Finished training.

README.md

@@ -23,7 +23,7 @@ model-index:
       args: irony
     metrics:
     - type: accuracy
-      value: 0.6293193717277487
+      value: 0.6408376963350786
       name: accuracy
 ---
 
@@ -34,7 +34,7 @@ should probably proofread and complete it, then remove this comment. -->
 
 This model is a fine-tuned version of [moghis/distilbert-base-uncased-finetuned-emotion](https://huggingface.co/moghis/distilbert-base-uncased-finetuned-emotion) on the tweet_eval dataset.
 It achieves the following results on the evaluation set:
-- accuracy: 0.6293
+- accuracy: 0.6408
 
 ## Model description
 
@@ -65,15 +65,15 @@ The following hyperparameters were used during training:
 
 | accuracy | train_loss | epoch |
 |:--------:|:----------:|:-----:|
-| 0.5236   | None       | 0     |
-| 0.5864   | 0.6928     | 0     |
-| 0.5885   | 0.6396     | 1     |
-| 0.6325   | 0.6038     | 2     |
-| 0.6461   | 0.5721     | 3     |
-| 0.6293   | 0.5499     | 4     |
-| 0.6251   | 0.5354     | 5     |
-| 0.6283   | 0.5097     | 6     |
-| 0.6293   | 0.5025     | 7     |
+| 0.4723   | None       | 0     |
+| 0.5874   | 0.6918     | 0     |
+| 0.6031   | 0.6420     | 1     |
+| 0.6283   | 0.6049     | 2     |
+| 0.6461   | 0.5723     | 3     |
+| 0.6314   | 0.5538     | 4     |
+| 0.6262   | 0.5363     | 5     |
+| 0.6440   | 0.5199     | 6     |
+| 0.6408   | 0.5056     | 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 sha256:2a25483e5a975649ece1a25862369dd82e17c82223dcc153c478c1a342297d6d
+oid sha256:af4790491a4300c87d394653d4bde226957a508001c500ff99218167f5c16b05
 size 2446056