TransferGraph
/

moshew_bert-mini-sst2-distilled-finetuned-lora-tweet_eval_irony

Text Classification

Eval Results (legacy)

Model card Files Files and versions

hilco commited on Feb 29, 2024

Commit

6864d4c

·

verified ·

1 Parent(s): 28e2169

Finished training.

Files changed (3) hide show

README.md +10 -10
adapter_config.json +2 -2
adapter_model.safetensors +1 -1

README.md CHANGED Viewed

@@ -22,7 +22,7 @@ model-index:
       args: irony
     metrics:
     - type: accuracy
-      value: 0.6230366492146597
       name: accuracy
 ---
@@ -33,7 +33,7 @@ should probably proofread and complete it, then remove this comment. -->
 This model is a fine-tuned version of [moshew/bert-mini-sst2-distilled](https://huggingface.co/moshew/bert-mini-sst2-distilled) on the tweet_eval dataset.
 It achieves the following results on the evaluation set:
-- accuracy: 0.6230
 ## Model description
@@ -65,14 +65,14 @@ The following hyperparameters were used during training:
 | accuracy | train_loss | epoch |
 |:--------:|:----------:|:-----:|
 | 0.5487   | None       | 0     |
-| 0.5738   | 0.6838     | 0     |
-| 0.6262   | 0.6699     | 1     |
-| 0.6251   | 0.6563     | 2     |
-| 0.6199   | 0.6446     | 3     |
-| 0.6188   | 0.6366     | 4     |
-| 0.6293   | 0.6367     | 5     |
-| 0.6209   | 0.6316     | 6     |
-| 0.6230   | 0.6324     | 7     |
 ### Framework versions

       args: irony
     metrics:
     - type: accuracy
+      value: 0.6115183246073298
       name: accuracy
 ---
 This model is a fine-tuned version of [moshew/bert-mini-sst2-distilled](https://huggingface.co/moshew/bert-mini-sst2-distilled) on the tweet_eval dataset.
 It achieves the following results on the evaluation set:
+- accuracy: 0.6115
 ## Model description
 | accuracy | train_loss | epoch |
 |:--------:|:----------:|:-----:|
 | 0.5487   | None       | 0     |
+| 0.5707   | 0.6844     | 0     |
+| 0.6199   | 0.6719     | 1     |
+| 0.6272   | 0.6578     | 2     |
+| 0.6251   | 0.6474     | 3     |
+| 0.6073   | 0.6398     | 4     |
+| 0.6199   | 0.6383     | 5     |
+| 0.6115   | 0.6333     | 6     |
+| 0.6115   | 0.6347     | 7     |
 ### Framework versions

adapter_config.json CHANGED Viewed

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

   "rank_pattern": {},
   "revision": null,
   "target_modules": [
+    "value",
+    "query"
   ],
   "task_type": "SEQ_CLS",
   "use_rslora": false

adapter_model.safetensors CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:74de70c40189d7d77cd84c8fb121261e9ea50e421f37fae846dd040cfd3526e1
 size 20824

 version https://git-lfs.github.com/spec/v1
+oid sha256:22b128bece8e074593df8b28d0db57e269a37ea9ccc10ae7984c7fff566e918d
 size 20824