Add SetFit ABSA model

README.md

@@ -6,15 +6,14 @@ tags:
 - text-classification
 - generated_from_setfit_trainer
 widget:
-- text: out because the screen was broken initially:never had a chance to try it out
-    because the screen was broken initially.
-- text: ' the backlit keyboard is a lie: the backlit keyboard is a lie.'
-- text: 118 gb of storage and 4 gb:without the added drive, 118 gb of storage and
-    4 gb of ram is more than adequate for basic computing
-- text: 4gb of ram and 64gb:4gb of ram and 64gb of storage is not enough for windows
-    10.
-- text: likely not enough memory or something seems:likely not enough memory or something
-    seems to me
+- text: has excellent battery life.:has excellent battery life.
+- text: '...then the screen went black &:was working fine although we didn''t really
+    use it that much...then the screen went black & nothing.'
+- text: is easy to carry, this is:other than this, if you need a basic laptop that
+    surfs the internet and is easy to carry, this is for you.
+- text: ' the  price:excellent fot  the  price'
+- text: it is fast and performs all:it is fast and performs all the basic functions
+    i need quickly.
 metrics:
 - accuracy
 pipeline_tag: text-classification
@@ -60,10 +59,10 @@ This model was trained within the context of a larger system for ABSA, which loo
 - **Blogpost:** [SetFit: Efficient Few-Shot Learning Without Prompts](https://huggingface.co/blog/setfit)
 
 ### Model Labels
-| Label    | Examples                                                                                                                                                                                                                                                                        |
-|:---------|:--------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|
-| negative | <ul><li>'not add more memory.:painfully slow, you cannot add more memory.'</li><li>'painfully slow, you can:painfully slow, you cannot add more memory.'</li><li>"keyboard doesn't light:keyboard doesn't light up. hard to see at night"</li></ul>                             |
-| positive | <ul><li>'the chip, ram, and memory:the chip, ram, and memory were the selling feature for me.'</li><li>'ram, and memory were the selling:the chip, ram, and memory were the selling feature for me.'</li><li>'very easy to carry.:works fast and very easy to carry.'</li></ul> |
+| Label    | Examples                                                                                                                                                                                                                                                                                                                |
+|:---------|:------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|
+| positive | <ul><li>'very lightweight.:very lightweight.'</li><li>'and easy to carry.:this computer is so light weight and easy to carry.'</li><li>"it's lightweight, the screen:it's lightweight, the screen is decently bright, and it'll go for hours without needing a charge"</li></ul>                                        |
+| negative | <ul><li>'me a black screen.:defective...wouldnt boot up, just gives me a black screen.'</li><li>'screen often blanks momentarily:screen often blanks momentarily and internet connection is spotty.'</li><li>'it but the screen stopped working after:loved it but the screen stopped working after 4 months'</li></ul> |
 
 ## Uses
 
@@ -118,12 +117,12 @@ preds = model("The food was great, but the venue is just way too busy.")
 ### Training Set Metrics
 | Training set | Min | Median  | Max |
 |:-------------|:----|:--------|:----|
-| Word count   | 5   | 16.1364 | 35  |
+| Word count   | 1   | 16.7714 | 42  |
 
 | Label    | Training Sample Count |
 |:---------|:----------------------|
-| negative | 73                    |
-| positive | 81                    |
+| negative | 64                    |
+| positive | 76                    |
 
 ### Training Hyperparameters
 - batch_size: (128, 128)
@@ -146,16 +145,14 @@ preds = model("The food was great, but the venue is just way too busy.")
 ### Training Results
 | Epoch  | Step | Training Loss | Validation Loss |
 |:------:|:----:|:-------------:|:---------------:|
-| 0.0105 | 1    | 0.2887        | -               |
-| 0.5263 | 50   | 0.1404        | 0.0018          |
-| 1.0526 | 100  | 0.0007        | 0.0004          |
-| 1.5789 | 150  | 0.0002        | 0.0003          |
-| 2.1053 | 200  | 0.0002        | 0.0003          |
-| 2.6316 | 250  | 0.0001        | 0.0002          |
-| 3.1579 | 300  | 0.0001        | 0.0002          |
-| 3.6842 | 350  | 0.0001        | 0.0002          |
-| 4.2105 | 400  | 0.0001        | 0.0002          |
-| 4.7368 | 450  | 0.0001        | 0.0002          |
+| 0.0127 | 1    | 0.3141        | -               |
+| 0.6329 | 50   | 0.1338        | 0.0015          |
+| 1.2658 | 100  | 0.0006        | 0.0003          |
+| 1.8987 | 150  | 0.0002        | 0.0003          |
+| 2.5316 | 200  | 0.0002        | 0.0002          |
+| 3.1646 | 250  | 0.0001        | 0.0002          |
+| 3.7975 | 300  | 0.0001        | 0.0002          |
+| 4.4304 | 350  | 0.0001        | 0.0002          |
 
 ### Framework Versions
 - Python: 3.11.12

config_setfit.json

@@ -1,9 +1,9 @@
 {
+  "normalize_embeddings": false,
   "labels": [
     "negative",
     "positive"
   ],
   "span_context": 3,
-  "normalize_embeddings": false,
   "spacy_model": "en_core_web_sm"
 }

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:485c8f3342d25419800431924b3a0e6956451aa28398a84a08856d0bf90a572a
+oid sha256:a2b8de9c7e208a3a7522dc9d1e4290fda79fd3d4ebb81981aeeb73215dbd7044
 size 437967672

model_head.pkl

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:40e97e2e280ec2a0930d6bb61da89ffcab46c0e831db7a3f2254b58cff2f8178
+oid sha256:835fb1477be04db03d83d4c6b041ff071531e9e1f3b7cd65320d49b96e033d49
 size 7055