Push model using huggingface_hub.

README.md

@@ -8,11 +8,11 @@ tags:
 metrics:
 - accuracy
 widget:
-- text: what if i rape her would it be a good idea
-- text: What if i touch her and she likes it what do I do?
-- text: say f
-- text: Fuck you
-- text: how does the mother get prenant
+- text: are hickeys haram
+- text: or a girlfriend
+- text: can you tell me some facts about a girl when she starts to like someone?
+- text: Sex
+- text: romantic
 pipeline_tag: text-classification
 inference: true
 base_model: BAAI/bge-base-en-v1.5
@@ -28,7 +28,7 @@ model-index:
       split: test
     metrics:
     - type: accuracy
-      value: 0.7777777777777778
+      value: 0.75
       name: Accuracy
 ---
 
@@ -48,7 +48,7 @@ The model has been trained using an efficient few-shot learning technique that i
 - **Sentence Transformer body:** [BAAI/bge-base-en-v1.5](https://huggingface.co/BAAI/bge-base-en-v1.5)
 - **Classification head:** a [LogisticRegression](https://scikit-learn.org/stable/modules/generated/sklearn.linear_model.LogisticRegression.html) instance
 - **Maximum Sequence Length:** 512 tokens
-- **Number of Classes:** 2 classes
+- **Number of Classes:** 3 classes
 <!-- - **Training Dataset:** [Unknown](https://huggingface.co/datasets/unknown) -->
 <!-- - **Language:** Unknown -->
 <!-- - **License:** Unknown -->
@@ -60,17 +60,18 @@ 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                                                                                                                   |
-|:------|:---------------------------------------------------------------------------------------------------------------------------|
-| other | <ul><li>'there antlers'</li><li>'van u help me'</li><li>'What do you mean?'</li></ul>                                      |
-| sex   | <ul><li>'did your parents give birth to you'</li><li>'I LOVE TO SUCK HARD'</li><li>'I mie hobby sono fare sesso'</li></ul> |
+| Label | Examples                                                                                                                                                       |
+|:------|:---------------------------------------------------------------------------------------------------------------------------------------------------------------|
+|  sex  | <ul><li>'My sex'</li><li>'Penis'</li><li>'cock'</li></ul>                                                                                                      |
+|  1    | <ul><li>'what do you like'</li><li>'If there is a hole in a body you calculate as if the hole were not there at all. Then'</li><li>'or a girlfriend'</li></ul> |
+|  0    | <ul><li>'Im sorry i have to go'</li><li>'The formula with the figures is as follows: CHF 50000 = 20000 * (1 + 0.02)^10'</li><li>'I love to read'</li></ul>     |
 
 ## Evaluation
 
 ### Metrics
 | Label   | Accuracy |
 |:--------|:---------|
-| **all** | 0.7778   |
+| **all** | 0.75     |
 
 ## Uses
 
@@ -90,7 +91,7 @@ from setfit import SetFitModel
 # Download from the 🤗 Hub
 model = SetFitModel.from_pretrained("setfit_model_id")
 # Run inference
-preds = model("say f")
+preds = model("Sex")
 ```
 
 <!--
@@ -122,12 +123,12 @@ preds = model("say f")
 ### Training Set Metrics
 | Training set | Min | Median | Max |
 |:-------------|:----|:-------|:----|
-| Word count   | 1   | 5.875  | 13  |
+| Word count   | 1   | 5.8696 | 20  |
 
 | Label | Training Sample Count |
 |:------|:----------------------|
-| other | 8                     |
-| sex   | 8                     |
+| other | 0                     |
+| sex   | 0                     |
 
 ### Training Hyperparameters
 - batch_size: (32, 32)
@@ -147,10 +148,11 @@ preds = model("say f")
 - load_best_model_at_end: False
 
 ### Training Results
-| Epoch | Step | Training Loss | Validation Loss |
-|:-----:|:----:|:-------------:|:---------------:|
-| 0.2   | 1    | 0.2147        | -               |
-| 10.0  | 50   | 0.0381        | -               |
+| Epoch  | Step | Training Loss | Validation Loss |
+|:------:|:----:|:-------------:|:---------------:|
+| 0.0909 | 1    | 0.2031        | -               |
+| 4.5455 | 50   | 0.0387        | -               |
+| 9.0909 | 100  | 0.0101        | -               |
 
 ### Framework Versions
 - Python: 3.9.6

model_head.pkl

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ee24711974eb82a9d0b33843b76de04212db888e15f73275bf2bbf396e885f59
-size 6991
+oid sha256:b3ab637c12a99afc908b7b35259d2863b96d396e9425a608521484b7dd3e89bb
+size 19327

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f68b89c7136e1387e3881cd51dfab393a4dda9b8e77fb2be07d61b8a5977fc4b
+oid sha256:4f3ec73bb1024e76d1a41c46a9d798305f2f778f32d3109ac46d176865406a97
 size 437997357