Finished training.

README.md

@@ -23,7 +23,7 @@ model-index:
       args: irony
     metrics:
     - type: accuracy
-      value: 0.6785340314136126
+      value: 0.6701570680628273
       name: accuracy
 ---
 
@@ -34,7 +34,7 @@ should probably proofread and complete it, then remove this comment. -->
 
 This model is a fine-tuned version of [markt23917/finetuning-sentiment-model-3000-samples](https://huggingface.co/markt23917/finetuning-sentiment-model-3000-samples) on the tweet_eval dataset.
 It achieves the following results on the evaluation set:
-- accuracy: 0.6785
+- accuracy: 0.6702
 
 ## Model description
 
@@ -66,14 +66,14 @@ The following hyperparameters were used during training:
 | accuracy | train_loss | epoch |
 |:--------:|:----------:|:-----:|
 | 0.5152   | None       | 0     |
-| 0.6209   | 0.6689     | 0     |
-| 0.6199   | 0.6225     | 1     |
-| 0.6649   | 0.5806     | 2     |
-| 0.6639   | 0.5615     | 3     |
-| 0.6660   | 0.5418     | 4     |
-| 0.6461   | 0.5177     | 5     |
-| 0.6733   | 0.5047     | 6     |
-| 0.6785   | 0.4949     | 7     |
+| 0.6157   | 0.6663     | 0     |
+| 0.6272   | 0.6178     | 1     |
+| 0.6555   | 0.5885     | 2     |
+| 0.6733   | 0.5579     | 3     |
+| 0.6733   | 0.5368     | 4     |
+| 0.6492   | 0.5197     | 5     |
+| 0.6691   | 0.5042     | 6     |
+| 0.6702   | 0.4924     | 7     |
 
 
 ### 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 sha256:586e730279d5dece93358fb61a44a513007d7cc101a518be31852028f0cf496d
+oid sha256:aed88c449981613c5c67463cffb2023bac595b164c39177d1c9553ccdae1f661
 size 2446056