finetuned with additional names

README.md

@@ -6,19 +6,20 @@ tags:
 - generated_from_trainer
 - dataset_size:30415
 - loss:BinaryCrossEntropyLoss
+base_model: cross-encoder/stsb-roberta-base
 pipeline_tag: text-ranking
 library_name: sentence-transformers
 ---
 
-# CrossEncoder
+# CrossEncoder based on cross-encoder/stsb-roberta-base
 
-This is a [Cross Encoder](https://www.sbert.net/docs/cross_encoder/usage/usage.html) model trained using the [sentence-transformers](https://www.SBERT.net) library. It computes scores for pairs of texts, which can be used for text reranking and semantic search.
+This is a [Cross Encoder](https://www.sbert.net/docs/cross_encoder/usage/usage.html) model finetuned from [cross-encoder/stsb-roberta-base](https://huggingface.co/cross-encoder/stsb-roberta-base) using the [sentence-transformers](https://www.SBERT.net) library. It computes scores for pairs of texts, which can be used for text reranking and semantic search.
 
 ## Model Details
 
 ### Model Description
 - **Model Type:** Cross Encoder
-<!-- - **Base model:** [Unknown](https://huggingface.co/unknown) -->
+- **Base model:** [cross-encoder/stsb-roberta-base](https://huggingface.co/cross-encoder/stsb-roberta-base) <!-- at revision d576534b67143e2c70ee9966d7fdbf5835728d13 -->
 - **Maximum Sequence Length:** 512 tokens
 - **Number of Output Labels:** 1 label
 <!-- - **Training Dataset:** Unknown -->
@@ -50,11 +51,11 @@ from sentence_transformers import CrossEncoder
 model = CrossEncoder("foochun/bge-reranker-ft-v2")
 # Get scores for pairs of texts
 pairs = [
-    ['ruben s/o veerasamy', 'ruben a/p veerasamy'],
-    ['aravind a/l krishnamurthy', 'krishnamurthy s/o aravind'],
-    ['nazmi bin ishak', 'siti rohani binti kassim'],
-    ['lena yap zhen liang', 'liang zhen yap'],
-    ['radhika a/p krishnan', 'radhika a/p arun'],
+    ['chitra nadarajah', 'chitra a/p nadarajah'],
+    ['nik azlina binti nik din', 'norhayati binti mustafa'],
+    ['soh min pek', 'pek soh min'],
+    ['nurul hazimah binti januiddi', 'salmah binti alias'],
+    ['afiq muiz bin azman shah', 'elyana binti emrizal'],
 ]
 scores = model.predict(pairs)
 print(scores.shape)
@@ -62,13 +63,13 @@ print(scores.shape)
 
 # Or rank different texts based on similarity to a single text
 ranks = model.rank(
-    'ruben s/o veerasamy',
+    'chitra nadarajah',
     [
-        'ruben a/p veerasamy',
-        'krishnamurthy s/o aravind',
-        'siti rohani binti kassim',
-        'liang zhen yap',
-        'radhika a/p arun',
+        'chitra a/p nadarajah',
+        'norhayati binti mustafa',
+        'pek soh min',
+        'salmah binti alias',
+        'elyana binti emrizal',
     ]
 )
 # [{'corpus_id': ..., 'score': ...}, {'corpus_id': ..., 'score': ...}, ...]
@@ -119,16 +120,16 @@ You can finetune this model on your own dataset.
 * Size: 30,415 training samples
 * Columns: <code>sentence_0</code>, <code>sentence_1</code>, and <code>label</code>
 * Approximate statistics based on the first 1000 samples:
-  |         | sentence_0                                                                                     | sentence_1                                                                                    | label                                                           |
-  |:--------|:-----------------------------------------------------------------------------------------------|:----------------------------------------------------------------------------------------------|:----------------------------------------------------------------|
-  | type    | string                                                                                         | string                                                                                        | float                                                           |
-  | details | <ul><li>min: 10 characters</li><li>mean: 20.81 characters</li><li>max: 45 characters</li></ul> | <ul><li>min: 9 characters</li><li>mean: 19.08 characters</li><li>max: 46 characters</li></ul> | <ul><li>min: 0.55</li><li>mean: 0.74</li><li>max: 1.0</li></ul> |
+  |         | sentence_0                                                                                    | sentence_1                                                                                    | label                                                           |
+  |:--------|:----------------------------------------------------------------------------------------------|:----------------------------------------------------------------------------------------------|:----------------------------------------------------------------|
+  | type    | string                                                                                        | string                                                                                        | float                                                           |
+  | details | <ul><li>min: 9 characters</li><li>mean: 21.12 characters</li><li>max: 40 characters</li></ul> | <ul><li>min: 9 characters</li><li>mean: 19.14 characters</li><li>max: 40 characters</li></ul> | <ul><li>min: 0.55</li><li>mean: 0.73</li><li>max: 1.0</li></ul> |
 * Samples:
-  | sentence_0                             | sentence_1                             | label              |
-  |:---------------------------------------|:---------------------------------------|:-------------------|
-  | <code>ruben s/o veerasamy</code>       | <code>ruben a/p veerasamy</code>       | <code>0.623</code> |
-  | <code>aravind a/l krishnamurthy</code> | <code>krishnamurthy s/o aravind</code> | <code>0.55</code>  |
-  | <code>nazmi bin ishak</code>           | <code>siti rohani binti kassim</code>  | <code>0.55</code>  |
+  | sentence_0                            | sentence_1                           | label             |
+  |:--------------------------------------|:-------------------------------------|:------------------|
+  | <code>chitra nadarajah</code>         | <code>chitra a/p nadarajah</code>    | <code>0.9</code>  |
+  | <code>nik azlina binti nik din</code> | <code>norhayati binti mustafa</code> | <code>0.55</code> |
+  | <code>soh min pek</code>              | <code>pek soh min</code>             | <code>0.9</code>  |
 * Loss: [<code>BinaryCrossEntropyLoss</code>](https://sbert.net/docs/package_reference/cross_encoder/losses.html#binarycrossentropyloss) with these parameters:
   ```json
   {
@@ -143,7 +144,6 @@ You can finetune this model on your own dataset.
 - `per_device_train_batch_size`: 64
 - `per_device_eval_batch_size`: 64
 - `num_train_epochs`: 5
-- `fp16`: True
 
 #### All Hyperparameters
 <details><summary>Click to expand</summary>
@@ -187,7 +187,7 @@ You can finetune this model on your own dataset.
 - `jit_mode_eval`: False
 - `use_ipex`: False
 - `bf16`: False
-- `fp16`: True
+- `fp16`: False
 - `fp16_opt_level`: O1
 - `half_precision_backend`: auto
 - `bf16_full_eval`: False
@@ -271,19 +271,19 @@ You can finetune this model on your own dataset.
 ### Training Logs
 | Epoch  | Step | Training Loss |
 |:------:|:----:|:-------------:|
-| 1.0504 | 500  | 0.4667        |
-| 2.1008 | 1000 | 0.4669        |
-| 3.1513 | 1500 | 0.4658        |
-| 4.2017 | 2000 | 0.4664        |
+| 1.0504 | 500  | 0.4846        |
+| 2.1008 | 1000 | 0.4684        |
+| 3.1513 | 1500 | 0.4673        |
+| 4.2017 | 2000 | 0.4668        |
 
 
 ### Framework Versions
-- Python: 3.11.9
+- Python: 3.10.18
 - Sentence Transformers: 5.0.0
-- Transformers: 4.53.0
+- Transformers: 4.53.2
 - PyTorch: 2.6.0+cu124
-- Accelerate: 1.8.1
-- Datasets: 3.6.0
+- Accelerate: 1.9.0
+- Datasets: 4.0.0
 - Tokenizers: 0.21.2
 
 ## Citation

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:59a5c1e90b355682d5319edde509f646c127eea8493dcc7ff63bc13b0dc648d5
+oid sha256:a1723dd01ed39501db798471c5f74ef3924865dd965ffb858e32fbca6b5edc6a
 size 498609748