Add new SentenceTransformer model.

README.md

@@ -45,34 +45,34 @@ tags:
 - sentence-similarity
 - feature-extraction
 - generated_from_trainer
-- dataset_size:124
+- dataset_size:228
 - loss:MultipleNegativesRankingLoss
 widget:
-- source_sentence: なにも要らない
+- source_sentence: 家の外を探そう
   sentences:
-  - 欲しくない
-  - 暖炉を調べよう
-  - キャンドルがいいな
-- source_sentence: 試すため
+  - ベットを調べよう
+  - 何を作ったの？
+  - 外を見てみよう
+- source_sentence: 物の姿を変える魔法が使える村人を知っている？
   sentences:
-  - 誰にもらったやつ？
-  - スカーフはナイトスタンドにある？
-  - ためすため
-- source_sentence: ビーフシチュー作った？
+  - 中を見てみよう
+  - ベッドにある？
+  - 物体の形を変えられる魔法使いを知っている？
+- source_sentence: ぬいぐるみが花
   sentences:
-  - 昨日作ったのはビーフシチュー？
-  - キャンドル要らない
-  - 昨日夕飯にビーフシチュー食べた？
-- source_sentence: あれってキミのスカーフ？
+  - リリアンはどんな呪文が使えるの？
+  - ぬいぐるみ
+  - 花がぬいぐるみに変えられている
+- source_sentence: ベッドにスカーフはある？
   sentences:
-  - あの木の上にあるやつはなに？
-  - あれってレオのスカーフ？
-  - どっちをさがせばいい？
-- source_sentence: どっちも欲しくない
+  - 井戸へ行ったことある？
+  - どっちも要らない
+  - スカーフはベッドにある？
+- source_sentence: キャンドル頂戴
   sentences:
-  - 気にスカーフがひっかかってる
-  - 花壇を調べよう
-  - タイマツ要らない
+  - 祭壇の些細な違和感ってなに？
+  - やっぱり、キャンドルがいい
+  - テーブルを調べよう
 model-index:
 - name: SentenceTransformer based on colorfulscoop/sbert-base-ja
   results:
@@ -84,109 +84,109 @@ model-index:
       type: custom-arc-semantics-data
     metrics:
     - type: cosine_accuracy
-      value: 0.967741935483871
+      value: 0.9827586206896551
       name: Cosine Accuracy
     - type: cosine_accuracy_threshold
-      value: 0.2947738766670227
+      value: 0.2341834306716919
       name: Cosine Accuracy Threshold
     - type: cosine_f1
-      value: 0.9836065573770492
+      value: 0.9913043478260869
       name: Cosine F1
     - type: cosine_f1_threshold
-      value: 0.2947738766670227
+      value: 0.2341834306716919
       name: Cosine F1 Threshold
     - type: cosine_precision
       value: 1.0
       name: Cosine Precision
     - type: cosine_recall
-      value: 0.967741935483871
+      value: 0.9827586206896551
       name: Cosine Recall
     - type: cosine_ap
-      value: 0.9999999999999998
+      value: 1.0
       name: Cosine Ap
     - type: dot_accuracy
-      value: 0.967741935483871
+      value: 0.9827586206896551
       name: Dot Accuracy
     - type: dot_accuracy_threshold
-      value: 144.98019409179688
+      value: 134.29324340820312
       name: Dot Accuracy Threshold
     - type: dot_f1
-      value: 0.9836065573770492
+      value: 0.9913043478260869
       name: Dot F1
     - type: dot_f1_threshold
-      value: 144.98019409179688
+      value: 134.29324340820312
       name: Dot F1 Threshold
     - type: dot_precision
       value: 1.0
       name: Dot Precision
     - type: dot_recall
-      value: 0.967741935483871
+      value: 0.9827586206896551
       name: Dot Recall
     - type: dot_ap
-      value: 0.9999999999999998
+      value: 1.0
       name: Dot Ap
     - type: manhattan_accuracy
-      value: 0.967741935483871
+      value: 0.9827586206896551
       name: Manhattan Accuracy
     - type: manhattan_accuracy_threshold
-      value: 585.5504150390625
+      value: 644.1650390625
       name: Manhattan Accuracy Threshold
     - type: manhattan_f1
-      value: 0.9836065573770492
+      value: 0.9913043478260869
       name: Manhattan F1
     - type: manhattan_f1_threshold
-      value: 585.5504150390625
+      value: 644.1650390625
       name: Manhattan F1 Threshold
     - type: manhattan_precision
       value: 1.0
       name: Manhattan Precision
     - type: manhattan_recall
-      value: 0.967741935483871
+      value: 0.9827586206896551
       name: Manhattan Recall
     - type: manhattan_ap
-      value: 0.9999999999999998
+      value: 1.0
       name: Manhattan Ap
     - type: euclidean_accuracy
-      value: 0.967741935483871
+      value: 0.9827586206896551
       name: Euclidean Accuracy
     - type: euclidean_accuracy_threshold
-      value: 26.343276977539062
+      value: 29.542858123779297
       name: Euclidean Accuracy Threshold
     - type: euclidean_f1
-      value: 0.9836065573770492
+      value: 0.9913043478260869
       name: Euclidean F1
     - type: euclidean_f1_threshold
-      value: 26.343276977539062
+      value: 29.542858123779297
       name: Euclidean F1 Threshold
     - type: euclidean_precision
       value: 1.0
       name: Euclidean Precision
     - type: euclidean_recall
-      value: 0.967741935483871
+      value: 0.9827586206896551
       name: Euclidean Recall
     - type: euclidean_ap
-      value: 0.9999999999999998
+      value: 1.0
       name: Euclidean Ap
     - type: max_accuracy
-      value: 0.967741935483871
+      value: 0.9827586206896551
       name: Max Accuracy
     - type: max_accuracy_threshold
-      value: 585.5504150390625
+      value: 644.1650390625
       name: Max Accuracy Threshold
     - type: max_f1
-      value: 0.9836065573770492
+      value: 0.9913043478260869
       name: Max F1
     - type: max_f1_threshold
-      value: 585.5504150390625
+      value: 644.1650390625
       name: Max F1 Threshold
     - type: max_precision
       value: 1.0
       name: Max Precision
     - type: max_recall
-      value: 0.967741935483871
+      value: 0.9827586206896551
       name: Max Recall
     - type: max_ap
-      value: 0.9999999999999998
+      value: 1.0
       name: Max Ap
 ---
 
@@ -239,9 +239,9 @@ from sentence_transformers import SentenceTransformer
 model = SentenceTransformer("LeoChiuu/sbert-base-ja-arc")
 # Run inference
 sentences = [
-    'どっちも欲しくない',
-    'タイマツ要らない',
-    '花壇を調べよう',
+    'キャンドル頂戴',
+    'やっぱり、キャンドルがいい',
+    'テーブルを調べよう',
 ]
 embeddings = model.encode(sentences)
 print(embeddings.shape)
@@ -287,40 +287,40 @@ You can finetune this model on your own dataset.
 
 | Metric                       | Value    |
 |:-----------------------------|:---------|
-| cosine_accuracy              | 0.9677   |
-| cosine_accuracy_threshold    | 0.2948   |
-| cosine_f1                    | 0.9836   |
-| cosine_f1_threshold          | 0.2948   |
+| cosine_accuracy              | 0.9828   |
+| cosine_accuracy_threshold    | 0.2342   |
+| cosine_f1                    | 0.9913   |
+| cosine_f1_threshold          | 0.2342   |
 | cosine_precision             | 1.0      |
-| cosine_recall                | 0.9677   |
+| cosine_recall                | 0.9828   |
 | cosine_ap                    | 1.0      |
-| dot_accuracy                 | 0.9677   |
-| dot_accuracy_threshold       | 144.9802 |
-| dot_f1                       | 0.9836   |
-| dot_f1_threshold             | 144.9802 |
+| dot_accuracy                 | 0.9828   |
+| dot_accuracy_threshold       | 134.2932 |
+| dot_f1                       | 0.9913   |
+| dot_f1_threshold             | 134.2932 |
 | dot_precision                | 1.0      |
-| dot_recall                   | 0.9677   |
+| dot_recall                   | 0.9828   |
 | dot_ap                       | 1.0      |
-| manhattan_accuracy           | 0.9677   |
-| manhattan_accuracy_threshold | 585.5504 |
-| manhattan_f1                 | 0.9836   |
-| manhattan_f1_threshold       | 585.5504 |
+| manhattan_accuracy           | 0.9828   |
+| manhattan_accuracy_threshold | 644.165  |
+| manhattan_f1                 | 0.9913   |
+| manhattan_f1_threshold       | 644.165  |
 | manhattan_precision          | 1.0      |
-| manhattan_recall             | 0.9677   |
+| manhattan_recall             | 0.9828   |
 | manhattan_ap                 | 1.0      |
-| euclidean_accuracy           | 0.9677   |
-| euclidean_accuracy_threshold | 26.3433  |
-| euclidean_f1                 | 0.9836   |
-| euclidean_f1_threshold       | 26.3433  |
+| euclidean_accuracy           | 0.9828   |
+| euclidean_accuracy_threshold | 29.5429  |
+| euclidean_f1                 | 0.9913   |
+| euclidean_f1_threshold       | 29.5429  |
 | euclidean_precision          | 1.0      |
-| euclidean_recall             | 0.9677   |
+| euclidean_recall             | 0.9828   |
 | euclidean_ap                 | 1.0      |
-| max_accuracy                 | 0.9677   |
-| max_accuracy_threshold       | 585.5504 |
-| max_f1                       | 0.9836   |
-| max_f1_threshold             | 585.5504 |
+| max_accuracy                 | 0.9828   |
+| max_accuracy_threshold       | 644.165  |
+| max_f1                       | 0.9913   |
+| max_f1_threshold             | 644.165  |
 | max_precision                | 1.0      |
-| max_recall                   | 0.9677   |
+| max_recall                   | 0.9828   |
 | **max_ap**                   | **1.0**  |
 
 <!--
@@ -342,19 +342,19 @@ You can finetune this model on your own dataset.
 #### Unnamed Dataset
 
 
-* Size: 124 training samples
+* Size: 228 training samples
 * Columns: <code>text1</code>, <code>text2</code>, and <code>label</code>
 * Approximate statistics based on the first 1000 samples:
   |         | text1                                                                            | text2                                                                            | label                        |
   |:--------|:---------------------------------------------------------------------------------|:---------------------------------------------------------------------------------|:-----------------------------|
   | type    | string                                                                           | string                                                                           | int                          |
-  | details | <ul><li>min: 4 tokens</li><li>mean: 8.59 tokens</li><li>max: 14 tokens</li></ul> | <ul><li>min: 5 tokens</li><li>mean: 8.58 tokens</li><li>max: 14 tokens</li></ul> | <ul><li>1: 100.00%</li></ul> |
+  | details | <ul><li>min: 4 tokens</li><li>mean: 8.28 tokens</li><li>max: 15 tokens</li></ul> | <ul><li>min: 4 tokens</li><li>mean: 8.63 tokens</li><li>max: 14 tokens</li></ul> | <ul><li>1: 100.00%</li></ul> |
 * Samples:
-  | text1                   | text2                  | label          |
-  |:------------------------|:-----------------------|:---------------|
-  | <code>昨晩何を食べたの？</code>  | <code>昨夜何を食べたの？</code> | <code>1</code> |
-  | <code>スリッパをはいたの？</code> | <code>スリッパはいてた？</code> | <code>1</code> |
-  | <code>家の中</code>        | <code>家の中へ行こう</code>   | <code>1</code> |
+  | text1                       | text2                   | label          |
+  |:----------------------------|:------------------------|:---------------|
+  | <code>キャンドルを用意して</code>     | <code>ロウソク</code>       | <code>1</code> |
+  | <code>なんで話せるの？</code>       | <code>なんでしゃべれるの？</code> | <code>1</code> |
+  | <code>それは物の見た目を変える魔法</code> | <code>物の見た目を変える</code>  | <code>1</code> |
 * Loss: [<code>MultipleNegativesRankingLoss</code>](https://sbert.net/docs/package_reference/sentence_transformer/losses.html#multiplenegativesrankingloss) with these parameters:
   ```json
   {
@@ -368,19 +368,19 @@ You can finetune this model on your own dataset.
 #### Unnamed Dataset
 
 
-* Size: 31 evaluation samples
+* Size: 58 evaluation samples
 * Columns: <code>text1</code>, <code>text2</code>, and <code>label</code>
 * Approximate statistics based on the first 1000 samples:
   |         | text1                                                                            | text2                                                                            | label                        |
   |:--------|:---------------------------------------------------------------------------------|:---------------------------------------------------------------------------------|:-----------------------------|
   | type    | string                                                                           | string                                                                           | int                          |
-  | details | <ul><li>min: 5 tokens</li><li>mean: 8.39 tokens</li><li>max: 14 tokens</li></ul> | <ul><li>min: 4 tokens</li><li>mean: 9.06 tokens</li><li>max: 14 tokens</li></ul> | <ul><li>1: 100.00%</li></ul> |
+  | details | <ul><li>min: 4 tokens</li><li>mean: 8.33 tokens</li><li>max: 13 tokens</li></ul> | <ul><li>min: 4 tokens</li><li>mean: 8.38 tokens</li><li>max: 13 tokens</li></ul> | <ul><li>1: 100.00%</li></ul> |
 * Samples:
-  | text1                 | text2                  | label          |
-  |:----------------------|:-----------------------|:---------------|
-  | <code>花壇</code>       | <code>花壇を調べよう</code>   | <code>1</code> |
-  | <code>タイマツ要らない</code> | <code>キャンドル要らない</code> | <code>1</code> |
-  | <code>なにも要らない</code>  | <code>欲しくない</code>     | <code>1</code> |
+  | text1                       | text2                       | label          |
+  |:----------------------------|:----------------------------|:---------------|
+  | <code>雲より高くってどこ？</code>     | <code>雲より高くってなに？</code>     | <code>1</code> |
+  | <code>気にスカーフがひっかかってる</code> | <code>キにスカーフが引っかかってる</code> | <code>1</code> |
+  | <code>夕飯が辛かったから</code>      | <code>夕飯に辛いスープを飲んだから</code> | <code>1</code> |
 * Loss: [<code>MultipleNegativesRankingLoss</code>](https://sbert.net/docs/package_reference/sentence_transformer/losses.html#multiplenegativesrankingloss) with these parameters:
   ```json
   {
@@ -519,27 +519,27 @@ You can finetune this model on your own dataset.
 ### Training Logs
 | Epoch | Step | Training Loss | loss   | custom-arc-semantics-data_max_ap |
 |:-----:|:----:|:-------------:|:------:|:--------------------------------:|
-| None  | 0    | -             | -      | 1.0000                           |
-| 1.0   | 16   | 0.5617        | 0.5022 | 1.0000                           |
-| 2.0   | 32   | 0.2461        | 0.3870 | 1.0000                           |
-| 3.0   | 48   | 0.0968        | 0.3929 | 1.0000                           |
-| 4.0   | 64   | 0.0408        | 0.4012 | 1.0000                           |
-| 5.0   | 80   | 0.0151        | 0.4023 | 1.0000                           |
-| 6.0   | 96   | 0.0118        | 0.3851 | 1.0000                           |
-| 7.0   | 112  | 0.0087        | 0.3637 | 1.0000                           |
-| 8.0   | 128  | 0.0053        | 0.3662 | 1.0000                           |
-| 9.0   | 144  | 0.0046        | 0.3799 | 1.0000                           |
-| 10.0  | 160  | 0.002         | 0.3772 | 1.0000                           |
-| 11.0  | 176  | 0.0025        | 0.3765 | 1.0000                           |
-| 12.0  | 192  | 0.0021        | 0.3751 | 1.0000                           |
-| 13.0  | 208  | 0.0015        | 0.3752 | 1.0000                           |
+| None  | 0    | -             | -      | 1.0                              |
+| 1.0   | 29   | 0.6181        | 0.3774 | 1.0                              |
+| 2.0   | 58   | 0.2538        | 0.3356 | 1.0                              |
+| 3.0   | 87   | 0.063         | 0.3885 | 1.0                              |
+| 4.0   | 116  | 0.015         | 0.4536 | 1.0                              |
+| 5.0   | 145  | 0.0061        | 0.4475 | 1.0                              |
+| 6.0   | 174  | 0.002         | 0.4805 | 1.0                              |
+| 7.0   | 203  | 0.0015        | 0.4826 | 1.0                              |
+| 8.0   | 232  | 0.0012        | 0.4831 | 1.0                              |
+| 9.0   | 261  | 0.0008        | 0.4848 | 1.0                              |
+| 10.0  | 290  | 0.0006        | 0.4862 | 1.0                              |
+| 11.0  | 319  | 0.0006        | 0.4883 | 1.0                              |
+| 12.0  | 348  | 0.0007        | 0.4903 | 1.0                              |
+| 13.0  | 377  | 0.0006        | 0.4912 | 1.0                              |
 
 
 ### Framework Versions
 - Python: 3.10.14
 - Sentence Transformers: 3.0.1
 - Transformers: 4.44.2
-- PyTorch: 2.4.0+cu121
+- PyTorch: 2.4.1+cu121
 - Accelerate: 0.34.0
 - Datasets: 2.20.0
 - Tokenizers: 0.19.1

config_sentence_transformers.json

@@ -2,7 +2,7 @@
   "__version__": {
     "sentence_transformers": "3.0.1",
     "transformers": "4.44.2",
-    "pytorch": "2.4.0+cu121"
+    "pytorch": "2.4.1+cu121"
   },
   "prompts": {},
   "default_prompt_name": null,

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8fc4e45d599bf652009a700bbe34833cd60aa374b5cc54118f054d6133e99844
+oid sha256:039721c1fad0c0fa6d3c342ca79d7eb552b0005e9c34c0bcc96c0455e340a82d
 size 442491744