huggingface.co/CDXV/hack_ai_embbedding_model

README.md

@@ -8,32 +8,35 @@ tags:
 - loss:CoSENTLoss
 base_model: abdeljalilELmajjodi/model
 widget:
-- source_sentence: A few people in a restaurant setting, one of them is drinking orange
-    juice.
+- source_sentence: Children smiling and waving at camera
   sentences:
+  - The kids are frowning
   - The people are eating omelettes.
-  - There are women showing affection.
-  - A school hosts a basketball game.
-- source_sentence: An older man is drinking orange juice at a restaurant.
+  - Near a couple of restaurants, two people walk across the street.
+- source_sentence: Two women, holding food carryout containers, hug.
   sentences:
-  - The woman and man are playing baseball together.
+  - two coworkers cross pathes on a street
+  - The woman is wearing white.
   - Two groups of rival gang members flipped each other off.
-  - Two women are at a restaurant drinking wine.
+- source_sentence: A woman is walking across the street eating a banana, while a man
+    is following with his briefcase.
+  sentences:
+  - A woman eats a banana and walks across a street, and there is a man trailing behind
+    her.
+  - An elderly man sits in a small shop.
+  - The adults are both male and female.
 - source_sentence: People waiting to get on a train or just getting off.
   sentences:
-  - There are people just getting on a train
-  - The woman is wearing green.
+  - There are people waiting on a train.
+  - The two sisters saw each other across the crowded diner and shared a hug, both
+    clutching their doggie bags.
   - There are two woman in this picture.
-- source_sentence: A man, woman, and child enjoying themselves on a beach.
-  sentences:
-  - A family of three is at the beach.
-  - A blond man getting a drink of water from a fountain in the park.
-  - The diners are at a restaurant.
-- source_sentence: A couple playing with a little boy on the beach.
+- source_sentence: The school is having a special event in order to show the american
+    culture on how other cultures are dealt with in parties.
   sentences:
-  - The people are sitting at desks in school.
-  - The people are standing still on the curb.
-  - A couple watch a little girl play by herself on the beach.
+  - They are protesting outside the capital.
+  - A woman ordering pizza.
+  - A school is hosting an event.
 pipeline_tag: sentence-similarity
 library_name: sentence-transformers
 metrics:
@@ -50,10 +53,10 @@ model-index:
       type: pair-score-evaluator-dev
     metrics:
     - type: pearson_cosine
-      value: 0.037203406650844886
+      value: -0.22939457943411037
       name: Pearson Cosine
     - type: spearman_cosine
-      value: 0.07040057435528181
+      value: -0.18637822325921868
       name: Spearman Cosine
 ---
 
@@ -107,9 +110,9 @@ from sentence_transformers import SentenceTransformer
 model = SentenceTransformer("sentence_transformers_model_id")
 # Run inference
 sentences = [
-    'A couple playing with a little boy on the beach.',
-    'A couple watch a little girl play by herself on the beach.',
-    'The people are sitting at desks in school.',
+    'The school is having a special event in order to show the american culture on how other cultures are dealt with in parties.',
+    'A school is hosting an event.',
+    'They are protesting outside the capital.',
 ]
 embeddings = model.encode(sentences)
 print(embeddings.shape)
@@ -118,9 +121,9 @@ print(embeddings.shape)
 # Get the similarity scores for the embeddings
 similarities = model.similarity(embeddings, embeddings)
 print(similarities)
-# tensor([[1.0000, 0.9975, 0.9887],
-#         [0.9975, 1.0000, 0.9894],
-#         [0.9887, 0.9894, 1.0000]])
+# tensor([[1.0000, 0.9755, 0.9818],
+#         [0.9755, 1.0000, 0.9960],
+#         [0.9818, 0.9960, 1.0000]])
 ```
 <!--
 ### Direct Usage (Transformers)
@@ -155,10 +158,10 @@ You can finetune this model on your own dataset.
 * Dataset: `pair-score-evaluator-dev`
 * Evaluated with [<code>EmbeddingSimilarityEvaluator</code>](https://sbert.net/docs/package_reference/sentence_transformer/evaluation.html#sentence_transformers.sentence_transformer.evaluation.EmbeddingSimilarityEvaluator)
 
-| Metric              | Value      |
-|:--------------------|:-----------|
-| pearson_cosine      | 0.0372     |
-| **spearman_cosine** | **0.0704** |
+| Metric              | Value       |
+|:--------------------|:------------|
+| pearson_cosine      | -0.2294     |
+| **spearman_cosine** | **-0.1864** |
 
 <!--
 ## Bias, Risks and Limitations
@@ -182,16 +185,16 @@ You can finetune this model on your own dataset.
 * Size: 80 training samples
 * Columns: <code>sentence1</code>, <code>sentence2</code>, and <code>score</code>
 * Approximate statistics based on the first 80 samples:
-  |         | sentence1                                                                          | sentence2                                                                         | score                                                         |
-  |:--------|:-----------------------------------------------------------------------------------|:----------------------------------------------------------------------------------|:--------------------------------------------------------------|
-  | type    | string                                                                             | string                                                                            | float                                                         |
-  | details | <ul><li>min: 10 tokens</li><li>mean: 27.69 tokens</li><li>max: 52 tokens</li></ul> | <ul><li>min: 5 tokens</li><li>mean: 11.95 tokens</li><li>max: 29 tokens</li></ul> | <ul><li>min: 0.0</li><li>mean: 0.5</li><li>max: 1.0</li></ul> |
+  |         | sentence1                                                                          | sentence2                                                                        | score                                                          |
+  |:--------|:-----------------------------------------------------------------------------------|:---------------------------------------------------------------------------------|:---------------------------------------------------------------|
+  | type    | string                                                                             | string                                                                           | float                                                          |
+  | details | <ul><li>min: 10 tokens</li><li>mean: 25.76 tokens</li><li>max: 52 tokens</li></ul> | <ul><li>min: 5 tokens</li><li>mean: 11.9 tokens</li><li>max: 29 tokens</li></ul> | <ul><li>min: 0.0</li><li>mean: 0.48</li><li>max: 1.0</li></ul> |
 * Samples:
-  | sentence1                                                                                                                                                                                                      | sentence2                                       | score            |
-  |:---------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|:------------------------------------------------|:-----------------|
-  | <code>Two adults, one female in white, with shades and one male, gray clothes, walking across a street, away from a eatery with a blurred image of a dark colored red shirted person in the foreground.</code> | <code>Two adults swimming in water</code>       | <code>0.0</code> |
-  | <code>Two adults, one female in white, with shades and one male, gray clothes, walking across a street, away from a eatery with a blurred image of a dark colored red shirted person in the foreground.</code> | <code>Two friends cross a street.</code>        | <code>0.5</code> |
-  | <code>Woman in white in foreground and a man slightly behind walking with a sign for John's Pizza and Gyro in the background.</code>                                                                           | <code>They are working for John's Pizza.</code> | <code>0.5</code> |
+  | sentence1                                                                                      | sentence2                                                | score            |
+  |:-----------------------------------------------------------------------------------------------|:---------------------------------------------------------|:-----------------|
+  | <code>A man with blond-hair, and a brown shirt drinking out of a public water fountain.</code> | <code>A blond man drinking water from a fountain.</code> | <code>1.0</code> |
+  | <code>A man, woman, and child enjoying themselves on a beach.</code>                           | <code>A family of three is at the mall shopping.</code>  | <code>0.0</code> |
+  | <code>A woman wearing all white and eating, walks next to a man holding a briefcase.</code>    | <code>A married couple is sleeping.</code>               | <code>0.0</code> |
 * Loss: [<code>CoSENTLoss</code>](https://sbert.net/docs/package_reference/sentence_transformer/losses.html#cosentloss) with these parameters:
   ```json
   {
@@ -208,16 +211,16 @@ You can finetune this model on your own dataset.
 * Size: 20 evaluation samples
 * Columns: <code>sentence1</code>, <code>sentence2</code>, and <code>score</code>
 * Approximate statistics based on the first 20 samples:
-  |         | sentence1                                                                         | sentence2                                                                        | score                                                          |
-  |:--------|:----------------------------------------------------------------------------------|:---------------------------------------------------------------------------------|:---------------------------------------------------------------|
-  | type    | string                                                                            | string                                                                           | float                                                          |
-  | details | <ul><li>min: 11 tokens</li><li>mean: 17.9 tokens</li><li>max: 28 tokens</li></ul> | <ul><li>min: 8 tokens</li><li>mean: 12.1 tokens</li><li>max: 29 tokens</li></ul> | <ul><li>min: 0.0</li><li>mean: 0.53</li><li>max: 1.0</li></ul> |
+  |         | sentence1                                                                         | sentence2                                                                        | score                                                         |
+  |:--------|:----------------------------------------------------------------------------------|:---------------------------------------------------------------------------------|:--------------------------------------------------------------|
+  | type    | string                                                                            | string                                                                           | float                                                         |
+  | details | <ul><li>min: 10 tokens</li><li>mean: 25.6 tokens</li><li>max: 52 tokens</li></ul> | <ul><li>min: 8 tokens</li><li>mean: 12.3 tokens</li><li>max: 29 tokens</li></ul> | <ul><li>min: 0.0</li><li>mean: 0.6</li><li>max: 1.0</li></ul> |
 * Samples:
-  | sentence1                                                          | sentence2                                             | score            |
-  |:-------------------------------------------------------------------|:------------------------------------------------------|:-----------------|
-  | <code>Two women, holding food carryout containers, hug.</code>     | <code>Two women hug each other.</code>                | <code>1.0</code> |
-  | <code>Two blond women are hugging one another.</code>              | <code>There are women showing affection.</code>       | <code>1.0</code> |
-  | <code>People waiting to get on a train or just getting off.</code> | <code>There are people just getting on a train</code> | <code>1.0</code> |
+  | sentence1                                                                                                                                                | sentence2                                                                     | score            |
+  |:---------------------------------------------------------------------------------------------------------------------------------------------------------|:------------------------------------------------------------------------------|:-----------------|
+  | <code>A man and a woman cross the street in front of a pizza and gyro restaurant.</code>                                                                 | <code>Near a couple of restaurants, two people walk across the street.</code> | <code>1.0</code> |
+  | <code>Woman in white in foreground and a man slightly behind walking with a sign for John's Pizza and Gyro in the background.</code>                     | <code>A woman ordering pizza.</code>                                          | <code>0.5</code> |
+  | <code>An older man sits with his orange juice at a small table in a coffee shop while employees in bright colored shirts smile in the background.</code> | <code>A boy flips a burger.</code>                                            | <code>0.0</code> |
 * Loss: [<code>CoSENTLoss</code>](https://sbert.net/docs/package_reference/sentence_transformer/losses.html#cosentloss) with these parameters:
   ```json
   {
@@ -342,14 +345,14 @@ You can finetune this model on your own dataset.
 ### Training Logs
 | Epoch   | Step   | Training Loss | Validation Loss | pair-score-evaluator-dev_spearman_cosine |
 |:-------:|:------:|:-------------:|:---------------:|:----------------------------------------:|
-| 0.1     | 1      | 3.1682        | -               | -                                        |
-| 0.5     | 5      | 3.1271        | -               | -                                        |
-| **1.0** | **10** | **2.9318**    | **2.534**       | **0.0704**                               |
+| 0.1     | 1      | 2.7147        | -               | -                                        |
+| 0.5     | 5      | 3.4691        | -               | -                                        |
+| **1.0** | **10** | **3.0569**    | **2.7822**      | **-0.1864**                              |
 
 * The bold row denotes the saved checkpoint.
 
 ### Training Time
-- **Training**: 5.8 minutes
+- **Training**: 3.3 minutes
 
 ### Framework Versions
 - Python: 3.12.13