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": 384,
+    "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,

README.md

@@ -5,51 +5,231 @@ tags:
 - feature-extraction
 - dense
 - generated_from_trainer
-- dataset_size:100000
+- dataset_size:713743
 - loss:MultipleNegativesRankingLoss
-base_model: prajjwal1/bert-small
+base_model: thenlper/gte-small
 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_accuracy@10
+- cosine_precision@1
+- cosine_precision@3
+- cosine_precision@5
+- cosine_precision@10
+- cosine_recall@1
+- cosine_recall@3
+- cosine_recall@5
+- cosine_recall@10
+- cosine_ndcg@10
+- cosine_mrr@10
+- cosine_map@100
+model-index:
+- name: SentenceTransformer based on thenlper/gte-small
+  results:
+  - task:
+      type: information-retrieval
+      name: Information Retrieval
+    dataset:
+      name: NanoMSMARCO
+      type: NanoMSMARCO
+    metrics:
+    - type: cosine_accuracy@1
+      value: 0.28
+      name: Cosine Accuracy@1
+    - type: cosine_accuracy@3
+      value: 0.58
+      name: Cosine Accuracy@3
+    - type: cosine_accuracy@5
+      value: 0.64
+      name: Cosine Accuracy@5
+    - type: cosine_accuracy@10
+      value: 0.72
+      name: Cosine Accuracy@10
+    - type: cosine_precision@1
+      value: 0.28
+      name: Cosine Precision@1
+    - type: cosine_precision@3
+      value: 0.19333333333333333
+      name: Cosine Precision@3
+    - type: cosine_precision@5
+      value: 0.128
+      name: Cosine Precision@5
+    - type: cosine_precision@10
+      value: 0.07200000000000001
+      name: Cosine Precision@10
+    - type: cosine_recall@1
+      value: 0.28
+      name: Cosine Recall@1
+    - type: cosine_recall@3
+      value: 0.58
+      name: Cosine Recall@3
+    - type: cosine_recall@5
+      value: 0.64
+      name: Cosine Recall@5
+    - type: cosine_recall@10
+      value: 0.72
+      name: Cosine Recall@10
+    - type: cosine_ndcg@10
+      value: 0.5075011853031293
+      name: Cosine Ndcg@10
+    - type: cosine_mrr@10
+      value: 0.4386111111111111
+      name: Cosine Mrr@10
+    - type: cosine_map@100
+      value: 0.4533366047009664
+      name: Cosine Map@100
+  - task:
+      type: information-retrieval
+      name: Information Retrieval
+    dataset:
+      name: NanoNQ
+      type: NanoNQ
+    metrics:
+    - type: cosine_accuracy@1
+      value: 0.32
+      name: Cosine Accuracy@1
+    - type: cosine_accuracy@3
+      value: 0.54
+      name: Cosine Accuracy@3
+    - type: cosine_accuracy@5
+      value: 0.6
+      name: Cosine Accuracy@5
+    - type: cosine_accuracy@10
+      value: 0.66
+      name: Cosine Accuracy@10
+    - type: cosine_precision@1
+      value: 0.32
+      name: Cosine Precision@1
+    - type: cosine_precision@3
+      value: 0.18666666666666665
+      name: Cosine Precision@3
+    - type: cosine_precision@5
+      value: 0.128
+      name: Cosine Precision@5
+    - type: cosine_precision@10
+      value: 0.07
+      name: Cosine Precision@10
+    - type: cosine_recall@1
+      value: 0.3
+      name: Cosine Recall@1
+    - type: cosine_recall@3
+      value: 0.51
+      name: Cosine Recall@3
+    - type: cosine_recall@5
+      value: 0.58
+      name: Cosine Recall@5
+    - type: cosine_recall@10
+      value: 0.64
+      name: Cosine Recall@10
+    - type: cosine_ndcg@10
+      value: 0.48687028758380874
+      name: Cosine Ndcg@10
+    - type: cosine_mrr@10
+      value: 0.4465
+      name: Cosine Mrr@10
+    - type: cosine_map@100
+      value: 0.44172587957864395
+      name: Cosine Map@100
+  - task:
+      type: nano-beir
+      name: Nano BEIR
+    dataset:
+      name: NanoBEIR mean
+      type: NanoBEIR_mean
+    metrics:
+    - type: cosine_accuracy@1
+      value: 0.30000000000000004
+      name: Cosine Accuracy@1
+    - type: cosine_accuracy@3
+      value: 0.56
+      name: Cosine Accuracy@3
+    - type: cosine_accuracy@5
+      value: 0.62
+      name: Cosine Accuracy@5
+    - type: cosine_accuracy@10
+      value: 0.69
+      name: Cosine Accuracy@10
+    - type: cosine_precision@1
+      value: 0.30000000000000004
+      name: Cosine Precision@1
+    - type: cosine_precision@3
+      value: 0.19
+      name: Cosine Precision@3
+    - type: cosine_precision@5
+      value: 0.128
+      name: Cosine Precision@5
+    - type: cosine_precision@10
+      value: 0.07100000000000001
+      name: Cosine Precision@10
+    - type: cosine_recall@1
+      value: 0.29000000000000004
+      name: Cosine Recall@1
+    - type: cosine_recall@3
+      value: 0.5449999999999999
+      name: Cosine Recall@3
+    - type: cosine_recall@5
+      value: 0.61
+      name: Cosine Recall@5
+    - type: cosine_recall@10
+      value: 0.6799999999999999
+      name: Cosine Recall@10
+    - type: cosine_ndcg@10
+      value: 0.497185736443469
+      name: Cosine Ndcg@10
+    - type: cosine_mrr@10
+      value: 0.4425555555555556
+      name: Cosine Mrr@10
+    - type: cosine_map@100
+      value: 0.44753124213980516
+      name: Cosine Map@100
 ---
 
-# SentenceTransformer based on prajjwal1/bert-small
+# SentenceTransformer based on thenlper/gte-small
 
-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 [thenlper/gte-small](https://huggingface.co/thenlper/gte-small). 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
 
 ### Model Description
 - **Model Type:** Sentence Transformer
-- **Base model:** [prajjwal1/bert-small](https://huggingface.co/prajjwal1/bert-small) <!-- at revision 0ec5f86f27c1a77d704439db5e01c307ea11b9d4 -->
+- **Base model:** [thenlper/gte-small](https://huggingface.co/thenlper/gte-small) <!-- at revision 17e1f347d17fe144873b1201da91788898c639cd -->
 - **Maximum Sequence Length:** 128 tokens
-- **Output Dimensionality:** 512 dimensions
+- **Output Dimensionality:** 384 dimensions
 - **Similarity Function:** Cosine Similarity
 <!-- - **Training Dataset:** Unknown -->
 <!-- - **Language:** Unknown -->
@@ -66,7 +246,8 @@ 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})
+  (1): Pooling({'word_embedding_dimension': 384, '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): Normalize()
 )
 ```
 
@@ -85,23 +266,23 @@ 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?',
+    'What is the difference between economic growth and economic development?',
+    'What is the difference between economic growth and economic development?',
+    'the difference between economic growth and economic development is What?',
 ]
 embeddings = model.encode(sentences)
 print(embeddings.shape)
-# [3, 512]
+# [3, 384]
 
 # Get the similarity scores for the embeddings
 similarities = model.similarity(embeddings, embeddings)
 print(similarities)
-# tensor([[1.0000, 0.8563, 0.0594],
-#         [0.8563, 1.0000, 0.1245],
-#         [0.0594, 0.1245, 1.0000]])
+# tensor([[ 1.0001,  1.0001, -0.0307],
+#         [ 1.0001,  1.0001, -0.0307],
+#         [-0.0307, -0.0307,  1.0001]])
 ```
 
 <!--
@@ -128,6 +309,65 @@ 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
+
+* Datasets: `NanoMSMARCO` and `NanoNQ`
+* Evaluated with [<code>InformationRetrievalEvaluator</code>](https://sbert.net/docs/package_reference/sentence_transformer/evaluation.html#sentence_transformers.evaluation.InformationRetrievalEvaluator)
+
+| Metric              | NanoMSMARCO | NanoNQ     |
+|:--------------------|:------------|:-----------|
+| cosine_accuracy@1   | 0.28        | 0.32       |
+| cosine_accuracy@3   | 0.58        | 0.54       |
+| cosine_accuracy@5   | 0.64        | 0.6        |
+| cosine_accuracy@10  | 0.72        | 0.66       |
+| cosine_precision@1  | 0.28        | 0.32       |
+| cosine_precision@3  | 0.1933      | 0.1867     |
+| cosine_precision@5  | 0.128       | 0.128      |
+| cosine_precision@10 | 0.072       | 0.07       |
+| cosine_recall@1     | 0.28        | 0.3        |
+| cosine_recall@3     | 0.58        | 0.51       |
+| cosine_recall@5     | 0.64        | 0.58       |
+| cosine_recall@10    | 0.72        | 0.64       |
+| **cosine_ndcg@10**  | **0.5075**  | **0.4869** |
+| cosine_mrr@10       | 0.4386      | 0.4465     |
+| cosine_map@100      | 0.4533      | 0.4417     |
+
+#### Nano BEIR
+
+* Dataset: `NanoBEIR_mean`
+* Evaluated with [<code>NanoBEIREvaluator</code>](https://sbert.net/docs/package_reference/sentence_transformer/evaluation.html#sentence_transformers.evaluation.NanoBEIREvaluator) with these parameters:
+  ```json
+  {
+      "dataset_names": [
+          "msmarco",
+          "nq"
+      ],
+      "dataset_id": "lightonai/NanoBEIR-en"
+  }
+  ```
+
+| Metric              | Value      |
+|:--------------------|:-----------|
+| cosine_accuracy@1   | 0.3        |
+| cosine_accuracy@3   | 0.56       |
+| cosine_accuracy@5   | 0.62       |
+| cosine_accuracy@10  | 0.69       |
+| cosine_precision@1  | 0.3        |
+| cosine_precision@3  | 0.19       |
+| cosine_precision@5  | 0.128      |
+| cosine_precision@10 | 0.071      |
+| cosine_recall@1     | 0.29       |
+| cosine_recall@3     | 0.545      |
+| cosine_recall@5     | 0.61       |
+| cosine_recall@10    | 0.68       |
+| **cosine_ndcg@10**  | **0.4972** |
+| cosine_mrr@10       | 0.4426     |
+| cosine_map@100      | 0.4475     |
+
 <!--
 ## Bias, Risks and Limitations
 
@@ -146,23 +386,49 @@ 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: 16.07 tokens</li><li>max: 53 tokens</li></ul> | <ul><li>min: 6 tokens</li><li>mean: 16.03 tokens</li><li>max: 53 tokens</li></ul> | <ul><li>min: 6 tokens</li><li>mean: 16.81 tokens</li><li>max: 58 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: 15.52 tokens</li><li>max: 74 tokens</li></ul> | <ul><li>min: 6 tokens</li><li>mean: 15.51 tokens</li><li>max: 74 tokens</li></ul> | <ul><li>min: 6 tokens</li><li>mean: 16.79 tokens</li><li>max: 69 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
   }
@@ -171,36 +437,49 @@ You can finetune this model on your own dataset.
 ### Training Hyperparameters
 #### Non-Default Hyperparameters
 
-- `per_device_train_batch_size`: 64
-- `per_device_eval_batch_size`: 64
+- `eval_strategy`: steps
+- `per_device_train_batch_size`: 128
+- `per_device_eval_batch_size`: 128
+- `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
+- `per_device_train_batch_size`: 128
+- `per_device_eval_batch_size`: 128
 - `per_gpu_train_batch_size`: None
 - `per_gpu_eval_batch_size`: None
 - `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 +507,14 @@ 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 +524,23 @@ 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 +567,43 @@ 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 | NanoMSMARCO_cosine_ndcg@10 | NanoNQ_cosine_ndcg@10 | NanoBEIR_mean_cosine_ndcg@10 |
+|:------:|:----:|:-------------:|:---------------:|:--------------------------:|:---------------------:|:----------------------------:|
+| 0      | 0    | -             | 3.6810          | 0.6259                     | 0.6583                | 0.6421                       |
+| 0.0448 | 250  | 2.585         | 0.6156          | 0.5723                     | 0.5298                | 0.5511                       |
+| 0.0897 | 500  | 0.6653        | 0.4478          | 0.6142                     | 0.5301                | 0.5722                       |
+| 0.1345 | 750  | 0.5594        | 0.4191          | 0.5786                     | 0.5355                | 0.5570                       |
+| 0.1793 | 1000 | 0.5315        | 0.4058          | 0.5597                     | 0.5291                | 0.5444                       |
+| 0.2242 | 1250 | 0.5141        | 0.3980          | 0.5490                     | 0.5255                | 0.5372                       |
+| 0.2690 | 1500 | 0.4986        | 0.3916          | 0.5286                     | 0.5331                | 0.5308                       |
+| 0.3138 | 1750 | 0.4909        | 0.3857          | 0.5386                     | 0.5297                | 0.5342                       |
+| 0.3587 | 2000 | 0.4831        | 0.3818          | 0.5175                     | 0.5155                | 0.5165                       |
+| 0.4035 | 2250 | 0.4752        | 0.3785          | 0.5105                     | 0.5292                | 0.5198                       |
+| 0.4484 | 2500 | 0.4707        | 0.3758          | 0.5208                     | 0.4986                | 0.5097                       |
+| 0.4932 | 2750 | 0.4646        | 0.3733          | 0.5182                     | 0.5016                | 0.5099                       |
+| 0.5380 | 3000 | 0.4636        | 0.3713          | 0.5127                     | 0.4969                | 0.5048                       |
+| 0.5829 | 3250 | 0.4602        | 0.3693          | 0.5112                     | 0.4869                | 0.4991                       |
+| 0.6277 | 3500 | 0.4597        | 0.3678          | 0.5170                     | 0.5000                | 0.5085                       |
+| 0.6725 | 3750 | 0.4555        | 0.3665          | 0.5127                     | 0.4899                | 0.5013                       |
+| 0.7174 | 4000 | 0.4541        | 0.3661          | 0.5130                     | 0.4869                | 0.5000                       |
+| 0.7622 | 4250 | 0.4528        | 0.3649          | 0.5078                     | 0.4887                | 0.4982                       |
+| 0.8070 | 4500 | 0.4495        | 0.3643          | 0.5073                     | 0.4867                | 0.4970                       |
+| 0.8519 | 4750 | 0.4524        | 0.3640          | 0.5049                     | 0.4875                | 0.4962                       |
+| 0.8967 | 5000 | 0.4516        | 0.3637          | 0.5075                     | 0.4869                | 0.4972                       |
 
 
 ### Framework Versions
@@ -321,7 +612,7 @@ You can finetune this model on your own dataset.
 - Transformers: 4.57.3
 - PyTorch: 2.9.1+cu128
 - Accelerate: 1.12.0
-- Datasets: 4.4.2
+- Datasets: 2.21.0
 - Tokenizers: 0.22.1
 
 ## Citation

modules.json

@@ -10,5 +10,11 @@
     "name": "1",
     "path": "1_Pooling",
     "type": "sentence_transformers.models.Pooling"
+  },
+  {
+    "idx": 2,
+    "name": "2",
+    "path": "2_Normalize",
+    "type": "sentence_transformers.models.Normalize"
   }
 ]