Add SetFit model

README.md

@@ -8,11 +8,11 @@ tags:
 metrics:
 - accuracy
 widget:
-- text: WackoJaco
-- text: ' mds - BlockLayoutThreeColumnSmallWithMpuAndVizAd.html '
-- text: ' Riko Miyase in Vol. 251 '
-- text: 2 Easy Steps
-- text: / 0:30
+- text: 6 months ago
+- text: / 0:00
+- text: Advertisement
+- text: Editing a saved reply
+- text: User-Sync
 pipeline_tag: text-classification
 inference: true
 base_model: sentence-transformers/paraphrase-mpnet-base-v2
@@ -28,7 +28,7 @@ model-index:
       split: test
     metrics:
     - type: accuracy
-      value: 0.8823529411764706
+      value: 0.5882352941176471
       name: Accuracy
 ---
 
@@ -60,17 +60,17 @@ The model has been trained using an efficient few-shot learning technique that i
 - **Blogpost:** [SetFit: Efficient Few-Shot Learning Without Prompts](https://huggingface.co/blog/setfit)
 
 ### Model Labels
-| Label | Examples                                                                                                                                                                                                                                                          |
-|:------|:------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|
-| True  | <ul><li>'Sponsored'</li><li>'Variety.com'</li><li>'LIV Golf’s Battle for World Ranking Points Fails'</li></ul>                                                                                                                                                    |
-| False | <ul><li>' - Decorate your avatar with premium frames. All existing frames that have already been released will remain free. We will continue to add more premium frames in the future!'</li><li>'Sint Maarten (Dutch part)'</li><li>'History Education'</li></ul> |
+| Label | Examples                                                                                                               |
+|:------|:-----------------------------------------------------------------------------------------------------------------------|
+| False | <ul><li>'mmmmmmmmmmlli'</li><li>'Middle-Earth: Shadow of...'</li><li>'Intel Core i7-4790 (Desktop) 3.60 GHz'</li></ul> |
+| True  | <ul><li>'Wall Street Eyes Nikki Haley as Trump Spoiler'</li><li>' Google Tag Manager '</li><li>'/ 0:12'</li></ul>      |
 
 ## Evaluation
 
 ### Metrics
 | Label   | Accuracy |
 |:--------|:---------|
-| **all** | 0.8824   |
+| **all** | 0.5882   |
 
 ## Uses
 
@@ -90,7 +90,7 @@ from setfit import SetFitModel
 # Download from the 🤗 Hub
 model = SetFitModel.from_pretrained("setfit_model_id")
 # Run inference
-preds = model("/ 0:30")
+preds = model("/ 0:00")
 ```
 
 <!--
@@ -122,12 +122,12 @@ preds = model("/ 0:30")
 ### Training Set Metrics
 | Training set | Min | Median | Max |
 |:-------------|:----|:-------|:----|
-| Word count   | 1   | 5.6418 | 59  |
+| Word count   | 1   | 5.2985 | 59  |
 
 | Label | Training Sample Count |
 |:------|:----------------------|
-| False | 28                    |
-| True  | 39                    |
+| False | 31                    |
+| True  | 36                    |
 
 ### Training Hyperparameters
 - batch_size: (16, 16)
@@ -150,10 +150,10 @@ preds = model("/ 0:30")
 ### Training Results
 | Epoch  | Step | Training Loss | Validation Loss |
 |:------:|:----:|:-------------:|:---------------:|
-| 0.0060 | 1    | 0.332         | -               |
-| 0.2976 | 50   | 0.1734        | -               |
+| 0.0060 | 1    | 0.4128        | -               |
+| 0.2976 | 50   | 0.1656        | -               |
 | 0.5952 | 100  | 0.0051        | -               |
-| 0.8929 | 150  | 0.004         | -               |
+| 0.8929 | 150  | 0.003         | -               |
 
 ### Framework Versions
 - Python: 3.11.0

config_setfit.json

@@ -1,4 +1,4 @@
 {
-  "labels": null,
-  "normalize_embeddings": false
+  "normalize_embeddings": false,
+  "labels": null
 }

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d939c5e4f98b84d0cbdb49370dca5a4e0c1709179f8aeed11d7ba9878c20fcb0
+oid sha256:e690fa2f3a3eb1af3c1034a232ad7ae6b88220f48f5bb2c531caf2700e94f77e
 size 437967672

model_head.pkl

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:42d90357a426dcb6849f5d362222849bc071ff7c04b002ad89c541ba6ac5826c
+oid sha256:9cebd294c4ca0c4ea8b633dac1f631bddbaec619d472af66fe08bfc9c77d1a70
 size 6991