Finished training.

README.md

@@ -22,7 +22,7 @@ model-index:
       args: default
     metrics:
     - type: accuracy
-      value: 0.9292105263157895
+      value: 0.9327631578947368
       name: accuracy
 ---
 
@@ -33,7 +33,7 @@ should probably proofread and complete it, then remove this comment. -->
 
 This model is a fine-tuned version of [cambridgeltl/guardian_news_distilbert-base-uncased](https://huggingface.co/cambridgeltl/guardian_news_distilbert-base-uncased) on the ag_news dataset.
 It achieves the following results on the evaluation set:
-- accuracy: 0.9292
+- accuracy: 0.9328
 
 ## Model description
 
@@ -64,11 +64,11 @@ The following hyperparameters were used during training:
 
 | accuracy | train_loss | epoch |
 |:--------:|:----------:|:-----:|
-| 0.2217   | None       | 0     |
-| 0.9161   | 0.3026     | 0     |
-| 0.9237   | 0.2310     | 1     |
-| 0.9274   | 0.2043     | 2     |
-| 0.9292   | 0.1898     | 3     |
+| 0.2264   | None       | 0     |
+| 0.9164   | 0.3023     | 0     |
+| 0.9237   | 0.2296     | 1     |
+| 0.9296   | 0.2051     | 2     |
+| 0.9328   | 0.1905     | 3     |
 
 
 ### Framework versions

adapter_config.json

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

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1f88b317195ada0cfbaa297c6450f7163a777c8b325491c0a64cb3523d9b5a13
+oid sha256:057f33d00cec388d729117215adc402724f8320531a0287a44569757bd31529f
 size 2452208