Add new SentenceTransformer model

1_Pooling/config.json

@@ -1,7 +1,7 @@
 {
-    "word_embedding_dimension": 512,
-    "pooling_mode_cls_token": true,
-    "pooling_mode_mean_tokens": false,
+    "word_embedding_dimension": 768,
+    "pooling_mode_cls_token": false,
+    "pooling_mode_mean_tokens": true,
     "pooling_mode_max_tokens": false,
     "pooling_mode_mean_sqrt_len_tokens": false,
     "pooling_mode_weightedmean_tokens": false,

2_Dense/config.json

@@ -0,0 +1,6 @@
+{
+    "in_features": 768,
+    "out_features": 3072,
+    "bias": false,
+    "activation_function": "torch.nn.modules.linear.Identity"
+}

2_Dense/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3d2aa8f88c6a0e99a33e1795c480e6cedd06cfca13afd579a3eba0c79371db12
+size 9437272

3_Dense/config.json

@@ -0,0 +1,6 @@
+{
+    "in_features": 3072,
+    "out_features": 768,
+    "bias": false,
+    "activation_function": "torch.nn.modules.linear.Identity"
+}

3_Dense/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:db522a8aa84c6b3d2bb1fb8bd7d8828e0f58bf897fcebcd331065e233a3b545c
+size 9437272

README.md

@@ -5,51 +5,123 @@ tags:
 - feature-extraction
 - dense
 - generated_from_trainer
-- dataset_size:100000
+- dataset_size:713743
 - loss:MultipleNegativesRankingLoss
-base_model: prajjwal1/bert-small
+base_model: google/embeddinggemma-300m
 widget:
-- source_sentence: How do I calculate IQ?
+- source_sentence: 'Abraham Lincoln: Why is the Gettysburg Address so memorable?'
   sentences:
-  - What is the easiest way to know my IQ?
-  - How do I calculate not IQ ?
-  - What are some creative and innovative business ideas with less investment in India?
-- source_sentence: How can I learn martial arts in my home?
+  - 'Abraham Lincoln: Why is the Gettysburg Address so memorable?'
+  - What does the Gettysburg Address really mean?
+  - What is eatalo.com?
+- source_sentence: Has the influence of Ancient Carthage in science, math, and society
+    been underestimated?
   sentences:
-  - How can I learn martial arts by myself?
-  - What are the advantages and disadvantages of investing in gold?
-  - Can people see that I have looked at their pictures on instagram if I am not following
-    them?
-- source_sentence: When Enterprise picks you up do you have to take them back?
+  - How does one earn money online without an investment from home?
+  - Has the influence of Ancient Carthage in science, math, and society been underestimated?
+  - Has the influence of the Ancient Etruscans in science and math been underestimated?
+- source_sentence: Is there any app that shares charging to others like share it how
+    we transfer files?
   sentences:
-  - Are there any software Training institute in Tuticorin?
-  - When Enterprise picks you up do you have to take them back?
-  - When Enterprise picks you up do them have to take youback?
-- source_sentence: What are some non-capital goods?
+  - How do you think of Chinese claims that the present Private Arbitration is illegal,
+    its verdict violates the UNCLOS and is illegal?
+  - Is there any app that shares charging to others like share it how we transfer
+    files?
+  - Are there any platforms that provides end-to-end encryption for file transfer/
+    sharing?
+- source_sentence: Why AAP’s MLA Dinesh Mohaniya has been arrested?
   sentences:
-  - What are capital goods?
-  - How is the value of [math]\pi[/math] calculated?
-  - What are some non-capital goods?
-- source_sentence: What is the QuickBooks technical support phone number in New York?
+  - What are your views on the latest sex scandal by AAP MLA Sandeep Kumar?
+  - What is a dc current? What are some examples?
+  - Why AAP’s MLA Dinesh Mohaniya has been arrested?
+- source_sentence: What is the difference between economic growth and economic development?
   sentences:
-  - What caused the Great Depression?
-  - Can I apply for PR in Canada?
-  - Which is the best QuickBooks Hosting Support Number in New York?
+  - How cold can the Gobi Desert get, and how do its average temperatures compare
+    to the ones in the Simpson Desert?
+  - the difference between economic growth and economic development is What?
+  - What is the difference between economic growth and economic development?
 pipeline_tag: sentence-similarity
 library_name: sentence-transformers
+metrics:
+- cosine_accuracy@1
+- cosine_accuracy@3
+- cosine_accuracy@5
+- cosine_precision@1
+- cosine_precision@3
+- cosine_precision@5
+- cosine_recall@1
+- cosine_recall@3
+- cosine_recall@5
+- cosine_ndcg@10
+- cosine_mrr@1
+- cosine_mrr@5
+- cosine_mrr@10
+- cosine_map@100
+model-index:
+- name: SentenceTransformer based on google/embeddinggemma-300m
+  results:
+  - task:
+      type: information-retrieval
+      name: Information Retrieval
+    dataset:
+      name: val
+      type: val
+    metrics:
+    - type: cosine_accuracy@1
+      value: 0.0
+      name: Cosine Accuracy@1
+    - type: cosine_accuracy@3
+      value: 0.0
+      name: Cosine Accuracy@3
+    - type: cosine_accuracy@5
+      value: 2.5e-05
+      name: Cosine Accuracy@5
+    - type: cosine_precision@1
+      value: 0.0
+      name: Cosine Precision@1
+    - type: cosine_precision@3
+      value: 0.0
+      name: Cosine Precision@3
+    - type: cosine_precision@5
+      value: 5.0e-06
+      name: Cosine Precision@5
+    - type: cosine_recall@1
+      value: 0.0
+      name: Cosine Recall@1
+    - type: cosine_recall@3
+      value: 0.0
+      name: Cosine Recall@3
+    - type: cosine_recall@5
+      value: 2.5e-05
+      name: Cosine Recall@5
+    - type: cosine_ndcg@10
+      value: 4.0643645983386815e-05
+      name: Cosine Ndcg@10
+    - type: cosine_mrr@1
+      value: 0.0
+      name: Cosine Mrr@1
+    - type: cosine_mrr@5
+      value: 5.0e-06
+      name: Cosine Mrr@5
+    - type: cosine_mrr@10
+      value: 1.697420634920635e-05
+      name: Cosine Mrr@10
+    - type: cosine_map@100
+      value: 5.219463554638405e-05
+      name: Cosine Map@100
 ---
 
-# SentenceTransformer based on prajjwal1/bert-small
+# SentenceTransformer based on google/embeddinggemma-300m
 
-This is a [sentence-transformers](https://www.SBERT.net) model finetuned from [prajjwal1/bert-small](https://huggingface.co/prajjwal1/bert-small). It maps sentences & paragraphs to a 512-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 [google/embeddinggemma-300m](https://huggingface.co/google/embeddinggemma-300m). It maps sentences & paragraphs to a 768-dimensional dense vector space and can be used for semantic textual similarity, semantic search, paraphrase mining, text classification, clustering, and more.
 
 ## Model Details
 
 ### Model Description
 - **Model Type:** Sentence Transformer
-- **Base model:** [prajjwal1/bert-small](https://huggingface.co/prajjwal1/bert-small) <!-- at revision 0ec5f86f27c1a77d704439db5e01c307ea11b9d4 -->
+- **Base model:** [google/embeddinggemma-300m](https://huggingface.co/google/embeddinggemma-300m) <!-- at revision 57c266a740f537b4dc058e1b0cda161fd15afa75 -->
 - **Maximum Sequence Length:** 128 tokens
-- **Output Dimensionality:** 512 dimensions
+- **Output Dimensionality:** 768 dimensions
 - **Similarity Function:** Cosine Similarity
 <!-- - **Training Dataset:** Unknown -->
 <!-- - **Language:** Unknown -->
@@ -65,8 +137,11 @@ This is a [sentence-transformers](https://www.SBERT.net) model finetuned from [p
 
 ```
 SentenceTransformer(
-  (0): Transformer({'max_seq_length': 128, 'do_lower_case': False, 'architecture': 'BertModel'})
-  (1): Pooling({'word_embedding_dimension': 512, 'pooling_mode_cls_token': True, 'pooling_mode_mean_tokens': False, 'pooling_mode_max_tokens': False, 'pooling_mode_mean_sqrt_len_tokens': False, 'pooling_mode_weightedmean_tokens': False, 'pooling_mode_lasttoken': False, 'include_prompt': True})
+  (0): Transformer({'max_seq_length': 128, 'do_lower_case': False, 'architecture': 'Gemma3TextModel'})
+  (1): Pooling({'word_embedding_dimension': 768, 'pooling_mode_cls_token': False, 'pooling_mode_mean_tokens': True, 'pooling_mode_max_tokens': False, 'pooling_mode_mean_sqrt_len_tokens': False, 'pooling_mode_weightedmean_tokens': False, 'pooling_mode_lasttoken': False, 'include_prompt': True})
+  (2): Dense({'in_features': 768, 'out_features': 3072, 'bias': False, 'activation_function': 'torch.nn.modules.linear.Identity'})
+  (3): Dense({'in_features': 3072, 'out_features': 768, 'bias': False, 'activation_function': 'torch.nn.modules.linear.Identity'})
+  (4): Normalize()
 )
 ```
 
@@ -85,23 +160,25 @@ Then you can load this model and run inference.
 from sentence_transformers import SentenceTransformer
 
 # Download from the 🤗 Hub
-model = SentenceTransformer("sentence_transformers_model_id")
+model = SentenceTransformer("redis/model-b-structured")
 # Run inference
-sentences = [
-    'What is the QuickBooks technical support phone number in New York?',
-    'Which is the best QuickBooks Hosting Support Number in New York?',
-    'Can I apply for PR in Canada?',
+queries = [
+    "What is the difference between economic growth and economic development?",
 ]
-embeddings = model.encode(sentences)
-print(embeddings.shape)
-# [3, 512]
+documents = [
+    'What is the difference between economic growth and economic development?',
+    'the difference between economic growth and economic development is What?',
+    'How cold can the Gobi Desert get, and how do its average temperatures compare to the ones in the Simpson Desert?',
+]
+query_embeddings = model.encode_query(queries)
+document_embeddings = model.encode_document(documents)
+print(query_embeddings.shape, document_embeddings.shape)
+# [1, 768] [3, 768]
 
 # Get the similarity scores for the embeddings
-similarities = model.similarity(embeddings, embeddings)
+similarities = model.similarity(query_embeddings, document_embeddings)
 print(similarities)
-# tensor([[1.0000, 0.8563, 0.0594],
-#         [0.8563, 1.0000, 0.1245],
-#         [0.0594, 0.1245, 1.0000]])
+# tensor([[nan, nan, nan]])
 ```
 
 <!--
@@ -128,6 +205,32 @@ You can finetune this model on your own dataset.
 *List how the model may foreseeably be misused and address what users ought not to do with the model.*
 -->
 
+## Evaluation
+
+### Metrics
+
+#### Information Retrieval
+
+* Dataset: `val`
+* Evaluated with [<code>InformationRetrievalEvaluator</code>](https://sbert.net/docs/package_reference/sentence_transformer/evaluation.html#sentence_transformers.evaluation.InformationRetrievalEvaluator)
+
+| Metric             | Value   |
+|:-------------------|:--------|
+| cosine_accuracy@1  | 0.0     |
+| cosine_accuracy@3  | 0.0     |
+| cosine_accuracy@5  | 0.0     |
+| cosine_precision@1 | 0.0     |
+| cosine_precision@3 | 0.0     |
+| cosine_precision@5 | 0.0     |
+| cosine_recall@1    | 0.0     |
+| cosine_recall@3    | 0.0     |
+| cosine_recall@5    | 0.0     |
+| **cosine_ndcg@10** | **0.0** |
+| cosine_mrr@1       | 0.0     |
+| cosine_mrr@5       | 0.0     |
+| cosine_mrr@10      | 0.0     |
+| cosine_map@100     | 0.0001  |
+
 <!--
 ## Bias, Risks and Limitations
 
@@ -146,23 +249,49 @@ You can finetune this model on your own dataset.
 
 #### Unnamed Dataset
 
-* Size: 100,000 training samples
-* Columns: <code>sentence_0</code>, <code>sentence_1</code>, and <code>sentence_2</code>
+* Size: 713,743 training samples
+* Columns: <code>anchor</code>, <code>positive</code>, and <code>negative</code>
+* Approximate statistics based on the first 1000 samples:
+  |         | anchor                                                                           | positive                                                                          | negative                                                                          |
+  |:--------|:---------------------------------------------------------------------------------|:----------------------------------------------------------------------------------|:----------------------------------------------------------------------------------|
+  | type    | string                                                                           | string                                                                            | string                                                                            |
+  | details | <ul><li>min: 6 tokens</li><li>mean: 15.9 tokens</li><li>max: 63 tokens</li></ul> | <ul><li>min: 6 tokens</li><li>mean: 15.86 tokens</li><li>max: 63 tokens</li></ul> | <ul><li>min: 6 tokens</li><li>mean: 16.63 tokens</li><li>max: 61 tokens</li></ul> |
+* Samples:
+  | anchor                                                                         | positive                                                                              | negative                                                                                                          |
+  |:-------------------------------------------------------------------------------|:--------------------------------------------------------------------------------------|:------------------------------------------------------------------------------------------------------------------|
+  | <code>Which one is better Linux OS? Ubuntu or Mint?</code>                     | <code>Why do you use Linux Mint?</code>                                               | <code>Which one is not better Linux OS ? Ubuntu or Mint ?</code>                                                  |
+  | <code>What is flow?</code>                                                     | <code>What is flow?</code>                                                            | <code>What are flow lines?</code>                                                                                 |
+  | <code>How is Trump planning to get Mexico to pay for his supposed wall?</code> | <code>How is it possible for Donald Trump to force Mexico to pay for the wall?</code> | <code>Why do we connect the positive terminal before the negative terminal to ground in a vehicle battery?</code> |
+* Loss: [<code>MultipleNegativesRankingLoss</code>](https://sbert.net/docs/package_reference/sentence_transformer/losses.html#multiplenegativesrankingloss) with these parameters:
+  ```json
+  {
+      "scale": 7.0,
+      "similarity_fct": "cos_sim",
+      "gather_across_devices": false
+  }
+  ```
+
+### Evaluation Dataset
+
+#### Unnamed Dataset
+
+* Size: 40,000 evaluation samples
+* Columns: <code>anchor</code>, <code>positive</code>, and <code>negative</code>
 * Approximate statistics based on the first 1000 samples:
-  |         | sentence_0                                                                        | sentence_1                                                                        | sentence_2                                                                        |
+  |         | anchor                                                                            | positive                                                                          | negative                                                                          |
   |:--------|:----------------------------------------------------------------------------------|:----------------------------------------------------------------------------------|:----------------------------------------------------------------------------------|
   | type    | string                                                                            | string                                                                            | string                                                                            |
-  | details | <ul><li>min: 6 tokens</li><li>mean: 15.79 tokens</li><li>max: 66 tokens</li></ul> | <ul><li>min: 6 tokens</li><li>mean: 15.68 tokens</li><li>max: 66 tokens</li></ul> | <ul><li>min: 7 tokens</li><li>mean: 16.37 tokens</li><li>max: 67 tokens</li></ul> |
+  | details | <ul><li>min: 6 tokens</li><li>mean: 15.38 tokens</li><li>max: 75 tokens</li></ul> | <ul><li>min: 6 tokens</li><li>mean: 15.39 tokens</li><li>max: 75 tokens</li></ul> | <ul><li>min: 6 tokens</li><li>mean: 16.58 tokens</li><li>max: 68 tokens</li></ul> |
 * Samples:
-  | sentence_0                                                       | sentence_1                                                       | sentence_2                                                                        |
-  |:-----------------------------------------------------------------|:-----------------------------------------------------------------|:----------------------------------------------------------------------------------|
-  | <code>Is masturbating bad for boys?</code>                       | <code>Is masturbating bad for boys?</code>                       | <code>How harmful or unhealthy is masturbation?</code>                            |
-  | <code>Does a train engine move in reverse?</code>                | <code>Does a train engine move in reverse?</code>                | <code>Time moves forward, not in reverse. Doesn't that make time a vector?</code> |
-  | <code>What is the most badass thing anyone has ever done?</code> | <code>What is the most badass thing anyone has ever done?</code> | <code>anyone is the most badass thing Whathas ever done?</code>                   |
+  | anchor                                                                                                                                                       | positive                                                                                                                                                     | negative                                                                                                                                                            |
+  |:-------------------------------------------------------------------------------------------------------------------------------------------------------------|:-------------------------------------------------------------------------------------------------------------------------------------------------------------|:--------------------------------------------------------------------------------------------------------------------------------------------------------------------|
+  | <code>Why are all my questions on Quora marked needing improvement?</code>                                                                                   | <code>Why are all my questions immediately being marked as needing improvement?</code>                                                                       | <code>For a post-graduate student in IIT, is it allowed to take an external scholarship as a top-up to his/her MHRD assistantship?</code>                           |
+  | <code>Can blue butter fly needle with vaccum tube be reused? Is it HIV risk? . Heard the needle is too small to be reused . Had blood draw at clinic?</code> | <code>Can blue butter fly needle with vaccum tube be reused? Is it HIV risk? . Heard the needle is too small to be reused . Had blood draw at clinic?</code> | <code>Can blue butter fly needle with vaccum tube be reused not ? Is it HIV risk ? . Heard the needle is too small to be reused . Had blood draw at clinic ?</code> |
+  | <code>Why do people still believe the world is flat?</code>                                                                                                  | <code>Why are there still people who believe the world is flat?</code>                                                                                       | <code>I'm not able to buy Udemy course .it is not accepting mine and my friends debit card.my card can be used for Flipkart .how to purchase now?</code>            |
 * Loss: [<code>MultipleNegativesRankingLoss</code>](https://sbert.net/docs/package_reference/sentence_transformer/losses.html#multiplenegativesrankingloss) with these parameters:
   ```json
   {
-      "scale": 20.0,
+      "scale": 7.0,
       "similarity_fct": "cos_sim",
       "gather_across_devices": false
   }
@@ -171,17 +300,30 @@ You can finetune this model on your own dataset.
 ### Training Hyperparameters
 #### Non-Default Hyperparameters
 
+- `eval_strategy`: steps
 - `per_device_train_batch_size`: 64
 - `per_device_eval_batch_size`: 64
+- `learning_rate`: 2e-05
+- `weight_decay`: 0.0001
+- `max_steps`: 5000
+- `warmup_ratio`: 0.1
 - `fp16`: True
-- `multi_dataset_batch_sampler`: round_robin
+- `dataloader_drop_last`: True
+- `dataloader_num_workers`: 1
+- `dataloader_prefetch_factor`: 1
+- `load_best_model_at_end`: True
+- `optim`: adamw_torch
+- `ddp_find_unused_parameters`: False
+- `push_to_hub`: True
+- `hub_model_id`: redis/model-b-structured
+- `eval_on_start`: True
 
 #### All Hyperparameters
 <details><summary>Click to expand</summary>
 
 - `overwrite_output_dir`: False
 - `do_predict`: False
-- `eval_strategy`: no
+- `eval_strategy`: steps
 - `prediction_loss_only`: True
 - `per_device_train_batch_size`: 64
 - `per_device_eval_batch_size`: 64
@@ -190,17 +332,17 @@ You can finetune this model on your own dataset.
 - `gradient_accumulation_steps`: 1
 - `eval_accumulation_steps`: None
 - `torch_empty_cache_steps`: None
-- `learning_rate`: 5e-05
-- `weight_decay`: 0.0
+- `learning_rate`: 2e-05
+- `weight_decay`: 0.0001
 - `adam_beta1`: 0.9
 - `adam_beta2`: 0.999
 - `adam_epsilon`: 1e-08
-- `max_grad_norm`: 1
-- `num_train_epochs`: 3
-- `max_steps`: -1
+- `max_grad_norm`: 1.0
+- `num_train_epochs`: 3.0
+- `max_steps`: 5000
 - `lr_scheduler_type`: linear
 - `lr_scheduler_kwargs`: {}
-- `warmup_ratio`: 0.0
+- `warmup_ratio`: 0.1
 - `warmup_steps`: 0
 - `log_level`: passive
 - `log_level_replica`: warning
@@ -228,14 +370,14 @@ You can finetune this model on your own dataset.
 - `tpu_num_cores`: None
 - `tpu_metrics_debug`: False
 - `debug`: []
-- `dataloader_drop_last`: False
-- `dataloader_num_workers`: 0
-- `dataloader_prefetch_factor`: None
+- `dataloader_drop_last`: True
+- `dataloader_num_workers`: 1
+- `dataloader_prefetch_factor`: 1
 - `past_index`: -1
 - `disable_tqdm`: False
 - `remove_unused_columns`: True
 - `label_names`: None
-- `load_best_model_at_end`: False
+- `load_best_model_at_end`: True
 - `ignore_data_skip`: False
 - `fsdp`: []
 - `fsdp_min_num_params`: 0
@@ -245,23 +387,23 @@ You can finetune this model on your own dataset.
 - `parallelism_config`: None
 - `deepspeed`: None
 - `label_smoothing_factor`: 0.0
-- `optim`: adamw_torch_fused
+- `optim`: adamw_torch
 - `optim_args`: None
 - `adafactor`: False
 - `group_by_length`: False
 - `length_column_name`: length
 - `project`: huggingface
 - `trackio_space_id`: trackio
-- `ddp_find_unused_parameters`: None
+- `ddp_find_unused_parameters`: False
 - `ddp_bucket_cap_mb`: None
 - `ddp_broadcast_buffers`: False
 - `dataloader_pin_memory`: True
 - `dataloader_persistent_workers`: False
 - `skip_memory_metrics`: True
 - `use_legacy_prediction_loop`: False
-- `push_to_hub`: False
+- `push_to_hub`: True
 - `resume_from_checkpoint`: None
-- `hub_model_id`: None
+- `hub_model_id`: redis/model-b-structured
 - `hub_strategy`: every_save
 - `hub_private_repo`: None
 - `hub_always_push`: False
@@ -288,31 +430,43 @@ You can finetune this model on your own dataset.
 - `neftune_noise_alpha`: None
 - `optim_target_modules`: None
 - `batch_eval_metrics`: False
-- `eval_on_start`: False
+- `eval_on_start`: True
 - `use_liger_kernel`: False
 - `liger_kernel_config`: None
 - `eval_use_gather_object`: False
 - `average_tokens_across_devices`: True
 - `prompts`: None
 - `batch_sampler`: batch_sampler
-- `multi_dataset_batch_sampler`: round_robin
+- `multi_dataset_batch_sampler`: proportional
 - `router_mapping`: {}
 - `learning_rate_mapping`: {}
 
 </details>
 
 ### Training Logs
-| Epoch  | Step | Training Loss |
-|:------:|:----:|:-------------:|
-| 0.3199 | 500  | 0.4294        |
-| 0.6398 | 1000 | 0.1268        |
-| 0.9597 | 1500 | 0.1           |
-| 1.2796 | 2000 | 0.0792        |
-| 1.5995 | 2500 | 0.0706        |
-| 1.9194 | 3000 | 0.0687        |
-| 2.2393 | 3500 | 0.0584        |
-| 2.5592 | 4000 | 0.057         |
-| 2.8791 | 4500 | 0.0581        |
+| Epoch  | Step | Training Loss | Validation Loss | val_cosine_ndcg@10 |
+|:------:|:----:|:-------------:|:---------------:|:------------------:|
+| 0      | 0    | -             | 1.1196          | 0.8084             |
+| 0.0224 | 250  | 0.3432        | 0.2247          | 0.8873             |
+| 0.0448 | 500  | 0.2279        | 0.2306          | 0.8821             |
+| 0.0673 | 750  | 0.2253        | 0.2339          | 0.8802             |
+| 0.0897 | 1000 | 0.2231        | 0.2147          | 0.8882             |
+| 0.1121 | 1250 | 0.2091        | 0.2115          | 0.8881             |
+| 0.1345 | 1500 | 0.2145        | 0.2059          | 0.8886             |
+| 0.1569 | 1750 | 0.2049        | 0.2025          | 0.8910             |
+| 0.1793 | 2000 | 0.2066        | nan             | 0.0346             |
+| 0.2018 | 2250 | 0.2012        | 0.2087          | 0.8929             |
+| 0.2242 | 2500 | 0.2175        | 0.2187          | 0.8960             |
+| 0.2466 | 2750 | 0.2311        | nan             | 0.2274             |
+| 0.2690 | 3000 | 0.2477        | nan             | 0.1686             |
+| 0.2914 | 3250 | 0.2484        | nan             | 0.1686             |
+| 0.3138 | 3500 | 0.253         | nan             | 0.1686             |
+| 0.3363 | 3750 | 0.249         | nan             | 0.1686             |
+| 0.3587 | 4000 | 0.2524        | nan             | 0.1686             |
+| 0.3811 | 4250 | 0.2502        | nan             | 0.0000             |
+| 0.4035 | 4500 | 0.0           | nan             | 0.0000             |
+| 0.4259 | 4750 | 0.0           | nan             | 0.0000             |
+| 0.4484 | 5000 | 0.0           | nan             | 0.0000             |
 
 
 ### Framework Versions

config_sentence_transformers.json

@@ -6,8 +6,20 @@
     "pytorch": "2.9.1+cu128"
   },
   "prompts": {
-    "query": "",
-    "document": ""
+    "query": "task: search result | query: ",
+    "document": "title: none | text: ",
+    "BitextMining": "task: search result | query: ",
+    "Clustering": "task: clustering | query: ",
+    "Classification": "task: classification | query: ",
+    "InstructionRetrieval": "task: code retrieval | query: ",
+    "MultilabelClassification": "task: classification | query: ",
+    "PairClassification": "task: sentence similarity | query: ",
+    "Reranking": "task: search result | query: ",
+    "Retrieval": "task: search result | query: ",
+    "Retrieval-query": "task: search result | query: ",
+    "Retrieval-document": "title: none | text: ",
+    "STS": "task: sentence similarity | query: ",
+    "Summarization": "task: summarization | query: "
   },
   "default_prompt_name": null,
   "similarity_fn_name": "cosine"

modules.json

@@ -10,5 +10,23 @@
     "name": "1",
     "path": "1_Pooling",
     "type": "sentence_transformers.models.Pooling"
+  },
+  {
+    "idx": 2,
+    "name": "2",
+    "path": "2_Dense",
+    "type": "sentence_transformers.models.Dense"
+  },
+  {
+    "idx": 3,
+    "name": "3",
+    "path": "3_Dense",
+    "type": "sentence_transformers.models.Dense"
+  },
+  {
+    "idx": 4,
+    "name": "4",
+    "path": "4_Normalize",
+    "type": "sentence_transformers.models.Normalize"
   }
 ]