Finished training.

README.md

@@ -23,7 +23,7 @@ model-index:
       args: default
     metrics:
     - type: accuracy
-      value: 0.9402631578947368
+      value: 0.940921052631579
       name: accuracy
 ---
 
@@ -34,7 +34,7 @@ should probably proofread and complete it, then remove this comment. -->
 
 This model is a fine-tuned version of [aXhyra/presentation_sentiment_1234567](https://huggingface.co/aXhyra/presentation_sentiment_1234567) on the ag_news dataset.
 It achieves the following results on the evaluation set:
-- accuracy: 0.9403
+- accuracy: 0.9409
 
 ## Model description
 
@@ -65,11 +65,11 @@ The following hyperparameters were used during training:
 
 | accuracy | train_loss | epoch |
 |:--------:|:----------:|:-----:|
-| 0.2379   | None       | 0     |
-| 0.9259   | 0.2633     | 0     |
-| 0.9299   | 0.2003     | 1     |
-| 0.9382   | 0.1767     | 2     |
-| 0.9403   | 0.1601     | 3     |
+| 0.2316   | None       | 0     |
+| 0.9238   | 0.2605     | 0     |
+| 0.9334   | 0.1991     | 1     |
+| 0.9374   | 0.1759     | 2     |
+| 0.9409   | 0.1597     | 3     |
 
 
 ### Framework versions

adapter_config.json

@@ -19,8 +19,8 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "q_lin",
-    "v_lin"
+    "v_lin",
+    "q_lin"
   ],
   "task_type": "SEQ_CLS",
   "use_rslora": false

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:045a099fbf3346c8688c9d531b0eaa3306d24109b4c717e24bcf51d068c2e1b5
+oid sha256:0e77003354a3f853a80bfc6a079b7c9d1dc460e265523cefca4520db101fcd5c
 size 2452208