Add SetFit ABSA model

README.md

@@ -1,4 +1,6 @@
 ---
+language: en
+license: apache-2.0
 library_name: setfit
 tags:
 - setfit
@@ -6,33 +8,36 @@ tags:
 - sentence-transformers
 - text-classification
 - generated_from_setfit_trainer
+datasets:
+- tomaarsen/setfit-absa-semeval-restaurants
 metrics:
 - accuracy
 widget:
-- text: and very good prices.:Very good service and very good prices.
-- text: 'very particular about sushi and were both:We are very particular about sushi
-    and were both please with every choice which included: ceviche mix (special),
-    crab dumplings, assorted sashimi, sushi and rolls, two types of sake, and the
-    banana tempura.'
-- text: good and the waiters are friendly.:It's really also the service, is good and
-    the waiters are friendly.
-- text: Our food was great too:Our food was great too!
-- text: The food was pretty good:The food was pretty good, but a little flavorless
-    and the portions very small, including dessert.
+- text: (both in quantity AND quality):The Prix Fixe menu is worth every penny and
+    you get more than enough (both in quantity AND quality).
+- text: over 100 different beers to offer thier:The have over 100 different beers
+    to offer thier guest so that made my husband very happy and the food was delicious,
+    if I must recommend a dish it must be the pumkin tortelini.
+- text: back with a plate of dumplings.:Get your food to go, find a bench, and kick
+    back with a plate of dumplings.
+- text: the udon was soy sauce and water.:The soup for the udon was soy sauce and
+    water.
+- text: times for the beef cubes - they're:i've been back to nha trang literally a
+    hundred times for the beef cubes - they're that good.
 pipeline_tag: text-classification
 inference: false
 co2_eq_emissions:
-  emissions: 5.960609724371976
+  emissions: 10.256079923743641
   source: codecarbon
   training_type: fine-tuning
   on_cloud: false
   cpu_model: 13th Gen Intel(R) Core(TM) i7-13700K
   ram_total_size: 31.777088165283203
-  hours_used: 0.073
+  hours_used: 0.117
   hardware_used: 1 x NVIDIA GeForce RTX 3090
 base_model: BAAI/bge-small-en-v1.5
 model-index:
-- name: SetFit Polarity Model with BAAI/bge-small-en-v1.5
+- name: SetFit Polarity Model with BAAI/bge-small-en-v1.5 on SemEval 2014 Task 4 (Restaurants)
   results:
   - task:
       type: text-classification
@@ -40,16 +45,16 @@ model-index:
     dataset:
       name: SemEval 2014 Task 4 (Restaurants)
       type: tomaarsen/setfit-absa-semeval-restaurants
-      split: train[384:]
+      split: test
     metrics:
     - type: accuracy
-      value: 0.7260223048327138
+      value: 0.7467434110875493
       name: Accuracy
 ---
 
-# SetFit Polarity Model with BAAI/bge-small-en-v1.5
+# SetFit Polarity Model with BAAI/bge-small-en-v1.5 on SemEval 2014 Task 4 (Restaurants)
 
-This is a [SetFit](https://github.com/huggingface/setfit) model that can be used for Aspect Based Sentiment Analysis (ABSA). This SetFit model uses [BAAI/bge-small-en-v1.5](https://huggingface.co/BAAI/bge-small-en-v1.5) as the Sentence Transformer embedding model. A [LogisticRegression](https://scikit-learn.org/stable/modules/generated/sklearn.linear_model.LogisticRegression.html) instance is used for classification. In particular, this model is in charge of classifying aspect polarities.
+This is a [SetFit](https://github.com/huggingface/setfit) model trained on the [SemEval 2014 Task 4 (Restaurants)](https://huggingface.co/datasets/tomaarsen/setfit-absa-semeval-restaurants) dataset that can be used for Aspect Based Sentiment Analysis (ABSA). This SetFit model uses [BAAI/bge-small-en-v1.5](https://huggingface.co/BAAI/bge-small-en-v1.5) as the Sentence Transformer embedding model. A [LogisticRegression](https://scikit-learn.org/stable/modules/generated/sklearn.linear_model.LogisticRegression.html) instance is used for classification. In particular, this model is in charge of classifying aspect polarities.
 
 The model has been trained using an efficient few-shot learning technique that involves:
 
@@ -72,9 +77,9 @@ This model was trained within the context of a larger system for ABSA, which loo
 - **SetFitABSA Polarity Model:** [tomaarsen/setfit-absa-bge-small-en-v1.5-restaurants-polarity](https://huggingface.co/tomaarsen/setfit-absa-bge-small-en-v1.5-restaurants-polarity)
 - **Maximum Sequence Length:** 512 tokens
 - **Number of Classes:** 4 classes
-<!-- - **Training Dataset:** [Unknown](https://huggingface.co/datasets/unknown) -->
-<!-- - **Language:** Unknown -->
-<!-- - **License:** Unknown -->
+- **Training Dataset:** [SemEval 2014 Task 4 (Restaurants)](https://huggingface.co/datasets/tomaarsen/setfit-absa-semeval-restaurants)
+- **Language:** en
+- **License:** apache-2.0
 
 ### Model Sources
 
@@ -95,7 +100,7 @@ This model was trained within the context of a larger system for ABSA, which loo
 ### Metrics
 | Label   | Accuracy |
 |:--------|:---------|
-| **all** | 0.7260   |
+| **all** | 0.7467   |
 
 ## Uses
 
@@ -150,14 +155,14 @@ preds = model("The food was great, but the venue is just way too busy.")
 ### Training Set Metrics
 | Training set | Min | Median  | Max |
 |:-------------|:----|:--------|:----|
-| Word count   | 6   | 22.4902 | 51  |
+| Word count   | 6   | 22.4980 | 51  |
 
 | Label    | Training Sample Count |
 |:---------|:----------------------|
 | conflict | 6                     |
-| negative | 37                    |
-| neutral  | 30                    |
-| positive | 131                   |
+| negative | 43                    |
+| neutral  | 36                    |
+| positive | 170                   |
 
 ### Training Hyperparameters
 - batch_size: (256, 256)
@@ -178,21 +183,25 @@ preds = model("The food was great, but the venue is just way too busy.")
 ### Training Results
 | Epoch      | Step    | Training Loss | Validation Loss |
 |:----------:|:-------:|:-------------:|:---------------:|
-| 0.0115     | 1       | 0.2334        | -               |
-| 0.5747     | 50      | 0.2242        | -               |
-| **1.1494** | **100** | **0.1609**    | **0.1859**      |
-| 1.7241     | 150     | 0.0932        | -               |
-| 2.2989     | 200     | 0.0302        | 0.2054          |
-| 2.8736     | 250     | 0.0206        | -               |
-| 3.4483     | 300     | 0.0071        | 0.2427          |
-| 4.0230     | 350     | 0.003         | -               |
-| 4.5977     | 400     | 0.0025        | 0.2654          |
+| 0.0078     | 1       | 0.2411        | -               |
+| 0.3876     | 50      | 0.2293        | -               |
+| 0.7752     | 100     | 0.185         | 0.1885          |
+| 1.1628     | 150     | 0.0962        | -               |
+| **1.5504** | **200** | **0.0299**    | **0.1782**      |
+| 1.9380     | 250     | 0.0306        | -               |
+| 2.3256     | 300     | 0.0136        | 0.2029          |
+| 2.7132     | 350     | 0.0065        | -               |
+| 3.1008     | 400     | 0.0024        | 0.229           |
+| 3.4884     | 450     | 0.0014        | -               |
+| 3.8760     | 500     | 0.0016        | 0.2434          |
+| 4.2636     | 550     | 0.001         | -               |
+| 4.6512     | 600     | 0.001         | 0.2483          |
 
 * The bold row denotes the saved checkpoint.
 ### Environmental Impact
 Carbon emissions were measured using [CodeCarbon](https://github.com/mlco2/codecarbon).
-- **Carbon Emitted**: 0.006 kg of CO2
-- **Hours Used**: 0.073 hours
+- **Carbon Emitted**: 0.010 kg of CO2
+- **Hours Used**: 0.117 hours
 
 ### Training Hardware
 - **On Cloud**: No

config.json

@@ -1,5 +1,5 @@
 {
-  "_name_or_path": "models\\step_100\\",
+  "_name_or_path": "models\\step_200\\",
   "architectures": [
     "BertModel"
   ],

config_setfit.json

@@ -1,5 +1,5 @@
 {
+  "normalize_embeddings": false,
   "labels": null,
-  "span_context": 3,
-  "normalize_embeddings": false
+  "span_context": 3
 }

model_head.pkl

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:328d505003cc0ab45d534a2f8bf5051f278c35e282e4291b394cda9ae107fe04
+oid sha256:1b437ed4ffbecdadb959aa70509ffe3bf675317baa9912d546f572812fb554f6
 size 13271

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0e8f7b15a77ed76e6167761443ddbb79a90ef913589f55a2f5afa90d3e61a670
+oid sha256:8504f13d57651bb139a3c2c2d7103cdbb18ef68cd7d1af06e755aa8a28d38cd5
 size 133511213