Add SetFit ABSA model

README.md

@@ -6,20 +6,15 @@ tags:
 - text-classification
 - generated_from_setfit_trainer
 widget:
-- text: food:What is even better, is that the prices are very affordable as well,
-    and the food is really good.
-- text: 'cuisine:An oasis of refinement:  Food, though somewhat uneven, often reaches
-    the pinnacles of new American fine cuisine - chef''s passion (and kitchen''s precise
-    execution) is most evident in the fish dishes and soups.'
-- text: check:Had we been stalling I could understand where they were coming from,
-    but we had been there less than an hour and they hadn't even brought us a check
-    yet!
-- text: back waiters:I understand the area and folks you need not come here for the
-    romantic, alluring ambiance or the five star service featuring a sommlier and
-    a complicated maze of captain and back waiters - you come for the authentic foods,
-    the tastes, the experiance.
-- text: wine selection:The wine selection (by the glass and bottle) is wonderful and
-    I always recommend that friends make a reservation if they're going to be in town.
+- text: bench:Get your food to go, find a bench, and kick back with a plate of dumplings.
+- text: comparison:Frankly, when you compare what you can have here for lunch, versus
+    McDs or so many other sandwich shops in the city, there is no comparison.
+- text: ton:We had crawfish boiled and despite making a mess, it was a ton of fun
+    and quite tasty as well.
+- text: traffic noise:It is set far from the small street it's on, and there is no
+    traffic noise.
+- text: food:The only thing more wonderful than the food (which is exceptional) is
+    the service.
 metrics:
 - accuracy
 - f1_micro
@@ -45,28 +40,28 @@ model-index:
       split: test
     metrics:
     - type: accuracy
-      value: 0.8539823008849557
+      value: 0.8612873980054397
       name: Accuracy
     - type: f1_micro
-      value: 0.8539823008849557
+      value: 0.8612873980054397
       name: F1_Micro
     - type: f1_macro
-      value: 0.8479541701494363
+      value: 0.8539516827486352
       name: F1_Macro
     - type: f1_weighted
-      value: 0.8517050070515373
+      value: 0.8604149464336351
       name: F1_Weighted
     - type: precision_micro
-      value: 0.8539823008849557
+      value: 0.8612873980054397
       name: Precision_Micro
     - type: precision_macro
-      value: 0.8644139566395663
+      value: 0.8591116944822033
       name: Precision_Macro
     - type: recall_micro
-      value: 0.8539823008849557
+      value: 0.8612873980054397
       name: Recall_Micro
     - type: recall_macro
-      value: 0.8422413107452478
+      value: 0.8501826112588928
       name: Recall_Macro
 ---
 
@@ -117,7 +112,7 @@ This model was trained within the context of a larger system for ABSA, which loo
 ### Metrics
 | Label   | Accuracy | F1_Micro | F1_Macro | F1_Weighted | Precision_Micro | Precision_Macro | Recall_Micro | Recall_Macro |
 |:--------|:---------|:---------|:---------|:------------|:----------------|:----------------|:-------------|:-------------|
-| **all** | 0.8540   | 0.8540   | 0.8480   | 0.8517      | 0.8540          | 0.8644          | 0.8540       | 0.8422       |
+| **all** | 0.8613   | 0.8613   | 0.8540   | 0.8604      | 0.8613          | 0.8591          | 0.8613       | 0.8502       |
 
 ## Uses
 
@@ -172,12 +167,12 @@ preds = model("The food was great, but the venue is just way too busy.")
 ### Training Set Metrics
 | Training set | Min | Median  | Max |
 |:-------------|:----|:--------|:----|
-| Word count   | 4   | 17.9296 | 37  |
+| Word count   | 4   | 19.4181 | 45  |
 
 | Label     | Training Sample Count |
 |:----------|:----------------------|
-| no aspect | 71                    |
-| aspect    | 128                   |
+| no aspect | 167                   |
+| aspect    | 254                   |
 
 ### Training Hyperparameters
 - batch_size: (128, 128)
@@ -200,25 +195,28 @@ preds = model("The food was great, but the venue is just way too busy.")
 ### Training Results
 | Epoch  | Step | Training Loss | Validation Loss |
 |:------:|:----:|:-------------:|:---------------:|
-| 0.0059 | 1    | 0.311         | -               |
-| 0.2959 | 50   | 0.2716        | 0.2559          |
-| 0.5917 | 100  | 0.1808        | 0.2302          |
-| 0.8876 | 150  | 0.0201        | 0.2321          |
-| 1.1834 | 200  | 0.0027        | 0.2249          |
-| 1.4793 | 250  | 0.0017        | 0.2325          |
-| 1.7751 | 300  | 0.0008        | 0.2361          |
-| 2.0710 | 350  | 0.0007        | 0.2496          |
-| 2.3669 | 400  | 0.0006        | 0.2306          |
-| 2.6627 | 450  | 0.0005        | 0.2370          |
+| 0.0014 | 1    | 0.3269        | -               |
+| 0.0689 | 50   | 0.3079        | 0.2812          |
+| 0.1377 | 100  | 0.2566        | 0.2496          |
+| 0.2066 | 150  | 0.2388        | 0.2281          |
+| 0.2755 | 200  | 0.1867        | 0.1864          |
+| 0.3444 | 250  | 0.0713        | 0.1830          |
+| 0.4132 | 300  | 0.0132        | 0.1900          |
+| 0.4821 | 350  | 0.0038        | 0.1806          |
+| 0.5510 | 400  | 0.002         | 0.1896          |
+| 0.6198 | 450  | 0.0016        | 0.1843          |
+| 0.6887 | 500  | 0.0008        | 0.1892          |
+| 0.7576 | 550  | 0.0009        | 0.2014          |
+| 0.8264 | 600  | 0.0009        | 0.1840          |
 
 ### Framework Versions
-- Python: 3.11.12
+- Python: 3.11.13
 - SetFit: 1.1.2
-- Sentence Transformers: 3.4.1
-- spaCy: 3.8.5
-- Transformers: 4.51.3
+- Sentence Transformers: 4.1.0
+- spaCy: 3.8.7
+- Transformers: 4.52.4
 - PyTorch: 2.6.0+cu124
-- Datasets: 3.5.1
+- Datasets: 3.6.0
 - Tokenizers: 0.21.1
 
 ## Citation

config.json

@@ -18,7 +18,7 @@
   "pad_token_id": 0,
   "position_embedding_type": "absolute",
   "torch_dtype": "float32",
-  "transformers_version": "4.51.3",
+  "transformers_version": "4.52.4",
   "type_vocab_size": 2,
   "use_cache": true,
   "vocab_size": 30522

config_sentence_transformers.json

@@ -1,7 +1,7 @@
 {
   "__version__": {
-    "sentence_transformers": "3.4.1",
-    "transformers": "4.51.3",
+    "sentence_transformers": "4.1.0",
+    "transformers": "4.52.4",
     "pytorch": "2.6.0+cu124"
   },
   "prompts": {},

config_setfit.json

@@ -1,9 +1,9 @@
 {
-  "spacy_model": "en_core_web_lg",
   "normalize_embeddings": false,
   "labels": [
     "no aspect",
     "aspect"
   ],
+  "spacy_model": "en_core_web_lg",
   "span_context": 0
 }

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3b18d16aca34ce420c1788dc1b084dc9dae7d95dc3d0656b272a85c8107817d1
+oid sha256:999a6a1b887de74026a1047226ed8e46321a2cd72916bc970d4dd2e8f2c0f4d9
 size 90864192

model_head.pkl

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b3a40227a02bb5dd09d320828b6af908002b2d6b8aa84d50eec6230b0be1c95c
+oid sha256:97987c95cf8356d221a0fe58df01834382c95baba9c5eb7139b55baa0145b465
 size 3919