Add new SentenceTransformer model

.gitattributes

@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+tokenizer.json filter=lfs diff=lfs merge=lfs -text

1_Pooling/config.json

@@ -0,0 +1,10 @@
+{
+  "word_embedding_dimension": 1024,
+  "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
+}

README.md

@@ -0,0 +1,803 @@
+---
+language:
+- ru
+license: apache-2.0
+tags:
+- sentence-transformers
+- sentence-similarity
+- feature-extraction
+- generated_from_trainer
+- dataset_size:904
+- loss:MatryoshkaLoss
+- loss:MultipleNegativesRankingLoss
+base_model: BAAI/bge-m3
+widget:
+- source_sentence: Какой у тебя план на будущее?
+  sentences:
+  - Работа — это скучно, если не считать, что Уголовный розыск считает меня своим
+    работником.
+  - Я дам вам парабеллум, если дружба станет слишком серьезной!
+  - План? Из Васюков полетят сигналы на Марс, а я буду на Земле собирать деньги на
+    билет.
+- source_sentence: Какой у тебя любимый фильм?
+  sentences:
+  - Может быть, тебе дать еще список фильмов, где много денег?
+  - Вам нужно путешествовать так, чтобы потом не забыть, где памятник.
+  - А доисторические спортсмены в матрацах не тренируются?
+- source_sentence: Как ты проводишь свободное время?
+  sentences:
+  - Напиток? Командовать парадом буду я!
+  - Нас топят — мы выплываем, а свободное время — это для плавания!
+  - От мертвого осла уши получишь у Пушкина, а от фильмов — только кадры.
+- source_sentence: Как ты проводишь свободное время?
+  sentences:
+  - Картина битвы мне ясна, но я предпочитаю не сражаться с скукой.
+  - Спорт — это для тех, кто не знает, что они произошли от коровы!
+  - Тайный союз меча и орала! Свободное время — это когда можно ничего не делать и
+    не переживать!
+- source_sentence: Какой у тебя любимый фильм?
+  sentences:
+  - А что, разве я похож на человека, который не любит читать между строк?
+  - У нас хотя и не Париж, но кино у нас всегда с интригой!
+  - Фильм? Знойная женщина, мечта поэта — вот мой любимый сюжет!
+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: BGE m3 for Ostap project
+  results:
+  - task:
+      type: information-retrieval
+      name: Information Retrieval
+    dataset:
+      name: dim 1024
+      type: dim_1024
+    metrics:
+    - type: cosine_accuracy@1
+      value: 0.14933628318584072
+      name: Cosine Accuracy@1
+    - type: cosine_accuracy@3
+      value: 0.2665929203539823
+      name: Cosine Accuracy@3
+    - type: cosine_accuracy@5
+      value: 0.34292035398230086
+      name: Cosine Accuracy@5
+    - type: cosine_accuracy@10
+      value: 0.4856194690265487
+      name: Cosine Accuracy@10
+    - type: cosine_precision@1
+      value: 0.14933628318584072
+      name: Cosine Precision@1
+    - type: cosine_precision@3
+      value: 0.08886430678466074
+      name: Cosine Precision@3
+    - type: cosine_precision@5
+      value: 0.06858407079646017
+      name: Cosine Precision@5
+    - type: cosine_precision@10
+      value: 0.04856194690265486
+      name: Cosine Precision@10
+    - type: cosine_recall@1
+      value: 0.14933628318584072
+      name: Cosine Recall@1
+    - type: cosine_recall@3
+      value: 0.2665929203539823
+      name: Cosine Recall@3
+    - type: cosine_recall@5
+      value: 0.34292035398230086
+      name: Cosine Recall@5
+    - type: cosine_recall@10
+      value: 0.4856194690265487
+      name: Cosine Recall@10
+    - type: cosine_ndcg@10
+      value: 0.2942645243659726
+      name: Cosine Ndcg@10
+    - type: cosine_mrr@10
+      value: 0.23620329400196635
+      name: Cosine Mrr@10
+    - type: cosine_map@100
+      value: 0.2600956714540916
+      name: Cosine Map@100
+  - task:
+      type: information-retrieval
+      name: Information Retrieval
+    dataset:
+      name: dim 768
+      type: dim_768
+    metrics:
+    - type: cosine_accuracy@1
+      value: 0.14601769911504425
+      name: Cosine Accuracy@1
+    - type: cosine_accuracy@3
+      value: 0.26548672566371684
+      name: Cosine Accuracy@3
+    - type: cosine_accuracy@5
+      value: 0.3473451327433628
+      name: Cosine Accuracy@5
+    - type: cosine_accuracy@10
+      value: 0.48672566371681414
+      name: Cosine Accuracy@10
+    - type: cosine_precision@1
+      value: 0.14601769911504425
+      name: Cosine Precision@1
+    - type: cosine_precision@3
+      value: 0.08849557522123894
+      name: Cosine Precision@3
+    - type: cosine_precision@5
+      value: 0.06946902654867257
+      name: Cosine Precision@5
+    - type: cosine_precision@10
+      value: 0.048672566371681415
+      name: Cosine Precision@10
+    - type: cosine_recall@1
+      value: 0.14601769911504425
+      name: Cosine Recall@1
+    - type: cosine_recall@3
+      value: 0.26548672566371684
+      name: Cosine Recall@3
+    - type: cosine_recall@5
+      value: 0.3473451327433628
+      name: Cosine Recall@5
+    - type: cosine_recall@10
+      value: 0.48672566371681414
+      name: Cosine Recall@10
+    - type: cosine_ndcg@10
+      value: 0.2931785163867407
+      name: Cosine Ndcg@10
+    - type: cosine_mrr@10
+      value: 0.2343512958280655
+      name: Cosine Mrr@10
+    - type: cosine_map@100
+      value: 0.2581995173126666
+      name: Cosine Map@100
+  - task:
+      type: information-retrieval
+      name: Information Retrieval
+    dataset:
+      name: dim 512
+      type: dim_512
+    metrics:
+    - type: cosine_accuracy@1
+      value: 0.14823008849557523
+      name: Cosine Accuracy@1
+    - type: cosine_accuracy@3
+      value: 0.26548672566371684
+      name: Cosine Accuracy@3
+    - type: cosine_accuracy@5
+      value: 0.34513274336283184
+      name: Cosine Accuracy@5
+    - type: cosine_accuracy@10
+      value: 0.4944690265486726
+      name: Cosine Accuracy@10
+    - type: cosine_precision@1
+      value: 0.14823008849557523
+      name: Cosine Precision@1
+    - type: cosine_precision@3
+      value: 0.08849557522123894
+      name: Cosine Precision@3
+    - type: cosine_precision@5
+      value: 0.06902654867256636
+      name: Cosine Precision@5
+    - type: cosine_precision@10
+      value: 0.04944690265486726
+      name: Cosine Precision@10
+    - type: cosine_recall@1
+      value: 0.14823008849557523
+      name: Cosine Recall@1
+    - type: cosine_recall@3
+      value: 0.26548672566371684
+      name: Cosine Recall@3
+    - type: cosine_recall@5
+      value: 0.34513274336283184
+      name: Cosine Recall@5
+    - type: cosine_recall@10
+      value: 0.4944690265486726
+      name: Cosine Recall@10
+    - type: cosine_ndcg@10
+      value: 0.2965536225707287
+      name: Cosine Ndcg@10
+    - type: cosine_mrr@10
+      value: 0.23654261483354377
+      name: Cosine Mrr@10
+    - type: cosine_map@100
+      value: 0.2597641504609653
+      name: Cosine Map@100
+  - task:
+      type: information-retrieval
+      name: Information Retrieval
+    dataset:
+      name: dim 256
+      type: dim_256
+    metrics:
+    - type: cosine_accuracy@1
+      value: 0.14491150442477876
+      name: Cosine Accuracy@1
+    - type: cosine_accuracy@3
+      value: 0.2688053097345133
+      name: Cosine Accuracy@3
+    - type: cosine_accuracy@5
+      value: 0.34845132743362833
+      name: Cosine Accuracy@5
+    - type: cosine_accuracy@10
+      value: 0.4911504424778761
+      name: Cosine Accuracy@10
+    - type: cosine_precision@1
+      value: 0.14491150442477876
+      name: Cosine Precision@1
+    - type: cosine_precision@3
+      value: 0.08960176991150441
+      name: Cosine Precision@3
+    - type: cosine_precision@5
+      value: 0.06969026548672566
+      name: Cosine Precision@5
+    - type: cosine_precision@10
+      value: 0.049115044247787606
+      name: Cosine Precision@10
+    - type: cosine_recall@1
+      value: 0.14491150442477876
+      name: Cosine Recall@1
+    - type: cosine_recall@3
+      value: 0.2688053097345133
+      name: Cosine Recall@3
+    - type: cosine_recall@5
+      value: 0.34845132743362833
+      name: Cosine Recall@5
+    - type: cosine_recall@10
+      value: 0.4911504424778761
+      name: Cosine Recall@10
+    - type: cosine_ndcg@10
+      value: 0.2942530832557106
+      name: Cosine Ndcg@10
+    - type: cosine_mrr@10
+      value: 0.2342999367888746
+      name: Cosine Mrr@10
+    - type: cosine_map@100
+      value: 0.2580055991240585
+      name: Cosine Map@100
+  - task:
+      type: information-retrieval
+      name: Information Retrieval
+    dataset:
+      name: dim 128
+      type: dim_128
+    metrics:
+    - type: cosine_accuracy@1
+      value: 0.14712389380530974
+      name: Cosine Accuracy@1
+    - type: cosine_accuracy@3
+      value: 0.2665929203539823
+      name: Cosine Accuracy@3
+    - type: cosine_accuracy@5
+      value: 0.34623893805309736
+      name: Cosine Accuracy@5
+    - type: cosine_accuracy@10
+      value: 0.4944690265486726
+      name: Cosine Accuracy@10
+    - type: cosine_precision@1
+      value: 0.14712389380530974
+      name: Cosine Precision@1
+    - type: cosine_precision@3
+      value: 0.08886430678466076
+      name: Cosine Precision@3
+    - type: cosine_precision@5
+      value: 0.06924778761061946
+      name: Cosine Precision@5
+    - type: cosine_precision@10
+      value: 0.04944690265486726
+      name: Cosine Precision@10
+    - type: cosine_recall@1
+      value: 0.14712389380530974
+      name: Cosine Recall@1
+    - type: cosine_recall@3
+      value: 0.2665929203539823
+      name: Cosine Recall@3
+    - type: cosine_recall@5
+      value: 0.34623893805309736
+      name: Cosine Recall@5
+    - type: cosine_recall@10
+      value: 0.4944690265486726
+      name: Cosine Recall@10
+    - type: cosine_ndcg@10
+      value: 0.2963702071144291
+      name: Cosine Ndcg@10
+    - type: cosine_mrr@10
+      value: 0.2362221695462843
+      name: Cosine Mrr@10
+    - type: cosine_map@100
+      value: 0.25976571809408944
+      name: Cosine Map@100
+  - task:
+      type: information-retrieval
+      name: Information Retrieval
+    dataset:
+      name: dim 64
+      type: dim_64
+    metrics:
+    - type: cosine_accuracy@1
+      value: 0.14601769911504425
+      name: Cosine Accuracy@1
+    - type: cosine_accuracy@3
+      value: 0.26991150442477874
+      name: Cosine Accuracy@3
+    - type: cosine_accuracy@5
+      value: 0.3473451327433628
+      name: Cosine Accuracy@5
+    - type: cosine_accuracy@10
+      value: 0.497787610619469
+      name: Cosine Accuracy@10
+    - type: cosine_precision@1
+      value: 0.14601769911504425
+      name: Cosine Precision@1
+    - type: cosine_precision@3
+      value: 0.08997050147492625
+      name: Cosine Precision@3
+    - type: cosine_precision@5
+      value: 0.06946902654867257
+      name: Cosine Precision@5
+    - type: cosine_precision@10
+      value: 0.049778761061946904
+      name: Cosine Precision@10
+    - type: cosine_recall@1
+      value: 0.14601769911504425
+      name: Cosine Recall@1
+    - type: cosine_recall@3
+      value: 0.26991150442477874
+      name: Cosine Recall@3
+    - type: cosine_recall@5
+      value: 0.3473451327433628
+      name: Cosine Recall@5
+    - type: cosine_recall@10
+      value: 0.497787610619469
+      name: Cosine Recall@10
+    - type: cosine_ndcg@10
+      value: 0.29684044099735196
+      name: Cosine Ndcg@10
+    - type: cosine_mrr@10
+      value: 0.23588767734232302
+      name: Cosine Mrr@10
+    - type: cosine_map@100
+      value: 0.2592174386566743
+      name: Cosine Map@100
+---
+
+# BGE m3 for Ostap project
+
+This is a [sentence-transformers](https://www.SBERT.net) model finetuned from [BAAI/bge-m3](https://huggingface.co/BAAI/bge-m3). It maps sentences & paragraphs to a 1024-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:** [BAAI/bge-m3](https://huggingface.co/BAAI/bge-m3) <!-- at revision 5617a9f61b028005a4858fdac845db406aefb181 -->
+- **Maximum Sequence Length:** 8192 tokens
+- **Output Dimensionality:** 1024 dimensions
+- **Similarity Function:** Cosine Similarity
+<!-- - **Training Dataset:** Unknown -->
+- **Language:** ru
+- **License:** apache-2.0
+
+### Model Sources
+
+- **Documentation:** [Sentence Transformers Documentation](https://sbert.net)
+- **Repository:** [Sentence Transformers on GitHub](https://github.com/UKPLab/sentence-transformers)
+- **Hugging Face:** [Sentence Transformers on Hugging Face](https://huggingface.co/models?library=sentence-transformers)
+
+### Full Model Architecture
+
+```
+SentenceTransformer(
+  (0): Transformer({'max_seq_length': 8192, 'do_lower_case': False}) with Transformer model: XLMRobertaModel 
+  (1): Pooling({'word_embedding_dimension': 1024, '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})
+  (2): Normalize()
+)
+```
+
+## Usage
+
+### Direct Usage (Sentence Transformers)
+
+First install the Sentence Transformers library:
+
+```bash
+pip install -U sentence-transformers
+```
+
+Then you can load this model and run inference.
+```python
+from sentence_transformers import SentenceTransformer
+
+# Download from the 🤗 Hub
+model = SentenceTransformer("fitlemon/bge-m3-ru-ostap")
+# Run inference
+sentences = [
+    'Какой у тебя любимый фильм?',
+    'У нас хотя и не Париж, но кино у нас всегда с интригой!',
+    'Фильм? Знойная женщина, мечта поэта — вот мой любимый сюжет!',
+]
+embeddings = model.encode(sentences)
+print(embeddings.shape)
+# [3, 1024]
+
+# Get the similarity scores for the embeddings
+similarities = model.similarity(embeddings, embeddings)
+print(similarities.shape)
+# [3, 3]
+```
+
+<!--
+### Direct Usage (Transformers)
+
+<details><summary>Click to see the direct usage in Transformers</summary>
+
+</details>
+-->
+
+<!--
+### Downstream Usage (Sentence Transformers)
+
+You can finetune this model on your own dataset.
+
+<details><summary>Click to expand</summary>
+
+</details>
+-->
+
+<!--
+### Out-of-Scope Use
+
+*List how the model may foreseeably be misused and address what users ought not to do with the model.*
+-->
+
+## Evaluation
+
+### Metrics
+
+#### Information Retrieval
+
+* Datasets: `dim_1024`, `dim_768`, `dim_512`, `dim_256`, `dim_128` and `dim_64`
+* Evaluated with [<code>InformationRetrievalEvaluator</code>](https://sbert.net/docs/package_reference/sentence_transformer/evaluation.html#sentence_transformers.evaluation.InformationRetrievalEvaluator)
+
+| Metric              | dim_1024   | dim_768    | dim_512    | dim_256    | dim_128    | dim_64     |
+|:--------------------|:-----------|:-----------|:-----------|:-----------|:-----------|:-----------|
+| cosine_accuracy@1   | 0.1493     | 0.146      | 0.1482     | 0.1449     | 0.1471     | 0.146      |
+| cosine_accuracy@3   | 0.2666     | 0.2655     | 0.2655     | 0.2688     | 0.2666     | 0.2699     |
+| cosine_accuracy@5   | 0.3429     | 0.3473     | 0.3451     | 0.3485     | 0.3462     | 0.3473     |
+| cosine_accuracy@10  | 0.4856     | 0.4867     | 0.4945     | 0.4912     | 0.4945     | 0.4978     |
+| cosine_precision@1  | 0.1493     | 0.146      | 0.1482     | 0.1449     | 0.1471     | 0.146      |
+| cosine_precision@3  | 0.0889     | 0.0885     | 0.0885     | 0.0896     | 0.0889     | 0.09       |
+| cosine_precision@5  | 0.0686     | 0.0695     | 0.069      | 0.0697     | 0.0692     | 0.0695     |
+| cosine_precision@10 | 0.0486     | 0.0487     | 0.0494     | 0.0491     | 0.0494     | 0.0498     |
+| cosine_recall@1     | 0.1493     | 0.146      | 0.1482     | 0.1449     | 0.1471     | 0.146      |
+| cosine_recall@3     | 0.2666     | 0.2655     | 0.2655     | 0.2688     | 0.2666     | 0.2699     |
+| cosine_recall@5     | 0.3429     | 0.3473     | 0.3451     | 0.3485     | 0.3462     | 0.3473     |
+| cosine_recall@10    | 0.4856     | 0.4867     | 0.4945     | 0.4912     | 0.4945     | 0.4978     |
+| **cosine_ndcg@10**  | **0.2943** | **0.2932** | **0.2966** | **0.2943** | **0.2964** | **0.2968** |
+| cosine_mrr@10       | 0.2362     | 0.2344     | 0.2365     | 0.2343     | 0.2362     | 0.2359     |
+| cosine_map@100      | 0.2601     | 0.2582     | 0.2598     | 0.258      | 0.2598     | 0.2592     |
+
+<!--
+## Bias, Risks and Limitations
+
+*What are the known or foreseeable issues stemming from this model? You could also flag here known failure cases or weaknesses of the model.*
+-->
+
+<!--
+### Recommendations
+
+*What are recommendations with respect to the foreseeable issues? For example, filtering explicit content.*
+-->
+
+## Training Details
+
+### Training Dataset
+
+#### Unnamed Dataset
+
+* Size: 904 training samples
+* Columns: <code>question</code> and <code>answer</code>
+* Approximate statistics based on the first 904 samples:
+  |         | question                                                                          | answer                                                                            |
+  |:--------|:----------------------------------------------------------------------------------|:----------------------------------------------------------------------------------|
+  | type    | string                                                                            | string                                                                            |
+  | details | <ul><li>min: 6 tokens</li><li>mean: 10.16 tokens</li><li>max: 14 tokens</li></ul> | <ul><li>min: 8 tokens</li><li>mean: 20.91 tokens</li><li>max: 43 tokens</li></ul> |
+* Samples:
+  | question                                       | answer                                                                              |
+  |:-----------------------------------------------|:------------------------------------------------------------------------------------|
+  | <code>Как ты проводишь свободное время?</code> | <code>Любителя бьют, а время — не ждет!</code>                                      |
+  | <code>Какой у тебя план на будущее?</code>     | <code>План на будущее? Широкие массы миллиардеров уже составили его за меня.</code> |
+  | <code>Какой у тебя любимый цвет?</code>        | <code>Вы мне в конце концов не художник, не дизайнер и не стилист.</code>           |
+* Loss: [<code>MatryoshkaLoss</code>](https://sbert.net/docs/package_reference/sentence_transformer/losses.html#matryoshkaloss) with these parameters:
+  ```json
+  {
+      "loss": "MultipleNegativesRankingLoss",
+      "matryoshka_dims": [
+          1024,
+          768,
+          512,
+          256,
+          128,
+          64
+      ],
+      "matryoshka_weights": [
+          1,
+          1,
+          1,
+          1,
+          1,
+          1
+      ],
+      "n_dims_per_step": -1
+  }
+  ```
+
+### Training Hyperparameters
+#### Non-Default Hyperparameters
+
+- `eval_strategy`: epoch
+- `learning_rate`: 2e-05
+- `num_train_epochs`: 4
+- `lr_scheduler_type`: cosine
+- `warmup_ratio`: 0.1
+- `fp16`: True
+- `tf32`: False
+- `load_best_model_at_end`: True
+- `optim`: adamw_torch_fused
+- `batch_sampler`: no_duplicates
+
+#### All Hyperparameters
+<details><summary>Click to expand</summary>
+
+- `overwrite_output_dir`: False
+- `do_predict`: False
+- `eval_strategy`: epoch
+- `prediction_loss_only`: True
+- `per_device_train_batch_size`: 8
+- `per_device_eval_batch_size`: 8
+- `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`: 2e-05
+- `weight_decay`: 0.0
+- `adam_beta1`: 0.9
+- `adam_beta2`: 0.999
+- `adam_epsilon`: 1e-08
+- `max_grad_norm`: 1.0
+- `num_train_epochs`: 4
+- `max_steps`: -1
+- `lr_scheduler_type`: cosine
+- `lr_scheduler_kwargs`: {}
+- `warmup_ratio`: 0.1
+- `warmup_steps`: 0
+- `log_level`: passive
+- `log_level_replica`: warning
+- `log_on_each_node`: True
+- `logging_nan_inf_filter`: True
+- `save_safetensors`: True
+- `save_on_each_node`: False
+- `save_only_model`: False
+- `restore_callback_states_from_checkpoint`: False
+- `no_cuda`: False
+- `use_cpu`: False
+- `use_mps_device`: False
+- `seed`: 42
+- `data_seed`: None
+- `jit_mode_eval`: False
+- `use_ipex`: False
+- `bf16`: False
+- `fp16`: True
+- `fp16_opt_level`: O1
+- `half_precision_backend`: auto
+- `bf16_full_eval`: False
+- `fp16_full_eval`: False
+- `tf32`: False
+- `local_rank`: 0
+- `ddp_backend`: None
+- `tpu_num_cores`: None
+- `tpu_metrics_debug`: False
+- `debug`: []
+- `dataloader_drop_last`: False
+- `dataloader_num_workers`: 0
+- `dataloader_prefetch_factor`: None
+- `past_index`: -1
+- `disable_tqdm`: False
+- `remove_unused_columns`: True
+- `label_names`: None
+- `load_best_model_at_end`: True
+- `ignore_data_skip`: False
+- `fsdp`: []
+- `fsdp_min_num_params`: 0
+- `fsdp_config`: {'min_num_params': 0, 'xla': False, 'xla_fsdp_v2': False, 'xla_fsdp_grad_ckpt': False}
+- `fsdp_transformer_layer_cls_to_wrap`: None
+- `accelerator_config`: {'split_batches': False, 'dispatch_batches': None, 'even_batches': True, 'use_seedable_sampler': True, 'non_blocking': False, 'gradient_accumulation_kwargs': None}
+- `deepspeed`: None
+- `label_smoothing_factor`: 0.0
+- `optim`: adamw_torch_fused
+- `optim_args`: None
+- `adafactor`: False
+- `group_by_length`: False
+- `length_column_name`: length
+- `ddp_find_unused_parameters`: None
+- `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
+- `resume_from_checkpoint`: None
+- `hub_model_id`: None
+- `hub_strategy`: every_save
+- `hub_private_repo`: None
+- `hub_always_push`: False
+- `gradient_checkpointing`: False
+- `gradient_checkpointing_kwargs`: None
+- `include_inputs_for_metrics`: False
+- `include_for_metrics`: []
+- `eval_do_concat_batches`: True
+- `fp16_backend`: auto
+- `push_to_hub_model_id`: None
+- `push_to_hub_organization`: None
+- `mp_parameters`: 
+- `auto_find_batch_size`: False
+- `full_determinism`: False
+- `torchdynamo`: None
+- `ray_scope`: last
+- `ddp_timeout`: 1800
+- `torch_compile`: False
+- `torch_compile_backend`: None
+- `torch_compile_mode`: None
+- `dispatch_batches`: None
+- `split_batches`: None
+- `include_tokens_per_second`: False
+- `include_num_input_tokens_seen`: False
+- `neftune_noise_alpha`: None
+- `optim_target_modules`: None
+- `batch_eval_metrics`: False
+- `eval_on_start`: False
+- `use_liger_kernel`: False
+- `eval_use_gather_object`: False
+- `average_tokens_across_devices`: False
+- `prompts`: None
+- `batch_sampler`: no_duplicates
+- `multi_dataset_batch_sampler`: proportional
+
+</details>
+
+### Training Logs
+| Epoch      | Step    | Training Loss | dim_1024_cosine_ndcg@10 | dim_768_cosine_ndcg@10 | dim_512_cosine_ndcg@10 | dim_256_cosine_ndcg@10 | dim_128_cosine_ndcg@10 | dim_64_cosine_ndcg@10 |
+|:----------:|:-------:|:-------------:|:-----------------------:|:----------------------:|:----------------------:|:----------------------:|:----------------------:|:---------------------:|
+| 0.0885     | 10      | 6.8669        | -                       | -                      | -                      | -                      | -                      | -                     |
+| 0.1770     | 20      | 4.9384        | -                       | -                      | -                      | -                      | -                      | -                     |
+| 0.2655     | 30      | 3.1491        | -                       | -                      | -                      | -                      | -                      | -                     |
+| 0.3540     | 40      | 2.5456        | -                       | -                      | -                      | -                      | -                      | -                     |
+| 0.4425     | 50      | 3.6943        | -                       | -                      | -                      | -                      | -                      | -                     |
+| 0.5310     | 60      | 1.8947        | -                       | -                      | -                      | -                      | -                      | -                     |
+| 0.6195     | 70      | 2.1762        | -                       | -                      | -                      | -                      | -                      | -                     |
+| 0.7080     | 80      | 1.9446        | -                       | -                      | -                      | -                      | -                      | -                     |
+| 0.7965     | 90      | 1.5278        | -                       | -                      | -                      | -                      | -                      | -                     |
+| 0.8850     | 100     | 2.0417        | -                       | -                      | -                      | -                      | -                      | -                     |
+| 0.9735     | 110     | 3.7804        | -                       | -                      | -                      | -                      | -                      | -                     |
+| 1.0        | 113     | -             | 0.2751                  | 0.2747                 | 0.2761                 | 0.2786                 | 0.2764                 | 0.2715                |
+| 1.0619     | 120     | 1.9706        | -                       | -                      | -                      | -                      | -                      | -                     |
+| 1.1504     | 130     | 1.7073        | -                       | -                      | -                      | -                      | -                      | -                     |
+| 1.2389     | 140     | 1.3279        | -                       | -                      | -                      | -                      | -                      | -                     |
+| 1.3274     | 150     | 1.2724        | -                       | -                      | -                      | -                      | -                      | -                     |
+| 1.4159     | 160     | 2.4455        | -                       | -                      | -                      | -                      | -                      | -                     |
+| 1.5044     | 170     | 0.5255        | -                       | -                      | -                      | -                      | -                      | -                     |
+| 1.5929     | 180     | 2.5764        | -                       | -                      | -                      | -                      | -                      | -                     |
+| 1.6814     | 190     | 1.56          | -                       | -                      | -                      | -                      | -                      | -                     |
+| 1.7699     | 200     | 0.9105        | -                       | -                      | -                      | -                      | -                      | -                     |
+| 1.8584     | 210     | 1.9859        | -                       | -                      | -                      | -                      | -                      | -                     |
+| 1.9469     | 220     | 1.6355        | -                       | -                      | -                      | -                      | -                      | -                     |
+| 2.0088     | 227     | -             | 0.2837                  | 0.2852                 | 0.2880                 | 0.2899                 | 0.2926                 | 0.2902                |
+| 2.0265     | 230     | 0.6769        | -                       | -                      | -                      | -                      | -                      | -                     |
+| 2.1150     | 240     | 0.764         | -                       | -                      | -                      | -                      | -                      | -                     |
+| 2.2035     | 250     | 1.0598        | -                       | -                      | -                      | -                      | -                      | -                     |
+| 2.2920     | 260     | 0.9267        | -                       | -                      | -                      | -                      | -                      | -                     |
+| 2.3805     | 270     | 0.9687        | -                       | -                      | -                      | -                      | -                      | -                     |
+| 2.4690     | 280     | 0.7875        | -                       | -                      | -                      | -                      | -                      | -                     |
+| 2.5575     | 290     | 1.3853        | -                       | -                      | -                      | -                      | -                      | -                     |
+| 2.6460     | 300     | 0.8114        | -                       | -                      | -                      | -                      | -                      | -                     |
+| 2.7345     | 310     | 1.6069        | -                       | -                      | -                      | -                      | -                      | -                     |
+| 2.8230     | 320     | 0.8149        | -                       | -                      | -                      | -                      | -                      | -                     |
+| 2.9115     | 330     | 0.8858        | -                       | -                      | -                      | -                      | -                      | -                     |
+| 3.0        | 340     | 0.7858        | 0.2920                  | 0.2917                 | 0.2929                 | 0.2927                 | 0.2967                 | 0.2969                |
+| 3.0885     | 350     | 0.5889        | -                       | -                      | -                      | -                      | -                      | -                     |
+| 3.1770     | 360     | 0.3542        | -                       | -                      | -                      | -                      | -                      | -                     |
+| 3.2655     | 370     | 0.5868        | -                       | -                      | -                      | -                      | -                      | -                     |
+| 3.3540     | 380     | 0.4988        | -                       | -                      | -                      | -                      | -                      | -                     |
+| 3.4425     | 390     | 0.4577        | -                       | -                      | -                      | -                      | -                      | -                     |
+| 3.5310     | 400     | 0.4735        | -                       | -                      | -                      | -                      | -                      | -                     |
+| 3.6195     | 410     | 1.2588        | -                       | -                      | -                      | -                      | -                      | -                     |
+| 3.7080     | 420     | 0.6346        | -                       | -                      | -                      | -                      | -                      | -                     |
+| 3.7965     | 430     | 0.3013        | -                       | -                      | -                      | -                      | -                      | -                     |
+| 3.8850     | 440     | 0.6734        | -                       | -                      | -                      | -                      | -                      | -                     |
+| 3.9735     | 450     | 0.3469        | -                       | -                      | -                      | -                      | -                      | -                     |
+| **3.9912** | **452** | **-**         | **0.2943**              | **0.2932**             | **0.2966**             | **0.2943**             | **0.2964**             | **0.2968**            |
+
+* The bold row denotes the saved checkpoint.
+
+### Framework Versions
+- Python: 3.11.11
+- Sentence Transformers: 3.4.1
+- Transformers: 4.48.3
+- PyTorch: 2.5.1+cu124
+- Accelerate: 1.3.0
+- Datasets: 3.3.2
+- Tokenizers: 0.21.0
+
+## Citation
+
+### BibTeX
+
+#### Sentence Transformers
+```bibtex
+@inproceedings{reimers-2019-sentence-bert,
+    title = "Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks",
+    author = "Reimers, Nils and Gurevych, Iryna",
+    booktitle = "Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing",
+    month = "11",
+    year = "2019",
+    publisher = "Association for Computational Linguistics",
+    url = "https://arxiv.org/abs/1908.10084",
+}
+```
+
+#### MatryoshkaLoss
+```bibtex
+@misc{kusupati2024matryoshka,
+    title={Matryoshka Representation Learning},
+    author={Aditya Kusupati and Gantavya Bhatt and Aniket Rege and Matthew Wallingford and Aditya Sinha and Vivek Ramanujan and William Howard-Snyder and Kaifeng Chen and Sham Kakade and Prateek Jain and Ali Farhadi},
+    year={2024},
+    eprint={2205.13147},
+    archivePrefix={arXiv},
+    primaryClass={cs.LG}
+}
+```
+
+#### MultipleNegativesRankingLoss
+```bibtex
+@misc{henderson2017efficient,
+    title={Efficient Natural Language Response Suggestion for Smart Reply},
+    author={Matthew Henderson and Rami Al-Rfou and Brian Strope and Yun-hsuan Sung and Laszlo Lukacs and Ruiqi Guo and Sanjiv Kumar and Balint Miklos and Ray Kurzweil},
+    year={2017},
+    eprint={1705.00652},
+    archivePrefix={arXiv},
+    primaryClass={cs.CL}
+}
+```
+
+<!--
+## Glossary
+
+*Clearly define terms in order to be accessible across audiences.*
+-->
+
+<!--
+## Model Card Authors
+
+*Lists the people who create the model card, providing recognition and accountability for the detailed work that goes into its construction.*
+-->
+
+<!--
+## Model Card Contact
+
+*Provides a way for people who have updates to the Model Card, suggestions, or questions, to contact the Model Card authors.*
+-->

config.json

@@ -0,0 +1,28 @@
+{
+  "_name_or_path": "BAAI/bge-m3",
+  "architectures": [
+    "XLMRobertaModel"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "bos_token_id": 0,
+  "classifier_dropout": null,
+  "eos_token_id": 2,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 1024,
+  "initializer_range": 0.02,
+  "intermediate_size": 4096,
+  "layer_norm_eps": 1e-05,
+  "max_position_embeddings": 8194,
+  "model_type": "xlm-roberta",
+  "num_attention_heads": 16,
+  "num_hidden_layers": 24,
+  "output_past": true,
+  "pad_token_id": 1,
+  "position_embedding_type": "absolute",
+  "torch_dtype": "float32",
+  "transformers_version": "4.48.3",
+  "type_vocab_size": 1,
+  "use_cache": true,
+  "vocab_size": 250002
+}

config_sentence_transformers.json

@@ -0,0 +1,10 @@
+{
+  "__version__": {
+    "sentence_transformers": "3.4.1",
+    "transformers": "4.48.3",
+    "pytorch": "2.5.1+cu124"
+  },
+  "prompts": {},
+  "default_prompt_name": null,
+  "similarity_fn_name": "cosine"
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:923a8e25262a389b428fca10c01f7e05c4371e0c4301694a5147203de8d340a3
+size 2271064456

modules.json

@@ -0,0 +1,20 @@
+[
+  {
+    "idx": 0,
+    "name": "0",
+    "path": "",
+    "type": "sentence_transformers.models.Transformer"
+  },
+  {
+    "idx": 1,
+    "name": "1",
+    "path": "1_Pooling",
+    "type": "sentence_transformers.models.Pooling"
+  },
+  {
+    "idx": 2,
+    "name": "2",
+    "path": "2_Normalize",
+    "type": "sentence_transformers.models.Normalize"
+  }
+]

sentence_bert_config.json

@@ -0,0 +1,4 @@
+{
+  "max_seq_length": 8192,
+  "do_lower_case": false
+}

sentencepiece.bpe.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cfc8146abe2a0488e9e2a0c56de7952f7c11ab059eca145a0a727afce0db2865
+size 5069051

special_tokens_map.json

@@ -0,0 +1,51 @@
+{
+  "bos_token": {
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "cls_token": {
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "mask_token": {
+    "content": "<mask>",
+    "lstrip": true,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<pad>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "sep_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e4f7e21bec3fb0044ca0bb2d50eb5d4d8c596273c422baef84466d2c73748b9c
+size 17083053

tokenizer_config.json

@@ -0,0 +1,56 @@
+{
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<pad>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "</s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "3": {
+      "content": "<unk>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "250001": {
+      "content": "<mask>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "<s>",
+  "clean_up_tokenization_spaces": true,
+  "cls_token": "<s>",
+  "eos_token": "</s>",
+  "extra_special_tokens": {},
+  "mask_token": "<mask>",
+  "model_max_length": 8192,
+  "pad_token": "<pad>",
+  "sep_token": "</s>",
+  "sp_model_kwargs": {},
+  "tokenizer_class": "XLMRobertaTokenizer",
+  "unk_token": "<unk>"
+}