Finished training.

README.md

@@ -23,7 +23,7 @@ model-index:
       args: default
     metrics:
     - type: accuracy
-      value: 0.9338157894736843
+      value: 0.9331578947368421
       name: accuracy
 ---
 
@@ -34,7 +34,7 @@ should probably proofread and complete it, then remove this comment. -->
 
 This model is a fine-tuned version of [vesteinn/XLMR-ENIS-finetuned-cola](https://huggingface.co/vesteinn/XLMR-ENIS-finetuned-cola) on the ag_news dataset.
 It achieves the following results on the evaluation set:
-- accuracy: 0.9338
+- accuracy: 0.9332
 
 ## Model description
 
@@ -65,11 +65,11 @@ The following hyperparameters were used during training:
 
 | accuracy | train_loss | epoch |
 |:--------:|:----------:|:-----:|
-| 0.2561   | None       | 0     |
-| 0.9184   | 0.3061     | 0     |
-| 0.9261   | 0.2359     | 1     |
-| 0.9343   | 0.2114     | 2     |
-| 0.9338   | 0.1985     | 3     |
+| 0.2057   | None       | 0     |
+| 0.9182   | 0.3066     | 0     |
+| 0.9261   | 0.2382     | 1     |
+| 0.9326   | 0.2125     | 2     |
+| 0.9332   | 0.1993     | 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:c4f62a7bf171f5615fcf9a66afc005f4bcdcca678e4c61993d46f1a4a7741cef
+oid sha256:8bc106c45a286c59383e109377e38faf8bf12f9f5e0601b6a1fc195a2fc3c015
 size 2529464