 0.6723
+- accuracy: 0.6618
 
 ## Model description
 
@@ -65,15 +65,15 @@ The following hyperparameters were used during training:
 
 | accuracy | train_loss | epoch |
 |:--------:|:----------:|:-----:|
-| 0.4733   | None       | 0     |
-| 0.5518   | 0.7046     | 0     |
-| 0.5749   | 0.6710     | 1     |
-| 0.5948   | 0.6381     | 2     |
-| 0.6283   | 0.6162     | 3     |
-| 0.6492   | 0.5958     | 4     |
-| 0.6178   | 0.5804     | 5     |
-| 0.6649   | 0.5671     | 6     |
-| 0.6723   | 0.5654     | 7     |
+| 0.4827   | None       | 0     |
+| 0.5372   | 0.7000     | 0     |
+| 0.5832   | 0.6775     | 1     |
+| 0.6157   | 0.6412     | 2     |
+| 0.6335   | 0.6156     | 3     |
+| 0.6524   | 0.5930     | 4     |
+| 0.6314   | 0.5777     | 5     |
+| 0.6586   | 0.5745     | 6     |
+| 0.6618   | 0.5686     | 7     |
 
 
 ### 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 sha256:547ae12033a4c994d2a820d8ba200630cd630b27fe5e09318eefec7782ef41c3
+oid sha256:8bd10531dde898da975ce3ed122b284a7dcd5af45fd8e5f0df97a0b96e2e49b1
 size 160400