Add new SentenceTransformer model.

README.md

@@ -1,7 +1,5 @@
 ---
 base_model: sentence-transformers/all-MiniLM-L6-v2
-datasets: []
-language: []
 library_name: sentence-transformers
 metrics:
 - cosine_accuracy
@@ -45,34 +43,34 @@ tags:
 - sentence-similarity
 - feature-extraction
 - generated_from_trainer
-- dataset_size:560
+- dataset_size:965
 - loss:CoSENTLoss
 widget:
-- source_sentence: Let's search inside
+- source_sentence: To test the spell
   sentences:
-  - Stuffed animal
-  - Let's look inside
-  - What is worse?
-- source_sentence: I want a torch
+  - Are you a magic spell user?
+  - What happened?
+  - Who is your daughter?
+- source_sentence: Someone used a magic spell to change the flower into a plush
   sentences:
-  - What do you think of Spike
-  - Actually I want a torch
-  - Why candle?
-- source_sentence: Magic trace
+  - Have you been to a well?
+  - These Bottles.
+  - Magic is on the plush
+- source_sentence: What spells can the villagers use?
   sentences:
-  - A sword.
-  - ' Why is he so tiny?'
-  - 'The flower is changed into flower. '
-- source_sentence: Did you use illusion?
+  - Jack
+  - Do you know a mage who changes shape of material?
+  - These lillies are important.
+- source_sentence: Why are you pressured?
   sentences:
-  - Do you use illusion?
-  - You are a cat?
-  - It's Toby
-- source_sentence: Do you see your scarf in the watering can?
+  - A picture.
+  - Sophie why are you pressured?
+  - Change the look of object
+- source_sentence: I found lillies.
   sentences:
-  - What is the Weeping Tree?
-  - Are these your footprints?
-  - Magic user
+  - Someone who can change item
+  - These lillies.
+  - Are you plotting?
 model-index:
 - name: SentenceTransformer based on sentence-transformers/all-MiniLM-L6-v2
   results:
@@ -80,119 +78,119 @@ model-index:
       type: binary-classification
       name: Binary Classification
     dataset:
-      name: custom arc semantics data
-      type: custom-arc-semantics-data
+      name: custom arc semantics data en
+      type: custom-arc-semantics-data-en
     metrics:
     - type: cosine_accuracy
-      value: 0.9285714285714286
+      value: 0.8756476683937824
       name: Cosine Accuracy
     - type: cosine_accuracy_threshold
-      value: 0.42927420139312744
+      value: 0.3563339114189148
       name: Cosine Accuracy Threshold
     - type: cosine_f1
-      value: 0.9425287356321839
+      value: 0.8928571428571428
       name: Cosine F1
     - type: cosine_f1_threshold
-      value: 0.2269928753376007
+      value: 0.3563339114189148
       name: Cosine F1 Threshold
     - type: cosine_precision
-      value: 0.9111111111111111
+      value: 0.847457627118644
       name: Cosine Precision
     - type: cosine_recall
-      value: 0.9761904761904762
+      value: 0.9433962264150944
       name: Cosine Recall
     - type: cosine_ap
-      value: 0.9720863676601571
+      value: 0.93108620584637
       name: Cosine Ap
     - type: dot_accuracy
-      value: 0.9285714285714286
+      value: 0.8756476683937824
       name: Dot Accuracy
     - type: dot_accuracy_threshold
-      value: 0.42927438020706177
+      value: 0.3563339114189148
       name: Dot Accuracy Threshold
     - type: dot_f1
-      value: 0.9425287356321839
+      value: 0.8928571428571428
       name: Dot F1
     - type: dot_f1_threshold
-      value: 0.22699296474456787
+      value: 0.3563339114189148
       name: Dot F1 Threshold
     - type: dot_precision
-      value: 0.9111111111111111
+      value: 0.847457627118644
       name: Dot Precision
     - type: dot_recall
-      value: 0.9761904761904762
+      value: 0.9433962264150944
       name: Dot Recall
     - type: dot_ap
-      value: 0.9720863676601571
+      value: 0.93108620584637
       name: Dot Ap
     - type: manhattan_accuracy
-      value: 0.9285714285714286
+      value: 0.8756476683937824
       name: Manhattan Accuracy
     - type: manhattan_accuracy_threshold
-      value: 16.630834579467773
+      value: 17.202983856201172
       name: Manhattan Accuracy Threshold
     - type: manhattan_f1
-      value: 0.9431818181818182
+      value: 0.8909090909090909
       name: Manhattan F1
     - type: manhattan_f1_threshold
-      value: 19.740108489990234
+      value: 17.202983856201172
       name: Manhattan F1 Threshold
     - type: manhattan_precision
-      value: 0.9021739130434783
+      value: 0.8596491228070176
       name: Manhattan Precision
     - type: manhattan_recall
-      value: 0.9880952380952381
+      value: 0.9245283018867925
       name: Manhattan Recall
     - type: manhattan_ap
-      value: 0.9728353486982702
+      value: 0.9302290531425504
       name: Manhattan Ap
     - type: euclidean_accuracy
-      value: 0.9285714285714286
+      value: 0.8756476683937824
       name: Euclidean Accuracy
     - type: euclidean_accuracy_threshold
-      value: 1.068155288696289
+      value: 1.1346065998077393
       name: Euclidean Accuracy Threshold
     - type: euclidean_f1
-      value: 0.9425287356321839
+      value: 0.8928571428571428
       name: Euclidean F1
     - type: euclidean_f1_threshold
-      value: 1.2433418035507202
+      value: 1.1346065998077393
       name: Euclidean F1 Threshold
     - type: euclidean_precision
-      value: 0.9111111111111111
+      value: 0.847457627118644
       name: Euclidean Precision
     - type: euclidean_recall
-      value: 0.9761904761904762
+      value: 0.9433962264150944
       name: Euclidean Recall
     - type: euclidean_ap
-      value: 0.9720863676601571
+      value: 0.93108620584637
       name: Euclidean Ap
     - type: max_accuracy
-      value: 0.9285714285714286
+      value: 0.8756476683937824
       name: Max Accuracy
     - type: max_accuracy_threshold
-      value: 16.630834579467773
+      value: 17.202983856201172
       name: Max Accuracy Threshold
     - type: max_f1
-      value: 0.9431818181818182
+      value: 0.8928571428571428
       name: Max F1
     - type: max_f1_threshold
-      value: 19.740108489990234
+      value: 17.202983856201172
       name: Max F1 Threshold
     - type: max_precision
-      value: 0.9111111111111111
+      value: 0.8596491228070176
       name: Max Precision
     - type: max_recall
-      value: 0.9880952380952381
+      value: 0.9433962264150944
       name: Max Recall
     - type: max_ap
-      value: 0.9728353486982702
+      value: 0.93108620584637
       name: Max Ap
 ---
 
 # SentenceTransformer based on sentence-transformers/all-MiniLM-L6-v2
 
-This is a [sentence-transformers](https://www.SBERT.net) model finetuned from [sentence-transformers/all-MiniLM-L6-v2](https://huggingface.co/sentence-transformers/all-MiniLM-L6-v2). It maps sentences & paragraphs to a 384-dimensional dense vector space and can be used for semantic textual similarity, semantic search, paraphrase mining, text classification, clustering, and more.
+This is a [sentence-transformers](https://www.SBERT.net) model finetuned from [sentence-transformers/all-MiniLM-L6-v2](https://huggingface.co/sentence-transformers/all-MiniLM-L6-v2) on the csv dataset. It maps sentences & paragraphs to a 384-dimensional dense vector space and can be used for semantic textual similarity, semantic search, paraphrase mining, text classification, clustering, and more.
 
 ## Model Details
 
@@ -202,7 +200,8 @@ This is a [sentence-transformers](https://www.SBERT.net) model finetuned from [s
 - **Maximum Sequence Length:** 256 tokens
 - **Output Dimensionality:** 384 tokens
 - **Similarity Function:** Cosine Similarity
-<!-- - **Training Dataset:** Unknown -->
+- **Training Dataset:**
+    - csv
 <!-- - **Language:** Unknown -->
 <!-- - **License:** Unknown -->
 
@@ -240,9 +239,9 @@ from sentence_transformers import SentenceTransformer
 model = SentenceTransformer("LeoChiuu/all-MiniLM-L6-v2-arc")
 # Run inference
 sentences = [
-    'Do you see your scarf in the watering can?',
-    'Are these your footprints?',
-    'Magic user',
+    'I found lillies.',
+    'These lillies.',
+    'Are you plotting?',
 ]
 embeddings = model.encode(sentences)
 print(embeddings.shape)
@@ -283,46 +282,46 @@ You can finetune this model on your own dataset.
 ### Metrics
 
 #### Binary Classification
-* Dataset: `custom-arc-semantics-data`
+* Dataset: `custom-arc-semantics-data-en`
 * Evaluated with [<code>BinaryClassificationEvaluator</code>](https://sbert.net/docs/package_reference/sentence_transformer/evaluation.html#sentence_transformers.evaluation.BinaryClassificationEvaluator)
 
 | Metric                       | Value      |
 |:-----------------------------|:-----------|
-| cosine_accuracy              | 0.9286     |
-| cosine_accuracy_threshold    | 0.4293     |
-| cosine_f1                    | 0.9425     |
-| cosine_f1_threshold          | 0.227      |
-| cosine_precision             | 0.9111     |
-| cosine_recall                | 0.9762     |
-| cosine_ap                    | 0.9721     |
-| dot_accuracy                 | 0.9286     |
-| dot_accuracy_threshold       | 0.4293     |
-| dot_f1                       | 0.9425     |
-| dot_f1_threshold             | 0.227      |
-| dot_precision                | 0.9111     |
-| dot_recall                   | 0.9762     |
-| dot_ap                       | 0.9721     |
-| manhattan_accuracy           | 0.9286     |
-| manhattan_accuracy_threshold | 16.6308    |
-| manhattan_f1                 | 0.9432     |
-| manhattan_f1_threshold       | 19.7401    |
-| manhattan_precision          | 0.9022     |
-| manhattan_recall             | 0.9881     |
-| manhattan_ap                 | 0.9728     |
-| euclidean_accuracy           | 0.9286     |
-| euclidean_accuracy_threshold | 1.0682     |
-| euclidean_f1                 | 0.9425     |
-| euclidean_f1_threshold       | 1.2433     |
-| euclidean_precision          | 0.9111     |
-| euclidean_recall             | 0.9762     |
-| euclidean_ap                 | 0.9721     |
-| max_accuracy                 | 0.9286     |
-| max_accuracy_threshold       | 16.6308    |
-| max_f1                       | 0.9432     |
-| max_f1_threshold             | 19.7401    |
-| max_precision                | 0.9111     |
-| max_recall                   | 0.9881     |
-| **max_ap**                   | **0.9728** |
+| cosine_accuracy              | 0.8756     |
+| cosine_accuracy_threshold    | 0.3563     |
+| cosine_f1                    | 0.8929     |
+| cosine_f1_threshold          | 0.3563     |
+| cosine_precision             | 0.8475     |
+| cosine_recall                | 0.9434     |
+| cosine_ap                    | 0.9311     |
+| dot_accuracy                 | 0.8756     |
+| dot_accuracy_threshold       | 0.3563     |
+| dot_f1                       | 0.8929     |
+| dot_f1_threshold             | 0.3563     |
+| dot_precision                | 0.8475     |
+| dot_recall                   | 0.9434     |
+| dot_ap                       | 0.9311     |
+| manhattan_accuracy           | 0.8756     |
+| manhattan_accuracy_threshold | 17.203     |
+| manhattan_f1                 | 0.8909     |
+| manhattan_f1_threshold       | 17.203     |
+| manhattan_precision          | 0.8596     |
+| manhattan_recall             | 0.9245     |
+| manhattan_ap                 | 0.9302     |
+| euclidean_accuracy           | 0.8756     |
+| euclidean_accuracy_threshold | 1.1346     |
+| euclidean_f1                 | 0.8929     |
+| euclidean_f1_threshold       | 1.1346     |
+| euclidean_precision          | 0.8475     |
+| euclidean_recall             | 0.9434     |
+| euclidean_ap                 | 0.9311     |
+| max_accuracy                 | 0.8756     |
+| max_accuracy_threshold       | 17.203     |
+| max_f1                       | 0.8929     |
+| max_f1_threshold             | 17.203     |
+| max_precision                | 0.8596     |
+| max_recall                   | 0.9434     |
+| **max_ap**                   | **0.9311** |
 
 <!--
 ## Bias, Risks and Limitations
@@ -340,22 +339,22 @@ You can finetune this model on your own dataset.
 
 ### Training Dataset
 
-#### Unnamed Dataset
+#### csv
 
-
-* Size: 560 training samples
+* Dataset: csv
+* Size: 965 training samples
 * Columns: <code>text1</code>, <code>text2</code>, and <code>label</code>
-* Approximate statistics based on the first 1000 samples:
+* Approximate statistics based on the first 965 samples:
   |         | text1                                                                           | text2                                                                            | label                                           |
   |:--------|:--------------------------------------------------------------------------------|:---------------------------------------------------------------------------------|:------------------------------------------------|
   | type    | string                                                                          | string                                                                           | int                                             |
-  | details | <ul><li>min: 3 tokens</li><li>mean: 7.2 tokens</li><li>max: 18 tokens</li></ul> | <ul><li>min: 3 tokens</li><li>mean: 7.26 tokens</li><li>max: 18 tokens</li></ul> | <ul><li>0: ~36.07%</li><li>1: ~63.93%</li></ul> |
+  | details | <ul><li>min: 3 tokens</li><li>mean: 7.3 tokens</li><li>max: 18 tokens</li></ul> | <ul><li>min: 3 tokens</li><li>mean: 7.18 tokens</li><li>max: 18 tokens</li></ul> | <ul><li>0: ~42.10%</li><li>1: ~57.90%</li></ul> |
 * Samples:
-  | text1                                                | text2                                                                     | label          |
-  |:-----------------------------------------------------|:--------------------------------------------------------------------------|:---------------|
-  | <code>When it was dinner</code>                      | <code>Dinner time</code>                                                  | <code>1</code> |
-  | <code>Did you cook chicken noodle last night?</code> | <code>Did you make chicken noodle for dinner?</code>                      | <code>1</code> |
-  | <code>Someone who can change item</code>             | <code>Someone who uses magic that turns something into something. </code> | <code>1</code> |
+  | text1                                     | text2                           | label          |
+  |:------------------------------------------|:--------------------------------|:---------------|
+  | <code>What did you eat last night?</code> | <code>What did you cook?</code> | <code>1</code> |
+  | <code>I don't like you</code>             | <code>I hate you</code>         | <code>1</code> |
+  | <code>Tell me about theier magic</code>   | <code>Elder</code>              | <code>0</code> |
 * Loss: [<code>CoSENTLoss</code>](https://sbert.net/docs/package_reference/sentence_transformer/losses.html#cosentloss) with these parameters:
   ```json
   {
@@ -366,22 +365,22 @@ You can finetune this model on your own dataset.
 
 ### Evaluation Dataset
 
-#### Unnamed Dataset
-
+#### csv
 
-* Size: 140 evaluation samples
+* Dataset: csv
+* Size: 965 evaluation samples
 * Columns: <code>text1</code>, <code>text2</code>, and <code>label</code>
-* Approximate statistics based on the first 1000 samples:
+* Approximate statistics based on the first 965 samples:
   |         | text1                                                                            | text2                                                                            | label                                           |
   |:--------|:---------------------------------------------------------------------------------|:---------------------------------------------------------------------------------|:------------------------------------------------|
   | type    | string                                                                           | string                                                                           | int                                             |
-  | details | <ul><li>min: 3 tokens</li><li>mean: 6.99 tokens</li><li>max: 18 tokens</li></ul> | <ul><li>min: 3 tokens</li><li>mean: 7.29 tokens</li><li>max: 18 tokens</li></ul> | <ul><li>0: ~40.00%</li><li>1: ~60.00%</li></ul> |
+  | details | <ul><li>min: 3 tokens</li><li>mean: 7.14 tokens</li><li>max: 18 tokens</li></ul> | <ul><li>min: 3 tokens</li><li>mean: 6.93 tokens</li><li>max: 18 tokens</li></ul> | <ul><li>0: ~45.08%</li><li>1: ~54.92%</li></ul> |
 * Samples:
-  | text1                                    | text2                                    | label          |
-  |:-----------------------------------------|:-----------------------------------------|:---------------|
-  | <code>Let's check inside</code>          | <code>Let's search inside</code>         | <code>1</code> |
-  | <code>Sohpie, are you okay?</code>       | <code>Sophie Are you pressured?</code>   | <code>0</code> |
-  | <code>This wine glass is related.</code> | <code>This sword looks important.</code> | <code>0</code> |
+  | text1                                            | text2                              | label          |
+  |:-------------------------------------------------|:-----------------------------------|:---------------|
+  | <code>To test the spell</code>                   | <code>Who is your daughter?</code> | <code>0</code> |
+  | <code>I think this painting is important.</code> | <code>A book.</code>               | <code>0</code> |
+  | <code>Is the scarf in the fireplace?</code>      | <code>Candle</code>                | <code>0</code> |
 * Loss: [<code>CoSENTLoss</code>](https://sbert.net/docs/package_reference/sentence_transformer/losses.html#cosentloss) with these parameters:
   ```json
   {
@@ -395,7 +394,7 @@ You can finetune this model on your own dataset.
 
 - `eval_strategy`: epoch
 - `learning_rate`: 2e-05
-- `num_train_epochs`: 13
+- `num_train_epochs`: 2
 - `warmup_ratio`: 0.1
 - `fp16`: True
 - `batch_sampler`: no_duplicates
@@ -420,7 +419,7 @@ You can finetune this model on your own dataset.
 - `adam_beta2`: 0.999
 - `adam_epsilon`: 1e-08
 - `max_grad_norm`: 1.0
-- `num_train_epochs`: 13
+- `num_train_epochs`: 2
 - `max_steps`: -1
 - `lr_scheduler_type`: linear
 - `lr_scheduler_kwargs`: {}
@@ -518,27 +517,16 @@ You can finetune this model on your own dataset.
 </details>
 
 ### Training Logs
-| Epoch | Step | Training Loss | loss   | custom-arc-semantics-data_max_ap |
-|:-----:|:----:|:-------------:|:------:|:--------------------------------:|
-| None  | 0    | -             | -      | 0.9254                           |
-| 1.0   | 70   | 2.9684        | 1.4087 | 0.9425                           |
-| 2.0   | 140  | 1.4461        | 1.0942 | 0.9629                           |
-| 3.0   | 210  | 0.6005        | 0.8398 | 0.9680                           |
-| 4.0   | 280  | 0.3021        | 0.7577 | 0.9703                           |
-| 5.0   | 350  | 0.2412        | 0.7216 | 0.9715                           |
-| 6.0   | 420  | 0.1816        | 0.7538 | 0.9722                           |
-| 7.0   | 490  | 0.1512        | 0.8049 | 0.9726                           |
-| 8.0   | 560  | 0.1208        | 0.7602 | 0.9726                           |
-| 9.0   | 630  | 0.0915        | 0.7286 | 0.9729                           |
-| 10.0  | 700  | 0.0553        | 0.7072 | 0.9729                           |
-| 11.0  | 770  | 0.0716        | 0.6984 | 0.9730                           |
-| 12.0  | 840  | 0.0297        | 0.7063 | 0.9725                           |
-| 13.0  | 910  | 0.0462        | 0.6997 | 0.9728                           |
+| Epoch | Step | Training Loss | loss   | custom-arc-semantics-data-en_max_ap |
+|:-----:|:----:|:-------------:|:------:|:-----------------------------------:|
+| None  | 0    | -             | -      | 0.8832                              |
+| 1.0   | 97   | 2.266         | 2.0829 | 0.9252                              |
+| 2.0   | 194  | 1.0666        | 1.8713 | 0.9311                              |
 
 
 ### Framework Versions
 - Python: 3.10.14
-- Sentence Transformers: 3.0.1
+- Sentence Transformers: 3.1.0
 - Transformers: 4.44.2
 - PyTorch: 2.4.1+cu121
 - Accelerate: 0.34.2

config_sentence_transformers.json

@@ -1,6 +1,6 @@
 {
   "__version__": {
-    "sentence_transformers": "3.0.1",
+    "sentence_transformers": "3.1.0",
     "transformers": "4.44.2",
     "pytorch": "2.4.1+cu121"
   },

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2d9ab6b7472780e4b9271e02f535d125c33cef1b145ab2f8d3135ed97c72aea5
+oid sha256:2380e8cf990e70e06384ac349d98edb264c17102e09a5f6f7cbdd00d64bd236c
 size 90864192