Finished training.

README.md

@@ -23,7 +23,7 @@ model-index:
       args: irony
     metrics:
     - type: accuracy
-      value: 0.6816753926701571
+      value: 0.6795811518324607
       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-large-uncased](https://huggingface.co/bert-large-uncased) on the tweet_eval dataset.
 It achieves the following results on the evaluation set:
-- accuracy: 0.6817
+- accuracy: 0.6796
 
 ## Model description
 
@@ -65,15 +65,15 @@ The following hyperparameters were used during training:
 
 | accuracy | train_loss | epoch |
 |:--------:|:----------:|:-----:|
-| 0.5298   | None       | 0     |
-| 0.5780   | 0.7258     | 0     |
-| 0.6      | 0.6816     | 1     |
-| 0.6377   | 0.6598     | 2     |
-| 0.6597   | 0.6146     | 3     |
-| 0.6712   | 0.5971     | 4     |
-| 0.6586   | 0.5722     | 5     |
-| 0.6796   | 0.5649     | 6     |
-| 0.6817   | 0.5577     | 7     |
+| 0.5246   | None       | 0     |
+| 0.5623   | 0.7215     | 0     |
+| 0.6126   | 0.6870     | 1     |
+| 0.6241   | 0.6593     | 2     |
+| 0.6461   | 0.6275     | 3     |
+| 0.6628   | 0.6105     | 4     |
+| 0.6660   | 0.5844     | 5     |
+| 0.6796   | 0.5745     | 6     |
+| 0.6796   | 0.5646     | 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:c0e5e570ad664e3181294cbaec21c38dc5a6d949d54cf08ed760288d31be397c
+oid sha256:c7cbc561f7b5df2a4ee9d3ecc33e6daf75e2fc9c61a55973d96b77b5e7167160
 size 415000