Add new SentenceTransformer model

1_Pooling/config.json

@@ -0,0 +1,10 @@
+{
+  "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
+}

README.md

@@ -0,0 +1,762 @@
+---
+base_model: BAAI/bge-base-en-v1.5
+language:
+- fr
+library_name: sentence-transformers
+license: apache-2.0
+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
+pipeline_tag: sentence-similarity
+tags:
+- sentence-transformers
+- sentence-similarity
+- feature-extraction
+- generated_from_trainer
+- dataset_size:47560
+- loss:MatryoshkaLoss
+- loss:MultipleNegativesRankingLoss
+widget:
+- source_sentence: Qui a écouté le roi Asa et envoyé son armée contre les villes d'Israël?
+  sentences:
+  - Ben-Hadad.
+  - Il se prosterna devant le roi, le visage contre terre.
+  - Baescha, fils d'Achija.
+- source_sentence: Quelle est l'importance de distribuer tous ses biens aux pauvres
+    sans charité?
+  sentences:
+  - Adina, fils de Schiza, était le chef des Rubénites.
+  - Distribuer tous ses biens aux pauvres sans charité ne sert à rien.
+  - L'Éternel.
+- source_sentence: Qui sont les enfants du père d'Étham?
+  sentences:
+  - Jizreel, Jischma, Jidbasch et leur sœur Hatselelponi.
+  - Chaque division comptait vingt-quatre mille hommes.
+  - 'Hosa était un fils de Merari et il avait quatre fils: Schimri, Hilkija, Thebalia,
+    et Zacharie.'
+- source_sentence: Combien de temps Nadab, fils de Jéroboam, a-t-il régné sur Israël?
+  sentences:
+  - Ils sont des serviteurs par le moyen desquels les frères ont cru, selon que le
+    Seigneur l'a donné à chacun.
+  - 'Sept fils: Jeusch, Benjamin, Éhud, Kenaana, Zéthan, Tarsis et Achischachar, enregistrés
+    au nombre de dix-sept mille deux cents.'
+  - Deux ans.
+- source_sentence: Quand les Lévites devaient-ils se présenter pour louer et célébrer
+    l'Éternel?
+  sentences:
+  - Chaque matin et chaque soir.
+  - Cinq mille talents d'or et dix mille talents d'argent ont été donnés.
+  - Il doit demeurer circoncis.
+model-index:
+- name: BGE base bible test
+  results:
+  - task:
+      type: information-retrieval
+      name: Information Retrieval
+    dataset:
+      name: dim 768
+      type: dim_768
+    metrics:
+    - type: cosine_accuracy@1
+      value: 0.13359388879019363
+      name: Cosine Accuracy@1
+    - type: cosine_accuracy@3
+      value: 0.18795523183513946
+      name: Cosine Accuracy@3
+    - type: cosine_accuracy@5
+      value: 0.21389234322259726
+      name: Cosine Accuracy@5
+    - type: cosine_accuracy@10
+      value: 0.25102149582519095
+      name: Cosine Accuracy@10
+    - type: cosine_precision@1
+      value: 0.13359388879019363
+      name: Cosine Precision@1
+    - type: cosine_precision@3
+      value: 0.06265174394504648
+      name: Cosine Precision@3
+    - type: cosine_precision@5
+      value: 0.04277846864451945
+      name: Cosine Precision@5
+    - type: cosine_precision@10
+      value: 0.0251021495825191
+      name: Cosine Precision@10
+    - type: cosine_recall@1
+      value: 0.13359388879019363
+      name: Cosine Recall@1
+    - type: cosine_recall@3
+      value: 0.18795523183513946
+      name: Cosine Recall@3
+    - type: cosine_recall@5
+      value: 0.21389234322259726
+      name: Cosine Recall@5
+    - type: cosine_recall@10
+      value: 0.25102149582519095
+      name: Cosine Recall@10
+    - type: cosine_ndcg@10
+      value: 0.18816833747648484
+      name: Cosine Ndcg@10
+    - type: cosine_mrr@10
+      value: 0.16858798117458645
+      name: Cosine Mrr@10
+    - type: cosine_map@100
+      value: 0.17400088915411802
+      name: Cosine Map@100
+  - task:
+      type: information-retrieval
+      name: Information Retrieval
+    dataset:
+      name: dim 512
+      type: dim_512
+    metrics:
+    - type: cosine_accuracy@1
+      value: 0.12773139101083675
+      name: Cosine Accuracy@1
+    - type: cosine_accuracy@3
+      value: 0.18546811156510926
+      name: Cosine Accuracy@3
+    - type: cosine_accuracy@5
+      value: 0.20572037662106946
+      name: Cosine Accuracy@5
+    - type: cosine_accuracy@10
+      value: 0.24213892343222598
+      name: Cosine Accuracy@10
+    - type: cosine_precision@1
+      value: 0.12773139101083675
+      name: Cosine Precision@1
+    - type: cosine_precision@3
+      value: 0.061822703855036416
+      name: Cosine Precision@3
+    - type: cosine_precision@5
+      value: 0.041144075324213894
+      name: Cosine Precision@5
+    - type: cosine_precision@10
+      value: 0.0242138923432226
+      name: Cosine Precision@10
+    - type: cosine_recall@1
+      value: 0.12773139101083675
+      name: Cosine Recall@1
+    - type: cosine_recall@3
+      value: 0.18546811156510926
+      name: Cosine Recall@3
+    - type: cosine_recall@5
+      value: 0.20572037662106946
+      name: Cosine Recall@5
+    - type: cosine_recall@10
+      value: 0.24213892343222598
+      name: Cosine Recall@10
+    - type: cosine_ndcg@10
+      value: 0.18151482198424093
+      name: Cosine Ndcg@10
+    - type: cosine_mrr@10
+      value: 0.1625760305898876
+      name: Cosine Mrr@10
+    - type: cosine_map@100
+      value: 0.16802226648065993
+      name: Cosine Map@100
+  - task:
+      type: information-retrieval
+      name: Information Retrieval
+    dataset:
+      name: dim 256
+      type: dim_256
+    metrics:
+    - type: cosine_accuracy@1
+      value: 0.12488896784508793
+      name: Cosine Accuracy@1
+    - type: cosine_accuracy@3
+      value: 0.17463137324569195
+      name: Cosine Accuracy@3
+    - type: cosine_accuracy@5
+      value: 0.19737075857168235
+      name: Cosine Accuracy@5
+    - type: cosine_accuracy@10
+      value: 0.23272339669568307
+      name: Cosine Accuracy@10
+    - type: cosine_precision@1
+      value: 0.12488896784508793
+      name: Cosine Precision@1
+    - type: cosine_precision@3
+      value: 0.058210457748563975
+      name: Cosine Precision@3
+    - type: cosine_precision@5
+      value: 0.03947415171433648
+      name: Cosine Precision@5
+    - type: cosine_precision@10
+      value: 0.023272339669568307
+      name: Cosine Precision@10
+    - type: cosine_recall@1
+      value: 0.12488896784508793
+      name: Cosine Recall@1
+    - type: cosine_recall@3
+      value: 0.17463137324569195
+      name: Cosine Recall@3
+    - type: cosine_recall@5
+      value: 0.19737075857168235
+      name: Cosine Recall@5
+    - type: cosine_recall@10
+      value: 0.23272339669568307
+      name: Cosine Recall@10
+    - type: cosine_ndcg@10
+      value: 0.17440736005896854
+      name: Cosine Ndcg@10
+    - type: cosine_mrr@10
+      value: 0.156282728049472
+      name: Cosine Mrr@10
+    - type: cosine_map@100
+      value: 0.16141647615447188
+      name: Cosine Map@100
+  - task:
+      type: information-retrieval
+      name: Information Retrieval
+    dataset:
+      name: dim 128
+      type: dim_128
+    metrics:
+    - type: cosine_accuracy@1
+      value: 0.10943329188132883
+      name: Cosine Accuracy@1
+    - type: cosine_accuracy@3
+      value: 0.15686622845976195
+      name: Cosine Accuracy@3
+    - type: cosine_accuracy@5
+      value: 0.17853970509859654
+      name: Cosine Accuracy@5
+    - type: cosine_accuracy@10
+      value: 0.20838514833895896
+      name: Cosine Accuracy@10
+    - type: cosine_precision@1
+      value: 0.10943329188132883
+      name: Cosine Precision@1
+    - type: cosine_precision@3
+      value: 0.052288742819920644
+      name: Cosine Precision@3
+    - type: cosine_precision@5
+      value: 0.03570794101971931
+      name: Cosine Precision@5
+    - type: cosine_precision@10
+      value: 0.0208385148338959
+      name: Cosine Precision@10
+    - type: cosine_recall@1
+      value: 0.10943329188132883
+      name: Cosine Recall@1
+    - type: cosine_recall@3
+      value: 0.15686622845976195
+      name: Cosine Recall@3
+    - type: cosine_recall@5
+      value: 0.17853970509859654
+      name: Cosine Recall@5
+    - type: cosine_recall@10
+      value: 0.20838514833895896
+      name: Cosine Recall@10
+    - type: cosine_ndcg@10
+      value: 0.15566336146326976
+      name: Cosine Ndcg@10
+    - type: cosine_mrr@10
+      value: 0.13917031134121227
+      name: Cosine Mrr@10
+    - type: cosine_map@100
+      value: 0.14405644027137798
+      name: Cosine Map@100
+  - task:
+      type: information-retrieval
+      name: Information Retrieval
+    dataset:
+      name: dim 64
+      type: dim_64
+    metrics:
+    - type: cosine_accuracy@1
+      value: 0.08935867827322792
+      name: Cosine Accuracy@1
+    - type: cosine_accuracy@3
+      value: 0.13181737431160065
+      name: Cosine Accuracy@3
+    - type: cosine_accuracy@5
+      value: 0.15011547344110854
+      name: Cosine Accuracy@5
+    - type: cosine_accuracy@10
+      value: 0.17694084206786284
+      name: Cosine Accuracy@10
+    - type: cosine_precision@1
+      value: 0.08935867827322792
+      name: Cosine Precision@1
+    - type: cosine_precision@3
+      value: 0.04393912477053354
+      name: Cosine Precision@3
+    - type: cosine_precision@5
+      value: 0.03002309468822171
+      name: Cosine Precision@5
+    - type: cosine_precision@10
+      value: 0.01769408420678629
+      name: Cosine Precision@10
+    - type: cosine_recall@1
+      value: 0.08935867827322792
+      name: Cosine Recall@1
+    - type: cosine_recall@3
+      value: 0.13181737431160065
+      name: Cosine Recall@3
+    - type: cosine_recall@5
+      value: 0.15011547344110854
+      name: Cosine Recall@5
+    - type: cosine_recall@10
+      value: 0.17694084206786284
+      name: Cosine Recall@10
+    - type: cosine_ndcg@10
+      value: 0.13031373727839585
+      name: Cosine Ndcg@10
+    - type: cosine_mrr@10
+      value: 0.11575599150656894
+      name: Cosine Mrr@10
+    - type: cosine_map@100
+      value: 0.12066444582998255
+      name: Cosine Map@100
+---
+
+# BGE base bible test
+
+This is a [sentence-transformers](https://www.SBERT.net) model finetuned from [BAAI/bge-base-en-v1.5](https://huggingface.co/BAAI/bge-base-en-v1.5) on the json dataset. 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:** [BAAI/bge-base-en-v1.5](https://huggingface.co/BAAI/bge-base-en-v1.5) <!-- at revision a5beb1e3e68b9ab74eb54cfd186867f64f240e1a -->
+- **Maximum Sequence Length:** 512 tokens
+- **Output Dimensionality:** 768 dimensions
+- **Similarity Function:** Cosine Similarity
+- **Training Dataset:**
+    - json
+- **Language:** fr
+- **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': 512, 'do_lower_case': True}) with Transformer model: BertModel 
+  (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})
+  (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("Steve77/bge-base-bible-retrieval")
+# Run inference
+sentences = [
+    "Quand les Lévites devaient-ils se présenter pour louer et célébrer l'Éternel?",
+    'Chaque matin et chaque soir.',
+    "Cinq mille talents d'or et dix mille talents d'argent ont été donnés.",
+]
+embeddings = model.encode(sentences)
+print(embeddings.shape)
+# [3, 768]
+
+# 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_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_768    | dim_512    | dim_256    | dim_128    | dim_64     |
+|:--------------------|:-----------|:-----------|:-----------|:-----------|:-----------|
+| cosine_accuracy@1   | 0.1336     | 0.1277     | 0.1249     | 0.1094     | 0.0894     |
+| cosine_accuracy@3   | 0.188      | 0.1855     | 0.1746     | 0.1569     | 0.1318     |
+| cosine_accuracy@5   | 0.2139     | 0.2057     | 0.1974     | 0.1785     | 0.1501     |
+| cosine_accuracy@10  | 0.251      | 0.2421     | 0.2327     | 0.2084     | 0.1769     |
+| cosine_precision@1  | 0.1336     | 0.1277     | 0.1249     | 0.1094     | 0.0894     |
+| cosine_precision@3  | 0.0627     | 0.0618     | 0.0582     | 0.0523     | 0.0439     |
+| cosine_precision@5  | 0.0428     | 0.0411     | 0.0395     | 0.0357     | 0.03       |
+| cosine_precision@10 | 0.0251     | 0.0242     | 0.0233     | 0.0208     | 0.0177     |
+| cosine_recall@1     | 0.1336     | 0.1277     | 0.1249     | 0.1094     | 0.0894     |
+| cosine_recall@3     | 0.188      | 0.1855     | 0.1746     | 0.1569     | 0.1318     |
+| cosine_recall@5     | 0.2139     | 0.2057     | 0.1974     | 0.1785     | 0.1501     |
+| cosine_recall@10    | 0.251      | 0.2421     | 0.2327     | 0.2084     | 0.1769     |
+| **cosine_ndcg@10**  | **0.1882** | **0.1815** | **0.1744** | **0.1557** | **0.1303** |
+| cosine_mrr@10       | 0.1686     | 0.1626     | 0.1563     | 0.1392     | 0.1158     |
+| cosine_map@100      | 0.174      | 0.168      | 0.1614     | 0.1441     | 0.1207     |
+
+<!--
+## 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
+
+#### json
+
+* Dataset: json
+* Size: 47,560 training samples
+* Columns: <code>anchor</code> and <code>positive</code>
+* Approximate statistics based on the first 1000 samples:
+  |         | anchor                                                                            | positive                                                                           |
+  |:--------|:----------------------------------------------------------------------------------|:-----------------------------------------------------------------------------------|
+  | type    | string                                                                            | string                                                                             |
+  | details | <ul><li>min: 8 tokens</li><li>mean: 21.23 tokens</li><li>max: 45 tokens</li></ul> | <ul><li>min: 3 tokens</li><li>mean: 25.14 tokens</li><li>max: 110 tokens</li></ul> |
+* Samples:
+  | anchor                                                | positive                                            |
+  |:------------------------------------------------------|:----------------------------------------------------|
+  | <code>Quels sont les noms des fils de Schobal?</code> | <code>Aljan, Manahath, Ébal, Schephi et Onam</code> |
+  | <code>Quels sont les noms des fils de Tsibeon?</code> | <code>Ajja et Ana</code>                            |
+  | <code>Qui est le fils d'Ana?</code>                   | <code>Dischon</code>                                |
+* Loss: [<code>MatryoshkaLoss</code>](https://sbert.net/docs/package_reference/sentence_transformer/losses.html#matryoshkaloss) with these parameters:
+  ```json
+  {
+      "loss": "MultipleNegativesRankingLoss",
+      "matryoshka_dims": [
+          768,
+          512,
+          256,
+          128,
+          64
+      ],
+      "matryoshka_weights": [
+          1,
+          1,
+          1,
+          1,
+          1
+      ],
+      "n_dims_per_step": -1
+  }
+  ```
+
+### Training Hyperparameters
+#### Non-Default Hyperparameters
+
+- `eval_strategy`: epoch
+- `per_device_train_batch_size`: 16
+- `per_device_eval_batch_size`: 16
+- `gradient_accumulation_steps`: 16
+- `learning_rate`: 2e-05
+- `lr_scheduler_type`: cosine
+- `warmup_ratio`: 0.1
+- `bf16`: True
+- `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`: 16
+- `per_device_eval_batch_size`: 16
+- `per_gpu_train_batch_size`: None
+- `per_gpu_eval_batch_size`: None
+- `gradient_accumulation_steps`: 16
+- `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`: 3
+- `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`: True
+- `fp16`: False
+- `fp16_opt_level`: O1
+- `half_precision_backend`: auto
+- `bf16_full_eval`: False
+- `fp16_full_eval`: False
+- `tf32`: None
+- `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`: False
+- `hub_always_push`: False
+- `gradient_checkpointing`: False
+- `gradient_checkpointing_kwargs`: None
+- `include_inputs_for_metrics`: False
+- `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
+- `prompts`: None
+- `batch_sampler`: no_duplicates
+- `multi_dataset_batch_sampler`: proportional
+
+</details>
+
+### Training Logs
+| Epoch      | Step    | Training Loss | 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 |
+|:----------:|:-------:|:-------------:|:----------------------:|:----------------------:|:----------------------:|:----------------------:|:---------------------:|
+| 0.0538     | 10      | 12.8804       | -                      | -                      | -                      | -                      | -                     |
+| 0.1076     | 20      | 12.4714       | -                      | -                      | -                      | -                      | -                     |
+| 0.1615     | 30      | 11.8263       | -                      | -                      | -                      | -                      | -                     |
+| 0.2153     | 40      | 11.014        | -                      | -                      | -                      | -                      | -                     |
+| 0.2691     | 50      | 10.1609       | -                      | -                      | -                      | -                      | -                     |
+| 0.3229     | 60      | 10.6807       | -                      | -                      | -                      | -                      | -                     |
+| 0.3767     | 70      | 9.3215        | -                      | -                      | -                      | -                      | -                     |
+| 0.4305     | 80      | 10.3719       | -                      | -                      | -                      | -                      | -                     |
+| 0.4844     | 90      | 9.4147        | -                      | -                      | -                      | -                      | -                     |
+| 0.5382     | 100     | 9.5567        | -                      | -                      | -                      | -                      | -                     |
+| 0.5920     | 110     | 8.7699        | -                      | -                      | -                      | -                      | -                     |
+| 0.6458     | 120     | 9.0428        | -                      | -                      | -                      | -                      | -                     |
+| 0.6996     | 130     | 9.0977        | -                      | -                      | -                      | -                      | -                     |
+| 0.7534     | 140     | 8.0843        | -                      | -                      | -                      | -                      | -                     |
+| 0.8073     | 150     | 8.1363        | -                      | -                      | -                      | -                      | -                     |
+| 0.8611     | 160     | 7.5306        | -                      | -                      | -                      | -                      | -                     |
+| 0.9149     | 170     | 7.7972        | -                      | -                      | -                      | -                      | -                     |
+| 0.9687     | 180     | 7.9644        | -                      | -                      | -                      | -                      | -                     |
+| 0.9956     | 185     | -             | 0.1917                 | 0.1879                 | 0.1784                 | 0.1583                 | 0.1268                |
+| 1.0225     | 190     | 7.6124        | -                      | -                      | -                      | -                      | -                     |
+| 1.0764     | 200     | 6.6315        | -                      | -                      | -                      | -                      | -                     |
+| 1.1302     | 210     | 7.2313        | -                      | -                      | -                      | -                      | -                     |
+| 1.1840     | 220     | 6.5394        | -                      | -                      | -                      | -                      | -                     |
+| 1.2378     | 230     | 6.7843        | -                      | -                      | -                      | -                      | -                     |
+| 1.2916     | 240     | 6.9276        | -                      | -                      | -                      | -                      | -                     |
+| 1.3454     | 250     | 7.2281        | -                      | -                      | -                      | -                      | -                     |
+| 1.3993     | 260     | 6.9158        | -                      | -                      | -                      | -                      | -                     |
+| 1.4531     | 270     | 6.5158        | -                      | -                      | -                      | -                      | -                     |
+| 1.5069     | 280     | 6.916         | -                      | -                      | -                      | -                      | -                     |
+| 1.5607     | 290     | 6.5717        | -                      | -                      | -                      | -                      | -                     |
+| 1.6145     | 300     | 6.9225        | -                      | -                      | -                      | -                      | -                     |
+| 1.6683     | 310     | 7.3981        | -                      | -                      | -                      | -                      | -                     |
+| 1.7222     | 320     | 6.894         | -                      | -                      | -                      | -                      | -                     |
+| 1.7760     | 330     | 6.0293        | -                      | -                      | -                      | -                      | -                     |
+| 1.8298     | 340     | 5.9389        | -                      | -                      | -                      | -                      | -                     |
+| 1.8836     | 350     | 5.959         | -                      | -                      | -                      | -                      | -                     |
+| 1.9374     | 360     | 6.4268        | -                      | -                      | -                      | -                      | -                     |
+| 1.9913     | 370     | 6.7366        | -                      | -                      | -                      | -                      | -                     |
+| **1.9966** | **371** | **-**         | **0.2012**             | **0.1965**             | **0.1862**             | **0.1633**             | **0.1361**            |
+| 2.0451     | 380     | 5.7871        | -                      | -                      | -                      | -                      | -                     |
+| 2.0989     | 390     | 5.7358        | -                      | -                      | -                      | -                      | -                     |
+| 2.1527     | 400     | 6.0964        | -                      | -                      | -                      | -                      | -                     |
+| 2.2065     | 410     | 5.8331        | -                      | -                      | -                      | -                      | -                     |
+| 2.2603     | 420     | 5.6152        | -                      | -                      | -                      | -                      | -                     |
+| 2.3142     | 430     | 6.5018        | -                      | -                      | -                      | -                      | -                     |
+| 2.3680     | 440     | 5.9798        | -                      | -                      | -                      | -                      | -                     |
+| 2.4218     | 450     | 6.0598        | -                      | -                      | -                      | -                      | -                     |
+| 2.4756     | 460     | 5.8222        | -                      | -                      | -                      | -                      | -                     |
+| 2.5294     | 470     | 6.303         | -                      | -                      | -                      | -                      | -                     |
+| 2.5832     | 480     | 5.9648        | -                      | -                      | -                      | -                      | -                     |
+| 2.6371     | 490     | 6.415         | -                      | -                      | -                      | -                      | -                     |
+| 2.6909     | 500     | 7.084         | -                      | -                      | -                      | -                      | -                     |
+| 2.7447     | 510     | 5.692         | -                      | -                      | -                      | -                      | -                     |
+| 2.7985     | 520     | 5.7706        | -                      | -                      | -                      | -                      | -                     |
+| 2.8523     | 530     | 5.6943        | -                      | -                      | -                      | -                      | -                     |
+| 2.9062     | 540     | 5.6817        | -                      | -                      | -                      | -                      | -                     |
+| 2.9600     | 550     | 6.1265        | -                      | -                      | -                      | -                      | -                     |
+| 2.9869     | 555     | -             | 0.1882                 | 0.1815                 | 0.1744                 | 0.1557                 | 0.1303                |
+
+* The bold row denotes the saved checkpoint.
+
+### Framework Versions
+- Python: 3.11.11
+- Sentence Transformers: 3.3.1
+- Transformers: 4.45.2
+- PyTorch: 2.5.1
+- Accelerate: 1.2.1
+- Datasets: 2.19.1
+- Tokenizers: 0.20.1
+
+## 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 +1,32 @@
+{
+  "_name_or_path": "BAAI/bge-base-en-v1.5",
+  "architectures": [
+    "BertModel"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "classifier_dropout": null,
+  "gradient_checkpointing": false,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 768,
+  "id2label": {
+    "0": "LABEL_0"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "label2id": {
+    "LABEL_0": 0
+  },
+  "layer_norm_eps": 1e-12,
+  "max_position_embeddings": 512,
+  "model_type": "bert",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
+  "pad_token_id": 0,
+  "position_embedding_type": "absolute",
+  "torch_dtype": "float32",
+  "transformers_version": "4.45.2",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 30522
+}

config_sentence_transformers.json

@@ -0,0 +1,10 @@
+{
+  "__version__": {
+    "sentence_transformers": "3.3.1",
+    "transformers": "4.45.2",
+    "pytorch": "2.5.1"
+  },
+  "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:e7a1d37e06ff7b9d21e40b371b6cab97e896a6afe043f56b77f79f8c4cadf1f0
+size 437951328

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": 512,
+  "do_lower_case": true
+}

special_tokens_map.json

@@ -0,0 +1,37 @@
+{
+  "cls_token": {
+    "content": "[CLS]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "mask_token": {
+    "content": "[MASK]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "[PAD]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "sep_token": {
+    "content": "[SEP]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "[UNK]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer_config.json

@@ -0,0 +1,57 @@
+{
+  "added_tokens_decoder": {
+    "0": {
+      "content": "[PAD]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "100": {
+      "content": "[UNK]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "101": {
+      "content": "[CLS]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "102": {
+      "content": "[SEP]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "103": {
+      "content": "[MASK]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "clean_up_tokenization_spaces": true,
+  "cls_token": "[CLS]",
+  "do_basic_tokenize": true,
+  "do_lower_case": true,
+  "mask_token": "[MASK]",
+  "model_max_length": 512,
+  "never_split": null,
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "strip_accents": null,
+  "tokenize_chinese_chars": true,
+  "tokenizer_class": "BertTokenizer",
+  "unk_token": "[UNK]"
+}