Add SetFit model

README.md

@@ -31,7 +31,7 @@ model-index:
       split: test
     metrics:
     - type: accuracy
-      value: 0.7492537313432835
+      value: 0.6701492537313433
       name: Accuracy
 ---
 
@@ -63,17 +63,17 @@ 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                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                            |
-|:------|:------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|
-| 1     | <ul><li>'I would have liked to have had some photos with this ebook, just for breaking up the monotony of the print.'</li><li>'Or if the copy was just the result of scanning the book badly ...thanks to amazon I got a refund but this edition should be taken down!...I am not sure about the good reviews, but Spanish is my first lanngauge and this is a terrible edition of a great book!'</li><li>'Must read but I wished the second book continued their story and not switch to another brother in his family!'</li></ul> |
-| 0     | <ul><li>'One problem: tried without success to change ear tip from large to small .'</li><li>"I would recommend this book to people that miss Breaking Bad and want to hear a fresh take on Jesse's life."</li><li>"How can I review on a product that I haven't gotten."</li></ul>                                                                                                                                                                                                                                                 |
+| Label | Examples                                                                                                                                                                                                                                                                                                                 |
+|:------|:-------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|
+| 1     | <ul><li>"If harder wood would have been used this would not be an issue, and it's the jig's biggest design flaw IMO...very disappointing."</li><li>'I felt the books could have been condensed into two or even one.'</li><li>'Should have an option for a big bigger though.'</li></ul>                                 |
+| 0     | <ul><li>'But all in all they provide a box within which I can place my books on a shelf in the garage without worry.'</li><li>'The only drawback for me is that there should be a slightly larger earbud with these.'</li><li>'I just wanted something to protect my chair while my furry friend sat with me!'</li></ul> |
 
 ## Evaluation
 
 ### Metrics
 | Label   | Accuracy |
 |:--------|:---------|
-| **all** | 0.7493   |
+| **all** | 0.6701   |
 
 ## Uses
 
@@ -125,7 +125,7 @@ preds = model("I wished it had the output on back instead of on the side.")
 ### Training Set Metrics
 | Training set | Min | Median | Max |
 |:-------------|:----|:-------|:----|
-| Word count   | 9   | 22.75  | 50  |
+| Word count   | 9   | 16.375 | 26  |
 
 | Label | Training Sample Count |
 |:------|:----------------------|
@@ -153,8 +153,8 @@ preds = model("I wished it had the output on back instead of on the side.")
 ### Training Results
 | Epoch  | Step | Training Loss | Validation Loss |
 |:------:|:----:|:-------------:|:---------------:|
-| 0.0125 | 1    | 0.2386        | -               |
-| 0.625  | 50   | 0.0033        | -               |
+| 0.0125 | 1    | 0.208         | -               |
+| 0.625  | 50   | 0.0007        | -               |
 
 ### Framework Versions
 - Python: 3.8.10

config_setfit.json

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

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7bcb7891170b811263c8daa48859b5428a04ba601706a38f566a7d0383ff62e4
+oid sha256:39977b457ab9734328e71d775cbd68093fdcf44581eb29ef1da3ababba16dbba
 size 437967672

model_head.pkl

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:78cc3441edf70b63e334714ec1ebee296af3ef279a1c062baa5c9e701d51426f
+oid sha256:62ad1a0497d32fa94d82eccce5ee0c4df59c1410f9cca4742e3f752e1ab0e95c
 size 6991