Upload fine-tuned 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 +1,511 @@
+---
+language:
+- en
+license: apache-2.0
+tags:
+- sentence-transformers
+- sentence-similarity
+- feature-extraction
+- generated_from_trainer
+- dataset_size:843
+- loss:MatryoshkaLoss
+- loss:MultipleNegativesRankingLoss
+base_model: BAAI/bge-base-en-v1.5
+widget:
+- source_sentence: (1) No person shall make attempt to commit an offence. Even if
+    it is impossible for an offence to be committed for which attempt is made, attempt
+    shall be considered to have been committed. Except as otherwise provided elsewhere
+    in this Act, a person who attempts, or causes attempt, to commit an offence shall
+    be punished with one half of the punishment specified for such offence. .
+  sentences:
+  - How is the punishment for an attempt determined?
+  - What are the different types of guarantees?
+  - What are the specific types of crimes that are considered 'strict liability'?
+- source_sentence: ': (1) No person shall commit, or cause to be committed, cheating.
+    (2) For the purposes of sub-section (1), a person who dishonestly causes any kind
+    of loss, damage or injury to another person whom he or she makes believe in some
+    matter or to any other person or obtains any benefit for him or her or any one
+    else by omitting to do as per such belief or by inducement, fraudulent, dishonest
+    or otherwise deceptive act or preventing such other person from doing any act
+    shall be considered to commit cheating.'
+  sentences:
+  - How is 'fraudulent concealment' defined?
+  - What are the terms and restrictions that must be followed when producing explosives
+    under a license?
+  - What is the process for determining the appropriate penalty for a cheating offense?
+- source_sentence: (1) No person shall restraint or otherwise obstruct or hinder a
+    person who, upon knowing that an offence has been committed or is about to be
+    committed, intends to give information or notice about such offence to the police
+    or competent authority. imprisonment for a term not exceeding two years or a fine
+    not exceeding twenty thousand rupees or both the sentences.
+  sentences:
+  - What actions constitute 'restraint, obstruction, or hindrance'?
+  - What are the consequences of engaging in such conduct?
+  - What are the different categories of victims, and how do the penalties vary based
+    on their age?
+- source_sentence: This law prohibits the creation, use, possession, or sale of inaccurate
+    weighing, measuring, or quality-standard instruments.  It also prohibits tampering
+    with seals or marks on these instruments, or manipulating their accuracy.  Violations
+    carry a penalty of up to three years imprisonment and a fine.  Instruments and
+    tools used in the offense are subject to forfeiture.
+  sentences:
+  - What are the penalties for using banned currency?
+  - What is the time frame for reporting an offense under this law?
+  - When does this law come into effect?
+- source_sentence: This section lists factors that decrease the seriousness of a crime.  These
+    include age (under 18 or over 75), lack of intent, provocation by the victim,
+    retaliation for a serious offense, confession and remorse, surrender to authorities,
+    compensation to the victim, diminished capacity, insignificant harm, assistance
+    in the judicial process, confession with a promise of no future crime, and crimes
+    committed under duress.
+  sentences:
+  - What constitutes "lack of intent" in this context?
+  - What is the difference between an attempt and the actual commission of a crime?
+  - What are the exceptions to the prohibition on property transactions in marriage?
+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 base Financial Matryoshka
+  results:
+  - task:
+      type: information-retrieval
+      name: Information Retrieval
+    dataset:
+      name: dim 128
+      type: dim_128
+    metrics:
+    - type: cosine_accuracy@1
+      value: 0.13744075829383887
+      name: Cosine Accuracy@1
+    - type: cosine_accuracy@3
+      value: 0.4312796208530806
+      name: Cosine Accuracy@3
+    - type: cosine_accuracy@5
+      value: 0.5450236966824644
+      name: Cosine Accuracy@5
+    - type: cosine_accuracy@10
+      value: 0.6445497630331753
+      name: Cosine Accuracy@10
+    - type: cosine_precision@1
+      value: 0.13744075829383887
+      name: Cosine Precision@1
+    - type: cosine_precision@3
+      value: 0.14375987361769352
+      name: Cosine Precision@3
+    - type: cosine_precision@5
+      value: 0.10900473933649289
+      name: Cosine Precision@5
+    - type: cosine_precision@10
+      value: 0.06445497630331752
+      name: Cosine Precision@10
+    - type: cosine_recall@1
+      value: 0.13744075829383887
+      name: Cosine Recall@1
+    - type: cosine_recall@3
+      value: 0.4312796208530806
+      name: Cosine Recall@3
+    - type: cosine_recall@5
+      value: 0.5450236966824644
+      name: Cosine Recall@5
+    - type: cosine_recall@10
+      value: 0.6445497630331753
+      name: Cosine Recall@10
+    - type: cosine_ndcg@10
+      value: 0.38906851558265765
+      name: Cosine Ndcg@10
+    - type: cosine_mrr@10
+      value: 0.3073817046565864
+      name: Cosine Mrr@10
+    - type: cosine_map@100
+      value: 0.31738583597003633
+      name: Cosine Map@100
+---
+
+# BGE base Financial Matryoshka
+
+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). 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:** Unknown -->
+- **Language:** en
+- **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("sentence_transformers_model_id")
+# Run inference
+sentences = [
+    'This section lists factors that decrease the seriousness of a crime.  These include age (under 18 or over 75), lack of intent, provocation by the victim, retaliation for a serious offense, confession and remorse, surrender to authorities, compensation to the victim, diminished capacity, insignificant harm, assistance in the judicial process, confession with a promise of no future crime, and crimes committed under duress.',
+    'What constitutes "lack of intent" in this context?',
+    'What are the exceptions to the prohibition on property transactions in marriage?',
+]
+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
+
+* Dataset: `dim_128`
+* Evaluated with [<code>InformationRetrievalEvaluator</code>](https://sbert.net/docs/package_reference/sentence_transformer/evaluation.html#sentence_transformers.evaluation.InformationRetrievalEvaluator)
+
+| Metric              | Value      |
+|:--------------------|:-----------|
+| cosine_accuracy@1   | 0.1374     |
+| cosine_accuracy@3   | 0.4313     |
+| cosine_accuracy@5   | 0.545      |
+| cosine_accuracy@10  | 0.6445     |
+| cosine_precision@1  | 0.1374     |
+| cosine_precision@3  | 0.1438     |
+| cosine_precision@5  | 0.109      |
+| cosine_precision@10 | 0.0645     |
+| cosine_recall@1     | 0.1374     |
+| cosine_recall@3     | 0.4313     |
+| cosine_recall@5     | 0.545      |
+| cosine_recall@10    | 0.6445     |
+| **cosine_ndcg@10**  | **0.3891** |
+| cosine_mrr@10       | 0.3074     |
+| cosine_map@100      | 0.3174     |
+
+<!--
+## 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: 843 training samples
+* Columns: <code>positive</code> and <code>anchor</code>
+* Approximate statistics based on the first 843 samples:
+  |         | positive                                                                           | anchor                                                                            |
+  |:--------|:-----------------------------------------------------------------------------------|:----------------------------------------------------------------------------------|
+  | type    | string                                                                             | string                                                                            |
+  | details | <ul><li>min: 9 tokens</li><li>mean: 66.68 tokens</li><li>max: 151 tokens</li></ul> | <ul><li>min: 7 tokens</li><li>mean: 14.77 tokens</li><li>max: 39 tokens</li></ul> |
+* Samples:
+  | positive                                                                                                                                                                                                                                                                                                                        | anchor                                                                                                  |
+  |:--------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|:--------------------------------------------------------------------------------------------------------|
+  | <code>This law prohibits unlawful detention of individuals.  It outlines penalties for unlawful confinement and obstruction of a person's movement.  It also specifies a time limit for complaints related to certain offenses.</code>                                                                                          | <code>What is the process for reporting unlawful detention?</code>                                      |
+  | <code>No complaint shall lie in relation to any of the offences under Section 290, after the expiry of three months from the date of commission of such offence, and in relation to any of the other offences under this Chapter, after the expiry of three months from the date of knowledge of commission of such act.</code> | <code>What are the time limits for reporting and prosecuting offenses related to animal cruelty?</code> |
+  | <code>(1) No person, being legally bound to receive a summons, process, notice, arrest warrant or order issued by the competent authority, shall abscond, with mala fide intention to avoid being served with such summons, process, notice, arrest warrant or order.</code>                                                    | <code>What is the legal definition of being "legally bound" to receive a document?</code>               |
+* Loss: [<code>MatryoshkaLoss</code>](https://sbert.net/docs/package_reference/sentence_transformer/losses.html#matryoshkaloss) with these parameters:
+  ```json
+  {
+      "loss": "MultipleNegativesRankingLoss",
+      "matryoshka_dims": [
+          128
+      ],
+      "matryoshka_weights": [
+          1
+      ],
+      "n_dims_per_step": -1
+  }
+  ```
+
+### Training Hyperparameters
+#### Non-Default Hyperparameters
+
+- `eval_strategy`: epoch
+- `per_device_train_batch_size`: 32
+- `per_device_eval_batch_size`: 16
+- `gradient_accumulation_steps`: 16
+- `learning_rate`: 2e-05
+- `num_train_epochs`: 1
+- `lr_scheduler_type`: cosine
+- `warmup_ratio`: 0.1
+- `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`: 32
+- `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`: 1
+- `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`: False
+- `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  | dim_128_cosine_ndcg@10 |
+|:----------:|:-----:|:----------------------:|
+| **0.5926** | **1** | **0.3891**             |
+
+* The bold row denotes the saved checkpoint.
+
+### Framework Versions
+- Python: 3.10.12
+- Sentence Transformers: 3.3.1
+- Transformers: 4.47.1
+- PyTorch: 2.5.1+cu121
+- Accelerate: 0.27.0
+- Datasets: 3.2.0
+- 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.*
+-->

checkpoint-22/1_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
+}

checkpoint-22/README.md

@@ -0,0 +1,522 @@
+---
+language:
+- en
+license: apache-2.0
+tags:
+- sentence-transformers
+- sentence-similarity
+- feature-extraction
+- generated_from_trainer
+- dataset_size:843
+- loss:MatryoshkaLoss
+- loss:MultipleNegativesRankingLoss
+base_model: BAAI/bge-base-en-v1.5
+widget:
+- source_sentence: (1) No person shall make attempt to commit an offence. Even if
+    it is impossible for an offence to be committed for which attempt is made, attempt
+    shall be considered to have been committed. Except as otherwise provided elsewhere
+    in this Act, a person who attempts, or causes attempt, to commit an offence shall
+    be punished with one half of the punishment specified for such offence. .
+  sentences:
+  - How is the punishment for an attempt determined?
+  - What are the different types of guarantees?
+  - What are the specific types of crimes that are considered 'strict liability'?
+- source_sentence: ': (1) No person shall commit, or cause to be committed, cheating.
+    (2) For the purposes of sub-section (1), a person who dishonestly causes any kind
+    of loss, damage or injury to another person whom he or she makes believe in some
+    matter or to any other person or obtains any benefit for him or her or any one
+    else by omitting to do as per such belief or by inducement, fraudulent, dishonest
+    or otherwise deceptive act or preventing such other person from doing any act
+    shall be considered to commit cheating.'
+  sentences:
+  - How is 'fraudulent concealment' defined?
+  - What are the terms and restrictions that must be followed when producing explosives
+    under a license?
+  - What is the process for determining the appropriate penalty for a cheating offense?
+- source_sentence: (1) No person shall restraint or otherwise obstruct or hinder a
+    person who, upon knowing that an offence has been committed or is about to be
+    committed, intends to give information or notice about such offence to the police
+    or competent authority. imprisonment for a term not exceeding two years or a fine
+    not exceeding twenty thousand rupees or both the sentences.
+  sentences:
+  - What actions constitute 'restraint, obstruction, or hindrance'?
+  - What are the consequences of engaging in such conduct?
+  - What are the different categories of victims, and how do the penalties vary based
+    on their age?
+- source_sentence: This law prohibits the creation, use, possession, or sale of inaccurate
+    weighing, measuring, or quality-standard instruments.  It also prohibits tampering
+    with seals or marks on these instruments, or manipulating their accuracy.  Violations
+    carry a penalty of up to three years imprisonment and a fine.  Instruments and
+    tools used in the offense are subject to forfeiture.
+  sentences:
+  - What are the penalties for using banned currency?
+  - What is the time frame for reporting an offense under this law?
+  - When does this law come into effect?
+- source_sentence: This section lists factors that decrease the seriousness of a crime.  These
+    include age (under 18 or over 75), lack of intent, provocation by the victim,
+    retaliation for a serious offense, confession and remorse, surrender to authorities,
+    compensation to the victim, diminished capacity, insignificant harm, assistance
+    in the judicial process, confession with a promise of no future crime, and crimes
+    committed under duress.
+  sentences:
+  - What constitutes "lack of intent" in this context?
+  - What is the difference between an attempt and the actual commission of a crime?
+  - What are the exceptions to the prohibition on property transactions in marriage?
+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 base Financial Matryoshka
+  results:
+  - task:
+      type: information-retrieval
+      name: Information Retrieval
+    dataset:
+      name: dim 128
+      type: dim_128
+    metrics:
+    - type: cosine_accuracy@1
+      value: 0.22748815165876776
+      name: Cosine Accuracy@1
+    - type: cosine_accuracy@3
+      value: 0.5592417061611374
+      name: Cosine Accuracy@3
+    - type: cosine_accuracy@5
+      value: 0.6872037914691943
+      name: Cosine Accuracy@5
+    - type: cosine_accuracy@10
+      value: 0.7962085308056872
+      name: Cosine Accuracy@10
+    - type: cosine_precision@1
+      value: 0.22748815165876776
+      name: Cosine Precision@1
+    - type: cosine_precision@3
+      value: 0.18641390205371247
+      name: Cosine Precision@3
+    - type: cosine_precision@5
+      value: 0.13744075829383884
+      name: Cosine Precision@5
+    - type: cosine_precision@10
+      value: 0.07962085308056871
+      name: Cosine Precision@10
+    - type: cosine_recall@1
+      value: 0.22748815165876776
+      name: Cosine Recall@1
+    - type: cosine_recall@3
+      value: 0.5592417061611374
+      name: Cosine Recall@3
+    - type: cosine_recall@5
+      value: 0.6872037914691943
+      name: Cosine Recall@5
+    - type: cosine_recall@10
+      value: 0.7962085308056872
+      name: Cosine Recall@10
+    - type: cosine_ndcg@10
+      value: 0.5057041685567575
+      name: Cosine Ndcg@10
+    - type: cosine_mrr@10
+      value: 0.4129203340103815
+      name: Cosine Mrr@10
+    - type: cosine_map@100
+      value: 0.4195949550112758
+      name: Cosine Map@100
+---
+
+# BGE base Financial Matryoshka
+
+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). 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:** Unknown -->
+- **Language:** en
+- **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("sentence_transformers_model_id")
+# Run inference
+sentences = [
+    'This section lists factors that decrease the seriousness of a crime.  These include age (under 18 or over 75), lack of intent, provocation by the victim, retaliation for a serious offense, confession and remorse, surrender to authorities, compensation to the victim, diminished capacity, insignificant harm, assistance in the judicial process, confession with a promise of no future crime, and crimes committed under duress.',
+    'What constitutes "lack of intent" in this context?',
+    'What are the exceptions to the prohibition on property transactions in marriage?',
+]
+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
+
+* Dataset: `dim_128`
+* Evaluated with [<code>InformationRetrievalEvaluator</code>](https://sbert.net/docs/package_reference/sentence_transformer/evaluation.html#sentence_transformers.evaluation.InformationRetrievalEvaluator)
+
+| Metric              | Value      |
+|:--------------------|:-----------|
+| cosine_accuracy@1   | 0.2275     |
+| cosine_accuracy@3   | 0.5592     |
+| cosine_accuracy@5   | 0.6872     |
+| cosine_accuracy@10  | 0.7962     |
+| cosine_precision@1  | 0.2275     |
+| cosine_precision@3  | 0.1864     |
+| cosine_precision@5  | 0.1374     |
+| cosine_precision@10 | 0.0796     |
+| cosine_recall@1     | 0.2275     |
+| cosine_recall@3     | 0.5592     |
+| cosine_recall@5     | 0.6872     |
+| cosine_recall@10    | 0.7962     |
+| **cosine_ndcg@10**  | **0.5057** |
+| cosine_mrr@10       | 0.4129     |
+| cosine_map@100      | 0.4196     |
+
+<!--
+## 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: 843 training samples
+* Columns: <code>positive</code> and <code>anchor</code>
+* Approximate statistics based on the first 843 samples:
+  |         | positive                                                                           | anchor                                                                            |
+  |:--------|:-----------------------------------------------------------------------------------|:----------------------------------------------------------------------------------|
+  | type    | string                                                                             | string                                                                            |
+  | details | <ul><li>min: 9 tokens</li><li>mean: 66.68 tokens</li><li>max: 151 tokens</li></ul> | <ul><li>min: 7 tokens</li><li>mean: 14.77 tokens</li><li>max: 39 tokens</li></ul> |
+* Samples:
+  | positive                                                                                                                                                                                                                                                                                                                        | anchor                                                                                                  |
+  |:--------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|:--------------------------------------------------------------------------------------------------------|
+  | <code>This law prohibits unlawful detention of individuals.  It outlines penalties for unlawful confinement and obstruction of a person's movement.  It also specifies a time limit for complaints related to certain offenses.</code>                                                                                          | <code>What is the process for reporting unlawful detention?</code>                                      |
+  | <code>No complaint shall lie in relation to any of the offences under Section 290, after the expiry of three months from the date of commission of such offence, and in relation to any of the other offences under this Chapter, after the expiry of three months from the date of knowledge of commission of such act.</code> | <code>What are the time limits for reporting and prosecuting offenses related to animal cruelty?</code> |
+  | <code>(1) No person, being legally bound to receive a summons, process, notice, arrest warrant or order issued by the competent authority, shall abscond, with mala fide intention to avoid being served with such summons, process, notice, arrest warrant or order.</code>                                                    | <code>What is the legal definition of being "legally bound" to receive a document?</code>               |
+* Loss: [<code>MatryoshkaLoss</code>](https://sbert.net/docs/package_reference/sentence_transformer/losses.html#matryoshkaloss) with these parameters:
+  ```json
+  {
+      "loss": "MultipleNegativesRankingLoss",
+      "matryoshka_dims": [
+          128
+      ],
+      "matryoshka_weights": [
+          1
+      ],
+      "n_dims_per_step": -1
+  }
+  ```
+
+### Training Hyperparameters
+#### Non-Default Hyperparameters
+
+- `eval_strategy`: epoch
+- `per_device_train_batch_size`: 32
+- `per_device_eval_batch_size`: 16
+- `gradient_accumulation_steps`: 16
+- `learning_rate`: 2e-05
+- `num_train_epochs`: 30
+- `lr_scheduler_type`: cosine
+- `warmup_ratio`: 0.1
+- `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`: 32
+- `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`: 30
+- `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`: False
+- `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_128_cosine_ndcg@10 |
+|:----------:|:-----:|:-------------:|:----------------------:|
+| **0.5926** | **1** | **-**         | **0.3891**             |
+| 1.0        | 2     | -             | 0.4127                 |
+| 2.0        | 4     | -             | 0.4611                 |
+| 3.0        | 6     | -             | 0.4676                 |
+| 4.0        | 8     | -             | 0.4909                 |
+| 5.0        | 10    | 1.1743        | 0.4808                 |
+| 6.0        | 12    | -             | 0.4891                 |
+| 7.0        | 14    | -             | 0.5027                 |
+| 8.0        | 16    | -             | 0.4979                 |
+| 9.0        | 18    | -             | 0.5047                 |
+| 10.0       | 20    | 0.5481        | 0.5031                 |
+| 11.0       | 22    | -             | 0.5057                 |
+
+* The bold row denotes the saved checkpoint.
+
+### Framework Versions
+- Python: 3.10.12
+- Sentence Transformers: 3.3.1
+- Transformers: 4.47.1
+- PyTorch: 2.5.1+cu121
+- Accelerate: 0.27.0
+- Datasets: 3.2.0
+- 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.*
+-->

checkpoint-22/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": "4.47.1",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 30522
+}

checkpoint-22/config_sentence_transformers.json

@@ -0,0 +1,10 @@
+{
+  "__version__": {
+    "sentence_transformers": "3.3.1",
+    "transformers": "4.47.1",
+    "pytorch": "2.5.1+cu121"
+  },
+  "prompts": {},
+  "default_prompt_name": null,
+  "similarity_fn_name": "cosine"
+}

checkpoint-22/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5335aa639a8a337c9d55541256abea22d90f9087c2a6d8344804675de776523e
+size 437951328

checkpoint-22/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"
+  }
+]

checkpoint-22/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:56401e0afb6ad4061210adb67cea0957f1a998412d6d13769bd97f796e735848
+size 14244

checkpoint-22/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:64a7cbea70391b8ccce3b98e2c324c25f2ae8f235754e0ed6e936df11409a9d1
+size 1064

checkpoint-22/sentence_bert_config.json

@@ -0,0 +1,4 @@
+{
+  "max_seq_length": 512,
+  "do_lower_case": true
+}

checkpoint-22/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
+  }
+}

checkpoint-22/tokenizer_config.json

@@ -0,0 +1,58 @@
+{
+  "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,
+  "extra_special_tokens": {},
+  "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]"
+}

checkpoint-22/trainer_state.json

@@ -0,0 +1,300 @@
+{
+  "best_metric": 0.5057041685567575,
+  "best_model_checkpoint": "/content/drive/MyDrive/Kaanun/bge_models_weights/checkpoint-22",
+  "epoch": 11.0,
+  "eval_steps": 500,
+  "global_step": 22,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.0,
+      "eval_dim_128_cosine_accuracy@1": 0.16113744075829384,
+      "eval_dim_128_cosine_accuracy@10": 0.6682464454976303,
+      "eval_dim_128_cosine_accuracy@3": 0.4597156398104265,
+      "eval_dim_128_cosine_accuracy@5": 0.5687203791469194,
+      "eval_dim_128_cosine_map@100": 0.3403695803235615,
+      "eval_dim_128_cosine_mrr@10": 0.3310708643647034,
+      "eval_dim_128_cosine_ndcg@10": 0.4127209358099893,
+      "eval_dim_128_cosine_precision@1": 0.16113744075829384,
+      "eval_dim_128_cosine_precision@10": 0.06682464454976303,
+      "eval_dim_128_cosine_precision@3": 0.1532385466034755,
+      "eval_dim_128_cosine_precision@5": 0.11374407582938388,
+      "eval_dim_128_cosine_recall@1": 0.16113744075829384,
+      "eval_dim_128_cosine_recall@10": 0.6682464454976303,
+      "eval_dim_128_cosine_recall@3": 0.4597156398104265,
+      "eval_dim_128_cosine_recall@5": 0.5687203791469194,
+      "eval_runtime": 4.2031,
+      "eval_samples_per_second": 0.0,
+      "eval_sequential_score": 0.4127209358099893,
+      "eval_steps_per_second": 0.0,
+      "step": 2
+    },
+    {
+      "epoch": 2.0,
+      "eval_dim_128_cosine_accuracy@1": 0.22748815165876776,
+      "eval_dim_128_cosine_accuracy@10": 0.7061611374407583,
+      "eval_dim_128_cosine_accuracy@3": 0.4976303317535545,
+      "eval_dim_128_cosine_accuracy@5": 0.6161137440758294,
+      "eval_dim_128_cosine_map@100": 0.39139098029603353,
+      "eval_dim_128_cosine_mrr@10": 0.38265252388475157,
+      "eval_dim_128_cosine_ndcg@10": 0.46108879234694766,
+      "eval_dim_128_cosine_precision@1": 0.22748815165876776,
+      "eval_dim_128_cosine_precision@10": 0.07061611374407582,
+      "eval_dim_128_cosine_precision@3": 0.16587677725118483,
+      "eval_dim_128_cosine_precision@5": 0.12322274881516586,
+      "eval_dim_128_cosine_recall@1": 0.22748815165876776,
+      "eval_dim_128_cosine_recall@10": 0.7061611374407583,
+      "eval_dim_128_cosine_recall@3": 0.4976303317535545,
+      "eval_dim_128_cosine_recall@5": 0.6161137440758294,
+      "eval_runtime": 3.9064,
+      "eval_samples_per_second": 0.0,
+      "eval_sequential_score": 0.46108879234694766,
+      "eval_steps_per_second": 0.0,
+      "step": 4
+    },
+    {
+      "epoch": 3.0,
+      "eval_dim_128_cosine_accuracy@1": 0.21800947867298578,
+      "eval_dim_128_cosine_accuracy@10": 0.7393364928909952,
+      "eval_dim_128_cosine_accuracy@3": 0.5165876777251185,
+      "eval_dim_128_cosine_accuracy@5": 0.6255924170616114,
+      "eval_dim_128_cosine_map@100": 0.3893562232228884,
+      "eval_dim_128_cosine_mrr@10": 0.38131347325660137,
+      "eval_dim_128_cosine_ndcg@10": 0.46756907555767835,
+      "eval_dim_128_cosine_precision@1": 0.21800947867298578,
+      "eval_dim_128_cosine_precision@10": 0.07393364928909951,
+      "eval_dim_128_cosine_precision@3": 0.17219589257503948,
+      "eval_dim_128_cosine_precision@5": 0.12511848341232226,
+      "eval_dim_128_cosine_recall@1": 0.21800947867298578,
+      "eval_dim_128_cosine_recall@10": 0.7393364928909952,
+      "eval_dim_128_cosine_recall@3": 0.5165876777251185,
+      "eval_dim_128_cosine_recall@5": 0.6255924170616114,
+      "eval_runtime": 3.9779,
+      "eval_samples_per_second": 0.0,
+      "eval_sequential_score": 0.46756907555767835,
+      "eval_steps_per_second": 0.0,
+      "step": 6
+    },
+    {
+      "epoch": 4.0,
+      "eval_dim_128_cosine_accuracy@1": 0.23696682464454977,
+      "eval_dim_128_cosine_accuracy@10": 0.7630331753554502,
+      "eval_dim_128_cosine_accuracy@3": 0.5497630331753555,
+      "eval_dim_128_cosine_accuracy@5": 0.6540284360189573,
+      "eval_dim_128_cosine_map@100": 0.41172122261842037,
+      "eval_dim_128_cosine_mrr@10": 0.40448356277740155,
+      "eval_dim_128_cosine_ndcg@10": 0.49093979707861896,
+      "eval_dim_128_cosine_precision@1": 0.23696682464454977,
+      "eval_dim_128_cosine_precision@10": 0.07630331753554502,
+      "eval_dim_128_cosine_precision@3": 0.18325434439178515,
+      "eval_dim_128_cosine_precision@5": 0.13080568720379146,
+      "eval_dim_128_cosine_recall@1": 0.23696682464454977,
+      "eval_dim_128_cosine_recall@10": 0.7630331753554502,
+      "eval_dim_128_cosine_recall@3": 0.5497630331753555,
+      "eval_dim_128_cosine_recall@5": 0.6540284360189573,
+      "eval_runtime": 4.0653,
+      "eval_samples_per_second": 0.0,
+      "eval_sequential_score": 0.49093979707861896,
+      "eval_steps_per_second": 0.0,
+      "step": 8
+    },
+    {
+      "epoch": 5.0,
+      "grad_norm": 45.40250778198242,
+      "learning_rate": 1.686241637868734e-05,
+      "loss": 1.1743,
+      "step": 10
+    },
+    {
+      "epoch": 5.0,
+      "eval_dim_128_cosine_accuracy@1": 0.20853080568720378,
+      "eval_dim_128_cosine_accuracy@10": 0.7582938388625592,
+      "eval_dim_128_cosine_accuracy@3": 0.5497630331753555,
+      "eval_dim_128_cosine_accuracy@5": 0.6587677725118484,
+      "eval_dim_128_cosine_map@100": 0.39983825778494503,
+      "eval_dim_128_cosine_mrr@10": 0.39171368389377875,
+      "eval_dim_128_cosine_ndcg@10": 0.4808079658208555,
+      "eval_dim_128_cosine_precision@1": 0.20853080568720378,
+      "eval_dim_128_cosine_precision@10": 0.07582938388625592,
+      "eval_dim_128_cosine_precision@3": 0.18325434439178517,
+      "eval_dim_128_cosine_precision@5": 0.13175355450236967,
+      "eval_dim_128_cosine_recall@1": 0.20853080568720378,
+      "eval_dim_128_cosine_recall@10": 0.7582938388625592,
+      "eval_dim_128_cosine_recall@3": 0.5497630331753555,
+      "eval_dim_128_cosine_recall@5": 0.6587677725118484,
+      "eval_runtime": 3.9109,
+      "eval_samples_per_second": 0.0,
+      "eval_sequential_score": 0.4808079658208555,
+      "eval_steps_per_second": 0.0,
+      "step": 10
+    },
+    {
+      "epoch": 6.0,
+      "eval_dim_128_cosine_accuracy@1": 0.2132701421800948,
+      "eval_dim_128_cosine_accuracy@10": 0.7725118483412322,
+      "eval_dim_128_cosine_accuracy@3": 0.5450236966824644,
+      "eval_dim_128_cosine_accuracy@5": 0.6777251184834123,
+      "eval_dim_128_cosine_map@100": 0.40598541933929044,
+      "eval_dim_128_cosine_mrr@10": 0.3981606860753781,
+      "eval_dim_128_cosine_ndcg@10": 0.48914093383392965,
+      "eval_dim_128_cosine_precision@1": 0.2132701421800948,
+      "eval_dim_128_cosine_precision@10": 0.07725118483412322,
+      "eval_dim_128_cosine_precision@3": 0.18167456556082145,
+      "eval_dim_128_cosine_precision@5": 0.13554502369668245,
+      "eval_dim_128_cosine_recall@1": 0.2132701421800948,
+      "eval_dim_128_cosine_recall@10": 0.7725118483412322,
+      "eval_dim_128_cosine_recall@3": 0.5450236966824644,
+      "eval_dim_128_cosine_recall@5": 0.6777251184834123,
+      "eval_runtime": 4.0272,
+      "eval_samples_per_second": 0.0,
+      "eval_sequential_score": 0.48914093383392965,
+      "eval_steps_per_second": 0.0,
+      "step": 12
+    },
+    {
+      "epoch": 7.0,
+      "eval_dim_128_cosine_accuracy@1": 0.23696682464454977,
+      "eval_dim_128_cosine_accuracy@10": 0.7725118483412322,
+      "eval_dim_128_cosine_accuracy@3": 0.5592417061611374,
+      "eval_dim_128_cosine_accuracy@5": 0.6824644549763034,
+      "eval_dim_128_cosine_map@100": 0.4239892051486296,
+      "eval_dim_128_cosine_mrr@10": 0.41595388550364865,
+      "eval_dim_128_cosine_ndcg@10": 0.5026698240348001,
+      "eval_dim_128_cosine_precision@1": 0.23696682464454977,
+      "eval_dim_128_cosine_precision@10": 0.07725118483412322,
+      "eval_dim_128_cosine_precision@3": 0.18641390205371247,
+      "eval_dim_128_cosine_precision@5": 0.13649289099526066,
+      "eval_dim_128_cosine_recall@1": 0.23696682464454977,
+      "eval_dim_128_cosine_recall@10": 0.7725118483412322,
+      "eval_dim_128_cosine_recall@3": 0.5592417061611374,
+      "eval_dim_128_cosine_recall@5": 0.6824644549763034,
+      "eval_runtime": 3.9845,
+      "eval_samples_per_second": 0.0,
+      "eval_sequential_score": 0.5026698240348001,
+      "eval_steps_per_second": 0.0,
+      "step": 14
+    },
+    {
+      "epoch": 8.0,
+      "eval_dim_128_cosine_accuracy@1": 0.22274881516587677,
+      "eval_dim_128_cosine_accuracy@10": 0.7819905213270142,
+      "eval_dim_128_cosine_accuracy@3": 0.5592417061611374,
+      "eval_dim_128_cosine_accuracy@5": 0.6824644549763034,
+      "eval_dim_128_cosine_map@100": 0.41434628700872,
+      "eval_dim_128_cosine_mrr@10": 0.4067573158805388,
+      "eval_dim_128_cosine_ndcg@10": 0.49785247883707107,
+      "eval_dim_128_cosine_precision@1": 0.22274881516587677,
+      "eval_dim_128_cosine_precision@10": 0.07819905213270142,
+      "eval_dim_128_cosine_precision@3": 0.18641390205371247,
+      "eval_dim_128_cosine_precision@5": 0.13649289099526066,
+      "eval_dim_128_cosine_recall@1": 0.22274881516587677,
+      "eval_dim_128_cosine_recall@10": 0.7819905213270142,
+      "eval_dim_128_cosine_recall@3": 0.5592417061611374,
+      "eval_dim_128_cosine_recall@5": 0.6824644549763034,
+      "eval_runtime": 4.0093,
+      "eval_samples_per_second": 0.0,
+      "eval_sequential_score": 0.49785247883707107,
+      "eval_steps_per_second": 0.0,
+      "step": 16
+    },
+    {
+      "epoch": 9.0,
+      "eval_dim_128_cosine_accuracy@1": 0.23696682464454977,
+      "eval_dim_128_cosine_accuracy@10": 0.7819905213270142,
+      "eval_dim_128_cosine_accuracy@3": 0.5545023696682464,
+      "eval_dim_128_cosine_accuracy@5": 0.6872037914691943,
+      "eval_dim_128_cosine_map@100": 0.4238089651869204,
+      "eval_dim_128_cosine_mrr@10": 0.41594072068005733,
+      "eval_dim_128_cosine_ndcg@10": 0.5047472995112773,
+      "eval_dim_128_cosine_precision@1": 0.23696682464454977,
+      "eval_dim_128_cosine_precision@10": 0.07819905213270142,
+      "eval_dim_128_cosine_precision@3": 0.1848341232227488,
+      "eval_dim_128_cosine_precision@5": 0.13744075829383884,
+      "eval_dim_128_cosine_recall@1": 0.23696682464454977,
+      "eval_dim_128_cosine_recall@10": 0.7819905213270142,
+      "eval_dim_128_cosine_recall@3": 0.5545023696682464,
+      "eval_dim_128_cosine_recall@5": 0.6872037914691943,
+      "eval_runtime": 4.1008,
+      "eval_samples_per_second": 0.0,
+      "eval_sequential_score": 0.5047472995112773,
+      "eval_steps_per_second": 0.0,
+      "step": 18
+    },
+    {
+      "epoch": 10.0,
+      "grad_norm": 35.63777160644531,
+      "learning_rate": 6.039202339608432e-06,
+      "loss": 0.5481,
+      "step": 20
+    },
+    {
+      "epoch": 10.0,
+      "eval_dim_128_cosine_accuracy@1": 0.22748815165876776,
+      "eval_dim_128_cosine_accuracy@10": 0.7867298578199052,
+      "eval_dim_128_cosine_accuracy@3": 0.5734597156398105,
+      "eval_dim_128_cosine_accuracy@5": 0.6872037914691943,
+      "eval_dim_128_cosine_map@100": 0.41945253821826306,
+      "eval_dim_128_cosine_mrr@10": 0.4121304445948996,
+      "eval_dim_128_cosine_ndcg@10": 0.5031216432900927,
+      "eval_dim_128_cosine_precision@1": 0.22748815165876776,
+      "eval_dim_128_cosine_precision@10": 0.07867298578199051,
+      "eval_dim_128_cosine_precision@3": 0.19115323854660346,
+      "eval_dim_128_cosine_precision@5": 0.13744075829383884,
+      "eval_dim_128_cosine_recall@1": 0.22748815165876776,
+      "eval_dim_128_cosine_recall@10": 0.7867298578199052,
+      "eval_dim_128_cosine_recall@3": 0.5734597156398105,
+      "eval_dim_128_cosine_recall@5": 0.6872037914691943,
+      "eval_runtime": 3.9667,
+      "eval_samples_per_second": 0.0,
+      "eval_sequential_score": 0.5031216432900927,
+      "eval_steps_per_second": 0.0,
+      "step": 20
+    },
+    {
+      "epoch": 11.0,
+      "eval_dim_128_cosine_accuracy@1": 0.22748815165876776,
+      "eval_dim_128_cosine_accuracy@10": 0.7962085308056872,
+      "eval_dim_128_cosine_accuracy@3": 0.5592417061611374,
+      "eval_dim_128_cosine_accuracy@5": 0.6872037914691943,
+      "eval_dim_128_cosine_map@100": 0.4195949550112758,
+      "eval_dim_128_cosine_mrr@10": 0.4129203340103815,
+      "eval_dim_128_cosine_ndcg@10": 0.5057041685567575,
+      "eval_dim_128_cosine_precision@1": 0.22748815165876776,
+      "eval_dim_128_cosine_precision@10": 0.07962085308056871,
+      "eval_dim_128_cosine_precision@3": 0.18641390205371247,
+      "eval_dim_128_cosine_precision@5": 0.13744075829383884,
+      "eval_dim_128_cosine_recall@1": 0.22748815165876776,
+      "eval_dim_128_cosine_recall@10": 0.7962085308056872,
+      "eval_dim_128_cosine_recall@3": 0.5592417061611374,
+      "eval_dim_128_cosine_recall@5": 0.6872037914691943,
+      "eval_runtime": 3.9949,
+      "eval_samples_per_second": 0.0,
+      "eval_sequential_score": 0.5057041685567575,
+      "eval_steps_per_second": 0.0,
+      "step": 22
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 30,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 30,
+  "save_steps": 500,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 0.0,
+  "train_batch_size": 32,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-22/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:65cb4f201c5ee4acd9ba4182f64fbc2110c157cd08a8321a9d97a0f435fd9b49
+size 5688

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": "4.47.1",
+  "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": "4.47.1",
+    "pytorch": "2.5.1+cu121"
+  },
+  "prompts": {},
+  "default_prompt_name": null,
+  "similarity_fn_name": "cosine"
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0d4db737f56aaea90796b5a8d219de0eee958295a575c611f6b417ad340151da
+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"
+  }
+]

runs/Jan02_09-18-42_1afe4c3f2790/events.out.tfevents.1735809557.1afe4c3f2790.457.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:95cfabd32461143d8d12e6cfab9dd0b0c8cce76ea989a645d70b9e24063d0d75
+size 88

runs/Jan02_09-20-23_1afe4c3f2790/events.out.tfevents.1735809626.1afe4c3f2790.1755.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:827c2b964e706b816ded4b47a59995e51aa478b13f09784597eecb941fcb9d8f
+size 88

runs/Jan02_09-20-23_1afe4c3f2790/events.out.tfevents.1735809855.1afe4c3f2790.1755.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cbc824104ec977a47d56b27b65902f497f68be305a9d0108f5b6a5bb136af304
+size 6151

runs/Jan02_09-25-33_1afe4c3f2790/events.out.tfevents.1735809939.1afe4c3f2790.1755.2

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b23f65ca656bdfcfd50c5c2f151d4976998373459907d692851025bd9bf92c03
+size 88

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 +1,58 @@
+{
+  "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,
+  "extra_special_tokens": {},
+  "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]"
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9496f9b248af5ef52e94cb16dc40df89fabece2b037adeefc18c12b1e961e451
+size 5688