Finished training.

README.md

@@ -23,7 +23,7 @@ model-index:
       args: default
     metrics:
     - type: accuracy
-      value: 0.8907894736842106
+      value: 0.8935526315789474
       name: accuracy
 ---
 
@@ -34,7 +34,7 @@ should probably proofread and complete it, then remove this comment. -->
 
 This model is a fine-tuned version of [IMSyPP/hate_speech_it](https://huggingface.co/IMSyPP/hate_speech_it) on the ag_news dataset.
 It achieves the following results on the evaluation set:
-- accuracy: 0.8908
+- accuracy: 0.8936
 
 ## Model description
 
@@ -66,10 +66,10 @@ The following hyperparameters were used during training:
 | accuracy | train_loss | epoch |
 |:--------:|:----------:|:-----:|
 | 0.25     | None       | 0     |
-| 0.8776   | 0.4575     | 0     |
-| 0.8821   | 0.3458     | 1     |
-| 0.8913   | 0.3150     | 2     |
-| 0.8908   | 0.2993     | 3     |
+| 0.8780   | 0.4558     | 0     |
+| 0.8858   | 0.3405     | 1     |
+| 0.8928   | 0.3146     | 2     |
+| 0.8936   | 0.2976     | 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 sha256:6139a582b98efd76731a7dac74a9bee999a073ab24f0bdd6b49a91cfdc8bd4c4
+oid sha256:86c8dbda098281e27ff249bc56aa77a25845bdc388a2fd0a42b3623837af7b23
 size 166552