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:a6b426a1f3bcc1950784ec4666be84cea539fc2fa0059db1af22054cdbbd22be
+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:ee4a45e2a8cf5587848f22331e8b1e700a5e47a425ea87b3ffe66880405fb445
+size 9437272

README.md

@@ -5,51 +5,124 @@ tags:
 - feature-extraction
 - dense
 - generated_from_trainer
-- dataset_size:100000
+- dataset_size:359997
 - loss:MultipleNegativesRankingLoss
-base_model: prajjwal1/bert-small
+base_model: google/embeddinggemma-300m
 widget:
-- source_sentence: How do I polish my English skills?
+- source_sentence: When do you use Ms. or Mrs.? Is one for a married woman and one
+    for one that's not married? Which one is for what?
   sentences:
-  - How can we polish English skills?
-  - Why should I move to Israel as a Jew?
-  - What are vitamins responsible for?
-- source_sentence: Can I use the Kozuka Gothic Pro font as a font-face on my web site?
+  - When do you use Ms. or Mrs.? Is one for a married woman and one for one that's
+    not married? Which one is for what?
+  - Nations that do/does otherwise? Which one do I use?
+  - Why don't bikes have a gear indicator?
+- source_sentence: Which ointment is applied to the face of UFC fighters at the commencement
+    of a bout? What does it do?
   sentences:
-  - Can I use the Kozuka Gothic Pro font as a font-face on my web site?
-  - Why are Google, Facebook, YouTube and other social networking sites banned in
-    China?
-  - What font is used in Bloomberg Terminal?
-- source_sentence: Is Quora the best Q&A site?
+  - How can I save a Snapchat video that others posted?
+  - Which ointment is applied to the face of UFC fighters at the commencement of a
+    bout? What does it do?
+  - How do I get the body of a UFC Fighter?
+- source_sentence: Do you love the life you live?
   sentences:
-  - What was the best Quora question ever?
-  - Is Quora the best inquiry site?
-  - Where do I buy Oway hair products online?
-- source_sentence: How can I customize my walking speed on Google Maps?
+  - Can I do shoulder and triceps workout on same day? What other combinations like
+    this can I do?
+  - Do you love the life you're living?
+  - Where can you find an online TI-84 calculator?
+- source_sentence: Ordered food on Swiggy 3 days ago.After accepting my money, said
+    no more on Menu! When if ever will I atleast get refund in cr card a/c?
   sentences:
-  - How do I bring back Google maps icon in my home screen?
-  - How many pages are there in all the Harry Potter books combined?
-  - How can I customize my walking speed on Google Maps?
-- source_sentence: DId something exist before the Big Bang?
+  - Is getting to the Tel Aviv airport to catch a 5:30 AM flight very expensive?
+  - How do I die and make it look like an accident?
+  - Ordered food on Swiggy 3 days ago.After accepting my money, said no more on Menu!
+    When if ever will I atleast get refund in cr card a/c?
+- source_sentence: How do you earn money on Quora?
   sentences:
-  - How can I improve my memory problem?
-  - Where can I buy Fairy Tail Manga?
-  - Is there a scientific name for what existed before the Big Bang?
+  - What is a cheap healthy diet I can keep the same and eat every day?
+  - What are some things new employees should know going into their first day at Maximus?
+  - What is the best way to make money on Quora?
 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: 0.00065
+      name: Cosine Accuracy@1
+    - type: cosine_accuracy@3
+      value: 0.7986
+      name: Cosine Accuracy@3
+    - type: cosine_accuracy@5
+      value: 0.880825
+      name: Cosine Accuracy@5
+    - type: cosine_precision@1
+      value: 0.00065
+      name: Cosine Precision@1
+    - type: cosine_precision@3
+      value: 0.26619999999999994
+      name: Cosine Precision@3
+    - type: cosine_precision@5
+      value: 0.17616500000000002
+      name: Cosine Precision@5
+    - type: cosine_recall@1
+      value: 0.00065
+      name: Cosine Recall@1
+    - type: cosine_recall@3
+      value: 0.7986
+      name: Cosine Recall@3
+    - type: cosine_recall@5
+      value: 0.880825
+      name: Cosine Recall@5
+    - type: cosine_ndcg@10
+      value: 0.45147470340355694
+      name: Cosine Ndcg@10
+    - type: cosine_mrr@1
+      value: 0.00065
+      name: Cosine Mrr@1
+    - type: cosine_mrr@5
+      value: 0.288667083333407
+      name: Cosine Mrr@5
+    - type: cosine_mrr@10
+      value: 0.2951483234127803
+      name: Cosine Mrr@10
+    - type: cosine_map@100
+      value: 0.2980051496600344
+      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 +138,11 @@ 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 +161,25 @@ 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-a-baseline")
 # Run inference
-sentences = [
-    'DId something exist before the Big Bang?',
-    'Is there a scientific name for what existed before the Big Bang?',
-    'Where can I buy Fairy Tail Manga?',
+queries = [
+    "How do you earn money on Quora?",
 ]
-embeddings = model.encode(sentences)
-print(embeddings.shape)
-# [3, 512]
+documents = [
+    'What is the best way to make money on Quora?',
+    'What are some things new employees should know going into their first day at Maximus?',
+    'What is a cheap healthy diet I can keep the same and eat every day?',
+]
+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,  0.7596, -0.0398],
-#         [ 0.7596,  1.0000, -0.0308],
-#         [-0.0398, -0.0308,  1.0000]])
+# tensor([[ 0.9829, -0.0321, -0.0412]])
 ```
 
 <!--
@@ -128,6 +206,32 @@ 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  | 0.0006     |
+| cosine_accuracy@3  | 0.7986     |
+| cosine_accuracy@5  | 0.8808     |
+| cosine_precision@1 | 0.0006     |
+| cosine_precision@3 | 0.2662     |
+| cosine_precision@5 | 0.1762     |
+| cosine_recall@1    | 0.0006     |
+| cosine_recall@3    | 0.7986     |
+| cosine_recall@5    | 0.8808     |
+| **cosine_ndcg@10** | **0.4515** |
+| cosine_mrr@1       | 0.0006     |
+| cosine_mrr@5       | 0.2887     |
+| cosine_mrr@10      | 0.2951     |
+| cosine_map@100     | 0.298      |
+
 <!--
 ## Bias, Risks and Limitations
 
@@ -146,23 +250,49 @@ 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: 359,997 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: 4 tokens</li><li>mean: 15.38 tokens</li><li>max: 60 tokens</li></ul> | <ul><li>min: 4 tokens</li><li>mean: 15.48 tokens</li><li>max: 60 tokens</li></ul> | <ul><li>min: 5 tokens</li><li>mean: 16.77 tokens</li><li>max: 128 tokens</li></ul> |
+* Samples:
+  | anchor                                                                          | positive                                                                                             | negative                                                                                                                 |
+  |:--------------------------------------------------------------------------------|:-----------------------------------------------------------------------------------------------------|:-------------------------------------------------------------------------------------------------------------------------|
+  | <code>Shall I upgrade my iPhone 5s to iOS 10 final version?</code>              | <code>Should I upgrade an iPhone 5s to iOS 10?</code>                                                | <code>Whether extension of CA-articleship is to be served at same firm/company?</code>                                   |
+  | <code>Is Donald Trump really going to be the president of United States?</code> | <code>Do you think Donald Trump could conceivably be the next President of the United States?</code> | <code>Since solid carbon dioxide is dry ice and incredibly cold, why doesn't it have an effect on global warming?</code> |
+  | <code>What are real tips to improve work life balance?</code>                   | <code>What are the best ways to create a work life balance?</code>                                   | <code>How do you open a briefcase combination lock without the combination?</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                                                                         |
-  |:--------|:----------------------------------------------------------------------------------|:---------------------------------------------------------------------------------|:-----------------------------------------------------------------------------------|
-  | type    | string                                                                            | string                                                                           | string                                                                             |
-  | details | <ul><li>min: 3 tokens</li><li>mean: 15.53 tokens</li><li>max: 59 tokens</li></ul> | <ul><li>min: 3 tokens</li><li>mean: 15.5 tokens</li><li>max: 59 tokens</li></ul> | <ul><li>min: 6 tokens</li><li>mean: 16.87 tokens</li><li>max: 128 tokens</li></ul> |
+  |         | anchor                                                                            | positive                                                                          | negative                                                                          |
+  |:--------|:----------------------------------------------------------------------------------|:----------------------------------------------------------------------------------|:----------------------------------------------------------------------------------|
+  | type    | string                                                                            | string                                                                            | string                                                                            |
+  | details | <ul><li>min: 6 tokens</li><li>mean: 15.61 tokens</li><li>max: 70 tokens</li></ul> | <ul><li>min: 6 tokens</li><li>mean: 15.66 tokens</li><li>max: 70 tokens</li></ul> | <ul><li>min: 6 tokens</li><li>mean: 16.81 tokens</li><li>max: 77 tokens</li></ul> |
 * Samples:
-  | sentence_0                                                                              | sentence_1                                                                              | sentence_2                                                             |
-  |:----------------------------------------------------------------------------------------|:----------------------------------------------------------------------------------------|:-----------------------------------------------------------------------|
-  | <code>Is there visitor entry facility in Jaipur airport. How much is the ticket?</code> | <code>Is there visitor entry facility in Jaipur airport. How much is the ticket?</code> | <code>How much is the airport tax in bogota?</code>                    |
-  | <code>Which concept is more important: good planning or hard work?</code>               | <code>Which concept is more important: good planning or hard work?</code>               | <code>What is important in life: luck or hard work?</code>             |
-  | <code>What is the most efficient way to make money?</code>                              | <code>How can I make my money make money?</code>                                        | <code>What can one learn about Quantum Mechanics in 10 minutes?</code> |
+  | anchor                                                                                                            | positive                                                                                                          | negative                                                                                                                                  |
+  |:------------------------------------------------------------------------------------------------------------------|:------------------------------------------------------------------------------------------------------------------|:------------------------------------------------------------------------------------------------------------------------------------------|
+  | <code>Why were feathered dinosaur fossils only found in the last 20 years?</code>                                 | <code>Why were feathered dinosaur fossils only found in the last 20 years?</code>                                 | <code>Why are only few people aware that many dinosaurs had feathers?</code>                                                              |
+  | <code>If FOX News is the conservative news station, which cable news network is for liberals/progressives?</code> | <code>If FOX News is the conservative news station, which cable news network is for liberals/progressives?</code> | <code>How much did Fox News and conservative leaning media networks stoke the anger that contributed to Donald Trump's popularity?</code> |
+  | <code>How can guys last longer during sex?</code>                                                                 | <code>How do I last longer in sex?</code>                                                                         | <code>What is a permanent solution for rough and puffy hair?</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 +301,30 @@ 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-a-baseline
+- `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 +333,17 @@ 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 +371,14 @@ 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 +388,23 @@ 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-a-baseline
 - `hub_strategy`: every_save
 - `hub_private_repo`: None
 - `hub_always_push`: False
@@ -288,31 +431,43 @@ 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  | 0.2284        |
-| 0.6398 | 1000 | 0.0571        |
-| 0.9597 | 1500 | 0.0486        |
-| 1.2796 | 2000 | 0.0378        |
-| 1.5995 | 2500 | 0.0367        |
-| 1.9194 | 3000 | 0.0338        |
-| 2.2393 | 3500 | 0.0327        |
-| 2.5592 | 4000 | 0.0285        |
-| 2.8791 | 4500 | 0.0285        |
+| Epoch  | Step | Training Loss | Validation Loss | val_cosine_ndcg@10 |
+|:------:|:----:|:-------------:|:---------------:|:------------------:|
+| 0      | 0    | -             | 0.9732          | 0.8903             |
+| 0.0445 | 250  | 0.3014        | 0.2430          | 0.8863             |
+| 0.0889 | 500  | 0.2442        | 0.2489          | 0.8875             |
+| 0.1334 | 750  | 0.2504        | nan             | 0.0293             |
+| 0.1778 | 1000 | 0.2492        | nan             | 0.8871             |
+| 0.2223 | 1250 | 0.2676        | nan             | 0.4514             |
+| 0.2667 | 1500 | 0.2804        | nan             | 0.4514             |
+| 0.3112 | 1750 | 0.2782        | nan             | 0.4514             |
+| 0.3556 | 2000 | 0.28          | nan             | 0.4515             |
+| 0.4001 | 2250 | 0.2814        | nan             | 0.4515             |
+| 0.4445 | 2500 | 0.2758        | nan             | 0.4515             |
+| 0.4890 | 2750 | 0.2792        | nan             | 0.4515             |
+| 0.5334 | 3000 | 0.2807        | nan             | 0.4515             |
+| 0.5779 | 3250 | 0.282         | nan             | 0.4515             |
+| 0.6223 | 3500 | 0.2785        | nan             | 0.4515             |
+| 0.6668 | 3750 | 0.28          | nan             | 0.4515             |
+| 0.7112 | 4000 | 0.2813        | nan             | 0.4515             |
+| 0.7557 | 4250 | 0.2823        | nan             | 0.4515             |
+| 0.8001 | 4500 | 0.2791        | nan             | 0.4515             |
+| 0.8446 | 4750 | 0.2789        | nan             | 0.4515             |
+| 0.8890 | 5000 | 0.282         | nan             | 0.4515             |
 
 
 ### 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"
   }
 ]