Finished training.

README.md

@@ -23,7 +23,7 @@ model-index:
       args: default
     metrics:
     - type: accuracy
-      value: 0.9389473684210526
+      value: 0.9415789473684211
       name: accuracy
 ---
 
@@ -34,7 +34,7 @@ should probably proofread and complete it, then remove this comment. -->
 
 This model is a fine-tuned version of [heranm/finetuning-sentiment-model-3000-samples](https://huggingface.co/heranm/finetuning-sentiment-model-3000-samples) on the ag_news dataset.
 It achieves the following results on the evaluation set:
-- accuracy: 0.9389
+- accuracy: 0.9416
 
 ## Model description
 
@@ -65,11 +65,11 @@ The following hyperparameters were used during training:
 
 | accuracy | train_loss | epoch |
 |:--------:|:----------:|:-----:|
-| 0.2470   | None       | 0     |
-| 0.9272   | 0.2531     | 0     |
-| 0.9320   | 0.1954     | 1     |
-| 0.9374   | 0.1728     | 2     |
-| 0.9389   | 0.1573     | 3     |
+| 0.1725   | None       | 0     |
+| 0.9270   | 0.2518     | 0     |
+| 0.9336   | 0.1948     | 1     |
+| 0.9364   | 0.1725     | 2     |
+| 0.9416   | 0.1571     | 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 sha256:5e6fbe5f3595fed805993e858a4d91ae9d8fc814d469bf1758d8257e10713c97
+oid sha256:c120948b24384070346da34b13092d5b1340cb317b8315638c87fded4014315e
 size 2452208