Add new SentenceTransformer model

1_Pooling/config.json

@@ -1,5 +1,5 @@
 {
-    "word_embedding_dimension": 512,
+    "word_embedding_dimension": 768,
     "pooling_mode_cls_token": true,
     "pooling_mode_mean_tokens": false,
     "pooling_mode_max_tokens": false,

README.md

@@ -5,51 +5,232 @@ tags:
 - feature-extraction
 - dense
 - generated_from_trainer
-- dataset_size:100000
+- dataset_size:359997
 - loss:MultipleNegativesRankingLoss
-base_model: prajjwal1/bert-small
+base_model: Alibaba-NLP/gte-modernbert-base
 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_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 Alibaba-NLP/gte-modernbert-base
+  results:
+  - task:
+      type: information-retrieval
+      name: Information Retrieval
+    dataset:
+      name: NanoMSMARCO
+      type: NanoMSMARCO
+    metrics:
+    - type: cosine_accuracy@1
+      value: 0.38
+      name: Cosine Accuracy@1
+    - type: cosine_accuracy@3
+      value: 0.62
+      name: Cosine Accuracy@3
+    - type: cosine_accuracy@5
+      value: 0.72
+      name: Cosine Accuracy@5
+    - type: cosine_accuracy@10
+      value: 0.78
+      name: Cosine Accuracy@10
+    - type: cosine_precision@1
+      value: 0.38
+      name: Cosine Precision@1
+    - type: cosine_precision@3
+      value: 0.20666666666666667
+      name: Cosine Precision@3
+    - type: cosine_precision@5
+      value: 0.14400000000000002
+      name: Cosine Precision@5
+    - type: cosine_precision@10
+      value: 0.078
+      name: Cosine Precision@10
+    - type: cosine_recall@1
+      value: 0.38
+      name: Cosine Recall@1
+    - type: cosine_recall@3
+      value: 0.62
+      name: Cosine Recall@3
+    - type: cosine_recall@5
+      value: 0.72
+      name: Cosine Recall@5
+    - type: cosine_recall@10
+      value: 0.78
+      name: Cosine Recall@10
+    - type: cosine_ndcg@10
+      value: 0.5792677770404034
+      name: Cosine Ndcg@10
+    - type: cosine_mrr@10
+      value: 0.5150238095238094
+      name: Cosine Mrr@10
+    - type: cosine_map@100
+      value: 0.5260186479155519
+      name: Cosine Map@100
+  - task:
+      type: information-retrieval
+      name: Information Retrieval
+    dataset:
+      name: NanoNQ
+      type: NanoNQ
+    metrics:
+    - type: cosine_accuracy@1
+      value: 0.38
+      name: Cosine Accuracy@1
+    - type: cosine_accuracy@3
+      value: 0.58
+      name: Cosine Accuracy@3
+    - type: cosine_accuracy@5
+      value: 0.66
+      name: Cosine Accuracy@5
+    - type: cosine_accuracy@10
+      value: 0.74
+      name: Cosine Accuracy@10
+    - type: cosine_precision@1
+      value: 0.38
+      name: Cosine Precision@1
+    - type: cosine_precision@3
+      value: 0.2
+      name: Cosine Precision@3
+    - type: cosine_precision@5
+      value: 0.14
+      name: Cosine Precision@5
+    - type: cosine_precision@10
+      value: 0.078
+      name: Cosine Precision@10
+    - type: cosine_recall@1
+      value: 0.36
+      name: Cosine Recall@1
+    - type: cosine_recall@3
+      value: 0.54
+      name: Cosine Recall@3
+    - type: cosine_recall@5
+      value: 0.62
+      name: Cosine Recall@5
+    - type: cosine_recall@10
+      value: 0.7
+      name: Cosine Recall@10
+    - type: cosine_ndcg@10
+      value: 0.5417937853620868
+      name: Cosine Ndcg@10
+    - type: cosine_mrr@10
+      value: 0.5033571428571428
+      name: Cosine Mrr@10
+    - type: cosine_map@100
+      value: 0.4942594774374801
+      name: Cosine Map@100
+  - task:
+      type: nano-beir
+      name: Nano BEIR
+    dataset:
+      name: NanoBEIR mean
+      type: NanoBEIR_mean
+    metrics:
+    - type: cosine_accuracy@1
+      value: 0.38
+      name: Cosine Accuracy@1
+    - type: cosine_accuracy@3
+      value: 0.6
+      name: Cosine Accuracy@3
+    - type: cosine_accuracy@5
+      value: 0.69
+      name: Cosine Accuracy@5
+    - type: cosine_accuracy@10
+      value: 0.76
+      name: Cosine Accuracy@10
+    - type: cosine_precision@1
+      value: 0.38
+      name: Cosine Precision@1
+    - type: cosine_precision@3
+      value: 0.20333333333333334
+      name: Cosine Precision@3
+    - type: cosine_precision@5
+      value: 0.14200000000000002
+      name: Cosine Precision@5
+    - type: cosine_precision@10
+      value: 0.078
+      name: Cosine Precision@10
+    - type: cosine_recall@1
+      value: 0.37
+      name: Cosine Recall@1
+    - type: cosine_recall@3
+      value: 0.5800000000000001
+      name: Cosine Recall@3
+    - type: cosine_recall@5
+      value: 0.6699999999999999
+      name: Cosine Recall@5
+    - type: cosine_recall@10
+      value: 0.74
+      name: Cosine Recall@10
+    - type: cosine_ndcg@10
+      value: 0.5605307812012451
+      name: Cosine Ndcg@10
+    - type: cosine_mrr@10
+      value: 0.5091904761904762
+      name: Cosine Mrr@10
+    - type: cosine_map@100
+      value: 0.510139062676516
+      name: Cosine Map@100
 ---
 
-# SentenceTransformer based on prajjwal1/bert-small
+# SentenceTransformer based on Alibaba-NLP/gte-modernbert-base
 
-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 [Alibaba-NLP/gte-modernbert-base](https://huggingface.co/Alibaba-NLP/gte-modernbert-base). 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:** [Alibaba-NLP/gte-modernbert-base](https://huggingface.co/Alibaba-NLP/gte-modernbert-base) <!-- at revision e7f32e3c00f91d699e8c43b53106206bcc72bb22 -->
 - **Maximum Sequence Length:** 128 tokens
-- **Output Dimensionality:** 512 dimensions
+- **Output Dimensionality:** 768 dimensions
 - **Similarity Function:** Cosine Similarity
 <!-- - **Training Dataset:** Unknown -->
 <!-- - **Language:** Unknown -->
@@ -65,8 +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})
+  (0): Transformer({'max_seq_length': 128, 'do_lower_case': False, 'architecture': 'ModernBertModel'})
+  (1): Pooling({'word_embedding_dimension': 768, '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})
 )
 ```
 
@@ -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-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?',
+    'How do you earn money on Quora?',
+    '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?',
 ]
 embeddings = model.encode(sentences)
 print(embeddings.shape)
-# [3, 512]
+# [3, 768]
 
 # Get the similarity scores for the embeddings
 similarities = model.similarity(embeddings, embeddings)
 print(similarities)
-# tensor([[ 1.0000,  0.7596, -0.0398],
-#         [ 0.7596,  1.0000, -0.0308],
-#         [-0.0398, -0.0308,  1.0000]])
+# tensor([[ 1.0000,  0.9926, -0.0086],
+#         [ 0.9926,  1.0000, -0.0135],
+#         [-0.0086, -0.0135,  1.0000]])
 ```
 
 <!--
@@ -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   | 0.38        | 0.38       |
+| cosine_accuracy@3   | 0.62        | 0.58       |
+| cosine_accuracy@5   | 0.72        | 0.66       |
+| cosine_accuracy@10  | 0.78        | 0.74       |
+| cosine_precision@1  | 0.38        | 0.38       |
+| cosine_precision@3  | 0.2067      | 0.2        |
+| cosine_precision@5  | 0.144       | 0.14       |
+| cosine_precision@10 | 0.078       | 0.078      |
+| cosine_recall@1     | 0.38        | 0.36       |
+| cosine_recall@3     | 0.62        | 0.54       |
+| cosine_recall@5     | 0.72        | 0.62       |
+| cosine_recall@10    | 0.78        | 0.7        |
+| **cosine_ndcg@10**  | **0.5793**  | **0.5418** |
+| cosine_mrr@10       | 0.515       | 0.5034     |
+| cosine_map@100      | 0.526       | 0.4943     |
+
+#### 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   | 0.38       |
+| cosine_accuracy@3   | 0.6        |
+| cosine_accuracy@5   | 0.69       |
+| cosine_accuracy@10  | 0.76       |
+| cosine_precision@1  | 0.38       |
+| cosine_precision@3  | 0.2033     |
+| cosine_precision@5  | 0.142      |
+| cosine_precision@10 | 0.078      |
+| cosine_recall@1     | 0.37       |
+| cosine_recall@3     | 0.58       |
+| cosine_recall@5     | 0.67       |
+| cosine_recall@10    | 0.74       |
+| **cosine_ndcg@10**  | **0.5605** |
+| cosine_mrr@10       | 0.5092     |
+| cosine_map@100      | 0.5101     |
+
 <!--
 ## 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: 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: 15.4 tokens</li><li>max: 47 tokens</li></ul> | <ul><li>min: 4 tokens</li><li>mean: 15.47 tokens</li><li>max: 47 tokens</li></ul> | <ul><li>min: 5 tokens</li><li>mean: 16.9 tokens</li><li>max: 125 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: 15.68 tokens</li><li>max: 72 tokens</li></ul> | <ul><li>min: 6 tokens</li><li>mean: 15.75 tokens</li><li>max: 72 tokens</li></ul> | <ul><li>min: 6 tokens</li><li>mean: 16.95 tokens</li><li>max: 78 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
   }
@@ -171,36 +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-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
+- `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-a-baseline
 - `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  | 0.2284        |
-| 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 | NanoMSMARCO_cosine_ndcg@10 | NanoNQ_cosine_ndcg@10 | NanoBEIR_mean_cosine_ndcg@10 |
+|:------:|:----:|:-------------:|:---------------:|:--------------------------:|:---------------------:|:----------------------------:|
+| 0      | 0    | -             | 2.1886          | 0.6530                     | 0.6552                | 0.6541                       |
+| 0.0889 | 250  | 0.9475        | 0.4116          | 0.6233                     | 0.6439                | 0.6336                       |
+| 0.1778 | 500  | 0.3963        | 0.3836          | 0.6137                     | 0.6372                | 0.6254                       |
+| 0.2667 | 750  | 0.3776        | 0.3707          | 0.6243                     | 0.6259                | 0.6251                       |
+| 0.3556 | 1000 | 0.3675        | 0.3638          | 0.6250                     | 0.5981                | 0.6116                       |
+| 0.4445 | 1250 | 0.358         | 0.3581          | 0.6170                     | 0.6045                | 0.6108                       |
+| 0.5334 | 1500 | 0.3575        | 0.3544          | 0.6049                     | 0.5821                | 0.5935                       |
+| 0.6223 | 1750 | 0.3521        | 0.3513          | 0.5835                     | 0.5619                | 0.5727                       |
+| 0.7112 | 2000 | 0.3489        | 0.3486          | 0.5955                     | 0.5576                | 0.5765                       |
+| 0.8001 | 2250 | 0.3465        | 0.3463          | 0.6037                     | 0.5786                | 0.5911                       |
+| 0.8890 | 2500 | 0.3461        | 0.3440          | 0.5884                     | 0.5691                | 0.5788                       |
+| 0.9780 | 2750 | 0.3446        | 0.3428          | 0.5809                     | 0.5627                | 0.5718                       |
+| 1.0669 | 3000 | 0.328         | 0.3423          | 0.5701                     | 0.5599                | 0.5650                       |
+| 1.1558 | 3250 | 0.3235        | 0.3416          | 0.5691                     | 0.5419                | 0.5555                       |
+| 1.2447 | 3500 | 0.3221        | 0.3406          | 0.5694                     | 0.5534                | 0.5614                       |
+| 1.3336 | 3750 | 0.3221        | 0.3397          | 0.5736                     | 0.5519                | 0.5628                       |
+| 1.4225 | 4000 | 0.3196        | 0.3391          | 0.5811                     | 0.5416                | 0.5613                       |
+| 1.5114 | 4250 | 0.3201        | 0.3386          | 0.5525                     | 0.5538                | 0.5532                       |
+| 1.6003 | 4500 | 0.321         | 0.3384          | 0.5801                     | 0.5380                | 0.5591                       |
+| 1.6892 | 4750 | 0.3192        | 0.3382          | 0.5799                     | 0.5474                | 0.5636                       |
+| 1.7781 | 5000 | 0.3203        | 0.3379          | 0.5793                     | 0.5418                | 0.5605                       |
 
 
 ### 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

config_sentence_transformers.json

@@ -1,5 +1,4 @@
 {
-  "model_type": "SentenceTransformer",
   "__version__": {
     "sentence_transformers": "5.2.0",
     "transformers": "4.57.3",
@@ -10,5 +9,6 @@
     "document": ""
   },
   "default_prompt_name": null,
-  "similarity_fn_name": "cosine"
+  "similarity_fn_name": "cosine",
+  "model_type": "SentenceTransformer"
 }